[PATCHES] Networking

[David Miller <davem@davemloft.net>]

[-- Attachment #1: Type: Text/Plain, Size: 102 bytes --]


Please queue up the following networking bug fixes for v5.6 and
v5.7 -stable, respectively.

Thanks!

[-- Attachment #2: net_56.mbox --]
[-- Type: Application/Octet-Stream, Size: 26200 bytes --]

From e38e9d797167b9b817953ce21055ff7c97600250 Mon Sep 17 00:00:00 2001
From: Wang Hai <wanghai38@huawei.com>
Date: Tue, 9 Jun 2020 22:18:16 +0800
Subject: [PATCH 1/9] dccp: Fix possible memleak in dccp_init and dccp_fini

[ Upstream commit c96b6acc8f89a4a7f6258dfe1d077654c11415be ]

There are some memory leaks in dccp_init() and dccp_fini().

In dccp_fini() and the error handling path in dccp_init(), free lhash2
is missing. Add inet_hashinfo2_free_mod() to do it.

If inet_hashinfo2_init_mod() failed in dccp_init(),
percpu_counter_destroy() should be called to destroy dccp_orphan_count.
It need to goto out_free_percpu when inet_hashinfo2_init_mod() failed.

Fixes: c92c81df93df ("net: dccp: fix kernel crash on module load")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wang Hai <wanghai38@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h | 6 ++++++
 net/dccp/proto.c              | 7 +++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index d0019d3395cf..59802eb8d2cc 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -185,6 +185,12 @@ static inline spinlock_t *inet_ehash_lockp(
 
 int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo);
 
+static inline void inet_hashinfo2_free_mod(struct inet_hashinfo *h)
+{
+	kfree(h->lhash2);
+	h->lhash2 = NULL;
+}
+
 static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
 {
 	kvfree(hashinfo->ehash_locks);
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 4af8a98fe784..c13b6609474b 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1139,14 +1139,14 @@ static int __init dccp_init(void)
 	inet_hashinfo_init(&dccp_hashinfo);
 	rc = inet_hashinfo2_init_mod(&dccp_hashinfo);
 	if (rc)
-		goto out_fail;
+		goto out_free_percpu;
 	rc = -ENOBUFS;
 	dccp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("dccp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
 				  SLAB_HWCACHE_ALIGN, NULL);
 	if (!dccp_hashinfo.bind_bucket_cachep)
-		goto out_free_percpu;
+		goto out_free_hashinfo2;
 
 	/*
 	 * Size and allocate the main established and bind bucket
@@ -1242,6 +1242,8 @@ static int __init dccp_init(void)
 	free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order);
 out_free_bind_bucket_cachep:
 	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
+out_free_hashinfo2:
+	inet_hashinfo2_free_mod(&dccp_hashinfo);
 out_free_percpu:
 	percpu_counter_destroy(&dccp_orphan_count);
 out_fail:
@@ -1265,6 +1267,7 @@ static void __exit dccp_fini(void)
 	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
 	dccp_ackvec_exit();
 	dccp_sysctl_exit();
+	inet_hashinfo2_free_mod(&dccp_hashinfo);
 	percpu_counter_destroy(&dccp_orphan_count);
 }
 
-- 
2.26.2


From bba96760433c5ebd5b98e47a9fb497ed9c810804 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 9 Jun 2020 00:02:39 +0200
Subject: [PATCH 2/9] net: mvneta: do not redirect frames during
 reconfiguration

[ Upstream commit 62a502cc91f97e3ffd312d9b42e8d01a137c63ff ]

Disable frames injection in mvneta_xdp_xmit routine during hw
re-configuration in order to avoid hardware hangs

Fixes: b0a43db9087a ("net: mvneta: add XDP_TX support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 11babc79dc6c..14318dca6921 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -418,11 +418,17 @@ struct mvneta_pcpu_port {
 	u32			cause_rx_tx;
 };
 
+enum {
+	__MVNETA_DOWN,
+};
+
 struct mvneta_port {
 	u8 id;
 	struct mvneta_pcpu_port __percpu	*ports;
 	struct mvneta_pcpu_stats __percpu	*stats;
 
+	unsigned long state;
+
 	int pkt_size;
 	void __iomem *base;
 	struct mvneta_rx_queue *rxqs;
@@ -2066,6 +2072,9 @@ mvneta_xdp_xmit(struct net_device *dev, int num_frame,
 	int i, drops = 0;
 	u32 ret;
 
+	if (unlikely(test_bit(__MVNETA_DOWN, &pp->state)))
+		return -ENETDOWN;
+
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
 
@@ -3489,12 +3498,16 @@ static void mvneta_start_dev(struct mvneta_port *pp)
 
 	phylink_start(pp->phylink);
 	netif_tx_start_all_queues(pp->dev);
+
+	clear_bit(__MVNETA_DOWN, &pp->state);
 }
 
 static void mvneta_stop_dev(struct mvneta_port *pp)
 {
 	unsigned int cpu;
 
+	set_bit(__MVNETA_DOWN, &pp->state);
+
 	phylink_stop(pp->phylink);
 
 	if (!pp->neta_armada3700) {
-- 
2.26.2


From d58905ad274e19f7042c6c1e0b6f1170f87b61c1 Mon Sep 17 00:00:00 2001
From: tannerlove <tannerlove@google.com>
Date: Tue, 9 Jun 2020 17:21:32 -0400
Subject: [PATCH 3/9] selftests/net: in rxtimestamp getopt_long needs
 terminating null entry

[ Upstream commit 865a6cbb2288f8af7f9dc3b153c61b7014fdcf1e ]

getopt_long requires the last element to be filled with zeros.
Otherwise, passing an unrecognized option can cause a segfault.

Fixes: 16e781224198 ("selftests/net: Add a test to validate behavior of rx timestamps")
Signed-off-by: Tanner Love <tannerlove@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/networking/timestamping/rxtimestamp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
index 6dee9e636a95..422e7761254d 100644
--- a/tools/testing/selftests/networking/timestamping/rxtimestamp.c
+++ b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
@@ -115,6 +115,7 @@ static struct option long_options[] = {
 	{ "tcp", no_argument, 0, 't' },
 	{ "udp", no_argument, 0, 'u' },
 	{ "ip", no_argument, 0, 'i' },
+	{ NULL, 0, NULL, 0 },
 };
 
 static int next_port = 19999;
-- 
2.26.2


From cae765cf91fb0ba6b36f49a60d22b92ae7dff6d7 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@mellanox.com>
Date: Wed, 6 May 2020 15:59:48 +0300
Subject: [PATCH 4/9] net/mlx5: drain health workqueue in case of driver load
 error

[ Upstream commit 42ea9f1b5c625fad225d4ac96a7e757dd4199d9c ]

In case there is a work in the health WQ when we teardown the driver,
in driver load error flow, the health work will try to read dev->iseg,
which was already unmap in mlx5_pci_close().
Fix it by draining the health workqueue first thing in mlx5_pci_close().

Trace of the error:
BUG: unable to handle page fault for address: ffffb5b141c18014
PF: supervisor read access in kernel mode
PF: error_code(0x0000) - not-present page
PGD 1fe95d067 P4D 1fe95d067 PUD 1fe95e067 PMD 1b7823067 PTE 0
Oops: 0000 [#1] SMP PTI
CPU: 3 PID: 6755 Comm: kworker/u128:2 Not tainted 5.2.0-net-next-mlx5-hv_stats-over-last-worked-hyperv #1
Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006  04/28/2016
Workqueue: mlx5_healtha050:00:02.0 mlx5_fw_fatal_reporter_err_work [mlx5_core]
RIP: 0010:ioread32be+0x30/0x40
Code: 00 77 27 48 81 ff 00 00 01 00 76 07 0f b7 d7 ed 0f c8 c3 55 48 c7 c6 3b ee d5 9f 48 89 e5 e8 67 fc ff ff b8 ff ff ff ff 5d c3 <8b> 07 0f c8 c3 66 66 2e 0f 1f 84 00 00 00 00 00 48 81 fe ff ff 03
RSP: 0018:ffffb5b14c56fd78 EFLAGS: 00010292
RAX: ffffb5b141c18000 RBX: ffff8e9f78a801c0 RCX: 0000000000000000
RDX: 0000000000000001 RSI: ffff8e9f7ecd7628 RDI: ffffb5b141c18014
RBP: ffffb5b14c56fd90 R08: 0000000000000001 R09: 0000000000000000
R10: ffff8e9f372a2c30 R11: ffff8e9f87f4bc40 R12: ffff8e9f372a1fc0
R13: ffff8e9f78a80000 R14: ffffffffc07136a0 R15: ffff8e9f78ae6f20
FS:  0000000000000000(0000) GS:ffff8e9f7ecc0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffb5b141c18014 CR3: 00000001c8f82006 CR4: 00000000003606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 ? mlx5_health_try_recover+0x4d/0x270 [mlx5_core]
 mlx5_fw_fatal_reporter_recover+0x16/0x20 [mlx5_core]
 devlink_health_reporter_recover+0x1c/0x50
 devlink_health_report+0xfb/0x240
 mlx5_fw_fatal_reporter_err_work+0x65/0xd0 [mlx5_core]
 process_one_work+0x1fb/0x4e0
 ? process_one_work+0x16b/0x4e0
 worker_thread+0x4f/0x3d0
 kthread+0x10d/0x140
 ? process_one_work+0x4e0/0x4e0
 ? kthread_cancel_delayed_work_sync+0x20/0x20
 ret_from_fork+0x1f/0x30
Modules linked in: nfsv3 rpcsec_gss_krb5 nfsv4 nfs fscache 8021q garp mrp stp llc ipmi_devintf ipmi_msghandler rpcrdma rdma_ucm ib_iser rdma_cm ib_umad iw_cm ib_ipoib libiscsi scsi_transport_iscsi ib_cm mlx5_ib ib_uverbs ib_core mlx5_core sb_edac crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel aes_x86_64 mlxfw crypto_simd cryptd glue_helper input_leds hyperv_fb intel_rapl_perf joydev serio_raw pci_hyperv pci_hyperv_mini mac_hid hv_balloon nfsd auth_rpcgss nfs_acl lockd grace sunrpc sch_fq_codel ip_tables x_tables autofs4 hv_utils hid_generic hv_storvsc ptp hid_hyperv hid hv_netvsc hyperv_keyboard pps_core scsi_transport_fc psmouse hv_vmbus i2c_piix4 floppy pata_acpi
CR2: ffffb5b141c18014
---[ end trace b12c5503157cad24 ]---
RIP: 0010:ioread32be+0x30/0x40
Code: 00 77 27 48 81 ff 00 00 01 00 76 07 0f b7 d7 ed 0f c8 c3 55 48 c7 c6 3b ee d5 9f 48 89 e5 e8 67 fc ff ff b8 ff ff ff ff 5d c3 <8b> 07 0f c8 c3 66 66 2e 0f 1f 84 00 00 00 00 00 48 81 fe ff ff 03
RSP: 0018:ffffb5b14c56fd78 EFLAGS: 00010292
RAX: ffffb5b141c18000 RBX: ffff8e9f78a801c0 RCX: 0000000000000000
RDX: 0000000000000001 RSI: ffff8e9f7ecd7628 RDI: ffffb5b141c18014
RBP: ffffb5b14c56fd90 R08: 0000000000000001 R09: 0000000000000000
R10: ffff8e9f372a2c30 R11: ffff8e9f87f4bc40 R12: ffff8e9f372a1fc0
R13: ffff8e9f78a80000 R14: ffffffffc07136a0 R15: ffff8e9f78ae6f20
FS:  0000000000000000(0000) GS:ffff8e9f7ecc0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffb5b141c18014 CR3: 00000001c8f82006 CR4: 00000000003606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
BUG: sleeping function called from invalid context at ./include/linux/percpu-rwsem.h:38
in_atomic(): 0, irqs_disabled(): 1, pid: 6755, name: kworker/u128:2
INFO: lockdep is turned off.
CPU: 3 PID: 6755 Comm: kworker/u128:2 Tainted: G      D           5.2.0-net-next-mlx5-hv_stats-over-last-worked-hyperv #1
Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006  04/28/2016
Workqueue: mlx5_healtha050:00:02.0 mlx5_fw_fatal_reporter_err_work [mlx5_core]
Call Trace:
 dump_stack+0x63/0x88
 ___might_sleep+0x10a/0x130
 __might_sleep+0x4a/0x80
 exit_signals+0x33/0x230
 ? blocking_notifier_call_chain+0x16/0x20
 do_exit+0xb1/0xc30
 ? kthread+0x10d/0x140
 ? process_one_work+0x4e0/0x4e0

Fixes: 52c368dc3da7 ("net/mlx5: Move health and page alloc init to mdev_init")
Signed-off-by: Shay Drory <shayd@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 20e12e14cfa8..d7986f64494b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -794,6 +794,11 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 
 static void mlx5_pci_close(struct mlx5_core_dev *dev)
 {
+	/* health work might still be active, and it needs pci bar in
+	 * order to know the NIC state. Therefore, drain the health WQ
+	 * before removing the pci bars
+	 */
+	mlx5_drain_health_wq(dev);
 	iounmap(dev->iseg);
 	pci_clear_master(dev->pdev);
 	release_bar(dev->pdev);
-- 
2.26.2


From 41480989ed1932e62e7e113d567b5d230793bff8 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@mellanox.com>
Date: Thu, 7 May 2020 09:32:53 +0300
Subject: [PATCH 5/9] net/mlx5: Fix fatal error handling during device load

[ Upstream commit b6e0b6bebe0732d5cac51f0791f269d2413b8980 ]

Currently, in case of fatal error during mlx5_load_one(), we cannot
enter error state until mlx5_load_one() is finished, what can take
several minutes until commands will get timeouts, because these commands
can't be processed due to the fatal error.
Fix it by setting dev->state as MLX5_DEVICE_STATE_INTERNAL_ERROR before
requesting the lock.

Fixes: c1d4d2e92ad6 ("net/mlx5: Avoid calling sleeping function by the health poll thread")
Signed-off-by: Shay Drory <shayd@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 68e7ef7ca52d..ffb360fe44d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -193,15 +193,23 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev)
 
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 {
+	bool err_detected = false;
+
+	/* Mark the device as fatal in order to abort FW commands */
+	if ((check_fatal_sensors(dev) || force) &&
+	    dev->state == MLX5_DEVICE_STATE_UP) {
+		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
+		err_detected = true;
+	}
 	mutex_lock(&dev->intf_state_mutex);
-	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
-		goto unlock;
+	if (!err_detected && dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
+		goto unlock;/* a previous error is still being handled */
 	if (dev->state == MLX5_DEVICE_STATE_UNINITIALIZED) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		goto unlock;
 	}
 
-	if (check_fatal_sensors(dev) || force) {
+	if (check_fatal_sensors(dev) || force) { /* protected state setting */
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		mlx5_cmd_flush(dev);
 	}
-- 
2.26.2


From 36e5e43e4ab8cda5043736716a5ed14bf4e75b1e Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 1 Jun 2020 16:03:44 +0300
Subject: [PATCH 6/9] net/mlx5e: Fix repeated XSK usage on one channel

[ Upstream commit 36d45fb9d2fdf348d778bfe73f0427db1c6f9bc7 ]

After an XSK is closed, the relevant structures in the channel are not
zeroed. If an XSK is opened the second time on the same channel without
recreating channels, the stray values in the structures will lead to
incorrect operation of queues, which causes CQE errors, and the new
socket doesn't work at all.

This patch fixes the issue by explicitly zeroing XSK-related structs in
the channel on XSK close. Note that those structs are zeroed on channel
creation, and usually a configuration change (XDP program is set)
happens on XSK open, which leads to recreating channels, so typical XSK
usecases don't suffer from this issue. However, if XSKs are opened and
closed on the same channel without removing the XDP program, this bug
reproduces.

Fixes: db05815b36cb ("net/mlx5e: Add XSK zero-copy support")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index c28cbae42331..2c80205dc939 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -152,6 +152,10 @@ void mlx5e_close_xsk(struct mlx5e_channel *c)
 	mlx5e_close_cq(&c->xskicosq.cq);
 	mlx5e_close_xdpsq(&c->xsksq);
 	mlx5e_close_cq(&c->xsksq.cq);
+
+	memset(&c->xskrq, 0, sizeof(c->xskrq));
+	memset(&c->xsksq, 0, sizeof(c->xsksq));
+	memset(&c->xskicosq, 0, sizeof(c->xskicosq));
 }
 
 void mlx5e_activate_xsk(struct mlx5e_channel *c)
-- 
2.26.2


From 308ba307118c616ee6345ff768ae93d370ba4440 Mon Sep 17 00:00:00 2001
From: Corentin Labbe <clabbe@baylibre.com>
Date: Wed, 10 Jun 2020 09:53:44 +0000
Subject: [PATCH 7/9] net: cadence: macb: disable NAPI on error

[ Upstream commit 014406babc1f5f887a08737566b5b356c7018242 ]

When the PHY is not working, the macb driver crash on a second try to
setup it.
[   78.545994] macb e000b000.ethernet eth0: Could not attach PHY (-19)
ifconfig: SIOCSIFFLAGS: No such device
[   78.655457] ------------[ cut here ]------------
[   78.656014] kernel BUG at /linux-next/include/linux/netdevice.h:521!
[   78.656504] Internal error: Oops - BUG: 0 [#1] SMP ARM
[   78.657079] Modules linked in:
[   78.657795] CPU: 0 PID: 122 Comm: ifconfig Not tainted 5.7.0-next-20200609 #1
[   78.658202] Hardware name: Xilinx Zynq Platform
[   78.659632] PC is at macb_open+0x220/0x294
[   78.660160] LR is at 0x0
[   78.660373] pc : [<c0b0a634>]    lr : [<00000000>]    psr: 60000013
[   78.660716] sp : c89ffd70  ip : c8a28800  fp : c199bac0
[   78.661040] r10: 00000000  r9 : c8838540  r8 : c8838568
[   78.661362] r7 : 00000001  r6 : c8838000  r5 : c883c000  r4 : 00000000
[   78.661724] r3 : 00000010  r2 : 00000000  r1 : 00000000  r0 : 00000000
[   78.662187] Flags: nZCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
[   78.662635] Control: 10c5387d  Table: 08b64059  DAC: 00000051
[   78.663035] Process ifconfig (pid: 122, stack limit = 0x(ptrval))
[   78.663476] Stack: (0xc89ffd70 to 0xc8a00000)
[   78.664121] fd60:                                     00000000 c89fe000 c8838000 c89fe000
[   78.664866] fd80: 00000000 c11ff9ac c8838028 00000000 00000000 c0de6f2c 00000001 c1804eec
[   78.665579] fda0: c19b8178 c8838000 00000000 ca760866 c8838000 00000001 00001043 c89fe000
[   78.666355] fdc0: 00001002 c0de72f4 c89fe000 c0de8dc0 00008914 c89fe000 c199bac0 ca760866
[   78.667111] fde0: c89ffddc c8838000 00001002 00000000 c8838138 c881010c 00008914 c0de7364
[   78.667862] fe00: 00000000 c89ffe70 c89fe000 ffffffff c881010c c0e8bd48 00000003 00000000
[   78.668601] fe20: c8838000 c8810100 39c1118f 00039c11 c89a0960 00001043 00000000 000a26d0
[   78.669343] fe40: b6f43000 ca760866 c89a0960 00000051 befe6c50 00008914 c8b2a3c0 befe6c50
[   78.670086] fe60: 00000003 ee610500 00000000 c0e8ef58 30687465 00000000 00000000 00000000
[   78.670865] fe80: 00001043 00000000 000a26d0 b6f43000 c89a0600 ee40ae7c c8870d00 c0ddabf4
[   78.671593] fea0: c89ffeec c0ddabf4 c89ffeec c199bac0 00008913 c0ddac48 c89ffeec c89fe000
[   78.672324] fec0: befe6c50 ca760866 befe6c50 00008914 c89fe000 befe6c50 c8b2a3c0 c0dc00e4
[   78.673088] fee0: c89a0480 00000201 00000cc0 30687465 00000000 00000000 00000000 00001002
[   78.673822] ff00: 00000000 000a26d0 b6f43000 ca760866 00008914 c8b2a3c0 000a0ec4 c8b2a3c0
[   78.674576] ff20: befe6c50 c04b21bc 000d5004 00000817 c89a0480 c0315f94 00000000 00000003
[   78.675415] ff40: c19a2bc8 c8a3cc00 c89fe000 00000255 00000000 00000000 00000000 000d5000
[   78.676182] ff60: 000f6000 c180b2a0 00000817 c0315e64 000d5004 c89fffb0 b6ec0c30 ca760866
[   78.676928] ff80: 00000000 000b609b befe6c50 000a0ec4 00000036 c03002c4 c89fe000 00000036
[   78.677673] ffa0: 00000000 c03000c0 000b609b befe6c50 00000003 00008914 befe6c50 000b609b
[   78.678415] ffc0: 000b609b befe6c50 000a0ec4 00000036 befe6e0c befe6f1a 000d5150 00000000
[   78.679154] ffe0: 000d41e4 befe6bf4 00019648 b6e4509c 20000010 00000003 00000000 00000000
[   78.681059] [<c0b0a634>] (macb_open) from [<c0de6f2c>] (__dev_open+0xd0/0x154)
[   78.681571] [<c0de6f2c>] (__dev_open) from [<c0de72f4>] (__dev_change_flags+0x16c/0x1c4)
[   78.682015] [<c0de72f4>] (__dev_change_flags) from [<c0de7364>] (dev_change_flags+0x18/0x48)
[   78.682493] [<c0de7364>] (dev_change_flags) from [<c0e8bd48>] (devinet_ioctl+0x5e4/0x75c)
[   78.682945] [<c0e8bd48>] (devinet_ioctl) from [<c0e8ef58>] (inet_ioctl+0x1f0/0x3b4)
[   78.683381] [<c0e8ef58>] (inet_ioctl) from [<c0dc00e4>] (sock_ioctl+0x39c/0x664)
[   78.683818] [<c0dc00e4>] (sock_ioctl) from [<c04b21bc>] (ksys_ioctl+0x2d8/0x9c0)
[   78.684343] [<c04b21bc>] (ksys_ioctl) from [<c03000c0>] (ret_fast_syscall+0x0/0x54)
[   78.684789] Exception stack(0xc89fffa8 to 0xc89ffff0)
[   78.685346] ffa0:                   000b609b befe6c50 00000003 00008914 befe6c50 000b609b
[   78.686106] ffc0: 000b609b befe6c50 000a0ec4 00000036 befe6e0c befe6f1a 000d5150 00000000
[   78.686710] ffe0: 000d41e4 befe6bf4 00019648 b6e4509c
[   78.687582] Code: 9a000003 e5983078 e3130001 1affffef (e7f001f2)
[   78.688788] ---[ end trace e3f2f6ab69754eae ]---

This is due to NAPI left enabled if macb_phylink_connect() fail.

Fixes: 7897b071ac3b ("net: macb: convert to phylink")
Signed-off-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index f42382c2ecd0..9b91a7b8a362 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2545,13 +2545,16 @@ static int macb_open(struct net_device *dev)
 
 	err = macb_phylink_connect(bp);
 	if (err)
-		goto pm_exit;
+		goto napi_exit;
 
 	netif_tx_start_all_queues(dev);
 
 	if (bp->ptp_info)
 		bp->ptp_info->ptp_init(dev);
 
+napi_exit:
+	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
+		napi_disable(&queue->napi);
 pm_exit:
 	if (err) {
 		pm_runtime_put_sync(&bp->pdev->dev);
-- 
2.26.2


From e8e1aaafcc89f4d8843768ac1902cd303825896a Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Mon, 15 Jun 2020 14:18:54 +0100
Subject: [PATCH 8/9] net: macb: Only disable NAPI on the actual error path

[ Upstream commit 939a5bf7c9b7a1ad9c5d3481c93766a522773531 ]

A recent change added a disable to NAPI into macb_open, this was
intended to only happen on the error path but accidentally applies
to all paths. This causes NAPI to be disabled on the success path, which
leads to the network to no longer functioning.

Fixes: 014406babc1f ("net: cadence: macb: disable NAPI on error")
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Tested-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 9b91a7b8a362..9067b413d6b7 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2552,15 +2552,14 @@ static int macb_open(struct net_device *dev)
 	if (bp->ptp_info)
 		bp->ptp_info->ptp_init(dev);
 
+	return 0;
+
 napi_exit:
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
 		napi_disable(&queue->napi);
 pm_exit:
-	if (err) {
-		pm_runtime_put_sync(&bp->pdev->dev);
-		return err;
-	}
-	return 0;
+	pm_runtime_put_sync(&bp->pdev->dev);
+	return err;
 }
 
 static int macb_close(struct net_device *dev)
-- 
2.26.2


From 350270dba0124e4a244dcefd259ac287dcec07f6 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Thu, 14 May 2020 05:12:56 -0500
Subject: [PATCH 9/9] net/mlx5: Disable reload while removing the device

[ Upstream commit 60904cd349abc98cb888fc28d1ca55a8e2cf87b3 ]

While unregistration is in progress, user might be reloading the
interface.
This can race with unregistration in below flow which uses the
resources which are getting disabled by reload flow.

Hence, disable the devlink reloading first when removing the device.

     CPU0                                   CPU1
     ----                                   ----
local_pci_remove()                  devlink_mutex
  remove_one()                       devlink_nl_cmd_reload()
    mlx5_unregister_device()           devlink_reload()
                                       ops->reload_down()
                                         mlx5_unload_one()

Fixes: 4383cfcc65e7 ("net/mlx5: Add devlink reload")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 2 --
 drivers/net/ethernet/mellanox/mlx5/core/main.c    | 2 ++
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 184c3eaefbcb..c190eb267f3c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -256,7 +256,6 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
 		goto params_reg_err;
 	mlx5_devlink_set_params_init_values(devlink);
 	devlink_params_publish(devlink);
-	devlink_reload_enable(devlink);
 	return 0;
 
 params_reg_err:
@@ -266,7 +265,6 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
 
 void mlx5_devlink_unregister(struct devlink *devlink)
 {
-	devlink_reload_disable(devlink);
 	devlink_params_unregister(devlink, mlx5_devlink_params,
 				  ARRAY_SIZE(mlx5_devlink_params));
 	devlink_unregister(devlink);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index d7986f64494b..743491babf88 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1371,6 +1371,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err);
 
 	pci_save_state(pdev);
+	devlink_reload_enable(devlink);
 	return 0;
 
 err_load_one:
@@ -1388,6 +1389,7 @@ static void remove_one(struct pci_dev *pdev)
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
 	struct devlink *devlink = priv_to_devlink(dev);
 
+	devlink_reload_disable(devlink);
 	mlx5_crdump_disable(dev);
 	mlx5_devlink_unregister(devlink);
 
-- 
2.26.2


[-- Attachment #3: net_57.mbox --]
[-- Type: Application/Octet-Stream, Size: 40954 bytes --]

From 0e957172ba6f9880e9f92ebb15ff4140cc86b4b4 Mon Sep 17 00:00:00 2001
From: Wang Hai <wanghai38@huawei.com>
Date: Tue, 9 Jun 2020 22:18:16 +0800
Subject: [PATCH 01/16] dccp: Fix possible memleak in dccp_init and dccp_fini

[ Upstream commit c96b6acc8f89a4a7f6258dfe1d077654c11415be ]

There are some memory leaks in dccp_init() and dccp_fini().

In dccp_fini() and the error handling path in dccp_init(), free lhash2
is missing. Add inet_hashinfo2_free_mod() to do it.

If inet_hashinfo2_init_mod() failed in dccp_init(),
percpu_counter_destroy() should be called to destroy dccp_orphan_count.
It need to goto out_free_percpu when inet_hashinfo2_init_mod() failed.

Fixes: c92c81df93df ("net: dccp: fix kernel crash on module load")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wang Hai <wanghai38@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h | 6 ++++++
 net/dccp/proto.c              | 7 +++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index ad64ba6a057f..92560974ea67 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -185,6 +185,12 @@ static inline spinlock_t *inet_ehash_lockp(
 
 int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo);
 
+static inline void inet_hashinfo2_free_mod(struct inet_hashinfo *h)
+{
+	kfree(h->lhash2);
+	h->lhash2 = NULL;
+}
+
 static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
 {
 	kvfree(hashinfo->ehash_locks);
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 4af8a98fe784..c13b6609474b 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1139,14 +1139,14 @@ static int __init dccp_init(void)
 	inet_hashinfo_init(&dccp_hashinfo);
 	rc = inet_hashinfo2_init_mod(&dccp_hashinfo);
 	if (rc)
-		goto out_fail;
+		goto out_free_percpu;
 	rc = -ENOBUFS;
 	dccp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("dccp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
 				  SLAB_HWCACHE_ALIGN, NULL);
 	if (!dccp_hashinfo.bind_bucket_cachep)
-		goto out_free_percpu;
+		goto out_free_hashinfo2;
 
 	/*
 	 * Size and allocate the main established and bind bucket
@@ -1242,6 +1242,8 @@ static int __init dccp_init(void)
 	free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order);
 out_free_bind_bucket_cachep:
 	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
+out_free_hashinfo2:
+	inet_hashinfo2_free_mod(&dccp_hashinfo);
 out_free_percpu:
 	percpu_counter_destroy(&dccp_orphan_count);
 out_fail:
@@ -1265,6 +1267,7 @@ static void __exit dccp_fini(void)
 	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
 	dccp_ackvec_exit();
 	dccp_sysctl_exit();
+	inet_hashinfo2_free_mod(&dccp_hashinfo);
 	percpu_counter_destroy(&dccp_orphan_count);
 }
 
-- 
2.26.2


From 1ba487ccaa0266875a18345853a5dc1fd4b67b54 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 9 Jun 2020 00:02:39 +0200
Subject: [PATCH 02/16] net: mvneta: do not redirect frames during
 reconfiguration

[ Upstream commit 62a502cc91f97e3ffd312d9b42e8d01a137c63ff ]

Disable frames injection in mvneta_xdp_xmit routine during hw
re-configuration in order to avoid hardware hangs

Fixes: b0a43db9087a ("net: mvneta: add XDP_TX support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 51889770958d..43b44a1e8f69 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -451,11 +451,17 @@ struct mvneta_pcpu_port {
 	u32			cause_rx_tx;
 };
 
+enum {
+	__MVNETA_DOWN,
+};
+
 struct mvneta_port {
 	u8 id;
 	struct mvneta_pcpu_port __percpu	*ports;
 	struct mvneta_pcpu_stats __percpu	*stats;
 
+	unsigned long state;
+
 	int pkt_size;
 	void __iomem *base;
 	struct mvneta_rx_queue *rxqs;
@@ -2112,6 +2118,9 @@ mvneta_xdp_xmit(struct net_device *dev, int num_frame,
 	struct netdev_queue *nq;
 	u32 ret;
 
+	if (unlikely(test_bit(__MVNETA_DOWN, &pp->state)))
+		return -ENETDOWN;
+
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
 
@@ -3562,12 +3571,16 @@ static void mvneta_start_dev(struct mvneta_port *pp)
 
 	phylink_start(pp->phylink);
 	netif_tx_start_all_queues(pp->dev);
+
+	clear_bit(__MVNETA_DOWN, &pp->state);
 }
 
 static void mvneta_stop_dev(struct mvneta_port *pp)
 {
 	unsigned int cpu;
 
+	set_bit(__MVNETA_DOWN, &pp->state);
+
 	phylink_stop(pp->phylink);
 
 	if (!pp->neta_armada3700) {
-- 
2.26.2


From 72db283350cf6e92ffd55d9e264c1816fbf6a150 Mon Sep 17 00:00:00 2001
From: tannerlove <tannerlove@google.com>
Date: Tue, 9 Jun 2020 17:21:32 -0400
Subject: [PATCH 03/16] selftests/net: in rxtimestamp getopt_long needs
 terminating null entry

[ Upstream commit 865a6cbb2288f8af7f9dc3b153c61b7014fdcf1e ]

getopt_long requires the last element to be filled with zeros.
Otherwise, passing an unrecognized option can cause a segfault.

Fixes: 16e781224198 ("selftests/net: Add a test to validate behavior of rx timestamps")
Signed-off-by: Tanner Love <tannerlove@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rxtimestamp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c
index 6dee9e636a95..422e7761254d 100644
--- a/tools/testing/selftests/net/rxtimestamp.c
+++ b/tools/testing/selftests/net/rxtimestamp.c
@@ -115,6 +115,7 @@ static struct option long_options[] = {
 	{ "tcp", no_argument, 0, 't' },
 	{ "udp", no_argument, 0, 'u' },
 	{ "ip", no_argument, 0, 'i' },
+	{ NULL, 0, NULL, 0 },
 };
 
 static int next_port = 19999;
-- 
2.26.2


From f432ef4db06adb2755dadbe67d8d836d1601ad6b Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@mellanox.com>
Date: Wed, 6 May 2020 15:59:48 +0300
Subject: [PATCH 04/16] net/mlx5: drain health workqueue in case of driver load
 error

[ Upstream commit 42ea9f1b5c625fad225d4ac96a7e757dd4199d9c ]

In case there is a work in the health WQ when we teardown the driver,
in driver load error flow, the health work will try to read dev->iseg,
which was already unmap in mlx5_pci_close().
Fix it by draining the health workqueue first thing in mlx5_pci_close().

Trace of the error:
BUG: unable to handle page fault for address: ffffb5b141c18014
PF: supervisor read access in kernel mode
PF: error_code(0x0000) - not-present page
PGD 1fe95d067 P4D 1fe95d067 PUD 1fe95e067 PMD 1b7823067 PTE 0
Oops: 0000 [#1] SMP PTI
CPU: 3 PID: 6755 Comm: kworker/u128:2 Not tainted 5.2.0-net-next-mlx5-hv_stats-over-last-worked-hyperv #1
Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006  04/28/2016
Workqueue: mlx5_healtha050:00:02.0 mlx5_fw_fatal_reporter_err_work [mlx5_core]
RIP: 0010:ioread32be+0x30/0x40
Code: 00 77 27 48 81 ff 00 00 01 00 76 07 0f b7 d7 ed 0f c8 c3 55 48 c7 c6 3b ee d5 9f 48 89 e5 e8 67 fc ff ff b8 ff ff ff ff 5d c3 <8b> 07 0f c8 c3 66 66 2e 0f 1f 84 00 00 00 00 00 48 81 fe ff ff 03
RSP: 0018:ffffb5b14c56fd78 EFLAGS: 00010292
RAX: ffffb5b141c18000 RBX: ffff8e9f78a801c0 RCX: 0000000000000000
RDX: 0000000000000001 RSI: ffff8e9f7ecd7628 RDI: ffffb5b141c18014
RBP: ffffb5b14c56fd90 R08: 0000000000000001 R09: 0000000000000000
R10: ffff8e9f372a2c30 R11: ffff8e9f87f4bc40 R12: ffff8e9f372a1fc0
R13: ffff8e9f78a80000 R14: ffffffffc07136a0 R15: ffff8e9f78ae6f20
FS:  0000000000000000(0000) GS:ffff8e9f7ecc0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffb5b141c18014 CR3: 00000001c8f82006 CR4: 00000000003606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 ? mlx5_health_try_recover+0x4d/0x270 [mlx5_core]
 mlx5_fw_fatal_reporter_recover+0x16/0x20 [mlx5_core]
 devlink_health_reporter_recover+0x1c/0x50
 devlink_health_report+0xfb/0x240
 mlx5_fw_fatal_reporter_err_work+0x65/0xd0 [mlx5_core]
 process_one_work+0x1fb/0x4e0
 ? process_one_work+0x16b/0x4e0
 worker_thread+0x4f/0x3d0
 kthread+0x10d/0x140
 ? process_one_work+0x4e0/0x4e0
 ? kthread_cancel_delayed_work_sync+0x20/0x20
 ret_from_fork+0x1f/0x30
Modules linked in: nfsv3 rpcsec_gss_krb5 nfsv4 nfs fscache 8021q garp mrp stp llc ipmi_devintf ipmi_msghandler rpcrdma rdma_ucm ib_iser rdma_cm ib_umad iw_cm ib_ipoib libiscsi scsi_transport_iscsi ib_cm mlx5_ib ib_uverbs ib_core mlx5_core sb_edac crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel aes_x86_64 mlxfw crypto_simd cryptd glue_helper input_leds hyperv_fb intel_rapl_perf joydev serio_raw pci_hyperv pci_hyperv_mini mac_hid hv_balloon nfsd auth_rpcgss nfs_acl lockd grace sunrpc sch_fq_codel ip_tables x_tables autofs4 hv_utils hid_generic hv_storvsc ptp hid_hyperv hid hv_netvsc hyperv_keyboard pps_core scsi_transport_fc psmouse hv_vmbus i2c_piix4 floppy pata_acpi
CR2: ffffb5b141c18014
---[ end trace b12c5503157cad24 ]---
RIP: 0010:ioread32be+0x30/0x40
Code: 00 77 27 48 81 ff 00 00 01 00 76 07 0f b7 d7 ed 0f c8 c3 55 48 c7 c6 3b ee d5 9f 48 89 e5 e8 67 fc ff ff b8 ff ff ff ff 5d c3 <8b> 07 0f c8 c3 66 66 2e 0f 1f 84 00 00 00 00 00 48 81 fe ff ff 03
RSP: 0018:ffffb5b14c56fd78 EFLAGS: 00010292
RAX: ffffb5b141c18000 RBX: ffff8e9f78a801c0 RCX: 0000000000000000
RDX: 0000000000000001 RSI: ffff8e9f7ecd7628 RDI: ffffb5b141c18014
RBP: ffffb5b14c56fd90 R08: 0000000000000001 R09: 0000000000000000
R10: ffff8e9f372a2c30 R11: ffff8e9f87f4bc40 R12: ffff8e9f372a1fc0
R13: ffff8e9f78a80000 R14: ffffffffc07136a0 R15: ffff8e9f78ae6f20
FS:  0000000000000000(0000) GS:ffff8e9f7ecc0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffb5b141c18014 CR3: 00000001c8f82006 CR4: 00000000003606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
BUG: sleeping function called from invalid context at ./include/linux/percpu-rwsem.h:38
in_atomic(): 0, irqs_disabled(): 1, pid: 6755, name: kworker/u128:2
INFO: lockdep is turned off.
CPU: 3 PID: 6755 Comm: kworker/u128:2 Tainted: G      D           5.2.0-net-next-mlx5-hv_stats-over-last-worked-hyperv #1
Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006  04/28/2016
Workqueue: mlx5_healtha050:00:02.0 mlx5_fw_fatal_reporter_err_work [mlx5_core]
Call Trace:
 dump_stack+0x63/0x88
 ___might_sleep+0x10a/0x130
 __might_sleep+0x4a/0x80
 exit_signals+0x33/0x230
 ? blocking_notifier_call_chain+0x16/0x20
 do_exit+0xb1/0xc30
 ? kthread+0x10d/0x140
 ? process_one_work+0x4e0/0x4e0

Fixes: 52c368dc3da7 ("net/mlx5: Move health and page alloc init to mdev_init")
Signed-off-by: Shay Drory <shayd@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 17f818a54090..3b7d68df9cf2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -795,6 +795,11 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 
 static void mlx5_pci_close(struct mlx5_core_dev *dev)
 {
+	/* health work might still be active, and it needs pci bar in
+	 * order to know the NIC state. Therefore, drain the health WQ
+	 * before removing the pci bars
+	 */
+	mlx5_drain_health_wq(dev);
 	iounmap(dev->iseg);
 	pci_clear_master(dev->pdev);
 	release_bar(dev->pdev);
-- 
2.26.2


From 9a281917d2f8b76825e51d1df879dc26b71cff63 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@mellanox.com>
Date: Thu, 7 May 2020 09:32:53 +0300
Subject: [PATCH 05/16] net/mlx5: Fix fatal error handling during device load

[ Upstream commit b6e0b6bebe0732d5cac51f0791f269d2413b8980 ]

Currently, in case of fatal error during mlx5_load_one(), we cannot
enter error state until mlx5_load_one() is finished, what can take
several minutes until commands will get timeouts, because these commands
can't be processed due to the fatal error.
Fix it by setting dev->state as MLX5_DEVICE_STATE_INTERNAL_ERROR before
requesting the lock.

Fixes: c1d4d2e92ad6 ("net/mlx5: Avoid calling sleeping function by the health poll thread")
Signed-off-by: Shay Drory <shayd@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index f99e1752d4e5..e22b7ae11275 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -193,15 +193,23 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev)
 
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 {
+	bool err_detected = false;
+
+	/* Mark the device as fatal in order to abort FW commands */
+	if ((check_fatal_sensors(dev) || force) &&
+	    dev->state == MLX5_DEVICE_STATE_UP) {
+		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
+		err_detected = true;
+	}
 	mutex_lock(&dev->intf_state_mutex);
-	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
-		goto unlock;
+	if (!err_detected && dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
+		goto unlock;/* a previous error is still being handled */
 	if (dev->state == MLX5_DEVICE_STATE_UNINITIALIZED) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		goto unlock;
 	}
 
-	if (check_fatal_sensors(dev) || force) {
+	if (check_fatal_sensors(dev) || force) { /* protected state setting */
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		mlx5_cmd_flush(dev);
 	}
-- 
2.26.2


From c6714a1176fad553a1bd65e77e178ed6df759f5b Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 1 Jun 2020 16:03:44 +0300
Subject: [PATCH 06/16] net/mlx5e: Fix repeated XSK usage on one channel

[ Upstream commit 36d45fb9d2fdf348d778bfe73f0427db1c6f9bc7 ]

After an XSK is closed, the relevant structures in the channel are not
zeroed. If an XSK is opened the second time on the same channel without
recreating channels, the stray values in the structures will lead to
incorrect operation of queues, which causes CQE errors, and the new
socket doesn't work at all.

This patch fixes the issue by explicitly zeroing XSK-related structs in
the channel on XSK close. Note that those structs are zeroed on channel
creation, and usually a configuration change (XDP program is set)
happens on XSK open, which leads to recreating channels, so typical XSK
usecases don't suffer from this issue. However, if XSKs are opened and
closed on the same channel without removing the XDP program, this bug
reproduces.

Fixes: db05815b36cb ("net/mlx5e: Add XSK zero-copy support")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index c28cbae42331..2c80205dc939 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -152,6 +152,10 @@ void mlx5e_close_xsk(struct mlx5e_channel *c)
 	mlx5e_close_cq(&c->xskicosq.cq);
 	mlx5e_close_xdpsq(&c->xsksq);
 	mlx5e_close_cq(&c->xsksq.cq);
+
+	memset(&c->xskrq, 0, sizeof(c->xskrq));
+	memset(&c->xsksq, 0, sizeof(c->xsksq));
+	memset(&c->xskicosq, 0, sizeof(c->xskicosq));
 }
 
 void mlx5e_activate_xsk(struct mlx5e_channel *c)
-- 
2.26.2


From af47bf872485fac8aa259965c61af97d719f156d Mon Sep 17 00:00:00 2001
From: Corentin Labbe <clabbe@baylibre.com>
Date: Wed, 10 Jun 2020 09:53:44 +0000
Subject: [PATCH 07/16] net: cadence: macb: disable NAPI on error

[ Upstream commit 014406babc1f5f887a08737566b5b356c7018242 ]

When the PHY is not working, the macb driver crash on a second try to
setup it.
[   78.545994] macb e000b000.ethernet eth0: Could not attach PHY (-19)
ifconfig: SIOCSIFFLAGS: No such device
[   78.655457] ------------[ cut here ]------------
[   78.656014] kernel BUG at /linux-next/include/linux/netdevice.h:521!
[   78.656504] Internal error: Oops - BUG: 0 [#1] SMP ARM
[   78.657079] Modules linked in:
[   78.657795] CPU: 0 PID: 122 Comm: ifconfig Not tainted 5.7.0-next-20200609 #1
[   78.658202] Hardware name: Xilinx Zynq Platform
[   78.659632] PC is at macb_open+0x220/0x294
[   78.660160] LR is at 0x0
[   78.660373] pc : [<c0b0a634>]    lr : [<00000000>]    psr: 60000013
[   78.660716] sp : c89ffd70  ip : c8a28800  fp : c199bac0
[   78.661040] r10: 00000000  r9 : c8838540  r8 : c8838568
[   78.661362] r7 : 00000001  r6 : c8838000  r5 : c883c000  r4 : 00000000
[   78.661724] r3 : 00000010  r2 : 00000000  r1 : 00000000  r0 : 00000000
[   78.662187] Flags: nZCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
[   78.662635] Control: 10c5387d  Table: 08b64059  DAC: 00000051
[   78.663035] Process ifconfig (pid: 122, stack limit = 0x(ptrval))
[   78.663476] Stack: (0xc89ffd70 to 0xc8a00000)
[   78.664121] fd60:                                     00000000 c89fe000 c8838000 c89fe000
[   78.664866] fd80: 00000000 c11ff9ac c8838028 00000000 00000000 c0de6f2c 00000001 c1804eec
[   78.665579] fda0: c19b8178 c8838000 00000000 ca760866 c8838000 00000001 00001043 c89fe000
[   78.666355] fdc0: 00001002 c0de72f4 c89fe000 c0de8dc0 00008914 c89fe000 c199bac0 ca760866
[   78.667111] fde0: c89ffddc c8838000 00001002 00000000 c8838138 c881010c 00008914 c0de7364
[   78.667862] fe00: 00000000 c89ffe70 c89fe000 ffffffff c881010c c0e8bd48 00000003 00000000
[   78.668601] fe20: c8838000 c8810100 39c1118f 00039c11 c89a0960 00001043 00000000 000a26d0
[   78.669343] fe40: b6f43000 ca760866 c89a0960 00000051 befe6c50 00008914 c8b2a3c0 befe6c50
[   78.670086] fe60: 00000003 ee610500 00000000 c0e8ef58 30687465 00000000 00000000 00000000
[   78.670865] fe80: 00001043 00000000 000a26d0 b6f43000 c89a0600 ee40ae7c c8870d00 c0ddabf4
[   78.671593] fea0: c89ffeec c0ddabf4 c89ffeec c199bac0 00008913 c0ddac48 c89ffeec c89fe000
[   78.672324] fec0: befe6c50 ca760866 befe6c50 00008914 c89fe000 befe6c50 c8b2a3c0 c0dc00e4
[   78.673088] fee0: c89a0480 00000201 00000cc0 30687465 00000000 00000000 00000000 00001002
[   78.673822] ff00: 00000000 000a26d0 b6f43000 ca760866 00008914 c8b2a3c0 000a0ec4 c8b2a3c0
[   78.674576] ff20: befe6c50 c04b21bc 000d5004 00000817 c89a0480 c0315f94 00000000 00000003
[   78.675415] ff40: c19a2bc8 c8a3cc00 c89fe000 00000255 00000000 00000000 00000000 000d5000
[   78.676182] ff60: 000f6000 c180b2a0 00000817 c0315e64 000d5004 c89fffb0 b6ec0c30 ca760866
[   78.676928] ff80: 00000000 000b609b befe6c50 000a0ec4 00000036 c03002c4 c89fe000 00000036
[   78.677673] ffa0: 00000000 c03000c0 000b609b befe6c50 00000003 00008914 befe6c50 000b609b
[   78.678415] ffc0: 000b609b befe6c50 000a0ec4 00000036 befe6e0c befe6f1a 000d5150 00000000
[   78.679154] ffe0: 000d41e4 befe6bf4 00019648 b6e4509c 20000010 00000003 00000000 00000000
[   78.681059] [<c0b0a634>] (macb_open) from [<c0de6f2c>] (__dev_open+0xd0/0x154)
[   78.681571] [<c0de6f2c>] (__dev_open) from [<c0de72f4>] (__dev_change_flags+0x16c/0x1c4)
[   78.682015] [<c0de72f4>] (__dev_change_flags) from [<c0de7364>] (dev_change_flags+0x18/0x48)
[   78.682493] [<c0de7364>] (dev_change_flags) from [<c0e8bd48>] (devinet_ioctl+0x5e4/0x75c)
[   78.682945] [<c0e8bd48>] (devinet_ioctl) from [<c0e8ef58>] (inet_ioctl+0x1f0/0x3b4)
[   78.683381] [<c0e8ef58>] (inet_ioctl) from [<c0dc00e4>] (sock_ioctl+0x39c/0x664)
[   78.683818] [<c0dc00e4>] (sock_ioctl) from [<c04b21bc>] (ksys_ioctl+0x2d8/0x9c0)
[   78.684343] [<c04b21bc>] (ksys_ioctl) from [<c03000c0>] (ret_fast_syscall+0x0/0x54)
[   78.684789] Exception stack(0xc89fffa8 to 0xc89ffff0)
[   78.685346] ffa0:                   000b609b befe6c50 00000003 00008914 befe6c50 000b609b
[   78.686106] ffc0: 000b609b befe6c50 000a0ec4 00000036 befe6e0c befe6f1a 000d5150 00000000
[   78.686710] ffe0: 000d41e4 befe6bf4 00019648 b6e4509c
[   78.687582] Code: 9a000003 e5983078 e3130001 1affffef (e7f001f2)
[   78.688788] ---[ end trace e3f2f6ab69754eae ]---

This is due to NAPI left enabled if macb_phylink_connect() fail.

Fixes: 7897b071ac3b ("net: macb: convert to phylink")
Signed-off-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 36290a8e2a84..5b9d7c60eebc 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2558,13 +2558,16 @@ static int macb_open(struct net_device *dev)
 
 	err = macb_phylink_connect(bp);
 	if (err)
-		goto pm_exit;
+		goto napi_exit;
 
 	netif_tx_start_all_queues(dev);
 
 	if (bp->ptp_info)
 		bp->ptp_info->ptp_init(dev);
 
+napi_exit:
+	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
+		napi_disable(&queue->napi);
 pm_exit:
 	if (err) {
 		pm_runtime_put_sync(&bp->pdev->dev);
-- 
2.26.2


From 77f66dc2d4a06e7fe0c6defd772bc11cda4659b4 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Mon, 15 Jun 2020 14:18:54 +0100
Subject: [PATCH 08/16] net: macb: Only disable NAPI on the actual error path

[ Upstream commit 939a5bf7c9b7a1ad9c5d3481c93766a522773531 ]

A recent change added a disable to NAPI into macb_open, this was
intended to only happen on the error path but accidentally applies
to all paths. This causes NAPI to be disabled on the success path, which
leads to the network to no longer functioning.

Fixes: 014406babc1f ("net: cadence: macb: disable NAPI on error")
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Tested-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 5b9d7c60eebc..67933079aeea 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2565,15 +2565,14 @@ static int macb_open(struct net_device *dev)
 	if (bp->ptp_info)
 		bp->ptp_info->ptp_init(dev);
 
+	return 0;
+
 napi_exit:
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
 		napi_disable(&queue->napi);
 pm_exit:
-	if (err) {
-		pm_runtime_put_sync(&bp->pdev->dev);
-		return err;
-	}
-	return 0;
+	pm_runtime_put_sync(&bp->pdev->dev);
+	return err;
 }
 
 static int macb_close(struct net_device *dev)
-- 
2.26.2


From 00d44c0b9a019ea695ebfe946a87f6fd4e4b8769 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Thu, 14 May 2020 05:12:56 -0500
Subject: [PATCH 09/16] net/mlx5: Disable reload while removing the device

[ Upstream commit 60904cd349abc98cb888fc28d1ca55a8e2cf87b3 ]

While unregistration is in progress, user might be reloading the
interface.
This can race with unregistration in below flow which uses the
resources which are getting disabled by reload flow.

Hence, disable the devlink reloading first when removing the device.

     CPU0                                   CPU1
     ----                                   ----
local_pci_remove()                  devlink_mutex
  remove_one()                       devlink_nl_cmd_reload()
    mlx5_unregister_device()           devlink_reload()
                                       ops->reload_down()
                                         mlx5_unload_one()

Fixes: 4383cfcc65e7 ("net/mlx5: Add devlink reload")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 2 --
 drivers/net/ethernet/mellanox/mlx5/core/main.c    | 2 ++
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index e94f0c4d74a7..a99fe4b02b9b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -283,7 +283,6 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
 		goto params_reg_err;
 	mlx5_devlink_set_params_init_values(devlink);
 	devlink_params_publish(devlink);
-	devlink_reload_enable(devlink);
 	return 0;
 
 params_reg_err:
@@ -293,7 +292,6 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
 
 void mlx5_devlink_unregister(struct devlink *devlink)
 {
-	devlink_reload_disable(devlink);
 	devlink_params_unregister(devlink, mlx5_devlink_params,
 				  ARRAY_SIZE(mlx5_devlink_params));
 	devlink_unregister(devlink);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 3b7d68df9cf2..980f6b833cbe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1373,6 +1373,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err);
 
 	pci_save_state(pdev);
+	devlink_reload_enable(devlink);
 	return 0;
 
 err_load_one:
@@ -1390,6 +1391,7 @@ static void remove_one(struct pci_dev *pdev)
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
 	struct devlink *devlink = priv_to_devlink(dev);
 
+	devlink_reload_disable(devlink);
 	mlx5_crdump_disable(dev);
 	mlx5_devlink_unregister(devlink);
 
-- 
2.26.2


From bd7652d8bc0446bf3847ba624fb3be7a9aedf8bc Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 10 Jun 2020 10:49:00 +0200
Subject: [PATCH 10/16] mptcp: don't leak msk in token container

[ Upstream commit 4b5af44129d0653a4df44e5511c7d480c61c8f3c ]

If a listening MPTCP socket has unaccepted sockets at close
time, the related msks are freed via mptcp_sock_destruct(),
which in turn does not invoke the proto->destroy() method
nor the mptcp_token_destroy() function.

Due to the above, the child msk socket is not removed from
the token container, leading to later UaF.

Address the issue explicitly removing the token even in the
above error path.

Fixes: 79c0949e9a09 ("mptcp: Add key generation and token tree")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/subflow.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 8968b2c065e7..e6feb05a93dc 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -393,6 +393,7 @@ static void mptcp_sock_destruct(struct sock *sk)
 		sock_orphan(sk);
 	}
 
+	mptcp_token_destroy(mptcp_sk(sk)->token);
 	inet_sock_destruct(sk);
 }
 
-- 
2.26.2


From 5679121a115076eced43fb8c0f2a7af77e685516 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Mon, 8 Jun 2020 20:41:43 -0700
Subject: [PATCH 11/16] ionic: wait on queue start until after IFF_UP

[ Upstream commit 976ee3b21119dcf5c6d96233d688a1453f29fa83 ]

The netif_running() test looks at __LINK_STATE_START which
gets set before ndo_open() is called, there is a window of
time between that and when the queues are actually ready to
be run.  If ionic_check_link_status() notices that the link is
up very soon after netif_running() becomes true, it might try
to run the queues before they are ready, causing all manner of
potential issues.  Since the netdev->flags IFF_UP isn't set
until after ndo_open() returns, we can wait for that before
we allow ionic_check_link_status() to start the queues.

On the way back to close, __LINK_STATE_START is cleared before
calling ndo_stop(), and IFF_UP is cleared after.  Both of
these need to be true in order to safely stop the queues
from ionic_check_link_status().

Fixes: 49d3b493673a ("ionic: disable the queues on link down")
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index f8a9c1bcffc9..7aa037c3fe02 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -105,7 +105,7 @@ static void ionic_link_status_check(struct ionic_lif *lif)
 			netif_carrier_on(netdev);
 		}
 
-		if (netif_running(lif->netdev))
+		if (lif->netdev->flags & IFF_UP && netif_running(lif->netdev))
 			ionic_start_queues(lif);
 	} else {
 		if (netif_carrier_ok(netdev)) {
@@ -113,7 +113,7 @@ static void ionic_link_status_check(struct ionic_lif *lif)
 			netif_carrier_off(netdev);
 		}
 
-		if (netif_running(lif->netdev))
+		if (lif->netdev->flags & IFF_UP && netif_running(lif->netdev))
 			ionic_stop_queues(lif);
 	}
 
-- 
2.26.2


From 927a56609e7fa3822ccef43683b9a0bc572f500f Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 10 Jun 2020 10:47:41 +0200
Subject: [PATCH 12/16] mptcp: fix races between shutdown and recvmsg

[ Upstream commit 5969856ae8ce29c9d523a1a6145cbd9e87f7046c ]

The msk sk_shutdown flag is set by a workqueue, possibly
introducing some delay in user-space notification. If the last
subflow carries some data with the fin packet, the user space
can wake-up before RCV_SHUTDOWN is set. If it executes unblocking
recvmsg(), it may return with an error instead of eof.

Address the issue explicitly checking for eof in recvmsg(), when
no data is found.

Fixes: 59832e246515 ("mptcp: subflow: check parent mptcp socket on subflow state change")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 45 +++++++++++++++++++++++---------------------
 1 file changed, 24 insertions(+), 21 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 34dd0e278a82..4bf4f629975d 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -357,6 +357,27 @@ void mptcp_subflow_eof(struct sock *sk)
 		sock_hold(sk);
 }
 
+static void mptcp_check_for_eof(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+	struct sock *sk = (struct sock *)msk;
+	int receivers = 0;
+
+	mptcp_for_each_subflow(msk, subflow)
+		receivers += !subflow->rx_eof;
+
+	if (!receivers && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
+		/* hopefully temporary hack: propagate shutdown status
+		 * to msk, when all subflows agree on it
+		 */
+		sk->sk_shutdown |= RCV_SHUTDOWN;
+
+		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
+		set_bit(MPTCP_DATA_READY, &msk->flags);
+		sk->sk_data_ready(sk);
+	}
+}
+
 static void mptcp_stop_timer(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
@@ -933,6 +954,9 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 				break;
 			}
 
+			if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
+				mptcp_check_for_eof(msk);
+
 			if (sk->sk_shutdown & RCV_SHUTDOWN)
 				break;
 
@@ -1070,27 +1094,6 @@ static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
 	return 0;
 }
 
-static void mptcp_check_for_eof(struct mptcp_sock *msk)
-{
-	struct mptcp_subflow_context *subflow;
-	struct sock *sk = (struct sock *)msk;
-	int receivers = 0;
-
-	mptcp_for_each_subflow(msk, subflow)
-		receivers += !subflow->rx_eof;
-
-	if (!receivers && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
-		/* hopefully temporary hack: propagate shutdown status
-		 * to msk, when all subflows agree on it
-		 */
-		sk->sk_shutdown |= RCV_SHUTDOWN;
-
-		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
-		set_bit(MPTCP_DATA_READY, &msk->flags);
-		sk->sk_data_ready(sk);
-	}
-}
-
 static void mptcp_worker(struct work_struct *work)
 {
 	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
-- 
2.26.2


From 2a90c5fa9fa8b3e6e4e011009d8a4dc719eac616 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Sat, 13 Jun 2020 17:54:14 +0300
Subject: [PATCH 13/16] net: ethernet: ti: ale: fix allmulti for nu type ale

[ Upstream commit bc139119a1708ae3db1ebb379630f286e28d06e8 ]

On AM65xx MCU CPSW2G NUSS and 66AK2E/L NUSS allmulti setting does not allow
unregistered mcast packets to pass.

This happens, because ALE VLAN entries on these SoCs do not contain port
masks for reg/unreg mcast packets, but instead store indexes of
ALE_VLAN_MASK_MUXx_REG registers which intended for store port masks for
reg/unreg mcast packets.
This path was missed by commit 9d1f6447274f ("net: ethernet: ti: ale: fix
seeing unreg mcast packets with promisc and allmulti disabled").

Hence, fix it by taking into account ALE type in cpsw_ale_set_allmulti().

Fixes: 9d1f6447274f ("net: ethernet: ti: ale: fix seeing unreg mcast packets with promisc and allmulti disabled")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw_ale.c | 49 ++++++++++++++++++++++++------
 1 file changed, 40 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index 8dc6be11b2ff..9ad872bfae3a 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -604,10 +604,44 @@ void cpsw_ale_set_unreg_mcast(struct cpsw_ale *ale, int unreg_mcast_mask,
 	}
 }
 
+static void cpsw_ale_vlan_set_unreg_mcast(struct cpsw_ale *ale, u32 *ale_entry,
+					  int allmulti)
+{
+	int unreg_mcast;
+
+	unreg_mcast =
+		cpsw_ale_get_vlan_unreg_mcast(ale_entry,
+					      ale->vlan_field_bits);
+	if (allmulti)
+		unreg_mcast |= ALE_PORT_HOST;
+	else
+		unreg_mcast &= ~ALE_PORT_HOST;
+	cpsw_ale_set_vlan_unreg_mcast(ale_entry, unreg_mcast,
+				      ale->vlan_field_bits);
+}
+
+static void
+cpsw_ale_vlan_set_unreg_mcast_idx(struct cpsw_ale *ale, u32 *ale_entry,
+				  int allmulti)
+{
+	int unreg_mcast;
+	int idx;
+
+	idx = cpsw_ale_get_vlan_unreg_mcast_idx(ale_entry);
+
+	unreg_mcast = readl(ale->params.ale_regs + ALE_VLAN_MASK_MUX(idx));
+
+	if (allmulti)
+		unreg_mcast |= ALE_PORT_HOST;
+	else
+		unreg_mcast &= ~ALE_PORT_HOST;
+
+	writel(unreg_mcast, ale->params.ale_regs + ALE_VLAN_MASK_MUX(idx));
+}
+
 void cpsw_ale_set_allmulti(struct cpsw_ale *ale, int allmulti, int port)
 {
 	u32 ale_entry[ALE_ENTRY_WORDS];
-	int unreg_mcast = 0;
 	int type, idx;
 
 	for (idx = 0; idx < ale->params.ale_entries; idx++) {
@@ -624,15 +658,12 @@ void cpsw_ale_set_allmulti(struct cpsw_ale *ale, int allmulti, int port)
 		if (port != -1 && !(vlan_members & BIT(port)))
 			continue;
 
-		unreg_mcast =
-			cpsw_ale_get_vlan_unreg_mcast(ale_entry,
-						      ale->vlan_field_bits);
-		if (allmulti)
-			unreg_mcast |= ALE_PORT_HOST;
+		if (!ale->params.nu_switch_ale)
+			cpsw_ale_vlan_set_unreg_mcast(ale, ale_entry, allmulti);
 		else
-			unreg_mcast &= ~ALE_PORT_HOST;
-		cpsw_ale_set_vlan_unreg_mcast(ale_entry, unreg_mcast,
-					      ale->vlan_field_bits);
+			cpsw_ale_vlan_set_unreg_mcast_idx(ale, ale_entry,
+							  allmulti);
+
 		cpsw_ale_write(ale, idx, ale_entry);
 	}
 }
-- 
2.26.2


From 1ce4852a085afd271e3f56fb3b5ccd68fe01a4be Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Sat, 13 Jun 2020 17:52:59 +0300
Subject: [PATCH 14/16] net: ethernet: ti: am65-cpsw-nuss: fix ale parameters
 init

[ Upstream commit 2074f9eaa58795a99e9da61c10f93180f810cfd6 ]

The ALE parameters structure is created on stack, so it has to be reset
before passing to cpsw_ale_create() to avoid garbage values.

Fixes: 93a76530316a ("net: ethernet: ti: introduce am65x/j721e gigabit eth subsystem driver")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 88f52a2f85b3..3e4388e6b5fa 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -1804,7 +1804,7 @@ MODULE_DEVICE_TABLE(of, am65_cpsw_nuss_of_mtable);
 
 static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 {
-	struct cpsw_ale_params ale_params;
+	struct cpsw_ale_params ale_params = { 0 };
 	const struct of_device_id *of_id;
 	struct device *dev = &pdev->dev;
 	struct am65_cpsw_common *common;
-- 
2.26.2


From 1a08dc2c655f61654965d88230abbdafed9bbc95 Mon Sep 17 00:00:00 2001
From: Valentin Longchamp <valentin@longchamp.me>
Date: Tue, 9 Jun 2020 22:11:54 +0200
Subject: [PATCH 15/16] net: sched: export __netdev_watchdog_up()

[ Upstream commit 1a3db27ad9a72d033235b9673653962c02e3486e ]

Since the quiesce/activate rework, __netdev_watchdog_up() is directly
called in the ucc_geth driver.

Unfortunately, this function is not available for modules and thus
ucc_geth cannot be built as a module anymore. Fix it by exporting
__netdev_watchdog_up().

Since the commit introducing the regression was backported to stable
branches, this one should ideally be as well.

Fixes: 79dde73cf9bc ("net/ethernet/freescale: rework quiesce/activate for ucc_geth")
Signed-off-by: Valentin Longchamp <valentin@longchamp.me>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 2efd5b61acef..9763da6daa9f 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -464,6 +464,7 @@ void __netdev_watchdog_up(struct net_device *dev)
 			dev_hold(dev);
 	}
 }
+EXPORT_SYMBOL_GPL(__netdev_watchdog_up);
 
 static void dev_watchdog_up(struct net_device *dev)
 {
-- 
2.26.2


From 92942dd74d997710ba130616ad13a1d5fe5a3315 Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Sun, 7 Jun 2020 15:40:40 +0000
Subject: [PATCH 16/16] net/mlx5e: CT: Fix ipv6 nat header rewrite actions

[ Upstream commit 0d156f2deda8675c29fa2b8b5ed9b374370e47f2 ]

Set the ipv6 word fields according to the hardware definitions.

Fixes: ac991b48d43c ("net/mlx5e: CT: Offload established flows")
Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/tc_ct.c   | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index 4eb305af0106..153d6eb19d3c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -320,21 +320,21 @@ mlx5_tc_ct_parse_mangle_to_mod_act(struct flow_action_entry *act,
 
 	case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
 		MLX5_SET(set_action_in, modact, length, 0);
-		if (offset == offsetof(struct ipv6hdr, saddr))
+		if (offset == offsetof(struct ipv6hdr, saddr) + 12)
 			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0;
-		else if (offset == offsetof(struct ipv6hdr, saddr) + 4)
-			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32;
 		else if (offset == offsetof(struct ipv6hdr, saddr) + 8)
+			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32;
+		else if (offset == offsetof(struct ipv6hdr, saddr) + 4)
 			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64;
-		else if (offset == offsetof(struct ipv6hdr, saddr) + 12)
+		else if (offset == offsetof(struct ipv6hdr, saddr))
 			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96;
-		else if (offset == offsetof(struct ipv6hdr, daddr))
+		else if (offset == offsetof(struct ipv6hdr, daddr) + 12)
 			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0;
-		else if (offset == offsetof(struct ipv6hdr, daddr) + 4)
-			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32;
 		else if (offset == offsetof(struct ipv6hdr, daddr) + 8)
+			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32;
+		else if (offset == offsetof(struct ipv6hdr, daddr) + 4)
 			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64;
-		else if (offset == offsetof(struct ipv6hdr, daddr) + 12)
+		else if (offset == offsetof(struct ipv6hdr, daddr))
 			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96;
 		else
 			return -EOPNOTSUPP;
-- 
2.26.2