diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-20 11:57:05 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-20 11:57:05 +0300 |
commit | fa2e1ba3e9e39072fa7a6a9d11ac432c505b4ac7 (patch) | |
tree | 9a8eb0d867559af3a55a88856d23036dabdf3f1c /net/ipv4/fib_semantics.c | |
parent | f4484d138b31e8fa1ba410363b5b9664f68974af (diff) | |
parent | ff9fc0a31d85fcf0011eb4bc4ecaf47d3cc9e21c (diff) | |
download | linux-fa2e1ba3e9e39072fa7a6a9d11ac432c505b4ac7.tar.xz |
Merge tag 'net-5.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from netfilter, bpf.
Quite a handful of old regression fixes but most of those are
pre-5.16.
Current release - regressions:
- fix memory leaks in the skb free deferral scheme if upper layer
protocols are used, i.e. in-kernel TCP readers like TLS
Current release - new code bugs:
- nf_tables: fix NULL check typo in _clone() functions
- change the default to y for Vertexcom vendor Kconfig
- a couple of fixes to incorrect uses of ref tracking
- two fixes for constifying netdev->dev_addr
Previous releases - regressions:
- bpf:
- various verifier fixes mainly around register offset handling
when passed to helper functions
- fix mount source displayed for bpffs (none -> bpffs)
- bonding:
- fix extraction of ports for connection hash calculation
- fix bond_xmit_broadcast return value when some devices are down
- phy: marvell: add Marvell specific PHY loopback
- sch_api: don't skip qdisc attach on ingress, prevent ref leak
- htb: restore minimal packet size handling in rate control
- sfp: fix high power modules without diagnostic monitoring
- mscc: ocelot:
- don't let phylink re-enable TX PAUSE on the NPI port
- don't dereference NULL pointers with shared tc filters
- smsc95xx: correct reset handling for LAN9514
- cpsw: avoid alignment faults by taking NET_IP_ALIGN into account
- phy: micrel: use kszphy_suspend/_resume for irq aware devices,
avoid races with the interrupt
Previous releases - always broken:
- xdp: check prog type before updating BPF link
- smc: resolve various races around abnormal connection termination
- sit: allow encapsulated IPv6 traffic to be delivered locally
- axienet: fix init/reset handling, add missing barriers, read the
right status words, stop queues correctly
- add missing dev_put() in sock_timestamping_bind_phc()
Misc:
- ipv4: prevent accidentally passing RTO_ONLINK to
ip_route_output_key_hash() by sanitizing flags
- ipv4: avoid quadratic behavior in netns dismantle
- stmmac: dwmac-oxnas: add support for OX810SE
- fsl: xgmac_mdio: add workaround for erratum A-009885"
* tag 'net-5.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (92 commits)
ipv4: add net_hash_mix() dispersion to fib_info_laddrhash keys
ipv4: avoid quadratic behavior in netns dismantle
net/fsl: xgmac_mdio: Fix incorrect iounmap when removing module
powerpc/fsl/dts: Enable WA for erratum A-009885 on fman3l MDIO buses
dt-bindings: net: Document fsl,erratum-a009885
net/fsl: xgmac_mdio: Add workaround for erratum A-009885
net: mscc: ocelot: fix using match before it is set
net: phy: micrel: use kszphy_suspend()/kszphy_resume for irq aware devices
net: cpsw: avoid alignment faults by taking NET_IP_ALIGN into account
nfc: llcp: fix NULL error pointer dereference on sendmsg() after failed bind()
net: axienet: increase default TX ring size to 128
net: axienet: fix for TX busy handling
net: axienet: fix number of TX ring slots for available check
net: axienet: Fix TX ring slot available check
net: axienet: limit minimum TX ring size
net: axienet: add missing memory barriers
net: axienet: reset core on initialization prior to MDIO access
net: axienet: Wait for PhyRstCmplt after core reset
net: axienet: increase reset timeout
bpf, selftests: Add ringbuf memory type confusion test
...
Diffstat (limited to 'net/ipv4/fib_semantics.c')
-rw-r--r-- | net/ipv4/fib_semantics.c | 76 |
1 files changed, 40 insertions, 36 deletions
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 828de171708f..b4589861b84c 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -29,6 +29,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/netlink.h> +#include <linux/hash.h> #include <net/arp.h> #include <net/ip.h> @@ -51,6 +52,7 @@ static DEFINE_SPINLOCK(fib_info_lock); static struct hlist_head *fib_info_hash; static struct hlist_head *fib_info_laddrhash; static unsigned int fib_info_hash_size; +static unsigned int fib_info_hash_bits; static unsigned int fib_info_cnt; #define DEVINDEX_HASHBITS 8 @@ -249,7 +251,6 @@ void free_fib_info(struct fib_info *fi) pr_warn("Freeing alive fib_info %p\n", fi); return; } - fib_info_cnt--; call_rcu(&fi->rcu, free_fib_info_rcu); } @@ -260,6 +261,10 @@ void fib_release_info(struct fib_info *fi) spin_lock_bh(&fib_info_lock); if (fi && refcount_dec_and_test(&fi->fib_treeref)) { hlist_del(&fi->fib_hash); + + /* Paired with READ_ONCE() in fib_create_info(). */ + WRITE_ONCE(fib_info_cnt, fib_info_cnt - 1); + if (fi->fib_prefsrc) hlist_del(&fi->fib_lhash); if (fi->nh) { @@ -316,11 +321,15 @@ static inline int nh_comp(struct fib_info *fi, struct fib_info *ofi) static inline unsigned int fib_devindex_hashfn(unsigned int val) { - unsigned int mask = DEVINDEX_HASHSIZE - 1; + return hash_32(val, DEVINDEX_HASHBITS); +} + +static struct hlist_head * +fib_info_devhash_bucket(const struct net_device *dev) +{ + u32 val = net_hash_mix(dev_net(dev)) ^ dev->ifindex; - return (val ^ - (val >> DEVINDEX_HASHBITS) ^ - (val >> (DEVINDEX_HASHBITS * 2))) & mask; + return &fib_info_devhash[fib_devindex_hashfn(val)]; } static unsigned int fib_info_hashfn_1(int init_val, u8 protocol, u8 scope, @@ -430,12 +439,11 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev) { struct hlist_head *head; struct fib_nh *nh; - unsigned int hash; spin_lock(&fib_info_lock); - hash = fib_devindex_hashfn(dev->ifindex); - head = &fib_info_devhash[hash]; + head = fib_info_devhash_bucket(dev); + hlist_for_each_entry(nh, head, nh_hash) { if (nh->fib_nh_dev == dev && nh->fib_nh_gw4 == gw && @@ -1240,13 +1248,13 @@ int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope, return err; } -static inline unsigned int fib_laddr_hashfn(__be32 val) +static struct hlist_head * +fib_info_laddrhash_bucket(const struct net *net, __be32 val) { - unsigned int mask = (fib_info_hash_size - 1); + u32 slot = hash_32(net_hash_mix(net) ^ (__force u32)val, + fib_info_hash_bits); - return ((__force u32)val ^ - ((__force u32)val >> 7) ^ - ((__force u32)val >> 14)) & mask; + return &fib_info_laddrhash[slot]; } static struct hlist_head *fib_info_hash_alloc(int bytes) @@ -1282,6 +1290,7 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, old_info_hash = fib_info_hash; old_laddrhash = fib_info_laddrhash; fib_info_hash_size = new_size; + fib_info_hash_bits = ilog2(new_size); for (i = 0; i < old_size; i++) { struct hlist_head *head = &fib_info_hash[i]; @@ -1299,21 +1308,20 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, } fib_info_hash = new_info_hash; + fib_info_laddrhash = new_laddrhash; for (i = 0; i < old_size; i++) { - struct hlist_head *lhead = &fib_info_laddrhash[i]; + struct hlist_head *lhead = &old_laddrhash[i]; struct hlist_node *n; struct fib_info *fi; hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) { struct hlist_head *ldest; - unsigned int new_hash; - new_hash = fib_laddr_hashfn(fi->fib_prefsrc); - ldest = &new_laddrhash[new_hash]; + ldest = fib_info_laddrhash_bucket(fi->fib_net, + fi->fib_prefsrc); hlist_add_head(&fi->fib_lhash, ldest); } } - fib_info_laddrhash = new_laddrhash; spin_unlock_bh(&fib_info_lock); @@ -1430,7 +1438,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg, #endif err = -ENOBUFS; - if (fib_info_cnt >= fib_info_hash_size) { + + /* Paired with WRITE_ONCE() in fib_release_info() */ + if (READ_ONCE(fib_info_cnt) >= fib_info_hash_size) { unsigned int new_size = fib_info_hash_size << 1; struct hlist_head *new_info_hash; struct hlist_head *new_laddrhash; @@ -1462,7 +1472,6 @@ struct fib_info *fib_create_info(struct fib_config *cfg, return ERR_PTR(err); } - fib_info_cnt++; fi->fib_net = net; fi->fib_protocol = cfg->fc_protocol; fi->fib_scope = cfg->fc_scope; @@ -1591,12 +1600,13 @@ link_it: refcount_set(&fi->fib_treeref, 1); refcount_set(&fi->fib_clntref, 1); spin_lock_bh(&fib_info_lock); + fib_info_cnt++; hlist_add_head(&fi->fib_hash, &fib_info_hash[fib_info_hashfn(fi)]); if (fi->fib_prefsrc) { struct hlist_head *head; - head = &fib_info_laddrhash[fib_laddr_hashfn(fi->fib_prefsrc)]; + head = fib_info_laddrhash_bucket(net, fi->fib_prefsrc); hlist_add_head(&fi->fib_lhash, head); } if (fi->nh) { @@ -1604,12 +1614,10 @@ link_it: } else { change_nexthops(fi) { struct hlist_head *head; - unsigned int hash; if (!nexthop_nh->fib_nh_dev) continue; - hash = fib_devindex_hashfn(nexthop_nh->fib_nh_dev->ifindex); - head = &fib_info_devhash[hash]; + head = fib_info_devhash_bucket(nexthop_nh->fib_nh_dev); hlist_add_head(&nexthop_nh->nh_hash, head); } endfor_nexthops(fi) } @@ -1870,16 +1878,16 @@ nla_put_failure: */ int fib_sync_down_addr(struct net_device *dev, __be32 local) { - int ret = 0; - unsigned int hash = fib_laddr_hashfn(local); - struct hlist_head *head = &fib_info_laddrhash[hash]; int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; struct net *net = dev_net(dev); + struct hlist_head *head; struct fib_info *fi; + int ret = 0; if (!fib_info_laddrhash || local == 0) return 0; + head = fib_info_laddrhash_bucket(net, local); hlist_for_each_entry(fi, head, fib_lhash) { if (!net_eq(fi->fib_net, net) || fi->fib_tb_id != tb_id) @@ -1961,8 +1969,7 @@ void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig) void fib_sync_mtu(struct net_device *dev, u32 orig_mtu) { - unsigned int hash = fib_devindex_hashfn(dev->ifindex); - struct hlist_head *head = &fib_info_devhash[hash]; + struct hlist_head *head = fib_info_devhash_bucket(dev); struct fib_nh *nh; hlist_for_each_entry(nh, head, nh_hash) { @@ -1981,12 +1988,11 @@ void fib_sync_mtu(struct net_device *dev, u32 orig_mtu) */ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force) { - int ret = 0; - int scope = RT_SCOPE_NOWHERE; + struct hlist_head *head = fib_info_devhash_bucket(dev); struct fib_info *prev_fi = NULL; - unsigned int hash = fib_devindex_hashfn(dev->ifindex); - struct hlist_head *head = &fib_info_devhash[hash]; + int scope = RT_SCOPE_NOWHERE; struct fib_nh *nh; + int ret = 0; if (force) scope = -1; @@ -2131,7 +2137,6 @@ out: int fib_sync_up(struct net_device *dev, unsigned char nh_flags) { struct fib_info *prev_fi; - unsigned int hash; struct hlist_head *head; struct fib_nh *nh; int ret; @@ -2147,8 +2152,7 @@ int fib_sync_up(struct net_device *dev, unsigned char nh_flags) } prev_fi = NULL; - hash = fib_devindex_hashfn(dev->ifindex); - head = &fib_info_devhash[hash]; + head = fib_info_devhash_bucket(dev); ret = 0; hlist_for_each_entry(nh, head, nh_hash) { |