Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

14 files changed, 106 insertions, 41 deletions

diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 503a6e2499..0fe2f085c0 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -3,8 +3,6 @@
 # Makefile for the linux ppc-specific parts of the memory manager.
 #
 
-ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
-
 obj-y				:= fault.o mem.o pgtable.o maccess.o pageattr.o \
 				   init_$(BITS).o pgtable_$(BITS).o \
 				   pgtable-frag.o ioremap.o ioremap_$(BITS).o \
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index 100f999871..625fe7d08e 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -184,7 +184,7 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 
 static bool is_module_segment(unsigned long addr)
 {
-	if (!IS_ENABLED(CONFIG_MODULES))
+	if (!IS_ENABLED(CONFIG_EXECMEM))
 		return false;
 	if (addr < ALIGN_DOWN(MODULES_VADDR, SZ_256M))
 		return false;
diff --git a/arch/powerpc/mm/book3s64/Makefile b/arch/powerpc/mm/book3s64/Makefile
index cad2abc173..33af579585 100644
--- a/arch/powerpc/mm/book3s64/Makefile
+++ b/arch/powerpc/mm/book3s64/Makefile
@@ -1,7 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 
-ccflags-y	:= $(NO_MINIMAL_TOC)
-
 obj-y				+= mmu_context.o pgtable.o trace.o
 ifdef CONFIG_PPC_64S_HASH_MMU
 CFLAGS_REMOVE_slb.o = $(CC_FLAGS_FTRACE)
diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c
index c0b58afb9a..ef3ce37f1b 100644
--- a/arch/powerpc/mm/book3s64/slice.c
+++ b/arch/powerpc/mm/book3s64/slice.c
@@ -282,12 +282,10 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
 {
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
 	unsigned long found, next_end;
-	struct vm_unmapped_area_info info;
-
-	info.flags = 0;
-	info.length = len;
-	info.align_mask = PAGE_MASK & ((1ul << pshift) - 1);
-	info.align_offset = 0;
+	struct vm_unmapped_area_info info = {
+		.length = len,
+		.align_mask = PAGE_MASK & ((1ul << pshift) - 1),
+	};
 	/*
 	 * Check till the allow max value for this mmap request
 	 */
@@ -326,13 +324,13 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm,
 {
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
 	unsigned long found, prev;
-	struct vm_unmapped_area_info info;
+	struct vm_unmapped_area_info info = {
+		.flags = VM_UNMAPPED_AREA_TOPDOWN,
+		.length = len,
+		.align_mask = PAGE_MASK & ((1ul << pshift) - 1),
+	};
 	unsigned long min_addr = max(PAGE_SIZE, mmap_min_addr);
 
-	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
-	info.length = len;
-	info.align_mask = PAGE_MASK & ((1ul << pshift) - 1);
-	info.align_offset = 0;
 	/*
 	 * If we are trying to allocate above DEFAULT_MAP_WINDOW
 	 * Add the different to the mmap_base.
diff --git a/arch/powerpc/mm/cacheflush.c b/arch/powerpc/mm/cacheflush.c
index 15189592da..7186516eca 100644
--- a/arch/powerpc/mm/cacheflush.c
+++ b/arch/powerpc/mm/cacheflush.c
@@ -78,7 +78,7 @@ EXPORT_SYMBOL(flush_icache_range);
 
 #ifdef CONFIG_HIGHMEM
 /**
- * flush_dcache_icache_phys() - Flush a page by it's physical address
+ * flush_dcache_icache_phys() - Flush a page by its physical address
  * @physaddr: the physical address of the page
  */
 static void flush_dcache_icache_phys(unsigned long physaddr)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 53335ae21a..2156904524 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -71,23 +71,26 @@ static noinline int bad_area_nosemaphore(struct pt_regs *regs, unsigned long add
 	return __bad_area_nosemaphore(regs, address, SEGV_MAPERR);
 }
 
-static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code)
+static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code,
+		      struct mm_struct *mm, struct vm_area_struct *vma)
 {
-	struct mm_struct *mm = current->mm;
 
 	/*
 	 * Something tried to access memory that isn't in our memory map..
 	 * Fix it, but check if it's kernel or user first..
 	 */
-	mmap_read_unlock(mm);
+	if (mm)
+		mmap_read_unlock(mm);
+	else
+		vma_end_read(vma);
 
 	return __bad_area_nosemaphore(regs, address, si_code);
 }
 
 static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address,
+				    struct mm_struct *mm,
 				    struct vm_area_struct *vma)
 {
-	struct mm_struct *mm = current->mm;
 	int pkey;
 
 	/*
@@ -109,7 +112,10 @@ static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address,
 	 */
 	pkey = vma_pkey(vma);
 
-	mmap_read_unlock(mm);
+	if (mm)
+		mmap_read_unlock(mm);
+	else
+		vma_end_read(vma);
 
 	/*
 	 * If we are in kernel mode, bail out with a SEGV, this will
@@ -124,9 +130,10 @@ static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address,
 	return 0;
 }
 
-static noinline int bad_access(struct pt_regs *regs, unsigned long address)
+static noinline int bad_access(struct pt_regs *regs, unsigned long address,
+			       struct mm_struct *mm, struct vm_area_struct *vma)
 {
-	return __bad_area(regs, address, SEGV_ACCERR);
+	return __bad_area(regs, address, SEGV_ACCERR, mm, vma);
 }
 
 static int do_sigbus(struct pt_regs *regs, unsigned long address,
@@ -479,13 +486,13 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	if (unlikely(access_pkey_error(is_write, is_exec,
 				       (error_code & DSISR_KEYFAULT), vma))) {
-		vma_end_read(vma);
-		goto lock_mmap;
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		return bad_access_pkey(regs, address, NULL, vma);
 	}
 
 	if (unlikely(access_error(is_write, is_exec, vma))) {
-		vma_end_read(vma);
-		goto lock_mmap;
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		return bad_access(regs, address, NULL, vma);
 	}
 
 	fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
@@ -521,10 +528,10 @@ retry:
 
 	if (unlikely(access_pkey_error(is_write, is_exec,
 				       (error_code & DSISR_KEYFAULT), vma)))
-		return bad_access_pkey(regs, address, vma);
+		return bad_access_pkey(regs, address, mm, vma);
 
 	if (unlikely(access_error(is_write, is_exec, vma)))
-		return bad_access(regs, address);
+		return bad_access(regs, address, mm, vma);
 
 	/*
 	 * If for any reason at all we couldn't handle the fault,
diff --git a/arch/powerpc/mm/kasan/init_book3e_64.c b/arch/powerpc/mm/kasan/init_book3e_64.c
index 11519e88dc..43c03b84ff 100644
--- a/arch/powerpc/mm/kasan/init_book3e_64.c
+++ b/arch/powerpc/mm/kasan/init_book3e_64.c
@@ -112,7 +112,7 @@ void __init kasan_init(void)
 	pte_t zero_pte = pfn_pte(virt_to_pfn(kasan_early_shadow_page), PAGE_KERNEL_RO);
 
 	for_each_mem_range(i, &start, &end)
-		kasan_init_phys_region((void *)start, (void *)end);
+		kasan_init_phys_region(phys_to_virt(start), phys_to_virt(end));
 
 	if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
 		kasan_remove_zero_shadow((void *)VMALLOC_START, VMALLOC_SIZE);
diff --git a/arch/powerpc/mm/kasan/init_book3s_64.c b/arch/powerpc/mm/kasan/init_book3s_64.c
index 9300d641cf..3fb5ce4f48 100644
--- a/arch/powerpc/mm/kasan/init_book3s_64.c
+++ b/arch/powerpc/mm/kasan/init_book3s_64.c
@@ -62,7 +62,7 @@ void __init kasan_init(void)
 	}
 
 	for_each_mem_range(i, &start, &end)
-		kasan_init_phys_region((void *)start, (void *)end);
+		kasan_init_phys_region(phys_to_virt(start), phys_to_virt(end));
 
 	for (i = 0; i < PTRS_PER_PTE; i++)
 		__set_pte_at(&init_mm, (unsigned long)kasan_early_shadow_page,
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 3a440004b9..d325217ab2 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -16,6 +16,8 @@
 #include <linux/highmem.h>
 #include <linux/suspend.h>
 #include <linux/dma-direct.h>
+#include <linux/execmem.h>
+#include <linux/vmalloc.h>
 
 #include <asm/swiotlb.h>
 #include <asm/machdep.h>
@@ -30,7 +32,7 @@
 
 #include <mm/mmu_decl.h>
 
-unsigned long long memory_limit;
+unsigned long long memory_limit __initdata;
 
 unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
 EXPORT_SYMBOL(empty_zero_page);
@@ -406,3 +408,66 @@ int devmem_is_allowed(unsigned long pfn)
  * the EHEA driver. Drop this when drivers/net/ethernet/ibm/ehea is removed.
  */
 EXPORT_SYMBOL_GPL(walk_system_ram_range);
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+	pgprot_t kprobes_prot = strict_module_rwx_enabled() ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
+	pgprot_t prot = strict_module_rwx_enabled() ? PAGE_KERNEL : PAGE_KERNEL_EXEC;
+	unsigned long fallback_start = 0, fallback_end = 0;
+	unsigned long start, end;
+
+	/*
+	 * BOOK3S_32 and 8xx define MODULES_VADDR for text allocations and
+	 * allow allocating data in the entire vmalloc space
+	 */
+#ifdef MODULES_VADDR
+	unsigned long limit = (unsigned long)_etext - SZ_32M;
+
+	BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR);
+
+	/* First try within 32M limit from _etext to avoid branch trampolines */
+	if (MODULES_VADDR < PAGE_OFFSET && MODULES_END > limit) {
+		start = limit;
+		fallback_start = MODULES_VADDR;
+		fallback_end = MODULES_END;
+	} else {
+		start = MODULES_VADDR;
+	}
+
+	end = MODULES_END;
+#else
+	start = VMALLOC_START;
+	end = VMALLOC_END;
+#endif
+
+	execmem_info = (struct execmem_info){
+		.ranges = {
+			[EXECMEM_DEFAULT] = {
+				.start	= start,
+				.end	= end,
+				.pgprot	= prot,
+				.alignment = 1,
+				.fallback_start	= fallback_start,
+				.fallback_end	= fallback_end,
+			},
+			[EXECMEM_KPROBES] = {
+				.start	= VMALLOC_START,
+				.end	= VMALLOC_END,
+				.pgprot	= kprobes_prot,
+				.alignment = 1,
+			},
+			[EXECMEM_MODULE_DATA] = {
+				.start	= VMALLOC_START,
+				.end	= VMALLOC_END,
+				.pgprot	= PAGE_KERNEL,
+				.alignment = 1,
+			},
+		},
+	};
+
+	return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
index 43d4842bb1..d93433e26d 100644
--- a/arch/powerpc/mm/nohash/8xx.c
+++ b/arch/powerpc/mm/nohash/8xx.c
@@ -94,7 +94,8 @@ static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa,
 		return -EINVAL;
 
 	set_huge_pte_at(&init_mm, va, ptep,
-			pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)), psize);
+			pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)),
+			1UL << mmu_psize_to_shift(psize));
 
 	return 0;
 }
diff --git a/arch/powerpc/mm/nohash/Makefile b/arch/powerpc/mm/nohash/Makefile
index f3894e79d5..b3f0498dd4 100644
--- a/arch/powerpc/mm/nohash/Makefile
+++ b/arch/powerpc/mm/nohash/Makefile
@@ -1,7 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 
-ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
-
 obj-y				+= mmu_context.o tlb.o tlb_low.o kup.o
 obj-$(CONFIG_PPC_BOOK3E_64)  	+= tlb_low_64e.o book3e_pgtable.o
 obj-$(CONFIG_40x)		+= 40x.o
diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c
index cdff129abb..5c8d1bb98b 100644
--- a/arch/powerpc/mm/nohash/kaslr_booke.c
+++ b/arch/powerpc/mm/nohash/kaslr_booke.c
@@ -376,7 +376,7 @@ notrace void __init kaslr_early_init(void *dt_ptr, phys_addr_t size)
 		create_kaslr_tlb_entry(1, tlb_virt, tlb_phys);
 	}
 
-	/* Copy the kernel to it's new location and run */
+	/* Copy the kernel to its new location and run */
 	memcpy((void *)kernstart_virt_addr, (void *)_stext, kernel_sz);
 	flush_icache_range(kernstart_virt_addr, kernstart_virt_addr + kernel_sz);
 
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 9b99113cb5..6621cfc3ba 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -102,7 +102,7 @@ struct page *p4d_page(p4d_t p4d)
 {
 	if (p4d_leaf(p4d)) {
 		if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP))
-			VM_WARN_ON(!p4d_huge(p4d));
+			VM_WARN_ON(!p4d_leaf(p4d));
 		return pte_page(p4d_pte(p4d));
 	}
 	return virt_to_page(p4d_pgtable(p4d));
@@ -113,7 +113,7 @@ struct page *pud_page(pud_t pud)
 {
 	if (pud_leaf(pud)) {
 		if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP))
-			VM_WARN_ON(!pud_huge(pud));
+			VM_WARN_ON(!pud_leaf(pud));
 		return pte_page(pud_pte(pud));
 	}
 	return virt_to_page(pud_pgtable(pud));
@@ -132,7 +132,7 @@ struct page *pmd_page(pmd_t pmd)
 		 * enabled so these checks can't be used.
 		 */
 		if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP))
-			VM_WARN_ON(!(pmd_leaf(pmd) || pmd_huge(pmd)));
+			VM_WARN_ON(!pmd_leaf(pmd));
 		return pte_page(pmd_pte(pmd));
 	}
 	return virt_to_page(pmd_page_vaddr(pmd));
diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
index 9a60158783..a6baa6166d 100644
--- a/arch/powerpc/mm/ptdump/hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -491,7 +491,7 @@ static void walk_vmemmap(struct pg_state *st)
 	 * Traverse the vmemmaped memory and dump pages that are in the hash
 	 * pagetable.
 	 */
-	while (ptr->list) {
+	while (ptr) {
 		hpte_find(st, ptr->virt_addr, mmu_vmemmap_psize);
 		ptr = ptr->list;
 	}