[PATCH v2 net-next 5/8] bpf: Add BPF_MAP_GET_FD_BY_ID

;id. In the error path of bpf_map_inc_not_zero(), it may have to call __bpf_map_put(map, false) which does not need to take the map_idr_lock when freeing the map->id. It is currently limited to CAP_SYS_ADMIN which we can consider to lift it in followup patches. Signed-off-by: Martin KaFai L

[PATCH v2 net-next 1/8] bpf: Introduce bpf_prog ID

to the prog_idr. After bpf_prog_select_runtime(), the prog is read-only. Hence, the id is stored in 'struct bpf_prog_aux'. Signed-off-by: Martin KaFai Lau <ka...@fb.com> Acked-by: Alexei Starovoitov <a...@fb.com> Acked-by: Daniel Borkmann <dan...@iogearbox.net> --- include

Re: [PATCH net-next 0/8] Introduce bpf ID

On Tue, May 30, 2017 at 06:35:37PM -0600, David Ahern wrote: > On 5/30/17 6:08 PM, Martin KaFai Lau wrote: > > This patch series: > > 1) Introduce ID for both bpf_prog and bpf_map. > > 2) Add bpf commands to iterate the prog IDs and map > >IDs of the system. >

[PATCH net-next 5/8] bpf: Add BPF_MAP_GET_FD_BY_ID

;id. In the error path of bpf_map_inc_not_zero(), it may have to call __bpf_map_put(map, false) which does not need to take the map_idr_lock when freeing the map->id. It is currently limited to CAP_SYS_ADMIN which we can consider to lift it in followup patches. Signed-off-by: Martin KaFai L

[PATCH net-next 6/8] bpf: Add jited_len to struct bpf_prog

Add jited_len to struct bpf_prog. It will be useful for the struct bpf_prog_info which will be added in the later patch. Signed-off-by: Martin KaFai Lau <ka...@fb.com> Acked-by: Alexei Starovoitov <a...@fb.com> Acked-by: Daniel Borkmann <dan...@iogearbox.net> --- arch/arm64/

[PATCH net-next 2/8] bpf: Introduce bpf_map ID

This patch generates an unique ID for each created bpf_map. The approach is similar to the earlier patch for bpf_prog ID. It is worth to note that the bpf_map's ID and bpf_prog's ID are in two independent ID spaces and both have the same valid range: [1, INT_MAX). Signed-off-by: Martin KaFai Lau

[PATCH net-next 3/8] bpf: Add BPF_(PROG|MAP)_GET_NEXT_ID command

. Signed-off-by: Martin KaFai Lau <ka...@fb.com> Acked-by: Alexei Starovoitov <a...@fb.com> Acked-by: Daniel Borkmann <dan...@iogearbox.net> --- include/uapi/linux/bpf.h | 7 +++ kernel/bpf/syscall.c | 38 ++ 2 files changed, 45 inserti

[PATCH net-next 8/8] bpf: Test for bpf ID

Add test to exercise the bpf_prog/map id generation, bpf_(prog|map)_get_next_id(), bpf_(prog|map)_get_fd_by_id() and bpf_get_obj_info_by_fd(). Signed-off-by: Martin KaFai Lau <ka...@fb.com> Acked-by: Alexei Starovoitov <a...@fb.com> Acked-by: Daniel Borkmann <dan...@iogearbox.

[PATCH net-next 1/8] bpf: Introduce bpf_prog ID

to the prog_idr. After bpf_prog_select_runtime(), the prog is read-only. Hence, the id is stored in 'struct bpf_prog_aux'. Signed-off-by: Martin KaFai Lau <ka...@fb.com> Acked-by: Alexei Starovoitov <a...@fb.com> Acked-by: Daniel Borkmann <dan...@iogearbox.net> --- include

[PATCH net-next 7/8] bpf: Add BPF_OBJ_GET_INFO_BY_FD

the bpf_attr. Signed-off-by: Martin KaFai Lau <ka...@fb.com> Acked-by: Alexei Starovoitov <a...@fb.com> Acked-by: Daniel Borkmann <dan...@iogearbox.net> --- include/linux/filter.h | 2 - include/uapi/linux/bpf.h | 28 kernel/bpf/s

[PATCH net-next 4/8] bpf: Add BPF_PROG_GET_FD_BY_ID

->id. In the error path of bpf_prog_inc_not_zero(), it may have to call __bpf_prog_put(map, false) which does not need to take the prog_idr_lock when freeing the prog->id. It is currently limited to CAP_SYS_ADMIN which we can consider to lift it in followup patches. Signed-off-by: Martin KaF

[PATCH net-next 0/8] Introduce bpf ID

and it is not meant to be a complete list. They can be extended in the future patches. Martin KaFai Lau (8): bpf: Introduce bpf_prog ID bpf: Introduce bpf_map ID bpf: Add BPF_(PROG|MAP)_GET_NEXT_ID command bpf: Add BPF_PROG_GET_FD_BY_ID bpf: Add BPF_MAP_GET_FD_BY_ID bpf: Add

Re: [RFC net-next 0/2] Introduce bpf_prog ID and iteration

On Thu, Apr 27, 2017 at 03:36:59PM +0200, Hannes Frederic Sowa wrote: > It would help a lot if you could pass the prog_id back during program > creation, otherwise it will be kind of difficult to get a hold on which > program is where. ;) Thanks for your feedback :). Make sense. I will look into

Re: [RFC net-next 2/2] bpf: Test for bpf_prog ID and BPF_PROG_GET_NEXT_ID

On Thu, Apr 27, 2017 at 09:23:18AM +0200, Alexander Alemayhu wrote: > On Wed, Apr 26, 2017 at 11:24:49PM -0700, Martin KaFai Lau wrote: > > Add test to exercise the bpf_prog id generation > > and iteration. > > > Could test_prog_id be a function in tools/testing/se

[RFC net-next 1/2] bpf: Introduce bpf_prog ID

The ID is generated by the existing idr_alloc_cyclic(). This patch also adds BPF_PROG_GET_NEXT_ID to allow userspace to iterate all bpf_prog id(s). The API is trying to be consistent with the existing BPF_MAP_GET_NEXT_KEY. Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- include

[RFC net-next 2/2] bpf: Test for bpf_prog ID and BPF_PROG_GET_NEXT_ID

Add test to exercise the bpf_prog id generation and iteration. Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- tools/include/uapi/linux/bpf.h | 6 ++ tools/lib/bpf/bpf.c| 11 tools/lib/bpf/bpf.h| 1 + tools/testing/sel

[RFC net-next 0/2] Introduce bpf_prog ID and iteration

This patchset introduces the bpf_prog ID and a new bpf cmd to iterate all bpf_prog in the system. It is still incomplete. The idea can be extended to bpf_map. Martin KaFai Lau (2): bpf: Introduce bpf_prog ID bpf: Test for bpf_prog ID and BPF_PROG_GET_NEXT_ID include/linux/filter.h

Re: [PATCH v4 net] net: ipv6: regenerate host route if moved to gc list

On Tue, Apr 25, 2017 at 09:17:29AM -0700, David Ahern wrote: [...] > > All of those faults are fixed by regenerating the host route if the > existing one has been moved to the gc list, something that can be > determined by checking if the rt6i_ref counter is 0. Acked-by: Martin K

Re: [PATCH v3 net] net: ipv6: regenerate host route if moved to gc list

On Mon, Apr 24, 2017 at 01:37:00PM -0600, David Ahern wrote: > On 4/24/17 10:39 AM, Eric Dumazet wrote: > > > > Very nice changelog ! > > > Thanks. Given my aggressive brain cell recycling program, I needed to > write down the analysis. > > > > >> diff --git a/net/ipv6/addrconf.c

Re: [PATCH v2 net] net: ipv6: regenerate host route if moved to gc list

On Sat, Apr 22, 2017 at 07:12:34PM -0600, David Ahern wrote: > On 4/22/17 4:00 PM, Martin KaFai Lau wrote: > > On Sat, Apr 22, 2017 at 09:40:37AM -0700, David Ahern wrote: > > [...] > >> diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c > >> index

Re: [PATCH v2 net] net: ipv6: regenerate host route if moved to gc list

On Sat, Apr 22, 2017 at 09:40:37AM -0700, David Ahern wrote: [...] > diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c > index 08f9e8ea7a81..97e86158bbcb 100644 > --- a/net/ipv6/addrconf.c > +++ b/net/ipv6/addrconf.c > @@ -3303,14 +3303,24 @@ static void addrconf_gre_config(struct net_device

Re: [PATCH net] net: ipv6: regenerate host route if moved to gc list

On Fri, Apr 21, 2017 at 04:40:30PM -0700, David Ahern wrote: > Taking down the loopback device wreaks havoc on IPv6 routes. By > extension, taking a VRF device wreaks havoc on its table. > > Dmitry and Andrey both reported heap out-of-bounds reports in the IPv6 > FIB code while running syzkaller

[PATCH net v3] net/mlx5e: Fix race in mlx5e_sw_stats and mlx5e_vport_stats

rom mlx5e_update_vport_counters() v1: Use temp and memcpy Fixes: 9218b44dcc05 ("net/mlx5e: Statistics handling refactoring") Suggested-by: Eric Dumazet <eric.duma...@gmail.com> Suggested-by: Saeed Mahameed <sae...@mellanox.com> Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- drivers/

Re: [PATCH net] net: ipv6: RTF_PCPU should not be settable from userspace

On Thu, Apr 20, 2017 at 04:37:18PM -0700, Cong Wang wrote: > On Thu, Apr 20, 2017 at 3:43 PM, David Ahern wrote: > > > > I scanned the others. It is not clear that others should fail with > > EINVAL. Certainly a mask of unused flags can be added, but to me that is > > on

Re: [PATCH net] net: ipv6: RTF_PCPU should not be settable from userspace

On Thu, Apr 20, 2017 at 04:43:03PM -0600, David Ahern wrote: > On 4/20/17 4:39 PM, Cong Wang wrote: > > On Wed, Apr 19, 2017 at 2:19 PM, David Ahern > > wrote: > >> > >> Fix by checking for the flag and failing with EINVAL. > >> > > > > I am still not sure about this.

Re: [PATCH net v2] net/mlx5e: Fix race in mlx5e_sw_stats and mlx5e_vport_stats

On Thu, Apr 20, 2017 at 08:00:41AM -0700, Eric Dumazet wrote: > On Thu, 2017-04-20 at 07:15 -0700, Martin KaFai Lau wrote: > > > A follow-up patch approach by Gal will be nice. > > Note that I had a similar issue on mlx4. > > Stats are cleared/reset at open time, bu

Re: [PATCH net v2] net/mlx5e: Fix race in mlx5e_sw_stats and mlx5e_vport_stats

On Thu, Apr 20, 2017 at 05:00:13PM +0300, Saeed Mahameed wrote: > On Thu, Apr 20, 2017 at 2:32 AM, Martin KaFai Lau <ka...@fb.com> wrote: > > We have observed a sudden spike in rx/tx_packets and rx/tx_bytes > > reported under /proc/net/dev. There is a race in mlx5e_update

[PATCH net v2] net/mlx5e: Fix race in mlx5e_sw_stats and mlx5e_vport_stats

> Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 7 +-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 66c133757a5e

Re: [RFC PATCH net] net/mlx5e: Race between mlx5e_update_stats() and getting the stats

On Wed, Apr 19, 2017 at 01:24:38PM -0700, Eric Dumazet wrote: > On Wed, 2017-04-19 at 11:29 -0700, Martin KaFai Lau wrote: > > We have observed a sudden spike in rx/tx_packets and rx/tx_bytes > > reported under /proc/net/dev. It seems there is a race in > > mlx5e_up

Re: [PATCH net] net: ipv6: RTF_PCPU should not be settable from userspace

ly inserted route appear > as though it is a per-cpu route. ip6_rt_cache_alloc sees the flag set > and expects rt->dst.from to be set - which it is not since it is not > really a per-cpu copy. The subsequent call to __ip6_dst_alloc then > generates the fault. > > Fix by checking

[RFC PATCH net] net/mlx5e: Race between mlx5e_update_stats() and getting the stats

tries to show what I have suspected and start the discussion. Signed-off-by: Martin KaFai Lau <ka...@fb.com> Cc: Saeed Mahameed <sae...@mellanox.com> --- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 7 +-- drivers/net/ethernet/mellanox/mlx5/core/en_main.c| 3 +++ 2 file

[PATCH net-next 1/6] bpf: lru: Add test_lru_sanity6 for BPF_F_NO_COMMON_LRU

test_lru_sanity3 is not applicable to BPF_F_NO_COMMON_LRU. It just happens to work when PERCPU_FREE_TARGET == 16. This patch: 1) Disable test_lru_sanity3 for BPF_F_NO_COMMON_LRU 2) Add test_lru_sanity6 to test list rotation for the BPF_F_NO_COMMON_LRU map. Signed-off-by: Martin KaFai Lau <

[PATCH net-next 6/6] bpf: lru: Add map-in-map LRU example

962743 (9.96M/s) Notes that the max_entries for the map-in-map LRU test is 126 which is the max_entries for each inner LRU map. 8 processes have been started, so 8 * 126 = 1008 (~10M) which is close to what is used in the BPF_F_NO_COMMON_LRU test. Signed-off-by: Martin KaFai Lau <ka.

[PATCH net-next 0/6] bpf: LRU performance and test-program improvements

The first 4 patches make a few improvements to the LRU tests. Patch 5/6 is to improve the performance of BPF_F_NO_COMMON_LRU map. Patch 6/6 adds an example in using LRU map with map-in-map. Martin KaFai Lau (6): bpf: lru: Add test_lru_sanity6 for BPF_F_NO_COMMON_LRU bpf: lru: Cleanup

[PATCH net-next 3/6] bpf: lru: Refactor LRU map tests in map_perf_test

to nocommon_lru_hash_map to avoid the confusion with percpu_hash_map. Signed-off-by: Martin KaFai Lau <ka...@fb.com> Acked-by: Alexei Starovoitov <a...@kernel.org> Acked-by: Daniel Borkmann <dan...@iogearbox.net> --- samples/bpf/map_perf_test_kern.c | 43 +++

[PATCH net-next 5/6] bpf: lru: Lower the PERCPU_NR_SCANS from 16 to 4

0k.a0_01.out 4 1 nr_misses: 67036 (Before) vs 67031 (After) Signed-off-by: Martin KaFai Lau <ka...@fb.com> Acked-by: Alexei Starovoitov <a...@kernel.org> Acked-by: Daniel Borkmann <dan...@iogearbox.net> --- kernel/bpf/bpf_lru_list.c | 2 +- tools/testing/se

[PATCH net-next 4/6] bpf: Allow bpf sample programs (*_user.c) to change bpf_map_def

the max_entries as a cmdline arg and then configure the bpf_map_def during runtime. This patch adds two cmdline args. One is to configure the map's max_entries. Another is to configure the max_cnt which controls how many times a syscall is called. Signed-off-by: Martin KaFai Lau <ka...@fb.com>

[PATCH net-next 2/6] bpf: lru: Cleanup test_lru_map.c

This patch does the following cleanup on test_lru_map.c 1) Fix indentation (Replace spaces by tabs) 2) Remove redundant BPF_F_NO_COMMON_LRU test 3) Simplify some comments Signed-off-by: Martin KaFai Lau <ka...@fb.com> Acked-by: Alexei Starovoitov <a...@kernel.org> Acked-by: Daniel B

[PATCH net-next 2/4] bpf: Add array of maps support

s not depend on the outer_map. The inner_map_fd is merely used to initialize the inner_map_meta of the outer_map. Also, for the outer_map: * It allows element update and delete from syscall * It allows element lookup from bpf_prog The above is similar to the current fd_array pattern. Signed-off-by:

[PATCH net-next 0/4] bpf: Add map-in-map support

This patchset adds map-in-map support (map->map). One use case is the (vips -> webservers) in the L4 load balancer so that different vips can be backed by different set of webservers. Please refer to the individual commit log for details. Martin KaFai Lau (4): bpf: Fix and simplific

[PATCH net-next 4/4] bpf: Add tests for map-in-map

Test cases for array of maps and hash of maps. Signed-off-by: Martin KaFai Lau <ka...@fb.com> Acked-by: Alexei Starovoitov <a...@kernel.org> --- samples/bpf/Makefile| 4 + samples/bpf/bpf_helpers.h | 1 + samples/bp

[PATCH net-next 1/4] bpf: Fix and simplifications on inline map lookup

: 1. Calculate elem_size from map->value_size. It removes the need for 'struct bpf_array' which makes the later map-in-map implementation easier. 2. Remove the 'elem_size == 1' test Fixes: 81ed18ab3098 ("bpf: add helper inlining infra and optimize map_array lookup") Signed

[PATCH net-next 3/4] bpf: Add hash of maps support

e without disallowing BPF_PROG_TYPE_PERF_EVENT from using map-in-map first. Signed-off-by: Martin KaFai Lau <ka...@fb.com> Acked-by: Alexei Starovoitov <a...@kernel.org> Acked-by: Daniel Borkmann <dan...@iogearbox.net> --- include/linux/bpf.h | 2 + include/uapi/linux/bpf.h |

Re: [Patch net v3] ipv6: check for ip6_null_entry in __ip6_del_rt_siblings()

On Wed, Mar 01, 2017 at 04:07:38PM -0800, David Ahern wrote: > On 3/1/17 3:16 PM, Martin KaFai Lau wrote: > > [ An unrelated topic. I wonder ip -6 r del xyz::/0 would delete > > the gateway route...] > > a very related question ... > > ip -6 r del x::/0 comes down to

Re: [Patch net v3] ipv6: check for ip6_null_entry in __ip6_del_rt_siblings()

On Mon, Feb 27, 2017 at 04:14:04PM -0800, David Ahern wrote: > On 2/27/17 4:07 PM, Cong Wang wrote: > > Andrey reported a NULL pointer deref bug in ipv6_route_ioctl() > > -> ip6_route_del() -> __ip6_del_rt_siblings() code path. This is > > because ip6_null_entry is returned in this path since

[PATCH net] bpf: Fix bpf_xdp_event_output

itov <a...@kernel.org> Cc: Daniel Borkmann <dan...@iogearbox.net> Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- net/core/filter.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index e466e0040137..ebaeaf2e46e8 10

[PATCH net v2 1/2] mlx4: Fix memory leak after mlx4_en_update_priv()

e_tx; 2153} 2154} Fixes: ec25bc04ed8e ("net/mlx4_en: Add resilience in low memory systems") Cc: Eugenia Emantayev <euge...@mellanox.com> Cc: Saeed Mahameed <sae...@mellanox.com> Cc: Tariq Toukan <tar...@mellanox.com> Signed-off-by: Martin KaFai La

[PATCH net v2 2/2] mlx4: xdp_prog becomes inactive after ethtool '-L' or '-G'

pport for fast rx drop bpf program") Cc: Brenden Blanco <bbla...@plumgrid.com> Cc: Saeed Mahameed <sae...@mellanox.com> Cc: Tariq Toukan <tar...@mellanox.com> Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 4 ++--

[PATCH net v2 0/2] mlx4: Misc bug fixes after reinitializing queues

This patchset fixes misc bugs after reinitializing queues (e.g. by ethtool -L). v2: * Add another fix to mem leak in tx_ring[t] and tx_cq[t] * In mlx4_en_try_alloc_resources(), move all xdp_prog logic after calling mlx4_en_alloc_resources() Martin KaFai Lau (2): mlx4: Fix memory leak after

Re: [PATCH net] mlx4: xdp_prog becomes inactive after ethtool '-L' or '-G'

On Mon, Jan 30, 2017 at 07:18:28PM +0200, Tariq Toukan wrote: > Hi Martin, > > Thanks for your patch. > > It looks good to me, in general. > I just have one small comment below. Thanks for your feedback and sorry for the delay. > > On 28/01/2017 9:40 AM, Martin KaFai

Re: [PATCH net] mlx4: xdp_prog becomes inactive after ethtool '-L' or '-G'

On Tue, Jan 31, 2017 at 01:11:40PM -0500, David Miller wrote: > From: Tariq Toukan > Date: Mon, 30 Jan 2017 19:18:28 +0200 > > > It looks good to me, in general. > > I just have one small comment below. > > Martin, please address Tariq's feedback. Sorry for the delay. I am

[PATCH net] mlx4: xdp_prog becomes inactive after ethtool '-L' or '-G'

pport for fast rx drop bpf program") Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 4 +- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 52 - drivers/net/ethernet/mellanox/mlx4/mlx4_en.h| 3 +- 3 f

[PATCH net-next v2] net/mlx5e: Support bpf_xdp_adjust_head()

moved from en_main.c to en.h. MLX5E_HW2SW_MTU is also moved to en.h for symmetric reason but it is not a must. v2: - Keep the xdp specific logic in mlx5e_xdp_handle() - Update dma_len after the sanity checks in mlx5e_xmit_xdp_frame() Signed-off-by: Martin KaFai Lau <ka...@fb.com> ---

[PATCH] bpf: Fix test_lru_sanity5() in test_lru_map.c

989f ("bpf: Add tests for the LRU bpf_htab") Reported-by: Daniel Borkmann <dan...@iogearbox.net> Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- tools/testing/selftests/bpf/test_lru_map.c | 53 +++--- 1 file changed, 27 insertions(+), 26 deletion

Re: [PATCH net-next] net/mlx5e: Support bpf_xdp_adjust_head()

On Fri, Jan 13, 2017 at 03:58:46PM +0200, Saeed Mahameed wrote: > >> > @@ -680,7 +687,7 @@ static inline void mlx5e_xmit_xdp_frame(struct > >> > mlx5e_rq *rq, > >> > memset(wqe, 0, sizeof(*wqe)); > >> > > >> > /* copy the inline part */ > >> > -

[PATCH net-next] net/mlx5e: Support bpf_xdp_adjust_head()

moved from en_main.c to en.h. MLX5E_HW2SW_MTU is also moved to en.h for symmetric reason but it is not a must. Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 4 ++ drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 18 +++

Re: [PATCH net-next] bpf: Remove unused but set variable in __bpf_lru_list_shrink_inactive()

first_node’ set but > not used [-Wunused-but-set-variable] > > Cc: Martin KaFai Lau <ka...@fb.com> > Signed-off-by: Tobias Klauser <tklau...@distanz.ch> > --- > kernel/bpf/bpf_lru_list.c | 3 +-- > 1 file changed, 1 insertion(+), 2 deletions(-) > > diff --git a/kernel/

Re: [PATCH net-next] bpf: Remove unused but set variable in __bpf_lru_list_shrink_inactive()

t; building with 'W=1': > > > > kernel/bpf/bpf_lru_list.c:216:41: warning: variable ‘first_node’ set but > > not used [-Wunused-but-set-variable] > > > > Cc: Martin KaFai Lau <ka...@fb.com> > > Signed-off-by: Tobias Klauser <tklau...@distanz.ch> > >

Re: [PATCH net-next] bpf: Make unnecessarily global functions static

ru_list.c:577:6: warning: no previous prototype for > > ‘bpf_percpu_lru_populate’ [-Wmissing-prototypes] > > > > Cc: Martin KaFai Lau <ka...@fb.com> > > Signed-off-by: Tobias Klauser <tklau...@distanz.ch> > > Acked-by: Alexei Starovoitov <a...@kernel.org> Thanks for the patch. Acked-by: Martin KaFai Lau <ka...@fb.com>

Re: [PATCH net v2] mlx4: Return EOPNOTSUPP instead of ENOTSUPP

On Tue, Jan 10, 2017 at 10:04:55PM +0200, Saeed Mahameed wrote: > On Tue, Jan 10, 2017 at 7:41 PM, Martin KaFai Lau <ka...@fb.com> wrote: > > In commit b45f0674b997 ("mlx4: xdp: Allow raising MTU up to one page minus > > eth and vlan hdrs"), > > it chan

Re: [PATCH net] mlx4: Return EOPNOTSUPP instead of ENOTSUPP

On Tue, Jan 10, 2017 at 03:43:39PM +0300, Sergei Shtylyov wrote: > Hello! > > On 01/10/2017 01:13 AM, Martin KaFai Lau wrote: > > >In commit b45f0674b997 ("mlx4: xdp: Allow raising MTU up to one page minus > >eth and vlan hdrs"), > >it changed ENOTSUPP to

[PATCH net v2] mlx4: Return EOPNOTSUPP instead of ENOTSUPP

In commit b45f0674b997 ("mlx4: xdp: Allow raising MTU up to one page minus eth and vlan hdrs"), it changed EOPNOTSUPP to ENOTSUPP by mistake. This patch fixes it. Fixes: b45f0674b997 ("mlx4: xdp: Allow raising MTU up to one page minus eth and vlan hdrs") Signed-off-by:

[PATCH net] mlx4: Return EOPNOTSUPP instead of ENOTSUPP

In commit b45f0674b997 ("mlx4: xdp: Allow raising MTU up to one page minus eth and vlan hdrs"), it changed ENOTSUPP to EOPNOTSUPP by mistake. This patch fixes it. Fixes: b45f0674b997 ("mlx4: xdp: Allow raising MTU up to one page minus eth and vlan hdrs") Signed-off-by:

Re: mlx4: Bug in XDP_TX + 16 rx-queues

On Tue, Dec 20, 2016 at 02:02:05PM +0200, Tariq Toukan wrote: > Thanks Martin, nice catch! > > > On 20/12/2016 1:37 AM, Martin KaFai Lau wrote: > >Hi Tariq, > > > >On Sat, Dec 17, 2016 at 02:18:03AM -0800, Martin KaFai Lau wrote: > >>Hi All, > >>

Re: mlx4: Bug in XDP_TX + 16 rx-queues

Hi Tariq, On Sat, Dec 17, 2016 at 02:18:03AM -0800, Martin KaFai Lau wrote: > Hi All, > > I have been debugging with XDP_TX and 16 rx-queues. > > 1) When 16 rx-queues is used and an XDP prog is doing XDP_TX, > it seems that the packet cannot be XDP_TX out if the pkt >

Re: mlx4: Bug in XDP_TX + 16 rx-queues

On Sun, Dec 18, 2016 at 12:31:30PM +0200, Tariq Toukan wrote: > Hi Martin, > > > On 17/12/2016 12:18 PM, Martin KaFai Lau wrote: > >Hi All, > > > >I have been debugging with XDP_TX and 16 rx-queues. > > > >1) When 16 rx-queues is used and an XDP prog is

mlx4: Bug in XDP_TX + 16 rx-queues

Hi All, I have been debugging with XDP_TX and 16 rx-queues. 1) When 16 rx-queues is used and an XDP prog is doing XDP_TX, it seems that the packet cannot be XDP_TX out if the pkt is received from some particular CPUs (/rx-queues). 2) If 8 rx-queues is used, it does not have problem. 3) The 16

[PATCH v4 net-next 0/4]: Allow head adjustment in XDP prog

ead() in patch 1 2. Ensure no less than ETH_HLEN data in bpf_xdp_adjust_head() in patch 1 3. Some clarifications in commit log messages of patch 2 and 3 Thanks, Martin Martin KaFai Lau (4): bpf: xdp: Allow head adjustment in XDP prog mlx4: xdp: Allow raising MTU up to one page minus eth and vlan h

[PATCH v4 net-next 4/4] bpf: xdp: Add XDP example for head adjustment

rgs of the user prog. Acked-by: Alexei Starovoitov <a...@kernel.org> Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- samples/bpf/Makefile | 4 + samples/bpf/bpf_helpers.h| 2 + samples/bpf/bpf_load.c | 94 + samples

[PATCH v4 net-next 2/4] mlx4: xdp: Allow raising MTU up to one page minus eth and vlan hdrs

this patch is doing. It will be useful in the next patch which allows XDP program to extend the packet by adding new header(s). Note: In the earlier XDP patches, there is already existing guard to ensure the page/pkt scheme only applies when XDP is active in mlx4. Signed-off-by: Martin KaFai Lau <

[PATCH v4 net-next 1/4] bpf: xdp: Allow head adjustment in XDP prog

on skb. This patch adds one "xdp_adjust_head" bit to bpf_prog for the XDP-capable driver to check if the XDP prog requires bpf_xdp_adjust_head() support. The driver can then decide to error out during XDP_SETUP_PROG. Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- arch/powerpc/ne

[PATCH v4 net-next 3/4] mlx4: xdp: Reserve headroom for receiving packet when XDP prog is active

Reserve XDP_PACKET_HEADROOM for packet and enable bpf_xdp_adjust_head() support. This patch only affects the code path when XDP is active. After testing, the tx_dropped counter is incremented if the xdp_prog sends more than wire MTU. Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- d

Re: [PATCH v3 net-next 1/4] bpf: xdp: Allow head adjustment in XDP prog

On Wed, Dec 07, 2016 at 08:37:58AM -0800, Alexei Starovoitov wrote: > On Wed, Dec 07, 2016 at 11:41:12AM +, Jakub Kicinski wrote: > > > I see nothing wrong if this is exposed/made visible in the usual way > > > through > > > ethtool -k as well. I guess at least that would be the expected way

[PATCH v3 net-next 1/4] bpf: xdp: Allow head adjustment in XDP prog

g> Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- arch/powerpc/net/bpf_jit_comp64.c | 4 ++-- arch/s390/net/bpf_jit_comp.c | 2 +- arch/x86/net/bpf_jit_comp.c| 2 +- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 3 +++

[PATCH v3 net-next 4/4] bpf: xdp: Add XDP example for head adjustment

rgs of the user prog. Acked-by: Alexei Starovoitov <a...@kernel.org> Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- samples/bpf/Makefile | 4 + samples/bpf/bpf_helpers.h | 2 + samples/bpf/bpf_load.c| 94 ++ samples/bpf/bpf_load.h

[PATCH v3 net-next 3/4] mlx4: xdp: Reserve headroom for receiving packet when XDP prog is active

Reserve XDP_PACKET_HEADROOM for packet and enable bpf_xdp_adjust_head() support. This patch only affects the code path when XDP is active. After testing, the tx_dropped counter is incremented if the xdp_prog sends more than wire MTU. Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- d

[PATCH v3 net-next 0/4]: Allow head adjustment in XDP prog

3of4 v2: 1. Make a variable name change in bpf_xdp_adjust_head() in patch 1 2. Ensure no less than ETH_HLEN data in bpf_xdp_adjust_head() in patch 1 3. Some clarifications in commit log messages of patch 2 and 3 Thanks, Martin Martin KaFai Lau (4): bpf: xdp: Allow head adjustment in XDP prog

[PATCH v3 net-next 2/4] mlx4: xdp: Allow raising MTU up to one page minus eth and vlan hdrs

this patch is doing. It will be useful in the next patch which allows XDP program to extend the packet by adding new header(s). Note: In the earlier XDP patches, there is already existing guard to ensure the page/pkt scheme only applies when XDP is active in mlx4. Signed-off-by: Martin KaFai Lau <

Re: [PATCH v2 net-next 3/4] mlx4: xdp: Reserve headroom for receiving packet when XDP prog is active

On Tue, Dec 06, 2016 at 11:40:19PM +0200, Saeed Mahameed wrote: > On Tue, Dec 6, 2016 at 8:27 PM, Martin KaFai Lau <ka...@fb.com> wrote: > > On Tue, Dec 06, 2016 at 06:50:47PM +0200, Saeed Mahameed wrote: > >> On Mon, Dec 5, 2016 at 9:55 PM, Martin KaFai Lau <ka...@f

Re: [PATCH v2 net-next 1/4] bpf: xdp: Allow head adjustment in XDP prog

On Tue, Dec 06, 2016 at 09:35:31AM -0800, John Fastabend wrote: > On 16-12-03 07:17 PM, Martin KaFai Lau wrote: > > This patch allows XDP prog to extend/remove the packet > > data at the head (like adding or removing header). It is > > done by adding a new XDP helpe

Re: [PATCH v2 net-next 3/4] mlx4: xdp: Reserve headroom for receiving packet when XDP prog is active

On Tue, Dec 06, 2016 at 06:50:47PM +0200, Saeed Mahameed wrote: > On Mon, Dec 5, 2016 at 9:55 PM, Martin KaFai Lau <ka...@fb.com> wrote: > > On Mon, Dec 05, 2016 at 02:54:06AM +0200, Saeed Mahameed wrote: > >> On Sun, Dec 4, 2016 at 5:17 AM, Martin KaFai Lau <ka...@fb

Re: [PATCH v2 net-next 3/4] mlx4: xdp: Reserve headroom for receiving packet when XDP prog is active

On Mon, Dec 05, 2016 at 02:54:06AM +0200, Saeed Mahameed wrote: > On Sun, Dec 4, 2016 at 5:17 AM, Martin KaFai Lau <ka...@fb.com> wrote: > > Reserve XDP_PACKET_HEADROOM and honor bpf_xdp_adjust_head() > > when XDP prog is active. This patch only affects the code > &

Re: [PATCH net-next 2/4] mlx4: xdp: Allow raising MTU up to one page minus eth and vlan hdrs

On Fri, Dec 02, 2016 at 04:07:09PM -0800, Rick Jones wrote: > On 12/02/2016 03:23 PM, Martin KaFai Lau wrote: > >When XDP prog is attached, it is currently limiting > >MTU to be FRAG_SZ0 - ETH_HLEN - (2 * VLAN_HLEN) which is 1514 > >in x86. > > > >AFAICT, since

[PATCH v2 net-next 3/4] mlx4: xdp: Reserve headroom for receiving packet when XDP prog is active

Reserve XDP_PACKET_HEADROOM and honor bpf_xdp_adjust_head() when XDP prog is active. This patch only affects the code path when XDP is active. Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 17 +++-- drivers/net/ethernet/me

[PATCH v2 net-next 4/4] bpf: xdp: Add XDP example for head adjustment

rgs of the user prog. Acked-by: Alexei Starovoitov <a...@kernel.org> Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- samples/bpf/Makefile | 4 + samples/bpf/bpf_helpers.h | 2 + samples/bpf/bpf_load.c| 94 ++ samples/bpf/bpf_load.h

[PATCH v2 net-next 0/4]: Allow head adjustment in XDP prog

This series adds a helper to allow head adjusting in XDP prog. mlx4 driver has been modified to support this feature. An example is written to encapsulate a packet with an IPv4/v6 header and then XDP_TX it out. v2: 1. Make a variable name change in bpf_xdp_adjust_head() in patch 1 2. Ensure no

[PATCH v2 net-next 1/4] bpf: xdp: Allow head adjustment in XDP prog

on skb. Acked-by: Alexei Starovoitov <a...@kernel.org> Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- arch/powerpc/net/bpf_jit_comp64.c | 4 ++-- arch/s390/net/bpf_jit_comp.c | 2 +- arch/x86/net/bpf_jit_comp.c | 2 +- include/linux/filter.h| 2 +- includ

[PATCH v2 net-next 2/4] mlx4: xdp: Allow raising MTU up to one page minus eth and vlan hdrs

this patch is doing. It will be useful in the next patch which allows XDP program to extend the packet by adding new header(s). Note: In the earlier XDP patches, there is already existing guard to ensure the page/pkt scheme only applies when XDP is active in mlx4. Signed-off-by: Martin KaFai Lau <

Re: [PATCH net-next 1/4] bpf: xdp: Allow head adjustment in XDP prog

On Sat, Dec 03, 2016 at 04:24:13PM +0100, Jesper Dangaard Brouer wrote: > On Fri, 2 Dec 2016 15:23:30 -0800 > Martin KaFai Lau <ka...@fb.com> wrote: > > > -bool bpf_helper_changes_skb_data(void *func) > > +BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, off

Re: [PATCH net-next 1/4] bpf: xdp: Allow head adjustment in XDP prog

On Sat, Dec 03, 2016 at 01:22:05AM +0100, Daniel Borkmann wrote: > On 12/03/2016 12:23 AM, Martin KaFai Lau wrote: > >This patch allows XDP prog to extend/remove the packet > >data at the head (like adding or removing header). It is > >done by adding a new XDP helpe

Re: [PATCH net-next 2/4] mlx4: xdp: Allow raising MTU up to one page minus eth and vlan hdrs

On Fri, Dec 02, 2016 at 06:15:26PM -0800, Eric Dumazet wrote: > On Fri, 2016-12-02 at 16:53 -0800, Alexei Starovoitov wrote: > > On 12/2/16 4:38 PM, Eric Dumazet wrote: > > > On Fri, 2016-12-02 at 15:23 -0800, Martin KaFai Lau wrote: > > >> When XDP prog is atta

[PATCH net-next 3/4] mlx4: xdp: Reserve headroom for receiving packet when XDP prog is active

Reserve XDP_PACKET_HEADROOM when XDP prog is active. Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 17 +++-- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 23 +-- drivers/net/ethernet/mellanox/mlx4/e

[PATCH net-next 1/4] bpf: xdp: Allow head adjustment in XDP prog

on skb. Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- arch/powerpc/net/bpf_jit_comp64.c | 4 ++-- arch/s390/net/bpf_jit_comp.c | 2 +- arch/x86/net/bpf_jit_comp.c | 2 +- include/linux/filter.h| 2 +- include/uapi/linux/bpf.h | 11 ++- kernel/bpf/

[PATCH net-next 2/4] mlx4: xdp: Allow raising MTU up to one page minus eth and vlan hdrs

. It will be useful in the next patch which allows XDP program to extend the packet by adding new header(s). Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 28 +++- drivers/net/ethernet/mellanox/mlx4/en_rx.c

[PATCH net-next 4/4] bpf: xdp: Add XDP example for head adjustment

rgs of the user prog. Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- samples/bpf/Makefile | 4 + samples/bpf/bpf_helpers.h | 2 + samples/bpf/bpf_load.c| 94 ++ samples/bpf/bpf_load.h| 1 + samples/bpf/xdp1_user.c

[PATCH net-next 0/4]: Allow head adjustment in XDP prog

This series adds a helper to allow head adjustment in XDP prog. mlx4 driver has been modified to support this feature. An example is written to encapsulate a packet with an IPv4/v6 header and then XDP_TX it out. Thanks, --Martin

Re: linux-next: build warning after merge of the net-next tree

On Wed, Nov 16, 2016 at 11:36:47AM +1100, Stephen Rothwell wrote: > Hi all, > > After merging the net-next tree, today's linux-next build (x86_64 > allmodconfig) produced this warning: > > kernel/bpf/bpf_lru_list.c: In function > '__bpf_lru_list_rotate_inactive.isra.3': >

[PATCH net-next] bpf: Fix compilation warning in __bpf_lru_list_rotate_inactive

ile() loop which must have >=1 iterations. This patch initializes next to get rid of the compiler warning. Fixes: 3a08c2fd7634 ("bpf: LRU List") Reported-by: David Miller <da...@davemloft.net> Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- kernel/bpf/bpf_lru_list.c | 2 +-

Re: [PATCH v2 net-next 0/6] bpf: LRU map

On Tue, Nov 15, 2016 at 11:59:24AM -0500, David Miller wrote: > From: David Miller <da...@redhat.com> > Date: Tue, 15 Nov 2016 11:51:23 -0500 (EST) > > > From: Martin KaFai Lau <ka...@fb.com> > > Date: Fri, 11 Nov 2016 10:55:05 -0800 > > > >

[PATCH v2 net-next 6/6] bpf: Add tests for the LRU bpf_htab

t 32 $i | awk '{r += $3}END{print r " updates"}'; done 1 cpus: 2896553 updates 4 cpus: 9766395 updates 8 cpus: 17460553 updates Signed-off-by: Martin KaFai Lau <ka...@fb.com> --- samples/bpf/Makefile | 2 + samples/bpf/map_perf_test_kern.c

<    1   2   3   4   5   6   7   8   >