'maps' is a generic storage of different types for sharing data between kernel
and userspace.
The maps are accessed from user space via BPF syscall, which has commands:
- create a map with given type and attributes
fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size)
returns fd or negative error
- lookup key in a given map referenced by fd
err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->value
returns zero and stores found elem into value or negative error
- create or update key/value pair in a given map
err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->value
returns zero or negative error
- find and delete element by key in a given map
err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key
- iterate map elements (based on input key return next_key)
err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size)
using attr->map_fd, attr->key, attr->next_key
- close(fd) deletes the map
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
done as separate commit to ease conflict resolution
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
BPF syscall is a multiplexor for a range of different operations on eBPF.
This patch introduces syscall with single command to create a map.
Next patch adds commands to access maps.
'maps' is a generic storage of different types for sharing data between kernel
and userspace.
Userspace example:
/* this syscall wrapper creates a map with given type and attributes
* and returns map_fd on success.
* use close(map_fd) to delete the map
*/
int bpf_create_map(enum bpf_map_type map_type, int key_size,
int value_size, int max_entries)
{
union bpf_attr attr = {
.map_type = map_type,
.key_size = key_size,
.value_size = value_size,
.max_entries = max_entries
};
return bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
}
'union bpf_attr' is backwards compatible with future extensions.
More details in Documentation/networking/filter.txt and in manpage
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While using a MQ + NETEM setup, I had confirmation that the default
timer migration ( /proc/sys/kernel/timer_migration ) is killing us.
Installing this on a receiver side of a TCP_STREAM test, (NIC has 8 TX
queues) :
EST="est 1sec 4sec"
for ETH in eth1
do
tc qd del dev $ETH root 2>/dev/null
tc qd add dev $ETH root handle 1: mq
tc qd add dev $ETH parent 1:1 $EST netem limit 70000 delay 6ms
tc qd add dev $ETH parent 1:2 $EST netem limit 70000 delay 8ms
tc qd add dev $ETH parent 1:3 $EST netem limit 70000 delay 10ms
tc qd add dev $ETH parent 1:4 $EST netem limit 70000 delay 12ms
tc qd add dev $ETH parent 1:5 $EST netem limit 70000 delay 14ms
tc qd add dev $ETH parent 1:6 $EST netem limit 70000 delay 16ms
tc qd add dev $ETH parent 1:7 $EST netem limit 80000 delay 18ms
tc qd add dev $ETH parent 1:8 $EST netem limit 90000 delay 20ms
done
We can see that timers get migrated into a single cpu, presumably idle
at the time timers are set up.
Then all qdisc dequeues run from this cpu and huge lock contention
happens. This single cpu is stuck in softirq mode and cannot dequeue
fast enough.
39.24% [kernel] [k] _raw_spin_lock
2.65% [kernel] [k] netem_enqueue
1.80% [kernel] [k] netem_dequeue
1.63% [kernel] [k] copy_user_enhanced_fast_string
1.45% [kernel] [k] _raw_spin_lock_bh
By pinning qdisc timers on the cpu running the qdisc, we respect proper
XPS setting and remove this lock contention.
5.84% [kernel] [k] netem_enqueue
4.83% [kernel] [k] _raw_spin_lock
2.92% [kernel] [k] copy_user_enhanced_fast_string
Current Qdiscs that benefit from this change are :
netem, cbq, fq, hfsc, tbf, htb.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tom Herbert says:
====================
net: Eliminate gso_send_check
gso_send_check presents a lot of complexity for what it is being used
for. It seems that there are only two cases where it might be effective:
TCP and UFO paths. In these cases, the gso_send_check function
initializes the TCP or UDP checksum respectively to the pseudo header
checksum so that the checksum computation is appropriately offloaded or
computed in the gso_segment functions. The gso_send_check functions
are only called from dev.c in skb_mac_gso_segment when ip_summed !=
CHECKSUM_PARTIAL (which seems very unlikely in TCP case). We can move
the logic of this into the respective gso_segment functions where the
checksum is initialized if ip_summed != CHECKSUM_PARTIAL.
With the above cases handled, gso_send_check is no longer needed, so
we can remove all uses of it and the fields in the offload callbacks.
With this change, ip_summed in the skb should be preserved though all
the layers of gso_segment calls.
In follow-on patches, we may be able to remove the check setup code in
tcp_gso_segment if we can guarantee that ip_summed will always be
CHECKSUM_PARTIAL (verify all paths and probably add an assert in
tcp_gro_segment).
Tested these patches by:
- netperf TCP_STREAM test with GSO enabled
- Forced ip_summed != CHECKSUM_PARTIAL with above
- Ran UDP_RR with 10000 request size over GRE tunnel. This exercised
UFO path.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The send_check logic was only interesting in cases of TCP offload and
UDP UFO where the checksum needed to be initialized to the pseudo
header checksum. Now we've moved that logic into the related
gso_segment functions so gso_send_check is no longer needed.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In udp[46]_ufo_send_check the UDP checksum initialized to the pseudo
header checksum. We can move this logic into udp[46]_ufo_fragment.
After this change udp[64]_ufo_send_check is a no-op.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In tcp_v[46]_gso_send_check the TCP checksum is initialized to the
pseudo header checksum using __tcp_v[46]_send_check. We can move this
logic into new tcp[46]_gso_segment functions to be done when
ip_summed != CHECKSUM_PARTIAL (ip_summed == CHECKSUM_PARTIAL should be
the common case, possibly always true when taking GSO path). After this
change tcp_v[46]_gso_send_check is no-op.
Signed-off-by: Tom Herbert <therbert@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Beniamino Galvani says:
====================
net: stmmac glue layer for Amlogic Meson SoCs
the Ethernet controller available in Amlogic Meson6 and Meson8 SoCs is
a Synopsys DesignWare MAC IP core, already supported by the stmmac
driver.
These patches add a glue layer to the driver for the platform-specific
settings required by the Amlogic variant.
This has been tested on a Amlogic S802 device with the initial Meson
support submitted by Carlo Caione [1].
[1] http://lwn.net/Articles/612000/
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Add the device tree bindings documentation for the Amlogic Meson
variant of the Synopsys DesignWare MAC.
Signed-off-by: Beniamino Galvani <b.galvani@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The Ethernet controller available in Meson6 and Meson8 SoCs is a
Synopsys DesignWare MAC IP core, already supported by the stmmac
driver.
This glue layer implements some platform-specific settings needed by
the Amlogic variant.
Signed-off-by: Beniamino Galvani <b.galvani@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking fixes from David Miller:
"Here is a quick pull request primarily meant to address the deconfig
fallout from changing SCSI_NETLINK from being used via 'select' to
being used via 'depends'.
I applied a set of 5 patches written by Michal Marek, and then I
carefully audited all of the remaining config files, basically:
1) I scanned every arch config file, and if it mentioned CONFIG_INET
or CONFIG_UNIX, I made sure it had CONFIG_NET=y
2) After that, I scanned every arch config file, and if it did not
have CONFIG_NET=y I made sure it did not reference any networking
config options.
Finally, we have some late breaking wireless fixes in here from John
Linville and co"
[ And there's a sparc bpf fix snuck in too ]
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
sparc: bpf_jit: fix loads from negative offsets
parisc: Update defconfigs which were missing CONFIG_NET.
powerpc: Update defconfigs which were missing CONFIG_NET.
s390: Update defconfigs which were missing CONFIG_NET.
mips: Update some more defconfigs which were missing CONFIG_NET.
sparc: Set CONFIG_NET=y in defconfigs
sh: Set CONFIG_NET=y in defconfigs
powerpc: Set CONFIG_NET=y in defconfigs
parisc: Set CONFIG_NET=y in defconfigs
mips: Set CONFIG_NET=y in defconfigs
brcmfmac: Fix off by one bug in brcmf_count_20mhz_channels()
ath9k: Fix NULL pointer dereference on early irq
net: rfkill: gpio: Fix clock status
NFC: st21nfca: Fix potential depmod dependency cycle
NFC: st21nfcb: Fix depmod dependency cycle
NFC: microread: Potential overflows in microread_target_discovered()
- fix BPF_LD|ABS|IND from negative offsets:
make sure to sign extend lower 32 bits in 64-bit register
before calling C helpers from JITed code, otherwise 'int k'
argument of bpf_internal_load_pointer_neg_helper() function
will be added as large unsigned integer, causing packet size
check to trigger and abort the program.
It's worth noting that JITed code for 'A = A op K' will affect
upper 32 bits differently depending whether K is simm13 or not.
Since small constants are sign extended, whereas large constants
are stored in temp register and zero extended.
That is ok and we don't have to pay a penalty of sign extension
for every sethi, since all classic BPF instructions have 32-bit
semantics and we only need to set correct upper bits when
transitioning from JITed code into C.
- though instructions 'A &= 0' and 'A *= 0' are odd, JIT compiler
should not optimize them out
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
John W. Linville says:
====================
pull request: wireless 2014-09-23
Please consider pulling this one last batch of fixes intended for the 3.17 stream!
For the NFC bits, Samuel says:
"Hopefully not too late for a handful of NFC fixes:
- 2 potential build failures for ST21NFCA and ST21NFCB, triggered by a
depmod dependenyc cycle.
- One potential buffer overflow in the microread driver."
On top of that...
Emil Goode provides a fix for a brcmfmac off-by-one regression which
was introduced in the 3.17 cycle.
Loic Poulain fixes a polarity mismatch for a variable assignment
inside of rfkill-gpio.
Wojciech Dubowik prevents a NULL pointer dereference in ath9k.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit df568d8e ("scsi: Use 'depends' with LIBFC instead of
'select'.") removed what happened to be the only instance of 'select
NET'. Defconfigs that were relying on the select now lack networking
support.
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit df568d8e ("scsi: Use 'depends' with LIBFC instead of
'select'.") removed what happened to be the only instance of 'select
NET'. Defconfigs that were relying on the select now lack networking
support.
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit df568d8e ("scsi: Use 'depends' with LIBFC instead of
'select'.") removed what happened to be the only instance of 'select
NET'. Defconfigs that were relying on the select now lack networking
support.
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit df568d8e ("scsi: Use 'depends' with LIBFC instead of
'select'.") removed what happened to be the only instance of 'select
NET'. Defconfigs that were relying on the select now lack networking
support.
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 5d6be6a5 ("scsi_netlink : Make SCSI_NETLINK dependent on NET
instead of selecting NET") removed what happened to be the only instance
of 'select NET'. Defconfigs that were relying on the select now lack
networking support.
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: sparclinux@vger.kernel.org
Signed-off-by: Michal Marek <mmarek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 5d6be6a5 ("scsi_netlink : Make SCSI_NETLINK dependent on NET
instead of selecting NET") removed what happened to be the only instance
of 'select NET'. Defconfigs that were relying on the select now lack
networking support.
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: linux-sh@vger.kernel.org
Signed-off-by: Michal Marek <mmarek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 5d6be6a5 ("scsi_netlink : Make SCSI_NETLINK dependent on NET
instead of selecting NET") removed what happened to be the only instance
of 'select NET'. Defconfigs that were relying on the select now lack
networking support.
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Michal Marek <mmarek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 5d6be6a5 ("scsi_netlink : Make SCSI_NETLINK dependent on NET
instead of selecting NET") removed what happened to be the only instance
of 'select NET'. Defconfigs that were relying on the select now lack
networking support.
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: linux-parisc@vger.kernel.org
Signed-off-by: Michal Marek <mmarek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 5d6be6a5 ("scsi_netlink : Make SCSI_NETLINK dependent on NET
instead of selecting NET") removed what happened to be the only instance
of 'select NET'. Defconfigs that were relying on the select now lack
networking support.
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: linux-mips@linux-mips.org
Signed-off-by: Michal Marek <mmarek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull one last block fix from Jens Axboe:
"We've had an issue with scsi-mq where probing takes forever. This was
bisected down to the percpu changes for blk_mq_queue_enter(), and the
fact we now suffer an RCU grace period when killing a queue. SCSI
creates and destroys tons of queues, so this let to 10s of seconds of
stalls at boot for some.
Tejun has a real fix for this, but it's too involved for 3.17. So
this is a temporary workaround to expedite the queue killing until we
can fold in the real fix for 3.18 when that merge window opens"
* 'for-linus' of git://git.kernel.dk/linux-block:
blk-mq, percpu_ref: implement a kludge for SCSI blk-mq stall during probe
Alexei Starovoitov
Eric Dumazet
David S. Miller
Tom Herbert
Beniamino Galvani
Linus Torvalds
Michal Marek