From 18d82cde743237def9f80171e32be1153f5cadac Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Wed, 10 Apr 2024 11:48:24 +0200 Subject: [PATCH 01/21] mptcp: add last time fields in mptcp_info This patch adds "last time" fields last_data_sent, last_data_recv and last_ack_recv in struct mptcp_sock to record the last time data_sent, data_recv and ack_recv happened. They all are initialized as tcp_jiffies32 in __mptcp_init_sock(), and updated as tcp_jiffies32 too when data is sent in __subflow_push_pending(), data is received in __mptcp_move_skbs_from_subflow(), and ack is received in ack_update_msk(). Similar to tcpi_last_data_sent, tcpi_last_data_recv and tcpi_last_ack_recv exposed with TCP, this patch exposes the last time "an action happened" for MPTCP in mptcp_info, named mptcpi_last_data_sent, mptcpi_last_data_recv and mptcpi_last_ack_recv, calculated in mptcp_diag_fill_info() as the time deltas between now and the newly added last time fields in mptcp_sock. Since msk->last_ack_recv needs to be protected by mptcp_data_lock/unlock, and lock_sock_fast can sleep and be quite slow, move the entire mptcp_data_lock/unlock block after the lock/unlock_sock_fast block. Then mptcpi_last_data_sent and mptcpi_last_data_recv are set in lock/unlock_sock_fast block, while mptcpi_last_ack_recv is set in mptcp_data_lock/unlock block, which is protected by a spinlock and should not block for too long. Also add three reserved bytes in struct mptcp_info not to have holes in this structure exposed to userspace. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/446 Signed-off-by: Geliang Tang Reviewed-by: Mat Martineau Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://lore.kernel.org/r/20240410-upstream-net-next-20240405-mptcp-last-time-info-v2-1-f95bd6b33e51@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 4 ++++ net/mptcp/options.c | 1 + net/mptcp/protocol.c | 7 +++++++ net/mptcp/protocol.h | 3 +++ net/mptcp/sockopt.c | 16 +++++++++++----- 5 files changed, 26 insertions(+), 5 deletions(-) diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 74cfe496891e..67d015df8893 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -58,6 +58,10 @@ struct mptcp_info { __u64 mptcpi_bytes_received; __u64 mptcpi_bytes_acked; __u8 mptcpi_subflows_total; + __u8 reserved[3]; + __u32 mptcpi_last_data_sent; + __u32 mptcpi_last_data_recv; + __u32 mptcpi_last_ack_recv; }; /* MPTCP Reset reason codes, rfc8684 */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 27ca42c77b02..8e8dcfbc2993 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1068,6 +1068,7 @@ static void ack_update_msk(struct mptcp_sock *msk, __mptcp_snd_una_update(msk, new_snd_una); __mptcp_data_acked(sk); } + msk->last_ack_recv = tcp_jiffies32; mptcp_data_unlock(sk); trace_ack_update_msk(mp_opt->data_ack, diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 995b53cd021c..f8bc34f0d973 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -706,6 +706,8 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, } } while (more_data_avail); + if (moved > 0) + msk->last_data_recv = tcp_jiffies32; *bytes += moved; return done; } @@ -1556,6 +1558,8 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk, err = copied; out: + if (err > 0) + msk->last_data_sent = tcp_jiffies32; return err; } @@ -2793,6 +2797,9 @@ static void __mptcp_init_sock(struct sock *sk) WRITE_ONCE(msk->allow_infinite_fallback, true); msk->recovery = false; msk->subflow_id = 1; + msk->last_data_sent = tcp_jiffies32; + msk->last_data_recv = tcp_jiffies32; + msk->last_ack_recv = tcp_jiffies32; mptcp_pm_data_init(msk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 46f4655b7123..fdfa843e2d88 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -282,6 +282,9 @@ struct mptcp_sock { u64 bytes_acked; u64 snd_una; u64 wnd_end; + u32 last_data_sent; + u32 last_data_recv; + u32 last_ack_recv; unsigned long timer_ival; u32 token; int rmem_released; diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 9d5d42a77bcc..1fea43f5b6f3 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -898,6 +898,7 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) struct sock *sk = (struct sock *)msk; u32 flags = 0; bool slow; + u32 now; memset(info, 0, sizeof(*info)); @@ -926,11 +927,6 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) if (READ_ONCE(msk->can_ack)) flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED; info->mptcpi_flags = flags; - mptcp_data_lock(sk); - info->mptcpi_snd_una = msk->snd_una; - info->mptcpi_rcv_nxt = msk->ack_seq; - info->mptcpi_bytes_acked = msk->bytes_acked; - mptcp_data_unlock(sk); slow = lock_sock_fast(sk); info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled); @@ -942,7 +938,17 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) info->mptcpi_bytes_retrans = msk->bytes_retrans; info->mptcpi_subflows_total = info->mptcpi_subflows + __mptcp_has_initial_subflow(msk); + now = tcp_jiffies32; + info->mptcpi_last_data_sent = jiffies_to_msecs(now - msk->last_data_sent); + info->mptcpi_last_data_recv = jiffies_to_msecs(now - msk->last_data_recv); unlock_sock_fast(sk, slow); + + mptcp_data_lock(sk); + info->mptcpi_last_ack_recv = jiffies_to_msecs(now - msk->last_ack_recv); + info->mptcpi_snd_una = msk->snd_una; + info->mptcpi_rcv_nxt = msk->ack_seq; + info->mptcpi_bytes_acked = msk->bytes_acked; + mptcp_data_unlock(sk); } EXPORT_SYMBOL_GPL(mptcp_diag_fill_info); From 22724c89892f5d08a350941734125194b8f97c21 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Wed, 10 Apr 2024 11:48:25 +0200 Subject: [PATCH 02/21] selftests: mptcp: test last time mptcp_info This patch adds a new helper chk_msk_info() to show the counters in mptcp_info of the given info, and check that the timestamps move forward. Use it to show newly added last_data_sent, last_data_recv and last_ack_recv in mptcp_info in chk_last_time_info(). Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://lore.kernel.org/r/20240410-upstream-net-next-20240405-mptcp-last-time-info-v2-2-f95bd6b33e51@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/diag.sh | 53 +++++++++++++++++++++++ 1 file changed, 53 insertions(+) diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index bc97ab33a00e..776d43a6922d 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -200,6 +200,58 @@ chk_msk_cestab() "${expected}" "${msg}" "" } +msk_info_get_value() +{ + local port="${1}" + local info="${2}" + + ss -N "${ns}" -inHM dport "${port}" | \ + mptcp_lib_get_info_value "${info}" "${info}" +} + +chk_msk_info() +{ + local port="${1}" + local info="${2}" + local cnt="${3}" + local msg="....chk ${info}" + local delta_ms=250 # half what we waited before, just to be sure + local now + + now=$(msk_info_get_value "${port}" "${info}") + + mptcp_lib_print_title "${msg}" + if { [ -z "${cnt}" ] || [ -z "${now}" ]; } && + ! mptcp_lib_expect_all_features; then + mptcp_lib_pr_skip "Feature probably not supported" + mptcp_lib_result_skip "${msg}" + elif [ "$((cnt + delta_ms))" -lt "${now}" ]; then + mptcp_lib_pr_ok + mptcp_lib_result_pass "${msg}" + else + mptcp_lib_pr_fail "value of ${info} changed by $((now - cnt))ms," \ + "expected at least ${delta_ms}ms" + mptcp_lib_result_fail "${msg}" + ret=${KSFT_FAIL} + fi +} + +chk_last_time_info() +{ + local port="${1}" + local data_sent data_recv ack_recv + + data_sent=$(msk_info_get_value "${port}" "last_data_sent") + data_recv=$(msk_info_get_value "${port}" "last_data_recv") + ack_recv=$(msk_info_get_value "${port}" "last_ack_recv") + + sleep 0.5 # wait to check after if the timestamps difference + + chk_msk_info "${port}" "last_data_sent" "${data_sent}" + chk_msk_info "${port}" "last_data_recv" "${data_recv}" + chk_msk_info "${port}" "last_ack_recv" "${ack_recv}" +} + wait_connected() { local listener_ns="${1}" @@ -233,6 +285,7 @@ echo "b" | \ 127.0.0.1 >/dev/null & wait_connected $ns 10000 chk_msk_nr 2 "after MPC handshake " +chk_last_time_info 10000 chk_msk_remote_key_nr 2 "....chk remote_key" chk_msk_fallback_nr 0 "....chk no fallback" chk_msk_inuse 2 From f6d827b180bda01f8805bf5e85307419b0d6f890 Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Wed, 10 Apr 2024 12:05:01 -0700 Subject: [PATCH 03/21] net: move skb ref helpers to new header Add a new header, linux/skbuff_ref.h, which contains all the skb_*_ref() helpers. Many of the consumers of skbuff.h do not actually use any of the skb ref helpers, and we can speed up compilation a bit by minimizing this header file. Additionally in the later patch in the series we add page_pool support to skb_frag_ref(), which requires some page_pool dependencies. We can now add these dependencies to skbuff_ref.h instead of a very ubiquitous skbuff.h Signed-off-by: Mina Almasry Link: https://lore.kernel.org/r/20240410190505.1225848-2-almasrymina@google.com Signed-off-by: Jakub Kicinski --- .../chelsio/inline_crypto/ch_ktls/chcr_ktls.c | 1 + drivers/net/ethernet/marvell/sky2.c | 1 + drivers/net/ethernet/mellanox/mlx4/en_rx.c | 1 + drivers/net/ethernet/sun/cassini.c | 1 + drivers/net/veth.c | 1 + drivers/net/xen-netback/netback.c | 1 + include/linux/skbuff.h | 63 ---------------- include/linux/skbuff_ref.h | 75 +++++++++++++++++++ net/core/gro.c | 1 + net/core/skbuff.c | 1 + net/ipv4/esp4.c | 1 + net/ipv4/tcp_output.c | 1 + net/ipv6/esp6.c | 1 + net/tls/tls_device.c | 1 + net/tls/tls_device_fallback.c | 1 + net/tls/tls_strp.c | 1 + 16 files changed, 89 insertions(+), 63 deletions(-) create mode 100644 include/linux/skbuff_ref.h diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c index 6482728794dd..e8e460a92e0e 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "chcr_ktls.h" static LIST_HEAD(uld_ctx_list); diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 07720841a8d7..f3f7f4cc27b3 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -34,6 +34,7 @@ #include #include #include +#include #include diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index eac49657bd07..8328df8645d5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #if IS_ENABLED(CONFIG_IPV6) diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index bfb903506367..8f1f43dbb76d 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -73,6 +73,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/veth.c b/drivers/net/veth.c index bcdfbf61eb66..426e68a95067 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #define DRV_NAME "veth" diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index ef76850d9bcd..48254fc07d64 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -38,6 +38,7 @@ #include #include #include +#include #include diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7135a3e94afd..4072a7ee3859 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3492,73 +3492,10 @@ static inline struct page *skb_frag_page(const skb_frag_t *frag) return netmem_to_page(frag->netmem); } -/** - * __skb_frag_ref - take an addition reference on a paged fragment. - * @frag: the paged fragment - * - * Takes an additional reference on the paged fragment @frag. - */ -static inline void __skb_frag_ref(skb_frag_t *frag) -{ - get_page(skb_frag_page(frag)); -} - -/** - * skb_frag_ref - take an addition reference on a paged fragment of an skb. - * @skb: the buffer - * @f: the fragment offset. - * - * Takes an additional reference on the @f'th paged fragment of @skb. - */ -static inline void skb_frag_ref(struct sk_buff *skb, int f) -{ - __skb_frag_ref(&skb_shinfo(skb)->frags[f]); -} - int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog); -bool napi_pp_put_page(struct page *page); - -static inline void -skb_page_unref(struct page *page, bool recycle) -{ -#ifdef CONFIG_PAGE_POOL - if (recycle && napi_pp_put_page(page)) - return; -#endif - put_page(page); -} - -/** - * __skb_frag_unref - release a reference on a paged fragment. - * @frag: the paged fragment - * @recycle: recycle the page if allocated via page_pool - * - * Releases a reference on the paged fragment @frag - * or recycles the page via the page_pool API. - */ -static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) -{ - skb_page_unref(skb_frag_page(frag), recycle); -} - -/** - * skb_frag_unref - release a reference on a paged fragment of an skb. - * @skb: the buffer - * @f: the fragment offset - * - * Releases a reference on the @f'th paged fragment of @skb. - */ -static inline void skb_frag_unref(struct sk_buff *skb, int f) -{ - struct skb_shared_info *shinfo = skb_shinfo(skb); - - if (!skb_zcopy_managed(skb)) - __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); -} - /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h new file mode 100644 index 000000000000..11f0a4063403 --- /dev/null +++ b/include/linux/skbuff_ref.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Skb ref helpers. + * + */ + +#ifndef _LINUX_SKBUFF_REF_H +#define _LINUX_SKBUFF_REF_H + +#include + +/** + * __skb_frag_ref - take an addition reference on a paged fragment. + * @frag: the paged fragment + * + * Takes an additional reference on the paged fragment @frag. + */ +static inline void __skb_frag_ref(skb_frag_t *frag) +{ + get_page(skb_frag_page(frag)); +} + +/** + * skb_frag_ref - take an addition reference on a paged fragment of an skb. + * @skb: the buffer + * @f: the fragment offset. + * + * Takes an additional reference on the @f'th paged fragment of @skb. + */ +static inline void skb_frag_ref(struct sk_buff *skb, int f) +{ + __skb_frag_ref(&skb_shinfo(skb)->frags[f]); +} + +bool napi_pp_put_page(struct page *page); + +static inline void +skb_page_unref(struct page *page, bool recycle) +{ +#ifdef CONFIG_PAGE_POOL + if (recycle && napi_pp_put_page(page)) + return; +#endif + put_page(page); +} + +/** + * __skb_frag_unref - release a reference on a paged fragment. + * @frag: the paged fragment + * @recycle: recycle the page if allocated via page_pool + * + * Releases a reference on the paged fragment @frag + * or recycles the page via the page_pool API. + */ +static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) +{ + skb_page_unref(skb_frag_page(frag), recycle); +} + +/** + * skb_frag_unref - release a reference on a paged fragment of an skb. + * @skb: the buffer + * @f: the fragment offset + * + * Releases a reference on the @f'th paged fragment of @skb. + */ +static inline void skb_frag_unref(struct sk_buff *skb, int f) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (!skb_zcopy_managed(skb)) + __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); +} + +#endif /* _LINUX_SKBUFF_REF_H */ diff --git a/net/core/gro.c b/net/core/gro.c index 83f35d99a682..2459ab697f7f 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -3,6 +3,7 @@ #include #include #include +#include #define MAX_GRO_SKBS 8 diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ab970ded8a7b..2554a6f5f386 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -51,6 +51,7 @@ #endif #include #include +#include #include #include #include diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 40330253f076..dff04580318f 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -20,6 +20,7 @@ #include #include #include +#include #include diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9282fafc0e61..61119d42b0fd 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -44,6 +44,7 @@ #include #include #include +#include #include diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index fb431d0a3475..6bc0a84c8d05 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -36,6 +36,7 @@ #include #include #include +#include #include diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index bf8ed36b1ad6..ab6e694f7bc2 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -37,6 +37,7 @@ #include #include #include +#include #include "tls.h" #include "trace.h" diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 4e7228f275fa..f9e3d3d90dcf 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -33,6 +33,7 @@ #include #include #include +#include #include "tls.h" diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index ca1e0e198ceb..58c4b06f4f0c 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -2,6 +2,7 @@ /* Copyright (c) 2016 Tom Herbert */ #include +#include #include #include #include From a580ea994fd37f4105028f5a85c38ff6508a2b25 Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Wed, 10 Apr 2024 12:05:02 -0700 Subject: [PATCH 04/21] net: mirror skb frag ref/unref helpers Refactor some of the skb frag ref/unref helpers for improved clarity. Implement napi_pp_get_page() to be the mirror counterpart of napi_pp_put_page(). Implement skb_page_ref() to be the mirror of skb_page_unref(). Improve __skb_frag_ref() to become a mirror counterpart of __skb_frag_unref(). Previously unref could handle pp & non-pp pages, while the ref could only handle non-pp pages. Now both the ref & unref helpers can correctly handle both pp & non-pp pages. Now that __skb_frag_ref() can handle both pp & non-pp pages, remove skb_pp_frag_ref(), and use __skb_frag_ref() instead. This lets us remove pp specific handling from skb_try_coalesce. Additionally, since __skb_frag_ref() can now handle both pp & non-pp pages, a latent issue in skb_shift() should now be fixed. Previously this function would do a non-pp ref & pp unref on potential pp frags (fragfrom). After this patch, skb_shift() should correctly do a pp ref/unref on pp frags. Signed-off-by: Mina Almasry Reviewed-by: Dragos Tatulea Reviewed-by: Jacob Keller Link: https://lore.kernel.org/r/20240410190505.1225848-3-almasrymina@google.com Signed-off-by: Jakub Kicinski --- .../chelsio/inline_crypto/ch_ktls/chcr_ktls.c | 2 +- drivers/net/ethernet/sun/cassini.c | 4 +- drivers/net/veth.c | 2 +- include/linux/skbuff_ref.h | 39 ++++++++++++++-- net/core/skbuff.c | 46 ++----------------- net/tls/tls_device_fallback.c | 2 +- 6 files changed, 44 insertions(+), 51 deletions(-) diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c index e8e460a92e0e..3832c2e8ea5a 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c @@ -1659,7 +1659,7 @@ static void chcr_ktls_copy_record_in_skb(struct sk_buff *nskb, for (i = 0; i < record->num_frags; i++) { skb_shinfo(nskb)->frags[i] = record->frags[i]; /* increase the frag ref count */ - __skb_frag_ref(&skb_shinfo(nskb)->frags[i]); + __skb_frag_ref(&skb_shinfo(nskb)->frags[i], nskb->pp_recycle); } skb_shinfo(nskb)->nr_frags = record->num_frags; diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 8f1f43dbb76d..f058e154a3bc 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -2000,7 +2000,7 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, skb->len += hlen - swivel; skb_frag_fill_page_desc(frag, page->buffer, off, hlen - swivel); - __skb_frag_ref(frag); + __skb_frag_ref(frag, skb->pp_recycle); /* any more data? */ if ((words[0] & RX_COMP1_SPLIT_PKT) && ((dlen -= hlen) > 0)) { @@ -2024,7 +2024,7 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, frag++; skb_frag_fill_page_desc(frag, page->buffer, 0, hlen); - __skb_frag_ref(frag); + __skb_frag_ref(frag, skb->pp_recycle); RX_USED_ADD(page, hlen + cp->crc_size); } diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 426e68a95067..0b0293629329 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -717,7 +717,7 @@ static void veth_xdp_get(struct xdp_buff *xdp) return; for (i = 0; i < sinfo->nr_frags; i++) - __skb_frag_ref(&sinfo->frags[i]); + __skb_frag_ref(&sinfo->frags[i], false); } static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq, diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h index 11f0a4063403..4dcdbe9fbc5f 100644 --- a/include/linux/skbuff_ref.h +++ b/include/linux/skbuff_ref.h @@ -8,16 +8,47 @@ #define _LINUX_SKBUFF_REF_H #include +#include + +#ifdef CONFIG_PAGE_POOL +static inline bool is_pp_page(struct page *page) +{ + return (page->pp_magic & ~0x3UL) == PP_SIGNATURE; +} + +static inline bool napi_pp_get_page(struct page *page) +{ + page = compound_head(page); + + if (!is_pp_page(page)) + return false; + + page_pool_ref_page(page); + return true; +} +#endif + +static inline void skb_page_ref(struct page *page, bool recycle) +{ +#ifdef CONFIG_PAGE_POOL + if (recycle && napi_pp_get_page(page)) + return; +#endif + get_page(page); +} /** * __skb_frag_ref - take an addition reference on a paged fragment. * @frag: the paged fragment + * @recycle: skb->pp_recycle param of the parent skb. False if no parent skb. * - * Takes an additional reference on the paged fragment @frag. + * Takes an additional reference on the paged fragment @frag. Obtains the + * correct reference count depending on whether skb->pp_recycle is set and + * whether the frag is a page pool frag. */ -static inline void __skb_frag_ref(skb_frag_t *frag) +static inline void __skb_frag_ref(skb_frag_t *frag, bool recycle) { - get_page(skb_frag_page(frag)); + skb_page_ref(skb_frag_page(frag), recycle); } /** @@ -29,7 +60,7 @@ static inline void __skb_frag_ref(skb_frag_t *frag) */ static inline void skb_frag_ref(struct sk_buff *skb, int f) { - __skb_frag_ref(&skb_shinfo(skb)->frags[f]); + __skb_frag_ref(&skb_shinfo(skb)->frags[f], skb->pp_recycle); } bool napi_pp_put_page(struct page *page); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2554a6f5f386..ea052fa710d8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -907,11 +907,6 @@ static void skb_clone_fraglist(struct sk_buff *skb) skb_get(list); } -static bool is_pp_page(struct page *page) -{ - return (page->pp_magic & ~0x3UL) == PP_SIGNATURE; -} - int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom) { @@ -1033,37 +1028,6 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data) return napi_pp_put_page(virt_to_page(data)); } -/** - * skb_pp_frag_ref() - Increase fragment references of a page pool aware skb - * @skb: page pool aware skb - * - * Increase the fragment reference count (pp_ref_count) of a skb. This is - * intended to gain fragment references only for page pool aware skbs, - * i.e. when skb->pp_recycle is true, and not for fragments in a - * non-pp-recycling skb. It has a fallback to increase references on normal - * pages, as page pool aware skbs may also have normal page fragments. - */ -static int skb_pp_frag_ref(struct sk_buff *skb) -{ - struct skb_shared_info *shinfo; - struct page *head_page; - int i; - - if (!skb->pp_recycle) - return -EINVAL; - - shinfo = skb_shinfo(skb); - - for (i = 0; i < shinfo->nr_frags; i++) { - head_page = compound_head(skb_frag_page(&shinfo->frags[i])); - if (likely(is_pp_page(head_page))) - page_pool_ref_page(head_page); - else - page_ref_inc(head_page); - } - return 0; -} - static void skb_kfree_head(void *head, unsigned int end_offset) { if (end_offset == SKB_SMALL_HEAD_HEADROOM) @@ -4176,7 +4140,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) to++; } else { - __skb_frag_ref(fragfrom); + __skb_frag_ref(fragfrom, skb->pp_recycle); skb_frag_page_copy(fragto, fragfrom); skb_frag_off_copy(fragto, fragfrom); skb_frag_size_set(fragto, todo); @@ -4826,7 +4790,7 @@ normal: } *nskb_frag = (i < 0) ? skb_head_frag_to_page_desc(frag_skb) : *frag; - __skb_frag_ref(nskb_frag); + __skb_frag_ref(nskb_frag, nskb->pp_recycle); size = skb_frag_size(nskb_frag); if (pos < offset) { @@ -5957,10 +5921,8 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, /* if the skb is not cloned this does nothing * since we set nr_frags to 0. */ - if (skb_pp_frag_ref(from)) { - for (i = 0; i < from_shinfo->nr_frags; i++) - __skb_frag_ref(&from_shinfo->frags[i]); - } + for (i = 0; i < from_shinfo->nr_frags; i++) + __skb_frag_ref(&from_shinfo->frags[i], from->pp_recycle); to->truesize += delta; to->len += len; diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index f9e3d3d90dcf..9237dded4467 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -278,7 +278,7 @@ static int fill_sg_in(struct scatterlist *sg_in, for (i = 0; remaining > 0; i++) { skb_frag_t *frag = &record->frags[i]; - __skb_frag_ref(frag); + __skb_frag_ref(frag, false); sg_set_page(sg_in + i, skb_frag_page(frag), skb_frag_size(frag), skb_frag_off(frag)); From 919b38a916b4c616f1ead7d551de74bfcbe13e3c Mon Sep 17 00:00:00 2001 From: Carolina Jubran Date: Thu, 11 Apr 2024 00:41:54 +0300 Subject: [PATCH 05/21] net/mlx5e: Expose the VF/SF RX drop counter on the representor Q counters are device-level counters that track specific events, among which are out_of_buffer events. These events occur when packets are dropped due to a lack of receive buffer in the RX queue. Expose the total number of out_of_buffer events on the VFs/SFs to their respective representor, using the "ip stats group link" under the name of "rx_missed". The "rx_missed" equals the sum of all Q counters out_of_buffer values allocated on the VFs/SFs. Signed-off-by: Carolina Jubran Reviewed-by: Gal Pressman Reviewed-by: Aya Levin Reviewed-by: Rahul Rameshbabu Signed-off-by: Tariq Toukan Reviewed-by: Jacob Keller Link: https://lore.kernel.org/r/20240410214154.250583-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/mellanox/mlx5/core/en_rep.c | 42 ++++++++++++++++++- .../ethernet/mellanox/mlx5/core/en_stats.h | 2 + 2 files changed, 43 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index a74ee698671c..6acecf2e7cf6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -273,6 +273,40 @@ out: kvfree(out); } +static int mlx5e_rep_query_aggr_q_counter(struct mlx5_core_dev *dev, int vport, void *out) +{ + u32 in[MLX5_ST_SZ_DW(query_q_counter_in)] = {}; + + MLX5_SET(query_q_counter_in, in, opcode, MLX5_CMD_OP_QUERY_Q_COUNTER); + MLX5_SET(query_q_counter_in, in, other_vport, 1); + MLX5_SET(query_q_counter_in, in, vport_number, vport); + MLX5_SET(query_q_counter_in, in, aggregate, 1); + + return mlx5_cmd_exec_inout(dev, query_q_counter, in, out); +} + +static void mlx5e_rep_update_vport_q_counter(struct mlx5e_priv *priv) +{ + struct mlx5e_rep_stats *rep_stats = &priv->stats.rep_stats; + u32 out[MLX5_ST_SZ_DW(query_q_counter_out)] = {}; + struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5_eswitch_rep *rep = rpriv->rep; + int err; + + if (!MLX5_CAP_GEN(priv->mdev, q_counter_other_vport) || + !MLX5_CAP_GEN(priv->mdev, q_counter_aggregation)) + return; + + err = mlx5e_rep_query_aggr_q_counter(priv->mdev, rep->vport, out); + if (err) { + netdev_warn(priv->netdev, "failed reading stats on vport %d, error %d\n", + rep->vport, err); + return; + } + + rep_stats->rx_vport_out_of_buffer = MLX5_GET(query_q_counter_out, out, out_of_buffer); +} + static void mlx5e_rep_get_strings(struct net_device *dev, u32 stringset, u8 *data) { @@ -1229,6 +1263,12 @@ static int mlx5e_update_rep_rx(struct mlx5e_priv *priv) return 0; } +static void mlx5e_rep_stats_update_ndo_stats(struct mlx5e_priv *priv) +{ + mlx5e_stats_update_ndo_stats(priv); + mlx5e_rep_update_vport_q_counter(priv); +} + static int mlx5e_rep_event_mpesw(struct mlx5e_priv *priv) { struct mlx5e_rep_priv *rpriv = priv->ppriv; @@ -1421,7 +1461,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = { .enable = mlx5e_rep_enable, .disable = mlx5e_rep_disable, .update_rx = mlx5e_update_rep_rx, - .update_stats = mlx5e_stats_update_ndo_stats, + .update_stats = mlx5e_rep_stats_update_ndo_stats, .rx_handlers = &mlx5e_rx_handlers_rep, .max_tc = 1, .stats_grps = mlx5e_rep_stats_grps, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 9cee4c9472e9..650732288616 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -484,6 +484,7 @@ struct mlx5e_rep_stats { u64 tx_vport_rdma_multicast_bytes; u64 vport_loopback_packets; u64 vport_loopback_bytes; + u64 rx_vport_out_of_buffer; }; struct mlx5e_stats { @@ -504,6 +505,7 @@ static inline void mlx5e_stats_copy_rep_stats(struct rtnl_link_stats64 *vf_vport vf_vport->tx_packets = rep_stats->vport_tx_packets; vf_vport->rx_bytes = rep_stats->vport_rx_bytes; vf_vport->tx_bytes = rep_stats->vport_tx_bytes; + vf_vport->rx_missed_errors = rep_stats->rx_vport_out_of_buffer; } extern mlx5e_stats_grp_t mlx5e_nic_stats_grps[]; From e1eb10f8ef1068e565b24daa3e95bd8bc95d8cdc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Asbj=C3=B8rn=20Sloth=20T=C3=B8nnesen?= Date: Wed, 10 Apr 2024 11:47:17 +0000 Subject: [PATCH 06/21] flow_offload: fix flow_offload_has_one_action() kdoc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit include/net/flow_offload.h:351: warning: No description found for return value of 'flow_offload_has_one_action' Signed-off-by: Asbjørn Sloth Tønnesen Reviewed-by: Pieter Jansen van Vuuren Link: https://lore.kernel.org/r/20240410114718.15145-1-ast@fiberby.net Signed-off-by: Jakub Kicinski --- include/net/flow_offload.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 314087a5e181..7726b4a97050 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -345,7 +345,7 @@ static inline bool flow_action_has_entries(const struct flow_action *action) * flow_offload_has_one_action() - check if exactly one action is present * @action: tc filter flow offload action * - * Returns true if exactly one action is present. + * Return: true if exactly one action is present. */ static inline bool flow_offload_has_one_action(const struct flow_action *action) { From e0f89d2864b062b027196925ea19f94b2ce50d6a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 10 Apr 2024 11:19:50 +0000 Subject: [PATCH 07/21] mpls: no longer hold RTNL in mpls_netconf_dump_devconf() - Use for_each_netdev_dump() to no longer rely on net->dev_index_head hash table. - No longer care of net->dev_base_seq - Fix return value at the end of a dump, so that NLMSG_DONE can be appended to current skb, saving one recvmsg() system call. - No longer grab RTNL, RCU protection is enough, afer adding one READ_ONCE(mdev->input_enabled) in mpls_netconf_fill_devconf() Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20240410111951.2673193-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/mpls/af_mpls.c | 59 +++++++++++++++++----------------------------- 1 file changed, 22 insertions(+), 37 deletions(-) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 1303acb9cdd2..0315b8deed3f 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1154,7 +1154,7 @@ static int mpls_netconf_fill_devconf(struct sk_buff *skb, struct mpls_dev *mdev, if ((all || type == NETCONFA_INPUT) && nla_put_s32(skb, NETCONFA_INPUT, - mdev->input_enabled) < 0) + READ_ONCE(mdev->input_enabled)) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); @@ -1303,11 +1303,12 @@ static int mpls_netconf_dump_devconf(struct sk_buff *skb, { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); - struct hlist_head *head; + struct { + unsigned long ifindex; + } *ctx = (void *)cb->ctx; struct net_device *dev; struct mpls_dev *mdev; - int idx, s_idx; - int h, s_h; + int err = 0; if (cb->strict_check) { struct netlink_ext_ack *extack = cb->extack; @@ -1324,40 +1325,23 @@ static int mpls_netconf_dump_devconf(struct sk_buff *skb, } } - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - rcu_read_lock(); - cb->seq = net->dev_base_seq; - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - mdev = mpls_dev_get(dev); - if (!mdev) - goto cont; - if (mpls_netconf_fill_devconf(skb, mdev, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, - RTM_NEWNETCONF, - NLM_F_MULTI, - NETCONFA_ALL) < 0) { - rcu_read_unlock(); - goto done; - } - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); -cont: - idx++; - } - rcu_read_unlock(); + rcu_read_lock(); + for_each_netdev_dump(net, dev, ctx->ifindex) { + mdev = mpls_dev_get(dev); + if (!mdev) + continue; + err = mpls_netconf_fill_devconf(skb, mdev, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, + RTM_NEWNETCONF, + NLM_F_MULTI, + NETCONFA_ALL); + if (err < 0) + break; } -done: - cb->args[0] = h; - cb->args[1] = idx; + rcu_read_unlock(); - return skb->len; + return err; } #define MPLS_PERDEV_SYSCTL_OFFSET(field) \ @@ -2773,7 +2757,8 @@ static int __init mpls_init(void) mpls_getroute, mpls_dump_routes, 0); rtnl_register_module(THIS_MODULE, PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf, - mpls_netconf_dump_devconf, 0); + mpls_netconf_dump_devconf, + RTNL_FLAG_DUMP_UNLOCKED); err = ipgre_tunnel_encap_add_mpls_ops(); if (err) pr_err("Can't add mpls over gre tunnel ops\n"); From 8959bf2acfbccd6abd2f1bf844716a27355103b2 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Tue, 9 Apr 2024 06:33:05 -0700 Subject: [PATCH 08/21] net: usb: qmi_wwan: Leverage core stats allocator With commit 34d21de99cea9 ("net: Move {l,t,d}stats allocation to core and convert veth & vrf"), stats allocation could be done on net core instead of in this driver. With this new approach, the driver doesn't have to bother with error handling (allocation failure checking, making sure free happens in the right spot, etc). This is core responsibility now. Remove the allocation in the qmi_wwan driver and leverage the network core allocation instead. Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20240409133307.2058099-1-leitao@debian.org Signed-off-by: Jakub Kicinski --- drivers/net/usb/qmi_wwan.c | 8 +------- drivers/net/usb/usbnet.c | 1 + 2 files changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index e2e181378f41..5528a9c2b9d6 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -133,6 +133,7 @@ static void qmimux_setup(struct net_device *dev) dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; dev->netdev_ops = &qmimux_netdev_ops; dev->mtu = 1500; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->needs_free_netdev = true; } @@ -257,12 +258,6 @@ static int qmimux_register_device(struct net_device *real_dev, u8 mux_id) priv->mux_id = mux_id; priv->real_dev = real_dev; - new_dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!new_dev->tstats) { - err = -ENOBUFS; - goto out_free_newdev; - } - new_dev->sysfs_groups[0] = &qmi_wwan_sysfs_qmimux_attr_group; err = register_netdevice(new_dev); @@ -295,7 +290,6 @@ static void qmimux_unregister_device(struct net_device *dev, struct qmimux_priv *priv = netdev_priv(dev); struct net_device *real_dev = priv->real_dev; - free_percpu(dev->tstats); netdev_upper_dev_unlink(real_dev, dev); unregister_netdevice_queue(dev, head); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index e84efa661589..f3f7f686fe9c 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1733,6 +1733,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) dev->hard_mtu = net->mtu + net->hard_header_len; net->min_mtu = 0; net->max_mtu = ETH_MAX_MTU; + net->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; net->netdev_ops = &usbnet_netdev_ops; net->watchdog_timeo = TX_TIMEOUT_JIFFIES; From 3cddfeca9f02d95f87a562c5bdd1f46cf4e35632 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Tue, 9 Apr 2024 06:33:06 -0700 Subject: [PATCH 09/21] net: usb: qmi_wwan: Remove generic .ndo_get_stats64 Commit 3e2f544dd8a33 ("net: get stats64 if device if driver is configured") moved the callback to dev_get_tstats64() to net core, so, unless the driver is doing some custom stats collection, it does not need to set .ndo_get_stats64. Since this driver is now relying in NETDEV_PCPU_STAT_TSTATS, then, it doesn't need to set the dev_get_tstats64() generic .ndo_get_stats64 function pointer. Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20240409133307.2058099-2-leitao@debian.org Signed-off-by: Jakub Kicinski --- drivers/net/usb/qmi_wwan.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 5528a9c2b9d6..0e764f09a57d 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -121,7 +121,6 @@ static const struct net_device_ops qmimux_netdev_ops = { .ndo_open = qmimux_open, .ndo_stop = qmimux_stop, .ndo_start_xmit = qmimux_start_xmit, - .ndo_get_stats64 = dev_get_tstats64, }; static void qmimux_setup(struct net_device *dev) @@ -638,7 +637,6 @@ static const struct net_device_ops qmi_wwan_netdev_ops = { .ndo_start_xmit = usbnet_start_xmit, .ndo_tx_timeout = usbnet_tx_timeout, .ndo_change_mtu = usbnet_change_mtu, - .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = qmi_wwan_mac_addr, .ndo_validate_addr = eth_validate_addr, }; From 05ea491641d338422edbd87af3b311c16ea762f5 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Tue, 9 Apr 2024 11:28:05 -0400 Subject: [PATCH 10/21] tcp: add support for SO_PEEK_OFF socket option When reading received messages from a socket with MSG_PEEK, we may want to read the contents with an offset, like we can do with pread/preadv() when reading files. Currently, it is not possible to do that. In this commit, we add support for the SO_PEEK_OFF socket option for TCP, in a similar way it is done for Unix Domain sockets. In the iperf3 log examples shown below, we can observe a throughput improvement of 15-20 % in the direction host->namespace when using the protocol splicer 'pasta' (https://passt.top). This is a consistent result. pasta(1) and passt(1) implement user-mode networking for network namespaces (containers) and virtual machines by means of a translation layer between Layer-2 network interface and native Layer-4 sockets (TCP, UDP, ICMP/ICMPv6 echo). Received, pending TCP data to the container/guest is kept in kernel buffers until acknowledged, so the tool routinely needs to fetch new data from socket, skipping data that was already sent. At the moment this is implemented using a dummy buffer passed to recvmsg(). With this change, we don't need a dummy buffer and the related buffer copy (copy_to_user()) anymore. passt and pasta are supported in KubeVirt and libvirt/qemu. jmaloy@freyr:~/passt$ perf record -g ./pasta --config-net -f SO_PEEK_OFF not supported by kernel. jmaloy@freyr:~/passt# iperf3 -s ----------------------------------------------------------- Server listening on 5201 (test #1) ----------------------------------------------------------- Accepted connection from 192.168.122.1, port 44822 [ 5] local 192.168.122.180 port 5201 connected to 192.168.122.1 port 44832 [ ID] Interval Transfer Bitrate [ 5] 0.00-1.00 sec 1.02 GBytes 8.78 Gbits/sec [ 5] 1.00-2.00 sec 1.06 GBytes 9.08 Gbits/sec [ 5] 2.00-3.00 sec 1.07 GBytes 9.15 Gbits/sec [ 5] 3.00-4.00 sec 1.10 GBytes 9.46 Gbits/sec [ 5] 4.00-5.00 sec 1.03 GBytes 8.85 Gbits/sec [ 5] 5.00-6.00 sec 1.10 GBytes 9.44 Gbits/sec [ 5] 6.00-7.00 sec 1.11 GBytes 9.56 Gbits/sec [ 5] 7.00-8.00 sec 1.07 GBytes 9.20 Gbits/sec [ 5] 8.00-9.00 sec 667 MBytes 5.59 Gbits/sec [ 5] 9.00-10.00 sec 1.03 GBytes 8.83 Gbits/sec [ 5] 10.00-10.04 sec 30.1 MBytes 6.36 Gbits/sec - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate [ 5] 0.00-10.04 sec 10.3 GBytes 8.78 Gbits/sec receiver ----------------------------------------------------------- Server listening on 5201 (test #2) ----------------------------------------------------------- ^Ciperf3: interrupt - the server has terminated jmaloy@freyr:~/passt# logout [ perf record: Woken up 23 times to write data ] [ perf record: Captured and wrote 5.696 MB perf.data (35580 samples) ] jmaloy@freyr:~/passt$ jmaloy@freyr:~/passt$ perf record -g ./pasta --config-net -f SO_PEEK_OFF supported by kernel. jmaloy@freyr:~/passt# iperf3 -s ----------------------------------------------------------- Server listening on 5201 (test #1) ----------------------------------------------------------- Accepted connection from 192.168.122.1, port 52084 [ 5] local 192.168.122.180 port 5201 connected to 192.168.122.1 port 52098 [ ID] Interval Transfer Bitrate [ 5] 0.00-1.00 sec 1.32 GBytes 11.3 Gbits/sec [ 5] 1.00-2.00 sec 1.19 GBytes 10.2 Gbits/sec [ 5] 2.00-3.00 sec 1.26 GBytes 10.8 Gbits/sec [ 5] 3.00-4.00 sec 1.36 GBytes 11.7 Gbits/sec [ 5] 4.00-5.00 sec 1.33 GBytes 11.4 Gbits/sec [ 5] 5.00-6.00 sec 1.21 GBytes 10.4 Gbits/sec [ 5] 6.00-7.00 sec 1.31 GBytes 11.2 Gbits/sec [ 5] 7.00-8.00 sec 1.25 GBytes 10.7 Gbits/sec [ 5] 8.00-9.00 sec 1.33 GBytes 11.5 Gbits/sec [ 5] 9.00-10.00 sec 1.24 GBytes 10.7 Gbits/sec [ 5] 10.00-10.04 sec 56.0 MBytes 12.1 Gbits/sec - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate [ 5] 0.00-10.04 sec 12.9 GBytes 11.0 Gbits/sec receiver ----------------------------------------------------------- Server listening on 5201 (test #2) ----------------------------------------------------------- ^Ciperf3: interrupt - the server has terminated logout [ perf record: Woken up 20 times to write data ] [ perf record: Captured and wrote 5.040 MB perf.data (33411 samples) ] jmaloy@freyr:~/passt$ The perf record confirms this result. Below, we can observe that the CPU spends significantly less time in the function ____sys_recvmsg() when we have offset support. Without offset support: ---------------------- jmaloy@freyr:~/passt$ perf report -q --symbol-filter=do_syscall_64 \ -p ____sys_recvmsg -x --stdio -i perf.data | head -1 46.32% 0.00% passt.avx2 [kernel.vmlinux] [k] do_syscall_64 ____sys_recvmsg With offset support: ---------------------- jmaloy@freyr:~/passt$ perf report -q --symbol-filter=do_syscall_64 \ -p ____sys_recvmsg -x --stdio -i perf.data | head -1 28.12% 0.00% passt.avx2 [kernel.vmlinux] [k] do_syscall_64 ____sys_recvmsg Suggested-by: Paolo Abeni Reviewed-by: Stefano Brivio Signed-off-by: Jon Maloy Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20240409152805.913891-1-jmaloy@redhat.com Signed-off-by: Jakub Kicinski --- net/ipv4/af_inet.c | 1 + net/ipv4/tcp.c | 16 ++++++++++------ 2 files changed, 11 insertions(+), 6 deletions(-) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 55bd72997b31..a7cfeda28bb2 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1072,6 +1072,7 @@ const struct proto_ops inet_stream_ops = { #endif .splice_eof = inet_splice_eof, .splice_read = tcp_splice_read, + .set_peek_off = sk_set_peek_off, .read_sock = tcp_read_sock, .read_skb = tcp_read_skb, .sendmsg_locked = tcp_sendmsg_locked, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e1bf468e0d22..f23b97777ea5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1419,8 +1419,6 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) struct sk_buff *skb; int copied = 0, err = 0; - /* XXX -- need to support SO_PEEK_OFF */ - skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) @@ -2331,6 +2329,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int target; /* Read at least this many bytes */ long timeo; struct sk_buff *skb, *last; + u32 peek_offset = 0; u32 urg_hole = 0; err = -ENOTCONN; @@ -2364,7 +2363,8 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, seq = &tp->copied_seq; if (flags & MSG_PEEK) { - peek_seq = tp->copied_seq; + peek_offset = max(sk_peek_offset(sk, flags), 0); + peek_seq = tp->copied_seq + peek_offset; seq = &peek_seq; } @@ -2467,11 +2467,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, } if ((flags & MSG_PEEK) && - (peek_seq - copied - urg_hole != tp->copied_seq)) { + (peek_seq - peek_offset - copied - urg_hole != tp->copied_seq)) { net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n", current->comm, task_pid_nr(current)); - peek_seq = tp->copied_seq; + peek_seq = tp->copied_seq + peek_offset; } continue; @@ -2512,7 +2512,10 @@ found_ok_skb: WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; - + if (flags & MSG_PEEK) + sk_peek_offset_fwd(sk, used); + else + sk_peek_offset_bwd(sk, used); tcp_rcv_space_adjust(sk); skip_copy: @@ -3013,6 +3016,7 @@ int tcp_disconnect(struct sock *sk, int flags) __skb_queue_purge(&sk->sk_receive_queue); WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); WRITE_ONCE(tp->urg_data, 0); + sk_set_peek_off(sk, -1); tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); skb_rbtree_purge(&tp->out_of_order_queue); From 5618603f5d063c8d769d2e64cd440f787567fd13 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Wed, 10 Apr 2024 15:14:29 +0200 Subject: [PATCH 11/21] ipv4: Remove RTO_ONLINK. RTO_ONLINK was a flag used in ->flowi4_tos that allowed to alter the scope of an IPv4 route lookup. Setting this flag was equivalent to specifying RT_SCOPE_LINK in ->flowi4_scope. With commit ec20b2830093 ("ipv4: Set scope explicitly in ip_route_output()."), the last users of RTO_ONLINK have been removed. Therefore, we can now drop the code that checked this bit and stop modifying ->flowi4_scope in ip_route_output_key_hash(). Signed-off-by: Guillaume Nault Reviewed-by: Przemek Kitszel Reviewed-by: David Ahern Link: https://lore.kernel.org/r/57de760565cab55df7b129f523530ac6475865b2.1712754146.git.gnault@redhat.com Signed-off-by: Jakub Kicinski --- include/net/route.h | 2 -- net/ipv4/route.c | 14 +------------- 2 files changed, 1 insertion(+), 15 deletions(-) diff --git a/include/net/route.h b/include/net/route.h index 315a8acee6c6..630d1ef6868a 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -35,8 +35,6 @@ #include #include -#define RTO_ONLINK 0x01 - static inline __u8 ip_sock_rt_scope(const struct sock *sk) { if (sock_flag(sk, SOCK_LOCALROUTE)) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d36ace160d42..6133f1fd848e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -106,9 +106,6 @@ #include "fib_lookup.h" -#define RT_FL_TOS(oldflp4) \ - ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) - #define RT_GC_TIMEOUT (300*HZ) #define DEFAULT_MIN_PMTU (512 + 20 + 20) @@ -498,15 +495,6 @@ void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) } EXPORT_SYMBOL(__ip_select_ident); -static void ip_rt_fix_tos(struct flowi4 *fl4) -{ - __u8 tos = RT_FL_TOS(fl4); - - fl4->flowi4_tos = tos & IPTOS_RT_MASK; - if (tos & RTO_ONLINK) - fl4->flowi4_scope = RT_SCOPE_LINK; -} - static void __build_flow_key(const struct net *net, struct flowi4 *fl4, const struct sock *sk, const struct iphdr *iph, int oif, __u8 tos, u8 prot, u32 mark, @@ -2636,7 +2624,7 @@ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, struct rtable *rth; fl4->flowi4_iif = LOOPBACK_IFINDEX; - ip_rt_fix_tos(fl4); + fl4->flowi4_tos &= IPTOS_RT_MASK; rcu_read_lock(); rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); From f7ac8fbd3215e72824c08b53cd2ff272d42eb823 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 10 Apr 2024 15:41:36 +0100 Subject: [PATCH 12/21] tls: remove redundant assignment to variable decrypted The variable decrypted is being assigned a value that is never read, the control of flow after the assignment is via an return path and decrypted is not referenced in this path. The assignment is redundant and can be removed. Cleans up clang scan warning: net/tls/tls_sw.c:2150:4: warning: Value stored to 'decrypted' is never read [deadcode.DeadStores] Signed-off-by: Colin Ian King Link: https://lore.kernel.org/r/20240410144136.289030-1-colin.i.king@gmail.com Signed-off-by: Jakub Kicinski --- net/tls/tls_sw.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index b783231668c6..305a412785f5 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2147,7 +2147,6 @@ recv_end: if (ret) { if (err >= 0 || err == -EINPROGRESS) err = ret; - decrypted = 0; goto end; } From dd0c9855b41310470086500c9963bbb64bb90dd0 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Wed, 10 Apr 2024 20:42:38 +0100 Subject: [PATCH 13/21] net: dsa: introduce dsa_phylink_to_port() We convert from a phylink_config struct to a dsa_port struct in many places, let's provide a helper for this. Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: Russell King (Oracle) Reviewed-by: Vladimir Oltean Link: https://lore.kernel.org/r/E1rudqA-006K9B-85@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 6 ++++++ net/dsa/port.c | 12 ++++++------ 2 files changed, 12 insertions(+), 6 deletions(-) diff --git a/include/net/dsa.h b/include/net/dsa.h index 7c0da9effe4e..f228b479a5fd 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -327,6 +327,12 @@ struct dsa_port { }; }; +static inline struct dsa_port * +dsa_phylink_to_port(struct phylink_config *config) +{ + return container_of(config, struct dsa_port, pl_config); +} + /* TODO: ideally DSA ports would have a single dp->link_dp member, * and no dst->rtable nor this struct dsa_link would be needed, * but this would require some more complex tree walking, diff --git a/net/dsa/port.c b/net/dsa/port.c index c42dac87671b..02bf1c306bdc 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1558,7 +1558,7 @@ static struct phylink_pcs * dsa_port_phylink_mac_select_pcs(struct phylink_config *config, phy_interface_t interface) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_port *dp = dsa_phylink_to_port(config); struct phylink_pcs *pcs = ERR_PTR(-EOPNOTSUPP); struct dsa_switch *ds = dp->ds; @@ -1572,7 +1572,7 @@ static int dsa_port_phylink_mac_prepare(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_port *dp = dsa_phylink_to_port(config); struct dsa_switch *ds = dp->ds; int err = 0; @@ -1587,7 +1587,7 @@ static void dsa_port_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_port *dp = dsa_phylink_to_port(config); struct dsa_switch *ds = dp->ds; if (!ds->ops->phylink_mac_config) @@ -1600,7 +1600,7 @@ static int dsa_port_phylink_mac_finish(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_port *dp = dsa_phylink_to_port(config); struct dsa_switch *ds = dp->ds; int err = 0; @@ -1615,7 +1615,7 @@ static void dsa_port_phylink_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_port *dp = dsa_phylink_to_port(config); struct phy_device *phydev = NULL; struct dsa_switch *ds = dp->ds; @@ -1638,7 +1638,7 @@ static void dsa_port_phylink_mac_link_up(struct phylink_config *config, int speed, int duplex, bool tx_pause, bool rx_pause) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_port *dp = dsa_phylink_to_port(config); struct dsa_switch *ds = dp->ds; if (!ds->ops->phylink_mac_link_up) { From cae425cb43feddd9fd62fc1b25567f9463da4915 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Wed, 10 Apr 2024 20:42:43 +0100 Subject: [PATCH 14/21] net: dsa: allow DSA switch drivers to provide their own phylink mac ops Rather than having a shim for each and every phylink MAC operation, allow DSA switch drivers to provide their own ops structure. When a DSA driver provides the phylink MAC operations, the shimmed ops must not be provided, so fail an attempt to register a switch with both the phylink_mac_ops in struct dsa_switch and the phylink_mac_* operations populated in dsa_switch_ops populated. Signed-off-by: Russell King (Oracle) Reviewed-by: Vladimir Oltean Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/E1rudqF-006K9H-Cc@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 5 +++++ net/dsa/dsa.c | 11 +++++++++++ net/dsa/port.c | 26 ++++++++++++++++++++------ 3 files changed, 36 insertions(+), 6 deletions(-) diff --git a/include/net/dsa.h b/include/net/dsa.h index f228b479a5fd..7edfd8de8882 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -457,6 +457,11 @@ struct dsa_switch { */ const struct dsa_switch_ops *ops; + /* + * Allow a DSA switch driver to override the phylink MAC ops + */ + const struct phylink_mac_ops *phylink_mac_ops; + /* * User mii_bus and devices for the individual ports. */ diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 09d2f5d4b3dd..2f347cd37316 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -1505,6 +1505,17 @@ static int dsa_switch_probe(struct dsa_switch *ds) if (!ds->num_ports) return -EINVAL; + if (ds->phylink_mac_ops) { + if (ds->ops->phylink_mac_select_pcs || + ds->ops->phylink_mac_prepare || + ds->ops->phylink_mac_config || + ds->ops->phylink_mac_finish || + ds->ops->phylink_mac_link_down || + ds->ops->phylink_mac_link_up || + ds->ops->adjust_link) + return -EINVAL; + } + if (np) { err = dsa_switch_parse_of(ds, np); if (err) diff --git a/net/dsa/port.c b/net/dsa/port.c index 02bf1c306bdc..c6febc3d96d9 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1662,6 +1662,7 @@ static const struct phylink_mac_ops dsa_port_phylink_mac_ops = { int dsa_port_phylink_create(struct dsa_port *dp) { + const struct phylink_mac_ops *mac_ops; struct dsa_switch *ds = dp->ds; phy_interface_t mode; struct phylink *pl; @@ -1685,8 +1686,12 @@ int dsa_port_phylink_create(struct dsa_port *dp) } } - pl = phylink_create(&dp->pl_config, of_fwnode_handle(dp->dn), - mode, &dsa_port_phylink_mac_ops); + mac_ops = &dsa_port_phylink_mac_ops; + if (ds->phylink_mac_ops) + mac_ops = ds->phylink_mac_ops; + + pl = phylink_create(&dp->pl_config, of_fwnode_handle(dp->dn), mode, + mac_ops); if (IS_ERR(pl)) { pr_err("error creating PHYLINK: %ld\n", PTR_ERR(pl)); return PTR_ERR(pl); @@ -1952,12 +1957,23 @@ static void dsa_shared_port_validate_of(struct dsa_port *dp, dn, dsa_port_is_cpu(dp) ? "CPU" : "DSA", dp->index); } +static void dsa_shared_port_link_down(struct dsa_port *dp) +{ + struct dsa_switch *ds = dp->ds; + + if (ds->phylink_mac_ops && ds->phylink_mac_ops->mac_link_down) + ds->phylink_mac_ops->mac_link_down(&dp->pl_config, MLO_AN_FIXED, + PHY_INTERFACE_MODE_NA); + else if (ds->ops->phylink_mac_link_down) + ds->ops->phylink_mac_link_down(ds, dp->index, MLO_AN_FIXED, + PHY_INTERFACE_MODE_NA); +} + int dsa_shared_port_link_register_of(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; bool missing_link_description; bool missing_phy_mode; - int port = dp->index; dsa_shared_port_validate_of(dp, &missing_phy_mode, &missing_link_description); @@ -1973,9 +1989,7 @@ int dsa_shared_port_link_register_of(struct dsa_port *dp) "Skipping phylink registration for %s port %d\n", dsa_port_is_cpu(dp) ? "CPU" : "DSA", dp->index); } else { - if (ds->ops->phylink_mac_link_down) - ds->ops->phylink_mac_link_down(ds, port, - MLO_AN_FIXED, PHY_INTERFACE_MODE_NA); + dsa_shared_port_link_down(dp); return dsa_shared_port_phylink_register(dp); } From 0cb6da0c487d21236514f230bd6d2b799ee0a822 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Wed, 10 Apr 2024 20:42:48 +0100 Subject: [PATCH 15/21] net: dsa: mv88e6xxx: provide own phylink MAC operations Convert mv88e6xxx to provide its own phylink MAC operations, thus avoiding the shim layer in DSA's port.c Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: Russell King (Oracle) Reviewed-by: Vladimir Oltean Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/E1rudqK-006K9N-HY@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski --- drivers/net/dsa/mv88e6xxx/chip.c | 63 ++++++++++++++++++++------------ 1 file changed, 39 insertions(+), 24 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index c95787cb9086..e950a634a3c7 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -790,24 +790,27 @@ static void mv88e6xxx_get_caps(struct dsa_switch *ds, int port, } } -static struct phylink_pcs *mv88e6xxx_mac_select_pcs(struct dsa_switch *ds, - int port, - phy_interface_t interface) +static struct phylink_pcs * +mv88e6xxx_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) { - struct mv88e6xxx_chip *chip = ds->priv; + struct dsa_port *dp = dsa_phylink_to_port(config); + struct mv88e6xxx_chip *chip = dp->ds->priv; struct phylink_pcs *pcs = ERR_PTR(-EOPNOTSUPP); if (chip->info->ops->pcs_ops) - pcs = chip->info->ops->pcs_ops->pcs_select(chip, port, + pcs = chip->info->ops->pcs_ops->pcs_select(chip, dp->index, interface); return pcs; } -static int mv88e6xxx_mac_prepare(struct dsa_switch *ds, int port, +static int mv88e6xxx_mac_prepare(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { - struct mv88e6xxx_chip *chip = ds->priv; + struct dsa_port *dp = dsa_phylink_to_port(config); + struct mv88e6xxx_chip *chip = dp->ds->priv; + int port = dp->index; int err = 0; /* In inband mode, the link may come up at any time while the link @@ -826,11 +829,13 @@ static int mv88e6xxx_mac_prepare(struct dsa_switch *ds, int port, return err; } -static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, +static void mv88e6xxx_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { - struct mv88e6xxx_chip *chip = ds->priv; + struct dsa_port *dp = dsa_phylink_to_port(config); + struct mv88e6xxx_chip *chip = dp->ds->priv; + int port = dp->index; int err = 0; mv88e6xxx_reg_lock(chip); @@ -846,13 +851,15 @@ err_unlock: mv88e6xxx_reg_unlock(chip); if (err && err != -EOPNOTSUPP) - dev_err(ds->dev, "p%d: failed to configure MAC/PCS\n", port); + dev_err(chip->dev, "p%d: failed to configure MAC/PCS\n", port); } -static int mv88e6xxx_mac_finish(struct dsa_switch *ds, int port, +static int mv88e6xxx_mac_finish(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { - struct mv88e6xxx_chip *chip = ds->priv; + struct dsa_port *dp = dsa_phylink_to_port(config); + struct mv88e6xxx_chip *chip = dp->ds->priv; + int port = dp->index; int err = 0; /* Undo the forced down state above after completing configuration @@ -876,12 +883,14 @@ static int mv88e6xxx_mac_finish(struct dsa_switch *ds, int port, return err; } -static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port, +static void mv88e6xxx_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { - struct mv88e6xxx_chip *chip = ds->priv; + struct dsa_port *dp = dsa_phylink_to_port(config); + struct mv88e6xxx_chip *chip = dp->ds->priv; const struct mv88e6xxx_ops *ops; + int port = dp->index; int err = 0; ops = chip->info->ops; @@ -904,14 +913,16 @@ static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port, "p%d: failed to force MAC link down\n", port); } -static void mv88e6xxx_mac_link_up(struct dsa_switch *ds, int port, - unsigned int mode, phy_interface_t interface, +static void mv88e6xxx_mac_link_up(struct phylink_config *config, struct phy_device *phydev, + unsigned int mode, phy_interface_t interface, int speed, int duplex, bool tx_pause, bool rx_pause) { - struct mv88e6xxx_chip *chip = ds->priv; + struct dsa_port *dp = dsa_phylink_to_port(config); + struct mv88e6xxx_chip *chip = dp->ds->priv; const struct mv88e6xxx_ops *ops; + int port = dp->index; int err = 0; ops = chip->info->ops; @@ -937,7 +948,7 @@ error: mv88e6xxx_reg_unlock(chip); if (err && err != -EOPNOTSUPP) - dev_err(ds->dev, + dev_err(chip->dev, "p%d: failed to configure MAC link up\n", port); } @@ -6922,6 +6933,15 @@ static int mv88e6xxx_crosschip_lag_leave(struct dsa_switch *ds, int sw_index, return err_sync ? : err_pvt; } +static const struct phylink_mac_ops mv88e6xxx_phylink_mac_ops = { + .mac_select_pcs = mv88e6xxx_mac_select_pcs, + .mac_prepare = mv88e6xxx_mac_prepare, + .mac_config = mv88e6xxx_mac_config, + .mac_finish = mv88e6xxx_mac_finish, + .mac_link_down = mv88e6xxx_mac_link_down, + .mac_link_up = mv88e6xxx_mac_link_up, +}; + static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .get_tag_protocol = mv88e6xxx_get_tag_protocol, .change_tag_protocol = mv88e6xxx_change_tag_protocol, @@ -6930,12 +6950,6 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .port_setup = mv88e6xxx_port_setup, .port_teardown = mv88e6xxx_port_teardown, .phylink_get_caps = mv88e6xxx_get_caps, - .phylink_mac_select_pcs = mv88e6xxx_mac_select_pcs, - .phylink_mac_prepare = mv88e6xxx_mac_prepare, - .phylink_mac_config = mv88e6xxx_mac_config, - .phylink_mac_finish = mv88e6xxx_mac_finish, - .phylink_mac_link_down = mv88e6xxx_mac_link_down, - .phylink_mac_link_up = mv88e6xxx_mac_link_up, .get_strings = mv88e6xxx_get_strings, .get_ethtool_stats = mv88e6xxx_get_ethtool_stats, .get_eth_mac_stats = mv88e6xxx_get_eth_mac_stats, @@ -7004,6 +7018,7 @@ static int mv88e6xxx_register_switch(struct mv88e6xxx_chip *chip) ds->priv = chip; ds->dev = dev; ds->ops = &mv88e6xxx_switch_ops; + ds->phylink_mac_ops = &mv88e6xxx_phylink_mac_ops; ds->ageing_time_min = chip->info->age_time_coeff; ds->ageing_time_max = chip->info->age_time_coeff * U8_MAX; From deb8af5243504e379878ae3f9a091b21422d65b2 Mon Sep 17 00:00:00 2001 From: Alexander Couzens Date: Tue, 9 Apr 2024 09:30:11 +0200 Subject: [PATCH 16/21] net: phy: realtek: configure SerDes mode for rtl822xb PHYs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The rtl8221b and rtl8226b series support switching SerDes mode between 2500base-x and sgmii based on the negotiated copper speed. Configure this switching mode according to SerDes modes supported by host. There is an additional datasheet for RTL8226B/RTL8221B called "SERDES MODE SETTING FLOW APPLICATION NOTE" where a sequence is described to setup interface and rate adapter mode. However, there is no documentation about the meaning of registers and bits, it's literally just magic numbers and pseudo-code. Signed-off-by: Alexander Couzens [ refactored, dropped HiSGMII mode and changed commit message ] Signed-off-by: Marek Behún [ changed rtl822x_update_interface() to use vendor register ] [ always fill in possible interfaces ] [ only apply to rtl8221b and rtl8226b phy's ] [ set phydev->rate_matching in .config_init() ] Signed-off-by: Eric Woudstra Reviewed-by: Russell King (Oracle) Reviewed-by: should come before them, without any blank lines. As the Signed-off-by: David S. Miller --- drivers/net/phy/realtek.c | 114 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 110 insertions(+), 4 deletions(-) diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 1fa70427b2a2..70cd1834a832 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -54,6 +54,16 @@ RTL8201F_ISR_LINK) #define RTL8201F_IER 0x13 +#define RTL822X_VND1_SERDES_OPTION 0x697a +#define RTL822X_VND1_SERDES_OPTION_MODE_MASK GENMASK(5, 0) +#define RTL822X_VND1_SERDES_OPTION_MODE_2500BASEX_SGMII 0 +#define RTL822X_VND1_SERDES_OPTION_MODE_2500BASEX 2 + +#define RTL822X_VND1_SERDES_CTRL3 0x7580 +#define RTL822X_VND1_SERDES_CTRL3_MODE_MASK GENMASK(5, 0) +#define RTL822X_VND1_SERDES_CTRL3_MODE_SGMII 0x02 +#define RTL822X_VND1_SERDES_CTRL3_MODE_2500BASEX 0x16 + #define RTL8366RB_POWER_SAVE 0x15 #define RTL8366RB_POWER_SAVE_ON BIT(12) @@ -659,6 +669,63 @@ static int rtl822x_write_mmd(struct phy_device *phydev, int devnum, u16 regnum, return ret; } +static int rtl822xb_config_init(struct phy_device *phydev) +{ + bool has_2500, has_sgmii; + u16 mode; + int ret; + + has_2500 = test_bit(PHY_INTERFACE_MODE_2500BASEX, + phydev->host_interfaces) || + phydev->interface == PHY_INTERFACE_MODE_2500BASEX; + + has_sgmii = test_bit(PHY_INTERFACE_MODE_SGMII, + phydev->host_interfaces) || + phydev->interface == PHY_INTERFACE_MODE_SGMII; + + /* fill in possible interfaces */ + __assign_bit(PHY_INTERFACE_MODE_2500BASEX, phydev->possible_interfaces, + has_2500); + __assign_bit(PHY_INTERFACE_MODE_SGMII, phydev->possible_interfaces, + has_sgmii); + + if (!has_2500 && !has_sgmii) + return 0; + + /* determine SerDes option mode */ + if (has_2500 && !has_sgmii) { + mode = RTL822X_VND1_SERDES_OPTION_MODE_2500BASEX; + phydev->rate_matching = RATE_MATCH_PAUSE; + } else { + mode = RTL822X_VND1_SERDES_OPTION_MODE_2500BASEX_SGMII; + phydev->rate_matching = RATE_MATCH_NONE; + } + + /* the following sequence with magic numbers sets up the SerDes + * option mode + */ + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x75f3, 0); + if (ret < 0) + return ret; + + ret = phy_modify_mmd_changed(phydev, MDIO_MMD_VEND1, + RTL822X_VND1_SERDES_OPTION, + RTL822X_VND1_SERDES_OPTION_MODE_MASK, + mode); + if (ret < 0) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x6a04, 0x0503); + if (ret < 0) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x6f10, 0xd455); + if (ret < 0) + return ret; + + return phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x6f11, 0x8020); +} + static int rtl822x_get_features(struct phy_device *phydev) { int val; @@ -695,6 +762,28 @@ static int rtl822x_config_aneg(struct phy_device *phydev) return __genphy_config_aneg(phydev, ret); } +static void rtl822xb_update_interface(struct phy_device *phydev) +{ + int val; + + if (!phydev->link) + return; + + /* Change interface according to serdes mode */ + val = phy_read_mmd(phydev, MDIO_MMD_VEND1, RTL822X_VND1_SERDES_CTRL3); + if (val < 0) + return; + + switch (val & RTL822X_VND1_SERDES_CTRL3_MODE_MASK) { + case RTL822X_VND1_SERDES_CTRL3_MODE_2500BASEX: + phydev->interface = PHY_INTERFACE_MODE_2500BASEX; + break; + case RTL822X_VND1_SERDES_CTRL3_MODE_SGMII: + phydev->interface = PHY_INTERFACE_MODE_SGMII; + break; + } +} + static int rtl822x_read_status(struct phy_device *phydev) { int ret; @@ -716,6 +805,19 @@ static int rtl822x_read_status(struct phy_device *phydev) return rtlgen_get_speed(phydev); } +static int rtl822xb_read_status(struct phy_device *phydev) +{ + int ret; + + ret = rtl822x_read_status(phydev); + if (ret < 0) + return ret; + + rtl822xb_update_interface(phydev); + + return 0; +} + static bool rtlgen_supports_2_5gbps(struct phy_device *phydev) { int val; @@ -988,7 +1090,8 @@ static struct phy_driver realtek_drvs[] = { .name = "RTL8226B_RTL8221B 2.5Gbps PHY", .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, - .read_status = rtl822x_read_status, + .config_init = rtl822xb_config_init, + .read_status = rtl822xb_read_status, .suspend = genphy_suspend, .resume = rtlgen_resume, .read_page = rtl821x_read_page, @@ -1010,7 +1113,8 @@ static struct phy_driver realtek_drvs[] = { .name = "RTL8226B-CG_RTL8221B-CG 2.5Gbps PHY", .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, - .read_status = rtl822x_read_status, + .config_init = rtl822xb_config_init, + .read_status = rtl822xb_read_status, .suspend = genphy_suspend, .resume = rtlgen_resume, .read_page = rtl821x_read_page, @@ -1020,7 +1124,8 @@ static struct phy_driver realtek_drvs[] = { .name = "RTL8221B-VB-CG 2.5Gbps PHY", .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, - .read_status = rtl822x_read_status, + .config_init = rtl822xb_config_init, + .read_status = rtl822xb_read_status, .suspend = genphy_suspend, .resume = rtlgen_resume, .read_page = rtl821x_read_page, @@ -1030,7 +1135,8 @@ static struct phy_driver realtek_drvs[] = { .name = "RTL8221B-VM-CG 2.5Gbps PHY", .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, - .read_status = rtl822x_read_status, + .config_init = rtl822xb_config_init, + .read_status = rtl822xb_read_status, .suspend = genphy_suspend, .resume = rtlgen_resume, .read_page = rtl821x_read_page, From c189dbd738243be6775bb6878366bf63e27bfd05 Mon Sep 17 00:00:00 2001 From: Eric Woudstra Date: Tue, 9 Apr 2024 09:30:12 +0200 Subject: [PATCH 17/21] net: phy: realtek: add get_rate_matching() for rtl822xb PHYs Uses vendor register to determine if SerDes is setup in rate-matching mode. Rate-matching only supported when SerDes is set to 2500base-x. Signed-off-by: Eric Woudstra Signed-off-by: David S. Miller --- drivers/net/phy/realtek.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 70cd1834a832..08d338271bd0 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -726,6 +726,27 @@ static int rtl822xb_config_init(struct phy_device *phydev) return phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x6f11, 0x8020); } +static int rtl822xb_get_rate_matching(struct phy_device *phydev, + phy_interface_t iface) +{ + int val; + + /* Only rate matching at 2500base-x */ + if (iface != PHY_INTERFACE_MODE_2500BASEX) + return RATE_MATCH_NONE; + + val = phy_read_mmd(phydev, MDIO_MMD_VEND1, RTL822X_VND1_SERDES_OPTION); + if (val < 0) + return val; + + if ((val & RTL822X_VND1_SERDES_OPTION_MODE_MASK) == + RTL822X_VND1_SERDES_OPTION_MODE_2500BASEX) + return RATE_MATCH_PAUSE; + + /* RTL822X_VND1_SERDES_OPTION_MODE_2500BASEX_SGMII */ + return RATE_MATCH_NONE; +} + static int rtl822x_get_features(struct phy_device *phydev) { int val; @@ -1091,6 +1112,7 @@ static struct phy_driver realtek_drvs[] = { .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, .config_init = rtl822xb_config_init, + .get_rate_matching = rtl822xb_get_rate_matching, .read_status = rtl822xb_read_status, .suspend = genphy_suspend, .resume = rtlgen_resume, @@ -1114,6 +1136,7 @@ static struct phy_driver realtek_drvs[] = { .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, .config_init = rtl822xb_config_init, + .get_rate_matching = rtl822xb_get_rate_matching, .read_status = rtl822xb_read_status, .suspend = genphy_suspend, .resume = rtlgen_resume, @@ -1125,6 +1148,7 @@ static struct phy_driver realtek_drvs[] = { .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, .config_init = rtl822xb_config_init, + .get_rate_matching = rtl822xb_get_rate_matching, .read_status = rtl822xb_read_status, .suspend = genphy_suspend, .resume = rtlgen_resume, @@ -1136,6 +1160,7 @@ static struct phy_driver realtek_drvs[] = { .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, .config_init = rtl822xb_config_init, + .get_rate_matching = rtl822xb_get_rate_matching, .read_status = rtl822xb_read_status, .suspend = genphy_suspend, .resume = rtlgen_resume, From ad5ce743a6b0329f642d80be50ef7b534e908fba Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Tue, 9 Apr 2024 09:30:13 +0200 Subject: [PATCH 18/21] net: phy: realtek: Add driver instances for rtl8221b via Clause 45 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Collected from several commits in [PATCH net-next] "Realtek RTL822x PHY rework to c45 and SerDes interface switching" The instances are used by Clause 45 only accessible PHY's on several sfp modules, which are using RollBall protocol. Signed-off-by: Marek Behún [ Added matching functions to differentiate C45 instances ] Signed-off-by: Eric Woudstra Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/realtek.c | 135 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 131 insertions(+), 4 deletions(-) diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 08d338271bd0..f4a6f073a1f7 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -64,6 +64,13 @@ #define RTL822X_VND1_SERDES_CTRL3_MODE_SGMII 0x02 #define RTL822X_VND1_SERDES_CTRL3_MODE_2500BASEX 0x16 +/* RTL822X_VND2_XXXXX registers are only accessible when phydev->is_c45 + * is set, they cannot be accessed by C45-over-C22. + */ +#define RTL822X_VND2_GBCR 0xa412 + +#define RTL822X_VND2_GANLPAR 0xa414 + #define RTL8366RB_POWER_SAVE 0x15 #define RTL8366RB_POWER_SAVE_ON BIT(12) @@ -74,6 +81,9 @@ #define RTL_GENERIC_PHYID 0x001cc800 #define RTL_8211FVD_PHYID 0x001cc878 +#define RTL_8221B_VB_CG 0x001cc849 +#define RTL_8221B_VN_CG 0x001cc84a +#define RTL_8251B 0x001cc862 MODULE_DESCRIPTION("Realtek PHY driver"); MODULE_AUTHOR("Johnson Leung"); @@ -839,6 +849,67 @@ static int rtl822xb_read_status(struct phy_device *phydev) return 0; } +static int rtl822x_c45_config_aneg(struct phy_device *phydev) +{ + bool changed = false; + int ret, val; + + if (phydev->autoneg == AUTONEG_DISABLE) + return genphy_c45_pma_setup_forced(phydev); + + ret = genphy_c45_an_config_aneg(phydev); + if (ret < 0) + return ret; + if (ret > 0) + changed = true; + + val = linkmode_adv_to_mii_ctrl1000_t(phydev->advertising); + + /* Vendor register as C45 has no standardized support for 1000BaseT */ + ret = phy_modify_mmd_changed(phydev, MDIO_MMD_VEND2, RTL822X_VND2_GBCR, + ADVERTISE_1000FULL, val); + if (ret < 0) + return ret; + if (ret > 0) + changed = true; + + return genphy_c45_check_and_restart_aneg(phydev, changed); +} + +static int rtl822x_c45_read_status(struct phy_device *phydev) +{ + int ret, val; + + ret = genphy_c45_read_status(phydev); + if (ret < 0) + return ret; + + /* Vendor register as C45 has no standardized support for 1000BaseT */ + if (phydev->autoneg == AUTONEG_ENABLE) { + val = phy_read_mmd(phydev, MDIO_MMD_VEND2, + RTL822X_VND2_GANLPAR); + if (val < 0) + return val; + + mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, val); + } + + return 0; +} + +static int rtl822xb_c45_read_status(struct phy_device *phydev) +{ + int ret; + + ret = rtl822x_c45_read_status(phydev); + if (ret < 0) + return ret; + + rtl822xb_update_interface(phydev); + + return 0; +} + static bool rtlgen_supports_2_5gbps(struct phy_device *phydev) { int val; @@ -862,6 +933,35 @@ static int rtl8226_match_phy_device(struct phy_device *phydev) rtlgen_supports_2_5gbps(phydev); } +static int rtlgen_is_c45_match(struct phy_device *phydev, unsigned int id, + bool is_c45) +{ + if (phydev->is_c45) + return is_c45 && (id == phydev->c45_ids.device_ids[1]); + else + return !is_c45 && (id == phydev->phy_id); +} + +static int rtl8221b_vb_cg_c22_match_phy_device(struct phy_device *phydev) +{ + return rtlgen_is_c45_match(phydev, RTL_8221B_VB_CG, false); +} + +static int rtl8221b_vb_cg_c45_match_phy_device(struct phy_device *phydev) +{ + return rtlgen_is_c45_match(phydev, RTL_8221B_VB_CG, true); +} + +static int rtl8221b_vn_cg_c22_match_phy_device(struct phy_device *phydev) +{ + return rtlgen_is_c45_match(phydev, RTL_8221B_VN_CG, false); +} + +static int rtl8221b_vn_cg_c45_match_phy_device(struct phy_device *phydev) +{ + return rtlgen_is_c45_match(phydev, RTL_8221B_VN_CG, true); +} + static int rtlgen_resume(struct phy_device *phydev) { int ret = genphy_resume(phydev); @@ -872,6 +972,15 @@ static int rtlgen_resume(struct phy_device *phydev) return ret; } +static int rtlgen_c45_resume(struct phy_device *phydev) +{ + int ret = genphy_c45_pma_resume(phydev); + + msleep(20); + + return ret; +} + static int rtl9000a_config_init(struct phy_device *phydev) { phydev->autoneg = AUTONEG_DISABLE; @@ -1143,8 +1252,8 @@ static struct phy_driver realtek_drvs[] = { .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, }, { - PHY_ID_MATCH_EXACT(0x001cc849), - .name = "RTL8221B-VB-CG 2.5Gbps PHY", + .match_phy_device = rtl8221b_vb_cg_c22_match_phy_device, + .name = "RTL8221B-VB-CG 2.5Gbps PHY (C22)", .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, .config_init = rtl822xb_config_init, @@ -1155,8 +1264,17 @@ static struct phy_driver realtek_drvs[] = { .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, }, { - PHY_ID_MATCH_EXACT(0x001cc84a), - .name = "RTL8221B-VM-CG 2.5Gbps PHY", + .match_phy_device = rtl8221b_vb_cg_c45_match_phy_device, + .name = "RTL8221B-VB-CG 2.5Gbps PHY (C45)", + .config_init = rtl822xb_config_init, + .get_rate_matching = rtl822xb_get_rate_matching, + .config_aneg = rtl822x_c45_config_aneg, + .read_status = rtl822xb_c45_read_status, + .suspend = genphy_c45_pma_suspend, + .resume = rtlgen_c45_resume, + }, { + .match_phy_device = rtl8221b_vn_cg_c22_match_phy_device, + .name = "RTL8221B-VM-CG 2.5Gbps PHY (C22)", .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, .config_init = rtl822xb_config_init, @@ -1166,6 +1284,15 @@ static struct phy_driver realtek_drvs[] = { .resume = rtlgen_resume, .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, + }, { + .match_phy_device = rtl8221b_vn_cg_c45_match_phy_device, + .name = "RTL8221B-VN-CG 2.5Gbps PHY (C45)", + .config_init = rtl822xb_config_init, + .get_rate_matching = rtl822xb_get_rate_matching, + .config_aneg = rtl822x_c45_config_aneg, + .read_status = rtl822xb_c45_read_status, + .suspend = genphy_c45_pma_suspend, + .resume = rtlgen_c45_resume, }, { PHY_ID_MATCH_EXACT(0x001cc862), .name = "RTL8251B 5Gbps PHY", From 2e4ea707c7e04eb83e58c43e0e744bbdf6b23ff2 Mon Sep 17 00:00:00 2001 From: Eric Woudstra Date: Tue, 9 Apr 2024 09:30:14 +0200 Subject: [PATCH 19/21] net: phy: realtek: Change rtlgen_get_speed() to rtlgen_decode_speed() The value of the register to determine the speed, is retrieved differently when using Clause 45 only. To use the rtlgen_get_speed() function in this case, pass the value of the register as argument to rtlgen_get_speed(). The function would then always return 0, so change it to void. A better name for this function now is rtlgen_decode_speed(). Replace a call to genphy_read_status() followed by rtlgen_get_speed() with a call to rtlgen_read_status() in rtl822x_read_status(). Add reading speed to rtl822x_c45_read_status(). Signed-off-by: Eric Woudstra Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/realtek.c | 46 +++++++++++++++++++++------------------ 1 file changed, 25 insertions(+), 21 deletions(-) diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index f4a6f073a1f7..901c6f7b04c2 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -71,6 +71,8 @@ #define RTL822X_VND2_GANLPAR 0xa414 +#define RTL822X_VND2_PHYSR 0xa434 + #define RTL8366RB_POWER_SAVE 0x15 #define RTL8366RB_POWER_SAVE_ON BIT(12) @@ -551,17 +553,8 @@ static int rtl8366rb_config_init(struct phy_device *phydev) } /* get actual speed to cover the downshift case */ -static int rtlgen_get_speed(struct phy_device *phydev) +static void rtlgen_decode_speed(struct phy_device *phydev, int val) { - int val; - - if (!phydev->link) - return 0; - - val = phy_read_paged(phydev, 0xa43, 0x12); - if (val < 0) - return val; - switch (val & RTLGEN_SPEED_MASK) { case 0x0000: phydev->speed = SPEED_10; @@ -584,19 +577,26 @@ static int rtlgen_get_speed(struct phy_device *phydev) default: break; } - - return 0; } static int rtlgen_read_status(struct phy_device *phydev) { - int ret; + int ret, val; ret = genphy_read_status(phydev); if (ret < 0) return ret; - return rtlgen_get_speed(phydev); + if (!phydev->link) + return 0; + + val = phy_read_paged(phydev, 0xa43, 0x12); + if (val < 0) + return val; + + rtlgen_decode_speed(phydev, val); + + return 0; } static int rtlgen_read_mmd(struct phy_device *phydev, int devnum, u16 regnum) @@ -817,8 +817,6 @@ static void rtl822xb_update_interface(struct phy_device *phydev) static int rtl822x_read_status(struct phy_device *phydev) { - int ret; - if (phydev->autoneg == AUTONEG_ENABLE) { int lpadv = phy_read_paged(phydev, 0xa5d, 0x13); @@ -829,11 +827,7 @@ static int rtl822x_read_status(struct phy_device *phydev) lpadv); } - ret = genphy_read_status(phydev); - if (ret < 0) - return ret; - - return rtlgen_get_speed(phydev); + return rtlgen_read_status(phydev); } static int rtl822xb_read_status(struct phy_device *phydev) @@ -894,6 +888,16 @@ static int rtl822x_c45_read_status(struct phy_device *phydev) mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, val); } + if (!phydev->link) + return 0; + + /* Read actual speed from vendor register. */ + val = phy_read_mmd(phydev, MDIO_MMD_VEND2, RTL822X_VND2_PHYSR); + if (val < 0) + return val; + + rtlgen_decode_speed(phydev, val); + return 0; } From 2d9ce64862705b33397d54dafecc5f51d8b1bb06 Mon Sep 17 00:00:00 2001 From: Eric Woudstra Date: Tue, 9 Apr 2024 09:30:15 +0200 Subject: [PATCH 20/21] net: phy: realtek: add rtl822x_c45_get_features() to set supported port Sets ETHTOOL_LINK_MODE_TP_BIT in phydev->supported. Signed-off-by: Eric Woudstra Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/realtek.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 901c6f7b04c2..7ab41f95dae5 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -843,6 +843,14 @@ static int rtl822xb_read_status(struct phy_device *phydev) return 0; } +static int rtl822x_c45_get_features(struct phy_device *phydev) +{ + linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, + phydev->supported); + + return genphy_c45_pma_read_abilities(phydev); +} + static int rtl822x_c45_config_aneg(struct phy_device *phydev) { bool changed = false; @@ -1272,6 +1280,7 @@ static struct phy_driver realtek_drvs[] = { .name = "RTL8221B-VB-CG 2.5Gbps PHY (C45)", .config_init = rtl822xb_config_init, .get_rate_matching = rtl822xb_get_rate_matching, + .get_features = rtl822x_c45_get_features, .config_aneg = rtl822x_c45_config_aneg, .read_status = rtl822xb_c45_read_status, .suspend = genphy_c45_pma_suspend, @@ -1293,6 +1302,7 @@ static struct phy_driver realtek_drvs[] = { .name = "RTL8221B-VN-CG 2.5Gbps PHY (C45)", .config_init = rtl822xb_config_init, .get_rate_matching = rtl822xb_get_rate_matching, + .get_features = rtl822x_c45_get_features, .config_aneg = rtl822x_c45_config_aneg, .read_status = rtl822xb_c45_read_status, .suspend = genphy_c45_pma_suspend, From 1c77c721916ae108c2c5865986735bfe92000908 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Tue, 9 Apr 2024 09:30:16 +0200 Subject: [PATCH 21/21] net: sfp: add quirk for another multigig RollBall transceiver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add quirk for another RollBall copper transceiver: Turris RTSFP-2.5G, containing 2.5g capable RTL8221B PHY. Signed-off-by: Marek Behún Signed-off-by: Eric Woudstra Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/sfp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index f75c9eb3958e..6e7639fc64dd 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -506,6 +506,7 @@ static const struct sfp_quirk sfp_quirks[] = { SFP_QUIRK_M("OEM", "SFP-2.5G-T", sfp_quirk_oem_2_5g), SFP_QUIRK_F("OEM", "RTSFP-10", sfp_fixup_rollball_cc), SFP_QUIRK_F("OEM", "RTSFP-10G", sfp_fixup_rollball_cc), + SFP_QUIRK_F("Turris", "RTSFP-2.5G", sfp_fixup_rollball), SFP_QUIRK_F("Turris", "RTSFP-10", sfp_fixup_rollball), SFP_QUIRK_F("Turris", "RTSFP-10G", sfp_fixup_rollball), };