From: Lorenzo Bianconi lorenzo@kernel.org

[ Upstream commit 481fc927c8289919cc0be58666fcd1b7da187a0c ]

Introduce rcu section in mt7921_mcu_tx_rate_report before dereferencing wcid pointer otherwise loockdep will report the following issue:

[ 115.245740] ============================= [ 115.245754] WARNING: suspicious RCU usage [ 115.245771] 5.10.20 #0 Not tainted [ 115.245784] ----------------------------- [ 115.245816] other info that might help us debug this: [ 115.245830] rcu_scheduler_active = 2, debug_locks = 1 [ 115.245845] 3 locks held by kworker/u4:1/20: [ 115.245858] #0: ffffff80065ab138 ((wq_completion)phy0){+.+.}-{0:0}, at: process_one_work+0x1f8/0x6b8 [ 115.245948] #1: ffffffc01198bdd8 ((work_completion)(&(&dev->mphy.mac_work)->work)){+.+.}-{0:0}, at: process_one_8 [ 115.246027] #2: ffffff8006543ce8 (&dev->mutex#2){+.+.}-{3:3}, at: mt7921_mac_work+0x60/0x2b0 [mt7921e] [ 115.246125] [ 115.246125] stack backtrace: [ 115.246142] CPU: 1 PID: 20 Comm: kworker/u4:1 Not tainted 5.10.20 #0 [ 115.246152] Hardware name: MediaTek MT7622 RFB1 board (DT) [ 115.246168] Workqueue: phy0 mt7921_mac_work [mt7921e] [ 115.246188] Call trace: [ 115.246201] dump_backtrace+0x0/0x1a8 [ 115.246213] show_stack+0x14/0x30 [ 115.246228] dump_stack+0xec/0x134 [ 115.246240] lockdep_rcu_suspicious+0xcc/0xdc [ 115.246255] mt7921_get_wtbl_info+0x2a4/0x310 [mt7921e] [ 115.246269] mt7921_mac_work+0x284/0x2b0 [mt7921e] [ 115.246281] process_one_work+0x2a0/0x6b8 [ 115.246293] worker_thread+0x40/0x440 [ 115.246305] kthread+0x144/0x148 [ 115.246317] ret_from_fork+0x10/0x18

Fixes: 1c099ab44727c ("mt76: mt7921: add MCU support") Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org Signed-off-by: Felix Fietkau nbd@nbd.name Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/mediatek/mt76/mt7921/mcu.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c index 62afbad77596..9a140e4734b5 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c @@ -404,9 +404,12 @@ mt7921_mcu_tx_rate_report(struct mt7921_dev *dev, struct sk_buff *skb,

if (wlan_idx >= MT76_N_WCIDS) return; + + rcu_read_lock(); + wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]); if (!wcid) - return; + goto out;

msta = container_of(wcid, struct mt7921_sta, wcid); stats = &msta->stats; @@ -414,6 +417,8 @@ mt7921_mcu_tx_rate_report(struct mt7921_dev *dev, struct sk_buff *skb, /* current rate */ mt7921_mcu_tx_rate_parse(mphy, &peer, &rate, curr); stats->tx_rate = rate; +out: + rcu_read_unlock(); }

static void

From: Lorenzo Bianconi lorenzo@kernel.org

[ Upstream commit 509559c35bcd23d5a046624b225cb3e99a9f1481 ]

Similar to usb device, re-initialize mt76x0e device after resume in order to fix mt7630e hang during suspend/resume

Reported-by: Luca Trombin luca.trombin@gmail.com Fixes: c2a4d9fbabfb9 ("mt76x0: inital split between pci and usb") Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org Signed-off-by: Kalle Valo kvalo@codeaurora.org Link: https://lore.kernel.org/r/4812f9611624b34053c1592fd9c175b67d4ffcb4.162040602... Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/wireless/mediatek/mt76/mt76x0/pci.c | 81 ++++++++++++++++++- 1 file changed, 77 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c index 02d0aa0b815e..d2489dc9dc13 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c @@ -87,7 +87,7 @@ static const struct ieee80211_ops mt76x0e_ops = { .reconfig_complete = mt76x02_reconfig_complete, };

-static int mt76x0e_register_device(struct mt76x02_dev *dev) +static int mt76x0e_init_hardware(struct mt76x02_dev *dev, bool resume) { int err;

@@ -100,9 +100,11 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev) if (err < 0) return err;

- err = mt76x02_dma_init(dev); - if (err < 0) - return err; + if (!resume) { + err = mt76x02_dma_init(dev); + if (err < 0) + return err; + }

err = mt76x0_init_hardware(dev); if (err < 0) @@ -123,6 +125,17 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev) mt76_clear(dev, 0x110, BIT(9)); mt76_set(dev, MT_MAX_LEN_CFG, BIT(13));

+ return 0; +} + +static int mt76x0e_register_device(struct mt76x02_dev *dev) +{ + int err; + + err = mt76x0e_init_hardware(dev, false); + if (err < 0) + return err; + err = mt76x0_register_device(dev); if (err < 0) return err; @@ -167,6 +180,8 @@ mt76x0e_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) return ret;

+ mt76_pci_disable_aspm(pdev); + mdev = mt76_alloc_device(&pdev->dev, sizeof(*dev), &mt76x0e_ops, &drv_ops); if (!mdev) @@ -220,6 +235,60 @@ mt76x0e_remove(struct pci_dev *pdev) mt76_free_device(mdev); }

+#ifdef CONFIG_PM +static int mt76x0e_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct mt76_dev *mdev = pci_get_drvdata(pdev); + struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76); + int i; + + mt76_worker_disable(&mdev->tx_worker); + for (i = 0; i < ARRAY_SIZE(mdev->phy.q_tx); i++) + mt76_queue_tx_cleanup(dev, mdev->phy.q_tx[i], true); + for (i = 0; i < ARRAY_SIZE(mdev->q_mcu); i++) + mt76_queue_tx_cleanup(dev, mdev->q_mcu[i], true); + napi_disable(&mdev->tx_napi); + + mt76_for_each_q_rx(mdev, i) + napi_disable(&mdev->napi[i]); + + mt76x02_dma_disable(dev); + mt76x02_mcu_cleanup(dev); + mt76x0_chip_onoff(dev, false, false); + + pci_enable_wake(pdev, pci_choose_state(pdev, state), true); + pci_save_state(pdev); + + return pci_set_power_state(pdev, pci_choose_state(pdev, state)); +} + +static int mt76x0e_resume(struct pci_dev *pdev) +{ + struct mt76_dev *mdev = pci_get_drvdata(pdev); + struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76); + int err, i; + + err = pci_set_power_state(pdev, PCI_D0); + if (err) + return err; + + pci_restore_state(pdev); + + mt76_worker_enable(&mdev->tx_worker); + + mt76_for_each_q_rx(mdev, i) { + mt76_queue_rx_reset(dev, i); + napi_enable(&mdev->napi[i]); + napi_schedule(&mdev->napi[i]); + } + + napi_enable(&mdev->tx_napi); + napi_schedule(&mdev->tx_napi); + + return mt76x0e_init_hardware(dev, true); +} +#endif /* CONFIG_PM */ + static const struct pci_device_id mt76x0e_device_table[] = { { PCI_DEVICE(0x14c3, 0x7610) }, { PCI_DEVICE(0x14c3, 0x7630) }, @@ -237,6 +306,10 @@ static struct pci_driver mt76x0e_driver = { .id_table = mt76x0e_device_table, .probe = mt76x0e_probe, .remove = mt76x0e_remove, +#ifdef CONFIG_PM + .suspend = mt76x0e_suspend, + .resume = mt76x0e_resume, +#endif /* CONFIG_PM */ };

module_pci_driver(mt76x0e_driver);

From: Grant Peltier grantpeltier93@gmail.com

[ Upstream commit 2a29db088c7ae7121801a0d7a60740ed2d18c4f3 ]

The initial version of the RAA228228 datasheet claimed that the device supported READ_TEMPERATURE_3 but not READ_TEMPERATURE_1. It has since been discovered that the datasheet was incorrect. The RAA228228 does support READ_TEMPERATURE_1 but does not support READ_TEMPERATURE_3.

Signed-off-by: Grant Peltier grantpeltier93@gmail.com Fixes: 51fb91ed5a6f ("hwmon: (pmbus/isl68137) remove READ_TEMPERATURE_1 telemetry for RAA228228") Link: https://lore.kernel.org/r/20210514211954.GA24646@raspberrypi Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/pmbus/isl68137.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/pmbus/isl68137.c b/drivers/hwmon/pmbus/isl68137.c index 2bee930d3900..789242ed72e5 100644 --- a/drivers/hwmon/pmbus/isl68137.c +++ b/drivers/hwmon/pmbus/isl68137.c @@ -244,8 +244,8 @@ static int isl68137_probe(struct i2c_client *client) info->read_word_data = raa_dmpvr2_read_word_data; break; case raa_dmpvr2_2rail_nontc: - info->func[0] &= ~PMBUS_HAVE_TEMP; - info->func[1] &= ~PMBUS_HAVE_TEMP; + info->func[0] &= ~PMBUS_HAVE_TEMP3; + info->func[1] &= ~PMBUS_HAVE_TEMP3; fallthrough; case raa_dmpvr2_2rail: info->pages = 2;

From: Changbin Du changbin.du@gmail.com

[ Upstream commit 668a84c1bfb2b3fd5a10847825a854d63fac7baa ]

setup_arch() would invoke efi_init()->efi_get_fdt_params(). If no valid fdt found then initial_boot_params will be null. So we should stop further fdt processing here. I encountered this issue on risc-v.

Signed-off-by: Changbin Du changbin.du@gmail.com Fixes: b91540d52a08b ("RISC-V: Add EFI runtime services") Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/firmware/efi/fdtparams.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/firmware/efi/fdtparams.c b/drivers/firmware/efi/fdtparams.c index bb042ab7c2be..e901f8564ca0 100644 --- a/drivers/firmware/efi/fdtparams.c +++ b/drivers/firmware/efi/fdtparams.c @@ -98,6 +98,9 @@ u64 __init efi_get_fdt_params(struct efi_memory_map_data *mm) BUILD_BUG_ON(ARRAY_SIZE(target) != ARRAY_SIZE(name)); BUILD_BUG_ON(ARRAY_SIZE(target) != ARRAY_SIZE(dt_params[0].params));

+ if (!fdt) + return 0; + for (i = 0; i < ARRAY_SIZE(dt_params); i++) { node = fdt_path_offset(fdt, dt_params[i].path); if (node < 0)

From: Dan Carpenter dan.carpenter@oracle.com

[ Upstream commit c4039b29fe9637e1135912813f830994af4c867f ]

If the buffer has slashes up to the end then this will read past the end of the array. I don't anticipate that this is an issue for many people in real life, but it's the right thing to do and it makes static checkers happy.

Fixes: 7a88a6227dc7 ("efi/libstub: Fix path separator regression") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/firmware/efi/libstub/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/libstub/file.c b/drivers/firmware/efi/libstub/file.c index 4e81c6077188..dd95f330fe6e 100644 --- a/drivers/firmware/efi/libstub/file.c +++ b/drivers/firmware/efi/libstub/file.c @@ -103,7 +103,7 @@ static int find_file_option(const efi_char16_t *cmdline, int cmdline_len, return 0;

/* Skip any leading slashes */ - while (cmdline[i] == L'/' || cmdline[i] == L'\') + while (i < cmdline_len && (cmdline[i] == L'/' || cmdline[i] == L'\')) i++;

while (--result_len > 0 && i < cmdline_len) {

From: Zhen Lei thunder.leizhen@huawei.com

[ Upstream commit d1ce2c79156d3baf0830990ab06d296477b93c26 ]

The error code returned from vfio_ext_cap_len() is stored in 'len', not in 'ret'.

Fixes: 89e1f7d4c66d ("vfio: Add PCI device driver") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Zhen Lei thunder.leizhen@huawei.com Reviewed-by: Max Gurtovoy mgurtovoy@nvidia.com Message-Id: 20210515020458.6771-1-thunder.leizhen@huawei.com Signed-off-by: Alex Williamson alex.williamson@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/vfio/pci/vfio_pci_config.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index a402adee8a21..47f21a6ca7fe 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -1581,7 +1581,7 @@ static int vfio_ecap_init(struct vfio_pci_device *vdev) if (len == 0xFF) { len = vfio_ext_cap_len(vdev, ecap, epos); if (len < 0) - return ret; + return len; } }

From: Wei Yongjun weiyongjun1@huawei.com

[ Upstream commit 752774ce7793a1f8baa55aae31f3b4caac49cbe4 ]

Fix to return a negative error code from the framebuffer_alloc() error handling case instead of 0, also release regions in some error handing cases.

Fixes: cacade1946a4 ("sample: vfio mdev display - guest driver") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Wei Yongjun weiyongjun1@huawei.com Message-Id: 20210520133641.1421378-1-weiyongjun1@huawei.com Signed-off-by: Alex Williamson alex.williamson@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- samples/vfio-mdev/mdpy-fb.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/samples/vfio-mdev/mdpy-fb.c b/samples/vfio-mdev/mdpy-fb.c index 21dbf63d6e41..9ec93d90e8a5 100644 --- a/samples/vfio-mdev/mdpy-fb.c +++ b/samples/vfio-mdev/mdpy-fb.c @@ -117,22 +117,27 @@ static int mdpy_fb_probe(struct pci_dev *pdev, if (format != DRM_FORMAT_XRGB8888) { pci_err(pdev, "format mismatch (0x%x != 0x%x)\n", format, DRM_FORMAT_XRGB8888); - return -EINVAL; + ret = -EINVAL; + goto err_release_regions; } if (width < 100 || width > 10000) { pci_err(pdev, "width (%d) out of range\n", width); - return -EINVAL; + ret = -EINVAL; + goto err_release_regions; } if (height < 100 || height > 10000) { pci_err(pdev, "height (%d) out of range\n", height); - return -EINVAL; + ret = -EINVAL; + goto err_release_regions; } pci_info(pdev, "mdpy found: %dx%d framebuffer\n", width, height);

info = framebuffer_alloc(sizeof(struct mdpy_fb_par), &pdev->dev); - if (!info) + if (!info) { + ret = -ENOMEM; goto err_release_regions; + } pci_set_drvdata(pdev, info); par = info->par;

From: Julian Anastasov ja@ssi.bg

[ Upstream commit 56e4ee82e850026d71223262c07df7d6af3bd872 ]

syzbot reported memory leak [1] when adding service with HASHED flag. We should ignore this flag both from sockopt and netlink provided data, otherwise the service is not hashed and not visible while releasing resources.

[1] BUG: memory leak unreferenced object 0xffff888115227800 (size 512): comm "syz-executor263", pid 8658, jiffies 4294951882 (age 12.560s) 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: [<ffffffff83977188>] kmalloc include/linux/slab.h:556 [inline] [<ffffffff83977188>] kzalloc include/linux/slab.h:686 [inline] [<ffffffff83977188>] ip_vs_add_service+0x598/0x7c0 net/netfilter/ipvs/ip_vs_ctl.c:1343 [<ffffffff8397d770>] do_ip_vs_set_ctl+0x810/0xa40 net/netfilter/ipvs/ip_vs_ctl.c:2570 [<ffffffff838449a8>] nf_setsockopt+0x68/0xa0 net/netfilter/nf_sockopt.c:101 [<ffffffff839ae4e9>] ip_setsockopt+0x259/0x1ff0 net/ipv4/ip_sockglue.c:1435 [<ffffffff839fa03c>] raw_setsockopt+0x18c/0x1b0 net/ipv4/raw.c:857 [<ffffffff83691f20>] __sys_setsockopt+0x1b0/0x360 net/socket.c:2117 [<ffffffff836920f2>] __do_sys_setsockopt net/socket.c:2128 [inline] [<ffffffff836920f2>] __se_sys_setsockopt net/socket.c:2125 [inline] [<ffffffff836920f2>] __x64_sys_setsockopt+0x22/0x30 net/socket.c:2125 [<ffffffff84350efa>] do_syscall_64+0x3a/0xb0 arch/x86/entry/common.c:47 [<ffffffff84400068>] entry_SYSCALL_64_after_hwframe+0x44/0xae

Reported-and-tested-by: syzbot+e562383183e4b1766930@syzkaller.appspotmail.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Julian Anastasov ja@ssi.bg Reviewed-by: Simon Horman horms@verge.net.au Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/ipvs/ip_vs_ctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index d45dbcba8b49..c25097092a06 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1367,7 +1367,7 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, ip_vs_addr_copy(svc->af, &svc->addr, &u->addr); svc->port = u->port; svc->fwmark = u->fwmark; - svc->flags = u->flags; + svc->flags = u->flags & ~IP_VS_SVC_F_HASHED; svc->timeout = u->timeout * HZ; svc->netmask = u->netmask; svc->ipvs = ipvs;

From: Zhen Lei thunder.leizhen@huawei.com

[ Upstream commit 3dd653c077efda8152f4dd395359617d577a54cd ]

Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function.

Fixes: 224ee88fe395 ("Input: add force feedback driver for PID devices") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Zhen Lei thunder.leizhen@huawei.com Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/usbhid/hid-pidff.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/hid/usbhid/hid-pidff.c b/drivers/hid/usbhid/hid-pidff.c index fddac7c72f64..07a9fe97d2e0 100644 --- a/drivers/hid/usbhid/hid-pidff.c +++ b/drivers/hid/usbhid/hid-pidff.c @@ -1292,6 +1292,7 @@ int hid_pidff_init(struct hid_device *hid)

if (pidff->pool[PID_DEVICE_MANAGED_POOL].value && pidff->pool[PID_DEVICE_MANAGED_POOL].value[0] == 0) { + error = -EPERM; hid_notice(hid, "device does not support device managed pool\n"); goto fail;

From: Arnd Bergmann arnd@arndb.de

[ Upstream commit dc5f9f55502e13ba05731d5046a14620aa2ff456 ]

clang doesn't like printing a 32-bit integer using %hX format string:

drivers/hid/i2c-hid/i2c-hid-core.c:994:18: error: format specifies type 'unsigned short' but the argument has type '__u32' (aka 'unsigned int') [-Werror,-Wformat] client->name, hid->vendor, hid->product); ^~~~~~~~~~~ drivers/hid/i2c-hid/i2c-hid-core.c:994:31: error: format specifies type 'unsigned short' but the argument has type '__u32' (aka 'unsigned int') [-Werror,-Wformat] client->name, hid->vendor, hid->product); ^~~~~~~~~~~~

Use an explicit cast to truncate it to the low 16 bits instead.

Fixes: 9ee3e06610fd ("HID: i2c-hid: override HID descriptors for certain devices") Signed-off-by: Arnd Bergmann arnd@arndb.de Reviewed-by: Nathan Chancellor nathan@kernel.org Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/i2c-hid/i2c-hid-core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 9993133989a5..f9d28ad17d9c 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -990,8 +990,8 @@ int i2c_hid_core_probe(struct i2c_client *client, struct i2chid_ops *ops, hid->vendor = le16_to_cpu(ihid->hdesc.wVendorID); hid->product = le16_to_cpu(ihid->hdesc.wProductID);

- snprintf(hid->name, sizeof(hid->name), "%s %04hX:%04hX", - client->name, hid->vendor, hid->product); + snprintf(hid->name, sizeof(hid->name), "%s %04X:%04X", + client->name, (u16)hid->vendor, (u16)hid->product); strlcpy(hid->phys, dev_name(&client->dev), sizeof(hid->phys));

ihid->quirks = i2c_hid_lookup_quirk(hid->vendor, hid->product);

From: Parav Pandit parav@nvidia.com

[ Upstream commit b28d8f0c25a9b0355116cace5f53ea52bd4020c8 ]

Physical port name, port number attributes do not belong to virtual port flavour. When VF or SF virtual ports are registered they incorrectly append "np0" string in the netdevice name of the VF/SF.

Before this fix, VF netdevice name were ens2f0np0v0, ens2f0np0v1 for VF 0 and 1 respectively.

After the fix, they are ens2f0v0, ens2f0v1.

With this fix, reading /sys/class/net/ens2f0v0/phys_port_name returns -EOPNOTSUPP.

Also devlink port show example for 2 VFs on one PF to ensure that any physical port attributes are not exposed.

$ devlink port show pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false pci/0000:06:00.3/196608: type eth netdev ens2f0v0 flavour virtual splittable false pci/0000:06:00.4/262144: type eth netdev ens2f0v1 flavour virtual splittable false

This change introduces a netdevice name change on systemd/udev version 245 and higher which honors phys_port_name sysfs file for generation of netdevice name.

This also aligns to phys_port_name usage which is limited to switchdev ports as described in [1].

[1] https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/tree/Doc...

Fixes: acf1ee44ca5d ("devlink: Introduce devlink port flavour virtual") Signed-off-by: Parav Pandit parav@nvidia.com Reviewed-by: Jiri Pirko jiri@nvidia.com Link: https://lore.kernel.org/r/20210526200027.14008-1-parav@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/devlink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/devlink.c b/net/core/devlink.c index 737b61c2976e..4c363fa7d4d1 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -705,7 +705,6 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, case DEVLINK_PORT_FLAVOUR_PHYSICAL: case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: - case DEVLINK_PORT_FLAVOUR_VIRTUAL: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER, attrs->phys.port_number)) return -EMSGSIZE; @@ -8629,7 +8628,6 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,

switch (attrs->flavour) { case DEVLINK_PORT_FLAVOUR_PHYSICAL: - case DEVLINK_PORT_FLAVOUR_VIRTUAL: if (!attrs->split) n = snprintf(name, len, "p%u", attrs->phys.port_number); else @@ -8670,6 +8668,8 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, attrs->pci_sf.sf); break; + case DEVLINK_PORT_FLAVOUR_VIRTUAL: + return -EOPNOTSUPP; }

if (n >= len)

From: Ariel Levkovich lariel@nvidia.com

[ Upstream commit fb91702b743dec78d6507c53a2dec8a8883f509d ]

Fix current behavior of skipping template allocation in case the ct action is in zone 0.

Skipping the allocation may cause the datapath ct code to ignore the entire ct action with all its attributes (commit, nat) in case the ct action in zone 0 was preceded by a ct clear action.

The ct clear action sets the ct_state to untracked and resets the skb->_nfct pointer. Under these conditions and without an allocated ct template, the skb->_nfct pointer will remain NULL which will cause the tc ct action handler to exit without handling commit and nat actions, if such exist.

For example, the following rule in OVS dp: recirc_id(0x2),ct_state(+new-est-rel-rpl+trk),ct_label(0/0x1), \ in_port(eth0),actions:ct_clear,ct(commit,nat(src=10.11.0.12)), \ recirc(0x37a)

Will result in act_ct skipping the commit and nat actions in zone 0.

The change removes the skipping of template allocation for zone 0 and treats it the same as any other zone.

Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct") Signed-off-by: Ariel Levkovich lariel@nvidia.com Acked-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Link: https://lore.kernel.org/r/20210526170110.54864-1-lariel@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/act_ct.c | 3 --- 1 file changed, 3 deletions(-)

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 371fd64638d2..ba7f57cb41c3 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1205,9 +1205,6 @@ static int tcf_ct_fill_params(struct net *net, sizeof(p->zone)); }

- if (p->zone == NF_CT_DEFAULT_ZONE_ID) - return 0; - nf_ct_zone_init(&zone, p->zone, NF_CT_DEFAULT_ZONE_DIR, 0); tmpl = nf_ct_tmpl_alloc(net, &zone, GFP_KERNEL); if (!tmpl) {

From: Paolo Abeni pabeni@redhat.com

[ Upstream commit 06f9a435b3aa12f4de6da91f11fdce8ce7b46205 ]

In subflow_syn_recv_sock() we currently skip options parsing for OoO packet, given that such packets may not carry the relevant MPC option.

If the peer generates an MPC+data TSO packet and some of the early segments are lost or get reorder, we server will ignore the peer key, causing transient, unexpected fallback to TCP.

The solution is always parsing the incoming MPTCP options, and do the fallback only for in-order packets. This actually cleans the existing code a bit.

Fixes: d22f4988ffec ("mptcp: process MP_CAPABLE data option") Reported-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/mptcp/subflow.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 1936db3574d2..8878317b4386 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -608,21 +608,20 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,

/* if the sk is MP_CAPABLE, we try to fetch the client key */ if (subflow_req->mp_capable) { - if (TCP_SKB_CB(skb)->seq != subflow_req->ssn_offset + 1) { - /* here we can receive and accept an in-window, - * out-of-order pkt, which will not carry the MP_CAPABLE - * opt even on mptcp enabled paths - */ - goto create_msk; - } - + /* we can receive and accept an in-window, out-of-order pkt, + * which may not carry the MP_CAPABLE opt even on mptcp enabled + * paths: always try to extract the peer key, and fallback + * for packets missing it. + * Even OoO DSS packets coming legitly after dropped or + * reordered MPC will cause fallback, but we don't have other + * options. + */ mptcp_get_options(skb, &mp_opt); if (!mp_opt.mp_capable) { fallback = true; goto create_child; }

-create_msk: new_msk = mptcp_sk_clone(listener->conn, &mp_opt, req); if (!new_msk) fallback = true;

From: Sagi Grimberg sagi@grimberg.me

[ Upstream commit 12b2aaadb6d5ef77434e8db21f469f46fe2d392e ]

We have only 2 inline sg entries and we allow 4 sg entries for the send wr sge. Larger sgls entries will be chained. However when we build in-capsule send wr sge, we iterate without taking into account that the sgl may be chained and still fit in-capsule (which can happen if the sgl is bigger than 2, but lower-equal to 4).

Fix in-capsule data mapping to correctly iterate chained sgls.

Fixes: 38e1800275d3 ("nvme-rdma: Avoid preallocating big SGL for data") Reported-by: Walker, Benjamin benjamin.walker@intel.com Signed-off-by: Sagi Grimberg sagi@grimberg.me Reviewed-by: Max Gurtovoy mgurtovoy@nvidia.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/rdma.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index be905d4fdb47..ce8b3ce7582b 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1319,16 +1319,17 @@ static int nvme_rdma_map_sg_inline(struct nvme_rdma_queue *queue, int count) { struct nvme_sgl_desc *sg = &c->common.dptr.sgl; - struct scatterlist *sgl = req->data_sgl.sg_table.sgl; struct ib_sge *sge = &req->sge[1]; + struct scatterlist *sgl; u32 len = 0; int i;

- for (i = 0; i < count; i++, sgl++, sge++) { + for_each_sg(req->data_sgl.sg_table.sgl, sgl, count, i) { sge->addr = sg_dma_address(sgl); sge->length = sg_dma_len(sgl); sge->lkey = queue->device->pd->local_dma_lkey; len += sge->length; + sge++; }

sg->addr = cpu_to_le64(queue->ctrl->ctrl.icdoff);

From: Li Huafei lihuafei1@huawei.com

[ Upstream commit 3cb17cce1e76ccc5499915a4d7e095a1ad6bf7ff ]

If we just check whether the variable can be converted, 'tvar' should be a null pointer. However, the null pointer check is missing in the 'Constant value' execution path.

The following cases can trigger this problem:

$ cat test.c #include <stdio.h>

void main(void) { int a; const int b = 1;

asm volatile("mov %1, %0" : "=r"(a): "i"(b)); printf("a: %d\n", a); }

$ gcc test.c -o test -O -g $ sudo ./perf probe -x ./test -L "main" <main@/home/lhf/test.c:0> 0 void main(void) { 2 int a; const int b = 1;

asm volatile("mov %1, %0" : "=r"(a): "i"(b)); 6 printf("a: %d\n", a); }

$ sudo ./perf probe -x ./test -V "main:6" Segmentation fault

The check on 'tvar' is added. If 'tavr' is a null pointer, we return 0 to indicate that the variable can be converted. Now, we can successfully show the variables that can be accessed.

$ sudo ./perf probe -x ./test -V "main:6" Available variables at main:6 @<main+13> char* __fmt int a int b

However, the variable 'b' cannot be tracked.

$ sudo ./perf probe -x ./test -D "main:6 b" Failed to find the location of the 'b' variable at this address. Perhaps it has been optimized out. Use -V with the --range option to show 'b' location range. Error: Failed to add events.

This is because __die_find_variable_cb() did not successfully match variable 'b', which has the DW_AT_const_value attribute instead of DW_AT_location. We added support for DW_AT_const_value in __die_find_variable_cb(). With this modification, we can successfully track the variable 'b'.

$ sudo ./perf probe -x ./test -D "main:6 b" p:probe_test/main_L6 /home/lhf/test:0x1156 b=\1:s32

Fixes: 66f69b219716 ("perf probe: Support DW_AT_const_value constant value") Signed-off-by: Li Huafei lihuafei1@huawei.com Tested-by: Arnaldo Carvalho de Melo acme@redhat.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Frank Ch. Eigler fche@redhat.com Cc: Jianlin Lv jianlin.lv@arm.com Cc: Jiri Olsa jolsa@redhat.com Cc: Mark Rutland mark.rutland@arm.com Cc: Masami Hiramatsu mhiramat@kernel.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Srikar Dronamraju srikar@linux.vnet.ibm.com Cc: Yang Jihong yangjihong1@huawei.com Cc: Zhang Jinhao zhangjinhao2@huawei.com http://lore.kernel.org/lkml/20210601092750.169601-1-lihuafei1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/dwarf-aux.c | 8 ++++++-- tools/perf/util/probe-finder.c | 3 +++ 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 7b2d471a6419..4343356f3cf9 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -975,9 +975,13 @@ static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data) if ((tag == DW_TAG_formal_parameter || tag == DW_TAG_variable) && die_compare_name(die_mem, fvp->name) && - /* Does the DIE have location information or external instance? */ + /* + * Does the DIE have location information or const value + * or external instance? + */ (dwarf_attr(die_mem, DW_AT_external, &attr) || - dwarf_attr(die_mem, DW_AT_location, &attr))) + dwarf_attr(die_mem, DW_AT_location, &attr) || + dwarf_attr(die_mem, DW_AT_const_value, &attr))) return DIE_FIND_CB_END; if (dwarf_haspc(die_mem, fvp->addr)) return DIE_FIND_CB_CONTINUE; diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 1b118c9c86a6..bba61b95a37a 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -190,6 +190,9 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr, immediate_value_is_supported()) { Dwarf_Sword snum;

+ if (!tvar) + return 0; + dwarf_formsdata(&attr, &snum); ret = asprintf(&tvar->value, "\%ld", (long)snum);

From: Alexander Aring aahringo@redhat.com

[ Upstream commit dd9082f4a9f94280fbbece641bf8fc0a25f71f7a ]

This patch fixes the in-kernel mark setting by doing an additional sk_dst_reset() which was introduced by commit 50254256f382 ("sock: Reset dst when changing sk_mark via setsockopt"). The code is now shared to avoid any further suprises when changing the socket mark value.

Fixes: 84d1c617402e ("net: sock: add sock_set_mark") Reported-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Signed-off-by: Alexander Aring aahringo@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/sock.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c index 9c7b143e7a96..a266760cd65e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -815,10 +815,18 @@ void sock_set_rcvbuf(struct sock *sk, int val) } EXPORT_SYMBOL(sock_set_rcvbuf);

+static void __sock_set_mark(struct sock *sk, u32 val) +{ + if (val != sk->sk_mark) { + sk->sk_mark = val; + sk_dst_reset(sk); + } +} + void sock_set_mark(struct sock *sk, u32 val) { lock_sock(sk); - sk->sk_mark = val; + __sock_set_mark(sk, val); release_sock(sk); } EXPORT_SYMBOL(sock_set_mark); @@ -1126,10 +1134,10 @@ set_sndbuf: case SO_MARK: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; - } else if (val != sk->sk_mark) { - sk->sk_mark = val; - sk_dst_reset(sk); + break; } + + __sock_set_mark(sk, val); break;

case SO_RXQ_OVFL:

From: Maxim Mikityanskiy maximmi@nvidia.com

[ Upstream commit c55dcdd435aa6c6ad6ccac0a4c636d010ee367a4 ]

When a netdev with active TLS offload goes down, tls_device_down is called to stop the offload and tear down the TLS context. However, the socket stays alive, and it still points to the TLS context, which is now deallocated. If a netdev goes up, while the connection is still active, and the data flow resumes after a number of TCP retransmissions, it will lead to a use-after-free of the TLS context.

This commit addresses this bug by keeping the context alive until its normal destruction, and implements the necessary fallbacks, so that the connection can resume in software (non-offloaded) kTLS mode.

On the TX side tls_sw_fallback is used to encrypt all packets. The RX side already has all the necessary fallbacks, because receiving non-decrypted packets is supported. The thing needed on the RX side is to block resync requests, which are normally produced after receiving non-decrypted packets.

The necessary synchronization is implemented for a graceful teardown: first the fallbacks are deployed, then the driver resources are released (it used to be possible to have a tls_dev_resync after tls_dev_del).

A new flag called TLS_RX_DEV_DEGRADED is added to indicate the fallback mode. It's used to skip the RX resync logic completely, as it becomes useless, and some objects may be released (for example, resync_async, which is allocated and freed by the driver).

Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure") Signed-off-by: Maxim Mikityanskiy maximmi@nvidia.com Reviewed-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/tls.h | 9 ++++++ net/tls/tls_device.c | 52 +++++++++++++++++++++++++++++++---- net/tls/tls_device_fallback.c | 7 +++++ net/tls/tls_main.c | 1 + 4 files changed, 64 insertions(+), 5 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h index 6531ace2a68b..8341a8d1e807 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -193,6 +193,11 @@ struct tls_offload_context_tx { (sizeof(struct tls_offload_context_tx) + TLS_DRIVER_STATE_SIZE_TX)

enum tls_context_flags { + /* tls_device_down was called after the netdev went down, device state + * was released, and kTLS works in software, even though rx_conf is + * still TLS_HW (needed for transition). + */ + TLS_RX_DEV_DEGRADED = 0, /* Unlike RX where resync is driven entirely by the core in TX only * the driver knows when things went out of sync, so we need the flag * to be atomic. @@ -265,6 +270,7 @@ struct tls_context {

/* cache cold stuff */ struct proto *sk_proto; + struct sock *sk;

void (*sk_destruct)(struct sock *sk);

@@ -447,6 +453,9 @@ static inline u16 tls_user_config(struct tls_context *ctx, bool tx) struct sk_buff * tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, struct sk_buff *skb); +struct sk_buff * +tls_validate_xmit_skb_sw(struct sock *sk, struct net_device *dev, + struct sk_buff *skb);

static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) { diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 2602d61a8d28..9b1ea17f3b1d 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -50,6 +50,7 @@ static void tls_device_gc_task(struct work_struct *work); static DECLARE_WORK(tls_device_gc_work, tls_device_gc_task); static LIST_HEAD(tls_device_gc_list); static LIST_HEAD(tls_device_list); +static LIST_HEAD(tls_device_down_list); static DEFINE_SPINLOCK(tls_device_lock);

static void tls_device_free_ctx(struct tls_context *ctx) @@ -759,6 +760,8 @@ void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq)

if (tls_ctx->rx_conf != TLS_HW) return; + if (unlikely(test_bit(TLS_RX_DEV_DEGRADED, &tls_ctx->flags))) + return;

prot = &tls_ctx->prot_info; rx_ctx = tls_offload_ctx_rx(tls_ctx); @@ -961,6 +964,17 @@ int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx,

ctx->sw.decrypted |= is_decrypted;

+ if (unlikely(test_bit(TLS_RX_DEV_DEGRADED, &tls_ctx->flags))) { + if (likely(is_encrypted || is_decrypted)) + return 0; + + /* After tls_device_down disables the offload, the next SKB will + * likely have initial fragments decrypted, and final ones not + * decrypted. We need to reencrypt that single SKB. + */ + return tls_device_reencrypt(sk, skb); + } + /* Return immediately if the record is either entirely plaintext or * entirely ciphertext. Otherwise handle reencrypt partially decrypted * record. @@ -1290,6 +1304,26 @@ static int tls_device_down(struct net_device *netdev) spin_unlock_irqrestore(&tls_device_lock, flags);

list_for_each_entry_safe(ctx, tmp, &list, list) { + /* Stop offloaded TX and switch to the fallback. + * tls_is_sk_tx_device_offloaded will return false. + */ + WRITE_ONCE(ctx->sk->sk_validate_xmit_skb, tls_validate_xmit_skb_sw); + + /* Stop the RX and TX resync. + * tls_dev_resync must not be called after tls_dev_del. + */ + WRITE_ONCE(ctx->netdev, NULL); + + /* Start skipping the RX resync logic completely. */ + set_bit(TLS_RX_DEV_DEGRADED, &ctx->flags); + + /* Sync with inflight packets. After this point: + * TX: no non-encrypted packets will be passed to the driver. + * RX: resync requests from the driver will be ignored. + */ + synchronize_net(); + + /* Release the offload context on the driver side. */ if (ctx->tx_conf == TLS_HW) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX); @@ -1297,13 +1331,21 @@ static int tls_device_down(struct net_device *netdev) !test_bit(TLS_RX_DEV_CLOSED, &ctx->flags)) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_RX); - WRITE_ONCE(ctx->netdev, NULL); - synchronize_net(); + dev_put(netdev); - list_del_init(&ctx->list);

- if (refcount_dec_and_test(&ctx->refcount)) - tls_device_free_ctx(ctx); + /* Move the context to a separate list for two reasons: + * 1. When the context is deallocated, list_del is called. + * 2. It's no longer an offloaded context, so we don't want to + * run offload-specific code on this context. + */ + spin_lock_irqsave(&tls_device_lock, flags); + list_move_tail(&ctx->list, &tls_device_down_list); + spin_unlock_irqrestore(&tls_device_lock, flags); + + /* Device contexts for RX and TX will be freed in on sk_destruct + * by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW. + */ }

up_write(&device_offload_lock); diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index cacf040872c7..e40bedd112b6 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -431,6 +431,13 @@ struct sk_buff *tls_validate_xmit_skb(struct sock *sk, } EXPORT_SYMBOL_GPL(tls_validate_xmit_skb);

+struct sk_buff *tls_validate_xmit_skb_sw(struct sock *sk, + struct net_device *dev, + struct sk_buff *skb) +{ + return tls_sw_fallback(sk, skb); +} + struct sk_buff *tls_encrypt_skb(struct sk_buff *skb) { return tls_sw_fallback(skb->sk, skb); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 47b7c5334c34..fde56ff49163 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -636,6 +636,7 @@ struct tls_context *tls_ctx_create(struct sock *sk) mutex_init(&ctx->tx_lock); rcu_assign_pointer(icsk->icsk_ulp_data, ctx); ctx->sk_proto = READ_ONCE(sk->sk_prot); + ctx->sk = sk; return ctx; }

From: Moshe Shemesh moshe@nvidia.com

[ Upstream commit 5940e64281c09976ce2b560244217e610bf9d029 ]

In case driver sent NACK to firmware on sync reset request, it will get sync reset abort event while it didn't set sync reset requested mode. Thus, on abort sync reset event handler, driver should check reset requested is set before trying to stop sync reset poll.

Fixes: 7dd6df329d4c ("net/mlx5: Handle sync reset abort event") Signed-off-by: Moshe Shemesh moshe@nvidia.com Reviewed-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index f9042e147c7f..ee710ce00795 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -354,6 +354,9 @@ static void mlx5_sync_reset_abort_event(struct work_struct *work) reset_abort_work); struct mlx5_core_dev *dev = fw_reset->dev;

+ if (!test_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags)) + return; + mlx5_sync_reset_clear_reset_requested(dev, true); mlx5_core_warn(dev, "PCI Sync FW Update Reset Aborted.\n"); }

From: Roi Dayan roid@nvidia.com

[ Upstream commit 2a2c84facd4af661d71be6e81fd9d490ac7fdc53 ]

On some devices the ignore flow level cap is not supported and we shouldn't use it. Setting the dest ft with mlx5_chains_get_tc_end_ft() already gives the correct end ft if ignore flow level cap is supported or not.

Fixes: 39ac237ce009 ("net/mlx5: E-Switch, Refactor chains and priorities") Signed-off-by: Roi Dayan roid@nvidia.com Reviewed-by: Paul Blakey paulb@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h | 5 +++++ 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index d4a2f8d1ee9f..3719452a7803 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -349,7 +349,8 @@ esw_setup_slow_path_dest(struct mlx5_flow_destination *dest, struct mlx5_fs_chains *chains, int i) { - flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; + if (mlx5_chains_ignore_flow_level_supported(chains)) + flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest[i].ft = mlx5_chains_get_tc_end_ft(chains); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c index 381325b4a863..b607ed5a74bb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c @@ -111,7 +111,7 @@ bool mlx5_chains_prios_supported(struct mlx5_fs_chains *chains) return chains->flags & MLX5_CHAINS_AND_PRIOS_SUPPORTED; }

-static bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains) +bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains) { return chains->flags & MLX5_CHAINS_IGNORE_FLOW_LEVEL_SUPPORTED; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h index 6d5be31b05dd..9f53a0823558 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h @@ -27,6 +27,7 @@ struct mlx5_chains_attr {

bool mlx5_chains_prios_supported(struct mlx5_fs_chains *chains); +bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains); bool mlx5_chains_backwards_supported(struct mlx5_fs_chains *chains); u32 @@ -72,6 +73,10 @@ mlx5_chains_set_end_ft(struct mlx5_fs_chains *chains,

#else /* CONFIG_MLX5_CLS_ACT */

+static inline bool +mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains) +{ return false; } + static inline struct mlx5_flow_table * mlx5_chains_get_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio, u32 level) { return ERR_PTR(-EOPNOTSUPP); }

From: Max Gurtovoy mgurtovoy@nvidia.com

[ Upstream commit bcd9a0797d73eeff659582f23277e7ab6e5f18f3 ]

In case p2p device was found but the p2p pool is empty, the nvme target is still trying to free the sgl from the p2p pool instead of the regular sgl pool and causing a crash (BUG() is called). Instead, assign the p2p_dev for the request only if it was allocated from p2p pool.

This is the crash that was caused:

[Sun May 30 19:13:53 2021] ------------[ cut here ]------------ [Sun May 30 19:13:53 2021] kernel BUG at lib/genalloc.c:518! [Sun May 30 19:13:53 2021] invalid opcode: 0000 [#1] SMP PTI ... [Sun May 30 19:13:53 2021] kernel BUG at lib/genalloc.c:518! ... [Sun May 30 19:13:53 2021] RIP: 0010:gen_pool_free_owner+0xa8/0xb0 ... [Sun May 30 19:13:53 2021] Call Trace: [Sun May 30 19:13:53 2021] ------------[ cut here ]------------ [Sun May 30 19:13:53 2021] pci_free_p2pmem+0x2b/0x70 [Sun May 30 19:13:53 2021] pci_p2pmem_free_sgl+0x4f/0x80 [Sun May 30 19:13:53 2021] nvmet_req_free_sgls+0x1e/0x80 [nvmet] [Sun May 30 19:13:53 2021] kernel BUG at lib/genalloc.c:518! [Sun May 30 19:13:53 2021] nvmet_rdma_release_rsp+0x4e/0x1f0 [nvmet_rdma] [Sun May 30 19:13:53 2021] nvmet_rdma_send_done+0x1c/0x60 [nvmet_rdma]

Fixes: c6e3f1339812 ("nvmet: add metadata support for block devices") Reviewed-by: Israel Rukshin israelr@nvidia.com Signed-off-by: Max Gurtovoy mgurtovoy@nvidia.com Reviewed-by: Logan Gunthorpe logang@deltatee.com Reviewed-by: Chaitanya Kulkarni chaitanya.kulkarni@wdc.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/target/core.c | 33 ++++++++++++++++----------------- 1 file changed, 16 insertions(+), 17 deletions(-)

diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 348057fdc568..7d16cb4cd8ac 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -999,19 +999,23 @@ static unsigned int nvmet_data_transfer_len(struct nvmet_req *req) return req->transfer_len - req->metadata_len; }

-static int nvmet_req_alloc_p2pmem_sgls(struct nvmet_req *req) +static int nvmet_req_alloc_p2pmem_sgls(struct pci_dev *p2p_dev, + struct nvmet_req *req) { - req->sg = pci_p2pmem_alloc_sgl(req->p2p_dev, &req->sg_cnt, + req->sg = pci_p2pmem_alloc_sgl(p2p_dev, &req->sg_cnt, nvmet_data_transfer_len(req)); if (!req->sg) goto out_err;

if (req->metadata_len) { - req->metadata_sg = pci_p2pmem_alloc_sgl(req->p2p_dev, + req->metadata_sg = pci_p2pmem_alloc_sgl(p2p_dev, &req->metadata_sg_cnt, req->metadata_len); if (!req->metadata_sg) goto out_free_sg; } + + req->p2p_dev = p2p_dev; + return 0; out_free_sg: pci_p2pmem_free_sgl(req->p2p_dev, req->sg); @@ -1019,25 +1023,19 @@ out_err: return -ENOMEM; }

-static bool nvmet_req_find_p2p_dev(struct nvmet_req *req) +static struct pci_dev *nvmet_req_find_p2p_dev(struct nvmet_req *req) { - if (!IS_ENABLED(CONFIG_PCI_P2PDMA)) - return false; - - if (req->sq->ctrl && req->sq->qid && req->ns) { - req->p2p_dev = radix_tree_lookup(&req->sq->ctrl->p2p_ns_map, - req->ns->nsid); - if (req->p2p_dev) - return true; - } - - req->p2p_dev = NULL; - return false; + if (!IS_ENABLED(CONFIG_PCI_P2PDMA) || + !req->sq->ctrl || !req->sq->qid || !req->ns) + return NULL; + return radix_tree_lookup(&req->sq->ctrl->p2p_ns_map, req->ns->nsid); }

int nvmet_req_alloc_sgls(struct nvmet_req *req) { - if (nvmet_req_find_p2p_dev(req) && !nvmet_req_alloc_p2pmem_sgls(req)) + struct pci_dev *p2p_dev = nvmet_req_find_p2p_dev(req); + + if (p2p_dev && !nvmet_req_alloc_p2pmem_sgls(p2p_dev, req)) return 0;

req->sg = sgl_alloc(nvmet_data_transfer_len(req), GFP_KERNEL, @@ -1066,6 +1064,7 @@ void nvmet_req_free_sgls(struct nvmet_req *req) pci_p2pmem_free_sgl(req->p2p_dev, req->sg); if (req->metadata_sg) pci_p2pmem_free_sgl(req->p2p_dev, req->metadata_sg); + req->p2p_dev = NULL; } else { sgl_free(req->sg); if (req->metadata_sg)

From: Pablo Neira Ayuso pablo@netfilter.org

[ Upstream commit 8971ee8b087750a23f3cd4dc55bff2d0303fd267 ]

The private helper data size cannot be updated. However, updates that contain NFCTH_PRIV_DATA_LEN might bogusly hit EBUSY even if the size is the same.

Fixes: 12f7a505331e ("netfilter: add user-space connection tracking helper infrastructure") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nfnetlink_cthelper.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 0f94fce1d3ed..04a12a264cf7 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -380,10 +380,14 @@ static int nfnl_cthelper_update(const struct nlattr * const tb[], struct nf_conntrack_helper *helper) { + u32 size; int ret;

- if (tb[NFCTH_PRIV_DATA_LEN]) - return -EBUSY; + if (tb[NFCTH_PRIV_DATA_LEN]) { + size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN])); + if (size != helper->data_len) + return -EBUSY; + }

if (tb[NFCTH_POLICY]) { ret = nfnl_cthelper_update_policy(helper, tb[NFCTH_POLICY]);

From: Daniel Borkmann daniel@iogearbox.net

[ Upstream commit ff40e51043af63715ab413995ff46996ecf9583f ]

Commit 59438b46471a ("security,lockdown,selinux: implement SELinux lockdown") added an implementation of the locked_down LSM hook to SELinux, with the aim to restrict which domains are allowed to perform operations that would breach lockdown. This is indirectly also getting audit subsystem involved to report events. The latter is problematic, as reported by Ondrej and Serhei, since it can bring down the whole system via audit:

1) The audit events that are triggered due to calls to security_locked_down() can OOM kill a machine, see below details [0].

2) It also seems to be causing a deadlock via avc_has_perm()/slow_avc_audit() when trying to wake up kauditd, for example, when using trace_sched_switch() tracepoint, see details in [1]. Triggering this was not via some hypothetical corner case, but with existing tools like runqlat & runqslower from bcc, for example, which make use of this tracepoint. Rough call sequence goes like:

rq_lock(rq) -> -------------------------+ trace_sched_switch() -> | bpf_prog_xyz() -> +-> deadlock selinux_lockdown() -> | audit_log_end() -> | wake_up_interruptible() -> | try_to_wake_up() -> | rq_lock(rq) --------------+

What's worse is that the intention of 59438b46471a to further restrict lockdown settings for specific applications in respect to the global lockdown policy is completely broken for BPF. The SELinux policy rule for the current lockdown check looks something like this:

allow <who> <who> : lockdown { <reason> };

However, this doesn't match with the 'current' task where the security_locked_down() is executed, example: httpd does a syscall. There is a tracing program attached to the syscall which triggers a BPF program to run, which ends up doing a bpf_probe_read_kernel{,_str}() helper call. The selinux_lockdown() hook does the permission check against 'current', that is, httpd in this example. httpd has literally zero relation to this tracing program, and it would be nonsensical having to write an SELinux policy rule against httpd to let the tracing helper pass. The policy in this case needs to be against the entity that is installing the BPF program. For example, if bpftrace would generate a histogram of syscall counts by user space application:

bpftrace -e 'tracepoint:raw_syscalls:sys_enter { @[comm] = count(); }'

bpftrace would then go and generate a BPF program from this internally. One way of doing it [for the sake of the example] could be to call bpf_get_current_task() helper and then access current->comm via one of bpf_probe_read_kernel{,_str}() helpers. So the program itself has nothing to do with httpd or any other random app doing a syscall here. The BPF program _explicitly initiated_ the lockdown check. The allow/deny policy belongs in the context of bpftrace: meaning, you want to grant bpftrace access to use these helpers, but other tracers on the system like my_random_tracer _not_.

Therefore fix all three issues at the same time by taking a completely different approach for the security_locked_down() hook, that is, move the check into the program verification phase where we actually retrieve the BPF func proto. This also reliably gets the task (current) that is trying to install the BPF tracing program, e.g. bpftrace/bcc/perf/systemtap/etc, and it also fixes the OOM since we're moving this out of the BPF helper's fast-path which can be called several millions of times per second.

The check is then also in line with other security_locked_down() hooks in the system where the enforcement is performed at open/load time, for example, open_kcore() for /proc/kcore access or module_sig_check() for module signatures just to pick few random ones. What's out of scope in the fix as well as in other security_locked_down() hook locations /outside/ of BPF subsystem is that if the lockdown policy changes on the fly there is no retrospective action. This requires a different discussion, potentially complex infrastructure, and it's also not clear whether this can be solved generically. Either way, it is out of scope for a suitable stable fix which this one is targeting. Note that the breakage is specifically on 59438b46471a where it started to rely on 'current' as UAPI behavior, and _not_ earlier infrastructure such as 9d1f8be5cf42 ("bpf: Restrict bpf when kernel lockdown is in confidentiality mode").

[0] https://bugzilla.redhat.com/show_bug.cgi?id=1955585, Jakub Hrozek says:

I starting seeing this with F-34. When I run a container that is traced with BPF to record the syscalls it is doing, auditd is flooded with messages like:

type=AVC msg=audit(1619784520.593:282387): avc: denied { confidentiality } for pid=476 comm="auditd" lockdown_reason="use of bpf to read kernel RAM" scontext=system_u:system_r:auditd_t:s0 tcontext=system_u:system_r:auditd_t:s0 tclass=lockdown permissive=0

This seems to be leading to auditd running out of space in the backlog buffer and eventually OOMs the machine.

[...] auditd running at 99% CPU presumably processing all the messages, eventually I get: Apr 30 12:20:42 fedora kernel: audit: backlog limit exceeded Apr 30 12:20:42 fedora kernel: audit: backlog limit exceeded Apr 30 12:20:42 fedora kernel: audit: audit_backlog=2152579 > audit_backlog_limit=64 Apr 30 12:20:42 fedora kernel: audit: audit_backlog=2152626 > audit_backlog_limit=64 Apr 30 12:20:42 fedora kernel: audit: audit_backlog=2152694 > audit_backlog_limit=64 Apr 30 12:20:42 fedora kernel: audit: audit_lost=6878426 audit_rate_limit=0 audit_backlog_limit=64 Apr 30 12:20:45 fedora kernel: oci-seccomp-bpf invoked oom-killer: gfp_mask=0x100cca(GFP_HIGHUSER_MOVABLE), order=0, oom_score_adj=-1000 Apr 30 12:20:45 fedora kernel: CPU: 0 PID: 13284 Comm: oci-seccomp-bpf Not tainted 5.11.12-300.fc34.x86_64 #1 Apr 30 12:20:45 fedora kernel: Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.fc32 04/01/2014 [...]

[1] https://lore.kernel.org/linux-audit/CANYvDQN7H5tVp47fbYcRasv4XF07eUbsDwT_eDC..., Serhei Makarov says:

Upstream kernel 5.11.0-rc7 and later was found to deadlock during a bpf_probe_read_compat() call within a sched_switch tracepoint. The problem is reproducible with the reg_alloc3 testcase from SystemTap's BPF backend testsuite on x86_64 as well as the runqlat, runqslower tools from bcc on ppc64le. Example stack trace:

[...] [ 730.868702] stack backtrace: [ 730.869590] CPU: 1 PID: 701 Comm: in:imjournal Not tainted, 5.12.0-0.rc2.20210309git144c79ef3353.166.fc35.x86_64 #1 [ 730.871605] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014 [ 730.873278] Call Trace: [ 730.873770] dump_stack+0x7f/0xa1 [ 730.874433] check_noncircular+0xdf/0x100 [ 730.875232] __lock_acquire+0x1202/0x1e10 [ 730.876031] ? __lock_acquire+0xfc0/0x1e10 [ 730.876844] lock_acquire+0xc2/0x3a0 [ 730.877551] ? __wake_up_common_lock+0x52/0x90 [ 730.878434] ? lock_acquire+0xc2/0x3a0 [ 730.879186] ? lock_is_held_type+0xa7/0x120 [ 730.880044] ? skb_queue_tail+0x1b/0x50 [ 730.880800] _raw_spin_lock_irqsave+0x4d/0x90 [ 730.881656] ? __wake_up_common_lock+0x52/0x90 [ 730.882532] __wake_up_common_lock+0x52/0x90 [ 730.883375] audit_log_end+0x5b/0x100 [ 730.884104] slow_avc_audit+0x69/0x90 [ 730.884836] avc_has_perm+0x8b/0xb0 [ 730.885532] selinux_lockdown+0xa5/0xd0 [ 730.886297] security_locked_down+0x20/0x40 [ 730.887133] bpf_probe_read_compat+0x66/0xd0 [ 730.887983] bpf_prog_250599c5469ac7b5+0x10f/0x820 [ 730.888917] trace_call_bpf+0xe9/0x240 [ 730.889672] perf_trace_run_bpf_submit+0x4d/0xc0 [ 730.890579] perf_trace_sched_switch+0x142/0x180 [ 730.891485] ? __schedule+0x6d8/0xb20 [ 730.892209] __schedule+0x6d8/0xb20 [ 730.892899] schedule+0x5b/0xc0 [ 730.893522] exit_to_user_mode_prepare+0x11d/0x240 [ 730.894457] syscall_exit_to_user_mode+0x27/0x70 [ 730.895361] entry_SYSCALL_64_after_hwframe+0x44/0xae [...]

Fixes: 59438b46471a ("security,lockdown,selinux: implement SELinux lockdown") Reported-by: Ondrej Mosnacek omosnace@redhat.com Reported-by: Jakub Hrozek jhrozek@redhat.com Reported-by: Serhei Makarov smakarov@redhat.com Reported-by: Jiri Olsa jolsa@redhat.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Acked-by: Alexei Starovoitov ast@kernel.org Tested-by: Jiri Olsa jolsa@redhat.com Cc: Paul Moore paul@paul-moore.com Cc: James Morris jamorris@linux.microsoft.com Cc: Jerome Marchand jmarchan@redhat.com Cc: Frank Eigler fche@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Link: https://lore.kernel.org/bpf/01135120-8bf7-df2e-cff0-1d73f1f841c3@iogearbox.n... Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/bpf/helpers.c | 7 +++++-- kernel/trace/bpf_trace.c | 32 ++++++++++++-------------------- 2 files changed, 17 insertions(+), 22 deletions(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 308427fe03a3..6140e91e9c89 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -14,6 +14,7 @@ #include <linux/jiffies.h> #include <linux/pid_namespace.h> #include <linux/proc_ns.h> +#include <linux/security.h>

#include "../../lib/kstrtox.h"

@@ -741,11 +742,13 @@ bpf_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return &bpf_probe_read_kernel_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return &bpf_probe_read_kernel_str_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_kernel_str_proto; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; default: diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index b0c45d923f0f..9bb3d2823f44 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -215,16 +215,11 @@ const struct bpf_func_proto bpf_probe_read_user_str_proto = { static __always_inline int bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) { - int ret = security_locked_down(LOCKDOWN_BPF_READ); + int ret;

- if (unlikely(ret < 0)) - goto fail; ret = copy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) - goto fail; - return ret; -fail: - memset(dst, 0, size); + memset(dst, 0, size); return ret; }

@@ -246,10 +241,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_proto = { static __always_inline int bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr) { - int ret = security_locked_down(LOCKDOWN_BPF_READ); - - if (unlikely(ret < 0)) - goto fail; + int ret;

/* * The strncpy_from_kernel_nofault() call will likely not fill the @@ -262,11 +254,7 @@ bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr) */ ret = strncpy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) - goto fail; - - return ret; -fail: - memset(dst, 0, size); + memset(dst, 0, size); return ret; }

@@ -1322,16 +1310,20 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return &bpf_probe_read_kernel_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return &bpf_probe_read_kernel_str_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_kernel_str_proto; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE case BPF_FUNC_probe_read: - return &bpf_probe_read_compat_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_str: - return &bpf_probe_read_compat_str_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_compat_str_proto; #endif #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id:

From: Wei Yongjun weiyongjun1@huawei.com

[ Upstream commit 373e864cf52403b0974c2f23ca8faf9104234555 ]

Fix to return negative error code -ENOBUFS from the error handling case instead of 0, as done elsewhere in this function.

Fixes: 3e9c156e2c21 ("ieee802154: add netlink interfaces for llsec") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Wei Yongjun weiyongjun1@huawei.com Link: https://lore.kernel.org/r/20210519141614.3040055-1-weiyongjun1@huawei.com Signed-off-by: Stefan Schmidt stefan@datenfreihafen.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ieee802154/nl-mac.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index 0c1b0770c59e..c23c152860b7 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -680,8 +680,10 @@ int ieee802154_llsec_getparams(struct sk_buff *skb, struct genl_info *info) nla_put_u8(msg, IEEE802154_ATTR_LLSEC_SECLEVEL, params.out_level) || nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER, be32_to_cpu(params.frame_counter)) || - ieee802154_llsec_fill_key_id(msg, &params.out_key)) + ieee802154_llsec_fill_key_id(msg, &params.out_key)) { + rc = -ENOBUFS; goto out_free; + }

dev_put(dev);

From: Magnus Karlsson magnus.karlsson@intel.com

[ Upstream commit 74431c40b9c5fa673fff83ec157a76a69efd5c72 ]

Add missing exception tracing to XDP when a number of different errors can occur. The support was only partial. Several errors where not logged which would confuse the user quite a lot not knowing where and why the packets disappeared.

Fixes: 9cbc948b5a20 ("igb: add XDP support") Reported-by: Jesper Dangaard Brouer brouer@redhat.com Signed-off-by: Magnus Karlsson magnus.karlsson@intel.com Tested-by: Vishakha Jambekar vishakha.jambekar@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/igb/igb_main.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index a41b85f1fc94..caa8929289ae 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8395,18 +8395,20 @@ static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter, break; case XDP_TX: result = igb_xdp_xmit_back(adapter, xdp); + if (result == IGB_XDP_CONSUMED) + goto out_failure; break; case XDP_REDIRECT: err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); - if (!err) - result = IGB_XDP_REDIR; - else - result = IGB_XDP_CONSUMED; + if (err) + goto out_failure; + result = IGB_XDP_REDIR; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_DROP:

From: Maciej Fijalkowski maciej.fijalkowski@intel.com

[ Upstream commit e102db780e1c14f10c70dafa7684af22a745b51d ]

Commit c7a219048e45 ("ice: Remove xsk_buff_pool from VSI structure") silently introduced a regression and broke the Tx side of AF_XDP in copy mode. xsk_pool on ice_ring is set only based on the existence of the XDP prog on the VSI which in turn picks ice_clean_tx_irq_zc to be executed. That is not something that should happen for copy mode as it should use the regular data path ice_clean_tx_irq.

This results in a following splat when xdpsock is run in txonly or l2fwd scenarios in copy mode:

<snip> [ 106.050195] BUG: kernel NULL pointer dereference, address: 0000000000000030 [ 106.057269] #PF: supervisor read access in kernel mode [ 106.062493] #PF: error_code(0x0000) - not-present page [ 106.067709] PGD 0 P4D 0 [ 106.070293] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 106.074721] CPU: 61 PID: 0 Comm: swapper/61 Not tainted 5.12.0-rc2+ #45 [ 106.081436] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0008.031920191559 03/19/2019 [ 106.092027] RIP: 0010:xp_raw_get_dma+0x36/0x50 [ 106.096551] Code: 74 14 48 b8 ff ff ff ff ff ff 00 00 48 21 f0 48 c1 ee 30 48 01 c6 48 8b 87 90 00 00 00 48 89 f2 81 e6 ff 0f 00 00 48 c1 ea 0c <48> 8b 04 d0 48 83 e0 fe 48 01 f0 c3 66 66 2e 0f 1f 84 00 00 00 00 [ 106.115588] RSP: 0018:ffffc9000d694e50 EFLAGS: 00010206 [ 106.120893] RAX: 0000000000000000 RBX: ffff88984b8c8a00 RCX: ffff889852581800 [ 106.128137] RDX: 0000000000000006 RSI: 0000000000000000 RDI: ffff88984cd8b800 [ 106.135383] RBP: ffff888123b50001 R08: ffff889896800000 R09: 0000000000000800 [ 106.142628] R10: 0000000000000000 R11: ffffffff826060c0 R12: 00000000000000ff [ 106.149872] R13: 0000000000000000 R14: 0000000000000040 R15: ffff888123b50018 [ 106.157117] FS: 0000000000000000(0000) GS:ffff8897e0f40000(0000) knlGS:0000000000000000 [ 106.165332] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 106.171163] CR2: 0000000000000030 CR3: 000000000560a004 CR4: 00000000007706e0 [ 106.178408] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 106.185653] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 106.192898] PKRU: 55555554 [ 106.195653] Call Trace: [ 106.198143] <IRQ> [ 106.200196] ice_clean_tx_irq_zc+0x183/0x2a0 [ice] [ 106.205087] ice_napi_poll+0x3e/0x590 [ice] [ 106.209356] __napi_poll+0x2a/0x160 [ 106.212911] net_rx_action+0xd6/0x200 [ 106.216634] __do_softirq+0xbf/0x29b [ 106.220274] irq_exit_rcu+0x88/0xc0 [ 106.223819] common_interrupt+0x7b/0xa0 [ 106.227719] </IRQ> [ 106.229857] asm_common_interrupt+0x1e/0x40 </snip>

Fix this by introducing the bitmap of queues that are zero-copy enabled, where each bit, corresponding to a queue id that xsk pool is being configured on, will be set/cleared within ice_xsk_pool_{en,dis}able and checked within ice_xsk_pool(). The latter is a function used for deciding which napi poll routine is executed. Idea is being taken from our other drivers such as i40e and ixgbe.

Fixes: c7a219048e45 ("ice: Remove xsk_buff_pool from VSI structure") Signed-off-by: Maciej Fijalkowski maciej.fijalkowski@intel.com Tested-by: Kiran Bhandare kiranx.bhandare@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ice/ice.h | 8 +++++--- drivers/net/ethernet/intel/ice/ice_lib.c | 10 ++++++++++ drivers/net/ethernet/intel/ice/ice_xsk.c | 3 +++ 3 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 17101c45cbcd..f668296ca677 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -325,6 +325,7 @@ struct ice_vsi { struct ice_tc_cfg tc_cfg; struct bpf_prog *xdp_prog; struct ice_ring **xdp_rings; /* XDP ring array */ + unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */ u16 num_xdp_txq; /* Used XDP queues */ u8 xdp_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */

@@ -534,15 +535,16 @@ static inline void ice_set_ring_xdp(struct ice_ring *ring) */ static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_ring *ring) { + struct ice_vsi *vsi = ring->vsi; u16 qid = ring->q_index;

if (ice_ring_is_xdp(ring)) - qid -= ring->vsi->num_xdp_txq; + qid -= vsi->num_xdp_txq;

- if (!ice_is_xdp_ena_vsi(ring->vsi)) + if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) return NULL;

- return xsk_get_pool_from_qid(ring->vsi->netdev, qid); + return xsk_get_pool_from_qid(vsi->netdev, qid); }

/** diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 195d122c9cb2..9b38b2768884 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -105,8 +105,14 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) if (!vsi->q_vectors) goto err_vectors;

+ vsi->af_xdp_zc_qps = bitmap_zalloc(max_t(int, vsi->alloc_txq, vsi->alloc_rxq), GFP_KERNEL); + if (!vsi->af_xdp_zc_qps) + goto err_zc_qps; + return 0;

+err_zc_qps: + devm_kfree(dev, vsi->q_vectors); err_vectors: devm_kfree(dev, vsi->rxq_map); err_rxq_map: @@ -286,6 +292,10 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi)

dev = ice_pf_to_dev(pf);

+ if (vsi->af_xdp_zc_qps) { + bitmap_free(vsi->af_xdp_zc_qps); + vsi->af_xdp_zc_qps = NULL; + } /* free the ring and vector containers */ if (vsi->q_vectors) { devm_kfree(dev, vsi->q_vectors); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 9f94d9159acd..47efc89a336f 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -273,6 +273,7 @@ static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid) if (!pool) return -EINVAL;

+ clear_bit(qid, vsi->af_xdp_zc_qps); xsk_pool_dma_unmap(pool, ICE_RX_DMA_ATTR);

return 0; @@ -303,6 +304,8 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) if (err) return err;

+ set_bit(qid, vsi->af_xdp_zc_qps); + return 0; }

From: Coco Li lixiaoyan@google.com

[ Upstream commit 821bbf79fe46a8b1d18aa456e8ed0a3c208c3754 ]

Reported by syzbot: HEAD commit: 90c911ad Merge tag 'fixes' of git://git.kernel.org/pub/scm.. git tree: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master dashboard link: https://syzkaller.appspot.com/bug?extid=123aa35098fd3c000eb7 compiler: Debian clang version 11.0.1-2

================================================================== BUG: KASAN: slab-out-of-bounds in fib6_nh_get_excptn_bucket net/ipv6/route.c:1604 [inline] BUG: KASAN: slab-out-of-bounds in fib6_nh_flush_exceptions+0xbd/0x360 net/ipv6/route.c:1732 Read of size 8 at addr ffff8880145c78f8 by task syz-executor.4/17760

CPU: 0 PID: 17760 Comm: syz-executor.4 Not tainted 5.12.0-rc8-syzkaller #0 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x202/0x31e lib/dump_stack.c:120 print_address_description+0x5f/0x3b0 mm/kasan/report.c:232 __kasan_report mm/kasan/report.c:399 [inline] kasan_report+0x15c/0x200 mm/kasan/report.c:416 fib6_nh_get_excptn_bucket net/ipv6/route.c:1604 [inline] fib6_nh_flush_exceptions+0xbd/0x360 net/ipv6/route.c:1732 fib6_nh_release+0x9a/0x430 net/ipv6/route.c:3536 fib6_info_destroy_rcu+0xcb/0x1c0 net/ipv6/ip6_fib.c:174 rcu_do_batch kernel/rcu/tree.c:2559 [inline] rcu_core+0x8f6/0x1450 kernel/rcu/tree.c:2794 __do_softirq+0x372/0x7a6 kernel/softirq.c:345 invoke_softirq kernel/softirq.c:221 [inline] __irq_exit_rcu+0x22c/0x260 kernel/softirq.c:422 irq_exit_rcu+0x5/0x20 kernel/softirq.c:434 sysvec_apic_timer_interrupt+0x91/0xb0 arch/x86/kernel/apic/apic.c:1100 </IRQ> asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:632 RIP: 0010:lock_acquire+0x1f6/0x720 kernel/locking/lockdep.c:5515 Code: f6 84 24 a1 00 00 00 02 0f 85 8d 02 00 00 f7 c3 00 02 00 00 49 bd 00 00 00 00 00 fc ff df 74 01 fb 48 c7 44 24 40 0e 36 e0 45 <4b> c7 44 3d 00 00 00 00 00 4b c7 44 3d 09 00 00 00 00 43 c7 44 3d RSP: 0018:ffffc90009e06560 EFLAGS: 00000206 RAX: 1ffff920013c0cc0 RBX: 0000000000000246 RCX: dffffc0000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffc90009e066e0 R08: dffffc0000000000 R09: fffffbfff1f992b1 R10: fffffbfff1f992b1 R11: 0000000000000000 R12: 0000000000000000 R13: dffffc0000000000 R14: 0000000000000000 R15: 1ffff920013c0cb4 rcu_lock_acquire+0x2a/0x30 include/linux/rcupdate.h:267 rcu_read_lock include/linux/rcupdate.h:656 [inline] ext4_get_group_info+0xea/0x340 fs/ext4/ext4.h:3231 ext4_mb_prefetch+0x123/0x5d0 fs/ext4/mballoc.c:2212 ext4_mb_regular_allocator+0x8a5/0x28f0 fs/ext4/mballoc.c:2379 ext4_mb_new_blocks+0xc6e/0x24f0 fs/ext4/mballoc.c:4982 ext4_ext_map_blocks+0x2be3/0x7210 fs/ext4/extents.c:4238 ext4_map_blocks+0xab3/0x1cb0 fs/ext4/inode.c:638 ext4_getblk+0x187/0x6c0 fs/ext4/inode.c:848 ext4_bread+0x2a/0x1c0 fs/ext4/inode.c:900 ext4_append+0x1a4/0x360 fs/ext4/namei.c:67 ext4_init_new_dir+0x337/0xa10 fs/ext4/namei.c:2768 ext4_mkdir+0x4b8/0xc00 fs/ext4/namei.c:2814 vfs_mkdir+0x45b/0x640 fs/namei.c:3819 ovl_do_mkdir fs/overlayfs/overlayfs.h:161 [inline] ovl_mkdir_real+0x53/0x1a0 fs/overlayfs/dir.c:146 ovl_create_real+0x280/0x490 fs/overlayfs/dir.c:193 ovl_workdir_create+0x425/0x600 fs/overlayfs/super.c:788 ovl_make_workdir+0xed/0x1140 fs/overlayfs/super.c:1355 ovl_get_workdir fs/overlayfs/super.c:1492 [inline] ovl_fill_super+0x39ee/0x5370 fs/overlayfs/super.c:2035 mount_nodev+0x52/0xe0 fs/super.c:1413 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x86/0x270 fs/super.c:1497 do_new_mount fs/namespace.c:2903 [inline] path_mount+0x196f/0x2be0 fs/namespace.c:3233 do_mount fs/namespace.c:3246 [inline] __do_sys_mount fs/namespace.c:3454 [inline] __se_sys_mount+0x2f9/0x3b0 fs/namespace.c:3431 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x4665f9 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f68f2b87188 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 000000000056bf60 RCX: 00000000004665f9 RDX: 00000000200000c0 RSI: 0000000020000000 RDI: 000000000040000a RBP: 00000000004bfbb9 R08: 0000000020000100 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000056bf60 R13: 00007ffe19002dff R14: 00007f68f2b87300 R15: 0000000000022000

Allocated by task 17768: kasan_save_stack mm/kasan/common.c:38 [inline] kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:427 [inline] ____kasan_kmalloc+0xc2/0xf0 mm/kasan/common.c:506 kasan_kmalloc include/linux/kasan.h:233 [inline] __kmalloc+0xb4/0x380 mm/slub.c:4055 kmalloc include/linux/slab.h:559 [inline] kzalloc include/linux/slab.h:684 [inline] fib6_info_alloc+0x2c/0xd0 net/ipv6/ip6_fib.c:154 ip6_route_info_create+0x55d/0x1a10 net/ipv6/route.c:3638 ip6_route_add+0x22/0x120 net/ipv6/route.c:3728 inet6_rtm_newroute+0x2cd/0x2260 net/ipv6/route.c:5352 rtnetlink_rcv_msg+0xb34/0xe70 net/core/rtnetlink.c:5553 netlink_rcv_skb+0x1f0/0x460 net/netlink/af_netlink.c:2502 netlink_unicast_kernel net/netlink/af_netlink.c:1312 [inline] netlink_unicast+0x7de/0x9b0 net/netlink/af_netlink.c:1338 netlink_sendmsg+0xaa6/0xe90 net/netlink/af_netlink.c:1927 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x5a2/0x900 net/socket.c:2350 ___sys_sendmsg net/socket.c:2404 [inline] __sys_sendmsg+0x319/0x400 net/socket.c:2433 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xae

Last potentially related work creation: kasan_save_stack+0x27/0x50 mm/kasan/common.c:38 kasan_record_aux_stack+0xee/0x120 mm/kasan/generic.c:345 __call_rcu kernel/rcu/tree.c:3039 [inline] call_rcu+0x1b1/0xa30 kernel/rcu/tree.c:3114 fib6_info_release include/net/ip6_fib.h:337 [inline] ip6_route_info_create+0x10c4/0x1a10 net/ipv6/route.c:3718 ip6_route_add+0x22/0x120 net/ipv6/route.c:3728 inet6_rtm_newroute+0x2cd/0x2260 net/ipv6/route.c:5352 rtnetlink_rcv_msg+0xb34/0xe70 net/core/rtnetlink.c:5553 netlink_rcv_skb+0x1f0/0x460 net/netlink/af_netlink.c:2502 netlink_unicast_kernel net/netlink/af_netlink.c:1312 [inline] netlink_unicast+0x7de/0x9b0 net/netlink/af_netlink.c:1338 netlink_sendmsg+0xaa6/0xe90 net/netlink/af_netlink.c:1927 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x5a2/0x900 net/socket.c:2350 ___sys_sendmsg net/socket.c:2404 [inline] __sys_sendmsg+0x319/0x400 net/socket.c:2433 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xae

Second to last potentially related work creation: kasan_save_stack+0x27/0x50 mm/kasan/common.c:38 kasan_record_aux_stack+0xee/0x120 mm/kasan/generic.c:345 insert_work+0x54/0x400 kernel/workqueue.c:1331 __queue_work+0x981/0xcc0 kernel/workqueue.c:1497 queue_work_on+0x111/0x200 kernel/workqueue.c:1524 queue_work include/linux/workqueue.h:507 [inline] call_usermodehelper_exec+0x283/0x470 kernel/umh.c:433 kobject_uevent_env+0x1349/0x1730 lib/kobject_uevent.c:617 kvm_uevent_notify_change+0x309/0x3b0 arch/x86/kvm/../../../virt/kvm/kvm_main.c:4809 kvm_destroy_vm arch/x86/kvm/../../../virt/kvm/kvm_main.c:877 [inline] kvm_put_kvm+0x9c/0xd10 arch/x86/kvm/../../../virt/kvm/kvm_main.c:920 kvm_vcpu_release+0x53/0x60 arch/x86/kvm/../../../virt/kvm/kvm_main.c:3120 __fput+0x352/0x7b0 fs/file_table.c:280 task_work_run+0x146/0x1c0 kernel/task_work.c:140 tracehook_notify_resume include/linux/tracehook.h:189 [inline] exit_to_user_mode_loop kernel/entry/common.c:174 [inline] exit_to_user_mode_prepare+0x10b/0x1e0 kernel/entry/common.c:208 __syscall_exit_to_user_mode_work kernel/entry/common.c:290 [inline] syscall_exit_to_user_mode+0x26/0x70 kernel/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x44/0xae

The buggy address belongs to the object at ffff8880145c7800 which belongs to the cache kmalloc-192 of size 192 The buggy address is located 56 bytes to the right of 192-byte region [ffff8880145c7800, ffff8880145c78c0) The buggy address belongs to the page: page:ffffea00005171c0 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x145c7 flags: 0xfff00000000200(slab) raw: 00fff00000000200 ffffea00006474c0 0000000200000002 ffff888010c41a00 raw: 0000000000000000 0000000080100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected

Memory state around the buggy address: ffff8880145c7780: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc ffff8880145c7800: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00

ffff8880145c7880: 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc fc

^ ffff8880145c7900: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880145c7980: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc ==================================================================

In the ip6_route_info_create function, in the case that the nh pointer is not NULL, the fib6_nh in fib6_info has not been allocated. Therefore, when trying to free fib6_info in this error case using fib6_info_release, the function will call fib6_info_destroy_rcu, which it will access fib6_nh_release(f6i->fib6_nh); However, f6i->fib6_nh doesn't have any refcount yet given the lack of allocation causing the reported memory issue above. Therefore, releasing the empty pointer directly instead would be the solution.

Fixes: f88d8ea67fbdb ("ipv6: Plumb support for nexthop object in a fib6_info") Fixes: 706ec91916462 ("ipv6: Fix nexthop refcnt leak when creating ipv6 route info") Signed-off-by: Coco Li lixiaoyan@google.com Cc: David Ahern dsahern@kernel.org Reviewed-by: Eric Dumazet edumazet@google.com Reviewed-by: David Ahern dsahern@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/route.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 373d48073106..36e80b3598b0 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3676,11 +3676,11 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, if (nh) { if (rt->fib6_src.plen) { NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); - goto out; + goto out_free; } if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); - goto out; + goto out_free; } rt->nh = nh; fib6_nh = nexthop_fib6_nh(rt->nh); @@ -3717,6 +3717,10 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, out: fib6_info_release(rt); return ERR_PTR(err); +out_free: + ip_fib_metrics_put(rt->fib6_metrics); + kfree(rt); + return ERR_PTR(err); }

int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,

From: Brett Creeley brett.creeley@intel.com

[ Upstream commit 8679f07a9922068b9b6be81b632f52cac45d1b91 ]

Some AVF drivers expect the VF_MBX_ATQLEN register to be cleared for any type of VFR/VFLR. Fix this by clearing the VF_MBX_ATQLEN register at the same time as VF_MBX_ARQLEN.

Fixes: 82ba01282cf8 ("ice: clear VF ARQLEN register on reset") Signed-off-by: Brett Creeley brett.creeley@intel.com Tested-by: Konrad Jankowski konrad0.jankowski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ice/ice_hw_autogen.h | 1 + drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 12 +++++++----- 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 093a1818a392..1998821896c0 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -31,6 +31,7 @@ #define PF_FW_ATQLEN_ATQOVFL_M BIT(29) #define PF_FW_ATQLEN_ATQCRIT_M BIT(30) #define VF_MBX_ARQLEN(_VF) (0x0022BC00 + ((_VF) * 4)) +#define VF_MBX_ATQLEN(_VF) (0x0022A800 + ((_VF) * 4)) #define PF_FW_ATQLEN_ATQENABLE_M BIT(31) #define PF_FW_ATQT 0x00080400 #define PF_MBX_ARQBAH 0x0022E400 diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 1f38a8d0c525..0f2a4d48574e 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -435,13 +435,15 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr) */ clear_bit(ICE_VF_STATE_INIT, vf->vf_states);

- /* VF_MBX_ARQLEN is cleared by PFR, so the driver needs to clear it - * in the case of VFR. If this is done for PFR, it can mess up VF - * resets because the VF driver may already have started cleanup - * by the time we get here. + /* VF_MBX_ARQLEN and VF_MBX_ATQLEN are cleared by PFR, so the driver + * needs to clear them in the case of VFR/VFLR. If this is done for + * PFR, it can mess up VF resets because the VF driver may already + * have started cleanup by the time we get here. */ - if (!is_pfr) + if (!is_pfr) { wr32(hw, VF_MBX_ARQLEN(vf->vf_id), 0); + wr32(hw, VF_MBX_ATQLEN(vf->vf_id), 0); + }

/* In the case of a VFLR, the HW has already reset the VF and we * just need to clean up, so don't hit the VFRTRIG register.

From: Paul Greenwalt paul.greenwalt@intel.com

[ Upstream commit 5cd349c349d6ec52862e550d3576893d35ab8ac2 ]

Ethtool incorrectly reported supported and advertised auto-negotiation settings for a backplane PHY image which did not support auto-negotiation. This can occur when using media or PHY type for reporting ethtool supported and advertised auto-negotiation settings.

Remove setting supported and advertised auto-negotiation settings based on PHY type in ice_phy_type_to_ethtool(), and MAC type in ice_get_link_ksettings().

Ethtool supported and advertised auto-negotiation settings should be based on the PHY image using the AQ command get PHY capabilities with media. Add setting supported and advertised auto-negotiation settings based get PHY capabilities with media in ice_get_link_ksettings().

Fixes: 48cb27f2fd18 ("ice: Implement handlers for ethtool PHY/link operations") Signed-off-by: Paul Greenwalt paul.greenwalt@intel.com Tested-by: Tony Brelinski tonyx.brelinski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ice/ice_ethtool.c | 51 +++----------------- 1 file changed, 6 insertions(+), 45 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 32ba71a16165..f80fff97d8dc 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1797,49 +1797,6 @@ ice_phy_type_to_ethtool(struct net_device *netdev, ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB, 100000baseKR4_Full); } - - /* Autoneg PHY types */ - if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX || - phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_T || - phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_KX || - phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_T || - phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_KX || - phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_T || - phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_KR || - phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_T || - phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_KR_CR1 || - phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_T || - phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR || - phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR_S || - phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR1 || - phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR || - phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR_S || - phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR1 || - phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_CR4 || - phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_KR4) { - ethtool_link_ksettings_add_link_mode(ks, supported, - Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - Autoneg); - } - if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CR2 || - phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR2 || - phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CP || - phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4) { - ethtool_link_ksettings_add_link_mode(ks, supported, - Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - Autoneg); - } - if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CR4 || - phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR4 || - phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4 || - phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CP2) { - ethtool_link_ksettings_add_link_mode(ks, supported, - Autoneg); - ethtool_link_ksettings_add_link_mode(ks, advertising, - Autoneg); - } }

#define TEST_SET_BITS_TIMEOUT 50 @@ -1996,9 +1953,7 @@ ice_get_link_ksettings(struct net_device *netdev, ks->base.port = PORT_TP; break; case ICE_MEDIA_BACKPLANE: - ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); ethtool_link_ksettings_add_link_mode(ks, supported, Backplane); - ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); ethtool_link_ksettings_add_link_mode(ks, advertising, Backplane); ks->base.port = PORT_NONE; @@ -2073,6 +2028,12 @@ ice_get_link_ksettings(struct net_device *netdev, if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN) ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);

+ /* Set supported and advertised autoneg */ + if (ice_is_phy_caps_an_enabled(caps)) { + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + } + done: kfree(caps); return err;

From: Roja Rani Yarubandi rojay@codeaurora.org

[ Upstream commit 9f78c607600ce4f2a952560de26534715236f612 ]

If the hardware is still accessing memory after SMMU translation is disabled (as part of smmu shutdown callback), then the IOVAs (I/O virtual address) which it was using will go on the bus as the physical addresses which will result in unknown crashes like NoC/interconnect errors.

So, implement shutdown callback for i2c driver to suspend the bus during system "reboot" or "shutdown".

Fixes: 37692de5d523 ("i2c: i2c-qcom-geni: Add bus driver for the Qualcomm GENI I2C controller") Signed-off-by: Roja Rani Yarubandi rojay@codeaurora.org Reviewed-by: Stephen Boyd swboyd@chromium.org Signed-off-by: Wolfram Sang wsa@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/i2c/busses/i2c-qcom-geni.c | 9 +++++++++ 1 file changed, 9 insertions(+)

diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 214b4c913a13..c3ae66ba6345 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -650,6 +650,14 @@ static int geni_i2c_remove(struct platform_device *pdev) return 0; }

+static void geni_i2c_shutdown(struct platform_device *pdev) +{ + struct geni_i2c_dev *gi2c = platform_get_drvdata(pdev); + + /* Make client i2c transfers start failing */ + i2c_mark_adapter_suspended(&gi2c->adap); +} + static int __maybe_unused geni_i2c_runtime_suspend(struct device *dev) { int ret; @@ -714,6 +722,7 @@ MODULE_DEVICE_TABLE(of, geni_i2c_dt_match); static struct platform_driver geni_i2c_driver = { .probe = geni_i2c_probe, .remove = geni_i2c_remove, + .shutdown = geni_i2c_shutdown, .driver = { .name = "geni_i2c", .pm = &geni_i2c_pm_ops,

From: Rahul Lakkireddy rahul.lakkireddy@chelsio.com

[ Upstream commit 3822d0670c9d4342794d73e0d0e615322b40438e ]

When configuring TC-MQPRIO offload, only turn off netdev carrier and don't bring physical link down in hardware. Otherwise, when the physical link is brought up again after configuration, it gets re-trained and stalls ongoing traffic.

Also, when firmware is no longer accessible or crashed, avoid sending FLOWC and waiting for reply that will never come.

Fix following hung_task_timeout_secs trace seen in these cases.

INFO: task tc:20807 blocked for more than 122 seconds. Tainted: G S 5.13.0-rc3+ #122 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:tc state:D stack:14768 pid:20807 ppid: 19366 flags:0x00000000 Call Trace: __schedule+0x27b/0x6a0 schedule+0x37/0xa0 schedule_preempt_disabled+0x5/0x10 __mutex_lock.isra.14+0x2a0/0x4a0 ? netlink_lookup+0x120/0x1a0 ? rtnl_fill_ifinfo+0x10f0/0x10f0 __netlink_dump_start+0x70/0x250 rtnetlink_rcv_msg+0x28b/0x380 ? rtnl_fill_ifinfo+0x10f0/0x10f0 ? rtnl_calcit.isra.42+0x120/0x120 netlink_rcv_skb+0x4b/0xf0 netlink_unicast+0x1a0/0x280 netlink_sendmsg+0x216/0x440 sock_sendmsg+0x56/0x60 __sys_sendto+0xe9/0x150 ? handle_mm_fault+0x6d/0x1b0 ? do_user_addr_fault+0x1c5/0x620 __x64_sys_sendto+0x1f/0x30 do_syscall_64+0x3c/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f7f73218321 RSP: 002b:00007ffd19626208 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 000055b7c0a8b240 RCX: 00007f7f73218321 RDX: 0000000000000028 RSI: 00007ffd19626210 RDI: 0000000000000003 RBP: 000055b7c08680ff R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000055b7c085f5f6 R13: 000055b7c085f60a R14: 00007ffd19636470 R15: 00007ffd196262a0

Fixes: b1396c2bd675 ("cxgb4: parse and configure TC-MQPRIO offload") Signed-off-by: Rahul Lakkireddy rahul.lakkireddy@chelsio.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 2 -- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 4 ++-- drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c | 9 ++++++--- drivers/net/ethernet/chelsio/cxgb4/sge.c | 6 ++++++ 4 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 314f8d806723..9058f09f921e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -2177,8 +2177,6 @@ int cxgb4_update_mac_filt(struct port_info *pi, unsigned int viid, bool persistent, u8 *smt_idx); int cxgb4_get_msix_idx_from_bmap(struct adapter *adap); void cxgb4_free_msix_idx_in_bmap(struct adapter *adap, u32 msix_idx); -int cxgb_open(struct net_device *dev); -int cxgb_close(struct net_device *dev); void cxgb4_enable_rx(struct adapter *adap, struct sge_rspq *q); void cxgb4_quiesce_rx(struct sge_rspq *q); int cxgb4_port_mirror_alloc(struct net_device *dev); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 421bd9b88028..1f601de02e70 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2834,7 +2834,7 @@ static void cxgb_down(struct adapter *adapter) /* * net_device operations */ -int cxgb_open(struct net_device *dev) +static int cxgb_open(struct net_device *dev) { struct port_info *pi = netdev_priv(dev); struct adapter *adapter = pi->adapter; @@ -2882,7 +2882,7 @@ out_unlock: return err; }

-int cxgb_close(struct net_device *dev) +static int cxgb_close(struct net_device *dev) { struct port_info *pi = netdev_priv(dev); struct adapter *adapter = pi->adapter; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c index 6c259de96f96..338b04f339b3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c @@ -589,7 +589,8 @@ int cxgb4_setup_tc_mqprio(struct net_device *dev, * down before configuring tc params. */ if (netif_running(dev)) { - cxgb_close(dev); + netif_tx_stop_all_queues(dev); + netif_carrier_off(dev); needs_bring_up = true; }

@@ -615,8 +616,10 @@ int cxgb4_setup_tc_mqprio(struct net_device *dev, }

out: - if (needs_bring_up) - cxgb_open(dev); + if (needs_bring_up) { + netif_tx_start_all_queues(dev); + netif_carrier_on(dev); + }

mutex_unlock(&adap->tc_mqprio->mqprio_mutex); return ret; diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 1e5f2edb70cf..6a099cb34b12 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2556,6 +2556,12 @@ int cxgb4_ethofld_send_flowc(struct net_device *dev, u32 eotid, u32 tc) if (!eosw_txq) return -ENOMEM;

+ if (!(adap->flags & CXGB4_FW_OK)) { + /* Don't stall caller when access to FW is lost */ + complete(&eosw_txq->completion); + return -EIO; + } + skb = alloc_skb(len, GFP_KERNEL); if (!skb) return -ENOMEM;

From: Magnus Karlsson magnus.karlsson@intel.com

[ Upstream commit f6c10b48f8c8da44adaff730d8e700b6272add2b ]

Add missing exception tracing to XDP when a number of different errors can occur. The support was only partial. Several errors where not logged which would confuse the user quite a lot not knowing where and why the packets disappeared.

Fixes: 74608d17fe29 ("i40e: add support for XDP_TX action") Fixes: 0a714186d3c0 ("i40e: add AF_XDP zero-copy Rx support") Reported-by: Jesper Dangaard Brouer brouer@redhat.com Signed-off-by: Magnus Karlsson magnus.karlsson@intel.com Tested-by: Kiran Bhandare kiranx.bhandare@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 7 ++++++- drivers/net/ethernet/intel/i40e/i40e_xsk.c | 8 ++++++-- 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 70b515049540..c358d9049881 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2313,15 +2313,20 @@ static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp) case XDP_TX: xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index]; result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring); + if (result == I40E_XDP_CONSUMED) + goto out_failure; break; case XDP_REDIRECT: err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED; + if (err) + goto out_failure; + result = I40E_XDP_REDIR; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 3af72dc08539..5b39c457bd77 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -162,9 +162,10 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)

if (likely(act == XDP_REDIRECT)) { err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED; + if (err) + goto out_failure; rcu_read_unlock(); - return result; + return I40E_XDP_REDIR; }

switch (act) { @@ -173,11 +174,14 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) case XDP_TX: xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index]; result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring); + if (result == I40E_XDP_CONSUMED) + goto out_failure; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; /* handle aborts by dropping packet */ case XDP_DROP:

From: Magnus Karlsson magnus.karlsson@intel.com

[ Upstream commit 89d65df024c59988291f643b4e45d1528c51aef9 ]

Add missing exception tracing to XDP when a number of different errors can occur. The support was only partial. Several errors where not logged which would confuse the user quite a lot not knowing where and why the packets disappeared.

Fixes: efc2214b6047 ("ice: Add support for XDP") Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Reported-by: Jesper Dangaard Brouer brouer@redhat.com Signed-off-by: Magnus Karlsson magnus.karlsson@intel.com Tested-by: Kiran Bhandare kiranx.bhandare@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ice/ice_txrx.c | 12 +++++++++--- drivers/net/ethernet/intel/ice/ice_xsk.c | 8 ++++++-- 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 44b6849ec008..113e53efffd7 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -523,7 +523,7 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct ice_ring *xdp_ring; - int err; + int err, result; u32 act;

act = bpf_prog_run_xdp(xdp_prog, xdp); @@ -532,14 +532,20 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp, return ICE_XDP_PASS; case XDP_TX: xdp_ring = rx_ring->vsi->xdp_rings[smp_processor_id()]; - return ice_xmit_xdp_buff(xdp, xdp_ring); + result = ice_xmit_xdp_buff(xdp, xdp_ring); + if (result == ICE_XDP_CONSUMED) + goto out_failure; + return result; case XDP_REDIRECT: err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - return !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED; + if (err) + goto out_failure; + return ICE_XDP_REDIR; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_DROP: diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index adb2f12bcb87..f1d4240e57df 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -479,9 +479,10 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)

if (likely(act == XDP_REDIRECT)) { err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED; + if (err) + goto out_failure; rcu_read_unlock(); - return result; + return ICE_XDP_REDIR; }

switch (act) { @@ -490,11 +491,14 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) case XDP_TX: xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->q_index]; result = ice_xmit_xdp_buff(xdp, xdp_ring); + if (result == ICE_XDP_CONSUMED) + goto out_failure; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_DROP:

From: Magnus Karlsson magnus.karlsson@intel.com

[ Upstream commit 8281356b1cab1cccc71412eb4cf28b99d6bb2c19 ]

Add missing exception tracing to XDP when a number of different errors can occur. The support was only partial. Several errors where not logged which would confuse the user quite a lot not knowing where and why the packets disappeared.

Fixes: 33fdc82f0883 ("ixgbe: add support for XDP_TX action") Fixes: d0bcacd0a130 ("ixgbe: add AF_XDP zero-copy Rx support") Reported-by: Jesper Dangaard Brouer brouer@redhat.com Signed-off-by: Magnus Karlsson magnus.karlsson@intel.com Tested-by: Vishakha Jambekar vishakha.jambekar@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 16 ++++++++-------- drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c | 14 ++++++++------ 2 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index cffb95f8f632..c194158a421c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2213,23 +2213,23 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, break; case XDP_TX: xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) { - result = IXGBE_XDP_CONSUMED; - break; - } + if (unlikely(!xdpf)) + goto out_failure; result = ixgbe_xmit_xdp_ring(adapter, xdpf); + if (result == IXGBE_XDP_CONSUMED) + goto out_failure; break; case XDP_REDIRECT: err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); - if (!err) - result = IXGBE_XDP_REDIR; - else - result = IXGBE_XDP_CONSUMED; + if (err) + goto out_failure; + result = IXGBE_XDP_REDIR; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 91ad5b902673..f72d2978263b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -106,9 +106,10 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,

if (likely(act == XDP_REDIRECT)) { err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED; + if (err) + goto out_failure; rcu_read_unlock(); - return result; + return IXGBE_XDP_REDIR; }

switch (act) { @@ -116,16 +117,17 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, break; case XDP_TX: xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) { - result = IXGBE_XDP_CONSUMED; - break; - } + if (unlikely(!xdpf)) + goto out_failure; result = ixgbe_xmit_xdp_ring(adapter, xdpf); + if (result == IXGBE_XDP_CONSUMED) + goto out_failure; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; /* handle aborts by dropping packet */ case XDP_DROP:

From: Jens Wiklander jens.wiklander@linaro.org

[ Upstream commit 673c7aa2436bfc857b92417f3e590a297c586dde ]

Prior to this patch optee_open_session() was making assumptions about the internal format of uuid_t by casting a memory location in a parameter struct to uuid_t *. Fix this using export_uuid() to get a well defined binary representation and also add an octets field in struct optee_msg_param in order to avoid casting.

Fixes: c5b4312bea5d ("tee: optee: Add support for session login client UUID generation") Suggested-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Jens Wiklander jens.wiklander@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/tee/optee/call.c | 6 ++++-- drivers/tee/optee/optee_msg.h | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/tee/optee/call.c b/drivers/tee/optee/call.c index 7a77e375b503..6b52f0c526ba 100644 --- a/drivers/tee/optee/call.c +++ b/drivers/tee/optee/call.c @@ -216,6 +216,7 @@ int optee_open_session(struct tee_context *ctx, struct optee_msg_arg *msg_arg; phys_addr_t msg_parg; struct optee_session *sess = NULL; + uuid_t client_uuid;

/* +2 for the meta parameters added below */ shm = get_msg_arg(ctx, arg->num_params + 2, &msg_arg, &msg_parg); @@ -236,10 +237,11 @@ int optee_open_session(struct tee_context *ctx, memcpy(&msg_arg->params[0].u.value, arg->uuid, sizeof(arg->uuid)); msg_arg->params[1].u.value.c = arg->clnt_login;

- rc = tee_session_calc_client_uuid((uuid_t *)&msg_arg->params[1].u.value, - arg->clnt_login, arg->clnt_uuid); + rc = tee_session_calc_client_uuid(&client_uuid, arg->clnt_login, + arg->clnt_uuid); if (rc) goto out; + export_uuid(msg_arg->params[1].u.octets, &client_uuid);

rc = optee_to_msg_param(msg_arg->params + 2, arg->num_params, param); if (rc) diff --git a/drivers/tee/optee/optee_msg.h b/drivers/tee/optee/optee_msg.h index 81ff593ac4ec..e3d72d09c484 100644 --- a/drivers/tee/optee/optee_msg.h +++ b/drivers/tee/optee/optee_msg.h @@ -9,7 +9,7 @@ #include <linux/types.h>

/* - * This file defines the OP-TEE message protocol used to communicate + * This file defines the OP-TEE message protocol (ABI) used to communicate * with an instance of OP-TEE running in secure world. * * This file is divided into two sections. @@ -144,9 +144,10 @@ struct optee_msg_param_value { * @tmem: parameter by temporary memory reference * @rmem: parameter by registered memory reference * @value: parameter by opaque value + * @octets: parameter by octet string * * @attr & OPTEE_MSG_ATTR_TYPE_MASK indicates if tmem, rmem or value is used in - * the union. OPTEE_MSG_ATTR_TYPE_VALUE_* indicates value, + * the union. OPTEE_MSG_ATTR_TYPE_VALUE_* indicates value or octets, * OPTEE_MSG_ATTR_TYPE_TMEM_* indicates @tmem and * OPTEE_MSG_ATTR_TYPE_RMEM_* indicates @rmem, * OPTEE_MSG_ATTR_TYPE_NONE indicates that none of the members are used. @@ -157,6 +158,7 @@ struct optee_msg_param { struct optee_msg_param_tmem tmem; struct optee_msg_param_rmem rmem; struct optee_msg_param_value value; + u8 octets[24]; } u; };

From: Michael Walle michael@walle.cc

[ Upstream commit dabea675faf16e8682aa478ff3ce65dd775620bc ]

While enabling EDAC support for the LS1028A it was discovered that the memory node has a wrong endianness setting as well as a wrong interrupt assignment. Fix both.

This was tested on a sl28 board. To force ECC errors, you can use the error injection supported by the controller in hardware (with CONFIG_EDAC_DEBUG enabled):

# enable error injection $ echo 0x100 > /sys/devices/system/edac/mc/mc0/inject_ctrl # flip lowest bit of the data $ echo 0x1 > /sys/devices/system/edac/mc/mc0/inject_data_lo

Fixes: 8897f3255c9c ("arm64: dts: Add support for NXP LS1028A SoC") Signed-off-by: Michael Walle michael@walle.cc Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index 262fbad8f0ec..1b264e5e947a 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -201,8 +201,8 @@ ddr: memory-controller@1080000 { compatible = "fsl,qoriq-memory-controller"; reg = <0x0 0x1080000 0x0 0x1000>; - interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>; - big-endian; + interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>; + little-endian; };

dcfg: syscon@1e00000 {

From: Lucas Stach l.stach@pengutronix.de

[ Upstream commit ac0cbf9d13dccfd09bebc2f8f5697b6d3ffe27c4 ]

As this is a fixed regulator on the board there was no harm in the wrong voltage being specified, apart from a confusing reporting to userspace.

Fixes: 4a13b3bec3b4 ("arm64: dts: imx: add Zii Ultra board support") Signed-off-by: Lucas Stach l.stach@pengutronix.de Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi index 1e5d34e81ab7..a08a568c31d9 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi @@ -45,8 +45,8 @@ reg_12p0_main: regulator-12p0-main { compatible = "regulator-fixed"; regulator-name = "12V_MAIN"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; + regulator-min-microvolt = <12000000>; + regulator-max-microvolt = <12000000>; regulator-always-on; };

From: Michael Walle michael@walle.cc

[ Upstream commit 52387bb9a4a75b88887383cb91d3995ae6f4044a ]

During hardware validation it was noticed that the clock isn't continuously enabled when there is no link. This is because the 125MHz clock is derived from the internal PLL which seems to go into some kind of power-down mode every once in a while. The LS1028A expects a contiuous clock. Thus enable the PLL all the time.

Also, the RGMII pad voltage is wrong, it was configured to 2.5V (that is the VDDH regulator). The correct voltage is 1.8V, i.e. the VDDIO regulator.

This fix is for the freescale/fsl-ls1028a-kontron-sl28-var1.dts.

Fixes: 642856097c18 ("arm64: dts: freescale: sl28: add variant 1") Signed-off-by: Michael Walle michael@walle.cc Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- .../arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var1.dts | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var1.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var1.dts index 6c309b97587d..e8d31279b7a3 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var1.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var1.dts @@ -46,7 +46,8 @@ eee-broken-100tx; qca,clk-out-frequency = <125000000>; qca,clk-out-strength = <AR803X_STRENGTH_FULL>; - vddio-supply = <&vddh>; + qca,keep-pll-enabled; + vddio-supply = <&vddio>;

vddio: vddio-regulator { regulator-name = "VDDIO";

From: Fabio Estevam festevam@gmail.com

[ Upstream commit 0e2fa4959c4f44815ce33e46e4054eeb0f346053 ]

According to Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml, the correct name of the property is 'fsl,tuning-step'.

Fix it accordingly.

Signed-off-by: Fabio Estevam festevam@gmail.com Fixes: f13f571ac8a1 ("ARM: dts: imx7d-pico: Extend peripherals support") Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/imx7d-pico.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/boot/dts/imx7d-pico.dtsi b/arch/arm/boot/dts/imx7d-pico.dtsi index e57da0d32b98..e519897fae08 100644 --- a/arch/arm/boot/dts/imx7d-pico.dtsi +++ b/arch/arm/boot/dts/imx7d-pico.dtsi @@ -351,7 +351,7 @@ pinctrl-2 = <&pinctrl_usdhc1_200mhz>; cd-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>; bus-width = <4>; - tuning-step = <2>; + fsl,tuning-step = <2>; vmmc-supply = <&reg_3p3v>; wakeup-source; no-1-8-v;

From: Tony Lindgren tony@atomide.com

[ Upstream commit c8692ad416dcc420ce1b403596a425c8f4c2720b ]

Looks like the swsup_sidle_act quirk handling is unreliable for serial ports. The serial ports just eventually stop idling until woken up and re-idled again. As the serial port not idling blocks any deeper SoC idle states, it's adds an annoying random flakeyness for power management.

Let's just switch to swsup_sidle quirk instead like we already do for omap3 uarts. This means we manually idle the port instead of trying to use the hardware autoidle features when not in use.

For more details on why the serial ports have been using swsup_idle_act, see commit 66dde54e978a ("ARM: OMAP2+: hwmod-data: UART IP needs software control to manage sidle modes"). It seems that the swsup_idle_act quirk handling is not enough though, and for example the TI Android kernel changed to using swsup_sidle with commit 77c34c84e1e0 ("OMAP4: HWMOD: UART1: disable smart-idle.").

Fixes: b4a9a7a38917 ("bus: ti-sysc: Handle swsup idle mode quirks") Cc: Carl Philipp Klemm philipp@uvos.xyz Cc: Ivan Jelincic parazyd@dyne.org Cc: Merlijn Wajer merlijn@wizzup.org Cc: Pavel Machek pavel@ucw.cz Cc: Sebastian Reichel sre@kernel.org Cc: Sicelo A. Mhlongo absicsz@gmail.com Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/bus/ti-sysc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 49c47b939f21..30e9b700273e 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1454,9 +1454,9 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), /* Uarts on omap4 and later */ SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x50411e03, 0xffff00ff, - SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x47422e03, 0xffffffff, - SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE),

/* Quirks that need to be set based on the module address */ SYSC_QUIRK("mcpdm", 0x40132000, 0, 0x10, -ENODEV, 0x50000800, 0xffffffff,

From: Hoang Le hoang.h.le@dektech.com.au

[ Upstream commit b83e214b2e04204f1fc674574362061492c37245 ]

Add extack error messages for -EINVAL errors when enabling bearer, getting/setting properties for a media/bearer

Acked-by: Jon Maloy jmaloy@redhat.com Signed-off-by: Hoang Le hoang.h.le@dektech.com.au Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/tipc/bearer.c | 50 +++++++++++++++++++++++++++++++++++++---------- 1 file changed, 40 insertions(+), 10 deletions(-)

diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index a4389ef08a98..1090f21fcfac 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -243,7 +243,8 @@ void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest) */ static int tipc_enable_bearer(struct net *net, const char *name, u32 disc_domain, u32 prio, - struct nlattr *attr[]) + struct nlattr *attr[], + struct netlink_ext_ack *extack) { struct tipc_net *tn = tipc_net(net); struct tipc_bearer_names b_names; @@ -257,17 +258,20 @@ static int tipc_enable_bearer(struct net *net, const char *name,

if (!bearer_name_validate(name, &b_names)) { errstr = "illegal name"; + NL_SET_ERR_MSG(extack, "Illegal name"); goto rejected; }

if (prio > TIPC_MAX_LINK_PRI && prio != TIPC_MEDIA_LINK_PRI) { errstr = "illegal priority"; + NL_SET_ERR_MSG(extack, "Illegal priority"); goto rejected; }

m = tipc_media_find(b_names.media_name); if (!m) { errstr = "media not registered"; + NL_SET_ERR_MSG(extack, "Media not registered"); goto rejected; }

@@ -281,6 +285,7 @@ static int tipc_enable_bearer(struct net *net, const char *name, break; if (!strcmp(name, b->name)) { errstr = "already enabled"; + NL_SET_ERR_MSG(extack, "Already enabled"); goto rejected; } bearer_id++; @@ -292,6 +297,7 @@ static int tipc_enable_bearer(struct net *net, const char *name, name, prio); if (prio == TIPC_MIN_LINK_PRI) { errstr = "cannot adjust to lower"; + NL_SET_ERR_MSG(extack, "Cannot adjust to lower"); goto rejected; } pr_warn("Bearer <%s>: trying with adjusted priority\n", name); @@ -302,6 +308,7 @@ static int tipc_enable_bearer(struct net *net, const char *name,

if (bearer_id >= MAX_BEARERS) { errstr = "max 3 bearers permitted"; + NL_SET_ERR_MSG(extack, "Max 3 bearers permitted"); goto rejected; }

@@ -315,6 +322,7 @@ static int tipc_enable_bearer(struct net *net, const char *name, if (res) { kfree(b); errstr = "failed to enable media"; + NL_SET_ERR_MSG(extack, "Failed to enable media"); goto rejected; }

@@ -331,6 +339,7 @@ static int tipc_enable_bearer(struct net *net, const char *name, if (res) { bearer_disable(net, b); errstr = "failed to create discoverer"; + NL_SET_ERR_MSG(extack, "Failed to create discoverer"); goto rejected; }

@@ -909,6 +918,7 @@ int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info) bearer = tipc_bearer_find(net, name); if (!bearer) { err = -EINVAL; + NL_SET_ERR_MSG(info->extack, "Bearer not found"); goto err_out; }

@@ -948,8 +958,10 @@ int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) name = nla_data(attrs[TIPC_NLA_BEARER_NAME]);

bearer = tipc_bearer_find(net, name); - if (!bearer) + if (!bearer) { + NL_SET_ERR_MSG(info->extack, "Bearer not found"); return -EINVAL; + }

bearer_disable(net, bearer);

@@ -1007,7 +1019,8 @@ int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); }

- return tipc_enable_bearer(net, bearer, domain, prio, attrs); + return tipc_enable_bearer(net, bearer, domain, prio, attrs, + info->extack); }

int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) @@ -1046,6 +1059,7 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) b = tipc_bearer_find(net, name); if (!b) { rtnl_unlock(); + NL_SET_ERR_MSG(info->extack, "Bearer not found"); return -EINVAL; }

@@ -1086,8 +1100,10 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) name = nla_data(attrs[TIPC_NLA_BEARER_NAME]);

b = tipc_bearer_find(net, name); - if (!b) + if (!b) { + NL_SET_ERR_MSG(info->extack, "Bearer not found"); return -EINVAL; + }

if (attrs[TIPC_NLA_BEARER_PROP]) { struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; @@ -1106,12 +1122,18 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) if (props[TIPC_NLA_PROP_WIN]) b->max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); if (props[TIPC_NLA_PROP_MTU]) { - if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) + if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) { + NL_SET_ERR_MSG(info->extack, + "MTU property is unsupported"); return -EINVAL; + } #ifdef CONFIG_TIPC_MEDIA_UDP if (tipc_udp_mtu_bad(nla_get_u32 - (props[TIPC_NLA_PROP_MTU]))) + (props[TIPC_NLA_PROP_MTU]))) { + NL_SET_ERR_MSG(info->extack, + "MTU value is out-of-range"); return -EINVAL; + } b->mtu = nla_get_u32(props[TIPC_NLA_PROP_MTU]); tipc_node_apply_property(net, b, TIPC_NLA_PROP_MTU); #endif @@ -1239,6 +1261,7 @@ int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); media = tipc_media_find(name); if (!media) { + NL_SET_ERR_MSG(info->extack, "Media not found"); err = -EINVAL; goto err_out; } @@ -1275,9 +1298,10 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) name = nla_data(attrs[TIPC_NLA_MEDIA_NAME]);

m = tipc_media_find(name); - if (!m) + if (!m) { + NL_SET_ERR_MSG(info->extack, "Media not found"); return -EINVAL; - + } if (attrs[TIPC_NLA_MEDIA_PROP]) { struct nlattr *props[TIPC_NLA_PROP_MAX + 1];

@@ -1293,12 +1317,18 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) if (props[TIPC_NLA_PROP_WIN]) m->max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); if (props[TIPC_NLA_PROP_MTU]) { - if (m->type_id != TIPC_MEDIA_TYPE_UDP) + if (m->type_id != TIPC_MEDIA_TYPE_UDP) { + NL_SET_ERR_MSG(info->extack, + "MTU property is unsupported"); return -EINVAL; + } #ifdef CONFIG_TIPC_MEDIA_UDP if (tipc_udp_mtu_bad(nla_get_u32 - (props[TIPC_NLA_PROP_MTU]))) + (props[TIPC_NLA_PROP_MTU]))) { + NL_SET_ERR_MSG(info->extack, + "MTU value is out-of-range"); return -EINVAL; + } m->mtu = nla_get_u32(props[TIPC_NLA_PROP_MTU]); #endif }

From: Johan Hovold johan@kernel.org

[ Upstream commit e359b4411c2836cf87c8776682d1b594635570de ]

When DMA is enabled the receive handler runs in a threaded handler, but the primary handler up until very recently neither disabled interrupts in the device or used IRQF_ONESHOT. This would lead to a deadlock if an interrupt comes in while the threaded receive handler is running under the port lock.

Commit ad7676812437 ("serial: stm32: fix a deadlock condition with wakeup event") claimed to fix an unrelated deadlock, but unfortunately also disabled interrupts in the threaded handler. While this prevents the deadlock mentioned in the previous paragraph it also defeats the purpose of using a threaded handler in the first place.

Fix this by making the interrupt one-shot and not disabling interrupts in the threaded handler.

Note that (receive) DMA must not be used for a console port as the threaded handler could be interrupted while holding the port lock, something which could lead to a deadlock in case an interrupt handler ends up calling printk.

Fixes: ad7676812437 ("serial: stm32: fix a deadlock condition with wakeup event") Fixes: 3489187204eb ("serial: stm32: adding dma support") Cc: stable@vger.kernel.org # 4.9 Cc: Alexandre TORGUE alexandre.torgue@st.com Cc: Gerald Baeza gerald.baeza@st.com Reviewed-by: Valentin Caronvalentin.caron@foss.st.com Signed-off-by: Johan Hovold johan@kernel.org Link: https://lore.kernel.org/r/20210416140557.25177-3-johan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/tty/serial/stm32-usart.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index 99dfa884cbef..68c6535bbf7f 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -214,14 +214,11 @@ static void stm32_usart_receive_chars(struct uart_port *port, bool threaded) struct tty_port *tport = &port->state->port; struct stm32_port *stm32_port = to_stm32_port(port); const struct stm32_usart_offsets *ofs = &stm32_port->info->ofs; - unsigned long c, flags; + unsigned long c; u32 sr; char flag;

- if (threaded) - spin_lock_irqsave(&port->lock, flags); - else - spin_lock(&port->lock); + spin_lock(&port->lock);

while (stm32_usart_pending_rx(port, &sr, &stm32_port->last_res, threaded)) { @@ -278,10 +275,7 @@ static void stm32_usart_receive_chars(struct uart_port *port, bool threaded) uart_insert_char(port, sr, USART_SR_ORE, c, flag); }

- if (threaded) - spin_unlock_irqrestore(&port->lock, flags); - else - spin_unlock(&port->lock); + spin_unlock(&port->lock);

tty_flip_buffer_push(tport); } @@ -654,7 +648,8 @@ static int stm32_usart_startup(struct uart_port *port)

ret = request_threaded_irq(port->irq, stm32_usart_interrupt, stm32_usart_threaded_interrupt, - IRQF_NO_SUSPEND, name, port); + IRQF_ONESHOT | IRQF_NO_SUSPEND, + name, port); if (ret) return ret;

@@ -1136,6 +1131,13 @@ static int stm32_usart_of_dma_rx_probe(struct stm32_port *stm32port, struct dma_async_tx_descriptor *desc = NULL; int ret;

+ /* + * Using DMA and threaded handler for the console could lead to + * deadlocks. + */ + if (uart_console(port)) + return -ENODEV; + /* Request DMA RX channel */ stm32port->rx_ch = dma_request_slave_channel(dev, "rx"); if (!stm32port->rx_ch) {

From: Ilya Dryomov idryomov@gmail.com

[ Upstream commit 61ca49a9105faefa003b37542cebad8722f8ae22 ]

With the introduction of enforcing mode, setting global_id as soon as we get it in the first MAuth reply will result in EACCES if the connection is reset before we get the second MAuth reply containing an auth ticket -- because on retry we would attempt to reclaim that global_id with no auth ticket at hand.

Neither ceph_auth_client nor ceph_mon_client depend on global_id being set ealy, so just delay the setting until we get and process the second MAuth reply. While at it, complain if the monitor sends a zero global_id or changes our global_id as the session is likely to fail after that.

Cc: stable@vger.kernel.org # needs backporting for < 5.11 Signed-off-by: Ilya Dryomov idryomov@gmail.com Reviewed-by: Sage Weil sage@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/ceph/auth.c | 36 +++++++++++++++++++++++------------- 1 file changed, 23 insertions(+), 13 deletions(-)

diff --git a/net/ceph/auth.c b/net/ceph/auth.c index eb261aa5fe18..de407e8feb97 100644 --- a/net/ceph/auth.c +++ b/net/ceph/auth.c @@ -36,6 +36,20 @@ static int init_protocol(struct ceph_auth_client *ac, int proto) } }

+static void set_global_id(struct ceph_auth_client *ac, u64 global_id) +{ + dout("%s global_id %llu\n", __func__, global_id); + + if (!global_id) + pr_err("got zero global_id\n"); + + if (ac->global_id && global_id != ac->global_id) + pr_err("global_id changed from %llu to %llu\n", ac->global_id, + global_id); + + ac->global_id = global_id; +} + /* * setup, teardown. */ @@ -222,11 +236,6 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac,

payload_end = payload + payload_len;

- if (global_id && ac->global_id != global_id) { - dout(" set global_id %lld -> %lld\n", ac->global_id, global_id); - ac->global_id = global_id; - } - if (ac->negotiating) { /* server does not support our protocols? */ if (!protocol && result < 0) { @@ -253,11 +262,16 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac,

ret = ac->ops->handle_reply(ac, result, payload, payload_end, NULL, NULL, NULL, NULL); - if (ret == -EAGAIN) + if (ret == -EAGAIN) { ret = build_request(ac, true, reply_buf, reply_len); - else if (ret) + goto out; + } else if (ret) { pr_err("auth protocol '%s' mauth authentication failed: %d\n", ceph_auth_proto_name(ac->protocol), result); + goto out; + } + + set_global_id(ac, global_id);

out: mutex_unlock(&ac->mutex); @@ -484,15 +498,11 @@ int ceph_auth_handle_reply_done(struct ceph_auth_client *ac, int ret;

mutex_lock(&ac->mutex); - if (global_id && ac->global_id != global_id) { - dout("%s global_id %llu -> %llu\n", __func__, ac->global_id, - global_id); - ac->global_id = global_id; - } - ret = ac->ops->handle_reply(ac, 0, reply, reply + reply_len, session_key, session_key_len, con_secret, con_secret_len); + if (!ret) + set_global_id(ac, global_id); mutex_unlock(&ac->mutex); return ret; }

From: Simon Ser contact@emersion.fr

[ Upstream commit e0c16eb4b3610298a74ae5504c7f6939b12be991 ]

This error code-path is missing a drm_gem_object_put call. Other error code-paths are fine.

Signed-off-by: Simon Ser contact@emersion.fr Fixes: 1769152ac64b ("drm/amdgpu: Fail fb creation from imported dma-bufs. (v2)") Cc: Alex Deucher alexander.deucher@amd.com Cc: Harry Wentland hwentlan@amd.com Cc: Nicholas Kazlauskas nicholas.kazlauskas@amd.com Cc: Bas Nieuwenhuizen bas@basnieuwenhuizen.nl Reviewed-by: Christian König christian.koenig@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index a2ac44cc2a6d..e80cc2928b58 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -944,6 +944,7 @@ amdgpu_display_user_framebuffer_create(struct drm_device *dev, domains = amdgpu_display_supported_domains(drm_to_adev(dev), bo->flags); if (obj->import_attach && !(domains & AMDGPU_GEM_DOMAIN_GTT)) { drm_dbg_kms(dev, "Cannot create framebuffer from imported dma_buf\n"); + drm_gem_object_put(obj); return ERR_PTR(-EINVAL); }

From: Pavel Begunkov asml.silence@gmail.com

[ Upstream commit 8c3f9cd1603d0e4af6c50ebc6d974ab7bdd03cf4 ]

__io_cqring_fill_event() takes cflags as long to squeeze it into u32 in an CQE, awhile all users pass int or unsigned. Replace it with unsigned int and store it as u32 in struct io_completion to match CQE.

Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- fs/io_uring.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c index 89f4e5e80b9e..5cc76fa9d4a1 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -653,7 +653,7 @@ struct io_unlink { struct io_completion { struct file *file; struct list_head list; - int cflags; + u32 cflags; };

struct io_async_connect { @@ -1476,7 +1476,8 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, return ret; }

-static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags) +static void __io_cqring_fill_event(struct io_kiocb *req, long res, + unsigned int cflags) { struct io_ring_ctx *ctx = req->ctx; struct io_uring_cqe *cqe;

From: Pavel Begunkov asml.silence@gmail.com

[ Upstream commit 447c19f3b5074409c794b350b10306e1da1ef4ba ]

Always remove linked timeout on io_link_timeout_fn() from the master request link list, otherwise we may get use-after-free when first io_link_timeout_fn() puts linked timeout in the fail path, and then will be found and put on master's free.

Cc: stable@vger.kernel.org # 5.10+ Fixes: 90cd7e424969d ("io_uring: track link timeout's master explicitly") Reported-and-tested-by: syzbot+5a864149dd970b546223@syzkaller.appspotmail.com Signed-off-by: Pavel Begunkov asml.silence@gmail.com Link: https://lore.kernel.org/r/69c46bf6ce37fec4fdcd98f0882e18eb07ce693a.162099012... Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- fs/io_uring.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c index dd8b3fac877c..359d1abb089c 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6289,10 +6289,11 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) * We don't expect the list to be empty, that will only happen if we * race with the completion of the linked work. */ - if (prev && req_ref_inc_not_zero(prev)) + if (prev) { io_remove_next_linked(prev); - else - prev = NULL; + if (!req_ref_inc_not_zero(prev)) + prev = NULL; + } spin_unlock_irqrestore(&ctx->completion_lock, flags);

if (prev) {

From: James Zhu James.Zhu@amd.com

[ Upstream commit 23f10a571da5eaa63b7845d16e2f49837e841ab9 ]

Add cancel_delayed_work_sync before set power gating state to avoid race condition issue when power gating.

Signed-off-by: James Zhu James.Zhu@amd.com Reviewed-by: Leo Liu leo.liu@amd.com Acked-by: Christian König christian.koenig@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c index dc947c8ffe21..e6c4a36eaf9a 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c @@ -187,14 +187,14 @@ static int jpeg_v2_5_hw_init(void *handle) static int jpeg_v2_5_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - struct amdgpu_ring *ring; int i;

+ cancel_delayed_work_sync(&adev->vcn.idle_work); + for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { if (adev->jpeg.harvest_config & (1 << i)) continue;

- ring = &adev->jpeg.inst[i].ring_dec; if (adev->jpeg.cur_state != AMD_PG_STATE_GATE && RREG32_SOC15(JPEG, i, mmUVD_JRBC_STATUS)) jpeg_v2_5_set_powergating_state(adev, AMD_PG_STATE_GATE);

From: Lin Ma linma@zju.edu.cn

commit 6a137caec23aeb9e036cdfd8a46dd8a366460e5d upstream.

In the cleanup routine for failed initialization of HCI device, the flush_work(&hdev->rx_work) need to be finished before the flush_work(&hdev->cmd_work). Otherwise, the hci_rx_work() can possibly invoke new cmd_work and cause a bug, like double free, in late processings.

This was assigned CVE-2021-3564.

This patch reorder the flush_work() to fix this bug.

Cc: Marcel Holtmann marcel@holtmann.org Cc: Johan Hedberg johan.hedberg@gmail.com Cc: Luiz Augusto von Dentz luiz.dentz@gmail.com Cc: "David S. Miller" davem@davemloft.net Cc: Jakub Kicinski kuba@kernel.org Cc: linux-bluetooth@vger.kernel.org Cc: netdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Lin Ma linma@zju.edu.cn Signed-off-by: Hao Xiong mart1n@zju.edu.cn Cc: stable stable@vger.kernel.org Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bluetooth/hci_core.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1608,8 +1608,13 @@ setup_failed: } else { /* Init failed, cleanup */ flush_work(&hdev->tx_work); - flush_work(&hdev->cmd_work); + + /* Since hci_rx_work() is possible to awake new cmd_work + * it should be flushed first to avoid unexpected call of + * hci_cmd_work() + */ flush_work(&hdev->rx_work); + flush_work(&hdev->cmd_work);

skb_queue_purge(&hdev->cmd_q); skb_queue_purge(&hdev->rx_q);

From: Jason A. Donenfeld Jason@zx2c4.com

commit cc5060ca0285efe2728bced399a1955a7ce808b2 upstream.

Apparently, various versions of gcc have O3-related miscompiles. Looking at the difference between -O2 and -O3 for gcc 11 doesn't indicate miscompiles, but the difference also doesn't seem so significant for performance that it's worth risking.

Link: https://lore.kernel.org/lkml/CAHk-=wjuoGyxDhAF8SsrTkN0-YfCx7E6jUN3ikC_tn2AKW... Link: https://lore.kernel.org/lkml/CAHmME9otB5Wwxp7H8bR_i2uH2esEMvoBMC8uEXBMH9p0q1... Reported-by: Linus Torvalds torvalds@linux-foundation.org Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Cc: stable@vger.kernel.org Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireguard/Makefile | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/net/wireguard/Makefile +++ b/drivers/net/wireguard/Makefile @@ -1,5 +1,4 @@ -ccflags-y := -O3 -ccflags-y += -D'pr_fmt(fmt)=KBUILD_MODNAME ": " fmt' +ccflags-y := -D'pr_fmt(fmt)=KBUILD_MODNAME ": " fmt' ccflags-$(CONFIG_WIREGUARD_DEBUG) += -DDEBUG wireguard-y := main.o wireguard-y += noise.o

From: Jason A. Donenfeld Jason@zx2c4.com

commit 24b70eeeb4f46c09487f8155239ebfb1f875774a upstream.

Many of the synchronization points are sometimes called under the rtnl lock, which means we should use synchronize_net rather than synchronize_rcu. Under the hood, this expands to using the expedited flavor of function in the event that rtnl is held, in order to not stall other concurrent changes.

This fixes some very, very long delays when removing multiple peers at once, which would cause some operations to take several minutes.

Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Cc: stable@vger.kernel.org Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireguard/peer.c | 6 +++--- drivers/net/wireguard/socket.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-)

--- a/drivers/net/wireguard/peer.c +++ b/drivers/net/wireguard/peer.c @@ -89,7 +89,7 @@ static void peer_make_dead(struct wg_pee /* Mark as dead, so that we don't allow jumping contexts after. */ WRITE_ONCE(peer->is_dead, true);

- /* The caller must now synchronize_rcu() for this to take effect. */ + /* The caller must now synchronize_net() for this to take effect. */ }

static void peer_remove_after_dead(struct wg_peer *peer) @@ -161,7 +161,7 @@ void wg_peer_remove(struct wg_peer *peer lockdep_assert_held(&peer->device->device_update_lock);

peer_make_dead(peer); - synchronize_rcu(); + synchronize_net(); peer_remove_after_dead(peer); }

@@ -179,7 +179,7 @@ void wg_peer_remove_all(struct wg_device peer_make_dead(peer); list_add_tail(&peer->peer_list, &dead_peers); } - synchronize_rcu(); + synchronize_net(); list_for_each_entry_safe(peer, temp, &dead_peers, peer_list) peer_remove_after_dead(peer); } --- a/drivers/net/wireguard/socket.c +++ b/drivers/net/wireguard/socket.c @@ -430,7 +430,7 @@ void wg_socket_reinit(struct wg_device * if (new4) wg->incoming_port = ntohs(inet_sk(new4)->inet_sport); mutex_unlock(&wg->socket_update_lock); - synchronize_rcu(); + synchronize_net(); sock_free(old4); sock_free(old6); }

From: Jason A. Donenfeld Jason@zx2c4.com

commit f8873d11d4121aad35024f9379e431e0c83abead upstream.

Some distros may enable strict rp_filter by default, which will prevent vethc from receiving the packets with an unrouteable reverse path address.

Reported-by: Hangbin Liu liuhangbin@gmail.com Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Cc: stable@vger.kernel.org Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/wireguard/netns.sh | 1 + 1 file changed, 1 insertion(+)

--- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -363,6 +363,7 @@ ip1 -6 rule add table main suppress_pref ip1 -4 route add default dev wg0 table 51820 ip1 -4 rule add not fwmark 51820 table 51820 ip1 -4 rule add table main suppress_prefixlength 0 +n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/vethc/rp_filter' # Flood the pings instead of sending just one, to trigger routing table reference counting bugs. n1 ping -W 1 -c 100 -f 192.168.99.7 n1 ping -W 1 -c 100 -f abab::1111

From: Jason A. Donenfeld Jason@zx2c4.com

commit f634f418c227c912e7ea95a3299efdc9b10e4022 upstream.

Previously, deleting peers would require traversing the entire trie in order to rebalance nodes and safely free them. This meant that removing 1000 peers from a trie with a half million nodes would take an extremely long time, during which we're holding the rtnl lock. Large-scale users were reporting 200ms latencies added to the networking stack as a whole every time their userspace software would queue up significant removals. That's a serious situation.

This commit fixes that by maintaining a double pointer to the parent's bit pointer for each node, and then using the already existing node list belonging to each peer to go directly to the node, fix up its pointers, and free it with RCU. This means removal is O(1) instead of O(n), and we don't use gobs of stack.

The removal algorithm has the same downside as the code that it fixes: it won't collapse needlessly long runs of fillers. We can enhance that in the future if it ever becomes a problem. This commit documents that limitation with a TODO comment in code, a small but meaningful improvement over the prior situation.

Currently the biggest flaw, which the next commit addresses, is that because this increases the node size on 64-bit machines from 60 bytes to 68 bytes. 60 rounds up to 64, but 68 rounds up to 128. So we wind up using twice as much memory per node, because of power-of-two allocations, which is a big bummer. We'll need to figure something out there.

Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Cc: stable@vger.kernel.org Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireguard/allowedips.c | 130 +++++++++++++++---------------------- drivers/net/wireguard/allowedips.h | 9 -- 2 files changed, 56 insertions(+), 83 deletions(-)

--- a/drivers/net/wireguard/allowedips.c +++ b/drivers/net/wireguard/allowedips.c @@ -66,60 +66,6 @@ static void root_remove_peer_lists(struc } }

-static void walk_remove_by_peer(struct allowedips_node __rcu **top, - struct wg_peer *peer, struct mutex *lock) -{ -#define REF(p) rcu_access_pointer(p) -#define DEREF(p) rcu_dereference_protected(*(p), lockdep_is_held(lock)) -#define PUSH(p) ({ \ - WARN_ON(IS_ENABLED(DEBUG) && len >= 128); \ - stack[len++] = p; \ - }) - - struct allowedips_node __rcu **stack[128], **nptr; - struct allowedips_node *node, *prev; - unsigned int len; - - if (unlikely(!peer || !REF(*top))) - return; - - for (prev = NULL, len = 0, PUSH(top); len > 0; prev = node) { - nptr = stack[len - 1]; - node = DEREF(nptr); - if (!node) { - --len; - continue; - } - if (!prev || REF(prev->bit[0]) == node || - REF(prev->bit[1]) == node) { - if (REF(node->bit[0])) - PUSH(&node->bit[0]); - else if (REF(node->bit[1])) - PUSH(&node->bit[1]); - } else if (REF(node->bit[0]) == prev) { - if (REF(node->bit[1])) - PUSH(&node->bit[1]); - } else { - if (rcu_dereference_protected(node->peer, - lockdep_is_held(lock)) == peer) { - RCU_INIT_POINTER(node->peer, NULL); - list_del_init(&node->peer_list); - if (!node->bit[0] || !node->bit[1]) { - rcu_assign_pointer(*nptr, DEREF( - &node->bit[!REF(node->bit[0])])); - kfree_rcu(node, rcu); - node = DEREF(nptr); - } - } - --len; - } - } - -#undef REF -#undef DEREF -#undef PUSH -} - static unsigned int fls128(u64 a, u64 b) { return a ? fls64(a) + 64U : fls64(b); @@ -224,6 +170,7 @@ static int add(struct allowedips_node __ RCU_INIT_POINTER(node->peer, peer); list_add_tail(&node->peer_list, &peer->allowedips_list); copy_and_assign_cidr(node, key, cidr, bits); + rcu_assign_pointer(node->parent_bit, trie); rcu_assign_pointer(*trie, node); return 0; } @@ -243,9 +190,9 @@ static int add(struct allowedips_node __ if (!node) { down = rcu_dereference_protected(*trie, lockdep_is_held(lock)); } else { - down = rcu_dereference_protected(CHOOSE_NODE(node, key), - lockdep_is_held(lock)); + down = rcu_dereference_protected(CHOOSE_NODE(node, key), lockdep_is_held(lock)); if (!down) { + rcu_assign_pointer(newnode->parent_bit, &CHOOSE_NODE(node, key)); rcu_assign_pointer(CHOOSE_NODE(node, key), newnode); return 0; } @@ -254,29 +201,37 @@ static int add(struct allowedips_node __ parent = node;

if (newnode->cidr == cidr) { + rcu_assign_pointer(down->parent_bit, &CHOOSE_NODE(newnode, down->bits)); rcu_assign_pointer(CHOOSE_NODE(newnode, down->bits), down); - if (!parent) + if (!parent) { + rcu_assign_pointer(newnode->parent_bit, trie); rcu_assign_pointer(*trie, newnode); - else - rcu_assign_pointer(CHOOSE_NODE(parent, newnode->bits), - newnode); - } else { - node = kzalloc(sizeof(*node), GFP_KERNEL); - if (unlikely(!node)) { - list_del(&newnode->peer_list); - kfree(newnode); - return -ENOMEM; + } else { + rcu_assign_pointer(newnode->parent_bit, &CHOOSE_NODE(parent, newnode->bits)); + rcu_assign_pointer(CHOOSE_NODE(parent, newnode->bits), newnode); } - INIT_LIST_HEAD(&node->peer_list); - copy_and_assign_cidr(node, newnode->bits, cidr, bits); + return 0; + } + + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (unlikely(!node)) { + list_del(&newnode->peer_list); + kfree(newnode); + return -ENOMEM; + } + INIT_LIST_HEAD(&node->peer_list); + copy_and_assign_cidr(node, newnode->bits, cidr, bits);

- rcu_assign_pointer(CHOOSE_NODE(node, down->bits), down); - rcu_assign_pointer(CHOOSE_NODE(node, newnode->bits), newnode); - if (!parent) - rcu_assign_pointer(*trie, node); - else - rcu_assign_pointer(CHOOSE_NODE(parent, node->bits), - node); + rcu_assign_pointer(down->parent_bit, &CHOOSE_NODE(node, down->bits)); + rcu_assign_pointer(CHOOSE_NODE(node, down->bits), down); + rcu_assign_pointer(newnode->parent_bit, &CHOOSE_NODE(node, newnode->bits)); + rcu_assign_pointer(CHOOSE_NODE(node, newnode->bits), newnode); + if (!parent) { + rcu_assign_pointer(node->parent_bit, trie); + rcu_assign_pointer(*trie, node); + } else { + rcu_assign_pointer(node->parent_bit, &CHOOSE_NODE(parent, node->bits)); + rcu_assign_pointer(CHOOSE_NODE(parent, node->bits), node); } return 0; } @@ -335,9 +290,30 @@ int wg_allowedips_insert_v6(struct allow void wg_allowedips_remove_by_peer(struct allowedips *table, struct wg_peer *peer, struct mutex *lock) { + struct allowedips_node *node, *child, *tmp; + + if (list_empty(&peer->allowedips_list)) + return; ++table->seq; - walk_remove_by_peer(&table->root4, peer, lock); - walk_remove_by_peer(&table->root6, peer, lock); + list_for_each_entry_safe(node, tmp, &peer->allowedips_list, peer_list) { + list_del_init(&node->peer_list); + RCU_INIT_POINTER(node->peer, NULL); + if (node->bit[0] && node->bit[1]) + continue; + child = rcu_dereference_protected( + node->bit[!rcu_access_pointer(node->bit[0])], + lockdep_is_held(lock)); + if (child) + child->parent_bit = node->parent_bit; + *rcu_dereference_protected(node->parent_bit, lockdep_is_held(lock)) = child; + kfree_rcu(node, rcu); + + /* TODO: Note that we currently don't walk up and down in order to + * free any potential filler nodes. This means that this function + * doesn't free up as much as it could, which could be revisited + * at some point. + */ + } }

int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr) --- a/drivers/net/wireguard/allowedips.h +++ b/drivers/net/wireguard/allowedips.h @@ -15,14 +15,11 @@ struct wg_peer; struct allowedips_node { struct wg_peer __rcu *peer; struct allowedips_node __rcu *bit[2]; - /* While it may seem scandalous that we waste space for v4, - * we're alloc'ing to the nearest power of 2 anyway, so this - * doesn't actually make a difference. - */ - u8 bits[16] __aligned(__alignof(u64)); u8 cidr, bit_at_a, bit_at_b, bitlen; + u8 bits[16] __aligned(__alignof(u64));

- /* Keep rarely used list at bottom to be beyond cache line. */ + /* Keep rarely used members at bottom to be beyond cache line. */ + struct allowedips_node *__rcu *parent_bit; /* XXX: this puts us at 68->128 bytes instead of 60->64 bytes!! */ union { struct list_head peer_list; struct rcu_head rcu;

From: Jason A. Donenfeld Jason@zx2c4.com

commit bf7b042dc62a31f66d3a41dd4dfc7806f267b307 upstream.

When removing single nodes, it's possible that that node's parent is an empty intermediate node, in which case, it too should be removed. Otherwise the trie fills up and never is fully emptied, leading to gradual memory leaks over time for tries that are modified often. There was originally code to do this, but was removed during refactoring in 2016 and never reworked. Now that we have proper parent pointers from the previous commits, we can implement this properly.

In order to reduce branching and expensive comparisons, we want to keep the double pointer for parent assignment (which lets us easily chain up to the root), but we still need to actually get the parent's base address. So encode the bit number into the last two bits of the pointer, and pack and unpack it as needed. This is a little bit clumsy but is the fastest and less memory wasteful of the compromises. Note that we align the root struct here to a minimum of 4, because it's embedded into a larger struct, and we're relying on having the bottom two bits for our flag, which would only be 16-bit aligned on m68k.

The existing macro-based helpers were a bit unwieldy for adding the bit packing to, so this commit replaces them with safer and clearer ordinary functions.

We add a test to the randomized/fuzzer part of the selftests, to free the randomized tries by-peer, refuzz it, and repeat, until it's supposed to be empty, and then then see if that actually resulted in the whole thing being emptied. That combined with kmemcheck should hopefully make sure this commit is doing what it should. Along the way this resulted in various other cleanups of the tests and fixes for recent graphviz.

Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Cc: stable@vger.kernel.org Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireguard/allowedips.c | 102 ++++++++++------- drivers/net/wireguard/allowedips.h | 4 drivers/net/wireguard/selftest/allowedips.c | 162 +++++++++++++--------------- 3 files changed, 137 insertions(+), 131 deletions(-)

--- a/drivers/net/wireguard/allowedips.c +++ b/drivers/net/wireguard/allowedips.c @@ -30,8 +30,11 @@ static void copy_and_assign_cidr(struct node->bitlen = bits; memcpy(node->bits, src, bits / 8U); } -#define CHOOSE_NODE(parent, key) \ - parent->bit[(key[parent->bit_at_a] >> parent->bit_at_b) & 1] + +static inline u8 choose(struct allowedips_node *node, const u8 *key) +{ + return (key[node->bit_at_a] >> node->bit_at_b) & 1; +}

static void push_rcu(struct allowedips_node **stack, struct allowedips_node __rcu *p, unsigned int *len) @@ -112,7 +115,7 @@ static struct allowedips_node *find_node found = node; if (node->cidr == bits) break; - node = rcu_dereference_bh(CHOOSE_NODE(node, key)); + node = rcu_dereference_bh(node->bit[choose(node, key)]); } return found; } @@ -144,8 +147,7 @@ static bool node_placement(struct allowe u8 cidr, u8 bits, struct allowedips_node **rnode, struct mutex *lock) { - struct allowedips_node *node = rcu_dereference_protected(trie, - lockdep_is_held(lock)); + struct allowedips_node *node = rcu_dereference_protected(trie, lockdep_is_held(lock)); struct allowedips_node *parent = NULL; bool exact = false;

@@ -155,13 +157,24 @@ static bool node_placement(struct allowe exact = true; break; } - node = rcu_dereference_protected(CHOOSE_NODE(parent, key), - lockdep_is_held(lock)); + node = rcu_dereference_protected(parent->bit[choose(parent, key)], lockdep_is_held(lock)); } *rnode = parent; return exact; }

+static inline void connect_node(struct allowedips_node **parent, u8 bit, struct allowedips_node *node) +{ + node->parent_bit_packed = (unsigned long)parent | bit; + rcu_assign_pointer(*parent, node); +} + +static inline void choose_and_connect_node(struct allowedips_node *parent, struct allowedips_node *node) +{ + u8 bit = choose(parent, node->bits); + connect_node(&parent->bit[bit], bit, node); +} + static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, u8 cidr, struct wg_peer *peer, struct mutex *lock) { @@ -177,8 +190,7 @@ static int add(struct allowedips_node __ RCU_INIT_POINTER(node->peer, peer); list_add_tail(&node->peer_list, &peer->allowedips_list); copy_and_assign_cidr(node, key, cidr, bits); - rcu_assign_pointer(node->parent_bit, trie); - rcu_assign_pointer(*trie, node); + connect_node(trie, 2, node); return 0; } if (node_placement(*trie, key, cidr, bits, &node, lock)) { @@ -197,10 +209,10 @@ static int add(struct allowedips_node __ if (!node) { down = rcu_dereference_protected(*trie, lockdep_is_held(lock)); } else { - down = rcu_dereference_protected(CHOOSE_NODE(node, key), lockdep_is_held(lock)); + const u8 bit = choose(node, key); + down = rcu_dereference_protected(node->bit[bit], lockdep_is_held(lock)); if (!down) { - rcu_assign_pointer(newnode->parent_bit, &CHOOSE_NODE(node, key)); - rcu_assign_pointer(CHOOSE_NODE(node, key), newnode); + connect_node(&node->bit[bit], bit, newnode); return 0; } } @@ -208,15 +220,11 @@ static int add(struct allowedips_node __ parent = node;

if (newnode->cidr == cidr) { - rcu_assign_pointer(down->parent_bit, &CHOOSE_NODE(newnode, down->bits)); - rcu_assign_pointer(CHOOSE_NODE(newnode, down->bits), down); - if (!parent) { - rcu_assign_pointer(newnode->parent_bit, trie); - rcu_assign_pointer(*trie, newnode); - } else { - rcu_assign_pointer(newnode->parent_bit, &CHOOSE_NODE(parent, newnode->bits)); - rcu_assign_pointer(CHOOSE_NODE(parent, newnode->bits), newnode); - } + choose_and_connect_node(newnode, down); + if (!parent) + connect_node(trie, 2, newnode); + else + choose_and_connect_node(parent, newnode); return 0; }

@@ -229,17 +237,12 @@ static int add(struct allowedips_node __ INIT_LIST_HEAD(&node->peer_list); copy_and_assign_cidr(node, newnode->bits, cidr, bits);

- rcu_assign_pointer(down->parent_bit, &CHOOSE_NODE(node, down->bits)); - rcu_assign_pointer(CHOOSE_NODE(node, down->bits), down); - rcu_assign_pointer(newnode->parent_bit, &CHOOSE_NODE(node, newnode->bits)); - rcu_assign_pointer(CHOOSE_NODE(node, newnode->bits), newnode); - if (!parent) { - rcu_assign_pointer(node->parent_bit, trie); - rcu_assign_pointer(*trie, node); - } else { - rcu_assign_pointer(node->parent_bit, &CHOOSE_NODE(parent, node->bits)); - rcu_assign_pointer(CHOOSE_NODE(parent, node->bits), node); - } + choose_and_connect_node(node, down); + choose_and_connect_node(node, newnode); + if (!parent) + connect_node(trie, 2, node); + else + choose_and_connect_node(parent, node); return 0; }

@@ -297,7 +300,8 @@ int wg_allowedips_insert_v6(struct allow void wg_allowedips_remove_by_peer(struct allowedips *table, struct wg_peer *peer, struct mutex *lock) { - struct allowedips_node *node, *child, *tmp; + struct allowedips_node *node, *child, **parent_bit, *parent, *tmp; + bool free_parent;

if (list_empty(&peer->allowedips_list)) return; @@ -307,19 +311,29 @@ void wg_allowedips_remove_by_peer(struct RCU_INIT_POINTER(node->peer, NULL); if (node->bit[0] && node->bit[1]) continue; - child = rcu_dereference_protected( - node->bit[!rcu_access_pointer(node->bit[0])], - lockdep_is_held(lock)); + child = rcu_dereference_protected(node->bit[!rcu_access_pointer(node->bit[0])], + lockdep_is_held(lock)); if (child) - child->parent_bit = node->parent_bit; - *rcu_dereference_protected(node->parent_bit, lockdep_is_held(lock)) = child; + child->parent_bit_packed = node->parent_bit_packed; + parent_bit = (struct allowedips_node **)(node->parent_bit_packed & ~3UL); + *parent_bit = child; + parent = (void *)parent_bit - + offsetof(struct allowedips_node, bit[node->parent_bit_packed & 1]); + free_parent = !rcu_access_pointer(node->bit[0]) && + !rcu_access_pointer(node->bit[1]) && + (node->parent_bit_packed & 3) <= 1 && + !rcu_access_pointer(parent->peer); + if (free_parent) + child = rcu_dereference_protected( + parent->bit[!(node->parent_bit_packed & 1)], + lockdep_is_held(lock)); call_rcu(&node->rcu, node_free_rcu); - - /* TODO: Note that we currently don't walk up and down in order to - * free any potential filler nodes. This means that this function - * doesn't free up as much as it could, which could be revisited - * at some point. - */ + if (!free_parent) + continue; + if (child) + child->parent_bit_packed = parent->parent_bit_packed; + *(struct allowedips_node **)(parent->parent_bit_packed & ~3UL) = child; + call_rcu(&parent->rcu, node_free_rcu); } }

--- a/drivers/net/wireguard/allowedips.h +++ b/drivers/net/wireguard/allowedips.h @@ -19,7 +19,7 @@ struct allowedips_node { u8 bits[16] __aligned(__alignof(u64));

/* Keep rarely used members at bottom to be beyond cache line. */ - struct allowedips_node *__rcu *parent_bit; + unsigned long parent_bit_packed; union { struct list_head peer_list; struct rcu_head rcu; @@ -30,7 +30,7 @@ struct allowedips { struct allowedips_node __rcu *root4; struct allowedips_node __rcu *root6; u64 seq; -}; +} __aligned(4); /* We pack the lower 2 bits of &root, but m68k only gives 16-bit alignment. */

void wg_allowedips_init(struct allowedips *table); void wg_allowedips_free(struct allowedips *table, struct mutex *mutex); --- a/drivers/net/wireguard/selftest/allowedips.c +++ b/drivers/net/wireguard/selftest/allowedips.c @@ -19,32 +19,22 @@

#include <linux/siphash.h>

-static __init void swap_endian_and_apply_cidr(u8 *dst, const u8 *src, u8 bits, - u8 cidr) -{ - swap_endian(dst, src, bits); - memset(dst + (cidr + 7) / 8, 0, bits / 8 - (cidr + 7) / 8); - if (cidr) - dst[(cidr + 7) / 8 - 1] &= ~0U << ((8 - (cidr % 8)) % 8); -} - static __init void print_node(struct allowedips_node *node, u8 bits) { char *fmt_connection = KERN_DEBUG "\t"%p/%d" -> "%p/%d";\n"; - char *fmt_declaration = KERN_DEBUG - "\t"%p/%d"[style=%s, color="#%06x"];\n"; + char *fmt_declaration = KERN_DEBUG "\t"%p/%d"[style=%s, color="#%06x"];\n"; + u8 ip1[16], ip2[16], cidr1, cidr2; char *style = "dotted"; - u8 ip1[16], ip2[16]; u32 color = 0;

+ if (node == NULL) + return; if (bits == 32) { fmt_connection = KERN_DEBUG "\t"%pI4/%d" -> "%pI4/%d";\n"; - fmt_declaration = KERN_DEBUG - "\t"%pI4/%d"[style=%s, color="#%06x"];\n"; + fmt_declaration = KERN_DEBUG "\t"%pI4/%d"[style=%s, color="#%06x"];\n"; } else if (bits == 128) { fmt_connection = KERN_DEBUG "\t"%pI6/%d" -> "%pI6/%d";\n"; - fmt_declaration = KERN_DEBUG - "\t"%pI6/%d"[style=%s, color="#%06x"];\n"; + fmt_declaration = KERN_DEBUG "\t"%pI6/%d"[style=%s, color="#%06x"];\n"; } if (node->peer) { hsiphash_key_t key = { { 0 } }; @@ -55,24 +45,20 @@ static __init void print_node(struct all hsiphash_1u32(0xabad1dea, &key) % 200; style = "bold"; } - swap_endian_and_apply_cidr(ip1, node->bits, bits, node->cidr); - printk(fmt_declaration, ip1, node->cidr, style, color); + wg_allowedips_read_node(node, ip1, &cidr1); + printk(fmt_declaration, ip1, cidr1, style, color); if (node->bit[0]) { - swap_endian_and_apply_cidr(ip2, - rcu_dereference_raw(node->bit[0])->bits, bits, - node->cidr); - printk(fmt_connection, ip1, node->cidr, ip2, - rcu_dereference_raw(node->bit[0])->cidr); - print_node(rcu_dereference_raw(node->bit[0]), bits); + wg_allowedips_read_node(rcu_dereference_raw(node->bit[0]), ip2, &cidr2); + printk(fmt_connection, ip1, cidr1, ip2, cidr2); } if (node->bit[1]) { - swap_endian_and_apply_cidr(ip2, - rcu_dereference_raw(node->bit[1])->bits, - bits, node->cidr); - printk(fmt_connection, ip1, node->cidr, ip2, - rcu_dereference_raw(node->bit[1])->cidr); - print_node(rcu_dereference_raw(node->bit[1]), bits); + wg_allowedips_read_node(rcu_dereference_raw(node->bit[1]), ip2, &cidr2); + printk(fmt_connection, ip1, cidr1, ip2, cidr2); } + if (node->bit[0]) + print_node(rcu_dereference_raw(node->bit[0]), bits); + if (node->bit[1]) + print_node(rcu_dereference_raw(node->bit[1]), bits); }

static __init void print_tree(struct allowedips_node __rcu *top, u8 bits) @@ -121,8 +107,8 @@ static __init inline union nf_inet_addr { union nf_inet_addr mask;

- memset(&mask, 0x00, 128 / 8); - memset(&mask, 0xff, cidr / 8); + memset(&mask, 0, sizeof(mask)); + memset(&mask.all, 0xff, cidr / 8); if (cidr % 32) mask.all[cidr / 32] = (__force u32)htonl( (0xFFFFFFFFUL << (32 - (cidr % 32))) & 0xFFFFFFFFUL); @@ -149,42 +135,36 @@ horrible_mask_self(struct horrible_allow }

static __init inline bool -horrible_match_v4(const struct horrible_allowedips_node *node, - struct in_addr *ip) +horrible_match_v4(const struct horrible_allowedips_node *node, struct in_addr *ip) { return (ip->s_addr & node->mask.ip) == node->ip.ip; }

static __init inline bool -horrible_match_v6(const struct horrible_allowedips_node *node, - struct in6_addr *ip) +horrible_match_v6(const struct horrible_allowedips_node *node, struct in6_addr *ip) { - return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) == - node->ip.ip6[0] && - (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) == - node->ip.ip6[1] && - (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) == - node->ip.ip6[2] && + return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) == node->ip.ip6[0] && + (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) == node->ip.ip6[1] && + (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) == node->ip.ip6[2] && (ip->in6_u.u6_addr32[3] & node->mask.ip6[3]) == node->ip.ip6[3]; }

static __init void -horrible_insert_ordered(struct horrible_allowedips *table, - struct horrible_allowedips_node *node) +horrible_insert_ordered(struct horrible_allowedips *table, struct horrible_allowedips_node *node) { struct horrible_allowedips_node *other = NULL, *where = NULL; u8 my_cidr = horrible_mask_to_cidr(node->mask);

hlist_for_each_entry(other, &table->head, table) { - if (!memcmp(&other->mask, &node->mask, - sizeof(union nf_inet_addr)) && - !memcmp(&other->ip, &node->ip, - sizeof(union nf_inet_addr)) && - other->ip_version == node->ip_version) { + if (other->ip_version == node->ip_version && + !memcmp(&other->mask, &node->mask, sizeof(union nf_inet_addr)) && + !memcmp(&other->ip, &node->ip, sizeof(union nf_inet_addr))) { other->value = node->value; kfree(node); return; } + } + hlist_for_each_entry(other, &table->head, table) { where = other; if (horrible_mask_to_cidr(other->mask) <= my_cidr) break; @@ -201,8 +181,7 @@ static __init int horrible_allowedips_insert_v4(struct horrible_allowedips *table, struct in_addr *ip, u8 cidr, void *value) { - struct horrible_allowedips_node *node = kzalloc(sizeof(*node), - GFP_KERNEL); + struct horrible_allowedips_node *node = kzalloc(sizeof(*node), GFP_KERNEL);

if (unlikely(!node)) return -ENOMEM; @@ -219,8 +198,7 @@ static __init int horrible_allowedips_insert_v6(struct horrible_allowedips *table, struct in6_addr *ip, u8 cidr, void *value) { - struct horrible_allowedips_node *node = kzalloc(sizeof(*node), - GFP_KERNEL); + struct horrible_allowedips_node *node = kzalloc(sizeof(*node), GFP_KERNEL);

if (unlikely(!node)) return -ENOMEM; @@ -234,39 +212,43 @@ horrible_allowedips_insert_v6(struct hor }

static __init void * -horrible_allowedips_lookup_v4(struct horrible_allowedips *table, - struct in_addr *ip) +horrible_allowedips_lookup_v4(struct horrible_allowedips *table, struct in_addr *ip) { struct horrible_allowedips_node *node; - void *ret = NULL;

hlist_for_each_entry(node, &table->head, table) { - if (node->ip_version != 4) - continue; - if (horrible_match_v4(node, ip)) { - ret = node->value; - break; - } + if (node->ip_version == 4 && horrible_match_v4(node, ip)) + return node->value; } - return ret; + return NULL; }

static __init void * -horrible_allowedips_lookup_v6(struct horrible_allowedips *table, - struct in6_addr *ip) +horrible_allowedips_lookup_v6(struct horrible_allowedips *table, struct in6_addr *ip) { struct horrible_allowedips_node *node; - void *ret = NULL;

hlist_for_each_entry(node, &table->head, table) { - if (node->ip_version != 6) + if (node->ip_version == 6 && horrible_match_v6(node, ip)) + return node->value; + } + return NULL; +} + + +static __init void +horrible_allowedips_remove_by_value(struct horrible_allowedips *table, void *value) +{ + struct horrible_allowedips_node *node; + struct hlist_node *h; + + hlist_for_each_entry_safe(node, h, &table->head, table) { + if (node->value != value) continue; - if (horrible_match_v6(node, ip)) { - ret = node->value; - break; - } + hlist_del(&node->table); + kfree(node); } - return ret; + }

static __init bool randomized_test(void) @@ -397,23 +379,33 @@ static __init bool randomized_test(void) print_tree(t.root6, 128); }

- for (i = 0; i < NUM_QUERIES; ++i) { - prandom_bytes(ip, 4); - if (lookup(t.root4, 32, ip) != - horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) { - pr_err("allowedips random self-test: FAIL\n"); - goto free; + for (j = 0;; ++j) { + for (i = 0; i < NUM_QUERIES; ++i) { + prandom_bytes(ip, 4); + if (lookup(t.root4, 32, ip) != horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) { + horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip); + pr_err("allowedips random v4 self-test: FAIL\n"); + goto free; + } + prandom_bytes(ip, 16); + if (lookup(t.root6, 128, ip) != horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) { + pr_err("allowedips random v6 self-test: FAIL\n"); + goto free; + } } + if (j >= NUM_PEERS) + break; + mutex_lock(&mutex); + wg_allowedips_remove_by_peer(&t, peers[j], &mutex); + mutex_unlock(&mutex); + horrible_allowedips_remove_by_value(&h, peers[j]); }

- for (i = 0; i < NUM_QUERIES; ++i) { - prandom_bytes(ip, 16); - if (lookup(t.root6, 128, ip) != - horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) { - pr_err("allowedips random self-test: FAIL\n"); - goto free; - } + if (t.root4 || t.root6) { + pr_err("allowedips random self-test removal: FAIL\n"); + goto free; } + ret = true;

free:

From: Pavel Skripkin paskripkin@gmail.com

commit a2805dca5107d5603f4bbc027e81e20d93476e96 upstream.

caif_enroll_dev() can fail in some cases. Ingnoring these cases can lead to memory leak due to not assigning link_support pointer to anywhere.

Fixes: 7c18d2205ea7 ("caif: Restructure how link caif link layer enroll") Cc: stable@vger.kernel.org Signed-off-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/caif/caif_dev.h | 2 +- include/net/caif/cfcnfg.h | 2 +- net/caif/caif_dev.c | 8 +++++--- net/caif/cfcnfg.c | 16 +++++++++++----- 4 files changed, 18 insertions(+), 10 deletions(-)

--- a/include/net/caif/caif_dev.h +++ b/include/net/caif/caif_dev.h @@ -119,7 +119,7 @@ void caif_free_client(struct cflayer *ad * The link_support layer is used to add any Link Layer specific * framing. */ -void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, +int caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, struct cflayer *link_support, int head_room, struct cflayer **layer, int (**rcv_func)( struct sk_buff *, struct net_device *, --- a/include/net/caif/cfcnfg.h +++ b/include/net/caif/cfcnfg.h @@ -62,7 +62,7 @@ void cfcnfg_remove(struct cfcnfg *cfg); * @fcs: Specify if checksum is used in CAIF Framing Layer. * @head_room: Head space needed by link specific protocol. */ -void +int cfcnfg_add_phy_layer(struct cfcnfg *cnfg, struct net_device *dev, struct cflayer *phy_layer, enum cfcnfg_phy_preference pref, --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -308,7 +308,7 @@ static void dev_flowctrl(struct net_devi caifd_put(caifd); }

-void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, +int caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, struct cflayer *link_support, int head_room, struct cflayer **layer, int (**rcv_func)(struct sk_buff *, struct net_device *, @@ -319,11 +319,12 @@ void caif_enroll_dev(struct net_device * enum cfcnfg_phy_preference pref; struct cfcnfg *cfg = get_cfcnfg(dev_net(dev)); struct caif_device_entry_list *caifdevs; + int res;

caifdevs = caif_device_list(dev_net(dev)); caifd = caif_device_alloc(dev); if (!caifd) - return; + return -ENOMEM; *layer = &caifd->layer; spin_lock_init(&caifd->flow_lock);

@@ -344,7 +345,7 @@ void caif_enroll_dev(struct net_device * strlcpy(caifd->layer.name, dev->name, sizeof(caifd->layer.name)); caifd->layer.transmit = transmit; - cfcnfg_add_phy_layer(cfg, + res = cfcnfg_add_phy_layer(cfg, dev, &caifd->layer, pref, @@ -354,6 +355,7 @@ void caif_enroll_dev(struct net_device * mutex_unlock(&caifdevs->lock); if (rcv_func) *rcv_func = receive; + return res; } EXPORT_SYMBOL(caif_enroll_dev);

--- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -450,7 +450,7 @@ unlock: rcu_read_unlock(); }

-void +int cfcnfg_add_phy_layer(struct cfcnfg *cnfg, struct net_device *dev, struct cflayer *phy_layer, enum cfcnfg_phy_preference pref, @@ -459,7 +459,7 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg { struct cflayer *frml; struct cfcnfg_phyinfo *phyinfo = NULL; - int i; + int i, res = 0; u8 phyid;

mutex_lock(&cnfg->lock); @@ -473,12 +473,15 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg goto got_phyid; } pr_warn("Too many CAIF Link Layers (max 6)\n"); + res = -EEXIST; goto out;

got_phyid: phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC); - if (!phyinfo) + if (!phyinfo) { + res = -ENOMEM; goto out_err; + }

phy_layer->id = phyid; phyinfo->pref = pref; @@ -492,8 +495,10 @@ got_phyid:

frml = cffrml_create(phyid, fcs);

- if (!frml) + if (!frml) { + res = -ENOMEM; goto out_err; + } phyinfo->frm_layer = frml; layer_set_up(frml, cnfg->mux);

@@ -511,11 +516,12 @@ got_phyid: list_add_rcu(&phyinfo->node, &cnfg->phys); out: mutex_unlock(&cnfg->lock); - return; + return res;

out_err: kfree(phyinfo); mutex_unlock(&cnfg->lock); + return res; } EXPORT_SYMBOL(cfcnfg_add_phy_layer);

From: Pavel Skripkin paskripkin@gmail.com

commit 7f5d86669fa4d485523ddb1d212e0a2d90bd62bb upstream.

In case of caif_enroll_dev() fail, allocated link_support won't be assigned to the corresponding structure. So simply free allocated pointer in case of error.

Fixes: 7ad65bf68d70 ("caif: Add support for CAIF over CDC NCM USB interface") Cc: stable@vger.kernel.org Signed-off-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/caif/caif_usb.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)

--- a/net/caif/caif_usb.c +++ b/net/caif/caif_usb.c @@ -115,6 +115,11 @@ static struct cflayer *cfusbl_create(int return (struct cflayer *) this; }

+static void cfusbl_release(struct cflayer *layer) +{ + kfree(layer); +} + static struct packet_type caif_usb_type __read_mostly = { .type = cpu_to_be16(ETH_P_802_EX1), }; @@ -127,6 +132,7 @@ static int cfusbl_device_notify(struct n struct cflayer *layer, *link_support; struct usbnet *usbnet; struct usb_device *usbdev; + int res;

/* Check whether we have a NCM device, and find its VID/PID. */ if (!(dev->dev.parent && dev->dev.parent->driver && @@ -169,8 +175,11 @@ static int cfusbl_device_notify(struct n if (dev->num_tx_queues > 1) pr_warn("USB device uses more than one tx queue\n");

- caif_enroll_dev(dev, &common, link_support, CFUSB_MAX_HEADLEN, + res = caif_enroll_dev(dev, &common, link_support, CFUSB_MAX_HEADLEN, &layer, &caif_usb_type.func); + if (res) + goto err; + if (!pack_added) dev_add_pack(&caif_usb_type); pack_added = true; @@ -178,6 +187,9 @@ static int cfusbl_device_notify(struct n strlcpy(layer->name, dev->name, sizeof(layer->name));

return 0; +err: + cfusbl_release(link_support); + return res; }

static struct notifier_block caif_device_notifier = {

From: Johan Hovold johan@kernel.org

commit 4b4f6cecca446abcb686c6e6c451d4f1ec1a7497 upstream.

Commit 9d7b18668956 ("HID: magicmouse: add support for Apple Magic Trackpad 2") added a sanity check for an Apple trackpad but returned success instead of -ENODEV when the check failed. This means that the remove callback will dereference the never-initialised driver data pointer when the driver is later unbound (e.g. on USB disconnect).

Reported-by: syzbot+ee6f6e2e68886ca256a8@syzkaller.appspotmail.com Fixes: 9d7b18668956 ("HID: magicmouse: add support for Apple Magic Trackpad 2") Cc: stable@vger.kernel.org # 4.20 Cc: Claudio Mettler claudio@ponyfleisch.ch Cc: Marek Wyborski marek.wyborski@emwesoft.com Cc: Sean O'Brien seobrien@chromium.org Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hid/hid-magicmouse.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -597,7 +597,7 @@ static int magicmouse_probe(struct hid_d if (id->vendor == USB_VENDOR_ID_APPLE && id->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2 && hdev->type != HID_TYPE_USBMOUSE) - return 0; + return -ENODEV;

msc = devm_kzalloc(&hdev->dev, sizeof(*msc), GFP_KERNEL); if (msc == NULL) {

From: Bob Peterson rpeterso@redhat.com

commit 20265d9a67e40eafd39a8884658ca2e36f05985d upstream.

Before this patch, in the unlikely event that gfs2_glock_dq encountered a withdraw, it would do a wait_on_bit to wait for its journal to be recovered, but it never released the glock's spin_lock, which caused a scheduling-while-atomic error.

This patch unlocks the lockref spin_lock before waiting for recovery.

Fixes: 601ef0d52e96 ("gfs2: Force withdraw to replay journals and wait for it to finish") Cc: stable@vger.kernel.org # v5.7+ Reported-by: Alexander Aring aahringo@redhat.com Signed-off-by: Bob Peterson rpeterso@redhat.com Signed-off-by: Andreas Gruenbacher agruenba@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/gfs2/glock.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1465,9 +1465,11 @@ void gfs2_glock_dq(struct gfs2_holder *g glock_blocked_by_withdraw(gl) && gh->gh_gl != sdp->sd_jinode_gl) { sdp->sd_glock_dqs_held++; + spin_unlock(&gl->gl_lockref.lock); might_sleep(); wait_on_bit(&sdp->sd_flags, SDF_WITHDRAW_RECOVERY, TASK_UNINTERRUPTIBLE); + spin_lock(&gl->gl_lockref.lock); } if (gh->gh_flags & GL_NOCACHE) handle_callback(gl, LM_ST_UNLOCKED, 0, false);

From: Carlos M carlos.marr.pz@gmail.com

commit 901be145a46eb79879367d853194346a549e623d upstream.

For the HP Pavilion 15-CK0xx, with audio subsystem ID 0x103c:0x841c, adding a line in patch_realtek.c to apply the ALC269_FIXUP_HP_MUTE_LED_MIC3 fix activates the mute key LED.

Signed-off-by: Carlos M carlos.marr.pz@gmail.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210531202026.35427-1-carlos.marr.pz@gmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8289,6 +8289,7 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0x103c, 0x82bf, "HP G3 mini", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x82c0, "HP G3 mini premium", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), + SND_PCI_QUIRK(0x103c, 0x841c, "HP Pavilion 15-CK0xx", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x84da, "HP OMEN dc0019-ur", ALC295_FIXUP_HP_OMEN), SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),

From: Michal Vokáč michal.vokac@ysoft.com

commit 0e4a4a08cd78efcaddbc2e4c5ed86b5a5cb8a15e upstream.

The FEC does not have a PHY so it should not have a phy-handle. It is connected to the switch at RGMII level so we need a fixed-link sub-node on both ends.

This was not a problem until the qca8k.c driver was converted to PHYLINK by commit b3591c2a3661 ("net: dsa: qca8k: Switch to PHYLINK instead of PHYLIB"). That commit revealed the FEC configuration was not correct.

Fixes: 87489ec3a77f ("ARM: dts: imx: Add Y Soft IOTA Draco, Hydra and Ursa boards") Cc: stable@vger.kernel.org Signed-off-by: Michal Vokáč michal.vokac@ysoft.com Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/boot/dts/imx6dl-yapp4-common.dtsi | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi +++ b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi @@ -105,9 +105,13 @@ phy-reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; phy-reset-duration = <20>; phy-supply = <&sw2_reg>; - phy-handle = <&ethphy0>; status = "okay";

+ fixed-link { + speed = <1000>; + full-duplex; + }; + mdio { #address-cells = <1>; #size-cells = <0>;

From: Alexey Makhalov amakhalov@vmware.com

commit afd09b617db3786b6ef3dc43e28fe728cfea84df upstream.

Buffer head references must be released before calling kill_bdev(); otherwise the buffer head (and its page referenced by b_data) will not be freed by kill_bdev, and subsequently that bh will be leaked.

If blocksizes differ, sb_set_blocksize() will kill current buffers and page cache by using kill_bdev(). And then super block will be reread again but using correct blocksize this time. sb_set_blocksize() didn't fully free superblock page and buffer head, and being busy, they were not freed and instead leaked.

This can easily be reproduced by calling an infinite loop of:

systemctl start <ext4_on_lvm>.mount, and systemctl stop <ext4_on_lvm>.mount

... since systemd creates a cgroup for each slice which it mounts, and the bh leak get amplified by a dying memory cgroup that also never gets freed, and memory consumption is much more easily noticed.

Fixes: ce40733ce93d ("ext4: Check for return value from sb_set_blocksize") Fixes: ac27a0ec112a ("ext4: initial copy of files from ext3") Link: https://lore.kernel.org/r/20210521075533.95732-1-amakhalov@vmware.com Signed-off-by: Alexey Makhalov amakhalov@vmware.com Signed-off-by: Theodore Ts'o tytso@mit.edu Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/super.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)

--- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4449,14 +4449,20 @@ static int ext4_fill_super(struct super_ }

if (sb->s_blocksize != blocksize) { + /* + * bh must be released before kill_bdev(), otherwise + * it won't be freed and its page also. kill_bdev() + * is called by sb_set_blocksize(). + */ + brelse(bh); /* Validate the filesystem blocksize */ if (!sb_set_blocksize(sb, blocksize)) { ext4_msg(sb, KERN_ERR, "bad block size %d", blocksize); + bh = NULL; goto failed_mount; }

- brelse(bh); logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE; offset = do_div(logical_sb_block, blocksize); bh = ext4_sb_bread_unmovable(sb, logical_sb_block); @@ -5176,8 +5182,9 @@ failed_mount: kfree(get_qf_name(sb, sbi, i)); #endif fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); - ext4_blkdev_remove(sbi); + /* ext4_blkdev_remove() calls kill_bdev(), release bh before it. */ brelse(bh); + ext4_blkdev_remove(sbi); out_fail: sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock);

From: Harshad Shirwadkar harshadshirwadkar@gmail.com

commit a7ba36bc94f20b6c77f16364b9a23f582ea8faac upstream.

Fast commit recovery data on disk may not be aligned. So, when the recovery code reads it, this patch makes sure that fast commit info found on-disk is first memcpy-ed into an aligned variable before accessing it. As a consequence of it, we also remove some macros that could resulted in unaligned accesses.

Cc: stable@kernel.org Fixes: 8016e29f4362 ("ext4: fast commit recovery path") Signed-off-by: Harshad Shirwadkar harshadshirwadkar@gmail.com Link: https://lore.kernel.org/r/20210519215920.2037527-1-harshads@google.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/fast_commit.c | 170 ++++++++++++++++++++++++++------------------------ fs/ext4/fast_commit.h | 19 ----- 2 files changed, 90 insertions(+), 99 deletions(-)

--- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -1288,28 +1288,29 @@ struct dentry_info_args { };

static inline void tl_to_darg(struct dentry_info_args *darg, - struct ext4_fc_tl *tl) + struct ext4_fc_tl *tl, u8 *val) { - struct ext4_fc_dentry_info *fcd; + struct ext4_fc_dentry_info fcd;

- fcd = (struct ext4_fc_dentry_info *)ext4_fc_tag_val(tl); + memcpy(&fcd, val, sizeof(fcd));

- darg->parent_ino = le32_to_cpu(fcd->fc_parent_ino); - darg->ino = le32_to_cpu(fcd->fc_ino); - darg->dname = fcd->fc_dname; - darg->dname_len = ext4_fc_tag_len(tl) - - sizeof(struct ext4_fc_dentry_info); + darg->parent_ino = le32_to_cpu(fcd.fc_parent_ino); + darg->ino = le32_to_cpu(fcd.fc_ino); + darg->dname = val + offsetof(struct ext4_fc_dentry_info, fc_dname); + darg->dname_len = le16_to_cpu(tl->fc_len) - + sizeof(struct ext4_fc_dentry_info); }

/* Unlink replay function */ -static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl) +static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl, + u8 *val) { struct inode *inode, *old_parent; struct qstr entry; struct dentry_info_args darg; int ret = 0;

- tl_to_darg(&darg, tl); + tl_to_darg(&darg, tl, val);

trace_ext4_fc_replay(sb, EXT4_FC_TAG_UNLINK, darg.ino, darg.parent_ino, darg.dname_len); @@ -1399,13 +1400,14 @@ out: }

/* Link replay function */ -static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl) +static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl, + u8 *val) { struct inode *inode; struct dentry_info_args darg; int ret = 0;

- tl_to_darg(&darg, tl); + tl_to_darg(&darg, tl, val); trace_ext4_fc_replay(sb, EXT4_FC_TAG_LINK, darg.ino, darg.parent_ino, darg.dname_len);

@@ -1450,9 +1452,10 @@ static int ext4_fc_record_modified_inode /* * Inode replay function */ -static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl) +static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl, + u8 *val) { - struct ext4_fc_inode *fc_inode; + struct ext4_fc_inode fc_inode; struct ext4_inode *raw_inode; struct ext4_inode *raw_fc_inode; struct inode *inode = NULL; @@ -1460,9 +1463,9 @@ static int ext4_fc_replay_inode(struct s int inode_len, ino, ret, tag = le16_to_cpu(tl->fc_tag); struct ext4_extent_header *eh;

- fc_inode = (struct ext4_fc_inode *)ext4_fc_tag_val(tl); + memcpy(&fc_inode, val, sizeof(fc_inode));

- ino = le32_to_cpu(fc_inode->fc_ino); + ino = le32_to_cpu(fc_inode.fc_ino); trace_ext4_fc_replay(sb, tag, ino, 0, 0);

inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); @@ -1474,12 +1477,13 @@ static int ext4_fc_replay_inode(struct s

ext4_fc_record_modified_inode(sb, ino);

- raw_fc_inode = (struct ext4_inode *)fc_inode->fc_raw_inode; + raw_fc_inode = (struct ext4_inode *) + (val + offsetof(struct ext4_fc_inode, fc_raw_inode)); ret = ext4_get_fc_inode_loc(sb, ino, &iloc); if (ret) goto out;

- inode_len = ext4_fc_tag_len(tl) - sizeof(struct ext4_fc_inode); + inode_len = le16_to_cpu(tl->fc_len) - sizeof(struct ext4_fc_inode); raw_inode = ext4_raw_inode(&iloc);

memcpy(raw_inode, raw_fc_inode, offsetof(struct ext4_inode, i_block)); @@ -1547,14 +1551,15 @@ out: * inode for which we are trying to create a dentry here, should already have * been replayed before we start here. */ -static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl) +static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl, + u8 *val) { int ret = 0; struct inode *inode = NULL; struct inode *dir = NULL; struct dentry_info_args darg;

- tl_to_darg(&darg, tl); + tl_to_darg(&darg, tl, val);

trace_ext4_fc_replay(sb, EXT4_FC_TAG_CREAT, darg.ino, darg.parent_ino, darg.dname_len); @@ -1633,9 +1638,9 @@ static int ext4_fc_record_regions(struct

/* Replay add range tag */ static int ext4_fc_replay_add_range(struct super_block *sb, - struct ext4_fc_tl *tl) + struct ext4_fc_tl *tl, u8 *val) { - struct ext4_fc_add_range *fc_add_ex; + struct ext4_fc_add_range fc_add_ex; struct ext4_extent newex, *ex; struct inode *inode; ext4_lblk_t start, cur; @@ -1645,15 +1650,14 @@ static int ext4_fc_replay_add_range(stru struct ext4_ext_path *path = NULL; int ret;

- fc_add_ex = (struct ext4_fc_add_range *)ext4_fc_tag_val(tl); - ex = (struct ext4_extent *)&fc_add_ex->fc_ex; + memcpy(&fc_add_ex, val, sizeof(fc_add_ex)); + ex = (struct ext4_extent *)&fc_add_ex.fc_ex;

trace_ext4_fc_replay(sb, EXT4_FC_TAG_ADD_RANGE, - le32_to_cpu(fc_add_ex->fc_ino), le32_to_cpu(ex->ee_block), + le32_to_cpu(fc_add_ex.fc_ino), le32_to_cpu(ex->ee_block), ext4_ext_get_actual_len(ex));

- inode = ext4_iget(sb, le32_to_cpu(fc_add_ex->fc_ino), - EXT4_IGET_NORMAL); + inode = ext4_iget(sb, le32_to_cpu(fc_add_ex.fc_ino), EXT4_IGET_NORMAL); if (IS_ERR(inode)) { jbd_debug(1, "Inode not found."); return 0; @@ -1762,32 +1766,33 @@ next:

/* Replay DEL_RANGE tag */ static int -ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl) +ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl, + u8 *val) { struct inode *inode; - struct ext4_fc_del_range *lrange; + struct ext4_fc_del_range lrange; struct ext4_map_blocks map; ext4_lblk_t cur, remaining; int ret;

- lrange = (struct ext4_fc_del_range *)ext4_fc_tag_val(tl); - cur = le32_to_cpu(lrange->fc_lblk); - remaining = le32_to_cpu(lrange->fc_len); + memcpy(&lrange, val, sizeof(lrange)); + cur = le32_to_cpu(lrange.fc_lblk); + remaining = le32_to_cpu(lrange.fc_len);

trace_ext4_fc_replay(sb, EXT4_FC_TAG_DEL_RANGE, - le32_to_cpu(lrange->fc_ino), cur, remaining); + le32_to_cpu(lrange.fc_ino), cur, remaining);

- inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL); + inode = ext4_iget(sb, le32_to_cpu(lrange.fc_ino), EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino)); + jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange.fc_ino)); return 0; }

ret = ext4_fc_record_modified_inode(sb, inode->i_ino);

jbd_debug(1, "DEL_RANGE, inode %ld, lblk %d, len %d\n", - inode->i_ino, le32_to_cpu(lrange->fc_lblk), - le32_to_cpu(lrange->fc_len)); + inode->i_ino, le32_to_cpu(lrange.fc_lblk), + le32_to_cpu(lrange.fc_len)); while (remaining > 0) { map.m_lblk = cur; map.m_len = remaining; @@ -1808,8 +1813,8 @@ ext4_fc_replay_del_range(struct super_bl }

ret = ext4_punch_hole(inode, - le32_to_cpu(lrange->fc_lblk) << sb->s_blocksize_bits, - le32_to_cpu(lrange->fc_len) << sb->s_blocksize_bits); + le32_to_cpu(lrange.fc_lblk) << sb->s_blocksize_bits, + le32_to_cpu(lrange.fc_len) << sb->s_blocksize_bits); if (ret) jbd_debug(1, "ext4_punch_hole returned %d", ret); ext4_ext_replay_shrink_inode(inode, @@ -1925,11 +1930,11 @@ static int ext4_fc_replay_scan(journal_t struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_fc_replay_state *state; int ret = JBD2_FC_REPLAY_CONTINUE; - struct ext4_fc_add_range *ext; - struct ext4_fc_tl *tl; - struct ext4_fc_tail *tail; - __u8 *start, *end; - struct ext4_fc_head *head; + struct ext4_fc_add_range ext; + struct ext4_fc_tl tl; + struct ext4_fc_tail tail; + __u8 *start, *end, *cur, *val; + struct ext4_fc_head head; struct ext4_extent *ex;

state = &sbi->s_fc_replay_state; @@ -1956,15 +1961,17 @@ static int ext4_fc_replay_scan(journal_t }

state->fc_replay_expected_off++; - fc_for_each_tl(start, end, tl) { + for (cur = start; cur < end; cur = cur + sizeof(tl) + le16_to_cpu(tl.fc_len)) { + memcpy(&tl, cur, sizeof(tl)); + val = cur + sizeof(tl); jbd_debug(3, "Scan phase, tag:%s, blk %lld\n", - tag2str(le16_to_cpu(tl->fc_tag)), bh->b_blocknr); - switch (le16_to_cpu(tl->fc_tag)) { + tag2str(le16_to_cpu(tl.fc_tag)), bh->b_blocknr); + switch (le16_to_cpu(tl.fc_tag)) { case EXT4_FC_TAG_ADD_RANGE: - ext = (struct ext4_fc_add_range *)ext4_fc_tag_val(tl); - ex = (struct ext4_extent *)&ext->fc_ex; + memcpy(&ext, val, sizeof(ext)); + ex = (struct ext4_extent *)&ext.fc_ex; ret = ext4_fc_record_regions(sb, - le32_to_cpu(ext->fc_ino), + le32_to_cpu(ext.fc_ino), le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex), ext4_ext_get_actual_len(ex)); if (ret < 0) @@ -1978,18 +1985,18 @@ static int ext4_fc_replay_scan(journal_t case EXT4_FC_TAG_INODE: case EXT4_FC_TAG_PAD: state->fc_cur_tag++; - state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl, - sizeof(*tl) + ext4_fc_tag_len(tl)); + state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur, + sizeof(tl) + le16_to_cpu(tl.fc_len)); break; case EXT4_FC_TAG_TAIL: state->fc_cur_tag++; - tail = (struct ext4_fc_tail *)ext4_fc_tag_val(tl); - state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl, - sizeof(*tl) + + memcpy(&tail, val, sizeof(tail)); + state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur, + sizeof(tl) + offsetof(struct ext4_fc_tail, fc_crc)); - if (le32_to_cpu(tail->fc_tid) == expected_tid && - le32_to_cpu(tail->fc_crc) == state->fc_crc) { + if (le32_to_cpu(tail.fc_tid) == expected_tid && + le32_to_cpu(tail.fc_crc) == state->fc_crc) { state->fc_replay_num_tags = state->fc_cur_tag; state->fc_regions_valid = state->fc_regions_used; @@ -2000,19 +2007,19 @@ static int ext4_fc_replay_scan(journal_t state->fc_crc = 0; break; case EXT4_FC_TAG_HEAD: - head = (struct ext4_fc_head *)ext4_fc_tag_val(tl); - if (le32_to_cpu(head->fc_features) & + memcpy(&head, val, sizeof(head)); + if (le32_to_cpu(head.fc_features) & ~EXT4_FC_SUPPORTED_FEATURES) { ret = -EOPNOTSUPP; break; } - if (le32_to_cpu(head->fc_tid) != expected_tid) { + if (le32_to_cpu(head.fc_tid) != expected_tid) { ret = JBD2_FC_REPLAY_STOP; break; } state->fc_cur_tag++; - state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl, - sizeof(*tl) + ext4_fc_tag_len(tl)); + state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur, + sizeof(tl) + le16_to_cpu(tl.fc_len)); break; default: ret = state->fc_replay_num_tags ? @@ -2036,11 +2043,11 @@ static int ext4_fc_replay(journal_t *jou { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_fc_tl *tl; - __u8 *start, *end; + struct ext4_fc_tl tl; + __u8 *start, *end, *cur, *val; int ret = JBD2_FC_REPLAY_CONTINUE; struct ext4_fc_replay_state *state = &sbi->s_fc_replay_state; - struct ext4_fc_tail *tail; + struct ext4_fc_tail tail;

if (pass == PASS_SCAN) { state->fc_current_pass = PASS_SCAN; @@ -2067,49 +2074,52 @@ static int ext4_fc_replay(journal_t *jou start = (u8 *)bh->b_data; end = (__u8 *)bh->b_data + journal->j_blocksize - 1;

- fc_for_each_tl(start, end, tl) { + for (cur = start; cur < end; cur = cur + sizeof(tl) + le16_to_cpu(tl.fc_len)) { + memcpy(&tl, cur, sizeof(tl)); + val = cur + sizeof(tl); + if (state->fc_replay_num_tags == 0) { ret = JBD2_FC_REPLAY_STOP; ext4_fc_set_bitmaps_and_counters(sb); break; } jbd_debug(3, "Replay phase, tag:%s\n", - tag2str(le16_to_cpu(tl->fc_tag))); + tag2str(le16_to_cpu(tl.fc_tag))); state->fc_replay_num_tags--; - switch (le16_to_cpu(tl->fc_tag)) { + switch (le16_to_cpu(tl.fc_tag)) { case EXT4_FC_TAG_LINK: - ret = ext4_fc_replay_link(sb, tl); + ret = ext4_fc_replay_link(sb, &tl, val); break; case EXT4_FC_TAG_UNLINK: - ret = ext4_fc_replay_unlink(sb, tl); + ret = ext4_fc_replay_unlink(sb, &tl, val); break; case EXT4_FC_TAG_ADD_RANGE: - ret = ext4_fc_replay_add_range(sb, tl); + ret = ext4_fc_replay_add_range(sb, &tl, val); break; case EXT4_FC_TAG_CREAT: - ret = ext4_fc_replay_create(sb, tl); + ret = ext4_fc_replay_create(sb, &tl, val); break; case EXT4_FC_TAG_DEL_RANGE: - ret = ext4_fc_replay_del_range(sb, tl); + ret = ext4_fc_replay_del_range(sb, &tl, val); break; case EXT4_FC_TAG_INODE: - ret = ext4_fc_replay_inode(sb, tl); + ret = ext4_fc_replay_inode(sb, &tl, val); break; case EXT4_FC_TAG_PAD: trace_ext4_fc_replay(sb, EXT4_FC_TAG_PAD, 0, - ext4_fc_tag_len(tl), 0); + le16_to_cpu(tl.fc_len), 0); break; case EXT4_FC_TAG_TAIL: trace_ext4_fc_replay(sb, EXT4_FC_TAG_TAIL, 0, - ext4_fc_tag_len(tl), 0); - tail = (struct ext4_fc_tail *)ext4_fc_tag_val(tl); - WARN_ON(le32_to_cpu(tail->fc_tid) != expected_tid); + le16_to_cpu(tl.fc_len), 0); + memcpy(&tail, val, sizeof(tail)); + WARN_ON(le32_to_cpu(tail.fc_tid) != expected_tid); break; case EXT4_FC_TAG_HEAD: break; default: - trace_ext4_fc_replay(sb, le16_to_cpu(tl->fc_tag), 0, - ext4_fc_tag_len(tl), 0); + trace_ext4_fc_replay(sb, le16_to_cpu(tl.fc_tag), 0, + le16_to_cpu(tl.fc_len), 0); ret = -ECANCELED; break; } --- a/fs/ext4/fast_commit.h +++ b/fs/ext4/fast_commit.h @@ -153,13 +153,6 @@ struct ext4_fc_replay_state { #define region_last(__region) (((__region)->lblk) + ((__region)->len) - 1) #endif

-#define fc_for_each_tl(__start, __end, __tl) \ - for (tl = (struct ext4_fc_tl *)(__start); \ - (__u8 *)tl < (__u8 *)(__end); \ - tl = (struct ext4_fc_tl *)((__u8 *)tl + \ - sizeof(struct ext4_fc_tl) + \ - + le16_to_cpu(tl->fc_len))) - static inline const char *tag2str(__u16 tag) { switch (tag) { @@ -186,16 +179,4 @@ static inline const char *tag2str(__u16 } }

-/* Get length of a particular tlv */ -static inline int ext4_fc_tag_len(struct ext4_fc_tl *tl) -{ - return le16_to_cpu(tl->fc_len); -} - -/* Get a pointer to "value" of a tlv */ -static inline __u8 *ext4_fc_tag_val(struct ext4_fc_tl *tl) -{ - return (__u8 *)tl + sizeof(*tl); -} - #endif /* __FAST_COMMIT_H__ */

From: Ritesh Harjani riteshh@linux.ibm.com

commit b45f189a19b38e01676628db79cd3eeb1333516e upstream.

When running generic/527 with fast_commit configuration, the following issue is seen on Power. With fast_commit, during ext4_fc_replay() (which can be called from ext4_fill_super()), if inode eviction happens then it can access an uninitialized percpu counter variable.

This patch adds the check before accessing the counters in ext4_free_inode() path.

[ 321.165371] run fstests generic/527 at 2021-04-29 08:38:43 [ 323.027786] EXT4-fs (dm-0): mounted filesystem with ordered data mode. Opts: block_validity. Quota mode: none. [ 323.618772] BUG: Unable to handle kernel data access on read at 0x1fbd80000 [ 323.619767] Faulting instruction address: 0xc000000000bae78c cpu 0x1: Vector: 300 (Data Access) at [c000000010706ef0] pc: c000000000bae78c: percpu_counter_add_batch+0x3c/0x100 lr: c0000000006d0bb0: ext4_free_inode+0x780/0xb90 pid = 5593, comm = mount ext4_free_inode+0x780/0xb90 ext4_evict_inode+0xa8c/0xc60 evict+0xfc/0x1e0 ext4_fc_replay+0xc50/0x20f0 do_one_pass+0xfe0/0x1350 jbd2_journal_recover+0x184/0x2e0 jbd2_journal_load+0x1c0/0x4a0 ext4_fill_super+0x2458/0x4200 mount_bdev+0x1dc/0x290 ext4_mount+0x28/0x40 legacy_get_tree+0x4c/0xa0 vfs_get_tree+0x4c/0x120 path_mount+0xcf8/0xd70 do_mount+0x80/0xd0 sys_mount+0x3fc/0x490 system_call_exception+0x384/0x3d0 system_call_common+0xec/0x278

Cc: stable@kernel.org Fixes: 8016e29f4362 ("ext4: fast commit recovery path") Signed-off-by: Ritesh Harjani riteshh@linux.ibm.com Reviewed-by: Harshad Shirwadkar harshadshirwadkar@gmail.com Link: https://lore.kernel.org/r/6cceb9a75c54bef8fa9696c1b08c8df5ff6169e2.161969241... Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/ialloc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -322,14 +322,16 @@ void ext4_free_inode(handle_t *handle, s if (is_directory) { count = ext4_used_dirs_count(sb, gdp) - 1; ext4_used_dirs_set(sb, gdp, count); - percpu_counter_dec(&sbi->s_dirs_counter); + if (percpu_counter_initialized(&sbi->s_dirs_counter)) + percpu_counter_dec(&sbi->s_dirs_counter); } ext4_inode_bitmap_csum_set(sb, block_group, gdp, bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8); ext4_group_desc_csum_set(sb, block_group, gdp); ext4_unlock_group(sb, block_group);

- percpu_counter_inc(&sbi->s_freeinodes_counter); + if (percpu_counter_initialized(&sbi->s_freeinodes_counter)) + percpu_counter_inc(&sbi->s_freeinodes_counter); if (sbi->s_log_groups_per_flex) { struct flex_groups *fg;

From: Thomas Bogendoerfer tsbogend@alpha.franken.de

commit 50c25ee97cf6ab011542167ab590c17012cea4ed upstream.

This reverts commit f685a533a7fab35c5d069dcd663f59c8e4171a75.

The MIPS cache flush logic needs to know whether the mapping was already established to decide how to flush caches. This is done by checking the valid bit in the PTE. The commit above breaks this logic by setting the valid in the PTE in new mappings, which causes kernel crashes.

Link: https://lkml.kernel.org/r/20210526094335.92948-1-tsbogend@alpha.franken.de Fixes: f685a533a7f ("MIPS: make userspace mapping young by default") Reported-by: Zhou Yanjie zhouyanjie@wanyeetech.com Signed-off-by: Thomas Bogendoerfer tsbogend@alpha.franken.de Cc: Huang Pei huangpei@loongson.cn Cc: Nicholas Piggin npiggin@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/mips/mm/cache.c | 30 ++++++++++++++---------------- include/linux/pgtable.h | 8 ++++++++ mm/memory.c | 4 ++++ 3 files changed, 26 insertions(+), 16 deletions(-)

--- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -157,31 +157,29 @@ unsigned long _page_cachable_default; EXPORT_SYMBOL(_page_cachable_default);

#define PM(p) __pgprot(_page_cachable_default | (p)) -#define PVA(p) PM(_PAGE_VALID | _PAGE_ACCESSED | (p))

static inline void setup_protection_map(void) { protection_map[0] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); - protection_map[1] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC); - protection_map[2] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); - protection_map[3] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC); - protection_map[4] = PVA(_PAGE_PRESENT); - protection_map[5] = PVA(_PAGE_PRESENT); - protection_map[6] = PVA(_PAGE_PRESENT); - protection_map[7] = PVA(_PAGE_PRESENT); + protection_map[1] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC); + protection_map[2] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); + protection_map[3] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC); + protection_map[4] = PM(_PAGE_PRESENT); + protection_map[5] = PM(_PAGE_PRESENT); + protection_map[6] = PM(_PAGE_PRESENT); + protection_map[7] = PM(_PAGE_PRESENT);

protection_map[8] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); - protection_map[9] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC); - protection_map[10] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | + protection_map[9] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC); + protection_map[10] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | _PAGE_NO_READ); - protection_map[11] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE); - protection_map[12] = PVA(_PAGE_PRESENT); - protection_map[13] = PVA(_PAGE_PRESENT); - protection_map[14] = PVA(_PAGE_PRESENT); - protection_map[15] = PVA(_PAGE_PRESENT); + protection_map[11] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE); + protection_map[12] = PM(_PAGE_PRESENT); + protection_map[13] = PM(_PAGE_PRESENT); + protection_map[14] = PM(_PAGE_PRESENT | _PAGE_WRITE); + protection_map[15] = PM(_PAGE_PRESENT | _PAGE_WRITE); }

-#undef _PVA #undef PM

void cpu_cache_init(void) --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -432,6 +432,14 @@ static inline void ptep_set_wrprotect(st * To be differentiate with macro pte_mkyoung, this macro is used on platforms * where software maintains page access bit. */ +#ifndef pte_sw_mkyoung +static inline pte_t pte_sw_mkyoung(pte_t pte) +{ + return pte; +} +#define pte_sw_mkyoung pte_sw_mkyoung +#endif + #ifndef pte_savedwrite #define pte_savedwrite pte_write #endif --- a/mm/memory.c +++ b/mm/memory.c @@ -2896,6 +2896,7 @@ static vm_fault_t wp_page_copy(struct vm } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma);

/* @@ -3561,6 +3562,7 @@ static vm_fault_t do_anonymous_page(stru __SetPageUptodate(page);

entry = mk_pte(page, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry));

@@ -3745,6 +3747,8 @@ void do_set_pte(struct vm_fault *vmf, st

if (prefault && arch_wants_old_prefaulted_pte()) entry = pte_mkold(entry); + else + entry = pte_sw_mkyoung(entry);

if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma);

From: Marco Elver elver@google.com

commit 8fd0e995cc7b6a7a8a40bc03d52a2cd445beeff4 upstream.

Since wait_event() uses TASK_UNINTERRUPTIBLE by default, waiting for an allocation counts towards load. However, for KFENCE, this does not make any sense, since there is no busy work we're awaiting.

Instead, use TASK_IDLE via wait_event_idle() to not count towards load.

BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1185565 Link: https://lkml.kernel.org/r/20210521083209.3740269-1-elver@google.com Fixes: 407f1d8c1b5f ("kfence: await for allocation using wait_event") Signed-off-by: Marco Elver elver@google.com Cc: Mel Gorman mgorman@suse.de Cc: Alexander Potapenko glider@google.com Cc: Dmitry Vyukov dvyukov@google.com Cc: David Laight David.Laight@ACULAB.COM Cc: Hillf Danton hdanton@sina.com Cc: stable@vger.kernel.org [5.12+] Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/kfence/core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -626,10 +626,10 @@ static void toggle_allocation_gate(struc * During low activity with no allocations we might wait a * while; let's avoid the hung task warning. */ - wait_event_timeout(allocation_wait, atomic_read(&kfence_allocation_gate), - sysctl_hung_task_timeout_secs * HZ / 2); + wait_event_idle_timeout(allocation_wait, atomic_read(&kfence_allocation_gate), + sysctl_hung_task_timeout_secs * HZ / 2); } else { - wait_event(allocation_wait, atomic_read(&kfence_allocation_gate)); + wait_event_idle(allocation_wait, atomic_read(&kfence_allocation_gate)); }

/* Disable static key and reset timer. */

From: Junxiao Bi junxiao.bi@oracle.com

commit 6bba4471f0cc1296fe3c2089b9e52442d3074b2e upstream.

When fallocate punches holes out of inode size, if original isize is in the middle of last cluster, then the part from isize to the end of the cluster will be zeroed with buffer write, at that time isize is not yet updated to match the new size, if writeback is kicked in, it will invoke ocfs2_writepage()->block_write_full_page() where the pages out of inode size will be dropped. That will cause file corruption. Fix this by zero out eof blocks when extending the inode size.

Running the following command with qemu-image 4.2.1 can get a corrupted coverted image file easily.

qemu-img convert -p -t none -T none -f qcow2 $qcow_image \ -O qcow2 -o compat=1.1 $qcow_image.conv

The usage of fallocate in qemu is like this, it first punches holes out of inode size, then extend the inode size.

fallocate(11, FALLOC_FL_KEEP_SIZE|FALLOC_FL_PUNCH_HOLE, 2276196352, 65536) = 0 fallocate(11, 0, 2276196352, 65536) = 0

v1: https://www.spinics.net/lists/linux-fsdevel/msg193999.html v2: https://lore.kernel.org/linux-fsdevel/20210525093034.GB4112@quack2.suse.cz/T...

Link: https://lkml.kernel.org/r/20210528210648.9124-1-junxiao.bi@oracle.com Signed-off-by: Junxiao Bi junxiao.bi@oracle.com Reviewed-by: Joseph Qi joseph.qi@linux.alibaba.com Cc: Jan Kara jack@suse.cz Cc: Mark Fasheh mark@fasheh.com Cc: Joel Becker jlbec@evilplan.org Cc: Changwei Ge gechangwei@live.cn Cc: Gang He ghe@suse.com Cc: Jun Piao piaojun@huawei.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ocfs2/file.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 50 insertions(+), 5 deletions(-)

--- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1858,6 +1858,45 @@ out: }

/* + * zero out partial blocks of one cluster. + * + * start: file offset where zero starts, will be made upper block aligned. + * len: it will be trimmed to the end of current cluster if "start + len" + * is bigger than it. + */ +static int ocfs2_zeroout_partial_cluster(struct inode *inode, + u64 start, u64 len) +{ + int ret; + u64 start_block, end_block, nr_blocks; + u64 p_block, offset; + u32 cluster, p_cluster, nr_clusters; + struct super_block *sb = inode->i_sb; + u64 end = ocfs2_align_bytes_to_clusters(sb, start); + + if (start + len < end) + end = start + len; + + start_block = ocfs2_blocks_for_bytes(sb, start); + end_block = ocfs2_blocks_for_bytes(sb, end); + nr_blocks = end_block - start_block; + if (!nr_blocks) + return 0; + + cluster = ocfs2_bytes_to_clusters(sb, start); + ret = ocfs2_get_clusters(inode, cluster, &p_cluster, + &nr_clusters, NULL); + if (ret) + return ret; + if (!p_cluster) + return 0; + + offset = start_block - ocfs2_clusters_to_blocks(sb, cluster); + p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset; + return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS); +} + +/* * Parts of this function taken from xfs_change_file_space() */ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, @@ -1867,7 +1906,7 @@ static int __ocfs2_change_file_space(str { int ret; s64 llen; - loff_t size; + loff_t size, orig_isize; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct buffer_head *di_bh = NULL; handle_t *handle; @@ -1898,6 +1937,7 @@ static int __ocfs2_change_file_space(str goto out_inode_unlock; }

+ orig_isize = i_size_read(inode); switch (sr->l_whence) { case 0: /*SEEK_SET*/ break; @@ -1905,7 +1945,7 @@ static int __ocfs2_change_file_space(str sr->l_start += f_pos; break; case 2: /*SEEK_END*/ - sr->l_start += i_size_read(inode); + sr->l_start += orig_isize; break; default: ret = -EINVAL; @@ -1959,6 +1999,14 @@ static int __ocfs2_change_file_space(str default: ret = -EINVAL; } + + /* zeroout eof blocks in the cluster. */ + if (!ret && change_size && orig_isize < size) { + ret = ocfs2_zeroout_partial_cluster(inode, orig_isize, + size - orig_isize); + if (!ret) + i_size_write(inode, size); + } up_write(&OCFS2_I(inode)->ip_alloc_sem); if (ret) { mlog_errno(ret); @@ -1975,9 +2023,6 @@ static int __ocfs2_change_file_space(str goto out_inode_unlock; }

- if (change_size && i_size_read(inode) < size) - i_size_write(inode, size); - inode->i_ctime = inode->i_mtime = current_time(inode); ret = ocfs2_mark_inode_dirty(handle, inode, di_bh); if (ret < 0)

From: Ding Hui dinghui@sangfor.com.cn

commit bac9c6fa1f929213bbd0ac9cdf21e8e2f0916828 upstream.

Recently we found that there is a lot MemFree left in /proc/meminfo after do a lot of pages soft offline, it's not quite correct.

Before Oscar's rework of soft offline for free pages [1], if we soft offline free pages, these pages are left in buddy with HWPoison flag, and NR_FREE_PAGES is not updated immediately. So the difference between NR_FREE_PAGES and real number of available free pages is also even big at the beginning.

However, with the workload running, when we catch HWPoison page in any alloc functions subsequently, we will remove it from buddy, meanwhile update the NR_FREE_PAGES and try again, so the NR_FREE_PAGES will get more and more closer to the real number of available free pages. (regardless of unpoison_memory())

Now, for offline free pages, after a successful call take_page_off_buddy(), the page is no longer belong to buddy allocator, and will not be used any more, but we missed accounting NR_FREE_PAGES in this situation, and there is no chance to be updated later.

Do update in take_page_off_buddy() like rmqueue() does, but avoid double counting if some one already set_migratetype_isolate() on the page.

[1]: commit 06be6ff3d2ec ("mm,hwpoison: rework soft offline for free pages")

Link: https://lkml.kernel.org/r/20210526075247.11130-1-dinghui@sangfor.com.cn Fixes: 06be6ff3d2ec ("mm,hwpoison: rework soft offline for free pages") Signed-off-by: Ding Hui dinghui@sangfor.com.cn Suggested-by: Naoya Horiguchi naoya.horiguchi@nec.com Reviewed-by: Oscar Salvador osalvador@suse.de Acked-by: David Hildenbrand david@redhat.com Acked-by: Naoya Horiguchi naoya.horiguchi@nec.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/page_alloc.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8951,6 +8951,8 @@ bool take_page_off_buddy(struct page *pa del_page_from_free_list(page_head, zone, page_order); break_down_buddy_pages(zone, page_head, page, 0, page_order, migratetype); + if (!is_migrate_isolate(migratetype)) + __mod_zone_freepage_state(zone, -1, migratetype); ret = true; break; }

From: Thomas Gleixner tglx@linutronix.de

commit 9bfecd05833918526cc7357d55e393393440c5fa upstream.

While digesting the XSAVE-related horrors which got introduced with the supervisor/user split, the recent addition of ENQCMD-related functionality got on the radar and turned out to be similarly broken.

update_pasid(), which is only required when X86_FEATURE_ENQCMD is available, is invoked from two places:

1) From switch_to() for the incoming task

2) Via a SMP function call from the IOMMU/SMV code

#1 is half-ways correct as it hacks around the brokenness of get_xsave_addr() by enforcing the state to be 'present', but all the conditionals in that code are completely pointless for that.

Also the invocation is just useless overhead because at that point it's guaranteed that TIF_NEED_FPU_LOAD is set on the incoming task and all of this can be handled at return to user space.

#2 is broken beyond repair. The comment in the code claims that it is safe to invoke this in an IPI, but that's just wishful thinking.

FPU state of a running task is protected by fregs_lock() which is nothing else than a local_bh_disable(). As BH-disabled regions run usually with interrupts enabled the IPI can hit a code section which modifies FPU state and there is absolutely no guarantee that any of the assumptions which are made for the IPI case is true.

Also the IPI is sent to all CPUs in mm_cpumask(mm), but the IPI is invoked with a NULL pointer argument, so it can hit a completely unrelated task and unconditionally force an update for nothing. Worse, it can hit a kernel thread which operates on a user space address space and set a random PASID for it.

The offending commit does not cleanly revert, but it's sufficient to force disable X86_FEATURE_ENQCMD and to remove the broken update_pasid() code to make this dysfunctional all over the place. Anything more complex would require more surgery and none of the related functions outside of the x86 core code are blatantly wrong, so removing those would be overkill.

As nothing enables the PASID bit in the IA32_XSS MSR yet, which is required to make this actually work, this cannot result in a regression except for related out of tree train-wrecks, but they are broken already today.

Fixes: 20f0afd1fb3d ("x86/mmu: Allocate/free a PASID") Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Andy Lutomirski luto@kernel.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/87mtsd6gr9.ffs@nanos.tec.linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/disabled-features.h | 7 +-- arch/x86/include/asm/fpu/api.h | 6 --- arch/x86/include/asm/fpu/internal.h | 7 --- arch/x86/kernel/fpu/xstate.c | 57 ------------------------------- 4 files changed, 3 insertions(+), 74 deletions(-)

--- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -56,11 +56,8 @@ # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif

-#ifdef CONFIG_IOMMU_SUPPORT -# define DISABLE_ENQCMD 0 -#else -# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31)) -#endif +/* Force disable because it's broken beyond repair */ +#define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))

#ifdef CONFIG_X86_SGX # define DISABLE_SGX 0 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -106,10 +106,6 @@ extern int cpu_has_xfeatures(u64 xfeatur */ #define PASID_DISABLED 0

-#ifdef CONFIG_IOMMU_SUPPORT -/* Update current's PASID MSR/state by mm's PASID. */ -void update_pasid(void); -#else static inline void update_pasid(void) { } -#endif + #endif /* _ASM_X86_FPU_API_H */ --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -584,13 +584,6 @@ static inline void switch_fpu_finish(str pkru_val = pk->pkru; } __write_pkru(pkru_val); - - /* - * Expensive PASID MSR write will be avoided in update_pasid() because - * TIF_NEED_FPU_LOAD was set. And the PASID state won't be updated - * unless it's different from mm->pasid to reduce overhead. - */ - update_pasid(); }

#endif /* _ASM_X86_FPU_INTERNAL_H */ --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1402,60 +1402,3 @@ int proc_pid_arch_status(struct seq_file return 0; } #endif /* CONFIG_PROC_PID_ARCH_STATUS */ - -#ifdef CONFIG_IOMMU_SUPPORT -void update_pasid(void) -{ - u64 pasid_state; - u32 pasid; - - if (!cpu_feature_enabled(X86_FEATURE_ENQCMD)) - return; - - if (!current->mm) - return; - - pasid = READ_ONCE(current->mm->pasid); - /* Set the valid bit in the PASID MSR/state only for valid pasid. */ - pasid_state = pasid == PASID_DISABLED ? - pasid : pasid | MSR_IA32_PASID_VALID; - - /* - * No need to hold fregs_lock() since the task's fpstate won't - * be changed by others (e.g. ptrace) while the task is being - * switched to or is in IPI. - */ - if (!test_thread_flag(TIF_NEED_FPU_LOAD)) { - /* The MSR is active and can be directly updated. */ - wrmsrl(MSR_IA32_PASID, pasid_state); - } else { - struct fpu *fpu = &current->thread.fpu; - struct ia32_pasid_state *ppasid_state; - struct xregs_state *xsave; - - /* - * The CPU's xstate registers are not currently active. Just - * update the PASID state in the memory buffer here. The - * PASID MSR will be loaded when returning to user mode. - */ - xsave = &fpu->state.xsave; - xsave->header.xfeatures |= XFEATURE_MASK_PASID; - ppasid_state = get_xsave_addr(xsave, XFEATURE_PASID); - /* - * Since XFEATURE_MASK_PASID is set in xfeatures, ppasid_state - * won't be NULL and no need to check its value. - * - * Only update the task's PASID state when it's different - * from the mm's pasid. - */ - if (ppasid_state->pasid != pasid_state) { - /* - * Invalid fpregs so that state restoring will pick up - * the PASID state. - */ - __fpu_invalidate_fpregs_state(fpu); - ppasid_state->pasid = pasid_state; - } - } -} -#endif /* CONFIG_IOMMU_SUPPORT */

From: Pu Wen puwen@hygon.cn

commit 009767dbf42ac0dbe3cf48c1ee224f6b778aa85a upstream.

The first two bits of the CPUID leaf 0x8000001F EAX indicate whether SEV or SME is supported, respectively. It's better to check whether SEV or SME is actually supported before accessing the MSR_AMD64_SEV to check whether SEV or SME is enabled.

This is both a bare-metal issue and a guest/VM issue. Since the first generation Hygon Dhyana CPU doesn't support the MSR_AMD64_SEV, reading that MSR results in a #GP - either directly from hardware in the bare-metal case or via the hypervisor (because the RDMSR is actually intercepted) in the guest/VM case, resulting in a failed boot. And since this is very early in the boot phase, rdmsrl_safe()/native_read_msr_safe() can't be used.

So check the CPUID bits first, before accessing the MSR.

[ tlendacky: Expand and improve commit message. ] [ bp: Massage commit message. ]

Fixes: eab696d8e8b9 ("x86/sev: Do not require Hypervisor CPUID bit for SEV guests") Signed-off-by: Pu Wen puwen@hygon.cn Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Tom Lendacky thomas.lendacky@amd.com Cc: stable@vger.kernel.org # v5.10+ Link: https://lkml.kernel.org/r/20210602070207.2480-1-puwen@hygon.cn Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/mm/mem_encrypt_identity.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)

--- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -504,10 +504,6 @@ void __init sme_enable(struct boot_param #define AMD_SME_BIT BIT(0) #define AMD_SEV_BIT BIT(1)

- /* Check the SEV MSR whether SEV or SME is enabled */ - sev_status = __rdmsr(MSR_AMD64_SEV); - feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; - /* * Check for the SME/SEV feature: * CPUID Fn8000_001F[EAX] @@ -519,11 +515,16 @@ void __init sme_enable(struct boot_param eax = 0x8000001f; ecx = 0; native_cpuid(&eax, &ebx, &ecx, &edx); - if (!(eax & feature_mask)) + /* Check whether SEV or SME is supported */ + if (!(eax & (AMD_SEV_BIT | AMD_SME_BIT))) return;

me_mask = 1UL << (ebx & 0x3f);

+ /* Check the SEV MSR whether SEV or SME is enabled */ + sev_status = __rdmsr(MSR_AMD64_SEV); + feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; + /* Check if memory encryption is enabled */ if (feature_mask == AMD_SME_BIT) { /*

From: Krzysztof Kozlowski krzysztof.kozlowski@canonical.com

commit 4ac06a1e013cf5fdd963317ffd3b968560f33bba upstream.

It's possible to trigger NULL pointer dereference by local unprivileged user, when calling getsockname() after failed bind() (e.g. the bind fails because LLCP_SAP_MAX used as SAP):

BUG: kernel NULL pointer dereference, address: 0000000000000000 CPU: 1 PID: 426 Comm: llcp_sock_getna Not tainted 5.13.0-rc2-next-20210521+ #9 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1 04/01/2014 Call Trace: llcp_sock_getname+0xb1/0xe0 __sys_getpeername+0x95/0xc0 ? lockdep_hardirqs_on_prepare+0xd5/0x180 ? syscall_enter_from_user_mode+0x1c/0x40 __x64_sys_getpeername+0x11/0x20 do_syscall_64+0x36/0x70 entry_SYSCALL_64_after_hwframe+0x44/0xae

This can be reproduced with Syzkaller C repro (bind followed by getpeername): https://syzkaller.appspot.com/x/repro.c?x=14def446e00000

Cc: stable@vger.kernel.org Fixes: d646960f7986 ("NFC: Initial LLCP support") Reported-by: syzbot+80fb126e7f7d8b1a5914@syzkaller.appspotmail.com Reported-by: butt3rflyh4ck butterflyhuangxx@gmail.com Signed-off-by: Krzysztof Kozlowski krzysztof.kozlowski@canonical.com Link: https://lore.kernel.org/r/20210531072138.5219-1-krzysztof.kozlowski@canonica... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/nfc/llcp_sock.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -110,6 +110,7 @@ static int llcp_sock_bind(struct socket if (!llcp_sock->service_name) { nfc_llcp_local_put(llcp_sock->local); llcp_sock->local = NULL; + llcp_sock->dev = NULL; ret = -ENOMEM; goto put_dev; } @@ -119,6 +120,7 @@ static int llcp_sock_bind(struct socket llcp_sock->local = NULL; kfree(llcp_sock->service_name); llcp_sock->service_name = NULL; + llcp_sock->dev = NULL; ret = -EADDRINUSE; goto put_dev; }

From: Nirmoy Das nirmoy.das@amd.com

commit 07438603a07e52f1c6aa731842bd298d2725b7be upstream.

Releasing pinned BOs is illegal now. UVD 6 was missing from: commit 2f40801dc553 ("drm/amdgpu: make sure we unpin the UVD BO")

Fixes: 2f40801dc553 ("drm/amdgpu: make sure we unpin the UVD BO") Cc: stable@vger.kernel.org Signed-off-by: Nirmoy Das nirmoy.das@amd.com Reviewed-by: Christian König christian.koenig@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -357,6 +357,7 @@ static int uvd_v6_0_enc_ring_test_ib(str

error: dma_fence_put(fence); + amdgpu_bo_unpin(bo); amdgpu_bo_unreserve(bo); amdgpu_bo_unref(&bo); return r;

From: Borislav Petkov bp@suse.de

commit 9a90ed065a155d13db0d0ffeaad5cc54e51c90c6 upstream.

There are machines out there with added value crap^WBIOS which provide an SMI handler for the local APIC thermal sensor interrupt. Out of reset, the BSP on those machines has something like 0x200 in that APIC register (timestamps left in because this whole issue is timing sensitive):

[ 0.033858] read lvtthmr: 0x330, val: 0x200

which means:

- bit 16 - the interrupt mask bit is clear and thus that interrupt is enabled - bits [10:8] have 010b which means SMI delivery mode.

Now, later during boot, when the kernel programs the local APIC, it soft-disables it temporarily through the spurious vector register:

setup_local_APIC:

...

/* * If this comes from kexec/kcrash the APIC might be enabled in * SPIV. Soft disable it before doing further initialization. */ value = apic_read(APIC_SPIV); value &= ~APIC_SPIV_APIC_ENABLED; apic_write(APIC_SPIV, value);

which means (from the SDM):

"10.4.7.2 Local APIC State After It Has Been Software Disabled

...

* The mask bits for all the LVT entries are set. Attempts to reset these bits will be ignored."

And this happens too:

[ 0.124111] APIC: Switch to symmetric I/O mode setup [ 0.124117] lvtthmr 0x200 before write 0xf to APIC 0xf0 [ 0.124118] lvtthmr 0x10200 after write 0xf to APIC 0xf0

This results in CPU 0 soft lockups depending on the placement in time when the APIC soft-disable happens. Those soft lockups are not 100% reproducible and the reason for that can only be speculated as no one tells you what SMM does. Likely, it confuses the SMM code that the APIC is disabled and the thermal interrupt doesn't doesn't fire at all, leading to CPU 0 stuck in SMM forever...

Now, before

4f432e8bb15b ("x86/mce: Get rid of mcheck_intel_therm_init()")

due to how the APIC_LVTTHMR was read before APIC initialization in mcheck_intel_therm_init(), it would read the value with the mask bit 16 clear and then intel_init_thermal() would replicate it onto the APs and all would be peachy - the thermal interrupt would remain enabled.

But that commit moved that reading to a later moment in intel_init_thermal(), resulting in reading APIC_LVTTHMR on the BSP too late and with its interrupt mask bit set.

Thus, revert back to the old behavior of reading the thermal LVT register before the APIC gets initialized.

Fixes: 4f432e8bb15b ("x86/mce: Get rid of mcheck_intel_therm_init()") Reported-by: James Feeney james@nurealm.net Signed-off-by: Borislav Petkov bp@suse.de Cc: stable@vger.kernel.org Cc: Zhang Rui rui.zhang@intel.com Cc: Srinivas Pandruvada srinivas.pandruvada@linux.intel.com Link: https://lkml.kernel.org/r/YKIqDdFNaXYd39wz@zn.tnic Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/thermal.h | 4 +++- arch/x86/kernel/setup.c | 9 +++++++++ drivers/thermal/intel/therm_throt.c | 15 +++++++++++---- 3 files changed, 23 insertions(+), 5 deletions(-)

--- a/arch/x86/include/asm/thermal.h +++ b/arch/x86/include/asm/thermal.h @@ -3,11 +3,13 @@ #define _ASM_X86_THERMAL_H

#ifdef CONFIG_X86_THERMAL_VECTOR +void therm_lvt_init(void); void intel_init_thermal(struct cpuinfo_x86 *c); bool x86_thermal_enabled(void); void intel_thermal_interrupt(void); #else -static inline void intel_init_thermal(struct cpuinfo_x86 *c) { } +static inline void therm_lvt_init(void) { } +static inline void intel_init_thermal(struct cpuinfo_x86 *c) { } #endif

#endif /* _ASM_X86_THERMAL_H */ --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -44,6 +44,7 @@ #include <asm/pci-direct.h> #include <asm/prom.h> #include <asm/proto.h> +#include <asm/thermal.h> #include <asm/unwind.h> #include <asm/vsyscall.h> #include <linux/vmalloc.h> @@ -1220,6 +1221,14 @@ void __init setup_arch(char **cmdline_p)

x86_init.timers.wallclock_init();

+ /* + * This needs to run before setup_local_APIC() which soft-disables the + * local APIC temporarily and that masks the thermal LVT interrupt, + * leading to softlockups on machines which have configured SMI + * interrupt delivery. + */ + therm_lvt_init(); + mcheck_init();

register_refined_jiffies(CLOCK_TICK_RATE); --- a/drivers/thermal/intel/therm_throt.c +++ b/drivers/thermal/intel/therm_throt.c @@ -621,6 +621,17 @@ bool x86_thermal_enabled(void) return atomic_read(&therm_throt_en); }

+void __init therm_lvt_init(void) +{ + /* + * This function is only called on boot CPU. Save the init thermal + * LVT value on BSP and use that value to restore APs' thermal LVT + * entry BIOS programmed later + */ + if (intel_thermal_supported(&boot_cpu_data)) + lvtthmr_init = apic_read(APIC_LVTTHMR); +} + void intel_init_thermal(struct cpuinfo_x86 *c) { unsigned int cpu = smp_processor_id(); @@ -630,10 +641,6 @@ void intel_init_thermal(struct cpuinfo_x if (!intel_thermal_supported(c)) return;

- /* On the BSP? */ - if (c == &boot_cpu_data) - lvtthmr_init = apic_read(APIC_LVTTHMR); - /* * First check if its enabled already, in which case there might * be some SMM goo which handles it, so we can't even put a handler

From: Josef Bacik josef@toxicpanda.com

commit d61bec08b904cf171835db98168f82bc338e92e4 upstream.

While doing error injection testing I saw that sometimes we'd get an abort that wouldn't stop the current transaction commit from completing. This abort was coming from finish ordered IO, but at this point in the transaction commit we should have gotten an error and stopped.

It turns out the abort came from finish ordered io while trying to write out the free space cache. It occurred to me that any failure inside of finish_ordered_io isn't actually raised to the person doing the writing, so we could have any number of failures in this path and think the ordered extent completed successfully and the inode was fine.

Fix this by marking the ordered extent with BTRFS_ORDERED_IOERR, and marking the mapping of the inode with mapping_set_error, so any callers that simply call fdatawait will also get the error.

With this we're seeing the IO error on the free space inode when we fail to do the finish_ordered_io.

CC: stable@vger.kernel.org # 4.19+ Signed-off-by: Josef Bacik josef@toxicpanda.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/inode.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)

--- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3011,6 +3011,18 @@ out: if (ret || truncated) { u64 unwritten_start = start;

+ /* + * If we failed to finish this ordered extent for any reason we + * need to make sure BTRFS_ORDERED_IOERR is set on the ordered + * extent, and mark the inode with the error if it wasn't + * already set. Any error during writeback would have already + * set the mapping error, so we need to set it if we're the ones + * marking this ordered extent as failed. + */ + if (ret && !test_and_set_bit(BTRFS_ORDERED_IOERR, + &ordered_extent->flags)) + mapping_set_error(ordered_extent->inode->i_mapping, -EIO); + if (truncated) unwritten_start += logical_len; clear_extent_uptodate(io_tree, unwritten_start, end, NULL);

From: Josef Bacik josef@toxicpanda.com

commit 856bd270dc4db209c779ce1e9555c7641ffbc88e upstream.

We are unconditionally returning 0 in cleanup_ref_head, despite the fact that btrfs_del_csums could fail. We need to return the error so the transaction gets aborted properly, fix this by returning ret from btrfs_del_csums in cleanup_ref_head.

Reviewed-by: Qu Wenruo wqu@suse.com CC: stable@vger.kernel.org # 4.19+ Signed-off-by: Josef Bacik josef@toxicpanda.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/extent-tree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1868,7 +1868,7 @@ static int cleanup_ref_head(struct btrfs trace_run_delayed_ref_head(fs_info, head, 0); btrfs_delayed_ref_unlock(head); btrfs_put_delayed_ref_head(head); - return 0; + return ret; }

static struct btrfs_delayed_ref_head *btrfs_obtain_ref_head(

From: Josef Bacik josef@toxicpanda.com

commit f96d44743a44e3332f75d23d2075bb8270900e1d upstream.

Error injection testing uncovered a case where we ended up with invalid link counts on an inode. This happened because we failed to notice an error when updating the inode while replaying the tree log, and committed the transaction with an invalid file system.

Fix this by checking the return value of btrfs_update_inode. This resolved the link count errors I was seeing, and we already properly handle passing up the error values in these paths.

CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Johannes Thumshirn johannes.thumshirn@wdc.com Reviewed-by: Qu Wenruo wqu@suse.com Signed-off-by: Josef Bacik josef@toxicpanda.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/tree-log.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

--- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1574,7 +1574,9 @@ static noinline int add_inode_ref(struct if (ret) goto out;

- btrfs_update_inode(trans, root, BTRFS_I(inode)); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); + if (ret) + goto out; }

ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + namelen; @@ -1749,7 +1751,9 @@ static noinline int fixup_inode_link_cou

if (nlink != inode->i_nlink) { set_nlink(inode, nlink); - btrfs_update_inode(trans, root, BTRFS_I(inode)); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); + if (ret) + goto out; } BTRFS_I(inode)->index_cnt = (u64)-1;

From: Josef Bacik josef@toxicpanda.com

commit dc09ef3562726cd520c8338c1640872a60187af5 upstream.

Error injection stress uncovered a problem where we'd leave a dangling inode ref if we failed during a rename_exchange. This happens because we insert the inode ref for one side of the rename, and then for the other side. If this second inode ref insert fails we'll leave the first one dangling and leave a corrupt file system behind. Fix this by aborting if we did the insert for the first inode ref.

CC: stable@vger.kernel.org # 4.9+ Signed-off-by: Josef Bacik josef@toxicpanda.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/inode.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9088,6 +9088,7 @@ static int btrfs_rename_exchange(struct int ret2; bool root_log_pinned = false; bool dest_log_pinned = false; + bool need_abort = false;

/* we only allow rename subvolume link between subvolumes */ if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest) @@ -9144,6 +9145,7 @@ static int btrfs_rename_exchange(struct old_idx); if (ret) goto out_fail; + need_abort = true; }

/* And now for the dest. */ @@ -9159,8 +9161,11 @@ static int btrfs_rename_exchange(struct new_ino, btrfs_ino(BTRFS_I(old_dir)), new_idx); - if (ret) + if (ret) { + if (need_abort) + btrfs_abort_transaction(trans, ret); goto out_fail; + } }

/* Update inode version and ctime/mtime. */

From: Mina Almasry almasrymina@google.com

[ Upstream commit d84cf06e3dd8c5c5b547b5d8931015fc536678e5 ]

The userfaultfd hugetlb tests cause a resv_huge_pages underflow. This happens when hugetlb_mcopy_atomic_pte() is called with !is_continue on an index for which we already have a page in the cache. When this happens, we allocate a second page, double consuming the reservation, and then fail to insert the page into the cache and return -EEXIST.

To fix this, we first check if there is a page in the cache which already consumed the reservation, and return -EEXIST immediately if so.

There is still a rare condition where we fail to copy the page contents AND race with a call for hugetlb_no_page() for this index and again we will underflow resv_huge_pages. That is fixed in a more complicated patch not targeted for -stable.

Test:

Hacked the code locally such that resv_huge_pages underflows produce a warning, then:

./tools/testing/selftests/vm/userfaultfd hugetlb_shared 10 2 /tmp/kokonut_test/huge/userfaultfd_test && echo test success ./tools/testing/selftests/vm/userfaultfd hugetlb 10 2 /tmp/kokonut_test/huge/userfaultfd_test && echo test success

Both tests succeed and produce no warnings. After the test runs number of free/resv hugepages is correct.

[mike.kravetz@oracle.com: changelog fixes]

Link: https://lkml.kernel.org/r/20210528004649.85298-1-almasrymina@google.com Fixes: 8fb5debc5fcd ("userfaultfd: hugetlbfs: add hugetlb_mcopy_atomic_pte for userfaultfd support") Signed-off-by: Mina Almasry almasrymina@google.com Reviewed-by: Mike Kravetz mike.kravetz@oracle.com Cc: Axel Rasmussen axelrasmussen@google.com Cc: Peter Xu peterx@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- mm/hugetlb.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-)

--- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4705,10 +4705,20 @@ int hugetlb_mcopy_atomic_pte(struct mm_s struct page *page;

if (!*pagep) { - ret = -ENOMEM; + /* If a page already exists, then it's UFFDIO_COPY for + * a non-missing case. Return -EEXIST. + */ + if (vm_shared && + hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { + ret = -EEXIST; + goto out; + } + page = alloc_huge_page(dst_vma, dst_addr, 0); - if (IS_ERR(page)) + if (IS_ERR(page)) { + ret = -ENOMEM; goto out; + }

ret = copy_huge_page_from_user(page, (const void __user *) src_addr,

From: Sean Christopherson seanjc@google.com

commit 0884335a2e653b8a045083aa1d57ce74269ac81d upstream.

Drop bits 63:32 on loads/stores to/from DRs and CRs when the vCPU is not in 64-bit mode. The APM states bits 63:32 are dropped for both DRs and CRs:

In 64-bit mode, the operand size is fixed at 64 bits without the need for a REX prefix. In non-64-bit mode, the operand size is fixed at 32 bits and the upper 32 bits of the destination are forced to 0.

Fixes: 7ff76d58a9dc ("KVM: SVM: enhance MOV CR intercept handler") Fixes: cae3797a4639 ("KVM: SVM: enhance mov DR intercept handler") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson seanjc@google.com Message-Id: 20210422022128.3464144-4-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sudip Mukherjee sudipm.mukherjee@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/svm/svm.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2532,7 +2532,7 @@ static int cr_interception(struct vcpu_s err = 0; if (cr >= 16) { /* mov to cr */ cr -= 16; - val = kvm_register_read(&svm->vcpu, reg); + val = kvm_register_readl(&svm->vcpu, reg); trace_kvm_cr_write(cr, val); switch (cr) { case 0: @@ -2578,7 +2578,7 @@ static int cr_interception(struct vcpu_s kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } - kvm_register_write(&svm->vcpu, reg, val); + kvm_register_writel(&svm->vcpu, reg, val); trace_kvm_cr_read(cr, val); } return kvm_complete_insn_gp(&svm->vcpu, err); @@ -2643,11 +2643,11 @@ static int dr_interception(struct vcpu_s dr = svm->vmcb->control.exit_code - SVM_EXIT_READ_DR0; if (dr >= 16) { /* mov to DRn */ dr -= 16; - val = kvm_register_read(&svm->vcpu, reg); + val = kvm_register_readl(&svm->vcpu, reg); err = kvm_set_dr(&svm->vcpu, dr, val); } else { kvm_get_dr(&svm->vcpu, dr, &val); - kvm_register_write(&svm->vcpu, reg, val); + kvm_register_writel(&svm->vcpu, reg, val); }

return kvm_complete_insn_gp(&svm->vcpu, err);

From: Vitaly Kuznetsov vkuznets@redhat.com

commit c02027b5742b5aa804ef08a4a9db433295533046 upstream.

Currenly, we disable kvmclock from machine_shutdown() hook and this only happens for boot CPU. We need to disable it for all CPUs to guard against memory corruption e.g. on restore from hibernate.

Note, writing '0' to kvmclock MSR doesn't clear memory location, it just prevents hypervisor from updating the location so for the short while after write and while CPU is still alive, the clock remains usable and correct so we don't need to switch to some other clocksource.

Signed-off-by: Vitaly Kuznetsov vkuznets@redhat.com Message-Id: 20210414123544.1060604-4-vkuznets@redhat.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Andrea Righi andrea.righi@canonical.com Signed-off-by: Krzysztof Kozlowski krzysztof.kozlowski@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/kvm_para.h | 4 ++-- arch/x86/kernel/kvm.c | 1 + arch/x86/kernel/kvmclock.c | 5 +---- 3 files changed, 4 insertions(+), 6 deletions(-)

--- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -7,8 +7,6 @@ #include <linux/interrupt.h> #include <uapi/asm/kvm_para.h>

-extern void kvmclock_init(void); - #ifdef CONFIG_KVM_GUEST bool kvm_check_and_clear_guest_paused(void); #else @@ -86,6 +84,8 @@ static inline long kvm_hypercall4(unsign }

#ifdef CONFIG_KVM_GUEST +void kvmclock_init(void); +void kvmclock_disable(void); bool kvm_para_available(void); unsigned int kvm_arch_para_features(void); unsigned int kvm_arch_para_hints(void); --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -468,6 +468,7 @@ static void kvm_guest_cpu_offline(void) wrmsrl(MSR_KVM_PV_EOI_EN, 0); kvm_pv_disable_apf(); apf_task_wake_all(); + kvmclock_disable(); }

static int kvm_cpu_online(unsigned int cpu) --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -220,11 +220,9 @@ static void kvm_crash_shutdown(struct pt } #endif

-static void kvm_shutdown(void) +void kvmclock_disable(void) { native_write_msr(msr_kvm_system_time, 0, 0); - kvm_disable_steal_time(); - native_machine_shutdown(); }

static void __init kvmclock_init_mem(void) @@ -351,7 +349,6 @@ void __init kvmclock_init(void) #endif x86_platform.save_sched_clock_state = kvm_save_sched_clock_state; x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state; - machine_ops.shutdown = kvm_shutdown; #ifdef CONFIG_KEXEC_CORE machine_ops.crash_shutdown = kvm_crash_shutdown; #endif