- 08 Feb, 2017 29 commits
-
-
Ido Schimmel authored
We currently use the scope of the FIB info to distinguish between a direct unicast route and a gatewayed one. However, the kernel is perfectly happy to configure a route with scope UNIVERSE to a directly connected network. Instead, we can rely on the first nexthop's scope to check if the route is gatewayed or not. Signed-off-by:
Ido Schimmel <idosch@mellanox.com> Signed-off-by:
Jiri Pirko <jiri@mellanox.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Ido Schimmel authored
Later in the patchset we'll add the NH_{ADD,DEL} events which will let us know when a nexthop is considered to be dead. Based on these events we need to be able to add or remove the nexthop from the device's tables. Therefore, store the private nexthop structs in a hash table and use the kernel's fib_nh struct as the key, so that we'll be able to easily find them when the events are received. Signed-off-by: -
Ido Schimmel authored
Currently, when we're notified about a new RTN_UNICAST route we perform a lookup on the nexthop group list looking for a group with a matching configuration to that found in the FIB info. This is quite inefficient. Instead, we can simply rely on the kernel to consolidate several FIB configurations into the same FIB info and use the FIB info as the key for our private nexthop group struct. Signed-off-by:
-
Ido Schimmel authored
When we invalidate a nexthop we should also invalidate its neighbour entry pointer as it might be destroyed later on. This makes the nexthop de-init function symmetric with its init and also ensures nobody will try to access the neighbour entry. Signed-off-by:
-
Jiri Pirko authored
No rollback is needed since the chain is in consistent state and mlxsw_afa_block_destroy() will take care of putting it away. So remove the one we have now which is wrong. Also move the set of 'finished' flag to the beginning of the function, because the block is certainly unusable for future action addition no matter if the function succeeds or not. Reported-by:
Dan Carpenter <dan.carpenter@oracle.com> Fixes: 4cda7d8d ("mlxsw: core: Introduce flexible actions support") Signed-off-by:
-
David S. Miller authored
Corentin Labbe says: ==================== net: stmmac: misc fix I am currently working on dwmac-sun8i glue driver for Allwinner H3/A83T/A64. This series is the result of all minor problem found in the stmmac driver. All patch are tested on cubieboard2 via dwmac-sunxi and on pine64/orangepis via dwmac-sun8i. Changes since v1: - Removed netdev_dbg() in "net: stmmac: print phy information" - Removed patch "net: stmmac: Implement NAPI for TX", it will be reworked - Changed error message in "Correct the error message about invalid speed" - Added some acked-by ==================== Signed-off-by: -
LABBE Corentin authored
checkpatch complains about two unsigned without type after. Since the value return is u32, it is simpler to replace it by u32 instead of "unsigned int" Signed-off-by:
Corentin Labbe <clabbe.montjoie@gmail.com> Acked-by:
Giuseppe Cavallaro <peppe.cavallaro@st.com> Signed-off-by:
-
LABBE Corentin authored
The u64 x variable in sysfs_display_ring is unused. This patch remove it. Signed-off-by:
-
LABBE Corentin authored
Since commit cf32deec ("stmmac: add tx_skbuff_dma to save descriptors used by PTP"), the struct dma_desc *p in stmmac_tx_clean was not used at all. This patch remove this dead code. Signed-off-by:
-
LABBE Corentin authored
When a PHY is found, printing which one was found (and which type/model) is a good information to know. Signed-off-by:
-
LABBE Corentin authored
The ethtool stat counter rx_crc from stmmac is mis-named, the name seems to speak about the number of RX CRC done, but in fact it is about errors. This patch rename it to rx_crc_errors, just like the same ifconfig counter. Signed-off-by:
-
LABBE Corentin authored
This patch rewrite two test against NULL value with correct style. Signed-off-by:
-
LABBE Corentin authored
The message about invalid speed does not state 1000 as a valid speed. It is much simpler to said that the speed is invalid. Signed-off-by:
-
LABBE Corentin authored
As said by checkpatch ENOSYS means 'invalid syscall nr' and nothing else. This patch replace ENOSYS by the more appropriate value EINVAL. Signed-off-by:
-
LABBE Corentin authored
The dwmac_dma_reset function use an open coded of readl_poll_timeout(). Replace the open coded handling with the proper function. Signed-off-by:
-
LABBE Corentin authored
The stmmac_mdio_busy_wait() function do the same job than readl_poll_timeout(). So is is better to replace it. Signed-off-by:
-
LABBE Corentin authored
Checkpatch complains about some code style problem on stmmac_mdio.c. This patch fix them. Signed-off-by:
-
LABBE Corentin authored
This patch fix the checkpatch warning about asm/io.h. Sorting all includes in the process. Signed-off-by:
-
LABBE Corentin authored
This patch fix the checkpatch warning about free software address. Signed-off-by:
-
LABBE Corentin authored
This patch fix some typos in comments. Signed-off-by:
-
LABBE Corentin authored
The bus_setup function pointer is not used at all, this patch remove it. Signed-off-by:
-
LABBE Corentin authored
the define MAC_RNABLE_RX have a typo, rename it to MAC_ENABLE_RX Signed-off-by:
-
Daniel Borkmann authored
Cap the maximum (total) value size and bail out if larger than KMALLOC_MAX_SIZE as otherwise it doesn't make any sense to proceed further, since we're guaranteed to fail to allocate elements anyway in lpm_trie_node_alloc(); likleyhood of failure is still high for large values, though, similarly as with htab case in non-prealloc. Next, make sure that cost vars are really u64 instead of size_t, so that we don't overflow on 32 bit and charge only tiny map.pages against memlock while allowing huge max_entries; cap also the max cost like we do with other map types. Fixes: b95a5c4d ("bpf: add a longest prefix match trie map implementation") Signed-off-by:
Daniel Borkmann <daniel@iogearbox.net> Acked-by:
Alexei Starovoitov <ast@kernel.org> Signed-off-by:
-
Roopa Prabhu authored
This fixes a bug and cleans up tunnelid range size calculation code by using consistent variable names and checks in size calculation and fill functions. tested for a few cases of vlan-vni range mappings: (output from patched iproute2): $bridge vlan showtunnel port vid tunid vxlan0 100-105 1000-1005 200 2000 210 2100 211-213 2100-2102 214 2104 216-217 2108-2109 219 2119 Fixes: efa5356b ("bridge: per vlan dst_metadata netlink support") Reported-by:Colin Ian King <colin.king@canonical.com> Signed-off-by:
Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by:
-
Eric Dumazet authored
We have many gro cells users, so lets move the code to avoid duplication. This creates a CONFIG_GRO_CELLS option. Signed-off-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
-
Philippe Reynes authored
The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. As I don't have the hardware, I'd be very pleased if someone may test this patch. Signed-off-by:Philippe Reynes <tremyfr@gmail.com> Reviewed-by:
-
Wu Fengguang authored
drivers/net/ethernet/qualcomm/emac/emac-ethtool.c:155:49-50: Unneeded semicolon Remove unneeded semicolon. Generated by: scripts/coccinelle/misc/semicolon.cocci CC: Timur Tabi <timur@codeaurora.org> Signed-off-by:
Fengguang Wu <fengguang.wu@intel.com> Signed-off-by:
-
Raju Lakkaraju authored
LED Mode: Microsemi PHY support 2 LEDs (LED[0] and LED[1]) to display different status information that can be selected by setting LED mode. LED Mode parameter (vsc8531, led-0-mode) and (vsc8531, led-1-mode) get from Device Tree. Signed-off-by:
Raju Lakkaraju <Raju.Lakkaraju@microsemi.com> Signed-off-by:
-
Dan Carpenter authored
This patch doesn't affect how the code works. My static checker complains that the mask and shift doesn't make sense because 0xffffff << 16 goes beyond the end of 32 bits. It should be 0xffff instead but the existing code won't cause runtime bugs. Also the casting here is not needed and not consistent with the rest of the code. Signed-off-by:
-
- 07 Feb, 2017 11 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller authored
The conflict was an interaction between a bug fix in the netvsc driver in 'net' and an optimization of the RX path in 'net-next'. Signed-off-by: -
Felix Manlunas authored
Fix smatch errors by not dereferencing iq pointer if it's NULL. See http://marc.info/?l=kernel-janitors&m=148637299004834&w=2Reported-by:
Felix Manlunas <felix.manlunas@cavium.com> Signed-off-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/davem/netLinus Torvalds authored
Pull networking fixes from David Miller: 1) Load correct firmware in rtl8192ce wireless driver, from Jurij Smakov. 2) Fix leak of tx_ring and tx_cq due to overwriting in mlx4 driver, from Martin KaFai Lau. 3) Need to reference count PHY driver module when it is attached, from Mao Wenan. 4) Don't do zero length vzalloc() in ethtool register dump, from Stanislaw Gruszka. 5) Defer net_disable_timestamp() to a workqueue to get out of locking issues, from Eric Dumazet. 6) We cannot drop the SKB dst when IP options refer to them, fix also from Eric Dumazet. 7) Incorrect packet header offset calculations in ip6_gre, again from Eric Dumazet. 8) Missing tcp_v6_restore_cb() causes use-after-free, from Eric too. 9) tcp_splice_read() can get into an infinite loop with URG, and hey it's from Eric once more. 10) vnet_hdr_sz can change asynchronously, so read it once during decision making in macvtap and tun, from Willem de Bruijn. 11) Can't use kernel stack for DMA transfers in USB networking drivers, from Ben Hutchings. 12) Handle csum errors properly in UDP by calling the proper destructor, from Eric Dumazet. 13) For non-deterministic softirq run when scheduling NAPI from a workqueue in mlx4, from Benjamin Poirier. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (28 commits) sctp: check af before verify address in sctp_addr_id2transport sctp: avoid BUG_ON on sctp_wait_for_sndbuf mlx4: Invoke softirqs after napi_reschedule udp: properly cope with csum errors catc: Use heap buffer for memory size test catc: Combine failure cleanup code in catc_probe() rtl8150: Use heap buffers for all register access pegasus: Use heap buffers for all register access macvtap: read vnet_hdr_size once tun: read vnet_hdr_sz once tcp: avoid infinite loop in tcp_splice_read() hns: avoid stack overflow with CONFIG_KASAN ipv6: Fix IPv6 packet loss in scenarios involving roaming + snooping switches ipv6: tcp: add a missing tcp_v6_restore_cb() nl80211: Fix mesh HT operation check mac80211: Fix adding of mesh vendor IEs mac80211: Allocate a sync skcipher explicitly for FILS AEAD mac80211: Fix FILS AEAD protection in Association Request frame ip6_gre: fix ip6gre_err() invalid reads netlabel: out of bound access in cipso_v4_validate() ... -
Hugh Dickins authored
Commit 6326fec1 ("mm: Use owner_priv bit for PageSwapCache, valid when PageSwapBacked") aliased PG_swapcache to PG_owner_priv_1 (and depending on PageSwapBacked being true). As a result, the KPF_SWAPCACHE bit in '/proc/kpageflags' should now be synthesized, instead of being shown on unrelated pages which just happen to have PG_owner_priv_1 set. Signed-off-by:
Hugh Dickins <hughd@google.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
stephen hemminger authored
Jiffies is volatile so read it once. Signed-off-by:
Stephen Hemminger <sthemmin@microsoft.com> Acked-by:
Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by:
-
Jiri Pirko authored
This fixes an issue reported by smatch: mlxsw_sp_acl_tcam_chunk_create() warn: impossible condition '(priority == (-1)) => (0-u32max == u64max)' Reported-by:
Or Gerlitz <ogerlitz@mellanox.com> Reported-by:
-
Roopa Prabhu authored
vtbegin should not be NULL in this function, Its already checked by the caller. this should silence the below smatch complaint: net/bridge/br_netlink_tunnel.c:144 br_fill_vlan_tinfo_range() error: we previously assumed 'vtbegin' could be null (see line 130) net/bridge/br_netlink_tunnel.c 129 130 if (vtbegin && vtend && (vtend->vid - vtbegin->vid) > 0) { ^^^^^^^ Check for NULL. Fixes: efa5356b ("bridge: per vlan dst_metadata netlink support") Reported-By: -
Marcelo Ricardo Leitner authored
__packed is considered harmful as it potentially generates code that doesn't perform well and its usage should be avoided as much as possible. This patch drops __packed from all SCTP structures except one, which is sctp_signed_cookie. In there it's required, as per changelog on commit 9834a2bb ("[SCTP]: Fix sctp_cookie alignment in the packet."). After this patch, no alignment changes neither in x86 or x86_64 and no exceptions were noticed during testing on both archs. Code size for SCTP module also didn't change with this patch. Cc: David Miller <davem@davemloft.net> Cc: David Laight <David.Laight@ACULAB.COM> Signed-off-by:
Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by:
-
Xin Long authored
Commit 6f29a130 ("sctp: sctp_addr_id2transport should verify the addr before looking up assoc") invoked sctp_verify_addr to verify the addr. But it didn't check af variable beforehand, once users pass an address with family = 0 through sockopt, sctp_get_af_specific will return NULL and NULL pointer dereference will be caused by af->sockaddr_len. This patch is to fix it by returning NULL if af variable is NULL. Fixes: 6f29a130 ("sctp: sctp_addr_id2transport should verify the addr before looking up assoc") Signed-off-by:
Xin Long <lucien.xin@gmail.com> Acked-by:
-
Nikolay Aleksandrov authored
These checks should go after the attributes have been parsed otherwise we're using tb uninitialized. Fixes: efa5356b ("bridge: per vlan dst_metadata netlink support") Reported-by:
-
Colin Ian King authored
The error check on err is redundant as it is being checked previously each time it has been updated. Remove this redundant check. Detected with CoverityScan, CID#140030("Logically dead code") Signed-off-by:
-
