Linux-kselftest-mirror

linux-kselftest-mirror@lists.linaro.org

106 participants
14258 discussions

[PATCH net-next v9 5/5] selftests: drv-net: devmem: add autorelease test

by Bobby Eshleman

From: Bobby Eshleman <bobbyeshleman(a)meta.com> Add test case for autorelease. The test case is the same as the RX test, but enables autorelease. The original RX test is changed to use the -a 0 flag to disable autorelease. TAP version 13 1..4 ok 1 devmem.check_rx ok 2 devmem.check_rx_autorelease ok 3 devmem.check_tx ok 4 devmem.check_tx_chunks Signed-off-by: Bobby Eshleman <bobbyeshleman(a)meta.com> --- Changes in v8: - removed stale/missing tests Changes in v7: - use autorelease netlink - remove sockopt tests --- tools/testing/selftests/drivers/net/hw/devmem.py | 21 +++++++++++++++++++-- tools/testing/selftests/drivers/net/hw/ncdevmem.c | 19 +++++++++++++------ 2 files changed, 32 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py index 45c2d49d55b6..dbe696a445bd 100755 --- a/tools/testing/selftests/drivers/net/hw/devmem.py +++ b/tools/testing/selftests/drivers/net/hw/devmem.py @@ -25,7 +25,24 @@ def check_rx(cfg) -> None: port = rand_port() socat = f"socat -u - TCP{cfg.addr_ipver}:{cfg.baddr}:{port},bind={cfg.remote_baddr}:{port}" - listen_cmd = f"{cfg.bin_local} -l -f {cfg.ifname} -s {cfg.addr} -p {port} -c {cfg.remote_addr} -v 7" + listen_cmd = f"{cfg.bin_local} -l -f {cfg.ifname} -s {cfg.addr} -p {port} -c {cfg.remote_addr} -v 7 -a 0" + + with bkg(listen_cmd, exit_wait=True) as ncdevmem: + wait_port_listen(port) + cmd(f"yes $(echo -e \x01\x02\x03\x04\x05\x06) | \ + head -c 1K | {socat}", host=cfg.remote, shell=True) + + ksft_eq(ncdevmem.ret, 0) + + +@ksft_disruptive +def check_rx_autorelease(cfg) -> None: + require_devmem(cfg) + + port = rand_port() + socat = f"socat -u - TCP{cfg.addr_ipver}:{cfg.baddr}:{port},bind={cfg.remote_baddr}:{port}" + listen_cmd = f"{cfg.bin_local} -l -f {cfg.ifname} -s {cfg.addr} -p {port} \ + -c {cfg.remote_addr} -v 7 -a 1" with bkg(listen_cmd, exit_wait=True) as ncdevmem: wait_port_listen(port) @@ -68,7 +85,7 @@ def main() -> None: cfg.bin_local = path.abspath(path.dirname(__file__) + "/ncdevmem") cfg.bin_remote = cfg.remote.deploy(cfg.bin_local) - ksft_run([check_rx, check_tx, check_tx_chunks], + ksft_run([check_rx, check_rx_autorelease, check_tx, check_tx_chunks], args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c index 3288ed04ce08..406f1771d9ec 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -92,6 +92,7 @@ static char *port; static size_t do_validation; static int start_queue = -1; static int num_queues = -1; +static int devmem_autorelease; static char *ifname; static unsigned int ifindex; static unsigned int dmabuf_id; @@ -679,7 +680,8 @@ static int configure_flow_steering(struct sockaddr_in6 *server_sin) static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd, struct netdev_queue_id *queues, - unsigned int n_queue_index, struct ynl_sock **ys) + unsigned int n_queue_index, struct ynl_sock **ys, + int autorelease) { struct netdev_bind_rx_req *req = NULL; struct netdev_bind_rx_rsp *rsp = NULL; @@ -695,6 +697,7 @@ static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd, req = netdev_bind_rx_req_alloc(); netdev_bind_rx_req_set_ifindex(req, ifindex); netdev_bind_rx_req_set_fd(req, dmabuf_fd); + netdev_bind_rx_req_set_autorelease(req, autorelease); __netdev_bind_rx_req_set_queues(req, queues, n_queue_index); rsp = netdev_bind_rx(*ys, req); @@ -872,7 +875,8 @@ static int do_server(struct memory_buffer *mem) goto err_reset_rss; } - if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys)) { + if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys, + devmem_autorelease)) { pr_err("Failed to bind"); goto err_reset_flow_steering; } @@ -1092,7 +1096,7 @@ int run_devmem_tests(void) goto err_reset_headersplit; } - if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) { + if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys, 0)) { pr_err("Binding empty queues array should have failed"); goto err_unbind; } @@ -1108,7 +1112,7 @@ int run_devmem_tests(void) goto err_reset_headersplit; } - if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) { + if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys, 0)) { pr_err("Configure dmabuf with header split off should have failed"); goto err_unbind; } @@ -1124,7 +1128,7 @@ int run_devmem_tests(void) goto err_reset_headersplit; } - if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) { + if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys, 0)) { pr_err("Failed to bind"); goto err_reset_headersplit; } @@ -1397,7 +1401,7 @@ int main(int argc, char *argv[]) int is_server = 0, opt; int ret, err = 1; - while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:z:")) != -1) { + while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:z:a:")) != -1) { switch (opt) { case 'l': is_server = 1; @@ -1426,6 +1430,9 @@ int main(int argc, char *argv[]) case 'z': max_chunk = atoi(optarg); break; + case 'a': + devmem_autorelease = atoi(optarg); + break; case '?': fprintf(stderr, "unknown option: %c\n", optopt); break; -- 2.47.3

16 minutes

[PATCH net-next v9 4/5] net: devmem: document NETDEV_A_DMABUF_AUTORELEASE netlink attribute

by Bobby Eshleman

From: Bobby Eshleman <bobbyeshleman(a)meta.com> Update devmem.rst documentation to describe the autorelease netlink attribute used during RX dmabuf binding. The autorelease attribute is specified at bind-time via the netlink API (NETDEV_CMD_BIND_RX) and controls what happens to outstanding tokens when the socket closes. Document the two token release modes (automatic vs manual), how to configure the binding for autorelease, the perf benefits, new caveats and restrictions, and the way the mode is enforced system-wide. Signed-off-by: Bobby Eshleman <bobbyeshleman(a)meta.com> --- Changes in v7: - Document netlink instead of sockopt - Mention system-wide locked to one mode --- Documentation/networking/devmem.rst | 70 +++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) diff --git a/Documentation/networking/devmem.rst b/Documentation/networking/devmem.rst index a6cd7236bfbd..67c63bc5a7ae 100644 --- a/Documentation/networking/devmem.rst +++ b/Documentation/networking/devmem.rst @@ -235,6 +235,76 @@ can be less than the tokens provided by the user in case of: (a) an internal kernel leak bug. (b) the user passed more than 1024 frags. + +Autorelease Control +~~~~~~~~~~~~~~~~~~~ + +The autorelease mode controls what happens to outstanding tokens (tokens not +released via SO_DEVMEM_DONTNEED) when the socket closes. Autorelease is +configured per-binding at binding creation time via the netlink API:: + + struct netdev_bind_rx_req *req; + struct netdev_bind_rx_rsp *rsp; + struct ynl_sock *ys; + struct ynl_error yerr; + + ys = ynl_sock_create(&ynl_netdev_family, &yerr); + + req = netdev_bind_rx_req_alloc(); + netdev_bind_rx_req_set_ifindex(req, ifindex); + netdev_bind_rx_req_set_fd(req, dmabuf_fd); + netdev_bind_rx_req_set_autorelease(req, 0); /* 0 = manual, 1 = auto */ + __netdev_bind_rx_req_set_queues(req, queues, n_queues); + + rsp = netdev_bind_rx(ys, req); + + dmabuf_id = rsp->id; + +When autorelease is disabled (0): + +- Outstanding tokens are NOT released when the socket closes +- Outstanding tokens are only released when the dmabuf is unbound +- Provides better performance by eliminating xarray overhead (~13% CPU reduction) +- Kernel tracks tokens via atomic reference counters in net_iov structures + +When autorelease is enabled (1): + +- Outstanding tokens are automatically released when the socket closes +- Backwards compatible behavior +- Kernel tracks tokens in an xarray per socket + +The default is autorelease disabled. + +Important: In both modes, applications should call SO_DEVMEM_DONTNEED to +return tokens as soon as they are done processing. The autorelease setting only +affects what happens to tokens that are still outstanding when close() is called. + +The mode is enforced system-wide. Once a binding is created with a specific +autorelease mode, all subsequent bindings system-wide must use the same mode. + + +Performance Considerations +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Disabling autorelease provides approximately ~13% CPU utilization improvement +in RX workloads. That said, applications must ensure all tokens are released +via SO_DEVMEM_DONTNEED before closing the socket, otherwise the backing pages +will remain pinned until the dmabuf is unbound. + + +Caveats +~~~~~~~ + +- Once a system-wide autorelease mode is selected (via the first binding), + all subsequent bindings must use the same mode. Attempts to create bindings + with a different mode will be rejected with -EINVAL. + +- Applications using manual release mode (autorelease=0) must ensure all tokens + are returned via SO_DEVMEM_DONTNEED before socket close to avoid resource + leaks during the lifetime of the dmabuf binding. Tokens not released before + close() will only be freed when the dmabuf is unbound. + + TX Interface ============ -- 2.47.3

16 minutes

[PATCH net-next v9 3/5] net: devmem: implement autorelease token management

by Bobby Eshleman

From: Bobby Eshleman <bobbyeshleman(a)meta.com> Add support for autorelease toggling of tokens using a static branch to control system-wide behavior. This allows applications to choose between two memory management modes: 1. Autorelease on: Leaked tokens are automatically released when the socket closes. 2. Autorelease off: Leaked tokens are released during dmabuf unbind. The autorelease mode is requested via the NETDEV_A_DMABUF_AUTORELEASE attribute of the NETDEV_CMD_BIND_RX message. Having separate modes per binding is disallowed and is rejected by netlink. The system will be "locked" into the mode that the first binding is set to. It can only be changed again once there are zero bindings on the system. Disabling autorelease offers ~13% improvement in CPU utilization. Static branching is used to limit the system to one mode or the other. Signed-off-by: Bobby Eshleman <bobbyeshleman(a)meta.com> --- Changes in v9: - Add missing stub for net_devmem_dmabuf_binding_get() when NET_DEVMEM=n - Add wrapper around tcp_devmem_ar_key accesses so that it may be stubbed out when NET_DEVMEM=n - only dec rx binding count for rx bindings in free (v8 did not exclude TX bindings) Changes in v8: - Only reset static key when bindings go to zero, defaulting back to disabled (Stan). - Fix bad usage of xarray spinlock for sleepy static branch switching, use mutex instead. - Access pp_ref_count via niov->desc instead of niov directly. - Move reset of static key to __net_devmem_dmabuf_binding_free() so that the static key can not be changed while there are outstanding tokens (free is only called when reference count reaches zero). - Add net_devmem_dmabuf_rx_bindings_count because tokens may be active even after xa_erase(), so static key changes must wait until all RX bindings are finally freed (not just when xarray is empty). A counter is a simple way to track this. - socket takes reference on the binding, to avoid use-after-free on sk_devmem_info.binding in the case that user releases all tokens, unbinds, then issues SO_DEVMEM_DONTNEED again (with bad token). - removed some comments that were unnecessary Changes in v7: - implement autorelease with static branch (Stan) - use netlink instead of sockopt (Stan) - merge uAPI and implementation patches into one patch (seemed less confusing) Changes in v6: - remove sk_devmem_info.autorelease, using binding->autorelease instead - move binding->autorelease check to outside of net_devmem_dmabuf_binding_put_urefs() (Mina) - remove overly defensive net_is_devmem_iov() (Mina) - add comment about multiple urefs mapping to a single netmem ref (Mina) - remove overly defense netmem NULL and netmem_is_net_iov checks (Mina) - use niov without casting back and forth with netmem (Mina) - move the autorelease flag from per-binding to per-socket (Mina) - remove the batching logic in sock_devmem_dontneed_manual_release() (Mina) - move autorelease check inside tcp_xa_pool_commit() (Mina) - remove single-binding restriction for autorelease mode (Mina) - unbind always checks for leaked urefs Changes in v5: - remove unused variables - introduce autorelease flag, preparing for future patch toggle new behavior Changes in v3: - make urefs per-binding instead of per-socket, reducing memory footprint - fallback to cleaning up references in dmabuf unbind if socket leaked tokens - drop ethtool patch Changes in v2: - always use GFP_ZERO for binding->vec (Mina) - remove WARN for changed binding (Mina) - remove extraneous binding ref get (Mina) - remove WARNs on invalid user input (Mina) - pre-assign niovs in binding->vec for RX case (Mina) - use atomic_set(, 0) to initialize sk_user_frags.urefs - fix length of alloc for urefs --- Documentation/netlink/specs/netdev.yaml | 12 ++++ include/net/netmem.h | 1 + include/net/sock.h | 7 ++- include/uapi/linux/netdev.h | 1 + net/core/devmem.c | 104 ++++++++++++++++++++++++++++---- net/core/devmem.h | 27 ++++++++- net/core/netdev-genl-gen.c | 5 +- net/core/netdev-genl.c | 10 ++- net/core/sock.c | 57 +++++++++++++++-- net/ipv4/tcp.c | 76 ++++++++++++++++++----- net/ipv4/tcp_ipv4.c | 11 +++- net/ipv4/tcp_minisocks.c | 3 +- tools/include/uapi/linux/netdev.h | 1 + 13 files changed, 269 insertions(+), 46 deletions(-) diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 596c306ce52b..7cbe9e7b9ee5 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -562,6 +562,17 @@ attribute-sets: type: u32 checks: min: 1 + - + name: autorelease + doc: | + Token autorelease mode. If true (1), leaked tokens are automatically + released when the socket closes. If false (0), leaked tokens are only + released when the dmabuf is unbound. Once a binding is created with a + specific mode, all subsequent bindings system-wide must use the same + mode. + + Optional. Defaults to false if not specified. + type: u8 operations: list: @@ -769,6 +780,7 @@ operations: - ifindex - fd - queues + - autorelease reply: attributes: - id diff --git a/include/net/netmem.h b/include/net/netmem.h index 9e10f4ac50c3..80d2263ba4ed 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -112,6 +112,7 @@ struct net_iov { }; struct net_iov_area *owner; enum net_iov_type type; + atomic_t uref; }; struct net_iov_area { diff --git a/include/net/sock.h b/include/net/sock.h index aafe8bdb2c0f..9d3d5bde15e9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -352,7 +352,7 @@ struct sk_filter; * @sk_scm_rights: flagged by SO_PASSRIGHTS to recv SCM_RIGHTS * @sk_scm_unused: unused flags for scm_recv() * @ns_tracker: tracker for netns reference - * @sk_user_frags: xarray of pages the user is holding a reference on. + * @sk_devmem_info: the devmem binding information for the socket * @sk_owner: reference to the real owner of the socket that calls * sock_lock_init_class_and_name(). */ @@ -584,7 +584,10 @@ struct sock { struct numa_drop_counters *sk_drop_counters; struct rcu_head sk_rcu; netns_tracker ns_tracker; - struct xarray sk_user_frags; + struct { + struct xarray frags; + struct net_devmem_dmabuf_binding *binding; + } sk_devmem_info; #if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) struct module *sk_owner; diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index e0b579a1df4f..1e5c209cb998 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -207,6 +207,7 @@ enum { NETDEV_A_DMABUF_QUEUES, NETDEV_A_DMABUF_FD, NETDEV_A_DMABUF_ID, + NETDEV_A_DMABUF_AUTORELEASE, __NETDEV_A_DMABUF_MAX, NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1) diff --git a/net/core/devmem.c b/net/core/devmem.c index 05a9a9e7abb9..05c16df657c7 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -11,6 +11,7 @@ #include <linux/genalloc.h> #include <linux/mm.h> #include <linux/netdevice.h> +#include <linux/skbuff_ref.h> #include <linux/types.h> #include <net/netdev_queues.h> #include <net/netdev_rx_queue.h> @@ -28,6 +29,19 @@ static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1); +/* If the user unbinds before releasing all tokens, the static key must not + * change until all tokens have been released (to avoid calling the wrong + * SO_DEVMEM_DONTNEED handler). We prevent this by making static key changes + * and binding alloc/free atomic with regards to each other, using the + * devmem_ar_lock. This works because binding free does not occur until all of + * the outstanding token's references on the binding are dropped. + */ +static DEFINE_MUTEX(devmem_ar_lock); + +DEFINE_STATIC_KEY_FALSE(tcp_devmem_ar_key); +EXPORT_SYMBOL(tcp_devmem_ar_key); +static int net_devmem_dmabuf_rx_bindings_count; + static const struct memory_provider_ops dmabuf_devmem_ops; bool net_is_devmem_iov(struct net_iov *niov) @@ -60,6 +74,14 @@ void __net_devmem_dmabuf_binding_free(struct work_struct *wq) size_t size, avail; + if (binding->direction == DMA_FROM_DEVICE) { + mutex_lock(&devmem_ar_lock); + net_devmem_dmabuf_rx_bindings_count--; + if (net_devmem_dmabuf_rx_bindings_count == 0) + static_branch_disable(&tcp_devmem_ar_key); + mutex_unlock(&devmem_ar_lock); + } + gen_pool_for_each_chunk(binding->chunk_pool, net_devmem_dmabuf_free_chunk_owner, NULL); @@ -116,6 +138,24 @@ void net_devmem_free_dmabuf(struct net_iov *niov) gen_pool_free(binding->chunk_pool, dma_addr, PAGE_SIZE); } +static void +net_devmem_dmabuf_binding_put_urefs(struct net_devmem_dmabuf_binding *binding) +{ + int i; + + for (i = 0; i < binding->dmabuf->size / PAGE_SIZE; i++) { + struct net_iov *niov; + netmem_ref netmem; + + niov = binding->vec[i]; + netmem = net_iov_to_netmem(niov); + + /* Multiple urefs map to only a single netmem ref. */ + if (atomic_xchg(&niov->uref, 0) > 0) + WARN_ON_ONCE(!napi_pp_put_page(netmem)); + } +} + void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) { struct netdev_rx_queue *rxq; @@ -143,6 +183,7 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) __net_mp_close_rxq(binding->dev, rxq_idx, &mp_params); } + net_devmem_dmabuf_binding_put_urefs(binding); net_devmem_dmabuf_binding_put(binding); } @@ -179,8 +220,10 @@ struct net_devmem_dmabuf_binding * net_devmem_bind_dmabuf(struct net_device *dev, struct device *dma_dev, enum dma_data_direction direction, - unsigned int dmabuf_fd, struct netdev_nl_sock *priv, - struct netlink_ext_ack *extack) + unsigned int dmabuf_fd, + struct netdev_nl_sock *priv, + struct netlink_ext_ack *extack, + bool autorelease) { struct net_devmem_dmabuf_binding *binding; static u32 id_alloc_next; @@ -231,14 +274,12 @@ net_devmem_bind_dmabuf(struct net_device *dev, goto err_detach; } - if (direction == DMA_TO_DEVICE) { - binding->vec = kvmalloc_array(dmabuf->size / PAGE_SIZE, - sizeof(struct net_iov *), - GFP_KERNEL); - if (!binding->vec) { - err = -ENOMEM; - goto err_unmap; - } + binding->vec = kvmalloc_array(dmabuf->size / PAGE_SIZE, + sizeof(struct net_iov *), + GFP_KERNEL | __GFP_ZERO); + if (!binding->vec) { + err = -ENOMEM; + goto err_unmap; } /* For simplicity we expect to make PAGE_SIZE allocations, but the @@ -292,25 +333,62 @@ net_devmem_bind_dmabuf(struct net_device *dev, niov = &owner->area.niovs[i]; niov->type = NET_IOV_DMABUF; niov->owner = &owner->area; + atomic_set(&niov->uref, 0); page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov), net_devmem_get_dma_addr(niov)); - if (direction == DMA_TO_DEVICE) - binding->vec[owner->area.base_virtual / PAGE_SIZE + i] = niov; + binding->vec[owner->area.base_virtual / PAGE_SIZE + i] = niov; } virtual += len; } + mutex_lock(&devmem_ar_lock); + + if (direction == DMA_FROM_DEVICE) { + if (net_devmem_dmabuf_rx_bindings_count > 0) { + bool mode; + + mode = static_key_enabled(&tcp_devmem_ar_key); + + /* When bindings exist, enforce that the mode does not + * change. + */ + if (mode != autorelease) { + NL_SET_ERR_MSG_FMT(extack, + "System already configured with autorelease=%d", + mode); + err = -EINVAL; + goto err_unlock_mutex; + } + } else if (autorelease) { + /* First binding with autorelease enabled sets the + * mode. If autorelease is false, the key is already + * disabled by default so no action is needed. + */ + static_branch_enable(&tcp_devmem_ar_key); + } + + net_devmem_dmabuf_rx_bindings_count++; + } + 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_chunks; + goto err_dec_binding_count; + + mutex_unlock(&devmem_ar_lock); list_add(&binding->list, &priv->bindings); return binding; +err_dec_binding_count: + if (direction == DMA_FROM_DEVICE) + net_devmem_dmabuf_rx_bindings_count--; + +err_unlock_mutex: + mutex_unlock(&devmem_ar_lock); err_free_chunks: gen_pool_for_each_chunk(binding->chunk_pool, net_devmem_dmabuf_free_chunk_owner, NULL); diff --git a/net/core/devmem.h b/net/core/devmem.h index 1ea6228e4f40..8c586f30e371 100644 --- a/net/core/devmem.h +++ b/net/core/devmem.h @@ -12,9 +12,13 @@ #include <net/netmem.h> #include <net/netdev_netlink.h> +#include <linux/jump_label.h> struct netlink_ext_ack; +/* static key for TCP devmem autorelease */ +extern struct static_key_false tcp_devmem_ar_key; + struct net_devmem_dmabuf_binding { struct dma_buf *dmabuf; struct dma_buf_attachment *attachment; @@ -61,7 +65,7 @@ struct net_devmem_dmabuf_binding { /* Array of net_iov pointers for this binding, sorted by virtual * address. This array is convenient to map the virtual addresses to - * net_iovs in the TX path. + * net_iovs. */ struct net_iov **vec; @@ -88,7 +92,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, struct device *dma_dev, enum dma_data_direction direction, unsigned int dmabuf_fd, struct netdev_nl_sock *priv, - struct netlink_ext_ack *extack); + struct netlink_ext_ack *extack, bool autorelease); struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id); 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, @@ -138,6 +142,11 @@ net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding) schedule_work(&binding->unbind_w); } +static inline bool net_devmem_autorelease_enabled(void) +{ + return static_branch_unlikely(&tcp_devmem_ar_key); +} + void net_devmem_get_net_iov(struct net_iov *niov); void net_devmem_put_net_iov(struct net_iov *niov); @@ -155,6 +164,12 @@ net_devmem_get_niov_at(struct net_devmem_dmabuf_binding *binding, size_t addr, #else struct net_devmem_dmabuf_binding; +static inline bool +net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding) +{ + return false; +} + static inline void net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding) { @@ -174,7 +189,8 @@ net_devmem_bind_dmabuf(struct net_device *dev, enum dma_data_direction direction, unsigned int dmabuf_fd, struct netdev_nl_sock *priv, - struct netlink_ext_ack *extack) + struct netlink_ext_ack *extack, + bool autorelease) { return ERR_PTR(-EOPNOTSUPP); } @@ -241,6 +257,11 @@ net_devmem_iov_binding(const struct net_iov *niov) { return NULL; } + +static inline bool net_devmem_autorelease_enabled(void) +{ + return false; +} #endif #endif /* _NET_DEVMEM_H */ diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index ba673e81716f..01b7765e11ec 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -86,10 +86,11 @@ static const struct nla_policy netdev_qstats_get_nl_policy[NETDEV_A_QSTATS_SCOPE }; /* NETDEV_CMD_BIND_RX - do */ -static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD + 1] = { +static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_AUTORELEASE + 1] = { [NETDEV_A_DMABUF_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), [NETDEV_A_DMABUF_FD] = { .type = NLA_U32, }, [NETDEV_A_DMABUF_QUEUES] = NLA_POLICY_NESTED(netdev_queue_id_nl_policy), + [NETDEV_A_DMABUF_AUTORELEASE] = { .type = NLA_U8, }, }; /* NETDEV_CMD_NAPI_SET - do */ @@ -188,7 +189,7 @@ static const struct genl_split_ops netdev_nl_ops[] = { .cmd = NETDEV_CMD_BIND_RX, .doit = netdev_nl_bind_rx_doit, .policy = netdev_bind_rx_nl_policy, - .maxattr = NETDEV_A_DMABUF_FD, + .maxattr = NETDEV_A_DMABUF_AUTORELEASE, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, { diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 470fabbeacd9..c742bb34865e 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -939,6 +939,7 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) struct netdev_nl_sock *priv; struct net_device *netdev; unsigned long *rxq_bitmap; + bool autorelease = false; struct device *dma_dev; struct sk_buff *rsp; int err = 0; @@ -952,6 +953,10 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]); + if (info->attrs[NETDEV_A_DMABUF_AUTORELEASE]) + autorelease = + !!nla_get_u8(info->attrs[NETDEV_A_DMABUF_AUTORELEASE]); + priv = genl_sk_priv_get(&netdev_nl_family, NETLINK_CB(skb).sk); if (IS_ERR(priv)) return PTR_ERR(priv); @@ -1002,7 +1007,8 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) } binding = net_devmem_bind_dmabuf(netdev, dma_dev, DMA_FROM_DEVICE, - dmabuf_fd, priv, info->extack); + dmabuf_fd, priv, info->extack, + autorelease); if (IS_ERR(binding)) { err = PTR_ERR(binding); goto err_rxq_bitmap; @@ -1097,7 +1103,7 @@ int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info) dma_dev = netdev_queue_get_dma_dev(netdev, 0); binding = net_devmem_bind_dmabuf(netdev, dma_dev, DMA_TO_DEVICE, - dmabuf_fd, priv, info->extack); + dmabuf_fd, priv, info->extack, false); if (IS_ERR(binding)) { err = PTR_ERR(binding); goto err_unlock_netdev; diff --git a/net/core/sock.c b/net/core/sock.c index f6526f43aa6e..6355c2ccfb8a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -87,6 +87,7 @@ #include <linux/unaligned.h> #include <linux/capability.h> +#include <linux/dma-buf.h> #include <linux/errno.h> #include <linux/errqueue.h> #include <linux/types.h> @@ -151,6 +152,7 @@ #include <uapi/linux/pidfd.h> #include "dev.h" +#include "devmem.h" static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); @@ -1081,6 +1083,44 @@ static int sock_reserve_memory(struct sock *sk, int bytes) #define MAX_DONTNEED_TOKENS 128 #define MAX_DONTNEED_FRAGS 1024 +static noinline_for_stack int +sock_devmem_dontneed_manual_release(struct sock *sk, + struct dmabuf_token *tokens, + unsigned int num_tokens) +{ + struct net_iov *niov; + unsigned int i, j; + netmem_ref netmem; + unsigned int token; + int num_frags = 0; + int ret = 0; + + if (!sk->sk_devmem_info.binding) + return -EINVAL; + + for (i = 0; i < num_tokens; i++) { + for (j = 0; j < tokens[i].token_count; j++) { + size_t size = sk->sk_devmem_info.binding->dmabuf->size; + + token = tokens[i].token_start + j; + if (token >= size / PAGE_SIZE) + break; + + if (++num_frags > MAX_DONTNEED_FRAGS) + return ret; + + niov = sk->sk_devmem_info.binding->vec[token]; + if (atomic_dec_and_test(&niov->uref)) { + netmem = net_iov_to_netmem(niov); + WARN_ON_ONCE(!napi_pp_put_page(netmem)); + } + ret++; + } + } + + return ret; +} + static noinline_for_stack int sock_devmem_dontneed_autorelease(struct sock *sk, struct dmabuf_token *tokens, unsigned int num_tokens) @@ -1089,32 +1129,33 @@ sock_devmem_dontneed_autorelease(struct sock *sk, struct dmabuf_token *tokens, int ret = 0, num_frags = 0; netmem_ref netmems[16]; - xa_lock_bh(&sk->sk_user_frags); + xa_lock_bh(&sk->sk_devmem_info.frags); for (i = 0; i < num_tokens; i++) { for (j = 0; j < tokens[i].token_count; j++) { if (++num_frags > MAX_DONTNEED_FRAGS) goto frag_limit_reached; netmem_ref netmem = (__force netmem_ref)__xa_erase( - &sk->sk_user_frags, tokens[i].token_start + j); + &sk->sk_devmem_info.frags, + tokens[i].token_start + j); if (!netmem || WARN_ON_ONCE(!netmem_is_net_iov(netmem))) continue; netmems[netmem_num++] = netmem; if (netmem_num == ARRAY_SIZE(netmems)) { - xa_unlock_bh(&sk->sk_user_frags); + xa_unlock_bh(&sk->sk_devmem_info.frags); for (k = 0; k < netmem_num; k++) WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); netmem_num = 0; - xa_lock_bh(&sk->sk_user_frags); + xa_lock_bh(&sk->sk_devmem_info.frags); } ret++; } } frag_limit_reached: - xa_unlock_bh(&sk->sk_user_frags); + xa_unlock_bh(&sk->sk_devmem_info.frags); for (k = 0; k < netmem_num; k++) WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); @@ -1145,7 +1186,11 @@ sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen) return -EFAULT; } - ret = sock_devmem_dontneed_autorelease(sk, tokens, num_tokens); + if (net_devmem_autorelease_enabled()) + ret = sock_devmem_dontneed_autorelease(sk, tokens, num_tokens); + else + ret = sock_devmem_dontneed_manual_release(sk, tokens, + num_tokens); kvfree(tokens); return ret; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d5319ebe2452..a8a4af552909 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -260,6 +260,7 @@ #include <linux/memblock.h> #include <linux/highmem.h> #include <linux/cache.h> +#include <linux/dma-buf.h> #include <linux/err.h> #include <linux/time.h> #include <linux/slab.h> @@ -492,7 +493,8 @@ 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); + xa_init_flags(&sk->sk_devmem_info.frags, XA_FLAGS_ALLOC1); + sk->sk_devmem_info.binding = NULL; } EXPORT_IPV6_MOD(tcp_init_sock); @@ -2424,11 +2426,12 @@ static void tcp_xa_pool_commit_locked(struct sock *sk, struct tcp_xa_pool *p) /* 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); + __xa_cmpxchg(&sk->sk_devmem_info.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]); + __xa_erase(&sk->sk_devmem_info.frags, p->tokens[i]); p->max = 0; p->idx = 0; @@ -2436,14 +2439,18 @@ static void tcp_xa_pool_commit_locked(struct sock *sk, struct tcp_xa_pool *p) static void tcp_xa_pool_commit(struct sock *sk, struct tcp_xa_pool *p) { + /* Skip xarray operations if autorelease is disabled (manual mode) */ + if (!net_devmem_autorelease_enabled()) + return; + if (!p->max) return; - xa_lock_bh(&sk->sk_user_frags); + xa_lock_bh(&sk->sk_devmem_info.frags); tcp_xa_pool_commit_locked(sk, p); - xa_unlock_bh(&sk->sk_user_frags); + xa_unlock_bh(&sk->sk_devmem_info.frags); } static int tcp_xa_pool_refill(struct sock *sk, struct tcp_xa_pool *p, @@ -2454,24 +2461,41 @@ static int tcp_xa_pool_refill(struct sock *sk, struct tcp_xa_pool *p, if (p->idx < p->max) return 0; - xa_lock_bh(&sk->sk_user_frags); + xa_lock_bh(&sk->sk_devmem_info.frags); tcp_xa_pool_commit_locked(sk, p); for (k = 0; k < max_frags; k++) { - err = __xa_alloc(&sk->sk_user_frags, &p->tokens[k], + err = __xa_alloc(&sk->sk_devmem_info.frags, &p->tokens[k], XA_ZERO_ENTRY, xa_limit_31b, GFP_KERNEL); if (err) break; } - xa_unlock_bh(&sk->sk_user_frags); + xa_unlock_bh(&sk->sk_devmem_info.frags); p->max = k; p->idx = 0; return k ? 0 : err; } +static void tcp_xa_pool_inc_pp_ref_count(struct tcp_xa_pool *tcp_xa_pool, + skb_frag_t *frag) +{ + struct net_iov *niov; + + niov = skb_frag_net_iov(frag); + + if (net_devmem_autorelease_enabled()) { + atomic_long_inc(&niov->desc.pp_ref_count); + tcp_xa_pool->netmems[tcp_xa_pool->idx++] = + skb_frag_netmem(frag); + } else { + if (atomic_inc_return(&niov->uref) == 1) + atomic_long_inc(&niov->desc.pp_ref_count); + } +} + /* On error, returns the -errno. On success, returns number of bytes sent to the * user. May not consume all of @remaining_len. */ @@ -2533,6 +2557,7 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, * sequence of cmsg */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + struct net_devmem_dmabuf_binding *binding = NULL; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; struct net_iov *niov; u64 frag_offset; @@ -2568,13 +2593,35 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, 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) + + binding = net_devmem_iov_binding(niov); + + if (!sk->sk_devmem_info.binding) { + net_devmem_dmabuf_binding_get(binding); + sk->sk_devmem_info.binding = binding; + } + + if (sk->sk_devmem_info.binding != binding) { + err = -EFAULT; goto out; + } + + if (net_devmem_autorelease_enabled()) { + err = tcp_xa_pool_refill(sk, + &tcp_xa_pool, + skb_shinfo(skb)->nr_frags - i); + if (err) + goto out; + + dmabuf_cmsg.frag_token = + tcp_xa_pool.tokens[tcp_xa_pool.idx]; + } else { + dmabuf_cmsg.frag_token = + net_iov_virtual_addr(niov) >> PAGE_SHIFT; + } + /* Will perform the exchange later */ - dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx]; dmabuf_cmsg.dmabuf_id = net_devmem_iov_binding_id(niov); offset += copy; @@ -2587,8 +2634,7 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, if (err) goto out; - atomic_long_inc(&niov->desc.pp_ref_count); - tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); + tcp_xa_pool_inc_pp_ref_count(&tcp_xa_pool, frag); sent += copy; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f8a9596e8f4d..7b1b5a17002f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -89,6 +89,9 @@ #include <crypto/md5.h> +#include <linux/dma-buf.h> +#include "../core/devmem.h" + #include <trace/events/tcp.h> #ifdef CONFIG_TCP_MD5SIG @@ -2492,7 +2495,7 @@ static void tcp_release_user_frags(struct sock *sk) unsigned long index; void *netmem; - xa_for_each(&sk->sk_user_frags, index, netmem) + xa_for_each(&sk->sk_devmem_info.frags, index, netmem) WARN_ON_ONCE(!napi_pp_put_page((__force netmem_ref)netmem)); #endif } @@ -2503,7 +2506,11 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_release_user_frags(sk); - xa_destroy(&sk->sk_user_frags); + xa_destroy(&sk->sk_devmem_info.frags); + if (sk->sk_devmem_info.binding) { + net_devmem_dmabuf_binding_put(sk->sk_devmem_info.binding); + sk->sk_devmem_info.binding = NULL; + } trace_tcp_destroy_sock(sk); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index bd5462154f97..2aec977f5c12 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -662,7 +662,8 @@ 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); + xa_init_flags(&newsk->sk_devmem_info.frags, XA_FLAGS_ALLOC1); + newsk->sk_devmem_info.binding = NULL; return newsk; } diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index e0b579a1df4f..1e5c209cb998 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -207,6 +207,7 @@ enum { NETDEV_A_DMABUF_QUEUES, NETDEV_A_DMABUF_FD, NETDEV_A_DMABUF_ID, + NETDEV_A_DMABUF_AUTORELEASE, __NETDEV_A_DMABUF_MAX, NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1) -- 2.47.3

16 minutes

[PATCH net-next v9 2/5] net: devmem: refactor sock_devmem_dontneed for autorelease split

by Bobby Eshleman

From: Bobby Eshleman <bobbyeshleman(a)meta.com> Refactor sock_devmem_dontneed() in preparation for supporting both autorelease and manual token release modes. Split the function into two parts: - sock_devmem_dontneed(): handles input validation, token allocation, and copying from userspace - sock_devmem_dontneed_autorelease(): performs the actual token release via xarray lookup and page pool put This separation allows a future commit to add a parallel sock_devmem_dontneed_manual_release() function that uses a different token tracking mechanism (per-niov reference counting) without duplicating the input validation logic. The refactoring is purely mechanical with no functional change. Only intended to minimize the noise in subsequent patches. Reviewed-by: Mina Almasry <almasrymina(a)google.com> Signed-off-by: Bobby Eshleman <bobbyeshleman(a)meta.com> --- net/core/sock.c | 52 ++++++++++++++++++++++++++++++++-------------------- 1 file changed, 32 insertions(+), 20 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index a1c8b47b0d56..f6526f43aa6e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1082,30 +1082,13 @@ static int sock_reserve_memory(struct sock *sk, int bytes) #define MAX_DONTNEED_FRAGS 1024 static noinline_for_stack int -sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen) +sock_devmem_dontneed_autorelease(struct sock *sk, struct dmabuf_token *tokens, + unsigned int num_tokens) { - unsigned int num_tokens, i, j, k, netmem_num = 0; - struct dmabuf_token *tokens; + unsigned int i, j, k, netmem_num = 0; int ret = 0, num_frags = 0; netmem_ref netmems[16]; - if (!sk_is_tcp(sk)) - return -EBADF; - - if (optlen % sizeof(*tokens) || - optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS) - return -EINVAL; - - num_tokens = optlen / sizeof(*tokens); - tokens = kvmalloc_array(num_tokens, sizeof(*tokens), GFP_KERNEL); - if (!tokens) - return -ENOMEM; - - if (copy_from_sockptr(tokens, optval, optlen)) { - kvfree(tokens); - return -EFAULT; - } - xa_lock_bh(&sk->sk_user_frags); for (i = 0; i < num_tokens; i++) { for (j = 0; j < tokens[i].token_count; j++) { @@ -1135,6 +1118,35 @@ sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen) for (k = 0; k < netmem_num; k++) WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); + return ret; +} + +static noinline_for_stack int +sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen) +{ + struct dmabuf_token *tokens; + unsigned int num_tokens; + int ret; + + if (!sk_is_tcp(sk)) + return -EBADF; + + if (optlen % sizeof(*tokens) || + optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS) + return -EINVAL; + + num_tokens = optlen / sizeof(*tokens); + tokens = kvmalloc_array(num_tokens, sizeof(*tokens), GFP_KERNEL); + if (!tokens) + return -ENOMEM; + + if (copy_from_sockptr(tokens, optval, optlen)) { + kvfree(tokens); + return -EFAULT; + } + + ret = sock_devmem_dontneed_autorelease(sk, tokens, num_tokens); + kvfree(tokens); return ret; } -- 2.47.3

16 minutes

[PATCH net-next v9 1/5] net: devmem: rename tx_vec to vec in dmabuf binding

by Bobby Eshleman

From: Bobby Eshleman <bobbyeshleman(a)meta.com> Rename the 'tx_vec' field in struct net_devmem_dmabuf_binding to 'vec'. This field holds pointers to net_iov structures. The rename prepares for reusing 'vec' for both TX and RX directions. No functional change intended. Reviewed-by: Mina Almasry <almasrymina(a)google.com> Signed-off-by: Bobby Eshleman <bobbyeshleman(a)meta.com> --- net/core/devmem.c | 22 +++++++++++----------- net/core/devmem.h | 2 +- 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/net/core/devmem.c b/net/core/devmem.c index ec4217d6c0b4..05a9a9e7abb9 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -75,7 +75,7 @@ void __net_devmem_dmabuf_binding_free(struct work_struct *wq) dma_buf_detach(binding->dmabuf, binding->attachment); dma_buf_put(binding->dmabuf); xa_destroy(&binding->bound_rxqs); - kvfree(binding->tx_vec); + kvfree(binding->vec); kfree(binding); } @@ -232,10 +232,10 @@ net_devmem_bind_dmabuf(struct net_device *dev, } if (direction == DMA_TO_DEVICE) { - binding->tx_vec = kvmalloc_array(dmabuf->size / PAGE_SIZE, - sizeof(struct net_iov *), - GFP_KERNEL); - if (!binding->tx_vec) { + binding->vec = kvmalloc_array(dmabuf->size / PAGE_SIZE, + sizeof(struct net_iov *), + GFP_KERNEL); + if (!binding->vec) { err = -ENOMEM; goto err_unmap; } @@ -249,7 +249,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, dev_to_node(&dev->dev)); if (!binding->chunk_pool) { err = -ENOMEM; - goto err_tx_vec; + goto err_vec; } virtual = 0; @@ -295,7 +295,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov), net_devmem_get_dma_addr(niov)); if (direction == DMA_TO_DEVICE) - binding->tx_vec[owner->area.base_virtual / PAGE_SIZE + i] = niov; + binding->vec[owner->area.base_virtual / PAGE_SIZE + i] = niov; } virtual += len; @@ -315,8 +315,8 @@ net_devmem_bind_dmabuf(struct net_device *dev, gen_pool_for_each_chunk(binding->chunk_pool, net_devmem_dmabuf_free_chunk_owner, NULL); gen_pool_destroy(binding->chunk_pool); -err_tx_vec: - kvfree(binding->tx_vec); +err_vec: + kvfree(binding->vec); err_unmap: dma_buf_unmap_attachment_unlocked(binding->attachment, binding->sgt, direction); @@ -363,7 +363,7 @@ struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk, int err = 0; binding = net_devmem_lookup_dmabuf(dmabuf_id); - if (!binding || !binding->tx_vec) { + if (!binding || !binding->vec) { err = -EINVAL; goto out_err; } @@ -414,7 +414,7 @@ net_devmem_get_niov_at(struct net_devmem_dmabuf_binding *binding, *off = virt_addr % PAGE_SIZE; *size = PAGE_SIZE - *off; - return binding->tx_vec[virt_addr / PAGE_SIZE]; + return binding->vec[virt_addr / PAGE_SIZE]; } /*** "Dmabuf devmem memory provider" ***/ diff --git a/net/core/devmem.h b/net/core/devmem.h index 0b43a648cd2e..1ea6228e4f40 100644 --- a/net/core/devmem.h +++ b/net/core/devmem.h @@ -63,7 +63,7 @@ struct net_devmem_dmabuf_binding { * address. This array is convenient to map the virtual addresses to * net_iovs in the TX path. */ - struct net_iov **tx_vec; + struct net_iov **vec; struct work_struct unbind_w; }; -- 2.47.3

16 minutes

[PATCH net-next] selftests: tls: avoid flakiness in data_steal

by Jakub Kicinski

We see the following failure a few times a week: # RUN global.data_steal ... # tls.c:3280:data_steal:Expected recv(cfd, buf2, sizeof(buf2), MSG_DONTWAIT) (10000) == -1 (-1) # data_steal: Test failed # FAIL global.data_steal not ok 8 global.data_steal The 10000 bytes read suggests that the child process did a recv() of half of the data using the TLS ULP and we're now getting the remaining half. The intent of the test is to get the child to enter _TCP_ recvmsg handler, so it needs to enter the syscall before parent installed the TLS recvmsg with setsockopt(SOL_TLS). Instead of the 10msec sleep send 1 byte of data and wait for the child to consume it. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: sd(a)queasysnail.net CC: shuah(a)kernel.org CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/net/tls.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index a4d16a460fbe..9e2ccea13d70 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -3260,17 +3260,25 @@ TEST(data_steal) { ASSERT_EQ(setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")), 0); /* Spawn a child and get it into the read wait path of the underlying - * TCP socket. + * TCP socket (before kernel .recvmsg is replaced with the TLS one). */ pid = fork(); ASSERT_GE(pid, 0); if (!pid) { - EXPECT_EQ(recv(cfd, buf, sizeof(buf) / 2, MSG_WAITALL), - sizeof(buf) / 2); + EXPECT_EQ(recv(cfd, buf, sizeof(buf) / 2 + 1, MSG_WAITALL), + sizeof(buf) / 2 + 1); exit(!__test_passed(_metadata)); } - usleep(10000); + /* Send a sync byte and poll until it's consumed to ensure + * the child is in recv() before we proceed to install TLS. + */ + ASSERT_EQ(send(fd, buf, 1, 0), 1); + do { + usleep(500); + } while (recv(cfd, buf, 1, MSG_PEEK | MSG_DONTWAIT) == 1); + EXPECT_EQ(errno, EAGAIN); + ASSERT_EQ(setsockopt(fd, SOL_TLS, TLS_TX, &tls, tls.len), 0); ASSERT_EQ(setsockopt(cfd, SOL_TLS, TLS_RX, &tls, tls.len), 0); -- 2.52.0

54 minutes

[PATCH net-next] selftests: drv-net: gro: increase the rcvbuf size

by Jakub Kicinski

The gro.py test (testing software GRO) is slightly flaky when running against fbnic. We see one flake per roughly 20 runs in NIPA, mostly in ipip.large, and always including some EAGAIN: # Shouldn't coalesce if exceed IP max pkt size: Test succeeded # Expected {65475 899 }, Total 2 packets # Received {65475 899 }, Total 2 packets. # Expected {64576 900 900 }, Total 3 packets # Received {64576 /home/virtme/testing/wt-24/tools/testing/selftests/drivers/net/gro: could not receive: Resource temporarily unavailable The test sends 2 large frames (64k + change). Looks like the default packet socket rcvbuf (~200kB) may not be large enough to hold them. Bump the rcvbuf to 1MB. Add a debug print showing socket statistics to make debugging this issue easier in the future. Without the rcvbuf increase we see: # Shouldn't coalesce if exceed IP max pkt size: Test succeeded # Expected {65475 899 }, Total 2 packets # Received {65475 899 }, Total 2 packets. # Expected {64576 900 900 }, Total 3 packets # Received {64576 Socket stats: packets=7, drops=3 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ # /home/virtme/testing/wt-24/tools/testing/selftests/drivers/net/gro: could not receive: Resource temporarily unavailable Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: willemb(a)google.com CC: anubhavsinggh(a)google.com CC: mohsin.bashr(a)gmail.com CC: shuah(a)kernel.org CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/drivers/net/gro.c | 25 ++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/drivers/net/gro.c b/tools/testing/selftests/drivers/net/gro.c index e894037d2e3e..751a8103f408 100644 --- a/tools/testing/selftests/drivers/net/gro.c +++ b/tools/testing/selftests/drivers/net/gro.c @@ -926,6 +926,28 @@ static void set_timeout(int fd) error(1, errno, "cannot set timeout, setsockopt failed"); } +static void set_rcvbuf(int fd) +{ + int bufsize = 1 * 1024 * 1024; /* 1 MB */ + + if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &bufsize, sizeof(bufsize))) + error(1, errno, "cannot set rcvbuf size, setsockopt failed"); +} + +static void recv_error(int fd, int rcv_errno) +{ + struct tpacket_stats stats; + socklen_t len; + + len = sizeof(stats); + if (getsockopt(fd, SOL_PACKET, PACKET_STATISTICS, &stats, &len)) + error(1, errno, "can't get stats"); + + fprintf(stderr, "Socket stats: packets=%u, drops=%u\n", + stats.tp_packets, stats.tp_drops); + error(1, rcv_errno, "could not receive"); +} + static void check_recv_pkts(int fd, int *correct_payload, int correct_num_pkts) { @@ -950,7 +972,7 @@ static void check_recv_pkts(int fd, int *correct_payload, ip_ext_len = 0; pkt_size = recv(fd, buffer, IP_MAXPACKET + ETH_HLEN + 1, 0); if (pkt_size < 0) - error(1, errno, "could not receive"); + recv_error(fd, errno); if (iph->version == 4) ip_ext_len = (iph->ihl - 5) * 4; @@ -1126,6 +1148,7 @@ static void gro_receiver(void) error(1, 0, "socket creation"); setup_sock_filter(rxfd); set_timeout(rxfd); + set_rcvbuf(rxfd); bind_packetsocket(rxfd); ksft_ready(); -- 2.52.0

54 minutes

[PATCH net-next] selftests: forwarding: update PTP tcpdump patterns

by Jakub Kicinski

Recent version of tcpdump (tcpdump-4.99.6-1.fc43.x86_64) seems to have removed the spurious space after msg type in PTP info, e.g.: before: PTPv2, majorSdoId: 0x0, msg type : sync msg, length: 44 after: PTPv2, majorSdoId: 0x0, msg type: sync msg, length: 44 Update our patterns to match both. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: vladimir.oltean(a)nxp.com CC: alexander.sverdlin(a)gmail.com CC: linux-kselftest(a)vger.kernel.org --- .../net/forwarding/local_termination.sh | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 892895659c7e..1f2bf6e81847 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -306,39 +306,39 @@ run_test() if [ $skip_ptp = false ]; then check_rcv $rcv_if_name "1588v2 over L2 transport, Sync" \ - "ethertype PTP (0x88f7).* PTPv2.* msg type : sync msg" \ + "ethertype PTP (0x88f7).* PTPv2.* msg type *: sync msg" \ true "$test_name" check_rcv $rcv_if_name "1588v2 over L2 transport, Follow-Up" \ - "ethertype PTP (0x88f7).* PTPv2.* msg type : follow up msg" \ + "ethertype PTP (0x88f7).* PTPv2.* msg type *: follow up msg" \ true "$test_name" check_rcv $rcv_if_name "1588v2 over L2 transport, Peer Delay Request" \ - "ethertype PTP (0x88f7).* PTPv2.* msg type : peer delay req msg" \ + "ethertype PTP (0x88f7).* PTPv2.* msg type *: peer delay req msg" \ true "$test_name" check_rcv $rcv_if_name "1588v2 over IPv4, Sync" \ - "ethertype IPv4 (0x0800).* PTPv2.* msg type : sync msg" \ + "ethertype IPv4 (0x0800).* PTPv2.* msg type *: sync msg" \ true "$test_name" check_rcv $rcv_if_name "1588v2 over IPv4, Follow-Up" \ - "ethertype IPv4 (0x0800).* PTPv2.* msg type : follow up msg" \ + "ethertype IPv4 (0x0800).* PTPv2.* msg type *: follow up msg" \ true "$test_name" check_rcv $rcv_if_name "1588v2 over IPv4, Peer Delay Request" \ - "ethertype IPv4 (0x0800).* PTPv2.* msg type : peer delay req msg" \ + "ethertype IPv4 (0x0800).* PTPv2.* msg type *: peer delay req msg" \ true "$test_name" check_rcv $rcv_if_name "1588v2 over IPv6, Sync" \ - "ethertype IPv6 (0x86dd).* PTPv2.* msg type : sync msg" \ + "ethertype IPv6 (0x86dd).* PTPv2.* msg type *: sync msg" \ true "$test_name" check_rcv $rcv_if_name "1588v2 over IPv6, Follow-Up" \ - "ethertype IPv6 (0x86dd).* PTPv2.* msg type : follow up msg" \ + "ethertype IPv6 (0x86dd).* PTPv2.* msg type *: follow up msg" \ true "$test_name" check_rcv $rcv_if_name "1588v2 over IPv6, Peer Delay Request" \ - "ethertype IPv6 (0x86dd).* PTPv2.* msg type : peer delay req msg" \ + "ethertype IPv6 (0x86dd).* PTPv2.* msg type *: peer delay req msg" \ true "$test_name" fi -- 2.52.0

54 minutes

[PATCH cgroup/for-6.20 v3 0/5] cgroup/cpuset: Don't invalidate sibling partitions on cpuset.cpus conflict

by Waiman Long

v3: - Patch 2: Change the condition for calling reset_partition_data() to (new_prs <= 0). - Patch 4: Update commit log and code comment to clarify the change. - Add a new patch 5 to move the empty cpus/mems check to cpuset1_validate_change(). v2: - Patch 1: additional comment - Patch 2: simplify the conditions for triggering call to compute_excpus(). - Patch 3: update description of cpuset.cpus.exclusive in cgroup-v2.rst to reflect the new behavior and change the name of the new cpus_excl_conflict() parameter to xcpus_changed. - Patch 4: update description of cpuset.cpus.partition in cgroup-v2.rst to clarify what exclusive CPUs will be used when a partition is created. This patch series is inspired by the cpuset patch sent by Sun Shaojie [1]. The idea is to avoid invalidating sibling partitions when there is a cpuset.cpus conflict. However this patch series does it in a slightly different way to make its behavior more consistent with other cpuset properties. The first 3 patches are just some cleanup and minor bug fixes on issues found during the investigation process. The last one is the major patch that changes the way cpuset.cpus is being handled during the partition creation process. Instead of invalidating sibling partitions when there is a conflict, it will strip out the conflicting exclusive CPUs and assign the remaining non-conflicting exclusive CPUs to the new partition unless there is no more CPU left which will fail the partition creation process. It is similar to the idea that cpuset.cpus.effective may only contain a subset of CPUs specified in cpuset.cpus. So cpuset.cpus.exclusive.effective may contain only a subset of cpuset.cpus when a partition is created without setting cpuset.cpus.exclusive. Even setting cpuset.cpus.exclusive instead of cpuset.cpus may not guarantee all the requested CPUs can be granted if parent doesn't have access to some of those exclusive CPUs. The difference is that conflicts from siblings is not possible with cpuset.cpus.exclusive as long as it can be set successfully without failure. [1] https://lore.kernel.org/lkml/20251117015708.977585-1-sunshaojie@kylinos.cn/ Waiman Long (5): cgroup/cpuset: Streamline rm_siblings_excl_cpus() cgroup/cpuset: Consistently compute effective_xcpus in update_cpumasks_hier() cgroup/cpuset: Don't fail cpuset.cpus change in v2 cgroup/cpuset: Don't invalidate sibling partitions on cpuset.cpus conflict cgroup/cpuset: Move the v1 empty cpus/mems check to cpuset1_validate_change() Documentation/admin-guide/cgroup-v2.rst | 40 +++-- kernel/cgroup/cpuset-internal.h | 12 ++ kernel/cgroup/cpuset-v1.c | 33 ++++ kernel/cgroup/cpuset.c | 163 ++++++------------ .../selftests/cgroup/test_cpuset_prs.sh | 29 +++- 5 files changed, 150 insertions(+), 127 deletions(-) -- 2.52.0

1 hour, 2 minutes

[PATCH] selftests/mm: ksm_tests: skip when not run as root

by Sun Jian

ksm_tests writes KSM sysfs knobs under /sys/kernel/mm/ksm, which requires root privileges. When run unprivileged, it fails with permission errors and reports FAIL, which is misleading. Skip the test early when not run as root to avoid false failures. Signed-off-by: Sun Jian <sun.jian.kdev(a)gmail.com> --- tools/testing/selftests/mm/ksm_tests.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index a0b48b839d54..c22cd9c61711 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -766,6 +766,11 @@ int main(int argc, char *argv[]) bool merge_across_nodes = KSM_MERGE_ACROSS_NODES_DEFAULT; long size_MB = 0; + if (geteuid() != 0) { + printf("# SKIP ksm_tests requires root privileges\n"); + return KSFT_SKIP; + } + while ((opt = getopt(argc, argv, "dha:p:l:z:m:s:t:MUZNPCHD")) != -1) { switch (opt) { case 'a': -- 2.43.0

1 hour, 18 minutes

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror