kexec_file, x86: move re-factored code to generic side

In the previous patches, commonly-used routines, exclude_mem_range() and
prepare_elf64_headers(), were carved out.  Now place them in kexec
common code.  A prefix "crash_" is given to each of their names to avoid
possible name collisions.

Link: http://lkml.kernel.org/r/20180306102303.9063-8-takahiro.akashi@linaro.org
Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Acked-by: Dave Young <dyoung@redhat.com>
Tested-by: Dave Young <dyoung@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Baoquan He <bhe@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/x86/kernel/crash.c

@@ -38,19 +38,6 @@
 #include <asm/virtext.h>
 #include <asm/intel_pt.h>
 
-/* 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];
-};
-
 /* Used while preparing memory map entries for second kernel */
 struct crash_memmap_data {
 	struct boot_params *params;
@@ -227,77 +214,6 @@ static struct crash_mem *fill_up_crash_elf_data(void)
 	return cmem;
 }
 
-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;
-	}
-
-	/* If a split happend, add the split to array */
-	if (!temp_range.end)
-		return 0;
-
-	/* Split happened */
-	if (i == mem->max_nr_ranges - 1)
-		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;
-}
-
 /*
  * Look for any unwanted ranges between mstart, mend and remove them. This
  * might lead to split and split ranges are put in cmem->ranges[] array
@@ -307,12 +223,13 @@ static int elf_header_exclude_ranges(struct crash_mem *cmem)
 	int ret = 0;
 
 	/* 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;
 	}
@@ -331,105 +248,6 @@ static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg)
 	return 0;
 }
 
-static int prepare_elf64_headers(struct crash_mem *cmem, bool kernel_map,
-		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;
-	unsigned int cpu, i;
-	unsigned long long notes_addr;
-	unsigned long mstart, mend;
-
-	/* extra phdr for vmcoreinfo elf note */
-	nr_phdr = nr_cpus + 1;
-	nr_phdr += cmem->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.
-	 */
-
-	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;
-
-	ehdr = (Elf64_Ehdr *)buf;
-	phdr = (Elf64_Phdr *)(ehdr + 1);
-	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->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)++;
-		phdr++;
-	}
-
-	/* Prepare one PT_NOTE header for vmcoreinfo */
-	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)++;
-	phdr++;
-
-	/* Prepare PT_LOAD type program header for kernel text region */
-	if (kernel_map) {
-		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++;
-		phdr++;
-	}
-
-	/* Go through all the ranges in cmem->ranges[] and prepare phdr */
-	for (i = 0; i < cmem->nr_ranges; i++) {
-		mstart = cmem->ranges[i].start;
-		mend = cmem->ranges[i].end;
-
-		phdr->p_type = PT_LOAD;
-		phdr->p_flags = PF_R|PF_W|PF_X;
-		phdr->p_offset  = mstart;
-
-		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++;
-		phdr++;
-		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);
-	}
-
-	*addr = buf;
-	*sz = elf_sz;
-	return 0;
-}
-
 /* Prepare elf headers. Return addr and size */
 static int prepare_elf_headers(struct kimage *image, void **addr,
 					unsigned long *sz)
@@ -454,7 +272,8 @@ static int prepare_elf_headers(struct kimage *image, void **addr,
 		goto out;
 
 	/* By default prepare 64bit headers */
-	ret =  prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz);
+	ret =  crash_prepare_elf64_headers(cmem,
+				IS_ENABLED(CONFIG_X86_64), addr, sz);
 	if (ret)
 		goto out;
 
@@ -518,14 +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 */

include/linux/kexec.h

@@ -168,6 +168,25 @@ 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 {

kernel/kexec_file.c

@@ -22,6 +22,11 @@
 #include <linux/ima.h>
 #include <crypto/hash.h>
 #include <crypto/sha.h>
+#include <linux/elf.h>
+#include <linux/elfcore.h>
+#include <linux/kernel.h>
+#include <linux/kexec.h>
+#include <linux/slab.h>
 #include <linux/syscalls.h>
 #include <linux/vmalloc.h>
 #include "kexec_internal.h"
@@ -1079,3 +1084,173 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name,
 	return 0;
 }
 #endif /* CONFIG_ARCH_HAS_KEXEC_PURGATORY */
+
+int crash_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;
+	}
+
+	/* If a split happened, add the split to array */
+	if (!temp_range.end)
+		return 0;
+
+	/* Split happened */
+	if (i == mem->max_nr_ranges - 1)
+		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;
+}
+
+int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
+			  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;
+	unsigned int cpu, i;
+	unsigned long long notes_addr;
+	unsigned long mstart, mend;
+
+	/* extra phdr for vmcoreinfo elf note */
+	nr_phdr = nr_cpus + 1;
+	nr_phdr += mem->nr_ranges;
+
+	/*
+	 * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
+	 * area (for example, ffffffff80000000 - ffffffffa0000000 on x86_64).
+	 * 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.
+	 */
+
+	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;
+
+	ehdr = (Elf64_Ehdr *)buf;
+	phdr = (Elf64_Phdr *)(ehdr + 1);
+	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->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)++;
+		phdr++;
+	}
+
+	/* Prepare one PT_NOTE header for vmcoreinfo */
+	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)++;
+	phdr++;
+
+	/* Prepare PT_LOAD type program header for kernel text region */
+	if (kernel_map) {
+		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++;
+		phdr++;
+	}
+
+	/* Go through all the ranges in mem->ranges[] and prepare phdr */
+	for (i = 0; i < mem->nr_ranges; i++) {
+		mstart = mem->ranges[i].start;
+		mend = mem->ranges[i].end;
+
+		phdr->p_type = PT_LOAD;
+		phdr->p_flags = PF_R|PF_W|PF_X;
+		phdr->p_offset  = mstart;
+
+		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++;
+		phdr++;
+		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);
+	}
+
+	*addr = buf;
+	*sz = elf_sz;
+	return 0;
+}