Merge branch 'akpm' (patches from Andrew)

Merge yet more updates from Andrew Morton:

 - various hotfixes

 - kexec_file updates and feature work

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (27 commits)
  kernel/kexec_file.c: move purgatories sha256 to common code
  kernel/kexec_file.c: allow archs to set purgatory load address
  kernel/kexec_file.c: remove mis-use of sh_offset field during purgatory load
  kernel/kexec_file.c: remove unneeded variables in kexec_purgatory_setup_sechdrs
  kernel/kexec_file.c: remove unneeded for-loop in kexec_purgatory_setup_sechdrs
  kernel/kexec_file.c: split up __kexec_load_puragory
  kernel/kexec_file.c: use read-only sections in arch_kexec_apply_relocations*
  kernel/kexec_file.c: search symbols in read-only kexec_purgatory
  kernel/kexec_file.c: make purgatory_info->ehdr const
  kernel/kexec_file.c: remove checks in kexec_purgatory_load
  include/linux/kexec.h: silence compile warnings
  kexec_file, x86: move re-factored code to generic side
  ...

arch/mips/mm/gup.c

@@ -178,6 +178,8 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 /*
  * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
  * back to the regular GUP.
+ * Note a difference with get_user_pages_fast: this always returns the
+ * number of pages pinned, 0 if no pages were pinned.
  */
 int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			  struct page **pages)

arch/powerpc/Kconfig

@@ -552,6 +552,9 @@ config KEXEC_FILE
 	  for kernel and initramfs as opposed to a list of segments as is the
 	  case for the older kexec call.
 
+config ARCH_HAS_KEXEC_PURGATORY
+	def_bool KEXEC_FILE
+
 config RELOCATABLE
 	bool "Build a relocatable kernel"
 	depends on PPC64 || (FLATMEM && (44x || FSL_BOOKE))

arch/powerpc/include/asm/kexec.h

@@ -95,7 +95,7 @@ static inline bool kdump_in_progress(void)
 }
 
 #ifdef CONFIG_KEXEC_FILE
-extern struct kexec_file_ops kexec_elf64_ops;
+extern const struct kexec_file_ops kexec_elf64_ops;
 
 #ifdef CONFIG_IMA_KEXEC
 #define ARCH_HAS_KIMAGE_ARCH

arch/powerpc/kernel/kexec_elf_64.c

@@ -572,7 +572,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 {
 	int ret;
 	unsigned int fdt_size;
-	unsigned long kernel_load_addr, purgatory_load_addr;
+	unsigned long kernel_load_addr;
 	unsigned long initrd_load_addr = 0, fdt_load_addr;
 	void *fdt;
 	const void *slave_code;
@@ -580,6 +580,8 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 	struct elf_info elf_info;
 	struct kexec_buf kbuf = { .image = image, .buf_min = 0,
 				  .buf_max = ppc64_rma_size };
+	struct kexec_buf pbuf = { .image = image, .buf_min = 0,
+				  .buf_max = ppc64_rma_size, .top_down = true };
 
 	ret = build_elf_exec_info(kernel_buf, kernel_len, &ehdr, &elf_info);
 	if (ret)
@@ -591,14 +593,13 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 
 	pr_debug("Loaded the kernel at 0x%lx\n", kernel_load_addr);
 
-	ret = kexec_load_purgatory(image, 0, ppc64_rma_size, true,
-				   &purgatory_load_addr);
+	ret = kexec_load_purgatory(image, &pbuf);
 	if (ret) {
 		pr_err("Loading purgatory failed.\n");
 		goto out;
 	}
 
-	pr_debug("Loaded purgatory at 0x%lx\n", purgatory_load_addr);
+	pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem);
 
 	if (initrd != NULL) {
 		kbuf.buffer = initrd;
@@ -657,7 +658,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 	return ret ? ERR_PTR(ret) : fdt;
 }
 
-struct kexec_file_ops kexec_elf64_ops = {
+const struct kexec_file_ops kexec_elf64_ops = {
 	.probe = elf64_probe,
 	.load = elf64_load,
 };

arch/powerpc/kernel/machine_kexec_file_64.c

@@ -31,52 +31,19 @@
 
 #define SLAVE_CODE_SIZE		256
 
-static struct kexec_file_ops *kexec_file_loaders[] = {
+const struct kexec_file_ops * const kexec_file_loaders[] = {
 	&kexec_elf64_ops,
+	NULL
 };
 
 int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
 				  unsigned long buf_len)
 {
-	int i, ret = -ENOEXEC;
-	struct kexec_file_ops *fops;
-
 	/* We don't support crash kernels yet. */
 	if (image->type == KEXEC_TYPE_CRASH)
 		return -EOPNOTSUPP;
 
-	for (i = 0; i < ARRAY_SIZE(kexec_file_loaders); i++) {
-		fops = kexec_file_loaders[i];
-		if (!fops || !fops->probe)
-			continue;
-
-		ret = fops->probe(buf, buf_len);
-		if (!ret) {
-			image->fops = fops;
-			return ret;
-		}
-	}
-
-	return ret;
-}
-
-void *arch_kexec_kernel_image_load(struct kimage *image)
-{
-	if (!image->fops || !image->fops->load)
-		return ERR_PTR(-ENOEXEC);
-
-	return image->fops->load(image, image->kernel_buf,
-				 image->kernel_buf_len, image->initrd_buf,
-				 image->initrd_buf_len, image->cmdline_buf,
-				 image->cmdline_buf_len);
-}
-
-int arch_kimage_file_post_load_cleanup(struct kimage *image)
-{
-	if (!image->fops || !image->fops->cleanup)
-		return 0;
-
-	return image->fops->cleanup(image->image_loader_data);
+	return kexec_image_probe_default(image, buf, buf_len);
 }
 
 /**

arch/s390/mm/gup.c

@@ -220,6 +220,8 @@ static inline int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr,
 /*
  * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
  * back to the regular GUP.
+ * Note a difference with get_user_pages_fast: this always returns the
+ * number of pages pinned, 0 if no pages were pinned.
  */
 int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			  struct page **pages)

arch/sh/mm/gup.c

@@ -160,6 +160,8 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 /*
  * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
  * back to the regular GUP.
+ * Note a difference with get_user_pages_fast: this always returns the
+ * number of pages pinned, 0 if no pages were pinned.
  */
 int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			  struct page **pages)

arch/sparc/mm/gup.c

@@ -193,6 +193,10 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 	return 1;
 }
 
+/*
+ * Note a difference with get_user_pages_fast: this always returns the
+ * number of pages pinned, 0 if no pages were pinned.
+ */
 int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			  struct page **pages)
 {

arch/x86/Kconfig

@@ -2008,6 +2008,9 @@ config KEXEC_FILE
 	  for kernel and initramfs as opposed to list of segments as
 	  accepted by previous system call.
 
+config ARCH_HAS_KEXEC_PURGATORY
+	def_bool KEXEC_FILE
+
 config KEXEC_VERIFY_SIG
 	bool "Verify kernel signature during kexec_file_load() syscall"
 	depends on KEXEC_FILE

arch/x86/include/asm/kexec-bzimage64.h

@@ -2,6 +2,6 @@
 #ifndef _ASM_KEXEC_BZIMAGE64_H
 #define _ASM_KEXEC_BZIMAGE64_H
 
-extern struct kexec_file_ops kexec_bzImage64_ops;
+extern const struct kexec_file_ops kexec_bzImage64_ops;
 
 #endif  /* _ASM_KEXE_BZIMAGE64_H */

arch/x86/kernel/crash.c

@@ -38,37 +38,6 @@
 #include <asm/virtext.h>
 #include <asm/intel_pt.h>
 
-/* Alignment required for elf header segment */
-#define ELF_CORE_HEADER_ALIGN   4096
-
-/* This primarily represents number of split ranges due to exclusion */
-#define CRASH_MAX_RANGES	16
-
-struct crash_mem_range {
-	u64 start, end;
-};
-
-struct crash_mem {
-	unsigned int nr_ranges;
-	struct crash_mem_range ranges[CRASH_MAX_RANGES];
-};
-
-/* Misc data about ram ranges needed to prepare elf headers */
-struct crash_elf_data {
-	struct kimage *image;
-	/*
-	 * Total number of ram ranges we have after various adjustments for
-	 * crash reserved region, etc.
-	 */
-	unsigned int max_nr_ranges;
-
-	/* Pointer to elf header */
-	void *ehdr;
-	/* Pointer to next phdr */
-	void *bufp;
-	struct crash_mem mem;
-};
-
 /* Used while preparing memory map entries for second kernel */
 struct crash_memmap_data {
 	struct boot_params *params;
@@ -218,124 +187,49 @@ static int get_nr_ram_ranges_callback(struct resource *res, void *arg)
 	return 0;
 }
 
-
 /* Gather all the required information to prepare elf headers for ram regions */
-static void fill_up_crash_elf_data(struct crash_elf_data *ced,
-				   struct kimage *image)
+static struct crash_mem *fill_up_crash_elf_data(void)
 {
 	unsigned int nr_ranges = 0;
-
-	ced->image = image;
+	struct crash_mem *cmem;
 
 	walk_system_ram_res(0, -1, &nr_ranges,
 				get_nr_ram_ranges_callback);
+	if (!nr_ranges)
+		return NULL;
 
-	ced->max_nr_ranges = nr_ranges;
-
-	/* Exclusion of crash region could split memory ranges */
-	ced->max_nr_ranges++;
-
-	/* If crashk_low_res is not 0, another range split possible */
-	if (crashk_low_res.end)
-		ced->max_nr_ranges++;
-}
-
-static int exclude_mem_range(struct crash_mem *mem,
-		unsigned long long mstart, unsigned long long mend)
-{
-	int i, j;
-	unsigned long long start, end;
-	struct crash_mem_range temp_range = {0, 0};
-
-	for (i = 0; i < mem->nr_ranges; i++) {
-		start = mem->ranges[i].start;
-		end = mem->ranges[i].end;
-
-		if (mstart > end || mend < start)
-			continue;
-
-		/* Truncate any area outside of range */
-		if (mstart < start)
-			mstart = start;
-		if (mend > end)
-			mend = end;
-
-		/* Found completely overlapping range */
-		if (mstart == start && mend == end) {
-			mem->ranges[i].start = 0;
-			mem->ranges[i].end = 0;
-			if (i < mem->nr_ranges - 1) {
-				/* Shift rest of the ranges to left */
-				for (j = i; j < mem->nr_ranges - 1; j++) {
-					mem->ranges[j].start =
-						mem->ranges[j+1].start;
-					mem->ranges[j].end =
-							mem->ranges[j+1].end;
-				}
-			}
-			mem->nr_ranges--;
-			return 0;
-		}
-
-		if (mstart > start && mend < end) {
-			/* Split original range */
-			mem->ranges[i].end = mstart - 1;
-			temp_range.start = mend + 1;
-			temp_range.end = end;
-		} else if (mstart != start)
-			mem->ranges[i].end = mstart - 1;
-		else
-			mem->ranges[i].start = mend + 1;
-		break;
-	}
+	/*
+	 * Exclusion of crash region and/or crashk_low_res may cause
+	 * another range split. So add extra two slots here.
+	 */
+	nr_ranges += 2;
+	cmem = vzalloc(sizeof(struct crash_mem) +
+			sizeof(struct crash_mem_range) * nr_ranges);
+	if (!cmem)
+		return NULL;
 
-	/* If a split happend, add the split to array */
-	if (!temp_range.end)
-		return 0;
+	cmem->max_nr_ranges = nr_ranges;
+	cmem->nr_ranges = 0;
 
-	/* Split happened */
-	if (i == CRASH_MAX_RANGES - 1) {
-		pr_err("Too many crash ranges after split\n");
-		return -ENOMEM;
-	}
-
-	/* Location where new range should go */
-	j = i + 1;
-	if (j < mem->nr_ranges) {
-		/* Move over all ranges one slot towards the end */
-		for (i = mem->nr_ranges - 1; i >= j; i--)
-			mem->ranges[i + 1] = mem->ranges[i];
-	}
-
-	mem->ranges[j].start = temp_range.start;
-	mem->ranges[j].end = temp_range.end;
-	mem->nr_ranges++;
-	return 0;
+	return cmem;
 }
 
 /*
  * Look for any unwanted ranges between mstart, mend and remove them. This
- * might lead to split and split ranges are put in ced->mem.ranges[] array
+ * might lead to split and split ranges are put in cmem->ranges[] array
  */
-static int elf_header_exclude_ranges(struct crash_elf_data *ced,
-		unsigned long long mstart, unsigned long long mend)
+static int elf_header_exclude_ranges(struct crash_mem *cmem)
 {
-	struct crash_mem *cmem = &ced->mem;
 	int ret = 0;
 
-	memset(cmem->ranges, 0, sizeof(cmem->ranges));
-
-	cmem->ranges[0].start = mstart;
-	cmem->ranges[0].end = mend;
-	cmem->nr_ranges = 1;
-
 	/* Exclude crashkernel region */
-	ret = exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
+	ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
 	if (ret)
 		return ret;
 
 	if (crashk_low_res.end) {
-		ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
+		ret = crash_exclude_mem_range(cmem, crashk_low_res.start,
+							crashk_low_res.end);
 		if (ret)
 			return ret;
 	}
@@ -345,144 +239,12 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced,
 
 static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg)
 {
-	struct crash_elf_data *ced = arg;
-	Elf64_Ehdr *ehdr;
-	Elf64_Phdr *phdr;
-	unsigned long mstart, mend;
-	struct kimage *image = ced->image;
-	struct crash_mem *cmem;
-	int ret, i;
-
-	ehdr = ced->ehdr;
-
-	/* Exclude unwanted mem ranges */
-	ret = elf_header_exclude_ranges(ced, res->start, res->end);
-	if (ret)
-		return ret;
-
-	/* Go through all the ranges in ced->mem.ranges[] and prepare phdr */
-	cmem = &ced->mem;
-
-	for (i = 0; i < cmem->nr_ranges; i++) {
-		mstart = cmem->ranges[i].start;
-		mend = cmem->ranges[i].end;
-
-		phdr = ced->bufp;
-		ced->bufp += sizeof(Elf64_Phdr);
-
-		phdr->p_type = PT_LOAD;
-		phdr->p_flags = PF_R|PF_W|PF_X;
-		phdr->p_offset  = mstart;
-
-		/*
-		 * If a range matches backup region, adjust offset to backup
-		 * segment.
-		 */
-		if (mstart == image->arch.backup_src_start &&
-		    (mend - mstart + 1) == image->arch.backup_src_sz)
-			phdr->p_offset = image->arch.backup_load_addr;
-
-		phdr->p_paddr = mstart;
-		phdr->p_vaddr = (unsigned long long) __va(mstart);
-		phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
-		phdr->p_align = 0;
-		ehdr->e_phnum++;
-		pr_debug("Crash PT_LOAD elf header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
-			phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
-			ehdr->e_phnum, phdr->p_offset);
-	}
-
-	return ret;
-}
-
-static int prepare_elf64_headers(struct crash_elf_data *ced,
-		void **addr, unsigned long *sz)
-{
-	Elf64_Ehdr *ehdr;
-	Elf64_Phdr *phdr;
-	unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz;
-	unsigned char *buf, *bufp;
-	unsigned int cpu;
-	unsigned long long notes_addr;
-	int ret;
+	struct crash_mem *cmem = arg;
 
-	/* extra phdr for vmcoreinfo elf note */
-	nr_phdr = nr_cpus + 1;
-	nr_phdr += ced->max_nr_ranges;
-
-	/*
-	 * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
-	 * area on x86_64 (ffffffff80000000 - ffffffffa0000000).
-	 * I think this is required by tools like gdb. So same physical
-	 * memory will be mapped in two elf headers. One will contain kernel
-	 * text virtual addresses and other will have __va(physical) addresses.
-	 */
+	cmem->ranges[cmem->nr_ranges].start = res->start;
+	cmem->ranges[cmem->nr_ranges].end = res->end;
+	cmem->nr_ranges++;
 
-	nr_phdr++;
-	elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr);
-	elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN);
-
-	buf = vzalloc(elf_sz);
-	if (!buf)
-		return -ENOMEM;
-
-	bufp = buf;
-	ehdr = (Elf64_Ehdr *)bufp;
-	bufp += sizeof(Elf64_Ehdr);
-	memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
-	ehdr->e_ident[EI_CLASS] = ELFCLASS64;
-	ehdr->e_ident[EI_DATA] = ELFDATA2LSB;
-	ehdr->e_ident[EI_VERSION] = EV_CURRENT;
-	ehdr->e_ident[EI_OSABI] = ELF_OSABI;
-	memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD);
-	ehdr->e_type = ET_CORE;
-	ehdr->e_machine = ELF_ARCH;
-	ehdr->e_version = EV_CURRENT;
-	ehdr->e_phoff = sizeof(Elf64_Ehdr);
-	ehdr->e_ehsize = sizeof(Elf64_Ehdr);
-	ehdr->e_phentsize = sizeof(Elf64_Phdr);
-
-	/* Prepare one phdr of type PT_NOTE for each present cpu */
-	for_each_present_cpu(cpu) {
-		phdr = (Elf64_Phdr *)bufp;
-		bufp += sizeof(Elf64_Phdr);
-		phdr->p_type = PT_NOTE;
-		notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
-		phdr->p_offset = phdr->p_paddr = notes_addr;
-		phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t);
-		(ehdr->e_phnum)++;
-	}
-
-	/* Prepare one PT_NOTE header for vmcoreinfo */
-	phdr = (Elf64_Phdr *)bufp;
-	bufp += sizeof(Elf64_Phdr);
-	phdr->p_type = PT_NOTE;
-	phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
-	phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
-	(ehdr->e_phnum)++;
-
-#ifdef CONFIG_X86_64
-	/* Prepare PT_LOAD type program header for kernel text region */
-	phdr = (Elf64_Phdr *)bufp;
-	bufp += sizeof(Elf64_Phdr);
-	phdr->p_type = PT_LOAD;
-	phdr->p_flags = PF_R|PF_W|PF_X;
-	phdr->p_vaddr = (Elf64_Addr)_text;
-	phdr->p_filesz = phdr->p_memsz = _end - _text;
-	phdr->p_offset = phdr->p_paddr = __pa_symbol(_text);
-	(ehdr->e_phnum)++;
-#endif
-
-	/* Prepare PT_LOAD headers for system ram chunks. */
-	ced->ehdr = ehdr;
-	ced->bufp = bufp;
-	ret = walk_system_ram_res(0, -1, ced,
-			prepare_elf64_ram_headers_callback);
-	if (ret < 0)
-		return ret;
-
-	*addr = buf;
-	*sz = elf_sz;
 	return 0;
 }
 
@@ -490,18 +252,46 @@ static int prepare_elf64_headers(struct crash_elf_data *ced,
 static int prepare_elf_headers(struct kimage *image, void **addr,
 					unsigned long *sz)
 {
-	struct crash_elf_data *ced;
-	int ret;
+	struct crash_mem *cmem;
+	Elf64_Ehdr *ehdr;
+	Elf64_Phdr *phdr;
+	int ret, i;
 
-	ced = kzalloc(sizeof(*ced), GFP_KERNEL);
-	if (!ced)
+	cmem = fill_up_crash_elf_data();
+	if (!cmem)
 		return -ENOMEM;
 
-	fill_up_crash_elf_data(ced, image);
+	ret = walk_system_ram_res(0, -1, cmem,
+				prepare_elf64_ram_headers_callback);
+	if (ret)
+		goto out;
+
+	/* Exclude unwanted mem ranges */
+	ret = elf_header_exclude_ranges(cmem);
+	if (ret)
+		goto out;
 
 	/* By default prepare 64bit headers */
-	ret =  prepare_elf64_headers(ced, addr, sz);
-	kfree(ced);
+	ret =  crash_prepare_elf64_headers(cmem,
+				IS_ENABLED(CONFIG_X86_64), addr, sz);
+	if (ret)
+		goto out;
+
+	/*
+	 * If a range matches backup region, adjust offset to backup
+	 * segment.
+	 */
+	ehdr = (Elf64_Ehdr *)*addr;
+	phdr = (Elf64_Phdr *)(ehdr + 1);
+	for (i = 0; i < ehdr->e_phnum; phdr++, i++)
+		if (phdr->p_type == PT_LOAD &&
+				phdr->p_paddr == image->arch.backup_src_start &&
+				phdr->p_memsz == image->arch.backup_src_sz) {
+			phdr->p_offset = image->arch.backup_load_addr;
+			break;
+		}
+out:
+	vfree(cmem);
 	return ret;
 }
 
@@ -547,14 +337,14 @@ static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem,
 	/* Exclude Backup region */
 	start = image->arch.backup_load_addr;
 	end = start + image->arch.backup_src_sz - 1;
-	ret = exclude_mem_range(cmem, start, end);
+	ret = crash_exclude_mem_range(cmem, start, end);
 	if (ret)
 		return ret;
 
 	/* Exclude elf header region */
 	start = image->arch.elf_load_addr;
 	end = start + image->arch.elf_headers_sz - 1;
-	return exclude_mem_range(cmem, start, end);
+	return crash_exclude_mem_range(cmem, start, end);
 }
 
 /* Prepare memory map for crash dump kernel */

arch/x86/kernel/kexec-bzimage64.c

@@ -334,7 +334,6 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	unsigned long setup_header_size, params_cmdline_sz;
 	struct boot_params *params;
 	unsigned long bootparam_load_addr, kernel_load_addr, initrd_load_addr;
-	unsigned long purgatory_load_addr;
 	struct bzimage64_data *ldata;
 	struct kexec_entry64_regs regs64;
 	void *stack;
@@ -342,6 +341,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	unsigned int efi_map_offset, efi_map_sz, efi_setup_data_offset;
 	struct kexec_buf kbuf = { .image = image, .buf_max = ULONG_MAX,
 				  .top_down = true };
+	struct kexec_buf pbuf = { .image = image, .buf_min = MIN_PURGATORY_ADDR,
+				  .buf_max = ULONG_MAX, .top_down = true };
 
 	header = (struct setup_header *)(kernel + setup_hdr_offset);
 	setup_sects = header->setup_sects;
@@ -379,14 +380,13 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	 * Load purgatory. For 64bit entry point, purgatory  code can be
 	 * anywhere.
 	 */
-	ret = kexec_load_purgatory(image, MIN_PURGATORY_ADDR, ULONG_MAX, 1,
-				   &purgatory_load_addr);
+	ret = kexec_load_purgatory(image, &pbuf);
 	if (ret) {
 		pr_err("Loading purgatory failed\n");
 		return ERR_PTR(ret);
 	}
 
-	pr_debug("Loaded purgatory at 0x%lx\n", purgatory_load_addr);
+	pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem);
 
 
 	/*
@@ -538,7 +538,7 @@ static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len)
 }
 #endif
 
-struct kexec_file_ops kexec_bzImage64_ops = {
+const struct kexec_file_ops kexec_bzImage64_ops = {
 	.probe = bzImage64_probe,
 	.load = bzImage64_load,
 	.cleanup = bzImage64_cleanup,

arch/x86/kernel/machine_kexec_64.c

@@ -30,8 +30,9 @@
 #include <asm/set_memory.h>
 
 #ifdef CONFIG_KEXEC_FILE
-static struct kexec_file_ops *kexec_file_loaders[] = {
+const struct kexec_file_ops * const kexec_file_loaders[] = {
 		&kexec_bzImage64_ops,
+		NULL
 };
 #endif
 
@@ -364,27 +365,6 @@ void arch_crash_save_vmcoreinfo(void)
 /* arch-dependent functionality related to kexec file-based syscall */
 
 #ifdef CONFIG_KEXEC_FILE
-int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
-				  unsigned long buf_len)
-{
-	int i, ret = -ENOEXEC;
-	struct kexec_file_ops *fops;
-
-	for (i = 0; i < ARRAY_SIZE(kexec_file_loaders); i++) {
-		fops = kexec_file_loaders[i];
-		if (!fops || !fops->probe)
-			continue;
-
-		ret = fops->probe(buf, buf_len);
-		if (!ret) {
-			image->fops = fops;
-			return ret;
-		}
-	}
-
-	return ret;
-}
-
 void *arch_kexec_kernel_image_load(struct kimage *image)
 {
 	vfree(image->arch.elf_headers);
@@ -399,88 +379,53 @@ void *arch_kexec_kernel_image_load(struct kimage *image)
 				 image->cmdline_buf_len);
 }
 
-int arch_kimage_file_post_load_cleanup(struct kimage *image)
-{
-	if (!image->fops || !image->fops->cleanup)
-		return 0;
-
-	return image->fops->cleanup(image->image_loader_data);
-}
-
-#ifdef CONFIG_KEXEC_VERIFY_SIG
-int arch_kexec_kernel_verify_sig(struct kimage *image, void *kernel,
-				 unsigned long kernel_len)
-{
-	if (!image->fops || !image->fops->verify_sig) {
-		pr_debug("kernel loader does not support signature verification.");
-		return -EKEYREJECTED;
-	}
-
-	return image->fops->verify_sig(kernel, kernel_len);
-}
-#endif
-
 /*
  * Apply purgatory relocations.
  *
- * ehdr: Pointer to elf headers
- * sechdrs: Pointer to section headers.
- * relsec: section index of SHT_RELA section.
+ * @pi:		Purgatory to be relocated.
+ * @section:	Section relocations applying to.
+ * @relsec:	Section containing RELAs.
+ * @symtabsec:	Corresponding symtab.
  *
  * TODO: Some of the code belongs to generic code. Move that in kexec.c.
  */
-int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr,
-				     Elf64_Shdr *sechdrs, unsigned int relsec)
+int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
+				     Elf_Shdr *section, const Elf_Shdr *relsec,
+				     const Elf_Shdr *symtabsec)
 {
 	unsigned int i;
 	Elf64_Rela *rel;
 	Elf64_Sym *sym;
 	void *location;
-	Elf64_Shdr *section, *symtabsec;
 	unsigned long address, sec_base, value;
 	const char *strtab, *name, *shstrtab;
+	const Elf_Shdr *sechdrs;
 
-	/*
-	 * ->sh_offset has been modified to keep the pointer to section
-	 * contents in memory
-	 */
-	rel = (void *)sechdrs[relsec].sh_offset;
-
-	/* Section to which relocations apply */
-	section = &sechdrs[sechdrs[relsec].sh_info];
-
-	pr_debug("Applying relocate section %u to %u\n", relsec,
-		 sechdrs[relsec].sh_info);
-
-	/* Associated symbol table */
-	symtabsec = &sechdrs[sechdrs[relsec].sh_link];
-
-	/* String table */
-	if (symtabsec->sh_link >= ehdr->e_shnum) {
-		/* Invalid strtab section number */
-		pr_err("Invalid string table section index %d\n",
-		       symtabsec->sh_link);
-		return -ENOEXEC;
-	}
+	/* String & section header string table */
+	sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff;
+	strtab = (char *)pi->ehdr + sechdrs[symtabsec->sh_link].sh_offset;
+	shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset;
 
-	strtab = (char *)sechdrs[symtabsec->sh_link].sh_offset;
+	rel = (void *)pi->ehdr + relsec->sh_offset;
 
-	/* section header string table */
-	shstrtab = (char *)sechdrs[ehdr->e_shstrndx].sh_offset;
+	pr_debug("Applying relocate section %s to %u\n",
+		 shstrtab + relsec->sh_name, relsec->sh_info);
 
-	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
+	for (i = 0; i < relsec->sh_size / sizeof(*rel); i++) {
 
 		/*
 		 * rel[i].r_offset contains byte offset from beginning
 		 * of section to the storage unit affected.
 		 *
-		 * This is location to update (->sh_offset). This is temporary
-		 * buffer where section is currently loaded. This will finally
-		 * be loaded to a different address later, pointed to by
+		 * This is location to update. This is temporary buffer
+		 * where section is currently loaded. This will finally be
+		 * loaded to a different address later, pointed to by
 		 * ->sh_addr. kexec takes care of moving it
 		 *  (kexec_load_segment()).
 		 */
-		location = (void *)(section->sh_offset + rel[i].r_offset);
+		location = pi->purgatory_buf;
+		location += section->sh_offset;
+		location += rel[i].r_offset;
 
 		/* Final address of the location */
 		address = section->sh_addr + rel[i].r_offset;
@@ -491,8 +436,8 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr,
 		 * to apply. ELF64_R_SYM() and ELF64_R_TYPE() macros get
 		 * these respectively.
 		 */
-		sym = (Elf64_Sym *)symtabsec->sh_offset +
-				ELF64_R_SYM(rel[i].r_info);
+		sym = (void *)pi->ehdr + symtabsec->sh_offset;
+		sym += ELF64_R_SYM(rel[i].r_info);
 
 		if (sym->st_name)
 			name = strtab + sym->st_name;
@@ -515,12 +460,12 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr,
 
 		if (sym->st_shndx == SHN_ABS)
 			sec_base = 0;
-		else if (sym->st_shndx >= ehdr->e_shnum) {
+		else if (sym->st_shndx >= pi->ehdr->e_shnum) {
 			pr_err("Invalid section %d for symbol %s\n",
 			       sym->st_shndx, name);
 			return -ENOEXEC;
 		} else
-			sec_base = sechdrs[sym->st_shndx].sh_addr;
+			sec_base = pi->sechdrs[sym->st_shndx].sh_addr;
 
 		value = sym->st_value;
 		value += sec_base;

arch/x86/purgatory/Makefile

@@ -6,6 +6,9 @@ purgatory-y := purgatory.o stack.o setup-x86_$(BITS).o sha256.o entry64.o string
 targets += $(purgatory-y)
 PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 
+$(obj)/sha256.o: $(srctree)/lib/sha256.c
+	$(call if_changed_rule,cc_o_c)
+
 LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib
 targets += purgatory.ro
 

arch/x86/purgatory/purgatory.c

@@ -11,9 +11,9 @@
  */
 
 #include <linux/bug.h>
+#include <linux/sha256.h>
 #include <asm/purgatory.h>
 
-#include "sha256.h"
 #include "../boot/string.h"
 
 unsigned long purgatory_backup_dest __section(.kexec-purgatory);

arch/x86/purgatory/string.c

@@ -10,4 +10,16 @@
  * Version 2.  See the file COPYING for more details.
  */
 
+#include <linux/types.h>
+
 #include "../boot/string.c"
+
+void *memcpy(void *dst, const void *src, size_t len)
+{
+	return __builtin_memcpy(dst, src, len);
+}
+
+void *memset(void *dst, int c, size_t len)
+{
+	return __builtin_memset(dst, c, len);
+}

fs/proc/generic.c

@@ -15,6 +15,7 @@
 #include <linux/stat.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/namei.h>
 #include <linux/slab.h>
 #include <linux/printk.h>
 #include <linux/mount.h>
@@ -217,6 +218,26 @@ void proc_free_inum(unsigned int inum)
 	ida_simple_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
 }
 
+static int proc_misc_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	if (atomic_read(&PDE(d_inode(dentry))->in_use) < 0)
+		return 0; /* revalidate */
+	return 1;
+}
+
+static int proc_misc_d_delete(const struct dentry *dentry)
+{
+	return atomic_read(&PDE(d_inode(dentry))->in_use) < 0;
+}
+
+static const struct dentry_operations proc_misc_dentry_ops = {
+	.d_revalidate	= proc_misc_d_revalidate,
+	.d_delete	= proc_misc_d_delete,
+};
+
 /*
  * Don't create negative dentries here, return -ENOENT by hand
  * instead.
@@ -234,7 +255,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry,
 		inode = proc_get_inode(dir->i_sb, de);
 		if (!inode)
 			return ERR_PTR(-ENOMEM);
-		d_set_d_op(dentry, &simple_dentry_operations);
+		d_set_d_op(dentry, &proc_misc_dentry_ops);
 		d_add(dentry, inode);
 		return NULL;
 	}

include/linux/kexec.h

@@ -99,21 +99,25 @@ struct compat_kexec_segment {
 
 #ifdef CONFIG_KEXEC_FILE
 struct purgatory_info {
-	/* Pointer to elf header of read only purgatory */
-	Elf_Ehdr *ehdr;
-
-	/* Pointer to purgatory sechdrs which are modifiable */
+	/*
+	 * Pointer to elf header at the beginning of kexec_purgatory.
+	 * Note: kexec_purgatory is read only
+	 */
+	const Elf_Ehdr *ehdr;
+	/*
+	 * Temporary, modifiable buffer for sechdrs used for relocation.
+	 * This memory can be freed post image load.
+	 */
 	Elf_Shdr *sechdrs;
 	/*
-	 * Temporary buffer location where purgatory is loaded and relocated
-	 * This memory can be freed post image load
+	 * Temporary, modifiable buffer for stripped purgatory used for
+	 * relocation. This memory can be freed post image load.
 	 */
 	void *purgatory_buf;
-
-	/* Address where purgatory is finally loaded and is executed from */
-	unsigned long purgatory_load_addr;
 };
 
+struct kimage;
+
 typedef int (kexec_probe_t)(const char *kernel_buf, unsigned long kernel_size);
 typedef void *(kexec_load_t)(struct kimage *image, char *kernel_buf,
 			     unsigned long kernel_len, char *initrd,
@@ -135,6 +139,11 @@ struct kexec_file_ops {
 #endif
 };
 
+extern const struct kexec_file_ops * const kexec_file_loaders[];
+
+int kexec_image_probe_default(struct kimage *image, void *buf,
+			      unsigned long buf_len);
+
 /**
  * struct kexec_buf - parameters for finding a place for a buffer in memory
  * @image:	kexec image in which memory to search.
@@ -159,10 +168,44 @@ struct kexec_buf {
 	bool top_down;
 };
 
+int kexec_load_purgatory(struct kimage *image, struct kexec_buf *kbuf);
+int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name,
+				   void *buf, unsigned int size,
+				   bool get_value);
+void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name);
+
+int __weak arch_kexec_apply_relocations_add(struct purgatory_info *pi,
+					    Elf_Shdr *section,
+					    const Elf_Shdr *relsec,
+					    const Elf_Shdr *symtab);
+int __weak arch_kexec_apply_relocations(struct purgatory_info *pi,
+					Elf_Shdr *section,
+					const Elf_Shdr *relsec,
+					const Elf_Shdr *symtab);
+
 int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
 			       int (*func)(struct resource *, void *));
 extern int kexec_add_buffer(struct kexec_buf *kbuf);
 int kexec_locate_mem_hole(struct kexec_buf *kbuf);
+
+/* Alignment required for elf header segment */
+#define ELF_CORE_HEADER_ALIGN   4096
+
+struct crash_mem_range {
+	u64 start, end;
+};
+
+struct crash_mem {
+	unsigned int max_nr_ranges;
+	unsigned int nr_ranges;
+	struct crash_mem_range ranges[0];
+};
+
+extern int crash_exclude_mem_range(struct crash_mem *mem,
+				   unsigned long long mstart,
+				   unsigned long long mend);
+extern int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
+				       void **addr, unsigned long *sz);
 #endif /* CONFIG_KEXEC_FILE */
 
 struct kimage {
@@ -209,7 +252,7 @@ struct kimage {
 	unsigned long cmdline_buf_len;
 
 	/* File operations provided by image loader */
-	struct kexec_file_ops *fops;
+	const struct kexec_file_ops *fops;
 
 	/* Image loader handling the kernel can store a pointer here */
 	void *image_loader_data;
@@ -226,14 +269,6 @@ extern void machine_kexec_cleanup(struct kimage *image);
 extern int kernel_kexec(void);
 extern struct page *kimage_alloc_control_pages(struct kimage *image,
 						unsigned int order);
-extern int kexec_load_purgatory(struct kimage *image, unsigned long min,
-				unsigned long max, int top_down,
-				unsigned long *load_addr);
-extern int kexec_purgatory_get_set_symbol(struct kimage *image,
-					  const char *name, void *buf,
-					  unsigned int size, bool get_value);
-extern void *kexec_purgatory_get_symbol_addr(struct kimage *image,
-					     const char *name);
 extern void __crash_kexec(struct pt_regs *);
 extern void crash_kexec(struct pt_regs *);
 int kexec_should_crash(struct task_struct *);
@@ -273,16 +308,6 @@ int crash_shrink_memory(unsigned long new_size);
 size_t crash_get_memory_size(void);
 void crash_free_reserved_phys_range(unsigned long begin, unsigned long end);
 
-int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
-					 unsigned long buf_len);
-void * __weak arch_kexec_kernel_image_load(struct kimage *image);
-int __weak arch_kimage_file_post_load_cleanup(struct kimage *image);
-int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf,
-					unsigned long buf_len);
-int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr,
-					Elf_Shdr *sechdrs, unsigned int relsec);
-int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
-					unsigned int relsec);
 void arch_kexec_protect_crashkres(void);
 void arch_kexec_unprotect_crashkres(void);
 

arch/x86/purgatory/sha256.h → include/linux/sha256.h

@@ -13,9 +13,18 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 
+/*
+ * Stand-alone implementation of the SHA256 algorithm. It is designed to
+ * have as little dependencies as possible so it can be used in the
+ * kexec_file purgatory. In other cases you should use the implementation in
+ * crypto/.
+ *
+ * For details see lib/sha256.c
+ */
+
 extern int sha256_init(struct sha256_state *sctx);
 extern int sha256_update(struct sha256_state *sctx, const u8 *input,
-				unsigned int length);
+			 unsigned int length);
 extern int sha256_final(struct sha256_state *sctx, u8 *hash);
 
 #endif /* SHA256_H */

ipc/shm.c

@@ -225,6 +225,12 @@ static int __shm_open(struct vm_area_struct *vma)
 	if (IS_ERR(shp))
 		return PTR_ERR(shp);
 
+	if (shp->shm_file != sfd->file) {
+		/* ID was reused */
+		shm_unlock(shp);
+		return -EINVAL;
+	}
+
 	shp->shm_atim = ktime_get_real_seconds();
 	ipc_update_pid(&shp->shm_lprid, task_tgid(current));
 	shp->shm_nattch++;
@@ -455,8 +461,9 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma)
 	int ret;
 
 	/*
-	 * In case of remap_file_pages() emulation, the file can represent
-	 * removed IPC ID: propogate shm_lock() error to caller.
+	 * In case of remap_file_pages() emulation, the file can represent an
+	 * IPC ID that was removed, and possibly even reused by another shm
+	 * segment already.  Propagate this case as an error to caller.
 	 */
 	ret = __shm_open(vma);
 	if (ret)
@@ -480,6 +487,7 @@ static int shm_release(struct inode *ino, struct file *file)
 	struct shm_file_data *sfd = shm_file_data(file);
 
 	put_ipc_ns(sfd->ns);
+	fput(sfd->file);
 	shm_file_data(file) = NULL;
 	kfree(sfd);
 	return 0;
@@ -1445,7 +1453,16 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 	file->f_mapping = shp->shm_file->f_mapping;
 	sfd->id = shp->shm_perm.id;
 	sfd->ns = get_ipc_ns(ns);
-	sfd->file = shp->shm_file;
+	/*
+	 * We need to take a reference to the real shm file to prevent the
+	 * pointer from becoming stale in cases where the lifetime of the outer
+	 * file extends beyond that of the shm segment.  It's not usually
+	 * possible, but it can happen during remap_file_pages() emulation as
+	 * that unmaps the memory, then does ->mmap() via file reference only.
+	 * We'll deny the ->mmap() if the shm segment was since removed, but to
+	 * detect shm ID reuse we need to compare the file pointers.
+	 */
+	sfd->file = get_file(shp->shm_file);
 	sfd->vm_ops = NULL;
 
 	err = security_mmap_file(file, prot, flags);