* Linux 6.6.144
@ 2026-07-04 11:59 Greg Kroah-Hartman
2026-07-04 11:59 ` Greg Kroah-Hartman
0 siblings, 1 reply; 2+ messages in thread
From: Greg Kroah-Hartman @ 2026-07-04 11:59 UTC (permalink / raw)
To: linux-kernel, akpm, torvalds, stable; +Cc: lwn, jslaby, Greg Kroah-Hartman
I'm announcing the release of the 6.6.144 kernel.
All users of the 6.6 kernel series must upgrade.
The updated 6.6.y git tree can be found at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git linux-6.6.y
and can be browsed at the normal kernel.org git web browser:
https://git.kernel.org/?p=linux/kernel/git/stable/linux-stable.git;a=summary
thanks,
greg k-h
------------
Documentation/userspace-api/ioctl/ioctl-number.rst | 463 ++--
Makefile | 2
arch/arm/mm/alignment.c | 4
arch/arm/mm/fault.c | 94
arch/arm64/Kconfig | 1
arch/mips/dec/prom/console.c | 7
arch/x86/kvm/hyperv.c | 5
arch/x86/kvm/mmu/mmu.c | 28
arch/x86/kvm/svm/sev.c | 1
arch/x86/kvm/vmx/vmx.c | 4
arch/x86/kvm/x86.c | 7
block/blk-cgroup.c | 21
drivers/base/memory.c | 3
drivers/bluetooth/btmtk.c | 15
drivers/char/agp/amd64-agp.c | 2
drivers/crypto/intel/qat/qat_common/adf_cfg_common.h | 32
drivers/crypto/intel/qat/qat_common/adf_cfg_user.h | 38
drivers/crypto/intel/qat/qat_common/adf_common_drv.h | 3
drivers/crypto/intel/qat/qat_common/adf_ctl_drv.c | 413 ---
drivers/crypto/intel/qat/qat_common/adf_dev_mgr.c | 70
drivers/fpga/of-fpga-region.c | 3
drivers/gpu/drm/amd/display/dc/bios/bios_parser.c | 15
drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c | 27
drivers/gpu/drm/amd/display/dc/bios/bios_parser_helper.h | 5
drivers/gpu/drm/v3d/v3d_drv.h | 8
drivers/gpu/drm/v3d/v3d_gem.c | 5
drivers/gpu/drm/v3d/v3d_irq.c | 24
drivers/gpu/drm/v3d/v3d_sched.c | 36
drivers/hv/hv_kvp.c | 25
drivers/hv/vmbus_drv.c | 29
drivers/i2c/i2c-stub.c | 5
drivers/infiniband/hw/bnxt_re/ib_verbs.c | 2
drivers/irqchip/irq-imgpdc.c | 6
drivers/media/test-drivers/vidtv/vidtv_mux.c | 8
drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c | 8
drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h | 1
drivers/net/wan/hdlc_ppp.c | 15
drivers/net/wireless/ath/ath11k/dp.c | 1
drivers/net/wireless/intel/iwlwifi/mvm/ptp.c | 2
drivers/net/wireless/mediatek/mt76/mt76x2/usb.c | 1
drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h | 2
drivers/net/wireless/realtek/rtw88/tx.c | 7
drivers/net/wireless/realtek/rtw88/usb.c | 13
drivers/ntb/hw/epf/ntb_hw_epf.c | 3
drivers/nvme/target/tcp.c | 29
drivers/power/reset/linkstation-poweroff.c | 2
drivers/regulator/core.c | 10
drivers/rpmsg/rpmsg_char.c | 15
drivers/slimbus/qcom-ngd-ctrl.c | 39
drivers/tty/serial/8250/8250_dw.c | 4
drivers/tty/serial/qcom_geni_serial.c | 9
drivers/tty/vt/vc_screen.c | 2
drivers/video/fbdev/core/fbmem.c | 12
drivers/video/fbdev/core/fbsysfs.c | 10
drivers/video/fbdev/core/modedb.c | 5
fs/dlm/lockspace.c | 2
fs/eventpoll.c | 142 -
fs/exfat/dir.c | 4
fs/f2fs/acl.c | 18
fs/f2fs/data.c | 16
fs/f2fs/extent_cache.c | 19
fs/f2fs/file.c | 9
fs/f2fs/inode.c | 9
fs/file_table.c | 46
fs/fuse/dev.c | 23
fs/fuse/file.c | 8
fs/gfs2/super.c | 1
fs/internal.h | 3
fs/nfs/client.c | 1
fs/nfs/pnfs.c | 2
fs/nfs/pnfs_nfs.c | 4
fs/nfsd/nfs2acl.c | 17
fs/nfsd/nfs3acl.c | 17
fs/nfsd/nfs4recover.c | 3
fs/nfsd/nfs4xdr.c | 3
fs/ntfs3/xattr.c | 12
fs/ocfs2/suballoc.c | 22
fs/open.c | 7
fs/overlayfs/file.c | 8
fs/smb/server/smb2pdu.c | 5
fs/smb/server/smbacl.c | 4
include/keys/request_key_auth-type.h | 2
include/linux/bpf_verifier.h | 4
include/linux/err.h | 12
include/linux/file.h | 2
include/linux/fs.h | 15
include/linux/kvm_host.h | 7
include/linux/lsm_audit.h | 2
include/linux/lsm_hook_defs.h | 5
include/linux/lsm_hooks.h | 1
include/linux/ring_buffer.h | 4
include/linux/security.h | 22
include/linux/skmsg.h | 15
include/net/phonet/pn_dev.h | 2
include/net/tc_act/tc_pedit.h | 1
kernel/bpf/cgroup.c | 2
kernel/bpf/verifier.c | 364 ++-
kernel/locking/rtmutex.c | 3
kernel/locking/rtmutex_api.c | 2
kernel/trace/bpf_trace.c | 4
kernel/trace/ftrace.c | 68
kernel/trace/ring_buffer.c | 67
kernel/trace/trace.c | 14
kernel/trace/trace_kdb.c | 8
lib/debugobjects.c | 56
net/9p/client.c | 3
net/batman-adv/bat_iv_ogm.c | 11
net/batman-adv/bat_v.c | 1
net/batman-adv/bat_v_ogm.c | 23
net/batman-adv/bridge_loop_avoidance.c | 28
net/batman-adv/distributed-arp-table.c | 12
net/batman-adv/fragmentation.c | 22
net/batman-adv/fragmentation.h | 3
net/batman-adv/netlink.c | 8
net/batman-adv/routing.c | 64
net/batman-adv/tp_meter.c | 113 -
net/batman-adv/translation-table.c | 32
net/batman-adv/tvlv.c | 69
net/batman-adv/types.h | 21
net/core/filter.c | 27
net/core/skmsg.c | 2
net/ipv4/ip_output.c | 20
net/ipv6/ip6_output.c | 22
net/ipv6/ip6_vti.c | 1
net/mac802154/llsec.c | 14
net/mptcp/pm_userspace.c | 13
net/netfilter/nf_tables_api.c | 2
net/phonet/pn_dev.c | 12
net/phonet/pn_netlink.c | 23
net/rxrpc/input.c | 13
net/sched/act_pedit.c | 77
net/tipc/crypto.c | 9
net/tls/tls_sw.c | 4
net/unix/af_unix.c | 3
net/unix/garbage.c | 2
scripts/link-vmlinux.sh | 4
scripts/sorttable.c | 1119 +++++++++-
scripts/sorttable.h | 500 ----
security/apparmor/include/policy_unpack.h | 19
security/apparmor/lsm.c | 16
security/apparmor/policy.c | 8
security/keys/internal.h | 2
security/keys/keyctl.c | 24
security/keys/keyctl_pkey.c | 9
security/keys/request_key_auth.c | 33
security/security.c | 110
security/selinux/hooks.c | 242 +-
security/selinux/include/objsec.h | 11
tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c | 34
tools/testing/selftests/bpf/progs/kprobe_multi_sleepable.c | 25
tools/testing/selftests/bpf/progs/verifier_scalar_ids.c | 253 +-
tools/testing/selftests/bpf/progs/verifier_spill_fill.c | 4
tools/testing/selftests/bpf/progs/verifier_subprog_precision.c | 2
tools/testing/selftests/bpf/verifier/precise.c | 4
tools/testing/selftests/ptp/testptp.c | 19
155 files changed, 3589 insertions(+), 2191 deletions(-)
Amir Goldstein (1):
fs: prepare for adding LSM blob to backing_file
André Draszik (1):
regulator: core: fix locking in regulator_resolve_supply() error path
Arnd Bergmann (1):
err.h: use __always_inline on all error pointer helpers
Ashutosh Desai (1):
KVM: SVM: Fix page overflow in sev_dbg_crypt() for ENCRYPT path
Bagas Sanjaya (1):
Documentation: ioctl-number: Extend "Include File" column width
Bitterblue Smith (1):
wifi: rtlwifi: rtl8821ae: Fix C2H bit location in RX descriptor
Bjoern Doebel (1):
ring-buffer: Remove ring_buffer_read_prepare_sync()
Bjorn Andersson (2):
slimbus: qcom-ngd-ctrl: Fix up platform_driver registration
slimbus: qcom-ngd-ctrl: Balance pm_runtime enablement for NGD
Bryam Vargas (1):
apparmor: mediate the implicit connect of TCP fast open sendmsg
Chaitanya Kulkarni (1):
nvmet-tcp: fix race between ICReq handling and queue teardown
Christian Brauner (8):
file: add fput() cleanup helper
eventpoll: use hlist_is_singular_node() in __ep_remove()
eventpoll: split __ep_remove()
eventpoll: kill __ep_remove()
eventpoll: drop vestigial __ prefix from ep_remove_{file,epi}()
eventpoll: rename ep_remove_safe() back to ep_remove()
eventpoll: move epi_fget() up
eventpoll: fix ep_remove struct eventpoll / struct file UAF
David Howells (1):
rxrpc: Fix the ACK parser to extract the SACK table for parsing
Davidlohr Bueso (1):
locking/rtmutex: Skip remove_waiter() when waiter is not enqueued
Dawei Feng (1):
bpf: use kvfree() for replaced sysctl write buffer
Dexuan Cui (1):
Drivers: hv: vmbus: Improve the logic of reserving fb_mmio on Gen2 VMs
Dominik Woźniak (1):
nfsd: check get_user() return when reading princhashlen
Dongli Zhang (1):
KVM: VMX: Update SVI during runtime APICv activation
Doruk Tan Ozturk (2):
mac802154: llsec: add skb_cow_data() before in-place crypto
tipc: fix slab-use-after-free Read in tipc_aead_decrypt_done
Eduard Zingerman (4):
bpf: Track equal scalars history on per-instruction level
bpf: Remove mark_precise_scalar_ids()
selftests/bpf: Tests for per-insn sync_linked_regs() precision tracking
selftests/bpf: Update comments find_equal_scalars->sync_linked_regs
Eric Dumazet (2):
ip6_vti: set netns_immutable on the fallback device.
inet: add indirect call wrapper for getfrag() calls
Fan Wu (1):
hdlc_ppp: sync per-proto timers before freeing hdlc state
Florian Westphal (1):
netfilter: nf_tables: always walk all pending catchall elements
Georgi Djakov (1):
drivers/base/memory: set mem->altmap after successful device registration
Gil Portnoy (1):
ksmbd: reject non-VALID session in compound request branch
Giovanni Cabiddu (1):
crypto: qat - remove unused character device and IOCTLs
Greg Kroah-Hartman (1):
Linux 6.6.144
Guannan Wang (1):
NFSD: Fix SECINFO_NO_NAME decode error cleanup
Guenter Roeck (1):
ftrace: Do not over-allocate ftrace memory
Harry Wentland (1):
drm/amd/display: Bound VBIOS record-chain walk loops
Helen Koike (1):
debugobjects: Do not fill_pool() if pi_blocked_on
Hem Parekh (1):
ksmbd: fix out-of-bounds read in smb_check_perm_dacl()
Herbert Xu (1):
crypto: qat - Return pointer directly in adf_ctl_alloc_resources
Hyunwoo Kim (1):
KVM: x86: hyper-v: Bound the bank index when querying sparse banks
Ian Bridges (2):
fbdev: fix use-after-free in store_modes()
fbdev: Fix fb_new_modelist to prevent null-ptr-deref in fb_videomode_to_var
Jann Horn (1):
fuse: limit FUSE_NOTIFY_RETRIEVE to uptodate folios
Jarkko Sakkinen (1):
KEYS: fix overflow in keyctl_pkey_params_get_2()
Jeff Layton (1):
nfsd: fix posix_acl leak on SETACL decode failure
Jiexun Wang (1):
af_unix: Reject SIOCATMARK on non-stream sockets
Joanne Koong (1):
fuse: re-lock request before replacing page cache folio
Jose Ignacio Tornos Martinez (1):
wifi: ath11k: fix warning when unbinding
Junjie Cao (1):
wifi: iwlwifi: mvm: fix race condition in PTP removal
Koichiro Den (1):
NTB: epf: Avoid pci_iounmap() with offset when PEER_SPAD and CONFIG share BAR
Konstantin Komarov (1):
ntfs3: reject direct userspace writes to reserved $LX* xattrs
Kuniyuki Iwashima (3):
phonet: Pass ifindex to fill_addr().
phonet: Pass net and ifindex to phonet_address_notify().
af_unix: Set gc_in_progress to true in unix_gc().
Lord Ulf Henrik Holmberg (1):
RDMA/bnxt_re: zero shared page before exposing to userspace
Luka Gejak (2):
wifi: rtw88: increase TX report timeout to fix race condition
wifi: rtw88: usb: fix memory leaks on USB write failures
Maciej W. Rozycki (1):
MIPS: DEC: Prevent initial console buffer from landing in XKPHYS
Markus Elfring (1):
NFS: Prevent resource leak in nfs_alloc_server()
Maíra Canal (2):
drm/v3d: Store the active job inside the queue's state
drm/v3d: Skip CSD when it has zeroed workgroups
Michael Bommarito (2):
exfat: fix potential use-after-free in exfat_find_dir_entry()
NFSv4/pNFS: reject zero-length r_addr in nfs4_decode_mp_ds_addr
Michal Koutný (1):
blk-cgroup: fix UAF in __blkcg_rstat_flush()
Miklos Szeredi (1):
virtiofs: fix UAF on submount umount
Mingyu Wang (1):
agp/amd64: Fix broken error propagation in agp_amd64_probe()
Paolo Bonzini (1):
KVM: x86: Fix shadow paging use-after-free due to unexpected role
Paul Moore (2):
lsm: add backing_file LSM hooks
selinux: fix overlayfs mmap() and mprotect() access checks
Pauli Virtanen (1):
Bluetooth: btmtk: accept too short WMT FUNC_CTRL events
Petr Machata (1):
Revert "ptp: add testptp mask test"
Qingshuang Fu (1):
irqchip/imgpdc: Fix resource leak, add missing chained handler cleanup on remove
Rajat Gupta (1):
net/sched: fix pedit partial COW leading to page cache corruption
Ruslan Valiyev (2):
media: vidtv: fix NULL pointer dereference in vidtv_mux_push_si
apparmor: fix use-after-free in rawdata dedup loop
Russell King (Oracle) (4):
ARM: group is_permission_fault() with is_translation_fault()
ARM: allow __do_kernel_fault() to report execution of memory faults
ARM: fix hash_name() fault
ARM: fix branch predictor hardening
Santosh Kalluri (1):
net: phonet: free phonet_device after RCU grace period
Sean Christopherson (1):
KVM: x86/mmu: Ensure hugepage is in by slot before checking max mapping level
Sebastian Andrzej Siewior (2):
debugobjects: Allow to refill the pool before SYSTEM_SCHEDULING
debugobjects: Use LD_WAIT_CONFIG instead of LD_WAIT_SLEEP
Shaomin Chen (1):
keys: Pin request_key_auth payload in instantiate paths
Steffen Persvold (1):
fbdev: modedb: Fix misaligned fields in the 1920x1080-60 mode
Stepan Ionichev (1):
serial: 8250_dw: unregister 8250 port if clk_notifier_register() fails
Steven Rostedt (25):
scripts/sorttable: Remove unused macro defines
scripts/sorttable: Remove unused write functions
scripts/sorttable: Remove unneeded Elf_Rel
scripts/sorttable: Have the ORC code use the _r() functions to read
scripts/sorttable: Make compare_extable() into two functions
scripts/sorttable: Convert Elf_Ehdr to union
scripts/sorttable: Replace Elf_Shdr Macro with a union
scripts/sorttable: Convert Elf_Sym MACRO over to a union
scripts/sorttable: Add helper functions for Elf_Ehdr
scripts/sorttable: Add helper functions for Elf_Shdr
scripts/sorttable: Add helper functions for Elf_Sym
scripts/sorttable: Use uint64_t for mcount sorting
scripts/sorttable: Move code from sorttable.h into sorttable.c
scripts/sorttable: Get start/stop_mcount_loc from ELF file directly
scripts/sorttable: Use a structure of function pointers for elf helpers
arm64: scripts/sorttable: Implement sorting mcount_loc at boot for arm64
scripts/sorttable: Have mcount rela sort use direct values
scripts/sorttable: Always use an array for the mcount_loc sorting
scripts/sorttable: Zero out weak functions in mcount_loc table
ftrace: Update the mcount_loc check of skipped entries
ftrace: Have ftrace pages output reflect freed pages
ftrace: Test mcount_loc addr before calling ftrace_call_addr()
ftrace: Check against is_kernel_text() instead of kaslr_offset()
scripts/sorttable: Use normal sort if theres no relocs in the mcount section
scripts/sorttable: Allow matches to functions before function entry
Sunmin Jeong (1):
f2fs: fix to round down start offset of fallocate for pin file
Sven Eckelmann (26):
batman-adv: tt: prevent TVLV entry number overflow
batman-adv: tp_meter: keep unacked list in ascending ordered
batman-adv: tp_meter: initialize dup_acks explicitly
batman-adv: tp_meter: initialize dec_cwnd explicitly
batman-adv: tp_meter: avoid window underflow
batman-adv: tp_meter: avoid divide-by-zero for dec_cwnd
batman-adv: tp_meter: fix fast recovery precondition
batman-adv: tp_meter: handle seqno wrap-around for fast recovery detection
batman-adv: tp_meter: add only finished tp_vars to lists
batman-adv: bla: annotate lasttime access with READ/WRITE_ONCE
batman-adv: prevent ELP transmission interval underflow
batman-adv: tp_meter: initialize last_recv_time during init
batman-adv: ensure bcast is writable before modifying TTL
batman-adv: fix (m|b)cast csum after decrementing TTL
batman-adv: frag: ensure fragment is writable before modifying TTL
batman-adv: frag: avoid underflow of TTL
batman-adv: v: prevent OGM aggregation on disabled hardif
batman-adv: tp_meter: restrict number of unacked list entries
batman-adv: tp_meter: annotate last_recv_time access with READ/WRITE_ONCE
batman-adv: tp_meter: prevent parallel modifications of last_recv
batman-adv: tp_meter: handle overlapping packets
batman-adv: tt: don't merge change entries with different VIDs
batman-adv: tt: track roam count per VID
batman-adv: dat: prevent false sharing between VLANs
batman-adv: tvlv: enforce 2-byte alignment
batman-adv: tvlv: avoid race of cifsnotfound handler state
Tao Cui (1):
mptcp: pm: fix extra_subflows underflow on userspace PM subflow creation
Thadeu Lima de Souza Cascardo (1):
dlm: prevent NPD when writing a positive value to event_done
Thorsten Blum (2):
hv: utils: handle and propagate errors in kvp_register
crypto: qat - Replace kzalloc() + copy_from_user() with memdup_user()
Tristan Madani (2):
Bluetooth: btmtk: validate WMT event SKB length before struct access
gfs2: fix use-after-free in gfs2_qd_dealloc
Tuo Li (1):
fbdev: modedb: fix a possible UAF in fb_find_mode()
Varun R Mallya (2):
bpf: Reject sleepable kprobe_multi programs at attach time
selftests/bpf: Add test to ensure kprobe_multi is not sleepable
Vasily Gorbik (1):
scripts/sorttable: Fix endianness handling in build-time mcount sort
Viken Dadhaniya (1):
serial: qcom_geni: Fix RX DMA stall when SE_DMA_RX_LEN_IN is zero
Waiman Long (1):
debugobjects: Dont call fill_pool() in early boot hardirq context
Weiming Shi (2):
i2c: stub: Reject I2C block transfers with invalid length
net: qualcomm: rmnet: fix endpoint use-after-free in rmnet_dellink()
Wenjie Qi (2):
f2fs: validate compress cache inode only when enabled
f2fs: keep atomic write retry from zeroing original data
Wentao Liang (3):
pNFS: Fix use-after-free in pnfs_update_layout()
fpga: region: fix use-after-free in child_regions_with_firmware()
power: reset: linkstation-poweroff: fix use-after-free in the linkstation_poweroff_init()
Wongi Lee (2):
ipv6: account for fraggap on the paged allocation path
ipv4: account for fraggap on the paged allocation path
Yi Yang (1):
vc_screen: fix null-ptr-deref in vcs_notifier() during concurrent vcs_write
Yiming Qian (1):
net: skmsg: preserve sg.copy across SG transforms
Yizhou Zhao (1):
9p: avoid putting oldfid in p9_client_walk() error path
Yongpeng Yang (1):
f2fs: fix incorrect FI_NO_EXTENT handling in __destroy_extent_node()
Yuho Choi (1):
rpmsg: char: Fix use-after-free on probe error path
Zenm Chen (1):
wifi: mt76: mt76x2u: Add support for ELECOM WDC-867SU3S
Zhang Cen (2):
f2fs: validate ACL entry sizes in f2fs_acl_from_disk()
ocfs2: reject oversized group bitmap descriptors
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: Linux 6.6.144
2026-07-04 11:59 Linux 6.6.144 Greg Kroah-Hartman
@ 2026-07-04 11:59 ` Greg Kroah-Hartman
0 siblings, 0 replies; 2+ messages in thread
From: Greg Kroah-Hartman @ 2026-07-04 11:59 UTC (permalink / raw)
To: linux-kernel, akpm, torvalds, stable; +Cc: lwn, jslaby, Greg Kroah-Hartman
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index 4ea5b837399a..264faaa9d7fa 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -66,17 +66,17 @@ This table lists ioctls visible from user land for Linux/x86. It contains
most drivers up to 2.6.31, but I know I am missing some. There has been
no attempt to list non-X86 architectures or ioctls from drivers/staging/.
-==== ===== ======================================================= ================================================================
-Code Seq# Include File Comments
+==== ===== ========================================================= ================================================================
+Code Seq# Include File Comments
(hex)
-==== ===== ======================================================= ================================================================
-0x00 00-1F linux/fs.h conflict!
-0x00 00-1F scsi/scsi_ioctl.h conflict!
-0x00 00-1F linux/fb.h conflict!
-0x00 00-1F linux/wavefront.h conflict!
+==== ===== ========================================================= ================================================================
+0x00 00-1F linux/fs.h conflict!
+0x00 00-1F scsi/scsi_ioctl.h conflict!
+0x00 00-1F linux/fb.h conflict!
+0x00 00-1F linux/wavefront.h conflict!
0x02 all linux/fd.h
0x03 all linux/hdreg.h
-0x04 D2-DC linux/umsdos_fs.h Dead since 2.6.11, but don't reuse these.
+0x04 D2-DC linux/umsdos_fs.h Dead since 2.6.11, but don't reuse these.
0x06 all linux/lp.h
0x09 all linux/raid/md_u.h
0x10 00-0F drivers/char/s390/vmcp.h
@@ -84,299 +84,298 @@ Code Seq# Include File Comments
0x10 20-2F arch/s390/include/uapi/asm/hypfs.h
0x12 all linux/fs.h
linux/blkpg.h
-0x1b all InfiniBand Subsystem
- <http://infiniband.sourceforge.net/>
+0x1b all InfiniBand Subsystem
+ <http://infiniband.sourceforge.net/>
0x20 all drivers/cdrom/cm206.h
0x22 all scsi/sg.h
-0x3E 00-0F linux/counter.h <mailto:linux-iio@vger.kernel.org>
+0x3E 00-0F linux/counter.h <mailto:linux-iio@vger.kernel.org>
'!' 00-1F uapi/linux/seccomp.h
-'#' 00-3F IEEE 1394 Subsystem
- Block for the entire subsystem
+'#' 00-3F IEEE 1394 Subsystem
+ Block for the entire subsystem
'$' 00-0F linux/perf_counter.h, linux/perf_event.h
-'%' 00-0F include/uapi/linux/stm.h System Trace Module subsystem
- <mailto:alexander.shishkin@linux.intel.com>
+'%' 00-0F include/uapi/linux/stm.h System Trace Module subsystem
+ <mailto:alexander.shishkin@linux.intel.com>
'&' 00-07 drivers/firewire/nosy-user.h
-'1' 00-1F linux/timepps.h PPS kit from Ulrich Windl
- <ftp://ftp.de.kernel.org/pub/linux/daemons/ntp/PPS/>
+'1' 00-1F linux/timepps.h PPS kit from Ulrich Windl
+ <ftp://ftp.de.kernel.org/pub/linux/daemons/ntp/PPS/>
'2' 01-04 linux/i2o.h
-'3' 00-0F drivers/s390/char/raw3270.h conflict!
-'3' 00-1F linux/suspend_ioctls.h, conflict!
+'3' 00-0F drivers/s390/char/raw3270.h conflict!
+'3' 00-1F linux/suspend_ioctls.h, conflict!
kernel/power/user.c
-'8' all SNP8023 advanced NIC card
- <mailto:mcr@solidum.com>
+'8' all SNP8023 advanced NIC card
+ <mailto:mcr@solidum.com>
';' 64-7F linux/vfio.h
';' 80-FF linux/iommufd.h
-'=' 00-3f uapi/linux/ptp_clock.h <mailto:richardcochran@gmail.com>
-'@' 00-0F linux/radeonfb.h conflict!
-'@' 00-0F drivers/video/aty/aty128fb.c conflict!
-'A' 00-1F linux/apm_bios.h conflict!
-'A' 00-0F linux/agpgart.h, conflict!
+'=' 00-3f uapi/linux/ptp_clock.h <mailto:richardcochran@gmail.com>
+'@' 00-0F linux/radeonfb.h conflict!
+'@' 00-0F drivers/video/aty/aty128fb.c conflict!
+'A' 00-1F linux/apm_bios.h conflict!
+'A' 00-0F linux/agpgart.h, conflict!
drivers/char/agp/compat_ioctl.h
-'A' 00-7F sound/asound.h conflict!
-'B' 00-1F linux/cciss_ioctl.h conflict!
-'B' 00-0F include/linux/pmu.h conflict!
-'B' C0-FF advanced bbus <mailto:maassen@uni-freiburg.de>
-'B' 00-0F xen/xenbus_dev.h conflict!
-'C' all linux/soundcard.h conflict!
-'C' 01-2F linux/capi.h conflict!
-'C' F0-FF drivers/net/wan/cosa.h conflict!
+'A' 00-7F sound/asound.h conflict!
+'B' 00-1F linux/cciss_ioctl.h conflict!
+'B' 00-0F include/linux/pmu.h conflict!
+'B' C0-FF advanced bbus <mailto:maassen@uni-freiburg.de>
+'B' 00-0F xen/xenbus_dev.h conflict!
+'C' all linux/soundcard.h conflict!
+'C' 01-2F linux/capi.h conflict!
+'C' F0-FF drivers/net/wan/cosa.h conflict!
'D' all arch/s390/include/asm/dasd.h
-'D' 40-5F drivers/scsi/dpt/dtpi_ioctl.h Dead since 2022
+'D' 40-5F drivers/scsi/dpt/dtpi_ioctl.h Dead since 2022
'D' 05 drivers/scsi/pmcraid.h
-'E' all linux/input.h conflict!
-'E' 00-0F xen/evtchn.h conflict!
-'F' all linux/fb.h conflict!
-'F' 01-02 drivers/scsi/pmcraid.h conflict!
-'F' 20 drivers/video/fsl-diu-fb.h conflict!
-'F' 20 drivers/video/intelfb/intelfb.h conflict!
-'F' 20 linux/ivtvfb.h conflict!
-'F' 20 linux/matroxfb.h conflict!
-'F' 20 drivers/video/aty/atyfb_base.c conflict!
-'F' 00-0F video/da8xx-fb.h conflict!
-'F' 80-8F linux/arcfb.h conflict!
-'F' DD video/sstfb.h conflict!
-'G' 00-3F drivers/misc/sgi-gru/grulib.h conflict!
-'G' 00-0F xen/gntalloc.h, xen/gntdev.h conflict!
-'H' 00-7F linux/hiddev.h conflict!
-'H' 00-0F linux/hidraw.h conflict!
-'H' 01 linux/mei.h conflict!
-'H' 02 linux/mei.h conflict!
-'H' 03 linux/mei.h conflict!
-'H' 00-0F sound/asound.h conflict!
-'H' 20-40 sound/asound_fm.h conflict!
-'H' 80-8F sound/sfnt_info.h conflict!
-'H' 10-8F sound/emu10k1.h conflict!
-'H' 10-1F sound/sb16_csp.h conflict!
-'H' 10-1F sound/hda_hwdep.h conflict!
-'H' 40-4F sound/hdspm.h conflict!
-'H' 40-4F sound/hdsp.h conflict!
+'E' all linux/input.h conflict!
+'E' 00-0F xen/evtchn.h conflict!
+'F' all linux/fb.h conflict!
+'F' 01-02 drivers/scsi/pmcraid.h conflict!
+'F' 20 drivers/video/fsl-diu-fb.h conflict!
+'F' 20 drivers/video/intelfb/intelfb.h conflict!
+'F' 20 linux/ivtvfb.h conflict!
+'F' 20 linux/matroxfb.h conflict!
+'F' 20 drivers/video/aty/atyfb_base.c conflict!
+'F' 00-0F video/da8xx-fb.h conflict!
+'F' 80-8F linux/arcfb.h conflict!
+'F' DD video/sstfb.h conflict!
+'G' 00-3F drivers/misc/sgi-gru/grulib.h conflict!
+'G' 00-0F xen/gntalloc.h, xen/gntdev.h conflict!
+'H' 00-7F linux/hiddev.h conflict!
+'H' 00-0F linux/hidraw.h conflict!
+'H' 01 linux/mei.h conflict!
+'H' 02 linux/mei.h conflict!
+'H' 03 linux/mei.h conflict!
+'H' 00-0F sound/asound.h conflict!
+'H' 20-40 sound/asound_fm.h conflict!
+'H' 80-8F sound/sfnt_info.h conflict!
+'H' 10-8F sound/emu10k1.h conflict!
+'H' 10-1F sound/sb16_csp.h conflict!
+'H' 10-1F sound/hda_hwdep.h conflict!
+'H' 40-4F sound/hdspm.h conflict!
+'H' 40-4F sound/hdsp.h conflict!
'H' 90 sound/usb/usx2y/usb_stream.h
-'H' 00-0F uapi/misc/habanalabs.h conflict!
+'H' 00-0F uapi/misc/habanalabs.h conflict!
'H' A0 uapi/linux/usb/cdc-wdm.h
-'H' C0-F0 net/bluetooth/hci.h conflict!
-'H' C0-DF net/bluetooth/hidp/hidp.h conflict!
-'H' C0-DF net/bluetooth/cmtp/cmtp.h conflict!
-'H' C0-DF net/bluetooth/bnep/bnep.h conflict!
-'H' F1 linux/hid-roccat.h <mailto:erazor_de@users.sourceforge.net>
+'H' C0-F0 net/bluetooth/hci.h conflict!
+'H' C0-DF net/bluetooth/hidp/hidp.h conflict!
+'H' C0-DF net/bluetooth/cmtp/cmtp.h conflict!
+'H' C0-DF net/bluetooth/bnep/bnep.h conflict!
+'H' F1 linux/hid-roccat.h <mailto:erazor_de@users.sourceforge.net>
'H' F8-FA sound/firewire.h
-'I' all linux/isdn.h conflict!
-'I' 00-0F drivers/isdn/divert/isdn_divert.h conflict!
-'I' 40-4F linux/mISDNif.h conflict!
+'I' all linux/isdn.h conflict!
+'I' 00-0F drivers/isdn/divert/isdn_divert.h conflict!
+'I' 40-4F linux/mISDNif.h conflict!
'K' all linux/kd.h
-'L' 00-1F linux/loop.h conflict!
-'L' 10-1F drivers/scsi/mpt3sas/mpt3sas_ctl.h conflict!
-'L' E0-FF linux/ppdd.h encrypted disk device driver
- <http://linux01.gwdg.de/~alatham/ppdd.html>
-'M' all linux/soundcard.h conflict!
-'M' 01-16 mtd/mtd-abi.h conflict!
+'L' 00-1F linux/loop.h conflict!
+'L' 10-1F drivers/scsi/mpt3sas/mpt3sas_ctl.h conflict!
+'L' E0-FF linux/ppdd.h encrypted disk device driver
+ <http://linux01.gwdg.de/~alatham/ppdd.html>
+'M' all linux/soundcard.h conflict!
+'M' 01-16 mtd/mtd-abi.h conflict!
and drivers/mtd/mtdchar.c
'M' 01-03 drivers/scsi/megaraid/megaraid_sas.h
-'M' 00-0F drivers/video/fsl-diu-fb.h conflict!
+'M' 00-0F drivers/video/fsl-diu-fb.h conflict!
'N' 00-1F drivers/usb/scanner.h
'N' 40-7F drivers/block/nvme.c
-'O' 00-06 mtd/ubi-user.h UBI
-'P' all linux/soundcard.h conflict!
-'P' 60-6F sound/sscape_ioctl.h conflict!
-'P' 00-0F drivers/usb/class/usblp.c conflict!
-'P' 01-09 drivers/misc/pci_endpoint_test.c conflict!
-'P' 00-0F xen/privcmd.h conflict!
-'P' 00-05 linux/tps6594_pfsm.h conflict!
+'O' 00-06 mtd/ubi-user.h UBI
+'P' all linux/soundcard.h conflict!
+'P' 60-6F sound/sscape_ioctl.h conflict!
+'P' 00-0F drivers/usb/class/usblp.c conflict!
+'P' 01-09 drivers/misc/pci_endpoint_test.c conflict!
+'P' 00-0F xen/privcmd.h conflict!
+'P' 00-05 linux/tps6594_pfsm.h conflict!
'Q' all linux/soundcard.h
-'R' 00-1F linux/random.h conflict!
-'R' 01 linux/rfkill.h conflict!
+'R' 00-1F linux/random.h conflict!
+'R' 01 linux/rfkill.h conflict!
'R' C0-DF net/bluetooth/rfcomm.h
'R' E0 uapi/linux/fsl_mc.h
-'S' all linux/cdrom.h conflict!
-'S' 80-81 scsi/scsi_ioctl.h conflict!
-'S' 82-FF scsi/scsi.h conflict!
-'S' 00-7F sound/asequencer.h conflict!
-'T' all linux/soundcard.h conflict!
-'T' 00-AF sound/asound.h conflict!
-'T' all arch/x86/include/asm/ioctls.h conflict!
-'T' C0-DF linux/if_tun.h conflict!
-'U' all sound/asound.h conflict!
-'U' 00-CF linux/uinput.h conflict!
+'S' all linux/cdrom.h conflict!
+'S' 80-81 scsi/scsi_ioctl.h conflict!
+'S' 82-FF scsi/scsi.h conflict!
+'S' 00-7F sound/asequencer.h conflict!
+'T' all linux/soundcard.h conflict!
+'T' 00-AF sound/asound.h conflict!
+'T' all arch/x86/include/asm/ioctls.h conflict!
+'T' C0-DF linux/if_tun.h conflict!
+'U' all sound/asound.h conflict!
+'U' 00-CF linux/uinput.h conflict!
'U' 00-EF linux/usbdevice_fs.h
'U' C0-CF drivers/bluetooth/hci_uart.h
-'V' all linux/vt.h conflict!
-'V' all linux/videodev2.h conflict!
-'V' C0 linux/ivtvfb.h conflict!
-'V' C0 linux/ivtv.h conflict!
-'V' C0 media/si4713.h conflict!
-'W' 00-1F linux/watchdog.h conflict!
-'W' 00-1F linux/wanrouter.h conflict! (pre 3.9)
-'W' 00-3F sound/asound.h conflict!
+'V' all linux/vt.h conflict!
+'V' all linux/videodev2.h conflict!
+'V' C0 linux/ivtvfb.h conflict!
+'V' C0 linux/ivtv.h conflict!
+'V' C0 media/si4713.h conflict!
+'W' 00-1F linux/watchdog.h conflict!
+'W' 00-1F linux/wanrouter.h conflict! (pre 3.9)
+'W' 00-3F sound/asound.h conflict!
'W' 40-5F drivers/pci/switch/switchtec.c
'W' 60-61 linux/watch_queue.h
-'X' all fs/xfs/xfs_fs.h, conflict!
+'X' all fs/xfs/xfs_fs.h, conflict!
fs/xfs/linux-2.6/xfs_ioctl32.h,
include/linux/falloc.h,
linux/fs.h,
-'X' all fs/ocfs2/ocfs_fs.h conflict!
-'X' 01 linux/pktcdvd.h conflict!
+'X' all fs/ocfs2/ocfs_fs.h conflict!
+'X' 01 linux/pktcdvd.h conflict!
'Z' 14-15 drivers/message/fusion/mptctl.h
-'[' 00-3F linux/usb/tmc.h USB Test and Measurement Devices
- <mailto:gregkh@linuxfoundation.org>
-'a' all linux/atm*.h, linux/sonet.h ATM on linux
- <http://lrcwww.epfl.ch/>
-'a' 00-0F drivers/crypto/qat/qat_common/adf_cfg_common.h conflict! qat driver
-'b' 00-FF conflict! bit3 vme host bridge
- <mailto:natalia@nikhefk.nikhef.nl>
-'b' 00-0F linux/dma-buf.h conflict!
-'c' 00-7F linux/comstats.h conflict!
-'c' 00-7F linux/coda.h conflict!
-'c' 00-1F linux/chio.h conflict!
-'c' 80-9F arch/s390/include/asm/chsc.h conflict!
+'[' 00-3F linux/usb/tmc.h USB Test and Measurement Devices
+ <mailto:gregkh@linuxfoundation.org>
+'a' all linux/atm*.h, linux/sonet.h ATM on linux
+ <http://lrcwww.epfl.ch/>
+'b' 00-FF conflict! bit3 vme host bridge
+ <mailto:natalia@nikhefk.nikhef.nl>
+'b' 00-0F linux/dma-buf.h conflict!
+'c' 00-7F linux/comstats.h conflict!
+'c' 00-7F linux/coda.h conflict!
+'c' 00-1F linux/chio.h conflict!
+'c' 80-9F arch/s390/include/asm/chsc.h conflict!
'c' A0-AF arch/x86/include/asm/msr.h conflict!
-'d' 00-FF linux/char/drm/drm.h conflict!
-'d' 02-40 pcmcia/ds.h conflict!
+'d' 00-FF linux/char/drm/drm.h conflict!
+'d' 02-40 pcmcia/ds.h conflict!
'd' F0-FF linux/digi1.h
-'e' all linux/digi1.h conflict!
-'f' 00-1F linux/ext2_fs.h conflict!
-'f' 00-1F linux/ext3_fs.h conflict!
-'f' 00-0F fs/jfs/jfs_dinode.h conflict!
-'f' 00-0F fs/ext4/ext4.h conflict!
-'f' 00-0F linux/fs.h conflict!
-'f' 00-0F fs/ocfs2/ocfs2_fs.h conflict!
+'e' all linux/digi1.h conflict!
+'f' 00-1F linux/ext2_fs.h conflict!
+'f' 00-1F linux/ext3_fs.h conflict!
+'f' 00-0F fs/jfs/jfs_dinode.h conflict!
+'f' 00-0F fs/ext4/ext4.h conflict!
+'f' 00-0F linux/fs.h conflict!
+'f' 00-0F fs/ocfs2/ocfs2_fs.h conflict!
'f' 13-27 linux/fscrypt.h
'f' 81-8F linux/fsverity.h
'g' 00-0F linux/usb/gadgetfs.h
'g' 20-2F linux/usb/g_printer.h
-'h' 00-7F conflict! Charon filesystem
- <mailto:zapman@interlan.net>
-'h' 00-1F linux/hpet.h conflict!
+'h' 00-7F conflict! Charon filesystem
+ <mailto:zapman@interlan.net>
+'h' 00-1F linux/hpet.h conflict!
'h' 80-8F fs/hfsplus/ioctl.c
-'i' 00-3F linux/i2o-dev.h conflict!
-'i' 0B-1F linux/ipmi.h conflict!
+'i' 00-3F linux/i2o-dev.h conflict!
+'i' 0B-1F linux/ipmi.h conflict!
'i' 80-8F linux/i8k.h
-'i' 90-9F `linux/iio/*.h` IIO
+'i' 90-9F `linux/iio/*.h` IIO
'j' 00-3F linux/joystick.h
-'k' 00-0F linux/spi/spidev.h conflict!
-'k' 00-05 video/kyro.h conflict!
-'k' 10-17 linux/hsi/hsi_char.h HSI character device
-'l' 00-3F linux/tcfs_fs.h transparent cryptographic file system
- <http://web.archive.org/web/%2A/http://mikonos.dia.unisa.it/tcfs>
-'l' 40-7F linux/udf_fs_i.h in development:
- <https://github.com/pali/udftools>
-'m' 00-09 linux/mmtimer.h conflict!
-'m' all linux/mtio.h conflict!
-'m' all linux/soundcard.h conflict!
-'m' all linux/synclink.h conflict!
-'m' 00-19 drivers/message/fusion/mptctl.h conflict!
-'m' 00 drivers/scsi/megaraid/megaraid_ioctl.h conflict!
+'k' 00-0F linux/spi/spidev.h conflict!
+'k' 00-05 video/kyro.h conflict!
+'k' 10-17 linux/hsi/hsi_char.h HSI character device
+'l' 00-3F linux/tcfs_fs.h transparent cryptographic file system
+ <http://web.archive.org/web/%2A/http://mikonos.dia.unisa.it/tcfs>
+'l' 40-7F linux/udf_fs_i.h in development:
+ <https://github.com/pali/udftools>
+'m' 00-09 linux/mmtimer.h conflict!
+'m' all linux/mtio.h conflict!
+'m' all linux/soundcard.h conflict!
+'m' all linux/synclink.h conflict!
+'m' 00-19 drivers/message/fusion/mptctl.h conflict!
+'m' 00 drivers/scsi/megaraid/megaraid_ioctl.h conflict!
'n' 00-7F linux/ncp_fs.h and fs/ncpfs/ioctl.c
-'n' 80-8F uapi/linux/nilfs2_api.h NILFS2
-'n' E0-FF linux/matroxfb.h matroxfb
-'o' 00-1F fs/ocfs2/ocfs2_fs.h OCFS2
-'o' 00-03 mtd/ubi-user.h conflict! (OCFS2 and UBI overlaps)
-'o' 40-41 mtd/ubi-user.h UBI
-'o' 01-A1 `linux/dvb/*.h` DVB
-'p' 00-0F linux/phantom.h conflict! (OpenHaptics needs this)
-'p' 00-1F linux/rtc.h conflict!
+'n' 80-8F uapi/linux/nilfs2_api.h NILFS2
+'n' E0-FF linux/matroxfb.h matroxfb
+'o' 00-1F fs/ocfs2/ocfs2_fs.h OCFS2
+'o' 00-03 mtd/ubi-user.h conflict! (OCFS2 and UBI overlaps)
+'o' 40-41 mtd/ubi-user.h UBI
+'o' 01-A1 `linux/dvb/*.h` DVB
+'p' 00-0F linux/phantom.h conflict! (OpenHaptics needs this)
+'p' 00-1F linux/rtc.h conflict!
'p' 40-7F linux/nvram.h
-'p' 80-9F linux/ppdev.h user-space parport
- <mailto:tim@cyberelk.net>
-'p' A1-A5 linux/pps.h LinuxPPS
- <mailto:giometti@linux.it>
+'p' 80-9F linux/ppdev.h user-space parport
+ <mailto:tim@cyberelk.net>
+'p' A1-A5 linux/pps.h LinuxPPS
+ <mailto:giometti@linux.it>
'q' 00-1F linux/serio.h
-'q' 80-FF linux/telephony.h Internet PhoneJACK, Internet LineJACK
- linux/ixjuser.h <http://web.archive.org/web/%2A/http://www.quicknet.net>
+'q' 80-FF linux/telephony.h Internet PhoneJACK, Internet LineJACK
+ linux/ixjuser.h <http://web.archive.org/web/%2A/http://www.quicknet.net>
'r' 00-1F linux/msdos_fs.h and fs/fat/dir.c
's' all linux/cdk.h
't' 00-7F linux/ppp-ioctl.h
't' 80-8F linux/isdn_ppp.h
-'t' 90-91 linux/toshiba.h toshiba and toshiba_acpi SMM
-'u' 00-1F linux/smb_fs.h gone
-'u' 20-3F linux/uvcvideo.h USB video class host driver
-'u' 40-4f linux/udmabuf.h userspace dma-buf misc device
-'v' 00-1F linux/ext2_fs.h conflict!
-'v' 00-1F linux/fs.h conflict!
-'v' 00-0F linux/sonypi.h conflict!
-'v' 00-0F media/v4l2-subdev.h conflict!
-'v' 20-27 arch/powerpc/include/uapi/asm/vas-api.h VAS API
-'v' C0-FF linux/meye.h conflict!
-'w' all CERN SCI driver
-'y' 00-1F packet based user level communications
- <mailto:zapman@interlan.net>
-'z' 00-3F CAN bus card conflict!
- <mailto:hdstich@connectu.ulm.circular.de>
-'z' 40-7F CAN bus card conflict!
- <mailto:oe@port.de>
-'z' 10-4F drivers/s390/crypto/zcrypt_api.h conflict!
+'t' 90-91 linux/toshiba.h toshiba and toshiba_acpi SMM
+'u' 00-1F linux/smb_fs.h gone
+'u' 20-3F linux/uvcvideo.h USB video class host driver
+'u' 40-4f linux/udmabuf.h userspace dma-buf misc device
+'v' 00-1F linux/ext2_fs.h conflict!
+'v' 00-1F linux/fs.h conflict!
+'v' 00-0F linux/sonypi.h conflict!
+'v' 00-0F media/v4l2-subdev.h conflict!
+'v' 20-27 arch/powerpc/include/uapi/asm/vas-api.h VAS API
+'v' C0-FF linux/meye.h conflict!
+'w' all CERN SCI driver
+'y' 00-1F packet based user level communications
+ <mailto:zapman@interlan.net>
+'z' 00-3F CAN bus card conflict!
+ <mailto:hdstich@connectu.ulm.circular.de>
+'z' 40-7F CAN bus card conflict!
+ <mailto:oe@port.de>
+'z' 10-4F drivers/s390/crypto/zcrypt_api.h conflict!
'|' 00-7F linux/media.h
0x80 00-1F linux/fb.h
0x81 00-1F linux/vduse.h
0x89 00-06 arch/x86/include/asm/sockios.h
0x89 0B-DF linux/sockios.h
-0x89 E0-EF linux/sockios.h SIOCPROTOPRIVATE range
-0x89 F0-FF linux/sockios.h SIOCDEVPRIVATE range
+0x89 E0-EF linux/sockios.h SIOCPROTOPRIVATE range
+0x89 F0-FF linux/sockios.h SIOCDEVPRIVATE range
0x8B all linux/wireless.h
-0x8C 00-3F WiNRADiO driver
- <http://www.winradio.com.au/>
+0x8C 00-3F WiNRADiO driver
+ <http://www.winradio.com.au/>
0x90 00 drivers/cdrom/sbpcd.h
0x92 00-0F drivers/usb/mon/mon_bin.c
0x93 60-7F linux/auto_fs.h
-0x94 all fs/btrfs/ioctl.h Btrfs filesystem
- and linux/fs.h some lifted to vfs/generic
-0x97 00-7F fs/ceph/ioctl.h Ceph file system
-0x99 00-0F 537-Addinboard driver
- <mailto:buk@buks.ipn.de>
-0xA0 all linux/sdp/sdp.h Industrial Device Project
- <mailto:kenji@bitgate.com>
-0xA1 0 linux/vtpm_proxy.h TPM Emulator Proxy Driver
-0xA2 all uapi/linux/acrn.h ACRN hypervisor
-0xA3 80-8F Port ACL in development:
- <mailto:tlewis@mindspring.com>
+0x94 all fs/btrfs/ioctl.h Btrfs filesystem
+ and linux/fs.h some lifted to vfs/generic
+0x97 00-7F fs/ceph/ioctl.h Ceph file system
+0x99 00-0F 537-Addinboard driver
+ <mailto:buk@buks.ipn.de>
+0xA0 all linux/sdp/sdp.h Industrial Device Project
+ <mailto:kenji@bitgate.com>
+0xA1 0 linux/vtpm_proxy.h TPM Emulator Proxy Driver
+0xA2 all uapi/linux/acrn.h ACRN hypervisor
+0xA3 80-8F Port ACL in development:
+ <mailto:tlewis@mindspring.com>
0xA3 90-9F linux/dtlk.h
-0xA4 00-1F uapi/linux/tee.h Generic TEE subsystem
-0xA4 00-1F uapi/asm/sgx.h <mailto:linux-sgx@vger.kernel.org>
-0xA5 01-05 linux/surface_aggregator/cdev.h Microsoft Surface Platform System Aggregator
- <mailto:luzmaximilian@gmail.com>
-0xA5 20-2F linux/surface_aggregator/dtx.h Microsoft Surface DTX driver
- <mailto:luzmaximilian@gmail.com>
+0xA4 00-1F uapi/linux/tee.h Generic TEE subsystem
+0xA4 00-1F uapi/asm/sgx.h <mailto:linux-sgx@vger.kernel.org>
+0xA5 01-05 linux/surface_aggregator/cdev.h Microsoft Surface Platform System Aggregator
+ <mailto:luzmaximilian@gmail.com>
+0xA5 20-2F linux/surface_aggregator/dtx.h Microsoft Surface DTX driver
+ <mailto:luzmaximilian@gmail.com>
0xAA 00-3F linux/uapi/linux/userfaultfd.h
0xAB 00-1F linux/nbd.h
0xAC 00-1F linux/raw.h
-0xAD 00 Netfilter device in development:
- <mailto:rusty@rustcorp.com.au>
-0xAE 00-1F linux/kvm.h Kernel-based Virtual Machine
- <mailto:kvm@vger.kernel.org>
-0xAE 40-FF linux/kvm.h Kernel-based Virtual Machine
- <mailto:kvm@vger.kernel.org>
-0xAE 20-3F linux/nitro_enclaves.h Nitro Enclaves
-0xAF 00-1F linux/fsl_hypervisor.h Freescale hypervisor
-0xB0 all RATIO devices in development:
- <mailto:vgo@ratio.de>
-0xB1 00-1F PPPoX
- <mailto:mostrows@styx.uwaterloo.ca>
+0xAD 00 Netfilter device in development:
+ <mailto:rusty@rustcorp.com.au>
+0xAE 00-1F linux/kvm.h Kernel-based Virtual Machine
+ <mailto:kvm@vger.kernel.org>
+0xAE 40-FF linux/kvm.h Kernel-based Virtual Machine
+ <mailto:kvm@vger.kernel.org>
+0xAE 20-3F linux/nitro_enclaves.h Nitro Enclaves
+0xAF 00-1F linux/fsl_hypervisor.h Freescale hypervisor
+0xB0 all RATIO devices in development:
+ <mailto:vgo@ratio.de>
+0xB1 00-1F PPPoX
+ <mailto:mostrows@styx.uwaterloo.ca>
0xB3 00 linux/mmc/ioctl.h
-0xB4 00-0F linux/gpio.h <mailto:linux-gpio@vger.kernel.org>
-0xB5 00-0F uapi/linux/rpmsg.h <mailto:linux-remoteproc@vger.kernel.org>
+0xB4 00-0F linux/gpio.h <mailto:linux-gpio@vger.kernel.org>
+0xB5 00-0F uapi/linux/rpmsg.h <mailto:linux-remoteproc@vger.kernel.org>
0xB6 all linux/fpga-dfl.h
-0xB7 all uapi/linux/remoteproc_cdev.h <mailto:linux-remoteproc@vger.kernel.org>
-0xB7 all uapi/linux/nsfs.h <mailto:Andrei Vagin <avagin@openvz.org>>
+0xB7 all uapi/linux/remoteproc_cdev.h <mailto:linux-remoteproc@vger.kernel.org>
+0xB7 all uapi/linux/nsfs.h <mailto:Andrei Vagin <avagin@openvz.org>>
0xC0 00-0F linux/usb/iowarrior.h
0xCA 00-0F uapi/misc/cxl.h
0xCA 10-2F uapi/misc/ocxl.h
0xCA 80-BF uapi/scsi/cxlflash_ioctl.h
-0xCB 00-1F CBM serial IEC bus in development:
- <mailto:michael.klein@puffin.lb.shuttle.de>
-0xCC 00-0F drivers/misc/ibmvmc.h pseries VMC driver
+0xCB 00-1F CBM serial IEC bus in development:
+ <mailto:michael.klein@puffin.lb.shuttle.de>
+0xCC 00-0F drivers/misc/ibmvmc.h pseries VMC driver
0xCD 01 linux/reiserfs_fs.h
-0xCE 01-02 uapi/linux/cxl_mem.h Compute Express Link Memory Devices
+0xCE 01-02 uapi/linux/cxl_mem.h Compute Express Link Memory Devices
0xCF 02 fs/smb/client/cifs_ioctl.h
0xDB 00-0F drivers/char/mwave/mwavepub.h
-0xDD 00-3F ZFCP device driver see drivers/s390/scsi/
- <mailto:aherrman@de.ibm.com>
+0xDD 00-3F ZFCP device driver see drivers/s390/scsi/
+ <mailto:aherrman@de.ibm.com>
0xE5 00-3F linux/fuse.h
-0xEC 00-01 drivers/platform/chrome/cros_ec_dev.h ChromeOS EC driver
-0xEE 00-09 uapi/linux/pfrut.h Platform Firmware Runtime Update and Telemetry
-0xF3 00-3F drivers/usb/misc/sisusbvga/sisusb.h sisfb (in development)
- <mailto:thomas@winischhofer.net>
-0xF6 all LTTng Linux Trace Toolkit Next Generation
- <mailto:mathieu.desnoyers@efficios.com>
-0xF8 all arch/x86/include/uapi/asm/amd_hsmp.h AMD HSMP EPYC system management interface driver
- <mailto:nchatrad@amd.com>
+0xEC 00-01 drivers/platform/chrome/cros_ec_dev.h ChromeOS EC driver
+0xEE 00-09 uapi/linux/pfrut.h Platform Firmware Runtime Update and Telemetry
+0xF3 00-3F drivers/usb/misc/sisusbvga/sisusb.h sisfb (in development)
+ <mailto:thomas@winischhofer.net>
+0xF6 all LTTng Linux Trace Toolkit Next Generation
+ <mailto:mathieu.desnoyers@efficios.com>
+0xF8 all arch/x86/include/uapi/asm/amd_hsmp.h AMD HSMP EPYC system management interface driver
+ <mailto:nchatrad@amd.com>
0xFD all linux/dm-ioctl.h
0xFE all linux/isst_if.h
-==== ===== ======================================================= ================================================================
+==== ===== ========================================================= ================================================================
diff --git a/Makefile b/Makefile
index a703a640d0c4..db02323ee4ca 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 6
PATCHLEVEL = 6
-SUBLEVEL = 143
+SUBLEVEL = 144
EXTRAVERSION =
NAME = Pinguïn Aangedreven
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index f8dd0b3cc8e0..ee264737be6d 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -22,6 +22,7 @@
#include <asm/cp15.h>
#include <asm/system_info.h>
+#include <asm/system_misc.h>
#include <asm/unaligned.h>
#include <asm/opcodes.h>
@@ -809,6 +810,9 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
int thumb2_32b = 0;
int fault;
+ if (addr >= TASK_SIZE && user_mode(regs))
+ harden_branch_predictor();
+
if (interrupts_enabled(regs))
local_irq_enable();
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index ed1a25f457e4..87ed5da30e44 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -128,6 +128,19 @@ static inline bool is_translation_fault(unsigned int fsr)
return false;
}
+static inline bool is_permission_fault(unsigned int fsr)
+{
+ int fs = fsr_fs(fsr);
+#ifdef CONFIG_ARM_LPAE
+ if ((fs & FS_MMU_NOLL_MASK) == FS_PERM_NOLL)
+ return true;
+#else
+ if (fs == FS_L1_PERM || fs == FS_L2_PERM)
+ return true;
+#endif
+ return false;
+}
+
static void die_kernel_fault(const char *msg, struct mm_struct *mm,
unsigned long addr, unsigned int fsr,
struct pt_regs *regs)
@@ -163,6 +176,8 @@ __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
*/
if (addr < PAGE_SIZE) {
msg = "NULL pointer dereference";
+ } else if (is_permission_fault(fsr) && fsr & FSR_LNX_PF) {
+ msg = "execution of memory";
} else {
if (is_translation_fault(fsr) &&
kfence_handle_page_fault(addr, is_write_fault(fsr), regs))
@@ -184,9 +199,6 @@ __do_user_fault(unsigned long addr, unsigned int fsr, unsigned int sig,
{
struct task_struct *tsk = current;
- if (addr > TASK_SIZE)
- harden_branch_predictor();
-
#ifdef CONFIG_DEBUG_USER
if (((user_debug & UDBG_SEGV) && (sig == SIGSEGV)) ||
((user_debug & UDBG_BUS) && (sig == SIGBUS))) {
@@ -229,17 +241,35 @@ void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000)
#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000)
-static inline bool is_permission_fault(unsigned int fsr)
+static int __kprobes
+do_kernel_address_page_fault(struct mm_struct *mm, unsigned long addr,
+ unsigned int fsr, struct pt_regs *regs)
{
- int fs = fsr_fs(fsr);
-#ifdef CONFIG_ARM_LPAE
- if ((fs & FS_MMU_NOLL_MASK) == FS_PERM_NOLL)
- return true;
-#else
- if (fs == FS_L1_PERM || fs == FS_L2_PERM)
- return true;
-#endif
- return false;
+ if (user_mode(regs)) {
+ /*
+ * Fault from user mode for a kernel space address. User mode
+ * should not be faulting in kernel space, which includes the
+ * vector/khelper page. Handle the branch predictor hardening
+ * while interrupts are still disabled, then send a SIGSEGV.
+ */
+ harden_branch_predictor();
+ __do_user_fault(addr, fsr, SIGSEGV, SEGV_MAPERR, regs);
+ } else {
+ /*
+ * Fault from kernel mode. Enable interrupts if they were
+ * enabled in the parent context. Section (upper page table)
+ * translation faults are handled via do_translation_fault(),
+ * so we will only get here for a non-present kernel space
+ * PTE or PTE permission fault. This may happen in exceptional
+ * circumstances and need the fixup tables to be walked.
+ */
+ if (interrupts_enabled(regs))
+ local_irq_enable();
+
+ __do_kernel_fault(mm, addr, fsr, regs);
+ }
+
+ return 0;
}
static int __kprobes
@@ -255,6 +285,12 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
if (kprobe_page_fault(regs, fsr))
return 0;
+ /*
+ * Handle kernel addresses faults separately, which avoids touching
+ * the mmap lock from contexts that are not able to sleep.
+ */
+ if (addr >= TASK_SIZE)
+ return do_kernel_address_page_fault(mm, addr, fsr, regs);
/* Enable interrupts if they were enabled in the parent context. */
if (interrupts_enabled(regs))
@@ -386,16 +422,20 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
* We enter here because the first level page table doesn't contain
* a valid entry for the address.
*
- * If the address is in kernel space (>= TASK_SIZE), then we are
- * probably faulting in the vmalloc() area.
+ * If this is a user address (addr < TASK_SIZE), we handle this as a
+ * normal page fault. This leaves the remainder of the function to handle
+ * kernel address translation faults.
+ *
+ * Since user mode is not permitted to access kernel addresses, pass these
+ * directly to do_kernel_address_page_fault() to handle.
*
- * If the init_task's first level page tables contains the relevant
- * entry, we copy the it to this task. If not, we send the process
- * a signal, fixup the exception, or oops the kernel.
+ * Otherwise, we're probably faulting in the vmalloc() area, so try to fix
+ * that up. Note that we must not take any locks or enable interrupts in
+ * this case.
*
- * NOTE! We MUST NOT take any locks for this case. We may be in an
- * interrupt or a critical region, and should only copy the information
- * from the master page table, nothing more.
+ * If vmalloc() fixup fails, that means the non-leaf page tables did not
+ * contain an entry for this address, so handle this via
+ * do_kernel_address_page_fault().
*/
#ifdef CONFIG_MMU
static int __kprobes
@@ -461,7 +501,8 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
return 0;
bad_area:
- do_bad_area(addr, fsr, regs);
+ do_kernel_address_page_fault(current->mm, addr, fsr, regs);
+
return 0;
}
#else /* CONFIG_MMU */
@@ -481,7 +522,16 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
static int
do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
+ /*
+ * If this is a kernel address, but from user mode, then userspace
+ * is trying bad stuff. Invoke the branch predictor handling.
+ * Interrupts are disabled here.
+ */
+ if (addr >= TASK_SIZE && user_mode(regs))
+ harden_branch_predictor();
+
do_bad_area(addr, fsr, regs);
+
return 0;
}
#endif /* CONFIG_ARM_LPAE */
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 9e04e4b33665..723e73042c1a 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -202,6 +202,7 @@ config ARM64
if DYNAMIC_FTRACE_WITH_ARGS
select HAVE_SAMPLE_FTRACE_DIRECT
select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
+ select HAVE_BUILDTIME_MCOUNT_SORT
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select HAVE_FAST_GUP
select HAVE_FTRACE_MCOUNT_RECORD
diff --git a/arch/mips/dec/prom/console.c b/arch/mips/dec/prom/console.c
index 31a8441d8431..b4f0dba3fa20 100644
--- a/arch/mips/dec/prom/console.c
+++ b/arch/mips/dec/prom/console.c
@@ -2,8 +2,9 @@
/*
* DECstation PROM-based early console support.
*
- * Copyright (C) 2004, 2007 Maciej W. Rozycki
+ * Copyright (C) 2004, 2007, 2026 Maciej W. Rozycki
*/
+#include <linux/bug.h>
#include <linux/console.h>
#include <linux/init.h>
#include <linux/kernel.h>
@@ -14,9 +15,11 @@
static void __init prom_console_write(struct console *con, const char *s,
unsigned int c)
{
- char buf[81];
+ static char buf[81] __initdata = { 0 };
unsigned int chunk = sizeof(buf) - 1;
+ BUG_ON((long)buf != (int)(long)buf);
+
while (c > 0) {
if (chunk > c)
chunk = c;
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 96c03f95212e..667245e34fc5 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1787,6 +1787,11 @@ static bool hv_is_vp_in_sparse_set(u32 vp_id, u64 valid_bank_mask, u64 sparse_ba
int valid_bit_nr = vp_id / HV_VCPUS_PER_SPARSE_BANK;
unsigned long sbank;
+ BUILD_BUG_ON(BITS_PER_TYPE(valid_bank_mask) != HV_MAX_SPARSE_VCPU_BANKS);
+
+ if (valid_bit_nr >= HV_MAX_SPARSE_VCPU_BANKS)
+ return false;
+
if (!test_bit(valid_bit_nr, (unsigned long *)&valid_bank_mask))
return false;
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 774bc26b8235..2453524ea4a1 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2337,13 +2337,15 @@ static struct kvm_mmu_page *kvm_mmu_get_child_sp(struct kvm_vcpu *vcpu,
u64 *sptep, gfn_t gfn,
bool direct, unsigned int access)
{
- union kvm_mmu_page_role role;
+ union kvm_mmu_page_role role = kvm_mmu_child_role(sptep, direct, access);
- if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep) &&
- spte_to_child_sp(*sptep) && spte_to_child_sp(*sptep)->gfn == gfn)
+ if (is_shadow_present_pte(*sptep) &&
+ !is_large_pte(*sptep) &&
+ spte_to_child_sp(*sptep) &&
+ spte_to_child_sp(*sptep)->gfn == gfn &&
+ spte_to_child_sp(*sptep)->role.word == role.word)
return ERR_PTR(-EEXIST);
- role = kvm_mmu_child_role(sptep, direct, access);
return kvm_mmu_get_shadow_page(vcpu, gfn, role);
}
@@ -6580,13 +6582,19 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
sp = sptep_to_sp(sptep);
/*
- * We cannot do huge page mapping for indirect shadow pages,
- * which are found on the last rmap (level = 1) when not using
- * tdp; such shadow pages are synced with the page table in
- * the guest, and the guest page table is using 4K page size
- * mapping if the indirect sp has level = 1.
+ * Direct shadow page can be replaced by a hugepage if the host
+ * mapping level allows it and the memslot maps all of the host
+ * hugepage. Note! If the memslot maps only part of the
+ * hugepage, sp->gfn may be below slot->base_gfn, and querying
+ * the max mapping level would cause an out-of-bounds lpage_info
+ * access. So the gfn bounds check *must* be done first.
+ *
+ * Indirect shadow pages are created when the guest page tables
+ * are using 4K pages. Since the host mapping is always
+ * constrained by the page size in the guest, indirect shadow
+ * pages are never collapsible.
*/
- if (sp->role.direct &&
+ if (sp->role.direct && is_gfn_in_memslot(slot, sp->gfn) &&
sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
PG_LEVEL_NUM)) {
kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index f676e4f4797a..afa3d9d8823a 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1004,6 +1004,7 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
s_off = vaddr & ~PAGE_MASK;
d_off = dst_vaddr & ~PAGE_MASK;
len = min_t(size_t, (PAGE_SIZE - s_off), size);
+ len = min_t(size_t, len, PAGE_SIZE - d_off);
if (dec)
ret = __sev_dbg_decrypt_user(kvm,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4a45e86c5e2f..85d301a03b20 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6851,10 +6851,6 @@ static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
* VM-Exit, otherwise L1 with run with a stale SVI.
*/
if (is_guest_mode(vcpu)) {
- /*
- * KVM is supposed to forward intercepted L2 EOIs to L1 if VID
- * is enabled in vmcs12; as above, the EOIs affect L2's vAPIC.
- */
to_vmx(vcpu)->nested.update_vmcs01_hwapic_isr = true;
return;
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3838b7336590..c04277b35e2e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10426,9 +10426,16 @@ void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
* pending. At the same time, KVM_REQ_EVENT may not be set as APICv was
* still active when the interrupt got accepted. Make sure
* kvm_check_and_inject_events() is called to check for that.
+ *
+ * Update SVI when APICv gets enabled, otherwise SVI won't reflect the
+ * highest bit in vISR and the next accelerated EOI in the guest won't
+ * be virtualized correctly (the CPU uses SVI to determine which vISR
+ * vector to clear).
*/
if (!apic->apicv_active)
kvm_make_request(KVM_REQ_EVENT, vcpu);
+ else
+ kvm_apic_update_hwapic_isr(vcpu);
out:
preempt_enable();
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4ac2f53e7f51..b8d8b6b58a6c 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -170,20 +170,10 @@ static void blkg_free(struct blkcg_gq *blkg)
static void __blkg_release(struct rcu_head *rcu)
{
struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head);
- struct blkcg *blkcg = blkg->blkcg;
- int cpu;
#ifdef CONFIG_BLK_CGROUP_PUNT_BIO
WARN_ON(!bio_list_empty(&blkg->async_bios));
#endif
- /*
- * Flush all the non-empty percpu lockless lists before releasing
- * us, given these stat belongs to us.
- *
- * blkg_stat_lock is for serializing blkg stat update
- */
- for_each_possible_cpu(cpu)
- __blkcg_rstat_flush(blkcg, cpu);
/* release the blkcg and parent blkg refs this blkg has been holding */
css_put(&blkg->blkcg->css);
@@ -201,6 +191,17 @@ static void __blkg_release(struct rcu_head *rcu)
static void blkg_release(struct percpu_ref *ref)
{
struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt);
+ struct blkcg *blkcg = blkg->blkcg;
+ int cpu;
+
+ /*
+ * Flush all the non-empty percpu lockless lists before releasing
+ * us, given these stat belongs to us.
+ *
+ * blkg_stat_lock is for serializing blkg stat update
+ */
+ for_each_possible_cpu(cpu)
+ __blkcg_rstat_flush(blkcg, cpu);
call_rcu(&blkg->rcu_head, __blkg_release);
}
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 9e413f522bd6..468ef9b3983c 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -773,7 +773,6 @@ static int add_memory_block(unsigned long block_id, unsigned long state,
mem->start_section_nr = block_id * sections_per_block;
mem->state = state;
mem->nid = NUMA_NO_NODE;
- mem->altmap = altmap;
INIT_LIST_HEAD(&mem->group_next);
#ifndef CONFIG_NUMA
@@ -791,6 +790,8 @@ static int add_memory_block(unsigned long block_id, unsigned long state,
if (ret)
return ret;
+ mem->altmap = altmap;
+
if (group) {
mem->group = group;
list_add(&mem->group_next, &group->memory_blocks);
diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c
index ad8753dda826..582915f9a8d7 100644
--- a/drivers/bluetooth/btmtk.c
+++ b/drivers/bluetooth/btmtk.c
@@ -655,8 +655,13 @@ int btmtk_usb_hci_wmt_sync(struct hci_dev *hdev,
if (data->evt_skb == NULL)
goto err_free_wc;
- /* Parse and handle the return WMT event */
- wmt_evt = (struct btmtk_hci_wmt_evt *)data->evt_skb->data;
+ wmt_evt = skb_pull_data(data->evt_skb, sizeof(*wmt_evt));
+ if (!wmt_evt) {
+ bt_dev_err(hdev, "WMT event too short (%u bytes)",
+ data->evt_skb->len);
+ err = -EINVAL;
+ goto err_free_skb;
+ }
if (wmt_evt->whdr.op != hdr->op) {
bt_dev_err(hdev, "Wrong op received %d expected %d",
wmt_evt->whdr.op, hdr->op);
@@ -672,6 +677,12 @@ int btmtk_usb_hci_wmt_sync(struct hci_dev *hdev,
status = BTMTK_WMT_PATCH_DONE;
break;
case BTMTK_WMT_FUNC_CTRL:
+ if (!skb_pull_data(data->evt_skb,
+ sizeof(wmt_evt_funcc->status))) {
+ status = BTMTK_WMT_ON_UNDONE;
+ break;
+ }
+
wmt_evt_funcc = (struct btmtk_hci_wmt_evt_funcc *)wmt_evt;
if (be16_to_cpu(wmt_evt_funcc->status) == 0x404)
status = BTMTK_WMT_ON_DONE;
diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c
index ce8651436609..e4b58108861e 100644
--- a/drivers/char/agp/amd64-agp.c
+++ b/drivers/char/agp/amd64-agp.c
@@ -546,7 +546,7 @@ static int agp_amd64_probe(struct pci_dev *pdev,
/* Fill in the mode register */
pci_read_config_dword(pdev, bridge->capndx+PCI_AGP_STATUS, &bridge->mode);
- if (cache_nbs(pdev, cap_ptr) == -1) {
+ if (cache_nbs(pdev, cap_ptr) < 0) {
agp_put_bridge(bridge);
return -ENODEV;
}
diff --git a/drivers/crypto/intel/qat/qat_common/adf_cfg_common.h b/drivers/crypto/intel/qat/qat_common/adf_cfg_common.h
index 6e5de1dab97b..8d8d5d02755e 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_cfg_common.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_cfg_common.h
@@ -4,18 +4,11 @@
#define ADF_CFG_COMMON_H_
#include <linux/types.h>
-#include <linux/ioctl.h>
#define ADF_CFG_MAX_STR_LEN 64
#define ADF_CFG_MAX_KEY_LEN_IN_BYTES ADF_CFG_MAX_STR_LEN
#define ADF_CFG_MAX_VAL_LEN_IN_BYTES ADF_CFG_MAX_STR_LEN
#define ADF_CFG_MAX_SECTION_LEN_IN_BYTES ADF_CFG_MAX_STR_LEN
-#define ADF_CFG_BASE_DEC 10
-#define ADF_CFG_BASE_HEX 16
-#define ADF_CFG_ALL_DEVICES 0xFE
-#define ADF_CFG_NO_DEVICE 0xFF
-#define ADF_CFG_AFFINITY_WHATEVER 0xFF
-#define MAX_DEVICE_NAME_SIZE 32
#define ADF_MAX_DEVICES (32 * 32)
#define ADF_DEVS_ARRAY_SIZE BITS_TO_LONGS(ADF_MAX_DEVICES)
@@ -48,29 +41,4 @@ enum adf_device_type {
DEV_C3XXXVF,
DEV_4XXX,
};
-
-struct adf_dev_status_info {
- enum adf_device_type type;
- __u32 accel_id;
- __u32 instance_id;
- __u8 num_ae;
- __u8 num_accel;
- __u8 num_logical_accel;
- __u8 banks_per_accel;
- __u8 state;
- __u8 bus;
- __u8 dev;
- __u8 fun;
- char name[MAX_DEVICE_NAME_SIZE];
-};
-
-#define ADF_CTL_IOC_MAGIC 'a'
-#define IOCTL_CONFIG_SYS_RESOURCE_PARAMETERS _IOW(ADF_CTL_IOC_MAGIC, 0, \
- struct adf_user_cfg_ctl_data)
-#define IOCTL_STOP_ACCEL_DEV _IOW(ADF_CTL_IOC_MAGIC, 1, \
- struct adf_user_cfg_ctl_data)
-#define IOCTL_START_ACCEL_DEV _IOW(ADF_CTL_IOC_MAGIC, 2, \
- struct adf_user_cfg_ctl_data)
-#define IOCTL_STATUS_ACCEL_DEV _IOW(ADF_CTL_IOC_MAGIC, 3, __u32)
-#define IOCTL_GET_NUM_DEVICES _IOW(ADF_CTL_IOC_MAGIC, 4, __s32)
#endif
diff --git a/drivers/crypto/intel/qat/qat_common/adf_cfg_user.h b/drivers/crypto/intel/qat/qat_common/adf_cfg_user.h
deleted file mode 100644
index 421f4fb8b4dd..000000000000
--- a/drivers/crypto/intel/qat/qat_common/adf_cfg_user.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: (BSD-3-Clause OR GPL-2.0-only) */
-/* Copyright(c) 2014 - 2020 Intel Corporation */
-#ifndef ADF_CFG_USER_H_
-#define ADF_CFG_USER_H_
-
-#include "adf_cfg_common.h"
-#include "adf_cfg_strings.h"
-
-struct adf_user_cfg_key_val {
- char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
- char val[ADF_CFG_MAX_VAL_LEN_IN_BYTES];
- union {
- struct adf_user_cfg_key_val *next;
- __u64 padding3;
- };
- enum adf_cfg_val_type type;
-} __packed;
-
-struct adf_user_cfg_section {
- char name[ADF_CFG_MAX_SECTION_LEN_IN_BYTES];
- union {
- struct adf_user_cfg_key_val *params;
- __u64 padding1;
- };
- union {
- struct adf_user_cfg_section *next;
- __u64 padding3;
- };
-} __packed;
-
-struct adf_user_cfg_ctl_data {
- union {
- struct adf_user_cfg_section *config_section;
- __u64 padding;
- };
- __u8 device_id;
-} __packed;
-#endif
diff --git a/drivers/crypto/intel/qat/qat_common/adf_common_drv.h b/drivers/crypto/intel/qat/qat_common/adf_common_drv.h
index 05d1402001a1..d9255b307c4b 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_common_drv.h
+++ b/drivers/crypto/intel/qat/qat_common/adf_common_drv.h
@@ -65,11 +65,8 @@ int adf_devmgr_add_dev(struct adf_accel_dev *accel_dev,
void adf_devmgr_rm_dev(struct adf_accel_dev *accel_dev,
struct adf_accel_dev *pf);
struct list_head *adf_devmgr_get_head(void);
-struct adf_accel_dev *adf_devmgr_get_dev_by_id(u32 id);
struct adf_accel_dev *adf_devmgr_get_first(void);
struct adf_accel_dev *adf_devmgr_pci_to_accel_dev(struct pci_dev *pci_dev);
-int adf_devmgr_verify_id(u32 id);
-void adf_devmgr_get_num_dev(u32 *num);
int adf_devmgr_in_reset(struct adf_accel_dev *accel_dev);
int adf_dev_started(struct adf_accel_dev *accel_dev);
int adf_dev_restarting_notify(struct adf_accel_dev *accel_dev);
diff --git a/drivers/crypto/intel/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/intel/qat/qat_common/adf_ctl_drv.c
index 29c4422f243c..36d5ebb3efab 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_ctl_drv.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_ctl_drv.c
@@ -2,419 +2,13 @@
/* Copyright(c) 2014 - 2020 Intel Corporation */
#include <crypto/algapi.h>
+#include <linux/errno.h>
#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/slab.h>
-#include <linux/fs.h>
-#include <linux/bitops.h>
-#include <linux/pci.h>
-#include <linux/cdev.h>
-#include <linux/uaccess.h>
-#include "adf_accel_devices.h"
#include "adf_common_drv.h"
-#include "adf_cfg.h"
-#include "adf_cfg_common.h"
-#include "adf_cfg_user.h"
-
-#define ADF_CFG_MAX_SECTION 512
-#define ADF_CFG_MAX_KEY_VAL 256
-
-#define DEVICE_NAME "qat_adf_ctl"
-
-static DEFINE_MUTEX(adf_ctl_lock);
-static long adf_ctl_ioctl(struct file *fp, unsigned int cmd, unsigned long arg);
-
-static const struct file_operations adf_ctl_ops = {
- .owner = THIS_MODULE,
- .unlocked_ioctl = adf_ctl_ioctl,
- .compat_ioctl = compat_ptr_ioctl,
-};
-
-struct adf_ctl_drv_info {
- unsigned int major;
- struct cdev drv_cdev;
- struct class *drv_class;
-};
-
-static struct adf_ctl_drv_info adf_ctl_drv;
-
-static void adf_chr_drv_destroy(void)
-{
- device_destroy(adf_ctl_drv.drv_class, MKDEV(adf_ctl_drv.major, 0));
- cdev_del(&adf_ctl_drv.drv_cdev);
- class_destroy(adf_ctl_drv.drv_class);
- unregister_chrdev_region(MKDEV(adf_ctl_drv.major, 0), 1);
-}
-
-static int adf_chr_drv_create(void)
-{
- dev_t dev_id;
- struct device *drv_device;
-
- if (alloc_chrdev_region(&dev_id, 0, 1, DEVICE_NAME)) {
- pr_err("QAT: unable to allocate chrdev region\n");
- return -EFAULT;
- }
-
- adf_ctl_drv.drv_class = class_create(DEVICE_NAME);
- if (IS_ERR(adf_ctl_drv.drv_class)) {
- pr_err("QAT: class_create failed for adf_ctl\n");
- goto err_chrdev_unreg;
- }
- adf_ctl_drv.major = MAJOR(dev_id);
- cdev_init(&adf_ctl_drv.drv_cdev, &adf_ctl_ops);
- if (cdev_add(&adf_ctl_drv.drv_cdev, dev_id, 1)) {
- pr_err("QAT: cdev add failed\n");
- goto err_class_destr;
- }
-
- drv_device = device_create(adf_ctl_drv.drv_class, NULL,
- MKDEV(adf_ctl_drv.major, 0),
- NULL, DEVICE_NAME);
- if (IS_ERR(drv_device)) {
- pr_err("QAT: failed to create device\n");
- goto err_cdev_del;
- }
- return 0;
-err_cdev_del:
- cdev_del(&adf_ctl_drv.drv_cdev);
-err_class_destr:
- class_destroy(adf_ctl_drv.drv_class);
-err_chrdev_unreg:
- unregister_chrdev_region(dev_id, 1);
- return -EFAULT;
-}
-
-static int adf_ctl_alloc_resources(struct adf_user_cfg_ctl_data **ctl_data,
- unsigned long arg)
-{
- struct adf_user_cfg_ctl_data *cfg_data;
-
- cfg_data = kzalloc(sizeof(*cfg_data), GFP_KERNEL);
- if (!cfg_data)
- return -ENOMEM;
-
- /* Initialize device id to NO DEVICE as 0 is a valid device id */
- cfg_data->device_id = ADF_CFG_NO_DEVICE;
-
- if (copy_from_user(cfg_data, (void __user *)arg, sizeof(*cfg_data))) {
- pr_err("QAT: failed to copy from user cfg_data.\n");
- kfree(cfg_data);
- return -EIO;
- }
-
- *ctl_data = cfg_data;
- return 0;
-}
-
-static int adf_add_key_value_data(struct adf_accel_dev *accel_dev,
- const char *section,
- const struct adf_user_cfg_key_val *key_val)
-{
- if (key_val->type == ADF_HEX) {
- long *ptr = (long *)key_val->val;
- long val = *ptr;
-
- if (adf_cfg_add_key_value_param(accel_dev, section,
- key_val->key, (void *)val,
- key_val->type)) {
- dev_err(&GET_DEV(accel_dev),
- "failed to add hex keyvalue.\n");
- return -EFAULT;
- }
- } else {
- if (adf_cfg_add_key_value_param(accel_dev, section,
- key_val->key, key_val->val,
- key_val->type)) {
- dev_err(&GET_DEV(accel_dev),
- "failed to add keyvalue.\n");
- return -EFAULT;
- }
- }
- return 0;
-}
-
-static int adf_copy_key_value_data(struct adf_accel_dev *accel_dev,
- struct adf_user_cfg_ctl_data *ctl_data)
-{
- struct adf_user_cfg_key_val key_val;
- struct adf_user_cfg_key_val *params_head;
- struct adf_user_cfg_section section, *section_head;
- int i, j;
-
- section_head = ctl_data->config_section;
-
- for (i = 0; section_head && i < ADF_CFG_MAX_SECTION; i++) {
- if (copy_from_user(§ion, (void __user *)section_head,
- sizeof(*section_head))) {
- dev_err(&GET_DEV(accel_dev),
- "failed to copy section info\n");
- goto out_err;
- }
-
- if (adf_cfg_section_add(accel_dev, section.name)) {
- dev_err(&GET_DEV(accel_dev),
- "failed to add section.\n");
- goto out_err;
- }
-
- params_head = section.params;
-
- for (j = 0; params_head && j < ADF_CFG_MAX_KEY_VAL; j++) {
- if (copy_from_user(&key_val, (void __user *)params_head,
- sizeof(key_val))) {
- dev_err(&GET_DEV(accel_dev),
- "Failed to copy keyvalue.\n");
- goto out_err;
- }
- if (adf_add_key_value_data(accel_dev, section.name,
- &key_val)) {
- goto out_err;
- }
- params_head = key_val.next;
- }
- section_head = section.next;
- }
- return 0;
-out_err:
- adf_cfg_del_all(accel_dev);
- return -EFAULT;
-}
-
-static int adf_ctl_ioctl_dev_config(struct file *fp, unsigned int cmd,
- unsigned long arg)
-{
- int ret;
- struct adf_user_cfg_ctl_data *ctl_data;
- struct adf_accel_dev *accel_dev;
-
- ret = adf_ctl_alloc_resources(&ctl_data, arg);
- if (ret)
- return ret;
-
- accel_dev = adf_devmgr_get_dev_by_id(ctl_data->device_id);
- if (!accel_dev) {
- ret = -EFAULT;
- goto out;
- }
-
- if (adf_dev_started(accel_dev)) {
- ret = -EFAULT;
- goto out;
- }
-
- if (adf_copy_key_value_data(accel_dev, ctl_data)) {
- ret = -EFAULT;
- goto out;
- }
- set_bit(ADF_STATUS_CONFIGURED, &accel_dev->status);
-out:
- kfree(ctl_data);
- return ret;
-}
-
-static int adf_ctl_is_device_in_use(int id)
-{
- struct adf_accel_dev *dev;
-
- list_for_each_entry(dev, adf_devmgr_get_head(), list) {
- if (id == dev->accel_id || id == ADF_CFG_ALL_DEVICES) {
- if (adf_devmgr_in_reset(dev) || adf_dev_in_use(dev)) {
- dev_info(&GET_DEV(dev),
- "device qat_dev%d is busy\n",
- dev->accel_id);
- return -EBUSY;
- }
- }
- }
- return 0;
-}
-
-static void adf_ctl_stop_devices(u32 id)
-{
- struct adf_accel_dev *accel_dev;
-
- list_for_each_entry(accel_dev, adf_devmgr_get_head(), list) {
- if (id == accel_dev->accel_id || id == ADF_CFG_ALL_DEVICES) {
- if (!adf_dev_started(accel_dev))
- continue;
-
- /* First stop all VFs */
- if (!accel_dev->is_vf)
- continue;
-
- adf_dev_down(accel_dev, false);
- }
- }
-
- list_for_each_entry(accel_dev, adf_devmgr_get_head(), list) {
- if (id == accel_dev->accel_id || id == ADF_CFG_ALL_DEVICES) {
- if (!adf_dev_started(accel_dev))
- continue;
-
- adf_dev_down(accel_dev, false);
- }
- }
-}
-
-static int adf_ctl_ioctl_dev_stop(struct file *fp, unsigned int cmd,
- unsigned long arg)
-{
- int ret;
- struct adf_user_cfg_ctl_data *ctl_data;
-
- ret = adf_ctl_alloc_resources(&ctl_data, arg);
- if (ret)
- return ret;
-
- if (adf_devmgr_verify_id(ctl_data->device_id)) {
- pr_err("QAT: Device %d not found\n", ctl_data->device_id);
- ret = -ENODEV;
- goto out;
- }
-
- ret = adf_ctl_is_device_in_use(ctl_data->device_id);
- if (ret)
- goto out;
-
- if (ctl_data->device_id == ADF_CFG_ALL_DEVICES)
- pr_info("QAT: Stopping all acceleration devices.\n");
- else
- pr_info("QAT: Stopping acceleration device qat_dev%d.\n",
- ctl_data->device_id);
-
- adf_ctl_stop_devices(ctl_data->device_id);
-
-out:
- kfree(ctl_data);
- return ret;
-}
-
-static int adf_ctl_ioctl_dev_start(struct file *fp, unsigned int cmd,
- unsigned long arg)
-{
- int ret;
- struct adf_user_cfg_ctl_data *ctl_data;
- struct adf_accel_dev *accel_dev;
-
- ret = adf_ctl_alloc_resources(&ctl_data, arg);
- if (ret)
- return ret;
-
- ret = -ENODEV;
- accel_dev = adf_devmgr_get_dev_by_id(ctl_data->device_id);
- if (!accel_dev)
- goto out;
-
- dev_info(&GET_DEV(accel_dev),
- "Starting acceleration device qat_dev%d.\n",
- ctl_data->device_id);
-
- ret = adf_dev_up(accel_dev, false);
-
- if (ret) {
- dev_err(&GET_DEV(accel_dev), "Failed to start qat_dev%d\n",
- ctl_data->device_id);
- adf_dev_down(accel_dev, false);
- }
-out:
- kfree(ctl_data);
- return ret;
-}
-
-static int adf_ctl_ioctl_get_num_devices(struct file *fp, unsigned int cmd,
- unsigned long arg)
-{
- u32 num_devices = 0;
-
- adf_devmgr_get_num_dev(&num_devices);
- if (copy_to_user((void __user *)arg, &num_devices, sizeof(num_devices)))
- return -EFAULT;
-
- return 0;
-}
-
-static int adf_ctl_ioctl_get_status(struct file *fp, unsigned int cmd,
- unsigned long arg)
-{
- struct adf_hw_device_data *hw_data;
- struct adf_dev_status_info dev_info;
- struct adf_accel_dev *accel_dev;
-
- if (copy_from_user(&dev_info, (void __user *)arg,
- sizeof(struct adf_dev_status_info))) {
- pr_err("QAT: failed to copy from user.\n");
- return -EFAULT;
- }
-
- accel_dev = adf_devmgr_get_dev_by_id(dev_info.accel_id);
- if (!accel_dev)
- return -ENODEV;
-
- hw_data = accel_dev->hw_device;
- dev_info.state = adf_dev_started(accel_dev) ? DEV_UP : DEV_DOWN;
- dev_info.num_ae = hw_data->get_num_aes(hw_data);
- dev_info.num_accel = hw_data->get_num_accels(hw_data);
- dev_info.num_logical_accel = hw_data->num_logical_accel;
- dev_info.banks_per_accel = hw_data->num_banks
- / hw_data->num_logical_accel;
- strscpy(dev_info.name, hw_data->dev_class->name, sizeof(dev_info.name));
- dev_info.instance_id = hw_data->instance_id;
- dev_info.type = hw_data->dev_class->type;
- dev_info.bus = accel_to_pci_dev(accel_dev)->bus->number;
- dev_info.dev = PCI_SLOT(accel_to_pci_dev(accel_dev)->devfn);
- dev_info.fun = PCI_FUNC(accel_to_pci_dev(accel_dev)->devfn);
-
- if (copy_to_user((void __user *)arg, &dev_info,
- sizeof(struct adf_dev_status_info))) {
- dev_err(&GET_DEV(accel_dev), "failed to copy status.\n");
- return -EFAULT;
- }
- return 0;
-}
-
-static long adf_ctl_ioctl(struct file *fp, unsigned int cmd, unsigned long arg)
-{
- int ret;
-
- if (mutex_lock_interruptible(&adf_ctl_lock))
- return -EFAULT;
-
- switch (cmd) {
- case IOCTL_CONFIG_SYS_RESOURCE_PARAMETERS:
- ret = adf_ctl_ioctl_dev_config(fp, cmd, arg);
- break;
-
- case IOCTL_STOP_ACCEL_DEV:
- ret = adf_ctl_ioctl_dev_stop(fp, cmd, arg);
- break;
-
- case IOCTL_START_ACCEL_DEV:
- ret = adf_ctl_ioctl_dev_start(fp, cmd, arg);
- break;
-
- case IOCTL_GET_NUM_DEVICES:
- ret = adf_ctl_ioctl_get_num_devices(fp, cmd, arg);
- break;
-
- case IOCTL_STATUS_ACCEL_DEV:
- ret = adf_ctl_ioctl_get_status(fp, cmd, arg);
- break;
- default:
- pr_err_ratelimited("QAT: Invalid ioctl %d\n", cmd);
- ret = -EFAULT;
- break;
- }
- mutex_unlock(&adf_ctl_lock);
- return ret;
-}
static int __init adf_register_ctl_device_driver(void)
{
- if (adf_chr_drv_create())
- goto err_chr_dev;
-
if (adf_init_misc_wq())
goto err_misc_wq;
@@ -446,15 +40,11 @@ static int __init adf_register_ctl_device_driver(void)
err_aer:
adf_exit_misc_wq();
err_misc_wq:
- adf_chr_drv_destroy();
-err_chr_dev:
- mutex_destroy(&adf_ctl_lock);
return -EFAULT;
}
static void __exit adf_unregister_ctl_device_driver(void)
{
- adf_chr_drv_destroy();
adf_exit_misc_wq();
adf_exit_aer();
adf_exit_vf_wq();
@@ -462,7 +52,6 @@ static void __exit adf_unregister_ctl_device_driver(void)
qat_crypto_unregister();
qat_compression_unregister();
adf_clean_vf_map(false);
- mutex_destroy(&adf_ctl_lock);
}
module_init(adf_register_ctl_device_driver);
diff --git a/drivers/crypto/intel/qat/qat_common/adf_dev_mgr.c b/drivers/crypto/intel/qat/qat_common/adf_dev_mgr.c
index 86ee36feefad..9bdfa5b1614f 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_dev_mgr.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_dev_mgr.c
@@ -45,19 +45,6 @@ static struct vf_id_map *adf_find_vf(u32 bdf)
return NULL;
}
-static int adf_get_vf_real_id(u32 fake)
-{
- struct list_head *itr;
-
- list_for_each(itr, &vfs_table) {
- struct vf_id_map *ptr =
- list_entry(itr, struct vf_id_map, list);
- if (ptr->fake_id == fake)
- return ptr->id;
- }
- return -1;
-}
-
/**
* adf_clean_vf_map() - Cleans VF id mapings
*
@@ -314,63 +301,6 @@ struct adf_accel_dev *adf_devmgr_pci_to_accel_dev(struct pci_dev *pci_dev)
}
EXPORT_SYMBOL_GPL(adf_devmgr_pci_to_accel_dev);
-struct adf_accel_dev *adf_devmgr_get_dev_by_id(u32 id)
-{
- struct list_head *itr;
- int real_id;
-
- mutex_lock(&table_lock);
- real_id = adf_get_vf_real_id(id);
- if (real_id < 0)
- goto unlock;
-
- id = real_id;
-
- list_for_each(itr, &accel_table) {
- struct adf_accel_dev *ptr =
- list_entry(itr, struct adf_accel_dev, list);
- if (ptr->accel_id == id) {
- mutex_unlock(&table_lock);
- return ptr;
- }
- }
-unlock:
- mutex_unlock(&table_lock);
- return NULL;
-}
-
-int adf_devmgr_verify_id(u32 id)
-{
- if (id == ADF_CFG_ALL_DEVICES)
- return 0;
-
- if (adf_devmgr_get_dev_by_id(id))
- return 0;
-
- return -ENODEV;
-}
-
-static int adf_get_num_dettached_vfs(void)
-{
- struct list_head *itr;
- int vfs = 0;
-
- mutex_lock(&table_lock);
- list_for_each(itr, &vfs_table) {
- struct vf_id_map *ptr =
- list_entry(itr, struct vf_id_map, list);
- if (ptr->bdf != ~0 && !ptr->attached)
- vfs++;
- }
- mutex_unlock(&table_lock);
- return vfs;
-}
-
-void adf_devmgr_get_num_dev(u32 *num)
-{
- *num = num_devices - adf_get_num_dettached_vfs();
-}
-
/**
* adf_dev_in_use() - Check whether accel_dev is currently in use
* @accel_dev: Pointer to acceleration device.
diff --git a/drivers/fpga/of-fpga-region.c b/drivers/fpga/of-fpga-region.c
index ed6eae985117..af3ab11e005c 100644
--- a/drivers/fpga/of-fpga-region.c
+++ b/drivers/fpga/of-fpga-region.c
@@ -168,11 +168,10 @@ static int child_regions_with_firmware(struct device_node *overlay)
fpga_region_of_match);
}
- of_node_put(child_region);
-
if (ret)
pr_err("firmware-name not allowed in child FPGA region: %pOF",
child_region);
+ of_node_put(child_region);
return ret;
}
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
index ac2a71e80723..fa8fcbcc421a 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
@@ -225,6 +225,7 @@ static enum bp_result bios_parser_get_i2c_info(struct dc_bios *dcb,
ATOM_COMMON_RECORD_HEADER *header;
ATOM_I2C_RECORD *record;
struct bios_parser *bp = BP_FROM_DCB(dcb);
+ int i;
if (!info)
return BP_RESULT_BADINPUT;
@@ -237,7 +238,7 @@ static enum bp_result bios_parser_get_i2c_info(struct dc_bios *dcb,
offset = le16_to_cpu(object->usRecordOffset)
+ bp->object_info_tbl_offset;
- for (;;) {
+ for (i = 0; i < BIOS_MAX_NUM_RECORD; i++) {
header = GET_IMAGE(ATOM_COMMON_RECORD_HEADER, offset);
if (!header)
@@ -296,11 +297,12 @@ static enum bp_result bios_parser_get_device_tag_record(
{
ATOM_COMMON_RECORD_HEADER *header;
uint32_t offset;
+ int i;
offset = le16_to_cpu(object->usRecordOffset)
+ bp->object_info_tbl_offset;
- for (;;) {
+ for (i = 0; i < BIOS_MAX_NUM_RECORD; i++) {
header = GET_IMAGE(ATOM_COMMON_RECORD_HEADER, offset);
if (!header)
@@ -873,6 +875,7 @@ static ATOM_HPD_INT_RECORD *get_hpd_record(struct bios_parser *bp,
{
ATOM_COMMON_RECORD_HEADER *header;
uint32_t offset;
+ int i;
if (!object) {
BREAK_TO_DEBUGGER(); /* Invalid object */
@@ -882,7 +885,7 @@ static ATOM_HPD_INT_RECORD *get_hpd_record(struct bios_parser *bp,
offset = le16_to_cpu(object->usRecordOffset)
+ bp->object_info_tbl_offset;
- for (;;) {
+ for (i = 0; i < BIOS_MAX_NUM_RECORD; i++) {
header = GET_IMAGE(ATOM_COMMON_RECORD_HEADER, offset);
if (!header)
@@ -1577,6 +1580,7 @@ static ATOM_ENCODER_CAP_RECORD_V2 *get_encoder_cap_record(
{
ATOM_COMMON_RECORD_HEADER *header;
uint32_t offset;
+ int i;
if (!object) {
BREAK_TO_DEBUGGER(); /* Invalid object */
@@ -1586,7 +1590,7 @@ static ATOM_ENCODER_CAP_RECORD_V2 *get_encoder_cap_record(
offset = le16_to_cpu(object->usRecordOffset)
+ bp->object_info_tbl_offset;
- for (;;) {
+ for (i = 0; i < BIOS_MAX_NUM_RECORD; i++) {
header = GET_IMAGE(ATOM_COMMON_RECORD_HEADER, offset);
if (!header)
@@ -2675,6 +2679,7 @@ static enum bp_result update_slot_layout_info(struct dc_bios *dcb,
unsigned int record_offset)
{
unsigned int j;
+ unsigned int n;
struct bios_parser *bp;
ATOM_BRACKET_LAYOUT_RECORD *record;
ATOM_COMMON_RECORD_HEADER *record_header;
@@ -2684,7 +2689,7 @@ static enum bp_result update_slot_layout_info(struct dc_bios *dcb,
record = NULL;
record_header = NULL;
- for (;;) {
+ for (n = 0; n < BIOS_MAX_NUM_RECORD; n++) {
record_header = GET_IMAGE(ATOM_COMMON_RECORD_HEADER, record_offset);
if (record_header == NULL) {
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index ed8f669a9a3e..33142f1c3746 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -391,6 +391,7 @@ static enum bp_result bios_parser_get_i2c_info(struct dc_bios *dcb,
struct atom_i2c_record *record;
struct atom_i2c_record dummy_record = {0};
struct bios_parser *bp = BP_FROM_DCB(dcb);
+ int i;
if (!info)
return BP_RESULT_BADINPUT;
@@ -424,7 +425,7 @@ static enum bp_result bios_parser_get_i2c_info(struct dc_bios *dcb,
break;
}
- for (;;) {
+ for (i = 0; i < BIOS_MAX_NUM_RECORD; i++) {
header = GET_IMAGE(struct atom_common_record_header, offset);
if (!header)
@@ -529,6 +530,7 @@ static struct atom_hpd_int_record *get_hpd_record_for_path_v3(struct bios_parser
{
struct atom_common_record_header *header;
uint32_t offset;
+ int i;
if (!object) {
BREAK_TO_DEBUGGER(); /* Invalid object */
@@ -537,7 +539,7 @@ static struct atom_hpd_int_record *get_hpd_record_for_path_v3(struct bios_parser
offset = object->disp_recordoffset + bp->object_info_tbl_offset;
- for (;;) {
+ for (i = 0; i < BIOS_MAX_NUM_RECORD; i++) {
header = GET_IMAGE(struct atom_common_record_header, offset);
if (!header)
@@ -607,6 +609,7 @@ static struct atom_hpd_int_record *get_hpd_record(
{
struct atom_common_record_header *header;
uint32_t offset;
+ int i;
if (!object) {
BREAK_TO_DEBUGGER(); /* Invalid object */
@@ -616,7 +619,7 @@ static struct atom_hpd_int_record *get_hpd_record(
offset = le16_to_cpu(object->disp_recordoffset)
+ bp->object_info_tbl_offset;
- for (;;) {
+ for (i = 0; i < BIOS_MAX_NUM_RECORD; i++) {
header = GET_IMAGE(struct atom_common_record_header, offset);
if (!header)
@@ -2125,6 +2128,7 @@ static struct atom_encoder_caps_record *get_encoder_cap_record(
{
struct atom_common_record_header *header;
uint32_t offset;
+ int i;
if (!object) {
BREAK_TO_DEBUGGER(); /* Invalid object */
@@ -2133,7 +2137,7 @@ static struct atom_encoder_caps_record *get_encoder_cap_record(
offset = object->encoder_recordoffset + bp->object_info_tbl_offset;
- for (;;) {
+ for (i = 0; i < BIOS_MAX_NUM_RECORD; i++) {
header = GET_IMAGE(struct atom_common_record_header, offset);
if (!header)
@@ -2162,6 +2166,7 @@ static struct atom_disp_connector_caps_record *get_disp_connector_caps_record(
{
struct atom_common_record_header *header;
uint32_t offset;
+ int i;
if (!object) {
BREAK_TO_DEBUGGER(); /* Invalid object */
@@ -2170,7 +2175,7 @@ static struct atom_disp_connector_caps_record *get_disp_connector_caps_record(
offset = object->disp_recordoffset + bp->object_info_tbl_offset;
- for (;;) {
+ for (i = 0; i < BIOS_MAX_NUM_RECORD; i++) {
header = GET_IMAGE(struct atom_common_record_header, offset);
if (!header)
@@ -2198,6 +2203,7 @@ static struct atom_connector_caps_record *get_connector_caps_record(struct bios_
{
struct atom_common_record_header *header;
uint32_t offset;
+ int i;
if (!object) {
BREAK_TO_DEBUGGER(); /* Invalid object */
@@ -2206,7 +2212,7 @@ static struct atom_connector_caps_record *get_connector_caps_record(struct bios_
offset = object->disp_recordoffset + bp->object_info_tbl_offset;
- for (;;) {
+ for (i = 0; i < BIOS_MAX_NUM_RECORD; i++) {
header = GET_IMAGE(struct atom_common_record_header, offset);
if (!header)
@@ -2286,6 +2292,7 @@ static struct atom_connector_speed_record *get_connector_speed_cap_record(struct
{
struct atom_common_record_header *header;
uint32_t offset;
+ int i;
if (!object) {
BREAK_TO_DEBUGGER(); /* Invalid object */
@@ -2294,7 +2301,7 @@ static struct atom_connector_speed_record *get_connector_speed_cap_record(struct
offset = object->disp_recordoffset + bp->object_info_tbl_offset;
- for (;;) {
+ for (i = 0; i < BIOS_MAX_NUM_RECORD; i++) {
header = GET_IMAGE(struct atom_common_record_header, offset);
if (!header)
@@ -3154,6 +3161,7 @@ static enum bp_result update_slot_layout_info(
{
unsigned int record_offset;
unsigned int j;
+ unsigned int n;
struct atom_display_object_path_v2 *object;
struct atom_bracket_layout_record *record;
struct atom_common_record_header *record_header;
@@ -3175,7 +3183,7 @@ static enum bp_result update_slot_layout_info(
(object->disp_recordoffset) +
(unsigned int)(bp->object_info_tbl_offset);
- for (;;) {
+ for (n = 0; n < BIOS_MAX_NUM_RECORD; n++) {
record_header = (struct atom_common_record_header *)
GET_IMAGE(struct atom_common_record_header,
@@ -3269,6 +3277,7 @@ static enum bp_result update_slot_layout_info_v2(
struct slot_layout_info *slot_layout_info)
{
unsigned int record_offset;
+ unsigned int n;
struct atom_display_object_path_v3 *object;
struct atom_bracket_layout_record_v2 *record;
struct atom_common_record_header *record_header;
@@ -3291,7 +3300,7 @@ static enum bp_result update_slot_layout_info_v2(
(object->disp_recordoffset) +
(unsigned int)(bp->object_info_tbl_offset);
- for (;;) {
+ for (n = 0; n < BIOS_MAX_NUM_RECORD; n++) {
record_header = (struct atom_common_record_header *)
GET_IMAGE(struct atom_common_record_header,
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser_helper.h b/drivers/gpu/drm/amd/display/dc/bios/bios_parser_helper.h
index e1b4a40a353d..da1e30de3c59 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser_helper.h
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser_helper.h
@@ -38,4 +38,9 @@ uint32_t bios_get_vga_enabled_displays(struct dc_bios *bios);
#define GET_IMAGE(type, offset) ((type *) bios_get_image(&bp->base, offset, sizeof(type)))
+/* Upper bound on the number of records in a VBIOS record chain. Prevents
+ * unbounded looping if the VBIOS image is malformed and lacks a terminator.
+ */
+#define BIOS_MAX_NUM_RECORD 256
+
#endif
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index bcef978ba9c4..91ea0a80879a 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -26,6 +26,9 @@ struct v3d_queue_state {
u64 fence_context;
u64 emit_seqno;
+
+ /* Currently active job for this queue */
+ struct v3d_job *active_job;
};
/* Performance monitor object. The perform lifetime is controlled by userspace
@@ -110,11 +113,6 @@ struct v3d_dev {
struct work_struct overflow_mem_work;
- struct v3d_bin_job *bin_job;
- struct v3d_render_job *render_job;
- struct v3d_tfu_job *tfu_job;
- struct v3d_csd_job *csd_job;
-
struct v3d_queue_state queue[V3D_MAX_QUEUES];
/* Spinlock used to synchronize the overflow memory
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 057f9525a8a4..f14c9f714335 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -1071,14 +1071,15 @@ void
v3d_gem_destroy(struct drm_device *dev)
{
struct v3d_dev *v3d = to_v3d_dev(dev);
+ enum v3d_queue q;
v3d_sched_fini(v3d);
/* Waiting for jobs to finish would need to be done before
* unregistering V3D.
*/
- WARN_ON(v3d->bin_job);
- WARN_ON(v3d->render_job);
+ for (q = 0; q < V3D_MAX_QUEUES; q++)
+ WARN_ON(v3d->queue[q].active_job);
drm_mm_takedown(&v3d->mm);
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
index 641315dbee8b..1717504742a6 100644
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -40,6 +40,8 @@ v3d_overflow_mem_work(struct work_struct *work)
container_of(work, struct v3d_dev, overflow_mem_work);
struct drm_device *dev = &v3d->drm;
struct v3d_bo *bo = v3d_bo_create(dev, NULL /* XXX: GMP */, 256 * 1024);
+ struct v3d_queue_state *queue = &v3d->queue[V3D_BIN];
+ struct v3d_bin_job *bin_job;
struct drm_gem_object *obj;
unsigned long irqflags;
@@ -59,13 +61,15 @@ v3d_overflow_mem_work(struct work_struct *work)
* some binner pool anyway.
*/
spin_lock_irqsave(&v3d->job_lock, irqflags);
- if (!v3d->bin_job) {
+ bin_job = (struct v3d_bin_job *)queue->active_job;
+
+ if (!bin_job) {
spin_unlock_irqrestore(&v3d->job_lock, irqflags);
goto out;
}
drm_gem_object_get(obj);
- list_add_tail(&bo->unref_head, &v3d->bin_job->render->unref_list);
+ list_add_tail(&bo->unref_head, &bin_job->render->unref_list);
spin_unlock_irqrestore(&v3d->job_lock, irqflags);
V3D_CORE_WRITE(0, V3D_PTB_BPOA, bo->node.start << PAGE_SHIFT);
@@ -99,11 +103,11 @@ v3d_irq(int irq, void *arg)
if (intsts & V3D_INT_FLDONE) {
struct v3d_fence *fence =
- to_v3d_fence(v3d->bin_job->base.irq_fence);
+ to_v3d_fence(v3d->queue[V3D_BIN].active_job->irq_fence);
trace_v3d_bcl_irq(&v3d->drm, fence->seqno);
- v3d->bin_job = NULL;
+ v3d->queue[V3D_BIN].active_job = NULL;
dma_fence_signal(&fence->base);
status = IRQ_HANDLED;
@@ -111,11 +115,11 @@ v3d_irq(int irq, void *arg)
if (intsts & V3D_INT_FRDONE) {
struct v3d_fence *fence =
- to_v3d_fence(v3d->render_job->base.irq_fence);
+ to_v3d_fence(v3d->queue[V3D_RENDER].active_job->irq_fence);
trace_v3d_rcl_irq(&v3d->drm, fence->seqno);
- v3d->render_job = NULL;
+ v3d->queue[V3D_RENDER].active_job = NULL;
dma_fence_signal(&fence->base);
status = IRQ_HANDLED;
@@ -123,11 +127,11 @@ v3d_irq(int irq, void *arg)
if (intsts & V3D_INT_CSDDONE) {
struct v3d_fence *fence =
- to_v3d_fence(v3d->csd_job->base.irq_fence);
+ to_v3d_fence(v3d->queue[V3D_CSD].active_job->irq_fence);
trace_v3d_csd_irq(&v3d->drm, fence->seqno);
- v3d->csd_job = NULL;
+ v3d->queue[V3D_CSD].active_job = NULL;
dma_fence_signal(&fence->base);
status = IRQ_HANDLED;
@@ -162,11 +166,11 @@ v3d_hub_irq(int irq, void *arg)
if (intsts & V3D_HUB_INT_TFUC) {
struct v3d_fence *fence =
- to_v3d_fence(v3d->tfu_job->base.irq_fence);
+ to_v3d_fence(v3d->queue[V3D_TFU].active_job->irq_fence);
trace_v3d_tfu_irq(&v3d->drm, fence->seqno);
- v3d->tfu_job = NULL;
+ v3d->queue[V3D_TFU].active_job = NULL;
dma_fence_signal(&fence->base);
status = IRQ_HANDLED;
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 41493cf3d03b..ab872bc81800 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -80,14 +80,18 @@ static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)
struct dma_fence *fence;
unsigned long irqflags;
- if (unlikely(job->base.base.s_fence->finished.error))
+ if (unlikely(job->base.base.s_fence->finished.error)) {
+ spin_lock_irqsave(&v3d->job_lock, irqflags);
+ v3d->queue[V3D_BIN].active_job = NULL;
+ spin_unlock_irqrestore(&v3d->job_lock, irqflags);
return NULL;
+ }
/* Lock required around bin_job update vs
* v3d_overflow_mem_work().
*/
spin_lock_irqsave(&v3d->job_lock, irqflags);
- v3d->bin_job = job;
+ v3d->queue[V3D_BIN].active_job = &job->base;
/* Clear out the overflow allocation, so we don't
* reuse the overflow attached to a previous job.
*/
@@ -134,10 +138,12 @@ static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job)
struct drm_device *dev = &v3d->drm;
struct dma_fence *fence;
- if (unlikely(job->base.base.s_fence->finished.error))
+ if (unlikely(job->base.base.s_fence->finished.error)) {
+ v3d->queue[V3D_RENDER].active_job = NULL;
return NULL;
+ }
- v3d->render_job = job;
+ v3d->queue[V3D_RENDER].active_job = &job->base;
/* Can we avoid this flush? We need to be careful of
* scheduling, though -- imagine job0 rendering to texture and
@@ -179,10 +185,12 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job)
struct drm_device *dev = &v3d->drm;
struct dma_fence *fence;
- if (unlikely(job->base.base.s_fence->finished.error))
+ if (unlikely(job->base.base.s_fence->finished.error)) {
+ v3d->queue[V3D_TFU].active_job = NULL;
return NULL;
+ }
- v3d->tfu_job = job;
+ v3d->queue[V3D_TFU].active_job = &job->base;
fence = v3d_fence_create(v3d, V3D_TFU);
if (IS_ERR(fence))
@@ -221,10 +229,22 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
struct dma_fence *fence;
int i;
- if (unlikely(job->base.base.s_fence->finished.error))
+ if (unlikely(job->base.base.s_fence->finished.error)) {
+ v3d->queue[V3D_CSD].active_job = NULL;
+ return NULL;
+ }
+
+ /* The HW interprets a workgroup size of 0 as 65536; however, the
+ * user-space driver exposes a maximum of 65535. Therefore, a 0 in
+ * any dimension means that we have no workgroups and the compute
+ * shader should not be dispatched.
+ */
+ if (!V3D_GET_FIELD(job->args.cfg[0], V3D_CSD_QUEUED_CFG0_NUM_WGS_X) ||
+ !V3D_GET_FIELD(job->args.cfg[1], V3D_CSD_QUEUED_CFG1_NUM_WGS_Y) ||
+ !V3D_GET_FIELD(job->args.cfg[2], V3D_CSD_QUEUED_CFG2_NUM_WGS_Z))
return NULL;
- v3d->csd_job = job;
+ v3d->queue[V3D_CSD].active_job = &job->base;
v3d_invalidate_caches(v3d);
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index 77017d951826..8019ef2cdcf2 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -93,7 +93,7 @@ static void kvp_send_key(struct work_struct *dummy);
static void kvp_respond_to_host(struct hv_kvp_msg *msg, int error);
static void kvp_timeout_func(struct work_struct *dummy);
static void kvp_host_handshake_func(struct work_struct *dummy);
-static void kvp_register(int);
+static int kvp_register(int);
static DECLARE_DELAYED_WORK(kvp_timeout_work, kvp_timeout_func);
static DECLARE_DELAYED_WORK(kvp_host_handshake_work, kvp_host_handshake_func);
@@ -127,24 +127,26 @@ static void kvp_register_done(void)
hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper);
}
-static void
+static int
kvp_register(int reg_value)
{
struct hv_kvp_msg *kvp_msg;
char *version;
+ int ret;
kvp_msg = kzalloc(sizeof(*kvp_msg), GFP_KERNEL);
+ if (!kvp_msg)
+ return -ENOMEM;
- if (kvp_msg) {
- version = kvp_msg->body.kvp_register.version;
- kvp_msg->kvp_hdr.operation = reg_value;
- strcpy(version, HV_DRV_VERSION);
+ version = kvp_msg->body.kvp_register.version;
+ kvp_msg->kvp_hdr.operation = reg_value;
+ strcpy(version, HV_DRV_VERSION);
- hvutil_transport_send(hvt, kvp_msg, sizeof(*kvp_msg),
- kvp_register_done);
- kfree(kvp_msg);
- }
+ ret = hvutil_transport_send(hvt, kvp_msg, sizeof(*kvp_msg),
+ kvp_register_done);
+ kfree(kvp_msg);
+ return ret;
}
static void kvp_timeout_func(struct work_struct *dummy)
@@ -186,9 +188,8 @@ static int kvp_handle_handshake(struct hv_kvp_msg *msg)
*/
pr_debug("KVP: userspace daemon ver. %d connected\n",
msg->kvp_hdr.operation);
- kvp_register(dm_reg_value);
- return 0;
+ return kvp_register(dm_reg_value);
}
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index c54d759b0738..da5c42201680 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2029,8 +2029,8 @@ static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx)
return AE_NO_MEMORY;
/* If this range overlaps the virtual TPM, truncate it. */
- if (end > VTPM_BASE_ADDRESS && start < VTPM_BASE_ADDRESS)
- end = VTPM_BASE_ADDRESS;
+ if (end >= VTPM_BASE_ADDRESS && start < VTPM_BASE_ADDRESS)
+ end = VTPM_BASE_ADDRESS - 1;
new_res->name = "hyperv mmio";
new_res->flags = IORESOURCE_MEM;
@@ -2097,12 +2097,31 @@ static void vmbus_mmio_remove(void)
static void __maybe_unused vmbus_reserve_fb(void)
{
resource_size_t start = 0, size;
+ resource_size_t low_mmio_base;
struct pci_dev *pdev;
if (efi_enabled(EFI_BOOT)) {
/* Gen2 VM: get FB base from EFI framebuffer */
start = screen_info.lfb_base;
size = max_t(__u32, screen_info.lfb_size, 0x800000);
+
+ low_mmio_base = hyperv_mmio->start;
+ if (!low_mmio_base || upper_32_bits(low_mmio_base) ||
+ (start && start < low_mmio_base)) {
+ pr_warn("Unexpected low mmio base %pa\n", &low_mmio_base);
+ } else {
+ /*
+ * If the kdump/kexec or CVM kernel's lfb_base
+ * is 0, fall back to the low mmio base.
+ */
+ if (!start)
+ start = low_mmio_base;
+ /*
+ * Reserve half of the space below 4GB for high
+ * resolutions, but cap the reservation to 128MB.
+ */
+ size = min((SZ_4G - start) / 2, SZ_128M);
+ }
} else {
/* Gen1 VM: get FB base from PCI */
pdev = pci_get_device(PCI_VENDOR_ID_MICROSOFT,
@@ -2122,8 +2141,10 @@ static void __maybe_unused vmbus_reserve_fb(void)
pci_dev_put(pdev);
}
- if (!start)
+ if (!start) {
+ pr_warn("Unexpected framebuffer mmio base of zero\n");
return;
+ }
/*
* Make a claim for the frame buffer in the resource tree under the
@@ -2133,6 +2154,8 @@ static void __maybe_unused vmbus_reserve_fb(void)
*/
for (; !fb_mmio && (size >= 0x100000); size >>= 1)
fb_mmio = __request_region(hyperv_mmio, start, size, fb_mmio_name, 0);
+
+ pr_info("hv_mmio=%pR,%pR fb=%pR\n", hyperv_mmio, hyperv_mmio->sibling, fb_mmio);
}
/**
diff --git a/drivers/i2c/i2c-stub.c b/drivers/i2c/i2c-stub.c
index d642cad219d9..3a2f472dd6b0 100644
--- a/drivers/i2c/i2c-stub.c
+++ b/drivers/i2c/i2c-stub.c
@@ -214,6 +214,11 @@ static s32 stub_xfer(struct i2c_adapter *adap, u16 addr, unsigned short flags,
* We ignore banks here, because banked chips don't use I2C
* block transfers
*/
+ if (data->block[0] == 0 ||
+ data->block[0] > I2C_SMBUS_BLOCK_MAX) {
+ ret = -EINVAL;
+ break;
+ }
if (data->block[0] > 256 - command) /* Avoid overrun */
data->block[0] = 256 - command;
len = data->block[0];
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 5a4644f7ad98..8f7e9a5285d0 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -4146,7 +4146,7 @@ int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata)
uctx->rdev = rdev;
- uctx->shpg = (void *)__get_free_page(GFP_KERNEL);
+ uctx->shpg = (void *)get_zeroed_page(GFP_KERNEL);
if (!uctx->shpg) {
rc = -ENOMEM;
goto fail;
diff --git a/drivers/irqchip/irq-imgpdc.c b/drivers/irqchip/irq-imgpdc.c
index 5831be454673..e5c5a7fd1552 100644
--- a/drivers/irqchip/irq-imgpdc.c
+++ b/drivers/irqchip/irq-imgpdc.c
@@ -378,6 +378,7 @@ static int pdc_intc_probe(struct platform_device *pdev)
dev_err(&pdev->dev, "cannot add IRQ domain\n");
return -ENOMEM;
}
+ priv->domain->flags |= IRQ_DOMAIN_FLAG_DESTROY_GC;
/*
* Set up 2 generic irq chips with 2 chip types.
@@ -465,6 +466,11 @@ static int pdc_intc_remove(struct platform_device *pdev)
{
struct pdc_intc_priv *priv = platform_get_drvdata(pdev);
+ for (unsigned int i = 0; i < priv->nr_perips; ++i)
+ irq_set_chained_handler_and_data(priv->perip_irqs[i], NULL, NULL);
+
+ irq_set_chained_handler_and_data(priv->syswake_irq, NULL, NULL);
+
irq_domain_remove(priv->domain);
return 0;
}
diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c
index 7dad97881fdb..00ae52dbc96e 100644
--- a/drivers/media/test-drivers/vidtv/vidtv_mux.c
+++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c
@@ -101,7 +101,8 @@ static int vidtv_mux_pid_ctx_init(struct vidtv_mux *m)
/* add a ctx for all PMT sections */
while (p) {
pid = vidtv_psi_get_pat_program_pid(p);
- vidtv_mux_create_pid_ctx_once(m, pid);
+ if (!vidtv_mux_create_pid_ctx_once(m, pid))
+ goto free;
p = p->next;
}
@@ -170,6 +171,9 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m)
nit_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_NIT_PID);
eit_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_EIT_PID);
+ if (!pat_ctx || !sdt_ctx || !nit_ctx || !eit_ctx)
+ return 0;
+
pat_args.offset = m->mux_buf_offset;
pat_args.continuity_counter = &pat_ctx->cc;
@@ -186,6 +190,8 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m)
}
pmt_ctx = vidtv_mux_get_pid_ctx(m, pmt_pid);
+ if (!pmt_ctx)
+ continue;
pmt_args.offset = m->mux_buf_offset;
pmt_args.pmt = m->si.pmt_secs[i];
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 5b69b9268c75..c15ffaadf8fd 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -210,8 +210,8 @@ static void rmnet_dellink(struct net_device *dev, struct list_head *head)
ep = rmnet_get_endpoint(real_port, mux_id);
if (ep) {
hlist_del_init_rcu(&ep->hlnode);
- rmnet_vnd_dellink(mux_id, real_port, ep);
- kfree(ep);
+ real_port->nr_rmnet_devs--;
+ kfree_rcu(ep, rcu);
}
netdev_upper_dev_unlink(real_dev, dev);
@@ -235,9 +235,9 @@ static void rmnet_force_unassociate_device(struct net_device *real_dev)
hash_for_each_safe(port->muxed_ep, bkt_ep, tmp_ep, ep, hlnode) {
unregister_netdevice_queue(ep->egress_dev, &list);
netdev_upper_dev_unlink(real_dev, ep->egress_dev);
- rmnet_vnd_dellink(ep->mux_id, port, ep);
hlist_del_init_rcu(&ep->hlnode);
- kfree(ep);
+ port->nr_rmnet_devs--;
+ kfree_rcu(ep, rcu);
}
rmnet_unregister_real_device(real_dev);
unregister_netdevice_many(&list);
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
index ed112d51ac5a..f50fae1c6bdd 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
@@ -18,6 +18,7 @@ struct rmnet_endpoint {
u8 mux_id;
struct net_device *egress_dev;
struct hlist_node hlnode;
+ struct rcu_head rcu;
};
struct rmnet_egress_agg_params {
diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c
index 37a3c989cba1..27b771146656 100644
--- a/drivers/net/wan/hdlc_ppp.c
+++ b/drivers/net/wan/hdlc_ppp.c
@@ -621,7 +621,6 @@ static void ppp_start(struct net_device *dev)
struct proto *proto = &ppp->protos[i];
proto->dev = dev;
- timer_setup(&proto->timer, ppp_timer, 0);
proto->state = CLOSED;
}
ppp->protos[IDX_LCP].pid = PID_LCP;
@@ -641,6 +640,15 @@ static void ppp_close(struct net_device *dev)
ppp_tx_flush();
}
+static void ppp_timer_release(struct net_device *dev)
+{
+ struct ppp *ppp = get_ppp(dev);
+ int i;
+
+ for (i = 0; i < IDX_COUNT; i++)
+ timer_shutdown_sync(&ppp->protos[i].timer);
+}
+
static struct hdlc_proto proto = {
.start = ppp_start,
.stop = ppp_stop,
@@ -649,6 +657,7 @@ static struct hdlc_proto proto = {
.ioctl = ppp_ioctl,
.netif_rx = ppp_rx,
.module = THIS_MODULE,
+ .detach = ppp_timer_release,
};
static const struct header_ops ppp_header_ops = {
@@ -659,7 +668,7 @@ static int ppp_ioctl(struct net_device *dev, struct if_settings *ifs)
{
hdlc_device *hdlc = dev_to_hdlc(dev);
struct ppp *ppp;
- int result;
+ int i, result;
switch (ifs->type) {
case IF_GET_PROTO:
@@ -687,6 +696,8 @@ static int ppp_ioctl(struct net_device *dev, struct if_settings *ifs)
return result;
ppp = get_ppp(dev);
+ for (i = 0; i < IDX_COUNT; i++)
+ timer_setup(&ppp->protos[i].timer, ppp_timer, 0);
spin_lock_init(&ppp->lock);
ppp->req_timeout = 2;
ppp->cr_retries = 10;
diff --git a/drivers/net/wireless/ath/ath11k/dp.c b/drivers/net/wireless/ath/ath11k/dp.c
index be0beb6bae8f..15fb15f58042 100644
--- a/drivers/net/wireless/ath/ath11k/dp.c
+++ b/drivers/net/wireless/ath/ath11k/dp.c
@@ -1039,6 +1039,7 @@ void ath11k_dp_free(struct ath11k_base *ab)
idr_destroy(&dp->tx_ring[i].txbuf_idr);
spin_unlock_bh(&dp->tx_ring[i].tx_idr_lock);
kfree(dp->tx_ring[i].tx_status);
+ dp->tx_ring[i].tx_status = NULL;
}
/* Deinit any SOC level resource */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c b/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c
index e89259de6f4c..273a6718c907 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c
@@ -316,11 +316,11 @@ void iwl_mvm_ptp_remove(struct iwl_mvm *mvm)
mvm->ptp_data.ptp_clock_info.name,
ptp_clock_index(mvm->ptp_data.ptp_clock));
+ cancel_delayed_work_sync(&mvm->ptp_data.dwork);
ptp_clock_unregister(mvm->ptp_data.ptp_clock);
mvm->ptp_data.ptp_clock = NULL;
memset(&mvm->ptp_data.ptp_clock_info, 0,
sizeof(mvm->ptp_data.ptp_clock_info));
mvm->ptp_data.last_gp2 = 0;
- cancel_delayed_work_sync(&mvm->ptp_data.dwork);
}
}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
index 00248e2b21ea..02723a43ea15 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
@@ -16,6 +16,7 @@ static const struct usb_device_id mt76x2u_device_table[] = {
{ USB_DEVICE(0x0e8d, 0x7612) }, /* Aukey USBAC1200 - Alfa AWUS036ACM */
{ USB_DEVICE(0x057c, 0x8503) }, /* Avm FRITZ!WLAN AC860 */
{ USB_DEVICE(0x7392, 0xb711) }, /* Edimax EW 7722 UAC */
+ { USB_DEVICE(0x056e, 0x400a) }, /* ELECOM WDC-867SU3S */
{ USB_DEVICE(0x0e8d, 0x7632) }, /* HC-M7662BU1 */
{ USB_DEVICE(0x0471, 0x2126) }, /* LiteOn WN4516R module, nonstandard USB connector */
{ USB_DEVICE(0x0471, 0x7600) }, /* LiteOn WN4519R module, nonstandard USB connector */
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h
index a9ed6fd41089..e7dd888ee692 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h
@@ -291,7 +291,7 @@ static inline int get_rx_desc_paggr(__le32 *__pdesc)
static inline int get_rx_status_desc_rpt_sel(__le32 *__pdesc)
{
- return le32_get_bits(*(__pdesc + 1), BIT(28));
+ return le32_get_bits(*(__pdesc + 2), BIT(28));
}
static inline int get_rx_desc_rxmcs(__le32 *__pdesc)
diff --git a/drivers/net/wireless/realtek/rtw88/tx.c b/drivers/net/wireless/realtek/rtw88/tx.c
index f63900b6621d..2122ff5ab50a 100644
--- a/drivers/net/wireless/realtek/rtw88/tx.c
+++ b/drivers/net/wireless/realtek/rtw88/tx.c
@@ -190,6 +190,7 @@ void rtw_tx_report_purge_timer(struct timer_list *t)
void rtw_tx_report_enqueue(struct rtw_dev *rtwdev, struct sk_buff *skb, u8 sn)
{
struct rtw_tx_report *tx_report = &rtwdev->tx_report;
+ unsigned long timeout = RTW_TX_PROBE_TIMEOUT;
unsigned long flags;
u8 *drv_data;
@@ -201,7 +202,11 @@ void rtw_tx_report_enqueue(struct rtw_dev *rtwdev, struct sk_buff *skb, u8 sn)
__skb_queue_tail(&tx_report->queue, skb);
spin_unlock_irqrestore(&tx_report->q_lock, flags);
- mod_timer(&tx_report->purge_timer, jiffies + RTW_TX_PROBE_TIMEOUT);
+ if (rtwdev->chip->id == RTW_CHIP_TYPE_8723D &&
+ rtwdev->hci.type == RTW_HCI_TYPE_USB)
+ timeout = msecs_to_jiffies(2500);
+
+ mod_timer(&tx_report->purge_timer, jiffies + timeout);
}
EXPORT_SYMBOL(rtw_tx_report_enqueue);
diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index 64d9183a4209..c64bc4091b40 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -339,6 +339,7 @@ static bool rtw_usb_tx_agg_skb(struct rtw_usb *rtwusb, struct sk_buff_head *list
int agg_num = 0;
unsigned int align_next = 0;
u8 qsel;
+ int ret;
if (skb_queue_empty(list))
return false;
@@ -394,7 +395,13 @@ static bool rtw_usb_tx_agg_skb(struct rtw_usb *rtwusb, struct sk_buff_head *list
tx_desc = (struct rtw_tx_desc *)skb_head->data;
qsel = le32_get_bits(tx_desc->w1, RTW_TX_DESC_W1_QSEL);
- rtw_usb_write_port(rtwdev, qsel, skb_head, rtw_usb_write_port_tx_complete, txcb);
+ ret = rtw_usb_write_port(rtwdev, qsel, skb_head,
+ rtw_usb_write_port_tx_complete, txcb);
+ if (ret) {
+ ieee80211_purge_tx_queue(rtwdev->hw, &txcb->tx_ack_queue);
+ kfree(txcb);
+ return false;
+ }
return true;
}
@@ -458,8 +465,10 @@ static int rtw_usb_write_data(struct rtw_dev *rtwdev,
ret = rtw_usb_write_port(rtwdev, qsel, skb,
rtw_usb_write_port_complete, skb);
- if (unlikely(ret))
+ if (unlikely(ret)) {
rtw_err(rtwdev, "failed to do USB write, ret=%d\n", ret);
+ dev_kfree_skb_any(skb);
+ }
return ret;
}
diff --git a/drivers/ntb/hw/epf/ntb_hw_epf.c b/drivers/ntb/hw/epf/ntb_hw_epf.c
index 5e79cfce8649..17bf7c8a1a55 100644
--- a/drivers/ntb/hw/epf/ntb_hw_epf.c
+++ b/drivers/ntb/hw/epf/ntb_hw_epf.c
@@ -646,7 +646,8 @@ static void ntb_epf_deinit_pci(struct ntb_epf_dev *ndev)
struct pci_dev *pdev = ndev->ntb.pdev;
pci_iounmap(pdev, ndev->ctrl_reg);
- pci_iounmap(pdev, ndev->peer_spad_reg);
+ if (ndev->barno_map[BAR_PEER_SPAD] != ndev->barno_map[BAR_CONFIG])
+ pci_iounmap(pdev, ndev->peer_spad_reg);
pci_iounmap(pdev, ndev->db_reg);
pci_release_regions(pdev);
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 5f85c4a812ab..4174fef03eac 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -380,6 +380,19 @@ static int nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd)
static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue)
{
+ /*
+ * Keep rcv_state at RECV_ERR even for the internal -ESHUTDOWN path.
+ * nvmet_tcp_handle_icreq() can return -ESHUTDOWN after the ICReq has
+ * already been consumed and queue teardown has started.
+ *
+ * If nvmet_tcp_data_ready() or nvmet_tcp_write_space() queues
+ * nvmet_tcp_io_work() again before nvmet_tcp_release_queue_work()
+ * cancels it, the queue must not keep that old receive state.
+ * Otherwise the next nvmet_tcp_io_work() run can reach
+ * nvmet_tcp_done_recv_pdu() and try to handle the same ICReq again.
+ *
+ * That is why queue->rcv_state needs to be updated before we return.
+ */
queue->rcv_state = NVMET_TCP_RECV_ERR;
if (queue->nvme_sq.ctrl)
nvmet_ctrl_fatal_error(queue->nvme_sq.ctrl);
@@ -935,10 +948,24 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue)
iov.iov_base = icresp;
iov.iov_len = sizeof(*icresp);
ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);
- if (ret < 0)
+ if (ret < 0) {
+ spin_lock_bh(&queue->state_lock);
+ if (queue->state == NVMET_TCP_Q_DISCONNECTING) {
+ spin_unlock_bh(&queue->state_lock);
+ return -ESHUTDOWN;
+ }
+ spin_unlock_bh(&queue->state_lock);
return ret; /* queue removal will cleanup */
+ }
+ spin_lock_bh(&queue->state_lock);
+ if (queue->state == NVMET_TCP_Q_DISCONNECTING) {
+ spin_unlock_bh(&queue->state_lock);
+ /* Tell nvmet_tcp_socket_error() teardown is in progress. */
+ return -ESHUTDOWN;
+ }
queue->state = NVMET_TCP_Q_LIVE;
+ spin_unlock_bh(&queue->state_lock);
nvmet_prepare_receive_pdu(queue);
return 0;
}
diff --git a/drivers/power/reset/linkstation-poweroff.c b/drivers/power/reset/linkstation-poweroff.c
index 02f5fdb8ffc4..e56d75bfcc43 100644
--- a/drivers/power/reset/linkstation-poweroff.c
+++ b/drivers/power/reset/linkstation-poweroff.c
@@ -163,10 +163,10 @@ static int __init linkstation_poweroff_init(void)
dn = of_find_matching_node(NULL, ls_poweroff_of_match);
if (!dn)
return -ENODEV;
- of_node_put(dn);
match = of_match_node(ls_poweroff_of_match, dn);
cfg = match->data;
+ of_node_put(dn);
dn = of_find_node_by_name(NULL, cfg->mdio_node_name);
if (!dn)
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index a1a26743430c..0eadf6dc30e2 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -2176,8 +2176,16 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
if (rdev->use_count) {
ret = regulator_enable(rdev->supply);
if (ret < 0) {
- _regulator_put(rdev->supply);
+ struct regulator *supply;
+
+ regulator_lock_two(rdev, rdev->supply->rdev, &ww_ctx);
+
+ supply = rdev->supply;
rdev->supply = NULL;
+
+ regulator_unlock_two(rdev, supply->rdev, &ww_ctx);
+
+ regulator_put(supply);
goto out;
}
}
diff --git a/drivers/rpmsg/rpmsg_char.c b/drivers/rpmsg/rpmsg_char.c
index 09833ad05da7..7aaf7d352904 100644
--- a/drivers/rpmsg/rpmsg_char.c
+++ b/drivers/rpmsg/rpmsg_char.c
@@ -104,6 +104,9 @@ static int rpmsg_ept_cb(struct rpmsg_device *rpdev, void *buf, int len,
struct rpmsg_eptdev *eptdev = priv;
struct sk_buff *skb;
+ if (!eptdev)
+ return 0;
+
skb = alloc_skb(len, GFP_ATOMIC);
if (!skb)
return -ENOMEM;
@@ -124,6 +127,9 @@ static int rpmsg_ept_flow_cb(struct rpmsg_device *rpdev, void *priv, bool enable
{
struct rpmsg_eptdev *eptdev = priv;
+ if (!eptdev)
+ return 0;
+
eptdev->remote_flow_restricted = enable;
eptdev->remote_flow_updated = true;
@@ -490,6 +496,7 @@ static int rpmsg_chrdev_probe(struct rpmsg_device *rpdev)
struct rpmsg_channel_info chinfo;
struct rpmsg_eptdev *eptdev;
struct device *dev = &rpdev->dev;
+ int ret;
memcpy(chinfo.name, rpdev->id.name, RPMSG_NAME_SIZE);
chinfo.src = rpdev->src;
@@ -502,13 +509,17 @@ static int rpmsg_chrdev_probe(struct rpmsg_device *rpdev)
/* Set the default_ept to the rpmsg device endpoint */
eptdev->default_ept = rpdev->ept;
+ ret = rpmsg_chrdev_eptdev_add(eptdev, chinfo);
+
+ if (ret)
+ return ret;
/*
* The rpmsg_ept_cb uses *priv parameter to get its rpmsg_eptdev context.
- * Storedit in default_ept *priv field.
+ * Stored it in default_ept *priv field.
*/
eptdev->default_ept->priv = eptdev;
- return rpmsg_chrdev_eptdev_add(eptdev, chinfo);
+ return 0;
}
static void rpmsg_chrdev_remove(struct rpmsg_device *rpdev)
diff --git a/drivers/slimbus/qcom-ngd-ctrl.c b/drivers/slimbus/qcom-ngd-ctrl.c
index 2fe3077fa7af..de1834d52cb8 100644
--- a/drivers/slimbus/qcom-ngd-ctrl.c
+++ b/drivers/slimbus/qcom-ngd-ctrl.c
@@ -1561,6 +1561,13 @@ static int of_qcom_slim_ngd_register(struct device *parent,
return -ENODEV;
}
+static void qcom_slim_ngd_unregister(struct qcom_slim_ngd_ctrl *ctrl)
+{
+ struct qcom_slim_ngd *ngd = ctrl->ngd;
+
+ platform_device_del(ngd->pdev);
+}
+
static int qcom_slim_ngd_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
@@ -1578,6 +1585,8 @@ static int qcom_slim_ngd_probe(struct platform_device *pdev)
ret = qcom_slim_ngd_qmi_svc_event_init(ctrl);
if (ret) {
dev_err(&pdev->dev, "QMI service registration failed:%d", ret);
+ pm_runtime_dont_use_autosuspend(dev);
+ pm_runtime_disable(dev);
return ret;
}
@@ -1663,7 +1672,6 @@ static int qcom_slim_ngd_ctrl_probe(struct platform_device *pdev)
goto err_pdr_lookup;
}
- platform_driver_register(&qcom_slim_ngd_driver);
return of_qcom_slim_ngd_register(dev, ctrl);
err_pdr_alloc:
@@ -1677,7 +1685,9 @@ static int qcom_slim_ngd_ctrl_probe(struct platform_device *pdev)
static int qcom_slim_ngd_ctrl_remove(struct platform_device *pdev)
{
- platform_driver_unregister(&qcom_slim_ngd_driver);
+ struct qcom_slim_ngd_ctrl *ctrl = platform_get_drvdata(pdev);
+
+ qcom_slim_ngd_unregister(ctrl);
return 0;
}
@@ -1686,6 +1696,7 @@ static int qcom_slim_ngd_remove(struct platform_device *pdev)
{
struct qcom_slim_ngd_ctrl *ctrl = platform_get_drvdata(pdev);
+ pm_runtime_dont_use_autosuspend(&pdev->dev);
pm_runtime_disable(&pdev->dev);
pdr_handle_release(ctrl->pdr);
qcom_unregister_ssr_notifier(ctrl->notifier, &ctrl->nb);
@@ -1756,6 +1767,28 @@ static struct platform_driver qcom_slim_ngd_driver = {
},
};
-module_platform_driver(qcom_slim_ngd_ctrl_driver);
+static int qcom_slim_ngd_init(void)
+{
+ int ret;
+
+ ret = platform_driver_register(&qcom_slim_ngd_driver);
+ if (ret)
+ return ret;
+
+ ret = platform_driver_register(&qcom_slim_ngd_ctrl_driver);
+ if (ret)
+ platform_driver_unregister(&qcom_slim_ngd_driver);
+
+ return ret;
+}
+
+static void qcom_slim_ngd_exit(void)
+{
+ platform_driver_unregister(&qcom_slim_ngd_ctrl_driver);
+ platform_driver_unregister(&qcom_slim_ngd_driver);
+}
+
+module_init(qcom_slim_ngd_init);
+module_exit(qcom_slim_ngd_exit);
MODULE_LICENSE("GPL v2");
MODULE_DESCRIPTION("Qualcomm SLIMBus NGD controller");
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index 60a05bfecde3..d1cf00cd945d 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -688,8 +688,10 @@ static int dw8250_probe(struct platform_device *pdev)
*/
if (data->clk) {
err = clk_notifier_register(data->clk, &data->clk_notifier);
- if (err)
+ if (err) {
+ serial8250_unregister_port(data->data.line);
return dev_err_probe(dev, err, "Failed to set the clock notifier\n");
+ }
queue_work(system_unbound_wq, &data->clk_work);
}
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 5083eaddd635..ab5b4c6c29de 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -838,12 +838,9 @@ static void qcom_geni_serial_handle_rx_dma(struct uart_port *uport, bool drop)
port->rx_dma_addr = 0;
rx_in = readl(uport->membase + SE_DMA_RX_LEN_IN);
- if (!rx_in) {
- dev_warn(uport->dev, "serial engine reports 0 RX bytes in!\n");
- return;
- }
-
- if (!drop)
+ if (!rx_in)
+ dev_warn_ratelimited(uport->dev, "serial engine reports 0 RX bytes in!\n");
+ else if (!drop)
handle_rx_uart(uport, rx_in, drop);
ret = geni_se_rx_dma_prep(&port->se, port->rx_buf,
diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c
index 829c4be66f3b..5c417b6426bb 100644
--- a/drivers/tty/vt/vc_screen.c
+++ b/drivers/tty/vt/vc_screen.c
@@ -699,7 +699,7 @@ vcs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
}
*ppos += written;
ret = written;
- if (written)
+ if (written && vc)
vcs_scr_updated(vc);
unlock_out:
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index 34b8e93f89a4..d4e41c6116ff 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -1190,6 +1190,18 @@ int fb_new_modelist(struct fb_info *info)
if (list_empty(&info->modelist))
return 1;
+ /*
+ * The new modelist may not contain the current mode (info->var), and
+ * fbcon_new_modelist() below only re-points consoles mapped to this
+ * framebuffer. Add the current mode here so info->var keeps a match
+ * even when fbcon is unbound.
+ */
+ if (!fb_match_mode(&info->var, &info->modelist)) {
+ fb_var_to_videomode(&mode, &info->var);
+ if (fb_add_videomode(&mode, &info->modelist))
+ return 1;
+ }
+
fbcon_new_modelist(info);
return 0;
diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c
index 1b3c9958ef5c..10c3cfb959f4 100644
--- a/drivers/video/fbdev/core/fbsysfs.c
+++ b/drivers/video/fbdev/core/fbsysfs.c
@@ -11,6 +11,7 @@
#include <linux/major.h>
#include "fb_internal.h"
+#include "fbcon.h"
#define FB_SYSFS_FLAG_ATTR 1
@@ -113,8 +114,15 @@ static ssize_t store_modes(struct device *device,
if (fb_new_modelist(fb_info)) {
fb_destroy_modelist(&fb_info->modelist);
list_splice(&old_list, &fb_info->modelist);
- } else
+ } else {
+ /*
+ * fb_display[i].mode and fb_info->mode both point into the old
+ * list. Clear them before it is freed.
+ */
+ fbcon_delete_modelist(&old_list);
+ fb_info->mode = NULL;
fb_destroy_modelist(&old_list);
+ }
unlock_fb_info(fb_info);
console_unlock();
diff --git a/drivers/video/fbdev/core/modedb.c b/drivers/video/fbdev/core/modedb.c
index 7196b055f2bd..7428d58e6ca8 100644
--- a/drivers/video/fbdev/core/modedb.c
+++ b/drivers/video/fbdev/core/modedb.c
@@ -258,7 +258,7 @@ static const struct fb_videomode modedb[] = {
FB_VMODE_DOUBLE },
/* 1920x1080 @ 60 Hz, 67.3 kHz hsync */
- { NULL, 60, 1920, 1080, 6734, 148, 88, 36, 4, 44, 5, 0,
+ { NULL, 60, 1920, 1080, 6734, 148, 88, 36, 4, 44, 5,
FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
FB_VMODE_NONINTERLACED },
@@ -625,7 +625,7 @@ int fb_find_mode(struct fb_var_screeninfo *var,
const struct fb_videomode *default_mode,
unsigned int default_bpp)
{
- char *mode_option_buf = NULL;
+ char *mode_option_buf __free(kfree) = NULL;
int i;
/* Set up defaults */
@@ -723,7 +723,6 @@ int fb_find_mode(struct fb_var_screeninfo *var,
res_specified = 1;
}
done:
- kfree(mode_option_buf);
if (cvt) {
struct fb_videomode cvt_mode;
int ret;
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 0b17657690d4..e793c6ef55e4 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -631,7 +631,7 @@ static int new_lockspace(const char *name, const char *cluster,
lockspace to start running (via sysfs) in dlm_ls_start(). */
error = do_uevent(ls, 1);
- if (error)
+ if (error < 0)
goto out_recoverd;
/* wait until recovery is successful or failed */
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 8a556560a5b2..0e09bddea16a 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -716,36 +716,47 @@ static void ep_free(struct eventpoll *ep)
}
/*
- * Removes a "struct epitem" from the eventpoll RB tree and deallocates
- * all the associated resources. Must be called with "mtx" held.
- * If the dying flag is set, do the removal only if force is true.
- * This prevents ep_clear_and_put() from dropping all the ep references
- * while running concurrently with eventpoll_release_file().
- * Returns true if the eventpoll can be disposed.
+ * The ffd.file pointer may be in the process of being torn down due to
+ * being closed, but we may not have finished eventpoll_release() yet.
+ *
+ * Normally, even with the atomic_long_inc_not_zero, the file may have
+ * been free'd and then gotten re-allocated to something else (since
+ * files are not RCU-delayed, they are SLAB_TYPESAFE_BY_RCU).
+ *
+ * But for epoll, users hold the ep->mtx mutex, and as such any file in
+ * the process of being free'd will block in eventpoll_release_file()
+ * and thus the underlying file allocation will not be free'd, and the
+ * file re-use cannot happen.
+ *
+ * For the same reason we can avoid a rcu_read_lock() around the
+ * operation - 'ffd.file' cannot go away even if the refcount has
+ * reached zero (but we must still not call out to ->poll() functions
+ * etc).
*/
-static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
+static struct file *epi_fget(const struct epitem *epi)
{
- struct file *file = epi->ffd.file;
- struct epitems_head *to_free;
- struct hlist_head *head;
+ struct file *file;
- lockdep_assert_irqs_enabled();
+ file = epi->ffd.file;
+ if (!atomic_long_inc_not_zero(&file->f_count))
+ file = NULL;
+ return file;
+}
- /*
- * Removes poll wait queue hooks.
- */
- ep_unregister_pollwait(ep, epi);
+/*
+ * Called with &file->f_lock held,
+ * returns with it released
+ */
+static void ep_remove_file(struct eventpoll *ep, struct epitem *epi,
+ struct file *file)
+{
+ struct epitems_head *to_free = NULL;
+ struct hlist_head *head = file->f_ep;
- /* Remove the current item from the list of epoll hooks */
- spin_lock(&file->f_lock);
- if (epi->dying && !force) {
- spin_unlock(&file->f_lock);
- return false;
- }
+ lockdep_assert_held(&ep->mtx);
+ lockdep_assert_held(&file->f_lock);
- to_free = NULL;
- head = file->f_ep;
- if (head->first == &epi->fllink && !epi->fllink.next) {
+ if (hlist_is_singular_node(&epi->fllink, head)) {
/* See eventpoll_release() for details. */
WRITE_ONCE(file->f_ep, NULL);
if (!is_file_epoll(file)) {
@@ -758,6 +769,11 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
hlist_del_rcu(&epi->fllink);
spin_unlock(&file->f_lock);
free_ephead(to_free);
+}
+
+static bool ep_remove_epi(struct eventpoll *ep, struct epitem *epi)
+{
+ lockdep_assert_held(&ep->mtx);
rb_erase_cached(&epi->rbn, &ep->rbr);
@@ -783,9 +799,31 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
/*
* ep_remove variant for callers owing an additional reference to the ep
*/
-static void ep_remove_safe(struct eventpoll *ep, struct epitem *epi)
+static void ep_remove(struct eventpoll *ep, struct epitem *epi)
{
- if (__ep_remove(ep, epi, false))
+ struct file *file __free(fput) = NULL;
+
+ lockdep_assert_irqs_enabled();
+ lockdep_assert_held(&ep->mtx);
+
+ ep_unregister_pollwait(ep, epi);
+
+ /* cheap sync with eventpoll_release_file() */
+ if (unlikely(READ_ONCE(epi->dying)))
+ return;
+
+ /*
+ * If we manage to grab a reference it means we're not in
+ * eventpoll_release_file() and aren't going to be.
+ */
+ file = epi_fget(epi);
+ if (!file)
+ return;
+
+ spin_lock(&file->f_lock);
+ ep_remove_file(ep, epi, file);
+
+ if (ep_remove_epi(ep, epi))
WARN_ON_ONCE(ep_refcount_dec_and_test(ep));
}
@@ -812,7 +850,7 @@ static void ep_clear_and_put(struct eventpoll *ep)
/*
* Walks through the whole tree and try to free each "struct epitem".
- * Note that ep_remove_safe() will not remove the epitem in case of a
+ * Note that ep_remove() will not remove the epitem in case of a
* racing eventpoll_release_file(); the latter will do the removal.
* At this point we are sure no poll callbacks will be lingering around.
* Since we still own a reference to the eventpoll struct, the loop can't
@@ -821,7 +859,7 @@ static void ep_clear_and_put(struct eventpoll *ep)
for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = next) {
next = rb_next(rbp);
epi = rb_entry(rbp, struct epitem, rbn);
- ep_remove_safe(ep, epi);
+ ep_remove(ep, epi);
cond_resched();
}
@@ -880,34 +918,6 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int dep
return res;
}
-/*
- * The ffd.file pointer may be in the process of being torn down due to
- * being closed, but we may not have finished eventpoll_release() yet.
- *
- * Normally, even with the atomic_long_inc_not_zero, the file may have
- * been free'd and then gotten re-allocated to something else (since
- * files are not RCU-delayed, they are SLAB_TYPESAFE_BY_RCU).
- *
- * But for epoll, users hold the ep->mtx mutex, and as such any file in
- * the process of being free'd will block in eventpoll_release_file()
- * and thus the underlying file allocation will not be free'd, and the
- * file re-use cannot happen.
- *
- * For the same reason we can avoid a rcu_read_lock() around the
- * operation - 'ffd.file' cannot go away even if the refcount has
- * reached zero (but we must still not call out to ->poll() functions
- * etc).
- */
-static struct file *epi_fget(const struct epitem *epi)
-{
- struct file *file;
-
- file = epi->ffd.file;
- if (!atomic_long_inc_not_zero(&file->f_count))
- file = NULL;
- return file;
-}
-
/*
* Differs from ep_eventpoll_poll() in that internal callers already have
* the ep->mtx so we need to start from depth=1, such that mutex_lock_nested()
@@ -994,7 +1004,7 @@ void eventpoll_release_file(struct file *file)
spin_lock(&file->f_lock);
if (file->f_ep && file->f_ep->first) {
epi = hlist_entry(file->f_ep->first, struct epitem, fllink);
- epi->dying = true;
+ WRITE_ONCE(epi->dying, true);
spin_unlock(&file->f_lock);
/*
@@ -1003,7 +1013,13 @@ void eventpoll_release_file(struct file *file)
*/
ep = epi->ep;
mutex_lock(&ep->mtx);
- dispose = __ep_remove(ep, epi, true);
+
+ ep_unregister_pollwait(ep, epi);
+
+ spin_lock(&file->f_lock);
+ ep_remove_file(ep, epi, file);
+ dispose = ep_remove_epi(ep, epi);
+
mutex_unlock(&ep->mtx);
if (dispose && ep_refcount_dec_and_test(ep))
@@ -1485,21 +1501,21 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
mutex_unlock(&tep->mtx);
/*
- * ep_remove_safe() calls in the later error paths can't lead to
+ * ep_remove() calls in the later error paths can't lead to
* ep_free() as the ep file itself still holds an ep reference.
*/
ep_get(ep);
/* now check if we've created too many backpaths */
if (unlikely(full_check && reverse_path_check())) {
- ep_remove_safe(ep, epi);
+ ep_remove(ep, epi);
return -EINVAL;
}
if (epi->event.events & EPOLLWAKEUP) {
error = ep_create_wakeup_source(epi);
if (error) {
- ep_remove_safe(ep, epi);
+ ep_remove(ep, epi);
return error;
}
}
@@ -1523,7 +1539,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
* high memory pressure.
*/
if (unlikely(!epq.epi)) {
- ep_remove_safe(ep, epi);
+ ep_remove(ep, epi);
return -ENOMEM;
}
@@ -2215,7 +2231,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
* The eventpoll itself is still alive: the refcount
* can't go to zero here.
*/
- ep_remove_safe(ep, epi);
+ ep_remove(ep, epi);
error = 0;
} else {
error = -ENOENT;
diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c
index 6139a57fde70..99625a2ad33b 100644
--- a/fs/exfat/dir.c
+++ b/fs/exfat/dir.c
@@ -1079,12 +1079,12 @@ int exfat_find_dir_entry(struct super_block *sb, struct exfat_inode_info *ei,
continue;
}
- brelse(bh);
if (entry_type == TYPE_EXTEND) {
unsigned short entry_uniname[16], unichar;
if (step != DIRENT_STEP_NAME ||
name_len >= MAX_NAME_LENGTH) {
+ brelse(bh);
step = DIRENT_STEP_FILE;
continue;
}
@@ -1095,6 +1095,7 @@ int exfat_find_dir_entry(struct super_block *sb, struct exfat_inode_info *ei,
uniname += EXFAT_FILE_NAME_LEN;
len = exfat_extract_uni_name(ep, entry_uniname);
+ brelse(bh);
name_len += len;
unichar = *(uniname+len);
@@ -1113,6 +1114,7 @@ int exfat_find_dir_entry(struct super_block *sb, struct exfat_inode_info *ei,
continue;
}
+ brelse(bh);
if (entry_type &
(TYPE_CRITICAL_SEC | TYPE_BENIGN_SEC)) {
if (step == DIRENT_STEP_SECD) {
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index ec2aeccb69a3..0aa926d8a6ef 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -46,6 +46,7 @@ static inline int f2fs_acl_count(size_t size)
static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
{
int i, count;
+ int err = -EINVAL;
struct posix_acl *acl;
struct f2fs_acl_header *hdr = (struct f2fs_acl_header *)value;
struct f2fs_acl_entry *entry = (struct f2fs_acl_entry *)(hdr + 1);
@@ -69,8 +70,11 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
for (i = 0; i < count; i++) {
- if ((char *)entry > end)
+ if (unlikely((char *)entry +
+ sizeof(struct f2fs_acl_entry_short) > end)) {
+ err = -EFSCORRUPTED;
goto fail;
+ }
acl->a_entries[i].e_tag = le16_to_cpu(entry->e_tag);
acl->a_entries[i].e_perm = le16_to_cpu(entry->e_perm);
@@ -85,6 +89,11 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
break;
case ACL_USER:
+ if (unlikely((char *)entry +
+ sizeof(struct f2fs_acl_entry) > end)) {
+ err = -EFSCORRUPTED;
+ goto fail;
+ }
acl->a_entries[i].e_uid =
make_kuid(&init_user_ns,
le32_to_cpu(entry->e_id));
@@ -92,6 +101,11 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
sizeof(struct f2fs_acl_entry));
break;
case ACL_GROUP:
+ if (unlikely((char *)entry +
+ sizeof(struct f2fs_acl_entry) > end)) {
+ err = -EFSCORRUPTED;
+ goto fail;
+ }
acl->a_entries[i].e_gid =
make_kgid(&init_user_ns,
le32_to_cpu(entry->e_id));
@@ -107,7 +121,7 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
return acl;
fail:
posix_acl_release(acl);
- return ERR_PTR(-EINVAL);
+ return ERR_PTR(err);
}
static void *f2fs_acl_to_disk(struct f2fs_sb_info *sbi,
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 7643c1d7dbb2..435791876561 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -3527,6 +3527,7 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
pgoff_t index = page->index;
int err = 0;
block_t ori_blk_addr = NULL_ADDR;
+ bool cow_has_reserved_block = false;
/* If pos is beyond the end of file, reserve a new block in COW inode */
if ((pos & PAGE_MASK) >= i_size_read(inode))
@@ -3536,9 +3537,11 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
err = __find_data_block(cow_inode, index, blk_addr);
if (err) {
return err;
- } else if (*blk_addr != NULL_ADDR) {
+ } else if (__is_valid_data_blkaddr(*blk_addr)) {
*use_cow = true;
return 0;
+ } else if (*blk_addr == NEW_ADDR) {
+ cow_has_reserved_block = true;
}
if (is_inode_flag_set(inode, FI_ATOMIC_REPLACE))
@@ -3551,10 +3554,13 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
reserve_block:
/* Finally, we should reserve a new block in COW inode for the update */
- err = __reserve_data_block(cow_inode, index, blk_addr, node_changed);
- if (err)
- return err;
- inc_atomic_write_cnt(inode);
+ if (!cow_has_reserved_block) {
+ err = __reserve_data_block(cow_inode, index, blk_addr,
+ node_changed);
+ if (err)
+ return err;
+ inc_atomic_write_cnt(inode);
+ }
if (ori_blk_addr != NULL_ADDR)
*blk_addr = ori_blk_addr;
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 09fd0cbd8f77..96f34d06df25 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -87,10 +87,9 @@ static bool __may_extent_tree(struct inode *inode, enum extent_type type)
if (!__init_may_extent_tree(inode, type))
return false;
- if (is_inode_flag_set(inode, FI_NO_EXTENT))
- return false;
-
if (type == EX_READ) {
+ if (is_inode_flag_set(inode, FI_NO_EXTENT))
+ return false;
if (is_inode_flag_set(inode, FI_COMPRESSED_FILE) &&
!f2fs_sb_has_readonly(F2FS_I_SB(inode)))
return false;
@@ -603,14 +602,10 @@ static unsigned int __destroy_extent_node(struct inode *inode,
while (atomic_read(&et->node_cnt)) {
write_lock(&et->lock);
- if (!is_inode_flag_set(inode, FI_NO_EXTENT))
- set_inode_flag(inode, FI_NO_EXTENT);
node_cnt += __free_extent_tree(sbi, et, nr_shrink);
write_unlock(&et->lock);
}
- f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
-
return node_cnt;
}
@@ -640,12 +635,12 @@ static void __update_extent_tree_range(struct inode *inode,
write_lock(&et->lock);
- if (is_inode_flag_set(inode, FI_NO_EXTENT)) {
- write_unlock(&et->lock);
- return;
- }
-
if (type == EX_READ) {
+ if (is_inode_flag_set(inode, FI_NO_EXTENT)) {
+ write_unlock(&et->lock);
+ return;
+ }
+
prev = et->largest;
dei.len = 0;
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 61914cc712c8..d321a42f97c8 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1826,8 +1826,15 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset,
if (f2fs_is_pinned_file(inode)) {
block_t sec_blks = CAP_BLKS_PER_SEC(sbi);
- block_t sec_len = roundup(map.m_len, sec_blks);
+ block_t sec_len;
+ if (map.m_lblk % sec_blks) {
+ map.m_lblk = rounddown(map.m_lblk, sec_blks);
+ map.m_len = pg_end - map.m_lblk;
+ if (off_end)
+ map.m_len++;
+ }
+ sec_len = roundup(map.m_len, sec_blks);
map.m_len = sec_blks;
next_alloc:
if (has_not_enough_free_secs(sbi, 0,
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index db80b6cad325..3546bdb04d15 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -544,8 +544,13 @@ static int do_read_inode(struct inode *inode)
static bool is_meta_ino(struct f2fs_sb_info *sbi, unsigned int ino)
{
- return ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi) ||
- ino == F2FS_COMPRESS_INO(sbi);
+ if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi))
+ return true;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ if (test_opt(sbi, COMPRESS_CACHE) && ino == F2FS_COMPRESS_INO(sbi))
+ return true;
+#endif
+ return false;
}
struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
diff --git a/fs/file_table.c b/fs/file_table.c
index 234284ef72a9..fa4d4c54f790 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -48,12 +48,12 @@ static struct percpu_counter nr_files __cacheline_aligned_in_smp;
struct backing_file {
struct file file;
struct path real_path;
+#ifdef CONFIG_SECURITY
+ void *security;
+#endif
};
-static inline struct backing_file *backing_file(struct file *f)
-{
- return container_of(f, struct backing_file, file);
-}
+#define backing_file(f) container_of(f, struct backing_file, file)
struct path *backing_file_real_path(struct file *f)
{
@@ -72,11 +72,29 @@ static void file_free_rcu(struct rcu_head *head)
kmem_cache_free(filp_cachep, f);
}
+#ifdef CONFIG_SECURITY
+void *backing_file_security(const struct file *f)
+{
+ return backing_file(f)->security;
+}
+
+void backing_file_set_security(struct file *f, void *security)
+{
+ backing_file(f)->security = security;
+}
+#endif /* CONFIG_SECURITY */
+
+static inline void backing_file_free(struct backing_file *ff)
+{
+ security_backing_file_free(&ff->file);
+ path_put(&ff->real_path);
+}
+
static inline void file_free(struct file *f)
{
security_file_free(f);
if (unlikely(f->f_mode & FMODE_BACKING))
- path_put(backing_file_real_path(f));
+ backing_file_free(backing_file(f));
if (likely(!(f->f_mode & FMODE_NOACCOUNT)))
percpu_counter_dec(&nr_files);
call_rcu(&f->f_rcuhead, file_free_rcu);
@@ -252,6 +270,14 @@ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
return f;
}
+static int init_backing_file(struct backing_file *ff,
+ const struct file *user_file)
+{
+ memset(&ff->real_path, 0, sizeof(ff->real_path));
+ backing_file_set_security(&ff->file, NULL);
+ return security_backing_file_alloc(&ff->file, user_file);
+}
+
/*
* Variant of alloc_empty_file() that allocates a backing_file container
* and doesn't check and modify nr_files.
@@ -259,7 +285,8 @@ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
* This is only for kernel internal use, and the allocate file must not be
* installed into file tables or such.
*/
-struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
+struct file *alloc_empty_backing_file(int flags, const struct cred *cred,
+ const struct file *user_file)
{
struct backing_file *ff;
int error;
@@ -274,7 +301,14 @@ struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
return ERR_PTR(error);
}
+ /* The f_mode flags must be set before fput(). */
ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT;
+ error = init_backing_file(ff, user_file);
+ if (unlikely(error)) {
+ fput(&ff->file);
+ return ERR_PTR(error);
+ }
+
return &ff->file;
}
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 29a6c3a5829d..b15ecd74a1bd 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -843,6 +843,10 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
if (WARN_ON(folio_test_mlocked(oldfolio)))
goto out_fallback_unlock;
+ err = lock_request(cs->req);
+ if (err)
+ goto out_fallback_unlock;
+
replace_page_cache_folio(oldfolio, newfolio);
folio_get(newfolio);
@@ -856,20 +860,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
*/
pipe_buf_release(cs->pipe, buf);
- err = 0;
- spin_lock(&cs->req->waitq.lock);
- if (test_bit(FR_ABORTED, &cs->req->flags))
- err = -ENOENT;
- else
- *pagep = &newfolio->page;
- spin_unlock(&cs->req->waitq.lock);
-
- if (err) {
- folio_unlock(newfolio);
- folio_put(newfolio);
- goto out_put_old;
- }
-
+ *pagep = &newfolio->page;
folio_unlock(oldfolio);
/* Drop ref for ap->pages[] array */
folio_put(oldfolio);
@@ -1722,6 +1713,10 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
page = find_get_page(mapping, index);
if (!page)
break;
+ if (!PageUptodate(page)) {
+ put_page(page);
+ break;
+ }
this_num = min_t(unsigned, num, PAGE_SIZE - offset);
ap->pages[ap->num_pages] = page;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 722b885831b1..7e2519844fc9 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -357,8 +357,14 @@ void fuse_file_release(struct inode *inode, struct fuse_file *ff,
* aio and closes the fd before the aio completes. Since aio takes its
* own ref to the file, the IO completion has to drop the ref, which is
* how the fuse server can end up closing its clients' files.
+ *
+ * Exception is virtio-fs, which is not affected by the above (server is
+ * on host, cannot close open files in guest). Virtio-fs needs sync
+ * release, because the num_waiting mechanism to wait for all requests
+ * before commencing with fs shutdown doesn't work if submounts are
+ * used.
*/
- fuse_file_put(ff, false);
+ fuse_file_put(ff, ff->fm->fc->auto_submounts);
}
void fuse_release_common(struct file *file, bool isdir)
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index d43cac46e1dd..ee370c586014 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -652,6 +652,7 @@ static void gfs2_put_super(struct super_block *sb)
gfs2_delete_debugfs_file(sdp);
gfs2_sys_fs_del(sdp);
+ rcu_barrier();
free_sbd(sdp);
}
diff --git a/fs/internal.h b/fs/internal.h
index d64ae03998cc..576026e1ce3a 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -93,7 +93,8 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
*/
struct file *alloc_empty_file(int flags, const struct cred *cred);
struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred);
-struct file *alloc_empty_backing_file(int flags, const struct cred *cred);
+struct file *alloc_empty_backing_file(int flags, const struct cred *cred,
+ const struct file *user_file);
static inline void put_file_access(struct file *file)
{
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index de4922ce4ac7..4350388d40cd 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1046,6 +1046,7 @@ struct nfs_server *nfs_alloc_server(void)
server->io_stats = nfs_alloc_iostats();
if (!server->io_stats) {
+ ida_free(&s_sysfs_ids, server->s_sysfs_id);
kfree(server);
return NULL;
}
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 315383941abd..90bd2afe23da 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -2094,11 +2094,11 @@ pnfs_update_layout(struct inode *ino,
dprintk("%s wait for layoutreturn\n", __func__);
lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo));
if (!IS_ERR(lseg)) {
- pnfs_put_layout_hdr(lo);
dprintk("%s retrying\n", __func__);
trace_pnfs_update_layout(ino, pos, count, iomode, lo,
lseg,
PNFS_UPDATE_LAYOUT_RETRY);
+ pnfs_put_layout_hdr(lo);
goto lookup_again;
}
trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 5314dabb725d..698d4d64c6b6 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -1102,14 +1102,14 @@ nfs4_decode_mp_ds_addr(struct net *net, struct xdr_stream *xdr, gfp_t gfp_flags)
/* r_netid */
nlen = xdr_stream_decode_string_dup(xdr, &netid, XDR_MAX_NETOBJ,
gfp_flags);
- if (unlikely(nlen < 0))
+ if (unlikely(nlen <= 0))
goto out_err;
/* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */
/* port is ".ABC.DEF", 8 chars max */
rlen = xdr_stream_decode_string_dup(xdr, &buf, INET6_ADDRSTRLEN +
IPV6_SCOPE_ID_LEN + 8, gfp_flags);
- if (unlikely(rlen < 0))
+ if (unlikely(rlen <= 0))
goto out_free_netid;
/* replace port '.' with '-' */
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index f1f32ad4f42c..bdcfab9e3a32 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -131,10 +131,7 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp)
resp->status = fh_getattr(fh, &resp->stat);
out:
- /* argp->acl_{access,default} may have been allocated in
- nfssvc_decode_setaclargs. */
- posix_acl_release(argp->acl_access);
- posix_acl_release(argp->acl_default);
+ /* argp->acl_{access,default} are released in nfsaclsvc_release_setacl. */
return rpc_success;
out_drop_lock:
@@ -312,6 +309,16 @@ static void nfsaclsvc_release_access(struct svc_rqst *rqstp)
struct nfsd3_voidargs { int dummy; };
+static void nfsaclsvc_release_setacl(struct svc_rqst *rqstp)
+{
+ struct nfsd3_setaclargs *argp = rqstp->rq_argp;
+ struct nfsd_attrstat *resp = rqstp->rq_resp;
+
+ fh_put(&resp->fh);
+ posix_acl_release(argp->acl_access);
+ posix_acl_release(argp->acl_default);
+}
+
#define ST 1 /* status*/
#define AT 21 /* attributes */
#define pAT (1+AT) /* post attributes - conditional */
@@ -345,7 +352,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = {
.pc_func = nfsacld_proc_setacl,
.pc_decode = nfsaclsvc_decode_setaclargs,
.pc_encode = nfssvc_encode_attrstatres,
- .pc_release = nfssvc_release_attrstat,
+ .pc_release = nfsaclsvc_release_setacl,
.pc_argsize = sizeof(struct nfsd3_setaclargs),
.pc_argzero = sizeof(struct nfsd3_setaclargs),
.pc_ressize = sizeof(struct nfsd_attrstat),
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index d7af28f44504..4e9c0f2ef796 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -118,10 +118,7 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp)
out_errno:
resp->status = nfserrno(error);
out:
- /* argp->acl_{access,default} may have been allocated in
- nfs3svc_decode_setaclargs. */
- posix_acl_release(argp->acl_access);
- posix_acl_release(argp->acl_default);
+ /* argp->acl_{access,default} are released in nfs3svc_release_setacl. */
return rpc_success;
}
@@ -225,6 +222,16 @@ static void nfs3svc_release_getacl(struct svc_rqst *rqstp)
struct nfsd3_voidargs { int dummy; };
+static void nfs3svc_release_setacl(struct svc_rqst *rqstp)
+{
+ struct nfsd3_setaclargs *argp = rqstp->rq_argp;
+ struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
+ fh_put(&resp->fh);
+ posix_acl_release(argp->acl_access);
+ posix_acl_release(argp->acl_default);
+}
+
#define ST 1 /* status*/
#define AT 21 /* attributes */
#define pAT (1+AT) /* post attributes - conditional */
@@ -258,7 +265,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = {
.pc_func = nfsd3_proc_setacl,
.pc_decode = nfs3svc_decode_setaclargs,
.pc_encode = nfs3svc_encode_setaclres,
- .pc_release = nfs3svc_release_fhandle,
+ .pc_release = nfs3svc_release_setacl,
.pc_argsize = sizeof(struct nfsd3_setaclargs),
.pc_argzero = sizeof(struct nfsd3_setaclargs),
.pc_ressize = sizeof(struct nfsd3_attrstat),
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 892fecce18b8..017044c27d38 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -815,7 +815,8 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg,
if (IS_ERR(name.data))
return PTR_ERR(name.data);
name.len = namelen;
- get_user(princhashlen, &ci->cc_princhash.cp_len);
+ if (get_user(princhashlen, &ci->cc_princhash.cp_len))
+ return -EFAULT;
if (princhashlen > 0) {
princhash.data = memdup_user(
&ci->cc_princhash.cp_data,
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 03a4a8de1114..e3b128cc2413 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1821,10 +1821,11 @@ static __be32 nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp,
union nfsd4_op_u *u)
{
struct nfsd4_secinfo_no_name *sin = &u->secinfo_no_name;
+
+ sin->sin_exp = NULL;
if (xdr_stream_decode_u32(argp->xdr, &sin->sin_style) < 0)
return nfserr_bad_xdr;
- sin->sin_exp = NULL;
return nfs_ok;
}
diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
index a03b4bce5fbf..1eace7c1b5bd 100644
--- a/fs/ntfs3/xattr.c
+++ b/fs/ntfs3/xattr.c
@@ -828,6 +828,12 @@ static int ntfs_getxattr(const struct xattr_handler *handler, struct dentry *de,
return err;
}
+static bool ntfs_is_reserved_lxattr(const char *name)
+{
+ return !strcmp(name, "$LXUID") || !strcmp(name, "$LXGID") ||
+ !strcmp(name, "$LXMOD") || !strcmp(name, "$LXDEV");
+}
+
/*
* ntfs_setxattr - inode_operations::setxattr
*/
@@ -932,6 +938,12 @@ static noinline int ntfs_setxattr(const struct xattr_handler *handler,
goto out;
}
+ /* Do not allow non privileged users to change $LXUID/$LXGID... */
+ if (ntfs_is_reserved_lxattr(name) && !capable(CAP_SYS_ADMIN)) {
+ err = -EPERM;
+ goto out;
+ }
+
/* Deal with NTFS extended attribute. */
err = ntfs_set_ea(inode, name, strlen(name), value, size, flags, 0,
NULL);
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 1adf206ba538..8104ba761b9b 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -201,8 +201,16 @@ static int ocfs2_validate_gd_parent(struct super_block *sb,
int resize)
{
unsigned int max_bits;
+ unsigned int max_bitmap_bits;
+ unsigned int max_bitmap_size;
+ int suballocator;
struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data;
+ suballocator = le64_to_cpu(di->i_blkno) != OCFS2_SB(sb)->bitmap_blkno;
+ max_bitmap_size = ocfs2_group_bitmap_size(sb, suballocator,
+ OCFS2_SB(sb)->s_feature_incompat);
+ max_bitmap_bits = max_bitmap_size * 8;
+
if (di->i_blkno != gd->bg_parent_dinode) {
do_error("Group descriptor #%llu has bad parent pointer (%llu, expected %llu)\n",
(unsigned long long)bh->b_blocknr,
@@ -210,6 +218,20 @@ static int ocfs2_validate_gd_parent(struct super_block *sb,
(unsigned long long)le64_to_cpu(di->i_blkno));
}
+ if (le16_to_cpu(gd->bg_size) > max_bitmap_size) {
+ do_error("Group descriptor #%llu has bitmap size %u but physical max of %u\n",
+ (unsigned long long)bh->b_blocknr,
+ le16_to_cpu(gd->bg_size),
+ max_bitmap_size);
+ }
+
+ if (le16_to_cpu(gd->bg_bits) > max_bitmap_bits) {
+ do_error("Group descriptor #%llu has bit count %u but physical max of %u\n",
+ (unsigned long long)bh->b_blocknr,
+ le16_to_cpu(gd->bg_bits),
+ max_bitmap_bits);
+ }
+
max_bits = le16_to_cpu(di->id2.i_chain.cl_cpg) * le16_to_cpu(di->id2.i_chain.cl_bpc);
if (le16_to_cpu(gd->bg_bits) > max_bits) {
do_error("Group descriptor #%llu has bit count of %u\n",
diff --git a/fs/open.c b/fs/open.c
index b5ea1dcbfb22..5b164481d80b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1175,18 +1175,19 @@ EXPORT_SYMBOL_GPL(kernel_file_open);
* the backing inode on the underlying filesystem, which can be
* retrieved using backing_file_real_path().
*/
-struct file *backing_file_open(const struct path *path, int flags,
+struct file *backing_file_open(const struct file *user_file, int flags,
const struct path *real_path,
const struct cred *cred)
{
+ const struct path *user_path = &user_file->f_path;
struct file *f;
int error;
- f = alloc_empty_backing_file(flags, cred);
+ f = alloc_empty_backing_file(flags, cred, user_file);
if (IS_ERR(f))
return f;
- f->f_path = *path;
+ f->f_path = *user_path;
path_get(real_path);
*backing_file_real_path(f) = *real_path;
error = do_dentry_open(f, d_inode(real_path->dentry), NULL);
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 8be4dc050d1e..07f00cf91977 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -60,7 +60,7 @@ static struct file *ovl_open_realfile(const struct file *file,
if (!inode_owner_or_capable(real_idmap, realinode))
flags &= ~O_NOATIME;
- realfile = backing_file_open(&file->f_path, flags, realpath,
+ realfile = backing_file_open(file, flags, realpath,
current_cred());
}
revert_creds(old_cred);
@@ -527,6 +527,7 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
{
+ struct file *user_file = vma->vm_file;
struct file *realfile = file->private_data;
const struct cred *old_cred;
int ret;
@@ -540,6 +541,11 @@ static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
vma_set_file(vma, realfile);
old_cred = ovl_override_creds(file_inode(file)->i_sb);
+ ret = security_mmap_backing_file(vma, realfile, user_file);
+ if (ret) {
+ revert_creds(old_cred);
+ return ret;
+ }
ret = call_mmap(vma->vm_file, vma);
revert_creds(old_cred);
ovl_file_accessed(file);
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 18901411e7f9..04fa2c9bba80 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -606,6 +606,11 @@ int smb2_check_user_session(struct ksmbd_work *work)
sess_id, work->sess->id);
return -EINVAL;
}
+ if (work->sess->state != SMB2_SESSION_VALID) {
+ pr_err("compound request on a non-valid session (state %d)\n",
+ work->sess->state);
+ return -EINVAL;
+ }
return 1;
}
diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c
index f04692e1400b..cd6c72fa1960 100644
--- a/fs/smb/server/smbacl.c
+++ b/fs/smb/server/smbacl.c
@@ -1419,7 +1419,9 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path,
break;
aces_size -= ace_size;
- if (ace->sid.num_subauth > SID_MAX_SUB_AUTHORITIES)
+ if (ace->sid.num_subauth > SID_MAX_SUB_AUTHORITIES ||
+ ace_size < offsetof(struct smb_ace, sid) + CIFS_SID_BASE_SIZE +
+ sizeof(__le32) * ace->sid.num_subauth)
break;
if (!compare_sids(&sid, &ace->sid) ||
diff --git a/include/keys/request_key_auth-type.h b/include/keys/request_key_auth-type.h
index 36b89a933310..01e42ee5f409 100644
--- a/include/keys/request_key_auth-type.h
+++ b/include/keys/request_key_auth-type.h
@@ -9,12 +9,14 @@
#define _KEYS_REQUEST_KEY_AUTH_TYPE_H
#include <linux/key.h>
+#include <linux/refcount.h>
/*
* Authorisation record for request_key().
*/
struct request_key_auth {
struct rcu_head rcu;
+ refcount_t usage;
struct key *target_key;
struct key *dest_keyring;
const struct cred *cred;
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index dba211d3bb9a..9a3b93c24f19 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -345,6 +345,10 @@ struct bpf_jmp_history_entry {
u32 prev_idx : 22;
/* special flags, e.g., whether insn is doing register stack spill/load */
u32 flags : 10;
+ /* additional registers that need precision tracking when this
+ * jump is backtracked, vector of six 10-bit records
+ */
+ u64 linked_regs;
};
/* Maximum number of register states that can exist at once */
diff --git a/include/linux/err.h b/include/linux/err.h
index b5d9bb2a2349..1eb63d69ca80 100644
--- a/include/linux/err.h
+++ b/include/linux/err.h
@@ -36,7 +36,7 @@
*
* Return: A pointer with @error encoded within its value.
*/
-static inline void * __must_check ERR_PTR(long error)
+static __always_inline void * __must_check ERR_PTR(long error)
{
return (void *) error;
}
@@ -46,7 +46,7 @@ static inline void * __must_check ERR_PTR(long error)
* @ptr: An error pointer.
* Return: The error code within @ptr.
*/
-static inline long __must_check PTR_ERR(__force const void *ptr)
+static __always_inline long __must_check PTR_ERR(__force const void *ptr)
{
return (long) ptr;
}
@@ -56,7 +56,7 @@ static inline long __must_check PTR_ERR(__force const void *ptr)
* @ptr: The pointer to check.
* Return: true if @ptr is an error pointer, false otherwise.
*/
-static inline bool __must_check IS_ERR(__force const void *ptr)
+static __always_inline bool __must_check IS_ERR(__force const void *ptr)
{
return IS_ERR_VALUE((unsigned long)ptr);
}
@@ -67,7 +67,7 @@ static inline bool __must_check IS_ERR(__force const void *ptr)
*
* Like IS_ERR(), but also returns true for a null pointer.
*/
-static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr)
+static __always_inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr)
{
return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr);
}
@@ -79,7 +79,7 @@ static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr)
* Explicitly cast an error-valued pointer to another pointer type in such a
* way as to make it clear that's what's going on.
*/
-static inline void * __must_check ERR_CAST(__force const void *ptr)
+static __always_inline void * __must_check ERR_CAST(__force const void *ptr)
{
/* cast away the const */
return (void *) ptr;
@@ -102,7 +102,7 @@ static inline void * __must_check ERR_CAST(__force const void *ptr)
*
* Return: The error code within @ptr if it is an error pointer; 0 otherwise.
*/
-static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr)
+static __always_inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr)
{
if (IS_ERR(ptr))
return PTR_ERR(ptr);
diff --git a/include/linux/file.h b/include/linux/file.h
index 6e9099d29343..221ba0888107 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -11,6 +11,7 @@
#include <linux/posix_types.h>
#include <linux/errno.h>
#include <linux/cleanup.h>
+#include <linux/err.h>
struct file;
@@ -93,6 +94,7 @@ extern void put_unused_fd(unsigned int fd);
DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T),
get_unused_fd_flags(flags), unsigned flags)
+DEFINE_FREE(fput, struct file *, if (!IS_ERR_OR_NULL(_T)) fput(_T))
extern void fd_install(unsigned int fd, struct file *file);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4cdeeaedaa40..5a897ee50f29 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2515,11 +2515,24 @@ struct file *dentry_open(const struct path *path, int flags,
const struct cred *creds);
struct file *dentry_create(const struct path *path, int flags, umode_t mode,
const struct cred *cred);
-struct file *backing_file_open(const struct path *path, int flags,
+struct file *backing_file_open(const struct file *user_file, int flags,
const struct path *real_path,
const struct cred *cred);
struct path *backing_file_real_path(struct file *f);
+#ifdef CONFIG_SECURITY
+void *backing_file_security(const struct file *f);
+void backing_file_set_security(struct file *f, void *security);
+#else
+static inline void *backing_file_security(const struct file *f)
+{
+ return NULL;
+}
+static inline void backing_file_set_security(struct file *f, void *security)
+{
+}
+#endif /* CONFIG_SECURITY */
+
/*
* file_real_path - get the path corresponding to f_inode
*
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ab09b08967bb..57c7b4009f57 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1650,6 +1650,11 @@ int kvm_request_irq_source_id(struct kvm *kvm);
void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
+static inline bool is_gfn_in_memslot(const struct kvm_memory_slot *slot, gfn_t gfn)
+{
+ return gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages;
+}
+
/*
* Returns a pointer to the memslot if it contains gfn.
* Otherwise returns NULL.
@@ -1660,7 +1665,7 @@ try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
if (!slot)
return NULL;
- if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages)
+ if (is_gfn_in_memslot(slot, gfn))
return slot;
else
return NULL;
diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h
index 97a8b21eb033..c0a2839253fa 100644
--- a/include/linux/lsm_audit.h
+++ b/include/linux/lsm_audit.h
@@ -93,7 +93,7 @@ struct common_audit_data {
#endif
char *kmod_name;
struct lsm_ioctlop_audit *op;
- struct file *file;
+ const struct file *file;
struct lsm_ibpkey_audit *ibpkey;
struct lsm_ibendport_audit *ibendport;
int reason;
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 2923754c13bc..567d7f16609c 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -169,6 +169,9 @@ LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir,
LSM_HOOK(int, 0, file_permission, struct file *file, int mask)
LSM_HOOK(int, 0, file_alloc_security, struct file *file)
LSM_HOOK(void, LSM_RET_VOID, file_free_security, struct file *file)
+LSM_HOOK(int, 0, backing_file_alloc, struct file *backing_file,
+ const struct file *user_file)
+LSM_HOOK(void, LSM_RET_VOID, backing_file_free, struct file *backing_file)
LSM_HOOK(int, 0, file_ioctl, struct file *file, unsigned int cmd,
unsigned long arg)
LSM_HOOK(int, 0, file_ioctl_compat, struct file *file, unsigned int cmd,
@@ -176,6 +179,8 @@ LSM_HOOK(int, 0, file_ioctl_compat, struct file *file, unsigned int cmd,
LSM_HOOK(int, 0, mmap_addr, unsigned long addr)
LSM_HOOK(int, 0, mmap_file, struct file *file, unsigned long reqprot,
unsigned long prot, unsigned long flags)
+LSM_HOOK(int, 0, mmap_backing_file, struct vm_area_struct *vma,
+ struct file *backing_file, struct file *user_file)
LSM_HOOK(int, 0, file_mprotect, struct vm_area_struct *vma,
unsigned long reqprot, unsigned long prot)
LSM_HOOK(int, 0, file_lock, struct file *file, unsigned int cmd)
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index dcb5e5b5eb13..3b56b60195ce 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -59,6 +59,7 @@ struct security_hook_list {
struct lsm_blob_sizes {
int lbs_cred;
int lbs_file;
+ int lbs_backing_file;
int lbs_inode;
int lbs_superblock;
int lbs_ipc;
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index ded528d23f85..382fbaa701f9 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -129,9 +129,7 @@ ring_buffer_consume(struct trace_buffer *buffer, int cpu, u64 *ts,
unsigned long *lost_events);
struct ring_buffer_iter *
-ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags);
-void ring_buffer_read_prepare_sync(void);
-void ring_buffer_read_start(struct ring_buffer_iter *iter);
+ring_buffer_read_start(struct trace_buffer *buffer, int cpu, gfp_t flags);
void ring_buffer_read_finish(struct ring_buffer_iter *iter);
struct ring_buffer_event *
diff --git a/include/linux/security.h b/include/linux/security.h
index 937840870d86..4866ffdb4e6c 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -389,11 +389,17 @@ int security_kernfs_init_security(struct kernfs_node *kn_dir,
int security_file_permission(struct file *file, int mask);
int security_file_alloc(struct file *file);
void security_file_free(struct file *file);
+int security_backing_file_alloc(struct file *backing_file,
+ const struct file *user_file);
+void security_backing_file_free(struct file *backing_file);
int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
int security_file_ioctl_compat(struct file *file, unsigned int cmd,
unsigned long arg);
int security_mmap_file(struct file *file, unsigned long prot,
unsigned long flags);
+int security_mmap_backing_file(struct vm_area_struct *vma,
+ struct file *backing_file,
+ struct file *user_file);
int security_mmap_addr(unsigned long addr);
int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
unsigned long prot);
@@ -984,6 +990,15 @@ static inline int security_file_alloc(struct file *file)
static inline void security_file_free(struct file *file)
{ }
+static inline int security_backing_file_alloc(struct file *backing_file,
+ const struct file *user_file)
+{
+ return 0;
+}
+
+static inline void security_backing_file_free(struct file *backing_file)
+{ }
+
static inline int security_file_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
@@ -1003,6 +1018,13 @@ static inline int security_mmap_file(struct file *file, unsigned long prot,
return 0;
}
+static inline int security_mmap_backing_file(struct vm_area_struct *vma,
+ struct file *backing_file,
+ struct file *user_file)
+{
+ return 0;
+}
+
static inline int security_mmap_addr(unsigned long addr)
{
return cap_mmap_addr(addr);
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index e923f1c24ce4..ed95128d29c6 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -4,6 +4,7 @@
#ifndef _LINUX_SKMSG_H
#define _LINUX_SKMSG_H
+#include <linux/bitops.h>
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/scatterlist.h>
@@ -190,11 +191,14 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src,
int which, u32 size)
{
dst->sg.data[which] = src->sg.data[which];
+ __assign_bit(which, dst->sg.copy, test_bit(which, src->sg.copy));
dst->sg.data[which].length = size;
dst->sg.size += size;
src->sg.size -= size;
src->sg.data[which].length -= size;
src->sg.data[which].offset += size;
+ if (!src->sg.data[which].length)
+ __clear_bit(which, src->sg.copy);
}
static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src)
@@ -264,16 +268,19 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page,
static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state)
{
do {
- if (copy_state)
- __set_bit(i, msg->sg.copy);
- else
- __clear_bit(i, msg->sg.copy);
+ __assign_bit(i, msg->sg.copy, copy_state);
sk_msg_iter_var_next(i);
if (i == msg->sg.end)
break;
} while (1);
}
+static inline void sk_msg_sg_copy_assign(struct sk_msg *dst, u32 dst_i,
+ const struct sk_msg *src, u32 src_i)
+{
+ __assign_bit(dst_i, dst->sg.copy, test_bit(src_i, src->sg.copy));
+}
+
static inline void sk_msg_sg_copy_set(struct sk_msg *msg, u32 start)
{
sk_msg_sg_copy(msg, start, true);
diff --git a/include/net/phonet/pn_dev.h b/include/net/phonet/pn_dev.h
index e9dc8dca5817..6b2102b4ece3 100644
--- a/include/net/phonet/pn_dev.h
+++ b/include/net/phonet/pn_dev.h
@@ -38,7 +38,7 @@ int phonet_address_add(struct net_device *dev, u8 addr);
int phonet_address_del(struct net_device *dev, u8 addr);
u8 phonet_address_get(struct net_device *dev, u8 addr);
int phonet_address_lookup(struct net *net, u8 addr);
-void phonet_address_notify(int event, struct net_device *dev, u8 addr);
+void phonet_address_notify(struct net *net, int event, u32 ifindex, u8 addr);
int phonet_route_add(struct net_device *dev, u8 daddr);
int phonet_route_del(struct net_device *dev, u8 daddr);
diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h
index 83fe39931781..a26d4cd3b8d6 100644
--- a/include/net/tc_act/tc_pedit.h
+++ b/include/net/tc_act/tc_pedit.h
@@ -14,7 +14,6 @@ struct tcf_pedit_key_ex {
struct tcf_pedit_parms {
struct tc_pedit_key *tcfp_keys;
struct tcf_pedit_key_ex *tcfp_keys_ex;
- u32 tcfp_off_max_hint;
unsigned char tcfp_nkeys;
unsigned char tcfp_flags;
struct rcu_head rcu;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 684fb450ad08..3aadbf81d8b1 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1776,7 +1776,7 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
kfree(ctx.cur_val);
if (ret == 1 && ctx.new_updated) {
- kfree(*buf);
+ kvfree(*buf);
*buf = ctx.new_val;
*pcount = ctx.new_len;
} else {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0d90236d0ad9..f638b2d3a42f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3461,9 +3461,87 @@ static bool is_jmp_point(struct bpf_verifier_env *env, int insn_idx)
return env->insn_aux_data[insn_idx].jmp_point;
}
+#define LR_FRAMENO_BITS 3
+#define LR_SPI_BITS 6
+#define LR_ENTRY_BITS (LR_SPI_BITS + LR_FRAMENO_BITS + 1)
+#define LR_SIZE_BITS 4
+#define LR_FRAMENO_MASK ((1ull << LR_FRAMENO_BITS) - 1)
+#define LR_SPI_MASK ((1ull << LR_SPI_BITS) - 1)
+#define LR_SIZE_MASK ((1ull << LR_SIZE_BITS) - 1)
+#define LR_SPI_OFF LR_FRAMENO_BITS
+#define LR_IS_REG_OFF (LR_SPI_BITS + LR_FRAMENO_BITS)
+#define LINKED_REGS_MAX 6
+
+struct linked_reg {
+ u8 frameno;
+ union {
+ u8 spi;
+ u8 regno;
+ };
+ bool is_reg;
+};
+
+struct linked_regs {
+ int cnt;
+ struct linked_reg entries[LINKED_REGS_MAX];
+};
+
+static struct linked_reg *linked_regs_push(struct linked_regs *s)
+{
+ if (s->cnt < LINKED_REGS_MAX)
+ return &s->entries[s->cnt++];
+
+ return NULL;
+}
+
+/* Use u64 as a vector of 6 10-bit values, use first 4-bits to track
+ * number of elements currently in stack.
+ * Pack one history entry for linked registers as 10 bits in the following format:
+ * - 3-bits frameno
+ * - 6-bits spi_or_reg
+ * - 1-bit is_reg
+ */
+static u64 linked_regs_pack(struct linked_regs *s)
+{
+ u64 val = 0;
+ int i;
+
+ for (i = 0; i < s->cnt; ++i) {
+ struct linked_reg *e = &s->entries[i];
+ u64 tmp = 0;
+
+ tmp |= e->frameno;
+ tmp |= e->spi << LR_SPI_OFF;
+ tmp |= (e->is_reg ? 1 : 0) << LR_IS_REG_OFF;
+
+ val <<= LR_ENTRY_BITS;
+ val |= tmp;
+ }
+ val <<= LR_SIZE_BITS;
+ val |= s->cnt;
+ return val;
+}
+
+static void linked_regs_unpack(u64 val, struct linked_regs *s)
+{
+ int i;
+
+ s->cnt = val & LR_SIZE_MASK;
+ val >>= LR_SIZE_BITS;
+
+ for (i = 0; i < s->cnt; ++i) {
+ struct linked_reg *e = &s->entries[i];
+
+ e->frameno = val & LR_FRAMENO_MASK;
+ e->spi = (val >> LR_SPI_OFF) & LR_SPI_MASK;
+ e->is_reg = (val >> LR_IS_REG_OFF) & 0x1;
+ val >>= LR_ENTRY_BITS;
+ }
+}
+
/* for any branch, call, exit record the history of jmps in the given state */
static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur,
- int insn_flags)
+ int insn_flags, u64 linked_regs)
{
u32 cnt = cur->jmp_history_cnt;
struct bpf_jmp_history_entry *p;
@@ -3479,6 +3557,10 @@ static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_st
"verifier insn history bug: insn_idx %d cur flags %x new flags %x\n",
env->insn_idx, env->cur_hist_ent->flags, insn_flags);
env->cur_hist_ent->flags |= insn_flags;
+ WARN_ONCE(env->cur_hist_ent->linked_regs != 0,
+ "verifier insn history bug: insn_idx %d linked_regs != 0: %#llx\n",
+ env->insn_idx, env->cur_hist_ent->linked_regs);
+ env->cur_hist_ent->linked_regs = linked_regs;
return 0;
}
@@ -3493,6 +3575,7 @@ static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_st
p->idx = env->insn_idx;
p->prev_idx = env->prev_insn_idx;
p->flags = insn_flags;
+ p->linked_regs = linked_regs;
cur->jmp_history_cnt = cnt;
env->cur_hist_ent = p;
@@ -3668,6 +3751,11 @@ static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg)
return bt->reg_masks[bt->frame] & (1 << reg);
}
+static inline bool bt_is_frame_reg_set(struct backtrack_state *bt, u32 frame, u32 reg)
+{
+ return bt->reg_masks[frame] & (1 << reg);
+}
+
static inline bool bt_is_frame_slot_set(struct backtrack_state *bt, u32 frame, u32 slot)
{
return bt->stack_masks[frame] & (1ull << slot);
@@ -3717,6 +3805,42 @@ static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask)
}
}
+/* If any register R in hist->linked_regs is marked as precise in bt,
+ * do bt_set_frame_{reg,slot}(bt, R) for all registers in hist->linked_regs.
+ */
+static void bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_jmp_history_entry *hist)
+{
+ struct linked_regs linked_regs;
+ bool some_precise = false;
+ int i;
+
+ if (!hist || hist->linked_regs == 0)
+ return;
+
+ linked_regs_unpack(hist->linked_regs, &linked_regs);
+ for (i = 0; i < linked_regs.cnt; ++i) {
+ struct linked_reg *e = &linked_regs.entries[i];
+
+ if ((e->is_reg && bt_is_frame_reg_set(bt, e->frameno, e->regno)) ||
+ (!e->is_reg && bt_is_frame_slot_set(bt, e->frameno, e->spi))) {
+ some_precise = true;
+ break;
+ }
+ }
+
+ if (!some_precise)
+ return;
+
+ for (i = 0; i < linked_regs.cnt; ++i) {
+ struct linked_reg *e = &linked_regs.entries[i];
+
+ if (e->is_reg)
+ bt_set_frame_reg(bt, e->frameno, e->regno);
+ else
+ bt_set_frame_slot(bt, e->frameno, e->spi);
+ }
+}
+
static bool calls_callback(struct bpf_verifier_env *env, int insn_idx);
/* For given verifier state backtrack_insn() is called from the last insn to
@@ -3756,6 +3880,12 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
}
+ /* If there is a history record that some registers gained range at this insn,
+ * propagate precision marks to those registers, so that bt_is_reg_set()
+ * accounts for these registers.
+ */
+ bt_sync_linked_regs(bt, hist);
+
if (class == BPF_ALU || class == BPF_ALU64) {
if (!bt_is_reg_set(bt, dreg))
return 0;
@@ -3985,7 +4115,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
*/
bt_set_reg(bt, dreg);
bt_set_reg(bt, sreg);
- /* else dreg <cond> K
+ } else if (BPF_SRC(insn->code) == BPF_K) {
+ /* dreg <cond> K
* Only dreg still needs precision before
* this insn, so for the K-based conditional
* there is nothing new to be marked.
@@ -4003,6 +4134,10 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
/* to be analyzed */
return -ENOTSUPP;
}
+ /* Propagate precision marks to linked registers, to account for
+ * registers marked as precise in this function.
+ */
+ bt_sync_linked_regs(bt, hist);
return 0;
}
@@ -4130,96 +4265,6 @@ static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_
}
}
-static bool idset_contains(struct bpf_idset *s, u32 id)
-{
- u32 i;
-
- for (i = 0; i < s->count; ++i)
- if (s->ids[i] == id)
- return true;
-
- return false;
-}
-
-static int idset_push(struct bpf_idset *s, u32 id)
-{
- if (WARN_ON_ONCE(s->count >= ARRAY_SIZE(s->ids)))
- return -EFAULT;
- s->ids[s->count++] = id;
- return 0;
-}
-
-static void idset_reset(struct bpf_idset *s)
-{
- s->count = 0;
-}
-
-/* Collect a set of IDs for all registers currently marked as precise in env->bt.
- * Mark all registers with these IDs as precise.
- */
-static int mark_precise_scalar_ids(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
-{
- struct bpf_idset *precise_ids = &env->idset_scratch;
- struct backtrack_state *bt = &env->bt;
- struct bpf_func_state *func;
- struct bpf_reg_state *reg;
- DECLARE_BITMAP(mask, 64);
- int i, fr;
-
- idset_reset(precise_ids);
-
- for (fr = bt->frame; fr >= 0; fr--) {
- func = st->frame[fr];
-
- bitmap_from_u64(mask, bt_frame_reg_mask(bt, fr));
- for_each_set_bit(i, mask, 32) {
- reg = &func->regs[i];
- if (!reg->id || reg->type != SCALAR_VALUE)
- continue;
- if (idset_push(precise_ids, reg->id))
- return -EFAULT;
- }
-
- bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr));
- for_each_set_bit(i, mask, 64) {
- if (i >= func->allocated_stack / BPF_REG_SIZE)
- break;
- if (!is_spilled_scalar_reg(&func->stack[i]))
- continue;
- reg = &func->stack[i].spilled_ptr;
- if (!reg->id)
- continue;
- if (idset_push(precise_ids, reg->id))
- return -EFAULT;
- }
- }
-
- for (fr = 0; fr <= st->curframe; ++fr) {
- func = st->frame[fr];
-
- for (i = BPF_REG_0; i < BPF_REG_10; ++i) {
- reg = &func->regs[i];
- if (!reg->id)
- continue;
- if (!idset_contains(precise_ids, reg->id))
- continue;
- bt_set_frame_reg(bt, fr, i);
- }
- for (i = 0; i < func->allocated_stack / BPF_REG_SIZE; ++i) {
- if (!is_spilled_scalar_reg(&func->stack[i]))
- continue;
- reg = &func->stack[i].spilled_ptr;
- if (!reg->id)
- continue;
- if (!idset_contains(precise_ids, reg->id))
- continue;
- bt_set_frame_slot(bt, fr, i);
- }
- }
-
- return 0;
-}
-
/*
* __mark_chain_precision() backtracks BPF program instruction sequence and
* chain of verifier states making sure that register *regno* (if regno >= 0)
@@ -4352,31 +4397,6 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
bt->frame, last_idx, first_idx, subseq_idx);
}
- /* If some register with scalar ID is marked as precise,
- * make sure that all registers sharing this ID are also precise.
- * This is needed to estimate effect of find_equal_scalars().
- * Do this at the last instruction of each state,
- * bpf_reg_state::id fields are valid for these instructions.
- *
- * Allows to track precision in situation like below:
- *
- * r2 = unknown value
- * ...
- * --- state #0 ---
- * ...
- * r1 = r2 // r1 and r2 now share the same ID
- * ...
- * --- state #1 {r1.id = A, r2.id = A} ---
- * ...
- * if (r2 > 10) goto exit; // find_equal_scalars() assigns range to r1
- * ...
- * --- state #2 {r1.id = A, r2.id = A} ---
- * r3 = r10
- * r3 += r1 // need to mark both r1 and r2
- */
- if (mark_precise_scalar_ids(env, st))
- return -EFAULT;
-
if (last_idx < 0) {
/* we are at the entry into subprog, which
* is expected for global funcs, but only if
@@ -4736,7 +4756,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
}
if (insn_flags)
- return push_jmp_history(env, env->cur_state, insn_flags);
+ return push_jmp_history(env, env->cur_state, insn_flags, 0);
return 0;
}
@@ -5032,7 +5052,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
insn_flags = 0; /* we are not restoring spilled register */
}
if (insn_flags)
- return push_jmp_history(env, env->cur_state, insn_flags);
+ return push_jmp_history(env, env->cur_state, insn_flags, 0);
return 0;
}
@@ -13540,7 +13560,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
ptr_reg = dst_reg;
else
/* Make sure ID is cleared otherwise dst_reg min/max could be
- * incorrectly propagated into other registers by find_equal_scalars()
+ * incorrectly propagated into other registers by sync_linked_regs()
*/
dst_reg->id = 0;
if (BPF_SRC(insn->code) == BPF_X) {
@@ -13700,7 +13720,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
*/
if (need_id)
/* Assign src and dst registers the same ID
- * that will be used by find_equal_scalars()
+ * that will be used by sync_linked_regs()
* to propagate min/max range.
*/
src_reg->id = ++env->id_gen;
@@ -13746,7 +13766,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
copy_register_state(dst_reg, src_reg);
/* Make sure ID is cleared if src_reg is not in u32
* range otherwise dst_reg min/max could be incorrectly
- * propagated into src_reg by find_equal_scalars()
+ * propagated into src_reg by sync_linked_regs()
*/
if (!is_src_reg_u32)
dst_reg->id = 0;
@@ -14564,19 +14584,75 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
return true;
}
-static void find_equal_scalars(struct bpf_verifier_state *vstate,
- struct bpf_reg_state *known_reg)
+static void __collect_linked_regs(struct linked_regs *reg_set, struct bpf_reg_state *reg,
+ u32 id, u32 frameno, u32 spi_or_reg, bool is_reg)
{
- struct bpf_func_state *state;
+ struct linked_reg *e;
+
+ if (reg->type != SCALAR_VALUE || reg->id != id)
+ return;
+
+ e = linked_regs_push(reg_set);
+ if (e) {
+ e->frameno = frameno;
+ e->is_reg = is_reg;
+ e->regno = spi_or_reg;
+ } else {
+ reg->id = 0;
+ }
+}
+
+/* For all R being scalar registers or spilled scalar registers
+ * in verifier state, save R in linked_regs if R->id == id.
+ * If there are too many Rs sharing same id, reset id for leftover Rs.
+ */
+static void collect_linked_regs(struct bpf_verifier_state *vstate, u32 id,
+ struct linked_regs *linked_regs)
+{
+ struct bpf_func_state *func;
struct bpf_reg_state *reg;
+ int i, j;
- bpf_for_each_reg_in_vstate(vstate, state, reg, ({
- if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) {
+ for (i = vstate->curframe; i >= 0; i--) {
+ func = vstate->frame[i];
+ for (j = 0; j < BPF_REG_FP; j++) {
+ reg = &func->regs[j];
+ __collect_linked_regs(linked_regs, reg, id, i, j, true);
+ }
+ for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) {
+ if (!is_spilled_reg(&func->stack[j]))
+ continue;
+ reg = &func->stack[j].spilled_ptr;
+ __collect_linked_regs(linked_regs, reg, id, i, j, false);
+ }
+ }
+}
+
+/* For all R in linked_regs, copy known_reg range into R
+ * if R->id == known_reg->id.
+ */
+static void sync_linked_regs(struct bpf_verifier_state *vstate, struct bpf_reg_state *known_reg,
+ struct linked_regs *linked_regs)
+{
+ struct bpf_reg_state *reg;
+ struct linked_reg *e;
+ int i;
+
+ for (i = 0; i < linked_regs->cnt; ++i) {
+ e = &linked_regs->entries[i];
+ reg = e->is_reg ? &vstate->frame[e->frameno]->regs[e->regno]
+ : &vstate->frame[e->frameno]->stack[e->spi].spilled_ptr;
+ if (reg->type != SCALAR_VALUE || reg == known_reg)
+ continue;
+ if (reg->id != known_reg->id)
+ continue;
+ {
s32 saved_subreg_def = reg->subreg_def;
+
copy_register_state(reg, known_reg);
reg->subreg_def = saved_subreg_def;
}
- }));
+ }
}
static int check_cond_jmp_op(struct bpf_verifier_env *env,
@@ -14587,6 +14663,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs;
struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL;
struct bpf_reg_state *eq_branch_regs;
+ struct linked_regs linked_regs = {};
u8 opcode = BPF_OP(insn->code);
bool is_jmp32;
int pred = -1;
@@ -14704,6 +14781,21 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
return 0;
}
+ /* Push scalar registers sharing same ID to jump history,
+ * do this before creating 'other_branch', so that both
+ * 'this_branch' and 'other_branch' share this history
+ * if parent state is created.
+ */
+ if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id)
+ collect_linked_regs(this_branch, src_reg->id, &linked_regs);
+ if (dst_reg->type == SCALAR_VALUE && dst_reg->id)
+ collect_linked_regs(this_branch, dst_reg->id, &linked_regs);
+ if (linked_regs.cnt > 1) {
+ err = push_jmp_history(env, this_branch, 0, linked_regs_pack(&linked_regs));
+ if (err)
+ return err;
+ }
+
other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx,
false);
if (!other_branch)
@@ -14746,8 +14838,9 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
src_reg, dst_reg, opcode);
if (src_reg->id &&
!WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) {
- find_equal_scalars(this_branch, src_reg);
- find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]);
+ sync_linked_regs(this_branch, src_reg, &linked_regs);
+ sync_linked_regs(other_branch, &other_branch_regs[insn->src_reg],
+ &linked_regs);
}
}
@@ -14759,8 +14852,9 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
if (dst_reg->type == SCALAR_VALUE && dst_reg->id &&
!WARN_ON_ONCE(dst_reg->id != other_branch_regs[insn->dst_reg].id)) {
- find_equal_scalars(this_branch, dst_reg);
- find_equal_scalars(other_branch, &other_branch_regs[insn->dst_reg]);
+ sync_linked_regs(this_branch, dst_reg, &linked_regs);
+ sync_linked_regs(other_branch, &other_branch_regs[insn->dst_reg],
+ &linked_regs);
}
/* if one pointer register is compared to another pointer
@@ -16182,7 +16276,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
*
* First verification path is [1-6]:
* - at (4) same bpf_reg_state::id (b) would be assigned to r6 and r7;
- * - at (5) r6 would be marked <= X, find_equal_scalars() would also mark
+ * - at (5) r6 would be marked <= X, sync_linked_regs() would also mark
* r7 <= X, because r6 and r7 share same id.
* Next verification path is [1-4, 6].
*
@@ -16915,7 +17009,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
* the current state.
*/
if (is_jmp_point(env, env->insn_idx))
- err = err ? : push_jmp_history(env, cur, 0);
+ err = err ? : push_jmp_history(env, cur, 0, 0);
err = err ? : propagate_precision(env, &sl->state);
if (err)
return err;
@@ -17181,7 +17275,7 @@ static int do_check(struct bpf_verifier_env *env)
}
if (is_jmp_point(env, env->insn_idx)) {
- err = push_jmp_history(env, state, 0);
+ err = push_jmp_history(env, state, 0, 0);
if (err)
return err;
}
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index def1f8fbc85c..6df2f674712a 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1524,6 +1524,9 @@ static void __sched remove_waiter(struct rt_mutex_base *lock,
lockdep_assert_held(&lock->wait_lock);
+ if (!waiter_task) /* never enqueued */
+ return;
+
scoped_guard(raw_spinlock, &waiter_task->pi_lock) {
rt_mutex_dequeue(lock, waiter);
waiter_task->pi_blocked_on = NULL;
diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c
index a6974d044593..06c3db9f6cf1 100644
--- a/kernel/locking/rtmutex_api.c
+++ b/kernel/locking/rtmutex_api.c
@@ -344,7 +344,7 @@ int __sched rt_mutex_start_proxy_lock(struct rt_mutex_base *lock,
raw_spin_lock_irq(&lock->wait_lock);
ret = __rt_mutex_start_proxy_lock(lock, waiter, task);
- if (unlikely(ret))
+ if (unlikely(ret < 0))
remove_waiter(lock, waiter);
raw_spin_unlock_irq(&lock->wait_lock);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index a896b80252ae..87e7cc2dc5cc 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2905,6 +2905,10 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
if (prog->expected_attach_type != BPF_TRACE_KPROBE_MULTI)
return -EINVAL;
+ /* kprobe_multi is not allowed to be sleepable. */
+ if (prog->aux->sleepable)
+ return -EINVAL;
+
flags = attr->link_create.kprobe_multi.flags;
if (flags & ~BPF_F_KPROBE_MULTI_RETURN)
return -EINVAL;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 94f7ed57d43e..07a4cbb7ffc0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1117,7 +1117,6 @@ struct ftrace_page {
};
#define ENTRY_SIZE sizeof(struct dyn_ftrace)
-#define ENTRIES_PER_PAGE (PAGE_SIZE / ENTRY_SIZE)
static struct ftrace_page *ftrace_pages_start;
static struct ftrace_page *ftrace_pages;
@@ -3245,7 +3244,8 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
return 0;
}
-static int ftrace_allocate_records(struct ftrace_page *pg, int count)
+static int ftrace_allocate_records(struct ftrace_page *pg, int count,
+ unsigned long *num_pages)
{
int order;
int pages;
@@ -3255,7 +3255,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count)
return -EINVAL;
/* We want to fill as much as possible, with no empty pages */
- pages = DIV_ROUND_UP(count, ENTRIES_PER_PAGE);
+ pages = DIV_ROUND_UP(count * ENTRY_SIZE, PAGE_SIZE);
order = fls(pages) - 1;
again:
@@ -3270,6 +3270,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count)
}
ftrace_number_of_pages += 1 << order;
+ *num_pages += 1 << order;
ftrace_number_of_groups++;
cnt = (PAGE_SIZE << order) / ENTRY_SIZE;
@@ -3298,12 +3299,14 @@ static void ftrace_free_pages(struct ftrace_page *pages)
}
static struct ftrace_page *
-ftrace_allocate_pages(unsigned long num_to_init)
+ftrace_allocate_pages(unsigned long num_to_init, unsigned long *num_pages)
{
struct ftrace_page *start_pg;
struct ftrace_page *pg;
int cnt;
+ *num_pages = 0;
+
if (!num_to_init)
return NULL;
@@ -3317,7 +3320,7 @@ ftrace_allocate_pages(unsigned long num_to_init)
* waste as little space as possible.
*/
for (;;) {
- cnt = ftrace_allocate_records(pg, num_to_init);
+ cnt = ftrace_allocate_records(pg, num_to_init, num_pages);
if (cnt < 0)
goto free_pages;
@@ -6526,6 +6529,7 @@ static int ftrace_process_locs(struct module *mod,
unsigned long *p;
unsigned long addr;
unsigned long flags = 0; /* Shut up gcc */
+ unsigned long pages;
int ret = -ENOMEM;
count = end - start;
@@ -6545,7 +6549,7 @@ static int ftrace_process_locs(struct module *mod,
test_is_sorted(start, count);
}
- start_pg = ftrace_allocate_pages(count);
+ start_pg = ftrace_allocate_pages(count, &pages);
if (!start_pg)
return -ENOMEM;
@@ -6577,7 +6581,9 @@ static int ftrace_process_locs(struct module *mod,
pg = start_pg;
while (p < end) {
unsigned long end_offset;
- addr = ftrace_call_adjust(*p++);
+
+ addr = *p++;
+
/*
* Some architecture linkers will pad between
* the different mcount_loc sections of different
@@ -6589,6 +6595,19 @@ static int ftrace_process_locs(struct module *mod,
continue;
}
+ /*
+ * If this is core kernel, make sure the address is in core
+ * or inittext, as weak functions get zeroed and KASLR can
+ * move them to something other than zero. It just will not
+ * move it to an area where kernel text is.
+ */
+ if (!mod && !(is_kernel_text(addr) || is_kernel_inittext(addr))) {
+ skipped++;
+ continue;
+ }
+
+ addr = ftrace_call_adjust(addr);
+
end_offset = (pg->index+1) * sizeof(pg->records[0]);
if (end_offset > PAGE_SIZE << pg->order) {
/* We should have allocated enough */
@@ -6628,11 +6647,41 @@ static int ftrace_process_locs(struct module *mod,
/* We should have used all pages unless we skipped some */
if (pg_unuse) {
- WARN_ON(!skipped);
+ unsigned long pg_remaining, remaining = 0;
+ long skip;
+
+ /* Count the number of entries unused and compare it to skipped. */
+ pg_remaining = (PAGE_SIZE << pg->order) / ENTRY_SIZE - pg->index;
+
+ if (!WARN(skipped < pg_remaining, "Extra allocated pages for ftrace")) {
+
+ skip = skipped - pg_remaining;
+
+ for (pg = pg_unuse; pg && skip > 0; pg = pg->next) {
+ remaining += 1 << pg->order;
+ skip -= (PAGE_SIZE << pg->order) / ENTRY_SIZE;
+ }
+
+ pages -= remaining;
+
+ /*
+ * Check to see if the number of pages remaining would
+ * just fit the number of entries skipped.
+ */
+ WARN(pg || skip > 0, "Extra allocated pages for ftrace: %lu with %lu skipped",
+ remaining, skipped);
+ }
/* Need to synchronize with ftrace_location_range() */
synchronize_rcu();
ftrace_free_pages(pg_unuse);
}
+
+ if (!mod) {
+ count -= skipped;
+ pr_info("ftrace: allocating %ld entries in %ld pages\n",
+ count, pages);
+ }
+
return ret;
}
@@ -7290,9 +7339,6 @@ void __init ftrace_init(void)
goto failed;
}
- pr_info("ftrace: allocating %ld entries in %ld pages\n",
- count, DIV_ROUND_UP(count, ENTRIES_PER_PAGE));
-
ret = ftrace_process_locs(NULL,
__start_mcount_loc,
__stop_mcount_loc);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 508edf1f3f1e..52c7dbccafed 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5084,28 +5084,20 @@ ring_buffer_consume(struct trace_buffer *buffer, int cpu, u64 *ts,
EXPORT_SYMBOL_GPL(ring_buffer_consume);
/**
- * ring_buffer_read_prepare - Prepare for a non consuming read of the buffer
+ * ring_buffer_read_start - start a non consuming read of the buffer
* @buffer: The ring buffer to read from
* @cpu: The cpu buffer to iterate over
* @flags: gfp flags to use for memory allocation
*
- * This performs the initial preparations necessary to iterate
- * through the buffer. Memory is allocated, buffer recording
- * is disabled, and the iterator pointer is returned to the caller.
- *
- * Disabling buffer recording prevents the reading from being
- * corrupted. This is not a consuming read, so a producer is not
- * expected.
- *
- * After a sequence of ring_buffer_read_prepare calls, the user is
- * expected to make at least one call to ring_buffer_read_prepare_sync.
- * Afterwards, ring_buffer_read_start is invoked to get things going
- * for real.
+ * This creates an iterator to allow non-consuming iteration through
+ * the buffer. If the buffer is disabled for writing, it will produce
+ * the same information each time, but if the buffer is still writing
+ * then the first hit of a write will cause the iteration to stop.
*
- * This overall must be paired with ring_buffer_read_finish.
+ * Must be paired with ring_buffer_read_finish.
*/
struct ring_buffer_iter *
-ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags)
+ring_buffer_read_start(struct trace_buffer *buffer, int cpu, gfp_t flags)
{
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_iter *iter;
@@ -5130,51 +5122,12 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags)
atomic_inc(&cpu_buffer->resize_disabled);
- return iter;
-}
-EXPORT_SYMBOL_GPL(ring_buffer_read_prepare);
-
-/**
- * ring_buffer_read_prepare_sync - Synchronize a set of prepare calls
- *
- * All previously invoked ring_buffer_read_prepare calls to prepare
- * iterators will be synchronized. Afterwards, read_buffer_read_start
- * calls on those iterators are allowed.
- */
-void
-ring_buffer_read_prepare_sync(void)
-{
- synchronize_rcu();
-}
-EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync);
-
-/**
- * ring_buffer_read_start - start a non consuming read of the buffer
- * @iter: The iterator returned by ring_buffer_read_prepare
- *
- * This finalizes the startup of an iteration through the buffer.
- * The iterator comes from a call to ring_buffer_read_prepare and
- * an intervening ring_buffer_read_prepare_sync must have been
- * performed.
- *
- * Must be paired with ring_buffer_read_finish.
- */
-void
-ring_buffer_read_start(struct ring_buffer_iter *iter)
-{
- struct ring_buffer_per_cpu *cpu_buffer;
- unsigned long flags;
-
- if (!iter)
- return;
-
- cpu_buffer = iter->cpu_buffer;
-
- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ guard(raw_spinlock_irqsave)(&cpu_buffer->reader_lock);
arch_spin_lock(&cpu_buffer->lock);
rb_iter_reset(iter);
arch_spin_unlock(&cpu_buffer->lock);
- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ return iter;
}
EXPORT_SYMBOL_GPL(ring_buffer_read_start);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 6b35666a4e0b..f57baf67726d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4792,21 +4792,15 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
if (iter->cpu_file == RING_BUFFER_ALL_CPUS) {
for_each_tracing_cpu(cpu) {
iter->buffer_iter[cpu] =
- ring_buffer_read_prepare(iter->array_buffer->buffer,
- cpu, GFP_KERNEL);
- }
- ring_buffer_read_prepare_sync();
- for_each_tracing_cpu(cpu) {
- ring_buffer_read_start(iter->buffer_iter[cpu]);
+ ring_buffer_read_start(iter->array_buffer->buffer,
+ cpu, GFP_KERNEL);
tracing_iter_reset(iter, cpu);
}
} else {
cpu = iter->cpu_file;
iter->buffer_iter[cpu] =
- ring_buffer_read_prepare(iter->array_buffer->buffer,
- cpu, GFP_KERNEL);
- ring_buffer_read_prepare_sync();
- ring_buffer_read_start(iter->buffer_iter[cpu]);
+ ring_buffer_read_start(iter->array_buffer->buffer,
+ cpu, GFP_KERNEL);
tracing_iter_reset(iter, cpu);
}
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index 59857a1ee44c..628c25693cef 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -43,17 +43,15 @@ static void ftrace_dump_buf(int skip_entries, long cpu_file)
if (cpu_file == RING_BUFFER_ALL_CPUS) {
for_each_tracing_cpu(cpu) {
iter.buffer_iter[cpu] =
- ring_buffer_read_prepare(iter.array_buffer->buffer,
- cpu, GFP_ATOMIC);
- ring_buffer_read_start(iter.buffer_iter[cpu]);
+ ring_buffer_read_start(iter.array_buffer->buffer,
+ cpu, GFP_ATOMIC);
tracing_iter_reset(&iter, cpu);
}
} else {
iter.cpu_file = cpu_file;
iter.buffer_iter[cpu_file] =
- ring_buffer_read_prepare(iter.array_buffer->buffer,
+ ring_buffer_read_start(iter.array_buffer->buffer,
cpu_file, GFP_ATOMIC);
- ring_buffer_read_start(iter.buffer_iter[cpu_file]);
tracing_iter_reset(&iter, cpu_file);
}
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 35cd384f7e8a..e4ef9d032d17 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -597,21 +597,59 @@ static struct debug_obj *lookup_object_or_alloc(void *addr, struct debug_bucket
return NULL;
}
-static void debug_objects_fill_pool(void)
+static inline bool debug_objects_is_pi_blocked_on(void)
+{
+#ifdef CONFIG_RT_MUTEXES
+ return current->pi_blocked_on != NULL;
+#else
+ return false;
+#endif
+}
+
+static inline bool can_fill_pool(void)
{
/*
- * On RT enabled kernels the pool refill must happen in preemptible
- * context -- for !RT kernels we rely on the fact that spinlock_t and
- * raw_spinlock_t are basically the same type and this lock-type
- * inversion works just fine.
+ * On !RT enabled kernels there are no restrictions and spinlock_t and
+ * raw_spinlock_t are the same types.
+ */
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ return true;
+
+ /*
+ * On RT enabled kernels, the task must not be blocked on a lock as
+ * that could corrupt the PI state when blocking on a lock in the
+ * allocation path.
*/
- if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) {
+ if (debug_objects_is_pi_blocked_on())
+ return false;
+
+ /*
+ * On RT enabled kernels the pool refill should happen in preemptible
+ * context.
+ */
+ if (preemptible())
+ return true;
+
+ /*
+ * Though during system boot before scheduling is set up, preemption is
+ * disabled and the pool can get exhausted. Before scheduling is active
+ * a task cannot be blocked on a sleeping lock, but it might hold a lock
+ * and if interrupted then hard interrupt context might run into a lock
+ * inversion. So exclude hard interrupt context from allocations before
+ * scheduling is active.
+ */
+ return system_state < SYSTEM_SCHEDULING && !in_hardirq();
+}
+
+static void debug_objects_fill_pool(void)
+{
+ if (can_fill_pool()) {
/*
* Annotate away the spinlock_t inside raw_spinlock_t warning
- * by temporarily raising the wait-type to WAIT_SLEEP, matching
- * the preemptible() condition above.
+ * by temporarily raising the wait-type to LD_WAIT_CONFIG, matching
+ * the preemptible() condition in can_fill_pool().
*/
- static DEFINE_WAIT_OVERRIDE_MAP(fill_pool_map, LD_WAIT_SLEEP);
+ static DEFINE_WAIT_OVERRIDE_MAP(fill_pool_map, LD_WAIT_CONFIG);
lock_map_acquire_try(&fill_pool_map);
fill_pool();
lock_map_release(&fill_pool_map);
diff --git a/net/9p/client.c b/net/9p/client.c
index cf73fe306219..c21ae8b8d649 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -1214,7 +1214,8 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
clunk_fid:
kfree(wqids);
- p9_fid_put(fid);
+ if (fid != oldfid)
+ p9_fid_put(fid);
fid = NULL;
error:
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index b37c9fb178ae..5dd3e1f281ba 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -310,14 +310,23 @@ batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len,
const struct batadv_ogm_packet *ogm_packet)
{
int next_buff_pos = 0;
+ u16 tvlv_len;
/* check if there is enough space for the header */
next_buff_pos += buff_pos + sizeof(*ogm_packet);
if (next_buff_pos > packet_len)
return false;
+ tvlv_len = ntohs(ogm_packet->tvlv_len);
+
+ /* the fields of an aggregated OGM are accessed assuming (at least)
+ * 2-byte alignment, so a following OGM must start at an even offset.
+ */
+ if (tvlv_len & 1)
+ return false;
+
/* check if there is enough space for the optional TVLV */
- next_buff_pos += ntohs(ogm_packet->tvlv_len);
+ next_buff_pos += tvlv_len;
return next_buff_pos <= packet_len;
}
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index d35479c465e2..e13b39121f2d 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -819,6 +819,7 @@ void batadv_v_hardif_init(struct batadv_hard_iface *hard_iface)
hard_iface->bat_v.aggr_len = 0;
skb_queue_head_init(&hard_iface->bat_v.aggr_list);
+ hard_iface->bat_v.aggr_list_enabled = false;
INIT_DELAYED_WORK(&hard_iface->bat_v.aggr_wq,
batadv_v_ogm_aggr_work);
}
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index 8cfc3944dcfd..c5c4d33cb198 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -254,11 +254,18 @@ static void batadv_v_ogm_queue_on_if(struct batadv_priv *bat_priv,
}
spin_lock_bh(&hard_iface->bat_v.aggr_list.lock);
+ if (!hard_iface->bat_v.aggr_list_enabled) {
+ kfree_skb(skb);
+ goto unlock;
+ }
+
if (!batadv_v_ogm_queue_left(skb, hard_iface))
batadv_v_ogm_aggr_send(bat_priv, hard_iface);
hard_iface->bat_v.aggr_len += batadv_v_ogm_len(skb);
__skb_queue_tail(&hard_iface->bat_v.aggr_list, skb);
+
+unlock:
spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock);
}
@@ -421,6 +428,10 @@ int batadv_v_ogm_iface_enable(struct batadv_hard_iface *hard_iface)
{
struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
+ spin_lock_bh(&hard_iface->bat_v.aggr_list.lock);
+ hard_iface->bat_v.aggr_list_enabled = true;
+ spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock);
+
batadv_v_ogm_start_queue_timer(hard_iface);
batadv_v_ogm_start_timer(bat_priv);
@@ -436,6 +447,7 @@ void batadv_v_ogm_iface_disable(struct batadv_hard_iface *hard_iface)
cancel_delayed_work_sync(&hard_iface->bat_v.aggr_wq);
spin_lock_bh(&hard_iface->bat_v.aggr_list.lock);
+ hard_iface->bat_v.aggr_list_enabled = false;
batadv_v_ogm_aggr_list_free(hard_iface);
spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock);
}
@@ -841,14 +853,23 @@ batadv_v_ogm_aggr_packet(int buff_pos, int packet_len,
const struct batadv_ogm2_packet *ogm2_packet)
{
int next_buff_pos = 0;
+ u16 tvlv_len;
/* check if there is enough space for the header */
next_buff_pos += buff_pos + sizeof(*ogm2_packet);
if (next_buff_pos > packet_len)
return false;
+ tvlv_len = ntohs(ogm2_packet->tvlv_len);
+
+ /* the fields of an aggregated OGMv2 are accessed assuming (at least)
+ * 2-byte alignment, so a following OGMv2 must start at an even offset.
+ */
+ if (tvlv_len & 1)
+ return false;
+
/* check if there is enough space for the optional TVLV */
- next_buff_pos += ntohs(ogm2_packet->tvlv_len);
+ next_buff_pos += tvlv_len;
return next_buff_pos <= packet_len;
}
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index cfb1eb25c6ac..ac12c06f11b8 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -512,7 +512,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, const u8 *orig,
return NULL;
entry->vid = vid;
- entry->lasttime = jiffies;
+ WRITE_ONCE(entry->lasttime, jiffies);
entry->crc = BATADV_BLA_CRC_INIT;
entry->bat_priv = bat_priv;
spin_lock_init(&entry->crc_lock);
@@ -580,7 +580,7 @@ batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv,
if (unlikely(!backbone_gw))
return;
- backbone_gw->lasttime = jiffies;
+ WRITE_ONCE(backbone_gw->lasttime, jiffies);
batadv_backbone_gw_put(backbone_gw);
}
@@ -714,7 +714,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
ether_addr_copy(claim->addr, mac);
spin_lock_init(&claim->backbone_lock);
claim->vid = vid;
- claim->lasttime = jiffies;
+ WRITE_ONCE(claim->lasttime, jiffies);
kref_get(&backbone_gw->refcount);
claim->backbone_gw = backbone_gw;
kref_init(&claim->refcount);
@@ -736,7 +736,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
return;
}
} else {
- claim->lasttime = jiffies;
+ WRITE_ONCE(claim->lasttime, jiffies);
if (claim->backbone_gw == backbone_gw)
/* no need to register a new backbone */
goto claim_free_ref;
@@ -769,7 +769,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
spin_lock_bh(&backbone_gw->crc_lock);
backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN);
spin_unlock_bh(&backbone_gw->crc_lock);
- backbone_gw->lasttime = jiffies;
+ WRITE_ONCE(backbone_gw->lasttime, jiffies);
claim_free_ref:
batadv_claim_put(claim);
@@ -858,7 +858,7 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr,
return true;
/* handle as ANNOUNCE frame */
- backbone_gw->lasttime = jiffies;
+ WRITE_ONCE(backbone_gw->lasttime, jiffies);
crc = ntohs(*((__force __be16 *)(&an_addr[4])));
batadv_dbg(BATADV_DBG_BLA, bat_priv,
@@ -1253,7 +1253,7 @@ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now)
head, hash_entry) {
if (now)
goto purge_now;
- if (!batadv_has_timed_out(backbone_gw->lasttime,
+ if (!batadv_has_timed_out(READ_ONCE(backbone_gw->lasttime),
BATADV_BLA_BACKBONE_TIMEOUT))
continue;
@@ -1334,7 +1334,7 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv,
primary_if->net_dev->dev_addr))
goto skip;
- if (!batadv_has_timed_out(claim->lasttime,
+ if (!batadv_has_timed_out(READ_ONCE(claim->lasttime),
BATADV_BLA_CLAIM_TIMEOUT))
goto skip;
@@ -1494,7 +1494,7 @@ static void batadv_bla_periodic_work(struct work_struct *work)
eth_random_addr(bat_priv->bla.loopdetect_addr);
bat_priv->bla.loopdetect_addr[0] = 0xba;
bat_priv->bla.loopdetect_addr[1] = 0xbe;
- bat_priv->bla.loopdetect_lasttime = jiffies;
+ WRITE_ONCE(bat_priv->bla.loopdetect_lasttime, jiffies);
atomic_set(&bat_priv->bla.loopdetect_next,
BATADV_BLA_LOOPDETECT_PERIODS);
@@ -1515,7 +1515,7 @@ static void batadv_bla_periodic_work(struct work_struct *work)
primary_if->net_dev->dev_addr))
continue;
- backbone_gw->lasttime = jiffies;
+ WRITE_ONCE(backbone_gw->lasttime, jiffies);
batadv_bla_send_announce(bat_priv, backbone_gw);
if (send_loopdetect)
@@ -1900,7 +1900,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb,
/* If the packet came too late, don't forward it on the mesh
* but don't consider that as loop. It might be a coincidence.
*/
- if (batadv_has_timed_out(bat_priv->bla.loopdetect_lasttime,
+ if (batadv_has_timed_out(READ_ONCE(bat_priv->bla.loopdetect_lasttime),
BATADV_BLA_LOOPDETECT_TIMEOUT))
return true;
@@ -2016,7 +2016,7 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
if (own_claim) {
/* ... allow it in any case */
- claim->lasttime = jiffies;
+ WRITE_ONCE(claim->lasttime, jiffies);
goto allow;
}
@@ -2118,7 +2118,7 @@ bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb,
/* if yes, the client has roamed and we have
* to unclaim it.
*/
- if (batadv_has_timed_out(claim->lasttime, 100)) {
+ if (batadv_has_timed_out(READ_ONCE(claim->lasttime), 100)) {
/* only unclaim if the last claim entry is
* older than 100 ms to make sure we really
* have a roaming client here.
@@ -2372,7 +2372,7 @@ batadv_bla_backbone_dump_entry(struct sk_buff *msg, u32 portid,
backbone_crc = backbone_gw->crc;
spin_unlock_bh(&backbone_gw->crc_lock);
- msecs = jiffies_to_msecs(jiffies - backbone_gw->lasttime);
+ msecs = jiffies_to_msecs(jiffies - READ_ONCE(backbone_gw->lasttime));
if (is_own)
if (nla_put_flag(msg, BATADV_ATTR_BLA_OWN)) {
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index c76bddbf816a..92d90e352d1f 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -215,10 +215,13 @@ static void batadv_dat_purge(struct work_struct *work)
*/
static bool batadv_compare_dat(const struct hlist_node *node, const void *data2)
{
- const void *data1 = container_of(node, struct batadv_dat_entry,
- hash_entry);
+ const struct batadv_dat_entry *entry1;
+ const struct batadv_dat_entry *entry2;
- return memcmp(data1, data2, sizeof(__be32)) == 0;
+ entry1 = container_of(node, struct batadv_dat_entry, hash_entry);
+ entry2 = data2;
+
+ return entry1->ip == entry2->ip && entry1->vid == entry2->vid;
}
/**
@@ -345,6 +348,9 @@ batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip,
if (dat_entry->ip != ip)
continue;
+ if (dat_entry->vid != vid)
+ continue;
+
if (!kref_get_unless_zero(&dat_entry->refcount))
continue;
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 4c1931940341..0138b0953e10 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -385,6 +385,8 @@ bool batadv_frag_skb_buffer(struct sk_buff **skb,
* @skb: skb to forward
* @recv_if: interface that the skb is received on
* @orig_node_src: originator that the skb is received from
+ * @rx_result: set to NET_RX_SUCCESS when the fragment was forwarded and
+ * NET_RX_DROP when it was dropped; only valid when true is returned
*
* Look up the next-hop of the fragments payload and check if the merged packet
* will exceed the MTU towards the next-hop. If so, the fragment is forwarded
@@ -394,7 +396,8 @@ bool batadv_frag_skb_buffer(struct sk_buff **skb,
*/
bool batadv_frag_skb_fwd(struct sk_buff *skb,
struct batadv_hard_iface *recv_if,
- struct batadv_orig_node *orig_node_src)
+ struct batadv_orig_node *orig_node_src,
+ int *rx_result)
{
struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
struct batadv_orig_node *orig_node_dst;
@@ -417,12 +420,29 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb,
*/
total_size = ntohs(packet->total_size);
if (total_size > neigh_node->if_incoming->net_dev->mtu) {
+ if (packet->ttl < 2) {
+ kfree_skb(skb);
+ *rx_result = NET_RX_DROP;
+ ret = true;
+ goto out;
+ }
+
+ if (skb_cow(skb, ETH_HLEN) < 0) {
+ kfree_skb(skb);
+ *rx_result = NET_RX_DROP;
+ ret = true;
+ goto out;
+ }
+
+ packet = (struct batadv_frag_packet *)skb->data;
+
batadv_inc_counter(bat_priv, BATADV_CNT_FRAG_FWD);
batadv_add_counter(bat_priv, BATADV_CNT_FRAG_FWD_BYTES,
skb->len + ETH_HLEN);
packet->ttl--;
batadv_send_unicast_skb(skb, neigh_node);
+ *rx_result = NET_RX_SUCCESS;
ret = true;
}
diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h
index dbf0871f8703..51e281027ab6 100644
--- a/net/batman-adv/fragmentation.h
+++ b/net/batman-adv/fragmentation.h
@@ -19,7 +19,8 @@ void batadv_frag_purge_orig(struct batadv_orig_node *orig,
bool (*check_cb)(struct batadv_frag_table_entry *));
bool batadv_frag_skb_fwd(struct sk_buff *skb,
struct batadv_hard_iface *recv_if,
- struct batadv_orig_node *orig_node_src);
+ struct batadv_orig_node *orig_node_src,
+ int *rx_result);
bool batadv_frag_skb_buffer(struct sk_buff **skb,
struct batadv_orig_node *orig_node);
int batadv_frag_send_packet(struct sk_buff *skb,
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index 0c64d81a7761..03ba6282af91 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -938,9 +938,15 @@ static int batadv_netlink_set_hardif(struct sk_buff *skb,
#ifdef CONFIG_BATMAN_ADV_BATMAN_V
if (info->attrs[BATADV_ATTR_ELP_INTERVAL]) {
+ u32 elp_interval;
+
attr = info->attrs[BATADV_ATTR_ELP_INTERVAL];
+ elp_interval = nla_get_u32(attr);
+
+ elp_interval = min_t(u32, elp_interval, INT_MAX);
+ elp_interval = max_t(u32, elp_interval, BATADV_JITTER);
- atomic_set(&hard_iface->bat_v.elp_interval, nla_get_u32(attr));
+ atomic_set(&hard_iface->bat_v.elp_interval, elp_interval);
}
if (info->attrs[BATADV_ATTR_THROUGHPUT_OVERRIDE]) {
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 163cd43c4821..ec278f73805e 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -8,6 +8,7 @@
#include "main.h"
#include <linux/atomic.h>
+#include <linux/build_bug.h>
#include <linux/byteorder/generic.h>
#include <linux/compiler.h>
#include <linux/errno.h>
@@ -205,6 +206,58 @@ bool batadv_check_management_packet(struct sk_buff *skb,
return true;
}
+/**
+ * batadv_skb_decrement_ttl() - decrement ttl in a batman-adv header, csum-safe
+ * @skb: the received packet with @skb->data pointing to the batman-adv header
+ *
+ * Supports the following packet types, all of which carry the TTL at offset 2:
+ *
+ * - batadv_ogm_packet
+ * - batadv_ogm2_packet
+ * - batadv_icmp_header
+ * - batadv_icmp_packet
+ * - batadv_icmp_tp_packet
+ * - batadv_icmp_packet_rr
+ * - batadv_unicast_packet
+ * - batadv_frag_packet
+ * - batadv_bcast_packet
+ * - batadv_mcast_packet
+ * - batadv_coded_packet
+ * - batadv_unicast_tvlv_packet
+ *
+ * Return: true if the packet may be forwarded (ttl decremented),
+ * false if it must be dropped (ttl would expire)
+ */
+static bool batadv_skb_decrement_ttl(struct sk_buff *skb)
+{
+ static const size_t ttl_offset = 2;
+ u8 *ttl_pos;
+
+ BUILD_BUG_ON(offsetof(struct batadv_ogm_packet, ttl) != ttl_offset);
+ BUILD_BUG_ON(offsetof(struct batadv_ogm2_packet, ttl) != ttl_offset);
+ BUILD_BUG_ON(offsetof(struct batadv_icmp_header, ttl) != ttl_offset);
+ BUILD_BUG_ON(offsetof(struct batadv_icmp_packet, ttl) != ttl_offset);
+ BUILD_BUG_ON(offsetof(struct batadv_icmp_tp_packet, ttl) != ttl_offset);
+ BUILD_BUG_ON(offsetof(struct batadv_icmp_packet_rr, ttl) != ttl_offset);
+ BUILD_BUG_ON(offsetof(struct batadv_unicast_packet, ttl) != ttl_offset);
+ BUILD_BUG_ON(offsetof(struct batadv_frag_packet, ttl) != ttl_offset);
+ BUILD_BUG_ON(offsetof(struct batadv_bcast_packet, ttl) != ttl_offset);
+ BUILD_BUG_ON(offsetof(struct batadv_coded_packet, ttl) != ttl_offset);
+ BUILD_BUG_ON(offsetof(struct batadv_unicast_tvlv_packet, ttl) != ttl_offset);
+
+ ttl_pos = skb->data + ttl_offset;
+
+ /* would expire on this hop -> drop, leave header + csum untouched */
+ if (*ttl_pos < 2)
+ return false;
+
+ skb_postpull_rcsum(skb, ttl_pos, 1);
+ (*ttl_pos)--;
+ skb_postpush_rcsum(skb, ttl_pos, 1);
+
+ return true;
+}
+
/**
* batadv_recv_my_icmp_packet() - receive an icmp packet locally
* @bat_priv: the bat priv with all the soft interface information
@@ -1121,10 +1174,9 @@ int batadv_recv_frag_packet(struct sk_buff *skb,
/* Route the fragment if it is not for us and too big to be merged. */
if (!batadv_is_my_mac(bat_priv, frag_packet->dest) &&
- batadv_frag_skb_fwd(skb, recv_if, orig_node_src)) {
+ batadv_frag_skb_fwd(skb, recv_if, orig_node_src, &ret)) {
/* skb was consumed */
skb = NULL;
- ret = NET_RX_SUCCESS;
goto put_orig_node;
}
@@ -1198,7 +1250,13 @@ int batadv_recv_bcast_packet(struct sk_buff *skb,
if (batadv_is_my_mac(bat_priv, bcast_packet->orig))
goto free_skb;
- if (bcast_packet->ttl-- < 2)
+ /* create a copy of the skb, if needed, to modify it. */
+ if (skb_cow(skb, ETH_HLEN) < 0)
+ goto free_skb;
+
+ bcast_packet = (struct batadv_bcast_packet *)skb->data;
+
+ if (!batadv_skb_decrement_ttl(skb))
goto free_skb;
orig_node = batadv_orig_hash_find(bat_priv, bcast_packet->orig);
diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c
index dfc337454992..50b83e0438a0 100644
--- a/net/batman-adv/tp_meter.c
+++ b/net/batman-adv/tp_meter.c
@@ -87,6 +87,11 @@
#define BATADV_TP_PLEN (BATADV_TP_PACKET_LEN - ETH_HLEN - \
sizeof(struct batadv_unicast_packet))
+/**
+ * BATADV_TP_MAX_UNACKED - maximum number of packets a receiver didn't yet ack
+ */
+#define BATADV_TP_MAX_UNACKED 100
+
static u8 batadv_tp_prerandom[4096] __read_mostly;
/**
@@ -154,9 +159,12 @@ static void batadv_tp_update_cwnd(struct batadv_tp_vars *tp_vars, u32 mss)
return;
}
+ /* prevent overflow in (mss * mss) << 3 */
+ mss = min_t(u32, mss, (1U << 14) - 1);
+
/* increment CWND at least of 1 (section 3.1 of RFC5681) */
tp_vars->dec_cwnd += max_t(u32, 1U << 3,
- ((mss * mss) << 6) / (tp_vars->cwnd << 3));
+ ((mss * mss) << 3) / tp_vars->cwnd);
if (tp_vars->dec_cwnd < (mss << 3)) {
spin_unlock_bh(&tp_vars->cwnd_lock);
return;
@@ -730,7 +738,7 @@ static void batadv_tp_recv_ack(struct batadv_priv *bat_priv,
if (atomic_read(&tp_vars->dup_acks) != 3)
goto out;
- if (recv_ack >= tp_vars->recover)
+ if (!batadv_seq_before(tp_vars->recover, recv_ack))
goto out;
/* if this is the third duplicate ACK do Fast Retransmit */
@@ -817,10 +825,15 @@ static void batadv_tp_recv_ack(struct batadv_priv *bat_priv,
static bool batadv_tp_avail(struct batadv_tp_vars *tp_vars,
size_t payload_len)
{
+ u32 last_sent = READ_ONCE(tp_vars->last_sent);
u32 win_left, win_limit;
win_limit = atomic_read(&tp_vars->last_acked) + tp_vars->cwnd;
- win_left = win_limit - tp_vars->last_sent;
+
+ if (batadv_seq_before(last_sent, win_limit))
+ win_left = win_limit - last_sent;
+ else
+ win_left = 0;
return win_left >= payload_len;
}
@@ -1045,6 +1058,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
tp_vars->icmp_uid = icmp_uid;
tp_vars->last_sent = BATADV_TP_FIRST_SEQ;
+ atomic_set(&tp_vars->dup_acks, 0);
atomic_set(&tp_vars->last_acked, BATADV_TP_FIRST_SEQ);
tp_vars->fast_recovery = false;
tp_vars->recover = BATADV_TP_FIRST_SEQ;
@@ -1054,6 +1068,8 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
* soft_interface, hence its MTU
*/
tp_vars->cwnd = BATADV_TP_PLEN * 3;
+ tp_vars->dec_cwnd = 0;
+
/* at the beginning initialise the SS threshold to the biggest possible
* window size, hence the AWND size
*/
@@ -1085,21 +1101,21 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
tp_vars->prerandom_offset = 0;
spin_lock_init(&tp_vars->prerandom_lock);
- kref_get(&tp_vars->refcount);
- hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list);
- spin_unlock_bh(&bat_priv->tp_list_lock);
-
tp_vars->test_length = test_length;
if (!tp_vars->test_length)
tp_vars->test_length = BATADV_TP_DEF_TEST_LENGTH;
+ /* init work item for finished tp tests */
+ INIT_DELAYED_WORK(&tp_vars->finish_work, batadv_tp_sender_finish);
+
+ kref_get(&tp_vars->refcount);
+ hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list);
+ spin_unlock_bh(&bat_priv->tp_list_lock);
+
batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
"Meter: starting throughput meter towards %pM (length=%ums)\n",
dst, test_length);
- /* init work item for finished tp tests */
- INIT_DELAYED_WORK(&tp_vars->finish_work, batadv_tp_sender_finish);
-
/* start tp kthread. This way the write() call issued from userspace can
* happily return and avoid to block
*/
@@ -1167,7 +1183,7 @@ static void batadv_tp_receiver_shutdown(struct timer_list *t)
bat_priv = tp_vars->bat_priv;
/* if there is recent activity rearm the timer */
- if (!batadv_has_timed_out(tp_vars->last_recv_time,
+ if (!batadv_has_timed_out(READ_ONCE(tp_vars->last_recv_time),
BATADV_TP_RECV_TIMEOUT)) {
/* reset the receiver shutdown timer */
batadv_tp_reset_receiver_timer(tp_vars);
@@ -1184,6 +1200,7 @@ static void batadv_tp_receiver_shutdown(struct timer_list *t)
list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) {
list_del(&un->list);
kfree(un);
+ tp_vars->unacked_count--;
}
spin_unlock_bh(&tp_vars->unacked_lock);
@@ -1267,7 +1284,8 @@ static int batadv_tp_send_ack(struct batadv_priv *bat_priv, const u8 *dst,
/**
* batadv_tp_handle_out_of_order() - store an out of order packet
* @tp_vars: the private data of the current TP meter session
- * @skb: the buffer containing the received packet
+ * @seqno: sequence number of new received packet
+ * @payload_len: length of the received packet
*
* Store the out of order packet in the unacked list for late processing. This
* packets are kept in this list so that they can be ACKed at once as soon as
@@ -1276,28 +1294,24 @@ static int batadv_tp_send_ack(struct batadv_priv *bat_priv, const u8 *dst,
* Return: true if the packed has been successfully processed, false otherwise
*/
static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars,
- const struct sk_buff *skb)
+ u32 seqno, u32 payload_len)
+ __must_hold(&tp_vars->unacked_lock)
{
- const struct batadv_icmp_tp_packet *icmp;
struct batadv_tp_unacked *un, *new;
- u32 payload_len;
bool added = false;
new = kmalloc(sizeof(*new), GFP_ATOMIC);
if (unlikely(!new))
return false;
- icmp = (struct batadv_icmp_tp_packet *)skb->data;
-
- new->seqno = ntohl(icmp->seqno);
- payload_len = skb->len - sizeof(struct batadv_unicast_packet);
+ new->seqno = seqno;
new->len = payload_len;
- spin_lock_bh(&tp_vars->unacked_lock);
/* if the list is empty immediately attach this new object */
if (list_empty(&tp_vars->unacked_list)) {
list_add(&new->list, &tp_vars->unacked_list);
- goto out;
+ tp_vars->unacked_count++;
+ return true;
}
/* otherwise loop over the list and either drop the packet because this
@@ -1325,17 +1339,26 @@ static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars,
* one is attached _after_ it. In this way the list is kept in
* ascending order
*/
- list_add_tail(&new->list, &un->list);
+ list_add(&new->list, &un->list);
added = true;
+ tp_vars->unacked_count++;
break;
}
/* received packet with smallest seqno out of order; add it to front */
- if (!added)
+ if (!added) {
list_add(&new->list, &tp_vars->unacked_list);
+ tp_vars->unacked_count++;
+ }
-out:
- spin_unlock_bh(&tp_vars->unacked_lock);
+ /* remove the last (biggest) unacked seqno when list is too large */
+ if (tp_vars->unacked_count > BATADV_TP_MAX_UNACKED) {
+ un = list_last_entry(&tp_vars->unacked_list,
+ struct batadv_tp_unacked, list);
+ list_del(&un->list);
+ kfree(un);
+ tp_vars->unacked_count--;
+ }
return true;
}
@@ -1346,6 +1369,7 @@ static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars,
* @tp_vars: the private data of the current TP meter session
*/
static void batadv_tp_ack_unordered(struct batadv_tp_vars *tp_vars)
+ __must_hold(&tp_vars->unacked_lock)
{
struct batadv_tp_unacked *un, *safe;
u32 to_ack;
@@ -1353,7 +1377,6 @@ static void batadv_tp_ack_unordered(struct batadv_tp_vars *tp_vars)
/* go through the unacked packet list and possibly ACK them as
* well
*/
- spin_lock_bh(&tp_vars->unacked_lock);
list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) {
/* the list is ordered, therefore it is possible to stop as soon
* there is a gap between the last acked seqno and the seqno of
@@ -1369,8 +1392,8 @@ static void batadv_tp_ack_unordered(struct batadv_tp_vars *tp_vars)
list_del(&un->list);
kfree(un);
+ tp_vars->unacked_count--;
}
- spin_unlock_bh(&tp_vars->unacked_lock);
}
/**
@@ -1392,8 +1415,10 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv,
tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig,
icmp->session, BATADV_TP_RECEIVER);
- if (tp_vars)
+ if (tp_vars) {
+ WRITE_ONCE(tp_vars->last_recv_time, jiffies);
goto out_unlock;
+ }
if (!atomic_add_unless(&bat_priv->tp_num, 1, BATADV_TP_MAX_NUM)) {
batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
@@ -1417,12 +1442,15 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv,
spin_lock_init(&tp_vars->unacked_lock);
INIT_LIST_HEAD(&tp_vars->unacked_list);
+ tp_vars->unacked_count = 0;
kref_get(&tp_vars->refcount);
- hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list);
+ timer_setup(&tp_vars->timer, batadv_tp_receiver_shutdown, 0);
+
+ WRITE_ONCE(tp_vars->last_recv_time, jiffies);
kref_get(&tp_vars->refcount);
- timer_setup(&tp_vars->timer, batadv_tp_receiver_shutdown, 0);
+ hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list);
batadv_tp_reset_receiver_timer(tp_vars);
@@ -1444,7 +1472,8 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv,
{
const struct batadv_icmp_tp_packet *icmp;
struct batadv_tp_vars *tp_vars;
- size_t packet_size;
+ u32 payload_len;
+ u32 to_ack;
u32 seqno;
icmp = (struct batadv_icmp_tp_packet *)skb->data;
@@ -1469,41 +1498,49 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv,
icmp->orig);
goto out;
}
+
+ WRITE_ONCE(tp_vars->last_recv_time, jiffies);
}
- tp_vars->last_recv_time = jiffies;
+ spin_lock_bh(&tp_vars->unacked_lock);
/* if the packet is a duplicate, it may be the case that an ACK has been
* lost. Resend the ACK
*/
- if (batadv_seq_before(seqno, tp_vars->last_recv))
+ payload_len = skb->len - sizeof(struct batadv_unicast_packet);
+ to_ack = seqno + payload_len;
+ if (batadv_seq_before(to_ack, tp_vars->last_recv))
goto send_ack;
/* if the packet is out of order enqueue it */
- if (ntohl(icmp->seqno) != tp_vars->last_recv) {
+ if (batadv_seq_before(tp_vars->last_recv, seqno)) {
/* exit immediately (and do not send any ACK) if the packet has
* not been enqueued correctly
*/
- if (!batadv_tp_handle_out_of_order(tp_vars, skb))
+ if (!batadv_tp_handle_out_of_order(tp_vars, seqno, payload_len)) {
+ spin_unlock_bh(&tp_vars->unacked_lock);
goto out;
+ }
/* send a duplicate ACK */
goto send_ack;
}
/* if everything was fine count the ACKed bytes */
- packet_size = skb->len - sizeof(struct batadv_unicast_packet);
- tp_vars->last_recv += packet_size;
+ tp_vars->last_recv = to_ack;
/* check if this ordered message filled a gap.... */
batadv_tp_ack_unordered(tp_vars);
send_ack:
+ to_ack = tp_vars->last_recv;
+ spin_unlock_bh(&tp_vars->unacked_lock);
+
/* send the ACK. If the received packet was out of order, the ACK that
* is going to be sent is a duplicate (the sender will count them and
* possibly enter Fast Retransmit as soon as it has reached 3)
*/
- batadv_tp_send_ack(bat_priv, icmp->orig, tp_vars->last_recv,
+ batadv_tp_send_ack(bat_priv, icmp->orig, to_ack,
icmp->timestamp, icmp->session, icmp->uid);
out:
batadv_tp_vars_put(tp_vars);
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 4045ddefc29b..2a7caab5c197 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -485,6 +485,9 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv,
if (!batadv_compare_eth(entry->change.addr, common->addr))
continue;
+ if (entry->change.vid != tt_change_node->change.vid)
+ continue;
+
/* DEL+ADD in the same orig interval have no effect and can be
* removed to avoid silly behaviour on the receiver side. The
* other way around (ADD+DEL) can happen in case of roaming of
@@ -850,11 +853,18 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node,
u16 total_entries = 0;
u8 *tt_change_ptr;
int vlan_entries;
+ u16 sum_entries;
spin_lock_bh(&orig_node->vlan_list_lock);
hlist_for_each_entry(vlan, &orig_node->vlan_list, list) {
vlan_entries = atomic_read(&vlan->tt.num_entries);
- total_entries += vlan_entries;
+
+ if (check_add_overflow(vlan_entries, total_entries, &sum_entries)) {
+ *tt_len = 0;
+ goto out;
+ }
+
+ total_entries = sum_entries;
num_vlan++;
}
@@ -941,15 +951,22 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
struct batadv_softif_vlan *vlan;
size_t change_offset;
u16 num_vlan = 0;
- u16 vlan_entries = 0;
u16 total_entries = 0;
u16 tvlv_len;
u8 *tt_change_ptr;
+ int vlan_entries;
+ u16 sum_entries;
spin_lock_bh(&bat_priv->softif_vlan_list_lock);
hlist_for_each_entry(vlan, &bat_priv->softif_vlan_list, list) {
vlan_entries = atomic_read(&vlan->tt.num_entries);
- total_entries += vlan_entries;
+
+ if (check_add_overflow(vlan_entries, total_entries, &sum_entries)) {
+ tvlv_len = 0;
+ goto out;
+ }
+
+ total_entries = sum_entries;
num_vlan++;
}
@@ -3500,6 +3517,7 @@ static void batadv_tt_roam_purge(struct batadv_priv *bat_priv)
* batadv_tt_check_roam_count() - check if a client has roamed too frequently
* @bat_priv: the bat priv with all the soft interface information
* @client: mac address of the roaming client
+ * @vid: VLAN identifier
*
* This function checks whether the client already reached the
* maximum number of possible roaming phases. In this case the ROAMING_ADV
@@ -3507,7 +3525,7 @@ static void batadv_tt_roam_purge(struct batadv_priv *bat_priv)
*
* Return: true if the ROAMING_ADV can be sent, false otherwise
*/
-static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client)
+static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client, u16 vid)
{
struct batadv_tt_roam_node *tt_roam_node;
bool ret = false;
@@ -3520,6 +3538,9 @@ static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client)
if (!batadv_compare_eth(tt_roam_node->addr, client))
continue;
+ if (tt_roam_node->vid != vid)
+ continue;
+
if (batadv_has_timed_out(tt_roam_node->first_time,
BATADV_ROAMING_MAX_TIME))
continue;
@@ -3541,6 +3562,7 @@ static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client)
atomic_set(&tt_roam_node->counter,
BATADV_ROAMING_MAX_COUNT - 1);
ether_addr_copy(tt_roam_node->addr, client);
+ tt_roam_node->vid = vid;
list_add(&tt_roam_node->list, &bat_priv->tt.roam_list);
ret = true;
@@ -3577,7 +3599,7 @@ static void batadv_send_roam_adv(struct batadv_priv *bat_priv, u8 *client,
/* before going on we have to check whether the client has
* already roamed to us too many times
*/
- if (!batadv_tt_check_roam_count(bat_priv, client))
+ if (!batadv_tt_check_roam_count(bat_priv, client, vid))
goto out;
batadv_dbg(BATADV_DBG_TT, bat_priv,
diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c
index 8d6b017c433c..cc66e231ccb8 100644
--- a/net/batman-adv/tvlv.c
+++ b/net/batman-adv/tvlv.c
@@ -398,7 +398,6 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv,
tvlv_handler->ogm_handler(bat_priv, orig_node,
BATADV_NO_FLAGS,
tvlv_value, tvlv_value_len);
- tvlv_handler->flags |= BATADV_TVLV_HANDLER_OGM_CALLED;
break;
case BATADV_UNICAST_TVLV:
if (!skb)
@@ -430,6 +429,48 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv,
return NET_RX_SUCCESS;
}
+/**
+ * batadv_tvlv_containers_contain() - check if a tvlv buffer holds a container
+ * @tvlv_value: tvlv content
+ * @tvlv_value_len: tvlv content length
+ * @type: tvlv container type to look for
+ * @version: tvlv container version to look for
+ *
+ * Return: true if a container of the given type and version is present in the
+ * tvlv buffer, false otherwise.
+ */
+static bool batadv_tvlv_containers_contain(void *tvlv_value,
+ u16 tvlv_value_len, u8 type,
+ u8 version)
+{
+ struct batadv_tvlv_hdr *tvlv_hdr;
+ u16 tvlv_value_cont_len;
+
+ while (tvlv_value_len >= sizeof(*tvlv_hdr)) {
+ tvlv_hdr = tvlv_value;
+ tvlv_value_cont_len = ntohs(tvlv_hdr->len);
+ tvlv_value = tvlv_hdr + 1;
+ tvlv_value_len -= sizeof(*tvlv_hdr);
+
+ if (tvlv_value_cont_len > tvlv_value_len)
+ break;
+
+ /* the next tvlv header is accessed assuming (at least) 2-byte
+ * alignment, so it must start at an even offset.
+ */
+ if (tvlv_value_cont_len & 1)
+ break;
+
+ if (tvlv_hdr->type == type && tvlv_hdr->version == version)
+ return true;
+
+ tvlv_value = (u8 *)tvlv_value + tvlv_value_cont_len;
+ tvlv_value_len -= tvlv_value_cont_len;
+ }
+
+ return false;
+}
+
/**
* batadv_tvlv_containers_process() - parse the given tvlv buffer to call the
* appropriate handlers
@@ -449,7 +490,9 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
struct sk_buff *skb, void *tvlv_value,
u16 tvlv_value_len)
{
+ u16 tvlv_value_start_len = tvlv_value_len;
struct batadv_tvlv_handler *tvlv_handler;
+ void *tvlv_value_start = tvlv_value;
struct batadv_tvlv_hdr *tvlv_hdr;
u16 tvlv_value_cont_len;
u8 cifnotfound = BATADV_TVLV_HANDLER_OGM_CIFNOTFND;
@@ -464,6 +507,12 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
if (tvlv_value_cont_len > tvlv_value_len)
break;
+ /* the next tvlv header is accessed assuming (at least) 2-byte
+ * alignment, so it must start at an even offset.
+ */
+ if (tvlv_value_cont_len & 1)
+ break;
+
tvlv_handler = batadv_tvlv_handler_get(bat_priv,
tvlv_hdr->type,
tvlv_hdr->version);
@@ -487,12 +536,20 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
if (!tvlv_handler->ogm_handler)
continue;
- if ((tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) &&
- !(tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CALLED))
- tvlv_handler->ogm_handler(bat_priv, orig_node,
- cifnotfound, NULL, 0);
+ if (!(tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND))
+ continue;
+
+ /* if the corresponding container was present then the handler
+ * was already called from the loop above
+ */
+ if (batadv_tvlv_containers_contain(tvlv_value_start,
+ tvlv_value_start_len,
+ tvlv_handler->type,
+ tvlv_handler->version))
+ continue;
- tvlv_handler->flags &= ~BATADV_TVLV_HANDLER_OGM_CALLED;
+ tvlv_handler->ogm_handler(bat_priv, orig_node,
+ cifnotfound, NULL, 0);
}
rcu_read_unlock();
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 2dfdc78d4ded..4856cc98fc3c 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -130,6 +130,12 @@ struct batadv_hard_iface_bat_v {
/** @aggr_list: queue for to be aggregated OGM packets */
struct sk_buff_head aggr_list;
+ /**
+ * @aggr_list_enabled: aggr_list is active and new skbs can be
+ * enqueued. Protected by aggr_list.lock after initialization
+ */
+ bool aggr_list_enabled:1;
+
/** @aggr_len: size of the OGM aggregate (excluding ethernet header) */
unsigned int aggr_len;
@@ -1485,9 +1491,12 @@ struct batadv_tp_vars {
/** @unacked_list: list of unacked packets (meta-info only) */
struct list_head unacked_list;
- /** @unacked_lock: protect unacked_list */
+ /** @unacked_lock: protect unacked_list + &batadv_tp_receiver.last_recv */
spinlock_t unacked_lock;
+ /** @unacked_count: number of unacked entries */
+ size_t unacked_count;
+
/** @last_recv_time: time (jiffies) a msg was received */
unsigned long last_recv_time;
@@ -1986,6 +1995,9 @@ struct batadv_tt_roam_node {
/** @addr: mac address of the client in the roaming phase */
u8 addr[ETH_ALEN];
+ /** @vid: VLAN identifier */
+ u16 vid;
+
/**
* @counter: number of allowed roaming events per client within a single
* OGM interval (changes are committed with each OGM)
@@ -2401,13 +2413,6 @@ enum batadv_tvlv_handler_flags {
* will call this handler even if its type was not found (with no data)
*/
BATADV_TVLV_HANDLER_OGM_CIFNOTFND = BIT(1),
-
- /**
- * @BATADV_TVLV_HANDLER_OGM_CALLED: interval tvlv handling flag - the
- * API marks a handler as being called, so it won't be called if the
- * BATADV_TVLV_HANDLER_OGM_CIFNOTFND flag was set
- */
- BATADV_TVLV_HANDLER_OGM_CALLED = BIT(2),
};
#endif /* _NET_BATMAN_ADV_TYPES_H_ */
diff --git a/net/core/filter.c b/net/core/filter.c
index 2922f88311ca..4a9c1367ea4d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2721,11 +2721,13 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
poffset += len;
sge->length = 0;
put_page(sg_page(sge));
+ __clear_bit(i, msg->sg.copy);
sk_msg_iter_var_next(i);
} while (i != last_sge);
sg_set_page(&msg->sg.data[first_sge], page, copy, 0);
+ __clear_bit(first_sge, msg->sg.copy);
/* To repair sg ring we need to shift entries. If we only
* had a single entry though we can just replace it and
@@ -2751,9 +2753,11 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
break;
msg->sg.data[i] = msg->sg.data[move_from];
+ sk_msg_sg_copy_assign(msg, i, msg, move_from);
msg->sg.data[move_from].length = 0;
msg->sg.data[move_from].page_link = 0;
msg->sg.data[move_from].offset = 0;
+ __clear_bit(move_from, msg->sg.copy);
sk_msg_iter_var_next(i);
} while (1);
@@ -2782,6 +2786,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
{
struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge;
u32 new, i = 0, l = 0, space, copy = 0, offset = 0;
+ bool sge_copy, nsge_copy, nnsge_copy, rsge_copy = false;
u8 *raw, *to, *from;
struct page *page;
@@ -2854,6 +2859,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
sk_msg_iter_var_prev(i);
psge = sk_msg_elem(msg, i);
rsge = sk_msg_elem_cpy(msg, i);
+ rsge_copy = test_bit(i, msg->sg.copy);
psge->length = start - offset;
rsge.length -= psge->length;
@@ -2878,24 +2884,32 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
/* Shift one or two slots as needed */
sge = sk_msg_elem_cpy(msg, new);
+ sge_copy = test_bit(new, msg->sg.copy);
sg_unmark_end(&sge);
nsge = sk_msg_elem_cpy(msg, i);
+ nsge_copy = test_bit(i, msg->sg.copy);
if (rsge.length) {
sk_msg_iter_var_next(i);
nnsge = sk_msg_elem_cpy(msg, i);
+ nnsge_copy = test_bit(i, msg->sg.copy);
sk_msg_iter_next(msg, end);
}
while (i != msg->sg.end) {
msg->sg.data[i] = sge;
+ __assign_bit(i, msg->sg.copy, sge_copy);
sge = nsge;
+ sge_copy = nsge_copy;
sk_msg_iter_var_next(i);
if (rsge.length) {
nsge = nnsge;
+ nsge_copy = nnsge_copy;
nnsge = sk_msg_elem_cpy(msg, i);
+ nnsge_copy = test_bit(i, msg->sg.copy);
} else {
nsge = sk_msg_elem_cpy(msg, i);
+ nsge_copy = test_bit(i, msg->sg.copy);
}
}
@@ -2909,6 +2923,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
get_page(sg_page(&rsge));
sk_msg_iter_var_next(new);
msg->sg.data[new] = rsge;
+ __assign_bit(new, msg->sg.copy, rsge_copy);
}
sk_msg_reset_curr(msg);
@@ -2936,25 +2951,33 @@ static void sk_msg_shift_left(struct sk_msg *msg, int i)
prev = i;
sk_msg_iter_var_next(i);
msg->sg.data[prev] = msg->sg.data[i];
+ sk_msg_sg_copy_assign(msg, prev, msg, i);
} while (i != msg->sg.end);
sk_msg_iter_prev(msg, end);
+ __clear_bit(msg->sg.end, msg->sg.copy);
}
static void sk_msg_shift_right(struct sk_msg *msg, int i)
{
struct scatterlist tmp, sge;
+ bool tmp_copy, sge_copy;
sk_msg_iter_next(msg, end);
sge = sk_msg_elem_cpy(msg, i);
+ sge_copy = test_bit(i, msg->sg.copy);
sk_msg_iter_var_next(i);
tmp = sk_msg_elem_cpy(msg, i);
+ tmp_copy = test_bit(i, msg->sg.copy);
while (i != msg->sg.end) {
msg->sg.data[i] = sge;
+ __assign_bit(i, msg->sg.copy, sge_copy);
sk_msg_iter_var_next(i);
sge = tmp;
+ sge_copy = tmp_copy;
tmp = sk_msg_elem_cpy(msg, i);
+ tmp_copy = test_bit(i, msg->sg.copy);
}
}
@@ -3014,6 +3037,8 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
struct scatterlist *nsge, *sge = sk_msg_elem(msg, i);
int a = start - offset;
int b = sge->length - pop - a;
+ u32 sge_i = i;
+ bool sge_copy = test_bit(i, msg->sg.copy);
sk_msg_iter_var_next(i);
@@ -3026,6 +3051,7 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
sg_set_page(nsge,
sg_page(sge),
b, sge->offset + pop + a);
+ __assign_bit(i, msg->sg.copy, sge_copy);
} else {
struct page *page, *orig;
u8 *to, *from;
@@ -3042,6 +3068,7 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
memcpy(to, from, a);
memcpy(to + a, from + a + pop, b);
sg_set_page(sge, page, a + b, 0);
+ __clear_bit(sge_i, msg->sg.copy);
put_page(orig);
}
pop = 0;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 403ad91c5c74..565229dfd3f2 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -66,6 +66,7 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
sge = &msg->sg.data[msg->sg.end];
sg_unmark_end(sge);
sg_set_page(sge, pfrag->page, use, orig_offset);
+ __clear_bit(msg->sg.end, msg->sg.copy);
get_page(pfrag->page);
sk_msg_iter_next(msg, end);
}
@@ -186,6 +187,7 @@ static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i,
sk_mem_uncharge(sk, len);
put_page(sg_page(sge));
}
+ __clear_bit(i, msg->sg.copy);
memset(sge, 0, sizeof(*sge));
return len;
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 305d0e2786a2..8502cd34b578 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1117,8 +1117,8 @@ static int __ip_append_data(struct sock *sk,
!(rt->dst.dev->features & NETIF_F_SG)))
alloclen = fraglen;
else {
- alloclen = fragheaderlen + transhdrlen;
- pagedlen = datalen - transhdrlen;
+ alloclen = fragheaderlen + transhdrlen + fraggap;
+ pagedlen = datalen - transhdrlen - fraggap;
}
alloclen += alloc_extra;
@@ -1165,10 +1165,10 @@ static int __ip_append_data(struct sock *sk,
}
copy = datalen - transhdrlen - fraggap - pagedlen;
- /* [!] NOTE: copy will be negative if pagedlen>0
- * because then the equation reduces to -fraggap.
- */
- if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
+ if (copy > 0 &&
+ INDIRECT_CALL_1(getfrag, ip_generic_getfrag,
+ from, data + transhdrlen, offset,
+ copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
goto error;
@@ -1212,8 +1212,9 @@ static int __ip_append_data(struct sock *sk,
unsigned int off;
off = skb->len;
- if (getfrag(from, skb_put(skb, copy),
- offset, copy, off, skb) < 0) {
+ if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag,
+ from, skb_put(skb, copy),
+ offset, copy, off, skb) < 0) {
__skb_trim(skb, off);
err = -EFAULT;
goto error;
@@ -1253,7 +1254,8 @@ static int __ip_append_data(struct sock *sk,
get_page(pfrag->page);
}
copy = min_t(int, copy, pfrag->size - pfrag->offset);
- if (getfrag(from,
+ if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag,
+ from,
page_address(pfrag->page) + pfrag->offset,
offset, copy, skb->len, skb) < 0)
goto error_efault;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 710aadbb2e26..2e2cd0e0d48a 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1633,8 +1633,8 @@ static int __ip6_append_data(struct sock *sk,
!(rt->dst.dev->features & NETIF_F_SG)))
alloclen = fraglen;
else {
- alloclen = fragheaderlen + transhdrlen;
- pagedlen = datalen - transhdrlen;
+ alloclen = fragheaderlen + transhdrlen + fraggap;
+ pagedlen = datalen - transhdrlen - fraggap;
}
alloclen += alloc_extra;
@@ -1649,10 +1649,7 @@ static int __ip6_append_data(struct sock *sk,
fraglen = datalen + fragheaderlen;
copy = datalen - transhdrlen - fraggap - pagedlen;
- /* [!] NOTE: copy may be negative if pagedlen>0
- * because then the equation may reduces to -fraggap.
- */
- if (copy < 0 && !(flags & MSG_SPLICE_PAGES)) {
+ if (copy < 0) {
err = -EINVAL;
goto error;
}
@@ -1698,8 +1695,9 @@ static int __ip6_append_data(struct sock *sk,
pskb_trim_unique(skb_prev, maxfraglen);
}
if (copy > 0 &&
- getfrag(from, data + transhdrlen, offset,
- copy, fraggap, skb) < 0) {
+ INDIRECT_CALL_1(getfrag, ip_generic_getfrag,
+ from, data + transhdrlen, offset,
+ copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
goto error;
@@ -1743,8 +1741,9 @@ static int __ip6_append_data(struct sock *sk,
unsigned int off;
off = skb->len;
- if (getfrag(from, skb_put(skb, copy),
- offset, copy, off, skb) < 0) {
+ if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag,
+ from, skb_put(skb, copy),
+ offset, copy, off, skb) < 0) {
__skb_trim(skb, off);
err = -EFAULT;
goto error;
@@ -1784,7 +1783,8 @@ static int __ip6_append_data(struct sock *sk,
get_page(pfrag->page);
}
copy = min_t(int, copy, pfrag->size - pfrag->offset);
- if (getfrag(from,
+ if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag,
+ from,
page_address(pfrag->page) + pfrag->offset,
offset, copy, skb->len, skb) < 0)
goto error_efault;
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 67cf616c1499..95cf8c52953c 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -1166,6 +1166,7 @@ static int __net_init vti6_init_net(struct net *net)
goto err_alloc_dev;
dev_net_set(ip6n->fb_tnl_dev, net);
ip6n->fb_tnl_dev->rtnl_link_ops = &vti6_link_ops;
+ ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL;
err = vti6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
if (err < 0)
diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c
index f13b07ebfb98..09a47104b577 100644
--- a/net/mac802154/llsec.c
+++ b/net/mac802154/llsec.c
@@ -710,6 +710,7 @@ int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb)
{
struct ieee802154_hdr hdr;
int rc, authlen, hlen;
+ struct sk_buff *trailer;
struct mac802154_llsec_key *key;
u32 frame_ctr;
@@ -769,6 +770,12 @@ int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb)
skb->mac_len = ieee802154_hdr_push(skb, &hdr);
skb_reset_mac_header(skb);
+ rc = skb_cow_data(skb, 0, &trailer);
+ if (rc < 0) {
+ llsec_key_put(key);
+ return rc;
+ }
+
rc = llsec_do_encrypt(skb, sec, &hdr, key);
llsec_key_put(key);
@@ -908,6 +915,13 @@ llsec_do_decrypt(struct sk_buff *skb, const struct mac802154_llsec *sec,
const struct ieee802154_hdr *hdr,
struct mac802154_llsec_key *key, __le64 dev_addr)
{
+ struct sk_buff *trailer;
+ int err;
+
+ err = skb_cow_data(skb, 0, &trailer);
+ if (err < 0)
+ return err;
+
if (hdr->sec.level == IEEE802154_SCF_SECLEVEL_ENC)
return llsec_do_decrypt_unauth(skb, sec, hdr, key, dev_addr);
else
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 8faf776cb977..663aeefbd1b2 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -408,18 +408,21 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info)
goto create_err;
}
+ spin_lock_bh(&msk->pm.lock);
+ msk->pm.subflows++;
+ spin_unlock_bh(&msk->pm.lock);
+
lock_sock(sk);
err = __mptcp_subflow_connect(sk, &addr_l, &addr_r);
release_sock(sk);
- spin_lock_bh(&msk->pm.lock);
- if (err)
+ if (err) {
+ spin_lock_bh(&msk->pm.lock);
mptcp_userspace_pm_delete_local_addr(msk, &local);
- else
- msk->pm.subflows++;
- spin_unlock_bh(&msk->pm.lock);
+ spin_unlock_bh(&msk->pm.lock);
+ }
create_err:
sock_put((struct sock *)msk);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 6fc88bf51109..c39fd25a9c97 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -652,7 +652,6 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx,
elem.priv = catchall->elem;
nft_set_elem_change_active(ctx->net, set, ext);
nft_setelem_data_deactivate(ctx->net, set, &elem);
- break;
}
}
@@ -5615,7 +5614,6 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx,
nft_clear(ctx->net, ext);
elem.priv = catchall->elem;
nft_setelem_data_activate(ctx->net, set, &elem);
- break;
}
}
diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c
index cde671d29d5d..3f020c362d6c 100644
--- a/net/phonet/pn_dev.c
+++ b/net/phonet/pn_dev.c
@@ -98,11 +98,14 @@ static void phonet_device_destroy(struct net_device *dev)
mutex_unlock(&pndevs->lock);
if (pnd) {
+ struct net *net = dev_net(dev);
+ u32 ifindex = dev->ifindex;
u8 addr;
for_each_set_bit(addr, pnd->addrs, 64)
- phonet_address_notify(RTM_DELADDR, dev, addr);
- kfree(pnd);
+ phonet_address_notify(net, RTM_DELADDR, ifindex, addr);
+
+ kfree_rcu(pnd, rcu);
}
}
@@ -244,8 +247,9 @@ static int phonet_device_autoconf(struct net_device *dev)
ret = phonet_address_add(dev, req.ifr_phonet_autoconf.device);
if (ret)
return ret;
- phonet_address_notify(RTM_NEWADDR, dev,
- req.ifr_phonet_autoconf.device);
+
+ phonet_address_notify(dev_net(dev), RTM_NEWADDR, dev->ifindex,
+ req.ifr_phonet_autoconf.device);
return 0;
}
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
index 894e5c72d6bf..23097085ad38 100644
--- a/net/phonet/pn_netlink.c
+++ b/net/phonet/pn_netlink.c
@@ -19,10 +19,10 @@
/* Device address handling */
-static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr,
+static int fill_addr(struct sk_buff *skb, u32 ifindex, u8 addr,
u32 portid, u32 seq, int event);
-void phonet_address_notify(int event, struct net_device *dev, u8 addr)
+void phonet_address_notify(struct net *net, int event, u32 ifindex, u8 addr)
{
struct sk_buff *skb;
int err = -ENOBUFS;
@@ -31,17 +31,18 @@ void phonet_address_notify(int event, struct net_device *dev, u8 addr)
nla_total_size(1), GFP_KERNEL);
if (skb == NULL)
goto errout;
- err = fill_addr(skb, dev, addr, 0, 0, event);
+
+ err = fill_addr(skb, ifindex, addr, 0, 0, event);
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
- rtnl_notify(skb, dev_net(dev), 0,
- RTNLGRP_PHONET_IFADDR, NULL, GFP_KERNEL);
+
+ rtnl_notify(skb, net, 0, RTNLGRP_PHONET_IFADDR, NULL, GFP_KERNEL);
return;
errout:
- rtnl_set_sk_err(dev_net(dev), RTNLGRP_PHONET_IFADDR, err);
+ rtnl_set_sk_err(net, RTNLGRP_PHONET_IFADDR, err);
}
static const struct nla_policy ifa_phonet_policy[IFA_MAX+1] = {
@@ -88,12 +89,12 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
else
err = phonet_address_del(dev, pnaddr);
if (!err)
- phonet_address_notify(nlh->nlmsg_type, dev, pnaddr);
+ phonet_address_notify(net, nlh->nlmsg_type, ifm->ifa_index, pnaddr);
return err;
}
-static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr,
- u32 portid, u32 seq, int event)
+static int fill_addr(struct sk_buff *skb, u32 ifindex, u8 addr,
+ u32 portid, u32 seq, int event)
{
struct ifaddrmsg *ifm;
struct nlmsghdr *nlh;
@@ -107,7 +108,7 @@ static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr,
ifm->ifa_prefixlen = 0;
ifm->ifa_flags = IFA_F_PERMANENT;
ifm->ifa_scope = RT_SCOPE_LINK;
- ifm->ifa_index = dev->ifindex;
+ ifm->ifa_index = ifindex;
if (nla_put_u8(skb, IFA_LOCAL, addr))
goto nla_put_failure;
nlmsg_end(skb, nlh);
@@ -140,7 +141,7 @@ static int getaddr_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
if (addr_idx++ < addr_start_idx)
continue;
- if (fill_addr(skb, pnd->netdev, addr << 2,
+ if (fill_addr(skb, pnd->netdev->ifindex, addr << 2,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, RTM_NEWADDR) < 0)
goto out;
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 9a162035d4c1..1157bf75ef9c 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -781,7 +781,18 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call,
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
unsigned int i, old_nacks = 0;
rxrpc_seq_t lowest_nak = seq + sp->nr_acks;
- u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket);
+ u8 sack[256] __aligned(sizeof(unsigned long));
+ u8 *acks = sack;
+
+ /* Extract the SACK table into a flat buffer rather than accessing it
+ * directly through skb->data, which is not guaranteed to be linear for
+ * a fragmented packet (skb_condense() can silently fail to linearise
+ * it).
+ */
+ if (skb_copy_bits(skb,
+ sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket),
+ sack, umin(sp->nr_acks, sizeof(sack))) < 0)
+ return;
for (i = 0; i < sp->nr_acks; i++) {
if (acks[i] == RXRPC_ACK_TYPE_ACK) {
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 1ef8fcfa9997..80b2a1e9d5ce 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -16,6 +16,8 @@
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/slab.h>
+#include <linux/overflow.h>
+#include <asm/unaligned.h>
#include <net/ipv6.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
@@ -242,7 +244,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
goto out_free_ex;
}
- nparms->tcfp_off_max_hint = 0;
nparms->tcfp_flags = parm->flags;
nparms->tcfp_nkeys = parm->nkeys;
@@ -268,14 +269,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
BITS_PER_TYPE(int) - 1,
nparms->tcfp_keys[i].shift);
- /* The AT option can read a single byte, we can bound the actual
- * value with uchar max.
- */
- cur += (0xff & offmask) >> nparms->tcfp_keys[i].shift;
-
- /* Each key touches 4 bytes starting from the computed offset */
- nparms->tcfp_off_max_hint =
- max(nparms->tcfp_off_max_hint, cur + 4);
}
p = to_pedit(*a);
@@ -318,15 +311,12 @@ static void tcf_pedit_cleanup(struct tc_action *a)
call_rcu(&parms->rcu, tcf_pedit_cleanup_rcu);
}
-static bool offset_valid(struct sk_buff *skb, int offset)
+static bool offset_valid(struct sk_buff *skb, int offset, int len)
{
- if (offset > 0 && offset > skb->len)
- return false;
-
- if (offset < 0 && -offset > skb_headroom(skb))
+ if (offset < -(int)skb_headroom(skb))
return false;
- return true;
+ return offset <= (int)skb->len - len;
}
static int pedit_l4_skb_offset(struct sk_buff *skb, int *hoffset, const int header_type)
@@ -393,18 +383,10 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb,
struct tcf_pedit_key_ex *tkey_ex;
struct tcf_pedit_parms *parms;
struct tc_pedit_key *tkey;
- u32 max_offset;
int i;
parms = rcu_dereference_bh(p->parms);
- max_offset = (skb_transport_header_was_set(skb) ?
- skb_transport_offset(skb) :
- skb_network_offset(skb)) +
- parms->tcfp_off_max_hint;
- if (skb_ensure_writable(skb, min(skb->len, max_offset)))
- goto done;
-
tcf_lastuse_update(&p->tcf_tm);
tcf_action_update_bstats(&p->common, skb);
@@ -412,10 +394,11 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb,
tkey_ex = parms->tcfp_keys_ex;
for (i = parms->tcfp_nkeys; i > 0; i--, tkey++) {
+ int write_offset, write_len;
int offset = tkey->off;
int hoffset = 0;
- u32 *ptr, hdata;
- u32 val;
+ u32 cur_val, val;
+ u32 *ptr;
int rc;
if (tkey_ex) {
@@ -433,13 +416,15 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb,
if (tkey->offmask) {
u8 *d, _d;
+ int at_offset;
- if (!offset_valid(skb, hoffset + tkey->at)) {
+ if (check_add_overflow(hoffset, (int)tkey->at, &at_offset) ||
+ !offset_valid(skb, at_offset, sizeof(_d))) {
pr_info_ratelimited("tc action pedit 'at' offset %d out of bounds\n",
hoffset + tkey->at);
goto bad;
}
- d = skb_header_pointer(skb, hoffset + tkey->at,
+ d = skb_header_pointer(skb, at_offset,
sizeof(_d), &_d);
if (!d)
goto bad;
@@ -451,31 +436,51 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb,
}
}
- if (!offset_valid(skb, hoffset + offset)) {
- pr_info_ratelimited("tc action pedit offset %d out of bounds\n", hoffset + offset);
+ if (check_add_overflow(hoffset, offset, &write_offset)) {
+ pr_info_ratelimited("tc action pedit offset overflow\n");
goto bad;
}
- ptr = skb_header_pointer(skb, hoffset + offset,
- sizeof(hdata), &hdata);
- if (!ptr)
+ if (!offset_valid(skb, write_offset, sizeof(*ptr))) {
+ pr_info_ratelimited("tc action pedit offset %d out of bounds\n",
+ write_offset);
goto bad;
+ }
+
+ if (write_offset < 0) {
+ if (skb_cow(skb, -write_offset))
+ goto bad;
+ if (write_offset + (int)sizeof(*ptr) > 0) {
+ if (skb_ensure_writable(skb,
+ min_t(int, skb->len,
+ write_offset + (int)sizeof(*ptr))))
+ goto bad;
+ }
+ } else {
+ if (check_add_overflow(write_offset, (int)sizeof(*ptr),
+ &write_len))
+ goto bad;
+ if (skb_ensure_writable(skb, min_t(int, skb->len,
+ write_len)))
+ goto bad;
+ }
+
+ ptr = (u32 *)(skb->data + write_offset);
+ cur_val = get_unaligned(ptr);
/* just do it, baby */
switch (cmd) {
case TCA_PEDIT_KEY_EX_CMD_SET:
val = tkey->val;
break;
case TCA_PEDIT_KEY_EX_CMD_ADD:
- val = (*ptr + tkey->val) & ~tkey->mask;
+ val = (cur_val + tkey->val) & ~tkey->mask;
break;
default:
pr_info_ratelimited("tc action pedit bad command (%d)\n", cmd);
goto bad;
}
- *ptr = ((*ptr & tkey->mask) ^ val);
- if (ptr == &hdata)
- skb_store_bits(skb, hoffset + offset, ptr, 4);
+ put_unaligned((cur_val & tkey->mask) ^ val, ptr);
}
goto done;
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index d7736d900271..d58db40d6c03 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -950,12 +950,20 @@ static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead,
goto exit;
}
+ /* Get net to avoid freed tipc_crypto when delete namespace */
+ if (!maybe_get_net(net)) {
+ tipc_bearer_put(b);
+ rc = -ENODEV;
+ goto exit;
+ }
+
/* Now, do decrypt */
rc = crypto_aead_decrypt(req);
if (rc == -EINPROGRESS || rc == -EBUSY)
return rc;
tipc_bearer_put(b);
+ put_net(net);
exit:
kfree(ctx);
@@ -993,6 +1001,7 @@ static void tipc_aead_decrypt_done(void *data, int err)
}
tipc_bearer_put(b);
+ put_net(net);
}
static inline int tipc_ehdr_size(struct tipc_ehdr *ehdr)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index cdc415de6da2..89f01227ca5b 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -623,6 +623,7 @@ static int tls_split_open_record(struct sock *sk, struct tls_rec *from,
struct scatterlist *sge, *osge, *nsge;
u32 orig_size = msg_opl->sg.size;
struct scatterlist tmp = { };
+ u32 tmp_i = 0;
struct sk_msg *msg_npl;
struct tls_rec *new;
int ret;
@@ -644,6 +645,7 @@ static int tls_split_open_record(struct sock *sk, struct tls_rec *from,
if (sge->length > apply) {
u32 len = sge->length - apply;
+ tmp_i = i;
get_page(sg_page(sge));
sg_set_page(&tmp, sg_page(sge), len,
sge->offset + apply);
@@ -675,6 +677,7 @@ static int tls_split_open_record(struct sock *sk, struct tls_rec *from,
nsge = sk_msg_elem(msg_npl, j);
if (tmp.length) {
memcpy(nsge, &tmp, sizeof(*nsge));
+ sk_msg_sg_copy_assign(msg_npl, j, msg_opl, tmp_i);
sk_msg_iter_var_next(j);
nsge = sk_msg_elem(msg_npl, j);
}
@@ -682,6 +685,7 @@ static int tls_split_open_record(struct sock *sk, struct tls_rec *from,
osge = sk_msg_elem(msg_opl, i);
while (osge->length) {
memcpy(nsge, osge, sizeof(*nsge));
+ sk_msg_sg_copy_assign(msg_npl, j, msg_opl, i);
sg_unmark_end(nsge);
sk_msg_iter_var_next(i);
sk_msg_iter_var_next(j);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 32892a40d139..8bd78cad69e7 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -3139,6 +3139,9 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
struct sk_buff *skb;
int answ = 0;
+ if (sk->sk_type != SOCK_STREAM)
+ return -EOPNOTSUPP;
+
skb = skb_peek(&sk->sk_receive_queue);
if (skb && skb == READ_ONCE(unix_sk(sk)->oob_skb))
answ = 1;
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 1cdb54c61619..fa6983dc3181 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -583,6 +583,8 @@ static void __unix_gc(struct work_struct *work)
struct sk_buff_head hitlist;
struct sk_buff *skb;
+ WRITE_ONCE(gc_in_progress, true);
+
spin_lock(&unix_gc_lock);
if (!unix_graph_maybe_cyclic) {
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index a9434a72cac4..ad16e25a62ce 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -198,13 +198,15 @@ mksysmap()
sorttable()
{
- ${objtree}/scripts/sorttable ${1}
+ ${NM} -S ${1} > .tmp_vmlinux.nm-sort
+ ${objtree}/scripts/sorttable -s .tmp_vmlinux.nm-sort ${1}
}
# Delete output files in case of error
cleanup()
{
rm -f .btf.*
+ rm -f .tmp_vmlinux.nm-sort
rm -f System.map
rm -f vmlinux
rm -f vmlinux.map
diff --git a/scripts/sorttable.c b/scripts/sorttable.c
index 83cdb843d92f..deed676bfe38 100644
--- a/scripts/sorttable.c
+++ b/scripts/sorttable.c
@@ -28,6 +28,7 @@
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
+#include <stdbool.h>
#include <string.h>
#include <unistd.h>
#include <errno.h>
@@ -64,14 +65,246 @@
#define EM_LOONGARCH 258
#endif
+typedef union {
+ Elf32_Ehdr e32;
+ Elf64_Ehdr e64;
+} Elf_Ehdr;
+
+typedef union {
+ Elf32_Shdr e32;
+ Elf64_Shdr e64;
+} Elf_Shdr;
+
+typedef union {
+ Elf32_Sym e32;
+ Elf64_Sym e64;
+} Elf_Sym;
+
+typedef union {
+ Elf32_Rela e32;
+ Elf64_Rela e64;
+} Elf_Rela;
+
static uint32_t (*r)(const uint32_t *);
static uint16_t (*r2)(const uint16_t *);
static uint64_t (*r8)(const uint64_t *);
static void (*w)(uint32_t, uint32_t *);
-static void (*w2)(uint16_t, uint16_t *);
static void (*w8)(uint64_t, uint64_t *);
typedef void (*table_sort_t)(char *, int);
+static struct elf_funcs {
+ int (*compare_extable)(const void *a, const void *b);
+ uint64_t (*ehdr_shoff)(Elf_Ehdr *ehdr);
+ uint16_t (*ehdr_shstrndx)(Elf_Ehdr *ehdr);
+ uint16_t (*ehdr_shentsize)(Elf_Ehdr *ehdr);
+ uint16_t (*ehdr_shnum)(Elf_Ehdr *ehdr);
+ uint64_t (*shdr_addr)(Elf_Shdr *shdr);
+ uint64_t (*shdr_offset)(Elf_Shdr *shdr);
+ uint64_t (*shdr_size)(Elf_Shdr *shdr);
+ uint64_t (*shdr_entsize)(Elf_Shdr *shdr);
+ uint32_t (*shdr_link)(Elf_Shdr *shdr);
+ uint32_t (*shdr_name)(Elf_Shdr *shdr);
+ uint32_t (*shdr_type)(Elf_Shdr *shdr);
+ uint8_t (*sym_type)(Elf_Sym *sym);
+ uint32_t (*sym_name)(Elf_Sym *sym);
+ uint64_t (*sym_value)(Elf_Sym *sym);
+ uint16_t (*sym_shndx)(Elf_Sym *sym);
+ uint64_t (*rela_offset)(Elf_Rela *rela);
+ uint64_t (*rela_info)(Elf_Rela *rela);
+ uint64_t (*rela_addend)(Elf_Rela *rela);
+ void (*rela_write_addend)(Elf_Rela *rela, uint64_t val);
+} e;
+
+static uint64_t ehdr64_shoff(Elf_Ehdr *ehdr)
+{
+ return r8(&ehdr->e64.e_shoff);
+}
+
+static uint64_t ehdr32_shoff(Elf_Ehdr *ehdr)
+{
+ return r(&ehdr->e32.e_shoff);
+}
+
+static uint64_t ehdr_shoff(Elf_Ehdr *ehdr)
+{
+ return e.ehdr_shoff(ehdr);
+}
+
+#define EHDR_HALF(fn_name) \
+static uint16_t ehdr64_##fn_name(Elf_Ehdr *ehdr) \
+{ \
+ return r2(&ehdr->e64.e_##fn_name); \
+} \
+ \
+static uint16_t ehdr32_##fn_name(Elf_Ehdr *ehdr) \
+{ \
+ return r2(&ehdr->e32.e_##fn_name); \
+} \
+ \
+static uint16_t ehdr_##fn_name(Elf_Ehdr *ehdr) \
+{ \
+ return e.ehdr_##fn_name(ehdr); \
+}
+
+EHDR_HALF(shentsize)
+EHDR_HALF(shstrndx)
+EHDR_HALF(shnum)
+
+#define SHDR_WORD(fn_name) \
+static uint32_t shdr64_##fn_name(Elf_Shdr *shdr) \
+{ \
+ return r(&shdr->e64.sh_##fn_name); \
+} \
+ \
+static uint32_t shdr32_##fn_name(Elf_Shdr *shdr) \
+{ \
+ return r(&shdr->e32.sh_##fn_name); \
+} \
+ \
+static uint32_t shdr_##fn_name(Elf_Shdr *shdr) \
+{ \
+ return e.shdr_##fn_name(shdr); \
+}
+
+#define SHDR_ADDR(fn_name) \
+static uint64_t shdr64_##fn_name(Elf_Shdr *shdr) \
+{ \
+ return r8(&shdr->e64.sh_##fn_name); \
+} \
+ \
+static uint64_t shdr32_##fn_name(Elf_Shdr *shdr) \
+{ \
+ return r(&shdr->e32.sh_##fn_name); \
+} \
+ \
+static uint64_t shdr_##fn_name(Elf_Shdr *shdr) \
+{ \
+ return e.shdr_##fn_name(shdr); \
+}
+
+#define SHDR_WORD(fn_name) \
+static uint32_t shdr64_##fn_name(Elf_Shdr *shdr) \
+{ \
+ return r(&shdr->e64.sh_##fn_name); \
+} \
+ \
+static uint32_t shdr32_##fn_name(Elf_Shdr *shdr) \
+{ \
+ return r(&shdr->e32.sh_##fn_name); \
+} \
+static uint32_t shdr_##fn_name(Elf_Shdr *shdr) \
+{ \
+ return e.shdr_##fn_name(shdr); \
+}
+
+SHDR_ADDR(addr)
+SHDR_ADDR(offset)
+SHDR_ADDR(size)
+SHDR_ADDR(entsize)
+
+SHDR_WORD(link)
+SHDR_WORD(name)
+SHDR_WORD(type)
+
+#define SYM_ADDR(fn_name) \
+static uint64_t sym64_##fn_name(Elf_Sym *sym) \
+{ \
+ return r8(&sym->e64.st_##fn_name); \
+} \
+ \
+static uint64_t sym32_##fn_name(Elf_Sym *sym) \
+{ \
+ return r(&sym->e32.st_##fn_name); \
+} \
+ \
+static uint64_t sym_##fn_name(Elf_Sym *sym) \
+{ \
+ return e.sym_##fn_name(sym); \
+}
+
+#define SYM_WORD(fn_name) \
+static uint32_t sym64_##fn_name(Elf_Sym *sym) \
+{ \
+ return r(&sym->e64.st_##fn_name); \
+} \
+ \
+static uint32_t sym32_##fn_name(Elf_Sym *sym) \
+{ \
+ return r(&sym->e32.st_##fn_name); \
+} \
+ \
+static uint32_t sym_##fn_name(Elf_Sym *sym) \
+{ \
+ return e.sym_##fn_name(sym); \
+}
+
+#define SYM_HALF(fn_name) \
+static uint16_t sym64_##fn_name(Elf_Sym *sym) \
+{ \
+ return r2(&sym->e64.st_##fn_name); \
+} \
+ \
+static uint16_t sym32_##fn_name(Elf_Sym *sym) \
+{ \
+ return r2(&sym->e32.st_##fn_name); \
+} \
+ \
+static uint16_t sym_##fn_name(Elf_Sym *sym) \
+{ \
+ return e.sym_##fn_name(sym); \
+}
+
+static uint8_t sym64_type(Elf_Sym *sym)
+{
+ return ELF64_ST_TYPE(sym->e64.st_info);
+}
+
+static uint8_t sym32_type(Elf_Sym *sym)
+{
+ return ELF32_ST_TYPE(sym->e32.st_info);
+}
+
+static uint8_t sym_type(Elf_Sym *sym)
+{
+ return e.sym_type(sym);
+}
+
+SYM_ADDR(value)
+SYM_WORD(name)
+SYM_HALF(shndx)
+
+#define __maybe_unused __attribute__((__unused__))
+
+#define RELA_ADDR(fn_name) \
+static uint64_t rela64_##fn_name(Elf_Rela *rela) \
+{ \
+ return r8((uint64_t *)&rela->e64.r_##fn_name); \
+} \
+ \
+static uint64_t rela32_##fn_name(Elf_Rela *rela) \
+{ \
+ return r((uint32_t *)&rela->e32.r_##fn_name); \
+} \
+ \
+static uint64_t __maybe_unused rela_##fn_name(Elf_Rela *rela) \
+{ \
+ return e.rela_##fn_name(rela); \
+}
+
+RELA_ADDR(offset)
+RELA_ADDR(info)
+RELA_ADDR(addend)
+
+static void rela64_write_addend(Elf_Rela *rela, uint64_t val)
+{
+ w8(val, (uint64_t *)&rela->e64.r_addend);
+}
+
+static void rela32_write_addend(Elf_Rela *rela, uint64_t val)
+{
+ w(val, (uint32_t *)&rela->e32.r_addend);
+}
+
/*
* Get the whole file as a programming convenience in order to avoid
* malloc+lseek+read+free of many pieces. If successful, then mmap
@@ -146,24 +379,14 @@ static void wbe(uint32_t val, uint32_t *x)
put_unaligned_be32(val, x);
}
-static void w2be(uint16_t val, uint16_t *x)
-{
- put_unaligned_be16(val, x);
-}
-
-static void w8be(uint64_t val, uint64_t *x)
-{
- put_unaligned_be64(val, x);
-}
-
static void wle(uint32_t val, uint32_t *x)
{
put_unaligned_le32(val, x);
}
-static void w2le(uint16_t val, uint16_t *x)
+static void w8be(uint64_t val, uint64_t *x)
{
- put_unaligned_le16(val, x);
+ put_unaligned_be64(val, x);
}
static void w8le(uint64_t val, uint64_t *x)
@@ -195,10 +418,740 @@ static inline unsigned int get_secindex(unsigned int shndx,
return r(&symtab_shndx_start[sym_offs]);
}
-/* 32 bit and 64 bit are very similar */
-#include "sorttable.h"
-#define SORTTABLE_64
-#include "sorttable.h"
+static int compare_extable_32(const void *a, const void *b)
+{
+ Elf32_Addr av = r(a);
+ Elf32_Addr bv = r(b);
+
+ if (av < bv)
+ return -1;
+ return av > bv;
+}
+
+static int compare_extable_64(const void *a, const void *b)
+{
+ Elf64_Addr av = r8(a);
+ Elf64_Addr bv = r8(b);
+
+ if (av < bv)
+ return -1;
+ return av > bv;
+}
+
+static int compare_extable(const void *a, const void *b)
+{
+ return e.compare_extable(a, b);
+}
+
+static inline void *get_index(void *start, int entsize, int index)
+{
+ return start + (entsize * index);
+}
+
+static int extable_ent_size;
+static int long_size;
+
+#define ERRSTR_MAXSZ 256
+
+#ifdef UNWINDER_ORC_ENABLED
+/* ORC unwinder only support X86_64 */
+#include <asm/orc_types.h>
+
+static char g_err[ERRSTR_MAXSZ];
+static int *g_orc_ip_table;
+static struct orc_entry *g_orc_table;
+
+static pthread_t orc_sort_thread;
+
+static inline unsigned long orc_ip(const int *ip)
+{
+ return (unsigned long)ip + *ip;
+}
+
+static int orc_sort_cmp(const void *_a, const void *_b)
+{
+ struct orc_entry *orc_a, *orc_b;
+ const int *a = g_orc_ip_table + *(int *)_a;
+ const int *b = g_orc_ip_table + *(int *)_b;
+ unsigned long a_val = orc_ip(a);
+ unsigned long b_val = orc_ip(b);
+
+ if (a_val > b_val)
+ return 1;
+ if (a_val < b_val)
+ return -1;
+
+ /*
+ * The "weak" section terminator entries need to always be on the left
+ * to ensure the lookup code skips them in favor of real entries.
+ * These terminator entries exist to handle any gaps created by
+ * whitelisted .o files which didn't get objtool generation.
+ */
+ orc_a = g_orc_table + (a - g_orc_ip_table);
+ orc_b = g_orc_table + (b - g_orc_ip_table);
+ if (orc_a->type == ORC_TYPE_UNDEFINED && orc_b->type == ORC_TYPE_UNDEFINED)
+ return 0;
+ return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1;
+}
+
+static void *sort_orctable(void *arg)
+{
+ int i;
+ int *idxs = NULL;
+ int *tmp_orc_ip_table = NULL;
+ struct orc_entry *tmp_orc_table = NULL;
+ unsigned int *orc_ip_size = (unsigned int *)arg;
+ unsigned int num_entries = *orc_ip_size / sizeof(int);
+ unsigned int orc_size = num_entries * sizeof(struct orc_entry);
+
+ idxs = (int *)malloc(*orc_ip_size);
+ if (!idxs) {
+ snprintf(g_err, ERRSTR_MAXSZ, "malloc idxs: %s",
+ strerror(errno));
+ pthread_exit(g_err);
+ }
+
+ tmp_orc_ip_table = (int *)malloc(*orc_ip_size);
+ if (!tmp_orc_ip_table) {
+ snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_ip_table: %s",
+ strerror(errno));
+ pthread_exit(g_err);
+ }
+
+ tmp_orc_table = (struct orc_entry *)malloc(orc_size);
+ if (!tmp_orc_table) {
+ snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_table: %s",
+ strerror(errno));
+ pthread_exit(g_err);
+ }
+
+ /* initialize indices array, convert ip_table to absolute address */
+ for (i = 0; i < num_entries; i++) {
+ idxs[i] = i;
+ tmp_orc_ip_table[i] = g_orc_ip_table[i] + i * sizeof(int);
+ }
+ memcpy(tmp_orc_table, g_orc_table, orc_size);
+
+ qsort(idxs, num_entries, sizeof(int), orc_sort_cmp);
+
+ for (i = 0; i < num_entries; i++) {
+ if (idxs[i] == i)
+ continue;
+
+ /* convert back to relative address */
+ g_orc_ip_table[i] = tmp_orc_ip_table[idxs[i]] - i * sizeof(int);
+ g_orc_table[i] = tmp_orc_table[idxs[i]];
+ }
+
+ free(idxs);
+ free(tmp_orc_ip_table);
+ free(tmp_orc_table);
+ pthread_exit(NULL);
+}
+#endif
+
+#ifdef MCOUNT_SORT_ENABLED
+
+static int compare_values_64(const void *a, const void *b)
+{
+ uint64_t av = *(uint64_t *)a;
+ uint64_t bv = *(uint64_t *)b;
+
+ if (av < bv)
+ return -1;
+ return av > bv;
+}
+
+static int compare_values_32(const void *a, const void *b)
+{
+ uint32_t av = *(uint32_t *)a;
+ uint32_t bv = *(uint32_t *)b;
+
+ if (av < bv)
+ return -1;
+ return av > bv;
+}
+
+static int (*compare_values)(const void *a, const void *b);
+
+/* Only used for sorting mcount table */
+static void rela_write_addend(Elf_Rela *rela, uint64_t val)
+{
+ e.rela_write_addend(rela, val);
+}
+
+struct func_info {
+ uint64_t addr;
+ uint64_t size;
+};
+
+/* List of functions created by: nm -S vmlinux */
+static struct func_info *function_list;
+static int function_list_size;
+
+/* Allocate functions in 1k blocks */
+#define FUNC_BLK_SIZE 1024
+#define FUNC_BLK_MASK (FUNC_BLK_SIZE - 1)
+
+static int add_field(uint64_t addr, uint64_t size)
+{
+ struct func_info *fi;
+ int fsize = function_list_size;
+
+ if (!(fsize & FUNC_BLK_MASK)) {
+ fsize += FUNC_BLK_SIZE;
+ fi = realloc(function_list, fsize * sizeof(struct func_info));
+ if (!fi)
+ return -1;
+ function_list = fi;
+ }
+ fi = &function_list[function_list_size++];
+ fi->addr = addr;
+ fi->size = size;
+ return 0;
+}
+
+/* Used for when mcount/fentry is before the function entry */
+static int before_func;
+
+/* Only return match if the address lies inside the function size */
+static int cmp_func_addr(const void *K, const void *A)
+{
+ uint64_t key = *(const uint64_t *)K;
+ const struct func_info *a = A;
+
+ if (key + before_func < a->addr)
+ return -1;
+ return key >= a->addr + a->size;
+}
+
+/* Find the function in function list that is bounded by the function size */
+static int find_func(uint64_t key)
+{
+ return bsearch(&key, function_list, function_list_size,
+ sizeof(struct func_info), cmp_func_addr) != NULL;
+}
+
+static int cmp_funcs(const void *A, const void *B)
+{
+ const struct func_info *a = A;
+ const struct func_info *b = B;
+
+ if (a->addr < b->addr)
+ return -1;
+ return a->addr > b->addr;
+}
+
+static int parse_symbols(const char *fname)
+{
+ FILE *fp;
+ char addr_str[20]; /* Only need 17, but round up to next int size */
+ char size_str[20];
+ char type;
+
+ fp = fopen(fname, "r");
+ if (!fp) {
+ perror(fname);
+ return -1;
+ }
+
+ while (fscanf(fp, "%16s %16s %c %*s\n", addr_str, size_str, &type) == 3) {
+ uint64_t addr;
+ uint64_t size;
+
+ /* Only care about functions */
+ if (type != 't' && type != 'T' && type != 'W')
+ continue;
+
+ addr = strtoull(addr_str, NULL, 16);
+ size = strtoull(size_str, NULL, 16);
+ if (add_field(addr, size) < 0)
+ return -1;
+ }
+ fclose(fp);
+
+ qsort(function_list, function_list_size, sizeof(struct func_info), cmp_funcs);
+
+ return 0;
+}
+
+static pthread_t mcount_sort_thread;
+static bool sort_reloc;
+
+static long rela_type;
+
+static char m_err[ERRSTR_MAXSZ];
+
+struct elf_mcount_loc {
+ Elf_Ehdr *ehdr;
+ Elf_Shdr *init_data_sec;
+ uint64_t start_mcount_loc;
+ uint64_t stop_mcount_loc;
+};
+
+/* Fill the array with the content of the relocs */
+static int fill_relocs(void *ptr, uint64_t size, Elf_Ehdr *ehdr, uint64_t start_loc)
+{
+ Elf_Shdr *shdr_start;
+ Elf_Rela *rel;
+ unsigned int shnum;
+ unsigned int count = 0;
+ int shentsize;
+ void *array_end = ptr + size;
+
+ shdr_start = (Elf_Shdr *)((char *)ehdr + ehdr_shoff(ehdr));
+ shentsize = ehdr_shentsize(ehdr);
+
+ shnum = ehdr_shnum(ehdr);
+ if (shnum == SHN_UNDEF)
+ shnum = shdr_size(shdr_start);
+
+ for (int i = 0; i < shnum; i++) {
+ Elf_Shdr *shdr = get_index(shdr_start, shentsize, i);
+ void *end;
+
+ if (shdr_type(shdr) != SHT_RELA)
+ continue;
+
+ rel = (void *)ehdr + shdr_offset(shdr);
+ end = (void *)rel + shdr_size(shdr);
+
+ for (; (void *)rel < end; rel = (void *)rel + shdr_entsize(shdr)) {
+ uint64_t offset = rela_offset(rel);
+
+ if (offset >= start_loc && offset < start_loc + size) {
+ if (ptr + long_size > array_end) {
+ snprintf(m_err, ERRSTR_MAXSZ,
+ "Too many relocations");
+ return -1;
+ }
+
+ /* Make sure this has the correct type */
+ if (rela_info(rel) != rela_type) {
+ snprintf(m_err, ERRSTR_MAXSZ,
+ "rela has type %lx but expected %lx\n",
+ (long)rela_info(rel), rela_type);
+ return -1;
+ }
+
+ if (long_size == 4)
+ *(uint32_t *)ptr = rela_addend(rel);
+ else
+ *(uint64_t *)ptr = rela_addend(rel);
+ ptr += long_size;
+ count++;
+ }
+ }
+ }
+ return count;
+}
+
+/* Put the sorted vals back into the relocation elements */
+static void replace_relocs(void *ptr, uint64_t size, Elf_Ehdr *ehdr, uint64_t start_loc)
+{
+ Elf_Shdr *shdr_start;
+ Elf_Rela *rel;
+ unsigned int shnum;
+ int shentsize;
+
+ shdr_start = (Elf_Shdr *)((char *)ehdr + ehdr_shoff(ehdr));
+ shentsize = ehdr_shentsize(ehdr);
+
+ shnum = ehdr_shnum(ehdr);
+ if (shnum == SHN_UNDEF)
+ shnum = shdr_size(shdr_start);
+
+ for (int i = 0; i < shnum; i++) {
+ Elf_Shdr *shdr = get_index(shdr_start, shentsize, i);
+ void *end;
+
+ if (shdr_type(shdr) != SHT_RELA)
+ continue;
+
+ rel = (void *)ehdr + shdr_offset(shdr);
+ end = (void *)rel + shdr_size(shdr);
+
+ for (; (void *)rel < end; rel = (void *)rel + shdr_entsize(shdr)) {
+ uint64_t offset = rela_offset(rel);
+
+ if (offset >= start_loc && offset < start_loc + size) {
+ if (long_size == 4)
+ rela_write_addend(rel, *(uint32_t *)ptr);
+ else
+ rela_write_addend(rel, *(uint64_t *)ptr);
+ ptr += long_size;
+ }
+ }
+ }
+}
+
+static int fill_addrs(void *ptr, uint64_t size, void *addrs)
+{
+ void *end = ptr + size;
+ int count = 0;
+
+ for (; ptr < end; ptr += long_size, addrs += long_size, count++) {
+ if (long_size == 4)
+ *(uint32_t *)ptr = r(addrs);
+ else
+ *(uint64_t *)ptr = r8(addrs);
+ }
+ return count;
+}
+
+static void replace_addrs(void *ptr, uint64_t size, void *addrs)
+{
+ void *end = ptr + size;
+
+ for (; ptr < end; ptr += long_size, addrs += long_size) {
+ if (long_size == 4)
+ w(*(uint32_t *)ptr, addrs);
+ else
+ w8(*(uint64_t *)ptr, addrs);
+ }
+}
+
+/* Sort the addresses stored between __start_mcount_loc to __stop_mcount_loc in vmlinux */
+static void *sort_mcount_loc(void *arg)
+{
+ struct elf_mcount_loc *emloc = (struct elf_mcount_loc *)arg;
+ uint64_t offset = emloc->start_mcount_loc - shdr_addr(emloc->init_data_sec)
+ + shdr_offset(emloc->init_data_sec);
+ uint64_t size = emloc->stop_mcount_loc - emloc->start_mcount_loc;
+ unsigned char *start_loc = (void *)emloc->ehdr + offset;
+ Elf_Ehdr *ehdr = emloc->ehdr;
+ void *e_msg = NULL;
+ void *vals;
+ int count;
+
+ vals = malloc(long_size * size);
+ if (!vals) {
+ snprintf(m_err, ERRSTR_MAXSZ, "Failed to allocate sort array");
+ pthread_exit(m_err);
+ }
+
+ if (sort_reloc) {
+ count = fill_relocs(vals, size, ehdr, emloc->start_mcount_loc);
+ /* gcc may use relocs to save the addresses, but clang does not. */
+ if (!count) {
+ count = fill_addrs(vals, size, start_loc);
+ sort_reloc = 0;
+ }
+ } else
+ count = fill_addrs(vals, size, start_loc);
+
+ if (count < 0) {
+ e_msg = m_err;
+ goto out;
+ }
+
+ if (count != size / long_size) {
+ snprintf(m_err, ERRSTR_MAXSZ, "Expected %u mcount elements but found %u\n",
+ (int)(size / long_size), count);
+ e_msg = m_err;
+ goto out;
+ }
+
+ /* zero out any locations not found by function list */
+ if (function_list_size) {
+ for (void *ptr = vals; ptr < vals + size; ptr += long_size) {
+ uint64_t key;
+
+ key = long_size == 4 ? *(uint32_t *)ptr : *(uint64_t *)ptr;
+ if (!find_func(key)) {
+ if (long_size == 4)
+ *(uint32_t *)ptr = 0;
+ else
+ *(uint64_t *)ptr = 0;
+ }
+ }
+ }
+
+ compare_values = long_size == 4 ? compare_values_32 : compare_values_64;
+
+ qsort(vals, count, long_size, compare_values);
+
+ if (sort_reloc)
+ replace_relocs(vals, size, ehdr, emloc->start_mcount_loc);
+ else
+ replace_addrs(vals, size, start_loc);
+
+out:
+ free(vals);
+
+ pthread_exit(e_msg);
+}
+
+/* Get the address of __start_mcount_loc and __stop_mcount_loc in System.map */
+static void get_mcount_loc(struct elf_mcount_loc *emloc, Elf_Shdr *symtab_sec,
+ const char *strtab)
+{
+ Elf_Sym *sym, *end_sym;
+ int symentsize = shdr_entsize(symtab_sec);
+ int found = 0;
+
+ sym = (void *)emloc->ehdr + shdr_offset(symtab_sec);
+ end_sym = (void *)sym + shdr_size(symtab_sec);
+
+ while (sym < end_sym) {
+ if (!strcmp(strtab + sym_name(sym), "__start_mcount_loc")) {
+ emloc->start_mcount_loc = sym_value(sym);
+ if (++found == 2)
+ break;
+ } else if (!strcmp(strtab + sym_name(sym), "__stop_mcount_loc")) {
+ emloc->stop_mcount_loc = sym_value(sym);
+ if (++found == 2)
+ break;
+ }
+ sym = (void *)sym + symentsize;
+ }
+
+ if (!emloc->start_mcount_loc) {
+ fprintf(stderr, "get start_mcount_loc error!");
+ return;
+ }
+
+ if (!emloc->stop_mcount_loc) {
+ fprintf(stderr, "get stop_mcount_loc error!");
+ return;
+ }
+}
+#else /* MCOUNT_SORT_ENABLED */
+static inline int parse_symbols(const char *fname) { return 0; }
+#endif
+
+static int do_sort(Elf_Ehdr *ehdr,
+ char const *const fname,
+ table_sort_t custom_sort)
+{
+ int rc = -1;
+ Elf_Shdr *shdr_start;
+ Elf_Shdr *strtab_sec = NULL;
+ Elf_Shdr *symtab_sec = NULL;
+ Elf_Shdr *extab_sec = NULL;
+ Elf_Shdr *string_sec;
+ Elf_Sym *sym;
+ const Elf_Sym *symtab;
+ Elf32_Word *symtab_shndx = NULL;
+ Elf_Sym *sort_needed_sym = NULL;
+ Elf_Shdr *sort_needed_sec;
+ uint32_t *sort_needed_loc;
+ void *sym_start;
+ void *sym_end;
+ const char *secstrings;
+ const char *strtab;
+ char *extab_image;
+ int sort_need_index;
+ int symentsize;
+ int shentsize;
+ int idx;
+ int i;
+ unsigned int shnum;
+ unsigned int shstrndx;
+#ifdef MCOUNT_SORT_ENABLED
+ struct elf_mcount_loc mstruct = {0};
+#endif
+#ifdef UNWINDER_ORC_ENABLED
+ unsigned int orc_ip_size = 0;
+ unsigned int orc_size = 0;
+ unsigned int orc_num_entries = 0;
+#endif
+
+ shdr_start = (Elf_Shdr *)((char *)ehdr + ehdr_shoff(ehdr));
+ shentsize = ehdr_shentsize(ehdr);
+
+ shstrndx = ehdr_shstrndx(ehdr);
+ if (shstrndx == SHN_XINDEX)
+ shstrndx = shdr_link(shdr_start);
+ string_sec = get_index(shdr_start, shentsize, shstrndx);
+ secstrings = (const char *)ehdr + shdr_offset(string_sec);
+
+ shnum = ehdr_shnum(ehdr);
+ if (shnum == SHN_UNDEF)
+ shnum = shdr_size(shdr_start);
+
+ for (i = 0; i < shnum; i++) {
+ Elf_Shdr *shdr = get_index(shdr_start, shentsize, i);
+
+ idx = shdr_name(shdr);
+ if (!strcmp(secstrings + idx, "__ex_table"))
+ extab_sec = shdr;
+ if (!strcmp(secstrings + idx, ".symtab"))
+ symtab_sec = shdr;
+ if (!strcmp(secstrings + idx, ".strtab"))
+ strtab_sec = shdr;
+
+ if (shdr_type(shdr) == SHT_SYMTAB_SHNDX)
+ symtab_shndx = (Elf32_Word *)((const char *)ehdr +
+ shdr_offset(shdr));
+
+#ifdef MCOUNT_SORT_ENABLED
+ /* locate the .init.data section in vmlinux */
+ if (!strcmp(secstrings + idx, ".init.data"))
+ mstruct.init_data_sec = shdr;
+#endif
+
+#ifdef UNWINDER_ORC_ENABLED
+ /* locate the ORC unwind tables */
+ if (!strcmp(secstrings + idx, ".orc_unwind_ip")) {
+ orc_ip_size = shdr_size(shdr);
+ g_orc_ip_table = (int *)((void *)ehdr +
+ shdr_offset(shdr));
+ }
+ if (!strcmp(secstrings + idx, ".orc_unwind")) {
+ orc_size = shdr_size(shdr);
+ g_orc_table = (struct orc_entry *)((void *)ehdr +
+ shdr_offset(shdr));
+ }
+#endif
+ } /* for loop */
+
+#ifdef UNWINDER_ORC_ENABLED
+ if (!g_orc_ip_table || !g_orc_table) {
+ fprintf(stderr,
+ "incomplete ORC unwind tables in file: %s\n", fname);
+ goto out;
+ }
+
+ orc_num_entries = orc_ip_size / sizeof(int);
+ if (orc_ip_size % sizeof(int) != 0 ||
+ orc_size % sizeof(struct orc_entry) != 0 ||
+ orc_num_entries != orc_size / sizeof(struct orc_entry)) {
+ fprintf(stderr,
+ "inconsistent ORC unwind table entries in file: %s\n",
+ fname);
+ goto out;
+ }
+
+ /* create thread to sort ORC unwind tables concurrently */
+ if (pthread_create(&orc_sort_thread, NULL,
+ sort_orctable, &orc_ip_size)) {
+ fprintf(stderr,
+ "pthread_create orc_sort_thread failed '%s': %s\n",
+ strerror(errno), fname);
+ goto out;
+ }
+#endif
+ if (!extab_sec) {
+ fprintf(stderr, "no __ex_table in file: %s\n", fname);
+ goto out;
+ }
+
+ if (!symtab_sec) {
+ fprintf(stderr, "no .symtab in file: %s\n", fname);
+ goto out;
+ }
+
+ if (!strtab_sec) {
+ fprintf(stderr, "no .strtab in file: %s\n", fname);
+ goto out;
+ }
+
+ extab_image = (void *)ehdr + shdr_offset(extab_sec);
+ strtab = (const char *)ehdr + shdr_offset(strtab_sec);
+ symtab = (const Elf_Sym *)((const char *)ehdr + shdr_offset(symtab_sec));
+
+#ifdef MCOUNT_SORT_ENABLED
+ mstruct.ehdr = ehdr;
+ get_mcount_loc(&mstruct, symtab_sec, strtab);
+
+ if (!mstruct.init_data_sec || !mstruct.start_mcount_loc || !mstruct.stop_mcount_loc) {
+ fprintf(stderr,
+ "incomplete mcount's sort in file: %s\n",
+ fname);
+ goto out;
+ }
+
+ /* create thread to sort mcount_loc concurrently */
+ if (pthread_create(&mcount_sort_thread, NULL, &sort_mcount_loc, &mstruct)) {
+ fprintf(stderr,
+ "pthread_create mcount_sort_thread failed '%s': %s\n",
+ strerror(errno), fname);
+ goto out;
+ }
+#endif
+
+ if (custom_sort) {
+ custom_sort(extab_image, shdr_size(extab_sec));
+ } else {
+ int num_entries = shdr_size(extab_sec) / extable_ent_size;
+ qsort(extab_image, num_entries,
+ extable_ent_size, compare_extable);
+ }
+
+ /* find the flag main_extable_sort_needed */
+ sym_start = (void *)ehdr + shdr_offset(symtab_sec);
+ sym_end = sym_start + shdr_size(symtab_sec);
+ symentsize = shdr_entsize(symtab_sec);
+
+ for (sym = sym_start; (void *)sym + symentsize < sym_end;
+ sym = (void *)sym + symentsize) {
+ if (sym_type(sym) != STT_OBJECT)
+ continue;
+ if (!strcmp(strtab + sym_name(sym),
+ "main_extable_sort_needed")) {
+ sort_needed_sym = sym;
+ break;
+ }
+ }
+
+ if (!sort_needed_sym) {
+ fprintf(stderr,
+ "no main_extable_sort_needed symbol in file: %s\n",
+ fname);
+ goto out;
+ }
+
+ sort_need_index = get_secindex(sym_shndx(sym),
+ ((void *)sort_needed_sym - (void *)symtab) / symentsize,
+ symtab_shndx);
+ sort_needed_sec = get_index(shdr_start, shentsize, sort_need_index);
+ sort_needed_loc = (void *)ehdr +
+ shdr_offset(sort_needed_sec) +
+ sym_value(sort_needed_sym) - shdr_addr(sort_needed_sec);
+
+ /* extable has been sorted, clear the flag */
+ w(0, sort_needed_loc);
+ rc = 0;
+
+out:
+#ifdef UNWINDER_ORC_ENABLED
+ if (orc_sort_thread) {
+ void *retval = NULL;
+ /* wait for ORC tables sort done */
+ rc = pthread_join(orc_sort_thread, &retval);
+ if (rc) {
+ fprintf(stderr,
+ "pthread_join failed '%s': %s\n",
+ strerror(errno), fname);
+ } else if (retval) {
+ rc = -1;
+ fprintf(stderr,
+ "failed to sort ORC tables '%s': %s\n",
+ (char *)retval, fname);
+ }
+ }
+#endif
+
+#ifdef MCOUNT_SORT_ENABLED
+ if (mcount_sort_thread) {
+ void *retval = NULL;
+ /* wait for mcount sort done */
+ rc = pthread_join(mcount_sort_thread, &retval);
+ if (rc) {
+ fprintf(stderr,
+ "pthread_join failed '%s': %s\n",
+ strerror(errno), fname);
+ } else if (retval) {
+ rc = -1;
+ fprintf(stderr,
+ "failed to sort mcount '%s': %s\n",
+ (char *)retval, fname);
+ }
+ }
+#endif
+ return rc;
+}
static int compare_relative_table(const void *a, const void *b)
{
@@ -267,17 +1220,15 @@ static void sort_relative_table_with_data(char *extab_image, int image_size)
static int do_file(char const *const fname, void *addr)
{
- int rc = -1;
- Elf32_Ehdr *ehdr = addr;
+ Elf_Ehdr *ehdr = addr;
table_sort_t custom_sort = NULL;
- switch (ehdr->e_ident[EI_DATA]) {
+ switch (ehdr->e32.e_ident[EI_DATA]) {
case ELFDATA2LSB:
r = rle;
r2 = r2le;
r8 = r8le;
w = wle;
- w2 = w2le;
w8 = w8le;
break;
case ELFDATA2MSB:
@@ -285,25 +1236,31 @@ static int do_file(char const *const fname, void *addr)
r2 = r2be;
r8 = r8be;
w = wbe;
- w2 = w2be;
w8 = w8be;
break;
default:
fprintf(stderr, "unrecognized ELF data encoding %d: %s\n",
- ehdr->e_ident[EI_DATA], fname);
+ ehdr->e32.e_ident[EI_DATA], fname);
return -1;
}
- if (memcmp(ELFMAG, ehdr->e_ident, SELFMAG) != 0 ||
- (r2(&ehdr->e_type) != ET_EXEC && r2(&ehdr->e_type) != ET_DYN) ||
- ehdr->e_ident[EI_VERSION] != EV_CURRENT) {
+ if (memcmp(ELFMAG, ehdr->e32.e_ident, SELFMAG) != 0 ||
+ (r2(&ehdr->e32.e_type) != ET_EXEC && r2(&ehdr->e32.e_type) != ET_DYN) ||
+ ehdr->e32.e_ident[EI_VERSION] != EV_CURRENT) {
fprintf(stderr, "unrecognized ET_EXEC/ET_DYN file %s\n", fname);
return -1;
}
- switch (r2(&ehdr->e_machine)) {
- case EM_386:
+ switch (r2(&ehdr->e32.e_machine)) {
case EM_AARCH64:
+#ifdef MCOUNT_SORT_ENABLED
+ sort_reloc = true;
+ rela_type = 0x403;
+ /* arm64 uses patchable function entry placing before function */
+ before_func = 8;
+#endif
+ /* fallthrough */
+ case EM_386:
case EM_LOONGARCH:
case EM_RISCV:
case EM_S390:
@@ -324,40 +1281,93 @@ static int do_file(char const *const fname, void *addr)
break;
default:
fprintf(stderr, "unrecognized e_machine %d %s\n",
- r2(&ehdr->e_machine), fname);
+ r2(&ehdr->e32.e_machine), fname);
return -1;
}
- switch (ehdr->e_ident[EI_CLASS]) {
- case ELFCLASS32:
- if (r2(&ehdr->e_ehsize) != sizeof(Elf32_Ehdr) ||
- r2(&ehdr->e_shentsize) != sizeof(Elf32_Shdr)) {
+ switch (ehdr->e32.e_ident[EI_CLASS]) {
+ case ELFCLASS32: {
+ struct elf_funcs efuncs = {
+ .compare_extable = compare_extable_32,
+ .ehdr_shoff = ehdr32_shoff,
+ .ehdr_shentsize = ehdr32_shentsize,
+ .ehdr_shstrndx = ehdr32_shstrndx,
+ .ehdr_shnum = ehdr32_shnum,
+ .shdr_addr = shdr32_addr,
+ .shdr_offset = shdr32_offset,
+ .shdr_link = shdr32_link,
+ .shdr_size = shdr32_size,
+ .shdr_name = shdr32_name,
+ .shdr_type = shdr32_type,
+ .shdr_entsize = shdr32_entsize,
+ .sym_type = sym32_type,
+ .sym_name = sym32_name,
+ .sym_value = sym32_value,
+ .sym_shndx = sym32_shndx,
+ .rela_offset = rela32_offset,
+ .rela_info = rela32_info,
+ .rela_addend = rela32_addend,
+ .rela_write_addend = rela32_write_addend,
+ };
+
+ e = efuncs;
+ long_size = 4;
+ extable_ent_size = 8;
+
+ if (r2(&ehdr->e32.e_ehsize) != sizeof(Elf32_Ehdr) ||
+ r2(&ehdr->e32.e_shentsize) != sizeof(Elf32_Shdr)) {
fprintf(stderr,
"unrecognized ET_EXEC/ET_DYN file: %s\n", fname);
- break;
+ return -1;
+ }
+
}
- rc = do_sort_32(ehdr, fname, custom_sort);
break;
- case ELFCLASS64:
- {
- Elf64_Ehdr *const ghdr = (Elf64_Ehdr *)ehdr;
- if (r2(&ghdr->e_ehsize) != sizeof(Elf64_Ehdr) ||
- r2(&ghdr->e_shentsize) != sizeof(Elf64_Shdr)) {
+ case ELFCLASS64: {
+ struct elf_funcs efuncs = {
+ .compare_extable = compare_extable_64,
+ .ehdr_shoff = ehdr64_shoff,
+ .ehdr_shentsize = ehdr64_shentsize,
+ .ehdr_shstrndx = ehdr64_shstrndx,
+ .ehdr_shnum = ehdr64_shnum,
+ .shdr_addr = shdr64_addr,
+ .shdr_offset = shdr64_offset,
+ .shdr_link = shdr64_link,
+ .shdr_size = shdr64_size,
+ .shdr_name = shdr64_name,
+ .shdr_type = shdr64_type,
+ .shdr_entsize = shdr64_entsize,
+ .sym_type = sym64_type,
+ .sym_name = sym64_name,
+ .sym_value = sym64_value,
+ .sym_shndx = sym64_shndx,
+ .rela_offset = rela64_offset,
+ .rela_info = rela64_info,
+ .rela_addend = rela64_addend,
+ .rela_write_addend = rela64_write_addend,
+ };
+
+ e = efuncs;
+ long_size = 8;
+ extable_ent_size = 16;
+
+ if (r2(&ehdr->e64.e_ehsize) != sizeof(Elf64_Ehdr) ||
+ r2(&ehdr->e64.e_shentsize) != sizeof(Elf64_Shdr)) {
fprintf(stderr,
"unrecognized ET_EXEC/ET_DYN file: %s\n",
fname);
- break;
+ return -1;
}
- rc = do_sort_64(ghdr, fname, custom_sort);
+
}
break;
default:
fprintf(stderr, "unrecognized ELF class %d %s\n",
- ehdr->e_ident[EI_CLASS], fname);
- break;
+ ehdr->e32.e_ident[EI_CLASS], fname);
+ return -1;
}
- return rc;
+ return do_sort(ehdr, fname, custom_sort);
}
int main(int argc, char *argv[])
@@ -365,14 +1375,29 @@ int main(int argc, char *argv[])
int i, n_error = 0; /* gcc-4.3.0 false positive complaint */
size_t size = 0;
void *addr = NULL;
+ int c;
+
+ while ((c = getopt(argc, argv, "s:")) >= 0) {
+ switch (c) {
+ case 's':
+ if (parse_symbols(optarg) < 0) {
+ fprintf(stderr, "Could not parse %s\n", optarg);
+ return -1;
+ }
+ break;
+ default:
+ fprintf(stderr, "usage: sorttable [-s nm-file] vmlinux...\n");
+ return 0;
+ }
+ }
- if (argc < 2) {
+ if ((argc - optind) < 1) {
fprintf(stderr, "usage: sorttable vmlinux...\n");
return 0;
}
/* Process each file in turn, allowing deep failure. */
- for (i = 1; i < argc; i++) {
+ for (i = optind; i < argc; i++) {
addr = mmap_file(argv[i], &size);
if (!addr) {
++n_error;
diff --git a/scripts/sorttable.h b/scripts/sorttable.h
deleted file mode 100644
index a7c5445baf00..000000000000
--- a/scripts/sorttable.h
+++ /dev/null
@@ -1,500 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * sorttable.h
- *
- * Added ORC unwind tables sort support and other updates:
- * Copyright (C) 1999-2019 Alibaba Group Holding Limited. by:
- * Shile Zhang <shile.zhang@linux.alibaba.com>
- *
- * Copyright 2011 - 2012 Cavium, Inc.
- *
- * Some of code was taken out of arch/x86/kernel/unwind_orc.c, written by:
- * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com>
- *
- * Some of this code was taken out of recordmcount.h written by:
- *
- * Copyright 2009 John F. Reiser <jreiser@BitWagon.com>. All rights reserved.
- * Copyright 2010 Steven Rostedt <srostedt@redhat.com>, Red Hat Inc.
- */
-
-#undef extable_ent_size
-#undef compare_extable
-#undef get_mcount_loc
-#undef sort_mcount_loc
-#undef elf_mcount_loc
-#undef do_sort
-#undef Elf_Addr
-#undef Elf_Ehdr
-#undef Elf_Shdr
-#undef Elf_Rel
-#undef Elf_Rela
-#undef Elf_Sym
-#undef ELF_R_SYM
-#undef Elf_r_sym
-#undef ELF_R_INFO
-#undef Elf_r_info
-#undef ELF_ST_BIND
-#undef ELF_ST_TYPE
-#undef fn_ELF_R_SYM
-#undef fn_ELF_R_INFO
-#undef uint_t
-#undef _r
-#undef _w
-
-#ifdef SORTTABLE_64
-# define extable_ent_size 16
-# define compare_extable compare_extable_64
-# define get_mcount_loc get_mcount_loc_64
-# define sort_mcount_loc sort_mcount_loc_64
-# define elf_mcount_loc elf_mcount_loc_64
-# define do_sort do_sort_64
-# define Elf_Addr Elf64_Addr
-# define Elf_Ehdr Elf64_Ehdr
-# define Elf_Shdr Elf64_Shdr
-# define Elf_Rel Elf64_Rel
-# define Elf_Rela Elf64_Rela
-# define Elf_Sym Elf64_Sym
-# define ELF_R_SYM ELF64_R_SYM
-# define Elf_r_sym Elf64_r_sym
-# define ELF_R_INFO ELF64_R_INFO
-# define Elf_r_info Elf64_r_info
-# define ELF_ST_BIND ELF64_ST_BIND
-# define ELF_ST_TYPE ELF64_ST_TYPE
-# define fn_ELF_R_SYM fn_ELF64_R_SYM
-# define fn_ELF_R_INFO fn_ELF64_R_INFO
-# define uint_t uint64_t
-# define _r r8
-# define _w w8
-#else
-# define extable_ent_size 8
-# define compare_extable compare_extable_32
-# define get_mcount_loc get_mcount_loc_32
-# define sort_mcount_loc sort_mcount_loc_32
-# define elf_mcount_loc elf_mcount_loc_32
-# define do_sort do_sort_32
-# define Elf_Addr Elf32_Addr
-# define Elf_Ehdr Elf32_Ehdr
-# define Elf_Shdr Elf32_Shdr
-# define Elf_Rel Elf32_Rel
-# define Elf_Rela Elf32_Rela
-# define Elf_Sym Elf32_Sym
-# define ELF_R_SYM ELF32_R_SYM
-# define Elf_r_sym Elf32_r_sym
-# define ELF_R_INFO ELF32_R_INFO
-# define Elf_r_info Elf32_r_info
-# define ELF_ST_BIND ELF32_ST_BIND
-# define ELF_ST_TYPE ELF32_ST_TYPE
-# define fn_ELF_R_SYM fn_ELF32_R_SYM
-# define fn_ELF_R_INFO fn_ELF32_R_INFO
-# define uint_t uint32_t
-# define _r r
-# define _w w
-#endif
-
-#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED)
-/* ORC unwinder only support X86_64 */
-#include <asm/orc_types.h>
-
-#define ERRSTR_MAXSZ 256
-
-char g_err[ERRSTR_MAXSZ];
-int *g_orc_ip_table;
-struct orc_entry *g_orc_table;
-
-pthread_t orc_sort_thread;
-
-static inline unsigned long orc_ip(const int *ip)
-{
- return (unsigned long)ip + *ip;
-}
-
-static int orc_sort_cmp(const void *_a, const void *_b)
-{
- struct orc_entry *orc_a, *orc_b;
- const int *a = g_orc_ip_table + *(int *)_a;
- const int *b = g_orc_ip_table + *(int *)_b;
- unsigned long a_val = orc_ip(a);
- unsigned long b_val = orc_ip(b);
-
- if (a_val > b_val)
- return 1;
- if (a_val < b_val)
- return -1;
-
- /*
- * The "weak" section terminator entries need to always be on the left
- * to ensure the lookup code skips them in favor of real entries.
- * These terminator entries exist to handle any gaps created by
- * whitelisted .o files which didn't get objtool generation.
- */
- orc_a = g_orc_table + (a - g_orc_ip_table);
- orc_b = g_orc_table + (b - g_orc_ip_table);
- if (orc_a->type == ORC_TYPE_UNDEFINED && orc_b->type == ORC_TYPE_UNDEFINED)
- return 0;
- return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1;
-}
-
-static void *sort_orctable(void *arg)
-{
- int i;
- int *idxs = NULL;
- int *tmp_orc_ip_table = NULL;
- struct orc_entry *tmp_orc_table = NULL;
- unsigned int *orc_ip_size = (unsigned int *)arg;
- unsigned int num_entries = *orc_ip_size / sizeof(int);
- unsigned int orc_size = num_entries * sizeof(struct orc_entry);
-
- idxs = (int *)malloc(*orc_ip_size);
- if (!idxs) {
- snprintf(g_err, ERRSTR_MAXSZ, "malloc idxs: %s",
- strerror(errno));
- pthread_exit(g_err);
- }
-
- tmp_orc_ip_table = (int *)malloc(*orc_ip_size);
- if (!tmp_orc_ip_table) {
- snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_ip_table: %s",
- strerror(errno));
- pthread_exit(g_err);
- }
-
- tmp_orc_table = (struct orc_entry *)malloc(orc_size);
- if (!tmp_orc_table) {
- snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_table: %s",
- strerror(errno));
- pthread_exit(g_err);
- }
-
- /* initialize indices array, convert ip_table to absolute address */
- for (i = 0; i < num_entries; i++) {
- idxs[i] = i;
- tmp_orc_ip_table[i] = g_orc_ip_table[i] + i * sizeof(int);
- }
- memcpy(tmp_orc_table, g_orc_table, orc_size);
-
- qsort(idxs, num_entries, sizeof(int), orc_sort_cmp);
-
- for (i = 0; i < num_entries; i++) {
- if (idxs[i] == i)
- continue;
-
- /* convert back to relative address */
- g_orc_ip_table[i] = tmp_orc_ip_table[idxs[i]] - i * sizeof(int);
- g_orc_table[i] = tmp_orc_table[idxs[i]];
- }
-
- free(idxs);
- free(tmp_orc_ip_table);
- free(tmp_orc_table);
- pthread_exit(NULL);
-}
-#endif
-
-static int compare_extable(const void *a, const void *b)
-{
- Elf_Addr av = _r(a);
- Elf_Addr bv = _r(b);
-
- if (av < bv)
- return -1;
- if (av > bv)
- return 1;
- return 0;
-}
-#ifdef MCOUNT_SORT_ENABLED
-pthread_t mcount_sort_thread;
-
-struct elf_mcount_loc {
- Elf_Ehdr *ehdr;
- Elf_Shdr *init_data_sec;
- uint_t start_mcount_loc;
- uint_t stop_mcount_loc;
-};
-
-/* Sort the addresses stored between __start_mcount_loc to __stop_mcount_loc in vmlinux */
-static void *sort_mcount_loc(void *arg)
-{
- struct elf_mcount_loc *emloc = (struct elf_mcount_loc *)arg;
- uint_t offset = emloc->start_mcount_loc - _r(&(emloc->init_data_sec)->sh_addr)
- + _r(&(emloc->init_data_sec)->sh_offset);
- uint_t count = emloc->stop_mcount_loc - emloc->start_mcount_loc;
- unsigned char *start_loc = (void *)emloc->ehdr + offset;
-
- qsort(start_loc, count/sizeof(uint_t), sizeof(uint_t), compare_extable);
- return NULL;
-}
-
-/* Get the address of __start_mcount_loc and __stop_mcount_loc in System.map */
-static void get_mcount_loc(uint_t *_start, uint_t *_stop)
-{
- FILE *file_start, *file_stop;
- char start_buff[20];
- char stop_buff[20];
- int len = 0;
-
- file_start = popen(" grep start_mcount System.map | awk '{print $1}' ", "r");
- if (!file_start) {
- fprintf(stderr, "get start_mcount_loc error!");
- return;
- }
-
- file_stop = popen(" grep stop_mcount System.map | awk '{print $1}' ", "r");
- if (!file_stop) {
- fprintf(stderr, "get stop_mcount_loc error!");
- pclose(file_start);
- return;
- }
-
- while (fgets(start_buff, sizeof(start_buff), file_start) != NULL) {
- len = strlen(start_buff);
- start_buff[len - 1] = '\0';
- }
- *_start = strtoul(start_buff, NULL, 16);
-
- while (fgets(stop_buff, sizeof(stop_buff), file_stop) != NULL) {
- len = strlen(stop_buff);
- stop_buff[len - 1] = '\0';
- }
- *_stop = strtoul(stop_buff, NULL, 16);
-
- pclose(file_start);
- pclose(file_stop);
-}
-#endif
-static int do_sort(Elf_Ehdr *ehdr,
- char const *const fname,
- table_sort_t custom_sort)
-{
- int rc = -1;
- Elf_Shdr *s, *shdr = (Elf_Shdr *)((char *)ehdr + _r(&ehdr->e_shoff));
- Elf_Shdr *strtab_sec = NULL;
- Elf_Shdr *symtab_sec = NULL;
- Elf_Shdr *extab_sec = NULL;
- Elf_Sym *sym;
- const Elf_Sym *symtab;
- Elf32_Word *symtab_shndx = NULL;
- Elf_Sym *sort_needed_sym = NULL;
- Elf_Shdr *sort_needed_sec;
- Elf_Rel *relocs = NULL;
- int relocs_size = 0;
- uint32_t *sort_needed_loc;
- const char *secstrings;
- const char *strtab;
- char *extab_image;
- int extab_index = 0;
- int i;
- int idx;
- unsigned int shnum;
- unsigned int shstrndx;
-#ifdef MCOUNT_SORT_ENABLED
- struct elf_mcount_loc mstruct = {0};
- uint_t _start_mcount_loc = 0;
- uint_t _stop_mcount_loc = 0;
-#endif
-#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED)
- unsigned int orc_ip_size = 0;
- unsigned int orc_size = 0;
- unsigned int orc_num_entries = 0;
-#endif
-
- shstrndx = r2(&ehdr->e_shstrndx);
- if (shstrndx == SHN_XINDEX)
- shstrndx = r(&shdr[0].sh_link);
- secstrings = (const char *)ehdr + _r(&shdr[shstrndx].sh_offset);
-
- shnum = r2(&ehdr->e_shnum);
- if (shnum == SHN_UNDEF)
- shnum = _r(&shdr[0].sh_size);
-
- for (i = 0, s = shdr; s < shdr + shnum; i++, s++) {
- idx = r(&s->sh_name);
- if (!strcmp(secstrings + idx, "__ex_table")) {
- extab_sec = s;
- extab_index = i;
- }
- if (!strcmp(secstrings + idx, ".symtab"))
- symtab_sec = s;
- if (!strcmp(secstrings + idx, ".strtab"))
- strtab_sec = s;
-
- if ((r(&s->sh_type) == SHT_REL ||
- r(&s->sh_type) == SHT_RELA) &&
- r(&s->sh_info) == extab_index) {
- relocs = (void *)ehdr + _r(&s->sh_offset);
- relocs_size = _r(&s->sh_size);
- }
- if (r(&s->sh_type) == SHT_SYMTAB_SHNDX)
- symtab_shndx = (Elf32_Word *)((const char *)ehdr +
- _r(&s->sh_offset));
-
-#ifdef MCOUNT_SORT_ENABLED
- /* locate the .init.data section in vmlinux */
- if (!strcmp(secstrings + idx, ".init.data")) {
- get_mcount_loc(&_start_mcount_loc, &_stop_mcount_loc);
- mstruct.ehdr = ehdr;
- mstruct.init_data_sec = s;
- mstruct.start_mcount_loc = _start_mcount_loc;
- mstruct.stop_mcount_loc = _stop_mcount_loc;
- }
-#endif
-
-#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED)
- /* locate the ORC unwind tables */
- if (!strcmp(secstrings + idx, ".orc_unwind_ip")) {
- orc_ip_size = s->sh_size;
- g_orc_ip_table = (int *)((void *)ehdr +
- s->sh_offset);
- }
- if (!strcmp(secstrings + idx, ".orc_unwind")) {
- orc_size = s->sh_size;
- g_orc_table = (struct orc_entry *)((void *)ehdr +
- s->sh_offset);
- }
-#endif
- } /* for loop */
-
-#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED)
- if (!g_orc_ip_table || !g_orc_table) {
- fprintf(stderr,
- "incomplete ORC unwind tables in file: %s\n", fname);
- goto out;
- }
-
- orc_num_entries = orc_ip_size / sizeof(int);
- if (orc_ip_size % sizeof(int) != 0 ||
- orc_size % sizeof(struct orc_entry) != 0 ||
- orc_num_entries != orc_size / sizeof(struct orc_entry)) {
- fprintf(stderr,
- "inconsistent ORC unwind table entries in file: %s\n",
- fname);
- goto out;
- }
-
- /* create thread to sort ORC unwind tables concurrently */
- if (pthread_create(&orc_sort_thread, NULL,
- sort_orctable, &orc_ip_size)) {
- fprintf(stderr,
- "pthread_create orc_sort_thread failed '%s': %s\n",
- strerror(errno), fname);
- goto out;
- }
-#endif
-
-#ifdef MCOUNT_SORT_ENABLED
- if (!mstruct.init_data_sec || !_start_mcount_loc || !_stop_mcount_loc) {
- fprintf(stderr,
- "incomplete mcount's sort in file: %s\n",
- fname);
- goto out;
- }
-
- /* create thread to sort mcount_loc concurrently */
- if (pthread_create(&mcount_sort_thread, NULL, &sort_mcount_loc, &mstruct)) {
- fprintf(stderr,
- "pthread_create mcount_sort_thread failed '%s': %s\n",
- strerror(errno), fname);
- goto out;
- }
-#endif
- if (!extab_sec) {
- fprintf(stderr, "no __ex_table in file: %s\n", fname);
- goto out;
- }
-
- if (!symtab_sec) {
- fprintf(stderr, "no .symtab in file: %s\n", fname);
- goto out;
- }
-
- if (!strtab_sec) {
- fprintf(stderr, "no .strtab in file: %s\n", fname);
- goto out;
- }
-
- extab_image = (void *)ehdr + _r(&extab_sec->sh_offset);
- strtab = (const char *)ehdr + _r(&strtab_sec->sh_offset);
- symtab = (const Elf_Sym *)((const char *)ehdr +
- _r(&symtab_sec->sh_offset));
-
- if (custom_sort) {
- custom_sort(extab_image, _r(&extab_sec->sh_size));
- } else {
- int num_entries = _r(&extab_sec->sh_size) / extable_ent_size;
- qsort(extab_image, num_entries,
- extable_ent_size, compare_extable);
- }
-
- /* If there were relocations, we no longer need them. */
- if (relocs)
- memset(relocs, 0, relocs_size);
-
- /* find the flag main_extable_sort_needed */
- for (sym = (void *)ehdr + _r(&symtab_sec->sh_offset);
- sym < sym + _r(&symtab_sec->sh_size) / sizeof(Elf_Sym);
- sym++) {
- if (ELF_ST_TYPE(sym->st_info) != STT_OBJECT)
- continue;
- if (!strcmp(strtab + r(&sym->st_name),
- "main_extable_sort_needed")) {
- sort_needed_sym = sym;
- break;
- }
- }
-
- if (!sort_needed_sym) {
- fprintf(stderr,
- "no main_extable_sort_needed symbol in file: %s\n",
- fname);
- goto out;
- }
-
- sort_needed_sec = &shdr[get_secindex(r2(&sym->st_shndx),
- sort_needed_sym - symtab,
- symtab_shndx)];
- sort_needed_loc = (void *)ehdr +
- _r(&sort_needed_sec->sh_offset) +
- _r(&sort_needed_sym->st_value) -
- _r(&sort_needed_sec->sh_addr);
-
- /* extable has been sorted, clear the flag */
- w(0, sort_needed_loc);
- rc = 0;
-
-out:
-#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED)
- if (orc_sort_thread) {
- void *retval = NULL;
- /* wait for ORC tables sort done */
- rc = pthread_join(orc_sort_thread, &retval);
- if (rc) {
- fprintf(stderr,
- "pthread_join failed '%s': %s\n",
- strerror(errno), fname);
- } else if (retval) {
- rc = -1;
- fprintf(stderr,
- "failed to sort ORC tables '%s': %s\n",
- (char *)retval, fname);
- }
- }
-#endif
-
-#ifdef MCOUNT_SORT_ENABLED
- if (mcount_sort_thread) {
- void *retval = NULL;
- /* wait for mcount sort done */
- rc = pthread_join(mcount_sort_thread, &retval);
- if (rc) {
- fprintf(stderr,
- "pthread_join failed '%s': %s\n",
- strerror(errno), fname);
- } else if (retval) {
- rc = -1;
- fprintf(stderr,
- "failed to sort mcount '%s': %s\n",
- (char *)retval, fname);
- }
- }
-#endif
- return rc;
-}
diff --git a/security/apparmor/include/policy_unpack.h b/security/apparmor/include/policy_unpack.h
index e5a95dc4da1f..b9de0fdf9ee5 100644
--- a/security/apparmor/include/policy_unpack.h
+++ b/security/apparmor/include/policy_unpack.h
@@ -163,6 +163,25 @@ aa_get_profile_loaddata(struct aa_loaddata *data)
return data;
}
+/**
+ * aa_get_profile_loaddata_not0 - get a profile reference count if not zero
+ * @data: reference to get a count on
+ *
+ * Like aa_get_profile_loaddata(), but safe to call on an entry that may
+ * be on a list (e.g. ns->rawdata_list) where the last pcount has already
+ * dropped and the deferred cleanup has not yet run.
+ *
+ * Returns: pointer to reference, or %NULL if @data is NULL or its
+ * profile refcount has already reached zero.
+ */
+static inline struct aa_loaddata *
+aa_get_profile_loaddata_not0(struct aa_loaddata *data)
+{
+ if (data && kref_get_unless_zero(&data->pcount))
+ return data;
+ return NULL;
+}
+
void __aa_loaddata_update(struct aa_loaddata *data, long revision);
bool aa_rawdata_eq(struct aa_loaddata *l, struct aa_loaddata *r);
void aa_loaddata_kref(struct kref *kref);
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 641f6510d7cb..79d0a9c1a99b 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -1033,7 +1033,21 @@ static int aa_sock_msg_perm(const char *op, u32 request, struct socket *sock,
static int apparmor_socket_sendmsg(struct socket *sock,
struct msghdr *msg, int size)
{
- return aa_sock_msg_perm(OP_SENDMSG, AA_MAY_SEND, sock, msg, size);
+ int error = aa_sock_msg_perm(OP_SENDMSG, AA_MAY_SEND, sock, msg, size);
+
+ if (error)
+ return error;
+
+ /* TCP fast open carries connect() semantics in sendmsg(); mediate
+ * the implicit connect so it cannot bypass the connect permission.
+ */
+ if ((msg->msg_flags & MSG_FASTOPEN) && msg->msg_name &&
+ (sk_is_tcp(sock->sk) ||
+ (sk_is_inet(sock->sk) && sock->sk->sk_type == SOCK_STREAM &&
+ sock->sk->sk_protocol == IPPROTO_MPTCP)))
+ error = aa_sk_perm(OP_CONNECT, AA_MAY_CONNECT, sock->sk);
+
+ return error;
}
/**
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index 2756fee2442b..c70e68977d61 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -1172,8 +1172,12 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label,
if (aa_rawdata_eq(rawdata_ent, udata)) {
struct aa_loaddata *tmp;
- tmp = aa_get_profile_loaddata(rawdata_ent);
- /* check we didn't fail the race */
+ /*
+ * Entries remain on rawdata_list with
+ * pcount == 0 until do_ploaddata_rmfs()
+ * runs; only take a live profile ref.
+ */
+ tmp = aa_get_profile_loaddata_not0(rawdata_ent);
if (tmp) {
aa_put_profile_loaddata(udata);
udata = tmp;
diff --git a/security/keys/internal.h b/security/keys/internal.h
index ec2ec335b613..b919495243e7 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -215,6 +215,8 @@ extern struct key *request_key_auth_new(struct key *target,
const void *callout_info,
size_t callout_len,
struct key *dest_keyring);
+struct request_key_auth *request_key_auth_get(struct key *authkey);
+void request_key_auth_put(struct request_key_auth *rka);
extern struct key *key_get_instantiation_authkey(key_serial_t target_id);
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index aa1dc43b16dd..127c17191785 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -1196,9 +1196,13 @@ static long keyctl_instantiate_key_common(key_serial_t id,
if (!instkey)
goto error;
- rka = instkey->payload.data[0];
- if (rka->target_key->serial != id)
+ rka = request_key_auth_get(instkey);
+ if (!rka) {
+ ret = -EKEYREVOKED;
goto error;
+ }
+ if (rka->target_key->serial != id)
+ goto error_put_rka;
/* pull the payload in if one was supplied */
payload = NULL;
@@ -1207,7 +1211,7 @@ static long keyctl_instantiate_key_common(key_serial_t id,
ret = -ENOMEM;
payload = kvmalloc(plen, GFP_KERNEL);
if (!payload)
- goto error;
+ goto error_put_rka;
ret = -EFAULT;
if (!copy_from_iter_full(payload, plen, from))
@@ -1233,6 +1237,8 @@ static long keyctl_instantiate_key_common(key_serial_t id,
error2:
kvfree_sensitive(payload, plen);
+error_put_rka:
+ request_key_auth_put(rka);
error:
return ret;
}
@@ -1358,15 +1364,19 @@ long keyctl_reject_key(key_serial_t id, unsigned timeout, unsigned error,
if (!instkey)
goto error;
- rka = instkey->payload.data[0];
- if (rka->target_key->serial != id)
+ rka = request_key_auth_get(instkey);
+ if (!rka) {
+ ret = -EKEYREVOKED;
goto error;
+ }
+ if (rka->target_key->serial != id)
+ goto error_put_rka;
/* find the destination keyring if present (which must also be
* writable) */
ret = get_instantiation_keyring(ringid, rka, &dest_keyring);
if (ret < 0)
- goto error;
+ goto error_put_rka;
/* instantiate the key and link it into a keyring */
ret = key_reject_and_link(rka->target_key, timeout, error,
@@ -1379,6 +1389,8 @@ long keyctl_reject_key(key_serial_t id, unsigned timeout, unsigned error,
if (ret == 0)
keyctl_change_reqkey_auth(NULL);
+error_put_rka:
+ request_key_auth_put(rka);
error:
return ret;
}
diff --git a/security/keys/keyctl_pkey.c b/security/keys/keyctl_pkey.c
index 97bc27bbf079..ba150ee2d4a3 100644
--- a/security/keys/keyctl_pkey.c
+++ b/security/keys/keyctl_pkey.c
@@ -138,28 +138,35 @@ static int keyctl_pkey_params_get_2(const struct keyctl_pkey_params __user *_par
if (uparams.in_len > info.max_dec_size ||
uparams.out_len > info.max_enc_size)
return -EINVAL;
+
+ params->out_len = info.max_enc_size;
break;
case KEYCTL_PKEY_DECRYPT:
if (uparams.in_len > info.max_enc_size ||
uparams.out_len > info.max_dec_size)
return -EINVAL;
+
+ params->out_len = info.max_dec_size;
break;
case KEYCTL_PKEY_SIGN:
if (uparams.in_len > info.max_data_size ||
uparams.out_len > info.max_sig_size)
return -EINVAL;
+
+ params->out_len = info.max_sig_size;
break;
case KEYCTL_PKEY_VERIFY:
if (uparams.in_len > info.max_data_size ||
uparams.in2_len > info.max_sig_size)
return -EINVAL;
+
+ params->out_len = info.max_sig_size;
break;
default:
BUG();
}
params->in_len = uparams.in_len;
- params->out_len = uparams.out_len; /* Note: same as in2_len */
return 0;
}
diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c
index 8f33cd170e42..bd34317b58cc 100644
--- a/security/keys/request_key_auth.c
+++ b/security/keys/request_key_auth.c
@@ -23,6 +23,7 @@ static void request_key_auth_describe(const struct key *, struct seq_file *);
static void request_key_auth_revoke(struct key *);
static void request_key_auth_destroy(struct key *);
static long request_key_auth_read(const struct key *, char *, size_t);
+static void request_key_auth_rcu_disposal(struct rcu_head *);
/*
* The request-key authorisation key type definition.
@@ -115,6 +116,31 @@ static void free_request_key_auth(struct request_key_auth *rka)
kfree(rka);
}
+/*
+ * Take a reference to the request-key authorisation payload so callers can
+ * drop authkey->sem before doing operations that may sleep.
+ */
+struct request_key_auth *request_key_auth_get(struct key *authkey)
+{
+ struct request_key_auth *rka;
+
+ down_read(&authkey->sem);
+ rka = dereference_key_locked(authkey);
+ if (rka && !test_bit(KEY_FLAG_REVOKED, &authkey->flags))
+ refcount_inc(&rka->usage);
+ else
+ rka = NULL;
+ up_read(&authkey->sem);
+
+ return rka;
+}
+
+void request_key_auth_put(struct request_key_auth *rka)
+{
+ if (rka && refcount_dec_and_test(&rka->usage))
+ call_rcu(&rka->rcu, request_key_auth_rcu_disposal);
+}
+
/*
* Dispose of the request_key_auth record under RCU conditions
*/
@@ -136,8 +162,10 @@ static void request_key_auth_revoke(struct key *key)
struct request_key_auth *rka = dereference_key_locked(key);
kenter("{%d}", key->serial);
+ if (!rka)
+ return;
rcu_assign_keypointer(key, NULL);
- call_rcu(&rka->rcu, request_key_auth_rcu_disposal);
+ request_key_auth_put(rka);
}
/*
@@ -150,7 +178,7 @@ static void request_key_auth_destroy(struct key *key)
kenter("{%d}", key->serial);
if (rka) {
rcu_assign_keypointer(key, NULL);
- call_rcu(&rka->rcu, request_key_auth_rcu_disposal);
+ request_key_auth_put(rka);
}
}
@@ -174,6 +202,7 @@ struct key *request_key_auth_new(struct key *target, const char *op,
rka = kzalloc(sizeof(*rka), GFP_KERNEL);
if (!rka)
goto error;
+ refcount_set(&rka->usage, 1);
rka->callout_info = kmemdup(callout_info, callout_len, GFP_KERNEL);
if (!rka->callout_info)
goto error_free_rka;
diff --git a/security/security.c b/security/security.c
index 1794860fd614..4b61766c3d27 100644
--- a/security/security.c
+++ b/security/security.c
@@ -78,6 +78,7 @@ struct security_hook_heads security_hook_heads __ro_after_init;
static BLOCKING_NOTIFIER_HEAD(blocking_lsm_notifier_chain);
static struct kmem_cache *lsm_file_cache;
+static struct kmem_cache *lsm_backing_file_cache;
static struct kmem_cache *lsm_inode_cache;
char *lsm_names;
@@ -200,6 +201,8 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed)
lsm_set_blob_size(&needed->lbs_cred, &blob_sizes.lbs_cred);
lsm_set_blob_size(&needed->lbs_file, &blob_sizes.lbs_file);
+ lsm_set_blob_size(&needed->lbs_backing_file,
+ &blob_sizes.lbs_backing_file);
/*
* The inode blob gets an rcu_head in addition to
* what the modules might need.
@@ -374,6 +377,7 @@ static void __init ordered_lsm_init(void)
init_debug("cred blob size = %d\n", blob_sizes.lbs_cred);
init_debug("file blob size = %d\n", blob_sizes.lbs_file);
+ init_debug("backing_file blob size = %d\n", blob_sizes.lbs_backing_file);
init_debug("inode blob size = %d\n", blob_sizes.lbs_inode);
init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc);
init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg);
@@ -388,6 +392,11 @@ static void __init ordered_lsm_init(void)
lsm_file_cache = kmem_cache_create("lsm_file_cache",
blob_sizes.lbs_file, 0,
SLAB_PANIC, NULL);
+ if (blob_sizes.lbs_backing_file)
+ lsm_backing_file_cache = kmem_cache_create(
+ "lsm_backing_file_cache",
+ blob_sizes.lbs_backing_file,
+ 0, SLAB_PANIC, NULL);
if (blob_sizes.lbs_inode)
lsm_inode_cache = kmem_cache_create("lsm_inode_cache",
blob_sizes.lbs_inode, 0,
@@ -616,6 +625,30 @@ static int lsm_file_alloc(struct file *file)
return 0;
}
+/**
+ * lsm_backing_file_alloc - allocate a composite backing file blob
+ * @backing_file: the backing file
+ *
+ * Allocate the backing file blob for all the modules.
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_backing_file_alloc(struct file *backing_file)
+{
+ void *blob;
+
+ if (!lsm_backing_file_cache) {
+ backing_file_set_security(backing_file, NULL);
+ return 0;
+ }
+
+ blob = kmem_cache_zalloc(lsm_backing_file_cache, GFP_KERNEL);
+ backing_file_set_security(backing_file, blob);
+ if (!blob)
+ return -ENOMEM;
+ return 0;
+}
+
/**
* lsm_inode_alloc - allocate a composite inode blob
* @inode: the inode that needs a blob
@@ -2630,6 +2663,57 @@ void security_file_free(struct file *file)
}
}
+/**
+ * security_backing_file_alloc() - Allocate and setup a backing file blob
+ * @backing_file: the backing file
+ * @user_file: the associated user visible file
+ *
+ * Allocate a backing file LSM blob and perform any necessary initialization of
+ * the LSM blob. There will be some operations where the LSM will not have
+ * access to @user_file after this point, so any important state associated
+ * with @user_file that is important to the LSM should be captured in the
+ * backing file's LSM blob.
+ *
+ * LSM's should avoid taking a reference to @user_file in this hook as it will
+ * result in problems later when the system attempts to drop/put the file
+ * references due to a circular dependency.
+ *
+ * Return: Return 0 if the hook is successful, negative values otherwise.
+ */
+int security_backing_file_alloc(struct file *backing_file,
+ const struct file *user_file)
+{
+ int rc;
+
+ rc = lsm_backing_file_alloc(backing_file);
+ if (rc)
+ return rc;
+ rc = call_int_hook(backing_file_alloc, 0, backing_file, user_file);
+ if (unlikely(rc))
+ security_backing_file_free(backing_file);
+
+ return rc;
+}
+
+/**
+ * security_backing_file_free() - Free a backing file blob
+ * @backing_file: the backing file
+ *
+ * Free any LSM state associate with a backing file's LSM blob, including the
+ * blob itself.
+ */
+void security_backing_file_free(struct file *backing_file)
+{
+ void *blob = backing_file_security(backing_file);
+
+ call_void_hook(backing_file_free, backing_file);
+
+ if (blob) {
+ backing_file_set_security(backing_file, NULL);
+ kmem_cache_free(lsm_backing_file_cache, blob);
+ }
+}
+
/**
* security_file_ioctl() - Check if an ioctl is allowed
* @file: associated file
@@ -2723,6 +2807,32 @@ int security_mmap_file(struct file *file, unsigned long prot,
return ima_file_mmap(file, prot, prot_adj, flags);
}
+/**
+ * security_mmap_backing_file - Check if mmap'ing a backing file is allowed
+ * @vma: the vm_area_struct for the mmap'd region
+ * @backing_file: the backing file being mmap'd
+ * @user_file: the user file being mmap'd
+ *
+ * Check permissions for a mmap operation on a stacked filesystem. This hook
+ * is called after the security_mmap_file() and is responsible for authorizing
+ * the mmap on @backing_file. It is important to note that the mmap operation
+ * on @user_file has already been authorized and the @vma->vm_file has been
+ * set to @backing_file.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_mmap_backing_file(struct vm_area_struct *vma,
+ struct file *backing_file,
+ struct file *user_file)
+{
+ /* recommended by the stackable filesystem devs */
+ if (WARN_ON_ONCE(!(backing_file->f_mode & FMODE_BACKING)))
+ return -EIO;
+
+ return call_int_hook(mmap_backing_file, 0, vma, backing_file, user_file);
+}
+EXPORT_SYMBOL_GPL(security_mmap_backing_file);
+
/**
* security_mmap_addr() - Check if mmap'ing an address is allowed
* @addr: address
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 60092d0b013c..3f11c5ae8fbf 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -1717,49 +1717,72 @@ static inline int file_path_has_perm(const struct cred *cred,
static int bpf_fd_pass(const struct file *file, u32 sid);
#endif
-/* Check whether a task can use an open file descriptor to
- access an inode in a given way. Check access to the
- descriptor itself, and then use dentry_has_perm to
- check a particular permission to the file.
- Access to the descriptor is implicitly granted if it
- has the same SID as the process. If av is zero, then
- access to the file is not checked, e.g. for cases
- where only the descriptor is affected like seek. */
-static int file_has_perm(const struct cred *cred,
- struct file *file,
- u32 av)
+static int __file_has_perm(const struct cred *cred, const struct file *file,
+ u32 av, bool bf_user_file)
+
{
- struct file_security_struct *fsec = selinux_file(file);
- struct inode *inode = file_inode(file);
struct common_audit_data ad;
- u32 sid = cred_sid(cred);
+ struct inode *inode;
+ u32 ssid = cred_sid(cred);
+ u32 tsid_fd;
int rc;
- ad.type = LSM_AUDIT_DATA_FILE;
- ad.u.file = file;
+ if (bf_user_file) {
+ struct backing_file_security_struct *bfsec;
+ const struct path *path;
- if (sid != fsec->sid) {
- rc = avc_has_perm(sid, fsec->sid,
- SECCLASS_FD,
- FD__USE,
- &ad);
+ if (WARN_ON(!(file->f_mode & FMODE_BACKING)))
+ return -EIO;
+
+ bfsec = selinux_backing_file(file);
+ path = &file->f_path;
+ tsid_fd = bfsec->uf_sid;
+ inode = d_inode(path->dentry);
+
+ ad.type = LSM_AUDIT_DATA_PATH;
+ ad.u.path = *path;
+ } else {
+ struct file_security_struct *fsec = selinux_file(file);
+
+ tsid_fd = fsec->sid;
+ inode = file_inode(file);
+
+ ad.type = LSM_AUDIT_DATA_FILE;
+ ad.u.file = file;
+ }
+
+ if (ssid != tsid_fd) {
+ rc = avc_has_perm(ssid, tsid_fd, SECCLASS_FD, FD__USE, &ad);
if (rc)
- goto out;
+ return rc;
}
#ifdef CONFIG_BPF_SYSCALL
- rc = bpf_fd_pass(file, cred_sid(cred));
+ /* regardless of backing vs user file, use the underlying file here */
+ rc = bpf_fd_pass(file, ssid);
if (rc)
return rc;
#endif
/* av is zero if only checking access to the descriptor. */
- rc = 0;
if (av)
- rc = inode_has_perm(cred, inode, av, &ad);
+ return inode_has_perm(cred, inode, av, &ad);
-out:
- return rc;
+ return 0;
+}
+
+/* Check whether a task can use an open file descriptor to
+ access an inode in a given way. Check access to the
+ descriptor itself, and then use dentry_has_perm to
+ check a particular permission to the file.
+ Access to the descriptor is implicitly granted if it
+ has the same SID as the process. If av is zero, then
+ access to the file is not checked, e.g. for cases
+ where only the descriptor is affected like seek. */
+static inline int file_has_perm(const struct cred *cred,
+ const struct file *file, u32 av)
+{
+ return __file_has_perm(cred, file, av, false);
}
/*
@@ -3638,6 +3661,17 @@ static int selinux_file_alloc_security(struct file *file)
return 0;
}
+static int selinux_backing_file_alloc(struct file *backing_file,
+ const struct file *user_file)
+{
+ struct backing_file_security_struct *bfsec;
+
+ bfsec = selinux_backing_file(backing_file);
+ bfsec->uf_sid = selinux_file(user_file)->sid;
+
+ return 0;
+}
+
/*
* Check whether a task has the ioctl permission and cmd
* operation to an inode.
@@ -3755,42 +3789,55 @@ static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd,
static int default_noexec __ro_after_init;
-static int file_map_prot_check(struct file *file, unsigned long prot, int shared)
+static int __file_map_prot_check(const struct cred *cred,
+ const struct file *file, unsigned long prot,
+ bool shared, bool bf_user_file)
{
- const struct cred *cred = current_cred();
- u32 sid = cred_sid(cred);
- int rc = 0;
+ struct inode *inode = NULL;
+ bool prot_exec = prot & PROT_EXEC;
+ bool prot_write = prot & PROT_WRITE;
+
+ if (file) {
+ if (bf_user_file)
+ inode = d_inode(file->f_path.dentry);
+ else
+ inode = file_inode(file);
+ }
+
+ if (default_noexec && prot_exec &&
+ (!file || IS_PRIVATE(inode) || (!shared && prot_write))) {
+ int rc;
+ u32 sid = cred_sid(cred);
- if (default_noexec &&
- (prot & PROT_EXEC) && (!file || IS_PRIVATE(file_inode(file)) ||
- (!shared && (prot & PROT_WRITE)))) {
/*
- * We are making executable an anonymous mapping or a
- * private file mapping that will also be writable.
- * This has an additional check.
+ * We are making executable an anonymous mapping or a private
+ * file mapping that will also be writable.
*/
- rc = avc_has_perm(sid, sid, SECCLASS_PROCESS,
- PROCESS__EXECMEM, NULL);
+ rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECMEM,
+ NULL);
if (rc)
- goto error;
+ return rc;
}
if (file) {
- /* read access is always possible with a mapping */
+ /* "read" always possible, "write" only if shared */
u32 av = FILE__READ;
-
- /* write access only matters if the mapping is shared */
- if (shared && (prot & PROT_WRITE))
+ if (shared && prot_write)
av |= FILE__WRITE;
-
- if (prot & PROT_EXEC)
+ if (prot_exec)
av |= FILE__EXECUTE;
- return file_has_perm(cred, file, av);
+ return __file_has_perm(cred, file, av, bf_user_file);
}
-error:
- return rc;
+ return 0;
+}
+
+static inline int file_map_prot_check(const struct cred *cred,
+ const struct file *file,
+ unsigned long prot, bool shared)
+{
+ return __file_map_prot_check(cred, file, prot, shared, false);
}
static int selinux_mmap_addr(unsigned long addr)
@@ -3806,36 +3853,80 @@ static int selinux_mmap_addr(unsigned long addr)
return rc;
}
-static int selinux_mmap_file(struct file *file,
- unsigned long reqprot __always_unused,
- unsigned long prot, unsigned long flags)
+static int selinux_mmap_file_common(const struct cred *cred, struct file *file,
+ unsigned long prot, bool shared)
{
- struct common_audit_data ad;
- int rc;
-
if (file) {
+ int rc;
+ struct common_audit_data ad;
+
ad.type = LSM_AUDIT_DATA_FILE;
ad.u.file = file;
- rc = inode_has_perm(current_cred(), file_inode(file),
- FILE__MAP, &ad);
+ rc = inode_has_perm(cred, file_inode(file), FILE__MAP, &ad);
if (rc)
return rc;
}
- return file_map_prot_check(file, prot,
- (flags & MAP_TYPE) == MAP_SHARED);
+ return file_map_prot_check(cred, file, prot, shared);
+}
+
+static int selinux_mmap_file(struct file *file,
+ unsigned long reqprot __always_unused,
+ unsigned long prot, unsigned long flags)
+{
+ return selinux_mmap_file_common(current_cred(), file, prot,
+ (flags & MAP_TYPE) == MAP_SHARED);
+}
+
+/**
+ * selinux_mmap_backing_file - Check mmap permissions on a backing file
+ * @vma: memory region
+ * @backing_file: stacked filesystem backing file
+ * @user_file: user visible file
+ *
+ * This is called after selinux_mmap_file() on stacked filesystems, and it
+ * is this function's responsibility to verify access to @backing_file and
+ * setup the SELinux state for possible later use in the mprotect() code path.
+ *
+ * By the time this function is called, mmap() access to @user_file has already
+ * been authorized and @vma->vm_file has been set to point to @backing_file.
+ *
+ * Return zero on success, negative values otherwise.
+ */
+static int selinux_mmap_backing_file(struct vm_area_struct *vma,
+ struct file *backing_file,
+ struct file *user_file __always_unused)
+{
+ unsigned long prot = 0;
+
+ /* translate vma->vm_flags perms into PROT perms */
+ if (vma->vm_flags & VM_READ)
+ prot |= PROT_READ;
+ if (vma->vm_flags & VM_WRITE)
+ prot |= PROT_WRITE;
+ if (vma->vm_flags & VM_EXEC)
+ prot |= PROT_EXEC;
+
+ return selinux_mmap_file_common(backing_file->f_cred, backing_file,
+ prot, vma->vm_flags & VM_SHARED);
}
static int selinux_file_mprotect(struct vm_area_struct *vma,
unsigned long reqprot __always_unused,
unsigned long prot)
{
+ int rc;
const struct cred *cred = current_cred();
u32 sid = cred_sid(cred);
+ const struct file *file = vma->vm_file;
+ bool backing_file;
+ bool shared = vma->vm_flags & VM_SHARED;
+
+ /* check if we need to trigger the "backing files are awful" mode */
+ backing_file = file && (file->f_mode & FMODE_BACKING);
if (default_noexec &&
(prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) {
- int rc = 0;
/*
* We don't use the vma_is_initial_heap() helper as it has
* a history of problems and is currently broken on systems
@@ -3849,11 +3940,15 @@ static int selinux_file_mprotect(struct vm_area_struct *vma,
vma->vm_end <= vma->vm_mm->brk) {
rc = avc_has_perm(sid, sid, SECCLASS_PROCESS,
PROCESS__EXECHEAP, NULL);
- } else if (!vma->vm_file && (vma_is_initial_stack(vma) ||
+ if (rc)
+ return rc;
+ } else if (!file && (vma_is_initial_stack(vma) ||
vma_is_stack_for_current(vma))) {
rc = avc_has_perm(sid, sid, SECCLASS_PROCESS,
PROCESS__EXECSTACK, NULL);
- } else if (vma->vm_file && vma->anon_vma) {
+ if (rc)
+ return rc;
+ } else if (file && vma->anon_vma) {
/*
* We are making executable a file mapping that has
* had some COW done. Since pages might have been
@@ -3861,13 +3956,29 @@ static int selinux_file_mprotect(struct vm_area_struct *vma,
* modified content. This typically should only
* occur for text relocations.
*/
- rc = file_has_perm(cred, vma->vm_file, FILE__EXECMOD);
+ rc = __file_has_perm(cred, file, FILE__EXECMOD,
+ backing_file);
+ if (rc)
+ return rc;
+ if (backing_file) {
+ rc = file_has_perm(file->f_cred, file,
+ FILE__EXECMOD);
+ if (rc)
+ return rc;
+ }
}
+ }
+
+ rc = __file_map_prot_check(cred, file, prot, shared, backing_file);
+ if (rc)
+ return rc;
+ if (backing_file) {
+ rc = file_map_prot_check(file->f_cred, file, prot, shared);
if (rc)
return rc;
}
- return file_map_prot_check(vma->vm_file, prot, vma->vm_flags&VM_SHARED);
+ return 0;
}
static int selinux_file_lock(struct file *file, unsigned int cmd)
@@ -6870,6 +6981,7 @@ static void selinux_bpf_prog_free(struct bpf_prog_aux *aux)
struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = {
.lbs_cred = sizeof(struct task_security_struct),
.lbs_file = sizeof(struct file_security_struct),
+ .lbs_backing_file = sizeof(struct backing_file_security_struct),
.lbs_inode = sizeof(struct inode_security_struct),
.lbs_ipc = sizeof(struct ipc_security_struct),
.lbs_msg_msg = sizeof(struct msg_security_struct),
@@ -7074,9 +7186,11 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
LSM_HOOK_INIT(file_permission, selinux_file_permission),
LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security),
+ LSM_HOOK_INIT(backing_file_alloc, selinux_backing_file_alloc),
LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl),
LSM_HOOK_INIT(file_ioctl_compat, selinux_file_ioctl_compat),
LSM_HOOK_INIT(mmap_file, selinux_mmap_file),
+ LSM_HOOK_INIT(mmap_backing_file, selinux_mmap_backing_file),
LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr),
LSM_HOOK_INIT(file_mprotect, selinux_file_mprotect),
LSM_HOOK_INIT(file_lock, selinux_file_lock),
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index 8159fd53c3de..541933dd295c 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -60,6 +60,10 @@ struct file_security_struct {
u32 pseqno; /* Policy seqno at the time of file open */
};
+struct backing_file_security_struct {
+ u32 uf_sid; /* associated user file fsec->sid */
+};
+
struct superblock_security_struct {
u32 sid; /* SID of file system superblock */
u32 def_sid; /* default SID for labeling */
@@ -158,6 +162,13 @@ static inline struct file_security_struct *selinux_file(const struct file *file)
return file->f_security + selinux_blob_sizes.lbs_file;
}
+static inline struct backing_file_security_struct *
+selinux_backing_file(const struct file *backing_file)
+{
+ void *blob = backing_file_security(backing_file);
+ return blob + selinux_blob_sizes.lbs_backing_file;
+}
+
static inline struct inode_security_struct *selinux_inode(
const struct inode *inode)
{
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index 4041cfa670eb..d41e140c3150 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -4,6 +4,7 @@
#include "trace_helpers.h"
#include "kprobe_multi_empty.skel.h"
#include "kprobe_multi_override.skel.h"
+#include "kprobe_multi_sleepable.skel.h"
#include "bpf/libbpf_internal.h"
#include "bpf/hashmap.h"
@@ -214,7 +215,9 @@ static void test_attach_api_syms(void)
static void test_attach_api_fails(void)
{
LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
struct kprobe_multi *skel = NULL;
+ struct kprobe_multi_sleepable *sl_skel = NULL;
struct bpf_link *link = NULL;
unsigned long long addrs[2];
const char *syms[2] = {
@@ -222,6 +225,7 @@ static void test_attach_api_fails(void)
"bpf_fentry_test2",
};
__u64 cookies[2];
+ int saved_error, err;
addrs[0] = ksym_get_addr("bpf_fentry_test1");
addrs[1] = ksym_get_addr("bpf_fentry_test2");
@@ -300,9 +304,39 @@ static void test_attach_api_fails(void)
if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_5_error"))
goto cleanup;
+ /* fail_9 - sleepable kprobe multi should not attach */
+ sl_skel = kprobe_multi_sleepable__open();
+ if (!ASSERT_OK_PTR(sl_skel, "sleep_skel_open"))
+ goto cleanup;
+
+ sl_skel->bss->user_ptr = sl_skel;
+
+ err = bpf_program__set_flags(sl_skel->progs.handle_kprobe_multi_sleepable,
+ BPF_F_SLEEPABLE);
+ if (!ASSERT_OK(err, "sleep_skel_set_flags"))
+ goto cleanup;
+
+ err = kprobe_multi_sleepable__load(sl_skel);
+ if (!ASSERT_OK(err, "sleep_skel_load"))
+ goto cleanup;
+
+ link = bpf_program__attach_kprobe_multi_opts(sl_skel->progs.handle_kprobe_multi_sleepable,
+ "bpf_fentry_test1", NULL);
+ saved_error = -errno;
+
+ if (!ASSERT_ERR_PTR(link, "fail_9"))
+ goto cleanup;
+
+ if (!ASSERT_EQ(saved_error, -EINVAL, "fail_9_error"))
+ goto cleanup;
+
+ err = bpf_prog_test_run_opts(bpf_program__fd(sl_skel->progs.fentry), &topts);
+ ASSERT_OK(err, "bpf_prog_test_run_opts");
+
cleanup:
bpf_link__destroy(link);
kprobe_multi__destroy(skel);
+ kprobe_multi_sleepable__destroy(sl_skel);
}
static size_t symbol_hash(long key, void *ctx __maybe_unused)
diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi_sleepable.c b/tools/testing/selftests/bpf/progs/kprobe_multi_sleepable.c
new file mode 100644
index 000000000000..932e1d9c72e2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kprobe_multi_sleepable.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+void *user_ptr = 0;
+
+SEC("kprobe.multi")
+int handle_kprobe_multi_sleepable(struct pt_regs *ctx)
+{
+ int a, err;
+
+ err = bpf_copy_from_user(&a, sizeof(a), user_ptr);
+ barrier_var(a);
+ return err;
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(fentry)
+{
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
index 22a6cf6e8255..2eb85eb3a06c 100644
--- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
+++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
@@ -5,18 +5,27 @@
#include "bpf_misc.h"
/* Check that precision marks propagate through scalar IDs.
- * Registers r{0,1,2} have the same scalar ID at the moment when r0 is
- * marked to be precise, this mark is immediately propagated to r{1,2}.
+ * Registers r{0,1,2} have the same scalar ID.
+ * Range information is propagated for scalars sharing same ID.
+ * Check that precision mark for r0 causes precision marks for r{1,2}
+ * when range information is propagated for 'if <reg> <op> <const>' insn.
*/
SEC("socket")
__success __log_level(2)
-__msg("frame0: regs=r0,r1,r2 stack= before 4: (bf) r3 = r10")
+/* first 'if' branch */
+__msg("6: (0f) r3 += r0")
+__msg("frame0: regs=r0 stack= before 4: (25) if r1 > 0x7 goto pc+0")
+__msg("frame0: parent state regs=r0,r1,r2 stack=:")
__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0")
-__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0")
-__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255")
-__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns")
+/* second 'if' branch */
+__msg("from 4 to 5: ")
+__msg("6: (0f) r3 += r0")
+__msg("frame0: regs=r0 stack= before 5: (bf) r3 = r10")
+__msg("frame0: regs=r0 stack= before 4: (25) if r1 > 0x7 goto pc+0")
+/* parent state already has r{0,1,2} as precise */
+__msg("frame0: parent state regs= stack=:")
__flag(BPF_F_TEST_STATE_FREQ)
-__naked void precision_same_state(void)
+__naked void linked_regs_bpf_k(void)
{
asm volatile (
/* r0 = random number up to 0xff */
@@ -25,7 +34,8 @@ __naked void precision_same_state(void)
/* tie r0.id == r1.id == r2.id */
"r1 = r0;"
"r2 = r0;"
- /* force r0 to be precise, this immediately marks r1 and r2 as
+ "if r1 > 7 goto +0;"
+ /* force r0 to be precise, this eventually marks r1 and r2 as
* precise as well because of shared IDs
*/
"r3 = r10;"
@@ -37,22 +47,17 @@ __naked void precision_same_state(void)
: __clobber_all);
}
-/* Same as precision_same_state, but mark propagates through state /
- * parent state boundary.
+/* Registers r{0,1,2} share same ID when 'if r1 > ...' insn is processed,
+ * check that verifier marks r{1,2} as precise while backtracking
+ * 'if r1 > ...' with r0 already marked.
*/
SEC("socket")
__success __log_level(2)
-__msg("frame0: last_idx 6 first_idx 5 subseq_idx -1")
-__msg("frame0: regs=r0,r1,r2 stack= before 5: (bf) r3 = r10")
-__msg("frame0: parent state regs=r0,r1,r2 stack=:")
-__msg("frame0: regs=r0,r1,r2 stack= before 4: (05) goto pc+0")
-__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0")
-__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0")
-__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255")
-__msg("frame0: parent state regs=r0 stack=:")
-__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns")
__flag(BPF_F_TEST_STATE_FREQ)
-__naked void precision_cross_state(void)
+__msg("frame0: regs=r0 stack= before 5: (2d) if r1 > r3 goto pc+0")
+__msg("frame0: parent state regs=r0,r1,r2,r3 stack=:")
+__msg("frame0: regs=r0,r1,r2,r3 stack= before 4: (b7) r3 = 7")
+__naked void linked_regs_bpf_x_src(void)
{
asm volatile (
/* r0 = random number up to 0xff */
@@ -61,13 +66,13 @@ __naked void precision_cross_state(void)
/* tie r0.id == r1.id == r2.id */
"r1 = r0;"
"r2 = r0;"
- /* force checkpoint */
- "goto +0;"
- /* force r0 to be precise, this immediately marks r1 and r2 as
+ "r3 = 7;"
+ "if r1 > r3 goto +0;"
+ /* force r0 to be precise, this eventually marks r1 and r2 as
* precise as well because of shared IDs
*/
- "r3 = r10;"
- "r3 += r0;"
+ "r4 = r10;"
+ "r4 += r0;"
"r0 = 0;"
"exit;"
:
@@ -75,19 +80,17 @@ __naked void precision_cross_state(void)
: __clobber_all);
}
-/* Same as precision_same_state, but break one of the
- * links, note that r1 is absent from regs=... in __msg below.
+/* Registers r{0,1,2} share same ID when 'if r1 > r3' insn is processed,
+ * check that verifier marks r{0,1,2} as precise while backtracking
+ * 'if r1 > r3' with r3 already marked.
*/
SEC("socket")
__success __log_level(2)
-__msg("frame0: regs=r0,r2 stack= before 5: (bf) r3 = r10")
-__msg("frame0: regs=r0,r2 stack= before 4: (b7) r1 = 0")
-__msg("frame0: regs=r0,r2 stack= before 3: (bf) r2 = r0")
-__msg("frame0: regs=r0 stack= before 2: (bf) r1 = r0")
-__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255")
-__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns")
__flag(BPF_F_TEST_STATE_FREQ)
-__naked void precision_same_state_broken_link(void)
+__msg("frame0: regs=r3 stack= before 5: (2d) if r1 > r3 goto pc+0")
+__msg("frame0: parent state regs=r0,r1,r2,r3 stack=:")
+__msg("frame0: regs=r0,r1,r2,r3 stack= before 4: (b7) r3 = 7")
+__naked void linked_regs_bpf_x_dst(void)
{
asm volatile (
/* r0 = random number up to 0xff */
@@ -96,15 +99,13 @@ __naked void precision_same_state_broken_link(void)
/* tie r0.id == r1.id == r2.id */
"r1 = r0;"
"r2 = r0;"
- /* break link for r1, this is the only line that differs
- * compared to the previous test
- */
- "r1 = 0;"
- /* force r0 to be precise, this immediately marks r1 and r2 as
+ "r3 = 7;"
+ "if r1 > r3 goto +0;"
+ /* force r0 to be precise, this eventually marks r1 and r2 as
* precise as well because of shared IDs
*/
- "r3 = r10;"
- "r3 += r0;"
+ "r4 = r10;"
+ "r4 += r3;"
"r0 = 0;"
"exit;"
:
@@ -112,22 +113,18 @@ __naked void precision_same_state_broken_link(void)
: __clobber_all);
}
-/* Same as precision_same_state_broken_link, but with state /
- * parent state boundary.
+/* Same as linked_regs_bpf_k, but break one of the
+ * links, note that r1 is absent from regs=... in __msg below.
*/
SEC("socket")
__success __log_level(2)
-__msg("frame0: regs=r0,r2 stack= before 6: (bf) r3 = r10")
-__msg("frame0: regs=r0,r2 stack= before 5: (b7) r1 = 0")
-__msg("frame0: parent state regs=r0,r2 stack=:")
-__msg("frame0: regs=r0,r1,r2 stack= before 4: (05) goto pc+0")
-__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0")
-__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0")
-__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255")
+__msg("7: (0f) r3 += r0")
+__msg("frame0: regs=r0 stack= before 6: (bf) r3 = r10")
__msg("frame0: parent state regs=r0 stack=:")
-__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns")
+__msg("frame0: regs=r0 stack= before 5: (25) if r0 > 0x7 goto pc+0")
+__msg("frame0: parent state regs=r0,r2 stack=:")
__flag(BPF_F_TEST_STATE_FREQ)
-__naked void precision_cross_state_broken_link(void)
+__naked void linked_regs_broken_link(void)
{
asm volatile (
/* r0 = random number up to 0xff */
@@ -136,18 +133,13 @@ __naked void precision_cross_state_broken_link(void)
/* tie r0.id == r1.id == r2.id */
"r1 = r0;"
"r2 = r0;"
- /* force checkpoint, although link between r1 and r{0,2} is
- * broken by the next statement current precision tracking
- * algorithm can't react to it and propagates mark for r1 to
- * the parent state.
- */
- "goto +0;"
/* break link for r1, this is the only line that differs
- * compared to precision_cross_state()
+ * compared to the previous test
*/
"r1 = 0;"
- /* force r0 to be precise, this immediately marks r1 and r2 as
- * precise as well because of shared IDs
+ "if r0 > 7 goto +0;"
+ /* force r0 to be precise,
+ * this eventually marks r2 as precise because of shared IDs
*/
"r3 = r10;"
"r3 += r0;"
@@ -164,10 +156,16 @@ __naked void precision_cross_state_broken_link(void)
*/
SEC("socket")
__success __log_level(2)
-__msg("11: (0f) r2 += r1")
+__msg("12: (0f) r2 += r1")
/* Current state */
-__msg("frame2: last_idx 11 first_idx 10 subseq_idx -1")
-__msg("frame2: regs=r1 stack= before 10: (bf) r2 = r10")
+__msg("frame2: last_idx 12 first_idx 11 subseq_idx -1 ")
+__msg("frame2: regs=r1 stack= before 11: (bf) r2 = r10")
+__msg("frame2: parent state regs=r1 stack=")
+__msg("frame1: parent state regs= stack=")
+__msg("frame0: parent state regs= stack=")
+/* Parent state */
+__msg("frame2: last_idx 10 first_idx 10 subseq_idx 11 ")
+__msg("frame2: regs=r1 stack= before 10: (25) if r1 > 0x7 goto pc+0")
__msg("frame2: parent state regs=r1 stack=")
/* frame1.r{6,7} are marked because mark_precise_scalar_ids()
* looks for all registers with frame2.r1.id in the current state
@@ -192,7 +190,7 @@ __msg("frame1: regs=r1 stack= before 4: (85) call pc+1")
__msg("frame0: parent state regs=r1,r6 stack=")
/* Parent state */
__msg("frame0: last_idx 3 first_idx 1 subseq_idx 4")
-__msg("frame0: regs=r0,r1,r6 stack= before 3: (bf) r6 = r0")
+__msg("frame0: regs=r1,r6 stack= before 3: (bf) r6 = r0")
__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0")
__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255")
__flag(BPF_F_TEST_STATE_FREQ)
@@ -230,7 +228,8 @@ static __naked __noinline __used
void precision_many_frames__bar(void)
{
asm volatile (
- /* force r1 to be precise, this immediately marks:
+ "if r1 > 7 goto +0;"
+ /* force r1 to be precise, this eventually marks:
* - bar frame r1
* - foo frame r{1,6,7}
* - main frame r{1,6}
@@ -247,14 +246,16 @@ void precision_many_frames__bar(void)
*/
SEC("socket")
__success __log_level(2)
+__msg("11: (0f) r2 += r1")
/* foo frame */
-__msg("frame1: regs=r1 stack=-8,-16 before 9: (bf) r2 = r10")
+__msg("frame1: regs=r1 stack= before 10: (bf) r2 = r10")
+__msg("frame1: regs=r1 stack= before 9: (25) if r1 > 0x7 goto pc+0")
__msg("frame1: regs=r1 stack=-8,-16 before 8: (7b) *(u64 *)(r10 -16) = r1")
__msg("frame1: regs=r1 stack=-8 before 7: (7b) *(u64 *)(r10 -8) = r1")
__msg("frame1: regs=r1 stack= before 4: (85) call pc+2")
/* main frame */
-__msg("frame0: regs=r0,r1 stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r1")
-__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0")
+__msg("frame0: regs=r1 stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r1")
+__msg("frame0: regs=r1 stack= before 2: (bf) r1 = r0")
__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255")
__flag(BPF_F_TEST_STATE_FREQ)
__naked void precision_stack(void)
@@ -283,7 +284,8 @@ void precision_stack__foo(void)
*/
"*(u64*)(r10 - 8) = r1;"
"*(u64*)(r10 - 16) = r1;"
- /* force r1 to be precise, this immediately marks:
+ "if r1 > 7 goto +0;"
+ /* force r1 to be precise, this eventually marks:
* - foo frame r1,fp{-8,-16}
* - main frame r1,fp{-8}
*/
@@ -299,15 +301,17 @@ void precision_stack__foo(void)
SEC("socket")
__success __log_level(2)
/* r{6,7} */
-__msg("11: (0f) r3 += r7")
-__msg("frame0: regs=r6,r7 stack= before 10: (bf) r3 = r10")
+__msg("12: (0f) r3 += r7")
+__msg("frame0: regs=r7 stack= before 11: (bf) r3 = r10")
+__msg("frame0: regs=r7 stack= before 9: (25) if r7 > 0x7 goto pc+0")
/* ... skip some insns ... */
__msg("frame0: regs=r6,r7 stack= before 3: (bf) r7 = r0")
__msg("frame0: regs=r0,r6 stack= before 2: (bf) r6 = r0")
/* r{8,9} */
-__msg("12: (0f) r3 += r9")
-__msg("frame0: regs=r8,r9 stack= before 11: (0f) r3 += r7")
+__msg("13: (0f) r3 += r9")
+__msg("frame0: regs=r9 stack= before 12: (0f) r3 += r7")
/* ... skip some insns ... */
+__msg("frame0: regs=r9 stack= before 10: (25) if r9 > 0x7 goto pc+0")
__msg("frame0: regs=r8,r9 stack= before 7: (bf) r9 = r0")
__msg("frame0: regs=r0,r8 stack= before 6: (bf) r8 = r0")
__flag(BPF_F_TEST_STATE_FREQ)
@@ -328,8 +332,9 @@ __naked void precision_two_ids(void)
"r9 = r0;"
/* clear r0 id */
"r0 = 0;"
- /* force checkpoint */
- "goto +0;"
+ /* propagate equal scalars precision */
+ "if r7 > 7 goto +0;"
+ "if r9 > 7 goto +0;"
"r3 = r10;"
/* force r7 to be precise, this also marks r6 */
"r3 += r7;"
@@ -341,6 +346,102 @@ __naked void precision_two_ids(void)
: __clobber_all);
}
+SEC("socket")
+__success __log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+/* check thar r0 and r6 have different IDs after 'if',
+ * collect_linked_regs() can't tie more than 6 registers for a single insn.
+ */
+__msg("8: (25) if r0 > 0x7 goto pc+0 ; R0=scalar(id=1")
+__msg("9: (bf) r6 = r6 ; R6_w=scalar(id=2")
+/* check that r{0-5} are marked precise after 'if' */
+__msg("frame0: regs=r0 stack= before 8: (25) if r0 > 0x7 goto pc+0")
+__msg("frame0: parent state regs=r0,r1,r2,r3,r4,r5 stack=:")
+__naked void linked_regs_too_many_regs(void)
+{
+ asm volatile (
+ /* r0 = random number up to 0xff */
+ "call %[bpf_ktime_get_ns];"
+ "r0 &= 0xff;"
+ /* tie r{0-6} IDs */
+ "r1 = r0;"
+ "r2 = r0;"
+ "r3 = r0;"
+ "r4 = r0;"
+ "r5 = r0;"
+ "r6 = r0;"
+ /* propagate range for r{0-6} */
+ "if r0 > 7 goto +0;"
+ /* make r6 appear in the log */
+ "r6 = r6;"
+ /* force r0 to be precise,
+ * this would cause r{0-4} to be precise because of shared IDs
+ */
+ "r7 = r10;"
+ "r7 += r0;"
+ "r0 = 0;"
+ "exit;"
+ :
+ : __imm(bpf_ktime_get_ns)
+ : __clobber_all);
+}
+
+SEC("socket")
+__failure __log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+__msg("div by zero")
+__naked void linked_regs_broken_link_2(void)
+{
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "r7 = r0;"
+ "r8 = r0;"
+ "call %[bpf_get_prandom_u32];"
+ "if r0 > 1 goto +0;"
+ /* r7.id == r8.id,
+ * thus r7 precision implies r8 precision,
+ * which implies r0 precision because of the conditional below.
+ */
+ "if r8 >= r0 goto 1f;"
+ /* break id relation between r7 and r8 */
+ "r8 += r8;"
+ /* make r7 precise */
+ "if r7 == 0 goto 1f;"
+ "r0 /= 0;"
+"1:"
+ "r0 = 42;"
+ "exit;"
+ :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+/* Check that mark_chain_precision() for one of the conditional jump
+ * operands does not trigger equal scalars precision propagation.
+ */
+SEC("socket")
+__success __log_level(2)
+__msg("3: (25) if r1 > 0x100 goto pc+0")
+__msg("frame0: regs=r1 stack= before 2: (bf) r1 = r0")
+__naked void cjmp_no_linked_regs_trigger(void)
+{
+ asm volatile (
+ /* r0 = random number up to 0xff */
+ "call %[bpf_ktime_get_ns];"
+ "r0 &= 0xff;"
+ /* tie r0.id == r1.id */
+ "r1 = r0;"
+ /* the jump below would be predicted, thus r1 would be marked precise,
+ * this should not imply precision mark for r0
+ */
+ "if r1 > 256 goto +0;"
+ "r0 = 0;"
+ "exit;"
+ :
+ : __imm(bpf_ktime_get_ns)
+ : __clobber_all);
+}
+
/* Verify that check_ids() is used by regsafe() for scalars.
*
* r9 = ... some pointer with range X ...
diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
index 1f71f596d33f..07a2527a8f47 100644
--- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
+++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
@@ -392,7 +392,7 @@ __naked void spill_32bit_of_64bit_fail(void)
*(u32*)(r10 - 8) = r1; \
/* 32-bit fill r2 from stack. */ \
r2 = *(u32*)(r10 - 8); \
- /* Compare r2 with another register to trigger find_equal_scalars.\
+ /* Compare r2 with another register to trigger sync_linked_regs.\
* Having one random bit is important here, otherwise the verifier cuts\
* the corners. If the ID was mistakenly preserved on spill, this would\
* cause the verifier to think that r1 is also equal to zero in one of\
@@ -431,7 +431,7 @@ __naked void spill_16bit_of_32bit_fail(void)
*(u16*)(r10 - 8) = r1; \
/* 16-bit fill r2 from stack. */ \
r2 = *(u16*)(r10 - 8); \
- /* Compare r2 with another register to trigger find_equal_scalars.\
+ /* Compare r2 with another register to trigger sync_linked_regs.\
* Having one random bit is important here, otherwise the verifier cuts\
* the corners. If the ID was mistakenly preserved on spill, this would\
* cause the verifier to think that r1 is also equal to zero in one of\
diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
index 4b8b0f45d17d..a188e26f04da 100644
--- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
@@ -141,7 +141,7 @@ __msg("mark_precise: frame0: last_idx 14 first_idx 9")
__msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7")
__msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4")
__msg("mark_precise: frame0: regs=r6 stack= before 11: (25) if r6 > 0x3 goto pc+4")
-__msg("mark_precise: frame0: regs=r6 stack= before 10: (bf) r6 = r0")
+__msg("mark_precise: frame0: regs=r0,r6 stack= before 10: (bf) r6 = r0")
__msg("mark_precise: frame0: regs=r0 stack= before 9: (85) call bpf_loop")
/* State entering callback body popped from states stack */
__msg("from 9 to 17: frame1:")
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 8a2ff81d8350..59a020c35647 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -44,7 +44,7 @@
mark_precise: frame0: regs=r2 stack= before 23\
mark_precise: frame0: regs=r2 stack= before 22\
mark_precise: frame0: regs=r2 stack= before 20\
- mark_precise: frame0: parent state regs=r2 stack=:\
+ mark_precise: frame0: parent state regs=r2,r9 stack=:\
mark_precise: frame0: last_idx 19 first_idx 10\
mark_precise: frame0: regs=r2,r9 stack= before 19\
mark_precise: frame0: regs=r9 stack= before 18\
@@ -106,7 +106,7 @@
mark_precise: frame0: regs=r2 stack= before 22\
mark_precise: frame0: parent state regs=r2 stack=:\
mark_precise: frame0: last_idx 20 first_idx 20\
- mark_precise: frame0: regs=r2,r9 stack= before 20\
+ mark_precise: frame0: regs=r2 stack= before 20\
mark_precise: frame0: parent state regs=r2,r9 stack=:\
mark_precise: frame0: last_idx 19 first_idx 17\
mark_precise: frame0: regs=r2,r9 stack= before 19\
diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c
index e0aed424fe42..8f05212f8232 100644
--- a/tools/testing/selftests/ptp/testptp.c
+++ b/tools/testing/selftests/ptp/testptp.c
@@ -121,7 +121,6 @@ static void usage(char *progname)
" -d name device to open\n"
" -e val read 'val' external time stamp events\n"
" -f val adjust the ptp clock frequency by 'val' ppb\n"
- " -F chan Enable single channel mask and keep device open for debugfs verification.\n"
" -g get the ptp clock time\n"
" -h prints this message\n"
" -i val index for event/trigger\n"
@@ -190,7 +189,6 @@ int main(int argc, char *argv[])
int seconds = 0;
int readonly = 0;
int settime = 0;
- int channel = -1;
int64_t t1, t2, tp;
int64_t interval, offset;
@@ -200,7 +198,7 @@ int main(int argc, char *argv[])
progname = strrchr(argv[0], '/');
progname = progname ? 1+progname : argv[0];
- while (EOF != (c = getopt(argc, argv, "cd:e:f:F:ghH:i:k:lL:n:o:p:P:rsSt:T:w:x:Xz"))) {
+ while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:n:o:p:P:rsSt:T:w:x:Xz"))) {
switch (c) {
case 'c':
capabilities = 1;
@@ -214,9 +212,6 @@ int main(int argc, char *argv[])
case 'f':
adjfreq = atoi(optarg);
break;
- case 'F':
- channel = atoi(optarg);
- break;
case 'g':
gettime = 1;
break;
@@ -618,18 +613,6 @@ int main(int argc, char *argv[])
free(xts);
}
- if (channel >= 0) {
- if (ioctl(fd, PTP_MASK_CLEAR_ALL)) {
- perror("PTP_MASK_CLEAR_ALL");
- } else if (ioctl(fd, PTP_MASK_EN_SINGLE, (unsigned int *)&channel)) {
- perror("PTP_MASK_EN_SINGLE");
- } else {
- printf("Channel %d exclusively enabled. Check on debugfs.\n", channel);
- printf("Press any key to continue\n.");
- getchar();
- }
- }
-
close(fd);
return 0;
}
^ permalink raw reply related [flat|nested] 2+ messages in thread
end of thread, other threads:[~2026-07-04 11:59 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-07-04 11:59 Linux 6.6.144 Greg Kroah-Hartman
2026-07-04 11:59 ` Greg Kroah-Hartman
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox