linux-toradex.git/kernel/bpf/hashtab.c, branch v4.8-rc6

bpf: restore behavior of bpf_map_update_elem

2016-08-07T00:49:19+00:00

The introduction of pre-allocated hash elements inadvertently broke
the behavior of bpf hash maps where users expected to call
bpf_map_update_elem() without considering that the map can be full.
Some programs do:
old_value = bpf_map_lookup_elem(map, key);
if (old_value) {
  ... prepare new_value on stack ...
  bpf_map_update_elem(map, key, new_value);
}
Before pre-alloc the update() for existing element would work even
in 'map full' condition. Restore this behavior.

The above program could have updated old_value in place instead of
update() which would be faster and most programs use that approach,
but sometimes the values are large and the programs use update()
helper to do atomic replacement of the element.
Note we cannot simply update element's value in-place like percpu
hash map does and have to allocate extra num_possible_cpu elements
and use this extra reserve when the map is full.

Fixes: 6c9059817432 ("bpf: pre-allocate hash map elements")
Signed-off-by: Alexei Starovoitov 
Signed-off-by: David S. Miller

bpf: pre-allocate hash map elements

2016-03-08T20:28:31+00:00

If kprobe is placed on spin_unlock then calling kmalloc/kfree from
bpf programs is not safe, since the following dead lock is possible:
kfree->spin_lock(kmem_cache_node->lock)...spin_unlock->kprobe->
bpf_prog->map_update->kmalloc->spin_lock(of the same kmem_cache_node->lock)
and deadlocks.

The following solutions were considered and some implemented, but
eventually discarded
- kmem_cache_create for every map
- add recursion check to slow-path of slub
- use reserved memory in bpf_map_update for in_irq or in preempt_disabled
- kmalloc via irq_work

At the end pre-allocation of all map elements turned out to be the simplest
solution and since the user is charged upfront for all the memory, such
pre-allocation doesn't affect the user space visible behavior.

Since it's impossible to tell whether kprobe is triggered in a safe
location from kmalloc point of view, use pre-allocation by default
and introduce new BPF_F_NO_PREALLOC flag.

While testing of per-cpu hash maps it was discovered
that alloc_percpu(GFP_ATOMIC) has odd corner cases and often
fails to allocate memory even when 90% of it is free.
The pre-allocation of per-cpu hash elements solves this problem as well.

Turned out that bpf_map_update() quickly followed by
bpf_map_lookup()+bpf_map_delete() is very common pattern used
in many of iovisor/bcc/tools, so there is additional benefit of
pre-allocation, since such use cases are must faster.

Since all hash map elements are now pre-allocated we can remove
atomic increment of htab->count and save few more cycles.

Also add bpf_map_precharge_memlock() to check rlimit_memlock early to avoid
large malloc/free done by users who don't have sufficient limits.

Pre-allocation is done with vmalloc and alloc/free is done
via percpu_freelist. Here are performance numbers for different
pre-allocation algorithms that were implemented, but discarded
in favor of percpu_freelist:

1 cpu:
pcpu_ida	2.1M
pcpu_ida nolock	2.3M
bt		2.4M
kmalloc		1.8M
hlist+spinlock	2.3M
pcpu_freelist	2.6M

4 cpu:
pcpu_ida	1.5M
pcpu_ida nolock	1.8M
bt w/smp_align	1.7M
bt no/smp_align	1.1M
kmalloc		0.7M
hlist+spinlock	0.2M
pcpu_freelist	2.0M

8 cpu:
pcpu_ida	0.7M
bt w/smp_align	0.8M
kmalloc		0.4M
pcpu_freelist	1.5M

32 cpu:
kmalloc		0.13M
pcpu_freelist	0.49M

pcpu_ida nolock is a modified percpu_ida algorithm without
percpu_ida_cpu locks and without cross-cpu tag stealing.
It's faster than existing percpu_ida, but not as fast as pcpu_freelist.

bt is a variant of block/blk-mq-tag.c simlified and customized
for bpf use case. bt w/smp_align is using cache line for every 'long'
(similar to blk-mq-tag). bt no/smp_align allocates 'long'
bitmasks continuously to save memory. It's comparable to percpu_ida
and in some cases faster, but slower than percpu_freelist

hlist+spinlock is the simplest free list with single spinlock.
As expeceted it has very bad scaling in SMP.

kmalloc is existing implementation which is still available via
BPF_F_NO_PREALLOC flag. It's significantly slower in single cpu and
in 8 cpu setup it's 3 times slower than pre-allocation with pcpu_freelist,
but saves memory, so in cases where map->max_entries can be large
and number of map update/delete per second is low, it may make
sense to use it.

Signed-off-by: Alexei Starovoitov 
Signed-off-by: David S. Miller

bpf: grab rcu read lock for bpf_percpu_hash_update

2016-02-19T19:37:43+00:00

bpf_percpu_hash_update() expects rcu lock to be held and warns if it's not,
which pointed out a missing rcu read lock.

Fixes: 15a07b338 ("bpf: add lookup/update support for per-cpu hash and array maps")
Signed-off-by: Sasha Levin 
Acked-by: Alexei Starovoitov 
Acked-by: Daniel Borkmann 
Signed-off-by: David S. Miller

bpf: add lookup/update support for per-cpu hash and array maps

2016-02-06T08:34:36+00:00

The functions bpf_map_lookup_elem(map, key, value) and
bpf_map_update_elem(map, key, value, flags) need to get/set
values from all-cpus for per-cpu hash and array maps,
so that user space can aggregate/update them as necessary.

Example of single counter aggregation in user space:
  unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
  long values[nr_cpus];
  long value = 0;

  bpf_lookup_elem(fd, key, values);
  for (i = 0; i < nr_cpus; i++)
    value += values[i];

The user space must provide round_up(value_size, 8) * nr_cpus
array to get/set values, since kernel will use 'long' copy
of per-cpu values to try to copy good counters atomically.
It's a best-effort, since bpf programs and user space are racing
to access the same memory.

Signed-off-by: Alexei Starovoitov 
Signed-off-by: David S. Miller

bpf: introduce BPF_MAP_TYPE_PERCPU_HASH map

2016-02-06T08:34:35+00:00

Introduce BPF_MAP_TYPE_PERCPU_HASH map type which is used to do
accurate counters without need to use BPF_XADD instruction which turned
out to be too costly for high-performance network monitoring.
In the typical use case the 'key' is the flow tuple or other long
living object that sees a lot of events per second.

bpf_map_lookup_elem() returns per-cpu area.
Example:
struct {
  u32 packets;
  u32 bytes;
} * ptr = bpf_map_lookup_elem(&map, &key);
/* ptr points to this_cpu area of the value, so the following
 * increments will not collide with other cpus
 */
ptr->packets ++;
ptr->bytes += skb->len;

bpf_update_elem() atomically creates a new element where all per-cpu
values are zero initialized and this_cpu value is populated with
given 'value'.
Note that non-per-cpu hash map always allocates new element
and then deletes old after rcu grace period to maintain atomicity
of update. Per-cpu hash map updates element values in-place.

Signed-off-by: Alexei Starovoitov 
Signed-off-by: David S. Miller

bpf: hash: use per-bucket spinlock

2015-12-29T20:13:44+00:00

Both htab_map_update_elem() and htab_map_delete_elem() can be
called from eBPF program, and they may be in kernel hot path,
so it isn't efficient to use a per-hashtable lock in this two
helpers.

The per-hashtable spinlock is used for protecting bucket's
hlist, and per-bucket lock is just enough. This patch converts
the per-hashtable lock into per-bucket spinlock, so that
contention can be decreased a lot.

Signed-off-by: Ming Lei 
Acked-by: Daniel Borkmann 
Signed-off-by: David S. Miller

bpf: hash: move select_bucket() out of htab's spinlock

2015-12-29T20:13:44+00:00

The spinlock is just used for protecting the per-bucket
hlist, so it isn't needed for selecting bucket.

Acked-by: Daniel Borkmann 
Signed-off-by: Ming Lei 
Signed-off-by: David S. Miller

bpf: hash: use atomic count

2015-12-29T20:13:43+00:00

Preparing for removing global per-hashtable lock, so
the counter need to be defined as aotmic_t first.

Acked-by: Daniel Borkmann 
Signed-off-by: Ming Lei 
Signed-off-by: David S. Miller

bpf: fix allocation warnings in bpf maps and integer overflow

2015-12-03T04:36:00+00:00

For large map->value_size the user space can trigger memory allocation warnings like:
WARNING: CPU: 2 PID: 11122 at mm/page_alloc.c:2989
__alloc_pages_nodemask+0x695/0x14e0()
Call Trace:
 [<     inline     >] __dump_stack lib/dump_stack.c:15
 [] dump_stack+0x68/0x92 lib/dump_stack.c:50
 [] warn_slowpath_common+0xd9/0x140 kernel/panic.c:460
 [] warn_slowpath_null+0x29/0x30 kernel/panic.c:493
 [<     inline     >] __alloc_pages_slowpath mm/page_alloc.c:2989
 [] __alloc_pages_nodemask+0x695/0x14e0 mm/page_alloc.c:3235
 [] alloc_pages_current+0xee/0x340 mm/mempolicy.c:2055
 [<     inline     >] alloc_pages include/linux/gfp.h:451
 [] alloc_kmem_pages+0x16/0xf0 mm/page_alloc.c:3414
 [] kmalloc_order+0x19/0x60 mm/slab_common.c:1007
 [] kmalloc_order_trace+0x1f/0xa0 mm/slab_common.c:1018
 [<     inline     >] kmalloc_large include/linux/slab.h:390
 [] __kmalloc+0x234/0x250 mm/slub.c:3525
 [<     inline     >] kmalloc include/linux/slab.h:463
 [<     inline     >] map_update_elem kernel/bpf/syscall.c:288
 [<     inline     >] SYSC_bpf kernel/bpf/syscall.c:744

To avoid never succeeding kmalloc with order >= MAX_ORDER check that
elem->value_size and computed elem_size are within limits for both hash and
array type maps.
Also add __GFP_NOWARN to kmalloc(value_size | elem_size) to avoid OOM warnings.
Note kmalloc(key_size) is highly unlikely to trigger OOM, since key_size <= 512,
so keep those kmalloc-s as-is.

Large value_size can cause integer overflows in elem_size and map.pages
formulas, so check for that as well.

Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs")
Reported-by: Dmitry Vyukov 
Signed-off-by: Alexei Starovoitov 
Signed-off-by: David S. Miller

bpf: convert hashtab lock to raw lock

2015-11-02T20:45:43+00:00

When running bpf samples on rt kernel, it reports the below warning:

BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:917
in_atomic(): 1, irqs_disabled(): 128, pid: 477, name: ping
Preemption disabled at:[] kprobe_perf_func+0x30/0x228

CPU: 3 PID: 477 Comm: ping Not tainted 4.1.10-rt8 #4
Hardware name: Freescale Layerscape 2085a RDB Board (DT)
Call trace:
[] dump_backtrace+0x0/0x128
[] show_stack+0x20/0x30
[] dump_stack+0x7c/0xa0
[] ___might_sleep+0x188/0x1a0
[] rt_spin_lock+0x28/0x40
[] htab_map_update_elem+0x124/0x320
[] bpf_map_update_elem+0x40/0x58
[] __bpf_prog_run+0xd48/0x1640
[] trace_call_bpf+0x8c/0x100
[] kprobe_perf_func+0x30/0x228
[] kprobe_dispatcher+0x34/0x58
[] kprobe_handler+0x114/0x250
[] kprobe_breakpoint_handler+0x1c/0x30
[] brk_handler+0x88/0x98
[] do_debug_exception+0x50/0xb8
Exception stack(0xffff808349687460 to 0xffff808349687580)
7460: 4ca2b600 ffff8083 4a3a7000 ffff8083 49687620 ffff8083 0069c5f8 ffff8000
7480: 00000001 00000000 007e0628 ffff8000 496874b0 ffff8083 007e1de8 ffff8000
74a0: 496874d0 ffff8083 0008e04c ffff8000 00000001 00000000 4ca2b600 ffff8083
74c0: 00ba2e80 ffff8000 49687528 ffff8083 49687510 ffff8083 000e5c70 ffff8000
74e0: 00c22348 ffff8000 00000000 ffff8083 49687510 ffff8083 000e5c74 ffff8000
7500: 4ca2b600 ffff8083 49401800 ffff8083 00000001 00000000 00000000 00000000
7520: 496874d0 ffff8083 00000000 00000000 00000000 00000000 00000000 00000000
7540: 2f2e2d2c 33323130 00000000 00000000 4c944500 ffff8083 00000000 00000000
7560: 00000000 00000000 008751e0 ffff8000 00000001 00000000 124e2d1d 00107b77

Convert hashtab lock to raw lock to avoid such warning.

Signed-off-by: Yang Shi 
Acked-by: Daniel Borkmann 
Signed-off-by: David S. Miller