From: Felix Fietkau nbd@nbd.name

[ Upstream commit 94f0e6256c2ab6803c935634aa1f653174c94879 ]

Modifying the tx buffer list too early can leak DMA mappings

Signed-off-by: Felix Fietkau nbd@nbd.name Signed-off-by: Kalle Valo kvalo@codeaurora.org Link: https://lore.kernel.org/r/20210216135119.23809-2-nbd@nbd.name Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/mediatek/mt76/mt7915/mac.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c index 1b4d65310b88..c9dd6867e125 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c @@ -957,11 +957,6 @@ int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, } txp->nbuf = nbuf;

- /* pass partial skb header to fw */ - tx_info->buf[1].len = MT_CT_PARSE_LEN; - tx_info->buf[1].skip_unmap = true; - tx_info->nbuf = MT_CT_DMA_BUF_NUM; - txp->flags = cpu_to_le16(MT_CT_INFO_APPLY_TXD | MT_CT_INFO_FROM_HOST);

if (!key) @@ -999,6 +994,11 @@ int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, txp->rept_wds_wcid = cpu_to_le16(0x3ff); tx_info->skb = DMA_DUMMY_DATA;

+ /* pass partial skb header to fw */ + tx_info->buf[1].len = MT_CT_PARSE_LEN; + tx_info->buf[1].skip_unmap = true; + tx_info->nbuf = MT_CT_DMA_BUF_NUM; + return 0; }

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 2e344aada4c6..1753807cbf97 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -377,9 +377,16 @@ 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 316a9947541f..b574cce98dc3 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -2260,7 +2260,8 @@ 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 67cd6986634f..fd5ca11c4cbb 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3016,29 +3016,6 @@ 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]; @@ -3338,11 +3315,9 @@ 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: @@ -4678,7 +4653,6 @@ static void r8153_first_init(struct r8152 *tp) { u32 ocp_data;

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

@@ -4729,8 +4703,6 @@ static void r8153_enter_oob(struct r8152 *tp) { u32 ocp_data;

- 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); @@ -5456,10 +5428,15 @@ 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); rtl_runtime_suspend_enable(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 393d1c2cd853..e9c2d28efc81 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -9582,8 +9582,10 @@ 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: Xunlei Pang xlpang@linux.alibaba.com

[ Upstream commit 4f44657d74873735e93a50eb25014721a66aac19 ]

The current blkio.throttle.io_service_bytes_recursive doesn't work correctly.

As an example, for the following blkcg hierarchy: (Made 1GB READ in test1, 512MB READ in test2) test / \ test1 test2

$ head -n 1 test/test1/blkio.throttle.io_service_bytes_recursive 8:0 Read 1073684480 $ head -n 1 test/test2/blkio.throttle.io_service_bytes_recursive 8:0 Read 537448448 $ head -n 1 test/blkio.throttle.io_service_bytes_recursive 8:0 Read 537448448

Clearly, above data of "test" reflects "test2" not "test1"+"test2".

Do the correct summary in blkg_rwstat_recursive_sum().

Signed-off-by: Xunlei Pang xlpang@linux.alibaba.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-cgroup-rwstat.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/block/blk-cgroup-rwstat.c b/block/blk-cgroup-rwstat.c index 85d5790ac49b..3304e841df7c 100644 --- a/block/blk-cgroup-rwstat.c +++ b/block/blk-cgroup-rwstat.c @@ -109,6 +109,7 @@ void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,

lockdep_assert_held(&blkg->q->queue_lock);

+ memset(sum, 0, sizeof(*sum)); rcu_read_lock(); blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) { struct blkg_rwstat *rwstat; @@ -122,7 +123,7 @@ void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, rwstat = (void *)pos_blkg + off;

for (i = 0; i < BLKG_RWSTAT_NR; i++) - sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i); + sum->cnt[i] += blkg_rwstat_read_counter(rwstat, i); } rcu_read_unlock(); }

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 0a867d64d467..dc5b3c06d1e0 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1776,7 +1776,8 @@ 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 d391a45cebb6..4fab2ee5bbf5 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -2391,6 +2391,10 @@ 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); @@ -2553,6 +2557,17 @@ 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: Bob Peterson rpeterso@redhat.com

[ Upstream commit 1a5a2cfd34c17db73c53ef127272c8c1ae220485 ]

This patch adds code to function trans_drain to remove drained bd elements from the ail lists, if queued, before freeing the bd. If we don't remove the bd from the ail, function ail_drain will try to reference the bd after it has been freed by trans_drain.

Thanks to Andy Price for his analysis of the problem.

Reported-by: Andy Price anprice@redhat.com Signed-off-by: Bob Peterson rpeterso@redhat.com Signed-off-by: Andreas Gruenbacher agruenba@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/gfs2/log.c | 4 ++++ fs/gfs2/trans.c | 2 ++ 2 files changed, 6 insertions(+)

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 2e9314091c81..1955dea999f7 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -935,12 +935,16 @@ static void trans_drain(struct gfs2_trans *tr) while (!list_empty(head)) { bd = list_first_entry(head, struct gfs2_bufdata, bd_list); list_del_init(&bd->bd_list); + if (!list_empty(&bd->bd_ail_st_list)) + gfs2_remove_from_ail(bd); kmem_cache_free(gfs2_bufdata_cachep, bd); } head = &tr->tr_databuf; while (!list_empty(head)) { bd = list_first_entry(head, struct gfs2_bufdata, bd_list); list_del_init(&bd->bd_list); + if (!list_empty(&bd->bd_ail_st_list)) + gfs2_remove_from_ail(bd); kmem_cache_free(gfs2_bufdata_cachep, bd); } } diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index 6d4bf7ea7b3b..7f850ff6a05d 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -134,6 +134,8 @@ static struct gfs2_bufdata *gfs2_alloc_bufdata(struct gfs2_glock *gl, bd->bd_bh = bh; bd->bd_gl = gl; INIT_LIST_HEAD(&bd->bd_list); + INIT_LIST_HEAD(&bd->bd_ail_st_list); + INIT_LIST_HEAD(&bd->bd_ail_gl_list); bh->b_private = bd; return bd; }

From: Yang Li yang.lee@linux.alibaba.com

[ Upstream commit 6e5d5791730b55a1f987e1db84b078b91eb49e99 ]

fixed the following coccicheck: ./drivers/gpio/gpiolib-acpi.c:176:7-27: ERROR: Threaded IRQ with no primary handler requested without IRQF_ONESHOT

Make sure threaded IRQs without a primary handler are always request with IRQF_ONESHOT

Reported-by: Abaci Robot abaci@linux.alibaba.com Signed-off-by: Yang Li yang.lee@linux.alibaba.com Acked-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpio/gpiolib-acpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 495f779b2ab9..1aacd2a5a1fd 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -174,7 +174,7 @@ static void acpi_gpiochip_request_irq(struct acpi_gpio_chip *acpi_gpio, int ret, value;

ret = request_threaded_irq(event->irq, NULL, event->handler, - event->irqflags, "ACPI:Event", event); + event->irqflags | IRQF_ONESHOT, "ACPI:Event", event); if (ret) { dev_err(acpi_gpio->chip->parent, "Failed to setup interrupt handler for %d\n",

From: Frank Sorenson sorenson@redhat.com

[ Upstream commit ad3dbe35c833c2d4d0bbf3f04c785d32f931e7c9 ]

CREATE requests return a post_op_fh3, rather than nfs_fh3. The post_op_fh3 includes an extra word to indicate 'handle_follows'.

Without that additional word, create fails when full 64-byte filehandles are in use.

Add NFS3_post_op_fh_sz, and correct the size calculation for NFS3_createres_sz.

Signed-off-by: Frank Sorenson sorenson@redhat.com Signed-off-by: Anna Schumaker Anna.Schumaker@Netapp.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/nfs3xdr.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index ca10072644ff..ed1c83738c30 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -36,6 +36,7 @@ #define NFS3_pagepad_sz (1) /* Page padding */ #define NFS3_fhandle_sz (1+16) #define NFS3_fh_sz (NFS3_fhandle_sz) /* shorthand */ +#define NFS3_post_op_fh_sz (1+NFS3_fh_sz) #define NFS3_sattr_sz (15) #define NFS3_filename_sz (1+(NFS3_MAXNAMLEN>>2)) #define NFS3_path_sz (1+(NFS3_MAXPATHLEN>>2)) @@ -73,7 +74,7 @@ #define NFS3_readlinkres_sz (1+NFS3_post_op_attr_sz+1+NFS3_pagepad_sz) #define NFS3_readres_sz (1+NFS3_post_op_attr_sz+3+NFS3_pagepad_sz) #define NFS3_writeres_sz (1+NFS3_wcc_data_sz+4) -#define NFS3_createres_sz (1+NFS3_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz) +#define NFS3_createres_sz (1+NFS3_post_op_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz) #define NFS3_renameres_sz (1+(2 * NFS3_wcc_data_sz)) #define NFS3_linkres_sz (1+NFS3_post_op_attr_sz+NFS3_wcc_data_sz) #define NFS3_readdirres_sz (1+NFS3_post_op_attr_sz+2+NFS3_pagepad_sz)

From: Jia-Ju Bai baijiaju1990@gmail.com

[ Upstream commit 62765d39553cfd1ad340124fe1e280450e8c89e2 ]

When priv->rx_skbuff or priv->tx_skbuff is NULL, no error return code of uhdlc_init() is assigned. To fix this bug, ret is assigned with -ENOMEM in these cases.

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/wan/fsl_ucc_hdlc.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index dca97cd7c4e7..7eac6a3e1cde 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -204,14 +204,18 @@ static int uhdlc_init(struct ucc_hdlc_private *priv) priv->rx_skbuff = kcalloc(priv->rx_ring_size, sizeof(*priv->rx_skbuff), GFP_KERNEL); - if (!priv->rx_skbuff) + if (!priv->rx_skbuff) { + ret = -ENOMEM; goto free_ucc_pram; + }

priv->tx_skbuff = kcalloc(priv->tx_ring_size, sizeof(*priv->tx_skbuff), GFP_KERNEL); - if (!priv->tx_skbuff) + if (!priv->tx_skbuff) { + ret = -ENOMEM; goto free_rx_skbuff; + }

priv->skb_curtx = 0; priv->skb_dirtytx = 0;

From: Alex Marginean alexandru.marginean@nxp.com

[ Upstream commit 1b2395dfff5bb40228a187f21f577cd90673d344 ]

On LS1028A, the MAC RX FIFO defaults to the value 2, which is too high and may lead to RX lock-up under traffic at a rate higher than 6 Gbps. Set it to 1 instead, as recommended by the hardware design team and by later versions of the ENETC block guide.

Signed-off-by: Alex Marginean alexandru.marginean@nxp.com Reviewed-by: Claudiu Manoil claudiu.manoil@nxp.com Reviewed-by: Jason Liu jason.hui.liu@nxp.com Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/enetc/enetc_hw.h | 2 ++ drivers/net/ethernet/freescale/enetc/enetc_pf.c | 6 ++++++ 2 files changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index de0d20b0f489..00938f7960a4 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -234,6 +234,8 @@ enum enetc_bdr_type {TX, RX}; #define ENETC_PM0_MAXFRM 0x8014 #define ENETC_SET_TX_MTU(val) ((val) << 16) #define ENETC_SET_MAXFRM(val) ((val) & 0xffff) +#define ENETC_PM0_RX_FIFO 0x801c +#define ENETC_PM0_RX_FIFO_VAL 1

#define ENETC_PM_IMDIO_BASE 0x8030

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index ca02f033bea2..224fc37a6757 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -490,6 +490,12 @@ static void enetc_configure_port_mac(struct enetc_hw *hw)

enetc_port_wr(hw, ENETC_PM1_CMD_CFG, ENETC_PM0_CMD_PHY_TX_EN | ENETC_PM0_CMD_TXP | ENETC_PM0_PROMISC); + + /* On LS1028A, the MAC RX FIFO defaults to 2, which is too high + * and may lead to RX lock-up under traffic. Set it to 1 instead, + * as recommended by the hardware team. + */ + enetc_port_wr(hw, ENETC_PM0_RX_FIFO, ENETC_PM0_RX_FIFO_VAL); }

static void enetc_mac_config(struct enetc_hw *hw, phy_interface_t phy_mode)

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 3c081b6171a8..bfca7b8a6f31 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 7a7222d4c19c..b938d1d04d96 100644 --- a/drivers/irqchip/irq-ingenic-tcu.c +++ b/drivers/irqchip/irq-ingenic-tcu.c @@ -179,5 +179,6 @@ 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); IRQCHIP_DECLARE(x1000_tcu_irq, "ingenic,x1000-tcu", ingenic_tcu_irq_init); diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c index b61a8901ef72..ea36bb00be80 100644 --- a/drivers/irqchip/irq-ingenic.c +++ b/drivers/irqchip/irq-ingenic.c @@ -155,6 +155,7 @@ 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: Jiri Slaby jslaby@suse.cz

[ Upstream commit b3d9fc1436808a4ef9927e558b3415e728e710c5 ]

There is a test in Kconfig which takes inverted value of a compiler check: * config CC_HAS_INT128 def_bool !$(cc-option,$(m64-flag) -D__SIZEOF_INT128__=0)

This results in CC_HAS_INT128 not being in super-config generated by dummy-tools. So take this into account in the gcc script.

Signed-off-by: Jiri Slaby jslaby@suse.cz Signed-off-by: Masahiro Yamada masahiroy@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- scripts/dummy-tools/gcc | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/scripts/dummy-tools/gcc b/scripts/dummy-tools/gcc index 5c113cad5601..0d0589cf8184 100755 --- a/scripts/dummy-tools/gcc +++ b/scripts/dummy-tools/gcc @@ -85,3 +85,8 @@ if arg_contain -print-file-name=plugin "$@"; then echo $plugin_dir exit 0 fi + +# inverted return value +if arg_contain -D__SIZEOF_INT128__=0 "$@"; then + exit 1 +fi

From: Rob Gardner rob.gardner@oracle.com

[ Upstream commit e5e8b80d352ec999d2bba3ea584f541c83f4ca3f ]

is_no_fault_exception() has two bugs which were discovered via random opcode testing with stress-ng. Both are caused by improper filtering of opcodes.

The first bug can be triggered by a floating point store with a no-fault ASI, for instance "sta %f0, [%g0] #ASI_PNF", opcode C1A01040.

The code first tests op3[5] (0x1000000), which denotes a floating point instruction, and then tests op3[2] (0x200000), which denotes a store instruction. But these bits are not mutually exclusive, and the above mentioned opcode has both bits set. The intent is to filter out stores, so the test for stores must be done first in order to have any effect.

The second bug can be triggered by a floating point load with one of the invalid ASI values 0x8e or 0x8f, which pass this check in is_no_fault_exception(): if ((asi & 0xf2) == ASI_PNF)

An example instruction is "ldqa [%l7 + %o7] #ASI 0x8f, %f38", opcode CF95D1EF. Asi values greater than 0x8b (ASI_SNFL) are fatal in handle_ldf_stq(), and is_no_fault_exception() must not allow these invalid asi values to make it that far.

In both of these cases, handle_ldf_stq() reacts by calling sun4v_data_access_exception() or spitfire_data_access_exception(), which call is_no_fault_exception() and results in an infinite recursion.

Signed-off-by: Rob Gardner rob.gardner@oracle.com Tested-by: Anatoly Pugachev matorola@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- arch/sparc/kernel/traps_64.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index d92e5eaa4c1d..a850dccd78ea 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -275,14 +275,13 @@ bool is_no_fault_exception(struct pt_regs *regs) asi = (regs->tstate >> 24); /* saved %asi */ else asi = (insn >> 5); /* immediate asi */ - if ((asi & 0xf2) == ASI_PNF) { - if (insn & 0x1000000) { /* op3[5:4]=3 */ - handle_ldf_stq(insn, regs); - return true; - } else if (insn & 0x200000) { /* op3[2], stores */ + if ((asi & 0xf6) == ASI_PNF) { + if (insn & 0x200000) /* op3[2], stores */ return false; - } - handle_ld_nf(insn, regs); + if (insn & 0x1000000) /* op3[5:4]=3 (fp) */ + handle_ldf_stq(insn, regs); + else + handle_ld_nf(insn, regs); return true; } }

From: Tomer Tayar ttayar@habana.ai

[ Upstream commit ffd123fe839700366ea79b19ac3683bf56817372 ]

A device can be removed from the PCI subsystem while a process holds the file descriptor opened. In such a case, the driver attempts to kill the process, but as it is still possible that the process will be alive after this step, the device removal will complete, and we will end up with a process object that points to a device object which was already released.

To prevent the usage of this released device object, disable the following file operations for this process object, and avoid the cleanup steps when the file descriptor is eventually closed. The latter is just a best effort, as memory leak will occur.

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/common/device.c | 40 ++++++++++++++++--- .../misc/habanalabs/common/habanalabs_ioctl.c | 12 ++++++ 2 files changed, 46 insertions(+), 6 deletions(-)

diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index 6785329eee27..82c0306a9210 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -93,12 +93,19 @@ void hl_hpriv_put(struct hl_fpriv *hpriv) static int hl_device_release(struct inode *inode, struct file *filp) { struct hl_fpriv *hpriv = filp->private_data; + struct hl_device *hdev = hpriv->hdev; + + filp->private_data = NULL; + + if (!hdev) { + pr_crit("Closing FD after device was removed. Memory leak will occur and it is advised to reboot.\n"); + put_pid(hpriv->taskpid); + return 0; + }

hl_cb_mgr_fini(hpriv->hdev, &hpriv->cb_mgr); hl_ctx_mgr_fini(hpriv->hdev, &hpriv->ctx_mgr);

- filp->private_data = NULL; - hl_hpriv_put(hpriv);

return 0; @@ -107,16 +114,19 @@ static int hl_device_release(struct inode *inode, struct file *filp) static int hl_device_release_ctrl(struct inode *inode, struct file *filp) { struct hl_fpriv *hpriv = filp->private_data; - struct hl_device *hdev; + struct hl_device *hdev = hpriv->hdev;

filp->private_data = NULL;

- hdev = hpriv->hdev; + if (!hdev) { + pr_err("Closing FD after device was removed\n"); + goto out; + }

mutex_lock(&hdev->fpriv_list_lock); list_del(&hpriv->dev_node); mutex_unlock(&hdev->fpriv_list_lock); - +out: put_pid(hpriv->taskpid);

kfree(hpriv); @@ -136,8 +146,14 @@ static int hl_device_release_ctrl(struct inode *inode, struct file *filp) static int hl_mmap(struct file *filp, struct vm_area_struct *vma) { struct hl_fpriv *hpriv = filp->private_data; + struct hl_device *hdev = hpriv->hdev; unsigned long vm_pgoff;

+ if (!hdev) { + pr_err_ratelimited("Trying to mmap after device was removed! Please close FD\n"); + return -ENODEV; + } + vm_pgoff = vma->vm_pgoff; vma->vm_pgoff = HL_MMAP_OFFSET_VALUE_GET(vm_pgoff);

@@ -884,6 +900,16 @@ static int device_kill_open_processes(struct hl_device *hdev, u32 timeout) return -EBUSY; }

+static void device_disable_open_processes(struct hl_device *hdev) +{ + struct hl_fpriv *hpriv; + + mutex_lock(&hdev->fpriv_list_lock); + list_for_each_entry(hpriv, &hdev->fpriv_list, dev_node) + hpriv->hdev = NULL; + mutex_unlock(&hdev->fpriv_list_lock); +} + /* * hl_device_reset - reset the device * @@ -1538,8 +1564,10 @@ void hl_device_fini(struct hl_device *hdev) HL_PENDING_RESET_LONG_SEC);

rc = device_kill_open_processes(hdev, HL_PENDING_RESET_LONG_SEC); - if (rc) + if (rc) { dev_crit(hdev->dev, "Failed to kill all open processes\n"); + device_disable_open_processes(hdev); + }

hl_cb_pool_fini(hdev);

diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c index d25892d61ec9..0805e1173d54 100644 --- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c @@ -5,6 +5,8 @@ * All Rights Reserved. */

+#define pr_fmt(fmt) "habanalabs: " fmt + #include <uapi/misc/habanalabs.h> #include "habanalabs.h"

@@ -667,6 +669,11 @@ long hl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) const struct hl_ioctl_desc *ioctl = NULL; unsigned int nr = _IOC_NR(cmd);

+ if (!hdev) { + pr_err_ratelimited("Sending ioctl after device was removed! Please close FD\n"); + return -ENODEV; + } + if ((nr >= HL_COMMAND_START) && (nr < HL_COMMAND_END)) { ioctl = &hl_ioctls[nr]; } else { @@ -685,6 +692,11 @@ long hl_ioctl_control(struct file *filep, unsigned int cmd, unsigned long arg) const struct hl_ioctl_desc *ioctl = NULL; unsigned int nr = _IOC_NR(cmd);

+ if (!hdev) { + pr_err_ratelimited("Sending ioctl after device was removed! Please close FD\n"); + return -ENODEV; + } + if (nr == _IOC_NR(HL_IOCTL_INFO)) { ioctl = &hl_ioctls_control[nr]; } else {

From: Peter Zijlstra peterz@infradead.org

[ Upstream commit d5b0e0677bfd5efd17c5bbb00156931f0d41cb85 ]

Jakub reported that:

static struct net_device *rtl8139_init_board(struct pci_dev *pdev) { ... u64_stats_init(&tp->rx_stats.syncp); u64_stats_init(&tp->tx_stats.syncp); ... }

results in lockdep getting confused between the RX and TX stats lock. This is because u64_stats_init() is an inline calling seqcount_init(), which is a macro using a static variable to generate a lockdep class.

By wrapping that in an inline, we negate the effect of the macro and fold the static key variable, hence the confusion.

Fix by also making u64_stats_init() a macro for the case where it matters, leaving the other case an inline for argument validation etc.

Reported-by: Jakub Kicinski kuba@kernel.org Debugged-by: "Ahmed S. Darwish" a.darwish@linutronix.de Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Tested-by: "Erhard F." erhard_f@mailbox.org Link: https://lkml.kernel.org/r/YEXicy6+9MksdLZh@hirez.programming.kicks-ass.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/u64_stats_sync.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index c6abb79501b3..e81856c0ba13 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -115,12 +115,13 @@ static inline void u64_stats_inc(u64_stats_t *p) } #endif

+#if BITS_PER_LONG == 32 && defined(CONFIG_SMP) +#define u64_stats_init(syncp) seqcount_init(&(syncp)->seq) +#else static inline void u64_stats_init(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG == 32 && defined(CONFIG_SMP) - seqcount_init(&syncp->seq); -#endif } +#endif

static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) {

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 37a2abbe85c7..2351a232d90e 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: Damien Le Moal damien.lemoal@wdc.com

[ Upstream commit faa44c69daf9ccbd5b8a1aee13e0e0d037c0be17 ]

Similarly to a single zone reset operation (REQ_OP_ZONE_RESET), execute REQ_OP_ZONE_RESET_ALL operations with REQ_SYNC set.

Signed-off-by: Damien Le Moal damien.lemoal@wdc.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-zoned.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c index df0ecf6790d3..fc925f73d694 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -240,7 +240,7 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, */ if (op == REQ_OP_ZONE_RESET && blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) { - bio->bi_opf = REQ_OP_ZONE_RESET_ALL; + bio->bi_opf = REQ_OP_ZONE_RESET_ALL | REQ_SYNC; break; }

From: Sung Lee sung.lee@amd.com

[ Upstream commit b0075d114c33580f5c9fa9cee8e13d06db41471b ]

[WHY & HOW] Using values provided by DF for latency may cause hangs in multi display configurations. Revert change to previous value.

Tested-by: Daniel Wheeler daniel.wheeler@amd.com Signed-off-by: Sung Lee sung.lee@amd.com Reviewed-by: Haonan Wang Haonan.Wang2@amd.com Acked-by: Eryk Brol eryk.brol@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 4caeab6a09b3..4a3df13c9e49 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -296,7 +296,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .num_banks = 8, .num_chans = 4, .vmm_page_size_bytes = 4096, - .dram_clock_change_latency_us = 11.72, + .dram_clock_change_latency_us = 23.84, .return_bus_width_bytes = 64, .dispclk_dppclk_vco_speed_mhz = 3600, .xfc_bus_transport_time_us = 4,

From: Zhan Liu zhan.liu@amd.com

[ Upstream commit eda29602f1a8b2b32d8c8c354232d9d1ee1c064d ]

[Why] For DGPU Navi, the wm_table.nv_entries are used. These entires are not populated for DCN301 Vangogh APU, but instead wm_table.entries are.

[How] Use DCN21 Renoir style wm calculations.

Signed-off-by: Leo Li sunpeng.li@amd.com Signed-off-by: Zhan Liu zhan.liu@amd.com Reviewed-by: Dmytro Laktyushkin Dmytro.Laktyushkin@amd.com Acked-by: Zhan Liu zhan.liu@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../amd/display/dc/dcn301/dcn301_resource.c | 96 ++++++++++++++++++- 1 file changed, 95 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c index 35f5bf08ae96..23bc208cbfa4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c @@ -1722,12 +1722,106 @@ static void dcn301_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *b dml_init_instance(&dc->dml, &dcn3_01_soc, &dcn3_01_ip, DML_PROJECT_DCN30); }

+static void calculate_wm_set_for_vlevel( + int vlevel, + struct wm_range_table_entry *table_entry, + struct dcn_watermarks *wm_set, + struct display_mode_lib *dml, + display_e2e_pipe_params_st *pipes, + int pipe_cnt) +{ + double dram_clock_change_latency_cached = dml->soc.dram_clock_change_latency_us; + + ASSERT(vlevel < dml->soc.num_states); + /* only pipe 0 is read for voltage and dcf/soc clocks */ + pipes[0].clks_cfg.voltage = vlevel; + pipes[0].clks_cfg.dcfclk_mhz = dml->soc.clock_limits[vlevel].dcfclk_mhz; + pipes[0].clks_cfg.socclk_mhz = dml->soc.clock_limits[vlevel].socclk_mhz; + + dml->soc.dram_clock_change_latency_us = table_entry->pstate_latency_us; + dml->soc.sr_exit_time_us = table_entry->sr_exit_time_us; + dml->soc.sr_enter_plus_exit_time_us = table_entry->sr_enter_plus_exit_time_us; + + wm_set->urgent_ns = get_wm_urgent(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(dml, pipes, pipe_cnt) * 1000; + wm_set->pte_meta_urgent_ns = get_wm_memory_trip(dml, pipes, pipe_cnt) * 1000; + wm_set->frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(dml, pipes, pipe_cnt) * 1000; + wm_set->frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(dml, pipes, pipe_cnt) * 1000; + wm_set->urgent_latency_ns = get_urgent_latency(dml, pipes, pipe_cnt) * 1000; + dml->soc.dram_clock_change_latency_us = dram_clock_change_latency_cached; + +} + +static void dcn301_calculate_wm_and_dlg( + struct dc *dc, struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel_req) +{ + int i, pipe_idx; + int vlevel, vlevel_max; + struct wm_range_table_entry *table_entry; + struct clk_bw_params *bw_params = dc->clk_mgr->bw_params; + + ASSERT(bw_params); + + vlevel_max = bw_params->clk_table.num_entries - 1; + + /* WM Set D */ + table_entry = &bw_params->wm_table.entries[WM_D]; + if (table_entry->wm_type == WM_TYPE_RETRAINING) + vlevel = 0; + else + vlevel = vlevel_max; + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.d, + &context->bw_ctx.dml, pipes, pipe_cnt); + /* WM Set C */ + table_entry = &bw_params->wm_table.entries[WM_C]; + vlevel = min(max(vlevel_req, 2), vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.c, + &context->bw_ctx.dml, pipes, pipe_cnt); + /* WM Set B */ + table_entry = &bw_params->wm_table.entries[WM_B]; + vlevel = min(max(vlevel_req, 1), vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.b, + &context->bw_ctx.dml, pipes, pipe_cnt); + + /* WM Set A */ + table_entry = &bw_params->wm_table.entries[WM_A]; + vlevel = min(vlevel_req, vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.a, + &context->bw_ctx.dml, pipes, pipe_cnt); + + for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { + if (!context->res_ctx.pipe_ctx[i].stream) + continue; + + pipes[pipe_idx].clks_cfg.dispclk_mhz = get_dispclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt); + pipes[pipe_idx].clks_cfg.dppclk_mhz = get_dppclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); + + if (dc->config.forced_clocks) { + pipes[pipe_idx].clks_cfg.dispclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dispclk_mhz; + pipes[pipe_idx].clks_cfg.dppclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dppclk_mhz; + } + if (dc->debug.min_disp_clk_khz > pipes[pipe_idx].clks_cfg.dispclk_mhz * 1000) + pipes[pipe_idx].clks_cfg.dispclk_mhz = dc->debug.min_disp_clk_khz / 1000.0; + if (dc->debug.min_dpp_clk_khz > pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000) + pipes[pipe_idx].clks_cfg.dppclk_mhz = dc->debug.min_dpp_clk_khz / 1000.0; + + pipe_idx++; + } + + dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); +} + static struct resource_funcs dcn301_res_pool_funcs = { .destroy = dcn301_destroy_resource_pool, .link_enc_create = dcn301_link_encoder_create, .panel_cntl_create = dcn301_panel_cntl_create, .validate_bandwidth = dcn30_validate_bandwidth, - .calculate_wm_and_dlg = dcn30_calculate_wm_and_dlg, + .calculate_wm_and_dlg = dcn301_calculate_wm_and_dlg, .populate_dml_pipes = dcn30_populate_dml_pipes_from_context, .acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer, .add_stream_to_ctx = dcn30_add_stream_to_ctx,

From: Christian König christian.koenig@amd.com

[ Upstream commit cba2afb65cb05c3d197d17323fee4e3c9edef9cd ]

When AGP is compiled as module radeon must be compiled as module as well.

Signed-off-by: Christian König christian.koenig@amd.com Reviewed-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/Kconfig | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index af6c6d214d91..f0c0ccdc8a10 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -232,6 +232,7 @@ source "drivers/gpu/drm/arm/Kconfig" config DRM_RADEON tristate "ATI Radeon" depends on DRM && PCI && MMU + depends on AGP || !AGP select FW_LOADER select DRM_KMS_HELPER select DRM_TTM

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 a0f169a2d96f..206bf0a50487 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -366,6 +366,7 @@ 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: Hannes Reinecke hare@suse.de

[ Upstream commit ae3afe6308b43bbf49953101d4ba2c1c481133a8 ]

When a command has been aborted we should return NVME_SC_HOST_ABORTED_CMD to be consistent with the other transports.

Signed-off-by: Hannes Reinecke hare@suse.de Reviewed-by: Sagi Grimberg sagi@grimberg.me Reviewed-by: James Smart jsmart2021@gmail.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/fc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 0ddd2514b401..ca75338f2367 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1956,7 +1956,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) sizeof(op->rsp_iu), DMA_FROM_DEVICE);

if (opstate == FCPOP_STATE_ABORTED) - status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1); + status = cpu_to_le16(NVME_SC_HOST_ABORTED_CMD << 1); else if (freq->status) { status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1); dev_info(ctrl->ctrl.device,

From: Lv Yunlong lyl2019@mail.ustc.edu.cn

[ Upstream commit abec6561fc4e0fbb19591a0b35676d8c783b5493 ]

In nvmet_rdma_write_data_done, rsp is recoverd by wc->wr_cqe and freed by nvmet_rdma_release_rsp(). But after that, pr_info() used the freed chunk's member object and could leak the freed chunk address with wc->wr_cqe by computing the offset.

Signed-off-by: Lv Yunlong lyl2019@mail.ustc.edu.cn Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/target/rdma.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 06b6b742bb21..6c1f3ab7649c 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -802,9 +802,8 @@ static void nvmet_rdma_write_data_done(struct ib_cq *cq, struct ib_wc *wc) nvmet_req_uninit(&rsp->req); nvmet_rdma_release_rsp(rsp); if (wc->status != IB_WC_WR_FLUSH_ERR) { - pr_info("RDMA WRITE for CQE 0x%p failed with status %s (%d).\n", - wc->wr_cqe, ib_wc_status_msg(wc->status), - wc->status); + pr_info("RDMA WRITE for CQE failed with status %s (%d).\n", + ib_wc_status_msg(wc->status), wc->status); nvmet_rdma_error_comp(queue); } return;

From: J. Bruce Fields bfields@redhat.com

[ Upstream commit 4f8be1f53bf615102d103c0509ffa9596f65b718 ]

The NFSv4 protocol doesn't have any notion of reomoving an attribute, so removexattr(path,"system.nfs4_acl") doesn't make sense.

There's no documented return value. Arguably it could be EOPNOTSUPP but I'm a little worried an application might take that to mean that we don't support ACLs or xattrs. How about EINVAL?

Signed-off-by: J. Bruce Fields bfields@redhat.com Signed-off-by: Anna Schumaker Anna.Schumaker@Netapp.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/nfs4proc.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 7eb44f37558c..95d3b8540f8e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5896,6 +5896,9 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE); int ret, i;

+ /* You can't remove system.nfs4_acl: */ + if (buflen == 0) + return -EINVAL; if (!nfs4_server_supports_acls(server)) return -EOPNOTSUPP; if (npages > ARRAY_SIZE(pages))

From: Pavel Begunkov asml.silence@gmail.com

[ Upstream commit e1915f76a8981f0a750cf56515df42582a37c4b0 ]

As io_uring_cancel_files() and others let SQO to run between io_uring_try_cancel_requests(), SQO may generate new deferred requests, so it's safer to try to cancel them in it.

Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- fs/io_uring.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c index ef078182e7ca..c3cfaa367138 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -8861,11 +8861,11 @@ static bool io_cancel_task_cb(struct io_wq_work *work, void *data) return ret; }

-static void io_cancel_defer_files(struct io_ring_ctx *ctx, +static bool io_cancel_defer_files(struct io_ring_ctx *ctx, struct task_struct *task, struct files_struct *files) { - struct io_defer_entry *de = NULL; + struct io_defer_entry *de; LIST_HEAD(list);

spin_lock_irq(&ctx->completion_lock); @@ -8876,6 +8876,8 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx, } } spin_unlock_irq(&ctx->completion_lock); + if (list_empty(&list)) + return false;

while (!list_empty(&list)) { de = list_first_entry(&list, struct io_defer_entry, list); @@ -8885,6 +8887,7 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx, io_req_complete(de->req, -ECANCELED); kfree(de); } + return true; }

static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, @@ -8912,6 +8915,7 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, } }

+ ret |= io_cancel_defer_files(ctx, task, files); ret |= io_poll_remove_all(ctx, task, files); ret |= io_kill_timeouts(ctx, task, files); ret |= io_run_task_work(); @@ -8992,8 +8996,6 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx, io_sq_thread_park(ctx->sq_data); }

- io_cancel_defer_files(ctx, task, files); - io_uring_cancel_files(ctx, task, files); if (!files) io_uring_try_cancel_requests(ctx, task, NULL);

From: Sergei Trofimovich slyfox@gentoo.org

[ Upstream commit 0ceb1ace4a2778e34a5414e5349712ae4dc41d85 ]

In https://bugs.gentoo.org/769614 Dmitry noticed that `ptrace(PTRACE_GET_SYSCALL_INFO)` does not work for syscalls called via glibc's syscall() wrapper.

ia64 has two ways to call syscalls from userspace: via `break` and via `eps` instructions.

The difference is in stack layout:

1. `eps` creates simple stack frame: no locals, in{0..7} == out{0..8} 2. `break` uses userspace stack frame: may be locals (glibc provides one), in{0..7} == out{0..8}.

Both work fine in syscall handling cde itself.

But `ptrace(PTRACE_GET_SYSCALL_INFO)` uses unwind mechanism to re-extract syscall arguments but it does not account for locals.

The change always skips locals registers. It should not change `eps` path as kernel's handler already enforces locals=0 and fixes `break`.

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

Link: https://lkml.kernel.org/r/20210221002554.333076-1-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 Cc: Oleg Nesterov oleg@redhat.com Cc: John Paul Adrian Glaubitz glaubitz@physik.fu-berlin.de 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/kernel/ptrace.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c index c3490ee2daa5..e14f5653393a 100644 --- a/arch/ia64/kernel/ptrace.c +++ b/arch/ia64/kernel/ptrace.c @@ -2013,27 +2013,39 @@ static void syscall_get_set_args_cb(struct unw_frame_info *info, void *data) { struct syscall_get_set_args *args = data; struct pt_regs *pt = args->regs; - unsigned long *krbs, cfm, ndirty; + unsigned long *krbs, cfm, ndirty, nlocals, nouts; int i, count;

if (unw_unwind_to_user(info) < 0) return;

+ /* + * We get here via a few paths: + * - break instruction: cfm is shared with caller. + * syscall args are in out= regs, locals are non-empty. + * - epsinstruction: cfm is set by br.call + * locals don't exist. + * + * For both cases argguments are reachable in cfm.sof - cfm.sol. + * CFM: [ ... | sor: 17..14 | sol : 13..7 | sof : 6..0 ] + */ cfm = pt->cr_ifs; + nlocals = (cfm >> 7) & 0x7f; /* aka sol */ + nouts = (cfm & 0x7f) - nlocals; /* aka sof - sol */ krbs = (unsigned long *)info->task + IA64_RBS_OFFSET/8; ndirty = ia64_rse_num_regs(krbs, krbs + (pt->loadrs >> 19));

count = 0; if (in_syscall(pt)) - count = min_t(int, args->n, cfm & 0x7f); + count = min_t(int, args->n, nouts);

+ /* Iterate over outs. */ for (i = 0; i < count; i++) { + int j = ndirty + nlocals + i + args->i; if (args->rw) - *ia64_rse_skip_regs(krbs, ndirty + i + args->i) = - args->args[i]; + *ia64_rse_skip_regs(krbs, j) = args->args[i]; else - args->args[i] = *ia64_rse_skip_regs(krbs, - ndirty + i + args->i); + args->args[i] = *ia64_rse_skip_regs(krbs, j); }

if (!args->rw) {

From: Peter Zijlstra peterz@infradead.org

[ Upstream commit 880cfed3a012d7863f42251791cea7fe78c39390 ]

Some static call declarations are going to be needed on low level header files. Move the necessary material to the dedicated static call types header to avoid inclusion dependency hell.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Frederic Weisbecker frederic@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Link: https://lkml.kernel.org/r/20210118141223.123667-4-frederic@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/static_call.h | 21 ------------------- include/linux/static_call_types.h | 27 +++++++++++++++++++++++++ tools/include/linux/static_call_types.h | 27 +++++++++++++++++++++++++ 3 files changed, 54 insertions(+), 21 deletions(-)

diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 695da4c9b338..a2c064585c03 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -107,26 +107,10 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool

#define STATIC_CALL_TRAMP_ADDR(name) &STATIC_CALL_TRAMP(name)

-/* - * __ADDRESSABLE() is used to ensure the key symbol doesn't get stripped from - * the symbol table so that objtool can reference it when it generates the - * .static_call_sites section. - */ -#define __static_call(name) \ -({ \ - __ADDRESSABLE(STATIC_CALL_KEY(name)); \ - &STATIC_CALL_TRAMP(name); \ -}) - #else #define STATIC_CALL_TRAMP_ADDR(name) NULL #endif

- -#define DECLARE_STATIC_CALL(name, func) \ - extern struct static_call_key STATIC_CALL_KEY(name); \ - extern typeof(func) STATIC_CALL_TRAMP(name); - #define static_call_update(name, func) \ ({ \ BUILD_BUG_ON(!__same_type(*(func), STATIC_CALL_TRAMP(name))); \ @@ -174,7 +158,6 @@ extern int static_call_text_reserved(void *start, void *end); }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)

-#define static_call(name) __static_call(name) #define static_call_cond(name) (void)__static_call(name)

#define EXPORT_STATIC_CALL(name) \ @@ -207,7 +190,6 @@ struct static_call_key { }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)

-#define static_call(name) __static_call(name) #define static_call_cond(name) (void)__static_call(name)

static inline @@ -252,9 +234,6 @@ struct static_call_key { .func = NULL, \ }

-#define static_call(name) \ - ((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func)) - static inline void __static_call_nop(void) { }

/* diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h index 89135bb35bf7..08f78b1b88b4 100644 --- a/include/linux/static_call_types.h +++ b/include/linux/static_call_types.h @@ -4,6 +4,7 @@

#include <linux/types.h> #include <linux/stringify.h> +#include <linux/compiler.h>

#define STATIC_CALL_KEY_PREFIX __SCK__ #define STATIC_CALL_KEY_PREFIX_STR __stringify(STATIC_CALL_KEY_PREFIX) @@ -32,4 +33,30 @@ struct static_call_site { s32 key; };

+#define DECLARE_STATIC_CALL(name, func) \ + extern struct static_call_key STATIC_CALL_KEY(name); \ + extern typeof(func) STATIC_CALL_TRAMP(name); + +#ifdef CONFIG_HAVE_STATIC_CALL + +/* + * __ADDRESSABLE() is used to ensure the key symbol doesn't get stripped from + * the symbol table so that objtool can reference it when it generates the + * .static_call_sites section. + */ +#define __static_call(name) \ +({ \ + __ADDRESSABLE(STATIC_CALL_KEY(name)); \ + &STATIC_CALL_TRAMP(name); \ +}) + +#define static_call(name) __static_call(name) + +#else + +#define static_call(name) \ + ((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func)) + +#endif /* CONFIG_HAVE_STATIC_CALL */ + #endif /* _STATIC_CALL_TYPES_H */ diff --git a/tools/include/linux/static_call_types.h b/tools/include/linux/static_call_types.h index 89135bb35bf7..08f78b1b88b4 100644 --- a/tools/include/linux/static_call_types.h +++ b/tools/include/linux/static_call_types.h @@ -4,6 +4,7 @@

#include <linux/types.h> #include <linux/stringify.h> +#include <linux/compiler.h>

#define STATIC_CALL_KEY_PREFIX __SCK__ #define STATIC_CALL_KEY_PREFIX_STR __stringify(STATIC_CALL_KEY_PREFIX) @@ -32,4 +33,30 @@ struct static_call_site { s32 key; };

+#define DECLARE_STATIC_CALL(name, func) \ + extern struct static_call_key STATIC_CALL_KEY(name); \ + extern typeof(func) STATIC_CALL_TRAMP(name); + +#ifdef CONFIG_HAVE_STATIC_CALL + +/* + * __ADDRESSABLE() is used to ensure the key symbol doesn't get stripped from + * the symbol table so that objtool can reference it when it generates the + * .static_call_sites section. + */ +#define __static_call(name) \ +({ \ + __ADDRESSABLE(STATIC_CALL_KEY(name)); \ + &STATIC_CALL_TRAMP(name); \ +}) + +#define static_call(name) __static_call(name) + +#else + +#define static_call(name) \ + ((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func)) + +#endif /* CONFIG_HAVE_STATIC_CALL */ + #endif /* _STATIC_CALL_TYPES_H */

From: Peter Zijlstra peterz@infradead.org

[ Upstream commit 50bf8080a94d171e843fc013abec19d8ab9f50ae ]

Provided the target address of a R_X86_64_PC32 relocation is aligned, the low two bits should be invariant between the relative and absolute value.

Turns out the address is not aligned and things go sideways, ensure we transfer the bits in the absolute form when fixing up the key address.

Fixes: 73f44fe19d35 ("static_call: Allow module use without exposing static_call_key") Reported-by: Steven Rostedt rostedt@goodmis.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Tested-by: Steven Rostedt (VMware) rostedt@goodmis.org Link: https://lkml.kernel.org/r/20210225220351.GE4746@worktop.programming.kicks-as... Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/static_call.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/kernel/static_call.c b/kernel/static_call.c index db64c2331a32..5d53c354fbe7 100644 --- a/kernel/static_call.c +++ b/kernel/static_call.c @@ -358,7 +358,8 @@ static int static_call_add_module(struct module *mod) struct static_call_site *site;

for (site = start; site != stop; site++) { - unsigned long addr = (unsigned long)static_call_key(site); + unsigned long s_key = (long)site->key + (long)&site->key; + unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; unsigned long key;

/* @@ -382,8 +383,8 @@ static int static_call_add_module(struct module *mod) return -EINVAL; }

- site->key = (key - (long)&site->key) | - (site->key & STATIC_CALL_SITE_FLAGS); + key |= s_key & STATIC_CALL_SITE_FLAGS; + site->key = key - (long)&site->key; }

return __static_call_init(mod, start, stop);

From: Sean Christopherson seanjc@google.com

[ Upstream commit b318e8decf6b9ef1bcf4ca06fae6d6a2cb5d5c5c ]

Fix a plethora of issues with MSR filtering by installing the resulting filter as an atomic bundle instead of updating the live filter one range at a time. The KVM_X86_SET_MSR_FILTER ioctl() isn't truly atomic, as the hardware MSR bitmaps won't be updated until the next VM-Enter, but the relevant software struct is atomically updated, which is what KVM really needs.

Similar to the approach used for modifying memslots, make arch.msr_filter a SRCU-protected pointer, do all the work configuring the new filter outside of kvm->lock, and then acquire kvm->lock only when the new filter has been vetted and created. That way vCPU readers either see the old filter or the new filter in their entirety, not some half-baked state.

Yuan Yao pointed out a use-after-free in ksm_msr_allowed() due to a TOCTOU bug, but that's just the tip of the iceberg...

- Nothing is __rcu annotated, making it nigh impossible to audit the code for correctness. - kvm_add_msr_filter() has an unpaired smp_wmb(). Violation of kernel coding style aside, the lack of a smb_rmb() anywhere casts all code into doubt. - kvm_clear_msr_filter() has a double free TOCTOU bug, as it grabs count before taking the lock. - kvm_clear_msr_filter() also has memory leak due to the same TOCTOU bug.

The entire approach of updating the live filter is also flawed. While installing a new filter is inherently racy if vCPUs are running, fixing the above issues also makes it trivial to ensure certain behavior is deterministic, e.g. KVM can provide deterministic behavior for MSRs with identical settings in the old and new filters. An atomic update of the filter also prevents KVM from getting into a half-baked state, e.g. if installing a filter fails, the existing approach would leave the filter in a half-baked state, having already committed whatever bits of the filter were already processed.

[*] https://lkml.kernel.org/r/20210312083157.25403-1-yaoyuan0329os@gmail.com

Fixes: 1a155254ff93 ("KVM: x86: Introduce MSR filtering") Cc: stable@vger.kernel.org Cc: Alexander Graf graf@amazon.com Reported-by: Yuan Yao yaoyuan0329os@gmail.com Signed-off-by: Sean Christopherson seanjc@google.com Message-Id: 20210316184436.2544875-2-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- Documentation/virt/kvm/api.rst | 6 +- arch/x86/include/asm/kvm_host.h | 14 ++-- arch/x86/kvm/x86.c | 109 +++++++++++++++++++------------- 3 files changed, 78 insertions(+), 51 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 5570887a2dce..66d38520e65a 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4831,8 +4831,10 @@ If an MSR access is not permitted through the filtering, it generates a allows user space to deflect and potentially handle various MSR accesses into user space.

-If a vCPU is in running state while this ioctl is invoked, the vCPU may -experience inconsistent filtering behavior on MSR accesses. +Note, invoking this ioctl with a vCPU is running is inherently racy. However, +KVM does guarantee that vCPUs will see either the previous filter or the new +filter, e.g. MSRs with identical settings in both the old and new filter will +have deterministic behavior.

5. The kvm_run structure diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3d6616f6f6ef..e0cfd620b293 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -894,6 +894,12 @@ enum kvm_irqchip_mode { KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ };

+struct kvm_x86_msr_filter { + u8 count; + bool default_allow:1; + struct msr_bitmap_range ranges[16]; +}; + #define APICV_INHIBIT_REASON_DISABLE 0 #define APICV_INHIBIT_REASON_HYPERV 1 #define APICV_INHIBIT_REASON_NESTED 2 @@ -989,14 +995,12 @@ struct kvm_arch { bool guest_can_read_msr_platform_info; bool exception_payload_enabled;

+ bool bus_lock_detection_enabled; + /* Deflect RDMSR and WRMSR to user space when they trigger a #GP */ u32 user_space_msr_mask;

- struct { - u8 count; - bool default_allow:1; - struct msr_bitmap_range ranges[16]; - } msr_filter; + struct kvm_x86_msr_filter __rcu *msr_filter;

struct kvm_pmu_event_filter *pmu_event_filter; struct task_struct *nx_lpage_recovery_thread; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b967c1c774a1..f37f5c1430cf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1523,35 +1523,44 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);

bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type) { + struct kvm_x86_msr_filter *msr_filter; + struct msr_bitmap_range *ranges; struct kvm *kvm = vcpu->kvm; - struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges; - u32 count = kvm->arch.msr_filter.count; - u32 i; - bool r = kvm->arch.msr_filter.default_allow; + bool allowed; int idx; + u32 i;

- /* MSR filtering not set up or x2APIC enabled, allow everything */ - if (!count || (index >= 0x800 && index <= 0x8ff)) + /* x2APIC MSRs do not support filtering. */ + if (index >= 0x800 && index <= 0x8ff) return true;

- /* Prevent collision with set_msr_filter */ idx = srcu_read_lock(&kvm->srcu);

- for (i = 0; i < count; i++) { + msr_filter = srcu_dereference(kvm->arch.msr_filter, &kvm->srcu); + if (!msr_filter) { + allowed = true; + goto out; + } + + allowed = msr_filter->default_allow; + ranges = msr_filter->ranges; + + for (i = 0; i < msr_filter->count; i++) { u32 start = ranges[i].base; u32 end = start + ranges[i].nmsrs; u32 flags = ranges[i].flags; unsigned long *bitmap = ranges[i].bitmap;

if ((index >= start) && (index < end) && (flags & type)) { - r = !!test_bit(index - start, bitmap); + allowed = !!test_bit(index - start, bitmap); break; } }

+out: srcu_read_unlock(&kvm->srcu, idx);

- return r; + return allowed; } EXPORT_SYMBOL_GPL(kvm_msr_allowed);

@@ -5315,25 +5324,34 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, return r; }

-static void kvm_clear_msr_filter(struct kvm *kvm) +static struct kvm_x86_msr_filter *kvm_alloc_msr_filter(bool default_allow) +{ + struct kvm_x86_msr_filter *msr_filter; + + msr_filter = kzalloc(sizeof(*msr_filter), GFP_KERNEL_ACCOUNT); + if (!msr_filter) + return NULL; + + msr_filter->default_allow = default_allow; + return msr_filter; +} + +static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter) { u32 i; - u32 count = kvm->arch.msr_filter.count; - struct msr_bitmap_range ranges[16];

- mutex_lock(&kvm->lock); - kvm->arch.msr_filter.count = 0; - memcpy(ranges, kvm->arch.msr_filter.ranges, count * sizeof(ranges[0])); - mutex_unlock(&kvm->lock); - synchronize_srcu(&kvm->srcu); + if (!msr_filter) + return; + + for (i = 0; i < msr_filter->count; i++) + kfree(msr_filter->ranges[i].bitmap);

- for (i = 0; i < count; i++) - kfree(ranges[i].bitmap); + kfree(msr_filter); }

-static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user_range) +static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, + struct kvm_msr_filter_range *user_range) { - struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges; struct msr_bitmap_range range; unsigned long *bitmap = NULL; size_t bitmap_size; @@ -5367,11 +5385,9 @@ static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user goto err; }

- /* Everything ok, add this range identifier to our global pool */ - ranges[kvm->arch.msr_filter.count] = range; - /* Make sure we filled the array before we tell anyone to walk it */ - smp_wmb(); - kvm->arch.msr_filter.count++; + /* Everything ok, add this range identifier. */ + msr_filter->ranges[msr_filter->count] = range; + msr_filter->count++;

return 0; err: @@ -5382,10 +5398,11 @@ static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) { struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_x86_msr_filter *new_filter, *old_filter; struct kvm_msr_filter filter; bool default_allow; - int r = 0; bool empty = true; + int r = 0; u32 i;

if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) @@ -5398,25 +5415,32 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) if (empty && !default_allow) return -EINVAL;

- kvm_clear_msr_filter(kvm); - - kvm->arch.msr_filter.default_allow = default_allow; + new_filter = kvm_alloc_msr_filter(default_allow); + if (!new_filter) + return -ENOMEM;

- /* - * Protect from concurrent calls to this function that could trigger - * a TOCTOU violation on kvm->arch.msr_filter.count. - */ - mutex_lock(&kvm->lock); for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { - r = kvm_add_msr_filter(kvm, &filter.ranges[i]); - if (r) - break; + r = kvm_add_msr_filter(new_filter, &filter.ranges[i]); + if (r) { + kvm_free_msr_filter(new_filter); + return r; + } }

+ mutex_lock(&kvm->lock); + + /* The per-VM filter is protected by kvm->lock... */ + old_filter = srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1); + + rcu_assign_pointer(kvm->arch.msr_filter, new_filter); + synchronize_srcu(&kvm->srcu); + + kvm_free_msr_filter(old_filter); + kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED); mutex_unlock(&kvm->lock);

- return r; + return 0; }

long kvm_arch_vm_ioctl(struct file *filp, @@ -10536,8 +10560,6 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm)

void kvm_arch_destroy_vm(struct kvm *kvm) { - u32 i; - if (current->mm == kvm->mm) { /* * Free memory regions allocated on behalf of userspace, @@ -10554,8 +10576,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) } if (kvm_x86_ops.vm_destroy) kvm_x86_ops.vm_destroy(kvm); - for (i = 0; i < kvm->arch.msr_filter.count; i++) - kfree(kvm->arch.msr_filter.ranges[i].bitmap); + kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1)); kvm_pic_destroy(kvm); kvm_ioapic_destroy(kvm); kvm_free_vcpus(kvm);

From: Josef Bacik josef@toxicpanda.com

commit 3cb894972f1809aa8d087c42e5e8b26c64b7d508 upstream.

While helping Neal fix his broken file system I added a debug patch to catch if we were calling btrfs_search_slot with a NULL root, and this stack trace popped:

we tried to search with a NULL root CPU: 0 PID: 1760 Comm: mount Not tainted 5.11.0-155.nealbtrfstest.1.fc34.x86_64 #1 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/22/2020 Call Trace: dump_stack+0x6b/0x83 btrfs_search_slot.cold+0x11/0x1b ? btrfs_init_dev_replace+0x36/0x450 btrfs_init_dev_replace+0x71/0x450 open_ctree+0x1054/0x1610 btrfs_mount_root.cold+0x13/0xfa legacy_get_tree+0x27/0x40 vfs_get_tree+0x25/0xb0 vfs_kern_mount.part.0+0x71/0xb0 btrfs_mount+0x131/0x3d0 ? legacy_get_tree+0x27/0x40 ? btrfs_show_options+0x640/0x640 legacy_get_tree+0x27/0x40 vfs_get_tree+0x25/0xb0 path_mount+0x441/0xa80 __x64_sys_mount+0xf4/0x130 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f644730352e

Fix this by not starting the device replace stuff if we do not have a NULL dev root.

Reported-by: Neal Gompa ngompa13@gmail.com CC: stable@vger.kernel.org # 5.11+ Signed-off-by: Josef Bacik josef@toxicpanda.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/dev-replace.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -80,6 +80,9 @@ int btrfs_init_dev_replace(struct btrfs_ struct btrfs_dev_replace_item *ptr; u64 src_devid;

+ if (!dev_root) + return 0; + path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM;

From: Josef Bacik josef@toxicpanda.com

commit 820a49dafc3304de06f296c35c9ff1ebc1666343 upstream.

Neal reported a panic trying to use -o rescue=all

BUG: kernel NULL pointer dereference, address: 0000000000000030 PGD 0 P4D 0 Oops: 0000 [#1] SMP NOPTI CPU: 0 PID: 696 Comm: mount Tainted: G W 5.12.0-rc2+ #296 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014 RIP: 0010:btrfs_device_init_dev_stats+0x1d/0x200 RSP: 0018:ffffafaec1483bb8 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff9a5715bcb298 RCX: 0000000000000070 RDX: ffff9a5703248000 RSI: ffff9a57052ea150 RDI: ffff9a5715bca400 RBP: ffff9a57052ea150 R08: 0000000000000070 R09: ffff9a57052ea150 R10: 000130faf0741c10 R11: 0000000000000000 R12: ffff9a5703700000 R13: 0000000000000000 R14: ffff9a5715bcb278 R15: ffff9a57052ea150 FS: 00007f600d122c40(0000) GS:ffff9a577bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000030 CR3: 0000000112a46005 CR4: 0000000000370ef0 Call Trace: ? btrfs_init_dev_stats+0x1f/0xf0 ? kmem_cache_alloc+0xef/0x1f0 btrfs_init_dev_stats+0x5f/0xf0 open_ctree+0x10cb/0x1720 btrfs_mount_root.cold+0x12/0xea legacy_get_tree+0x27/0x40 vfs_get_tree+0x25/0xb0 vfs_kern_mount.part.0+0x71/0xb0 btrfs_mount+0x10d/0x380 legacy_get_tree+0x27/0x40 vfs_get_tree+0x25/0xb0 path_mount+0x433/0xa00 __x64_sys_mount+0xe3/0x120 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae

This happens because when we call btrfs_init_dev_stats we do device->fs_info->dev_root. However device->fs_info isn't initialized because we were only calling btrfs_init_devices_late() if we properly read the device root. However we don't actually need the device root to init the devices, this function simply assigns the devices their ->fs_info pointer properly, so this needs to be done unconditionally always so that we can properly dereference device->fs_info in rescue cases.

Reported-by: Neal Gompa ngompa13@gmail.com CC: stable@vger.kernel.org # 5.11+ Signed-off-by: Josef Bacik josef@toxicpanda.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/disk-io.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2300,8 +2300,9 @@ static int btrfs_read_roots(struct btrfs } else { set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); fs_info->dev_root = root; - btrfs_init_devices_late(fs_info); } + /* Initialize fs_info for all devices in any case */ + btrfs_init_devices_late(fs_info);

/* If IGNOREDATACSUMS is set don't bother reading the csum root. */ if (!btrfs_test_opt(fs_info, IGNOREDATACSUMS)) {

From: Filipe Manana fdmanana@suse.com

commit 8d488a8c7ba22d7112fbf6b0a82beb1cdea1c0d5 upstream.

During the mount procedure we are calling btrfs_orphan_cleanup() against the root tree, which will find all orphans items in this tree. When an orphan item corresponds to a deleted subvolume/snapshot (instead of an inode space cache), it must not delete the orphan item, because that will cause btrfs_find_orphan_roots() to not find the orphan item and therefore not add the corresponding subvolume root to the list of dead roots, which results in the subvolume's tree never being deleted by the cleanup thread.

The same applies to the remount from RO to RW path.

Fix this by making btrfs_find_orphan_roots() run before calling btrfs_orphan_cleanup() against the root tree.

A test case for fstests will follow soon.

Reported-by: Robbie Ko robbieko@synology.com Link: https://lore.kernel.org/linux-btrfs/b19f4310-35e0-606e-1eea-2dd84d28c5da@syn... Fixes: 638331fa56caea ("btrfs: fix transaction leak and crash after cleaning up orphans on RO mount") CC: stable@vger.kernel.org # 5.11+ Signed-off-by: Filipe Manana fdmanana@suse.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/disk-io.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-)

--- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2914,6 +2914,21 @@ int btrfs_start_pre_rw_mount(struct btrf } }

+ /* + * btrfs_find_orphan_roots() is responsible for finding all the dead + * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load + * them into the fs_info->fs_roots_radix tree. This must be done before + * calling btrfs_orphan_cleanup() on the tree root. If we don't do it + * first, then btrfs_orphan_cleanup() will delete a dead root's orphan + * item before the root's tree is deleted - this means that if we unmount + * or crash before the deletion completes, on the next mount we will not + * delete what remains of the tree because the orphan item does not + * exists anymore, which is what tells us we have a pending deletion. + */ + ret = btrfs_find_orphan_roots(fs_info); + if (ret) + goto out; + ret = btrfs_cleanup_fs_roots(fs_info); if (ret) goto out; @@ -2973,7 +2988,6 @@ int btrfs_start_pre_rw_mount(struct btrf } }

- ret = btrfs_find_orphan_roots(fs_info); out: return ret; }

From: Ondrej Mosnacek omosnace@redhat.com

commit 6406887a12ee5dcdaffff1a8508d91113d545559 upstream.

Commit 02a52c5c8c3b ("selinux: move policy commit after updating selinuxfs") moved the selinux_policy_commit() call out of security_load_policy() into sel_write_load(), which caused a subtle yet rather serious bug.

The problem is that security_load_policy() passes a reference to the convert_params local variable to sidtab_convert(), which stores it in the sidtab, where it may be accessed until the policy is swapped over and RCU synchronized. Before 02a52c5c8c3b, selinux_policy_commit() was called directly from security_load_policy(), so the convert_params pointer remained valid all the way until the old sidtab was destroyed, but now that's no longer the case and calls to sidtab_context_to_sid() on the old sidtab after security_load_policy() returns may cause invalid memory accesses.

This can be easily triggered using the stress test from commit ee1a84fdfeed ("selinux: overhaul sidtab to fix bug and improve performance"): ``` function rand_cat() { echo $(( $RANDOM % 1024 )) }

function do_work() { while true; do echo -n "system_u:system_r:kernel_t:s0:c$(rand_cat),c$(rand_cat)" \ >/sys/fs/selinux/context 2>/dev/null || true done }

do_work >/dev/null & do_work >/dev/null & do_work >/dev/null &

while load_policy; do echo -n .; sleep 0.1; done

kill %1 kill %2 kill %3 ```

Fix this by allocating the temporary sidtab convert structures dynamically and passing them among the selinux_policy_{load,cancel,commit} functions.

Fixes: 02a52c5c8c3b ("selinux: move policy commit after updating selinuxfs") Cc: stable@vger.kernel.org Tested-by: Tyler Hicks tyhicks@linux.microsoft.com Reviewed-by: Tyler Hicks tyhicks@linux.microsoft.com Signed-off-by: Ondrej Mosnacek omosnace@redhat.com [PM: merge fuzz in security.h and services.c] Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- security/selinux/include/security.h | 15 ++++++-- security/selinux/selinuxfs.c | 10 ++--- security/selinux/ss/services.c | 65 ++++++++++++++++++++++-------------- 3 files changed, 56 insertions(+), 34 deletions(-)

--- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -219,14 +219,21 @@ static inline bool selinux_policycap_gen return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_GENFS_SECLABEL_SYMLINKS]); }

+struct selinux_policy_convert_data; + +struct selinux_load_state { + struct selinux_policy *policy; + struct selinux_policy_convert_data *convert_data; +}; + int security_mls_enabled(struct selinux_state *state); int security_load_policy(struct selinux_state *state, - void *data, size_t len, - struct selinux_policy **newpolicyp); + void *data, size_t len, + struct selinux_load_state *load_state); void selinux_policy_commit(struct selinux_state *state, - struct selinux_policy *newpolicy); + struct selinux_load_state *load_state); void selinux_policy_cancel(struct selinux_state *state, - struct selinux_policy *policy); + struct selinux_load_state *load_state); int security_read_policy(struct selinux_state *state, void **data, size_t *len);

--- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -616,7 +616,7 @@ static ssize_t sel_write_load(struct fil

{ struct selinux_fs_info *fsi = file_inode(file)->i_sb->s_fs_info; - struct selinux_policy *newpolicy; + struct selinux_load_state load_state; ssize_t length; void *data = NULL;

@@ -642,19 +642,19 @@ static ssize_t sel_write_load(struct fil if (copy_from_user(data, buf, count) != 0) goto out;

- length = security_load_policy(fsi->state, data, count, &newpolicy); + length = security_load_policy(fsi->state, data, count, &load_state); if (length) { pr_warn_ratelimited("SELinux: failed to load policy\n"); goto out; }

- length = sel_make_policy_nodes(fsi, newpolicy); + length = sel_make_policy_nodes(fsi, load_state.policy); if (length) { - selinux_policy_cancel(fsi->state, newpolicy); + selinux_policy_cancel(fsi->state, &load_state); goto out; }

- selinux_policy_commit(fsi->state, newpolicy); + selinux_policy_commit(fsi->state, &load_state);

length = count;

--- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -66,6 +66,17 @@ #include "audit.h" #include "policycap_names.h"

+struct convert_context_args { + struct selinux_state *state; + struct policydb *oldp; + struct policydb *newp; +}; + +struct selinux_policy_convert_data { + struct convert_context_args args; + struct sidtab_convert_params sidtab_params; +}; + /* Forward declaration. */ static int context_struct_to_string(struct policydb *policydb, struct context *context, @@ -1973,12 +1984,6 @@ static inline int convert_context_handle return 0; }

-struct convert_context_args { - struct selinux_state *state; - struct policydb *oldp; - struct policydb *newp; -}; - /* * Convert the values in the security context * structure `oldc' from the values specified @@ -2158,7 +2163,7 @@ static void selinux_policy_cond_free(str }

void selinux_policy_cancel(struct selinux_state *state, - struct selinux_policy *policy) + struct selinux_load_state *load_state) { struct selinux_policy *oldpolicy;

@@ -2166,7 +2171,8 @@ void selinux_policy_cancel(struct selinu lockdep_is_held(&state->policy_mutex));

sidtab_cancel_convert(oldpolicy->sidtab); - selinux_policy_free(policy); + selinux_policy_free(load_state->policy); + kfree(load_state->convert_data); }

static void selinux_notify_policy_change(struct selinux_state *state, @@ -2181,9 +2187,9 @@ static void selinux_notify_policy_change }

void selinux_policy_commit(struct selinux_state *state, - struct selinux_policy *newpolicy) + struct selinux_load_state *load_state) { - struct selinux_policy *oldpolicy; + struct selinux_policy *oldpolicy, *newpolicy = load_state->policy; u32 seqno;

oldpolicy = rcu_dereference_protected(state->policy, @@ -2223,6 +2229,7 @@ void selinux_policy_commit(struct selinu /* Free the old policy */ synchronize_rcu(); selinux_policy_free(oldpolicy); + kfree(load_state->convert_data);

/* Notify others of the policy change */ selinux_notify_policy_change(state, seqno); @@ -2239,11 +2246,10 @@ void selinux_policy_commit(struct selinu * loading the new policy. */ int security_load_policy(struct selinux_state *state, void *data, size_t len, - struct selinux_policy **newpolicyp) + struct selinux_load_state *load_state) { struct selinux_policy *newpolicy, *oldpolicy; - struct sidtab_convert_params convert_params; - struct convert_context_args args; + struct selinux_policy_convert_data *convert_data; int rc = 0; struct policy_file file = { data, len }, *fp = &file;

@@ -2273,10 +2279,10 @@ int security_load_policy(struct selinux_ goto err_mapping; }

- if (!selinux_initialized(state)) { /* First policy load, so no need to preserve state from old policy */ - *newpolicyp = newpolicy; + load_state->policy = newpolicy; + load_state->convert_data = NULL; return 0; }

@@ -2290,29 +2296,38 @@ int security_load_policy(struct selinux_ goto err_free_isids; }

+ convert_data = kmalloc(sizeof(*convert_data), GFP_KERNEL); + if (!convert_data) { + rc = -ENOMEM; + goto err_free_isids; + } + /* * Convert the internal representations of contexts * in the new SID table. */ - args.state = state; - args.oldp = &oldpolicy->policydb; - args.newp = &newpolicy->policydb; - - convert_params.func = convert_context; - convert_params.args = &args; - convert_params.target = newpolicy->sidtab; + convert_data->args.state = state; + convert_data->args.oldp = &oldpolicy->policydb; + convert_data->args.newp = &newpolicy->policydb; + + convert_data->sidtab_params.func = convert_context; + convert_data->sidtab_params.args = &convert_data->args; + convert_data->sidtab_params.target = newpolicy->sidtab;

- rc = sidtab_convert(oldpolicy->sidtab, &convert_params); + rc = sidtab_convert(oldpolicy->sidtab, &convert_data->sidtab_params); if (rc) { pr_err("SELinux: unable to convert the internal" " representation of contexts in the new SID" " table\n"); - goto err_free_isids; + goto err_free_convert_data; }

- *newpolicyp = newpolicy; + load_state->policy = newpolicy; + load_state->convert_data = convert_data; return 0;

+err_free_convert_data: + kfree(convert_data); err_free_isids: sidtab_destroy(newpolicy->sidtab); err_mapping:

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 @@ -47,8 +47,16 @@ 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: Thomas Hebb tommyhebb@gmail.com

commit 6d679578fe9c762c8fbc3d796a067cbba84a7884 upstream.

Commit ca0246bb97c2 ("z3fold: fix possible reclaim races") introduced the PAGE_CLAIMED flag "to avoid racing on a z3fold 'headless' page release." By atomically testing and setting the bit in each of z3fold_free() and z3fold_reclaim_page(), a double-free was avoided.

However, commit dcf5aedb24f8 ("z3fold: stricter locking and more careful reclaim") appears to have unintentionally broken this behavior by moving the PAGE_CLAIMED check in z3fold_reclaim_page() to after the page lock gets taken, which only happens for non-headless pages. For headless pages, the check is now skipped entirely and races can occur again.

I have observed such a race on my system:

page:00000000ffbd76b7 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x165316 flags: 0x2ffff0000000000() raw: 02ffff0000000000 ffffea0004535f48 ffff8881d553a170 0000000000000000 raw: 0000000000000000 0000000000000011 00000000ffffffff 0000000000000000 page dumped because: VM_BUG_ON_PAGE(page_ref_count(page) == 0) ------------[ cut here ]------------ kernel BUG at include/linux/mm.h:707! invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 2 PID: 291928 Comm: kworker/2:0 Tainted: G B 5.10.7-arch1-1-kasan #1 Hardware name: Gigabyte Technology Co., Ltd. H97N-WIFI/H97N-WIFI, BIOS F9b 03/03/2016 Workqueue: zswap-shrink shrink_worker RIP: 0010:__free_pages+0x10a/0x130 Code: c1 e7 06 48 01 ef 45 85 e4 74 d1 44 89 e6 31 d2 41 83 ec 01 e8 e7 b0 ff ff eb da 48 c7 c6 e0 32 91 88 48 89 ef e8 a6 89 f8 ff <0f> 0b 4c 89 e7 e8 fc 79 07 00 e9 33 ff ff ff 48 89 ef e8 ff 79 07 RSP: 0000:ffff88819a2ffb98 EFLAGS: 00010296 RAX: 0000000000000000 RBX: ffffea000594c5a8 RCX: 0000000000000000 RDX: 1ffffd4000b298b7 RSI: 0000000000000000 RDI: ffffea000594c5b8 RBP: ffffea000594c580 R08: 000000000000003e R09: ffff8881d5520bbb R10: ffffed103aaa4177 R11: 0000000000000001 R12: ffffea000594c5b4 R13: 0000000000000000 R14: ffff888165316000 R15: ffffea000594c588 FS: 0000000000000000(0000) GS:ffff8881d5500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f7c8c3654d8 CR3: 0000000103f42004 CR4: 00000000001706e0 Call Trace: z3fold_zpool_shrink+0x9b6/0x1240 shrink_worker+0x35/0x90 process_one_work+0x70c/0x1210 worker_thread+0x539/0x1200 kthread+0x330/0x400 ret_from_fork+0x22/0x30 Modules linked in: rfcomm ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter ccm algif_aead des_generic libdes ecb algif_skcipher cmac bnep md4 algif_hash af_alg vfat fat intel_rapl_msr intel_rapl_common x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel iwlmvm hid_logitech_hidpp kvm at24 mac80211 snd_hda_codec_realtek iTCO_wdt snd_hda_codec_generic intel_pmc_bxt snd_hda_codec_hdmi ledtrig_audio iTCO_vendor_support mei_wdt mei_hdcp snd_hda_intel snd_intel_dspcfg libarc4 soundwire_intel irqbypass iwlwifi soundwire_generic_allocation rapl soundwire_cadence intel_cstate snd_hda_codec intel_uncore btusb joydev mousedev snd_usb_audio pcspkr btrtl uvcvideo nouveau btbcm i2c_i801 btintel snd_hda_core videobuf2_vmalloc i2c_smbus snd_usbmidi_lib videobuf2_memops bluetooth snd_hwdep soundwire_bus snd_soc_rt5640 videobuf2_v4l2 cfg80211 snd_soc_rl6231 videobuf2_common snd_rawmidi lpc_ich alx videodev mdio snd_seq_device snd_soc_core mc ecdh_generic mxm_wmi mei_me hid_logitech_dj wmi snd_compress e1000e ac97_bus mei ttm rfkill snd_pcm_dmaengine ecc snd_pcm snd_timer snd soundcore mac_hid acpi_pad pkcs8_key_parser it87 hwmon_vid crypto_user fuse ip_tables x_tables ext4 crc32c_generic crc16 mbcache jbd2 dm_crypt cbc encrypted_keys trusted tpm rng_core usbhid dm_mod crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel aesni_intel crypto_simd cryptd glue_helper xhci_pci xhci_pci_renesas i915 video intel_gtt i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops cec drm agpgart ---[ end trace 126d646fc3dc0ad8 ]---

To fix the issue, re-add the earlier test and set in the case where we have a headless page.

Link: https://lkml.kernel.org/r/c8106dbe6d8390b290cd1d7f873a2942e805349e.161545204... Fixes: dcf5aedb24f8 ("z3fold: stricter locking and more careful reclaim") Signed-off-by: Thomas Hebb tommyhebb@gmail.com Reviewed-by: Vitaly Wool vitaly.wool@konsulko.com Cc: Jongseok Kim ks77sj@gmail.com Cc: Snild Dolkow snild@sony.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/z3fold.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-)

--- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -1353,8 +1353,22 @@ static int z3fold_reclaim_page(struct z3 page = list_entry(pos, struct page, lru);

zhdr = page_address(page); - if (test_bit(PAGE_HEADLESS, &page->private)) + if (test_bit(PAGE_HEADLESS, &page->private)) { + /* + * For non-headless pages, we wait to do this + * until we have the page lock to avoid racing + * with __z3fold_alloc(). Headless pages don't + * have a lock (and __z3fold_alloc() will never + * see them), but we still need to test and set + * PAGE_CLAIMED to avoid racing with + * z3fold_free(), so just do it now before + * leaving the loop. + */ + if (test_and_set_bit(PAGE_CLAIMED, &page->private)) + continue; + break; + }

if (kref_get_unless_zero(&zhdr->refcount) == 0) { zhdr = NULL;

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: Andrey Konovalov andreyknvl@google.com

commit cf10bd4c4aff8dd64d1aa7f2a529d0c672bc16af upstream.

To allow performing tag checks on page_alloc addresses obtained via page_address(), tag-based KASAN modes store tags for page_alloc allocations in page->flags.

Currently, the default tag value stored in page->flags is 0x00. Therefore, page_address() returns a 0x00ffff... address for pages that were not allocated via page_alloc.

This might cause problems. A particular case we encountered is a conflict with KFENCE. If a KFENCE-allocated slab object is being freed via kfree(page_address(page) + offset), the address passed to kfree() will get tagged with 0x00 (as slab pages keep the default per-page tags). This leads to is_kfence_address() check failing, and a KFENCE object ending up in normal slab freelist, which causes memory corruptions.

This patch changes the way KASAN stores tag in page-flags: they are now stored xor'ed with 0xff. This way, KASAN doesn't need to initialize per-page flags for every created page, which might be slow.

With this change, page_address() returns natively-tagged (with 0xff) pointers for pages that didn't have tags set explicitly.

This patch fixes the encountered conflict with KFENCE and prevents more similar issues that can occur in the future.

Link: https://lkml.kernel.org/r/1a41abb11c51b264511d9e71c303bb16d5cb367b.161547545... Fixes: 2813b9c02962 ("kasan, mm, arm64: tag non slab memory allocated via pagealloc") Signed-off-by: Andrey Konovalov andreyknvl@google.com Reviewed-by: Marco Elver elver@google.com Cc: Catalin Marinas catalin.marinas@arm.com Cc: Will Deacon will.deacon@arm.com Cc: Vincenzo Frascino vincenzo.frascino@arm.com Cc: Dmitry Vyukov dvyukov@google.com Cc: Andrey Ryabinin aryabinin@virtuozzo.com Cc: Alexander Potapenko glider@google.com Cc: Peter Collingbourne pcc@google.com Cc: Evgenii Stepanov eugenis@google.com Cc: Branislav Rankov Branislav.Rankov@arm.com Cc: Kevin Brodsky kevin.brodsky@arm.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 --- include/linux/mm.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-)

--- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1431,16 +1431,28 @@ static inline bool cpupid_match_pid(stru

#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)

+/* + * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid + * setting tags for all pages to native kernel tag value 0xff, as the default + * value 0x00 maps to 0xff. + */ + static inline u8 page_kasan_tag(const struct page *page) { - if (kasan_enabled()) - return (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; - return 0xff; + u8 tag = 0xff; + + if (kasan_enabled()) { + tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; + tag ^= 0xff; + } + + return tag; }

static inline void page_kasan_tag_set(struct page *page, u8 tag) { if (kasan_enabled()) { + tag ^= 0xff; page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; }

From: Ira Weiny ira.weiny@intel.com

commit 487cfade12fae0eb707bdce71c4d585128238a7d upstream.

The kernel test robot found that __kmap_local_sched_out() was not correctly skipping the guard pages when DEBUG_KMAP_LOCAL_FORCE_MAP was set.[1] This was due to DEBUG_HIGHMEM check being used.

Change the configuration check to be correct.

[1] https://lore.kernel.org/lkml/20210304083825.GB17830@xsang-OptiPlex-9020/

Link: https://lkml.kernel.org/r/20210318230657.1497881-1-ira.weiny@intel.com Fixes: 0e91a0c6984c ("mm/highmem: Provide CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP") Signed-off-by: Ira Weiny ira.weiny@intel.com Reported-by: kernel test robot oliver.sang@intel.com Reviewed-by: Thomas Gleixner tglx@linutronix.de Cc: Thomas Gleixner tglx@linutronix.de Cc: Oliver Sang oliver.sang@intel.com Cc: Chaitanya Kulkarni Chaitanya.Kulkarni@wdc.com Cc: David Sterba dsterba@suse.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/highmem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/highmem.c b/mm/highmem.c index 86f2b9495f9c..6ef8f5e05e7e 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -618,7 +618,7 @@ void __kmap_local_sched_out(void) int idx;

/* With debug all even slots are unmapped and act as guard */ - if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) { + if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { WARN_ON_ONCE(!pte_none(pteval)); continue; } @@ -654,7 +654,7 @@ void __kmap_local_sched_in(void) int idx;

/* With debug all even slots are unmapped and act as guard */ - if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) { + if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { WARN_ON_ONCE(!pte_none(pteval)); continue; }

From: Vegard Nossum vegard.nossum@oracle.com

commit 25928deeb1e4e2cdae1dccff349320c6841eb5f8 upstream.

ACPICA commit 29da9a2a3f5b2c60420893e5c6309a0586d7a329

ACPI is allocating an object using kmalloc(), but then frees it using kmem_cache_free(<"Acpi-Namespace" kmem_cache>).

This is wrong and can lead to boot failures manifesting like this:

hpet0: 3 comparators, 64-bit 100.000000 MHz counter clocksource: Switched to clocksource tsc-early BUG: unable to handle page fault for address: 000000003ffe0018 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.6.0+ #211 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 RIP: 0010:kmem_cache_alloc+0x70/0x1d0 Code: 00 00 4c 8b 45 00 65 49 8b 50 08 65 4c 03 05 6f cc e7 7e 4d 8b 20 4d 85 e4 0f 84 3d 01 00 00 8b 45 20 48 8b 7d 00 48 8d 4a 01 <49> 8b 1c 04 4c 89 e0 65 48 0f c7 0f 0f 94 c0 84 c0 74 c5 8b 45 20 RSP: 0000:ffffc90000013df8 EFLAGS: 00010206 RAX: 0000000000000018 RBX: ffffffff81c49200 RCX: 0000000000000002 RDX: 0000000000000001 RSI: 0000000000000dc0 RDI: 000000000002b300 RBP: ffff88803e403d00 R08: ffff88803ec2b300 R09: 0000000000000001 R10: 0000000000000dc0 R11: 0000000000000006 R12: 000000003ffe0000 R13: ffffffff8110a583 R14: 0000000000000dc0 R15: ffffffff81c49a80 FS: 0000000000000000(0000) GS:ffff88803ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000003ffe0018 CR3: 0000000001c0a001 CR4: 00000000003606f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __trace_define_field+0x33/0xa0 event_trace_init+0xeb/0x2b4 tracer_init_tracefs+0x60/0x195 ? register_tracer+0x1e7/0x1e7 do_one_initcall+0x74/0x160 kernel_init_freeable+0x190/0x1f0 ? rest_init+0x9a/0x9a kernel_init+0x5/0xf6 ret_from_fork+0x35/0x40 CR2: 000000003ffe0018 ---[ end trace 707efa023f2ee960 ]--- RIP: 0010:kmem_cache_alloc+0x70/0x1d0

Bisection leads to unrelated changes in slab; Vlastimil Babka suggests an unrelated layout or slab merge change merely exposed the underlying bug.

Link: https://lore.kernel.org/lkml/4dc93ff8-f86e-f4c9-ebeb-6d3153a78d03@oracle.com... Link: https://lore.kernel.org/r/a1461e21-c744-767d-6dfc-6641fd3e3ce2@siemens.com Link: https://github.com/acpica/acpica/commit/29da9a2a Fixes: f79c8e4136ea ("ACPICA: Namespace: simplify creation of the initial/default namespace") Reported-by: Jan Kiszka jan.kiszka@siemens.com Diagnosed-by: Vlastimil Babka vbabka@suse.cz Diagnosed-by: Kees Cook keescook@chromium.org Signed-off-by: Vegard Nossum vegard.nossum@oracle.com Signed-off-by: Bob Moore robert.moore@intel.com Signed-off-by: Erik Kaneda erik.kaneda@intel.com Cc: 5.10+ stable@vger.kernel.org # 5.10+ Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/acpi/acpica/nsaccess.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/acpi/acpica/nsaccess.c +++ b/drivers/acpi/acpica/nsaccess.c @@ -99,13 +99,12 @@ acpi_status acpi_ns_root_initialize(void * just create and link the new node(s) here. */ new_node = - ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_namespace_node)); + acpi_ns_create_node(*ACPI_CAST_PTR(u32, init_val->name)); if (!new_node) { status = AE_NO_MEMORY; goto unlock_and_exit; }

- ACPI_COPY_NAMESEG(new_node->name.ascii, init_val->name); new_node->descriptor_type = ACPI_DESC_TYPE_NAMED; new_node->type = init_val->type;

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 @@ -325,6 +325,7 @@ 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 @@ -322,6 +322,7 @@ 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: Nicolas Ferre nicolas.ferre@microchip.com

commit 2c69c8a1736eace8de491d480e6e577a27c2087c upstream.

Fix the whole mux-mask table according to datasheet for the sam9x60 product. Too much functions for pins were disabled leading to misunderstandings when enabling more peripherals or taking this table as an example for another board. Take advantage of this fix to move the mux-mask in the SoC file where it belongs and use lower case letters for hex numbers like everywhere in the file.

Signed-off-by: Nicolas Ferre nicolas.ferre@microchip.com Fixes: 1e5f532c2737 ("ARM: dts: at91: sam9x60: add device tree for soc and board") Cc: stable@vger.kernel.org # 5.6+ Cc: Sandeep Sheriker Mallikarjun sandeepsheriker.mallikarjun@microchip.com Reviewed-by: Tudor Ambarus tudor.ambarus@microchip.com Link: https://lore.kernel.org/r/20210310152006.15018-1-nicolas.ferre@microchip.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/boot/dts/at91-sam9x60ek.dts | 8 -------- arch/arm/boot/dts/sam9x60.dtsi | 9 +++++++++ 2 files changed, 9 insertions(+), 8 deletions(-)

--- a/arch/arm/boot/dts/at91-sam9x60ek.dts +++ b/arch/arm/boot/dts/at91-sam9x60ek.dts @@ -334,14 +334,6 @@ };

&pinctrl { - atmel,mux-mask = < - /* A B C */ - 0xFFFFFEFF 0xC0E039FF 0xEF00019D /* pioA */ - 0x03FFFFFF 0x02FC7E68 0x00780000 /* pioB */ - 0xffffffff 0xF83FFFFF 0xB800F3FC /* pioC */ - 0x003FFFFF 0x003F8000 0x00000000 /* pioD */ - >; - adc { pinctrl_adc_default: adc_default { atmel,pins = <AT91_PIOB 15 AT91_PERIPH_A AT91_PINCTRL_NONE>; --- a/arch/arm/boot/dts/sam9x60.dtsi +++ b/arch/arm/boot/dts/sam9x60.dtsi @@ -606,6 +606,15 @@ compatible = "microchip,sam9x60-pinctrl", "atmel,at91sam9x5-pinctrl", "atmel,at91rm9200-pinctrl", "simple-bus"; ranges = <0xfffff400 0xfffff400 0x800>;

+ /* mux-mask corresponding to sam9x60 SoC in TFBGA228L package */ + atmel,mux-mask = < + /* A B C */ + 0xffffffff 0xffe03fff 0xef00019d /* pioA */ + 0x03ffffff 0x02fc7e7f 0x00780000 /* pioB */ + 0xffffffff 0xffffffff 0xf83fffff /* pioC */ + 0x003fffff 0x003f8000 0x00000000 /* pioD */ + >; + pioA: gpio@fffff400 { compatible = "microchip,sam9x60-gpio", "atmel,at91sam9x5-gpio", "atmel,at91rm9200-gpio"; reg = <0xfffff400 0x200>;

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: Daniel Vetter daniel.vetter@ffwll.ch

commit cd5297b0855f17c8b4e3ef1d20c6a3656209c7b3 upstream.

Nothing checks userptr.ro except this call to pup_fast, which means there's nothing actually preventing userspace from writing to this. Which means you can just read-only mmap any file you want, userptr it and then write to it with the gpu. Not good.

The right way to handle this is FOLL_WRITE | FOLL_FORCE, which will break any COW mappings and update tracking for MAY_WRITE mappings so there's no exploit and the vm isn't confused about what's going on. For any legit use case there's no difference from what userspace can observe and do.

Reviewed-by: Lucas Stach l.stach@pengutronix.de Cc: stable@vger.kernel.org Cc: John Hubbard jhubbard@nvidia.com Signed-off-by: Daniel Vetter daniel.vetter@intel.com Cc: Lucas Stach l.stach@pengutronix.de Cc: Russell King linux+etnaviv@armlinux.org.uk Cc: Christian Gmeiner christian.gmeiner@gmail.com Cc: etnaviv@lists.freedesktop.org Link: https://patchwork.freedesktop.org/patch/msgid/20210301095254.1946084-1-danie... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/etnaviv/etnaviv_gem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -689,7 +689,7 @@ static int etnaviv_gem_userptr_get_pages struct page **pages = pvec + pinned;

ret = pin_user_pages_fast(ptr, num_pages, - !userptr->ro ? FOLL_WRITE : 0, pages); + FOLL_WRITE | FOLL_FORCE, pages); if (ret < 0) { unpin_user_pages(pvec, pinned); kvfree(pvec);

From: Alex Deucher alexander.deucher@amd.com

commit 5c458585c0141754cdcbf25feebb547dd671b559 upstream.

Commit 098214999c8f added fetching of the AUX_DPHY register values from the vbios, but it also changed the default values in the case when there are no values in the vbios. This causes problems with displays with high refresh rates. To fix this, switch back to the original default value for AUX_DPHY_TX_CONTROL.

Fixes: 098214999c8f ("drm/amd/display: Read VBIOS Golden Settings Tbl") Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1426 Reviewed-by: Harry Wentland harry.wentland@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: Igor Kravchenko Igor.Kravchenko@amd.com Cc: Aric Cyr Aric.Cyr@amd.com Cc: Aurabindo Pillai aurabindo.pillai@amd.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c @@ -341,8 +341,7 @@ void enc2_hw_init(struct link_encoder *e } else { AUX_REG_WRITE(AUX_DPHY_RX_CONTROL0, 0x103d1110);

- AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c4d); - + AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c7a); }

//AUX_DPHY_TX_REF_CONTROL'AUX_TX_REF_DIV HW default is 0x32;

From: Alex Deucher alexander.deucher@amd.com

commit c933b111094f2818571fc51b81b98ee0d370c035 upstream.

Add new DID.

Reviewed-by: Guchun Chen guchun.chen@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1102,6 +1102,7 @@ static const struct pci_device_id pciidl {0x1002, 0x73A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, {0x1002, 0x73AB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, {0x1002, 0x73AE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73AF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, {0x1002, 0x73BF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},

/* Van Gogh */

From: Imre Deak imre.deak@intel.com

commit 8840e3bd981f128846b01c12d3966d115e8617c9 upstream.

To optimize some task deferring it until runtime resume unless someone holds a runtime PM reference (because in this case the task can be done w/o the overhead of runtime resume), we have to use the runtime PM get-if-active logic: If the runtime PM usage count is 0 (and so get-if-in-use would return false) the runtime suspend handler is not necessarily called yet (it could be just pending), so the device is not necessarily powered down, and so the runtime resume handler is not guaranteed to be called.

The fence revocation depends on the above deferral, so add a get-if-active helper and use it during fence revocation.

v2: - Add code comment explaining the fence reg programming deferral logic to i915_vma_revoke_fence(). (Chris) - Add Cc: stable and Fixes: tags. (Chris) - Fix the function docbook comment.

Cc: Chris Wilson chris@chris-wilson.co.uk Cc: stable@vger.kernel.org # v4.12+ Fixes: 181df2d458f3 ("drm/i915: Take rpm wakelock for releasing the fence on unbind") Reviewed-by: Chris Wilson chris@chris-wilson.co.uk Signed-off-by: Imre Deak imre.deak@intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20210322204223.919936-1-imre.d... (cherry picked from commit 9d58aa46291d4d696bb1eac3436d3118f7bf2573) Signed-off-by: Rodrigo Vivi rodrigo.vivi@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c | 13 +++++++++++- drivers/gpu/drm/i915/intel_runtime_pm.c | 29 ++++++++++++++++++++++----- drivers/gpu/drm/i915/intel_runtime_pm.h | 5 ++++ 3 files changed, 41 insertions(+), 6 deletions(-)

--- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -316,7 +316,18 @@ void i915_vma_revoke_fence(struct i915_v WRITE_ONCE(fence->vma, NULL); vma->fence = NULL;

- with_intel_runtime_pm_if_in_use(fence_to_uncore(fence)->rpm, wakeref) + /* + * Skip the write to HW if and only if the device is currently + * suspended. + * + * If the driver does not currently hold a wakeref (if_in_use == 0), + * the device may currently be runtime suspended, or it may be woken + * up before the suspend takes place. If the device is not suspended + * (powered down) and we skip clearing the fence register, the HW is + * left in an undefined state where we may end up with multiple + * registers overlapping. + */ + with_intel_runtime_pm_if_active(fence_to_uncore(fence)->rpm, wakeref) fence_write(fence); }

--- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -412,12 +412,20 @@ intel_wakeref_t intel_runtime_pm_get(str }

/** - * intel_runtime_pm_get_if_in_use - grab a runtime pm reference if device in use + * __intel_runtime_pm_get_if_active - grab a runtime pm reference if device is active * @rpm: the intel_runtime_pm structure + * @ignore_usecount: get a ref even if dev->power.usage_count is 0 * * This function grabs a device-level runtime pm reference if the device is - * already in use and ensures that it is powered up. It is illegal to try - * and access the HW should intel_runtime_pm_get_if_in_use() report failure. + * already active and ensures that it is powered up. It is illegal to try + * and access the HW should intel_runtime_pm_get_if_active() report failure. + * + * If @ignore_usecount=true, a reference will be acquired even if there is no + * user requiring the device to be powered up (dev->power.usage_count == 0). + * If the function returns false in this case then it's guaranteed that the + * device's runtime suspend hook has been called already or that it will be + * called (and hence it's also guaranteed that the device's runtime resume + * hook will be called eventually). * * Any runtime pm reference obtained by this function must have a symmetric * call to intel_runtime_pm_put() to release the reference again. @@ -425,7 +433,8 @@ intel_wakeref_t intel_runtime_pm_get(str * Returns: the wakeref cookie to pass to intel_runtime_pm_put(), evaluates * as True if the wakeref was acquired, or False otherwise. */ -intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm) +static intel_wakeref_t __intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm, + bool ignore_usecount) { if (IS_ENABLED(CONFIG_PM)) { /* @@ -434,7 +443,7 @@ intel_wakeref_t intel_runtime_pm_get_if_ * function, since the power state is undefined. This applies * atm to the late/early system suspend/resume handlers. */ - if (pm_runtime_get_if_in_use(rpm->kdev) <= 0) + if (pm_runtime_get_if_active(rpm->kdev, ignore_usecount) <= 0) return 0; }

@@ -443,6 +452,16 @@ intel_wakeref_t intel_runtime_pm_get_if_ return track_intel_runtime_pm_wakeref(rpm); }

+intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm) +{ + return __intel_runtime_pm_get_if_active(rpm, false); +} + +intel_wakeref_t intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm) +{ + return __intel_runtime_pm_get_if_active(rpm, true); +} + /** * intel_runtime_pm_get_noresume - grab a runtime pm reference * @rpm: the intel_runtime_pm structure --- a/drivers/gpu/drm/i915/intel_runtime_pm.h +++ b/drivers/gpu/drm/i915/intel_runtime_pm.h @@ -177,6 +177,7 @@ void intel_runtime_pm_driver_release(str

intel_wakeref_t intel_runtime_pm_get(struct intel_runtime_pm *rpm); intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm); +intel_wakeref_t intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm); intel_wakeref_t intel_runtime_pm_get_noresume(struct intel_runtime_pm *rpm); intel_wakeref_t intel_runtime_pm_get_raw(struct intel_runtime_pm *rpm);

@@ -188,6 +189,10 @@ intel_wakeref_t intel_runtime_pm_get_raw for ((wf) = intel_runtime_pm_get_if_in_use(rpm); (wf); \ intel_runtime_pm_put((rpm), (wf)), (wf) = 0)

+#define with_intel_runtime_pm_if_active(rpm, wf) \ + for ((wf) = intel_runtime_pm_get_if_active(rpm); (wf); \ + intel_runtime_pm_put((rpm), (wf)), (wf) = 0) + void intel_runtime_pm_put_unchecked(struct intel_runtime_pm *rpm); #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM) void intel_runtime_pm_put(struct intel_runtime_pm *rpm, intel_wakeref_t wref);

From: Mikulas Patocka mpatocka@redhat.com

commit 5424a0b867e65f1ecf34ffe88d091a4fcbb35bc1 upstream.

When a DM device is first created it doesn't yet have an established capacity, therefore the use of set_capacity_and_notify() should be conditional given the potential for needless pr_info "detected capacity change" noise even if capacity is 0.

One could argue that the pr_info() in set_capacity_and_notify() is misplaced, but that position is not held uniformly.

Signed-off-by: Mikulas Patocka mpatocka@redhat.com Fixes: f64d9b2eacb9 ("dm: use set_capacity_and_notify") 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.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2016,7 +2016,10 @@ static struct dm_table *__bind(struct ma if (size != dm_get_size(md)) memset(&md->geometry, 0, sizeof(md->geometry));

- set_capacity_and_notify(md->disk, size); + if (!get_capacity(md->disk)) + set_capacity(md->disk, size); + else + set_capacity_and_notify(md->disk, size);

dm_table_event_callback(t, event_callback, md);

From: Grygorii Strashko grygorii.strashko@ti.com

[ Upstream commit 7d7275b3e866cf8092bd12553ec53ba26864f7bb ]

The main purpose of l3 IRQs is to catch OCP bus access errors and identify corresponding code places by showing call stack, so it's important to handle L3 interconnect errors as fast as possible. On RT these IRQs will became threaded and will be scheduled much more late from the moment actual error occurred so showing completely useless information.

Hence, mark l3 IRQs as IRQF_NO_THREAD so they will not be forced threaded on RT or if force_irqthreads = true.

Fixes: 0ee7261c9212 ("drivers: bus: Move the OMAP interconnect driver to drivers/bus/") Signed-off-by: Grygorii Strashko grygorii.strashko@ti.com Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/bus/omap_l3_noc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/bus/omap_l3_noc.c b/drivers/bus/omap_l3_noc.c index b040447575ad..dcfb32ee5cb6 100644 --- a/drivers/bus/omap_l3_noc.c +++ b/drivers/bus/omap_l3_noc.c @@ -285,7 +285,7 @@ static int omap_l3_probe(struct platform_device *pdev) */ l3->debug_irq = platform_get_irq(pdev, 0); ret = devm_request_irq(l3->dev, l3->debug_irq, l3_interrupt_handler, - 0x0, "l3-dbg-irq", l3); + IRQF_NO_THREAD, "l3-dbg-irq", l3); if (ret) { dev_err(l3->dev, "request_irq failed for %d\n", l3->debug_irq); @@ -294,7 +294,7 @@ static int omap_l3_probe(struct platform_device *pdev)

l3->app_irq = platform_get_irq(pdev, 1); ret = devm_request_irq(l3->dev, l3->app_irq, l3_interrupt_handler, - 0x0, "l3-app-irq", l3); + IRQF_NO_THREAD, "l3-app-irq", l3); if (ret) dev_err(l3->dev, "request_irq failed for %d\n", l3->app_irq);

From: Tony Lindgren tony@atomide.com

[ Upstream commit fbfa463be8dc7957ee4f81556e9e1ea2a951807d ]

When I dropped legacy data for omap4 and dra7 smartreflex in favor of device tree based data, it seems I only testd for the "SmartReflex Class3 initialized" line in dmesg. I missed the fact that there is also omap_devinit_smartreflex() that happens later, and now it produces an error on boot for "No Voltage table for the corresponding vdd. Cannot create debugfs entries for n-values".

This happens as we no longer have the smartreflex instance legacy data, and have not yet moved completely to device tree based booting for the driver. Let's fix the issue by changing the smartreflex init to use names. This should all eventually go away in favor of doing the init in the driver based on devicetree compatible value.

Note that dra7xx_init_early() is not calling any voltage domain init like omap54xx_voltagedomains_init(), or a dra7 specific voltagedomains init. This means that on dra7 smartreflex is still not fully initialized, and also seems to be missing the related devicetree nodes.

Fixes: a6b1e717e942 ("ARM: OMAP2+: Drop legacy platform data for omap4 smartreflex") Fixes: e54740b4afe8 ("ARM: OMAP2+: Drop legacy platform data for dra7 smartreflex") Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mach-omap2/sr_device.c | 75 +++++++++++++++++++++++++-------- 1 file changed, 58 insertions(+), 17 deletions(-)

diff --git a/arch/arm/mach-omap2/sr_device.c b/arch/arm/mach-omap2/sr_device.c index 62df666c2bd0..17b66f0d0dee 100644 --- a/arch/arm/mach-omap2/sr_device.c +++ b/arch/arm/mach-omap2/sr_device.c @@ -88,34 +88,26 @@ static void __init sr_set_nvalues(struct omap_volt_data *volt_data,

extern struct omap_sr_data omap_sr_pdata[];

-static int __init sr_dev_init(struct omap_hwmod *oh, void *user) +static int __init sr_init_by_name(const char *name, const char *voltdm) { struct omap_sr_data *sr_data = NULL; struct omap_volt_data *volt_data; - struct omap_smartreflex_dev_attr *sr_dev_attr; static int i;

- if (!strncmp(oh->name, "smartreflex_mpu_iva", 20) || - !strncmp(oh->name, "smartreflex_mpu", 16)) + if (!strncmp(name, "smartreflex_mpu_iva", 20) || + !strncmp(name, "smartreflex_mpu", 16)) sr_data = &omap_sr_pdata[OMAP_SR_MPU]; - else if (!strncmp(oh->name, "smartreflex_core", 17)) + else if (!strncmp(name, "smartreflex_core", 17)) sr_data = &omap_sr_pdata[OMAP_SR_CORE]; - else if (!strncmp(oh->name, "smartreflex_iva", 16)) + else if (!strncmp(name, "smartreflex_iva", 16)) sr_data = &omap_sr_pdata[OMAP_SR_IVA];

if (!sr_data) { - pr_err("%s: Unknown instance %s\n", __func__, oh->name); + pr_err("%s: Unknown instance %s\n", __func__, name); return -EINVAL; }

- sr_dev_attr = (struct omap_smartreflex_dev_attr *)oh->dev_attr; - if (!sr_dev_attr || !sr_dev_attr->sensor_voltdm_name) { - pr_err("%s: No voltage domain specified for %s. Cannot initialize\n", - __func__, oh->name); - goto exit; - } - - sr_data->name = oh->name; + sr_data->name = name; if (cpu_is_omap343x()) sr_data->ip_type = 1; else @@ -136,10 +128,10 @@ static int __init sr_dev_init(struct omap_hwmod *oh, void *user) } }

- sr_data->voltdm = voltdm_lookup(sr_dev_attr->sensor_voltdm_name); + sr_data->voltdm = voltdm_lookup(voltdm); if (!sr_data->voltdm) { pr_err("%s: Unable to get voltage domain pointer for VDD %s\n", - __func__, sr_dev_attr->sensor_voltdm_name); + __func__, voltdm); goto exit; }

@@ -160,6 +152,20 @@ exit: return 0; }

+static int __init sr_dev_init(struct omap_hwmod *oh, void *user) +{ + struct omap_smartreflex_dev_attr *sr_dev_attr; + + sr_dev_attr = (struct omap_smartreflex_dev_attr *)oh->dev_attr; + if (!sr_dev_attr || !sr_dev_attr->sensor_voltdm_name) { + pr_err("%s: No voltage domain specified for %s. Cannot initialize\n", + __func__, oh->name); + return 0; + } + + return sr_init_by_name(oh->name, sr_dev_attr->sensor_voltdm_name); +} + /* * API to be called from board files to enable smartreflex * autocompensation at init. @@ -169,7 +175,42 @@ void __init omap_enable_smartreflex_on_init(void) sr_enable_on_init = true; }

+static const char * const omap4_sr_instances[] = { + "mpu", + "iva", + "core", +}; + +static const char * const dra7_sr_instances[] = { + "mpu", + "core", +}; + int __init omap_devinit_smartreflex(void) { + const char * const *sr_inst; + int i, nr_sr = 0; + + if (soc_is_omap44xx()) { + sr_inst = omap4_sr_instances; + nr_sr = ARRAY_SIZE(omap4_sr_instances); + + } else if (soc_is_dra7xx()) { + sr_inst = dra7_sr_instances; + nr_sr = ARRAY_SIZE(dra7_sr_instances); + } + + if (nr_sr) { + const char *name, *voltdm; + + for (i = 0; i < nr_sr; i++) { + name = kasprintf(GFP_KERNEL, "smartreflex_%s", sr_inst[i]); + voltdm = sr_inst[i]; + sr_init_by_name(name, voltdm); + } + + return 0; + } + return omap_hwmod_for_each_by_class("smartreflex", sr_dev_init, NULL); }

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 02bfcdf50a7a..36abe756282e 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -301,8 +301,7 @@ 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: Tal Lossos tallossos@gmail.com

[ Upstream commit 769c18b254ca191b45047e1fcb3b2ce56fada0b6 ]

bpf_fd_inode_storage_lookup_elem() returned NULL when getting a bad FD, which caused -ENOENT in bpf_map_copy_value. -EBADF error is better than -ENOENT for a bad FD behaviour.

The patch was partially contributed by CyberArk Software, Inc.

Fixes: 8ea636848aca ("bpf: Implement bpf_local_storage for inodes") Signed-off-by: Tal Lossos tallossos@gmail.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Acked-by: Yonghong Song yhs@fb.com Acked-by: KP Singh kpsingh@kernel.org Link: https://lore.kernel.org/bpf/20210307120948.61414-1-tallossos@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/bpf/bpf_inode_storage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 6639640523c0..b58b2efb9b43 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -109,7 +109,7 @@ static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key) fd = *(int *)key; f = fget_raw(fd); if (!f) - return NULL; + return ERR_PTR(-EBADF);

sdata = inode_storage_lookup(f->f_inode, map, true); fput(f);

From: Tariq Toukan tariqt@nvidia.com

[ Upstream commit d5dd03b26ba49c4ffe67ee1937add82293c19794 ]

Since cited patch, MLX5E_REQUIRED_WQE_MTTS is not a power of two. Hence, usage of MLX5E_LOG_ALIGNED_MPWQE_PPW should be replaced, as it lost some accuracy. Use the designated macro to calculate the number of required MTTs.

This makes sure the solution in cited patch works properly.

While here, un-inline mlx5e_get_mpwqe_offset(), and remove the unused RQ parameter.

Fixes: c3c9402373fe ("net/mlx5e: Add resiliency in Striding RQ mode for packets larger than MTU") Signed-off-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.h | 7 ++++--- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 6 +++--- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 4 ++-- 3 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 055baf3b6cb1..f258f2f9b8cf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -90,14 +90,15 @@ struct page_pool; MLX5_MPWRQ_LOG_WQE_SZ - PAGE_SHIFT : 0) #define MLX5_MPWRQ_PAGES_PER_WQE BIT(MLX5_MPWRQ_WQE_PAGE_ORDER)

-#define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2) +#define MLX5_ALIGN_MTTS(mtts) (ALIGN(mtts, 8)) +#define MLX5_ALIGNED_MTTS_OCTW(mtts) ((mtts) / 2) +#define MLX5_MTT_OCTW(mtts) (MLX5_ALIGNED_MTTS_OCTW(MLX5_ALIGN_MTTS(mtts))) /* Add another page to MLX5E_REQUIRED_WQE_MTTS as a buffer between * WQEs, This page will absorb write overflow by the hardware, when * receiving packets larger than MTU. These oversize packets are * dropped by the driver at a later stage. */ -#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE + 1, 8)) -#define MLX5E_LOG_ALIGNED_MPWQE_PPW (ilog2(MLX5E_REQUIRED_WQE_MTTS)) +#define MLX5E_REQUIRED_WQE_MTTS (MLX5_ALIGN_MTTS(MLX5_MPWRQ_PAGES_PER_WQE + 1)) #define MLX5E_REQUIRED_MTTS(wqes) (wqes * MLX5E_REQUIRED_WQE_MTTS) #define MLX5E_MAX_RQ_NUM_MTTS \ ((1 << 16) * 2) /* So that MLX5_MTT_OCTW(num_mtts) fits into u16 */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index a2e0b548bf57..e479cce3e2b1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -305,9 +305,9 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq rq->wqe_overflow.addr); }

-static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix) +static u64 mlx5e_get_mpwqe_offset(u16 wqe_ix) { - return (wqe_ix << MLX5E_LOG_ALIGNED_MPWQE_PPW) << PAGE_SHIFT; + return MLX5E_REQUIRED_MTTS(wqe_ix) << PAGE_SHIFT; }

static void mlx5e_init_frags_partition(struct mlx5e_rq *rq) @@ -547,7 +547,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, mlx5_wq_ll_get_wqe(&rq->mpwqe.wq, i); u32 byte_count = rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz; - u64 dma_offset = mlx5e_get_mpwqe_offset(rq, i); + u64 dma_offset = mlx5e_get_mpwqe_offset(i);

wqe->data[0].addr = cpu_to_be64(dma_offset + rq->buff.headroom); wqe->data[0].byte_count = cpu_to_be32(byte_count); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 4864deed9dc9..b2e71a045df0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -505,7 +505,6 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) struct mlx5e_icosq *sq = rq->icosq; struct mlx5_wq_cyc *wq = &sq->wq; struct mlx5e_umr_wqe *umr_wqe; - u16 xlt_offset = ix << (MLX5E_LOG_ALIGNED_MPWQE_PPW - 1); u16 pi; int err; int i; @@ -536,7 +535,8 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) umr_wqe->ctrl.opmod_idx_opcode = cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) | MLX5_OPCODE_UMR); - umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset); + umr_wqe->uctrl.xlt_offset = + cpu_to_be16(MLX5_ALIGNED_MTTS_OCTW(MLX5E_REQUIRED_MTTS(ix)));

sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) { .wqe_type = MLX5E_ICOSQ_WQE_UMR_RX,

From: Maxim Mikityanskiy maximmi@mellanox.com

[ Upstream commit e5eb01344e9b09bb9d255b9727449186f7168df8 ]

Each RQ (including XSK RQs) takes a reference to the XDP program. When an XDP program is attached or detached, the channels and queues are recreated, however, there is a special flow for changing an active XDP program to another one. In that flow, channels and queues stay alive, but the refcounts of the old and new XDP programs are adjusted. This flow didn't increment refcount by the number of active XSK RQs, and this commit fixes it.

Fixes: db05815b36cb ("net/mlx5e: Add XSK zero-copy support") Signed-off-by: Maxim Mikityanskiy maximmi@mellanox.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_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 3248741af440..1386212ad3f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4550,8 +4550,10 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) struct mlx5e_channel *c = priv->channels.c[i];

mlx5e_rq_replace_xdp_prog(&c->rq, prog); - if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) + if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) { + bpf_prog_inc(prog); mlx5e_rq_replace_xdp_prog(&c->xskrq, prog); + } }

unlock:

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 e472ed0eacfb..7ed3f9f79f11 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: Wei Wang weiwan@google.com

[ Upstream commit 28259bac7f1dde06d8ba324e222bbec9d4e92f2b ]

Syzbot reported the suspecious RCU usage in nexthop_fib6_nh() when called from ipv6_route_seq_show(). The reason is ipv6_route_seq_start() calls rcu_read_lock_bh(), while nexthop_fib6_nh() calls rcu_dereference_rtnl(). The fix proposed is to add a variant of nexthop_fib6_nh() to use rcu_dereference_bh_rtnl() for ipv6_route_seq_show().

The reported trace is as follows: ./include/net/nexthop.h:416 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1 2 locks held by syz-executor.0/17895: at: seq_read+0x71/0x12a0 fs/seq_file.c:169 at: seq_file_net include/linux/seq_file_net.h:19 [inline] at: ipv6_route_seq_start+0xaf/0x300 net/ipv6/ip6_fib.c:2616

stack backtrace: CPU: 1 PID: 17895 Comm: syz-executor.0 Not tainted 4.15.0-syzkaller #0 Call Trace: [<ffffffff849edf9e>] __dump_stack lib/dump_stack.c:17 [inline] [<ffffffff849edf9e>] dump_stack+0xd8/0x147 lib/dump_stack.c:53 [<ffffffff8480b7fa>] lockdep_rcu_suspicious+0x153/0x15d kernel/locking/lockdep.c:5745 [<ffffffff8459ada6>] nexthop_fib6_nh include/net/nexthop.h:416 [inline] [<ffffffff8459ada6>] ipv6_route_native_seq_show net/ipv6/ip6_fib.c:2488 [inline] [<ffffffff8459ada6>] ipv6_route_seq_show+0x436/0x7a0 net/ipv6/ip6_fib.c:2673 [<ffffffff81c556df>] seq_read+0xccf/0x12a0 fs/seq_file.c:276 [<ffffffff81dbc62c>] proc_reg_read+0x10c/0x1d0 fs/proc/inode.c:231 [<ffffffff81bc28ae>] do_loop_readv_writev fs/read_write.c:714 [inline] [<ffffffff81bc28ae>] do_loop_readv_writev fs/read_write.c:701 [inline] [<ffffffff81bc28ae>] do_iter_read+0x49e/0x660 fs/read_write.c:935 [<ffffffff81bc81ab>] vfs_readv+0xfb/0x170 fs/read_write.c:997 [<ffffffff81c88847>] kernel_readv fs/splice.c:361 [inline] [<ffffffff81c88847>] default_file_splice_read+0x487/0x9c0 fs/splice.c:416 [<ffffffff81c86189>] do_splice_to+0x129/0x190 fs/splice.c:879 [<ffffffff81c86f66>] splice_direct_to_actor+0x256/0x890 fs/splice.c:951 [<ffffffff81c8777d>] do_splice_direct+0x1dd/0x2b0 fs/splice.c:1060 [<ffffffff81bc4747>] do_sendfile+0x597/0xce0 fs/read_write.c:1459 [<ffffffff81bca205>] SYSC_sendfile64 fs/read_write.c:1520 [inline] [<ffffffff81bca205>] SyS_sendfile64+0x155/0x170 fs/read_write.c:1506 [<ffffffff81015fcf>] do_syscall_64+0x1ff/0x310 arch/x86/entry/common.c:305 [<ffffffff84a00076>] entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: f88d8ea67fbdb ("ipv6: Plumb support for nexthop object in a fib6_info") Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: Wei Wang weiwan@google.com Cc: David Ahern dsahern@kernel.org Cc: Ido Schimmel idosch@idosch.org Cc: Petr Machata petrm@nvidia.com Cc: Eric Dumazet edumazet@google.com Reviewed-by: Ido Schimmel idosch@nvidia.com Reviewed-by: David Ahern dsahern@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/nexthop.h | 24 ++++++++++++++++++++++++ net/ipv6/ip6_fib.c | 2 +- 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 226930d66b63..abd620103cec 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -400,6 +400,7 @@ static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel) int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, struct netlink_ext_ack *extack);

+/* Caller should either hold rcu_read_lock(), or RTNL. */ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) { struct nh_info *nhi; @@ -420,6 +421,29 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) return NULL; }

+/* Variant of nexthop_fib6_nh(). + * Caller should either hold rcu_read_lock_bh(), or RTNL. + */ +static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh) +{ + struct nh_info *nhi; + + if (nh->is_group) { + struct nh_group *nh_grp; + + nh_grp = rcu_dereference_bh_rtnl(nh->nh_grp); + nh = nexthop_mpath_select(nh_grp, 0); + if (!nh) + return NULL; + } + + nhi = rcu_dereference_bh_rtnl(nh->nh_info); + if (nhi->family == AF_INET6) + return &nhi->fib6_nh; + + return NULL; +} + static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) { struct fib6_nh *fib6_nh; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index f43e27555725..1fb79dbde0cb 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2485,7 +2485,7 @@ static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) const struct net_device *dev;

if (rt->nh) - fib6_nh = nexthop_fib6_nh(rt->nh); + fib6_nh = nexthop_fib6_nh_bh(rt->nh);

seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen);

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 96556c64c95d..10c94a3936ca 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -43,13 +43,14 @@ 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 edb0a1027b38..510324916e91 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -584,8 +584,10 @@ 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 8876529465c368beafd51a70f79d7a738f2aadf4 ]

Fix Pause Frame Advertising when getting the advertisement via ethtool. Remove setting the "advertising" bit in link_ksettings during default case when Tx and Rx are in off state with Auto Negotiate off.

Below is the original output of advertisement link during Tx and Rx off: Advertised pause frame use: Symmetric Receive-only

Expected output: Advertised pause frame use: No

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 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/igc/igc_ethtool.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index ec8cd69d4992..35c104a02bed 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1709,9 +1709,7 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev, Asym_Pause); break; default: - ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - Asym_Pause); + break; }

status = pm_runtime_suspended(&adapter->pdev->dev) ?

From: Andre Guedes andre.guedes@intel.com

[ Upstream commit fc9e5020971d57d7d0b3fef9e2ab2108fcb5588b ]

The comment describing the timestamps layout in the packet buffer is wrong and the code is actually retrieving the timestamp in Timer 1 reference instead of Timer 0. This hasn't been a big issue so far because hardware is configured to report both timestamps using Timer 0 (see IGC_SRRCTL register configuration in igc_ptp_enable_rx_timestamp() helper). This patch fixes the comment and the code so we retrieve the timestamp in Timer 0 reference as expected.

This patch also takes the opportunity to get rid of the hw.mac.type check since it is not required.

Fixes: 81b055205e8ba ("igc: Add support for RX timestamping") Signed-off-by: Andre Guedes andre.guedes@intel.com Signed-off-by: Vedang Patel vedang.patel@intel.com Signed-off-by: Jithu Joseph jithu.joseph@intel.com Reviewed-by: Maciej Fijalkowski maciej.fijalkowski@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/igc/igc.h | 2 +- drivers/net/ethernet/intel/igc/igc_ptp.c | 72 +++++++++++++----------- 2 files changed, 41 insertions(+), 33 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 35baae900c1f..6dca67d9c25d 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -545,7 +545,7 @@ void igc_ptp_init(struct igc_adapter *adapter); void igc_ptp_reset(struct igc_adapter *adapter); void igc_ptp_suspend(struct igc_adapter *adapter); void igc_ptp_stop(struct igc_adapter *adapter); -void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, void *va, +void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, __le32 *va, struct sk_buff *skb); int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index ac0b9c85da7c..545f4d0e67cf 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -152,46 +152,54 @@ static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, }

/** - * igc_ptp_rx_pktstamp - retrieve Rx per packet timestamp + * igc_ptp_rx_pktstamp - Retrieve timestamp from Rx packet buffer * @q_vector: Pointer to interrupt specific structure * @va: Pointer to address containing Rx buffer * @skb: Buffer containing timestamp and packet * - * This function is meant to retrieve the first timestamp from the - * first buffer of an incoming frame. The value is stored in little - * endian format starting on byte 0. There's a second timestamp - * starting on byte 8. - **/ -void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, void *va, + * This function retrieves the timestamp saved in the beginning of packet + * buffer. While two timestamps are available, one in timer0 reference and the + * other in timer1 reference, this function considers only the timestamp in + * timer0 reference. + */ +void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, __le32 *va, struct sk_buff *skb) { struct igc_adapter *adapter = q_vector->adapter; - __le64 *regval = (__le64 *)va; - int adjust = 0; - - /* The timestamp is recorded in little endian format. - * DWORD: | 0 | 1 | 2 | 3 - * Field: | Timer0 Low | Timer0 High | Timer1 Low | Timer1 High + u64 regval; + int adjust; + + /* Timestamps are saved in little endian at the beginning of the packet + * buffer following the layout: + * + * DWORD: | 0 | 1 | 2 | 3 | + * Field: | Timer1 SYSTIML | Timer1 SYSTIMH | Timer0 SYSTIML | Timer0 SYSTIMH | + * + * SYSTIML holds the nanoseconds part while SYSTIMH holds the seconds + * part of the timestamp. */ - igc_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), - le64_to_cpu(regval[0])); - - /* adjust timestamp for the RX latency based on link speed */ - if (adapter->hw.mac.type == igc_i225) { - switch (adapter->link_speed) { - case SPEED_10: - adjust = IGC_I225_RX_LATENCY_10; - break; - case SPEED_100: - adjust = IGC_I225_RX_LATENCY_100; - break; - case SPEED_1000: - adjust = IGC_I225_RX_LATENCY_1000; - break; - case SPEED_2500: - adjust = IGC_I225_RX_LATENCY_2500; - break; - } + regval = le32_to_cpu(va[2]); + regval |= (u64)le32_to_cpu(va[3]) << 32; + igc_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval); + + /* Adjust timestamp for the RX latency based on link speed */ + switch (adapter->link_speed) { + case SPEED_10: + adjust = IGC_I225_RX_LATENCY_10; + break; + case SPEED_100: + adjust = IGC_I225_RX_LATENCY_100; + break; + case SPEED_1000: + adjust = IGC_I225_RX_LATENCY_1000; + break; + case SPEED_2500: + adjust = IGC_I225_RX_LATENCY_2500; + break; + default: + adjust = 0; + netdev_warn_once(adapter->netdev, "Imprecise timestamp\n"); + break; } skb_hwtstamps(skb)->hwtstamp = ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust);

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 88faf05e23ba..0b1e890dd583 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: Lv Yunlong lyl2019@mail.ustc.edu.cn

[ Upstream commit db74623a3850db99cb9692fda9e836a56b74198d ]

In qlcnic_83xx_get_minidump_template, fw_dump->tmpl_hdr was freed by vfree(). But unfortunately, it is used when extended is true.

Fixes: 7061b2bdd620e ("qlogic: Deletion of unnecessary checks before two function calls") Signed-off-by: Lv Yunlong lyl2019@mail.ustc.edu.cn Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c index 7760a3394e93..7ecb3dfe30bd 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c @@ -1425,6 +1425,7 @@ void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *adapter)

if (fw_dump->tmpl_hdr == NULL || current_version > prev_version) { vfree(fw_dump->tmpl_hdr); + fw_dump->tmpl_hdr = NULL;

if (qlcnic_83xx_md_check_extended_dump_capability(adapter)) extended = !qlcnic_83xx_extend_md_capab(adapter); @@ -1443,6 +1444,8 @@ void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *adapter) struct qlcnic_83xx_dump_template_hdr *hdr;

hdr = fw_dump->tmpl_hdr; + if (!hdr) + return; hdr->drv_cap_mask = 0x1f; fw_dump->cap_mask = 0x1f; dev_info(&pdev->dev,

From: Magnus Karlsson magnus.karlsson@intel.com

[ Upstream commit ed0907e3bdcfc7fe1c1756a480451e757b207a69 ]

Fix the wrong napi work done reporting in the xsk path of the ice driver. The code in the main Rx processing loop was written to assume that the buffer allocation code returns true if all allocations where successful and false if not. In contrast with all other Intel NIC xsk drivers, the ice_alloc_rx_bufs_zc() has the inverted logic messing up the work done reporting in the napi loop.

This can be fixed either by inverting the return value from ice_alloc_rx_bufs_zc() in the function that uses this in an incorrect way, or by changing the return value of ice_alloc_rx_bufs_zc(). We chose the latter as it makes all the xsk allocation functions for Intel NICs behave in the same way. My guess is that it was this unexpected discrepancy that gave rise to this bug in the first place.

Fixes: 5bb0c4b5eb61 ("ice, xsk: Move Rx allocation out of while-loop") Reported-by: Maciej Fijalkowski maciej.fijalkowski@intel.com Signed-off-by: Magnus Karlsson magnus.karlsson@intel.com Tested-by: Kiran Bhandare kiranx.bhandare@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ice/ice_base.c | 6 ++++-- drivers/net/ethernet/intel/ice/ice_xsk.c | 10 +++++----- 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 3124a3bf519a..952e41a1e001 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -418,6 +418,8 @@ int ice_setup_rx_ctx(struct ice_ring *ring) writel(0, ring->tail);

if (ring->xsk_pool) { + bool ok; + if (!xsk_buff_can_alloc(ring->xsk_pool, num_bufs)) { dev_warn(dev, "XSK buffer pool does not provide enough addresses to fill %d buffers on Rx ring %d\n", num_bufs, ring->q_index); @@ -426,8 +428,8 @@ int ice_setup_rx_ctx(struct ice_ring *ring) return 0; }

- err = ice_alloc_rx_bufs_zc(ring, num_bufs); - if (err) + ok = ice_alloc_rx_bufs_zc(ring, num_bufs); + if (!ok) dev_info(dev, "Failed to allocate some buffers on XSK buffer pool enabled Rx ring %d (pf_q %d)\n", ring->q_index, pf_q); return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 1782146db644..69ee1a8e87ab 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -408,18 +408,18 @@ xsk_pool_if_up: * This function allocates a number of Rx buffers from the fill ring * or the internal recycle mechanism and places them on the Rx ring. * - * Returns false if all allocations were successful, true if any fail. + * Returns true if all allocations were successful, false if any fail. */ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) { union ice_32b_rx_flex_desc *rx_desc; u16 ntu = rx_ring->next_to_use; struct ice_rx_buf *rx_buf; - bool ret = false; + bool ok = true; dma_addr_t dma;

if (!count) - return false; + return true;

rx_desc = ICE_RX_DESC(rx_ring, ntu); rx_buf = &rx_ring->rx_buf[ntu]; @@ -427,7 +427,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) do { rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_pool); if (!rx_buf->xdp) { - ret = true; + ok = false; break; }

@@ -452,7 +452,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) ice_release_rx_desc(rx_ring, ntu); }

- return ret; + return ok; }

/**

From: Douglas Anderson dianders@chromium.org

[ Upstream commit 148ddaa89d4a0a927c4353398096cc33687755c1 ]

While picking commit a8cd989e1a57 ("mmc: sdhci-msm: Warn about overclocking SD/MMC") back to my tree I was surprised that it was reporting warnings. I thought I fixed those! Looking closer at the fix, I see that I totally bungled it (or at least I halfway bungled it). The SD card clock got fixed (and that was the one I was really focused on fixing), but I totally adjusted the wrong clock for eMMC. Sigh. Let's fix my dumb mistake.

Now both SD and eMMC have floor for the "apps" clock.

This doesn't matter a lot for the final clock rate for HS400 eMMC but could matter if someone happens to put some slower eMMC on a sc7180. We also transition through some of these lower rates sometimes and having them wrong could cause problems during these transitions. These were the messages I was seeing at boot: mmc1: Card appears overclocked; req 52000000 Hz, actual 100000000 Hz mmc1: Card appears overclocked; req 52000000 Hz, actual 100000000 Hz mmc1: Card appears overclocked; req 104000000 Hz, actual 192000000 Hz

Fixes: 6d37a8d19283 ("clk: qcom: gcc-sc7180: Use floor ops for sdcc clks") Signed-off-by: Douglas Anderson dianders@chromium.org Link: https://lore.kernel.org/r/20210224095013.1.I2e2ba4978cfca06520dfb5d757768f9c... Reviewed-by: Taniya Das tdas@codeaurora.org Signed-off-by: Stephen Boyd sboyd@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clk/qcom/gcc-sc7180.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/qcom/gcc-sc7180.c b/drivers/clk/qcom/gcc-sc7180.c index 88e896abb663..da8b627ca156 100644 --- a/drivers/clk/qcom/gcc-sc7180.c +++ b/drivers/clk/qcom/gcc-sc7180.c @@ -620,7 +620,7 @@ static struct clk_rcg2 gcc_sdcc1_apps_clk_src = { .name = "gcc_sdcc1_apps_clk_src", .parent_data = gcc_parent_data_1, .num_parents = 5, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_floor_ops, }, };

@@ -642,7 +642,7 @@ static struct clk_rcg2 gcc_sdcc1_ice_core_clk_src = { .name = "gcc_sdcc1_ice_core_clk_src", .parent_data = gcc_parent_data_0, .num_parents = 4, - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_ops, }, };

From: Eric Dumazet edumazet@google.com

[ Upstream commit 50535249f624d0072cd885bcdce4e4b6fb770160 ]

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: Sasha Levin sashal@kernel.org --- net/qrtr/qrtr.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index edb6ac17ceca..dfc820ee553a 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -1058,6 +1058,11 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, rc = copied;

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

From: Hangbin Liu liuhangbin@gmail.com

[ Upstream commit 31254dc9566221429d2cfb45fd5737985d70f2b6 ]

When fixing the bpf test_tunnel.sh geneve failure. I only fixed the IPv4 part but forgot the IPv6 issue. Similar with the IPv4 fixes 557c223b643a ("selftests/bpf: No need to drop the packet when there is no geneve opt"), when there is no tunnel option and bpf_skb_get_tunnel_opt() returns error, there is no need to drop the packets and break all geneve rx traffic. Just set opt_class to 0 and keep returning TC_ACT_OK at the end.

Fixes: 557c223b643a ("selftests/bpf: No need to drop the packet when there is no geneve opt") Fixes: 933a741e3b82 ("selftests/bpf: bpf tunnel test.") Signed-off-by: Hangbin Liu liuhangbin@gmail.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Acked-by: William Tu u9012063@gmail.com Link: https://lore.kernel.org/bpf/20210309032214.2112438-1-liuhangbin@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/bpf/progs/test_tunnel_kern.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index 9afe947cfae9..ba6eadfec565 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -508,10 +508,8 @@ int _ip6geneve_get_tunnel(struct __sk_buff *skb) }

ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt)); - if (ret < 0) { - ERROR(ret); - return TC_ACT_SHOT; - } + if (ret < 0) + gopt.opt_class = 0;

bpf_trace_printk(fmt, sizeof(fmt), key.tunnel_id, key.remote_ipv4, gopt.opt_class);

From: Xie He xie.he.0141@gmail.com

[ Upstream commit bf0ffea336b493c0a8c8bc27b46683ecf1e8f294 ]

"x25_close" is called by "hdlc_close" in "hdlc.c", which is called by hardware drivers' "ndo_stop" function. "x25_xmit" is called by "hdlc_start_xmit" in "hdlc.c", which is hardware drivers' "ndo_start_xmit" function. "x25_rx" is called by "hdlc_rcv" in "hdlc.c", which receives HDLC frames from "net/core/dev.c".

"x25_close" races with "x25_xmit" and "x25_rx" because their callers race.

However, we need to ensure that the LAPB APIs called in "x25_xmit" and "x25_rx" are called before "lapb_unregister" is called in "x25_close".

This patch adds locking to ensure when "x25_xmit" and "x25_rx" are doing their work, "lapb_unregister" is not yet called in "x25_close".

Reasons for not solving the racing between "x25_close" and "x25_xmit" by calling "netif_tx_disable" in "x25_close": 1. We still need to solve the racing between "x25_close" and "x25_rx"; 2. The design of the HDLC subsystem assumes the HDLC hardware drivers have full control over the TX queue, and the HDLC protocol drivers (like this driver) have no control. Controlling the queue here in the protocol driver may interfere with hardware drivers' control of the queue.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Xie He xie.he.0141@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wan/hdlc_x25.c | 42 +++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c index 4aaa6388b9ee..5a6a945f6c81 100644 --- a/drivers/net/wan/hdlc_x25.c +++ b/drivers/net/wan/hdlc_x25.c @@ -23,6 +23,8 @@

struct x25_state { x25_hdlc_proto settings; + bool up; + spinlock_t up_lock; /* Protects "up" */ };

static int x25_ioctl(struct net_device *dev, struct ifreq *ifr); @@ -104,6 +106,8 @@ static void x25_data_transmit(struct net_device *dev, struct sk_buff *skb)

static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) { + hdlc_device *hdlc = dev_to_hdlc(dev); + struct x25_state *x25st = state(hdlc); int result;

/* There should be a pseudo header of 1 byte added by upper layers. @@ -114,11 +118,19 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; }

+ spin_lock_bh(&x25st->up_lock); + if (!x25st->up) { + spin_unlock_bh(&x25st->up_lock); + kfree_skb(skb); + return NETDEV_TX_OK; + } + switch (skb->data[0]) { case X25_IFACE_DATA: /* Data to be transmitted */ skb_pull(skb, 1); if ((result = lapb_data_request(dev, skb)) != LAPB_OK) dev_kfree_skb(skb); + spin_unlock_bh(&x25st->up_lock); return NETDEV_TX_OK;

case X25_IFACE_CONNECT: @@ -147,6 +159,7 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) break; }

+ spin_unlock_bh(&x25st->up_lock); dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -164,6 +177,7 @@ static int x25_open(struct net_device *dev) .data_transmit = x25_data_transmit, }; hdlc_device *hdlc = dev_to_hdlc(dev); + struct x25_state *x25st = state(hdlc); struct lapb_parms_struct params; int result;

@@ -190,6 +204,10 @@ static int x25_open(struct net_device *dev) if (result != LAPB_OK) return -EINVAL;

+ spin_lock_bh(&x25st->up_lock); + x25st->up = true; + spin_unlock_bh(&x25st->up_lock); + return 0; }

@@ -197,6 +215,13 @@ static int x25_open(struct net_device *dev)

static void x25_close(struct net_device *dev) { + hdlc_device *hdlc = dev_to_hdlc(dev); + struct x25_state *x25st = state(hdlc); + + spin_lock_bh(&x25st->up_lock); + x25st->up = false; + spin_unlock_bh(&x25st->up_lock); + lapb_unregister(dev); }

@@ -205,15 +230,28 @@ static void x25_close(struct net_device *dev) static int x25_rx(struct sk_buff *skb) { struct net_device *dev = skb->dev; + hdlc_device *hdlc = dev_to_hdlc(dev); + struct x25_state *x25st = state(hdlc);

if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) { dev->stats.rx_dropped++; return NET_RX_DROP; }

- if (lapb_data_received(dev, skb) == LAPB_OK) + spin_lock_bh(&x25st->up_lock); + if (!x25st->up) { + spin_unlock_bh(&x25st->up_lock); + kfree_skb(skb); + dev->stats.rx_dropped++; + return NET_RX_DROP; + } + + if (lapb_data_received(dev, skb) == LAPB_OK) { + spin_unlock_bh(&x25st->up_lock); return NET_RX_SUCCESS; + }

+ spin_unlock_bh(&x25st->up_lock); dev->stats.rx_errors++; dev_kfree_skb_any(skb); return NET_RX_DROP; @@ -298,6 +336,8 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr) return result;

memcpy(&state(hdlc)->settings, &new_settings, size); + state(hdlc)->up = false; + spin_lock_init(&state(hdlc)->up_lock);

/* There's no header_ops so hard_header_len should be 0. */ dev->hard_header_len = 0;

From: Eric Dumazet edumazet@google.com

[ Upstream commit 0217ed2848e8538bcf9172d97ed2eeb4a26041bb ]

Before calling tipc_aead_key_size(ptr), we need to ensure we have enough data to dereference ptr->keylen.

We probably also want to make sure tipc_aead_key_size() wont overflow with malicious ptr->keylen values.

Syzbot reported:

BUG: KMSAN: uninit-value in __tipc_nl_node_set_key net/tipc/node.c:2971 [inline] BUG: KMSAN: uninit-value in tipc_nl_node_set_key+0x9bf/0x13b0 net/tipc/node.c:3023 CPU: 0 PID: 21060 Comm: syz-executor.5 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 __msan_warning+0x5f/0xa0 mm/kmsan/kmsan_instr.c:197 __tipc_nl_node_set_key net/tipc/node.c:2971 [inline] tipc_nl_node_set_key+0x9bf/0x13b0 net/tipc/node.c:3023 genl_family_rcv_msg_doit net/netlink/genetlink.c:739 [inline] genl_family_rcv_msg net/netlink/genetlink.c:783 [inline] genl_rcv_msg+0x1319/0x1610 net/netlink/genetlink.c:800 netlink_rcv_skb+0x6fa/0x810 net/netlink/af_netlink.c:2494 genl_rcv+0x63/0x80 net/netlink/genetlink.c:811 netlink_unicast_kernel net/netlink/af_netlink.c:1304 [inline] netlink_unicast+0x11d6/0x14a0 net/netlink/af_netlink.c:1330 netlink_sendmsg+0x1740/0x1840 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg net/socket.c:672 [inline] ____sys_sendmsg+0xcfc/0x12f0 net/socket.c:2345 ___sys_sendmsg net/socket.c:2399 [inline] __sys_sendmsg+0x714/0x830 net/socket.c:2432 __compat_sys_sendmsg net/compat.c:347 [inline] __do_compat_sys_sendmsg net/compat.c:354 [inline] __se_compat_sys_sendmsg+0xa7/0xc0 net/compat.c:351 __ia32_compat_sys_sendmsg+0x4a/0x70 net/compat.c:351 do_syscall_32_irqs_on arch/x86/entry/common.c:79 [inline] __do_fast_syscall_32+0x102/0x160 arch/x86/entry/common.c:141 do_fast_syscall_32+0x6a/0xc0 arch/x86/entry/common.c:166 do_SYSENTER_32+0x73/0x90 arch/x86/entry/common.c:209 entry_SYSENTER_compat_after_hwframe+0x4d/0x5c RIP: 0023:0xf7f60549 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d b4 26 00 00 00 00 8d b4 26 00 00 00 00 RSP: 002b:00000000f555a5fc EFLAGS: 00000296 ORIG_RAX: 0000000000000172 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000020000200 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:121 [inline] kmsan_internal_poison_shadow+0x5c/0xf0 mm/kmsan/kmsan.c:104 kmsan_slab_alloc+0x8d/0xe0 mm/kmsan/kmsan_hooks.c:76 slab_alloc_node mm/slub.c:2907 [inline] __kmalloc_node_track_caller+0xa37/0x1430 mm/slub.c:4527 __kmalloc_reserve net/core/skbuff.c:142 [inline] __alloc_skb+0x2f8/0xb30 net/core/skbuff.c:210 alloc_skb include/linux/skbuff.h:1099 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1176 [inline] netlink_sendmsg+0xdbc/0x1840 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg net/socket.c:672 [inline] ____sys_sendmsg+0xcfc/0x12f0 net/socket.c:2345 ___sys_sendmsg net/socket.c:2399 [inline] __sys_sendmsg+0x714/0x830 net/socket.c:2432 __compat_sys_sendmsg net/compat.c:347 [inline] __do_compat_sys_sendmsg net/compat.c:354 [inline] __se_compat_sys_sendmsg+0xa7/0xc0 net/compat.c:351 __ia32_compat_sys_sendmsg+0x4a/0x70 net/compat.c:351 do_syscall_32_irqs_on arch/x86/entry/common.c:79 [inline] __do_fast_syscall_32+0x102/0x160 arch/x86/entry/common.c:141 do_fast_syscall_32+0x6a/0xc0 arch/x86/entry/common.c:166 do_SYSENTER_32+0x73/0x90 arch/x86/entry/common.c:209 entry_SYSENTER_compat_after_hwframe+0x4d/0x5c

Fixes: e1f32190cf7d ("tipc: add support for AEAD key setting via netlink") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Tuong Lien tuong.t.lien@dektech.com.au Cc: Jon Maloy jmaloy@redhat.com Cc: Ying Xue ying.xue@windriver.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/tipc/node.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/tipc/node.c b/net/tipc/node.c index 008670d1f43e..136338b85504 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2895,17 +2895,22 @@ int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb,

#ifdef CONFIG_TIPC_CRYPTO static int tipc_nl_retrieve_key(struct nlattr **attrs, - struct tipc_aead_key **key) + struct tipc_aead_key **pkey) { struct nlattr *attr = attrs[TIPC_NLA_NODE_KEY]; + struct tipc_aead_key *key;

if (!attr) return -ENODATA;

- *key = (struct tipc_aead_key *)nla_data(attr); - if (nla_len(attr) < tipc_aead_key_size(*key)) + if (nla_len(attr) < sizeof(*key)) + return -EINVAL; + key = (struct tipc_aead_key *)nla_data(attr); + if (key->keylen > TIPC_AEAD_KEYLEN_MAX || + nla_len(attr) < tipc_aead_key_size(key)) return -EINVAL;

+ *pkey = key; return 0; }

From: Davide Caratti dcaratti@redhat.com

[ Upstream commit 13832ae2755395b2585500c85b64f5109a44227e ]

Currently, Linux computes the HMAC contained in ADD_ADDR sub-option using the Address Id and the IP Address, and hardcodes a destination port equal to zero. This is not ok for ADD_ADDR with port: ensure to account for the endpoint port when computing the HMAC, in compliance with RFC8684 §3.4.1.

Fixes: 22fb85ffaefb ("mptcp: add port support for ADD_ADDR suboption writing") Reviewed-by: Mat Martineau mathew.j.martineau@linux.intel.com Acked-by: Geliang Tang geliangtang@gmail.com Signed-off-by: Davide Caratti dcaratti@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/mptcp/options.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 2e26e39169b8..37ef0bf098f6 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -555,15 +555,15 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, }

static u64 add_addr_generate_hmac(u64 key1, u64 key2, u8 addr_id, - struct in_addr *addr) + struct in_addr *addr, u16 port) { u8 hmac[SHA256_DIGEST_SIZE]; u8 msg[7];

msg[0] = addr_id; memcpy(&msg[1], &addr->s_addr, 4); - msg[5] = 0; - msg[6] = 0; + msg[5] = port >> 8; + msg[6] = port & 0xFF;

mptcp_crypto_hmac_sha(key1, key2, msg, 7, hmac);

@@ -572,15 +572,15 @@ static u64 add_addr_generate_hmac(u64 key1, u64 key2, u8 addr_id,

#if IS_ENABLED(CONFIG_MPTCP_IPV6) static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id, - struct in6_addr *addr) + struct in6_addr *addr, u16 port) { u8 hmac[SHA256_DIGEST_SIZE]; u8 msg[19];

msg[0] = addr_id; memcpy(&msg[1], &addr->s6_addr, 16); - msg[17] = 0; - msg[18] = 0; + msg[17] = port >> 8; + msg[18] = port & 0xFF;

mptcp_crypto_hmac_sha(key1, key2, msg, 19, hmac);

@@ -634,7 +634,8 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * opts->ahmac = add_addr_generate_hmac(msk->local_key, msk->remote_key, opts->addr_id, - &opts->addr); + &opts->addr, + opts->port); } } #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -645,7 +646,8 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * opts->ahmac = add_addr6_generate_hmac(msk->local_key, msk->remote_key, opts->addr_id, - &opts->addr6); + &opts->addr6, + opts->port); } } #endif @@ -922,12 +924,14 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk, if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) hmac = add_addr_generate_hmac(msk->remote_key, msk->local_key, - mp_opt->addr_id, &mp_opt->addr); + mp_opt->addr_id, &mp_opt->addr, + mp_opt->port); #if IS_ENABLED(CONFIG_MPTCP_IPV6) else hmac = add_addr6_generate_hmac(msk->remote_key, msk->local_key, - mp_opt->addr_id, &mp_opt->addr6); + mp_opt->addr_id, &mp_opt->addr6, + mp_opt->port); #endif

pr_debug("msk=%p, ahmac=%llu, mp_opt->ahmac=%llu\n",

From: Marc Kleine-Budde mkl@pengutronix.de

[ Upstream commit d4eb538e1f48b3cf7bb6cb9eb39fe3e9e8a701f7 ]

The previous patch ensures that the TX flags (struct can_isotp_ll_options::tx_flags) are 0 for classic CAN frames or a user configured value for CAN-FD frames.

This patch sets the CAN frames flags unconditionally to the ISO-TP TX flags, so that they are initialized to a proper value. Otherwise when running "candump -x" on a classical CAN ISO-TP stream shows wrongly set "B" and "E" flags.

| $ candump any,0:0,#FFFFFFFF -extA | [...] | can0 TX B E 713 [8] 2B 0A 0B 0C 0D 0E 0F 00 | can0 TX B E 713 [8] 2C 01 02 03 04 05 06 07 | can0 TX B E 713 [8] 2D 08 09 0A 0B 0C 0D 0E | can0 TX B E 713 [8] 2E 0F 00 01 02 03 04 05

Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol") Link: https://lore.kernel.org/r/20210218215434.1708249-2-mkl@pengutronix.de Cc: Oliver Hartkopp socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- net/can/isotp.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/can/isotp.c b/net/can/isotp.c index e32d446c121e..430976485d95 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -215,8 +215,7 @@ static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus) if (ae) ncf->data[0] = so->opt.ext_address;

- if (so->ll.mtu == CANFD_MTU) - ncf->flags = so->ll.tx_flags; + ncf->flags = so->ll.tx_flags;

can_send_ret = can_send(nskb, 1); if (can_send_ret) @@ -790,8 +789,7 @@ isotp_tx_burst: so->tx.sn %= 16; so->tx.bs++;

- if (so->ll.mtu == CANFD_MTU) - cf->flags = so->ll.tx_flags; + cf->flags = so->ll.tx_flags;

skb->dev = dev; can_skb_set_owner(skb, sk); @@ -939,8 +937,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) }

/* send the first or only CAN frame */ - if (so->ll.mtu == CANFD_MTU) - cf->flags = so->ll.tx_flags; + cf->flags = so->ll.tx_flags;

skb->dev = dev; skb->sk = sk;

From: Angelo Dureghello angelo@kernel-space.org

[ Upstream commit 47c5e474bc1e1061fb037d13b5000b38967eb070 ]

For cases when flexcan is built-in, bitrate is still not set at registering. So flexcan_chip_freeze() generates:

[ 1.860000] *** ZERO DIVIDE *** FORMAT=4 [ 1.860000] Current process id is 1 [ 1.860000] BAD KERNEL TRAP: 00000000 [ 1.860000] PC: [<402e70c8>] flexcan_chip_freeze+0x1a/0xa8

To allow chip freeze, using an hardcoded timeout when bitrate is still not set.

Fixes: ec15e27cc890 ("can: flexcan: enable RX FIFO after FRZ/HALT valid") Link: https://lore.kernel.org/r/20210315231510.650593-1-angelo@kernel-space.org Signed-off-by: Angelo Dureghello angelo@kernel-space.org [mkl: use if instead of ? operator] Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/can/flexcan.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 2893297555eb..a9502fbc6dd6 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -697,9 +697,15 @@ static int flexcan_chip_disable(struct flexcan_priv *priv) static int flexcan_chip_freeze(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; - unsigned int timeout = 1000 * 1000 * 10 / priv->can.bittiming.bitrate; + unsigned int timeout; + u32 bitrate = priv->can.bittiming.bitrate; u32 reg;

+ if (bitrate) + timeout = 1000 * 1000 * 10 / bitrate; + else + timeout = FLEXCAN_TIMEOUT_US / 10; + reg = priv->read(&regs->mcr); reg |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT; priv->write(reg, &regs->mcr);

From: Tong Zhang ztong0001@gmail.com

[ Upstream commit 0429d6d89f97ebff4f17f13f5b5069c66bde8138 ]

There is a UAF in c_can_pci_remove(). dev is released by free_c_can_dev() and is used by pci_iounmap(pdev, priv->base) later. To fix this issue, save the mmio address before releasing dev.

Fixes: 5b92da0443c2 ("c_can_pci: generic module for C_CAN/D_CAN on PCI") Link: https://lore.kernel.org/r/20210301024512.539039-1-ztong0001@gmail.com Signed-off-by: Tong Zhang ztong0001@gmail.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/can/c_can/c_can_pci.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/c_can/c_can_pci.c b/drivers/net/can/c_can/c_can_pci.c index 406b4847e5dc..7efb60b50876 100644 --- a/drivers/net/can/c_can/c_can_pci.c +++ b/drivers/net/can/c_can/c_can_pci.c @@ -239,12 +239,13 @@ static void c_can_pci_remove(struct pci_dev *pdev) { struct net_device *dev = pci_get_drvdata(pdev); struct c_can_priv *priv = netdev_priv(dev); + void __iomem *addr = priv->base;

unregister_c_can_dev(dev);

free_c_can_dev(dev);

- pci_iounmap(pdev, priv->base); + pci_iounmap(pdev, addr); pci_disable_msi(pdev); pci_clear_master(pdev); pci_release_regions(pdev);

From: Torin Cooper-Bennun torin@maxiluxsystems.com

[ Upstream commit c0e399f3baf42279f48991554240af8c457535d1 ]

Message loss from RX FIFO 0 is already handled in m_can_handle_lost_msg(), with netdev output included.

Removing this warning also improves driver performance under heavy load, where m_can_do_rx_poll() may be called many times before this interrupt is cleared, causing this message to be output many times (thanks Mariusz Madej for this report).

Fixes: e0d1f4816f2a ("can: m_can: add Bosch M_CAN controller support") Link: https://lore.kernel.org/r/20210303103151.3760532-1-torin@maxiluxsystems.com Reported-by: Mariusz Madej mariusz.madej@xtrack.com 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 | 3 --- 1 file changed, 3 deletions(-)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index da551fd0f502..678679a8c907 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -501,9 +501,6 @@ static int m_can_do_rx_poll(struct net_device *dev, int quota) }

while ((rxfs & RXFS_FFL_MASK) && (quota > 0)) { - if (rxfs & RXFS_RFL) - netdev_warn(dev, "Rx FIFO 0 Message Lost\n"); - m_can_read_fifo(dev, rxfs);

quota--;

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 1944015fe9c1d9fa5e9eb7ffbbb5ef8954d6753b ]

Coverity reported the strange "if (~...)" condition that's always true. It suggested that ! was intended instead of ~, but upon further analysis I'm convinced that what really was intended was a comparison to 0xff/0xffff (in HT/VHT cases respectively), since this indicates that all of the rates are enabled.

Change the comparison accordingly.

I'm guessing this never really mattered because a reset to not having a rate mask is basically equivalent to having a mask that enables all rates.

Reported-by: Colin Ian King colin.king@canonical.com Fixes: 2ffbe6d33366 ("mac80211: fix and optimize MCS mask handling") Fixes: b119ad6e726c ("mac80211: add rate mask logic for vht rates") Reviewed-by: Colin Ian King colin.king@canonical.com Link: https://lore.kernel.org/r/20210212112213.36b38078f569.I8546a20c80bc1669058eb... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/cfg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index c4c70e30ad7f..68a0de02b561 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2950,14 +2950,14 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, continue;

for (j = 0; j < IEEE80211_HT_MCS_MASK_LEN; j++) { - if (~sdata->rc_rateidx_mcs_mask[i][j]) { + if (sdata->rc_rateidx_mcs_mask[i][j] != 0xff) { sdata->rc_has_mcs_mask[i] = true; break; } }

for (j = 0; j < NL80211_VHT_NSS_MAX; j++) { - if (~sdata->rc_rateidx_vht_mcs_mask[i][j]) { + if (sdata->rc_rateidx_vht_mcs_mask[i][j] != 0xffff) { sdata->rc_has_vht_mcs_mask[i] = true; break; }

From: Carlos Llamas cmllamas@google.com

[ Upstream commit 81f711d67a973bf8a6db9556faf299b4074d536e ]

Fix multiple warnings seen with gcc 10.2.1: reuseaddr_ports_exhausted.c:32:41: warning: missing braces around initializer [-Wmissing-braces] 32 | struct reuse_opts unreusable_opts[12] = { | ^ 33 | {0, 0, 0, 0}, | { } { }

Fixes: 7f204a7de8b0 ("selftests: net: Add SO_REUSEADDR test to check if 4-tuples are fully utilized.") Signed-off-by: Carlos Llamas cmllamas@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../selftests/net/reuseaddr_ports_exhausted.c | 32 +++++++++---------- 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c index 7b01b7c2ec10..066efd30e294 100644 --- a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c +++ b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c @@ -30,25 +30,25 @@ struct reuse_opts { };

struct reuse_opts unreusable_opts[12] = { - {0, 0, 0, 0}, - {0, 0, 0, 1}, - {0, 0, 1, 0}, - {0, 0, 1, 1}, - {0, 1, 0, 0}, - {0, 1, 0, 1}, - {0, 1, 1, 0}, - {0, 1, 1, 1}, - {1, 0, 0, 0}, - {1, 0, 0, 1}, - {1, 0, 1, 0}, - {1, 0, 1, 1}, + {{0, 0}, {0, 0}}, + {{0, 0}, {0, 1}}, + {{0, 0}, {1, 0}}, + {{0, 0}, {1, 1}}, + {{0, 1}, {0, 0}}, + {{0, 1}, {0, 1}}, + {{0, 1}, {1, 0}}, + {{0, 1}, {1, 1}}, + {{1, 0}, {0, 0}}, + {{1, 0}, {0, 1}}, + {{1, 0}, {1, 0}}, + {{1, 0}, {1, 1}}, };

struct reuse_opts reusable_opts[4] = { - {1, 1, 0, 0}, - {1, 1, 0, 1}, - {1, 1, 1, 0}, - {1, 1, 1, 1}, + {{1, 1}, {0, 0}}, + {{1, 1}, {0, 1}}, + {{1, 1}, {1, 0}}, + {{1, 1}, {1, 1}}, };

int bind_port(struct __test_metadata *_metadata, int reuseaddr, int reuseport)

From: Louis Peens louis.peens@corigine.com

[ Upstream commit 5c4f5e19d6a8e159127b9d653bb67e0dc7a28047 ]

Differentiate between ipv4 and ipv6 flows when configuring the pre_tunnel table to prevent them trampling each other in the table.

Fixes: 783461604f7e ("nfp: flower: update flow merge code to support IPv6 tunnels") 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/tunnel_conf.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 7248d248f604..d19c02e99114 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -16,8 +16,9 @@ #define NFP_FL_MAX_ROUTES 32

#define NFP_TUN_PRE_TUN_RULE_LIMIT 32 -#define NFP_TUN_PRE_TUN_RULE_DEL 0x1 -#define NFP_TUN_PRE_TUN_IDX_BIT 0x8 +#define NFP_TUN_PRE_TUN_RULE_DEL BIT(0) +#define NFP_TUN_PRE_TUN_IDX_BIT BIT(3) +#define NFP_TUN_PRE_TUN_IPV6_BIT BIT(7)

/** * struct nfp_tun_pre_run_rule - rule matched before decap @@ -1268,6 +1269,7 @@ int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app, { struct nfp_flower_priv *app_priv = app->priv; struct nfp_tun_offloaded_mac *mac_entry; + struct nfp_flower_meta_tci *key_meta; struct nfp_tun_pre_tun_rule payload; struct net_device *internal_dev; int err; @@ -1290,6 +1292,15 @@ int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app, if (!mac_entry) return -ENOENT;

+ /* Set/clear IPV6 bit. cpu_to_be16() swap will lead to MSB being + * set/clear for port_idx. + */ + key_meta = (struct nfp_flower_meta_tci *)flow->unmasked_data; + if (key_meta->nfp_flow_key_layer & NFP_FLOWER_LAYER_IPV6) + mac_entry->index |= NFP_TUN_PRE_TUN_IPV6_BIT; + else + mac_entry->index &= ~NFP_TUN_PRE_TUN_IPV6_BIT; + payload.port_idx = cpu_to_be16(mac_entry->index);

/* Copy mac id and vlan to flow - dev may not exist at delete time. */

From: Alexei Starovoitov ast@kernel.org

[ Upstream commit 8a141dd7f7060d1e64c14a5257e0babae20ac99b ]

The following sequence of commands: register_ftrace_direct(ip, addr1); modify_ftrace_direct(ip, addr1, addr2); unregister_ftrace_direct(ip, addr2); will cause the kernel to warn: [ 30.179191] WARNING: CPU: 2 PID: 1961 at kernel/trace/ftrace.c:5223 unregister_ftrace_direct+0x130/0x150 [ 30.180556] CPU: 2 PID: 1961 Comm: test_progs W O 5.12.0-rc2-00378-g86bc10a0a711-dirty #3246 [ 30.182453] RIP: 0010:unregister_ftrace_direct+0x130/0x150

When modify_ftrace_direct() changes the addr from old to new it should update the addr stored in ftrace_direct_funcs. Otherwise the final unregister_ftrace_direct() won't find the address and will cause the splat.

Fixes: 0567d6809182 ("ftrace: Add modify_ftrace_direct()") Signed-off-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: Steven Rostedt (VMware) rostedt@goodmis.org Link: https://lore.kernel.org/bpf/20210316195815.34714-1-alexei.starovoitov@gmail.... Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/trace/ftrace.c | 43 ++++++++++++++++++++++++++++++++++++++----- 1 file changed, 38 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4d8e35575549..b7e29db127fa 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5045,6 +5045,20 @@ struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr) return NULL; }