Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 fixes from Will Deacon:
 "Here's a sizeable batch of Friday the 13th arm64 fixes for -rc4. What
  could possibly go wrong?

  The obvious reason we have so much here is because of the holiday
  season right after the merge window, but we've also brought back an
  erratum workaround that was previously dropped at the last minute and
  there's an MTE coredumping fix that strays outside of the arch/arm64
  directory.

  Summary:

   - Fix PAGE_TABLE_CHECK failures on hugepage splitting path

   - Fix PSCI encoding of MEM_PROTECT_RANGE function in UAPI header

   - Fix NULL deref when accessing debugfs node if PSCI is not present

   - Fix MTE core dumping when VMA list is being updated concurrently

   - Fix SME signal frame handling when SVE is not implemented by the
     CPU

   - Fix asm constraints for cmpxchg_double() to hazard both words

   - Fix build failure with stack tracer and older versions of Clang

   - Bring back workaround for Cortex-A715 erratum 2645198"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: Fix build with CC=clang, CONFIG_FTRACE=y and CONFIG_STACK_TRACER=y
  arm64/mm: Define dummy pud_user_exec() when using 2-level page-table
  arm64: errata: Workaround possible Cortex-A715 [ESR|FAR]_ELx corruption
  firmware/psci: Don't register with debugfs if PSCI isn't available
  firmware/psci: Fix MEM_PROTECT_RANGE function numbers
  arm64/signal: Always allocate SVE signal frames on SME only systems
  arm64/signal: Always accept SVE signal frames on SME only systems
  arm64/sme: Fix context switch for SME only systems
  arm64: cmpxchg_double*: hazard against entire exchange variable
  arm64/uprobes: change the uprobe_opcode_t typedef to fix the sparse warning
  arm64: mte: Avoid the racy walk of the vma list during core dump
  elfcore: Add a cprm parameter to elf_core_extra_{phdrs,data_size}
  arm64: mte: Fix double-freeing of the temporary tag storage during coredump
  arm64: ptrace: Use ARM64_SME to guard the SME register enumerations
  arm64/mm: add pud_user_exec() check in pud_user_accessible_page()
  arm64/mm: fix incorrect file_map_count for invalid pmd

Author: torvalds

Documentation/arm64/silicon-errata.rst

@@ -120,6 +120,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A710     | #2224489        | ARM64_ERRATUM_2224489       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A715     | #2645198        | ARM64_ERRATUM_2645198       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-X2       | #2119858        | ARM64_ERRATUM_2119858       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-X2       | #2224489        | ARM64_ERRATUM_2224489       |

arch/arm64/Kconfig

@@ -184,8 +184,6 @@ config ARM64
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
-	select HAVE_DYNAMIC_FTRACE_WITH_ARGS \
-		if $(cc-option,-fpatchable-function-entry=2)
 	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
 		if DYNAMIC_FTRACE_WITH_ARGS
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
@@ -972,6 +970,22 @@ config ARM64_ERRATUM_2457168
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_2645198
+	bool "Cortex-A715: 2645198: Workaround possible [ESR|FAR]_ELx corruption"
+	default y
+	help
+	  This option adds the workaround for ARM Cortex-A715 erratum 2645198.
+
+	  If a Cortex-A715 cpu sees a page mapping permissions change from executable
+	  to non-executable, it may corrupt the ESR_ELx and FAR_ELx registers on the
+	  next instruction abort caused by permission fault.
+
+	  Only user-space does executable to non-executable permission transition via
+	  mprotect() system call. Workaround the problem by doing a break-before-make
+	  TLB invalidation, for all changes to executable user space mappings.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y

arch/arm64/include/asm/atomic_ll_sc.h

@@ -315,7 +315,7 @@ __ll_sc__cmpxchg_double##name(unsigned long old1,			\
 	"	cbnz	%w0, 1b\n"					\
 	"	" #mb "\n"						\
 	"2:"								\
-	: "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr)	\
+	: "=&r" (tmp), "=&r" (ret), "+Q" (*(__uint128_t *)ptr)		\
 	: "r" (old1), "r" (old2), "r" (new1), "r" (new2)		\
 	: cl);								\
 									\

arch/arm64/include/asm/atomic_lse.h

@@ -311,7 +311,7 @@ __lse__cmpxchg_double##name(unsigned long old1,				\
 	"	eor	%[old2], %[old2], %[oldval2]\n"			\
 	"	orr	%[old1], %[old1], %[old2]"			\
 	: [old1] "+&r" (x0), [old2] "+&r" (x1),				\
-	  [v] "+Q" (*(unsigned long *)ptr)				\
+	  [v] "+Q" (*(__uint128_t *)ptr)				\
 	: [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4),		\
 	  [oldval1] "r" (oldval1), [oldval2] "r" (oldval2)		\
 	: cl);								\

arch/arm64/include/asm/hugetlb.h

@@ -49,6 +49,15 @@ extern pte_t huge_ptep_get(pte_t *ptep);
 
 void __init arm64_hugetlb_cma_reserve(void);
 
+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep);
+
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 pte_t old_pte, pte_t new_pte);
+
 #include <asm-generic/hugetlb.h>
 
 #endif /* __ASM_HUGETLB_H */

arch/arm64/include/asm/pgtable.h

@@ -681,7 +681,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 #define pud_leaf(pud)		(pud_present(pud) && !pud_table(pud))
 #define pud_valid(pud)		pte_valid(pud_pte(pud))
 #define pud_user(pud)		pte_user(pud_pte(pud))
-
+#define pud_user_exec(pud)	pte_user_exec(pud_pte(pud))
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
@@ -730,6 +730,7 @@ static inline pmd_t *pud_pgtable(pud_t pud)
 #else
 
 #define pud_page_paddr(pud)	({ BUILD_BUG(); 0; })
+#define pud_user_exec(pud)	pud_user(pud) /* Always 0 with folding */
 
 /* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */
 #define pmd_set_fixmap(addr)		NULL
@@ -862,12 +863,12 @@ static inline bool pte_user_accessible_page(pte_t pte)
 
 static inline bool pmd_user_accessible_page(pmd_t pmd)
 {
-	return pmd_leaf(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
+	return pmd_leaf(pmd) && !pmd_present_invalid(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
 }
 
 static inline bool pud_user_accessible_page(pud_t pud)
 {
-	return pud_leaf(pud) && pud_user(pud);
+	return pud_leaf(pud) && (pud_user(pud) || pud_user_exec(pud));
 }
 #endif
 
@@ -1093,6 +1094,15 @@ static inline bool pud_sect_supported(void)
 }
 
 
+#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+#define ptep_modify_prot_start ptep_modify_prot_start
+extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep);
+
+#define ptep_modify_prot_commit ptep_modify_prot_commit
+extern void ptep_modify_prot_commit(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep,
+				    pte_t old_pte, pte_t new_pte);
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_PGTABLE_H */

arch/arm64/include/asm/uprobes.h

@@ -16,7 +16,7 @@
 #define UPROBE_SWBP_INSN_SIZE	AARCH64_INSN_SIZE
 #define UPROBE_XOL_SLOT_BYTES	MAX_UINSN_BYTES
 
-typedef u32 uprobe_opcode_t;
+typedef __le32 uprobe_opcode_t;
 
 struct arch_uprobe_task {
 };

arch/arm64/kernel/cpu_errata.c

@@ -661,6 +661,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_2645198
+	{
+		.desc = "ARM erratum 2645198",
+		.capability = ARM64_WORKAROUND_2645198,
+		ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A715)
+	},
+#endif
 #ifdef CONFIG_ARM64_ERRATUM_2077057
 	{
 		.desc = "ARM erratum 2077057",

arch/arm64/kernel/elfcore.c

@@ -8,28 +8,27 @@
 #include <asm/cpufeature.h>
 #include <asm/mte.h>
 
-#define for_each_mte_vma(vmi, vma)					\
+#define for_each_mte_vma(cprm, i, m)					\
 	if (system_supports_mte())					\
-		for_each_vma(vmi, vma)					\
-			if (vma->vm_flags & VM_MTE)
+		for (i = 0, m = cprm->vma_meta;				\
+		     i < cprm->vma_count;				\
+		     i++, m = cprm->vma_meta + i)			\
+			if (m->flags & VM_MTE)
 
-static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma)
+static unsigned long mte_vma_tag_dump_size(struct core_vma_metadata *m)
 {
-	if (vma->vm_flags & VM_DONTDUMP)
-		return 0;
-
-	return vma_pages(vma) * MTE_PAGE_TAG_STORAGE;
+	return (m->dump_size >> PAGE_SHIFT) * MTE_PAGE_TAG_STORAGE;
 }
 
 /* Derived from dump_user_range(); start/end must be page-aligned */
 static int mte_dump_tag_range(struct coredump_params *cprm,
-			      unsigned long start, unsigned long end)
+			      unsigned long start, unsigned long len)
 {
 	int ret = 1;
 	unsigned long addr;
 	void *tags = NULL;
 
-	for (addr = start; addr < end; addr += PAGE_SIZE) {
+	for (addr = start; addr < start + len; addr += PAGE_SIZE) {
 		struct page *page = get_dump_page(addr);
 
 		/*
@@ -65,7 +64,6 @@ static int mte_dump_tag_range(struct coredump_params *cprm,
 		mte_save_page_tags(page_address(page), tags);
 		put_page(page);
 		if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) {
-			mte_free_tag_storage(tags);
 			ret = 0;
 			break;
 		}
@@ -77,32 +75,32 @@ static int mte_dump_tag_range(struct coredump_params *cprm,
 	return ret;
 }
 
-Elf_Half elf_core_extra_phdrs(void)
+Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm)
 {
-	struct vm_area_struct *vma;
+	int i;
+	struct core_vma_metadata *m;
 	int vma_count = 0;
-	VMA_ITERATOR(vmi, current->mm, 0);
 
-	for_each_mte_vma(vmi, vma)
+	for_each_mte_vma(cprm, i, m)
 		vma_count++;
 
 	return vma_count;
 }
 
 int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
 {
-	struct vm_area_struct *vma;
-	VMA_ITERATOR(vmi, current->mm, 0);
+	int i;
+	struct core_vma_metadata *m;
 
-	for_each_mte_vma(vmi, vma) {
+	for_each_mte_vma(cprm, i, m) {
 		struct elf_phdr phdr;
 
 		phdr.p_type = PT_AARCH64_MEMTAG_MTE;
 		phdr.p_offset = offset;
-		phdr.p_vaddr = vma->vm_start;
+		phdr.p_vaddr = m->start;
 		phdr.p_paddr = 0;
-		phdr.p_filesz = mte_vma_tag_dump_size(vma);
-		phdr.p_memsz = vma->vm_end - vma->vm_start;
+		phdr.p_filesz = mte_vma_tag_dump_size(m);
+		phdr.p_memsz = m->end - m->start;
 		offset += phdr.p_filesz;
 		phdr.p_flags = 0;
 		phdr.p_align = 0;
@@ -114,28 +112,25 @@ int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
 	return 1;
 }
 
-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
 {
-	struct vm_area_struct *vma;
+	int i;
+	struct core_vma_metadata *m;
 	size_t data_size = 0;
-	VMA_ITERATOR(vmi, current->mm, 0);
 
-	for_each_mte_vma(vmi, vma)
-		data_size += mte_vma_tag_dump_size(vma);
+	for_each_mte_vma(cprm, i, m)
+		data_size += mte_vma_tag_dump_size(m);
 
 	return data_size;
 }
 
 int elf_core_write_extra_data(struct coredump_params *cprm)
 {
-	struct vm_area_struct *vma;
-	VMA_ITERATOR(vmi, current->mm, 0);
-
-	for_each_mte_vma(vmi, vma) {
-		if (vma->vm_flags & VM_DONTDUMP)
-			continue;
+	int i;
+	struct core_vma_metadata *m;
 
-		if (!mte_dump_tag_range(cprm, vma->vm_start, vma->vm_end))
+	for_each_mte_vma(cprm, i, m) {
+		if (!mte_dump_tag_range(cprm, m->start, m->dump_size))
 			return 0;
 	}
 

arch/arm64/kernel/fpsimd.c

@@ -385,7 +385,7 @@ static void task_fpsimd_load(void)
 	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!have_cpu_fpsimd_context());
 
-	if (system_supports_sve()) {
+	if (system_supports_sve() || system_supports_sme()) {
 		switch (current->thread.fp_type) {
 		case FP_STATE_FPSIMD:
 			/* Stop tracking SVE for this task until next use. */