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/fs/coredump.c | 349 +++++++++++++++++++++++++++++++++++++++++++++++++++++----
1 files changed, 320 insertions(+), 29 deletions(-)
diff --git a/kernel/fs/coredump.c b/kernel/fs/coredump.c
index 6250eaf..7c5edad 100644
--- a/kernel/fs/coredump.c
+++ b/kernel/fs/coredump.c
@@ -7,6 +7,7 @@
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/swap.h>
+#include <linux/ctype.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/pagemap.h>
@@ -40,6 +41,7 @@
#include <linux/fs.h>
#include <linux/path.h>
#include <linux/timekeeping.h>
+#include <linux/elf.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
@@ -152,10 +154,10 @@
return ret;
}
-static int cn_print_exe_file(struct core_name *cn)
+static int cn_print_exe_file(struct core_name *cn, bool name_only)
{
struct file *exe_file;
- char *pathbuf, *path;
+ char *pathbuf, *path, *ptr;
int ret;
exe_file = get_mm_exe_file(current->mm);
@@ -174,6 +176,11 @@
goto free_buf;
}
+ if (name_only) {
+ ptr = strrchr(path, '/');
+ if (ptr)
+ path = ptr + 1;
+ }
ret = cn_esc_printf(cn, "%s", path);
free_buf:
@@ -187,11 +194,13 @@
* name into corename, which must have space for at least
* CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
*/
-static int format_corename(struct core_name *cn, struct coredump_params *cprm)
+static int format_corename(struct core_name *cn, struct coredump_params *cprm,
+ size_t **argv, int *argc)
{
const struct cred *cred = current_cred();
const char *pat_ptr = core_pattern;
int ispipe = (*pat_ptr == '|');
+ bool was_space = false;
int pid_in_pattern = 0;
int err = 0;
@@ -201,12 +210,38 @@
return -ENOMEM;
cn->corename[0] = '\0';
- if (ispipe)
+ if (ispipe) {
+ int argvs = sizeof(core_pattern) / 2;
+ (*argv) = kmalloc_array(argvs, sizeof(**argv), GFP_KERNEL);
+ if (!(*argv))
+ return -ENOMEM;
+ (*argv)[(*argc)++] = 0;
++pat_ptr;
+ if (!(*pat_ptr))
+ return -ENOMEM;
+ }
/* Repeat as long as we have more pattern to process and more output
space */
while (*pat_ptr) {
+ /*
+ * Split on spaces before doing template expansion so that
+ * %e and %E don't get split if they have spaces in them
+ */
+ if (ispipe) {
+ if (isspace(*pat_ptr)) {
+ if (cn->used != 0)
+ was_space = true;
+ pat_ptr++;
+ continue;
+ } else if (was_space) {
+ was_space = false;
+ err = cn_printf(cn, "%c", '\0');
+ if (err)
+ return err;
+ (*argv)[(*argc)++] = cn->used;
+ }
+ }
if (*pat_ptr != '%') {
err = cn_printf(cn, "%c", *pat_ptr++);
} else {
@@ -273,12 +308,16 @@
utsname()->nodename);
up_read(&uts_sem);
break;
- /* executable */
+ /* executable, could be changed by prctl PR_SET_NAME etc */
case 'e':
err = cn_esc_printf(cn, "%s", current->comm);
break;
+ /* file name of executable */
+ case 'f':
+ err = cn_print_exe_file(cn, true);
+ break;
case 'E':
- err = cn_print_exe_file(cn);
+ err = cn_print_exe_file(cn, false);
break;
/* core limit size */
case 'c':
@@ -365,7 +404,7 @@
* of ->siglock provides a memory barrier.
*
* do_exit:
- * The caller holds mm->mmap_sem. This means that the task which
+ * The caller holds mm->mmap_lock. This means that the task which
* uses this mm can't pass exit_mm(), so it can't exit or clear
* its ->mm.
*
@@ -373,7 +412,7 @@
* It does list_replace_rcu(&leader->tasks, ¤t->tasks),
* we must see either old or new leader, this does not matter.
* However, it can change p->sighand, so lock_task_sighand(p)
- * must be used. Since p->mm != NULL and we hold ->mmap_sem
+ * must be used. Since p->mm != NULL and we hold ->mmap_lock
* it can't fail.
*
* Note also that "g" can be the old leader with ->mm == NULL
@@ -417,12 +456,12 @@
core_state->dumper.task = tsk;
core_state->dumper.next = NULL;
- if (down_write_killable(&mm->mmap_sem))
+ if (mmap_write_lock_killable(mm))
return -EINTR;
if (!mm->core_state)
core_waiters = zap_threads(tsk, mm, core_state, exit_code);
- up_write(&mm->mmap_sem);
+ mmap_write_unlock(mm);
if (core_waiters > 0) {
struct core_thread *ptr;
@@ -481,7 +520,7 @@
* but then we need to teach dump_write() to restart and clear
* TIF_SIGPENDING.
*/
- return signal_pending(current);
+ return fatal_signal_pending(current) || freezing(current);
}
static void wait_for_dump_helpers(struct file *file)
@@ -491,7 +530,7 @@
pipe_lock(pipe);
pipe->readers++;
pipe->writers--;
- wake_up_interruptible_sync(&pipe->wait);
+ wake_up_interruptible_sync(&pipe->rd_wait);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
pipe_unlock(pipe);
@@ -499,7 +538,7 @@
* We actually want wait_event_freezable() but then we need
* to clear TIF_SIGPENDING and improve dump_interrupted().
*/
- wait_event_interruptible(pipe->wait, pipe->readers == 1);
+ wait_event_interruptible(pipe->rd_wait, pipe->readers == 1);
pipe_lock(pipe);
pipe->readers--;
@@ -536,7 +575,7 @@
return err;
}
-void do_coredump(const siginfo_t *siginfo)
+void do_coredump(const kernel_siginfo_t *siginfo)
{
struct core_state core_state;
struct core_name cn;
@@ -546,6 +585,8 @@
struct cred *cred;
int retval = 0;
int ispipe;
+ size_t *argv = NULL;
+ int argc = 0;
struct files_struct *displaced;
/* require nonrelative corefile path and be extra careful */
bool need_suid_safe = false;
@@ -592,9 +633,10 @@
old_cred = override_creds(cred);
- ispipe = format_corename(&cn, &cprm);
+ ispipe = format_corename(&cn, &cprm, &argv, &argc);
if (ispipe) {
+ int argi;
int dump_count;
char **helper_argv;
struct subprocess_info *sub_info;
@@ -637,12 +679,16 @@
goto fail_dropcount;
}
- helper_argv = argv_split(GFP_KERNEL, cn.corename, NULL);
+ helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv),
+ GFP_KERNEL);
if (!helper_argv) {
printk(KERN_WARNING "%s failed to allocate memory\n",
__func__);
goto fail_dropcount;
}
+ for (argi = 0; argi < argc; argi++)
+ helper_argv[argi] = cn.corename + argv[argi];
+ helper_argv[argi] = NULL;
retval = -ENOMEM;
sub_info = call_usermodehelper_setup(helper_argv[0],
@@ -652,7 +698,7 @@
retval = call_usermodehelper_exec(sub_info,
UMH_WAIT_EXEC);
- argv_free(helper_argv);
+ kfree(helper_argv);
if (retval) {
printk(KERN_INFO "Core dump to |%s pipe failed\n",
cn.corename);
@@ -742,7 +788,7 @@
goto close_fail;
if (!(cprm.file->f_mode & FMODE_CAN_WRITE))
goto close_fail;
- if (do_truncate2(cprm.file->f_path.mnt, cprm.file->f_path.dentry, 0, 0, cprm.file))
+ if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file))
goto close_fail;
}
@@ -774,6 +820,7 @@
if (ispipe)
atomic_dec(&core_dump_count);
fail_unlock:
+ kfree(argv);
kfree(cn.corename);
coredump_finish(mm, core_dumped);
revert_creds(old_cred);
@@ -795,17 +842,17 @@
ssize_t n;
if (cprm->written + nr > cprm->limit)
return 0;
- while (nr) {
- if (dump_interrupted())
- return 0;
- n = __kernel_write(file, addr, nr, &pos);
- if (n <= 0)
- return 0;
- file->f_pos = pos;
- cprm->written += n;
- cprm->pos += n;
- nr -= n;
- }
+
+
+ if (dump_interrupted())
+ return 0;
+ n = __kernel_write(file, addr, nr, &pos);
+ if (n != nr)
+ return 0;
+ file->f_pos = pos;
+ cprm->written += n;
+ cprm->pos += n;
+
return 1;
}
EXPORT_SYMBOL(dump_emit);
@@ -830,6 +877,40 @@
}
}
EXPORT_SYMBOL(dump_skip);
+
+#ifdef CONFIG_ELF_CORE
+int dump_user_range(struct coredump_params *cprm, unsigned long start,
+ unsigned long len)
+{
+ unsigned long addr;
+
+ for (addr = start; addr < start + len; addr += PAGE_SIZE) {
+ struct page *page;
+ int stop;
+
+ /*
+ * To avoid having to allocate page tables for virtual address
+ * ranges that have never been used yet, and also to make it
+ * easy to generate sparse core files, use a helper that returns
+ * NULL when encountering an empty page table entry that would
+ * otherwise have been filled with the zero page.
+ */
+ page = get_dump_page(addr);
+ if (page) {
+ void *kaddr = kmap(page);
+
+ stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
+ kunmap(page);
+ put_user_page(page);
+ } else {
+ stop = !dump_skip(cprm, PAGE_SIZE);
+ }
+ if (stop)
+ return 0;
+ }
+ return 1;
+}
+#endif
int dump_align(struct coredump_params *cprm, int align)
{
@@ -857,3 +938,213 @@
}
}
EXPORT_SYMBOL(dump_truncate);
+
+/*
+ * The purpose of always_dump_vma() is to make sure that special kernel mappings
+ * that are useful for post-mortem analysis are included in every core dump.
+ * In that way we ensure that the core dump is fully interpretable later
+ * without matching up the same kernel and hardware config to see what PC values
+ * meant. These special mappings include - vDSO, vsyscall, and other
+ * architecture specific mappings
+ */
+static bool always_dump_vma(struct vm_area_struct *vma)
+{
+ /* Any vsyscall mappings? */
+ if (vma == get_gate_vma(vma->vm_mm))
+ return true;
+
+ /*
+ * Assume that all vmas with a .name op should always be dumped.
+ * If this changes, a new vm_ops field can easily be added.
+ */
+ if (vma->vm_ops && vma->vm_ops->name && vma->vm_ops->name(vma))
+ return true;
+
+ /*
+ * arch_vma_name() returns non-NULL for special architecture mappings,
+ * such as vDSO sections.
+ */
+ if (arch_vma_name(vma))
+ return true;
+
+ return false;
+}
+
+#define DUMP_SIZE_MAYBE_ELFHDR_PLACEHOLDER 1
+
+/*
+ * Decide how much of @vma's contents should be included in a core dump.
+ */
+static unsigned long vma_dump_size(struct vm_area_struct *vma,
+ unsigned long mm_flags)
+{
+#define FILTER(type) (mm_flags & (1UL << MMF_DUMP_##type))
+
+ /* always dump the vdso and vsyscall sections */
+ if (always_dump_vma(vma))
+ goto whole;
+
+ if (vma->vm_flags & VM_DONTDUMP)
+ return 0;
+
+ /* support for DAX */
+ if (vma_is_dax(vma)) {
+ if ((vma->vm_flags & VM_SHARED) && FILTER(DAX_SHARED))
+ goto whole;
+ if (!(vma->vm_flags & VM_SHARED) && FILTER(DAX_PRIVATE))
+ goto whole;
+ return 0;
+ }
+
+ /* Hugetlb memory check */
+ if (is_vm_hugetlb_page(vma)) {
+ if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
+ goto whole;
+ if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
+ goto whole;
+ return 0;
+ }
+
+ /* Do not dump I/O mapped devices or special mappings */
+ if (vma->vm_flags & VM_IO)
+ return 0;
+
+ /* By default, dump shared memory if mapped from an anonymous file. */
+ if (vma->vm_flags & VM_SHARED) {
+ if (file_inode(vma->vm_file)->i_nlink == 0 ?
+ FILTER(ANON_SHARED) : FILTER(MAPPED_SHARED))
+ goto whole;
+ return 0;
+ }
+
+ /* Dump segments that have been written to. */
+ if ((!IS_ENABLED(CONFIG_MMU) || vma->anon_vma) && FILTER(ANON_PRIVATE))
+ goto whole;
+ if (vma->vm_file == NULL)
+ return 0;
+
+ if (FILTER(MAPPED_PRIVATE))
+ goto whole;
+
+ /*
+ * If this is the beginning of an executable file mapping,
+ * dump the first page to aid in determining what was mapped here.
+ */
+ if (FILTER(ELF_HEADERS) &&
+ vma->vm_pgoff == 0 && (vma->vm_flags & VM_READ)) {
+ if ((READ_ONCE(file_inode(vma->vm_file)->i_mode) & 0111) != 0)
+ return PAGE_SIZE;
+
+ /*
+ * ELF libraries aren't always executable.
+ * We'll want to check whether the mapping starts with the ELF
+ * magic, but not now - we're holding the mmap lock,
+ * so copy_from_user() doesn't work here.
+ * Use a placeholder instead, and fix it up later in
+ * dump_vma_snapshot().
+ */
+ return DUMP_SIZE_MAYBE_ELFHDR_PLACEHOLDER;
+ }
+
+#undef FILTER
+
+ return 0;
+
+whole:
+ return vma->vm_end - vma->vm_start;
+}
+
+static struct vm_area_struct *first_vma(struct task_struct *tsk,
+ struct vm_area_struct *gate_vma)
+{
+ struct vm_area_struct *ret = tsk->mm->mmap;
+
+ if (ret)
+ return ret;
+ return gate_vma;
+}
+
+/*
+ * Helper function for iterating across a vma list. It ensures that the caller
+ * will visit `gate_vma' prior to terminating the search.
+ */
+static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma,
+ struct vm_area_struct *gate_vma)
+{
+ struct vm_area_struct *ret;
+
+ ret = this_vma->vm_next;
+ if (ret)
+ return ret;
+ if (this_vma == gate_vma)
+ return NULL;
+ return gate_vma;
+}
+
+/*
+ * Under the mmap_lock, take a snapshot of relevant information about the task's
+ * VMAs.
+ */
+int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count,
+ struct core_vma_metadata **vma_meta,
+ size_t *vma_data_size_ptr)
+{
+ struct vm_area_struct *vma, *gate_vma;
+ struct mm_struct *mm = current->mm;
+ int i;
+ size_t vma_data_size = 0;
+
+ /*
+ * Once the stack expansion code is fixed to not change VMA bounds
+ * under mmap_lock in read mode, this can be changed to take the
+ * mmap_lock in read mode.
+ */
+ if (mmap_write_lock_killable(mm))
+ return -EINTR;
+
+ gate_vma = get_gate_vma(mm);
+ *vma_count = mm->map_count + (gate_vma ? 1 : 0);
+
+ *vma_meta = kvmalloc_array(*vma_count, sizeof(**vma_meta), GFP_KERNEL);
+ if (!*vma_meta) {
+ mmap_write_unlock(mm);
+ return -ENOMEM;
+ }
+
+ for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
+ vma = next_vma(vma, gate_vma), i++) {
+ struct core_vma_metadata *m = (*vma_meta) + i;
+
+ m->start = vma->vm_start;
+ m->end = vma->vm_end;
+ m->flags = vma->vm_flags;
+ m->dump_size = vma_dump_size(vma, cprm->mm_flags);
+ }
+
+ mmap_write_unlock(mm);
+
+ if (WARN_ON(i != *vma_count)) {
+ kvfree(*vma_meta);
+ return -EFAULT;
+ }
+
+ for (i = 0; i < *vma_count; i++) {
+ struct core_vma_metadata *m = (*vma_meta) + i;
+
+ if (m->dump_size == DUMP_SIZE_MAYBE_ELFHDR_PLACEHOLDER) {
+ char elfmag[SELFMAG];
+
+ if (copy_from_user(elfmag, (void __user *)m->start, SELFMAG) ||
+ memcmp(elfmag, ELFMAG, SELFMAG) != 0) {
+ m->dump_size = 0;
+ } else {
+ m->dump_size = PAGE_SIZE;
+ }
+ }
+
+ vma_data_size += m->dump_size;
+ }
+
+ *vma_data_size_ptr = vma_data_size;
+ return 0;
+}
--
Gitblit v1.6.2