#include <linux/fcntl.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
+#include <linux/security.h>
#include <linux/highmem.h>
#include <linux/highuid.h>
#include <linux/personality.h>
#include <linux/ptrace.h>
#include <linux/init.h>
-#include <linux/smp_lock.h>
#include <linux/elf.h>
#include <linux/elf-fdpic.h>
#include <linux/elfcore.h>
+#include <linux/coredump.h>
#include <asm/uaccess.h>
#include <asm/param.h>
MODULE_LICENSE("GPL");
-static int load_elf_fdpic_binary(struct linux_binprm *, struct pt_regs *);
+static int load_elf_fdpic_binary(struct linux_binprm *);
static int elf_fdpic_fetch_phdrs(struct elf_fdpic_params *, struct file *);
static int elf_fdpic_map_file(struct elf_fdpic_params *, struct file *,
struct mm_struct *, const char *);
static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *,
struct file *, struct mm_struct *);
-#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
-static int elf_fdpic_core_dump(long, struct pt_regs *, struct file *);
+#ifdef CONFIG_ELF_CORE
+static int elf_fdpic_core_dump(struct coredump_params *cprm);
#endif
static struct linux_binfmt elf_fdpic_format = {
.module = THIS_MODULE,
.load_binary = load_elf_fdpic_binary,
-#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
+#ifdef CONFIG_ELF_CORE
.core_dump = elf_fdpic_core_dump,
#endif
.min_coredump = ELF_EXEC_PAGESIZE,
static int __init init_elf_fdpic_binfmt(void)
{
- return register_binfmt(&elf_fdpic_format);
+ register_binfmt(&elf_fdpic_format);
+ return 0;
}
static void __exit exit_elf_fdpic_binfmt(void)
retval = kernel_read(file, params->hdr.e_phoff,
(char *) params->phdrs, size);
- if (retval < 0)
- return retval;
+ if (unlikely(retval != size))
+ return retval < 0 ? retval : -ENOEXEC;
/* determine stack size for this binary */
phdr = params->phdrs;
/*
* load an fdpic binary into various bits of memory
*/
-static int load_elf_fdpic_binary(struct linux_binprm *bprm,
- struct pt_regs *regs)
+static int load_elf_fdpic_binary(struct linux_binprm *bprm)
{
struct elf_fdpic_params exec_params, interp_params;
+ struct pt_regs *regs = current_pt_regs();
struct elf_phdr *phdr;
unsigned long stack_size, entryaddr;
-#ifndef CONFIG_MMU
- unsigned long fullsize;
-#endif
#ifdef ELF_FDPIC_PLAT_INIT
unsigned long dynaddr;
+#endif
+#ifndef CONFIG_MMU
+ unsigned long stack_prot;
#endif
struct file *interpreter = NULL; /* to shut gcc up */
char *interpreter_name = NULL;
phdr->p_offset,
interpreter_name,
phdr->p_filesz);
- if (retval < 0)
+ if (unlikely(retval != phdr->p_filesz)) {
+ if (retval >= 0)
+ retval = -ENOEXEC;
goto error;
+ }
retval = -ENOENT;
if (interpreter_name[phdr->p_filesz - 1] != '\0')
* mm->dumpable = 0 regardless of the interpreter's
* permissions.
*/
- if (file_permission(interpreter, MAY_READ) < 0)
- bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP;
+ would_dump(bprm, interpreter);
retval = kernel_read(interpreter, 0, bprm->buf,
BINPRM_BUF_SIZE);
- if (retval < 0)
+ if (unlikely(retval != BINPRM_BUF_SIZE)) {
+ if (retval >= 0)
+ retval = -ENOEXEC;
goto error;
+ }
interp_params.hdr = *((struct elfhdr *) bprm->buf);
break;
}
stack_size = exec_params.stack_size;
- if (stack_size < interp_params.stack_size)
- stack_size = interp_params.stack_size;
-
if (exec_params.flags & ELF_FDPIC_FLAG_EXEC_STACK)
executable_stack = EXSTACK_ENABLE_X;
else if (exec_params.flags & ELF_FDPIC_FLAG_NOEXEC_STACK)
executable_stack = EXSTACK_DISABLE_X;
- else if (interp_params.flags & ELF_FDPIC_FLAG_EXEC_STACK)
- executable_stack = EXSTACK_ENABLE_X;
- else if (interp_params.flags & ELF_FDPIC_FLAG_NOEXEC_STACK)
- executable_stack = EXSTACK_DISABLE_X;
else
executable_stack = EXSTACK_DEFAULT;
+ if (stack_size == 0) {
+ stack_size = interp_params.stack_size;
+ if (interp_params.flags & ELF_FDPIC_FLAG_EXEC_STACK)
+ executable_stack = EXSTACK_ENABLE_X;
+ else if (interp_params.flags & ELF_FDPIC_FLAG_NOEXEC_STACK)
+ executable_stack = EXSTACK_DISABLE_X;
+ else
+ executable_stack = EXSTACK_DEFAULT;
+ }
+
retval = -ENOEXEC;
if (stack_size == 0)
goto error;
* defunct, deceased, etc. after this point we have to exit via
* error_kill */
set_personality(PER_LINUX_FDPIC);
+ if (elf_read_implies_exec(&exec_params.hdr, executable_stack))
+ current->personality |= READ_IMPLIES_EXEC;
+
+ setup_new_exec(bprm);
+
set_binfmt(&elf_fdpic_format);
current->mm->start_code = 0;
current->mm->context.exec_fdpic_loadmap = 0;
current->mm->context.interp_fdpic_loadmap = 0;
- current->flags &= ~PF_FORKNOEXEC;
-
#ifdef CONFIG_MMU
elf_fdpic_arch_lay_out_mm(&exec_params,
&interp_params,
if (stack_size < PAGE_SIZE * 2)
stack_size = PAGE_SIZE * 2;
- down_write(¤t->mm->mmap_sem);
- current->mm->start_brk = do_mmap(NULL, 0, stack_size,
- PROT_READ | PROT_WRITE | PROT_EXEC,
- MAP_PRIVATE | MAP_ANONYMOUS | MAP_GROWSDOWN,
+ stack_prot = PROT_READ | PROT_WRITE;
+ if (executable_stack == EXSTACK_ENABLE_X ||
+ (executable_stack == EXSTACK_DEFAULT && VM_STACK_FLAGS & VM_EXEC))
+ stack_prot |= PROT_EXEC;
+
+ current->mm->start_brk = vm_mmap(NULL, 0, stack_size, stack_prot,
+ MAP_PRIVATE | MAP_ANONYMOUS |
+ MAP_UNINITIALIZED | MAP_GROWSDOWN,
0);
if (IS_ERR_VALUE(current->mm->start_brk)) {
- up_write(¤t->mm->mmap_sem);
retval = current->mm->start_brk;
current->mm->start_brk = 0;
goto error_kill;
}
- /* expand the stack mapping to use up the entire allocation granule */
- fullsize = ksize((char *) current->mm->start_brk);
- if (!IS_ERR_VALUE(do_mremap(current->mm->start_brk, stack_size,
- fullsize, 0, 0)))
- stack_size = fullsize;
- up_write(¤t->mm->mmap_sem);
-
current->mm->brk = current->mm->start_brk;
current->mm->context.end_brk = current->mm->start_brk;
current->mm->context.end_brk +=
current->mm->start_stack = current->mm->start_brk + stack_size;
#endif
- compute_creds(bprm);
- current->flags &= ~PF_FORKNOEXEC;
+ install_exec_creds(bprm);
if (create_elf_fdpic_tables(bprm, current->mm,
&exec_params, &interp_params) < 0)
goto error_kill;
entryaddr = interp_params.entry_addr ?: exec_params.entry_addr;
start_thread(regs, entryaddr, current->mm->start_stack);
- if (unlikely(current->ptrace & PT_PTRACED)) {
- if (current->ptrace & PT_TRACE_EXEC)
- ptrace_notify((PTRACE_EVENT_EXEC << 8) | SIGTRAP);
- else
- send_sig(SIGTRAP, current, 0);
- }
-
retval = 0;
error:
}
/*****************************************************************************/
+
+#ifndef ELF_BASE_PLATFORM
/*
- * present useful information to the program
+ * AT_BASE_PLATFORM indicates the "real" hardware/microarchitecture.
+ * If the arch defines ELF_BASE_PLATFORM (in asm/elf.h), the value
+ * will be copied to the user stack in the same manner as AT_PLATFORM.
+ */
+#define ELF_BASE_PLATFORM NULL
+#endif
+
+/*
+ * present useful information to the program by shovelling it onto the new
+ * process's stack
*/
static int create_elf_fdpic_tables(struct linux_binprm *bprm,
struct mm_struct *mm,
struct elf_fdpic_params *exec_params,
struct elf_fdpic_params *interp_params)
{
+ const struct cred *cred = current_cred();
unsigned long sp, csp, nitems;
elf_caddr_t __user *argv, *envp;
size_t platform_len = 0, len;
- char *k_platform;
- char __user *u_platform, *p;
- long hwcap;
+ char *k_platform, *k_base_platform;
+ char __user *u_platform, *u_base_platform, *p;
int loop;
+ int nr; /* reset for each csp adjustment */
- /* we're going to shovel a whole load of stuff onto the stack */
#ifdef CONFIG_MMU
- sp = bprm->p;
+ /* In some cases (e.g. Hyper-Threading), we want to avoid L1 evictions
+ * by the processes running on the same package. One thing we can do is
+ * to shuffle the initial stack for them, so we give the architecture
+ * an opportunity to do so here.
+ */
+ sp = arch_align_stack(bprm->p);
#else
sp = mm->start_stack;
return -EFAULT;
#endif
- /* get hold of platform and hardware capabilities masks for the machine
- * we are running on. In some cases (Sparc), this info is impossible
- * to get, in others (i386) it is merely difficult.
+ /*
+ * If this architecture has a platform capability string, copy it
+ * to userspace. In some cases (Sparc), this info is impossible
+ * for userspace to get any other way, in others (i386) it is
+ * merely difficult.
*/
- hwcap = ELF_HWCAP;
k_platform = ELF_PLATFORM;
u_platform = NULL;
return -EFAULT;
}
-#if defined(__i386__) && defined(CONFIG_SMP)
- /* in some cases (e.g. Hyper-Threading), we want to avoid L1 evictions
- * by the processes running on the same package. One thing we can do is
- * to shuffle the initial stack for them.
- *
- * the conditionals here are unneeded, but kept in to make the code
- * behaviour the same as pre change unless we have hyperthreaded
- * processors. This keeps Mr Marcelo Person happier but should be
- * removed for 2.5
+ /*
+ * If this architecture has a "base" platform capability
+ * string, copy it to userspace.
*/
- if (smp_num_siblings > 1)
- sp = sp - ((current->pid % 64) << 7);
-#endif
+ k_base_platform = ELF_BASE_PLATFORM;
+ u_base_platform = NULL;
+
+ if (k_base_platform) {
+ platform_len = strlen(k_base_platform) + 1;
+ sp -= platform_len;
+ u_base_platform = (char __user *) sp;
+ if (__copy_to_user(u_base_platform, k_base_platform, platform_len) != 0)
+ return -EFAULT;
+ }
sp &= ~7UL;
}
/* force 16 byte _final_ alignment here for generality */
-#define DLINFO_ITEMS 13
+#define DLINFO_ITEMS 15
- nitems = 1 + DLINFO_ITEMS + (k_platform ? 1 : 0);
-#ifdef DLINFO_ARCH_ITEMS
- nitems += DLINFO_ARCH_ITEMS;
-#endif
+ nitems = 1 + DLINFO_ITEMS + (k_platform ? 1 : 0) +
+ (k_base_platform ? 1 : 0) + AT_VECTOR_SIZE_ARCH;
+
+ if (bprm->interp_flags & BINPRM_FLAGS_EXECFD)
+ nitems++;
csp = sp;
sp -= nitems * 2 * sizeof(unsigned long);
sp -= sp & 15UL;
/* put the ELF interpreter info on the stack */
-#define NEW_AUX_ENT(nr, id, val) \
+#define NEW_AUX_ENT(id, val) \
do { \
struct { unsigned long _id, _val; } __user *ent; \
\
ent = (void __user *) csp; \
__put_user((id), &ent[nr]._id); \
__put_user((val), &ent[nr]._val); \
+ nr++; \
} while (0)
+ nr = 0;
csp -= 2 * sizeof(unsigned long);
- NEW_AUX_ENT(0, AT_NULL, 0);
+ NEW_AUX_ENT(AT_NULL, 0);
if (k_platform) {
+ nr = 0;
csp -= 2 * sizeof(unsigned long);
- NEW_AUX_ENT(0, AT_PLATFORM,
+ NEW_AUX_ENT(AT_PLATFORM,
(elf_addr_t) (unsigned long) u_platform);
}
+ if (k_base_platform) {
+ nr = 0;
+ csp -= 2 * sizeof(unsigned long);
+ NEW_AUX_ENT(AT_BASE_PLATFORM,
+ (elf_addr_t) (unsigned long) u_base_platform);
+ }
+
+ if (bprm->interp_flags & BINPRM_FLAGS_EXECFD) {
+ nr = 0;
+ csp -= 2 * sizeof(unsigned long);
+ NEW_AUX_ENT(AT_EXECFD, bprm->interp_data);
+ }
+
+ nr = 0;
csp -= DLINFO_ITEMS * 2 * sizeof(unsigned long);
- NEW_AUX_ENT( 0, AT_HWCAP, hwcap);
- NEW_AUX_ENT( 1, AT_PAGESZ, PAGE_SIZE);
- NEW_AUX_ENT( 2, AT_CLKTCK, CLOCKS_PER_SEC);
- NEW_AUX_ENT( 3, AT_PHDR, exec_params->ph_addr);
- NEW_AUX_ENT( 4, AT_PHENT, sizeof(struct elf_phdr));
- NEW_AUX_ENT( 5, AT_PHNUM, exec_params->hdr.e_phnum);
- NEW_AUX_ENT( 6, AT_BASE, interp_params->elfhdr_addr);
- NEW_AUX_ENT( 7, AT_FLAGS, 0);
- NEW_AUX_ENT( 8, AT_ENTRY, exec_params->entry_addr);
- NEW_AUX_ENT( 9, AT_UID, (elf_addr_t) current->uid);
- NEW_AUX_ENT(10, AT_EUID, (elf_addr_t) current->euid);
- NEW_AUX_ENT(11, AT_GID, (elf_addr_t) current->gid);
- NEW_AUX_ENT(12, AT_EGID, (elf_addr_t) current->egid);
+ NEW_AUX_ENT(AT_HWCAP, ELF_HWCAP);
+#ifdef ELF_HWCAP2
+ NEW_AUX_ENT(AT_HWCAP2, ELF_HWCAP2);
+#endif
+ NEW_AUX_ENT(AT_PAGESZ, PAGE_SIZE);
+ NEW_AUX_ENT(AT_CLKTCK, CLOCKS_PER_SEC);
+ NEW_AUX_ENT(AT_PHDR, exec_params->ph_addr);
+ NEW_AUX_ENT(AT_PHENT, sizeof(struct elf_phdr));
+ NEW_AUX_ENT(AT_PHNUM, exec_params->hdr.e_phnum);
+ NEW_AUX_ENT(AT_BASE, interp_params->elfhdr_addr);
+ NEW_AUX_ENT(AT_FLAGS, 0);
+ NEW_AUX_ENT(AT_ENTRY, exec_params->entry_addr);
+ NEW_AUX_ENT(AT_UID, (elf_addr_t) from_kuid_munged(cred->user_ns, cred->uid));
+ NEW_AUX_ENT(AT_EUID, (elf_addr_t) from_kuid_munged(cred->user_ns, cred->euid));
+ NEW_AUX_ENT(AT_GID, (elf_addr_t) from_kgid_munged(cred->user_ns, cred->gid));
+ NEW_AUX_ENT(AT_EGID, (elf_addr_t) from_kgid_munged(cred->user_ns, cred->egid));
+ NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm));
+ NEW_AUX_ENT(AT_EXECFN, bprm->exec);
#ifdef ARCH_DLINFO
+ nr = 0;
+ csp -= AT_VECTOR_SIZE_ARCH * 2 * sizeof(unsigned long);
+
/* ARCH_DLINFO must come last so platform specific code can enforce
* special alignment requirements on the AUXV if necessary (eg. PPC).
*/
p = (char __user *) current->mm->arg_start;
for (loop = bprm->argc; loop > 0; loop--) {
__put_user((elf_caddr_t) p, argv++);
- len = strnlen_user(p, PAGE_SIZE * MAX_ARG_PAGES);
- if (!len || len > PAGE_SIZE * MAX_ARG_PAGES)
+ len = strnlen_user(p, MAX_ARG_STRLEN);
+ if (!len || len > MAX_ARG_STRLEN)
return -EINVAL;
p += len;
}
current->mm->env_start = (unsigned long) p;
for (loop = bprm->envc; loop > 0; loop--) {
__put_user((elf_caddr_t)(unsigned long) p, envp++);
- len = strnlen_user(p, PAGE_SIZE * MAX_ARG_PAGES);
- if (!len || len > PAGE_SIZE * MAX_ARG_PAGES)
+ len = strnlen_user(p, MAX_ARG_STRLEN);
+ if (!len || len > MAX_ARG_STRLEN)
return -EINVAL;
p += len;
}
dynamic_error:
printk("ELF FDPIC %s with invalid DYNAMIC section (inode=%lu)\n",
- what, file->f_path.dentry->d_inode->i_ino);
+ what, file_inode(file)->i_ino);
return -ELIBBAD;
}
struct elf32_fdpic_loadseg *seg;
struct elf32_phdr *phdr;
unsigned long load_addr, base = ULONG_MAX, top = 0, maddr = 0, mflags;
- loff_t fpos;
int loop, ret;
load_addr = params->load_addr;
if (params->flags & ELF_FDPIC_FLAG_EXECUTABLE)
mflags |= MAP_EXECUTABLE;
- down_write(&mm->mmap_sem);
- maddr = do_mmap(NULL, load_addr, top - base,
+ maddr = vm_mmap(NULL, load_addr, top - base,
PROT_READ | PROT_WRITE | PROT_EXEC, mflags, 0);
- up_write(&mm->mmap_sem);
if (IS_ERR_VALUE(maddr))
return (int) maddr;
if (params->phdrs[loop].p_type != PT_LOAD)
continue;
- fpos = phdr->p_offset;
-
seg->addr = maddr + (phdr->p_vaddr - base);
seg->p_vaddr = phdr->p_vaddr;
seg->p_memsz = phdr->p_memsz;
- ret = file->f_op->read(file, (void *) seg->addr,
- phdr->p_filesz, &fpos);
+ ret = read_code(file, seg->addr, phdr->p_offset,
+ phdr->p_filesz);
if (ret < 0)
return ret;
params->elfhdr_addr = seg->addr;
/* clear any space allocated but not loaded */
- if (phdr->p_filesz < phdr->p_memsz)
- clear_user((void *) (seg->addr + phdr->p_filesz),
- phdr->p_memsz - phdr->p_filesz);
+ if (phdr->p_filesz < phdr->p_memsz) {
+ if (clear_user((void *) (seg->addr + phdr->p_filesz),
+ phdr->p_memsz - phdr->p_filesz))
+ return -EFAULT;
+ }
if (mm) {
if (phdr->p_flags & PF_X) {
}
} else if (!mm->start_data) {
mm->start_data = seg->addr;
-#ifndef CONFIG_MMU
mm->end_data = seg->addr + phdr->p_memsz;
-#endif
}
-
-#ifdef CONFIG_MMU
- if (seg->addr + phdr->p_memsz > mm->end_data)
- mm->end_data = seg->addr + phdr->p_memsz;
-#endif
}
seg++;
/* create the mapping */
disp = phdr->p_vaddr & ~PAGE_MASK;
- down_write(&mm->mmap_sem);
- maddr = do_mmap(file, maddr, phdr->p_memsz + disp, prot, flags,
+ maddr = vm_mmap(file, maddr, phdr->p_memsz + disp, prot, flags,
phdr->p_offset - disp);
- up_write(&mm->mmap_sem);
kdebug("mmap[%d] <file> sz=%lx pr=%x fl=%x of=%lx --> %08lx",
loop, phdr->p_memsz + disp, prot, flags,
* PT_LOAD */
if (prot & PROT_WRITE && disp > 0) {
kdebug("clear[%d] ad=%lx sz=%lx", loop, maddr, disp);
- clear_user((void __user *) maddr, disp);
+ if (clear_user((void __user *) maddr, disp))
+ return -EFAULT;
maddr += disp;
}
unsigned long xmaddr;
flags |= MAP_FIXED | MAP_ANONYMOUS;
- down_write(&mm->mmap_sem);
- xmaddr = do_mmap(NULL, xaddr, excess - excess1,
+ xmaddr = vm_mmap(NULL, xaddr, excess - excess1,
prot, flags, 0);
- up_write(&mm->mmap_sem);
kdebug("mmap[%d] <anon>"
" ad=%lx sz=%lx pr=%x fl=%x of=0 --> %08lx",
if (prot & PROT_WRITE && excess1 > 0) {
kdebug("clear[%d] ad=%lx sz=%lx",
loop, maddr + phdr->p_filesz, excess1);
- clear_user((void __user *) maddr + phdr->p_filesz,
- excess1);
+ if (clear_user((void __user *) maddr + phdr->p_filesz,
+ excess1))
+ return -EFAULT;
}
#else
if (excess > 0) {
kdebug("clear[%d] ad=%lx sz=%lx",
loop, maddr + phdr->p_filesz, excess);
- clear_user((void *) maddr + phdr->p_filesz, excess);
+ if (clear_user((void *) maddr + phdr->p_filesz, excess))
+ return -EFAULT;
}
#endif
*
* Modelled on fs/binfmt_elf.c core dumper
*/
-#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
-
-/*
- * These are the only things you should do on a core-file: use only these
- * functions to write out all the necessary info.
- */
-static int dump_write(struct file *file, const void *addr, int nr)
-{
- return file->f_op->write(file, addr, nr, &file->f_pos) == nr;
-}
-
-static int dump_seek(struct file *file, loff_t off)
-{
- if (file->f_op->llseek) {
- if (file->f_op->llseek(file, off, SEEK_SET) != off)
- return 0;
- } else {
- file->f_pos = off;
- }
- return 1;
-}
+#ifdef CONFIG_ELF_CORE
/*
* Decide whether a segment is worth dumping; default is yes to be
*
* I think we should skip something. But I am not sure how. H.J.
*/
-static int maydump(struct vm_area_struct *vma)
+static int maydump(struct vm_area_struct *vma, unsigned long mm_flags)
{
+ int dump_ok;
+
/* Do not dump I/O mapped devices or special mappings */
- if (vma->vm_flags & (VM_IO | VM_RESERVED)) {
+ if (vma->vm_flags & VM_IO) {
kdcore("%08lx: %08lx: no (IO)", vma->vm_start, vma->vm_flags);
return 0;
}
return 0;
}
- /* Dump shared memory only if mapped from an anonymous file. */
+ /* By default, dump shared memory if mapped from an anonymous file. */
if (vma->vm_flags & VM_SHARED) {
- if (vma->vm_file->f_path.dentry->d_inode->i_nlink == 0) {
- kdcore("%08lx: %08lx: no (share)", vma->vm_start, vma->vm_flags);
- return 1;
+ if (file_inode(vma->vm_file)->i_nlink == 0) {
+ dump_ok = test_bit(MMF_DUMP_ANON_SHARED, &mm_flags);
+ kdcore("%08lx: %08lx: %s (share)", vma->vm_start,
+ vma->vm_flags, dump_ok ? "yes" : "no");
+ return dump_ok;
}
- kdcore("%08lx: %08lx: no (share)", vma->vm_start, vma->vm_flags);
- return 0;
+ dump_ok = test_bit(MMF_DUMP_MAPPED_SHARED, &mm_flags);
+ kdcore("%08lx: %08lx: %s (share)", vma->vm_start,
+ vma->vm_flags, dump_ok ? "yes" : "no");
+ return dump_ok;
}
#ifdef CONFIG_MMU
- /* If it hasn't been written to, don't write it out */
+ /* By default, if it hasn't been written to, don't write it out */
if (!vma->anon_vma) {
- kdcore("%08lx: %08lx: no (!anon)", vma->vm_start, vma->vm_flags);
- return 0;
+ dump_ok = test_bit(MMF_DUMP_MAPPED_PRIVATE, &mm_flags);
+ kdcore("%08lx: %08lx: %s (!anon)", vma->vm_start,
+ vma->vm_flags, dump_ok ? "yes" : "no");
+ return dump_ok;
}
#endif
- kdcore("%08lx: %08lx: yes", vma->vm_start, vma->vm_flags);
- return 1;
+ dump_ok = test_bit(MMF_DUMP_ANON_PRIVATE, &mm_flags);
+ kdcore("%08lx: %08lx: %s", vma->vm_start, vma->vm_flags,
+ dump_ok ? "yes" : "no");
+ return dump_ok;
}
/* An ELF note in memory */
/* #define DEBUG */
-#define DUMP_WRITE(addr, nr) \
- do { if (!dump_write(file, (addr), (nr))) return 0; } while(0)
-#define DUMP_SEEK(off) \
- do { if (!dump_seek(file, (off))) return 0; } while(0)
+#define DUMP_WRITE(addr, nr, foffset) \
+ do { if (!dump_write(file, (addr), (nr))) return 0; *foffset += (nr); } while(0)
-static int writenote(struct memelfnote *men, struct file *file)
+static int alignfile(struct file *file, loff_t *foffset)
{
- struct elf_note en;
+ static const char buf[4] = { 0, };
+ DUMP_WRITE(buf, roundup(*foffset, 4) - *foffset, foffset);
+ return 1;
+}
+static int writenote(struct memelfnote *men, struct file *file,
+ loff_t *foffset)
+{
+ struct elf_note en;
en.n_namesz = strlen(men->name) + 1;
en.n_descsz = men->datasz;
en.n_type = men->type;
- DUMP_WRITE(&en, sizeof(en));
- DUMP_WRITE(men->name, en.n_namesz);
- /* XXX - cast from long long to long to avoid need for libgcc.a */
- DUMP_SEEK(roundup((unsigned long)file->f_pos, 4)); /* XXX */
- DUMP_WRITE(men->data, men->datasz);
- DUMP_SEEK(roundup((unsigned long)file->f_pos, 4)); /* XXX */
+ DUMP_WRITE(&en, sizeof(en), foffset);
+ DUMP_WRITE(men->name, en.n_namesz, foffset);
+ if (!alignfile(file, foffset))
+ return 0;
+ DUMP_WRITE(men->data, men->datasz, foffset);
+ if (!alignfile(file, foffset))
+ return 0;
return 1;
}
#undef DUMP_WRITE
-#undef DUMP_SEEK
-
-#define DUMP_WRITE(addr, nr) \
- if ((size += (nr)) > limit || !dump_write(file, (addr), (nr))) \
- goto end_coredump;
-#define DUMP_SEEK(off) \
- if (!dump_seek(file, (off))) \
- goto end_coredump;
static inline void fill_elf_fdpic_header(struct elfhdr *elf, int segs)
{
/*
* fill up all the fields in prstatus from the given task struct, except
- * registers which need to be filled up seperately.
+ * registers which need to be filled up separately.
*/
static void fill_prstatus(struct elf_prstatus *prstatus,
struct task_struct *p, long signr)
prstatus->pr_info.si_signo = prstatus->pr_cursig = signr;
prstatus->pr_sigpend = p->pending.signal.sig[0];
prstatus->pr_sighold = p->blocked.sig[0];
- prstatus->pr_pid = p->pid;
- prstatus->pr_ppid = p->parent->pid;
- prstatus->pr_pgrp = process_group(p);
- prstatus->pr_sid = process_session(p);
+ rcu_read_lock();
+ prstatus->pr_ppid = task_pid_vnr(rcu_dereference(p->real_parent));
+ rcu_read_unlock();
+ prstatus->pr_pid = task_pid_vnr(p);
+ prstatus->pr_pgrp = task_pgrp_vnr(p);
+ prstatus->pr_sid = task_session_vnr(p);
if (thread_group_leader(p)) {
+ struct task_cputime cputime;
+
/*
- * This is the record for the group leader. Add in the
- * cumulative times of previous dead threads. This total
- * won't include the time of each live thread whose state
- * is included in the core dump. The final total reported
- * to our parent process when it calls wait4 will include
- * those sums as well as the little bit more time it takes
- * this and each other thread to finish dying after the
- * core dump synchronization phase.
+ * This is the record for the group leader. It shows the
+ * group-wide total, not its individual thread total.
*/
- cputime_to_timeval(cputime_add(p->utime, p->signal->utime),
- &prstatus->pr_utime);
- cputime_to_timeval(cputime_add(p->stime, p->signal->stime),
- &prstatus->pr_stime);
+ thread_group_cputime(p, &cputime);
+ cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
+ cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
} else {
- cputime_to_timeval(p->utime, &prstatus->pr_utime);
- cputime_to_timeval(p->stime, &prstatus->pr_stime);
+ cputime_t utime, stime;
+
+ task_cputime(p, &utime, &stime);
+ cputime_to_timeval(utime, &prstatus->pr_utime);
+ cputime_to_timeval(stime, &prstatus->pr_stime);
}
cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
struct mm_struct *mm)
{
+ const struct cred *cred;
unsigned int i, len;
/* first copy the parameters from user space */
psinfo->pr_psargs[i] = ' ';
psinfo->pr_psargs[len] = 0;
- psinfo->pr_pid = p->pid;
- psinfo->pr_ppid = p->parent->pid;
- psinfo->pr_pgrp = process_group(p);
- psinfo->pr_sid = process_session(p);
+ rcu_read_lock();
+ psinfo->pr_ppid = task_pid_vnr(rcu_dereference(p->real_parent));
+ rcu_read_unlock();
+ psinfo->pr_pid = task_pid_vnr(p);
+ psinfo->pr_pgrp = task_pgrp_vnr(p);
+ psinfo->pr_sid = task_session_vnr(p);
i = p->state ? ffz(~p->state) + 1 : 0;
psinfo->pr_state = i;
psinfo->pr_zomb = psinfo->pr_sname == 'Z';
psinfo->pr_nice = task_nice(p);
psinfo->pr_flag = p->flags;
- SET_UID(psinfo->pr_uid, p->uid);
- SET_GID(psinfo->pr_gid, p->gid);
+ rcu_read_lock();
+ cred = __task_cred(p);
+ SET_UID(psinfo->pr_uid, from_kuid_munged(cred->user_ns, cred->uid));
+ SET_GID(psinfo->pr_gid, from_kgid_munged(cred->user_ns, cred->gid));
+ rcu_read_unlock();
strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname));
return 0;
elf_fpregset_t fpu; /* NT_PRFPREG */
struct task_struct *thread;
#ifdef ELF_CORE_COPY_XFPREGS
- elf_fpxregset_t xfpu; /* NT_PRXFPREG */
+ elf_fpxregset_t xfpu; /* ELF_CORE_XFPREG_TYPE */
#endif
struct memelfnote notes[3];
int num_notes;
#ifdef ELF_CORE_COPY_XFPREGS
if (elf_core_copy_task_xfpregs(p, &t->xfpu)) {
- fill_note(&t->notes[2], "LINUX", NT_PRXFPREG, sizeof(t->xfpu),
- &t->xfpu);
+ fill_note(&t->notes[2], "LINUX", ELF_CORE_XFPREG_TYPE,
+ sizeof(t->xfpu), &t->xfpu);
t->num_notes++;
sz += notesize(&t->notes[2]);
}
return sz;
}
+static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
+ elf_addr_t e_shoff, int segs)
+{
+ elf->e_shoff = e_shoff;
+ elf->e_shentsize = sizeof(*shdr4extnum);
+ elf->e_shnum = 1;
+ elf->e_shstrndx = SHN_UNDEF;
+
+ memset(shdr4extnum, 0, sizeof(*shdr4extnum));
+
+ shdr4extnum->sh_type = SHT_NULL;
+ shdr4extnum->sh_size = elf->e_shnum;
+ shdr4extnum->sh_link = elf->e_shstrndx;
+ shdr4extnum->sh_info = segs;
+}
+
/*
* dump the segments for an MMU process
*/
#ifdef CONFIG_MMU
-static int elf_fdpic_dump_segments(struct file *file, struct mm_struct *mm,
- size_t *size, unsigned long *limit)
+static int elf_fdpic_dump_segments(struct file *file, size_t *size,
+ unsigned long *limit, unsigned long mm_flags)
{
struct vm_area_struct *vma;
+ int err = 0;
for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
unsigned long addr;
- if (!maydump(vma))
+ if (!maydump(vma, mm_flags))
continue;
- for (addr = vma->vm_start;
- addr < vma->vm_end;
- addr += PAGE_SIZE
- ) {
- struct vm_area_struct *vma;
- struct page *page;
-
- if (get_user_pages(current, current->mm, addr, 1, 0, 1,
- &page, &vma) <= 0) {
- DUMP_SEEK(file->f_pos + PAGE_SIZE);
- }
- else if (page == ZERO_PAGE(addr)) {
- page_cache_release(page);
- DUMP_SEEK(file->f_pos + PAGE_SIZE);
- }
- else {
- void *kaddr;
-
- flush_cache_page(vma, addr, page_to_pfn(page));
- kaddr = kmap(page);
- if ((*size += PAGE_SIZE) > *limit ||
- !dump_write(file, kaddr, PAGE_SIZE)
- ) {
- kunmap(page);
- page_cache_release(page);
- return -EIO;
- }
+ for (addr = vma->vm_start; addr < vma->vm_end;
+ addr += PAGE_SIZE) {
+ struct page *page = get_dump_page(addr);
+ if (page) {
+ void *kaddr = kmap(page);
+ *size += PAGE_SIZE;
+ if (*size > *limit)
+ err = -EFBIG;
+ else if (!dump_write(file, kaddr, PAGE_SIZE))
+ err = -EIO;
kunmap(page);
page_cache_release(page);
- }
+ } else if (!dump_seek(file, PAGE_SIZE))
+ err = -EFBIG;
+ if (err)
+ goto out;
}
}
-
- return 0;
-
-end_coredump:
- return -EFBIG;
+out:
+ return err;
}
#endif
* dump the segments for a NOMMU process
*/
#ifndef CONFIG_MMU
-static int elf_fdpic_dump_segments(struct file *file, struct mm_struct *mm,
- size_t *size, unsigned long *limit)
+static int elf_fdpic_dump_segments(struct file *file, size_t *size,
+ unsigned long *limit, unsigned long mm_flags)
{
- struct vm_list_struct *vml;
-
- for (vml = current->mm->context.vmlist; vml; vml = vml->next) {
- struct vm_area_struct *vma = vml->vma;
+ struct vm_area_struct *vma;
- if (!maydump(vma))
+ for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
+ if (!maydump(vma, mm_flags))
continue;
if ((*size += PAGE_SIZE) > *limit)
}
#endif
+static size_t elf_core_vma_data_size(unsigned long mm_flags)
+{
+ struct vm_area_struct *vma;
+ size_t size = 0;
+
+ for (vma = current->mm->mmap; vma; vma = vma->vm_next)
+ if (maydump(vma, mm_flags))
+ size += vma->vm_end - vma->vm_start;
+ return size;
+}
+
/*
* Actual dumper
*
* and then they are actually written out. If we run out of core limit
* we just truncate.
*/
-static int elf_fdpic_core_dump(long signr, struct pt_regs *regs,
- struct file *file)
+static int elf_fdpic_core_dump(struct coredump_params *cprm)
{
#define NUM_NOTES 6
int has_dumped = 0;
int i;
struct vm_area_struct *vma;
struct elfhdr *elf = NULL;
- loff_t offset = 0, dataoff;
- unsigned long limit = current->signal->rlim[RLIMIT_CORE].rlim_cur;
+ loff_t offset = 0, dataoff, foffset;
int numnote;
struct memelfnote *notes = NULL;
struct elf_prstatus *prstatus = NULL; /* NT_PRSTATUS */
struct elf_prpsinfo *psinfo = NULL; /* NT_PRPSINFO */
- struct task_struct *g, *p;
LIST_HEAD(thread_list);
struct list_head *t;
elf_fpregset_t *fpu = NULL;
elf_fpxregset_t *xfpu = NULL;
#endif
int thread_status_size = 0;
-#ifndef CONFIG_MMU
- struct vm_list_struct *vml;
-#endif
elf_addr_t *auxv;
+ struct elf_phdr *phdr4note = NULL;
+ struct elf_shdr *shdr4extnum = NULL;
+ Elf_Half e_phnum;
+ elf_addr_t e_shoff;
/*
* We no longer stop all VM operations.
goto cleanup;
#endif
- if (signr) {
+ if (cprm->siginfo->si_signo) {
+ struct core_thread *ct;
struct elf_thread_status *tmp;
- rcu_read_lock();
- do_each_thread(g,p)
- if (current->mm == p->mm && current != p) {
- tmp = kzalloc(sizeof(*tmp), GFP_ATOMIC);
- if (!tmp) {
- rcu_read_unlock();
- goto cleanup;
- }
- tmp->thread = p;
- list_add(&tmp->list, &thread_list);
- }
- while_each_thread(g,p);
- rcu_read_unlock();
+
+ for (ct = current->mm->core_state->dumper.next;
+ ct; ct = ct->next) {
+ tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+ if (!tmp)
+ goto cleanup;
+
+ tmp->thread = ct->task;
+ list_add(&tmp->list, &thread_list);
+ }
+
list_for_each(t, &thread_list) {
struct elf_thread_status *tmp;
int sz;
tmp = list_entry(t, struct elf_thread_status, list);
- sz = elf_dump_thread_status(signr, tmp);
+ sz = elf_dump_thread_status(cprm->siginfo->si_signo, tmp);
thread_status_size += sz;
}
}
/* now collect the dump for the current */
- fill_prstatus(prstatus, current, signr);
- elf_core_copy_regs(&prstatus->pr_reg, regs);
+ fill_prstatus(prstatus, current, cprm->siginfo->si_signo);
+ elf_core_copy_regs(&prstatus->pr_reg, cprm->regs);
-#ifdef CONFIG_MMU
segs = current->mm->map_count;
-#else
- segs = 0;
- for (vml = current->mm->context.vmlist; vml; vml = vml->next)
- segs++;
-#endif
-#ifdef ELF_CORE_EXTRA_PHDRS
- segs += ELF_CORE_EXTRA_PHDRS;
-#endif
+ segs += elf_core_extra_phdrs();
+
+ /* for notes section */
+ segs++;
+
+ /* If segs > PN_XNUM(0xffff), then e_phnum overflows. To avoid
+ * this, kernel supports extended numbering. Have a look at
+ * include/linux/elf.h for further information. */
+ e_phnum = segs > PN_XNUM ? PN_XNUM : segs;
/* Set up header */
- fill_elf_fdpic_header(elf, segs + 1); /* including notes section */
+ fill_elf_fdpic_header(elf, e_phnum);
has_dumped = 1;
- current->flags |= PF_DUMPCORE;
-
/*
* Set up the notes in similar form to SVR4 core dumps made
* with info from their /proc.
/* Try to dump the FPU. */
if ((prstatus->pr_fpvalid =
- elf_core_copy_task_fpregs(current, regs, fpu)))
+ elf_core_copy_task_fpregs(current, cprm->regs, fpu)))
fill_note(notes + numnote++,
"CORE", NT_PRFPREG, sizeof(*fpu), fpu);
#ifdef ELF_CORE_COPY_XFPREGS
if (elf_core_copy_task_xfpregs(current, xfpu))
fill_note(notes + numnote++,
- "LINUX", NT_PRXFPREG, sizeof(*xfpu), xfpu);
+ "LINUX", ELF_CORE_XFPREG_TYPE, sizeof(*xfpu), xfpu);
#endif
fs = get_fs();
set_fs(KERNEL_DS);
- DUMP_WRITE(elf, sizeof(*elf));
offset += sizeof(*elf); /* Elf header */
- offset += (segs+1) * sizeof(struct elf_phdr); /* Program headers */
+ offset += segs * sizeof(struct elf_phdr); /* Program headers */
+ foffset = offset;
/* Write notes phdr entry */
{
- struct elf_phdr phdr;
int sz = 0;
for (i = 0; i < numnote; i++)
sz += thread_status_size;
- fill_elf_note_phdr(&phdr, sz, offset);
+ phdr4note = kmalloc(sizeof(*phdr4note), GFP_KERNEL);
+ if (!phdr4note)
+ goto end_coredump;
+
+ fill_elf_note_phdr(phdr4note, sz, offset);
offset += sz;
- DUMP_WRITE(&phdr, sizeof(phdr));
}
/* Page-align dumped data */
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
+ offset += elf_core_vma_data_size(cprm->mm_flags);
+ offset += elf_core_extra_data_size();
+ e_shoff = offset;
+
+ if (e_phnum == PN_XNUM) {
+ shdr4extnum = kmalloc(sizeof(*shdr4extnum), GFP_KERNEL);
+ if (!shdr4extnum)
+ goto end_coredump;
+ fill_extnum_info(elf, shdr4extnum, e_shoff, segs);
+ }
+
+ offset = dataoff;
+
+ size += sizeof(*elf);
+ if (size > cprm->limit || !dump_write(cprm->file, elf, sizeof(*elf)))
+ goto end_coredump;
+
+ size += sizeof(*phdr4note);
+ if (size > cprm->limit
+ || !dump_write(cprm->file, phdr4note, sizeof(*phdr4note)))
+ goto end_coredump;
+
/* write program headers for segments dump */
- for (
-#ifdef CONFIG_MMU
- vma = current->mm->mmap; vma; vma = vma->vm_next
-#else
- vml = current->mm->context.vmlist; vml; vml = vml->next
-#endif
- ) {
+ for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
struct elf_phdr phdr;
size_t sz;
-#ifndef CONFIG_MMU
- vma = vml->vma;
-#endif
-
sz = vma->vm_end - vma->vm_start;
phdr.p_type = PT_LOAD;
phdr.p_offset = offset;
phdr.p_vaddr = vma->vm_start;
phdr.p_paddr = 0;
- phdr.p_filesz = maydump(vma) ? sz : 0;
+ phdr.p_filesz = maydump(vma, cprm->mm_flags) ? sz : 0;
phdr.p_memsz = sz;
offset += phdr.p_filesz;
phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
phdr.p_flags |= PF_X;
phdr.p_align = ELF_EXEC_PAGESIZE;
- DUMP_WRITE(&phdr, sizeof(phdr));
+ size += sizeof(phdr);
+ if (size > cprm->limit
+ || !dump_write(cprm->file, &phdr, sizeof(phdr)))
+ goto end_coredump;
}
-#ifdef ELF_CORE_WRITE_EXTRA_PHDRS
- ELF_CORE_WRITE_EXTRA_PHDRS;
-#endif
+ if (!elf_core_write_extra_phdrs(cprm->file, offset, &size, cprm->limit))
+ goto end_coredump;
/* write out the notes section */
for (i = 0; i < numnote; i++)
- if (!writenote(notes + i, file))
+ if (!writenote(notes + i, cprm->file, &foffset))
goto end_coredump;
/* write out the thread status notes section */
list_entry(t, struct elf_thread_status, list);
for (i = 0; i < tmp->num_notes; i++)
- if (!writenote(&tmp->notes[i], file))
+ if (!writenote(&tmp->notes[i], cprm->file, &foffset))
goto end_coredump;
}
- DUMP_SEEK(dataoff);
+ if (!dump_seek(cprm->file, dataoff - foffset))
+ goto end_coredump;
- if (elf_fdpic_dump_segments(file, current->mm, &size, &limit) < 0)
+ if (elf_fdpic_dump_segments(cprm->file, &size, &cprm->limit,
+ cprm->mm_flags) < 0)
goto end_coredump;
-#ifdef ELF_CORE_WRITE_EXTRA_DATA
- ELF_CORE_WRITE_EXTRA_DATA;
-#endif
+ if (!elf_core_write_extra_data(cprm->file, &size, cprm->limit))
+ goto end_coredump;
- if (file->f_pos != offset) {
+ if (e_phnum == PN_XNUM) {
+ size += sizeof(*shdr4extnum);
+ if (size > cprm->limit
+ || !dump_write(cprm->file, shdr4extnum,
+ sizeof(*shdr4extnum)))
+ goto end_coredump;
+ }
+
+ if (cprm->file->f_pos != offset) {
/* Sanity check */
printk(KERN_WARNING
"elf_core_dump: file->f_pos (%lld) != offset (%lld)\n",
- file->f_pos, offset);
+ cprm->file->f_pos, offset);
}
end_coredump:
list_del(tmp);
kfree(list_entry(tmp, struct elf_thread_status, list));
}
-
+ kfree(phdr4note);
kfree(elf);
kfree(prstatus);
kfree(psinfo);
kfree(notes);
kfree(fpu);
+ kfree(shdr4extnum);
#ifdef ELF_CORE_COPY_XFPREGS
kfree(xfpu);
#endif
#undef NUM_NOTES
}
-#endif /* USE_ELF_CORE_DUMP */
+#endif /* CONFIG_ELF_CORE */
Code Review / linux-3.10.git / blobdiff