Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller:

 1) Restore previous behavior of CAP_SYS_ADMIN wrt loading networking
    BPF programs, from Maciej Żenczykowski.

 2) Fix dropped broadcasts in mac80211 code, from Seevalamuthu
    Mariappan.

 3) Slay memory leak in nl80211 bss color attribute parsing code, from
    Luca Coelho.

 4) Get route from skb properly in ip_route_use_hint(), from Miaohe Lin.

 5) Don't allow anything other than ARPHRD_ETHER in llc code, from Eric
    Dumazet.

 6) xsk code dips too deeply into DMA mapping implementation internals.
    Add dma_need_sync and use it. From Christoph Hellwig

 7) Enforce power-of-2 for BPF ringbuf sizes. From Andrii Nakryiko.

 8) Check for disallowed attributes when loading flow dissector BPF
    programs. From Lorenz Bauer.

 9) Correct packet injection to L3 tunnel devices via AF_PACKET, from
    Jason A. Donenfeld.

10) Don't advertise checksum offload on ipa devices that don't support
    it. From Alex Elder.

11) Resolve several issues in TCP MD5 signature support. Missing memory
    barriers, bogus options emitted when using syncookies, and failure
    to allow md5 key changes in established states. All from Eric
    Dumazet.

12) Fix interface leak in hsr code, from Taehee Yoo.

13) VF reset fixes in hns3 driver, from Huazhong Tan.

14) Make loopback work again with ipv6 anycast, from David Ahern.

15) Fix TX starvation under high load in fec driver, from Tobias
    Waldekranz.

16) MLD2 payload lengths not checked properly in bridge multicast code,
    from Linus Lüssing.

17) Packet scheduler code that wants to find the inner protocol
    currently only works for one level of VLAN encapsulation. Allow
    Q-in-Q situations to work properly here, from Toke
    Høiland-Jørgensen.

18) Fix route leak in l2tp, from Xin Long.

19) Resolve conflict between the sk->sk_user_data usage of bpf reuseport
    support and various protocols. From Martin KaFai Lau.

20) Fix socket cgroup v2 reference counting in some situations, from
    Cong Wang.

21) Cure memory leak in mlx5 connection tracking offload support, from
    Eli Britstein.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (146 commits)
  mlxsw: pci: Fix use-after-free in case of failed devlink reload
  mlxsw: spectrum_router: Remove inappropriate usage of WARN_ON()
  net: macb: fix call to pm_runtime in the suspend/resume functions
  net: macb: fix macb_suspend() by removing call to netif_carrier_off()
  net: macb: fix macb_get/set_wol() when moving to phylink
  net: macb: mark device wake capable when "magic-packet" property present
  net: macb: fix wakeup test in runtime suspend/resume routines
  bnxt_en: fix NULL dereference in case SR-IOV configuration fails
  libbpf: Fix libbpf hashmap on (I)LP32 architectures
  net/mlx5e: CT: Fix memory leak in cleanup
  net/mlx5e: Fix port buffers cell size value
  net/mlx5e: Fix 50G per lane indication
  net/mlx5e: Fix CPU mapping after function reload to avoid aRFS RX crash
  net/mlx5e: Fix VXLAN configuration restore after function reload
  net/mlx5e: Fix usage of rcu-protected pointer
  net/mxl5e: Verify that rpriv is not NULL
  net/mlx5: E-Switch, Fix vlan or qos setting in legacy mode
  net/mlx5: Fix eeprom support for SFP module
  cgroup: Fix sock_cgroup_data on big-endian.
  selftests: bpf: Fix detach from sockmap tests
  ...

12 files changed, 102 insertions, 14 deletions

diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h
index 4052d649f36d..47d5b0c708c9 100644
--- a/include/linux/bpf-netns.h
+++ b/include/linux/bpf-netns.h
@@ -33,7 +33,7 @@ int netns_bpf_prog_query(const union bpf_attr *attr,
 			 union bpf_attr __user *uattr);
 int netns_bpf_prog_attach(const union bpf_attr *attr,
 			  struct bpf_prog *prog);
-int netns_bpf_prog_detach(const union bpf_attr *attr);
+int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
 int netns_bpf_link_create(const union bpf_attr *attr,
 			  struct bpf_prog *prog);
 #else
@@ -49,7 +49,8 @@ static inline int netns_bpf_prog_attach(const union bpf_attr *attr,
 	return -EOPNOTSUPP;
 }
 
-static inline int netns_bpf_prog_detach(const union bpf_attr *attr)
+static inline int netns_bpf_prog_detach(const union bpf_attr *attr,
+					enum bpf_prog_type ptype)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 07052d44bca1..9750a1902ee5 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1543,13 +1543,16 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map)
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
 #if defined(CONFIG_BPF_STREAM_PARSER)
-int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which);
+int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
+			 struct bpf_prog *old, u32 which);
 int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
+int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
 void sock_map_unhash(struct sock *sk);
 void sock_map_close(struct sock *sk, long timeout);
 #else
 static inline int sock_map_prog_update(struct bpf_map *map,
-				       struct bpf_prog *prog, u32 which)
+				       struct bpf_prog *prog,
+				       struct bpf_prog *old, u32 which)
 {
 	return -EOPNOTSUPP;
 }
@@ -1559,6 +1562,12 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr,
 {
 	return -EINVAL;
 }
+
+static inline int sock_map_prog_detach(const union bpf_attr *attr,
+				       enum bpf_prog_type ptype)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_BPF_STREAM_PARSER */
 
 #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 5c1ea99b480f..8b81fbb4497c 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -82,6 +82,11 @@ static inline bool btf_type_is_int(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_INT;
 }
 
+static inline bool btf_type_is_small_int(const struct btf_type *t)
+{
+	return btf_type_is_int(t) && t->size <= sizeof(u64);
+}
+
 static inline bool btf_type_is_enum(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM;
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 52661155f85f..fee0b5547cd0 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -790,7 +790,9 @@ struct sock_cgroup_data {
 	union {
 #ifdef __LITTLE_ENDIAN
 		struct {
-			u8	is_data;
+			u8	is_data : 1;
+			u8	no_refcnt : 1;
+			u8	unused : 6;
 			u8	padding;
 			u16	prioidx;
 			u32	classid;
@@ -800,7 +802,9 @@ struct sock_cgroup_data {
 			u32	classid;
 			u16	prioidx;
 			u8	padding;
-			u8	is_data;
+			u8	unused : 6;
+			u8	no_refcnt : 1;
+			u8	is_data : 1;
 		} __packed;
 #endif
 		u64		val;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 4598e4da6b1b..618838c48313 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -822,6 +822,7 @@ extern spinlock_t cgroup_sk_update_lock;
 
 void cgroup_sk_alloc_disable(void);
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
+void cgroup_sk_clone(struct sock_cgroup_data *skcd);
 void cgroup_sk_free(struct sock_cgroup_data *skcd);
 
 static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
@@ -835,7 +836,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 	 */
 	v = READ_ONCE(skcd->val);
 
-	if (v & 1)
+	if (v & 3)
 		return &cgrp_dfl_root.cgrp;
 
 	return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
@@ -847,6 +848,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 #else	/* CONFIG_CGROUP_DATA */
 
 static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {}
+static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {}
 static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
 
 #endif	/* CONFIG_CGROUP_DATA */
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index cdfa400f89b3..5184735a0fe8 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -85,4 +85,5 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
 int dma_direct_supported(struct device *dev, u64 mask);
+bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 78f677cf45ab..a33ed3954ed4 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -461,6 +461,7 @@ int dma_set_mask(struct device *dev, u64 mask);
 int dma_set_coherent_mask(struct device *dev, u64 mask);
 u64 dma_get_required_mask(struct device *dev);
 size_t dma_max_mapping_size(struct device *dev);
+bool dma_need_sync(struct device *dev, dma_addr_t dma_addr);
 unsigned long dma_get_merge_boundary(struct device *dev);
 #else /* CONFIG_HAS_DMA */
 static inline dma_addr_t dma_map_page_attrs(struct device *dev,
@@ -571,6 +572,10 @@ static inline size_t dma_max_mapping_size(struct device *dev)
 {
 	return 0;
 }
+static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	return false;
+}
 static inline unsigned long dma_get_merge_boundary(struct device *dev)
 {
 	return 0;
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index fe15f831841b..9f732499ea88 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -3333,13 +3333,17 @@ struct ieee80211_multiple_bssid_configuration {
 #define WLAN_AKM_SUITE_TDLS			SUITE(0x000FAC, 7)
 #define WLAN_AKM_SUITE_SAE			SUITE(0x000FAC, 8)
 #define WLAN_AKM_SUITE_FT_OVER_SAE		SUITE(0x000FAC, 9)
+#define WLAN_AKM_SUITE_AP_PEER_KEY		SUITE(0x000FAC, 10)
 #define WLAN_AKM_SUITE_8021X_SUITE_B		SUITE(0x000FAC, 11)
 #define WLAN_AKM_SUITE_8021X_SUITE_B_192	SUITE(0x000FAC, 12)
+#define WLAN_AKM_SUITE_FT_8021X_SHA384		SUITE(0x000FAC, 13)
 #define WLAN_AKM_SUITE_FILS_SHA256		SUITE(0x000FAC, 14)
 #define WLAN_AKM_SUITE_FILS_SHA384		SUITE(0x000FAC, 15)
 #define WLAN_AKM_SUITE_FT_FILS_SHA256		SUITE(0x000FAC, 16)
 #define WLAN_AKM_SUITE_FT_FILS_SHA384		SUITE(0x000FAC, 17)
 #define WLAN_AKM_SUITE_OWE			SUITE(0x000FAC, 18)
+#define WLAN_AKM_SUITE_FT_PSK_SHA384		SUITE(0x000FAC, 19)
+#define WLAN_AKM_SUITE_PSK_SHA384		SUITE(0x000FAC, 20)
 
 #define WLAN_MAX_KEY_LEN		32
 
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index b05e855f1ddd..41a518336673 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -25,6 +25,8 @@
 #define VLAN_ETH_DATA_LEN	1500	/* Max. octets in payload	 */
 #define VLAN_ETH_FRAME_LEN	1518	/* Max. octets in frame sans FCS */
 
+#define VLAN_MAX_DEPTH	8		/* Max. number of nested VLAN tags parsed */
+
 /*
  * 	struct vlan_hdr - vlan header
  * 	@h_vlan_TCI: priority and VLAN ID
@@ -577,10 +579,10 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
+static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
 					 int *depth)
 {
-	unsigned int vlan_depth = skb->mac_len;
+	unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH;
 
 	/* if type is 802.1Q/AD then the header should already be
 	 * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
@@ -595,13 +597,12 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
 			vlan_depth = ETH_HLEN;
 		}
 		do {
-			struct vlan_hdr *vh;
+			struct vlan_hdr vhdr, *vh;
 
-			if (unlikely(!pskb_may_pull(skb,
-						    vlan_depth + VLAN_HLEN)))
+			vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr);
+			if (unlikely(!vh || !--parse_depth))
 				return 0;
 
-			vh = (struct vlan_hdr *)(skb->data + vlan_depth);
 			type = vh->h_vlan_encapsulated_proto;
 			vlan_depth += VLAN_HLEN;
 		} while (eth_type_vlan(type));
@@ -620,11 +621,25 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 vlan_get_protocol(struct sk_buff *skb)
+static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
 {
 	return __vlan_get_protocol(skb, skb->protocol, NULL);
 }
 
+/* A getter for the SKB protocol field which will handle VLAN tags consistently
+ * whether VLAN acceleration is enabled or not.
+ */
+static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan)
+{
+	if (!skip_vlan)
+		/* VLAN acceleration strips the VLAN header from the skb and
+		 * moves it to skb->vlan_proto
+		 */
+		return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol;
+
+	return vlan_get_protocol(skb);
+}
+
 static inline void vlan_set_encap_proto(struct sk_buff *skb,
 					struct vlan_hdr *vhdr)
 {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 13c0e4556eda..1e6ca716635a 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -147,6 +147,7 @@ enum {
 	MLX5_REG_MCDA		 = 0x9063,
 	MLX5_REG_MCAM		 = 0x907f,
 	MLX5_REG_MIRC		 = 0x9162,
+	MLX5_REG_SBCAM		 = 0xB01F,
 	MLX5_REG_RESOURCE_DUMP   = 0xC000,
 };
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index ca1887dd0423..073b79eacc99 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -9960,6 +9960,34 @@ struct mlx5_ifc_pptb_reg_bits {
 	u8         untagged_buff[0x4];
 };
 
+struct mlx5_ifc_sbcam_reg_bits {
+	u8         reserved_at_0[0x8];
+	u8         feature_group[0x8];
+	u8         reserved_at_10[0x8];
+	u8         access_reg_group[0x8];
+
+	u8         reserved_at_20[0x20];
+
+	u8         sb_access_reg_cap_mask[4][0x20];
+
+	u8         reserved_at_c0[0x80];
+
+	u8         sb_feature_cap_mask[4][0x20];
+
+	u8         reserved_at_1c0[0x40];
+
+	u8         cap_total_buffer_size[0x20];
+
+	u8         cap_cell_size[0x10];
+	u8         cap_max_pg_buffers[0x8];
+	u8         cap_num_pool_supported[0x8];
+
+	u8         reserved_at_240[0x8];
+	u8         cap_sbsr_stat_size[0x8];
+	u8         cap_max_tclass_data[0x8];
+	u8         cap_max_cpu_ingress_tclass_sb[0x8];
+};
+
 struct mlx5_ifc_pbmc_reg_bits {
 	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 08674cd14d5a..1e9ed840b9fc 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -430,6 +430,19 @@ static inline void psock_set_prog(struct bpf_prog **pprog,
 		bpf_prog_put(prog);
 }
 
+static inline int psock_replace_prog(struct bpf_prog **pprog,
+				     struct bpf_prog *prog,
+				     struct bpf_prog *old)
+{
+	if (cmpxchg(pprog, old, prog) != old)
+		return -ENOENT;
+
+	if (old)
+		bpf_prog_put(old);
+
+	return 0;
+}
+
 static inline void psock_progs_drop(struct sk_psock_progs *progs)
 {
 	psock_set_prog(&progs->msg_parser, NULL);