read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
{
char *buf = file->private_data;
- ssize_t acc = 0;
- size_t size, tsz;
- size_t elf_buflen;
+ size_t phdrs_offset, notes_offset, data_offset;
+ size_t phdrs_len, notes_len;
+ struct kcore_list *m;
+ size_t tsz;
int nphdr;
unsigned long start;
+ size_t orig_buflen = buflen;
+ int ret = 0;
- read_lock(&kclist_lock);
- size = get_kcore_size(&nphdr, &elf_buflen);
+ down_read(&kclist_lock);
+
+ get_kcore_size(&nphdr, &phdrs_len, ¬es_len, &data_offset);
+ phdrs_offset = sizeof(struct elfhdr);
+ notes_offset = phdrs_offset + phdrs_len;
+
+ /* ELF file header. */
+ if (buflen && *fpos < sizeof(struct elfhdr)) {
+ struct elfhdr ehdr = {
+ .e_ident = {
+ [EI_MAG0] = ELFMAG0,
+ [EI_MAG1] = ELFMAG1,
+ [EI_MAG2] = ELFMAG2,
+ [EI_MAG3] = ELFMAG3,
+ [EI_CLASS] = ELF_CLASS,
+ [EI_DATA] = ELF_DATA,
+ [EI_VERSION] = EV_CURRENT,
+ [EI_OSABI] = ELF_OSABI,
+ },
+ .e_type = ET_CORE,
+ .e_machine = ELF_ARCH,
+ .e_version = EV_CURRENT,
+ .e_phoff = sizeof(struct elfhdr),
+ .e_flags = ELF_CORE_EFLAGS,
+ .e_ehsize = sizeof(struct elfhdr),
+ .e_phentsize = sizeof(struct elf_phdr),
+ .e_phnum = nphdr,
+ };
+
+ tsz = min_t(size_t, buflen, sizeof(struct elfhdr) - *fpos);
+ if (copy_to_user(buffer, (char *)&ehdr + *fpos, tsz)) {
+ ret = -EFAULT;
+ goto out;
+ }
- if (buflen == 0 || *fpos >= size) {
- read_unlock(&kclist_lock);
- return 0;
+ buffer += tsz;
+ buflen -= tsz;
+ *fpos += tsz;
}
- /* trim buflen to not go beyond EOF */
- if (buflen > size - *fpos)
- buflen = size - *fpos;
-
- /* construct an ELF core header if we'll need some of it */
- if (*fpos < elf_buflen) {
- char * elf_buf;
-
- tsz = elf_buflen - *fpos;
- if (buflen < tsz)
- tsz = buflen;
- elf_buf = kzalloc(elf_buflen, GFP_ATOMIC);
- if (!elf_buf) {
- read_unlock(&kclist_lock);
- return -ENOMEM;
+ /* ELF program headers. */
+ if (buflen && *fpos < phdrs_offset + phdrs_len) {
+ struct elf_phdr *phdrs, *phdr;
+
+ phdrs = kzalloc(phdrs_len, GFP_KERNEL);
+ if (!phdrs) {
+ ret = -ENOMEM;
+ goto out;
}
- elf_kcore_store_hdr(elf_buf, nphdr, elf_buflen);
- read_unlock(&kclist_lock);
- if (copy_to_user(buffer, elf_buf + *fpos, tsz)) {
- kfree(elf_buf);
- return -EFAULT;
+
+ phdrs[0].p_type = PT_NOTE;
+ phdrs[0].p_offset = notes_offset;
+ phdrs[0].p_filesz = notes_len;
+
+ phdr = &phdrs[1];
+ list_for_each_entry(m, &kclist_head, list) {
+ phdr->p_type = PT_LOAD;
+ phdr->p_flags = PF_R | PF_W | PF_X;
+ phdr->p_offset = kc_vaddr_to_offset(m->addr) + data_offset;
- phdr->p_vaddr = (size_t)m->addr;
- if (m->type == KCORE_RAM)
++ if (m->type == KCORE_REMAP)
++ phdr->p_vaddr = (size_t)m->vaddr;
++ else
++ phdr->p_vaddr = (size_t)m->addr;
++ if (m->type == KCORE_RAM || m->type == KCORE_REMAP)
+ phdr->p_paddr = __pa(m->addr);
+ else if (m->type == KCORE_TEXT)
+ phdr->p_paddr = __pa_symbol(m->addr);
+ else
+ phdr->p_paddr = (elf_addr_t)-1;
+ phdr->p_filesz = phdr->p_memsz = m->size;
+ phdr->p_align = PAGE_SIZE;
+ phdr++;
}
- kfree(elf_buf);
+
+ tsz = min_t(size_t, buflen, phdrs_offset + phdrs_len - *fpos);
+ if (copy_to_user(buffer, (char *)phdrs + *fpos - phdrs_offset,
+ tsz)) {
+ kfree(phdrs);
+ ret = -EFAULT;
+ goto out;
+ }
+ kfree(phdrs);
+
+ buffer += tsz;
buflen -= tsz;
*fpos += tsz;
- buffer += tsz;
- acc += tsz;
+ }
+
+ /* ELF note segment. */
+ if (buflen && *fpos < notes_offset + notes_len) {
+ struct elf_prstatus prstatus = {};
+ struct elf_prpsinfo prpsinfo = {
+ .pr_sname = 'R',
+ .pr_fname = "vmlinux",
+ };
+ char *notes;
+ size_t i = 0;
+
+ strlcpy(prpsinfo.pr_psargs, saved_command_line,
+ sizeof(prpsinfo.pr_psargs));
+
+ notes = kzalloc(notes_len, GFP_KERNEL);
+ if (!notes) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ append_kcore_note(notes, &i, CORE_STR, NT_PRSTATUS, &prstatus,
+ sizeof(prstatus));
+ append_kcore_note(notes, &i, CORE_STR, NT_PRPSINFO, &prpsinfo,
+ sizeof(prpsinfo));
+ append_kcore_note(notes, &i, CORE_STR, NT_TASKSTRUCT, current,
+ arch_task_struct_size);
+ /*
+ * vmcoreinfo_size is mostly constant after init time, but it
+ * can be changed by crash_save_vmcoreinfo(). Racing here with a
+ * panic on another CPU before the machine goes down is insanely
+ * unlikely, but it's better to not leave potential buffer
+ * overflows lying around, regardless.
+ */
+ append_kcore_note(notes, &i, VMCOREINFO_NOTE_NAME, 0,
+ vmcoreinfo_data,
+ min(vmcoreinfo_size, notes_len - i));
+
+ tsz = min_t(size_t, buflen, notes_offset + notes_len - *fpos);
+ if (copy_to_user(buffer, notes + *fpos - notes_offset, tsz)) {
+ kfree(notes);
+ ret = -EFAULT;
+ goto out;
+ }
+ kfree(notes);
- /* leave now if filled buffer already */
- if (buflen == 0)
- return acc;
- } else
- read_unlock(&kclist_lock);
+ buffer += tsz;
+ buflen -= tsz;
+ *fpos += tsz;
+ }
/*
* Check to see if our file offset matches with any of