From 33d077996a87175b155fe88030e8fec7ca76327e Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Wed, 3 Jun 2020 01:50:11 +0200 Subject: [PATCH 01/35] netfilter: nft_set_rbtree: Don't account for expired elements on insertion While checking the validity of insertion in __nft_rbtree_insert(), we currently ignore conflicting elements and intervals only if they are not active within the next generation. However, if we consider expired elements and intervals as potentially conflicting and overlapping, we'll return error for entries that should be added instead. This is particularly visible with garbage collection intervals that are comparable with the element timeout itself, as reported by Mike Dillinger. Other than the simple issue of denying insertion of valid entries, this might also result in insertion of a single element (opening or closing) out of a given interval. With single entries (that are inserted as intervals of size 1), this leads in turn to the creation of new intervals. For example: # nft add element t s { 192.0.2.1 } # nft list ruleset [...] elements = { 192.0.2.1-255.255.255.255 } Always ignore expired elements active in the next generation, while checking for conflicts. It might be more convenient to introduce a new macro that covers both inactive and expired items, as this type of check also appears quite frequently in other set back-ends. This is however beyond the scope of this fix and can be deferred to a separate patch. Other than the overlap detection cases introduced by commit 7c84d41416d8 ("netfilter: nft_set_rbtree: Detect partial overlaps on insertion"), we also have to cover the original conflict check dealing with conflicts between two intervals of size 1, which was introduced before support for timeout was introduced. This won't return an error to the user as -EEXIST is masked by nft if NLM_F_EXCL is not given, but would result in a silent failure adding the entry. Reported-by: Mike Dillinger Cc: # 5.6.x Fixes: 8d8540c4f5e0 ("netfilter: nft_set_rbtree: add timeout support") Fixes: 7c84d41416d8 ("netfilter: nft_set_rbtree: Detect partial overlaps on insertion") Signed-off-by: Stefano Brivio Acked-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_set_rbtree.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 62f416bc0579..b6aad3fc46c3 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -271,12 +271,14 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, if (nft_rbtree_interval_start(new)) { if (nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, genmask)) + nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) overlap = false; } else { overlap = nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, - genmask); + genmask) && + !nft_set_elem_expired(&rbe->ext); } } else if (d > 0) { p = &parent->rb_right; @@ -284,9 +286,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, if (nft_rbtree_interval_end(new)) { overlap = nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, - genmask); + genmask) && + !nft_set_elem_expired(&rbe->ext); } else if (nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, genmask)) { + nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) { overlap = true; } } else { @@ -294,15 +298,18 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, nft_rbtree_interval_start(new)) { p = &parent->rb_left; - if (nft_set_elem_active(&rbe->ext, genmask)) + if (nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) overlap = false; } else if (nft_rbtree_interval_start(rbe) && nft_rbtree_interval_end(new)) { p = &parent->rb_right; - if (nft_set_elem_active(&rbe->ext, genmask)) + if (nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) overlap = false; - } else if (nft_set_elem_active(&rbe->ext, genmask)) { + } else if (nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) { *ext = &rbe->ext; return -EEXIST; } else { From c3829285b2e6a0d5461078d7f6cbb2c2b4bf8c4e Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Mon, 8 Jun 2020 10:50:29 +0200 Subject: [PATCH 02/35] netfilter: nft_set_pipapo: Disable preemption before getting per-CPU pointer The lkp kernel test robot reports, with CONFIG_DEBUG_PREEMPT enabled: [ 165.316525] BUG: using smp_processor_id() in preemptible [00000000] code: nft/6247 [ 165.319547] caller is nft_pipapo_insert+0x464/0x610 [nf_tables] [ 165.321846] CPU: 1 PID: 6247 Comm: nft Not tainted 5.6.0-rc5-01595-ge32a4dc6512ce3 #1 [ 165.332128] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 [ 165.334892] Call Trace: [ 165.336435] dump_stack+0x8f/0xcb [ 165.338128] debug_smp_processor_id+0xb2/0xc0 [ 165.340117] nft_pipapo_insert+0x464/0x610 [nf_tables] [ 165.342290] ? nft_trans_alloc_gfp+0x1c/0x60 [nf_tables] [ 165.344420] ? rcu_read_lock_sched_held+0x52/0x80 [ 165.346460] ? nft_trans_alloc_gfp+0x1c/0x60 [nf_tables] [ 165.348543] ? __mmu_interval_notifier_insert+0xa0/0xf0 [ 165.350629] nft_add_set_elem+0x5ff/0xa90 [nf_tables] [ 165.352699] ? __lock_acquire+0x241/0x1400 [ 165.354573] ? __lock_acquire+0x241/0x1400 [ 165.356399] ? reacquire_held_locks+0x12f/0x200 [ 165.358384] ? nf_tables_valid_genid+0x1f/0x40 [nf_tables] [ 165.360502] ? nla_strcmp+0x10/0x50 [ 165.362199] ? nft_table_lookup+0x4f/0xa0 [nf_tables] [ 165.364217] ? nla_strcmp+0x10/0x50 [ 165.365891] ? nf_tables_newsetelem+0xd5/0x150 [nf_tables] [ 165.367997] nf_tables_newsetelem+0xd5/0x150 [nf_tables] [ 165.370083] nfnetlink_rcv_batch+0x4fd/0x790 [nfnetlink] [ 165.372205] ? __lock_acquire+0x241/0x1400 [ 165.374058] ? __nla_validate_parse+0x57/0x8a0 [ 165.375989] ? cap_inode_getsecurity+0x230/0x230 [ 165.377954] ? security_capable+0x38/0x50 [ 165.379795] nfnetlink_rcv+0x11d/0x140 [nfnetlink] [ 165.381779] netlink_unicast+0x1b2/0x280 [ 165.383612] netlink_sendmsg+0x351/0x470 [ 165.385439] sock_sendmsg+0x5b/0x60 [ 165.387133] ____sys_sendmsg+0x200/0x280 [ 165.388871] ? copy_msghdr_from_user+0xd9/0x160 [ 165.390805] ___sys_sendmsg+0x88/0xd0 [ 165.392524] ? __might_fault+0x3e/0x90 [ 165.394273] ? sock_getsockopt+0x3d5/0xbb0 [ 165.396021] ? __handle_mm_fault+0x545/0x6a0 [ 165.397822] ? find_held_lock+0x2d/0x90 [ 165.399593] ? __sys_sendmsg+0x5e/0xa0 [ 165.401338] __sys_sendmsg+0x5e/0xa0 [ 165.402979] do_syscall_64+0x60/0x280 [ 165.404680] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 165.406621] RIP: 0033:0x7ff1fa46e783 [ 165.408299] Code: c7 c0 ff ff ff ff eb bb 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 64 8b 04 25 18 00 00 00 85 c0 75 14 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 55 c3 0f 1f 40 00 48 83 ec 28 89 54 24 1c 48 [ 165.414163] RSP: 002b:00007ffedf59ea78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 165.416804] RAX: ffffffffffffffda RBX: 00007ffedf59fc60 RCX: 00007ff1fa46e783 [ 165.419419] RDX: 0000000000000000 RSI: 00007ffedf59fb10 RDI: 0000000000000005 [ 165.421886] RBP: 00007ffedf59fc10 R08: 00007ffedf59ea54 R09: 0000000000000001 [ 165.424445] R10: 00007ff1fa630c6c R11: 0000000000000246 R12: 0000000000020000 [ 165.426954] R13: 0000000000000280 R14: 0000000000000005 R15: 00007ffedf59ea90 Disable preemption before accessing the lookup scratch area in nft_pipapo_insert(). Reported-by: kernel test robot Analysed-by: Florian Westphal Cc: # 5.6.x Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Stefano Brivio Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_set_pipapo.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 8b5acc6910fd..8c04388296b0 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1242,7 +1242,9 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); } - if (!*this_cpu_ptr(m->scratch) || bsize_max > m->bsize_max) { + if (!*get_cpu_ptr(m->scratch) || bsize_max > m->bsize_max) { + put_cpu_ptr(m->scratch); + err = pipapo_realloc_scratch(m, bsize_max); if (err) return err; @@ -1250,6 +1252,8 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, this_cpu_write(nft_pipapo_scratch_index, false); m->bsize_max = bsize_max; + } else { + put_cpu_ptr(m->scratch); } *ext2 = &e->ext; From 6c2d2176a85eb2fd65eb7cfe94b3bad0acce99c0 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 10 Jun 2020 19:28:53 +0200 Subject: [PATCH 03/35] netfilter: ctnetlink: memleak in filter initialization error path Release the filter object in case of error. Fixes: cb8aa9a3affb ("netfilter: ctnetlink: add kernel side filtering for dump") Reported-by: syzbot+38b8b548a851a01793c5@syzkaller.appspotmail.com Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_netlink.c | 32 +++++++++++++++++++--------- 1 file changed, 22 insertions(+), 10 deletions(-) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d7bd8b1f27d5..832eabecfbdd 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -939,7 +939,8 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) filter->mark.mask = 0xffffffff; } } else if (cda[CTA_MARK_MASK]) { - return ERR_PTR(-EINVAL); + err = -EINVAL; + goto err_filter; } #endif if (!cda[CTA_FILTER]) @@ -947,15 +948,17 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone); if (err < 0) - return ERR_PTR(err); + goto err_filter; err = ctnetlink_parse_filter(cda[CTA_FILTER], filter); if (err < 0) - return ERR_PTR(err); + goto err_filter; if (filter->orig_flags) { - if (!cda[CTA_TUPLE_ORIG]) - return ERR_PTR(-EINVAL); + if (!cda[CTA_TUPLE_ORIG]) { + err = -EINVAL; + goto err_filter; + } err = ctnetlink_parse_tuple_filter(cda, &filter->orig, CTA_TUPLE_ORIG, @@ -963,23 +966,32 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) &filter->zone, filter->orig_flags); if (err < 0) - return ERR_PTR(err); + goto err_filter; } if (filter->reply_flags) { - if (!cda[CTA_TUPLE_REPLY]) - return ERR_PTR(-EINVAL); + if (!cda[CTA_TUPLE_REPLY]) { + err = -EINVAL; + goto err_filter; + } err = ctnetlink_parse_tuple_filter(cda, &filter->reply, CTA_TUPLE_REPLY, filter->family, &filter->zone, filter->orig_flags); - if (err < 0) - return ERR_PTR(err); + if (err < 0) { + err = -EINVAL; + goto err_filter; + } } return filter; + +err_filter: + kfree(filter); + + return ERR_PTR(err); } static bool ctnetlink_needs_filter(u8 family, const struct nlattr * const *cda) From 3003055f50663095472144994dac0339076031a8 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 10 Jun 2020 19:29:16 +0200 Subject: [PATCH 04/35] netfilter: nf_tables: hook list memleak in flowtable deletion After looking up for the flowtable hooks that need to be removed, release the hook objects in the deletion list. The error path needs to released these hook objects too. Fixes: abadb2f865d7 ("netfilter: nf_tables: delete devices from flowtable") Reported-by: syzbot+eb9d5924c51d6d59e094@syzkaller.appspotmail.com Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 073aa1051d43..7647ecfa0d40 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6550,12 +6550,22 @@ err1: return err; } +static void nft_flowtable_hook_release(struct nft_flowtable_hook *flowtable_hook) +{ + struct nft_hook *this, *next; + + list_for_each_entry_safe(this, next, &flowtable_hook->list, list) { + list_del(&this->list); + kfree(this); + } +} + static int nft_delflowtable_hook(struct nft_ctx *ctx, struct nft_flowtable *flowtable) { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; - struct nft_hook *this, *next, *hook; + struct nft_hook *this, *hook; struct nft_trans *trans; int err; @@ -6564,33 +6574,40 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, if (err < 0) return err; - list_for_each_entry_safe(this, next, &flowtable_hook.list, list) { + list_for_each_entry(this, &flowtable_hook.list, list) { hook = nft_hook_list_find(&flowtable->hook_list, this); if (!hook) { err = -ENOENT; goto err_flowtable_del_hook; } hook->inactive = true; - list_del(&this->list); - kfree(this); } trans = nft_trans_alloc(ctx, NFT_MSG_DELFLOWTABLE, sizeof(struct nft_trans_flowtable)); - if (!trans) - return -ENOMEM; + if (!trans) { + err = -ENOMEM; + goto err_flowtable_del_hook; + } nft_trans_flowtable(trans) = flowtable; nft_trans_flowtable_update(trans) = true; INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); + nft_flowtable_hook_release(&flowtable_hook); list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; err_flowtable_del_hook: - list_for_each_entry(hook, &flowtable_hook.list, list) + list_for_each_entry(this, &flowtable_hook.list, list) { + hook = nft_hook_list_find(&flowtable->hook_list, this); + if (!hook) + break; + hook->inactive = false; + } + nft_flowtable_hook_release(&flowtable_hook); return err; } From 33cf601da7a42b1a78d04746aea47b85ccb5c49b Mon Sep 17 00:00:00 2001 From: Ka-Cheong Poon Date: Mon, 15 Jun 2020 00:40:25 -0700 Subject: [PATCH 05/35] net/rds: NULL pointer de-reference in rds_ib_add_one() The parent field of a struct device may be NULL. The macro ibdev_to_node() should check for that. Signed-off-by: Ka-Cheong Poon Acked-by: Santosh Shilimkar Signed-off-by: David S. Miller --- net/rds/ib.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/net/rds/ib.h b/net/rds/ib.h index 5ae069d39eab..8dfff43cf07f 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -264,7 +264,13 @@ struct rds_ib_device { int *vector_load; }; -#define ibdev_to_node(ibdev) dev_to_node((ibdev)->dev.parent) +static inline int ibdev_to_node(struct ib_device *ibdev) +{ + struct device *parent; + + parent = ibdev->dev.parent; + return parent ? dev_to_node(parent) : NUMA_NO_NODE; +} #define rdsibdev_to_node(rdsibdev) ibdev_to_node(rdsibdev->dev) /* bits for i_ack_flags */ From c06c1f87b66e74c29ecc68020e0312c565deebe0 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Mon, 15 Jun 2020 16:28:03 +0800 Subject: [PATCH 06/35] mptcp: drop MPTCP_PM_MAX_ADDR We have defined MPTCP_PM_ADDR_MAX in pm_netlink.c, so drop this duplicate macro. Fixes: 1b1c7a0ef7f3 ("mptcp: Add path manager interface") Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts Signed-off-by: David S. Miller --- net/mptcp/protocol.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 809687d3f410..70ed698bd206 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -135,8 +135,6 @@ static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field) ((nib & 0xF) << 8) | field); } -#define MPTCP_PM_MAX_ADDR 4 - struct mptcp_addr_info { sa_family_t family; __be16 port; From 35ed87add7def6809cf7815cc495a6537bc3bb01 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 15 Jun 2020 09:29:11 +0100 Subject: [PATCH 07/35] net: axienet: fix spelling mistake in comment "Exteneded" -> "extended" There is a spelling mistake in a comment. Fix it. Signed-off-by: Colin Ian King Acked-by: Michal Simek Signed-off-by: David S. Miller --- drivers/net/ethernet/xilinx/xilinx_axienet.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index fbaf3c987d9c..f34c7903ff52 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -186,7 +186,7 @@ #define XAE_RAF_TXVSTRPMODE_MASK 0x00000180 /* Tx VLAN STRIP mode */ #define XAE_RAF_RXVSTRPMODE_MASK 0x00000600 /* Rx VLAN STRIP mode */ #define XAE_RAF_NEWFNCENBL_MASK 0x00000800 /* New function mode */ -/* Exteneded Multicast Filtering mode */ +/* Extended Multicast Filtering mode */ #define XAE_RAF_EMULTIFLTRENBL_MASK 0x00001000 #define XAE_RAF_STATSRST_MASK 0x00002000 /* Stats. Counter Reset */ #define XAE_RAF_RXBADFRMEN_MASK 0x00004000 /* Recv Bad Frame Enable */ From a386bc5b2155bf1fc76229481ac7e7f2a646d966 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Mon, 15 Jun 2020 16:34:28 +0800 Subject: [PATCH 08/35] mptcp: use list_first_entry_or_null Use list_first_entry_or_null to simplify the code. Signed-off-by: Geliang Tang Signed-off-by: David S. Miller --- net/mptcp/protocol.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 70ed698bd206..db56535dfc29 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -232,10 +232,7 @@ static inline struct mptcp_data_frag *mptcp_rtx_head(const struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - if (list_empty(&msk->rtx_queue)) - return NULL; - - return list_first_entry(&msk->rtx_queue, struct mptcp_data_frag, list); + return list_first_entry_or_null(&msk->rtx_queue, struct mptcp_data_frag, list); } struct mptcp_subflow_request_sock { From 0acb47a3a09381d20fb643aa195cf5840aac3bb4 Mon Sep 17 00:00:00 2001 From: Wang Qing Date: Mon, 15 Jun 2020 17:02:23 +0800 Subject: [PATCH 09/35] qlcnic: Use kobj_to_dev() instead Use kobj_to_dev() instead of container_of() Signed-off-by: Wang Qing Signed-off-by: David S. Miller --- .../net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c | 34 +++++++++---------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c index 8d7b9bb910f2..10037639ac2c 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c @@ -269,7 +269,7 @@ static ssize_t qlcnic_sysfs_read_crb(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); int ret; @@ -286,7 +286,7 @@ static ssize_t qlcnic_sysfs_write_crb(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); int ret; @@ -315,7 +315,7 @@ static ssize_t qlcnic_sysfs_read_mem(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); u64 data; int ret; @@ -337,7 +337,7 @@ static ssize_t qlcnic_sysfs_write_mem(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); u64 data; int ret; @@ -402,7 +402,7 @@ static ssize_t qlcnic_sysfs_write_pm_config(struct file *filp, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_pm_func_cfg *pm_cfg; u32 id, action, pci_func; @@ -452,7 +452,7 @@ static ssize_t qlcnic_sysfs_read_pm_config(struct file *filp, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_pm_func_cfg *pm_cfg; u8 pci_func; @@ -545,7 +545,7 @@ static ssize_t qlcnic_sysfs_write_esw_config(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_esw_func_cfg *esw_cfg; struct qlcnic_npar_info *npar; @@ -629,7 +629,7 @@ static ssize_t qlcnic_sysfs_read_esw_config(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_esw_func_cfg *esw_cfg; u8 pci_func; @@ -681,7 +681,7 @@ static ssize_t qlcnic_sysfs_write_npar_config(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_info nic_info; struct qlcnic_npar_func_cfg *np_cfg; @@ -728,7 +728,7 @@ static ssize_t qlcnic_sysfs_read_npar_config(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_npar_func_cfg *np_cfg; struct qlcnic_info nic_info; @@ -775,7 +775,7 @@ static ssize_t qlcnic_sysfs_get_port_stats(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_esw_statistics port_stats; int ret; @@ -810,7 +810,7 @@ static ssize_t qlcnic_sysfs_get_esw_stats(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_esw_statistics esw_stats; int ret; @@ -845,7 +845,7 @@ static ssize_t qlcnic_sysfs_clear_esw_stats(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); int ret; @@ -875,7 +875,7 @@ static ssize_t qlcnic_sysfs_clear_port_stats(struct file *file, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); int ret; @@ -904,7 +904,7 @@ static ssize_t qlcnic_sysfs_read_pci_config(struct file *file, char *buf, loff_t offset, size_t size) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); struct qlcnic_pci_func_cfg *pci_cfg; struct qlcnic_pci_info *pci_info; @@ -946,7 +946,7 @@ static ssize_t qlcnic_83xx_sysfs_flash_read_handler(struct file *filp, { unsigned char *p_read_buf; int ret, count; - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); if (!size) @@ -1124,7 +1124,7 @@ static ssize_t qlcnic_83xx_sysfs_flash_write_handler(struct file *filp, int ret; static int flash_mode; unsigned long data; - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); ret = kstrtoul(buf, 16, &data); From 939a5bf7c9b7a1ad9c5d3481c93766a522773531 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Mon, 15 Jun 2020 14:18:54 +0100 Subject: [PATCH 10/35] net: macb: Only disable NAPI on the actual error path A recent change added a disable to NAPI into macb_open, this was intended to only happen on the error path but accidentally applies to all paths. This causes NAPI to be disabled on the success path, which leads to the network to no longer functioning. Fixes: 014406babc1f ("net: cadence: macb: disable NAPI on error") Signed-off-by: Charles Keepax Tested-by: Corentin Labbe Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb_main.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 5b9d7c60eebc..67933079aeea 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -2565,15 +2565,14 @@ static int macb_open(struct net_device *dev) if (bp->ptp_info) bp->ptp_info->ptp_init(dev); + return 0; + napi_exit: for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) napi_disable(&queue->napi); pm_exit: - if (err) { - pm_runtime_put_sync(&bp->pdev->dev); - return err; - } - return 0; + pm_runtime_put_sync(&bp->pdev->dev); + return err; } static int macb_close(struct net_device *dev) From dff515a3e71dc8ab3b9dcc2e23a9b5fca88b3c18 Mon Sep 17 00:00:00 2001 From: Thomas Falcon Date: Mon, 15 Jun 2020 10:29:23 -0500 Subject: [PATCH 11/35] ibmvnic: Harden device login requests The VNIC driver's "login" command sequence is the final step in the driver's initialization process with device firmware, confirming the available device queue resources to be utilized by the driver. Under high system load, firmware may not respond to the request in a timely manner or may abort the request. In such cases, the driver should reattempt the login command sequence. In case of a device error, the number of retries is bounded. Signed-off-by: Thomas Falcon Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 1b4d04e4474b..2baf7b3ff4cb 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -842,12 +842,13 @@ static int ibmvnic_login(struct net_device *netdev) struct ibmvnic_adapter *adapter = netdev_priv(netdev); unsigned long timeout = msecs_to_jiffies(30000); int retry_count = 0; + int retries = 10; bool retry; int rc; do { retry = false; - if (retry_count > IBMVNIC_MAX_QUEUES) { + if (retry_count > retries) { netdev_warn(netdev, "Login attempts exceeded\n"); return -1; } @@ -862,11 +863,23 @@ static int ibmvnic_login(struct net_device *netdev) if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { - netdev_warn(netdev, "Login timed out\n"); - return -1; + netdev_warn(netdev, "Login timed out, retrying...\n"); + retry = true; + adapter->init_done_rc = 0; + retry_count++; + continue; } - if (adapter->init_done_rc == PARTIALSUCCESS) { + if (adapter->init_done_rc == ABORTED) { + netdev_warn(netdev, "Login aborted, retrying...\n"); + retry = true; + adapter->init_done_rc = 0; + retry_count++; + /* FW or device may be busy, so + * wait a bit before retrying login + */ + msleep(500); + } else if (adapter->init_done_rc == PARTIALSUCCESS) { retry_count++; release_sub_crqs(adapter, 1); From e89df5c4322c1bf495f62d74745895b5fd2a4393 Mon Sep 17 00:00:00 2001 From: Zekun Shen Date: Mon, 15 Jun 2020 11:50:29 -0400 Subject: [PATCH 12/35] net: alx: fix race condition in alx_remove There is a race condition exist during termination. The path is alx_stop and then alx_remove. An alx_schedule_link_check could be called before alx_stop by interrupt handler and invoke alx_link_check later. Alx_stop frees the napis, and alx_remove cancels any pending works. If any of the work is scheduled before termination and invoked before alx_remove, a null-ptr-deref occurs because both expect alx->napis[i]. This patch fix the race condition by moving cancel_work_sync functions before alx_free_napis inside alx_stop. Because interrupt handler can call alx_schedule_link_check again, alx_free_irq is moved before cancel_work_sync calls too. Signed-off-by: Zekun Shen Signed-off-by: David S. Miller --- drivers/net/ethernet/atheros/alx/main.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index b9b4edb913c1..9b7f1af5f574 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1249,8 +1249,12 @@ out_disable_adv_intr: static void __alx_stop(struct alx_priv *alx) { - alx_halt(alx); alx_free_irq(alx); + + cancel_work_sync(&alx->link_check_wk); + cancel_work_sync(&alx->reset_wk); + + alx_halt(alx); alx_free_rings(alx); alx_free_napis(alx); } @@ -1855,9 +1859,6 @@ static void alx_remove(struct pci_dev *pdev) struct alx_priv *alx = pci_get_drvdata(pdev); struct alx_hw *hw = &alx->hw; - cancel_work_sync(&alx->link_check_wk); - cancel_work_sync(&alx->reset_wk); - /* restore permanent mac address */ alx_set_macaddr(hw, hw->perm_addr); From 6e701c299469dd2b8a64056051c6834809152424 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 15 Jun 2020 19:42:44 +0300 Subject: [PATCH 13/35] MAINTAINERS: merge entries for felix and ocelot drivers The ocelot switchdev driver also provides a set of library functions for the felix DSA driver, which in practice means that most of the patches will be of interest to both groups of driver maintainers. So, as also suggested in the discussion here, let's merge the 2 entries into a single larger one: https://www.spinics.net/lists/netdev/msg657412.html Note that the entry has been renamed into "OCELOT SWITCH" since neither Vitesse nor Microsemi exist any longer as company names, instead they are now named Microchip (which again might be subject to change in the future), so use the device family name instead. Suggested-by: Alexandre Belloni Signed-off-by: Vladimir Oltean Acked-by: Horatiu Vultur Signed-off-by: David S. Miller --- MAINTAINERS | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 68f21d46614c..b4bd00f64f19 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11369,14 +11369,6 @@ L: dmaengine@vger.kernel.org S: Supported F: drivers/dma/at_xdmac.c -MICROSEMI ETHERNET SWITCH DRIVER -M: Alexandre Belloni -M: Microchip Linux Driver Support -L: netdev@vger.kernel.org -S: Supported -F: drivers/net/ethernet/mscc/ -F: include/soc/mscc/ocelot* - MICROSEMI MIPS SOCS M: Alexandre Belloni M: Microchip Linux Driver Support @@ -12335,6 +12327,18 @@ M: Peter Zijlstra S: Supported F: tools/objtool/ +OCELOT ETHERNET SWITCH DRIVER +M: Microchip Linux Driver Support +M: Vladimir Oltean +M: Claudiu Manoil +M: Alexandre Belloni +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/dsa/ocelot/* +F: drivers/net/ethernet/mscc/ +F: include/soc/mscc/ocelot* +F: net/dsa/tag_ocelot.c + OCXL (Open Coherent Accelerator Processor Interface OpenCAPI) DRIVER M: Frederic Barrat M: Andrew Donnellan @@ -18254,14 +18258,6 @@ S: Maintained F: drivers/input/serio/userio.c F: include/uapi/linux/userio.h -VITESSE FELIX ETHERNET SWITCH DRIVER -M: Vladimir Oltean -M: Claudiu Manoil -L: netdev@vger.kernel.org -S: Maintained -F: drivers/net/dsa/ocelot/* -F: net/dsa/tag_ocelot.c - VIVID VIRTUAL VIDEO DRIVER M: Hans Verkuil L: linux-media@vger.kernel.org From 2084ccf6259cc95e0575f0fafc93595d0219a9f6 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 14 Jun 2020 19:57:07 -0400 Subject: [PATCH 14/35] bnxt_en: Simplify bnxt_resume(). The separate steps we do in bnxt_resume() can be done more simply by calling bnxt_hwrm_func_qcaps(). This change will add an extra __bnxt_hwrm_func_qcaps() call which is needed anyway on older firmware. Fixes: f9b69d7f6279 ("bnxt_en: Fix suspend/resume path on 57500 chips") Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c62589c266b2..1dc38d9c5252 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -12133,19 +12133,9 @@ static int bnxt_resume(struct device *device) goto resume_exit; } - if (bnxt_hwrm_queue_qportcfg(bp)) { - rc = -ENODEV; + rc = bnxt_hwrm_func_qcaps(bp); + if (rc) goto resume_exit; - } - - if (bp->hwrm_spec_code >= 0x10803) { - if (bnxt_alloc_ctx_mem(bp)) { - rc = -ENODEV; - goto resume_exit; - } - } - if (BNXT_NEW_RM(bp)) - bnxt_hwrm_func_resc_qcaps(bp, false); if (bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, false)) { rc = -ENODEV; From 59ae210173ff86256fa0cdba4ea4d608c61e123d Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 14 Jun 2020 19:57:08 -0400 Subject: [PATCH 15/35] bnxt_en: Re-enable SRIOV during resume. If VFs are enabled, we need to re-configure them during resume because firmware has been reset while resuming. Otherwise, the VFs won't work after resume. Fixes: c16d4ee0e397 ("bnxt_en: Refactor logic to re-enable SRIOV after firmware reset detected.") Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 1dc38d9c5252..0d97f471f520 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -12151,6 +12151,8 @@ static int bnxt_resume(struct device *device) resume_exit: bnxt_ulp_start(bp, rc); + if (!rc) + bnxt_reenable_sriov(bp); rtnl_unlock(); return rc; } From 6e2f83884c099de0e87b15a820736e522755d074 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 14 Jun 2020 19:57:09 -0400 Subject: [PATCH 16/35] bnxt_en: Fix AER reset logic on 57500 chips. AER reset should follow the same steps as suspend/resume. We need to free context memory during AER reset and allocate new context memory during recovery by calling bnxt_hwrm_func_qcaps(). We also need to call bnxt_reenable_sriov() to restore the VFs. Fixes: bae361c54fb6 ("bnxt_en: Improve AER slot reset.") Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 0d97f471f520..47b45ea696f8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -12196,6 +12196,9 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, bnxt_close(netdev); pci_disable_device(pdev); + bnxt_free_ctx_mem(bp); + kfree(bp->ctx); + bp->ctx = NULL; rtnl_unlock(); /* Request a slot slot reset. */ @@ -12229,12 +12232,16 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) pci_set_master(pdev); err = bnxt_hwrm_func_reset(bp); - if (!err && netif_running(netdev)) - err = bnxt_open(netdev); - - if (!err) - result = PCI_ERS_RESULT_RECOVERED; + if (!err) { + err = bnxt_hwrm_func_qcaps(bp); + if (!err && netif_running(netdev)) + err = bnxt_open(netdev); + } bnxt_ulp_start(bp, err); + if (!err) { + bnxt_reenable_sriov(bp); + result = PCI_ERS_RESULT_RECOVERED; + } } if (result != PCI_ERS_RESULT_RECOVERED) { From e000940473d1423a42ef9c823fb23ccffe3f07ea Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Sun, 14 Jun 2020 19:57:10 -0400 Subject: [PATCH 17/35] bnxt_en: Return from timer if interface is not in open state. This will avoid many uneccessary error logs when driver or firmware is in reset. Fixes: 230d1f0de754 ("bnxt_en: Handle firmware reset.") Signed-off-by: Vasundhara Volam Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 47b45ea696f8..b93e05f91d77 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -10037,7 +10037,7 @@ static void bnxt_timer(struct timer_list *t) struct bnxt *bp = from_timer(bp, t, timer); struct net_device *dev = bp->dev; - if (!netif_running(dev)) + if (!netif_running(dev) || !test_bit(BNXT_STATE_OPEN, &bp->state)) return; if (atomic_read(&bp->intr_sem) != 0) From ea2fce88d2fd678ed9d45354ff49b73f1d5615dd Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Thu, 11 Jun 2020 15:57:50 +0800 Subject: [PATCH 18/35] mld: fix memory leak in ipv6_mc_destroy_dev() Commit a84d01647989 ("mld: fix memory leak in mld_del_delrec()") fixed the memory leak of MLD, but missing the ipv6_mc_destroy_dev() path, in which mca_sources are leaked after ma_put(). Using ip6_mc_clear_src() to take care of the missing free. BUG: memory leak unreferenced object 0xffff8881113d3180 (size 64): comm "syz-executor071", pid 389, jiffies 4294887985 (age 17.943s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 ff 02 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 01 00 00 00 00 00 00 00 00 ................ backtrace: [<000000002cbc483c>] kmalloc include/linux/slab.h:555 [inline] [<000000002cbc483c>] kzalloc include/linux/slab.h:669 [inline] [<000000002cbc483c>] ip6_mc_add1_src net/ipv6/mcast.c:2237 [inline] [<000000002cbc483c>] ip6_mc_add_src+0x7f5/0xbb0 net/ipv6/mcast.c:2357 [<0000000058b8b1ff>] ip6_mc_source+0xe0c/0x1530 net/ipv6/mcast.c:449 [<000000000bfc4fb5>] do_ipv6_setsockopt.isra.12+0x1b2c/0x3b30 net/ipv6/ipv6_sockglue.c:754 [<00000000e4e7a722>] ipv6_setsockopt+0xda/0x150 net/ipv6/ipv6_sockglue.c:950 [<0000000029260d9a>] rawv6_setsockopt+0x45/0x100 net/ipv6/raw.c:1081 [<000000005c1b46f9>] __sys_setsockopt+0x131/0x210 net/socket.c:2132 [<000000008491f7db>] __do_sys_setsockopt net/socket.c:2148 [inline] [<000000008491f7db>] __se_sys_setsockopt net/socket.c:2145 [inline] [<000000008491f7db>] __x64_sys_setsockopt+0xba/0x150 net/socket.c:2145 [<00000000c7bc11c5>] do_syscall_64+0xa1/0x530 arch/x86/entry/common.c:295 [<000000005fb7a3f3>] entry_SYSCALL_64_after_hwframe+0x49/0xb3 Fixes: 1666d49e1d41 ("mld: do not remove mld souce list info when set link down") Reported-by: Hulk Robot Signed-off-by: Wang Hai Acked-by: Hangbin Liu Signed-off-by: David S. Miller --- net/ipv6/mcast.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 7e12d2114158..8cd2782a31e4 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2615,6 +2615,7 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev) idev->mc_list = i->next; write_unlock_bh(&idev->lock); + ip6_mc_clear_src(i); ma_put(i); write_lock_bh(&idev->lock); } From adaff6d906d74dfe34d44fd18d5a7596d293df44 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 11 Jun 2020 16:01:39 +0200 Subject: [PATCH 19/35] net: ethernet: mtk-star-emac: simplify interrupt handling During development we tried to make the interrupt handling as fine-grained as possible with TX and RX interrupts being disabled/enabled independently and the counter registers reset from workqueue context. Unfortunately after thorough testing of current mainline, we noticed the driver has become unstable under heavy load. While this is hard to reproduce, it's quite consistent in the driver's current form. This patch proposes to go back to the previous approach of doing all processing in napi context with all interrupts masked in order to make the driver usable in mainline linux. This doesn't impact the performance on pumpkin boards at all and it's in line with what many ethernet drivers do in mainline linux anyway. At the same time we're adding a FIXME comment about the need to improve the interrupt handling. Fixes: 8c7bd5a454ff ("net: ethernet: mtk-star-emac: new driver") Signed-off-by: Bartosz Golaszewski Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_star_emac.c | 118 +++++------------- 1 file changed, 29 insertions(+), 89 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c index f1ace4fec19f..3e765bdcf9e1 100644 --- a/drivers/net/ethernet/mediatek/mtk_star_emac.c +++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c @@ -24,7 +24,6 @@ #include #include #include -#include #define MTK_STAR_DRVNAME "mtk_star_emac" @@ -262,7 +261,6 @@ struct mtk_star_priv { spinlock_t lock; struct rtnl_link_stats64 stats; - struct work_struct stats_work; }; static struct device *mtk_star_get_dev(struct mtk_star_priv *priv) @@ -432,42 +430,6 @@ static void mtk_star_intr_disable(struct mtk_star_priv *priv) regmap_write(priv->regs, MTK_STAR_REG_INT_MASK, ~0); } -static void mtk_star_intr_enable_tx(struct mtk_star_priv *priv) -{ - regmap_clear_bits(priv->regs, MTK_STAR_REG_INT_MASK, - MTK_STAR_BIT_INT_STS_TNTC); -} - -static void mtk_star_intr_enable_rx(struct mtk_star_priv *priv) -{ - regmap_clear_bits(priv->regs, MTK_STAR_REG_INT_MASK, - MTK_STAR_BIT_INT_STS_FNRC); -} - -static void mtk_star_intr_enable_stats(struct mtk_star_priv *priv) -{ - regmap_clear_bits(priv->regs, MTK_STAR_REG_INT_MASK, - MTK_STAR_REG_INT_STS_MIB_CNT_TH); -} - -static void mtk_star_intr_disable_tx(struct mtk_star_priv *priv) -{ - regmap_set_bits(priv->regs, MTK_STAR_REG_INT_MASK, - MTK_STAR_BIT_INT_STS_TNTC); -} - -static void mtk_star_intr_disable_rx(struct mtk_star_priv *priv) -{ - regmap_set_bits(priv->regs, MTK_STAR_REG_INT_MASK, - MTK_STAR_BIT_INT_STS_FNRC); -} - -static void mtk_star_intr_disable_stats(struct mtk_star_priv *priv) -{ - regmap_set_bits(priv->regs, MTK_STAR_REG_INT_MASK, - MTK_STAR_REG_INT_STS_MIB_CNT_TH); -} - static unsigned int mtk_star_intr_read(struct mtk_star_priv *priv) { unsigned int val; @@ -663,20 +625,6 @@ static void mtk_star_update_stats(struct mtk_star_priv *priv) stats->rx_errors += stats->rx_fifo_errors; } -/* This runs in process context and parallel TX and RX paths executing in - * napi context may result in losing some stats data but this should happen - * seldom enough to be acceptable. - */ -static void mtk_star_update_stats_work(struct work_struct *work) -{ - struct mtk_star_priv *priv = container_of(work, struct mtk_star_priv, - stats_work); - - mtk_star_update_stats(priv); - mtk_star_reset_counters(priv); - mtk_star_intr_enable_stats(priv); -} - static struct sk_buff *mtk_star_alloc_skb(struct net_device *ndev) { uintptr_t tail, offset; @@ -767,42 +715,25 @@ static void mtk_star_free_tx_skbs(struct mtk_star_priv *priv) mtk_star_ring_free_skbs(priv, ring, mtk_star_dma_unmap_tx); } -/* All processing for TX and RX happens in the napi poll callback. */ +/* All processing for TX and RX happens in the napi poll callback. + * + * FIXME: The interrupt handling should be more fine-grained with each + * interrupt enabled/disabled independently when needed. Unfortunatly this + * turned out to impact the driver's stability and until we have something + * working properly, we're disabling all interrupts during TX & RX processing + * or when resetting the counter registers. + */ static irqreturn_t mtk_star_handle_irq(int irq, void *data) { struct mtk_star_priv *priv; struct net_device *ndev; - bool need_napi = false; - unsigned int status; ndev = data; priv = netdev_priv(ndev); if (netif_running(ndev)) { - status = mtk_star_intr_read(priv); - - if (status & MTK_STAR_BIT_INT_STS_TNTC) { - mtk_star_intr_disable_tx(priv); - need_napi = true; - } - - if (status & MTK_STAR_BIT_INT_STS_FNRC) { - mtk_star_intr_disable_rx(priv); - need_napi = true; - } - - if (need_napi) - napi_schedule(&priv->napi); - - /* One of the counters reached 0x8000000 - update stats and - * reset all counters. - */ - if (unlikely(status & MTK_STAR_REG_INT_STS_MIB_CNT_TH)) { - mtk_star_intr_disable_stats(priv); - schedule_work(&priv->stats_work); - } - - mtk_star_intr_ack_all(priv); + mtk_star_intr_disable(priv); + napi_schedule(&priv->napi); } return IRQ_HANDLED; @@ -1169,8 +1100,6 @@ static void mtk_star_tx_complete_all(struct mtk_star_priv *priv) if (wake && netif_queue_stopped(ndev)) netif_wake_queue(ndev); - mtk_star_intr_enable_tx(priv); - spin_unlock(&priv->lock); } @@ -1332,20 +1261,32 @@ static int mtk_star_process_rx(struct mtk_star_priv *priv, int budget) static int mtk_star_poll(struct napi_struct *napi, int budget) { struct mtk_star_priv *priv; + unsigned int status; int received = 0; priv = container_of(napi, struct mtk_star_priv, napi); - /* Clean-up all TX descriptors. */ - mtk_star_tx_complete_all(priv); - /* Receive up to $budget packets. */ - received = mtk_star_process_rx(priv, budget); + status = mtk_star_intr_read(priv); + mtk_star_intr_ack_all(priv); - if (received < budget) { - napi_complete_done(napi, received); - mtk_star_intr_enable_rx(priv); + if (status & MTK_STAR_BIT_INT_STS_TNTC) + /* Clean-up all TX descriptors. */ + mtk_star_tx_complete_all(priv); + + if (status & MTK_STAR_BIT_INT_STS_FNRC) + /* Receive up to $budget packets. */ + received = mtk_star_process_rx(priv, budget); + + if (unlikely(status & MTK_STAR_REG_INT_STS_MIB_CNT_TH)) { + mtk_star_update_stats(priv); + mtk_star_reset_counters(priv); } + if (received < budget) + napi_complete_done(napi, received); + + mtk_star_intr_enable(priv); + return received; } @@ -1532,7 +1473,6 @@ static int mtk_star_probe(struct platform_device *pdev) ndev->max_mtu = MTK_STAR_MAX_FRAME_SIZE; spin_lock_init(&priv->lock); - INIT_WORK(&priv->stats_work, mtk_star_update_stats_work); base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) From a6379f0ad6375a707e915518ecd5c2270afcd395 Mon Sep 17 00:00:00 2001 From: Aditya Pakki Date: Fri, 12 Jun 2020 15:01:54 -0500 Subject: [PATCH 20/35] test_objagg: Fix potential memory leak in error handling In case of failure of check_expect_hints_stats(), the resources allocated by objagg_hints_get should be freed. The patch fixes this issue. Signed-off-by: Aditya Pakki Signed-off-by: David S. Miller --- lib/test_objagg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/test_objagg.c b/lib/test_objagg.c index 72c1abfa154d..da137939a410 100644 --- a/lib/test_objagg.c +++ b/lib/test_objagg.c @@ -979,10 +979,10 @@ err_check_expect_stats2: err_world2_obj_get: for (i--; i >= 0; i--) world_obj_put(&world2, objagg, hints_case->key_ids[i]); - objagg_hints_put(hints); - objagg_destroy(objagg2); i = hints_case->key_ids_count; + objagg_destroy(objagg2); err_check_expect_hints_stats: + objagg_hints_put(hints); err_hints_get: err_check_expect_stats: err_world_obj_get: From 58d0c864e1a759a15c9df78f50ea5a5c32b3989e Mon Sep 17 00:00:00 2001 From: Aditya Pakki Date: Fri, 12 Jun 2020 15:27:55 -0500 Subject: [PATCH 21/35] rocker: fix incorrect error handling in dma_rings_init In rocker_dma_rings_init, the goto blocks in case of errors caused by the functions rocker_dma_cmd_ring_waits_alloc() and rocker_dma_ring_create() are incorrect. The patch fixes the order consistent with cleanup in rocker_dma_rings_fini(). Signed-off-by: Aditya Pakki Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 7585cd2270ba..fc99e7118e49 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -647,10 +647,10 @@ static int rocker_dma_rings_init(struct rocker *rocker) err_dma_event_ring_bufs_alloc: rocker_dma_ring_destroy(rocker, &rocker->event_ring); err_dma_event_ring_create: + rocker_dma_cmd_ring_waits_free(rocker); +err_dma_cmd_ring_waits_alloc: rocker_dma_ring_bufs_free(rocker, &rocker->cmd_ring, PCI_DMA_BIDIRECTIONAL); -err_dma_cmd_ring_waits_alloc: - rocker_dma_cmd_ring_waits_free(rocker); err_dma_cmd_ring_bufs_alloc: rocker_dma_ring_destroy(rocker, &rocker->cmd_ring); return err; From 534a8bf0ccdd7b3f7a4eb22b5992d3aa1da08f93 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sat, 13 Jun 2020 23:59:30 +0300 Subject: [PATCH 22/35] MAINTAINERS: switch to my private email for Renesas Ethernet drivers I no longer work for Cogent Embedded (but my old email still works :-)), and still would like to continue looking after the Renesas Ethernet drivers and bindings. Let's switch to my private email. Signed-off-by: Sergei Shtylyov Acked-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index b4bd00f64f19..301330e02bca 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14538,7 +14538,7 @@ F: Documentation/devicetree/bindings/i2c/renesas,iic-emev2.txt F: drivers/i2c/busses/i2c-emev2.c RENESAS ETHERNET DRIVERS -R: Sergei Shtylyov +R: Sergei Shtylyov L: netdev@vger.kernel.org L: linux-renesas-soc@vger.kernel.org F: Documentation/devicetree/bindings/net/renesas,*.txt From cc970925feb9a38c2f0d34305518e00a3084ce85 Mon Sep 17 00:00:00 2001 From: Sven Auhagen Date: Sun, 14 Jun 2020 09:19:17 +0200 Subject: [PATCH 23/35] mvpp2: ethtool rxtx stats fix The ethtool rx and tx queue statistics are reporting wrong values. Fix reading out the correct ones. Signed-off-by: Sven Auhagen Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 2b5dad2ec650..5d4ec95be869 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -1544,7 +1544,7 @@ static void mvpp2_read_stats(struct mvpp2_port *port) for (q = 0; q < port->ntxqs; q++) for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_txq_regs); i++) *pstats++ += mvpp2_read_index(port->priv, - MVPP22_CTRS_TX_CTR(port->id, i), + MVPP22_CTRS_TX_CTR(port->id, q), mvpp2_ethtool_txq_regs[i].offset); /* Rxqs are numbered from 0 from the user standpoint, but not from the @@ -1553,7 +1553,7 @@ static void mvpp2_read_stats(struct mvpp2_port *port) for (q = 0; q < port->nrxqs; q++) for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_rxq_regs); i++) *pstats++ += mvpp2_read_index(port->priv, - port->first_rxq + i, + port->first_rxq + q, mvpp2_ethtool_rxq_regs[i].offset); } From c92cbaea3cc0a80807e386922f801eb6d3652c81 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 14 Jun 2020 23:54:09 +0300 Subject: [PATCH 24/35] net: dsa: sja1105: fix PTP timestamping with large tc-taprio cycles It isn't actually described clearly at all in UM10944.pdf, but on TX of a management frame (such as PTP), this needs to happen: - The destination MAC address (i.e. 01-80-c2-00-00-0e), along with the desired destination port, need to be installed in one of the 4 management slots of the switch, over SPI. - The host can poll over SPI for that management slot's ENFPORT field. That gets unset when the switch has matched the slot to the frame. And therein lies the problem. ENFPORT does not mean that the packet has been transmitted. Just that it has been received over the CPU port, and that the mgmt slot is yet again available. This is relevant because of what we are doing in sja1105_ptp_txtstamp_skb, which is called right after sja1105_mgmt_xmit. We are in a hard real-time deadline, since the hardware only gives us 24 bits of TX timestamp, so we need to read the full PTP clock to reconstruct it. Because we're in a hurry (in an attempt to make sure that we have a full 64-bit PTP time which is as close as possible to the actual transmission time of the frame, to avoid 24-bit wraparounds), first we read the PTP clock, then we poll for the TX timestamp to become available. But of course, we don't know for sure that the frame has been transmitted when we read the full PTP clock. We had assumed that ENFPORT means it has, but the assumption is incorrect. And while in most real-life scenarios this has never been caught due to software delays, nowhere is this fact more obvious than with a tc-taprio offload, where PTP traffic gets a small timeslot very rarely (example: 1 packet per 10 ms). In that case, we will be reading the PTP clock for timestamp reconstruction too early (before the packet has been transmitted), and this renders the reconstruction procedure incorrect (see the assumptions described in the comments found on function sja1105_tstamp_reconstruct). So the PTP TX timestamps will be off by 1<<24 clock ticks, or 135 ms (1 tick is 8 ns). So fix this case of premature optimization by simply reordering the sja1105_ptpegr_ts_poll and the sja1105_ptpclkval_read function calls. It turns out that in practice, the 135 ms hard deadline for PTP timestamp wraparound is not so hard, since even the most bandwidth-intensive PTP profiles, such as 802.1AS-2011, have a sync frame interval of 125 ms. So if we couldn't deliver a timestamp in 135 ms (which we can), we're toast and have much bigger problems anyway. Fixes: 47ed985e97f5 ("net: dsa: sja1105: Add logic for TX timestamping") Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_ptp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index bc0e47c1dbb9..177134596458 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -891,16 +891,16 @@ void sja1105_ptp_txtstamp_skb(struct dsa_switch *ds, int port, mutex_lock(&ptp_data->lock); - rc = sja1105_ptpclkval_read(priv, &ticks, NULL); + rc = sja1105_ptpegr_ts_poll(ds, port, &ts); if (rc < 0) { - dev_err(ds->dev, "Failed to read PTP clock: %d\n", rc); + dev_err(ds->dev, "timed out polling for tstamp\n"); kfree_skb(skb); goto out; } - rc = sja1105_ptpegr_ts_poll(ds, port, &ts); + rc = sja1105_ptpclkval_read(priv, &ticks, NULL); if (rc < 0) { - dev_err(ds->dev, "timed out polling for tstamp\n"); + dev_err(ds->dev, "Failed to read PTP clock: %d\n", rc); kfree_skb(skb); goto out; } From 762f926d6f19b9ab4dee0f98d55fc67e276cd094 Mon Sep 17 00:00:00 2001 From: Alaa Hleihel Date: Sun, 14 Jun 2020 14:12:48 +0300 Subject: [PATCH 25/35] net/sched: act_ct: Make tcf_ct_flow_table_restore_skb inline Currently, tcf_ct_flow_table_restore_skb is exported by act_ct module, therefore modules using it will have hard-dependency on act_ct and will require loading it all the time. This can lead to an unnecessary overhead on systems that do not use hardware connection tracking action (ct_metadata action) in the first place. To relax the hard-dependency between the modules, we unexport this function and make it a static inline one. Fixes: 30b0cf90c6dd ("net/sched: act_ct: Support restoring conntrack info on skbs") Signed-off-by: Alaa Hleihel Reviewed-by: Roi Dayan Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/tc_act/tc_ct.h | 11 ++++++++++- net/sched/act_ct.c | 11 ----------- 2 files changed, 10 insertions(+), 12 deletions(-) diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h index 79654bcb9a29..8250d6f0a462 100644 --- a/include/net/tc_act/tc_ct.h +++ b/include/net/tc_act/tc_ct.h @@ -66,7 +66,16 @@ static inline struct nf_flowtable *tcf_ct_ft(const struct tc_action *a) #endif /* CONFIG_NF_CONNTRACK */ #if IS_ENABLED(CONFIG_NET_ACT_CT) -void tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie); +static inline void +tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie) +{ + enum ip_conntrack_info ctinfo = cookie & NFCT_INFOMASK; + struct nf_conn *ct; + + ct = (struct nf_conn *)(cookie & NFCT_PTRMASK); + nf_conntrack_get(&ct->ct_general); + nf_ct_set(skb, ct, ctinfo); +} #else static inline void tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie) { } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index e29f0f45d688..e9f3576cbf71 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1543,17 +1543,6 @@ static void __exit ct_cleanup_module(void) destroy_workqueue(act_ct_wq); } -void tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie) -{ - enum ip_conntrack_info ctinfo = cookie & NFCT_INFOMASK; - struct nf_conn *ct; - - ct = (struct nf_conn *)(cookie & NFCT_PTRMASK); - nf_conntrack_get(&ct->ct_general); - nf_ct_set(skb, ct, ctinfo); -} -EXPORT_SYMBOL_GPL(tcf_ct_flow_table_restore_skb); - module_init(ct_init_module); module_exit(ct_cleanup_module); MODULE_AUTHOR("Paul Blakey "); From 505ee3a1cab96785fbc2c7cdb41ab677ec270c3c Mon Sep 17 00:00:00 2001 From: Alaa Hleihel Date: Sun, 14 Jun 2020 14:12:49 +0300 Subject: [PATCH 26/35] netfilter: flowtable: Make nf_flow_table_offload_add/del_cb inline Currently, nf_flow_table_offload_add/del_cb are exported by nf_flow_table module, therefore modules using them will have hard-dependency on nf_flow_table and will require loading it all the time. This can lead to an unnecessary overhead on systems that do not use this API. To relax the hard-dependency between the modules, we unexport these functions and make them static inline. Fixes: 978703f42549 ("netfilter: flowtable: Add API for registering to flow table events") Signed-off-by: Alaa Hleihel Reviewed-by: Roi Dayan Reviewed-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/netfilter/nf_flow_table.h | 49 ++++++++++++++++++++++++--- net/netfilter/nf_flow_table_core.c | 45 ------------------------ 2 files changed, 45 insertions(+), 49 deletions(-) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index d7338bfd7b0f..16e8b2f8d006 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -161,10 +161,51 @@ struct nf_flow_route { struct flow_offload *flow_offload_alloc(struct nf_conn *ct); void flow_offload_free(struct flow_offload *flow); -int nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table, - flow_setup_cb_t *cb, void *cb_priv); -void nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, - flow_setup_cb_t *cb, void *cb_priv); +static inline int +nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table, + flow_setup_cb_t *cb, void *cb_priv) +{ + struct flow_block *block = &flow_table->flow_block; + struct flow_block_cb *block_cb; + int err = 0; + + down_write(&flow_table->flow_block_lock); + block_cb = flow_block_cb_lookup(block, cb, cb_priv); + if (block_cb) { + err = -EEXIST; + goto unlock; + } + + block_cb = flow_block_cb_alloc(cb, cb_priv, cb_priv, NULL); + if (IS_ERR(block_cb)) { + err = PTR_ERR(block_cb); + goto unlock; + } + + list_add_tail(&block_cb->list, &block->cb_list); + +unlock: + up_write(&flow_table->flow_block_lock); + return err; +} + +static inline void +nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, + flow_setup_cb_t *cb, void *cb_priv) +{ + struct flow_block *block = &flow_table->flow_block; + struct flow_block_cb *block_cb; + + down_write(&flow_table->flow_block_lock); + block_cb = flow_block_cb_lookup(block, cb, cb_priv); + if (block_cb) { + list_del(&block_cb->list); + flow_block_cb_free(block_cb); + } else { + WARN_ON(true); + } + up_write(&flow_table->flow_block_lock); +} int flow_offload_route_init(struct flow_offload *flow, const struct nf_flow_route *route); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 6a3034f84ab6..afa85171df38 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -387,51 +387,6 @@ static void nf_flow_offload_work_gc(struct work_struct *work) queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ); } -int nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table, - flow_setup_cb_t *cb, void *cb_priv) -{ - struct flow_block *block = &flow_table->flow_block; - struct flow_block_cb *block_cb; - int err = 0; - - down_write(&flow_table->flow_block_lock); - block_cb = flow_block_cb_lookup(block, cb, cb_priv); - if (block_cb) { - err = -EEXIST; - goto unlock; - } - - block_cb = flow_block_cb_alloc(cb, cb_priv, cb_priv, NULL); - if (IS_ERR(block_cb)) { - err = PTR_ERR(block_cb); - goto unlock; - } - - list_add_tail(&block_cb->list, &block->cb_list); - -unlock: - up_write(&flow_table->flow_block_lock); - return err; -} -EXPORT_SYMBOL_GPL(nf_flow_table_offload_add_cb); - -void nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, - flow_setup_cb_t *cb, void *cb_priv) -{ - struct flow_block *block = &flow_table->flow_block; - struct flow_block_cb *block_cb; - - down_write(&flow_table->flow_block_lock); - block_cb = flow_block_cb_lookup(block, cb, cb_priv); - if (block_cb) { - list_del(&block_cb->list); - flow_block_cb_free(block_cb); - } else { - WARN_ON(true); - } - up_write(&flow_table->flow_block_lock); -} -EXPORT_SYMBOL_GPL(nf_flow_table_offload_del_cb); static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff, __be16 port, __be16 new_port) From b8ad540dd4e40566c520dff491fc06c71ae6b989 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Mon, 15 Jun 2020 09:35:22 +0800 Subject: [PATCH 27/35] mptcp: fix memory leak in mptcp_subflow_create_socket() socket malloced by sock_create_kern() should be release before return in the error handling, otherwise it cause memory leak. unreferenced object 0xffff88810910c000 (size 1216): comm "00000003_test_m", pid 12238, jiffies 4295050289 (age 54.237s) hex dump (first 32 bytes): 01 00 00 00 01 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 2f 30 0a 81 88 ff ff ........./0..... backtrace: [<00000000e877f89f>] sock_alloc_inode+0x18/0x1c0 [<0000000093d1dd51>] alloc_inode+0x63/0x1d0 [<000000005673fec6>] new_inode_pseudo+0x14/0xe0 [<00000000b5db6be8>] sock_alloc+0x3c/0x260 [<00000000e7e3cbb2>] __sock_create+0x89/0x620 [<0000000023e48593>] mptcp_subflow_create_socket+0xc0/0x5e0 [<00000000419795e4>] __mptcp_socket_create+0x1ad/0x3f0 [<00000000b2f942e8>] mptcp_stream_connect+0x281/0x4f0 [<00000000c80cd5cc>] __sys_connect_file+0x14d/0x190 [<00000000dc761f11>] __sys_connect+0x128/0x160 [<000000008b14e764>] __x64_sys_connect+0x6f/0xb0 [<000000007b4f93bd>] do_syscall_64+0xa1/0x530 [<00000000d3e770b6>] entry_SYSCALL_64_after_hwframe+0x49/0xb3 Fixes: 2303f994b3e1 ("mptcp: Associate MPTCP context with TCP socket") Signed-off-by: Wei Yongjun Signed-off-by: David S. Miller --- net/mptcp/subflow.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index bf132575040d..bbdb74b8bc3c 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1053,8 +1053,10 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) err = tcp_set_ulp(sf->sk, "mptcp"); release_sock(sf->sk); - if (err) + if (err) { + sock_release(sf); return err; + } /* the newly created socket really belongs to the owning MPTCP master * socket, even if for additional subflows the allocation is performed From 662051215c758ae8545451628816204ed6cd372d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Jun 2020 20:37:07 -0700 Subject: [PATCH 28/35] tcp: grow window for OOO packets only for SACK flows Back in 2013, we made a change that broke fast retransmit for non SACK flows. Indeed, for these flows, a sender needs to receive three duplicate ACK before starting fast retransmit. Sending ACK with different receive window do not count. Even if enabling SACK is strongly recommended these days, there still are some cases where it has to be disabled. Not increasing the window seems better than having to rely on RTO. After the fix, following packetdrill test gives : // Initialize connection 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 1) = 0 +0 < S 0:0(0) win 32792 +0 > S. 0:0(0) ack 1 +0 < . 1:1(0) ack 1 win 514 +0 accept(3, ..., ...) = 4 +0 < . 1:1001(1000) ack 1 win 514 // Quick ack +0 > . 1:1(0) ack 1001 win 264 +0 < . 2001:3001(1000) ack 1 win 514 // DUPACK : Normally we should not change the window +0 > . 1:1(0) ack 1001 win 264 +0 < . 3001:4001(1000) ack 1 win 514 // DUPACK : Normally we should not change the window +0 > . 1:1(0) ack 1001 win 264 +0 < . 4001:5001(1000) ack 1 win 514 // DUPACK : Normally we should not change the window +0 > . 1:1(0) ack 1001 win 264 +0 < . 1001:2001(1000) ack 1 win 514 // Hole is repaired. +0 > . 1:1(0) ack 5001 win 272 Fixes: 4e4f1fc22681 ("tcp: properly increase rcv_ssthresh for ofo packets") Signed-off-by: Eric Dumazet Reported-by: Venkat Venkatsubra Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 83330a6cb242..12fda8f27b08 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4605,7 +4605,11 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb, skb, &fragstolen)) { coalesce_done: - tcp_grow_window(sk, skb); + /* For non sack flows, do not grow window to force DUPACK + * and trigger fast retransmit. + */ + if (tcp_is_sack(tp)) + tcp_grow_window(sk, skb); kfree_skb_partial(skb, fragstolen); skb = NULL; goto add_sack; @@ -4689,7 +4693,11 @@ add_sack: tcp_sack_new_ofo_skb(sk, seq, end_seq); end: if (skb) { - tcp_grow_window(sk, skb); + /* For non sack flows, do not grow window to force DUPACK + * and trigger fast retransmit. + */ + if (tcp_is_sack(tp)) + tcp_grow_window(sk, skb); skb_condense(skb); skb_set_owner_r(skb, sk); } From 807eaf99688ce162a98a7501477644782d4af098 Mon Sep 17 00:00:00 2001 From: Sven Auhagen Date: Tue, 16 Jun 2020 06:35:29 +0200 Subject: [PATCH 29/35] mvpp2: remove module bugfix The remove function does not destroy all BM Pools when per cpu pool is active. When reloading the mvpp2 as a module the BM Pools are still active in hardware and due to the bug have twice the size now old + new. This eventually leads to a kernel crash. v2: * add Fixes tag Fixes: 7d04b0b13b11 ("mvpp2: percpu buffers") Signed-off-by: Sven Auhagen Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 5d4ec95be869..24f4d8e0da98 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5983,8 +5983,8 @@ static int mvpp2_remove(struct platform_device *pdev) { struct mvpp2 *priv = platform_get_drvdata(pdev); struct fwnode_handle *fwnode = pdev->dev.fwnode; + int i = 0, poolnum = MVPP2_BM_POOLS_NUM; struct fwnode_handle *port_fwnode; - int i = 0; mvpp2_dbgfs_cleanup(priv); @@ -5998,7 +5998,10 @@ static int mvpp2_remove(struct platform_device *pdev) destroy_workqueue(priv->stats_queue); - for (i = 0; i < MVPP2_BM_POOLS_NUM; i++) { + if (priv->percpu_pools) + poolnum = mvpp2_get_nrxqs(priv) * 2; + + for (i = 0; i < poolnum; i++) { struct mvpp2_bm_pool *bm_pool = &priv->bm_pools[i]; mvpp2_bm_pool_destroy(&pdev->dev, priv, bm_pool); From b15bb8817f991497d97ae55d8c0e349a9d1e1478 Mon Sep 17 00:00:00 2001 From: Martin Date: Tue, 16 Jun 2020 11:18:58 +0530 Subject: [PATCH 30/35] bareudp: Fixed configuration to avoid having garbage values Code to initialize the conf structure while gathering the configuration of the device was missing. Fixes: 571912c69f0e ("net: UDP tunnel encapsulation module for tunnelling different protocols like MPLS, IP, NSH etc.") Signed-off-by: Martin Signed-off-by: David S. Miller --- drivers/net/bareudp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index efd1a1d1f35e..5d3c691a1c66 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -552,6 +552,8 @@ static int bareudp_validate(struct nlattr *tb[], struct nlattr *data[], static int bareudp2info(struct nlattr *data[], struct bareudp_conf *conf, struct netlink_ext_ack *extack) { + memset(conf, 0, sizeof(*conf)); + if (!data[IFLA_BAREUDP_PORT]) { NL_SET_ERR_MSG(extack, "port not specified"); return -EINVAL; From 60833d54d56c21e7538296eb2e00e104768fd047 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 16 Jun 2020 10:14:58 +0300 Subject: [PATCH 31/35] mlxsw: spectrum: Adjust headroom buffers for 8x ports The port's headroom buffers are used to store packets while they traverse the device's pipeline and also to store packets that are egress mirrored. On Spectrum-3, ports with eight lanes use two headroom buffers between which the configured headroom size is split. In order to prevent packet loss, multiply the calculated headroom size by two for 8x ports. Fixes: da382875c616 ("mlxsw: spectrum: Extend to support Spectrum-3 ASIC") Signed-off-by: Ido Schimmel Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 ++ drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 13 +++++++++++++ .../net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 1 + drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c | 1 + 4 files changed, 17 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 5ffa32b75e5f..55af877763ed 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -978,8 +978,10 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu, lossy = !(pfc || pause_en); thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu); + mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &thres_cells); delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc, pause_en); + mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &delay_cells); total_cells = thres_cells + delay_cells; taken_headroom_cells += total_cells; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 6f96ca50c9ba..6e87457dd635 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -374,6 +374,19 @@ mlxsw_sp_port_vlan_find_by_vid(const struct mlxsw_sp_port *mlxsw_sp_port, return NULL; } +static inline void +mlxsw_sp_port_headroom_8x_adjust(const struct mlxsw_sp_port *mlxsw_sp_port, + u16 *p_size) +{ + /* Ports with eight lanes use two headroom buffers between which the + * configured headroom size is split. Therefore, multiply the calculated + * headroom size by two. + */ + if (mlxsw_sp_port->mapping.width != 8) + return; + *p_size *= 2; +} + enum mlxsw_sp_flood_type { MLXSW_SP_FLOOD_TYPE_UC, MLXSW_SP_FLOOD_TYPE_BC, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 21bfb2f6a6f0..f25a8b084b4b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -312,6 +312,7 @@ static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port) if (i == MLXSW_SP_PB_UNUSED) continue; + mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &size); mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, i, size); } mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 304eb8c3d8bd..f843545d3478 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -782,6 +782,7 @@ mlxsw_sp_span_port_buffer_update(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu) speed = 0; buffsize = mlxsw_sp_span_buffsize_get(mlxsw_sp, speed, mtu); + mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, (u16 *) &buffsize); mlxsw_reg_sbib_pack(sbib_pl, mlxsw_sp_port->local_port, buffsize); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); } From ea12fe9dee97d1f284ee980845444859cfcb307d Mon Sep 17 00:00:00 2001 From: Tim Harvey Date: Tue, 16 Jun 2020 08:31:58 -0700 Subject: [PATCH 32/35] lan743x: add MODULE_DEVICE_TABLE for module loading alias Without a MODULE_DEVICE_TABLE the attributes are missing that create an alias for auto-loading the module in userspace via hotplug. Signed-off-by: Tim Harvey Signed-off-by: David S. Miller --- drivers/net/ethernet/microchip/lan743x_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index c5c5c688b7e2..f1711ac86d0c 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -3091,6 +3091,8 @@ static const struct pci_device_id lan743x_pcidev_tbl[] = { { 0, } }; +MODULE_DEVICE_TABLE(pci, lan743x_pcidev_tbl); + static struct pci_driver lan743x_pcidev_driver = { .name = DRIVER_NAME, .id_table = lan743x_pcidev_tbl, From 6bf6be1127f7e6d4bf39f84d56854e944d045d74 Mon Sep 17 00:00:00 2001 From: Chen Yu Date: Fri, 22 May 2020 01:59:00 +0800 Subject: [PATCH 33/35] e1000e: Do not wake up the system via WOL if device wakeup is disabled Currently the system will be woken up via WOL(Wake On LAN) even if the device wakeup ability has been disabled via sysfs: cat /sys/devices/pci0000:00/0000:00:1f.6/power/wakeup disabled The system should not be woken up if the user has explicitly disabled the wake up ability for this device. This patch clears the WOL ability of this network device if the user has disabled the wake up ability in sysfs. Fixes: bc7f75fa9788 ("[E1000E]: New pci-express e1000 driver") Reported-by: "Rafael J. Wysocki" Reviewed-by: Andy Shevchenko Cc: Signed-off-by: Chen Yu Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/netdev.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index a279f4fa9962..e2ad3f38c75c 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6611,11 +6611,17 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) struct net_device *netdev = pci_get_drvdata(pdev); struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - u32 ctrl, ctrl_ext, rctl, status; - /* Runtime suspend should only enable wakeup for link changes */ - u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol; + u32 ctrl, ctrl_ext, rctl, status, wufc; int retval = 0; + /* Runtime suspend should only enable wakeup for link changes */ + if (runtime) + wufc = E1000_WUFC_LNKC; + else if (device_may_wakeup(&pdev->dev)) + wufc = adapter->wol; + else + wufc = 0; + status = er32(STATUS); if (status & E1000_STATUS_LU) wufc &= ~E1000_WUFC_LNKC; @@ -6672,7 +6678,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) if (adapter->hw.phy.type == e1000_phy_igp_3) { e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw); } else if (hw->mac.type >= e1000_pch_lpt) { - if (!(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC))) + if (wufc && !(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC))) /* ULP does not support wake from unicast, multicast * or broadcast. */ From eb6779d4c505145f3d4331da505f4c058d02ad04 Mon Sep 17 00:00:00 2001 From: Vaibhav Gupta Date: Mon, 25 May 2020 17:57:10 +0530 Subject: [PATCH 34/35] e1000: use generic power management With legacy PM hooks, it was the responsibility of a driver to manage PCI states and also the device's power state. The generic approach is to let PCI core handle the work. e1000_suspend() calls __e1000_shutdown() to perform intermediate tasks. __e1000_shutdown() modifies the value of "wake" (device should be wakeup enabled or not), responsible for controlling the flow of legacy PM. Since, PCI core has no idea about the value of "wake", new code for generic PM may produce unexpected results. Thus, use "device_set_wakeup_enable()" to wakeup-enable the device accordingly. Signed-off-by: Vaibhav Gupta Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000/e1000_main.c | 49 +++++-------------- 1 file changed, 13 insertions(+), 36 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index d9fa4600f745..4b2de08137be 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -151,10 +151,8 @@ static int e1000_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid); static void e1000_restore_vlan(struct e1000_adapter *adapter); -#ifdef CONFIG_PM -static int e1000_suspend(struct pci_dev *pdev, pm_message_t state); -static int e1000_resume(struct pci_dev *pdev); -#endif +static int __maybe_unused e1000_suspend(struct device *dev); +static int __maybe_unused e1000_resume(struct device *dev); static void e1000_shutdown(struct pci_dev *pdev); #ifdef CONFIG_NET_POLL_CONTROLLER @@ -179,16 +177,16 @@ static const struct pci_error_handlers e1000_err_handler = { .resume = e1000_io_resume, }; +static SIMPLE_DEV_PM_OPS(e1000_pm_ops, e1000_suspend, e1000_resume); + static struct pci_driver e1000_driver = { .name = e1000_driver_name, .id_table = e1000_pci_tbl, .probe = e1000_probe, .remove = e1000_remove, -#ifdef CONFIG_PM - /* Power Management Hooks */ - .suspend = e1000_suspend, - .resume = e1000_resume, -#endif + .driver = { + .pm = &e1000_pm_ops, + }, .shutdown = e1000_shutdown, .err_handler = &e1000_err_handler }; @@ -5060,9 +5058,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake) struct e1000_hw *hw = &adapter->hw; u32 ctrl, ctrl_ext, rctl, status; u32 wufc = adapter->wol; -#ifdef CONFIG_PM - int retval = 0; -#endif netif_device_detach(netdev); @@ -5076,12 +5071,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake) e1000_down(adapter); } -#ifdef CONFIG_PM - retval = pci_save_state(pdev); - if (retval) - return retval; -#endif - status = er32(STATUS); if (status & E1000_STATUS_LU) wufc &= ~E1000_WUFC_LNKC; @@ -5142,37 +5131,26 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake) return 0; } -#ifdef CONFIG_PM -static int e1000_suspend(struct pci_dev *pdev, pm_message_t state) +static int __maybe_unused e1000_suspend(struct device *dev) { int retval; + struct pci_dev *pdev = to_pci_dev(dev); bool wake; retval = __e1000_shutdown(pdev, &wake); - if (retval) - return retval; + device_set_wakeup_enable(dev, wake); - if (wake) { - pci_prepare_to_sleep(pdev); - } else { - pci_wake_from_d3(pdev, false); - pci_set_power_state(pdev, PCI_D3hot); - } - - return 0; + return retval; } -static int e1000_resume(struct pci_dev *pdev) +static int __maybe_unused e1000_resume(struct device *dev) { + struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; u32 err; - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - pci_save_state(pdev); - if (adapter->need_ioport) err = pci_enable_device(pdev); else @@ -5209,7 +5187,6 @@ static int e1000_resume(struct pci_dev *pdev) return 0; } -#endif static void e1000_shutdown(struct pci_dev *pdev) { From 880e6269fd6e60249c8f5f1b98295e9f7e56636d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 27 May 2020 15:47:00 +0200 Subject: [PATCH 35/35] e1000e: fix unused-function warning The CONFIG_PM_SLEEP #ifdef checks in this file are inconsistent, leading to a warning about sometimes unused function: drivers/net/ethernet/intel/e1000e/netdev.c:137:13: error: unused function 'e1000e_check_me' [-Werror,-Wunused-function] Rather than adding more #ifdefs, just remove them completely and mark the PM functions as __maybe_unused to let the compiler work it out on it own. Fixes: e086ba2fccda ("e1000e: disable s0ix entry and exit flows for ME systems") Signed-off-by: Arnd Bergmann Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/netdev.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index e2ad3f38c75c..6f6479ca1267 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6349,7 +6349,6 @@ fl_out: pm_runtime_put_sync(netdev->dev.parent); } -#ifdef CONFIG_PM_SLEEP /* S0ix implementation */ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter) { @@ -6571,7 +6570,6 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) mac_data &= ~E1000_CTRL_EXT_FORCE_SMBUS; ew32(CTRL_EXT, mac_data); } -#endif /* CONFIG_PM_SLEEP */ static int e1000e_pm_freeze(struct device *dev) { @@ -6875,7 +6873,6 @@ err_irq: return rc; } -#ifdef CONFIG_PM static int __e1000_resume(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); @@ -6941,8 +6938,7 @@ static int __e1000_resume(struct pci_dev *pdev) return 0; } -#ifdef CONFIG_PM_SLEEP -static int e1000e_pm_suspend(struct device *dev) +static __maybe_unused int e1000e_pm_suspend(struct device *dev) { struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); @@ -6966,7 +6962,7 @@ static int e1000e_pm_suspend(struct device *dev) return rc; } -static int e1000e_pm_resume(struct device *dev) +static __maybe_unused int e1000e_pm_resume(struct device *dev) { struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); @@ -6985,9 +6981,8 @@ static int e1000e_pm_resume(struct device *dev) return e1000e_pm_thaw(dev); } -#endif /* CONFIG_PM_SLEEP */ -static int e1000e_pm_runtime_idle(struct device *dev) +static __maybe_unused int e1000e_pm_runtime_idle(struct device *dev) { struct net_device *netdev = dev_get_drvdata(dev); struct e1000_adapter *adapter = netdev_priv(netdev); @@ -7003,7 +6998,7 @@ static int e1000e_pm_runtime_idle(struct device *dev) return -EBUSY; } -static int e1000e_pm_runtime_resume(struct device *dev) +static __maybe_unused int e1000e_pm_runtime_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -7020,7 +7015,7 @@ static int e1000e_pm_runtime_resume(struct device *dev) return rc; } -static int e1000e_pm_runtime_suspend(struct device *dev) +static __maybe_unused int e1000e_pm_runtime_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -7045,7 +7040,6 @@ static int e1000e_pm_runtime_suspend(struct device *dev) return 0; } -#endif /* CONFIG_PM */ static void e1000_shutdown(struct pci_dev *pdev) {