From 2e07a521e1e424787af3bfc59615de4220856c35 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:28 +0100 Subject: skbuff: add SKBFL_DONT_ORPHAN flag We don't want to list every single ubuf_info callback in skb_orphan_frags(), add a flag controlling the behaviour. Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d3d10556f0fa..8e12b3b9ad6c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -686,10 +686,13 @@ enum { * charged to the kernel memory. */ SKBFL_PURE_ZEROCOPY = BIT(2), + + SKBFL_DONT_ORPHAN = BIT(3), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) -#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY) +#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ + SKBFL_DONT_ORPHAN) /* * The callback notifies userspace to release buffers when skb DMA is done in @@ -3182,8 +3185,7 @@ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; - if (!skb_zcopy_is_nouarg(skb) && - skb_uarg(skb)->callback == msg_zerocopy_callback) + if (skb_shinfo(skb)->flags & SKBFL_DONT_ORPHAN) return 0; return skb_copy_ubufs(skb, gfp_mask); } -- cgit From 7c701d92b2b5e5175dbfec875816474b802b0c45 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:29 +0100 Subject: skbuff: carry external ubuf_info in msghdr Make possible for network in-kernel callers like io_uring to pass in a custom ubuf_info by setting it in a new field of struct msghdr. Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 17311ad9f9af..7bac9fc1cee0 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -69,6 +69,7 @@ struct msghdr { unsigned int msg_flags; /* flags on received message */ __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ + struct ubuf_info *msg_ubuf; }; struct user_msghdr { -- cgit From ebe73a284f4de8c5d401adeccd9b8fe3183b6e95 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 12 Jul 2022 21:52:30 +0100 Subject: net: Allow custom iter handler in msghdr Add support for custom iov_iter handling to msghdr. The idea is that in-kernel subsystems want control over how an SG is split. Signed-off-by: David Ahern [pavel: move callback into msghdr] Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 7 ++++--- include/linux/socket.h | 4 ++++ 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8e12b3b9ad6c..a8a2dd4cfdfd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1776,13 +1776,14 @@ void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, bool success); -int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, - struct iov_iter *from, size_t length); +int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb, struct iov_iter *from, + size_t length); static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { - return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len); + return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len); } int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, diff --git a/include/linux/socket.h b/include/linux/socket.h index 7bac9fc1cee0..3c11ef18a9cf 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -14,6 +14,8 @@ struct file; struct pid; struct cred; struct socket; +struct sock; +struct sk_buff; #define __sockaddr_check_size(size) \ BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage))) @@ -70,6 +72,8 @@ struct msghdr { __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ struct ubuf_info *msg_ubuf; + int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb, + struct iov_iter *from, size_t length); }; struct user_msghdr { -- cgit From 753f1ca4e1e50248a1b760c9774d6d6b354562cc Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:31 +0100 Subject: net: introduce managed frags infrastructure Some users like io_uring can do page pinning more efficiently, so we want a way to delegate referencing to other subsystems. For that add a new flag called SKBFL_MANAGED_FRAG_REFS. When set, skb doesn't hold page references and upper layers are responsivle to managing page lifetime. It's allowed to convert skbs from managed to normal by calling skb_zcopy_downgrade_managed(). The function will take all needed page references and clear the flag. It's needed, for instance, to avoid mixing managed modes. Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a8a2dd4cfdfd..07004593d7ca 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -688,11 +688,16 @@ enum { SKBFL_PURE_ZEROCOPY = BIT(2), SKBFL_DONT_ORPHAN = BIT(3), + + /* page references are managed by the ubuf_info, so it's safe to + * use frags only up until ubuf_info is released + */ + SKBFL_MANAGED_FRAG_REFS = BIT(4), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ - SKBFL_DONT_ORPHAN) + SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) /* * The callback notifies userspace to release buffers when skb DMA is done in @@ -1810,6 +1815,11 @@ static inline bool skb_zcopy_pure(const struct sk_buff *skb) return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; } +static inline bool skb_zcopy_managed(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->flags & SKBFL_MANAGED_FRAG_REFS; +} + static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, const struct sk_buff *skb2) { @@ -1884,6 +1894,14 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) } } +void __skb_zcopy_downgrade_managed(struct sk_buff *skb); + +static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) +{ + if (unlikely(skb_zcopy_managed(skb))) + __skb_zcopy_downgrade_managed(skb); +} + static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; @@ -3499,7 +3517,10 @@ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) */ static inline void skb_frag_unref(struct sk_buff *skb, int f) { - __skb_frag_unref(&skb_shinfo(skb)->frags[f], skb->pp_recycle); + struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (!skb_zcopy_managed(skb)) + __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); } /** -- cgit From 84ce071e38a6e25ea3ea91188e5482ac1f17b3af Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:32 +0100 Subject: net: introduce __skb_fill_page_desc_noacc Managed pages contain pinned userspace pages and controlled by upper layers, there is no need in tracking skb->pfmemalloc for them. Introduce a helper for filling frags but ignoring page tracking, it'll be needed later. Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 07004593d7ca..1111adefd906 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2550,6 +2550,22 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb) return skb_headlen(skb) + __skb_pagelen(skb); } +static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, + int i, struct page *page, + int off, int size) +{ + skb_frag_t *frag = &shinfo->frags[i]; + + /* + * Propagate page pfmemalloc to the skb if we can. The problem is + * that not all callers have unique ownership of the page but rely + * on page_is_pfmemalloc doing the right thing(tm). + */ + frag->bv_page = page; + frag->bv_offset = off; + skb_frag_size_set(frag, size); +} + /** * __skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised @@ -2566,17 +2582,7 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb) static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - - /* - * Propagate page pfmemalloc to the skb if we can. The problem is - * that not all callers have unique ownership of the page but rely - * on page_is_pfmemalloc doing the right thing(tm). - */ - frag->bv_page = page; - frag->bv_offset = off; - skb_frag_size_set(frag, size); - + __skb_fill_page_desc_noacc(skb_shinfo(skb), i, page, off, size); page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; -- cgit From e70cb60893ca64b7df06864aa16c1cf6d6c671db Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:37 +0100 Subject: io_uring: export io_put_task() Make io_put_task() available to non-core parts of io_uring, we'll need it for notification infrastructure. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/3686807d4c03b72e389947b0e8692d4d44334ef0.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index d54b8b7e0746..368c34d14b13 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -4,6 +4,7 @@ #include #include #include +#include #include struct io_wq_work_node { @@ -43,6 +44,30 @@ struct io_hash_table { unsigned hash_bits; }; +/* + * Arbitrary limit, can be raised if need be + */ +#define IO_RINGFD_REG_MAX 16 + +struct io_uring_task { + /* submission side */ + int cached_refs; + const struct io_ring_ctx *last; + struct io_wq *io_wq; + struct file *registered_rings[IO_RINGFD_REG_MAX]; + + struct xarray xa; + struct wait_queue_head wait; + atomic_t in_idle; + atomic_t inflight_tracked; + struct percpu_counter inflight; + + struct { /* task_work */ + struct llist_head task_list; + struct callback_head task_work; + } ____cacheline_aligned_in_smp; +}; + struct io_uring { u32 head ____cacheline_aligned_in_smp; u32 tail ____cacheline_aligned_in_smp; -- cgit From eb42cebb2cf24c48f60c32856a4bba93d42659c8 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:38 +0100 Subject: io_uring: add zc notification infrastructure Add internal part of send zerocopy notifications. There are two main structures, the first one is struct io_notif, which carries inside struct ubuf_info and maps 1:1 to it. io_uring will be binding a number of zerocopy send requests to it and ask to complete (aka flush) it. When flushed and all attached requests and skbs complete, it'll generate one and only one CQE. There are intended to be passed into the network layer as struct msghdr::msg_ubuf. The second concept is notification slots. The userspace will be able to register an array of slots and subsequently addressing them by the index in the array. Slots are independent of each other. Each slot can have only one notifier at a time (called active notifier) but many notifiers during the lifetime. When active, a notifier not going to post any completion but the userspace can attach requests to it by specifying the corresponding slot while issueing send zc requests. Eventually, the userspace will want to "flush" the notifier losing any way to attach new requests to it, however it can use the next atomatically added notifier of this slot or of any other slot. When the network layer is done with all enqueued skbs attached to a notifier and doesn't need the specified in them user data, the flushed notifier will post a CQE. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/3ecf54c31a85762bf679b0a432c9f43ecf7e61cc.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 368c34d14b13..f7fab3758cb9 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -34,6 +34,9 @@ struct io_file_table { unsigned int alloc_hint; }; +struct io_notif; +struct io_notif_slot; + struct io_hash_bucket { spinlock_t lock; struct hlist_head list; @@ -237,6 +240,8 @@ struct io_ring_ctx { unsigned nr_user_files; unsigned nr_user_bufs; struct io_mapped_ubuf **user_bufs; + struct io_notif_slot *notif_slots; + unsigned nr_notif_slots; struct io_submit_state submit_state; -- cgit From eb4a299b2f95437af6183946c2a2e850621cefdb Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:39 +0100 Subject: io_uring: cache struct io_notif kmalloc'ing struct io_notif is too expensive when done frequently, cache them as many other resources in io_uring. Keep two list, the first one is from where we're getting notifiers, it's protected by ->uring_lock. The second is protected by ->completion_lock, to which we queue released notifiers. Then we splice one list into another when needed. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/9dec18f7fcbab9f4bd40b96e5ae158b119945230.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index f7fab3758cb9..144493cbadb5 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -249,6 +249,9 @@ struct io_ring_ctx { struct xarray io_bl_xa; struct list_head io_buffers_cache; + /* struct io_notif cache, protected by uring_lock */ + struct list_head notif_list; + struct io_hash_table cancel_table_locked; struct list_head cq_overflow_list; struct io_alloc_cache apoll_cache; @@ -259,6 +262,10 @@ struct io_ring_ctx { struct io_wq_work_list locked_free_list; unsigned int locked_free_nr; + /* struct io_notif cache protected by completion_lock */ + struct list_head notif_list_locked; + unsigned int notif_locked_nr; + const struct cred *sq_creds; /* cred used for __io_sq_thread() */ struct io_sq_data *sq_data; /* if using sq thread polling */ -- cgit From 14b146b688ad9593f5eee93d51a34d09a47e50b5 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 27 Jul 2022 10:30:41 +0100 Subject: io_uring: notification completion optimisation We want to use all optimisations that we have for io_uring requests like completion batching, memory caching and more but for zc notifications. Fortunately, notification perfectly fit the request model so we can overlay them onto struct io_kiocb and use all the infratructure. Most of the fields of struct io_notif natively fits into io_kiocb, so we replace struct io_notif with struct io_kiocb carrying struct io_notif_data in the cmd cache line. Then we adapt io_alloc_notif() to use io_alloc_req()/io_alloc_req_refill(), and kill leftovers of hand coded caching. __io_notif_complete_tw() is converted to use io_uring's tw infra. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/9e010125175e80baf51f0ca63bdc7cc6a4a9fa56.1658913593.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 144493cbadb5..f7fab3758cb9 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -249,9 +249,6 @@ struct io_ring_ctx { struct xarray io_bl_xa; struct list_head io_buffers_cache; - /* struct io_notif cache, protected by uring_lock */ - struct list_head notif_list; - struct io_hash_table cancel_table_locked; struct list_head cq_overflow_list; struct io_alloc_cache apoll_cache; @@ -262,10 +259,6 @@ struct io_ring_ctx { struct io_wq_work_list locked_free_list; unsigned int locked_free_nr; - /* struct io_notif cache protected by completion_lock */ - struct list_head notif_list_locked; - unsigned int notif_locked_nr; - const struct cred *sq_creds; /* cred used for __io_sq_thread() */ struct io_sq_data *sq_data; /* if using sq thread polling */ -- cgit