From: Sasha Levin Date: Mon, 3 Aug 2020 01:29:27 +0000 (-0400) Subject: Fixes for 4.4 X-Git-Tag: v5.7.13~17^2 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=bc6dbeee4195630ee48cbe8daa430ed63d72aab1;p=thirdparty%2Fkernel%2Fstable-queue.git Fixes for 4.4 Signed-off-by: Sasha Levin --- diff --git a/queue-4.4/mac80211-mesh-free-ie-data-when-leaving-mesh.patch b/queue-4.4/mac80211-mesh-free-ie-data-when-leaving-mesh.patch new file mode 100644 index 00000000000..a35f412ab73 --- /dev/null +++ b/queue-4.4/mac80211-mesh-free-ie-data-when-leaving-mesh.patch @@ -0,0 +1,61 @@ +From a61284cd84e9c3facb46de809d861eb442875c59 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sat, 4 Jul 2020 15:50:07 +0200 +Subject: mac80211: mesh: Free ie data when leaving mesh + +From: Remi Pommarel + +[ Upstream commit 6a01afcf8468d3ca2bd8bbb27503f60dcf643b20 ] + +At ieee80211_join_mesh() some ie data could have been allocated (see +copy_mesh_setup()) and need to be cleaned up when leaving the mesh. + +This fixes the following kmemleak report: + +unreferenced object 0xffff0000116bc600 (size 128): + comm "wpa_supplicant", pid 608, jiffies 4294898983 (age 293.484s) + hex dump (first 32 bytes): + 30 14 01 00 00 0f ac 04 01 00 00 0f ac 04 01 00 0............... + 00 0f ac 08 00 00 00 00 c4 65 40 00 00 00 00 00 .........e@..... + backtrace: + [<00000000bebe439d>] __kmalloc_track_caller+0x1c0/0x330 + [<00000000a349dbe1>] kmemdup+0x28/0x50 + [<0000000075d69baa>] ieee80211_join_mesh+0x6c/0x3b8 [mac80211] + [<00000000683bb98b>] __cfg80211_join_mesh+0x1e8/0x4f0 [cfg80211] + [<0000000072cb507f>] nl80211_join_mesh+0x520/0x6b8 [cfg80211] + [<0000000077e9bcf9>] genl_family_rcv_msg+0x374/0x680 + [<00000000b1bd936d>] genl_rcv_msg+0x78/0x108 + [<0000000022c53788>] netlink_rcv_skb+0xb0/0x1c0 + [<0000000011af8ec9>] genl_rcv+0x34/0x48 + [<0000000069e41f53>] netlink_unicast+0x268/0x2e8 + [<00000000a7517316>] netlink_sendmsg+0x320/0x4c0 + [<0000000069cba205>] ____sys_sendmsg+0x354/0x3a0 + [<00000000e06bab0f>] ___sys_sendmsg+0xd8/0x120 + [<0000000037340728>] __sys_sendmsg+0xa4/0xf8 + [<000000004fed9776>] __arm64_sys_sendmsg+0x44/0x58 + [<000000001c1e5647>] el0_svc_handler+0xd0/0x1a0 + +Fixes: c80d545da3f7 (mac80211: Let userspace enable and configure vendor specific path selection.) +Signed-off-by: Remi Pommarel +Link: https://lore.kernel.org/r/20200704135007.27292-1-repk@triplefau.lt +Signed-off-by: Johannes Berg +Signed-off-by: Sasha Levin +--- + net/mac80211/cfg.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c +index cf3917c6da0a6..8360fda24bca0 100644 +--- a/net/mac80211/cfg.c ++++ b/net/mac80211/cfg.c +@@ -1766,6 +1766,7 @@ static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev) + ieee80211_stop_mesh(sdata); + mutex_lock(&sdata->local->mtx); + ieee80211_vif_release_channel(sdata); ++ kfree(sdata->u.mesh.ie); + mutex_unlock(&sdata->local->mtx); + + return 0; +-- +2.25.1 + diff --git a/queue-4.4/mlxsw-core-increase-scope-of-rcu-read-side-critical-.patch b/queue-4.4/mlxsw-core-increase-scope-of-rcu-read-side-critical-.patch new file mode 100644 index 00000000000..0a9f343dd1e --- /dev/null +++ b/queue-4.4/mlxsw-core-increase-scope-of-rcu-read-side-critical-.patch @@ -0,0 +1,52 @@ +From ce3218d86de8564c8d095b4e557712b3a36d9197 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 29 Jul 2020 12:26:45 +0300 +Subject: mlxsw: core: Increase scope of RCU read-side critical section + +From: Ido Schimmel + +[ Upstream commit 7d8e8f3433dc8d1dc87c1aabe73a154978fb4c4d ] + +The lifetime of the Rx listener item ('rxl_item') is managed using RCU, +but is dereferenced outside of RCU read-side critical section, which can +lead to a use-after-free. + +Fix this by increasing the scope of the RCU read-side critical section. + +Fixes: 93c1edb27f9e ("mlxsw: Introduce Mellanox switch driver core") +Signed-off-by: Ido Schimmel +Reviewed-by: Jiri Pirko +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/mellanox/mlxsw/core.c | 6 ++++-- + 1 file changed, 4 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c +index 97f0d93caf994..085aaad902937 100644 +--- a/drivers/net/ethernet/mellanox/mlxsw/core.c ++++ b/drivers/net/ethernet/mellanox/mlxsw/core.c +@@ -1208,9 +1208,10 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, + break; + } + } +- rcu_read_unlock(); +- if (!found) ++ if (!found) { ++ rcu_read_unlock(); + goto drop; ++ } + + pcpu_stats = this_cpu_ptr(mlxsw_core->pcpu_stats); + u64_stats_update_begin(&pcpu_stats->syncp); +@@ -1221,6 +1222,7 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, + u64_stats_update_end(&pcpu_stats->syncp); + + rxl->func(skb, local_port, rxl_item->priv); ++ rcu_read_unlock(); + return; + + drop: +-- +2.25.1 + diff --git a/queue-4.4/net-ethernet-ravb-exit-if-re-initialization-fails-in.patch b/queue-4.4/net-ethernet-ravb-exit-if-re-initialization-fails-in.patch new file mode 100644 index 00000000000..9c2fbd04870 --- /dev/null +++ b/queue-4.4/net-ethernet-ravb-exit-if-re-initialization-fails-in.patch @@ -0,0 +1,91 @@ +From 6d15eda306975ff213f5ddf38c195ef94c9616fa Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 21 Jul 2020 15:23:12 +0900 +Subject: net: ethernet: ravb: exit if re-initialization fails in tx timeout + +From: Yoshihiro Shimoda + +[ Upstream commit 015c5d5e6aa3523c758a70eb87b291cece2dbbb4 ] + +According to the report of [1], this driver is possible to cause +the following error in ravb_tx_timeout_work(). + +ravb e6800000.ethernet ethernet: failed to switch device to config mode + +This error means that the hardware could not change the state +from "Operation" to "Configuration" while some tx and/or rx queue +are operating. After that, ravb_config() in ravb_dmac_init() will fail, +and then any descriptors will be not allocaled anymore so that NULL +pointer dereference happens after that on ravb_start_xmit(). + +To fix the issue, the ravb_tx_timeout_work() should check +the return values of ravb_stop_dma() and ravb_dmac_init(). +If ravb_stop_dma() fails, ravb_tx_timeout_work() re-enables TX and RX +and just exits. If ravb_dmac_init() fails, just exits. + +[1] +https://lore.kernel.org/linux-renesas-soc/20200518045452.2390-1-dirk.behme@de.bosch.com/ + +Reported-by: Dirk Behme +Signed-off-by: Yoshihiro Shimoda +Reviewed-by: Sergei Shtylyov +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/renesas/ravb_main.c | 26 ++++++++++++++++++++++-- + 1 file changed, 24 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c +index 5b6320f9c935f..460b29ac5fd86 100644 +--- a/drivers/net/ethernet/renesas/ravb_main.c ++++ b/drivers/net/ethernet/renesas/ravb_main.c +@@ -1291,6 +1291,7 @@ static void ravb_tx_timeout_work(struct work_struct *work) + struct ravb_private *priv = container_of(work, struct ravb_private, + work); + struct net_device *ndev = priv->ndev; ++ int error; + + netif_tx_stop_all_queues(ndev); + +@@ -1298,15 +1299,36 @@ static void ravb_tx_timeout_work(struct work_struct *work) + ravb_ptp_stop(ndev); + + /* Wait for DMA stopping */ +- ravb_stop_dma(ndev); ++ if (ravb_stop_dma(ndev)) { ++ /* If ravb_stop_dma() fails, the hardware is still operating ++ * for TX and/or RX. So, this should not call the following ++ * functions because ravb_dmac_init() is possible to fail too. ++ * Also, this should not retry ravb_stop_dma() again and again ++ * here because it's possible to wait forever. So, this just ++ * re-enables the TX and RX and skip the following ++ * re-initialization procedure. ++ */ ++ ravb_rcv_snd_enable(ndev); ++ goto out; ++ } + + ravb_ring_free(ndev, RAVB_BE); + ravb_ring_free(ndev, RAVB_NC); + + /* Device init */ +- ravb_dmac_init(ndev); ++ error = ravb_dmac_init(ndev); ++ if (error) { ++ /* If ravb_dmac_init() fails, descriptors are freed. So, this ++ * should return here to avoid re-enabling the TX and RX in ++ * ravb_emac_init(). ++ */ ++ netdev_err(ndev, "%s: ravb_dmac_init() failed, error %d\n", ++ __func__, error); ++ return; ++ } + ravb_emac_init(ndev); + ++out: + /* Initialise PTP Clock driver */ + ravb_ptp_init(ndev, priv->pdev); + +-- +2.25.1 + diff --git a/queue-4.4/net-lan78xx-add-missing-endpoint-sanity-check.patch b/queue-4.4/net-lan78xx-add-missing-endpoint-sanity-check.patch new file mode 100644 index 00000000000..c9840c1d24e --- /dev/null +++ b/queue-4.4/net-lan78xx-add-missing-endpoint-sanity-check.patch @@ -0,0 +1,45 @@ +From f868ccb6788839d37af5b8bb26939e0fe7a8ae8c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 28 Jul 2020 14:10:29 +0200 +Subject: net: lan78xx: add missing endpoint sanity check + +From: Johan Hovold + +[ Upstream commit 8d8e95fd6d69d774013f51e5f2ee10c6e6d1fc14 ] + +Add the missing endpoint sanity check to prevent a NULL-pointer +dereference should a malicious device lack the expected endpoints. + +Note that the driver has a broken endpoint-lookup helper, +lan78xx_get_endpoints(), which can end up accepting interfaces in an +altsetting without endpoints as long as *some* altsetting has a bulk-in +and a bulk-out endpoint. + +Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver") +Cc: Woojung.Huh@microchip.com +Signed-off-by: Johan Hovold +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/usb/lan78xx.c | 5 +++++ + 1 file changed, 5 insertions(+) + +diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c +index 75a3865a80d23..3f2f524c338d6 100644 +--- a/drivers/net/usb/lan78xx.c ++++ b/drivers/net/usb/lan78xx.c +@@ -2978,6 +2978,11 @@ static int lan78xx_probe(struct usb_interface *intf, + netdev->mtu = dev->hard_mtu - netdev->hard_header_len; + netif_set_gso_max_size(netdev, MAX_SINGLE_PACKET_SIZE - MAX_HEADER); + ++ if (intf->cur_altsetting->desc.bNumEndpoints < 3) { ++ ret = -ENODEV; ++ goto out3; ++ } ++ + dev->ep_blkin = (intf->cur_altsetting)->endpoint + 0; + dev->ep_blkout = (intf->cur_altsetting)->endpoint + 1; + dev->ep_intr = (intf->cur_altsetting)->endpoint + 2; +-- +2.25.1 + diff --git a/queue-4.4/net-lan78xx-fix-transfer-buffer-memory-leak.patch b/queue-4.4/net-lan78xx-fix-transfer-buffer-memory-leak.patch new file mode 100644 index 00000000000..937fed635f1 --- /dev/null +++ b/queue-4.4/net-lan78xx-fix-transfer-buffer-memory-leak.patch @@ -0,0 +1,36 @@ +From 59ee7037dc43dcd0303421be7ec3765a7094a3fa Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 28 Jul 2020 14:10:30 +0200 +Subject: net: lan78xx: fix transfer-buffer memory leak + +From: Johan Hovold + +[ Upstream commit 63634aa679ba8b5e306ad0727120309ae6ba8a8e ] + +The interrupt URB transfer-buffer was never freed on disconnect or after +probe errors. + +Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver") +Cc: Woojung.Huh@microchip.com +Signed-off-by: Johan Hovold +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/usb/lan78xx.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c +index 3f2f524c338d6..1fb5d5f3475cf 100644 +--- a/drivers/net/usb/lan78xx.c ++++ b/drivers/net/usb/lan78xx.c +@@ -3006,6 +3006,7 @@ static int lan78xx_probe(struct usb_interface *intf, + usb_fill_int_urb(dev->urb_intr, dev->udev, + dev->pipe_intr, buf, maxp, + intr_complete, dev, period); ++ dev->urb_intr->transfer_flags |= URB_FREE_BUFFER; + } + } + +-- +2.25.1 + diff --git a/queue-4.4/nfc-s3fwrn5-add-missing-release-on-skb-in-s3fwrn5_re.patch b/queue-4.4/nfc-s3fwrn5-add-missing-release-on-skb-in-s3fwrn5_re.patch new file mode 100644 index 00000000000..688dd124459 --- /dev/null +++ b/queue-4.4/nfc-s3fwrn5-add-missing-release-on-skb-in-s3fwrn5_re.patch @@ -0,0 +1,34 @@ +From e1deaae747bb76597d2d9ae3359b2f251c2aba48 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sat, 18 Jul 2020 00:31:49 -0500 +Subject: nfc: s3fwrn5: add missing release on skb in s3fwrn5_recv_frame + +From: Navid Emamdoost + +[ Upstream commit 1e8fd3a97f2d83a7197876ceb4f37b4c2b00a0f3 ] + +The implementation of s3fwrn5_recv_frame() is supposed to consume skb on +all execution paths. Release skb before returning -ENODEV. + +Signed-off-by: Navid Emamdoost +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/nfc/s3fwrn5/core.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/drivers/nfc/s3fwrn5/core.c b/drivers/nfc/s3fwrn5/core.c +index 0d866ca295e3f..cafab107ba9bc 100644 +--- a/drivers/nfc/s3fwrn5/core.c ++++ b/drivers/nfc/s3fwrn5/core.c +@@ -209,6 +209,7 @@ int s3fwrn5_recv_frame(struct nci_dev *ndev, struct sk_buff *skb, + case S3FWRN5_MODE_FW: + return s3fwrn5_fw_recv_frame(ndev, skb); + default: ++ kfree_skb(skb); + return -ENODEV; + } + } +-- +2.25.1 + diff --git a/queue-4.4/revert-i2c-cadence-fix-the-hold-bit-setting.patch b/queue-4.4/revert-i2c-cadence-fix-the-hold-bit-setting.patch new file mode 100644 index 00000000000..5587b8545b5 --- /dev/null +++ b/queue-4.4/revert-i2c-cadence-fix-the-hold-bit-setting.patch @@ -0,0 +1,74 @@ +From 7644eacbb977e49ec4824a23d00052292a65669f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 3 Jul 2020 19:25:49 +0530 +Subject: Revert "i2c: cadence: Fix the hold bit setting" + +From: Raviteja Narayanam + +[ Upstream commit 0db9254d6b896b587759e2c844c277fb1a6da5b9 ] + +This reverts commit d358def706880defa4c9e87381c5bf086a97d5f9. + +There are two issues with "i2c: cadence: Fix the hold bit setting" commit. + +1. In case of combined message request from user space, when the HOLD +bit is cleared in cdns_i2c_mrecv function, a STOP condition is sent +on the bus even before the last message is started. This is because when +the HOLD bit is cleared, the FIFOS are empty and there is no pending +transfer. The STOP condition should occur only after the last message +is completed. + +2. The code added by the commit is redundant. Driver is handling the +setting/clearing of HOLD bit in right way before the commit. + +The setting of HOLD bit based on 'bus_hold_flag' is taken care in +cdns_i2c_master_xfer function even before cdns_i2c_msend/cdns_i2c_recv +functions. + +The clearing of HOLD bit is taken care at the end of cdns_i2c_msend and +cdns_i2c_recv functions based on bus_hold_flag and byte count. +Since clearing of HOLD bit is done after the slave address is written to +the register (writing to address register triggers the message transfer), +it is ensured that STOP condition occurs at the right time after +completion of the pending transfer (last message). + +Signed-off-by: Raviteja Narayanam +Acked-by: Michal Simek +Signed-off-by: Wolfram Sang +Signed-off-by: Sasha Levin +--- + drivers/i2c/busses/i2c-cadence.c | 9 ++------- + 1 file changed, 2 insertions(+), 7 deletions(-) + +diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c +index 6d32e6da3110d..84deed6571bdf 100644 +--- a/drivers/i2c/busses/i2c-cadence.c ++++ b/drivers/i2c/busses/i2c-cadence.c +@@ -378,10 +378,8 @@ static void cdns_i2c_mrecv(struct cdns_i2c *id) + * Check for the message size against FIFO depth and set the + * 'hold bus' bit if it is greater than FIFO depth. + */ +- if ((id->recv_count > CDNS_I2C_FIFO_DEPTH) || id->bus_hold_flag) ++ if (id->recv_count > CDNS_I2C_FIFO_DEPTH) + ctrl_reg |= CDNS_I2C_CR_HOLD; +- else +- ctrl_reg = ctrl_reg & ~CDNS_I2C_CR_HOLD; + + cdns_i2c_writereg(ctrl_reg, CDNS_I2C_CR_OFFSET); + +@@ -438,11 +436,8 @@ static void cdns_i2c_msend(struct cdns_i2c *id) + * Check for the message size against FIFO depth and set the + * 'hold bus' bit if it is greater than FIFO depth. + */ +- if ((id->send_count > CDNS_I2C_FIFO_DEPTH) || id->bus_hold_flag) ++ if (id->send_count > CDNS_I2C_FIFO_DEPTH) + ctrl_reg |= CDNS_I2C_CR_HOLD; +- else +- ctrl_reg = ctrl_reg & ~CDNS_I2C_CR_HOLD; +- + cdns_i2c_writereg(ctrl_reg, CDNS_I2C_CR_OFFSET); + + /* Clear the interrupts in interrupt status register. */ +-- +2.25.1 + diff --git a/queue-4.4/series b/queue-4.4/series index 3898fde2b88..0fefb95de4e 100644 --- a/queue-4.4/series +++ b/queue-4.4/series @@ -18,3 +18,12 @@ x86-build-lto-fix-truncated-.bss-with-fdata-sections.patch x86-vmlinux.lds-page-align-end-of-.page_aligned-sect.patch fbdev-detect-integer-underflow-at-struct-fbcon_ops-c.patch rds-prevent-kernel-infoleak-in-rds_notify_queue_get.patch +sh-fix-validation-of-system-call-number.patch +net-lan78xx-add-missing-endpoint-sanity-check.patch +net-lan78xx-fix-transfer-buffer-memory-leak.patch +mlxsw-core-increase-scope-of-rcu-read-side-critical-.patch +mac80211-mesh-free-ie-data-when-leaving-mesh.patch +nfc-s3fwrn5-add-missing-release-on-skb-in-s3fwrn5_re.patch +net-ethernet-ravb-exit-if-re-initialization-fails-in.patch +revert-i2c-cadence-fix-the-hold-bit-setting.patch +xen-netfront-fix-potential-deadlock-in-xennet_remove.patch diff --git a/queue-4.4/sh-fix-validation-of-system-call-number.patch b/queue-4.4/sh-fix-validation-of-system-call-number.patch new file mode 100644 index 00000000000..322d2221bed --- /dev/null +++ b/queue-4.4/sh-fix-validation-of-system-call-number.patch @@ -0,0 +1,57 @@ +From 7b95d7fb61c8397fb1344a3774b324eb5567820f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 23 Jul 2020 01:13:19 +0200 +Subject: sh: Fix validation of system call number + +From: Michael Karcher + +[ Upstream commit 04a8a3d0a73f51c7c2da84f494db7ec1df230e69 ] + +The slow path for traced system call entries accessed a wrong memory +location to get the number of the maximum allowed system call number. +Renumber the numbered "local" label for the correct location to avoid +collisions with actual local labels. + +Signed-off-by: Michael Karcher +Tested-by: John Paul Adrian Glaubitz +Fixes: f3a8308864f920d2 ("sh: Add a few missing irqflags tracing markers.") +Signed-off-by: Rich Felker +Signed-off-by: Sasha Levin +--- + arch/sh/kernel/entry-common.S | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S +index 5a9017ba26aba..3b0aa0ae43b4b 100644 +--- a/arch/sh/kernel/entry-common.S ++++ b/arch/sh/kernel/entry-common.S +@@ -203,7 +203,7 @@ syscall_trace_entry: + mov.l @(OFF_R7,r15), r7 ! arg3 + mov.l @(OFF_R3,r15), r3 ! syscall_nr + ! +- mov.l 2f, r10 ! Number of syscalls ++ mov.l 6f, r10 ! Number of syscalls + cmp/hs r10, r3 + bf syscall_call + mov #-ENOSYS, r0 +@@ -348,7 +348,7 @@ ENTRY(system_call) + tst r9, r8 + bf syscall_trace_entry + ! +- mov.l 2f, r8 ! Number of syscalls ++ mov.l 6f, r8 ! Number of syscalls + cmp/hs r8, r3 + bt syscall_badsys + ! +@@ -387,7 +387,7 @@ syscall_exit: + #if !defined(CONFIG_CPU_SH2) + 1: .long TRA + #endif +-2: .long NR_syscalls ++6: .long NR_syscalls + 3: .long sys_call_table + 7: .long do_syscall_trace_enter + 8: .long do_syscall_trace_leave +-- +2.25.1 + diff --git a/queue-4.4/xen-netfront-fix-potential-deadlock-in-xennet_remove.patch b/queue-4.4/xen-netfront-fix-potential-deadlock-in-xennet_remove.patch new file mode 100644 index 00000000000..4f236deed5e --- /dev/null +++ b/queue-4.4/xen-netfront-fix-potential-deadlock-in-xennet_remove.patch @@ -0,0 +1,134 @@ +From 19acbd10c4b32867fcb4bfe5b99f10e5ce3b8500 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 24 Jul 2020 10:59:10 +0200 +Subject: xen-netfront: fix potential deadlock in xennet_remove() + +From: Andrea Righi + +[ Upstream commit c2c633106453611be07821f53dff9e93a9d1c3f0 ] + +There's a potential race in xennet_remove(); this is what the driver is +doing upon unregistering a network device: + + 1. state = read bus state + 2. if state is not "Closed": + 3. request to set state to "Closing" + 4. wait for state to be set to "Closing" + 5. request to set state to "Closed" + 6. wait for state to be set to "Closed" + +If the state changes to "Closed" immediately after step 1 we are stuck +forever in step 4, because the state will never go back from "Closed" to +"Closing". + +Make sure to check also for state == "Closed" in step 4 to prevent the +deadlock. + +Also add a 5 sec timeout any time we wait for the bus state to change, +to avoid getting stuck forever in wait_event(). + +Signed-off-by: Andrea Righi +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/xen-netfront.c | 64 +++++++++++++++++++++++++------------- + 1 file changed, 42 insertions(+), 22 deletions(-) + +diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c +index 02b6a6c108400..7d4c0c46a889d 100644 +--- a/drivers/net/xen-netfront.c ++++ b/drivers/net/xen-netfront.c +@@ -62,6 +62,8 @@ module_param_named(max_queues, xennet_max_queues, uint, 0644); + MODULE_PARM_DESC(max_queues, + "Maximum number of queues per virtual interface"); + ++#define XENNET_TIMEOUT (5 * HZ) ++ + static const struct ethtool_ops xennet_ethtool_ops; + + struct netfront_cb { +@@ -1349,12 +1351,15 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev) + + netif_carrier_off(netdev); + +- xenbus_switch_state(dev, XenbusStateInitialising); +- wait_event(module_wq, +- xenbus_read_driver_state(dev->otherend) != +- XenbusStateClosed && +- xenbus_read_driver_state(dev->otherend) != +- XenbusStateUnknown); ++ do { ++ xenbus_switch_state(dev, XenbusStateInitialising); ++ err = wait_event_timeout(module_wq, ++ xenbus_read_driver_state(dev->otherend) != ++ XenbusStateClosed && ++ xenbus_read_driver_state(dev->otherend) != ++ XenbusStateUnknown, XENNET_TIMEOUT); ++ } while (!err); ++ + return netdev; + + exit: +@@ -2166,28 +2171,43 @@ static const struct attribute_group xennet_dev_group = { + }; + #endif /* CONFIG_SYSFS */ + +-static int xennet_remove(struct xenbus_device *dev) ++static void xennet_bus_close(struct xenbus_device *dev) + { +- struct netfront_info *info = dev_get_drvdata(&dev->dev); +- +- dev_dbg(&dev->dev, "%s\n", dev->nodename); ++ int ret; + +- if (xenbus_read_driver_state(dev->otherend) != XenbusStateClosed) { ++ if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed) ++ return; ++ do { + xenbus_switch_state(dev, XenbusStateClosing); +- wait_event(module_wq, +- xenbus_read_driver_state(dev->otherend) == +- XenbusStateClosing || +- xenbus_read_driver_state(dev->otherend) == +- XenbusStateUnknown); ++ ret = wait_event_timeout(module_wq, ++ xenbus_read_driver_state(dev->otherend) == ++ XenbusStateClosing || ++ xenbus_read_driver_state(dev->otherend) == ++ XenbusStateClosed || ++ xenbus_read_driver_state(dev->otherend) == ++ XenbusStateUnknown, ++ XENNET_TIMEOUT); ++ } while (!ret); ++ ++ if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed) ++ return; + ++ do { + xenbus_switch_state(dev, XenbusStateClosed); +- wait_event(module_wq, +- xenbus_read_driver_state(dev->otherend) == +- XenbusStateClosed || +- xenbus_read_driver_state(dev->otherend) == +- XenbusStateUnknown); +- } ++ ret = wait_event_timeout(module_wq, ++ xenbus_read_driver_state(dev->otherend) == ++ XenbusStateClosed || ++ xenbus_read_driver_state(dev->otherend) == ++ XenbusStateUnknown, ++ XENNET_TIMEOUT); ++ } while (!ret); ++} ++ ++static int xennet_remove(struct xenbus_device *dev) ++{ ++ struct netfront_info *info = dev_get_drvdata(&dev->dev); + ++ xennet_bus_close(dev); + xennet_disconnect_backend(info); + + if (info->netdev->reg_state == NETREG_REGISTERED) +-- +2.25.1 +