8 files changed, 42 insertions, 84 deletions
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 2b6f50dd5478..5c1023a6d78c 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -928,6 +928,7 @@ config VDSO
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_VDSO_32
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_VDSO_DATA_STORE
 	help
 	  Place in the process address space an ELF shared object
 	  providing fast implementations of gettimeofday and
diff --git a/arch/arm/mm/cache-l2x0-pmu.c b/arch/arm/mm/cache-l2x0-pmu.c
index 993fefdc167a..93ef0502b7ff 100644
--- a/arch/arm/mm/cache-l2x0-pmu.c
+++ b/arch/arm/mm/cache-l2x0-pmu.c
@@ -539,8 +539,7 @@ static __init int l2x0_pmu_init(void)
 	 * at higher frequencies.
 	 */
 	l2x0_pmu_poll_period = ms_to_ktime(1000);
-	hrtimer_init(&l2x0_pmu_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	l2x0_pmu_hrtimer.function = l2x0_pmu_poll;
+	hrtimer_setup(&l2x0_pmu_hrtimer, l2x0_pmu_poll, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
 	cpumask_set_cpu(0, &pmu_cpu);
 	ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_L2X0_ONLINE,
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 2bec87c3327d..39fd5df73317 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -62,7 +62,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,
 }
 
 static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
-		      unsigned long pfn, struct vm_fault *vmf)
+		      unsigned long pfn, bool need_lock)
 {
 	spinlock_t *ptl;
 	pgd_t *pgd;
@@ -99,12 +99,11 @@ again:
 	if (!pte)
 		return 0;
 
-	/*
-	 * If we are using split PTE locks, then we need to take the page
-	 * lock here.  Otherwise we are using shared mm->page_table_lock
-	 * which is already locked, thus cannot take it.
-	 */
-	if (ptl != vmf->ptl) {
+	if (need_lock) {
+		/*
+		 * Use nested version here to indicate that we are already
+		 * holding one similar spinlock.
+		 */
 		spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
 		if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) {
 			pte_unmap_unlock(pte, ptl);
@@ -114,7 +113,7 @@ again:
 
 	ret = do_adjust_pte(vma, address, pfn, pte);
 
-	if (ptl != vmf->ptl)
+	if (need_lock)
 		spin_unlock(ptl);
 	pte_unmap(pte);
 
@@ -123,9 +122,10 @@ again:
 
 static void
 make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
-	      unsigned long addr, pte_t *ptep, unsigned long pfn,
-	      struct vm_fault *vmf)
+	      unsigned long addr, pte_t *ptep, unsigned long pfn)
 {
+	const unsigned long pmd_start_addr = ALIGN_DOWN(addr, PMD_SIZE);
+	const unsigned long pmd_end_addr = pmd_start_addr + PMD_SIZE;
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *mpnt;
 	unsigned long offset;
@@ -142,6 +142,14 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 	flush_dcache_mmap_lock(mapping);
 	vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) {
 		/*
+		 * If we are using split PTE locks, then we need to take the pte
+		 * lock. Otherwise we are using shared mm->page_table_lock which
+		 * is already locked, thus cannot take it.
+		 */
+		bool need_lock = IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS);
+		unsigned long mpnt_addr;
+
+		/*
 		 * If this VMA is not in our MM, we can ignore it.
 		 * Note that we intentionally mask out the VMA
 		 * that we are fixing up.
@@ -151,7 +159,12 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 		if (!(mpnt->vm_flags & VM_MAYSHARE))
 			continue;
 		offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT;
-		aliases += adjust_pte(mpnt, mpnt->vm_start + offset, pfn, vmf);
+		mpnt_addr = mpnt->vm_start + offset;
+
+		/* Avoid deadlocks by not grabbing the same PTE lock again. */
+		if (mpnt_addr >= pmd_start_addr && mpnt_addr < pmd_end_addr)
+			need_lock = false;
+		aliases += adjust_pte(mpnt, mpnt_addr, pfn, need_lock);
 	}
 	flush_dcache_mmap_unlock(mapping);
 	if (aliases)
@@ -194,7 +207,7 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
 		__flush_dcache_folio(mapping, folio);
 	if (mapping) {
 		if (cache_is_vivt())
-			make_coherent(mapping, vma, addr, ptep, pfn, vmf);
+			make_coherent(mapping, vma, addr, ptep, pfn);
 		else if (vma->vm_flags & VM_EXEC)
 			__flush_icache_all();
 	}
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 5345d218899a..54bdca025c9f 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -237,56 +237,17 @@ static inline void poison_init_mem(void *s, size_t count)
 		*p++ = 0xe7fddef0;
 }
 
-static void __init free_highpages(void)
-{
-#ifdef CONFIG_HIGHMEM
-	unsigned long max_low = max_low_pfn;
-	phys_addr_t range_start, range_end;
-	u64 i;
-
-	/* set highmem page free */
-	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
-				&range_start, &range_end, NULL) {
-		unsigned long start = PFN_UP(range_start);
-		unsigned long end = PFN_DOWN(range_end);
-
-		/* Ignore complete lowmem entries */
-		if (end <= max_low)
-			continue;
-
-		/* Truncate partial highmem entries */
-		if (start < max_low)
-			start = max_low;
-
-		for (; start < end; start++)
-			free_highmem_page(pfn_to_page(start));
-	}
-#endif
-}
-
-/*
- * mem_init() marks the free areas in the mem_map and tells us how much
- * memory is free.  This is done after various parts of the system have
- * claimed their memory after the kernel image.
- */
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 #ifdef CONFIG_ARM_LPAE
 	swiotlb_init(max_pfn > arm_dma_pfn_limit, SWIOTLB_VERBOSE);
 #endif
 
-	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
-
-	/* this will put all unused low memory onto the freelists */
-	memblock_free_all();
-
 #ifdef CONFIG_SA1111
 	/* now that our DMA memory is actually so designated, we can free it */
-	free_reserved_area(__va(PHYS_OFFSET), swapper_pg_dir, -1, NULL);
+	memblock_phys_free(PHYS_OFFSET, __pa(swapper_pg_dir) - PHYS_OFFSET);
 #endif
 
-	free_highpages();
-
 	/*
 	 * Check boundaries twice: Some fundamental inconsistencies can
 	 * be detected at build time already.
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 89f1c97f3079..748698e91a4b 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -436,7 +436,7 @@ void __arm_iomem_set_ro(void __iomem *ptr, size_t size)
 	set_memory_ro((unsigned long)ptr, PAGE_ALIGN(size) / PAGE_SIZE);
 }
 
-void *arch_memremap_wb(phys_addr_t phys_addr, size_t size)
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
 {
 	return (__force void *)arch_ioremap_caller(phys_addr, size,
 						   MT_MEMORY_RW,
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index f5b7a16c5803..f02f872ea8a9 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -726,13 +726,8 @@ EXPORT_SYMBOL(phys_mem_access_prot);
 
 static void __init *early_alloc(unsigned long sz)
 {
-	void *ptr = memblock_alloc(sz, sz);
+	return memblock_alloc_or_panic(sz, sz);
 
-	if (!ptr)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, sz, sz);
-
-	return ptr;
 }
 
 static void *__init late_alloc(unsigned long sz)
@@ -1027,10 +1022,7 @@ void __init iotable_init(struct map_desc *io_desc, int nr)
 	if (!nr)
 		return;
 
-	svm = memblock_alloc(sizeof(*svm) * nr, __alignof__(*svm));
-	if (!svm)
-		panic("%s: Failed to allocate %zu bytes align=0x%zx\n",
-		      __func__, sizeof(*svm) * nr, __alignof__(*svm));
+	svm = memblock_alloc_or_panic(sizeof(*svm) * nr, __alignof__(*svm));
 
 	for (md = io_desc; nr; md++, nr--) {
 		create_mapping(md);
@@ -1052,10 +1044,7 @@ void __init vm_reserve_area_early(unsigned long addr, unsigned long size,
 	struct vm_struct *vm;
 	struct static_vm *svm;
 
-	svm = memblock_alloc(sizeof(*svm), __alignof__(*svm));
-	if (!svm)
-		panic("%s: Failed to allocate %zu bytes align=0x%zx\n",
-		      __func__, sizeof(*svm), __alignof__(*svm));
+	svm = memblock_alloc_or_panic(sizeof(*svm), __alignof__(*svm));
 
 	vm = &svm->vm;
 	vm->addr = (void *)addr;
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index c415f3859b20..d638cc87807e 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -162,10 +162,7 @@ void __init paging_init(const struct machine_desc *mdesc)
 	mpu_setup();
 
 	/* allocate the zero page. */
-	zero_page = (void *)memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-	if (!zero_page)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, PAGE_SIZE, PAGE_SIZE);
+	zero_page = (void *)memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 
 	bootmem_init();
 
@@ -251,7 +248,7 @@ void __iomem *pci_remap_cfgspace(resource_size_t res_cookie, size_t size)
 EXPORT_SYMBOL_GPL(pci_remap_cfgspace);
 #endif
 
-void *arch_memremap_wb(phys_addr_t phys_addr, size_t size)
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
 {
 	return (void *)phys_addr;
 }
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index f8e9bc58a84f..4eb81b7ed03a 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -17,11 +17,11 @@
 #include "mm.h"
 
 #ifdef CONFIG_ARM_LPAE
-#define __pgd_alloc()	kmalloc_array(PTRS_PER_PGD, sizeof(pgd_t), GFP_KERNEL)
-#define __pgd_free(pgd)	kfree(pgd)
+#define _pgd_alloc(mm)		kmalloc_array(PTRS_PER_PGD, sizeof(pgd_t), GFP_KERNEL | __GFP_ZERO)
+#define _pgd_free(mm, pgd)	kfree(pgd)
 #else
-#define __pgd_alloc()	(pgd_t *)__get_free_pages(GFP_KERNEL, 2)
-#define __pgd_free(pgd)	free_pages((unsigned long)pgd, 2)
+#define _pgd_alloc(mm)		__pgd_alloc(mm, 2)
+#define _pgd_free(mm, pgd)	__pgd_free(mm, pgd)
 #endif
 
 /*
@@ -35,12 +35,10 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	pmd_t *new_pmd, *init_pmd;
 	pte_t *new_pte, *init_pte;
 
-	new_pgd = __pgd_alloc();
+	new_pgd = _pgd_alloc(mm);
 	if (!new_pgd)
 		goto no_pgd;
 
-	memset(new_pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
-
 	/*
 	 * Copy over the kernel and IO PGD entries
 	 */
@@ -134,7 +132,7 @@ no_pmd:
 no_pud:
 	p4d_free(mm, new_p4d);
 no_p4d:
-	__pgd_free(new_pgd);
+	_pgd_free(mm, new_pgd);
 no_pgd:
 	return NULL;
 }
@@ -207,5 +205,5 @@ no_pgd:
 		p4d_free(mm, p4d);
 	}
 #endif
-	__pgd_free(pgd_base);
+	_pgd_free(mm, pgd_base);
 }