From 25af7406df5915f04d5f1c8f081dabb0ead1cdcc Mon Sep 17 00:00:00 2001
From: Isaac Manjarres <isaacmanjarres@google.com>
Date: Thu, 18 Aug 2022 18:28:51 +0100
Subject: ARM: 9229/1: amba: Fix use-after-free in amba_read_periphid()

After commit f2d3b9a46e0e ("ARM: 9220/1: amba: Remove deferred device
addition"), it became possible for amba_read_periphid() to be invoked
concurrently from two threads for a particular AMBA device.

Consider the case where a thread (T0) is registering an AMBA driver, and
searching for all of the devices it can match with on the AMBA bus.
Suppose that another thread (T1) is executing the deferred probe work,
and is searching through all of the AMBA drivers on the bus for a driver
that matches a particular AMBA device. Assume that both threads begin
operating on the same AMBA device and the device's peripheral ID is
still unknown.

In this scenario, the amba_match() function will be invoked for the
same AMBA device by both threads, which means amba_read_periphid()
can also be invoked by both threads, and both threads will be able
to manipulate the AMBA device's pclk pointer without any synchronization.
It's possible that one thread will initialize the pclk pointer, then the
other thread will re-initialize it, overwriting the previous value, and
both will race to free the same pclk, resulting in a use-after-free for
whichever thread frees the pclk last.

Add a lock per AMBA device to synchronize the handling with detecting the
peripheral ID to avoid the use-after-free scenario.

The following KFENCE bug report helped detect this problem:
==================================================================
BUG: KFENCE: use-after-free read in clk_disable+0x14/0x34

Use-after-free read at 0x(ptrval) (in kfence-#19):
 clk_disable+0x14/0x34
 amba_read_periphid+0xdc/0x134
 amba_match+0x3c/0x84
 __driver_attach+0x20/0x158
 bus_for_each_dev+0x74/0xc0
 bus_add_driver+0x154/0x1e8
 driver_register+0x88/0x11c
 do_one_initcall+0x8c/0x2fc
 kernel_init_freeable+0x190/0x220
 kernel_init+0x10/0x108
 ret_from_fork+0x14/0x3c
 0x0

kfence-#19: 0x(ptrval)-0x(ptrval), size=36, cache=kmalloc-64

allocated by task 8 on cpu 0 at 11.629931s:
 clk_hw_create_clk+0x38/0x134
 amba_get_enable_pclk+0x10/0x68
 amba_read_periphid+0x28/0x134
 amba_match+0x3c/0x84
 __device_attach_driver+0x2c/0xc4
 bus_for_each_drv+0x80/0xd0
 __device_attach+0xb0/0x1f0
 bus_probe_device+0x88/0x90
 deferred_probe_work_func+0x8c/0xc0
 process_one_work+0x23c/0x690
 worker_thread+0x34/0x488
 kthread+0xd4/0xfc
 ret_from_fork+0x14/0x3c
 0x0

freed by task 8 on cpu 0 at 11.630095s:
 amba_read_periphid+0xec/0x134
 amba_match+0x3c/0x84
 __device_attach_driver+0x2c/0xc4
 bus_for_each_drv+0x80/0xd0
 __device_attach+0xb0/0x1f0
 bus_probe_device+0x88/0x90
 deferred_probe_work_func+0x8c/0xc0
 process_one_work+0x23c/0x690
 worker_thread+0x34/0x488
 kthread+0xd4/0xfc
 ret_from_fork+0x14/0x3c
 0x0

Cc: Saravana Kannan <saravanak@google.com>
Cc: patches@armlinux.org.uk
Fixes: f2d3b9a46e0e ("ARM: 9220/1: amba: Remove deferred device addition")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Isaac J. Manjarres <isaacmanjarres@google.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
---
 include/linux/amba/bus.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index e94cdf235f1d..5001e14c5c06 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -67,6 +67,7 @@ struct amba_device {
 	struct clk		*pclk;
 	struct device_dma_parameters dma_parms;
 	unsigned int		periphid;
+	struct mutex		periphid_lock;
 	unsigned int		cid;
 	struct amba_cs_uci_id	uci;
 	unsigned int		irq[AMBA_NR_IRQS];
-- 
cgit v1.2.3


From ac56a0b48da86fd1b4389632fb7c4c8a5d86eefa Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 26 Aug 2022 15:39:28 +0100
Subject: rxrpc: Fix ICMP/ICMP6 error handling

Because rxrpc pretends to be a tunnel on top of a UDP/UDP6 socket, allowing
it to siphon off UDP packets early in the handling of received UDP packets
thereby avoiding the packet going through the UDP receive queue, it doesn't
get ICMP packets through the UDP ->sk_error_report() callback.  In fact, it
doesn't appear that there's any usable option for getting hold of ICMP
packets.

Fix this by adding a new UDP encap hook to distribute error messages for
UDP tunnels.  If the hook is set, then the tunnel driver will be able to
see ICMP packets.  The hook provides the offset into the packet of the UDP
header of the original packet that caused the notification.

An alternative would be to call the ->error_handler() hook - but that
requires that the skbuff be cloned (as ip_icmp_error() or ipv6_cmp_error()
do, though isn't really necessary or desirable in rxrpc's case is we want
to parse them there and then, not queue them).

Changes
=======
ver #3)
 - Fixed an uninitialised variable.

ver #2)
 - Fixed some missing CONFIG_AF_RXRPC_IPV6 conditionals.

Fixes: 5271953cad31 ("rxrpc: Use the UDP encap_rcv hook")
Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/linux/udp.h        |   1 +
 include/net/udp_tunnel.h   |   4 +
 net/ipv4/udp.c             |   2 +
 net/ipv4/udp_tunnel_core.c |   1 +
 net/ipv6/udp.c             |   5 +-
 net/rxrpc/ar-internal.h    |   1 +
 net/rxrpc/local_object.c   |   1 +
 net/rxrpc/peer_event.c     | 293 +++++++++++++++++++++++++++++++++++++++------
 8 files changed, 270 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/udp.h b/include/linux/udp.h
index 254a2654400f..e96da4157d04 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -70,6 +70,7 @@ struct udp_sock {
 	 * For encapsulation sockets.
 	 */
 	int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
+	void (*encap_err_rcv)(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset);
 	int (*encap_err_lookup)(struct sock *sk, struct sk_buff *skb);
 	void (*encap_destroy)(struct sock *sk);
 
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index afc7ce713657..72394f441dad 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -67,6 +67,9 @@ static inline int udp_sock_create(struct net *net,
 typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
 typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk,
 					     struct sk_buff *skb);
+typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk,
+					   struct sk_buff *skb,
+					   unsigned int udp_offset);
 typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
 typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk,
 						    struct list_head *head,
@@ -80,6 +83,7 @@ struct udp_tunnel_sock_cfg {
 	__u8  encap_type;
 	udp_tunnel_encap_rcv_t encap_rcv;
 	udp_tunnel_encap_err_lookup_t encap_err_lookup;
+	udp_tunnel_encap_err_rcv_t encap_err_rcv;
 	udp_tunnel_encap_destroy_t encap_destroy;
 	udp_tunnel_gro_receive_t gro_receive;
 	udp_tunnel_gro_complete_t gro_complete;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 34eda973bbf1..cd72158e953a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -783,6 +783,8 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	 */
 	if (tunnel) {
 		/* ...not for tunnels though: we don't have a sending socket */
+		if (udp_sk(sk)->encap_err_rcv)
+			udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2);
 		goto out;
 	}
 	if (!inet->recverr) {
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index 8efaf8c3fe2a..8242c8947340 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -72,6 +72,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 
 	udp_sk(sk)->encap_type = cfg->encap_type;
 	udp_sk(sk)->encap_rcv = cfg->encap_rcv;
+	udp_sk(sk)->encap_err_rcv = cfg->encap_err_rcv;
 	udp_sk(sk)->encap_err_lookup = cfg->encap_err_lookup;
 	udp_sk(sk)->encap_destroy = cfg->encap_destroy;
 	udp_sk(sk)->gro_receive = cfg->gro_receive;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 16c176e7c69a..3366d6a77ff2 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -616,8 +616,11 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	}
 
 	/* Tunnels don't have an application socket: don't pass errors back */
-	if (tunnel)
+	if (tunnel) {
+		if (udp_sk(sk)->encap_err_rcv)
+			udp_sk(sk)->encap_err_rcv(sk, skb, offset);
 		goto out;
+	}
 
 	if (!np->recverr) {
 		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 571436064cd6..62c70709d798 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -982,6 +982,7 @@ void rxrpc_send_keepalive(struct rxrpc_peer *);
 /*
  * peer_event.c
  */
+void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset);
 void rxrpc_error_report(struct sock *);
 void rxrpc_peer_keepalive_worker(struct work_struct *);
 
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 96ecb7356c0f..79bb02eb67b2 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -137,6 +137,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 
 	tuncfg.encap_type = UDP_ENCAP_RXRPC;
 	tuncfg.encap_rcv = rxrpc_input_packet;
+	tuncfg.encap_err_rcv = rxrpc_encap_err_rcv;
 	tuncfg.sk_user_data = local;
 	setup_udp_tunnel_sock(net, local->socket, &tuncfg);
 
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index be032850ae8c..32561e9567fe 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -16,22 +16,105 @@
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
 #include <net/ip.h>
+#include <net/icmp.h>
 #include "ar-internal.h"
 
+static void rxrpc_adjust_mtu(struct rxrpc_peer *, unsigned int);
 static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
 static void rxrpc_distribute_error(struct rxrpc_peer *, int,
 				   enum rxrpc_call_completion);
 
 /*
- * Find the peer associated with an ICMP packet.
+ * Find the peer associated with an ICMPv4 packet.
  */
 static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
-						     const struct sk_buff *skb,
+						     struct sk_buff *skb,
+						     unsigned int udp_offset,
+						     unsigned int *info,
 						     struct sockaddr_rxrpc *srx)
 {
-	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
+	struct iphdr *ip, *ip0 = ip_hdr(skb);
+	struct icmphdr *icmp = icmp_hdr(skb);
+	struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset);
 
-	_enter("");
+	_enter("%u,%u,%u", ip0->protocol, icmp->type, icmp->code);
+
+	switch (icmp->type) {
+	case ICMP_DEST_UNREACH:
+		*info = ntohs(icmp->un.frag.mtu);
+		fallthrough;
+	case ICMP_TIME_EXCEEDED:
+	case ICMP_PARAMETERPROB:
+		ip = (struct iphdr *)((void *)icmp + 8);
+		break;
+	default:
+		return NULL;
+	}
+
+	memset(srx, 0, sizeof(*srx));
+	srx->transport_type = local->srx.transport_type;
+	srx->transport_len = local->srx.transport_len;
+	srx->transport.family = local->srx.transport.family;
+
+	/* Can we see an ICMP4 packet on an ICMP6 listening socket?  and vice
+	 * versa?
+	 */
+	switch (srx->transport.family) {
+	case AF_INET:
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr, &ip->daddr,
+		       sizeof(struct in_addr));
+		break;
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case AF_INET6:
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr, &ip->daddr,
+		       sizeof(struct in_addr));
+		break;
+#endif
+
+	default:
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+
+	_net("ICMP {%pISp}", &srx->transport);
+	return rxrpc_lookup_peer_rcu(local, srx);
+}
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+/*
+ * Find the peer associated with an ICMPv6 packet.
+ */
+static struct rxrpc_peer *rxrpc_lookup_peer_icmp6_rcu(struct rxrpc_local *local,
+						      struct sk_buff *skb,
+						      unsigned int udp_offset,
+						      unsigned int *info,
+						      struct sockaddr_rxrpc *srx)
+{
+	struct icmp6hdr *icmp = icmp6_hdr(skb);
+	struct ipv6hdr *ip, *ip0 = ipv6_hdr(skb);
+	struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset);
+
+	_enter("%u,%u,%u", ip0->nexthdr, icmp->icmp6_type, icmp->icmp6_code);
+
+	switch (icmp->icmp6_type) {
+	case ICMPV6_DEST_UNREACH:
+		*info = ntohl(icmp->icmp6_mtu);
+		fallthrough;
+	case ICMPV6_PKT_TOOBIG:
+	case ICMPV6_TIME_EXCEED:
+	case ICMPV6_PARAMPROB:
+		ip = (struct ipv6hdr *)((void *)icmp + 8);
+		break;
+	default:
+		return NULL;
+	}
 
 	memset(srx, 0, sizeof(*srx));
 	srx->transport_type = local->srx.transport_type;
@@ -41,6 +124,165 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
 	/* Can we see an ICMP4 packet on an ICMP6 listening socket?  and vice
 	 * versa?
 	 */
+	switch (srx->transport.family) {
+	case AF_INET:
+		_net("Rx ICMP6 on v4 sock");
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr,
+		       &ip->daddr.s6_addr32[3], sizeof(struct in_addr));
+		break;
+	case AF_INET6:
+		_net("Rx ICMP6");
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin6.sin6_addr, &ip->daddr,
+		       sizeof(struct in6_addr));
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+
+	_net("ICMP {%pISp}", &srx->transport);
+	return rxrpc_lookup_peer_rcu(local, srx);
+}
+#endif /* CONFIG_AF_RXRPC_IPV6 */
+
+/*
+ * Handle an error received on the local endpoint as a tunnel.
+ */
+void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb,
+			 unsigned int udp_offset)
+{
+	struct sock_extended_err ee;
+	struct sockaddr_rxrpc srx;
+	struct rxrpc_local *local;
+	struct rxrpc_peer *peer;
+	unsigned int info = 0;
+	int err;
+	u8 version = ip_hdr(skb)->version;
+	u8 type = icmp_hdr(skb)->type;
+	u8 code = icmp_hdr(skb)->code;
+
+	rcu_read_lock();
+	local = rcu_dereference_sk_user_data(sk);
+	if (unlikely(!local)) {
+		rcu_read_unlock();
+		return;
+	}
+
+	rxrpc_new_skb(skb, rxrpc_skb_received);
+
+	switch (ip_hdr(skb)->version) {
+	case IPVERSION:
+		peer = rxrpc_lookup_peer_icmp_rcu(local, skb, udp_offset,
+						  &info, &srx);
+		break;
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case 6:
+		peer = rxrpc_lookup_peer_icmp6_rcu(local, skb, udp_offset,
+						   &info, &srx);
+		break;
+#endif
+	default:
+		rcu_read_unlock();
+		return;
+	}
+
+	if (peer && !rxrpc_get_peer_maybe(peer))
+		peer = NULL;
+	if (!peer) {
+		rcu_read_unlock();
+		return;
+	}
+
+	memset(&ee, 0, sizeof(ee));
+
+	switch (version) {
+	case IPVERSION:
+		switch (type) {
+		case ICMP_DEST_UNREACH:
+			switch (code) {
+			case ICMP_FRAG_NEEDED:
+				rxrpc_adjust_mtu(peer, info);
+				rcu_read_unlock();
+				rxrpc_put_peer(peer);
+				return;
+			default:
+				break;
+			}
+
+			err = EHOSTUNREACH;
+			if (code <= NR_ICMP_UNREACH) {
+				/* Might want to do something different with
+				 * non-fatal errors
+				 */
+				//harderr = icmp_err_convert[code].fatal;
+				err = icmp_err_convert[code].errno;
+			}
+			break;
+
+		case ICMP_TIME_EXCEEDED:
+			err = EHOSTUNREACH;
+			break;
+		default:
+			err = EPROTO;
+			break;
+		}
+
+		ee.ee_origin = SO_EE_ORIGIN_ICMP;
+		ee.ee_type = type;
+		ee.ee_code = code;
+		ee.ee_errno = err;
+		break;
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case 6:
+		switch (type) {
+		case ICMPV6_PKT_TOOBIG:
+			rxrpc_adjust_mtu(peer, info);
+			rcu_read_unlock();
+			rxrpc_put_peer(peer);
+			return;
+		}
+
+		icmpv6_err_convert(type, code, &err);
+
+		if (err == EACCES)
+			err = EHOSTUNREACH;
+
+		ee.ee_origin = SO_EE_ORIGIN_ICMP6;
+		ee.ee_type = type;
+		ee.ee_code = code;
+		ee.ee_errno = err;
+		break;
+#endif
+	}
+
+	trace_rxrpc_rx_icmp(peer, &ee, &srx);
+
+	rxrpc_distribute_error(peer, err, RXRPC_CALL_NETWORK_ERROR);
+	rcu_read_unlock();
+	rxrpc_put_peer(peer);
+}
+
+/*
+ * Find the peer associated with a local error.
+ */
+static struct rxrpc_peer *rxrpc_lookup_peer_local_rcu(struct rxrpc_local *local,
+						      const struct sk_buff *skb,
+						      struct sockaddr_rxrpc *srx)
+{
+	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
+
+	_enter("");
+
+	memset(srx, 0, sizeof(*srx));
+	srx->transport_type = local->srx.transport_type;
+	srx->transport_len = local->srx.transport_len;
+	srx->transport.family = local->srx.transport.family;
+
 	switch (srx->transport.family) {
 	case AF_INET:
 		srx->transport_len = sizeof(srx->transport.sin);
@@ -104,10 +346,8 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
 /*
  * Handle an MTU/fragmentation problem.
  */
-static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *serr)
+static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, unsigned int mtu)
 {
-	u32 mtu = serr->ee.ee_info;
-
 	_net("Rx ICMP Fragmentation Needed (%d)", mtu);
 
 	/* wind down the local interface MTU */
@@ -148,7 +388,7 @@ void rxrpc_error_report(struct sock *sk)
 	struct sock_exterr_skb *serr;
 	struct sockaddr_rxrpc srx;
 	struct rxrpc_local *local;
-	struct rxrpc_peer *peer;
+	struct rxrpc_peer *peer = NULL;
 	struct sk_buff *skb;
 
 	rcu_read_lock();
@@ -172,41 +412,20 @@ void rxrpc_error_report(struct sock *sk)
 	}
 	rxrpc_new_skb(skb, rxrpc_skb_received);
 	serr = SKB_EXT_ERR(skb);
-	if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
-		_leave("UDP empty message");
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		return;
-	}
 
-	peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx);
-	if (peer && !rxrpc_get_peer_maybe(peer))
-		peer = NULL;
-	if (!peer) {
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		_leave(" [no peer]");
-		return;
-	}
-
-	trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
-
-	if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
-	     serr->ee.ee_type == ICMP_DEST_UNREACH &&
-	     serr->ee.ee_code == ICMP_FRAG_NEEDED)) {
-		rxrpc_adjust_mtu(peer, serr);
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		rxrpc_put_peer(peer);
-		_leave(" [MTU update]");
-		return;
+	if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL) {
+		peer = rxrpc_lookup_peer_local_rcu(local, skb, &srx);
+		if (peer && !rxrpc_get_peer_maybe(peer))
+			peer = NULL;
+		if (peer) {
+			trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
+			rxrpc_store_error(peer, serr);
+		}
 	}
 
-	rxrpc_store_error(peer, serr);
 	rcu_read_unlock();
 	rxrpc_free_skb(skb, rxrpc_skb_freed);
 	rxrpc_put_peer(peer);
-
 	_leave("");
 }
 
-- 
cgit v1.2.3


From 3261400639463a853ba2b3be8bd009c2a8089775 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 31 Aug 2022 23:38:09 +0000
Subject: tcp: TX zerocopy should not sense pfmemalloc status

We got a recent syzbot report [1] showing a possible misuse
of pfmemalloc page status in TCP zerocopy paths.

Indeed, for pages coming from user space or other layers,
using page_is_pfmemalloc() is moot, and possibly could give
false positives.

There has been attempts to make page_is_pfmemalloc() more robust,
but not using it in the first place in this context is probably better,
removing cpu cycles.

Note to stable teams :

You need to backport 84ce071e38a6 ("net: introduce
__skb_fill_page_desc_noacc") as a prereq.

Race is more probable after commit c07aea3ef4d4
("mm: add a signature in struct page") because page_is_pfmemalloc()
is now using low order bit from page->lru.next, which can change
more often than page->index.

Low order bit should never be set for lru.next (when used as an anchor
in LRU list), so KCSAN report is mostly a false positive.

Backporting to older kernel versions seems not necessary.

[1]
BUG: KCSAN: data-race in lru_add_fn / tcp_build_frag

write to 0xffffea0004a1d2c8 of 8 bytes by task 18600 on cpu 0:
__list_add include/linux/list.h:73 [inline]
list_add include/linux/list.h:88 [inline]
lruvec_add_folio include/linux/mm_inline.h:105 [inline]
lru_add_fn+0x440/0x520 mm/swap.c:228
folio_batch_move_lru+0x1e1/0x2a0 mm/swap.c:246
folio_batch_add_and_move mm/swap.c:263 [inline]
folio_add_lru+0xf1/0x140 mm/swap.c:490
filemap_add_folio+0xf8/0x150 mm/filemap.c:948
__filemap_get_folio+0x510/0x6d0 mm/filemap.c:1981
pagecache_get_page+0x26/0x190 mm/folio-compat.c:104
grab_cache_page_write_begin+0x2a/0x30 mm/folio-compat.c:116
ext4_da_write_begin+0x2dd/0x5f0 fs/ext4/inode.c:2988
generic_perform_write+0x1d4/0x3f0 mm/filemap.c:3738
ext4_buffered_write_iter+0x235/0x3e0 fs/ext4/file.c:270
ext4_file_write_iter+0x2e3/0x1210
call_write_iter include/linux/fs.h:2187 [inline]
new_sync_write fs/read_write.c:491 [inline]
vfs_write+0x468/0x760 fs/read_write.c:578
ksys_write+0xe8/0x1a0 fs/read_write.c:631
__do_sys_write fs/read_write.c:643 [inline]
__se_sys_write fs/read_write.c:640 [inline]
__x64_sys_write+0x3e/0x50 fs/read_write.c:640
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

read to 0xffffea0004a1d2c8 of 8 bytes by task 18611 on cpu 1:
page_is_pfmemalloc include/linux/mm.h:1740 [inline]
__skb_fill_page_desc include/linux/skbuff.h:2422 [inline]
skb_fill_page_desc include/linux/skbuff.h:2443 [inline]
tcp_build_frag+0x613/0xb20 net/ipv4/tcp.c:1018
do_tcp_sendpages+0x3e8/0xaf0 net/ipv4/tcp.c:1075
tcp_sendpage_locked net/ipv4/tcp.c:1140 [inline]
tcp_sendpage+0x89/0xb0 net/ipv4/tcp.c:1150
inet_sendpage+0x7f/0xc0 net/ipv4/af_inet.c:833
kernel_sendpage+0x184/0x300 net/socket.c:3561
sock_sendpage+0x5a/0x70 net/socket.c:1054
pipe_to_sendpage+0x128/0x160 fs/splice.c:361
splice_from_pipe_feed fs/splice.c:415 [inline]
__splice_from_pipe+0x222/0x4d0 fs/splice.c:559
splice_from_pipe fs/splice.c:594 [inline]
generic_splice_sendpage+0x89/0xc0 fs/splice.c:743
do_splice_from fs/splice.c:764 [inline]
direct_splice_actor+0x80/0xa0 fs/splice.c:931
splice_direct_to_actor+0x305/0x620 fs/splice.c:886
do_splice_direct+0xfb/0x180 fs/splice.c:974
do_sendfile+0x3bf/0x910 fs/read_write.c:1249
__do_sys_sendfile64 fs/read_write.c:1317 [inline]
__se_sys_sendfile64 fs/read_write.c:1303 [inline]
__x64_sys_sendfile64+0x10c/0x150 fs/read_write.c:1303
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

value changed: 0x0000000000000000 -> 0xffffea0004a1d288

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 18611 Comm: syz-executor.4 Not tainted 6.0.0-rc2-syzkaller-00248-ge022620b5d05-dirty #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/22/2022

Fixes: c07aea3ef4d4 ("mm: add a signature in struct page")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 21 +++++++++++++++++++++
 net/core/datagram.c    |  2 +-
 net/ipv4/tcp.c         |  2 +-
 3 files changed, 23 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ca8afa382bf2..18e163a3460d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2444,6 +2444,27 @@ static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
 	skb_shinfo(skb)->nr_frags = i + 1;
 }
 
+/**
+ * skb_fill_page_desc_noacc - initialise a paged fragment in an skb
+ * @skb: buffer containing fragment to be initialised
+ * @i: paged fragment index to initialise
+ * @page: the page to use for this fragment
+ * @off: the offset to the data with @page
+ * @size: the length of the data
+ *
+ * Variant of skb_fill_page_desc() which does not deal with
+ * pfmemalloc, if page is not owned by us.
+ */
+static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i,
+					    struct page *page, int off,
+					    int size)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+	__skb_fill_page_desc_noacc(shinfo, i, page, off, size);
+	shinfo->nr_frags = i + 1;
+}
+
 void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
 		     int size, unsigned int truesize);
 
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 7255531f63ae..e4ff2db40c98 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -677,7 +677,7 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
 				page_ref_sub(last_head, refs);
 				refs = 0;
 			}
-			skb_fill_page_desc(skb, frag++, head, start, size);
+			skb_fill_page_desc_noacc(skb, frag++, head, start, size);
 		}
 		if (refs)
 			page_ref_sub(last_head, refs);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e5011c136fdb..6cdfce6f2867 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1015,7 +1015,7 @@ new_segment:
 		skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
 	} else {
 		get_page(page);
-		skb_fill_page_desc(skb, i, page, offset, copy);
+		skb_fill_page_desc_noacc(skb, i, page, offset, copy);
 	}
 
 	if (!(flags & MSG_NO_SHARED_FRAGS))
-- 
cgit v1.2.3


From b30f7c8eb0780e1479a9882526e838664271f4c9 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Thu, 1 Sep 2022 13:07:32 +0100
Subject: spi: mux: Fix mux interaction with fast path optimisations

The spi-mux driver is rather too clever and attempts to resubmit any
message that is submitted to it to the parent controller with some
adjusted callbacks.  This does not play at all nicely with the fast
path which now sets flags on the message indicating that it's being
handled through the fast path, we see async messages flagged as being on
the fast path.  Ideally the spi-mux code would duplicate the message but
that's rather invasive and a bit fragile in that it relies on the mux
knowing which fields in the message to copy.  Instead teach the core
that there are controllers which can't cope with the fast path and have
the mux flag itself as being such a controller, ensuring that messages
going via the mux don't get partially handled via the fast path.

This will reduce the performance of any spi-mux connected device since
we'll now always use the thread for both the actual controller and the
mux controller instead of just the actual controller but given that we
were always hitting the slow path anyway it's hopefully not too much of
an additional cost and it allows us to keep the fast path.

Fixes: ae7d2346dc89 ("spi: Don't use the message queue if possible in spi_sync")
Reported-by: Casper Andersson <casper.casan@gmail.com>
Tested-by: Casper Andersson <casper.casan@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20220901120732.49245-1-broonie@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-mux.c   | 1 +
 drivers/spi/spi.c       | 2 +-
 include/linux/spi/spi.h | 2 ++
 3 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/spi/spi-mux.c b/drivers/spi/spi-mux.c
index f5d32ec4634e..0709e987bd5a 100644
--- a/drivers/spi/spi-mux.c
+++ b/drivers/spi/spi-mux.c
@@ -161,6 +161,7 @@ static int spi_mux_probe(struct spi_device *spi)
 	ctlr->num_chipselect = mux_control_states(priv->mux);
 	ctlr->bus_num = -1;
 	ctlr->dev.of_node = spi->dev.of_node;
+	ctlr->must_async = true;
 
 	ret = devm_spi_register_controller(&spi->dev, ctlr);
 	if (ret)
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 8f97a3eacdea..5cbe090f7676 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -4033,7 +4033,7 @@ static int __spi_sync(struct spi_device *spi, struct spi_message *message)
 	 * guard against reentrancy from a different context. The io_mutex
 	 * will catch those cases.
 	 */
-	if (READ_ONCE(ctlr->queue_empty)) {
+	if (READ_ONCE(ctlr->queue_empty) && !ctlr->must_async) {
 		message->actual_length = 0;
 		message->status = -EINPROGRESS;
 
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index e6c73d5ff1a8..f089ee1ead58 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -469,6 +469,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch
  *	SPI_TRANS_FAIL_NO_START.
  * @queue_empty: signal green light for opportunistically skipping the queue
  *	for spi_sync transfers.
+ * @must_async: disable all fast paths in the core
  *
  * Each SPI controller can communicate with one or more @spi_device
  * children.  These make a small bus, sharing MOSI, MISO and SCK signals
@@ -690,6 +691,7 @@ struct spi_controller {
 
 	/* Flag for enabling opportunistic skipping of the queue in spi_sync */
 	bool			queue_empty;
+	bool			must_async;
 };
 
 static inline void *spi_controller_get_devdata(struct spi_controller *ctlr)
-- 
cgit v1.2.3


From 2aec909912da55a6e469fd6ee8412080a5433ed2 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Aug 2022 11:46:38 +0200
Subject: wifi: use struct_group to copy addresses

We sometimes copy all the addresses from the 802.11 header
for the AAD, which may cause complaints from fortify checks.
Use struct_group() to avoid the compiler warnings/errors.

Change-Id: Ic3ea389105e7813b22095b295079eecdabde5045
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h          | 8 +++++---
 net/mac80211/wpa.c                 | 4 ++--
 net/wireless/lib80211_crypt_ccmp.c | 2 +-
 3 files changed, 8 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 55e6f4ad0ca6..b6e6d5b40774 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -310,9 +310,11 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2)
 struct ieee80211_hdr {
 	__le16 frame_control;
 	__le16 duration_id;
-	u8 addr1[ETH_ALEN];
-	u8 addr2[ETH_ALEN];
-	u8 addr3[ETH_ALEN];
+	struct_group(addrs,
+		u8 addr1[ETH_ALEN];
+		u8 addr2[ETH_ALEN];
+		u8 addr3[ETH_ALEN];
+	);
 	__le16 seq_ctrl;
 	u8 addr4[ETH_ALEN];
 } __packed __aligned(2);
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index 93ec2f349748..20f742b5503b 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -351,7 +351,7 @@ static u8 ccmp_gcmp_aad(struct sk_buff *skb, u8 *aad)
 	 * FC | A1 | A2 | A3 | SC | [A4] | [QC] */
 	put_unaligned_be16(len_a, &aad[0]);
 	put_unaligned(mask_fc, (__le16 *)&aad[2]);
-	memcpy(&aad[4], &hdr->addr1, 3 * ETH_ALEN);
+	memcpy(&aad[4], &hdr->addrs, 3 * ETH_ALEN);
 
 	/* Mask Seq#, leave Frag# */
 	aad[22] = *((u8 *) &hdr->seq_ctrl) & 0x0f;
@@ -792,7 +792,7 @@ static void bip_aad(struct sk_buff *skb, u8 *aad)
 				IEEE80211_FCTL_MOREDATA);
 	put_unaligned(mask_fc, (__le16 *) &aad[0]);
 	/* A1 || A2 || A3 */
-	memcpy(aad + 2, &hdr->addr1, 3 * ETH_ALEN);
+	memcpy(aad + 2, &hdr->addrs, 3 * ETH_ALEN);
 }
 
 
diff --git a/net/wireless/lib80211_crypt_ccmp.c b/net/wireless/lib80211_crypt_ccmp.c
index 6a5f08f7491e..cca5e1cf089e 100644
--- a/net/wireless/lib80211_crypt_ccmp.c
+++ b/net/wireless/lib80211_crypt_ccmp.c
@@ -136,7 +136,7 @@ static int ccmp_init_iv_and_aad(const struct ieee80211_hdr *hdr,
 	pos = (u8 *) hdr;
 	aad[0] = pos[0] & 0x8f;
 	aad[1] = pos[1] & 0xc7;
-	memcpy(aad + 2, hdr->addr1, 3 * ETH_ALEN);
+	memcpy(aad + 2, &hdr->addrs, 3 * ETH_ALEN);
 	pos = (u8 *) & hdr->seq_ctrl;
 	aad[20] = pos[0] & 0x0f;
 	aad[21] = 0;		/* all bits masked */
-- 
cgit v1.2.3


From dec9b2f1e0455a151a7293c367da22ab973f713e Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 2 Sep 2022 16:59:15 +0200
Subject: debugfs: add debugfs_lookup_and_remove()

There is a very common pattern of using
debugfs_remove(debufs_lookup(..)) which results in a dentry leak of the
dentry that was looked up.  Instead of having to open-code the correct
pattern of calling dput() on the dentry, create
debugfs_lookup_and_remove() to handle this pattern automatically and
properly without any memory leaks.

Cc: stable <stable@kernel.org>
Reported-by: Kuyo Chang <kuyo.chang@mediatek.com>
Tested-by: Kuyo Chang <kuyo.chang@mediatek.com>
Link: https://lore.kernel.org/r/YxIaQ8cSinDR881k@kroah.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/debugfs/inode.c      | 22 ++++++++++++++++++++++
 include/linux/debugfs.h |  6 ++++++
 2 files changed, 28 insertions(+)

(limited to 'include/linux')

diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 3dcf0b8b4e93..232cfdf095ae 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -744,6 +744,28 @@ void debugfs_remove(struct dentry *dentry)
 }
 EXPORT_SYMBOL_GPL(debugfs_remove);
 
+/**
+ * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it
+ * @name: a pointer to a string containing the name of the item to look up.
+ * @parent: a pointer to the parent dentry of the item.
+ *
+ * This is the equlivant of doing something like
+ * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting
+ * handled for the directory being looked up.
+ */
+void debugfs_lookup_and_remove(const char *name, struct dentry *parent)
+{
+	struct dentry *dentry;
+
+	dentry = debugfs_lookup(name, parent);
+	if (!dentry)
+		return;
+
+	debugfs_remove(dentry);
+	dput(dentry);
+}
+EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove);
+
 /**
  * debugfs_rename - rename a file/directory in the debugfs filesystem
  * @old_dir: a pointer to the parent dentry for the renamed object. This
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index c869f1e73d75..f60674692d36 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -91,6 +91,8 @@ struct dentry *debugfs_create_automount(const char *name,
 void debugfs_remove(struct dentry *dentry);
 #define debugfs_remove_recursive debugfs_remove
 
+void debugfs_lookup_and_remove(const char *name, struct dentry *parent);
+
 const struct file_operations *debugfs_real_fops(const struct file *filp);
 
 int debugfs_file_get(struct dentry *dentry);
@@ -225,6 +227,10 @@ static inline void debugfs_remove(struct dentry *dentry)
 static inline void debugfs_remove_recursive(struct dentry *dentry)
 { }
 
+static inline void debugfs_lookup_and_remove(const char *name,
+					     struct dentry *parent)
+{ }
+
 const struct file_operations *debugfs_real_fops(const struct file *filp);
 
 static inline int debugfs_file_get(struct dentry *dentry)
-- 
cgit v1.2.3


From 9ca05b0f27de928be121cccf07735819dc9e1ed3 Mon Sep 17 00:00:00 2001
From: Maher Sanalla <msanalla@nvidia.com>
Date: Mon, 29 Aug 2022 12:02:27 +0300
Subject: RDMA/mlx5: Rely on RoCE fw cap instead of devlink when setting
 profile

When the RDMA auxiliary driver probes, it sets its profile based on
devlink driverinit value. The latter might not be in sync with FW yet
(In case devlink reload is not performed), thus causing a mismatch
between RDMA driver and FW. This results in the following FW syndrome
when the RDMA driver tries to adjust RoCE state, which fails the probe:

"0xC1F678 | modify_nic_vport_context: roce_en set on a vport that
doesn't support roce"

To prevent this, select the PF profile based on FW RoCE capability
instead of relying on devlink driverinit value.
To provide backward compatibility of the RoCE disable feature, on older
FW's where roce_rw is not set (FW RoCE capability is read-only), keep
the current behavior e.g., rely on devlink driverinit value.

Fixes: fbfa97b4d79f ("net/mlx5: Disable roce at HCA level")
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Link: https://lore.kernel.org/r/cb34ce9a1df4a24c135cb804db87f7d2418bd6cc.1661763459.git.leonro@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/main.c              |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 23 +++++++++++++++++++++--
 include/linux/mlx5/driver.h                    | 19 ++++++++++---------
 3 files changed, 32 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index fc94a1b25485..883d7c60143e 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -4336,7 +4336,7 @@ static int mlx5r_probe(struct auxiliary_device *adev,
 	dev->mdev = mdev;
 	dev->num_ports = num_ports;
 
-	if (ll == IB_LINK_LAYER_ETHERNET && !mlx5_is_roce_init_enabled(mdev))
+	if (ll == IB_LINK_LAYER_ETHERNET && !mlx5_get_roce_state(mdev))
 		profile = &raw_eth_profile;
 	else
 		profile = &pf_profile;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index bec8d6d0b5f6..4870a88cecb7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -494,6 +494,24 @@ static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev)
 	return err;
 }
 
+bool mlx5_is_roce_on(struct mlx5_core_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	union devlink_param_value val;
+	int err;
+
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
+						 &val);
+
+	if (!err)
+		return val.vbool;
+
+	mlx5_core_dbg(dev, "Failed to get param. err = %d\n", err);
+	return MLX5_CAP_GEN(dev, roce);
+}
+EXPORT_SYMBOL(mlx5_is_roce_on);
+
 static int handle_hca_cap_2(struct mlx5_core_dev *dev, void *set_ctx)
 {
 	void *set_hca_cap;
@@ -597,7 +615,8 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 			 MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix));
 
 	if (MLX5_CAP_GEN(dev, roce_rw_supported))
-		MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev));
+		MLX5_SET(cmd_hca_cap, set_hca_cap, roce,
+			 mlx5_is_roce_on(dev));
 
 	max_uc_list = max_uc_list_get_devlink_param(dev);
 	if (max_uc_list > 0)
@@ -623,7 +642,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
  */
 static bool is_roce_fw_disabled(struct mlx5_core_dev *dev)
 {
-	return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_init_enabled(dev)) ||
+	return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_on(dev)) ||
 		(!MLX5_CAP_GEN(dev, roce_rw_supported) && !MLX5_CAP_GEN(dev, roce));
 }
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 96b16fbe1aa4..d6338fb449c8 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1279,16 +1279,17 @@ enum {
 	MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32,
 };
 
-static inline bool mlx5_is_roce_init_enabled(struct mlx5_core_dev *dev)
+bool mlx5_is_roce_on(struct mlx5_core_dev *dev);
+
+static inline bool mlx5_get_roce_state(struct mlx5_core_dev *dev)
 {
-	struct devlink *devlink = priv_to_devlink(dev);
-	union devlink_param_value val;
-	int err;
-
-	err = devlink_param_driverinit_value_get(devlink,
-						 DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
-						 &val);
-	return err ? MLX5_CAP_GEN(dev, roce) : val.vbool;
+	if (MLX5_CAP_GEN(dev, roce_rw_supported))
+		return MLX5_CAP_GEN(dev, roce);
+
+	/* If RoCE cap is read-only in FW, get RoCE state from devlink
+	 * in order to support RoCE enable/disable feature
+	 */
+	return mlx5_is_roce_on(dev);
 }
 
 #endif /* MLX5_DRIVER_H */
-- 
cgit v1.2.3


From 9fc18f6d56d5b79d527c17a8100a0965d18345cf Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 21 Aug 2022 16:06:44 +0200
Subject: dma-mapping: mark dma_supported static

Now that the remaining users in drivers are gone, this function can be
marked static.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-mapping.h | 5 -----
 kernel/dma/mapping.c        | 3 +--
 2 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 25a30906289d..0ee20b764000 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -139,7 +139,6 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
 bool dma_can_mmap(struct device *dev);
-int dma_supported(struct device *dev, u64 mask);
 bool dma_pci_p2pdma_supported(struct device *dev);
 int dma_set_mask(struct device *dev, u64 mask);
 int dma_set_coherent_mask(struct device *dev, u64 mask);
@@ -248,10 +247,6 @@ static inline bool dma_can_mmap(struct device *dev)
 {
 	return false;
 }
-static inline int dma_supported(struct device *dev, u64 mask)
-{
-	return 0;
-}
 static inline bool dma_pci_p2pdma_supported(struct device *dev)
 {
 	return false;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 49cbf3e33de7..27f272381cf2 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -707,7 +707,7 @@ int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL_GPL(dma_mmap_noncontiguous);
 
-int dma_supported(struct device *dev, u64 mask)
+static int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
@@ -721,7 +721,6 @@ int dma_supported(struct device *dev, u64 mask)
 		return 1;
 	return ops->dma_supported(dev, mask);
 }
-EXPORT_SYMBOL(dma_supported);
 
 bool dma_pci_p2pdma_supported(struct device *dev)
 {
-- 
cgit v1.2.3


From 2f79cdfe58c13949bbbb65ba5926abfe9561d0ec Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 31 Aug 2022 09:46:12 -0700
Subject: fs: only do a memory barrier for the first set_buffer_uptodate()

Commit d4252071b97d ("add barriers to buffer_uptodate and
set_buffer_uptodate") added proper memory barriers to the buffer head
BH_Uptodate bit, so that anybody who tests a buffer for being up-to-date
will be guaranteed to actually see initialized state.

However, that commit didn't _just_ add the memory barrier, it also ended
up dropping the "was it already set" logic that the BUFFER_FNS() macro
had.

That's conceptually the right thing for a generic "this is a memory
barrier" operation, but in the case of the buffer contents, we really
only care about the memory barrier for the _first_ time we set the bit,
in that the only memory ordering protection we need is to avoid anybody
seeing uninitialized memory contents.

Any other access ordering wouldn't be about the BH_Uptodate bit anyway,
and would require some other proper lock (typically BH_Lock or the folio
lock).  A reader that races with somebody invalidating the buffer head
isn't an issue wrt the memory ordering, it's a serialization issue.

Now, you'd think that the buffer head operations don't matter in this
day and age (and I certainly thought so), but apparently some loads
still end up being heavy users of buffer heads.  In particular, the
kernel test robot reported that not having this bit access optimization
in place caused a noticeable direct IO performance regression on ext4:

  fxmark.ssd_ext4_no_jnl_DWTL_54_directio.works/sec -26.5% regression

although you presumably need a fast disk and a lot of cores to actually
notice.

Link: https://lore.kernel.org/all/Yw8L7HTZ%2FdE2%2Fo9C@xsang-OptiPlex-9020/
Reported-by: kernel test robot <oliver.sang@intel.com>
Tested-by: Fengwei Yin <fengwei.yin@intel.com>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/buffer_head.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 089c9ade4325..df518c429667 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -137,6 +137,17 @@ BUFFER_FNS(Defer_Completion, defer_completion)
 
 static __always_inline void set_buffer_uptodate(struct buffer_head *bh)
 {
+	/*
+	 * If somebody else already set this uptodate, they will
+	 * have done the memory barrier, and a reader will thus
+	 * see *some* valid buffer state.
+	 *
+	 * Any other serialization (with IO errors or whatever that
+	 * might clear the bit) has to come from other state (eg BH_Lock).
+	 */
+	if (test_bit(BH_Uptodate, &bh->b_state))
+		return;
+
 	/*
 	 * make it consistent with folio_mark_uptodate
 	 * pairs with smp_load_acquire in buffer_uptodate
-- 
cgit v1.2.3


From 9cd4f1434479f1ac25c440c421fbf52069079914 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Sun, 11 Sep 2022 11:18:45 +0800
Subject: iommu/vt-d: Fix possible recursive locking in intel_iommu_init()

The global rwsem dmar_global_lock was introduced by commit 3a5670e8ac932
("iommu/vt-d: Introduce a rwsem to protect global data structures"). It
is used to protect DMAR related global data from DMAR hotplug operations.

The dmar_global_lock used in the intel_iommu_init() might cause recursive
locking issue, for example, intel_iommu_get_resv_regions() is taking the
dmar_global_lock from within a section where intel_iommu_init() already
holds it via probe_acpi_namespace_devices().

Using dmar_global_lock in intel_iommu_init() could be relaxed since it is
unlikely that any IO board must be hot added before the IOMMU subsystem is
initialized. This eliminates the possible recursive locking issue by moving
down DMAR hotplug support after the IOMMU is initialized and removing the
uses of dmar_global_lock in intel_iommu_init().

Fixes: d5692d4af08cd ("iommu/vt-d: Fix suspicious RCU usage in probe_acpi_namespace_devices()")
Reported-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/894db0ccae854b35c73814485569b634237b5538.1657034828.git.robin.murphy@arm.com
Link: https://lore.kernel.org/r/20220718235325.3952426-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/dmar.c  |  7 +++++++
 drivers/iommu/intel/iommu.c | 27 ++-------------------------
 include/linux/dmar.h        |  4 +++-
 3 files changed, 12 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 5a8f780e7ffd..497c912ad9e1 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -2349,6 +2349,13 @@ static int dmar_device_hotplug(acpi_handle handle, bool insert)
 	if (!dmar_in_use())
 		return 0;
 
+	/*
+	 * It's unlikely that any I/O board is hot added before the IOMMU
+	 * subsystem is initialized.
+	 */
+	if (IS_ENABLED(CONFIG_INTEL_IOMMU) && !intel_iommu_enabled)
+		return -EOPNOTSUPP;
+
 	if (dmar_detect_dsm(handle, DMAR_DSM_FUNC_DRHD)) {
 		tmp = handle;
 	} else {
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 64d30895a4c8..1f2cd43cf9bc 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3019,13 +3019,7 @@ static int __init init_dmars(void)
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
 		if (pasid_supported(iommu) && ecap_prs(iommu->ecap)) {
-			/*
-			 * Call dmar_alloc_hwirq() with dmar_global_lock held,
-			 * could cause possible lock race condition.
-			 */
-			up_write(&dmar_global_lock);
 			ret = intel_svm_enable_prq(iommu);
-			down_write(&dmar_global_lock);
 			if (ret)
 				goto free_iommu;
 		}
@@ -3938,7 +3932,6 @@ int __init intel_iommu_init(void)
 	force_on = (!intel_iommu_tboot_noforce && tboot_force_iommu()) ||
 		    platform_optin_force_iommu();
 
-	down_write(&dmar_global_lock);
 	if (dmar_table_init()) {
 		if (force_on)
 			panic("tboot: Failed to initialize DMAR table\n");
@@ -3951,16 +3944,6 @@ int __init intel_iommu_init(void)
 		goto out_free_dmar;
 	}
 
-	up_write(&dmar_global_lock);
-
-	/*
-	 * The bus notifier takes the dmar_global_lock, so lockdep will
-	 * complain later when we register it under the lock.
-	 */
-	dmar_register_bus_notifier();
-
-	down_write(&dmar_global_lock);
-
 	if (!no_iommu)
 		intel_iommu_debugfs_init();
 
@@ -4005,11 +3988,9 @@ int __init intel_iommu_init(void)
 		pr_err("Initialization failed\n");
 		goto out_free_dmar;
 	}
-	up_write(&dmar_global_lock);
 
 	init_iommu_pm_ops();
 
-	down_read(&dmar_global_lock);
 	for_each_active_iommu(iommu, drhd) {
 		/*
 		 * The flush queue implementation does not perform
@@ -4027,13 +4008,11 @@ int __init intel_iommu_init(void)
 				       "%s", iommu->name);
 		iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL);
 	}
-	up_read(&dmar_global_lock);
 
 	bus_set_iommu(&pci_bus_type, &intel_iommu_ops);
 	if (si_domain && !hw_pass_through)
 		register_memory_notifier(&intel_iommu_memory_nb);
 
-	down_read(&dmar_global_lock);
 	if (probe_acpi_namespace_devices())
 		pr_warn("ACPI name space devices didn't probe correctly\n");
 
@@ -4044,17 +4023,15 @@ int __init intel_iommu_init(void)
 
 		iommu_disable_protect_mem_regions(iommu);
 	}
-	up_read(&dmar_global_lock);
-
-	pr_info("Intel(R) Virtualization Technology for Directed I/O\n");
 
 	intel_iommu_enabled = 1;
+	dmar_register_bus_notifier();
+	pr_info("Intel(R) Virtualization Technology for Directed I/O\n");
 
 	return 0;
 
 out_free_dmar:
 	intel_iommu_free_dmars();
-	up_write(&dmar_global_lock);
 	return ret;
 }
 
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index d81a51978d01..8917a32173c4 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -65,6 +65,7 @@ struct dmar_pci_notify_info {
 
 extern struct rw_semaphore dmar_global_lock;
 extern struct list_head dmar_drhd_units;
+extern int intel_iommu_enabled;
 
 #define for_each_drhd_unit(drhd)					\
 	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list,		\
@@ -88,7 +89,8 @@ extern struct list_head dmar_drhd_units;
 static inline bool dmar_rcu_check(void)
 {
 	return rwsem_is_locked(&dmar_global_lock) ||
-	       system_state == SYSTEM_BOOTING;
+	       system_state == SYSTEM_BOOTING ||
+	       (IS_ENABLED(CONFIG_INTEL_IOMMU) && !intel_iommu_enabled);
 }
 
 #define	dmar_rcu_dereference(p)	rcu_dereference_check((p), dmar_rcu_check())
-- 
cgit v1.2.3