From: Vinicius Costa Gomes vinicius.gomes@intel.com

[ Upstream commit 56ea7ed103b46970e171eb1c95916f393d64eeff ]

Cleans the next descriptor to watch (next_to_watch) when cleaning the TX ring.

Failure to do so can cause invalid memory accesses. If igc_poll() runs while the controller is being reset this can lead to the driver try to free a skb that was already freed.

Log message:

[ 101.525242] refcount_t: underflow; use-after-free. [ 101.525251] WARNING: CPU: 1 PID: 646 at lib/refcount.c:28 refcount_warn_saturate+0xab/0xf0 [ 101.525259] Modules linked in: sch_etf(E) sch_mqprio(E) rfkill(E) intel_rapl_msr(E) intel_rapl_common(E) x86_pkg_temp_thermal(E) intel_powerclamp(E) coretemp(E) binfmt_misc(E) kvm_intel(E) kvm(E) irqbypass(E) crc32_pclmul(E) ghash_clmulni_intel(E) aesni_intel(E) mei_wdt(E) libaes(E) crypto_simd(E) cryptd(E) glue_helper(E) snd_hda_codec_hdmi(E) rapl(E) intel_cstate(E) snd_hda_intel(E) snd_intel_dspcfg(E) sg(E) soundwire_intel(E) intel_uncore(E) at24(E) soundwire_generic_allocation(E) iTCO_wdt(E) soundwire_cadence(E) intel_pmc_bxt(E) serio_raw(E) snd_hda_codec(E) iTCO_vendor_support(E) watchdog(E) snd_hda_core(E) snd_hwdep(E) snd_soc_core(E) snd_compress(E) snd_pcsp(E) soundwire_bus(E) snd_pcm(E) evdev(E) snd_timer(E) mei_me(E) snd(E) soundcore(E) mei(E) configfs(E) ip_tables(E) x_tables(E) autofs4(E) ext4(E) crc32c_generic(E) crc16(E) mbcache(E) jbd2(E) sd_mod(E) t10_pi(E) crc_t10dif(E) crct10dif_generic(E) i915(E) ahci(E) libahci(E) ehci_pci(E) igb(E) xhci_pci(E) ehci_hcd(E) [ 101.525303] drm_kms_helper(E) dca(E) xhci_hcd(E) libata(E) crct10dif_pclmul(E) cec(E) crct10dif_common(E) tsn(E) igc(E) e1000e(E) ptp(E) i2c_i801(E) crc32c_intel(E) psmouse(E) i2c_algo_bit(E) i2c_smbus(E) scsi_mod(E) lpc_ich(E) pps_core(E) usbcore(E) drm(E) button(E) video(E) [ 101.525318] CPU: 1 PID: 646 Comm: irq/37-enp7s0-T Tainted: G E 5.10.30-rt37-tsn1-rt-ipipe #ipipe [ 101.525320] Hardware name: SIEMENS AG SIMATIC IPC427D/A5E31233588, BIOS V17.02.09 03/31/2017 [ 101.525322] RIP: 0010:refcount_warn_saturate+0xab/0xf0 [ 101.525325] Code: 05 31 48 44 01 01 e8 f0 c6 42 00 0f 0b c3 80 3d 1f 48 44 01 00 75 90 48 c7 c7 78 a8 f3 a6 c6 05 0f 48 44 01 01 e8 d1 c6 42 00 <0f> 0b c3 80 3d fe 47 44 01 00 0f 85 6d ff ff ff 48 c7 c7 d0 a8 f3 [ 101.525327] RSP: 0018:ffffbdedc0917cb8 EFLAGS: 00010286 [ 101.525329] RAX: 0000000000000000 RBX: ffff98fd6becbf40 RCX: 0000000000000001 [ 101.525330] RDX: 0000000000000001 RSI: ffffffffa6f2700c RDI: 00000000ffffffff [ 101.525332] RBP: ffff98fd6becc14c R08: ffffffffa7463d00 R09: ffffbdedc0917c50 [ 101.525333] R10: ffffffffa74c3578 R11: 0000000000000034 R12: 00000000ffffff00 [ 101.525335] R13: ffff98fd6b0b1000 R14: 0000000000000039 R15: ffff98fd6be35c40 [ 101.525337] FS: 0000000000000000(0000) GS:ffff98fd6e240000(0000) knlGS:0000000000000000 [ 101.525339] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 101.525341] CR2: 00007f34135a3a70 CR3: 0000000150210003 CR4: 00000000001706e0 [ 101.525343] Call Trace: [ 101.525346] sock_wfree+0x9c/0xa0 [ 101.525353] unix_destruct_scm+0x7b/0xa0 [ 101.525358] skb_release_head_state+0x40/0x90 [ 101.525362] skb_release_all+0xe/0x30 [ 101.525364] napi_consume_skb+0x57/0x160 [ 101.525367] igc_poll+0xb7/0xc80 [igc] [ 101.525376] ? sched_clock+0x5/0x10 [ 101.525381] ? sched_clock_cpu+0xe/0x100 [ 101.525385] net_rx_action+0x14c/0x410 [ 101.525388] __do_softirq+0xe9/0x2f4 [ 101.525391] __local_bh_enable_ip+0xe3/0x110 [ 101.525395] ? irq_finalize_oneshot.part.47+0xe0/0xe0 [ 101.525398] irq_forced_thread_fn+0x6a/0x80 [ 101.525401] irq_thread+0xe8/0x180 [ 101.525403] ? wake_threads_waitq+0x30/0x30 [ 101.525406] ? irq_thread_check_affinity+0xd0/0xd0 [ 101.525408] kthread+0x183/0x1a0 [ 101.525412] ? kthread_park+0x80/0x80 [ 101.525415] ret_from_fork+0x22/0x30

Fixes: 13b5b7fd6a4a ("igc: Add support for Tx/Rx rings") Reported-by: Erez Geva erez.geva.ext@siemens.com Signed-off-by: Vinicius Costa Gomes vinicius.gomes@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_main.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index f1adf154ec4a..9cac1e74a2ba 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -217,6 +217,8 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring) DMA_TO_DEVICE); }

+ tx_buffer->next_to_watch = NULL; + /* move us one more past the eop_desc for start of next pkt */ tx_buffer++; i++;

From: Tom Rix trix@redhat.com

[ Upstream commit 05682a0a61b6cbecd97a0f37f743b2cbfd516977 ]

Static analysis reports this problem

igc_main.c:4944:20: warning: The left operand of '&' is a garbage value if (!(phy_data & SR_1000T_REMOTE_RX_STATUS) && ~~~~~~~~ ^

phy_data is set by the call to igc_read_phy_reg() only if there is a read_reg() op, else it is unset and a 0 is returned. Change the return to -EOPNOTSUPP.

Fixes: 208983f099d9 ("igc: Add watchdog") Signed-off-by: Tom Rix trix@redhat.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 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 25871351730b..58e842cbf6ef 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -560,7 +560,7 @@ static inline s32 igc_read_phy_reg(struct igc_hw *hw, u32 offset, u16 *data) if (hw->phy.ops.read_reg) return hw->phy.ops.read_reg(hw, offset, data);

- return 0; + return -EOPNOTSUPP; }

void igc_reinit_locked(struct igc_adapter *);

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit c6bc9e5ce5d37cb3e6b552f41b92a193db1806ab ]

If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function.

Fixes: c9a11c23ceb6 ("igc: Add netdev") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Tested-by: Dvora Fuxbrumer dvorax.fuxbrumer@linux.intel.com Acked-by: Sasha Neftin sasha.neftin@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/igc/igc_main.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 9cac1e74a2ba..a8d5f196fdbd 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -5596,6 +5596,7 @@ err_sw_init: err_ioremap: free_netdev(netdev); err_alloc_etherdev: + pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma:

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit e85e14d68f517ef12a5fb8123fff65526b35b6cd ]

If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function.

Fixes: 19ae1b3fb99c ("fm10k: Add support for PCI power management and error handling") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 9e3103fae723..caedf24c24c1 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -2227,6 +2227,7 @@ err_sw_init: err_ioremap: free_netdev(netdev); err_alloc_netdev: + pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma:

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit af30cbd2f4d6d66a9b6094e0aa32420bc8b20e08 ]

If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function.

Fixes: 5eae00c57f5e ("i40evf: main driver core") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/iavf/iavf_main.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index e612c24fa384..44bafedd09f2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3798,6 +3798,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err_ioremap: free_netdev(netdev); err_alloc_etherdev: + pci_disable_pcie_error_reporting(pdev); pci_release_regions(pdev); err_pci_reg: err_dma:

From: Jedrzej Jagielski jedrzej.jagielski@intel.com

[ Upstream commit 382a7c20d9253bcd5715789b8179528d0f3de72c ]

Assignment to *ring should be done after correctness check of the argument queue.

Fixes: 91db364236c8 ("igb: Refactor igb_configure_cbs()") Signed-off-by: Jedrzej Jagielski jedrzej.jagielski@intel.com Acked-by: Vinicius Costa Gomes vinicius.gomes@intel.com Tested-by: Tony Brelinski tonyx.brelinski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/igb/igb_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 9f83ff55394c..b0e900d1eae2 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1685,14 +1685,15 @@ static bool is_any_txtime_enabled(struct igb_adapter *adapter) **/ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue) { - struct igb_ring *ring = adapter->tx_ring[queue]; struct net_device *netdev = adapter->netdev; struct e1000_hw *hw = &adapter->hw; + struct igb_ring *ring; u32 tqavcc, tqavctrl; u16 value;

WARN_ON(hw->mac.type != e1000_i210); WARN_ON(queue < 0 || queue > 1); + ring = adapter->tx_ring[queue];

/* If any of the Qav features is enabled, configure queues as SR and * with HIGH PRIO. If none is, then configure them with LOW PRIO and

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit 2342ae10d1272d411a468a85a67647dd115b344f ]

If the 'register_netdev() call fails, we must release the resources allocated by the previous 'gve_init_priv()' call, as already done in the remove function.

Add a new label and the missing 'gve_teardown_priv_resources()' in the error handling path.

Fixes: 893ce44df565 ("gve: Add basic driver framework for Compute Engine Virtual NIC") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Reviewed-by: Catherine Sullivan csully@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/google/gve/gve_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 79cefe85a799..b43c6ff07614 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1349,13 +1349,16 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent)

err = register_netdev(dev); if (err) - goto abort_with_wq; + goto abort_with_gve_init;

dev_info(&pdev->dev, "GVE version %s\n", gve_version_str); gve_clear_probe_in_progress(priv); queue_work(priv->gve_wq, &priv->service_task); return 0;

+abort_with_gve_init: + gve_teardown_priv_resources(priv); + abort_with_wq: destroy_workqueue(priv->gve_wq);

From: Taehee Yoo ap420073@gmail.com

[ Upstream commit b648eba4c69e5819880b4907e7fcb2bb576069ab ]

To dereference bond->curr_active_slave, it uses rcu_dereference(). But it and the caller doesn't acquire RCU so a warning occurs. So add rcu_read_lock().

Test commands: ip link add dummy0 type dummy ip link add bond0 type bond ip link set dummy0 master bond0 ip link set dummy0 up ip link set bond0 up ip x s add proto esp dst 14.1.1.1 src 15.1.1.1 spi 0x07 \ mode transport \ reqid 0x07 replay-window 32 aead 'rfc4106(gcm(aes))' \ 0x44434241343332312423222114131211f4f3f2f1 128 sel \ src 14.0.0.52/24 dst 14.0.0.70/24 proto tcp offload \ dev bond0 dir in

Splat looks like: ============================= WARNING: suspicious RCU usage 5.13.0-rc3+ #1168 Not tainted ----------------------------- drivers/net/bonding/bond_main.c:411 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1 1 lock held by ip/684: #0: ffffffff9a2757c0 (&net->xfrm.xfrm_cfg_mutex){+.+.}-{3:3}, at: xfrm_netlink_rcv+0x59/0x80 [xfrm_user] 55.191733][ T684] stack backtrace: CPU: 0 PID: 684 Comm: ip Not tainted 5.13.0-rc3+ #1168 Call Trace: dump_stack+0xa4/0xe5 bond_ipsec_add_sa+0x18c/0x1f0 [bonding] xfrm_dev_state_add+0x2a9/0x770 ? memcpy+0x38/0x60 xfrm_add_sa+0x2278/0x3b10 [xfrm_user] ? xfrm_get_policy+0xaa0/0xaa0 [xfrm_user] ? register_lock_class+0x1750/0x1750 xfrm_user_rcv_msg+0x331/0x660 [xfrm_user] ? rcu_read_lock_sched_held+0x91/0xc0 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? find_held_lock+0x3a/0x1c0 ? mutex_lock_io_nested+0x1210/0x1210 ? sched_clock_cpu+0x18/0x170 netlink_rcv_skb+0x121/0x350 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? netlink_ack+0x9d0/0x9d0 ? netlink_deliver_tap+0x17c/0xa50 xfrm_netlink_rcv+0x68/0x80 [xfrm_user] netlink_unicast+0x41c/0x610 ? netlink_attachskb+0x710/0x710 netlink_sendmsg+0x6b9/0xb70 [ ... ]

Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo ap420073@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_main.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c5a646d06102..026f4511bf7b 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -403,10 +403,12 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) struct net_device *bond_dev = xs->xso.dev; struct bonding *bond; struct slave *slave; + int err;

if (!bond_dev) return -EINVAL;

+ rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); xs->xso.real_dev = slave->dev; @@ -415,10 +417,13 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) if (!(slave->dev->xfrmdev_ops && slave->dev->xfrmdev_ops->xdo_dev_state_add)) { slave_warn(bond_dev, slave->dev, "Slave does not support ipsec offload\n"); + rcu_read_unlock(); return -EINVAL; }

- return slave->dev->xfrmdev_ops->xdo_dev_state_add(xs); + err = slave->dev->xfrmdev_ops->xdo_dev_state_add(xs); + rcu_read_unlock(); + return err; }

/**

From: Taehee Yoo ap420073@gmail.com

[ Upstream commit 2de7e4f67599affc97132bd07e30e3bd59d0b777 ]

There are two pointers in struct xfrm_state_offload, *dev, *real_dev. These are used in callback functions of struct xfrmdev_ops. The *dev points whether bonding interface or real interface. If bonding ipsec offload is used, it points bonding interface If not, it points real interface. And real_dev always points real interface. So, ixgbevf should always use real_dev instead of dev. Of course, real_dev always not be null.

Test commands: ip link add bond0 type bond #eth0 is ixgbevf interface ip link set eth0 master bond0 ip link set bond0 up ip x s add proto esp dst 14.1.1.1 src 15.1.1.1 spi 0x07 mode \ transport reqid 0x07 replay-window 32 aead 'rfc4106(gcm(aes))' \ 0x44434241343332312423222114131211f4f3f2f1 128 sel src 14.0.0.52/24 \ dst 14.0.0.70/24 proto tcp offload dev bond0 dir in

Splat looks like: KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 6 PID: 688 Comm: ip Not tainted 5.13.0-rc3+ #1168 RIP: 0010:ixgbevf_ipsec_find_empty_idx+0x28/0x1b0 [ixgbevf] Code: 00 00 0f 1f 44 00 00 55 53 48 89 fb 48 83 ec 08 40 84 f6 0f 84 9c 00 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 01 0f 8e 4c 01 00 00 66 81 3b 00 04 0f RSP: 0018:ffff8880089af390 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000001 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: ffff8880089af4f8 R08: 0000000000000003 R09: fffffbfff4287e11 R10: 0000000000000001 R11: ffff888005de8908 R12: 0000000000000000 R13: ffff88810936a000 R14: ffff88810936a000 R15: ffff888004d78040 FS: 00007fdf9883a680(0000) GS:ffff88811a400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055bc14adbf40 CR3: 000000000b87c005 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ixgbevf_ipsec_add_sa+0x1bf/0x9c0 [ixgbevf] ? rcu_read_lock_sched_held+0x91/0xc0 ? ixgbevf_ipsec_parse_proto_keys.isra.9+0x280/0x280 [ixgbevf] ? lock_acquire+0x191/0x720 ? bond_ipsec_add_sa+0x48/0x350 [bonding] ? lockdep_hardirqs_on_prepare+0x3e0/0x3e0 ? rcu_read_lock_held+0x91/0xa0 ? rcu_read_lock_sched_held+0xc0/0xc0 bond_ipsec_add_sa+0x193/0x350 [bonding] xfrm_dev_state_add+0x2a9/0x770 ? memcpy+0x38/0x60 xfrm_add_sa+0x2278/0x3b10 [xfrm_user] ? xfrm_get_policy+0xaa0/0xaa0 [xfrm_user] ? register_lock_class+0x1750/0x1750 xfrm_user_rcv_msg+0x331/0x660 [xfrm_user] ? rcu_read_lock_sched_held+0x91/0xc0 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? find_held_lock+0x3a/0x1c0 ? mutex_lock_io_nested+0x1210/0x1210 ? sched_clock_cpu+0x18/0x170 netlink_rcv_skb+0x121/0x350 [ ... ]

Fixes: 272c2330adc9 ("xfrm: bail early on slave pass over skb") Signed-off-by: Taehee Yoo ap420073@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ixgbevf/ipsec.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c index caaea2c920a6..e3e4676af9e4 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c +++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c @@ -211,7 +211,7 @@ struct xfrm_state *ixgbevf_ipsec_find_rx_state(struct ixgbevf_ipsec *ipsec, static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs, u32 *mykey, u32 *mysalt) { - struct net_device *dev = xs->xso.dev; + struct net_device *dev = xs->xso.real_dev; unsigned char *key_data; char *alg_name = NULL; int key_len; @@ -260,12 +260,15 @@ static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs, **/ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs) { - struct net_device *dev = xs->xso.dev; - struct ixgbevf_adapter *adapter = netdev_priv(dev); - struct ixgbevf_ipsec *ipsec = adapter->ipsec; + struct net_device *dev = xs->xso.real_dev; + struct ixgbevf_adapter *adapter; + struct ixgbevf_ipsec *ipsec; u16 sa_idx; int ret;

+ adapter = netdev_priv(dev); + ipsec = adapter->ipsec; + if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) { netdev_err(dev, "Unsupported protocol 0x%04x for IPsec offload\n", xs->id.proto); @@ -383,11 +386,14 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs) **/ static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs) { - struct net_device *dev = xs->xso.dev; - struct ixgbevf_adapter *adapter = netdev_priv(dev); - struct ixgbevf_ipsec *ipsec = adapter->ipsec; + struct net_device *dev = xs->xso.real_dev; + struct ixgbevf_adapter *adapter; + struct ixgbevf_ipsec *ipsec; u16 sa_idx;

+ adapter = netdev_priv(dev); + ipsec = adapter->ipsec; + if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) { sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_RX_INDEX;

From: Taehee Yoo ap420073@gmail.com

[ Upstream commit b121693381b112b78c076dea171ee113e237c0e4 ]

bonding interface can be nested and it supports ipsec offload. So, it allows setting the nested bonding + ipsec scenario. But code does not support this scenario. So, it should be disallowed.

interface graph: bond2 | bond1 | eth0

The nested bonding + ipsec offload may not a real usecase. So, disallowing this scenario is fine.

Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo ap420073@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_main.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index a7b6550063b2..d85a19c06c69 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -419,8 +419,9 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) xs->xso.real_dev = slave->dev; bond->xs = xs;

- if (!(slave->dev->xfrmdev_ops - && slave->dev->xfrmdev_ops->xdo_dev_state_add)) { + if (!slave->dev->xfrmdev_ops || + !slave->dev->xfrmdev_ops->xdo_dev_state_add || + netif_is_bond_master(slave->dev)) { slave_warn(bond_dev, slave->dev, "Slave does not support ipsec offload\n"); rcu_read_unlock(); return -EINVAL; @@ -453,8 +454,9 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)

xs->xso.real_dev = slave->dev;

- if (!(slave->dev->xfrmdev_ops - && slave->dev->xfrmdev_ops->xdo_dev_state_delete)) { + if (!slave->dev->xfrmdev_ops || + !slave->dev->xfrmdev_ops->xdo_dev_state_delete || + netif_is_bond_master(slave->dev)) { slave_warn(bond_dev, slave->dev, "%s: no slave xdo_dev_state_delete\n", __func__); goto out; } @@ -479,8 +481,9 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) return true;

- if (!(slave_dev->xfrmdev_ops - && slave_dev->xfrmdev_ops->xdo_dev_offload_ok)) { + if (!slave_dev->xfrmdev_ops || + !slave_dev->xfrmdev_ops->xdo_dev_offload_ok || + netif_is_bond_master(slave_dev)) { slave_warn(bond_dev, slave_dev, "%s: no slave xdo_dev_offload_ok\n", __func__); return false; }

From: Taehee Yoo ap420073@gmail.com

[ Upstream commit 955b785ec6b3b2f9b91914d6eeac8ee66ee29239 ]

To dereference bond->curr_active_slave, it uses rcu_dereference(). But it and the caller doesn't acquire RCU so a warning occurs. So add rcu_read_lock().

Splat looks like: WARNING: suspicious RCU usage 5.13.0-rc6+ #1179 Not tainted drivers/net/bonding/bond_main.c:571 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1 1 lock held by ping/974: #0: ffff888109e7db70 (sk_lock-AF_INET){+.+.}-{0:0}, at: raw_sendmsg+0x1303/0x2cb0

stack backtrace: CPU: 2 PID: 974 Comm: ping Not tainted 5.13.0-rc6+ #1179 Call Trace: dump_stack+0xa4/0xe5 bond_ipsec_offload_ok+0x1f4/0x260 [bonding] xfrm_output+0x179/0x890 xfrm4_output+0xfa/0x410 ? __xfrm4_output+0x4b0/0x4b0 ? __ip_make_skb+0xecc/0x2030 ? xfrm4_udp_encap_rcv+0x800/0x800 ? ip_local_out+0x21/0x3a0 ip_send_skb+0x37/0xa0 raw_sendmsg+0x1bfd/0x2cb0

Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo ap420073@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_main.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 3f67b4b794ac..d267791a06c0 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -573,24 +573,34 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) struct net_device *real_dev; struct slave *curr_active; struct bonding *bond; + int err;

bond = netdev_priv(bond_dev); + rcu_read_lock(); curr_active = rcu_dereference(bond->curr_active_slave); real_dev = curr_active->dev;

- if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) - return true; + if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { + err = true; + goto out; + }

- if (!xs->xso.real_dev) - return false; + if (!xs->xso.real_dev) { + err = false; + goto out; + }

if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_offload_ok || netif_is_bond_master(real_dev)) { - return false; + err = false; + goto out; }

- return real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); + err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); +out: + rcu_read_unlock(); + return err; }

static const struct xfrmdev_ops bond_xfrmdev_ops = {

From: Nicolas Dichtel nicolas.dichtel@6wind.com

[ Upstream commit ccd27f05ae7b8ebc40af5b004e94517a919aa862 ]

The goal of commit df789fe75206 ("ipv6: Provide ipv6 version of "disable_policy" sysctl") was to have the disable_policy from ipv4 available on ipv6. However, it's not exactly the same mechanism. On IPv4, all packets coming from an interface, which has disable_policy set, bypass the policy check. For ipv6, this is done only for local packets, ie for packets destinated to an address configured on the incoming interface.

Let's align ipv6 with ipv4 so that the 'disable_policy' sysctl has the same effect for both protocols.

My first approach was to create a new kind of route cache entries, to be able to set DST_NOPOLICY without modifying routes. This would have added a lot of code. Because the local delivery path is already handled, I choose to focus on the forwarding path to minimize code churn.

Fixes: df789fe75206 ("ipv6: Provide ipv6 version of "disable_policy" sysctl") Signed-off-by: Nicolas Dichtel nicolas.dichtel@6wind.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/ip6_output.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 497974b4372a..b7ffb4f227a4 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -479,7 +479,9 @@ int ip6_forward(struct sk_buff *skb) if (skb_warn_if_lro(skb)) goto drop;

- if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { + if (!net->ipv6.devconf_all->disable_policy && + !idev->cnf.disable_policy && + !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; }

From: Hangbin Liu liuhangbin@gmail.com

[ Upstream commit 24b671aad4eae423e1abf5b7f08d9a5235458b8d ]

If the kernel doesn't enable option CONFIG_IPV6_SUBTREES, the RTA_SRC info will not be exported to userspace in rt6_fill_node(). And ip cmd will not print "from ::" to the route output. So remove this check.

Fixes: ec8105352869 ("selftests: Add redirect tests") Signed-off-by: Hangbin Liu liuhangbin@gmail.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 --- tools/testing/selftests/net/icmp_redirect.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh index bf361f30d6ef..bfcabee50155 100755 --- a/tools/testing/selftests/net/icmp_redirect.sh +++ b/tools/testing/selftests/net/icmp_redirect.sh @@ -311,7 +311,7 @@ check_exception()

if [ "$with_redirect" = "yes" ]; then ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \ - grep -q "${H2_N2_IP6} from :: via ${R2_LLADDR} dev br0.*${mtu}" + grep -q "${H2_N2_IP6} .*via ${R2_LLADDR} dev br0.*${mtu}" elif [ -n "${mtu}" ]; then ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \ grep -q "${mtu}"

From: Uwe Kleine-König u.kleine-koenig@pengutronix.de

[ Upstream commit 65e2e6c1c20104ed19060a38f4edbf14e9f9a9a5 ]

As the last call to sprd_pwm_apply() might have exited early if state->enabled was false, the values for period and duty_cycle stored in pwm->state might not have been written to hardware and it must be ensured that they are configured before enabling the PWM.

Fixes: 8aae4b02e8a6 ("pwm: sprd: Add Spreadtrum PWM support") Signed-off-by: Uwe Kleine-König u.kleine-koenig@pengutronix.de Signed-off-by: Thierry Reding thierry.reding@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pwm/pwm-sprd.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/pwm/pwm-sprd.c b/drivers/pwm/pwm-sprd.c index 98c479dfae31..3041f0b3bbb6 100644 --- a/drivers/pwm/pwm-sprd.c +++ b/drivers/pwm/pwm-sprd.c @@ -183,13 +183,10 @@ static int sprd_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, } }

- if (state->period != cstate->period || - state->duty_cycle != cstate->duty_cycle) { - ret = sprd_pwm_config(spc, pwm, state->duty_cycle, - state->period); - if (ret) - return ret; - } + ret = sprd_pwm_config(spc, pwm, state->duty_cycle, + state->period); + if (ret) + return ret;

sprd_pwm_write(spc, pwm->hwpwm, SPRD_PWM_ENABLE, 1); } else if (cstate->enabled) {

From: Zack Rusin zackr@vmware.com

[ Upstream commit 34bd46bcf3de72cbffcdc42d3fa67e543d1c869b ]

Change 2ef4fb92363c ("drm/vmwgfx: Make sure bo's are unpinned before putting them back") caused a conflict in one of the drm trees and the merge commit 68a32ba14177 ("Merge tag 'drm-next-2021-04-28' of git://anongit.freedesktop.org/drm/drm") accidently re-added code that the original change was removing. Fixed by removing the incorrect buffer unpin - it has already been unpinned two lines above.

Fixes: 68a32ba14177 ("Merge tag 'drm-next-2021-04-28' of git://anongit.freedesktop.org/drm/drm") Signed-off-by: Zack Rusin zackr@vmware.com Reviewed-by: Martin Krastev krastevm@vmware.com Link: https://patchwork.freedesktop.org/patch/msgid/20210615182336.995192-4-zackr@... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/vmwgfx/vmwgfx_mob.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c index 5648664f71bc..f2d625415458 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c @@ -354,7 +354,6 @@ static void vmw_otable_batch_takedown(struct vmw_private *dev_priv, ttm_bo_unpin(bo); ttm_bo_unreserve(bo);

- ttm_bo_unpin(batch->otable_bo); ttm_bo_put(batch->otable_bo); batch->otable_bo = NULL; }

From: Jianguo Wu wujianguo@chinatelecom.cn

[ Upstream commit 030d37bd1cd2443a1f21db47eb301899bfa45a2a ]

In subflow_check_req(), if subflow sport is mismatch, will put msk, destroy token, and destruct req, then return -EPERM, which can be done by subflow_req_destructor() via:

tcp_conn_request() |--__reqsk_free() |--subflow_req_destructor()

So we should remove these redundant code, otherwise will call tcp_v4_reqsk_destructor() twice, and may double free inet_rsk(req)->ireq_opt.

Fixes: 5bc56388c74f ("mptcp: add port number check for MP_JOIN") Signed-off-by: Jianguo Wu wujianguo@chinatelecom.cn Signed-off-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/mptcp/subflow.c | 5 ----- 1 file changed, 5 deletions(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index cbc452d0901e..5493c851ca6c 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -212,11 +212,6 @@ again: ntohs(inet_sk(sk_listener)->inet_sport), ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) { - sock_put((struct sock *)subflow_req->msk); - mptcp_token_destroy_request(req); - tcp_request_sock_ops.destructor(req); - subflow_req->msk = NULL; - subflow_req->mp_join = 0; SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX); return -EPERM; }

From: Geliang Tang geliangtang@gmail.com

[ Upstream commit c863225b79426459feca2ef5b0cc2f07e8e68771 ]

This patch added a new parameter name sk in mptcp_get_options().

Acked-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Geliang Tang geliangtang@gmail.com Signed-off-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/mptcp/options.c | 5 +++-- net/mptcp/protocol.h | 3 ++- net/mptcp/subflow.c | 10 +++++----- 3 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c index b87e46f515fb..72b1067d5aa2 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -323,7 +323,8 @@ static void mptcp_parse_option(const struct sk_buff *skb, } }

-void mptcp_get_options(const struct sk_buff *skb, +void mptcp_get_options(const struct sock *sk, + const struct sk_buff *skb, struct mptcp_options_received *mp_opt) { const struct tcphdr *th = tcp_hdr(skb); @@ -1010,7 +1011,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) return; }

- mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (!check_fully_established(msk, sk, subflow, skb, &mp_opt)) return;

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 7b634568f49c..f74258377c05 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -576,7 +576,8 @@ int __init mptcp_proto_v6_init(void); struct sock *mptcp_sk_clone(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct request_sock *req); -void mptcp_get_options(const struct sk_buff *skb, +void mptcp_get_options(const struct sock *sk, + const struct sk_buff *skb, struct mptcp_options_received *mp_opt);

void mptcp_finish_connect(struct sock *sk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 5221cfce5390..78e787ef8fff 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -150,7 +150,7 @@ static int subflow_check_req(struct request_sock *req, return -EINVAL; #endif

- mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk_listener, skb, &mp_opt);

if (mp_opt.mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); @@ -244,7 +244,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, int err;

subflow_init_req(req, sk_listener); - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk_listener, skb, &mp_opt);

if (mp_opt.mp_capable && mp_opt.mp_join) return -EINVAL; @@ -403,7 +403,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->ssn_offset = TCP_SKB_CB(skb)->seq; pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset);

- mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (subflow->request_mptcp) { if (!mp_opt.mp_capable) { MPTCP_INC_STATS(sock_net(sk), @@ -650,7 +650,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, * reordered MPC will cause fallback, but we don't have other * options. */ - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (!mp_opt.mp_capable) { fallback = true; goto create_child; @@ -660,7 +660,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, if (!new_msk) fallback = true; } else if (subflow_req->mp_join) { - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt) || !mptcp_can_accept_new_subflow(subflow_req->msk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);

From: Jianguo Wu wujianguo@chinatelecom.cn

[ Upstream commit a7da441621c7945fbfd43ed239c93b8073cda502 ]

After patch "mptcp: fix syncookie process if mptcp can not_accept new subflow", if subflow is limited, MP_JOIN SYN is dropped, and no SYN/ACK will be replied.

So in case "multiple subflows limited by server", the expected SYN/ACK number should be 1.

Fixes: 00587187ad30 ("selftests: mptcp: add test cases for mptcp join tests with syn cookies") Reported-by: kernel test robot oliver.sang@intel.com Signed-off-by: Jianguo Wu wujianguo@chinatelecom.cn Signed-off-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index fd99485cf2a4..e8ac852c6ff6 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1341,7 +1341,7 @@ syncookies_tests() ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflows limited by server w cookies" 2 2 1 + chk_join_nr "subflows limited by server w cookies" 2 1 1

# test signal address with cookies reset_with_cookies

From: Paolo Abeni pabeni@redhat.com

[ Upstream commit fde56eea01f96b664eb63033990be0fd2a945da5 ]

The current cleanup rbuf tries a bit too hard to avoid acquiring the subflow socket lock. We may end-up delaying the needed ack, or skip acking a blocked subflow.

Address the above extending the conditions used to trigger the cleanup to reflect more closely what TCP does and invoking tcp_cleanup_rbuf() on all the active subflows.

Note that we can't replicate the exact tests implemented in tcp_cleanup_rbuf(), as MPTCP lacks some of the required info - e.g. ping-pong mode.

Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/mptcp/protocol.c | 56 ++++++++++++++++++-------------------------- net/mptcp/protocol.h | 1 - 2 files changed, 23 insertions(+), 34 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 0f36fefcc77e..18f152bdb66f 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -433,49 +433,46 @@ static void mptcp_send_ack(struct mptcp_sock *msk) } }

-static bool mptcp_subflow_cleanup_rbuf(struct sock *ssk) +static void mptcp_subflow_cleanup_rbuf(struct sock *ssk) { bool slow; - int ret;

slow = lock_sock_fast(ssk); - ret = tcp_can_send_ack(ssk); - if (ret) + if (tcp_can_send_ack(ssk)) tcp_cleanup_rbuf(ssk, 1); unlock_sock_fast(ssk, slow); - return ret; +} + +static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) +{ + const struct inet_connection_sock *icsk = inet_csk(ssk); + bool ack_pending = READ_ONCE(icsk->icsk_ack.pending); + const struct tcp_sock *tp = tcp_sk(ssk); + + return (ack_pending & ICSK_ACK_SCHED) && + ((READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->rcv_wup) > + READ_ONCE(icsk->icsk_ack.rcv_mss)) || + (rx_empty && ack_pending & + (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED))); }

static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) { - struct sock *ack_hint = READ_ONCE(msk->ack_hint); int old_space = READ_ONCE(msk->old_wspace); struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; - bool cleanup; + int space = __mptcp_space(sk); + bool cleanup, rx_empty;

- /* this is a simple superset of what tcp_cleanup_rbuf() implements - * so that we don't have to acquire the ssk socket lock most of the time - * to do actually nothing - */ - cleanup = __mptcp_space(sk) - old_space >= max(0, old_space); - if (!cleanup) - return; + cleanup = (space > 0) && (space >= (old_space << 1)); + rx_empty = !atomic_read(&sk->sk_rmem_alloc);

- /* if the hinted ssk is still active, try to use it */ - if (likely(ack_hint)) { - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

- if (ack_hint == ssk && mptcp_subflow_cleanup_rbuf(ssk)) - return; - } + if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty)) + mptcp_subflow_cleanup_rbuf(ssk); } - - /* otherwise pick the first active subflow */ - mptcp_for_each_subflow(msk, subflow) - if (mptcp_subflow_cleanup_rbuf(mptcp_subflow_tcp_sock(subflow))) - return; }

static bool mptcp_check_data_fin(struct sock *sk) @@ -620,7 +617,6 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, break; } } while (more_data_avail); - WRITE_ONCE(msk->ack_hint, ssk);

*bytes += moved; return done; @@ -1955,7 +1951,6 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) __mptcp_update_rmem(sk); done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); mptcp_data_unlock(sk); - tcp_cleanup_rbuf(ssk, moved);

if (unlikely(ssk->sk_err)) __mptcp_error_report(sk); @@ -1971,7 +1966,6 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) ret |= __mptcp_ofo_queue(msk); __mptcp_splice_receive_queue(sk); mptcp_data_unlock(sk); - mptcp_cleanup_rbuf(msk); } if (ret) mptcp_check_data_fin((struct sock *)msk); @@ -2216,9 +2210,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (ssk == msk->last_snd) msk->last_snd = NULL;

- if (ssk == msk->ack_hint) - msk->ack_hint = NULL; - if (ssk == msk->first) msk->first = NULL;

@@ -2433,7 +2424,6 @@ static int __mptcp_init_sock(struct sock *sk) msk->tx_pending_data = 0; msk->size_goal_cache = TCP_BASE_MSS;

- msk->ack_hint = NULL; msk->first = NULL; inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index f74258377c05..f842c832f6b0 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -236,7 +236,6 @@ struct mptcp_sock { bool rcv_fastclose; bool use_64bit_ack; /* Set when we received a 64-bit DSN */ spinlock_t join_list_lock; - struct sock *ack_hint; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue;

From: Marek Behún kabel@kernel.org

[ Upstream commit a5de4be0aaaa66a2fa98e8a33bdbed3bd0682804 ]

It seems that we cannot differentiate 88X3310 from 88X3340 by simply looking at bit 3 of revision ID. This only works on revisions A0 and A1. On revision B0, this bit is always 1.

Instead use the 3.d00d register for differentiation, since this register contains information about number of ports on the device.

Fixes: 9885d016ffa9 ("net: phy: marvell10g: add separate structure for 88X3340") Signed-off-by: Marek Behún kabel@kernel.org Reported-by: Matteo Croce mcroce@linux.microsoft.com Tested-by: Matteo Croce mcroce@microsoft.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/phy/marvell10g.c | 40 +++++++++++++++++++++++++++++++----- include/linux/marvell_phy.h | 6 +----- 2 files changed, 36 insertions(+), 10 deletions(-)

diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index bbbc6ac8fa82..53a433442803 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -78,6 +78,11 @@ enum { /* Temperature read register (88E2110 only) */ MV_PCS_TEMP = 0x8042,

+ /* Number of ports on the device */ + MV_PCS_PORT_INFO = 0xd00d, + MV_PCS_PORT_INFO_NPORTS_MASK = 0x0380, + MV_PCS_PORT_INFO_NPORTS_SHIFT = 7, + /* These registers appear at 0x800X and 0xa00X - the 0xa00X control * registers appear to set themselves to the 0x800X when AN is * restarted, but status registers appear readable from either. @@ -966,6 +971,30 @@ static const struct mv3310_chip mv2111_type = { #endif };

+static int mv3310_get_number_of_ports(struct phy_device *phydev) +{ + int ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_PORT_INFO); + if (ret < 0) + return ret; + + ret &= MV_PCS_PORT_INFO_NPORTS_MASK; + ret >>= MV_PCS_PORT_INFO_NPORTS_SHIFT; + + return ret + 1; +} + +static int mv3310_match_phy_device(struct phy_device *phydev) +{ + return mv3310_get_number_of_ports(phydev) == 1; +} + +static int mv3340_match_phy_device(struct phy_device *phydev) +{ + return mv3310_get_number_of_ports(phydev) == 4; +} + static int mv211x_match_phy_device(struct phy_device *phydev, bool has_5g) { int val; @@ -994,7 +1023,8 @@ static int mv2111_match_phy_device(struct phy_device *phydev) static struct phy_driver mv3310_drivers[] = { { .phy_id = MARVELL_PHY_ID_88X3310, - .phy_id_mask = MARVELL_PHY_ID_88X33X0_MASK, + .phy_id_mask = MARVELL_PHY_ID_MASK, + .match_phy_device = mv3310_match_phy_device, .name = "mv88x3310", .driver_data = &mv3310_type, .get_features = mv3310_get_features, @@ -1011,8 +1041,9 @@ static struct phy_driver mv3310_drivers[] = { .set_loopback = genphy_c45_loopback, }, { - .phy_id = MARVELL_PHY_ID_88X3340, - .phy_id_mask = MARVELL_PHY_ID_88X33X0_MASK, + .phy_id = MARVELL_PHY_ID_88X3310, + .phy_id_mask = MARVELL_PHY_ID_MASK, + .match_phy_device = mv3340_match_phy_device, .name = "mv88x3340", .driver_data = &mv3340_type, .get_features = mv3310_get_features, @@ -1069,8 +1100,7 @@ static struct phy_driver mv3310_drivers[] = { module_phy_driver(mv3310_drivers);

static struct mdio_device_id __maybe_unused mv3310_tbl[] = { - { MARVELL_PHY_ID_88X3310, MARVELL_PHY_ID_88X33X0_MASK }, - { MARVELL_PHY_ID_88X3340, MARVELL_PHY_ID_88X33X0_MASK }, + { MARVELL_PHY_ID_88X3310, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E2110, MARVELL_PHY_ID_MASK }, { }, }; diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index acee44b9db26..0f06c2287b52 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -22,14 +22,10 @@ #define MARVELL_PHY_ID_88E1545 0x01410ea0 #define MARVELL_PHY_ID_88E1548P 0x01410ec0 #define MARVELL_PHY_ID_88E3016 0x01410e60 +#define MARVELL_PHY_ID_88X3310 0x002b09a0 #define MARVELL_PHY_ID_88E2110 0x002b09b0 #define MARVELL_PHY_ID_88X2222 0x01410f10

-/* PHY IDs and mask for Alaska 10G PHYs */ -#define MARVELL_PHY_ID_88X33X0_MASK 0xfffffff8 -#define MARVELL_PHY_ID_88X3310 0x002b09a0 -#define MARVELL_PHY_ID_88X3340 0x002b09a8 - /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */ #define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0

From: Vladimir Oltean vladimir.oltean@nxp.com

[ Upstream commit e56c6bbd98dc1cefb6f9c5d795fd29016e4f2fe7 ]

The point with a *dev and a *brport_dev is that when we have a LAG net device that is a bridge port, *dev is an ocelot net device and *brport_dev is the bonding/team net device. The ocelot net device beneath the LAG does not exist from the bridge's perspective, so we need to sync the switchdev objects belonging to the brport_dev and not to the dev.

Fixes: e4bd44e89dcf ("net: ocelot: replay switchdev events when joining bridge") 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/mscc/ocelot_net.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index aad33d22c33f..3dc577183a40 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -1287,6 +1287,7 @@ static int ocelot_netdevice_lag_leave(struct net_device *dev, }

static int ocelot_netdevice_changeupper(struct net_device *dev, + struct net_device *brport_dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack; @@ -1296,11 +1297,11 @@ static int ocelot_netdevice_changeupper(struct net_device *dev,

if (netif_is_bridge_master(info->upper_dev)) { if (info->linking) - err = ocelot_netdevice_bridge_join(dev, dev, + err = ocelot_netdevice_bridge_join(dev, brport_dev, info->upper_dev, extack); else - err = ocelot_netdevice_bridge_leave(dev, dev, + err = ocelot_netdevice_bridge_leave(dev, brport_dev, info->upper_dev); } if (netif_is_lag_master(info->upper_dev)) { @@ -1335,7 +1336,7 @@ ocelot_netdevice_lag_changeupper(struct net_device *dev, if (ocelot_port->bond != dev) return NOTIFY_OK;

- err = ocelot_netdevice_changeupper(lower, info); + err = ocelot_netdevice_changeupper(lower, dev, info); if (err) return notifier_from_errno(err); } @@ -1374,7 +1375,7 @@ static int ocelot_netdevice_event(struct notifier_block *unused, struct netdev_notifier_changeupper_info *info = ptr;

if (ocelot_netdevice_dev_check(dev)) - return ocelot_netdevice_changeupper(dev, info); + return ocelot_netdevice_changeupper(dev, dev, info);

if (netif_is_lag_master(dev)) return ocelot_netdevice_lag_changeupper(dev, info);

From: Like Xu like.xu.linux@gmail.com

[ Upstream commit 7234c362ccb3c2228f06f19f93b132de9cfa7ae4 ]

The AMD platform does not support the functions Ah CPUID leaf. The returned results for this entry should all remain zero just like the native does:

AMD host: 0x0000000a 0x00: eax=0x00000000 ebx=0x00000000 ecx=0x00000000 edx=0x00000000 (uncanny) AMD guest: 0x0000000a 0x00: eax=0x00000000 ebx=0x00000000 ecx=0x00000000 edx=0x00008000

Fixes: cadbaa039b99 ("perf/x86/intel: Make anythread filter support conditional") Signed-off-by: Like Xu likexu@tencent.com Message-Id: 20210628074354.33848-1-likexu@tencent.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/cpuid.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index ca7866d63e98..739be5da3bca 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -765,7 +765,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)

edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS); edx.split.bit_width_fixed = cap.bit_width_fixed; - edx.split.anythread_deprecated = 1; + if (cap.version) + edx.split.anythread_deprecated = 1; edx.split.reserved1 = 0; edx.split.reserved2 = 0;

From: Sean Christopherson seanjc@google.com

[ Upstream commit c7a1b2b678c54ac19320daf525038d0e2e43ca7c ]

Use IS_ERR() instead of checking for a NULL pointer when querying for sev_pin_memory() failures. sev_pin_memory() always returns an error code cast to a pointer, or a valid pointer; it never returns NULL.

Reported-by: Dan Carpenter dan.carpenter@oracle.com Cc: Steve Rutherford srutherford@google.com Cc: Brijesh Singh brijesh.singh@amd.com Cc: Ashish Kalra ashish.kalra@amd.com Fixes: d3d1af85e2c7 ("KVM: SVM: Add KVM_SEND_UPDATE_DATA command") Fixes: 15fb7de1a7f5 ("KVM: SVM: Add KVM_SEV_RECEIVE_UPDATE_DATA command") Signed-off-by: Sean Christopherson seanjc@google.com Message-Id: 20210506175826.2166383-3-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/svm/sev.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 3dc3e2897804..02d60d7f903d 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1271,8 +1271,8 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Pin guest memory */ guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK, PAGE_SIZE, &n, 0); - if (!guest_page) - return -EFAULT; + if (IS_ERR(guest_page)) + return PTR_ERR(guest_page);

/* allocate memory for header and transport buffer */ ret = -ENOMEM; @@ -1463,11 +1463,12 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) data.trans_len = params.trans_len;

/* Pin guest memory */ - ret = -EFAULT; guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK, PAGE_SIZE, &n, 0); - if (!guest_page) + if (IS_ERR(guest_page)) { + ret = PTR_ERR(guest_page); goto e_free_trans; + }

/* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */ data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;

From: Zev Weiss zev@bewilderbeest.net

[ Upstream commit 812bae32e5d50914f75a6e036d3bde39ca86b0c3 ]

This device-tree was merged with a provisional vuart IRQ-polarity property that was still under review and ended up taking a somewhat different form. This patch updates it to match the final form of the new vuart properties, which additionally allow specifying the SIRQ number and LPC address.

Signed-off-by: Zev Weiss zev@bewilderbeest.net Reviewed-by: Andrew Jeffery andrew@aj.id.au Fixes: ca03042f0f12 ("serial: 8250_aspeed_vuart: add aspeed, lpc-io-reg and aspeed, lpc-interrupts DT properties") Reviewed-by: Joel Stanley joel@jms.id.au Link: https://lore.kernel.org/r/20210416075113.18047-1-zev@bewilderbeest.net Signed-off-by: Joel Stanley joel@jms.id.au Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts b/arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts index dcab6e78dfa4..8be40c8283af 100644 --- a/arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts +++ b/arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts @@ -4,6 +4,7 @@ #include "aspeed-g5.dtsi" #include <dt-bindings/gpio/aspeed-gpio.h> #include <dt-bindings/i2c/i2c.h> +#include <dt-bindings/interrupt-controller/irq.h>

/{ model = "ASRock E3C246D4I BMC"; @@ -73,7 +74,8 @@

&vuart { status = "okay"; - aspeed,sirq-active-high; + aspeed,lpc-io-reg = <0x2f8>; + aspeed,lpc-interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; };

&mac0 {

From: Riccardo Mancini rickyman7@gmail.com

[ Upstream commit 0967ebffe098157180a0bbd180ac90348c6e07d7 ]

ASan reports a memory leak of nsinfo during the execution of:

# perf test "31: Lookup mmap thread"

The leak is caused by a refcounted variable being replaced without dropping the refcount.

This patch makes sure that the refcnt of nsinfo is decreased when a refcounted variable is replaced with a new value.

Signed-off-by: Riccardo Mancini rickyman7@gmail.com Fixes: 27c9c3424fc217da ("perf inject: Add --buildid-all option") Cc: Ian Rogers irogers@google.com Cc: Jiri Olsa jolsa@redhat.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: http://lore.kernel.org/lkml/55223bc8821b34ccb01f92ef1401c02b6a32e61f.1626343... [ Split from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/builtin-inject.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index ddccc0eb7390..614e428e4ac5 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -358,9 +358,10 @@ static struct dso *findnew_dso(int pid, int tid, const char *filename, dso = machine__findnew_dso_id(machine, filename, id); }

- if (dso) + if (dso) { + nsinfo__put(dso->nsinfo); dso->nsinfo = nsi; - else + } else nsinfo__put(nsi);

thread__put(thread);

From: Riccardo Mancini rickyman7@gmail.com

[ Upstream commit dedeb4be203b382ba7245d13079bc3b0f6d40c65 ]

ASan reports a memory leak of nsinfo during the execution of:

# perf test "31: Lookup mmap thread".

The leak is caused by a refcounted variable being replaced without dropping the refcount.

This patch makes sure that the refcnt of nsinfo is decreased whenever a refcounted variable is replaced with a new value.

Signed-off-by: Riccardo Mancini rickyman7@gmail.com Fixes: 544abd44c7064c8a ("perf probe: Allow placing uprobes in alternate namespaces.") Cc: Ian Rogers irogers@google.com Cc: Jiri Olsa jolsa@redhat.com Cc: Krister Johansen kjlx@templeofstupid.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: http://lore.kernel.org/lkml/55223bc8821b34ccb01f92ef1401c02b6a32e61f.1626343... [ Split from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/probe-event.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index a78c8d59a555..9cc89a047b15 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -180,8 +180,10 @@ struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user) struct map *map;

map = dso__new_map(target); - if (map && map->dso) + if (map && map->dso) { + nsinfo__put(map->dso->nsinfo); map->dso->nsinfo = nsinfo__get(nsi); + } return map; } else { return kernel_get_module_map(target);

From: Riccardo Mancini rickyman7@gmail.com

[ Upstream commit 233f2dc1c284337286f9a64c0152236779a42f6c ]

ASan reports a memory leak related to session->evlist while running:

# perf test "41: Session topology".

When perf_data is in write mode, session->evlist is owned by the caller, which should also take care of deleting it.

This patch adds the missing evlist__delete().

Signed-off-by: Riccardo Mancini rickyman7@gmail.com Fixes: c84974ed9fb67293 ("perf test: Add entry to test cpu topology") Cc: Ian Rogers irogers@google.com Cc: Jiri Olsa jolsa@redhat.com Cc: Kan Liang kan.liang@intel.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: http://lore.kernel.org/lkml/822f741f06eb25250fb60686cf30a35f447e9e91.1626343... Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/tests/topology.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index ec4e3b21b831..b5efe675b321 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -61,6 +61,7 @@ static int session_write_header(char *path) TEST_ASSERT_VAL("failed to write header", !perf_session__write_header(session, session->evlist, data.file.fd, true));

+ evlist__delete(session->evlist); perf_session__delete(session);

return 0;

From: Riccardo Mancini rickyman7@gmail.com

[ Upstream commit dccfca926c351ba0893af4c8b481477bdb2881a4 ]

ASan reports a memory leak while running:

# perf test "49: Synthesize attr update"

Caused by a string being duplicated but never freed.

This patch adds the missing free().

Note that evsel->unit is not deallocated together with evsel since it is supposed to be a constant string.

Signed-off-by: Riccardo Mancini rickyman7@gmail.com Fixes: a6e5281780d1da65 ("perf tools: Add event_update event unit type") Cc: Ian Rogers irogers@google.com Cc: Jiri Olsa jolsa@redhat.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: http://lore.kernel.org/lkml/1fbc8158663fb0d4d5392e36bae564f6ad60be3c.1626343... Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/tests/event_update.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index 932ab0740d11..44a50527f9d9 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -88,6 +88,7 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu struct evsel *evsel; struct event_name tmp; struct evlist *evlist = evlist__new_default(); + char *unit = strdup("KRAVA");

TEST_ASSERT_VAL("failed to get evlist", evlist);

@@ -98,7 +99,7 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu

perf_evlist__id_add(&evlist->core, &evsel->core, 0, 0, 123);

- evsel->unit = strdup("KRAVA"); + evsel->unit = unit;

TEST_ASSERT_VAL("failed to synthesize attr update unit", !perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit)); @@ -118,6 +119,7 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu TEST_ASSERT_VAL("failed to synthesize attr update cpus", !perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus));

+ free(unit); evlist__delete(evlist); return 0; }

From: Riccardo Mancini rickyman7@gmail.com

[ Upstream commit 244d1797c8c8e850b8de7992af713aa5c70d5650 ]

ASan reports a memory leak when running:

# perf test "65: maps__merge_in"

This is the second and final patch addressing these memory leaks.

This time, the problem is simply that the maps object is never destructed.

This patch adds the missing maps__exit call.

Signed-off-by: Riccardo Mancini rickyman7@gmail.com Fixes: 79b6bb73f888933c ("perf maps: Merge 'struct maps' with 'struct map_groups'") Cc: Ian Rogers irogers@google.com Cc: Jiri Olsa jolsa@redhat.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: http://lore.kernel.org/lkml/a1a29b97a58738987d150e94d4ebfad0282fb038.1626343... Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/tests/maps.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c index edcbc70ff9d6..1ac72919fa35 100644 --- a/tools/perf/tests/maps.c +++ b/tools/perf/tests/maps.c @@ -116,5 +116,7 @@ int test__maps__merge_in(struct test *t __maybe_unused, int subtest __maybe_unus

ret = check_maps(merged3, ARRAY_SIZE(merged3), &maps); TEST_ASSERT_VAL("merge check failed", !ret); + + maps__exit(&maps); return TEST_OK; }

From: Riccardo Mancini rickyman7@gmail.com

[ Upstream commit a37338aad8c4d8676173ead14e881d2ec308155c ]

ASan reports the memory leak of the strings allocated by sort_help() when running perf report.

This patch changes the returned pointer to char* (instead of const char*), saves it in a temporary variable, and finally deallocates it at function exit.

Signed-off-by: Riccardo Mancini rickyman7@gmail.com Fixes: 702fb9b415e7c99b ("perf report: Show all sort keys in help output") Cc: Andi Kleen ak@linux.intel.com Cc: Ian Rogers irogers@google.com Cc: Jiri Olsa jolsa@redhat.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: http://lore.kernel.org/lkml/a38b13f02812a8a6759200b9063c6191337f44d4.1626343... Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/builtin-report.c | 33 ++++++++++++++++++++++----------- tools/perf/util/sort.c | 2 +- tools/perf/util/sort.h | 2 +- 3 files changed, 24 insertions(+), 13 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 36f9ccfeb38a..ce420f910ff8 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1167,6 +1167,8 @@ int cmd_report(int argc, const char **argv) .annotation_opts = annotation__default_options, .skip_empty = true, }; + char *sort_order_help = sort_help("sort by key(s):"); + char *field_order_help = sort_help("output field(s): overhead period sample "); const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), @@ -1201,9 +1203,9 @@ int cmd_report(int argc, const char **argv) OPT_BOOLEAN(0, "header-only", &report.header_only, "Show only data header."), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - sort_help("sort by key(s):")), + sort_order_help), OPT_STRING('F', "fields", &field_order, "key[,keys...]", - sort_help("output field(s): overhead period sample ")), + field_order_help), OPT_BOOLEAN(0, "show-cpu-utilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), OPT_BOOLEAN_FLAG(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, @@ -1336,11 +1338,11 @@ int cmd_report(int argc, const char **argv) char sort_tmp[128];

if (ret < 0) - return ret; + goto exit;

ret = perf_config(report__config, &report); if (ret) - return ret; + goto exit;

argc = parse_options(argc, argv, options, report_usage, 0); if (argc) { @@ -1354,8 +1356,10 @@ int cmd_report(int argc, const char **argv) report.symbol_filter_str = argv[0]; }

- if (annotate_check_args(&report.annotation_opts) < 0) - return -EINVAL; + if (annotate_check_args(&report.annotation_opts) < 0) { + ret = -EINVAL; + goto exit; + }

if (report.mmaps_mode) report.tasks_mode = true; @@ -1369,12 +1373,14 @@ int cmd_report(int argc, const char **argv) if (symbol_conf.vmlinux_name && access(symbol_conf.vmlinux_name, R_OK)) { pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name); - return -EINVAL; + ret = -EINVAL; + goto exit; } if (symbol_conf.kallsyms_name && access(symbol_conf.kallsyms_name, R_OK)) { pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name); - return -EINVAL; + ret = -EINVAL; + goto exit; }

if (report.inverted_callchain) @@ -1398,12 +1404,14 @@ int cmd_report(int argc, const char **argv)

repeat: session = perf_session__new(&data, false, &report.tool); - if (IS_ERR(session)) - return PTR_ERR(session); + if (IS_ERR(session)) { + ret = PTR_ERR(session); + goto exit; + }

ret = evswitch__init(&report.evswitch, session->evlist, stderr); if (ret) - return ret; + goto exit;

if (zstd_init(&(session->zstd_data), 0) < 0) pr_warning("Decompression initialization failed. Reported data may be incomplete.\n"); @@ -1638,5 +1646,8 @@ error:

zstd_fini(&(session->zstd_data)); perf_session__delete(session); +exit: + free(sort_order_help); + free(field_order_help); return ret; } diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 88ce47f2547e..568a88c001c6 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -3370,7 +3370,7 @@ static void add_hpp_sort_string(struct strbuf *sb, struct hpp_dimension *s, int add_key(sb, s[i].name, llen); }

-const char *sort_help(const char *prefix) +char *sort_help(const char *prefix) { struct strbuf sb; char *s; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 87a092645aa7..b67c469aba79 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -302,7 +302,7 @@ void reset_output_field(void); void sort__setup_elide(FILE *fp); void perf_hpp__set_elide(int idx, bool elide);

-const char *sort_help(const char *prefix); +char *sort_help(const char *prefix);

int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);

From: Riccardo Mancini rickyman7@gmail.com

[ Upstream commit faf3ac305d61341c74e5cdd9e41daecce7f67bfe ]

ASan reports several memory leaks while running:

# perf test "82: Use vfs_getname probe to get syscall args filenames"

Two of these are caused by some refcounts not being decreased on perf-script exit, namely script.threads and script.cpus.

This patch adds the missing __put calls in a new perf_script__exit function, which is called at the end of cmd_script.

This patch concludes the fixes of all remaining memory leaks in perf test "82: Use vfs_getname probe to get syscall args filenames".

Signed-off-by: Riccardo Mancini rickyman7@gmail.com Fixes: cfc8874a48599249 ("perf script: Process cpu/threads maps") Cc: Ian Rogers irogers@google.com Cc: Jiri Olsa jolsa@redhat.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: http://lore.kernel.org/lkml/5ee73b19791c6fa9d24c4d57f4ac1a23609400d7.1626343... Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/builtin-script.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 8a6656ab835b..c43c2963117d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2534,6 +2534,12 @@ static void perf_script__exit_per_event_dump_stats(struct perf_script *script) } }

+static void perf_script__exit(struct perf_script *script) +{ + perf_thread_map__put(script->threads); + perf_cpu_map__put(script->cpus); +} + static int __cmd_script(struct perf_script *script) { int ret; @@ -3994,6 +4000,7 @@ out_delete: zstd_fini(&(session->zstd_data)); evlist__free_stats(session->evlist); perf_session__delete(session); + perf_script__exit(&script);

if (script_started) cleanup_scripting();

From: Riccardo Mancini rickyman7@gmail.com

[ Upstream commit e0fa7ab42232e742dcb3de9f3c1f6127b5adc019 ]

ASan reports some memory leaks when running:

# perf test "42: BPF filter"

This second leak is caused by a strlist not being dellocated on error inside probe_file__del_events.

This patch adds a goto label before the deallocation and makes the error path jump to it.

Signed-off-by: Riccardo Mancini rickyman7@gmail.com Fixes: e7895e422e4da63d ("perf probe: Split del_perf_probe_events()") Cc: Ian Rogers irogers@google.com Cc: Jiri Olsa jolsa@redhat.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: http://lore.kernel.org/lkml/174963c587ae77fa108af794669998e4ae558338.1626343... Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/probe-file.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 52273542e6ef..3f6de459ac2b 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -342,11 +342,11 @@ int probe_file__del_events(int fd, struct strfilter *filter)

ret = probe_file__get_events(fd, filter, namelist); if (ret < 0) - return ret; + goto out;

ret = probe_file__del_strlist(fd, namelist); +out: strlist__delete(namelist); - return ret; }

From: Yang Jihong yangjihong1@huawei.com

[ Upstream commit b0f008551f0bf4d5f6db9b5f0e071b02790d6a2e ]

The tracepoints trace_sched_stat_{wait, sleep, iowait} are not exposed to user if CONFIG_SCHEDSTATS is not set, "perf sched record" records the three events. As a result, the command fails.

Before:

#perf sched record sleep 1 event syntax error: 'sched:sched_stat_wait' ___ unknown tracepoint

Error: File /sys/kernel/tracing/events/sched/sched_stat_wait not found. Hint: Perhaps this kernel misses some CONFIG_ setting to enable this feature?.

Run 'perf list' for a list of valid events

Usage: perf record [<options>] [<command>] or: perf record [<options>] -- <command> [<options>]

-e, --event <event> event selector. use 'perf list' to list available events

Solution: Check whether schedstat tracepoints are exposed. If no, these events are not recorded.

After: # perf sched record sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.163 MB perf.data (1091 samples) ] # perf sched report run measurement overhead: 4736 nsecs sleep measurement overhead: 9059979 nsecs the run test took 999854 nsecs the sleep test took 8945271 nsecs nr_run_events: 716 nr_sleep_events: 785 nr_wakeup_events: 0 ... ------------------------------------------------------------

Fixes: 2a09b5de235a6 ("sched/fair: do not expose some tracepoints to user if CONFIG_SCHEDSTATS is not set") Signed-off-by: Yang Jihong yangjihong1@huawei.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Jiri Olsa jolsa@redhat.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Steven Rostedt (VMware) rostedt@goodmis.org Cc: Yafang Shao laoar.shao@gmail.com Link: http://lore.kernel.org/lkml/20210713112358.194693-1-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/builtin-sched.c | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 954ce2f594e9..3e5b7faf0c16 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -3335,6 +3335,16 @@ static void setup_sorting(struct perf_sched *sched, const struct option *options sort_dimension__add("pid", &sched->cmp_pid); }

+static bool schedstat_events_exposed(void) +{ + /* + * Select "sched:sched_stat_wait" event to check + * whether schedstat tracepoints are exposed. + */ + return IS_ERR(trace_event__tp_format("sched", "sched_stat_wait")) ? + false : true; +} + static int __cmd_record(int argc, const char **argv) { unsigned int rec_argc, i, j; @@ -3346,21 +3356,33 @@ static int __cmd_record(int argc, const char **argv) "-m", "1024", "-c", "1", "-e", "sched:sched_switch", - "-e", "sched:sched_stat_wait", - "-e", "sched:sched_stat_sleep", - "-e", "sched:sched_stat_iowait", "-e", "sched:sched_stat_runtime", "-e", "sched:sched_process_fork", "-e", "sched:sched_wakeup_new", "-e", "sched:sched_migrate_task", }; + + /* + * The tracepoints trace_sched_stat_{wait, sleep, iowait} + * are not exposed to user if CONFIG_SCHEDSTATS is not set, + * to prevent "perf sched record" execution failure, determine + * whether to record schedstat events according to actual situation. + */ + const char * const schedstat_args[] = { + "-e", "sched:sched_stat_wait", + "-e", "sched:sched_stat_sleep", + "-e", "sched:sched_stat_iowait", + }; + unsigned int schedstat_argc = schedstat_events_exposed() ? + ARRAY_SIZE(schedstat_args) : 0; + struct tep_event *waking_event;

/* * +2 for either "-e", "sched:sched_wakeup" or * "-e", "sched:sched_waking" */ - rec_argc = ARRAY_SIZE(record_args) + 2 + argc - 1; + rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1; rec_argv = calloc(rec_argc + 1, sizeof(char *));

if (rec_argv == NULL) @@ -3376,6 +3398,9 @@ static int __cmd_record(int argc, const char **argv) else rec_argv[i++] = strdup("sched:sched_wakeup");

+ for (j = 0; j < schedstat_argc; j++) + rec_argv[i++] = strdup(schedstat_args[j]); + for (j = 1; j < (unsigned int)argc; j++, i++) rec_argv[i] = argv[j];

From: Charles Keepax ckeepax@opensource.cirrus.com

[ Upstream commit dd6fb8ff2210f74b056bf9234d0605e8c26a8ac0 ]

When wm_coeff_tlv_get was updated it was accidentally switch to the _raw version of the helper causing it to ignore the current DSP state it should be checking. Switch the code back to the correct helper so that users can't read the controls when they arn't available.

Fixes: 73ecf1a673d3 ("ASoC: wm_adsp: Correct cache handling of new kernel control API") Signed-off-by: Charles Keepax ckeepax@opensource.cirrus.com Link: https://lore.kernel.org/r/20210626155941.12251-1-ckeepax@opensource.cirrus.c... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/codecs/wm_adsp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 3dc119daf2f6..cef05d81c39b 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -1213,7 +1213,7 @@ static int wm_coeff_tlv_get(struct snd_kcontrol *kctl,

mutex_lock(&ctl->dsp->pwr_lock);

- ret = wm_coeff_read_ctrl_raw(ctl, ctl->cache, size); + ret = wm_coeff_read_ctrl(ctl, ctl->cache, size);

if (!ret && copy_to_user(bytes, ctl->cache, size)) ret = -EFAULT;

From: Axel Lin axel.lin@ingics.com

[ Upstream commit ae60e6a9d24e89a74e2512204ad04de94921bdd2 ]

Use unsigned int instead of u32 for regmap_read/regmap_update_bits val argument.

Signed-off-by: Axel Lin axel.lin@ingics.com Link: https://lore.kernel.org/r/20210619124133.4096683-1-axel.lin@ingics.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/regulator/hi6421-regulator.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/regulator/hi6421-regulator.c b/drivers/regulator/hi6421-regulator.c index dc631c1a46b4..bff8c515dcde 100644 --- a/drivers/regulator/hi6421-regulator.c +++ b/drivers/regulator/hi6421-regulator.c @@ -386,7 +386,7 @@ static int hi6421_regulator_enable(struct regulator_dev *rdev) static unsigned int hi6421_regulator_ldo_get_mode(struct regulator_dev *rdev) { struct hi6421_regulator_info *info = rdev_get_drvdata(rdev); - u32 reg_val; + unsigned int reg_val;

regmap_read(rdev->regmap, rdev->desc->enable_reg, &reg_val); if (reg_val & info->mode_mask) @@ -398,7 +398,7 @@ static unsigned int hi6421_regulator_ldo_get_mode(struct regulator_dev *rdev) static unsigned int hi6421_regulator_buck_get_mode(struct regulator_dev *rdev) { struct hi6421_regulator_info *info = rdev_get_drvdata(rdev); - u32 reg_val; + unsigned int reg_val;

regmap_read(rdev->regmap, rdev->desc->enable_reg, &reg_val); if (reg_val & info->mode_mask) @@ -411,7 +411,7 @@ static int hi6421_regulator_ldo_set_mode(struct regulator_dev *rdev, unsigned int mode) { struct hi6421_regulator_info *info = rdev_get_drvdata(rdev); - u32 new_mode; + unsigned int new_mode;

switch (mode) { case REGULATOR_MODE_NORMAL: @@ -435,7 +435,7 @@ static int hi6421_regulator_buck_set_mode(struct regulator_dev *rdev, unsigned int mode) { struct hi6421_regulator_info *info = rdev_get_drvdata(rdev); - u32 new_mode; + unsigned int new_mode;

switch (mode) { case REGULATOR_MODE_NORMAL:

From: Peter Hess peter.hess@ph-home.de

[ Upstream commit 3a70dd2d050331ee4cf5ad9d5c0a32d83ead9a43 ]

In FIFO mode were two problems: - RX mode was never handled and - in this case the tx_buf pointer was NULL and caused an exception

fix this by handling RX mode in mtk_spi_fifo_transfer

Fixes: a568231f4632 ("spi: mediatek: Add spi bus for Mediatek MT8173") Signed-off-by: Peter Hess peter.hess@ph-home.de Signed-off-by: Frank Wunderlich frank-w@public-files.de Link: https://lore.kernel.org/r/20210706121609.680534-1-linux@fw-web.de Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-mt65xx.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 976f73b9e299..8d5fa7f1e506 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -427,13 +427,23 @@ static int mtk_spi_fifo_transfer(struct spi_master *master, mtk_spi_setup_packet(master);

cnt = xfer->len / 4; - iowrite32_rep(mdata->base + SPI_TX_DATA_REG, xfer->tx_buf, cnt); + if (xfer->tx_buf) + iowrite32_rep(mdata->base + SPI_TX_DATA_REG, xfer->tx_buf, cnt); + + if (xfer->rx_buf) + ioread32_rep(mdata->base + SPI_RX_DATA_REG, xfer->rx_buf, cnt);

remainder = xfer->len % 4; if (remainder > 0) { reg_val = 0; - memcpy(&reg_val, xfer->tx_buf + (cnt * 4), remainder); - writel(reg_val, mdata->base + SPI_TX_DATA_REG); + if (xfer->tx_buf) { + memcpy(&reg_val, xfer->tx_buf + (cnt * 4), remainder); + writel(reg_val, mdata->base + SPI_TX_DATA_REG); + } + if (xfer->rx_buf) { + reg_val = readl(mdata->base + SPI_RX_DATA_REG); + memcpy(xfer->rx_buf + (cnt * 4), &reg_val, remainder); + } }

mtk_spi_enable_transfer(master);

From: Xuan Zhuo xuanzhuo@linux.alibaba.com

[ Upstream commit 5e21bb4e812566aef86fbb77c96a4ec0782286e4 ]

These two types of XDP progs (BPF_XDP_DEVMAP, BPF_XDP_CPUMAP) will not be executed directly in the driver, therefore we should also not directly run them from here. To run in these two situations, there must be further preparations done, otherwise these may cause a kernel panic.

For more details, see also dev_xdp_attach().

[ 46.982479] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 46.984295] #PF: supervisor read access in kernel mode [ 46.985777] #PF: error_code(0x0000) - not-present page [ 46.987227] PGD 800000010dca4067 P4D 800000010dca4067 PUD 10dca6067 PMD 0 [ 46.989201] Oops: 0000 [#1] SMP PTI [ 46.990304] CPU: 7 PID: 562 Comm: a.out Not tainted 5.13.0+ #44 [ 46.992001] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/24 [ 46.995113] RIP: 0010:___bpf_prog_run+0x17b/0x1710 [ 46.996586] Code: 49 03 14 cc e8 76 f6 fe ff e9 ad fe ff ff 0f b6 43 01 48 0f bf 4b 02 48 83 c3 08 89 c2 83 e0 0f c0 ea 04 02 [ 47.001562] RSP: 0018:ffffc900005afc58 EFLAGS: 00010246 [ 47.003115] RAX: 0000000000000000 RBX: ffffc9000023f068 RCX: 0000000000000000 [ 47.005163] RDX: 0000000000000000 RSI: 0000000000000079 RDI: ffffc900005afc98 [ 47.007135] RBP: 0000000000000000 R08: ffffc9000023f048 R09: c0000000ffffdfff [ 47.009171] R10: 0000000000000001 R11: ffffc900005afb40 R12: ffffc900005afc98 [ 47.011172] R13: 0000000000000001 R14: 0000000000000001 R15: ffffffff825258a8 [ 47.013244] FS: 00007f04a5207580(0000) GS:ffff88842fdc0000(0000) knlGS:0000000000000000 [ 47.015705] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 47.017475] CR2: 0000000000000000 CR3: 0000000100182005 CR4: 0000000000770ee0 [ 47.019558] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 47.021595] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 47.023574] PKRU: 55555554 [ 47.024571] Call Trace: [ 47.025424] __bpf_prog_run32+0x32/0x50 [ 47.026296] ? printk+0x53/0x6a [ 47.027066] ? ktime_get+0x39/0x90 [ 47.027895] bpf_test_run.cold.28+0x23/0x123 [ 47.028866] ? printk+0x53/0x6a [ 47.029630] bpf_prog_test_run_xdp+0x149/0x1d0 [ 47.030649] __sys_bpf+0x1305/0x23d0 [ 47.031482] __x64_sys_bpf+0x17/0x20 [ 47.032316] do_syscall_64+0x3a/0x80 [ 47.033165] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 47.034254] RIP: 0033:0x7f04a51364dd [ 47.035133] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 48 [ 47.038768] RSP: 002b:00007fff8f9fc518 EFLAGS: 00000213 ORIG_RAX: 0000000000000141 [ 47.040344] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f04a51364dd [ 47.041749] RDX: 0000000000000048 RSI: 0000000020002a80 RDI: 000000000000000a [ 47.043171] RBP: 00007fff8f9fc530 R08: 0000000002049300 R09: 0000000020000100 [ 47.044626] R10: 0000000000000004 R11: 0000000000000213 R12: 0000000000401070 [ 47.046088] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 47.047579] Modules linked in: [ 47.048318] CR2: 0000000000000000 [ 47.049120] ---[ end trace 7ad34443d5be719a ]--- [ 47.050273] RIP: 0010:___bpf_prog_run+0x17b/0x1710 [ 47.051343] Code: 49 03 14 cc e8 76 f6 fe ff e9 ad fe ff ff 0f b6 43 01 48 0f bf 4b 02 48 83 c3 08 89 c2 83 e0 0f c0 ea 04 02 [ 47.054943] RSP: 0018:ffffc900005afc58 EFLAGS: 00010246 [ 47.056068] RAX: 0000000000000000 RBX: ffffc9000023f068 RCX: 0000000000000000 [ 47.057522] RDX: 0000000000000000 RSI: 0000000000000079 RDI: ffffc900005afc98 [ 47.058961] RBP: 0000000000000000 R08: ffffc9000023f048 R09: c0000000ffffdfff [ 47.060390] R10: 0000000000000001 R11: ffffc900005afb40 R12: ffffc900005afc98 [ 47.061803] R13: 0000000000000001 R14: 0000000000000001 R15: ffffffff825258a8 [ 47.063249] FS: 00007f04a5207580(0000) GS:ffff88842fdc0000(0000) knlGS:0000000000000000 [ 47.065070] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 47.066307] CR2: 0000000000000000 CR3: 0000000100182005 CR4: 0000000000770ee0 [ 47.067747] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 47.069217] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 47.070652] PKRU: 55555554 [ 47.071318] Kernel panic - not syncing: Fatal exception [ 47.072854] Kernel Offset: disabled [ 47.073683] ---[ end Kernel panic - not syncing: Fatal exception ]---

Fixes: 9216477449f3 ("bpf: cpumap: Add the possibility to attach an eBPF program to cpumap") Fixes: fbee97feed9b ("bpf: Add support to attach bpf program to a devmap entry") Reported-by: Abaci abaci@linux.alibaba.com Signed-off-by: Xuan Zhuo xuanzhuo@linux.alibaba.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: Dust Li dust.li@linux.alibaba.com Acked-by: Jesper Dangaard Brouer brouer@redhat.com Acked-by: David Ahern dsahern@kernel.org Acked-by: Song Liu songliubraving@fb.com Link: https://lore.kernel.org/bpf/20210708080409.73525-1-xuanzhuo@linux.alibaba.co... Signed-off-by: Sasha Levin sashal@kernel.org --- net/bpf/test_run.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index a5d72c48fb66..28ac3c96fa88 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -701,6 +701,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, void *data; int ret;

+ if (prog->expected_attach_type == BPF_XDP_DEVMAP || + prog->expected_attach_type == BPF_XDP_CPUMAP) + return -EINVAL; if (kattr->test.ctx_in || kattr->test.ctx_out) return -EINVAL;

From: Xuan Zhuo xuanzhuo@linux.alibaba.com

[ Upstream commit 5acc7d3e8d342858405fbbc671221f676b547ce7 ]

The problem occurs between dev_get_by_index() and dev_xdp_attach_link(). At this point, dev_xdp_uninstall() is called. Then xdp link will not be detached automatically when dev is released. But link->dev already points to dev, when xdp link is released, dev will still be accessed, but dev has been released.

dev_get_by_index() | link->dev = dev | | rtnl_lock() | unregister_netdevice_many() | dev_xdp_uninstall() | rtnl_unlock() rtnl_lock(); | dev_xdp_attach_link() | rtnl_unlock(); | | netdev_run_todo() // dev released bpf_xdp_link_release() | /* access dev. | use-after-free */ |

[ 45.966867] BUG: KASAN: use-after-free in bpf_xdp_link_release+0x3b8/0x3d0 [ 45.967619] Read of size 8 at addr ffff00000f9980c8 by task a.out/732 [ 45.968297] [ 45.968502] CPU: 1 PID: 732 Comm: a.out Not tainted 5.13.0+ #22 [ 45.969222] Hardware name: linux,dummy-virt (DT) [ 45.969795] Call trace: [ 45.970106] dump_backtrace+0x0/0x4c8 [ 45.970564] show_stack+0x30/0x40 [ 45.970981] dump_stack_lvl+0x120/0x18c [ 45.971470] print_address_description.constprop.0+0x74/0x30c [ 45.972182] kasan_report+0x1e8/0x200 [ 45.972659] __asan_report_load8_noabort+0x2c/0x50 [ 45.973273] bpf_xdp_link_release+0x3b8/0x3d0 [ 45.973834] bpf_link_free+0xd0/0x188 [ 45.974315] bpf_link_put+0x1d0/0x218 [ 45.974790] bpf_link_release+0x3c/0x58 [ 45.975291] __fput+0x20c/0x7e8 [ 45.975706] ____fput+0x24/0x30 [ 45.976117] task_work_run+0x104/0x258 [ 45.976609] do_notify_resume+0x894/0xaf8 [ 45.977121] work_pending+0xc/0x328 [ 45.977575] [ 45.977775] The buggy address belongs to the page: [ 45.978369] page:fffffc00003e6600 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x4f998 [ 45.979522] flags: 0x7fffe0000000000(node=0|zone=0|lastcpupid=0x3ffff) [ 45.980349] raw: 07fffe0000000000 fffffc00003e6708 ffff0000dac3c010 0000000000000000 [ 45.981309] raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 [ 45.982259] page dumped because: kasan: bad access detected [ 45.982948] [ 45.983153] Memory state around the buggy address: [ 45.983753] ffff00000f997f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 45.984645] ffff00000f998000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 45.985533] >ffff00000f998080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 45.986419] ^ [ 45.987112] ffff00000f998100: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 45.988006] ffff00000f998180: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 45.988895] ================================================================== [ 45.989773] Disabling lock debugging due to kernel taint [ 45.990552] Kernel panic - not syncing: panic_on_warn set ... [ 45.991166] CPU: 1 PID: 732 Comm: a.out Tainted: G B 5.13.0+ #22 [ 45.991929] Hardware name: linux,dummy-virt (DT) [ 45.992448] Call trace: [ 45.992753] dump_backtrace+0x0/0x4c8 [ 45.993208] show_stack+0x30/0x40 [ 45.993627] dump_stack_lvl+0x120/0x18c [ 45.994113] dump_stack+0x1c/0x34 [ 45.994530] panic+0x3a4/0x7d8 [ 45.994930] end_report+0x194/0x198 [ 45.995380] kasan_report+0x134/0x200 [ 45.995850] __asan_report_load8_noabort+0x2c/0x50 [ 45.996453] bpf_xdp_link_release+0x3b8/0x3d0 [ 45.997007] bpf_link_free+0xd0/0x188 [ 45.997474] bpf_link_put+0x1d0/0x218 [ 45.997942] bpf_link_release+0x3c/0x58 [ 45.998429] __fput+0x20c/0x7e8 [ 45.998833] ____fput+0x24/0x30 [ 45.999247] task_work_run+0x104/0x258 [ 45.999731] do_notify_resume+0x894/0xaf8 [ 46.000236] work_pending+0xc/0x328 [ 46.000697] SMP: stopping secondary CPUs [ 46.001226] Dumping ftrace buffer: [ 46.001663] (ftrace buffer empty) [ 46.002110] Kernel Offset: disabled [ 46.002545] CPU features: 0x00000001,23202c00 [ 46.003080] Memory Limit: none

Fixes: aa8d3a716b59db6c ("bpf, xdp: Add bpf_link-based XDP attachment API") Reported-by: Abaci abaci@linux.alibaba.com Signed-off-by: Xuan Zhuo xuanzhuo@linux.alibaba.com Signed-off-by: Alexei Starovoitov ast@kernel.org Reviewed-by: Dust Li dust.li@linux.alibaba.com Acked-by: Andrii Nakryiko andrii@kernel.org Link: https://lore.kernel.org/bpf/20210710031635.41649-1-xuanzhuo@linux.alibaba.co... Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/dev.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c index 4f29dde4ed0a..0dcedcdf6d7e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9659,14 +9659,17 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) struct net_device *dev; int err, fd;

+ rtnl_lock(); dev = dev_get_by_index(net, attr->link_create.target_ifindex); - if (!dev) + if (!dev) { + rtnl_unlock(); return -EINVAL; + }

link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; - goto out_put_dev; + goto unlock; }

bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog); @@ -9676,14 +9679,14 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); - goto out_put_dev; + goto unlock; }

- rtnl_lock(); err = dev_xdp_attach_link(dev, NULL, link); rtnl_unlock();

if (err) { + link->dev = NULL; bpf_link_cleanup(&link_primer); goto out_put_dev; } @@ -9693,6 +9696,9 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) dev_put(dev); return fd;

+unlock: + rtnl_unlock(); + out_put_dev: dev_put(dev); return err;

From: Nicolas Saenz Julienne nsaenzju@redhat.com

[ Upstream commit aebacb7f6ca1926918734faae14d1f0b6fae5cb7 ]

31cd0e119d50 ("timers: Recalculate next timer interrupt only when necessary") subtly altered get_next_timer_interrupt()'s behaviour. The function no longer consistently returns KTIME_MAX with no timers pending.

In order to decide if there are any timers pending we check whether the next expiry will happen NEXT_TIMER_MAX_DELTA jiffies from now. Unfortunately, the next expiry time and the timer base clock are no longer updated in unison. The former changes upon certain timer operations (enqueue, expire, detach), whereas the latter keeps track of jiffies as they move forward. Ultimately breaking the logic above.

A simplified example:

- Upon entering get_next_timer_interrupt() with:

jiffies = 1 base->clk = 0; base->next_expiry = NEXT_TIMER_MAX_DELTA;

'base->next_expiry == base->clk + NEXT_TIMER_MAX_DELTA', the function returns KTIME_MAX.

- 'base->clk' is updated to the jiffies value.

- The next time we enter get_next_timer_interrupt(), taking into account no timer operations happened:

base->clk = 1; base->next_expiry = NEXT_TIMER_MAX_DELTA;

'base->next_expiry != base->clk + NEXT_TIMER_MAX_DELTA', the function returns a valid expire time, which is incorrect.

This ultimately might unnecessarily rearm sched's timer on nohz_full setups, and add latency to the system[1].

So, introduce 'base->timers_pending'[2], update it every time 'base->next_expiry' changes, and use it in get_next_timer_interrupt().

[1] See tick_nohz_stop_tick(). [2] A quick pahole check on x86_64 and arm64 shows it doesn't make 'struct timer_base' any bigger.

Fixes: 31cd0e119d50 ("timers: Recalculate next timer interrupt only when necessary") Signed-off-by: Nicolas Saenz Julienne nsaenzju@redhat.com Signed-off-by: Frederic Weisbecker frederic@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/time/timer.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/kernel/time/timer.c b/kernel/time/timer.c index d111adf4a0cb..99b97ccefdbd 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -207,6 +207,7 @@ struct timer_base { unsigned int cpu; bool next_expiry_recalc; bool is_idle; + bool timers_pending; DECLARE_BITMAP(pending_map, WHEEL_SIZE); struct hlist_head vectors[WHEEL_SIZE]; } ____cacheline_aligned; @@ -595,6 +596,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, * can reevaluate the wheel: */ base->next_expiry = bucket_expiry; + base->timers_pending = true; base->next_expiry_recalc = false; trigger_dyntick_cpu(base, timer); } @@ -1596,6 +1598,7 @@ static unsigned long __next_timer_interrupt(struct timer_base *base) }

base->next_expiry_recalc = false; + base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA);

return next; } @@ -1647,7 +1650,6 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); u64 expires = KTIME_MAX; unsigned long nextevt; - bool is_max_delta;

/* * Pretend that there is no timer pending if the cpu is offline. @@ -1660,7 +1662,6 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) if (base->next_expiry_recalc) base->next_expiry = __next_timer_interrupt(base); nextevt = base->next_expiry; - is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);

/* * We have a fresh next event. Check whether we can forward the @@ -1678,7 +1679,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) expires = basem; base->is_idle = false; } else { - if (!is_max_delta) + if (base->timers_pending) expires = basem + (u64)(nextevt - basej) * TICK_NSEC; /* * If we expect to sleep more than a tick, mark the base idle. @@ -1961,6 +1962,7 @@ int timers_prepare_cpu(unsigned int cpu) base = per_cpu_ptr(&timer_bases[b], cpu); base->clk = jiffies; base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA; + base->timers_pending = false; base->is_idle = false; } return 0;

From: Geert Uytterhoeven geert+renesas@glider.be

[ Upstream commit 99bb2ebab953435852340cdb198c5abbf0bb5dd3 ]

Making global2 support mandatory removed the Kconfig symbol NET_DSA_MV88E6XXX_GLOBAL2. This symbol also served as an intermediate symbol to make NET_DSA_MV88E6XXX_PTP depend on NET_DSA_MV88E6XXX. With the symbol removed, the user is always asked about PTP support for Marvell 88E6xxx switches, even if the latter support is not enabled.

Fix this by reinstating the dependency.

Fixes: 63368a7416df144b ("net: dsa: mv88e6xxx: Make global2 support mandatory") Signed-off-by: Geert Uytterhoeven geert+renesas@glider.be Reviewed-by: Andrew Lunn andrew@lunn.ch Reviewed-by: Vladimir Oltean olteanv@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/mv88e6xxx/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/Kconfig b/drivers/net/dsa/mv88e6xxx/Kconfig index 05af632b0f59..634a48e6616b 100644 --- a/drivers/net/dsa/mv88e6xxx/Kconfig +++ b/drivers/net/dsa/mv88e6xxx/Kconfig @@ -12,7 +12,7 @@ config NET_DSA_MV88E6XXX config NET_DSA_MV88E6XXX_PTP bool "PTP support for Marvell 88E6xxx" default n - depends on PTP_1588_CLOCK + depends on NET_DSA_MV88E6XXX && PTP_1588_CLOCK help Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch chips that support it.

From: Colin Ian King colin.king@canonical.com

[ Upstream commit 91091656252f5d6d8c476e0c92776ce9fae7b445 ]

Currently array jit->seen_reg[r1] is being accessed before the range checking of index r1. The range changing on r1 should be performed first since it will avoid any potential out-of-range accesses on the array seen_reg[] and also it is more optimal to perform checks on r1 before fetching data from the array. Fix this by swapping the order of the checks before the array access.

Fixes: 054623105728 ("s390/bpf: Add s390x eBPF JIT compiler backend") Signed-off-by: Colin Ian King colin.king@canonical.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Tested-by: Ilya Leoshkevich iii@linux.ibm.com Acked-by: Ilya Leoshkevich iii@linux.ibm.com Link: https://lore.kernel.org/bpf/20210715125712.24690-1-colin.king@canonical.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/net/bpf_jit_comp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 63cae0476bb4..2ae419f5115a 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -112,7 +112,7 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1) { u32 r1 = reg2hex[b1];

- if (!jit->seen_reg[r1] && r1 >= 6 && r1 <= 15) + if (r1 >= 6 && r1 <= 15 && !jit->seen_reg[r1]) jit->seen_reg[r1] = 1; }

From: John Fastabend john.fastabend@gmail.com

[ Upstream commit 228a4a7ba8e99bb9ef980b62f71e3be33f4aae69 ]

The proc socket stats use sk_prot->inuse_idx value to record inuse sock stats. We currently do not set this correctly from sockmap side. The result is reading sock stats '/proc/net/sockstat' gives incorrect values. The socket counter is incremented correctly, but because we don't set the counter correctly when we replace sk_prot we may omit the decrement.

To get the correct inuse_idx value move the core_initcall that initializes the TCP proto handlers to late_initcall. This way it is initialized after TCP has the chance to assign the inuse_idx value from the register protocol handler.

Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Suggested-by: Jakub Sitnicki jakub@cloudflare.com Signed-off-by: John Fastabend john.fastabend@gmail.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: Cong Wang cong.wang@bytedance.com Link: https://lore.kernel.org/bpf/20210712195546.423990-3-john.fastabend@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_bpf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index ad9d17923fc5..b65201ba4d93 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -486,7 +486,7 @@ static int __init tcp_bpf_v4_build_proto(void) tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV4], &tcp_prot); return 0; } -core_initcall(tcp_bpf_v4_build_proto); +late_initcall(tcp_bpf_v4_build_proto);

static int tcp_bpf_assert_proto_ops(struct proto *ops) {

From: Tobias Klauser tklauser@distanz.ch

[ Upstream commit d444b06e40855219ef38b5e9286db16d435f06dc ]

Fix and add a missing NULL check for the prior malloc() call.

Fixes: 49a086c201a9 ("bpftool: implement prog load command") Signed-off-by: Tobias Klauser tklauser@distanz.ch Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: Quentin Monnet quentin@isovalent.com Acked-by: Roman Gushchin guro@fb.com Link: https://lore.kernel.org/bpf/20210715110609.29364-1-tklauser@distanz.ch Signed-off-by: Sasha Levin sashal@kernel.org --- tools/bpf/bpftool/common.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 1828bba19020..dc6daa193557 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -222,6 +222,11 @@ int mount_bpffs_for_pin(const char *name) int err = 0;

file = malloc(strlen(name) + 1); + if (!file) { + p_err("mem alloc failed"); + return -1; + } + strcpy(file, name); dir = dirname(file);

From: Yoshitaka Ikeda ikeda@nskint.co.jp

[ Upstream commit 55cef88bbf12f3bfbe5c2379a8868a034707e755 ]

Fix below division by zero warning: - Added an if statement because buswidth can be zero, resulting in division by zero. - The modified code was based on another driver (atmel-quadspi).

[ 0.795337] Division by zero in kernel. : [ 0.834051] [<807fd40c>] (__div0) from [<804e1acc>] (Ldiv0+0x8/0x10) [ 0.839097] [<805f0710>] (cqspi_exec_mem_op) from [<805edb4c>] (spi_mem_exec_op+0x3b0/0x3f8)

Fixes: 7512eaf54190 ("spi: cadence-quadspi: Fix dummy cycle calculation when buswidth > 1") Signed-off-by: Yoshitaka Ikeda ikeda@nskint.co.jp Link: https://lore.kernel.org/r/ed989af6-da88-4e0b-9ed8-126db6cad2e4@nskint.co.jp Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-cadence-quadspi.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 7a00346ff9b9..13d1f0ce618e 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -307,11 +307,13 @@ static unsigned int cqspi_calc_rdreg(struct cqspi_flash_pdata *f_pdata)

static unsigned int cqspi_calc_dummy(const struct spi_mem_op *op, bool dtr) { - unsigned int dummy_clk; + unsigned int dummy_clk = 0;

- dummy_clk = op->dummy.nbytes * (8 / op->dummy.buswidth); - if (dtr) - dummy_clk /= 2; + if (op->dummy.buswidth && op->dummy.nbytes) { + dummy_clk = op->dummy.nbytes * (8 / op->dummy.buswidth); + if (dtr) + dummy_clk /= 2; + }

return dummy_clk; }

From: Roman Skakun Roman_Skakun@epam.com

[ Upstream commit 40ac971eab89330d6153e7721e88acd2d98833f9 ]

xen-swiotlb can use vmalloc backed addresses for dma coherent allocations and uses the common helpers. Properly handle them to unbreak Xen on ARM platforms.

Fixes: 1b65c4e5a9af ("swiotlb-xen: use xen_alloc/free_coherent_pages") Signed-off-by: Roman Skakun roman_skakun@epam.com Reviewed-by: Andrii Anisov andrii_anisov@epam.com [hch: split the patch, renamed the helpers] Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/dma/ops_helpers.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c index 910ae69cae77..af4a6ef48ce0 100644 --- a/kernel/dma/ops_helpers.c +++ b/kernel/dma/ops_helpers.c @@ -5,6 +5,13 @@ */ #include <linux/dma-map-ops.h>

+static struct page *dma_common_vaddr_to_page(void *cpu_addr) +{ + if (is_vmalloc_addr(cpu_addr)) + return vmalloc_to_page(cpu_addr); + return virt_to_page(cpu_addr); +} + /* * Create scatter-list for the already allocated DMA buffer. */ @@ -12,7 +19,7 @@ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { - struct page *page = virt_to_page(cpu_addr); + struct page *page = dma_common_vaddr_to_page(cpu_addr); int ret;

ret = sg_alloc_table(sgt, 1, GFP_KERNEL); @@ -32,6 +39,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, unsigned long user_count = vma_pages(vma); unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; unsigned long off = vma->vm_pgoff; + struct page *page = dma_common_vaddr_to_page(cpu_addr); int ret = -ENXIO;

vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs); @@ -43,7 +51,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, return -ENXIO;

return remap_pfn_range(vma, vma->vm_start, - page_to_pfn(virt_to_page(cpu_addr)) + vma->vm_pgoff, + page_to_pfn(page) + vma->vm_pgoff, user_count << PAGE_SHIFT, vma->vm_page_prot); #else return -ENXIO;

From: Michal Suchanek msuchanek@suse.de

[ Upstream commit 674a9f1f6815849bfb5bf385e7da8fc198aaaba9 ]

Missing TPM final event log table is not a firmware bug.

Clearly if providing event log in the old format makes the final event log invalid it should not be provided at least in that case.

Fixes: b4f1874c6216 ("tpm: check event log version before reading final events") Signed-off-by: Michal Suchanek msuchanek@suse.de Reviewed-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/firmware/efi/tpm.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c index c1955d320fec..8f665678e9e3 100644 --- a/drivers/firmware/efi/tpm.c +++ b/drivers/firmware/efi/tpm.c @@ -62,9 +62,11 @@ int __init efi_tpm_eventlog_init(void) tbl_size = sizeof(*log_tbl) + log_tbl->size; memblock_reserve(efi.tpm_log, tbl_size);

- if (efi.tpm_final_log == EFI_INVALID_TABLE_ADDR || - log_tbl->version != EFI_TCG2_EVENT_LOG_FORMAT_TCG_2) { - pr_warn(FW_BUG "TPM Final Events table missing or invalid\n"); + if (efi.tpm_final_log == EFI_INVALID_TABLE_ADDR) { + pr_info("TPM Final Events table not present\n"); + goto out; + } else if (log_tbl->version != EFI_TCG2_EVENT_LOG_FORMAT_TCG_2) { + pr_warn(FW_BUG "TPM Final Events table invalid\n"); goto out; }

From: Nicholas Piggin npiggin@gmail.com

[ Upstream commit bd31ecf44b8e18ccb1e5f6b50f85de6922a60de3 ]

When running CPU_FTR_P9_TM_HV_ASSIST, HFSCR[TM] is set for the guest even if the host has CONFIG_TRANSACTIONAL_MEM=n, which causes it to be unprepared to handle guest exits while transactional.

Normal guests don't have a problem because the HTM capability will not be advertised, but a rogue or buggy one could crash the host.

Fixes: 4bb3c7a0208f ("KVM: PPC: Book3S HV: Work around transactional memory bugs in POWER9") Reported-by: Alexey Kardashevskiy aik@ozlabs.ru Signed-off-by: Nicholas Piggin npiggin@gmail.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20210716024310.164448-1-npiggin@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/kvm/book3s_hv.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 67cc164c4ac1..395f98158e81 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2445,8 +2445,10 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP | HFSCR_PREFIX; if (cpu_has_feature(CPU_FTR_HVMODE)) { vcpu->arch.hfscr &= mfspr(SPRN_HFSCR); +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) vcpu->arch.hfscr |= HFSCR_TM; +#endif } if (cpu_has_feature(CPU_FTR_TM_COMP)) vcpu->arch.hfscr |= HFSCR_TM;

From: Pavel Skripkin paskripkin@gmail.com

[ Upstream commit f5051bcece50140abd1a11a2d36dc3ec5484fc32 ]

Syzbot reported memory leak in tcindex_set_parms(). The problem was in non-freed perfect hash in tcindex_partial_destroy_work().

In tcindex_set_parms() new tcindex_data is allocated and some fields from old one are copied to new one, but not the perfect hash. Since tcindex_partial_destroy_work() is the destroy function for old tcindex_data, we need to free perfect hash to avoid memory leak.

Reported-and-tested-by: syzbot+f0bbb2287b8993d4fa74@syzkaller.appspotmail.com Fixes: 331b72922c5f ("net: sched: RCU cls_tcindex") Signed-off-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/cls_tcindex.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 5b274534264c..e9a8a2c86bbd 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -278,6 +278,8 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r, TCA_TCINDEX_POLICE); }

+static void tcindex_free_perfect_hash(struct tcindex_data *cp); + static void tcindex_partial_destroy_work(struct work_struct *work) { struct tcindex_data *p = container_of(to_rcu_work(work), @@ -285,7 +287,8 @@ static void tcindex_partial_destroy_work(struct work_struct *work) rwork);

rtnl_lock(); - kfree(p->perfect); + if (p->perfect) + tcindex_free_perfect_hash(p); kfree(p); rtnl_unlock(); }

From: Nguyen Dinh Phi phind.uet@gmail.com

[ Upstream commit 517a16b1a88bdb6b530f48d5d153478b2552d9a8 ]

Commit 63346650c1a9 ("netrom: switch to sock timer API") switched to use sock timer API. It replaces mod_timer() by sk_reset_timer(), and del_timer() by sk_stop_timer().

Function sk_reset_timer() will increase the refcount of sock if it is called on an inactive timer, hence, in case the timer expires, we need to decrease the refcount ourselves in the handler, otherwise, the sock refcount will be unbalanced and the sock will never be freed.

Signed-off-by: Nguyen Dinh Phi phind.uet@gmail.com Reported-by: syzbot+10f1194569953b72f1ae@syzkaller.appspotmail.com Fixes: 63346650c1a9 ("netrom: switch to sock timer API") Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/netrom/nr_timer.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index 9115f8a7dd45..a8da88db7893 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -121,11 +121,9 @@ static void nr_heartbeat_expiry(struct timer_list *t) is accepted() it isn't 'dead' so doesn't get removed. */ if (sock_flag(sk, SOCK_DESTROY) || (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { - sock_hold(sk); bh_unlock_sock(sk); nr_destroy_socket(sk); - sock_put(sk); - return; + goto out; } break;

@@ -146,6 +144,8 @@ static void nr_heartbeat_expiry(struct timer_list *t)

nr_start_heartbeat(sk); bh_unlock_sock(sk); +out: + sock_put(sk); }

static void nr_t2timer_expiry(struct timer_list *t) @@ -159,6 +159,7 @@ static void nr_t2timer_expiry(struct timer_list *t) nr_enquiry_response(sk); } bh_unlock_sock(sk); + sock_put(sk); }

static void nr_t4timer_expiry(struct timer_list *t) @@ -169,6 +170,7 @@ static void nr_t4timer_expiry(struct timer_list *t) bh_lock_sock(sk); nr_sk(sk)->condition &= ~NR_COND_PEER_RX_BUSY; bh_unlock_sock(sk); + sock_put(sk); }

static void nr_idletimer_expiry(struct timer_list *t) @@ -197,6 +199,7 @@ static void nr_idletimer_expiry(struct timer_list *t) sock_set_flag(sk, SOCK_DEAD); } bh_unlock_sock(sk); + sock_put(sk); }

static void nr_t1timer_expiry(struct timer_list *t) @@ -209,8 +212,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_1: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_write_internal(sk, NR_CONNREQ); @@ -220,8 +222,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_2: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_write_internal(sk, NR_DISCREQ); @@ -231,8 +232,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_3: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_requeue_frames(sk); @@ -241,5 +241,7 @@ static void nr_t1timer_expiry(struct timer_list *t) }

nr_start_t1timer(sk); +out: bh_unlock_sock(sk); + sock_put(sk); }

From: Dmitry Bogdanov d.bogdanov@yadro.com

[ Upstream commit 6d8e7e7c932162bccd06872362751b0e1d76f5af ]

WRITE SAME(32) command handling reads WRPROTECT at the wrong offset in 1st byte instead of 10th byte.

Link: https://lore.kernel.org/r/20210702091655.22818-1-d.bogdanov@yadro.com Fixes: afd73f1b60fc ("target: Perform PROTECT sanity checks for WRITE_SAME") Signed-off-by: Dmitry Bogdanov d.bogdanov@yadro.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/target/target_core_sbc.c | 35 ++++++++++++++++---------------- 1 file changed, 17 insertions(+), 18 deletions(-)

diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 7b07e557dc8d..6594bb0b9df0 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -25,7 +25,7 @@ #include "target_core_alua.h"

static sense_reason_t -sbc_check_prot(struct se_device *, struct se_cmd *, unsigned char *, u32, bool); +sbc_check_prot(struct se_device *, struct se_cmd *, unsigned char, u32, bool); static sense_reason_t sbc_execute_unmap(struct se_cmd *cmd);

static sense_reason_t @@ -279,14 +279,14 @@ static inline unsigned long long transport_lba_64_ext(unsigned char *cdb) }

static sense_reason_t -sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *ops) +sbc_setup_write_same(struct se_cmd *cmd, unsigned char flags, struct sbc_ops *ops) { struct se_device *dev = cmd->se_dev; sector_t end_lba = dev->transport->get_blocks(dev) + 1; unsigned int sectors = sbc_get_write_same_sectors(cmd); sense_reason_t ret;

- if ((flags[0] & 0x04) || (flags[0] & 0x02)) { + if ((flags & 0x04) || (flags & 0x02)) { pr_err("WRITE_SAME PBDATA and LBDATA" " bits not supported for Block Discard" " Emulation\n"); @@ -308,7 +308,7 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o }

/* We always have ANC_SUP == 0 so setting ANCHOR is always an error */ - if (flags[0] & 0x10) { + if (flags & 0x10) { pr_warn("WRITE SAME with ANCHOR not supported\n"); return TCM_INVALID_CDB_FIELD; } @@ -316,7 +316,7 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o * Special case for WRITE_SAME w/ UNMAP=1 that ends up getting * translated into block discard requests within backend code. */ - if (flags[0] & 0x08) { + if (flags & 0x08) { if (!ops->execute_unmap) return TCM_UNSUPPORTED_SCSI_OPCODE;

@@ -331,7 +331,7 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o if (!ops->execute_write_same) return TCM_UNSUPPORTED_SCSI_OPCODE;

- ret = sbc_check_prot(dev, cmd, &cmd->t_task_cdb[0], sectors, true); + ret = sbc_check_prot(dev, cmd, flags >> 5, sectors, true); if (ret) return ret;

@@ -717,10 +717,9 @@ sbc_set_prot_op_checks(u8 protect, bool fabric_prot, enum target_prot_type prot_ }

static sense_reason_t -sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb, +sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char protect, u32 sectors, bool is_write) { - u8 protect = cdb[1] >> 5; int sp_ops = cmd->se_sess->sup_prot_ops; int pi_prot_type = dev->dev_attrib.pi_prot_type; bool fabric_prot = false; @@ -768,7 +767,7 @@ sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb, fallthrough; default: pr_err("Unable to determine pi_prot_type for CDB: 0x%02x " - "PROTECT: 0x%02x\n", cdb[0], protect); + "PROTECT: 0x%02x\n", cmd->t_task_cdb[0], protect); return TCM_INVALID_CDB_FIELD; }

@@ -843,7 +842,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) if (sbc_check_dpofua(dev, cmd, cdb)) return TCM_INVALID_CDB_FIELD;

- ret = sbc_check_prot(dev, cmd, cdb, sectors, false); + ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, false); if (ret) return ret;

@@ -857,7 +856,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) if (sbc_check_dpofua(dev, cmd, cdb)) return TCM_INVALID_CDB_FIELD;

- ret = sbc_check_prot(dev, cmd, cdb, sectors, false); + ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, false); if (ret) return ret;

@@ -871,7 +870,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) if (sbc_check_dpofua(dev, cmd, cdb)) return TCM_INVALID_CDB_FIELD;

- ret = sbc_check_prot(dev, cmd, cdb, sectors, false); + ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, false); if (ret) return ret;

@@ -892,7 +891,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) if (sbc_check_dpofua(dev, cmd, cdb)) return TCM_INVALID_CDB_FIELD;

- ret = sbc_check_prot(dev, cmd, cdb, sectors, true); + ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, true); if (ret) return ret;

@@ -906,7 +905,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) if (sbc_check_dpofua(dev, cmd, cdb)) return TCM_INVALID_CDB_FIELD;

- ret = sbc_check_prot(dev, cmd, cdb, sectors, true); + ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, true); if (ret) return ret;

@@ -921,7 +920,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) if (sbc_check_dpofua(dev, cmd, cdb)) return TCM_INVALID_CDB_FIELD;

- ret = sbc_check_prot(dev, cmd, cdb, sectors, true); + ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, true); if (ret) return ret;

@@ -980,7 +979,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) size = sbc_get_size(cmd, 1); cmd->t_task_lba = get_unaligned_be64(&cdb[12]);

- ret = sbc_setup_write_same(cmd, &cdb[10], ops); + ret = sbc_setup_write_same(cmd, cdb[10], ops); if (ret) return ret; break; @@ -1079,7 +1078,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) size = sbc_get_size(cmd, 1); cmd->t_task_lba = get_unaligned_be64(&cdb[2]);

- ret = sbc_setup_write_same(cmd, &cdb[1], ops); + ret = sbc_setup_write_same(cmd, cdb[1], ops); if (ret) return ret; break; @@ -1097,7 +1096,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) * Follow sbcr26 with WRITE_SAME (10) and check for the existence * of byte 1 bit 3 UNMAP instead of original reserved field */ - ret = sbc_setup_write_same(cmd, &cdb[1], ops); + ret = sbc_setup_write_same(cmd, cdb[1], ops); if (ret) return ret; break;

From: Robert Richter rrichter@amd.com

[ Upstream commit d2cbbf1fe503c07e466c62f83aa1926d74d15821 ]

During a rework of initramfs code the INITRAMFS_COMPRESSION config option was removed in commit 65e00e04e5ae. A leftover as a dependency broke the config option ACPI_TABLE_OVERRIDE_VIA_ BUILTIN_INITRD that is used to enable the overriding of ACPI tables from built-in initrd. Fixing the dependency.

Fixes: 65e00e04e5ae ("initramfs: refactor the initramfs build rules") Signed-off-by: Robert Richter rrichter@amd.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index eedec61e3476..226f849fe7dc 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -370,7 +370,7 @@ config ACPI_TABLE_UPGRADE config ACPI_TABLE_OVERRIDE_VIA_BUILTIN_INITRD bool "Override ACPI tables from built-in initrd" depends on ACPI_TABLE_UPGRADE - depends on INITRAMFS_SOURCE!="" && INITRAMFS_COMPRESSION="" + depends on INITRAMFS_SOURCE!="" && INITRAMFS_COMPRESSION_NONE help This option provides functionality to override arbitrary ACPI tables from built-in uncompressed initrd.

From: Andy Shevchenko andy.shevchenko@gmail.com

[ Upstream commit 71f6428332844f38c7cb10461d9f29e9c9b983a0 ]

Currently it's possible to iterate over the dangling pointer in case the device suddenly disappears. This may happen becase callers put it at the end of a loop.

Instead, let's move that call inside acpi_dev_get_next_match_dev().

Fixes: 803abec64ef9 ("media: ipu3-cio2: Add cio2-bridge to ipu3-cio2 driver") Fixes: bf263f64e804 ("media: ACPI / bus: Add acpi_dev_get_next_match_dev() and helper macro") Fixes: edbd1bc4951e ("efi/dev-path-parser: Switch to use for_each_acpi_dev_match()") Signed-off-by: Andy Shevchenko andy.shevchenko@gmail.com Reviewed-by: Daniel Scally djrscally@gmail.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/utils.c | 7 +++---- drivers/firmware/efi/dev-path-parser.c | 1 - drivers/media/pci/intel/ipu3/cio2-bridge.c | 6 ++---- include/acpi/acpi_bus.h | 5 ----- 4 files changed, 5 insertions(+), 14 deletions(-)

diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index 3b54b8fd7396..27ec9d57f3b8 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -846,11 +846,9 @@ EXPORT_SYMBOL(acpi_dev_present); * Return the next match of ACPI device if another matching device was present * at the moment of invocation, or NULL otherwise. * - * FIXME: The function does not tolerate the sudden disappearance of @adev, e.g. - * in the case of a hotplug event. That said, the caller should ensure that - * this will never happen. - * * The caller is responsible for invoking acpi_dev_put() on the returned device. + * On the other hand the function invokes acpi_dev_put() on the given @adev + * assuming that its reference counter had been increased beforehand. * * See additional information in acpi_dev_present() as well. */ @@ -866,6 +864,7 @@ acpi_dev_get_next_match_dev(struct acpi_device *adev, const char *hid, const cha match.hrv = hrv;

dev = bus_find_device(&acpi_bus_type, start, &match, acpi_dev_match_cb); + acpi_dev_put(adev); return dev ? to_acpi_device(dev) : NULL; } EXPORT_SYMBOL(acpi_dev_get_next_match_dev); diff --git a/drivers/firmware/efi/dev-path-parser.c b/drivers/firmware/efi/dev-path-parser.c index 10d4457417a4..eb9c65f97841 100644 --- a/drivers/firmware/efi/dev-path-parser.c +++ b/drivers/firmware/efi/dev-path-parser.c @@ -34,7 +34,6 @@ static long __init parse_acpi_path(const struct efi_dev_path *node, break; if (!adev->pnp.unique_id && node->acpi.uid == 0) break; - acpi_dev_put(adev); } if (!adev) return -ENODEV; diff --git a/drivers/media/pci/intel/ipu3/cio2-bridge.c b/drivers/media/pci/intel/ipu3/cio2-bridge.c index 4657e99df033..59a36f922675 100644 --- a/drivers/media/pci/intel/ipu3/cio2-bridge.c +++ b/drivers/media/pci/intel/ipu3/cio2-bridge.c @@ -173,10 +173,8 @@ static int cio2_bridge_connect_sensor(const struct cio2_sensor_config *cfg, int ret;

for_each_acpi_dev_match(adev, cfg->hid, NULL, -1) { - if (!adev->status.enabled) { - acpi_dev_put(adev); + if (!adev->status.enabled) continue; - }

if (bridge->n_sensors >= CIO2_NUM_PORTS) { acpi_dev_put(adev); @@ -185,7 +183,6 @@ static int cio2_bridge_connect_sensor(const struct cio2_sensor_config *cfg, }

sensor = &bridge->sensors[bridge->n_sensors]; - sensor->adev = adev; strscpy(sensor->name, cfg->hid, sizeof(sensor->name));

ret = cio2_bridge_read_acpi_buffer(adev, "SSDB", @@ -215,6 +212,7 @@ static int cio2_bridge_connect_sensor(const struct cio2_sensor_config *cfg, goto err_free_swnodes; }

+ sensor->adev = acpi_dev_get(adev); adev->fwnode.secondary = fwnode;

dev_info(&cio2->dev, "Found supported sensor %s\n", diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 3a82faac5767..bff6a11bb21f 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -698,11 +698,6 @@ acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv); * @hrv: Hardware Revision of the device, pass -1 to not check _HRV * * The caller is responsible for invoking acpi_dev_put() on the returned device. - * - * FIXME: Due to above requirement there is a window that may invalidate @adev - * and next iteration will use a dangling pointer, e.g. in the case of a - * hotplug event. That said, the caller should ensure that this will never - * happen. */ #define for_each_acpi_dev_match(adev, hid, uid, hrv) \ for (adev = acpi_dev_get_first_match_dev(hid, uid, hrv); \

From: Michael Chan michael.chan@broadcom.com

[ Upstream commit 2c9f046bc377efd1f5e26e74817d5f96e9506c86 ]

The capabilities can change after firmware upgrade/downgrade, so we should get the up-to-date RoCE capabilities everytime bnxt_ulp_probe() is called.

Fixes: 2151fe0830fd ("bnxt_en: Handle RESET_NOTIFY async event from firmware.") Reviewed-by: Somnath Kotur somnath.kotur@broadcom.com Reviewed-by: Edwin Peer edwin.peer@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index a918e374f3c5..187ff643ad2a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -479,16 +479,17 @@ struct bnxt_en_dev *bnxt_ulp_probe(struct net_device *dev) if (!edev) return ERR_PTR(-ENOMEM); edev->en_ops = &bnxt_en_ops_tbl; - if (bp->flags & BNXT_FLAG_ROCEV1_CAP) - edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP; - if (bp->flags & BNXT_FLAG_ROCEV2_CAP) - edev->flags |= BNXT_EN_FLAG_ROCEV2_CAP; edev->net = dev; edev->pdev = bp->pdev; edev->l2_db_size = bp->db_size; edev->l2_db_size_nc = bp->db_size; bp->edev = edev; } + edev->flags &= ~BNXT_EN_FLAG_ROCE_CAP; + if (bp->flags & BNXT_FLAG_ROCEV1_CAP) + edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP; + if (bp->flags & BNXT_FLAG_ROCEV2_CAP) + edev->flags |= BNXT_EN_FLAG_ROCEV2_CAP; return bp->edev; } EXPORT_SYMBOL(bnxt_ulp_probe);

From: Somnath Kotur somnath.kotur@broadcom.com

[ Upstream commit 3958b1da725a477b4a222183d16a14d85445d4b6 ]

When bnxt_open() fails in the firmware reset path, the driver needs to gracefully abort, but it is executing code that should be invoked only in the success path. Define a function to abort FW reset and consolidate all error paths to call this new function.

Fixes: dab62e7c2de7 ("bnxt_en: Implement faster recovery for firmware fatal error.") Signed-off-by: Somnath Kotur somnath.kotur@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 31 +++++++++++++++-------- 1 file changed, 21 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 07efab5bad95..49aca3289c00 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11849,10 +11849,21 @@ static bool bnxt_fw_reset_timeout(struct bnxt *bp) (bp->fw_reset_max_dsecs * HZ / 10)); }

+static void bnxt_fw_reset_abort(struct bnxt *bp, int rc) +{ + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); + if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF) { + bnxt_ulp_start(bp, rc); + bnxt_dl_health_status_update(bp, false); + } + bp->fw_reset_state = 0; + dev_close(bp->dev); +} + static void bnxt_fw_reset_task(struct work_struct *work) { struct bnxt *bp = container_of(work, struct bnxt, fw_reset_task.work); - int rc; + int rc = 0;

if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { netdev_err(bp->dev, "bnxt_fw_reset_task() called when not in fw reset mode!\n"); @@ -11883,8 +11894,9 @@ static void bnxt_fw_reset_task(struct work_struct *work) bp->fw_reset_timestamp = jiffies; rtnl_lock(); if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) { + bnxt_fw_reset_abort(bp, rc); rtnl_unlock(); - goto fw_reset_abort; + return; } bnxt_fw_reset_close(bp); if (bp->fw_cap & BNXT_FW_CAP_ERR_RECOVER_RELOAD) { @@ -11933,6 +11945,7 @@ static void bnxt_fw_reset_task(struct work_struct *work) if (val == 0xffff) { if (bnxt_fw_reset_timeout(bp)) { netdev_err(bp->dev, "Firmware reset aborted, PCI config space invalid\n"); + rc = -ETIMEDOUT; goto fw_reset_abort; } bnxt_queue_fw_reset_work(bp, HZ / 1000); @@ -11942,6 +11955,7 @@ static void bnxt_fw_reset_task(struct work_struct *work) clear_bit(BNXT_STATE_FW_FATAL_COND, &bp->state); if (pci_enable_device(bp->pdev)) { netdev_err(bp->dev, "Cannot re-enable PCI device\n"); + rc = -ENODEV; goto fw_reset_abort; } pci_set_master(bp->pdev); @@ -11968,9 +11982,10 @@ static void bnxt_fw_reset_task(struct work_struct *work) } rc = bnxt_open(bp->dev); if (rc) { - netdev_err(bp->dev, "bnxt_open_nic() failed\n"); - clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); - dev_close(bp->dev); + netdev_err(bp->dev, "bnxt_open() failed during FW reset\n"); + bnxt_fw_reset_abort(bp, rc); + rtnl_unlock(); + return; }

bp->fw_reset_state = 0; @@ -11997,12 +12012,8 @@ fw_reset_abort_status: netdev_err(bp->dev, "fw_health_status 0x%x\n", sts); } fw_reset_abort: - clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); - if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF) - bnxt_dl_health_status_update(bp, false); - bp->fw_reset_state = 0; rtnl_lock(); - dev_close(bp->dev); + bnxt_fw_reset_abort(bp, rc); rtnl_unlock(); }

From: Somnath Kotur somnath.kotur@broadcom.com

[ Upstream commit 11a39259ff79b74bc99f8b7c44075a2d6d5e7ab1 ]

bnxt_half_open_nic() is called during during ethtool self test and is protected by rtnl_lock. Firmware reset can be happening at the same time. Only critical portions of the entire firmware reset sequence are protected by the rtnl_lock. It is possible that bnxt_half_open_nic() can be called when the firmware reset sequence is aborting. In that case, bnxt_half_open_nic() needs to check if the ABORT_ERR flag is set and abort if it is. The ethtool self test will fail but the NIC will be brought to a consistent IF_DOWN state.

Without this patch, if bnxt_half_open_nic() were to continue in this error state, it may crash like this:

bnxt_en 0000:82:00.1 enp130s0f1np1: FW reset in progress during close, FW reset will be aborted Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 ... Process ethtool (pid: 333327, stack limit = 0x0000000046476577) Call trace: bnxt_alloc_mem+0x444/0xef0 [bnxt_en] bnxt_half_open_nic+0x24/0xb8 [bnxt_en] bnxt_self_test+0x2dc/0x390 [bnxt_en] ethtool_self_test+0xe0/0x1f8 dev_ethtool+0x1744/0x22d0 dev_ioctl+0x190/0x3e0 sock_ioctl+0x238/0x480 do_vfs_ioctl+0xc4/0x758 ksys_ioctl+0x84/0xb8 __arm64_sys_ioctl+0x28/0x38 el0_svc_handler+0xb0/0x180 el0_svc+0x8/0xc

Fixes: a1301f08c5ac ("bnxt_en: Check abort error state in bnxt_open_nic().") Signed-off-by: Somnath Kotur somnath.kotur@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index be36dee65f90..3c3aa9467310 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -10104,6 +10104,12 @@ int bnxt_half_open_nic(struct bnxt *bp) { int rc = 0;

+ if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) { + netdev_err(bp->dev, "A previous firmware reset has not completed, aborting half open\n"); + rc = -ENODEV; + goto half_open_err; + } + rc = bnxt_alloc_mem(bp, false); if (rc) { netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);

From: Eric Dumazet edumazet@google.com

[ Upstream commit 6f20c8adb1813467ea52c1296d52c4e95978cb2f ]

tfo_active_disable_stamp is read and written locklessly. We need to annotate these accesses appropriately.

Then, we need to perform the atomic_inc(tfo_active_disable_times) after the timestamp has been updated, and thus add barriers to make sure tcp_fastopen_active_should_disable() wont read a stale timestamp.

Fixes: cf1ef3f0719b ("net/tcp_fastopen: Disable active side TFO in certain scenarios") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Wei Wang weiwan@google.com Cc: Yuchung Cheng ycheng@google.com Cc: Neal Cardwell ncardwell@google.com Acked-by: Wei Wang weiwan@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_fastopen.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index af2814c9342a..08548ff23d83 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -507,8 +507,15 @@ void tcp_fastopen_active_disable(struct sock *sk) { struct net *net = sock_net(sk);

+ /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */ + WRITE_ONCE(net->ipv4.tfo_active_disable_stamp, jiffies); + + /* Paired with smp_rmb() in tcp_fastopen_active_should_disable(). + * We want net->ipv4.tfo_active_disable_stamp to be updated first. + */ + smp_mb__before_atomic(); atomic_inc(&net->ipv4.tfo_active_disable_times); - net->ipv4.tfo_active_disable_stamp = jiffies; + NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE); }

@@ -526,10 +533,16 @@ bool tcp_fastopen_active_should_disable(struct sock *sk) if (!tfo_da_times) return false;

+ /* Paired with smp_mb__before_atomic() in tcp_fastopen_active_disable() */ + smp_rmb(); + /* Limit timout to max: 2^6 * initial timeout */ multiplier = 1 << min(tfo_da_times - 1, 6); - timeout = multiplier * tfo_bh_timeout * HZ; - if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout)) + + /* Paired with the WRITE_ONCE() in tcp_fastopen_active_disable(). */ + timeout = READ_ONCE(sock_net(sk)->ipv4.tfo_active_disable_stamp) + + multiplier * tfo_bh_timeout * HZ; + if (time_before(jiffies, timeout)) return true;

/* Mark check bit so we can check for successful active TFO

From: Chengwen Feng fengchengwen@huawei.com

[ Upstream commit 1b713d14dc3c077ec45e65dab4ea01a8bc41b8c1 ]

Currently, the mailbox synchronous communication between VF and PF use the following fields to maintain communication: 1. Origin_mbx_msg which was combined by message code and subcode, used to match request and response. 2. Received_resp which means whether received response.

There may possible mismatches of the following situation: 1. VF sends message A with code=1 subcode=1. 2. PF was blocked about 500ms when processing the message A. 3. VF will detect message A timeout because it can't get the response within 500ms. 4. VF sends message B with code=1 subcode=1 which equal message A. 5. PF processes the first message A and send the response message to VF. 6. VF will identify the response matched the message B because the code/subcode is the same. This will lead to mismatch of request and response.

To fix the above bug, we use the following scheme: 1. The message sent from VF was labelled with match_id which was a unique 16-bit non-zero value. 2. The response sent from PF will label with match_id which got from the request. 3. The VF uses the match_id to match request and response message.

As for PF driver, it only needs to copy the match_id from request to response.

Fixes: dde1a86e93ca ("net: hns3: Add mailbox support to PF driver") Signed-off-by: Chengwen Feng fengchengwen@huawei.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h | 6 ++++-- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 1 + 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index a2c17af57fde..d283beec9f66 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -135,7 +135,8 @@ struct hclge_mbx_vf_to_pf_cmd { u8 mbx_need_resp; u8 rsv1[1]; u8 msg_len; - u8 rsv2[3]; + u8 rsv2; + u16 match_id; struct hclge_vf_to_pf_msg msg; };

@@ -145,7 +146,8 @@ struct hclge_mbx_pf_to_vf_cmd { u8 dest_vfid; u8 rsv[3]; u8 msg_len; - u8 rsv1[3]; + u8 rsv1; + u16 match_id; struct hclge_pf_to_vf_msg msg; };

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index f1c9f4ada348..38b601031db4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -47,6 +47,7 @@ static int hclge_gen_resp_to_vf(struct hclge_vport *vport,

resp_pf_to_vf->dest_vfid = vf_to_pf_req->mbx_src_vfid; resp_pf_to_vf->msg_len = vf_to_pf_req->msg_len; + resp_pf_to_vf->match_id = vf_to_pf_req->match_id;

resp_pf_to_vf->msg.code = HCLGE_MBX_PF_VF_RESP; resp_pf_to_vf->msg.vf_mbx_msg_code = vf_to_pf_req->msg.code;

From: Alexandru Tachici alexandru.tachici@analog.com

[ Upstream commit c45c1e82bba130db4f19d9dbc1deefcf4ea994ed ]

The bcm2835_spi_transfer_one function can create a deadlock if it is called while another thread already has the CCF lock.

Signed-off-by: Alexandru Tachici alexandru.tachici@analog.com Fixes: f8043872e796 ("spi: add driver for BCM2835") Reviewed-by: Florian Fainelli f.fainelli@gmail.com Link: https://lore.kernel.org/r/20210716210245.13240-2-alexandru.tachici@analog.co... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-bcm2835.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index fe40626e45aa..61cbcc7e2121 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -84,6 +84,7 @@ MODULE_PARM_DESC(polling_limit_us, * struct bcm2835_spi - BCM2835 SPI controller * @regs: base address of register map * @clk: core clock, divided to calculate serial clock + * @clk_hz: core clock cached speed * @irq: interrupt, signals TX FIFO empty or RX FIFO ¾ full * @tfr: SPI transfer currently processed * @ctlr: SPI controller reverse lookup @@ -124,6 +125,7 @@ MODULE_PARM_DESC(polling_limit_us, struct bcm2835_spi { void __iomem *regs; struct clk *clk; + unsigned long clk_hz; int irq; struct spi_transfer *tfr; struct spi_controller *ctlr; @@ -1082,19 +1084,18 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr, struct spi_transfer *tfr) { struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr); - unsigned long spi_hz, clk_hz, cdiv; + unsigned long spi_hz, cdiv; unsigned long hz_per_byte, byte_limit; u32 cs = bs->prepare_cs[spi->chip_select];

/* set clock */ spi_hz = tfr->speed_hz; - clk_hz = clk_get_rate(bs->clk);

- if (spi_hz >= clk_hz / 2) { + if (spi_hz >= bs->clk_hz / 2) { cdiv = 2; /* clk_hz/2 is the fastest we can go */ } else if (spi_hz) { /* CDIV must be a multiple of two */ - cdiv = DIV_ROUND_UP(clk_hz, spi_hz); + cdiv = DIV_ROUND_UP(bs->clk_hz, spi_hz); cdiv += (cdiv % 2);

if (cdiv >= 65536) @@ -1102,7 +1103,7 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr, } else { cdiv = 0; /* 0 is the slowest we can go */ } - tfr->effective_speed_hz = cdiv ? (clk_hz / cdiv) : (clk_hz / 65536); + tfr->effective_speed_hz = cdiv ? (bs->clk_hz / cdiv) : (bs->clk_hz / 65536); bcm2835_wr(bs, BCM2835_SPI_CLK, cdiv);

/* handle all the 3-wire mode */ @@ -1320,6 +1321,7 @@ static int bcm2835_spi_probe(struct platform_device *pdev) return bs->irq ? bs->irq : -ENODEV;

clk_prepare_enable(bs->clk); + bs->clk_hz = clk_get_rate(bs->clk);

err = bcm2835_dma_init(ctlr, &pdev->dev, bs); if (err)

From: Peilin Ye peilin.ye@bytedance.com

[ Upstream commit 727d6a8b7ef3d25080fad228b2c4a1d4da5999c6 ]

Currently tcf_skbmod_act() assumes that packets use Ethernet as their L2 protocol, which is not always the case. As an example, for CAN devices:

$ ip link add dev vcan0 type vcan $ ip link set up vcan0 $ tc qdisc add dev vcan0 root handle 1: htb $ tc filter add dev vcan0 parent 1: protocol ip prio 10 \ matchall action skbmod swap mac

Doing the above silently corrupts all the packets. Do not perform skbmod actions for non-Ethernet packets.

Fixes: 86da71b57383 ("net_sched: Introduce skbmod action") Reviewed-by: Cong Wang cong.wang@bytedance.com Signed-off-by: Peilin Ye peilin.ye@bytedance.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/act_skbmod.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 81a1c67335be..8d17a543cc9f 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -6,6 +6,7 @@ */

#include <linux/module.h> +#include <linux/if_arp.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> @@ -33,6 +34,13 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&d->tcf_tm); bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb);

+ action = READ_ONCE(d->tcf_action); + if (unlikely(action == TC_ACT_SHOT)) + goto drop; + + if (!skb->dev || skb->dev->type != ARPHRD_ETHER) + return action; + /* XXX: if you are going to edit more fields beyond ethernet header * (example when you add IP header replacement or vlan swap) * then MAX_EDIT_LEN needs to change appropriately @@ -41,10 +49,6 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, if (unlikely(err)) /* best policy is to drop on the floor */ goto drop;

- action = READ_ONCE(d->tcf_action); - if (unlikely(action == TC_ACT_SHOT)) - goto drop; - p = rcu_dereference_bh(d->skbmod_p); flags = p->flags; if (flags & SKBMOD_F_DMAC)

From: Luis Henriques lhenriques@suse.de

[ Upstream commit cdb330f4b41ab55feb35487729e883c9e08b8a54 ]

If MDSs aren't available while mounting a filesystem, the session state will transition from SESSION_OPENING to SESSION_CLOSING. And in that scenario check_session_state() will be called from delayed_work() and trigger this WARN.

Avoid this by only WARNing after a session has already been established (i.e., the s_ttl will be different from 0).

Fixes: 62575e270f66 ("ceph: check session state after bumping session->s_seq") Signed-off-by: Luis Henriques lhenriques@suse.de Reviewed-by: Jeff Layton jlayton@kernel.org Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ceph/mds_client.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index e5af591d3bd4..86f09b1110a2 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4468,7 +4468,7 @@ bool check_session_state(struct ceph_mds_session *s) break; case CEPH_MDS_SESSION_CLOSING: /* Should never reach this when we're unmounting */ - WARN_ON_ONCE(true); + WARN_ON_ONCE(s->s_ttl); fallthrough; case CEPH_MDS_SESSION_NEW: case CEPH_MDS_SESSION_RESTARTING:

From: David Disseldorp ddiss@suse.de

[ Upstream commit a47fa41381a09e5997afd762664db4f5f6657e03 ]

CPU affinity control added with commit 39ae3edda325 ("scsi: target: core: Make completion affinity configurable") makes target_complete_cmd() queue work on a CPU based on se_tpg->se_tpg_wwn->cmd_compl_affinity state.

LIO's EXTENDED COPY worker is a special case in that read/write cmds are dispatched using the global xcopy_pt_tpg, which carries a NULL se_tpg_wwn pointer following initialization in target_xcopy_setup_pt().

The NULL xcopy_pt_tpg->se_tpg_wwn pointer is dereferenced on completion of any EXTENDED COPY initiated read/write cmds. E.g using the libiscsi SCSI.ExtendedCopy.Simple test:

BUG: kernel NULL pointer dereference, address: 00000000000001a8 RIP: 0010:target_complete_cmd+0x9d/0x130 [target_core_mod] Call Trace: fd_execute_rw+0x148/0x42a [target_core_file] ? __dynamic_pr_debug+0xa7/0xe0 ? target_check_reservation+0x5b/0x940 [target_core_mod] __target_execute_cmd+0x1e/0x90 [target_core_mod] transport_generic_new_cmd+0x17c/0x330 [target_core_mod] target_xcopy_issue_pt_cmd+0x9/0x60 [target_core_mod] target_xcopy_read_source.isra.7+0x10b/0x1b0 [target_core_mod] ? target_check_fua+0x40/0x40 [target_core_mod] ? transport_complete_task_attr+0x130/0x130 [target_core_mod] target_xcopy_do_work+0x61f/0xc00 [target_core_mod]

This fix makes target_complete_cmd() queue work on se_cmd->cpuid if se_tpg_wwn is NULL.

Link: https://lore.kernel.org/r/20210720225522.26291-1-ddiss@suse.de Fixes: 39ae3edda325 ("scsi: target: core: Make completion affinity configurable") Cc: Lee Duncan lduncan@suse.com Cc: Mike Christie michael.christie@oracle.com Reviewed-by: Mike Christie michael.christie@oracle.com Signed-off-by: David Disseldorp ddiss@suse.de Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/target/target_core_transport.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 7e35eddd9eb7..26ceabe34de5 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -886,7 +886,7 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) INIT_WORK(&cmd->work, success ? target_complete_ok_work : target_complete_failure_work);

- if (wwn->cmd_compl_affinity == SE_COMPL_AFFINITY_CPUID) + if (!wwn || wwn->cmd_compl_affinity == SE_COMPL_AFFINITY_CPUID) cpu = cmd->cpuid; else cpu = wwn->cmd_compl_affinity;

From: Zhihao Cheng chengzhihao1@huawei.com

[ Upstream commit 7764656b108cd308c39e9a8554353b8f9ca232a3 ]

Followling process: nvme_probe nvme_reset_ctrl nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING) queue_work(nvme_reset_wq, &ctrl->reset_work)

--------------> nvme_remove nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING) worker_thread process_one_work nvme_reset_work WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)

, which will trigger WARN_ON in nvme_reset_work(): [ 127.534298] WARNING: CPU: 0 PID: 139 at drivers/nvme/host/pci.c:2594 [ 127.536161] CPU: 0 PID: 139 Comm: kworker/u8:7 Not tainted 5.13.0 [ 127.552518] Call Trace: [ 127.552840] ? kvm_sched_clock_read+0x25/0x40 [ 127.553936] ? native_send_call_func_single_ipi+0x1c/0x30 [ 127.555117] ? send_call_function_single_ipi+0x9b/0x130 [ 127.556263] ? __smp_call_single_queue+0x48/0x60 [ 127.557278] ? ttwu_queue_wakelist+0xfa/0x1c0 [ 127.558231] ? try_to_wake_up+0x265/0x9d0 [ 127.559120] ? ext4_end_io_rsv_work+0x160/0x290 [ 127.560118] process_one_work+0x28c/0x640 [ 127.561002] worker_thread+0x39a/0x700 [ 127.561833] ? rescuer_thread+0x580/0x580 [ 127.562714] kthread+0x18c/0x1e0 [ 127.563444] ? set_kthread_struct+0x70/0x70 [ 127.564347] ret_from_fork+0x1f/0x30

The preceding problem can be easily reproduced by executing following script (based on blktests suite): test() { pdev="$(_get_pci_dev_from_blkdev)" sysfs="/sys/bus/pci/devices/${pdev}" for ((i = 0; i < 10; i++)); do echo 1 > "$sysfs/remove" echo 1 > /sys/bus/pci/rescan done }

Since the device ctrl could be updated as an non-RESETTING state by repeating probe/remove in userspace (which is a normal situation), we can replace stack dumping WARN_ON with a warnning message.

Fixes: 82b057caefaff ("nvme-pci: fix multiple ctrl removal schedulin") Signed-off-by: Zhihao Cheng chengzhihao1@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/pci.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index c625da463330..fb1c5ae0da39 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2591,7 +2591,9 @@ static void nvme_reset_work(struct work_struct *work) bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL); int result;

- if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) { + if (dev->ctrl.state != NVME_CTRL_RESETTING) { + dev_warn(dev->ctrl.device, "ctrl state %d is not RESETTING\n", + dev->ctrl.state); result = -ENODEV; goto out; }

From: David Howells dhowells@redhat.com

[ Upstream commit 6c881ca0b3040f3e724eae513117ba4ddef86057 ]

To quote Alexey[1]:

I was adding custom tracepoint to the kernel, grabbed full F34 kernel .config, disabled modules and booted whole shebang as VM kernel.

Then did

perf record -a -e ...

It crashed:

general protection fault, probably for non-canonical address 0x435f5346592e4243: 0000 [#1] SMP PTI CPU: 1 PID: 842 Comm: cat Not tainted 5.12.6+ #26 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1.fc33 04/01/2014 RIP: 0010:t_show+0x22/0xd0

Then reproducer was narrowed to

# cat /sys/kernel/tracing/printk_formats

Original F34 kernel with modules didn't crash.

So I started to disable options and after disabling AFS everything started working again.

The root cause is that AFS was placing char arrays content into a section full of _pointers_ to strings with predictable consequences.

Non canonical address 435f5346592e4243 is "CB.YFS_" which came from CM_NAME macro.

Steps to reproduce:

CONFIG_AFS=y CONFIG_TRACING=y

# cat /sys/kernel/tracing/printk_formats

Fix this by the following means:

(1) Add enum->string translation tables in the event header with the AFS and YFS cache/callback manager operations listed by RPC operation ID.

(2) Modify the afs_cb_call tracepoint to print the string from the translation table rather than using the string at the afs_call name pointer.

(3) Switch translation table depending on the service we're being accessed as (AFS or YFS) in the tracepoint print clause. Will this cause problems to userspace utilities?

Note that the symbolic representation of the YFS service ID isn't available to this header, so I've put it in as a number. I'm not sure if this is the best way to do this.

(4) Remove the name wrangling (CM_NAME) macro and put the names directly into the afs_call_type structs in cmservice.c.

Fixes: 8e8d7f13b6d5a9 ("afs: Add some tracepoints") Reported-by: Alexey Dobriyan (SK hynix) adobriyan@gmail.com Signed-off-by: David Howells dhowells@redhat.com Reviewed-by: Steven Rostedt (VMware) rostedt@goodmis.org Reviewed-by: Marc Dionne marc.dionne@auristor.com cc: Andrew Morton akpm@linux-foundation.org cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/YLAXfvZ+rObEOdc%2F@localhost.localdomain/ [1] Link: https://lore.kernel.org/r/643721.1623754699@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162430903582.2896199.6098150063997983353.stgit@war... # v1 Link: https://lore.kernel.org/r/162609463957.3133237.15916579353149746363.stgit@wa... # v1 (repost) Link: https://lore.kernel.org/r/162610726860.3408253.445207609466288531.stgit@wart... # v2 Signed-off-by: Sasha Levin sashal@kernel.org --- fs/afs/cmservice.c | 25 ++++---------- include/trace/events/afs.h | 67 +++++++++++++++++++++++++++++++++++--- 2 files changed, 69 insertions(+), 23 deletions(-)

diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index d3c6bb22c5f4..a3f5de28be79 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -29,16 +29,11 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *);

static int afs_deliver_yfs_cb_callback(struct afs_call *);

-#define CM_NAME(name) \ - char afs_SRXCB##name##_name[] __tracepoint_string = \ - "CB." #name - /* * CB.CallBack operation type */ -static CM_NAME(CallBack); static const struct afs_call_type afs_SRXCBCallBack = { - .name = afs_SRXCBCallBack_name, + .name = "CB.CallBack", .deliver = afs_deliver_cb_callback, .destructor = afs_cm_destructor, .work = SRXAFSCB_CallBack, @@ -47,9 +42,8 @@ static const struct afs_call_type afs_SRXCBCallBack = { /* * CB.InitCallBackState operation type */ -static CM_NAME(InitCallBackState); static const struct afs_call_type afs_SRXCBInitCallBackState = { - .name = afs_SRXCBInitCallBackState_name, + .name = "CB.InitCallBackState", .deliver = afs_deliver_cb_init_call_back_state, .destructor = afs_cm_destructor, .work = SRXAFSCB_InitCallBackState, @@ -58,9 +52,8 @@ static const struct afs_call_type afs_SRXCBInitCallBackState = { /* * CB.InitCallBackState3 operation type */ -static CM_NAME(InitCallBackState3); static const struct afs_call_type afs_SRXCBInitCallBackState3 = { - .name = afs_SRXCBInitCallBackState3_name, + .name = "CB.InitCallBackState3", .deliver = afs_deliver_cb_init_call_back_state3, .destructor = afs_cm_destructor, .work = SRXAFSCB_InitCallBackState, @@ -69,9 +62,8 @@ static const struct afs_call_type afs_SRXCBInitCallBackState3 = { /* * CB.Probe operation type */ -static CM_NAME(Probe); static const struct afs_call_type afs_SRXCBProbe = { - .name = afs_SRXCBProbe_name, + .name = "CB.Probe", .deliver = afs_deliver_cb_probe, .destructor = afs_cm_destructor, .work = SRXAFSCB_Probe, @@ -80,9 +72,8 @@ static const struct afs_call_type afs_SRXCBProbe = { /* * CB.ProbeUuid operation type */ -static CM_NAME(ProbeUuid); static const struct afs_call_type afs_SRXCBProbeUuid = { - .name = afs_SRXCBProbeUuid_name, + .name = "CB.ProbeUuid", .deliver = afs_deliver_cb_probe_uuid, .destructor = afs_cm_destructor, .work = SRXAFSCB_ProbeUuid, @@ -91,9 +82,8 @@ static const struct afs_call_type afs_SRXCBProbeUuid = { /* * CB.TellMeAboutYourself operation type */ -static CM_NAME(TellMeAboutYourself); static const struct afs_call_type afs_SRXCBTellMeAboutYourself = { - .name = afs_SRXCBTellMeAboutYourself_name, + .name = "CB.TellMeAboutYourself", .deliver = afs_deliver_cb_tell_me_about_yourself, .destructor = afs_cm_destructor, .work = SRXAFSCB_TellMeAboutYourself, @@ -102,9 +92,8 @@ static const struct afs_call_type afs_SRXCBTellMeAboutYourself = { /* * YFS CB.CallBack operation type */ -static CM_NAME(YFS_CallBack); static const struct afs_call_type afs_SRXYFSCB_CallBack = { - .name = afs_SRXCBYFS_CallBack_name, + .name = "YFSCB.CallBack", .deliver = afs_deliver_yfs_cb_callback, .destructor = afs_cm_destructor, .work = SRXAFSCB_CallBack, diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 3ccf591b2374..9f73ed2cf061 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -174,6 +174,34 @@ enum afs_vl_operation { afs_VL_GetCapabilities = 65537, /* AFS Get VL server capabilities */ };

+enum afs_cm_operation { + afs_CB_CallBack = 204, /* AFS break callback promises */ + afs_CB_InitCallBackState = 205, /* AFS initialise callback state */ + afs_CB_Probe = 206, /* AFS probe client */ + afs_CB_GetLock = 207, /* AFS get contents of CM lock table */ + afs_CB_GetCE = 208, /* AFS get cache file description */ + afs_CB_GetXStatsVersion = 209, /* AFS get version of extended statistics */ + afs_CB_GetXStats = 210, /* AFS get contents of extended statistics data */ + afs_CB_InitCallBackState3 = 213, /* AFS initialise callback state, version 3 */ + afs_CB_ProbeUuid = 214, /* AFS check the client hasn't rebooted */ +}; + +enum yfs_cm_operation { + yfs_CB_Probe = 206, /* YFS probe client */ + yfs_CB_GetLock = 207, /* YFS get contents of CM lock table */ + yfs_CB_XStatsVersion = 209, /* YFS get version of extended statistics */ + yfs_CB_GetXStats = 210, /* YFS get contents of extended statistics data */ + yfs_CB_InitCallBackState3 = 213, /* YFS initialise callback state, version 3 */ + yfs_CB_ProbeUuid = 214, /* YFS check the client hasn't rebooted */ + yfs_CB_GetServerPrefs = 215, + yfs_CB_GetCellServDV = 216, + yfs_CB_GetLocalCell = 217, + yfs_CB_GetCacheConfig = 218, + yfs_CB_GetCellByNum = 65537, + yfs_CB_TellMeAboutYourself = 65538, /* get client capabilities */ + yfs_CB_CallBack = 64204, +}; + enum afs_edit_dir_op { afs_edit_dir_create, afs_edit_dir_create_error, @@ -436,6 +464,32 @@ enum afs_cb_break_reason { EM(afs_YFSVL_GetCellName, "YFSVL.GetCellName") \ E_(afs_VL_GetCapabilities, "VL.GetCapabilities")

+#define afs_cm_operations \ + EM(afs_CB_CallBack, "CB.CallBack") \ + EM(afs_CB_InitCallBackState, "CB.InitCallBackState") \ + EM(afs_CB_Probe, "CB.Probe") \ + EM(afs_CB_GetLock, "CB.GetLock") \ + EM(afs_CB_GetCE, "CB.GetCE") \ + EM(afs_CB_GetXStatsVersion, "CB.GetXStatsVersion") \ + EM(afs_CB_GetXStats, "CB.GetXStats") \ + EM(afs_CB_InitCallBackState3, "CB.InitCallBackState3") \ + E_(afs_CB_ProbeUuid, "CB.ProbeUuid") + +#define yfs_cm_operations \ + EM(yfs_CB_Probe, "YFSCB.Probe") \ + EM(yfs_CB_GetLock, "YFSCB.GetLock") \ + EM(yfs_CB_XStatsVersion, "YFSCB.XStatsVersion") \ + EM(yfs_CB_GetXStats, "YFSCB.GetXStats") \ + EM(yfs_CB_InitCallBackState3, "YFSCB.InitCallBackState3") \ + EM(yfs_CB_ProbeUuid, "YFSCB.ProbeUuid") \ + EM(yfs_CB_GetServerPrefs, "YFSCB.GetServerPrefs") \ + EM(yfs_CB_GetCellServDV, "YFSCB.GetCellServDV") \ + EM(yfs_CB_GetLocalCell, "YFSCB.GetLocalCell") \ + EM(yfs_CB_GetCacheConfig, "YFSCB.GetCacheConfig") \ + EM(yfs_CB_GetCellByNum, "YFSCB.GetCellByNum") \ + EM(yfs_CB_TellMeAboutYourself, "YFSCB.TellMeAboutYourself") \ + E_(yfs_CB_CallBack, "YFSCB.CallBack") + #define afs_edit_dir_ops \ EM(afs_edit_dir_create, "create") \ EM(afs_edit_dir_create_error, "c_fail") \ @@ -569,6 +623,8 @@ afs_server_traces; afs_cell_traces; afs_fs_operations; afs_vl_operations; +afs_cm_operations; +yfs_cm_operations; afs_edit_dir_ops; afs_edit_dir_reasons; afs_eproto_causes; @@ -649,20 +705,21 @@ TRACE_EVENT(afs_cb_call,

TP_STRUCT__entry( __field(unsigned int, call ) - __field(const char *, name ) __field(u32, op ) + __field(u16, service_id ) ),

TP_fast_assign( __entry->call = call->debug_id; - __entry->name = call->type->name; __entry->op = call->operation_ID; + __entry->service_id = call->service_id; ),

- TP_printk("c=%08x %s o=%u", + TP_printk("c=%08x %s", __entry->call, - __entry->name, - __entry->op) + __entry->service_id == 2501 ? + __print_symbolic(__entry->op, yfs_cm_operations) : + __print_symbolic(__entry->op, afs_cm_operations)) );

TRACE_EVENT(afs_call,

From: David Howells dhowells@redhat.com

[ Upstream commit 5a972474cf685bf99ca430979657095bda3a15c8 ]

Fix afs_writepages() to always set mapping->writeback_index to a page index and not a byte position[1].

Fixes: 31143d5d515e ("AFS: implement basic file write support") Reported-by: Marc Dionne marc.dionne@auristor.com Signed-off-by: David Howells dhowells@redhat.com Reviewed-by: Marc Dionne marc.dionne@auristor.com cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/CAB9dFdvHsLsw7CMnB+4cgciWDSqVjuij4mH3TaXnHQB8sz5rH... [1] Link: https://lore.kernel.org/r/162610728339.3408253.4604750166391496546.stgit@war... # v2 (no v1) Signed-off-by: Sasha Levin sashal@kernel.org --- fs/afs/write.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/afs/write.c b/fs/afs/write.c index 1ed62e0ccfe5..c0534697268e 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -784,7 +784,7 @@ int afs_writepages(struct address_space *mapping, } else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) { ret = afs_writepages_region(mapping, wbc, 0, LLONG_MAX, &next); if (wbc->nr_to_write > 0 && ret == 0) - mapping->writeback_index = next; + mapping->writeback_index = next / PAGE_SIZE; } else { ret = afs_writepages_region(mapping, wbc, wbc->range_start, wbc->range_end, &next);

From: Christoph Hellwig hch@lst.de

[ Upstream commit aaeb7bb061be545251606f4d9c82d710ca2a7c8e ]

When using Write Zeroes on a namespace that has protection information enabled they behavior without the PRACT bit counter-intuitive and will generally lead to validation failures when reading the written blocks. Fix this by always setting the PRACT bit that generates matching PI data on the fly.

Fixes: 6e02318eaea5 ("nvme: add support for the Write Zeroes command") Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Keith Busch kbusch@kernel.org Reviewed-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 66973bb56305..148e756857a8 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -880,7 +880,10 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns, cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req))); cmnd->write_zeroes.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); - cmnd->write_zeroes.control = 0; + if (nvme_ns_has_pi(ns)) + cmnd->write_zeroes.control = cpu_to_le16(NVME_RW_PRINFO_PRACT); + else + cmnd->write_zeroes.control = 0; return BLK_STS_OK; }

From: Vadim Fedorenko vfedorenko@novek.ru

[ Upstream commit 9bfce73c8921c92a9565562e6e7d458d37b7ce80 ]

Commit d26796ae5894 ("udp: check udp sock encap_type in __udp_lib_err") added checks for encapsulated sockets but it broke cases when there is no implementation of encap_err_lookup for encapsulation, i.e. ESP in UDP encapsulation. Fix it by calling encap_err_lookup only if socket implements this method otherwise treat it as legal socket.

Fixes: d26796ae5894 ("udp: check udp sock encap_type in __udp_lib_err") Signed-off-by: Vadim Fedorenko vfedorenko@novek.ru Reviewed-by: Xin Long lucien.xin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/udp.c | 25 +++++++++++++++++++------ net/ipv6/udp.c | 25 +++++++++++++++++++------ 2 files changed, 38 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ca9cf1051b1e..568dc31a0467 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -645,10 +645,12 @@ static struct sock *__udp4_lib_err_encap(struct net *net, const struct iphdr *iph, struct udphdr *uh, struct udp_table *udptable, + struct sock *sk, struct sk_buff *skb, u32 info) { + int (*lookup)(struct sock *sk, struct sk_buff *skb); int network_offset, transport_offset; - struct sock *sk; + struct udp_sock *up;

network_offset = skb_network_offset(skb); transport_offset = skb_transport_offset(skb); @@ -659,18 +661,28 @@ static struct sock *__udp4_lib_err_encap(struct net *net, /* Transport header needs to point to the UDP header */ skb_set_transport_header(skb, iph->ihl << 2);

+ if (sk) { + up = udp_sk(sk); + + lookup = READ_ONCE(up->encap_err_lookup); + if (lookup && lookup(sk, skb)) + sk = NULL; + + goto out; + } + sk = __udp4_lib_lookup(net, iph->daddr, uh->source, iph->saddr, uh->dest, skb->dev->ifindex, 0, udptable, NULL); if (sk) { - int (*lookup)(struct sock *sk, struct sk_buff *skb); - struct udp_sock *up = udp_sk(sk); + up = udp_sk(sk);

lookup = READ_ONCE(up->encap_err_lookup); if (!lookup || lookup(sk, skb)) sk = NULL; }

+out: if (!sk) sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info));

@@ -707,15 +719,16 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, inet_sdif(skb), udptable, NULL); + if (!sk || udp_sk(sk)->encap_type) { /* No socket for error: try tunnels before discarding */ - sk = ERR_PTR(-ENOENT); if (static_branch_unlikely(&udp_encap_needed_key)) { - sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb, + sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb, info); if (!sk) return 0; - } + } else + sk = ERR_PTR(-ENOENT);

if (IS_ERR(sk)) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 6774e776228c..2d3bd4a9b0d0 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -502,12 +502,14 @@ static struct sock *__udp6_lib_err_encap(struct net *net, const struct ipv6hdr *hdr, int offset, struct udphdr *uh, struct udp_table *udptable, + struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, __be32 info) { + int (*lookup)(struct sock *sk, struct sk_buff *skb); int network_offset, transport_offset; - struct sock *sk; + struct udp_sock *up;

network_offset = skb_network_offset(skb); transport_offset = skb_transport_offset(skb); @@ -518,18 +520,28 @@ static struct sock *__udp6_lib_err_encap(struct net *net, /* Transport header needs to point to the UDP header */ skb_set_transport_header(skb, offset);

+ if (sk) { + up = udp_sk(sk); + + lookup = READ_ONCE(up->encap_err_lookup); + if (lookup && lookup(sk, skb)) + sk = NULL; + + goto out; + } + sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source, &hdr->saddr, uh->dest, inet6_iif(skb), 0, udptable, skb); if (sk) { - int (*lookup)(struct sock *sk, struct sk_buff *skb); - struct udp_sock *up = udp_sk(sk); + up = udp_sk(sk);

lookup = READ_ONCE(up->encap_err_lookup); if (!lookup || lookup(sk, skb)) sk = NULL; }

+out: if (!sk) { sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code, offset, info)); @@ -558,16 +570,17 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,

sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, inet6_iif(skb), inet6_sdif(skb), udptable, NULL); + if (!sk || udp_sk(sk)->encap_type) { /* No socket for error: try tunnels before discarding */ - sk = ERR_PTR(-ENOENT); if (static_branch_unlikely(&udpv6_encap_needed_key)) { sk = __udp6_lib_err_encap(net, hdr, offset, uh, - udptable, skb, + udptable, sk, skb, opt, type, code, info); if (!sk) return 0; - } + } else + sk = ERR_PTR(-ENOENT);

if (IS_ERR(sk)) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),

From: Bin Meng bmeng.cn@gmail.com

[ Upstream commit d0e4dae74470fb709fc0ab61862c317938f4cc4d ]

Commit dd2d082b5760 ("riscv: Cleanup setup_bootmem()") adjusted the calling sequence in setup_bootmem(), which invalidates the fix commit de043da0b9e7 ("RISC-V: Fix usage of memblock_enforce_memory_limit") did for 32-bit RISC-V unfortunately.

So now 32-bit RISC-V does not boot again when testing booting kernel on QEMU 'virt' with '-m 2G', which was exactly what the original commit de043da0b9e7 ("RISC-V: Fix usage of memblock_enforce_memory_limit") tried to fix.

Fixes: dd2d082b5760 ("riscv: Cleanup setup_bootmem()") Signed-off-by: Bin Meng bmeng.cn@gmail.com Signed-off-by: Palmer Dabbelt palmerdabbelt@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/riscv/mm/init.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 4c4c92ce0bb8..9b23b95c50cf 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -123,7 +123,7 @@ void __init setup_bootmem(void) { phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); - phys_addr_t dram_end = memblock_end_of_DRAM(); + phys_addr_t dram_end; phys_addr_t max_mapped_addr = __pa(~(ulong)0);

#ifdef CONFIG_XIP_KERNEL @@ -146,6 +146,8 @@ void __init setup_bootmem(void) #endif memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);

+ dram_end = memblock_end_of_DRAM(); + /* * memblock allocator is not aware of the fact that last 4K bytes of * the addressable memory can not be mapped because of IS_ERR_VALUE

From: Vladimir Oltean vladimir.oltean@nxp.com

[ Upstream commit e40cba9490bab1414d45c2d62defc0ad4f6e4136 ]

This simple series of commands:

ip link add br0 type bridge vlan_filtering 1 ip link set swp0 master br0

fails on sja1105 with the following error: [ 33.439103] sja1105 spi0.1: vlan-lookup-table needs to have at least the default untagged VLAN [ 33.447710] sja1105 spi0.1: Invalid config, cannot upload Warning: sja1105: Failed to change VLAN Ethertype.

For context, sja1105 has 3 operating modes: - SJA1105_VLAN_UNAWARE: the dsa_8021q_vlans are committed to hardware - SJA1105_VLAN_FILTERING_FULL: the bridge_vlans are committed to hardware - SJA1105_VLAN_FILTERING_BEST_EFFORT: both the dsa_8021q_vlans and the bridge_vlans are committed to hardware

Swapping out a VLAN list and another in happens in sja1105_build_vlan_table(), which performs a delta update procedure. That function is called from a few places, notably from sja1105_vlan_filtering() which is called from the SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING handler.

The above set of 2 commands fails when run on a kernel pre-commit 8841f6e63f2c ("net: dsa: sja1105: make devlink property best_effort_vlan_filtering true by default"). So the priv->vlan_state transition that takes place is between VLAN-unaware and full VLAN filtering. So the dsa_8021q_vlans are swapped out and the bridge_vlans are swapped in.

So why does it fail?

Well, the bridge driver, through nbp_vlan_init(), first sets up the SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING attribute, and only then proceeds to call nbp_vlan_add for the default_pvid.

So when we swap out the dsa_8021q_vlans and swap in the bridge_vlans in the SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING handler, there are no bridge VLANs (yet). So we have wiped the VLAN table clean, and the low-level static config checker complains of an invalid configuration. We _will_ add the bridge VLANs using the dynamic config interface, albeit later, when nbp_vlan_add() calls us. So it is natural that it fails.

So why did it ever work?

Surprisingly, it looks like I only tested this configuration with 2 things set up in a particular way: - a network manager that brings all ports up - a kernel with CONFIG_VLAN_8021Q=y

It is widely known that commit ad1afb003939 ("vlan_dev: VLAN 0 should be treated as "no vlan tag" (802.1p packet)") installs VID 0 to every net device that comes up. DSA treats these VLANs as bridge VLANs, and therefore, in my testing, the list of bridge_vlans was never empty.

However, if CONFIG_VLAN_8021Q is not enabled, or the port is not up when it joins a VLAN-aware bridge, the bridge_vlans list will be temporarily empty, and the sja1105_static_config_reload() call from sja1105_vlan_filtering() will fail.

To fix this, the simplest thing is to keep VID 4095, the one used for CPU-injected control packets since commit ed040abca4c1 ("net: dsa: sja1105: use 4095 as the private VLAN for untagged traffic"), in the list of bridge VLANs too, not just the list of tag_8021q VLANs. This ensures that the list of bridge VLANs will never be empty.

Fixes: ec5ae61076d0 ("net: dsa: sja1105: save/restore VLANs using a delta commit method") Reported-by: Radu Pirea (NXP OSS) radu-nicolae.pirea@oss.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/dsa/sja1105/sja1105_main.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index ebe4d33cda27..6e5dbe9f3892 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -378,6 +378,12 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv) if (dsa_is_cpu_port(ds, port)) v->pvid = true; list_add(&v->list, &priv->dsa_8021q_vlans); + + v = kmemdup(v, sizeof(*v), GFP_KERNEL); + if (!v) + return -ENOMEM; + + list_add(&v->list, &priv->bridge_vlans); }

((struct sja1105_vlan_lookup_entry *)table->entries)[0] = pvid;

From: Yajun Deng yajun.deng@linux.dev

[ Upstream commit 9d85a6f44bd5585761947f40f7821c9cd78a1bbe ]

The 4th parameter in tc_chain_notify() should be flags rather than seq. Let's change it back correctly.

Fixes: 32a4f5ecd738 ("net: sched: introduce chain object to uapi") Signed-off-by: Yajun Deng yajun.deng@linux.dev Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/cls_api.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index d73b5c5514a9..e3e79e9bd706 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2904,7 +2904,7 @@ replay: break; case RTM_GETCHAIN: err = tc_chain_notify(chain, skb, n->nlmsg_seq, - n->nlmsg_seq, n->nlmsg_type, true); + n->nlmsg_flags, n->nlmsg_type, true); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send chain notify message"); break;

From: Ioana Ciornei ioana.ciornei@nxp.com

[ Upstream commit 7aaa0f311e2df2704fa8ddb8ed681a3b5841d0bf ]

Any interraction with the buffer pool (seeding a buffer, acquire one) is made through a software portal (SWP, a DPIO object). There are circumstances where the dpaa2-switch driver probes on a DPSW before any DPIO devices have been probed. In this case, seeding of the buffer pool will lead to a panic since no SWPs are initialized.

To fix this, seed the buffer pool after making sure that the software portals have been probed and are ready to be used.

Fixes: 0b1b71370458 ("staging: dpaa2-switch: handle Rx path on control interface") Signed-off-by: Ioana Ciornei ioana.ciornei@nxp.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/freescale/dpaa2/dpaa2-switch.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 05de37c3b64c..87321b7239cf 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -2770,32 +2770,32 @@ static int dpaa2_switch_ctrl_if_setup(struct ethsw_core *ethsw) if (err) return err;

- err = dpaa2_switch_seed_bp(ethsw); - if (err) - goto err_free_dpbp; - err = dpaa2_switch_alloc_rings(ethsw); if (err) - goto err_drain_dpbp; + goto err_free_dpbp;

err = dpaa2_switch_setup_dpio(ethsw); if (err) goto err_destroy_rings;

+ err = dpaa2_switch_seed_bp(ethsw); + if (err) + goto err_deregister_dpio; + err = dpsw_ctrl_if_enable(ethsw->mc_io, 0, ethsw->dpsw_handle); if (err) { dev_err(ethsw->dev, "dpsw_ctrl_if_enable err %d\n", err); - goto err_deregister_dpio; + goto err_drain_dpbp; }

return 0;

+err_drain_dpbp: + dpaa2_switch_drain_bp(ethsw); err_deregister_dpio: dpaa2_switch_free_dpio(ethsw); err_destroy_rings: dpaa2_switch_destroy_rings(ethsw); -err_drain_dpbp: - dpaa2_switch_drain_bp(ethsw); err_free_dpbp: dpaa2_switch_free_dpbp(ethsw);

From: Ronnie Sahlberg lsahlber@redhat.com

[ Upstream commit 488968a8945c119859d91bb6a8dc13bf50002f15 ]

Remove the conditional checking for out_data_len and skipping the fallocate if it is 0. This is wrong will actually change any legitimate the fallocate where the entire region is unallocated into a no-op.

Additionally, before allocating the range, if FALLOC_FL_KEEP_SIZE is set then we need to clamp the length of the fallocate region as to not extend the size of the file.

Fixes: 966a3cb7c7db ("cifs: improve fallocate emulation") Signed-off-by: Ronnie Sahlberg lsahlber@redhat.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cifs/smb2ops.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index cc253bbff696..64cad843ce72 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3663,11 +3663,6 @@ static int smb3_simple_fallocate_range(unsigned int xid, (char **)&out_data, &out_data_len); if (rc) goto out; - /* - * It is already all allocated - */ - if (out_data_len == 0) - goto out;

buf = kzalloc(1024 * 1024, GFP_KERNEL); if (buf == NULL) { @@ -3790,6 +3785,24 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, goto out; }

+ if (keep_size == true) { + /* + * We can not preallocate pages beyond the end of the file + * in SMB2 + */ + if (off >= i_size_read(inode)) { + rc = 0; + goto out; + } + /* + * For fallocates that are partially beyond the end of file, + * clamp len so we only fallocate up to the end of file. + */ + if (off + len > i_size_read(inode)) { + len = i_size_read(inode) - off; + } + } + if ((keep_size == true) || (i_size_read(inode) >= off + len)) { /* * At this point, we are trying to fallocate an internal

From: Linus Torvalds torvalds@linux-foundation.org

commit fc68f42aa737dc15e7665a4101d4168aadb8e4c4 upstream.

Commit 71f642833284 ("ACPI: utils: Fix reference counting in for_each_acpi_dev_match()") started doing "acpi_dev_put()" on a pointer that was possibly NULL. That fails miserably, because that helper inline function is not set up to handle that case.

Just make acpi_dev_put() silently accept a NULL pointer, rather than calling down to put_device() with an invalid offset off that NULL pointer.

Link: https://lore.kernel.org/lkml/a607c149-6bf6-0fd0-0e31-100378504da2@kernel.dk/ Reported-and-tested-by: Jens Axboe axboe@kernel.dk Tested-by: Daniel Scally djrscally@gmail.com Cc: Andy Shevchenko andy.shevchenko@gmail.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/acpi/acpi_bus.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -711,7 +711,8 @@ static inline struct acpi_device *acpi_d

static inline void acpi_dev_put(struct acpi_device *adev) { - put_device(&adev->dev); + if (adev) + put_device(&adev->dev); } #else /* CONFIG_ACPI */

From: Stephen Boyd swboyd@chromium.org

commit 10252bae863d09b9648bed2e035572d207200ca1 upstream.

There's a chance that the IDA allocated in mmc_alloc_host() is not freed for some time because it's freed as part of a class' release function (see mmc_host_classdev_release() where the IDA is freed). If another thread is holding a reference to the class, then only once all balancing device_put() calls (in turn calling kobject_put()) have been made will the IDA be released and usable again.

Normally this isn't a problem because the kobject is released before anything else that may want to use the same number tries to again, but with CONFIG_DEBUG_KOBJECT_RELEASE=y and OF aliases it becomes pretty easy to try to allocate an alias from the IDA twice while the first time it was allocated is still pending a call to ida_simple_remove(). It's also possible to trigger it by using CONFIG_DEBUG_KOBJECT_RELEASE and probe defering a driver at boot that calls mmc_alloc_host() before trying to get resources that may defer likes clks or regulators.

Instead of allocating from the IDA in this scenario, let's just skip it if we know this is an OF alias. The number is already "claimed" and devices that aren't using OF aliases won't try to use the claimed numbers anyway (see mmc_first_nonreserved_index()). This should avoid any issues with mmc_alloc_host() returning failures from the ida_simple_get() in the case that we're using an OF alias.

Cc: Matthias Schiffer matthias.schiffer@ew.tq-group.com Cc: Sujit Kautkar sujitka@chromium.org Reported-by: Zubin Mithra zsm@chromium.org Fixes: fa2d0aa96941 ("mmc: core: Allow setting slot index via device tree alias") Signed-off-by: Stephen Boyd swboyd@chromium.org Link: https://lore.kernel.org/r/20210623075002.1746924-3-swboyd@chromium.org Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mmc/core/host.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-)

--- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -75,7 +75,8 @@ static void mmc_host_classdev_release(st { struct mmc_host *host = cls_dev_to_mmc_host(dev); wakeup_source_unregister(host->ws); - ida_simple_remove(&mmc_host_ida, host->index); + if (of_alias_get_id(host->parent->of_node, "mmc") < 0) + ida_simple_remove(&mmc_host_ida, host->index); kfree(host); }

@@ -499,7 +500,7 @@ static int mmc_first_nonreserved_index(v */ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) { - int err; + int index; struct mmc_host *host; int alias_id, min_idx, max_idx;

@@ -512,20 +513,19 @@ struct mmc_host *mmc_alloc_host(int extr

alias_id = of_alias_get_id(dev->of_node, "mmc"); if (alias_id >= 0) { - min_idx = alias_id; - max_idx = alias_id + 1; + index = alias_id; } else { min_idx = mmc_first_nonreserved_index(); max_idx = 0; - }

- err = ida_simple_get(&mmc_host_ida, min_idx, max_idx, GFP_KERNEL); - if (err < 0) { - kfree(host); - return NULL; + index = ida_simple_get(&mmc_host_ida, min_idx, max_idx, GFP_KERNEL); + if (index < 0) { + kfree(host); + return NULL; + } }

- host->index = err; + host->index = index;

dev_set_name(&host->class_dev, "mmc%d", host->index); host->ws = wakeup_source_register(NULL, dev_name(&host->class_dev));

From: Alexander Egorenkov egorenar@linux.ibm.com

commit 463f36c76fa4ec015c640ff63ccf52e7527abee0 upstream.

The DMA code section of the decompressor must be compiled with expolines if Spectre V2 mitigation has been enabled for the decompressed kernel. This is required because although the decompressor's image contains the DMA code section, it is handed over to the decompressed kernel for use.

Because the DMA code is already slow w/o expolines, use expolines always regardless whether the decompressed kernel is using them or not. This simplifies the DMA code by dropping the conditional compilation of expolines.

Fixes: bf72630130c2 ("s390: use proper expoline sections for .dma code") Cc: stable@vger.kernel.org # 5.2 Signed-off-by: Alexander Egorenkov egorenar@linux.ibm.com Reviewed-by: Heiko Carstens hca@linux.ibm.com Signed-off-by: Heiko Carstens hca@linux.ibm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/s390/boot/text_dma.S | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-)

--- a/arch/s390/boot/text_dma.S +++ b/arch/s390/boot/text_dma.S @@ -9,16 +9,6 @@ #include <asm/errno.h> #include <asm/sigp.h>

-#ifdef CC_USING_EXPOLINE - .pushsection .dma.text.__s390_indirect_jump_r14,"axG" -__dma__s390_indirect_jump_r14: - larl %r1,0f - ex 0,0(%r1) - j . -0: br %r14 - .popsection -#endif - .section .dma.text,"ax" /* * Simplified version of expoline thunk. The normal thunks can not be used here, @@ -27,11 +17,10 @@ __dma__s390_indirect_jump_r14: * affects a few functions that are not performance-relevant. */ .macro BR_EX_DMA_r14 -#ifdef CC_USING_EXPOLINE - jg __dma__s390_indirect_jump_r14 -#else - br %r14 -#endif + larl %r1,0f + ex 0,0(%r1) + j . +0: br %r14 .endm

/*

From: Alexander Tsoy alexander@tsoy.me

commit b0084afde27fe8a504377dee65f55bc6aa776937 upstream.

These devices has two interfaces, but only the second interface contains the capture endpoint, thus quirk is required to delay the registration until the second interface appears.

Tested-by: Jakub Fišer jakub@ufiseru.cz Signed-off-by: Alexander Tsoy alexander@tsoy.me Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210721235605.53741-1-alexander@tsoy.me Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/usb/quirks.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1897,6 +1897,9 @@ static const struct registration_quirk r REG_QUIRK_ENTRY(0x0951, 0x16d8, 2), /* Kingston HyperX AMP */ REG_QUIRK_ENTRY(0x0951, 0x16ed, 2), /* Kingston HyperX Cloud Alpha S */ REG_QUIRK_ENTRY(0x0951, 0x16ea, 2), /* Kingston HyperX Cloud Flight S */ + REG_QUIRK_ENTRY(0x0ecb, 0x1f46, 2), /* JBL Quantum 600 */ + REG_QUIRK_ENTRY(0x0ecb, 0x2039, 2), /* JBL Quantum 400 */ + REG_QUIRK_ENTRY(0x0ecb, 0x203e, 2), /* JBL Quantum 800 */ { 0 } /* terminator */ };

From: Hui Wang hui.wang@canonical.com

commit e4efa82660e6d80338c554e45e903714e1b2c27b upstream.

This is a Lenovo ThinkStation machine which uses the codec alc623. There are 2 issues on this machine, the 1st one is the pop noise in the lineout, the 2nd one is there are 2 Front Mics and pulseaudio can't handle them, After applying the fixup of ALC623_FIXUP_LENOVO_THINKSTATION_P340 to this machine, the 2 issues are fixed.

Cc: stable@vger.kernel.org Signed-off-by: Hui Wang hui.wang@canonical.com Link: https://lore.kernel.org/r/20210719030231.6870-1-hui.wang@canonical.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8566,6 +8566,7 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0x17aa, 0x3151, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3176, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x17aa, 0x31af, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340), SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940", ALC298_FIXUP_LENOVO_SPK_VOLUME), SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF), SND_PCI_QUIRK(0x17aa, 0x3843, "Yoga 9i", ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP),

From: Alan Young consult.awy@gmail.com

commit 2e2832562c877e6530b8480982d99a4ff90c6777 upstream.

If a 32-bit application is being used with a 64-bit kernel and is using the mmap mechanism to write data, then the SNDRV_PCM_IOCTL_SYNC_PTR ioctl results in calling snd_pcm_ioctl_sync_ptr_compat(). Make this use pcm_lib_apply_appl_ptr() so that the substream's ack() method, if defined, is called.

The snd_pcm_sync_ptr() function, used in the 64-bit ioctl case, already uses snd_pcm_ioctl_sync_ptr_compat().

Fixes: 9027c4639ef1 ("ALSA: pcm: Call ack() whenever appl_ptr is updated") Signed-off-by: Alan Young consult.awy@gmail.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/c441f18c-eb2a-3bdd-299a-696ccca2de9c@gmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/core/pcm_native.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)

--- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -3057,9 +3057,14 @@ static int snd_pcm_ioctl_sync_ptr_compat boundary = 0x7fffffff; snd_pcm_stream_lock_irq(substream); /* FIXME: we should consider the boundary for the sync from app */ - if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL)) - control->appl_ptr = scontrol.appl_ptr; - else + if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL)) { + err = pcm_lib_apply_appl_ptr(substream, + scontrol.appl_ptr); + if (err < 0) { + snd_pcm_stream_unlock_irq(substream); + return err; + } + } else scontrol.appl_ptr = control->appl_ptr % boundary; if (!(sflags & SNDRV_PCM_SYNC_PTR_AVAIL_MIN)) control->avail_min = scontrol.avail_min;

From: Moritz Fischer mdf@kernel.org

commit 44cf53602f5a0db80d53c8fff6cdbcae59650a42 upstream.

This reverts commit d143825baf15f204dac60acdf95e428182aa3374.

Justin reports some of his systems now fail as result of this commit:

xhci_hcd 0000:04:00.0: Direct firmware load for renesas_usb_fw.mem failed with error -2 xhci_hcd 0000:04:00.0: request_firmware failed: -2 xhci_hcd: probe of 0000:04:00.0 failed with error -2

The revert brings back the original issue the commit tried to solve but at least unbreaks existing systems relying on previous behavior.

Cc: stable@vger.kernel.org Cc: Mathias Nyman mathias.nyman@intel.com Cc: Vinod Koul vkoul@kernel.org Cc: Justin Forbes jmforbes@linuxtx.org Reported-by: Justin Forbes jmforbes@linuxtx.org Signed-off-by: Moritz Fischer mdf@kernel.org Fixes: d143825baf15 ("usb: renesas-xhci: Fix handling of unknown ROM state") Link: https://lore.kernel.org/r/20210719070519.41114-1-mdf@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/host/xhci-pci-renesas.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

--- a/drivers/usb/host/xhci-pci-renesas.c +++ b/drivers/usb/host/xhci-pci-renesas.c @@ -207,8 +207,7 @@ static int renesas_check_rom_state(struc return 0;

case RENESAS_ROM_STATUS_NO_RESULT: /* No result yet */ - dev_dbg(&pdev->dev, "Unknown ROM status ...\n"); - break; + return 0;

case RENESAS_ROM_STATUS_ERROR: /* Error State */ default: /* All other states are marked as "Reserved states" */ @@ -225,12 +224,13 @@ static int renesas_fw_check_running(stru u8 fw_state; int err;

- /* - * Only if device has ROM and loaded FW we can skip loading and - * return success. Otherwise (even unknown state), attempt to load FW. - */ - if (renesas_check_rom(pdev) && !renesas_check_rom_state(pdev)) - return 0; + /* Check if device has ROM and loaded, if so skip everything */ + err = renesas_check_rom(pdev); + if (err) { /* we have rom */ + err = renesas_check_rom_state(pdev); + if (!err) + return err; + }

/* * Test if the device is actually needing the firmware. As most

From: Mathias Nyman mathias.nyman@linux.intel.com

commit 72f68bf5c756f5ce1139b31daae2684501383ad5 upstream.

There's a small window where a USB 2 remote wake may be left unhandled due to a race between hub thread and xhci port event interrupt handler.

When the resume event is detected in the xhci interrupt handler it kicks the hub timer, which should move the port from resume to U0 once resume has been signalled for long enough.

To keep the hub "thread" running we set a bus_state->resuming_ports flag. This flag makes sure hub timer function kicks itself.

checking this flag was not properly protected by the spinlock. Flag was copied to a local variable before lock was taken. The local variable was then checked later with spinlock held.

If interrupt is handled right after copying the flag to the local variable we end up stopping the hub thread before it can handle the USB 2 resume.

CPU0 CPU1 (hub thread) (xhci event handler)

xhci_hub_status_data() status = bus_state->resuming_ports; <Interrupt> handle_port_status() spin_lock() bus_state->resuming_ports = 1 set_flag(HCD_FLAG_POLL_RH) spin_unlock() spin_lock() if (!status) clear_flag(HCD_FLAG_POLL_RH) spin_unlock()

Fix this by taking the lock a bit earlier so that it covers the resuming_ports flag copy in the hub thread

Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Link: https://lore.kernel.org/r/20210715150651.1996099-2-mathias.nyman@linux.intel... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/host/xhci-hub.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -1638,11 +1638,12 @@ int xhci_hub_status_data(struct usb_hcd * Inform the usbcore about resume-in-progress by returning * a non-zero value even if there are no status changes. */ + spin_lock_irqsave(&xhci->lock, flags); + status = bus_state->resuming_ports;

mask = PORT_CSC | PORT_PEC | PORT_OCC | PORT_PLC | PORT_WRC | PORT_CEC;

- spin_lock_irqsave(&xhci->lock, flags); /* For each port, did anything change? If so, set that bit in buf. */ for (i = 0; i < max_ports; i++) { temp = readl(ports[i]->addr);

From: Nicholas Piggin npiggin@gmail.com

commit f62f3c20647ebd5fb6ecb8f0b477b9281c44c10a upstream.

The kvmppc_rtas_hcall() sets the host rtas_args.rets pointer based on the rtas_args.nargs that was provided by the guest. That guest nargs value is not range checked, so the guest can cause the host rets pointer to be pointed outside the args array. The individual rtas function handlers check the nargs and nrets values to ensure they are correct, but if they are not, the handlers store a -3 (0xfffffffd) failure indication in rets[0] which corrupts host memory.

Fix this by testing up front whether the guest supplied nargs and nret would exceed the array size, and fail the hcall directly without storing a failure indication to rets[0].

Also expand on a comment about why we kill the guest and try not to return errors directly if we have a valid rets[0] pointer.

Fixes: 8e591cb72047 ("KVM: PPC: Book3S: Add infrastructure to implement kernel-side RTAS calls") Cc: stable@vger.kernel.org # v3.10+ Reported-by: Alexey Kardashevskiy aik@ozlabs.ru Signed-off-by: Nicholas Piggin npiggin@gmail.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/kvm/book3s_rtas.c | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-)

--- a/arch/powerpc/kvm/book3s_rtas.c +++ b/arch/powerpc/kvm/book3s_rtas.c @@ -242,6 +242,17 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *v * value so we can restore it on the way out. */ orig_rets = args.rets; + if (be32_to_cpu(args.nargs) >= ARRAY_SIZE(args.args)) { + /* + * Don't overflow our args array: ensure there is room for + * at least rets[0] (even if the call specifies 0 nret). + * + * Each handler must then check for the correct nargs and nret + * values, but they may always return failure in rets[0]. + */ + rc = -EINVAL; + goto fail; + } args.rets = &args.args[be32_to_cpu(args.nargs)];

mutex_lock(&vcpu->kvm->arch.rtas_token_lock); @@ -269,9 +280,17 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *v fail: /* * We only get here if the guest has called RTAS with a bogus - * args pointer. That means we can't get to the args, and so we - * can't fail the RTAS call. So fail right out to userspace, - * which should kill the guest. + * args pointer or nargs/nret values that would overflow the + * array. That means we can't get to the args, and so we can't + * fail the RTAS call. So fail right out to userspace, which + * should kill the guest. + * + * SLOF should actually pass the hcall return value from the + * rtas handler call in r3, so enter_rtas could be modified to + * return a failure indication in r3 and we could return such + * errors to the guest rather than failing to host userspace. + * However old guests that don't test for failure could then + * continue silently after errors, so for now we won't do this. */ return rc; }

From: Mathias Nyman mathias.nyman@linux.intel.com

commit 1b7f56fbc7a1b66967b6114d1b5f5a257c3abae6 upstream.

The device initiated link power management U1/U2 states should not be enabled in case the system exit latency plus one bus interval (125us) is greater than the shortest service interval of any periodic endpoint.

This is the case for both U1 and U2 sytstem exit latencies and link states.

See USB 3.2 section 9.4.9 "Set Feature" for more details

Note, before this patch the host and device initiated U1/U2 lpm states were both enabled with lpm. After this patch it's possible to end up with only host inititated U1/U2 lpm in case the exit latencies won't allow device initiated lpm.

If this case we still want to set the udev->usb3_lpm_ux_enabled flag so that sysfs users can see the link may go to U1/U2.

Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Cc: stable stable@vger.kernel.org Link: https://lore.kernel.org/r/20210715150122.1995966-2-mathias.nyman@linux.intel... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/core/hub.c | 68 ++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 56 insertions(+), 12 deletions(-)

--- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -4091,6 +4091,47 @@ static int usb_set_lpm_timeout(struct us }

/* + * Don't allow device intiated U1/U2 if the system exit latency + one bus + * interval is greater than the minimum service interval of any active + * periodic endpoint. See USB 3.2 section 9.4.9 + */ +static bool usb_device_may_initiate_lpm(struct usb_device *udev, + enum usb3_link_state state) +{ + unsigned int sel; /* us */ + int i, j; + + if (state == USB3_LPM_U1) + sel = DIV_ROUND_UP(udev->u1_params.sel, 1000); + else if (state == USB3_LPM_U2) + sel = DIV_ROUND_UP(udev->u2_params.sel, 1000); + else + return false; + + for (i = 0; i < udev->actconfig->desc.bNumInterfaces; i++) { + struct usb_interface *intf; + struct usb_endpoint_descriptor *desc; + unsigned int interval; + + intf = udev->actconfig->interface[i]; + if (!intf) + continue; + + for (j = 0; j < intf->cur_altsetting->desc.bNumEndpoints; j++) { + desc = &intf->cur_altsetting->endpoint[j].desc; + + if (usb_endpoint_xfer_int(desc) || + usb_endpoint_xfer_isoc(desc)) { + interval = (1 << (desc->bInterval - 1)) * 125; + if (sel + 125 > interval) + return false; + } + } + } + return true; +} + +/* * Enable the hub-initiated U1/U2 idle timeouts, and enable device-initiated * U1/U2 entry. * @@ -4162,20 +4203,23 @@ static void usb_enable_link_state(struct * U1/U2_ENABLE */ if (udev->actconfig && - usb_set_device_initiated_lpm(udev, state, true) == 0) { - if (state == USB3_LPM_U1) - udev->usb3_lpm_u1_enabled = 1; - else if (state == USB3_LPM_U2) - udev->usb3_lpm_u2_enabled = 1; - } else { - /* Don't request U1/U2 entry if the device - * cannot transition to U1/U2. - */ - usb_set_lpm_timeout(udev, state, 0); - hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state); + usb_device_may_initiate_lpm(udev, state)) { + if (usb_set_device_initiated_lpm(udev, state, true)) { + /* + * Request to enable device initiated U1/U2 failed, + * better to turn off lpm in this case. + */ + usb_set_lpm_timeout(udev, state, 0); + hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state); + return; + } } -}

+ if (state == USB3_LPM_U1) + udev->usb3_lpm_u1_enabled = 1; + else if (state == USB3_LPM_U2) + udev->usb3_lpm_u2_enabled = 1; +} /* * Disable the hub-initiated U1/U2 idle timeouts, and disable device-initiated * U1/U2 entry.