Merge tag 'net-5.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bpf, can and netfilter.

  Current release - regressions:

   - bpf: do not reject when the stack read size is different from the
     tracked scalar size

   - net: fix premature exit from NAPI state polling in napi_disable()

   - riscv, bpf: fix RV32 broken build, and silence RV64 warning

  Current release - new code bugs:

   - net: fix possible NULL deref in sock_reserve_memory

   - amt: fix error return code in amt_init(); fix stopping the
     workqueue

   - ax88796c: use the correct ioctl callback

  Previous releases - always broken:

   - bpf: stop caching subprog index in the bpf_pseudo_func insn

   - security: fixups for the security hooks in sctp

   - nfc: add necessary privilege flags in netlink layer, limit
     operations to admin only

   - vsock: prevent unnecessary refcnt inc for non-blocking connect

   - net/smc: fix sk_refcnt underflow on link down and fallback

   - nfnetlink_queue: fix OOB when mac header was cleared

   - can: j1939: ignore invalid messages per standard

   - bpf, sockmap:
      - fix race in ingress receive verdict with redirect to self
      - fix incorrect sk_skb data_end access when src_reg = dst_reg
      - strparser, and tls are reusing qdisc_skb_cb and colliding

   - ethtool: fix ethtool msg len calculation for pause stats

   - vlan: fix a UAF in vlan_dev_real_dev() when ref-holder tries to
     access an unregistering real_dev

   - udp6: make encap_rcv() bump the v6 not v4 stats

   - drv: prestera: add explicit padding to fix m68k build

   - drv: felix: fix broken VLAN-tagged PTP under VLAN-aware bridge

   - drv: mvpp2: fix wrong SerDes reconfiguration order

  Misc & small latecomers:

   - ipvs: auto-load ipvs on genl access

   - mctp: sanity check the struct sockaddr_mctp padding fields

   - libfs: support RENAME_EXCHANGE in simple_rename()

   - avoid double accounting for pure zerocopy skbs"

* tag 'net-5.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (123 commits)
  selftests/net: udpgso_bench_rx: fix port argument
  net: wwan: iosm: fix compilation warning
  cxgb4: fix eeprom len when diagnostics not implemented
  net: fix premature exit from NAPI state polling in napi_disable()
  net/smc: fix sk_refcnt underflow on linkdown and fallback
  net/mlx5: Lag, fix a potential Oops with mlx5_lag_create_definer()
  gve: fix unmatched u64_stats_update_end()
  net: ethernet: lantiq_etop: Fix compilation error
  selftests: forwarding: Fix packet matching in mirroring selftests
  vsock: prevent unnecessary refcnt inc for nonblocking connect
  net: marvell: mvpp2: Fix wrong SerDes reconfiguration order
  net: ethernet: ti: cpsw_ale: Fix access to un-initialized memory
  net: stmmac: allow a tc-taprio base-time of zero
  selftests: net: test_vxlan_under_vrf: fix HV connectivity test
  net: hns3: allow configure ETS bandwidth of all TCs
  net: hns3: remove check VF uc mac exist when set by PF
  net: hns3: fix some mac statistics is always 0 in device version V2
  net: hns3: fix kernel crash when unload VF while it is being reset
  net: hns3: sync rx ring head in echo common pull
  net: hns3: fix pfc packet number incorrect after querying pfc parameters
  ...

1 files changed, 34 insertions, 1 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 0bd6520329f6..686a666d073d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -454,9 +454,15 @@ enum {
 	 * all frags to avoid possible bad checksum
 	 */
 	SKBFL_SHARED_FRAG = BIT(1),
+
+	/* segment contains only zerocopy data and should not be
+	 * charged to the kernel memory.
+	 */
+	SKBFL_PURE_ZEROCOPY = BIT(2),
 };
 
 #define SKBFL_ZEROCOPY_FRAG	(SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG)
+#define SKBFL_ALL_ZEROCOPY	(SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY)
 
 /*
  * The callback notifies userspace to release buffers when skb DMA is done in
@@ -1464,6 +1470,17 @@ static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb)
 	return is_zcopy ? skb_uarg(skb) : NULL;
 }
 
+static inline bool skb_zcopy_pure(const struct sk_buff *skb)
+{
+	return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY;
+}
+
+static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1,
+				       const struct sk_buff *skb2)
+{
+	return skb_zcopy_pure(skb1) == skb_zcopy_pure(skb2);
+}
+
 static inline void net_zcopy_get(struct ubuf_info *uarg)
 {
 	refcount_inc(&uarg->refcnt);
@@ -1528,7 +1545,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success)
 		if (!skb_zcopy_is_nouarg(skb))
 			uarg->callback(skb, uarg, zerocopy_success);
 
-		skb_shinfo(skb)->flags &= ~SKBFL_ZEROCOPY_FRAG;
+		skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY;
 	}
 }
 
@@ -1675,6 +1692,22 @@ static inline int skb_unclone(struct sk_buff *skb, gfp_t pri)
 	return 0;
 }
 
+/* This variant of skb_unclone() makes sure skb->truesize is not changed */
+static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri)
+{
+	might_sleep_if(gfpflags_allow_blocking(pri));
+
+	if (skb_cloned(skb)) {
+		unsigned int save = skb->truesize;
+		int res;
+
+		res = pskb_expand_head(skb, 0, 0, pri);
+		skb->truesize = save;
+		return res;
+	}
+	return 0;
+}
+
 /**
  *	skb_header_cloned - is the header a clone
  *	@skb: buffer to check