[PATCH AUTOSEL 5.10 005/176] libbpf: Fix reuse of pinned map on older kernel

[PATCH AUTOSEL 5.10 005/176] libbpf: Fix reuse of pinned map on older kernel

[Sasha Levin]

From: Martynas Pumputis <m@lambda.lt>

[ Upstream commit 97eb31384af943d6b97eb5947262cee4ef25cb87 ]

When loading a BPF program with a pinned map, the loader checks whether
the pinned map can be reused, i.e. their properties match. To derive
such of the pinned map, the loader invokes BPF_OBJ_GET_INFO_BY_FD and
then does the comparison.

Unfortunately, on < 4.12 kernels the BPF_OBJ_GET_INFO_BY_FD is not
available, so loading the program fails with the following error:

	libbpf: failed to get map info for map FD 5: Invalid argument
	libbpf: couldn't reuse pinned map at
		'/sys/fs/bpf/tc/globals/cilium_call_policy': parameter
		mismatch"
	libbpf: map 'cilium_call_policy': error reusing pinned map
	libbpf: map 'cilium_call_policy': failed to create:
		Invalid argument(-22)
	libbpf: failed to load object 'bpf_overlay.o'

To fix this, fallback to derivation of the map properties via
/proc/$PID/fdinfo/$MAP_FD if BPF_OBJ_GET_INFO_BY_FD fails with EINVAL,
which can be used as an indicator that the kernel doesn't support
the latter.

Signed-off-by: Martynas Pumputis <m@lambda.lt>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210712125552.58705-1-m@lambda.lt
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/libbpf.c | 48 +++++++++++++++++++++++++++++++++++++++---
 1 file changed, 45 insertions(+), 3 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 95eef7ebdac5..a4e61dd5d8b3 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -3613,6 +3613,42 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
 	return 0;
 }
 
+static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info)
+{
+	char file[PATH_MAX], buff[4096];
+	FILE *fp;
+	__u32 val;
+	int err;
+
+	snprintf(file, sizeof(file), "/proc/%d/fdinfo/%d", getpid(), fd);
+	memset(info, 0, sizeof(*info));
+
+	fp = fopen(file, "r");
+	if (!fp) {
+		err = -errno;
+		pr_warn("failed to open %s: %d. No procfs support?\n", file,
+			err);
+		return err;
+	}
+
+	while (fgets(buff, sizeof(buff), fp)) {
+		if (sscanf(buff, "map_type:\t%u", &val) == 1)
+			info->type = val;
+		else if (sscanf(buff, "key_size:\t%u", &val) == 1)
+			info->key_size = val;
+		else if (sscanf(buff, "value_size:\t%u", &val) == 1)
+			info->value_size = val;
+		else if (sscanf(buff, "max_entries:\t%u", &val) == 1)
+			info->max_entries = val;
+		else if (sscanf(buff, "map_flags:\t%i", &val) == 1)
+			info->map_flags = val;
+	}
+
+	fclose(fp);
+
+	return 0;
+}
+
 int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 {
 	struct bpf_map_info info = {};
@@ -3621,6 +3657,8 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 	char *new_name;
 
 	err = bpf_obj_get_info_by_fd(fd, &info, &len);
+	if (err && errno == EINVAL)
+		err = bpf_get_map_info_from_fdinfo(fd, &info);
 	if (err)
 		return err;
 
@@ -4032,12 +4070,16 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd)
 	struct bpf_map_info map_info = {};
 	char msg[STRERR_BUFSIZE];
 	__u32 map_info_len;
+	int err;
 
 	map_info_len = sizeof(map_info);
 
-	if (bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len)) {
-		pr_warn("failed to get map info for map FD %d: %s\n",
-			map_fd, libbpf_strerror_r(errno, msg, sizeof(msg)));
+	err = bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len);
+	if (err && errno == EINVAL)
+		err = bpf_get_map_info_from_fdinfo(map_fd, &map_info);
+	if (err) {
+		pr_warn("failed to get map info for map FD %d: %s\n", map_fd,
+			libbpf_strerror_r(errno, msg, sizeof(msg)));
 		return false;
 	}
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 009/176] tipc: keep the skb in rcv queue until the whole data is read

[Sasha Levin]

From: Xin Long <lucien.xin@gmail.com>

[ Upstream commit f4919ff59c2828064b4156e3c3600a169909bcf4 ]

Currently, when userspace reads a datagram with a buffer that is
smaller than this datagram, the data will be truncated and only
part of it can be received by users. It doesn't seem right that
users don't know the datagram size and have to use a huge buffer
to read it to avoid the truncation.

This patch to fix it by keeping the skb in rcv queue until the
whole data is read by users. Only the last msg of the datagram
will be marked with MSG_EOR, just as TCP/SCTP does.

Note that this will work as above only when MSG_EOR is set in the
flags parameter of recvmsg(), so that it won't break any old user
applications.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/tipc/socket.c | 36 +++++++++++++++++++++++++++---------
 1 file changed, 27 insertions(+), 9 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 9bd72468bc68..963047c57c27 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1887,6 +1887,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
 	bool connected = !tipc_sk_type_connectionless(sk);
 	struct tipc_sock *tsk = tipc_sk(sk);
 	int rc, err, hlen, dlen, copy;
+	struct tipc_skb_cb *skb_cb;
 	struct sk_buff_head xmitq;
 	struct tipc_msg *hdr;
 	struct sk_buff *skb;
@@ -1910,6 +1911,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
 		if (unlikely(rc))
 			goto exit;
 		skb = skb_peek(&sk->sk_receive_queue);
+		skb_cb = TIPC_SKB_CB(skb);
 		hdr = buf_msg(skb);
 		dlen = msg_data_sz(hdr);
 		hlen = msg_hdr_sz(hdr);
@@ -1929,18 +1931,33 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
 
 	/* Capture data if non-error msg, otherwise just set return value */
 	if (likely(!err)) {
-		copy = min_t(int, dlen, buflen);
-		if (unlikely(copy != dlen))
-			m->msg_flags |= MSG_TRUNC;
-		rc = skb_copy_datagram_msg(skb, hlen, m, copy);
+		int offset = skb_cb->bytes_read;
+
+		copy = min_t(int, dlen - offset, buflen);
+		rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy);
+		if (unlikely(rc))
+			goto exit;
+		if (unlikely(offset + copy < dlen)) {
+			if (flags & MSG_EOR) {
+				if (!(flags & MSG_PEEK))
+					skb_cb->bytes_read = offset + copy;
+			} else {
+				m->msg_flags |= MSG_TRUNC;
+				skb_cb->bytes_read = 0;
+			}
+		} else {
+			if (flags & MSG_EOR)
+				m->msg_flags |= MSG_EOR;
+			skb_cb->bytes_read = 0;
+		}
 	} else {
 		copy = 0;
 		rc = 0;
-		if (err != TIPC_CONN_SHUTDOWN && connected && !m->msg_control)
+		if (err != TIPC_CONN_SHUTDOWN && connected && !m->msg_control) {
 			rc = -ECONNRESET;
+			goto exit;
+		}
 	}
-	if (unlikely(rc))
-		goto exit;
 
 	/* Mark message as group event if applicable */
 	if (unlikely(grp_evt)) {
@@ -1963,9 +1980,10 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
 		tipc_node_distr_xmit(sock_net(sk), &xmitq);
 	}
 
-	tsk_advance_rx_queue(sk);
+	if (!skb_cb->bytes_read)
+		tsk_advance_rx_queue(sk);
 
-	if (likely(!connected))
+	if (likely(!connected) || skb_cb->bytes_read)
 		goto exit;
 
 	/* Send connection flow control advertisement when applicable */
-- 
2.30.2

[PATCH AUTOSEL 5.10 010/176] net: phy: Fix data type in DP83822 dp8382x_disable_wol()

[Sasha Levin]

From: Marek Vasut <marex@denx.de>

[ Upstream commit 0d6835ffe50c9c1f098b5704394331710b67af48 ]

The last argument of phy_clear_bits_mmd(..., u16 val); is u16 and not
int, just inline the value into the function call arguments.

No functional change.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Reviewed-by: Florian Fainelli <f.fainelli@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/net/phy/dp83822.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index a9b058bb1be8..7bf43031cea8 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -305,11 +305,9 @@ static int dp83822_config_intr(struct phy_device *phydev)
 
 static int dp8382x_disable_wol(struct phy_device *phydev)
 {
-	int value = DP83822_WOL_EN | DP83822_WOL_MAGIC_EN |
-		    DP83822_WOL_SECURE_ON;
-
-	return phy_clear_bits_mmd(phydev, DP83822_DEVADDR,
-				  MII_DP83822_WOL_CFG, value);
+	return phy_clear_bits_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG,
+				  DP83822_WOL_EN | DP83822_WOL_MAGIC_EN |
+				  DP83822_WOL_SECURE_ON);
 }
 
 static int dp83822_read_status(struct phy_device *phydev)
-- 
2.30.2

[PATCH AUTOSEL 5.10 012/176] iavf: do not override the adapter state in the watchdog task

[Sasha Levin]

From: Stefan Assmann <sassmann@kpanic.de>

[ Upstream commit 22c8fd71d3a5e6fe584ccc2c1e8760e5baefd5aa ]

The iavf watchdog task overrides adapter->state to __IAVF_RESETTING
when it detects a pending reset. Then schedules iavf_reset_task() which
takes care of the reset.

The reset task is capable of handling the reset without changing
adapter->state. In fact we lose the state information when the watchdog
task prematurely changes the adapter state. This may lead to a crash if
instead of the reset task the iavf_remove() function gets called before
the reset task.
In that case (if we were in state __IAVF_RUNNING previously) the
iavf_remove() function triggers iavf_close() which fails to close the
device because of the incorrect state information.

This may result in a crash due to pending interrupts.
kernel BUG at drivers/pci/msi.c:357!
[...]
Call Trace:
 [<ffffffffbddf24dd>] pci_disable_msix+0x3d/0x50
 [<ffffffffc08d2a63>] iavf_reset_interrupt_capability+0x23/0x40 [iavf]
 [<ffffffffc08d312a>] iavf_remove+0x10a/0x350 [iavf]
 [<ffffffffbddd3359>] pci_device_remove+0x39/0xc0
 [<ffffffffbdeb492f>] __device_release_driver+0x7f/0xf0
 [<ffffffffbdeb49c3>] device_release_driver+0x23/0x30
 [<ffffffffbddcabb4>] pci_stop_bus_device+0x84/0xa0
 [<ffffffffbddcacc2>] pci_stop_and_remove_bus_device+0x12/0x20
 [<ffffffffbddf361f>] pci_iov_remove_virtfn+0xaf/0x160
 [<ffffffffbddf3bcc>] sriov_disable+0x3c/0xf0
 [<ffffffffbddf3ca3>] pci_disable_sriov+0x23/0x30
 [<ffffffffc0667365>] i40e_free_vfs+0x265/0x2d0 [i40e]
 [<ffffffffc0667624>] i40e_pci_sriov_configure+0x144/0x1f0 [i40e]
 [<ffffffffbddd5307>] sriov_numvfs_store+0x177/0x1d0
Code: 00 00 e8 3c 25 e3 ff 49 c7 86 88 08 00 00 00 00 00 00 5b 41 5c 41 5d 41 5e 41 5f 5d c3 48 8b 7b 28 e8 0d 44
RIP  [<ffffffffbbbf1068>] free_msi_irqs+0x188/0x190

The solution is to not touch the adapter->state in iavf_watchdog_task()
and let the reset task handle the state transition.

Signed-off-by: Stefan Assmann <sassmann@kpanic.de>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 7023aa147043..da401d5694bf 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -1951,7 +1951,6 @@ static void iavf_watchdog_task(struct work_struct *work)
 		/* check for hw reset */
 	reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK;
 	if (!reg_val) {
-		adapter->state = __IAVF_RESETTING;
 		adapter->flags |= IAVF_FLAG_RESET_PENDING;
 		adapter->aq_required = 0;
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
-- 
2.30.2

[PATCH AUTOSEL 5.10 013/176] iavf: fix locking of critical sections

[Sasha Levin]

From: Stefan Assmann <sassmann@kpanic.de>

[ Upstream commit 226d528512cfac890a1619aea4301f3dd314fe60 ]

To avoid races between iavf_init_task(), iavf_reset_task(),
iavf_watchdog_task(), iavf_adminq_task() as well as the shutdown and
remove functions more locking is required.
The current protection by __IAVF_IN_CRITICAL_TASK is needed in
additional places.

- The reset task performs state transitions, therefore needs locking.
- The adminq task acts on replies from the PF in
  iavf_virtchnl_completion() which may alter the states.
- The init task is not only run during probe but also if a VF gets stuck
  to reinitialize it.
- The shutdown function performs a state transition.
- The remove function performs a state transition and also free's
  resources.

iavf_lock_timeout() is introduced to avoid waiting infinitely
and cause a deadlock. Rather unlock and print a warning.

Signed-off-by: Stefan Assmann <sassmann@kpanic.de>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 57 ++++++++++++++++++---
 1 file changed, 50 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index da401d5694bf..f06c079e812e 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -131,6 +131,30 @@ enum iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw,
 	return 0;
 }
 
+/**
+ * iavf_lock_timeout - try to set bit but give up after timeout
+ * @adapter: board private structure
+ * @bit: bit to set
+ * @msecs: timeout in msecs
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int iavf_lock_timeout(struct iavf_adapter *adapter,
+			     enum iavf_critical_section_t bit,
+			     unsigned int msecs)
+{
+	unsigned int wait, delay = 10;
+
+	for (wait = 0; wait < msecs; wait += delay) {
+		if (!test_and_set_bit(bit, &adapter->crit_section))
+			return 0;
+
+		msleep(delay);
+	}
+
+	return -1;
+}
+
 /**
  * iavf_schedule_reset - Set the flags and schedule a reset event
  * @adapter: board private structure
@@ -2064,6 +2088,10 @@ static void iavf_reset_task(struct work_struct *work)
 	if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
 		return;
 
+	if (iavf_lock_timeout(adapter, __IAVF_IN_CRITICAL_TASK, 200)) {
+		schedule_work(&adapter->reset_task);
+		return;
+	}
 	while (test_and_set_bit(__IAVF_IN_CLIENT_TASK,
 				&adapter->crit_section))
 		usleep_range(500, 1000);
@@ -2278,6 +2306,8 @@ static void iavf_adminq_task(struct work_struct *work)
 	if (!event.msg_buf)
 		goto out;
 
+	if (iavf_lock_timeout(adapter, __IAVF_IN_CRITICAL_TASK, 200))
+		goto freedom;
 	do {
 		ret = iavf_clean_arq_element(hw, &event, &pending);
 		v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high);
@@ -2291,6 +2321,7 @@ static void iavf_adminq_task(struct work_struct *work)
 		if (pending != 0)
 			memset(event.msg_buf, 0, IAVF_MAX_AQ_BUF_SIZE);
 	} while (pending);
+	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
 
 	if ((adapter->flags &
 	     (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) ||
@@ -3593,6 +3624,10 @@ static void iavf_init_task(struct work_struct *work)
 						    init_task.work);
 	struct iavf_hw *hw = &adapter->hw;
 
+	if (iavf_lock_timeout(adapter, __IAVF_IN_CRITICAL_TASK, 5000)) {
+		dev_warn(&adapter->pdev->dev, "failed to set __IAVF_IN_CRITICAL_TASK in %s\n", __FUNCTION__);
+		return;
+	}
 	switch (adapter->state) {
 	case __IAVF_STARTUP:
 		if (iavf_startup(adapter) < 0)
@@ -3605,14 +3640,14 @@ static void iavf_init_task(struct work_struct *work)
 	case __IAVF_INIT_GET_RESOURCES:
 		if (iavf_init_get_resources(adapter) < 0)
 			goto init_failed;
-		return;
+		goto out;
 	default:
 		goto init_failed;
 	}
 
 	queue_delayed_work(iavf_wq, &adapter->init_task,
 			   msecs_to_jiffies(30));
-	return;
+	goto out;
 init_failed:
 	if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) {
 		dev_err(&adapter->pdev->dev,
@@ -3621,9 +3656,11 @@ static void iavf_init_task(struct work_struct *work)
 		iavf_shutdown_adminq(hw);
 		adapter->state = __IAVF_STARTUP;
 		queue_delayed_work(iavf_wq, &adapter->init_task, HZ * 5);
-		return;
+		goto out;
 	}
 	queue_delayed_work(iavf_wq, &adapter->init_task, HZ);
+out:
+	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
 }
 
 /**
@@ -3640,9 +3677,12 @@ static void iavf_shutdown(struct pci_dev *pdev)
 	if (netif_running(netdev))
 		iavf_close(netdev);
 
+	if (iavf_lock_timeout(adapter, __IAVF_IN_CRITICAL_TASK, 5000))
+		dev_warn(&adapter->pdev->dev, "failed to set __IAVF_IN_CRITICAL_TASK in %s\n", __FUNCTION__);
 	/* Prevent the watchdog from running. */
 	adapter->state = __IAVF_REMOVE;
 	adapter->aq_required = 0;
+	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
 
 #ifdef CONFIG_PM
 	pci_save_state(pdev);
@@ -3870,10 +3910,6 @@ static void iavf_remove(struct pci_dev *pdev)
 				 err);
 	}
 
-	/* Shut down all the garbage mashers on the detention level */
-	adapter->state = __IAVF_REMOVE;
-	adapter->aq_required = 0;
-	adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
 	iavf_request_reset(adapter);
 	msleep(50);
 	/* If the FW isn't responding, kick it once, but only once. */
@@ -3881,6 +3917,13 @@ static void iavf_remove(struct pci_dev *pdev)
 		iavf_request_reset(adapter);
 		msleep(50);
 	}
+	if (iavf_lock_timeout(adapter, __IAVF_IN_CRITICAL_TASK, 5000))
+		dev_warn(&adapter->pdev->dev, "failed to set __IAVF_IN_CRITICAL_TASK in %s\n", __FUNCTION__);
+
+	/* Shut down all the garbage mashers on the detention level */
+	adapter->state = __IAVF_REMOVE;
+	adapter->aq_required = 0;
+	adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
 	iavf_free_all_tx_resources(adapter);
 	iavf_free_all_rx_resources(adapter);
 	iavf_misc_irq_disable(adapter);
-- 
2.30.2

[PATCH AUTOSEL 5.10 016/176] netlink: Deal with ESRCH error in nlmsg_notify()

[Sasha Levin]

From: Yajun Deng <yajun.deng@linux.dev>

[ Upstream commit fef773fc8110d8124c73a5e6610f89e52814637d ]

Yonghong Song report:
The bpf selftest tc_bpf failed with latest bpf-next.
The following is the command to run and the result:
$ ./test_progs -n 132
[   40.947571] bpf_testmod: loading out-of-tree module taints kernel.
test_tc_bpf:PASS:test_tc_bpf__open_and_load 0 nsec
test_tc_bpf:PASS:bpf_tc_hook_create(BPF_TC_INGRESS) 0 nsec
test_tc_bpf:PASS:bpf_tc_hook_create invalid hook.attach_point 0 nsec
test_tc_bpf_basic:PASS:bpf_obj_get_info_by_fd 0 nsec
test_tc_bpf_basic:PASS:bpf_tc_attach 0 nsec
test_tc_bpf_basic:PASS:handle set 0 nsec
test_tc_bpf_basic:PASS:priority set 0 nsec
test_tc_bpf_basic:PASS:prog_id set 0 nsec
test_tc_bpf_basic:PASS:bpf_tc_attach replace mode 0 nsec
test_tc_bpf_basic:PASS:bpf_tc_query 0 nsec
test_tc_bpf_basic:PASS:handle set 0 nsec
test_tc_bpf_basic:PASS:priority set 0 nsec
test_tc_bpf_basic:PASS:prog_id set 0 nsec
libbpf: Kernel error message: Failed to send filter delete notification
test_tc_bpf_basic:FAIL:bpf_tc_detach unexpected error: -3 (errno 3)
test_tc_bpf:FAIL:test_tc_internal ingress unexpected error: -3 (errno 3)

The failure seems due to the commit
    cfdf0d9ae75b ("rtnetlink: use nlmsg_notify() in rtnetlink_send()")

Deal with ESRCH error in nlmsg_notify() even the report variable is zero.

Reported-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Yajun Deng <yajun.deng@linux.dev>
Link: https://lore.kernel.org/r/20210719051816.11762-1-yajun.deng@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netlink/af_netlink.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index e527f5686e2b..8434da3c0487 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2537,13 +2537,15 @@ int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid,
 		/* errors reported via destination sk->sk_err, but propagate
 		 * delivery errors if NETLINK_BROADCAST_ERROR flag is set */
 		err = nlmsg_multicast(sk, skb, exclude_portid, group, flags);
+		if (err == -ESRCH)
+			err = 0;
 	}
 
 	if (report) {
 		int err2;
 
 		err2 = nlmsg_unicast(sk, skb, portid);
-		if (!err || err == -ESRCH)
+		if (!err)
 			err = err2;
 	}
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 022/176] igc: Check if num of q_vectors is smaller than max before array access

[Sasha Levin]

From: Sasha Neftin <sasha.neftin@intel.com>

[ Upstream commit 373e2829e7c2e1e606503cdb5c97749f512a4be9 ]

Ensure that the adapter->q_vector[MAX_Q_VECTORS] array isn't accessed
beyond its size. It was fixed by using a local variable num_q_vectors
as a limit for loop index, and ensure that num_q_vectors is not bigger
than MAX_Q_VECTORS.

Suggested-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Dvora Fuxbrumer <dvorax.fuxbrumer@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 013dd2955381..cae090a07252 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -4083,6 +4083,7 @@ static irqreturn_t igc_msix_ring(int irq, void *data)
  */
 static int igc_request_msix(struct igc_adapter *adapter)
 {
+	unsigned int num_q_vectors = adapter->num_q_vectors;
 	int i = 0, err = 0, vector = 0, free_vector = 0;
 	struct net_device *netdev = adapter->netdev;
 
@@ -4091,7 +4092,13 @@ static int igc_request_msix(struct igc_adapter *adapter)
 	if (err)
 		goto err_out;
 
-	for (i = 0; i < adapter->num_q_vectors; i++) {
+	if (num_q_vectors > MAX_Q_VECTORS) {
+		num_q_vectors = MAX_Q_VECTORS;
+		dev_warn(&adapter->pdev->dev,
+			 "The number of queue vectors (%d) is higher than max allowed (%d)\n",
+			 adapter->num_q_vectors, MAX_Q_VECTORS);
+	}
+	for (i = 0; i < num_q_vectors; i++) {
 		struct igc_q_vector *q_vector = adapter->q_vector[i];
 
 		vector++;
-- 
2.30.2

[PATCH AUTOSEL 5.10 037/176] nfp: fix return statement in nfp_net_parse_meta()

[Sasha Levin]

From: Niklas Söderlund <niklas.soderlund@corigine.com>

[ Upstream commit 4431531c482a2c05126caaa9fcc5053a4a5c495b ]

The return type of the function is bool and while NULL do evaluate to
false it's not very nice, fix this by explicitly returning false. There
is no functional change.

Signed-off-by: Niklas Söderlund <niklas.soderlund@corigine.com>
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 437226866ce8..dfc1f32cda2b 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1697,7 +1697,7 @@ nfp_net_parse_meta(struct net_device *netdev, struct nfp_meta_parsed *meta,
 		case NFP_NET_META_RESYNC_INFO:
 			if (nfp_net_tls_rx_resync_req(netdev, data, pkt,
 						      pkt_len))
-				return NULL;
+				return false;
 			data += sizeof(struct nfp_net_tls_resync_req);
 			break;
 		default:
-- 
2.30.2

[PATCH AUTOSEL 5.10 039/176] ethtool: improve compat ioctl handling

[Sasha Levin]

From: Arnd Bergmann <arnd@arndb.de>

[ Upstream commit dd98d2895de6485c884a9cb42de69fed02826fa4 ]

The ethtool compat ioctl handling is hidden away in net/socket.c,
which introduces a couple of minor oddities:

- The implementation may end up diverging, as seen in the RXNFC
  extension in commit 84a1d9c48200 ("net: ethtool: extend RXNFC
  API to support RSS spreading of filter matches") that does not work
  in compat mode.

- Most architectures do not need the compat handling at all
  because u64 and compat_u64 have the same alignment.

- On x86, the conversion is done for both x32 and i386 user space,
  but it's actually wrong to do it for x32 and cannot work there.

- On 32-bit Arm, it never worked for compat oabi user space, since
  that needs to do the same conversion but does not.

- It would be nice to get rid of both compat_alloc_user_space()
  and copy_in_user() throughout the kernel.

None of these actually seems to be a serious problem that real
users are likely to encounter, but fixing all of them actually
leads to code that is both shorter and more readable.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/ethtool.h |   4 --
 net/ethtool/ioctl.c     | 136 +++++++++++++++++++++++++++++++++++-----
 net/socket.c            | 125 +-----------------------------------
 3 files changed, 121 insertions(+), 144 deletions(-)

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 6408b446051f..b98291d391f3 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -17,8 +17,6 @@
 #include <linux/compat.h>
 #include <uapi/linux/ethtool.h>
 
-#ifdef CONFIG_COMPAT
-
 struct compat_ethtool_rx_flow_spec {
 	u32		flow_type;
 	union ethtool_flow_union h_u;
@@ -38,8 +36,6 @@ struct compat_ethtool_rxnfc {
 	u32				rule_locs[];
 };
 
-#endif /* CONFIG_COMPAT */
-
 #include <linux/rculist.h>
 
 /**
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 68ff19af195c..97b402b2d6fb 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -7,6 +7,7 @@
  * the information ethtool needs.
  */
 
+#include <linux/compat.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/capability.h>
@@ -807,6 +808,120 @@ static noinline_for_stack int ethtool_get_sset_info(struct net_device *dev,
 	return ret;
 }
 
+static noinline_for_stack int
+ethtool_rxnfc_copy_from_compat(struct ethtool_rxnfc *rxnfc,
+			       const struct compat_ethtool_rxnfc __user *useraddr,
+			       size_t size)
+{
+	struct compat_ethtool_rxnfc crxnfc = {};
+
+	/* We expect there to be holes between fs.m_ext and
+	 * fs.ring_cookie and at the end of fs, but nowhere else.
+	 * On non-x86, no conversion should be needed.
+	 */
+	BUILD_BUG_ON(!IS_ENABLED(CONFIG_X86_64) &&
+		     sizeof(struct compat_ethtool_rxnfc) !=
+		     sizeof(struct ethtool_rxnfc));
+	BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_ext) +
+		     sizeof(useraddr->fs.m_ext) !=
+		     offsetof(struct ethtool_rxnfc, fs.m_ext) +
+		     sizeof(rxnfc->fs.m_ext));
+	BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.location) -
+		     offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) !=
+		     offsetof(struct ethtool_rxnfc, fs.location) -
+		     offsetof(struct ethtool_rxnfc, fs.ring_cookie));
+
+	if (copy_from_user(&crxnfc, useraddr, min(size, sizeof(crxnfc))))
+		return -EFAULT;
+
+	*rxnfc = (struct ethtool_rxnfc) {
+		.cmd		= crxnfc.cmd,
+		.flow_type	= crxnfc.flow_type,
+		.data		= crxnfc.data,
+		.fs		= {
+			.flow_type	= crxnfc.fs.flow_type,
+			.h_u		= crxnfc.fs.h_u,
+			.h_ext		= crxnfc.fs.h_ext,
+			.m_u		= crxnfc.fs.m_u,
+			.m_ext		= crxnfc.fs.m_ext,
+			.ring_cookie	= crxnfc.fs.ring_cookie,
+			.location	= crxnfc.fs.location,
+		},
+		.rule_cnt	= crxnfc.rule_cnt,
+	};
+
+	return 0;
+}
+
+static int ethtool_rxnfc_copy_from_user(struct ethtool_rxnfc *rxnfc,
+					const void __user *useraddr,
+					size_t size)
+{
+	if (compat_need_64bit_alignment_fixup())
+		return ethtool_rxnfc_copy_from_compat(rxnfc, useraddr, size);
+
+	if (copy_from_user(rxnfc, useraddr, size))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int ethtool_rxnfc_copy_to_compat(void __user *useraddr,
+					const struct ethtool_rxnfc *rxnfc,
+					size_t size, const u32 *rule_buf)
+{
+	struct compat_ethtool_rxnfc crxnfc;
+
+	memset(&crxnfc, 0, sizeof(crxnfc));
+	crxnfc = (struct compat_ethtool_rxnfc) {
+		.cmd		= rxnfc->cmd,
+		.flow_type	= rxnfc->flow_type,
+		.data		= rxnfc->data,
+		.fs		= {
+			.flow_type	= rxnfc->fs.flow_type,
+			.h_u		= rxnfc->fs.h_u,
+			.h_ext		= rxnfc->fs.h_ext,
+			.m_u		= rxnfc->fs.m_u,
+			.m_ext		= rxnfc->fs.m_ext,
+			.ring_cookie	= rxnfc->fs.ring_cookie,
+			.location	= rxnfc->fs.location,
+		},
+		.rule_cnt	= rxnfc->rule_cnt,
+	};
+
+	if (copy_to_user(useraddr, &crxnfc, min(size, sizeof(crxnfc))))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int ethtool_rxnfc_copy_to_user(void __user *useraddr,
+				      const struct ethtool_rxnfc *rxnfc,
+				      size_t size, const u32 *rule_buf)
+{
+	int ret;
+
+	if (compat_need_64bit_alignment_fixup()) {
+		ret = ethtool_rxnfc_copy_to_compat(useraddr, rxnfc, size,
+						   rule_buf);
+		useraddr += offsetof(struct compat_ethtool_rxnfc, rule_locs);
+	} else {
+		ret = copy_to_user(useraddr, &rxnfc, size);
+		useraddr += offsetof(struct ethtool_rxnfc, rule_locs);
+	}
+
+	if (ret)
+		return -EFAULT;
+
+	if (rule_buf) {
+		if (copy_to_user(useraddr, rule_buf,
+				 rxnfc->rule_cnt * sizeof(u32)))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
 static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
 						u32 cmd, void __user *useraddr)
 {
@@ -825,7 +940,7 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
 		info_size = (offsetof(struct ethtool_rxnfc, data) +
 			     sizeof(info.data));
 
-	if (copy_from_user(&info, useraddr, info_size))
+	if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size))
 		return -EFAULT;
 
 	rc = dev->ethtool_ops->set_rxnfc(dev, &info);
@@ -833,7 +948,7 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
 		return rc;
 
 	if (cmd == ETHTOOL_SRXCLSRLINS &&
-	    copy_to_user(useraddr, &info, info_size))
+	    ethtool_rxnfc_copy_to_user(useraddr, &info, info_size, NULL))
 		return -EFAULT;
 
 	return 0;
@@ -859,7 +974,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev,
 		info_size = (offsetof(struct ethtool_rxnfc, data) +
 			     sizeof(info.data));
 
-	if (copy_from_user(&info, useraddr, info_size))
+	if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size))
 		return -EFAULT;
 
 	/* If FLOW_RSS was requested then user-space must be using the
@@ -867,7 +982,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev,
 	 */
 	if (cmd == ETHTOOL_GRXFH && info.flow_type & FLOW_RSS) {
 		info_size = sizeof(info);
-		if (copy_from_user(&info, useraddr, info_size))
+		if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size))
 			return -EFAULT;
 		/* Since malicious users may modify the original data,
 		 * we need to check whether FLOW_RSS is still requested.
@@ -893,18 +1008,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev,
 	if (ret < 0)
 		goto err_out;
 
-	ret = -EFAULT;
-	if (copy_to_user(useraddr, &info, info_size))
-		goto err_out;
-
-	if (rule_buf) {
-		useraddr += offsetof(struct ethtool_rxnfc, rule_locs);
-		if (copy_to_user(useraddr, rule_buf,
-				 info.rule_cnt * sizeof(u32)))
-			goto err_out;
-	}
-	ret = 0;
-
+	ret = ethtool_rxnfc_copy_to_user(useraddr, &info, info_size, rule_buf);
 err_out:
 	kfree(rule_buf);
 
diff --git a/net/socket.c b/net/socket.c
index dd5da07bc1ff..d52c265ad449 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -3112,128 +3112,6 @@ static int compat_dev_ifconf(struct net *net, struct compat_ifconf __user *uifc3
 	return 0;
 }
 
-static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32)
-{
-	struct compat_ethtool_rxnfc __user *compat_rxnfc;
-	bool convert_in = false, convert_out = false;
-	size_t buf_size = 0;
-	struct ethtool_rxnfc __user *rxnfc = NULL;
-	struct ifreq ifr;
-	u32 rule_cnt = 0, actual_rule_cnt;
-	u32 ethcmd;
-	u32 data;
-	int ret;
-
-	if (get_user(data, &ifr32->ifr_ifru.ifru_data))
-		return -EFAULT;
-
-	compat_rxnfc = compat_ptr(data);
-
-	if (get_user(ethcmd, &compat_rxnfc->cmd))
-		return -EFAULT;
-
-	/* Most ethtool structures are defined without padding.
-	 * Unfortunately struct ethtool_rxnfc is an exception.
-	 */
-	switch (ethcmd) {
-	default:
-		break;
-	case ETHTOOL_GRXCLSRLALL:
-		/* Buffer size is variable */
-		if (get_user(rule_cnt, &compat_rxnfc->rule_cnt))
-			return -EFAULT;
-		if (rule_cnt > KMALLOC_MAX_SIZE / sizeof(u32))
-			return -ENOMEM;
-		buf_size += rule_cnt * sizeof(u32);
-		fallthrough;
-	case ETHTOOL_GRXRINGS:
-	case ETHTOOL_GRXCLSRLCNT:
-	case ETHTOOL_GRXCLSRULE:
-	case ETHTOOL_SRXCLSRLINS:
-		convert_out = true;
-		fallthrough;
-	case ETHTOOL_SRXCLSRLDEL:
-		buf_size += sizeof(struct ethtool_rxnfc);
-		convert_in = true;
-		rxnfc = compat_alloc_user_space(buf_size);
-		break;
-	}
-
-	if (copy_from_user(&ifr.ifr_name, &ifr32->ifr_name, IFNAMSIZ))
-		return -EFAULT;
-
-	ifr.ifr_data = convert_in ? rxnfc : (void __user *)compat_rxnfc;
-
-	if (convert_in) {
-		/* We expect there to be holes between fs.m_ext and
-		 * fs.ring_cookie and at the end of fs, but nowhere else.
-		 */
-		BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_ext) +
-			     sizeof(compat_rxnfc->fs.m_ext) !=
-			     offsetof(struct ethtool_rxnfc, fs.m_ext) +
-			     sizeof(rxnfc->fs.m_ext));
-		BUILD_BUG_ON(
-			offsetof(struct compat_ethtool_rxnfc, fs.location) -
-			offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) !=
-			offsetof(struct ethtool_rxnfc, fs.location) -
-			offsetof(struct ethtool_rxnfc, fs.ring_cookie));
-
-		if (copy_in_user(rxnfc, compat_rxnfc,
-				 (void __user *)(&rxnfc->fs.m_ext + 1) -
-				 (void __user *)rxnfc) ||
-		    copy_in_user(&rxnfc->fs.ring_cookie,
-				 &compat_rxnfc->fs.ring_cookie,
-				 (void __user *)(&rxnfc->fs.location + 1) -
-				 (void __user *)&rxnfc->fs.ring_cookie))
-			return -EFAULT;
-		if (ethcmd == ETHTOOL_GRXCLSRLALL) {
-			if (put_user(rule_cnt, &rxnfc->rule_cnt))
-				return -EFAULT;
-		} else if (copy_in_user(&rxnfc->rule_cnt,
-					&compat_rxnfc->rule_cnt,
-					sizeof(rxnfc->rule_cnt)))
-			return -EFAULT;
-	}
-
-	ret = dev_ioctl(net, SIOCETHTOOL, &ifr, NULL);
-	if (ret)
-		return ret;
-
-	if (convert_out) {
-		if (copy_in_user(compat_rxnfc, rxnfc,
-				 (const void __user *)(&rxnfc->fs.m_ext + 1) -
-				 (const void __user *)rxnfc) ||
-		    copy_in_user(&compat_rxnfc->fs.ring_cookie,
-				 &rxnfc->fs.ring_cookie,
-				 (const void __user *)(&rxnfc->fs.location + 1) -
-				 (const void __user *)&rxnfc->fs.ring_cookie) ||
-		    copy_in_user(&compat_rxnfc->rule_cnt, &rxnfc->rule_cnt,
-				 sizeof(rxnfc->rule_cnt)))
-			return -EFAULT;
-
-		if (ethcmd == ETHTOOL_GRXCLSRLALL) {
-			/* As an optimisation, we only copy the actual
-			 * number of rules that the underlying
-			 * function returned.  Since Mallory might
-			 * change the rule count in user memory, we
-			 * check that it is less than the rule count
-			 * originally given (as the user buffer size),
-			 * which has been range-checked.
-			 */
-			if (get_user(actual_rule_cnt, &rxnfc->rule_cnt))
-				return -EFAULT;
-			if (actual_rule_cnt < rule_cnt)
-				rule_cnt = actual_rule_cnt;
-			if (copy_in_user(&compat_rxnfc->rule_locs[0],
-					 &rxnfc->rule_locs[0],
-					 rule_cnt * sizeof(u32)))
-				return -EFAULT;
-		}
-	}
-
-	return 0;
-}
-
 static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32)
 {
 	compat_uptr_t uptr32;
@@ -3390,8 +3268,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 		return old_bridge_ioctl(argp);
 	case SIOCGIFCONF:
 		return compat_dev_ifconf(net, argp);
-	case SIOCETHTOOL:
-		return ethtool_ioctl(net, argp);
 	case SIOCWANDEV:
 		return compat_siocwandev(net, argp);
 	case SIOCGIFMAP:
@@ -3404,6 +3280,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 		return sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD,
 					    !COMPAT_USE_64BIT_TIME);
 
+	case SIOCETHTOOL:
 	case SIOCBONDSLAVEINFOQUERY:
 	case SIOCBONDINFOQUERY:
 	case SIOCSHWTSTAMP:
-- 
2.30.2

[PATCH AUTOSEL 5.10 042/176] bpf/tests: Fix copy-and-paste error in double word test

[Sasha Levin]

From: Johan Almbladh <johan.almbladh@anyfinetworks.com>

[ Upstream commit ae7f47041d928b1a2f28717d095b4153c63cbf6a ]

This test now operates on DW as stated instead of W, which was
already covered by another test.

Signed-off-by: Johan Almbladh <johan.almbladh@anyfinetworks.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210721104058.3755254-1-johan.almbladh@anyfinetworks.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 lib/test_bpf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index ca7d635bccd9..ca8eef2f6442 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -4286,8 +4286,8 @@ static struct bpf_test tests[] = {
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 0),
 			BPF_LD_IMM64(R1, 0xffffffffffffffffLL),
-			BPF_STX_MEM(BPF_W, R10, R1, -40),
-			BPF_LDX_MEM(BPF_W, R0, R10, -40),
+			BPF_STX_MEM(BPF_DW, R10, R1, -40),
+			BPF_LDX_MEM(BPF_DW, R0, R10, -40),
 			BPF_EXIT_INSN(),
 		},
 		INTERNAL,
-- 
2.30.2

[PATCH AUTOSEL 5.10 043/176] bpf/tests: Do not PASS tests without actually testing the result

[Sasha Levin]

From: Johan Almbladh <johan.almbladh@anyfinetworks.com>

[ Upstream commit 2b7e9f25e590726cca76700ebdb10e92a7a72ca1 ]

Each test case can have a set of sub-tests, where each sub-test can
run the cBPF/eBPF test snippet with its own data_size and expected
result. Before, the end of the sub-test array was indicated by both
data_size and result being zero. However, most or all of the internal
eBPF tests has a data_size of zero already. When such a test also had
an expected value of zero, the test was never run but reported as
PASS anyway.

Now the test runner always runs the first sub-test, regardless of the
data_size and result values. The sub-test array zero-termination only
applies for any additional sub-tests.

There are other ways fix it of course, but this solution at least
removes the surprise of eBPF tests with a zero result always succeeding.

Signed-off-by: Johan Almbladh <johan.almbladh@anyfinetworks.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210721103822.3755111-1-johan.almbladh@anyfinetworks.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 lib/test_bpf.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index ca8eef2f6442..4a9137c8551a 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -6664,7 +6664,14 @@ static int run_one(const struct bpf_prog *fp, struct bpf_test *test)
 		u64 duration;
 		u32 ret;
 
-		if (test->test[i].data_size == 0 &&
+		/*
+		 * NOTE: Several sub-tests may be present, in which case
+		 * a zero {data_size, result} tuple indicates the end of
+		 * the sub-test array. The first test is always run,
+		 * even if both data_size and result happen to be zero.
+		 */
+		if (i > 0 &&
+		    test->test[i].data_size == 0 &&
 		    test->test[i].result == 0)
 			break;
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 049/176] ipv4: ip_output.c: Fix out-of-bounds warning in ip_copy_addrs()

[Sasha Levin]

From: "Gustavo A. R. Silva" <gustavoars@kernel.org>

[ Upstream commit 6321c7acb82872ef6576c520b0e178eaad3a25c0 ]

Fix the following out-of-bounds warning:

    In function 'ip_copy_addrs',
        inlined from '__ip_queue_xmit' at net/ipv4/ip_output.c:517:2:
net/ipv4/ip_output.c:449:2: warning: 'memcpy' offset [40, 43] from the object at 'fl' is out of the bounds of referenced subobject 'saddr' with type 'unsigned int' at offset 36 [-Warray-bounds]
      449 |  memcpy(&iph->saddr, &fl4->saddr,
          |  ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
      450 |         sizeof(fl4->saddr) + sizeof(fl4->daddr));
          |         ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The problem is that the original code is trying to copy data into a
couple of struct members adjacent to each other in a single call to
memcpy(). This causes a legitimate compiler warning because memcpy()
overruns the length of &iph->saddr and &fl4->saddr. As these are just
a couple of struct members, fix this by using direct assignments,
instead of memcpy().

This helps with the ongoing efforts to globally enable -Warray-bounds
and get us closer to being able to tighten the FORTIFY_SOURCE routines
on memcpy().

Link: https://github.com/KSPP/linux/issues/109
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/lkml/d5ae2e65-1f18-2577-246f-bada7eee6ccd@intel.com/
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/ipv4/ip_output.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 560d5dc43562..10d4cde31c6b 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -445,8 +445,9 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4)
 {
 	BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) !=
 		     offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr));
-	memcpy(&iph->saddr, &fl4->saddr,
-	       sizeof(fl4->saddr) + sizeof(fl4->daddr));
+
+	iph->saddr = fl4->saddr;
+	iph->daddr = fl4->daddr;
 }
 
 /* Note: skb->sk can be different from sk, in case of tunnels */
-- 
2.30.2

[PATCH AUTOSEL 5.10 050/176] flow_dissector: Fix out-of-bounds warnings

[Sasha Levin]

From: "Gustavo A. R. Silva" <gustavoars@kernel.org>

[ Upstream commit 323e0cb473e2a8706ff162b6b4f4fa16023c9ba7 ]

Fix the following out-of-bounds warnings:

    net/core/flow_dissector.c: In function '__skb_flow_dissect':
>> net/core/flow_dissector.c:1104:4: warning: 'memcpy' offset [24, 39] from the object at '<unknown>' is out of the bounds of referenced subobject 'saddr' with type 'struct in6_addr' at offset 8 [-Warray-bounds]
     1104 |    memcpy(&key_addrs->v6addrs, &iph->saddr,
          |    ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     1105 |           sizeof(key_addrs->v6addrs));
          |           ~~~~~~~~~~~~~~~~~~~~~~~~~~~
    In file included from include/linux/ipv6.h:5,
                     from net/core/flow_dissector.c:6:
    include/uapi/linux/ipv6.h:133:18: note: subobject 'saddr' declared here
      133 |  struct in6_addr saddr;
          |                  ^~~~~
>> net/core/flow_dissector.c:1059:4: warning: 'memcpy' offset [16, 19] from the object at '<unknown>' is out of the bounds of referenced subobject 'saddr' with type 'unsigned int' at offset 12 [-Warray-bounds]
     1059 |    memcpy(&key_addrs->v4addrs, &iph->saddr,
          |    ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     1060 |           sizeof(key_addrs->v4addrs));
          |           ~~~~~~~~~~~~~~~~~~~~~~~~~~~
    In file included from include/linux/ip.h:17,
                     from net/core/flow_dissector.c:5:
    include/uapi/linux/ip.h:103:9: note: subobject 'saddr' declared here
      103 |  __be32 saddr;
          |         ^~~~~

The problem is that the original code is trying to copy data into a
couple of struct members adjacent to each other in a single call to
memcpy().  So, the compiler legitimately complains about it. As these
are just a couple of members, fix this by copying each one of them in
separate calls to memcpy().

This helps with the ongoing efforts to globally enable -Warray-bounds
and get us closer to being able to tighten the FORTIFY_SOURCE routines
on memcpy().

Link: https://github.com/KSPP/linux/issues/109
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/lkml/d5ae2e65-1f18-2577-246f-bada7eee6ccd@intel.com/
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/core/flow_dissector.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index c52e5ea654e9..813c709c61cf 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1047,8 +1047,10 @@ bool __skb_flow_dissect(const struct net *net,
 							      FLOW_DISSECTOR_KEY_IPV4_ADDRS,
 							      target_container);
 
-			memcpy(&key_addrs->v4addrs, &iph->saddr,
-			       sizeof(key_addrs->v4addrs));
+			memcpy(&key_addrs->v4addrs.src, &iph->saddr,
+			       sizeof(key_addrs->v4addrs.src));
+			memcpy(&key_addrs->v4addrs.dst, &iph->daddr,
+			       sizeof(key_addrs->v4addrs.dst));
 			key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
 		}
 
@@ -1092,8 +1094,10 @@ bool __skb_flow_dissect(const struct net *net,
 							      FLOW_DISSECTOR_KEY_IPV6_ADDRS,
 							      target_container);
 
-			memcpy(&key_addrs->v6addrs, &iph->saddr,
-			       sizeof(key_addrs->v6addrs));
+			memcpy(&key_addrs->v6addrs.src, &iph->saddr,
+			       sizeof(key_addrs->v6addrs.src));
+			memcpy(&key_addrs->v6addrs.dst, &iph->daddr,
+			       sizeof(key_addrs->v6addrs.dst));
 			key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 		}
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 058/176] samples: bpf: Fix tracex7 error raised on the missing argument

[Sasha Levin]

From: Juhee Kang <claudiajkang@gmail.com>

[ Upstream commit 7d07006f05922b95518be403f08ef8437b67aa32 ]

The current behavior of 'tracex7' doesn't consist with other bpf samples
tracex{1..6}. Other samples do not require any argument to run with, but
tracex7 should be run with btrfs device argument. (it should be executed
with test_override_return.sh)

Currently, tracex7 doesn't have any description about how to run this
program and raises an unexpected error. And this result might be
confusing since users might not have a hunch about how to run this
program.

    // Current behavior
    # ./tracex7
    sh: 1: Syntax error: word unexpected (expecting ")")
    // Fixed behavior
    # ./tracex7
    ERROR: Run with the btrfs device argument!

In order to fix this error, this commit adds logic to report a message
and exit when running this program with a missing argument.

Additionally in test_override_return.sh, there is a problem with
multiple directory(tmpmnt) creation. So in this commit adds a line with
removing the directory with every execution.

Signed-off-by: Juhee Kang <claudiajkang@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210727041056.23455-1-claudiajkang@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 samples/bpf/test_override_return.sh | 1 +
 samples/bpf/tracex7_user.c          | 5 +++++
 2 files changed, 6 insertions(+)

diff --git a/samples/bpf/test_override_return.sh b/samples/bpf/test_override_return.sh
index e68b9ee6814b..35db26f736b9 100755
--- a/samples/bpf/test_override_return.sh
+++ b/samples/bpf/test_override_return.sh
@@ -1,5 +1,6 @@
 #!/bin/bash
 
+rm -r tmpmnt
 rm -f testfile.img
 dd if=/dev/zero of=testfile.img bs=1M seek=1000 count=1
 DEVICE=$(losetup --show -f testfile.img)
diff --git a/samples/bpf/tracex7_user.c b/samples/bpf/tracex7_user.c
index fdcd6580dd73..8be7ce18d3ba 100644
--- a/samples/bpf/tracex7_user.c
+++ b/samples/bpf/tracex7_user.c
@@ -14,6 +14,11 @@ int main(int argc, char **argv)
 	int ret = 0;
 	FILE *f;
 
+	if (!argv[1]) {
+		fprintf(stderr, "ERROR: Run with the btrfs device argument!\n");
+		return 0;
+	}
+
 	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
 	obj = bpf_object__open_file(filename, NULL);
 	if (libbpf_get_error(obj)) {
-- 
2.30.2

[PATCH AUTOSEL 5.10 059/176] libbpf: Fix race when pinning maps in parallel

[Sasha Levin]

From: Martynas Pumputis <m@lambda.lt>

[ Upstream commit 043c5bb3c4f43670ab4fea0b847373ab42d25f3e ]

When loading in parallel multiple programs which use the same to-be
pinned map, it is possible that two instances of the loader will call
bpf_object__create_maps() at the same time. If the map doesn't exist
when both instances call bpf_object__reuse_map(), then one of the
instances will fail with EEXIST when calling bpf_map__pin().

Fix the race by retrying reusing a map if bpf_map__pin() returns
EEXIST. The fix is similar to the one in iproute2: e4c4685fd6e4 ("bpf:
Fix race condition with map pinning").

Before retrying the pinning, we don't do any special cleaning of an
internal map state. The closer code inspection revealed that it's not
required:

    - bpf_object__create_map(): map->inner_map is destroyed after a
      successful call, map->fd is closed if pinning fails.
    - bpf_object__populate_internal_map(): created map elements is
      destroyed upon close(map->fd).
    - init_map_slots(): slots are freed after their initialization.

Signed-off-by: Martynas Pumputis <m@lambda.lt>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210726152001.34845-1-m@lambda.lt
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/libbpf.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a4e61dd5d8b3..d24531bb69d4 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4286,10 +4286,13 @@ bpf_object__create_maps(struct bpf_object *obj)
 	char *cp, errmsg[STRERR_BUFSIZE];
 	unsigned int i, j;
 	int err;
+	bool retried;
 
 	for (i = 0; i < obj->nr_maps; i++) {
 		map = &obj->maps[i];
 
+		retried = false;
+retry:
 		if (map->pin_path) {
 			err = bpf_object__reuse_map(map);
 			if (err) {
@@ -4297,6 +4300,12 @@ bpf_object__create_maps(struct bpf_object *obj)
 					map->name);
 				goto err_out;
 			}
+			if (retried && map->fd < 0) {
+				pr_warn("map '%s': cannot find pinned map\n",
+					map->name);
+				err = -ENOENT;
+				goto err_out;
+			}
 		}
 
 		if (map->fd >= 0) {
@@ -4330,9 +4339,13 @@ bpf_object__create_maps(struct bpf_object *obj)
 		if (map->pin_path && !map->pinned) {
 			err = bpf_map__pin(map, NULL);
 			if (err) {
+				zclose(map->fd);
+				if (!retried && err == -EEXIST) {
+					retried = true;
+					goto retry;
+				}
 				pr_warn("map '%s': failed to auto-pin at '%s': %d\n",
 					map->name, map->pin_path, err);
-				zclose(map->fd);
 				goto err_out;
 			}
 		}
-- 
2.30.2

[PATCH AUTOSEL 5.10 062/176] Bluetooth: skip invalid hci_sync_conn_complete_evt

[Sasha Levin]

From: Desmond Cheong Zhi Xi <desmondcheongzx@gmail.com>

[ Upstream commit 92fe24a7db751b80925214ede43f8d2be792ea7b ]

Syzbot reported a corrupted list in kobject_add_internal [1]. This
happens when multiple HCI_EV_SYNC_CONN_COMPLETE event packets with
status 0 are sent for the same HCI connection. This causes us to
register the device more than once which corrupts the kset list.

As this is forbidden behavior, we add a check for whether we're
trying to process the same HCI_EV_SYNC_CONN_COMPLETE event multiple
times for one connection. If that's the case, the event is invalid, so
we report an error that the device is misbehaving, and ignore the
packet.

Link: https://syzkaller.appspot.com/bug?extid=66264bf2fd0476be7e6c [1]
Reported-by: syzbot+66264bf2fd0476be7e6c@syzkaller.appspotmail.com
Tested-by: syzbot+66264bf2fd0476be7e6c@syzkaller.appspotmail.com
Signed-off-by: Desmond Cheong Zhi Xi <desmondcheongzx@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/bluetooth/hci_event.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index e59ae24a8f17..45de2d8b9a9d 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -4329,6 +4329,21 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev,
 
 	switch (ev->status) {
 	case 0x00:
+		/* The synchronous connection complete event should only be
+		 * sent once per new connection. Receiving a successful
+		 * complete event when the connection status is already
+		 * BT_CONNECTED means that the device is misbehaving and sent
+		 * multiple complete event packets for the same new connection.
+		 *
+		 * Registering the device more than once can corrupt kernel
+		 * memory, hence upon detecting this invalid event, we report
+		 * an error and ignore the packet.
+		 */
+		if (conn->state == BT_CONNECTED) {
+			bt_dev_err(hdev, "Ignoring connect complete event for existing connection");
+			goto unlock;
+		}
+
 		conn->handle = __le16_to_cpu(ev->handle);
 		conn->state  = BT_CONNECTED;
 		conn->type   = ev->link_type;
-- 
2.30.2

[PATCH AUTOSEL 5.10 067/176] bonding: 3ad: fix the concurrency between __bond_release_one() and bond_3ad_state_machine_handler()

[Sasha Levin]

From: Yufeng Mo <moyufeng@huawei.com>

[ Upstream commit 220ade77452c15ecb1ab94c3f8aaeb6d033c3582 ]

Some time ago, I reported a calltrace issue
"did not find a suitable aggregator", please see[1].
After a period of analysis and reproduction, I find
that this problem is caused by concurrency.

Before the problem occurs, the bond structure is like follows:

bond0 - slaver0(eth0) - agg0.lag_ports -> port0 - port1
                      \
                        port0
      \
        slaver1(eth1) - agg1.lag_ports -> NULL
                      \
                        port1

If we run 'ifenslave bond0 -d eth1', the process is like below:

excuting __bond_release_one()
|
bond_upper_dev_unlink()[step1]
|                       |                       |
|                       |                       bond_3ad_lacpdu_recv()
|                       |                       ->bond_3ad_rx_indication()
|                       |                       spin_lock_bh()
|                       |                       ->ad_rx_machine()
|                       |                       ->__record_pdu()[step2]
|                       |                       spin_unlock_bh()
|                       |                       |
|                       bond_3ad_state_machine_handler()
|                       spin_lock_bh()
|                       ->ad_port_selection_logic()
|                       ->try to find free aggregator[step3]
|                       ->try to find suitable aggregator[step4]
|                       ->did not find a suitable aggregator[step5]
|                       spin_unlock_bh()
|                       |
|                       |
bond_3ad_unbind_slave() |
spin_lock_bh()
spin_unlock_bh()

step1: already removed slaver1(eth1) from list, but port1 remains
step2: receive a lacpdu and update port0
step3: port0 will be removed from agg0.lag_ports. The struct is
       "agg0.lag_ports -> port1" now, and agg0 is not free. At the
	   same time, slaver1/agg1 has been removed from the list by step1.
	   So we can't find a free aggregator now.
step4: can't find suitable aggregator because of step2
step5: cause a calltrace since port->aggregator is NULL

To solve this concurrency problem, put bond_upper_dev_unlink()
after bond_3ad_unbind_slave(). In this way, we can invalid the port
first and skip this port in bond_3ad_state_machine_handler(). This
eliminates the situation that the slaver has been removed from the
list but the port is still valid.

[1]https://lore.kernel.org/netdev/10374.1611947473@famine/

Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Acked-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/bonding/bond_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 018af1e38eb9..645c7cabcbe4 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2219,7 +2219,6 @@ static int __bond_release_one(struct net_device *bond_dev,
 	/* recompute stats just before removing the slave */
 	bond_get_stats(bond->dev, &bond->bond_stats);
 
-	bond_upper_dev_unlink(bond, slave);
 	/* unregister rx_handler early so bond_handle_frame wouldn't be called
 	 * for this slave anymore.
 	 */
@@ -2228,6 +2227,8 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (BOND_MODE(bond) == BOND_MODE_8023AD)
 		bond_3ad_unbind_slave(slave);
 
+	bond_upper_dev_unlink(bond, slave);
+
 	if (bond_mode_can_use_xmit_hash(bond))
 		bond_update_slave_arr(bond, slave);
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 071/176] bpf: Fix off-by-one in tail call count limiting

[Sasha Levin]

From: Johan Almbladh <johan.almbladh@anyfinetworks.com>

[ Upstream commit b61a28cf11d61f512172e673b8f8c4a6c789b425 ]

Before, the interpreter allowed up to MAX_TAIL_CALL_CNT + 1 tail calls.
Now precisely MAX_TAIL_CALL_CNT is allowed, which is in line with the
behavior of the x86 JITs.

Signed-off-by: Johan Almbladh <johan.almbladh@anyfinetworks.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210728164741.350370-1-johan.almbladh@anyfinetworks.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index d12efb2550d3..f25b23fddbee 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1565,7 +1565,7 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 
 		if (unlikely(index >= array->map.max_entries))
 			goto out;
-		if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT))
+		if (unlikely(tail_call_cnt >= MAX_TAIL_CALL_CNT))
 			goto out;
 
 		tail_call_cnt++;
-- 
2.30.2

[PATCH AUTOSEL 5.10 091/176] net: ethernet: stmmac: Do not use unreachable() in ipq806x_gmac_probe()

[Sasha Levin]

From: Nathan Chancellor <nathan@kernel.org>

[ Upstream commit 4367355dd90942a71641c98c40c74589c9bddf90 ]

When compiling with clang in certain configurations, an objtool warning
appears:

drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.o: warning: objtool:
ipq806x_gmac_probe() falls through to next function phy_modes()

This happens because the unreachable annotation in the third switch
statement is not eliminated. The compiler should know that the first
default case would prevent the second and third from being reached as
the comment notes but sanitizer options can make it harder for the
compiler to reason this out.

Help the compiler out by eliminating the unreachable() annotation and
unifying the default case error handling so that there is no objtool
warning, the meaning of the code stays the same, and there is less
duplication.

Reported-by: Sami Tolvanen <samitolvanen@google.com>
Tested-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../ethernet/stmicro/stmmac/dwmac-ipq806x.c    | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
index 749585fe6fc9..90f69f43770a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -289,10 +289,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 		val &= ~NSS_COMMON_GMAC_CTL_PHY_IFACE_SEL;
 		break;
 	default:
-		dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n",
-			phy_modes(gmac->phy_mode));
-		err = -EINVAL;
-		goto err_remove_config_dt;
+		goto err_unsupported_phy;
 	}
 	regmap_write(gmac->nss_common, NSS_COMMON_GMAC_CTL(gmac->id), val);
 
@@ -309,10 +306,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 			NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id);
 		break;
 	default:
-		dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n",
-			phy_modes(gmac->phy_mode));
-		err = -EINVAL;
-		goto err_remove_config_dt;
+		goto err_unsupported_phy;
 	}
 	regmap_write(gmac->nss_common, NSS_COMMON_CLK_SRC_CTRL, val);
 
@@ -329,8 +323,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 				NSS_COMMON_CLK_GATE_GMII_TX_EN(gmac->id);
 		break;
 	default:
-		/* We don't get here; the switch above will have errored out */
-		unreachable();
+		goto err_unsupported_phy;
 	}
 	regmap_write(gmac->nss_common, NSS_COMMON_CLK_GATE, val);
 
@@ -361,6 +354,11 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_unsupported_phy:
+	dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n",
+		phy_modes(gmac->phy_mode));
+	err = -EINVAL;
+
 err_remove_config_dt:
 	stmmac_remove_config_dt(pdev, plat_dat);
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 099/176] selftests/bpf: Fix xdp_tx.c prog section name

[Sasha Levin]

From: Jussi Maki <joamaki@gmail.com>

[ Upstream commit 95413846cca37f20000dd095cf6d91f8777129d7 ]

The program type cannot be deduced from 'tx' which causes an invalid
argument error when trying to load xdp_tx.o using the skeleton.
Rename the section name to "xdp" so that libbpf can deduce the type.

Signed-off-by: Jussi Maki <joamaki@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210731055738.16820-7-joamaki@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/progs/xdp_tx.c   | 2 +-
 tools/testing/selftests/bpf/test_xdp_veth.sh | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/xdp_tx.c b/tools/testing/selftests/bpf/progs/xdp_tx.c
index 94e6c2b281cb..5f725c720e00 100644
--- a/tools/testing/selftests/bpf/progs/xdp_tx.c
+++ b/tools/testing/selftests/bpf/progs/xdp_tx.c
@@ -3,7 +3,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-SEC("tx")
+SEC("xdp")
 int xdp_tx(struct xdp_md *xdp)
 {
 	return XDP_TX;
diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh
index ba8ffcdaac30..995278e684b6 100755
--- a/tools/testing/selftests/bpf/test_xdp_veth.sh
+++ b/tools/testing/selftests/bpf/test_xdp_veth.sh
@@ -108,7 +108,7 @@ ip link set dev veth2 xdp pinned $BPF_DIR/progs/redirect_map_1
 ip link set dev veth3 xdp pinned $BPF_DIR/progs/redirect_map_2
 
 ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp_dummy
-ip -n ns2 link set dev veth22 xdp obj xdp_tx.o sec tx
+ip -n ns2 link set dev veth22 xdp obj xdp_tx.o sec xdp
 ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp_dummy
 
 trap cleanup EXIT
-- 
2.30.2

[PATCH AUTOSEL 5.10 101/176] Bluetooth: schedule SCO timeouts with delayed_work

[Sasha Levin]

From: Desmond Cheong Zhi Xi <desmondcheongzx@gmail.com>

[ Upstream commit ba316be1b6a00db7126ed9a39f9bee434a508043 ]

struct sock.sk_timer should be used as a sock cleanup timer. However,
SCO uses it to implement sock timeouts.

This causes issues because struct sock.sk_timer's callback is run in
an IRQ context, and the timer callback function sco_sock_timeout takes
a spin lock on the socket. However, other functions such as
sco_conn_del and sco_conn_ready take the spin lock with interrupts
enabled.

This inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} lock usage could
lead to deadlocks as reported by Syzbot [1]:
       CPU0
       ----
  lock(slock-AF_BLUETOOTH-BTPROTO_SCO);
  <Interrupt>
    lock(slock-AF_BLUETOOTH-BTPROTO_SCO);

To fix this, we use delayed work to implement SCO sock timouts
instead. This allows us to avoid taking the spin lock on the socket in
an IRQ context, and corrects the misuse of struct sock.sk_timer.

As a note, cancel_delayed_work is used instead of
cancel_delayed_work_sync in sco_sock_set_timer and
sco_sock_clear_timer to avoid a deadlock. In the future, the call to
bh_lock_sock inside sco_sock_timeout should be changed to lock_sock to
synchronize with other functions using lock_sock. However, since
sco_sock_set_timer and sco_sock_clear_timer are sometimes called under
the locked socket (in sco_connect and __sco_sock_close),
cancel_delayed_work_sync might cause them to sleep until an
sco_sock_timeout that has started finishes running. But
sco_sock_timeout would also sleep until it can grab the lock_sock.

Using cancel_delayed_work is fine because sco_sock_timeout does not
change from run to run, hence there is no functional difference
between:
1. waiting for a timeout to finish running before scheduling another
timeout
2. scheduling another timeout while a timeout is running.

Link: https://syzkaller.appspot.com/bug?id=9089d89de0502e120f234ca0fc8a703f7368b31e [1]
Reported-by: syzbot+2f6d7c28bb4bf7e82060@syzkaller.appspotmail.com
Tested-by: syzbot+2f6d7c28bb4bf7e82060@syzkaller.appspotmail.com
Signed-off-by: Desmond Cheong Zhi Xi <desmondcheongzx@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/bluetooth/sco.c | 35 +++++++++++++++++++++++++++++------
 1 file changed, 29 insertions(+), 6 deletions(-)

diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 22a110f37abc..8f4389370d33 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -48,6 +48,8 @@ struct sco_conn {
 	spinlock_t	lock;
 	struct sock	*sk;
 
+	struct delayed_work	timeout_work;
+
 	unsigned int    mtu;
 };
 
@@ -74,9 +76,20 @@ struct sco_pinfo {
 #define SCO_CONN_TIMEOUT	(HZ * 40)
 #define SCO_DISCONN_TIMEOUT	(HZ * 2)
 
-static void sco_sock_timeout(struct timer_list *t)
+static void sco_sock_timeout(struct work_struct *work)
 {
-	struct sock *sk = from_timer(sk, t, sk_timer);
+	struct sco_conn *conn = container_of(work, struct sco_conn,
+					     timeout_work.work);
+	struct sock *sk;
+
+	sco_conn_lock(conn);
+	sk = conn->sk;
+	if (sk)
+		sock_hold(sk);
+	sco_conn_unlock(conn);
+
+	if (!sk)
+		return;
 
 	BT_DBG("sock %p state %d", sk, sk->sk_state);
 
@@ -91,14 +104,21 @@ static void sco_sock_timeout(struct timer_list *t)
 
 static void sco_sock_set_timer(struct sock *sk, long timeout)
 {
+	if (!sco_pi(sk)->conn)
+		return;
+
 	BT_DBG("sock %p state %d timeout %ld", sk, sk->sk_state, timeout);
-	sk_reset_timer(sk, &sk->sk_timer, jiffies + timeout);
+	cancel_delayed_work(&sco_pi(sk)->conn->timeout_work);
+	schedule_delayed_work(&sco_pi(sk)->conn->timeout_work, timeout);
 }
 
 static void sco_sock_clear_timer(struct sock *sk)
 {
+	if (!sco_pi(sk)->conn)
+		return;
+
 	BT_DBG("sock %p state %d", sk, sk->sk_state);
-	sk_stop_timer(sk, &sk->sk_timer);
+	cancel_delayed_work(&sco_pi(sk)->conn->timeout_work);
 }
 
 /* ---- SCO connections ---- */
@@ -179,6 +199,9 @@ static void sco_conn_del(struct hci_conn *hcon, int err)
 		bh_unlock_sock(sk);
 		sco_sock_kill(sk);
 		sock_put(sk);
+
+		/* Ensure no more work items will run before freeing conn. */
+		cancel_delayed_work_sync(&conn->timeout_work);
 	}
 
 	hcon->sco_data = NULL;
@@ -193,6 +216,8 @@ static void __sco_chan_add(struct sco_conn *conn, struct sock *sk,
 	sco_pi(sk)->conn = conn;
 	conn->sk = sk;
 
+	INIT_DELAYED_WORK(&conn->timeout_work, sco_sock_timeout);
+
 	if (parent)
 		bt_accept_enqueue(parent, sk, true);
 }
@@ -500,8 +525,6 @@ static struct sock *sco_sock_alloc(struct net *net, struct socket *sock,
 
 	sco_pi(sk)->setting = BT_VOICE_CVSD_16BIT;
 
-	timer_setup(&sk->sk_timer, sco_sock_timeout, 0);
-
 	bt_sock_link(&sco_sk_list, sk);
 	return sk;
 }
-- 
2.30.2

[PATCH AUTOSEL 5.10 102/176] Bluetooth: avoid circular locks in sco_sock_connect

[Sasha Levin]

From: Desmond Cheong Zhi Xi <desmondcheongzx@gmail.com>

[ Upstream commit 734bc5ff783115aa3164f4e9dd5967ae78e0a8ab ]

In a future patch, calls to bh_lock_sock in sco.c should be replaced
by lock_sock now that none of the functions are run in IRQ context.

However, doing so results in a circular locking dependency:

======================================================
WARNING: possible circular locking dependency detected
5.14.0-rc4-syzkaller #0 Not tainted
------------------------------------------------------
syz-executor.2/14867 is trying to acquire lock:
ffff88803e3c1120 (sk_lock-AF_BLUETOOTH-BTPROTO_SCO){+.+.}-{0:0}, at:
lock_sock include/net/sock.h:1613 [inline]
ffff88803e3c1120 (sk_lock-AF_BLUETOOTH-BTPROTO_SCO){+.+.}-{0:0}, at:
sco_conn_del+0x12a/0x2a0 net/bluetooth/sco.c:191

but task is already holding lock:
ffffffff8d2dc7c8 (hci_cb_list_lock){+.+.}-{3:3}, at:
hci_disconn_cfm include/net/bluetooth/hci_core.h:1497 [inline]
ffffffff8d2dc7c8 (hci_cb_list_lock){+.+.}-{3:3}, at:
hci_conn_hash_flush+0xda/0x260 net/bluetooth/hci_conn.c:1608

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #2 (hci_cb_list_lock){+.+.}-{3:3}:
       __mutex_lock_common kernel/locking/mutex.c:959 [inline]
       __mutex_lock+0x12a/0x10a0 kernel/locking/mutex.c:1104
       hci_connect_cfm include/net/bluetooth/hci_core.h:1482 [inline]
       hci_remote_features_evt net/bluetooth/hci_event.c:3263 [inline]
       hci_event_packet+0x2f4d/0x7c50 net/bluetooth/hci_event.c:6240
       hci_rx_work+0x4f8/0xd30 net/bluetooth/hci_core.c:5122
       process_one_work+0x98d/0x1630 kernel/workqueue.c:2276
       worker_thread+0x658/0x11f0 kernel/workqueue.c:2422
       kthread+0x3e5/0x4d0 kernel/kthread.c:319
       ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295

-> #1 (&hdev->lock){+.+.}-{3:3}:
       __mutex_lock_common kernel/locking/mutex.c:959 [inline]
       __mutex_lock+0x12a/0x10a0 kernel/locking/mutex.c:1104
       sco_connect net/bluetooth/sco.c:245 [inline]
       sco_sock_connect+0x227/0xa10 net/bluetooth/sco.c:601
       __sys_connect_file+0x155/0x1a0 net/socket.c:1879
       __sys_connect+0x161/0x190 net/socket.c:1896
       __do_sys_connect net/socket.c:1906 [inline]
       __se_sys_connect net/socket.c:1903 [inline]
       __x64_sys_connect+0x6f/0xb0 net/socket.c:1903
       do_syscall_x64 arch/x86/entry/common.c:50 [inline]
       do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
       entry_SYSCALL_64_after_hwframe+0x44/0xae

-> #0 (sk_lock-AF_BLUETOOTH-BTPROTO_SCO){+.+.}-{0:0}:
       check_prev_add kernel/locking/lockdep.c:3051 [inline]
       check_prevs_add kernel/locking/lockdep.c:3174 [inline]
       validate_chain kernel/locking/lockdep.c:3789 [inline]
       __lock_acquire+0x2a07/0x54a0 kernel/locking/lockdep.c:5015
       lock_acquire kernel/locking/lockdep.c:5625 [inline]
       lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5590
       lock_sock_nested+0xca/0x120 net/core/sock.c:3170
       lock_sock include/net/sock.h:1613 [inline]
       sco_conn_del+0x12a/0x2a0 net/bluetooth/sco.c:191
       sco_disconn_cfm+0x71/0xb0 net/bluetooth/sco.c:1202
       hci_disconn_cfm include/net/bluetooth/hci_core.h:1500 [inline]
       hci_conn_hash_flush+0x127/0x260 net/bluetooth/hci_conn.c:1608
       hci_dev_do_close+0x528/0x1130 net/bluetooth/hci_core.c:1778
       hci_unregister_dev+0x1c0/0x5a0 net/bluetooth/hci_core.c:4015
       vhci_release+0x70/0xe0 drivers/bluetooth/hci_vhci.c:340
       __fput+0x288/0x920 fs/file_table.c:280
       task_work_run+0xdd/0x1a0 kernel/task_work.c:164
       exit_task_work include/linux/task_work.h:32 [inline]
       do_exit+0xbd4/0x2a60 kernel/exit.c:825
       do_group_exit+0x125/0x310 kernel/exit.c:922
       get_signal+0x47f/0x2160 kernel/signal.c:2808
       arch_do_signal_or_restart+0x2a9/0x1c40 arch/x86/kernel/signal.c:865
       handle_signal_work kernel/entry/common.c:148 [inline]
       exit_to_user_mode_loop kernel/entry/common.c:172 [inline]
       exit_to_user_mode_prepare+0x17d/0x290 kernel/entry/common.c:209
       __syscall_exit_to_user_mode_work kernel/entry/common.c:291 [inline]
       syscall_exit_to_user_mode+0x19/0x60 kernel/entry/common.c:302
       ret_from_fork+0x15/0x30 arch/x86/entry/entry_64.S:288

other info that might help us debug this:

Chain exists of:
  sk_lock-AF_BLUETOOTH-BTPROTO_SCO --> &hdev->lock --> hci_cb_list_lock

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(hci_cb_list_lock);
                               lock(&hdev->lock);
                               lock(hci_cb_list_lock);
  lock(sk_lock-AF_BLUETOOTH-BTPROTO_SCO);

 *** DEADLOCK ***

The issue is that the lock hierarchy should go from &hdev->lock -->
hci_cb_list_lock --> sk_lock-AF_BLUETOOTH-BTPROTO_SCO. For example,
one such call trace is:

  hci_dev_do_close():
    hci_dev_lock();
    hci_conn_hash_flush():
      hci_disconn_cfm():
        mutex_lock(&hci_cb_list_lock);
        sco_disconn_cfm():
        sco_conn_del():
          lock_sock(sk);

However, in sco_sock_connect, we call lock_sock before calling
hci_dev_lock inside sco_connect, thus inverting the lock hierarchy.

We fix this by pulling the call to hci_dev_lock out from sco_connect.

Signed-off-by: Desmond Cheong Zhi Xi <desmondcheongzx@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/bluetooth/sco.c | 39 ++++++++++++++++-----------------------
 1 file changed, 16 insertions(+), 23 deletions(-)

diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 8f4389370d33..21bd4ed98311 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -237,44 +237,32 @@ static int sco_chan_add(struct sco_conn *conn, struct sock *sk,
 	return err;
 }
 
-static int sco_connect(struct sock *sk)
+static int sco_connect(struct hci_dev *hdev, struct sock *sk)
 {
 	struct sco_conn *conn;
 	struct hci_conn *hcon;
-	struct hci_dev  *hdev;
 	int err, type;
 
 	BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst);
 
-	hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR);
-	if (!hdev)
-		return -EHOSTUNREACH;
-
-	hci_dev_lock(hdev);
-
 	if (lmp_esco_capable(hdev) && !disable_esco)
 		type = ESCO_LINK;
 	else
 		type = SCO_LINK;
 
 	if (sco_pi(sk)->setting == BT_VOICE_TRANSPARENT &&
-	    (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) {
-		err = -EOPNOTSUPP;
-		goto done;
-	}
+	    (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev)))
+		return -EOPNOTSUPP;
 
 	hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst,
 			       sco_pi(sk)->setting);
-	if (IS_ERR(hcon)) {
-		err = PTR_ERR(hcon);
-		goto done;
-	}
+	if (IS_ERR(hcon))
+		return PTR_ERR(hcon);
 
 	conn = sco_conn_add(hcon);
 	if (!conn) {
 		hci_conn_drop(hcon);
-		err = -ENOMEM;
-		goto done;
+		return -ENOMEM;
 	}
 
 	/* Update source addr of the socket */
@@ -282,7 +270,7 @@ static int sco_connect(struct sock *sk)
 
 	err = sco_chan_add(conn, sk, NULL);
 	if (err)
-		goto done;
+		return err;
 
 	if (hcon->state == BT_CONNECTED) {
 		sco_sock_clear_timer(sk);
@@ -292,9 +280,6 @@ static int sco_connect(struct sock *sk)
 		sco_sock_set_timer(sk, sk->sk_sndtimeo);
 	}
 
-done:
-	hci_dev_unlock(hdev);
-	hci_dev_put(hdev);
 	return err;
 }
 
@@ -589,6 +574,7 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen
 {
 	struct sockaddr_sco *sa = (struct sockaddr_sco *) addr;
 	struct sock *sk = sock->sk;
+	struct hci_dev  *hdev;
 	int err;
 
 	BT_DBG("sk %p", sk);
@@ -603,12 +589,19 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen
 	if (sk->sk_type != SOCK_SEQPACKET)
 		return -EINVAL;
 
+	hdev = hci_get_route(&sa->sco_bdaddr, &sco_pi(sk)->src, BDADDR_BREDR);
+	if (!hdev)
+		return -EHOSTUNREACH;
+	hci_dev_lock(hdev);
+
 	lock_sock(sk);
 
 	/* Set destination address and psm */
 	bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr);
 
-	err = sco_connect(sk);
+	err = sco_connect(hdev, sk);
+	hci_dev_unlock(hdev);
+	hci_dev_put(hdev);
 	if (err)
 		goto done;
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 104/176] net/mlx5: Fix variable type to match 64bit

[Sasha Levin]

From: Eran Ben Elisha <eranbe@nvidia.com>

[ Upstream commit 979aa51967add26b37f9d77e01729d44a2da8e5f ]

Fix the following smatch warning:
wait_func_handle_exec_timeout() warn: should '1 << ent->idx' be a 64 bit type?

Use 1ULL, to have a 64 bit type variable.

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Eran Ben Elisha <eranbe@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index e49387dbef98..2e55e0088871 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -865,7 +865,7 @@ static void cb_timeout_handler(struct work_struct *work)
 	ent->ret = -ETIMEDOUT;
 	mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, timeout. Will cause a leak of a command resource\n",
 		       ent->idx, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
-	mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+	mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true);
 
 out:
 	cmd_ent_put(ent); /* for the cmd_ent_get() took on schedule delayed work */
@@ -982,7 +982,7 @@ static void cmd_work_handler(struct work_struct *work)
 		MLX5_SET(mbox_out, ent->out, status, status);
 		MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
 
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+		mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true);
 		return;
 	}
 
@@ -996,7 +996,7 @@ static void cmd_work_handler(struct work_struct *work)
 		poll_timeout(ent);
 		/* make sure we read the descriptor after ownership is SW */
 		rmb();
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, (ent->ret == -ETIMEDOUT));
+		mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, (ent->ret == -ETIMEDOUT));
 	}
 }
 
@@ -1056,7 +1056,7 @@ static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev,
 		       mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
 
 	ent->ret = -ETIMEDOUT;
-	mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+	mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true);
 }
 
 static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
-- 
2.30.2

[PATCH AUTOSEL 5.10 107/176] mac80211: Fix monitor MTU limit so that A-MSDUs get through

[Sasha Levin]

From: Johan Almbladh <johan.almbladh@anyfinetworks.com>

[ Upstream commit 79f5962baea74ce1cd4e5949598944bff854b166 ]

The maximum MTU was set to 2304, which is the maximum MSDU size. While
this is valid for normal WLAN interfaces, it is too low for monitor
interfaces. A monitor interface may receive and inject MPDU frames, and
the maximum MPDU frame size is larger than 2304. The MPDU may also
contain an A-MSDU frame, in which case the size may be much larger than
the MTU limit. Since the maximum size of an A-MSDU depends on the PHY
mode of the transmitting STA, it is not possible to set an exact MTU
limit for a monitor interface. Now the maximum MTU for a monitor
interface is unrestricted.

Signed-off-by: Johan Almbladh <johan.almbladh@anyfinetworks.com>
Link: https://lore.kernel.org/r/20210628123246.2070558-1-johan.almbladh@anyfinetworks.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/mac80211/iface.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 30589b4c09da..3a15ef8dd322 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -2000,9 +2000,16 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 
 		netdev_set_default_ethtool_ops(ndev, &ieee80211_ethtool_ops);
 
-		/* MTU range: 256 - 2304 */
+		/* MTU range is normally 256 - 2304, where the upper limit is
+		 * the maximum MSDU size. Monitor interfaces send and receive
+		 * MPDU and A-MSDU frames which may be much larger so we do
+		 * not impose an upper limit in that case.
+		 */
 		ndev->min_mtu = 256;
-		ndev->max_mtu = local->hw.max_mtu;
+		if (type == NL80211_IFTYPE_MONITOR)
+			ndev->max_mtu = 0;
+		else
+			ndev->max_mtu = local->hw.max_mtu;
 
 		ret = register_netdevice(ndev);
 		if (ret) {
-- 
2.30.2

[PATCH AUTOSEL 5.10 115/176] Bluetooth: Fix handling of LE Enhanced Connection Complete

[Sasha Levin]

From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>

[ Upstream commit cafae4cd625502f65d1798659c1aa9b62d38cc56 ]

LE Enhanced Connection Complete contains the Local RPA used in the
connection which must be used when set otherwise there could problems
when pairing since the address used by the remote stack could be the
Local RPA:

BLUETOOTH CORE SPECIFICATION Version 5.2 | Vol 4, Part E
page 2396

  'Resolvable Private Address being used by the local device for this
  connection. This is only valid when the Own_Address_Type (from the
  HCI_LE_Create_Connection, HCI_LE_Set_Advertising_Parameters,
  HCI_LE_Set_Extended_Advertising_Parameters, or
  HCI_LE_Extended_Create_Connection commands) is set to 0x02 or
  0x03, and the Controller generated a resolvable private address for the
  local device using a non-zero local IRK. For other Own_Address_Type
  values, the Controller shall return all zeros.'

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/bluetooth/hci_event.c | 93 ++++++++++++++++++++++++++-------------
 1 file changed, 62 insertions(+), 31 deletions(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 45de2d8b9a9d..9f52145bb7b7 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -5070,9 +5070,64 @@ static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev,
 }
 #endif
 
+static void le_conn_update_addr(struct hci_conn *conn, bdaddr_t *bdaddr,
+				u8 bdaddr_type, bdaddr_t *local_rpa)
+{
+	if (conn->out) {
+		conn->dst_type = bdaddr_type;
+		conn->resp_addr_type = bdaddr_type;
+		bacpy(&conn->resp_addr, bdaddr);
+
+		/* Check if the controller has set a Local RPA then it must be
+		 * used instead or hdev->rpa.
+		 */
+		if (local_rpa && bacmp(local_rpa, BDADDR_ANY)) {
+			conn->init_addr_type = ADDR_LE_DEV_RANDOM;
+			bacpy(&conn->init_addr, local_rpa);
+		} else if (hci_dev_test_flag(conn->hdev, HCI_PRIVACY)) {
+			conn->init_addr_type = ADDR_LE_DEV_RANDOM;
+			bacpy(&conn->init_addr, &conn->hdev->rpa);
+		} else {
+			hci_copy_identity_address(conn->hdev, &conn->init_addr,
+						  &conn->init_addr_type);
+		}
+	} else {
+		conn->resp_addr_type = conn->hdev->adv_addr_type;
+		/* Check if the controller has set a Local RPA then it must be
+		 * used instead or hdev->rpa.
+		 */
+		if (local_rpa && bacmp(local_rpa, BDADDR_ANY)) {
+			conn->resp_addr_type = ADDR_LE_DEV_RANDOM;
+			bacpy(&conn->resp_addr, local_rpa);
+		} else if (conn->hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) {
+			/* In case of ext adv, resp_addr will be updated in
+			 * Adv Terminated event.
+			 */
+			if (!ext_adv_capable(conn->hdev))
+				bacpy(&conn->resp_addr,
+				      &conn->hdev->random_addr);
+		} else {
+			bacpy(&conn->resp_addr, &conn->hdev->bdaddr);
+		}
+
+		conn->init_addr_type = bdaddr_type;
+		bacpy(&conn->init_addr, bdaddr);
+
+		/* For incoming connections, set the default minimum
+		 * and maximum connection interval. They will be used
+		 * to check if the parameters are in range and if not
+		 * trigger the connection update procedure.
+		 */
+		conn->le_conn_min_interval = conn->hdev->le_conn_min_interval;
+		conn->le_conn_max_interval = conn->hdev->le_conn_max_interval;
+	}
+}
+
 static void le_conn_complete_evt(struct hci_dev *hdev, u8 status,
-			bdaddr_t *bdaddr, u8 bdaddr_type, u8 role, u16 handle,
-			u16 interval, u16 latency, u16 supervision_timeout)
+				 bdaddr_t *bdaddr, u8 bdaddr_type,
+				 bdaddr_t *local_rpa, u8 role, u16 handle,
+				 u16 interval, u16 latency,
+				 u16 supervision_timeout)
 {
 	struct hci_conn_params *params;
 	struct hci_conn *conn;
@@ -5120,32 +5175,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status,
 		cancel_delayed_work(&conn->le_conn_timeout);
 	}
 
-	if (!conn->out) {
-		/* Set the responder (our side) address type based on
-		 * the advertising address type.
-		 */
-		conn->resp_addr_type = hdev->adv_addr_type;
-		if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) {
-			/* In case of ext adv, resp_addr will be updated in
-			 * Adv Terminated event.
-			 */
-			if (!ext_adv_capable(hdev))
-				bacpy(&conn->resp_addr, &hdev->random_addr);
-		} else {
-			bacpy(&conn->resp_addr, &hdev->bdaddr);
-		}
-
-		conn->init_addr_type = bdaddr_type;
-		bacpy(&conn->init_addr, bdaddr);
-
-		/* For incoming connections, set the default minimum
-		 * and maximum connection interval. They will be used
-		 * to check if the parameters are in range and if not
-		 * trigger the connection update procedure.
-		 */
-		conn->le_conn_min_interval = hdev->le_conn_min_interval;
-		conn->le_conn_max_interval = hdev->le_conn_max_interval;
-	}
+	le_conn_update_addr(conn, bdaddr, bdaddr_type, local_rpa);
 
 	/* Lookup the identity address from the stored connection
 	 * address and address type.
@@ -5239,7 +5269,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);
 
 	le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type,
-			     ev->role, le16_to_cpu(ev->handle),
+			     NULL, ev->role, le16_to_cpu(ev->handle),
 			     le16_to_cpu(ev->interval),
 			     le16_to_cpu(ev->latency),
 			     le16_to_cpu(ev->supervision_timeout));
@@ -5253,7 +5283,7 @@ static void hci_le_enh_conn_complete_evt(struct hci_dev *hdev,
 	BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);
 
 	le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type,
-			     ev->role, le16_to_cpu(ev->handle),
+			     &ev->local_rpa, ev->role, le16_to_cpu(ev->handle),
 			     le16_to_cpu(ev->interval),
 			     le16_to_cpu(ev->latency),
 			     le16_to_cpu(ev->supervision_timeout));
@@ -5289,7 +5319,8 @@ static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	if (conn) {
 		struct adv_info *adv_instance;
 
-		if (hdev->adv_addr_type != ADDR_LE_DEV_RANDOM)
+		if (hdev->adv_addr_type != ADDR_LE_DEV_RANDOM ||
+		    bacmp(&conn->resp_addr, BDADDR_ANY))
 			return;
 
 		if (!hdev->cur_adv_instance) {
-- 
2.30.2

[PATCH AUTOSEL 5.10 119/176] tcp: enable data-less, empty-cookie SYN with TFO_SERVER_COOKIE_NOT_REQD

[Sasha Levin]

From: Luke Hsiao <lukehsiao@google.com>

[ Upstream commit e3faa49bcecdfcc80e94dd75709d6acb1a5d89f6 ]

Since the original TFO server code was implemented in commit
168a8f58059a22feb9e9a2dcc1b8053dbbbc12ef ("tcp: TCP Fast Open Server -
main code path") the TFO server code has supported the sysctl bit flag
TFO_SERVER_COOKIE_NOT_REQD. Currently, when the TFO_SERVER_ENABLE and
TFO_SERVER_COOKIE_NOT_REQD sysctl bit flags are set, a server connection
will accept a SYN with N bytes of data (N > 0) that has no TFO cookie,
create a new fast open connection, process the incoming data in the SYN,
and make the connection ready for accepting. After accepting, the
connection is ready for read()/recvmsg() to read the N bytes of data in
the SYN, ready for write()/sendmsg() calls and data transmissions to
transmit data.

This commit changes an edge case in this feature by changing this
behavior to apply to (N >= 0) bytes of data in the SYN rather than only
(N > 0) bytes of data in the SYN. Now, a server will accept a data-less
SYN without a TFO cookie if TFO_SERVER_COOKIE_NOT_REQD is set.

Caveat! While this enables a new kind of TFO (data-less empty-cookie
SYN), some firewall rules setup may not work if they assume such packets
are not legit TFOs and will filter them.

Signed-off-by: Luke Hsiao <lukehsiao@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20210816205105.2533289-1-luke.w.hsiao@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/ipv4/tcp_fastopen.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index d49709ba8e16..107111984384 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -379,8 +379,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 		return NULL;
 	}
 
-	if (syn_data &&
-	    tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD))
+	if (tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD))
 		goto fastopen;
 
 	if (foc->len == 0) {
-- 
2.30.2

[PATCH AUTOSEL 5.10 120/176] rpc: fix gss_svc_init cleanup on failure

[Sasha Levin]

From: "J. Bruce Fields" <bfields@redhat.com>

[ Upstream commit 5a4753446253a427c0ff1e433b9c4933e5af207c ]

The failure case here should be rare, but it's obviously wrong.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/auth_gss/svcauth_gss.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 6dff64374bfe..e22f2d65457d 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -1980,7 +1980,7 @@ gss_svc_init_net(struct net *net)
 		goto out2;
 	return 0;
 out2:
-	destroy_use_gss_proxy_proc_entry(net);
+	rsi_cache_destroy_net(net);
 out1:
 	rsc_cache_destroy_net(net);
 	return rv;
-- 
2.30.2

[PATCH AUTOSEL 5.10 121/176] selftests/bpf: Fix flaky send_signal test

[Sasha Levin]

From: Yonghong Song <yhs@fb.com>

[ Upstream commit b16ac5bf732a5e23d164cf908ec7742d6a6120d3 ]

libbpf CI has reported send_signal test is flaky although
I am not able to reproduce it in my local environment.
But I am able to reproduce with on-demand libbpf CI ([1]).

Through code analysis, the following is possible reason.
The failed subtest runs bpf program in softirq environment.
Since bpf_send_signal() only sends to a fork of "test_progs"
process. If the underlying current task is
not "test_progs", bpf_send_signal() will not be triggered
and the subtest will fail.

To reduce the chances where the underlying process is not
the intended one, this patch boosted scheduling priority to
-20 (highest allowed by setpriority() call). And I did
10 runs with on-demand libbpf CI with this patch and I
didn't observe any failures.

 [1] https://github.com/libbpf/libbpf/actions/workflows/ondemand.yml

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210817190923.3186725-1-yhs@fb.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../selftests/bpf/prog_tests/send_signal.c       | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c
index 7043e6ded0e6..75b72c751772 100644
--- a/tools/testing/selftests/bpf/prog_tests/send_signal.c
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <sys/time.h>
+#include <sys/resource.h>
 #include "test_send_signal_kern.skel.h"
 
 static volatile int sigusr1_received = 0;
@@ -41,12 +43,23 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 	}
 
 	if (pid == 0) {
+		int old_prio;
+
 		/* install signal handler and notify parent */
 		signal(SIGUSR1, sigusr1_handler);
 
 		close(pipe_c2p[0]); /* close read */
 		close(pipe_p2c[1]); /* close write */
 
+		/* boost with a high priority so we got a higher chance
+		 * that if an interrupt happens, the underlying task
+		 * is this process.
+		 */
+		errno = 0;
+		old_prio = getpriority(PRIO_PROCESS, 0);
+		ASSERT_OK(errno, "getpriority");
+		ASSERT_OK(setpriority(PRIO_PROCESS, 0, -20), "setpriority");
+
 		/* notify parent signal handler is installed */
 		CHECK(write(pipe_c2p[1], buf, 1) != 1, "pipe_write", "err %d\n", -errno);
 
@@ -62,6 +75,9 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 		/* wait for parent notification and exit */
 		CHECK(read(pipe_p2c[0], buf, 1) != 1, "pipe_read", "err %d\n", -errno);
 
+		/* restore the old priority */
+		ASSERT_OK(setpriority(PRIO_PROCESS, 0, old_prio), "setpriority");
+
 		close(pipe_c2p[1]);
 		close(pipe_p2c[0]);
 		exit(0);
-- 
2.30.2

[PATCH AUTOSEL 5.10 124/176] net: Fix offloading indirect devices dependency on qdisc order creation

[Sasha Levin]

From: Eli Cohen <elic@nvidia.com>

[ Upstream commit 74fc4f828769cca1c3be89ea92cb88feaa27ef52 ]

Currently, when creating an ingress qdisc on an indirect device before
the driver registered for callbacks, the driver will not have a chance
to register its filter configuration callbacks.

To fix that, modify the code such that it keeps track of all the ingress
qdiscs that call flow_indr_dev_setup_offload(). When a driver calls
flow_indr_dev_register(),  go through the list of tracked ingress qdiscs
and call the driver callback entry point so as to give it a chance to
register its callback.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Eli Cohen <elic@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/flow_offload.h            |  1 +
 net/core/flow_offload.c               | 89 ++++++++++++++++++++++++++-
 net/netfilter/nf_flow_table_offload.c |  1 +
 net/netfilter/nf_tables_offload.c     |  1 +
 net/sched/cls_api.c                   |  1 +
 5 files changed, 92 insertions(+), 1 deletion(-)

diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index 123b1e9ea304..010d58159887 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -444,6 +444,7 @@ struct flow_block_offload {
 	struct list_head *driver_block_list;
 	struct netlink_ext_ack *extack;
 	struct Qdisc *sch;
+	struct list_head *cb_list_head;
 };
 
 enum tc_setup_type;
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index 715b67f6c62f..e3f0d5906811 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -321,6 +321,7 @@ EXPORT_SYMBOL(flow_block_cb_setup_simple);
 static DEFINE_MUTEX(flow_indr_block_lock);
 static LIST_HEAD(flow_block_indr_list);
 static LIST_HEAD(flow_block_indr_dev_list);
+static LIST_HEAD(flow_indir_dev_list);
 
 struct flow_indr_dev {
 	struct list_head		list;
@@ -346,6 +347,33 @@ static struct flow_indr_dev *flow_indr_dev_alloc(flow_indr_block_bind_cb_t *cb,
 	return indr_dev;
 }
 
+struct flow_indir_dev_info {
+	void *data;
+	struct net_device *dev;
+	struct Qdisc *sch;
+	enum tc_setup_type type;
+	void (*cleanup)(struct flow_block_cb *block_cb);
+	struct list_head list;
+	enum flow_block_command command;
+	enum flow_block_binder_type binder_type;
+	struct list_head *cb_list;
+};
+
+static void existing_qdiscs_register(flow_indr_block_bind_cb_t *cb, void *cb_priv)
+{
+	struct flow_block_offload bo;
+	struct flow_indir_dev_info *cur;
+
+	list_for_each_entry(cur, &flow_indir_dev_list, list) {
+		memset(&bo, 0, sizeof(bo));
+		bo.command = cur->command;
+		bo.binder_type = cur->binder_type;
+		INIT_LIST_HEAD(&bo.cb_list);
+		cb(cur->dev, cur->sch, cb_priv, cur->type, &bo, cur->data, cur->cleanup);
+		list_splice(&bo.cb_list, cur->cb_list);
+	}
+}
+
 int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv)
 {
 	struct flow_indr_dev *indr_dev;
@@ -367,6 +395,7 @@ int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv)
 	}
 
 	list_add(&indr_dev->list, &flow_block_indr_dev_list);
+	existing_qdiscs_register(cb, cb_priv);
 	mutex_unlock(&flow_indr_block_lock);
 
 	return 0;
@@ -463,7 +492,59 @@ struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb,
 }
 EXPORT_SYMBOL(flow_indr_block_cb_alloc);
 
-int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch,
+static struct flow_indir_dev_info *find_indir_dev(void *data)
+{
+	struct flow_indir_dev_info *cur;
+
+	list_for_each_entry(cur, &flow_indir_dev_list, list) {
+		if (cur->data == data)
+			return cur;
+	}
+	return NULL;
+}
+
+static int indir_dev_add(void *data, struct net_device *dev, struct Qdisc *sch,
+			 enum tc_setup_type type, void (*cleanup)(struct flow_block_cb *block_cb),
+			 struct flow_block_offload *bo)
+{
+	struct flow_indir_dev_info *info;
+
+	info = find_indir_dev(data);
+	if (info)
+		return -EEXIST;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->data = data;
+	info->dev = dev;
+	info->sch = sch;
+	info->type = type;
+	info->cleanup = cleanup;
+	info->command = bo->command;
+	info->binder_type = bo->binder_type;
+	info->cb_list = bo->cb_list_head;
+
+	list_add(&info->list, &flow_indir_dev_list);
+	return 0;
+}
+
+static int indir_dev_remove(void *data)
+{
+	struct flow_indir_dev_info *info;
+
+	info = find_indir_dev(data);
+	if (!info)
+		return -ENOENT;
+
+	list_del(&info->list);
+
+	kfree(info);
+	return 0;
+}
+
+int flow_indr_dev_setup_offload(struct net_device *dev,	struct Qdisc *sch,
 				enum tc_setup_type type, void *data,
 				struct flow_block_offload *bo,
 				void (*cleanup)(struct flow_block_cb *block_cb))
@@ -471,6 +552,12 @@ int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch,
 	struct flow_indr_dev *this;
 
 	mutex_lock(&flow_indr_block_lock);
+
+	if (bo->command == FLOW_BLOCK_BIND)
+		indir_dev_add(data, dev, sch, type, cleanup, bo);
+	else if (bo->command == FLOW_BLOCK_UNBIND)
+		indir_dev_remove(data);
+
 	list_for_each_entry(this, &flow_block_indr_dev_list, list)
 		this->cb(dev, sch, this->cb_priv, type, bo, data, cleanup);
 
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 92047cea3c17..a6b654b028dd 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -940,6 +940,7 @@ static void nf_flow_table_block_offload_init(struct flow_block_offload *bo,
 	bo->command	= cmd;
 	bo->binder_type	= FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
 	bo->extack	= extack;
+	bo->cb_list_head = &flowtable->flow_block.cb_list;
 	INIT_LIST_HEAD(&bo->cb_list);
 }
 
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index 9ce776175214..e5fcbb0e4b8e 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -323,6 +323,7 @@ static void nft_flow_block_offload_init(struct flow_block_offload *bo,
 	bo->command	= cmd;
 	bo->binder_type	= FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
 	bo->extack	= extack;
+	bo->cb_list_head = &basechain->flow_block.cb_list;
 	INIT_LIST_HEAD(&bo->cb_list);
 }
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 31ac76a9189e..8073657a0fd2 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -634,6 +634,7 @@ static void tcf_block_offload_init(struct flow_block_offload *bo,
 	bo->block_shared = shared;
 	bo->extack = extack;
 	bo->sch = sch;
+	bo->cb_list_head = &flow_block->cb_list;
 	INIT_LIST_HEAD(&bo->cb_list);
 }
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 131/176] rtl8xxxu: Fix the handling of TX A-MPDU aggregation

[Sasha Levin]

From: Chris Chiu <chris.chiu@canonical.com>

[ Upstream commit 95a581ab3592082c60a08090aabe09ac7d0bd650 ]

The TX A-MPDU aggregation is not handled in the driver since the
ieee80211_start_tx_ba_session has never been started properly.
Start and stop the TX BA session by tracking the TX aggregation
status of each TID. Fix the ampdu_action and the tx descriptor
accordingly with the given TID.

Signed-off-by: Chris Chiu <chris.chiu@canonical.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210804151325.86600-1-chris.chiu@canonical.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/wireless/realtek/rtl8xxxu/rtl8xxxu.h  |  2 ++
 .../wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 33 ++++++++++++++-----
 2 files changed, 26 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
index acb6b0cd3667..b28fa0c4d180 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
@@ -1378,6 +1378,8 @@ struct rtl8xxxu_priv {
 	u8 no_pape:1;
 	u8 int_buf[USB_INTR_CONTENT_LENGTH];
 	u8 rssi_level;
+	DECLARE_BITMAP(tx_aggr_started, IEEE80211_NUM_TIDS);
+	DECLARE_BITMAP(tid_tx_operational, IEEE80211_NUM_TIDS);
 	/*
 	 * Only one virtual interface permitted because only STA mode
 	 * is supported and no iface_combinations are provided.
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
index 5cd7ef3625c5..0d374a294840 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
@@ -4805,6 +4805,8 @@ rtl8xxxu_fill_txdesc_v1(struct ieee80211_hw *hw, struct ieee80211_hdr *hdr,
 	struct ieee80211_rate *tx_rate = ieee80211_get_tx_rate(hw, tx_info);
 	struct rtl8xxxu_priv *priv = hw->priv;
 	struct device *dev = &priv->udev->dev;
+	u8 *qc = ieee80211_get_qos_ctl(hdr);
+	u8 tid = qc[0] & IEEE80211_QOS_CTL_TID_MASK;
 	u32 rate;
 	u16 rate_flags = tx_info->control.rates[0].flags;
 	u16 seq_number;
@@ -4828,7 +4830,7 @@ rtl8xxxu_fill_txdesc_v1(struct ieee80211_hw *hw, struct ieee80211_hdr *hdr,
 
 	tx_desc->txdw3 = cpu_to_le32((u32)seq_number << TXDESC32_SEQ_SHIFT);
 
-	if (ampdu_enable)
+	if (ampdu_enable && test_bit(tid, priv->tid_tx_operational))
 		tx_desc->txdw1 |= cpu_to_le32(TXDESC32_AGG_ENABLE);
 	else
 		tx_desc->txdw1 |= cpu_to_le32(TXDESC32_AGG_BREAK);
@@ -4876,6 +4878,8 @@ rtl8xxxu_fill_txdesc_v2(struct ieee80211_hw *hw, struct ieee80211_hdr *hdr,
 	struct rtl8xxxu_priv *priv = hw->priv;
 	struct device *dev = &priv->udev->dev;
 	struct rtl8xxxu_txdesc40 *tx_desc40;
+	u8 *qc = ieee80211_get_qos_ctl(hdr);
+	u8 tid = qc[0] & IEEE80211_QOS_CTL_TID_MASK;
 	u32 rate;
 	u16 rate_flags = tx_info->control.rates[0].flags;
 	u16 seq_number;
@@ -4902,7 +4906,7 @@ rtl8xxxu_fill_txdesc_v2(struct ieee80211_hw *hw, struct ieee80211_hdr *hdr,
 
 	tx_desc40->txdw9 = cpu_to_le32((u32)seq_number << TXDESC40_SEQ_SHIFT);
 
-	if (ampdu_enable)
+	if (ampdu_enable && test_bit(tid, priv->tid_tx_operational))
 		tx_desc40->txdw2 |= cpu_to_le32(TXDESC40_AGG_ENABLE);
 	else
 		tx_desc40->txdw2 |= cpu_to_le32(TXDESC40_AGG_BREAK);
@@ -5015,12 +5019,19 @@ static void rtl8xxxu_tx(struct ieee80211_hw *hw,
 	if (ieee80211_is_data_qos(hdr->frame_control) && sta) {
 		if (sta->ht_cap.ht_supported) {
 			u32 ampdu, val32;
+			u8 *qc = ieee80211_get_qos_ctl(hdr);
+			u8 tid = qc[0] & IEEE80211_QOS_CTL_TID_MASK;
 
 			ampdu = (u32)sta->ht_cap.ampdu_density;
 			val32 = ampdu << TXDESC_AMPDU_DENSITY_SHIFT;
 			tx_desc->txdw2 |= cpu_to_le32(val32);
 
 			ampdu_enable = true;
+
+			if (!test_bit(tid, priv->tx_aggr_started) &&
+			    !(skb->protocol == cpu_to_be16(ETH_P_PAE)))
+				if (!ieee80211_start_tx_ba_session(sta, tid, 0))
+					set_bit(tid, priv->tx_aggr_started);
 		}
 	}
 
@@ -6095,6 +6106,7 @@ rtl8xxxu_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct device *dev = &priv->udev->dev;
 	u8 ampdu_factor, ampdu_density;
 	struct ieee80211_sta *sta = params->sta;
+	u16 tid = params->tid;
 	enum ieee80211_ampdu_mlme_action action = params->action;
 
 	switch (action) {
@@ -6107,17 +6119,20 @@ rtl8xxxu_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		dev_dbg(dev,
 			"Changed HT: ampdu_factor %02x, ampdu_density %02x\n",
 			ampdu_factor, ampdu_density);
-		break;
+		return IEEE80211_AMPDU_TX_START_IMMEDIATE;
+	case IEEE80211_AMPDU_TX_STOP_CONT:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH:
-		dev_dbg(dev, "%s: IEEE80211_AMPDU_TX_STOP_FLUSH\n", __func__);
-		rtl8xxxu_set_ampdu_factor(priv, 0);
-		rtl8xxxu_set_ampdu_min_space(priv, 0);
-		break;
 	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
-		dev_dbg(dev, "%s: IEEE80211_AMPDU_TX_STOP_FLUSH_CONT\n",
-			 __func__);
+		dev_dbg(dev, "%s: IEEE80211_AMPDU_TX_STOP\n", __func__);
 		rtl8xxxu_set_ampdu_factor(priv, 0);
 		rtl8xxxu_set_ampdu_min_space(priv, 0);
+		clear_bit(tid, priv->tx_aggr_started);
+		clear_bit(tid, priv->tid_tx_operational);
+		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
+		break;
+	case IEEE80211_AMPDU_TX_OPERATIONAL:
+		dev_dbg(dev, "%s: IEEE80211_AMPDU_TX_OPERATIONAL\n", __func__);
+		set_bit(tid, priv->tid_tx_operational);
 		break;
 	case IEEE80211_AMPDU_RX_START:
 		dev_dbg(dev, "%s: IEEE80211_AMPDU_RX_START\n", __func__);
-- 
2.30.2

[PATCH AUTOSEL 5.10 132/176] rtw88: use read_poll_timeout instead of fixed sleep

[Sasha Levin]

From: Chin-Yen Lee <timlee@realtek.com>

[ Upstream commit 02a55c0009a55b204e1e5c17295431f0a9e7d3b6 ]

In current wow flow, driver calls rtw_wow_fw_start and sleep for 100ms,
to wait firmware finish preliminary work and then update the value of
WOWLAN_WAKE_REASON register to zero. But later firmware will start wow
function with power-saving mode, in which mode the value of
WOWLAN_WAKE_REASON register is 0xea. So driver may get 0xea value and
return fail. We use read_poll_timeout instead to check the value to avoid
this issue.

Signed-off-by: Chin-Yen Lee <timlee@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210728014335.8785-2-pkshih@realtek.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/realtek/rtw88/wow.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/wow.c b/drivers/net/wireless/realtek/rtw88/wow.c
index 2fcdf70a3a77..bb2fd4e544f0 100644
--- a/drivers/net/wireless/realtek/rtw88/wow.c
+++ b/drivers/net/wireless/realtek/rtw88/wow.c
@@ -283,15 +283,26 @@ static void rtw_wow_rx_dma_start(struct rtw_dev *rtwdev)
 
 static int rtw_wow_check_fw_status(struct rtw_dev *rtwdev, bool wow_enable)
 {
-	/* wait 100ms for wow firmware to finish work */
-	msleep(100);
+	int ret;
+	u8 check;
+	u32 check_dis;
 
 	if (wow_enable) {
-		if (rtw_read8(rtwdev, REG_WOWLAN_WAKE_REASON))
+		ret = read_poll_timeout(rtw_read8, check, !check, 1000,
+					100000, true, rtwdev,
+					REG_WOWLAN_WAKE_REASON);
+		if (ret)
 			goto wow_fail;
 	} else {
-		if (rtw_read32_mask(rtwdev, REG_FE1IMR, BIT_FS_RXDONE) ||
-		    rtw_read32_mask(rtwdev, REG_RXPKT_NUM, BIT_RW_RELEASE))
+		ret = read_poll_timeout(rtw_read32_mask, check_dis,
+					!check_dis, 1000, 100000, true, rtwdev,
+					REG_FE1IMR, BIT_FS_RXDONE);
+		if (ret)
+			goto wow_fail;
+		ret = read_poll_timeout(rtw_read32_mask, check_dis,
+					!check_dis, 1000, 100000, false, rtwdev,
+					REG_RXPKT_NUM, BIT_RW_RELEASE);
+		if (ret)
 			goto wow_fail;
 	}
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 133/176] rtw88: wow: build wow function only if CONFIG_PM is on

[Sasha Levin]

From: Ping-Ke Shih <pkshih@realtek.com>

[ Upstream commit 05e45887382c4c0f9522515759b34991aa17e69d ]

The kernel test robot reports undefined reference after we report wakeup
reason to mac80211. This is because CONFIG_PM is not defined in the testing
configuration file. In fact, functions within wow.c are used if CONFIG_PM
is defined, so use CONFIG_PM to decide whether we build this file or not.

The reported messages are:
   hppa-linux-ld: drivers/net/wireless/realtek/rtw88/wow.o: in function `rtw_wow_show_wakeup_reason':
>> (.text+0x6c4): undefined reference to `ieee80211_report_wowlan_wakeup'
>> hppa-linux-ld: (.text+0x6e0): undefined reference to `ieee80211_report_wowlan_wakeup'

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210728014335.8785-4-pkshih@realtek.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/realtek/rtw88/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw88/Makefile b/drivers/net/wireless/realtek/rtw88/Makefile
index c0e4b111c8b4..73d6807a8cdf 100644
--- a/drivers/net/wireless/realtek/rtw88/Makefile
+++ b/drivers/net/wireless/realtek/rtw88/Makefile
@@ -15,9 +15,9 @@ rtw88_core-y += main.o \
 	   ps.o \
 	   sec.o \
 	   bf.o \
-	   wow.o \
 	   regd.o
 
+rtw88_core-$(CONFIG_PM) += wow.o
 
 obj-$(CONFIG_RTW88_8822B)	+= rtw88_8822b.o
 rtw88_8822b-objs		:= rtw8822b.o rtw8822b_table.o
-- 
2.30.2

[PATCH AUTOSEL 5.10 134/176] rtw88: wow: fix size access error of probe request

[Sasha Levin]

From: Chin-Yen Lee <timlee@realtek.com>

[ Upstream commit 69c7044526d984df672b8d9b6d6998c34617cde4 ]

Current flow will lead to null ptr access because of trying
to get the size of freed probe-request packets. We store the
information of packet size into rsvd page instead and also fix
the size error issue, which will cause unstable behavoir of
sending probe request by wow firmware.

Signed-off-by: Chin-Yen Lee <timlee@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20210728014335.8785-6-pkshih@realtek.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/realtek/rtw88/fw.c | 8 ++++++--
 drivers/net/wireless/realtek/rtw88/fw.h | 1 +
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c
index b2fd87834f23..0452630bcfac 100644
--- a/drivers/net/wireless/realtek/rtw88/fw.c
+++ b/drivers/net/wireless/realtek/rtw88/fw.c
@@ -684,7 +684,7 @@ static u16 rtw_get_rsvd_page_probe_req_size(struct rtw_dev *rtwdev,
 			continue;
 		if ((!ssid && !rsvd_pkt->ssid) ||
 		    rtw_ssid_equal(rsvd_pkt->ssid, ssid))
-			size = rsvd_pkt->skb->len;
+			size = rsvd_pkt->probe_req_size;
 	}
 
 	return size;
@@ -912,6 +912,8 @@ static struct sk_buff *rtw_get_rsvd_page_skb(struct ieee80211_hw *hw,
 							 ssid->ssid_len, 0);
 		else
 			skb_new = ieee80211_probereq_get(hw, vif->addr, NULL, 0, 0);
+		if (skb_new)
+			rsvd_pkt->probe_req_size = (u16)skb_new->len;
 		break;
 	case RSVD_NLO_INFO:
 		skb_new = rtw_nlo_info_get(hw);
@@ -1508,6 +1510,7 @@ int rtw_fw_dump_fifo(struct rtw_dev *rtwdev, u8 fifo_sel, u32 addr, u32 size,
 static void __rtw_fw_update_pkt(struct rtw_dev *rtwdev, u8 pkt_id, u16 size,
 				u8 location)
 {
+	struct rtw_chip_info *chip = rtwdev->chip;
 	u8 h2c_pkt[H2C_PKT_SIZE] = {0};
 	u16 total_size = H2C_PKT_HDR_SIZE + H2C_PKT_UPDATE_PKT_LEN;
 
@@ -1518,6 +1521,7 @@ static void __rtw_fw_update_pkt(struct rtw_dev *rtwdev, u8 pkt_id, u16 size,
 	UPDATE_PKT_SET_LOCATION(h2c_pkt, location);
 
 	/* include txdesc size */
+	size += chip->tx_pkt_desc_sz;
 	UPDATE_PKT_SET_SIZE(h2c_pkt, size);
 
 	rtw_fw_send_h2c_packet(rtwdev, h2c_pkt);
@@ -1527,7 +1531,7 @@ void rtw_fw_update_pkt_probe_req(struct rtw_dev *rtwdev,
 				 struct cfg80211_ssid *ssid)
 {
 	u8 loc;
-	u32 size;
+	u16 size;
 
 	loc = rtw_get_rsvd_page_probe_req_location(rtwdev, ssid);
 	if (!loc) {
diff --git a/drivers/net/wireless/realtek/rtw88/fw.h b/drivers/net/wireless/realtek/rtw88/fw.h
index 08644540d259..f4aed247e3bd 100644
--- a/drivers/net/wireless/realtek/rtw88/fw.h
+++ b/drivers/net/wireless/realtek/rtw88/fw.h
@@ -117,6 +117,7 @@ struct rtw_rsvd_page {
 	u8 page;
 	bool add_txdesc;
 	struct cfg80211_ssid *ssid;
+	u16 probe_req_size;
 };
 
 enum rtw_keep_alive_pkt_type {
-- 
2.30.2

[PATCH AUTOSEL 5.10 135/176] octeontx2-pf: Fix NIX1_RX interface backpressure

[Sasha Levin]

From: Subbaraya Sundeep <sbhatta@marvell.com>

[ Upstream commit e8fb4df1f5d84bc08dd4f4827821a851d2eab241 ]

'bp_ena' in Aura context is NIX block index, setting it
zero will always backpressure NIX0 block, even if NIXLF
belongs to NIX1. Hence fix this by setting it appropriately
based on NIX block address.

Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../ethernet/marvell/octeontx2/nic/otx2_common.c  | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index df238e46e2ae..b062ed06235d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -1129,7 +1129,22 @@ static int otx2_aura_init(struct otx2_nic *pfvf, int aura_id,
 	/* Enable backpressure for RQ aura */
 	if (aura_id < pfvf->hw.rqpool_cnt) {
 		aq->aura.bp_ena = 0;
+		/* If NIX1 LF is attached then specify NIX1_RX.
+		 *
+		 * Below NPA_AURA_S[BP_ENA] is set according to the
+		 * NPA_BPINTF_E enumeration given as:
+		 * 0x0 + a*0x1 where 'a' is 0 for NIX0_RX and 1 for NIX1_RX so
+		 * NIX0_RX is 0x0 + 0*0x1 = 0
+		 * NIX1_RX is 0x0 + 1*0x1 = 1
+		 * But in HRM it is given that
+		 * "NPA_AURA_S[BP_ENA](w1[33:32]) - Enable aura backpressure to
+		 * NIX-RX based on [BP] level. One bit per NIX-RX; index
+		 * enumerated by NPA_BPINTF_E."
+		 */
+		if (pfvf->nix_blkaddr == BLKADDR_NIX1)
+			aq->aura.bp_ena = 1;
 		aq->aura.nix0_bpid = pfvf->bpid[0];
+
 		/* Set backpressure level for RQ's Aura */
 		aq->aura.bp = RQ_BP_LVL_AURA;
 	}
-- 
2.30.2

[PATCH AUTOSEL 5.10 149/176] selftests/bpf: Enlarge select() timeout for test_maps

[Sasha Levin]

From: Li Zhijian <lizhijian@cn.fujitsu.com>

[ Upstream commit 2d82d73da35b72b53fe0d96350a2b8d929d07e42 ]

0Day robot observed that it's easily timeout on a heavy load host.
-------------------
 # selftests: bpf: test_maps
 # Fork 1024 tasks to 'test_update_delete'
 # Fork 1024 tasks to 'test_update_delete'
 # Fork 100 tasks to 'test_hashmap'
 # Fork 100 tasks to 'test_hashmap_percpu'
 # Fork 100 tasks to 'test_hashmap_sizes'
 # Fork 100 tasks to 'test_hashmap_walk'
 # Fork 100 tasks to 'test_arraymap'
 # Fork 100 tasks to 'test_arraymap_percpu'
 # Failed sockmap unexpected timeout
 not ok 3 selftests: bpf: test_maps # exit=1
 # selftests: bpf: test_lru_map
 # nr_cpus:8
-------------------
Since this test will be scheduled by 0Day to a random host that could have
only a few cpus(2-8), enlarge the timeout to avoid a false NG report.

In practice, i tried to pin it to only one cpu by 'taskset 0x01 ./test_maps',
and knew 10S is likely enough, but i still perfer to a larger value 30.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20210820015556.23276-2-lizhijian@cn.fujitsu.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/test_maps.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 0d92ebcb335d..179e680e8d13 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -968,7 +968,7 @@ static void test_sockmap(unsigned int tasks, void *data)
 
 		FD_ZERO(&w);
 		FD_SET(sfd[3], &w);
-		to.tv_sec = 1;
+		to.tv_sec = 30;
 		to.tv_usec = 0;
 		s = select(sfd[3] + 1, &w, NULL, NULL, &to);
 		if (s == -1) {
-- 
2.30.2

[PATCH AUTOSEL 5.10 160/176] iwlwifi: pcie: free RBs during configure

[Sasha Levin]

From: Johannes Berg <johannes.berg@intel.com>

[ Upstream commit 6ac5720086c8b176794eb74c5cc09f8b79017f38 ]

When switching op-modes, or more generally when reconfiguring,
we might switch the RB size. In _iwl_pcie_rx_init() we have a
comment saying we must free all RBs since we might switch the
size, but this is actually too late: the switch has been done
and we'll free the buffers with the wrong size.

Fix this by always freeing the buffers, if any, at the start
of configure, instead of only after the size may have changed.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20210802170640.42d7c93279c4.I07f74e65aab0e3d965a81206fcb289dc92d74878@changeid
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/intel/iwlwifi/pcie/rx.c    | 5 ++++-
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 3 +++
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 94299f259518..2c13fa8f2820 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -544,6 +544,9 @@ void iwl_pcie_free_rbs_pool(struct iwl_trans *trans)
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int i;
 
+	if (!trans_pcie->rx_pool)
+		return;
+
 	for (i = 0; i < RX_POOL_SIZE(trans_pcie->num_rx_bufs); i++) {
 		if (!trans_pcie->rx_pool[i].page)
 			continue;
@@ -1094,7 +1097,7 @@ static int _iwl_pcie_rx_init(struct iwl_trans *trans)
 	INIT_LIST_HEAD(&rba->rbd_empty);
 	spin_unlock(&rba->lock);
 
-	/* free all first - we might be reconfigured for a different size */
+	/* free all first - we overwrite everything here */
 	iwl_pcie_free_rbs_pool(trans);
 
 	for (i = 0; i < RX_QUEUE_SIZE; i++)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index bb990be7c870..082768ec8aa8 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -1909,6 +1909,9 @@ static void iwl_trans_pcie_configure(struct iwl_trans *trans,
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
+	/* free all first - we might be reconfigured for a different size */
+	iwl_pcie_free_rbs_pool(trans);
+
 	trans->txqs.cmd.q_id = trans_cfg->cmd_queue;
 	trans->txqs.cmd.fifo = trans_cfg->cmd_fifo;
 	trans->txqs.cmd.wdg_timeout = trans_cfg->cmd_q_wdg_timeout;
-- 
2.30.2

[PATCH AUTOSEL 5.10 161/176] iwlwifi: mvm: fix a memory leak in iwl_mvm_mac_ctxt_beacon_changed

[Sasha Levin]

From: Zhang Qilong <zhangqilong3@huawei.com>

[ Upstream commit 0f5d44ac6e55551798dd3da0ff847c8df5990822 ]

If beacon_inject_active is true, we will return without freeing
beacon.  Fid that by freeing it before returning.

Signed-off-by: Zhang Qilong <zhangqilong3@huawei.com>
[reworded the commit message]
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20210802172232.d16206ca60fc.I9984a9b442c84814c307cee3213044e24d26f38a@changeid
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index cbdebefb854a..6f5951aed8a7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -1044,8 +1044,10 @@ int iwl_mvm_mac_ctxt_beacon_changed(struct iwl_mvm *mvm,
 		return -ENOMEM;
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
-	if (mvm->beacon_inject_active)
+	if (mvm->beacon_inject_active) {
+		dev_kfree_skb(beacon);
 		return -EBUSY;
+	}
 #endif
 
 	ret = iwl_mvm_mac_ctxt_send_beacon(mvm, vif, beacon);
-- 
2.30.2

[PATCH AUTOSEL 5.10 162/176] iwlwifi: mvm: avoid static queue number aliasing

[Sasha Levin]

From: Johannes Berg <johannes.berg@intel.com>

[ Upstream commit c6ce1c74ef2923b8ffd85f7f8b486f804f343b39 ]

When TVQM is enabled (iwl_mvm_has_new_tx_api() is true), then
queue numbers are just sequentially assigned 0, 1, 2, ...
Prior to TVQM, in DQA, there were some statically allocated
queue numbers:
 * IWL_MVM_DQA_AUX_QUEUE == 1,
 * both IWL_MVM_DQA_INJECT_MONITOR_QUEUE and
   IWL_MVM_DQA_P2P_DEVICE_QUEUE == 2, and
 * IWL_MVM_DQA_AP_PROBE_RESP_QUEUE == 9.

Now, these values are assigned to the members mvm->aux_queue,
mvm->snif_queue, mvm->probe_queue and mvm->p2p_dev_queue by
default. Normally, this doesn't really matter, and if TVQM is
in fact available we override them to the real values after
allocating a queue for use there.

However, this allocation doesn't always happen. For example,
for mvm->p2p_dev_queue (== 2) it only happens when the P2P
Device interface is started, if any. If it's not started, the
value in mvm->p2p_dev_queue remains 2. This wouldn't really
matter all that much if it weren't for iwl_mvm_is_static_queue()
which checks a queue number against one of those four static
numbers.

Now, if no P2P Device or monitor interface is added then queue
2 may be dynamically allocated, yet alias mvm->p2p_dev_queue or
mvm->snif_queue, and thus iwl_mvm_is_static_queue() erroneously
returns true for it. If it then gets full, all interface queues
are stopped, instead of just backpressuring against the one TXQ
that's really the only affected one.

This clearly can lead to issues, as everything is stopped even
if just a single TXQ filled its corresponding HW queue, if it
happens to have an appropriate number (2 or 9, AUX is always
reassigned.) Due to a mac80211 bug, this also led to a situation
in which the queues remained stopped across a deauthentication
and then attempts to connect to a new AP started failing, but
that's fixed separately.

Fix all of this by simply initializing the queue numbers to
the invalid value until they're used, if TVQM is enabled, and
also setting them back to that value when the queues are later
freed again.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20210802172232.2e47e623f9e2.I9b0830dafbb68ef35b7b8f0f46160abec02ac7d0@changeid
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 24 +++++++++++++---
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 30 ++++++++++++--------
 2 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index cb83490f1016..0be8ff30b13e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -678,10 +678,26 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 
 	mvm->fw_restart = iwlwifi_mod_params.fw_restart ? -1 : 0;
 
-	mvm->aux_queue = IWL_MVM_DQA_AUX_QUEUE;
-	mvm->snif_queue = IWL_MVM_DQA_INJECT_MONITOR_QUEUE;
-	mvm->probe_queue = IWL_MVM_DQA_AP_PROBE_RESP_QUEUE;
-	mvm->p2p_dev_queue = IWL_MVM_DQA_P2P_DEVICE_QUEUE;
+	if (iwl_mvm_has_new_tx_api(mvm)) {
+		/*
+		 * If we have the new TX/queue allocation API initialize them
+		 * all to invalid numbers. We'll rewrite the ones that we need
+		 * later, but that doesn't happen for all of them all of the
+		 * time (e.g. P2P Device is optional), and if a dynamic queue
+		 * ends up getting number 2 (IWL_MVM_DQA_P2P_DEVICE_QUEUE) then
+		 * iwl_mvm_is_static_queue() erroneously returns true, and we
+		 * might have things getting stuck.
+		 */
+		mvm->aux_queue = IWL_MVM_INVALID_QUEUE;
+		mvm->snif_queue = IWL_MVM_INVALID_QUEUE;
+		mvm->probe_queue = IWL_MVM_INVALID_QUEUE;
+		mvm->p2p_dev_queue = IWL_MVM_INVALID_QUEUE;
+	} else {
+		mvm->aux_queue = IWL_MVM_DQA_AUX_QUEUE;
+		mvm->snif_queue = IWL_MVM_DQA_INJECT_MONITOR_QUEUE;
+		mvm->probe_queue = IWL_MVM_DQA_AP_PROBE_RESP_QUEUE;
+		mvm->p2p_dev_queue = IWL_MVM_DQA_P2P_DEVICE_QUEUE;
+	}
 
 	mvm->sf_state = SF_UNINIT;
 	if (iwl_mvm_has_unified_ucode(mvm))
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index a66a5c19474a..ef62839894c7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -362,8 +362,9 @@ static int iwl_mvm_invalidate_sta_queue(struct iwl_mvm *mvm, int queue,
 }
 
 static int iwl_mvm_disable_txq(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
-			       int queue, u8 tid, u8 flags)
+			       u16 *queueptr, u8 tid, u8 flags)
 {
+	int queue = *queueptr;
 	struct iwl_scd_txq_cfg_cmd cmd = {
 		.scd_queue = queue,
 		.action = SCD_CFG_DISABLE_QUEUE,
@@ -372,6 +373,7 @@ static int iwl_mvm_disable_txq(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 
 	if (iwl_mvm_has_new_tx_api(mvm)) {
 		iwl_trans_txq_free(mvm->trans, queue);
+		*queueptr = IWL_MVM_INVALID_QUEUE;
 
 		return 0;
 	}
@@ -533,6 +535,7 @@ static int iwl_mvm_free_inactive_queue(struct iwl_mvm *mvm, int queue,
 	u8 sta_id, tid;
 	unsigned long disable_agg_tids = 0;
 	bool same_sta;
+	u16 queue_tmp = queue;
 	int ret;
 
 	lockdep_assert_held(&mvm->mutex);
@@ -555,7 +558,7 @@ static int iwl_mvm_free_inactive_queue(struct iwl_mvm *mvm, int queue,
 		iwl_mvm_invalidate_sta_queue(mvm, queue,
 					     disable_agg_tids, false);
 
-	ret = iwl_mvm_disable_txq(mvm, old_sta, queue, tid, 0);
+	ret = iwl_mvm_disable_txq(mvm, old_sta, &queue_tmp, tid, 0);
 	if (ret) {
 		IWL_ERR(mvm,
 			"Failed to free inactive queue %d (ret=%d)\n",
@@ -1230,6 +1233,7 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 	unsigned int wdg_timeout =
 		iwl_mvm_get_wd_timeout(mvm, mvmsta->vif, false, false);
 	int queue = -1;
+	u16 queue_tmp;
 	unsigned long disable_agg_tids = 0;
 	enum iwl_mvm_agg_state queue_state;
 	bool shared_queue = false, inc_ssn;
@@ -1378,7 +1382,8 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 	return 0;
 
 out_err:
-	iwl_mvm_disable_txq(mvm, sta, queue, tid, 0);
+	queue_tmp = queue;
+	iwl_mvm_disable_txq(mvm, sta, &queue_tmp, tid, 0);
 
 	return ret;
 }
@@ -1825,7 +1830,7 @@ static void iwl_mvm_disable_sta_queues(struct iwl_mvm *mvm,
 		if (mvm_sta->tid_data[i].txq_id == IWL_MVM_INVALID_QUEUE)
 			continue;
 
-		iwl_mvm_disable_txq(mvm, sta, mvm_sta->tid_data[i].txq_id, i,
+		iwl_mvm_disable_txq(mvm, sta, &mvm_sta->tid_data[i].txq_id, i,
 				    0);
 		mvm_sta->tid_data[i].txq_id = IWL_MVM_INVALID_QUEUE;
 	}
@@ -2033,7 +2038,7 @@ static int iwl_mvm_add_int_sta_with_queue(struct iwl_mvm *mvm, int macidx,
 	ret = iwl_mvm_add_int_sta_common(mvm, sta, addr, macidx, maccolor);
 	if (ret) {
 		if (!iwl_mvm_has_new_tx_api(mvm))
-			iwl_mvm_disable_txq(mvm, NULL, *queue,
+			iwl_mvm_disable_txq(mvm, NULL, queue,
 					    IWL_MAX_TID_COUNT, 0);
 		return ret;
 	}
@@ -2106,7 +2111,7 @@ int iwl_mvm_rm_snif_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 	if (WARN_ON_ONCE(mvm->snif_sta.sta_id == IWL_MVM_INVALID_STA))
 		return -EINVAL;
 
-	iwl_mvm_disable_txq(mvm, NULL, mvm->snif_queue, IWL_MAX_TID_COUNT, 0);
+	iwl_mvm_disable_txq(mvm, NULL, &mvm->snif_queue, IWL_MAX_TID_COUNT, 0);
 	ret = iwl_mvm_rm_sta_common(mvm, mvm->snif_sta.sta_id);
 	if (ret)
 		IWL_WARN(mvm, "Failed sending remove station\n");
@@ -2123,7 +2128,7 @@ int iwl_mvm_rm_aux_sta(struct iwl_mvm *mvm)
 	if (WARN_ON_ONCE(mvm->aux_sta.sta_id == IWL_MVM_INVALID_STA))
 		return -EINVAL;
 
-	iwl_mvm_disable_txq(mvm, NULL, mvm->aux_queue, IWL_MAX_TID_COUNT, 0);
+	iwl_mvm_disable_txq(mvm, NULL, &mvm->aux_queue, IWL_MAX_TID_COUNT, 0);
 	ret = iwl_mvm_rm_sta_common(mvm, mvm->aux_sta.sta_id);
 	if (ret)
 		IWL_WARN(mvm, "Failed sending remove station\n");
@@ -2219,7 +2224,7 @@ static void iwl_mvm_free_bcast_sta_queues(struct iwl_mvm *mvm,
 					  struct ieee80211_vif *vif)
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-	int queue;
+	u16 *queueptr, queue;
 
 	lockdep_assert_held(&mvm->mutex);
 
@@ -2228,10 +2233,10 @@ static void iwl_mvm_free_bcast_sta_queues(struct iwl_mvm *mvm,
 	switch (vif->type) {
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_ADHOC:
-		queue = mvm->probe_queue;
+		queueptr = &mvm->probe_queue;
 		break;
 	case NL80211_IFTYPE_P2P_DEVICE:
-		queue = mvm->p2p_dev_queue;
+		queueptr = &mvm->p2p_dev_queue;
 		break;
 	default:
 		WARN(1, "Can't free bcast queue on vif type %d\n",
@@ -2239,7 +2244,8 @@ static void iwl_mvm_free_bcast_sta_queues(struct iwl_mvm *mvm,
 		return;
 	}
 
-	iwl_mvm_disable_txq(mvm, NULL, queue, IWL_MAX_TID_COUNT, 0);
+	queue = *queueptr;
+	iwl_mvm_disable_txq(mvm, NULL, queueptr, IWL_MAX_TID_COUNT, 0);
 	if (iwl_mvm_has_new_tx_api(mvm))
 		return;
 
@@ -2474,7 +2480,7 @@ int iwl_mvm_rm_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 
 	iwl_mvm_flush_sta(mvm, &mvmvif->mcast_sta, true);
 
-	iwl_mvm_disable_txq(mvm, NULL, mvmvif->cab_queue, 0, 0);
+	iwl_mvm_disable_txq(mvm, NULL, &mvmvif->cab_queue, 0, 0);
 
 	ret = iwl_mvm_rm_sta_common(mvm, mvmvif->mcast_sta.sta_id);
 	if (ret)
-- 
2.30.2

[PATCH AUTOSEL 5.10 163/176] iwlwifi: mvm: fix access to BSS elements

[Sasha Levin]

From: Johannes Berg <johannes.berg@intel.com>

[ Upstream commit 6c608cd6962ebdf84fd3de6d42f88ed64d2f4e1b ]

BSS elements are protected using RCU, so we need to use
RCU properly to access them, fix that.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20210805130823.fd8b5791ab44.Iba26800a6301078d3782fb249c476dd8ac2bf3c6@changeid
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 8cba923b1ec6..d2af6909fcc8 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -3028,16 +3028,20 @@ static void iwl_mvm_check_he_obss_narrow_bw_ru_iter(struct wiphy *wiphy,
 						    void *_data)
 {
 	struct iwl_mvm_he_obss_narrow_bw_ru_data *data = _data;
+	const struct cfg80211_bss_ies *ies;
 	const struct element *elem;
 
-	elem = cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, bss->ies->data,
-				  bss->ies->len);
+	rcu_read_lock();
+	ies = rcu_dereference(bss->ies);
+	elem = cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, ies->data,
+				  ies->len);
 
 	if (!elem || elem->datalen < 10 ||
 	    !(elem->data[10] &
 	      WLAN_EXT_CAPA10_OBSS_NARROW_BW_RU_TOLERANCE_SUPPORT)) {
 		data->tolerated = false;
 	}
+	rcu_read_unlock();
 }
 
 static void iwl_mvm_check_he_obss_narrow_bw_ru(struct ieee80211_hw *hw,
-- 
2.30.2

[PATCH AUTOSEL 5.10 164/176] iwlwifi: fw: correctly limit to monitor dump

[Sasha Levin]

From: Johannes Berg <johannes.berg@intel.com>

[ Upstream commit e6344c060209ef4e970cac18adeac1676a2a73cd ]

In commit 79f033f6f229 ("iwlwifi: dbg: don't limit dump decisions
to all or monitor") we changed the code to pass around a bitmap,
but in the monitor_only case, one place accidentally used the bit
number, not the bit mask, resulting in CSR and FW_INFO getting
dumped instead of monitor data. Fix that.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20210805141826.774fd8729a33.Ic985a787071d1c0b127ef0ba8367da896ee11f57@changeid
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index ab4a8b942c81..419eaa5cf0b5 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -2303,7 +2303,7 @@ static void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt,
 		return;
 
 	if (dump_data->monitor_only)
-		dump_mask &= IWL_FW_ERROR_DUMP_FW_MONITOR;
+		dump_mask &= BIT(IWL_FW_ERROR_DUMP_FW_MONITOR);
 
 	fw_error_dump.trans_ptr = iwl_trans_dump_data(fwrt->trans, dump_mask);
 	file_len = le32_to_cpu(dump_file->file_len);
-- 
2.30.2

[PATCH AUTOSEL 5.10 165/176] iwlwifi: mvm: Fix scan channel flags settings

[Sasha Levin]

From: Ilan Peer <ilan.peer@intel.com>

[ Upstream commit 090f1be3abf3069ef856b29761f181808bf55917 ]

The iwl_mvm_scan_ch_n_aps_flag() is called with a variable
before the value of the variable is set. Fix it.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20210826224715.f6f188980a5e.Ie7331a8b94004d308f6cbde44e519155a5be91dd@changeid
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 875281cf7fc0..f2f23f8bfd70 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1682,7 +1682,7 @@ iwl_mvm_umac_scan_cfg_channels_v6(struct iwl_mvm *mvm,
 		struct iwl_scan_channel_cfg_umac *cfg = &cp->channel_config[i];
 		u32 n_aps_flag =
 			iwl_mvm_scan_ch_n_aps_flag(vif_type,
-						   cfg->v2.channel_num);
+						   channels[i]->hw_value);
 
 		cfg->flags = cpu_to_le32(flags | n_aps_flag);
 		cfg->v2.channel_num = channels[i]->hw_value;
-- 
2.30.2

[PATCH AUTOSEL 5.10 166/176] net/mlx5: DR, fix a potential use-after-free bug

[Sasha Levin]

From: Wentao_Liang <Wentao_Liang_g@163.com>

[ Upstream commit 6cc64770fb386b10a64a1fe09328396de7bb5262 ]

In line 849 (#1), "mlx5dr_htbl_put(cur_htbl);" drops the reference to
cur_htbl and may cause cur_htbl to be freed.

However, cur_htbl is subsequently used in the next line, which may result
in an use-after-free bug.

Fix this by calling mlx5dr_err() before the cur_htbl is put.

Signed-off-by: Wentao_Liang <Wentao_Liang_g@163.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index b3c9dc032026..478de5ded7c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -824,9 +824,9 @@ dr_rule_handle_ste_branch(struct mlx5dr_rule *rule,
 			new_htbl = dr_rule_rehash(rule, nic_rule, cur_htbl,
 						  ste_location, send_ste_list);
 			if (!new_htbl) {
-				mlx5dr_htbl_put(cur_htbl);
 				mlx5dr_err(dmn, "Failed creating rehash table, htbl-log_size: %d\n",
 					   cur_htbl->chunk_size);
+				mlx5dr_htbl_put(cur_htbl);
 			} else {
 				cur_htbl = new_htbl;
 			}
-- 
2.30.2

[PATCH AUTOSEL 5.10 167/176] net/mlx5: DR, Enable QP retransmission

[Sasha Levin]

From: Yevgeny Kliteynik <kliteyn@nvidia.com>

[ Upstream commit ec449ed8230cd30769de3cb70ee0fce293047372 ]

Under high stress, SW steering might get stuck on polling for completion
that never comes.
For such cases QP needs to have protocol retransmission mechanism enabled.
Currently the retransmission timeout is defined as 0 (unlimited). Fix this
by defining a real timeout.

Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index ea3c6cf27db4..eb6677f737a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -605,6 +605,7 @@ static int dr_cmd_modify_qp_rtr2rts(struct mlx5_core_dev *mdev,
 
 	MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt);
 	MLX5_SET(qpc, qpc, rnr_retry, attr->rnr_retry);
+	MLX5_SET(qpc, qpc, primary_address_path.ack_timeout, 0x8); /* ~1ms */
 
 	MLX5_SET(rtr2rts_qp_in, in, opcode, MLX5_CMD_OP_RTR2RTS_QP);
 	MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->qpn);
-- 
2.30.2

[PATCH AUTOSEL 5.10 169/176] selftests/bpf: Fix potential unreleased lock

[Sasha Levin]

From: Chengfeng Ye <cyeaa@connect.ust.hk>

[ Upstream commit 47bb27a20d6ea22cd092c1fc2bb4fcecac374838 ]

This lock is not released if the program
return at the patched branch.

Signed-off-by: Chengfeng Ye <cyeaa@connect.ust.hk>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210827074140.118671-1-cyeaa@connect.ust.hk
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
index ec281b0363b8..86f97681ad89 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
@@ -195,8 +195,10 @@ static void run_test(int cgroup_fd)
 
 	pthread_mutex_lock(&server_started_mtx);
 	if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread,
-				      (void *)&server_fd)))
+				      (void *)&server_fd))) {
+		pthread_mutex_unlock(&server_started_mtx);
 		goto close_server_fd;
+	}
 	pthread_cond_wait(&server_started, &server_started_mtx);
 	pthread_mutex_unlock(&server_started_mtx);
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 170/176] wcn36xx: Fix missing frame timestamp for beacon/probe-resp

[Sasha Levin]

From: Loic Poulain <loic.poulain@linaro.org>

[ Upstream commit 8678fd31f2d3eb14f2b8b39c9bc266f16fa24b22 ]

When receiving a beacon or probe response, we should update the
boottime_ns field which is the timestamp the frame was received at.
(cf mac80211.h)

This fixes a scanning issue with Android since it relies on this
timestamp to determine when the AP has been seen for the last time
(via the nl80211 BSS_LAST_SEEN_BOOTTIME parameter).

Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Reviewed-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/1629992768-23785-1-git-send-email-loic.poulain@linaro.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/ath/wcn36xx/txrx.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/ath/wcn36xx/txrx.c b/drivers/net/wireless/ath/wcn36xx/txrx.c
index 1b831157ede1..cab196bb38cd 100644
--- a/drivers/net/wireless/ath/wcn36xx/txrx.c
+++ b/drivers/net/wireless/ath/wcn36xx/txrx.c
@@ -287,6 +287,10 @@ int wcn36xx_rx_skb(struct wcn36xx *wcn, struct sk_buff *skb)
 		status.rate_idx = 0;
 	}
 
+	if (ieee80211_is_beacon(hdr->frame_control) ||
+	    ieee80211_is_probe_resp(hdr->frame_control))
+		status.boottime_ns = ktime_get_boottime_ns();
+
 	memcpy(IEEE80211_SKB_RXCB(skb), &status, sizeof(status));
 
 	if (ieee80211_is_beacon(hdr->frame_control)) {
-- 
2.30.2

[PATCH AUTOSEL 5.10 171/176] ath9k: fix OOB read ar9300_eeprom_restore_internal

[Sasha Levin]

From: Zekun Shen <bruceshenzk@gmail.com>

[ Upstream commit 23151b9ae79e3bc4f6a0c4cd3a7f355f68dad128 ]

Bad header can have large length field which can cause OOB.
cptr is the last bytes for read, and the eeprom is parsed
from high to low address. The OOB, triggered by the condition
length > cptr could cause memory error with a read on
negative index.

There are some sanity check around length, but it is not
compared with cptr (the remaining bytes). Here, the
corrupted/bad EEPROM can cause panic.

I was able to reproduce the crash, but I cannot find the
log and the reproducer now. After I applied the patch, the
bug is no longer reproducible.

Signed-off-by: Zekun Shen <bruceshenzk@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/YM3xKsQJ0Hw2hjrc@Zekuns-MBP-16.fios-router.home
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/ath/ath9k/ar9003_eeprom.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
index b4885a700296..b0a4ca3559fd 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
@@ -3351,7 +3351,8 @@ static int ar9300_eeprom_restore_internal(struct ath_hw *ah,
 			"Found block at %x: code=%d ref=%d length=%d major=%d minor=%d\n",
 			cptr, code, reference, length, major, minor);
 		if ((!AR_SREV_9485(ah) && length >= 1024) ||
-		    (AR_SREV_9485(ah) && length > EEPROM_DATA_LEN_9485)) {
+		    (AR_SREV_9485(ah) && length > EEPROM_DATA_LEN_9485) ||
+		    (length > cptr)) {
 			ath_dbg(common, EEPROM, "Skipping bad header\n");
 			cptr -= COMP_HDR_LEN;
 			continue;
-- 
2.30.2

[PATCH AUTOSEL 5.10 172/176] ath9k: fix sleeping in atomic context

[Sasha Levin]

From: Miaoqing Pan <miaoqing@codeaurora.org>

[ Upstream commit 7c48662b9d56666219f526a71ace8c15e6e12f1f ]

The problem is that gpio_free() can sleep and the cfg_soc() can be
called with spinlocks held. One problematic call tree is:

--> ath_reset_internal() takes &sc->sc_pcu_lock spin lock
   --> ath9k_hw_reset()
      --> ath9k_hw_gpio_request_in()
         --> ath9k_hw_gpio_request()
            --> ath9k_hw_gpio_cfg_soc()

Remove gpio_free(), use error message instead, so we should make sure
there is no GPIO conflict.

Also remove ath9k_hw_gpio_free() from ath9k_hw_apply_gpio_override(),
as gpio_mask will never be set for SOC chips.

Signed-off-by: Miaoqing Pan <miaoqing@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/1628481916-15030-1-git-send-email-miaoqing@codeaurora.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/ath/ath9k/hw.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index c86faebbc459..6b2668f065d5 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -1622,7 +1622,6 @@ static void ath9k_hw_apply_gpio_override(struct ath_hw *ah)
 		ath9k_hw_gpio_request_out(ah, i, NULL,
 					  AR_GPIO_OUTPUT_MUX_AS_OUTPUT);
 		ath9k_hw_set_gpio(ah, i, !!(ah->gpio_val & BIT(i)));
-		ath9k_hw_gpio_free(ah, i);
 	}
 }
 
@@ -2730,14 +2729,17 @@ static void ath9k_hw_gpio_cfg_output_mux(struct ath_hw *ah, u32 gpio, u32 type)
 static void ath9k_hw_gpio_cfg_soc(struct ath_hw *ah, u32 gpio, bool out,
 				  const char *label)
 {
+	int err;
+
 	if (ah->caps.gpio_requested & BIT(gpio))
 		return;
 
-	/* may be requested by BSP, free anyway */
-	gpio_free(gpio);
-
-	if (gpio_request_one(gpio, out ? GPIOF_OUT_INIT_LOW : GPIOF_IN, label))
+	err = gpio_request_one(gpio, out ? GPIOF_OUT_INIT_LOW : GPIOF_IN, label);
+	if (err) {
+		ath_err(ath9k_hw_common(ah), "request GPIO%d failed:%d\n",
+			gpio, err);
 		return;
+	}
 
 	ah->caps.gpio_requested |= BIT(gpio);
 }
-- 
2.30.2

[PATCH AUTOSEL 5.10 173/176] net: fix NULL pointer reference in cipso_v4_doi_free

[Sasha Levin]

From: 王贇 <yun.wang@linux.alibaba.com>

[ Upstream commit 733c99ee8be9a1410287cdbb943887365e83b2d6 ]

In netlbl_cipsov4_add_std() when 'doi_def->map.std' alloc
failed, we sometime observe panic:

  BUG: kernel NULL pointer dereference, address:
  ...
  RIP: 0010:cipso_v4_doi_free+0x3a/0x80
  ...
  Call Trace:
   netlbl_cipsov4_add_std+0xf4/0x8c0
   netlbl_cipsov4_add+0x13f/0x1b0
   genl_family_rcv_msg_doit.isra.15+0x132/0x170
   genl_rcv_msg+0x125/0x240

This is because in cipso_v4_doi_free() there is no check
on 'doi_def->map.std' when 'doi_def->type' equal 1, which
is possibe, since netlbl_cipsov4_add_std() haven't initialize
it before alloc 'doi_def->map.std'.

This patch just add the check to prevent panic happen for similar
cases.

Reported-by: Abaci <abaci@linux.alibaba.com>
Signed-off-by: Michael Wang <yun.wang@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netlabel/netlabel_cipso_v4.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index 4f50a64315cf..e34ab5b227f3 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -144,8 +144,8 @@ static int netlbl_cipsov4_add_std(struct genl_info *info,
 		return -ENOMEM;
 	doi_def->map.std = kzalloc(sizeof(*doi_def->map.std), GFP_KERNEL);
 	if (doi_def->map.std == NULL) {
-		ret_val = -ENOMEM;
-		goto add_std_failure;
+		kfree(doi_def);
+		return -ENOMEM;
 	}
 	doi_def->type = CIPSO_V4_MAP_TRANS;
 
-- 
2.30.2

[PATCH AUTOSEL 5.10 174/176] fix array-index-out-of-bounds in taprio_change

[Sasha Levin]

From: Haimin Zhang <tcs_kernel@tencent.com>

[ Upstream commit efe487fce3061d94222c6501d7be3aa549b3dc78 ]

syzbot report an array-index-out-of-bounds in taprio_change
index 16 is out of range for type '__u16 [16]'
that's because mqprio->num_tc is lager than TC_MAX_QUEUE,so we check
the return value of netdev_set_num_tc.

Reported-by: syzbot+2b3e5fb6c7ef285a94f6@syzkaller.appspotmail.com
Signed-off-by: Haimin Zhang <tcs_kernel@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sched/sch_taprio.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 00853065dfa0..cb5e5220da55 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1502,7 +1502,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	taprio_set_picos_per_byte(dev, q);
 
 	if (mqprio) {
-		netdev_set_num_tc(dev, mqprio->num_tc);
+		err = netdev_set_num_tc(dev, mqprio->num_tc);
+		if (err)
+			goto free_sched;
 		for (i = 0; i < mqprio->num_tc; i++)
 			netdev_set_tc_queue(dev, i,
 					    mqprio->count[i],
-- 
2.30.2

[PATCH AUTOSEL 5.10 175/176] net: w5100: check return value after calling platform_get_resource()

[Sasha Levin]

From: Yang Yingliang <yangyingliang@huawei.com>

[ Upstream commit a39ff4a47f3e1da3b036817ef436b1a9be10783a ]

It will cause null-ptr-deref if platform_get_resource() returns NULL,
we need check the return value.

Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/wiznet/w5100.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
index c0d181a7f83a..0b7135a3c585 100644
--- a/drivers/net/ethernet/wiznet/w5100.c
+++ b/drivers/net/ethernet/wiznet/w5100.c
@@ -1052,6 +1052,8 @@ static int w5100_mmio_probe(struct platform_device *pdev)
 		mac_addr = data->mac_addr;
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!mem)
+		return -EINVAL;
 	if (resource_size(mem) < W5100_BUS_DIRECT_SIZE)
 		ops = &w5100_mmio_indirect_ops;
 	else
-- 
2.30.2

[PATCH AUTOSEL 5.10 176/176] net: hns3: clean up a type mismatch warning

[Sasha Levin]

From: Guojia Liao <liaoguojia@huawei.com>

[ Upstream commit e79c0e324b011b0288cd411a5b53870a7730f163 ]

abs() returns signed long, which could not convert the type
as unsigned, and it may cause a mismatch type warning from
static tools. To fix it, this patch uses an variable to save
the abs()'s result and does a explicit conversion.

Signed-off-by: Guojia Liao <liaoguojia@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@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_mbx.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index 61f6f0287cbe..ff9d84a7147f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -10,7 +10,14 @@
 
 static u16 hclge_errno_to_resp(int errno)
 {
-	return abs(errno);
+	int resp = abs(errno);
+
+	/* The status for pf to vf msg cmd is u16, constrainted by HW.
+	 * We need to keep the same type with it.
+	 * The intput errno is the stander error code, it's safely to
+	 * use a u16 to store the abs(errno).
+	 */
+	return (u16)resp;
 }
 
 /* hclge_gen_resp_to_vf: used to generate a synchronous response to VF when PF
-- 
2.30.2