- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6] mlxsw: spectrum_router: Fix neighbour use-after-free
by Cai Xinchen 19 Jan '26

19 Jan '26

From: Ido Schimmel <idosch(a)nvidia.com> stable inclusion from stable-v6.6.120 commit 4a3c569005f42ab5e5b2ad637132a33bf102cc08 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13354 CVE: CVE-2025-68801 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 8b0e69763ef948fb872a7767df4be665d18f5fd4 ] We sometimes observe use-after-free when dereferencing a neighbour [1]. The problem seems to be that the driver stores a pointer to the neighbour, but without holding a reference on it. A reference is only taken when the neighbour is used by a nexthop. Fix by simplifying the reference counting scheme. Always take a reference when storing a neighbour pointer in a neighbour entry. Avoid taking a referencing when the neighbour is used by a nexthop as the neighbour entry associated with the nexthop already holds a reference. Tested by running the test that uncovered the problem over 300 times. Without this patch the problem was reproduced after a handful of iterations. [1] BUG: KASAN: slab-use-after-free in mlxsw_sp_neigh_entry_update+0x2d4/0x310 Read of size 8 at addr ffff88817f8e3420 by task ip/3929 CPU: 3 UID: 0 PID: 3929 Comm: ip Not tainted 6.18.0-rc4-virtme-g36b21a067510 #3 PREEMPT(full) Hardware name: Nvidia SN5600/VMOD0013, BIOS 5.13 05/31/2023 Call Trace: <TASK> dump_stack_lvl+0x6f/0xa0 print_address_description.constprop.0+0x6e/0x300 print_report+0xfc/0x1fb kasan_report+0xe4/0x110 mlxsw_sp_neigh_entry_update+0x2d4/0x310 mlxsw_sp_router_rif_gone_sync+0x35f/0x510 mlxsw_sp_rif_destroy+0x1ea/0x730 mlxsw_sp_inetaddr_port_vlan_event+0xa1/0x1b0 __mlxsw_sp_inetaddr_lag_event+0xcc/0x130 __mlxsw_sp_inetaddr_event+0xf5/0x3c0 mlxsw_sp_router_netdevice_event+0x1015/0x1580 notifier_call_chain+0xcc/0x150 call_netdevice_notifiers_info+0x7e/0x100 __netdev_upper_dev_unlink+0x10b/0x210 netdev_upper_dev_unlink+0x79/0xa0 vrf_del_slave+0x18/0x50 do_set_master+0x146/0x7d0 do_setlink.isra.0+0x9a0/0x2880 rtnl_newlink+0x637/0xb20 rtnetlink_rcv_msg+0x6fe/0xb90 netlink_rcv_skb+0x123/0x380 netlink_unicast+0x4a3/0x770 netlink_sendmsg+0x75b/0xc90 __sock_sendmsg+0xbe/0x160 ____sys_sendmsg+0x5b2/0x7d0 ___sys_sendmsg+0xfd/0x180 __sys_sendmsg+0x124/0x1c0 do_syscall_64+0xbb/0xfd0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 [...] Allocated by task 109: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 __kasan_kmalloc+0x7b/0x90 __kmalloc_noprof+0x2c1/0x790 neigh_alloc+0x6af/0x8f0 ___neigh_create+0x63/0xe90 mlxsw_sp_nexthop_neigh_init+0x430/0x7e0 mlxsw_sp_nexthop_type_init+0x212/0x960 mlxsw_sp_nexthop6_group_info_init.constprop.0+0x81f/0x1280 mlxsw_sp_nexthop6_group_get+0x392/0x6a0 mlxsw_sp_fib6_entry_create+0x46a/0xfd0 mlxsw_sp_router_fib6_replace+0x1ed/0x5f0 mlxsw_sp_router_fib6_event_work+0x10a/0x2a0 process_one_work+0xd57/0x1390 worker_thread+0x4d6/0xd40 kthread+0x355/0x5b0 ret_from_fork+0x1d4/0x270 ret_from_fork_asm+0x11/0x20 Freed by task 154: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 __kasan_save_free_info+0x3b/0x60 __kasan_slab_free+0x43/0x70 kmem_cache_free_bulk.part.0+0x1eb/0x5e0 kvfree_rcu_bulk+0x1f2/0x260 kfree_rcu_work+0x130/0x1b0 process_one_work+0xd57/0x1390 worker_thread+0x4d6/0xd40 kthread+0x355/0x5b0 ret_from_fork+0x1d4/0x270 ret_from_fork_asm+0x11/0x20 Last potentially related work creation: kasan_save_stack+0x30/0x50 kasan_record_aux_stack+0x8c/0xa0 kvfree_call_rcu+0x93/0x5b0 mlxsw_sp_router_neigh_event_work+0x67d/0x860 process_one_work+0xd57/0x1390 worker_thread+0x4d6/0xd40 kthread+0x355/0x5b0 ret_from_fork+0x1d4/0x270 ret_from_fork_asm+0x11/0x20 Fixes: 6cf3c971dc84 ("mlxsw: spectrum_router: Add private neigh table") Signed-off-by: Ido Schimmel <idosch(a)nvidia.com> Reviewed-by: Petr Machata <petrm(a)nvidia.com> Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://patch.msgid.link/92d75e21d95d163a41b5cea67a15cd33f547cba6.176469565… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Cai Xinchen <caixinchen1(a)huawei.com> --- .../ethernet/mellanox/mlxsw/spectrum_router.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 0534b10e29c5..2bf332838d2e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2264,6 +2264,7 @@ mlxsw_sp_neigh_entry_alloc(struct mlxsw_sp *mlxsw_sp, struct neighbour *n, if (!neigh_entry) return NULL; + neigh_hold(n); neigh_entry->key.n = n; neigh_entry->rif = rif; INIT_LIST_HEAD(&neigh_entry->nexthop_list); @@ -2273,6 +2274,7 @@ mlxsw_sp_neigh_entry_alloc(struct mlxsw_sp *mlxsw_sp, struct neighbour *n, static void mlxsw_sp_neigh_entry_free(struct mlxsw_sp_neigh_entry *neigh_entry) { + neigh_release(neigh_entry->key.n); kfree(neigh_entry); } @@ -4203,6 +4205,8 @@ mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp, if (err) goto err_neigh_entry_insert; + neigh_release(old_n); + read_lock_bh(&n->lock); nud_state = n->nud_state; dead = n->dead; @@ -4211,14 +4215,10 @@ mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp, list_for_each_entry(nh, &neigh_entry->nexthop_list, neigh_list_node) { - neigh_release(old_n); - neigh_clone(n); __mlxsw_sp_nexthop_neigh_update(nh, !entry_connected); mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp); } - neigh_release(n); - return 0; err_neigh_entry_insert: @@ -4311,6 +4311,11 @@ static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp, } } + /* Release the reference taken by neigh_lookup() / neigh_create() since + * neigh_entry already holds one. + */ + neigh_release(n); + /* If that is the first nexthop connected to that neigh, add to * nexthop_neighs_list */ @@ -4337,11 +4342,9 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh) { struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry; - struct neighbour *n; if (!neigh_entry) return; - n = neigh_entry->key.n; __mlxsw_sp_nexthop_neigh_update(nh, true); list_del(&nh->neigh_list_node); @@ -4355,8 +4358,6 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp, if (!neigh_entry->connected && list_empty(&neigh_entry->nexthop_list)) mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry); - - neigh_release(n); } static bool mlxsw_sp_ipip_netdev_ul_up(struct net_device *ol_dev) -- 2.34.1

2 1

[PATCH OLK-6.6] mlxsw: spectrum_mr: Fix use-after-free when updating multicast route stats
by Cai Xinchen 19 Jan '26

19 Jan '26

From: Ido Schimmel <idosch(a)nvidia.com> stable inclusion from stable-v6.6.120 commit 5f2831fc593c2b2efbff7dd0dd7441cec76adcd5 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13353 CVE: CVE-2025-68800 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 8ac1dacec458f55f871f7153242ed6ab60373b90 ] Cited commit added a dedicated mutex (instead of RTNL) to protect the multicast route list, so that it will not change while the driver periodically traverses it in order to update the kernel about multicast route stats that were queried from the device. One instance of list entry deletion (during route replace) was missed and it can result in a use-after-free [1]. Fix by acquiring the mutex before deleting the entry from the list and releasing it afterwards. [1] BUG: KASAN: slab-use-after-free in mlxsw_sp_mr_stats_update+0x4a5/0x540 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c:1006 [mlxsw_spectrum] Read of size 8 at addr ffff8881523c2fa8 by task kworker/2:5/22043 CPU: 2 UID: 0 PID: 22043 Comm: kworker/2:5 Not tainted 6.18.0-rc1-custom-g1a3d6d7cd014 #1 PREEMPT(full) Hardware name: Mellanox Technologies Ltd. MSN2010/SA002610, BIOS 5.6.5 08/24/2017 Workqueue: mlxsw_core mlxsw_sp_mr_stats_update [mlxsw_spectrum] Call Trace: <TASK> dump_stack_lvl+0xba/0x110 print_report+0x174/0x4f5 kasan_report+0xdf/0x110 mlxsw_sp_mr_stats_update+0x4a5/0x540 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c:1006 [mlxsw_spectrum] process_one_work+0x9cc/0x18e0 worker_thread+0x5df/0xe40 kthread+0x3b8/0x730 ret_from_fork+0x3e9/0x560 ret_from_fork_asm+0x1a/0x30 </TASK> Allocated by task 29933: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 __kasan_kmalloc+0x8f/0xa0 mlxsw_sp_mr_route_add+0xd8/0x4770 [mlxsw_spectrum] mlxsw_sp_router_fibmr_event_work+0x371/0xad0 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:7965 [mlxsw_spectrum] process_one_work+0x9cc/0x18e0 worker_thread+0x5df/0xe40 kthread+0x3b8/0x730 ret_from_fork+0x3e9/0x560 ret_from_fork_asm+0x1a/0x30 Freed by task 29933: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 __kasan_save_free_info+0x3b/0x70 __kasan_slab_free+0x43/0x70 kfree+0x14e/0x700 mlxsw_sp_mr_route_add+0x2dea/0x4770 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c:444 [mlxsw_spectrum] mlxsw_sp_router_fibmr_event_work+0x371/0xad0 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:7965 [mlxsw_spectrum] process_one_work+0x9cc/0x18e0 worker_thread+0x5df/0xe40 kthread+0x3b8/0x730 ret_from_fork+0x3e9/0x560 ret_from_fork_asm+0x1a/0x30 Fixes: f38656d06725 ("mlxsw: spectrum_mr: Protect multicast route list with a lock") Signed-off-by: Ido Schimmel <idosch(a)nvidia.com> Reviewed-by: Petr Machata <petrm(a)nvidia.com> Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://patch.msgid.link/f996feecfd59fde297964bfc85040b6d83ec6089.176469565… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Cai Xinchen <caixinchen1(a)huawei.com> --- drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c index 5afe6b155ef0..81935f87bfcd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c @@ -440,7 +440,9 @@ int mlxsw_sp_mr_route_add(struct mlxsw_sp_mr_table *mr_table, rhashtable_remove_fast(&mr_table->route_ht, &mr_orig_route->ht_node, mlxsw_sp_mr_route_ht_params); + mutex_lock(&mr_table->route_list_lock); list_del(&mr_orig_route->node); + mutex_unlock(&mr_table->route_list_lock); mlxsw_sp_mr_route_destroy(mr_table, mr_orig_route); } -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS 0/2] Fix CVE-2022-50885
by Hongtao Zhang 19 Jan '26

19 Jan '26

*** BLURB HERE *** Zhang Xiaoxu (1): [Backport] RDMA/rxe: Fix NULL-ptr-deref in rxe_qp_do_cleanup() when socket create failed Zhu Yanjun (1): [Backport] RDMA/rxe: Fix the error caused by qp->sk drivers/infiniband/sw/rxe/rxe_qp.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) -- 2.34.1

2 3

[PATCH OLK-5.10] wifi: cfg80211: fix use-after-free in cmp_bss()
by Zhang Changzhong 19 Jan '26

19 Jan '26

From: Dmitry Antipov <dmantipov(a)yandex.ru> stable inclusion from stable-v5.10.243 commit a97a9791e455bb0cd5e7a38b5abcb05523d4e21c category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/8428 CVE: CVE-2025-39864 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 26e84445f02ce6b2fe5f3e0e28ff7add77f35e08 ] Following bss_free() quirk introduced in commit 776b3580178f ("cfg80211: track hidden SSID networks properly"), adjust cfg80211_update_known_bss() to free the last beacon frame elements only if they're not shared via the corresponding 'hidden_beacon_bss' pointer. Reported-by: syzbot+30754ca335e6fb7e3092(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=30754ca335e6fb7e3092 Fixes: 3ab8227d3e7d ("cfg80211: refactor cfg80211_bss_update") Signed-off-by: Dmitry Antipov <dmantipov(a)yandex.ru> Link: https://patch.msgid.link/20250813135236.799384-1-dmantipov@yandex.ru Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhang Changzhong <zhangchangzhong(a)huawei.com> --- net/wireless/scan.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 76a27b6..a9bb676f 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1697,7 +1697,8 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev, */ f = rcu_access_pointer(new->pub.beacon_ies); - kfree_rcu((struct cfg80211_bss_ies *)f, rcu_head); + if (!new->pub.hidden_beacon_bss) + kfree_rcu((struct cfg80211_bss_ies *)f, rcu_head); return false; } -- 2.9.5

2 1

[PATCH OLK-6.6] ptr_ring: do not block hard interrupts in ptr_ring_resize_multiple()
by Zhang Changzhong 19 Jan '26

19 Jan '26

From: Eric Dumazet <edumazet(a)google.com> mainline inclusion from mainline-v6.14-rc1 commit a126061c80d5efb4baef4bcf346094139cd81df6 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/135 CVE: CVE-2024-57994 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------------- Jakub added a lockdep_assert_no_hardirq() check in __page_pool_put_page() to increase test coverage. syzbot found a splat caused by hard irq blocking in ptr_ring_resize_multiple() [1] As current users of ptr_ring_resize_multiple() do not require hard irqs being masked, replace it to only block BH. Rename helpers to better reflect they are safe against BH only. - ptr_ring_resize_multiple() to ptr_ring_resize_multiple_bh() - skb_array_resize_multiple() to skb_array_resize_multiple_bh() [1] WARNING: CPU: 1 PID: 9150 at net/core/page_pool.c:709 __page_pool_put_page net/core/page_pool.c:709 [inline] WARNING: CPU: 1 PID: 9150 at net/core/page_pool.c:709 page_pool_put_unrefed_netmem+0x157/0xa40 net/core/page_pool.c:780 Modules linked in: CPU: 1 UID: 0 PID: 9150 Comm: syz.1.1052 Not tainted 6.11.0-rc3-syzkaller-00202-gf8669d7b5f5d #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/06/2024 RIP: 0010:__page_pool_put_page net/core/page_pool.c:709 [inline] RIP: 0010:page_pool_put_unrefed_netmem+0x157/0xa40 net/core/page_pool.c:780 Code: 74 0e e8 7c aa fb f7 eb 43 e8 75 aa fb f7 eb 3c 65 8b 1d 38 a8 6a 76 31 ff 89 de e8 a3 ae fb f7 85 db 74 0b e8 5a aa fb f7 90 <0f> 0b 90 eb 1d 65 8b 1d 15 a8 6a 76 31 ff 89 de e8 84 ae fb f7 85 RSP: 0018:ffffc9000bda6b58 EFLAGS: 00010083 RAX: ffffffff8997e523 RBX: 0000000000000000 RCX: 0000000000040000 RDX: ffffc9000fbd0000 RSI: 0000000000001842 RDI: 0000000000001843 RBP: 0000000000000000 R08: ffffffff8997df2c R09: 1ffffd40003a000d R10: dffffc0000000000 R11: fffff940003a000e R12: ffffea0001d00040 R13: ffff88802e8a4000 R14: dffffc0000000000 R15: 00000000ffffffff FS: 00007fb7aaf716c0(0000) GS:ffff8880b9300000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fa15a0d4b72 CR3: 00000000561b0000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> tun_ptr_free drivers/net/tun.c:617 [inline] __ptr_ring_swap_queue include/linux/ptr_ring.h:571 [inline] ptr_ring_resize_multiple_noprof include/linux/ptr_ring.h:643 [inline] tun_queue_resize drivers/net/tun.c:3694 [inline] tun_device_event+0xaaf/0x1080 drivers/net/tun.c:3714 notifier_call_chain+0x19f/0x3e0 kernel/notifier.c:93 call_netdevice_notifiers_extack net/core/dev.c:2032 [inline] call_netdevice_notifiers net/core/dev.c:2046 [inline] dev_change_tx_queue_len+0x158/0x2a0 net/core/dev.c:9024 do_setlink+0xff6/0x41f0 net/core/rtnetlink.c:2923 rtnl_setlink+0x40d/0x5a0 net/core/rtnetlink.c:3201 rtnetlink_rcv_msg+0x73f/0xcf0 net/core/rtnetlink.c:6647 netlink_rcv_skb+0x1e3/0x430 net/netlink/af_netlink.c:2550 Fixes: ff4e538c8c3e ("page_pool: add a lockdep check for recycling in hardirq") Reported-by: syzbot+f56a5c5eac2b28439810(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/671e10df.050a0220.2b8c0f.01cf.GAE@google.com… Signed-off-by: Eric Dumazet <edumazet(a)google.com> Acked-by: Michael S. Tsirkin <mst(a)redhat.com> Acked-by: Jason Wang <jasowang(a)redhat.com> Link: https://patch.msgid.link/20241217135121.326370-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: include/linux/ptr_ring.h include/linux/skb_array.h [Did not backport 2c321f3f70bc.] Signed-off-by: Liu Jian <liujian56(a)huawei.com> Signed-off-by: Zhang Changzhong <zhangchangzhong(a)huawei.com> --- drivers/net/tap.c | 6 +++--- drivers/net/tun.c | 6 +++--- include/linux/ptr_ring.h | 17 ++++++++--------- include/linux/skb_array.h | 13 +++++++------ net/sched/sch_generic.c | 4 ++-- 5 files changed, 23 insertions(+), 23 deletions(-) diff --git a/drivers/net/tap.c b/drivers/net/tap.c index e7212a64..2c4f9d1 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -1330,9 +1330,9 @@ int tap_queue_resize(struct tap_dev *tap) list_for_each_entry(q, &tap->queue_list, next) rings[i++] = &q->ring; - ret = ptr_ring_resize_multiple(rings, n, - dev->tx_queue_len, GFP_KERNEL, - __skb_array_destroy_skb); + ret = ptr_ring_resize_multiple_bh(rings, n, + dev->tx_queue_len, GFP_KERNEL, + __skb_array_destroy_skb); kfree(rings); return ret; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index c1fdf88..97dbec8d 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -3682,9 +3682,9 @@ static int tun_queue_resize(struct tun_struct *tun) list_for_each_entry(tfile, &tun->disabled, next) rings[i++] = &tfile->tx_ring; - ret = ptr_ring_resize_multiple(rings, n, - dev->tx_queue_len, GFP_KERNEL, - tun_ptr_free); + ret = ptr_ring_resize_multiple_bh(rings, n, + dev->tx_queue_len, GFP_KERNEL, + tun_ptr_free); kfree(rings); return ret; diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 808f9d3..65da2155 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -613,15 +613,14 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, /* * Note: producer lock is nested within consumer lock, so if you * resize you must make sure all uses nest correctly. - * In particular if you consume ring in interrupt or BH context, you must - * disable interrupts/BH when doing so. + * In particular if you consume ring in BH context, you must + * disable BH when doing so. */ -static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, - unsigned int nrings, - int size, - gfp_t gfp, void (*destroy)(void *)) +static inline int ptr_ring_resize_multiple_bh(struct ptr_ring **rings, + unsigned int nrings, + int size, gfp_t gfp, + void (*destroy)(void *)) { - unsigned long flags; void ***queues; int i; @@ -636,12 +635,12 @@ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, } for (i = 0; i < nrings; ++i) { - spin_lock_irqsave(&(rings[i])->consumer_lock, flags); + spin_lock_bh(&(rings[i])->consumer_lock); spin_lock(&(rings[i])->producer_lock); queues[i] = __ptr_ring_swap_queue(rings[i], queues[i], size, gfp, destroy); spin_unlock(&(rings[i])->producer_lock); - spin_unlock_irqrestore(&(rings[i])->consumer_lock, flags); + spin_unlock_bh(&(rings[i])->consumer_lock); } for (i = 0; i < nrings; ++i) diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h index e2d45b7..4ef109a 100644 --- a/include/linux/skb_array.h +++ b/include/linux/skb_array.h @@ -198,14 +198,15 @@ static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb); } -static inline int skb_array_resize_multiple(struct skb_array **rings, - int nrings, unsigned int size, - gfp_t gfp) +static inline int skb_array_resize_multiple_bh(struct skb_array **rings, + int nrings, + unsigned int size, + gfp_t gfp) { BUILD_BUG_ON(offsetof(struct skb_array, ring)); - return ptr_ring_resize_multiple((struct ptr_ring **)rings, - nrings, size, gfp, - __skb_array_destroy_skb); + return ptr_ring_resize_multiple_bh((struct ptr_ring **)rings, + nrings, size, gfp, + __skb_array_destroy_skb); } static inline void skb_array_cleanup(struct skb_array *a) diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 9664a63..47cf61e 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -907,8 +907,8 @@ static int pfifo_fast_change_tx_queue_len(struct Qdisc *sch, bands[prio] = q; } - return skb_array_resize_multiple(bands, PFIFO_FAST_BANDS, new_len, - GFP_KERNEL); + return skb_array_resize_multiple_bh(bands, PFIFO_FAST_BANDS, new_len, + GFP_KERNEL); } struct Qdisc_ops pfifo_fast_ops __read_mostly = { -- 2.9.5

2 1

[PATCH openEuler-1.0-LTS 0/2] [Backport] RDMA/rxe: Fix NULL-ptr-deref
by Hongtao Zhang 19 Jan '26

19 Jan '26

*** BLURB HERE *** Zhang Xiaoxu (1): [Backport] RDMA/rxe: Fix NULL-ptr-deref in rxe_qp_do_cleanup() when socket create failed Zhu Yanjun (1): [Backport] RDMA/rxe: Fix the error caused by qp->sk drivers/infiniband/sw/rxe/rxe_qp.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) -- 2.34.1

2 3

[PATCH OLK-6.6] NFS: Automounted filesystems should inherit ro,noexec,nodev,sync flags
by Wang Zhaolong 19 Jan '26

19 Jan '26

From: Trond Myklebust <trond.myklebust(a)hammerspace.com> stable inclusion from stable-v6.6.120 commit dce10c59211e5cd763a62ea01e79b82a629811e3 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13299 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 8675c69816e4276b979ff475ee5fac4688f80125 ] When a filesystem is being automounted, it needs to preserve the user-set superblock mount options, such as the "ro" flag. Reported-by: Li Lingfeng <lilingfeng3(a)huawei.com> Link: https://lore.kernel.org/all/20240604112636.236517-3-lilingfeng@huaweicloud.… Fixes: f2aedb713c28 ("NFS: Add fs_context support.") Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Zhaolong <wangzhaolong(a)huaweicloud.com> --- fs/nfs/namespace.c | 6 ++++++ fs/nfs/super.c | 4 ---- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index e7494cdd957e..40d7163bca87 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -147,10 +147,11 @@ struct vfsmount *nfs_d_automount(struct path *path) struct nfs_fs_context *ctx; struct fs_context *fc; struct vfsmount *mnt = ERR_PTR(-ENOMEM); struct nfs_server *server = NFS_SB(path->dentry->d_sb); struct nfs_client *client = server->nfs_client; + unsigned long s_flags = path->dentry->d_sb->s_flags; int timeout = READ_ONCE(nfs_mountpoint_expiry_timeout); int ret; if (IS_ROOT(path->dentry)) return ERR_PTR(-ESTALE); @@ -172,10 +173,15 @@ struct vfsmount *nfs_d_automount(struct path *path) if (fc->net_ns != client->cl_net) { put_net(fc->net_ns); fc->net_ns = get_net(client->cl_net); } + /* Inherit the flags covered by NFS_SB_MASK */ + fc->sb_flags_mask |= NFS_SB_MASK; + fc->sb_flags &= ~NFS_SB_MASK; + fc->sb_flags |= s_flags & NFS_SB_MASK; + /* for submounts we want the same server; referrals will reassign */ memcpy(&ctx->nfs_server._address, &client->cl_addr, client->cl_addrlen); ctx->nfs_server.addrlen = client->cl_addrlen; ctx->nfs_server.port = server->port; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 1c2969cb907e..9fa3d17981bd 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1318,14 +1318,10 @@ int nfs_get_tree_common(struct fs_context *fc) /* -o noac implies -o sync */ if (server->flags & NFS_MOUNT_NOAC) fc->sb_flags |= SB_SYNCHRONOUS; - if (ctx->clone_data.sb) - if (ctx->clone_data.sb->s_flags & SB_SYNCHRONOUS) - fc->sb_flags |= SB_SYNCHRONOUS; - /* Get a superblock - note that we may end up sharing one that already exists */ fc->s_fs_info = server; s = sget_fc(fc, compare_super, nfs_set_super); fc->s_fs_info = NULL; if (IS_ERR(s)) { -- 2.34.3

2 1

[PATCH openEuler-1.0-LTS] scsi/hiraid: Support New Raid feature
by LinKun 19 Jan '26

19 Jan '26

From: 岳智超 <yuezhichao1(a)h-partners.com> driver inclusion category: feature bugzilla: https://atomgit.com/openeuler/kernel/issues/8291 CVE: NA -------------------------------- Add thread irq for io queue Add stream detect Signed-off-by: 岳智超 <yuezhichao1(a)h-partners.com> --- drivers/scsi/hisi_raid/hiraid.h | 34 ++ drivers/scsi/hisi_raid/hiraid_main.c | 586 ++++++++++++++++++++++++++- 2 files changed, 603 insertions(+), 17 deletions(-) diff --git a/drivers/scsi/hisi_raid/hiraid.h b/drivers/scsi/hisi_raid/hiraid.h index 1ebc3dd..d107951 100644 --- a/drivers/scsi/hisi_raid/hiraid.h +++ b/drivers/scsi/hisi_raid/hiraid.h @@ -683,6 +683,7 @@ struct hiraid_queue { atomic_t inflight; void *sense_buffer_virt; dma_addr_t sense_buffer_phy; + s32 pci_irq; struct dma_pool *prp_small_pool; }; @@ -756,5 +757,38 @@ struct hiraid_sdev_hostdata { u16 pend_count; }; +enum stream_type { + TYPE_TOTAL, + TYPE_WRITE, + TYPE_READ, + TYPE_CLEAN, + TYPE_BOTTOM +}; + +struct HIRAID_STREAM_S { + /* recog-window */ + u64 stream_lba; + u32 stream_len; + u16 vd_id; + u16 type; + /* aging ctrl */ + int aging_credit; + int aging_grade; + u16 stream_id; + u16 using; +}; + +struct IO_LIST_S { + struct list_head list; + struct hiraid_scsi_io_cmd io_cmd; + struct hiraid_queue *submit_queue; + unsigned int sector_size; +}; + +struct spinlock_list_head_s { + struct list_head list; + spinlock_t lock; +}; + #endif diff --git a/drivers/scsi/hisi_raid/hiraid_main.c b/drivers/scsi/hisi_raid/hiraid_main.c index f84182f..281fe79 100644 --- a/drivers/scsi/hisi_raid/hiraid_main.c +++ b/drivers/scsi/hisi_raid/hiraid_main.c @@ -35,6 +35,10 @@ #include <scsi/scsi_transport.h> #include <scsi/scsi_dbg.h> #include <scsi/sg.h> +#include <linux/kthread.h> +#include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/sched/prio.h> #include "hiraid.h" @@ -107,6 +111,13 @@ static u32 log_debug_switch; module_param(log_debug_switch, uint, 0644); MODULE_PARM_DESC(log_debug_switch, "set log state, default zero for switch off"); +static bool threaded_irq = false; +module_param(threaded_irq, bool, 0444); +MODULE_PARM_DESC(threaded_irq, "use threaded irq for io queue, default off"); + +static u32 poll_delay_min = 9; +static u32 poll_delay_max = 19; + static int extra_pool_num_set(const char *val, const struct kernel_param *kp) { u8 n = 0; @@ -153,7 +164,7 @@ static struct workqueue_struct *work_queue; __func__, ##__VA_ARGS__); \ } while (0) -#define HIRAID_DRV_VERSION "1.1.0.0" +#define HIRAID_DRV_VERSION "1.1.0.1" #define ADMIN_TIMEOUT (admin_tmout * HZ) #define USRCMD_TIMEOUT (180 * HZ) @@ -170,6 +181,15 @@ static struct workqueue_struct *work_queue; #define MAX_CAN_QUEUE (4096 - 1) #define MIN_CAN_QUEUE (1024 - 1) +#define MAX_DECREASE_GRADE (-8) +#define MAX_INCREASE_GRADE 8 +#define INC_GRADE 1 +#define MIN_CREDIT 0 +#define MAX_CREDIT 64 +#define CREDIT_THRES 32 +#define MIN(a, b) (((a) < (b)) ? (a) : (b)) +#define MAX(a, b) (((a) > (b)) ? (a) : (b)) + enum SENSE_STATE_CODE { SENSE_STATE_OK = 0, SENSE_STATE_NEED_CHECK, @@ -765,6 +785,404 @@ static int hiraid_build_sgl(struct hiraid_dev *hdev, return 0; } +#define MAX_PD_NUM (40 + 1) +#define MAX_STREAM_NUM 8 +#define PER_MB (1024 * 1024) +#define MAX_IO_NUM (200 * PER_MB) +#define STREAM_LEN (4 * PER_MB) +#define MAX_IO_NUM_ONCE 128 +#define IO_SUBMIT_TIME_OUT 100 +#define MAX_AGING_NUM 130 + +#define MIN_IO_SEND_TIME 10 +#define MAX_IO_SEND_TIME 50 + +#define MIN_WAIT_IO_SEND_TIME 10 +#define MAX_WAIT_IO_SEND_TIME 20 + +enum io_operation_type { + TYPE_DELETE_SINGLE_IO = 1, + TYPE_DELETE_SINGLE_IO_LIST, + TYPE_DELETE_ALL_IO_LIST +}; + +struct HIRAID_STREAM_S stream_array[MAX_PD_NUM][MAX_STREAM_NUM] = {0}; +struct spinlock_list_head_s io_heads_per_stream[MAX_PD_NUM * MAX_STREAM_NUM]; +spinlock_t stream_array_lock; + +u64 g_io_transport_num[MAX_PD_NUM][MAX_STREAM_NUM] = {0}; +u16 g_io_stream_num[MAX_PD_NUM][TYPE_BOTTOM] = {0}; +u16 g_io_count = 1; + +void hiraid_inc_io_transport_num(u16 disk_id, u16 streamd_id, u16 nlb) +{ + g_io_transport_num[disk_id][streamd_id] += nlb; +} + +void hiraid_refresh_io_transport_num(u16 disk_id, u16 streamd_id) +{ + g_io_transport_num[disk_id][streamd_id] = 0; +} + +void hiraid_inc_stream_num(u16 disk_id) +{ + spin_lock(&stream_array_lock); + g_io_stream_num[disk_id][TYPE_TOTAL]++; + spin_unlock(&stream_array_lock); +} + +void hiraid_dec_stream_num(u16 disk_id) +{ + spin_lock(&stream_array_lock); + if (g_io_stream_num[disk_id][TYPE_TOTAL] > 0) + g_io_stream_num[disk_id][TYPE_TOTAL]--; + spin_unlock(&stream_array_lock); +} + +static bool hiraid_io_recog_check_stream_exceed(u16 disk_id) +{ + bool exceed_flag; + + spin_lock(&stream_array_lock); + exceed_flag = (g_io_stream_num[disk_id][TYPE_TOTAL] >= MAX_STREAM_NUM); + spin_unlock(&stream_array_lock); + return exceed_flag; +} + +static u16 hiraid_get_stream_num(u16 disk_id) +{ + return g_io_stream_num[disk_id][TYPE_TOTAL]; +} + +static inline struct HIRAID_STREAM_S *hiraid_get_stream(u16 disk_id, + u16 stream_id) +{ + return &stream_array[disk_id][stream_id]; +} + +static inline struct spinlock_list_head_s *hiraid_get_io_head(u16 disk_id) +{ + return &(io_heads_per_stream[disk_id]); +} + +static bool hiraid_recognition_acknowledge(const struct HIRAID_STREAM_S *stream) +{ + return (stream->aging_credit >= CREDIT_THRES) ? true : false; +} + +void hiraid_io_recognition_init(void) +{ + u16 i; + + spin_lock_init(&stream_array_lock); + for (i = 0; i < (MAX_PD_NUM * MAX_STREAM_NUM); i++) { + INIT_LIST_HEAD(&hiraid_get_io_head(i)->list); + spin_lock_init(&hiraid_get_io_head(i)->lock); + } +} + +static void hiraid_io_recognition_iterator(struct HIRAID_STREAM_S *stream, + int direction) +{ + stream->aging_grade = stream->aging_grade + direction * INC_GRADE; + stream->aging_grade = MAX(stream->aging_grade, MAX_DECREASE_GRADE); + stream->aging_grade = MIN(stream->aging_grade, MAX_INCREASE_GRADE); + stream->aging_credit = stream->aging_credit + stream->aging_grade; + stream->aging_credit = MAX(stream->aging_credit, MIN_CREDIT); + stream->aging_credit = MIN(stream->aging_credit, MAX_CREDIT); +} + +struct HIRAID_STREAM_S *hiraid_io_pick_stream( + struct hiraid_scsi_rw_cmd *req, u16 type) +{ + struct HIRAID_STREAM_S *first_hit_stream = NULL; + struct HIRAID_STREAM_S *temp_stream = NULL; + u16 pick_flag = 0; + u8 i; + + for (i = 0; i < MAX_STREAM_NUM; i++) { + temp_stream = &stream_array[req->hdid][i]; + temp_stream->stream_id = i; + if (req->slba < temp_stream->stream_lba || + req->slba >= temp_stream->stream_lba + + temp_stream->stream_len || + temp_stream->type != type) { + continue; + } + if (!pick_flag) { + temp_stream->stream_lba = req->slba; + first_hit_stream = temp_stream; + pick_flag = 1; + continue; + } + hiraid_dec_stream_num(req->hdid); + memset(temp_stream, 0, + sizeof(struct HIRAID_STREAM_S)); // 去重影 + } + return first_hit_stream; +} + +static struct HIRAID_STREAM_S *hiraid_init_flow_stream(struct hiraid_scsi_rw_cmd *req, + u16 type) +{ + int i; + struct HIRAID_STREAM_S *stream = NULL; + + for (i = 0; i < MAX_STREAM_NUM; i++) { + stream = hiraid_get_stream(req->hdid, i); + if (!stream->using) { + stream->using = 1; + stream->stream_id = i; + break; + } + } + stream->stream_lba = req->slba; + stream->vd_id = req->hdid; + stream->type = type; + stream->aging_credit = 0; + stream->aging_grade = 0; + stream->stream_len = STREAM_LEN; + return stream; +} + +static struct HIRAID_STREAM_S *hiraid_stream_detect(struct hiraid_dev *hdev, + struct hiraid_scsi_rw_cmd *io_cmd) +{ + u16 type = io_cmd->opcode == HIRAID_CMD_WRITE ? TYPE_WRITE : TYPE_READ; + struct HIRAID_STREAM_S *stream = hiraid_io_pick_stream(io_cmd, type); + + if (stream != NULL) { /* 可以命中一个stream */ + return stream; + } + + if (hiraid_io_recog_check_stream_exceed(io_cmd->hdid)) + return NULL; + stream = hiraid_init_flow_stream(io_cmd, type); + hiraid_inc_stream_num(io_cmd->hdid); + return stream; +} + +u64 g_io_last_pull_time[MAX_PD_NUM] = {0}; + +static u16 hiraid_get_submit_io_stream(u16 did, struct hiraid_dev *hdev) +{ + u64 temp_num, i; + static u16 stream_num[MAX_PD_NUM] = {0}; + + if (g_io_last_pull_time[did] == 0) + g_io_last_pull_time[did] = jiffies_to_msecs(jiffies); + + for (i = 0; i < MAX_STREAM_NUM; i++) { + temp_num = g_io_transport_num[did][i]; + if (temp_num != 0) { + if ((temp_num < MAX_IO_NUM) && + ((jiffies_to_msecs(jiffies) - g_io_last_pull_time[did]) + < IO_SUBMIT_TIME_OUT)) { + stream_num[did] = i; + return i; + } + g_io_last_pull_time[did] = jiffies_to_msecs(jiffies); + hiraid_refresh_io_transport_num(did, i); + stream_num[did] = ((i+1) % MAX_STREAM_NUM); + return ((i+1) % MAX_STREAM_NUM); + } + } + g_io_last_pull_time[did] = jiffies_to_msecs(jiffies); + return ((stream_num[did]++) % MAX_STREAM_NUM); +} + +static void hiraid_submit_io_stream(u16 hdid, struct hiraid_dev *hdev) +{ + struct spinlock_list_head_s *io_slist = NULL; + struct list_head *node = NULL; + struct list_head *next_node = NULL; + struct hiraid_scsi_io_cmd io_cmd = {0}; + struct hiraid_queue *submit_queue = NULL; + unsigned int sector_size = 0; + u16 submit_stream_id = hiraid_get_submit_io_stream(hdid, hdev); + + struct IO_LIST_S *temp_io_stream = NULL; + u16 count = 0; + + io_slist = hiraid_get_io_head(hdid * MAX_STREAM_NUM + submit_stream_id); + spin_lock(&io_slist->lock); + list_for_each_safe(node, next_node, &io_slist->list) { + temp_io_stream = list_entry(node, struct IO_LIST_S, list); + list_del_init(node); + io_cmd = temp_io_stream->io_cmd; + submit_queue = temp_io_stream->submit_queue; + sector_size = temp_io_stream->sector_size; + kfree(temp_io_stream); + temp_io_stream = NULL; + spin_unlock(&io_slist->lock); + hiraid_submit_cmd(submit_queue, &io_cmd); + hiraid_inc_io_transport_num(hdid, + submit_stream_id, io_cmd.rw.nlb * sector_size); + // 单次下发不超过MAX_IO_NUM_ONCE，避免仅发送单盘 + if (++count >= MAX_IO_NUM_ONCE) { + spin_lock(&io_slist->lock); + break; + } + spin_lock(&io_slist->lock); + } + spin_unlock(&io_slist->lock); +} + +static u8 hiraid_detect_if_aging(void) +{ + if (++g_io_count == MAX_AGING_NUM) { + g_io_count = 0; + return 1; + } + return 0; +} + +static void hiraid_aging(struct hiraid_dev *hdev) +{ + struct HIRAID_STREAM_S *temp_stream = NULL; + int i = 0; + int j = 0; + + for (i = 1; i < MAX_PD_NUM; i++) { + for (j = 0; j < MAX_STREAM_NUM; j++) { + temp_stream = hiraid_get_stream(i, j); + if (temp_stream->using) { + hiraid_io_recognition_iterator(temp_stream, -1); + if (temp_stream->aging_credit <= 0) { + hiraid_dec_stream_num(i); + memset(temp_stream, + 0, sizeof(struct HIRAID_STREAM_S)); // 老化 + } + } + } + } +} + +static u8 hiraid_io_list_operation(u32 hdid, u16 cid, u16 hwq, u8 operation) +{ + int i, j; + + struct spinlock_list_head_s *io_slist = NULL; + struct list_head *node = NULL; + struct list_head *next_node = NULL; + struct hiraid_scsi_io_cmd *io_cmd = NULL; + struct hiraid_queue *hiraidq = NULL; + struct IO_LIST_S *temp_io_stream = NULL; + + u8 max_hd_num = operation == TYPE_DELETE_ALL_IO_LIST ? + MAX_PD_NUM : hdid + 1; + for (i = hdid; i < max_hd_num; i++) { + for (j = 0; j < MAX_STREAM_NUM; j++) { + io_slist = hiraid_get_io_head(i * MAX_STREAM_NUM + j); + spin_lock(&io_slist->lock); + list_for_each_safe(node, next_node, &io_slist->list) { + temp_io_stream = list_entry(node, + struct IO_LIST_S, list); + io_cmd = &(temp_io_stream->io_cmd); + hiraidq = temp_io_stream->submit_queue; + if (operation >= TYPE_DELETE_SINGLE_IO_LIST) { + list_del_init(node); + kfree(temp_io_stream); + temp_io_stream = NULL; + } else { + if ((io_cmd->rw.cmd_id == cid) && + (hiraidq->qid == hwq)) { + list_del_init(node); + spin_unlock(&io_slist->lock); + kfree(temp_io_stream); + return 1; + } + } + } + spin_unlock(&io_slist->lock); + } + } + return 0; +} + +static u8 hiraid_check_io_list(u32 hdid, u16 cid, u16 hwq) +{ + return hiraid_io_list_operation(hdid, cid, hwq, TYPE_DELETE_SINGLE_IO); +} + +static u8 hiraid_delete_single_pd_io_list(u32 hdid) +{ + return hiraid_io_list_operation(hdid, 0, 0, TYPE_DELETE_SINGLE_IO_LIST); +} + +static u8 hiraid_delete_all_io_list(void) +{ + return hiraid_io_list_operation(0, 0, 0, TYPE_DELETE_ALL_IO_LIST); +} + +static void hiraid_wait_for_io_submit(struct hiraid_dev *hdev) +{ + struct spinlock_list_head_s *io_slist = NULL; + int i = 0; + int io_flush_finished; + + do { + io_flush_finished = 1; + for (i = 0; i < (MAX_PD_NUM * MAX_STREAM_NUM); i++) { + io_slist = hiraid_get_io_head(i); + if (!list_empty(&io_slist->list)) { + io_flush_finished = 0; + break; + } + } + usleep_range(MIN_WAIT_IO_SEND_TIME, MAX_WAIT_IO_SEND_TIME); + } while (!io_flush_finished); +} + +static u8 hiraid_add_io_to_list(struct hiraid_queue *submit_queue, + struct HIRAID_STREAM_S *tmp_stream, struct hiraid_scsi_io_cmd io_cmd, + unsigned int sector_size) +{ + struct spinlock_list_head_s *io_slist = NULL; + struct IO_LIST_S *new_io_node = NULL; + + new_io_node = kmalloc(sizeof(struct IO_LIST_S), GFP_KERNEL); + if (!new_io_node) + return 0; + new_io_node->io_cmd = io_cmd; + new_io_node->submit_queue = submit_queue; + new_io_node->sector_size = sector_size; + io_slist = hiraid_get_io_head(io_cmd.rw.hdid * + MAX_STREAM_NUM + tmp_stream->stream_id); + spin_lock(&io_slist->lock); + INIT_LIST_HEAD(&(new_io_node->list)); + list_add_tail(&(new_io_node->list), &io_slist->list); + spin_unlock(&io_slist->lock); + return 1; +} + +static void hiraid_submit_io_threading(struct hiraid_dev *hdev) +{ + int i = 1; + + while (!kthread_should_stop()) { + for (i = 1; i < MAX_PD_NUM; i++) + hiraid_submit_io_stream(i, hdev); + usleep_range(MIN_IO_SEND_TIME, MAX_IO_SEND_TIME); + } +} + +static void hiraid_destroy_io_stream_resource(struct hiraid_dev *hdev) +{ + u16 i; + + for (i = 0; i < (MAX_PD_NUM * MAX_STREAM_NUM); i++) + list_del_init(&hiraid_get_io_head(i)->list); +} + +struct task_struct *g_hiraid_submit_task; +static void hiraid_init_io_stream(struct hiraid_dev *hdev) +{ + hiraid_io_recognition_init(); + g_hiraid_submit_task = kthread_run((void *)hiraid_submit_io_threading, + hdev, "hiraid_submit_thread"); +} + #define HIRAID_RW_FUA BIT(14) static int hiraid_setup_rw_cmd(struct hiraid_dev *hdev, @@ -866,6 +1284,30 @@ static int hiraid_setup_nonrw_cmd(struct hiraid_dev *hdev, return 0; } +static bool hiraid_disk_is_hdd(u8 attr) +{ + switch (HIRAID_DEV_DISK_TYPE(attr)) { + case HIRAID_SAS_HDD_VD: + case HIRAID_SATA_HDD_VD: + case HIRAID_SAS_HDD_PD: + case HIRAID_SATA_HDD_PD: + return true; + default: + return false; + } +} + +static bool hiraid_disk_is_hdd_rawdrive(u8 attr) +{ + switch (HIRAID_DEV_DISK_TYPE(attr)) { + case HIRAID_SAS_HDD_PD: + case HIRAID_SATA_HDD_PD: + return true; + default: + return false; + } +} + static int hiraid_setup_io_cmd(struct hiraid_dev *hdev, struct hiraid_scsi_io_cmd *io_cmd, struct scsi_cmnd *scmd) @@ -1023,6 +1465,7 @@ static int hiraid_queue_command(struct Scsi_Host *shost, struct hiraid_sdev_hostdata *hostdata; struct hiraid_scsi_io_cmd io_cmd; struct hiraid_queue *ioq; + struct HIRAID_STREAM_S *tmp_stm = NULL; u16 hwq, cid; int ret; @@ -1085,6 +1528,23 @@ static int hiraid_queue_command(struct Scsi_Host *shost, } WRITE_ONCE(mapbuf->state, CMD_FLIGHT); + + if (hiraid_is_rw_scmd(scmd) && + hiraid_disk_is_hdd_rawdrive(hostdata->attr)) { + if (hiraid_detect_if_aging()) + hiraid_aging(hdev); + tmp_stm = hiraid_stream_detect(hdev, &(io_cmd.rw)); + if (tmp_stm != NULL) { + hiraid_io_recognition_iterator(tmp_stm, 1); + if (hiraid_recognition_acknowledge(tmp_stm) && + (hiraid_get_stream_num(io_cmd.rw.hdid) > 1)) { + if (hiraid_add_io_to_list(ioq, + tmp_stm, io_cmd, sdev->sector_size)) { + return 0; + } + } + } + } hiraid_submit_cmd(ioq, &io_cmd); return 0; @@ -1135,19 +1595,6 @@ static int hiraid_disk_qd(u8 attr) } } -static bool hiraid_disk_is_hdd(u8 attr) -{ - switch (HIRAID_DEV_DISK_TYPE(attr)) { - case HIRAID_SAS_HDD_VD: - case HIRAID_SATA_HDD_VD: - case HIRAID_SAS_HDD_PD: - case HIRAID_SATA_HDD_PD: - return true; - default: - return false; - } -} - static int hiraid_slave_alloc(struct scsi_device *sdev) { struct hiraid_sdev_hostdata *hostdata; @@ -1305,6 +1752,7 @@ static int hiraid_alloc_queue(struct hiraid_dev *hdev, u16 qid, u16 depth) hiraidq->q_depth = depth; hiraidq->qid = qid; hiraidq->cq_vector = -1; + hiraidq->pci_irq = -1; hdev->queue_count++; return 0; @@ -1593,12 +2041,38 @@ static inline bool hiraid_process_cq(struct hiraid_queue *hiraidq, u16 *start, u16 *end, int tag) { bool found = false; + *start = hiraidq->cq_head; + while (!found && hiraid_cqe_pending(hiraidq)) { + if (le16_to_cpu(hiraidq->cqes[hiraidq->cq_head].cmd_id) == tag) + found = true; + hiraid_update_cq_head(hiraidq); + } + *end = hiraidq->cq_head; + + if (*start != *end) + writel(hiraidq->cq_head, + hiraidq->q_db + hiraidq->hdev->db_stride); + + return found; +} +static inline bool hiraid_process_cq_for_thread(struct hiraid_queue *hiraidq, + u16 *start, u16 *end, + u8 *wakeup_thread_flag, int tag) +{ + bool found = false; + u16 max_io_num = hiraidq->q_depth / 4; + u16 io_count = 0; *start = hiraidq->cq_head; while (!found && hiraid_cqe_pending(hiraidq)) { if (le16_to_cpu(hiraidq->cqes[hiraidq->cq_head].cmd_id) == tag) found = true; hiraid_update_cq_head(hiraidq); + + if (++io_count >= max_io_num) { + *wakeup_thread_flag = 1; + break; + } } *end = hiraidq->cq_head; @@ -1646,6 +2120,55 @@ static irqreturn_t hiraid_handle_irq(int irq, void *data) return ret; } +static irqreturn_t hiraid_io_poll(int irq, void *data) +{ + struct hiraid_queue *hiraidq = data; + irqreturn_t ret = IRQ_NONE; + u16 start, end; + + do { + spin_lock(&hiraidq->cq_lock); + hiraid_process_cq(hiraidq, &start, &end, -1); + hiraidq->last_cq_head = hiraidq->cq_head; + spin_unlock(&hiraidq->cq_lock); + + if (start != end) { + hiraid_complete_cqes(hiraidq, start, end); + ret = IRQ_HANDLED; + } + usleep_range(poll_delay_min, poll_delay_max); + } while (start != end); + enable_irq(hiraidq->pci_irq); + return ret; +} + +static irqreturn_t hiraid_io_irq(int irq, void *data) +{ + struct hiraid_queue *hiraidq = data; + irqreturn_t ret = IRQ_NONE; + u16 start, end; + u8 wakeup_thread_flag = 0; + + spin_lock(&hiraidq->cq_lock); + if (hiraidq->cq_head != hiraidq->last_cq_head) + ret = IRQ_HANDLED; + + hiraid_process_cq_for_thread(hiraidq, &start, + &end, &wakeup_thread_flag, -1); + hiraidq->last_cq_head = hiraidq->cq_head; + spin_unlock(&hiraidq->cq_lock); + + if (start != end) { + hiraid_complete_cqes(hiraidq, start, end); + ret = IRQ_HANDLED; + } + if (wakeup_thread_flag) { + disable_irq_nosync(hiraidq->pci_irq); + ret = IRQ_WAKE_THREAD; + } + return ret; +} + static int hiraid_setup_admin_queue(struct hiraid_dev *hdev) { struct hiraid_queue *adminq = &hdev->queues[0]; @@ -1681,9 +2204,11 @@ static int hiraid_setup_admin_queue(struct hiraid_dev *hdev) NULL, adminq, "hiraid%d_q%d", hdev->instance, adminq->qid); if (ret) { adminq->cq_vector = -1; + adminq->pci_irq = -1; return ret; } + adminq->pci_irq = pci_irq_vector(hdev->pdev, adminq->cq_vector); hiraid_init_queue(adminq, 0); dev_info(hdev->dev, "setup admin queue success, queuecount[%d] online[%d] pagesize[%d]\n", @@ -1958,14 +2483,23 @@ static int hiraid_create_queue(struct hiraid_queue *hiraidq, u16 qid) goto delete_cq; hiraidq->cq_vector = cq_vector; - ret = pci_request_irq(hdev->pdev, cq_vector, hiraid_handle_irq, NULL, - hiraidq, "hiraid%d_q%d", hdev->instance, qid); + if (threaded_irq) + ret = pci_request_irq(hdev->pdev, cq_vector, hiraid_io_irq, + hiraid_io_poll, hiraidq, "hiraid%d_q%d", + hdev->instance, qid); + else + ret = pci_request_irq(hdev->pdev, cq_vector, hiraid_handle_irq, + NULL, hiraidq, "hiraid%d_q%d", + hdev->instance, qid); + if (ret) { hiraidq->cq_vector = -1; + hiraidq->pci_irq = -1; dev_err(hdev->dev, "request queue[%d] irq failed\n", qid); goto delete_sq; } + hiraidq->pci_irq = pci_irq_vector(hdev->pdev, hiraidq->cq_vector); hiraid_init_queue(hiraidq, qid); return 0; @@ -2122,10 +2656,11 @@ static int hiraid_setup_io_queues(struct hiraid_dev *hdev) adminq, "hiraid%d_q%d", hdev->instance, adminq->qid); if (ret) { dev_err(hdev->dev, "request admin irq failed\n"); + adminq->pci_irq = -1; adminq->cq_vector = -1; return ret; } - + adminq->pci_irq = pci_irq_vector(hdev->pdev, adminq->cq_vector); hdev->online_queues++; for (i = hdev->queue_count; i <= hdev->max_qid; i++) { @@ -3304,6 +3839,12 @@ static int hiraid_abort(struct scsi_cmnd *scmd) cid = mapbuf->cid; hwq = mapbuf->hiraidq->qid; + if (hiraid_check_io_list(hostdata->hdid, cid, hwq)) { + dev_warn(hdev->dev, "find cid[%d] qid[%d] in host, abort succ\n", + cid, hwq); + return SUCCESS; + } + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, send abort\n", cid, hwq); ret = hiraid_send_abort_cmd(hdev, hostdata->hdid, hwq, cid); if (ret != -ETIME) { @@ -3339,6 +3880,7 @@ static int hiraid_scsi_reset(struct scsi_cmnd *scmd, enum hiraid_rst_type rst) if ((ret == 0) || (ret == FW_EH_DEV_NONE && rst == HIRAID_RESET_TARGET)) { if (rst == HIRAID_RESET_TARGET) { + hiraid_delete_single_pd_io_list(hostdata->hdid); ret = wait_tgt_reset_io_done(scmd); if (ret) { dev_warn(hdev->dev, "sdev[%d:%d] target has %d peding cmd, target reset failed\n", @@ -3378,6 +3920,7 @@ static int hiraid_host_reset(struct scsi_cmnd *scmd) dev_warn(hdev->dev, "sdev[%d:%d] send host reset\n", scmd->device->channel, scmd->device->id); + hiraid_delete_all_io_list(); if (hiraid_reset_work_sync(hdev) == -EBUSY) flush_work(&hdev->reset_work); @@ -3411,6 +3954,7 @@ static pci_ers_result_t hiraid_pci_error_detected(struct pci_dev *pdev, scsi_block_requests(hdev->shost); hiraid_dev_state_trans(hdev, DEV_RESETTING); + hiraid_delete_all_io_list(); return PCI_ERS_RESULT_NEED_RESET; case pci_channel_io_perm_failure: @@ -4044,6 +4588,7 @@ static int hiraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto unregist_bsg; scsi_scan_host(hdev->shost); + hiraid_init_io_stream(hdev); return 0; @@ -4075,6 +4620,13 @@ static void hiraid_remove(struct pci_dev *pdev) dev_info(hdev->dev, "enter hiraid remove\n"); + if (pci_device_is_present(pdev)) + hiraid_wait_for_io_submit(hdev); + + kthread_stop(g_hiraid_submit_task); + hiraid_delete_all_io_list(); + hiraid_destroy_io_stream_resource(hdev); + hiraid_dev_state_trans(hdev, DEV_DELETING); flush_work(&hdev->reset_work); -- 2.45.1.windows.1

2 1

[PATCH OLK-5.10] [Backport] HID: usbhid: Eliminate recurrent out-of-bounds bug in usbhid_parse()
by Chen Jinghuang 19 Jan '26

19 Jan '26

From: Terry Junge <linuxhid(a)cosmicgizmosystems.com> stable inclusion from stable-v5.10.239 commit 41827a2dbdd7880df9881506dee13bc88d4230bb category: bugfix bugzilla: 9660 CVE: CVE-2025-38103 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit fe7f7ac8e0c708446ff017453add769ffc15deed upstream. Update struct hid_descriptor to better reflect the mandatory and optional parts of the HID Descriptor as per USB HID 1.11 specification. Note: the kernel currently does not parse any optional HID class descriptors, only the mandatory report descriptor. Update all references to member element desc[0] to rpt_desc. Add test to verify bLength and bNumDescriptors values are valid. Replace the for loop with direct access to the mandatory HID class descriptor member for the report descriptor. This eliminates the possibility of getting an out-of-bounds fault. Add a warning message if the HID descriptor contains any unsupported optional HID class descriptors. Reported-by: syzbot+c52569baf0c843f35495(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=c52569baf0c843f35495 Fixes: f043bfc98c19 ("HID: usbhid: fix out-of-bounds bug") Cc: stable(a)vger.kernel.org Signed-off-by: Terry Junge <linuxhid(a)cosmicgizmosystems.com> Reviewed-by: Michael Kelley <mhklinux(a)outlook.com> Signed-off-by: Jiri Kosina <jkosina(a)suse.com> Signed-off-by: Terry Junge <linuxhid(a)cosmicgizmosystems.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Chen Jinghuang <chenjinghuang2(a)huawei.com> --- drivers/hid/hid-hyperv.c | 5 +++-- drivers/hid/usbhid/hid-core.c | 25 ++++++++++++++----------- drivers/usb/gadget/function/f_hid.c | 12 ++++++------ include/linux/hid.h | 3 ++- 4 files changed, 25 insertions(+), 20 deletions(-) diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c index b7704dd6809d..bf77cfb723d5 100644 --- a/drivers/hid/hid-hyperv.c +++ b/drivers/hid/hid-hyperv.c @@ -199,7 +199,8 @@ static void mousevsc_on_receive_device_info(struct mousevsc_dev *input_device, if (!input_device->hid_desc) goto cleanup; - input_device->report_desc_size = desc->desc[0].wDescriptorLength; + input_device->report_desc_size = le16_to_cpu( + desc->rpt_desc.wDescriptorLength); if (input_device->report_desc_size == 0) { input_device->dev_info_status = -EINVAL; goto cleanup; @@ -217,7 +218,7 @@ static void mousevsc_on_receive_device_info(struct mousevsc_dev *input_device, memcpy(input_device->report_desc, ((unsigned char *)desc) + desc->bLength, - desc->desc[0].wDescriptorLength); + le16_to_cpu(desc->rpt_desc.wDescriptorLength)); /* Send the ack */ memset(&ack, 0, sizeof(struct mousevsc_prt_msg)); diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index 009a0469d54f..c3b104c72e49 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -984,12 +984,11 @@ static int usbhid_parse(struct hid_device *hid) struct usb_host_interface *interface = intf->cur_altsetting; struct usb_device *dev = interface_to_usbdev (intf); struct hid_descriptor *hdesc; + struct hid_class_descriptor *hcdesc; u32 quirks = 0; unsigned int rsize = 0; char *rdesc; - int ret, n; - int num_descriptors; - size_t offset = offsetof(struct hid_descriptor, desc); + int ret; quirks = hid_lookup_quirk(hid); @@ -1011,20 +1010,19 @@ static int usbhid_parse(struct hid_device *hid) return -ENODEV; } - if (hdesc->bLength < sizeof(struct hid_descriptor)) { - dbg_hid("hid descriptor is too short\n"); + if (!hdesc->bNumDescriptors || + hdesc->bLength != sizeof(*hdesc) + + (hdesc->bNumDescriptors - 1) * sizeof(*hcdesc)) { + dbg_hid("hid descriptor invalid, bLen=%hhu bNum=%hhu\n", + hdesc->bLength, hdesc->bNumDescriptors); return -EINVAL; } hid->version = le16_to_cpu(hdesc->bcdHID); hid->country = hdesc->bCountryCode; - num_descriptors = min_t(int, hdesc->bNumDescriptors, - (hdesc->bLength - offset) / sizeof(struct hid_class_descriptor)); - - for (n = 0; n < num_descriptors; n++) - if (hdesc->desc[n].bDescriptorType == HID_DT_REPORT) - rsize = le16_to_cpu(hdesc->desc[n].wDescriptorLength); + if (hdesc->rpt_desc.bDescriptorType == HID_DT_REPORT) + rsize = le16_to_cpu(hdesc->rpt_desc.wDescriptorLength); if (!rsize || rsize > HID_MAX_DESCRIPTOR_SIZE) { dbg_hid("weird size of report descriptor (%u)\n", rsize); @@ -1052,6 +1050,11 @@ static int usbhid_parse(struct hid_device *hid) goto err; } + if (hdesc->bNumDescriptors > 1) + hid_warn(intf, + "%u unsupported optional hid class descriptors\n", + (int)(hdesc->bNumDescriptors - 1)); + hid->quirks |= quirks; return 0; diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index ba018aeb21d8..2f30699f0426 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -114,8 +114,8 @@ static struct hid_descriptor hidg_desc = { .bcdHID = cpu_to_le16(0x0101), .bCountryCode = 0x00, .bNumDescriptors = 0x1, - /*.desc[0].bDescriptorType = DYNAMIC */ - /*.desc[0].wDescriptorLenght = DYNAMIC */ + /*.rpt_desc.bDescriptorType = DYNAMIC */ + /*.rpt_desc.wDescriptorLength = DYNAMIC */ }; /* Super-Speed Support */ @@ -724,8 +724,8 @@ static int hidg_setup(struct usb_function *f, struct hid_descriptor hidg_desc_copy = hidg_desc; VDBG(cdev, "USB_REQ_GET_DESCRIPTOR: HID\n"); - hidg_desc_copy.desc[0].bDescriptorType = HID_DT_REPORT; - hidg_desc_copy.desc[0].wDescriptorLength = + hidg_desc_copy.rpt_desc.bDescriptorType = HID_DT_REPORT; + hidg_desc_copy.rpt_desc.wDescriptorLength = cpu_to_le16(hidg->report_desc_length); length = min_t(unsigned short, length, @@ -966,8 +966,8 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f) * We can use hidg_desc struct here but we should not relay * that its content won't change after returning from this function. */ - hidg_desc.desc[0].bDescriptorType = HID_DT_REPORT; - hidg_desc.desc[0].wDescriptorLength = + hidg_desc.rpt_desc.bDescriptorType = HID_DT_REPORT; + hidg_desc.rpt_desc.wDescriptorLength = cpu_to_le16(hidg->report_desc_length); hidg_hs_in_ep_desc.bEndpointAddress = diff --git a/include/linux/hid.h b/include/linux/hid.h index 9e306bf9959d..03627c96d814 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -674,8 +674,9 @@ struct hid_descriptor { __le16 bcdHID; __u8 bCountryCode; __u8 bNumDescriptors; + struct hid_class_descriptor rpt_desc; - struct hid_class_descriptor desc[1]; + struct hid_class_descriptor opt_descs[]; } __attribute__ ((packed)); #define HID_DEVICE(b, g, ven, prod) \ -- 2.34.1

2 1

[PATCH OLK-5.10] scsi/hiraid: Support New Raid feature
by LinKun 19 Jan '26

19 Jan '26

From: 岳智超 <yuezhichao1(a)h-partners.com> driver inclusion category: feature bugzilla: https://atomgit.com/openeuler/kernel/issues/8290 CVE: NA -------------------------------- Add thread irq for io queue Add stream detect Signed-off-by: 岳智超 <yuezhichao1(a)h-partners.com> --- drivers/scsi/hisi_raid/hiraid.h | 34 ++ drivers/scsi/hisi_raid/hiraid_main.c | 586 ++++++++++++++++++++++++++- 2 files changed, 604 insertions(+), 16 deletions(-) diff --git a/drivers/scsi/hisi_raid/hiraid.h b/drivers/scsi/hisi_raid/hiraid.h index 04b2e25..b7e3c71 100644 --- a/drivers/scsi/hisi_raid/hiraid.h +++ b/drivers/scsi/hisi_raid/hiraid.h @@ -686,6 +686,7 @@ struct hiraid_queue { atomic_t inflight; void *sense_buffer_virt; dma_addr_t sense_buffer_phy; + s32 pci_irq; struct dma_pool *prp_small_pool; }; @@ -760,5 +761,38 @@ struct hiraid_sdev_hostdata { u16 pend_count; }; +enum stream_type { + TYPE_TOTAL, + TYPE_WRITE, + TYPE_READ, + TYPE_CLEAN, + TYPE_BOTTOM +}; + +struct HIRAID_STREAM_S { + /* recog-window */ + u64 stream_lba; + u32 stream_len; + u16 vd_id; + u16 type; + /* aging ctrl */ + int aging_credit; + int aging_grade; + u16 stream_id; + u16 using; +}; + +struct IO_LIST_S { + struct list_head list; + struct hiraid_scsi_io_cmd io_cmd; + struct hiraid_queue *submit_queue; + unsigned int sector_size; +}; + +struct spinlock_list_head_s { + struct list_head list; + spinlock_t lock; +}; + #endif diff --git a/drivers/scsi/hisi_raid/hiraid_main.c b/drivers/scsi/hisi_raid/hiraid_main.c index 2f33339..a7dc746 100644 --- a/drivers/scsi/hisi_raid/hiraid_main.c +++ b/drivers/scsi/hisi_raid/hiraid_main.c @@ -35,6 +35,10 @@ #include <scsi/scsi_transport.h> #include <scsi/scsi_dbg.h> #include <scsi/sg.h> +#include <linux/kthread.h> +#include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/sched/prio.h> #include "hiraid.h" @@ -107,6 +111,13 @@ static u32 log_debug_switch; module_param(log_debug_switch, uint, 0644); MODULE_PARM_DESC(log_debug_switch, "set log state, default zero for switch off"); +static bool threaded_irq = false; +module_param(threaded_irq, bool, 0444); +MODULE_PARM_DESC(threaded_irq, "use threaded irq for io queue, default off"); + +static u32 poll_delay_min = 9; +static u32 poll_delay_max = 19; + static int extra_pool_num_set(const char *val, const struct kernel_param *kp) { u8 n = 0; @@ -152,7 +163,7 @@ static struct workqueue_struct *work_queue; __func__, ##__VA_ARGS__); \ } while (0) -#define HIRAID_DRV_VERSION "1.1.0.1" +#define HIRAID_DRV_VERSION "1.1.0.2" #define ADMIN_TIMEOUT (admin_tmout * HZ) #define USRCMD_TIMEOUT (180 * HZ) @@ -169,6 +180,15 @@ static struct workqueue_struct *work_queue; #define MAX_CAN_QUEUE (4096 - 1) #define MIN_CAN_QUEUE (1024 - 1) +#define MAX_DECREASE_GRADE (-8) +#define MAX_INCREASE_GRADE 8 +#define INC_GRADE 1 +#define MIN_CREDIT 0 +#define MAX_CREDIT 64 +#define CREDIT_THRES 32 +#define MIN(a, b) (((a) < (b)) ? (a) : (b)) +#define MAX(a, b) (((a) > (b)) ? (a) : (b)) + enum SENSE_STATE_CODE { SENSE_STATE_OK = 0, SENSE_STATE_NEED_CHECK, @@ -749,6 +769,404 @@ static int hiraid_build_sgl(struct hiraid_dev *hdev, struct hiraid_scsi_io_cmd * return 0; } +#define MAX_PD_NUM (40 + 1) +#define MAX_STREAM_NUM 8 +#define PER_MB (1024 * 1024) +#define MAX_IO_NUM (200 * PER_MB) +#define STREAM_LEN (4 * PER_MB) +#define MAX_IO_NUM_ONCE 128 +#define IO_SUBMIT_TIME_OUT 100 +#define MAX_AGING_NUM 130 + +#define MIN_IO_SEND_TIME 10 +#define MAX_IO_SEND_TIME 50 + +#define MIN_WAIT_IO_SEND_TIME 10 +#define MAX_WAIT_IO_SEND_TIME 20 + +enum io_operation_type { + TYPE_DELETE_SINGLE_IO = 1, + TYPE_DELETE_SINGLE_IO_LIST, + TYPE_DELETE_ALL_IO_LIST +}; + +struct HIRAID_STREAM_S stream_array[MAX_PD_NUM][MAX_STREAM_NUM] = {0}; +struct spinlock_list_head_s io_heads_per_stream[MAX_PD_NUM * MAX_STREAM_NUM]; +spinlock_t stream_array_lock; + +u64 g_io_transport_num[MAX_PD_NUM][MAX_STREAM_NUM] = {0}; +u16 g_io_stream_num[MAX_PD_NUM][TYPE_BOTTOM] = {0}; +u16 g_io_count = 1; + +void hiraid_inc_io_transport_num(u16 disk_id, u16 streamd_id, u16 nlb) +{ + g_io_transport_num[disk_id][streamd_id] += nlb; +} + +void hiraid_refresh_io_transport_num(u16 disk_id, u16 streamd_id) +{ + g_io_transport_num[disk_id][streamd_id] = 0; +} + +void hiraid_inc_stream_num(u16 disk_id) +{ + spin_lock(&stream_array_lock); + g_io_stream_num[disk_id][TYPE_TOTAL]++; + spin_unlock(&stream_array_lock); +} + +void hiraid_dec_stream_num(u16 disk_id) +{ + spin_lock(&stream_array_lock); + if (g_io_stream_num[disk_id][TYPE_TOTAL] > 0) + g_io_stream_num[disk_id][TYPE_TOTAL]--; + spin_unlock(&stream_array_lock); +} + +static bool hiraid_io_recog_check_stream_exceed(u16 disk_id) +{ + bool exceed_flag; + + spin_lock(&stream_array_lock); + exceed_flag = (g_io_stream_num[disk_id][TYPE_TOTAL] >= MAX_STREAM_NUM); + spin_unlock(&stream_array_lock); + return exceed_flag; +} + +static u16 hiraid_get_stream_num(u16 disk_id) +{ + return g_io_stream_num[disk_id][TYPE_TOTAL]; +} + +static inline struct HIRAID_STREAM_S *hiraid_get_stream(u16 disk_id, + u16 stream_id) +{ + return &stream_array[disk_id][stream_id]; +} + +static inline struct spinlock_list_head_s *hiraid_get_io_head(u16 disk_id) +{ + return &(io_heads_per_stream[disk_id]); +} + +static bool hiraid_recognition_acknowledge(const struct HIRAID_STREAM_S *stream) +{ + return (stream->aging_credit >= CREDIT_THRES) ? true : false; +} + +void hiraid_io_recognition_init(void) +{ + u16 i; + + spin_lock_init(&stream_array_lock); + for (i = 0; i < (MAX_PD_NUM * MAX_STREAM_NUM); i++) { + INIT_LIST_HEAD(&hiraid_get_io_head(i)->list); + spin_lock_init(&hiraid_get_io_head(i)->lock); + } +} + +static void hiraid_io_recognition_iterator(struct HIRAID_STREAM_S *stream, + int direction) +{ + stream->aging_grade = stream->aging_grade + direction * INC_GRADE; + stream->aging_grade = MAX(stream->aging_grade, MAX_DECREASE_GRADE); + stream->aging_grade = MIN(stream->aging_grade, MAX_INCREASE_GRADE); + stream->aging_credit = stream->aging_credit + stream->aging_grade; + stream->aging_credit = MAX(stream->aging_credit, MIN_CREDIT); + stream->aging_credit = MIN(stream->aging_credit, MAX_CREDIT); +} + +struct HIRAID_STREAM_S *hiraid_io_pick_stream( + struct hiraid_scsi_rw_cmd *req, u16 type) +{ + struct HIRAID_STREAM_S *first_hit_stream = NULL; + struct HIRAID_STREAM_S *temp_stream = NULL; + u16 pick_flag = 0; + u8 i; + + for (i = 0; i < MAX_STREAM_NUM; i++) { + temp_stream = &stream_array[req->hdid][i]; + temp_stream->stream_id = i; + if (req->slba < temp_stream->stream_lba || + req->slba >= temp_stream->stream_lba + + temp_stream->stream_len || + temp_stream->type != type) { + continue; + } + if (!pick_flag) { + temp_stream->stream_lba = req->slba; + first_hit_stream = temp_stream; + pick_flag = 1; + continue; + } + hiraid_dec_stream_num(req->hdid); + memset(temp_stream, 0, + sizeof(struct HIRAID_STREAM_S)); // 去重影 + } + return first_hit_stream; +} + +static struct HIRAID_STREAM_S *hiraid_init_flow_stream(struct hiraid_scsi_rw_cmd *req, + u16 type) +{ + int i; + struct HIRAID_STREAM_S *stream = NULL; + + for (i = 0; i < MAX_STREAM_NUM; i++) { + stream = hiraid_get_stream(req->hdid, i); + if (!stream->using) { + stream->using = 1; + stream->stream_id = i; + break; + } + } + stream->stream_lba = req->slba; + stream->vd_id = req->hdid; + stream->type = type; + stream->aging_credit = 0; + stream->aging_grade = 0; + stream->stream_len = STREAM_LEN; + return stream; +} + +static struct HIRAID_STREAM_S *hiraid_stream_detect(struct hiraid_dev *hdev, + struct hiraid_scsi_rw_cmd *io_cmd) +{ + u16 type = io_cmd->opcode == HIRAID_CMD_WRITE ? TYPE_WRITE : TYPE_READ; + struct HIRAID_STREAM_S *stream = hiraid_io_pick_stream(io_cmd, type); + + if (stream != NULL) { /* 可以命中一个stream */ + return stream; + } + + if (hiraid_io_recog_check_stream_exceed(io_cmd->hdid)) + return NULL; + stream = hiraid_init_flow_stream(io_cmd, type); + hiraid_inc_stream_num(io_cmd->hdid); + return stream; +} + +u64 g_io_last_pull_time[MAX_PD_NUM] = {0}; + +static u16 hiraid_get_submit_io_stream(u16 did, struct hiraid_dev *hdev) +{ + u64 temp_num, i; + static u16 stream_num[MAX_PD_NUM] = {0}; + + if (g_io_last_pull_time[did] == 0) + g_io_last_pull_time[did] = jiffies_to_msecs(jiffies); + + for (i = 0; i < MAX_STREAM_NUM; i++) { + temp_num = g_io_transport_num[did][i]; + if (temp_num != 0) { + if ((temp_num < MAX_IO_NUM) && + ((jiffies_to_msecs(jiffies) - g_io_last_pull_time[did]) + < IO_SUBMIT_TIME_OUT)) { + stream_num[did] = i; + return i; + } + g_io_last_pull_time[did] = jiffies_to_msecs(jiffies); + hiraid_refresh_io_transport_num(did, i); + stream_num[did] = ((i+1) % MAX_STREAM_NUM); + return ((i+1) % MAX_STREAM_NUM); + } + } + g_io_last_pull_time[did] = jiffies_to_msecs(jiffies); + return ((stream_num[did]++) % MAX_STREAM_NUM); +} + +static void hiraid_submit_io_stream(u16 hdid, struct hiraid_dev *hdev) +{ + struct spinlock_list_head_s *io_slist = NULL; + struct list_head *node = NULL; + struct list_head *next_node = NULL; + struct hiraid_scsi_io_cmd io_cmd = {0}; + struct hiraid_queue *submit_queue = NULL; + unsigned int sector_size = 0; + u16 submit_stream_id = hiraid_get_submit_io_stream(hdid, hdev); + + struct IO_LIST_S *temp_io_stream = NULL; + u16 count = 0; + + io_slist = hiraid_get_io_head(hdid * MAX_STREAM_NUM + submit_stream_id); + spin_lock(&io_slist->lock); + list_for_each_safe(node, next_node, &io_slist->list) { + temp_io_stream = list_entry(node, struct IO_LIST_S, list); + list_del_init(node); + io_cmd = temp_io_stream->io_cmd; + submit_queue = temp_io_stream->submit_queue; + sector_size = temp_io_stream->sector_size; + kfree(temp_io_stream); + temp_io_stream = NULL; + spin_unlock(&io_slist->lock); + hiraid_submit_cmd(submit_queue, &io_cmd); + hiraid_inc_io_transport_num(hdid, + submit_stream_id, io_cmd.rw.nlb * sector_size); + // 单次下发不超过MAX_IO_NUM_ONCE，避免仅发送单盘 + if (++count >= MAX_IO_NUM_ONCE) { + spin_lock(&io_slist->lock); + break; + } + spin_lock(&io_slist->lock); + } + spin_unlock(&io_slist->lock); +} + +static u8 hiraid_detect_if_aging(void) +{ + if (++g_io_count == MAX_AGING_NUM) { + g_io_count = 0; + return 1; + } + return 0; +} + +static void hiraid_aging(struct hiraid_dev *hdev) +{ + struct HIRAID_STREAM_S *temp_stream = NULL; + int i = 0; + int j = 0; + + for (i = 1; i < MAX_PD_NUM; i++) { + for (j = 0; j < MAX_STREAM_NUM; j++) { + temp_stream = hiraid_get_stream(i, j); + if (temp_stream->using) { + hiraid_io_recognition_iterator(temp_stream, -1); + if (temp_stream->aging_credit <= 0) { + hiraid_dec_stream_num(i); + memset(temp_stream, + 0, sizeof(struct HIRAID_STREAM_S)); // 老化 + } + } + } + } +} + +static u8 hiraid_io_list_operation(u32 hdid, u16 cid, u16 hwq, u8 operation) +{ + int i, j; + + struct spinlock_list_head_s *io_slist = NULL; + struct list_head *node = NULL; + struct list_head *next_node = NULL; + struct hiraid_scsi_io_cmd *io_cmd = NULL; + struct hiraid_queue *hiraidq = NULL; + struct IO_LIST_S *temp_io_stream = NULL; + + u8 max_hd_num = operation == TYPE_DELETE_ALL_IO_LIST ? + MAX_PD_NUM : hdid + 1; + for (i = hdid; i < max_hd_num; i++) { + for (j = 0; j < MAX_STREAM_NUM; j++) { + io_slist = hiraid_get_io_head(i * MAX_STREAM_NUM + j); + spin_lock(&io_slist->lock); + list_for_each_safe(node, next_node, &io_slist->list) { + temp_io_stream = list_entry(node, + struct IO_LIST_S, list); + io_cmd = &(temp_io_stream->io_cmd); + hiraidq = temp_io_stream->submit_queue; + if (operation >= TYPE_DELETE_SINGLE_IO_LIST) { + list_del_init(node); + kfree(temp_io_stream); + temp_io_stream = NULL; + } else { + if ((io_cmd->rw.cmd_id == cid) && + (hiraidq->qid == hwq)) { + list_del_init(node); + spin_unlock(&io_slist->lock); + kfree(temp_io_stream); + return 1; + } + } + } + spin_unlock(&io_slist->lock); + } + } + return 0; +} + +static u8 hiraid_check_io_list(u32 hdid, u16 cid, u16 hwq) +{ + return hiraid_io_list_operation(hdid, cid, hwq, TYPE_DELETE_SINGLE_IO); +} + +static u8 hiraid_delete_single_pd_io_list(u32 hdid) +{ + return hiraid_io_list_operation(hdid, 0, 0, TYPE_DELETE_SINGLE_IO_LIST); +} + +static u8 hiraid_delete_all_io_list(void) +{ + return hiraid_io_list_operation(0, 0, 0, TYPE_DELETE_ALL_IO_LIST); +} + +static void hiraid_wait_for_io_submit(struct hiraid_dev *hdev) +{ + struct spinlock_list_head_s *io_slist = NULL; + int i = 0; + int io_flush_finished; + + do { + io_flush_finished = 1; + for (i = 0; i < (MAX_PD_NUM * MAX_STREAM_NUM); i++) { + io_slist = hiraid_get_io_head(i); + if (!list_empty(&io_slist->list)) { + io_flush_finished = 0; + break; + } + } + usleep_range(MIN_WAIT_IO_SEND_TIME, MAX_WAIT_IO_SEND_TIME); + } while (!io_flush_finished); +} + +static u8 hiraid_add_io_to_list(struct hiraid_queue *submit_queue, + struct HIRAID_STREAM_S *tmp_stream, struct hiraid_scsi_io_cmd io_cmd, + unsigned int sector_size) +{ + struct spinlock_list_head_s *io_slist = NULL; + struct IO_LIST_S *new_io_node = NULL; + + new_io_node = kmalloc(sizeof(struct IO_LIST_S), GFP_KERNEL); + if (!new_io_node) + return 0; + new_io_node->io_cmd = io_cmd; + new_io_node->submit_queue = submit_queue; + new_io_node->sector_size = sector_size; + io_slist = hiraid_get_io_head(io_cmd.rw.hdid * + MAX_STREAM_NUM + tmp_stream->stream_id); + spin_lock(&io_slist->lock); + INIT_LIST_HEAD(&(new_io_node->list)); + list_add_tail(&(new_io_node->list), &io_slist->list); + spin_unlock(&io_slist->lock); + return 1; +} + +static void hiraid_submit_io_threading(struct hiraid_dev *hdev) +{ + int i = 1; + + while (!kthread_should_stop()) { + for (i = 1; i < MAX_PD_NUM; i++) + hiraid_submit_io_stream(i, hdev); + usleep_range(MIN_IO_SEND_TIME, MAX_IO_SEND_TIME); + } +} + +static void hiraid_destroy_io_stream_resource(struct hiraid_dev *hdev) +{ + u16 i; + + for (i = 0; i < (MAX_PD_NUM * MAX_STREAM_NUM); i++) + list_del_init(&hiraid_get_io_head(i)->list); +} + +struct task_struct *g_hiraid_submit_task; +static void hiraid_init_io_stream(struct hiraid_dev *hdev) +{ + hiraid_io_recognition_init(); + g_hiraid_submit_task = kthread_run((void *)hiraid_submit_io_threading, + hdev, "hiraid_submit_thread"); +} + #define HIRAID_RW_FUA BIT(14) #define RW_LENGTH_ZERO (67) @@ -871,6 +1289,30 @@ static int hiraid_setup_nonrw_cmd(struct hiraid_dev *hdev, return 0; } +static bool hiraid_disk_is_hdd(u8 attr) +{ + switch (HIRAID_DEV_DISK_TYPE(attr)) { + case HIRAID_SAS_HDD_VD: + case HIRAID_SATA_HDD_VD: + case HIRAID_SAS_HDD_PD: + case HIRAID_SATA_HDD_PD: + return true; + default: + return false; + } +} + +static bool hiraid_disk_is_hdd_rawdrive(u8 attr) +{ + switch (HIRAID_DEV_DISK_TYPE(attr)) { + case HIRAID_SAS_HDD_PD: + case HIRAID_SATA_HDD_PD: + return true; + default: + return false; + } +} + static int hiraid_setup_io_cmd(struct hiraid_dev *hdev, struct hiraid_scsi_io_cmd *io_cmd, struct scsi_cmnd *scmd, struct hiraid_mapmange *mapbuf) @@ -1025,6 +1467,7 @@ static int hiraid_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd) struct hiraid_sdev_hostdata *hostdata; struct hiraid_scsi_io_cmd io_cmd; struct hiraid_queue *ioq; + struct HIRAID_STREAM_S *tmp_stm = NULL; u16 hwq, cid; int ret; @@ -1092,6 +1535,23 @@ static int hiraid_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd) } WRITE_ONCE(mapbuf->state, CMD_FLIGHT); + + if (hiraid_is_rw_scmd(scmd) && + hiraid_disk_is_hdd_rawdrive(hostdata->attr)) { + if (hiraid_detect_if_aging()) + hiraid_aging(hdev); + tmp_stm = hiraid_stream_detect(hdev, &(io_cmd.rw)); + if (tmp_stm != NULL) { + hiraid_io_recognition_iterator(tmp_stm, 1); + if (hiraid_recognition_acknowledge(tmp_stm) && + (hiraid_get_stream_num(io_cmd.rw.hdid) > 1)) { + if (hiraid_add_io_to_list(ioq, + tmp_stm, io_cmd, sdev->sector_size)) { + return 0; + } + } + } + } hiraid_submit_cmd(ioq, &io_cmd); return 0; @@ -1141,19 +1601,6 @@ static int hiraid_disk_qd(u8 attr) } } -static bool hiraid_disk_is_hdd(u8 attr) -{ - switch (HIRAID_DEV_DISK_TYPE(attr)) { - case HIRAID_SAS_HDD_VD: - case HIRAID_SATA_HDD_VD: - case HIRAID_SAS_HDD_PD: - case HIRAID_SATA_HDD_PD: - return true; - default: - return false; - } -} - static int hiraid_slave_alloc(struct scsi_device *sdev) { struct hiraid_sdev_hostdata *hostdata; @@ -1305,6 +1752,7 @@ static int hiraid_alloc_queue(struct hiraid_dev *hdev, u16 qid, u16 depth) hiraidq->q_depth = depth; hiraidq->qid = qid; hiraidq->cq_vector = -1; + hiraidq->pci_irq = -1; hdev->queue_count++; return 0; @@ -1594,6 +2042,33 @@ static inline bool hiraid_process_cq(struct hiraid_queue *hiraidq, u16 *start, u return found; } +static inline bool hiraid_process_cq_for_thread(struct hiraid_queue *hiraidq, + u16 *start, u16 *end, + u8 *wakeup_thread_flag, int tag) +{ + bool found = false; + u16 max_io_num = hiraidq->q_depth / 4; + u16 io_count = 0; + *start = hiraidq->cq_head; + while (!found && hiraid_cqe_pending(hiraidq)) { + if (le16_to_cpu(hiraidq->cqes[hiraidq->cq_head].cmd_id) == tag) + found = true; + hiraid_update_cq_head(hiraidq); + + if (++io_count >= max_io_num) { + *wakeup_thread_flag = 1; + break; + } + } + *end = hiraidq->cq_head; + + if (*start != *end) + writel(hiraidq->cq_head, + hiraidq->q_db + hiraidq->hdev->db_stride); + + return found; +} + static bool hiraid_poll_cq(struct hiraid_queue *hiraidq, int cid) { u16 start, end; @@ -1631,6 +2106,55 @@ static irqreturn_t hiraid_handle_irq(int irq, void *data) return ret; } +static irqreturn_t hiraid_io_poll(int irq, void *data) +{ + struct hiraid_queue *hiraidq = data; + irqreturn_t ret = IRQ_NONE; + u16 start, end; + + do { + spin_lock(&hiraidq->cq_lock); + hiraid_process_cq(hiraidq, &start, &end, -1); + hiraidq->last_cq_head = hiraidq->cq_head; + spin_unlock(&hiraidq->cq_lock); + + if (start != end) { + hiraid_complete_cqes(hiraidq, start, end); + ret = IRQ_HANDLED; + } + usleep_range(poll_delay_min, poll_delay_max); + } while (start != end); + enable_irq(hiraidq->pci_irq); + return ret; +} + +static irqreturn_t hiraid_io_irq(int irq, void *data) +{ + struct hiraid_queue *hiraidq = data; + irqreturn_t ret = IRQ_NONE; + u16 start, end; + u8 wakeup_thread_flag = 0; + + spin_lock(&hiraidq->cq_lock); + if (hiraidq->cq_head != hiraidq->last_cq_head) + ret = IRQ_HANDLED; + + hiraid_process_cq_for_thread(hiraidq, &start, + &end, &wakeup_thread_flag, -1); + hiraidq->last_cq_head = hiraidq->cq_head; + spin_unlock(&hiraidq->cq_lock); + + if (start != end) { + hiraid_complete_cqes(hiraidq, start, end); + ret = IRQ_HANDLED; + } + if (wakeup_thread_flag) { + disable_irq_nosync(hiraidq->pci_irq); + ret = IRQ_WAKE_THREAD; + } + return ret; +} + static int hiraid_setup_admin_queue(struct hiraid_dev *hdev) { struct hiraid_queue *adminq = &hdev->queues[0]; @@ -1666,9 +2190,11 @@ static int hiraid_setup_admin_queue(struct hiraid_dev *hdev) adminq, "hiraid%d_q%d", hdev->instance, adminq->qid); if (ret) { adminq->cq_vector = -1; + adminq->pci_irq = -1; return ret; } + adminq->pci_irq = pci_irq_vector(hdev->pdev, adminq->cq_vector); hiraid_init_queue(adminq, 0); dev_info(hdev->dev, "setup admin queue success, queuecount[%d] online[%d] pagesize[%d]\n", @@ -1937,14 +2463,23 @@ static int hiraid_create_queue(struct hiraid_queue *hiraidq, u16 qid) goto delete_cq; hiraidq->cq_vector = cq_vector; - ret = pci_request_irq(hdev->pdev, cq_vector, hiraid_handle_irq, NULL, - hiraidq, "hiraid%d_q%d", hdev->instance, qid); + + if (threaded_irq) + ret = pci_request_irq(hdev->pdev, cq_vector, hiraid_io_irq, + hiraid_io_poll, hiraidq, "hiraid%d_q%d", + hdev->instance, qid); + else + ret = pci_request_irq(hdev->pdev, cq_vector, hiraid_handle_irq, + NULL, hiraidq, "hiraid%d_q%d", + hdev->instance, qid); if (ret) { hiraidq->cq_vector = -1; + hiraidq->pci_irq = -1; dev_err(hdev->dev, "request queue[%d] irq failed\n", qid); goto delete_sq; } + hiraidq->pci_irq = pci_irq_vector(hdev->pdev, hiraidq->cq_vector); hiraid_init_queue(hiraidq, qid); return 0; @@ -2094,10 +2629,12 @@ static int hiraid_setup_io_queues(struct hiraid_dev *hdev) adminq, "hiraid%d_q%d", hdev->instance, adminq->qid); if (ret) { dev_err(hdev->dev, "request admin irq failed\n"); + adminq->pci_irq = -1; adminq->cq_vector = -1; return ret; } + adminq->pci_irq = pci_irq_vector(hdev->pdev, adminq->cq_vector); hdev->online_queues++; for (i = hdev->queue_count; i <= hdev->max_qid; i++) { @@ -3232,6 +3769,12 @@ static int hiraid_abort(struct scsi_cmnd *scmd) cid = mapbuf->cid; hwq = mapbuf->hiraidq->qid; + if (hiraid_check_io_list(hostdata->hdid, cid, hwq)) { + dev_warn(hdev->dev, "find cid[%d] qid[%d] in host, abort succ\n", + cid, hwq); + return SUCCESS; + } + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, send abort\n", cid, hwq); ret = hiraid_send_abort_cmd(hdev, hostdata->hdid, hwq, cid); if (ret != -ETIME) { @@ -3263,6 +3806,7 @@ static int hiraid_scsi_reset(struct scsi_cmnd *scmd, enum hiraid_rst_type rst) ret = hiraid_send_reset_cmd(hdev, rst, hostdata->hdid); if ((ret == 0) || (ret == FW_EH_DEV_NONE && rst == HIRAID_RESET_TARGET)) { if (rst == HIRAID_RESET_TARGET) { + hiraid_delete_single_pd_io_list(hostdata->hdid); ret = wait_tgt_reset_io_done(scmd); if (ret) { dev_warn(hdev->dev, "sdev[%d:%d] target has %d peding cmd, target reset failed\n", @@ -3300,6 +3844,7 @@ static int hiraid_host_reset(struct scsi_cmnd *scmd) dev_warn(hdev->dev, "sdev[%d:%d] send host reset\n", scmd->device->channel, scmd->device->id); + hiraid_delete_all_io_list(); if (hiraid_reset_work_sync(hdev) == -EBUSY) flush_work(&hdev->reset_work); @@ -3333,6 +3878,7 @@ static pci_ers_result_t hiraid_pci_error_detected(struct pci_dev *pdev, scsi_block_requests(hdev->shost); hiraid_dev_state_trans(hdev, DEV_RESETTING); + hiraid_delete_all_io_list(); return PCI_ERS_RESULT_NEED_RESET; case pci_channel_io_perm_failure: @@ -3906,6 +4452,7 @@ static int hiraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto unregist_bsg; scsi_scan_host(hdev->shost); + hiraid_init_io_stream(hdev); return 0; @@ -3937,6 +4484,13 @@ static void hiraid_remove(struct pci_dev *pdev) dev_info(hdev->dev, "enter hiraid remove\n"); + if (pci_device_is_present(pdev)) + hiraid_wait_for_io_submit(hdev); + + kthread_stop(g_hiraid_submit_task); + hiraid_delete_all_io_list(); + hiraid_destroy_io_stream_resource(hdev); + hiraid_dev_state_trans(hdev, DEV_DELETING); flush_work(&hdev->reset_work); -- 2.45.1.windows.1

2 1