Merge tag 'loongarch-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson

Pull LoongArch updates from Huacai Chen:

 - Fix objtool about do_syscall() and Clang

 - Enable generic CPU vulnerabilites support

 - Enable ACPI BGRT handling

 - Rework CPU feature probe from CPUCFG/IOCSR

 - Add ARCH_HAS_SET_MEMORY support

 - Add ARCH_HAS_SET_DIRECT_MAP support

 - Improve hardware page table walker

 - Simplify _percpu_read() and _percpu_write()

 - Add advanced extended IRQ model documentions

 - Some bug fixes and other small changes

* tag 'loongarch-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson:
  Docs/LoongArch: Add advanced extended IRQ model description
  LoongArch: Remove posix_types.h include from sigcontext.h
  LoongArch: Fix memleak in pci_acpi_scan_root()
  LoongArch: Simplify _percpu_read() and _percpu_write()
  LoongArch: Improve hardware page table walker
  LoongArch: Add ARCH_HAS_SET_DIRECT_MAP support
  LoongArch: Add ARCH_HAS_SET_MEMORY support
  LoongArch: Rework CPU feature probe from CPUCFG/IOCSR
  LoongArch: Enable ACPI BGRT handling
  LoongArch: Enable generic CPU vulnerabilites support
  LoongArch: Remove STACK_FRAME_NON_STANDARD(do_syscall)
  LoongArch: Set AS_HAS_THIN_ADD_SUB as y if AS_IS_LLVM
  LoongArch: Enable objtool for Clang
  objtool: Handle frame pointer related instructions

8 files changed, 118 insertions, 129 deletions

diff --git a/arch/loongarch/include/asm/atomic.h b/arch/loongarch/include/asm/atomic.h
index 99af8b3160a8..c86f0ab922ec 100644
--- a/arch/loongarch/include/asm/atomic.h
+++ b/arch/loongarch/include/asm/atomic.h
@@ -15,6 +15,7 @@
 #define __LL		"ll.w	"
 #define __SC		"sc.w	"
 #define __AMADD		"amadd.w	"
+#define __AMOR		"amor.w		"
 #define __AMAND_DB	"amand_db.w	"
 #define __AMOR_DB	"amor_db.w	"
 #define __AMXOR_DB	"amxor_db.w	"
@@ -22,6 +23,7 @@
 #define __LL		"ll.d	"
 #define __SC		"sc.d	"
 #define __AMADD		"amadd.d	"
+#define __AMOR		"amor.d		"
 #define __AMAND_DB	"amand_db.d	"
 #define __AMOR_DB	"amor_db.d	"
 #define __AMXOR_DB	"amxor_db.d	"
diff --git a/arch/loongarch/include/asm/cpu-features.h b/arch/loongarch/include/asm/cpu-features.h
index 16a716f88a5c..fc83bb32f9f0 100644
--- a/arch/loongarch/include/asm/cpu-features.h
+++ b/arch/loongarch/include/asm/cpu-features.h
@@ -51,6 +51,7 @@
 #define cpu_has_lbt_mips	cpu_opt(LOONGARCH_CPU_LBT_MIPS)
 #define cpu_has_lbt		(cpu_has_lbt_x86|cpu_has_lbt_arm|cpu_has_lbt_mips)
 #define cpu_has_csr		cpu_opt(LOONGARCH_CPU_CSR)
+#define cpu_has_iocsr		cpu_opt(LOONGARCH_CPU_IOCSR)
 #define cpu_has_tlb		cpu_opt(LOONGARCH_CPU_TLB)
 #define cpu_has_watch		cpu_opt(LOONGARCH_CPU_WATCH)
 #define cpu_has_vint		cpu_opt(LOONGARCH_CPU_VINT)
@@ -65,6 +66,7 @@
 #define cpu_has_guestid		cpu_opt(LOONGARCH_CPU_GUESTID)
 #define cpu_has_hypervisor	cpu_opt(LOONGARCH_CPU_HYPERVISOR)
 #define cpu_has_ptw		cpu_opt(LOONGARCH_CPU_PTW)
+#define cpu_has_lspw		cpu_opt(LOONGARCH_CPU_LSPW)
 #define cpu_has_avecint		cpu_opt(LOONGARCH_CPU_AVECINT)
 
 #endif /* __ASM_CPU_FEATURES_H */
diff --git a/arch/loongarch/include/asm/cpu.h b/arch/loongarch/include/asm/cpu.h
index 843f9c4ec980..98cf4d7b4b0a 100644
--- a/arch/loongarch/include/asm/cpu.h
+++ b/arch/loongarch/include/asm/cpu.h
@@ -87,19 +87,21 @@ enum cpu_type_enum {
 #define CPU_FEATURE_LBT_MIPS		12	/* CPU has MIPS Binary Translation */
 #define CPU_FEATURE_TLB			13	/* CPU has TLB */
 #define CPU_FEATURE_CSR			14	/* CPU has CSR */
-#define CPU_FEATURE_WATCH		15	/* CPU has watchpoint registers */
-#define CPU_FEATURE_VINT		16	/* CPU has vectored interrupts */
-#define CPU_FEATURE_CSRIPI		17	/* CPU has CSR-IPI */
-#define CPU_FEATURE_EXTIOI		18	/* CPU has EXT-IOI */
-#define CPU_FEATURE_PREFETCH		19	/* CPU has prefetch instructions */
-#define CPU_FEATURE_PMP			20	/* CPU has perfermance counter */
-#define CPU_FEATURE_SCALEFREQ		21	/* CPU supports cpufreq scaling */
-#define CPU_FEATURE_FLATMODE		22	/* CPU has flat mode */
-#define CPU_FEATURE_EIODECODE		23	/* CPU has EXTIOI interrupt pin decode mode */
-#define CPU_FEATURE_GUESTID		24	/* CPU has GuestID feature */
-#define CPU_FEATURE_HYPERVISOR		25	/* CPU has hypervisor (running in VM) */
-#define CPU_FEATURE_PTW			26	/* CPU has hardware page table walker */
-#define CPU_FEATURE_AVECINT		27	/* CPU has avec interrupt */
+#define CPU_FEATURE_IOCSR		15	/* CPU has IOCSR */
+#define CPU_FEATURE_WATCH		16	/* CPU has watchpoint registers */
+#define CPU_FEATURE_VINT		17	/* CPU has vectored interrupts */
+#define CPU_FEATURE_CSRIPI		18	/* CPU has CSR-IPI */
+#define CPU_FEATURE_EXTIOI		19	/* CPU has EXT-IOI */
+#define CPU_FEATURE_PREFETCH		20	/* CPU has prefetch instructions */
+#define CPU_FEATURE_PMP			21	/* CPU has perfermance counter */
+#define CPU_FEATURE_SCALEFREQ		22	/* CPU supports cpufreq scaling */
+#define CPU_FEATURE_FLATMODE		23	/* CPU has flat mode */
+#define CPU_FEATURE_EIODECODE		24	/* CPU has EXTIOI interrupt pin decode mode */
+#define CPU_FEATURE_GUESTID		25	/* CPU has GuestID feature */
+#define CPU_FEATURE_HYPERVISOR		26	/* CPU has hypervisor (running in VM) */
+#define CPU_FEATURE_PTW			27	/* CPU has hardware page table walker */
+#define CPU_FEATURE_LSPW		28	/* CPU has LSPW (lddir/ldpte instructions) */
+#define CPU_FEATURE_AVECINT		29	/* CPU has AVEC interrupt */
 
 #define LOONGARCH_CPU_CPUCFG		BIT_ULL(CPU_FEATURE_CPUCFG)
 #define LOONGARCH_CPU_LAM		BIT_ULL(CPU_FEATURE_LAM)
@@ -115,6 +117,7 @@ enum cpu_type_enum {
 #define LOONGARCH_CPU_LBT_ARM		BIT_ULL(CPU_FEATURE_LBT_ARM)
 #define LOONGARCH_CPU_LBT_MIPS		BIT_ULL(CPU_FEATURE_LBT_MIPS)
 #define LOONGARCH_CPU_TLB		BIT_ULL(CPU_FEATURE_TLB)
+#define LOONGARCH_CPU_IOCSR		BIT_ULL(CPU_FEATURE_IOCSR)
 #define LOONGARCH_CPU_CSR		BIT_ULL(CPU_FEATURE_CSR)
 #define LOONGARCH_CPU_WATCH		BIT_ULL(CPU_FEATURE_WATCH)
 #define LOONGARCH_CPU_VINT		BIT_ULL(CPU_FEATURE_VINT)
@@ -128,6 +131,7 @@ enum cpu_type_enum {
 #define LOONGARCH_CPU_GUESTID		BIT_ULL(CPU_FEATURE_GUESTID)
 #define LOONGARCH_CPU_HYPERVISOR	BIT_ULL(CPU_FEATURE_HYPERVISOR)
 #define LOONGARCH_CPU_PTW		BIT_ULL(CPU_FEATURE_PTW)
+#define LOONGARCH_CPU_LSPW		BIT_ULL(CPU_FEATURE_LSPW)
 #define LOONGARCH_CPU_AVECINT		BIT_ULL(CPU_FEATURE_AVECINT)
 
 #endif /* _ASM_CPU_H */
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index 04bf1a7f903a..26542413a5b0 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/arch/loongarch/include/asm/loongarch.h
@@ -62,6 +62,7 @@
 #define LOONGARCH_CPUCFG1		0x1
 #define  CPUCFG1_ISGR32			BIT(0)
 #define  CPUCFG1_ISGR64			BIT(1)
+#define  CPUCFG1_ISA			GENMASK(1, 0)
 #define  CPUCFG1_PAGING			BIT(2)
 #define  CPUCFG1_IOCSR			BIT(3)
 #define  CPUCFG1_PABITS			GENMASK(11, 4)
diff --git a/arch/loongarch/include/asm/mmu_context.h b/arch/loongarch/include/asm/mmu_context.h
index 9f97c3453b9c..304363bd3935 100644
--- a/arch/loongarch/include/asm/mmu_context.h
+++ b/arch/loongarch/include/asm/mmu_context.h
@@ -49,12 +49,12 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 
 /* Normal, classic get_new_mmu_context */
 static inline void
-get_new_mmu_context(struct mm_struct *mm, unsigned long cpu)
+get_new_mmu_context(struct mm_struct *mm, unsigned long cpu, bool *need_flush)
 {
 	u64 asid = asid_cache(cpu);
 
 	if (!((++asid) & cpu_asid_mask(&cpu_data[cpu])))
-		local_flush_tlb_user();	/* start new asid cycle */
+		*need_flush = true;	/* start new asid cycle */
 
 	cpu_context(cpu, mm) = asid_cache(cpu) = asid;
 }
@@ -74,21 +74,34 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	return 0;
 }
 
+static inline void atomic_update_pgd_asid(unsigned long asid, unsigned long pgdl)
+{
+	__asm__ __volatile__(
+	"csrwr %[pgdl_val], %[pgdl_reg] \n\t"
+	"csrwr %[asid_val], %[asid_reg] \n\t"
+	: [asid_val] "+r" (asid), [pgdl_val] "+r" (pgdl)
+	: [asid_reg] "i" (LOONGARCH_CSR_ASID), [pgdl_reg] "i" (LOONGARCH_CSR_PGDL)
+	: "memory"
+	);
+}
+
 static inline void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 				      struct task_struct *tsk)
 {
+	bool need_flush = false;
 	unsigned int cpu = smp_processor_id();
 
 	/* Check if our ASID is of an older version and thus invalid */
 	if (!asid_valid(next, cpu))
-		get_new_mmu_context(next, cpu);
-
-	write_csr_asid(cpu_asid(cpu, next));
+		get_new_mmu_context(next, cpu, &need_flush);
 
 	if (next != &init_mm)
-		csr_write64((unsigned long)next->pgd, LOONGARCH_CSR_PGDL);
+		atomic_update_pgd_asid(cpu_asid(cpu, next), (unsigned long)next->pgd);
 	else
-		csr_write64((unsigned long)invalid_pg_dir, LOONGARCH_CSR_PGDL);
+		atomic_update_pgd_asid(cpu_asid(cpu, next), (unsigned long)invalid_pg_dir);
+
+	if (need_flush)
+		local_flush_tlb_user(); /* Flush tlb after update ASID */
 
 	/*
 	 * Mark current->active_mm as not "active" anymore.
@@ -135,9 +148,15 @@ drop_mmu_context(struct mm_struct *mm, unsigned int cpu)
 	asid = read_csr_asid() & cpu_asid_mask(&current_cpu_data);
 
 	if (asid == cpu_asid(cpu, mm)) {
+		bool need_flush = false;
+
 		if (!current->mm || (current->mm == mm)) {
-			get_new_mmu_context(mm, cpu);
+			get_new_mmu_context(mm, cpu, &need_flush);
+
 			write_csr_asid(cpu_asid(cpu, mm));
+			if (need_flush)
+				local_flush_tlb_user(); /* Flush tlb after update ASID */
+
 			goto out;
 		}
 	}
diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h
index 8f290e5546cf..87be9b14e9da 100644
--- a/arch/loongarch/include/asm/percpu.h
+++ b/arch/loongarch/include/asm/percpu.h
@@ -68,75 +68,6 @@ PERCPU_OP(and, and, &)
 PERCPU_OP(or, or, |)
 #undef PERCPU_OP
 
-static __always_inline unsigned long __percpu_read(void __percpu *ptr, int size)
-{
-	unsigned long ret;
-
-	switch (size) {
-	case 1:
-		__asm__ __volatile__ ("ldx.b %[ret], $r21, %[ptr]	\n"
-		: [ret] "=&r"(ret)
-		: [ptr] "r"(ptr)
-		: "memory");
-		break;
-	case 2:
-		__asm__ __volatile__ ("ldx.h %[ret], $r21, %[ptr]	\n"
-		: [ret] "=&r"(ret)
-		: [ptr] "r"(ptr)
-		: "memory");
-		break;
-	case 4:
-		__asm__ __volatile__ ("ldx.w %[ret], $r21, %[ptr]	\n"
-		: [ret] "=&r"(ret)
-		: [ptr] "r"(ptr)
-		: "memory");
-		break;
-	case 8:
-		__asm__ __volatile__ ("ldx.d %[ret], $r21, %[ptr]	\n"
-		: [ret] "=&r"(ret)
-		: [ptr] "r"(ptr)
-		: "memory");
-		break;
-	default:
-		ret = 0;
-		BUILD_BUG();
-	}
-
-	return ret;
-}
-
-static __always_inline void __percpu_write(void __percpu *ptr, unsigned long val, int size)
-{
-	switch (size) {
-	case 1:
-		__asm__ __volatile__("stx.b %[val], $r21, %[ptr]	\n"
-		:
-		: [val] "r" (val), [ptr] "r" (ptr)
-		: "memory");
-		break;
-	case 2:
-		__asm__ __volatile__("stx.h %[val], $r21, %[ptr]	\n"
-		:
-		: [val] "r" (val), [ptr] "r" (ptr)
-		: "memory");
-		break;
-	case 4:
-		__asm__ __volatile__("stx.w %[val], $r21, %[ptr]	\n"
-		:
-		: [val] "r" (val), [ptr] "r" (ptr)
-		: "memory");
-		break;
-	case 8:
-		__asm__ __volatile__("stx.d %[val], $r21, %[ptr]	\n"
-		:
-		: [val] "r" (val), [ptr] "r" (ptr)
-		: "memory");
-		break;
-	default:
-		BUILD_BUG();
-	}
-}
-
 static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, int size)
 {
 	switch (size) {
@@ -157,6 +88,33 @@ static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 	return 0;
 }
 
+#define __pcpu_op_1(op)		op ".b "
+#define __pcpu_op_2(op)		op ".h "
+#define __pcpu_op_4(op)		op ".w "
+#define __pcpu_op_8(op)		op ".d "
+
+#define _percpu_read(size, _pcp)					\
+({									\
+	typeof(_pcp) __pcp_ret;						\
+									\
+	__asm__ __volatile__(						\
+		__pcpu_op_##size("ldx") "%[ret], $r21, %[ptr]	\n"	\
+		: [ret] "=&r"(__pcp_ret)				\
+		: [ptr] "r"(&(_pcp))					\
+		: "memory");						\
+									\
+	__pcp_ret;							\
+})
+
+#define _percpu_write(size, _pcp, _val)					\
+do {									\
+	__asm__ __volatile__(						\
+		__pcpu_op_##size("stx") "%[val], $r21, %[ptr]	\n"	\
+		:							\
+		: [val] "r"(_val), [ptr] "r"(&(_pcp))			\
+		: "memory");						\
+} while (0)
+
 /* this_cpu_cmpxchg */
 #define _protect_cmpxchg_local(pcp, o, n)			\
 ({								\
@@ -167,18 +125,6 @@ static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 	__ret;							\
 })
 
-#define _percpu_read(pcp)						\
-({									\
-	typeof(pcp) __retval;						\
-	__retval = (typeof(pcp))__percpu_read(&(pcp), sizeof(pcp));	\
-	__retval;							\
-})
-
-#define _percpu_write(pcp, val)						\
-do {									\
-	__percpu_write(&(pcp), (unsigned long)(val), sizeof(pcp));	\
-} while (0)								\
-
 #define _pcp_protect(operation, pcp, val)			\
 ({								\
 	typeof(pcp) __retval;					\
@@ -215,15 +161,15 @@ do {									\
 #define this_cpu_or_4(pcp, val) _percpu_or(pcp, val)
 #define this_cpu_or_8(pcp, val) _percpu_or(pcp, val)
 
-#define this_cpu_read_1(pcp) _percpu_read(pcp)
-#define this_cpu_read_2(pcp) _percpu_read(pcp)
-#define this_cpu_read_4(pcp) _percpu_read(pcp)
-#define this_cpu_read_8(pcp) _percpu_read(pcp)
+#define this_cpu_read_1(pcp) _percpu_read(1, pcp)
+#define this_cpu_read_2(pcp) _percpu_read(2, pcp)
+#define this_cpu_read_4(pcp) _percpu_read(4, pcp)
+#define this_cpu_read_8(pcp) _percpu_read(8, pcp)
 
-#define this_cpu_write_1(pcp, val) _percpu_write(pcp, val)
-#define this_cpu_write_2(pcp, val) _percpu_write(pcp, val)
-#define this_cpu_write_4(pcp, val) _percpu_write(pcp, val)
-#define this_cpu_write_8(pcp, val) _percpu_write(pcp, val)
+#define this_cpu_write_1(pcp, val) _percpu_write(1, pcp, val)
+#define this_cpu_write_2(pcp, val) _percpu_write(2, pcp, val)
+#define this_cpu_write_4(pcp, val) _percpu_write(4, pcp, val)
+#define this_cpu_write_8(pcp, val) _percpu_write(8, pcp, val)
 
 #define this_cpu_xchg_1(pcp, val) _percpu_xchg(pcp, val)
 #define this_cpu_xchg_2(pcp, val) _percpu_xchg(pcp, val)
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 85431f20a14d..9965f52ef65b 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -331,29 +331,23 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 		 * Make sure the buddy is global too (if it's !none,
 		 * it better already be global)
 		 */
+		if (pte_none(ptep_get(buddy))) {
 #ifdef CONFIG_SMP
-		/*
-		 * For SMP, multiple CPUs can race, so we need to do
-		 * this atomically.
-		 */
-		unsigned long page_global = _PAGE_GLOBAL;
-		unsigned long tmp;
-
-		__asm__ __volatile__ (
-		"1:"	__LL	"%[tmp], %[buddy]		\n"
-		"	bnez	%[tmp], 2f			\n"
-		"	 or	%[tmp], %[tmp], %[global]	\n"
-			__SC	"%[tmp], %[buddy]		\n"
-		"	beqz	%[tmp], 1b			\n"
-		"	nop					\n"
-		"2:						\n"
-		__WEAK_LLSC_MB
-		: [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp)
-		: [global] "r" (page_global));
+			/*
+			 * For SMP, multiple CPUs can race, so we need
+			 * to do this atomically.
+			 */
+			__asm__ __volatile__(
+			__AMOR "$zero, %[global], %[buddy] \n"
+			: [buddy] "+ZB" (buddy->pte)
+			: [global] "r" (_PAGE_GLOBAL)
+			: "memory");
+
+			DBAR(0b11000); /* o_wrw = 0b11000 */
 #else /* !CONFIG_SMP */
-		if (pte_none(ptep_get(buddy)))
 			WRITE_ONCE(*buddy, __pte(pte_val(ptep_get(buddy)) | _PAGE_GLOBAL));
 #endif /* CONFIG_SMP */
+		}
 	}
 }
 
diff --git a/arch/loongarch/include/asm/set_memory.h b/arch/loongarch/include/asm/set_memory.h
new file mode 100644
index 000000000000..d70505b6676c
--- /dev/null
+++ b/arch/loongarch/include/asm/set_memory.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2024 Loongson Technology Corporation Limited
+ */
+
+#ifndef _ASM_LOONGARCH_SET_MEMORY_H
+#define _ASM_LOONGARCH_SET_MEMORY_H
+
+/*
+ * Functions to change memory attributes.
+ */
+int set_memory_x(unsigned long addr, int numpages);
+int set_memory_nx(unsigned long addr, int numpages);
+int set_memory_ro(unsigned long addr, int numpages);
+int set_memory_rw(unsigned long addr, int numpages);
+
+bool kernel_page_present(struct page *page);
+int set_direct_map_default_noflush(struct page *page);
+int set_direct_map_invalid_noflush(struct page *page);
+
+#endif /* _ASM_LOONGARCH_SET_MEMORY_H */