summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-09-10 18:19:42 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2015-09-10 18:19:42 -0700
commit33e247c7e58d335d70ecb84fd869091e2e4b8dcb (patch)
treee8561e1993dff03f8e56d10a5795fe9d379a3390 /kernel
parentd71fc239b6915a8b750e9a447311029ff45b6580 (diff)
parent452e06af1f0149b01201f94264d452cd7a95db7a (diff)
downloadlinux-33e247c7e58d335d70ecb84fd869091e2e4b8dcb.tar.gz
linux-33e247c7e58d335d70ecb84fd869091e2e4b8dcb.tar.bz2
linux-33e247c7e58d335d70ecb84fd869091e2e4b8dcb.zip
Merge branch 'akpm' (patches from Andrew)
Merge third patch-bomb from Andrew Morton: - even more of the rest of MM - lib/ updates - checkpatch updates - small changes to a few scruffy filesystems - kmod fixes/cleanups - kexec updates - a dma-mapping cleanup series from hch * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (81 commits) dma-mapping: consolidate dma_set_mask dma-mapping: consolidate dma_supported dma-mapping: cosolidate dma_mapping_error dma-mapping: consolidate dma_{alloc,free}_noncoherent dma-mapping: consolidate dma_{alloc,free}_{attrs,coherent} mm: use vma_is_anonymous() in create_huge_pmd() and wp_huge_pmd() mm: make sure all file VMAs have ->vm_ops set mm, mpx: add "vm_flags_t vm_flags" arg to do_mmap_pgoff() mm: mark most vm_operations_struct const namei: fix warning while make xmldocs caused by namei.c ipc: convert invalid scenarios to use WARN_ON zlib_deflate/deftree: remove bi_reverse() lib/decompress_unlzma: Do a NULL check for pointer lib/decompressors: use real out buf size for gunzip with kernel fs/affs: make root lookup from blkdev logical size sysctl: fix int -> unsigned long assignments in INT_MIN case kexec: export KERNEL_IMAGE_SIZE to vmcoreinfo kexec: align crash_notes allocation to make it be inside one physical page kexec: remove unnecessary test in kimage_alloc_crash_control_pages() kexec: split kexec_load syscall from kexec core code ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile2
-rw-r--r--kernel/cred.c13
-rw-r--r--kernel/events/core.c2
-rw-r--r--kernel/extable.c1
-rw-r--r--kernel/kexec.c2531
-rw-r--r--kernel/kexec_core.c1534
-rw-r--r--kernel/kexec_file.c1045
-rw-r--r--kernel/kexec_internal.h22
-rw-r--r--kernel/kmod.c100
-rw-r--r--kernel/ksysfs.c6
-rw-r--r--kernel/printk/printk.c2
-rw-r--r--kernel/reboot.c2
-rw-r--r--kernel/sysctl.c12
13 files changed, 2681 insertions, 2591 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index e0d7587e7684..d4988410b410 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -49,7 +49,9 @@ obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_MODULE_SIG) += module_signing.o
obj-$(CONFIG_KALLSYMS) += kallsyms.o
obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
+obj-$(CONFIG_KEXEC_CORE) += kexec_core.o
obj-$(CONFIG_KEXEC) += kexec.o
+obj-$(CONFIG_KEXEC_FILE) += kexec_file.o
obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
obj-$(CONFIG_COMPAT) += compat.o
obj-$(CONFIG_CGROUPS) += cgroup.o
diff --git a/kernel/cred.c b/kernel/cred.c
index ec1c07667ec1..71179a09c1d6 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -20,11 +20,16 @@
#include <linux/cn_proc.h>
#if 0
-#define kdebug(FMT, ...) \
- printk("[%-5.5s%5u] "FMT"\n", current->comm, current->pid ,##__VA_ARGS__)
+#define kdebug(FMT, ...) \
+ printk("[%-5.5s%5u] " FMT "\n", \
+ current->comm, current->pid, ##__VA_ARGS__)
#else
-#define kdebug(FMT, ...) \
- no_printk("[%-5.5s%5u] "FMT"\n", current->comm, current->pid ,##__VA_ARGS__)
+#define kdebug(FMT, ...) \
+do { \
+ if (0) \
+ no_printk("[%-5.5s%5u] " FMT "\n", \
+ current->comm, current->pid, ##__VA_ARGS__); \
+} while (0)
#endif
static struct kmem_cache *cred_jar;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e8183895691c..f548f69c4299 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9094,7 +9094,7 @@ static void perf_event_init_cpu(int cpu)
mutex_unlock(&swhash->hlist_mutex);
}
-#if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC
+#if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC_CORE
static void __perf_event_exit_context(void *__info)
{
struct remove_event re = { .detach_group = true };
diff --git a/kernel/extable.c b/kernel/extable.c
index c98f926277a8..e820ccee9846 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -18,7 +18,6 @@
#include <linux/ftrace.h>
#include <linux/memory.h>
#include <linux/module.h>
-#include <linux/ftrace.h>
#include <linux/mutex.h>
#include <linux/init.h>
diff --git a/kernel/kexec.c b/kernel/kexec.c
index a785c1015e25..4c5edc357923 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1,156 +1,22 @@
/*
- * kexec.c - kexec system call
+ * kexec.c - kexec_load system call
* Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.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) "kexec: " fmt
-
#include <linux/capability.h>
#include <linux/mm.h>
#include <linux/file.h>
-#include <linux/slab.h>
-#include <linux/fs.h>
#include <linux/kexec.h>
#include <linux/mutex.h>
#include <linux/list.h>
-#include <linux/highmem.h>
#include <linux/syscalls.h>
-#include <linux/reboot.h>
-#include <linux/ioport.h>
-#include <linux/hardirq.h>
-#include <linux/elf.h>
-#include <linux/elfcore.h>
-#include <linux/utsname.h>
-#include <linux/numa.h>
-#include <linux/suspend.h>
-#include <linux/device.h>
-#include <linux/freezer.h>
-#include <linux/pm.h>
-#include <linux/cpu.h>
-#include <linux/console.h>
#include <linux/vmalloc.h>
-#include <linux/swap.h>
-#include <linux/syscore_ops.h>
-#include <linux/compiler.h>
-#include <linux/hugetlb.h>
-
-#include <asm/page.h>
-#include <asm/uaccess.h>
-#include <asm/io.h>
-#include <asm/sections.h>
-
-#include <crypto/hash.h>
-#include <crypto/sha.h>
-
-/* Per cpu memory for storing cpu states in case of system crash. */
-note_buf_t __percpu *crash_notes;
-
-/* vmcoreinfo stuff */
-static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
-u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
-size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
-
-/* Flag to indicate we are going to kexec a new kernel */
-bool kexec_in_progress = false;
-
-/*
- * Declare these symbols weak so that if architecture provides a purgatory,
- * these will be overridden.
- */
-char __weak kexec_purgatory[0];
-size_t __weak kexec_purgatory_size = 0;
-
-#ifdef CONFIG_KEXEC_FILE
-static int kexec_calculate_store_digests(struct kimage *image);
-#endif
-
-/* Location of the reserved area for the crash kernel */
-struct resource crashk_res = {
- .name = "Crash kernel",
- .start = 0,
- .end = 0,
- .flags = IORESOURCE_BUSY | IORESOURCE_MEM
-};
-struct resource crashk_low_res = {
- .name = "Crash kernel",
- .start = 0,
- .end = 0,
- .flags = IORESOURCE_BUSY | IORESOURCE_MEM
-};
-
-int kexec_should_crash(struct task_struct *p)
-{
- /*
- * If crash_kexec_post_notifiers is enabled, don't run
- * crash_kexec() here yet, which must be run after panic
- * notifiers in panic().
- */
- if (crash_kexec_post_notifiers)
- return 0;
- /*
- * There are 4 panic() calls in do_exit() path, each of which
- * corresponds to each of these 4 conditions.
- */
- if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops)
- return 1;
- return 0;
-}
-
-/*
- * When kexec transitions to the new kernel there is a one-to-one
- * mapping between physical and virtual addresses. On processors
- * where you can disable the MMU this is trivial, and easy. For
- * others it is still a simple predictable page table to setup.
- *
- * In that environment kexec copies the new kernel to its final
- * resting place. This means I can only support memory whose
- * physical address can fit in an unsigned long. In particular
- * addresses where (pfn << PAGE_SHIFT) > ULONG_MAX cannot be handled.
- * If the assembly stub has more restrictive requirements
- * KEXEC_SOURCE_MEMORY_LIMIT and KEXEC_DEST_MEMORY_LIMIT can be
- * defined more restrictively in <asm/kexec.h>.
- *
- * The code for the transition from the current kernel to the
- * the new kernel is placed in the control_code_buffer, whose size
- * is given by KEXEC_CONTROL_PAGE_SIZE. In the best case only a single
- * page of memory is necessary, but some architectures require more.
- * Because this memory must be identity mapped in the transition from
- * virtual to physical addresses it must live in the range
- * 0 - TASK_SIZE, as only the user space mappings are arbitrarily
- * modifiable.
- *
- * The assembly stub in the control code buffer is passed a linked list
- * of descriptor pages detailing the source pages of the new kernel,
- * and the destination addresses of those source pages. As this data
- * structure is not used in the context of the current OS, it must
- * be self-contained.
- *
- * The code has been made to work with highmem pages and will use a
- * destination page in its final resting place (if it happens
- * to allocate it). The end product of this is that most of the
- * physical address space, and most of RAM can be used.
- *
- * Future directions include:
- * - allocating a page table with the control code buffer identity
- * mapped, to simplify machine_kexec and make kexec_on_panic more
- * reliable.
- */
-
-/*
- * KIMAGE_NO_DEST is an impossible destination address..., for
- * allocating pages whose destination address we do not care about.
- */
-#define KIMAGE_NO_DEST (-1UL)
+#include <linux/slab.h>
-static int kimage_is_destination_range(struct kimage *image,
- unsigned long start, unsigned long end);
-static struct page *kimage_alloc_page(struct kimage *image,
- gfp_t gfp_mask,
- unsigned long dest);
+#include "kexec_internal.h"
static int copy_user_segment_list(struct kimage *image,
unsigned long nr_segments,
@@ -169,125 +35,6 @@ static int copy_user_segment_list(struct kimage *image,
return ret;
}
-static int sanity_check_segment_list(struct kimage *image)
-{
- int result, i;
- unsigned long nr_segments = image->nr_segments;
-
- /*
- * Verify we have good destination addresses. The caller is
- * responsible for making certain we don't attempt to load
- * the new image into invalid or reserved areas of RAM. This
- * just verifies it is an address we can use.
- *
- * Since the kernel does everything in page size chunks ensure
- * the destination addresses are page aligned. Too many
- * special cases crop of when we don't do this. The most
- * insidious is getting overlapping destination addresses
- * simply because addresses are changed to page size
- * granularity.
- */
- result = -EADDRNOTAVAIL;
- for (i = 0; i < nr_segments; i++) {
- unsigned long mstart, mend;
-
- mstart = image->segment[i].mem;
- mend = mstart + image->segment[i].memsz;
- if ((mstart & ~PAGE_MASK) || (mend & ~PAGE_MASK))
- return result;
- if (mend >= KEXEC_DESTINATION_MEMORY_LIMIT)
- return result;
- }
-
- /* Verify our destination addresses do not overlap.
- * If we alloed overlapping destination addresses
- * through very weird things can happen with no
- * easy explanation as one segment stops on another.
- */
- result = -EINVAL;
- for (i = 0; i < nr_segments; i++) {
- unsigned long mstart, mend;
- unsigned long j;
-
- mstart = image->segment[i].mem;
- mend = mstart + image->segment[i].memsz;
- for (j = 0; j < i; j++) {
- unsigned long pstart, pend;
- pstart = image->segment[j].mem;
- pend = pstart + image->segment[j].memsz;
- /* Do the segments overlap ? */
- if ((mend > pstart) && (mstart < pend))
- return result;
- }
- }
-
- /* Ensure our buffer sizes are strictly less than
- * our memory sizes. This should always be the case,
- * and it is easier to check up front than to be surprised
- * later on.
- */
- result = -EINVAL;
- for (i = 0; i < nr_segments; i++) {
- if (image->segment[i].bufsz > image->segment[i].memsz)
- return result;
- }
-
- /*
- * Verify we have good destination addresses. Normally
- * the caller is responsible for making certain we don't
- * attempt to load the new image into invalid or reserved
- * areas of RAM. But crash kernels are preloaded into a
- * reserved area of ram. We must ensure the addresses
- * are in the reserved area otherwise preloading the
- * kernel could corrupt things.
- */
-
- if (image->type == KEXEC_TYPE_CRASH) {
- result = -EADDRNOTAVAIL;
- for (i = 0; i < nr_segments; i++) {
- unsigned long mstart, mend;
-
- mstart = image->segment[i].mem;
- mend = mstart + image->segment[i].memsz - 1;
- /* Ensure we are within the crash kernel limits */
- if ((mstart < crashk_res.start) ||
- (mend > crashk_res.end))
- return result;
- }
- }
-
- return 0;
-}
-
-static struct kimage *do_kimage_alloc_init(void)
-{
- struct kimage *image;
-
- /* Allocate a controlling structure */
- image = kzalloc(sizeof(*image), GFP_KERNEL);
- if (!image)
- return NULL;
-
- image->head = 0;
- image->entry = &image->head;
- image->last_entry = &image->head;
- image->control_page = ~0; /* By default this does not apply */
- image->type = KEXEC_TYPE_DEFAULT;
-
- /* Initialize the list of control pages */
- INIT_LIST_HEAD(&image->control_pages);
-
- /* Initialize the list of destination pages */
- INIT_LIST_HEAD(&image->dest_pages);
-
- /* Initialize the list of unusable pages */
- INIT_LIST_HEAD(&image->unusable_pages);
-
- return image;
-}
-
-static void kimage_free_page_list(struct list_head *list);
-
static int kimage_alloc_init(struct kimage **rimage, unsigned long entry,
unsigned long nr_segments,
struct kexec_segment __user *segments,
@@ -354,873 +101,6 @@ out_free_image:
return ret;
}
-#ifdef CONFIG_KEXEC_FILE
-static int copy_file_from_fd(int fd, void **buf, unsigned long *buf_len)
-{
- struct fd f = fdget(fd);
- int ret;
- struct kstat stat;
- loff_t pos;
- ssize_t bytes = 0;
-
- if (!f.file)
- return -EBADF;
-
- ret = vfs_getattr(&f.file->f_path, &stat);
- if (ret)
- goto out;
-
- if (stat.size > INT_MAX) {
- ret = -EFBIG;
- goto out;
- }
-
- /* Don't hand 0 to vmalloc, it whines. */
- if (stat.size == 0) {
- ret = -EINVAL;
- goto out;
- }
-
- *buf = vmalloc(stat.size);
- if (!*buf) {
- ret = -ENOMEM;
- goto out;
- }
-
- pos = 0;
- while (pos < stat.size) {
- bytes = kernel_read(f.file, pos, (char *)(*buf) + pos,
- stat.size - pos);
- if (bytes < 0) {
- vfree(*buf);
- ret = bytes;
- goto out;
- }
-
- if (bytes == 0)
- break;
- pos += bytes;
- }
-
- if (pos != stat.size) {
- ret = -EBADF;
- vfree(*buf);
- goto out;
- }
-
- *buf_len = pos;
-out:
- fdput(f);
- 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 -ENOEXEC;
-}
-
-void * __weak arch_kexec_kernel_image_load(struct kimage *image)
-{
- return ERR_PTR(-ENOEXEC);
-}
-
-void __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)
-{
- return -EKEYREJECTED;
-}
-
-/* Apply relocations of type RELA */
-int __weak
-arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
- unsigned int relsec)
-{
- pr_err("RELA relocation unsupported.\n");
- return -ENOEXEC;
-}
-
-/* Apply relocations of type REL */
-int __weak
-arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
- unsigned int relsec)
-{
- 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
- * been loaded into separate segments and have been copied elsewhere.
- */
-static void kimage_file_post_load_cleanup(struct kimage *image)
-{
- struct purgatory_info *pi = &image->purgatory_info;
-
- vfree(image->kernel_buf);
- image->kernel_buf = NULL;
-
- vfree(image->initrd_buf);
- image->initrd_buf = NULL;
-
- kfree(image->cmdline_buf);
- image->cmdline_buf = NULL;
-
- vfree(pi->purgatory_buf);
- pi->purgatory_buf = NULL;
-
- vfree(pi->sechdrs);
- pi->sechdrs = NULL;
-
- /* See if architecture has anything to cleanup post load */
- arch_kimage_file_post_load_cleanup(image);
-
- /*
- * Above call should have called into bootloader to free up
- * any data stored in kimage->image_loader_data. It should
- * be ok now to free it up.
- */
- kfree(image->image_loader_data);
- image->image_loader_data = NULL;
-}
-
-/*
- * In file mode list of segments is prepared by kernel. Copy relevant
- * data from user space, do error checking, prepare segment list
- */
-static int
-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 = 0;
- void *ldata;
-
- ret = copy_file_from_fd(kernel_fd, &image->kernel_buf,
- &image->kernel_buf_len);
- if (ret)
- return ret;
-
- /* Call arch image probe handlers */
- ret = arch_kexec_kernel_image_probe(image, image->kernel_buf,
- image->kernel_buf_len);
-
- 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");
- 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 = copy_file_from_fd(initrd_fd, &image->initrd_buf,
- &image->initrd_buf_len);
- if (ret)
- goto out;
- }
-
- if (cmdline_len) {
- image->cmdline_buf = kzalloc(cmdline_len, GFP_KERNEL);
- if (!image->cmdline_buf) {
- ret = -ENOMEM;
- goto out;
- }
-
- ret = copy_from_user(image->cmdline_buf, cmdline_ptr,
- cmdline_len);
- if (ret) {
- ret = -EFAULT;
- goto out;
- }
-
- image->cmdline_buf_len = cmdline_len;
-
- /* command line should be a string with last byte null */
- if (image->cmdline_buf[cmdline_len - 1] != '\0') {
- ret = -EINVAL;
- goto out;
- }
- }
-
- /* Call arch image load handlers */
- ldata = arch_kexec_kernel_image_load(image);
-
- if (IS_ERR(ldata)) {
- ret = PTR_ERR(ldata);
- goto out;
- }
-
- image->image_loader_data = ldata;
-out:
- /* In case of error, free up all allocated memory in this function */
- if (ret)
- kimage_file_post_load_cleanup(image);
- return ret;
-}
-
-static int
-kimage_file_alloc_init(struct kimage **rimage, int kernel_fd,
- int initrd_fd, const char __user *cmdline_ptr,
- unsigned long cmdline_len, unsigned long flags)
-{
- int ret;
- struct kimage *image;
- bool kexec_on_panic = flags & KEXEC_FILE_ON_CRASH;
-
- image = do_kimage_alloc_init();
- if (!image)
- return -ENOMEM;
-
- image->file_mode = 1;
-
- if (kexec_on_panic) {
- /* Enable special crash kernel control page alloc policy. */
- image->control_page = crashk_res.start;
- image->type = KEXEC_TYPE_CRASH;
- }
-
- ret = kimage_file_prepare_segments(image, kernel_fd, initrd_fd,
- cmdline_ptr, cmdline_len, flags);
- if (ret)
- goto out_free_image;
-
- ret = sanity_check_segment_list(image);
- if (ret)
- goto out_free_post_load_bufs;
-
- ret = -ENOMEM;
- image->control_code_page = kimage_alloc_control_pages(image,
- get_order(KEXEC_CONTROL_PAGE_SIZE));
- if (!image->control_code_page) {
- pr_err("Could not allocate control_code_buffer\n");
- goto out_free_post_load_bufs;
- }
-
- if (!kexec_on_panic) {
- image->swap_page = kimage_alloc_control_pages(image, 0);
- if (!image->swap_page) {
- pr_err("Could not allocate swap buffer\n");
- goto out_free_control_pages;
- }
- }
-
- *rimage = image;
- return 0;
-out_free_control_pages:
- kimage_free_page_list(&image->control_pages);
-out_free_post_load_bufs:
- kimage_file_post_load_cleanup(image);
-out_free_image:
- kfree(image);
- return ret;
-}
-#else /* CONFIG_KEXEC_FILE */
-static inline void kimage_file_post_load_cleanup(struct kimage *image) { }
-#endif /* CONFIG_KEXEC_FILE */
-
-static int kimage_is_destination_range(struct kimage *image,
- unsigned long start,
- unsigned long end)
-{
- unsigned long i;
-
- for (i = 0; i < image->nr_segments; i++) {
- unsigned long mstart, mend;
-
- mstart = image->segment[i].mem;
- mend = mstart + image->segment[i].memsz;
- if ((end > mstart) && (start < mend))
- return 1;
- }
-
- return 0;
-}
-
-static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order)
-{
- struct page *pages;
-
- pages = alloc_pages(gfp_mask, order);
- if (pages) {
- unsigned int count, i;
- pages->mapping = NULL;
- set_page_private(pages, order);
- count = 1 << order;
- for (i = 0; i < count; i++)
- SetPageReserved(pages + i);
- }
-
- return pages;
-}
-
-static void kimage_free_pages(struct page *page)
-{
- unsigned int order, count, i;
-
- order = page_private(page);
- count = 1 << order;
- for (i = 0; i < count; i++)
- ClearPageReserved(page + i);
- __free_pages(page, order);
-}
-
-static void kimage_free_page_list(struct list_head *list)
-{
- struct list_head *pos, *next;
-
- list_for_each_safe(pos, next, list) {
- struct page *page;
-
- page = list_entry(pos, struct page, lru);
- list_del(&page->lru);
- kimage_free_pages(page);
- }
-}
-
-static struct page *kimage_alloc_normal_control_pages(struct kimage *image,
- unsigned int order)
-{
- /* Control pages are special, they are the intermediaries
- * that are needed while we copy the rest of the pages
- * to their final resting place. As such they must
- * not conflict with either the destination addresses
- * or memory the kernel is already using.
- *
- * The only case where we really need more than one of
- * these are for architectures where we cannot disable
- * the MMU and must instead generate an identity mapped
- * page table for all of the memory.
- *
- * At worst this runs in O(N) of the image size.
- */
- struct list_head extra_pages;
- struct page *pages;
- unsigned int count;
-
- count = 1 << order;
- INIT_LIST_HEAD(&extra_pages);
-
- /* Loop while I can allocate a page and the page allocated
- * is a destination page.
- */
- do {
- unsigned long pfn, epfn, addr, eaddr;
-
- pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order);
- if (!pages)
- break;
- pfn = page_to_pfn(pages);
- epfn = pfn + count;
- addr = pfn << PAGE_SHIFT;
- eaddr = epfn << PAGE_SHIFT;
- if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) ||
- kimage_is_destination_range(image, addr, eaddr)) {
- list_add(&pages->lru, &extra_pages);
- pages = NULL;
- }
- } while (!pages);
-
- if (pages) {
- /* Remember the allocated page... */
- list_add(&pages->lru, &image->control_pages);
-
- /* Because the page is already in it's destination
- * location we will never allocate another page at
- * that address. Therefore kimage_alloc_pages
- * will not return it (again) and we don't need
- * to give it an entry in image->segment[].
- */
- }
- /* Deal with the destination pages I have inadvertently allocated.
- *
- * Ideally I would convert multi-page allocations into single
- * page allocations, and add everything to image->dest_pages.
- *
- * For now it is simpler to just free the pages.
- */
- kimage_free_page_list(&extra_pages);
-
- return pages;
-}
-
-static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
- unsigned int order)
-{
- /* Control pages are special, they are the intermediaries
- * that are needed while we copy the rest of the pages
- * to their final resting place. As such they must
- * not conflict with either the destination addresses
- * or memory the kernel is already using.
- *
- * Control pages are also the only pags we must allocate
- * when loading a crash kernel. All of the other pages
- * are specified by the segments and we just memcpy
- * into them directly.
- *
- * The only case where we really need more than one of
- * these are for architectures where we cannot disable
- * the MMU and must instead generate an identity mapped
- * page table for all of the memory.
- *
- * Given the low demand this implements a very simple
- * allocator that finds the first hole of the appropriate
- * size in the reserved memory region, and allocates all
- * of the memory up to and including the hole.
- */
- unsigned long hole_start, hole_end, size;
- struct page *pages;
-
- pages = NULL;
- size = (1 << order) << PAGE_SHIFT;
- hole_start = (image->control_page + (size - 1)) & ~(size - 1);
- hole_end = hole_start + size - 1;
- while (hole_end <= crashk_res.end) {
- unsigned long i;
-
- if (hole_end > KEXEC_CRASH_CONTROL_MEMORY_LIMIT)
- break;
- /* See if I overlap any of the segments */
- for (i = 0; i < image->nr_segments; i++) {
- unsigned long mstart, mend;
-
- mstart = image->segment[i].mem;
- mend = mstart + image->segment[i].memsz - 1;
- if ((hole_end >= mstart) && (hole_start <= mend)) {
- /* Advance the hole to the end of the segment */
- hole_start = (mend + (size - 1)) & ~(size - 1);
- hole_end = hole_start + size - 1;
- break;
- }
- }
- /* If I don't overlap any segments I have found my hole! */
- if (i == image->nr_segments) {
- pages = pfn_to_page(hole_start >> PAGE_SHIFT);
- break;
- }
- }
- if (pages)
- image->control_page = hole_end;
-
- return pages;
-}
-
-
-struct page *kimage_alloc_control_pages(struct kimage *image,
- unsigned int order)
-{
- struct page *pages = NULL;
-
- switch (image->type) {
- case KEXEC_TYPE_DEFAULT:
- pages = kimage_alloc_normal_control_pages(image, order);
- break;
- case KEXEC_TYPE_CRASH:
- pages = kimage_alloc_crash_control_pages(image, order);
- break;
- }
-
- return pages;
-}
-
-static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
-{
- if (*image->entry != 0)
- image->entry++;
-
- if (image->entry == image->last_entry) {
- kimage_entry_t *ind_page;
- struct page *page;
-
- page = kimage_alloc_page(image, GFP_KERNEL, KIMAGE_NO_DEST);
- if (!page)
- return -ENOMEM;
-
- ind_page = page_address(page);
- *image->entry = virt_to_phys(ind_page) | IND_INDIRECTION;
- image->entry = ind_page;
- image->last_entry = ind_page +
- ((PAGE_SIZE/sizeof(kimage_entry_t)) - 1);
- }
- *image->entry = entry;
- image->entry++;
- *image->entry = 0;
-
- return 0;
-}
-
-static int kimage_set_destination(struct kimage *image,
- unsigned long destination)
-{
- int result;
-
- destination &= PAGE_MASK;
- result = kimage_add_entry(image, destination | IND_DESTINATION);
-
- return result;
-}
-
-
-static int kimage_add_page(struct kimage *image, unsigned long page)
-{
- int result;
-
- page &= PAGE_MASK;
- result = kimage_add_entry(image, page | IND_SOURCE);
-
- return result;
-}
-
-
-static void kimage_free_extra_pages(struct kimage *image)
-{
- /* Walk through and free any extra destination pages I may have */
- kimage_free_page_list(&image->dest_pages);
-
- /* Walk through and free any unusable pages I have cached */
- kimage_free_page_list(&image->unusable_pages);
-
-}
-static void kimage_terminate(struct kimage *image)
-{
- if (*image->entry != 0)
- image->entry++;
-
- *image->entry = IND_DONE;
-}
-
-#define for_each_kimage_entry(image, ptr, entry) \
- for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \
- ptr = (entry & IND_INDIRECTION) ? \
- phys_to_virt((entry & PAGE_MASK)) : ptr + 1)
-
-static void kimage_free_entry(kimage_entry_t entry)
-{
- struct page *page;
-
- page = pfn_to_page(entry >> PAGE_SHIFT);
- kimage_free_pages(page);
-}
-
-static void kimage_free(struct kimage *image)
-{
- kimage_entry_t *ptr, entry;
- kimage_entry_t ind = 0;
-
- if (!image)
- return;
-
- kimage_free_extra_pages(image);
- for_each_kimage_entry(image, ptr, entry) {
- if (entry & IND_INDIRECTION) {
- /* Free the previous indirection page */
- if (ind & IND_INDIRECTION)
- kimage_free_entry(ind);
- /* Save this indirection page until we are
- * done with it.
- */
- ind = entry;
- } else if (entry & IND_SOURCE)
- kimage_free_entry(entry);
- }
- /* Free the final indirection page */
- if (ind & IND_INDIRECTION)
- kimage_free_entry(ind);
-
- /* Handle any machine specific cleanup */
- machine_kexec_cleanup(image);
-
- /* Free the kexec control pages... */
- kimage_free_page_list(&image->control_pages);
-
- /*
- * Free up any temporary buffers allocated. This might hit if
- * error occurred much later after buffer allocation.
- */
- if (image->file_mode)
- kimage_file_post_load_cleanup(image);
-
- kfree(image);
-}
-
-static kimage_entry_t *kimage_dst_used(struct kimage *image,
- unsigned long page)
-{
- kimage_entry_t *ptr, entry;
- unsigned long destination = 0;
-
- for_each_kimage_entry(image, ptr, entry) {
- if (entry & IND_DESTINATION)
- destination = entry & PAGE_MASK;
- else if (entry & IND_SOURCE) {
- if (page == destination)
- return ptr;
- destination += PAGE_SIZE;
- }
- }
-
- return NULL;
-}
-
-static struct page *kimage_alloc_page(struct kimage *image,
- gfp_t gfp_mask,
- unsigned long destination)
-{
- /*
- * Here we implement safeguards to ensure that a source page
- * is not copied to its destination page before the data on
- * the destination page is no longer useful.
- *
- * To do this we maintain the invariant that a source page is
- * either its own destination page, or it is not a
- * destination page at all.
- *
- * That is slightly stronger than required, but the proof
- * that no problems will