| Message ID | 20241221004236.2629280-4-almasrymina@google.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | Device memory TCP TX | expand |
On 12/21, Mina Almasry wrote: > Currently net_iovs support only pp ref counts, and do not support a > page ref equivalent. > > This is fine for the RX path as net_iovs are used exclusively with the > pp and only pp refcounting is needed there. The TX path however does not > use pp ref counts, thus, support for get_page/put_page equivalent is > needed for netmem. > > Support get_netmem/put_netmem. Check the type of the netmem before > passing it to page or net_iov specific code to obtain a page ref > equivalent. > > For dmabuf net_iovs, we obtain a ref on the underlying binding. This > ensures the entire binding doesn't disappear until all the net_iovs have > been put_netmem'ed. We do not need to track the refcount of individual > dmabuf net_iovs as we don't allocate/free them from a pool similar to > what the buddy allocator does for pages. > > This code is written to be extensible by other net_iov implementers. > get_netmem/put_netmem will check the type of the netmem and route it to > the correct helper: > > pages -> [get|put]_page() > dmabuf net_iovs -> net_devmem_[get|put]_net_iov() > new net_iovs -> new helpers > > Signed-off-by: Mina Almasry <almasrymina@google.com> > > --- > include/linux/skbuff_ref.h | 4 ++-- > include/net/netmem.h | 3 +++ > net/core/devmem.c | 10 ++++++++++ > net/core/devmem.h | 11 +++++++++++ > net/core/skbuff.c | 30 ++++++++++++++++++++++++++++++ > 5 files changed, 56 insertions(+), 2 deletions(-) > > diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h > index 0f3c58007488..9e49372ef1a0 100644 > --- a/include/linux/skbuff_ref.h > +++ b/include/linux/skbuff_ref.h > @@ -17,7 +17,7 @@ > */ > static inline void __skb_frag_ref(skb_frag_t *frag) > { > - get_page(skb_frag_page(frag)); > + get_netmem(skb_frag_netmem(frag)); > } > > /** > @@ -40,7 +40,7 @@ static inline void skb_page_unref(netmem_ref netmem, bool recycle) > if (recycle && napi_pp_put_page(netmem)) > return; > #endif [..] > - put_page(netmem_to_page(netmem)); > + put_netmem(netmem); I moved the release operation onto a workqueue in my series [1] to avoid calling dmabuf detach (which can sleep) from the socket close path (which is called with bh disabled). You should probably do something similar, see the trace attached below. 1: https://github.com/fomichev/linux/commit/3b3ad4f36771a376c204727e5a167c4993d4c65a#diff-3c58b866674b2f9beb5ac7349f81566e4df595c25c647710203549589d450f2dR436 (the condition to trigger that is to have an skb in the write queue and call close from the userspace) [ 1.548495] BUG: sleeping function called from invalid context at drivers/dma-buf/dma-buf.c:1255 [ 1.548741] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 149, name: ncdevmem [ 1.548926] preempt_count: 201, expected: 0 [ 1.549026] RCU nest depth: 0, expected: 0 [ 1.549197] [ 1.549237] ============================= [ 1.549331] [ BUG: Invalid wait context ] [ 1.549425] 6.13.0-rc3-00770-gbc9ef9606dc9-dirty #15 Tainted: G W [ 1.549609] ----------------------------- [ 1.549704] ncdevmem/149 is trying to lock: [ 1.549801] ffff8880066701c0 (reservation_ww_class_mutex){+.+.}-{4:4}, at: dma_buf_unmap_attachment_unlocked+0x4b/0x90 [ 1.550051] other info that might help us debug this: [ 1.550167] context-{5:5} [ 1.550229] 3 locks held by ncdevmem/149: [ 1.550322] #0: ffff888005730208 (&sb->s_type->i_mutex_key#11){+.+.}-{4:4}, at: sock_close+0x40/0xf0 [ 1.550530] #1: ffff88800b148f98 (sk_lock-AF_INET6){+.+.}-{0:0}, at: tcp_close+0x19/0x80 [ 1.550731] #2: ffff88800b148f18 (slock-AF_INET6){+.-.}-{3:3}, at: __tcp_close+0x185/0x4b0 [ 1.550921] stack backtrace: [ 1.550990] CPU: 0 UID: 0 PID: 149 Comm: ncdevmem Tainted: G W 6.13.0-rc3-00770-gbc9ef9606dc9-dirty #15 [ 1.551233] Tainted: [W]=WARN [ 1.551304] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.16.3-1-1 04/01/2014 [ 1.551518] Call Trace: [ 1.551584] <TASK> [ 1.551636] dump_stack_lvl+0x86/0xc0 [ 1.551723] __lock_acquire+0xb0f/0xc30 [ 1.551814] ? dma_buf_unmap_attachment_unlocked+0x4b/0x90 [ 1.551941] lock_acquire+0xf1/0x2a0 [ 1.552026] ? dma_buf_unmap_attachment_unlocked+0x4b/0x90 [ 1.552152] ? dma_buf_unmap_attachment_unlocked+0x4b/0x90 [ 1.552281] ? dma_buf_unmap_attachment_unlocked+0x4b/0x90 [ 1.552408] __ww_mutex_lock+0x121/0x1060 [ 1.552503] ? dma_buf_unmap_attachment_unlocked+0x4b/0x90 [ 1.552648] ww_mutex_lock+0x3d/0xa0 [ 1.552733] dma_buf_unmap_attachment_unlocked+0x4b/0x90 [ 1.552857] __net_devmem_dmabuf_binding_free+0x56/0xb0 [ 1.552979] skb_release_data+0x120/0x1f0 [ 1.553074] __kfree_skb+0x29/0xa0 [ 1.553156] tcp_write_queue_purge+0x41/0x310 [ 1.553259] tcp_v4_destroy_sock+0x127/0x320 [ 1.553363] ? __tcp_close+0x169/0x4b0 [ 1.553452] inet_csk_destroy_sock+0x53/0x130 [ 1.553560] __tcp_close+0x421/0x4b0 [ 1.553646] tcp_close+0x24/0x80 [ 1.553724] inet_release+0x5d/0x90 [ 1.553806] sock_close+0x4a/0xf0 [ 1.553886] __fput+0x9c/0x2b0 [ 1.553960] task_work_run+0x89/0xc0 [ 1.554046] do_exit+0x27f/0x980 [ 1.554125] do_group_exit+0xa4/0xb0 [ 1.554211] __x64_sys_exit_group+0x17/0x20 [ 1.554309] x64_sys_call+0x21a0/0x21a0 [ 1.554400] do_syscall_64+0xec/0x1d0 [ 1.554487] ? exc_page_fault+0x8a/0xf0 [ 1.554585] entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 1.554703] RIP: 0033:0x7f2f8a27abcd
diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h index 0f3c58007488..9e49372ef1a0 100644 --- a/include/linux/skbuff_ref.h +++ b/include/linux/skbuff_ref.h @@ -17,7 +17,7 @@ */ static inline void __skb_frag_ref(skb_frag_t *frag) { - get_page(skb_frag_page(frag)); + get_netmem(skb_frag_netmem(frag)); } /** @@ -40,7 +40,7 @@ static inline void skb_page_unref(netmem_ref netmem, bool recycle) if (recycle && napi_pp_put_page(netmem)) return; #endif - put_page(netmem_to_page(netmem)); + put_netmem(netmem); } /** diff --git a/include/net/netmem.h b/include/net/netmem.h index 1b58faa4f20f..d30f31878a09 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -245,4 +245,7 @@ static inline unsigned long netmem_get_dma_addr(netmem_ref netmem) return __netmem_clear_lsb(netmem)->dma_addr; } +void get_netmem(netmem_ref netmem); +void put_netmem(netmem_ref netmem); + #endif /* _NET_NETMEM_H */ diff --git a/net/core/devmem.c b/net/core/devmem.c index 0b6ed7525b22..f7e06a8cba01 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -322,6 +322,16 @@ void dev_dmabuf_uninstall(struct net_device *dev) } } +void net_devmem_get_net_iov(struct net_iov *niov) +{ + net_devmem_dmabuf_binding_get(niov->owner->binding); +} + +void net_devmem_put_net_iov(struct net_iov *niov) +{ + net_devmem_dmabuf_binding_put(niov->owner->binding); +} + /*** "Dmabuf devmem memory provider" ***/ int mp_dmabuf_devmem_init(struct page_pool *pool) diff --git a/net/core/devmem.h b/net/core/devmem.h index 76099ef9c482..54e30fea80b3 100644 --- a/net/core/devmem.h +++ b/net/core/devmem.h @@ -119,6 +119,9 @@ net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding) __net_devmem_dmabuf_binding_free(binding); } +void net_devmem_get_net_iov(struct net_iov *niov); +void net_devmem_put_net_iov(struct net_iov *niov); + struct net_iov * net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding); void net_devmem_free_dmabuf(struct net_iov *ppiov); @@ -126,6 +129,14 @@ void net_devmem_free_dmabuf(struct net_iov *ppiov); #else struct net_devmem_dmabuf_binding; +static inline void net_devmem_get_net_iov(struct net_iov *niov) +{ +} + +static inline void net_devmem_put_net_iov(struct net_iov *niov) +{ +} + static inline void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a441613a1e6c..815245d5c36b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -88,6 +88,7 @@ #include <linux/textsearch.h> #include "dev.h" +#include "devmem.h" #include "netmem_priv.h" #include "sock_destructor.h" @@ -7290,3 +7291,32 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, return false; } EXPORT_SYMBOL(csum_and_copy_from_iter_full); + +void get_netmem(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) { + /* Assume any net_iov is devmem and route it to + * net_devmem_get_net_iov. As new net_iov types are added they + * need to be checked here. + */ + net_devmem_get_net_iov(netmem_to_net_iov(netmem)); + return; + } + get_page(netmem_to_page(netmem)); +} +EXPORT_SYMBOL(get_netmem); + +void put_netmem(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) { + /* Assume any net_iov is devmem and route it to + * net_devmem_put_net_iov. As new net_iov types are added they + * need to be checked here. + */ + net_devmem_put_net_iov(netmem_to_net_iov(netmem)); + return; + } + + put_page(netmem_to_page(netmem)); +} +EXPORT_SYMBOL(put_netmem);
Currently net_iovs support only pp ref counts, and do not support a page ref equivalent. This is fine for the RX path as net_iovs are used exclusively with the pp and only pp refcounting is needed there. The TX path however does not use pp ref counts, thus, support for get_page/put_page equivalent is needed for netmem. Support get_netmem/put_netmem. Check the type of the netmem before passing it to page or net_iov specific code to obtain a page ref equivalent. For dmabuf net_iovs, we obtain a ref on the underlying binding. This ensures the entire binding doesn't disappear until all the net_iovs have been put_netmem'ed. We do not need to track the refcount of individual dmabuf net_iovs as we don't allocate/free them from a pool similar to what the buddy allocator does for pages. This code is written to be extensible by other net_iov implementers. get_netmem/put_netmem will check the type of the netmem and route it to the correct helper: pages -> [get|put]_page() dmabuf net_iovs -> net_devmem_[get|put]_net_iov() new net_iovs -> new helpers Signed-off-by: Mina Almasry <almasrymina@google.com> --- include/linux/skbuff_ref.h | 4 ++-- include/net/netmem.h | 3 +++ net/core/devmem.c | 10 ++++++++++ net/core/devmem.h | 11 +++++++++++ net/core/skbuff.c | 30 ++++++++++++++++++++++++++++++ 5 files changed, 56 insertions(+), 2 deletions(-)