kernel.git/net/core/page_pool.c, branch linux-6.15.y

net: page_pool: allow enabling recycling late, fix false positive warning

2025-08-20T16:35:48Z

[ Upstream commit 64fdaa94bfe0cca3a0f4b2dd922486c5f59fe678 ] Page pool can have pages "directly" (locklessly) recycled to it, if the NAPI that owns the page pool is scheduled to run on the same CPU. To make this safe we check that the NAPI is disabled while we destroy the page pool. In most cases NAPI and page pool lifetimes are tied together so this happens naturally. The queue API expects the following order of calls: -> mem_alloc alloc new pp -> stop napi_disable -> start napi_enable -> mem_free free old pp Here we allocate the page pool in ->mem_alloc and free in ->mem_free. But the NAPIs are only stopped between ->stop and ->start. We created page_pool_disable_direct_recycling() to safely shut down the recycling in ->stop. This way the page_pool_destroy() call in ->mem_free doesn't have to worry about recycling any more. Unfortunately, the page_pool_disable_direct_recycling() is not enough to deal with failures which necessitate freeing the _new_ page pool. If we hit a failure in ->mem_alloc or ->stop the new page pool has to be freed while the NAPI is active (assuming driver attaches the page pool to an existing NAPI instance and doesn't reallocate NAPIs). Freeing the new page pool is technically safe because it hasn't been used for any packets, yet, so there can be no recycling. But the check in napi_assert_will_not_race() has no way of knowing that. We could check if page pool is empty but that'd make the check much less likely to trigger during development. Add page_pool_enable_direct_recycling(), pairing with page_pool_disable_direct_recycling(). It will allow us to create the new page pools in "disabled" state and only enable recycling when we know the reconfig operation will not fail. Coincidentally it will also let us re-enable the recycling for the old pool, if the reconfig failed: -> mem_alloc (new) -> stop (old) # disables direct recycling for old -> start (new) # fail!! -> start (old) # go back to old pp but direct recycling is lost :( -> mem_free (new) The new helper is idempotent to make the life easier for drivers, which can operate in HDS mode and support zero-copy Rx. The driver can call the helper twice whether there are two pools or it has multiple references to a single pool. Fixes: 40eca00ae605 ("bnxt_en: unlink page pool when stopping Rx queue") Tested-by: David Wei Link: https://patch.msgid.link/20250805003654.2944974-1-kuba@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin

net: page_pool: Don't recycle into cache on PREEMPT_RT

2025-06-27T10:13:23Z

[ Upstream commit 32471b2f481dea8624f27669d36ffd131d24b732 ] With preemptible softirq and no per-CPU locking in local_bh_disable() on PREEMPT_RT the consumer can be preempted while a skb is returned. Avoid the race by disabling the recycle into the cache on PREEMPT_RT. Cc: Jesper Dangaard Brouer Cc: Ilias Apalodimas Signed-off-by: Sebastian Andrzej Siewior Link: https://patch.msgid.link/20250512092736.229935-2-bigeasy@linutronix.de Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin

page_pool: Fix use-after-free in page_pool_recycle_in_ring

2025-06-19T13:40:35Z

[ Upstream commit 271683bb2cf32e5126c592b5d5e6a756fa374fd9 ] syzbot reported a uaf in page_pool_recycle_in_ring: BUG: KASAN: slab-use-after-free in lock_release+0x151/0xa30 kernel/locking/lockdep.c:5862 Read of size 8 at addr ffff8880286045a0 by task syz.0.284/6943 CPU: 0 UID: 0 PID: 6943 Comm: syz.0.284 Not tainted 6.13.0-rc3-syzkaller-gdfa94ce54f41 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Call Trace: __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0x169/0x550 mm/kasan/report.c:489 kasan_report+0x143/0x180 mm/kasan/report.c:602 lock_release+0x151/0xa30 kernel/locking/lockdep.c:5862 __raw_spin_unlock_bh include/linux/spinlock_api_smp.h:165 [inline] _raw_spin_unlock_bh+0x1b/0x40 kernel/locking/spinlock.c:210 spin_unlock_bh include/linux/spinlock.h:396 [inline] ptr_ring_produce_bh include/linux/ptr_ring.h:164 [inline] page_pool_recycle_in_ring net/core/page_pool.c:707 [inline] page_pool_put_unrefed_netmem+0x748/0xb00 net/core/page_pool.c:826 page_pool_put_netmem include/net/page_pool/helpers.h:323 [inline] page_pool_put_full_netmem include/net/page_pool/helpers.h:353 [inline] napi_pp_put_page+0x149/0x2b0 net/core/skbuff.c:1036 skb_pp_recycle net/core/skbuff.c:1047 [inline] skb_free_head net/core/skbuff.c:1094 [inline] skb_release_data+0x6c4/0x8a0 net/core/skbuff.c:1125 skb_release_all net/core/skbuff.c:1190 [inline] __kfree_skb net/core/skbuff.c:1204 [inline] sk_skb_reason_drop+0x1c9/0x380 net/core/skbuff.c:1242 kfree_skb_reason include/linux/skbuff.h:1263 [inline] __skb_queue_purge_reason include/linux/skbuff.h:3343 [inline] root cause is: page_pool_recycle_in_ring ptr_ring_produce spin_lock(&r->producer_lock); WRITE_ONCE(r->queue[r->producer++], ptr) //recycle last page to pool page_pool_release page_pool_scrub page_pool_empty_ring ptr_ring_consume page_pool_return_page //release all page __page_pool_destroy free_percpu(pool->recycle_stats); free(pool) //free spin_unlock(&r->producer_lock); //pool->ring uaf read recycle_stat_inc(pool, ring); page_pool can be free while page pool recycle the last page in ring. Add producer-lock barrier to page_pool_release to prevent the page pool from being free before all pages have been recycled. recycle_stat_inc() is empty when CONFIG_PAGE_POOL_STATS is not enabled, which will trigger Wempty-body build warning. Add definition for pool stat macro to fix warning. Suggested-by: Jakub Kicinski Link: https://lore.kernel.org/netdev/20250513083123.3514193-1-dongchenchen2@huawei.com Fixes: ff7d6b27f894 ("page_pool: refurbish version of page_pool code") Reported-by: syzbot+204a4382fcb3311f3858@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=204a4382fcb3311f3858 Signed-off-by: Dong Chenchen Reviewed-by: Toke Høiland-Jørgensen Reviewed-by: Mina Almasry Link: https://patch.msgid.link/20250527114152.3119109-1-dongchenchen2@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin

page_pool: Track DMA-mapped pages and unmap them when destroying the pool

2025-06-19T13:39:42Z

[ Upstream commit ee62ce7a1d909ccba0399680a03c2dee83bcae95 ] When enabling DMA mapping in page_pool, pages are kept DMA mapped until they are released from the pool, to avoid the overhead of re-mapping the pages every time they are used. This causes resource leaks and/or crashes when there are pages still outstanding while the device is torn down, because page_pool will attempt an unmap through a non-existent DMA device on the subsequent page return. To fix this, implement a simple tracking of outstanding DMA-mapped pages in page pool using an xarray. This was first suggested by Mina[0], and turns out to be fairly straight forward: We simply store pointers to pages directly in the xarray with xa_alloc() when they are first DMA mapped, and remove them from the array on unmap. Then, when a page pool is torn down, it can simply walk the xarray and unmap all pages still present there before returning, which also allows us to get rid of the get/put_device() calls in page_pool. Using xa_cmpxchg(), no additional synchronisation is needed, as a page will only ever be unmapped once. To avoid having to walk the entire xarray on unmap to find the page reference, we stash the ID assigned by xa_alloc() into the page structure itself, using the upper bits of the pp_magic field. This requires a couple of defines to avoid conflicting with the POINTER_POISON_DELTA define, but this is all evaluated at compile-time, so does not affect run-time performance. The bitmap calculations in this patch gives the following number of bits for different architectures: - 23 bits on 32-bit architectures - 21 bits on PPC64 (because of the definition of ILLEGAL_POINTER_VALUE) - 32 bits on other 64-bit architectures Stashing a value into the unused bits of pp_magic does have the effect that it can make the value stored there lie outside the unmappable range (as governed by the mmap_min_addr sysctl), for architectures that don't define ILLEGAL_POINTER_VALUE. This means that if one of the pointers that is aliased to the pp_magic field (such as page->lru.next) is dereferenced while the page is owned by page_pool, that could lead to a dereference into userspace, which is a security concern. The risk of this is mitigated by the fact that (a) we always clear pp_magic before releasing a page from page_pool, and (b) this would need a use-after-free bug for struct page, which can have many other risks since page->lru.next is used as a generic list pointer in multiple places in the kernel. As such, with this patch we take the position that this risk is negligible in practice. For more discussion, see[1]. Since all the tracking added in this patch is performed on DMA map/unmap, no additional code is needed in the fast path, meaning the performance overhead of this tracking is negligible there. A micro-benchmark shows that the total overhead of the tracking itself is about 400 ns (39 cycles(tsc) 395.218 ns; sum for both map and unmap[2]). Since this cost is only paid on DMA map and unmap, it seems like an acceptable cost to fix the late unmap issue. Further optimisation can narrow the cases where this cost is paid (for instance by eliding the tracking when DMA map/unmap is a no-op). The extra memory needed to track the pages is neatly encapsulated inside xarray, which uses the 'struct xa_node' structure to track items. This structure is 576 bytes long, with slots for 64 items, meaning that a full node occurs only 9 bytes of overhead per slot it tracks (in practice, it probably won't be this efficient, but in any case it should be an acceptable overhead). [0] https://lore.kernel.org/all/CAHS8izPg7B5DwKfSuzz-iOop_YRbk3Sd6Y4rX7KBG9DcVJcyWg@mail.gmail.com/ [1] https://lore.kernel.org/r/20250320023202.GA25514@openwall.com [2] https://lore.kernel.org/r/ae07144c-9295-4c9d-a400-153bb689fe9e@huawei.com Reported-by: Yonglong Liu Closes: https://lore.kernel.org/r/8743264a-9700-4227-a556-5f931c720211@huawei.com Fixes: ff7d6b27f894 ("page_pool: refurbish version of page_pool code") Suggested-by: Mina Almasry Reviewed-by: Mina Almasry Reviewed-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Qiuling Ren Tested-by: Yuying Ma Tested-by: Yonglong Liu Acked-by: Jesper Dangaard Brouer Signed-off-by: Toke Høiland-Jørgensen Link: https://patch.msgid.link/20250409-page-pool-track-dma-v9-2-6a9ef2e0cba8@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin

net: protect rxq->mp_params with the instance lock

2025-03-25T17:06:49Z

Ensure that all accesses to mp_params are under the netdev instance lock. The only change we need is to move dev_memory_provider_uninstall() under the lock. Appropriately swap the asserts. Reviewed-by: Mina Almasry Acked-by: Stanislav Fomichev Link: https://patch.msgid.link/20250324224537.248800-8-kuba@kernel.org Signed-off-by: Jakub Kicinski

page_pool: avoid infinite loop to schedule delayed worker

2025-02-18T11:48:29Z

We noticed the kworker in page_pool_release_retry() was waken up repeatedly and infinitely in production because of the buggy driver causing the inflight less than 0 and warning us in page_pool_inflight()[1]. Since the inflight value goes negative, it means we should not expect the whole page_pool to get back to work normally. This patch mitigates the adverse effect by not rescheduling the kworker when detecting the inflight negative in page_pool_release_retry(). [1] [Mon Feb 10 20:36:11 2025] ------------[ cut here ]------------ [Mon Feb 10 20:36:11 2025] Negative(-51446) inflight packet-pages ... [Mon Feb 10 20:36:11 2025] Call Trace: [Mon Feb 10 20:36:11 2025] page_pool_release_retry+0x23/0x70 [Mon Feb 10 20:36:11 2025] process_one_work+0x1b1/0x370 [Mon Feb 10 20:36:11 2025] worker_thread+0x37/0x3a0 [Mon Feb 10 20:36:11 2025] kthread+0x11a/0x140 [Mon Feb 10 20:36:11 2025] ? process_one_work+0x370/0x370 [Mon Feb 10 20:36:11 2025] ? __kthread_cancel_work+0x40/0x40 [Mon Feb 10 20:36:11 2025] ret_from_fork+0x35/0x40 [Mon Feb 10 20:36:11 2025] ---[ end trace ebffe800f33e7e34 ]--- Note: before this patch, the above calltrace would flood the dmesg due to repeated reschedule of release_dw kworker. Signed-off-by: Jason Xing Reviewed-by: Mina Almasry Link: https://patch.msgid.link/20250214064250.85987-1-kerneljasonxing@gmail.com Signed-off-by: Paolo Abeni

net: page_pool: avoid false positive warning if NAPI was never added

2025-02-08T01:21:03Z

We expect NAPI to be in disabled state when page pool is torn down. But it is also legal if the NAPI is completely uninitialized. Reviewed-by: Mina Almasry Link: https://patch.msgid.link/20250206225638.1387810-4-kuba@kernel.org Signed-off-by: Jakub Kicinski

net: page_pool: add memory provider helpers

2025-02-07T00:27:31Z

Add helpers for memory providers to interact with page pools. net_mp_niov_{set,clear}_page_pool() serve to [dis]associate a net_iov with a page pool. If used, the memory provider is responsible to match "set" calls with "clear" once a net_iov is not going to be used by a page pool anymore, changing a page pool, etc. Acked-by: Jakub Kicinski Signed-off-by: Pavel Begunkov Signed-off-by: David Wei Link: https://patch.msgid.link/20250204215622.695511-10-dw@davidwei.uk Signed-off-by: Jakub Kicinski

net: page_pool: create hooks for custom memory providers

2025-02-07T00:27:30Z

A spin off from the original page pool memory providers patch by Jakub, which allows extending page pools with custom allocators. One of such providers is devmem TCP, and the other is io_uring zerocopy added in following patches. Link: https://lore.kernel.org/netdev/20230707183935.997267-7-kuba@kernel.org/ Co-developed-by: Jakub Kicinski # initial mp proposal Signed-off-by: Pavel Begunkov Signed-off-by: David Wei Link: https://patch.msgid.link/20250204215622.695511-5-dw@davidwei.uk Signed-off-by: Jakub Kicinski

Merge tag 'net-6.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

2025-01-30T20:24:20Z

Pull networking fixes from Jakub Kicinski: "Including fixes from IPSec, netfilter and Bluetooth. Nothing really stands out, but as usual there's a slight concentration of fixes for issues added in the last two weeks before the merge window, and driver bugs from 6.13 which tend to get discovered upon wider distribution. Current release - regressions: - net: revert RTNL changes in unregister_netdevice_many_notify() - Bluetooth: fix possible infinite recursion of btusb_reset - eth: adjust locking in some old drivers which protect their state with spinlocks to avoid sleeping in atomic; core protects netdev state with a mutex now Previous releases - regressions: - eth: - mlx5e: make sure we pass node ID, not CPU ID to kvzalloc_node() - bgmac: reduce max frame size to support just 1500 bytes; the jumbo frame support would previously cause OOB writes, but now fails outright - mptcp: blackhole only if 1st SYN retrans w/o MPC is accepted, avoid false detection of MPTCP blackholing Previous releases - always broken: - mptcp: handle fastopen disconnect correctly - xfrm: - make sure skb->sk is a full sock before accessing its fields - fix taking a lock with preempt disabled for RT kernels - usb: ipheth: improve safety of packet metadata parsing; prevent potential OOB accesses - eth: renesas: fix missing rtnl lock in suspend/resume path" * tag 'net-6.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (88 commits) MAINTAINERS: add Neal to TCP maintainers net: revert RTNL changes in unregister_netdevice_many_notify() net: hsr: fix fill_frame_info() regression vs VLAN packets doc: mptcp: sysctl: blackhole_timeout is per-netns mptcp: blackhole only if 1st SYN retrans w/o MPC is accepted netfilter: nf_tables: reject mismatching sum of field_len with set key length net: sh_eth: Fix missing rtnl lock in suspend/resume path net: ravb: Fix missing rtnl lock in suspend/resume path selftests/net: Add test for loading devbound XDP program in generic mode net: xdp: Disallow attaching device-bound programs in generic mode tcp: correct handling of extreme memory squeeze bgmac: reduce max frame size to support just MTU 1500 vsock/test: Add test for connect() retries vsock/test: Add test for UAF due to socket unbinding vsock/test: Introduce vsock_connect_fd() vsock/test: Introduce vsock_bind() vsock: Allow retrying on connect() failure vsock: Keep the binding until socket destruction Bluetooth: L2CAP: accept zero as a special value for MTU auto-selection Bluetooth: btnxpuart: Fix glitches seen in dual A2DP streaming ...