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

Pull arm64 updates from Catalin Marinas:

 - arm64 support for syscall emulation via PTRACE_SYSEMU{,_SINGLESTEP}

 - Wire up VM_FLUSH_RESET_PERMS for arm64, allowing the core code to
   manage the permissions of executable vmalloc regions more strictly

 - Slight performance improvement by keeping softirqs enabled while
   touching the FPSIMD/SVE state (kernel_neon_begin/end)

 - Expose a couple of ARMv8.5 features to user (HWCAP): CondM (new
   XAFLAG and AXFLAG instructions for floating point comparison flags
   manipulation) and FRINT (rounding floating point numbers to integers)

 - Re-instate ARM64_PSEUDO_NMI support which was previously marked as
   BROKEN due to some bugs (now fixed)

 - Improve parking of stopped CPUs and implement an arm64-specific
   panic_smp_self_stop() to avoid warning on not being able to stop
   secondary CPUs during panic

 - perf: enable the ARM Statistical Profiling Extensions (SPE) on ACPI
   platforms

 - perf: DDR performance monitor support for iMX8QXP

 - cache_line_size() can now be set from DT or ACPI/PPTT if provided to
   cope with a system cache info not exposed via the CPUID registers

 - Avoid warning on hardware cache line size greater than
   ARCH_DMA_MINALIGN if the system is fully coherent

 - arm64 do_page_fault() and hugetlb cleanups

 - Refactor set_pte_at() to avoid redundant READ_ONCE(*ptep)

 - Ignore ACPI 5.1 FADTs reported as 5.0 (infer from the
   'arm_boot_flags' introduced in 5.1)

 - CONFIG_RANDOMIZE_BASE now enabled in defconfig

 - Allow the selection of ARM64_MODULE_PLTS, currently only done via
   RANDOMIZE_BASE (and an erratum workaround), allowing modules to spill
   over into the vmalloc area

 - Make ZONE_DMA32 configurable

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (54 commits)
  perf: arm_spe: Enable ACPI/Platform automatic module loading
  arm_pmu: acpi: spe: Add initial MADT/SPE probing
  ACPI/PPTT: Add function to return ACPI 6.3 Identical tokens
  ACPI/PPTT: Modify node flag detection to find last IDENTICAL
  x86/entry: Simplify _TIF_SYSCALL_EMU handling
  arm64: rename dump_instr as dump_kernel_instr
  arm64/mm: Drop [PTE|PMD]_TYPE_FAULT
  arm64: Implement panic_smp_self_stop()
  arm64: Improve parking of stopped CPUs
  arm64: Expose FRINT capabilities to userspace
  arm64: Expose ARMv8.5 CondM capability to userspace
  arm64: defconfig: enable CONFIG_RANDOMIZE_BASE
  arm64: ARM64_MODULES_PLTS must depend on MODULES
  arm64: bpf: do not allocate executable memory
  arm64/kprobes: set VM_FLUSH_RESET_PERMS on kprobe instruction pages
  arm64/mm: wire up CONFIG_ARCH_HAS_SET_DIRECT_MAP
  arm64: module: create module allocations without exec permissions
  arm64: Allow user selection of ARM64_MODULE_PLTS
  acpi/arm64: ignore 5.1 FADTs that are reported as 5.0
  arm64: Allow selecting Pseudo-NMI again
  ...

6 files changed, 92 insertions, 60 deletions

diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 5992eb9a9a08..1d17dbeafe76 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -80,10 +80,6 @@ static int __swiotlb_mmap_pfn(struct vm_area_struct *vma,
 
 static int __init arm64_dma_init(void)
 {
-	WARN_TAINT(ARCH_DMA_MINALIGN < cache_line_size(),
-		   TAINT_CPU_OUT_OF_SPEC,
-		   "ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)",
-		   ARCH_DMA_MINALIGN, cache_line_size());
 	return dma_atomic_pool_init(GFP_DMA32, __pgprot(PROT_NORMAL_NC));
 }
 arch_initcall(arm64_dma_init);
@@ -461,6 +457,14 @@ static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			const struct iommu_ops *iommu, bool coherent)
 {
+	int cls = cache_line_size_of_cpu();
+
+	WARN_TAINT(!coherent && cls > ARCH_DMA_MINALIGN,
+		   TAINT_CPU_OUT_OF_SPEC,
+		   "%s %s: ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)",
+		   dev_driver_string(dev), dev_name(dev),
+		   ARCH_DMA_MINALIGN, cls);
+
 	dev->dma_coherent = coherent;
 	__iommu_setup_dma_ops(dev, dma_base, size, iommu);
 
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 2d115016feb4..c8c61b1eb479 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -384,40 +384,31 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
 #define VM_FAULT_BADACCESS	0x020000
 
 static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
-			   unsigned int mm_flags, unsigned long vm_flags,
-			   struct task_struct *tsk)
+			   unsigned int mm_flags, unsigned long vm_flags)
 {
-	struct vm_area_struct *vma;
-	vm_fault_t fault;
+	struct vm_area_struct *vma = find_vma(mm, addr);
 
-	vma = find_vma(mm, addr);
-	fault = VM_FAULT_BADMAP;
 	if (unlikely(!vma))
-		goto out;
-	if (unlikely(vma->vm_start > addr))
-		goto check_stack;
+		return VM_FAULT_BADMAP;
 
 	/*
 	 * Ok, we have a good vm_area for this memory access, so we can handle
 	 * it.
 	 */
-good_area:
+	if (unlikely(vma->vm_start > addr)) {
+		if (!(vma->vm_flags & VM_GROWSDOWN))
+			return VM_FAULT_BADMAP;
+		if (expand_stack(vma, addr))
+			return VM_FAULT_BADMAP;
+	}
+
 	/*
 	 * Check that the permissions on the VMA allow for the fault which
 	 * occurred.
 	 */
-	if (!(vma->vm_flags & vm_flags)) {
-		fault = VM_FAULT_BADACCESS;
-		goto out;
-	}
-
+	if (!(vma->vm_flags & vm_flags))
+		return VM_FAULT_BADACCESS;
 	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags);
-
-check_stack:
-	if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
-		goto good_area;
-out:
-	return fault;
 }
 
 static bool is_el0_instruction_abort(unsigned int esr)
@@ -425,12 +416,20 @@ static bool is_el0_instruction_abort(unsigned int esr)
 	return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW;
 }
 
+/*
+ * Note: not valid for EL1 DC IVAC, but we never use that such that it
+ * should fault. EL0 cannot issue DC IVAC (undef).
+ */
+static bool is_write_abort(unsigned int esr)
+{
+	return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM);
+}
+
 static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 				   struct pt_regs *regs)
 {
 	const struct fault_info *inf;
-	struct task_struct *tsk;
-	struct mm_struct *mm;
+	struct mm_struct *mm = current->mm;
 	vm_fault_t fault, major = 0;
 	unsigned long vm_flags = VM_READ | VM_WRITE;
 	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -438,9 +437,6 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	if (notify_page_fault(regs, esr))
 		return 0;
 
-	tsk = current;
-	mm  = tsk->mm;
-
 	/*
 	 * If we're in an interrupt or have no user context, we must not take
 	 * the fault.
@@ -453,7 +449,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 
 	if (is_el0_instruction_abort(esr)) {
 		vm_flags = VM_EXEC;
-	} else if ((esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM)) {
+		mm_flags |= FAULT_FLAG_INSTRUCTION;
+	} else if (is_write_abort(esr)) {
 		vm_flags = VM_WRITE;
 		mm_flags |= FAULT_FLAG_WRITE;
 	}
@@ -492,12 +489,14 @@ retry:
 		 */
 		might_sleep();
 #ifdef CONFIG_DEBUG_VM
-		if (!user_mode(regs) && !search_exception_tables(regs->pc))
+		if (!user_mode(regs) && !search_exception_tables(regs->pc)) {
+			up_read(&mm->mmap_sem);
 			goto no_context;
+		}
 #endif
 	}
 
-	fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);
+	fault = __do_page_fault(mm, addr, mm_flags, vm_flags);
 	major |= fault & VM_FAULT_MAJOR;
 
 	if (fault & VM_FAULT_RETRY) {
@@ -537,11 +536,11 @@ retry:
 		 * that point.
 		 */
 		if (major) {
-			tsk->maj_flt++;
+			current->maj_flt++;
 			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
 				      addr);
 		} else {
-			tsk->min_flt++;
+			current->min_flt++;
 			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
 				      addr);
 		}
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index f475e54fbc43..bbeb6a5a6ba6 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -228,7 +228,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 
 	if (sz == PUD_SIZE) {
 		ptep = (pte_t *)pudp;
-	} else if (sz == (PAGE_SIZE * CONT_PTES)) {
+	} else if (sz == (CONT_PTE_SIZE)) {
 		pmdp = pmd_alloc(mm, pudp, addr);
 
 		WARN_ON(addr & (sz - 1));
@@ -246,7 +246,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 			ptep = huge_pmd_share(mm, addr, pudp);
 		else
 			ptep = (pte_t *)pmd_alloc(mm, pudp, addr);
-	} else if (sz == (PMD_SIZE * CONT_PMDS)) {
+	} else if (sz == (CONT_PMD_SIZE)) {
 		pmdp = pmd_alloc(mm, pudp, addr);
 		WARN_ON(addr & (sz - 1));
 		return (pte_t *)pmdp;
@@ -454,9 +454,9 @@ static int __init hugetlbpage_init(void)
 #ifdef CONFIG_ARM64_4K_PAGES
 	add_huge_page_size(PUD_SIZE);
 #endif
-	add_huge_page_size(PMD_SIZE * CONT_PMDS);
+	add_huge_page_size(CONT_PMD_SIZE);
 	add_huge_page_size(PMD_SIZE);
-	add_huge_page_size(PAGE_SIZE * CONT_PTES);
+	add_huge_page_size(CONT_PTE_SIZE);
 
 	return 0;
 }
@@ -470,9 +470,9 @@ static __init int setup_hugepagesz(char *opt)
 #ifdef CONFIG_ARM64_4K_PAGES
 	case PUD_SIZE:
 #endif
-	case PMD_SIZE * CONT_PMDS:
+	case CONT_PMD_SIZE:
 	case PMD_SIZE:
-	case PAGE_SIZE * CONT_PTES:
+	case CONT_PTE_SIZE:
 		add_huge_page_size(ps);
 		return 1;
 	}
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 749c9b269f08..f3c795278def 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -180,8 +180,9 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
 
-	if (IS_ENABLED(CONFIG_ZONE_DMA32))
-		max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys());
+#ifdef CONFIG_ZONE_DMA32
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys());
+#endif
 	max_zone_pfns[ZONE_NORMAL] = max;
 
 	free_area_init_nodes(max_zone_pfns);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index e5ae8663f230..3645f29bd814 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -765,7 +765,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 
 	return 0;
 }
-#endif	/* CONFIG_ARM64_64K_PAGES */
+#endif	/* !ARM64_SWAPPER_USES_SECTION_MAPS */
 void vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap)
 {
@@ -960,32 +960,28 @@ int __init arch_ioremap_pmd_supported(void)
 
 int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
 {
-	pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT |
-					pgprot_val(mk_sect_prot(prot)));
-	pud_t new_pud = pfn_pud(__phys_to_pfn(phys), sect_prot);
+	pud_t new_pud = pfn_pud(__phys_to_pfn(phys), mk_pud_sect_prot(prot));
 
 	/* Only allow permission changes for now */
 	if (!pgattr_change_is_safe(READ_ONCE(pud_val(*pudp)),
 				   pud_val(new_pud)))
 		return 0;
 
-	BUG_ON(phys & ~PUD_MASK);
+	VM_BUG_ON(phys & ~PUD_MASK);
 	set_pud(pudp, new_pud);
 	return 1;
 }
 
 int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot)
 {
-	pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT |
-					pgprot_val(mk_sect_prot(prot)));
-	pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), sect_prot);
+	pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), mk_pmd_sect_prot(prot));
 
 	/* Only allow permission changes for now */
 	if (!pgattr_change_is_safe(READ_ONCE(pmd_val(*pmdp)),
 				   pmd_val(new_pmd)))
 		return 0;
 
-	BUG_ON(phys & ~PMD_MASK);
+	VM_BUG_ON(phys & ~PMD_MASK);
 	set_pmd(pmdp, new_pmd);
 	return 1;
 }
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 47b057bfa803..fcdcf6cd7677 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -151,17 +151,48 @@ int set_memory_valid(unsigned long addr, int numpages, int enable)
 					__pgprot(PTE_VALID));
 }
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
+int set_direct_map_invalid_noflush(struct page *page)
+{
+	struct page_change_data data = {
+		.set_mask = __pgprot(0),
+		.clear_mask = __pgprot(PTE_VALID),
+	};
+
+	if (!rodata_full)
+		return 0;
+
+	return apply_to_page_range(&init_mm,
+				   (unsigned long)page_address(page),
+				   PAGE_SIZE, change_page_range, &data);
+}
+
+int set_direct_map_default_noflush(struct page *page)
+{
+	struct page_change_data data = {
+		.set_mask = __pgprot(PTE_VALID | PTE_WRITE),
+		.clear_mask = __pgprot(PTE_RDONLY),
+	};
+
+	if (!rodata_full)
+		return 0;
+
+	return apply_to_page_range(&init_mm,
+				   (unsigned long)page_address(page),
+				   PAGE_SIZE, change_page_range, &data);
+}
+
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
+	if (!debug_pagealloc_enabled() && !rodata_full)
+		return;
+
 	set_memory_valid((unsigned long)page_address(page), numpages, enable);
 }
-#ifdef CONFIG_HIBERNATION
+
 /*
- * When built with CONFIG_DEBUG_PAGEALLOC and CONFIG_HIBERNATION, this function
- * is used to determine if a linear map page has been marked as not-valid by
- * CONFIG_DEBUG_PAGEALLOC. Walk the page table and check the PTE_VALID bit.
- * This is based on kern_addr_valid(), which almost does what we need.
+ * This function is used to determine if a linear map page has been marked as
+ * not-valid. Walk the page table and check the PTE_VALID bit. This is based
+ * on kern_addr_valid(), which almost does what we need.
  *
  * Because this is only called on the kernel linear map,  p?d_sect() implies
  * p?d_present(). When debug_pagealloc is enabled, sections mappings are
@@ -175,6 +206,9 @@ bool kernel_page_present(struct page *page)
 	pte_t *ptep;
 	unsigned long addr = (unsigned long)page_address(page);
 
+	if (!debug_pagealloc_enabled() && !rodata_full)
+		return true;
+
 	pgdp = pgd_offset_k(addr);
 	if (pgd_none(READ_ONCE(*pgdp)))
 		return false;
@@ -196,5 +230,3 @@ bool kernel_page_present(struct page *page)
 	ptep = pte_offset_kernel(pmdp, addr);
 	return pte_valid(READ_ONCE(*ptep));
 }
-#endif /* CONFIG_HIBERNATION */
-#endif /* CONFIG_DEBUG_PAGEALLOC */