Merge branch 'linux-linaro-lsk-v4.4' into linux-linaro-lsk-v4.4-android

Conflicts:
	arch/arm64/kernel/armv8_deprecated.c
	arch/arm64/kernel/efi.c
	arch/arm64/kernel/entry.S
	arch/arm64/kernel/head.S
	arch/arm64/kernel/hw_breakpoint.c
	arch/arm64/mm/mmu.c
	include/linux/memblock.h
	mm/memblock.c

3 files changed, 260 insertions, 75 deletions

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 678878077996..74ac8a90ba3f 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -29,11 +29,14 @@
 #include <linux/gfp.h>
 #include <linux/memblock.h>
 #include <linux/sort.h>
+#include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 #include <linux/efi.h>
 #include <linux/swiotlb.h>
+#include <linux/kexec.h>
+#include <linux/crash_dump.h>
 
 #include <asm/boot.h>
 #include <asm/fixmap.h>
@@ -75,6 +78,142 @@ static int __init early_initrd(char *p)
 early_param("initrd", early_initrd);
 #endif
 
+#ifdef CONFIG_KEXEC_CORE
+/*
+ * reserve_crashkernel() - reserves memory for crash kernel
+ *
+ * This function reserves memory area given in "crashkernel=" kernel command
+ * line parameter. The memory reserved is used by dump capture kernel when
+ * primary kernel is crashing.
+ */
+static void __init reserve_crashkernel(void)
+{
+	unsigned long long crash_base, crash_size;
+	int ret;
+
+	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
+				&crash_size, &crash_base);
+	/* no crashkernel= or invalid value specified */
+	if (ret || !crash_size)
+		return;
+
+	crash_size = PAGE_ALIGN(crash_size);
+
+	if (crash_base == 0) {
+		/* Current arm64 boot protocol requires 2MB alignment */
+		crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT,
+				crash_size, SZ_2M);
+		if (crash_base == 0) {
+			pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
+				crash_size);
+			return;
+		}
+	} else {
+		/* User specifies base address explicitly. */
+		if (!memblock_is_region_memory(crash_base, crash_size)) {
+			pr_warn("cannot reserve crashkernel: region is not memory\n");
+			return;
+		}
+
+		if (memblock_is_region_reserved(crash_base, crash_size)) {
+			pr_warn("cannot reserve crashkernel: region overlaps reserved memory\n");
+			return;
+		}
+
+		if (!IS_ALIGNED(crash_base, SZ_2M)) {
+			pr_warn("cannot reserve crashkernel: base address is not 2MB aligned\n");
+			return;
+		}
+	}
+	memblock_reserve(crash_base, crash_size);
+
+	pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
+		crash_base, crash_base + crash_size, crash_size >> 20);
+
+	crashk_res.start = crash_base;
+	crashk_res.end = crash_base + crash_size - 1;
+}
+
+static void __init kexec_reserve_crashkres_pages(void)
+{
+#ifdef CONFIG_HIBERNATION
+	phys_addr_t addr;
+	struct page *page;
+
+	if (!crashk_res.end)
+		return;
+
+	/*
+	 * To reduce the size of hibernation image, all the pages are
+	 * marked as Reserved initially.
+	 */
+	for (addr = crashk_res.start; addr < (crashk_res.end + 1);
+			addr += PAGE_SIZE) {
+		page = phys_to_page(addr);
+		SetPageReserved(page);
+	}
+#endif
+}
+#else
+static void __init reserve_crashkernel(void)
+{
+}
+
+static void __init kexec_reserve_crashkres_pages(void)
+{
+}
+#endif /* CONFIG_KEXEC_CORE */
+
+#ifdef CONFIG_CRASH_DUMP
+static int __init early_init_dt_scan_elfcorehdr(unsigned long node,
+		const char *uname, int depth, void *data)
+{
+	const __be32 *reg;
+	int len;
+
+	if (depth != 1 || strcmp(uname, "chosen") != 0)
+		return 0;
+
+	reg = of_get_flat_dt_prop(node, "linux,elfcorehdr", &len);
+	if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells)))
+		return 1;
+
+	elfcorehdr_addr = dt_mem_next_cell(dt_root_addr_cells, &reg);
+	elfcorehdr_size = dt_mem_next_cell(dt_root_size_cells, &reg);
+
+	return 1;
+}
+
+/*
+ * reserve_elfcorehdr() - reserves memory for elf core header
+ *
+ * This function reserves the memory occupied by an elf core header
+ * described in the device tree. This region contains all the
+ * information about primary kernel's core image and is used by a dump
+ * capture kernel to access the system memory on primary kernel.
+ */
+static void __init reserve_elfcorehdr(void)
+{
+	of_scan_flat_dt(early_init_dt_scan_elfcorehdr, NULL);
+
+	if (!elfcorehdr_size)
+		return;
+
+	if (memblock_is_region_reserved(elfcorehdr_addr, elfcorehdr_size)) {
+		pr_warn("elfcorehdr is overlapped\n");
+		return;
+	}
+
+	memblock_reserve(elfcorehdr_addr, elfcorehdr_size);
+
+	pr_info("Reserving %lldKB of memory at 0x%llx for elfcorehdr\n",
+		elfcorehdr_size >> 10, elfcorehdr_addr);
+}
+#else
+static void __init reserve_elfcorehdr(void)
+{
+}
+#endif /* CONFIG_CRASH_DUMP */
 /*
  * Return the maximum physical address for ZONE_DMA (DMA_BIT_MASK(32)). It
  * currently assumes that for memory starting above 4G, 32-bit devices will
@@ -168,10 +307,45 @@ static int __init early_mem(char *p)
 }
 early_param("mem", early_mem);
 
+static int __init early_init_dt_scan_usablemem(unsigned long node,
+		const char *uname, int depth, void *data)
+{
+	struct memblock_region *usablemem = data;
+	const __be32 *reg;
+	int len;
+
+	if (depth != 1 || strcmp(uname, "chosen") != 0)
+		return 0;
+
+	reg = of_get_flat_dt_prop(node, "linux,usable-memory-range", &len);
+	if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells)))
+		return 1;
+
+	usablemem->base = dt_mem_next_cell(dt_root_addr_cells, &reg);
+	usablemem->size = dt_mem_next_cell(dt_root_size_cells, &reg);
+
+	return 1;
+}
+
+static void __init fdt_enforce_memory_region(void)
+{
+	struct memblock_region reg = {
+		.size = 0,
+	};
+
+	of_scan_flat_dt(early_init_dt_scan_usablemem, &reg);
+
+	if (reg.size)
+		memblock_cap_memory_range(reg.base, reg.size);
+}
+
 void __init arm64_memblock_init(void)
 {
 	const s64 linear_region_size = -(s64)PAGE_OFFSET;
 
+	/* Handle linux,usable-memory-range property */
+	fdt_enforce_memory_region();
+
 	/*
 	 * Ensure that the linear region takes up exactly half of the kernel
 	 * virtual address space. This way, we can distinguish a linear address
@@ -248,6 +422,11 @@ void __init arm64_memblock_init(void)
 		arm64_dma_phys_limit = max_zone_dma_phys();
 	else
 		arm64_dma_phys_limit = PHYS_MASK + 1;
+
+	reserve_crashkernel();
+
+	reserve_elfcorehdr();
+
 	dma_contiguous_reserve(arm64_dma_phys_limit);
 
 	memblock_allow_resize();
@@ -361,6 +540,8 @@ void __init mem_init(void)
 	/* this will put all unused low memory onto the freelists */
 	free_all_bootmem();
 
+	kexec_reserve_crashkres_pages();
+
 	mem_init_print_info(NULL);
 
 #define MLK(b, t) b, t, ((t) - (b)) >> 10
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 1cab2703f5a8..2d2b6643a31e 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -21,6 +21,8 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/kexec.h>
 #include <linux/libfdt.h>
 #include <linux/mman.h>
 #include <linux/nodemask.h>
@@ -156,29 +158,10 @@ static void split_pud(pud_t *old_pud, pmd_t *pmd)
 	} while (pmd++, i++, i < PTRS_PER_PMD);
 }
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void))
-{
-
-	/*
-	 * If debug_page_alloc is enabled we must map the linear map
-	 * using pages. However, other mappings created by
-	 * create_mapping_noalloc must use sections in some cases. Allow
-	 * sections to be used in those cases, where no pgtable_alloc
-	 * function is provided.
-	 */
-	return !pgtable_alloc || !debug_pagealloc_enabled();
-}
-#else
-static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void))
-{
-	return true;
-}
-#endif
-
 static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 				  phys_addr_t phys, pgprot_t prot,
-				  phys_addr_t (*pgtable_alloc)(void))
+				  phys_addr_t (*pgtable_alloc)(void),
+				  bool allow_block_mappings)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -209,7 +192,7 @@ static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 		next = pmd_addr_end(addr, end);
 		/* try section mapping first */
 		if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
-		      block_mappings_allowed(pgtable_alloc)) {
+		      (!pgtable_alloc || allow_block_mappings)) {
 			pmd_t old_pmd =*pmd;
 			pmd_set_huge(pmd, phys, prot);
 			/*
@@ -248,7 +231,8 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next,
 
 static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 				  phys_addr_t phys, pgprot_t prot,
-				  phys_addr_t (*pgtable_alloc)(void))
+				  phys_addr_t (*pgtable_alloc)(void),
+				  bool allow_block_mappings)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -269,7 +253,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 		 * For 4K granule only, attempt to put down a 1GB block
 		 */
 		if (use_1G_block(addr, next, phys) &&
-		    block_mappings_allowed(pgtable_alloc)) {
+		      (!pgtable_alloc || allow_block_mappings)) {
 			pud_t old_pud = *pud;
 			pud_set_huge(pud, phys, prot);
 
@@ -290,7 +274,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 			}
 		} else {
 			alloc_init_pmd(pud, addr, next, phys, prot,
-				       pgtable_alloc);
+				       pgtable_alloc, allow_block_mappings);
 		}
 		phys += next - addr;
 	} while (pud++, addr = next, addr != end);
@@ -304,7 +288,8 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
  */
 static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt,
 				    phys_addr_t size, pgprot_t prot,
-				    phys_addr_t (*pgtable_alloc)(void))
+				    phys_addr_t (*pgtable_alloc)(void),
+				    bool allow_block_mappings)
 {
 	unsigned long addr, length, end, next;
 
@@ -322,7 +307,8 @@ static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt,
 	end = addr + length;
 	do {
 		next = pgd_addr_end(addr, end);
-		alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc);
+		alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc,
+			      (!pgtable_alloc || allow_block_mappings));
 		phys += next - addr;
 	} while (pgd++, addr = next, addr != end);
 }
@@ -340,9 +326,11 @@ static phys_addr_t late_pgtable_alloc(void)
 static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 				 unsigned long virt, phys_addr_t size,
 				 pgprot_t prot,
-				 phys_addr_t (*alloc)(void))
+				 phys_addr_t (*alloc)(void),
+				 bool allow_block_mappings)
 {
-	init_pgd(pgd_offset_raw(pgdir, virt), phys, virt, size, prot, alloc);
+	init_pgd(pgd_offset_raw(pgdir, virt), phys, virt, size, prot, alloc,
+		 allow_block_mappings);
 }
 
 /*
@@ -358,16 +346,15 @@ static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
 			&phys, virt);
 		return;
 	}
-	__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot,
-			     NULL);
+	__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, true);
 }
 
 void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 			       unsigned long virt, phys_addr_t size,
-			       pgprot_t prot)
+			       pgprot_t prot, bool allow_block_mappings)
 {
 	__create_pgd_mapping(mm->pgd, phys, virt, size, prot,
-			     late_pgtable_alloc);
+			     late_pgtable_alloc, allow_block_mappings);
 }
 
 static void create_mapping_late(phys_addr_t phys, unsigned long virt,
@@ -380,56 +367,35 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt,
 	}
 
 	__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot,
-			     late_pgtable_alloc);
+			     late_pgtable_alloc, !debug_pagealloc_enabled());
 }
 
-static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end)
+static void __init __map_memblock(pgd_t *pgd, phys_addr_t start,
+				  phys_addr_t end, pgprot_t prot,
+				  bool allow_block_mappings)
+{
+	__create_pgd_mapping(pgd, start, __phys_to_virt(start), end - start,
+			     prot, early_pgtable_alloc, allow_block_mappings);
+}
+
+static void __init map_mem(pgd_t *pgd)
 {
 	unsigned long kernel_start = __pa(_text);
 	unsigned long kernel_end = __pa(__init_begin);
+	struct memblock_region *reg;
 
 	/*
 	 * Take care not to create a writable alias for the
 	 * read-only text and rodata sections of the kernel image.
+	 * So temporarily mark them as NOMAP to skip mappings in
+	 * the following for-loop
 	 */
-
-	/* No overlap with the kernel text/rodata */
-	if (end < kernel_start || start >= kernel_end) {
-		__create_pgd_mapping(pgd, start, __phys_to_virt(start),
-				     end - start, PAGE_KERNEL,
-				     early_pgtable_alloc);
-		return;
-	}
-
-	/*
-	 * This block overlaps the kernel text/rodata mappings.
-	 * Map the portion(s) which don't overlap.
-	 */
-	if (start < kernel_start)
-		__create_pgd_mapping(pgd, start,
-				     __phys_to_virt(start),
-				     kernel_start - start, PAGE_KERNEL,
-				     early_pgtable_alloc);
-	if (kernel_end < end)
-		__create_pgd_mapping(pgd, kernel_end,
-				     __phys_to_virt(kernel_end),
-				     end - kernel_end, PAGE_KERNEL,
-				     early_pgtable_alloc);
-
-	/*
-	 * Map the linear alias of the [_text, __init_begin) interval as
-	 * read-only/non-executable. This makes the contents of the
-	 * region accessible to subsystems such as hibernate, but
-	 * protects it from inadvertent modification or execution.
-	 */
-	__create_pgd_mapping(pgd, kernel_start, __phys_to_virt(kernel_start),
-			     kernel_end - kernel_start, PAGE_KERNEL_RO,
-			     early_pgtable_alloc);
-}
-
-static void __init map_mem(pgd_t *pgd)
-{
-	struct memblock_region *reg;
+	memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
+#ifdef CONFIG_KEXEC_CORE
+	if (crashk_res.end)
+		memblock_mark_nomap(crashk_res.start,
+				    resource_size(&crashk_res));
+#endif
 
 	/* map all the memory banks */
 	for_each_memblock(memory, reg) {
@@ -441,8 +407,33 @@ static void __init map_mem(pgd_t *pgd)
 		if (memblock_is_nomap(reg))
 			continue;
 
-		__map_memblock(pgd, start, end);
+		__map_memblock(pgd, start, end,
+			       PAGE_KERNEL, !debug_pagealloc_enabled());
 	}
+
+	/*
+	 * Map the linear alias of the [_text, __init_begin) interval as
+	 * read-only/non-executable. This makes the contents of the
+	 * region accessible to subsystems such as hibernate, but
+	 * protects it from inadvertent modification or execution.
+	 */
+	__map_memblock(pgd, kernel_start, kernel_end,
+		       PAGE_KERNEL_RO, !debug_pagealloc_enabled());
+	memblock_clear_nomap(kernel_start, kernel_end - kernel_start);
+
+#ifdef CONFIG_KEXEC_CORE
+	/*
+	 * Use page-level mappings here so that we can shrink the region
+	 * in page granularity and put back unused memory to buddy system
+	 * through /sys/kernel/kexec_crash_size interface.
+	 */
+	if (crashk_res.end) {
+		__map_memblock(pgd, crashk_res.start, crashk_res.end + 1,
+			       PAGE_KERNEL, false);
+		memblock_clear_nomap(crashk_res.start,
+				     resource_size(&crashk_res));
+	}
+#endif
 }
 
 void mark_rodata_ro(void)
@@ -481,7 +472,7 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
 	BUG_ON(!PAGE_ALIGNED(size));
 
 	__create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot,
-			     early_pgtable_alloc);
+			     early_pgtable_alloc, !debug_pagealloc_enabled());
 
 	vma->addr	= va_start;
 	vma->phys_addr	= pa_start;
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 8def55e7249b..9ef0b013e6d4 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -125,6 +125,19 @@ int set_memory_x(unsigned long addr, int numpages)
 }
 EXPORT_SYMBOL_GPL(set_memory_x);
 
+
+int set_memory_valid(unsigned long addr, int numpages, int enable)
+{
+	if (enable)
+		return __change_memory_common(addr, PAGE_SIZE * numpages,
+					__pgprot(PTE_VALID),
+					__pgprot(0));
+	else
+		return __change_memory_common(addr, PAGE_SIZE * numpages,
+					__pgprot(0),
+					__pgprot(PTE_VALID));
+}
+
 #ifdef CONFIG_DEBUG_PAGEALLOC
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {