From 993ce09fe622866d2126839ebf5875b6175f9f7f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 21 Sep 2024 14:25:37 -0400 Subject: [PATCH 1/5] NFSD: Mark filecache "down" if init fails [ Upstream commit dc0d0f885aa422f621bc1c2124133eff566b0bc8 ] NeilBrown says: > The handling of NFSD_FILE_CACHE_UP is strange. nfsd_file_cache_init() > sets it, but doesn't clear it on failure. So if nfsd_file_cache_init() > fails for some reason, nfsd_file_cache_shutdown() would still try to > clean up if it was called. Reported-by: NeilBrown Fixes: c7b824c3d06c ("NFSD: Replace the "init once" mechanism") Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- fs/nfsd/filecache.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 31169f0cc3d7..585163b4e11c 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -717,7 +717,7 @@ nfsd_file_cache_init(void) ret = rhltable_init(&nfsd_file_rhltable, &nfsd_file_rhash_params); if (ret) - return ret; + goto out; ret = -ENOMEM; nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", 0, 0); @@ -769,6 +769,8 @@ nfsd_file_cache_init(void) INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_gc_worker); out: + if (ret) + clear_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags); return ret; out_notifier: lease_unregister_notifier(&nfsd_file_lease_notifier); From 1fc13f6a41665217480b977f31cdddc47646a3c5 Mon Sep 17 00:00:00 2001 From: Dave Ertman Date: Wed, 18 Sep 2024 14:02:56 -0400 Subject: [PATCH 2/5] ice: fix VLAN replay after reset [ Upstream commit 0eae2c136cb624e4050092feb59f18159b4f2512 ] There is a bug currently when there are more than one VLAN defined and any reset that affects the PF is initiated, after the reset rebuild no traffic will pass on any VLAN but the last one created. This is caused by the iteration though the VLANs during replay each clearing the vsi_map bitmap of the VSI that is being replayed. The problem is that during rhe replay, the pointer to the vsi_map bitmap is used by each successive vlan to determine if it should be replayed on this VSI. The logic was that the replay of the VLAN would replace the bit in the map before the next VLAN would iterate through. But, since the replay copies the old bitmap pointer to filt_replay_rules and creates a new one for the recreated VLANS, it does not do this, and leaves the old bitmap broken to be used to replay the remaining VLANs. Since the old bitmap will be cleaned up in post replay cleanup, there is no need to alter it and break following VLAN replay, so don't clear the bit. Fixes: 334cb0626de1 ("ice: Implement VSI replay framework") Reviewed-by: Przemek Kitszel Signed-off-by: Dave Ertman Reviewed-by: Jacob Keller Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_switch.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 1645fb527fdb..68d756e86ca1 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -2789,8 +2789,6 @@ ice_replay_vsi_fltr(struct ice_hw *hw, u16 vsi_handle, u8 recp_id, if (!itr->vsi_list_info || !test_bit(vsi_handle, itr->vsi_list_info->vsi_map)) continue; - /* Clearing it so that the logic can add it back */ - clear_bit(vsi_handle, itr->vsi_list_info->vsi_map); f_entry.fltr_info.vsi_handle = vsi_handle; f_entry.fltr_info.fltr_act = ICE_FWD_TO_VSI; /* update the src in case it is VSI num */ From 64f1b4922b6e042473e4980a06a2d908bdb6943f Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 19 Sep 2024 11:50:33 +0300 Subject: [PATCH 3/5] SUNRPC: Fix integer overflow in decode_rc_list() [ Upstream commit 6dbf1f341b6b35bcc20ff95b6b315e509f6c5369 ] The math in "rc_list->rcl_nrefcalls * 2 * sizeof(uint32_t)" could have an integer overflow. Add bounds checking on rc_list->rcl_nrefcalls to fix that. Fixes: 4aece6a19cf7 ("nfs41: cb_sequence xdr implementation") Signed-off-by: Dan Carpenter Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/callback_xdr.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index db69fc267c9a..c8f5a0555ad2 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -372,6 +372,8 @@ static __be32 decode_rc_list(struct xdr_stream *xdr, rc_list->rcl_nrefcalls = ntohl(*p++); if (rc_list->rcl_nrefcalls) { + if (unlikely(rc_list->rcl_nrefcalls > xdr->buf->len)) + goto out; p = xdr_inline_decode(xdr, rc_list->rcl_nrefcalls * 2 * sizeof(uint32_t)); if (unlikely(p == NULL)) From f892165c564e3aab272948dbb556cc20e290c55a Mon Sep 17 00:00:00 2001 From: Yanjun Zhang Date: Tue, 1 Oct 2024 16:39:30 +0800 Subject: [PATCH 4/5] NFSv4: Prevent NULL-pointer dereference in nfs42_complete_copies() [ Upstream commit a848c29e3486189aaabd5663bc11aea50c5bd144 ] On the node of an NFS client, some files saved in the mountpoint of the NFS server were copied to another location of the same NFS server. Accidentally, the nfs42_complete_copies() got a NULL-pointer dereference crash with the following syslog: [232064.838881] NFSv4: state recovery failed for open file nfs/pvc-12b5200d-cd0f-46a3-b9f0-af8f4fe0ef64.qcow2, error = -116 [232064.839360] NFSv4: state recovery failed for open file nfs/pvc-12b5200d-cd0f-46a3-b9f0-af8f4fe0ef64.qcow2, error = -116 [232066.588183] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000058 [232066.588586] Mem abort info: [232066.588701] ESR = 0x0000000096000007 [232066.588862] EC = 0x25: DABT (current EL), IL = 32 bits [232066.589084] SET = 0, FnV = 0 [232066.589216] EA = 0, S1PTW = 0 [232066.589340] FSC = 0x07: level 3 translation fault [232066.589559] Data abort info: [232066.589683] ISV = 0, ISS = 0x00000007 [232066.589842] CM = 0, WnR = 0 [232066.589967] user pgtable: 64k pages, 48-bit VAs, pgdp=00002000956ff400 [232066.590231] [0000000000000058] pgd=08001100ae100003, p4d=08001100ae100003, pud=08001100ae100003, pmd=08001100b3c00003, pte=0000000000000000 [232066.590757] Internal error: Oops: 96000007 [#1] SMP [232066.590958] Modules linked in: rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs ocfs2_dlmfs ocfs2_stack_o2cb ocfs2_dlm vhost_net vhost vhost_iotlb tap tun ipt_rpfilter xt_multiport ip_set_hash_ip ip_set_hash_net xfrm_interface xfrm6_tunnel tunnel4 tunnel6 esp4 ah4 wireguard libcurve25519_generic veth xt_addrtype xt_set nf_conntrack_netlink ip_set_hash_ipportnet ip_set_hash_ipportip ip_set_bitmap_port ip_set_hash_ipport dummy ip_set ip_vs_sh ip_vs_wrr ip_vs_rr ip_vs iptable_filter sch_ingress nfnetlink_cttimeout vport_gre ip_gre ip_tunnel gre vport_geneve geneve vport_vxlan vxlan ip6_udp_tunnel udp_tunnel openvswitch nf_conncount dm_round_robin dm_service_time dm_multipath xt_nat xt_MASQUERADE nft_chain_nat nf_nat xt_mark xt_conntrack xt_comment nft_compat nft_counter nf_tables nfnetlink ocfs2 ocfs2_nodemanager ocfs2_stackglue iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi ipmi_ssif nbd overlay 8021q garp mrp bonding tls rfkill sunrpc ext4 mbcache jbd2 [232066.591052] vfat fat cas_cache cas_disk ses enclosure scsi_transport_sas sg acpi_ipmi ipmi_si ipmi_devintf ipmi_msghandler ip_tables vfio_pci vfio_pci_core vfio_virqfd vfio_iommu_type1 vfio dm_mirror dm_region_hash dm_log dm_mod nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 br_netfilter bridge stp llc fuse xfs libcrc32c ast drm_vram_helper qla2xxx drm_kms_helper syscopyarea crct10dif_ce sysfillrect ghash_ce sysimgblt sha2_ce fb_sys_fops cec sha256_arm64 sha1_ce drm_ttm_helper ttm nvme_fc igb sbsa_gwdt nvme_fabrics drm nvme_core i2c_algo_bit i40e scsi_transport_fc megaraid_sas aes_neon_bs [232066.596953] CPU: 6 PID: 4124696 Comm: 10.253.166.125- Kdump: loaded Not tainted 5.15.131-9.cl9_ocfs2.aarch64 #1 [232066.597356] Hardware name: Great Wall .\x93\x8e...RF6260 V5/GWMSSE2GL1T, BIOS T656FBE_V3.0.18 2024-01-06 [232066.597721] pstate: 20400009 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [232066.598034] pc : nfs4_reclaim_open_state+0x220/0x800 [nfsv4] [232066.598327] lr : nfs4_reclaim_open_state+0x12c/0x800 [nfsv4] [232066.598595] sp : ffff8000f568fc70 [232066.598731] x29: ffff8000f568fc70 x28: 0000000000001000 x27: ffff21003db33000 [232066.599030] x26: ffff800005521ae0 x25: ffff0100f98fa3f0 x24: 0000000000000001 [232066.599319] x23: ffff800009920008 x22: ffff21003db33040 x21: ffff21003db33050 [232066.599628] x20: ffff410172fe9e40 x19: ffff410172fe9e00 x18: 0000000000000000 [232066.599914] x17: 0000000000000000 x16: 0000000000000004 x15: 0000000000000000 [232066.600195] x14: 0000000000000000 x13: ffff800008e685a8 x12: 00000000eac0c6e6 [232066.600498] x11: 0000000000000000 x10: 0000000000000008 x9 : ffff8000054e5828 [232066.600784] x8 : 00000000ffffffbf x7 : 0000000000000001 x6 : 000000000a9eb14a [232066.601062] x5 : 0000000000000000 x4 : ffff70ff8a14a800 x3 : 0000000000000058 [232066.601348] x2 : 0000000000000001 x1 : 54dce46366daa6c6 x0 : 0000000000000000 [232066.601636] Call trace: [232066.601749] nfs4_reclaim_open_state+0x220/0x800 [nfsv4] [232066.601998] nfs4_do_reclaim+0x1b8/0x28c [nfsv4] [232066.602218] nfs4_state_manager+0x928/0x10f0 [nfsv4] [232066.602455] nfs4_run_state_manager+0x78/0x1b0 [nfsv4] [232066.602690] kthread+0x110/0x114 [232066.602830] ret_from_fork+0x10/0x20 [232066.602985] Code: 1400000d f9403f20 f9402e61 91016003 (f9402c00) [232066.603284] SMP: stopping secondary CPUs [232066.606936] Starting crashdump kernel... [232066.607146] Bye! Analysing the vmcore, we know that nfs4_copy_state listed by destination nfs_server->ss_copies was added by the field copies in handle_async_copy(), and we found a waiting copy process with the stack as: PID: 3511963 TASK: ffff710028b47e00 CPU: 0 COMMAND: "cp" #0 [ffff8001116ef740] __switch_to at ffff8000081b92f4 #1 [ffff8001116ef760] __schedule at ffff800008dd0650 #2 [ffff8001116ef7c0] schedule at ffff800008dd0a00 #3 [ffff8001116ef7e0] schedule_timeout at ffff800008dd6aa0 #4 [ffff8001116ef860] __wait_for_common at ffff800008dd166c #5 [ffff8001116ef8e0] wait_for_completion_interruptible at ffff800008dd1898 #6 [ffff8001116ef8f0] handle_async_copy at ffff8000055142f4 [nfsv4] #7 [ffff8001116ef970] _nfs42_proc_copy at ffff8000055147c8 [nfsv4] #8 [ffff8001116efa80] nfs42_proc_copy at ffff800005514cf0 [nfsv4] #9 [ffff8001116efc50] __nfs4_copy_file_range.constprop.0 at ffff8000054ed694 [nfsv4] The NULL-pointer dereference was due to nfs42_complete_copies() listed the nfs_server->ss_copies by the field ss_copies of nfs4_copy_state. So the nfs4_copy_state address ffff0100f98fa3f0 was offset by 0x10 and the data accessed through this pointer was also incorrect. Generally, the ordered list nfs4_state_owner->so_states indicate open(O_RDWR) or open(O_WRITE) states are reclaimed firstly by nfs4_reclaim_open_state(). When destination state reclaim is failed with NFS_STATE_RECOVERY_FAILED and copies are not deleted in nfs_server->ss_copies, the source state may be passed to the nfs42_complete_copies() process earlier, resulting in this crash scene finally. To solve this issue, we add a list_head nfs_server->ss_src_copies for a server-to-server copy specially. Fixes: 0e65a32c8a56 ("NFS: handle source server reboot") Signed-off-by: Yanjun Zhang Reviewed-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/client.c | 1 + fs/nfs/nfs42proc.c | 2 +- fs/nfs/nfs4state.c | 2 +- include/linux/nfs_fs_sb.h | 1 + 4 files changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 1437eb31dd03..6afb66b8855e 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -927,6 +927,7 @@ struct nfs_server *nfs_alloc_server(void) INIT_LIST_HEAD(&server->layouts); INIT_LIST_HEAD(&server->state_owners_lru); INIT_LIST_HEAD(&server->ss_copies); + INIT_LIST_HEAD(&server->ss_src_copies); atomic_set(&server->active, 0); diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index dfeea712014b..47aa721d0d83 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -210,7 +210,7 @@ static int handle_async_copy(struct nfs42_copy_res *res, if (dst_server != src_server) { spin_lock(&src_server->nfs_client->cl_lock); - list_add_tail(©->src_copies, &src_server->ss_copies); + list_add_tail(©->src_copies, &src_server->ss_src_copies); spin_unlock(&src_server->nfs_client->cl_lock); } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index e5cdb700bbe7..807dd6f17e1b 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1596,7 +1596,7 @@ static void nfs42_complete_copies(struct nfs4_state_owner *sp, struct nfs4_state complete(©->completion); } } - list_for_each_entry(copy, &sp->so_server->ss_copies, src_copies) { + list_for_each_entry(copy, &sp->so_server->ss_src_copies, src_copies) { if ((test_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags) && !nfs4_stateid_match_other(&state->stateid, ©->parent_src_state->stateid))) diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 38e60ec742df..cb2cb4d9c013 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -230,6 +230,7 @@ struct nfs_server { struct list_head layouts; struct list_head delegations; struct list_head ss_copies; + struct list_head ss_src_copies; unsigned long mig_gen; unsigned long mig_status; From 21b5af7f0c99b3bf1fd02016e6708b613acbcaf4 Mon Sep 17 00:00:00 2001 From: Ingo van Lil Date: Wed, 2 Oct 2024 18:18:07 +0200 Subject: [PATCH 5/5] net: phy: dp83869: fix memory corruption when enabling fiber [ Upstream commit a842e443ca8184f2dc82ab307b43a8b38defd6a5 ] When configuring the fiber port, the DP83869 PHY driver incorrectly calls linkmode_set_bit() with a bit mask (1 << 10) rather than a bit number (10). This corrupts some other memory location -- in case of arm64 the priv pointer in the same structure. Since the advertising flags are updated from supported at the end of the function the incorrect line isn't needed at all and can be removed. Fixes: a29de52ba2a1 ("net: dp83869: Add ability to advertise Fiber connection") Signed-off-by: Ingo van Lil Reviewed-by: Alexander Sverdlin Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20241002161807.440378-1-inguin@gmx.de Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/phy/dp83869.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c index 65b69ff35e40..01b593e0bb4a 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -610,7 +610,6 @@ static int dp83869_configure_fiber(struct phy_device *phydev, phydev->supported); linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, phydev->supported); - linkmode_set_bit(ADVERTISED_FIBRE, phydev->advertising); if (dp83869->mode == DP83869_RGMII_1000_BASE) { linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT,