January 2024 - Linux-stable-mirror

[PATCH v2 1/5] fuse: Fix VM_MAYSHARE and direct_io_allow_mmap

by Bernd Schubert

There were multiple issues with direct_io_allow_mmap: - fuse_link_write_file() was missing, resulting in warnings in fuse_write_file_get() and EIO from msync() - "vma->vm_ops = &fuse_file_vm_ops" was not set, but especially fuse_page_mkwrite is needed. The semantics of invalidate_inode_pages2() is so far not clearly defined in fuse_file_mmap. It dates back to commit 3121bfe76311 ("fuse: fix "direct_io" private mmap") Though, as direct_io_allow_mmap is a new feature, that was for MAP_PRIVATE only. As invalidate_inode_pages2() is calling into fuse_launder_folio() and writes out dirty pages, it should be safe to call invalidate_inode_pages2 for MAP_PRIVATE and MAP_SHARED as well. Cc: Hao Xu <howeyxu(a)tencent.com> Cc: stable(a)vger.kernel.org Fixes: e78662e818f9 ("fuse: add a new fuse init flag to relax restrictions in no cache mode") Signed-off-by: Bernd Schubert <bschubert(a)ddn.com> Reviewed-by: Amir Goldstein <amir73il(a)gmail.com> --- fs/fuse/file.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 148a71b8b4d0..243f469cac07 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2476,7 +2476,10 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) invalidate_inode_pages2(file->f_mapping); - return generic_file_mmap(file, vma); + if (!(vma->vm_flags & VM_MAYSHARE)) { + /* MAP_PRIVATE */ + return generic_file_mmap(file, vma); + } } if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) -- 2.40.1

1 year, 4 months

4
8
0 0

[PATCH] crypto: ccp - Fix null pointer dereference in __sev_platform_shutdown_locked

by Kim Phillips

The SEV platform device can be shutdown with a null psp_master, e.g., using DEBUG_TEST_DRIVER_REMOVE. Found using KASAN: [ 137.148210] ccp 0000:23:00.1: enabling device (0000 -> 0002) [ 137.162647] ccp 0000:23:00.1: no command queues available [ 137.170598] ccp 0000:23:00.1: sev enabled [ 137.174645] ccp 0000:23:00.1: psp enabled [ 137.178890] general protection fault, probably for non-canonical address 0xdffffc000000001e: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC KASAN NOPTI [ 137.182693] KASAN: null-ptr-deref in range [0x00000000000000f0-0x00000000000000f7] [ 137.182693] CPU: 93 PID: 1 Comm: swapper/0 Not tainted 6.8.0-rc1+ #311 [ 137.182693] RIP: 0010:__sev_platform_shutdown_locked+0x51/0x180 [ 137.182693] Code: 08 80 3c 08 00 0f 85 0e 01 00 00 48 8b 1d 67 b6 01 08 48 b8 00 00 00 00 00 fc ff df 48 8d bb f0 00 00 00 48 89 f9 48 c1 e9 03 <80> 3c 01 00 0f 85 fe 00 00 00 48 8b 9b f0 00 00 00 48 85 db 74 2c [ 137.182693] RSP: 0018:ffffc900000cf9b0 EFLAGS: 00010216 [ 137.182693] RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 000000000000001e [ 137.182693] RDX: 0000000000000000 RSI: 0000000000000008 RDI: 00000000000000f0 [ 137.182693] RBP: ffffc900000cf9c8 R08: 0000000000000000 R09: fffffbfff58f5a66 [ 137.182693] R10: ffffc900000cf9c8 R11: ffffffffac7ad32f R12: ffff8881e5052c28 [ 137.182693] R13: ffff8881e5052c28 R14: ffff8881758e43e8 R15: ffffffffac64abf8 [ 137.182693] FS: 0000000000000000(0000) GS:ffff889de7000000(0000) knlGS:0000000000000000 [ 137.182693] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 137.182693] CR2: 0000000000000000 CR3: 0000001cf7c7e000 CR4: 0000000000350ef0 [ 137.182693] Call Trace: [ 137.182693] <TASK> [ 137.182693] ? show_regs+0x6c/0x80 [ 137.182693] ? __die_body+0x24/0x70 [ 137.182693] ? die_addr+0x4b/0x80 [ 137.182693] ? exc_general_protection+0x126/0x230 [ 137.182693] ? asm_exc_general_protection+0x2b/0x30 [ 137.182693] ? __sev_platform_shutdown_locked+0x51/0x180 [ 137.182693] sev_firmware_shutdown.isra.0+0x1e/0x80 [ 137.182693] sev_dev_destroy+0x49/0x100 [ 137.182693] psp_dev_destroy+0x47/0xb0 [ 137.182693] sp_destroy+0xbb/0x240 [ 137.182693] sp_pci_remove+0x45/0x60 [ 137.182693] pci_device_remove+0xaa/0x1d0 [ 137.182693] device_remove+0xc7/0x170 [ 137.182693] really_probe+0x374/0xbe0 [ 137.182693] ? srso_return_thunk+0x5/0x5f [ 137.182693] __driver_probe_device+0x199/0x460 [ 137.182693] driver_probe_device+0x4e/0xd0 [ 137.182693] __driver_attach+0x191/0x3d0 [ 137.182693] ? __pfx___driver_attach+0x10/0x10 [ 137.182693] bus_for_each_dev+0x100/0x190 [ 137.182693] ? __pfx_bus_for_each_dev+0x10/0x10 [ 137.182693] ? __kasan_check_read+0x15/0x20 [ 137.182693] ? srso_return_thunk+0x5/0x5f [ 137.182693] ? _raw_spin_unlock+0x27/0x50 [ 137.182693] driver_attach+0x41/0x60 [ 137.182693] bus_add_driver+0x2a8/0x580 [ 137.182693] driver_register+0x141/0x480 [ 137.182693] __pci_register_driver+0x1d6/0x2a0 [ 137.182693] ? srso_return_thunk+0x5/0x5f [ 137.182693] ? esrt_sysfs_init+0x1cd/0x5d0 [ 137.182693] ? __pfx_sp_mod_init+0x10/0x10 [ 137.182693] sp_pci_init+0x22/0x30 [ 137.182693] sp_mod_init+0x14/0x30 [ 137.182693] ? __pfx_sp_mod_init+0x10/0x10 [ 137.182693] do_one_initcall+0xd1/0x470 [ 137.182693] ? __pfx_do_one_initcall+0x10/0x10 [ 137.182693] ? parameq+0x80/0xf0 [ 137.182693] ? srso_return_thunk+0x5/0x5f [ 137.182693] ? __kmalloc+0x3b0/0x4e0 [ 137.182693] ? kernel_init_freeable+0x92d/0x1050 [ 137.182693] ? kasan_populate_vmalloc_pte+0x171/0x190 [ 137.182693] ? srso_return_thunk+0x5/0x5f [ 137.182693] kernel_init_freeable+0xa64/0x1050 [ 137.182693] ? __pfx_kernel_init+0x10/0x10 [ 137.182693] kernel_init+0x24/0x160 [ 137.182693] ? __switch_to_asm+0x3e/0x70 [ 137.182693] ret_from_fork+0x40/0x80 [ 137.182693] ? __pfx_kernel_init+0x10/0x10 [ 137.182693] ret_from_fork_asm+0x1b/0x30 [ 137.182693] </TASK> [ 137.182693] Modules linked in: [ 137.538483] ---[ end trace 0000000000000000 ]--- Fixes: 1b05ece0c9315 ("crypto: ccp - During shutdown, check SEV data pointer before using") Cc: stable(a)vger.kernel.org Reviewed-by: Mario Limonciello <mario.limonciello(a)amd.com> Signed-off-by: Kim Phillips <kim.phillips(a)amd.com> --- drivers/crypto/ccp/sev-dev.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index fcaccd0b5a65..53b217a62104 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -534,10 +534,16 @@ EXPORT_SYMBOL_GPL(sev_platform_init); static int __sev_platform_shutdown_locked(int *error) { - struct sev_device *sev = psp_master->sev_data; + struct psp_device *psp = psp_master; + struct sev_device *sev; int ret; - if (!sev || sev->state == SEV_STATE_UNINIT) + if (!psp || !psp->sev_data) + return 0; + + sev = psp->sev_data; + + if (sev->state == SEV_STATE_UNINIT) return 0; ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error); -- 2.34.1

1 year, 4 months

4
4
0 0

[PATCH regression fix 0/2] Input: atkbd - Fix Dell XPS 13 line suspend/resume regression

by Hans de Goede

Hi Dmitry, There have been multiple reports that the keyboard on Dell XPS 13 9350 / 9360 / 9370 models has stopped working after a suspend/resume after the merging of commit 936e4d49ecbc ("Input: atkbd - skip ATKBD_CMD_GETID in translated mode"). See the 4 closes tags in the first patch for 4 reports of this. I have been working with the first reporter on resolving this and testing on his Dell XPS 13 9360 confirms that these patches fix things. Unfortunately the commit causing the issue has also been picked up by multiple stable kernel series now. Can you please send these fixes to Linus ASAP, so that they can also be backported to the stable series ASAP ? Alternatively we could revert the commit causing this, but that commit is know to fix issues on a whole bunch of other laptops so I would rather not revert it. Regards, Hans Hans de Goede (2): Input: atkbd - Skip ATKBD_CMD_SETLEDS when skipping ATKBD_CMD_GETID Input: atkbd - Do not skip atkbd_deactivate() when skipping ATKBD_CMD_GETID drivers/input/keyboard/atkbd.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) -- 2.43.0

1 year, 4 months

3
8
0 0

[PATCH net 0/9] mptcp: fixes for recent issues reported by CI's

by Matthieu Baerts (NGI0)

This series of 9 patches fixes issues mostly identified by CI's not managed by the MPTCP maintainers. Thank you Linero (LKFT) and Netdev maintainers (NIPA) for running our kunit and selftests tests! For the first patch, it took a bit of time to identify the root cause. Some MPTCP Join selftest subtests have been "flaky", mostly in slow environments. It appears to be due to the use of a TCP-specific helper on an MPTCP socket. A fix for kernels >= v5.15. Patches 2 to 4 add missing kernel config to support NetFilter tables needed for IPTables commands. These kconfigs are usually enabled in default configurations, but apparently not for all architectures. Patches 2 and 3 can be backported up to v5.11 and the 4th one up to v5.19. Patch 5 increases the time limit for MPTCP selftests. It appears that many CI's execute tests in a VM without acceleration supports, e.g. QEmu without KVM. As a result, the tests take longer. Plus, there are more and more tests. This patch modifies the timeout added in v5.18. Patch 6 reduces the maximum rate and delay of the different links in some Simult Flows selftest subtests. The goal is to let slow VMs reach the maximum speed. The original rate was introduced in v5.11. Patch 7 lets CI changing the prefix of the subtests titles, to be able to run the same selftest multiple times with different parameters. With different titles, tests will be considered as different and not override previous results as it is the case with some CI envs. Subtests have been introduced in v6.6. Patch 8 and 9 make some MPTCP Join selftest subtests quicker by stopping the transfer when the expected events have been seen. Patch 8 can be backported up to v6.5. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Matthieu Baerts (NGI0) (8): selftests: mptcp: add missing kconfig for NF Filter selftests: mptcp: add missing kconfig for NF Filter in v6 selftests: mptcp: add missing kconfig for NF Mangle selftests: mptcp: increase timeout to 30 min selftests: mptcp: decrease BW in simult flows selftests: mptcp: allow changing subtests prefix selftests: mptcp: join: stop transfer when check is done (part 1) selftests: mptcp: join: stop transfer when check is done (part 2) Paolo Abeni (1): mptcp: fix data re-injection from stale subflow net/mptcp/protocol.c | 3 --- tools/testing/selftests/net/mptcp/config | 3 +++ tools/testing/selftests/net/mptcp/mptcp_join.sh | 27 +++++++++-------------- tools/testing/selftests/net/mptcp/mptcp_lib.sh | 2 +- tools/testing/selftests/net/mptcp/settings | 2 +- tools/testing/selftests/net/mptcp/simult_flows.sh | 8 +++---- 6 files changed, 20 insertions(+), 25 deletions(-) --- base-commit: c9ec85153fea6873c52ed4f5055c87263f1b54f9 change-id: 20240131-upstream-net-20240131-mptcp-ci-issues-9d68b5601e74 Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

1 year, 4 months

2
10
0 0

[PATCH V2 net] hv_netvsc: Fix race condition between netvsc_probe and netvsc_remove

by Souradeep Chakrabarti

In commit ac5047671758 ("hv_netvsc: Disable NAPI before closing the VMBus channel"), napi_disable was getting called for all channels, including all subchannels without confirming if they are enabled or not. This caused hv_netvsc getting hung at napi_disable, when netvsc_probe() has finished running but nvdev->subchan_work has not started yet. netvsc_subchan_work() -> rndis_set_subchannel() has not created the sub-channels and because of that netvsc_sc_open() is not running. netvsc_remove() calls cancel_work_sync(&nvdev->subchan_work), for which netvsc_subchan_work did not run. netif_napi_add() sets the bit NAPI_STATE_SCHED because it ensures NAPI cannot be scheduled. Then netvsc_sc_open() -> napi_enable will clear the NAPIF_STATE_SCHED bit, so it can be scheduled. napi_disable() does the opposite. Now during netvsc_device_remove(), when napi_disable is called for those subchannels, napi_disable gets stuck on infinite msleep. This fix addresses this problem by ensuring that napi_disable() is not getting called for non-enabled NAPI struct. But netif_napi_del() is still necessary for these non-enabled NAPI struct for cleanup purpose. Call trace: [ 654.559417] task:modprobe state:D stack: 0 pid: 2321 ppid: 1091 flags:0x00004002 [ 654.568030] Call Trace: [ 654.571221] <TASK> [ 654.573790] __schedule+0x2d6/0x960 [ 654.577733] schedule+0x69/0xf0 [ 654.581214] schedule_timeout+0x87/0x140 [ 654.585463] ? __bpf_trace_tick_stop+0x20/0x20 [ 654.590291] msleep+0x2d/0x40 [ 654.593625] napi_disable+0x2b/0x80 [ 654.597437] netvsc_device_remove+0x8a/0x1f0 [hv_netvsc] [ 654.603935] rndis_filter_device_remove+0x194/0x1c0 [hv_netvsc] [ 654.611101] ? do_wait_intr+0xb0/0xb0 [ 654.615753] netvsc_remove+0x7c/0x120 [hv_netvsc] [ 654.621675] vmbus_remove+0x27/0x40 [hv_vmbus] Cc: stable(a)vger.kernel.org Fixes: ac5047671758 ("hv_netvsc: Disable NAPI before closing the VMBus channel") Signed-off-by: Souradeep Chakrabarti <schakrabarti(a)linux.microsoft.com> Reviewed-by: Dexuan Cui <decui(a)microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz(a)microsoft.com> --- V1 -> V2: Changed commit message, added some more details on napi NAPIF_STATE_SCHED bit set and reset. --- drivers/net/hyperv/netvsc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 1dafa44155d0..a6fcbda64ecc 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -708,7 +708,10 @@ void netvsc_device_remove(struct hv_device *device) /* Disable NAPI and disassociate its context from the device. */ for (i = 0; i < net_device->num_chn; i++) { /* See also vmbus_reset_channel_cb(). */ - napi_disable(&net_device->chan_table[i].napi); + /* only disable enabled NAPI channel */ + if (i < ndev->real_num_rx_queues) + napi_disable(&net_device->chan_table[i].napi); + netif_napi_del(&net_device->chan_table[i].napi); } -- 2.34.1

1 year, 4 months

3
2
0 0

[PATCH] tty: fix atomicity violation in n_tty_read

by Gui-Dong Han

In n_tty_read(): if (packet && tty->link->ctrl.pktstatus) { ... spin_lock_irq(&tty->link->ctrl.lock); cs = tty->link->ctrl.pktstatus; tty->link->ctrl.pktstatus = 0; spin_unlock_irq(&tty->link->ctrl.lock); *kb++ = cs; ... In n_tty_read() function, there is a potential atomicity violation issue. The tty->link->ctrl.pktstatus might be set to 0 after being checked, which could lead to incorrect values in the kernel space buffer pointer (kb/kbuf). The check if (packet && tty->link->ctrl.pktstatus) occurs outside the spin_lock_irq(&tty->link->ctrl.lock) block. This may lead to tty->link->ctrl.pktstatus being altered between the check and the lock, causing *kb++ = cs; to be assigned with a zero pktstatus value. This possible bug is found by an experimental static analysis tool developed by our team, BassCheck[1]. This tool analyzes the locking APIs to extract function pairs that can be concurrently executed, and then analyzes the instructions in the paired functions to identify possible concurrency bugs including data races and atomicity violations. The above possible bug is reported when our tool analyzes the source code of Linux 5.17. To resolve this atomicity issue, it is suggested to move the condition check if (packet && tty->link->ctrl.pktstatus) inside the spin_lock block. With this patch applied, our tool no longer reports the bug, with the kernel configuration allyesconfig for x86_64. Due to the absence of the requisite hardware, we are unable to conduct runtime testing of the patch. Therefore, our verification is solely based on code logic analysis. [1] https://sites.google.com/view/basscheck/ Fixes: 64d608db38ff ("tty: cumulate and document tty_struct::ctrl* members") Cc: stable(a)vger.kernel.org Signed-off-by: Gui-Dong Han <2045gemini(a)gmail.com> --- drivers/tty/n_tty.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index f252d0b5a434..df54ab0c4d8c 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -2222,19 +2222,23 @@ static ssize_t n_tty_read(struct tty_struct *tty, struct file *file, u8 *kbuf, add_wait_queue(&tty->read_wait, &wait); while (nr) { /* First test for status change. */ + spin_lock_irq(&tty->link->ctrl.lock); if (packet && tty->link->ctrl.pktstatus) { u8 cs; - if (kb != kbuf) + if (kb != kbuf) { + spin_unlock_irq(&tty->link->ctrl.lock); break; - spin_lock_irq(&tty->link->ctrl.lock); + } cs = tty->link->ctrl.pktstatus; tty->link->ctrl.pktstatus = 0; spin_unlock_irq(&tty->link->ctrl.lock); *kb++ = cs; nr--; break; + } else { + spin_unlock_irq(&tty->link->ctrl.lock); } - + if (!input_available_p(tty, 0)) { up_read(&tty->termios_rwsem); tty_buffer_flush_work(tty->port); -- 2.34.1

1 year, 4 months

6
7
0 0

[PATCH 5.10/5.15 0/1] media: atomisp: add error checking to atomisp_create_pipes_stream()

by Anastasia Belova

atomisp_create_pipes_stream does not handle errors in __create_pipes and __create_streams in versions 5.10 and 5.15. The following patch may fix it. Found by Linux Verification Center (linuxtesting.org) with Svace.

1 year, 4 months

1
2
0 0

[PATCH] HID: i2c-hid-of: fix NULL-deref on failed power up

by Johan Hovold

A while back the I2C HID implementation was split in an ACPI and OF part, but the new OF driver never initialises the client pointer which is dereferenced on power-up failures. Fixes: b33752c30023 ("HID: i2c-hid: Reorganize so ACPI and OF are separate modules") Cc: stable(a)vger.kernel.org # 5.12 Cc: Douglas Anderson <dianders(a)chromium.org> Signed-off-by: Johan Hovold <johan+linaro(a)kernel.org> --- drivers/hid/i2c-hid/i2c-hid-of.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hid/i2c-hid/i2c-hid-of.c b/drivers/hid/i2c-hid/i2c-hid-of.c index c4e1fa0273c8..8be4d576da77 100644 --- a/drivers/hid/i2c-hid/i2c-hid-of.c +++ b/drivers/hid/i2c-hid/i2c-hid-of.c @@ -87,6 +87,7 @@ static int i2c_hid_of_probe(struct i2c_client *client) if (!ihid_of) return -ENOMEM; + ihid_of->client = client; ihid_of->ops.power_up = i2c_hid_of_power_up; ihid_of->ops.power_down = i2c_hid_of_power_down; -- 2.43.0

1 year, 4 months

4
3
0 0

[PATCH] hv_netvsc:Register VF in netvsc_probe if NET_DEVICE_REGISTER missed

by Shradha Gupta

If hv_netvsc driver is removed and reloaded, the NET_DEVICE_REGISTER handler cannot perform VF register successfully as the register call is received before netvsc_probe is finished. This is because we register register_netdevice_notifier() very early(even before vmbus_driver_register()). To fix this, we try to register each such matching VF( if it is visible as a netdevice) at the end of netvsc_probe. Cc: stable(a)vger.kernel.org Fixes: 85520856466e ("hv_netvsc: Fix race of register_netdevice_notifier and VF register") Suggested-by: Dexuan Cui <decui(a)microsoft.com> Signed-off-by: Shradha Gupta <shradhagupta(a)linux.microsoft.com> Tested-on: Ubuntu22 Testcases: LISA testsuites verify_reload_hyperv_modules, perf_tcp_ntttcp_sriov --- drivers/net/hyperv/netvsc_drv.c | 49 ++++++++++++++++++++++++++++----- 1 file changed, 42 insertions(+), 7 deletions(-) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 706ea5263e87..25c4dc9cc4bd 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -42,6 +42,10 @@ #define LINKCHANGE_INT (2 * HZ) #define VF_TAKEOVER_INT (HZ / 10) +/* Macros to define the context of vf registration */ +#define VF_REG_IN_PROBE 1 +#define VF_REG_IN_RECV_CBACK 2 + static unsigned int ring_size __ro_after_init = 128; module_param(ring_size, uint, 0444); MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)"); @@ -2183,7 +2187,7 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb) } static int netvsc_vf_join(struct net_device *vf_netdev, - struct net_device *ndev) + struct net_device *ndev, int context) { struct net_device_context *ndev_ctx = netdev_priv(ndev); int ret; @@ -2205,8 +2209,11 @@ static int netvsc_vf_join(struct net_device *vf_netdev, ndev->name, ret); goto upper_link_failed; } - - schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); + /* If this registration is called from probe context vf_takeover + * is taken care of later in probe itself. + */ + if (context == VF_REG_IN_RECV_CBACK) + schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); call_netdevice_notifiers(NETDEV_JOIN, vf_netdev); @@ -2344,7 +2351,7 @@ static int netvsc_prepare_bonding(struct net_device *vf_netdev) return NOTIFY_DONE; } -static int netvsc_register_vf(struct net_device *vf_netdev) +static int netvsc_register_vf(struct net_device *vf_netdev, int context) { struct net_device_context *net_device_ctx; struct netvsc_device *netvsc_dev; @@ -2384,7 +2391,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev) netdev_info(ndev, "VF registering: %s\n", vf_netdev->name); - if (netvsc_vf_join(vf_netdev, ndev) != 0) + if (netvsc_vf_join(vf_netdev, ndev, context) != 0) return NOTIFY_DONE; dev_hold(vf_netdev); @@ -2485,7 +2492,7 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev) static int netvsc_probe(struct hv_device *dev, const struct hv_vmbus_device_id *dev_id) { - struct net_device *net = NULL; + struct net_device *net = NULL, *vf_netdev; struct net_device_context *net_device_ctx; struct netvsc_device_info *device_info = NULL; struct netvsc_device *nvdev; @@ -2597,6 +2604,34 @@ static int netvsc_probe(struct hv_device *dev, } list_add(&net_device_ctx->list, &netvsc_dev_list); + + /* When the hv_netvsc driver is removed and readded, the + * NET_DEVICE_REGISTER for the vf device is replayed before probe + * is complete. This is because register_netdevice_notifier() gets + * registered before vmbus_driver_register() so that callback func + * is set before probe and we don't miss events like NETDEV_POST_INIT + * So, in this section we try to register each matching + * vf device that is present as a netdevice, knowing that it's register + * call is not processed in the netvsc_netdev_notifier(as probing is + * progress and get_netvsc_byslot fails). + */ + for_each_netdev(dev_net(net), vf_netdev) { + if (vf_netdev->netdev_ops == &device_ops) + continue; + + if (vf_netdev->type != ARPHRD_ETHER) + continue; + + if (is_vlan_dev(vf_netdev)) + continue; + + if (netif_is_bond_master(vf_netdev)) + continue; + + netvsc_prepare_bonding(vf_netdev); + netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE); + __netvsc_vf_setup(net, vf_netdev); + } rtnl_unlock(); netvsc_devinfo_put(device_info); @@ -2773,7 +2808,7 @@ static int netvsc_netdev_event(struct notifier_block *this, case NETDEV_POST_INIT: return netvsc_prepare_bonding(event_dev); case NETDEV_REGISTER: - return netvsc_register_vf(event_dev); + return netvsc_register_vf(event_dev, VF_REG_IN_RECV_CBACK); case NETDEV_UNREGISTER: return netvsc_unregister_vf(event_dev); case NETDEV_UP: -- 2.34.1

1 year, 4 months

5
12
0 0

[PATCH v2 4/7] tracefs: dentry lookup crapectomy

by Steven Rostedt

From: Linus Torvalds <torvalds(a)linux-foundation.org> The dentry lookup for eventfs files was very broken, and had lots of signs of the old situation where the filesystem names were all created statically in the dentry tree, rather than being looked up dynamically based on the eventfs data structures. You could see it in the naming - how it claimed to "create" dentries rather than just look up the dentries that were given it. You could see it in various nonsensical and very incorrect operations, like using "simple_lookup()" on the dentries that were passed in, which only results in those dentries becoming negative dentries. Which meant that any other lookup would possibly return ENOENT if it saw that negative dentry before the data was then later filled in. You could see it in the immense amount of nonsensical code that didn't actually just do lookups. Link: https://lore.kernel.org/linux-trace-kernel/202401291043.e62e89dc-oliver.san… Cc: stable(a)vger.kernel.org Fixes: c1504e510238 ("eventfs: Implement eventfs dir creation functions") Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- Changes since v1: https://lore.kernel.org/linux-trace-kernel/20240130190355.11486-3-torvalds@… - Fixed the lookup case of not found dentry, to return an error. This was added in a later patch when it should have been in this one. - Removed the calls to eventfs_{start,end,failed}_creating() fs/tracefs/event_inode.c | 285 ++++++++------------------------------- fs/tracefs/inode.c | 69 ---------- fs/tracefs/internal.h | 3 - 3 files changed, 58 insertions(+), 299 deletions(-) diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index e9819d719d2a..4878f4d578be 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -230,7 +230,6 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) { struct eventfs_inode *ei; - mutex_lock(&eventfs_mutex); do { // The parent is stable because we do not do renames dentry = dentry->d_parent; @@ -247,7 +246,6 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) } // Walk upwards until you find the events inode } while (!ei->is_events); - mutex_unlock(&eventfs_mutex); update_top_events_attr(ei, dentry->d_sb); @@ -280,11 +278,10 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode, } /** - * create_file - create a file in the tracefs filesystem - * @name: the name of the file to create. + * lookup_file - look up a file in the tracefs filesystem + * @dentry: the dentry to look up * @mode: the permission that the file should have. * @attr: saved attributes changed by user - * @parent: parent dentry for this file. * @data: something that the caller will want to get to later on. * @fop: struct file_operations that should be used for this file. * @@ -292,13 +289,13 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode, * directory. The inode.i_private pointer will point to @data in the open() * call. */ -static struct dentry *create_file(const char *name, umode_t mode, +static struct dentry *lookup_file(struct dentry *dentry, + umode_t mode, struct eventfs_attr *attr, - struct dentry *parent, void *data, + void *data, const struct file_operations *fop) { struct tracefs_inode *ti; - struct dentry *dentry; struct inode *inode; if (!(mode & S_IFMT)) @@ -307,15 +304,9 @@ static struct dentry *create_file(const char *name, umode_t mode, if (WARN_ON_ONCE(!S_ISREG(mode))) return NULL; - WARN_ON_ONCE(!parent); - dentry = eventfs_start_creating(name, parent); - - if (IS_ERR(dentry)) - return dentry; - inode = tracefs_get_inode(dentry->d_sb); if (unlikely(!inode)) - return eventfs_failed_creating(dentry); + return ERR_PTR(-ENOMEM); /* If the user updated the directory's attributes, use them */ update_inode_attr(dentry, inode, attr, mode); @@ -329,32 +320,29 @@ static struct dentry *create_file(const char *name, umode_t mode, ti = get_tracefs(inode); ti->flags |= TRACEFS_EVENT_INODE; - d_instantiate(dentry, inode); + + d_add(dentry, inode); fsnotify_create(dentry->d_parent->d_inode, dentry); - return eventfs_end_creating(dentry); + return dentry; }; /** - * create_dir - create a dir in the tracefs filesystem + * lookup_dir_entry - look up a dir in the tracefs filesystem + * @dentry: the directory to look up * @ei: the eventfs_inode that represents the directory to create - * @parent: parent dentry for this file. * - * This function will create a dentry for a directory represented by + * This function will look up a dentry for a directory represented by * a eventfs_inode. */ -static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent) +static struct dentry *lookup_dir_entry(struct dentry *dentry, + struct eventfs_inode *pei, struct eventfs_inode *ei) { struct tracefs_inode *ti; - struct dentry *dentry; struct inode *inode; - dentry = eventfs_start_creating(ei->name, parent); - if (IS_ERR(dentry)) - return dentry; - inode = tracefs_get_inode(dentry->d_sb); if (unlikely(!inode)) - return eventfs_failed_creating(dentry); + return ERR_PTR(-ENOMEM); /* If the user updated the directory's attributes, use them */ update_inode_attr(dentry, inode, &ei->attr, @@ -371,11 +359,14 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent /* Only directories have ti->private set to an ei, not files */ ti->private = ei; + dentry->d_fsdata = ei; + ei->dentry = dentry; // Remove me! + inc_nlink(inode); - d_instantiate(dentry, inode); + d_add(dentry, inode); inc_nlink(dentry->d_parent->d_inode); fsnotify_mkdir(dentry->d_parent->d_inode, dentry); - return eventfs_end_creating(dentry); + return dentry; } static void free_ei(struct eventfs_inode *ei) @@ -425,7 +416,7 @@ void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry) } /** - * create_file_dentry - create a dentry for a file of an eventfs_inode + * lookup_file_dentry - create a dentry for a file of an eventfs_inode * @ei: the eventfs_inode that the file will be created under * @idx: the index into the d_children[] of the @ei * @parent: The parent dentry of the created file. @@ -438,157 +429,21 @@ void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry) * address located at @e_dentry. */ static struct dentry * -create_file_dentry(struct eventfs_inode *ei, int idx, - struct dentry *parent, const char *name, umode_t mode, void *data, +lookup_file_dentry(struct dentry *dentry, + struct eventfs_inode *ei, int idx, + umode_t mode, void *data, const struct file_operations *fops) { struct eventfs_attr *attr = NULL; struct dentry **e_dentry = &ei->d_children[idx]; - struct dentry *dentry; - - WARN_ON_ONCE(!inode_is_locked(parent->d_inode)); - mutex_lock(&eventfs_mutex); - if (ei->is_freed) { - mutex_unlock(&eventfs_mutex); - return NULL; - } - /* If the e_dentry already has a dentry, use it */ - if (*e_dentry) { - dget(*e_dentry); - mutex_unlock(&eventfs_mutex); - return *e_dentry; - } - - /* ei->entry_attrs are protected by SRCU */ if (ei->entry_attrs) attr = &ei->entry_attrs[idx]; - mutex_unlock(&eventfs_mutex); - - dentry = create_file(name, mode, attr, parent, data, fops); - - mutex_lock(&eventfs_mutex); - - if (IS_ERR_OR_NULL(dentry)) { - /* - * When the mutex was released, something else could have - * created the dentry for this e_dentry. In which case - * use that one. - * - * If ei->is_freed is set, the e_dentry is currently on its - * way to being freed, don't return it. If e_dentry is NULL - * it means it was already freed. - */ - if (ei->is_freed) { - dentry = NULL; - } else { - dentry = *e_dentry; - dget(dentry); - } - mutex_unlock(&eventfs_mutex); - return dentry; - } - - if (!*e_dentry && !ei->is_freed) { - *e_dentry = dentry; - dentry->d_fsdata = ei; - } else { - /* - * Should never happen unless we get here due to being freed. - * Otherwise it means two dentries exist with the same name. - */ - WARN_ON_ONCE(!ei->is_freed); - dentry = NULL; - } - mutex_unlock(&eventfs_mutex); - - return dentry; -} - -/** - * eventfs_post_create_dir - post create dir routine - * @ei: eventfs_inode of recently created dir - * - * Map the meta-data of files within an eventfs dir to their parent dentry - */ -static void eventfs_post_create_dir(struct eventfs_inode *ei) -{ - struct eventfs_inode *ei_child; - - lockdep_assert_held(&eventfs_mutex); - - /* srcu lock already held */ - /* fill parent-child relation */ - list_for_each_entry_srcu(ei_child, &ei->children, list, - srcu_read_lock_held(&eventfs_srcu)) { - ei_child->d_parent = ei->dentry; - } -} - -/** - * create_dir_dentry - Create a directory dentry for the eventfs_inode - * @pei: The eventfs_inode parent of ei. - * @ei: The eventfs_inode to create the directory for - * @parent: The dentry of the parent of this directory - * - * This creates and attaches a directory dentry to the eventfs_inode @ei. - */ -static struct dentry * -create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei, - struct dentry *parent) -{ - struct dentry *dentry = NULL; - - WARN_ON_ONCE(!inode_is_locked(parent->d_inode)); - - mutex_lock(&eventfs_mutex); - if (pei->is_freed || ei->is_freed) { - mutex_unlock(&eventfs_mutex); - return NULL; - } - if (ei->dentry) { - /* If the eventfs_inode already has a dentry, use it */ - dentry = ei->dentry; - dget(dentry); - mutex_unlock(&eventfs_mutex); - return dentry; - } - mutex_unlock(&eventfs_mutex); + dentry->d_fsdata = ei; // NOTE: ei of _parent_ + lookup_file(dentry, mode, attr, data, fops); - dentry = create_dir(ei, parent); - - mutex_lock(&eventfs_mutex); - - if (IS_ERR_OR_NULL(dentry) && !ei->is_freed) { - /* - * When the mutex was released, something else could have - * created the dentry for this e_dentry. In which case - * use that one. - * - * If ei->is_freed is set, the e_dentry is currently on its - * way to being freed. - */ - dentry = ei->dentry; - if (dentry) - dget(dentry); - mutex_unlock(&eventfs_mutex); - return dentry; - } - - if (!ei->dentry && !ei->is_freed) { - ei->dentry = dentry; - eventfs_post_create_dir(ei); - dentry->d_fsdata = ei; - } else { - /* - * Should never happen unless we get here due to being freed. - * Otherwise it means two dentries exist with the same name. - */ - WARN_ON_ONCE(!ei->is_freed); - dentry = NULL; - } - mutex_unlock(&eventfs_mutex); + *e_dentry = dentry; // Remove me return dentry; } @@ -607,79 +462,55 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { - const struct file_operations *fops; - const struct eventfs_entry *entry; struct eventfs_inode *ei_child; struct tracefs_inode *ti; struct eventfs_inode *ei; - struct dentry *ei_dentry = NULL; - struct dentry *ret = NULL; - struct dentry *d; const char *name = dentry->d_name.name; - umode_t mode; - void *data; - int idx; - int i; - int r; + struct dentry *result = NULL; ti = get_tracefs(dir); if (!(ti->flags & TRACEFS_EVENT_INODE)) - return NULL; - - /* Grab srcu to prevent the ei from going away */ - idx = srcu_read_lock(&eventfs_srcu); + return ERR_PTR(-EIO); - /* - * Grab the eventfs_mutex to consistent value from ti->private. - * This s - */ mutex_lock(&eventfs_mutex); - ei = READ_ONCE(ti->private); - if (ei && !ei->is_freed) - ei_dentry = READ_ONCE(ei->dentry); - mutex_unlock(&eventfs_mutex); - - if (!ei || !ei_dentry) - goto out; - data = ei->data; + ei = ti->private; + if (!ei || ei->is_freed) + goto enoent; - list_for_each_entry_srcu(ei_child, &ei->children, list, - srcu_read_lock_held(&eventfs_srcu)) { + list_for_each_entry(ei_child, &ei->children, list) { if (strcmp(ei_child->name, name) != 0) continue; - ret = simple_lookup(dir, dentry, flags); - if (IS_ERR(ret)) - goto out; - d = create_dir_dentry(ei, ei_child, ei_dentry); - dput(d); + if (ei_child->is_freed) + goto enoent; + lookup_dir_entry(dentry, ei, ei_child); goto out; } - for (i = 0; i < ei->nr_entries; i++) { - entry = &ei->entries[i]; - if (strcmp(name, entry->name) == 0) { - void *cdata = data; - mutex_lock(&eventfs_mutex); - /* If ei->is_freed, then the event itself may be too */ - if (!ei->is_freed) - r = entry->callback(name, &mode, &cdata, &fops); - else - r = -1; - mutex_unlock(&eventfs_mutex); - if (r <= 0) - continue; - ret = simple_lookup(dir, dentry, flags); - if (IS_ERR(ret)) - goto out; - d = create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops); - dput(d); - break; - } + for (int i = 0; i < ei->nr_entries; i++) { + void *data; + umode_t mode; + const struct file_operations *fops; + const struct eventfs_entry *entry = &ei->entries[i]; + + if (strcmp(name, entry->name) != 0) + continue; + + data = ei->data; + if (entry->callback(name, &mode, &data, &fops) <= 0) + goto enoent; + + lookup_file_dentry(dentry, ei, i, mode, data, fops); + goto out; } + + enoent: + /* Don't cache negative lookups, just return an error */ + result = ERR_PTR(-ENOENT); + out: - srcu_read_unlock(&eventfs_srcu, idx); - return ret; + mutex_unlock(&eventfs_mutex); + return result; } /* diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 888e42087847..5c84460feeeb 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -495,75 +495,6 @@ struct dentry *tracefs_end_creating(struct dentry *dentry) return dentry; } -/** - * eventfs_start_creating - start the process of creating a dentry - * @name: Name of the file created for the dentry - * @parent: The parent dentry where this dentry will be created - * - * This is a simple helper function for the dynamically created eventfs - * files. When the directory of the eventfs files are accessed, their - * dentries are created on the fly. This function is used to start that - * process. - */ -struct dentry *eventfs_start_creating(const char *name, struct dentry *parent) -{ - struct dentry *dentry; - int error; - - /* Must always have a parent. */ - if (WARN_ON_ONCE(!parent)) - return ERR_PTR(-EINVAL); - - error = simple_pin_fs(&trace_fs_type, &tracefs_mount, - &tracefs_mount_count); - if (error) - return ERR_PTR(error); - - if (unlikely(IS_DEADDIR(parent->d_inode))) - dentry = ERR_PTR(-ENOENT); - else - dentry = lookup_one_len(name, parent, strlen(name)); - - if (!IS_ERR(dentry) && dentry->d_inode) { - dput(dentry); - dentry = ERR_PTR(-EEXIST); - } - - if (IS_ERR(dentry)) - simple_release_fs(&tracefs_mount, &tracefs_mount_count); - - return dentry; -} - -/** - * eventfs_failed_creating - clean up a failed eventfs dentry creation - * @dentry: The dentry to clean up - * - * If after calling eventfs_start_creating(), a failure is detected, the - * resources created by eventfs_start_creating() needs to be cleaned up. In - * that case, this function should be called to perform that clean up. - */ -struct dentry *eventfs_failed_creating(struct dentry *dentry) -{ - dput(dentry); - simple_release_fs(&tracefs_mount, &tracefs_mount_count); - return NULL; -} - -/** - * eventfs_end_creating - Finish the process of creating a eventfs dentry - * @dentry: The dentry that has successfully been created. - * - * This function is currently just a place holder to match - * eventfs_start_creating(). In case any synchronization needs to be added, - * this function will be used to implement that without having to modify - * the callers of eventfs_start_creating(). - */ -struct dentry *eventfs_end_creating(struct dentry *dentry) -{ - return dentry; -} - /* Find the inode that this will use for default */ static struct inode *instance_inode(struct dentry *parent, struct inode *inode) { diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index 7d84349ade87..09037e2c173d 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -80,9 +80,6 @@ struct dentry *tracefs_start_creating(const char *name, struct dentry *parent); struct dentry *tracefs_end_creating(struct dentry *dentry); struct dentry *tracefs_failed_creating(struct dentry *dentry); struct inode *tracefs_get_inode(struct super_block *sb); -struct dentry *eventfs_start_creating(const char *name, struct dentry *parent); -struct dentry *eventfs_failed_creating(struct dentry *dentry); -struct dentry *eventfs_end_creating(struct dentry *dentry); void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry); #endif /* _TRACEFS_INTERNAL_H */ -- 2.43.0

1 year, 4 months

2
5
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror January 2024