From ea08eeccae9297f7aabd2ef7f0c2517ac4549acc Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:18:26 +0000
Subject: [PATCH] write in 30M
---
kernel/kernel/kexec_file.c | 282 ++++++++++++++++++++++++++++++++++++++-----------------
1 files changed, 194 insertions(+), 88 deletions(-)
diff --git a/kernel/kernel/kexec_file.c b/kernel/kernel/kexec_file.c
index 89d41c0..804dc50 100644
--- a/kernel/kernel/kexec_file.c
+++ b/kernel/kernel/kexec_file.c
@@ -1,12 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* kexec: kexec_file_load system call
*
* Copyright (C) 2014 Red Hat Inc.
* Authors:
* Vivek Goyal <vgoyal@redhat.com>
- *
- * This source code is licensed under the GNU General Public License,
- * Version 2. See the file COPYING for more details.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -16,6 +14,7 @@
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/kexec.h>
+#include <linux/memblock.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/fs.h>
@@ -25,11 +24,19 @@
#include <linux/elf.h>
#include <linux/elfcore.h>
#include <linux/kernel.h>
-#include <linux/kexec.h>
-#include <linux/slab.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);
@@ -78,7 +85,7 @@
return kexec_image_load_default(image);
}
-static int kexec_image_post_load_cleanup_default(struct kimage *image)
+int kexec_image_post_load_cleanup_default(struct kimage *image)
{
if (!image->fops || !image->fops->cleanup)
return 0;
@@ -91,7 +98,7 @@
return kexec_image_post_load_cleanup_default(image);
}
-#ifdef CONFIG_KEXEC_VERIFY_SIG
+#ifdef CONFIG_KEXEC_SIG
static int kexec_image_verify_sig_default(struct kimage *image, void *buf,
unsigned long buf_len)
{
@@ -109,40 +116,6 @@
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
@@ -185,6 +158,37 @@
image->image_loader_data = NULL;
}
+#ifdef CONFIG_KEXEC_SIG
+static int
+kimage_validate_signature(struct kimage *image)
+{
+ int ret;
+
+ ret = arch_kexec_kernel_verify_sig(image, image->kernel_buf,
+ image->kernel_buf_len);
+ if (ret) {
+
+ 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
+ * image, permit it even if the kernel is otherwise locked
+ * down.
+ */
+ if (!ima_appraise_signature(READING_KEXEC_IMAGE) &&
+ security_locked_down(LOCKDOWN_KEXEC))
+ return -EPERM;
+
+ pr_debug("kernel signature verification failed (%d).\n", ret);
+ }
+
+ return 0;
+}
+#endif
+
/*
* In file mode list of segments is prepared by kernel. Copy relevant
* data from user space, do error checking, prepare segment list
@@ -194,18 +198,14 @@
const char __user *cmdline_ptr,
unsigned long cmdline_len, unsigned flags)
{
- int ret = 0;
+ int 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,
+ INT_MAX, NULL, READING_KEXEC_IMAGE);
+ if (ret < 0)
return ret;
- image->kernel_buf_len = size;
-
- /* IMA needs to pass the measurement list to the next kernel. */
- ima_add_kexec_buffer(image);
+ image->kernel_buf_len = ret;
/* Call arch image probe handlers */
ret = arch_kexec_kernel_image_probe(image, image->kernel_buf,
@@ -213,23 +213,21 @@
if (ret)
goto out;
-#ifdef CONFIG_KEXEC_VERIFY_SIG
- ret = arch_kexec_kernel_verify_sig(image, image->kernel_buf,
- image->kernel_buf_len);
- if (ret) {
- pr_debug("kernel signature verification failed.\n");
+#ifdef CONFIG_KEXEC_SIG
+ ret = kimage_validate_signature(image);
+
+ if (ret)
goto out;
- }
- pr_debug("kernel signature verification successful.\n");
#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,
+ INT_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) {
@@ -247,7 +245,13 @@
ret = -EINVAL;
goto out;
}
+
+ ima_kexec_cmdline(kernel_fd, image->cmdline_buf,
+ image->cmdline_buf_len - 1);
}
+
+ /* IMA needs to pass the measurement list to the next kernel. */
+ ima_add_kexec_buffer(image);
/* Call arch image load handlers */
ldata = arch_kexec_kernel_image_load(image);
@@ -339,7 +343,7 @@
image = NULL;
- if (!mutex_trylock(&kexec_mutex))
+ if (!kexec_trylock())
return -EBUSY;
dest_image = &kexec_image;
@@ -396,6 +400,10 @@
kimage_terminate(image);
+ ret = machine_kexec_post_load(image);
+ if (ret)
+ goto out;
+
/*
* Free up any temporary buffers allocated which are not needed
* after image has been loaded
@@ -407,7 +415,7 @@
if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image)
arch_kexec_protect_crashkres();
- mutex_unlock(&kexec_mutex);
+ kexec_unlock();
kimage_free(image);
return ret;
}
@@ -491,6 +499,11 @@
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;
@@ -506,8 +519,60 @@
return locate_mem_hole_bottom_up(start, end, kbuf);
}
+#ifdef CONFIG_ARCH_KEEP_MEMBLOCK
+static int kexec_walk_memblock(struct kexec_buf *kbuf,
+ int (*func)(struct resource *, void *))
+{
+ int ret = 0;
+ u64 i;
+ phys_addr_t mstart, mend;
+ struct resource res = { };
+
+ if (kbuf->image->type == KEXEC_TYPE_CRASH)
+ return func(&crashk_res, kbuf);
+
+ if (kbuf->top_down) {
+ for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE,
+ &mstart, &mend, NULL) {
+ /*
+ * In memblock, end points to the first byte after the
+ * range while in kexec, end points to the last byte
+ * in the range.
+ */
+ res.start = mstart;
+ res.end = mend - 1;
+ ret = func(&res, kbuf);
+ if (ret)
+ break;
+ }
+ } else {
+ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
+ &mstart, &mend, NULL) {
+ /*
+ * In memblock, end points to the first byte after the
+ * range while in kexec, end points to the last byte
+ * in the range.
+ */
+ res.start = mstart;
+ res.end = mend - 1;
+ ret = func(&res, kbuf);
+ if (ret)
+ break;
+ }
+ }
+
+ return ret;
+}
+#else
+static int kexec_walk_memblock(struct kexec_buf *kbuf,
+ int (*func)(struct resource *, void *))
+{
+ return 0;
+}
+#endif
+
/**
- * arch_kexec_walk_mem - call func(data) on free memory regions
+ * kexec_walk_resources - call func(data) on free memory regions
* @kbuf: Context info for the search. Also passed to @func.
* @func: Function to call for each memory region.
*
@@ -515,8 +580,8 @@
* and that value will be returned. If all free regions are visited without
* func returning non-zero, then zero will be returned.
*/
-int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
- int (*func)(struct resource *, void *))
+static int kexec_walk_resources(struct kexec_buf *kbuf,
+ int (*func)(struct resource *, void *))
{
if (kbuf->image->type == KEXEC_TYPE_CRASH)
return walk_iomem_res_desc(crashk_res.desc,
@@ -539,9 +604,29 @@
{
int ret;
- ret = arch_kexec_walk_mem(kbuf, locate_mem_hole_callback);
+ /* Arch knows where to place */
+ if (kbuf->mem != KEXEC_BUF_MEM_UNKNOWN)
+ return 0;
+
+ if (!IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
+ ret = kexec_walk_resources(kbuf, locate_mem_hole_callback);
+ else
+ ret = kexec_walk_memblock(kbuf, locate_mem_hole_callback);
return ret == 1 ? 0 : -EADDRNOTAVAIL;
+}
+
+/**
+ * arch_kexec_locate_mem_hole - Find free memory to place the segments.
+ * @kbuf: Parameters for the memory search.
+ *
+ * On success, kbuf->mem will have the start address of the memory region found.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int __weak arch_kexec_locate_mem_hole(struct kexec_buf *kbuf)
+{
+ return kexec_locate_mem_hole(kbuf);
}
/**
@@ -556,7 +641,6 @@
*/
int kexec_add_buffer(struct kexec_buf *kbuf)
{
-
struct kexec_segment *ksegment;
int ret;
@@ -584,7 +668,7 @@
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;
@@ -637,7 +721,6 @@
}
desc->tfm = tfm;
- desc->flags = 0;
ret = crypto_shash_init(desc);
if (ret < 0)
@@ -827,10 +910,22 @@
}
offset = ALIGN(offset, align);
+
+ /*
+ * Check if the segment contains the entry point, if so,
+ * calculate the value of image->start based on it.
+ * If the compiler has produced more than one .text section
+ * (Eg: .text.hot), they are generally after the main .text
+ * section, and they shall not be used to calculate
+ * image->start. So do not re-calculate image->start if it
+ * is not set to the initial value, and warn the user so they
+ * have a chance to fix their purgatory's linker script.
+ */
if (sechdrs[i].sh_flags & SHF_EXECINSTR &&
pi->ehdr->e_entry >= sechdrs[i].sh_addr &&
pi->ehdr->e_entry < (sechdrs[i].sh_addr
- + sechdrs[i].sh_size)) {
+ + sechdrs[i].sh_size) &&
+ !WARN_ON(kbuf->image->start != pi->ehdr->e_entry)) {
kbuf->image->start -= sechdrs[i].sh_addr;
kbuf->image->start += kbuf->mem + offset;
}
@@ -1069,24 +1164,26 @@
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) {
@@ -1097,20 +1194,29 @@
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;
}
@@ -1147,7 +1253,7 @@
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;
@@ -1155,7 +1261,7 @@
* 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.
*/
@@ -1182,7 +1288,7 @@
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));
@@ -1203,7 +1309,7 @@
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_vaddr = (unsigned long) _text;
phdr->p_filesz = phdr->p_memsz = _end - _text;
phdr->p_offset = phdr->p_paddr = __pa_symbol(_text);
ehdr->e_phnum++;
@@ -1220,14 +1326,14 @@
phdr->p_offset = mstart;
phdr->p_paddr = mstart;
- phdr->p_vaddr = (unsigned long long) __va(mstart);
+ phdr->p_vaddr = (unsigned 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",
+ 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;
--
Gitblit v1.6.2