android_kernel_samsung_msm8976/fs/binfmt_elf.c
Kaushal Kumar 4a36e44c45 This is the 3.10.84 stable release
-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2
 
 iQIcBAABCAAGBQJVoAOcAAoJEDjbvchgkmk+UhcP/1EOwnsJDcZ/sZkkclNgRmrJ
 yLBCW65caLAI2E3SmIdKvHQwIx7lHzX5gmWRBrvx+fIl4KhaNKEQ0NCOf1ATaVuQ
 MkYMdkicXWpLiFNdKokezryevGS8T1RME+2QlPFv3++Rby1Gy90YD5tu7YlIrEn7
 sPRJQHEPCzVAQ7Lqhd66yHICM6/QvdefXj4pjh7vV8IMb2YwnY4vqYt7RxnJCUfP
 tqljxrT274kzpA2awzALNh+o3B3/Y4W9ROmlDWviw3JBc9gEqFXYwbDf8KDwA5c0
 sp9GPGed/dV5DFuqRcAHksJenFnE3E4gZjo/R5hluHQU27peBuRfXev2hZyBfZqG
 796eUOky8fb0OiyxHfT2vhfGeD7CHI/asvIAORjDBVUqzJy9nkkby3XJ0U4tW+pz
 VkcilD2oHw1uRIFH3JoBWTJ9W6CYSNFG1qxw+brgfKT5otJG/dBiI8kBABx+aTq7
 V+A2cvf11oVwDEb93dnVypMGsfCywqzJUwEIRli9fTFjK7Fg9CBSGX38nwVGUaRv
 M2/NeloTyWqUQE41Nd11gCu+hKQRtUU77nxpZcSeKn1XsbpO9/7dHTwcELRuKnTD
 9XDksqPznXmC9KXGj7XMcRkLyWyB//JHjay0FCS6b4S6v7R5nrEIRjcpdB+H1WLd
 zMOXRH4ZlcOAS/Yt2QMd
 =8AB3
 -----END PGP SIGNATURE-----

Merge upstream tag 'v3.10.84' into LA.BR.1.3.3

This merge brings us up-to-date as of upstream tag v3.10.84

* tag 'v3.10.84' (317 commits):
  Linux 3.10.84
  fs: Fix S_NOSEC handling
  KVM: x86: make vapics_in_nmi_mode atomic
  MIPS: Fix KVM guest fixmap address
  x86/PCI: Use host bridge _CRS info on Foxconn K8M890-8237A
  powerpc/perf: Fix book3s kernel to userspace backtraces
  arm: KVM: force execution of HCPTR access on VM exit
  Revert "crypto: talitos - convert to use be16_add_cpu()"
  crypto: talitos - avoid memleak in talitos_alg_alloc()
  sctp: Fix race between OOTB responce and route removal
  packet: avoid out of bounds read in round robin fanout
  packet: read num_members once in packet_rcv_fanout()
  bridge: fix br_stp_set_bridge_priority race conditions
  bridge: fix multicast router rlist endless loop
  sparc: Use GFP_ATOMIC in ldc_alloc_exp_dring() as it can be called in softirq context
  Linux 3.10.83
  bus: mvebu: pass the coherency availability information at init time
  KVM: nSVM: Check for NRIPS support before updating control field
  ARM: clk-imx6q: refine sata's parent
  d_walk() might skip too much
  ipv6: update ip6_rt_last_gc every time GC is run
  ipv6: prevent fib6_run_gc() contention
  xfrm: Increase the garbage collector threshold
  Btrfs: make xattr replace operations atomic
  x86/microcode/intel: Guard against stack overflow in the loader
  fs: take i_mutex during prepare_binprm for set[ug]id executables
  hpsa: add missing pci_set_master in kdump path
  hpsa: refine the pci enable/disable handling
  sb_edac: Fix erroneous bytes->gigabytes conversion
  ACPICA: Utilities: Cleanup to remove useless ACPI_PRINTF/FORMAT_xxx helpers.
  ACPICA: Utilities: Cleanup to convert physical address printing formats.
  __ptrace_may_access() should not deny sub-threads
  include/linux/sched.h: don't use task->pid/tgid in same_thread_group/has_group_leader_pid
  netfilter: Zero the tuple in nfnl_cthelper_parse_tuple()
  netfilter: nfnetlink_cthelper: Remove 'const' and '&' to avoid warnings
  config: Enable NEED_DMA_MAP_STATE by default when SWIOTLB is selected
  get rid of s_files and files_lock
  fput: turn "list_head delayed_fput_list" into llist_head
  Linux 3.10.82
  lpfc: Add iotag memory barrier
  pipe: iovec: Fix memory corruption when retrying atomic copy as non-atomic
  drm/mgag200: Reject non-character-cell-aligned mode widths
  tracing: Have filter check for balanced ops
  crypto: caam - fix RNG buffer cache alignment
  Linux 3.10.81
  btrfs: cleanup orphans while looking up default subvolume
  btrfs: incorrect handling for fiemap_fill_next_extent return
  cfg80211: wext: clear sinfo struct before calling driver
  mm/memory_hotplug.c: set zone->wait_table to null after freeing it
  drm/i915: Fix DDC probe for passive adapters
  pata_octeon_cf: fix broken build
  ozwpan: unchecked signed subtraction leads to DoS
  ozwpan: divide-by-zero leading to panic
  ozwpan: Use proper check to prevent heap overflow
  MIPS: Fix enabling of DEBUG_STACKOVERFLOW
  ring-buffer-benchmark: Fix the wrong sched_priority of producer
  USB: serial: ftdi_sio: Add support for a Motion Tracker Development Board
  USB: cp210x: add ID for HubZ dual ZigBee and Z-Wave dongle
  block: fix ext_dev_lock lockdep report
  Input: elantech - fix detection of touchpads where the revision matches a known rate
  ALSA: usb-audio: add MAYA44 USB+ mixer control names
  ALSA: usb-audio: Add mic volume fix quirk for Logitech Quickcam Fusion
  ALSA: hda/realtek - Add a fixup for another Acer Aspire 9420
  iio: adis16400: Compute the scan mask from channel indices
  iio: adis16400: Use != channel indices for the two voltage channels
  iio: adis16400: Report pressure channel scale
  xen: netback: read hotplug script once at start of day.
  udp: fix behavior of wrong checksums
  net_sched: invoke ->attach() after setting dev->qdisc
  unix/caif: sk_socket can disappear when state is unlocked
  net: dp83640: fix broken calibration routine.
  bridge: fix parsing of MLDv2 reports
  ipv4: Avoid crashing in ip_error
  net: phy: Allow EEE for all RGMII variants
  Linux 3.10.80
  fs/binfmt_elf.c:load_elf_binary(): return -EINVAL on zero-length mappings
  vfs: read file_handle only once in handle_to_path
  ACPI / init: Fix the ordering of acpi_reserve_resources()
  Input: elantech - fix semi-mt protocol for v3 HW
  rtlwifi: rtl8192cu: Fix kernel deadlock
  md/raid5: don't record new size if resize_stripes fails.
  svcrpc: fix potential GSSX_ACCEPT_SEC_CONTEXT decoding failures
  ARM: fix missing syscall trace exit
  ARM: dts: imx27: only map 4 Kbyte for fec registers
  crypto: s390/ghash - Fix incorrect ghash icv buffer handling.
  rt2x00: add new rt2800usb device DWA 130
  libata: Ignore spurious PHY event on LPM policy change
  libata: Add helper to determine when PHY events should be ignored
  ext4: check for zero length extent explicitly
  ext4: convert write_begin methods to stable_page_writes semantics
  mmc: atmel-mci: fix bad variable type for clkdiv
  powerpc: Align TOC to 256 bytes
  usb: gadget: configfs: Fix interfaces array NULL-termination
  usb-storage: Add NO_WP_DETECT quirk for Lacie 059f:0651 devices
  USB: cp210x: add ID for KCF Technologies PRN device
  USB: pl2303: Remove support for Samsung I330
  USB: visor: Match I330 phone more precisely
  xhci: gracefully handle xhci_irq dead device
  xhci: Solve full event ring by increasing TRBS_PER_SEGMENT to 256
  xhci: fix isoc endpoint dequeue from advancing too far on transaction error
  target/pscsi: Don't leak scsi_host if hba is VIRTUAL_HOST
  ASoC: wm8994: correct BCLK DIV 348 to 384
  ASoC: wm8960: fix "RINPUT3" audio route error
  ASoC: mc13783: Fix wrong mask value used in mc13xxx_reg_rmw() calls
  ALSA: hda - Add headphone quirk for Lifebook E752
  ALSA: hda - Add Conexant codecs CX20721, CX20722, CX20723 and CX20724
  d_walk() might skip too much
  lib: Fix strnlen_user() to not touch memory after specified maximum
  hwmon: (ntc_thermistor) Ensure iio channel is of type IIO_VOLTAGE
  libceph: request a new osdmap if lingering request maps to no osd
  lguest: fix out-by-one error in address checking.
  fs, omfs: add NULL terminator in the end up the token list
  KVM: MMU: fix CR4.SMEP=1, CR0.WP=0 with shadow pages
  net: socket: Fix the wrong returns for recvmsg and sendmsg
  kernel: use the gnu89 standard explicitly
  staging, rtl8192e, LLVMLinux: Remove unused inline prototype
  staging: rtl8712, rtl8712: avoid lots of build warnings
  staging, rtl8192e, LLVMLinux: Change extern inline to static inline
  drm/i915: Fix declaration of intel_gmbus_{is_forced_bit/is_port_falid}
  staging: wlags49_h2: fix extern inline functions
  Linux 3.10.79
  ACPICA: Utilities: Cleanup to enforce ACPI_PHYSADDR_TO_PTR()/ACPI_PTR_TO_PHYSADDR().
  ACPICA: Tables: Change acpi_find_root_pointer() to use acpi_physical_address.
  revert "softirq: Add support for triggering softirq work on softirqs"
  sound/oss: fix deadlock in sequencer_ioctl(SNDCTL_SEQ_OUTOFBAND)
  mmc: card: Don't access RPMB partitions for normal read/write
  pinctrl: Don't just pretend to protect pinctrl_maps, do it for real
  drm/i915: Add missing MacBook Pro models with dual channel LVDS
  ARM: mvebu: armada-xp-openblocks-ax3-4: Disable internal RTC
  ARM: dts: imx23-olinuxino: Fix dr_mode of usb0
  ARM: dts: imx28: Fix AUART4 TX-DMA interrupt name
  ARM: dts: imx25: Add #pwm-cells to pwm4
  gpio: sysfs: fix memory leaks and device hotplug
  gpio: unregister gpiochip device before removing it
  xen/console: Update console event channel on resume
  mm/memory-failure: call shake_page() when error hits thp tail page
  nilfs2: fix sanity check of btree level in nilfs_btree_root_broken()
  ocfs2: dlm: fix race between purge and get lock resource
  Linux 3.10.78
  ARC: signal handling robustify
  UBI: fix soft lockup in ubi_check_volume()
  Drivers: hv: vmbus: Don't wait after requesting offers
  ARM: dts: dove: Fix uart[23] reg property
  staging: panel: fix lcd type
  usb: gadget: printer: enqueue printer's response for setup request
  usb: host: oxu210hp: use new USB_RESUME_TIMEOUT
  3w-sas: fix command completion race
  3w-9xxx: fix command completion race
  3w-xxxx: fix command completion race
  ext4: fix data corruption caused by unwritten and delayed extents
  rbd: end I/O the entire obj_request on error
  serial: of-serial: Remove device_type = "serial" registration
  ALSA: hda - Fix mute-LED fixed mode
  ALSA: emu10k1: Emu10k2 32 bit DMA mode
  ALSA: emu10k1: Fix card shortname string buffer overflow
  ALSA: emux: Fix mutex deadlock in OSS emulation
  ALSA: emux: Fix mutex deadlock at unloading
  ipv4: Missing sk_nulls_node_init() in ping_unhash().
  Linux 3.10.77
  s390: Fix build error
  nosave: consolidate __nosave_{begin,end} in <asm/sections.h>
  memstick: mspro_block: add missing curly braces
  C6x: time: Ensure consistency in __init
  wl18xx: show rx_frames_per_rates as an array as it really is
  lib: memzero_explicit: use barrier instead of OPTIMIZER_HIDE_VAR
  e1000: add dummy allocator to fix race condition between mtu change and netpoll
  ksoftirqd: Enable IRQs and call cond_resched() before poking RCU
  RCU pathwalk breakage when running into a symlink overmounting something
  drm/i915: cope with large i2c transfers
  drm/radeon: fix doublescan modes (v2)
  i2c: core: Export bus recovery functions
  IB/mlx4: Fix WQE LSO segment calculation
  IB/core: don't disallow registering region starting at 0x0
  IB/core: disallow registering 0-sized memory region
  stk1160: Make sure current buffer is released
  mvsas: fix panic on expander attached SATA devices
  Drivers: hv: vmbus: Fix a bug in the error path in vmbus_open()
  xtensa: provide __NR_sync_file_range2 instead of __NR_sync_file_range
  xtensa: xtfpga: fix hardware lockup caused by LCD driver
  ACPICA: Utilities: split IO address types from data type models.
  drivers: parport: Kconfig: exclude arm64 for PARPORT_PC
  scsi: storvsc: Fix a bug in copy_from_bounce_buffer()
  UBI: fix check for "too many bytes"
  UBI: initialize LEB number variable
  UBI: fix out of bounds write
  UBI: account for bitflips in both the VID header and data
  tools/power turbostat: Use $(CURDIR) instead of $(PWD) and add support for O= option in Makefile
  powerpc/perf: Cap 64bit userspace backtraces to PERF_MAX_STACK_DEPTH
  ext4: make fsync to sync parent dir in no-journal for real this time
  arm64: kernel: compiling issue, need delete read_current_timer()
  video: vgacon: Don't build on arm64
  console: Disable VGA text console support on cris
  drivers: parport: Kconfig: exclude h8300 for PARPORT_PC
  parport: disable PC-style parallel port support on cris
  rtlwifi: rtl8192cu: Add new device ID
  rtlwifi: rtl8192cu: Add new USB ID
  ptrace: fix race between ptrace_resume() and wait_task_stopped()
  fs/binfmt_elf.c: fix bug in loading of PIE binaries
  Input: elantech - fix absolute mode setting on some ASUS laptops
  ALSA: emu10k1: don't deadlock in proc-functions
  usb: core: hub: use new USB_RESUME_TIMEOUT
  usb: host: sl811: use new USB_RESUME_TIMEOUT
  usb: host: xhci: use new USB_RESUME_TIMEOUT
  usb: host: isp116x: use new USB_RESUME_TIMEOUT
  usb: host: r8a66597: use new USB_RESUME_TIMEOUT
  usb: define a generic USB_RESUME_TIMEOUT macro
  usb: phy: Find the right match in devm_usb_phy_match
  ARM: S3C64XX: Use fixed IRQ bases to avoid conflicts on Cragganmore
  ARM: 8320/1: fix integer overflow in ELF_ET_DYN_BASE
  power_supply: lp8788-charger: Fix leaked power supply on probe fail
  ring-buffer: Replace this_cpu_*() with __this_cpu_*()
  spi: spidev: fix possible arithmetic overflow for multi-transfer message
  cdc-wdm: fix endianness bug in debug statements
  MIPS: Hibernate: flush TLB entries earlier
  KVM: use slowpath for cross page cached accesses
  s390/hibernate: fix save and restore of kernel text section
  KVM: s390: Zero out current VMDB of STSI before including level3 data.
  usb: gadget: composite: enable BESL support
  Btrfs: fix inode eviction infinite loop after cloning into it
  Btrfs: fix log tree corruption when fs mounted with -o discard
  tcp: avoid looping in tcp_send_fin()
  tcp: fix possible deadlock in tcp_send_fin()
  ip_forward: Drop frames with attached skb->sk
  Linux 3.10.76
  dcache: Fix locking bugs in backported "deal with deadlock in d_walk()"
  arc: mm: Fix build failure
  sb_edac: avoid INTERNAL ERROR message in EDAC with unspecified channel
  x86: mm: move mmap_sem unlock from mm_fault_error() to caller
  vm: make stack guard page errors return VM_FAULT_SIGSEGV rather than SIGBUS
  vm: add VM_FAULT_SIGSEGV handling support
  deal with deadlock in d_walk()
  move d_rcu from overlapping d_child to overlapping d_alias
  kconfig: Fix warning "‘jump’ may be used uninitialized"
  KVM: x86: SYSENTER emulation is broken
  netfilter: conntrack: disable generic tracking for known protocols
  Bluetooth: Ignore isochronous endpoints for Intel USB bootloader
  Bluetooth: Add support for Intel bootloader devices
  Bluetooth: btusb: Add IMC Networks (Broadcom based)
  Bluetooth: Add firmware update for Atheros 0cf3:311f
  Bluetooth: Enable Atheros 0cf3:311e for firmware upload
  mm: Fix NULL pointer dereference in madvise(MADV_WILLNEED) support
  splice: Apply generic position and size checks to each write
  jfs: fix readdir regression
  serial: 8250_dw: Fix deadlock in LCR workaround
  benet: Call dev_kfree_skby_any instead of kfree_skb.
  ixgb: Call dev_kfree_skby_any instead of dev_kfree_skb.
  tg3: Call dev_kfree_skby_any instead of dev_kfree_skb.
  bnx2: Call dev_kfree_skby_any instead of dev_kfree_skb.
  r8169: Call dev_kfree_skby_any instead of dev_kfree_skb.
  8139too: Call dev_kfree_skby_any instead of dev_kfree_skb.
  8139cp: Call dev_kfree_skby_any instead of kfree_skb.
  tcp: tcp_make_synack() should clear skb->tstamp
  tcp: fix FRTO undo on cumulative ACK of SACKed range
  ipv6: Don't reduce hop limit for an interface
  tcp: prevent fetching dst twice in early demux code
  remove extra definitions of U32_MAX
  conditionally define U32_MAX
  Linux 3.10.75
  pagemap: do not leak physical addresses to non-privileged userspace
  console: Fix console name size mismatch
  IB/mlx4: Saturate RoCE port PMA counters in case of overflow
  kernel.h: define u8, s8, u32, etc. limits
  net: llc: use correct size for sysctl timeout entries
  net: rds: use correct size for max unacked packets and bytes
  ipc: fix compat msgrcv with negative msgtyp
  core, nfqueue, openvswitch: fix compilation warning
  media: s5p-mfc: fix mmap support for 64bit arch
  iscsi target: fix oops when adding reject pdu
  ocfs2: _really_ sync the right range
  be2iscsi: Fix kernel panic when device initialization fails
  cifs: fix use-after-free bug in find_writable_file
  usb: xhci: apply XHCI_AVOID_BEI quirk to all Intel xHCI controllers
  cpuidle: ACPI: do not overwrite name and description of C0
  dmaengine: omap-dma: Fix memory leak when terminating running transfer
  iio: imu: Use iio_trigger_get for indio_dev->trig assignment
  iio: inv_mpu6050: Clear timestamps fifo while resetting hardware fifo
  Defer processing of REQ_PREEMPT requests for blocked devices
  USB: ftdi_sio: Use jtag quirk for SNAP Connect E10
  USB: ftdi_sio: Added custom PID for Synapse Wireless product
  radeon: Do not directly dereference pointers to BIOS area.
  writeback: fix possible underflow in write bandwidth calculation
  writeback: add missing INITIAL_JIFFIES init in global_update_bandwidth()
  mm/memory hotplug: postpone the reset of obsolete pgdat
  nbd: fix possible memory leak
  iwlwifi: dvm: run INIT firmware again upon .start()
  IB/uverbs: Prevent integer overflow in ib_umem_get address arithmetic
  IB/core: Avoid leakage from kernel to user space
  tcp: Fix crash in TCP Fast Open
  selinux: fix sel_write_enforce broken return value
  ALSA: hda - Fix headphone pin config for Lifebook T731
  ALSA: usb - Creative USB X-Fi Pro SB1095 volume knob support
  ALSA: hda - Add one more node in the EAPD supporting candidate list
  Linux 3.10.74
  net: ethernet: pcnet32: Setup the SRAM and NOUFLO on Am79C97{3, 5}
  powerpc/mpc85xx: Add ranges to etsec2 nodes
  hfsplus: fix B-tree corruption after insertion at position 0
  dm: hold suspend_lock while suspending device during device deletion
  vt6655: RFbSetPower fix missing rate RATE_12M
  perf: Fix irq_work 'tail' recursion
  Revert "iwlwifi: mvm: fix failure path when power_update fails in add_interface"
  mac80211: drop unencrypted frames in mesh fwding
  mac80211: disable u-APSD queues by default
  nl80211: ignore HT/VHT capabilities without QoS/WMM
  tcm_qla2xxx: Fix incorrect use of __transport_register_session
  tcm_fc: missing curly braces in ft_invl_hw_context()
  ASoC: wm8955: Fix wrong value references for boolean kctl
  ASoC: adav80x: Fix wrong value references for boolean kctl
  ASoC: ak4641: Fix wrong value references for boolean kctl
  ASoC: wm8904: Fix wrong value references for boolean kctl
  ASoC: wm8903: Fix wrong value references for boolean kctl
  ASoC: wm2000: Fix wrong value references for boolean kctl
  ASoC: wm8731: Fix wrong value references for boolean kctl
  ASoC: tas5086: Fix wrong value references for boolean kctl
  ASoC: wm8960: Fix wrong value references for boolean kctl
  ASoC: cs4271: Fix wrong value references for boolean kctl
  ASoC: sgtl5000: remove useless register write clearing CHRGPUMP_POWERUP

Change-Id: Ib7976ee2c7224e39074157e28db4158db40b00db
Signed-off-by: Kaushal Kumar <kaushalk@codeaurora.org>
2015-09-30 13:25:40 +05:30

2260 lines
58 KiB
C

/*
* linux/fs/binfmt_elf.c
*
* These are the functions used to load ELF format executables as used
* on SVr4 machines. Information on the format may be found in the book
* "UNIX SYSTEM V RELEASE 4 Programmers Guide: Ansi C and Programming Support
* Tools".
*
* Copyright 1993, 1994: Eric Youngdale (ericy@cais.com).
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/errno.h>
#include <linux/signal.h>
#include <linux/binfmts.h>
#include <linux/string.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/personality.h>
#include <linux/elfcore.h>
#include <linux/init.h>
#include <linux/highuid.h>
#include <linux/compiler.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/vmalloc.h>
#include <linux/security.h>
#include <linux/random.h>
#include <linux/elf.h>
#include <linux/utsname.h>
#include <linux/coredump.h>
#include <linux/sched.h>
#include <asm/uaccess.h>
#include <asm/param.h>
#include <asm/page.h>
#ifndef user_long_t
#define user_long_t long
#endif
#ifndef user_siginfo_t
#define user_siginfo_t siginfo_t
#endif
static int load_elf_binary(struct linux_binprm *bprm);
static int load_elf_library(struct file *);
static unsigned long elf_map(struct file *, unsigned long, struct elf_phdr *,
int, int, unsigned long);
/*
* If we don't support core dumping, then supply a NULL so we
* don't even try.
*/
#ifdef CONFIG_ELF_CORE
static int elf_core_dump(struct coredump_params *cprm);
#else
#define elf_core_dump NULL
#endif
#if ELF_EXEC_PAGESIZE > PAGE_SIZE
#define ELF_MIN_ALIGN ELF_EXEC_PAGESIZE
#else
#define ELF_MIN_ALIGN PAGE_SIZE
#endif
#ifndef ELF_CORE_EFLAGS
#define ELF_CORE_EFLAGS 0
#endif
#define ELF_PAGESTART(_v) ((_v) & ~(unsigned long)(ELF_MIN_ALIGN-1))
#define ELF_PAGEOFFSET(_v) ((_v) & (ELF_MIN_ALIGN-1))
#define ELF_PAGEALIGN(_v) (((_v) + ELF_MIN_ALIGN - 1) & ~(ELF_MIN_ALIGN - 1))
static struct linux_binfmt elf_format = {
.module = THIS_MODULE,
.load_binary = load_elf_binary,
.load_shlib = load_elf_library,
.core_dump = elf_core_dump,
.min_coredump = ELF_EXEC_PAGESIZE,
};
#define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE)
static int set_brk(unsigned long start, unsigned long end)
{
start = ELF_PAGEALIGN(start);
end = ELF_PAGEALIGN(end);
if (end > start) {
unsigned long addr;
addr = vm_brk(start, end - start);
if (BAD_ADDR(addr))
return addr;
}
current->mm->start_brk = current->mm->brk = end;
return 0;
}
/* We need to explicitly zero any fractional pages
after the data section (i.e. bss). This would
contain the junk from the file that should not
be in memory
*/
static int padzero(unsigned long elf_bss)
{
unsigned long nbyte;
nbyte = ELF_PAGEOFFSET(elf_bss);
if (nbyte) {
nbyte = ELF_MIN_ALIGN - nbyte;
if (clear_user((void __user *) elf_bss, nbyte))
return -EFAULT;
}
return 0;
}
/* Let's use some macros to make this stack manipulation a little clearer */
#ifdef CONFIG_STACK_GROWSUP
#define STACK_ADD(sp, items) ((elf_addr_t __user *)(sp) + (items))
#define STACK_ROUND(sp, items) \
((15 + (unsigned long) ((sp) + (items))) &~ 15UL)
#define STACK_ALLOC(sp, len) ({ \
elf_addr_t __user *old_sp = (elf_addr_t __user *)sp; sp += len; \
old_sp; })
#else
#define STACK_ADD(sp, items) ((elf_addr_t __user *)(sp) - (items))
#define STACK_ROUND(sp, items) \
(((unsigned long) (sp - items)) &~ 15UL)
#define STACK_ALLOC(sp, len) ({ sp -= len ; sp; })
#endif
#ifndef ELF_BASE_PLATFORM
/*
* 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
static int
create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
unsigned long load_addr, unsigned long interp_load_addr)
{
unsigned long p = bprm->p;
int argc = bprm->argc;
int envc = bprm->envc;
elf_addr_t __user *argv;
elf_addr_t __user *envp;
elf_addr_t __user *sp;
elf_addr_t __user *u_platform;
elf_addr_t __user *u_base_platform;
elf_addr_t __user *u_rand_bytes;
const char *k_platform = ELF_PLATFORM;
const char *k_base_platform = ELF_BASE_PLATFORM;
unsigned char k_rand_bytes[16];
int items;
elf_addr_t *elf_info;
int ei_index = 0;
const struct cred *cred = current_cred();
struct vm_area_struct *vma;
/*
* 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.
*/
p = arch_align_stack(p);
/*
* 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.
*/
u_platform = NULL;
if (k_platform) {
size_t len = strlen(k_platform) + 1;
u_platform = (elf_addr_t __user *)STACK_ALLOC(p, len);
if (__copy_to_user(u_platform, k_platform, len))
return -EFAULT;
}
/*
* If this architecture has a "base" platform capability
* string, copy it to userspace.
*/
u_base_platform = NULL;
if (k_base_platform) {
size_t len = strlen(k_base_platform) + 1;
u_base_platform = (elf_addr_t __user *)STACK_ALLOC(p, len);
if (__copy_to_user(u_base_platform, k_base_platform, len))
return -EFAULT;
}
/*
* Generate 16 random bytes for userspace PRNG seeding.
*/
get_random_bytes(k_rand_bytes, sizeof(k_rand_bytes));
u_rand_bytes = (elf_addr_t __user *)
STACK_ALLOC(p, sizeof(k_rand_bytes));
if (__copy_to_user(u_rand_bytes, k_rand_bytes, sizeof(k_rand_bytes)))
return -EFAULT;
/* Create the ELF interpreter info */
elf_info = (elf_addr_t *)current->mm->saved_auxv;
/* update AT_VECTOR_SIZE_BASE if the number of NEW_AUX_ENT() changes */
#define NEW_AUX_ENT(id, val) \
do { \
elf_info[ei_index++] = id; \
elf_info[ei_index++] = val; \
} while (0)
#ifdef ARCH_DLINFO
/*
* ARCH_DLINFO must come first so PPC can do its special alignment of
* AUXV.
* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT() in
* ARCH_DLINFO changes
*/
ARCH_DLINFO;
#endif
NEW_AUX_ENT(AT_HWCAP, ELF_HWCAP);
NEW_AUX_ENT(AT_PAGESZ, ELF_EXEC_PAGESIZE);
NEW_AUX_ENT(AT_CLKTCK, CLOCKS_PER_SEC);
NEW_AUX_ENT(AT_PHDR, load_addr + exec->e_phoff);
NEW_AUX_ENT(AT_PHENT, sizeof(struct elf_phdr));
NEW_AUX_ENT(AT_PHNUM, exec->e_phnum);
NEW_AUX_ENT(AT_BASE, interp_load_addr);
NEW_AUX_ENT(AT_FLAGS, 0);
NEW_AUX_ENT(AT_ENTRY, exec->e_entry);
NEW_AUX_ENT(AT_UID, from_kuid_munged(cred->user_ns, cred->uid));
NEW_AUX_ENT(AT_EUID, from_kuid_munged(cred->user_ns, cred->euid));
NEW_AUX_ENT(AT_GID, from_kgid_munged(cred->user_ns, cred->gid));
NEW_AUX_ENT(AT_EGID, from_kgid_munged(cred->user_ns, cred->egid));
NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm));
NEW_AUX_ENT(AT_RANDOM, (elf_addr_t)(unsigned long)u_rand_bytes);
#ifdef ELF_HWCAP2
NEW_AUX_ENT(AT_HWCAP2, ELF_HWCAP2);
#endif
NEW_AUX_ENT(AT_EXECFN, bprm->exec);
if (k_platform) {
NEW_AUX_ENT(AT_PLATFORM,
(elf_addr_t)(unsigned long)u_platform);
}
if (k_base_platform) {
NEW_AUX_ENT(AT_BASE_PLATFORM,
(elf_addr_t)(unsigned long)u_base_platform);
}
if (bprm->interp_flags & BINPRM_FLAGS_EXECFD) {
NEW_AUX_ENT(AT_EXECFD, bprm->interp_data);
}
#undef NEW_AUX_ENT
/* AT_NULL is zero; clear the rest too */
memset(&elf_info[ei_index], 0,
sizeof current->mm->saved_auxv - ei_index * sizeof elf_info[0]);
/* And advance past the AT_NULL entry. */
ei_index += 2;
sp = STACK_ADD(p, ei_index);
items = (argc + 1) + (envc + 1) + 1;
bprm->p = STACK_ROUND(sp, items);
/* Point sp at the lowest address on the stack */
#ifdef CONFIG_STACK_GROWSUP
sp = (elf_addr_t __user *)bprm->p - items - ei_index;
bprm->exec = (unsigned long)sp; /* XXX: PARISC HACK */
#else
sp = (elf_addr_t __user *)bprm->p;
#endif
/*
* Grow the stack manually; some architectures have a limit on how
* far ahead a user-space access may be in order to grow the stack.
*/
vma = find_extend_vma(current->mm, bprm->p);
if (!vma)
return -EFAULT;
/* Now, let's put argc (and argv, envp if appropriate) on the stack */
if (__put_user(argc, sp++))
return -EFAULT;
argv = sp;
envp = argv + argc + 1;
/* Populate argv and envp */
p = current->mm->arg_end = current->mm->arg_start;
while (argc-- > 0) {
size_t len;
if (__put_user((elf_addr_t)p, argv++))
return -EFAULT;
len = strnlen_user((void __user *)p, MAX_ARG_STRLEN);
if (!len || len > MAX_ARG_STRLEN)
return -EINVAL;
p += len;
}
if (__put_user(0, argv))
return -EFAULT;
current->mm->arg_end = current->mm->env_start = p;
while (envc-- > 0) {
size_t len;
if (__put_user((elf_addr_t)p, envp++))
return -EFAULT;
len = strnlen_user((void __user *)p, MAX_ARG_STRLEN);
if (!len || len > MAX_ARG_STRLEN)
return -EINVAL;
p += len;
}
if (__put_user(0, envp))
return -EFAULT;
current->mm->env_end = p;
/* Put the elf_info on the stack in the right place. */
sp = (elf_addr_t __user *)envp + 1;
if (copy_to_user(sp, elf_info, ei_index * sizeof(elf_addr_t)))
return -EFAULT;
return 0;
}
#ifndef elf_map
static unsigned long elf_map(struct file *filep, unsigned long addr,
struct elf_phdr *eppnt, int prot, int type,
unsigned long total_size)
{
unsigned long map_addr;
unsigned long size = eppnt->p_filesz + ELF_PAGEOFFSET(eppnt->p_vaddr);
unsigned long off = eppnt->p_offset - ELF_PAGEOFFSET(eppnt->p_vaddr);
addr = ELF_PAGESTART(addr);
size = ELF_PAGEALIGN(size);
/* mmap() will return -EINVAL if given a zero size, but a
* segment with zero filesize is perfectly valid */
if (!size)
return addr;
/*
* total_size is the size of the ELF (interpreter) image.
* The _first_ mmap needs to know the full size, otherwise
* randomization might put this image into an overlapping
* position with the ELF binary image. (since size < total_size)
* So we first map the 'big' image - and unmap the remainder at
* the end. (which unmap is needed for ELF images with holes.)
*/
if (total_size) {
total_size = ELF_PAGEALIGN(total_size);
map_addr = vm_mmap(filep, addr, total_size, prot, type, off);
if (!BAD_ADDR(map_addr))
vm_munmap(map_addr+size, total_size-size);
} else
map_addr = vm_mmap(filep, addr, size, prot, type, off);
return(map_addr);
}
#endif /* !elf_map */
static unsigned long total_mapping_size(struct elf_phdr *cmds, int nr)
{
int i, first_idx = -1, last_idx = -1;
for (i = 0; i < nr; i++) {
if (cmds[i].p_type == PT_LOAD) {
last_idx = i;
if (first_idx == -1)
first_idx = i;
}
}
if (first_idx == -1)
return 0;
return cmds[last_idx].p_vaddr + cmds[last_idx].p_memsz -
ELF_PAGESTART(cmds[first_idx].p_vaddr);
}
/* This is much more generalized than the library routine read function,
so we keep this separate. Technically the library read function
is only provided so that we can read a.out libraries that have
an ELF header */
static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
struct file *interpreter, unsigned long *interp_map_addr,
unsigned long no_base)
{
struct elf_phdr *elf_phdata;
struct elf_phdr *eppnt;
unsigned long load_addr = 0;
int load_addr_set = 0;
unsigned long last_bss = 0, elf_bss = 0;
unsigned long error = ~0UL;
unsigned long total_size;
int retval, i, size;
/* First of all, some simple consistency checks */
if (interp_elf_ex->e_type != ET_EXEC &&
interp_elf_ex->e_type != ET_DYN)
goto out;
if (!elf_check_arch(interp_elf_ex))
goto out;
if (!interpreter->f_op || !interpreter->f_op->mmap)
goto out;
/*
* If the size of this structure has changed, then punt, since
* we will be doing the wrong thing.
*/
if (interp_elf_ex->e_phentsize != sizeof(struct elf_phdr))
goto out;
if (interp_elf_ex->e_phnum < 1 ||
interp_elf_ex->e_phnum > 65536U / sizeof(struct elf_phdr))
goto out;
/* Now read in all of the header information */
size = sizeof(struct elf_phdr) * interp_elf_ex->e_phnum;
if (size > ELF_MIN_ALIGN)
goto out;
elf_phdata = kmalloc(size, GFP_KERNEL);
if (!elf_phdata)
goto out;
retval = kernel_read(interpreter, interp_elf_ex->e_phoff,
(char *)elf_phdata, size);
error = -EIO;
if (retval != size) {
if (retval < 0)
error = retval;
goto out_close;
}
total_size = total_mapping_size(elf_phdata, interp_elf_ex->e_phnum);
if (!total_size) {
error = -EINVAL;
goto out_close;
}
eppnt = elf_phdata;
for (i = 0; i < interp_elf_ex->e_phnum; i++, eppnt++) {
if (eppnt->p_type == PT_LOAD) {
int elf_type = MAP_PRIVATE | MAP_DENYWRITE;
int elf_prot = 0;
unsigned long vaddr = 0;
unsigned long k, map_addr;
if (eppnt->p_flags & PF_R)
elf_prot = PROT_READ;
if (eppnt->p_flags & PF_W)
elf_prot |= PROT_WRITE;
if (eppnt->p_flags & PF_X)
elf_prot |= PROT_EXEC;
vaddr = eppnt->p_vaddr;
if (interp_elf_ex->e_type == ET_EXEC || load_addr_set)
elf_type |= MAP_FIXED;
else if (no_base && interp_elf_ex->e_type == ET_DYN)
load_addr = -vaddr;
map_addr = elf_map(interpreter, load_addr + vaddr,
eppnt, elf_prot, elf_type, total_size);
total_size = 0;
if (!*interp_map_addr)
*interp_map_addr = map_addr;
error = map_addr;
if (BAD_ADDR(map_addr))
goto out_close;
if (!load_addr_set &&
interp_elf_ex->e_type == ET_DYN) {
load_addr = map_addr - ELF_PAGESTART(vaddr);
load_addr_set = 1;
}
/*
* Check to see if the section's size will overflow the
* allowed task size. Note that p_filesz must always be
* <= p_memsize so it's only necessary to check p_memsz.
*/
k = load_addr + eppnt->p_vaddr;
if (BAD_ADDR(k) ||
eppnt->p_filesz > eppnt->p_memsz ||
eppnt->p_memsz > TASK_SIZE ||
TASK_SIZE - eppnt->p_memsz < k) {
error = -ENOMEM;
goto out_close;
}
/*
* Find the end of the file mapping for this phdr, and
* keep track of the largest address we see for this.
*/
k = load_addr + eppnt->p_vaddr + eppnt->p_filesz;
if (k > elf_bss)
elf_bss = k;
/*
* Do the same thing for the memory mapping - between
* elf_bss and last_bss is the bss section.
*/
k = load_addr + eppnt->p_memsz + eppnt->p_vaddr;
if (k > last_bss)
last_bss = k;
}
}
if (last_bss > elf_bss) {
/*
* Now fill out the bss section. First pad the last page up
* to the page boundary, and then perform a mmap to make sure
* that there are zero-mapped pages up to and including the
* last bss page.
*/
if (padzero(elf_bss)) {
error = -EFAULT;
goto out_close;
}
/* What we have mapped so far */
elf_bss = ELF_PAGESTART(elf_bss + ELF_MIN_ALIGN - 1);
/* Map the last of the bss segment */
error = vm_brk(elf_bss, last_bss - elf_bss);
if (BAD_ADDR(error))
goto out_close;
}
error = load_addr;
out_close:
kfree(elf_phdata);
out:
return error;
}
/*
* These are the functions used to load ELF style executables and shared
* libraries. There is no binary dependent code anywhere else.
*/
#define INTERPRETER_NONE 0
#define INTERPRETER_ELF 2
#ifndef STACK_RND_MASK
#define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */
#endif
static unsigned long randomize_stack_top(unsigned long stack_top)
{
unsigned long random_variable = 0;
if ((current->flags & PF_RANDOMIZE) &&
!(current->personality & ADDR_NO_RANDOMIZE)) {
random_variable = (unsigned long) get_random_int();
random_variable &= STACK_RND_MASK;
random_variable <<= PAGE_SHIFT;
}
#ifdef CONFIG_STACK_GROWSUP
return PAGE_ALIGN(stack_top) + random_variable;
#else
return PAGE_ALIGN(stack_top) - random_variable;
#endif
}
static int load_elf_binary(struct linux_binprm *bprm)
{
struct file *interpreter = NULL; /* to shut gcc up */
unsigned long load_addr = 0, load_bias = 0;
int load_addr_set = 0;
char * elf_interpreter = NULL;
unsigned long error;
struct elf_phdr *elf_ppnt, *elf_phdata;
unsigned long elf_bss, elf_brk;
int retval, i;
unsigned int size;
unsigned long elf_entry;
unsigned long interp_load_addr = 0;
unsigned long start_code, end_code, start_data, end_data;
unsigned long reloc_func_desc __maybe_unused = 0;
int executable_stack = EXSTACK_DEFAULT;
unsigned long def_flags = 0;
struct pt_regs *regs = current_pt_regs();
struct {
struct elfhdr elf_ex;
struct elfhdr interp_elf_ex;
} *loc;
loc = kmalloc(sizeof(*loc), GFP_KERNEL);
if (!loc) {
retval = -ENOMEM;
goto out_ret;
}
/* Get the exec-header */
loc->elf_ex = *((struct elfhdr *)bprm->buf);
retval = -ENOEXEC;
/* First of all, some simple consistency checks */
if (memcmp(loc->elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
goto out;
if (loc->elf_ex.e_type != ET_EXEC && loc->elf_ex.e_type != ET_DYN)
goto out;
if (!elf_check_arch(&loc->elf_ex))
goto out;
if (!bprm->file->f_op || !bprm->file->f_op->mmap)
goto out;
/* Now read in all of the header information */
if (loc->elf_ex.e_phentsize != sizeof(struct elf_phdr))
goto out;
if (loc->elf_ex.e_phnum < 1 ||
loc->elf_ex.e_phnum > 65536U / sizeof(struct elf_phdr))
goto out;
size = loc->elf_ex.e_phnum * sizeof(struct elf_phdr);
retval = -ENOMEM;
elf_phdata = kmalloc(size, GFP_KERNEL);
if (!elf_phdata)
goto out;
retval = kernel_read(bprm->file, loc->elf_ex.e_phoff,
(char *)elf_phdata, size);
if (retval != size) {
if (retval >= 0)
retval = -EIO;
goto out_free_ph;
}
elf_ppnt = elf_phdata;
elf_bss = 0;
elf_brk = 0;
start_code = ~0UL;
end_code = 0;
start_data = 0;
end_data = 0;
for (i = 0; i < loc->elf_ex.e_phnum; i++) {
if (elf_ppnt->p_type == PT_INTERP) {
/* This is the program interpreter used for
* shared libraries - for now assume that this
* is an a.out format binary
*/
retval = -ENOEXEC;
if (elf_ppnt->p_filesz > PATH_MAX ||
elf_ppnt->p_filesz < 2)
goto out_free_ph;
retval = -ENOMEM;
elf_interpreter = kmalloc(elf_ppnt->p_filesz,
GFP_KERNEL);
if (!elf_interpreter)
goto out_free_ph;
retval = kernel_read(bprm->file, elf_ppnt->p_offset,
elf_interpreter,
elf_ppnt->p_filesz);
if (retval != elf_ppnt->p_filesz) {
if (retval >= 0)
retval = -EIO;
goto out_free_interp;
}
/* make sure path is NULL terminated */
retval = -ENOEXEC;
if (elf_interpreter[elf_ppnt->p_filesz - 1] != '\0')
goto out_free_interp;
interpreter = open_exec(elf_interpreter);
retval = PTR_ERR(interpreter);
if (IS_ERR(interpreter))
goto out_free_interp;
/*
* If the binary is not readable then enforce
* mm->dumpable = 0 regardless of the interpreter's
* permissions.
*/
would_dump(bprm, interpreter);
retval = kernel_read(interpreter, 0, bprm->buf,
BINPRM_BUF_SIZE);
if (retval != BINPRM_BUF_SIZE) {
if (retval >= 0)
retval = -EIO;
goto out_free_dentry;
}
/* Get the exec headers */
loc->interp_elf_ex = *((struct elfhdr *)bprm->buf);
break;
}
elf_ppnt++;
}
elf_ppnt = elf_phdata;
for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++)
if (elf_ppnt->p_type == PT_GNU_STACK) {
if (elf_ppnt->p_flags & PF_X)
executable_stack = EXSTACK_ENABLE_X;
else
executable_stack = EXSTACK_DISABLE_X;
break;
}
/* Some simple consistency checks for the interpreter */
if (elf_interpreter) {
retval = -ELIBBAD;
/* Not an ELF interpreter */
if (memcmp(loc->interp_elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
goto out_free_dentry;
/* Verify the interpreter has a valid arch */
if (!elf_check_arch(&loc->interp_elf_ex))
goto out_free_dentry;
}
/* Flush all traces of the currently running executable */
retval = flush_old_exec(bprm);
if (retval)
goto out_free_dentry;
/* OK, This is the point of no return */
current->mm->def_flags = def_flags;
/* Do this immediately, since STACK_TOP as used in setup_arg_pages
may depend on the personality. */
SET_PERSONALITY(loc->elf_ex);
if (elf_read_implies_exec(loc->elf_ex, executable_stack))
current->personality |= READ_IMPLIES_EXEC;
if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
current->flags |= PF_RANDOMIZE;
setup_new_exec(bprm);
/* Do this so that we can load the interpreter, if need be. We will
change some of these later */
retval = setup_arg_pages(bprm, randomize_stack_top(STACK_TOP),
executable_stack);
if (retval < 0) {
send_sig(SIGKILL, current, 0);
goto out_free_dentry;
}
current->mm->start_stack = bprm->p;
/* Now we do a little grungy work by mmapping the ELF image into
the correct location in memory. */
for(i = 0, elf_ppnt = elf_phdata;
i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
int elf_prot = 0, elf_flags;
unsigned long k, vaddr;
unsigned long total_size = 0;
if (elf_ppnt->p_type != PT_LOAD)
continue;
if (unlikely (elf_brk > elf_bss)) {
unsigned long nbyte;
/* There was a PT_LOAD segment with p_memsz > p_filesz
before this one. Map anonymous pages, if needed,
and clear the area. */
retval = set_brk(elf_bss + load_bias,
elf_brk + load_bias);
if (retval) {
send_sig(SIGKILL, current, 0);
goto out_free_dentry;
}
nbyte = ELF_PAGEOFFSET(elf_bss);
if (nbyte) {
nbyte = ELF_MIN_ALIGN - nbyte;
if (nbyte > elf_brk - elf_bss)
nbyte = elf_brk - elf_bss;
if (clear_user((void __user *)elf_bss +
load_bias, nbyte)) {
/*
* This bss-zeroing can fail if the ELF
* file specifies odd protections. So
* we don't check the return value
*/
}
}
}
if (elf_ppnt->p_flags & PF_R)
elf_prot |= PROT_READ;
if (elf_ppnt->p_flags & PF_W)
elf_prot |= PROT_WRITE;
if (elf_ppnt->p_flags & PF_X)
elf_prot |= PROT_EXEC;
elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE;
vaddr = elf_ppnt->p_vaddr;
if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) {
elf_flags |= MAP_FIXED;
} else if (loc->elf_ex.e_type == ET_DYN) {
/* Try and get dynamic programs out of the way of the
* default mmap base, as well as whatever program they
* might try to exec. This is because the brk will
* follow the loader, and is not movable. */
#ifdef CONFIG_ARCH_BINFMT_ELF_RANDOMIZE_PIE
/* Memory randomization might have been switched off
* in runtime via sysctl or explicit setting of
* personality flags.
* If that is the case, retain the original non-zero
* load_bias value in order to establish proper
* non-randomized mappings.
*/
if (current->flags & PF_RANDOMIZE)
load_bias = 0;
else
load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
#else
load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
#endif
total_size = total_mapping_size(elf_phdata,
loc->elf_ex.e_phnum);
if (!total_size) {
retval = -EINVAL;
goto out_free_dentry;
}
}
error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt,
elf_prot, elf_flags, total_size);
if (BAD_ADDR(error)) {
send_sig(SIGKILL, current, 0);
retval = IS_ERR((void *)error) ?
PTR_ERR((void*)error) : -EINVAL;
goto out_free_dentry;
}
if (!load_addr_set) {
load_addr_set = 1;
load_addr = (elf_ppnt->p_vaddr - elf_ppnt->p_offset);
if (loc->elf_ex.e_type == ET_DYN) {
load_bias += error -
ELF_PAGESTART(load_bias + vaddr);
load_addr += load_bias;
reloc_func_desc = load_bias;
}
}
k = elf_ppnt->p_vaddr;
if (k < start_code)
start_code = k;
if (start_data < k)
start_data = k;
/*
* Check to see if the section's size will overflow the
* allowed task size. Note that p_filesz must always be
* <= p_memsz so it is only necessary to check p_memsz.
*/
if (BAD_ADDR(k) || elf_ppnt->p_filesz > elf_ppnt->p_memsz ||
elf_ppnt->p_memsz > TASK_SIZE ||
TASK_SIZE - elf_ppnt->p_memsz < k) {
/* set_brk can never work. Avoid overflows. */
send_sig(SIGKILL, current, 0);
retval = -EINVAL;
goto out_free_dentry;
}
k = elf_ppnt->p_vaddr + elf_ppnt->p_filesz;
if (k > elf_bss)
elf_bss = k;
if ((elf_ppnt->p_flags & PF_X) && end_code < k)
end_code = k;
if (end_data < k)
end_data = k;
k = elf_ppnt->p_vaddr + elf_ppnt->p_memsz;
if (k > elf_brk)
elf_brk = k;
}
loc->elf_ex.e_entry += load_bias;
elf_bss += load_bias;
elf_brk += load_bias;
start_code += load_bias;
end_code += load_bias;
start_data += load_bias;
end_data += load_bias;
/* Calling set_brk effectively mmaps the pages that we need
* for the bss and break sections. We must do this before
* mapping in the interpreter, to make sure it doesn't wind
* up getting placed where the bss needs to go.
*/
retval = set_brk(elf_bss, elf_brk);
if (retval) {
send_sig(SIGKILL, current, 0);
goto out_free_dentry;
}
if (likely(elf_bss != elf_brk) && unlikely(padzero(elf_bss))) {
send_sig(SIGSEGV, current, 0);
retval = -EFAULT; /* Nobody gets to see this, but.. */
goto out_free_dentry;
}
if (elf_interpreter) {
unsigned long interp_map_addr = 0;
elf_entry = load_elf_interp(&loc->interp_elf_ex,
interpreter,
&interp_map_addr,
load_bias);
if (!IS_ERR((void *)elf_entry)) {
/*
* load_elf_interp() returns relocation
* adjustment
*/
interp_load_addr = elf_entry;
elf_entry += loc->interp_elf_ex.e_entry;
}
if (BAD_ADDR(elf_entry)) {
force_sig(SIGSEGV, current);
retval = IS_ERR((void *)elf_entry) ?
(int)elf_entry : -EINVAL;
goto out_free_dentry;
}
reloc_func_desc = interp_load_addr;
allow_write_access(interpreter);
fput(interpreter);
kfree(elf_interpreter);
} else {
elf_entry = loc->elf_ex.e_entry;
if (BAD_ADDR(elf_entry)) {
force_sig(SIGSEGV, current);
retval = -EINVAL;
goto out_free_dentry;
}
}
kfree(elf_phdata);
set_binfmt(&elf_format);
#ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES
retval = arch_setup_additional_pages(bprm, !!elf_interpreter);
if (retval < 0) {
send_sig(SIGKILL, current, 0);
goto out;
}
#endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
install_exec_creds(bprm);
retval = create_elf_tables(bprm, &loc->elf_ex,
load_addr, interp_load_addr);
if (retval < 0) {
send_sig(SIGKILL, current, 0);
goto out;
}
/* N.B. passed_fileno might not be initialized? */
current->mm->end_code = end_code;
current->mm->start_code = start_code;
current->mm->start_data = start_data;
current->mm->end_data = end_data;
current->mm->start_stack = bprm->p;
#ifdef arch_randomize_brk
if ((current->flags & PF_RANDOMIZE) && (randomize_va_space > 1)) {
current->mm->brk = current->mm->start_brk =
arch_randomize_brk(current->mm);
#ifdef CONFIG_COMPAT_BRK
current->brk_randomized = 1;
#endif
}
#endif
if (current->personality & MMAP_PAGE_ZERO) {
/* Why this, you ask??? Well SVr4 maps page 0 as read-only,
and some applications "depend" upon this behavior.
Since we do not have the power to recompile these, we
emulate the SVr4 behavior. Sigh. */
error = vm_mmap(NULL, 0, PAGE_SIZE, PROT_READ | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE, 0);
}
#ifdef ELF_PLAT_INIT
/*
* The ABI may specify that certain registers be set up in special
* ways (on i386 %edx is the address of a DT_FINI function, for
* example. In addition, it may also specify (eg, PowerPC64 ELF)
* that the e_entry field is the address of the function descriptor
* for the startup routine, rather than the address of the startup
* routine itself. This macro performs whatever initialization to
* the regs structure is required as well as any relocations to the
* function descriptor entries when executing dynamically links apps.
*/
ELF_PLAT_INIT(regs, reloc_func_desc);
#endif
start_thread(regs, elf_entry, bprm->p);
retval = 0;
out:
kfree(loc);
out_ret:
return retval;
/* error cleanup */
out_free_dentry:
allow_write_access(interpreter);
if (interpreter)
fput(interpreter);
out_free_interp:
kfree(elf_interpreter);
out_free_ph:
kfree(elf_phdata);
goto out;
}
/* This is really simpleminded and specialized - we are loading an
a.out library that is given an ELF header. */
static int load_elf_library(struct file *file)
{
struct elf_phdr *elf_phdata;
struct elf_phdr *eppnt;
unsigned long elf_bss, bss, len;
int retval, error, i, j;
struct elfhdr elf_ex;
error = -ENOEXEC;
retval = kernel_read(file, 0, (char *)&elf_ex, sizeof(elf_ex));
if (retval != sizeof(elf_ex))
goto out;
if (memcmp(elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
goto out;
/* First of all, some simple consistency checks */
if (elf_ex.e_type != ET_EXEC || elf_ex.e_phnum > 2 ||
!elf_check_arch(&elf_ex) || !file->f_op || !file->f_op->mmap)
goto out;
/* Now read in all of the header information */
j = sizeof(struct elf_phdr) * elf_ex.e_phnum;
/* j < ELF_MIN_ALIGN because elf_ex.e_phnum <= 2 */
error = -ENOMEM;
elf_phdata = kmalloc(j, GFP_KERNEL);
if (!elf_phdata)
goto out;
eppnt = elf_phdata;
error = -ENOEXEC;
retval = kernel_read(file, elf_ex.e_phoff, (char *)eppnt, j);
if (retval != j)
goto out_free_ph;
for (j = 0, i = 0; i<elf_ex.e_phnum; i++)
if ((eppnt + i)->p_type == PT_LOAD)
j++;
if (j != 1)
goto out_free_ph;
while (eppnt->p_type != PT_LOAD)
eppnt++;
/* Now use mmap to map the library into memory. */
error = vm_mmap(file,
ELF_PAGESTART(eppnt->p_vaddr),
(eppnt->p_filesz +
ELF_PAGEOFFSET(eppnt->p_vaddr)),
PROT_READ | PROT_WRITE | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE,
(eppnt->p_offset -
ELF_PAGEOFFSET(eppnt->p_vaddr)));
if (error != ELF_PAGESTART(eppnt->p_vaddr))
goto out_free_ph;
elf_bss = eppnt->p_vaddr + eppnt->p_filesz;
if (padzero(elf_bss)) {
error = -EFAULT;
goto out_free_ph;
}
len = ELF_PAGESTART(eppnt->p_filesz + eppnt->p_vaddr +
ELF_MIN_ALIGN - 1);
bss = eppnt->p_memsz + eppnt->p_vaddr;
if (bss > len)
vm_brk(len, bss - len);
error = 0;
out_free_ph:
kfree(elf_phdata);
out:
return error;
}
#ifdef CONFIG_ELF_CORE
/*
* ELF core dumper
*
* Modelled on fs/exec.c:aout_core_dump()
* Jeremy Fitzhardinge <jeremy@sw.oz.au>
*/
/*
* 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;
/*
* arch_vma_name() returns non-NULL for special architecture mappings,
* such as vDSO sections.
*/
if (arch_vma_name(vma))
return true;
return false;
}
/*
* Decide what to dump of a segment, part, all or none.
*/
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;
/* Hugetlb memory check */
if (vma->vm_flags & VM_HUGETLB) {
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 (vma->anon_vma && FILTER(ANON_PRIVATE))
goto whole;
if (vma->vm_file == NULL)
return 0;
if (FILTER(MAPPED_PRIVATE))
goto whole;
/*
* If this looks like the beginning of a DSO or executable mapping,
* check for an ELF header. If we find one, 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)) {
u32 __user *header = (u32 __user *) vma->vm_start;
u32 word;
mm_segment_t fs = get_fs();
/*
* Doing it this way gets the constant folded by GCC.
*/
union {
u32 cmp;
char elfmag[SELFMAG];
} magic;
BUILD_BUG_ON(SELFMAG != sizeof word);
magic.elfmag[EI_MAG0] = ELFMAG0;
magic.elfmag[EI_MAG1] = ELFMAG1;
magic.elfmag[EI_MAG2] = ELFMAG2;
magic.elfmag[EI_MAG3] = ELFMAG3;
/*
* Switch to the user "segment" for get_user(),
* then put back what elf_core_dump() had in place.
*/
set_fs(USER_DS);
if (unlikely(get_user(word, header)))
word = 0;
set_fs(fs);
if (word == magic.cmp)
return PAGE_SIZE;
}
#undef FILTER
return 0;
whole:
return vma->vm_end - vma->vm_start;
}
/* An ELF note in memory */
struct memelfnote
{
const char *name;
int type;
unsigned int datasz;
void *data;
};
static int notesize(struct memelfnote *en)
{
int sz;
sz = sizeof(struct elf_note);
sz += roundup(strlen(en->name) + 1, 4);
sz += roundup(en->datasz, 4);
return sz;
}
#define DUMP_WRITE(addr, nr, foffset) \
do { if (!dump_write(file, (addr), (nr))) return 0; *foffset += (nr); } while(0)
static int alignfile(struct file *file, loff_t *foffset)
{
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), 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
static void fill_elf_header(struct elfhdr *elf, int segs,
u16 machine, u32 flags)
{
memset(elf, 0, sizeof(*elf));
memcpy(elf->e_ident, ELFMAG, SELFMAG);
elf->e_ident[EI_CLASS] = ELF_CLASS;
elf->e_ident[EI_DATA] = ELF_DATA;
elf->e_ident[EI_VERSION] = EV_CURRENT;
elf->e_ident[EI_OSABI] = ELF_OSABI;
elf->e_type = ET_CORE;
elf->e_machine = machine;
elf->e_version = EV_CURRENT;
elf->e_phoff = sizeof(struct elfhdr);
elf->e_flags = flags;
elf->e_ehsize = sizeof(struct elfhdr);
elf->e_phentsize = sizeof(struct elf_phdr);
elf->e_phnum = segs;
return;
}
static void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, loff_t offset)
{
phdr->p_type = PT_NOTE;
phdr->p_offset = offset;
phdr->p_vaddr = 0;
phdr->p_paddr = 0;
phdr->p_filesz = sz;
phdr->p_memsz = 0;
phdr->p_flags = 0;
phdr->p_align = 0;
return;
}
static void fill_note(struct memelfnote *note, const char *name, int type,
unsigned int sz, void *data)
{
note->name = name;
note->type = type;
note->datasz = sz;
note->data = data;
return;
}
/*
* fill up all the fields in prstatus from the given task struct, except
* 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];
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. It shows the
* group-wide total, not its individual thread total.
*/
thread_group_cputime(p, &cputime);
cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
} else {
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 */
memset(psinfo, 0, sizeof(struct elf_prpsinfo));
len = mm->arg_end - mm->arg_start;
if (len >= ELF_PRARGSZ)
len = ELF_PRARGSZ-1;
if (copy_from_user(&psinfo->pr_psargs,
(const char __user *)mm->arg_start, len))
return -EFAULT;
for(i = 0; i < len; i++)
if (psinfo->pr_psargs[i] == 0)
psinfo->pr_psargs[i] = ' ';
psinfo->pr_psargs[len] = 0;
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_sname = (i > 5) ? '.' : "RSDTZW"[i];
psinfo->pr_zomb = psinfo->pr_sname == 'Z';
psinfo->pr_nice = task_nice(p);
psinfo->pr_flag = p->flags;
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;
}
static void fill_auxv_note(struct memelfnote *note, struct mm_struct *mm)
{
elf_addr_t *auxv = (elf_addr_t *) mm->saved_auxv;
int i = 0;
do
i += 2;
while (auxv[i - 2] != AT_NULL);
fill_note(note, "CORE", NT_AUXV, i * sizeof(elf_addr_t), auxv);
}
static void fill_siginfo_note(struct memelfnote *note, user_siginfo_t *csigdata,
const siginfo_t *siginfo)
{
mm_segment_t old_fs = get_fs();
set_fs(KERNEL_DS);
copy_siginfo_to_user((user_siginfo_t __user *) csigdata, siginfo);
set_fs(old_fs);
fill_note(note, "CORE", NT_SIGINFO, sizeof(*csigdata), csigdata);
}
#define MAX_FILE_NOTE_SIZE (4*1024*1024)
/*
* Format of NT_FILE note:
*
* long count -- how many files are mapped
* long page_size -- units for file_ofs
* array of [COUNT] elements of
* long start
* long end
* long file_ofs
* followed by COUNT filenames in ASCII: "FILE1" NUL "FILE2" NUL...
*/
static int fill_files_note(struct memelfnote *note)
{
struct vm_area_struct *vma;
unsigned count, size, names_ofs, remaining, n;
user_long_t *data;
user_long_t *start_end_ofs;
char *name_base, *name_curpos;
/* *Estimated* file count and total data size needed */
count = current->mm->map_count;
size = count * 64;
names_ofs = (2 + 3 * count) * sizeof(data[0]);
alloc:
if (size >= MAX_FILE_NOTE_SIZE) /* paranoia check */
return -EINVAL;
size = round_up(size, PAGE_SIZE);
data = vmalloc(size);
if (!data)
return -ENOMEM;
start_end_ofs = data + 2;
name_base = name_curpos = ((char *)data) + names_ofs;
remaining = size - names_ofs;
count = 0;
for (vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) {
struct file *file;
const char *filename;
file = vma->vm_file;
if (!file)
continue;
filename = d_path(&file->f_path, name_curpos, remaining);
if (IS_ERR(filename)) {
if (PTR_ERR(filename) == -ENAMETOOLONG) {
vfree(data);
size = size * 5 / 4;
goto alloc;
}
continue;
}
/* d_path() fills at the end, move name down */
/* n = strlen(filename) + 1: */
n = (name_curpos + remaining) - filename;
remaining = filename - name_curpos;
memmove(name_curpos, filename, n);
name_curpos += n;
*start_end_ofs++ = vma->vm_start;
*start_end_ofs++ = vma->vm_end;
*start_end_ofs++ = vma->vm_pgoff;
count++;
}
/* Now we know exact count of files, can store it */
data[0] = count;
data[1] = PAGE_SIZE;
/*
* Count usually is less than current->mm->map_count,
* we need to move filenames down.
*/
n = current->mm->map_count - count;
if (n != 0) {
unsigned shift_bytes = n * 3 * sizeof(data[0]);
memmove(name_base - shift_bytes, name_base,
name_curpos - name_base);
name_curpos -= shift_bytes;
}
size = name_curpos - (char *)data;
fill_note(note, "CORE", NT_FILE, size, data);
return 0;
}
#ifdef CORE_DUMP_USE_REGSET
#include <linux/regset.h>
struct elf_thread_core_info {
struct elf_thread_core_info *next;
struct task_struct *task;
struct elf_prstatus prstatus;
struct memelfnote notes[0];
};
struct elf_note_info {
struct elf_thread_core_info *thread;
struct memelfnote psinfo;
struct memelfnote signote;
struct memelfnote auxv;
struct memelfnote files;
user_siginfo_t csigdata;
size_t size;
int thread_notes;
};
/*
* When a regset has a writeback hook, we call it on each thread before
* dumping user memory. On register window machines, this makes sure the
* user memory backing the register data is up to date before we read it.
*/
static void do_thread_regset_writeback(struct task_struct *task,
const struct user_regset *regset)
{
if (regset->writeback)
regset->writeback(task, regset, 1);
}
#ifndef PR_REG_SIZE
#define PR_REG_SIZE(S) sizeof(S)
#endif
#ifndef PRSTATUS_SIZE
#define PRSTATUS_SIZE(S) sizeof(S)
#endif
#ifndef PR_REG_PTR
#define PR_REG_PTR(S) (&((S)->pr_reg))
#endif
#ifndef SET_PR_FPVALID
#define SET_PR_FPVALID(S, V) ((S)->pr_fpvalid = (V))
#endif
static int fill_thread_core_info(struct elf_thread_core_info *t,
const struct user_regset_view *view,
long signr, size_t *total)
{
unsigned int i;
/*
* NT_PRSTATUS is the one special case, because the regset data
* goes into the pr_reg field inside the note contents, rather
* than being the whole note contents. We fill the reset in here.
* We assume that regset 0 is NT_PRSTATUS.
*/
fill_prstatus(&t->prstatus, t->task, signr);
(void) view->regsets[0].get(t->task, &view->regsets[0],
0, PR_REG_SIZE(t->prstatus.pr_reg),
PR_REG_PTR(&t->prstatus), NULL);
fill_note(&t->notes[0], "CORE", NT_PRSTATUS,
PRSTATUS_SIZE(t->prstatus), &t->prstatus);
*total += notesize(&t->notes[0]);
do_thread_regset_writeback(t->task, &view->regsets[0]);
/*
* Each other regset might generate a note too. For each regset
* that has no core_note_type or is inactive, we leave t->notes[i]
* all zero and we'll know to skip writing it later.
*/
for (i = 1; i < view->n; ++i) {
const struct user_regset *regset = &view->regsets[i];
do_thread_regset_writeback(t->task, regset);
if (regset->core_note_type && regset->get &&
(!regset->active || regset->active(t->task, regset))) {
int ret;
size_t size = regset->n * regset->size;
void *data = kmalloc(size, GFP_KERNEL);
if (unlikely(!data))
return 0;
ret = regset->get(t->task, regset,
0, size, data, NULL);
if (unlikely(ret))
kfree(data);
else {
if (regset->core_note_type != NT_PRFPREG)
fill_note(&t->notes[i], "LINUX",
regset->core_note_type,
size, data);
else {
SET_PR_FPVALID(&t->prstatus, 1);
fill_note(&t->notes[i], "CORE",
NT_PRFPREG, size, data);
}
*total += notesize(&t->notes[i]);
}
}
}
return 1;
}
static int fill_note_info(struct elfhdr *elf, int phdrs,
struct elf_note_info *info,
siginfo_t *siginfo, struct pt_regs *regs)
{
struct task_struct *dump_task = current;
const struct user_regset_view *view = task_user_regset_view(dump_task);
struct elf_thread_core_info *t;
struct elf_prpsinfo *psinfo;
struct core_thread *ct;
unsigned int i;
info->size = 0;
info->thread = NULL;
psinfo = kmalloc(sizeof(*psinfo), GFP_KERNEL);
if (psinfo == NULL) {
info->psinfo.data = NULL; /* So we don't free this wrongly */
return 0;
}
fill_note(&info->psinfo, "CORE", NT_PRPSINFO, sizeof(*psinfo), psinfo);
/*
* Figure out how many notes we're going to need for each thread.
*/
info->thread_notes = 0;
for (i = 0; i < view->n; ++i)
if (view->regsets[i].core_note_type != 0)
++info->thread_notes;
/*
* Sanity check. We rely on regset 0 being in NT_PRSTATUS,
* since it is our one special case.
*/
if (unlikely(info->thread_notes == 0) ||
unlikely(view->regsets[0].core_note_type != NT_PRSTATUS)) {
WARN_ON(1);
return 0;
}
/*
* Initialize the ELF file header.
*/
fill_elf_header(elf, phdrs,
view->e_machine, view->e_flags);
/*
* Allocate a structure for each thread.
*/
for (ct = &dump_task->mm->core_state->dumper; ct; ct = ct->next) {
t = kzalloc(offsetof(struct elf_thread_core_info,
notes[info->thread_notes]),
GFP_KERNEL);
if (unlikely(!t))
return 0;
t->task = ct->task;
if (ct->task == dump_task || !info->thread) {
t->next = info->thread;
info->thread = t;
} else {
/*
* Make sure to keep the original task at
* the head of the list.
*/
t->next = info->thread->next;
info->thread->next = t;
}
}
/*
* Now fill in each thread's information.
*/
for (t = info->thread; t != NULL; t = t->next)
if (!fill_thread_core_info(t, view, siginfo->si_signo, &info->size))
return 0;
/*
* Fill in the two process-wide notes.
*/
fill_psinfo(psinfo, dump_task->group_leader, dump_task->mm);
info->size += notesize(&info->psinfo);
fill_siginfo_note(&info->signote, &info->csigdata, siginfo);
info->size += notesize(&info->signote);
fill_auxv_note(&info->auxv, current->mm);
info->size += notesize(&info->auxv);
if (fill_files_note(&info->files) == 0)
info->size += notesize(&info->files);
return 1;
}
static size_t get_note_info_size(struct elf_note_info *info)
{
return info->size;
}
/*
* Write all the notes for each thread. When writing the first thread, the
* process-wide notes are interleaved after the first thread-specific note.
*/
static int write_note_info(struct elf_note_info *info,
struct file *file, loff_t *foffset)
{
bool first = 1;
struct elf_thread_core_info *t = info->thread;
do {
int i;
if (!writenote(&t->notes[0], file, foffset))
return 0;
if (first && !writenote(&info->psinfo, file, foffset))
return 0;
if (first && !writenote(&info->signote, file, foffset))
return 0;
if (first && !writenote(&info->auxv, file, foffset))
return 0;
if (first && info->files.data &&
!writenote(&info->files, file, foffset))
return 0;
for (i = 1; i < info->thread_notes; ++i)
if (t->notes[i].data &&
!writenote(&t->notes[i], file, foffset))
return 0;
first = 0;
t = t->next;
} while (t);
return 1;
}
static void free_note_info(struct elf_note_info *info)
{
struct elf_thread_core_info *threads = info->thread;
while (threads) {
unsigned int i;
struct elf_thread_core_info *t = threads;
threads = t->next;
WARN_ON(t->notes[0].data && t->notes[0].data != &t->prstatus);
for (i = 1; i < info->thread_notes; ++i)
kfree(t->notes[i].data);
kfree(t);
}
kfree(info->psinfo.data);
vfree(info->files.data);
}
#else
/* Here is the structure in which status of each thread is captured. */
struct elf_thread_status
{
struct list_head list;
struct elf_prstatus prstatus; /* NT_PRSTATUS */
elf_fpregset_t fpu; /* NT_PRFPREG */
struct task_struct *thread;
#ifdef ELF_CORE_COPY_XFPREGS
elf_fpxregset_t xfpu; /* ELF_CORE_XFPREG_TYPE */
#endif
struct memelfnote notes[3];
int num_notes;
};
/*
* In order to add the specific thread information for the elf file format,
* we need to keep a linked list of every threads pr_status and then create
* a single section for them in the final core file.
*/
static int elf_dump_thread_status(long signr, struct elf_thread_status *t)
{
int sz = 0;
struct task_struct *p = t->thread;
t->num_notes = 0;
fill_prstatus(&t->prstatus, p, signr);
elf_core_copy_task_regs(p, &t->prstatus.pr_reg);
fill_note(&t->notes[0], "CORE", NT_PRSTATUS, sizeof(t->prstatus),
&(t->prstatus));
t->num_notes++;
sz += notesize(&t->notes[0]);
if ((t->prstatus.pr_fpvalid = elf_core_copy_task_fpregs(p, NULL,
&t->fpu))) {
fill_note(&t->notes[1], "CORE", NT_PRFPREG, sizeof(t->fpu),
&(t->fpu));
t->num_notes++;
sz += notesize(&t->notes[1]);
}
#ifdef ELF_CORE_COPY_XFPREGS
if (elf_core_copy_task_xfpregs(p, &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]);
}
#endif
return sz;
}
struct elf_note_info {
struct memelfnote *notes;
struct memelfnote *notes_files;
struct elf_prstatus *prstatus; /* NT_PRSTATUS */
struct elf_prpsinfo *psinfo; /* NT_PRPSINFO */
struct list_head thread_list;
elf_fpregset_t *fpu;
#ifdef ELF_CORE_COPY_XFPREGS
elf_fpxregset_t *xfpu;
#endif
user_siginfo_t csigdata;
int thread_status_size;
int numnote;
};
static int elf_note_info_init(struct elf_note_info *info)
{
memset(info, 0, sizeof(*info));
INIT_LIST_HEAD(&info->thread_list);
/* Allocate space for ELF notes */
info->notes = kmalloc(8 * sizeof(struct memelfnote), GFP_KERNEL);
if (!info->notes)
return 0;
info->psinfo = kmalloc(sizeof(*info->psinfo), GFP_KERNEL);
if (!info->psinfo)
return 0;
info->prstatus = kmalloc(sizeof(*info->prstatus), GFP_KERNEL);
if (!info->prstatus)
return 0;
info->fpu = kmalloc(sizeof(*info->fpu), GFP_KERNEL);
if (!info->fpu)
return 0;
#ifdef ELF_CORE_COPY_XFPREGS
info->xfpu = kmalloc(sizeof(*info->xfpu), GFP_KERNEL);
if (!info->xfpu)
return 0;
#endif
return 1;
}
static int fill_note_info(struct elfhdr *elf, int phdrs,
struct elf_note_info *info,
siginfo_t *siginfo, struct pt_regs *regs)
{
struct list_head *t;
if (!elf_note_info_init(info))
return 0;
if (siginfo->si_signo) {
struct core_thread *ct;
struct elf_thread_status *ets;
for (ct = current->mm->core_state->dumper.next;
ct; ct = ct->next) {
ets = kzalloc(sizeof(*ets), GFP_KERNEL);
if (!ets)
return 0;
ets->thread = ct->task;
list_add(&ets->list, &info->thread_list);
}
list_for_each(t, &info->thread_list) {
int sz;
ets = list_entry(t, struct elf_thread_status, list);
sz = elf_dump_thread_status(siginfo->si_signo, ets);
info->thread_status_size += sz;
}
}
/* now collect the dump for the current */
memset(info->prstatus, 0, sizeof(*info->prstatus));
fill_prstatus(info->prstatus, current, siginfo->si_signo);
elf_core_copy_regs(&info->prstatus->pr_reg, regs);
/* Set up header */
fill_elf_header(elf, phdrs, ELF_ARCH, ELF_CORE_EFLAGS);
/*
* Set up the notes in similar form to SVR4 core dumps made
* with info from their /proc.
*/
fill_note(info->notes + 0, "CORE", NT_PRSTATUS,
sizeof(*info->prstatus), info->prstatus);
fill_psinfo(info->psinfo, current->group_leader, current->mm);
fill_note(info->notes + 1, "CORE", NT_PRPSINFO,
sizeof(*info->psinfo), info->psinfo);
fill_siginfo_note(info->notes + 2, &info->csigdata, siginfo);
fill_auxv_note(info->notes + 3, current->mm);
info->numnote = 4;
if (fill_files_note(info->notes + info->numnote) == 0) {
info->notes_files = info->notes + info->numnote;
info->numnote++;
}
/* Try to dump the FPU. */
info->prstatus->pr_fpvalid = elf_core_copy_task_fpregs(current, regs,
info->fpu);
if (info->prstatus->pr_fpvalid)
fill_note(info->notes + info->numnote++,
"CORE", NT_PRFPREG, sizeof(*info->fpu), info->fpu);
#ifdef ELF_CORE_COPY_XFPREGS
if (elf_core_copy_task_xfpregs(current, info->xfpu))
fill_note(info->notes + info->numnote++,
"LINUX", ELF_CORE_XFPREG_TYPE,
sizeof(*info->xfpu), info->xfpu);
#endif
return 1;
}
static size_t get_note_info_size(struct elf_note_info *info)
{
int sz = 0;
int i;
for (i = 0; i < info->numnote; i++)
sz += notesize(info->notes + i);
sz += info->thread_status_size;
return sz;
}
static int write_note_info(struct elf_note_info *info,
struct file *file, loff_t *foffset)
{
int i;
struct list_head *t;
for (i = 0; i < info->numnote; i++)
if (!writenote(info->notes + i, file, foffset))
return 0;
/* write out the thread status notes section */
list_for_each(t, &info->thread_list) {
struct elf_thread_status *tmp =
list_entry(t, struct elf_thread_status, list);
for (i = 0; i < tmp->num_notes; i++)
if (!writenote(&tmp->notes[i], file, foffset))
return 0;
}
return 1;
}
static void free_note_info(struct elf_note_info *info)
{
while (!list_empty(&info->thread_list)) {
struct list_head *tmp = info->thread_list.next;
list_del(tmp);
kfree(list_entry(tmp, struct elf_thread_status, list));
}
/* Free data possibly allocated by fill_files_note(): */
if (info->notes_files)
vfree(info->notes_files->data);
kfree(info->prstatus);
kfree(info->psinfo);
kfree(info->notes);
kfree(info->fpu);
#ifdef ELF_CORE_COPY_XFPREGS
kfree(info->xfpu);
#endif
}
#endif
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;
}
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;
}
static size_t elf_core_vma_data_size(struct vm_area_struct *gate_vma,
unsigned long mm_flags)
{
struct vm_area_struct *vma;
size_t size = 0;
for (vma = first_vma(current, gate_vma); vma != NULL;
vma = next_vma(vma, gate_vma))
size += vma_dump_size(vma, mm_flags);
return size;
}
/*
* Actual dumper
*
* This is a two-pass process; first we find the offsets of the bits,
* and then they are actually written out. If we run out of core limit
* we just truncate.
*/
static int elf_core_dump(struct coredump_params *cprm)
{
int has_dumped = 0;
mm_segment_t fs;
int segs;
size_t size = 0;
struct vm_area_struct *vma, *gate_vma;
struct elfhdr *elf = NULL;
loff_t offset = 0, dataoff, foffset;
struct elf_note_info info = { };
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.
*
* This is because those proceses that could possibly change map_count
* or the mmap / vma pages are now blocked in do_exit on current
* finishing this core dump.
*
* Only ptrace can touch these memory addresses, but it doesn't change
* the map_count or the pages allocated. So no possibility of crashing
* exists while dumping the mm->vm_next areas to the core file.
*/
/* alloc memory for large data structures: too large to be on stack */
elf = kmalloc(sizeof(*elf), GFP_KERNEL);
if (!elf)
goto out;
/*
* The number of segs are recored into ELF header as 16bit value.
* Please check DEFAULT_MAX_MAP_COUNT definition when you modify here.
*/
segs = current->mm->map_count;
segs += elf_core_extra_phdrs();
gate_vma = get_gate_vma(current->mm);
if (gate_vma != NULL)
segs++;
/* 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;
/*
* Collect all the non-memory information about the process for the
* notes. This also sets up the file header.
*/
if (!fill_note_info(elf, e_phnum, &info, cprm->siginfo, cprm->regs))
goto cleanup;
has_dumped = 1;
fs = get_fs();
set_fs(KERNEL_DS);
offset += sizeof(*elf); /* Elf header */
offset += segs * sizeof(struct elf_phdr); /* Program headers */
foffset = offset;
/* Write notes phdr entry */
{
size_t sz = get_note_info_size(&info);
sz += elf_coredump_extra_notes_size();
phdr4note = kmalloc(sizeof(*phdr4note), GFP_KERNEL);
if (!phdr4note)
goto end_coredump;
fill_elf_note_phdr(phdr4note, sz, offset);
offset += sz;
}
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
offset += elf_core_vma_data_size(gate_vma, 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 (vma = first_vma(current, gate_vma); vma != NULL;
vma = next_vma(vma, gate_vma)) {
struct elf_phdr phdr;
phdr.p_type = PT_LOAD;
phdr.p_offset = offset;
phdr.p_vaddr = vma->vm_start;
phdr.p_paddr = 0;
phdr.p_filesz = vma_dump_size(vma, cprm->mm_flags);
phdr.p_memsz = vma->vm_end - vma->vm_start;
offset += phdr.p_filesz;
phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
if (vma->vm_flags & VM_WRITE)
phdr.p_flags |= PF_W;
if (vma->vm_flags & VM_EXEC)
phdr.p_flags |= PF_X;
phdr.p_align = ELF_EXEC_PAGESIZE;
size += sizeof(phdr);
if (size > cprm->limit
|| !dump_write(cprm->file, &phdr, sizeof(phdr)))
goto end_coredump;
}
if (!elf_core_write_extra_phdrs(cprm->file, offset, &size, cprm->limit))
goto end_coredump;
/* write out the notes section */
if (!write_note_info(&info, cprm->file, &foffset))
goto end_coredump;
if (elf_coredump_extra_notes_write(cprm->file, &foffset))
goto end_coredump;
/* Align to page */
if (!dump_seek(cprm->file, dataoff - foffset))
goto end_coredump;
for (vma = first_vma(current, gate_vma); vma != NULL;
vma = next_vma(vma, gate_vma)) {
unsigned long addr;
unsigned long end;
end = vma->vm_start + vma_dump_size(vma, cprm->mm_flags);
for (addr = vma->vm_start; addr < end; addr += PAGE_SIZE) {
struct page *page;
int stop;
page = get_dump_page(addr);
if (page) {
void *kaddr = kmap(page);
stop = ((size += PAGE_SIZE) > cprm->limit) ||
!dump_write(cprm->file, kaddr,
PAGE_SIZE);
kunmap(page);
page_cache_release(page);
} else
stop = !dump_seek(cprm->file, PAGE_SIZE);
if (stop)
goto end_coredump;
}
}
if (!elf_core_write_extra_data(cprm->file, &size, cprm->limit))
goto end_coredump;
if (e_phnum == PN_XNUM) {
size += sizeof(*shdr4extnum);
if (size > cprm->limit
|| !dump_write(cprm->file, shdr4extnum,
sizeof(*shdr4extnum)))
goto end_coredump;
}
end_coredump:
set_fs(fs);
cleanup:
free_note_info(&info);
kfree(shdr4extnum);
kfree(phdr4note);
kfree(elf);
out:
return has_dumped;
}
#endif /* CONFIG_ELF_CORE */
static int __init init_elf_binfmt(void)
{
register_binfmt(&elf_format);
return 0;
}
static void __exit exit_elf_binfmt(void)
{
/* Remove the COFF and ELF loaders. */
unregister_binfmt(&elf_format);
}
core_initcall(init_elf_binfmt);
module_exit(exit_elf_binfmt);
MODULE_LICENSE("GPL");