From: Jakub Kicinski kuba@kernel.org

The page providers which try to reuse the same pages will need to hold onto the ref, even if page gets released from the pool - as in releasing the page from the pp just transfers the "ownership" reference from pp to the provider, and provider will wait for other references to be gone before feeding this page back into the pool.

Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Mina Almasry almasrymina@google.com

---

- This is implemented by Jakub in his RFC: https://lore.kernel.org/netdev/f8270765-a27b-6ccf-33ea-cda097168d79@redhat.c...

I take no credit for the idea or implementation; I only added minor edits to make this workable with device memory TCP, and removed some hacky test code. This is a critical dependency of device memory TCP and thus I'm pulling it into this series to make it revewable and mergeable.

- There is a pending discussion about the acceptance of the page_pool memory provider hooks:

https://lore.kernel.org/netdev/20240403002053.2376017-3-almasrymina@google.c...

I'm unsure if the discussion has been resolved yet. There seems to be agreement that the io_uring use case without dmabuf is good but unsure about the ops. The conversation will likely continue to this iteration.

Cc: Christoph Hellwig hch@infradead.org

RFC v3 -> v1 - Removed unusued mem_provider. (Yunsheng). - Replaced memory_provider & mp_priv with netdev_rx_queue (Jakub).

--- include/net/page_pool/types.h | 12 ++++++++++ net/core/page_pool.c | 43 +++++++++++++++++++++++++++++++---- 2 files changed, 50 insertions(+), 5 deletions(-)

diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index a6ebed0022160..2bf15ca6bfd48 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -52,6 +52,7 @@ struct pp_alloc_cache { * @dev: device, for DMA pre-mapping purposes * @netdev: netdev this pool will serve (leave as NULL if none or multiple) * @napi: NAPI which is the sole consumer of pages, otherwise NULL + * @queue: struct netdev_rx_queue this page_pool is being created for. * @dma_dir: DMA mapping direction * @max_len: max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV @@ -64,6 +65,7 @@ struct page_pool_params { int nid; struct device *dev; struct napi_struct *napi; + struct netdev_rx_queue *queue; enum dma_data_direction dma_dir; unsigned int max_len; unsigned int offset; @@ -126,6 +128,13 @@ struct page_pool_stats { }; #endif

+struct memory_provider_ops { + int (*init)(struct page_pool *pool); + void (*destroy)(struct page_pool *pool); + struct page *(*alloc_pages)(struct page_pool *pool, gfp_t gfp); + bool (*release_page)(struct page_pool *pool, struct page *page); +}; + struct page_pool { struct page_pool_params_fast p;

@@ -176,6 +185,9 @@ struct page_pool { */ struct ptr_ring ring;

+ void *mp_priv; + const struct memory_provider_ops *mp_ops; + #ifdef CONFIG_PAGE_POOL_STATS /* recycle stats are per-cpu to avoid locking */ struct page_pool_recycle_stats __percpu *recycle_stats; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 8bcc7014a61a0..ae403397df09d 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -26,6 +26,8 @@

#include "page_pool_priv.h"

+static DEFINE_STATIC_KEY_FALSE(page_pool_mem_providers); + #define DEFER_TIME (msecs_to_jiffies(1000)) #define DEFER_WARN_INTERVAL (60 * HZ)

@@ -178,6 +180,7 @@ static int page_pool_init(struct page_pool *pool, int cpuid) { unsigned int ring_qsize = 1024; /* Default */ + int err;

memcpy(&pool->p, &params->fast, sizeof(pool->p)); memcpy(&pool->slow, &params->slow, sizeof(pool->slow)); @@ -249,10 +252,25 @@ static int page_pool_init(struct page_pool *pool, /* Driver calling page_pool_create() also call page_pool_destroy() */ refcount_set(&pool->user_cnt, 1);

+ if (pool->mp_ops) { + err = pool->mp_ops->init(pool); + if (err) { + pr_warn("%s() mem-provider init failed %d\n", __func__, + err); + goto free_ptr_ring; + } + + static_branch_inc(&page_pool_mem_providers); + } + if (pool->p.flags & PP_FLAG_DMA_MAP) get_device(pool->p.dev);

return 0; + +free_ptr_ring: + ptr_ring_cleanup(&pool->ring, NULL); + return err; }

static void page_pool_uninit(struct page_pool *pool) @@ -547,7 +565,10 @@ struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp) return page;

/* Slow-path: cache empty, do real allocation */ - page = __page_pool_alloc_pages_slow(pool, gfp); + if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops) + page = pool->mp_ops->alloc_pages(pool, gfp); + else + page = __page_pool_alloc_pages_slow(pool, gfp); return page; } EXPORT_SYMBOL(page_pool_alloc_pages); @@ -605,10 +626,13 @@ void __page_pool_release_page_dma(struct page_pool *pool, struct page *page) void page_pool_return_page(struct page_pool *pool, struct page *page) { int count; + bool put;

- __page_pool_release_page_dma(pool, page); - - page_pool_clear_pp_info(page); + put = true; + if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops) + put = pool->mp_ops->release_page(pool, page); + else + __page_pool_release_page_dma(pool, page);

/* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. @@ -616,7 +640,10 @@ void page_pool_return_page(struct page_pool *pool, struct page *page) count = atomic_inc_return_relaxed(&pool->pages_state_release_cnt); trace_page_pool_state_release(pool, page, count);

- put_page(page); + if (put) { + page_pool_clear_pp_info(page); + put_page(page); + } /* An optimization would be to call __free_pages(page, pool->p.order) * knowing page is not part of page-cache (thus avoiding a * __page_cache_release() call). @@ -919,6 +946,12 @@ static void __page_pool_destroy(struct page_pool *pool)

page_pool_unlist(pool); page_pool_uninit(pool); + + if (pool->mp_ops) { + pool->mp_ops->destroy(pool); + static_branch_dec(&page_pool_mem_providers); + } + kfree(pool); }

Add a netdev_dmabuf_binding struct which represents the dma-buf-to-netdevice binding. The netlink API will bind the dma-buf to rx queues on the netdevice. On the binding, the dma_buf_attach & dma_buf_map_attachment will occur. The entries in the sg_table from mapping will be inserted into a genpool to make it ready for allocation.

The chunks in the genpool are owned by a dmabuf_chunk_owner struct which holds the dma-buf offset of the base of the chunk and the dma_addr of the chunk. Both are needed to use allocations that come from this chunk.

We create a new type that represents an allocation from the genpool: net_iov. We setup the net_iov allocation size in the genpool to PAGE_SIZE for simplicity: to match the PAGE_SIZE normally allocated by the page pool and given to the drivers.

The user can unbind the dmabuf from the netdevice by closing the netlink socket that established the binding. We do this so that the binding is automatically unbound even if the userspace process crashes.

The binding and unbinding leaves an indicator in struct netdev_rx_queue that the given queue is bound, but the binding doesn't take effect until the driver actually reconfigures its queues, and re-initializes its page pool.

The netdev_dmabuf_binding struct is refcounted, and releases its resources only when all the refs are released.

Signed-off-by: Willem de Bruijn willemb@google.com Signed-off-by: Kaiyuan Zhang kaiyuanz@google.com Signed-off-by: Mina Almasry almasrymina@google.com

---

v9: https://lore.kernel.org/all/20240403002053.2376017-5-almasrymina@google.com/ - Removed net_devmem_restart_rx_queues and put it in its own patch (David).

v8: - move dmabuf_devmem_ops usage to later patch to avoid patch-by-patch build error.

v7: - Use IS_ERR() instead of IS_ERR_OR_NULL() for the dma_buf_get() return value. - Changes netdev_* naming in devmem.c to net_devmem_* (Yunsheng). - DMA_BIDIRECTIONAL -> DMA_FROM_DEVICE (Yunsheng). - Added a comment around recovering of the old rx queue in net_devmem_restart_rx_queue(), and added freeing of old_mem if the restart of the old queue fails. (Yunsheng). - Use kernel-family sock-priv (Jakub). - Put pp_memory_provider_params in netdev_rx_queue instead of the dma-buf specific binding (Pavel & David). - Move queue management ops to queue_mgmt_ops instead of netdev_ops (Jakub). - Remove excess whitespaces (Jakub). - Use genlmsg_iput (Jakub).

v6: - Validate rx queue index - Refactor new functions into devmem.c (Pavel)

v5: - Renamed page_pool_iov to net_iov, and moved that support to devmem.h or netmem.h.

v1: - Introduce devmem.h instead of bloating netdevice.h (Jakub) - ENOTSUPP -> EOPNOTSUPP (checkpatch.pl I think) - Remove unneeded rcu protection for binding->list (rtnl protected) - Removed extraneous err_binding_put: label. - Removed dma_addr += len (Paolo). - Don't override err on netdev_bind_dmabuf_to_queue failure. - Rename devmem -> dmabuf (David). - Add id to dmabuf binding (David/Stan). - Fix missing xa_destroy bound_rq_list. - Use queue api to reset bound RX queues (Jakub). - Update netlink API for rx-queue type (tx/re) (Jakub).

RFC v3: - Support multi rx-queue binding

--- Documentation/netlink/specs/netdev.yaml | 4 + include/net/devmem.h | 111 +++++++++++ include/net/netdev_rx_queue.h | 2 + include/net/netmem.h | 10 + include/net/page_pool/types.h | 5 + net/core/Makefile | 2 +- net/core/dev.c | 3 + net/core/devmem.c | 254 ++++++++++++++++++++++++ net/core/netdev-genl-gen.c | 4 + net/core/netdev-genl-gen.h | 4 + net/core/netdev-genl.c | 105 +++++++++- 11 files changed, 501 insertions(+), 3 deletions(-) create mode 100644 include/net/devmem.h create mode 100644 net/core/devmem.c

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 0a4e57b718916..38f90225d1e9b 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -655,6 +655,10 @@ operations: - tx-packets - tx-bytes

+kernel-family: + headers: [ "linux/list.h"] + sock-priv: struct list_head + mcast-groups: list: - diff --git a/include/net/devmem.h b/include/net/devmem.h new file mode 100644 index 0000000000000..fa03bdabdffd9 --- /dev/null +++ b/include/net/devmem.h @@ -0,0 +1,111 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Device memory TCP support + * + * Authors: Mina Almasry almasrymina@google.com + * Willem de Bruijn willemb@google.com + * Kaiyuan Zhang kaiyuanz@google.com + * + */ +#ifndef _NET_DEVMEM_H +#define _NET_DEVMEM_H + +struct net_devmem_dmabuf_binding { + struct dma_buf *dmabuf; + struct dma_buf_attachment *attachment; + struct sg_table *sgt; + struct net_device *dev; + struct gen_pool *chunk_pool; + + /* The user holds a ref (via the netlink API) for as long as they want + * the binding to remain alive. Each page pool using this binding holds + * a ref to keep the binding alive. Each allocated net_iov holds a + * ref. + * + * The binding undos itself and unmaps the underlying dmabuf once all + * those refs are dropped and the binding is no longer desired or in + * use. + */ + refcount_t ref; + + /* The list of bindings currently active. Used for netlink to notify us + * of the user dropping the bind. + */ + struct list_head list; + + /* rxq's this binding is active on. */ + struct xarray bound_rxq_list; + + /* ID of this binding. Globally unique to all bindings currently + * active. + */ + u32 id; +}; + +/* Owner of the dma-buf chunks inserted into the gen pool. Each scatterlist + * entry from the dmabuf is inserted into the genpool as a chunk, and needs + * this owner struct to keep track of some metadata necessary to create + * allocations from this chunk. + */ +struct dmabuf_genpool_chunk_owner { + /* Offset into the dma-buf where this chunk starts. */ + unsigned long base_virtual; + + /* dma_addr of the start of the chunk. */ + dma_addr_t base_dma_addr; + + /* Array of net_iovs for this chunk. */ + struct net_iov *niovs; + size_t num_niovs; + + struct net_devmem_dmabuf_binding *binding; +}; + +#ifdef CONFIG_DMA_SHARED_BUFFER +void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding); +int net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, + struct net_devmem_dmabuf_binding **out); +void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding); +int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct net_devmem_dmabuf_binding *binding); +#else +static inline void +__net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) +{ +} + +static inline int net_devmem_bind_dmabuf(struct net_device *dev, + unsigned int dmabuf_fd, + struct net_devmem_dmabuf_binding **out) +{ + return -EOPNOTSUPP; +} +static inline void +net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) +{ +} + +static inline int +net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct net_devmem_dmabuf_binding *binding) +{ + return -EOPNOTSUPP; +} +#endif + +static inline void +net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding) +{ + refcount_inc(&binding->ref); +} + +static inline void +net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding) +{ + if (!refcount_dec_and_test(&binding->ref)) + return; + + __net_devmem_dmabuf_binding_free(binding); +} + +#endif /* _NET_DEVMEM_H */ diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index e78ca52d67fbf..ac34f5fb4f71d 100644 --- a/include/net/netdev_rx_queue.h +++ b/include/net/netdev_rx_queue.h @@ -6,6 +6,7 @@ #include <linux/netdevice.h> #include <linux/sysfs.h> #include <net/xdp.h> +#include <net/page_pool/types.h>

/* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { @@ -25,6 +26,7 @@ struct netdev_rx_queue { * Readers and writers must hold RTNL */ struct napi_struct *napi; + struct pp_memory_provider_params mp_params; } ____cacheline_aligned_in_smp;

/* diff --git a/include/net/netmem.h b/include/net/netmem.h index d8b810245c1da..72e932a1a9489 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -8,6 +8,16 @@ #ifndef _NET_NETMEM_H #define _NET_NETMEM_H

+#include <net/devmem.h> + +/* net_iov */ + +struct net_iov { + struct dmabuf_genpool_chunk_owner *owner; +}; + +/* netmem */ + /** * typedef netmem_ref - a nonexistent type marking a reference to generic * network memory. diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 2bf15ca6bfd48..d6409d4ca8c77 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -135,6 +135,11 @@ struct memory_provider_ops { bool (*release_page)(struct page_pool *pool, struct page *page); };

+struct pp_memory_provider_params { + const struct memory_provider_ops *mp_ops; + void *mp_priv; +}; + struct page_pool { struct page_pool_params_fast p;

diff --git a/net/core/Makefile b/net/core/Makefile index f82232b358a2c..6b43611fb4a43 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -13,7 +13,7 @@ obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \ fib_notifier.o xdp.o flow_offload.o gro.o \ - netdev-genl.o netdev-genl-gen.o gso.o + netdev-genl.o netdev-genl-gen.o gso.o devmem.o

obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o

diff --git a/net/core/dev.c b/net/core/dev.c index d2ce91a334c1d..b879da266c1f3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -159,6 +159,9 @@ #include <net/page_pool/helpers.h> #include <net/rps.h> #include <linux/phy_link_topology_core.h> +#include <linux/genalloc.h> +#include <linux/dma-buf.h> +#include <net/devmem.h>

#include "dev.h" #include "net-sysfs.h" diff --git a/net/core/devmem.c b/net/core/devmem.c new file mode 100644 index 0000000000000..d82f92d7cf9ce --- /dev/null +++ b/net/core/devmem.c @@ -0,0 +1,254 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Devmem TCP + * + * Authors: Mina Almasry almasrymina@google.com + * Willem de Bruijn willemdebruijn.kernel@gmail.com + * Kaiyuan Zhang <kaiyuanz@google.com + */ + +#include <linux/types.h> +#include <linux/mm.h> +#include <linux/netdevice.h> +#include <trace/events/page_pool.h> +#include <net/netdev_rx_queue.h> +#include <net/page_pool/types.h> +#include <net/page_pool/helpers.h> +#include <linux/genalloc.h> +#include <linux/dma-buf.h> +#include <net/devmem.h> +#include <net/netdev_queues.h> + +/* Device memory support */ + +#ifdef CONFIG_DMA_SHARED_BUFFER +static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool, + struct gen_pool_chunk *chunk, + void *not_used) +{ + struct dmabuf_genpool_chunk_owner *owner = chunk->owner; + + kvfree(owner->niovs); + kfree(owner); +} + +void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) +{ + size_t size, avail; + + gen_pool_for_each_chunk(binding->chunk_pool, + net_devmem_dmabuf_free_chunk_owner, NULL); + + size = gen_pool_size(binding->chunk_pool); + avail = gen_pool_avail(binding->chunk_pool); + + if (!WARN(size != avail, "can't destroy genpool. size=%zu, avail=%zu", + size, avail)) + gen_pool_destroy(binding->chunk_pool); + + dma_buf_unmap_attachment(binding->attachment, binding->sgt, + DMA_FROM_DEVICE); + dma_buf_detach(binding->dmabuf, binding->attachment); + dma_buf_put(binding->dmabuf); + xa_destroy(&binding->bound_rxq_list); + kfree(binding); +} + +/* Protected by rtnl_lock() */ +static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1); + +void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) +{ + struct netdev_rx_queue *rxq; + unsigned long xa_idx; + unsigned int rxq_idx; + + if (!binding) + return; + + if (binding->list.next) + list_del(&binding->list); + + xa_for_each(&binding->bound_rxq_list, xa_idx, rxq) { + if (rxq->mp_params.mp_priv == binding) { + /* We hold the rtnl_lock while binding/unbinding + * dma-buf, so we can't race with another thread that + * is also modifying this value. However, the page_pool + * may read this config while it's creating its + * rx-queues. WRITE_ONCE() here to match the + * READ_ONCE() in the page_pool. + */ + WRITE_ONCE(rxq->mp_params.mp_ops, NULL); + WRITE_ONCE(rxq->mp_params.mp_priv, NULL); + + rxq_idx = get_netdev_rx_queue_index(rxq); + + netdev_rx_queue_restart(binding->dev, rxq_idx); + } + } + + xa_erase(&net_devmem_dmabuf_bindings, binding->id); + + net_devmem_dmabuf_binding_put(binding); +} + +int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct net_devmem_dmabuf_binding *binding) +{ + struct netdev_rx_queue *rxq; + u32 xa_idx; + int err; + + if (rxq_idx >= dev->num_rx_queues) + return -ERANGE; + + rxq = __netif_get_rx_queue(dev, rxq_idx); + if (rxq->mp_params.mp_priv) + return -EEXIST; + + err = xa_alloc(&binding->bound_rxq_list, &xa_idx, rxq, xa_limit_32b, + GFP_KERNEL); + if (err) + return err; + + /* We hold the rtnl_lock while binding/unbinding dma-buf, so we can't + * race with another thread that is also modifying this value. However, + * the driver may read this config while it's creating its * rx-queues. + * WRITE_ONCE() here to match the READ_ONCE() in the driver. + */ + WRITE_ONCE(rxq->mp_params.mp_priv, binding); + + err = netdev_rx_queue_restart(dev, rxq_idx); + if (err) + goto err_xa_erase; + + return 0; + +err_xa_erase: + WRITE_ONCE(rxq->mp_params.mp_ops, NULL); + WRITE_ONCE(rxq->mp_params.mp_priv, NULL); + xa_erase(&binding->bound_rxq_list, xa_idx); + + return err; +} + +int net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, + struct net_devmem_dmabuf_binding **out) +{ + struct net_devmem_dmabuf_binding *binding; + static u32 id_alloc_next; + struct scatterlist *sg; + struct dma_buf *dmabuf; + unsigned int sg_idx, i; + unsigned long virtual; + int err; + + dmabuf = dma_buf_get(dmabuf_fd); + if (IS_ERR(dmabuf)) + return -EBADFD; + + binding = kzalloc_node(sizeof(*binding), GFP_KERNEL, + dev_to_node(&dev->dev)); + if (!binding) { + err = -ENOMEM; + goto err_put_dmabuf; + } + + binding->dev = dev; + + err = xa_alloc_cyclic(&net_devmem_dmabuf_bindings, &binding->id, + binding, xa_limit_32b, &id_alloc_next, + GFP_KERNEL); + if (err < 0) + goto err_free_binding; + + xa_init_flags(&binding->bound_rxq_list, XA_FLAGS_ALLOC); + + refcount_set(&binding->ref, 1); + + binding->dmabuf = dmabuf; + + binding->attachment = dma_buf_attach(binding->dmabuf, dev->dev.parent); + if (IS_ERR(binding->attachment)) { + err = PTR_ERR(binding->attachment); + goto err_free_id; + } + + binding->sgt = + dma_buf_map_attachment(binding->attachment, DMA_BIDIRECTIONAL); + if (IS_ERR(binding->sgt)) { + err = PTR_ERR(binding->sgt); + goto err_detach; + } + + /* For simplicity we expect to make PAGE_SIZE allocations, but the + * binding can be much more flexible than that. We may be able to + * allocate MTU sized chunks here. Leave that for future work... + */ + binding->chunk_pool = + gen_pool_create(PAGE_SHIFT, dev_to_node(&dev->dev)); + if (!binding->chunk_pool) { + err = -ENOMEM; + goto err_unmap; + } + + virtual = 0; + for_each_sgtable_dma_sg(binding->sgt, sg, sg_idx) { + dma_addr_t dma_addr = sg_dma_address(sg); + struct dmabuf_genpool_chunk_owner *owner; + size_t len = sg_dma_len(sg); + struct net_iov *niov; + + owner = kzalloc_node(sizeof(*owner), GFP_KERNEL, + dev_to_node(&dev->dev)); + owner->base_virtual = virtual; + owner->base_dma_addr = dma_addr; + owner->num_niovs = len / PAGE_SIZE; + owner->binding = binding; + + err = gen_pool_add_owner(binding->chunk_pool, dma_addr, + dma_addr, len, dev_to_node(&dev->dev), + owner); + if (err) { + err = -EINVAL; + goto err_free_chunks; + } + + owner->niovs = kvmalloc_array(owner->num_niovs, + sizeof(*owner->niovs), + GFP_KERNEL); + if (!owner->niovs) { + err = -ENOMEM; + goto err_free_chunks; + } + + for (i = 0; i < owner->num_niovs; i++) { + niov = &owner->niovs[i]; + niov->owner = owner; + } + + virtual += len; + } + + *out = binding; + + return 0; + +err_free_chunks: + gen_pool_for_each_chunk(binding->chunk_pool, + net_devmem_dmabuf_free_chunk_owner, NULL); + gen_pool_destroy(binding->chunk_pool); +err_unmap: + dma_buf_unmap_attachment(binding->attachment, binding->sgt, + DMA_BIDIRECTIONAL); +err_detach: + dma_buf_detach(dmabuf, binding->attachment); +err_free_id: + xa_erase(&net_devmem_dmabuf_bindings, binding->id); +err_free_binding: + kfree(binding); +err_put_dmabuf: + dma_buf_put(dmabuf); + return err; +} +#endif diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index 9acd0d893765a..3dcd25049e593 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -9,6 +9,7 @@ #include "netdev-genl-gen.h"

#include <uapi/linux/netdev.h> +#include <linux/list.h>

/* Integer value ranges */ static const struct netlink_range_validation netdev_a_page_pool_id_range = { @@ -187,4 +188,7 @@ struct genl_family netdev_nl_family __ro_after_init = { .n_split_ops = ARRAY_SIZE(netdev_nl_ops), .mcgrps = netdev_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(netdev_nl_mcgrps), + .sock_priv_size = sizeof(struct list_head), + .sock_priv_init = (void *)netdev_nl_sock_priv_init, + .sock_priv_destroy = (void *)netdev_nl_sock_priv_destroy, }; diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index ca5a0983f2834..2c431b7dcbc84 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -10,6 +10,7 @@ #include <net/genetlink.h>

#include <uapi/linux/netdev.h> +#include <linux/list.h>

/* Common nested types */ extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1]; @@ -40,4 +41,7 @@ enum {

extern struct genl_family netdev_nl_family;

+void netdev_nl_sock_priv_init(struct list_head *priv); +void netdev_nl_sock_priv_destroy(struct list_head *priv); + #endif /* _LINUX_NETDEV_GEN_H */ diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index df14da2909184..e5f7565ffef34 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -10,6 +10,7 @@ #include <net/netdev_rx_queue.h> #include <net/netdev_queues.h> #include <net/busy_poll.h> +#include <net/devmem.h>

#include "netdev-genl-gen.h" #include "dev.h" @@ -719,10 +720,96 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, return err; }

-/* Stub */ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) { - return 0; + struct nlattr *tb[ARRAY_SIZE(netdev_queue_dmabuf_nl_policy)]; + struct net_devmem_dmabuf_binding *out_binding; + struct list_head *sock_binding_list; + u32 ifindex, dmabuf_fd, rxq_idx; + struct net_device *netdev; + struct sk_buff *rsp; + struct nlattr *attr; + int rem, err = 0; + void *hdr; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_BIND_DMABUF_DMABUF_FD) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_BIND_DMABUF_QUEUES)) + return -EINVAL; + + ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); + dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_BIND_DMABUF_DMABUF_FD]); + + rtnl_lock(); + + netdev = __dev_get_by_index(genl_info_net(info), ifindex); + if (!netdev) { + err = -ENODEV; + goto err_unlock; + } + + err = net_devmem_bind_dmabuf(netdev, dmabuf_fd, &out_binding); + if (err) + goto err_unlock; + + nla_for_each_attr(attr, genlmsg_data(info->genlhdr), + genlmsg_len(info->genlhdr), rem) { + if (nla_type(attr) != NETDEV_A_BIND_DMABUF_QUEUES) + continue; + + err = nla_parse_nested( + tb, ARRAY_SIZE(netdev_queue_dmabuf_nl_policy) - 1, attr, + netdev_queue_dmabuf_nl_policy, info->extack); + if (err < 0) + goto err_unbind; + + rxq_idx = nla_get_u32(tb[NETDEV_A_QUEUE_DMABUF_IDX]); + if (rxq_idx >= netdev->num_rx_queues) { + err = -ERANGE; + goto err_unbind; + } + + err = net_devmem_bind_dmabuf_to_queue(netdev, rxq_idx, + out_binding); + if (err) + goto err_unbind; + } + + sock_binding_list = genl_sk_priv_get(&netdev_nl_family, + NETLINK_CB(skb).sk); + if (IS_ERR(sock_binding_list)) { + err = PTR_ERR(sock_binding_list); + goto err_unbind; + } + + list_add(&out_binding->list, sock_binding_list); + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) { + err = -ENOMEM; + goto err_unbind; + } + + hdr = genlmsg_iput(rsp, info); + if (!hdr) { + err = -EMSGSIZE; + goto err_genlmsg_free; + } + + nla_put_u32(rsp, NETDEV_A_BIND_DMABUF_DMABUF_ID, out_binding->id); + genlmsg_end(rsp, hdr); + + rtnl_unlock(); + + return genlmsg_reply(rsp, info); + +err_genlmsg_free: + nlmsg_free(rsp); +err_unbind: + net_devmem_unbind_dmabuf(out_binding); +err_unlock: + rtnl_unlock(); + return err; }

static int netdev_genl_netdevice_event(struct notifier_block *nb, @@ -769,3 +856,17 @@ static int __init netdev_genl_init(void) }

subsys_initcall(netdev_genl_init); + +void netdev_nl_sock_priv_init(struct list_head *priv) +{ + INIT_LIST_HEAD(priv); +} + +void netdev_nl_sock_priv_destroy(struct list_head *priv) +{ + struct net_devmem_dmabuf_binding *binding; + struct net_devmem_dmabuf_binding *temp; + + list_for_each_entry_safe(binding, temp, priv, list) + net_devmem_unbind_dmabuf(binding); +}

Implement netdev devmem allocator. The allocator takes a given struct netdev_dmabuf_binding as input and allocates net_iov from that binding.

The allocation simply delegates to the binding's genpool for the allocation logic and wraps the returned memory region in a net_iov struct.

Signed-off-by: Willem de Bruijn willemb@google.com Signed-off-by: Kaiyuan Zhang kaiyuanz@google.com Signed-off-by: Mina Almasry almasrymina@google.com

---

v8: - Rename netdev_dmabuf_binding -> net_devmem_dmabuf_binding to avoid patch-by-patch build error. - Move niov->pp_magic/pp/pp_ref_counter usage to later patch to avoid patch-by-patch build error.

v7: - netdev_ -> net_devmem_* naming (Yunsheng).

v6: - Add comment on net_iov_dma_addr to explain why we don't use niov->dma_addr (Pavel) - Refactor new functions into net/core/devmem.c (Pavel)

v1: - Rename devmem -> dmabuf (David).

--- include/net/devmem.h | 13 +++++++++++++ include/net/netmem.h | 40 ++++++++++++++++++++++++++++++++++++++++ net/core/devmem.c | 36 ++++++++++++++++++++++++++++++++++++ 3 files changed, 89 insertions(+)

diff --git a/include/net/devmem.h b/include/net/devmem.h index fa03bdabdffd9..cd3186f5d1fbd 100644 --- a/include/net/devmem.h +++ b/include/net/devmem.h @@ -68,7 +68,20 @@ int net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding); int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, struct net_devmem_dmabuf_binding *binding); +struct net_iov * +net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding); +void net_devmem_free_dmabuf(struct net_iov *ppiov); #else +static inline struct net_iov * +net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding) +{ + return NULL; +} + +static inline void net_devmem_free_dmabuf(struct net_iov *ppiov) +{ +} + static inline void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) { diff --git a/include/net/netmem.h b/include/net/netmem.h index 72e932a1a9489..33014370a8858 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -14,8 +14,48 @@

struct net_iov { struct dmabuf_genpool_chunk_owner *owner; + unsigned long dma_addr; };

+static inline struct dmabuf_genpool_chunk_owner * +net_iov_owner(const struct net_iov *niov) +{ + return niov->owner; +} + +static inline unsigned int net_iov_idx(const struct net_iov *niov) +{ + return niov - net_iov_owner(niov)->niovs; +} + +/* This returns the absolute dma_addr_t calculated from + * net_iov_owner(niov)->owner->base_dma_addr, not the page_pool-owned + * niov->dma_addr. + * + * The absolute dma_addr_t is a dma_addr_t that is always uncompressed. + * + * The page_pool-owner niov->dma_addr is the absolute dma_addr compressed into + * an unsigned long. Special handling is done when the unsigned long is 32-bit + * but the dma_addr_t is 64-bit. + * + * In general code looking for the dma_addr_t should use net_iov_dma_addr(), + * while page_pool code looking for the unsigned long dma_addr which mirrors + * the field in struct page should use niov->dma_addr. + */ +static inline dma_addr_t net_iov_dma_addr(const struct net_iov *niov) +{ + struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov); + + return owner->base_dma_addr + + ((dma_addr_t)net_iov_idx(niov) << PAGE_SHIFT); +} + +static inline struct net_devmem_dmabuf_binding * +net_iov_binding(const struct net_iov *niov) +{ + return net_iov_owner(niov)->binding; +} + /* netmem */

/** diff --git a/net/core/devmem.c b/net/core/devmem.c index d82f92d7cf9ce..1f90e23a81441 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -54,6 +54,42 @@ void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) kfree(binding); }

+struct net_iov * +net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding) +{ + struct dmabuf_genpool_chunk_owner *owner; + unsigned long dma_addr; + struct net_iov *niov; + ssize_t offset; + ssize_t index; + + dma_addr = gen_pool_alloc_owner(binding->chunk_pool, PAGE_SIZE, + (void **)&owner); + if (!dma_addr) + return NULL; + + offset = dma_addr - owner->base_dma_addr; + index = offset / PAGE_SIZE; + niov = &owner->niovs[index]; + + niov->dma_addr = 0; + + net_devmem_dmabuf_binding_get(binding); + + return niov; +} + +void net_devmem_free_dmabuf(struct net_iov *niov) +{ + struct net_devmem_dmabuf_binding *binding = net_iov_binding(niov); + unsigned long dma_addr = net_iov_dma_addr(niov); + + if (gen_pool_has_addr(binding->chunk_pool, dma_addr, PAGE_SIZE)) + gen_pool_free(binding->chunk_pool, dma_addr, PAGE_SIZE); + + net_devmem_dmabuf_binding_put(binding); +} + /* Protected by rtnl_lock() */ static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1);

Abstrace the memory type from the page_pool so we can later add support for new memory types. Convert the page_pool to use the new netmem type abstraction, rather than use struct page directly.

As of this patch the netmem type is a no-op abstraction: it's always a struct page underneath. All the page pool internals are converted to use struct netmem instead of struct page, and the page pool now exports 2 APIs:

1. The existing struct page API. 2. The new struct netmem API.

Keeping the existing API is transitional; we do not want to refactor all the current drivers using the page pool at once.

The netmem abstraction is currently a no-op. The page_pool uses page_to_netmem() to convert allocated pages to netmem, and uses netmem_to_page() to convert the netmem back to pages to pass to mm APIs,

Follow up patches to this series add non-paged netmem support to the page_pool. This change is factored out on its own to limit the code churn to this 1 patch, for ease of code review.

Signed-off-by: Mina Almasry almasrymina@google.com

---

v9: - Fix sparse error (Simon).

v8: - Fix napi_pp_put_page() taking netmem instead of page to fix patch-by-patch build error. - Add net/netmem.h include in this patch to fix patch-by-patch build error.

v6:

- Rebased on top of the merged netmem_ref type.

Cc: linux-mm@kvack.org Cc: Matthew Wilcox willy@infradead.org

--- include/linux/skbuff_ref.h | 4 +- include/net/netmem.h | 15 ++ include/net/page_pool/helpers.h | 124 +++++++++---- include/net/page_pool/types.h | 18 +- include/trace/events/page_pool.h | 29 +-- net/bpf/test_run.c | 5 +- net/core/page_pool.c | 303 +++++++++++++++++-------------- net/core/skbuff.c | 8 +- 8 files changed, 305 insertions(+), 201 deletions(-)

diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h index 11f0a40634033..16c241a234728 100644 --- a/include/linux/skbuff_ref.h +++ b/include/linux/skbuff_ref.h @@ -32,13 +32,13 @@ 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); +bool napi_pp_put_page(netmem_ref netmem);

static inline void skb_page_unref(struct page *page, bool recycle) { #ifdef CONFIG_PAGE_POOL - if (recycle && napi_pp_put_page(page)) + if (recycle && napi_pp_put_page(page_to_netmem(page))) return; #endif put_page(page); diff --git a/include/net/netmem.h b/include/net/netmem.h index 33014370a8858..5f1c728618f23 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -88,4 +88,19 @@ static inline netmem_ref page_to_netmem(struct page *page) return (__force netmem_ref)page; }

+static inline int netmem_ref_count(netmem_ref netmem) +{ + return page_ref_count(netmem_to_page(netmem)); +} + +static inline unsigned long netmem_to_pfn(netmem_ref netmem) +{ + return page_to_pfn(netmem_to_page(netmem)); +} + +static inline netmem_ref netmem_compound_head(netmem_ref netmem) +{ + return page_to_netmem(compound_head(netmem_to_page(netmem))); +} + #endif /* _NET_NETMEM_H */ diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 873631c79ab16..a3998d299afd9 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -55,6 +55,8 @@ #include <linux/dma-mapping.h>

#include <net/page_pool/types.h> +#include <net/net_debug.h> +#include <net/netmem.h>

#ifdef CONFIG_PAGE_POOL_STATS /* Deprecated driver-facing API, use netlink instead */ @@ -103,7 +105,7 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) * Get a page fragment from the page allocator or page_pool caches. * * Return: - * Return allocated page fragment, otherwise return NULL. + * Return allocated page fragment, otherwise return 0. */ static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, unsigned int *offset, @@ -114,22 +116,22 @@ static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, return page_pool_alloc_frag(pool, offset, size, gfp); }

-static inline struct page *page_pool_alloc(struct page_pool *pool, - unsigned int *offset, - unsigned int *size, gfp_t gfp) +static inline netmem_ref page_pool_alloc(struct page_pool *pool, + unsigned int *offset, + unsigned int *size, gfp_t gfp) { unsigned int max_size = PAGE_SIZE << pool->p.order; - struct page *page; + netmem_ref netmem;

if ((*size << 1) > max_size) { *size = max_size; *offset = 0; - return page_pool_alloc_pages(pool, gfp); + return page_pool_alloc_netmem(pool, gfp); }

- page = page_pool_alloc_frag(pool, offset, *size, gfp); - if (unlikely(!page)) - return NULL; + netmem = page_pool_alloc_frag_netmem(pool, offset, *size, gfp); + if (unlikely(!netmem)) + return 0;

/* There is very likely not enough space for another fragment, so append * the remaining size to the current fragment to avoid truesize @@ -140,7 +142,7 @@ static inline struct page *page_pool_alloc(struct page_pool *pool, pool->frag_offset = max_size; }

- return page; + return netmem; }

/** @@ -154,7 +156,7 @@ static inline struct page *page_pool_alloc(struct page_pool *pool, * utilization and performance penalty. * * Return: - * Return allocated page or page fragment, otherwise return NULL. + * Return allocated page or page fragment, otherwise return 0. */ static inline struct page *page_pool_dev_alloc(struct page_pool *pool, unsigned int *offset, @@ -162,7 +164,7 @@ static inline struct page *page_pool_dev_alloc(struct page_pool *pool, { gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN);

- return page_pool_alloc(pool, offset, size, gfp); + return netmem_to_page(page_pool_alloc(pool, offset, size, gfp)); }

static inline void *page_pool_alloc_va(struct page_pool *pool, @@ -172,7 +174,8 @@ static inline void *page_pool_alloc_va(struct page_pool *pool, struct page *page;

/* Mask off __GFP_HIGHMEM to ensure we can use page_address() */ - page = page_pool_alloc(pool, &offset, size, gfp & ~__GFP_HIGHMEM); + page = netmem_to_page( + page_pool_alloc(pool, &offset, size, gfp & ~__GFP_HIGHMEM)); if (unlikely(!page)) return NULL;

@@ -189,7 +192,7 @@ static inline void *page_pool_alloc_va(struct page_pool *pool, * it returns va of the allocated page or page fragment. * * Return: - * Return the va for the allocated page or page fragment, otherwise return NULL. + * Return the va for the allocated page or page fragment, otherwise return 0. */ static inline void *page_pool_dev_alloc_va(struct page_pool *pool, unsigned int *size) @@ -212,6 +215,11 @@ page_pool_get_dma_dir(const struct page_pool *pool) return pool->p.dma_dir; }

+static inline void page_pool_fragment_netmem(netmem_ref netmem, long nr) +{ + atomic_long_set(&netmem_to_page(netmem)->pp_ref_count, nr); +} + /** * page_pool_fragment_page() - split a fresh page into fragments * @page: page to split @@ -232,11 +240,12 @@ page_pool_get_dma_dir(const struct page_pool *pool) */ static inline void page_pool_fragment_page(struct page *page, long nr) { - atomic_long_set(&page->pp_ref_count, nr); + page_pool_fragment_netmem(page_to_netmem(page), nr); }

-static inline long page_pool_unref_page(struct page *page, long nr) +static inline long page_pool_unref_netmem(netmem_ref netmem, long nr) { + struct page *page = netmem_to_page(netmem); long ret;

/* If nr == pp_ref_count then we have cleared all remaining @@ -279,15 +288,41 @@ static inline long page_pool_unref_page(struct page *page, long nr) return ret; }

+static inline long page_pool_unref_page(struct page *page, long nr) +{ + return page_pool_unref_netmem(page_to_netmem(page), nr); +} + +static inline void page_pool_ref_netmem(netmem_ref netmem) +{ + atomic_long_inc(&netmem_to_page(netmem)->pp_ref_count); +} + static inline void page_pool_ref_page(struct page *page) { - atomic_long_inc(&page->pp_ref_count); + page_pool_ref_netmem(page_to_netmem(page)); }

-static inline bool page_pool_is_last_ref(struct page *page) +static inline bool page_pool_is_last_ref(netmem_ref netmem) { /* If page_pool_unref_page() returns 0, we were the last user */ - return page_pool_unref_page(page, 1) == 0; + return page_pool_unref_netmem(netmem, 1) == 0; +} + +static inline void page_pool_put_netmem(struct page_pool *pool, + netmem_ref netmem, + unsigned int dma_sync_size, + bool allow_direct) +{ + /* When page_pool isn't compiled-in, net/core/xdp.c doesn't + * allow registering MEM_TYPE_PAGE_POOL, but shield linker. + */ +#ifdef CONFIG_PAGE_POOL + if (!page_pool_is_last_ref(netmem)) + return; + + page_pool_put_unrefed_netmem(pool, netmem, dma_sync_size, allow_direct); +#endif }

/** @@ -308,15 +343,15 @@ static inline void page_pool_put_page(struct page_pool *pool, unsigned int dma_sync_size, bool allow_direct) { - /* When page_pool isn't compiled-in, net/core/xdp.c doesn't - * allow registering MEM_TYPE_PAGE_POOL, but shield linker. - */ -#ifdef CONFIG_PAGE_POOL - if (!page_pool_is_last_ref(page)) - return; + page_pool_put_netmem(pool, page_to_netmem(page), dma_sync_size, + allow_direct); +}

- page_pool_put_unrefed_page(pool, page, dma_sync_size, allow_direct); -#endif +static inline void page_pool_put_full_netmem(struct page_pool *pool, + netmem_ref netmem, + bool allow_direct) +{ + page_pool_put_netmem(pool, netmem, -1, allow_direct); }

/** @@ -331,7 +366,7 @@ static inline void page_pool_put_page(struct page_pool *pool, static inline void page_pool_put_full_page(struct page_pool *pool, struct page *page, bool allow_direct) { - page_pool_put_page(pool, page, -1, allow_direct); + page_pool_put_netmem(pool, page_to_netmem(page), -1, allow_direct); }

/** @@ -365,6 +400,18 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va, page_pool_put_page(pool, virt_to_head_page(va), -1, allow_direct); }

+static inline dma_addr_t page_pool_get_dma_addr_netmem(netmem_ref netmem) +{ + struct page *page = netmem_to_page(netmem); + + dma_addr_t ret = page->dma_addr; + + if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) + ret <<= PAGE_SHIFT; + + return ret; +} + /** * page_pool_get_dma_addr() - Retrieve the stored DMA address. * @page: page allocated from a page pool @@ -372,18 +419,16 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va, * Fetch the DMA address of the page. The page pool to which the page belongs * must had been created with PP_FLAG_DMA_MAP. */ -static inline dma_addr_t page_pool_get_dma_addr(const struct page *page) +static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - dma_addr_t ret = page->dma_addr; - - if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) - ret <<= PAGE_SHIFT; - - return ret; + return page_pool_get_dma_addr_netmem(page_to_netmem(page)); }

-static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr) +static inline bool page_pool_set_dma_addr_netmem(netmem_ref netmem, + dma_addr_t addr) { + struct page *page = netmem_to_page(netmem); + if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) { page->dma_addr = addr >> PAGE_SHIFT;

@@ -410,7 +455,7 @@ static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr) * associated PP doesn't perform sync-for-device. */ static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool, - const struct page *page, + struct page *page, u32 offset, u32 dma_sync_size) { dma_sync_single_range_for_cpu(pool->p.dev, @@ -419,6 +464,11 @@ static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool, page_pool_get_dma_dir(pool)); }

+static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr) +{ + return page_pool_set_dma_addr_netmem(page_to_netmem(page), addr); +} + static inline bool page_pool_put(struct page_pool *pool) { return refcount_dec_and_test(&pool->user_cnt); diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index d6409d4ca8c77..c51e45b343f10 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -6,6 +6,7 @@ #include <linux/dma-direction.h> #include <linux/ptr_ring.h> #include <linux/types.h> +#include <net/netmem.h>

#define PP_FLAG_DMA_MAP BIT(0) /* Should page_pool do the DMA * map/unmap @@ -40,7 +41,7 @@ #define PP_ALLOC_CACHE_REFILL 64 struct pp_alloc_cache { u32 count; - struct page *cache[PP_ALLOC_CACHE_SIZE]; + netmem_ref cache[PP_ALLOC_CACHE_SIZE]; };

/** @@ -73,7 +74,7 @@ struct page_pool_params { struct_group_tagged(page_pool_params_slow, slow, struct net_device *netdev; /* private: used by test code only */ - void (*init_callback)(struct page *page, void *arg); + void (*init_callback)(netmem_ref netmem, void *arg); void *init_arg; ); }; @@ -131,8 +132,8 @@ struct page_pool_stats { struct memory_provider_ops { int (*init)(struct page_pool *pool); void (*destroy)(struct page_pool *pool); - struct page *(*alloc_pages)(struct page_pool *pool, gfp_t gfp); - bool (*release_page)(struct page_pool *pool, struct page *page); + netmem_ref (*alloc_pages)(struct page_pool *pool, gfp_t gfp); + bool (*release_page)(struct page_pool *pool, netmem_ref netmem); };

struct pp_memory_provider_params { @@ -147,7 +148,7 @@ struct page_pool { bool has_init_callback;

long frag_users; - struct page *frag_page; + netmem_ref frag_page; unsigned int frag_offset; u32 pages_state_hold_cnt;

@@ -219,8 +220,12 @@ struct page_pool { };

struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp); +netmem_ref page_pool_alloc_netmem(struct page_pool *pool, gfp_t gfp); struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset, unsigned int size, gfp_t gfp); +netmem_ref page_pool_alloc_frag_netmem(struct page_pool *pool, + unsigned int *offset, unsigned int size, + gfp_t gfp); struct page_pool *page_pool_create(const struct page_pool_params *params); struct page_pool *page_pool_create_percpu(const struct page_pool_params *params, int cpuid); @@ -250,6 +255,9 @@ static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data, } #endif

+void page_pool_put_unrefed_netmem(struct page_pool *pool, netmem_ref netmem, + unsigned int dma_sync_size, + bool allow_direct); void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page, unsigned int dma_sync_size, bool allow_direct); diff --git a/include/trace/events/page_pool.h b/include/trace/events/page_pool.h index 6834356b2d2ae..c5b6383ff2760 100644 --- a/include/trace/events/page_pool.h +++ b/include/trace/events/page_pool.h @@ -42,51 +42,52 @@ TRACE_EVENT(page_pool_release, TRACE_EVENT(page_pool_state_release,

TP_PROTO(const struct page_pool *pool, - const struct page *page, u32 release), + netmem_ref netmem, u32 release),

- TP_ARGS(pool, page, release), + TP_ARGS(pool, netmem, release),

TP_STRUCT__entry( __field(const struct page_pool *, pool) - __field(const struct page *, page) + __field(netmem_ref, netmem) __field(u32, release) __field(unsigned long, pfn) ),

TP_fast_assign( __entry->pool = pool; - __entry->page = page; + __entry->netmem = netmem; __entry->release = release; - __entry->pfn = page_to_pfn(page); + __entry->pfn = netmem_to_pfn(netmem); ),

- TP_printk("page_pool=%p page=%p pfn=0x%lx release=%u", - __entry->pool, __entry->page, __entry->pfn, __entry->release) + TP_printk("page_pool=%p netmem=%lu pfn=0x%lx release=%u", + __entry->pool, (__force unsigned long)__entry->netmem, + __entry->pfn, __entry->release) );

TRACE_EVENT(page_pool_state_hold,

TP_PROTO(const struct page_pool *pool, - const struct page *page, u32 hold), + netmem_ref netmem, u32 hold),

- TP_ARGS(pool, page, hold), + TP_ARGS(pool, netmem, hold),

TP_STRUCT__entry( __field(const struct page_pool *, pool) - __field(const struct page *, page) + __field(netmem_ref, netmem) __field(u32, hold) __field(unsigned long, pfn) ),

TP_fast_assign( __entry->pool = pool; - __entry->page = page; + __entry->netmem = netmem; __entry->hold = hold; - __entry->pfn = page_to_pfn(page); + __entry->pfn = netmem_to_pfn(netmem); ),

- TP_printk("page_pool=%p page=%p pfn=0x%lx hold=%u", - __entry->pool, __entry->page, __entry->pfn, __entry->hold) + TP_printk("page_pool=%p netmem=%lu pfn=0x%lx hold=%u", + __entry->pool, __entry->netmem, __entry->pfn, __entry->hold) );

TRACE_EVENT(page_pool_update_nid, diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index f6aad4ed2ab2f..b4cde1cc887d0 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -127,9 +127,10 @@ struct xdp_test_data { #define TEST_XDP_FRAME_SIZE (PAGE_SIZE - sizeof(struct xdp_page_head)) #define TEST_XDP_MAX_BATCH 256

-static void xdp_test_run_init_page(struct page *page, void *arg) +static void xdp_test_run_init_page(netmem_ref netmem, void *arg) { - struct xdp_page_head *head = phys_to_virt(page_to_phys(page)); + struct xdp_page_head *head = + phys_to_virt(page_to_phys(netmem_to_page(netmem))); struct xdp_buff *new_ctx, *orig_ctx; u32 headroom = XDP_PACKET_HEADROOM; struct xdp_test_data *xdp = arg; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index ae403397df09d..33f91bf6d5dc2 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -330,19 +330,18 @@ struct page_pool *page_pool_create(const struct page_pool_params *params) } EXPORT_SYMBOL(page_pool_create);

-static void page_pool_return_page(struct page_pool *pool, struct page *page); +static void page_pool_return_page(struct page_pool *pool, netmem_ref netmem);

-noinline -static struct page *page_pool_refill_alloc_cache(struct page_pool *pool) +static noinline netmem_ref page_pool_refill_alloc_cache(struct page_pool *pool) { struct ptr_ring *r = &pool->ring; - struct page *page; + netmem_ref netmem; int pref_nid; /* preferred NUMA node */

/* Quicker fallback, avoid locks when ring is empty */ if (__ptr_ring_empty(r)) { alloc_stat_inc(pool, empty); - return NULL; + return 0; }

/* Softirq guarantee CPU and thus NUMA node is stable. This, @@ -357,56 +356,56 @@ static struct page *page_pool_refill_alloc_cache(struct page_pool *pool)

/* Refill alloc array, but only if NUMA match */ do { - page = __ptr_ring_consume(r); - if (unlikely(!page)) + netmem = (__force netmem_ref)__ptr_ring_consume(r); + if (unlikely(!netmem)) break;

- if (likely(page_to_nid(page) == pref_nid)) { - pool->alloc.cache[pool->alloc.count++] = page; + if (likely(page_to_nid(netmem_to_page(netmem)) == pref_nid)) { + pool->alloc.cache[pool->alloc.count++] = netmem; } else { /* NUMA mismatch; * (1) release 1 page to page-allocator and * (2) break out to fallthrough to alloc_pages_node. * This limit stress on page buddy alloactor. */ - page_pool_return_page(pool, page); + page_pool_return_page(pool, netmem); alloc_stat_inc(pool, waive); - page = NULL; + netmem = 0; break; } } while (pool->alloc.count < PP_ALLOC_CACHE_REFILL);

/* Return last page */ if (likely(pool->alloc.count > 0)) { - page = pool->alloc.cache[--pool->alloc.count]; + netmem = pool->alloc.cache[--pool->alloc.count]; alloc_stat_inc(pool, refill); }

- return page; + return netmem; }

/* fast path */ -static struct page *__page_pool_get_cached(struct page_pool *pool) +static netmem_ref __page_pool_get_cached(struct page_pool *pool) { - struct page *page; + netmem_ref netmem;

/* Caller MUST guarantee safe non-concurrent access, e.g. softirq */ if (likely(pool->alloc.count)) { /* Fast-path */ - page = pool->alloc.cache[--pool->alloc.count]; + netmem = pool->alloc.cache[--pool->alloc.count]; alloc_stat_inc(pool, fast); } else { - page = page_pool_refill_alloc_cache(pool); + netmem = page_pool_refill_alloc_cache(pool); }

- return page; + return netmem; }

static void page_pool_dma_sync_for_device(const struct page_pool *pool, - const struct page *page, + const netmem_ref netmem, unsigned int dma_sync_size) { - dma_addr_t dma_addr = page_pool_get_dma_addr(page); + dma_addr_t dma_addr = page_pool_get_dma_addr_netmem(netmem);

dma_sync_size = min(dma_sync_size, pool->p.max_len); dma_sync_single_range_for_device(pool->p.dev, dma_addr, @@ -414,7 +413,7 @@ static void page_pool_dma_sync_for_device(const struct page_pool *pool, pool->p.dma_dir); }

-static bool page_pool_dma_map(struct page_pool *pool, struct page *page) +static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem) { dma_addr_t dma;

@@ -423,18 +422,18 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page) * into page private data (i.e 32bit cpu with 64bit DMA caps) * This mapping is kept for lifetime of page, until leaving pool. */ - dma = dma_map_page_attrs(pool->p.dev, page, 0, - (PAGE_SIZE << pool->p.order), - pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC | - DMA_ATTR_WEAK_ORDERING); + dma = dma_map_page_attrs(pool->p.dev, netmem_to_page(netmem), 0, + (PAGE_SIZE << pool->p.order), pool->p.dma_dir, + DMA_ATTR_SKIP_CPU_SYNC | + DMA_ATTR_WEAK_ORDERING); if (dma_mapping_error(pool->p.dev, dma)) return false;

- if (page_pool_set_dma_addr(page, dma)) + if (page_pool_set_dma_addr_netmem(netmem, dma)) goto unmap_failed;

if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) - page_pool_dma_sync_for_device(pool, page, pool->p.max_len); + page_pool_dma_sync_for_device(pool, netmem, pool->p.max_len);

return true;

@@ -446,9 +445,10 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page) return false; }

-static void page_pool_set_pp_info(struct page_pool *pool, - struct page *page) +static void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem) { + struct page *page = netmem_to_page(netmem); + page->pp = pool; page->pp_magic |= PP_SIGNATURE;

@@ -458,13 +458,15 @@ static void page_pool_set_pp_info(struct page_pool *pool, * is dirtying the same cache line as the page->pp_magic above, so * the overhead is negligible. */ - page_pool_fragment_page(page, 1); + page_pool_fragment_netmem(netmem, 1); if (pool->has_init_callback) - pool->slow.init_callback(page, pool->slow.init_arg); + pool->slow.init_callback(netmem, pool->slow.init_arg); }

-static void page_pool_clear_pp_info(struct page *page) +static void page_pool_clear_pp_info(netmem_ref netmem) { + struct page *page = netmem_to_page(netmem); + page->pp_magic = 0; page->pp = NULL; } @@ -480,34 +482,34 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool, return NULL;

if ((pool->p.flags & PP_FLAG_DMA_MAP) && - unlikely(!page_pool_dma_map(pool, page))) { + unlikely(!page_pool_dma_map(pool, page_to_netmem(page)))) { put_page(page); return NULL; }

alloc_stat_inc(pool, slow_high_order); - page_pool_set_pp_info(pool, page); + page_pool_set_pp_info(pool, page_to_netmem(page));

/* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; - trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt); + trace_page_pool_state_hold(pool, page_to_netmem(page), + pool->pages_state_hold_cnt); return page; }

/* slow path */ -noinline -static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, - gfp_t gfp) +static noinline netmem_ref __page_pool_alloc_pages_slow(struct page_pool *pool, + gfp_t gfp) { const int bulk = PP_ALLOC_CACHE_REFILL; unsigned int pp_flags = pool->p.flags; unsigned int pp_order = pool->p.order; - struct page *page; + netmem_ref netmem; int i, nr_pages;

/* Don't support bulk alloc for high-order pages */ if (unlikely(pp_order)) - return __page_pool_alloc_page_order(pool, gfp); + return page_to_netmem(__page_pool_alloc_page_order(pool, gfp));

/* Unnecessary as alloc cache is empty, but guarantees zero count */ if (unlikely(pool->alloc.count > 0)) @@ -516,60 +518,67 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, /* Mark empty alloc.cache slots "empty" for alloc_pages_bulk_array */ memset(&pool->alloc.cache, 0, sizeof(void *) * bulk);

- nr_pages = alloc_pages_bulk_array_node(gfp, pool->p.nid, bulk, - pool->alloc.cache); + nr_pages = alloc_pages_bulk_array_node(gfp, + pool->p.nid, bulk, + (struct page **)pool->alloc.cache); if (unlikely(!nr_pages)) - return NULL; + return 0;

/* Pages have been filled into alloc.cache array, but count is zero and * page element have not been (possibly) DMA mapped. */ for (i = 0; i < nr_pages; i++) { - page = pool->alloc.cache[i]; + netmem = pool->alloc.cache[i]; if ((pp_flags & PP_FLAG_DMA_MAP) && - unlikely(!page_pool_dma_map(pool, page))) { - put_page(page); + unlikely(!page_pool_dma_map(pool, netmem))) { + put_page(netmem_to_page(netmem)); continue; }

- page_pool_set_pp_info(pool, page); - pool->alloc.cache[pool->alloc.count++] = page; + page_pool_set_pp_info(pool, netmem); + pool->alloc.cache[pool->alloc.count++] = netmem; /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; - trace_page_pool_state_hold(pool, page, + trace_page_pool_state_hold(pool, netmem, pool->pages_state_hold_cnt); }

/* Return last page */ if (likely(pool->alloc.count > 0)) { - page = pool->alloc.cache[--pool->alloc.count]; + netmem = pool->alloc.cache[--pool->alloc.count]; alloc_stat_inc(pool, slow); } else { - page = NULL; + netmem = 0; }

/* When page just alloc'ed is should/must have refcnt 1. */ - return page; + return netmem; }

/* For using page_pool replace: alloc_pages() API calls, but provide * synchronization guarantee for allocation side. */ -struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp) +netmem_ref page_pool_alloc_netmem(struct page_pool *pool, gfp_t gfp) { - struct page *page; + netmem_ref netmem;

/* Fast-path: Get a page from cache */ - page = __page_pool_get_cached(pool); - if (page) - return page; + netmem = __page_pool_get_cached(pool); + if (netmem) + return netmem;

/* Slow-path: cache empty, do real allocation */ if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops) - page = pool->mp_ops->alloc_pages(pool, gfp); + netmem = pool->mp_ops->alloc_pages(pool, gfp); else - page = __page_pool_alloc_pages_slow(pool, gfp); - return page; + netmem = __page_pool_alloc_pages_slow(pool, gfp); + return netmem; +} +EXPORT_SYMBOL(page_pool_alloc_netmem); + +struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp) +{ + return netmem_to_page(page_pool_alloc_netmem(pool, gfp)); } EXPORT_SYMBOL(page_pool_alloc_pages); ALLOW_ERROR_INJECTION(page_pool_alloc_pages, NULL); @@ -598,8 +607,8 @@ s32 page_pool_inflight(const struct page_pool *pool, bool strict) return inflight; }

-static __always_inline -void __page_pool_release_page_dma(struct page_pool *pool, struct page *page) +static __always_inline void __page_pool_release_page_dma(struct page_pool *pool, + netmem_ref netmem) { dma_addr_t dma;

@@ -609,13 +618,13 @@ void __page_pool_release_page_dma(struct page_pool *pool, struct page *page) */ return;

- dma = page_pool_get_dma_addr(page); + dma = page_pool_get_dma_addr_netmem(netmem);

/* When page is unmapped, it cannot be returned to our pool */ dma_unmap_page_attrs(pool->p.dev, dma, PAGE_SIZE << pool->p.order, pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING); - page_pool_set_dma_addr(page, 0); + page_pool_set_dma_addr_netmem(netmem, 0); }

/* Disconnects a page (from a page_pool). API users can have a need @@ -623,26 +632,26 @@ void __page_pool_release_page_dma(struct page_pool *pool, struct page *page) * a regular page (that will eventually be returned to the normal * page-allocator via put_page). */ -void page_pool_return_page(struct page_pool *pool, struct page *page) +void page_pool_return_page(struct page_pool *pool, netmem_ref netmem) { int count; bool put;

put = true; if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops) - put = pool->mp_ops->release_page(pool, page); + put = pool->mp_ops->release_page(pool, netmem); else - __page_pool_release_page_dma(pool, page); + __page_pool_release_page_dma(pool, netmem);

/* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. */ count = atomic_inc_return_relaxed(&pool->pages_state_release_cnt); - trace_page_pool_state_release(pool, page, count); + trace_page_pool_state_release(pool, netmem, count);

if (put) { - page_pool_clear_pp_info(page); - put_page(page); + page_pool_clear_pp_info(netmem); + put_page(netmem_to_page(netmem)); } /* An optimization would be to call __free_pages(page, pool->p.order) * knowing page is not part of page-cache (thus avoiding a @@ -650,14 +659,14 @@ void page_pool_return_page(struct page_pool *pool, struct page *page) */ }

-static bool page_pool_recycle_in_ring(struct page_pool *pool, struct page *page) +static bool page_pool_recycle_in_ring(struct page_pool *pool, netmem_ref netmem) { int ret; /* BH protection not needed if current is softirq */ if (in_softirq()) - ret = ptr_ring_produce(&pool->ring, page); + ret = ptr_ring_produce(&pool->ring, (__force void *)netmem); else - ret = ptr_ring_produce_bh(&pool->ring, page); + ret = ptr_ring_produce_bh(&pool->ring, (__force void *)netmem);

if (!ret) { recycle_stat_inc(pool, ring); @@ -672,7 +681,7 @@ static bool page_pool_recycle_in_ring(struct page_pool *pool, struct page *page) * * Caller must provide appropriate safe context. */ -static bool page_pool_recycle_in_cache(struct page *page, +static bool page_pool_recycle_in_cache(netmem_ref netmem, struct page_pool *pool) { if (unlikely(pool->alloc.count == PP_ALLOC_CACHE_SIZE)) { @@ -681,14 +690,15 @@ static bool page_pool_recycle_in_cache(struct page *page, }

/* Caller MUST have verified/know (page_ref_count(page) == 1) */ - pool->alloc.cache[pool->alloc.count++] = page; + pool->alloc.cache[pool->alloc.count++] = netmem; recycle_stat_inc(pool, cached); return true; }

-static bool __page_pool_page_can_be_recycled(const struct page *page) +static bool __page_pool_page_can_be_recycled(netmem_ref netmem) { - return page_ref_count(page) == 1 && !page_is_pfmemalloc(page); + return page_ref_count(netmem_to_page(netmem)) == 1 && + !page_is_pfmemalloc(netmem_to_page(netmem)); }

/* If the page refcnt == 1, this will try to recycle the page. @@ -697,8 +707,8 @@ static bool __page_pool_page_can_be_recycled(const struct page *page) * If the page refcnt != 1, then the page will be returned to memory * subsystem. */ -static __always_inline struct page * -__page_pool_put_page(struct page_pool *pool, struct page *page, +static __always_inline netmem_ref +__page_pool_put_page(struct page_pool *pool, netmem_ref netmem, unsigned int dma_sync_size, bool allow_direct) { lockdep_assert_no_hardirq(); @@ -712,18 +722,18 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, * page is NOT reusable when allocated when system is under * some pressure. (page_is_pfmemalloc) */ - if (likely(__page_pool_page_can_be_recycled(page))) { + if (likely(__page_pool_page_can_be_recycled(netmem))) { /* Read barrier done in page_ref_count / READ_ONCE */

if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) - page_pool_dma_sync_for_device(pool, page, + page_pool_dma_sync_for_device(pool, netmem, dma_sync_size);

- if (allow_direct && page_pool_recycle_in_cache(page, pool)) - return NULL; + if (allow_direct && page_pool_recycle_in_cache(netmem, pool)) + return 0;

/* Page found as candidate for recycling */ - return page; + return netmem; } /* Fallback/non-XDP mode: API user have elevated refcnt. * @@ -739,9 +749,9 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, * will be invoking put_page. */ recycle_stat_inc(pool, released_refcnt); - page_pool_return_page(pool, page); + page_pool_return_page(pool, netmem);

- return NULL; + return 0; }

static bool page_pool_napi_local(const struct page_pool *pool) @@ -767,19 +777,28 @@ static bool page_pool_napi_local(const struct page_pool *pool) return napi && READ_ONCE(napi->list_owner) == cpuid; }

-void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, bool allow_direct) +void page_pool_put_unrefed_netmem(struct page_pool *pool, netmem_ref netmem, + unsigned int dma_sync_size, bool allow_direct) { if (!allow_direct) allow_direct = page_pool_napi_local(pool);

- page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct); - if (page && !page_pool_recycle_in_ring(pool, page)) { + netmem = + __page_pool_put_page(pool, netmem, dma_sync_size, allow_direct); + if (netmem && !page_pool_recycle_in_ring(pool, netmem)) { /* Cache full, fallback to free pages */ recycle_stat_inc(pool, ring_full); - page_pool_return_page(pool, page); + page_pool_return_page(pool, netmem); } } +EXPORT_SYMBOL(page_pool_put_unrefed_netmem); + +void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, bool allow_direct) +{ + page_pool_put_unrefed_netmem(pool, page_to_netmem(page), dma_sync_size, + allow_direct); +} EXPORT_SYMBOL(page_pool_put_unrefed_page);

/** @@ -807,16 +826,16 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, allow_direct = page_pool_napi_local(pool);

for (i = 0; i < count; i++) { - struct page *page = virt_to_head_page(data[i]); + netmem_ref netmem = page_to_netmem(virt_to_head_page(data[i]));

/* It is not the last user for the page frag case */ - if (!page_pool_is_last_ref(page)) + if (!page_pool_is_last_ref(netmem)) continue;

- page = __page_pool_put_page(pool, page, -1, allow_direct); + netmem = __page_pool_put_page(pool, netmem, -1, allow_direct); /* Approved for bulk recycling in ptr_ring cache */ - if (page) - data[bulk_len++] = page; + if (netmem) + data[bulk_len++] = (__force void *)netmem; }

if (!bulk_len) @@ -842,100 +861,108 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, * since put_page() with refcnt == 1 can be an expensive operation */ for (; i < bulk_len; i++) - page_pool_return_page(pool, data[i]); + page_pool_return_page(pool, (__force netmem_ref)data[i]); } EXPORT_SYMBOL(page_pool_put_page_bulk);

-static struct page *page_pool_drain_frag(struct page_pool *pool, - struct page *page) +static netmem_ref page_pool_drain_frag(struct page_pool *pool, + netmem_ref netmem) { long drain_count = BIAS_MAX - pool->frag_users;

/* Some user is still using the page frag */ - if (likely(page_pool_unref_page(page, drain_count))) - return NULL; + if (likely(page_pool_unref_netmem(netmem, drain_count))) + return 0;

- if (__page_pool_page_can_be_recycled(page)) { + if (__page_pool_page_can_be_recycled(netmem)) { if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) - page_pool_dma_sync_for_device(pool, page, -1); + page_pool_dma_sync_for_device(pool, netmem, -1);

- return page; + return netmem; }

- page_pool_return_page(pool, page); - return NULL; + page_pool_return_page(pool, netmem); + return 0; }

static void page_pool_free_frag(struct page_pool *pool) { long drain_count = BIAS_MAX - pool->frag_users; - struct page *page = pool->frag_page; + netmem_ref netmem = pool->frag_page;

- pool->frag_page = NULL; + pool->frag_page = 0;

- if (!page || page_pool_unref_page(page, drain_count)) + if (!netmem || page_pool_unref_netmem(netmem, drain_count)) return;

- page_pool_return_page(pool, page); + page_pool_return_page(pool, netmem); }

-struct page *page_pool_alloc_frag(struct page_pool *pool, - unsigned int *offset, - unsigned int size, gfp_t gfp) +netmem_ref page_pool_alloc_frag_netmem(struct page_pool *pool, + unsigned int *offset, unsigned int size, + gfp_t gfp) { unsigned int max_size = PAGE_SIZE << pool->p.order; - struct page *page = pool->frag_page; + netmem_ref netmem = pool->frag_page;

if (WARN_ON(size > max_size)) - return NULL; + return 0;

size = ALIGN(size, dma_get_cache_alignment()); *offset = pool->frag_offset;

- if (page && *offset + size > max_size) { - page = page_pool_drain_frag(pool, page); - if (page) { + if (netmem && *offset + size > max_size) { + netmem = page_pool_drain_frag(pool, netmem); + if (netmem) { alloc_stat_inc(pool, fast); goto frag_reset; } }

- if (!page) { - page = page_pool_alloc_pages(pool, gfp); - if (unlikely(!page)) { - pool->frag_page = NULL; - return NULL; + if (!netmem) { + netmem = page_pool_alloc_netmem(pool, gfp); + if (unlikely(!netmem)) { + pool->frag_page = 0; + return 0; }

- pool->frag_page = page; + pool->frag_page = netmem;

frag_reset: pool->frag_users = 1; *offset = 0; pool->frag_offset = size; - page_pool_fragment_page(page, BIAS_MAX); - return page; + page_pool_fragment_netmem(netmem, BIAS_MAX); + return netmem; }

pool->frag_users++; pool->frag_offset = *offset + size; alloc_stat_inc(pool, fast); - return page; + return netmem; +} +EXPORT_SYMBOL(page_pool_alloc_frag_netmem); + +struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset, + unsigned int size, gfp_t gfp) +{ + return netmem_to_page(page_pool_alloc_frag_netmem(pool, offset, size, + gfp)); } EXPORT_SYMBOL(page_pool_alloc_frag);

static void page_pool_empty_ring(struct page_pool *pool) { - struct page *page; + netmem_ref netmem;

/* Empty recycle ring */ - while ((page = ptr_ring_consume_bh(&pool->ring))) { + while ((netmem = (__force netmem_ref)ptr_ring_consume_bh(&pool->ring))) { /* Verify the refcnt invariant of cached pages */ - if (!(page_ref_count(page) == 1)) + if (!(page_ref_count(netmem_to_page(netmem)) == 1)) pr_crit("%s() page_pool refcnt %d violation\n", - __func__, page_ref_count(page)); + __func__, netmem_ref_count(netmem));

- page_pool_return_page(pool, page); + page_pool_return_page(pool, netmem); } }

@@ -957,7 +984,7 @@ static void __page_pool_destroy(struct page_pool *pool)

static void page_pool_empty_alloc_cache_once(struct page_pool *pool) { - struct page *page; + netmem_ref netmem;

if (pool->destroy_cnt) return; @@ -967,8 +994,8 @@ static void page_pool_empty_alloc_cache_once(struct page_pool *pool) * call concurrently. */ while (pool->alloc.count) { - page = pool->alloc.cache[--pool->alloc.count]; - page_pool_return_page(pool, page); + netmem = pool->alloc.cache[--pool->alloc.count]; + page_pool_return_page(pool, netmem); } }

@@ -1074,15 +1101,15 @@ EXPORT_SYMBOL(page_pool_destroy); /* Caller must provide appropriate safe context, e.g. NAPI. */ void page_pool_update_nid(struct page_pool *pool, int new_nid) { - struct page *page; + netmem_ref netmem;

trace_page_pool_update_nid(pool, new_nid); pool->p.nid = new_nid;

/* Flush pool alloc cache, as refill will check NUMA node */ while (pool->alloc.count) { - page = pool->alloc.cache[--pool->alloc.count]; - page_pool_return_page(pool, page); + netmem = pool->alloc.cache[--pool->alloc.count]; + page_pool_return_page(pool, netmem); } } EXPORT_SYMBOL(page_pool_update_nid); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 466999a7515e6..92d1748fef465 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1002,8 +1002,10 @@ int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, EXPORT_SYMBOL(skb_cow_data_for_xdp);

#if IS_ENABLED(CONFIG_PAGE_POOL) -bool napi_pp_put_page(struct page *page) +bool napi_pp_put_page(netmem_ref netmem) { + struct page *page = netmem_to_page(netmem); + page = compound_head(page);

/* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation @@ -1016,7 +1018,7 @@ bool napi_pp_put_page(struct page *page) if (unlikely(!is_pp_page(page))) return false;

- page_pool_put_full_page(page->pp, page, false); + page_pool_put_full_netmem(page->pp, page_to_netmem(page), false);

return true; } @@ -1027,7 +1029,7 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data) { if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) return false; - return napi_pp_put_page(virt_to_page(data)); + return napi_pp_put_page(page_to_netmem(virt_to_page(data))); }

/**

Implement a memory provider that allocates dmabuf devmem in the form of net_iov.

The provider receives a reference to the struct netdev_dmabuf_binding via the pool->mp_priv pointer. The driver needs to set this pointer for the provider in the net_iov.

The provider obtains a reference on the netdev_dmabuf_binding which guarantees the binding and the underlying mapping remains alive until the provider is destroyed.

Usage of PP_FLAG_DMA_MAP is required for this memory provide such that the page_pool can provide the driver with the dma-addrs of the devmem.

Support for PP_FLAG_DMA_SYNC_DEV is omitted for simplicity & p.order != 0.

Signed-off-by: Willem de Bruijn willemb@google.com Signed-off-by: Kaiyuan Zhang kaiyuanz@google.com Signed-off-by: Mina Almasry almasrymina@google.com

---

v8: - Use skb_frag_size instead of frag->bv_len to fix patch-by-patch build error

v6: - refactor new memory provider functions into net/core/devmem.c (Pavel)

v2: - Disable devmem for p.order != 0

v1: - static_branch check in page_is_page_pool_iov() (Willem & Paolo). - PP_DEVMEM -> PP_IOV (David). - Require PP_FLAG_DMA_MAP (Jakub).

--- include/net/netmem.h | 15 ++++++ include/net/page_pool/helpers.h | 22 +++++++++ include/net/page_pool/types.h | 2 + net/core/devmem.c | 83 +++++++++++++++++++++++++++++++++ net/core/page_pool.c | 38 +++++++-------- 5 files changed, 138 insertions(+), 22 deletions(-)

diff --git a/include/net/netmem.h b/include/net/netmem.h index 4534dee7ec39c..a4a87a46bb216 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -122,6 +122,21 @@ static inline struct page *netmem_to_page(netmem_ref netmem) return (__force struct page *)netmem; }

+static inline struct net_iov *netmem_to_net_iov(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + return (struct net_iov *)((__force unsigned long)netmem & + ~NET_IOV); + + DEBUG_NET_WARN_ON_ONCE(true); + return NULL; +} + +static inline netmem_ref net_iov_to_netmem(struct net_iov *niov) +{ + return (__force netmem_ref)((unsigned long)niov | NET_IOV); +} + static inline netmem_ref page_to_netmem(struct page *page) { return (__force netmem_ref)page; diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index f6f126914c6ee..16cca34b0e297 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -477,4 +477,26 @@ static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid) page_pool_update_nid(pool, new_nid); }

+static inline void page_pool_set_pp_info(struct page_pool *pool, + netmem_ref netmem) +{ + netmem_set_pp(netmem, pool); + netmem_or_pp_magic(netmem, PP_SIGNATURE); + + /* Ensuring all pages have been split into one fragment initially: + * page_pool_set_pp_info() is only called once for every page when it + * is allocated from the page allocator and page_pool_fragment_page() + * is dirtying the same cache line as the page->pp_magic above, so + * the overhead is negligible. + */ + page_pool_fragment_netmem(netmem, 1); + if (pool->has_init_callback) + pool->slow.init_callback(netmem, pool->slow.init_arg); +} + +static inline void page_pool_clear_pp_info(netmem_ref netmem) +{ + netmem_clear_pp_magic(netmem); + netmem_set_pp(netmem, NULL); +} #endif /* _NET_PAGE_POOL_HELPERS_H */ diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index c51e45b343f10..7813d0f71f5f6 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -141,6 +141,8 @@ struct pp_memory_provider_params { void *mp_priv; };

+extern const struct memory_provider_ops dmabuf_devmem_ops; + struct page_pool { struct page_pool_params_fast p;

diff --git a/net/core/devmem.c b/net/core/devmem.c index c455f1825daad..3da5630862290 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -155,6 +155,7 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, * the driver may read this config while it's creating its * rx-queues. * WRITE_ONCE() here to match the READ_ONCE() in the driver. */ + WRITE_ONCE(rxq->mp_params.mp_ops, &dmabuf_devmem_ops); WRITE_ONCE(rxq->mp_params.mp_priv, binding);

err = netdev_rx_queue_restart(dev, rxq_idx); @@ -291,3 +292,85 @@ int net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, return err; } #endif + +/*** "Dmabuf devmem memory provider" ***/ + +static int mp_dmabuf_devmem_init(struct page_pool *pool) +{ + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; + + if (!binding) + return -EINVAL; + + if (!(pool->p.flags & PP_FLAG_DMA_MAP)) + return -EOPNOTSUPP; + + if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) + return -EOPNOTSUPP; + + if (pool->p.order != 0) + return -E2BIG; + + net_devmem_dmabuf_binding_get(binding); + return 0; +} + +static netmem_ref mp_dmabuf_devmem_alloc_pages(struct page_pool *pool, + gfp_t gfp) +{ + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; + netmem_ref netmem; + struct net_iov *niov; + dma_addr_t dma_addr; + + niov = net_devmem_alloc_dmabuf(binding); + if (!niov) + return 0; + + dma_addr = net_iov_dma_addr(niov); + + netmem = net_iov_to_netmem(niov); + + page_pool_set_pp_info(pool, netmem); + + if (page_pool_set_dma_addr_netmem(netmem, dma_addr)) + goto err_free; + + pool->pages_state_hold_cnt++; + trace_page_pool_state_hold(pool, netmem, pool->pages_state_hold_cnt); + return netmem; + +err_free: + net_devmem_free_dmabuf(niov); + return 0; +} + +static void mp_dmabuf_devmem_destroy(struct page_pool *pool) +{ + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; + + net_devmem_dmabuf_binding_put(binding); +} + +static bool mp_dmabuf_devmem_release_page(struct page_pool *pool, + netmem_ref netmem) +{ + WARN_ON_ONCE(!netmem_is_net_iov(netmem)); + WARN_ON_ONCE(atomic_long_read(netmem_get_pp_ref_count_ref(netmem)) != + 1); + + page_pool_clear_pp_info(netmem); + + net_devmem_free_dmabuf(netmem_to_net_iov(netmem)); + + /* We don't want the page pool put_page()ing our net_iovs. */ + return false; +} + +const struct memory_provider_ops dmabuf_devmem_ops = { + .init = mp_dmabuf_devmem_init, + .destroy = mp_dmabuf_devmem_destroy, + .alloc_pages = mp_dmabuf_devmem_alloc_pages, + .release_page = mp_dmabuf_devmem_release_page, +}; +EXPORT_SYMBOL(dmabuf_devmem_ops); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 37994b58490d8..3fa30f7ca76a2 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -13,6 +13,7 @@

#include <net/page_pool/helpers.h> #include <net/xdp.h> +#include <net/netdev_rx_queue.h>

#include <linux/dma-direction.h> #include <linux/dma-mapping.h> @@ -21,12 +22,15 @@ #include <linux/poison.h> #include <linux/ethtool.h> #include <linux/netdevice.h> +#include <linux/genalloc.h> +#include <net/devmem.h>

#include <trace/events/page_pool.h>

#include "page_pool_priv.h"

DEFINE_STATIC_KEY_FALSE(page_pool_mem_providers); +EXPORT_SYMBOL(page_pool_mem_providers);

#define DEFER_TIME (msecs_to_jiffies(1000)) #define DEFER_WARN_INTERVAL (60 * HZ) @@ -179,7 +183,9 @@ static int page_pool_init(struct page_pool *pool, const struct page_pool_params *params, int cpuid) { + const struct memory_provider_ops *mp_ops = NULL; unsigned int ring_qsize = 1024; /* Default */ + void *mp_priv = NULL; int err;

memcpy(&pool->p, &params->fast, sizeof(pool->p)); @@ -252,6 +258,16 @@ static int page_pool_init(struct page_pool *pool, /* Driver calling page_pool_create() also call page_pool_destroy() */ refcount_set(&pool->user_cnt, 1);

+ if (pool->p.queue) { + mp_ops = READ_ONCE(pool->p.queue->mp_params.mp_ops); + mp_priv = READ_ONCE(pool->p.queue->mp_params.mp_priv); + } + + if (mp_ops && mp_priv) { + pool->mp_ops = mp_ops; + pool->mp_priv = mp_priv; + } + if (pool->mp_ops) { err = pool->mp_ops->init(pool); if (err) { @@ -445,28 +461,6 @@ static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem) return false; }

-static void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem) -{ - netmem_set_pp(netmem, pool); - netmem_or_pp_magic(netmem, PP_SIGNATURE); - - /* Ensuring all pages have been split into one fragment initially: - * page_pool_set_pp_info() is only called once for every page when it - * is allocated from the page allocator and page_pool_fragment_page() - * is dirtying the same cache line as the page->pp_magic above, so - * the overhead is negligible. - */ - page_pool_fragment_netmem(netmem, 1); - if (pool->has_init_callback) - pool->slow.init_callback(netmem, pool->slow.init_arg); -} - -static void page_pool_clear_pp_info(netmem_ref netmem) -{ - netmem_clear_pp_magic(netmem); - netmem_set_pp(netmem, NULL); -} - static struct page *__page_pool_alloc_page_order(struct page_pool *pool, gfp_t gfp) {

For device memory TCP, we expect the skb headers to be available in host memory for access, and we expect the skb frags to be in device memory and unaccessible to the host. We expect there to be no mixing and matching of device memory frags (unaccessible) with host memory frags (accessible) in the same skb.

Add a skb->devmem flag which indicates whether the frags in this skb are device memory frags or not.

__skb_fill_netmem_desc() now checks frags added to skbs for net_iov, and marks the skb as skb->devmem accordingly.

Add checks through the network stack to avoid accessing the frags of devmem skbs and avoid coalescing devmem skbs with non devmem skbs.

Signed-off-by: Willem de Bruijn willemb@google.com Signed-off-by: Kaiyuan Zhang kaiyuanz@google.com Signed-off-by: Mina Almasry almasrymina@google.com

---

v9: https://lore.kernel.org/netdev/20240403002053.2376017-11-almasrymina@google.... - change skb->readable to skb->unreadable (Pavel/David).

skb->readable was very complicated, because by default skbs are readable so the flag needed to be set to true in all code paths where new skbs were created or cloned. Forgetting to set skb->readable=true in some paths caused crashes.

Flip it to skb->unreadable so that the default 0 value works well, and we only need to set it to true when we add unreadable frags.

v6 - skb->dmabuf -> skb->readable (Pavel). Pavel's original suggestion was to remove the skb->dmabuf flag entirely, but when I looked into it closely, I found the issue that if we remove the flag we have to dereference the shinfo(skb) pointer to obtain the first frag, which can cause a performance regression if it dirties the cache line when the shinfo(skb) was not really needed. Instead, I converted the skb->dmabuf flag into a generic skb->readable flag which can be re-used by io_uring.

Changes in v1: - Rename devmem -> dmabuf (David). - Flip skb_frags_not_readable (Jakub).

--- include/linux/skbuff.h | 19 +++++++++++++++-- include/net/tcp.h | 5 +++-- net/core/datagram.c | 6 ++++++ net/core/gro.c | 5 ++++- net/core/skbuff.c | 48 ++++++++++++++++++++++++++++++++++++++++-- net/ipv4/tcp.c | 3 +++ net/ipv4/tcp_input.c | 13 +++++++++--- net/ipv4/tcp_output.c | 5 ++++- net/packet/af_packet.c | 4 ++-- 9 files changed, 95 insertions(+), 13 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0dcf1c5824415..e5eb49602c290 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -820,6 +820,8 @@ typedef unsigned char *sk_buff_data_t; * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) + * @unreadable: indicates that at least 1 of the fragments in this skb is + * unreadable. * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required @@ -1003,7 +1005,7 @@ struct sk_buff { #if IS_ENABLED(CONFIG_IP_SCTP) __u8 csum_not_inet:1; #endif - + __u8 unreadable:1; #if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS) __u16 tc_index; /* traffic control index */ #endif @@ -1794,6 +1796,12 @@ static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) __skb_zcopy_downgrade_managed(skb); }

+/* Return true if frags in this skb are readable by the host. */ +static inline bool skb_frags_readable(const struct sk_buff *skb) +{ + return !skb->unreadable; +} + static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; @@ -2510,10 +2518,17 @@ static inline void skb_len_add(struct sk_buff *skb, int delta) static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { - struct page *page = netmem_to_page(netmem); + struct page *page;

__skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size);

+ if (netmem_is_net_iov(netmem)) { + skb->unreadable = true; + return; + } + + page = netmem_to_page(netmem); + /* 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). diff --git a/include/net/tcp.h b/include/net/tcp.h index 8f63a163c7de9..4389e6a525801 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1059,7 +1059,7 @@ static inline int tcp_skb_mss(const struct sk_buff *skb)

static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb) { - return likely(!TCP_SKB_CB(skb)->eor); + return likely(!TCP_SKB_CB(skb)->eor && skb_frags_readable(skb)); }

static inline bool tcp_skb_can_collapse(const struct sk_buff *to, @@ -1067,7 +1067,8 @@ static inline bool tcp_skb_can_collapse(const struct sk_buff *to, { return likely(tcp_skb_can_collapse_to(to) && mptcp_skb_can_collapse(to, from) && - skb_pure_zcopy_same(to, from)); + skb_pure_zcopy_same(to, from) && + skb_frags_readable(to) == skb_frags_readable(from)); }

/* Events passed to congestion control interface */ diff --git a/net/core/datagram.c b/net/core/datagram.c index e614cfd8e14a5..b29f881df0e83 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -407,6 +407,9 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset, return 0; }

+ if (!skb_frags_readable(skb)) + goto short_copy; + /* Copy paged appendix. Hmm... why does this look so complicated? */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; @@ -619,6 +622,9 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, if (msg && msg->msg_ubuf && msg->sg_from_iter) return msg->sg_from_iter(sk, skb, from, length);

+ if (!skb_frags_readable(skb)) + return -EFAULT; + frag = skb_shinfo(skb)->nr_frags;

while (length && iov_iter_count(from)) { diff --git a/net/core/gro.c b/net/core/gro.c index 10fb2145bcb2b..e216e0faeb665 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -424,6 +424,9 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow) { struct skb_shared_info *pinfo = skb_shinfo(skb);

+ if (WARN_ON_ONCE(!skb_frags_readable(skb))) + return; + BUG_ON(skb->end - skb->tail < grow);

memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow); @@ -445,7 +448,7 @@ static void gro_try_pull_from_frag0(struct sk_buff *skb) { int grow = skb_gro_offset(skb) - skb_headlen(skb);

- if (grow > 0) + if (grow > 0 && skb_frags_readable(skb)) gro_pull_from_frag0(skb, grow); }

diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 99cf1ee73836d..7257bfbb8d2c2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1951,6 +1951,9 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) if (skb_shared(skb) || skb_unclone(skb, gfp_mask)) return -EINVAL;

+ if (!skb_frags_readable(skb)) + return -EFAULT; + if (!num_frags) goto release;

@@ -2124,6 +2127,9 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) unsigned int size; int headerlen;

+ if (!skb_frags_readable(skb)) + return NULL; + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL;

@@ -2462,6 +2468,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, struct sk_buff *n; int oldheadroom;

+ if (!skb_frags_readable(skb)) + return NULL; + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL;

@@ -2806,6 +2815,9 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta) */ int i, k, eat = (skb->tail + delta) - skb->end;

+ if (!skb_frags_readable(skb)) + return NULL; + if (eat > 0 || skb_cloned(skb)) { if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0, GFP_ATOMIC)) @@ -2959,6 +2971,9 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) to += copy; }

+ if (!skb_frags_readable(skb)) + goto fault; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *f = &skb_shinfo(skb)->frags[i]; @@ -3147,6 +3162,9 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, /* * then map the fragments */ + if (!skb_frags_readable(skb)) + return false; + for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];

@@ -3370,6 +3388,9 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) from += copy; }

+ if (!skb_frags_readable(skb)) + goto fault; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int end; @@ -3449,6 +3470,9 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, pos = copy; }

+ if (!skb_frags_readable(skb)) + return 0; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; @@ -3549,6 +3573,9 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, pos = copy; }

+ if (!skb_frags_readable(skb)) + return 0; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end;

@@ -4040,6 +4067,7 @@ static inline void skb_split_inside_header(struct sk_buff *skb, skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i];

skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags; + skb1->unreadable = skb->unreadable; skb_shinfo(skb)->nr_frags = 0; skb1->data_len = skb->data_len; skb1->len += skb1->data_len; @@ -4054,6 +4082,7 @@ static inline void skb_split_no_header(struct sk_buff *skb, { int i, k = 0; const int nfrags = skb_shinfo(skb)->nr_frags; + const int unreadable = skb->unreadable;

skb_shinfo(skb)->nr_frags = 0; skb1->len = skb1->data_len = skb->len - len; @@ -4087,6 +4116,12 @@ static inline void skb_split_no_header(struct sk_buff *skb, pos += size; } skb_shinfo(skb1)->nr_frags = k; + + if (skb_shinfo(skb)->nr_frags) + skb->unreadable = unreadable; + + if (skb_shinfo(skb1)->nr_frags) + skb1->unreadable = unreadable; }

/** @@ -4322,6 +4357,9 @@ unsigned int skb_seq_read(unsigned int consumed, const u8 **data, return block_limit - abs_offset; }

+ if (!skb_frags_readable(st->cur_skb)) + return 0; + if (st->frag_idx == 0 && !st->frag_data) st->stepped_offset += skb_headlen(st->cur_skb);

@@ -5934,7 +5972,10 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (to->pp_recycle != from->pp_recycle) return false;

- if (len <= skb_tailroom(to)) { + if (skb_frags_readable(from) != skb_frags_readable(to)) + return false; + + if (len <= skb_tailroom(to) && skb_frags_readable(from)) { if (len) BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); *delta_truesize = 0; @@ -6111,6 +6152,9 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len) if (!pskb_may_pull(skb, write_len)) return -ENOMEM;

+ if (!skb_frags_readable(skb)) + return -EFAULT; + if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0;

@@ -6790,7 +6834,7 @@ void skb_condense(struct sk_buff *skb) { if (skb->data_len) { if (skb->data_len > skb->end - skb->tail || - skb_cloned(skb)) + skb_cloned(skb) || !skb_frags_readable(skb)) return;

/* Nice, we can free page frag(s) right now */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7e7f32f95c684..843197c6ea3ea 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2154,6 +2154,9 @@ static int tcp_zerocopy_receive(struct sock *sk, skb = tcp_recv_skb(sk, seq, &offset); }

+ if (!skb_frags_readable(skb)) + break; + if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); zc->msg_flags |= TCP_CMSG_TS; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4ccfec4bb6248..3529a079e32d8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5342,6 +5342,9 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root, for (end_of_skbs = true; skb != NULL && skb != tail; skb = n) { n = tcp_skb_next(skb, list);

+ if (!skb_frags_readable(skb)) + goto skip_this; + /* No new bits? It is possible on ofo queue. */ if (!before(start, TCP_SKB_CB(skb)->end_seq)) { skb = tcp_collapse_one(sk, skb, list, root); @@ -5362,17 +5365,20 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root, break; }

- if (n && n != tail && mptcp_skb_can_collapse(skb, n) && + if (n && n != tail && skb_frags_readable(n) && + mptcp_skb_can_collapse(skb, n) && TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) { end_of_skbs = false; break; }

+skip_this: /* Decided to skip this, advance start seq. */ start = TCP_SKB_CB(skb)->end_seq; } if (end_of_skbs || - (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) + (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) || + !skb_frags_readable(skb)) return;

__skb_queue_head_init(&tmp); @@ -5414,7 +5420,8 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root, if (!skb || skb == tail || !mptcp_skb_can_collapse(nskb, skb) || - (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) + (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) || + !skb_frags_readable(skb)) goto end; if (skb_cmp_decrypted(skb, nskb)) goto end; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 95caf8aaa8bea..24afab8e4d0e5 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2344,7 +2344,8 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)

if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb) || - !skb_pure_zcopy_same(skb, next)) + !skb_pure_zcopy_same(skb, next) || + skb_frags_readable(skb) != skb_frags_readable(next)) return false;

len -= skb->len; @@ -3264,6 +3265,8 @@ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) return false; if (skb_cloned(skb)) return false; + if (!skb_frags_readable(skb)) + return false; /* Some heuristics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) return false; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8c6d3fbb4ed87..2dc1b18d3b7dc 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2156,7 +2156,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, } }

- snaplen = skb->len; + snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb);

res = run_filter(skb, sk, snaplen); if (!res) @@ -2276,7 +2276,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } }

- snaplen = skb->len; + snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb);

res = run_filter(skb, sk, snaplen); if (!res)

Add an interface for the user to notify the kernel that it is done reading the devmem dmabuf frags returned as cmsg. The kernel will drop the reference on the frags to make them available for reuse.

Signed-off-by: Willem de Bruijn willemb@google.com Signed-off-by: Kaiyuan Zhang kaiyuanz@google.com Signed-off-by: Mina Almasry almasrymina@google.com

---

v7: - Updated SO_DEVMEM_* uapi to use the next available entry (Arnd).

v6: - Squash in locking optimizations from edumazet@google.com. With his changes we lock the xarray once per sock_devmem_dontneed operation rather than once per frag.

Changes in v1: - devmemtoken -> dmabuf_token (David). - Use napi_pp_put_page() for refcounting (Yunsheng). - Fix build error with missing socket options on other asms.

--- arch/alpha/include/uapi/asm/socket.h | 1 + arch/mips/include/uapi/asm/socket.h | 1 + arch/parisc/include/uapi/asm/socket.h | 1 + arch/sparc/include/uapi/asm/socket.h | 1 + include/uapi/asm-generic/socket.h | 1 + include/uapi/linux/uio.h | 4 ++ net/core/sock.c | 61 +++++++++++++++++++++++++++ 7 files changed, 70 insertions(+)

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index ef4656a41058a..251b73c5481ea 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -144,6 +144,7 @@ #define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR #define SO_DEVMEM_DMABUF 79 #define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF +#define SO_DEVMEM_DONTNEED 80

#if !defined(__KERNEL__)

diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 414807d55e33f..8ab7582291abf 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -155,6 +155,7 @@ #define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR #define SO_DEVMEM_DMABUF 79 #define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF +#define SO_DEVMEM_DONTNEED 80

#if !defined(__KERNEL__)

diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 2b817efd45444..38fc0b188e084 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -136,6 +136,7 @@ #define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR #define SO_DEVMEM_DMABUF 79 #define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF +#define SO_DEVMEM_DONTNEED 80

#if !defined(__KERNEL__)

diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 00248fc689773..57084ed2f3c4e 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -137,6 +137,7 @@ #define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR #define SO_DEVMEM_DMABUF 0x0058 #define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF +#define SO_DEVMEM_DONTNEED 0x0059

#if !defined(__KERNEL__)

diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 25a2f5255f523..1acb77780f103 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -135,6 +135,7 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77

+#define SO_DEVMEM_DONTNEED 97 #define SO_DEVMEM_LINEAR 98 #define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR #define SO_DEVMEM_DMABUF 99 diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h index 3a22ddae376a2..d17f8fcd93ec9 100644 --- a/include/uapi/linux/uio.h +++ b/include/uapi/linux/uio.h @@ -33,6 +33,10 @@ struct dmabuf_cmsg { */ };

+struct dmabuf_token { + __u32 token_start; + __u32 token_count; +}; /* * UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1) */ diff --git a/net/core/sock.c b/net/core/sock.c index 8d6e638b5426d..2edb988259e8d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -124,6 +124,7 @@ #include <linux/netdevice.h> #include <net/protocol.h> #include <linux/skbuff.h> +#include <linux/skbuff_ref.h> #include <net/net_namespace.h> #include <net/request_sock.h> #include <net/sock.h> @@ -1049,6 +1050,62 @@ static int sock_reserve_memory(struct sock *sk, int bytes) return 0; }

+#ifdef CONFIG_PAGE_POOL +static noinline_for_stack int +sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen) +{ + unsigned int num_tokens, i, j, k, netmem_num = 0; + struct dmabuf_token *tokens; + netmem_ref netmems[16]; + int ret; + + if (sk->sk_type != SOCK_STREAM || sk->sk_protocol != IPPROTO_TCP) + return -EBADF; + + if (optlen % sizeof(struct dmabuf_token) || + optlen > sizeof(*tokens) * 128) + return -EINVAL; + + tokens = kvmalloc_array(128, sizeof(*tokens), GFP_KERNEL); + if (!tokens) + return -ENOMEM; + + num_tokens = optlen / sizeof(struct dmabuf_token); + if (copy_from_sockptr(tokens, optval, optlen)) + return -EFAULT; + + ret = 0; + + xa_lock_bh(&sk->sk_user_frags); + for (i = 0; i < num_tokens; i++) { + for (j = 0; j < tokens[i].token_count; j++) { + netmem_ref netmem = (__force netmem_ref)__xa_erase( + &sk->sk_user_frags, tokens[i].token_start + j); + + if (netmem && + !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) { + netmems[netmem_num++] = netmem; + if (netmem_num == ARRAY_SIZE(netmems)) { + xa_unlock_bh(&sk->sk_user_frags); + for (k = 0; k < netmem_num; k++) + WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); + netmem_num = 0; + xa_lock_bh(&sk->sk_user_frags); + } + ret++; + } + } + } + + xa_unlock_bh(&sk->sk_user_frags); + for (k = 0; k < netmem_num; k++) + WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); + + kvfree(tokens); + return ret; +} +#endif + void sockopt_lock_sock(struct sock *sk) { /* When current->bpf_ctx is set, the setsockopt is called from @@ -1200,6 +1257,10 @@ int sk_setsockopt(struct sock *sk, int level, int optname, ret = -EOPNOTSUPP; return ret; } +#ifdef CONFIG_PAGE_POOL + case SO_DEVMEM_DONTNEED: + return sock_devmem_dontneed(sk, optval, optlen); +#endif }

sockopt_lock_sock(sk);

Add documentation outlining the usage and details of devmem TCP.

Signed-off-by: Mina Almasry almasrymina@google.com

---

v9: https://lore.kernel.org/netdev/20240403002053.2376017-14-almasrymina@google.... - Bagas doc suggestions.

v8: - Applied docs suggestions (Randy). Thanks!

v7: - Applied docs suggestions (Jakub).

v2:

- Missing spdx (simon) - add to index.rst (simon)

--- Documentation/networking/devmem.rst | 258 ++++++++++++++++++++++++++++ Documentation/networking/index.rst | 1 + 2 files changed, 259 insertions(+) create mode 100644 Documentation/networking/devmem.rst

diff --git a/Documentation/networking/devmem.rst b/Documentation/networking/devmem.rst new file mode 100644 index 0000000000000..f32acfd62075d --- /dev/null +++ b/Documentation/networking/devmem.rst @@ -0,0 +1,258 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================= +Device Memory TCP +================= + + +Intro +===== + +Device memory TCP (devmem TCP) enables receiving data directly into device +memory (dmabuf). The feature is currently implemented for TCP sockets. + + +Opportunity +----------- + +A large number of data transfers have device memory as the source and/or +destination. Accelerators drastically increased the prevalence of such +transfers. Some examples include: + +- Distributed training, where ML accelerators, such as GPUs on different hosts, + exchange data. + +- Distributed raw block storage applications transfer large amounts of data with + remote SSDs. Much of this data does not require host processing. + +Typically the Device-to-Device data transfers in the network are implemented as +the following low-level operations: Device-to-Host copy, Host-to-Host network +transfer, and Host-to-Device copy. + +The flow involving host copies is suboptimal, especially for bulk data transfers, +and can put significant strains on system resources such as host memory +bandwidth and PCIe bandwidth. + +Devmem TCP optimizes this use case by implementing socket APIs that enable +the user to receive incoming network packets directly into device memory. + +Packet payloads go directly from the NIC to device memory. + +Packet headers go to host memory and are processed by the TCP/IP stack +normally. The NIC must support header split to achieve this. + +Advantages: + +- Alleviate host memory bandwidth pressure, compared to existing + network-transfer + device-copy semantics. + +- Alleviate PCIe bandwidth pressure, by limiting data transfer to the lowest + level of the PCIe tree, compared to the traditional path which sends data + through the root complex. + + +More Info +--------- + + slides, video + https://netdevconf.org/0x17/sessions/talk/device-memory-tcp.html + + patchset + [RFC PATCH v6 00/12] Device Memory TCP + https://lore.kernel.org/netdev/20240305020153.2787423-1-almasrymina@google.c... + + +Interface +========= + +Example +------- + +tools/testing/selftests/net/ncdevmem.c:do_server shows an example of setting up +the RX path of this API. + +NIC Setup +--------- + +Header split, flow steering, & RSS are required features for devmem TCP. + +Header split is used to split incoming packets into a header buffer in host +memory, and a payload buffer in device memory. + +Flow steering & RSS are used to ensure that only flows targeting devmem land on +an RX queue bound to devmem. + +Enable header split & flow steering:: + + # enable header split + ethtool -G eth1 tcp-data-split on + + + # enable flow steering + ethtool -K eth1 ntuple on + +Configure RSS to steer all traffic away from the target RX queue (queue 15 in +this example):: + + ethtool --set-rxfh-indir eth1 equal 15 + + +The user must bind a dmabuf to any number of RX queues on a given NIC using +the netlink API:: + + /* Bind dmabuf to NIC RX queue 15 */ + struct netdev_queue *queues; + queues = malloc(sizeof(*queues) * 1); + + queues[0]._present.type = 1; + queues[0]._present.idx = 1; + queues[0].type = NETDEV_RX_QUEUE_TYPE_RX; + queues[0].idx = 15; + + *ys = ynl_sock_create(&ynl_netdev_family, &yerr); + + req = netdev_bind_rx_req_alloc(); + netdev_bind_rx_req_set_ifindex(req, 1 /* ifindex */); + netdev_bind_rx_req_set_dmabuf_fd(req, dmabuf_fd); + __netdev_bind_rx_req_set_queues(req, queues, n_queue_index); + + rsp = netdev_bind_rx(*ys, req); + + dmabuf_id = rsp->dmabuf_id; + + +The netlink API returns a dmabuf_id: a unique ID that refers to this dmabuf +that has been bound. + +Socket Setup +------------ + +The socket must be flow steered to the dmabuf bound RX queue:: + + ethtool -N eth1 flow-type tcp4 ... queue 15, + + +Receiving data +-------------- + +The user application must signal to the kernel that it is capable of receiving +devmem data by passing the MSG_SOCK_DEVMEM flag to recvmsg:: + + ret = recvmsg(fd, &msg, MSG_SOCK_DEVMEM); + +Applications that do not specify the MSG_SOCK_DEVMEM flag will receive an EFAULT +on devmem data. + +Devmem data is received directly into the dmabuf bound to the NIC in 'NIC +Setup', and the kernel signals such to the user via the SCM_DEVMEM_* cmsgs:: + + for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) { + if (cm->cmsg_level != SOL_SOCKET || + (cm->cmsg_type != SCM_DEVMEM_DMABUF && + cm->cmsg_type != SCM_DEVMEM_LINEAR)) + continue; + + dmabuf_cmsg = (struct dmabuf_cmsg *)CMSG_DATA(cm); + + if (cm->cmsg_type == SCM_DEVMEM_DMABUF) { + /* Frag landed in dmabuf. + * + * dmabuf_cmsg->dmabuf_id is the dmabuf the + * frag landed on. + * + * dmabuf_cmsg->frag_offset is the offset into + * the dmabuf where the frag starts. + * + * dmabuf_cmsg->frag_size is the size of the + * frag. + * + * dmabuf_cmsg->frag_token is a token used to + * refer to this frag for later freeing. + */ + + struct dmabuf_token token; + token.token_start = dmabuf_cmsg->frag_token; + token.token_count = 1; + continue; + } + + if (cm->cmsg_type == SCM_DEVMEM_LINEAR) + /* Frag landed in linear buffer. + * + * dmabuf_cmsg->frag_size is the size of the + * frag. + */ + continue; + + } + +Applications may receive 2 cmsgs: + +- SCM_DEVMEM_DMABUF: this indicates the fragment landed in the dmabuf indicated + by dmabuf_id. + +- SCM_DEVMEM_LINEAR: this indicates the fragment landed in the linear buffer. + This typically happens when the NIC is unable to split the packet at the + header boundary, such that part (or all) of the payload landed in host + memory. + +Applications may receive no SO_DEVMEM_* cmsgs. That indicates non-devmem, +regular TCP data that landed on an RX queue not bound to a dmabuf. + + +Freeing frags +------------- + +Frags received via SCM_DEVMEM_DMABUF are pinned by the kernel while the user +processes the frag. The user must return the frag to the kernel via +SO_DEVMEM_DONTNEED:: + + ret = setsockopt(client_fd, SOL_SOCKET, SO_DEVMEM_DONTNEED, &token, + sizeof(token)); + +The user must ensure the tokens are returned to the kernel in a timely manner. +Failure to do so will exhaust the limited dmabuf that is bound to the RX queue +and will lead to packet drops. + + +Implementation & Caveats +======================== + +Unreadable skbs +--------------- + +Devmem payloads are inaccessible to the kernel processing the packets. This +results in a few quirks for payloads of devmem skbs: + +- Loopback is not functional. Loopback relies on copying the payload, which is + not possible with devmem skbs. + +- Software checksum calculation fails. + +- TCP Dump and bpf can't access devmem packet payloads. + + +Testing +======= + +More realistic example code can be found in the kernel source under +tools/testing/selftests/net/ncdevmem.c + +ncdevmem is a devmem TCP netcat. It works very similarly to netcat, but +receives data directly into a udmabuf. + +To run ncdevmem, you need to run it on a server on the machine under test, and +you need to run netcat on a peer to provide the TX data. + +ncdevmem has a validation mode as well that expects a repeating pattern of +incoming data and validates it as such. For example, you can launch +ncdevmem on the server by:: + + ncdevmem -s <server IP> -c <client IP> -f eth1 -d 3 -n 0000:06:00.0 -l \ + -p 5201 -v 7 + +On client side, use regular netcat to send TX data to ncdevmem process +on the server:: + + yes $(echo -e \x01\x02\x03\x04\x05\x06) | \ + tr \n \0 | head -c 5G | nc <server IP> 5201 -p 5201 diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index 7664c0bfe461c..64e8ae22520ad 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -48,6 +48,7 @@ Contents: cdc_mbim dccp dctcp + devmem dns_resolver driver eql