From: Heiko Thiery heiko.thiery@gmail.com

[ Upstream commit 6a4d7234ae9a3bb31181f348ade9bbdb55aeb5c5 ]

When accessing the timecounter register on an i.MX8MQ the kernel hangs. This is only the case when the interface is down. This can be reproduced by reading with 'phc_ctrl eth0 get'.

Like described in the change in 91c0d987a9788dcc5fe26baafd73bf9242b68900 the igp clock is disabled when the interface is down and leads to a system hang.

So we check if the ptp clock status before reading the timecounter register.

Signed-off-by: Heiko Thiery heiko.thiery@gmail.com Acked-by: Richard Cochran richardcochran@gmail.com Link: https://lore.kernel.org/r/20210225211514.9115-1-heiko.thiery@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/fec_ptp.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 945643c02615..49fad118988b 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -382,9 +382,16 @@ static int fec_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) u64 ns; unsigned long flags;

+ mutex_lock(&adapter->ptp_clk_mutex); + /* Check the ptp clock */ + if (!adapter->ptp_clk_on) { + mutex_unlock(&adapter->ptp_clk_mutex); + return -EINVAL; + } spin_lock_irqsave(&adapter->tmreg_lock, flags); ns = timecounter_read(&adapter->tc); spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + mutex_unlock(&adapter->ptp_clk_mutex);

*ts = ns_to_timespec64(ns);

From: Tong Zhang ztong0001@gmail.com

[ Upstream commit 4deb550bc3b698a1f03d0332cde3df154d1b6c1e ]

label err_eni_release is reachable when eni_start() fail. In eni_start() it calls dev->phy->start() in the last step, if start() fail we don't need to call phy->stop(), if start() is never called, we neither need to call phy->stop(), otherwise null-ptr-deref will happen.

In order to fix this issue, don't call phy->stop() in label err_eni_release

[ 4.875714] ================================================================== [ 4.876091] BUG: KASAN: null-ptr-deref in suni_stop+0x47/0x100 [suni] [ 4.876433] Read of size 8 at addr 0000000000000030 by task modprobe/95 [ 4.876778] [ 4.876862] CPU: 0 PID: 95 Comm: modprobe Not tainted 5.11.0-rc7-00090-gdcc0b49040c7 #2 [ 4.877290] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-48-gd94 [ 4.877876] Call Trace: [ 4.878009] dump_stack+0x7d/0xa3 [ 4.878191] kasan_report.cold+0x10c/0x10e [ 4.878410] ? __slab_free+0x2f0/0x340 [ 4.878612] ? suni_stop+0x47/0x100 [suni] [ 4.878832] suni_stop+0x47/0x100 [suni] [ 4.879043] eni_do_release+0x3b/0x70 [eni] [ 4.879269] eni_init_one.cold+0x1152/0x1747 [eni] [ 4.879528] ? _raw_spin_lock_irqsave+0x7b/0xd0 [ 4.879768] ? eni_ioctl+0x270/0x270 [eni] [ 4.879990] ? __mutex_lock_slowpath+0x10/0x10 [ 4.880226] ? eni_ioctl+0x270/0x270 [eni] [ 4.880448] local_pci_probe+0x6f/0xb0 [ 4.880650] pci_device_probe+0x171/0x240 [ 4.880864] ? pci_device_remove+0xe0/0xe0 [ 4.881086] ? kernfs_create_link+0xb6/0x110 [ 4.881315] ? sysfs_do_create_link_sd.isra.0+0x76/0xe0 [ 4.881594] really_probe+0x161/0x420 [ 4.881791] driver_probe_device+0x6d/0xd0 [ 4.882010] device_driver_attach+0x82/0x90 [ 4.882233] ? device_driver_attach+0x90/0x90 [ 4.882465] __driver_attach+0x60/0x100 [ 4.882671] ? device_driver_attach+0x90/0x90 [ 4.882903] bus_for_each_dev+0xe1/0x140 [ 4.883114] ? subsys_dev_iter_exit+0x10/0x10 [ 4.883346] ? klist_node_init+0x61/0x80 [ 4.883557] bus_add_driver+0x254/0x2a0 [ 4.883764] driver_register+0xd3/0x150 [ 4.883971] ? 0xffffffffc0038000 [ 4.884149] do_one_initcall+0x84/0x250 [ 4.884355] ? trace_event_raw_event_initcall_finish+0x150/0x150 [ 4.884674] ? unpoison_range+0xf/0x30 [ 4.884875] ? ____kasan_kmalloc.constprop.0+0x84/0xa0 [ 4.885150] ? unpoison_range+0xf/0x30 [ 4.885352] ? unpoison_range+0xf/0x30 [ 4.885557] do_init_module+0xf8/0x350 [ 4.885760] load_module+0x3fe6/0x4340 [ 4.885960] ? vm_unmap_ram+0x1d0/0x1d0 [ 4.886166] ? ____kasan_kmalloc.constprop.0+0x84/0xa0 [ 4.886441] ? module_frob_arch_sections+0x20/0x20 [ 4.886697] ? __do_sys_finit_module+0x108/0x170 [ 4.886941] __do_sys_finit_module+0x108/0x170 [ 4.887178] ? __ia32_sys_init_module+0x40/0x40 [ 4.887419] ? file_open_root+0x200/0x200 [ 4.887634] ? do_sys_open+0x85/0xe0 [ 4.887826] ? filp_open+0x50/0x50 [ 4.888009] ? fpregs_assert_state_consistent+0x4d/0x60 [ 4.888287] ? exit_to_user_mode_prepare+0x2f/0x130 [ 4.888547] do_syscall_64+0x33/0x40 [ 4.888739] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 4.889010] RIP: 0033:0x7ff62fcf1cf7 [ 4.889202] Code: 48 89 57 30 48 8b 04 24 48 89 47 38 e9 1d a0 02 00 48 89 f8 48 89 f71 [ 4.890172] RSP: 002b:00007ffe6644ade8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 [ 4.890570] RAX: ffffffffffffffda RBX: 0000000000f2ca70 RCX: 00007ff62fcf1cf7 [ 4.890944] RDX: 0000000000000000 RSI: 0000000000f2b9e0 RDI: 0000000000000003 [ 4.891318] RBP: 0000000000000003 R08: 0000000000000000 R09: 0000000000000001 [ 4.891691] R10: 00007ff62fd55300 R11: 0000000000000246 R12: 0000000000f2b9e0 [ 4.892064] R13: 0000000000000000 R14: 0000000000f2bdd0 R15: 0000000000000001 [ 4.892439] ==================================================================

Signed-off-by: Tong Zhang ztong0001@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/atm/eni.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c index bedaebd5a495..de52428b8833 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -2281,7 +2281,8 @@ static int eni_init_one(struct pci_dev *pci_dev, return rc;

err_eni_release: - eni_do_release(dev); + dev->phy = NULL; + iounmap(ENI_DEV(dev)->ioaddr); err_unregister: atm_dev_deregister(dev); err_free_consistent:

From: Hayes Wang hayeswang@realtek.com

[ Upstream commit 4b5dc1a94d4f92b5845e98bd9ae344b26d933aad ]

This reverts commit 134f98bcf1b898fb9d6f2b91bc85dd2e5478b4b8.

The r8153_mac_clk_spd() is used for RTL8153A only, because the register table of RTL8153B is different from RTL8153A. However, this function would be called when RTL8153B calls r8153_first_init() and r8153_enter_oob(). That causes RTL8153B becomes unstable when suspending and resuming. The worst case may let the device stop working.

Besides, revert this commit to disable MAC clock speed down for RTL8153A. It would avoid the known issue when enabling U1. The data of the first control transfer may be wrong when exiting U1.

Signed-off-by: Hayes Wang hayeswang@realtek.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/r8152.c | 35 ++++++----------------------------- 1 file changed, 6 insertions(+), 29 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 22f093797f41..486cf511d2bf 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -2836,29 +2836,6 @@ static void __rtl_set_wol(struct r8152 *tp, u32 wolopts) device_set_wakeup_enable(&tp->udev->dev, false); }

-static void r8153_mac_clk_spd(struct r8152 *tp, bool enable) -{ - /* MAC clock speed down */ - if (enable) { - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, - ALDPS_SPDWN_RATIO); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, - EEE_SPDWN_RATIO); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, - PKT_AVAIL_SPDWN_EN | SUSPEND_SPDWN_EN | - U1U2_SPDWN_EN | L1_SPDWN_EN); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4, - PWRSAVE_SPDWN_EN | RXDV_SPDWN_EN | TX10MIDLE_EN | - TP100_SPDWN_EN | TP500_SPDWN_EN | EEE_SPDWN_EN | - TP1000_SPDWN_EN); - } else { - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, 0); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, 0); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, 0); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4, 0); - } -} - static void r8153_u1u2en(struct r8152 *tp, bool enable) { u8 u1u2[8]; @@ -3158,11 +3135,9 @@ static void rtl8153_runtime_enable(struct r8152 *tp, bool enable) if (enable) { r8153_u1u2en(tp, false); r8153_u2p3en(tp, false); - r8153_mac_clk_spd(tp, true); rtl_runtime_suspend_enable(tp, true); } else { rtl_runtime_suspend_enable(tp, false); - r8153_mac_clk_spd(tp, false);

switch (tp->version) { case RTL_VER_03: @@ -3727,7 +3702,6 @@ static void r8153_first_init(struct r8152 *tp) u32 ocp_data; int i;

- r8153_mac_clk_spd(tp, false); rxdy_gated_en(tp, true); r8153_teredo_off(tp);

@@ -3789,8 +3763,6 @@ static void r8153_enter_oob(struct r8152 *tp) u32 ocp_data; int i;

- r8153_mac_clk_spd(tp, true); - ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL); ocp_data &= ~NOW_IS_OOB; ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data); @@ -4498,9 +4470,14 @@ static void r8153_init(struct r8152 *tp)

ocp_write_word(tp, MCU_TYPE_USB, USB_CONNECT_TIMER, 0x0001);

+ /* MAC clock speed down */ + ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, 0); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, 0); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, 0); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4, 0); + r8153_power_cut_en(tp, false); r8153_u1u2en(tp, true); - r8153_mac_clk_spd(tp, false); usb_enable_lpm(tp->udev);

ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6);

From: Dinghao Liu dinghao.liu@zju.edu.cn

[ Upstream commit 7a766381634da19fc837619b0a34590498d9d29a ]

When ixgbe_fdir_write_perfect_filter_82599() fails, input allocated by kzalloc() has not been freed, which leads to memleak.

Signed-off-by: Dinghao Liu dinghao.liu@zju.edu.cn Reviewed-by: Paul Menzel pmenzel@molgen.mpg.de 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/ixgbe/ixgbe_main.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index f60554064403..1b8e70585c44 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -9595,8 +9595,10 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter, ixgbe_atr_compute_perfect_hash_82599(&input->filter, mask); err = ixgbe_fdir_write_perfect_filter_82599(hw, &input->filter, input->sw_idx, queue); - if (!err) - ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx); + if (err) + goto err_out_w_lock; + + ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx); spin_unlock(&adapter->fdir_perfect_lock);

if ((uhtid != 0x800) && (adapter->jump_tables[uhtid]))

From: Jia-Ju Bai baijiaju1990@gmail.com

[ Upstream commit 6650d31f21b8a0043613ae0a4a2e42e49dc20b2d ]

When iavf_process_config() fails, no error return code of iavf_init_get_resources() is assigned. To fix this bug, err is assigned with the return value of iavf_process_config(), and then err is checked.

Reported-by: TOTE Robot oslab@tsinghua.edu.cn Signed-off-by: Jia-Ju Bai baijiaju1990@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/iavf/iavf_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 56e6bec9af79..cffc8c1044f2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1786,7 +1786,8 @@ static int iavf_init_get_resources(struct iavf_adapter *adapter) goto err_alloc; }

- if (iavf_process_config(adapter)) + err = iavf_process_config(adapter); + if (err) goto err_alloc; adapter->current_op = VIRTCHNL_OP_UNKNOWN;

From: Michael Braun michael-dev@fami-braun.de

[ Upstream commit d8861bab48b6c1fc3cdbcab8ff9d1eaea43afe7f ]

When using jumbo packets and overrunning rx queue with napi enabled, the following sequence is observed in gfar_add_rx_frag:

| lstatus | | skb | t | lstatus, size, flags | first | len, data_len, *ptr | ---+--------------------------------------+-------+-----------------------+ 13 | 18002348, 9032, INTERRUPT LAST | 0 | 9600, 8000, f554c12e | 12 | 10000640, 1600, INTERRUPT | 0 | 8000, 6400, f554c12e | 11 | 10000640, 1600, INTERRUPT | 0 | 6400, 4800, f554c12e | 10 | 10000640, 1600, INTERRUPT | 0 | 4800, 3200, f554c12e | 09 | 10000640, 1600, INTERRUPT | 0 | 3200, 1600, f554c12e | 08 | 14000640, 1600, INTERRUPT FIRST | 0 | 1600, 0, f554c12e | 07 | 14000640, 1600, INTERRUPT FIRST | 1 | 0, 0, f554c12e | 06 | 1c000080, 128, INTERRUPT LAST FIRST | 1 | 0, 0, abf3bd6e | 05 | 18002348, 9032, INTERRUPT LAST | 0 | 8000, 6400, c5a57780 | 04 | 10000640, 1600, INTERRUPT | 0 | 6400, 4800, c5a57780 | 03 | 10000640, 1600, INTERRUPT | 0 | 4800, 3200, c5a57780 | 02 | 10000640, 1600, INTERRUPT | 0 | 3200, 1600, c5a57780 | 01 | 10000640, 1600, INTERRUPT | 0 | 1600, 0, c5a57780 | 00 | 14000640, 1600, INTERRUPT FIRST | 1 | 0, 0, c5a57780 |

So at t=7 a new packets is started but not finished, probably due to rx overrun - but rx overrun is not indicated in the flags. Instead a new packets starts at t=8. This results in skb->len to exceed size for the LAST fragment at t=13 and thus a negative fragment size added to the skb.

This then crashes:

kernel BUG at include/linux/skbuff.h:2277! Oops: Exception in kernel mode, sig: 5 [#1] ... NIP [c04689f4] skb_pull+0x2c/0x48 LR [c03f62ac] gfar_clean_rx_ring+0x2e4/0x844 Call Trace: [ec4bfd38] [c06a84c4] _raw_spin_unlock_irqrestore+0x60/0x7c (unreliable) [ec4bfda8] [c03f6a44] gfar_poll_rx_sq+0x48/0xe4 [ec4bfdc8] [c048d504] __napi_poll+0x54/0x26c [ec4bfdf8] [c048d908] net_rx_action+0x138/0x2c0 [ec4bfe68] [c06a8f34] __do_softirq+0x3a4/0x4fc [ec4bfed8] [c0040150] run_ksoftirqd+0x58/0x70 [ec4bfee8] [c0066ecc] smpboot_thread_fn+0x184/0x1cc [ec4bff08] [c0062718] kthread+0x140/0x144 [ec4bff38] [c0012350] ret_from_kernel_thread+0x14/0x1c

This patch fixes this by checking for computed LAST fragment size, so a negative sized fragment is never added. In order to prevent the newer rx frame from getting corrupted, the FIRST flag is checked to discard the incomplete older frame.

Signed-off-by: Michael Braun michael-dev@fami-braun.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/gianfar.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 5cb58ab1eec9..a8959a092344 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -2388,6 +2388,10 @@ static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus, if (lstatus & BD_LFLAG(RXBD_LAST)) size -= skb->len;

+ WARN(size < 0, "gianfar: rx fragment size underflow"); + if (size < 0) + return false; + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, rxb->page_offset + RXBUF_ALIGNMENT, size, GFAR_RXB_TRUESIZE); @@ -2550,6 +2554,17 @@ static int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, if (lstatus & BD_LFLAG(RXBD_EMPTY)) break;

+ /* lost RXBD_LAST descriptor due to overrun */ + if (skb && + (lstatus & BD_LFLAG(RXBD_FIRST))) { + /* discard faulty buffer */ + dev_kfree_skb(skb); + skb = NULL; + rx_queue->stats.rx_dropped++; + + /* can continue normally */ + } + /* order rx buffer descriptor reads */ rmb();

From: Sudeep Holla sudeep.holla@arm.com

[ Upstream commit fbb31cb805fd3574d3be7defc06a7fd2fd9af7d2 ]

Add "arm,vexpress" to cpufreq-dt-platdev blacklist since the actual scaling is handled by the firmware cpufreq drivers(scpi, scmi and vexpress-spc).

Signed-off-by: Sudeep Holla sudeep.holla@arm.com Signed-off-by: Viresh Kumar viresh.kumar@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/cpufreq/cpufreq-dt-platdev.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index bca8d1f47fd2..1200842c3da4 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -103,6 +103,8 @@ static const struct of_device_id whitelist[] __initconst = { static const struct of_device_id blacklist[] __initconst = { { .compatible = "allwinner,sun50i-h6", },

+ { .compatible = "arm,vexpress", }, + { .compatible = "calxeda,highbank", }, { .compatible = "calxeda,ecx-2000", },

From: Timo Rothenpieler timo@rothenpieler.org

[ Upstream commit a0590473c5e6c4ef17c3132ad08fbad170f72d55 ]

This follows what was done in 8c2fabc6542d9d0f8b16bd1045c2eda59bdcde13. With the default being m, it's impossible to build the module into the kernel.

Signed-off-by: Timo Rothenpieler timo@rothenpieler.org Signed-off-by: Anna Schumaker Anna.Schumaker@Netapp.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index e7dd07f47825..e84c187d942e 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -127,7 +127,7 @@ config PNFS_BLOCK config PNFS_FLEXFILE_LAYOUT tristate depends on NFS_V4_1 && NFS_V3 - default m + default NFS_V4

config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN string "NFSv4.1 Implementation ID Domain"

From: Jia-Ju Bai baijiaju1990@gmail.com

[ Upstream commit 143c253f42bad20357e7e4432087aca747c43384 ]

When hns_assemble_skb() returns NULL to skb, no error return code of hns_nic_clear_all_rx_fetch() is assigned. To fix this bug, ret is assigned with -ENOMEM in this case.

Reported-by: TOTE Robot oslab@tsinghua.edu.cn Signed-off-by: Jia-Ju Bai baijiaju1990@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 6d5d53cfc7ab..7516f6823090 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1677,8 +1677,10 @@ static int hns_nic_clear_all_rx_fetch(struct net_device *ndev) for (j = 0; j < fetch_num; j++) { /* alloc one skb and init */ skb = hns_assemble_skb(ndev); - if (!skb) + if (!skb) { + ret = -ENOMEM; goto out; + } rd = &tx_ring_data(priv, skb->queue_mapping); hns_nic_net_xmit_hw(ndev, skb, rd);

From: Paul Cercueil paul@crapouillou.net

[ Upstream commit 2e2696223676d56db1a93acfca722c1b96cd552d ]

The second IRQ line really is optional, so use platform_get_irq_optional() to obtain it.

Signed-off-by: Paul Cercueil paul@crapouillou.net Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/davicom/dm9000.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 0928bec79fe4..4b958681d66e 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1512,7 +1512,7 @@ dm9000_probe(struct platform_device *pdev) goto out; }

- db->irq_wake = platform_get_irq(pdev, 1); + db->irq_wake = platform_get_irq_optional(pdev, 1); if (db->irq_wake >= 0) { dev_dbg(db->dev, "wakeup irq %d\n", db->irq_wake);

From: Tong Zhang ztong0001@gmail.com

[ Upstream commit 4416e98594dc04590ebc498fc4e530009535c511 ]

this one is similar to the phy_data allocation fix in uPD98402, the driver allocate the idt77105_priv and store to dev_data but later dereference using dev->dev_data, which will cause null-ptr-dereference.

fix this issue by changing dev_data to phy_data so that PRIV(dev) can work correctly.

Signed-off-by: Tong Zhang ztong0001@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/atm/idt77105.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/atm/idt77105.c b/drivers/atm/idt77105.c index 63871859e6e8..52c2878b755d 100644 --- a/drivers/atm/idt77105.c +++ b/drivers/atm/idt77105.c @@ -262,7 +262,7 @@ static int idt77105_start(struct atm_dev *dev) { unsigned long flags;

- if (!(dev->dev_data = kmalloc(sizeof(struct idt77105_priv),GFP_KERNEL))) + if (!(dev->phy_data = kmalloc(sizeof(struct idt77105_priv),GFP_KERNEL))) return -ENOMEM; PRIV(dev)->dev = dev; spin_lock_irqsave(&idt77105_priv_lock, flags); @@ -337,7 +337,7 @@ static int idt77105_stop(struct atm_dev *dev) else idt77105_all = walk->next; dev->phy = NULL; - dev->dev_data = NULL; + dev->phy_data = NULL; kfree(walk); break; }

From: Paul Cercueil paul@crapouillou.net

[ Upstream commit 5fbecd2389f48e1415799c63130d0cdce1cf3f60 ]

Add support for the interrupt controller found in the JZ4760 SoC, which works exactly like the one in the JZ4770.

Signed-off-by: Paul Cercueil paul@crapouillou.net Signed-off-by: Marc Zyngier maz@kernel.org Link: https://lore.kernel.org/r/20210307172014.73481-2-paul@crapouillou.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/irqchip/irq-ingenic-tcu.c | 1 + drivers/irqchip/irq-ingenic.c | 1 + 2 files changed, 2 insertions(+)

diff --git a/drivers/irqchip/irq-ingenic-tcu.c b/drivers/irqchip/irq-ingenic-tcu.c index 6d05cefe9d79..02a82723a57a 100644 --- a/drivers/irqchip/irq-ingenic-tcu.c +++ b/drivers/irqchip/irq-ingenic-tcu.c @@ -179,4 +179,5 @@ static int __init ingenic_tcu_irq_init(struct device_node *np, } IRQCHIP_DECLARE(jz4740_tcu_irq, "ingenic,jz4740-tcu", ingenic_tcu_irq_init); IRQCHIP_DECLARE(jz4725b_tcu_irq, "ingenic,jz4725b-tcu", ingenic_tcu_irq_init); +IRQCHIP_DECLARE(jz4760_tcu_irq, "ingenic,jz4760-tcu", ingenic_tcu_irq_init); IRQCHIP_DECLARE(jz4770_tcu_irq, "ingenic,jz4770-tcu", ingenic_tcu_irq_init); diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c index dda512dfe2c1..31bc11f15bfa 100644 --- a/drivers/irqchip/irq-ingenic.c +++ b/drivers/irqchip/irq-ingenic.c @@ -168,6 +168,7 @@ static int __init intc_2chip_of_init(struct device_node *node, { return ingenic_intc_of_init(node, 2); } +IRQCHIP_DECLARE(jz4760_intc, "ingenic,jz4760-intc", intc_2chip_of_init); IRQCHIP_DECLARE(jz4770_intc, "ingenic,jz4770-intc", intc_2chip_of_init); IRQCHIP_DECLARE(jz4775_intc, "ingenic,jz4775-intc", intc_2chip_of_init); IRQCHIP_DECLARE(jz4780_intc, "ingenic,jz4780-intc", intc_2chip_of_init);

From: Tomer Tayar ttayar@habana.ai

[ Upstream commit 27ac5aada024e0821c86540ad18f37edadd77d5e ]

The refcount of the "hl_fpriv" structure is not used for the control device, and thus hl_hpriv_put() is not called when releasing this device. This results with no call to put_pid(), so add it explicitly in hl_device_release_ctrl().

Signed-off-by: Tomer Tayar ttayar@habana.ai Reviewed-by: Oded Gabbay ogabbay@kernel.org Signed-off-by: Oded Gabbay ogabbay@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/misc/habanalabs/device.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index 3486bf33474d..e3d943c65419 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -108,6 +108,8 @@ static int hl_device_release_ctrl(struct inode *inode, struct file *filp) list_del(&hpriv->dev_node); mutex_unlock(&hdev->fpriv_list_lock);

+ put_pid(hpriv->taskpid); + kfree(hpriv);

return 0;

From: satya priya skakit@codeaurora.org

[ Upstream commit e610e072c87a30658479a7b4c51e1801cb3f450c ]

Correct the REGULATOR_LINEAR_RANGE and n_voltges for pmic5_hfsmps515 buck.

Signed-off-by: satya priya skakit@codeaurora.org Link: https://lore.kernel.org/r/1614155592-14060-4-git-send-email-skakit@codeauror... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/regulator/qcom-rpmh-regulator.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c index 68d22acdb037..2de7af13288e 100644 --- a/drivers/regulator/qcom-rpmh-regulator.c +++ b/drivers/regulator/qcom-rpmh-regulator.c @@ -726,8 +726,8 @@ static const struct rpmh_vreg_hw_data pmic5_ftsmps510 = { static const struct rpmh_vreg_hw_data pmic5_hfsmps515 = { .regulator_type = VRM, .ops = &rpmh_regulator_vrm_ops, - .voltage_range = REGULATOR_LINEAR_RANGE(2800000, 0, 4, 16000), - .n_voltages = 5, + .voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 235, 16000), + .n_voltages = 236, .pmic_mode_map = pmic_mode_map_pmic5_smps, .of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode, };

From: Nirmoy Das nirmoy.das@amd.com

[ Upstream commit 521f04f9e3ffc73ef96c776035f8a0a31b4cdd81 ]

FB BO should not be ttm_bo_type_kernel type and amdgpufb_create_pinned_object() pins the FB BO anyway.

Signed-off-by: Nirmoy Das nirmoy.das@amd.com Acked-by: Christian König christian.koenig@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c index eaa5e7b7c19d..fd94a17fb2c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c @@ -146,7 +146,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev, size = mode_cmd->pitches[0] * height; aligned_size = ALIGN(size, PAGE_SIZE); ret = amdgpu_gem_object_create(adev, aligned_size, 0, domain, flags, - ttm_bo_type_kernel, NULL, &gobj); + ttm_bo_type_device, NULL, &gobj); if (ret) { pr_err("failed to allocate framebuffer (%d)\n", aligned_size); return -ENOMEM;

From: Hannes Reinecke hare@suse.de

[ Upstream commit d3589381987ec879b03f8ce3039df57e87f05901 ]

NVME_REQ_CANCELLED is translated into -EINTR in nvme_submit_sync_cmd(), so we should be setting this flags during nvme_cancel_request() to ensure that the callers to nvme_submit_sync_cmd() will get the correct error code when the controller is reset.

Signed-off-by: Hannes Reinecke hare@suse.de Reviewed-by: Keith Busch kbusch@kernel.org Reviewed-by: Sagi Grimberg sagi@grimberg.me Reviewed-by: Chao Leng lengchao@huawei.com Reviewed-by: Daniel Wagner dwagner@suse.de Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/core.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 308f3a28e12a..67ea531e8b34 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -312,6 +312,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved) return true;

nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD; + nvme_req(req)->flags |= NVME_REQ_CANCELLED; blk_mq_complete_request(req); return true; }

From: Dmitry Monakhov dmtrmonakhov@yandex-team.ru

[ Upstream commit abbb5f5929ec6c52574c430c5475c158a65c2a8c ]

This adds a quirk for Samsung PM1725a drive which fixes timeouts and I/O errors due to the fact that the controller does not properly handle the Write Zeroes command, dmesg log:

nvme nvme0: I/O 528 QID 10 timeout, aborting nvme nvme0: I/O 529 QID 10 timeout, aborting nvme nvme0: I/O 530 QID 10 timeout, aborting nvme nvme0: I/O 531 QID 10 timeout, aborting nvme nvme0: I/O 532 QID 10 timeout, aborting nvme nvme0: I/O 533 QID 10 timeout, aborting nvme nvme0: I/O 534 QID 10 timeout, aborting nvme nvme0: I/O 535 QID 10 timeout, aborting nvme nvme0: Abort status: 0x0 nvme nvme0: Abort status: 0x0 nvme nvme0: Abort status: 0x0 nvme nvme0: Abort status: 0x0 nvme nvme0: Abort status: 0x0 nvme nvme0: Abort status: 0x0 nvme nvme0: Abort status: 0x0 nvme nvme0: Abort status: 0x0 nvme nvme0: I/O 528 QID 10 timeout, reset controller nvme nvme0: controller is down; will reset: CSTS=0x3, PCI_STATUS=0x10 nvme nvme0: Device not ready; aborting reset, CSTS=0x3 nvme nvme0: Device not ready; aborting reset, CSTS=0x3 nvme nvme0: Removing after probe failure status: -19 nvme0n1: detected capacity change from 6251233968 to 0 blk_update_request: I/O error, dev nvme0n1, sector 32776 op 0x1:(WRITE) flags 0x3000 phys_seg 6 prio class 0 blk_update_request: I/O error, dev nvme0n1, sector 113319936 op 0x9:(WRITE_ZEROES) flags 0x800 phys_seg 0 prio class 0 Buffer I/O error on dev nvme0n1p2, logical block 1, lost async page write blk_update_request: I/O error, dev nvme0n1, sector 113319680 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 Buffer I/O error on dev nvme0n1p2, logical block 2, lost async page write blk_update_request: I/O error, dev nvme0n1, sector 113319424 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 Buffer I/O error on dev nvme0n1p2, logical block 3, lost async page write blk_update_request: I/O error, dev nvme0n1, sector 113319168 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 Buffer I/O error on dev nvme0n1p2, logical block 4, lost async page write blk_update_request: I/O error, dev nvme0n1, sector 113318912 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 Buffer I/O error on dev nvme0n1p2, logical block 5, lost async page write blk_update_request: I/O error, dev nvme0n1, sector 113318656 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 Buffer I/O error on dev nvme0n1p2, logical block 6, lost async page write blk_update_request: I/O error, dev nvme0n1, sector 113318400 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 blk_update_request: I/O error, dev nvme0n1, sector 113318144 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 blk_update_request: I/O error, dev nvme0n1, sector 113317888 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0

Signed-off-by: Dmitry Monakhov dmtrmonakhov@yandex-team.ru Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/pci.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index fc18738dcf8f..3bee3724e9fa 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3176,6 +3176,7 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, { PCI_DEVICE(0x144d, 0xa822), /* Samsung PM1725a */ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY | + NVME_QUIRK_DISABLE_WRITE_ZEROES| NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE(0x1987, 0x5016), /* Phison E16 */ .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },

From: Daniel Wagner dwagner@suse.de

[ Upstream commit 9ec491447b90ad6a4056a9656b13f0b3a1e83043 ]

register_disk() suppress uevents for devices with the GENHD_FL_HIDDEN but enables uevents at the end again in order to announce disk after possible partitions are created.

When the device is removed the uevents are still on and user land sees 'remove' messages for devices which were never 'add'ed to the system.

KERNEL[95481.571887] remove /devices/virtual/nvme-fabrics/ctl/nvme5/nvme0c5n1 (block)

Let's suppress the uevents for GENHD_FL_HIDDEN by not enabling the uevents at all.

Signed-off-by: Daniel Wagner dwagner@suse.de Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Martin Wilck mwilck@suse.com Link: https://lore.kernel.org/r/20210311151917.136091-1-dwagner@suse.de Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/genhd.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/block/genhd.c b/block/genhd.c index 604f0a2cbc9a..2f6f341a8fbb 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -637,10 +637,8 @@ static void register_disk(struct device *parent, struct gendisk *disk, disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj); disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);

- if (disk->flags & GENHD_FL_HIDDEN) { - dev_set_uevent_suppress(ddev, 0); + if (disk->flags & GENHD_FL_HIDDEN) return; - }

/* No minors to use for partitions */ if (!disk_part_scan_enabled(disk))

From: Sergei Trofimovich slyfox@gentoo.org

[ Upstream commit 61bf318eac2c13356f7bd1c6a05421ef504ccc8a ]

In https://bugs.gentoo.org/769614 Dmitry noticed that `ptrace(PTRACE_GET_SYSCALL_INFO)` does not return error sign properly.

The bug is in mismatch between get/set errors:

static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { return regs->r10 == -1 ? regs->r8:0; }

static inline long syscall_get_return_value(struct task_struct *task, struct pt_regs *regs) { return regs->r8; }

static inline void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, int error, long val) { if (error) { /* error < 0, but ia64 uses > 0 return value */ regs->r8 = -error; regs->r10 = -1; } else { regs->r8 = val; regs->r10 = 0; } }

Tested on v5.10 on rx3600 machine (ia64 9040 CPU).

Link: https://lkml.kernel.org/r/20210221002554.333076-2-slyfox@gentoo.org Link: https://bugs.gentoo.org/769614 Signed-off-by: Sergei Trofimovich slyfox@gentoo.org Reported-by: Dmitry V. Levin ldv@altlinux.org Reviewed-by: Dmitry V. Levin ldv@altlinux.org Cc: John Paul Adrian Glaubitz glaubitz@physik.fu-berlin.de Cc: Oleg Nesterov oleg@redhat.com 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 --- arch/ia64/include/asm/syscall.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/ia64/include/asm/syscall.h b/arch/ia64/include/asm/syscall.h index 6c6f16e409a8..0d23c0049301 100644 --- a/arch/ia64/include/asm/syscall.h +++ b/arch/ia64/include/asm/syscall.h @@ -32,7 +32,7 @@ static inline void syscall_rollback(struct task_struct *task, static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { - return regs->r10 == -1 ? regs->r8:0; + return regs->r10 == -1 ? -regs->r8:0; }

static inline long syscall_get_return_value(struct task_struct *task,

From: Hans de Goede hdegoede@redhat.com

commit 538d2dd0b9920334e6596977a664e9e7bac73703 upstream.

Stop reporting SW_DOCK events because this breaks suspend-on-lid-close.

SW_DOCK should only be reported for docking stations, but all the DSDTs in my DSDT collection which use the intel-vbtn code, always seem to use this for 2-in-1s / convertibles and set SW_DOCK=1 when in laptop-mode (in tandem with setting SW_TABLET_MODE=0).

This causes userspace to think the laptop is docked to a port-replicator and to disable suspend-on-lid-close, which is undesirable.

Map the dock events to KEY_IGNORE to avoid this broken SW_DOCK reporting.

Note this may theoretically cause us to stop reporting SW_DOCK on some device where the 0xCA and 0xCB intel-vbtn events are actually used for reporting docking to a classic docking-station / port-replicator but I'm not aware of any such devices.

Also the most important thing is that we only report SW_DOCK when it reliably reports being docked to a classic docking-station without any false positives, which clearly is not the case here. If there is a chance of reporting false positives then it is better to not report SW_DOCK at all.

Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede hdegoede@redhat.com Link: https://lore.kernel.org/r/20210321163513.72328-1-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/platform/x86/intel-vbtn.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)

--- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -46,8 +46,16 @@ static const struct key_entry intel_vbtn };

static const struct key_entry intel_vbtn_switchmap[] = { - { KE_SW, 0xCA, { .sw = { SW_DOCK, 1 } } }, /* Docked */ - { KE_SW, 0xCB, { .sw = { SW_DOCK, 0 } } }, /* Undocked */ + /* + * SW_DOCK should only be reported for docking stations, but DSDTs using the + * intel-vbtn code, always seem to use this for 2-in-1s / convertibles and set + * SW_DOCK=1 when in laptop-mode (in tandem with setting SW_TABLET_MODE=0). + * This causes userspace to think the laptop is docked to a port-replicator + * and to disable suspend-on-lid-close, which is undesirable. + * Map the dock events to KEY_IGNORE to avoid this broken SW_DOCK reporting. + */ + { KE_IGNORE, 0xCA, { .sw = { SW_DOCK, 1 } } }, /* Docked */ + { KE_IGNORE, 0xCB, { .sw = { SW_DOCK, 0 } } }, /* Undocked */ { KE_SW, 0xCC, { .sw = { SW_TABLET_MODE, 1 } } }, /* Tablet */ { KE_SW, 0xCD, { .sw = { SW_TABLET_MODE, 0 } } }, /* Laptop */ };

From: Phillip Lougher phillip@squashfs.org.uk

commit 8b44ca2b634527151af07447a8090a5f3a043321 upstream.

The checks for maximum metadata block size is missing SQUASHFS_BLOCK_OFFSET (the two byte length count).

Link: https://lkml.kernel.org/r/2069685113.2081245.1614583677427@webmail.123-reg.c... Fixes: f37aa4c7366e23f ("squashfs: add more sanity checks in id lookup") Signed-off-by: Phillip Lougher phillip@squashfs.org.uk Cc: Sean Nyekjaer sean@geanix.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/squashfs/id.c | 6 ++++-- fs/squashfs/xattr_id.c | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-)

--- a/fs/squashfs/id.c +++ b/fs/squashfs/id.c @@ -97,14 +97,16 @@ __le64 *squashfs_read_id_index_table(str start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]);

- if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } }

start = le64_to_cpu(table[indexes - 1]); - if (start >= id_table_start || (id_table_start - start) > SQUASHFS_METADATA_SIZE) { + if (start >= id_table_start || (id_table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -109,14 +109,16 @@ __le64 *squashfs_read_xattr_id_table(str start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]);

- if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } }

start = le64_to_cpu(table[indexes - 1]); - if (start >= table_start || (table_start - start) > SQUASHFS_METADATA_SIZE) { + if (start >= table_start || (table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); }

From: Nick Desaulniers ndesaulniers@google.com

commit 60bcf728ee7c60ac2a1f9a0eaceb3a7b3954cd2b upstream.

LLVM changed the expected function signatures for llvm_gcda_start_file() and llvm_gcda_emit_function() in the clang-11 release. Users of clang-11 or newer may have noticed their kernels failing to boot due to a panic when enabling CONFIG_GCOV_KERNEL=y +CONFIG_GCOV_PROFILE_ALL=y. Fix up the function signatures so calling these functions doesn't panic the kernel.

Link: https://reviews.llvm.org/rGcdd683b516d147925212724b09ec6fb792a40041 Link: https://reviews.llvm.org/rG13a633b438b6500ecad9e4f936ebadf3411d0f44 Link: https://lkml.kernel.org/r/20210312224132.3413602-2-ndesaulniers@google.com Signed-off-by: Nick Desaulniers ndesaulniers@google.com Reported-by: Prasad Sodagudi psodagud@quicinc.com Suggested-by: Nathan Chancellor nathan@kernel.org Reviewed-by: Fangrui Song maskray@google.com Tested-by: Nathan Chancellor nathan@kernel.org Acked-by: Peter Oberparleiter oberpar@linux.ibm.com Reviewed-by: Nathan Chancellor nathan@kernel.org Cc: stable@vger.kernel.org [5.4+] 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 --- kernel/gcov/clang.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+)

--- a/kernel/gcov/clang.c +++ b/kernel/gcov/clang.c @@ -75,7 +75,9 @@ struct gcov_fn_info {

u32 num_counters; u64 *counters; +#if CONFIG_CLANG_VERSION < 110000 const char *function_name; +#endif };

static struct gcov_info *current_info; @@ -105,6 +107,7 @@ void llvm_gcov_init(llvm_gcov_callback w } EXPORT_SYMBOL(llvm_gcov_init);

+#if CONFIG_CLANG_VERSION < 110000 void llvm_gcda_start_file(const char *orig_filename, const char version[4], u32 checksum) { @@ -113,7 +116,17 @@ void llvm_gcda_start_file(const char *or current_info->checksum = checksum; } EXPORT_SYMBOL(llvm_gcda_start_file); +#else +void llvm_gcda_start_file(const char *orig_filename, u32 version, u32 checksum) +{ + current_info->filename = orig_filename; + current_info->version = version; + current_info->checksum = checksum; +} +EXPORT_SYMBOL(llvm_gcda_start_file); +#endif

+#if CONFIG_CLANG_VERSION < 110000 void llvm_gcda_emit_function(u32 ident, const char *function_name, u32 func_checksum, u8 use_extra_checksum, u32 cfg_checksum) { @@ -133,6 +146,24 @@ void llvm_gcda_emit_function(u32 ident, list_add_tail(&info->head, &current_info->functions); } EXPORT_SYMBOL(llvm_gcda_emit_function); +#else +void llvm_gcda_emit_function(u32 ident, u32 func_checksum, + u8 use_extra_checksum, u32 cfg_checksum) +{ + struct gcov_fn_info *info = kzalloc(sizeof(*info), GFP_KERNEL); + + if (!info) + return; + + INIT_LIST_HEAD(&info->head); + info->ident = ident; + info->checksum = func_checksum; + info->use_extra_checksum = use_extra_checksum; + info->cfg_checksum = cfg_checksum; + list_add_tail(&info->head, &current_info->functions); +} +EXPORT_SYMBOL(llvm_gcda_emit_function); +#endif

void llvm_gcda_emit_arcs(u32 num_counters, u64 *counters) { @@ -295,6 +326,7 @@ void gcov_info_add(struct gcov_info *dst } }

+#if CONFIG_CLANG_VERSION < 110000 static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn) { size_t cv_size; /* counter values size */ @@ -322,6 +354,28 @@ err_name: kfree(fn_dup); return NULL; } +#else +static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn) +{ + size_t cv_size; /* counter values size */ + struct gcov_fn_info *fn_dup = kmemdup(fn, sizeof(*fn), + GFP_KERNEL); + if (!fn_dup) + return NULL; + INIT_LIST_HEAD(&fn_dup->head); + + cv_size = fn->num_counters * sizeof(fn->counters[0]); + fn_dup->counters = vmalloc(cv_size); + if (!fn_dup->counters) { + kfree(fn_dup); + return NULL; + } + + memcpy(fn_dup->counters, fn->counters, cv_size); + + return fn_dup; +} +#endif

/** * gcov_info_dup - duplicate profiling data set @@ -362,6 +416,7 @@ err: * gcov_info_free - release memory for profiling data set duplicate * @info: profiling data set duplicate to free */ +#if CONFIG_CLANG_VERSION < 110000 void gcov_info_free(struct gcov_info *info) { struct gcov_fn_info *fn, *tmp; @@ -375,6 +430,20 @@ void gcov_info_free(struct gcov_info *in kfree(info->filename); kfree(info); } +#else +void gcov_info_free(struct gcov_info *info) +{ + struct gcov_fn_info *fn, *tmp; + + list_for_each_entry_safe(fn, tmp, &info->functions, head) { + vfree(fn->counters); + list_del(&fn->head); + kfree(fn); + } + kfree(info->filename); + kfree(info); +} +#endif

#define ITER_STRIDE PAGE_SIZE

From: Horia Geantă horia.geanta@nxp.com

commit 9c3a16f88385e671b63a0de7b82b85e604a80f42 upstream.

Crypto engine (CAAM) on LS1046A platform is configured HW-coherent, mark accordingly the DT node.

As reported by Greg and Sascha, and explained by Robin, lack of "dma-coherent" property for an IP that is configured HW-coherent can lead to problems, e.g. on v5.11:

kernel BUG at drivers/crypto/caam/jr.c:247! Internal error: Oops - BUG: 0 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.11.0-20210225-3-00039-g434215968816-dirty #12 Hardware name: TQ TQMLS1046A SoM on Arkona AT1130 (C300) board (DT) pstate: 60000005 (nZCv daif -PAN -UAO -TCO BTYPE=--) pc : caam_jr_dequeue+0x98/0x57c lr : caam_jr_dequeue+0x98/0x57c sp : ffff800010003d50 x29: ffff800010003d50 x28: ffff8000118d4000 x27: ffff8000118d4328 x26: 00000000000001f0 x25: ffff0008022be480 x24: ffff0008022c6410 x23: 00000000000001f1 x22: ffff8000118d4329 x21: 0000000000004d80 x20: 00000000000001f1 x19: 0000000000000001 x18: 0000000000000020 x17: 0000000000000000 x16: 0000000000000015 x15: ffff800011690230 x14: 2e2e2e2e2e2e2e2e x13: 2e2e2e2e2e2e2020 x12: 3030303030303030 x11: ffff800011700a38 x10: 00000000fffff000 x9 : ffff8000100ada30 x8 : ffff8000116a8a38 x7 : 0000000000000001 x6 : 0000000000000000 x5 : 0000000000000000 x4 : 0000000000000000 x3 : 00000000ffffffff x2 : 0000000000000000 x1 : 0000000000000000 x0 : 0000000000001800 Call trace: caam_jr_dequeue+0x98/0x57c tasklet_action_common.constprop.0+0x164/0x18c tasklet_action+0x44/0x54 __do_softirq+0x160/0x454 __irq_exit_rcu+0x164/0x16c irq_exit+0x1c/0x30 __handle_domain_irq+0xc0/0x13c gic_handle_irq+0x5c/0xf0 el1_irq+0xb4/0x180 arch_cpu_idle+0x18/0x30 default_idle_call+0x3c/0x1c0 do_idle+0x23c/0x274 cpu_startup_entry+0x34/0x70 rest_init+0xdc/0xec arch_call_rest_init+0x1c/0x28 start_kernel+0x4ac/0x4e4 Code: 91392021 912c2000 d377d8c6 97f24d96 (d4210000)

Cc: stable@vger.kernel.org # v4.10+ Fixes: 8126d88162a5 ("arm64: dts: add QorIQ LS1046A SoC support") Link: https://lore.kernel.org/linux-crypto/fe6faa24-d8f7-d18f-adfa-44fa0caa1598@ar... Reported-by: Greg Ungerer gerg@kernel.org Reported-by: Sascha Hauer s.hauer@pengutronix.de Tested-by: Sascha Hauer s.hauer@pengutronix.de Signed-off-by: Horia Geantă horia.geanta@nxp.com Acked-by: Greg Ungerer gerg@kernel.org Acked-by: Li Yang leoyang.li@nxp.com Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi | 1 + 1 file changed, 1 insertion(+)

--- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi @@ -244,6 +244,7 @@ ranges = <0x0 0x00 0x1700000 0x100000>; reg = <0x00 0x1700000 0x0 0x100000>; interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>; + dma-coherent;

sec_jr0: jr@10000 { compatible = "fsl,sec-v5.4-job-ring",

From: Horia Geantă horia.geanta@nxp.com

commit 4fb3a074755b7737c4081cffe0ccfa08c2f2d29d upstream.

Crypto engine (CAAM) on LS1043A platform is configured HW-coherent, mark accordingly the DT node.

Lack of "dma-coherent" property for an IP that is configured HW-coherent can lead to problems, similar to what has been reported for LS1046A.

Cc: stable@vger.kernel.org # v4.8+ Fixes: 63dac35b58f4 ("arm64: dts: ls1043a: add crypto node") Link: https://lore.kernel.org/linux-crypto/fe6faa24-d8f7-d18f-adfa-44fa0caa1598@ar... Signed-off-by: Horia Geantă horia.geanta@nxp.com Acked-by: Li Yang leoyang.li@nxp.com Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi | 1 + 1 file changed, 1 insertion(+)

--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi @@ -241,6 +241,7 @@ ranges = <0x0 0x00 0x1700000 0x100000>; reg = <0x00 0x1700000 0x0 0x100000>; interrupts = <0 75 0x4>; + dma-coherent;

sec_jr0: jr@10000 { compatible = "fsl,sec-v5.4-job-ring",

From: Mimi Zohar zohar@linux.ibm.com

commit 92063f3ca73aab794bd5408d3361fd5b5ea33079 upstream.

The kernel may be built with multiple LSMs, but only a subset may be enabled on the boot command line by specifying "lsm=". Not including "integrity" on the ordered LSM list may result in a NULL deref.

As reported by Dmitry Vyukov: in qemu: qemu-system-x86_64 -enable-kvm -machine q35,nvdimm -cpu max,migratable=off -smp 4 -m 4G,slots=4,maxmem=16G -hda wheezy.img -kernel arch/x86/boot/bzImage -nographic -vga std -soundhw all -usb -usbdevice tablet -bt hci -bt device:keyboard -net user,host=10.0.2.10,hostfwd=tcp::10022-:22 -net nic,model=virtio-net-pci -object memory-backend-file,id=pmem1,share=off,mem-path=/dev/zero,size=64M -device nvdimm,id=nvdimm1,memdev=pmem1 -append "console=ttyS0 root=/dev/sda earlyprintk=serial rodata=n oops=panic panic_on_warn=1 panic=86400 lsm=smack numa=fake=2 nopcid dummy_hcd.num=8" -pidfile vm_pid -m 2G -cpu host

But it crashes on NULL deref in integrity_inode_get during boot:

Run /sbin/init as init process BUG: kernel NULL pointer dereference, address: 000000000000001c PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP KASAN CPU: 3 PID: 1 Comm: swapper/0 Not tainted 5.12.0-rc2+ #97 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-44-g88ab0c15525c-prebuilt.qemu.org 04/01/2014 RIP: 0010:kmem_cache_alloc+0x2b/0x370 mm/slub.c:2920 Code: 57 41 56 41 55 41 54 41 89 f4 55 48 89 fd 53 48 83 ec 10 44 8b 3d d9 1f 90 0b 65 48 8b 04 25 28 00 00 00 48 89 44 24 08 31 c0 <8b> 5f 1c 4cf RSP: 0000:ffffc9000032f9d8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff888017fc4f00 RCX: 0000000000000000 RDX: ffff888040220000 RSI: 0000000000000c40 RDI: 0000000000000000 RBP: 0000000000000000 R08: 0000000000000000 R09: ffff888019263627 R10: ffffffff83937cd1 R11: 0000000000000000 R12: 0000000000000c40 R13: ffff888019263538 R14: 0000000000000000 R15: 0000000000ffffff FS: 0000000000000000(0000) GS:ffff88802d180000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000001c CR3: 000000000b48e000 CR4: 0000000000750ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: integrity_inode_get+0x47/0x260 security/integrity/iint.c:105 process_measurement+0x33d/0x17e0 security/integrity/ima/ima_main.c:237 ima_bprm_check+0xde/0x210 security/integrity/ima/ima_main.c:474 security_bprm_check+0x7d/0xa0 security/security.c:845 search_binary_handler fs/exec.c:1708 [inline] exec_binprm fs/exec.c:1761 [inline] bprm_execve fs/exec.c:1830 [inline] bprm_execve+0x764/0x19a0 fs/exec.c:1792 kernel_execve+0x370/0x460 fs/exec.c:1973 try_to_run_init_process+0x14/0x4e init/main.c:1366 kernel_init+0x11d/0x1b8 init/main.c:1477 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:294 Modules linked in: CR2: 000000000000001c ---[ end trace 22d601a500de7d79 ]---

Since LSMs and IMA may be configured at build time, but not enabled at run time, panic the system if "integrity" was not initialized before use.

Reported-by: Dmitry Vyukov dvyukov@google.com Fixes: 79f7865d844c ("LSM: Introduce "lsm=" for boottime LSM selection") Cc: stable@vger.kernel.org Signed-off-by: Mimi Zohar zohar@linux.ibm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- security/integrity/iint.c | 8 ++++++++ 1 file changed, 8 insertions(+)

--- a/security/integrity/iint.c +++ b/security/integrity/iint.c @@ -98,6 +98,14 @@ struct integrity_iint_cache *integrity_i struct rb_node *node, *parent = NULL; struct integrity_iint_cache *iint, *test_iint;

+ /* + * The integrity's "iint_cache" is initialized at security_init(), + * unless it is not included in the ordered list of LSMs enabled + * on the boot command line. + */ + if (!iint_cache) + panic("%s: lsm=integrity required.\n", __func__); + iint = integrity_iint_find(inode); if (iint) return iint;

From: Mikulas Patocka mpatocka@redhat.com

commit 4edbe1d7bcffcd6269f3b5eb63f710393ff2ec7a upstream.

If there are not any dm devices, we need to zero the "dev" argument in the first structure dm_name_list. However, this can cause out of bounds write, because the "needed" variable is zero and len may be less than eight.

Fix this bug by reporting DM_BUFFER_FULL_FLAG if the result buffer is too small to hold the "nl->dev" value.

Signed-off-by: Mikulas Patocka mpatocka@redhat.com Reported-by: Dan Carpenter dan.carpenter@oracle.com Cc: stable@vger.kernel.org Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/md/dm-ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -529,7 +529,7 @@ static int list_devices(struct file *fil * Grab our output buffer. */ nl = orig_nl = get_result_buffer(param, param_size, &len); - if (len < needed) { + if (len < needed || len < sizeof(nl->dev)) { param->flags |= DM_BUFFER_FULL_FLAG; goto out; }

From: Maciej Fijalkowski maciej.fijalkowski@intel.com

[ Upstream commit edbea922025169c0e5cdca5ebf7bf5374cc5566c ]

Currently, veth_xmit() would call the skb_record_rx_queue() only when there is XDP program loaded on peer interface in native mode.

If peer has XDP prog in generic mode, then netif_receive_generic_xdp() has a call to netif_get_rxqueue(skb), so for multi-queue veth it will not be possible to grab a correct rxq.

To fix that, store queue_mapping independently of XDP prog presence on peer interface.

Fixes: 638264dc9022 ("veth: Support per queue XDP ring") Signed-off-by: Maciej Fijalkowski maciej.fijalkowski@intel.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Acked-by: Toshiaki Makita toshiaki.makita1@gmail.com Link: https://lore.kernel.org/bpf/20210303152903.11172-1-maciej.fijalkowski@intel.... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/veth.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 88cfd63f08a6..44ad412f9a06 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -254,8 +254,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) if (rxq < rcv->real_num_rx_queues) { rq = &rcv_priv->rq[rxq]; rcv_xdp = rcu_access_pointer(rq->xdp_prog); - if (rcv_xdp) - skb_record_rx_queue(skb, rxq); + skb_record_rx_queue(skb, rxq); }

skb_tx_timestamp(skb);

From: Maor Dickman maord@nvidia.com

[ Upstream commit 385d40b042e60aa0b677d7b400a0fefb44bcbaf4 ]

The cited change added offload support for Geneve options without verifying the validity of the options masks, this caused offload of rules with match on Geneve options with class,type and data masks which are zero to fail.

Fix by ignoring the match on Geneve options in case option masks are all zero.

Fixes: 9272e3df3023 ("net/mlx5e: Geneve, Add support for encap/decap flows offload") Signed-off-by: Maor Dickman maord@nvidia.com Reviewed-by: Roi Dayan roid@nvidia.com Reviewed-by: Oz Shlomo ozsh@nvidia.com Reviewed-by: Yevgeny Kliteynik kliteyn@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c index 951ea26d96bc..6d27f69cc7fc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c @@ -227,6 +227,10 @@ static int mlx5e_tc_tun_parse_geneve_options(struct mlx5e_priv *priv, option_key = (struct geneve_opt *)&enc_opts.key->data[0]; option_mask = (struct geneve_opt *)&enc_opts.mask->data[0];

+ if (option_mask->opt_class == 0 && option_mask->type == 0 && + !memchr_inv(option_mask->opt_data, 0, option_mask->length * 4)) + return 0; + if (option_key->length > max_tlv_option_data_len) { NL_SET_ERR_MSG_MOD(extack, "Matching on GENEVE options: unsupported option len");

From: Eric Dumazet edumazet@google.com

[ Upstream commit dd4fa1dae9f4847cc1fd78ca468ad69e16e5db3e ]

macvlan_count_rx() can be called from process context, it is thus necessary to disable preemption before calling u64_stats_update_begin()

syzbot was able to spot this on 32bit arch:

WARNING: CPU: 1 PID: 4632 at include/linux/seqlock.h:271 __seqprop_assert include/linux/seqlock.h:271 [inline] WARNING: CPU: 1 PID: 4632 at include/linux/seqlock.h:271 __seqprop_assert.constprop.0+0xf0/0x11c include/linux/seqlock.h:269 Modules linked in: Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 4632 Comm: kworker/1:3 Not tainted 5.12.0-rc2-syzkaller #0 Hardware name: ARM-Versatile Express Workqueue: events macvlan_process_broadcast Backtrace: [<82740468>] (dump_backtrace) from [<827406dc>] (show_stack+0x18/0x1c arch/arm/kernel/traps.c:252) r7:00000080 r6:60000093 r5:00000000 r4:8422a3c4 [<827406c4>] (show_stack) from [<82751b58>] (__dump_stack lib/dump_stack.c:79 [inline]) [<827406c4>] (show_stack) from [<82751b58>] (dump_stack+0xb8/0xe8 lib/dump_stack.c:120) [<82751aa0>] (dump_stack) from [<82741270>] (panic+0x130/0x378 kernel/panic.c:231) r7:830209b4 r6:84069ea4 r5:00000000 r4:844350d0 [<82741140>] (panic) from [<80244924>] (__warn+0xb0/0x164 kernel/panic.c:605) r3:8404ec8c r2:00000000 r1:00000000 r0:830209b4 r7:0000010f [<80244874>] (__warn) from [<82741520>] (warn_slowpath_fmt+0x68/0xd4 kernel/panic.c:628) r7:81363f70 r6:0000010f r5:83018e50 r4:00000000 [<827414bc>] (warn_slowpath_fmt) from [<81363f70>] (__seqprop_assert include/linux/seqlock.h:271 [inline]) [<827414bc>] (warn_slowpath_fmt) from [<81363f70>] (__seqprop_assert.constprop.0+0xf0/0x11c include/linux/seqlock.h:269) r8:5a109000 r7:0000000f r6:a568dac0 r5:89802300 r4:00000001 [<81363e80>] (__seqprop_assert.constprop.0) from [<81364af0>] (u64_stats_update_begin include/linux/u64_stats_sync.h:128 [inline]) [<81363e80>] (__seqprop_assert.constprop.0) from [<81364af0>] (macvlan_count_rx include/linux/if_macvlan.h:47 [inline]) [<81363e80>] (__seqprop_assert.constprop.0) from [<81364af0>] (macvlan_broadcast+0x154/0x26c drivers/net/macvlan.c:291) r5:89802300 r4:8a927740 [<8136499c>] (macvlan_broadcast) from [<81365020>] (macvlan_process_broadcast+0x258/0x2d0 drivers/net/macvlan.c:317) r10:81364f78 r9:8a86d000 r8:8a9c7e7c r7:8413aa5c r6:00000000 r5:00000000 r4:89802840 [<81364dc8>] (macvlan_process_broadcast) from [<802696a4>] (process_one_work+0x2d4/0x998 kernel/workqueue.c:2275) r10:00000008 r9:8404ec98 r8:84367a02 r7:ddfe6400 r6:ddfe2d40 r5:898dac80 r4:8a86d43c [<802693d0>] (process_one_work) from [<80269dcc>] (worker_thread+0x64/0x54c kernel/workqueue.c:2421) r10:00000008 r9:8a9c6000 r8:84006d00 r7:ddfe2d78 r6:898dac94 r5:ddfe2d40 r4:898dac80 [<80269d68>] (worker_thread) from [<80271f40>] (kthread+0x184/0x1a4 kernel/kthread.c:292) r10:85247e64 r9:898dac80 r8:80269d68 r7:00000000 r6:8a9c6000 r5:89a2ee40 r4:8a97bd00 [<80271dbc>] (kthread) from [<80200114>] (ret_from_fork+0x14/0x20 arch/arm/kernel/entry-common.S:158) Exception stack(0x8a9c7fb0 to 0x8a9c7ff8)

Fixes: 412ca1550cbe ("macvlan: Move broadcasts into a work queue") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Herbert Xu herbert@gondor.apana.org.au Reported-by: syzbot syzkaller@googlegroups.com Acked-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/if_macvlan.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index a367ead4bf4b..e11555989090 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -42,13 +42,14 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, if (likely(success)) { struct vlan_pcpu_stats *pcpu_stats;

- pcpu_stats = this_cpu_ptr(vlan->pcpu_stats); + pcpu_stats = get_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); pcpu_stats->rx_packets++; pcpu_stats->rx_bytes += len; if (multicast) pcpu_stats->rx_multicast++; u64_stats_update_end(&pcpu_stats->syncp); + put_cpu_ptr(vlan->pcpu_stats); } else { this_cpu_inc(vlan->pcpu_stats->rx_errors); }

From: Florian Fainelli f.fainelli@gmail.com

[ Upstream commit 47142ed6c34d544ae9f0463e58d482289cbe0d46 ]

Similar to commit 92696286f3bb37ba50e4bd8d1beb24afb759a799 ("net: bcmgenet: Set phydev->dev_flags only for internal PHYs") we need to qualify the phydev->dev_flags based on whether the port is connected to an internal or external PHY otherwise we risk having a flags collision with a completely different interpretation depending on the driver.

Fixes: aa9aef77c761 ("net: dsa: bcm_sf2: communicate integrated PHY revision to PHY driver") Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/bcm_sf2.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index ca425c15953b..0ee1c0a7b165 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -479,8 +479,10 @@ static u32 bcm_sf2_sw_get_phy_flags(struct dsa_switch *ds, int port) * in bits 15:8 and the patch level in bits 7:0 which is exactly what * the REG_PHY_REVISION register layout is. */ - - return priv->hw_params.gphy_rev; + if (priv->int_phy_mask & BIT(port)) + return priv->hw_params.gphy_rev; + else + return 0; }

static void bcm_sf2_sw_validate(struct dsa_switch *ds, int port,

From: Muhammad Husaini Zulkifli muhammad.husaini.zulkifli@intel.com

[ Upstream commit 9a4a1cdc5ab52118c1f2b216f4240830b6528d32 ]

The Supported Pause Frame always display "No" even though the Advertised pause frame showing the correct setting based on the pause parameters via ethtool. Set bit in link_ksettings to "Supported" for Pause Frame.

Before output: Supported pause frame use: No

Expected output: Supported pause frame use: Symmetric

Fixes: 8c5ad0dae93c ("igc: Add ethtool support") Signed-off-by: Muhammad Husaini Zulkifli muhammad.husaini.zulkifli@intel.com Reviewed-by: Malli C mallikarjuna.chilakala@intel.com Tested-by: Dvora Fuxbrumer dvorax.fuxbrumer@linux.intel.com Acked-by: Sasha Neftin sasha.neftin@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/igc/igc_ethtool.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index d1a25d679b89..cbcb8611ab50 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1690,6 +1690,9 @@ static int igc_get_link_ksettings(struct net_device *netdev, Autoneg); }

+ /* Set pause flow control settings */ + ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); + switch (hw->fc.requested_mode) { case igc_fc_full: ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);

From: Dinghao Liu dinghao.liu@zju.edu.cn

[ Upstream commit b52912b8293f2c496f42583e65599aee606a0c18 ]

There is one e1e_wphy() call in e1000_set_d0_lplu_state_82571 that we have caught its return value but lack further handling. Check and terminate the execution flow just like other e1e_wphy() in this function.

Fixes: bc7f75fa9788 ("[E1000E]: New pci-express e1000 driver (currently for ICH9 devices only)") Signed-off-by: Dinghao Liu dinghao.liu@zju.edu.cn Acked-by: Sasha Neftin sasha.neftin@intel.com Tested-by: Dvora Fuxbrumer dvorax.fuxbrumer@linux.intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/e1000e/82571.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 2c1bab377b2a..1fd4406173a8 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -899,6 +899,8 @@ static s32 e1000_set_d0_lplu_state_82571(struct e1000_hw *hw, bool active) } else { data &= ~IGP02E1000_PM_D0_LPLU; ret_val = e1e_wphy(hw, IGP02E1000_PHY_POWER_MGMT, data); + if (ret_val) + return ret_val; /* LPLU and SmartSpeed are mutually exclusive. LPLU is used * during Dx states where the power conservation is most * important. During driver activity we should enable

From: Dylan Hung dylan_hung@aspeedtech.com

[ Upstream commit 6897087323a2fde46df32917462750c069668b2f ]

The interrupt handler may set the flag to reset the mac in the future, but that flag is not cleared once the reset has occurred.

Fixes: 10cbd6407609 ("ftgmac100: Rework NAPI & interrupts handling") Signed-off-by: Dylan Hung dylan_hung@aspeedtech.com Acked-by: Benjamin Herrenschmidt benh@kernel.crashing.org Reviewed-by: Joel Stanley joel@jms.id.au Signed-off-by: Joel Stanley joel@jms.id.au Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/faraday/ftgmac100.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 1aea22d2540f..4050f81f788c 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1307,6 +1307,7 @@ static int ftgmac100_poll(struct napi_struct *napi, int budget) */ if (unlikely(priv->need_mac_restart)) { ftgmac100_start_hw(priv); + priv->need_mac_restart = false;

/* Re-enable "bad" interrupts */ iowrite32(FTGMAC100_INT_BAD,

From: Florian Westphal fw@strlen.de

[ Upstream commit b58f33d49e426dc66e98ed73afb5d97b15a25f2d ]

Before this change, the mask is never included in the netlink message, so "conntrack -E expect" always prints 0.0.0.0.

In older kernels the l3num callback struct was passed as argument, based on tuple->src.l3num. After the l3num indirection got removed, the call chain is based on m.src.l3num, but this value is 0xffff.

Init l3num to the correct value.

Fixes: f957be9d349a3 ("netfilter: conntrack: remove ctnetlink callbacks from l3 protocol trackers") Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_conntrack_netlink.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index b7f0d52e5f1b..783af451a832 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2680,6 +2680,7 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb, memset(&m, 0xFF, sizeof(m)); memcpy(&m.src.u3, &mask->src.u3, sizeof(m.src.u3)); m.src.u.all = mask->src.u.all; + m.src.l3num = tuple->src.l3num; m.dst.protonum = tuple->dst.protonum;

nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK);

From: Stephane Grosjean s.grosjean@peak-system.com

[ Upstream commit 59ec7b89ed3e921cd0625a8c83f31a30d485fdf8 ]

Since the peak_usb driver also supports the CAN-USB interfaces "PCAN-USB X6" and "PCAN-Chip USB" from PEAK-System GmbH, this patch adds their names to the list of explicitly supported devices.

Fixes: ea8b65b596d7 ("can: usb: Add support of PCAN-Chip USB stamp module") Fixes: f00b534ded60 ("can: peak: Add support for PCAN-USB X6 USB interface") Link: https://lore.kernel.org/r/20210309082128.23125-3-s.grosjean@peak-system.com Signed-off-by: Stephane Grosjean s.grosjean@peak-system.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/can/usb/peak_usb/pcan_usb_fd.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index 96bbdef672bc..17a5641d81b3 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -18,6 +18,8 @@

MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB FD adapter"); MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB Pro FD adapter"); +MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-Chip USB"); +MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB X6 adapter");

#define PCAN_USBPROFD_CHANNEL_COUNT 2 #define PCAN_USBFD_CHANNEL_COUNT 1

From: Jimmy Assarsson extja@kvaser.com

[ Upstream commit 7c6e6bce08f918b64459415f58061d4d6df44994 ]

Under certain circumstances, when switching from Kvaser's linuxcan driver (kvpciefd) to the SocketCAN driver (kvaser_pciefd), the bus load reporting is not disabled. This is flooding the kernel log with prints like: [3485.574677] kvaser_pciefd 0000:02:00.0: Received unexpected packet type 0x00000009

Always put the controller in the expected state, instead of assuming that bus load reporting is inactive.

Note: If bus load reporting is enabled when the driver is loaded, you will still get a number of bus load packages (and printouts), before it is disabled.

Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Link: https://lore.kernel.org/r/20210309091724.31262-1-jimmyassarsson@gmail.com Signed-off-by: Jimmy Assarsson extja@kvaser.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/can/kvaser_pciefd.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 72acd1ba162d..e7a26ec9bdc1 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -57,6 +57,7 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); #define KVASER_PCIEFD_KCAN_STAT_REG 0x418 #define KVASER_PCIEFD_KCAN_MODE_REG 0x41c #define KVASER_PCIEFD_KCAN_BTRN_REG 0x420 +#define KVASER_PCIEFD_KCAN_BUS_LOAD_REG 0x424 #define KVASER_PCIEFD_KCAN_BTRD_REG 0x428 #define KVASER_PCIEFD_KCAN_PWM_REG 0x430 /* Loopback control register */ @@ -947,6 +948,9 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) timer_setup(&can->bec_poll_timer, kvaser_pciefd_bec_poll_timer, 0);

+ /* Disable Bus load reporting */ + iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_BUS_LOAD_REG); + tx_npackets = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NPACKETS_REG); if (((tx_npackets >> KVASER_PCIEFD_KCAN_TX_NPACKETS_MAX_SHIFT) &

From: Tong Zhang ztong0001@gmail.com

[ Upstream commit 6e2fe01dd6f98da6cae8b07cd5cfa67abc70d97d ]

Currently doing modprobe c_can_pci will make the kernel complain:

Unbalanced pm_runtime_enable!

this is caused by pm_runtime_enable() called before pm is initialized.

This fix is similar to 227619c3ff7c, move those pm_enable/disable code to c_can_platform.

Fixes: 4cdd34b26826 ("can: c_can: Add runtime PM support to Bosch C_CAN/D_CAN controller") Link: http://lore.kernel.org/r/20210302025542.987600-1-ztong0001@gmail.com Signed-off-by: Tong Zhang ztong0001@gmail.com Tested-by: Uwe Kleine-König u.kleine-koenig@pengutronix.de Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/can/c_can/c_can.c | 24 +----------------------- drivers/net/can/c_can/c_can_platform.c | 6 +++++- 2 files changed, 6 insertions(+), 24 deletions(-)

diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index 8e9f5620c9a2..f14e739ba3f4 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -212,18 +212,6 @@ static const struct can_bittiming_const c_can_bittiming_const = { .brp_inc = 1, };

-static inline void c_can_pm_runtime_enable(const struct c_can_priv *priv) -{ - if (priv->device) - pm_runtime_enable(priv->device); -} - -static inline void c_can_pm_runtime_disable(const struct c_can_priv *priv) -{ - if (priv->device) - pm_runtime_disable(priv->device); -} - static inline void c_can_pm_runtime_get_sync(const struct c_can_priv *priv) { if (priv->device) @@ -1334,7 +1322,6 @@ static const struct net_device_ops c_can_netdev_ops = {

int register_c_can_dev(struct net_device *dev) { - struct c_can_priv *priv = netdev_priv(dev); int err;

/* Deactivate pins to prevent DRA7 DCAN IP from being @@ -1344,28 +1331,19 @@ int register_c_can_dev(struct net_device *dev) */ pinctrl_pm_select_sleep_state(dev->dev.parent);

- c_can_pm_runtime_enable(priv); - dev->flags |= IFF_ECHO; /* we support local echo */ dev->netdev_ops = &c_can_netdev_ops;

err = register_candev(dev); - if (err) - c_can_pm_runtime_disable(priv); - else + if (!err) devm_can_led_init(dev); - return err; } EXPORT_SYMBOL_GPL(register_c_can_dev);

void unregister_c_can_dev(struct net_device *dev) { - struct c_can_priv *priv = netdev_priv(dev); - unregister_candev(dev); - - c_can_pm_runtime_disable(priv); } EXPORT_SYMBOL_GPL(unregister_c_can_dev);

diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c index b5145a7f874c..f2b0408ce87d 100644 --- a/drivers/net/can/c_can/c_can_platform.c +++ b/drivers/net/can/c_can/c_can_platform.c @@ -29,6 +29,7 @@ #include <linux/list.h> #include <linux/io.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/clk.h> #include <linux/of.h> #include <linux/of_device.h> @@ -385,6 +386,7 @@ static int c_can_plat_probe(struct platform_device *pdev) platform_set_drvdata(pdev, dev); SET_NETDEV_DEV(dev, &pdev->dev);

+ pm_runtime_enable(priv->device); ret = register_c_can_dev(dev); if (ret) { dev_err(&pdev->dev, "registering %s failed (err=%d)\n", @@ -397,6 +399,7 @@ static int c_can_plat_probe(struct platform_device *pdev) return 0;

exit_free_device: + pm_runtime_disable(priv->device); free_c_can_dev(dev); exit: dev_err(&pdev->dev, "probe failed\n"); @@ -407,9 +410,10 @@ exit: static int c_can_plat_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); + struct c_can_priv *priv = netdev_priv(dev);

unregister_c_can_dev(dev); - + pm_runtime_disable(priv->device); free_c_can_dev(dev);

return 0;

From: Torin Cooper-Bennun torin@maxiluxsystems.com

[ Upstream commit e98d9ee64ee2cc9b1d1a8e26610ec4d0392ebe50 ]

For M_CAN peripherals, m_can_rx_handler() was called with quota = 1, which caused any error handling to block RX from taking place until the next time the IRQ handler is called. This had been observed to cause RX to be blocked indefinitely in some cases.

This is fixed by calling m_can_rx_handler with a sensibly high quota.

Fixes: f524f829b75a ("can: m_can: Create a m_can platform framework") Link: https://lore.kernel.org/r/20210303144350.4093750-1-torin@maxiluxsystems.com Suggested-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Torin Cooper-Bennun torin@maxiluxsystems.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/can/m_can/m_can.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index cf72a7e464ec..b2224113987c 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -839,7 +839,7 @@ static int m_can_rx_peripheral(struct net_device *dev) { struct m_can_classdev *cdev = netdev_priv(dev);

- m_can_rx_handler(dev, 1); + m_can_rx_handler(dev, M_CAN_NAPI_WEIGHT);

m_can_enable_all_interrupts(cdev);

From: Louis Peens louis.peens@corigine.com

[ Upstream commit d8ce0275e45ec809a33f98fc080fe7921b720dfb ]

pre_tun_rule flows does not follow the usual add-flow path, instead they are used to update the pre_tun table on the firmware. This means that if the mask-id gets allocated here the firmware will never see the "NFP_FL_META_FLAG_MANAGE_MASK" flag for the specific mask id, which triggers the allocation on the firmware side. This leads to the firmware mask being corrupted and causing all sorts of strange behaviour.

Fixes: f12725d98cbe ("nfp: flower: offload pre-tunnel rules") Signed-off-by: Louis Peens louis.peens@corigine.com Signed-off-by: Simon Horman simon.horman@netronome.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../ethernet/netronome/nfp/flower/metadata.c | 24 +++++++++++++------ 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c index 5defd31d481c..aa06fcb38f8b 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c +++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c @@ -327,8 +327,14 @@ int nfp_compile_flow_metadata(struct nfp_app *app, goto err_free_ctx_entry; }

+ /* Do net allocate a mask-id for pre_tun_rules. These flows are used to + * configure the pre_tun table and are never actually send to the + * firmware as an add-flow message. This causes the mask-id allocation + * on the firmware to get out of sync if allocated here. + */ new_mask_id = 0; - if (!nfp_check_mask_add(app, nfp_flow->mask_data, + if (!nfp_flow->pre_tun_rule.dev && + !nfp_check_mask_add(app, nfp_flow->mask_data, nfp_flow->meta.mask_len, &nfp_flow->meta.flags, &new_mask_id)) { NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot allocate a new mask id"); @@ -359,7 +365,8 @@ int nfp_compile_flow_metadata(struct nfp_app *app, goto err_remove_mask; }

- if (!nfp_check_mask_remove(app, nfp_flow->mask_data, + if (!nfp_flow->pre_tun_rule.dev && + !nfp_check_mask_remove(app, nfp_flow->mask_data, nfp_flow->meta.mask_len, NULL, &new_mask_id)) { NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot release mask id"); @@ -374,8 +381,10 @@ int nfp_compile_flow_metadata(struct nfp_app *app, return 0;

err_remove_mask: - nfp_check_mask_remove(app, nfp_flow->mask_data, nfp_flow->meta.mask_len, - NULL, &new_mask_id); + if (!nfp_flow->pre_tun_rule.dev) + nfp_check_mask_remove(app, nfp_flow->mask_data, + nfp_flow->meta.mask_len, + NULL, &new_mask_id); err_remove_rhash: WARN_ON_ONCE(rhashtable_remove_fast(&priv->stats_ctx_table, &ctx_entry->ht_node, @@ -406,9 +415,10 @@ int nfp_modify_flow_metadata(struct nfp_app *app,

__nfp_modify_flow_metadata(priv, nfp_flow);

- nfp_check_mask_remove(app, nfp_flow->mask_data, - nfp_flow->meta.mask_len, &nfp_flow->meta.flags, - &new_mask_id); + if (!nfp_flow->pre_tun_rule.dev) + nfp_check_mask_remove(app, nfp_flow->mask_data, + nfp_flow->meta.mask_len, &nfp_flow->meta.flags, + &new_mask_id);

/* Update flow payload with mask ids. */ nfp_flow->unmasked_data[NFP_FL_MASK_ID_LOCATION] = new_mask_id;

From: Geetha sowjanya gakula@marvell.com

[ Upstream commit ae2619dd4fccdad9876aa5f900bd85484179c50f ]

Current devlink code try to free already freed irqs as the irq_allocate flag is not cleared after free leading to kernel crash while removing rvu driver. The patch fixes the irq free sequence and clears the irq_allocate flag on free.

Fixes: 7304ac4567bc ("octeontx2-af: Add mailbox IRQ and msg handlers") Signed-off-by: Geetha sowjanya gakula@marvell.com Signed-off-by: Hariprasad Kelam hkelam@marvell.com Signed-off-by: Sunil Kovvuri Goutham sgoutham@marvell.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index e581091c09c4..02b4620f7368 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -1980,8 +1980,10 @@ static void rvu_unregister_interrupts(struct rvu *rvu) INTR_MASK(rvu->hw->total_pfs) & ~1ULL);

for (irq = 0; irq < rvu->num_vec; irq++) { - if (rvu->irq_allocated[irq]) + if (rvu->irq_allocated[irq]) { free_irq(pci_irq_vector(rvu->pdev, irq), rvu); + rvu->irq_allocated[irq] = false; + } }

pci_free_irq_vectors(rvu->pdev);

From: Johan Hovold johan@kernel.org

[ Upstream commit c79a707072fe3fea0e3c92edee6ca85c1e53c29f ]

Set the disconnected flag before releasing the data interface in case netdev registration fails to avoid having the disconnect callback try to deregister the never registered netdev (and trigger a WARN_ON()).

Fixes: 87cf65601e17 ("USB host CDC Phonet network interface driver") Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/cdc-phonet.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index bcabd39d136a..f778172356e6 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -387,6 +387,8 @@ static int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *i

err = register_netdev(dev); if (err) { + /* Set disconnected flag so that disconnect() returns early. */ + pnd->disconnected = 1; usb_driver_release_interface(&usbpn_driver, data_intf); goto out; }

From: Corentin Labbe clabbe@baylibre.com

[ Upstream commit 014dfa26ce1c647af09bf506285ef67e0e3f0a6b ]

MTU cannot be changed on dwmac-sun8i. (ip link set eth0 mtu xxx returning EINVAL) This is due to tx_fifo_size being 0, since this value is used to compute valid MTU range. Like dwmac-sunxi (with commit 806fd188ce2a ("net: stmmac: dwmac-sunxi: Provide TX and RX fifo sizes")) dwmac-sun8i need to have tx and rx fifo sizes set. I have used values from datasheets. After this patch, setting a non-default MTU (like 1000) value works and network is still useable.

Tested-on: sun8i-h3-orangepi-pc Tested-on: sun8i-r40-bananapi-m2-ultra Tested-on: sun50i-a64-bananapi-m64 Tested-on: sun50i-h5-nanopi-neo-plus2 Tested-on: sun50i-h6-pine-h64 Fixes: 9f93ac8d408 ("net-next: stmmac: Add dwmac-sun8i") Reported-by: Belisko Marek marek.belisko@gmail.com Signed-off-by: Corentin Labbe clabbe@baylibre.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index c4c9cbdeb601..2f6258ca9515 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -1206,6 +1206,8 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) plat_dat->init = sun8i_dwmac_init; plat_dat->exit = sun8i_dwmac_exit; plat_dat->setup = sun8i_dwmac_setup; + plat_dat->tx_fifo_size = 4096; + plat_dat->rx_fifo_size = 16384;

ret = sun8i_dwmac_init(pdev, plat_dat->bsp_priv); if (ret)

From: Jean-Philippe Brucker jean-philippe@linaro.org

[ Upstream commit 901ee1d750f29a335423eeb9463c3ca461ca18c2 ]

The vmlinux.h generated from BTF is invalid when building drivers/phy/ti/phy-gmii-sel.c with clang:

vmlinux.h:61702:27: error: array type has incomplete element type ‘struct reg_field’ 61702 | const struct reg_field (*regfields)[3]; | ^~~~~~~~~

bpftool generates a forward declaration for this struct regfield, which compilers aren't happy about. Here's a simplified reproducer:

struct inner { int val; }; struct outer { struct inner (*ptr_to_array)[2]; } A;

After build with clang -> bpftool btf dump c -> clang/gcc: ./def-clang.h:11:23: error: array has incomplete element type 'struct inner' struct inner (*ptr_to_array)[2];

Member ptr_to_array of struct outer is a pointer to an array of struct inner. In the DWARF generated by clang, struct outer appears before struct inner, so when converting BTF of struct outer into C, bpftool issues a forward declaration to struct inner. With GCC the DWARF info is reversed so struct inner gets fully defined.

That forward declaration is not sufficient when compilers handle an array of the struct, even when it's only used through a pointer. Note that we can trigger the same issue with an intermediate typedef:

struct inner { int val; }; typedef struct inner inner2_t[2]; struct outer { inner2_t *ptr_to_array; } A;

Becomes:

struct inner; typedef struct inner inner2_t[2];

And causes:

./def-clang.h:10:30: error: array has incomplete element type 'struct inner' typedef struct inner inner2_t[2];

To fix this, clear through_ptr whenever we encounter an intermediate array, to make the inner struct part of a strong link and force full declaration.

Fixes: 351131b51c7a ("libbpf: add btf_dump API for BTF-to-C conversion") Signed-off-by: Jean-Philippe Brucker jean-philippe@linaro.org Signed-off-by: Andrii Nakryiko andrii@kernel.org Link: https://lore.kernel.org/bpf/20210319112554.794552-2-jean-philippe@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/lib/bpf/btf_dump.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index d9e386b8f47e..b2fc45250450 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -443,7 +443,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return err;

case BTF_KIND_ARRAY: - return btf_dump_order_type(d, btf_array(t)->type, through_ptr); + return btf_dump_order_type(d, btf_array(t)->type, false);

case BTF_KIND_STRUCT: case BTF_KIND_UNION: {

From: Pavel Tatashin pasha.tatashin@soleen.com

[ Upstream commit 141f8202cfa4192c3af79b6cbd68e7760bb01b5a ]

The ppos points to a position in the old kernel memory (and in case of arm64 in the crash kernel since elfcorehdr is passed as a segment). The function should update the ppos by the amount that was read. This bug is not exposed by accident, but other platforms update this value properly. So, fix it in ARM64 version of elfcorehdr_read() as well.

Signed-off-by: Pavel Tatashin pasha.tatashin@soleen.com Fixes: e62aaeac426a ("arm64: kdump: provide /proc/vmcore file") Reviewed-by: Tyler Hicks tyhicks@linux.microsoft.com Link: https://lore.kernel.org/r/20210319205054.743368-1-pasha.tatashin@soleen.com Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/kernel/crash_dump.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c index e6e284265f19..58303a9ec32c 100644 --- a/arch/arm64/kernel/crash_dump.c +++ b/arch/arm64/kernel/crash_dump.c @@ -64,5 +64,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) { memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count); + *ppos += count; + return count; }

From: Aya Levin ayal@nvidia.com

[ Upstream commit 4eacfe72e3e037e3fc019113df32c39a705148c2 ]

Expose error value when failing to comply to command: $ ethtool --set-priv-flags eth2 rx_cqe_compress [on/off]

Fixes: be7e87f92b58 ("net/mlx5e: Fail safe cqe compressing/moderation mode setting") Signed-off-by: Aya Levin ayal@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/en_ethtool.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 01089c2283d7..e09b4a96a1d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1811,6 +1811,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; + int err;

if (!MLX5_CAP_GEN(mdev, cqe_compression)) return -EOPNOTSUPP; @@ -1820,7 +1821,10 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, return -EINVAL; }

- mlx5e_modify_rx_cqe_compression_locked(priv, enable); + err = mlx5e_modify_rx_cqe_compression_locked(priv, enable); + if (err) + return err; + priv->channels.params.rx_cqe_compress_def = enable;

return 0;

From: Potnuri Bharat Teja bharat@chelsio.com

[ Upstream commit 3408be145a5d6418ff955fe5badde652be90e700 ]

Not setting the ipv6 bit while destroying ipv6 listening servers may result in potential fatal adapter errors due to lookup engine memory hash errors. Therefore always set ipv6 field while destroying ipv6 listening servers.

Fixes: 830662f6f032 ("RDMA/cxgb4: Add support for active and passive open connection with IPv6 address") Link: https://lore.kernel.org/r/20210324190453.8171-1-bharat@chelsio.com Signed-off-by: Potnuri Bharat Teja bharat@chelsio.com Reviewed-by: Leon Romanovsky leonro@nvidia.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/cxgb4/cm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 30e08bcc9afb..3c78f8c32d12 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -3610,13 +3610,13 @@ int c4iw_destroy_listen(struct iw_cm_id *cm_id) ep->com.local_addr.ss_family == AF_INET) { err = cxgb4_remove_server_filter( ep->com.dev->rdev.lldi.ports[0], ep->stid, - ep->com.dev->rdev.lldi.rxq_ids[0], 0); + ep->com.dev->rdev.lldi.rxq_ids[0], false); } else { struct sockaddr_in6 *sin6; c4iw_init_wr_wait(ep->com.wr_waitp); err = cxgb4_remove_server( ep->com.dev->rdev.lldi.ports[0], ep->stid, - ep->com.dev->rdev.lldi.rxq_ids[0], 0); + ep->com.dev->rdev.lldi.rxq_ids[0], true); if (err) goto done; err = c4iw_wait_for_reply(&ep->com.dev->rdev, ep->com.wr_waitp,

From: Mark Tomlinson mark.tomlinson@alliedtelesis.co.nz

[ Upstream commit d3d40f237480abf3268956daf18cdc56edd32834 ]

This reverts commit cc00bcaa589914096edef7fb87ca5cee4a166b5c.

This (and the preceding) patch basically re-implemented the RCU mechanisms of patch 784544739a25. That patch was replaced because of the performance problems that it created when replacing tables. Now, we have the same issue: the call to synchronize_rcu() makes replacing tables slower by as much as an order of magnitude.

Prior to using RCU a script calling "iptables" approx. 200 times was taking 1.16s. With RCU this increased to 11.59s.

Revert these patches and fix the issue in a different way.

Signed-off-by: Mark Tomlinson mark.tomlinson@alliedtelesis.co.nz Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/netfilter/x_tables.h | 5 +-- net/ipv4/netfilter/arp_tables.c | 14 ++++----- net/ipv4/netfilter/ip_tables.c | 14 ++++----- net/ipv6/netfilter/ip6_tables.c | 14 ++++----- net/netfilter/x_tables.c | 49 +++++++++++++++++++++--------- 5 files changed, 56 insertions(+), 40 deletions(-)

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index f5c21b7d2974..1b261c51b3a3 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -227,7 +227,7 @@ struct xt_table { unsigned int valid_hooks;

/* Man behind the curtain... */ - struct xt_table_info __rcu *private; + struct xt_table_info *private;

/* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; @@ -448,9 +448,6 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu)

struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *);

-struct xt_table_info -*xt_table_get_private_protected(const struct xt_table *table); - #ifdef CONFIG_COMPAT #include <net/compat.h>

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 12d242fedffd..680a1320399d 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -203,7 +203,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,

local_bh_disable(); addend = xt_write_recseq_begin(); - private = rcu_access_pointer(table->private); + private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct arpt_entry **)private->jumpstack[cpu]; @@ -649,7 +649,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private;

/* We need atomic snapshot of counters: rest doesn't change * (other than comefrom, which userspace doesn't care @@ -673,7 +673,7 @@ static int copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct arpt_entry *e; struct xt_counters *counters; - struct xt_table_info *private = xt_table_get_private_protected(table); + struct xt_table_info *private = table->private; int ret = 0; void *loc_cpu_entry;

@@ -808,7 +808,7 @@ static int get_info(struct net *net, void __user *user, t = xt_request_find_table_lock(net, NFPROTO_ARP, name); if (!IS_ERR(t)) { struct arpt_getinfo info; - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT struct xt_table_info tmp;

@@ -861,7 +861,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr,

t = xt_find_table_lock(net, NFPROTO_ARP, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private;

if (get.size == private->size) ret = copy_entries_to_user(private->size, @@ -1020,7 +1020,7 @@ static int do_add_counters(struct net *net, const void __user *user, }

local_bh_disable(); - private = xt_table_get_private_protected(t); + private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1357,7 +1357,7 @@ static int compat_copy_entries_to_user(unsigned int total_size, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index cbbc8a7b8278..8c320b7a423c 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -258,7 +258,7 @@ ipt_do_table(struct sk_buff *skb, WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); - private = rcu_access_pointer(table->private); + private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ipt_entry **)private->jumpstack[cpu]; @@ -791,7 +791,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private;

/* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -815,7 +815,7 @@ copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct ipt_entry *e; struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; int ret = 0; const void *loc_cpu_entry;

@@ -965,7 +965,7 @@ static int get_info(struct net *net, void __user *user, t = xt_request_find_table_lock(net, AF_INET, name); if (!IS_ERR(t)) { struct ipt_getinfo info; - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT struct xt_table_info tmp;

@@ -1019,7 +1019,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr,

t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); @@ -1175,7 +1175,7 @@ do_add_counters(struct net *net, const void __user *user, }

local_bh_disable(); - private = xt_table_get_private_protected(t); + private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1570,7 +1570,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 01cdde25eb16..85d8ed970cdc 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -280,7 +280,7 @@ ip6t_do_table(struct sk_buff *skb,

local_bh_disable(); addend = xt_write_recseq_begin(); - private = rcu_access_pointer(table->private); + private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; @@ -807,7 +807,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private;

/* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -831,7 +831,7 @@ copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct ip6t_entry *e; struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; int ret = 0; const void *loc_cpu_entry;

@@ -981,7 +981,7 @@ static int get_info(struct net *net, void __user *user, t = xt_request_find_table_lock(net, AF_INET6, name); if (!IS_ERR(t)) { struct ip6t_getinfo info; - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT struct xt_table_info tmp;

@@ -1036,7 +1036,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr,

t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { - struct xt_table_info *private = xt_table_get_private_protected(t); + struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); @@ -1191,7 +1191,7 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len, }

local_bh_disable(); - private = xt_table_get_private_protected(t); + private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1579,7 +1579,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 8b60fc04c67c..ef6d51a3798b 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1351,14 +1351,6 @@ struct xt_counters *xt_counters_alloc(unsigned int counters) } EXPORT_SYMBOL(xt_counters_alloc);

-struct xt_table_info -*xt_table_get_private_protected(const struct xt_table *table) -{ - return rcu_dereference_protected(table->private, - mutex_is_locked(&xt[table->af].mutex)); -} -EXPORT_SYMBOL(xt_table_get_private_protected); - struct xt_table_info * xt_replace_table(struct xt_table *table, unsigned int num_counters, @@ -1366,6 +1358,7 @@ xt_replace_table(struct xt_table *table, int *error) { struct xt_table_info *private; + unsigned int cpu; int ret;

ret = xt_jumpstack_alloc(newinfo); @@ -1375,20 +1368,47 @@ xt_replace_table(struct xt_table *table, }

/* Do the substitution. */ - private = xt_table_get_private_protected(table); + local_bh_disable(); + private = table->private;

/* Check inside lock: is the old number correct? */ if (num_counters != private->number) { pr_debug("num_counters != table->private->number (%u/%u)\n", num_counters, private->number); + local_bh_enable(); *error = -EAGAIN; return NULL; }

newinfo->initial_entries = private->initial_entries; + /* + * Ensure contents of newinfo are visible before assigning to + * private. + */ + smp_wmb(); + table->private = newinfo; + + /* make sure all cpus see new ->private value */ + smp_wmb();

- rcu_assign_pointer(table->private, newinfo); - synchronize_rcu(); + /* + * Even though table entries have now been swapped, other CPU's + * may still be using the old entries... + */ + local_bh_enable(); + + /* ... so wait for even xt_recseq on all cpus */ + for_each_possible_cpu(cpu) { + seqcount_t *s = &per_cpu(xt_recseq, cpu); + u32 seq = raw_read_seqcount(s); + + if (seq & 1) { + do { + cond_resched(); + cpu_relax(); + } while (seq == raw_read_seqcount(s)); + } + }

#ifdef CONFIG_AUDIT if (audit_enabled) { @@ -1429,12 +1449,12 @@ struct xt_table *xt_register_table(struct net *net, }

/* Simplifies replace_table code. */ - rcu_assign_pointer(table->private, bootstrap); + table->private = bootstrap;

if (!xt_replace_table(table, 0, newinfo, &ret)) goto unlock;

- private = xt_table_get_private_protected(table); + private = table->private; pr_debug("table->private->number = %u\n", private->number);

/* save number of initial entries */ @@ -1457,8 +1477,7 @@ void *xt_unregister_table(struct xt_table *table) struct xt_table_info *private;

mutex_lock(&xt[table->af].mutex); - private = xt_table_get_private_protected(table); - RCU_INIT_POINTER(table->private, NULL); + private = table->private; list_del(&table->list); mutex_unlock(&xt[table->af].mutex); kfree(table);

From: Mark Tomlinson mark.tomlinson@alliedtelesis.co.nz

[ Upstream commit abe7034b9a8d57737e80cc16d60ed3666990bdbf ]

This reverts commit 443d6e86f821a165fae3fc3fc13086d27ac140b1.

This (and the following) patch basically re-implemented the RCU mechanisms of patch 784544739a25. That patch was replaced because of the performance problems that it created when replacing tables. Now, we have the same issue: the call to synchronize_rcu() makes replacing tables slower by as much as an order of magnitude.

Revert these patches and fix the issue in a different way.

Signed-off-by: Mark Tomlinson mark.tomlinson@alliedtelesis.co.nz Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/netfilter/arp_tables.c | 2 +- net/ipv4/netfilter/ip_tables.c | 2 +- net/ipv6/netfilter/ip6_tables.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 680a1320399d..f1f78a742b36 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1406,7 +1406,7 @@ static int compat_get_entries(struct net *net, xt_compat_lock(NFPROTO_ARP); t = xt_find_table_lock(net, NFPROTO_ARP, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; struct xt_table_info info;

ret = compat_table_info(private, &info); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 8c320b7a423c..10b91ebdf213 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1616,7 +1616,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr, xt_compat_lock(AF_INET); t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size) diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 85d8ed970cdc..c973ace208c5 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1625,7 +1625,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, xt_compat_lock(AF_INET6); t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size)

From: Andy Shevchenko andriy.shevchenko@linux.intel.com

[ Upstream commit eb50aaf960e3bedfef79063411ffd670da94b84b ]

The decrementation of acpi_device_bus_id->instance_no in acpi_device_del() is incorrect, because it may cause a duplicate instance number to be allocated next time a device with the same acpi_device_bus_id is added.

Replace above mentioned approach by using IDA framework.

While at it, define the instance range to be [0, 4096).

Fixes: e49bd2dd5a50 ("ACPI: use PNPID:instance_no as bus_id of ACPI device") Fixes: ca9dc8d42b30 ("ACPI / scan: Fix acpi_bus_id_list bookkeeping") Signed-off-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Cc: 4.10+ stable@vger.kernel.org # 4.10+ Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/internal.h | 6 +++++- drivers/acpi/scan.c | 33 ++++++++++++++++++++++++++++----- include/acpi/acpi_bus.h | 1 + 3 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 1db2e1bb72ba..159c422601bc 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -9,6 +9,8 @@ #ifndef _ACPI_INTERNAL_H_ #define _ACPI_INTERNAL_H_

+#include <linux/idr.h> + #define PREFIX "ACPI: "

int early_acpi_osi_init(void); @@ -96,9 +98,11 @@ void acpi_scan_table_handler(u32 event, void *table, void *context);

extern struct list_head acpi_bus_id_list;

+#define ACPI_MAX_DEVICE_INSTANCES 4096 + struct acpi_device_bus_id { const char *bus_id; - unsigned int instance_no; + struct ida instance_ida; struct list_head node; };

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index ddde1229e2b3..dbb5919f23e2 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -483,9 +483,8 @@ static void acpi_device_del(struct acpi_device *device) list_for_each_entry(acpi_device_bus_id, &acpi_bus_id_list, node) if (!strcmp(acpi_device_bus_id->bus_id, acpi_device_hid(device))) { - if (acpi_device_bus_id->instance_no > 0) - acpi_device_bus_id->instance_no--; - else { + ida_simple_remove(&acpi_device_bus_id->instance_ida, device->pnp.instance_no); + if (ida_is_empty(&acpi_device_bus_id->instance_ida)) { list_del(&acpi_device_bus_id->node); kfree_const(acpi_device_bus_id->bus_id); kfree(acpi_device_bus_id); @@ -636,6 +635,21 @@ static struct acpi_device_bus_id *acpi_device_bus_id_match(const char *dev_id) return NULL; }

+static int acpi_device_set_name(struct acpi_device *device, + struct acpi_device_bus_id *acpi_device_bus_id) +{ + struct ida *instance_ida = &acpi_device_bus_id->instance_ida; + int result; + + result = ida_simple_get(instance_ida, 0, ACPI_MAX_DEVICE_INSTANCES, GFP_KERNEL); + if (result < 0) + return result; + + device->pnp.instance_no = result; + dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, result); + return 0; +} + int acpi_device_add(struct acpi_device *device, void (*release)(struct device *)) { @@ -670,7 +684,9 @@ int acpi_device_add(struct acpi_device *device,

acpi_device_bus_id = acpi_device_bus_id_match(acpi_device_hid(device)); if (acpi_device_bus_id) { - acpi_device_bus_id->instance_no++; + result = acpi_device_set_name(device, acpi_device_bus_id); + if (result) + goto err_unlock; } else { acpi_device_bus_id = kzalloc(sizeof(*acpi_device_bus_id), GFP_KERNEL); @@ -686,9 +702,16 @@ int acpi_device_add(struct acpi_device *device, goto err_unlock; }

+ ida_init(&acpi_device_bus_id->instance_ida); + + result = acpi_device_set_name(device, acpi_device_bus_id); + if (result) { + kfree(acpi_device_bus_id); + goto err_unlock; + } + list_add_tail(&acpi_device_bus_id->node, &acpi_bus_id_list); } - dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, acpi_device_bus_id->instance_no);

if (device->parent) list_add_tail(&device->node, &device->parent->children); diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index defed629073b..4d67a67964fa 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -232,6 +232,7 @@ struct acpi_pnp_type {

struct acpi_device_pnp { acpi_bus_id bus_id; /* Object name */ + int instance_no; /* Instance number of this object */ struct acpi_pnp_type type; /* ID type */ acpi_bus_address bus_address; /* _ADR */ char *unique_id; /* _UID */

From: David Jeffery djeffery@redhat.com

[ Upstream commit a958937ff166fc60d1c3a721036f6ff41bfa2821 ]

When a stacked block device inserts a request into another block device using blk_insert_cloned_request, the request's nr_phys_segments field gets recalculated by a call to blk_recalc_rq_segments in blk_cloned_rq_check_limits. But blk_recalc_rq_segments does not know how to handle multi-segment discards. For disk types which can handle multi-segment discards like nvme, this results in discard requests which claim a single segment when it should report several, triggering a warning in nvme and causing nvme to fail the discard from the invalid state.

WARNING: CPU: 5 PID: 191 at drivers/nvme/host/core.c:700 nvme_setup_discard+0x170/0x1e0 [nvme_core] ... nvme_setup_cmd+0x217/0x270 [nvme_core] nvme_loop_queue_rq+0x51/0x1b0 [nvme_loop] __blk_mq_try_issue_directly+0xe7/0x1b0 blk_mq_request_issue_directly+0x41/0x70 ? blk_account_io_start+0x40/0x50 dm_mq_queue_rq+0x200/0x3e0 blk_mq_dispatch_rq_list+0x10a/0x7d0 ? __sbitmap_queue_get+0x25/0x90 ? elv_rb_del+0x1f/0x30 ? deadline_remove_request+0x55/0xb0 ? dd_dispatch_request+0x181/0x210 __blk_mq_do_dispatch_sched+0x144/0x290 ? bio_attempt_discard_merge+0x134/0x1f0 __blk_mq_sched_dispatch_requests+0x129/0x180 blk_mq_sched_dispatch_requests+0x30/0x60 __blk_mq_run_hw_queue+0x47/0xe0 __blk_mq_delay_run_hw_queue+0x15b/0x170 blk_mq_sched_insert_requests+0x68/0xe0 blk_mq_flush_plug_list+0xf0/0x170 blk_finish_plug+0x36/0x50 xlog_cil_committed+0x19f/0x290 [xfs] xlog_cil_process_committed+0x57/0x80 [xfs] xlog_state_do_callback+0x1e0/0x2a0 [xfs] xlog_ioend_work+0x2f/0x80 [xfs] process_one_work+0x1b6/0x350 worker_thread+0x53/0x3e0 ? process_one_work+0x350/0x350 kthread+0x11b/0x140 ? __kthread_bind_mask+0x60/0x60 ret_from_fork+0x22/0x30

This patch fixes blk_recalc_rq_segments to be aware of devices which can have multi-segment discards. It calculates the correct discard segment count by counting the number of bio as each discard bio is considered its own segment.

Fixes: 1e739730c5b9 ("block: optionally merge discontiguous discard bios into a single request") Signed-off-by: David Jeffery djeffery@redhat.com Reviewed-by: Ming Lei ming.lei@redhat.com Reviewed-by: Laurence Oberman loberman@redhat.com Link: https://lore.kernel.org/r/20210211143807.GA115624@redhat Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-merge.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/block/blk-merge.c b/block/blk-merge.c index 86c4c1ef8742..03959bfe961c 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -370,6 +370,14 @@ unsigned int blk_recalc_rq_segments(struct request *rq) switch (bio_op(rq->bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: + if (queue_max_discard_segments(rq->q) > 1) { + struct bio *bio = rq->bio; + + for_each_bio(bio) + nr_phys_segs++; + return nr_phys_segs; + } + return 1; case REQ_OP_WRITE_ZEROES: return 0; case REQ_OP_WRITE_SAME:

From: Jia-Ju Bai baijiaju1990@gmail.com

[ Upstream commit f69953837ca5d98aa983a138dc0b90a411e9c763 ]

When kzalloc() returns NULL to qedi->global_queues[i], no error return code of qedi_alloc_global_queues() is assigned. To fix this bug, status is assigned with -ENOMEM in this case.

Link: https://lore.kernel.org/r/20210308033024.27147-1-baijiaju1990@gmail.com Fixes: ace7f46ba5fd ("scsi: qedi: Add QLogic FastLinQ offload iSCSI driver framework.") Reported-by: TOTE Robot oslab@tsinghua.edu.cn Acked-by: Manish Rangankar mrangankar@marvell.com Signed-off-by: Jia-Ju Bai baijiaju1990@gmail.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/qedi/qedi_main.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index fdd966fea7f6..4498add3d4d6 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -1605,6 +1605,7 @@ static int qedi_alloc_global_queues(struct qedi_ctx *qedi) if (!qedi->global_queues[i]) { QEDI_ERR(&qedi->dbg_ctx, "Unable to allocation global queue %d.\n", i); + status = -ENOMEM; goto mem_alloc_failure; }

From: Thomas Gleixner tglx@linutronix.de

commit 291da9d4a9eb3a1cb0610b7f4480f5b52b1825e7 upstream.

If CONFIG_DEBUG_LOCK_ALLOC=n then mutex_lock_io_nested() maps to mutex_lock() which is clearly wrong because mutex_lock() lacks the io_schedule_prepare()/finish() invocations.

Map it to mutex_lock_io().

Fixes: f21860bac05b ("locking/mutex, sched/wait: Fix the mutex_lock_io_nested() define") Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/878s6fshii.fsf@nanos.tec.linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/mutex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -171,7 +171,7 @@ extern void mutex_lock_io(struct mutex * # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock) # define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock) # define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) -# define mutex_lock_io_nested(lock, subclass) mutex_lock(lock) +# define mutex_lock_io_nested(lock, subclass) mutex_lock_io(lock) #endif

/*

From: Martin Willi martin@strongswan.org

commit 3a5ca857079ea022e0b1b17fc154f7ad7dbc150f upstream.

When a non-initial netns is destroyed, the usual policy is to delete all virtual network interfaces contained, but move physical interfaces back to the initial netns. This keeps the physical interface visible on the system.

CAN devices are somewhat special, as they define rtnl_link_ops even if they are physical devices. If a CAN interface is moved into a non-initial netns, destroying that netns lets the interface vanish instead of moving it back to the initial netns. default_device_exit() skips CAN interfaces due to having rtnl_link_ops set. Reproducer:

ip netns add foo ip link set can0 netns foo ip netns delete foo

WARNING: CPU: 1 PID: 84 at net/core/dev.c:11030 ops_exit_list+0x38/0x60 CPU: 1 PID: 84 Comm: kworker/u4:2 Not tainted 5.10.19 #1 Workqueue: netns cleanup_net [<c010e700>] (unwind_backtrace) from [<c010a1d8>] (show_stack+0x10/0x14) [<c010a1d8>] (show_stack) from [<c086dc10>] (dump_stack+0x94/0xa8) [<c086dc10>] (dump_stack) from [<c086b938>] (__warn+0xb8/0x114) [<c086b938>] (__warn) from [<c086ba10>] (warn_slowpath_fmt+0x7c/0xac) [<c086ba10>] (warn_slowpath_fmt) from [<c0629f20>] (ops_exit_list+0x38/0x60) [<c0629f20>] (ops_exit_list) from [<c062a5c4>] (cleanup_net+0x230/0x380) [<c062a5c4>] (cleanup_net) from [<c0142c20>] (process_one_work+0x1d8/0x438) [<c0142c20>] (process_one_work) from [<c0142ee4>] (worker_thread+0x64/0x5a8) [<c0142ee4>] (worker_thread) from [<c0148a98>] (kthread+0x148/0x14c) [<c0148a98>] (kthread) from [<c0100148>] (ret_from_fork+0x14/0x2c)

To properly restore physical CAN devices to the initial netns on owning netns exit, introduce a flag on rtnl_link_ops that can be set by drivers. For CAN devices setting this flag, default_device_exit() considers them non-virtual, applying the usual namespace move.

The issue was introduced in the commit mentioned below, as at that time CAN devices did not have a dellink() operation.

Fixes: e008b5fc8dc7 ("net: Simplfy default_device_exit and improve batching.") Link: https://lore.kernel.org/r/20210302122423.872326-1-martin@strongswan.org Signed-off-by: Martin Willi martin@strongswan.org Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/can/dev.c | 1 + include/net/rtnetlink.h | 2 ++ net/core/dev.c | 2 +- 3 files changed, 4 insertions(+), 1 deletion(-)

--- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -1226,6 +1226,7 @@ static void can_dellink(struct net_devic

static struct rtnl_link_ops can_link_ops __read_mostly = { .kind = "can", + .netns_refund = true, .maxtype = IFLA_CAN_MAX, .policy = can_policy, .setup = can_setup, --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -33,6 +33,7 @@ static inline int rtnl_msg_family(const * * @list: Used internally * @kind: Identifier + * @netns_refund: Physical device, move to init_net on netns exit * @maxtype: Highest device specific netlink attribute number * @policy: Netlink policy for device specific attribute validation * @validate: Optional validation function for netlink/changelink parameters @@ -64,6 +65,7 @@ struct rtnl_link_ops { size_t priv_size; void (*setup)(struct net_device *dev);

+ bool netns_refund; unsigned int maxtype; const struct nla_policy *policy; int (*validate)(struct nlattr *tb[], --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10121,7 +10121,7 @@ static void __net_exit default_device_ex continue;

/* Leave virtual devices for the generic cleanup */ - if (dev->rtnl_link_ops) + if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund) continue;

/* Push remaining network devices to init_net */

From: Eric Dumazet edumazet@google.com

commit 50535249f624d0072cd885bcdce4e4b6fb770160 upstream.

struct sockaddr_qrtr has a 2-byte hole, and qrtr_recvmsg() currently does not clear it before copying kernel data to user space.

It might be too late to name the hole since sockaddr_qrtr structure is uapi.

BUG: KMSAN: kernel-infoleak in kmsan_copy_to_user+0x9c/0xb0 mm/kmsan/kmsan_hooks.c:249 CPU: 0 PID: 29705 Comm: syz-executor.3 Not tainted 5.11.0-rc7-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x21c/0x280 lib/dump_stack.c:120 kmsan_report+0xfb/0x1e0 mm/kmsan/kmsan_report.c:118 kmsan_internal_check_memory+0x202/0x520 mm/kmsan/kmsan.c:402 kmsan_copy_to_user+0x9c/0xb0 mm/kmsan/kmsan_hooks.c:249 instrument_copy_to_user include/linux/instrumented.h:121 [inline] _copy_to_user+0x1ac/0x270 lib/usercopy.c:33 copy_to_user include/linux/uaccess.h:209 [inline] move_addr_to_user+0x3a2/0x640 net/socket.c:237 ____sys_recvmsg+0x696/0xd50 net/socket.c:2575 ___sys_recvmsg net/socket.c:2610 [inline] do_recvmmsg+0xa97/0x22d0 net/socket.c:2710 __sys_recvmmsg net/socket.c:2789 [inline] __do_sys_recvmmsg net/socket.c:2812 [inline] __se_sys_recvmmsg+0x24a/0x410 net/socket.c:2805 __x64_sys_recvmmsg+0x62/0x80 net/socket.c:2805 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x465f69 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:00007f43659d6188 EFLAGS: 00000246 ORIG_RAX: 000000000000012b RAX: ffffffffffffffda RBX: 000000000056bf60 RCX: 0000000000465f69 RDX: 0000000000000008 RSI: 0000000020003e40 RDI: 0000000000000003 RBP: 00000000004bfa8f R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000010060 R11: 0000000000000246 R12: 000000000056bf60 R13: 0000000000a9fb1f R14: 00007f43659d6300 R15: 0000000000022000

Local variable ----addr@____sys_recvmsg created at: ____sys_recvmsg+0x168/0xd50 net/socket.c:2550 ____sys_recvmsg+0x168/0xd50 net/socket.c:2550

Bytes 2-3 of 12 are uninitialized Memory access of size 12 starts at ffff88817c627b40 Data copied to user address 0000000020000140

Fixes: bdabad3e363d ("net: Add Qualcomm IPC router") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Courtney Cavin courtney.cavin@sonymobile.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/qrtr/qrtr.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -862,6 +862,11 @@ static int qrtr_recvmsg(struct socket *s rc = copied;

if (addr) { + /* There is an anonymous 2-byte hole after sq_family, + * make sure to clear it. + */ + memset(addr, 0, sizeof(*addr)); + cb = (struct qrtr_cb *)skb->cb; addr->sq_family = AF_QIPCRTR; addr->sq_node = cb->src_node;

From: Jan Kara jack@suse.cz

commit 163f0ec1df33cf468509ff38cbcbb5eb0d7fac60 upstream.

Syzbot is reporting that ext4 can enter fs reclaim from kvmalloc() while the transaction is started like:

fs_reclaim_acquire+0x117/0x150 mm/page_alloc.c:4340 might_alloc include/linux/sched/mm.h:193 [inline] slab_pre_alloc_hook mm/slab.h:493 [inline] slab_alloc_node mm/slub.c:2817 [inline] __kmalloc_node+0x5f/0x430 mm/slub.c:4015 kmalloc_node include/linux/slab.h:575 [inline] kvmalloc_node+0x61/0xf0 mm/util.c:587 kvmalloc include/linux/mm.h:781 [inline] ext4_xattr_inode_cache_find fs/ext4/xattr.c:1465 [inline] ext4_xattr_inode_lookup_create fs/ext4/xattr.c:1508 [inline] ext4_xattr_set_entry+0x1ce6/0x3780 fs/ext4/xattr.c:1649 ext4_xattr_ibody_set+0x78/0x2b0 fs/ext4/xattr.c:2224 ext4_xattr_set_handle+0x8f4/0x13e0 fs/ext4/xattr.c:2380 ext4_xattr_set+0x13a/0x340 fs/ext4/xattr.c:2493

This should be impossible since transaction start sets PF_MEMALLOC_NOFS. Add some assertions to the code to catch if something isn't working as expected early.

Link: https://lore.kernel.org/linux-ext4/000000000000563a0205bafb7970@google.com/ Signed-off-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20210222171626.21884-1-jack@suse.cz Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/xattr.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1476,6 +1476,9 @@ ext4_xattr_inode_cache_find(struct inode if (!ce) return NULL;

+ WARN_ON_ONCE(ext4_handle_valid(journal_current_handle()) && + !(current->flags & PF_MEMALLOC_NOFS)); + ea_data = ext4_kvmalloc(value_len, GFP_NOFS); if (!ea_data) { mb_cache_entry_put(ea_inode_cache, ce); @@ -2342,6 +2345,7 @@ ext4_xattr_set_handle(handle_t *handle, error = -ENOSPC; goto cleanup; } + WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); }

error = ext4_reserve_inode_write(handle, inode, &is.iloc);