From 92dd5452c1be873a1193561f4f691763103d22ac Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Tue, 19 Sep 2017 18:45:56 +0100 Subject: net: change skb->mac_header when Generic XDP calls adjust_head Since XDP's view of the packet includes the MAC header, moving the start- of-packet with bpf_xdp_adjust_head needs to also update the offset of the MAC header (which is relative to skb->head, not to the skb->data that was changed). Without this, tcpdump sees packets starting from the old MAC header rather than the new one, at least in my tests on the loopback device. Fixes: b5cdae3291f7 ("net: Generic XDP") Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- net/core/dev.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index fb766d906148..9a2254f9802f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3892,6 +3892,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, __skb_pull(skb, off); else if (off < 0) __skb_push(skb, -off); + skb->mac_header += off; switch (act) { case XDP_REDIRECT: -- cgit v1.3-8-gc7d7 From 581fe0ea61584d88072527ae9fb9dcb9d1f2783e Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 22 Sep 2017 19:42:37 -0400 Subject: net: orphan frags on stand-alone ptype in dev_queue_xmit_nit Zerocopy skbs frags are copied when the skb is looped to a local sock. Commit 1080e512d44d ("net: orphan frags on receive") introduced calls to skb_orphan_frags to deliver_skb and __netif_receive_skb for this. With msg_zerocopy, these skbs can also exist in the tx path and thus loop from dev_queue_xmit_nit. This already calls deliver_skb in its loop. But it does not orphan before a separate pt_prev->func(). Add the missing skb_orphan_frags_rx. Changes v1->v2: handle skb_orphan_frags_rx failure Fixes: 1f8b977ab32d ("sock: enable MSG_ZEROCOPY") Signed-off-by: Willem de Bruijn Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 9a2254f9802f..588b473194a8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1948,8 +1948,12 @@ again: goto again; } out_unlock: - if (pt_prev) - pt_prev->func(skb2, skb->dev, pt_prev, skb->dev); + if (pt_prev) { + if (!skb_orphan_frags_rx(skb2, GFP_ATOMIC)) + pt_prev->func(skb2, skb->dev, pt_prev, skb->dev); + else + kfree_skb(skb2); + } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(dev_queue_xmit_nit); -- cgit v1.3-8-gc7d7 From 52a59bd509e3dc458be99dcf333b778e6e3b3749 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 21 Sep 2017 23:33:29 +0300 Subject: net: use 32-bit arithmetic while allocating net device Private part of allocation is never big enough to warrant size_t. Space savings: add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-10 (-10) function old new delta alloc_netdev_mqs 1120 1110 -10 Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index fb766d906148..37d6a3c59e69 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7989,7 +7989,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned int txqs, unsigned int rxqs) { struct net_device *dev; - size_t alloc_size; + unsigned int alloc_size; struct net_device *p; BUG_ON(strlen(name) >= sizeof(dev->name)); -- cgit v1.3-8-gc7d7 From de8f3a83b0a0fddb2cf56e7a718127e9619ea3da Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 25 Sep 2017 02:25:51 +0200 Subject: bpf: add meta pointer for direct access This work enables generic transfer of metadata from XDP into skb. The basic idea is that we can make use of the fact that the resulting skb must be linear and already comes with a larger headroom for supporting bpf_xdp_adjust_head(), which mangles xdp->data. Here, we base our work on a similar principle and introduce a small helper bpf_xdp_adjust_meta() for adjusting a new pointer called xdp->data_meta. Thus, the packet has a flexible and programmable room for meta data, followed by the actual packet data. struct xdp_buff is therefore laid out that we first point to data_hard_start, then data_meta directly prepended to data followed by data_end marking the end of packet. bpf_xdp_adjust_head() takes into account whether we have meta data already prepended and if so, memmove()s this along with the given offset provided there's enough room. xdp->data_meta is optional and programs are not required to use it. The rationale is that when we process the packet in XDP (e.g. as DoS filter), we can push further meta data along with it for the XDP_PASS case, and give the guarantee that a clsact ingress BPF program on the same device can pick this up for further post-processing. Since we work with skb there, we can also set skb->mark, skb->priority or other skb meta data out of BPF, thus having this scratch space generic and programmable allows for more flexibility than defining a direct 1:1 transfer of potentially new XDP members into skb (it's also more efficient as we don't need to initialize/handle each of such new members). The facility also works together with GRO aggregation. The scratch space at the head of the packet can be multiple of 4 byte up to 32 byte large. Drivers not yet supporting xdp->data_meta can simply be set up with xdp->data_meta as xdp->data + 1 as bpf_xdp_adjust_meta() will detect this and bail out, such that the subsequent match against xdp->data for later access is guaranteed to fail. The verifier treats xdp->data_meta/xdp->data the same way as we treat xdp->data/xdp->data_end pointer comparisons. The requirement for doing the compare against xdp->data is that it hasn't been modified from it's original address we got from ctx access. It may have a range marking already from prior successful xdp->data/xdp->data_end pointer comparisons though. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: John Fastabend Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 1 + drivers/net/ethernet/cavium/thunder/nicvf_main.c | 1 + drivers/net/ethernet/intel/i40e/i40e_txrx.c | 1 + drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 1 + drivers/net/ethernet/mellanox/mlx4/en_rx.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 1 + .../net/ethernet/netronome/nfp/nfp_net_common.c | 1 + drivers/net/ethernet/qlogic/qede/qede_fp.c | 1 + drivers/net/tun.c | 1 + drivers/net/virtio_net.c | 2 + include/linux/bpf.h | 1 + include/linux/filter.h | 21 +++- include/linux/skbuff.h | 68 +++++++++++- include/uapi/linux/bpf.h | 13 ++- kernel/bpf/verifier.c | 114 ++++++++++++++++----- net/bpf/test_run.c | 1 + net/core/dev.c | 31 +++++- net/core/filter.c | 77 +++++++++++++- net/core/skbuff.c | 2 + 19 files changed, 297 insertions(+), 42 deletions(-) (limited to 'net/core/dev.c') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index d8f0c837b72c..06ce63c00821 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -94,6 +94,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, xdp.data_hard_start = *data_ptr - offset; xdp.data = *data_ptr; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = *data_ptr + *len; orig_data = xdp.data; mapping = rx_buf->mapping - bp->rx_dma_offset; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 49b80da51ba7..d68478afccbf 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -523,6 +523,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, xdp.data_hard_start = page_address(page); xdp.data = (void *)cpu_addr; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; orig_data = xdp.data; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 1519dfb851d0..f426762bd83a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2107,6 +2107,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) if (!skb) { xdp.data = page_address(rx_buffer->page) + rx_buffer->page_offset; + xdp_set_data_meta_invalid(&xdp); xdp.data_hard_start = xdp.data - i40e_rx_offset(rx_ring); xdp.data_end = xdp.data + size; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d962368d08d0..04bb03bda1cd 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2326,6 +2326,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, if (!skb) { xdp.data = page_address(rx_buffer->page) + rx_buffer->page_offset; + xdp_set_data_meta_invalid(&xdp); xdp.data_hard_start = xdp.data - ixgbe_rx_offset(rx_ring); xdp.data_end = xdp.data + size; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b97a55c827eb..8f9cb8abc497 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -762,6 +762,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud xdp.data_hard_start = va - frags[0].page_offset; xdp.data = va; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + length; orig_data = xdp.data; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index f1dd638384d3..30b3f3fbd719 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -794,6 +794,7 @@ static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq, return false; xdp.data = va + *rx_headroom; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + *len; xdp.data_hard_start = va; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 1c0187f0af51..e3a38be3600a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1583,6 +1583,7 @@ static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, void *hard_start, xdp.data_hard_start = hard_start; xdp.data = data + *off; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = data + *off + *len; orig_data = xdp.data; diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 6fc854b120b0..48ec4c56cddf 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1004,6 +1004,7 @@ static bool qede_rx_xdp(struct qede_dev *edev, xdp.data_hard_start = page_address(bd->data); xdp.data = xdp.data_hard_start + *data_offset; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + *len; /* Queues always have a full reset currently, so for the time diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 2c36f6ebad79..a6e0bffe3d29 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1468,6 +1468,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, xdp.data_hard_start = buf; xdp.data = buf + pad; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; orig_data = xdp.data; act = bpf_prog_run_xdp(xdp_prog, &xdp); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index dd14a4547932..fc059f193e7d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -554,6 +554,7 @@ static struct sk_buff *receive_small(struct net_device *dev, xdp.data_hard_start = buf + VIRTNET_RX_PAD + vi->hdr_len; xdp.data = xdp.data_hard_start + xdp_headroom; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; orig_data = xdp.data; act = bpf_prog_run_xdp(xdp_prog, &xdp); @@ -686,6 +687,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, data = page_address(xdp_page) + offset; xdp.data_hard_start = data - VIRTIO_XDP_HEADROOM + vi->hdr_len; xdp.data = data + vi->hdr_len; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + (len - vi->hdr_len); act = bpf_prog_run_xdp(xdp_prog, &xdp); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8390859e79e7..2b672c50f160 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -137,6 +137,7 @@ enum bpf_reg_type { PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ PTR_TO_STACK, /* reg == frame_pointer + offset */ + PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ }; diff --git a/include/linux/filter.h b/include/linux/filter.h index 052bab3d62e7..911d454af107 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -487,12 +487,14 @@ struct sk_filter { struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; + void *data_meta; void *data_end; }; struct xdp_buff { void *data; void *data_end; + void *data_meta; void *data_hard_start; }; @@ -507,7 +509,8 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb) struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > FIELD_SIZEOF(struct sk_buff, cb)); - cb->data_end = skb->data + skb_headlen(skb); + cb->data_meta = skb->data - skb_metadata_len(skb); + cb->data_end = skb->data + skb_headlen(skb); } static inline u8 *bpf_skb_cb(struct sk_buff *skb) @@ -728,8 +731,22 @@ int xdp_do_redirect(struct net_device *dev, struct bpf_prog *prog); void xdp_do_flush_map(void); +/* Drivers not supporting XDP metadata can use this helper, which + * rejects any room expansion for metadata as a result. + */ +static __always_inline void +xdp_set_data_meta_invalid(struct xdp_buff *xdp) +{ + xdp->data_meta = xdp->data + 1; +} + +static __always_inline bool +xdp_data_meta_unsupported(const struct xdp_buff *xdp) +{ + return unlikely(xdp->data_meta > xdp->data); +} + void bpf_warn_invalid_xdp_action(u32 act); -void bpf_warn_invalid_xdp_redirect(u32 ifindex); struct sock *do_sk_redirect_map(void); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f9db5539a6fb..19e64bfb1a66 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -489,8 +489,9 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, * the end of the header data, ie. at skb->end. */ struct skb_shared_info { - unsigned short _unused; - unsigned char nr_frags; + __u8 __unused; + __u8 meta_len; + __u8 nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ @@ -3400,6 +3401,69 @@ static inline ktime_t net_invalid_timestamp(void) return 0; } +static inline u8 skb_metadata_len(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->meta_len; +} + +static inline void *skb_metadata_end(const struct sk_buff *skb) +{ + return skb_mac_header(skb); +} + +static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, + const struct sk_buff *skb_b, + u8 meta_len) +{ + const void *a = skb_metadata_end(skb_a); + const void *b = skb_metadata_end(skb_b); + /* Using more efficient varaiant than plain call to memcmp(). */ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + u64 diffs = 0; + + switch (meta_len) { +#define __it(x, op) (x -= sizeof(u##op)) +#define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) + case 32: diffs |= __it_diff(a, b, 64); + case 24: diffs |= __it_diff(a, b, 64); + case 16: diffs |= __it_diff(a, b, 64); + case 8: diffs |= __it_diff(a, b, 64); + break; + case 28: diffs |= __it_diff(a, b, 64); + case 20: diffs |= __it_diff(a, b, 64); + case 12: diffs |= __it_diff(a, b, 64); + case 4: diffs |= __it_diff(a, b, 32); + break; + } + return diffs; +#else + return memcmp(a - meta_len, b - meta_len, meta_len); +#endif +} + +static inline bool skb_metadata_differs(const struct sk_buff *skb_a, + const struct sk_buff *skb_b) +{ + u8 len_a = skb_metadata_len(skb_a); + u8 len_b = skb_metadata_len(skb_b); + + if (!(len_a | len_b)) + return false; + + return len_a != len_b ? + true : __skb_metadata_differs(skb_a, skb_b, len_a); +} + +static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len) +{ + skb_shinfo(skb)->meta_len = meta_len; +} + +static inline void skb_metadata_clear(struct sk_buff *skb) +{ + skb_metadata_set(skb, 0); +} + struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 43ab5c402f98..e43491ac4823 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -582,6 +582,12 @@ union bpf_attr { * @map: pointer to sockmap to update * @key: key to insert/update sock in map * @flags: same flags as map update elem + * + * int bpf_xdp_adjust_meta(xdp_md, delta) + * Adjust the xdp_md.data_meta by delta + * @xdp_md: pointer to xdp_md + * @delta: An positive/negative integer to be added to xdp_md.data_meta + * Return: 0 on success or negative on error */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -638,6 +644,7 @@ union bpf_attr { FN(redirect_map), \ FN(sk_redirect_map), \ FN(sock_map_update), \ + FN(xdp_adjust_meta), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -715,7 +722,7 @@ struct __sk_buff { __u32 data_end; __u32 napi_id; - /* accessed by BPF_PROG_TYPE_sk_skb types */ + /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */ __u32 family; __u32 remote_ip4; /* Stored in network byte order */ __u32 local_ip4; /* Stored in network byte order */ @@ -723,6 +730,9 @@ struct __sk_buff { __u32 local_ip6[4]; /* Stored in network byte order */ __u32 remote_port; /* Stored in network byte order */ __u32 local_port; /* stored in host byte order */ + /* ... here. */ + + __u32 data_meta; }; struct bpf_tunnel_key { @@ -783,6 +793,7 @@ enum xdp_action { struct xdp_md { __u32 data; __u32 data_end; + __u32 data_meta; }; enum sk_action { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b914fbe1383e..f849eca36052 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -177,6 +177,12 @@ static __printf(1, 2) void verbose(const char *fmt, ...) va_end(args); } +static bool type_is_pkt_pointer(enum bpf_reg_type type) +{ + return type == PTR_TO_PACKET || + type == PTR_TO_PACKET_META; +} + /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", @@ -187,6 +193,7 @@ static const char * const reg_type_str[] = { [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null", [PTR_TO_STACK] = "fp", [PTR_TO_PACKET] = "pkt", + [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", }; @@ -226,7 +233,7 @@ static void print_verifier_state(struct bpf_verifier_state *state) verbose("(id=%d", reg->id); if (t != SCALAR_VALUE) verbose(",off=%d", reg->off); - if (t == PTR_TO_PACKET) + if (type_is_pkt_pointer(t)) verbose(",r=%d", reg->range); else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE || @@ -519,6 +526,31 @@ static void mark_reg_known_zero(struct bpf_reg_state *regs, u32 regno) __mark_reg_known_zero(regs + regno); } +static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) +{ + return type_is_pkt_pointer(reg->type); +} + +static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg) +{ + return reg_is_pkt_pointer(reg) || + reg->type == PTR_TO_PACKET_END; +} + +/* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */ +static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg, + enum bpf_reg_type which) +{ + /* The register can already have a range from prior markings. + * This is fine as long as it hasn't been advanced from its + * origin. + */ + return reg->type == which && + reg->id == 0 && + reg->off == 0 && + tnum_equals_const(reg->var_off, 0); +} + /* Attempts to improve min/max values based on var_off information */ static void __update_reg_bounds(struct bpf_reg_state *reg) { @@ -702,6 +734,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: + case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: case CONST_PTR_TO_MAP: return true; @@ -1047,7 +1080,10 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, switch (reg->type) { case PTR_TO_PACKET: - /* special case, because of NET_IP_ALIGN */ + case PTR_TO_PACKET_META: + /* Special case, because of NET_IP_ALIGN. Given metadata sits + * right in front, treat it the very same way. + */ return check_pkt_ptr_alignment(reg, off, size, strict); case PTR_TO_MAP_VALUE: pointer_desc = "value "; @@ -1124,8 +1160,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_ctx_access(env, insn_idx, off, size, t, ®_type); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a - * PTR_TO_PACKET[_END]. In the latter case, we know - * the offset is zero. + * PTR_TO_PACKET[_META,_END]. In the latter + * case, we know the offset is zero. */ if (reg_type == SCALAR_VALUE) mark_reg_unknown(state->regs, value_regno); @@ -1170,7 +1206,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else { err = check_stack_read(state, off, size, value_regno); } - } else if (reg->type == PTR_TO_PACKET) { + } else if (reg_is_pkt_pointer(reg)) { if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { verbose("cannot write into packet\n"); return -EACCES; @@ -1310,6 +1346,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, switch (reg->type) { case PTR_TO_PACKET: + case PTR_TO_PACKET_META: return check_packet_access(env, regno, reg->off, access_size); case PTR_TO_MAP_VALUE: return check_map_access(env, regno, reg->off, access_size); @@ -1342,7 +1379,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return 0; } - if (type == PTR_TO_PACKET && + if (type_is_pkt_pointer(type) && !may_access_direct_pkt_data(env, meta, BPF_READ)) { verbose("helper access to the packet is not allowed\n"); return -EACCES; @@ -1351,7 +1388,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) { expected_type = PTR_TO_STACK; - if (type != PTR_TO_PACKET && type != expected_type) + if (!type_is_pkt_pointer(type) && + type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_SIZE || arg_type == ARG_CONST_SIZE_OR_ZERO) { @@ -1375,7 +1413,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, */ if (register_is_null(*reg)) /* final test in check_stack_boundary() */; - else if (type != PTR_TO_PACKET && type != PTR_TO_MAP_VALUE && + else if (!type_is_pkt_pointer(type) && + type != PTR_TO_MAP_VALUE && type != expected_type) goto err_type; meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM; @@ -1401,7 +1440,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->key\n"); return -EACCES; } - if (type == PTR_TO_PACKET) + if (type_is_pkt_pointer(type)) err = check_packet_access(env, regno, reg->off, meta->map_ptr->key_size); else @@ -1417,7 +1456,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->value\n"); return -EACCES; } - if (type == PTR_TO_PACKET) + if (type_is_pkt_pointer(type)) err = check_packet_access(env, regno, reg->off, meta->map_ptr->value_size); else @@ -1590,8 +1629,8 @@ static int check_raw_mode(const struct bpf_func_proto *fn) return count > 1 ? -EINVAL : 0; } -/* Packet data might have moved, any old PTR_TO_PACKET[_END] are now invalid, - * so turn them into unknown SCALAR_VALUE. +/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] + * are now invalid, so turn them into unknown SCALAR_VALUE. */ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { @@ -1600,18 +1639,15 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) int i; for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == PTR_TO_PACKET || - regs[i].type == PTR_TO_PACKET_END) + if (reg_is_pkt_pointer_any(®s[i])) mark_reg_unknown(regs, i); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; - if (reg->type != PTR_TO_PACKET && - reg->type != PTR_TO_PACKET_END) - continue; - __mark_reg_unknown(reg); + if (reg_is_pkt_pointer_any(reg)) + __mark_reg_unknown(reg); } } @@ -1871,7 +1907,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; - if (ptr_reg->type == PTR_TO_PACKET) { + if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ dst_reg->range = 0; @@ -1931,7 +1967,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; - if (ptr_reg->type == PTR_TO_PACKET) { + if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) @@ -2421,7 +2457,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } static void find_good_pkt_pointers(struct bpf_verifier_state *state, - struct bpf_reg_state *dst_reg) + struct bpf_reg_state *dst_reg, + enum bpf_reg_type type) { struct bpf_reg_state *regs = state->regs, *reg; int i; @@ -2483,7 +2520,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. */ for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id) + if (regs[i].type == type && regs[i].id == dst_reg->id) /* keep the maximum range already checked */ regs[i].range = max_t(u16, regs[i].range, dst_reg->off); @@ -2491,7 +2528,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; - if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id) + if (reg->type == type && reg->id == dst_reg->id) reg->range = max_t(u16, reg->range, dst_reg->off); } } @@ -2856,19 +2893,39 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(this_branch, dst_reg); + find_good_pkt_pointers(this_branch, dst_reg, PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(other_branch, dst_reg); + find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(other_branch, ®s[insn->src_reg]); + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], + PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(this_branch, ®s[insn->src_reg]); + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], + PTR_TO_PACKET); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && + dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(®s[insn->src_reg], PTR_TO_PACKET)) { + find_good_pkt_pointers(this_branch, dst_reg, PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && + dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(®s[insn->src_reg], PTR_TO_PACKET)) { + find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && + reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + regs[insn->src_reg].type == PTR_TO_PACKET_META) { + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], + PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && + reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + regs[insn->src_reg].type == PTR_TO_PACKET_META) { + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], + PTR_TO_PACKET_META); } else if (is_pointer_value(env, insn->dst_reg)) { verbose("R%d pointer comparison prohibited\n", insn->dst_reg); return -EACCES; @@ -3298,8 +3355,9 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; /* Check our ids match any regs they're supposed to */ return check_ids(rold->id, rcur->id, idmap); + case PTR_TO_PACKET_META: case PTR_TO_PACKET: - if (rcur->type != PTR_TO_PACKET) + if (rcur->type != rold->type) return false; /* We must have at least as much range as the old ptr * did, so that any accesses which were safe before are diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index df672517b4fd..a86e6687026e 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -162,6 +162,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, xdp.data_hard_start = data; xdp.data = data + XDP_PACKET_HEADROOM + NET_IP_ALIGN; + xdp.data_meta = xdp.data; xdp.data_end = xdp.data + size; retval = bpf_test_run(prog, &xdp, repeat, &duration); diff --git a/net/core/dev.c b/net/core/dev.c index 97abddd9039a..e350c768d4b5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3864,8 +3864,8 @@ drop: static u32 netif_receive_generic_xdp(struct sk_buff *skb, struct bpf_prog *xdp_prog) { + u32 metalen, act = XDP_DROP; struct xdp_buff xdp; - u32 act = XDP_DROP; void *orig_data; int hlen, off; u32 mac_len; @@ -3876,8 +3876,25 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, if (skb_cloned(skb)) return XDP_PASS; - if (skb_linearize(skb)) - goto do_drop; + /* XDP packets must be linear and must have sufficient headroom + * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also + * native XDP provides, thus we need to do it here as well. + */ + if (skb_is_nonlinear(skb) || + skb_headroom(skb) < XDP_PACKET_HEADROOM) { + int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); + int troom = skb->tail + skb->data_len - skb->end; + + /* In case we have to go down the path and also linearize, + * then lets do the pskb_expand_head() work just once here. + */ + if (pskb_expand_head(skb, + hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, + troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) + goto do_drop; + if (troom > 0 && __skb_linearize(skb)) + goto do_drop; + } /* The XDP program wants to see the packet starting at the MAC * header. @@ -3885,6 +3902,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, mac_len = skb->data - skb_mac_header(skb); hlen = skb_headlen(skb) + mac_len; xdp.data = skb->data - mac_len; + xdp.data_meta = xdp.data; xdp.data_end = xdp.data + hlen; xdp.data_hard_start = skb->data - skb_headroom(skb); orig_data = xdp.data; @@ -3902,10 +3920,12 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, case XDP_REDIRECT: case XDP_TX: __skb_push(skb, mac_len); - /* fall through */ + break; case XDP_PASS: + metalen = xdp.data - xdp.data_meta; + if (metalen) + skb_metadata_set(skb, metalen); break; - default: bpf_warn_invalid_xdp_action(act); /* fall through */ @@ -4695,6 +4715,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; diffs |= skb_metadata_dst_cmp(p, skb); + diffs |= skb_metadata_differs(p, skb); if (maclen == ETH_HLEN) diffs |= compare_ether_header(skb_mac_header(p), skb_mac_header(skb)); diff --git a/net/core/filter.c b/net/core/filter.c index c468e7cfad19..9b6e7e84aafd 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2447,14 +2447,26 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = { .arg3_type = ARG_ANYTHING, }; +static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) +{ + return xdp_data_meta_unsupported(xdp) ? 0 : + xdp->data - xdp->data_meta; +} + BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset) { + unsigned long metalen = xdp_get_metalen(xdp); + void *data_start = xdp->data_hard_start + metalen; void *data = xdp->data + offset; - if (unlikely(data < xdp->data_hard_start || + if (unlikely(data < data_start || data > xdp->data_end - ETH_HLEN)) return -EINVAL; + if (metalen) + memmove(xdp->data_meta + offset, + xdp->data_meta, metalen); + xdp->data_meta += offset; xdp->data = data; return 0; @@ -2468,6 +2480,33 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset) +{ + void *meta = xdp->data_meta + offset; + unsigned long metalen = xdp->data - meta; + + if (xdp_data_meta_unsupported(xdp)) + return -ENOTSUPP; + if (unlikely(meta < xdp->data_hard_start || + meta > xdp->data)) + return -EINVAL; + if (unlikely((metalen & (sizeof(__u32) - 1)) || + (metalen > 32))) + return -EACCES; + + xdp->data_meta = meta; + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { + .func = bpf_xdp_adjust_meta, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + static int __bpf_tx_xdp(struct net_device *dev, struct bpf_map *map, struct xdp_buff *xdp, @@ -2692,7 +2731,8 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_clone_redirect || func == bpf_l3_csum_replace || func == bpf_l4_csum_replace || - func == bpf_xdp_adjust_head) + func == bpf_xdp_adjust_head || + func == bpf_xdp_adjust_meta) return true; return false; @@ -3288,6 +3328,8 @@ xdp_func_proto(enum bpf_func_id func_id) return &bpf_get_smp_processor_id_proto; case BPF_FUNC_xdp_adjust_head: return &bpf_xdp_adjust_head_proto; + case BPF_FUNC_xdp_adjust_meta: + return &bpf_xdp_adjust_meta_proto; case BPF_FUNC_redirect: return &bpf_xdp_redirect_proto; case BPF_FUNC_redirect_map: @@ -3418,6 +3460,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): if (size != size_default) return false; @@ -3444,6 +3487,7 @@ static bool sk_filter_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; @@ -3468,6 +3512,7 @@ static bool lwt_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): + case bpf_ctx_range(struct __sk_buff, data_meta): return false; } @@ -3586,6 +3631,9 @@ static bool tc_cls_act_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; + case bpf_ctx_range(struct __sk_buff, data_meta): + info->reg_type = PTR_TO_PACKET_META; + break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; @@ -3619,6 +3667,9 @@ static bool xdp_is_valid_access(int off, int size, case offsetof(struct xdp_md, data): info->reg_type = PTR_TO_PACKET; break; + case offsetof(struct xdp_md, data_meta): + info->reg_type = PTR_TO_PACKET_META; + break; case offsetof(struct xdp_md, data_end): info->reg_type = PTR_TO_PACKET_END; break; @@ -3677,6 +3728,12 @@ static bool sk_skb_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { + switch (off) { + case bpf_ctx_range(struct __sk_buff, tc_classid): + case bpf_ctx_range(struct __sk_buff, data_meta): + return false; + } + if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): @@ -3689,8 +3746,6 @@ static bool sk_skb_is_valid_access(int off, int size, } switch (off) { - case bpf_ctx_range(struct __sk_buff, tc_classid): - return false; case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; @@ -3847,6 +3902,15 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, offsetof(struct sk_buff, data)); break; + case offsetof(struct __sk_buff, data_meta): + off = si->off; + off -= offsetof(struct __sk_buff, data_meta); + off += offsetof(struct sk_buff, cb); + off += offsetof(struct bpf_skb_data_end, data_meta); + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, + si->src_reg, off); + break; + case offsetof(struct __sk_buff, data_end): off = si->off; off -= offsetof(struct __sk_buff, data_end); @@ -4095,6 +4159,11 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data)); break; + case offsetof(struct xdp_md, data_meta): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_meta), + si->dst_reg, si->src_reg, + offsetof(struct xdp_buff, data_meta)); + break; case offsetof(struct xdp_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end), si->dst_reg, si->src_reg, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 000ce735fa8d..d98c2e3ce2bf 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1509,6 +1509,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); + skb_metadata_clear(skb); + /* It is not generally safe to change skb->truesize. * For the moment, we really care of rx path, or * when skb is orphaned (not attached to a socket). -- cgit v1.3-8-gc7d7 From 6c5570016b972d9b1f0f6c2dca9cc0422b1f92bf Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 2 Oct 2017 23:50:05 +0200 Subject: net: core: decouple ifalias get/set from rtnl lock Device alias can be set by either rtnetlink (rtnl is held) or sysfs. rtnetlink hold the rtnl mutex, sysfs acquires it for this purpose. Add an extra mutex for it and use rcu to protect concurrent accesses. This allows the sysfs path to not take rtnl and would later allow to not hold it when dumping ifalias. Based on suggestion from Eric Dumazet. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 +++++++- net/core/dev.c | 52 +++++++++++++++++++++++++++++++++++------------ net/core/net-sysfs.c | 17 ++++++++-------- net/core/rtnetlink.c | 13 ++++++++++-- 4 files changed, 65 insertions(+), 25 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e1d6ef130611..d04424cfffba 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -826,6 +826,11 @@ struct xfrmdev_ops { }; #endif +struct dev_ifalias { + struct rcu_head rcuhead; + char ifalias[]; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1632,7 +1637,7 @@ enum netdev_priv_flags { struct net_device { char name[IFNAMSIZ]; struct hlist_node name_hlist; - char *ifalias; + struct dev_ifalias __rcu *ifalias; /* * I/O specific fields * FIXME: Merge these and struct ifmap into one @@ -3275,6 +3280,7 @@ void __dev_notify_flags(struct net_device *, unsigned int old_flags, unsigned int gchanges); int dev_change_name(struct net_device *, const char *); int dev_set_alias(struct net_device *, const char *, size_t); +int dev_get_alias(const struct net_device *, char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); int __dev_set_mtu(struct net_device *, int); int dev_set_mtu(struct net_device *, int); diff --git a/net/core/dev.c b/net/core/dev.c index e350c768d4b5..1770097cfd86 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -188,6 +188,8 @@ static struct napi_struct *napi_by_id(unsigned int napi_id); DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); +static DEFINE_MUTEX(ifalias_mutex); + /* protects napi_hash addition/deletion and napi_gen_id */ static DEFINE_SPINLOCK(napi_hash_lock); @@ -1265,29 +1267,53 @@ rollback: */ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) { - char *new_ifalias; - - ASSERT_RTNL(); + struct dev_ifalias *new_alias = NULL; if (len >= IFALIASZ) return -EINVAL; - if (!len) { - kfree(dev->ifalias); - dev->ifalias = NULL; - return 0; + if (len) { + new_alias = kmalloc(sizeof(*new_alias) + len + 1, GFP_KERNEL); + if (!new_alias) + return -ENOMEM; + + memcpy(new_alias->ifalias, alias, len); + new_alias->ifalias[len] = 0; } - new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); - if (!new_ifalias) - return -ENOMEM; - dev->ifalias = new_ifalias; - memcpy(dev->ifalias, alias, len); - dev->ifalias[len] = 0; + mutex_lock(&ifalias_mutex); + rcu_swap_protected(dev->ifalias, new_alias, + mutex_is_locked(&ifalias_mutex)); + mutex_unlock(&ifalias_mutex); + + if (new_alias) + kfree_rcu(new_alias, rcuhead); return len; } +/** + * dev_get_alias - get ifalias of a device + * @dev: device + * @alias: buffer to store name of ifalias + * @len: size of buffer + * + * get ifalias for a device. Caller must make sure dev cannot go + * away, e.g. rcu read lock or own a reference count to device. + */ +int dev_get_alias(const struct net_device *dev, char *name, size_t len) +{ + const struct dev_ifalias *alias; + int ret = 0; + + rcu_read_lock(); + alias = rcu_dereference(dev->ifalias); + if (alias) + ret = snprintf(name, len, "%s", alias->ifalias); + rcu_read_unlock(); + + return ret; +} /** * netdev_features_change - device changes features diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 927a6dcbad96..51d5836d8fb9 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -391,10 +391,7 @@ static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, if (len > 0 && buf[len - 1] == '\n') --count; - if (!rtnl_trylock()) - return restart_syscall(); ret = dev_set_alias(netdev, buf, count); - rtnl_unlock(); return ret < 0 ? ret : len; } @@ -403,13 +400,12 @@ static ssize_t ifalias_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); + char tmp[IFALIASZ]; ssize_t ret = 0; - if (!rtnl_trylock()) - return restart_syscall(); - if (netdev->ifalias) - ret = sprintf(buf, "%s\n", netdev->ifalias); - rtnl_unlock(); + ret = dev_get_alias(netdev, tmp, sizeof(tmp)); + if (ret > 0) + ret = sprintf(buf, "%s\n", tmp); return ret; } static DEVICE_ATTR_RW(ifalias); @@ -1488,7 +1484,10 @@ static void netdev_release(struct device *d) BUG_ON(dev->reg_state != NETREG_RELEASED); - kfree(dev->ifalias); + /* no need to wait for rcu grace period: + * device is dead and about to be freed. + */ + kfree(rcu_access_pointer(dev->ifalias)); netdev_freemem(dev); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e6955da0d58d..3961f87cdc76 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1366,6 +1366,16 @@ static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev) return nla_put_u32(skb, IFLA_LINK, ifindex); } +static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb, + struct net_device *dev) +{ + char buf[IFALIASZ]; + int ret; + + ret = dev_get_alias(dev, buf, sizeof(buf)); + return ret > 0 ? nla_put_string(skb, IFLA_IFALIAS, buf) : 0; +} + static int rtnl_fill_link_netnsid(struct sk_buff *skb, const struct net_device *dev) { @@ -1425,8 +1435,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || (dev->qdisc && nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) || - (dev->ifalias && - nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) || + nla_put_ifalias(skb, dev) || nla_put_u32(skb, IFLA_CARRIER_CHANGES, atomic_read(&dev->carrier_changes)) || nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down)) -- cgit v1.3-8-gc7d7 From 20e883204f0268b423799781e5efed786f8a11ba Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 4 Oct 2017 13:56:50 +0200 Subject: net: core: fix kerneldoc comment net/core/dev.c:1306: warning: No description found for parameter 'name' net/core/dev.c:1306: warning: Excess function parameter 'alias' description in 'dev_get_alias' Fixes: 6c5570016b97 ("net: core: decouple ifalias get/set from rtnl lock") Reported-by: kbuild test robot Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 1770097cfd86..454f05441546 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1295,7 +1295,7 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) /** * dev_get_alias - get ifalias of a device * @dev: device - * @alias: buffer to store name of ifalias + * @name: buffer to store name of ifalias * @len: size of buffer * * get ifalias for a device. Caller must make sure dev cannot go -- cgit v1.3-8-gc7d7 From 6621dd29eb9b5e6774ec7a9a75161352fdea47fc Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 3 Oct 2017 13:53:23 +0200 Subject: dev: advertise the new nsid when the netns iface changes x-netns interfaces are bound to two netns: the link netns and the upper netns. Usually, this kind of interfaces is created in the link netns and then moved to the upper netns. At the end, the interface is visible only in the upper netns. The link nsid is advertised via netlink in the upper netns, thus the user always knows where is the link part. There is no such mechanism in the link netns. When the interface is moved to another netns, the user cannot "follow" it. This patch adds a new netlink attribute which helps to follow an interface which moves to another netns. When the interface is unregistered, the new nsid is advertised. If the interface is a x-netns interface (ie rtnl_link_ops->get_link_net is defined), the nsid is allocated if needed. CC: Jason A. Donenfeld Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 4 +++- include/uapi/linux/if_link.h | 1 + net/core/dev.c | 11 ++++++++--- net/core/rtnetlink.c | 31 ++++++++++++++++++++++--------- 4 files changed, 34 insertions(+), 13 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index dea59c8eec54..1251638e60d3 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -17,9 +17,11 @@ extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, long expires, u32 error); void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags); +void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, + gfp_t flags, int *new_nsid); struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned change, u32 event, - gfp_t flags); + gfp_t flags, int *new_nsid); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ea87bd708ee9..cd580fc0e58f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -158,6 +158,7 @@ enum { IFLA_PAD, IFLA_XDP, IFLA_EVENT, + IFLA_NEW_NETNSID, __IFLA_MAX }; diff --git a/net/core/dev.c b/net/core/dev.c index 454f05441546..bffc75429184 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -145,6 +145,7 @@ #include #include #include +#include #include "net-sysfs.h" @@ -7204,7 +7205,7 @@ static void rollback_registered_many(struct list_head *head) if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, - GFP_KERNEL); + GFP_KERNEL, NULL); /* * Flush the unicast and multicast chains @@ -8291,7 +8292,7 @@ EXPORT_SYMBOL(unregister_netdev); int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat) { - int err; + int err, new_nsid; ASSERT_RTNL(); @@ -8347,7 +8348,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); - rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); + if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) + new_nsid = peernet2id_alloc(dev_net(dev), net); + else + new_nsid = peernet2id(dev_net(dev), net); + rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid); /* * Flush the unicast and multicast chains diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3fb1ca33cba4..1ee98b1369d5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -915,6 +915,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */ + rtnl_xdp_size() /* IFLA_XDP */ + nla_total_size(4) /* IFLA_EVENT */ + + nla_total_size(4) /* IFLA_NEW_NETNSID */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ } @@ -1384,7 +1385,7 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb, static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask, - u32 event) + u32 event, int *new_nsid) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -1472,6 +1473,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (rtnl_fill_link_netnsid(skb, dev)) goto nla_put_failure; + if (new_nsid && + nla_put_s32(skb, IFLA_NEW_NETNSID, *new_nsid) < 0) + goto nla_put_failure; + if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC))) goto nla_put_failure; @@ -1701,7 +1706,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, 0, flags, - ext_filter_mask, 0); + ext_filter_mask, 0, NULL); if (err < 0) { if (likely(skb->len)) @@ -2808,7 +2813,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, return -ENOBUFS; err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0); + nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0, NULL); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); @@ -2893,7 +2898,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned int change, - u32 event, gfp_t flags) + u32 event, gfp_t flags, int *new_nsid) { struct net *net = dev_net(dev); struct sk_buff *skb; @@ -2904,7 +2909,8 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, if (skb == NULL) goto errout; - err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event); + err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event, + new_nsid); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -2927,14 +2933,14 @@ void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags) static void rtmsg_ifinfo_event(int type, struct net_device *dev, unsigned int change, u32 event, - gfp_t flags) + gfp_t flags, int *new_nsid) { struct sk_buff *skb; if (dev->reg_state != NETREG_REGISTERED) return; - skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags); + skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid); if (skb) rtmsg_ifinfo_send(skb, dev, flags); } @@ -2942,10 +2948,17 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev, void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, gfp_t flags) { - rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags); + rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, NULL); } EXPORT_SYMBOL(rtmsg_ifinfo); +void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, + gfp_t flags, int *new_nsid) +{ + rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, + new_nsid); +} + static int nlmsg_populate_fdb_fill(struct sk_buff *skb, struct net_device *dev, u8 *addr, u16 vid, u32 pid, u32 seq, @@ -4321,7 +4334,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_RESEND_IGMP: case NETDEV_CHANGEINFODATA: rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event), - GFP_KERNEL); + GFP_KERNEL, NULL); break; default: break; -- cgit v1.3-8-gc7d7 From 51d0c04795a4b5d9a188336884887a9d394a94b0 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 4 Oct 2017 17:48:45 -0700 Subject: net: Add extack to netdev_notifier_info Add netlink_ext_ack to netdev_notifier_info to allow notifier handlers to return errors to userspace. Clean up the initialization in dev.c such that extack is easily added in subsequent patches where relevant. Specifically, remove the init call in call_netdevice_notifiers_info and have callers initalize on stack when info is declared. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 +++++- net/core/dev.c | 79 ++++++++++++++++++++++++++++------------------- 2 files changed, 56 insertions(+), 33 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d04424cfffba..05fcaba4b0d9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2309,7 +2309,8 @@ int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); struct netdev_notifier_info { - struct net_device *dev; + struct net_device *dev; + struct netlink_ext_ack *extack; }; struct netdev_notifier_change_info { @@ -2334,6 +2335,7 @@ static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { info->dev = dev; + info->extack = NULL; } static inline struct net_device * @@ -2342,6 +2344,12 @@ netdev_notifier_info_to_dev(const struct netdev_notifier_info *info) return info->dev; } +static inline struct netlink_ext_ack * +netdev_notifier_info_to_extack(const struct netdev_notifier_info *info) +{ + return info->extack; +} + int call_netdevice_notifiers(unsigned long val, struct net_device *dev); diff --git a/net/core/dev.c b/net/core/dev.c index bffc75429184..e27a6bc0ac4d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -163,7 +163,6 @@ static struct list_head offload_base __read_mostly; static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_info(unsigned long val, - struct net_device *dev, struct netdev_notifier_info *info); static struct napi_struct *napi_by_id(unsigned int napi_id); @@ -1339,10 +1338,11 @@ EXPORT_SYMBOL(netdev_features_change); void netdev_state_change(struct net_device *dev) { if (dev->flags & IFF_UP) { - struct netdev_notifier_change_info change_info; + struct netdev_notifier_change_info change_info = { + .info.dev = dev, + }; - change_info.flags_changed = 0; - call_netdevice_notifiers_info(NETDEV_CHANGE, dev, + call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); } @@ -1563,9 +1563,10 @@ EXPORT_SYMBOL(dev_disable_lro); static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, struct net_device *dev) { - struct netdev_notifier_info info; + struct netdev_notifier_info info = { + .dev = dev, + }; - netdev_notifier_info_init(&info, dev); return nb->notifier_call(nb, val, &info); } @@ -1690,11 +1691,9 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); */ static int call_netdevice_notifiers_info(unsigned long val, - struct net_device *dev, struct netdev_notifier_info *info) { ASSERT_RTNL(); - netdev_notifier_info_init(info, dev); return raw_notifier_call_chain(&netdev_chain, val, info); } @@ -1709,9 +1708,11 @@ static int call_netdevice_notifiers_info(unsigned long val, int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { - struct netdev_notifier_info info; + struct netdev_notifier_info info = { + .dev = dev, + }; - return call_netdevice_notifiers_info(val, dev, &info); + return call_netdevice_notifiers_info(val, &info); } EXPORT_SYMBOL(call_netdevice_notifiers); @@ -6278,7 +6279,15 @@ static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, void *upper_priv, void *upper_info) { - struct netdev_notifier_changeupper_info changeupper_info; + struct netdev_notifier_changeupper_info changeupper_info = { + .info = { + .dev = dev, + }, + .upper_dev = upper_dev, + .master = master, + .linking = true, + .upper_info = upper_info, + }; int ret = 0; ASSERT_RTNL(); @@ -6296,12 +6305,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (master && netdev_master_upper_dev_get(dev)) return -EBUSY; - changeupper_info.upper_dev = upper_dev; - changeupper_info.master = master; - changeupper_info.linking = true; - changeupper_info.upper_info = upper_info; - - ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, + ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) @@ -6312,7 +6316,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (ret) return ret; - ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev, + ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) @@ -6376,20 +6380,24 @@ EXPORT_SYMBOL(netdev_master_upper_dev_link); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev) { - struct netdev_notifier_changeupper_info changeupper_info; + struct netdev_notifier_changeupper_info changeupper_info = { + .info = { + .dev = dev, + }, + .upper_dev = upper_dev, + .linking = false, + }; ASSERT_RTNL(); - changeupper_info.upper_dev = upper_dev; changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev; - changeupper_info.linking = false; - call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, + call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); - call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev, + call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); } EXPORT_SYMBOL(netdev_upper_dev_unlink); @@ -6405,11 +6413,13 @@ EXPORT_SYMBOL(netdev_upper_dev_unlink); void netdev_bonding_info_change(struct net_device *dev, struct netdev_bonding_info *bonding_info) { - struct netdev_notifier_bonding_info info; + struct netdev_notifier_bonding_info info = { + .info.dev = dev, + }; memcpy(&info.bonding_info, bonding_info, sizeof(struct netdev_bonding_info)); - call_netdevice_notifiers_info(NETDEV_BONDING_INFO, dev, + call_netdevice_notifiers_info(NETDEV_BONDING_INFO, &info.info); } EXPORT_SYMBOL(netdev_bonding_info_change); @@ -6535,11 +6545,13 @@ EXPORT_SYMBOL(dev_get_nest_level); void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info) { - struct netdev_notifier_changelowerstate_info changelowerstate_info; + struct netdev_notifier_changelowerstate_info changelowerstate_info = { + .info.dev = lower_dev, + }; ASSERT_RTNL(); changelowerstate_info.lower_state_info = lower_state_info; - call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, lower_dev, + call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, &changelowerstate_info.info); } EXPORT_SYMBOL(netdev_lower_state_changed); @@ -6830,11 +6842,14 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, if (dev->flags & IFF_UP && (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) { - struct netdev_notifier_change_info change_info; - - change_info.flags_changed = changes; - call_netdevice_notifiers_info(NETDEV_CHANGE, dev, - &change_info.info); + struct netdev_notifier_change_info change_info = { + .info = { + .dev = dev, + }, + .flags_changed = changes, + }; + + call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); } } -- cgit v1.3-8-gc7d7 From 42ab19ee90292993370a30ad242599d75a3b749e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 4 Oct 2017 17:48:47 -0700 Subject: net: Add extack to upper device linking Add extack arg to netdev_upper_dev_link and netdev_master_upper_dev_link Signed-off-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 7 ++++--- drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c | 2 +- drivers/net/hyperv/netvsc_drv.c | 2 +- drivers/net/ipvlan/ipvlan_main.c | 2 +- drivers/net/macsec.c | 2 +- drivers/net/macvlan.c | 7 ++++--- drivers/net/macvtap.c | 2 +- drivers/net/team/team.c | 2 +- drivers/net/usb/qmi_wwan.c | 2 +- drivers/net/vrf.c | 7 ++++--- include/linux/if_macvlan.h | 3 ++- include/linux/netdevice.h | 6 ++++-- net/8021q/vlan.c | 6 +++--- net/8021q/vlan.h | 2 +- net/8021q/vlan_netlink.c | 2 +- net/batman-adv/hard-interface.c | 2 +- net/bridge/br_if.c | 2 +- net/core/dev.c | 15 ++++++++++----- net/openvswitch/vport-netdev.c | 3 ++- 19 files changed, 44 insertions(+), 32 deletions(-) (limited to 'net/core/dev.c') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 78feb94a36db..bc92307c2082 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1217,14 +1217,15 @@ static enum netdev_lag_tx_type bond_lag_tx_type(struct bonding *bond) } } -static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave) +static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave, + struct netlink_ext_ack *extack) { struct netdev_lag_upper_info lag_upper_info; int err; lag_upper_info.tx_type = bond_lag_tx_type(bond); err = netdev_master_upper_dev_link(slave->dev, bond->dev, slave, - &lag_upper_info); + &lag_upper_info, extack); if (err) return err; rtmsg_ifinfo(RTM_NEWLINK, slave->dev, IFF_SLAVE, GFP_KERNEL); @@ -1710,7 +1711,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, goto err_detach; } - res = bond_master_upper_dev_link(bond, new_slave); + res = bond_master_upper_dev_link(bond, new_slave, extack); if (res) { netdev_dbg(bond_dev, "Error %d calling bond_master_upper_dev_link\n", res); goto err_unregister; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 98f22551eb45..1af326a60cbb 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -178,7 +178,7 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, if (err) goto err1; - err = netdev_master_upper_dev_link(dev, real_dev, NULL, NULL); + err = netdev_master_upper_dev_link(dev, real_dev, NULL, NULL, extack); if (err) goto err2; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index f300ae61c6c6..dfb986421ec6 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1748,7 +1748,7 @@ static int netvsc_vf_join(struct net_device *vf_netdev, goto rx_handler_failed; } - ret = netdev_upper_dev_link(vf_netdev, ndev); + ret = netdev_upper_dev_link(vf_netdev, ndev, NULL); if (ret != 0) { netdev_err(vf_netdev, "can not set master device %s (err = %d)\n", diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index c74893c1e620..57c3856bab05 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -584,7 +584,7 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, if (err < 0) goto remove_ida; - err = netdev_upper_dev_link(phy_dev, dev); + err = netdev_upper_dev_link(phy_dev, dev, extack); if (err) { goto unregister_netdev; } diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 98e4deaa3a6a..ccbe4eaffe4d 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3244,7 +3244,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev, &macsec_netdev_addr_lock_key, macsec_get_nest_level(dev)); - err = netdev_upper_dev_link(real_dev, dev); + err = netdev_upper_dev_link(real_dev, dev, extack); if (err < 0) goto unregister; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 1ffe77e95d46..858bd66511a2 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1344,7 +1344,8 @@ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode, } int macvlan_common_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port; @@ -1433,7 +1434,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, goto destroy_macvlan_port; dev->priv_flags |= IFF_MACVLAN; - err = netdev_upper_dev_link(lowerdev, dev); + err = netdev_upper_dev_link(lowerdev, dev, extack); if (err) goto unregister_netdev; @@ -1456,7 +1457,7 @@ static int macvlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - return macvlan_common_newlink(src_net, dev, tb, data); + return macvlan_common_newlink(src_net, dev, tb, data, extack); } void macvlan_dellink(struct net_device *dev, struct list_head *head) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index c2d0ea2fb019..f62aea2fcfa9 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -105,7 +105,7 @@ static int macvtap_newlink(struct net *src_net, struct net_device *dev, /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ - err = macvlan_common_newlink(src_net, dev, tb, data); + err = macvlan_common_newlink(src_net, dev, tb, data, extack); if (err) { netdev_rx_handler_unregister(dev); return err; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 4359d45aa131..a468439969df 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1112,7 +1112,7 @@ static int team_upper_dev_link(struct team *team, struct team_port *port) lag_upper_info.tx_type = team->mode->lag_tx_type; err = netdev_master_upper_dev_link(port->dev, team->dev, NULL, - &lag_upper_info); + &lag_upper_info, NULL); if (err) return err; port->dev->priv_flags |= IFF_TEAM_PORT; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 8c3733608271..db7279d5b250 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -221,7 +221,7 @@ static int qmimux_register_device(struct net_device *real_dev, u8 mux_id) /* Account for reference in struct qmimux_priv_priv */ dev_hold(real_dev); - err = netdev_upper_dev_link(real_dev, new_dev); + err = netdev_upper_dev_link(real_dev, new_dev, NULL); if (err) goto out_unregister_netdev; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 4a082ef53533..77d0655a0250 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -764,7 +764,8 @@ static void cycle_netdev(struct net_device *dev) } } -static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) +static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev, + struct netlink_ext_ack *extack) { int ret; @@ -775,7 +776,7 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) return -EOPNOTSUPP; port_dev->priv_flags |= IFF_L3MDEV_SLAVE; - ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL); + ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL, extack); if (ret < 0) goto err; @@ -794,7 +795,7 @@ static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev, if (netif_is_l3_master(port_dev) || netif_is_l3_slave(port_dev)) return -EINVAL; - return do_vrf_add_slave(dev, port_dev); + return do_vrf_add_slave(dev, port_dev, extack); } /* inverse of do_vrf_add_slave */ diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index c9ec1343d187..10e319f41fb1 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -72,7 +72,8 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, extern void macvlan_common_setup(struct net_device *dev); extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]); + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack); extern void macvlan_count_rx(const struct macvlan_dev *vlan, unsigned int len, bool success, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 368a5064a487..31bb3010c69b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3919,10 +3919,12 @@ void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); struct net_device *netdev_master_upper_dev_get(struct net_device *dev); struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); -int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev); +int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, + struct netlink_ext_ack *extack); int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, - void *upper_priv, void *upper_info); + void *upper_priv, void *upper_info, + struct netlink_ext_ack *extack); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 9649579b5b9f..71c3e045505b 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -138,7 +138,7 @@ int vlan_check_real_dev(struct net_device *real_dev, return 0; } -int register_vlan_dev(struct net_device *dev) +int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; @@ -174,7 +174,7 @@ int register_vlan_dev(struct net_device *dev) if (err < 0) goto out_uninit_mvrp; - err = netdev_upper_dev_link(real_dev, dev); + err = netdev_upper_dev_link(real_dev, dev, extack); if (err) goto out_unregister_netdev; @@ -270,7 +270,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) vlan->flags = VLAN_FLAG_REORDER_HDR; new_dev->rtnl_link_ops = &vlan_link_ops; - err = register_vlan_dev(new_dev); + err = register_vlan_dev(new_dev, NULL); if (err < 0) goto out_free_newdev; diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index df8bd65dd370..94f8eed9f9b3 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -107,7 +107,7 @@ void vlan_dev_get_realdev_name(const struct net_device *dev, char *result); int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id); void vlan_setup(struct net_device *dev); -int register_vlan_dev(struct net_device *dev); +int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack); void unregister_vlan_dev(struct net_device *dev, struct list_head *head); bool vlan_dev_inherit_address(struct net_device *dev, struct net_device *real_dev); diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 5e831de3103e..6e7c5a6a7930 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -160,7 +160,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; - return register_vlan_dev(dev); + return register_vlan_dev(dev, extack); } static inline size_t vlan_qos_map_size(unsigned int n) diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index e348f76ea8c1..f7b413b9297e 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -738,7 +738,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, bat_priv = netdev_priv(hard_iface->soft_iface); ret = netdev_master_upper_dev_link(hard_iface->net_dev, - soft_iface, NULL, NULL); + soft_iface, NULL, NULL, NULL); if (ret) goto err_dev; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index f3aef22931ab..0a3fd727048d 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -540,7 +540,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) dev->priv_flags |= IFF_BRIDGE_PORT; - err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL); + err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL, NULL); if (err) goto err5; diff --git a/net/core/dev.c b/net/core/dev.c index e27a6bc0ac4d..fcddccb6be41 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6277,11 +6277,13 @@ static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, - void *upper_priv, void *upper_info) + void *upper_priv, void *upper_info, + struct netlink_ext_ack *extack) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { .dev = dev, + .extack = extack, }, .upper_dev = upper_dev, .master = master, @@ -6341,9 +6343,11 @@ rollback: * returns zero. */ int netdev_upper_dev_link(struct net_device *dev, - struct net_device *upper_dev) + struct net_device *upper_dev, + struct netlink_ext_ack *extack) { - return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL); + return __netdev_upper_dev_link(dev, upper_dev, false, + NULL, NULL, extack); } EXPORT_SYMBOL(netdev_upper_dev_link); @@ -6362,10 +6366,11 @@ EXPORT_SYMBOL(netdev_upper_dev_link); */ int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, - void *upper_priv, void *upper_info) + void *upper_priv, void *upper_info, + struct netlink_ext_ack *extack) { return __netdev_upper_dev_link(dev, upper_dev, true, - upper_priv, upper_info); + upper_priv, upper_info, extack); } EXPORT_SYMBOL(netdev_master_upper_dev_link); diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 0389398fa4ab..2e5e7a41d8ef 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -108,7 +108,8 @@ struct vport *ovs_netdev_link(struct vport *vport, const char *name) rtnl_lock(); err = netdev_master_upper_dev_link(vport->dev, - get_dpdev(vport->dp), NULL, NULL); + get_dpdev(vport->dp), + NULL, NULL, NULL); if (err) goto error_unlock; -- cgit v1.3-8-gc7d7 From 0ad646c81b2182f7fa67ec0c8c825e0ee165696d Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 13 Oct 2017 11:58:53 -0700 Subject: tun: call dev_get_valid_name() before register_netdevice() register_netdevice() could fail early when we have an invalid dev name, in which case ->ndo_uninit() is not called. For tun device, this is a problem because a timer etc. are already initialized and it expects ->ndo_uninit() to clean them up. We could move these initializations into a ->ndo_init() so that register_netdevice() knows better, however this is still complicated due to the logic in tun_detach(). Therefore, I choose to just call dev_get_valid_name() before register_netdevice(), which is quicker and much easier to audit. And for this specific case, it is already enough. Fixes: 96442e42429e ("tuntap: choose the txq based on rxq") Reported-by: Dmitry Alexeev Cc: Jason Wang Cc: "Michael S. Tsirkin" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- drivers/net/tun.c | 3 +++ include/linux/netdevice.h | 3 +++ net/core/dev.c | 6 +++--- 3 files changed, 9 insertions(+), 3 deletions(-) (limited to 'net/core/dev.c') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 5ce580f413b9..e21bf90b819f 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2027,6 +2027,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (!dev) return -ENOMEM; + err = dev_get_valid_name(net, dev, name); + if (err) + goto err_free_dev; dev_net_set(dev, net); dev->rtnl_link_ops = &tun_link_ops; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f535779d9dc1..2eaac7d75af4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3694,6 +3694,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs); +int dev_get_valid_name(struct net *net, struct net_device *dev, + const char *name); + #define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \ alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1) diff --git a/net/core/dev.c b/net/core/dev.c index 588b473194a8..11596a302a26 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1147,9 +1147,8 @@ static int dev_alloc_name_ns(struct net *net, return ret; } -static int dev_get_valid_name(struct net *net, - struct net_device *dev, - const char *name) +int dev_get_valid_name(struct net *net, struct net_device *dev, + const char *name) { BUG_ON(!net); @@ -1165,6 +1164,7 @@ static int dev_get_valid_name(struct net *net, return 0; } +EXPORT_SYMBOL(dev_get_valid_name); /** * dev_change_name - change name of a device -- cgit v1.3-8-gc7d7 From 8a5f2166a6288ee4b5a393f1ebc8cfb26b0510f0 Mon Sep 17 00:00:00 2001 From: Henrik Austad Date: Tue, 17 Oct 2017 12:10:10 +0200 Subject: net: export netdev_txq_to_tc to allow sch_mqprio to compile as module In commit 32302902ff09 ("mqprio: Reserve last 32 classid values for HW traffic classes and misc IDs") sch_mqprio started using netdev_txq_to_tc to find the correct tc instead of dev->tc_to_txq[] However, when mqprio is compiled as a module, it cannot resolve the symbol, leading to this error: ERROR: "netdev_txq_to_tc" [net/sched/sch_mqprio.ko] undefined! This adds an EXPORT_SYMBOL() since the other user in the kernel (netif_set_xps_queue) is also EXPORT_SYMBOL() (and not _GPL) or in a sysfs-callback. Cc: Alexander Duyck Cc: Jesus Sanchez-Palencia Cc: David S. Miller Signed-off-by: Henrik Austad Reviewed-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- net/core/dev.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index fcddccb6be41..d2b20e73080e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2040,6 +2040,7 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) return 0; } +EXPORT_SYMBOL(netdev_txq_to_tc); #ifdef CONFIG_XPS static DEFINE_MUTEX(xps_map_mutex); -- cgit v1.3-8-gc7d7 From 1c601d829ab0d7ac3ac44853f83db2206afe67fc Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 16 Oct 2017 12:19:39 +0200 Subject: bpf: cpumap xdp_buff to skb conversion and allocation This patch makes cpumap functional, by adding SKB allocation and invoking the network stack on the dequeuing CPU. For constructing the SKB on the remote CPU, the xdp_buff in converted into a struct xdp_pkt, and it mapped into the top headroom of the packet, to avoid allocating separate mem. For now, struct xdp_pkt is just a cpumap internal data structure, with info carried between enqueue to dequeue. If a driver doesn't have enough headroom it is simply dropped, with return code -EOVERFLOW. This will be picked up the xdp tracepoint infrastructure, to allow users to catch this. V2: take into account xdp->data_meta V4: - Drop busypoll tricks, keeping it more simple. - Skip RPS and Generic-XDP-recursive-reinjection, suggested by Alexei V5: correct RCU read protection around __netif_receive_skb_core. V6: Setting TASK_RUNNING vs TASK_INTERRUPTIBLE based on talk with Rik van Riel Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + kernel/bpf/cpumap.c | 152 +++++++++++++++++++++++++++++++++++++++------- net/core/dev.c | 27 ++++++++ 3 files changed, 158 insertions(+), 22 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 31bb3010c69b..bf014afcb914 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3260,6 +3260,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); +int netif_receive_skb_core(struct sk_buff *skb); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 768da6a2c265..ee7adf4352dd 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -25,6 +25,9 @@ #include #include +#include /* netif_receive_skb_core */ +#include /* eth_type_trans */ + /* General idea: XDP packets getting XDP redirected to another CPU, * will maximum be stored/queued for one driver ->poll() call. It is * guaranteed that setting flush bit and flush operation happen on @@ -179,6 +182,92 @@ static void cpu_map_kthread_stop(struct work_struct *work) kthread_stop(rcpu->kthread); } +/* For now, xdp_pkt is a cpumap internal data structure, with info + * carried between enqueue to dequeue. It is mapped into the top + * headroom of the packet, to avoid allocating separate mem. + */ +struct xdp_pkt { + void *data; + u16 len; + u16 headroom; + u16 metasize; + struct net_device *dev_rx; +}; + +/* Convert xdp_buff to xdp_pkt */ +static struct xdp_pkt *convert_to_xdp_pkt(struct xdp_buff *xdp) +{ + struct xdp_pkt *xdp_pkt; + int metasize; + int headroom; + + /* Assure headroom is available for storing info */ + headroom = xdp->data - xdp->data_hard_start; + metasize = xdp->data - xdp->data_meta; + metasize = metasize > 0 ? metasize : 0; + if ((headroom - metasize) < sizeof(*xdp_pkt)) + return NULL; + + /* Store info in top of packet */ + xdp_pkt = xdp->data_hard_start; + + xdp_pkt->data = xdp->data; + xdp_pkt->len = xdp->data_end - xdp->data; + xdp_pkt->headroom = headroom - sizeof(*xdp_pkt); + xdp_pkt->metasize = metasize; + + return xdp_pkt; +} + +struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, + struct xdp_pkt *xdp_pkt) +{ + unsigned int frame_size; + void *pkt_data_start; + struct sk_buff *skb; + + /* build_skb need to place skb_shared_info after SKB end, and + * also want to know the memory "truesize". Thus, need to + * know the memory frame size backing xdp_buff. + * + * XDP was designed to have PAGE_SIZE frames, but this + * assumption is not longer true with ixgbe and i40e. It + * would be preferred to set frame_size to 2048 or 4096 + * depending on the driver. + * frame_size = 2048; + * frame_len = frame_size - sizeof(*xdp_pkt); + * + * Instead, with info avail, skb_shared_info in placed after + * packet len. This, unfortunately fakes the truesize. + * Another disadvantage of this approach, the skb_shared_info + * is not at a fixed memory location, with mixed length + * packets, which is bad for cache-line hotness. + */ + frame_size = SKB_DATA_ALIGN(xdp_pkt->len) + xdp_pkt->headroom + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + pkt_data_start = xdp_pkt->data - xdp_pkt->headroom; + skb = build_skb(pkt_data_start, frame_size); + if (!skb) + return NULL; + + skb_reserve(skb, xdp_pkt->headroom); + __skb_put(skb, xdp_pkt->len); + if (xdp_pkt->metasize) + skb_metadata_set(skb, xdp_pkt->metasize); + + /* Essential SKB info: protocol and skb->dev */ + skb->protocol = eth_type_trans(skb, xdp_pkt->dev_rx); + + /* Optional SKB info, currently missing: + * - HW checksum info (skb->ip_summed) + * - HW RX hash (skb_set_hash) + * - RX ring dev queue index (skb_record_rx_queue) + */ + + return skb; +} + static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; @@ -191,15 +280,45 @@ static int cpu_map_kthread_run(void *data) * kthread_stop signal until queue is empty. */ while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { + unsigned int processed = 0, drops = 0; struct xdp_pkt *xdp_pkt; - schedule(); - /* Do work */ - while ((xdp_pkt = ptr_ring_consume(rcpu->queue))) { - /* For now just "refcnt-free" */ - page_frag_free(xdp_pkt); + /* Release CPU reschedule checks */ + if (__ptr_ring_empty(rcpu->queue)) { + __set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } else { + cond_resched(); + } + __set_current_state(TASK_RUNNING); + + /* Process packets in rcpu->queue */ + local_bh_disable(); + /* + * The bpf_cpu_map_entry is single consumer, with this + * kthread CPU pinned. Lockless access to ptr_ring + * consume side valid as no-resize allowed of queue. + */ + while ((xdp_pkt = __ptr_ring_consume(rcpu->queue))) { + struct sk_buff *skb; + int ret; + + skb = cpu_map_build_skb(rcpu, xdp_pkt); + if (!skb) { + page_frag_free(xdp_pkt); + continue; + } + + /* Inject into network stack */ + ret = netif_receive_skb_core(skb); + if (ret == NET_RX_DROP) + drops++; + + /* Limit BH-disable period */ + if (++processed == 8) + break; } - __set_current_state(TASK_INTERRUPTIBLE); + local_bh_enable(); /* resched point, may call do_softirq() */ } __set_current_state(TASK_RUNNING); @@ -490,13 +609,6 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, return 0; } -/* Notice: Will change in later patch */ -struct xdp_pkt { - void *data; - u16 len; - u16 headroom; -}; - /* Runs under RCU-read-side, plus in softirq under NAPI protection. * Thus, safe percpu variable access. */ @@ -524,17 +636,13 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx) { struct xdp_pkt *xdp_pkt; - int headroom; - /* For now this is just used as a void pointer to data_hard_start. - * Followup patch will generalize this. - */ - xdp_pkt = xdp->data_hard_start; + xdp_pkt = convert_to_xdp_pkt(xdp); + if (!xdp_pkt) + return -EOVERFLOW; - /* Fake writing into xdp_pkt->data to measure overhead */ - headroom = xdp->data - xdp->data_hard_start; - if (headroom < sizeof(*xdp_pkt)) - xdp_pkt->data = xdp->data; + /* Info needed when constructing SKB on remote CPU */ + xdp_pkt->dev_rx = dev_rx; bq_enqueue(rcpu, xdp_pkt); return 0; diff --git a/net/core/dev.c b/net/core/dev.c index d2b20e73080e..cf5894f0e6eb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4492,6 +4492,33 @@ out: return ret; } +/** + * netif_receive_skb_core - special purpose version of netif_receive_skb + * @skb: buffer to process + * + * More direct receive version of netif_receive_skb(). It should + * only be used by callers that have a need to skip RPS and Generic XDP. + * Caller must also take care of handling if (page_is_)pfmemalloc. + * + * This function may only be called from softirq context and interrupts + * should be enabled. + * + * Return values (usually ignored): + * NET_RX_SUCCESS: no congestion + * NET_RX_DROP: packet was dropped + */ +int netif_receive_skb_core(struct sk_buff *skb) +{ + int ret; + + rcu_read_lock(); + ret = __netif_receive_skb_core(skb, false); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(netif_receive_skb_core); + static int __netif_receive_skb(struct sk_buff *skb) { int ret; -- cgit v1.3-8-gc7d7 From 6aa7de059173a986114ac43b8f50b297a86f09a8 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 23 Oct 2017 14:07:29 -0700 Subject: locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE() Please do not apply this to mainline directly, instead please re-run the coccinelle script shown below and apply its output. For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't harmful, and changing them results in churn. However, for some features, the read/write distinction is critical to correct operation. To distinguish these cases, separate read/write accessors must be used. This patch migrates (most) remaining ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following coccinelle script: ---- // Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and // WRITE_ONCE() // $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland Signed-off-by: Paul E. McKenney Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- arch/arc/kernel/smp.c | 2 +- arch/arm/include/asm/spinlock.h | 2 +- arch/arm/mach-tegra/cpuidle-tegra20.c | 2 +- arch/arm/vdso/vgettimeofday.c | 2 +- arch/ia64/include/asm/spinlock.h | 8 ++--- arch/mips/include/asm/vdso.h | 2 +- arch/mips/kernel/pm-cps.c | 2 +- arch/mn10300/kernel/mn10300-serial.c | 4 +-- arch/parisc/include/asm/atomic.h | 2 +- arch/powerpc/platforms/powernv/opal-msglog.c | 2 +- arch/s390/include/asm/spinlock.h | 6 ++-- arch/s390/lib/spinlock.c | 16 +++++----- arch/sparc/include/asm/atomic_32.h | 2 +- arch/tile/gxio/dma_queue.c | 4 +-- arch/tile/include/gxio/dma_queue.h | 2 +- arch/tile/kernel/ptrace.c | 2 +- arch/x86/entry/common.c | 2 +- arch/x86/entry/vdso/vclock_gettime.c | 2 +- arch/x86/events/core.c | 2 +- arch/x86/include/asm/vgtod.h | 2 +- arch/x86/kernel/espfix_64.c | 6 ++-- arch/x86/kernel/nmi.c | 2 +- arch/x86/kvm/mmu.c | 4 +-- arch/x86/kvm/page_track.c | 2 +- arch/x86/xen/p2m.c | 2 +- arch/xtensa/platforms/xtfpga/lcd.c | 14 ++++----- block/blk-wbt.c | 2 +- drivers/base/core.c | 2 +- drivers/base/power/runtime.c | 4 +-- drivers/char/random.c | 4 +-- drivers/clocksource/bcm2835_timer.c | 2 +- drivers/crypto/caam/jr.c | 4 +-- drivers/crypto/nx/nx-842-powernv.c | 2 +- drivers/firewire/ohci.c | 10 +++--- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 4 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 4 +-- drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 2 +- drivers/gpu/drm/radeon/radeon_gem.c | 4 +-- drivers/gpu/drm/vmwgfx/vmwgfx_surface.c | 2 +- drivers/infiniband/hw/hfi1/file_ops.c | 2 +- drivers/infiniband/hw/hfi1/pio.c | 6 ++-- drivers/infiniband/hw/hfi1/ruc.c | 2 +- drivers/infiniband/hw/hfi1/sdma.c | 8 ++--- drivers/infiniband/hw/hfi1/sdma.h | 2 +- drivers/infiniband/hw/hfi1/uc.c | 4 +-- drivers/infiniband/hw/hfi1/ud.c | 4 +-- drivers/infiniband/hw/hfi1/user_sdma.c | 8 ++--- drivers/infiniband/hw/qib/qib_ruc.c | 2 +- drivers/infiniband/hw/qib/qib_uc.c | 4 +-- drivers/infiniband/hw/qib/qib_ud.c | 4 +-- drivers/infiniband/sw/rdmavt/qp.c | 6 ++-- drivers/input/misc/regulator-haptic.c | 2 +- drivers/md/dm-bufio.c | 10 +++--- drivers/md/dm-kcopyd.c | 4 +-- drivers/md/dm-stats.c | 36 +++++++++++----------- drivers/md/dm-switch.c | 2 +- drivers/md/dm-thin.c | 2 +- drivers/md/dm-verity-target.c | 2 +- drivers/md/dm.c | 4 +-- drivers/md/md.c | 2 +- drivers/md/raid5.c | 2 +- drivers/misc/mic/scif/scif_rb.c | 8 ++--- drivers/misc/mic/scif/scif_rma_list.c | 2 +- drivers/net/bonding/bond_alb.c | 2 +- drivers/net/bonding/bond_main.c | 6 ++-- drivers/net/ethernet/chelsio/cxgb4/sge.c | 4 +-- drivers/net/ethernet/emulex/benet/be_main.c | 2 +- drivers/net/ethernet/hisilicon/hip04_eth.c | 4 +-- drivers/net/ethernet/intel/i40e/i40e_debugfs.c | 4 +-- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 4 +-- drivers/net/ethernet/intel/i40e/i40e_ptp.c | 4 +-- drivers/net/ethernet/intel/igb/e1000_regs.h | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_common.h | 4 +-- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 8 ++--- drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c | 4 +-- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 2 +- drivers/net/ethernet/intel/ixgbevf/vf.h | 2 +- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 12 ++++---- drivers/net/ethernet/neterion/vxge/vxge-main.c | 2 +- drivers/net/ethernet/sfc/ef10.c | 10 +++--- drivers/net/ethernet/sfc/efx.c | 4 +-- drivers/net/ethernet/sfc/falcon/efx.c | 4 +-- drivers/net/ethernet/sfc/falcon/falcon.c | 4 +-- drivers/net/ethernet/sfc/falcon/farch.c | 8 ++--- drivers/net/ethernet/sfc/falcon/nic.h | 6 ++-- drivers/net/ethernet/sfc/falcon/tx.c | 6 ++-- drivers/net/ethernet/sfc/farch.c | 8 ++--- drivers/net/ethernet/sfc/nic.h | 6 ++-- drivers/net/ethernet/sfc/ptp.c | 10 +++--- drivers/net/ethernet/sfc/tx.c | 6 ++-- drivers/net/ethernet/sun/niu.c | 4 +-- drivers/net/tap.c | 2 +- drivers/net/tun.c | 4 +-- drivers/net/wireless/ath/ath5k/desc.c | 8 ++--- .../wireless/broadcom/brcm80211/brcmfmac/sdio.c | 2 +- drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 2 +- drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 4 +-- drivers/net/wireless/intel/iwlwifi/pcie/rx.c | 2 +- drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 10 +++--- drivers/net/wireless/mac80211_hwsim.c | 4 +-- drivers/scsi/qla2xxx/qla_target.c | 2 +- drivers/target/target_core_user.c | 2 +- drivers/usb/class/cdc-wdm.c | 2 +- drivers/usb/core/devio.c | 2 +- drivers/usb/core/sysfs.c | 4 +-- drivers/usb/gadget/udc/gr_udc.c | 4 +-- drivers/usb/host/ohci-hcd.c | 2 +- drivers/usb/host/uhci-hcd.h | 4 +-- drivers/vfio/vfio.c | 2 +- drivers/vhost/scsi.c | 2 +- fs/aio.c | 2 +- fs/buffer.c | 3 +- fs/crypto/keyinfo.c | 2 +- fs/direct-io.c | 2 +- fs/exec.c | 2 +- fs/fcntl.c | 2 +- fs/fs_pin.c | 4 +-- fs/fuse/dev.c | 2 +- fs/inode.c | 2 +- fs/namei.c | 4 +-- fs/namespace.c | 2 +- fs/nfs/dir.c | 8 ++--- fs/proc/array.c | 2 +- fs/proc_namespace.c | 2 +- fs/splice.c | 2 +- fs/userfaultfd.c | 8 ++--- fs/xfs/xfs_log_priv.h | 4 +-- include/linux/bitops.h | 4 +-- include/linux/dynamic_queue_limits.h | 2 +- include/linux/huge_mm.h | 2 +- include/linux/if_team.h | 2 +- include/linux/llist.h | 2 +- include/linux/pm_runtime.h | 2 +- include/net/ip_vs.h | 6 ++-- kernel/acct.c | 4 +-- kernel/events/core.c | 6 ++-- kernel/events/ring_buffer.c | 2 +- kernel/exit.c | 2 +- kernel/trace/ring_buffer.c | 2 +- kernel/trace/trace.h | 2 +- kernel/trace/trace_stack.c | 2 +- kernel/user_namespace.c | 2 +- lib/assoc_array.c | 20 ++++++------ lib/dynamic_queue_limits.c | 2 +- lib/llist.c | 2 +- lib/vsprintf.c | 4 +-- mm/huge_memory.c | 2 +- net/core/dev.c | 2 +- net/core/pktgen.c | 2 +- net/ipv4/inet_fragment.c | 2 +- net/ipv4/route.c | 2 +- net/ipv4/tcp_output.c | 2 +- net/ipv4/udp.c | 4 +-- net/ipv6/ip6_tunnel.c | 8 ++--- net/ipv6/udp.c | 4 +-- net/llc/llc_input.c | 4 +-- net/mac80211/sta_info.c | 2 +- net/netlabel/netlabel_calipso.c | 2 +- net/wireless/nl80211.c | 2 +- sound/firewire/amdtp-am824.c | 6 ++-- sound/firewire/amdtp-stream.c | 23 +++++++------- sound/firewire/amdtp-stream.h | 2 +- sound/firewire/digi00x/amdtp-dot.c | 6 ++-- sound/firewire/fireface/amdtp-ff.c | 4 +-- sound/firewire/fireface/ff-midi.c | 10 +++--- sound/firewire/fireface/ff-transaction.c | 8 ++--- sound/firewire/isight.c | 18 +++++------ sound/firewire/motu/amdtp-motu.c | 4 +-- sound/firewire/oxfw/oxfw-scs1x.c | 12 ++++---- sound/firewire/tascam/amdtp-tascam.c | 4 +-- sound/firewire/tascam/tascam-transaction.c | 6 ++-- sound/soc/xtensa/xtfpga-i2s.c | 6 ++-- sound/usb/bcd2000/bcd2000.c | 4 +-- tools/arch/x86/include/asm/atomic.h | 2 +- tools/include/asm-generic/atomic-gcc.h | 2 +- tools/perf/util/auxtrace.h | 4 +-- tools/perf/util/session.h | 2 +- virt/kvm/kvm_main.c | 2 +- 180 files changed, 383 insertions(+), 385 deletions(-) (limited to 'net/core/dev.c') diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index f46267153ec2..94cabe73664b 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -245,7 +245,7 @@ static void ipi_send_msg_one(int cpu, enum ipi_msg_type msg) * and read back old value */ do { - new = old = ACCESS_ONCE(*ipi_data_ptr); + new = old = READ_ONCE(*ipi_data_ptr); new |= 1U << msg; } while (cmpxchg(ipi_data_ptr, old, new) != old); diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index daa87212c9a1..77f50ae0aeb4 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -71,7 +71,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) while (lockval.tickets.next != lockval.tickets.owner) { wfe(); - lockval.tickets.owner = ACCESS_ONCE(lock->tickets.owner); + lockval.tickets.owner = READ_ONCE(lock->tickets.owner); } smp_mb(); diff --git a/arch/arm/mach-tegra/cpuidle-tegra20.c b/arch/arm/mach-tegra/cpuidle-tegra20.c index 76e4c83cd5c8..3f24addd7972 100644 --- a/arch/arm/mach-tegra/cpuidle-tegra20.c +++ b/arch/arm/mach-tegra/cpuidle-tegra20.c @@ -179,7 +179,7 @@ static int tegra20_idle_lp2_coupled(struct cpuidle_device *dev, bool entered_lp2 = false; if (tegra_pending_sgi()) - ACCESS_ONCE(abort_flag) = true; + WRITE_ONCE(abort_flag, true); cpuidle_coupled_parallel_barrier(dev, &abort_barrier); diff --git a/arch/arm/vdso/vgettimeofday.c b/arch/arm/vdso/vgettimeofday.c index 79214d5ff097..a9dd619c6c29 100644 --- a/arch/arm/vdso/vgettimeofday.c +++ b/arch/arm/vdso/vgettimeofday.c @@ -35,7 +35,7 @@ static notrace u32 __vdso_read_begin(const struct vdso_data *vdata) { u32 seq; repeat: - seq = ACCESS_ONCE(vdata->seq_count); + seq = READ_ONCE(vdata->seq_count); if (seq & 1) { cpu_relax(); goto repeat; diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h index 35b31884863b..e98775be112d 100644 --- a/arch/ia64/include/asm/spinlock.h +++ b/arch/ia64/include/asm/spinlock.h @@ -61,7 +61,7 @@ static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock) static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock) { - int tmp = ACCESS_ONCE(lock->lock); + int tmp = READ_ONCE(lock->lock); if (!(((tmp >> TICKET_SHIFT) ^ tmp) & TICKET_MASK)) return ia64_cmpxchg(acq, &lock->lock, tmp, tmp + 1, sizeof (tmp)) == tmp; @@ -73,19 +73,19 @@ static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) unsigned short *p = (unsigned short *)&lock->lock + 1, tmp; asm volatile ("ld2.bias %0=[%1]" : "=r"(tmp) : "r"(p)); - ACCESS_ONCE(*p) = (tmp + 2) & ~1; + WRITE_ONCE(*p, (tmp + 2) & ~1); } static inline int __ticket_spin_is_locked(arch_spinlock_t *lock) { - long tmp = ACCESS_ONCE(lock->lock); + long tmp = READ_ONCE(lock->lock); return !!(((tmp >> TICKET_SHIFT) ^ tmp) & TICKET_MASK); } static inline int __ticket_spin_is_contended(arch_spinlock_t *lock) { - long tmp = ACCESS_ONCE(lock->lock); + long tmp = READ_ONCE(lock->lock); return ((tmp - (tmp >> TICKET_SHIFT)) & TICKET_MASK) > 1; } diff --git a/arch/mips/include/asm/vdso.h b/arch/mips/include/asm/vdso.h index b7cd6cf77b83..91bf0c2c265c 100644 --- a/arch/mips/include/asm/vdso.h +++ b/arch/mips/include/asm/vdso.h @@ -99,7 +99,7 @@ static inline u32 vdso_data_read_begin(const union mips_vdso_data *data) u32 seq; while (true) { - seq = ACCESS_ONCE(data->seq_count); + seq = READ_ONCE(data->seq_count); if (likely(!(seq & 1))) { /* Paired with smp_wmb() in vdso_data_write_*(). */ smp_rmb(); diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c index 4655017f2377..1d2996cd58da 100644 --- a/arch/mips/kernel/pm-cps.c +++ b/arch/mips/kernel/pm-cps.c @@ -166,7 +166,7 @@ int cps_pm_enter_state(enum cps_pm_state state) nc_core_ready_count = nc_addr; /* Ensure ready_count is zero-initialised before the assembly runs */ - ACCESS_ONCE(*nc_core_ready_count) = 0; + WRITE_ONCE(*nc_core_ready_count, 0); coupled_barrier(&per_cpu(pm_barrier, core), online); /* Run the generated entry code */ diff --git a/arch/mn10300/kernel/mn10300-serial.c b/arch/mn10300/kernel/mn10300-serial.c index 7ecf69879e2d..d7ef1232a82a 100644 --- a/arch/mn10300/kernel/mn10300-serial.c +++ b/arch/mn10300/kernel/mn10300-serial.c @@ -543,7 +543,7 @@ static void mn10300_serial_receive_interrupt(struct mn10300_serial_port *port) try_again: /* pull chars out of the hat */ - ix = ACCESS_ONCE(port->rx_outp); + ix = READ_ONCE(port->rx_outp); if (CIRC_CNT(port->rx_inp, ix, MNSC_BUFFER_SIZE) == 0) { if (push && !tport->low_latency) tty_flip_buffer_push(tport); @@ -1724,7 +1724,7 @@ static int mn10300_serial_poll_get_char(struct uart_port *_port) if (mn10300_serial_int_tbl[port->rx_irq].port != NULL) { do { /* pull chars out of the hat */ - ix = ACCESS_ONCE(port->rx_outp); + ix = READ_ONCE(port->rx_outp); if (CIRC_CNT(port->rx_inp, ix, MNSC_BUFFER_SIZE) == 0) return NO_POLL_CHAR; diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 17b98a87e5e2..c57d4e8307f2 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -260,7 +260,7 @@ atomic64_set(atomic64_t *v, s64 i) static __inline__ s64 atomic64_read(const atomic64_t *v) { - return ACCESS_ONCE((v)->counter); + return READ_ONCE((v)->counter); } #define atomic64_inc(v) (atomic64_add( 1,(v))) diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c index 7a9cde0cfbd1..acd3206dfae3 100644 --- a/arch/powerpc/platforms/powernv/opal-msglog.c +++ b/arch/powerpc/platforms/powernv/opal-msglog.c @@ -43,7 +43,7 @@ ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count) if (!opal_memcons) return -ENODEV; - out_pos = be32_to_cpu(ACCESS_ONCE(opal_memcons->out_pos)); + out_pos = be32_to_cpu(READ_ONCE(opal_memcons->out_pos)); /* Now we've read out_pos, put a barrier in before reading the new * data it points to in conbuf. */ diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 9fa855f91e55..66f4160010ef 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -117,14 +117,14 @@ extern int _raw_write_trylock_retry(arch_rwlock_t *lp); static inline int arch_read_trylock_once(arch_rwlock_t *rw) { - int old = ACCESS_ONCE(rw->lock); + int old = READ_ONCE(rw->lock); return likely(old >= 0 && __atomic_cmpxchg_bool(&rw->lock, old, old + 1)); } static inline int arch_write_trylock_once(arch_rwlock_t *rw) { - int old = ACCESS_ONCE(rw->lock); + int old = READ_ONCE(rw->lock); return likely(old == 0 && __atomic_cmpxchg_bool(&rw->lock, 0, 0x80000000)); } @@ -211,7 +211,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw) int old; do { - old = ACCESS_ONCE(rw->lock); + old = READ_ONCE(rw->lock); } while (!__atomic_cmpxchg_bool(&rw->lock, old, old - 1)); } diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index b12663d653d8..34e30b9ea234 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -162,8 +162,8 @@ void _raw_read_lock_wait(arch_rwlock_t *rw) smp_yield_cpu(~owner); count = spin_retry; } - old = ACCESS_ONCE(rw->lock); - owner = ACCESS_ONCE(rw->owner); + old = READ_ONCE(rw->lock); + owner = READ_ONCE(rw->owner); if (old < 0) continue; if (__atomic_cmpxchg_bool(&rw->lock, old, old + 1)) @@ -178,7 +178,7 @@ int _raw_read_trylock_retry(arch_rwlock_t *rw) int old; while (count-- > 0) { - old = ACCESS_ONCE(rw->lock); + old = READ_ONCE(rw->lock); if (old < 0) continue; if (__atomic_cmpxchg_bool(&rw->lock, old, old + 1)) @@ -202,8 +202,8 @@ void _raw_write_lock_wait(arch_rwlock_t *rw, int prev) smp_yield_cpu(~owner); count = spin_retry; } - old = ACCESS_ONCE(rw->lock); - owner = ACCESS_ONCE(rw->owner); + old = READ_ONCE(rw->lock); + owner = READ_ONCE(rw->owner); smp_mb(); if (old >= 0) { prev = __RAW_LOCK(&rw->lock, 0x80000000, __RAW_OP_OR); @@ -230,8 +230,8 @@ void _raw_write_lock_wait(arch_rwlock_t *rw) smp_yield_cpu(~owner); count = spin_retry; } - old = ACCESS_ONCE(rw->lock); - owner = ACCESS_ONCE(rw->owner); + old = READ_ONCE(rw->lock); + owner = READ_ONCE(rw->owner); if (old >= 0 && __atomic_cmpxchg_bool(&rw->lock, old, old | 0x80000000)) prev = old; @@ -251,7 +251,7 @@ int _raw_write_trylock_retry(arch_rwlock_t *rw) int old; while (count-- > 0) { - old = ACCESS_ONCE(rw->lock); + old = READ_ONCE(rw->lock); if (old) continue; if (__atomic_cmpxchg_bool(&rw->lock, 0, 0x80000000)) diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index 7643e979e333..e2f398e9456c 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -31,7 +31,7 @@ void atomic_set(atomic_t *, int); #define atomic_set_release(v, i) atomic_set((v), (i)) -#define atomic_read(v) ACCESS_ONCE((v)->counter) +#define atomic_read(v) READ_ONCE((v)->counter) #define atomic_add(i, v) ((void)atomic_add_return( (int)(i), (v))) #define atomic_sub(i, v) ((void)atomic_add_return(-(int)(i), (v))) diff --git a/arch/tile/gxio/dma_queue.c b/arch/tile/gxio/dma_queue.c index baa60357f8ba..b7ba577d82ca 100644 --- a/arch/tile/gxio/dma_queue.c +++ b/arch/tile/gxio/dma_queue.c @@ -163,14 +163,14 @@ int __gxio_dma_queue_is_complete(__gxio_dma_queue_t *dma_queue, int64_t completion_slot, int update) { if (update) { - if (ACCESS_ONCE(dma_queue->hw_complete_count) > + if (READ_ONCE(dma_queue->hw_complete_count) > completion_slot) return 1; __gxio_dma_queue_update_credits(dma_queue); } - return ACCESS_ONCE(dma_queue->hw_complete_count) > completion_slot; + return READ_ONCE(dma_queue->hw_complete_count) > completion_slot; } EXPORT_SYMBOL_GPL(__gxio_dma_queue_is_complete); diff --git a/arch/tile/include/gxio/dma_queue.h b/arch/tile/include/gxio/dma_queue.h index b9e45e37649e..c8fd47edba30 100644 --- a/arch/tile/include/gxio/dma_queue.h +++ b/arch/tile/include/gxio/dma_queue.h @@ -121,7 +121,7 @@ static inline int64_t __gxio_dma_queue_reserve(__gxio_dma_queue_t *dma_queue, * if the result is LESS than "hw_complete_count". */ uint64_t complete; - complete = ACCESS_ONCE(dma_queue->hw_complete_count); + complete = READ_ONCE(dma_queue->hw_complete_count); slot |= (complete & 0xffffffffff000000); if (slot < complete) slot += 0x1000000; diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c index e1a078e6828e..d516d61751c2 100644 --- a/arch/tile/kernel/ptrace.c +++ b/arch/tile/kernel/ptrace.c @@ -255,7 +255,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, int do_syscall_trace_enter(struct pt_regs *regs) { - u32 work = ACCESS_ONCE(current_thread_info()->flags); + u32 work = READ_ONCE(current_thread_info()->flags); if ((work & _TIF_SYSCALL_TRACE) && tracehook_report_syscall_entry(regs)) { diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 03505ffbe1b6..eaa0ba66cf96 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -75,7 +75,7 @@ static long syscall_trace_enter(struct pt_regs *regs) if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) BUG_ON(regs != task_pt_regs(current)); - work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; + work = READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; if (unlikely(work & _TIF_SYSCALL_EMU)) emulated = true; diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index fa8dbfcf7ed3..11b13c4b43d5 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -318,7 +318,7 @@ int gettimeofday(struct timeval *, struct timezone *) notrace time_t __vdso_time(time_t *t) { /* This is atomic on x86 so we don't need any locks. */ - time_t result = ACCESS_ONCE(gtod->wall_time_sec); + time_t result = READ_ONCE(gtod->wall_time_sec); if (t) *t = result; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 589af1eec7c1..140d33288e78 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2118,7 +2118,7 @@ static int x86_pmu_event_init(struct perf_event *event) event->destroy(event); } - if (ACCESS_ONCE(x86_pmu.attr_rdpmc)) + if (READ_ONCE(x86_pmu.attr_rdpmc)) event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED; return err; diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index 022e59714562..53dd162576a8 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -48,7 +48,7 @@ static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s) unsigned ret; repeat: - ret = ACCESS_ONCE(s->seq); + ret = READ_ONCE(s->seq); if (unlikely(ret & 1)) { cpu_relax(); goto repeat; diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 9c4e7ba6870c..7d7715dde901 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -155,14 +155,14 @@ void init_espfix_ap(int cpu) page = cpu/ESPFIX_STACKS_PER_PAGE; /* Did another CPU already set this up? */ - stack_page = ACCESS_ONCE(espfix_pages[page]); + stack_page = READ_ONCE(espfix_pages[page]); if (likely(stack_page)) goto done; mutex_lock(&espfix_init_mutex); /* Did we race on the lock? */ - stack_page = ACCESS_ONCE(espfix_pages[page]); + stack_page = READ_ONCE(espfix_pages[page]); if (stack_page) goto unlock_done; @@ -200,7 +200,7 @@ void init_espfix_ap(int cpu) set_pte(&pte_p[n*PTE_STRIDE], pte); /* Job is done for this CPU and any CPU which shares this page */ - ACCESS_ONCE(espfix_pages[page]) = stack_page; + WRITE_ONCE(espfix_pages[page], stack_page); unlock_done: mutex_unlock(&espfix_init_mutex); diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 35aafc95e4b8..18bc9b51ac9b 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -105,7 +105,7 @@ static void nmi_max_handler(struct irq_work *w) { struct nmiaction *a = container_of(w, struct nmiaction, irq_work); int remainder_ns, decimal_msecs; - u64 whole_msecs = ACCESS_ONCE(a->max_duration); + u64 whole_msecs = READ_ONCE(a->max_duration); remainder_ns = do_div(whole_msecs, (1000 * 1000)); decimal_msecs = remainder_ns / 1000; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7a69cf053711..a119b361b8b7 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -443,7 +443,7 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) static u64 __get_spte_lockless(u64 *sptep) { - return ACCESS_ONCE(*sptep); + return READ_ONCE(*sptep); } #else union split_spte { @@ -4819,7 +4819,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, * If we don't have indirect shadow pages, it means no page is * write-protected, so we can exit simply. */ - if (!ACCESS_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) + if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) return; remote_flush = local_flush = false; diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c index ea67dc876316..01c1371f39f8 100644 --- a/arch/x86/kvm/page_track.c +++ b/arch/x86/kvm/page_track.c @@ -157,7 +157,7 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn, return false; index = gfn_to_index(gfn, slot->base_gfn, PT_PAGE_TABLE_LEVEL); - return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]); + return !!READ_ONCE(slot->arch.gfn_track[mode][index]); } void kvm_page_track_cleanup(struct kvm *kvm) diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 6083ba462f35..13b4f19b9131 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -547,7 +547,7 @@ int xen_alloc_p2m_entry(unsigned long pfn) if (p2m_top_mfn && pfn < MAX_P2M_PFN) { topidx = p2m_top_index(pfn); top_mfn_p = &p2m_top_mfn[topidx]; - mid_mfn = ACCESS_ONCE(p2m_top_mfn_p[topidx]); + mid_mfn = READ_ONCE(p2m_top_mfn_p[topidx]); BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p); diff --git a/arch/xtensa/platforms/xtfpga/lcd.c b/arch/xtensa/platforms/xtfpga/lcd.c index 4dc0c1b43f4b..2f7eb66c23ec 100644 --- a/arch/xtensa/platforms/xtfpga/lcd.c +++ b/arch/xtensa/platforms/xtfpga/lcd.c @@ -34,23 +34,23 @@ static void lcd_put_byte(u8 *addr, u8 data) { #ifdef CONFIG_XTFPGA_LCD_8BIT_ACCESS - ACCESS_ONCE(*addr) = data; + WRITE_ONCE(*addr, data); #else - ACCESS_ONCE(*addr) = data & 0xf0; - ACCESS_ONCE(*addr) = (data << 4) & 0xf0; + WRITE_ONCE(*addr, data & 0xf0); + WRITE_ONCE(*addr, (data << 4) & 0xf0); #endif } static int __init lcd_init(void) { - ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; + WRITE_ONCE(*LCD_INSTR_ADDR, LCD_DISPLAY_MODE8BIT); mdelay(5); - ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; + WRITE_ONCE(*LCD_INSTR_ADDR, LCD_DISPLAY_MODE8BIT); udelay(200); - ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; + WRITE_ONCE(*LCD_INSTR_ADDR, LCD_DISPLAY_MODE8BIT); udelay(50); #ifndef CONFIG_XTFPGA_LCD_8BIT_ACCESS - ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE4BIT; + WRITE_ONCE(*LCD_INSTR_ADDR, LCD_DISPLAY_MODE4BIT); udelay(50); lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_MODE4BIT); udelay(50); diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 6a9a0f03a67b..d822530e6aea 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -261,7 +261,7 @@ static inline bool stat_sample_valid(struct blk_rq_stat *stat) static u64 rwb_sync_issue_lat(struct rq_wb *rwb) { - u64 now, issue = ACCESS_ONCE(rwb->sync_issue); + u64 now, issue = READ_ONCE(rwb->sync_issue); if (!issue || !rwb->sync_cookie) return 0; diff --git a/drivers/base/core.c b/drivers/base/core.c index 12ebd055724c..4b8ba2a75a4d 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -668,7 +668,7 @@ const char *dev_driver_string(const struct device *dev) * so be careful about accessing it. dev->bus and dev->class should * never change once they are set, so they don't need special care. */ - drv = ACCESS_ONCE(dev->driver); + drv = READ_ONCE(dev->driver); return drv ? drv->name : (dev->bus ? dev->bus->name : (dev->class ? dev->class->name : "")); diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 7bcf80fa9ada..41d7c2b99f69 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -134,11 +134,11 @@ unsigned long pm_runtime_autosuspend_expiration(struct device *dev) if (!dev->power.use_autosuspend) goto out; - autosuspend_delay = ACCESS_ONCE(dev->power.autosuspend_delay); + autosuspend_delay = READ_ONCE(dev->power.autosuspend_delay); if (autosuspend_delay < 0) goto out; - last_busy = ACCESS_ONCE(dev->power.last_busy); + last_busy = READ_ONCE(dev->power.last_busy); elapsed = jiffies - last_busy; if (elapsed < 0) goto out; /* jiffies has wrapped around. */ diff --git a/drivers/char/random.c b/drivers/char/random.c index 8ad92707e45f..6c7ccac2679e 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -641,7 +641,7 @@ static void credit_entropy_bits(struct entropy_store *r, int nbits) return; retry: - entropy_count = orig = ACCESS_ONCE(r->entropy_count); + entropy_count = orig = READ_ONCE(r->entropy_count); if (nfrac < 0) { /* Debit */ entropy_count += nfrac; @@ -1265,7 +1265,7 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min, /* Can we pull enough? */ retry: - entropy_count = orig = ACCESS_ONCE(r->entropy_count); + entropy_count = orig = READ_ONCE(r->entropy_count); ibytes = nbytes; /* never pull more than available */ have_bytes = entropy_count >> (ENTROPY_SHIFT + 3); diff --git a/drivers/clocksource/bcm2835_timer.c b/drivers/clocksource/bcm2835_timer.c index 39e489a96ad7..60da2537bef9 100644 --- a/drivers/clocksource/bcm2835_timer.c +++ b/drivers/clocksource/bcm2835_timer.c @@ -71,7 +71,7 @@ static irqreturn_t bcm2835_time_interrupt(int irq, void *dev_id) if (readl_relaxed(timer->control) & timer->match_mask) { writel_relaxed(timer->match_mask, timer->control); - event_handler = ACCESS_ONCE(timer->evt.event_handler); + event_handler = READ_ONCE(timer->evt.event_handler); if (event_handler) event_handler(&timer->evt); return IRQ_HANDLED; diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c index d258953ff488..f4f258075b89 100644 --- a/drivers/crypto/caam/jr.c +++ b/drivers/crypto/caam/jr.c @@ -172,7 +172,7 @@ static void caam_jr_dequeue(unsigned long devarg) while (rd_reg32(&jrp->rregs->outring_used)) { - head = ACCESS_ONCE(jrp->head); + head = READ_ONCE(jrp->head); spin_lock(&jrp->outlock); @@ -341,7 +341,7 @@ int caam_jr_enqueue(struct device *dev, u32 *desc, spin_lock_bh(&jrp->inplock); head = jrp->head; - tail = ACCESS_ONCE(jrp->tail); + tail = READ_ONCE(jrp->tail); if (!rd_reg32(&jrp->rregs->inpring_avail) || CIRC_SPACE(head, tail, JOBR_DEPTH) <= 0) { diff --git a/drivers/crypto/nx/nx-842-powernv.c b/drivers/crypto/nx/nx-842-powernv.c index 874ddf5e9087..0f20f5ec9617 100644 --- a/drivers/crypto/nx/nx-842-powernv.c +++ b/drivers/crypto/nx/nx-842-powernv.c @@ -193,7 +193,7 @@ static int wait_for_csb(struct nx842_workmem *wmem, ktime_t start = wmem->start, now = ktime_get(); ktime_t timeout = ktime_add_ms(start, CSB_WAIT_MAX); - while (!(ACCESS_ONCE(csb->flags) & CSB_V)) { + while (!(READ_ONCE(csb->flags) & CSB_V)) { cpu_relax(); now = ktime_get(); if (ktime_after(now, timeout)) diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 8bf89267dc25..ccf52368a073 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -734,7 +734,7 @@ static unsigned int ar_search_last_active_buffer(struct ar_context *ctx, __le16 res_count, next_res_count; i = ar_first_buffer_index(ctx); - res_count = ACCESS_ONCE(ctx->descriptors[i].res_count); + res_count = READ_ONCE(ctx->descriptors[i].res_count); /* A buffer that is not yet completely filled must be the last one. */ while (i != last && res_count == 0) { @@ -742,8 +742,7 @@ static unsigned int ar_search_last_active_buffer(struct ar_context *ctx, /* Peek at the next descriptor. */ next_i = ar_next_buffer_index(i); rmb(); /* read descriptors in order */ - next_res_count = ACCESS_ONCE( - ctx->descriptors[next_i].res_count); + next_res_count = READ_ONCE(ctx->descriptors[next_i].res_count); /* * If the next descriptor is still empty, we must stop at this * descriptor. @@ -759,8 +758,7 @@ static unsigned int ar_search_last_active_buffer(struct ar_context *ctx, if (MAX_AR_PACKET_SIZE > PAGE_SIZE && i != last) { next_i = ar_next_buffer_index(next_i); rmb(); - next_res_count = ACCESS_ONCE( - ctx->descriptors[next_i].res_count); + next_res_count = READ_ONCE(ctx->descriptors[next_i].res_count); if (next_res_count != cpu_to_le16(PAGE_SIZE)) goto next_buffer_is_active; } @@ -2812,7 +2810,7 @@ static int handle_ir_buffer_fill(struct context *context, u32 buffer_dma; req_count = le16_to_cpu(last->req_count); - res_count = le16_to_cpu(ACCESS_ONCE(last->res_count)); + res_count = le16_to_cpu(READ_ONCE(last->res_count)); completed = req_count - res_count; buffer_dma = le32_to_cpu(last->data_address); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 333bad749067..303b5e099a98 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -260,7 +260,7 @@ static void amdgpu_fence_fallback(unsigned long arg) */ int amdgpu_fence_wait_empty(struct amdgpu_ring *ring) { - uint64_t seq = ACCESS_ONCE(ring->fence_drv.sync_seq); + uint64_t seq = READ_ONCE(ring->fence_drv.sync_seq); struct dma_fence *fence, **ptr; int r; @@ -300,7 +300,7 @@ unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring) amdgpu_fence_process(ring); emitted = 0x100000000ull; emitted -= atomic_read(&ring->fence_drv.last_seq); - emitted += ACCESS_ONCE(ring->fence_drv.sync_seq); + emitted += READ_ONCE(ring->fence_drv.sync_seq); return lower_32_bits(emitted); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 7171968f261e..6149a47fe63d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -788,11 +788,11 @@ static int amdgpu_debugfs_gem_bo_info(int id, void *ptr, void *data) seq_printf(m, "\t0x%08x: %12ld byte %s", id, amdgpu_bo_size(bo), placement); - offset = ACCESS_ONCE(bo->tbo.mem.start); + offset = READ_ONCE(bo->tbo.mem.start); if (offset != AMDGPU_BO_INVALID_OFFSET) seq_printf(m, " @ 0x%010Lx", offset); - pin_count = ACCESS_ONCE(bo->pin_count); + pin_count = READ_ONCE(bo->pin_count); if (pin_count) seq_printf(m, " pin count %d", pin_count); seq_printf(m, "\n"); diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index 38cea6fb25a8..a25f6c72f219 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -187,7 +187,7 @@ static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity) if (kfifo_is_empty(&entity->job_queue)) return false; - if (ACCESS_ONCE(entity->dependency)) + if (READ_ONCE(entity->dependency)) return false; return true; diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 3386452bd2f0..cf3deb283da5 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -451,7 +451,7 @@ int radeon_gem_busy_ioctl(struct drm_device *dev, void *data, else r = 0; - cur_placement = ACCESS_ONCE(robj->tbo.mem.mem_type); + cur_placement = READ_ONCE(robj->tbo.mem.mem_type); args->domain = radeon_mem_type_to_domain(cur_placement); drm_gem_object_put_unlocked(gobj); return r; @@ -481,7 +481,7 @@ int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data, r = ret; /* Flush HDP cache via MMIO if necessary */ - cur_placement = ACCESS_ONCE(robj->tbo.mem.mem_type); + cur_placement = READ_ONCE(robj->tbo.mem.mem_type); if (rdev->asic->mmio_hdp_flush && radeon_mem_type_to_domain(cur_placement) == RADEON_GEM_DOMAIN_VRAM) robj->rdev->asic->mmio_hdp_flush(rdev); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index a552e4ea5440..6ac094ee8983 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -904,7 +904,7 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv, if (unlikely(drm_is_render_client(file_priv))) require_exist = true; - if (ACCESS_ONCE(vmw_fpriv(file_priv)->locked_master)) { + if (READ_ONCE(vmw_fpriv(file_priv)->locked_master)) { DRM_ERROR("Locked master refused legacy " "surface reference.\n"); return -EACCES; diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index d9a1e9893136..97bea2e1aa6a 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -380,7 +380,7 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, if (sc->flags & SCF_FROZEN) { wait_event_interruptible_timeout( dd->event_queue, - !(ACCESS_ONCE(dd->flags) & HFI1_FROZEN), + !(READ_ONCE(dd->flags) & HFI1_FROZEN), msecs_to_jiffies(SEND_CTXT_HALT_TIMEOUT)); if (dd->flags & HFI1_FROZEN) return -ENOLCK; diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 7108a4b5e94c..75e740780285 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -1423,14 +1423,14 @@ retry: goto done; } /* copy from receiver cache line and recalculate */ - sc->alloc_free = ACCESS_ONCE(sc->free); + sc->alloc_free = READ_ONCE(sc->free); avail = (unsigned long)sc->credits - (sc->fill - sc->alloc_free); if (blocks > avail) { /* still no room, actively update */ sc_release_update(sc); - sc->alloc_free = ACCESS_ONCE(sc->free); + sc->alloc_free = READ_ONCE(sc->free); trycount++; goto retry; } @@ -1667,7 +1667,7 @@ void sc_release_update(struct send_context *sc) /* call sent buffer callbacks */ code = -1; /* code not yet set */ - head = ACCESS_ONCE(sc->sr_head); /* snapshot the head */ + head = READ_ONCE(sc->sr_head); /* snapshot the head */ tail = sc->sr_tail; while (head != tail) { pbuf = &sc->sr[tail].pbuf; diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c index b3291f0fde9a..a7fc664f0d4e 100644 --- a/drivers/infiniband/hw/hfi1/ruc.c +++ b/drivers/infiniband/hw/hfi1/ruc.c @@ -363,7 +363,7 @@ static void ruc_loopback(struct rvt_qp *sqp) again: smp_read_barrier_depends(); /* see post_one_send() */ - if (sqp->s_last == ACCESS_ONCE(sqp->s_head)) + if (sqp->s_last == READ_ONCE(sqp->s_head)) goto clr_busy; wqe = rvt_get_swqe_ptr(sqp, sqp->s_last); diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 6781bcdb10b3..08346d25441c 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -1725,7 +1725,7 @@ retry: swhead = sde->descq_head & sde->sdma_mask; /* this code is really bad for cache line trading */ - swtail = ACCESS_ONCE(sde->descq_tail) & sde->sdma_mask; + swtail = READ_ONCE(sde->descq_tail) & sde->sdma_mask; cnt = sde->descq_cnt; if (swhead < swtail) @@ -1872,7 +1872,7 @@ retry: if ((status & sde->idle_mask) && !idle_check_done) { u16 swtail; - swtail = ACCESS_ONCE(sde->descq_tail) & sde->sdma_mask; + swtail = READ_ONCE(sde->descq_tail) & sde->sdma_mask; if (swtail != hwhead) { hwhead = (u16)read_sde_csr(sde, SD(HEAD)); idle_check_done = 1; @@ -2222,7 +2222,7 @@ void sdma_seqfile_dump_sde(struct seq_file *s, struct sdma_engine *sde) u16 len; head = sde->descq_head & sde->sdma_mask; - tail = ACCESS_ONCE(sde->descq_tail) & sde->sdma_mask; + tail = READ_ONCE(sde->descq_tail) & sde->sdma_mask; seq_printf(s, SDE_FMT, sde->this_idx, sde->cpu, sdma_state_name(sde->state.current_state), @@ -3305,7 +3305,7 @@ int sdma_ahg_alloc(struct sdma_engine *sde) return -EINVAL; } while (1) { - nr = ffz(ACCESS_ONCE(sde->ahg_bits)); + nr = ffz(READ_ONCE(sde->ahg_bits)); if (nr > 31) { trace_hfi1_ahg_allocate(sde, -ENOSPC); return -ENOSPC; diff --git a/drivers/infiniband/hw/hfi1/sdma.h b/drivers/infiniband/hw/hfi1/sdma.h index 107011d8613b..374c59784950 100644 --- a/drivers/infiniband/hw/hfi1/sdma.h +++ b/drivers/infiniband/hw/hfi1/sdma.h @@ -445,7 +445,7 @@ static inline u16 sdma_descq_freecnt(struct sdma_engine *sde) { return sde->descq_cnt - (sde->descq_tail - - ACCESS_ONCE(sde->descq_head)) - 1; + READ_ONCE(sde->descq_head)) - 1; } static inline u16 sdma_descq_inprocess(struct sdma_engine *sde) diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c index 0b646173ca22..9a31c585427f 100644 --- a/drivers/infiniband/hw/hfi1/uc.c +++ b/drivers/infiniband/hw/hfi1/uc.c @@ -80,7 +80,7 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) goto bail; /* We are in the error state, flush the work request. */ smp_read_barrier_depends(); /* see post_one_send() */ - if (qp->s_last == ACCESS_ONCE(qp->s_head)) + if (qp->s_last == READ_ONCE(qp->s_head)) goto bail; /* If DMAs are in progress, we can't flush immediately. */ if (iowait_sdma_pending(&priv->s_iowait)) { @@ -121,7 +121,7 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) goto bail; /* Check if send work queue is empty. */ smp_read_barrier_depends(); /* see post_one_send() */ - if (qp->s_cur == ACCESS_ONCE(qp->s_head)) { + if (qp->s_cur == READ_ONCE(qp->s_head)) { clear_ahg(qp); goto bail; } diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c index 2ba74fdd6f15..7fec6b984e3e 100644 --- a/drivers/infiniband/hw/hfi1/ud.c +++ b/drivers/infiniband/hw/hfi1/ud.c @@ -487,7 +487,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) goto bail; /* We are in the error state, flush the work request. */ smp_read_barrier_depends(); /* see post_one_send */ - if (qp->s_last == ACCESS_ONCE(qp->s_head)) + if (qp->s_last == READ_ONCE(qp->s_head)) goto bail; /* If DMAs are in progress, we can't flush immediately. */ if (iowait_sdma_pending(&priv->s_iowait)) { @@ -501,7 +501,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) /* see post_one_send() */ smp_read_barrier_depends(); - if (qp->s_cur == ACCESS_ONCE(qp->s_head)) + if (qp->s_cur == READ_ONCE(qp->s_head)) goto bail; wqe = rvt_get_swqe_ptr(qp, qp->s_cur); diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index c0c0e0445cbf..8ec6e8a8d6f7 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -276,7 +276,7 @@ int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd, /* Wait until all requests have been freed. */ wait_event_interruptible( pq->wait, - (ACCESS_ONCE(pq->state) == SDMA_PKT_Q_INACTIVE)); + (READ_ONCE(pq->state) == SDMA_PKT_Q_INACTIVE)); kfree(pq->reqs); kfree(pq->req_in_use); kmem_cache_destroy(pq->txreq_cache); @@ -591,7 +591,7 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, if (ret != -EBUSY) { req->status = ret; WRITE_ONCE(req->has_error, 1); - if (ACCESS_ONCE(req->seqcomp) == + if (READ_ONCE(req->seqcomp) == req->seqsubmitted - 1) goto free_req; return ret; @@ -825,7 +825,7 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts) */ if (req->data_len) { iovec = &req->iovs[req->iov_idx]; - if (ACCESS_ONCE(iovec->offset) == iovec->iov.iov_len) { + if (READ_ONCE(iovec->offset) == iovec->iov.iov_len) { if (++req->iov_idx == req->data_iovs) { ret = -EFAULT; goto free_txreq; @@ -1390,7 +1390,7 @@ static void user_sdma_txreq_cb(struct sdma_txreq *txreq, int status) } else { if (status != SDMA_TXREQ_S_OK) req->status = status; - if (req->seqcomp == (ACCESS_ONCE(req->seqsubmitted) - 1) && + if (req->seqcomp == (READ_ONCE(req->seqsubmitted) - 1) && (READ_ONCE(req->done) || READ_ONCE(req->has_error))) { user_sdma_free_request(req, false); diff --git a/drivers/infiniband/hw/qib/qib_ruc.c b/drivers/infiniband/hw/qib/qib_ruc.c index 53efbb0b40c4..9a37e844d4c8 100644 --- a/drivers/infiniband/hw/qib/qib_ruc.c +++ b/drivers/infiniband/hw/qib/qib_ruc.c @@ -368,7 +368,7 @@ static void qib_ruc_loopback(struct rvt_qp *sqp) again: smp_read_barrier_depends(); /* see post_one_send() */ - if (sqp->s_last == ACCESS_ONCE(sqp->s_head)) + if (sqp->s_last == READ_ONCE(sqp->s_head)) goto clr_busy; wqe = rvt_get_swqe_ptr(sqp, sqp->s_last); diff --git a/drivers/infiniband/hw/qib/qib_uc.c b/drivers/infiniband/hw/qib/qib_uc.c index 498e2202e72c..bddcc37ace44 100644 --- a/drivers/infiniband/hw/qib/qib_uc.c +++ b/drivers/infiniband/hw/qib/qib_uc.c @@ -61,7 +61,7 @@ int qib_make_uc_req(struct rvt_qp *qp, unsigned long *flags) goto bail; /* We are in the error state, flush the work request. */ smp_read_barrier_depends(); /* see post_one_send() */ - if (qp->s_last == ACCESS_ONCE(qp->s_head)) + if (qp->s_last == READ_ONCE(qp->s_head)) goto bail; /* If DMAs are in progress, we can't flush immediately. */ if (atomic_read(&priv->s_dma_busy)) { @@ -91,7 +91,7 @@ int qib_make_uc_req(struct rvt_qp *qp, unsigned long *flags) goto bail; /* Check if send work queue is empty. */ smp_read_barrier_depends(); /* see post_one_send() */ - if (qp->s_cur == ACCESS_ONCE(qp->s_head)) + if (qp->s_cur == READ_ONCE(qp->s_head)) goto bail; /* * Start a new request. diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c index be4907453ac4..15962ed193ce 100644 --- a/drivers/infiniband/hw/qib/qib_ud.c +++ b/drivers/infiniband/hw/qib/qib_ud.c @@ -253,7 +253,7 @@ int qib_make_ud_req(struct rvt_qp *qp, unsigned long *flags) goto bail; /* We are in the error state, flush the work request. */ smp_read_barrier_depends(); /* see post_one_send */ - if (qp->s_last == ACCESS_ONCE(qp->s_head)) + if (qp->s_last == READ_ONCE(qp->s_head)) goto bail; /* If DMAs are in progress, we can't flush immediately. */ if (atomic_read(&priv->s_dma_busy)) { @@ -267,7 +267,7 @@ int qib_make_ud_req(struct rvt_qp *qp, unsigned long *flags) /* see post_one_send() */ smp_read_barrier_depends(); - if (qp->s_cur == ACCESS_ONCE(qp->s_head)) + if (qp->s_cur == READ_ONCE(qp->s_head)) goto bail; wqe = rvt_get_swqe_ptr(qp, qp->s_cur); diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 22df09ae809e..b670cb9d2006 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -1073,7 +1073,7 @@ int rvt_error_qp(struct rvt_qp *qp, enum ib_wc_status err) rdi->driver_f.notify_error_qp(qp); /* Schedule the sending tasklet to drain the send work queue. */ - if (ACCESS_ONCE(qp->s_last) != qp->s_head) + if (READ_ONCE(qp->s_last) != qp->s_head) rdi->driver_f.schedule_send(qp); rvt_clear_mr_refs(qp, 0); @@ -1686,7 +1686,7 @@ static inline int rvt_qp_is_avail( if (likely(qp->s_avail)) return 0; smp_read_barrier_depends(); /* see rc.c */ - slast = ACCESS_ONCE(qp->s_last); + slast = READ_ONCE(qp->s_last); if (qp->s_head >= slast) avail = qp->s_size - (qp->s_head - slast); else @@ -1917,7 +1917,7 @@ int rvt_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, * ahead and kick the send engine into gear. Otherwise we will always * just schedule the send to happen later. */ - call_send = qp->s_head == ACCESS_ONCE(qp->s_last) && !wr->next; + call_send = qp->s_head == READ_ONCE(qp->s_last) && !wr->next; for (; wr; wr = wr->next) { err = rvt_post_one_wr(qp, wr, &call_send); diff --git a/drivers/input/misc/regulator-haptic.c b/drivers/input/misc/regulator-haptic.c index 2e8f801932be..a1db1e5040dc 100644 --- a/drivers/input/misc/regulator-haptic.c +++ b/drivers/input/misc/regulator-haptic.c @@ -233,7 +233,7 @@ static int __maybe_unused regulator_haptic_resume(struct device *dev) haptic->suspended = false; - magnitude = ACCESS_ONCE(haptic->magnitude); + magnitude = READ_ONCE(haptic->magnitude); if (magnitude) regulator_haptic_set_voltage(haptic, magnitude); diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index d216a8f7bc22..33bb074d6941 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -347,7 +347,7 @@ static void __cache_size_refresh(void) BUG_ON(!mutex_is_locked(&dm_bufio_clients_lock)); BUG_ON(dm_bufio_client_count < 0); - dm_bufio_cache_size_latch = ACCESS_ONCE(dm_bufio_cache_size); + dm_bufio_cache_size_latch = READ_ONCE(dm_bufio_cache_size); /* * Use default if set to 0 and report the actual cache size used. @@ -960,7 +960,7 @@ static void __get_memory_limit(struct dm_bufio_client *c, { unsigned long buffers; - if (unlikely(ACCESS_ONCE(dm_bufio_cache_size) != dm_bufio_cache_size_latch)) { + if (unlikely(READ_ONCE(dm_bufio_cache_size) != dm_bufio_cache_size_latch)) { if (mutex_trylock(&dm_bufio_clients_lock)) { __cache_size_refresh(); mutex_unlock(&dm_bufio_clients_lock); @@ -1600,7 +1600,7 @@ static bool __try_evict_buffer(struct dm_buffer *b, gfp_t gfp) static unsigned long get_retain_buffers(struct dm_bufio_client *c) { - unsigned long retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes); + unsigned long retain_bytes = READ_ONCE(dm_bufio_retain_bytes); return retain_bytes >> (c->sectors_per_block_bits + SECTOR_SHIFT); } @@ -1647,7 +1647,7 @@ dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { struct dm_bufio_client *c = container_of(shrink, struct dm_bufio_client, shrinker); - return ACCESS_ONCE(c->n_buffers[LIST_CLEAN]) + ACCESS_ONCE(c->n_buffers[LIST_DIRTY]); + return READ_ONCE(c->n_buffers[LIST_CLEAN]) + READ_ONCE(c->n_buffers[LIST_DIRTY]); } /* @@ -1818,7 +1818,7 @@ EXPORT_SYMBOL_GPL(dm_bufio_set_sector_offset); static unsigned get_max_age_hz(void) { - unsigned max_age = ACCESS_ONCE(dm_bufio_max_age); + unsigned max_age = READ_ONCE(dm_bufio_max_age); if (max_age > UINT_MAX / HZ) max_age = UINT_MAX / HZ; diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index cf2c67e35eaf..eb45cc3df31d 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -107,7 +107,7 @@ static void io_job_start(struct dm_kcopyd_throttle *t) try_again: spin_lock_irq(&throttle_spinlock); - throttle = ACCESS_ONCE(t->throttle); + throttle = READ_ONCE(t->throttle); if (likely(throttle >= 100)) goto skip_limit; @@ -157,7 +157,7 @@ static void io_job_finish(struct dm_kcopyd_throttle *t) t->num_io_jobs--; - if (likely(ACCESS_ONCE(t->throttle) >= 100)) + if (likely(READ_ONCE(t->throttle) >= 100)) goto skip_limit; if (!t->num_io_jobs) { diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index 6028d8247f58..a1a5eec783cc 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -431,7 +431,7 @@ do_sync_free: synchronize_rcu_expedited(); dm_stat_free(&s->rcu_head); } else { - ACCESS_ONCE(dm_stat_need_rcu_barrier) = 1; + WRITE_ONCE(dm_stat_need_rcu_barrier, 1); call_rcu(&s->rcu_head, dm_stat_free); } return 0; @@ -639,12 +639,12 @@ void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw, */ last = raw_cpu_ptr(stats->last); stats_aux->merged = - (bi_sector == (ACCESS_ONCE(last->last_sector) && + (bi_sector == (READ_ONCE(last->last_sector) && ((bi_rw == WRITE) == - (ACCESS_ONCE(last->last_rw) == WRITE)) + (READ_ONCE(last->last_rw) == WRITE)) )); - ACCESS_ONCE(last->last_sector) = end_sector; - ACCESS_ONCE(last->last_rw) = bi_rw; + WRITE_ONCE(last->last_sector, end_sector); + WRITE_ONCE(last->last_rw, bi_rw); } rcu_read_lock(); @@ -693,22 +693,22 @@ static void __dm_stat_init_temporary_percpu_totals(struct dm_stat_shared *shared for_each_possible_cpu(cpu) { p = &s->stat_percpu[cpu][x]; - shared->tmp.sectors[READ] += ACCESS_ONCE(p->sectors[READ]); - shared->tmp.sectors[WRITE] += ACCESS_ONCE(p->sectors[WRITE]); - shared->tmp.ios[READ] += ACCESS_ONCE(p->ios[READ]); - shared->tmp.ios[WRITE] += ACCESS_ONCE(p->ios[WRITE]); - shared->tmp.merges[READ] += ACCESS_ONCE(p->merges[READ]); - shared->tmp.merges[WRITE] += ACCESS_ONCE(p->merges[WRITE]); - shared->tmp.ticks[READ] += ACCESS_ONCE(p->ticks[READ]); - shared->tmp.ticks[WRITE] += ACCESS_ONCE(p->ticks[WRITE]); - shared->tmp.io_ticks[READ] += ACCESS_ONCE(p->io_ticks[READ]); - shared->tmp.io_ticks[WRITE] += ACCESS_ONCE(p->io_ticks[WRITE]); - shared->tmp.io_ticks_total += ACCESS_ONCE(p->io_ticks_total); - shared->tmp.time_in_queue += ACCESS_ONCE(p->time_in_queue); + shared->tmp.sectors[READ] += READ_ONCE(p->sectors[READ]); + shared->tmp.sectors[WRITE] += READ_ONCE(p->sectors[WRITE]); + shared->tmp.ios[READ] += READ_ONCE(p->ios[READ]); + shared->tmp.ios[WRITE] += READ_ONCE(p->ios[WRITE]); + shared->tmp.merges[READ] += READ_ONCE(p->merges[READ]); + shared->tmp.merges[WRITE] += READ_ONCE(p->merges[WRITE]); + shared->tmp.ticks[READ] += READ_ONCE(p->ticks[READ]); + shared->tmp.ticks[WRITE] += READ_ONCE(p->ticks[WRITE]); + shared->tmp.io_ticks[READ] += READ_ONCE(p->io_ticks[READ]); + shared->tmp.io_ticks[WRITE] += READ_ONCE(p->io_ticks[WRITE]); + shared->tmp.io_ticks_total += READ_ONCE(p->io_ticks_total); + shared->tmp.time_in_queue += READ_ONCE(p->time_in_queue); if (s->n_histogram_entries) { unsigned i; for (i = 0; i < s->n_histogram_entries + 1; i++) - shared->tmp.histogram[i] += ACCESS_ONCE(p->histogram[i]); + shared->tmp.histogram[i] += READ_ONCE(p->histogram[i]); } } } diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c index 4c8de1ff78ca..8d0ba879777e 100644 --- a/drivers/md/dm-switch.c +++ b/drivers/md/dm-switch.c @@ -144,7 +144,7 @@ static unsigned switch_region_table_read(struct switch_ctx *sctx, unsigned long switch_get_position(sctx, region_nr, ®ion_index, &bit); - return (ACCESS_ONCE(sctx->region_table[region_index]) >> bit) & + return (READ_ONCE(sctx->region_table[region_index]) >> bit) & ((1 << sctx->region_table_entry_bits) - 1); } diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 1e25705209c2..89e5dff9b4cf 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2431,7 +2431,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) struct pool_c *pt = pool->ti->private; bool needs_check = dm_pool_metadata_needs_check(pool->pmd); enum pool_mode old_mode = get_pool_mode(pool); - unsigned long no_space_timeout = ACCESS_ONCE(no_space_timeout_secs) * HZ; + unsigned long no_space_timeout = READ_ONCE(no_space_timeout_secs) * HZ; /* * Never allow the pool to transition to PM_WRITE mode if user diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index bda3caca23ca..fba93237a780 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -589,7 +589,7 @@ static void verity_prefetch_io(struct work_struct *work) verity_hash_at_level(v, pw->block, i, &hash_block_start, NULL); verity_hash_at_level(v, pw->block + pw->n_blocks - 1, i, &hash_block_end, NULL); if (!i) { - unsigned cluster = ACCESS_ONCE(dm_verity_prefetch_cluster); + unsigned cluster = READ_ONCE(dm_verity_prefetch_cluster); cluster >>= v->data_dev_block_bits; if (unlikely(!cluster)) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 4be85324f44d..8aaffa19b29a 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -114,7 +114,7 @@ static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS; static int __dm_get_module_param_int(int *module_param, int min, int max) { - int param = ACCESS_ONCE(*module_param); + int param = READ_ONCE(*module_param); int modified_param = 0; bool modified = true; @@ -136,7 +136,7 @@ static int __dm_get_module_param_int(int *module_param, int min, int max) unsigned __dm_get_module_param(unsigned *module_param, unsigned def, unsigned max) { - unsigned param = ACCESS_ONCE(*module_param); + unsigned param = READ_ONCE(*module_param); unsigned modified_param = 0; if (!param) diff --git a/drivers/md/md.c b/drivers/md/md.c index 0ff1bbf6c90e..447ddcbc9566 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2651,7 +2651,7 @@ state_show(struct md_rdev *rdev, char *page) { char *sep = ","; size_t len = 0; - unsigned long flags = ACCESS_ONCE(rdev->flags); + unsigned long flags = READ_ONCE(rdev->flags); if (test_bit(Faulty, &flags) || (!test_bit(ExternalBbl, &flags) && diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 928e24a07133..7d9a50eed9db 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6072,7 +6072,7 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n */ rcu_read_lock(); for (i = 0; i < conf->raid_disks; i++) { - struct md_rdev *rdev = ACCESS_ONCE(conf->disks[i].rdev); + struct md_rdev *rdev = READ_ONCE(conf->disks[i].rdev); if (rdev == NULL || test_bit(Faulty, &rdev->flags)) still_degraded = 1; diff --git a/drivers/misc/mic/scif/scif_rb.c b/drivers/misc/mic/scif/scif_rb.c index 637cc4686742..b665757ca89a 100644 --- a/drivers/misc/mic/scif/scif_rb.c +++ b/drivers/misc/mic/scif/scif_rb.c @@ -138,7 +138,7 @@ void scif_rb_commit(struct scif_rb *rb) * the read barrier in scif_rb_count(..) */ wmb(); - ACCESS_ONCE(*rb->write_ptr) = rb->current_write_offset; + WRITE_ONCE(*rb->write_ptr, rb->current_write_offset); #ifdef CONFIG_INTEL_MIC_CARD /* * X100 Si bug: For the case where a Core is performing an EXT_WR @@ -147,7 +147,7 @@ void scif_rb_commit(struct scif_rb *rb) * This way, if ordering is violated for the Interrupt Message, it will * fall just behind the first Posted associated with the first EXT_WR. */ - ACCESS_ONCE(*rb->write_ptr) = rb->current_write_offset; + WRITE_ONCE(*rb->write_ptr, rb->current_write_offset); #endif } @@ -210,7 +210,7 @@ void scif_rb_update_read_ptr(struct scif_rb *rb) * scif_rb_space(..) */ mb(); - ACCESS_ONCE(*rb->read_ptr) = new_offset; + WRITE_ONCE(*rb->read_ptr, new_offset); #ifdef CONFIG_INTEL_MIC_CARD /* * X100 Si Bug: For the case where a Core is performing an EXT_WR @@ -219,7 +219,7 @@ void scif_rb_update_read_ptr(struct scif_rb *rb) * This way, if ordering is violated for the Interrupt Message, it will * fall just behind the first Posted associated with the first EXT_WR. */ - ACCESS_ONCE(*rb->read_ptr) = new_offset; + WRITE_ONCE(*rb->read_ptr, new_offset); #endif } diff --git a/drivers/misc/mic/scif/scif_rma_list.c b/drivers/misc/mic/scif/scif_rma_list.c index e1ef8daedd5a..a036dbb4101e 100644 --- a/drivers/misc/mic/scif/scif_rma_list.c +++ b/drivers/misc/mic/scif/scif_rma_list.c @@ -277,7 +277,7 @@ retry: * Need to restart list traversal if there has been * an asynchronous list entry deletion. */ - if (ACCESS_ONCE(ep->rma_info.async_list_del)) + if (READ_ONCE(ep->rma_info.async_list_del)) goto retry; } mutex_unlock(&ep->rma_info.rma_lock); diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index c02cc817a490..1ed9529e7bd1 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1378,7 +1378,7 @@ int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev) unsigned int count; slaves = rcu_dereference(bond->slave_arr); - count = slaves ? ACCESS_ONCE(slaves->count) : 0; + count = slaves ? READ_ONCE(slaves->count) : 0; if (likely(count)) tx_slave = slaves->arr[hash_index % count]; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c99dc59d729b..af51b90cecbb 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1167,7 +1167,7 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) slave = bond_slave_get_rcu(skb->dev); bond = slave->bond; - recv_probe = ACCESS_ONCE(bond->recv_probe); + recv_probe = READ_ONCE(bond->recv_probe); if (recv_probe) { ret = recv_probe(skb, bond, slave); if (ret == RX_HANDLER_CONSUMED) { @@ -3810,7 +3810,7 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev else bond_xmit_slave_id(bond, skb, 0); } else { - int slave_cnt = ACCESS_ONCE(bond->slave_cnt); + int slave_cnt = READ_ONCE(bond->slave_cnt); if (likely(slave_cnt)) { slave_id = bond_rr_gen_slave_id(bond); @@ -3972,7 +3972,7 @@ static int bond_3ad_xor_xmit(struct sk_buff *skb, struct net_device *dev) unsigned int count; slaves = rcu_dereference(bond->slave_arr); - count = slaves ? ACCESS_ONCE(slaves->count) : 0; + count = slaves ? READ_ONCE(slaves->count) : 0; if (likely(count)) { slave = slaves->arr[bond_xmit_hash(bond, skb) % count]; bond_dev_queue_xmit(bond, skb, slave->dev); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 4ef68f69b58c..43f52a8fe708 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -405,7 +405,7 @@ void free_tx_desc(struct adapter *adap, struct sge_txq *q, */ static inline int reclaimable(const struct sge_txq *q) { - int hw_cidx = ntohs(ACCESS_ONCE(q->stat->cidx)); + int hw_cidx = ntohs(READ_ONCE(q->stat->cidx)); hw_cidx -= q->cidx; return hw_cidx < 0 ? hw_cidx + q->size : hw_cidx; } @@ -1375,7 +1375,7 @@ out_free: dev_kfree_skb_any(skb); */ static inline void reclaim_completed_tx_imm(struct sge_txq *q) { - int hw_cidx = ntohs(ACCESS_ONCE(q->stat->cidx)); + int hw_cidx = ntohs(READ_ONCE(q->stat->cidx)); int reclaim = hw_cidx - q->cidx; if (reclaim < 0) diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 0e3d9f39a807..c6e859a27ee6 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -605,7 +605,7 @@ static void accumulate_16bit_val(u32 *acc, u16 val) if (wrapped) newacc += 65536; - ACCESS_ONCE(*acc) = newacc; + WRITE_ONCE(*acc, newacc); } static void populate_erx_stats(struct be_adapter *adapter, diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 0cec06bec63e..340e28211135 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -373,7 +373,7 @@ static int hip04_tx_reclaim(struct net_device *ndev, bool force) unsigned int count; smp_rmb(); - count = tx_count(ACCESS_ONCE(priv->tx_head), tx_tail); + count = tx_count(READ_ONCE(priv->tx_head), tx_tail); if (count == 0) goto out; @@ -431,7 +431,7 @@ static int hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) dma_addr_t phys; smp_rmb(); - count = tx_count(tx_head, ACCESS_ONCE(priv->tx_tail)); + count = tx_count(tx_head, READ_ONCE(priv->tx_tail)); if (count == (TX_DESC_NUM - 1)) { netif_stop_queue(ndev); return NETDEV_TX_BUSY; diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 8f326f87a815..2cb9539c931e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -264,7 +264,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) vsi->rx_buf_failed, vsi->rx_page_failed); rcu_read_lock(); for (i = 0; i < vsi->num_queue_pairs; i++) { - struct i40e_ring *rx_ring = ACCESS_ONCE(vsi->rx_rings[i]); + struct i40e_ring *rx_ring = READ_ONCE(vsi->rx_rings[i]); if (!rx_ring) continue; @@ -320,7 +320,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) ITR_IS_DYNAMIC(rx_ring->rx_itr_setting) ? "dynamic" : "fixed"); } for (i = 0; i < vsi->num_queue_pairs; i++) { - struct i40e_ring *tx_ring = ACCESS_ONCE(vsi->tx_rings[i]); + struct i40e_ring *tx_ring = READ_ONCE(vsi->tx_rings[i]); if (!tx_ring) continue; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 05e89864f781..e9e04a485e0a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -1570,7 +1570,7 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, } rcu_read_lock(); for (j = 0; j < vsi->num_queue_pairs; j++) { - tx_ring = ACCESS_ONCE(vsi->tx_rings[j]); + tx_ring = READ_ONCE(vsi->tx_rings[j]); if (!tx_ring) continue; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 6498da8806cb..de1fcac7834d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -455,7 +455,7 @@ static void i40e_get_netdev_stats_struct(struct net_device *netdev, u64 bytes, packets; unsigned int start; - tx_ring = ACCESS_ONCE(vsi->tx_rings[i]); + tx_ring = READ_ONCE(vsi->tx_rings[i]); if (!tx_ring) continue; i40e_get_netdev_stats_struct_tx(tx_ring, stats); @@ -791,7 +791,7 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) rcu_read_lock(); for (q = 0; q < vsi->num_queue_pairs; q++) { /* locate Tx ring */ - p = ACCESS_ONCE(vsi->tx_rings[q]); + p = READ_ONCE(vsi->tx_rings[q]); do { start = u64_stats_fetch_begin_irq(&p->syncp); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index d8456c381c99..97381238eb7c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -130,7 +130,7 @@ static int i40e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) } smp_mb(); /* Force any pending update before accessing. */ - adj = ACCESS_ONCE(pf->ptp_base_adj); + adj = READ_ONCE(pf->ptp_base_adj); freq = adj; freq *= ppb; @@ -499,7 +499,7 @@ void i40e_ptp_set_increment(struct i40e_pf *pf) wr32(hw, I40E_PRTTSYN_INC_H, incval >> 32); /* Update the base adjustement value. */ - ACCESS_ONCE(pf->ptp_base_adj) = incval; + WRITE_ONCE(pf->ptp_base_adj, incval); smp_mb(); /* Force the above update. */ } diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h index 58adbf234e07..31a3f09df9f7 100644 --- a/drivers/net/ethernet/intel/igb/e1000_regs.h +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -375,7 +375,7 @@ u32 igb_rd32(struct e1000_hw *hw, u32 reg); /* write operations, indexed using DWORDS */ #define wr32(reg, val) \ do { \ - u8 __iomem *hw_addr = ACCESS_ONCE((hw)->hw_addr); \ + u8 __iomem *hw_addr = READ_ONCE((hw)->hw_addr); \ if (!E1000_REMOVED(hw_addr)) \ writel((val), &hw_addr[(reg)]); \ } while (0) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index fd4a46b03cc8..6bccc2be2b91 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -750,7 +750,7 @@ static void igb_cache_ring_register(struct igb_adapter *adapter) u32 igb_rd32(struct e1000_hw *hw, u32 reg) { struct igb_adapter *igb = container_of(hw, struct igb_adapter, hw); - u8 __iomem *hw_addr = ACCESS_ONCE(hw->hw_addr); + u8 __iomem *hw_addr = READ_ONCE(hw->hw_addr); u32 value = 0; if (E1000_REMOVED(hw_addr)) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h index e083732adf64..a01409e2e06c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h @@ -161,7 +161,7 @@ static inline bool ixgbe_removed(void __iomem *addr) static inline void ixgbe_write_reg(struct ixgbe_hw *hw, u32 reg, u32 value) { - u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); if (ixgbe_removed(reg_addr)) return; @@ -180,7 +180,7 @@ static inline void writeq(u64 val, void __iomem *addr) static inline void ixgbe_write_reg64(struct ixgbe_hw *hw, u32 reg, u64 value) { - u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); if (ixgbe_removed(reg_addr)) return; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 4d76afd13868..2224e691ee07 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -380,7 +380,7 @@ static void ixgbe_check_remove(struct ixgbe_hw *hw, u32 reg) */ u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg) { - u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); u32 value; if (ixgbe_removed(reg_addr)) @@ -8630,7 +8630,7 @@ static void ixgbe_get_stats64(struct net_device *netdev, rcu_read_lock(); for (i = 0; i < adapter->num_rx_queues; i++) { - struct ixgbe_ring *ring = ACCESS_ONCE(adapter->rx_ring[i]); + struct ixgbe_ring *ring = READ_ONCE(adapter->rx_ring[i]); u64 bytes, packets; unsigned int start; @@ -8646,12 +8646,12 @@ static void ixgbe_get_stats64(struct net_device *netdev, } for (i = 0; i < adapter->num_tx_queues; i++) { - struct ixgbe_ring *ring = ACCESS_ONCE(adapter->tx_ring[i]); + struct ixgbe_ring *ring = READ_ONCE(adapter->tx_ring[i]); ixgbe_get_ring_stats64(stats, ring); } for (i = 0; i < adapter->num_xdp_queues; i++) { - struct ixgbe_ring *ring = ACCESS_ONCE(adapter->xdp_ring[i]); + struct ixgbe_ring *ring = READ_ONCE(adapter->xdp_ring[i]); ixgbe_get_ring_stats64(stats, ring); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 86d6924a2b71..ae312c45696a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -378,7 +378,7 @@ static int ixgbe_ptp_adjfreq_82599(struct ptp_clock_info *ptp, s32 ppb) } smp_mb(); - incval = ACCESS_ONCE(adapter->base_incval); + incval = READ_ONCE(adapter->base_incval); freq = incval; freq *= ppb; @@ -1159,7 +1159,7 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) } /* update the base incval used to calculate frequency adjustment */ - ACCESS_ONCE(adapter->base_incval) = incval; + WRITE_ONCE(adapter->base_incval, incval); smp_mb(); /* need lock to prevent incorrect read while modifying cyclecounter */ diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 032f8ac06357..cacb30682434 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -164,7 +164,7 @@ static void ixgbevf_check_remove(struct ixgbe_hw *hw, u32 reg) u32 ixgbevf_read_reg(struct ixgbe_hw *hw, u32 reg) { - u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); u32 value; if (IXGBE_REMOVED(reg_addr)) diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.h b/drivers/net/ethernet/intel/ixgbevf/vf.h index 04d8d4ee4f04..c651fefcc3d2 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.h +++ b/drivers/net/ethernet/intel/ixgbevf/vf.h @@ -182,7 +182,7 @@ struct ixgbevf_info { static inline void ixgbe_write_reg(struct ixgbe_hw *hw, u32 reg, u32 value) { - u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); if (IXGBE_REMOVED(reg_addr)) return; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 8a32a8f7f9c0..3541a7f9d12e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -414,8 +414,8 @@ bool mlx4_en_process_tx_cq(struct net_device *dev, index = cons_index & size_mask; cqe = mlx4_en_get_cqe(buf, index, priv->cqe_size) + factor; - last_nr_txbb = ACCESS_ONCE(ring->last_nr_txbb); - ring_cons = ACCESS_ONCE(ring->cons); + last_nr_txbb = READ_ONCE(ring->last_nr_txbb); + ring_cons = READ_ONCE(ring->cons); ring_index = ring_cons & size_mask; stamp_index = ring_index; @@ -479,8 +479,8 @@ bool mlx4_en_process_tx_cq(struct net_device *dev, wmb(); /* we want to dirty this cache line once */ - ACCESS_ONCE(ring->last_nr_txbb) = last_nr_txbb; - ACCESS_ONCE(ring->cons) = ring_cons + txbbs_skipped; + WRITE_ONCE(ring->last_nr_txbb, last_nr_txbb); + WRITE_ONCE(ring->cons, ring_cons + txbbs_skipped); if (cq->type == TX_XDP) return done < budget; @@ -858,7 +858,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_drop; /* fetch ring->cons far ahead before needing it to avoid stall */ - ring_cons = ACCESS_ONCE(ring->cons); + ring_cons = READ_ONCE(ring->cons); real_size = get_real_size(skb, shinfo, dev, &lso_header_size, &inline_ok, &fragptr); @@ -1066,7 +1066,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) */ smp_rmb(); - ring_cons = ACCESS_ONCE(ring->cons); + ring_cons = READ_ONCE(ring->cons); if (unlikely(!mlx4_en_is_tx_ring_full(ring))) { netif_tx_wake_queue(ring->tx_queue); ring->wake_queue++; diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 50ea69d88480..5dd5f61e1114 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -2629,7 +2629,7 @@ static void vxge_poll_vp_lockup(unsigned long data) ring = &vdev->vpaths[i].ring; /* Truncated to machine word size number of frames */ - rx_frms = ACCESS_ONCE(ring->stats.rx_frms); + rx_frms = READ_ONCE(ring->stats.rx_frms); /* Did this vpath received any packets */ if (ring->stats.prev_rx_frms == rx_frms) { diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 13f72f5b18d2..a95a46bcd339 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -2073,7 +2073,7 @@ static irqreturn_t efx_ef10_msi_interrupt(int irq, void *dev_id) netif_vdbg(efx, intr, efx->net_dev, "IRQ %d on CPU %d\n", irq, raw_smp_processor_id()); - if (likely(ACCESS_ONCE(efx->irq_soft_enabled))) { + if (likely(READ_ONCE(efx->irq_soft_enabled))) { /* Note test interrupts */ if (context->index == efx->irq_level) efx->last_irq_cpu = raw_smp_processor_id(); @@ -2088,7 +2088,7 @@ static irqreturn_t efx_ef10_msi_interrupt(int irq, void *dev_id) static irqreturn_t efx_ef10_legacy_interrupt(int irq, void *dev_id) { struct efx_nic *efx = dev_id; - bool soft_enabled = ACCESS_ONCE(efx->irq_soft_enabled); + bool soft_enabled = READ_ONCE(efx->irq_soft_enabled); struct efx_channel *channel; efx_dword_t reg; u32 queues; @@ -3291,7 +3291,7 @@ static int efx_ef10_handle_rx_event(struct efx_channel *channel, bool rx_cont; u16 flags = 0; - if (unlikely(ACCESS_ONCE(efx->reset_pending))) + if (unlikely(READ_ONCE(efx->reset_pending))) return 0; /* Basic packet information */ @@ -3428,7 +3428,7 @@ efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) unsigned int tx_ev_q_label; int tx_descs = 0; - if (unlikely(ACCESS_ONCE(efx->reset_pending))) + if (unlikely(READ_ONCE(efx->reset_pending))) return 0; if (unlikely(EFX_QWORD_FIELD(*event, ESF_DZ_TX_DROP_EVENT))) @@ -5316,7 +5316,7 @@ static void efx_ef10_filter_remove_old(struct efx_nic *efx) int i; for (i = 0; i < HUNT_FILTER_TBL_ROWS; i++) { - if (ACCESS_ONCE(table->entry[i].spec) & + if (READ_ONCE(table->entry[i].spec) & EFX_EF10_FILTER_FLAG_AUTO_OLD) { rc = efx_ef10_filter_remove_internal(efx, 1U << EFX_FILTER_PRI_AUTO, i, true); diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index b9cb697b2818..016616a63880 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -2809,7 +2809,7 @@ static void efx_reset_work(struct work_struct *data) unsigned long pending; enum reset_type method; - pending = ACCESS_ONCE(efx->reset_pending); + pending = READ_ONCE(efx->reset_pending); method = fls(pending) - 1; if (method == RESET_TYPE_MC_BIST) @@ -2874,7 +2874,7 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type) /* If we're not READY then just leave the flags set as the cue * to abort probing or reschedule the reset later. */ - if (ACCESS_ONCE(efx->state) != STATE_READY) + if (READ_ONCE(efx->state) != STATE_READY) return; /* efx_process_channel() will no longer read events once a diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index 29614da91cbf..7263275fde4a 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -2545,7 +2545,7 @@ static void ef4_reset_work(struct work_struct *data) unsigned long pending; enum reset_type method; - pending = ACCESS_ONCE(efx->reset_pending); + pending = READ_ONCE(efx->reset_pending); method = fls(pending) - 1; if ((method == RESET_TYPE_RECOVER_OR_DISABLE || @@ -2605,7 +2605,7 @@ void ef4_schedule_reset(struct ef4_nic *efx, enum reset_type type) /* If we're not READY then just leave the flags set as the cue * to abort probing or reschedule the reset later. */ - if (ACCESS_ONCE(efx->state) != STATE_READY) + if (READ_ONCE(efx->state) != STATE_READY) return; queue_work(reset_workqueue, &efx->reset_work); diff --git a/drivers/net/ethernet/sfc/falcon/falcon.c b/drivers/net/ethernet/sfc/falcon/falcon.c index 93c713c1f627..cd8bb472d758 100644 --- a/drivers/net/ethernet/sfc/falcon/falcon.c +++ b/drivers/net/ethernet/sfc/falcon/falcon.c @@ -452,7 +452,7 @@ static irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id) "IRQ %d on CPU %d status " EF4_OWORD_FMT "\n", irq, raw_smp_processor_id(), EF4_OWORD_VAL(*int_ker)); - if (!likely(ACCESS_ONCE(efx->irq_soft_enabled))) + if (!likely(READ_ONCE(efx->irq_soft_enabled))) return IRQ_HANDLED; /* Check to see if we have a serious error condition */ @@ -1372,7 +1372,7 @@ static void falcon_reconfigure_mac_wrapper(struct ef4_nic *efx) ef4_oword_t reg; int link_speed, isolate; - isolate = !!ACCESS_ONCE(efx->reset_pending); + isolate = !!READ_ONCE(efx->reset_pending); switch (link_state->speed) { case 10000: link_speed = 3; break; diff --git a/drivers/net/ethernet/sfc/falcon/farch.c b/drivers/net/ethernet/sfc/falcon/farch.c index 05916c710d8c..494884f6af4a 100644 --- a/drivers/net/ethernet/sfc/falcon/farch.c +++ b/drivers/net/ethernet/sfc/falcon/farch.c @@ -834,7 +834,7 @@ ef4_farch_handle_tx_event(struct ef4_channel *channel, ef4_qword_t *event) struct ef4_nic *efx = channel->efx; int tx_packets = 0; - if (unlikely(ACCESS_ONCE(efx->reset_pending))) + if (unlikely(READ_ONCE(efx->reset_pending))) return 0; if (likely(EF4_QWORD_FIELD(*event, FSF_AZ_TX_EV_COMP))) { @@ -990,7 +990,7 @@ ef4_farch_handle_rx_event(struct ef4_channel *channel, const ef4_qword_t *event) struct ef4_rx_queue *rx_queue; struct ef4_nic *efx = channel->efx; - if (unlikely(ACCESS_ONCE(efx->reset_pending))) + if (unlikely(READ_ONCE(efx->reset_pending))) return; rx_ev_cont = EF4_QWORD_FIELD(*event, FSF_AZ_RX_EV_JUMBO_CONT); @@ -1504,7 +1504,7 @@ irqreturn_t ef4_farch_fatal_interrupt(struct ef4_nic *efx) irqreturn_t ef4_farch_legacy_interrupt(int irq, void *dev_id) { struct ef4_nic *efx = dev_id; - bool soft_enabled = ACCESS_ONCE(efx->irq_soft_enabled); + bool soft_enabled = READ_ONCE(efx->irq_soft_enabled); ef4_oword_t *int_ker = efx->irq_status.addr; irqreturn_t result = IRQ_NONE; struct ef4_channel *channel; @@ -1596,7 +1596,7 @@ irqreturn_t ef4_farch_msi_interrupt(int irq, void *dev_id) "IRQ %d on CPU %d status " EF4_OWORD_FMT "\n", irq, raw_smp_processor_id(), EF4_OWORD_VAL(*int_ker)); - if (!likely(ACCESS_ONCE(efx->irq_soft_enabled))) + if (!likely(READ_ONCE(efx->irq_soft_enabled))) return IRQ_HANDLED; /* Handle non-event-queue sources */ diff --git a/drivers/net/ethernet/sfc/falcon/nic.h b/drivers/net/ethernet/sfc/falcon/nic.h index a4c4592f6023..54ca457cdb15 100644 --- a/drivers/net/ethernet/sfc/falcon/nic.h +++ b/drivers/net/ethernet/sfc/falcon/nic.h @@ -83,7 +83,7 @@ static inline struct ef4_tx_queue *ef4_tx_queue_partner(struct ef4_tx_queue *tx_ static inline bool __ef4_nic_tx_is_empty(struct ef4_tx_queue *tx_queue, unsigned int write_count) { - unsigned int empty_read_count = ACCESS_ONCE(tx_queue->empty_read_count); + unsigned int empty_read_count = READ_ONCE(tx_queue->empty_read_count); if (empty_read_count == 0) return false; @@ -464,11 +464,11 @@ irqreturn_t ef4_farch_fatal_interrupt(struct ef4_nic *efx); static inline int ef4_nic_event_test_irq_cpu(struct ef4_channel *channel) { - return ACCESS_ONCE(channel->event_test_cpu); + return READ_ONCE(channel->event_test_cpu); } static inline int ef4_nic_irq_test_irq_cpu(struct ef4_nic *efx) { - return ACCESS_ONCE(efx->last_irq_cpu); + return READ_ONCE(efx->last_irq_cpu); } /* Global Resources */ diff --git a/drivers/net/ethernet/sfc/falcon/tx.c b/drivers/net/ethernet/sfc/falcon/tx.c index 6a75f4140a4b..6486814e97dc 100644 --- a/drivers/net/ethernet/sfc/falcon/tx.c +++ b/drivers/net/ethernet/sfc/falcon/tx.c @@ -134,8 +134,8 @@ static void ef4_tx_maybe_stop_queue(struct ef4_tx_queue *txq1) */ netif_tx_stop_queue(txq1->core_txq); smp_mb(); - txq1->old_read_count = ACCESS_ONCE(txq1->read_count); - txq2->old_read_count = ACCESS_ONCE(txq2->read_count); + txq1->old_read_count = READ_ONCE(txq1->read_count); + txq2->old_read_count = READ_ONCE(txq2->read_count); fill_level = max(txq1->insert_count - txq1->old_read_count, txq2->insert_count - txq2->old_read_count); @@ -524,7 +524,7 @@ void ef4_xmit_done(struct ef4_tx_queue *tx_queue, unsigned int index) /* Check whether the hardware queue is now empty */ if ((int)(tx_queue->read_count - tx_queue->old_write_count) >= 0) { - tx_queue->old_write_count = ACCESS_ONCE(tx_queue->write_count); + tx_queue->old_write_count = READ_ONCE(tx_queue->write_count); if (tx_queue->read_count == tx_queue->old_write_count) { smp_mb(); tx_queue->empty_read_count = diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index ba45150f53c7..86454d25a405 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -827,7 +827,7 @@ efx_farch_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) struct efx_nic *efx = channel->efx; int tx_packets = 0; - if (unlikely(ACCESS_ONCE(efx->reset_pending))) + if (unlikely(READ_ONCE(efx->reset_pending))) return 0; if (likely(EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_COMP))) { @@ -979,7 +979,7 @@ efx_farch_handle_rx_event(struct efx_channel *channel, const efx_qword_t *event) struct efx_rx_queue *rx_queue; struct efx_nic *efx = channel->efx; - if (unlikely(ACCESS_ONCE(efx->reset_pending))) + if (unlikely(READ_ONCE(efx->reset_pending))) return; rx_ev_cont = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_JUMBO_CONT); @@ -1520,7 +1520,7 @@ irqreturn_t efx_farch_fatal_interrupt(struct efx_nic *efx) irqreturn_t efx_farch_legacy_interrupt(int irq, void *dev_id) { struct efx_nic *efx = dev_id; - bool soft_enabled = ACCESS_ONCE(efx->irq_soft_enabled); + bool soft_enabled = READ_ONCE(efx->irq_soft_enabled); efx_oword_t *int_ker = efx->irq_status.addr; irqreturn_t result = IRQ_NONE; struct efx_channel *channel; @@ -1612,7 +1612,7 @@ irqreturn_t efx_farch_msi_interrupt(int irq, void *dev_id) "IRQ %d on CPU %d status " EFX_OWORD_FMT "\n", irq, raw_smp_processor_id(), EFX_OWORD_VAL(*int_ker)); - if (!likely(ACCESS_ONCE(efx->irq_soft_enabled))) + if (!likely(READ_ONCE(efx->irq_soft_enabled))) return IRQ_HANDLED; /* Handle non-event-queue sources */ diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h index 4d7fb8af880d..7b51b6371724 100644 --- a/drivers/net/ethernet/sfc/nic.h +++ b/drivers/net/ethernet/sfc/nic.h @@ -81,7 +81,7 @@ static struct efx_tx_queue *efx_tx_queue_partner(struct efx_tx_queue *tx_queue) static inline bool __efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue, unsigned int write_count) { - unsigned int empty_read_count = ACCESS_ONCE(tx_queue->empty_read_count); + unsigned int empty_read_count = READ_ONCE(tx_queue->empty_read_count); if (empty_read_count == 0) return false; @@ -617,11 +617,11 @@ irqreturn_t efx_farch_fatal_interrupt(struct efx_nic *efx); static inline int efx_nic_event_test_irq_cpu(struct efx_channel *channel) { - return ACCESS_ONCE(channel->event_test_cpu); + return READ_ONCE(channel->event_test_cpu); } static inline int efx_nic_irq_test_irq_cpu(struct efx_nic *efx) { - return ACCESS_ONCE(efx->last_irq_cpu); + return READ_ONCE(efx->last_irq_cpu); } /* Global Resources */ diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index 60cdb97f58e2..56c2db398def 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -658,7 +658,7 @@ static void efx_ptp_send_times(struct efx_nic *efx, /* Write host time for specified period or until MC is done */ while ((timespec64_compare(&now.ts_real, &limit) < 0) && - ACCESS_ONCE(*mc_running)) { + READ_ONCE(*mc_running)) { struct timespec64 update_time; unsigned int host_time; @@ -668,7 +668,7 @@ static void efx_ptp_send_times(struct efx_nic *efx, do { pps_get_ts(&now); } while ((timespec64_compare(&now.ts_real, &update_time) < 0) && - ACCESS_ONCE(*mc_running)); + READ_ONCE(*mc_running)); /* Synchronise NIC with single word of time only */ host_time = (now.ts_real.tv_sec << MC_NANOSECOND_BITS | @@ -832,14 +832,14 @@ static int efx_ptp_synchronize(struct efx_nic *efx, unsigned int num_readings) ptp->start.dma_addr); /* Clear flag that signals MC ready */ - ACCESS_ONCE(*start) = 0; + WRITE_ONCE(*start, 0); rc = efx_mcdi_rpc_start(efx, MC_CMD_PTP, synch_buf, MC_CMD_PTP_IN_SYNCHRONIZE_LEN); EFX_WARN_ON_ONCE_PARANOID(rc); /* Wait for start from MCDI (or timeout) */ timeout = jiffies + msecs_to_jiffies(MAX_SYNCHRONISE_WAIT_MS); - while (!ACCESS_ONCE(*start) && (time_before(jiffies, timeout))) { + while (!READ_ONCE(*start) && (time_before(jiffies, timeout))) { udelay(20); /* Usually start MCDI execution quickly */ loops++; } @@ -849,7 +849,7 @@ static int efx_ptp_synchronize(struct efx_nic *efx, unsigned int num_readings) if (!time_before(jiffies, timeout)) ++ptp->sync_timeouts; - if (ACCESS_ONCE(*start)) + if (READ_ONCE(*start)) efx_ptp_send_times(efx, &last_time); /* Collect results */ diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 32bf1fecf864..efb66ea21f27 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -136,8 +136,8 @@ static void efx_tx_maybe_stop_queue(struct efx_tx_queue *txq1) */ netif_tx_stop_queue(txq1->core_txq); smp_mb(); - txq1->old_read_count = ACCESS_ONCE(txq1->read_count); - txq2->old_read_count = ACCESS_ONCE(txq2->read_count); + txq1->old_read_count = READ_ONCE(txq1->read_count); + txq2->old_read_count = READ_ONCE(txq2->read_count); fill_level = max(txq1->insert_count - txq1->old_read_count, txq2->insert_count - txq2->old_read_count); @@ -752,7 +752,7 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) /* Check whether the hardware queue is now empty */ if ((int)(tx_queue->read_count - tx_queue->old_write_count) >= 0) { - tx_queue->old_write_count = ACCESS_ONCE(tx_queue->write_count); + tx_queue->old_write_count = READ_ONCE(tx_queue->write_count); if (tx_queue->read_count == tx_queue->old_write_count) { smp_mb(); tx_queue->empty_read_count = diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 6a4e8e1bbd90..8ab0fb6892d5 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -6245,7 +6245,7 @@ static void niu_get_rx_stats(struct niu *np, pkts = dropped = errors = bytes = 0; - rx_rings = ACCESS_ONCE(np->rx_rings); + rx_rings = READ_ONCE(np->rx_rings); if (!rx_rings) goto no_rings; @@ -6276,7 +6276,7 @@ static void niu_get_tx_stats(struct niu *np, pkts = errors = bytes = 0; - tx_rings = ACCESS_ONCE(np->tx_rings); + tx_rings = READ_ONCE(np->tx_rings); if (!tx_rings) goto no_rings; diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 21b71ae947fd..b55b29b90b88 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -257,7 +257,7 @@ static struct tap_queue *tap_get_queue(struct tap_dev *tap, * and validate that the result isn't NULL - in case we are * racing against queue removal. */ - int numvtaps = ACCESS_ONCE(tap->numvtaps); + int numvtaps = READ_ONCE(tap->numvtaps); __u32 rxq; if (!numvtaps) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index e21bf90b819f..27cd50c5bc9e 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -469,7 +469,7 @@ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, u32 numqueues = 0; rcu_read_lock(); - numqueues = ACCESS_ONCE(tun->numqueues); + numqueues = READ_ONCE(tun->numqueues); txq = __skb_get_hash_symmetric(skb); if (txq) { @@ -864,7 +864,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); tfile = rcu_dereference(tun->tfiles[txq]); - numqueues = ACCESS_ONCE(tun->numqueues); + numqueues = READ_ONCE(tun->numqueues); /* Drop packet if interface is not attached */ if (txq >= numqueues) diff --git a/drivers/net/wireless/ath/ath5k/desc.c b/drivers/net/wireless/ath/ath5k/desc.c index bd8d4392d68b..80f75139495f 100644 --- a/drivers/net/wireless/ath/ath5k/desc.c +++ b/drivers/net/wireless/ath/ath5k/desc.c @@ -500,13 +500,13 @@ ath5k_hw_proc_4word_tx_status(struct ath5k_hw *ah, tx_status = &desc->ud.ds_tx5212.tx_stat; - txstat1 = ACCESS_ONCE(tx_status->tx_status_1); + txstat1 = READ_ONCE(tx_status->tx_status_1); /* No frame has been send or error */ if (unlikely(!(txstat1 & AR5K_DESC_TX_STATUS1_DONE))) return -EINPROGRESS; - txstat0 = ACCESS_ONCE(tx_status->tx_status_0); + txstat0 = READ_ONCE(tx_status->tx_status_0); /* * Get descriptor status @@ -700,14 +700,14 @@ ath5k_hw_proc_5212_rx_status(struct ath5k_hw *ah, u32 rxstat0, rxstat1; rx_status = &desc->ud.ds_rx.rx_stat; - rxstat1 = ACCESS_ONCE(rx_status->rx_status_1); + rxstat1 = READ_ONCE(rx_status->rx_status_1); /* No frame received / not ready */ if (unlikely(!(rxstat1 & AR5K_5212_RX_DESC_STATUS1_DONE))) return -EINPROGRESS; memset(rs, 0, sizeof(struct ath5k_rx_status)); - rxstat0 = ACCESS_ONCE(rx_status->rx_status_0); + rxstat0 = READ_ONCE(rx_status->rx_status_0); /* * Frame receive status diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index 613caca7dc02..785a0f33b7e6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -3628,7 +3628,7 @@ static void brcmf_sdio_dataworker(struct work_struct *work) bus->dpc_running = true; wmb(); - while (ACCESS_ONCE(bus->dpc_triggered)) { + while (READ_ONCE(bus->dpc_triggered)) { bus->dpc_triggered = false; brcmf_sdio_dpc(bus); bus->idlecount = 0; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 231878969332..0f45f34e39d3 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -1118,7 +1118,7 @@ void iwl_mvm_set_hw_ctkill_state(struct iwl_mvm *mvm, bool state) static bool iwl_mvm_set_hw_rfkill_state(struct iwl_op_mode *op_mode, bool state) { struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode); - bool calibrating = ACCESS_ONCE(mvm->calibrating); + bool calibrating = READ_ONCE(mvm->calibrating); if (state) set_bit(IWL_MVM_STATUS_HW_RFKILL, &mvm->status); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 6f2e2af23219..6e9d3289b9d0 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -652,7 +652,7 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) return -1; } else if (info.control.vif->type == NL80211_IFTYPE_STATION && is_multicast_ether_addr(hdr->addr1)) { - u8 ap_sta_id = ACCESS_ONCE(mvmvif->ap_sta_id); + u8 ap_sta_id = READ_ONCE(mvmvif->ap_sta_id); if (ap_sta_id != IWL_MVM_INVALID_STA) sta_id = ap_sta_id; @@ -700,7 +700,7 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, snap_ip_tcp = 8 + skb_transport_header(skb) - skb_network_header(skb) + tcp_hdrlen(skb); - dbg_max_amsdu_len = ACCESS_ONCE(mvm->max_amsdu_len); + dbg_max_amsdu_len = READ_ONCE(mvm->max_amsdu_len); if (!sta->max_amsdu_len || !ieee80211_is_data_qos(hdr->frame_control) || diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index a06b6612b658..f25ce3a1ea50 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -1247,7 +1247,7 @@ restart: spin_lock(&rxq->lock); /* uCode's read index (stored in shared DRAM) indicates the last Rx * buffer that the driver may process (last buffer filled by ucode). */ - r = le16_to_cpu(ACCESS_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF; + r = le16_to_cpu(READ_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF; i = rxq->read; /* W/A 9000 device step A0 wrap-around bug */ diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 2e3e013ec95a..9ad3f4fe5894 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -2076,12 +2076,12 @@ static int iwl_trans_pcie_wait_txq_empty(struct iwl_trans *trans, int txq_idx) IWL_DEBUG_TX_QUEUES(trans, "Emptying queue %d...\n", txq_idx); txq = trans_pcie->txq[txq_idx]; - wr_ptr = ACCESS_ONCE(txq->write_ptr); + wr_ptr = READ_ONCE(txq->write_ptr); - while (txq->read_ptr != ACCESS_ONCE(txq->write_ptr) && + while (txq->read_ptr != READ_ONCE(txq->write_ptr) && !time_after(jiffies, now + msecs_to_jiffies(IWL_FLUSH_WAIT_MS))) { - u8 write_ptr = ACCESS_ONCE(txq->write_ptr); + u8 write_ptr = READ_ONCE(txq->write_ptr); if (WARN_ONCE(wr_ptr != write_ptr, "WR pointer moved while flushing %d -> %d\n", @@ -2553,7 +2553,7 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans, spin_lock(&rxq->lock); - r = le16_to_cpu(ACCESS_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF; + r = le16_to_cpu(READ_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF; for (i = rxq->read, j = 0; i != r && j < allocated_rb_nums; @@ -2814,7 +2814,7 @@ static struct iwl_trans_dump_data /* Dump RBs is supported only for pre-9000 devices (1 queue) */ struct iwl_rxq *rxq = &trans_pcie->rxq[0]; /* RBs */ - num_rbs = le16_to_cpu(ACCESS_ONCE(rxq->rb_stts->closed_rb_num)) + num_rbs = le16_to_cpu(READ_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF; num_rbs = (num_rbs - rxq->read) & RX_QUEUE_MASK; len += num_rbs * (sizeof(*data) + diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 6467ffac9811..d2b3d6177a55 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1380,7 +1380,7 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw, mac80211_hwsim_monitor_rx(hw, skb, channel); /* wmediumd mode check */ - _portid = ACCESS_ONCE(data->wmediumd); + _portid = READ_ONCE(data->wmediumd); if (_portid) return mac80211_hwsim_tx_frame_nl(hw, skb, _portid); @@ -1477,7 +1477,7 @@ static void mac80211_hwsim_tx_frame(struct ieee80211_hw *hw, struct ieee80211_channel *chan) { struct mac80211_hwsim_data *data = hw->priv; - u32 _pid = ACCESS_ONCE(data->wmediumd); + u32 _pid = READ_ONCE(data->wmediumd); if (ieee80211_hw_check(hw, SUPPORTS_RC_TABLE)) { struct ieee80211_tx_info *txi = IEEE80211_SKB_CB(skb); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index f05cfc83c9c8..f946bf889015 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -996,7 +996,7 @@ static void qlt_free_session_done(struct work_struct *work) if (logout_started) { bool traced = false; - while (!ACCESS_ONCE(sess->logout_completed)) { + while (!READ_ONCE(sess->logout_completed)) { if (!traced) { ql_dbg(ql_dbg_tgt_mgt, vha, 0xf086, "%s: waiting for sess %p logout\n", diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 942d094269fb..9469695f5871 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -985,7 +985,7 @@ static unsigned int tcmu_handle_completions(struct tcmu_dev *udev) mb = udev->mb_addr; tcmu_flush_dcache_range(mb, sizeof(*mb)); - while (udev->cmdr_last_cleaned != ACCESS_ONCE(mb->cmd_tail)) { + while (udev->cmdr_last_cleaned != READ_ONCE(mb->cmd_tail)) { struct tcmu_cmd_entry *entry = (void *) mb + CMDR_OFF + udev->cmdr_last_cleaned; struct tcmu_cmd *cmd; diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 3e865dbf878c..fbaa2a90d25d 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -483,7 +483,7 @@ static ssize_t wdm_read if (rv < 0) return -ERESTARTSYS; - cntr = ACCESS_ONCE(desc->length); + cntr = READ_ONCE(desc->length); if (cntr == 0) { desc->read = 0; retry: diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index e9326f31db8d..4ae667d8c238 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -150,7 +150,7 @@ static int usbfs_increase_memory_usage(u64 amount) { u64 lim; - lim = ACCESS_ONCE(usbfs_memory_mb); + lim = READ_ONCE(usbfs_memory_mb); lim <<= 20; atomic64_add(amount, &usbfs_memory_usage); diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index d930bfda4010..58d59c5f8592 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -973,7 +973,7 @@ static ssize_t interface_show(struct device *dev, struct device_attribute *attr, char *string; intf = to_usb_interface(dev); - string = ACCESS_ONCE(intf->cur_altsetting->string); + string = READ_ONCE(intf->cur_altsetting->string); if (!string) return 0; return sprintf(buf, "%s\n", string); @@ -989,7 +989,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, intf = to_usb_interface(dev); udev = interface_to_usbdev(intf); - alt = ACCESS_ONCE(intf->cur_altsetting); + alt = READ_ONCE(intf->cur_altsetting); return sprintf(buf, "usb:v%04Xp%04Xd%04Xdc%02Xdsc%02Xdp%02X" "ic%02Xisc%02Xip%02Xin%02X\n", diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c index 1f9941145746..0b59fa50aa30 100644 --- a/drivers/usb/gadget/udc/gr_udc.c +++ b/drivers/usb/gadget/udc/gr_udc.c @@ -1261,7 +1261,7 @@ static int gr_handle_in_ep(struct gr_ep *ep) if (!req->last_desc) return 0; - if (ACCESS_ONCE(req->last_desc->ctrl) & GR_DESC_IN_CTRL_EN) + if (READ_ONCE(req->last_desc->ctrl) & GR_DESC_IN_CTRL_EN) return 0; /* Not put in hardware buffers yet */ if (gr_read32(&ep->regs->epstat) & (GR_EPSTAT_B1 | GR_EPSTAT_B0)) @@ -1290,7 +1290,7 @@ static int gr_handle_out_ep(struct gr_ep *ep) if (!req->curr_desc) return 0; - ctrl = ACCESS_ONCE(req->curr_desc->ctrl); + ctrl = READ_ONCE(req->curr_desc->ctrl); if (ctrl & GR_DESC_OUT_CTRL_EN) return 0; /* Not received yet */ diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 44924824fa41..c86f89babd57 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -785,7 +785,7 @@ static void io_watchdog_func(unsigned long _ohci) } /* find the last TD processed by the controller. */ - head = hc32_to_cpu(ohci, ACCESS_ONCE(ed->hwHeadP)) & TD_MASK; + head = hc32_to_cpu(ohci, READ_ONCE(ed->hwHeadP)) & TD_MASK; td_start = td; td_next = list_prepare_entry(td, &ed->td_list, td_list); list_for_each_entry_continue(td_next, &ed->td_list, td_list) { diff --git a/drivers/usb/host/uhci-hcd.h b/drivers/usb/host/uhci-hcd.h index 91b22b2ea3aa..09a2a259941b 100644 --- a/drivers/usb/host/uhci-hcd.h +++ b/drivers/usb/host/uhci-hcd.h @@ -186,7 +186,7 @@ struct uhci_qh { * We need a special accessor for the element pointer because it is * subject to asynchronous updates by the controller. */ -#define qh_element(qh) ACCESS_ONCE((qh)->element) +#define qh_element(qh) READ_ONCE((qh)->element) #define LINK_TO_QH(uhci, qh) (UHCI_PTR_QH((uhci)) | \ cpu_to_hc32((uhci), (qh)->dma_handle)) @@ -274,7 +274,7 @@ struct uhci_td { * subject to asynchronous updates by the controller. */ #define td_status(uhci, td) hc32_to_cpu((uhci), \ - ACCESS_ONCE((td)->status)) + READ_ONCE((td)->status)) #define LINK_TO_TD(uhci, td) (cpu_to_hc32((uhci), (td)->dma_handle)) diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index f5a86f651f38..2bc3705a99bd 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -665,7 +665,7 @@ static int vfio_dev_viable(struct device *dev, void *data) { struct vfio_group *group = data; struct vfio_device *device; - struct device_driver *drv = ACCESS_ONCE(dev->driver); + struct device_driver *drv = READ_ONCE(dev->driver); struct vfio_unbound_dev *unbound; int ret = -EINVAL; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 046f6d280af5..35e929f132e8 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -929,7 +929,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) continue; } - tpg = ACCESS_ONCE(vs_tpg[*target]); + tpg = READ_ONCE(vs_tpg[*target]); if (unlikely(!tpg)) { /* Target does not exist, fail the request */ vhost_scsi_send_bad_target(vs, vq, head, out); diff --git a/fs/aio.c b/fs/aio.c index 5a2487217072..e6de7715228c 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -576,7 +576,7 @@ static int kiocb_cancel(struct aio_kiocb *kiocb) * actually has a cancel function, hence the cmpxchg() */ - cancel = ACCESS_ONCE(kiocb->ki_cancel); + cancel = READ_ONCE(kiocb->ki_cancel); do { if (!cancel || cancel == KIOCB_CANCELLED) return -EINVAL; diff --git a/fs/buffer.c b/fs/buffer.c index 170df856bdb9..32ce01f0f95f 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1692,7 +1692,8 @@ static struct buffer_head *create_page_buffers(struct page *page, struct inode * BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) - create_empty_buffers(page, 1 << ACCESS_ONCE(inode->i_blkbits), b_state); + create_empty_buffers(page, 1 << READ_ONCE(inode->i_blkbits), + b_state); return page_buffers(page); } diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 8e704d12a1cf..0083bd4fcaa5 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -373,7 +373,7 @@ void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci) struct fscrypt_info *prev; if (ci == NULL) - ci = ACCESS_ONCE(inode->i_crypt_info); + ci = READ_ONCE(inode->i_crypt_info); if (ci == NULL) return; diff --git a/fs/direct-io.c b/fs/direct-io.c index b53e66d9abd7..98fe1325da9d 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1152,7 +1152,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io, int flags) { - unsigned i_blkbits = ACCESS_ONCE(inode->i_blkbits); + unsigned i_blkbits = READ_ONCE(inode->i_blkbits); unsigned blkbits = i_blkbits; unsigned blocksize_mask = (1 << blkbits) - 1; ssize_t retval = -EINVAL; diff --git a/fs/exec.c b/fs/exec.c index 3e14ba25f678..1d6243d9f2b6 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1911,7 +1911,7 @@ void set_dumpable(struct mm_struct *mm, int value) return; do { - old = ACCESS_ONCE(mm->flags); + old = READ_ONCE(mm->flags); new = (old & ~MMF_DUMPABLE_MASK) | value; } while (cmpxchg(&mm->flags, old, new) != old); } diff --git a/fs/fcntl.c b/fs/fcntl.c index 448a1119f0be..57bf2964bb83 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -724,7 +724,7 @@ static void send_sigio_to_task(struct task_struct *p, * F_SETSIG can change ->signum lockless in parallel, make * sure we read it once and use the same value throughout. */ - int signum = ACCESS_ONCE(fown->signum); + int signum = READ_ONCE(fown->signum); if (!sigio_perm(p, fown, signum)) return; diff --git a/fs/fs_pin.c b/fs/fs_pin.c index e747b3d720ee..2d07f292b625 100644 --- a/fs/fs_pin.c +++ b/fs/fs_pin.c @@ -78,7 +78,7 @@ void mnt_pin_kill(struct mount *m) while (1) { struct hlist_node *p; rcu_read_lock(); - p = ACCESS_ONCE(m->mnt_pins.first); + p = READ_ONCE(m->mnt_pins.first); if (!p) { rcu_read_unlock(); break; @@ -92,7 +92,7 @@ void group_pin_kill(struct hlist_head *p) while (1) { struct hlist_node *q; rcu_read_lock(); - q = ACCESS_ONCE(p->first); + q = READ_ONCE(p->first); if (!q) { rcu_read_unlock(); break; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 13c65dd2d37d..a42d89371748 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -33,7 +33,7 @@ static struct fuse_dev *fuse_get_dev(struct file *file) * Lockless access is OK, because file->private data is set * once during mount and is valid until the file is released. */ - return ACCESS_ONCE(file->private_data); + return READ_ONCE(file->private_data); } static void fuse_request_init(struct fuse_req *req, struct page **pages, diff --git a/fs/inode.c b/fs/inode.c index d1e35b53bb23..fd401028a309 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2090,7 +2090,7 @@ void inode_set_flags(struct inode *inode, unsigned int flags, WARN_ON_ONCE(flags & ~mask); do { - old_flags = ACCESS_ONCE(inode->i_flags); + old_flags = READ_ONCE(inode->i_flags); new_flags = (old_flags & ~mask) | flags; } while (unlikely(cmpxchg(&inode->i_flags, old_flags, new_flags) != old_flags)); diff --git a/fs/namei.c b/fs/namei.c index c75ea03ca147..40a0f34bf990 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1209,7 +1209,7 @@ static int follow_managed(struct path *path, struct nameidata *nd) /* Given that we're not holding a lock here, we retain the value in a * local variable for each dentry as we look at it so that we don't see * the components of that value change under us */ - while (managed = ACCESS_ONCE(path->dentry->d_flags), + while (managed = READ_ONCE(path->dentry->d_flags), managed &= DCACHE_MANAGED_DENTRY, unlikely(managed != 0)) { /* Allow the filesystem to manage the transit without i_mutex @@ -1394,7 +1394,7 @@ int follow_down(struct path *path) unsigned managed; int ret; - while (managed = ACCESS_ONCE(path->dentry->d_flags), + while (managed = READ_ONCE(path->dentry->d_flags), unlikely(managed & DCACHE_MANAGED_DENTRY)) { /* Allow the filesystem to manage the transit without i_mutex * being held. diff --git a/fs/namespace.c b/fs/namespace.c index d18deb4c410b..e158ec6b527b 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -353,7 +353,7 @@ int __mnt_want_write(struct vfsmount *m) * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); - while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) + while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) cpu_relax(); /* * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 5ceaeb1f6fb6..f439f1c45008 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1081,7 +1081,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) int error; if (flags & LOOKUP_RCU) { - parent = ACCESS_ONCE(dentry->d_parent); + parent = READ_ONCE(dentry->d_parent); dir = d_inode_rcu(parent); if (!dir) return -ECHILD; @@ -1168,7 +1168,7 @@ out_set_verifier: nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); out_valid: if (flags & LOOKUP_RCU) { - if (parent != ACCESS_ONCE(dentry->d_parent)) + if (parent != READ_ONCE(dentry->d_parent)) return -ECHILD; } else dput(parent); @@ -1582,7 +1582,7 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) struct inode *dir; if (flags & LOOKUP_RCU) { - parent = ACCESS_ONCE(dentry->d_parent); + parent = READ_ONCE(dentry->d_parent); dir = d_inode_rcu(parent); if (!dir) return -ECHILD; @@ -1596,7 +1596,7 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) ret = -ECHILD; if (!(flags & LOOKUP_RCU)) dput(parent); - else if (parent != ACCESS_ONCE(dentry->d_parent)) + else if (parent != READ_ONCE(dentry->d_parent)) return -ECHILD; goto out; } diff --git a/fs/proc/array.c b/fs/proc/array.c index 77a8eacbe032..375e8bf0dd24 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -453,7 +453,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, cutime = sig->cutime; cstime = sig->cstime; cgtime = sig->cgtime; - rsslim = ACCESS_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur); + rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur); /* add up live thread stats at the group level */ if (whole) { diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 99dff222fe67..03afd5150916 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -27,7 +27,7 @@ static unsigned mounts_poll(struct file *file, poll_table *wait) poll_wait(file, &p->ns->poll, wait); - event = ACCESS_ONCE(ns->event); + event = READ_ONCE(ns->event); if (m->poll_event != event) { m->poll_event = event; res |= POLLERR | POLLPRI; diff --git a/fs/splice.c b/fs/splice.c index f3084cce0ea6..39e2dc01ac12 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -253,7 +253,7 @@ EXPORT_SYMBOL(add_to_pipe); */ int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { - unsigned int buffers = ACCESS_ONCE(pipe->buffers); + unsigned int buffers = READ_ONCE(pipe->buffers); spd->nr_pages_max = buffers; if (buffers <= PIPE_DEF_BUFFERS) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 1c713fd5b3e6..f46d133c0949 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -381,7 +381,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) * in __get_user_pages if userfaultfd_release waits on the * caller of handle_userfault to release the mmap_sem. */ - if (unlikely(ACCESS_ONCE(ctx->released))) { + if (unlikely(READ_ONCE(ctx->released))) { /* * Don't return VM_FAULT_SIGBUS in this case, so a non * cooperative manager can close the uffd after the @@ -477,7 +477,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) vmf->flags, reason); up_read(&mm->mmap_sem); - if (likely(must_wait && !ACCESS_ONCE(ctx->released) && + if (likely(must_wait && !READ_ONCE(ctx->released) && (return_to_userland ? !signal_pending(current) : !fatal_signal_pending(current)))) { wake_up_poll(&ctx->fd_wqh, POLLIN); @@ -586,7 +586,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, set_current_state(TASK_KILLABLE); if (ewq->msg.event == 0) break; - if (ACCESS_ONCE(ctx->released) || + if (READ_ONCE(ctx->released) || fatal_signal_pending(current)) { /* * &ewq->wq may be queued in fork_event, but @@ -833,7 +833,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) struct userfaultfd_wake_range range = { .len = 0, }; unsigned long new_flags; - ACCESS_ONCE(ctx->released) = true; + WRITE_ONCE(ctx->released, true); if (!mmget_not_zero(mm)) goto wakeup; diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 51bf7b827387..129975970d99 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -592,9 +592,9 @@ xlog_valid_lsn( * a transiently forward state. Instead, we can see the LSN in a * transiently behind state if we happen to race with a cycle wrap. */ - cur_cycle = ACCESS_ONCE(log->l_curr_cycle); + cur_cycle = READ_ONCE(log->l_curr_cycle); smp_rmb(); - cur_block = ACCESS_ONCE(log->l_curr_block); + cur_block = READ_ONCE(log->l_curr_block); if ((CYCLE_LSN(lsn) > cur_cycle) || (CYCLE_LSN(lsn) == cur_cycle && BLOCK_LSN(lsn) > cur_block)) { diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 8fbe259b197c..0a7ce668f8e0 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -236,7 +236,7 @@ static inline unsigned long __ffs64(u64 word) typeof(*ptr) old, new; \ \ do { \ - old = ACCESS_ONCE(*ptr); \ + old = READ_ONCE(*ptr); \ new = (old & ~mask) | bits; \ } while (cmpxchg(ptr, old, new) != old); \ \ @@ -251,7 +251,7 @@ static inline unsigned long __ffs64(u64 word) typeof(*ptr) old, new; \ \ do { \ - old = ACCESS_ONCE(*ptr); \ + old = READ_ONCE(*ptr); \ new = old & ~clear; \ } while (!(old & test) && \ cmpxchg(ptr, old, new) != old); \ diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h index a4be70398ce1..36dd4ffb5715 100644 --- a/include/linux/dynamic_queue_limits.h +++ b/include/linux/dynamic_queue_limits.h @@ -88,7 +88,7 @@ static inline void dql_queued(struct dql *dql, unsigned int count) /* Returns how many objects can be queued, < 0 indicates over limit. */ static inline int dql_avail(const struct dql *dql) { - return ACCESS_ONCE(dql->adj_limit) - ACCESS_ONCE(dql->num_queued); + return READ_ONCE(dql->adj_limit) - READ_ONCE(dql->num_queued); } /* Record number of completed objects and recalculate the limit. */ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 14bc21c2ee7f..785a00ca4628 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -221,7 +221,7 @@ extern struct page *huge_zero_page; static inline bool is_huge_zero_page(struct page *page) { - return ACCESS_ONCE(huge_zero_page) == page; + return READ_ONCE(huge_zero_page) == page; } static inline bool is_huge_zero_pmd(pmd_t pmd) diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 30294603526f..d95cae09dea0 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -247,7 +247,7 @@ static inline struct team_port *team_get_port_by_index(struct team *team, static inline int team_num_to_port_index(struct team *team, unsigned int num) { - int en_port_count = ACCESS_ONCE(team->en_port_count); + int en_port_count = READ_ONCE(team->en_port_count); if (unlikely(!en_port_count)) return 0; diff --git a/include/linux/llist.h b/include/linux/llist.h index 1957635e6d5f..85abc2915e8d 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -198,7 +198,7 @@ static inline void init_llist_head(struct llist_head *list) */ static inline bool llist_empty(const struct llist_head *head) { - return ACCESS_ONCE(head->first) == NULL; + return READ_ONCE(head->first) == NULL; } static inline struct llist_node *llist_next(struct llist_node *node) diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 2efb08a60e63..f0fc4700b6ff 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -105,7 +105,7 @@ static inline bool pm_runtime_callbacks_present(struct device *dev) static inline void pm_runtime_mark_last_busy(struct device *dev) { - ACCESS_ONCE(dev->power.last_busy) = jiffies; + WRITE_ONCE(dev->power.last_busy, jiffies); } static inline bool pm_runtime_is_irq_safe(struct device *dev) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 4f4f786255ef..3fadb6f9982b 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -983,12 +983,12 @@ static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) static inline int sysctl_sync_period(struct netns_ipvs *ipvs) { - return ACCESS_ONCE(ipvs->sysctl_sync_threshold[1]); + return READ_ONCE(ipvs->sysctl_sync_threshold[1]); } static inline unsigned int sysctl_sync_refresh_period(struct netns_ipvs *ipvs) { - return ACCESS_ONCE(ipvs->sysctl_sync_refresh_period); + return READ_ONCE(ipvs->sysctl_sync_refresh_period); } static inline int sysctl_sync_retries(struct netns_ipvs *ipvs) @@ -1013,7 +1013,7 @@ static inline int sysctl_sloppy_sctp(struct netns_ipvs *ipvs) static inline int sysctl_sync_ports(struct netns_ipvs *ipvs) { - return ACCESS_ONCE(ipvs->sysctl_sync_ports); + return READ_ONCE(ipvs->sysctl_sync_ports); } static inline int sysctl_sync_persist_mode(struct netns_ipvs *ipvs) diff --git a/kernel/acct.c b/kernel/acct.c index 5e72af29ab73..21eedd0dd81a 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -146,7 +146,7 @@ static struct bsd_acct_struct *acct_get(struct pid_namespace *ns) again: smp_rmb(); rcu_read_lock(); - res = to_acct(ACCESS_ONCE(ns->bacct)); + res = to_acct(READ_ONCE(ns->bacct)); if (!res) { rcu_read_unlock(); return NULL; @@ -158,7 +158,7 @@ again: } rcu_read_unlock(); mutex_lock(&res->lock); - if (res != to_acct(ACCESS_ONCE(ns->bacct))) { + if (res != to_acct(READ_ONCE(ns->bacct))) { mutex_unlock(&res->lock); acct_put(res); goto again; diff --git a/kernel/events/core.c b/kernel/events/core.c index 824a583079a1..8fd2f2d1358a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1200,7 +1200,7 @@ perf_event_ctx_lock_nested(struct perf_event *event, int nesting) again: rcu_read_lock(); - ctx = ACCESS_ONCE(event->ctx); + ctx = READ_ONCE(event->ctx); if (!atomic_inc_not_zero(&ctx->refcount)) { rcu_read_unlock(); goto again; @@ -5302,8 +5302,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) if (!rb) goto aux_unlock; - aux_offset = ACCESS_ONCE(rb->user_page->aux_offset); - aux_size = ACCESS_ONCE(rb->user_page->aux_size); + aux_offset = READ_ONCE(rb->user_page->aux_offset); + aux_size = READ_ONCE(rb->user_page->aux_size); if (aux_offset < perf_data_size(rb) + PAGE_SIZE) goto aux_unlock; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index f684d8e5fa2b..f3e37971c842 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -381,7 +381,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle, * (B) <-> (C) ordering is still observed by the pmu driver. */ if (!rb->aux_overwrite) { - aux_tail = ACCESS_ONCE(rb->user_page->aux_tail); + aux_tail = READ_ONCE(rb->user_page->aux_tail); handle->wakeup = rb->aux_wakeup + rb->aux_watermark; if (aux_head - aux_tail < perf_aux_size(rb)) handle->size = CIRC_SPACE(aux_head, aux_tail, perf_aux_size(rb)); diff --git a/kernel/exit.c b/kernel/exit.c index f6cad39f35df..6b4298a41167 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1339,7 +1339,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace, * Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition * can't confuse the checks below. */ - int exit_state = ACCESS_ONCE(p->exit_state); + int exit_state = READ_ONCE(p->exit_state); int ret; if (unlikely(exit_state == EXIT_DEAD)) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 81279c6602ff..845f3805c73d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2724,7 +2724,7 @@ rb_reserve_next_event(struct ring_buffer *buffer, * if it happened, we have to fail the write. */ barrier(); - if (unlikely(ACCESS_ONCE(cpu_buffer->buffer) != buffer)) { + if (unlikely(READ_ONCE(cpu_buffer->buffer) != buffer)) { local_dec(&cpu_buffer->committing); local_dec(&cpu_buffer->commits); return NULL; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 652c682707cd..9050c8b3ccde 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1459,7 +1459,7 @@ extern struct trace_event_file *find_event_file(struct trace_array *tr, static inline void *event_file_data(struct file *filp) { - return ACCESS_ONCE(file_inode(filp)->i_private); + return READ_ONCE(file_inode(filp)->i_private); } extern struct mutex event_mutex; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 49cb41412eec..780262210c9a 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -77,7 +77,7 @@ check_stack(unsigned long ip, unsigned long *stack) { unsigned long this_size, flags; unsigned long *p, *top, *start; static int tracer_frame; - int frame_size = ACCESS_ONCE(tracer_frame); + int frame_size = READ_ONCE(tracer_frame); int i, x; this_size = ((unsigned long)stack) & (THREAD_SIZE-1); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index c490f1e4313b..d32b45662fb6 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -894,7 +894,7 @@ static bool new_idmap_permitted(const struct file *file, int proc_setgroups_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; - unsigned long userns_flags = ACCESS_ONCE(ns->flags); + unsigned long userns_flags = READ_ONCE(ns->flags); seq_printf(seq, "%s\n", (userns_flags & USERNS_SETGROUPS_ALLOWED) ? diff --git a/lib/assoc_array.c b/lib/assoc_array.c index 155c55d8db5f..fe7953aead82 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -39,7 +39,7 @@ begin_node: /* Descend through a shortcut */ shortcut = assoc_array_ptr_to_shortcut(cursor); smp_read_barrier_depends(); - cursor = ACCESS_ONCE(shortcut->next_node); + cursor = READ_ONCE(shortcut->next_node); } node = assoc_array_ptr_to_node(cursor); @@ -55,7 +55,7 @@ begin_node: */ has_meta = 0; for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { - ptr = ACCESS_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); has_meta |= (unsigned long)ptr; if (ptr && assoc_array_ptr_is_leaf(ptr)) { /* We need a barrier between the read of the pointer @@ -89,7 +89,7 @@ continue_node: smp_read_barrier_depends(); for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { - ptr = ACCESS_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); if (assoc_array_ptr_is_meta(ptr)) { cursor = ptr; goto begin_node; @@ -98,7 +98,7 @@ continue_node: finished_node: /* Move up to the parent (may need to skip back over a shortcut) */ - parent = ACCESS_ONCE(node->back_pointer); + parent = READ_ONCE(node->back_pointer); slot = node->parent_slot; if (parent == stop) return 0; @@ -107,7 +107,7 @@ finished_node: shortcut = assoc_array_ptr_to_shortcut(parent); smp_read_barrier_depends(); cursor = parent; - parent = ACCESS_ONCE(shortcut->back_pointer); + parent = READ_ONCE(shortcut->back_pointer); slot = shortcut->parent_slot; if (parent == stop) return 0; @@ -147,7 +147,7 @@ int assoc_array_iterate(const struct assoc_array *array, void *iterator_data), void *iterator_data) { - struct assoc_array_ptr *root = ACCESS_ONCE(array->root); + struct assoc_array_ptr *root = READ_ONCE(array->root); if (!root) return 0; @@ -194,7 +194,7 @@ assoc_array_walk(const struct assoc_array *array, pr_devel("-->%s()\n", __func__); - cursor = ACCESS_ONCE(array->root); + cursor = READ_ONCE(array->root); if (!cursor) return assoc_array_walk_tree_empty; @@ -220,7 +220,7 @@ consider_node: slot = segments >> (level & ASSOC_ARRAY_KEY_CHUNK_MASK); slot &= ASSOC_ARRAY_FAN_MASK; - ptr = ACCESS_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); pr_devel("consider slot %x [ix=%d type=%lu]\n", slot, level, (unsigned long)ptr & 3); @@ -294,7 +294,7 @@ follow_shortcut: } while (sc_level < shortcut->skip_to_level); /* The shortcut matches the leaf's index to this point. */ - cursor = ACCESS_ONCE(shortcut->next_node); + cursor = READ_ONCE(shortcut->next_node); if (((level ^ sc_level) & ~ASSOC_ARRAY_KEY_CHUNK_MASK) != 0) { level = sc_level; goto jumped; @@ -337,7 +337,7 @@ void *assoc_array_find(const struct assoc_array *array, * the terminal node. */ for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) { - ptr = ACCESS_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); if (ptr && assoc_array_ptr_is_leaf(ptr)) { /* We need a barrier between the read of the pointer * and dereferencing the pointer - but only if we are diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c index f346715e2255..81770a55cb16 100644 --- a/lib/dynamic_queue_limits.c +++ b/lib/dynamic_queue_limits.c @@ -20,7 +20,7 @@ void dql_completed(struct dql *dql, unsigned int count) unsigned int ovlimit, completed, num_queued; bool all_prev_completed; - num_queued = ACCESS_ONCE(dql->num_queued); + num_queued = READ_ONCE(dql->num_queued); /* Can't complete more than what's in queue */ BUG_ON(count > num_queued - dql->num_completed); diff --git a/lib/llist.c b/lib/llist.c index ae5872b1df0c..7062e931a7bb 100644 --- a/lib/llist.c +++ b/lib/llist.c @@ -41,7 +41,7 @@ bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, struct llist_node *first; do { - new_last->next = first = ACCESS_ONCE(head->first); + new_last->next = first = READ_ONCE(head->first); } while (cmpxchg(&head->first, first, new_first) != first); return !first; diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 86c3385b9eb3..1746bae94d41 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -620,8 +620,8 @@ char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_sp rcu_read_lock(); for (i = 0; i < depth; i++, d = p) { - p = ACCESS_ONCE(d->d_parent); - array[i] = ACCESS_ONCE(d->d_name.name); + p = READ_ONCE(d->d_parent); + array[i] = READ_ONCE(d->d_name.name); if (p == d) { if (i) array[i] = ""; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 269b5df58543..c3bf907a03ee 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2715,7 +2715,7 @@ static unsigned long deferred_split_count(struct shrinker *shrink, struct shrink_control *sc) { struct pglist_data *pgdata = NODE_DATA(sc->nid); - return ACCESS_ONCE(pgdata->split_queue_len); + return READ_ONCE(pgdata->split_queue_len); } static unsigned long deferred_split_scan(struct shrinker *shrink, diff --git a/net/core/dev.c b/net/core/dev.c index 11596a302a26..61559ca3980b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3725,7 +3725,7 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, flow_table = rcu_dereference(rxqueue->rps_flow_table); if (flow_table && flow_id <= flow_table->mask) { rflow = &flow_table->flows[flow_id]; - cpu = ACCESS_ONCE(rflow->cpu); + cpu = READ_ONCE(rflow->cpu); if (rflow->filter == filter_id && cpu < nr_cpu_ids && ((int)(per_cpu(softnet_data, cpu).input_queue_head - rflow->last_qtail) < diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 6e1e10ff433a..3b2034f6d49d 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3377,7 +3377,7 @@ static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev) static void pktgen_xmit(struct pktgen_dev *pkt_dev) { - unsigned int burst = ACCESS_ONCE(pkt_dev->burst); + unsigned int burst = READ_ONCE(pkt_dev->burst); struct net_device *odev = pkt_dev->odev; struct netdev_queue *txq; struct sk_buff *skb; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index af74d0433453..f9597ba26599 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -164,7 +164,7 @@ static void inet_frag_worker(struct work_struct *work) local_bh_disable(); - for (i = ACCESS_ONCE(f->next_bucket); budget; --budget) { + for (i = READ_ONCE(f->next_bucket); budget; --budget) { evicted += inet_evict_bucket(f, &f->hash[i]); i = (i + 1) & (INETFRAGS_HASHSZ - 1); if (evicted > INETFRAGS_EVICT_MAX) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3d9f1c2f81c5..c0864562083b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -495,7 +495,7 @@ u32 ip_idents_reserve(u32 hash, int segs) { u32 *p_tstamp = ip_tstamps + hash % IP_IDENTS_SZ; atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ; - u32 old = ACCESS_ONCE(*p_tstamp); + u32 old = READ_ONCE(*p_tstamp); u32 now = (u32)jiffies; u32 new, delta = 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 0bc9e46a5369..48531da1aba6 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1908,7 +1908,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len)) goto send_now; - win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor); + win_divisor = READ_ONCE(sysctl_tcp_tso_win_divisor); if (win_divisor) { u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ebfbccae62fd..02ec9a349303 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1853,7 +1853,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ /* if we're overly short, let UDP handle it */ - encap_rcv = ACCESS_ONCE(up->encap_rcv); + encap_rcv = READ_ONCE(up->encap_rcv); if (encap_rcv) { int ret; @@ -2298,7 +2298,7 @@ void udp_destroy_sock(struct sock *sk) unlock_sock_fast(sk, slow); if (static_key_false(&udp_encap_needed) && up->encap_type) { void (*encap_destroy)(struct sock *sk); - encap_destroy = ACCESS_ONCE(up->encap_destroy); + encap_destroy = READ_ONCE(up->encap_destroy); if (encap_destroy) encap_destroy(sk); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a1c24443cd9e..dab946554157 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -490,7 +490,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, if (!t) goto out; - tproto = ACCESS_ONCE(t->parms.proto); + tproto = READ_ONCE(t->parms.proto); if (tproto != ipproto && tproto != 0) goto out; @@ -899,7 +899,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr); if (t) { - u8 tproto = ACCESS_ONCE(t->parms.proto); + u8 tproto = READ_ONCE(t->parms.proto); if (tproto != ipproto && tproto != 0) goto drop; @@ -1233,7 +1233,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - tproto = ACCESS_ONCE(t->parms.proto); + tproto = READ_ONCE(t->parms.proto); if (tproto != IPPROTO_IPIP && tproto != 0) return -1; @@ -1303,7 +1303,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; - tproto = ACCESS_ONCE(t->parms.proto); + tproto = READ_ONCE(t->parms.proto); if ((tproto != IPPROTO_IPV6 && tproto != 0) || ip6_tnl_addr_conflict(t, ipv6h)) return -1; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 40d7234c27b9..3f30fa313bf2 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -606,7 +606,7 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ /* if we're overly short, let UDP handle it */ - encap_rcv = ACCESS_ONCE(up->encap_rcv); + encap_rcv = READ_ONCE(up->encap_rcv); if (encap_rcv) { int ret; @@ -1432,7 +1432,7 @@ void udpv6_destroy_sock(struct sock *sk) if (static_key_false(&udpv6_encap_needed) && up->encap_type) { void (*encap_destroy)(struct sock *sk); - encap_destroy = ACCESS_ONCE(up->encap_destroy); + encap_destroy = READ_ONCE(up->encap_destroy); if (encap_destroy) encap_destroy(sk); } diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index dd3e83328ad5..82cb93f66b9b 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -193,7 +193,7 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev, */ rcv = rcu_dereference(sap->rcv_func); dest = llc_pdu_type(skb); - sap_handler = dest ? ACCESS_ONCE(llc_type_handlers[dest - 1]) : NULL; + sap_handler = dest ? READ_ONCE(llc_type_handlers[dest - 1]) : NULL; if (unlikely(!sap_handler)) { if (rcv) rcv(skb, dev, pt, orig_dev); @@ -214,7 +214,7 @@ drop: kfree_skb(skb); goto out; handle_station: - sta_handler = ACCESS_ONCE(llc_station_handler); + sta_handler = READ_ONCE(llc_station_handler); if (!sta_handler) goto drop; sta_handler(skb); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 69615016d5bf..214d2ba02877 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -2008,7 +2008,7 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate, static int sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo) { - u16 rate = ACCESS_ONCE(sta_get_last_rx_stats(sta)->last_rate); + u16 rate = READ_ONCE(sta_get_last_rx_stats(sta)->last_rate); if (rate == STA_STATS_RATE_INVALID) return -EINVAL; diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c index d177dd066504..4d748975117d 100644 --- a/net/netlabel/netlabel_calipso.c +++ b/net/netlabel/netlabel_calipso.c @@ -393,7 +393,7 @@ EXPORT_SYMBOL(netlbl_calipso_ops_register); static const struct netlbl_calipso_ops *netlbl_calipso_ops_get(void) { - return ACCESS_ONCE(calipso_ops); + return READ_ONCE(calipso_ops); } /** diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d396cb61a280..eb866647a27a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -14201,7 +14201,7 @@ static bool __nl80211_unexpected_frame(struct net_device *dev, u8 cmd, struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct sk_buff *msg; void *hdr; - u32 nlportid = ACCESS_ONCE(wdev->ap_unexpected_nlportid); + u32 nlportid = READ_ONCE(wdev->ap_unexpected_nlportid); if (!nlportid) return false; diff --git a/sound/firewire/amdtp-am824.c b/sound/firewire/amdtp-am824.c index 23ccddb20de1..4210e5c6262e 100644 --- a/sound/firewire/amdtp-am824.c +++ b/sound/firewire/amdtp-am824.c @@ -247,7 +247,7 @@ void amdtp_am824_midi_trigger(struct amdtp_stream *s, unsigned int port, struct amdtp_am824 *p = s->protocol; if (port < p->midi_ports) - ACCESS_ONCE(p->midi[port]) = midi; + WRITE_ONCE(p->midi[port], midi); } EXPORT_SYMBOL_GPL(amdtp_am824_midi_trigger); @@ -336,7 +336,7 @@ static unsigned int process_rx_data_blocks(struct amdtp_stream *s, __be32 *buffe unsigned int data_blocks, unsigned int *syt) { struct amdtp_am824 *p = s->protocol; - struct snd_pcm_substream *pcm = ACCESS_ONCE(s->pcm); + struct snd_pcm_substream *pcm = READ_ONCE(s->pcm); unsigned int pcm_frames; if (pcm) { @@ -357,7 +357,7 @@ static unsigned int process_tx_data_blocks(struct amdtp_stream *s, __be32 *buffe unsigned int data_blocks, unsigned int *syt) { struct amdtp_am824 *p = s->protocol; - struct snd_pcm_substream *pcm = ACCESS_ONCE(s->pcm); + struct snd_pcm_substream *pcm = READ_ONCE(s->pcm); unsigned int pcm_frames; if (pcm) { diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index 3fc581a5ad62..4a1dc145327b 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -376,7 +376,7 @@ static void update_pcm_pointers(struct amdtp_stream *s, ptr = s->pcm_buffer_pointer + frames; if (ptr >= pcm->runtime->buffer_size) ptr -= pcm->runtime->buffer_size; - ACCESS_ONCE(s->pcm_buffer_pointer) = ptr; + WRITE_ONCE(s->pcm_buffer_pointer, ptr); s->pcm_period_pointer += frames; if (s->pcm_period_pointer >= pcm->runtime->period_size) { @@ -388,7 +388,7 @@ static void update_pcm_pointers(struct amdtp_stream *s, static void pcm_period_tasklet(unsigned long data) { struct amdtp_stream *s = (void *)data; - struct snd_pcm_substream *pcm = ACCESS_ONCE(s->pcm); + struct snd_pcm_substream *pcm = READ_ONCE(s->pcm); if (pcm) snd_pcm_period_elapsed(pcm); @@ -453,7 +453,7 @@ static int handle_out_packet(struct amdtp_stream *s, s->data_block_counter = (s->data_block_counter + data_blocks) & 0xff; - buffer[0] = cpu_to_be32(ACCESS_ONCE(s->source_node_id_field) | + buffer[0] = cpu_to_be32(READ_ONCE(s->source_node_id_field) | (s->data_block_quadlets << CIP_DBS_SHIFT) | ((s->sph << CIP_SPH_SHIFT) & CIP_SPH_MASK) | s->data_block_counter); @@ -472,7 +472,7 @@ static int handle_out_packet(struct amdtp_stream *s, if (queue_out_packet(s, payload_length) < 0) return -EIO; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm && pcm_frames > 0) update_pcm_pointers(s, pcm, pcm_frames); @@ -504,7 +504,7 @@ static int handle_out_packet_without_header(struct amdtp_stream *s, if (queue_out_packet(s, payload_length) < 0) return -EIO; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm && pcm_frames > 0) update_pcm_pointers(s, pcm, pcm_frames); @@ -621,7 +621,7 @@ end: if (queue_in_packet(s) < 0) return -EIO; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm && pcm_frames > 0) update_pcm_pointers(s, pcm, pcm_frames); @@ -649,7 +649,7 @@ static int handle_in_packet_without_header(struct amdtp_stream *s, if (queue_in_packet(s) < 0) return -EIO; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm && pcm_frames > 0) update_pcm_pointers(s, pcm, pcm_frames); @@ -947,7 +947,7 @@ unsigned long amdtp_stream_pcm_pointer(struct amdtp_stream *s) if (!in_interrupt() && amdtp_stream_running(s)) fw_iso_context_flush_completions(s->context); - return ACCESS_ONCE(s->pcm_buffer_pointer); + return READ_ONCE(s->pcm_buffer_pointer); } EXPORT_SYMBOL(amdtp_stream_pcm_pointer); @@ -977,9 +977,8 @@ EXPORT_SYMBOL(amdtp_stream_pcm_ack); void amdtp_stream_update(struct amdtp_stream *s) { /* Precomputing. */ - ACCESS_ONCE(s->source_node_id_field) = - (fw_parent_device(s->unit)->card->node_id << CIP_SID_SHIFT) & - CIP_SID_MASK; + WRITE_ONCE(s->source_node_id_field, + (fw_parent_device(s->unit)->card->node_id << CIP_SID_SHIFT) & CIP_SID_MASK); } EXPORT_SYMBOL(amdtp_stream_update); @@ -1022,7 +1021,7 @@ void amdtp_stream_pcm_abort(struct amdtp_stream *s) { struct snd_pcm_substream *pcm; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm) snd_pcm_stop_xrun(pcm); } diff --git a/sound/firewire/amdtp-stream.h b/sound/firewire/amdtp-stream.h index ed6eafd10992..f9abd8b07ce6 100644 --- a/sound/firewire/amdtp-stream.h +++ b/sound/firewire/amdtp-stream.h @@ -220,7 +220,7 @@ static inline bool amdtp_stream_pcm_running(struct amdtp_stream *s) static inline void amdtp_stream_pcm_trigger(struct amdtp_stream *s, struct snd_pcm_substream *pcm) { - ACCESS_ONCE(s->pcm) = pcm; + WRITE_ONCE(s->pcm, pcm); } static inline bool cip_sfc_is_base_44100(enum cip_sfc sfc) diff --git a/sound/firewire/digi00x/amdtp-dot.c b/sound/firewire/digi00x/amdtp-dot.c index 1453c34ce99f..4a884a335248 100644 --- a/sound/firewire/digi00x/amdtp-dot.c +++ b/sound/firewire/digi00x/amdtp-dot.c @@ -327,7 +327,7 @@ void amdtp_dot_midi_trigger(struct amdtp_stream *s, unsigned int port, struct amdtp_dot *p = s->protocol; if (port < MAX_MIDI_PORTS) - ACCESS_ONCE(p->midi[port]) = midi; + WRITE_ONCE(p->midi[port], midi); } static unsigned int process_tx_data_blocks(struct amdtp_stream *s, @@ -338,7 +338,7 @@ static unsigned int process_tx_data_blocks(struct amdtp_stream *s, struct snd_pcm_substream *pcm; unsigned int pcm_frames; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm) { read_pcm_s32(s, pcm, buffer, data_blocks); pcm_frames = data_blocks; @@ -359,7 +359,7 @@ static unsigned int process_rx_data_blocks(struct amdtp_stream *s, struct snd_pcm_substream *pcm; unsigned int pcm_frames; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm) { write_pcm_s32(s, pcm, buffer, data_blocks); pcm_frames = data_blocks; diff --git a/sound/firewire/fireface/amdtp-ff.c b/sound/firewire/fireface/amdtp-ff.c index 780da9deb2f0..77c7598b61ab 100644 --- a/sound/firewire/fireface/amdtp-ff.c +++ b/sound/firewire/fireface/amdtp-ff.c @@ -108,7 +108,7 @@ static unsigned int process_rx_data_blocks(struct amdtp_stream *s, unsigned int data_blocks, unsigned int *syt) { - struct snd_pcm_substream *pcm = ACCESS_ONCE(s->pcm); + struct snd_pcm_substream *pcm = READ_ONCE(s->pcm); unsigned int pcm_frames; if (pcm) { @@ -127,7 +127,7 @@ static unsigned int process_tx_data_blocks(struct amdtp_stream *s, unsigned int data_blocks, unsigned int *syt) { - struct snd_pcm_substream *pcm = ACCESS_ONCE(s->pcm); + struct snd_pcm_substream *pcm = READ_ONCE(s->pcm); unsigned int pcm_frames; if (pcm) { diff --git a/sound/firewire/fireface/ff-midi.c b/sound/firewire/fireface/ff-midi.c index 949ee56b4e0e..6a49611ee462 100644 --- a/sound/firewire/fireface/ff-midi.c +++ b/sound/firewire/fireface/ff-midi.c @@ -22,7 +22,7 @@ static int midi_playback_open(struct snd_rawmidi_substream *substream) ff->running_status[substream->number] = 0; ff->rx_midi_error[substream->number] = false; - ACCESS_ONCE(ff->rx_midi_substreams[substream->number]) = substream; + WRITE_ONCE(ff->rx_midi_substreams[substream->number], substream); return 0; } @@ -38,7 +38,7 @@ static int midi_playback_close(struct snd_rawmidi_substream *substream) struct snd_ff *ff = substream->rmidi->private_data; cancel_work_sync(&ff->rx_midi_work[substream->number]); - ACCESS_ONCE(ff->rx_midi_substreams[substream->number]) = NULL; + WRITE_ONCE(ff->rx_midi_substreams[substream->number], NULL); return 0; } @@ -52,10 +52,10 @@ static void midi_capture_trigger(struct snd_rawmidi_substream *substream, spin_lock_irqsave(&ff->lock, flags); if (up) - ACCESS_ONCE(ff->tx_midi_substreams[substream->number]) = - substream; + WRITE_ONCE(ff->tx_midi_substreams[substream->number], + substream); else - ACCESS_ONCE(ff->tx_midi_substreams[substream->number]) = NULL; + WRITE_ONCE(ff->tx_midi_substreams[substream->number], NULL); spin_unlock_irqrestore(&ff->lock, flags); } diff --git a/sound/firewire/fireface/ff-transaction.c b/sound/firewire/fireface/ff-transaction.c index dd6c8e839647..332b29f8ed75 100644 --- a/sound/firewire/fireface/ff-transaction.c +++ b/sound/firewire/fireface/ff-transaction.c @@ -12,7 +12,7 @@ static void finish_transmit_midi_msg(struct snd_ff *ff, unsigned int port, int rcode) { struct snd_rawmidi_substream *substream = - ACCESS_ONCE(ff->rx_midi_substreams[port]); + READ_ONCE(ff->rx_midi_substreams[port]); if (rcode_is_permanent_error(rcode)) { ff->rx_midi_error[port] = true; @@ -60,7 +60,7 @@ static inline void fill_midi_buf(struct snd_ff *ff, unsigned int port, static void transmit_midi_msg(struct snd_ff *ff, unsigned int port) { struct snd_rawmidi_substream *substream = - ACCESS_ONCE(ff->rx_midi_substreams[port]); + READ_ONCE(ff->rx_midi_substreams[port]); u8 *buf = (u8 *)ff->msg_buf[port]; int i, len; @@ -159,7 +159,7 @@ static void handle_midi_msg(struct fw_card *card, struct fw_request *request, */ index = (quad >> 8) & 0xff; if (index > 0) { - substream = ACCESS_ONCE(ff->tx_midi_substreams[0]); + substream = READ_ONCE(ff->tx_midi_substreams[0]); if (substream != NULL) { byte = quad & 0xff; snd_rawmidi_receive(substream, &byte, 1); @@ -169,7 +169,7 @@ static void handle_midi_msg(struct fw_card *card, struct fw_request *request, /* Message in second port. */ index = (quad >> 24) & 0xff; if (index > 0) { - substream = ACCESS_ONCE(ff->tx_midi_substreams[1]); + substream = READ_ONCE(ff->tx_midi_substreams[1]); if (substream != NULL) { byte = (quad >> 16) & 0xff; snd_rawmidi_receive(substream, &byte, 1); diff --git a/sound/firewire/isight.c b/sound/firewire/isight.c index 5826aa8362f1..46092fa3ff9b 100644 --- a/sound/firewire/isight.c +++ b/sound/firewire/isight.c @@ -96,7 +96,7 @@ static void isight_update_pointers(struct isight *isight, unsigned int count) ptr += count; if (ptr >= runtime->buffer_size) ptr -= runtime->buffer_size; - ACCESS_ONCE(isight->buffer_pointer) = ptr; + WRITE_ONCE(isight->buffer_pointer, ptr); isight->period_counter += count; if (isight->period_counter >= runtime->period_size) { @@ -111,7 +111,7 @@ static void isight_samples(struct isight *isight, struct snd_pcm_runtime *runtime; unsigned int count1; - if (!ACCESS_ONCE(isight->pcm_running)) + if (!READ_ONCE(isight->pcm_running)) return; runtime = isight->pcm->runtime; @@ -131,7 +131,7 @@ static void isight_samples(struct isight *isight, static void isight_pcm_abort(struct isight *isight) { - if (ACCESS_ONCE(isight->pcm_active)) + if (READ_ONCE(isight->pcm_active)) snd_pcm_stop_xrun(isight->pcm); } @@ -141,7 +141,7 @@ static void isight_dropped_samples(struct isight *isight, unsigned int total) u32 dropped; unsigned int count1; - if (!ACCESS_ONCE(isight->pcm_running)) + if (!READ_ONCE(isight->pcm_running)) return; runtime = isight->pcm->runtime; @@ -293,7 +293,7 @@ static int isight_hw_params(struct snd_pcm_substream *substream, if (err < 0) return err; - ACCESS_ONCE(isight->pcm_active) = true; + WRITE_ONCE(isight->pcm_active, true); return 0; } @@ -331,7 +331,7 @@ static int isight_hw_free(struct snd_pcm_substream *substream) { struct isight *isight = substream->private_data; - ACCESS_ONCE(isight->pcm_active) = false; + WRITE_ONCE(isight->pcm_active, false); mutex_lock(&isight->mutex); isight_stop_streaming(isight); @@ -424,10 +424,10 @@ static int isight_trigger(struct snd_pcm_substream *substream, int cmd) switch (cmd) { case SNDRV_PCM_TRIGGER_START: - ACCESS_ONCE(isight->pcm_running) = true; + WRITE_ONCE(isight->pcm_running, true); break; case SNDRV_PCM_TRIGGER_STOP: - ACCESS_ONCE(isight->pcm_running) = false; + WRITE_ONCE(isight->pcm_running, false); break; default: return -EINVAL; @@ -439,7 +439,7 @@ static snd_pcm_uframes_t isight_pointer(struct snd_pcm_substream *substream) { struct isight *isight = substream->private_data; - return ACCESS_ONCE(isight->buffer_pointer); + return READ_ONCE(isight->buffer_pointer); } static int isight_create_pcm(struct isight *isight) diff --git a/sound/firewire/motu/amdtp-motu.c b/sound/firewire/motu/amdtp-motu.c index 96f0091144bb..f0555a24d90e 100644 --- a/sound/firewire/motu/amdtp-motu.c +++ b/sound/firewire/motu/amdtp-motu.c @@ -310,7 +310,7 @@ static unsigned int process_tx_data_blocks(struct amdtp_stream *s, if (p->midi_ports) read_midi_messages(s, buffer, data_blocks); - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (data_blocks > 0 && pcm) read_pcm_s32(s, pcm->runtime, buffer, data_blocks); @@ -374,7 +374,7 @@ static unsigned int process_rx_data_blocks(struct amdtp_stream *s, if (p->midi_ports) write_midi_messages(s, buffer, data_blocks); - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm) write_pcm_s32(s, pcm->runtime, buffer, data_blocks); else diff --git a/sound/firewire/oxfw/oxfw-scs1x.c b/sound/firewire/oxfw/oxfw-scs1x.c index 02d595665898..f33497cdc706 100644 --- a/sound/firewire/oxfw/oxfw-scs1x.c +++ b/sound/firewire/oxfw/oxfw-scs1x.c @@ -112,7 +112,7 @@ static void handle_hss(struct fw_card *card, struct fw_request *request, } if (length >= 1) { - stream = ACCESS_ONCE(scs->input); + stream = READ_ONCE(scs->input); if (stream) midi_input_packet(scs, stream, data, length); } @@ -183,7 +183,7 @@ static void scs_output_work(struct work_struct *work) if (scs->transaction_running) return; - stream = ACCESS_ONCE(scs->output); + stream = READ_ONCE(scs->output); if (!stream || scs->error) { scs->output_idle = true; wake_up(&scs->idle_wait); @@ -291,9 +291,9 @@ static void midi_capture_trigger(struct snd_rawmidi_substream *stream, int up) if (up) { scs->input_escape_count = 0; - ACCESS_ONCE(scs->input) = stream; + WRITE_ONCE(scs->input, stream); } else { - ACCESS_ONCE(scs->input) = NULL; + WRITE_ONCE(scs->input, NULL); } } @@ -319,10 +319,10 @@ static void midi_playback_trigger(struct snd_rawmidi_substream *stream, int up) scs->transaction_bytes = 0; scs->error = false; - ACCESS_ONCE(scs->output) = stream; + WRITE_ONCE(scs->output, stream); schedule_work(&scs->work); } else { - ACCESS_ONCE(scs->output) = NULL; + WRITE_ONCE(scs->output, NULL); } } static void midi_playback_drain(struct snd_rawmidi_substream *stream) diff --git a/sound/firewire/tascam/amdtp-tascam.c b/sound/firewire/tascam/amdtp-tascam.c index 6aff1fc1c72d..ab482423c165 100644 --- a/sound/firewire/tascam/amdtp-tascam.c +++ b/sound/firewire/tascam/amdtp-tascam.c @@ -124,7 +124,7 @@ static unsigned int process_tx_data_blocks(struct amdtp_stream *s, { struct snd_pcm_substream *pcm; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (data_blocks > 0 && pcm) read_pcm_s32(s, pcm, buffer, data_blocks); @@ -143,7 +143,7 @@ static unsigned int process_rx_data_blocks(struct amdtp_stream *s, /* This field is not used. */ *syt = 0x0000; - pcm = ACCESS_ONCE(s->pcm); + pcm = READ_ONCE(s->pcm); if (pcm) write_pcm_s32(s, pcm, buffer, data_blocks); else diff --git a/sound/firewire/tascam/tascam-transaction.c b/sound/firewire/tascam/tascam-transaction.c index 8967c52f5032..2ad692dd4b13 100644 --- a/sound/firewire/tascam/tascam-transaction.c +++ b/sound/firewire/tascam/tascam-transaction.c @@ -148,7 +148,7 @@ static void async_midi_port_callback(struct fw_card *card, int rcode, void *callback_data) { struct snd_fw_async_midi_port *port = callback_data; - struct snd_rawmidi_substream *substream = ACCESS_ONCE(port->substream); + struct snd_rawmidi_substream *substream = READ_ONCE(port->substream); /* This port is closed. */ if (substream == NULL) @@ -173,7 +173,7 @@ static void midi_port_work(struct work_struct *work) { struct snd_fw_async_midi_port *port = container_of(work, struct snd_fw_async_midi_port, work); - struct snd_rawmidi_substream *substream = ACCESS_ONCE(port->substream); + struct snd_rawmidi_substream *substream = READ_ONCE(port->substream); int generation; /* Under transacting or error state. */ @@ -282,7 +282,7 @@ static void handle_midi_tx(struct fw_card *card, struct fw_request *request, bytes = 3; } - substream = ACCESS_ONCE(tscm->tx_midi_substreams[port]); + substream = READ_ONCE(tscm->tx_midi_substreams[port]); if (substream != NULL) snd_rawmidi_receive(substream, b + 1, bytes); } diff --git a/sound/soc/xtensa/xtfpga-i2s.c b/sound/soc/xtensa/xtfpga-i2s.c index 8382ffa3bcaf..2472144b329e 100644 --- a/sound/soc/xtensa/xtfpga-i2s.c +++ b/sound/soc/xtensa/xtfpga-i2s.c @@ -165,7 +165,7 @@ static bool xtfpga_pcm_push_tx(struct xtfpga_i2s *i2s) tx_substream = rcu_dereference(i2s->tx_substream); tx_active = tx_substream && snd_pcm_running(tx_substream); if (tx_active) { - unsigned tx_ptr = ACCESS_ONCE(i2s->tx_ptr); + unsigned tx_ptr = READ_ONCE(i2s->tx_ptr); unsigned new_tx_ptr = i2s->tx_fn(i2s, tx_substream->runtime, tx_ptr); @@ -437,7 +437,7 @@ static int xtfpga_pcm_trigger(struct snd_pcm_substream *substream, int cmd) case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: - ACCESS_ONCE(i2s->tx_ptr) = 0; + WRITE_ONCE(i2s->tx_ptr, 0); rcu_assign_pointer(i2s->tx_substream, substream); xtfpga_pcm_refill_fifo(i2s); break; @@ -459,7 +459,7 @@ static snd_pcm_uframes_t xtfpga_pcm_pointer(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; struct xtfpga_i2s *i2s = runtime->private_data; - snd_pcm_uframes_t pos = ACCESS_ONCE(i2s->tx_ptr); + snd_pcm_uframes_t pos = READ_ONCE(i2s->tx_ptr); return pos < runtime->buffer_size ? pos : 0; } diff --git a/sound/usb/bcd2000/bcd2000.c b/sound/usb/bcd2000/bcd2000.c index 7371e5b06035..fc579f330601 100644 --- a/sound/usb/bcd2000/bcd2000.c +++ b/sound/usb/bcd2000/bcd2000.c @@ -108,7 +108,7 @@ static void bcd2000_midi_handle_input(struct bcd2000 *bcd2k, unsigned int payload_length, tocopy; struct snd_rawmidi_substream *midi_receive_substream; - midi_receive_substream = ACCESS_ONCE(bcd2k->midi_receive_substream); + midi_receive_substream = READ_ONCE(bcd2k->midi_receive_substream); if (!midi_receive_substream) return; @@ -139,7 +139,7 @@ static void bcd2000_midi_send(struct bcd2000 *bcd2k) BUILD_BUG_ON(sizeof(device_cmd_prefix) >= BUFSIZE); - midi_out_substream = ACCESS_ONCE(bcd2k->midi_out_substream); + midi_out_substream = READ_ONCE(bcd2k->midi_out_substream); if (!midi_out_substream) return; diff --git a/tools/arch/x86/include/asm/atomic.h b/tools/arch/x86/include/asm/atomic.h index 328eeceec709..96e2d06cb031 100644 --- a/tools/arch/x86/include/asm/atomic.h +++ b/tools/arch/x86/include/asm/atomic.h @@ -24,7 +24,7 @@ */ static inline int atomic_read(const atomic_t *v) { - return ACCESS_ONCE((v)->counter); + return READ_ONCE((v)->counter); } /** diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h index 5e9738f97bf3..97427e700e3b 100644 --- a/tools/include/asm-generic/atomic-gcc.h +++ b/tools/include/asm-generic/atomic-gcc.h @@ -21,7 +21,7 @@ */ static inline int atomic_read(const atomic_t *v) { - return ACCESS_ONCE((v)->counter); + return READ_ONCE((v)->counter); } /** diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 33b5e6cdf38c..d19e11b68de7 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -378,7 +378,7 @@ struct addr_filters { static inline u64 auxtrace_mmap__read_snapshot_head(struct auxtrace_mmap *mm) { struct perf_event_mmap_page *pc = mm->userpg; - u64 head = ACCESS_ONCE(pc->aux_head); + u64 head = READ_ONCE(pc->aux_head); /* Ensure all reads are done after we read the head */ rmb(); @@ -389,7 +389,7 @@ static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm) { struct perf_event_mmap_page *pc = mm->userpg; #if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT) - u64 head = ACCESS_ONCE(pc->aux_head); + u64 head = READ_ONCE(pc->aux_head); #else u64 head = __sync_val_compare_and_swap(&pc->aux_head, 0, 0); #endif diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 47b5e7dbcb18..aae9645c7122 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -113,7 +113,7 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session, extern volatile int session_done; -#define session_done() ACCESS_ONCE(session_done) +#define session_done() READ_ONCE(session_done) int perf_session__deliver_synth_event(struct perf_session *session, union perf_event *event, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 9deb5a245b83..ce507ae1d4f5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2302,7 +2302,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) continue; } else if (pass && i > last_boosted_vcpu) break; - if (!ACCESS_ONCE(vcpu->preempted)) + if (!READ_ONCE(vcpu->preempted)) continue; if (vcpu == me) continue; -- cgit v1.3-8-gc7d7 From 46209401f8f6116bd0b2c2d14a63958e83ffca0b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 3 Nov 2017 11:46:25 +0100 Subject: net: core: introduce mini_Qdisc and eliminate usage of tp->q for clsact fastpath In sch_handle_egress and sch_handle_ingress tp->q is used only in order to update stats. So stats and filter list are the only things that are needed in clsact qdisc fastpath processing. Introduce new mini_Qdisc struct to hold those items. Also, introduce a helper to swap the mini_Qdisc structures in case filter list head changes. This removes need for tp->q usage without added overhead. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 ++++++--- include/net/sch_generic.h | 32 ++++++++++++++++++++++++++++++++ net/core/dev.c | 21 +++++++++++---------- net/sched/sch_generic.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ net/sched/sch_ingress.c | 19 ++++++++++++++----- 5 files changed, 109 insertions(+), 18 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5e02f79b2110..7de7656550c2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1559,6 +1559,8 @@ enum netdev_priv_flags { * * @rx_handler: handler for received packets * @rx_handler_data: XXX: need comments on this one + * @miniq_ingress: ingress/clsact qdisc specific data for + * ingress processing * @ingress_queue: XXX: need comments on this one * @broadcast: hw bcast address * @@ -1576,7 +1578,8 @@ enum netdev_priv_flags { * @tx_global_lock: XXX: need comments on this one * * @xps_maps: XXX: need comments on this one - * + * @miniq_egress: clsact qdisc specific data for + * egress processing * @watchdog_timeo: Represents the timeout that is used by * the watchdog (see dev_watchdog()) * @watchdog_timer: List of timers @@ -1795,7 +1798,7 @@ struct net_device { void __rcu *rx_handler_data; #ifdef CONFIG_NET_CLS_ACT - struct tcf_proto __rcu *ingress_cl_list; + struct mini_Qdisc __rcu *miniq_ingress; #endif struct netdev_queue __rcu *ingress_queue; #ifdef CONFIG_NETFILTER_INGRESS @@ -1826,7 +1829,7 @@ struct net_device { struct xps_dev_maps __rcu *xps_maps; #endif #ifdef CONFIG_NET_CLS_ACT - struct tcf_proto __rcu *egress_cl_list; + struct mini_Qdisc __rcu *miniq_egress; #endif /* These may be needed for future network-power-down code. */ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index f230269e0bfb..c64e62c9450a 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -904,4 +904,36 @@ static inline void psched_ratecfg_getrate(struct tc_ratespec *res, res->linklayer = (r->linklayer & TC_LINKLAYER_MASK); } +/* Mini Qdisc serves for specific needs of ingress/clsact Qdisc. + * The fast path only needs to access filter list and to update stats + */ +struct mini_Qdisc { + struct tcf_proto *filter_list; + struct gnet_stats_basic_cpu __percpu *cpu_bstats; + struct gnet_stats_queue __percpu *cpu_qstats; + struct rcu_head rcu; +}; + +static inline void mini_qdisc_bstats_cpu_update(struct mini_Qdisc *miniq, + const struct sk_buff *skb) +{ + bstats_cpu_update(this_cpu_ptr(miniq->cpu_bstats), skb); +} + +static inline void mini_qdisc_qstats_cpu_drop(struct mini_Qdisc *miniq) +{ + this_cpu_inc(miniq->cpu_qstats->drops); +} + +struct mini_Qdisc_pair { + struct mini_Qdisc miniq1; + struct mini_Qdisc miniq2; + struct mini_Qdisc __rcu **p_miniq; +}; + +void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, + struct tcf_proto *tp_head); +void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, + struct mini_Qdisc __rcu **p_miniq); + #endif diff --git a/net/core/dev.c b/net/core/dev.c index 24ac9083bc13..1423cf4d695c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3274,22 +3274,22 @@ EXPORT_SYMBOL(dev_loopback_xmit); static struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { - struct tcf_proto *cl = rcu_dereference_bh(dev->egress_cl_list); + struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress); struct tcf_result cl_res; - if (!cl) + if (!miniq) return skb; /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ - qdisc_bstats_cpu_update(cl->q, skb); + mini_qdisc_bstats_cpu_update(miniq, skb); - switch (tcf_classify(skb, cl, &cl_res, false)) { + switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); break; case TC_ACT_SHOT: - qdisc_qstats_cpu_drop(cl->q); + mini_qdisc_qstats_cpu_drop(miniq); *ret = NET_XMIT_DROP; kfree_skb(skb); return NULL; @@ -4189,7 +4189,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { #ifdef CONFIG_NET_CLS_ACT - struct tcf_proto *cl = rcu_dereference_bh(skb->dev->ingress_cl_list); + struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress); struct tcf_result cl_res; /* If there's at least one ingress present somewhere (so @@ -4197,8 +4197,9 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, * that are not configured with an ingress qdisc will bail * out here. */ - if (!cl) + if (!miniq) return skb; + if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; @@ -4206,15 +4207,15 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, qdisc_skb_cb(skb)->pkt_len = skb->len; skb->tc_at_ingress = 1; - qdisc_bstats_cpu_update(cl->q, skb); + mini_qdisc_bstats_cpu_update(miniq, skb); - switch (tcf_classify(skb, cl, &cl_res, false)) { + switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); break; case TC_ACT_SHOT: - qdisc_qstats_cpu_drop(cl->q); + mini_qdisc_qstats_cpu_drop(miniq); kfree_skb(skb); return NULL; case TC_ACT_STOLEN: diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index aa74aa42b5d7..3839cbbdc32b 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1024,3 +1024,49 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r, } } EXPORT_SYMBOL(psched_ratecfg_precompute); + +static void mini_qdisc_rcu_func(struct rcu_head *head) +{ +} + +void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, + struct tcf_proto *tp_head) +{ + struct mini_Qdisc *miniq_old = rtnl_dereference(*miniqp->p_miniq); + struct mini_Qdisc *miniq; + + if (!tp_head) { + RCU_INIT_POINTER(*miniqp->p_miniq, NULL); + return; + } + + miniq = !miniq_old || miniq_old == &miniqp->miniq2 ? + &miniqp->miniq1 : &miniqp->miniq2; + + /* We need to make sure that readers won't see the miniq + * we are about to modify. So wait until previous call_rcu_bh callback + * is done. + */ + rcu_barrier_bh(); + miniq->filter_list = tp_head; + rcu_assign_pointer(*miniqp->p_miniq, miniq); + + if (miniq_old) + /* This is counterpart of the rcu barrier above. We need to + * block potential new user of miniq_old until all readers + * are not seeing it. + */ + call_rcu_bh(&miniq_old->rcu, mini_qdisc_rcu_func); +} +EXPORT_SYMBOL(mini_qdisc_pair_swap); + +void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, + struct mini_Qdisc __rcu **p_miniq) +{ + miniqp->miniq1.cpu_bstats = qdisc->cpu_bstats; + miniqp->miniq1.cpu_qstats = qdisc->cpu_qstats; + miniqp->miniq2.cpu_bstats = qdisc->cpu_bstats; + miniqp->miniq2.cpu_qstats = qdisc->cpu_qstats; + miniqp->p_miniq = p_miniq; +} +EXPORT_SYMBOL(mini_qdisc_pair_init); diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 811845815b8c..5ecc38f35d47 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -21,6 +21,7 @@ struct ingress_sched_data { struct tcf_block *block; struct tcf_block_ext_info block_info; + struct mini_Qdisc_pair miniqp; }; static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg) @@ -56,9 +57,9 @@ static struct tcf_block *ingress_tcf_block(struct Qdisc *sch, unsigned long cl) static void clsact_chain_head_change(struct tcf_proto *tp_head, void *priv) { - struct tcf_proto __rcu **p_filter_chain = priv; + struct mini_Qdisc_pair *miniqp = priv; - rcu_assign_pointer(*p_filter_chain, tp_head); + mini_qdisc_pair_swap(miniqp, tp_head); } static int ingress_init(struct Qdisc *sch, struct nlattr *opt) @@ -67,9 +68,11 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) struct net_device *dev = qdisc_dev(sch); int err; + mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress); + q->block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS; q->block_info.chain_head_change = clsact_chain_head_change; - q->block_info.chain_head_change_priv = &dev->ingress_cl_list; + q->block_info.chain_head_change_priv = &q->miniqp; err = tcf_block_get_ext(&q->block, sch, &q->block_info); if (err) @@ -128,6 +131,8 @@ struct clsact_sched_data { struct tcf_block *egress_block; struct tcf_block_ext_info ingress_block_info; struct tcf_block_ext_info egress_block_info; + struct mini_Qdisc_pair miniqp_ingress; + struct mini_Qdisc_pair miniqp_egress; }; static unsigned long clsact_find(struct Qdisc *sch, u32 classid) @@ -167,17 +172,21 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) struct net_device *dev = qdisc_dev(sch); int err; + mini_qdisc_pair_init(&q->miniqp_ingress, sch, &dev->miniq_ingress); + q->ingress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS; q->ingress_block_info.chain_head_change = clsact_chain_head_change; - q->ingress_block_info.chain_head_change_priv = &dev->ingress_cl_list; + q->ingress_block_info.chain_head_change_priv = &q->miniqp_ingress; err = tcf_block_get_ext(&q->ingress_block, sch, &q->ingress_block_info); if (err) return err; + mini_qdisc_pair_init(&q->miniqp_egress, sch, &dev->miniq_egress); + q->egress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS; q->egress_block_info.chain_head_change = clsact_chain_head_change; - q->egress_block_info.chain_head_change_priv = &dev->egress_cl_list; + q->egress_block_info.chain_head_change_priv = &q->miniqp_egress; err = tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info); if (err) -- cgit v1.3-8-gc7d7 From f4e63525ee35f9c02e9f51f90571718363e9a9a9 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 3 Nov 2017 13:56:16 -0700 Subject: net: bpf: rename ndo_xdp to ndo_bpf ndo_xdp is a control path callback for setting up XDP in the driver. We can reuse it for other forms of communication between the eBPF stack and the drivers. Rename the callback and associated structures and definitions. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Quentin Monnet Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h | 2 +- drivers/net/ethernet/cavium/thunder/nicvf_main.c | 4 +-- drivers/net/ethernet/intel/i40e/i40e_main.c | 6 ++-- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 +-- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 6 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 +-- .../net/ethernet/netronome/nfp/nfp_net_common.c | 4 +-- drivers/net/ethernet/qlogic/qede/qede.h | 2 +- drivers/net/ethernet/qlogic/qede/qede_filter.c | 2 +- drivers/net/ethernet/qlogic/qede/qede_main.c | 4 +-- drivers/net/tun.c | 4 +-- drivers/net/virtio_net.c | 4 +-- include/linux/netdevice.h | 23 ++++++++------- net/core/dev.c | 34 +++++++++++----------- net/core/rtnetlink.c | 4 +-- 17 files changed, 56 insertions(+), 55 deletions(-) (limited to 'net/core/dev.c') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 4e3d569bf32e..96416f5d97f3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7775,7 +7775,7 @@ static const struct net_device_ops bnxt_netdev_ops = { #endif .ndo_udp_tunnel_add = bnxt_udp_tunnel_add, .ndo_udp_tunnel_del = bnxt_udp_tunnel_del, - .ndo_xdp = bnxt_xdp, + .ndo_bpf = bnxt_xdp, .ndo_bridge_getlink = bnxt_bridge_getlink, .ndo_bridge_setlink = bnxt_bridge_setlink, .ndo_get_phys_port_name = bnxt_get_phys_port_name diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 06ce63c00821..261e5847557a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -208,7 +208,7 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog) return 0; } -int bnxt_xdp(struct net_device *dev, struct netdev_xdp *xdp) +int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp) { struct bnxt *bp = netdev_priv(dev); int rc; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h index 12a5ad66b564..414b748038ca 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h @@ -16,6 +16,6 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts); bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, struct page *page, u8 **data_ptr, unsigned int *len, u8 *event); -int bnxt_xdp(struct net_device *dev, struct netdev_xdp *xdp); +int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp); #endif diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 71989e180289..a063c36c4c58 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1741,7 +1741,7 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog) return 0; } -static int nicvf_xdp(struct net_device *netdev, struct netdev_xdp *xdp) +static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp) { struct nicvf *nic = netdev_priv(netdev); @@ -1774,7 +1774,7 @@ static const struct net_device_ops nicvf_netdev_ops = { .ndo_tx_timeout = nicvf_tx_timeout, .ndo_fix_features = nicvf_fix_features, .ndo_set_features = nicvf_set_features, - .ndo_xdp = nicvf_xdp, + .ndo_bpf = nicvf_xdp, }; static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index dfecaeda0654..05b94d87a6c3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -11648,12 +11648,12 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, } /** - * i40e_xdp - implements ndo_xdp for i40e + * i40e_xdp - implements ndo_bpf for i40e * @dev: netdevice * @xdp: XDP command **/ static int i40e_xdp(struct net_device *dev, - struct netdev_xdp *xdp) + struct netdev_bpf *xdp) { struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; @@ -11705,7 +11705,7 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_features_check = i40e_features_check, .ndo_bridge_getlink = i40e_ndo_bridge_getlink, .ndo_bridge_setlink = i40e_ndo_bridge_setlink, - .ndo_xdp = i40e_xdp, + .ndo_bpf = i40e_xdp, }; /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 507977994a03..e5dcb25be398 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10004,7 +10004,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) return 0; } -static int ixgbe_xdp(struct net_device *dev, struct netdev_xdp *xdp) +static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp) { struct ixgbe_adapter *adapter = netdev_priv(dev); @@ -10113,7 +10113,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_udp_tunnel_add = ixgbe_add_udp_tunnel_port, .ndo_udp_tunnel_del = ixgbe_del_udp_tunnel_port, .ndo_features_check = ixgbe_features_check, - .ndo_xdp = ixgbe_xdp, + .ndo_bpf = ixgbe_xdp, .ndo_xdp_xmit = ixgbe_xdp_xmit, .ndo_xdp_flush = ixgbe_xdp_flush, }; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index d611df2f274d..736a6ccaf05e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2916,7 +2916,7 @@ static u32 mlx4_xdp_query(struct net_device *dev) return prog_id; } -static int mlx4_xdp(struct net_device *dev, struct netdev_xdp *xdp) +static int mlx4_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: @@ -2958,7 +2958,7 @@ static const struct net_device_ops mlx4_netdev_ops = { .ndo_udp_tunnel_del = mlx4_en_del_vxlan_port, .ndo_features_check = mlx4_en_features_check, .ndo_set_tx_maxrate = mlx4_en_set_tx_maxrate, - .ndo_xdp = mlx4_xdp, + .ndo_bpf = mlx4_xdp, }; static const struct net_device_ops mlx4_netdev_ops_master = { @@ -2995,7 +2995,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = { .ndo_udp_tunnel_del = mlx4_en_del_vxlan_port, .ndo_features_check = mlx4_en_features_check, .ndo_set_tx_maxrate = mlx4_en_set_tx_maxrate, - .ndo_xdp = mlx4_xdp, + .ndo_bpf = mlx4_xdp, }; struct mlx4_en_bond { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 28ae00b3eb88..3b7b7bb84eb0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3831,7 +3831,7 @@ static u32 mlx5e_xdp_query(struct net_device *dev) return prog_id; } -static int mlx5e_xdp(struct net_device *dev, struct netdev_xdp *xdp) +static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: @@ -3883,7 +3883,7 @@ static const struct net_device_ops mlx5e_netdev_ops = { .ndo_rx_flow_steer = mlx5e_rx_flow_steer, #endif .ndo_tx_timeout = mlx5e_tx_timeout, - .ndo_xdp = mlx5e_xdp, + .ndo_bpf = mlx5e_xdp, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = mlx5e_netpoll, #endif diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 185a3dd35a3f..f6c6ad4e8a59 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -3378,7 +3378,7 @@ nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog, u32 flags, return 0; } -static int nfp_net_xdp(struct net_device *netdev, struct netdev_xdp *xdp) +static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp) { struct nfp_net *nn = netdev_priv(netdev); @@ -3441,7 +3441,7 @@ const struct net_device_ops nfp_net_netdev_ops = { .ndo_get_phys_port_name = nfp_port_get_phys_port_name, .ndo_udp_tunnel_add = nfp_net_add_vxlan_port, .ndo_udp_tunnel_del = nfp_net_del_vxlan_port, - .ndo_xdp = nfp_net_xdp, + .ndo_bpf = nfp_net_xdp, }; /** diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index adb700512baa..a3a70ade411f 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -503,7 +503,7 @@ void qede_fill_rss_params(struct qede_dev *edev, void qede_udp_tunnel_add(struct net_device *dev, struct udp_tunnel_info *ti); void qede_udp_tunnel_del(struct net_device *dev, struct udp_tunnel_info *ti); -int qede_xdp(struct net_device *dev, struct netdev_xdp *xdp); +int qede_xdp(struct net_device *dev, struct netdev_bpf *xdp); #ifdef CONFIG_DCB void qede_set_dcbnl_ops(struct net_device *ndev); diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index f79e36e4060a..c1a0708a7d7c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -1065,7 +1065,7 @@ static int qede_xdp_set(struct qede_dev *edev, struct bpf_prog *prog) return 0; } -int qede_xdp(struct net_device *dev, struct netdev_xdp *xdp) +int qede_xdp(struct net_device *dev, struct netdev_bpf *xdp) { struct qede_dev *edev = netdev_priv(dev); diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index e5ee9f274a71..8f9b3eb82137 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -556,7 +556,7 @@ static const struct net_device_ops qede_netdev_ops = { .ndo_udp_tunnel_add = qede_udp_tunnel_add, .ndo_udp_tunnel_del = qede_udp_tunnel_del, .ndo_features_check = qede_features_check, - .ndo_xdp = qede_xdp, + .ndo_bpf = qede_xdp, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = qede_rx_flow_steer, #endif @@ -594,7 +594,7 @@ static const struct net_device_ops qede_netdev_vf_xdp_ops = { .ndo_udp_tunnel_add = qede_udp_tunnel_add, .ndo_udp_tunnel_del = qede_udp_tunnel_del, .ndo_features_check = qede_features_check, - .ndo_xdp = qede_xdp, + .ndo_bpf = qede_xdp, }; /* ------------------------------------------------------------------------- diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 8125956f62a1..1a326b697221 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1141,7 +1141,7 @@ static u32 tun_xdp_query(struct net_device *dev) return 0; } -static int tun_xdp(struct net_device *dev, struct netdev_xdp *xdp) +static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: @@ -1185,7 +1185,7 @@ static const struct net_device_ops tap_netdev_ops = { .ndo_features_check = passthru_features_check, .ndo_set_rx_headroom = tun_set_headroom, .ndo_get_stats64 = tun_net_get_stats64, - .ndo_xdp = tun_xdp, + .ndo_bpf = tun_xdp, }; static void tun_flow_init(struct tun_struct *tun) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index fc059f193e7d..edf984406ba0 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2088,7 +2088,7 @@ static u32 virtnet_xdp_query(struct net_device *dev) return 0; } -static int virtnet_xdp(struct net_device *dev, struct netdev_xdp *xdp) +static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: @@ -2115,7 +2115,7 @@ static const struct net_device_ops virtnet_netdev = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = virtnet_netpoll, #endif - .ndo_xdp = virtnet_xdp, + .ndo_bpf = virtnet_xdp, .ndo_xdp_xmit = virtnet_xdp_xmit, .ndo_xdp_flush = virtnet_xdp_flush, .ndo_features_check = passthru_features_check, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7de7656550c2..9af9feaaeb64 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -779,10 +779,10 @@ enum tc_setup_type { TC_SETUP_CBS, }; -/* These structures hold the attributes of xdp state that are being passed - * to the netdevice through the xdp op. +/* These structures hold the attributes of bpf state that are being passed + * to the netdevice through the bpf op. */ -enum xdp_netdev_command { +enum bpf_netdev_command { /* Set or clear a bpf program used in the earliest stages of packet * rx. The prog will have been loaded as BPF_PROG_TYPE_XDP. The callee * is responsible for calling bpf_prog_put on any old progs that are @@ -801,8 +801,8 @@ enum xdp_netdev_command { struct netlink_ext_ack; -struct netdev_xdp { - enum xdp_netdev_command command; +struct netdev_bpf { + enum bpf_netdev_command command; union { /* XDP_SETUP_PROG */ struct { @@ -1124,9 +1124,10 @@ struct dev_ifalias { * appropriate rx headroom value allows avoiding skb head copy on * forward. Setting a negative value resets the rx headroom to the * default value. - * int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp); + * int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); * This function is used to set or query state related to XDP on the - * netdevice. See definition of enum xdp_netdev_command for details. + * netdevice and manage BPF offload. See definition of + * enum bpf_netdev_command for details. * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp); * This function is used to submit a XDP packet for transmit on a * netdevice. @@ -1315,8 +1316,8 @@ struct net_device_ops { struct sk_buff *skb); void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom); - int (*ndo_xdp)(struct net_device *dev, - struct netdev_xdp *xdp); + int (*ndo_bpf)(struct net_device *dev, + struct netdev_bpf *bpf); int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp); void (*ndo_xdp_flush)(struct net_device *dev); @@ -3311,10 +3312,10 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); -typedef int (*xdp_op_t)(struct net_device *dev, struct netdev_xdp *xdp); +typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, u32 flags); -u8 __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op, u32 *prog_id); +u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t xdp_op, u32 *prog_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); diff --git a/net/core/dev.c b/net/core/dev.c index 1423cf4d695c..10cde58d3275 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4545,7 +4545,7 @@ static int __netif_receive_skb(struct sk_buff *skb) return ret; } -static int generic_xdp_install(struct net_device *dev, struct netdev_xdp *xdp) +static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) { struct bpf_prog *old = rtnl_dereference(dev->xdp_prog); struct bpf_prog *new = xdp->prog; @@ -7090,26 +7090,26 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down) } EXPORT_SYMBOL(dev_change_proto_down); -u8 __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op, u32 *prog_id) +u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op, u32 *prog_id) { - struct netdev_xdp xdp; + struct netdev_bpf xdp; memset(&xdp, 0, sizeof(xdp)); xdp.command = XDP_QUERY_PROG; /* Query must always succeed. */ - WARN_ON(xdp_op(dev, &xdp) < 0); + WARN_ON(bpf_op(dev, &xdp) < 0); if (prog_id) *prog_id = xdp.prog_id; return xdp.prog_attached; } -static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op, +static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op, struct netlink_ext_ack *extack, u32 flags, struct bpf_prog *prog) { - struct netdev_xdp xdp; + struct netdev_bpf xdp; memset(&xdp, 0, sizeof(xdp)); if (flags & XDP_FLAGS_HW_MODE) @@ -7120,7 +7120,7 @@ static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op, xdp.flags = flags; xdp.prog = prog; - return xdp_op(dev, &xdp); + return bpf_op(dev, &xdp); } /** @@ -7137,24 +7137,24 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, { const struct net_device_ops *ops = dev->netdev_ops; struct bpf_prog *prog = NULL; - xdp_op_t xdp_op, xdp_chk; + bpf_op_t bpf_op, bpf_chk; int err; ASSERT_RTNL(); - xdp_op = xdp_chk = ops->ndo_xdp; - if (!xdp_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) + bpf_op = bpf_chk = ops->ndo_bpf; + if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) return -EOPNOTSUPP; - if (!xdp_op || (flags & XDP_FLAGS_SKB_MODE)) - xdp_op = generic_xdp_install; - if (xdp_op == xdp_chk) - xdp_chk = generic_xdp_install; + if (!bpf_op || (flags & XDP_FLAGS_SKB_MODE)) + bpf_op = generic_xdp_install; + if (bpf_op == bpf_chk) + bpf_chk = generic_xdp_install; if (fd >= 0) { - if (xdp_chk && __dev_xdp_attached(dev, xdp_chk, NULL)) + if (bpf_chk && __dev_xdp_attached(dev, bpf_chk, NULL)) return -EEXIST; if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && - __dev_xdp_attached(dev, xdp_op, NULL)) + __dev_xdp_attached(dev, bpf_op, NULL)) return -EBUSY; prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); @@ -7162,7 +7162,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, return PTR_ERR(prog); } - err = dev_xdp_install(dev, xdp_op, extack, flags, prog); + err = dev_xdp_install(dev, bpf_op, extack, flags, prog); if (err < 0 && prog) bpf_prog_put(prog); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8a8c51937edf..dc5ad84ac096 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1270,10 +1270,10 @@ static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id) *prog_id = generic_xdp_prog->aux->id; return XDP_ATTACHED_SKB; } - if (!ops->ndo_xdp) + if (!ops->ndo_bpf) return XDP_ATTACHED_NONE; - return __dev_xdp_attached(dev, ops->ndo_xdp, prog_id); + return __dev_xdp_attached(dev, ops->ndo_bpf, prog_id); } static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) -- cgit v1.3-8-gc7d7 From 248f346ffe9508dee0039db4ac839cb31ba3bdec Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 3 Nov 2017 13:56:20 -0700 Subject: xdp: allow attaching programs loaded for specific device Pass the netdev pointer to bpf_prog_get_type(). This way BPF code can decide whether the device matches what the code was loaded/translated for. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Quentin Monnet Signed-off-by: David S. Miller --- include/linux/bpf.h | 10 ++++++++++ kernel/bpf/syscall.c | 33 +++++++++++++++++++++++++++++---- net/core/dev.c | 6 +++++- 3 files changed, 44 insertions(+), 5 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 98bacd0fa5cc..c397934f91dd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -335,6 +335,8 @@ extern const struct bpf_verifier_ops xdp_analyzer_ops; struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); +struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, + struct net_device *netdev); struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog); @@ -428,6 +430,14 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, { return ERR_PTR(-EOPNOTSUPP); } + +static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, + enum bpf_prog_type type, + struct net_device *netdev) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3217c20ea91b..68f9123acd39 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1057,7 +1057,22 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) } EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); -static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type) +static bool bpf_prog_can_attach(struct bpf_prog *prog, + enum bpf_prog_type *attach_type, + struct net_device *netdev) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + + if (prog->type != *attach_type) + return false; + if (offload && offload->netdev != netdev) + return false; + + return true; +} + +static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, + struct net_device *netdev) { struct fd f = fdget(ufd); struct bpf_prog *prog; @@ -1065,7 +1080,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type) prog = ____bpf_prog_get(f); if (IS_ERR(prog)) return prog; - if (attach_type && (prog->type != *attach_type || prog->aux->offload)) { + if (attach_type && !bpf_prog_can_attach(prog, attach_type, netdev)) { prog = ERR_PTR(-EINVAL); goto out; } @@ -1078,12 +1093,12 @@ out: struct bpf_prog *bpf_prog_get(u32 ufd) { - return __bpf_prog_get(ufd, NULL); + return __bpf_prog_get(ufd, NULL, NULL); } struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) { - struct bpf_prog *prog = __bpf_prog_get(ufd, &type); + struct bpf_prog *prog = __bpf_prog_get(ufd, &type, NULL); if (!IS_ERR(prog)) trace_bpf_prog_get_type(prog); @@ -1091,6 +1106,16 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) } EXPORT_SYMBOL_GPL(bpf_prog_get_type); +struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, + struct net_device *netdev) +{ + struct bpf_prog *prog = __bpf_prog_get(ufd, &type, netdev); + + if (!IS_ERR(prog)) + trace_bpf_prog_get_type(prog); + return prog; +} + /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD prog_target_ifindex diff --git a/net/core/dev.c b/net/core/dev.c index 10cde58d3275..30b5fe32c525 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7157,7 +7157,11 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, __dev_xdp_attached(dev, bpf_op, NULL)) return -EBUSY; - prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); + if (bpf_op == ops->ndo_bpf) + prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, + dev); + else + prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); if (IS_ERR(prog)) return PTR_ERR(prog); } -- cgit v1.3-8-gc7d7 From ee21b18b6bdbb17a6e0b26255d2f662baf0d8409 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Sun, 12 Nov 2017 22:28:46 +0300 Subject: netdev: exit_net cleanup check added Be sure that dev_base_head list initialized in net_init hook was return to initial state Signed-off-by: Vasily Averin Signed-off-by: David S. Miller --- net/core/dev.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 30b5fe32c525..658337bf33e4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8667,6 +8667,8 @@ static void __net_exit netdev_exit(struct net *net) { kfree(net->dev_name_head); kfree(net->dev_index_head); + if (net != &init_net) + WARN_ON_ONCE(!list_empty(&net->dev_base_head)); } static struct pernet_operations __net_initdata netdev_net_ops = { -- cgit v1.3-8-gc7d7 From 51f299dd94bb1e28d03eefbc4fe0b9282f9ee2fa Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 13 Nov 2017 00:15:04 +0100 Subject: net: core: improve sanity checking in __dev_alloc_name __dev_alloc_name is called from the public (and exported) dev_alloc_name(), so we don't have a guarantee that strlen(name) is at most IFNAMSIZ. If somebody manages to get __dev_alloc_name called with a % char beyond the 31st character, we'd be making a snprintf() call that will very easily crash the kernel (using an appropriate %p extension, we'll likely dereference some completely bogus pointer). In the normal case where strlen() is sane, we don't even save anything by limiting to IFNAMSIZ, so just use strchr(). Signed-off-by: Rasmus Villemoes Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 658337bf33e4..1a5d31fdea27 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1064,7 +1064,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) unsigned long *inuse; struct net_device *d; - p = strnchr(name, IFNAMSIZ-1, '%'); + p = strchr(name, '%'); if (p) { /* * Verify the string as this thing may have come from -- cgit v1.3-8-gc7d7 From 2c88b855981481970b731bf3f4508400aac429fb Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 13 Nov 2017 00:15:05 +0100 Subject: net: core: move dev_alloc_name_ns a little higher No functional change. Signed-off-by: Rasmus Villemoes Signed-off-by: David S. Miller --- net/core/dev.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 1a5d31fdea27..4545685d2fa7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1107,6 +1107,19 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) return -ENFILE; } +static int dev_alloc_name_ns(struct net *net, + struct net_device *dev, + const char *name) +{ + char buf[IFNAMSIZ]; + int ret; + + ret = __dev_alloc_name(net, name, buf); + if (ret >= 0) + strlcpy(dev->name, buf, IFNAMSIZ); + return ret; +} + /** * dev_alloc_name - allocate a name for a device * @dev: device @@ -1136,19 +1149,6 @@ int dev_alloc_name(struct net_device *dev, const char *name) } EXPORT_SYMBOL(dev_alloc_name); -static int dev_alloc_name_ns(struct net *net, - struct net_device *dev, - const char *name) -{ - char buf[IFNAMSIZ]; - int ret; - - ret = __dev_alloc_name(net, name, buf); - if (ret >= 0) - strlcpy(dev->name, buf, IFNAMSIZ); - return ret; -} - int dev_get_valid_name(struct net *net, struct net_device *dev, const char *name) { -- cgit v1.3-8-gc7d7 From c46d7642e915106b0301bc4d53a79e8e806c2eb9 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 13 Nov 2017 00:15:06 +0100 Subject: net: core: eliminate dev_alloc_name{,_ns} code duplication dev_alloc_name contained a BUG_ON(), which I moved to dev_alloc_name_ns; the only other caller of that already has the same BUG_ON. Signed-off-by: Rasmus Villemoes Signed-off-by: David S. Miller --- net/core/dev.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 4545685d2fa7..7580c2046c95 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1114,6 +1114,7 @@ static int dev_alloc_name_ns(struct net *net, char buf[IFNAMSIZ]; int ret; + BUG_ON(!net); ret = __dev_alloc_name(net, name, buf); if (ret >= 0) strlcpy(dev->name, buf, IFNAMSIZ); @@ -1136,16 +1137,7 @@ static int dev_alloc_name_ns(struct net *net, int dev_alloc_name(struct net_device *dev, const char *name) { - char buf[IFNAMSIZ]; - struct net *net; - int ret; - - BUG_ON(!dev_net(dev)); - net = dev_net(dev); - ret = __dev_alloc_name(net, name, buf); - if (ret >= 0) - strlcpy(dev->name, buf, IFNAMSIZ); - return ret; + return dev_alloc_name_ns(dev_net(dev), dev, name); } EXPORT_SYMBOL(dev_alloc_name); -- cgit v1.3-8-gc7d7 From 6224abda0db8845756571833744d4414f144ecb5 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 13 Nov 2017 00:15:07 +0100 Subject: net: core: drop pointless check in __dev_alloc_name The only caller passes a stack buffer as buf, so it won't equal the passed-in name. Moreover, we're already using buf as a scratch buffer inside the if (p) {} block, so if buf and name were the same, that snprintf() call would be overwriting its own format string. Signed-off-by: Rasmus Villemoes Signed-off-by: David S. Miller --- net/core/dev.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 7580c2046c95..4cedc7595f1f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1095,8 +1095,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) free_page((unsigned long) inuse); } - if (buf != name) - snprintf(buf, IFNAMSIZ, name, i); + snprintf(buf, IFNAMSIZ, name, i); if (!__dev_get_by_name(net, buf)) return i; -- cgit v1.3-8-gc7d7 From 93809105cf9d43790839d8b8e29a8a505290ec68 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 13 Nov 2017 00:15:08 +0100 Subject: net: core: check dev_valid_name in __dev_alloc_name We currently only exclude non-sysfs-friendly names via dev_get_valid_name; there doesn't seem to be a reason to allow such names when we're called via dev_alloc_name. This does duplicate the dev_valid_name check in the dev_get_valid_name() case; we'll fix that shortly. Signed-off-by: Rasmus Villemoes Signed-off-by: David S. Miller --- net/core/dev.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 4cedc7595f1f..cb3d95edf58d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1064,6 +1064,9 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) unsigned long *inuse; struct net_device *d; + if (!dev_valid_name(name)) + return -EINVAL; + p = strchr(name, '%'); if (p) { /* -- cgit v1.3-8-gc7d7 From d6f295e9def0bee85b37bdffb95153721935c342 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 13 Nov 2017 00:15:09 +0100 Subject: net: core: maybe return -EEXIST in __dev_alloc_name If we're given format string with no %d, -EEXIST is a saner error code. Signed-off-by: Rasmus Villemoes Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index cb3d95edf58d..1bb856eaed1c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1106,7 +1106,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) * when the name is long and there isn't enough space left * for the digits, or if all bits are used. */ - return -ENFILE; + return p ? -ENFILE : -EEXIST; } static int dev_alloc_name_ns(struct net *net, -- cgit v1.3-8-gc7d7 From 87c320e51519a83c496ab7bfb4e96c8f9c001e89 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 13 Nov 2017 00:15:10 +0100 Subject: net: core: dev_get_valid_name is now the same as dev_alloc_name_ns If name contains a %, it's easy to see that this patch doesn't change anything (other than eliminate the duplicate dev_valid_name call). Otherwise, we'll now just spend a little time in snprintf() copying name to the stack buffer allocated in dev_alloc_name_ns, and do the __dev_get_by_name using that buffer rather than name. Signed-off-by: Rasmus Villemoes Signed-off-by: David S. Miller --- net/core/dev.c | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 1bb856eaed1c..ad5f90dacd92 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1146,19 +1146,7 @@ EXPORT_SYMBOL(dev_alloc_name); int dev_get_valid_name(struct net *net, struct net_device *dev, const char *name) { - BUG_ON(!net); - - if (!dev_valid_name(name)) - return -EINVAL; - - if (strchr(name, '%')) - return dev_alloc_name_ns(net, dev, name); - else if (__dev_get_by_name(net, name)) - return -EEXIST; - else if (dev->name != name) - strlcpy(dev->name, name, IFNAMSIZ); - - return 0; + return dev_alloc_name_ns(net, dev, name); } EXPORT_SYMBOL(dev_get_valid_name); -- cgit v1.3-8-gc7d7 From 288b3de55aace830f13280985ec9e6bcbff33b1b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 20 Nov 2017 15:21:54 -0800 Subject: bpf: offload: move offload device validation out to the drivers With TC shared block changes we can't depend on correct netdev pointer being available in cls_bpf. Move the device validation to the driver. Core will only make sure that offloaded programs are always attached in the driver (or in HW by the driver). We trust that drivers which implement offload callbacks will perform necessary checks. Moving the checks to the driver is generally a useful thing, in practice the check should be against a switchdev instance, not a netdev, given that most ASICs will probably allow using the same program on many ports. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: Jiri Pirko Signed-off-by: Daniel Borkmann --- drivers/net/ethernet/netronome/nfp/bpf/offload.c | 10 ++++++++-- include/linux/bpf.h | 4 ++-- kernel/bpf/syscall.c | 23 ++++++++++++----------- net/core/dev.c | 7 ++----- net/sched/cls_bpf.c | 8 +++----- 5 files changed, 27 insertions(+), 25 deletions(-) (limited to 'net/core/dev.c') diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index b6cee71f49d3..bc879aeb62d4 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -214,8 +214,14 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog, { int err; - if (prog && !prog->aux->offload) - return -EINVAL; + if (prog) { + struct bpf_dev_offload *offload = prog->aux->offload; + + if (!offload) + return -EINVAL; + if (offload->netdev != nn->dp.netdev) + return -EINVAL; + } if (prog && old_prog) { u8 cap; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c397934f91dd..f82be640731e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -336,7 +336,7 @@ extern const struct bpf_verifier_ops xdp_analyzer_ops; struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, - struct net_device *netdev); + bool attach_drv); struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog); @@ -433,7 +433,7 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, - struct net_device *netdev) + bool attach_drv) { return ERR_PTR(-EOPNOTSUPP); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8e9d065bb7cd..38da55905ab0 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1057,22 +1057,23 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) } EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); -static bool bpf_prog_can_attach(struct bpf_prog *prog, - enum bpf_prog_type *attach_type, - struct net_device *netdev) +static bool bpf_prog_get_ok(struct bpf_prog *prog, + enum bpf_prog_type *attach_type, bool attach_drv) { - struct bpf_dev_offload *offload = prog->aux->offload; + /* not an attachment, just a refcount inc, always allow */ + if (!attach_type) + return true; if (prog->type != *attach_type) return false; - if (offload && offload->netdev != netdev) + if (bpf_prog_is_dev_bound(prog->aux) && !attach_drv) return false; return true; } static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, - struct net_device *netdev) + bool attach_drv) { struct fd f = fdget(ufd); struct bpf_prog *prog; @@ -1080,7 +1081,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, prog = ____bpf_prog_get(f); if (IS_ERR(prog)) return prog; - if (attach_type && !bpf_prog_can_attach(prog, attach_type, netdev)) { + if (!bpf_prog_get_ok(prog, attach_type, attach_drv)) { prog = ERR_PTR(-EINVAL); goto out; } @@ -1093,12 +1094,12 @@ out: struct bpf_prog *bpf_prog_get(u32 ufd) { - return __bpf_prog_get(ufd, NULL, NULL); + return __bpf_prog_get(ufd, NULL, false); } struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) { - struct bpf_prog *prog = __bpf_prog_get(ufd, &type, NULL); + struct bpf_prog *prog = __bpf_prog_get(ufd, &type, false); if (!IS_ERR(prog)) trace_bpf_prog_get_type(prog); @@ -1107,9 +1108,9 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) EXPORT_SYMBOL_GPL(bpf_prog_get_type); struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, - struct net_device *netdev) + bool attach_drv) { - struct bpf_prog *prog = __bpf_prog_get(ufd, &type, netdev); + struct bpf_prog *prog = __bpf_prog_get(ufd, &type, attach_drv); if (!IS_ERR(prog)) trace_bpf_prog_get_type(prog); diff --git a/net/core/dev.c b/net/core/dev.c index 8ee29f4f5fa9..09525a27319c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7139,11 +7139,8 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, __dev_xdp_attached(dev, bpf_op, NULL)) return -EBUSY; - if (bpf_op == ops->ndo_bpf) - prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, - dev); - else - prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); + prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, + bpf_op == ops->ndo_bpf); if (IS_ERR(prog)) return PTR_ERR(prog); } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index fb680dafac5a..a9f3e317055c 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -382,15 +382,13 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, { struct bpf_prog *fp; char *name = NULL; + bool skip_sw; u32 bpf_fd; bpf_fd = nla_get_u32(tb[TCA_BPF_FD]); + skip_sw = gen_flags & TCA_CLS_FLAGS_SKIP_SW; - if (gen_flags & TCA_CLS_FLAGS_SKIP_SW) - fp = bpf_prog_get_type_dev(bpf_fd, BPF_PROG_TYPE_SCHED_CLS, - qdisc_dev(tp->q)); - else - fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_CLS); + fp = bpf_prog_get_type_dev(bpf_fd, BPF_PROG_TYPE_SCHED_CLS, skip_sw); if (IS_ERR(fp)) return PTR_ERR(fp); -- cgit v1.3-8-gc7d7 From 441a33031fe5a3e828fbc17a4f9a5bab9143243c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 20 Nov 2017 15:21:55 -0800 Subject: net: xdp: don't allow device-bound programs in driver mode Currently device-bound programs are not able to run on the host to save resources (host JIT is not invoked). Don't allow XDP programs to be attached without the HW_MODE flag. In theory if program is already translated for device offload the driver should choose to offload it instead of loading it in the driver. However, offloading translated program may still fail resulting in device-bound program being run on the host. Prevent this by refusing to attach device bound programs if XDP_FLAGS_HW_MODE is not set. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- net/core/dev.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 09525a27319c..5e2ba133fba7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7143,6 +7143,13 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, bpf_op == ops->ndo_bpf); if (IS_ERR(prog)) return PTR_ERR(prog); + + if (!(flags & XDP_FLAGS_HW_MODE) && + bpf_prog_is_dev_bound(prog->aux)) { + NL_SET_ERR_MSG(extack, "using device-bound program without HW_MODE flag is not supported"); + bpf_prog_put(prog); + return -EINVAL; + } } err = dev_xdp_install(dev, bpf_op, extack, flags, prog); -- cgit v1.3-8-gc7d7 From 0c19f846d582af919db66a5914a0189f9f92c936 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 21 Nov 2017 10:22:25 -0500 Subject: net: accept UFO datagrams from tuntap and packet Tuntap and similar devices can inject GSO packets. Accept type VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively. Processes are expected to use feature negotiation such as TUNSETOFFLOAD to detect supported offload types and refrain from injecting other packets. This process breaks down with live migration: guest kernels do not renegotiate flags, so destination hosts need to expose all features that the source host does. Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677. This patch introduces nearly(*) no new code to simplify verification. It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP insertion and software UFO segmentation. It does not reinstate protocol stack support, hardware offload (NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception of VIRTIO_NET_HDR_GSO_UDP packets in tuntap. To support SKB_GSO_UDP reappearing in the stack, also reinstate logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD by squashing in commit 939912216fa8 ("net: skb_needs_check() removes CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1 ("net: avoid skb_warn_bad_offload false positives on UFO"). (*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id, ipv6_proxy_select_ident is changed to return a __be32 and this is assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted at the end of the enum to minimize code churn. Tested Booted a v4.13 guest kernel with QEMU. On a host kernel before this patch `ethtool -k eth0` shows UFO disabled. After the patch, it is enabled, same as on a v4.13 host kernel. A UFO packet sent from the guest appears on the tap device: host: nc -l -p -u 8000 & tcpdump -n -i tap0 guest: dd if=/dev/zero of=payload.txt bs=1 count=2000 nc -u 192.16.1.1 8000 < payload.txt Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds, packets arriving fragmented: ./with_tap_pair.sh ./tap_send_ufo tap0 tap1 (from https://github.com/wdebruij/kerneltools/tree/master/tests) Changes v1 -> v2 - simplified set_offload change (review comment) - documented test procedure Link: http://lkml.kernel.org/r/ Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.") Reported-by: Michal Kubecek Signed-off-by: Willem de Bruijn Acked-by: Jason Wang Signed-off-by: David S. Miller --- drivers/net/tap.c | 2 +- drivers/net/tun.c | 2 + include/linux/netdev_features.h | 4 +- include/linux/netdevice.h | 1 + include/linux/skbuff.h | 2 + include/linux/virtio_net.h | 5 ++- include/net/ipv6.h | 1 + net/core/dev.c | 3 +- net/ipv4/af_inet.c | 12 +++++- net/ipv4/udp_offload.c | 49 ++++++++++++++++++++++-- net/ipv6/output_core.c | 31 +++++++++++++++ net/ipv6/udp_offload.c | 85 +++++++++++++++++++++++++++++++++++++++-- net/openvswitch/datapath.c | 14 +++++++ net/openvswitch/flow.c | 6 ++- net/sched/act_csum.c | 6 +++ 15 files changed, 209 insertions(+), 14 deletions(-) (limited to 'net/core/dev.c') diff --git a/drivers/net/tap.c b/drivers/net/tap.c index b13890953ebb..e9489b88407c 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -1077,7 +1077,7 @@ static long tap_ioctl(struct file *file, unsigned int cmd, case TUNSETOFFLOAD: /* let the user check for future flags */ if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | - TUN_F_TSO_ECN)) + TUN_F_TSO_ECN | TUN_F_UFO)) return -EINVAL; rtnl_lock(); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 5a2ea78a008f..6a7bde9bc4b2 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2370,6 +2370,8 @@ static int set_offload(struct tun_struct *tun, unsigned long arg) features |= NETIF_F_TSO6; arg &= ~(TUN_F_TSO4|TUN_F_TSO6); } + + arg &= ~TUN_F_UFO; } /* This gives the user a way to test for new features in future by diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index dc8b4896b77b..b1b0ca7ccb2b 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -54,8 +54,9 @@ enum { NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */ NETIF_F_GSO_SCTP_BIT, /* ... SCTP fragmentation */ NETIF_F_GSO_ESP_BIT, /* ... ESP with TSO */ + NETIF_F_GSO_UDP_BIT, /* ... UFO, deprecated except tuntap */ /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ - NETIF_F_GSO_ESP_BIT, + NETIF_F_GSO_UDP_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ @@ -132,6 +133,7 @@ enum { #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM) #define NETIF_F_GSO_SCTP __NETIF_F(GSO_SCTP) #define NETIF_F_GSO_ESP __NETIF_F(GSO_ESP) +#define NETIF_F_GSO_UDP __NETIF_F(GSO_UDP) #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER) #define NETIF_F_HW_VLAN_STAG_RX __NETIF_F(HW_VLAN_STAG_RX) #define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6b274bfe489f..ef789e1d679e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4140,6 +4140,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ed06e1c28fc7..bc486ef23f20 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -568,6 +568,8 @@ enum { SKB_GSO_SCTP = 1 << 14, SKB_GSO_ESP = 1 << 15, + + SKB_GSO_UDP = 1 << 16, }; #if BITS_PER_LONG > 32 diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 210034c896e3..f144216febc6 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -9,7 +9,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, const struct virtio_net_hdr *hdr, bool little_endian) { - unsigned short gso_type = 0; + unsigned int gso_type = 0; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { @@ -19,6 +19,9 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; break; + case VIRTIO_NET_HDR_GSO_UDP: + gso_type = SKB_GSO_UDP; + break; default: return -EINVAL; } diff --git a/include/net/ipv6.h b/include/net/ipv6.h index ec14f0d5a3a1..f73797e2fa60 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -767,6 +767,7 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr); +__be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); diff --git a/net/core/dev.c b/net/core/dev.c index 8ee29f4f5fa9..bbba19112f02 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2746,7 +2746,8 @@ EXPORT_SYMBOL(skb_mac_gso_segment); static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) { if (tx_path) - return skb->ip_summed != CHECKSUM_PARTIAL; + return skb->ip_summed != CHECKSUM_PARTIAL && + skb->ip_summed != CHECKSUM_UNNECESSARY; return skb->ip_summed == CHECKSUM_NONE; } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ce4aa827be05..f00499a46927 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1223,9 +1223,10 @@ EXPORT_SYMBOL(inet_sk_rebuild_header); struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features) { - bool fixedid = false, gso_partial, encap; + bool udpfrag = false, fixedid = false, gso_partial, encap; struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; + unsigned int offset = 0; struct iphdr *iph; int proto, tot_len; int nhoff; @@ -1260,6 +1261,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ERR_PTR(-EPROTONOSUPPORT); if (!skb->encapsulation || encap) { + udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP); fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID); /* fixed ID is invalid if DF bit is not set */ @@ -1279,7 +1281,13 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, skb = segs; do { iph = (struct iphdr *)(skb_mac_header(skb) + nhoff); - if (skb_is_gso(skb)) { + if (udpfrag) { + iph->frag_off = htons(offset >> 3); + if (skb->next) + iph->frag_off |= htons(IP_MF); + offset += skb->len - nhoff - ihl; + tot_len = skb->len - nhoff; + } else if (skb_is_gso(skb)) { if (!fixedid) { iph->id = htons(id); id += skb_shinfo(skb)->gso_segs; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index e360d55be555..01801b77bd0d 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -187,16 +187,57 @@ out_unlock: } EXPORT_SYMBOL(skb_udp_tunnel_segment); -static struct sk_buff *udp4_tunnel_segment(struct sk_buff *skb, - netdev_features_t features) +static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); + unsigned int mss; + __wsum csum; + struct udphdr *uh; + struct iphdr *iph; if (skb->encapsulation && (skb_shinfo(skb)->gso_type & - (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) + (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) { segs = skb_udp_tunnel_segment(skb, features, false); + goto out; + } + + if (!pskb_may_pull(skb, sizeof(struct udphdr))) + goto out; + + mss = skb_shinfo(skb)->gso_size; + if (unlikely(skb->len <= mss)) + goto out; + + /* Do software UFO. Complete and fill in the UDP checksum as + * HW cannot do checksum of UDP packets sent as multiple + * IP fragments. + */ + uh = udp_hdr(skb); + iph = ip_hdr(skb); + + uh->check = 0; + csum = skb_checksum(skb, 0, skb->len, 0); + uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + + /* If there is no outer header we can fake a checksum offload + * due to the fact that we have already done the checksum in + * software prior to segmenting the frame. + */ + if (!skb->encap_hdr_csum) + features |= NETIF_F_HW_CSUM; + + /* Fragment the skb. IP headers of the fragments are updated in + * inet_gso_segment() + */ + segs = skb_segment(skb, features); +out: return segs; } @@ -330,7 +371,7 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff) static const struct net_offload udpv4_offload = { .callbacks = { - .gso_segment = udp4_tunnel_segment, + .gso_segment = udp4_ufo_fragment, .gro_receive = udp4_gro_receive, .gro_complete = udp4_gro_complete, }, diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 4a7e5ffa5108..4fe7c90962dd 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -31,6 +31,37 @@ static u32 __ipv6_select_ident(struct net *net, u32 hashrnd, return id; } +/* This function exists only for tap drivers that must support broken + * clients requesting UFO without specifying an IPv6 fragment ID. + * + * This is similar to ipv6_select_ident() but we use an independent hash + * seed to limit information leakage. + * + * The network header must be set before calling this. + */ +__be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) +{ + static u32 ip6_proxy_idents_hashrnd __read_mostly; + struct in6_addr buf[2]; + struct in6_addr *addrs; + u32 id; + + addrs = skb_header_pointer(skb, + skb_network_offset(skb) + + offsetof(struct ipv6hdr, saddr), + sizeof(buf), buf); + if (!addrs) + return 0; + + net_get_random_once(&ip6_proxy_idents_hashrnd, + sizeof(ip6_proxy_idents_hashrnd)); + + id = __ipv6_select_ident(net, ip6_proxy_idents_hashrnd, + &addrs[1], &addrs[0]); + return htonl(id); +} +EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); + __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr) diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 455fd4e39333..a0f89ad76f9d 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -17,15 +17,94 @@ #include #include "ip6_offload.h" -static struct sk_buff *udp6_tunnel_segment(struct sk_buff *skb, - netdev_features_t features) +static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); + unsigned int mss; + unsigned int unfrag_ip6hlen, unfrag_len; + struct frag_hdr *fptr; + u8 *packet_start, *prevhdr; + u8 nexthdr; + u8 frag_hdr_sz = sizeof(struct frag_hdr); + __wsum csum; + int tnl_hlen; + int err; + + mss = skb_shinfo(skb)->gso_size; + if (unlikely(skb->len <= mss)) + goto out; if (skb->encapsulation && skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)) segs = skb_udp_tunnel_segment(skb, features, true); + else { + const struct ipv6hdr *ipv6h; + struct udphdr *uh; + + if (!pskb_may_pull(skb, sizeof(struct udphdr))) + goto out; + + /* Do software UFO. Complete and fill in the UDP checksum as HW cannot + * do checksum of UDP packets sent as multiple IP fragments. + */ + + uh = udp_hdr(skb); + ipv6h = ipv6_hdr(skb); + + uh->check = 0; + csum = skb_checksum(skb, 0, skb->len, 0); + uh->check = udp_v6_check(skb->len, &ipv6h->saddr, + &ipv6h->daddr, csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + + /* If there is no outer header we can fake a checksum offload + * due to the fact that we have already done the checksum in + * software prior to segmenting the frame. + */ + if (!skb->encap_hdr_csum) + features |= NETIF_F_HW_CSUM; + + /* Check if there is enough headroom to insert fragment header. */ + tnl_hlen = skb_tnl_header_len(skb); + if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) { + if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz)) + goto out; + } + + /* Find the unfragmentable header and shift it left by frag_hdr_sz + * bytes to insert fragment header. + */ + err = ip6_find_1stfragopt(skb, &prevhdr); + if (err < 0) + return ERR_PTR(err); + unfrag_ip6hlen = err; + nexthdr = *prevhdr; + *prevhdr = NEXTHDR_FRAGMENT; + unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + + unfrag_ip6hlen + tnl_hlen; + packet_start = (u8 *) skb->head + SKB_GSO_CB(skb)->mac_offset; + memmove(packet_start-frag_hdr_sz, packet_start, unfrag_len); + + SKB_GSO_CB(skb)->mac_offset -= frag_hdr_sz; + skb->mac_header -= frag_hdr_sz; + skb->network_header -= frag_hdr_sz; + + fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); + fptr->nexthdr = nexthdr; + fptr->reserved = 0; + fptr->identification = ipv6_proxy_select_ident(dev_net(skb->dev), skb); + + /* Fragment the skb. ipv6 header and the remaining fields of the + * fragment header are updated in ipv6_gso_segment() + */ + segs = skb_segment(skb, features); + } +out: return segs; } @@ -75,7 +154,7 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff) static const struct net_offload udpv6_offload = { .callbacks = { - .gso_segment = udp6_tunnel_segment, + .gso_segment = udp6_ufo_fragment, .gro_receive = udp6_gro_receive, .gro_complete = udp6_gro_complete, }, diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 0dab33fb9844..99cfafc2a139 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -308,6 +308,8 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, const struct dp_upcall_info *upcall_info, uint32_t cutlen) { + unsigned short gso_type = skb_shinfo(skb)->gso_type; + struct sw_flow_key later_key; struct sk_buff *segs, *nskb; int err; @@ -318,9 +320,21 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, if (segs == NULL) return -EINVAL; + if (gso_type & SKB_GSO_UDP) { + /* The initial flow key extracted by ovs_flow_key_extract() + * in this case is for a first fragment, so we need to + * properly mark later fragments. + */ + later_key = *key; + later_key.ip.frag = OVS_FRAG_TYPE_LATER; + } + /* Queue all of the segments. */ skb = segs; do { + if (gso_type & SKB_GSO_UDP && skb != segs) + key = &later_key; + err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen); if (err) break; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 864ddb1e3642..dbe2379329c5 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -631,7 +631,8 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) key->ip.frag = OVS_FRAG_TYPE_LATER; return 0; } - if (nh->frag_off & htons(IP_MF)) + if (nh->frag_off & htons(IP_MF) || + skb_shinfo(skb)->gso_type & SKB_GSO_UDP) key->ip.frag = OVS_FRAG_TYPE_FIRST; else key->ip.frag = OVS_FRAG_TYPE_NONE; @@ -747,6 +748,9 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) if (key->ip.frag == OVS_FRAG_TYPE_LATER) return 0; + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP) + key->ip.frag = OVS_FRAG_TYPE_FIRST; + /* Transport layer. */ if (key->ip.proto == NEXTHDR_TCP) { if (tcphdr_ok(skb)) { diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 1c40caadcff9..d836f998117b 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -229,6 +229,9 @@ static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl, const struct iphdr *iph; u16 ul; + if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP) + return 1; + /* * Support both UDP and UDPLITE checksum algorithms, Don't use * udph->len to get the real length without any protocol check, @@ -282,6 +285,9 @@ static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl, const struct ipv6hdr *ip6h; u16 ul; + if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP) + return 1; + /* * Support both UDP and UDPLITE checksum algorithms, Don't use * udph->len to get the real length without any protocol check, -- cgit v1.3-8-gc7d7