1 files changed, 113 insertions, 136 deletions

diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index faa74d5f6941..45637511e0de 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -20,16 +20,29 @@
 #include <linux/fs.h>
 #include <linux/ima.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <linux/elf.h>
 #include <linux/elfcore.h>
 #include <linux/kernel.h>
+#include <linux/kernel_read_file.h>
 #include <linux/syscalls.h>
 #include <linux/vmalloc.h>
 #include "kexec_internal.h"
 
+#ifdef CONFIG_KEXEC_SIG
+static bool sig_enforce = IS_ENABLED(CONFIG_KEXEC_SIG_FORCE);
+
+void set_kexec_sig_enforced(void)
+{
+	sig_enforce = true;
+}
+#endif
+
 static int kexec_calculate_store_digests(struct kimage *image);
 
+/* Maximum size in bytes for kernel/initrd files. */
+#define KEXEC_FILE_SIZE_MAX	min_t(s64, 4LL << 30, SSIZE_MAX)
+
 /*
  * Currently this is the only default function that is exported as some
  * architectures need it to do additional handlings.
@@ -52,14 +65,7 @@ int kexec_image_probe_default(struct kimage *image, void *buf,
 	return ret;
 }
 
-/* Architectures can provide this probe function */
-int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
-					 unsigned long buf_len)
-{
-	return kexec_image_probe_default(image, buf, buf_len);
-}
-
-static void *kexec_image_load_default(struct kimage *image)
+void *kexec_image_load_default(struct kimage *image)
 {
 	if (!image->fops || !image->fops->load)
 		return ERR_PTR(-ENOEXEC);
@@ -70,11 +76,6 @@ static void *kexec_image_load_default(struct kimage *image)
 				 image->cmdline_buf_len);
 }
 
-void * __weak arch_kexec_kernel_image_load(struct kimage *image)
-{
-	return kexec_image_load_default(image);
-}
-
 int kexec_image_post_load_cleanup_default(struct kimage *image)
 {
 	if (!image->fops || !image->fops->cleanup)
@@ -83,64 +84,6 @@ int kexec_image_post_load_cleanup_default(struct kimage *image)
 	return image->fops->cleanup(image->image_loader_data);
 }
 
-int __weak arch_kimage_file_post_load_cleanup(struct kimage *image)
-{
-	return kexec_image_post_load_cleanup_default(image);
-}
-
-#ifdef CONFIG_KEXEC_SIG
-static int kexec_image_verify_sig_default(struct kimage *image, void *buf,
-					  unsigned long buf_len)
-{
-	if (!image->fops || !image->fops->verify_sig) {
-		pr_debug("kernel loader does not support signature verification.\n");
-		return -EKEYREJECTED;
-	}
-
-	return image->fops->verify_sig(buf, buf_len);
-}
-
-int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf,
-					unsigned long buf_len)
-{
-	return kexec_image_verify_sig_default(image, buf, buf_len);
-}
-#endif
-
-/*
- * arch_kexec_apply_relocations_add - apply relocations of type RELA
- * @pi:		Purgatory to be relocated.
- * @section:	Section relocations applying to.
- * @relsec:	Section containing RELAs.
- * @symtab:	Corresponding symtab.
- *
- * Return: 0 on success, negative errno on error.
- */
-int __weak
-arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section,
-				 const Elf_Shdr *relsec, const Elf_Shdr *symtab)
-{
-	pr_err("RELA relocation unsupported.\n");
-	return -ENOEXEC;
-}
-
-/*
- * arch_kexec_apply_relocations - apply relocations of type REL
- * @pi:		Purgatory to be relocated.
- * @section:	Section relocations applying to.
- * @relsec:	Section containing RELs.
- * @symtab:	Corresponding symtab.
- *
- * Return: 0 on success, negative errno on error.
- */
-int __weak
-arch_kexec_apply_relocations(struct purgatory_info *pi, Elf_Shdr *section,
-			     const Elf_Shdr *relsec, const Elf_Shdr *symtab)
-{
-	pr_err("REL relocation unsupported.\n");
-	return -ENOEXEC;
-}
-
 /*
  * Free up memory used by kernel, initrd, and command line. This is temporary
  * memory allocation which is not needed any more after these buffers have
@@ -165,6 +108,11 @@ void kimage_file_post_load_cleanup(struct kimage *image)
 	vfree(pi->sechdrs);
 	pi->sechdrs = NULL;
 
+#ifdef CONFIG_IMA_KEXEC
+	vfree(image->ima_buffer);
+	image->ima_buffer = NULL;
+#endif /* CONFIG_IMA_KEXEC */
+
 	/* See if architecture has anything to cleanup post load */
 	arch_kimage_file_post_load_cleanup(image);
 
@@ -178,37 +126,50 @@ void kimage_file_post_load_cleanup(struct kimage *image)
 }
 
 #ifdef CONFIG_KEXEC_SIG
+#ifdef CONFIG_SIGNED_PE_FILE_VERIFICATION
+int kexec_kernel_verify_pe_sig(const char *kernel, unsigned long kernel_len)
+{
+	int ret;
+
+	ret = verify_pefile_signature(kernel, kernel_len,
+				      VERIFY_USE_SECONDARY_KEYRING,
+				      VERIFYING_KEXEC_PE_SIGNATURE);
+	if (ret == -ENOKEY && IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING)) {
+		ret = verify_pefile_signature(kernel, kernel_len,
+					      VERIFY_USE_PLATFORM_KEYRING,
+					      VERIFYING_KEXEC_PE_SIGNATURE);
+	}
+	return ret;
+}
+#endif
+
+static int kexec_image_verify_sig(struct kimage *image, void *buf,
+				  unsigned long buf_len)
+{
+	if (!image->fops || !image->fops->verify_sig) {
+		pr_debug("kernel loader does not support signature verification.\n");
+		return -EKEYREJECTED;
+	}
+
+	return image->fops->verify_sig(buf, buf_len);
+}
+
 static int
 kimage_validate_signature(struct kimage *image)
 {
-	const char *reason;
 	int ret;
 
-	ret = arch_kexec_kernel_verify_sig(image, image->kernel_buf,
-					   image->kernel_buf_len);
-	switch (ret) {
-	case 0:
-		break;
+	ret = kexec_image_verify_sig(image, image->kernel_buf,
+				     image->kernel_buf_len);
+	if (ret) {
 
-		/* Certain verification errors are non-fatal if we're not
-		 * checking errors, provided we aren't mandating that there
-		 * must be a valid signature.
-		 */
-	case -ENODATA:
-		reason = "kexec of unsigned image";
-		goto decide;
-	case -ENOPKG:
-		reason = "kexec of image with unsupported crypto";
-		goto decide;
-	case -ENOKEY:
-		reason = "kexec of image with unavailable key";
-	decide:
-		if (IS_ENABLED(CONFIG_KEXEC_SIG_FORCE)) {
-			pr_notice("%s rejected\n", reason);
+		if (sig_enforce) {
+			pr_notice("Enforced kernel signature verification failed (%d).\n", ret);
 			return ret;
 		}
 
-		/* If IMA is guaranteed to appraise a signature on the kexec
+		/*
+		 * If IMA is guaranteed to appraise a signature on the kexec
 		 * image, permit it even if the kernel is otherwise locked
 		 * down.
 		 */
@@ -216,17 +177,10 @@ kimage_validate_signature(struct kimage *image)
 		    security_locked_down(LOCKDOWN_KEXEC))
 			return -EPERM;
 
-		return 0;
-
-		/* All other errors are fatal, including nomem, unparseable
-		 * signatures and signature check failures - even if signatures
-		 * aren't required.
-		 */
-	default:
-		pr_notice("kernel signature verification failed (%d).\n", ret);
+		pr_debug("kernel signature verification failed (%d).\n", ret);
 	}
 
-	return ret;
+	return 0;
 }
 #endif
 
@@ -239,15 +193,15 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 			     const char __user *cmdline_ptr,
 			     unsigned long cmdline_len, unsigned flags)
 {
-	int ret;
+	ssize_t ret;
 	void *ldata;
-	loff_t size;
 
-	ret = kernel_read_file_from_fd(kernel_fd, &image->kernel_buf,
-				       &size, INT_MAX, READING_KEXEC_IMAGE);
-	if (ret)
+	ret = kernel_read_file_from_fd(kernel_fd, 0, &image->kernel_buf,
+				       KEXEC_FILE_SIZE_MAX, NULL,
+				       READING_KEXEC_IMAGE);
+	if (ret < 0)
 		return ret;
-	image->kernel_buf_len = size;
+	image->kernel_buf_len = ret;
 
 	/* Call arch image probe handlers */
 	ret = arch_kexec_kernel_image_probe(image, image->kernel_buf,
@@ -263,12 +217,13 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 #endif
 	/* It is possible that there no initramfs is being loaded */
 	if (!(flags & KEXEC_FILE_NO_INITRAMFS)) {
-		ret = kernel_read_file_from_fd(initrd_fd, &image->initrd_buf,
-					       &size, INT_MAX,
+		ret = kernel_read_file_from_fd(initrd_fd, 0, &image->initrd_buf,
+					       KEXEC_FILE_SIZE_MAX, NULL,
 					       READING_KEXEC_INITRAMFS);
-		if (ret)
+		if (ret < 0)
 			goto out;
-		image->initrd_buf_len = size;
+		image->initrd_buf_len = ret;
+		ret = 0;
 	}
 
 	if (cmdline_len) {
@@ -287,7 +242,7 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 			goto out;
 		}
 
-		ima_kexec_cmdline(image->cmdline_buf,
+		ima_kexec_cmdline(kernel_fd, image->cmdline_buf,
 				  image->cmdline_buf_len - 1);
 	}
 
@@ -384,7 +339,7 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 
 	image = NULL;
 
-	if (!mutex_trylock(&kexec_mutex))
+	if (!kexec_trylock())
 		return -EBUSY;
 
 	dest_image = &kexec_image;
@@ -456,7 +411,7 @@ out:
 	if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image)
 		arch_kexec_protect_crashkres();
 
-	mutex_unlock(&kexec_mutex);
+	kexec_unlock();
 	kimage_free(image);
 	return ret;
 }
@@ -540,6 +495,11 @@ static int locate_mem_hole_callback(struct resource *res, void *arg)
 	unsigned long sz = end - start + 1;
 
 	/* Returning 0 will take to next memory range */
+
+	/* Don't use memory that will be detected and handled by a driver. */
+	if (res->flags & IORESOURCE_SYSRAM_DRIVER_MANAGED)
+		return 0;
+
 	if (sz < kbuf->memsz)
 		return 0;
 
@@ -567,6 +527,11 @@ static int kexec_walk_memblock(struct kexec_buf *kbuf,
 	if (kbuf->image->type == KEXEC_TYPE_CRASH)
 		return func(&crashk_res, kbuf);
 
+	/*
+	 * Using MEMBLOCK_NONE will properly skip MEMBLOCK_DRIVER_MANAGED. See
+	 * IORESOURCE_SYSRAM_DRIVER_MANAGED handling in
+	 * locate_mem_hole_callback().
+	 */
 	if (kbuf->top_down) {
 		for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE,
 						&mstart, &mend, NULL) {
@@ -664,7 +629,6 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf)
  */
 int kexec_add_buffer(struct kexec_buf *kbuf)
 {
-
 	struct kexec_segment *ksegment;
 	int ret;
 
@@ -692,7 +656,7 @@ int kexec_add_buffer(struct kexec_buf *kbuf)
 	kbuf->buf_align = max(kbuf->buf_align, PAGE_SIZE);
 
 	/* Walk the RAM ranges and allocate a suitable range for the buffer */
-	ret = kexec_locate_mem_hole(kbuf);
+	ret = arch_kexec_locate_mem_hole(kbuf);
 	if (ret)
 		return ret;
 
@@ -739,8 +703,10 @@ static int kexec_calculate_store_digests(struct kimage *image)
 
 	sha_region_sz = KEXEC_SEGMENT_MAX * sizeof(struct kexec_sha_region);
 	sha_regions = vzalloc(sha_region_sz);
-	if (!sha_regions)
+	if (!sha_regions) {
+		ret = -ENOMEM;
 		goto out_free_desc;
+	}
 
 	desc->tfm   = tfm;
 
@@ -1174,24 +1140,26 @@ 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;
+	unsigned long long start, end, p_start, p_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;
+		p_start = mstart;
+		p_end = mend;
 
 		if (mstart > end || mend < start)
 			continue;
 
 		/* Truncate any area outside of range */
 		if (mstart < start)
-			mstart = start;
+			p_start = start;
 		if (mend > end)
-			mend = end;
+			p_end = end;
 
 		/* Found completely overlapping range */
-		if (mstart == start && mend == end) {
+		if (p_start == start && p_end == end) {
 			mem->ranges[i].start = 0;
 			mem->ranges[i].end = 0;
 			if (i < mem->nr_ranges - 1) {
@@ -1202,20 +1170,29 @@ int crash_exclude_mem_range(struct crash_mem *mem,
 					mem->ranges[j].end =
 							mem->ranges[j+1].end;
 				}
+
+				/*
+				 * Continue to check if there are another overlapping ranges
+				 * from the current position because of shifting the above
+				 * mem ranges.
+				 */
+				i--;
+				mem->nr_ranges--;
+				continue;
 			}
 			mem->nr_ranges--;
 			return 0;
 		}
 
-		if (mstart > start && mend < end) {
+		if (p_start > start && p_end < end) {
 			/* Split original range */
-			mem->ranges[i].end = mstart - 1;
-			temp_range.start = mend + 1;
+			mem->ranges[i].end = p_start - 1;
+			temp_range.start = p_end + 1;
 			temp_range.end = end;
-		} else if (mstart != start)
-			mem->ranges[i].end = mstart - 1;
+		} else if (p_start != start)
+			mem->ranges[i].end = p_start - 1;
 		else
-			mem->ranges[i].start = mend + 1;
+			mem->ranges[i].start = p_end + 1;
 		break;
 	}
 
@@ -1241,7 +1218,7 @@ int crash_exclude_mem_range(struct crash_mem *mem,
 	return 0;
 }
 
-int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
+int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
 			  void **addr, unsigned long *sz)
 {
 	Elf64_Ehdr *ehdr;
@@ -1252,7 +1229,7 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 	unsigned long long notes_addr;
 	unsigned long mstart, mend;
 
-	/* extra phdr for vmcoreinfo elf note */
+	/* extra phdr for vmcoreinfo ELF note */
 	nr_phdr = nr_cpus + 1;
 	nr_phdr += mem->nr_ranges;
 
@@ -1260,7 +1237,7 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 	 * 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
+	 * memory will be mapped in two ELF headers. One will contain kernel
 	 * text virtual addresses and other will have __va(physical) addresses.
 	 */
 
@@ -1287,7 +1264,7 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 	ehdr->e_ehsize = sizeof(Elf64_Ehdr);
 	ehdr->e_phentsize = sizeof(Elf64_Phdr);
 
-	/* Prepare one phdr of type PT_NOTE for each present cpu */
+	/* 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));
@@ -1305,7 +1282,7 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 	phdr++;
 
 	/* Prepare PT_LOAD type program header for kernel text region */
-	if (kernel_map) {
+	if (need_kernel_map) {
 		phdr->p_type = PT_LOAD;
 		phdr->p_flags = PF_R|PF_W|PF_X;
 		phdr->p_vaddr = (unsigned long) _text;
@@ -1329,10 +1306,10 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 		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",
+		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);
+		phdr++;
 	}
 
 	*addr = buf;