- Jan 05, 2022
-
-
Wei Yongjun authored
[ Upstream commit 1b9dadba ] 'phy->pending_skb' is alloced when device probe, but forgot to free in the error handling path and remove path, this cause memory leak as follows: unreferenced object 0xffff88800bc06800 (size 512): comm "8", pid 11775, jiffies 4295159829 (age 9.032s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000d66c09ce>] __kmalloc_node_track_caller+0x1ed/0x450 [<00000000c93382b3>] kmalloc_reserve+0x37/0xd0 [<000000005fea522c>] __alloc_skb+0x124/0x380 [<0000000019f29f9a>] st21nfca_hci_i2c_probe+0x170/0x8f2 Fix it by freeing 'pending_skb' in error and remove. Fixes: 68957303 ("NFC: ST21NFCA: Add driver for STMicroelectronics ST21NFCA NFC Chip") Reported-by:
Hulk Robot <hulkci@huawei.com> Signed-off-by:
-
Aleksander Jan Bajkowski authored
[ Upstream commit 5be60a94 ] Received frames have FCS truncated. There is no need to subtract FCS length from the statistics. Fixes: fe1a5642 ("net: lantiq: Add Lantiq / Intel VRX200 Ethernet driver") Signed-off-by:
-
Christophe JAILLET authored
[ Upstream commit 1cd5384c ] 'ndev' is a managed resource allocated with devm_alloc_etherdev(), so there is no need to call free_netdev() explicitly or there will be a double free(). Simplify all error handling paths accordingly. Fixes: d51b6ce4 ("net: ethernet: add ag71xx driver") Signed-off-by:
-
Matthias-Christian Ott authored
[ Upstream commit ca506fca ] The D-Link DSB-650TX (2001:4002) is unable to receive Ethernet frames that are longer than 1518 octets, for example, Ethernet frames that contain 802.1Q VLAN tags. The frames are sent to the pegasus driver via USB but the driver discards them because they have the Long_pkt field set to 1 in the received status report. The function read_bulk_callback of the pegasus driver treats such received "packets" (in the terminology of the hardware) as errors but the field simply does just indicate that the Ethernet frame (MAC destination to FCS) is longer than 1518 octets. It seems that in the 1990s there was a distinction between "giant" (> 1518) and "runt" (< 64) frames and the hardware includes flags to indicate this distinction. It seems that the purpose of the distinction "giant" frames was to not allow infinitely long frames due to transmission errors and to allow hardware to have an upper limit of the frame size. However, the hardware already has such limit with its 2048 octet receive buffer and, therefore, Long_pkt is merely a convention and should not be treated as a receive error. Actually, the hardware is even able to receive Ethernet frames with 2048 octets which exceeds the claimed limit frame size limit of the driver of 1536 octets (PEGASUS_MTU). Fixes: 1da177e4 ("Linux-2.6.12-rc2") Signed-off-by:
-
Karsten Graul authored
[ Upstream commit 6d7373da ] In smc_wr_tx_send_wait() the completion on index specified by pend->idx is initialized and after smc_wr_tx_send() was called the wait for completion starts. pend->idx is used to get the correct index for the wait, but the pend structure could already be cleared in smc_wr_tx_process_cqe(). Introduce pnd_idx to hold and use a local copy of the correct index. Fixes: 09c61d24 ("net/smc: wait for departure of an IB message") Signed-off-by:
-
Xin Long authored
[ Upstream commit 5ec7d18d ] This patch is to delay the endpoint free by calling call_rcu() to fix another use-after-free issue in sctp_sock_dump(): BUG: KASAN: use-after-free in __lock_acquire+0x36d9/0x4c20 Call Trace: __lock_acquire+0x36d9/0x4c20 kernel/locking/lockdep.c:3218 lock_acquire+0x1ed/0x520 kernel/locking/lockdep.c:3844 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline] _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168 spin_lock_bh include/linux/spinlock.h:334 [inline] __lock_sock+0x203/0x350 net/core/sock.c:2253 lock_sock_nested+0xfe/0x120 net/core/sock.c:2774 lock_sock include/net/sock.h:1492 [inline] sctp_sock_dump+0x122/0xb20 net/sctp/diag.c:324 sctp_for_each_transport+0x2b5/0x370 net/sctp/socket.c:5091 sctp_diag_dump+0x3ac/0x660 net/sctp/diag.c:527 __inet_diag_dump+0xa8/0x140 net/ipv4/inet_diag.c:1049 inet_diag_dump+0x9b/0x110 net/ipv4/inet_diag.c:1065 netlink_dump+0x606/0x1080 net/netlink/af_netlink.c:2244 __netlink_dump_start+0x59a/0x7c0 net/netlink/af_netlink.c:2352 netlink_dump_start include/linux/netlink.h:216 [inline] inet_diag_handler_cmd+0x2ce/0x3f0 net/ipv4/inet_diag.c:1170 __sock_diag_cmd net/core/sock_diag.c:232 [inline] sock_diag_rcv_msg+0x31d/0x410 net/core/sock_diag.c:263 netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2477 sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:274 This issue occurs when asoc is peeled off and the old sk is freed after getting it by asoc->base.sk and before calling lock_sock(sk). To prevent the sk free, as a holder of the sk, ep should be alive when calling lock_sock(). This patch uses call_rcu() and moves sock_put and ep free into sctp_endpoint_destroy_rcu(), so that it's safe to try to hold the ep under rcu_read_lock in sctp_transport_traverse_process(). If sctp_endpoint_hold() returns true, it means this ep is still alive and we have held it and can continue to dump it; If it returns false, it means this ep is dead and can be freed after rcu_read_unlock, and we should skip it. In sctp_sock_dump(), after locking the sk, if this ep is different from tsp->asoc->ep, it means during this dumping, this asoc was peeled off before calling lock_sock(), and the sk should be skipped; If this ep is the same with tsp->asoc->ep, it means no peeloff happens on this asoc, and due to lock_sock, no peeloff will happen either until release_sock. Note that delaying endpoint free won't delay the port release, as the port release happens in sctp_endpoint_destroy() before calling call_rcu(). Also, freeing endpoint by call_rcu() makes it safe to access the sk by asoc->base.sk in sctp_assocs_seq_show() and sctp_rcv(). Thanks Jones to bring this issue up. v1->v2: - improve the changelog. - add kfree(ep) into sctp_endpoint_destroy_rcu(), as Jakub noticed. Reported-by:
-
Coco Li authored
[ Upstream commit 5471d522 ] The below referenced commit correctly updated the computation of number of segments (gso_size) by using only the gso payload size and removing the header lengths. With this change the regression test started failing. Update the tests to match this new behavior. Both IPv4 and IPv6 tests are updated, as a separate patch in this series will update udp_v6_send_skb to match this change in udp_send_skb. Fixes: 158390e4 ("udp: using datalen to cap max gso segments") Signed-off-by:
-
Coco Li authored
[ Upstream commit 736ef37f ] The max number of UDP gso segments is intended to cap to UDP_MAX_SEGMENTS, this is checked in udp_send_skb(). skb->len contains network and transport header len here, we should use only data len instead. This is the ipv6 counterpart to the below referenced commit, which missed the ipv6 change Fixes: 158390e4 ("udp: using datalen to cap max gso segments") Signed-off-by:
-
Chris Mi authored
[ Upstream commit 2820110d ] When there is ct or sample action, the ct or sample rule will be deleted and return. But if there is an extra mirror action, the forward rule can't be deleted because of the return. Fix it by removing the return. Fixes: 69e2916e ("net/mlx5: CT: Add support for mirroring") Fixes: f94d6389 ("net/mlx5e: TC, Add support to offload sample action") Signed-off-by:
-
Roi Dayan authored
[ Upstream commit f3e02e47 ] Instead of having sparse ifdefs in source files use a single ifdef in the tc sample header file and use stubs. Signed-off-by:
-
Maxim Mikityanskiy authored
[ Upstream commit 19c4aba2 ] There are two ICOSQs per channel: one is needed for RX, and the other for async operations (XSK TX, kTLS offload). Currently, the recovery flow for both is the same, and async ICOSQ is mistakenly treated like the regular ICOSQ. This patch prevents running the regular ICOSQ recovery on async ICOSQ. The purpose of async ICOSQ is to handle XSK wakeup requests and post kTLS offload RX parameters, it has nothing to do with RQ and XSKRQ UMRs, so the regular recovery sequence is not applicable here. Fixes: be5323c8 ("net/mlx5e: Report and recover from CQE error on ICOSQ") Signed-off-by:
-
Maxim Mikityanskiy authored
[ Upstream commit 17958d7c ] Both regular RQ and XSKRQ use the same ICOSQ for UMRs. When doing recovery for the ICOSQ, don't forget to deactivate XSKRQ. XSK can be opened and closed while channels are active, so a new mutex prevents the ICOSQ recovery from running at the same time. The ICOSQ recovery deactivates and reactivates XSKRQ, so any parallel change in XSK state would break consistency. As the regular RQ is running, it's not enough to just flush the recovery work, because it can be rescheduled. Fixes: be5323c8 ("net/mlx5e: Report and recover from CQE error on ICOSQ") Signed-off-by:
-
Amir Tzin authored
[ Upstream commit 918fc385 ] Function mlx5e_tx_reporter_dump_sq() casts its void * argument to struct mlx5e_txqsq *, but in TX-timeout-recovery flow the argument is actually of type struct mlx5e_tx_timeout_ctx *. mlx5_core 0000:08:00.1 enp8s0f1: TX timeout detected mlx5_core 0000:08:00.1 enp8s0f1: TX timeout on queue: 1, SQ: 0x11ec, CQ: 0x146d, SQ Cons: 0x0 SQ Prod: 0x1, usecs since last trans: 21565000 BUG: stack guard page was hit at 0000000093f1a2de (stack is 00000000b66ea0dc..000000004d932dae) kernel stack overflow (page fault): 0000 [#1] SMP NOPTI CPU: 5 PID: 95 Comm: kworker/u20:1 Tainted: G W OE 5.13.0_mlnx #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Workqueue: mlx5e mlx5e_tx_timeout_work [mlx5_core] RIP: 0010:mlx5e_tx_reporter_dump_sq+0xd3/0x180 [mlx5_core] Call Trace: mlx5e_tx_reporter_dump+0x43/0x1c0 [mlx5_core] devlink_health_do_dump.part.91+0x71/0xd0 devlink_health_report+0x157/0x1b0 mlx5e_reporter_tx_timeout+0xb9/0xf0 [mlx5_core] ? mlx5e_tx_reporter_err_cqe_recover+0x1d0/0x1d0 [mlx5_core] ? mlx5e_health_queue_dump+0xd0/0xd0 [mlx5_core] ? update_load_avg+0x19b/0x550 ? set_next_entity+0x72/0x80 ? pick_next_task_fair+0x227/0x340 ? finish_task_switch+0xa2/0x280 mlx5e_tx_timeout_work+0x83/0xb0 [mlx5_core] process_one_work+0x1de/0x3a0 worker_thread+0x2d/0x3c0 ? process_one_work+0x3a0/0x3a0 kthread+0x115/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x1f/0x30 --[ end trace 51ccabea504edaff ]--- RIP: 0010:mlx5e_tx_reporter_dump_sq+0xd3/0x180 PKRU: 55555554 Kernel panic - not syncing: Fatal exception Kernel Offset: disabled end Kernel panic - not syncing: Fatal exception To fix this bug add a wrapper for mlx5e_tx_reporter_dump_sq() which extracts the sq from struct mlx5e_tx_timeout_ctx and set it as the TX-timeout-recovery flow dump callback. Fixes: 5f29458b ("net/mlx5e: Support dump callback in TX reporter") Signed-off-by:
-
Chris Mi authored
[ Upstream commit d671e109 ] Only prio 1 is supported if firmware doesn't support ignore flow level for nic mode. The offending commit removed the check wrongly. Add it back. Fixes: 9a99c8f1 ("net/mlx5e: E-Switch, Offload all chain 0 priorities when modify header and forward action is not supported") Signed-off-by:
-
Moshe Shemesh authored
[ Upstream commit 33de865f ] SF do not directly control the PCI device. During recovery flow SF should not be allowed to do pci disable or pci reset, its PF will do it. It fixes the following kernel trace: mlx5_core.sf mlx5_core.sf.25: mlx5_health_try_recover:387:(pid 40948): starting health recovery flow mlx5_core 0000:03:00.0: mlx5_pci_slot_reset was called mlx5_core 0000:03:00.0: wait vital counter value 0xab175 after 1 iterations mlx5_core.sf mlx5_core.sf.25: firmware version: 24.32.532 mlx5_core.sf mlx5_core.sf.23: mlx5_health_try_recover:387:(pid 40946): starting health recovery flow mlx5_core 0000:03:00.0: mlx5_pci_slot_reset was called mlx5_core 0000:03:00.0: wait vital counter value 0xab193 after 1 iterations mlx5_core.sf mlx5_core.sf.23: firmware version: 24.32.532 mlx5_core.sf mlx5_core.sf.25: mlx5_cmd_check:813:(pid 40948): ENABLE_HCA(0x104) op_mod(0x0) failed, status bad resource state(0x9), syndrome (0x658908) mlx5_core.sf mlx5_core.sf.25: mlx5_function_setup:1292:(pid 40948): enable hca failed mlx5_core.sf mlx5_core.sf.25: mlx5_health_try_recover:389:(pid 40948): health recovery failed Fixes: 1958fc2f ("net/mlx5: SF, Add auxiliary device driver") Signed-off-by:
-
Shay Drory authored
[ Upstream commit aa968f92 ] In case IRQ layer failed to find or to request irq, the driver is printing the first cpu of the provided affinity as part of the error print. Empty affinity is a valid input for the IRQ layer, and it is an error to call cpumask_first() on empty affinity. Remove the first cpu print from the error message. Fixes: c36326d3 ("net/mlx5: Round-Robin EQs over IRQs") Signed-off-by:
-
Miaoqian Lin authored
[ Upstream commit 6b8b4258 ] The mlx5_get_uars_page() function returns error pointers. Using IS_ERR() to check the return value to fix this. Fixes: 4ec9e7b0 ("net/mlx5: DR, Expose steering domain functionality") Signed-off-by:
-
Dan Carpenter authored
[ Upstream commit 9020be11 ] The "mybuf" string comes from the user, so we need to ensure that it is NUL terminated. Link: https://lore.kernel.org/r/20211214070527.GA27934@kili Fixes: bd2cdd5e ("scsi: lpfc: NVME Initiator: Add debugfs support") Reviewed-by:
-
Tom Rix authored
commit 732bc2ff upstream. Clang static analysis reports this warning hooks.c:5765:6: warning: 4th function call argument is an uninitialized value if (selinux_xfrm_postroute_last(sksec->sid, skb, &ad, proto)) ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ selinux_parse_skb() can return ok without setting proto. The later call to selinux_xfrm_postroute_last() does an early check of proto and can return ok if the garbage proto value matches. So initialize proto. Cc: stable@vger.kernel.org Fixes: eef9b416 ("selinux: cleanup selinux_xfrm_sock_rcv_skb() and selinux_xfrm_postroute_last()") Signed-off-by:
-
Javier Martinez Canillas authored
commit 4bc5e64e upstream. Commit 8633ef82 ("drivers/firmware: consolidate EFI framebuffer setup for all arches") made the Generic System Framebuffers (sysfb) driver able to be built on non-x86 architectures. But it left the efifb_setup_from_dmi() function prototype declaration in the architecture specific headers. This could lead to the following compiler warning as reported by the kernel test robot: drivers/firmware/efi/sysfb_efi.c:70:6: warning: no previous prototype for function 'efifb_setup_from_dmi' [-Wmissing-prototypes] void efifb_setup_from_dmi(struct screen_info *si, const char *opt) ^ drivers/firmware/efi/sysfb_efi.c:70:1: note: declare 'static' if the function is not intended to be used outside of this translation unit void efifb_setup_from_dmi(struct screen_info *si, const char *opt) Fixes: 8633ef82 ("drivers/firmware: consolidate EFI framebuffer setup for all arches") Reported-by:
-
Michael Ellerman authored
commit 8d84fca4 upstream. In note_prot_wx() we bail out without reporting anything if CONFIG_PPC_DEBUG_WX is disabled. But CONFIG_PPC_DEBUG_WX was removed in the conversion to generic ptdump, we now need to use CONFIG_DEBUG_WX instead. Fixes: e0847283 ("powerpc/ptdump: Convert powerpc to GENERIC_PTDUMP") Cc: stable@vger.kernel.org # v5.15+ Signed-off-by:
-
Heiko Carstens authored
commit 4eb1782e upstream. Commit 85bf17b2 ("recordmcount.pl: look for jgnop instruction as well as bcrl on s390") added a new alternative mnemonic for the existing brcl instruction. This is required for the combination old gcc version (pre 9.0) and binutils since version 2.37. However at the same time this commit introduced a typo, replacing brcl with bcrl. As a result no mcount locations are detected anymore with old gcc versions (pre 9.0) and binutils before version 2.37. Fix this by using the correct mnemonic again. Reported-by:
-
Libin Yang authored
[ Upstream commit 78ea40ef ] In the HDAS ACPI scope, the SoundWire may not be the direct child of HDAS. It needs to go through the ACPI table at max depth of 2 to find the SoundWire device from HDAS. Reviewed-by:
-
Libin Yang authored
[ Upstream commit 385f287f ] The existing code currently sets a pointer to an ACPI handle before checking that it's actually a SoundWire controller. This can lead to issues where the graph walk continues and eventually fails, but the pointer was set already. This patch changes the logic so that the information provided to the caller is set when a controller is found. Reviewed-by:
-
Jackie Liu authored
[ Upstream commit d7f55471 ] Fix modpost Section mismatch error in memblock_phys_alloc() [...] WARNING: modpost: vmlinux.o(.text.unlikely+0x1dcc): Section mismatch in reference from the function memblock_phys_alloc() to the function .init.text:memblock_phys_alloc_range() The function memblock_phys_alloc() references the function __init memblock_phys_alloc_range(). This is often because memblock_phys_alloc lacks a __init annotation or the annotation of memblock_phys_alloc_range is wrong. ERROR: modpost: Section mismatches detected. Set CONFIG_SECTION_MISMATCH_WARN_ONLY=y to allow them. [...] memblock_phys_alloc() is a one-line wrapper, make it __always_inline to avoid these section mismatches. Reported-by:
-
Wang Qing authored
[ Upstream commit eb66fb03 ] This should be (res->end - res->start + 1) here actually, use resource_size() derectly. Signed-off-by:
-
Miaoqian Lin authored
[ Upstream commit 804034c4 ] The devm_ioremap() function returns NULL on error, it doesn't return error pointers. Also according to doc of device_property_read_u64_array, values in info array are properties of device or NULL. Signed-off-by:
-
Helge Deller authored
[ Upstream commit 484730e5 ] When a trap 7 (Instruction access rights) occurs, this means the CPU couldn't execute an instruction due to missing execute permissions on the memory region. In this case it seems the CPU didn't even fetched the instruction from memory and thus did not store it in the cr19 (IIR) register before calling the trap handler. So, the trap handler will find some random old stale value in cr19. This patch simply overwrites the stale IIR value with a constant magic "bad food" value (0xbaadf00d), in the hope people don't start to try to understand the various random IIR values in trap 7 dumps. Noticed-by:
-
Paul Blakey authored
[ Upstream commit ec624fe7 ] BPF layer extends the qdisc control block via struct bpf_skb_data_end and because of that there is no more room to add variables to the qdisc layer control block without going over the skb->cb size. Extend the qdisc control block with a tc control block, and move all tc related variables to there as a pre-step for extending the tc control block with additional members. Signed-off-by:
-
Tetsuo Handa authored
[ Upstream commit f702e110 ] hwight16() is much faster. While we are at it, no need to include "perm =" part into data_race() macro, for perm is a local variable that cannot be accessed by other threads. Signed-off-by:
-
Dmitry Vyukov authored
[ Upstream commit 04e57a2d ] If tomoyo is used in a testing/fuzzing environment in learning mode, for lots of domains the quota will be exceeded and stay exceeded for prolonged periods of time. In such cases it's pointless (and slow) to walk the whole acl list again and again just to rediscover that the quota is exceeded. We already have the TOMOYO_DIF_QUOTA_WARNED flag that notes the overflow condition. Check it early to avoid the slowdown. [penguin-kernel] This patch causes a user visible change that the learning mode will not be automatically resumed after the quota is increased. To resume the learning mode, administrator will need to explicitly clear TOMOYO_DIF_QUOTA_WARNED flag after increasing the quota. But I think that this change is generally preferable, for administrator likely wants to optimize the acl list for that domain before increasing the quota, or that domain likely hits the quota again. Therefore, don't try to care to clear TOMOYO_DIF_QUOTA_WARNED flag automatically when the quota for that domain changed. Signed-off-by:
-
Samuel Čavoj authored
[ Upstream commit 44ee250a ] The ASUS UM325UA suffers from the same issue as the ASUS UX425UA, which is a very similar laptop. The i8042 device is not usable immediately after boot and fails to initialize, requiring a deferred retry. Enable the deferred probe quirk for the UM325UA. BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1190256 Signed-off-by:
-
Takashi Iwai authored
[ Upstream commit 9222ba68 ] We've got a bug report about the non-working keyboard on ASUS ZenBook UX425UA. It seems that the PS/2 device isn't ready immediately at boot but takes some seconds to get ready. Until now, the only workaround is to defer the probe, but it's available only when the driver is a module. However, many distros, including openSUSE as in the original report, build the PS/2 input drivers into kernel, hence it won't work easily. This patch adds the support for the deferred probe for i8042 stuff as a workaround of the problem above. When the deferred probe mode is enabled and the device couldn't be probed, it'll be repeated with the standard deferred probe mechanism. The deferred probe mode is enabled either via the new option i8042.probe_defer or via the quirk table entry. As of this patch, the quirk table contains only ASUS ZenBook UX425UA. The deferred probe part is based on Fabio's initial work. BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1190256 Signed-off-by:
-
- Dec 29, 2021
-
-
Greg Kroah-Hartman authored
Link: https://lore.kernel.org/r/20211227151331.502501367@linuxfoundation.org Tested-by:
-
Rémi Denis-Courmont authored
commit 75a2f315 upstream. This ioctl() implicitly assumed that the socket was already bound to a valid local socket name, i.e. Phonet object. If the socket was not bound, two separate problems would occur: 1) We'd send an pipe enablement request with an invalid source object. 2) Later socket calls could BUG on the socket unexpectedly being connected yet not bound to a valid object. Reported-by:
-
George Kennedy authored
commit 158b515f upstream. Avoid double free in tun_free_netdev() by moving the dev->tstats and tun->security allocs to a new ndo_init routine (tun_net_init()) that will be called by register_netdevice(). ndo_init is paired with the desctructor (tun_free_netdev()), so if there's an error in register_netdevice() the destructor will handle the frees. BUG: KASAN: double-free or invalid-free in selinux_tun_dev_free_security+0x1a/0x20 security/selinux/hooks.c:5605 CPU: 0 PID: 25750 Comm: syz-executor416 Not tainted 5.16.0-rc2-syzk #1 Hardware name: Red Hat KVM, BIOS Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x89/0xb5 lib/dump_stack.c:106 print_address_description.constprop.9+0x28/0x160 mm/kasan/report.c:247 kasan_report_invalid_free+0x55/0x80 mm/kasan/report.c:372 ____kasan_slab_free mm/kasan/common.c:346 [inline] __kasan_slab_free+0x107/0x120 mm/kasan/common.c:374 kasan_slab_free include/linux/kasan.h:235 [inline] slab_free_hook mm/slub.c:1723 [inline] slab_free_freelist_hook mm/slub.c:1749 [inline] slab_free mm/slub.c:3513 [inline] kfree+0xac/0x2d0 mm/slub.c:4561 selinux_tun_dev_free_security+0x1a/0x20 security/selinux/hooks.c:5605 security_tun_dev_free_security+0x4f/0x90 security/security.c:2342 tun_free_netdev+0xe6/0x150 drivers/net/tun.c:2215 netdev_run_todo+0x4df/0x840 net/core/dev.c:10627 rtnl_unlock+0x13/0x20 net/core/rtnetlink.c:112 __tun_chr_ioctl+0x80c/0x2870 drivers/net/tun.c:3302 tun_chr_ioctl+0x2f/0x40 drivers/net/tun.c:3311 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:874 [inline] __se_sys_ioctl fs/ioctl.c:860 [inline] __x64_sys_ioctl+0x19d/0x220 fs/ioctl.c:860 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x80 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Reported-by:
-
Lin Ma authored
commit b2f37aea upstream. The previous commit 3e0588c2 ("hamradio: defer ax25 kfree after unregister_netdev") reorder the kfree operations and unregister_netdev operation to prevent UAF. This commit improves the previous one by also deferring the nullify of the ax->tty pointer. Otherwise, a NULL pointer dereference bug occurs. Partial of the stack trace is shown below. BUG: kernel NULL pointer dereference, address: 0000000000000538 RIP: 0010:ax_xmit+0x1f9/0x400 ... Call Trace: dev_hard_start_xmit+0xec/0x320 sch_direct_xmit+0xea/0x240 __qdisc_run+0x166/0x5c0 __dev_queue_xmit+0x2c7/0xaf0 ax25_std_establish_data_link+0x59/0x60 ax25_connect+0x3a0/0x500 ? security_socket_connect+0x2b/0x40 __sys_connect+0x96/0xc0 ? __hrtimer_init+0xc0/0xc0 ? common_nsleep+0x2e/0x50 ? switch_fpu_return+0x139/0x1a0 __x64_sys_connect+0x11/0x20 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The crash point is shown as below static void ax_encaps(...) { ... set_bit(TTY_DO_WRITE_WAKEUP, &ax->tty->flags); // ax->tty = NULL! ... } By placing the nullify action after the unregister_netdev, the ax->tty pointer won't be assigned as NULL net_device framework layer is well synchronized. Signed-off-by:
-
Lin Ma authored
commit 3e0588c2 upstream. There is a possible race condition (use-after-free) like below (USE) | (FREE) ax25_sendmsg | ax25_queue_xmit | dev_queue_xmit | __dev_queue_xmit | __dev_xmit_skb | sch_direct_xmit | ... xmit_one | netdev_start_xmit | tty_ldisc_kill __netdev_start_xmit | mkiss_close ax_xmit | kfree ax_encaps | | Even though there are two synchronization primitives before the kfree: 1. wait_for_completion(&ax->dead). This can prevent the race with routines from mkiss_ioctl. However, it cannot stop the routine coming from upper layer, i.e., the ax25_sendmsg. 2. netif_stop_queue(ax->dev). It seems that this line of code aims to halt the transmit queue but it fails to stop the routine that already being xmit. This patch reorder the kfree after the unregister_netdev to avoid the possible UAF as the unregister_netdev() is well synchronized and won't return if there is a running routine. Signed-off-by:
-
Lin Ma authored
commit 1ade48d0 upstream. The existing cleanup routine implementation is not well synchronized with the syscall routine. When a device is detaching, below race could occur. static int ax25_sendmsg(...) { ... lock_sock() ax25 = sk_to_ax25(sk); if (ax25->ax25_dev == NULL) // CHECK ... ax25_queue_xmit(skb, ax25->ax25_dev->dev); // USE ... } static void ax25_kill_by_device(...) { ... if (s->ax25_dev == ax25_dev) { s->ax25_dev = NULL; ... } Other syscall functions like ax25_getsockopt, ax25_getname, ax25_info_show also suffer from similar races. To fix them, this patch introduce lock_sock() into ax25_kill_by_device in order to guarantee that the nullify action in cleanup routine cannot proceed when another socket request is pending. Signed-off-by:
-
Hayes Wang authored
commit b24edca3 upstream. There are some chances that the actual base of hardware is different from the value recorded by driver, so we have to reset the variable of ocp_base to sync it. Set ocp_base to -1. Then, it would be updated and the new base would be set to the hardware next time. Signed-off-by:
-