[PATCH AUTOSEL 5.4 01/73] cgroup-v1: cgroup_pidlist_next should update position index

[PATCH AUTOSEL 5.4 01/73] cgroup-v1: cgroup_pidlist_next should update position index

[Sasha Levin]

From: Vasily Averin <vvs@virtuozzo.com>

[ Upstream commit db8dd9697238be70a6b4f9d0284cd89f59c0e070 ]

if seq_file .next fuction does not change position index,
read after some lseek can generate unexpected output.

 # mount | grep cgroup
 # dd if=/mnt/cgroup.procs bs=1  # normal output
...
1294
1295
1296
1304
1382
584+0 records in
584+0 records out
584 bytes copied

dd: /mnt/cgroup.procs: cannot skip to specified offset
83  <<< generates end of last line
1383  <<< ... and whole last line once again
0+1 records in
0+1 records out
8 bytes copied

dd: /mnt/cgroup.procs: cannot skip to specified offset
1386  <<< generates last line anyway
0+1 records in
0+1 records out
5 bytes copied

https://bugzilla.kernel.org/show_bug.cgi?id=206283
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/cgroup/cgroup-v1.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 7f83f4121d8d0..2db582706ec5c 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -473,6 +473,7 @@ static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
 	 */
 	p++;
 	if (p >= end) {
+		(*pos)++;
 		return NULL;
 	} else {
 		*pos = *p;
-- 
2.20.1

[PATCH AUTOSEL 5.4 02/73] cgroup: Iterate tasks that did not finish do_exit()

[Sasha Levin]

From: Michal Koutný <mkoutny@suse.com>

[ Upstream commit 9c974c77246460fa6a92c18554c3311c8c83c160 ]

PF_EXITING is set earlier than actual removal from css_set when a task
is exitting. This can confuse cgroup.procs readers who see no PF_EXITING
tasks, however, rmdir is checking against css_set membership so it can
transitionally fail with EBUSY.

Fix this by listing tasks that weren't unlinked from css_set active
lists.
It may happen that other users of the task iterator (without
CSS_TASK_ITER_PROCS) spot a PF_EXITING task before cgroup_exit(). This
is equal to the state before commit c03cd7738a83 ("cgroup: Include dying
leaders with live threads in PROCS iterations") but it may be reviewed
later.

Reported-by: Suren Baghdasaryan <surenb@google.com>
Fixes: c03cd7738a83 ("cgroup: Include dying leaders with live threads in PROCS iterations")
Signed-off-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/cgroup.h |  1 +
 kernel/cgroup/cgroup.c | 23 ++++++++++++++++-------
 2 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 3ba3e6da13a6f..57577075d2049 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -62,6 +62,7 @@ struct css_task_iter {
 	struct list_head		*mg_tasks_head;
 	struct list_head		*dying_tasks_head;
 
+	struct list_head		*cur_tasks_head;
 	struct css_set			*cur_cset;
 	struct css_set			*cur_dcset;
 	struct task_struct		*cur_task;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 595c52d59f310..a1236b1b80383 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -4461,12 +4461,16 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
 		}
 	} while (!css_set_populated(cset) && list_empty(&cset->dying_tasks));
 
-	if (!list_empty(&cset->tasks))
+	if (!list_empty(&cset->tasks)) {
 		it->task_pos = cset->tasks.next;
-	else if (!list_empty(&cset->mg_tasks))
+		it->cur_tasks_head = &cset->tasks;
+	} else if (!list_empty(&cset->mg_tasks)) {
 		it->task_pos = cset->mg_tasks.next;
-	else
+		it->cur_tasks_head = &cset->mg_tasks;
+	} else {
 		it->task_pos = cset->dying_tasks.next;
+		it->cur_tasks_head = &cset->dying_tasks;
+	}
 
 	it->tasks_head = &cset->tasks;
 	it->mg_tasks_head = &cset->mg_tasks;
@@ -4524,10 +4528,14 @@ static void css_task_iter_advance(struct css_task_iter *it)
 		else
 			it->task_pos = it->task_pos->next;
 
-		if (it->task_pos == it->tasks_head)
+		if (it->task_pos == it->tasks_head) {
 			it->task_pos = it->mg_tasks_head->next;
-		if (it->task_pos == it->mg_tasks_head)
+			it->cur_tasks_head = it->mg_tasks_head;
+		}
+		if (it->task_pos == it->mg_tasks_head) {
 			it->task_pos = it->dying_tasks_head->next;
+			it->cur_tasks_head = it->dying_tasks_head;
+		}
 		if (it->task_pos == it->dying_tasks_head)
 			css_task_iter_advance_css_set(it);
 	} else {
@@ -4546,11 +4554,12 @@ static void css_task_iter_advance(struct css_task_iter *it)
 			goto repeat;
 
 		/* and dying leaders w/o live member threads */
-		if (!atomic_read(&task->signal->live))
+		if (it->cur_tasks_head == it->dying_tasks_head &&
+		    !atomic_read(&task->signal->live))
 			goto repeat;
 	} else {
 		/* skip all dying ones */
-		if (task->flags & PF_EXITING)
+		if (it->cur_tasks_head == it->dying_tasks_head)
 			goto repeat;
 	}
 }
-- 
2.20.1

[PATCH AUTOSEL 5.4 03/73] clk: imx8mn: Fix incorrect clock defines

[Sasha Levin]

From: Anson Huang <Anson.Huang@nxp.com>

[ Upstream commit 5eb40257047fb11085d582b7b9ccd0bffe900726 ]

IMX8MN_CLK_I2C4 and IMX8MN_CLK_UART1's index definitions are incorrect,
fix them.

Fixes: 1e80936a42e1 ("dt-bindings: imx: Add clock binding doc for i.MX8MN")
Signed-off-by: Anson Huang <Anson.Huang@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/dt-bindings/clock/imx8mn-clock.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/dt-bindings/clock/imx8mn-clock.h b/include/dt-bindings/clock/imx8mn-clock.h
index d7b201652f4cd..0c7c750fc2c41 100644
--- a/include/dt-bindings/clock/imx8mn-clock.h
+++ b/include/dt-bindings/clock/imx8mn-clock.h
@@ -122,8 +122,8 @@
 #define IMX8MN_CLK_I2C1				105
 #define IMX8MN_CLK_I2C2				106
 #define IMX8MN_CLK_I2C3				107
-#define IMX8MN_CLK_I2C4				118
-#define IMX8MN_CLK_UART1			119
+#define IMX8MN_CLK_I2C4				108
+#define IMX8MN_CLK_UART1			109
 #define IMX8MN_CLK_UART2			110
 #define IMX8MN_CLK_UART3			111
 #define IMX8MN_CLK_UART4			112
-- 
2.20.1

[PATCH AUTOSEL 5.4 04/73] batman-adv: Don't schedule OGM for disabled interface

[Sasha Levin]

From: Sven Eckelmann <sven@narfation.org>

[ Upstream commit 8e8ce08198de193e3d21d42e96945216e3d9ac7f ]

A transmission scheduling for an interface which is currently dropped by
batadv_iv_ogm_iface_disable could still be in progress. The B.A.T.M.A.N. V
is simply cancelling the workqueue item in an synchronous way but this is
not possible with B.A.T.M.A.N. IV because the OGM submissions are
intertwined.

Instead it has to stop submitting the OGM when it detect that the buffer
pointer is set to NULL.

Reported-by: syzbot+a98f2016f40b9cd3818a@syzkaller.appspotmail.com
Reported-by: syzbot+ac36b6a33c28a491e929@syzkaller.appspotmail.com
Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Cc: Hillf Danton <hdanton@sina.com>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/batman-adv/bat_iv_ogm.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 5b0b20e6da956..d88a4de022372 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -789,6 +789,10 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface)
 
 	lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex);
 
+	/* interface already disabled by batadv_iv_ogm_iface_disable */
+	if (!*ogm_buff)
+		return;
+
 	/* the interface gets activated here to avoid race conditions between
 	 * the moment of activating the interface in
 	 * hardif_activate_interface() where the originator mac is set and
-- 
2.20.1

[PATCH AUTOSEL 5.4 05/73] pinctrl: meson-gxl: fix GPIOX sdio pins

[Sasha Levin]

From: Nicolas Belin <nbelin@baylibre.com>

[ Upstream commit dc7a06b0dbbafac8623c2b7657e61362f2f479a7 ]

In the gxl driver, the sdio cmd and clk pins are inverted. It has not caused
any issue so far because devices using these pins always take both pins
so the resulting configuration is OK.

Fixes: 0f15f500ff2c ("pinctrl: meson: Add GXL pinctrl definitions")
Reviewed-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Nicolas Belin <nbelin@baylibre.com>
Link: https://lore.kernel.org/r/1582204512-7582-1-git-send-email-nbelin@baylibre.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/pinctrl/meson/pinctrl-meson-gxl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxl.c b/drivers/pinctrl/meson/pinctrl-meson-gxl.c
index 72c5373c8dc1e..e8d1f3050487f 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-gxl.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-gxl.c
@@ -147,8 +147,8 @@ static const unsigned int sdio_d0_pins[]	= { GPIOX_0 };
 static const unsigned int sdio_d1_pins[]	= { GPIOX_1 };
 static const unsigned int sdio_d2_pins[]	= { GPIOX_2 };
 static const unsigned int sdio_d3_pins[]	= { GPIOX_3 };
-static const unsigned int sdio_cmd_pins[]	= { GPIOX_4 };
-static const unsigned int sdio_clk_pins[]	= { GPIOX_5 };
+static const unsigned int sdio_clk_pins[]	= { GPIOX_4 };
+static const unsigned int sdio_cmd_pins[]	= { GPIOX_5 };
 static const unsigned int sdio_irq_pins[]	= { GPIOX_7 };
 
 static const unsigned int nand_ce0_pins[]	= { BOOT_8 };
-- 
2.20.1

[PATCH AUTOSEL 5.4 06/73] pinctrl: imx: scu: Align imx sc msg structs to 4

[Sasha Levin]

From: Leonard Crestez <leonard.crestez@nxp.com>

[ Upstream commit 4c48e549f39f8ed10cf8a0b6cb96f5eddf0391ce ]

The imx SC api strongly assumes that messages are composed out of
4-bytes words but some of our message structs have odd sizeofs.

This produces many oopses with CONFIG_KASAN=y.

Fix by marking with __aligned(4).

Fixes: b96eea718bf6 ("pinctrl: fsl: add scu based pinctrl support")
Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
Link: https://lore.kernel.org/r/bd7ad5fd755739a6d8d5f4f65e03b3ca4f457bd2.1582216144.git.leonard.crestez@nxp.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/pinctrl/freescale/pinctrl-scu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/freescale/pinctrl-scu.c b/drivers/pinctrl/freescale/pinctrl-scu.c
index 73bf1d9f9cc6f..23cf04bdfc55d 100644
--- a/drivers/pinctrl/freescale/pinctrl-scu.c
+++ b/drivers/pinctrl/freescale/pinctrl-scu.c
@@ -23,12 +23,12 @@ struct imx_sc_msg_req_pad_set {
 	struct imx_sc_rpc_msg hdr;
 	u32 val;
 	u16 pad;
-} __packed;
+} __packed __aligned(4);
 
 struct imx_sc_msg_req_pad_get {
 	struct imx_sc_rpc_msg hdr;
 	u16 pad;
-} __packed;
+} __packed __aligned(4);
 
 struct imx_sc_msg_resp_pad_get {
 	struct imx_sc_rpc_msg hdr;
-- 
2.20.1

[PATCH AUTOSEL 5.4 07/73] nfs: add minor version to nfs_server_key for fscache

[Sasha Levin]

From: Scott Mayhew <smayhew@redhat.com>

[ Upstream commit 55dee1bc0d72877b99805e42e0205087e98b9edd ]

An NFS client that mounts multiple exports from the same NFS
server with higher NFSv4 versions disabled (i.e. 4.2) and without
forcing a specific NFS version results in fscache index cookie
collisions and the following messages:
[  570.004348] FS-Cache: Duplicate cookie detected

Each nfs_client structure should have its own fscache index cookie,
so add the minorversion to nfs_server_key.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=200145
Signed-off-by: Scott Mayhew <smayhew@redhat.com>
Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/nfs/client.c     | 1 +
 fs/nfs/fscache.c    | 2 ++
 fs/nfs/nfs4client.c | 1 -
 3 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 30838304a0bf2..a05f77f9c21ed 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -153,6 +153,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 	if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL)
 		goto error_0;
 
+	clp->cl_minorversion = cl_init->minorversion;
 	clp->cl_nfs_mod = cl_init->nfs_mod;
 	if (!try_module_get(clp->cl_nfs_mod->owner))
 		goto error_dealloc;
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 3800ab6f08fa8..a6dcc2151e779 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -31,6 +31,7 @@ static DEFINE_SPINLOCK(nfs_fscache_keys_lock);
 struct nfs_server_key {
 	struct {
 		uint16_t	nfsversion;		/* NFS protocol version */
+		uint32_t	minorversion;		/* NFSv4 minor version */
 		uint16_t	family;			/* address family */
 		__be16		port;			/* IP port */
 	} hdr;
@@ -55,6 +56,7 @@ void nfs_fscache_get_client_cookie(struct nfs_client *clp)
 
 	memset(&key, 0, sizeof(key));
 	key.hdr.nfsversion = clp->rpc_ops->version;
+	key.hdr.minorversion = clp->cl_minorversion;
 	key.hdr.family = clp->cl_addr.ss_family;
 
 	switch (clp->cl_addr.ss_family) {
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index da6204025a2db..914feab64702c 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -216,7 +216,6 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
 	INIT_LIST_HEAD(&clp->cl_ds_clients);
 	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
 	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
-	clp->cl_minorversion = cl_init->minorversion;
 	clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
 	clp->cl_mig_gen = 1;
 #if IS_ENABLED(CONFIG_NFS_V4_1)
-- 
2.20.1

[PATCH AUTOSEL 5.4 08/73] pinctrl: core: Remove extra kref_get which blocks hogs being freed

[Sasha Levin]

From: Charles Keepax <ckeepax@opensource.cirrus.com>

[ Upstream commit aafd56fc79041bf36f97712d4b35208cbe07db90 ]

kref_init starts with the reference count at 1, which will be balanced
by the pinctrl_put in pinctrl_unregister. The additional kref_get in
pinctrl_claim_hogs will increase this count to 2 and cause the hogs to
not get freed when pinctrl_unregister is called.

Fixes: 6118714275f0 ("pinctrl: core: Fix pinctrl_register_and_init() with pinctrl_enable()")
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20200228154142.13860-1-ckeepax@opensource.cirrus.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/pinctrl/core.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 2bbd8ee935075..6381745e3bb18 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -2025,7 +2025,6 @@ static int pinctrl_claim_hogs(struct pinctrl_dev *pctldev)
 		return PTR_ERR(pctldev->p);
 	}
 
-	kref_get(&pctldev->p->users);
 	pctldev->hog_default =
 		pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT);
 	if (IS_ERR(pctldev->hog_default)) {
-- 
2.20.1

[PATCH AUTOSEL 5.4 09/73] r8152: check disconnect status after long sleep

[Sasha Levin]

From: You-Sheng Yang <vicamo.yang@canonical.com>

[ Upstream commit d64c7a08034b32c285e576208ae44fc3ba3fa7df ]

Dell USB Type C docking WD19/WD19DC attaches additional peripherals as:

  /: Bus 02.Port 1: Dev 1, Class=root_hub, Driver=xhci_hcd/6p, 5000M
      |__ Port 1: Dev 11, If 0, Class=Hub, Driver=hub/4p, 5000M
          |__ Port 3: Dev 12, If 0, Class=Hub, Driver=hub/4p, 5000M
          |__ Port 4: Dev 13, If 0, Class=Vendor Specific Class,
              Driver=r8152, 5000M

where usb 2-1-3 is a hub connecting all USB Type-A/C ports on the dock.

When hotplugging such dock with additional usb devices already attached on
it, the probing process may reset usb 2.1 port, therefore r8152 ethernet
device is also reset. However, during r8152 device init there are several
for-loops that, when it's unable to retrieve hardware registers due to
being disconnected from USB, may take up to 14 seconds each in practice,
and that has to be completed before USB may re-enumerate devices on the
bus. As a result, devices attached to the dock will only be available
after nearly 1 minute after the dock was plugged in:

  [ 216.388290] [250] r8152 2-1.4:1.0: usb_probe_interface
  [ 216.388292] [250] r8152 2-1.4:1.0: usb_probe_interface - got id
  [ 258.830410] r8152 2-1.4:1.0 (unnamed net_device) (uninitialized): PHY not ready
  [ 258.830460] r8152 2-1.4:1.0 (unnamed net_device) (uninitialized): Invalid header when reading pass-thru MAC addr
  [ 258.830464] r8152 2-1.4:1.0 (unnamed net_device) (uninitialized): Get ether addr fail

This happens in, for example, r8153_init:

  static int generic_ocp_read(struct r8152 *tp, u16 index, u16 size,
			    void *data, u16 type)
  {
    if (test_bit(RTL8152_UNPLUG, &tp->flags))
      return -ENODEV;
    ...
  }

  static u16 ocp_read_word(struct r8152 *tp, u16 type, u16 index)
  {
    u32 data;
    ...
    generic_ocp_read(tp, index, sizeof(tmp), &tmp, type | byen);

    data = __le32_to_cpu(tmp);
    ...
    return (u16)data;
  }

  static void r8153_init(struct r8152 *tp)
  {
    ...
    if (test_bit(RTL8152_UNPLUG, &tp->flags))
      return;

    for (i = 0; i < 500; i++) {
      if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) &
          AUTOLOAD_DONE)
        break;
      msleep(20);
    }
    ...
  }

Since ocp_read_word() doesn't check the return status of
generic_ocp_read(), and the only exit condition for the loop is to have
a match in the returned value, such loops will only ends after exceeding
its maximum runs when the device has been marked as disconnected, which
takes 500 * 20ms = 10 seconds in theory, 14 in practice.

To solve this long latency another test to RTL8152_UNPLUG flag should be
added after those 20ms sleep to skip unnecessary loops, so that the device
probe can complete early and proceed to parent port reset/reprobe process.

This can be reproduced on all kernel versions up to latest v5.6-rc2, but
after v5.5-rc7 the reproduce rate is dramatically lowered to 1/30 or less
while it was around 1/2.

Signed-off-by: You-Sheng Yang <vicamo.yang@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/usb/r8152.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 6912624eed4ad..44ea5dcc43fd1 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3006,6 +3006,8 @@ static u16 r8153_phy_status(struct r8152 *tp, u16 desired)
 		}
 
 		msleep(20);
+		if (test_bit(RTL8152_UNPLUG, &tp->flags))
+			break;
 	}
 
 	return data;
@@ -4419,7 +4421,10 @@ static void r8153_init(struct r8152 *tp)
 		if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) &
 		    AUTOLOAD_DONE)
 			break;
+
 		msleep(20);
+		if (test_bit(RTL8152_UNPLUG, &tp->flags))
+			break;
 	}
 
 	data = r8153_phy_status(tp, 0);
@@ -4545,7 +4550,10 @@ static void r8153b_init(struct r8152 *tp)
 		if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) &
 		    AUTOLOAD_DONE)
 			break;
+
 		msleep(20);
+		if (test_bit(RTL8152_UNPLUG, &tp->flags))
+			break;
 	}
 
 	data = r8153_phy_status(tp, 0);
-- 
2.20.1

[PATCH AUTOSEL 5.4 10/73] net: dsa: mv88e6xxx: fix lockup on warm boot

[Sasha Levin]

From: Russell King <rmk+kernel@armlinux.org.uk>

[ Upstream commit 0395823b8d9a4d87bd1bf74359123461c2ae801b ]

If the switch is not hardware reset on a warm boot, interrupts can be
left enabled, and possibly pending. This will cause us to enter an
infinite loop trying to service an interrupt we are unable to handle,
thereby preventing the kernel from booting.

Ensure that the global 2 interrupt sources are disabled before we claim
the parent interrupt.

Observed on the ZII development revision B and C platforms with
reworked serdes support, and using reboot -f to reboot the platform.

Fixes: dc30c35be720 ("net: dsa: mv88e6xxx: Implement interrupt support.")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/dsa/mv88e6xxx/global2.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c
index bdbb72fc20ede..6240976679e1e 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.c
+++ b/drivers/net/dsa/mv88e6xxx/global2.c
@@ -1083,6 +1083,13 @@ int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip)
 {
 	int err, irq, virq;
 
+	chip->g2_irq.masked = ~0;
+	mv88e6xxx_reg_lock(chip);
+	err = mv88e6xxx_g2_int_mask(chip, ~chip->g2_irq.masked);
+	mv88e6xxx_reg_unlock(chip);
+	if (err)
+		return err;
+
 	chip->g2_irq.domain = irq_domain_add_simple(
 		chip->dev->of_node, 16, 0, &mv88e6xxx_g2_irq_domain_ops, chip);
 	if (!chip->g2_irq.domain)
@@ -1092,7 +1099,6 @@ int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip)
 		irq_create_mapping(chip->g2_irq.domain, irq);
 
 	chip->g2_irq.chip = mv88e6xxx_g2_irq_chip;
-	chip->g2_irq.masked = ~0;
 
 	chip->device_irq = irq_find_mapping(chip->g1_irq.domain,
 					    MV88E6XXX_G1_STS_IRQ_DEVICE);
-- 
2.20.1

[PATCH AUTOSEL 5.4 11/73] net: phy: avoid clearing PHY interrupts twice in irq handler

[Sasha Levin]

From: Heiner Kallweit <hkallweit1@gmail.com>

[ Upstream commit 249bc9744e165abe74ae326f43e9d70bad54c3b7 ]

On all PHY drivers that implement did_interrupt() reading the interrupt
status bits clears them. This means we may loose an interrupt that
is triggered between calling did_interrupt() and phy_clear_interrupt().
As part of the fix make it a requirement that did_interrupt() clears
the interrupt.

The Fixes tag refers to the first commit where the patch applies
cleanly.

Fixes: 49644e68f472 ("net: phy: add callback for custom interrupt handler to struct phy_driver")
Reported-by: Michael Walle <michael@walle.cc>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/phy/phy.c | 3 ++-
 include/linux/phy.h   | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 105d389b58e74..ea890d802ffe5 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -761,7 +761,8 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat)
 		phy_trigger_machine(phydev);
 	}
 
-	if (phy_clear_interrupt(phydev))
+	/* did_interrupt() may have cleared the interrupt already */
+	if (!phydev->drv->did_interrupt && phy_clear_interrupt(phydev))
 		goto phy_err;
 	return IRQ_HANDLED;
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3d5d53313e6c0..bf87c59a98bb3 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -524,6 +524,7 @@ struct phy_driver {
 	/*
 	 * Checks if the PHY generated an interrupt.
 	 * For multi-PHY devices with shared PHY interrupt pin
+	 * Set interrupt bits have to be cleared.
 	 */
 	int (*did_interrupt)(struct phy_device *phydev);
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 12/73] bnxt_en: reinitialize IRQs when MTU is modified

[Sasha Levin]

From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>

[ Upstream commit a9b952d267e59a3b405e644930f46d252cea7122 ]

MTU changes may affect the number of IRQs so we must call
bnxt_close_nic()/bnxt_open_nic() with the irq_re_init parameter
set to true.  The reason is that a larger MTU may require
aggregation rings not needed with smaller MTU.  We may not be
able to allocate the required number of aggregation rings and
so we reduce the number of channels which will change the number
of IRQs.  Without this patch, it may crash eventually in
pci_disable_msix() when the IRQs are not properly unwound.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@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 | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 374e11a91790b..57c88e157f866 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10891,13 +10891,13 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu)
 	struct bnxt *bp = netdev_priv(dev);
 
 	if (netif_running(dev))
-		bnxt_close_nic(bp, false, false);
+		bnxt_close_nic(bp, true, false);
 
 	dev->mtu = new_mtu;
 	bnxt_set_ring_params(bp);
 
 	if (netif_running(dev))
-		return bnxt_open_nic(bp, false, false);
+		return bnxt_open_nic(bp, true, false);
 
 	return 0;
 }
-- 
2.20.1

[PATCH AUTOSEL 5.4 13/73] bnxt_en: fix error handling when flashing from file

[Sasha Levin]

From: Edwin Peer <edwin.peer@broadcom.com>

[ Upstream commit 22630e28f9c2b55abd217869cc0696def89f2284 ]

After bnxt_hwrm_do_send_message() was updated to return standard error
codes in a recent commit, a regression in bnxt_flash_package_from_file()
was introduced.  The return value does not properly reflect all
possible firmware errors when calling firmware to flash the package.

Fix it by consolidating all errors in one local variable rc instead
of having 2 variables for different errors.

Fixes: d4f1420d3656 ("bnxt_en: Convert error code in firmware message response to standard code.")
Signed-off-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>
---
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 24 +++++++++----------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index ece70f61c89a2..cfa647d5b44db 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2005,8 +2005,8 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 	struct hwrm_nvm_install_update_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_nvm_install_update_input install = {0};
 	const struct firmware *fw;
-	int rc, hwrm_err = 0;
 	u32 item_len;
+	int rc = 0;
 	u16 index;
 
 	bnxt_hwrm_fw_set_time(bp);
@@ -2050,15 +2050,14 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 			memcpy(kmem, fw->data, fw->size);
 			modify.host_src_addr = cpu_to_le64(dma_handle);
 
-			hwrm_err = hwrm_send_message(bp, &modify,
-						     sizeof(modify),
-						     FLASH_PACKAGE_TIMEOUT);
+			rc = hwrm_send_message(bp, &modify, sizeof(modify),
+					       FLASH_PACKAGE_TIMEOUT);
 			dma_free_coherent(&bp->pdev->dev, fw->size, kmem,
 					  dma_handle);
 		}
 	}
 	release_firmware(fw);
-	if (rc || hwrm_err)
+	if (rc)
 		goto err_exit;
 
 	if ((install_type & 0xffff) == 0)
@@ -2067,20 +2066,19 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 	install.install_type = cpu_to_le32(install_type);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
-	hwrm_err = _hwrm_send_message(bp, &install, sizeof(install),
-				      INSTALL_PACKAGE_TIMEOUT);
-	if (hwrm_err) {
+	rc = _hwrm_send_message(bp, &install, sizeof(install),
+				INSTALL_PACKAGE_TIMEOUT);
+	if (rc) {
 		u8 error_code = ((struct hwrm_err_output *)resp)->cmd_err;
 
 		if (resp->error_code && error_code ==
 		    NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) {
 			install.flags |= cpu_to_le16(
 			       NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG);
-			hwrm_err = _hwrm_send_message(bp, &install,
-						      sizeof(install),
-						      INSTALL_PACKAGE_TIMEOUT);
+			rc = _hwrm_send_message(bp, &install, sizeof(install),
+						INSTALL_PACKAGE_TIMEOUT);
 		}
-		if (hwrm_err)
+		if (rc)
 			goto flash_pkg_exit;
 	}
 
@@ -2092,7 +2090,7 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 flash_pkg_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 err_exit:
-	if (hwrm_err == -EACCES)
+	if (rc == -EACCES)
 		bnxt_print_admin_err(bp);
 	return rc;
 }
-- 
2.20.1

[PATCH AUTOSEL 5.4 14/73] cpupower: avoid multiple definition with gcc -fno-common

[Sasha Levin]

From: Mike Gilbert <floppym@gentoo.org>

[ Upstream commit 2de7fb60a4740135e03cf55c1982e393ccb87b6b ]

Building cpupower with -fno-common in CFLAGS results in errors due to
multiple definitions of the 'cpu_count' and 'start_time' variables.

./utils/idle_monitor/snb_idle.o:./utils/idle_monitor/cpupower-monitor.h:28:
multiple definition of `cpu_count';
./utils/idle_monitor/nhm_idle.o:./utils/idle_monitor/cpupower-monitor.h:28:
first defined here
...
./utils/idle_monitor/cpuidle_sysfs.o:./utils/idle_monitor/cpuidle_sysfs.c:22:
multiple definition of `start_time';
./utils/idle_monitor/amd_fam14h_idle.o:./utils/idle_monitor/amd_fam14h_idle.c:85:
first defined here

The -fno-common option will be enabled by default in GCC 10.

Bug: https://bugs.gentoo.org/707462
Signed-off-by: Mike Gilbert <floppym@gentoo.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c  | 2 +-
 tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c    | 2 +-
 tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c | 2 ++
 tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h | 2 +-
 4 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
index 3f893b99b337c..555cb338a71a4 100644
--- a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
@@ -82,7 +82,7 @@ static struct pci_access *pci_acc;
 static struct pci_dev *amd_fam14h_pci_dev;
 static int nbp1_entered;
 
-struct timespec start_time;
+static struct timespec start_time;
 static unsigned long long timediff;
 
 #ifdef DEBUG
diff --git a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
index f634aeb65c5f6..7fb4f7a291ad5 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
+++ b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
@@ -19,7 +19,7 @@ struct cpuidle_monitor cpuidle_sysfs_monitor;
 
 static unsigned long long **previous_count;
 static unsigned long long **current_count;
-struct timespec start_time;
+static struct timespec start_time;
 static unsigned long long timediff;
 
 static int cpuidle_get_count_percent(unsigned int id, double *percent,
diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
index d3c3e6e7aa26c..3d54fd4336261 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
+++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
@@ -27,6 +27,8 @@ struct cpuidle_monitor *all_monitors[] = {
 0
 };
 
+int cpu_count;
+
 static struct cpuidle_monitor *monitors[MONITORS_MAX];
 static unsigned int avail_monitors;
 
diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
index a2d901d3bfaf9..eafef38f1982e 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
+++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
@@ -25,7 +25,7 @@
 #endif
 #define CSTATE_DESC_LEN 60
 
-int cpu_count;
+extern int cpu_count;
 
 /* Hard to define the right names ...: */
 enum power_range_e {
-- 
2.20.1

[PATCH AUTOSEL 5.4 15/73] fib: add missing attribute validation for tun_id

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit 4c16d64ea04056f1b1b324ab6916019f6a064114 ]

Add missing netlink policy entry for FRA_TUN_ID.

Fixes: e7030878fc84 ("fib: Add fib rule match on tunnel id")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/fib_rules.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 20dcadd8eed94..7fed3193f81d4 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -108,6 +108,7 @@ struct fib_rule_notifier_info {
 	[FRA_OIFNAME]	= { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \
 	[FRA_PRIORITY]	= { .type = NLA_U32 }, \
 	[FRA_FWMARK]	= { .type = NLA_U32 }, \
+	[FRA_TUN_ID]	= { .type = NLA_U64 }, \
 	[FRA_FWMASK]	= { .type = NLA_U32 }, \
 	[FRA_TABLE]     = { .type = NLA_U32 }, \
 	[FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \
-- 
2.20.1

[PATCH AUTOSEL 5.4 16/73] can: add missing attribute validation for termination

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit ab02ad660586b94f5d08912a3952b939cf4c4430 ]

Add missing attribute validation for IFLA_CAN_TERMINATION
to the netlink policy.

Fixes: 12a6075cabc0 ("can: dev: add CAN interface termination API")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/can/dev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 1c88c361938cc..3a33fb5034005 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -884,6 +884,7 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = {
 				= { .len = sizeof(struct can_bittiming) },
 	[IFLA_CAN_DATA_BITTIMING_CONST]
 				= { .len = sizeof(struct can_bittiming_const) },
+	[IFLA_CAN_TERMINATION]	= { .type = NLA_U16 },
 };
 
 static int can_validate(struct nlattr *tb[], struct nlattr *data[],
-- 
2.20.1

[PATCH AUTOSEL 5.4 17/73] macsec: add missing attribute validation for port

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit 31d9a1c524964bac77b7f9d0a1ac140dc6b57461 ]

Add missing attribute validation for IFLA_MACSEC_PORT
to the netlink policy.

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/macsec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index afd8b2a082454..9dbe218eed1da 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -2977,6 +2977,7 @@ static const struct device_type macsec_type = {
 
 static const struct nla_policy macsec_rtnl_policy[IFLA_MACSEC_MAX + 1] = {
 	[IFLA_MACSEC_SCI] = { .type = NLA_U64 },
+	[IFLA_MACSEC_PORT] = { .type = NLA_U16 },
 	[IFLA_MACSEC_ICV_LEN] = { .type = NLA_U8 },
 	[IFLA_MACSEC_CIPHER_SUITE] = { .type = NLA_U64 },
 	[IFLA_MACSEC_WINDOW] = { .type = NLA_U32 },
-- 
2.20.1

[PATCH AUTOSEL 5.4 18/73] team: add missing attribute validation for port ifindex

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit dd25cb272ccce4db67dc8509278229099e4f5e99 ]

Add missing attribute validation for TEAM_ATTR_OPTION_PORT_IFINDEX
to the netlink policy.

Fixes: 80f7c6683fe0 ("team: add support for per-port options")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/team/team.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index ca70a1d840eb3..44dd26a62a6d3 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2240,6 +2240,7 @@ team_nl_option_policy[TEAM_ATTR_OPTION_MAX + 1] = {
 	[TEAM_ATTR_OPTION_CHANGED]		= { .type = NLA_FLAG },
 	[TEAM_ATTR_OPTION_TYPE]			= { .type = NLA_U8 },
 	[TEAM_ATTR_OPTION_DATA]			= { .type = NLA_BINARY },
+	[TEAM_ATTR_OPTION_PORT_IFINDEX]		= { .type = NLA_U32 },
 };
 
 static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info)
-- 
2.20.1

[PATCH AUTOSEL 5.4 19/73] team: add missing attribute validation for array index

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit 669fcd7795900cd1880237cbbb57a7db66cb9ac8 ]

Add missing attribute validation for TEAM_ATTR_OPTION_ARRAY_INDEX
to the netlink policy.

Fixes: b13033262d24 ("team: introduce array options")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/team/team.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 44dd26a62a6d3..4004f98e50d9f 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2241,6 +2241,7 @@ team_nl_option_policy[TEAM_ATTR_OPTION_MAX + 1] = {
 	[TEAM_ATTR_OPTION_TYPE]			= { .type = NLA_U8 },
 	[TEAM_ATTR_OPTION_DATA]			= { .type = NLA_BINARY },
 	[TEAM_ATTR_OPTION_PORT_IFINDEX]		= { .type = NLA_U32 },
+	[TEAM_ATTR_OPTION_ARRAY_INDEX]		= { .type = NLA_U32 },
 };
 
 static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info)
-- 
2.20.1

[PATCH AUTOSEL 5.4 20/73] netfilter: cthelper: add missing attribute validation for cthelper

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit c049b3450072b8e3998053490e025839fecfef31 ]

Add missing attribute validation for cthelper
to the netlink policy.

Fixes: 12f7a505331e ("netfilter: add user-space connection tracking helper infrastructure")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nfnetlink_cthelper.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 7525063c25f5f..60838d5fb8e06 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -742,6 +742,8 @@ static const struct nla_policy nfnl_cthelper_policy[NFCTH_MAX+1] = {
 	[NFCTH_NAME] = { .type = NLA_NUL_STRING,
 			 .len = NF_CT_HELPER_NAME_LEN-1 },
 	[NFCTH_QUEUE_NUM] = { .type = NLA_U32, },
+	[NFCTH_PRIV_DATA_LEN] = { .type = NLA_U32, },
+	[NFCTH_STATUS] = { .type = NLA_U32, },
 };
 
 static const struct nfnl_callback nfnl_cthelper_cb[NFNL_MSG_CTHELPER_MAX] = {
-- 
2.20.1

[PATCH AUTOSEL 5.4 21/73] netfilter: nft_payload: add missing attribute validation for payload csum flags

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit 9d6effb2f1523eb84516e44213c00f2fd9e6afff ]

Add missing attribute validation for NFTA_PAYLOAD_CSUM_FLAGS
to the netlink policy.

Fixes: 1814096980bb ("netfilter: nft_payload: layer 4 checksum adjustment for pseudoheader fields")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nft_payload.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 5cb2d8908d2a5..0e3bfbc26e790 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -121,6 +121,7 @@ static const struct nla_policy nft_payload_policy[NFTA_PAYLOAD_MAX + 1] = {
 	[NFTA_PAYLOAD_LEN]		= { .type = NLA_U32 },
 	[NFTA_PAYLOAD_CSUM_TYPE]	= { .type = NLA_U32 },
 	[NFTA_PAYLOAD_CSUM_OFFSET]	= { .type = NLA_U32 },
+	[NFTA_PAYLOAD_CSUM_FLAGS]	= { .type = NLA_U32 },
 };
 
 static int nft_payload_init(const struct nft_ctx *ctx,
-- 
2.20.1

[PATCH AUTOSEL 5.4 22/73] netfilter: nft_tunnel: add missing attribute validation for tunnels

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit 88a637719a1570705c02cacb3297af164b1714e7 ]

Add missing attribute validation for tunnel source and
destination ports to the netlink policy.

Fixes: af308b94a2a4 ("netfilter: nf_tables: add tunnel support")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nft_tunnel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 037e8fce9b30e..1effd4878619f 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -339,6 +339,8 @@ static const struct nla_policy nft_tunnel_key_policy[NFTA_TUNNEL_KEY_MAX + 1] =
 	[NFTA_TUNNEL_KEY_FLAGS]	= { .type = NLA_U32, },
 	[NFTA_TUNNEL_KEY_TOS]	= { .type = NLA_U8, },
 	[NFTA_TUNNEL_KEY_TTL]	= { .type = NLA_U8, },
+	[NFTA_TUNNEL_KEY_SPORT]	= { .type = NLA_U16, },
+	[NFTA_TUNNEL_KEY_DPORT]	= { .type = NLA_U16, },
 	[NFTA_TUNNEL_KEY_OPTS]	= { .type = NLA_NESTED, },
 };
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 23/73] net: phy: bcm63xx: fix OOPS due to missing driver name

[Sasha Levin]

From: Jonas Gorski <jonas.gorski@gmail.com>

[ Upstream commit 43de81b0601df7d7988d3f5617ee0987df65c883 ]

719655a14971 ("net: phy: Replace phy driver features u32 with link_mode
bitmap") was a bit over-eager and also removed the second phy driver's
name, resulting in a nasty OOPS on registration:

[    1.319854] CPU 0 Unable to handle kernel paging request at virtual address 00000000, epc == 804dd50c, ra == 804dd4f0
[    1.330859] Oops[#1]:
[    1.333138] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.4.22 #0
[    1.339217] $ 0   : 00000000 00000001 87ca7f00 805c1874
[    1.344590] $ 4   : 00000000 00000047 00585000 8701f800
[    1.349965] $ 8   : 8701f800 804f4a5c 00000003 64726976
[    1.355341] $12   : 00000001 00000000 00000000 00000114
[    1.360718] $16   : 87ca7f80 00000000 00000000 80639fe4
[    1.366093] $20   : 00000002 00000000 806441d0 80b90000
[    1.371470] $24   : 00000000 00000000
[    1.376847] $28   : 87c1e000 87c1fda0 80b90000 804dd4f0
[    1.382224] Hi    : d1c8f8da
[    1.385180] Lo    : 5518a480
[    1.388182] epc   : 804dd50c kset_find_obj+0x3c/0x114
[    1.393345] ra    : 804dd4f0 kset_find_obj+0x20/0x114
[    1.398530] Status: 10008703 KERNEL EXL IE
[    1.402833] Cause : 00800008 (ExcCode 02)
[    1.406952] BadVA : 00000000
[    1.409913] PrId  : 0002a075 (Broadcom BMIPS4350)
[    1.414745] Modules linked in:
[    1.417895] Process swapper/0 (pid: 1, threadinfo=(ptrval), task=(ptrval), tls=00000000)
[    1.426214] Stack : 87cec000 80630000 80639370 80640658 80640000 80049af4 80639fe4 8063a0d8
[    1.434816]         8063a0d8 802ef078 00000002 00000000 806441d0 80b90000 8063a0d8 802ef114
[    1.443417]         87cea0de 87c1fde0 00000000 804de488 87cea000 8063a0d8 8063a0d8 80334e48
[    1.452018]         80640000 8063984c 80639bf4 00000000 8065de48 00000001 8063a0d8 80334ed0
[    1.460620]         806441d0 80b90000 80b90000 802ef164 8065dd70 80620000 80b90000 8065de58
[    1.469222]         ...
[    1.471734] Call Trace:
[    1.474255] [<804dd50c>] kset_find_obj+0x3c/0x114
[    1.479141] [<802ef078>] driver_find+0x1c/0x44
[    1.483665] [<802ef114>] driver_register+0x74/0x148
[    1.488719] [<80334e48>] phy_driver_register+0x9c/0xd0
[    1.493968] [<80334ed0>] phy_drivers_register+0x54/0xe8
[    1.499345] [<8001061c>] do_one_initcall+0x7c/0x1f4
[    1.504374] [<80644ed8>] kernel_init_freeable+0x1d4/0x2b4
[    1.509940] [<804f4e24>] kernel_init+0x10/0xf8
[    1.514502] [<80018e68>] ret_from_kernel_thread+0x14/0x1c
[    1.520040] Code: 1060000c  02202025  90650000 <90810000> 24630001  14250004  24840001  14a0fffb  90650000
[    1.530061]
[    1.531698] ---[ end trace d52f1717cd29bdc8 ]---

Fix it by readding the name.

Fixes: 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap")
Signed-off-by: Jonas Gorski <jonas.gorski@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/phy/bcm63xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c
index 23f1958ba6ad4..459fb2069c7e0 100644
--- a/drivers/net/phy/bcm63xx.c
+++ b/drivers/net/phy/bcm63xx.c
@@ -73,6 +73,7 @@ static struct phy_driver bcm63xx_driver[] = {
 	/* same phy as above, with just a different OUI */
 	.phy_id		= 0x002bdc00,
 	.phy_id_mask	= 0xfffffc00,
+	.name		= "Broadcom BCM63XX (2)",
 	/* PHY_BASIC_FEATURES */
 	.flags		= PHY_IS_INTERNAL,
 	.config_init	= bcm63xx_config_init,
-- 
2.20.1

[PATCH AUTOSEL 5.4 24/73] drivers/of/of_mdio.c:fix of_mdiobus_register()

[Sasha Levin]

From: Dajun Jin <adajunjin@gmail.com>

[ Upstream commit 209c65b61d94344522c41a83cd6ce51aac5fd0a4 ]

When registers a phy_device successful, should terminate the loop
or the phy_device would be registered in other addr. If there are
multiple PHYs without reg properties, it will go wrong.

Signed-off-by: Dajun Jin <adajunjin@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/of/of_mdio.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index bd6129db64178..c34a6df712adb 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -268,6 +268,7 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 				rc = of_mdiobus_register_phy(mdio, child, addr);
 				if (rc && rc != -ENODEV)
 					goto unregister;
+				break;
 			}
 		}
 	}
-- 
2.20.1

[PATCH AUTOSEL 5.4 25/73] cgroup1: don't call release_agent when it is ""

[Sasha Levin]

From: Tycho Andersen <tycho@tycho.ws>

[ Upstream commit 2e5383d7904e60529136727e49629a82058a5607 ]

Older (and maybe current) versions of systemd set release_agent to "" when
shutting down, but do not set notify_on_release to 0.

Since 64e90a8acb85 ("Introduce STATIC_USERMODEHELPER to mediate
call_usermodehelper()"), we filter out such calls when the user mode helper
path is "". However, when used in conjunction with an actual (i.e. non "")
STATIC_USERMODEHELPER, the path is never "", so the real usermode helper
will be called with argv[0] == "".

Let's avoid this by not invoking the release_agent when it is "".

Signed-off-by: Tycho Andersen <tycho@tycho.ws>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/cgroup/cgroup-v1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 2db582706ec5c..f684c82efc2ea 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -784,7 +784,7 @@ void cgroup1_release_agent(struct work_struct *work)
 
 	pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
 	agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
-	if (!pathbuf || !agentbuf)
+	if (!pathbuf || !agentbuf || !strlen(agentbuf))
 		goto out;
 
 	spin_lock_irq(&css_set_lock);
-- 
2.20.1

[PATCH AUTOSEL 5.4 26/73] netfilter: nf_tables: dump NFTA_CHAIN_FLAGS attribute

[Sasha Levin]

From: Pablo Neira Ayuso <pablo@netfilter.org>

[ Upstream commit d78008de6103c708171baff9650a7862645d23b0 ]

Missing NFTA_CHAIN_FLAGS netlink attribute when dumping basechain
definitions.

Fixes: c9626a2cbdb2 ("netfilter: nf_tables: add hardware offload support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nf_tables_api.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 23544842b6923..bd76ef77c03f5 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1309,6 +1309,11 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
 					      lockdep_commit_lock_is_held(net));
 		if (nft_dump_stats(skb, stats))
 			goto nla_put_failure;
+
+		if ((chain->flags & NFT_CHAIN_HW_OFFLOAD) &&
+		    nla_put_be32(skb, NFTA_CHAIN_FLAGS,
+				 htonl(NFT_CHAIN_HW_OFFLOAD)))
+			goto nla_put_failure;
 	}
 
 	if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use)))
-- 
2.20.1

[PATCH AUTOSEL 5.4 27/73] netfilter: nf_tables: fix infinite loop when expr is not available

[Sasha Levin]

From: Florian Westphal <fw@strlen.de>

[ Upstream commit 1d305ba40eb8081ff21eeb8ca6ba5c70fd920934 ]

nft will loop forever if the kernel doesn't support an expression:

1. nft_expr_type_get() appends the family specific name to the module list.
2. -EAGAIN is returned to nfnetlink, nfnetlink calls abort path.
3. abort path sets ->done to true and calls request_module for the
   expression.
4. nfnetlink replays the batch, we end up in nft_expr_type_get() again.
5. nft_expr_type_get attempts to append family-specific name. This
   one already exists on the list, so we continue
6. nft_expr_type_get adds the generic expression name to the module
   list. -EAGAIN is returned, nfnetlink calls abort path.
7. abort path encounters the family-specific expression which
   has 'done' set, so it gets removed.
8. abort path requests the generic expression name, sets done to true.
9. batch is replayed.

If the expression could not be loaded, then we will end up back at 1),
because the family-specific name got removed and the cycle starts again.

Note that userspace can SIGKILL the nft process to stop the cycle, but
the desired behaviour is to return an error after the generic expr name
fails to load the expression.

Fixes: eb014de4fd418 ("netfilter: nf_tables: autoload modules from the abort path")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nf_tables_api.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index bd76ef77c03f5..068daff41f6e6 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6975,13 +6975,8 @@ static void nf_tables_module_autoload(struct net *net)
 	list_splice_init(&net->nft.module_list, &module_list);
 	mutex_unlock(&net->nft.commit_mutex);
 	list_for_each_entry_safe(req, next, &module_list, list) {
-		if (req->done) {
-			list_del(&req->list);
-			kfree(req);
-		} else {
-			request_module("%s", req->module);
-			req->done = true;
-		}
+		request_module("%s", req->module);
+		req->done = true;
 	}
 	mutex_lock(&net->nft.commit_mutex);
 	list_splice(&module_list, &net->nft.module_list);
@@ -7764,6 +7759,7 @@ static void __net_exit nf_tables_exit_net(struct net *net)
 	__nft_release_tables(net);
 	mutex_unlock(&net->nft.commit_mutex);
 	WARN_ON_ONCE(!list_empty(&net->nft.tables));
+	WARN_ON_ONCE(!list_empty(&net->nft.module_list));
 }
 
 static struct pernet_operations nf_tables_net_ops = {
-- 
2.20.1

[PATCH AUTOSEL 5.4 28/73] slip: make slhc_compress() more robust against malicious packets

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit 110a40dfb708fe940a3f3704d470e431c368d256 ]

Before accessing various fields in IPV4 network header
and TCP header, make sure the packet :

- Has IP version 4 (ip->version == 4)
- Has not a silly network length (ip->ihl >= 5)
- Is big enough to hold network and transport headers
- Has not a silly TCP header size (th->doff >= sizeof(struct tcphdr) / 4)

syzbot reported :

BUG: KMSAN: uninit-value in slhc_compress+0x5b9/0x2e60 drivers/net/slip/slhc.c:270
CPU: 0 PID: 11728 Comm: syz-executor231 Not tainted 5.6.0-rc2-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 slhc_compress+0x5b9/0x2e60 drivers/net/slip/slhc.c:270
 ppp_send_frame drivers/net/ppp/ppp_generic.c:1637 [inline]
 __ppp_xmit_process+0x1902/0x2970 drivers/net/ppp/ppp_generic.c:1495
 ppp_xmit_process+0x147/0x2f0 drivers/net/ppp/ppp_generic.c:1516
 ppp_write+0x6bb/0x790 drivers/net/ppp/ppp_generic.c:512
 do_loop_readv_writev fs/read_write.c:717 [inline]
 do_iter_write+0x812/0xdc0 fs/read_write.c:1000
 compat_writev+0x2df/0x5a0 fs/read_write.c:1351
 do_compat_pwritev64 fs/read_write.c:1400 [inline]
 __do_compat_sys_pwritev fs/read_write.c:1420 [inline]
 __se_compat_sys_pwritev fs/read_write.c:1414 [inline]
 __ia32_compat_sys_pwritev+0x349/0x3f0 fs/read_write.c:1414
 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline]
 do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410
 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139
RIP: 0023:0xf7f7cd99
Code: 90 e8 0b 00 00 00 f3 90 0f ae e8 eb f9 8d 74 26 00 89 3c 24 c3 90 90 90 90 90 90 90 90 90 90 90 90 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 eb 0d 90 90 90 90 90 90 90 90 90 90 90 90
RSP: 002b:00000000ffdb84ac EFLAGS: 00000217 ORIG_RAX: 000000000000014e
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00000000200001c0
RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000000000000003
RBP: 0000000040047459 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82
 slab_alloc_node mm/slub.c:2793 [inline]
 __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4401
 __kmalloc_reserve net/core/skbuff.c:142 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:210
 alloc_skb include/linux/skbuff.h:1051 [inline]
 ppp_write+0x115/0x790 drivers/net/ppp/ppp_generic.c:500
 do_loop_readv_writev fs/read_write.c:717 [inline]
 do_iter_write+0x812/0xdc0 fs/read_write.c:1000
 compat_writev+0x2df/0x5a0 fs/read_write.c:1351
 do_compat_pwritev64 fs/read_write.c:1400 [inline]
 __do_compat_sys_pwritev fs/read_write.c:1420 [inline]
 __se_compat_sys_pwritev fs/read_write.c:1414 [inline]
 __ia32_compat_sys_pwritev+0x349/0x3f0 fs/read_write.c:1414
 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline]
 do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410
 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139

Fixes: b5451d783ade ("slip: Move the SLIP drivers")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/slip/slhc.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index 58a69f830d29b..f78ceba42e57e 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -232,7 +232,7 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize,
 	struct cstate *cs = lcs->next;
 	unsigned long deltaS, deltaA;
 	short changes = 0;
-	int hlen;
+	int nlen, hlen;
 	unsigned char new_seq[16];
 	unsigned char *cp = new_seq;
 	struct iphdr *ip;
@@ -248,6 +248,8 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize,
 		return isize;
 
 	ip = (struct iphdr *) icp;
+	if (ip->version != 4 || ip->ihl < 5)
+		return isize;
 
 	/* Bail if this packet isn't TCP, or is an IP fragment */
 	if (ip->protocol != IPPROTO_TCP || (ntohs(ip->frag_off) & 0x3fff)) {
@@ -258,10 +260,14 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize,
 			comp->sls_o_tcp++;
 		return isize;
 	}
-	/* Extract TCP header */
+	nlen = ip->ihl * 4;
+	if (isize < nlen + sizeof(*th))
+		return isize;
 
-	th = (struct tcphdr *)(((unsigned char *)ip) + ip->ihl*4);
-	hlen = ip->ihl*4 + th->doff*4;
+	th = (struct tcphdr *)(icp + nlen);
+	if (th->doff < sizeof(struct tcphdr) / 4)
+		return isize;
+	hlen = nlen + th->doff * 4;
 
 	/*  Bail if the TCP packet isn't `compressible' (i.e., ACK isn't set or
 	 *  some other control bit is set). Also uncompressible if
-- 
2.20.1

[PATCH AUTOSEL 5.4 29/73] net: hns3: fix a not link up issue when fibre port supports autoneg

[Sasha Levin]

From: Jian Shen <shenjian15@huawei.com>

[ Upstream commit 68e1006f618e509fc7869259fe83ceec4a95dac3 ]

When fibre port supports auto-negotiation, the IMP(Intelligent
Management Process) processes the speed of auto-negotiation
and the  user's speed separately.
For below case, the port will get a not link up problem.
step 1: disables auto-negotiation and sets speed to A, then
the driver's MAC speed will be updated to A.
step 2: enables auto-negotiation and MAC gets negotiated
speed B, then the driver's MAC speed will be updated to B
through querying in periodical task.
step 3: MAC gets new negotiated speed A.
step 4: disables auto-negotiation and sets speed to B before
periodical task query new MAC speed A, the driver will  ignore
the speed configuration.

This patch fixes it by skipping speed and duplex checking when
fibre port supports auto-negotiation.

Fixes: 22f48e24a23d ("net: hns3: add autoneg and change speed support for fibre port")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index c01cf8ef69df9..d4652dea4569b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2417,10 +2417,12 @@ static int hclge_cfg_mac_speed_dup_hw(struct hclge_dev *hdev, int speed,
 
 int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex)
 {
+	struct hclge_mac *mac = &hdev->hw.mac;
 	int ret;
 
 	duplex = hclge_check_speed_dup(duplex, speed);
-	if (hdev->hw.mac.speed == speed && hdev->hw.mac.duplex == duplex)
+	if (!mac->support_autoneg && mac->speed == speed &&
+	    mac->duplex == duplex)
 		return 0;
 
 	ret = hclge_cfg_mac_speed_dup_hw(hdev, speed, duplex);
-- 
2.20.1

[PATCH AUTOSEL 5.4 30/73] futex: Fix inode life-time issue

[Sasha Levin]

From: Peter Zijlstra <peterz@infradead.org>

[ Upstream commit 8019ad13ef7f64be44d4f892af9c840179009254 ]

As reported by Jann, ihold() does not in fact guarantee inode
persistence. And instead of making it so, replace the usage of inode
pointers with a per boot, machine wide, unique inode identifier.

This sequence number is global, but shared (file backed) futexes are
rare enough that this should not become a performance issue.

Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/inode.c            |  1 +
 include/linux/fs.h    |  1 +
 include/linux/futex.h | 17 +++++----
 kernel/futex.c        | 89 ++++++++++++++++++++++++++-----------------
 4 files changed, 65 insertions(+), 43 deletions(-)

diff --git a/fs/inode.c b/fs/inode.c
index 96d62d97694ef..c5267a4db0f5e 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -137,6 +137,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_sb = sb;
 	inode->i_blkbits = sb->s_blocksize_bits;
 	inode->i_flags = 0;
+	atomic64_set(&inode->i_sequence, 0);
 	atomic_set(&inode->i_count, 1);
 	inode->i_op = &empty_iops;
 	inode->i_fop = &no_open_fops;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0b4d8fc79e0f3..06668379109e3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -698,6 +698,7 @@ struct inode {
 		struct rcu_head		i_rcu;
 	};
 	atomic64_t		i_version;
+	atomic64_t		i_sequence; /* see futex */
 	atomic_t		i_count;
 	atomic_t		i_dio_count;
 	atomic_t		i_writecount;
diff --git a/include/linux/futex.h b/include/linux/futex.h
index 5cc3fed27d4c2..b70df27d7e85c 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -31,23 +31,26 @@ struct task_struct;
 
 union futex_key {
 	struct {
+		u64 i_seq;
 		unsigned long pgoff;
-		struct inode *inode;
-		int offset;
+		unsigned int offset;
 	} shared;
 	struct {
+		union {
+			struct mm_struct *mm;
+			u64 __tmp;
+		};
 		unsigned long address;
-		struct mm_struct *mm;
-		int offset;
+		unsigned int offset;
 	} private;
 	struct {
+		u64 ptr;
 		unsigned long word;
-		void *ptr;
-		int offset;
+		unsigned int offset;
 	} both;
 };
 
-#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } }
+#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = 0ULL } }
 
 #ifdef CONFIG_FUTEX
 enum {
diff --git a/kernel/futex.c b/kernel/futex.c
index afbf928d6a6b0..07ab324885ac0 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -429,7 +429,7 @@ static void get_futex_key_refs(union futex_key *key)
 
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
-		ihold(key->shared.inode); /* implies smp_mb(); (B) */
+		smp_mb();		/* explicit smp_mb(); (B) */
 		break;
 	case FUT_OFF_MMSHARED:
 		futex_get_mm(key); /* implies smp_mb(); (B) */
@@ -463,7 +463,6 @@ static void drop_futex_key_refs(union futex_key *key)
 
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
-		iput(key->shared.inode);
 		break;
 	case FUT_OFF_MMSHARED:
 		mmdrop(key->private.mm);
@@ -505,6 +504,46 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout,
 	return timeout;
 }
 
+/*
+ * Generate a machine wide unique identifier for this inode.
+ *
+ * This relies on u64 not wrapping in the life-time of the machine; which with
+ * 1ns resolution means almost 585 years.
+ *
+ * This further relies on the fact that a well formed program will not unmap
+ * the file while it has a (shared) futex waiting on it. This mapping will have
+ * a file reference which pins the mount and inode.
+ *
+ * If for some reason an inode gets evicted and read back in again, it will get
+ * a new sequence number and will _NOT_ match, even though it is the exact same
+ * file.
+ *
+ * It is important that match_futex() will never have a false-positive, esp.
+ * for PI futexes that can mess up the state. The above argues that false-negatives
+ * are only possible for malformed programs.
+ */
+static u64 get_inode_sequence_number(struct inode *inode)
+{
+	static atomic64_t i_seq;
+	u64 old;
+
+	/* Does the inode already have a sequence number? */
+	old = atomic64_read(&inode->i_sequence);
+	if (likely(old))
+		return old;
+
+	for (;;) {
+		u64 new = atomic64_add_return(1, &i_seq);
+		if (WARN_ON_ONCE(!new))
+			continue;
+
+		old = atomic64_cmpxchg_relaxed(&inode->i_sequence, 0, new);
+		if (old)
+			return old;
+		return new;
+	}
+}
+
 /**
  * get_futex_key() - Get parameters which are the keys for a futex
  * @uaddr:	virtual address of the futex
@@ -517,9 +556,15 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout,
  *
  * The key words are stored in @key on success.
  *
- * For shared mappings, it's (page->index, file_inode(vma->vm_file),
- * offset_within_page).  For private mappings, it's (uaddr, current->mm).
- * We can usually work out the index without swapping in the page.
+ * For shared mappings (when @fshared), the key is:
+ *   ( inode->i_sequence, page->index, offset_within_page )
+ * [ also see get_inode_sequence_number() ]
+ *
+ * For private mappings (or when !@fshared), the key is:
+ *   ( current->mm, address, 0 )
+ *
+ * This allows (cross process, where applicable) identification of the futex
+ * without keeping the page pinned for the duration of the FUTEX_WAIT.
  *
  * lock_page() might sleep, the caller should not hold a spinlock.
  */
@@ -659,8 +704,6 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, enum futex_a
 		key->private.mm = mm;
 		key->private.address = address;
 
-		get_futex_key_refs(key); /* implies smp_mb(); (B) */
-
 	} else {
 		struct inode *inode;
 
@@ -692,40 +735,14 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, enum futex_a
 			goto again;
 		}
 
-		/*
-		 * Take a reference unless it is about to be freed. Previously
-		 * this reference was taken by ihold under the page lock
-		 * pinning the inode in place so i_lock was unnecessary. The
-		 * only way for this check to fail is if the inode was
-		 * truncated in parallel which is almost certainly an
-		 * application bug. In such a case, just retry.
-		 *
-		 * We are not calling into get_futex_key_refs() in file-backed
-		 * cases, therefore a successful atomic_inc return below will
-		 * guarantee that get_futex_key() will still imply smp_mb(); (B).
-		 */
-		if (!atomic_inc_not_zero(&inode->i_count)) {
-			rcu_read_unlock();
-			put_page(page);
-
-			goto again;
-		}
-
-		/* Should be impossible but lets be paranoid for now */
-		if (WARN_ON_ONCE(inode->i_mapping != mapping)) {
-			err = -EFAULT;
-			rcu_read_unlock();
-			iput(inode);
-
-			goto out;
-		}
-
 		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
-		key->shared.inode = inode;
+		key->shared.i_seq = get_inode_sequence_number(inode);
 		key->shared.pgoff = basepage_index(tail);
 		rcu_read_unlock();
 	}
 
+	get_futex_key_refs(key); /* implies smp_mb(); (B) */
+
 out:
 	put_page(page);
 	return err;
-- 
2.20.1

Re: [PATCH AUTOSEL 5.4 30/73] futex: Fix inode life-time issue

[Jann Horn]

On Wed, Mar 18, 2020 at 9:54 PM Sasha Levin <sashal@kernel.org> wrote:
>
> From: Peter Zijlstra <peterz@infradead.org>
>
> [ Upstream commit 8019ad13ef7f64be44d4f892af9c840179009254 ]
>
> As reported by Jann, ihold() does not in fact guarantee inode
> persistence. And instead of making it so, replace the usage of inode
> pointers with a per boot, machine wide, unique inode identifier.
>
> This sequence number is global, but shared (file backed) futexes are
> rare enough that this should not become a performance issue.

Please also take this patch, together with
8d67743653dce5a0e7aa500fcccb237cde7ad88e "futex: Unbreak futex
hashing", into the older stable branches. This has to go all the way
back; as far as I can tell, the bug already existed at the beginning
of git history.

Re: [PATCH AUTOSEL 5.4 30/73] futex: Fix inode life-time issue

[Greg Kroah-Hartman]

On Mon, Mar 23, 2020 at 08:18:04PM +0100, Jann Horn wrote:
> On Wed, Mar 18, 2020 at 9:54 PM Sasha Levin <sashal@kernel.org> wrote:
> >
> > From: Peter Zijlstra <peterz@infradead.org>
> >
> > [ Upstream commit 8019ad13ef7f64be44d4f892af9c840179009254 ]
> >
> > As reported by Jann, ihold() does not in fact guarantee inode
> > persistence. And instead of making it so, replace the usage of inode
> > pointers with a per boot, machine wide, unique inode identifier.
> >
> > This sequence number is global, but shared (file backed) futexes are
> > rare enough that this should not become a performance issue.
> 
> Please also take this patch, together with
> 8d67743653dce5a0e7aa500fcccb237cde7ad88e "futex: Unbreak futex
> hashing", into the older stable branches. This has to go all the way
> back; as far as I can tell, the bug already existed at the beginning
> of git history.

I have queued these up now, thanks for the hint.

greg k-h

backport request for 3.16 [was: Re: [PATCH AUTOSEL 5.4 30/73] futex: Fix inode life-time issue]

[Jann Horn]

@Ben: You'll probably also want to take these two into the next 3.16 release.

Sorry, I forgot that 3.16 has a different maintainer...

On Mon, Mar 23, 2020 at 8:18 PM Jann Horn <jannh@google.com> wrote:
>
> On Wed, Mar 18, 2020 at 9:54 PM Sasha Levin <sashal@kernel.org> wrote:
> >
> > From: Peter Zijlstra <peterz@infradead.org>
> >
> > [ Upstream commit 8019ad13ef7f64be44d4f892af9c840179009254 ]
> >
> > As reported by Jann, ihold() does not in fact guarantee inode
> > persistence. And instead of making it so, replace the usage of inode
> > pointers with a per boot, machine wide, unique inode identifier.
> >
> > This sequence number is global, but shared (file backed) futexes are
> > rare enough that this should not become a performance issue.
>
> Please also take this patch, together with
> 8d67743653dce5a0e7aa500fcccb237cde7ad88e "futex: Unbreak futex
> hashing", into the older stable branches. This has to go all the way
> back; as far as I can tell, the bug already existed at the beginning
> of git history.

[PATCH AUTOSEL 5.4 31/73] netfilter: nft_chain_nat: inet family is missing module ownership

[Sasha Levin]

From: Pablo Neira Ayuso <pablo@netfilter.org>

[ Upstream commit 6a42cefb25d8bdc1b391f4a53c78c32164eea2dd ]

Set owner to THIS_MODULE, otherwise the nft_chain_nat module might be
removed while there are still inet/nat chains in place.

[  117.942096] BUG: unable to handle page fault for address: ffffffffa0d5e040
[  117.942101] #PF: supervisor read access in kernel mode
[  117.942103] #PF: error_code(0x0000) - not-present page
[  117.942106] PGD 200c067 P4D 200c067 PUD 200d063 PMD 3dc909067 PTE 0
[  117.942113] Oops: 0000 [#1] PREEMPT SMP PTI
[  117.942118] CPU: 3 PID: 27 Comm: kworker/3:0 Not tainted 5.6.0-rc3+ #348
[  117.942133] Workqueue: events nf_tables_trans_destroy_work [nf_tables]
[  117.942145] RIP: 0010:nf_tables_chain_destroy.isra.0+0x94/0x15a [nf_tables]
[  117.942149] Code: f6 45 54 01 0f 84 d1 00 00 00 80 3b 05 74 44 48 8b 75 e8 48 c7 c7 72 be de a0 e8 56 e6 2d e0 48 8b 45 e8 48 c7 c7 7f be de a0 <48> 8b 30 e8 43 e6 2d e0 48 8b 45 e8 48 8b 40 10 48 85 c0 74 5b 8b
[  117.942152] RSP: 0018:ffffc9000015be10 EFLAGS: 00010292
[  117.942155] RAX: ffffffffa0d5e040 RBX: ffff88840be87fc2 RCX: 0000000000000007
[  117.942158] RDX: 0000000000000007 RSI: 0000000000000086 RDI: ffffffffa0debe7f
[  117.942160] RBP: ffff888403b54b50 R08: 0000000000001482 R09: 0000000000000004
[  117.942162] R10: 0000000000000000 R11: 0000000000000001 R12: ffff8883eda7e540
[  117.942164] R13: dead000000000122 R14: dead000000000100 R15: ffff888403b3db80
[  117.942167] FS:  0000000000000000(0000) GS:ffff88840e4c0000(0000) knlGS:0000000000000000
[  117.942169] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  117.942172] CR2: ffffffffa0d5e040 CR3: 00000003e4c52002 CR4: 00000000001606e0
[  117.942174] Call Trace:
[  117.942188]  nf_tables_trans_destroy_work.cold+0xd/0x12 [nf_tables]
[  117.942196]  process_one_work+0x1d6/0x3b0
[  117.942200]  worker_thread+0x45/0x3c0
[  117.942203]  ? process_one_work+0x3b0/0x3b0
[  117.942210]  kthread+0x112/0x130
[  117.942214]  ? kthread_create_worker_on_cpu+0x40/0x40
[  117.942221]  ret_from_fork+0x35/0x40

nf_tables_chain_destroy() crashes on module_put() because the module is
gone.

Fixes: d164385ec572 ("netfilter: nat: add inet family nat support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nft_chain_nat.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c
index ff9ac8ae0031f..eac4a901233f2 100644
--- a/net/netfilter/nft_chain_nat.c
+++ b/net/netfilter/nft_chain_nat.c
@@ -89,6 +89,7 @@ static const struct nft_chain_type nft_chain_nat_inet = {
 	.name		= "nat",
 	.type		= NFT_CHAIN_T_NAT,
 	.family		= NFPROTO_INET,
+	.owner		= THIS_MODULE,
 	.hook_mask	= (1 << NF_INET_PRE_ROUTING) |
 			  (1 << NF_INET_LOCAL_IN) |
 			  (1 << NF_INET_LOCAL_OUT) |
-- 
2.20.1

[PATCH AUTOSEL 5.4 32/73] dt-bindings: net: FMan erratum A050385

[Sasha Levin]

From: Madalin Bucur <madalin.bucur@nxp.com>

[ Upstream commit 26d5bb9e4c4b541c475751e015072eb2cbf70d15 ]

FMAN DMA read or writes under heavy traffic load may cause FMAN
internal resource leak; thus stopping further packet processing.

The FMAN internal queue can overflow when FMAN splits single
read or write transactions into multiple smaller transactions
such that more than 17 AXI transactions are in flight from FMAN
to interconnect. When the FMAN internal queue overflows, it can
stall further packet processing. The issue can occur with any one
of the following three conditions:

  1. FMAN AXI transaction crosses 4K address boundary (Errata
     A010022)
  2. FMAN DMA address for an AXI transaction is not 16 byte
     aligned, i.e. the last 4 bits of an address are non-zero
  3. Scatter Gather (SG) frames have more than one SG buffer in
     the SG list and any one of the buffers, except the last
     buffer in the SG list has data size that is not a multiple
     of 16 bytes, i.e., other than 16, 32, 48, 64, etc.

With any one of the above three conditions present, there is
likelihood of stalled FMAN packet processing, especially under
stress with multiple ports injecting line-rate traffic.

To avoid situations that stall FMAN packet processing, all of the
above three conditions must be avoided; therefore, configure the
system with the following rules:

  1. Frame buffers must not span a 4KB address boundary, unless
     the frame start address is 256 byte aligned
  2. All FMAN DMA start addresses (for example, BMAN buffer
     address, FD[address] + FD[offset]) are 16B aligned
  3. SG table and buffer addresses are 16B aligned and the size
     of SG buffers are multiple of 16 bytes, except for the last
     SG buffer that can be of any size.

Additional workaround notes:
- Address alignment of 64 bytes is recommended for maximally
efficient system bus transactions (although 16 byte alignment is
sufficient to avoid the stall condition)
- To support frame sizes that are larger than 4K bytes, there are
two options:
  1. Large single buffer frames that span a 4KB page boundary can
     be converted into SG frames to avoid transaction splits at
     the 4KB boundary,
  2. Align the large single buffer to 256B address boundaries,
     ensure that the frame address plus offset is 256B aligned.
- If software generated SG frames have buffers that are unaligned
and with random non-multiple of 16 byte lengths, before
transmitting such frames via FMAN, frames will need to be copied
into a new single buffer or multiple buffer SG frame that is
compliant with the three rules listed above.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 Documentation/devicetree/bindings/net/fsl-fman.txt | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt
index 299c0dcd67db4..1316f0aec0cf3 100644
--- a/Documentation/devicetree/bindings/net/fsl-fman.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fman.txt
@@ -110,6 +110,13 @@ PROPERTIES
 		Usage: required
 		Definition: See soc/fsl/qman.txt and soc/fsl/bman.txt
 
+- fsl,erratum-a050385
+		Usage: optional
+		Value type: boolean
+		Definition: A boolean property. Indicates the presence of the
+		erratum A050385 which indicates that DMA transactions that are
+		split can result in a FMan lock.
+
 =============================================================================
 FMan MURAM Node
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 33/73] arm64: dts: ls1043a: FMan erratum A050385

[Sasha Levin]

From: Madalin Bucur <madalin.bucur@nxp.com>

[ Upstream commit b54d3900862374e1bb2846e6b39d79c896c0b200 ]

The LS1043A SoC is affected by the A050385 erratum stating that
FMAN DMA read or writes under heavy traffic load may cause FMAN
internal resource leak thus stopping further packet processing.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi
index 6082ae0221364..d237162a87446 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi
@@ -20,6 +20,8 @@
 };
 
 &fman0 {
+	fsl,erratum-a050385;
+
 	/* these aliases provide the FMan ports mapping */
 	enet0: ethernet@e0000 {
 	};
-- 
2.20.1

[PATCH AUTOSEL 5.4 34/73] fsl/fman: detect FMan erratum A050385

[Sasha Levin]

From: Madalin Bucur <madalin.bucur@nxp.com>

[ Upstream commit b281f7b93b258ce1419043bbd898a29254d5c9c7 ]

Detect the presence of the A050385 erratum.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/freescale/fman/Kconfig | 28 +++++++++++++++++++++
 drivers/net/ethernet/freescale/fman/fman.c  | 18 +++++++++++++
 drivers/net/ethernet/freescale/fman/fman.h  |  5 ++++
 3 files changed, 51 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fman/Kconfig b/drivers/net/ethernet/freescale/fman/Kconfig
index 0139cb9042ec7..34150182cc35c 100644
--- a/drivers/net/ethernet/freescale/fman/Kconfig
+++ b/drivers/net/ethernet/freescale/fman/Kconfig
@@ -8,3 +8,31 @@ config FSL_FMAN
 	help
 		Freescale Data-Path Acceleration Architecture Frame Manager
 		(FMan) support
+
+config DPAA_ERRATUM_A050385
+	bool
+	depends on ARM64 && FSL_DPAA
+	default y
+	help
+		DPAA FMan erratum A050385 software workaround implementation:
+		align buffers, data start, SG fragment length to avoid FMan DMA
+		splits.
+		FMAN DMA read or writes under heavy traffic load may cause FMAN
+		internal resource leak thus stopping further packet processing.
+		The FMAN internal queue can overflow when FMAN splits single
+		read or write transactions into multiple smaller transactions
+		such that more than 17 AXI transactions are in flight from FMAN
+		to interconnect. When the FMAN internal queue overflows, it can
+		stall further packet processing. The issue can occur with any
+		one of the following three conditions:
+		1. FMAN AXI transaction crosses 4K address boundary (Errata
+		A010022)
+		2. FMAN DMA address for an AXI transaction is not 16 byte
+		aligned, i.e. the last 4 bits of an address are non-zero
+		3. Scatter Gather (SG) frames have more than one SG buffer in
+		the SG list and any one of the buffers, except the last
+		buffer in the SG list has data size that is not a multiple
+		of 16 bytes, i.e., other than 16, 32, 48, 64, etc.
+		With any one of the above three conditions present, there is
+		likelihood of stalled FMAN packet processing, especially under
+		stress with multiple ports injecting line-rate traffic.
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index 210749bf1eac1..4c2fa13a7dd7b 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -1,5 +1,6 @@
 /*
  * Copyright 2008-2015 Freescale Semiconductor Inc.
+ * Copyright 2020 NXP
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -566,6 +567,10 @@ struct fman_cfg {
 	u32 qmi_def_tnums_thresh;
 };
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+static bool fman_has_err_a050385;
+#endif
+
 static irqreturn_t fman_exceptions(struct fman *fman,
 				   enum fman_exceptions exception)
 {
@@ -2514,6 +2519,14 @@ struct fman *fman_bind(struct device *fm_dev)
 }
 EXPORT_SYMBOL(fman_bind);
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+bool fman_has_errata_a050385(void)
+{
+	return fman_has_err_a050385;
+}
+EXPORT_SYMBOL(fman_has_errata_a050385);
+#endif
+
 static irqreturn_t fman_err_irq(int irq, void *handle)
 {
 	struct fman *fman = (struct fman *)handle;
@@ -2841,6 +2854,11 @@ static struct fman *read_dts_node(struct platform_device *of_dev)
 		goto fman_free;
 	}
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+	fman_has_err_a050385 =
+		of_property_read_bool(fm_node, "fsl,erratum-a050385");
+#endif
+
 	return fman;
 
 fman_node_put:
diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h
index 935c317fa6964..f2ede1360f03a 100644
--- a/drivers/net/ethernet/freescale/fman/fman.h
+++ b/drivers/net/ethernet/freescale/fman/fman.h
@@ -1,5 +1,6 @@
 /*
  * Copyright 2008-2015 Freescale Semiconductor Inc.
+ * Copyright 2020 NXP
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -398,6 +399,10 @@ u16 fman_get_max_frm(void);
 
 int fman_get_rx_extra_headroom(void);
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+bool fman_has_errata_a050385(void);
+#endif
+
 struct fman *fman_bind(struct device *dev);
 
 #endif /* __FM_H */
-- 
2.20.1

[PATCH AUTOSEL 5.4 35/73] bonding/alb: make sure arp header is pulled before accessing it

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit b7469e83d2add567e4e0b063963db185f3167cea ]

Similar to commit 38f88c454042 ("bonding/alb: properly access headers
in bond_alb_xmit()"), we need to make sure arp header was pulled
in skb->head before blindly accessing it in rlb_arp_xmit().

Remove arp_pkt() private helper, since it is more readable/obvious
to have the following construct back to back :

	if (!pskb_network_may_pull(skb, sizeof(*arp)))
		return NULL;
	arp = (struct arp_pkt *)skb_network_header(skb);

syzbot reported :

BUG: KMSAN: uninit-value in bond_slave_has_mac_rx include/net/bonding.h:704 [inline]
BUG: KMSAN: uninit-value in rlb_arp_xmit drivers/net/bonding/bond_alb.c:662 [inline]
BUG: KMSAN: uninit-value in bond_alb_xmit+0x575/0x25e0 drivers/net/bonding/bond_alb.c:1477
CPU: 0 PID: 12743 Comm: syz-executor.4 Not tainted 5.6.0-rc2-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 bond_slave_has_mac_rx include/net/bonding.h:704 [inline]
 rlb_arp_xmit drivers/net/bonding/bond_alb.c:662 [inline]
 bond_alb_xmit+0x575/0x25e0 drivers/net/bonding/bond_alb.c:1477
 __bond_start_xmit drivers/net/bonding/bond_main.c:4257 [inline]
 bond_start_xmit+0x85d/0x2f70 drivers/net/bonding/bond_main.c:4282
 __netdev_start_xmit include/linux/netdevice.h:4524 [inline]
 netdev_start_xmit include/linux/netdevice.h:4538 [inline]
 xmit_one net/core/dev.c:3470 [inline]
 dev_hard_start_xmit+0x531/0xab0 net/core/dev.c:3486
 __dev_queue_xmit+0x37de/0x4220 net/core/dev.c:4063
 dev_queue_xmit+0x4b/0x60 net/core/dev.c:4096
 packet_snd net/packet/af_packet.c:2967 [inline]
 packet_sendmsg+0x8347/0x93b0 net/packet/af_packet.c:2992
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg net/socket.c:672 [inline]
 __sys_sendto+0xc1b/0xc50 net/socket.c:1998
 __do_sys_sendto net/socket.c:2010 [inline]
 __se_sys_sendto+0x107/0x130 net/socket.c:2006
 __x64_sys_sendto+0x6e/0x90 net/socket.c:2006
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45c479
Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fc77ffbbc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00007fc77ffbc6d4 RCX: 000000000045c479
RDX: 000000000000000e RSI: 00000000200004c0 RDI: 0000000000000003
RBP: 000000000076bf20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 0000000000000a04 R14: 00000000004cc7b0 R15: 000000000076bf2c

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82
 slab_alloc_node mm/slub.c:2793 [inline]
 __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4401
 __kmalloc_reserve net/core/skbuff.c:142 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:210
 alloc_skb include/linux/skbuff.h:1051 [inline]
 alloc_skb_with_frags+0x18c/0xa70 net/core/skbuff.c:5766
 sock_alloc_send_pskb+0xada/0xc60 net/core/sock.c:2242
 packet_alloc_skb net/packet/af_packet.c:2815 [inline]
 packet_snd net/packet/af_packet.c:2910 [inline]
 packet_sendmsg+0x66a0/0x93b0 net/packet/af_packet.c:2992
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg net/socket.c:672 [inline]
 __sys_sendto+0xc1b/0xc50 net/socket.c:1998
 __do_sys_sendto net/socket.c:2010 [inline]
 __se_sys_sendto+0x107/0x130 net/socket.c:2006
 __x64_sys_sendto+0x6e/0x90 net/socket.c:2006
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/bonding/bond_alb.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 1cc2cd894f877..c81698550e5a7 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -50,11 +50,6 @@ struct arp_pkt {
 };
 #pragma pack()
 
-static inline struct arp_pkt *arp_pkt(const struct sk_buff *skb)
-{
-	return (struct arp_pkt *)skb_network_header(skb);
-}
-
 /* Forward declaration */
 static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
 				      bool strict_match);
@@ -553,10 +548,11 @@ static void rlb_req_update_subnet_clients(struct bonding *bond, __be32 src_ip)
 	spin_unlock(&bond->mode_lock);
 }
 
-static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bond)
+static struct slave *rlb_choose_channel(struct sk_buff *skb,
+					struct bonding *bond,
+					const struct arp_pkt *arp)
 {
 	struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
-	struct arp_pkt *arp = arp_pkt(skb);
 	struct slave *assigned_slave, *curr_active_slave;
 	struct rlb_client_info *client_info;
 	u32 hash_index = 0;
@@ -653,8 +649,12 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon
  */
 static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 {
-	struct arp_pkt *arp = arp_pkt(skb);
 	struct slave *tx_slave = NULL;
+	struct arp_pkt *arp;
+
+	if (!pskb_network_may_pull(skb, sizeof(*arp)))
+		return NULL;
+	arp = (struct arp_pkt *)skb_network_header(skb);
 
 	/* Don't modify or load balance ARPs that do not originate locally
 	 * (e.g.,arrive via a bridge).
@@ -664,7 +664,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 
 	if (arp->op_code == htons(ARPOP_REPLY)) {
 		/* the arp must be sent on the selected rx channel */
-		tx_slave = rlb_choose_channel(skb, bond);
+		tx_slave = rlb_choose_channel(skb, bond, arp);
 		if (tx_slave)
 			bond_hw_addr_copy(arp->mac_src, tx_slave->dev->dev_addr,
 					  tx_slave->dev->addr_len);
@@ -676,7 +676,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 		 * When the arp reply is received the entry will be updated
 		 * with the correct unicast address of the client.
 		 */
-		tx_slave = rlb_choose_channel(skb, bond);
+		tx_slave = rlb_choose_channel(skb, bond, arp);
 
 		/* The ARP reply packets must be delayed so that
 		 * they can cancel out the influence of the ARP request.
-- 
2.20.1

[PATCH AUTOSEL 5.4 36/73] virtio_ring: Fix mem leak with vring_new_virtqueue()

[Sasha Levin]

From: Suman Anna <s-anna@ti.com>

[ Upstream commit f13f09a12cbd0c7b776e083c5d008b6c6a9c4e0b ]

The functions vring_new_virtqueue() and __vring_new_virtqueue() are used
with split rings, and any allocations within these functions are managed
outside of the .we_own_ring flag. The commit cbeedb72b97a ("virtio_ring:
allocate desc state for split ring separately") allocates the desc state
within the __vring_new_virtqueue() but frees it only when the .we_own_ring
flag is set. This leads to a memory leak when freeing such allocated
virtqueues with the vring_del_virtqueue() function.

Fix this by moving the desc_state free code outside the flag and only
for split rings. Issue was discovered during testing with remoteproc
and virtio_rpmsg.

Fixes: cbeedb72b97a ("virtio_ring: allocate desc state for split ring separately")
Signed-off-by: Suman Anna <s-anna@ti.com>
Link: https://lore.kernel.org/r/20200224212643.30672-1-s-anna@ti.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/virtio/virtio_ring.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 867c7ebd3f107..58b96baa8d488 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -2203,10 +2203,10 @@ void vring_del_virtqueue(struct virtqueue *_vq)
 					 vq->split.queue_size_in_bytes,
 					 vq->split.vring.desc,
 					 vq->split.queue_dma_addr);
-
-			kfree(vq->split.desc_state);
 		}
 	}
+	if (!vq->packed_ring)
+		kfree(vq->split.desc_state);
 	list_del(&_vq->list);
 	kfree(vq);
 }
-- 
2.20.1

[PATCH AUTOSEL 5.4 37/73] virtio-blk: fix hw_queue stopped on arbitrary error

[Sasha Levin]

From: Halil Pasic <pasic@linux.ibm.com>

[ Upstream commit f5f6b95c72f7f8bb46eace8c5306c752d0133daa ]

Since nobody else is going to restart our hw_queue for us, the
blk_mq_start_stopped_hw_queues() is in virtblk_done() is not sufficient
necessarily sufficient to ensure that the queue will get started again.
In case of global resource outage (-ENOMEM because mapping failure,
because of swiotlb full) our virtqueue may be empty and we can get
stuck with a stopped hw_queue.

Let us not stop the queue on arbitrary errors, but only on -EONSPC which
indicates a full virtqueue, where the hw_queue is guaranteed to get
started by virtblk_done() before when it makes sense to carry on
submitting requests. Let us also remove a stale comment.

Signed-off-by: Halil Pasic <pasic@linux.ibm.com>
Cc: Jens Axboe <axboe@kernel.dk>
Fixes: f7728002c1c7 ("virtio_ring: fix return code on DMA mapping fails")
Link: https://lore.kernel.org/r/20200213123728.61216-2-pasic@linux.ibm.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/block/virtio_blk.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 7ffd719d89def..c2ed3e9128e3a 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -339,10 +339,12 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 		err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num);
 	if (err) {
 		virtqueue_kick(vblk->vqs[qid].vq);
-		blk_mq_stop_hw_queue(hctx);
+		/* Don't stop the queue if -ENOMEM: we may have failed to
+		 * bounce the buffer due to global resource outage.
+		 */
+		if (err == -ENOSPC)
+			blk_mq_stop_hw_queue(hctx);
 		spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
-		/* Out of mem doesn't actually happen, since we fall back
-		 * to direct descriptors */
 		if (err == -ENOMEM || err == -ENOSPC)
 			return BLK_STS_DEV_RESOURCE;
 		return BLK_STS_IOERR;
-- 
2.20.1

[PATCH AUTOSEL 5.4 38/73] virtio_balloon: Adjust label in virtballoon_probe

[Sasha Levin]

From: Nathan Chancellor <natechancellor@gmail.com>

[ Upstream commit 6ae4edab2fbf86ec92fbf0a8f0c60b857d90d50f ]

Clang warns when CONFIG_BALLOON_COMPACTION is unset:

../drivers/virtio/virtio_balloon.c:963:1: warning: unused label
'out_del_vqs' [-Wunused-label]
out_del_vqs:
^~~~~~~~~~~~
1 warning generated.

Move the label within the preprocessor block since it is only used when
CONFIG_BALLOON_COMPACTION is set.

Fixes: 1ad6f58ea936 ("virtio_balloon: Fix memory leaks on errors in virtballoon_probe()")
Link: https://github.com/ClangBuiltLinux/linux/issues/886
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Link: https://lore.kernel.org/r/20200216004039.23464-1-natechancellor@gmail.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/virtio/virtio_balloon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index d2c4eb9efd70b..7aaf150f89ba0 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -958,8 +958,8 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	iput(vb->vb_dev_info.inode);
 out_kern_unmount:
 	kern_unmount(balloon_mnt);
-#endif
 out_del_vqs:
+#endif
 	vdev->config->del_vqs(vdev);
 out_free_vb:
 	kfree(vb);
-- 
2.20.1

[PATCH AUTOSEL 5.4 39/73] ipvlan: do not add hardware address of master to its unicast filter list

[Sasha Levin]

From: Jiri Wiesner <jwiesner@suse.com>

[ Upstream commit 63aae7b17344d4b08a7d05cb07044de4c0f9dcc6 ]

There is a problem when ipvlan slaves are created on a master device that
is a vmxnet3 device (ipvlan in VMware guests). The vmxnet3 driver does not
support unicast address filtering. When an ipvlan device is brought up in
ipvlan_open(), the ipvlan driver calls dev_uc_add() to add the hardware
address of the vmxnet3 master device to the unicast address list of the
master device, phy_dev->uc. This inevitably leads to the vmxnet3 master
device being forced into promiscuous mode by __dev_set_rx_mode().

Promiscuous mode is switched on the master despite the fact that there is
still only one hardware address that the master device should use for
filtering in order for the ipvlan device to be able to receive packets.
The comment above struct net_device describes the uc_promisc member as a
"counter, that indicates, that promiscuous mode has been enabled due to
the need to listen to additional unicast addresses in a device that does
not implement ndo_set_rx_mode()". Moreover, the design of ipvlan
guarantees that only the hardware address of a master device,
phy_dev->dev_addr, will be used to transmit and receive all packets from
its ipvlan slaves. Thus, the unicast address list of the master device
should not be modified by ipvlan_open() and ipvlan_stop() in order to make
ipvlan a workable option on masters that do not support unicast address
filtering.

Fixes: 2ad7bf3638411 ("ipvlan: Initial check-in of the IPVLAN driver")
Reported-by: Per Sundstrom <per.sundstrom@redqube.se>
Signed-off-by: Jiri Wiesner <jwiesner@suse.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ipvlan/ipvlan_main.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index ba3dfac1d9043..b805abc9ec3b4 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -164,7 +164,6 @@ static void ipvlan_uninit(struct net_device *dev)
 static int ipvlan_open(struct net_device *dev)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
-	struct net_device *phy_dev = ipvlan->phy_dev;
 	struct ipvl_addr *addr;
 
 	if (ipvlan->port->mode == IPVLAN_MODE_L3 ||
@@ -178,7 +177,7 @@ static int ipvlan_open(struct net_device *dev)
 		ipvlan_ht_addr_add(ipvlan, addr);
 	rcu_read_unlock();
 
-	return dev_uc_add(phy_dev, phy_dev->dev_addr);
+	return 0;
 }
 
 static int ipvlan_stop(struct net_device *dev)
@@ -190,8 +189,6 @@ static int ipvlan_stop(struct net_device *dev)
 	dev_uc_unsync(phy_dev, dev);
 	dev_mc_unsync(phy_dev, dev);
 
-	dev_uc_del(phy_dev, phy_dev->dev_addr);
-
 	rcu_read_lock();
 	list_for_each_entry_rcu(addr, &ipvlan->addrs, anode)
 		ipvlan_ht_addr_del(addr);
-- 
2.20.1

[PATCH AUTOSEL 5.4 40/73] net: stmmac: dwmac1000: Disable ACS if enhanced descs are not used

[Sasha Levin]

From: Remi Pommarel <repk@triplefau.lt>

[ Upstream commit b723bd933980f4956dabc8a8d84b3e83be8d094c ]

ACS (auto PAD/FCS stripping) removes FCS off 802.3 packets (LLC) so that
there is no need to manually strip it for such packets. The enhanced DMA
descriptors allow to flag LLC packets so that the receiving callback can
use that to strip FCS manually or not. On the other hand, normal
descriptors do not support that.

Thus in order to not truncate LLC packet ACS should be disabled when
using normal DMA descriptors.

Fixes: 47dd7a540b8a0 ("net: add support for STMicroelectronics Ethernet controllers.")
Signed-off-by: Remi Pommarel <repk@triplefau.lt>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 3d69da112625e..43a785f86c69d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -24,6 +24,7 @@
 static void dwmac1000_core_init(struct mac_device_info *hw,
 				struct net_device *dev)
 {
+	struct stmmac_priv *priv = netdev_priv(dev);
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value = readl(ioaddr + GMAC_CONTROL);
 	int mtu = dev->mtu;
@@ -35,7 +36,7 @@ static void dwmac1000_core_init(struct mac_device_info *hw,
 	 * Broadcom tags can look like invalid LLC/SNAP packets and cause the
 	 * hardware to truncate packets on reception.
 	 */
-	if (netdev_uses_dsa(dev))
+	if (netdev_uses_dsa(dev) || !priv->plat->enh_desc)
 		value &= ~GMAC_CONTROL_ACS;
 
 	if (mtu > 1500)
-- 
2.20.1

[PATCH AUTOSEL 5.4 41/73] drm/amd/display: update soc bb for nv14

[Sasha Levin]

From: Martin Leung <martin.leung@amd.com>

[ Upstream commit d5349775c1726ce997b8eb4982cd85a01f1c8b42 ]

[why]
nv14 previously inherited soc bb from generic dcn 2, did not match
watermark values according to memory team

[how]
add nv14 specific soc bb: copy nv2 generic that it was
using from before, but changed num channels to 8

Signed-off-by: Martin Leung <martin.leung@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../drm/amd/display/dc/dcn20/dcn20_resource.c | 114 ++++++++++++++++++
 1 file changed, 114 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 3b7769a3e67e3..c13dce760098c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -269,6 +269,117 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_0_soc = {
 	.use_urgent_burst_bw = 0
 };
 
+struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = {
+	.clock_limits = {
+			{
+				.state = 0,
+				.dcfclk_mhz = 560.0,
+				.fabricclk_mhz = 560.0,
+				.dispclk_mhz = 513.0,
+				.dppclk_mhz = 513.0,
+				.phyclk_mhz = 540.0,
+				.socclk_mhz = 560.0,
+				.dscclk_mhz = 171.0,
+				.dram_speed_mts = 8960.0,
+			},
+			{
+				.state = 1,
+				.dcfclk_mhz = 694.0,
+				.fabricclk_mhz = 694.0,
+				.dispclk_mhz = 642.0,
+				.dppclk_mhz = 642.0,
+				.phyclk_mhz = 600.0,
+				.socclk_mhz = 694.0,
+				.dscclk_mhz = 214.0,
+				.dram_speed_mts = 11104.0,
+			},
+			{
+				.state = 2,
+				.dcfclk_mhz = 875.0,
+				.fabricclk_mhz = 875.0,
+				.dispclk_mhz = 734.0,
+				.dppclk_mhz = 734.0,
+				.phyclk_mhz = 810.0,
+				.socclk_mhz = 875.0,
+				.dscclk_mhz = 245.0,
+				.dram_speed_mts = 14000.0,
+			},
+			{
+				.state = 3,
+				.dcfclk_mhz = 1000.0,
+				.fabricclk_mhz = 1000.0,
+				.dispclk_mhz = 1100.0,
+				.dppclk_mhz = 1100.0,
+				.phyclk_mhz = 810.0,
+				.socclk_mhz = 1000.0,
+				.dscclk_mhz = 367.0,
+				.dram_speed_mts = 16000.0,
+			},
+			{
+				.state = 4,
+				.dcfclk_mhz = 1200.0,
+				.fabricclk_mhz = 1200.0,
+				.dispclk_mhz = 1284.0,
+				.dppclk_mhz = 1284.0,
+				.phyclk_mhz = 810.0,
+				.socclk_mhz = 1200.0,
+				.dscclk_mhz = 428.0,
+				.dram_speed_mts = 16000.0,
+			},
+			/*Extra state, no dispclk ramping*/
+			{
+				.state = 5,
+				.dcfclk_mhz = 1200.0,
+				.fabricclk_mhz = 1200.0,
+				.dispclk_mhz = 1284.0,
+				.dppclk_mhz = 1284.0,
+				.phyclk_mhz = 810.0,
+				.socclk_mhz = 1200.0,
+				.dscclk_mhz = 428.0,
+				.dram_speed_mts = 16000.0,
+			},
+		},
+	.num_states = 5,
+	.sr_exit_time_us = 8.6,
+	.sr_enter_plus_exit_time_us = 10.9,
+	.urgent_latency_us = 4.0,
+	.urgent_latency_pixel_data_only_us = 4.0,
+	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
+	.urgent_latency_vm_data_only_us = 4.0,
+	.urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096,
+	.urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096,
+	.urgent_out_of_order_return_per_channel_vm_only_bytes = 4096,
+	.pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0,
+	.pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0,
+	.pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0,
+	.max_avg_sdp_bw_use_normal_percent = 40.0,
+	.max_avg_dram_bw_use_normal_percent = 40.0,
+	.writeback_latency_us = 12.0,
+	.ideal_dram_bw_after_urgent_percent = 40.0,
+	.max_request_size_bytes = 256,
+	.dram_channel_width_bytes = 2,
+	.fabric_datapath_to_dcn_data_return_bytes = 64,
+	.dcn_downspread_percent = 0.5,
+	.downspread_percent = 0.38,
+	.dram_page_open_time_ns = 50.0,
+	.dram_rw_turnaround_time_ns = 17.5,
+	.dram_return_buffer_per_channel_bytes = 8192,
+	.round_trip_ping_latency_dcfclk_cycles = 131,
+	.urgent_out_of_order_return_per_channel_bytes = 256,
+	.channel_interleave_bytes = 256,
+	.num_banks = 8,
+	.num_chans = 8,
+	.vmm_page_size_bytes = 4096,
+	.dram_clock_change_latency_us = 404.0,
+	.dummy_pstate_latency_us = 5.0,
+	.writeback_dram_clock_change_latency_us = 23.0,
+	.return_bus_width_bytes = 64,
+	.dispclk_dppclk_vco_speed_mhz = 3850,
+	.xfc_bus_transport_time_us = 20,
+	.xfc_xbuf_latency_tolerance_us = 4,
+	.use_urgent_burst_bw = 0
+};
+
 struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { 0 };
 
 #ifndef mmDP0_DP_DPHY_INTERNAL_CTRL
@@ -3135,6 +3246,9 @@ static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s
 static struct _vcs_dpi_soc_bounding_box_st *get_asic_rev_soc_bb(
 	uint32_t hw_internal_rev)
 {
+	if (ASICREV_IS_NAVI14_M(hw_internal_rev))
+		return &dcn2_0_nv14_soc;
+
 	if (ASICREV_IS_NAVI12_P(hw_internal_rev))
 		return &dcn2_0_nv12_soc;
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 42/73] drm/amdgpu: correct ROM_INDEX/DATA offset for VEGA20

[Sasha Levin]

From: Hawking Zhang <Hawking.Zhang@amd.com>

[ Upstream commit f1c2cd3f8fb959123a9beba18c0e8112dcb2e137 ]

The ROMC_INDEX/DATA offset was changed to e4/e5 since
from smuio_v11 (vega20/arcturus).

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Tested-by: Candice Li <Candice.Li@amd.com>
Reviewed-by: Candice Li <Candice.Li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/soc15.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 80934ca172607..c086262cc181d 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -84,6 +84,13 @@
 #define HDP_MEM_POWER_CTRL__RC_MEM_POWER_CTRL_EN_MASK	0x00010000L
 #define HDP_MEM_POWER_CTRL__RC_MEM_POWER_LS_EN_MASK		0x00020000L
 #define mmHDP_MEM_POWER_CTRL_BASE_IDX	0
+
+/* for Vega20/arcturus regiter offset change */
+#define	mmROM_INDEX_VG20				0x00e4
+#define	mmROM_INDEX_VG20_BASE_IDX			0
+#define	mmROM_DATA_VG20					0x00e5
+#define	mmROM_DATA_VG20_BASE_IDX			0
+
 /*
  * Indirect registers accessor
  */
@@ -304,6 +311,8 @@ static bool soc15_read_bios_from_rom(struct amdgpu_device *adev,
 {
 	u32 *dw_ptr;
 	u32 i, length_dw;
+	uint32_t rom_index_offset;
+	uint32_t rom_data_offset;
 
 	if (bios == NULL)
 		return false;
@@ -316,11 +325,23 @@ static bool soc15_read_bios_from_rom(struct amdgpu_device *adev,
 	dw_ptr = (u32 *)bios;
 	length_dw = ALIGN(length_bytes, 4) / 4;
 
+	switch (adev->asic_type) {
+	case CHIP_VEGA20:
+	case CHIP_ARCTURUS:
+		rom_index_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_INDEX_VG20);
+		rom_data_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_DATA_VG20);
+		break;
+	default:
+		rom_index_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_INDEX);
+		rom_data_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_DATA);
+		break;
+	}
+
 	/* set rom index to 0 */
-	WREG32(SOC15_REG_OFFSET(SMUIO, 0, mmROM_INDEX), 0);
+	WREG32(rom_index_offset, 0);
 	/* read out the rom data */
 	for (i = 0; i < length_dw; i++)
-		dw_ptr[i] = RREG32(SOC15_REG_OFFSET(SMUIO, 0, mmROM_DATA));
+		dw_ptr[i] = RREG32(rom_data_offset);
 
 	return true;
 }
-- 
2.20.1

[PATCH AUTOSEL 5.4 43/73] futex: Unbreak futex hashing

[Sasha Levin]

From: Thomas Gleixner <tglx@linutronix.de>

[ Upstream commit 8d67743653dce5a0e7aa500fcccb237cde7ad88e ]

The recent futex inode life time fix changed the ordering of the futex key
union struct members, but forgot to adjust the hash function accordingly,

As a result the hashing omits the leading 64bit and even hashes beyond the
futex key causing a bad hash distribution which led to a ~100% performance
regression.

Hand in the futex key pointer instead of a random struct member and make
the size calculation based of the struct offset.

Fixes: 8019ad13ef7f ("futex: Fix inode life-time issue")
Reported-by: Rong Chen <rong.a.chen@intel.com>
Decoded-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Rong Chen <rong.a.chen@intel.com>
Link: https://lkml.kernel.org/r/87h7yy90ve.fsf@nanos.tec.linutronix.de
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/futex.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/futex.c b/kernel/futex.c
index 07ab324885ac0..5660c02b01b05 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -385,9 +385,9 @@ static inline int hb_waiters_pending(struct futex_hash_bucket *hb)
  */
 static struct futex_hash_bucket *hash_futex(union futex_key *key)
 {
-	u32 hash = jhash2((u32*)&key->both.word,
-			  (sizeof(key->both.word)+sizeof(key->both.ptr))/4,
+	u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4,
 			  key->both.offset);
+
 	return &futex_queues[hash & (futex_hashsize - 1)];
 }
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 44/73] ipvlan: don't deref eth hdr before checking it's set

[Sasha Levin]

From: Mahesh Bandewar <maheshb@google.com>

[ Upstream commit ad8192767c9f9cf97da57b9ffcea70fb100febef ]

IPvlan in L3 mode discards outbound multicast packets but performs
the check before ensuring the ether-header is set or not. This is
an error that Eric found through code browsing.

Fixes: 2ad7bf363841 (“ipvlan: Initial check-in of the IPVLAN driver.”)
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ipvlan/ipvlan_core.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 30cd0c4f0be0b..53dac397db37f 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -498,19 +498,21 @@ static int ipvlan_process_outbound(struct sk_buff *skb)
 	struct ethhdr *ethh = eth_hdr(skb);
 	int ret = NET_XMIT_DROP;
 
-	/* In this mode we dont care about multicast and broadcast traffic */
-	if (is_multicast_ether_addr(ethh->h_dest)) {
-		pr_debug_ratelimited("Dropped {multi|broad}cast of type=[%x]\n",
-				     ntohs(skb->protocol));
-		kfree_skb(skb);
-		goto out;
-	}
-
 	/* The ipvlan is a pseudo-L2 device, so the packets that we receive
 	 * will have L2; which need to discarded and processed further
 	 * in the net-ns of the main-device.
 	 */
 	if (skb_mac_header_was_set(skb)) {
+		/* In this mode we dont care about
+		 * multicast and broadcast traffic */
+		if (is_multicast_ether_addr(ethh->h_dest)) {
+			pr_debug_ratelimited(
+				"Dropped {multi|broad}cast of type=[%x]\n",
+				ntohs(skb->protocol));
+			kfree_skb(skb);
+			goto out;
+		}
+
 		skb_pull(skb, sizeof(*ethh));
 		skb->mac_header = (typeof(skb->mac_header))~0U;
 		skb_reset_network_header(skb);
-- 
2.20.1

[PATCH AUTOSEL 5.4 45/73] ipvlan: add cond_resched_rcu() while processing muticast backlog

[Sasha Levin]

From: Mahesh Bandewar <maheshb@google.com>

[ Upstream commit e18b353f102e371580f3f01dd47567a25acc3c1d ]

If there are substantial number of slaves created as simulated by
Syzbot, the backlog processing could take much longer and result
into the issue found in the Syzbot report.

INFO: rcu_sched detected stalls on CPUs/tasks:
        (detected by 1, t=10502 jiffies, g=5049, c=5048, q=752)
All QSes seen, last rcu_sched kthread activity 10502 (4294965563-4294955061), jiffies_till_next_fqs=1, root ->qsmask 0x0
syz-executor.1  R  running task on cpu   1  10984 11210   3866 0x30020008 179034491270
Call Trace:
 <IRQ>
 [<ffffffff81497163>] _sched_show_task kernel/sched/core.c:8063 [inline]
 [<ffffffff81497163>] _sched_show_task.cold+0x2fd/0x392 kernel/sched/core.c:8030
 [<ffffffff8146a91b>] sched_show_task+0xb/0x10 kernel/sched/core.c:8073
 [<ffffffff815c931b>] print_other_cpu_stall kernel/rcu/tree.c:1577 [inline]
 [<ffffffff815c931b>] check_cpu_stall kernel/rcu/tree.c:1695 [inline]
 [<ffffffff815c931b>] __rcu_pending kernel/rcu/tree.c:3478 [inline]
 [<ffffffff815c931b>] rcu_pending kernel/rcu/tree.c:3540 [inline]
 [<ffffffff815c931b>] rcu_check_callbacks.cold+0xbb4/0xc29 kernel/rcu/tree.c:2876
 [<ffffffff815e3962>] update_process_times+0x32/0x80 kernel/time/timer.c:1635
 [<ffffffff816164f0>] tick_sched_handle+0xa0/0x180 kernel/time/tick-sched.c:161
 [<ffffffff81616ae4>] tick_sched_timer+0x44/0x130 kernel/time/tick-sched.c:1193
 [<ffffffff815e75f7>] __run_hrtimer kernel/time/hrtimer.c:1393 [inline]
 [<ffffffff815e75f7>] __hrtimer_run_queues+0x307/0xd90 kernel/time/hrtimer.c:1455
 [<ffffffff815e90ea>] hrtimer_interrupt+0x2ea/0x730 kernel/time/hrtimer.c:1513
 [<ffffffff844050f4>] local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1031 [inline]
 [<ffffffff844050f4>] smp_apic_timer_interrupt+0x144/0x5e0 arch/x86/kernel/apic/apic.c:1056
 [<ffffffff84401cbe>] apic_timer_interrupt+0x8e/0xa0 arch/x86/entry/entry_64.S:778
RIP: 0010:do_raw_read_lock+0x22/0x80 kernel/locking/spinlock_debug.c:153
RSP: 0018:ffff8801dad07ab8 EFLAGS: 00000a02 ORIG_RAX: ffffffffffffff12
RAX: 0000000000000000 RBX: ffff8801c4135680 RCX: 0000000000000000
RDX: 1ffff10038826afe RSI: ffff88019d816bb8 RDI: ffff8801c41357f0
RBP: ffff8801dad07ac0 R08: 0000000000004b15 R09: 0000000000310273
R10: ffff88019d816bb8 R11: 0000000000000001 R12: ffff8801c41357e8
R13: 0000000000000000 R14: ffff8801cfb19850 R15: ffff8801cfb198b0
 [<ffffffff8101460e>] __raw_read_lock_bh include/linux/rwlock_api_smp.h:177 [inline]
 [<ffffffff8101460e>] _raw_read_lock_bh+0x3e/0x50 kernel/locking/spinlock.c:240
 [<ffffffff840d78ca>] ipv6_chk_mcast_addr+0x11a/0x6f0 net/ipv6/mcast.c:1006
 [<ffffffff84023439>] ip6_mc_input+0x319/0x8e0 net/ipv6/ip6_input.c:482
 [<ffffffff840211c8>] dst_input include/net/dst.h:449 [inline]
 [<ffffffff840211c8>] ip6_rcv_finish+0x408/0x610 net/ipv6/ip6_input.c:78
 [<ffffffff840214de>] NF_HOOK include/linux/netfilter.h:292 [inline]
 [<ffffffff840214de>] NF_HOOK include/linux/netfilter.h:286 [inline]
 [<ffffffff840214de>] ipv6_rcv+0x10e/0x420 net/ipv6/ip6_input.c:278
 [<ffffffff83a29efa>] __netif_receive_skb_one_core+0x12a/0x1f0 net/core/dev.c:5303
 [<ffffffff83a2a15c>] __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:5417
 [<ffffffff83a2f536>] process_backlog+0x216/0x6c0 net/core/dev.c:6243
 [<ffffffff83a30d1b>] napi_poll net/core/dev.c:6680 [inline]
 [<ffffffff83a30d1b>] net_rx_action+0x47b/0xfb0 net/core/dev.c:6748
 [<ffffffff846002c8>] __do_softirq+0x2c8/0x99a kernel/softirq.c:317
 [<ffffffff813e656a>] invoke_softirq kernel/softirq.c:399 [inline]
 [<ffffffff813e656a>] irq_exit+0x16a/0x1a0 kernel/softirq.c:439
 [<ffffffff84405115>] exiting_irq arch/x86/include/asm/apic.h:561 [inline]
 [<ffffffff84405115>] smp_apic_timer_interrupt+0x165/0x5e0 arch/x86/kernel/apic/apic.c:1058
 [<ffffffff84401cbe>] apic_timer_interrupt+0x8e/0xa0 arch/x86/entry/entry_64.S:778
 </IRQ>
RIP: 0010:__sanitizer_cov_trace_pc+0x26/0x50 kernel/kcov.c:102
RSP: 0018:ffff880196033bd8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff12
RAX: ffff88019d8161c0 RBX: 00000000ffffffff RCX: ffffc90003501000
RDX: 0000000000000002 RSI: ffffffff816236d1 RDI: 0000000000000005
RBP: ffff880196033bd8 R08: ffff88019d8161c0 R09: 0000000000000000
R10: 1ffff10032c067f0 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000080 R14: 0000000000000000 R15: 0000000000000000
 [<ffffffff816236d1>] do_futex+0x151/0x1d50 kernel/futex.c:3548
 [<ffffffff816260f0>] C_SYSC_futex kernel/futex_compat.c:201 [inline]
 [<ffffffff816260f0>] compat_SyS_futex+0x270/0x3b0 kernel/futex_compat.c:175
 [<ffffffff8101da17>] do_syscall_32_irqs_on arch/x86/entry/common.c:353 [inline]
 [<ffffffff8101da17>] do_fast_syscall_32+0x357/0xe1c arch/x86/entry/common.c:415
 [<ffffffff84401a9b>] entry_SYSENTER_compat+0x8b/0x9d arch/x86/entry/entry_64_compat.S:139
RIP: 0023:0xf7f23c69
RSP: 002b:00000000f5d1f12c EFLAGS: 00000282 ORIG_RAX: 00000000000000f0
RAX: ffffffffffffffda RBX: 000000000816af88 RCX: 0000000000000080
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000000000816af8c
RBP: 00000000f5d1f228 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
rcu_sched kthread starved for 10502 jiffies! g5049 c5048 f0x2 RCU_GP_WAIT_FQS(3) ->state=0x0 ->cpu=1
rcu_sched       R  running task on cpu   1  13048     8      2 0x90000000 179099587640
Call Trace:
 [<ffffffff8147321f>] context_switch+0x60f/0xa60 kernel/sched/core.c:3209
 [<ffffffff8100095a>] __schedule+0x5aa/0x1da0 kernel/sched/core.c:3934
 [<ffffffff810021df>] schedule+0x8f/0x1b0 kernel/sched/core.c:4011
 [<ffffffff8101116d>] schedule_timeout+0x50d/0xee0 kernel/time/timer.c:1803
 [<ffffffff815c13f1>] rcu_gp_kthread+0xda1/0x3b50 kernel/rcu/tree.c:2327
 [<ffffffff8144b318>] kthread+0x348/0x420 kernel/kthread.c:246
 [<ffffffff84400266>] ret_from_fork+0x56/0x70 arch/x86/entry/entry_64.S:393

Fixes: ba35f8588f47 (“ipvlan: Defer multicast / broadcast processing to a work-queue”)
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ipvlan/ipvlan_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 53dac397db37f..5759e91dec710 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -277,6 +277,7 @@ void ipvlan_process_multicast(struct work_struct *work)
 			}
 			ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
 			local_bh_enable();
+			cond_resched_rcu();
 		}
 		rcu_read_unlock();
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 46/73] macvlan: add cond_resched() during multicast processing

[Sasha Levin]

From: Mahesh Bandewar <maheshb@google.com>

[ Upstream commit ce9a4186f9ac475c415ffd20348176a4ea366670 ]

The Rx bound multicast packets are deferred to a workqueue and
macvlan can also suffer from the same attack that was discovered
by Syzbot for IPvlan. This solution is not as effective as in
IPvlan. IPvlan defers all (Tx and Rx) multicast packet processing
to a workqueue while macvlan does this way only for the Rx. This
fix should address the Rx codition to certain extent.

Tx is still suseptible. Tx multicast processing happens when
.ndo_start_xmit is called, hence we cannot add cond_resched().
However, it's not that severe since the user which is generating
 / flooding will be affected the most.

Fixes: 412ca1550cbe ("macvlan: Move broadcasts into a work queue")
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/macvlan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index c5bf61565726b..26f6be4796c75 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -334,6 +334,8 @@ static void macvlan_process_broadcast(struct work_struct *w)
 		if (src)
 			dev_put(src->dev);
 		consume_skb(skb);
+
+		cond_resched();
 	}
 }
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 47/73] ipvlan: do not use cond_resched_rcu() in ipvlan_process_multicast()

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit afe207d80a61e4d6e7cfa0611a4af46d0ba95628 ]

Commit e18b353f102e ("ipvlan: add cond_resched_rcu() while
processing muticast backlog") added a cond_resched_rcu() in a loop
using rcu protection to iterate over slaves.

This is breaking rcu rules, so lets instead use cond_resched()
at a point we can reschedule

Fixes: e18b353f102e ("ipvlan: add cond_resched_rcu() while processing muticast backlog")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ipvlan/ipvlan_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 5759e91dec710..8801d093135c3 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -277,7 +277,6 @@ void ipvlan_process_multicast(struct work_struct *work)
 			}
 			ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
 			local_bh_enable();
-			cond_resched_rcu();
 		}
 		rcu_read_unlock();
 
@@ -294,6 +293,7 @@ void ipvlan_process_multicast(struct work_struct *work)
 		}
 		if (dev)
 			dev_put(dev);
+		cond_resched();
 	}
 }
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 48/73] drm/exynos: Fix cleanup of IOMMU related objects

[Sasha Levin]

From: Marek Szyprowski <m.szyprowski@samsung.com>

[ Upstream commit 07dc3678bacc2a75b1900febea7d996a31f178a2 ]

Store the IOMMU mapping created by the device core of each Exynos DRM
sub-device and restore it when the Exynos DRM driver is unbound. This
fixes IOMMU initialization failure for the second time when a deferred
probe is triggered from the bind() callback of master's compound DRM
driver. This also fixes the following issue found using kmemleak
detector:

unreferenced object 0xc2137640 (size 64):
  comm "swapper/0", pid 1, jiffies 4294937900 (age 3127.400s)
  hex dump (first 32 bytes):
    50 a3 14 c2 80 a2 14 c2 01 00 00 00 20 00 00 00  P........... ...
    00 10 00 00 00 80 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<3acd268d>] arch_setup_dma_ops+0x4c/0x104
    [<9f7d2cce>] of_dma_configure+0x19c/0x3a4
    [<ba07704b>] really_probe+0xb0/0x47c
    [<4f510e4f>] driver_probe_device+0x78/0x1c4
    [<7481a0cf>] device_driver_attach+0x58/0x60
    [<0ff8f5c1>] __driver_attach+0xb8/0x158
    [<86006144>] bus_for_each_dev+0x74/0xb4
    [<10159dca>] bus_add_driver+0x1c0/0x200
    [<8a265265>] driver_register+0x74/0x108
    [<e0f3451a>] exynos_drm_init+0xb0/0x134
    [<db3fc7ba>] do_one_initcall+0x90/0x458
    [<6da35917>] kernel_init_freeable+0x188/0x200
    [<db3f74d4>] kernel_init+0x8/0x110
    [<1f3cddf9>] ret_from_fork+0x14/0x20
    [<8cd12507>] 0x0
unreferenced object 0xc214a280 (size 128):
  comm "swapper/0", pid 1, jiffies 4294937900 (age 3127.400s)
  hex dump (first 32 bytes):
    00 a0 ec ed 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<3acd268d>] arch_setup_dma_ops+0x4c/0x104
    [<9f7d2cce>] of_dma_configure+0x19c/0x3a4
    [<ba07704b>] really_probe+0xb0/0x47c
    [<4f510e4f>] driver_probe_device+0x78/0x1c4
    [<7481a0cf>] device_driver_attach+0x58/0x60
    [<0ff8f5c1>] __driver_attach+0xb8/0x158
    [<86006144>] bus_for_each_dev+0x74/0xb4
    [<10159dca>] bus_add_driver+0x1c0/0x200
    [<8a265265>] driver_register+0x74/0x108
    [<e0f3451a>] exynos_drm_init+0xb0/0x134
    [<db3fc7ba>] do_one_initcall+0x90/0x458
    [<6da35917>] kernel_init_freeable+0x188/0x200
    [<db3f74d4>] kernel_init+0x8/0x110
    [<1f3cddf9>] ret_from_fork+0x14/0x20
    [<8cd12507>] 0x0
unreferenced object 0xedeca000 (size 4096):
  comm "swapper/0", pid 1, jiffies 4294937900 (age 3127.400s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<3acd268d>] arch_setup_dma_ops+0x4c/0x104
    [<9f7d2cce>] of_dma_configure+0x19c/0x3a4
    [<ba07704b>] really_probe+0xb0/0x47c
    [<4f510e4f>] driver_probe_device+0x78/0x1c4
    [<7481a0cf>] device_driver_attach+0x58/0x60
    [<0ff8f5c1>] __driver_attach+0xb8/0x158
    [<86006144>] bus_for_each_dev+0x74/0xb4
    [<10159dca>] bus_add_driver+0x1c0/0x200
    [<8a265265>] driver_register+0x74/0x108
    [<e0f3451a>] exynos_drm_init+0xb0/0x134
    [<db3fc7ba>] do_one_initcall+0x90/0x458
    [<6da35917>] kernel_init_freeable+0x188/0x200
    [<db3f74d4>] kernel_init+0x8/0x110
    [<1f3cddf9>] ret_from_fork+0x14/0x20
    [<8cd12507>] 0x0
unreferenced object 0xc214a300 (size 128):
  comm "swapper/0", pid 1, jiffies 4294937900 (age 3127.400s)
  hex dump (first 32 bytes):
    00 a3 14 c2 00 a3 14 c2 00 40 18 c2 00 80 18 c2  .........@......
    02 00 02 00 ad 4e ad de ff ff ff ff ff ff ff ff  .....N..........
  backtrace:
    [<08cbd8bc>] iommu_domain_alloc+0x24/0x50
    [<b835abee>] arm_iommu_create_mapping+0xe4/0x134
    [<3acd268d>] arch_setup_dma_ops+0x4c/0x104
    [<9f7d2cce>] of_dma_configure+0x19c/0x3a4
    [<ba07704b>] really_probe+0xb0/0x47c
    [<4f510e4f>] driver_probe_device+0x78/0x1c4
    [<7481a0cf>] device_driver_attach+0x58/0x60
    [<0ff8f5c1>] __driver_attach+0xb8/0x158
    [<86006144>] bus_for_each_dev+0x74/0xb4
    [<10159dca>] bus_add_driver+0x1c0/0x200
    [<8a265265>] driver_register+0x74/0x108
    [<e0f3451a>] exynos_drm_init+0xb0/0x134
    [<db3fc7ba>] do_one_initcall+0x90/0x458
    [<6da35917>] kernel_init_freeable+0x188/0x200
    [<db3f74d4>] kernel_init+0x8/0x110
    [<1f3cddf9>] ret_from_fork+0x14/0x20

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/exynos/exynos5433_drm_decon.c |  5 ++--
 drivers/gpu/drm/exynos/exynos7_drm_decon.c    |  5 ++--
 drivers/gpu/drm/exynos/exynos_drm_dma.c       | 28 +++++++++++++------
 drivers/gpu/drm/exynos/exynos_drm_drv.h       |  6 ++--
 drivers/gpu/drm/exynos/exynos_drm_fimc.c      |  5 ++--
 drivers/gpu/drm/exynos/exynos_drm_fimd.c      |  5 ++--
 drivers/gpu/drm/exynos/exynos_drm_g2d.c       |  5 ++--
 drivers/gpu/drm/exynos/exynos_drm_gsc.c       |  5 ++--
 drivers/gpu/drm/exynos/exynos_drm_rotator.c   |  5 ++--
 drivers/gpu/drm/exynos/exynos_drm_scaler.c    |  6 ++--
 drivers/gpu/drm/exynos/exynos_mixer.c         |  7 +++--
 11 files changed, 53 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 2d5cbfda3ca79..9c262daf5816e 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -55,6 +55,7 @@ static const char * const decon_clks_name[] = {
 struct decon_context {
 	struct device			*dev;
 	struct drm_device		*drm_dev;
+	void				*dma_priv;
 	struct exynos_drm_crtc		*crtc;
 	struct exynos_drm_plane		planes[WINDOWS_NR];
 	struct exynos_drm_plane_config	configs[WINDOWS_NR];
@@ -644,7 +645,7 @@ static int decon_bind(struct device *dev, struct device *master, void *data)
 
 	decon_clear_channels(ctx->crtc);
 
-	return exynos_drm_register_dma(drm_dev, dev);
+	return exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv);
 }
 
 static void decon_unbind(struct device *dev, struct device *master, void *data)
@@ -654,7 +655,7 @@ static void decon_unbind(struct device *dev, struct device *master, void *data)
 	decon_disable(ctx->crtc);
 
 	/* detach this sub driver from iommu mapping if supported. */
-	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev);
+	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv);
 }
 
 static const struct component_ops decon_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index f0640950bd465..6fd40410dfd2e 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -40,6 +40,7 @@
 struct decon_context {
 	struct device			*dev;
 	struct drm_device		*drm_dev;
+	void				*dma_priv;
 	struct exynos_drm_crtc		*crtc;
 	struct exynos_drm_plane		planes[WINDOWS_NR];
 	struct exynos_drm_plane_config	configs[WINDOWS_NR];
@@ -127,13 +128,13 @@ static int decon_ctx_initialize(struct decon_context *ctx,
 
 	decon_clear_channels(ctx->crtc);
 
-	return exynos_drm_register_dma(drm_dev, ctx->dev);
+	return exynos_drm_register_dma(drm_dev, ctx->dev, &ctx->dma_priv);
 }
 
 static void decon_ctx_remove(struct decon_context *ctx)
 {
 	/* detach this sub driver from iommu mapping if supported. */
-	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev);
+	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv);
 }
 
 static u32 decon_calc_clkdiv(struct decon_context *ctx,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c
index 9ebc02768847e..619f81435c1b2 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dma.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c
@@ -58,7 +58,7 @@ static inline void clear_dma_max_seg_size(struct device *dev)
  * mapping.
  */
 static int drm_iommu_attach_device(struct drm_device *drm_dev,
-				struct device *subdrv_dev)
+				struct device *subdrv_dev, void **dma_priv)
 {
 	struct exynos_drm_private *priv = drm_dev->dev_private;
 	int ret;
@@ -74,7 +74,14 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev,
 		return ret;
 
 	if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) {
-		if (to_dma_iommu_mapping(subdrv_dev))
+		/*
+		 * Keep the original DMA mapping of the sub-device and
+		 * restore it on Exynos DRM detach, otherwise the DMA
+		 * framework considers it as IOMMU-less during the next
+		 * probe (in case of deferred probe or modular build)
+		 */
+		*dma_priv = to_dma_iommu_mapping(subdrv_dev);
+		if (*dma_priv)
 			arm_iommu_detach_device(subdrv_dev);
 
 		ret = arm_iommu_attach_device(subdrv_dev, priv->mapping);
@@ -98,19 +105,21 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev,
  * mapping
  */
 static void drm_iommu_detach_device(struct drm_device *drm_dev,
-				struct device *subdrv_dev)
+				    struct device *subdrv_dev, void **dma_priv)
 {
 	struct exynos_drm_private *priv = drm_dev->dev_private;
 
-	if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU))
+	if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) {
 		arm_iommu_detach_device(subdrv_dev);
-	else if (IS_ENABLED(CONFIG_IOMMU_DMA))
+		arm_iommu_attach_device(subdrv_dev, *dma_priv);
+	} else if (IS_ENABLED(CONFIG_IOMMU_DMA))
 		iommu_detach_device(priv->mapping, subdrv_dev);
 
 	clear_dma_max_seg_size(subdrv_dev);
 }
 
-int exynos_drm_register_dma(struct drm_device *drm, struct device *dev)
+int exynos_drm_register_dma(struct drm_device *drm, struct device *dev,
+			    void **dma_priv)
 {
 	struct exynos_drm_private *priv = drm->dev_private;
 
@@ -137,13 +146,14 @@ int exynos_drm_register_dma(struct drm_device *drm, struct device *dev)
 		priv->mapping = mapping;
 	}
 
-	return drm_iommu_attach_device(drm, dev);
+	return drm_iommu_attach_device(drm, dev, dma_priv);
 }
 
-void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev)
+void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev,
+			       void **dma_priv)
 {
 	if (IS_ENABLED(CONFIG_EXYNOS_IOMMU))
-		drm_iommu_detach_device(drm, dev);
+		drm_iommu_detach_device(drm, dev, dma_priv);
 }
 
 void exynos_drm_cleanup_dma(struct drm_device *drm)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index d4014ba592fdc..735f436c857cc 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -223,8 +223,10 @@ static inline bool is_drm_iommu_supported(struct drm_device *drm_dev)
 	return priv->mapping ? true : false;
 }
 
-int exynos_drm_register_dma(struct drm_device *drm, struct device *dev);
-void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev);
+int exynos_drm_register_dma(struct drm_device *drm, struct device *dev,
+			    void **dma_priv);
+void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev,
+			       void **dma_priv);
 void exynos_drm_cleanup_dma(struct drm_device *drm);
 
 #ifdef CONFIG_DRM_EXYNOS_DPI
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 8ea2e1d77802a..29ab8be8604c9 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -97,6 +97,7 @@ struct fimc_scaler {
 struct fimc_context {
 	struct exynos_drm_ipp ipp;
 	struct drm_device *drm_dev;
+	void		*dma_priv;
 	struct device	*dev;
 	struct exynos_drm_ipp_task	*task;
 	struct exynos_drm_ipp_formats	*formats;
@@ -1133,7 +1134,7 @@ static int fimc_bind(struct device *dev, struct device *master, void *data)
 
 	ctx->drm_dev = drm_dev;
 	ipp->drm_dev = drm_dev;
-	exynos_drm_register_dma(drm_dev, dev);
+	exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv);
 
 	exynos_drm_ipp_register(dev, ipp, &ipp_funcs,
 			DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE |
@@ -1153,7 +1154,7 @@ static void fimc_unbind(struct device *dev, struct device *master,
 	struct exynos_drm_ipp *ipp = &ctx->ipp;
 
 	exynos_drm_ipp_unregister(dev, ipp);
-	exynos_drm_unregister_dma(drm_dev, dev);
+	exynos_drm_unregister_dma(drm_dev, dev, &ctx->dma_priv);
 }
 
 static const struct component_ops fimc_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 8d0a929104e53..34e6b22173fae 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -167,6 +167,7 @@ static struct fimd_driver_data exynos5420_fimd_driver_data = {
 struct fimd_context {
 	struct device			*dev;
 	struct drm_device		*drm_dev;
+	void				*dma_priv;
 	struct exynos_drm_crtc		*crtc;
 	struct exynos_drm_plane		planes[WINDOWS_NR];
 	struct exynos_drm_plane_config	configs[WINDOWS_NR];
@@ -1090,7 +1091,7 @@ static int fimd_bind(struct device *dev, struct device *master, void *data)
 	if (is_drm_iommu_supported(drm_dev))
 		fimd_clear_channels(ctx->crtc);
 
-	return exynos_drm_register_dma(drm_dev, dev);
+	return exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv);
 }
 
 static void fimd_unbind(struct device *dev, struct device *master,
@@ -1100,7 +1101,7 @@ static void fimd_unbind(struct device *dev, struct device *master,
 
 	fimd_disable(ctx->crtc);
 
-	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev);
+	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv);
 
 	if (ctx->encoder)
 		exynos_dpi_remove(ctx->encoder);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index 2a3382d43bc90..fcee33a43aca3 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -232,6 +232,7 @@ struct g2d_runqueue_node {
 
 struct g2d_data {
 	struct device			*dev;
+	void				*dma_priv;
 	struct clk			*gate_clk;
 	void __iomem			*regs;
 	int				irq;
@@ -1409,7 +1410,7 @@ static int g2d_bind(struct device *dev, struct device *master, void *data)
 		return ret;
 	}
 
-	ret = exynos_drm_register_dma(drm_dev, dev);
+	ret = exynos_drm_register_dma(drm_dev, dev, &g2d->dma_priv);
 	if (ret < 0) {
 		dev_err(dev, "failed to enable iommu.\n");
 		g2d_fini_cmdlist(g2d);
@@ -1434,7 +1435,7 @@ static void g2d_unbind(struct device *dev, struct device *master, void *data)
 	priv->g2d_dev = NULL;
 
 	cancel_work_sync(&g2d->runqueue_work);
-	exynos_drm_unregister_dma(g2d->drm_dev, dev);
+	exynos_drm_unregister_dma(g2d->drm_dev, dev, &g2d->dma_priv);
 }
 
 static const struct component_ops g2d_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 88b6fcaa20be0..45e9aee8366a8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -97,6 +97,7 @@ struct gsc_scaler {
 struct gsc_context {
 	struct exynos_drm_ipp ipp;
 	struct drm_device *drm_dev;
+	void		*dma_priv;
 	struct device	*dev;
 	struct exynos_drm_ipp_task	*task;
 	struct exynos_drm_ipp_formats	*formats;
@@ -1169,7 +1170,7 @@ static int gsc_bind(struct device *dev, struct device *master, void *data)
 
 	ctx->drm_dev = drm_dev;
 	ctx->drm_dev = drm_dev;
-	exynos_drm_register_dma(drm_dev, dev);
+	exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv);
 
 	exynos_drm_ipp_register(dev, ipp, &ipp_funcs,
 			DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE |
@@ -1189,7 +1190,7 @@ static void gsc_unbind(struct device *dev, struct device *master,
 	struct exynos_drm_ipp *ipp = &ctx->ipp;
 
 	exynos_drm_ipp_unregister(dev, ipp);
-	exynos_drm_unregister_dma(drm_dev, dev);
+	exynos_drm_unregister_dma(drm_dev, dev, &ctx->dma_priv);
 }
 
 static const struct component_ops gsc_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index b98482990d1ad..dafa87b820529 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -56,6 +56,7 @@ struct rot_variant {
 struct rot_context {
 	struct exynos_drm_ipp ipp;
 	struct drm_device *drm_dev;
+	void		*dma_priv;
 	struct device	*dev;
 	void __iomem	*regs;
 	struct clk	*clock;
@@ -243,7 +244,7 @@ static int rotator_bind(struct device *dev, struct device *master, void *data)
 
 	rot->drm_dev = drm_dev;
 	ipp->drm_dev = drm_dev;
-	exynos_drm_register_dma(drm_dev, dev);
+	exynos_drm_register_dma(drm_dev, dev, &rot->dma_priv);
 
 	exynos_drm_ipp_register(dev, ipp, &ipp_funcs,
 			   DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE,
@@ -261,7 +262,7 @@ static void rotator_unbind(struct device *dev, struct device *master,
 	struct exynos_drm_ipp *ipp = &rot->ipp;
 
 	exynos_drm_ipp_unregister(dev, ipp);
-	exynos_drm_unregister_dma(rot->drm_dev, rot->dev);
+	exynos_drm_unregister_dma(rot->drm_dev, rot->dev, &rot->dma_priv);
 }
 
 static const struct component_ops rotator_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c
index 497973e9b2c55..93c43c8d914ee 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_scaler.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c
@@ -39,6 +39,7 @@ struct scaler_data {
 struct scaler_context {
 	struct exynos_drm_ipp		ipp;
 	struct drm_device		*drm_dev;
+	void				*dma_priv;
 	struct device			*dev;
 	void __iomem			*regs;
 	struct clk			*clock[SCALER_MAX_CLK];
@@ -450,7 +451,7 @@ static int scaler_bind(struct device *dev, struct device *master, void *data)
 
 	scaler->drm_dev = drm_dev;
 	ipp->drm_dev = drm_dev;
-	exynos_drm_register_dma(drm_dev, dev);
+	exynos_drm_register_dma(drm_dev, dev, &scaler->dma_priv);
 
 	exynos_drm_ipp_register(dev, ipp, &ipp_funcs,
 			DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE |
@@ -470,7 +471,8 @@ static void scaler_unbind(struct device *dev, struct device *master,
 	struct exynos_drm_ipp *ipp = &scaler->ipp;
 
 	exynos_drm_ipp_unregister(dev, ipp);
-	exynos_drm_unregister_dma(scaler->drm_dev, scaler->dev);
+	exynos_drm_unregister_dma(scaler->drm_dev, scaler->dev,
+				  &scaler->dma_priv);
 }
 
 static const struct component_ops scaler_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 7b24338fad3c8..22f494145411a 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -94,6 +94,7 @@ struct mixer_context {
 	struct platform_device *pdev;
 	struct device		*dev;
 	struct drm_device	*drm_dev;
+	void			*dma_priv;
 	struct exynos_drm_crtc	*crtc;
 	struct exynos_drm_plane	planes[MIXER_WIN_NR];
 	unsigned long		flags;
@@ -894,12 +895,14 @@ static int mixer_initialize(struct mixer_context *mixer_ctx,
 		}
 	}
 
-	return exynos_drm_register_dma(drm_dev, mixer_ctx->dev);
+	return exynos_drm_register_dma(drm_dev, mixer_ctx->dev,
+				       &mixer_ctx->dma_priv);
 }
 
 static void mixer_ctx_remove(struct mixer_context *mixer_ctx)
 {
-	exynos_drm_unregister_dma(mixer_ctx->drm_dev, mixer_ctx->dev);
+	exynos_drm_unregister_dma(mixer_ctx->drm_dev, mixer_ctx->dev,
+				  &mixer_ctx->dma_priv);
 }
 
 static int mixer_enable_vblank(struct exynos_drm_crtc *crtc)
-- 
2.20.1

[PATCH AUTOSEL 5.4 49/73] i2c: i801: Do not add ICH_RES_IO_SMI for the iTCO_wdt device

[Sasha Levin]

From: Mika Westerberg <mika.westerberg@linux.intel.com>

[ Upstream commit 04bbb97d1b732b2d197f103c5818f5c214a4cf81 ]

Martin noticed that nct6775 driver does not load properly on his system
in v5.4+ kernels. The issue was bisected to commit b84398d6d7f9 ("i2c:
i801: Use iTCO version 6 in Cannon Lake PCH and beyond") but it is
likely not the culprit because the faulty code has been in the driver
already since commit 9424693035a5 ("i2c: i801: Create iTCO device on
newer Intel PCHs"). So more likely some commit that added PCI IDs of
recent chipsets made the driver to create the iTCO_wdt device on Martins
system.

The issue was debugged to be PCI configuration access to the PMC device
that is not present. This returns all 1's when read and this caused the
iTCO_wdt driver to accidentally request resourses used by nct6775.

It turns out that the SMI resource is only required for some ancient
systems, not the ones supported by this driver. For this reason do not
populate the SMI resource at all and drop all the related code. The
driver now always populates the main I/O resource and only in case of SPT
(Intel Sunrisepoint) compatible devices it adds another resource for the
NO_REBOOT bit. These two resources are of different types so
platform_get_resource() used by the iTCO_wdt driver continues to find
the both resources at index 0.

Link: https://lore.kernel.org/linux-hwmon/CAM1AHpQ4196tyD=HhBu-2donSsuogabkfP03v1YF26Q7_BgvgA@mail.gmail.com/
Fixes: 9424693035a5 ("i2c: i801: Create iTCO device on newer Intel PCHs")
[wsa: complete fix needs all of http://patchwork.ozlabs.org/project/linux-i2c/list/?series=160959&state=*]
Reported-by: Martin Volf <martin.volf.42@gmail.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/i2c/busses/i2c-i801.c | 45 ++++++++++-------------------------
 1 file changed, 12 insertions(+), 33 deletions(-)

diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index f1c714acc2806..3ff6fbd79b127 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -129,11 +129,6 @@
 #define TCOBASE		0x050
 #define TCOCTL		0x054
 
-#define ACPIBASE		0x040
-#define ACPIBASE_SMI_OFF	0x030
-#define ACPICTRL		0x044
-#define ACPICTRL_EN		0x080
-
 #define SBREG_BAR		0x10
 #define SBREG_SMBCTRL		0xc6000c
 #define SBREG_SMBCTRL_DNV	0xcf000c
@@ -1544,7 +1539,7 @@ i801_add_tco_spt(struct i801_priv *priv, struct pci_dev *pci_dev,
 		pci_bus_write_config_byte(pci_dev->bus, devfn, 0xe1, hidden);
 	spin_unlock(&p2sb_spinlock);
 
-	res = &tco_res[ICH_RES_MEM_OFF];
+	res = &tco_res[1];
 	if (pci_dev->device == PCI_DEVICE_ID_INTEL_DNV_SMBUS)
 		res->start = (resource_size_t)base64_addr + SBREG_SMBCTRL_DNV;
 	else
@@ -1554,7 +1549,7 @@ i801_add_tco_spt(struct i801_priv *priv, struct pci_dev *pci_dev,
 	res->flags = IORESOURCE_MEM;
 
 	return platform_device_register_resndata(&pci_dev->dev, "iTCO_wdt", -1,
-					tco_res, 3, &spt_tco_platform_data,
+					tco_res, 2, &spt_tco_platform_data,
 					sizeof(spt_tco_platform_data));
 }
 
@@ -1567,17 +1562,16 @@ static struct platform_device *
 i801_add_tco_cnl(struct i801_priv *priv, struct pci_dev *pci_dev,
 		 struct resource *tco_res)
 {
-	return platform_device_register_resndata(&pci_dev->dev, "iTCO_wdt", -1,
-					tco_res, 2, &cnl_tco_platform_data,
-					sizeof(cnl_tco_platform_data));
+	return platform_device_register_resndata(&pci_dev->dev,
+			"iTCO_wdt", -1, tco_res, 1, &cnl_tco_platform_data,
+			sizeof(cnl_tco_platform_data));
 }
 
 static void i801_add_tco(struct i801_priv *priv)
 {
-	u32 base_addr, tco_base, tco_ctl, ctrl_val;
 	struct pci_dev *pci_dev = priv->pci_dev;
-	struct resource tco_res[3], *res;
-	unsigned int devfn;
+	struct resource tco_res[2], *res;
+	u32 tco_base, tco_ctl;
 
 	/* If we have ACPI based watchdog use that instead */
 	if (acpi_has_watchdog())
@@ -1592,30 +1586,15 @@ static void i801_add_tco(struct i801_priv *priv)
 		return;
 
 	memset(tco_res, 0, sizeof(tco_res));
-
-	res = &tco_res[ICH_RES_IO_TCO];
-	res->start = tco_base & ~1;
-	res->end = res->start + 32 - 1;
-	res->flags = IORESOURCE_IO;
-
 	/*
-	 * Power Management registers.
+	 * Always populate the main iTCO IO resource here. The second entry
+	 * for NO_REBOOT MMIO is filled by the SPT specific function.
 	 */
-	devfn = PCI_DEVFN(PCI_SLOT(pci_dev->devfn), 2);
-	pci_bus_read_config_dword(pci_dev->bus, devfn, ACPIBASE, &base_addr);
-
-	res = &tco_res[ICH_RES_IO_SMI];
-	res->start = (base_addr & ~1) + ACPIBASE_SMI_OFF;
-	res->end = res->start + 3;
+	res = &tco_res[0];
+	res->start = tco_base & ~1;
+	res->end = res->start + 32 - 1;
 	res->flags = IORESOURCE_IO;
 
-	/*
-	 * Enable the ACPI I/O space.
-	 */
-	pci_bus_read_config_dword(pci_dev->bus, devfn, ACPICTRL, &ctrl_val);
-	ctrl_val |= ACPICTRL_EN;
-	pci_bus_write_config_dword(pci_dev->bus, devfn, ACPICTRL, ctrl_val);
-
 	if (priv->features & FEATURE_TCO_CNL)
 		priv->tco_pdev = i801_add_tco_cnl(priv, pci_dev, tco_res);
 	else
-- 
2.20.1

Re: [PATCH AUTOSEL 5.4 49/73] i2c: i801: Do not add ICH_RES_IO_SMI for the iTCO_wdt device

[Wolfram Sang]

[-- Attachment #1: Type: text/plain, Size: 263 bytes --]


> [wsa: complete fix needs all of http://patchwork.ozlabs.org/project/linux-i2c/list/?series=160959&state=*]

Please take care of the line above if you want to backport. I don't
think the dependencies are suitable for stable, so they don't have the
stable tag.


[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

Re: [PATCH AUTOSEL 5.4 49/73] i2c: i801: Do not add ICH_RES_IO_SMI for the iTCO_wdt device

[Sasha Levin]

On Thu, Mar 19, 2020 at 08:30:21AM +0100, Wolfram Sang wrote:
>
>> [wsa: complete fix needs all of http://patchwork.ozlabs.org/project/linux-i2c/list/?series=160959&state=*]
>
>Please take care of the line above if you want to backport. I don't
>think the dependencies are suitable for stable, so they don't have the
>stable tag.

I'll drop it, thanks!

-- 
Thanks,
Sasha

[PATCH AUTOSEL 5.4 50/73] iommu/vt-d: Fix RCU-list bugs in intel_iommu_init()

[Sasha Levin]

From: Qian Cai <cai@lca.pw>

[ Upstream commit 2d48ea0efb8887ebba3e3720bb5b738aced4e574 ]

There are several places traverse RCU-list without holding any lock in
intel_iommu_init(). Fix them by acquiring dmar_global_lock.

 WARNING: suspicious RCU usage
 -----------------------------
 drivers/iommu/intel-iommu.c:5216 RCU-list traversed in non-reader section!!

 other info that might help us debug this:

 rcu_scheduler_active = 2, debug_locks = 1
 no locks held by swapper/0/1.

 Call Trace:
  dump_stack+0xa0/0xea
  lockdep_rcu_suspicious+0x102/0x10b
  intel_iommu_init+0x947/0xb13
  pci_iommu_init+0x26/0x62
  do_one_initcall+0xfe/0x500
  kernel_init_freeable+0x45a/0x4f8
  kernel_init+0x11/0x139
  ret_from_fork+0x3a/0x50
 DMAR: Intel(R) Virtualization Technology for Directed I/O

Fixes: d8190dc63886 ("iommu/vt-d: Enable DMA remapping after rmrr mapped")
Signed-off-by: Qian Cai <cai@lca.pw>
Acked-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/intel-iommu.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 760a242d0801d..9b3d169c6ff53 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -5023,6 +5023,7 @@ int __init intel_iommu_init(void)
 
 	init_iommu_pm_ops();
 
+	down_read(&dmar_global_lock);
 	for_each_active_iommu(iommu, drhd) {
 		iommu_device_sysfs_add(&iommu->iommu, NULL,
 				       intel_iommu_groups,
@@ -5030,6 +5031,7 @@ int __init intel_iommu_init(void)
 		iommu_device_set_ops(&iommu->iommu, &intel_iommu_ops);
 		iommu_device_register(&iommu->iommu);
 	}
+	up_read(&dmar_global_lock);
 
 	bus_set_iommu(&pci_bus_type, &intel_iommu_ops);
 	if (si_domain && !hw_pass_through)
@@ -5040,7 +5042,6 @@ int __init intel_iommu_init(void)
 	down_read(&dmar_global_lock);
 	if (probe_acpi_namespace_devices())
 		pr_warn("ACPI name space devices didn't probe correctly\n");
-	up_read(&dmar_global_lock);
 
 	/* Finally, we enable the DMA remapping hardware. */
 	for_each_iommu(iommu, drhd) {
@@ -5049,6 +5050,8 @@ int __init intel_iommu_init(void)
 
 		iommu_disable_protect_mem_regions(iommu);
 	}
+	up_read(&dmar_global_lock);
+
 	pr_info("Intel(R) Virtualization Technology for Directed I/O\n");
 
 	intel_iommu_enabled = 1;
-- 
2.20.1

[PATCH AUTOSEL 5.4 51/73] iommu/vt-d: Silence RCU-list debugging warnings

[Sasha Levin]

From: Qian Cai <cai@lca.pw>

[ Upstream commit f5152416528c2295f35dd9c9bd4fb27c4032413d ]

Similar to the commit 02d715b4a818 ("iommu/vt-d: Fix RCU list debugging
warnings"), there are several other places that call
list_for_each_entry_rcu() outside of an RCU read side critical section
but with dmar_global_lock held. Silence those false positives as well.

 drivers/iommu/intel-iommu.c:4288 RCU-list traversed in non-reader section!!
 1 lock held by swapper/0/1:
  #0: ffffffff935892c8 (dmar_global_lock){+.+.}, at: intel_iommu_init+0x1ad/0xb97

 drivers/iommu/dmar.c:366 RCU-list traversed in non-reader section!!
 1 lock held by swapper/0/1:
  #0: ffffffff935892c8 (dmar_global_lock){+.+.}, at: intel_iommu_init+0x125/0xb97

 drivers/iommu/intel-iommu.c:5057 RCU-list traversed in non-reader section!!
 1 lock held by swapper/0/1:
  #0: ffffffffa71892c8 (dmar_global_lock){++++}, at: intel_iommu_init+0x61a/0xb13

Signed-off-by: Qian Cai <cai@lca.pw>
Acked-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/dmar.c | 3 ++-
 include/linux/dmar.h | 6 ++++--
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 7196cabafb252..6ec5da4d028f9 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -363,7 +363,8 @@ dmar_find_dmaru(struct acpi_dmar_hardware_unit *drhd)
 {
 	struct dmar_drhd_unit *dmaru;
 
-	list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list)
+	list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list,
+				dmar_rcu_check())
 		if (dmaru->segment == drhd->segment &&
 		    dmaru->reg_base_addr == drhd->address)
 			return dmaru;
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index a7cf3599d9a1c..e0d52e9358c9c 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -73,11 +73,13 @@ extern struct list_head dmar_drhd_units;
 	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)
 
 #define for_each_active_drhd_unit(drhd)					\
-	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)		\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list,		\
+				dmar_rcu_check())			\
 		if (drhd->ignored) {} else
 
 #define for_each_active_iommu(i, drhd)					\
-	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)		\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list,		\
+				dmar_rcu_check())			\
 		if (i=drhd->iommu, drhd->ignored) {} else
 
 #define for_each_iommu(i, drhd)						\
-- 
2.20.1

[PATCH AUTOSEL 5.4 52/73] i2c: gpio: suppress error on probe defer

[Sasha Levin]

From: Hamish Martin <hamish.martin@alliedtelesis.co.nz>

[ Upstream commit 3747cd2efe7ecb9604972285ab3f60c96cb753a8 ]

If a GPIO we are trying to use is not available and we are deferring
the probe, don't output an error message.
This seems to have been the intent of commit 05c74778858d
("i2c: gpio: Add support for named gpios in DT") but the error was
still output due to not checking the updated 'retdesc'.

Fixes: 05c74778858d ("i2c: gpio: Add support for named gpios in DT")
Signed-off-by: Hamish Martin <hamish.martin@alliedtelesis.co.nz>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/i2c/busses/i2c-gpio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-gpio.c b/drivers/i2c/busses/i2c-gpio.c
index 3a9e840a35466..a4a6825c87583 100644
--- a/drivers/i2c/busses/i2c-gpio.c
+++ b/drivers/i2c/busses/i2c-gpio.c
@@ -348,7 +348,7 @@ static struct gpio_desc *i2c_gpio_get_desc(struct device *dev,
 	if (ret == -ENOENT)
 		retdesc = ERR_PTR(-EPROBE_DEFER);
 
-	if (ret != -EPROBE_DEFER)
+	if (PTR_ERR(retdesc) != -EPROBE_DEFER)
 		dev_err(dev, "error trying to get descriptor: %d\n", ret);
 
 	return retdesc;
-- 
2.20.1

[PATCH AUTOSEL 5.4 53/73] s390/qeth: don't reset default_out_queue

[Sasha Levin]

From: Julian Wiedmann <jwi@linux.ibm.com>

[ Upstream commit 240c1948491b81cfe40f84ea040a8f2a4966f101 ]

When an OSA device in prio-queue setup is reduced to 1 TX queue due to
HW restrictions, we reset its the default_out_queue to 0.

In the old code this was needed so that qeth_get_priority_queue() gets
the queue selection right. But with proper multiqueue support we already
reduced dev->real_num_tx_queues to 1, and so the stack puts all traffic
on txq 0 without even calling .ndo_select_queue.

Thus we can preserve the user's configuration, and apply it if the OSA
device later re-gains support for multiple TX queues.

Fixes: 73dc2daf110f ("s390/qeth: add TX multiqueue support for OSA devices")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/s390/net/qeth_core_main.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index b727d1e34523e..ac8ad951a4203 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1244,7 +1244,6 @@ static int qeth_osa_set_output_queues(struct qeth_card *card, bool single)
 	if (count == 1)
 		dev_info(&card->gdev->dev, "Priority Queueing not supported\n");
 
-	card->qdio.default_out_queue = single ? 0 : QETH_DEFAULT_QUEUE;
 	card->qdio.no_out_queues = count;
 	return 0;
 }
-- 
2.20.1

[PATCH AUTOSEL 5.4 54/73] s390/qeth: handle error when backing RX buffer

[Sasha Levin]

From: Julian Wiedmann <jwi@linux.ibm.com>

[ Upstream commit 17413852804d7e86e6f0576cca32c1541817800e ]

qeth_init_qdio_queues() fills the RX ring with an initial set of
RX buffers. If qeth_init_input_buffer() fails to back one of the RX
buffers with memory, we need to bail out and report the error.

Fixes: 4a71df50047f ("qeth: new qeth device driver")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/s390/net/qeth_core_main.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index ac8ad951a4203..fe70e9875bde0 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -2633,12 +2633,12 @@ static int qeth_init_input_buffer(struct qeth_card *card,
 		buf->rx_skb = netdev_alloc_skb(card->dev,
 					       QETH_RX_PULL_LEN + ETH_HLEN);
 		if (!buf->rx_skb)
-			return 1;
+			return -ENOMEM;
 	}
 
 	pool_entry = qeth_find_free_buffer_pool_entry(card);
 	if (!pool_entry)
-		return 1;
+		return -ENOBUFS;
 
 	/*
 	 * since the buffer is accessed only from the input_tasklet
@@ -2670,10 +2670,15 @@ int qeth_init_qdio_queues(struct qeth_card *card)
 	/* inbound queue */
 	qdio_reset_buffers(card->qdio.in_q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q);
 	memset(&card->rx, 0, sizeof(struct qeth_rx));
+
 	qeth_initialize_working_pool_list(card);
 	/*give only as many buffers to hardware as we have buffer pool entries*/
-	for (i = 0; i < card->qdio.in_buf_pool.buf_count - 1; ++i)
-		qeth_init_input_buffer(card, &card->qdio.in_q->bufs[i]);
+	for (i = 0; i < card->qdio.in_buf_pool.buf_count - 1; i++) {
+		rc = qeth_init_input_buffer(card, &card->qdio.in_q->bufs[i]);
+		if (rc)
+			return rc;
+	}
+
 	card->qdio.in_q->next_buf_to_init =
 		card->qdio.in_buf_pool.buf_count - 1;
 	rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, 0, 0,
-- 
2.20.1

[PATCH AUTOSEL 5.4 55/73] scsi: ipr: Fix softlockup when rescanning devices in petitboot

[Sasha Levin]

From: Wen Xiong <wenxiong@linux.vnet.ibm.com>

[ Upstream commit 394b61711f3ce33f75bf70a3e22938464a13b3ee ]

When trying to rescan disks in petitboot shell, we hit the following
softlockup stacktrace:

Kernel panic - not syncing: System is deadlocked on memory
[  241.223394] CPU: 32 PID: 693 Comm: sh Not tainted 5.4.16-openpower1 #1
[  241.223406] Call Trace:
[  241.223415] [c0000003f07c3180] [c000000000493fc4] dump_stack+0xa4/0xd8 (unreliable)
[  241.223432] [c0000003f07c31c0] [c00000000007d4ac] panic+0x148/0x3cc
[  241.223446] [c0000003f07c3260] [c000000000114b10] out_of_memory+0x468/0x4c4
[  241.223461] [c0000003f07c3300] [c0000000001472b0] __alloc_pages_slowpath+0x594/0x6d8
[  241.223476] [c0000003f07c3420] [c00000000014757c] __alloc_pages_nodemask+0x188/0x1a4
[  241.223492] [c0000003f07c34a0] [c000000000153e10] alloc_pages_current+0xcc/0xd8
[  241.223508] [c0000003f07c34e0] [c0000000001577ac] alloc_slab_page+0x30/0x98
[  241.223524] [c0000003f07c3520] [c0000000001597fc] new_slab+0x138/0x40c
[  241.223538] [c0000003f07c35f0] [c00000000015b204] ___slab_alloc+0x1e4/0x404
[  241.223552] [c0000003f07c36c0] [c00000000015b450] __slab_alloc+0x2c/0x48
[  241.223566] [c0000003f07c36f0] [c00000000015b754] kmem_cache_alloc_node+0x9c/0x1b4
[  241.223582] [c0000003f07c3760] [c000000000218c48] blk_alloc_queue_node+0x34/0x270
[  241.223599] [c0000003f07c37b0] [c000000000226574] blk_mq_init_queue+0x2c/0x78
[  241.223615] [c0000003f07c37e0] [c0000000002ff710] scsi_mq_alloc_queue+0x28/0x70
[  241.223631] [c0000003f07c3810] [c0000000003005b8] scsi_alloc_sdev+0x184/0x264
[  241.223647] [c0000003f07c38a0] [c000000000300ba0] scsi_probe_and_add_lun+0x288/0xa3c
[  241.223663] [c0000003f07c3a00] [c000000000301768] __scsi_scan_target+0xcc/0x478
[  241.223679] [c0000003f07c3b20] [c000000000301c64] scsi_scan_channel.part.9+0x74/0x7c
[  241.223696] [c0000003f07c3b70] [c000000000301df4] scsi_scan_host_selected+0xe0/0x158
[  241.223712] [c0000003f07c3bd0] [c000000000303f04] store_scan+0x104/0x114
[  241.223727] [c0000003f07c3cb0] [c0000000002d5ac4] dev_attr_store+0x30/0x4c
[  241.223741] [c0000003f07c3cd0] [c0000000001dbc34] sysfs_kf_write+0x64/0x78
[  241.223756] [c0000003f07c3cf0] [c0000000001da858] kernfs_fop_write+0x170/0x1b8
[  241.223773] [c0000003f07c3d40] [c0000000001621fc] __vfs_write+0x34/0x60
[  241.223787] [c0000003f07c3d60] [c000000000163c2c] vfs_write+0xa8/0xcc
[  241.223802] [c0000003f07c3db0] [c000000000163df4] ksys_write+0x70/0xbc
[  241.223816] [c0000003f07c3e20] [c00000000000b40c] system_call+0x5c/0x68

As a part of the scan process Linux will allocate and configure a
scsi_device for each target to be scanned. If the device is not present,
then the scsi_device is torn down. As a part of scsi_device teardown a
workqueue item will be scheduled and the lockups we see are because there
are 250k workqueue items to be processed.  Accoding to the specification of
SIS-64 sas controller, max_channel should be decreased on SIS-64 adapters
to 4.

The patch fixes softlockup issue.

Thanks for Oliver Halloran's help with debugging and explanation!

Link: https://lore.kernel.org/r/1583510248-23672-1-git-send-email-wenxiong@linux.vnet.ibm.com
Signed-off-by: Wen Xiong <wenxiong@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/ipr.c | 3 ++-
 drivers/scsi/ipr.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 079c04bc448af..7a57b61f0340e 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -9947,6 +9947,7 @@ static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg,
 	ioa_cfg->max_devs_supported = ipr_max_devs;
 
 	if (ioa_cfg->sis64) {
+		host->max_channel = IPR_MAX_SIS64_BUSES;
 		host->max_id = IPR_MAX_SIS64_TARGETS_PER_BUS;
 		host->max_lun = IPR_MAX_SIS64_LUNS_PER_TARGET;
 		if (ipr_max_devs > IPR_MAX_SIS64_DEVS)
@@ -9955,6 +9956,7 @@ static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg,
 					   + ((sizeof(struct ipr_config_table_entry64)
 					       * ioa_cfg->max_devs_supported)));
 	} else {
+		host->max_channel = IPR_VSET_BUS;
 		host->max_id = IPR_MAX_NUM_TARGETS_PER_BUS;
 		host->max_lun = IPR_MAX_NUM_LUNS_PER_TARGET;
 		if (ipr_max_devs > IPR_MAX_PHYSICAL_DEVS)
@@ -9964,7 +9966,6 @@ static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg,
 					       * ioa_cfg->max_devs_supported)));
 	}
 
-	host->max_channel = IPR_VSET_BUS;
 	host->unique_id = host->host_no;
 	host->max_cmd_len = IPR_MAX_CDB_LEN;
 	host->can_queue = ioa_cfg->max_cmds;
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index a67baeb36d1f7..b97aa9ac2ffe5 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -1300,6 +1300,7 @@ struct ipr_resource_entry {
 #define IPR_ARRAY_VIRTUAL_BUS			0x1
 #define IPR_VSET_VIRTUAL_BUS			0x2
 #define IPR_IOAFP_VIRTUAL_BUS			0x3
+#define IPR_MAX_SIS64_BUSES			0x4
 
 #define IPR_GET_RES_PHYS_LOC(res) \
 	(((res)->bus << 24) | ((res)->target << 8) | (res)->lun)
-- 
2.20.1

[PATCH AUTOSEL 5.4 56/73] nl80211: add missing attribute validation for critical protocol indication

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit 0e1a1d853ecedc99da9d27f9f5c376935547a0e2 ]

Add missing attribute validation for critical protocol fields
to the netlink policy.

Fixes: 5de17984898c ("cfg80211: introduce critical protocol indication from user-space")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20200303051058.4089398-2-kuba@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/wireless/nl80211.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 17514744af9e0..9ca16ca0528ac 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -530,6 +530,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_MDID] = { .type = NLA_U16 },
 	[NL80211_ATTR_IE_RIC] = { .type = NLA_BINARY,
 				  .len = IEEE80211_MAX_DATA_LEN },
+	[NL80211_ATTR_CRIT_PROT_ID] = { .type = NLA_U16 },
+	[NL80211_ATTR_MAX_CRIT_PROT_DURATION] = { .type = NLA_U16 },
 	[NL80211_ATTR_PEER_AID] =
 		NLA_POLICY_RANGE(NLA_U16, 1, IEEE80211_MAX_AID),
 	[NL80211_ATTR_CH_SWITCH_COUNT] = { .type = NLA_U32 },
-- 
2.20.1

[PATCH AUTOSEL 5.4 57/73] nl80211: add missing attribute validation for beacon report scanning

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit 056e9375e1f3c4bf2fd49b70258c7daf788ecd9d ]

Add missing attribute validation for beacon report scanning
to the netlink policy.

Fixes: 1d76250bd34a ("nl80211: support beacon report scanning")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20200303051058.4089398-3-kuba@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/wireless/nl80211.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 9ca16ca0528ac..f0c6c522964c2 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -469,6 +469,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_WOWLAN_TRIGGERS] = { .type = NLA_NESTED },
 	[NL80211_ATTR_STA_PLINK_STATE] =
 		NLA_POLICY_MAX(NLA_U8, NUM_NL80211_PLINK_STATES - 1),
+	[NL80211_ATTR_MEASUREMENT_DURATION] = { .type = NLA_U16 },
+	[NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY] = { .type = NLA_FLAG },
 	[NL80211_ATTR_MESH_PEER_AID] =
 		NLA_POLICY_RANGE(NLA_U16, 1, IEEE80211_MAX_AID),
 	[NL80211_ATTR_SCHED_SCAN_INTERVAL] = { .type = NLA_U32 },
-- 
2.20.1

[PATCH AUTOSEL 5.4 58/73] nl80211: add missing attribute validation for channel switch

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit 5cde05c61cbe13cbb3fa66d52b9ae84f7975e5e6 ]

Add missing attribute validation for NL80211_ATTR_OPER_CLASS
to the netlink policy.

Fixes: 1057d35ede5d ("cfg80211: introduce TDLS channel switch commands")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20200303051058.4089398-4-kuba@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/wireless/nl80211.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index f0c6c522964c2..321c132747ce7 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -564,6 +564,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 		NLA_POLICY_MAX(NLA_U8, IEEE80211_NUM_UPS - 1),
 	[NL80211_ATTR_ADMITTED_TIME] = { .type = NLA_U16 },
 	[NL80211_ATTR_SMPS_MODE] = { .type = NLA_U8 },
+	[NL80211_ATTR_OPER_CLASS] = { .type = NLA_U8 },
 	[NL80211_ATTR_MAC_MASK] = {
 		.type = NLA_EXACT_LEN_WARN,
 		.len = ETH_ALEN
-- 
2.20.1

[PATCH AUTOSEL 5.4 59/73] mac80211: Do not send mesh HWMP PREQ if HWMP is disabled

[Sasha Levin]

From: Nicolas Cavallari <nicolas.cavallari@green-communications.fr>

[ Upstream commit ba32679cac50c38fdf488296f96b1f3175532b8e ]

When trying to transmit to an unknown destination, the mesh code would
unconditionally transmit a HWMP PREQ even if HWMP is not the current
path selection algorithm.

Signed-off-by: Nicolas Cavallari <nicolas.cavallari@green-communications.fr>
Link: https://lore.kernel.org/r/20200305140409.12204-1-cavallar@lri.fr
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/mac80211/mesh_hwmp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index d699833703819..38a0383dfbcfa 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -1152,7 +1152,8 @@ int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
-	if (!(mpath->flags & MESH_PATH_RESOLVING))
+	if (!(mpath->flags & MESH_PATH_RESOLVING) &&
+	    mesh_path_sel_is_hwmp(sdata))
 		mesh_queue_preq(mpath, PREQ_Q_F_START);
 
 	if (skb_queue_len(&mpath->frame_queue) >= MESH_FRAME_QUEUE_LEN)
-- 
2.20.1

[PATCH AUTOSEL 5.4 60/73] driver code: clarify and fix platform device DMA mask allocation

[Sasha Levin]

From: Christoph Hellwig <hch@lst.de>

[ Upstream commit e3a36eb6dfaeea8175c05d5915dcf0b939be6dab ]

This does three inter-related things to clarify the usage of the
platform device dma_mask field. In the process, fix the bug introduced
by cdfee5623290 ("driver core: initialize a default DMA mask for
platform device") that caused Artem Tashkinov's laptop to not boot with
newer Fedora kernels.

This does:

 - First off, rename the field to "platform_dma_mask" to make it
   greppable.

   We have way too many different random fields called "dma_mask" in
   various data structures, where some of them are actual masks, and
   some of them are just pointers to the mask. And the structures all
   have pointers to each other, or embed each other inside themselves,
   and "pdev" sometimes means "platform device" and sometimes it means
   "PCI device".

   So to make it clear in the code when you actually use this new field,
   give it a unique name (it really should be something even more unique
   like "platform_device_dma_mask", since it's per platform device, not
   per platform, but that gets old really fast, and this is unique
   enough in context).

   To further clarify when the field gets used, initialize it when we
   actually start using it with the default value.

 - Then, use this field instead of the random one-off allocation in
   platform_device_register_full() that is now unnecessary since we now
   already have a perfectly fine allocation for it in the platform
   device structure.

 - The above then allows us to fix the actual bug, where the error path
   of platform_device_register_full() would unconditionally free the
   platform device DMA allocation with 'kfree()'.

   That kfree() was dont regardless of whether the allocation had been
   done earlier with the (now removed) kmalloc, or whether
   setup_pdev_dma_masks() had already been used and the dma_mask pointer
   pointed to the mask that was part of the platform device.

It seems most people never triggered the error path, or only triggered
it from a call chain that set an explicit pdevinfo->dma_mask value (and
thus caused the unnecessary allocation that was "cleaned up" in the
error path) before calling platform_device_register_full().

Robin Murphy points out that in Artem's case the wdat_wdt driver failed
in platform_device_add(), and that was the one that had called
platform_device_register_full() with pdevinfo.dma_mask = 0, and would
have caused that kfree() of pdev.dma_mask corrupting the heap.

A later unrelated kmalloc() then oopsed due to the heap corruption.

Fixes: cdfee5623290 ("driver core: initialize a default DMA mask for platform device")
Reported-bisected-and-tested-by:  Artem S. Tashkinov <aros@gmx.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/base/platform.c         | 25 ++++++-------------------
 include/linux/platform_device.h |  2 +-
 2 files changed, 7 insertions(+), 20 deletions(-)

diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 60386a32208ff..604a461848c98 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -335,10 +335,10 @@ static void setup_pdev_dma_masks(struct platform_device *pdev)
 {
 	if (!pdev->dev.coherent_dma_mask)
 		pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
-	if (!pdev->dma_mask)
-		pdev->dma_mask = DMA_BIT_MASK(32);
-	if (!pdev->dev.dma_mask)
-		pdev->dev.dma_mask = &pdev->dma_mask;
+	if (!pdev->dev.dma_mask) {
+		pdev->platform_dma_mask = DMA_BIT_MASK(32);
+		pdev->dev.dma_mask = &pdev->platform_dma_mask;
+	}
 };
 
 /**
@@ -634,20 +634,8 @@ struct platform_device *platform_device_register_full(
 	pdev->dev.of_node_reused = pdevinfo->of_node_reused;
 
 	if (pdevinfo->dma_mask) {
-		/*
-		 * This memory isn't freed when the device is put,
-		 * I don't have a nice idea for that though.  Conceptually
-		 * dma_mask in struct device should not be a pointer.
-		 * See http://thread.gmane.org/gmane.linux.kernel.pci/9081
-		 */
-		pdev->dev.dma_mask =
-			kmalloc(sizeof(*pdev->dev.dma_mask), GFP_KERNEL);
-		if (!pdev->dev.dma_mask)
-			goto err;
-
-		kmemleak_ignore(pdev->dev.dma_mask);
-
-		*pdev->dev.dma_mask = pdevinfo->dma_mask;
+		pdev->platform_dma_mask = pdevinfo->dma_mask;
+		pdev->dev.dma_mask = &pdev->platform_dma_mask;
 		pdev->dev.coherent_dma_mask = pdevinfo->dma_mask;
 	}
 
@@ -672,7 +660,6 @@ struct platform_device *platform_device_register_full(
 	if (ret) {
 err:
 		ACPI_COMPANION_SET(&pdev->dev, NULL);
-		kfree(pdev->dev.dma_mask);
 		platform_device_put(pdev);
 		return ERR_PTR(ret);
 	}
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index f2688404d1cd7..569f446502bed 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -24,7 +24,7 @@ struct platform_device {
 	int		id;
 	bool		id_auto;
 	struct device	dev;
-	u64		dma_mask;
+	u64		platform_dma_mask;
 	u32		num_resources;
 	struct resource	*resource;
 
-- 
2.20.1

Re: [PATCH AUTOSEL 5.4 60/73] driver code: clarify and fix platform device DMA mask allocation

[Greg Kroah-Hartman]

On Wed, Mar 18, 2020 at 04:53:24PM -0400, Sasha Levin wrote:
> From: Christoph Hellwig <hch@lst.de>
> 
> [ Upstream commit e3a36eb6dfaeea8175c05d5915dcf0b939be6dab ]

This is already in 5.4.26 and 5.5.10, so no need to try to apply it
again :)

thanks,

greg k-h

[PATCH AUTOSEL 5.4 61/73] dpaa_eth: Remove unnecessary boolean expression in dpaa_get_headroom

[Sasha Levin]

From: Nathan Chancellor <natechancellor@gmail.com>

[ Upstream commit 7395f62d95aafacdb9bd4996ec2f95b4a655d7e6 ]

Clang warns:

drivers/net/ethernet/freescale/dpaa/dpaa_eth.c:2860:9: warning:
converting the result of '?:' with integer constants to a boolean always
evaluates to 'true' [-Wtautological-constant-compare]
        return DPAA_FD_DATA_ALIGNMENT ? ALIGN(headroom,
               ^
drivers/net/ethernet/freescale/dpaa/dpaa_eth.c:131:34: note: expanded
from macro 'DPAA_FD_DATA_ALIGNMENT'
\#define DPAA_FD_DATA_ALIGNMENT  (fman_has_errata_a050385() ? 64 : 16)
                                 ^
1 warning generated.

This was exposed by commit 3c68b8fffb48 ("dpaa_eth: FMan erratum A050385
workaround") even though it appears to have been an issue since the
introductory commit 9ad1a3749333 ("dpaa_eth: add support for DPAA
Ethernet") since DPAA_FD_DATA_ALIGNMENT has never been able to be zero.

Just replace the whole boolean expression with the true branch, as it is
always been true.

Link: https://github.com/ClangBuiltLinux/linux/issues/928
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Reviewed-by: Madalin Bucur <madalin.bucur@oss.nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index e130233b50853..00c4beb760c35 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2770,9 +2770,7 @@ static inline u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl)
 	headroom = (u16)(bl->priv_data_size + DPAA_PARSE_RESULTS_SIZE +
 		DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE);
 
-	return DPAA_FD_DATA_ALIGNMENT ? ALIGN(headroom,
-					      DPAA_FD_DATA_ALIGNMENT) :
-					headroom;
+	return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT);
 }
 
 static int dpaa_eth_probe(struct platform_device *pdev)
-- 
2.20.1

[PATCH AUTOSEL 5.4 62/73] net: fec: validate the new settings in fec_enet_set_coalesce()

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit ab14961d10d02d20767612c78ce148f6eb85bd58 ]

fec_enet_set_coalesce() validates the previously set params
and if they are within range proceeds to apply the new ones.
The new ones, however, are not validated. This seems backwards,
probably a copy-paste error?

Compile tested only.

Fixes: d851b47b22fc ("net: fec: add interrupt coalescence feature support")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/freescale/fec_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 8336f4cbaf955..3fc8a66e4f41a 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2529,15 +2529,15 @@ fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
 		return -EINVAL;
 	}
 
-	cycle = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr);
+	cycle = fec_enet_us_to_itr_clock(ndev, ec->rx_coalesce_usecs);
 	if (cycle > 0xFFFF) {
 		dev_err(dev, "Rx coalesced usec exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
-	cycle = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr);
+	cycle = fec_enet_us_to_itr_clock(ndev, ec->tx_coalesce_usecs);
 	if (cycle > 0xFFFF) {
-		dev_err(dev, "Rx coalesced usec exceed hardware limitation\n");
+		dev_err(dev, "Tx coalesced usec exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 63/73] sxgbe: Fix off by one in samsung driver strncpy size arg

[Sasha Levin]

From: Dominik Czarnota <dominik.b.czarnota@gmail.com>

[ Upstream commit f3cc008bf6d59b8d93b4190e01d3e557b0040e15 ]

This patch fixes an off-by-one error in strncpy size argument in
drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c. The issue is that in:

        strncmp(opt, "eee_timer:", 6)

the passed string literal: "eee_timer:" has 10 bytes (without the NULL
byte) and the passed size argument is 6. As a result, the logic will
also accept other, malformed strings, e.g. "eee_tiXXX:".

This bug doesn't seem to have any security impact since its present in
module's cmdline parsing code.

Signed-off-by: Dominik Czarnota <dominik.b.czarnota@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index c56fcbb370665..38767d7979147 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -2279,7 +2279,7 @@ static int __init sxgbe_cmdline_opt(char *str)
 	if (!str || !*str)
 		return -EINVAL;
 	while ((opt = strsep(&str, ",")) != NULL) {
-		if (!strncmp(opt, "eee_timer:", 6)) {
+		if (!strncmp(opt, "eee_timer:", 10)) {
 			if (kstrtoint(opt + 10, 0, &eee_timer))
 				goto err;
 		}
-- 
2.20.1

[PATCH AUTOSEL 5.4 64/73] net: mvmdio: avoid error message for optional IRQ

[Sasha Levin]

From: Chris Packham <chris.packham@alliedtelesis.co.nz>

[ Upstream commit e1f550dc44a4d535da4e25ada1b0eaf8f3417929 ]

Per the dt-binding the interrupt is optional so use
platform_get_irq_optional() instead of platform_get_irq(). Since
commit 7723f4c5ecdb ("driver core: platform: Add an error message to
platform_get_irq*()") platform_get_irq() produces an error message

  orion-mdio f1072004.mdio: IRQ index 0 not found

which is perfectly normal if one hasn't specified the optional property
in the device tree.

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/marvell/mvmdio.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index 0b9e851f3da4f..d2e2dc5384287 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -347,7 +347,7 @@ static int orion_mdio_probe(struct platform_device *pdev)
 	}
 
 
-	dev->err_interrupt = platform_get_irq(pdev, 0);
+	dev->err_interrupt = platform_get_irq_optional(pdev, 0);
 	if (dev->err_interrupt > 0 &&
 	    resource_size(r) < MVMDIO_ERR_INT_MASK + 4) {
 		dev_err(&pdev->dev,
@@ -364,8 +364,8 @@ static int orion_mdio_probe(struct platform_device *pdev)
 		writel(MVMDIO_ERR_INT_SMI_DONE,
 			dev->regs + MVMDIO_ERR_INT_MASK);
 
-	} else if (dev->err_interrupt == -EPROBE_DEFER) {
-		ret = -EPROBE_DEFER;
+	} else if (dev->err_interrupt < 0) {
+		ret = dev->err_interrupt;
 		goto out_mdio;
 	}
 
-- 
2.20.1

Re: [PATCH AUTOSEL 5.4 64/73] net: mvmdio: avoid error message for optional IRQ

[Chris Packham]

On Wed, 2020-03-18 at 16:53 -0400, Sasha Levin wrote:
> From: Chris Packham <chris.packham@alliedtelesis.co.nz>
> 
> [ Upstream commit e1f550dc44a4d535da4e25ada1b0eaf8f3417929 ]
> 
> Per the dt-binding the interrupt is optional so use
> platform_get_irq_optional() instead of platform_get_irq(). Since
> commit 7723f4c5ecdb ("driver core: platform: Add an error message to
> platform_get_irq*()") platform_get_irq() produces an error message
> 
>   orion-mdio f1072004.mdio: IRQ index 0 not found
> 
> which is perfectly normal if one hasn't specified the optional property
> in the device tree.
> 
> Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
> Reviewed-by: Andrew Lunn <andrew@lunn.ch>
> Signed-off-by: David S. Miller <davem@davemloft.net>
> Signed-off-by: Sasha Levin <sashal@kernel.org>
> ---
>  drivers/net/ethernet/marvell/mvmdio.c | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
> index 0b9e851f3da4f..d2e2dc5384287 100644
> --- a/drivers/net/ethernet/marvell/mvmdio.c
> +++ b/drivers/net/ethernet/marvell/mvmdio.c
> @@ -347,7 +347,7 @@ static int orion_mdio_probe(struct platform_device *pdev)
>  	}
>  
>  
> -	dev->err_interrupt = platform_get_irq(pdev, 0);
> +	dev->err_interrupt = platform_get_irq_optional(pdev, 0);
>  	if (dev->err_interrupt > 0 &&
>  	    resource_size(r) < MVMDIO_ERR_INT_MASK + 4) {
>  		dev_err(&pdev->dev,
> @@ -364,8 +364,8 @@ static int orion_mdio_probe(struct platform_device *pdev)
>  		writel(MVMDIO_ERR_INT_SMI_DONE,
>  			dev->regs + MVMDIO_ERR_INT_MASK);
>  
> -	} else if (dev->err_interrupt == -EPROBE_DEFER) {
> -		ret = -EPROBE_DEFER;
> +	} else if (dev->err_interrupt < 0) {
> +		ret = dev->err_interrupt;
>  		goto out_mdio;
>  	}
>  

NAK.

Please don't apply this one. It caused a different bug and was
reverted.

Dave has just applied the correct one to net/master commit id is
fa2632f74e57bbc869c8ad37751a11b6147a3acc

[PATCH AUTOSEL 5.4 65/73] net: hns3: fix "tc qdisc del" failed issue

[Sasha Levin]

From: Yonglong Liu <liuyonglong@huawei.com>

[ Upstream commit 5eb01ddfcfb25e6ebc404a41deae946bde776731 ]

The HNS3 driver supports to configure TC numbers and TC to priority
map via "tc" tool. But when delete the rule, will fail, because
the HNS3 driver needs at least one TC, but the "tc" tool sets TC
number to zero when delete.

This patch makes sure that the TC number is at least one.

Fixes: 30d240dfa2e8 ("net: hns3: Add mqprio hardware offload support in hns3 driver")
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 0c8d2269bc46e..403e0f089f2af 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1596,7 +1596,7 @@ static int hns3_setup_tc(struct net_device *netdev, void *type_data)
 	netif_dbg(h, drv, netdev, "setup tc: num_tc=%u\n", tc);
 
 	return (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ?
-		kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP;
+		kinfo->dcb_ops->setup_tc(h, tc ? tc : 1, prio_tc) : -EOPNOTSUPP;
 }
 
 static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type,
-- 
2.20.1

[PATCH AUTOSEL 5.4 66/73] net: systemport: fix index check to avoid an array out of bounds access

[Sasha Levin]

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

[ Upstream commit c0368595c1639947839c0db8294ee96aca0b3b86 ]

Currently the bounds check on index is off by one and can lead to
an out of bounds access on array priv->filters_loc when index is
RXCHK_BRCM_TAG_MAX.

Fixes: bb9051a2b230 ("net: systemport: Add support for WAKE_FILTER")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 4a27577e137bc..ad86a186ddc5f 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2135,7 +2135,7 @@ static int bcm_sysport_rule_set(struct bcm_sysport_priv *priv,
 		return -ENOSPC;
 
 	index = find_first_zero_bit(priv->filters, RXCHK_BRCM_TAG_MAX);
-	if (index > RXCHK_BRCM_TAG_MAX)
+	if (index >= RXCHK_BRCM_TAG_MAX)
 		return -ENOSPC;
 
 	/* Location is the classification ID, and index is the position
-- 
2.20.1

[PATCH AUTOSEL 5.4 67/73] iommu/vt-d: quirk_ioat_snb_local_iommu: replace WARN_TAINT with pr_warn + add_taint

[Sasha Levin]

From: Hans de Goede <hdegoede@redhat.com>

[ Upstream commit 81ee85d0462410de8eeeec1b9761941fd6ed8c7b ]

Quoting from the comment describing the WARN functions in
include/asm-generic/bug.h:

 * WARN(), WARN_ON(), WARN_ON_ONCE, and so on can be used to report
 * significant kernel issues that need prompt attention if they should ever
 * appear at runtime.
 *
 * Do not use these macros when checking for invalid external inputs

The (buggy) firmware tables which the dmar code was calling WARN_TAINT
for really are invalid external inputs. They are not under the kernel's
control and the issues in them cannot be fixed by a kernel update.
So logging a backtrace, which invites bug reports to be filed about this,
is not helpful.

Fixes: 556ab45f9a77 ("ioat2: catch and recover from broken vtd configurations v6")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20200309182510.373875-1-hdegoede@redhat.com
BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=701847
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/intel-iommu.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 9b3d169c6ff53..be39363244389 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4129,10 +4129,11 @@ static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
 
 	/* we know that the this iommu should be at offset 0xa000 from vtbar */
 	drhd = dmar_find_matched_drhd_unit(pdev);
-	if (WARN_TAINT_ONCE(!drhd || drhd->reg_base_addr - vtbar != 0xa000,
-			    TAINT_FIRMWARE_WORKAROUND,
-			    "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n"))
+	if (!drhd || drhd->reg_base_addr - vtbar != 0xa000) {
+		pr_warn_once(FW_BUG "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n");
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
 		pdev->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
+	}
 }
 DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quirk_ioat_snb_local_iommu);
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 68/73] iommu/vt-d: Fix debugfs register reads

[Sasha Levin]

From: Megha Dey <megha.dey@linux.intel.com>

[ Upstream commit ba3b01d7a6f4ab9f8a0557044c9a7678f64ae070 ]

Commit 6825d3ea6cde ("iommu/vt-d: Add debugfs support to show register
contents") dumps the register contents for all IOMMU devices.

Currently, a 64 bit read(dmar_readq) is done for all the IOMMU registers,
even though some of the registers are 32 bits, which is incorrect.

Use the correct read function variant (dmar_readl/dmar_readq) while
reading the contents of 32/64 bit registers respectively.

Signed-off-by: Megha Dey <megha.dey@linux.intel.com>
Link: https://lore.kernel.org/r/1583784587-26126-2-git-send-email-megha.dey@linux.intel.com
Acked-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/intel-iommu-debugfs.c | 40 ++++++++++++++++++-----------
 include/linux/intel-iommu.h         |  2 ++
 2 files changed, 27 insertions(+), 15 deletions(-)

diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c
index 471f05d452e01..80378c10dd77a 100644
--- a/drivers/iommu/intel-iommu-debugfs.c
+++ b/drivers/iommu/intel-iommu-debugfs.c
@@ -32,38 +32,42 @@ struct iommu_regset {
 
 #define IOMMU_REGSET_ENTRY(_reg_)					\
 	{ DMAR_##_reg_##_REG, __stringify(_reg_) }
-static const struct iommu_regset iommu_regs[] = {
+
+static const struct iommu_regset iommu_regs_32[] = {
 	IOMMU_REGSET_ENTRY(VER),
-	IOMMU_REGSET_ENTRY(CAP),
-	IOMMU_REGSET_ENTRY(ECAP),
 	IOMMU_REGSET_ENTRY(GCMD),
 	IOMMU_REGSET_ENTRY(GSTS),
-	IOMMU_REGSET_ENTRY(RTADDR),
-	IOMMU_REGSET_ENTRY(CCMD),
 	IOMMU_REGSET_ENTRY(FSTS),
 	IOMMU_REGSET_ENTRY(FECTL),
 	IOMMU_REGSET_ENTRY(FEDATA),
 	IOMMU_REGSET_ENTRY(FEADDR),
 	IOMMU_REGSET_ENTRY(FEUADDR),
-	IOMMU_REGSET_ENTRY(AFLOG),
 	IOMMU_REGSET_ENTRY(PMEN),
 	IOMMU_REGSET_ENTRY(PLMBASE),
 	IOMMU_REGSET_ENTRY(PLMLIMIT),
+	IOMMU_REGSET_ENTRY(ICS),
+	IOMMU_REGSET_ENTRY(PRS),
+	IOMMU_REGSET_ENTRY(PECTL),
+	IOMMU_REGSET_ENTRY(PEDATA),
+	IOMMU_REGSET_ENTRY(PEADDR),
+	IOMMU_REGSET_ENTRY(PEUADDR),
+};
+
+static const struct iommu_regset iommu_regs_64[] = {
+	IOMMU_REGSET_ENTRY(CAP),
+	IOMMU_REGSET_ENTRY(ECAP),
+	IOMMU_REGSET_ENTRY(RTADDR),
+	IOMMU_REGSET_ENTRY(CCMD),
+	IOMMU_REGSET_ENTRY(AFLOG),
 	IOMMU_REGSET_ENTRY(PHMBASE),
 	IOMMU_REGSET_ENTRY(PHMLIMIT),
 	IOMMU_REGSET_ENTRY(IQH),
 	IOMMU_REGSET_ENTRY(IQT),
 	IOMMU_REGSET_ENTRY(IQA),
-	IOMMU_REGSET_ENTRY(ICS),
 	IOMMU_REGSET_ENTRY(IRTA),
 	IOMMU_REGSET_ENTRY(PQH),
 	IOMMU_REGSET_ENTRY(PQT),
 	IOMMU_REGSET_ENTRY(PQA),
-	IOMMU_REGSET_ENTRY(PRS),
-	IOMMU_REGSET_ENTRY(PECTL),
-	IOMMU_REGSET_ENTRY(PEDATA),
-	IOMMU_REGSET_ENTRY(PEADDR),
-	IOMMU_REGSET_ENTRY(PEUADDR),
 	IOMMU_REGSET_ENTRY(MTRRCAP),
 	IOMMU_REGSET_ENTRY(MTRRDEF),
 	IOMMU_REGSET_ENTRY(MTRR_FIX64K_00000),
@@ -126,10 +130,16 @@ static int iommu_regset_show(struct seq_file *m, void *unused)
 		 * by adding the offset to the pointer (virtual address).
 		 */
 		raw_spin_lock_irqsave(&iommu->register_lock, flag);
-		for (i = 0 ; i < ARRAY_SIZE(iommu_regs); i++) {
-			value = dmar_readq(iommu->reg + iommu_regs[i].offset);
+		for (i = 0 ; i < ARRAY_SIZE(iommu_regs_32); i++) {
+			value = dmar_readl(iommu->reg + iommu_regs_32[i].offset);
+			seq_printf(m, "%-16s\t0x%02x\t\t0x%016llx\n",
+				   iommu_regs_32[i].regs, iommu_regs_32[i].offset,
+				   value);
+		}
+		for (i = 0 ; i < ARRAY_SIZE(iommu_regs_64); i++) {
+			value = dmar_readq(iommu->reg + iommu_regs_64[i].offset);
 			seq_printf(m, "%-16s\t0x%02x\t\t0x%016llx\n",
-				   iommu_regs[i].regs, iommu_regs[i].offset,
+				   iommu_regs_64[i].regs, iommu_regs_64[i].offset,
 				   value);
 		}
 		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 6d8bf4bdf240d..1e5dad8b8e59b 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -120,6 +120,8 @@
 
 #define dmar_readq(a) readq(a)
 #define dmar_writeq(a,v) writeq(v,a)
+#define dmar_readl(a) readl(a)
+#define dmar_writel(a, v) writel(v, a)
 
 #define DMAR_VER_MAJOR(v)		(((v) & 0xf0) >> 4)
 #define DMAR_VER_MINOR(v)		((v) & 0x0f)
-- 
2.20.1

[PATCH AUTOSEL 5.4 69/73] i2c: acpi: put device when verifying client fails

[Sasha Levin]

From: Wolfram Sang <wsa+renesas@sang-engineering.com>

[ Upstream commit 8daee952b4389729358665fb91949460641659d4 ]

i2c_verify_client() can fail, so we need to put the device when that
happens.

Fixes: 525e6fabeae2 ("i2c / ACPI: add support for ACPI reconfigure notifications")
Reported-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/i2c/i2c-core-acpi.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c
index 62a1c92ab803d..ce70b5288472c 100644
--- a/drivers/i2c/i2c-core-acpi.c
+++ b/drivers/i2c/i2c-core-acpi.c
@@ -394,9 +394,17 @@ EXPORT_SYMBOL_GPL(i2c_acpi_find_adapter_by_handle);
 static struct i2c_client *i2c_acpi_find_client_by_adev(struct acpi_device *adev)
 {
 	struct device *dev;
+	struct i2c_client *client;
 
 	dev = bus_find_device_by_acpi_dev(&i2c_bus_type, adev);
-	return dev ? i2c_verify_client(dev) : NULL;
+	if (!dev)
+		return NULL;
+
+	client = i2c_verify_client(dev);
+	if (!client)
+		put_device(dev);
+
+	return client;
 }
 
 static int i2c_acpi_notify(struct notifier_block *nb, unsigned long value,
-- 
2.20.1

[PATCH AUTOSEL 5.4 70/73] iommu/vt-d: Fix the wrong printing in RHSA parsing

[Sasha Levin]

From: Zhenzhong Duan <zhenzhong.duan@gmail.com>

[ Upstream commit b0bb0c22c4db623f2e7b1a471596fbf1c22c6dc5 ]

When base address in RHSA structure doesn't match base address in
each DRHD structure, the base address in last DRHD is printed out.

This doesn't make sense when there are multiple DRHD units, fix it
by printing the buggy RHSA's base address.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@gmail.com>
Fixes: fd0c8894893cb ("intel-iommu: Set a more specific taint flag for invalid BIOS DMAR tables")
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/dmar.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 6ec5da4d028f9..aa15155b9401f 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -476,7 +476,7 @@ static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
 		1, TAINT_FIRMWARE_WORKAROUND,
 		"Your BIOS is broken; RHSA refers to non-existent DMAR unit at %llx\n"
 		"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
-		drhd->reg_base_addr,
+		rhsa->base_address,
 		dmi_get_system_info(DMI_BIOS_VENDOR),
 		dmi_get_system_info(DMI_BIOS_VERSION),
 		dmi_get_system_info(DMI_PRODUCT_VERSION));
-- 
2.20.1

[PATCH AUTOSEL 5.4 71/73] iommu/vt-d: Ignore devices with out-of-spec domain number

[Sasha Levin]

From: Daniel Drake <drake@endlessm.com>

[ Upstream commit da72a379b2ec0bad3eb265787f7008bead0b040c ]

VMD subdevices are created with a PCI domain ID of 0x10000 or
higher.

These subdevices are also handled like all other PCI devices by
dmar_pci_bus_notifier().

However, when dmar_alloc_pci_notify_info() take records of such devices,
it will truncate the domain ID to a u16 value (in info->seg).
The device at (e.g.) 10000:00:02.0 is then treated by the DMAR code as if
it is 0000:00:02.0.

In the unlucky event that a real device also exists at 0000:00:02.0 and
also has a device-specific entry in the DMAR table,
dmar_insert_dev_scope() will crash on:
   BUG_ON(i >= devices_cnt);

That's basically a sanity check that only one PCI device matches a
single DMAR entry; in this case we seem to have two matching devices.

Fix this by ignoring devices that have a domain number higher than
what can be looked up in the DMAR table.

This problem was carefully diagnosed by Jian-Hong Pan.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Daniel Drake <drake@endlessm.com>
Fixes: 59ce0515cdaf3 ("iommu/vt-d: Update DRHD/RMRR/ATSR device scope caches when PCI hotplug happens")
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/dmar.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index aa15155b9401f..34e705d3b6bb6 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/iommu.h>
 #include <linux/numa.h>
+#include <linux/limits.h>
 #include <asm/irq_remapping.h>
 #include <asm/iommu_table.h>
 
@@ -128,6 +129,13 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event)
 
 	BUG_ON(dev->is_virtfn);
 
+	/*
+	 * Ignore devices that have a domain number higher than what can
+	 * be looked up in DMAR, e.g. VMD subdevices with domain 0x10000
+	 */
+	if (pci_domain_nr(dev->bus) > U16_MAX)
+		return NULL;
+
 	/* Only generate path[] for device addition event */
 	if (event == BUS_NOTIFY_ADD_DEVICE)
 		for (tmp = dev; tmp; tmp = tmp->bus->self)
-- 
2.20.1

[PATCH AUTOSEL 5.4 72/73] iommu/amd: Fix IOMMU AVIC not properly update the is_run bit in IRTE

[Sasha Levin]

From: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>

[ Upstream commit 730ad0ede130015a773229573559e97ba0943065 ]

Commit b9c6ff94e43a ("iommu/amd: Re-factor guest virtual APIC
(de-)activation code") accidentally left out the ir_data pointer when
calling modity_irte_ga(), which causes the function amd_iommu_update_ga()
to return prematurely due to struct amd_ir_data.ref is NULL and
the "is_run" bit of IRTE does not get updated properly.

This results in bad I/O performance since IOMMU AVIC always generate GA Log
entry and notify IOMMU driver and KVM when it receives interrupt from the
PCI pass-through device instead of directly inject interrupt to the vCPU.

Fixes by passing ir_data when calling modify_irte_ga() as done previously.

Fixes: b9c6ff94e43a ("iommu/amd: Re-factor guest virtual APIC (de-)activation code")
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/amd_iommu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 8bd5d608a82c2..bc77714983421 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -4421,7 +4421,7 @@ int amd_iommu_activate_guest_mode(void *data)
 	entry->lo.fields_vapic.ga_tag      = ir_data->ga_tag;
 
 	return modify_irte_ga(ir_data->irq_2_irte.devid,
-			      ir_data->irq_2_irte.index, entry, NULL);
+			      ir_data->irq_2_irte.index, entry, ir_data);
 }
 EXPORT_SYMBOL(amd_iommu_activate_guest_mode);
 
@@ -4447,7 +4447,7 @@ int amd_iommu_deactivate_guest_mode(void *data)
 				APICID_TO_IRTE_DEST_HI(cfg->dest_apicid);
 
 	return modify_irte_ga(ir_data->irq_2_irte.devid,
-			      ir_data->irq_2_irte.index, entry, NULL);
+			      ir_data->irq_2_irte.index, entry, ir_data);
 }
 EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode);
 
-- 
2.20.1

[PATCH AUTOSEL 5.4 73/73] iommu/vt-d: Populate debugfs if IOMMUs are detected

[Sasha Levin]

From: Megha Dey <megha.dey@linux.intel.com>

[ Upstream commit 1da8347d8505c137fb07ff06bbcd3f2bf37409bc ]

Currently, the intel iommu debugfs directory(/sys/kernel/debug/iommu/intel)
gets populated only when DMA remapping is enabled (dmar_disabled = 0)
irrespective of whether interrupt remapping is enabled or not.

Instead, populate the intel iommu debugfs directory if any IOMMUs are
detected.

Cc: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: ee2636b8670b1 ("iommu/vt-d: Enable base Intel IOMMU debugfs support")
Signed-off-by: Megha Dey <megha.dey@linux.intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iommu/intel-iommu-debugfs.c | 11 ++++++++++-
 drivers/iommu/intel-iommu.c         |  4 +++-
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c
index 80378c10dd77a..bdf095e9dbe03 100644
--- a/drivers/iommu/intel-iommu-debugfs.c
+++ b/drivers/iommu/intel-iommu-debugfs.c
@@ -281,9 +281,16 @@ static int dmar_translation_struct_show(struct seq_file *m, void *unused)
 {
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu;
+	u32 sts;
 
 	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd) {
+		sts = dmar_readl(iommu->reg + DMAR_GSTS_REG);
+		if (!(sts & DMA_GSTS_TES)) {
+			seq_printf(m, "DMA Remapping is not enabled on %s\n",
+				   iommu->name);
+			continue;
+		}
 		root_tbl_walk(m, iommu);
 		seq_putc(m, '\n');
 	}
@@ -353,6 +360,7 @@ static int ir_translation_struct_show(struct seq_file *m, void *unused)
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu;
 	u64 irta;
+	u32 sts;
 
 	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd) {
@@ -362,7 +370,8 @@ static int ir_translation_struct_show(struct seq_file *m, void *unused)
 		seq_printf(m, "Remapped Interrupt supported on IOMMU: %s\n",
 			   iommu->name);
 
-		if (iommu->ir_table) {
+		sts = dmar_readl(iommu->reg + DMAR_GSTS_REG);
+		if (iommu->ir_table && (sts & DMA_GSTS_IRES)) {
 			irta = virt_to_phys(iommu->ir_table->base);
 			seq_printf(m, " IR table address:%llx\n", irta);
 			ir_tbl_remap_entry_show(m, iommu);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index be39363244389..ef38e98b5bceb 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4961,6 +4961,9 @@ int __init intel_iommu_init(void)
 
 	down_write(&dmar_global_lock);
 
+	if (!no_iommu)
+		intel_iommu_debugfs_init();
+
 	if (no_iommu || dmar_disabled) {
 		/*
 		 * We exit the function here to ensure IOMMU's remapping and
@@ -5056,7 +5059,6 @@ int __init intel_iommu_init(void)
 	pr_info("Intel(R) Virtualization Technology for Directed I/O\n");
 
 	intel_iommu_enabled = 1;
-	intel_iommu_debugfs_init();
 
 	return 0;
 
-- 
2.20.1