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.

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 5e43a08d3231..ffe5f31fb0da 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 dd364d738c00..795b7ff1c01f 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -25,6 +25,8 @@

#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)

@@ -177,6 +179,7 @@ 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)); @@ -248,10 +251,25 @@ 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) @@ -546,7 +564,10 @@ 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); @@ -603,10 +624,13 @@ 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. @@ -614,7 +638,10 @@ 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). @@ -889,6 +916,12 @@ 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

---

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 | 303 ++++++++++++++++++++++++ net/core/netdev-genl-gen.c | 4 + net/core/netdev-genl-gen.h | 4 + net/core/netdev-genl.c | 105 +++++++- 11 files changed, 550 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 275d1faa87a6..bf4e58dfe9dd 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -550,6 +550,10 @@ 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 000000000000..fa03bdabdffd --- /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 aa1716fb0e53..f0d093f72a2c 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 d8b810245c1d..72e932a1a948 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 ffe5f31fb0da..07e6afafedbe 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 21d6fbc7e884..f5b7bfaba097 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 818699dea9d7..7ef8def6ec43 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -157,6 +157,9 @@ #include <net/page_pool/types.h> #include <net/page_pool/helpers.h> #include <net/rps.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 000000000000..02a6abaecf40 --- /dev/null +++ b/net/core/devmem.c @@ -0,0 +1,303 @@ +// 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); +} + +static int net_devmem_restart_rx_queue(struct net_device *dev, int rxq_idx) +{ + void *new_mem; + void *old_mem; + int err; + + if (!dev->queue_mgmt_ops->ndo_queue_stop || + !dev->queue_mgmt_ops->ndo_queue_mem_free || + !dev->queue_mgmt_ops->ndo_queue_mem_alloc || + !dev->queue_mgmt_ops->ndo_queue_start) + return -EOPNOTSUPP; + + new_mem = dev->queue_mgmt_ops->ndo_queue_mem_alloc(dev, rxq_idx); + if (!new_mem) + return -ENOMEM; + + err = dev->queue_mgmt_ops->ndo_queue_stop(dev, rxq_idx, &old_mem); + if (err) + goto err_free_new_mem; + + err = dev->queue_mgmt_ops->ndo_queue_start(dev, rxq_idx, new_mem); + if (err) + goto err_start_queue; + + dev->queue_mgmt_ops->ndo_queue_mem_free(dev, old_mem); + + return 0; + +err_start_queue: + /* Restarting the queue with old_mem should be successful as we haven't + * changed any of the queue configuration, and there is not much we can + * do to recover from a failure here. + * + * WARN if the we fail to recover the old rx queue, and at least free + * old_mem so we don't also leak that. + */ + if (dev->queue_mgmt_ops->ndo_queue_start(dev, rxq_idx, old_mem)) { + WARN(1, + "Failed to restart old queue in error path. RX queue %d may be unhealthy.", + rxq_idx); + dev->queue_mgmt_ops->ndo_queue_mem_free(dev, &old_mem); + } + +err_free_new_mem: + dev->queue_mgmt_ops->ndo_queue_mem_free(dev, new_mem); + + return err; +} + +/* 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); + + net_devmem_restart_rx_queue(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 = net_devmem_restart_rx_queue(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 bbaaa1b36b5b..da65595750fd 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 = { @@ -186,4 +187,7 @@ 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 ca5a0983f283..2c431b7dcbc8 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 67711d29d0d4..38b2fe090adc 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" @@ -674,10 +675,96 @@ 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, @@ -724,3 +811,17 @@ 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); +}

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

---

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.h | 6 +- include/net/netmem.h | 15 ++ include/net/page_pool/helpers.h | 122 +++++++++---- 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 | 7 +- 8 files changed, 304 insertions(+), 201 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b7f1ecdaec38..c9659e9d843e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3510,13 +3510,13 @@ int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog); -bool napi_pp_put_page(struct page *page, bool napi_safe); +bool napi_pp_put_page(netmem_ref netmem, bool napi_safe);

static inline void skb_page_unref(const struct sk_buff *skb, struct page *page, bool napi_safe) { #ifdef CONFIG_PAGE_POOL - if (skb->pp_recycle && napi_pp_put_page(page, napi_safe)) + if (skb->pp_recycle && napi_pp_put_page(page_to_netmem(page), napi_safe)) return; #endif put_page(page); @@ -3528,7 +3528,7 @@ napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe) struct page *page = skb_frag_page(frag);

#ifdef CONFIG_PAGE_POOL - if (recycle && napi_pp_put_page(page, napi_safe)) + if (recycle && napi_pp_put_page(page_to_netmem(page), napi_safe)) return; #endif put_page(page); diff --git a/include/net/netmem.h b/include/net/netmem.h index 33014370a885..5f1c728618f2 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 1d397c1a0043..61814f91a458 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -53,6 +53,8 @@ #define _NET_PAGE_POOL_HELPERS_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 */ @@ -101,7 +103,7 @@ 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, @@ -112,22 +114,22 @@ 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 @@ -138,7 +140,7 @@ static inline struct page *page_pool_alloc(struct page_pool *pool, pool->frag_offset = max_size; }

- return page; + return netmem; }

/** @@ -152,7 +154,7 @@ 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, @@ -160,7 +162,7 @@ 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, @@ -170,9 +172,10 @@ 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; + return 0;

return page_address(page) + offset; } @@ -187,7 +190,7 @@ 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) @@ -210,6 +213,11 @@ inline enum dma_data_direction page_pool_get_dma_dir(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 @@ -230,11 +238,12 @@ inline enum dma_data_direction page_pool_get_dma_dir(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 @@ -277,15 +286,41 @@ 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 }

/** @@ -306,15 +341,15 @@ 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); }

/** @@ -329,7 +364,7 @@ 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); }

/** @@ -363,6 +398,18 @@ 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 @@ -372,16 +419,14 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va, */ 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;

@@ -395,6 +440,11 @@ static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr) return false; }

+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 07e6afafedbe..f04af1613f59 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 6834356b2d2a..c5b6383ff276 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 61efeadaff8d..fc300e807e1d 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 795b7ff1c01f..c8125be3a6e2 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -329,19 +329,18 @@ 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, @@ -356,56 +355,56 @@ 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(struct page_pool *pool, - struct page *page, + 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, @@ -413,7 +412,7 @@ static void page_pool_dma_sync_for_device(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;

@@ -422,18 +421,18 @@ 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;

@@ -445,9 +444,10 @@ 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;

@@ -457,13 +457,15 @@ 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; } @@ -479,34 +481,34 @@ 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)) @@ -515,60 +517,67 @@ 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);

@@ -596,8 +605,8 @@ 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;

@@ -607,13 +616,13 @@ 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 @@ -621,26 +630,26 @@ 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 @@ -648,14 +657,14 @@ 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); @@ -670,7 +679,7 @@ 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)) { @@ -679,14 +688,15 @@ 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. @@ -695,8 +705,8 @@ 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(); @@ -710,19 +720,19 @@ __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 && in_softirq() && - page_pool_recycle_in_cache(page, pool)) - return NULL; + 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. * @@ -738,21 +748,30 @@ __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; }

-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) { - 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);

/** @@ -777,16 +796,16 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, bool in_softirq;

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

if (unlikely(!bulk_len)) @@ -812,100 +831,108 @@ 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); } }

@@ -927,7 +954,7 @@ 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; @@ -937,8 +964,8 @@ 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); } }

@@ -1044,15 +1071,15 @@ 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 a1be84be5d35..dc6b1f6435e2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1004,8 +1004,9 @@ 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_safe) +bool napi_pp_put_page(netmem_ref netmem, bool napi_safe) { + struct page *page = netmem_to_page(netmem); bool allow_direct = false; struct page_pool *pp;

@@ -1042,7 +1043,7 @@ bool napi_pp_put_page(struct page *page, bool napi_safe) * The page will be returned to the pool here regardless of the * 'flipped' fragment being in use or not. */ - page_pool_put_full_page(pp, page, allow_direct); + page_pool_put_full_netmem(pp, page_to_netmem(page), allow_direct);

return true; } @@ -1053,7 +1054,7 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data, bool napi_safe) { if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) return false; - return napi_pp_put_page(virt_to_page(data), napi_safe); + return napi_pp_put_page(page_to_netmem(virt_to_page(data)), napi_safe); }

/**

Convert netmem to be a union of struct page and struct netmem. Overload the LSB of struct netmem* to indicate that it's a net_iov, otherwise it's a page.

Currently these entries in struct page are rented by the page_pool and used exclusively by the net stack:

struct { unsigned long pp_magic; struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; atomic_long_t pp_ref_count; };

Mirror these (and only these) entries into struct net_iov and implement netmem helpers that can access these common fields regardless of whether the underlying type is page or net_iov.

Implement checks for net_iov in netmem helpers which delegate to mm APIs, to ensure net_iov are never passed to the mm stack.

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

---

v7: - Remove static_branch_unlikely from netmem_to_net_iov(). We're getting better results from the fast path in bench_page_pool_simple tests without the static_branch_unlikely, and the addition of static_branch_unlikely doesn't improve performance of devmem TCP.

Additionally only check netmem_to_net_iov() if CONFIG_DMA_SHARED_BUFFER is enabled, otherwise dmabuf net_iovs cannot exist anyway.

net-next base: 8 cycle fast path. with static_branch_unlikely: 10 cycle fast path. without static_branch_unlikely: 9 cycle fast path. CONFIG_DMA_SHARED_BUFFER disabled: 8 cycle fast path as baseline.

Performance of devmem TCP is at 95% line rate is regardless of static_branch_unlikely or not.

v6: - Rebased on top of the merged netmem_ref type. - Rebased on top of the merged skb_pp_frag_ref() changes.

v5: - Use netmem instead of page* with LSB set. - Use pp_ref_count for refcounting net_iov. - Removed many of the custom checks for netmem.

v1: - Disable fragmentation support for iov properly. - fix napi_pp_put_page() path (Yunsheng). - Use pp_frag_count for devmem refcounting.

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

--- include/net/netmem.h | 141 ++++++++++++++++++++++++++++++-- include/net/page_pool/helpers.h | 25 +++--- net/core/devmem.c | 3 + net/core/page_pool.c | 26 +++--- net/core/skbuff.c | 23 +++--- 5 files changed, 172 insertions(+), 46 deletions(-)

diff --git a/include/net/netmem.h b/include/net/netmem.h index 5f1c728618f2..74eeaa34883e 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -9,14 +9,51 @@ #define _NET_NETMEM_H

#include <net/devmem.h> +#include <net/net_debug.h>

/* net_iov */

+DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers); + +/* We overload the LSB of the struct page pointer to indicate whether it's + * a page or net_iov. + */ +#define NET_IOV 0x01UL + struct net_iov { + unsigned long __unused_padding; + unsigned long pp_magic; + struct page_pool *pp; struct dmabuf_genpool_chunk_owner *owner; unsigned long dma_addr; + atomic_long_t pp_ref_count; };

+/* These fields in struct page are used by the page_pool and net stack: + * + * struct { + * unsigned long pp_magic; + * struct page_pool *pp; + * unsigned long _pp_mapping_pad; + * unsigned long dma_addr; + * atomic_long_t pp_ref_count; + * }; + * + * We mirror the page_pool fields here so the page_pool can access these fields + * without worrying whether the underlying fields belong to a page or net_iov. + * + * The non-net stack fields of struct page are private to the mm stack and must + * never be mirrored to net_iov. + */ +#define NET_IOV_ASSERT_OFFSET(pg, iov) \ + static_assert(offsetof(struct page, pg) == \ + offsetof(struct net_iov, iov)) +NET_IOV_ASSERT_OFFSET(pp_magic, pp_magic); +NET_IOV_ASSERT_OFFSET(pp, pp); +NET_IOV_ASSERT_OFFSET(dma_addr, dma_addr); +NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count); +#undef NET_IOV_ASSERT_OFFSET + static inline struct dmabuf_genpool_chunk_owner * net_iov_owner(const struct net_iov *niov) { @@ -69,20 +106,26 @@ net_iov_binding(const struct net_iov *niov) */ typedef unsigned long __bitwise netmem_ref;

+static inline bool netmem_is_net_iov(const netmem_ref netmem) +{ +#if defined(CONFIG_PAGE_POOL) && defined(CONFIG_DMA_SHARED_BUFFER) + return (__force unsigned long)netmem & NET_IOV; +#else + return false; +#endif +} + /* This conversion fails (returns NULL) if the netmem_ref is not struct page * backed. - * - * Currently struct page is the only possible netmem, and this helper never - * fails. */ static inline struct page *netmem_to_page(netmem_ref netmem) { + if (WARN_ON_ONCE(netmem_is_net_iov(netmem))) + return NULL; + return (__force struct page *)netmem; }

-/* Converting from page to netmem is always safe, because a page can always be - * a netmem. - */ static inline netmem_ref page_to_netmem(struct page *page) { return (__force netmem_ref)page; @@ -90,17 +133,103 @@ static inline netmem_ref page_to_netmem(struct page *page)

static inline int netmem_ref_count(netmem_ref netmem) { + /* The non-pp refcount of net_iov is always 1. On net_iov, we only + * support pp refcounting which uses the pp_ref_count field. + */ + if (netmem_is_net_iov(netmem)) + return 1; + return page_ref_count(netmem_to_page(netmem)); }

static inline unsigned long netmem_to_pfn(netmem_ref netmem) { + if (netmem_is_net_iov(netmem)) + return 0; + return page_to_pfn(netmem_to_page(netmem)); }

+static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem) +{ + return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV); +} + +static inline unsigned long netmem_get_pp_magic(netmem_ref netmem) +{ + return __netmem_clear_lsb(netmem)->pp_magic; +} + +static inline void netmem_or_pp_magic(netmem_ref netmem, unsigned long pp_magic) +{ + __netmem_clear_lsb(netmem)->pp_magic |= pp_magic; +} + +static inline void netmem_clear_pp_magic(netmem_ref netmem) +{ + __netmem_clear_lsb(netmem)->pp_magic = 0; +} + +static inline struct page_pool *netmem_get_pp(netmem_ref netmem) +{ + return __netmem_clear_lsb(netmem)->pp; +} + +static inline void netmem_set_pp(netmem_ref netmem, struct page_pool *pool) +{ + __netmem_clear_lsb(netmem)->pp = pool; +} + +static inline unsigned long netmem_get_dma_addr(netmem_ref netmem) +{ + return __netmem_clear_lsb(netmem)->dma_addr; +} + +static inline void netmem_set_dma_addr(netmem_ref netmem, + unsigned long dma_addr) +{ + __netmem_clear_lsb(netmem)->dma_addr = dma_addr; +} + +static inline atomic_long_t *netmem_get_pp_ref_count_ref(netmem_ref netmem) +{ + return &__netmem_clear_lsb(netmem)->pp_ref_count; +} + +static inline bool netmem_is_pref_nid(netmem_ref netmem, int pref_nid) +{ + /* Assume net_iov are on the preferred node without actually + * checking... + * + * This check is only used to check for recycling memory in the page + * pool's fast paths. Currently the only implementation of net_iov + * is dmabuf device memory. It's a deliberate decision by the user to + * bind a certain dmabuf to a certain netdev, and the netdev rx queue + * would not be able to reallocate memory from another dmabuf that + * exists on the preferred node, so, this check doesn't make much sense + * in this case. Assume all net_iovs can be recycled for now. + */ + if (netmem_is_net_iov(netmem)) + return true; + + return page_to_nid(netmem_to_page(netmem)) == pref_nid; +} + static inline netmem_ref netmem_compound_head(netmem_ref netmem) { + /* niov are never compounded */ + if (netmem_is_net_iov(netmem)) + return netmem; + return page_to_netmem(compound_head(netmem_to_page(netmem))); }

+static inline void *netmem_address(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + return NULL; + + return page_address(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 61814f91a458..c6a55eddefae 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -215,7 +215,7 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)

static inline void page_pool_fragment_netmem(netmem_ref netmem, long nr) { - atomic_long_set(&netmem_to_page(netmem)->pp_ref_count, nr); + atomic_long_set(netmem_get_pp_ref_count_ref(netmem), nr); }

/** @@ -243,7 +243,7 @@ static inline void page_pool_fragment_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); + atomic_long_t *pp_ref_count = netmem_get_pp_ref_count_ref(netmem); long ret;

/* If nr == pp_ref_count then we have cleared all remaining @@ -260,19 +260,19 @@ static inline long page_pool_unref_netmem(netmem_ref netmem, long nr) * initially, and only overwrite it when the page is partitioned into * more than one piece. */ - if (atomic_long_read(&page->pp_ref_count) == nr) { + if (atomic_long_read(pp_ref_count) == nr) { /* As we have ensured nr is always one for constant case using * the BUILD_BUG_ON(), only need to handle the non-constant case * here for pp_ref_count draining, which is a rare case. */ BUILD_BUG_ON(__builtin_constant_p(nr) && nr != 1); if (!__builtin_constant_p(nr)) - atomic_long_set(&page->pp_ref_count, 1); + atomic_long_set(pp_ref_count, 1);

return 0; }

- ret = atomic_long_sub_return(nr, &page->pp_ref_count); + ret = atomic_long_sub_return(nr, pp_ref_count); WARN_ON(ret < 0);

/* We are the last user here too, reset pp_ref_count back to 1 to @@ -281,7 +281,7 @@ static inline long page_pool_unref_netmem(netmem_ref netmem, long nr) * page_pool_unref_page() currently. */ if (unlikely(!ret)) - atomic_long_set(&page->pp_ref_count, 1); + atomic_long_set(pp_ref_count, 1);

return ret; } @@ -400,9 +400,7 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va,

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; + dma_addr_t ret = netmem_get_dma_addr(netmem);

if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) ret <<= PAGE_SHIFT; @@ -425,18 +423,17 @@ static inline dma_addr_t page_pool_get_dma_addr(struct page *page) 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; + netmem_set_dma_addr(netmem, addr >> PAGE_SHIFT);

/* We assume page alignment to shave off bottom bits, * if this "compression" doesn't work we need to drop. */ - return addr != (dma_addr_t)page->dma_addr << PAGE_SHIFT; + return addr != (dma_addr_t)netmem_get_dma_addr(netmem) + << PAGE_SHIFT; }

- page->dma_addr = addr; + netmem_set_dma_addr(netmem, addr); return false; }

diff --git a/net/core/devmem.c b/net/core/devmem.c index 268fc8455a6d..c25ede5f6fb9 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -121,7 +121,10 @@ net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding) index = offset / PAGE_SIZE; niov = &owner->niovs[index];

+ niov->pp_magic = 0; + niov->pp = NULL; niov->dma_addr = 0; + atomic_long_set(&niov->pp_ref_count, 0);

net_devmem_dmabuf_binding_get(binding);

diff --git a/net/core/page_pool.c b/net/core/page_pool.c index c8125be3a6e2..c7bffd08218b 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -25,7 +25,7 @@

#include "page_pool_priv.h"

-static DEFINE_STATIC_KEY_FALSE(page_pool_mem_providers); +DEFINE_STATIC_KEY_FALSE(page_pool_mem_providers);

#define DEFER_TIME (msecs_to_jiffies(1000)) #define DEFER_WARN_INTERVAL (60 * HZ) @@ -359,7 +359,7 @@ static noinline netmem_ref page_pool_refill_alloc_cache(struct page_pool *pool) if (unlikely(!netmem)) break;

- if (likely(page_to_nid(netmem_to_page(netmem)) == pref_nid)) { + if (likely(netmem_is_pref_nid(netmem, pref_nid))) { pool->alloc.cache[pool->alloc.count++] = netmem; } else { /* NUMA mismatch; @@ -446,10 +446,8 @@ static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem)

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; + 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 @@ -464,10 +462,8 @@ static void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem)

static void page_pool_clear_pp_info(netmem_ref netmem) { - struct page *page = netmem_to_page(netmem); - - page->pp_magic = 0; - page->pp = NULL; + netmem_clear_pp_magic(netmem); + netmem_set_pp(netmem, NULL); }

static struct page *__page_pool_alloc_page_order(struct page_pool *pool, @@ -695,8 +691,9 @@ static bool page_pool_recycle_in_cache(netmem_ref netmem,

static bool __page_pool_page_can_be_recycled(netmem_ref netmem) { - return page_ref_count(netmem_to_page(netmem)) == 1 && - !page_is_pfmemalloc(netmem_to_page(netmem)); + return netmem_is_net_iov(netmem) || + (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. @@ -718,7 +715,7 @@ __page_pool_put_page(struct page_pool *pool, netmem_ref netmem, * refcnt == 1 means page_pool owns page, and can recycle it. * * page is NOT reusable when allocated when system is under - * some pressure. (page_is_pfmemalloc) + * some pressure. (page_pool_page_is_pfmemalloc) */ if (likely(__page_pool_page_can_be_recycled(netmem))) { /* Read barrier done in page_ref_count / READ_ONCE */ @@ -734,6 +731,7 @@ __page_pool_put_page(struct page_pool *pool, netmem_ref netmem, /* Page found as candidate for recycling */ return netmem; } + /* Fallback/non-XDP mode: API user have elevated refcnt. * * Many drivers split up the page into fragments, and some @@ -928,7 +926,7 @@ static void page_pool_empty_ring(struct page_pool *pool) /* Empty recycle ring */ while ((netmem = (__force netmem_ref)ptr_ring_consume_bh(&pool->ring))) { /* Verify the refcnt invariant of cached pages */ - if (!(page_ref_count(netmem_to_page(netmem)) == 1)) + if (!(netmem_ref_count(netmem) == 1)) pr_crit("%s() page_pool refcnt %d violation\n", __func__, netmem_ref_count(netmem));

diff --git a/net/core/skbuff.c b/net/core/skbuff.c index dc6b1f6435e2..753d61680d69 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -906,9 +906,9 @@ static void skb_clone_fraglist(struct sk_buff *skb) skb_get(list); }

-static bool is_pp_page(struct page *page) +static bool is_pp_netmem(netmem_ref netmem) { - return (page->pp_magic & ~0x3UL) == PP_SIGNATURE; + return (netmem_get_pp_magic(netmem) & ~0x3UL) == PP_SIGNATURE; }

int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, @@ -1006,11 +1006,10 @@ EXPORT_SYMBOL(skb_cow_data_for_xdp); #if IS_ENABLED(CONFIG_PAGE_POOL) bool napi_pp_put_page(netmem_ref netmem, bool napi_safe) { - struct page *page = netmem_to_page(netmem); bool allow_direct = false; struct page_pool *pp;

- page = compound_head(page); + netmem = netmem_compound_head(netmem);

/* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation * in order to preserve any existing bits, such as bit 0 for the @@ -1019,10 +1018,10 @@ bool napi_pp_put_page(netmem_ref netmem, bool napi_safe) * and page_is_pfmemalloc() is checked in __page_pool_put_page() * to avoid recycling the pfmemalloc page. */ - if (unlikely(!is_pp_page(page))) + if (unlikely(!is_pp_netmem(netmem))) return false;

- pp = page->pp; + pp = netmem_get_pp(netmem);

/* Allow direct recycle if we have reasons to believe that we are * in the same context as the consumer would run, so there's @@ -1043,7 +1042,7 @@ bool napi_pp_put_page(netmem_ref netmem, bool napi_safe) * The page will be returned to the pool here regardless of the * 'flipped' fragment being in use or not. */ - page_pool_put_full_netmem(pp, page_to_netmem(page), allow_direct); + page_pool_put_full_netmem(pp, netmem, allow_direct);

return true; } @@ -1070,7 +1069,7 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data, bool napi_safe) static int skb_pp_frag_ref(struct sk_buff *skb) { struct skb_shared_info *shinfo; - struct page *head_page; + netmem_ref head_netmem; int i;

if (!skb->pp_recycle) @@ -1079,11 +1078,11 @@ static int skb_pp_frag_ref(struct sk_buff *skb) shinfo = skb_shinfo(skb);

for (i = 0; i < shinfo->nr_frags; i++) { - head_page = compound_head(skb_frag_page(&shinfo->frags[i])); - if (likely(is_pp_page(head_page))) - page_pool_ref_page(head_page); + head_netmem = netmem_compound_head(shinfo->frags[i].netmem); + if (likely(is_pp_netmem(head_netmem))) + page_pool_ref_netmem(head_netmem); else - page_ref_inc(head_page); + page_ref_inc(netmem_to_page(head_netmem)); } return 0; }

Make skb_frag_page() fail in the case where the frag is not backed by a page, and fix its relevant callers to handle this case.

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

---

v6: - Rebased on top of the merged netmem changes.

Changes in v1: - Fix illegal_highdma() (Yunsheng). - Rework napi_pp_put_page() slightly to reduce code churn (Willem).

--- include/linux/skbuff.h | 53 +++++++++++++++++++++++++++++++++++------- net/core/dev.c | 3 ++- net/core/gro.c | 3 ++- net/core/skbuff.c | 11 +++++++++ net/ipv4/esp4.c | 2 +- net/ipv4/tcp.c | 3 +++ net/ipv6/esp6.c | 2 +- 7 files changed, 65 insertions(+), 12 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c9659e9d843e..fb4c2cf441f4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3472,17 +3472,53 @@ static inline void skb_frag_off_copy(skb_frag_t *fragto, fragto->offset = fragfrom->offset; }

+/* Returns true if the skb_frag contains a net_iov. */ +static inline bool skb_frag_is_net_iov(const skb_frag_t *frag) +{ + return netmem_is_net_iov(frag->netmem); +} + +/** + * skb_frag_net_iov - retrieve the net_iov referred to by fragment + * @frag: the fragment + * + * Returns the &struct net_iov associated with @frag. Returns NULL if this + * frag has no associated net_iov. + */ +static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag) +{ + if (!skb_frag_is_net_iov(frag)) + return NULL; + + return netmem_to_net_iov(frag->netmem); +} + /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * - * Returns the &struct page associated with @frag. + * Returns the &struct page associated with @frag. Returns NULL if this frag + * has no associated page. */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { + if (skb_frag_is_net_iov(frag)) + return NULL; + return netmem_to_page(frag->netmem); }

+/** + * skb_frag_netmem - retrieve the netmem referred to by a fragment + * @frag: the fragment + * + * Returns the &netmem_ref associated with @frag. + */ +static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag) +{ + return frag->netmem; +} + /** * __skb_frag_ref - take an addition reference on a paged fragment. * @frag: the paged fragment @@ -3513,25 +3549,23 @@ int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, bool napi_pp_put_page(netmem_ref netmem, bool napi_safe);

static inline void -skb_page_unref(const struct sk_buff *skb, struct page *page, bool napi_safe) +skb_page_unref(const struct sk_buff *skb, netmem_ref netmem, bool napi_safe) { #ifdef CONFIG_PAGE_POOL - if (skb->pp_recycle && napi_pp_put_page(page_to_netmem(page), napi_safe)) + if (skb->pp_recycle && napi_pp_put_page(netmem, napi_safe)) return; #endif - put_page(page); + put_page(netmem_to_page(netmem)); }

static inline void napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe) { - struct page *page = skb_frag_page(frag); - #ifdef CONFIG_PAGE_POOL - if (recycle && napi_pp_put_page(page_to_netmem(page), napi_safe)) + if (recycle && napi_pp_put_page(skb_frag_netmem(frag), napi_safe)) return; #endif - put_page(page); + put_page(skb_frag_page(frag)); }

/** @@ -3571,6 +3605,9 @@ static inline void skb_frag_unref(struct sk_buff *skb, int f) */ static inline void *skb_frag_address(const skb_frag_t *frag) { + if (!skb_frag_page(frag)) + return NULL; + return page_address(skb_frag_page(frag)) + skb_frag_off(frag); }

diff --git a/net/core/dev.c b/net/core/dev.c index 7ef8def6ec43..94adc63957d1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3416,8 +3416,9 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) if (!(dev->features & NETIF_F_HIGHDMA)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct page *page = skb_frag_page(frag);

- if (PageHighMem(skb_frag_page(frag))) + if (page && PageHighMem(page)) return 1; } } diff --git a/net/core/gro.c b/net/core/gro.c index ee30d4f0c038..eef20c82c5c3 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -380,7 +380,8 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) pinfo = skb_shinfo(skb); frag0 = &pinfo->frags[0];

- if (pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0)) && + if (pinfo->nr_frags && skb_frag_page(frag0) && + !PageHighMem(skb_frag_page(frag0)) && (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 753d61680d69..8cd80ac2bdb5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1374,6 +1374,14 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) struct page *p; u8 *vaddr;

+ if (skb_frag_is_net_iov(frag)) { + printk("%sskb frag %d: not readable\n", level, i); + len -= skb_frag_size(frag); + if (!len) + break; + continue; + } + skb_frag_foreach_page(frag, skb_frag_off(frag), skb_frag_size(frag), p, p_off, p_len, copied) { @@ -3141,6 +3149,9 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];

+ if (WARN_ON_ONCE(!skb_frag_page(f))) + return false; + if (__splice_segment(skb_frag_page(f), skb_frag_off(f), skb_frag_size(f), offset, len, spd, false, sk, pipe)) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index d33d12421814..3b2a6a033efa 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -114,7 +114,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - skb_page_unref(skb, sg_page(sg), false); + skb_page_unref(skb, page_to_netmem(sg_page(sg)), false); }

#ifdef CONFIG_INET_ESPINTCP diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e767721b3a58..7bf5fbec0e34 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2167,6 +2167,9 @@ static int tcp_zerocopy_receive(struct sock *sk, break; } page = skb_frag_page(frags); + if (WARN_ON_ONCE(!page)) + break; + prefetchw(page); pages[pages_to_map++] = page; length += PAGE_SIZE; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 7371886d4f9f..342c07f0c6c4 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -131,7 +131,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - skb_page_unref(skb, sg_page(sg), false); + skb_page_unref(skb, page_to_netmem(sg_page(sg)), false); }

#ifdef CONFIG_INET6_ESPINTCP

In tcp_recvmsg_locked(), detect if the skb being received by the user is a devmem skb. In this case - if the user provided the MSG_SOCK_DEVMEM flag - pass it to tcp_recvmsg_devmem() for custom handling.

tcp_recvmsg_devmem() copies any data in the skb header to the linear buffer, and returns a cmsg to the user indicating the number of bytes returned in the linear buffer.

tcp_recvmsg_devmem() then loops over the unaccessible devmem skb frags, and returns to the user a cmsg_devmem indicating the location of the data in the dmabuf device memory. cmsg_devmem contains this information:

1. the offset into the dmabuf where the payload starts. 'frag_offset'. 2. the size of the frag. 'frag_size'. 3. an opaque token 'frag_token' to return to the kernel when the buffer is to be released.

The pages awaiting freeing are stored in the newly added sk->sk_user_frags, and each page passed to userspace is get_page()'d. This reference is dropped once the userspace indicates that it is done reading this page. All pages are released when the socket is destroyed.

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 the SO_DEVMEM_* uapi to use the next available entries (Arnd). - Updated dmabuf_cmsg struct to be __u64 padded (Arnd). - Squashed fix from Eric to initialize sk_user_frags for passive sockets (Eric).

v6 - skb->dmabuf -> skb->readable (Pavel) - Fixed asm definitions of SO_DEVMEM_LINEAR/SO_DEVMEM_DMABUF not found on some archs. - Squashed in locking optimizations from edumazet@google.com. With this change we lock the xarray once per per tcp_recvmsg_dmabuf() rather than once per frag in xa_alloc().

Changes in v1: - Added dmabuf_id to dmabuf_cmsg (David/Stan). - Devmem -> dmabuf (David). - Change tcp_recvmsg_dmabuf() check to skb->dmabuf (Paolo). - Use __skb_frag_ref() & napi_pp_put_page() for refcounting (Yunsheng).

RFC v3: - Fixed issue with put_cmsg() failing silently.

--- arch/alpha/include/uapi/asm/socket.h | 5 + arch/mips/include/uapi/asm/socket.h | 5 + arch/parisc/include/uapi/asm/socket.h | 5 + arch/sparc/include/uapi/asm/socket.h | 5 + include/linux/socket.h | 1 + include/net/netmem.h | 13 ++ include/net/sock.h | 2 + include/uapi/asm-generic/socket.h | 5 + include/uapi/linux/uio.h | 13 ++ net/ipv4/tcp.c | 248 +++++++++++++++++++++++++- net/ipv4/tcp_ipv4.c | 9 + net/ipv4/tcp_minisocks.c | 2 + 12 files changed, 308 insertions(+), 5 deletions(-)

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index e94f621903fe..ef4656a41058 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -140,6 +140,11 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77

+#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__)

#if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 60ebaed28a4c..414807d55e33 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -151,6 +151,11 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77

+#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__)

#if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index be264c2b1a11..2b817efd4544 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -132,6 +132,11 @@ #define SO_PASSPIDFD 0x404A #define SO_PEERPIDFD 0x404B

+#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__)

#if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 682da3714686..00248fc68977 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -133,6 +133,11 @@ #define SO_PASSPIDFD 0x0055 #define SO_PEERPIDFD 0x0056

+#define SO_DEVMEM_LINEAR 0x0057 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 0x0058 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__)

diff --git a/include/linux/socket.h b/include/linux/socket.h index 139c330ccf2c..f11ab541439e 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -326,6 +326,7 @@ struct ucred { * plain text and require encryption */

+#define MSG_SOCK_DEVMEM 0x2000000 /* Receive devmem skbs as cmsg */ #define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #define MSG_SPLICE_PAGES 0x8000000 /* Splice the pages from the iterator in sendmsg() */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ diff --git a/include/net/netmem.h b/include/net/netmem.h index 34aa1c80c1ca..c7fb1e4dc679 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -65,6 +65,19 @@ static inline unsigned int net_iov_idx(const struct net_iov *niov) return niov - net_iov_owner(niov)->niovs; }

+static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov) +{ + struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov); + + return owner->base_virtual + + ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT); +} + +static inline u32 net_iov_binding_id(const struct net_iov *niov) +{ + return net_iov_owner(niov)->binding->id; +} + /* 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. diff --git a/include/net/sock.h b/include/net/sock.h index 2253eefe2848..e4b134ca18dc 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -337,6 +337,7 @@ struct sk_filter; * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference + * @sk_user_frags: xarray of pages the user is holding a reference on. */ struct sock { /* @@ -542,6 +543,7 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; + struct xarray sk_user_frags; };

enum sk_pacing { diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 8ce8a39a1e5f..25a2f5255f52 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -135,6 +135,11 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77

+#define SO_DEVMEM_LINEAR 98 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 99 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__)

#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h index 059b1a9147f4..3a22ddae376a 100644 --- a/include/uapi/linux/uio.h +++ b/include/uapi/linux/uio.h @@ -20,6 +20,19 @@ struct iovec __kernel_size_t iov_len; /* Must be size_t (1003.1g) */ };

+struct dmabuf_cmsg { + __u64 frag_offset; /* offset into the dmabuf where the frag starts. + */ + __u32 frag_size; /* size of the frag. */ + __u32 frag_token; /* token representing this frag for + * DEVMEM_DONTNEED. + */ + __u32 dmabuf_id; /* dmabuf id this frag belongs to. */ + __u32 flags; /* Currently unused. Reserved for future + * uses. + */ +}; + /* * UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1) */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9548fedf7966..d3e4ddecc537 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -462,6 +462,7 @@ void tcp_init_sock(struct sock *sk)

set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); + xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1); } EXPORT_SYMBOL(tcp_init_sock);

@@ -2313,6 +2314,213 @@ static int tcp_inq_hint(struct sock *sk) return inq; }

+/* batch __xa_alloc() calls and reduce xa_lock()/xa_unlock() overhead. */ +struct tcp_xa_pool { + u8 max; /* max <= MAX_SKB_FRAGS */ + u8 idx; /* idx <= max */ + __u32 tokens[MAX_SKB_FRAGS]; + netmem_ref netmems[MAX_SKB_FRAGS]; +}; + +static void tcp_xa_pool_commit(struct sock *sk, struct tcp_xa_pool *p, + bool lock) +{ + int i; + + if (!p->max) + return; + if (lock) + xa_lock_bh(&sk->sk_user_frags); + /* Commit part that has been copied to user space. */ + for (i = 0; i < p->idx; i++) + __xa_cmpxchg(&sk->sk_user_frags, p->tokens[i], XA_ZERO_ENTRY, + (__force void *)p->netmems[i], GFP_KERNEL); + /* Rollback what has been pre-allocated and is no longer needed. */ + for (; i < p->max; i++) + __xa_erase(&sk->sk_user_frags, p->tokens[i]); + if (lock) + xa_unlock_bh(&sk->sk_user_frags); + p->max = 0; + p->idx = 0; +} + +static int tcp_xa_pool_refill(struct sock *sk, struct tcp_xa_pool *p, + unsigned int max_frags) +{ + int err, k; + + if (p->idx < p->max) + return 0; + + xa_lock_bh(&sk->sk_user_frags); + + tcp_xa_pool_commit(sk, p, false); + for (k = 0; k < max_frags; k++) { + err = __xa_alloc(&sk->sk_user_frags, &p->tokens[k], + XA_ZERO_ENTRY, xa_limit_31b, GFP_KERNEL); + if (err) + break; + } + + xa_unlock_bh(&sk->sk_user_frags); + + p->max = k; + p->idx = 0; + return k ? 0 : err; +} + +/* On error, returns the -errno. On success, returns number of bytes sent to the + * user. May not consume all of @remaining_len. + */ +static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, + unsigned int offset, struct msghdr *msg, + int remaining_len) +{ + struct dmabuf_cmsg dmabuf_cmsg = { 0 }; + struct tcp_xa_pool tcp_xa_pool; + unsigned int start; + int i, copy, n; + int sent = 0; + int err = 0; + + tcp_xa_pool.max = 0; + tcp_xa_pool.idx = 0; + do { + start = skb_headlen(skb); + + if (skb->readable) { + err = -ENODEV; + goto out; + } + + /* Copy header. */ + copy = start - offset; + if (copy > 0) { + copy = min(copy, remaining_len); + + n = copy_to_iter(skb->data + offset, copy, + &msg->msg_iter); + if (n != copy) { + err = -EFAULT; + goto out; + } + + offset += copy; + remaining_len -= copy; + + /* First a dmabuf_cmsg for # bytes copied to user + * buffer. + */ + memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg)); + dmabuf_cmsg.frag_size = copy; + err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR, + sizeof(dmabuf_cmsg), &dmabuf_cmsg); + if (err || msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~MSG_CTRUNC; + if (!err) + err = -ETOOSMALL; + goto out; + } + + sent += copy; + + if (remaining_len == 0) + goto out; + } + + /* after that, send information of dmabuf pages through a + * sequence of cmsg + */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct net_iov *niov; + u64 frag_offset; + int end; + + /* !skb->readable should indicate that ALL the frags in + * this skb are dmabuf net_iovs. We're checking + * for that flag above, but also check individual frags + * here. If the tcp stack is not setting skb->readable + * correctly, we still don't want to crash here when + * accessing pgmap or priv below. + */ + if (!skb_frag_net_iov(frag)) { + net_err_ratelimited("Found non-dmabuf skb with net_iov"); + err = -ENODEV; + goto out; + } + + niov = skb_frag_net_iov(frag); + end = start + skb_frag_size(frag); + copy = end - offset; + + if (copy > 0) { + copy = min(copy, remaining_len); + + frag_offset = net_iov_virtual_addr(niov) + + skb_frag_off(frag) + offset - + start; + dmabuf_cmsg.frag_offset = frag_offset; + dmabuf_cmsg.frag_size = copy; + err = tcp_xa_pool_refill(sk, &tcp_xa_pool, + skb_shinfo(skb)->nr_frags - i); + if (err) + goto out; + + /* Will perform the exchange later */ + dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx]; + dmabuf_cmsg.dmabuf_id = net_iov_binding_id(niov); + + offset += copy; + remaining_len -= copy; + + err = put_cmsg(msg, SOL_SOCKET, + SO_DEVMEM_DMABUF, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err || msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~MSG_CTRUNC; + if (!err) + err = -ETOOSMALL; + goto out; + } + + atomic_long_inc(&niov->pp_ref_count); + tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); + + sent += copy; + + if (remaining_len == 0) + goto out; + } + start = end; + } + + tcp_xa_pool_commit(sk, &tcp_xa_pool, true); + if (!remaining_len) + goto out; + + /* if remaining_len is not satisfied yet, we need to go to the + * next frag in the frag_list to satisfy remaining_len. + */ + skb = skb_shinfo(skb)->frag_list ?: skb->next; + + offset = offset - start; + } while (skb); + + if (remaining_len) { + err = -EFAULT; + goto out; + } + +out: + tcp_xa_pool_commit(sk, &tcp_xa_pool, true); + if (!sent) + sent = err; + + return sent; +} + /* * This routine copies from a sock struct into the user buffer. * @@ -2326,6 +2534,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int *cmsg_flags) { struct tcp_sock *tp = tcp_sk(sk); + int last_copied_dmabuf = -1; /* uninitialized */ int copied = 0; u32 peek_seq; u32 *seq; @@ -2503,15 +2712,44 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, }

if (!(flags & MSG_TRUNC)) { - err = skb_copy_datagram_msg(skb, offset, msg, used); - if (err) { - /* Exception. Bailout! */ - if (!copied) - copied = -EFAULT; + if (last_copied_dmabuf != -1 && + last_copied_dmabuf != !skb->readable) break; + + if (skb->readable) { + err = skb_copy_datagram_msg(skb, offset, msg, + used); + if (err) { + /* Exception. Bailout! */ + if (!copied) + copied = -EFAULT; + break; + } + } else { + if (!(flags & MSG_SOCK_DEVMEM)) { + /* dmabuf skbs can only be received + * with the MSG_SOCK_DEVMEM flag. + */ + if (!copied) + copied = -EFAULT; + + break; + } + + err = tcp_recvmsg_dmabuf(sk, skb, offset, msg, + used); + if (err <= 0) { + if (!copied) + copied = -EFAULT; + + break; + } + used = err; } }

+ last_copied_dmabuf = !skb->readable; + WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1e0a9762f92e..1d82bffe959c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2498,6 +2498,15 @@ static void tcp_md5sig_info_free_rcu(struct rcu_head *head) void tcp_v4_destroy_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + __maybe_unused unsigned long index; + __maybe_unused void *netmem; + +#ifdef CONFIG_PAGE_POOL + xa_for_each(&sk->sk_user_frags, index, netmem) + WARN_ON_ONCE(!napi_pp_put_page((__force netmem_ref)netmem, false)); +#endif + + xa_destroy(&sk->sk_user_frags);

trace_tcp_destroy_sock(sk);

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 5b21a07ddf9a..a4c398c25572 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -625,6 +625,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,

__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);

+ xa_init_flags(&newsk->sk_user_frags, XA_FLAGS_ALLOC1); + return newsk; } EXPORT_SYMBOL(tcp_create_openreq_child);

Add documentation outlining the usage and details of devmem TCP.

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

---

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

v7: - Applied docs suggestions (Jakub).

v2:

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

fix docs

--- Documentation/networking/devmem.rst | 256 ++++++++++++++++++++++++++++ Documentation/networking/index.rst | 1 + 2 files changed, 257 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 000000000000..e4e978fbcdbd --- /dev/null +++ b/Documentation/networking/devmem.rst @@ -0,0 +1,256 @@ +.. 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:: + + # On server: + ncdevmem -s <server IP> -c <client IP> -f eth1 -d 3 -n 0000:06:00.0 -l \ + -p 5201 -v 7 + + # On client: + 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 473d72c36d61..6b47a51caad6 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

ncdevmem is a devmem TCP netcat. It works similarly to netcat, but it sends and receives data using the devmem TCP APIs. It uses udmabuf as the dmabuf provider. It is compatible with a regular netcat running on a peer, or a ncdevmem running on a peer.

In addition to normal netcat support, ncdevmem has a validation mode, where it sends a specific pattern and validates this pattern on the receiver side to ensure data integrity.

Suggested-by: Stanislav Fomichev sdf@google.com Signed-off-by: Mina Almasry almasrymina@google.com

---

v6: - Updated to bind 8 queues. - Added RSS configuration. - Added some more tests for the netlink API.

Changes in v1: - Many more general cleanups (Willem). - Removed driver reset (Jakub). - Removed hardcoded if index (Paolo).

RFC v2: - General cleanups (Willem).

--- tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 5 + tools/testing/selftests/net/ncdevmem.c | 546 +++++++++++++++++++++++++ 3 files changed, 552 insertions(+) create mode 100644 tools/testing/selftests/net/ncdevmem.c

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index d996a0ab0765..d11814a1b5cf 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -17,6 +17,7 @@ ipv6_flowlabel ipv6_flowlabel_mgr log.txt msg_zerocopy +ncdevmem nettest psock_fanout psock_snd diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index cb418a2346bc..7a1c9ccecb83 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,6 +5,10 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ $(KHDR_INCLUDES) # Additional include paths needed by kselftest.h CFLAGS += -I../ +CFLAGS += -I../../../net/ynl/generated/ +CFLAGS += -I../../../net/ynl/lib/ + +LDLIBS += ../../../net/ynl/lib/ynl.a ../../../net/ynl/generated/protos.a

TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \ rtnetlink.sh xfrm_policy.sh test_blackhole_dev.sh @@ -92,6 +96,7 @@ TEST_PROGS += test_bridge_backup_port.sh TEST_PROGS += fdb_flush.sh TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh +TEST_GEN_FILES += ncdevmem

TEST_FILES := settings TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c new file mode 100644 index 000000000000..11bfe3e1125b --- /dev/null +++ b/tools/testing/selftests/net/ncdevmem.c @@ -0,0 +1,546 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#define __EXPORTED_HEADERS__ + +#include <linux/uio.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <stdbool.h> +#include <string.h> +#include <errno.h> +#define __iovec_defined +#include <fcntl.h> +#include <malloc.h> +#include <error.h> + +#include <arpa/inet.h> +#include <sys/socket.h> +#include <sys/mman.h> +#include <sys/ioctl.h> +#include <sys/syscall.h> + +#include <linux/memfd.h> +#include <linux/if.h> +#include <linux/dma-buf.h> +#include <linux/udmabuf.h> +#include <libmnl/libmnl.h> +#include <linux/types.h> +#include <linux/netlink.h> +#include <linux/genetlink.h> +#include <linux/netdev.h> +#include <time.h> + +#include "netdev-user.h" +#include <ynl.h> + +#define PAGE_SHIFT 12 +#define TEST_PREFIX "ncdevmem" +#define NUM_PAGES 16000 + +#ifndef MSG_SOCK_DEVMEM +#define MSG_SOCK_DEVMEM 0x2000000 +#endif + +/* + * tcpdevmem netcat. Works similarly to netcat but does device memory TCP + * instead of regular TCP. Uses udmabuf to mock a dmabuf provider. + * + * Usage: + * + * On server: + * ncdevmem -s <server IP> -c <client IP> -f eth1 -d 3 -n 0000:06:00.0 -l \ + * -p 5201 -v 7 + * + * On client: + * yes $(echo -e \x01\x02\x03\x04\x05\x06) | \ + * tr \n \0 | \ + * head -c 5G | \ + * nc <server IP> 5201 -p 5201 + * + * Note this is compatible with regular netcat. i.e. the sender or receiver can + * be replaced with regular netcat to test the RX or TX path in isolation. + */ + +static char *server_ip = "192.168.1.4"; +static char *client_ip = "192.168.1.2"; +static char *port = "5201"; +static size_t do_validation; +static int start_queue = 8; +static int num_queues = 8; +static char *ifname = "eth1"; +static unsigned int ifindex = 3; +static char *nic_pci_addr = "0000:06:00.0"; +static unsigned int iterations; +static unsigned int dmabuf_id; + +void print_bytes(void *ptr, size_t size) +{ + unsigned char *p = ptr; + int i; + + for (i = 0; i < size; i++) + printf("%02hhX ", p[i]); + printf("\n"); +} + +void print_nonzero_bytes(void *ptr, size_t size) +{ + unsigned char *p = ptr; + unsigned int i; + + for (i = 0; i < size; i++) + putchar(p[i]); + printf("\n"); +} + +void validate_buffer(void *line, size_t size) +{ + static unsigned char seed = 1; + unsigned char *ptr = line; + int errors = 0; + size_t i; + + for (i = 0; i < size; i++) { + if (ptr[i] != seed) { + fprintf(stderr, + "Failed validation: expected=%u, actual=%u, index=%lu\n", + seed, ptr[i], i); + errors++; + if (errors > 20) + error(1, 0, "validation failed."); + } + seed++; + if (seed == do_validation) + seed = 0; + } + + fprintf(stdout, "Validated buffer\n"); +} + +static void reset_flow_steering(void) +{ + char command[256]; + + memset(command, 0, sizeof(command)); + snprintf(command, sizeof(command), "sudo ethtool -K %s ntuple off", + "eth1"); + system(command); + + memset(command, 0, sizeof(command)); + snprintf(command, sizeof(command), "sudo ethtool -K %s ntuple on", + "eth1"); + system(command); +} + +static void configure_rss(void) +{ + char command[256]; + + memset(command, 0, sizeof(command)); + snprintf(command, sizeof(command), "sudo ethtool -X %s equal %d", + ifname, start_queue); + system(command); +} + +static void configure_flow_steering(void) +{ + char command[256]; + + memset(command, 0, sizeof(command)); + snprintf(command, sizeof(command), + "sudo ethtool -N %s flow-type tcp4 src-ip %s dst-ip %s src-port %s dst-port %s queue %d", + ifname, client_ip, server_ip, port, port, start_queue); + system(command); +} + +static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd, + struct netdev_queue_dmabuf *queues, + unsigned int n_queue_index, struct ynl_sock **ys) +{ + struct netdev_bind_rx_req *req = NULL; + struct netdev_bind_rx_rsp *rsp = NULL; + struct ynl_error yerr; + + *ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!*ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return -1; + } + + req = netdev_bind_rx_req_alloc(); + netdev_bind_rx_req_set_ifindex(req, 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); + if (!rsp) { + perror("netdev_bind_rx"); + goto err_close; + } + + if (!rsp->_present.dmabuf_id) { + perror("dmabuf_id not present"); + goto err_close; + } + + printf("got dmabuf id=%d\n", rsp->dmabuf_id); + dmabuf_id = rsp->dmabuf_id; + + netdev_bind_rx_req_free(req); + netdev_bind_rx_rsp_free(rsp); + + return 0; + +err_close: + fprintf(stderr, "YNL failed: %s\n", (*ys)->err.msg); + netdev_bind_rx_req_free(req); + ynl_sock_destroy(*ys); + return -1; +} + +static void create_udmabuf(int *devfd, int *memfd, int *buf, size_t dmabuf_size) +{ + struct udmabuf_create create; + int ret; + + *devfd = open("/dev/udmabuf", O_RDWR); + if (*devfd < 0) { + error(70, 0, + "%s: [skip,no-udmabuf: Unable to access DMA buffer device file]\n", + TEST_PREFIX); + } + + *memfd = memfd_create("udmabuf-test", MFD_ALLOW_SEALING); + if (*memfd < 0) + error(70, 0, "%s: [skip,no-memfd]\n", TEST_PREFIX); + + /* Required for udmabuf */ + ret = fcntl(*memfd, F_ADD_SEALS, F_SEAL_SHRINK); + if (ret < 0) + error(73, 0, "%s: [skip,fcntl-add-seals]\n", TEST_PREFIX); + + ret = ftruncate(*memfd, dmabuf_size); + if (ret == -1) + error(74, 0, "%s: [FAIL,memfd-truncate]\n", TEST_PREFIX); + + memset(&create, 0, sizeof(create)); + + create.memfd = *memfd; + create.offset = 0; + create.size = dmabuf_size; + *buf = ioctl(*devfd, UDMABUF_CREATE, &create); + if (*buf < 0) + error(75, 0, "%s: [FAIL, create udmabuf]\n", TEST_PREFIX); +} + +int do_server(void) +{ + char ctrl_data[sizeof(int) * 20000]; + struct netdev_queue_dmabuf *queues; + size_t non_page_aligned_frags = 0; + struct sockaddr_in client_addr; + struct sockaddr_in server_sin; + size_t page_aligned_frags = 0; + int devfd, memfd, buf, ret; + size_t total_received = 0; + socklen_t client_addr_len; + bool is_devmem = false; + char *buf_mem = NULL; + struct ynl_sock *ys; + size_t dmabuf_size; + char iobuf[819200]; + char buffer[256]; + int socket_fd; + int client_fd; + size_t i = 0; + int opt = 1; + + dmabuf_size = getpagesize() * NUM_PAGES; + + create_udmabuf(&devfd, &memfd, &buf, dmabuf_size); + + reset_flow_steering(); + + /* Configure RSS to divert all traffic from our devmem queues */ + configure_rss(); + + /* Flow steer our devmem flows to start_queue */ + configure_flow_steering(); + + sleep(1); + + queues = malloc(sizeof(*queues) * num_queues); + + for (i = 0; i < num_queues; i++) { + queues[i]._present.type = 1; + queues[i]._present.idx = 1; + queues[i].type = NETDEV_QUEUE_TYPE_RX; + queues[i].idx = start_queue + i; + } + + if (bind_rx_queue(ifindex, buf, queues, num_queues, &ys)) + error(1, 0, "Failed to bind\n"); + + buf_mem = mmap(NULL, dmabuf_size, PROT_READ | PROT_WRITE, MAP_SHARED, + buf, 0); + if (buf_mem == MAP_FAILED) + error(1, 0, "mmap()"); + + server_sin.sin_family = AF_INET; + server_sin.sin_port = htons(atoi(port)); + + ret = inet_pton(server_sin.sin_family, server_ip, &server_sin.sin_addr); + if (socket < 0) + error(79, 0, "%s: [FAIL, create socket]\n", TEST_PREFIX); + + socket_fd = socket(server_sin.sin_family, SOCK_STREAM, 0); + if (socket < 0) + error(errno, errno, "%s: [FAIL, create socket]\n", TEST_PREFIX); + + ret = setsockopt(socket_fd, SOL_SOCKET, SO_REUSEPORT, &opt, + sizeof(opt)); + if (ret) + error(errno, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX); + + ret = setsockopt(socket_fd, SOL_SOCKET, SO_REUSEADDR, &opt, + sizeof(opt)); + if (ret) + error(errno, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX); + + printf("binding to address %s:%d\n", server_ip, + ntohs(server_sin.sin_port)); + + ret = bind(socket_fd, &server_sin, sizeof(server_sin)); + if (ret) + error(errno, errno, "%s: [FAIL, bind]\n", TEST_PREFIX); + + ret = listen(socket_fd, 1); + if (ret) + error(errno, errno, "%s: [FAIL, listen]\n", TEST_PREFIX); + + client_addr_len = sizeof(client_addr); + + inet_ntop(server_sin.sin_family, &server_sin.sin_addr, buffer, + sizeof(buffer)); + printf("Waiting or connection on %s:%d\n", buffer, + ntohs(server_sin.sin_port)); + client_fd = accept(socket_fd, &client_addr, &client_addr_len); + + inet_ntop(client_addr.sin_family, &client_addr.sin_addr, buffer, + sizeof(buffer)); + printf("Got connection from %s:%d\n", buffer, + ntohs(client_addr.sin_port)); + + while (1) { + struct iovec iov = { .iov_base = iobuf, + .iov_len = sizeof(iobuf) }; + struct dmabuf_cmsg *dmabuf_cmsg = NULL; + struct dma_buf_sync sync = { 0 }; + struct cmsghdr *cm = NULL; + struct msghdr msg = { 0 }; + struct dmabuf_token token; + ssize_t ret; + + is_devmem = false; + printf("\n\n"); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = ctrl_data; + msg.msg_controllen = sizeof(ctrl_data); + ret = recvmsg(client_fd, &msg, MSG_SOCK_DEVMEM); + printf("recvmsg ret=%ld\n", ret); + if (ret < 0 && (errno == EAGAIN || errno == EWOULDBLOCK)) + continue; + if (ret < 0) { + perror("recvmsg"); + continue; + } + if (ret == 0) { + printf("client exited\n"); + goto cleanup; + } + + i++; + 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)) { + fprintf(stdout, "skipping non-devmem cmsg\n"); + continue; + } + + dmabuf_cmsg = (struct dmabuf_cmsg *)CMSG_DATA(cm); + is_devmem = true; + + if (cm->cmsg_type == SCM_DEVMEM_LINEAR) { + /* TODO: process data copied from skb's linear + * buffer. + */ + fprintf(stdout, + "SCM_DEVMEM_LINEAR. dmabuf_cmsg->frag_size=%u\n", + dmabuf_cmsg->frag_size); + + continue; + } + + token.token_start = dmabuf_cmsg->frag_token; + token.token_count = 1; + + total_received += dmabuf_cmsg->frag_size; + printf("received frag_page=%llu, in_page_offset=%llu, frag_offset=%llu, frag_size=%u, token=%u, total_received=%lu, dmabuf_id=%u\n", + dmabuf_cmsg->frag_offset >> PAGE_SHIFT, + dmabuf_cmsg->frag_offset % getpagesize(), + dmabuf_cmsg->frag_offset, dmabuf_cmsg->frag_size, + dmabuf_cmsg->frag_token, total_received, + dmabuf_cmsg->dmabuf_id); + + if (dmabuf_cmsg->dmabuf_id != dmabuf_id) + error(1, 0, + "received on wrong dmabuf_id: flow steering error\n"); + + if (dmabuf_cmsg->frag_size % getpagesize()) + non_page_aligned_frags++; + else + page_aligned_frags++; + + sync.flags = DMA_BUF_SYNC_READ | DMA_BUF_SYNC_START; + ioctl(buf, DMA_BUF_IOCTL_SYNC, &sync); + + if (do_validation) + validate_buffer( + ((unsigned char *)buf_mem) + + dmabuf_cmsg->frag_offset, + dmabuf_cmsg->frag_size); + else + print_nonzero_bytes( + ((unsigned char *)buf_mem) + + dmabuf_cmsg->frag_offset, + dmabuf_cmsg->frag_size); + + sync.flags = DMA_BUF_SYNC_READ | DMA_BUF_SYNC_END; + ioctl(buf, DMA_BUF_IOCTL_SYNC, &sync); + + ret = setsockopt(client_fd, SOL_SOCKET, + SO_DEVMEM_DONTNEED, &token, + sizeof(token)); + if (ret != 1) + error(1, 0, + "SO_DEVMEM_DONTNEED not enough tokens"); + } + if (!is_devmem) + error(1, 0, "flow steering error\n"); + + printf("total_received=%lu\n", total_received); + } + + fprintf(stdout, "%s: ok\n", TEST_PREFIX); + + fprintf(stdout, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n", + page_aligned_frags, non_page_aligned_frags); + + fprintf(stdout, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n", + page_aligned_frags, non_page_aligned_frags); + +cleanup: + + munmap(buf_mem, dmabuf_size); + close(client_fd); + close(socket_fd); + close(buf); + close(memfd); + close(devfd); + ynl_sock_destroy(ys); + + return 0; +} + +void run_devmem_tests(void) +{ + struct netdev_queue_dmabuf *queues; + int devfd, memfd, buf; + struct ynl_sock *ys; + size_t dmabuf_size; + size_t i = 0; + + dmabuf_size = getpagesize() * NUM_PAGES; + + create_udmabuf(&devfd, &memfd, &buf, dmabuf_size); + + /* Configure RSS to divert all traffic from our devmem queues */ + configure_rss(); + + sleep(1); + + queues = malloc(sizeof(*queues) * num_queues); + + for (i = 0; i < num_queues; i++) { + queues[i]._present.type = 1; + queues[i]._present.idx = 1; + queues[i].type = NETDEV_QUEUE_TYPE_RX; + queues[i].idx = start_queue + i; + } + + if (bind_rx_queue(ifindex, buf, queues, num_queues, &ys)) + error(1, 0, "Failed to bind\n"); + + /* Closing the netlink socket does an implicit unbind */ + ynl_sock_destroy(ys); +} + +int main(int argc, char *argv[]) +{ + int is_server = 0, opt; + + while ((opt = getopt(argc, argv, "ls:c:p:v:q:f:n:i:d:")) != -1) { + switch (opt) { + case 'l': + is_server = 1; + break; + case 's': + server_ip = optarg; + break; + case 'c': + client_ip = optarg; + break; + case 'p': + port = optarg; + break; + case 'v': + do_validation = atoll(optarg); + break; + case 'q': + num_queues = atoi(optarg); + break; + case 't': + start_queue = atoi(optarg); + break; + case 'f': + ifname = optarg; + break; + case 'd': + ifindex = atoi(optarg); + break; + case 'n': + nic_pci_addr = optarg; + break; + case 'i': + iterations = atoll(optarg); + break; + case '?': + printf("unknown option: %c\n", optopt); + break; + } + } + + for (; optind < argc; optind++) + printf("extra arguments: %s\n", argv[optind]); + + run_devmem_tests(); + + if (is_server) + return do_server(); + + return 0; +}