mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-17 09:14:19 +08:00
d83525ca62
Introduce 'struct bpf_spin_lock' and bpf_spin_lock/unlock() helpers to let
bpf program serialize access to other variables.
Example:
struct hash_elem {
int cnt;
struct bpf_spin_lock lock;
};
struct hash_elem * val = bpf_map_lookup_elem(&hash_map, &key);
if (val) {
bpf_spin_lock(&val->lock);
val->cnt++;
bpf_spin_unlock(&val->lock);
}
Restrictions and safety checks:
- bpf_spin_lock is only allowed inside HASH and ARRAY maps.
- BTF description of the map is mandatory for safety analysis.
- bpf program can take one bpf_spin_lock at a time, since two or more can
cause dead locks.
- only one 'struct bpf_spin_lock' is allowed per map element.
It drastically simplifies implementation yet allows bpf program to use
any number of bpf_spin_locks.
- when bpf_spin_lock is taken the calls (either bpf2bpf or helpers) are not allowed.
- bpf program must bpf_spin_unlock() before return.
- bpf program can access 'struct bpf_spin_lock' only via
bpf_spin_lock()/bpf_spin_unlock() helpers.
- load/store into 'struct bpf_spin_lock lock;' field is not allowed.
- to use bpf_spin_lock() helper the BTF description of map value must be
a struct and have 'struct bpf_spin_lock anyname;' field at the top level.
Nested lock inside another struct is not allowed.
- syscall map_lookup doesn't copy bpf_spin_lock field to user space.
- syscall map_update and program map_update do not update bpf_spin_lock field.
- bpf_spin_lock cannot be on the stack or inside networking packet.
bpf_spin_lock can only be inside HASH or ARRAY map value.
- bpf_spin_lock is available to root only and to all program types.
- bpf_spin_lock is not allowed in inner maps of map-in-map.
- ld_abs is not allowed inside spin_lock-ed region.
- tracing progs and socket filter progs cannot use bpf_spin_lock due to
insufficient preemption checks
Implementation details:
- cgroup-bpf class of programs can nest with xdp/tc programs.
Hence bpf_spin_lock is equivalent to spin_lock_irqsave.
Other solutions to avoid nested bpf_spin_lock are possible.
Like making sure that all networking progs run with softirq disabled.
spin_lock_irqsave is the simplest and doesn't add overhead to the
programs that don't use it.
- arch_spinlock_t is used when its implemented as queued_spin_lock
- archs can force their own arch_spinlock_t
- on architectures where queued_spin_lock is not available and
sizeof(arch_spinlock_t) != sizeof(__u32) trivial lock is used.
- presence of bpf_spin_lock inside map value could have been indicated via
extra flag during map_create, but specifying it via BTF is cleaner.
It provides introspection for map key/value and reduces user mistakes.
Next steps:
- allow bpf_spin_lock in other map types (like cgroup local storage)
- introduce BPF_F_LOCK flag for bpf_map_update() syscall and helper
to request kernel to grab bpf_spin_lock before rewriting the value.
That will serialize access to map elements.
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
254 lines
4.8 KiB
Plaintext
254 lines
4.8 KiB
Plaintext
#
|
|
# The ARCH_INLINE foo is necessary because select ignores "depends on"
|
|
#
|
|
config ARCH_INLINE_SPIN_TRYLOCK
|
|
bool
|
|
|
|
config ARCH_INLINE_SPIN_TRYLOCK_BH
|
|
bool
|
|
|
|
config ARCH_INLINE_SPIN_LOCK
|
|
bool
|
|
|
|
config ARCH_INLINE_SPIN_LOCK_BH
|
|
bool
|
|
|
|
config ARCH_INLINE_SPIN_LOCK_IRQ
|
|
bool
|
|
|
|
config ARCH_INLINE_SPIN_LOCK_IRQSAVE
|
|
bool
|
|
|
|
config ARCH_INLINE_SPIN_UNLOCK
|
|
bool
|
|
|
|
config ARCH_INLINE_SPIN_UNLOCK_BH
|
|
bool
|
|
|
|
config ARCH_INLINE_SPIN_UNLOCK_IRQ
|
|
bool
|
|
|
|
config ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE
|
|
bool
|
|
|
|
|
|
config ARCH_INLINE_READ_TRYLOCK
|
|
bool
|
|
|
|
config ARCH_INLINE_READ_LOCK
|
|
bool
|
|
|
|
config ARCH_INLINE_READ_LOCK_BH
|
|
bool
|
|
|
|
config ARCH_INLINE_READ_LOCK_IRQ
|
|
bool
|
|
|
|
config ARCH_INLINE_READ_LOCK_IRQSAVE
|
|
bool
|
|
|
|
config ARCH_INLINE_READ_UNLOCK
|
|
bool
|
|
|
|
config ARCH_INLINE_READ_UNLOCK_BH
|
|
bool
|
|
|
|
config ARCH_INLINE_READ_UNLOCK_IRQ
|
|
bool
|
|
|
|
config ARCH_INLINE_READ_UNLOCK_IRQRESTORE
|
|
bool
|
|
|
|
|
|
config ARCH_INLINE_WRITE_TRYLOCK
|
|
bool
|
|
|
|
config ARCH_INLINE_WRITE_LOCK
|
|
bool
|
|
|
|
config ARCH_INLINE_WRITE_LOCK_BH
|
|
bool
|
|
|
|
config ARCH_INLINE_WRITE_LOCK_IRQ
|
|
bool
|
|
|
|
config ARCH_INLINE_WRITE_LOCK_IRQSAVE
|
|
bool
|
|
|
|
config ARCH_INLINE_WRITE_UNLOCK
|
|
bool
|
|
|
|
config ARCH_INLINE_WRITE_UNLOCK_BH
|
|
bool
|
|
|
|
config ARCH_INLINE_WRITE_UNLOCK_IRQ
|
|
bool
|
|
|
|
config ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
|
|
bool
|
|
|
|
config UNINLINE_SPIN_UNLOCK
|
|
bool
|
|
|
|
#
|
|
# lock_* functions are inlined when:
|
|
# - DEBUG_SPINLOCK=n and GENERIC_LOCKBREAK=n and ARCH_INLINE_*LOCK=y
|
|
#
|
|
# trylock_* functions are inlined when:
|
|
# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
|
|
#
|
|
# unlock and unlock_irq functions are inlined when:
|
|
# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
|
|
# or
|
|
# - DEBUG_SPINLOCK=n and PREEMPT=n
|
|
#
|
|
# unlock_bh and unlock_irqrestore functions are inlined when:
|
|
# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
|
|
#
|
|
|
|
if !DEBUG_SPINLOCK
|
|
|
|
config INLINE_SPIN_TRYLOCK
|
|
def_bool y
|
|
depends on ARCH_INLINE_SPIN_TRYLOCK
|
|
|
|
config INLINE_SPIN_TRYLOCK_BH
|
|
def_bool y
|
|
depends on ARCH_INLINE_SPIN_TRYLOCK_BH
|
|
|
|
config INLINE_SPIN_LOCK
|
|
def_bool y
|
|
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK
|
|
|
|
config INLINE_SPIN_LOCK_BH
|
|
def_bool y
|
|
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_BH
|
|
|
|
config INLINE_SPIN_LOCK_IRQ
|
|
def_bool y
|
|
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_IRQ
|
|
|
|
config INLINE_SPIN_LOCK_IRQSAVE
|
|
def_bool y
|
|
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_IRQSAVE
|
|
|
|
config INLINE_SPIN_UNLOCK_BH
|
|
def_bool y
|
|
depends on ARCH_INLINE_SPIN_UNLOCK_BH
|
|
|
|
config INLINE_SPIN_UNLOCK_IRQ
|
|
def_bool y
|
|
depends on !PREEMPT || ARCH_INLINE_SPIN_UNLOCK_IRQ
|
|
|
|
config INLINE_SPIN_UNLOCK_IRQRESTORE
|
|
def_bool y
|
|
depends on ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE
|
|
|
|
|
|
config INLINE_READ_TRYLOCK
|
|
def_bool y
|
|
depends on ARCH_INLINE_READ_TRYLOCK
|
|
|
|
config INLINE_READ_LOCK
|
|
def_bool y
|
|
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK
|
|
|
|
config INLINE_READ_LOCK_BH
|
|
def_bool y
|
|
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_BH
|
|
|
|
config INLINE_READ_LOCK_IRQ
|
|
def_bool y
|
|
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_IRQ
|
|
|
|
config INLINE_READ_LOCK_IRQSAVE
|
|
def_bool y
|
|
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_IRQSAVE
|
|
|
|
config INLINE_READ_UNLOCK
|
|
def_bool y
|
|
depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK
|
|
|
|
config INLINE_READ_UNLOCK_BH
|
|
def_bool y
|
|
depends on ARCH_INLINE_READ_UNLOCK_BH
|
|
|
|
config INLINE_READ_UNLOCK_IRQ
|
|
def_bool y
|
|
depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK_IRQ
|
|
|
|
config INLINE_READ_UNLOCK_IRQRESTORE
|
|
def_bool y
|
|
depends on ARCH_INLINE_READ_UNLOCK_IRQRESTORE
|
|
|
|
|
|
config INLINE_WRITE_TRYLOCK
|
|
def_bool y
|
|
depends on ARCH_INLINE_WRITE_TRYLOCK
|
|
|
|
config INLINE_WRITE_LOCK
|
|
def_bool y
|
|
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK
|
|
|
|
config INLINE_WRITE_LOCK_BH
|
|
def_bool y
|
|
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_BH
|
|
|
|
config INLINE_WRITE_LOCK_IRQ
|
|
def_bool y
|
|
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_IRQ
|
|
|
|
config INLINE_WRITE_LOCK_IRQSAVE
|
|
def_bool y
|
|
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_IRQSAVE
|
|
|
|
config INLINE_WRITE_UNLOCK
|
|
def_bool y
|
|
depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK
|
|
|
|
config INLINE_WRITE_UNLOCK_BH
|
|
def_bool y
|
|
depends on ARCH_INLINE_WRITE_UNLOCK_BH
|
|
|
|
config INLINE_WRITE_UNLOCK_IRQ
|
|
def_bool y
|
|
depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK_IRQ
|
|
|
|
config INLINE_WRITE_UNLOCK_IRQRESTORE
|
|
def_bool y
|
|
depends on ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
|
|
|
|
endif
|
|
|
|
config ARCH_SUPPORTS_ATOMIC_RMW
|
|
bool
|
|
|
|
config MUTEX_SPIN_ON_OWNER
|
|
def_bool y
|
|
depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW
|
|
|
|
config RWSEM_SPIN_ON_OWNER
|
|
def_bool y
|
|
depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW
|
|
|
|
config LOCK_SPIN_ON_OWNER
|
|
def_bool y
|
|
depends on MUTEX_SPIN_ON_OWNER || RWSEM_SPIN_ON_OWNER
|
|
|
|
config ARCH_USE_QUEUED_SPINLOCKS
|
|
bool
|
|
|
|
config QUEUED_SPINLOCKS
|
|
def_bool y if ARCH_USE_QUEUED_SPINLOCKS
|
|
depends on SMP
|
|
|
|
config BPF_ARCH_SPINLOCK
|
|
bool
|
|
|
|
config ARCH_USE_QUEUED_RWLOCKS
|
|
bool
|
|
|
|
config QUEUED_RWLOCKS
|
|
def_bool y if ARCH_USE_QUEUED_RWLOCKS
|
|
depends on SMP
|