This work adds support for "persistent" eBPF maps/programs. The term
"persistent" is to be understood that maps/programs have a facility
that lets them survive process termination. This is desired by various
eBPF subsystem users.
Just to name one example: tc classifier/action. Whenever tc parses
the ELF object, extracts and loads maps/progs into the kernel, these
file descriptors will be out of reach after the tc instance exits.
So a subsequent tc invocation won't be able to access/relocate on this
resource, and therefore maps cannot easily be shared, f.e. between the
ingress and egress networking data path.
The current workaround is that Unix domain sockets (UDS) need to be
instrumented in order to pass the created eBPF map/program file
descriptors to a third party management daemon through UDS' socket
passing facility. This makes it a bit complicated to deploy shared
eBPF maps or programs (programs f.e. for tail calls) among various
processes.
We've been brainstorming on how we could tackle this issue and various
approches have been tried out so far, which can be read up further in
the below reference.
The architecture we eventually ended up with is a minimal file system
that can hold map/prog objects. The file system is a per mount namespace
singleton, and the default mount point is /sys/fs/bpf/. Any subsequent
mounts within a given namespace will point to the same instance. The
file system allows for creating a user-defined directory structure.
The objects for maps/progs are created/fetched through bpf(2) with
two new commands (BPF_OBJ_PIN/BPF_OBJ_GET). I.e. a bpf file descriptor
along with a pathname is being passed to bpf(2) that in turn creates
(we call it eBPF object pinning) the file system nodes. Only the pathname
is being passed to bpf(2) for getting a new BPF file descriptor to an
existing node. The user can use that to access maps and progs later on,
through bpf(2). Removal of file system nodes is being managed through
normal VFS functions such as unlink(2), etc. The file system code is
kept to a very minimum and can be further extended later on.
The next step I'm working on is to add dump eBPF map/prog commands
to bpf(2), so that a specification from a given file descriptor can
be retrieved. This can be used by things like CRIU but also applications
can inspect the meta data after calling BPF_OBJ_GET.
Big thanks also to Alexei and Hannes who significantly contributed
in the design discussion that eventually let us end up with this
architecture here.
Reference: https://lkml.org/lkml/2015/10/15/925
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
We currently have duplicated cleanup code in bpf_prog_put() and
bpf_prog_put_rcu() cleanup paths. Back then we decided that it was
not worth it to make it a common helper called by both, but with
the recent addition of resource charging, we could have avoided
the fix in commit ac00737f4e ("bpf: Need to call bpf_prog_uncharge_memlock
from bpf_prog_put") if we would have had only a single, common path.
We can simplify it further by assigning aux->prog only once during
allocation time.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a bpf_map_get() function that we're going to use later on and
align/clean the remaining helpers a bit so that we have them a bit
more consistent:
- __bpf_map_get() and __bpf_prog_get() that both work on the fd
struct, check whether the descriptor is eBPF and return the
pointer to the map/prog stored in the private data.
Also, we can return f.file->private_data directly, the function
signature is enough of a documentation already.
- bpf_map_get() and bpf_prog_get() that both work on u32 user fd,
call their respective __bpf_map_get()/__bpf_prog_get() variants,
and take a reference.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since we're going to use anon_inode_getfd() invocations in more than just
the current places, make a helper function for both, so that we only need
to pass a map/prog pointer to the helper itself in order to get a fd. The
new helpers are called bpf_map_new_fd() and bpf_prog_new_fd().
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support for dumping a process' (classic BPF) seccomp
filters via ptrace.
PTRACE_SECCOMP_GET_FILTER allows the tracer to dump the user's classic BPF
seccomp filters. addr should be an integer which represents the ith seccomp
filter (0 is the most recently installed filter). data should be a struct
sock_filter * with enough room for the ith filter, or NULL, in which case
the filter is not saved. The return value for this command is the number of
BPF instructions the program represents, or negative in the case of errors.
Command specific errors are ENOENT: which indicates that there is no ith
filter in this seccomp tree, and EMEDIUMTYPE, which indicates that the ith
filter was not installed as a classic BPF filter.
A caveat with this approach is that there is no way to get explicitly at
the heirarchy of seccomp filters, and users need to memcmp() filters to
decide which are inherited. This means that a task which installs two of
the same filter can potentially confuse users of this interface.
v2: * make save_orig const
* check that the orig_prog exists (not necessary right now, but when
grows eBPF support it will be)
* s/n/filter_off and make it an unsigned long to match ptrace
* count "down" the tree instead of "up" when passing a filter offset
v3: * don't take the current task's lock for inspecting its seccomp mode
* use a 0x42** constant for the ptrace command value
v4: * don't copy to userspace while holding spinlocks
v5: * add another condition to WARN_ON
v6: * rebase on net-next
Signed-off-by: Tycho Andersen <tycho.andersen@canonical.com>
Acked-by: Kees Cook <keescook@chromium.org>
CC: Will Drewry <wad@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Pavel Emelyanov <xemul@parallels.com>
CC: Serge E. Hallyn <serge.hallyn@ubuntu.com>
CC: Alexei Starovoitov <ast@kernel.org>
CC: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull module preemption fix from Rusty Russell:
"Turns out we should have always been disabling preemption here;
someone finally caught it thanks to Peter Z's additional checks"
* tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux:
module: Fix locking in symbol_put_addr()
exported perf symbols are GPL only, mark eBPF helper functions
used in tracing as GPL only as well.
Suggested-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix safety checks for bpf_perf_event_read():
- only non-inherited events can be added to perf_event_array map
(do this check statically at map insertion time)
- dynamically check that event is local and !pmu->count
Otherwise buggy bpf program can cause kernel splat.
Also fix error path after perf_event_attrs()
and remove redundant 'extern'.
Fixes: 35578d7984 ("bpf: Implement function bpf_perf_event_read() that get the selected hardware PMU conuter")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Wang Nan <wangnan0@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull scheduler fixes from Ingo Molnar:
"Misc fixes all around the map: an instrumentation fix, a nohz
usability fix, a lockdep annotation fix and two task group scheduling
fixes"
* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/core: Add missing lockdep_unpin() annotations
sched/deadline: Fix migration of SCHED_DEADLINE tasks
nohz: Revert "nohz: Set isolcpus when nohz_full is set"
sched/fair: Update task group's load_avg after task migration
sched/fair: Fix overly small weight for interactive group entities
sched, tracing: Stop/start critical timings around the idle=poll idle loop
Merge fixes from Andrew Morton:
"9 fixes"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
ocfs2/dlm: unlock lockres spinlock before dlm_lockres_put
fault-inject: fix inverted interval/probability values in printk
lib/Kconfig.debug: disable -Wframe-larger-than warnings with KASAN=y
mm: make sendfile(2) killable
thp: use is_zero_pfn() only after pte_present() check
mailmap: update Javier Martinez Canillas' email
MAINTAINERS: add Sergey as zsmalloc reviewer
mm: cma: fix incorrect type conversion for size during dma allocation
kmod: don't run async usermode helper as a child of kworker thread
call_usermodehelper_exec_sync() does fork() + wait() with "unignored"
SIGCHLD. What we have missed is that this worker thread can have other
children previously forked by call_usermodehelper_exec_work() without
UMH_WAIT_PROC. If such a child exits in between it becomes a zombie
because auto-reaping only works if SIGCHLD is ignored, and nobody can
reap it (unless/until this worker thread exits too).
Change the !UMH_WAIT_PROC case to use CLONE_PARENT.
Note: this is only first step. All PF_KTHREAD tasks, even created by
kernel_thread() should have ->parent == kthreadd by default.
Fixes: bb304a5c6f ("kmod: handle UMH_WAIT_PROC from system unbound workqueue")
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This helper is used to send raw data from eBPF program into
special PERF_TYPE_SOFTWARE/PERF_COUNT_SW_BPF_OUTPUT perf_event.
User space needs to perf_event_open() it (either for one or all cpus) and
store FD into perf_event_array (similar to bpf_perf_event_read() helper)
before eBPF program can send data into it.
Today the programs triggered by kprobe collect the data and either store
it into the maps or print it via bpf_trace_printk() where latter is the debug
facility and not suitable to stream the data. This new helper replaces
such bpf_trace_printk() usage and allows programs to have dedicated
channel into user space for post-processing of the raw data collected.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of WARN_ON in perf_event_output() on unpaded raw samples,
pad them automatically.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The code in stack tracer should not be executed within an NMI as it grabs
spinlocks and stack tracing an NMI gives the possibility of causing a
deadlock. Although this is safe on x86_64, because it does not perform stack
traces when the task struct stack is not in use (interrupts and NMIs), it
may be an issue for NMIs on i386 and other archs that use the same stack as
the NMI.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
The stack tracer was triggering the WARN_ON() in module.c:
static void module_assert_mutex_or_preempt(void)
{
#ifdef CONFIG_LOCKDEP
if (unlikely(!debug_locks))
return;
WARN_ON(!rcu_read_lock_sched_held() &&
!lockdep_is_held(&module_mutex));
#endif
}
The reason is that the stack tracer traces all function calls, and some of
those calls happen while exiting or entering user space and idle. Some of
these functions are called after RCU had already stopped watching, as RCU
does not watch userspace or idle CPUs.
If a max stack is hit, then the save_stack_trace() is called, which will
check module addresses and call module_assert_mutex_or_preempt(), and then
trigger the warning. Sad part is, the warning itself will also do a stack
trace and tigger the same warning. That probably should be fixed.
The warning was added by 0be964be0d "module: Sanitize RCU usage and
locking" but this bug has probably been around longer. But it's unlikely to
cause much harm, but the new warning causes the system to lock up.
Cc: stable@vger.kernel.org # 4.2+
Cc: Peter Zijlstra <peterz@infradead.org>
Cc:"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Conflicts:
drivers/net/usb/asix_common.c
net/ipv4/inet_connection_sock.c
net/switchdev/switchdev.c
In the inet_connection_sock.c case the request socket hashing scheme
is completely different in net-next.
The other two conflicts were overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit:
9d51426242 ("sched/deadline: Reduce rq lock contention by eliminating locking of non-feasible target")
broke select_task_rq_dl() and find_lock_later_rq(), because it introduced
a comparison between the local task's deadline and dl.earliest_dl.curr of
the remote queue.
However, if the remote runqueue does not contain any SCHED_DEADLINE
task its earliest_dl.curr is 0 (always smaller than the deadline of
the local task) and the remote runqueue is not selected for pushing.
As a result, if an application creates multiple SCHED_DEADLINE
threads, they will never be pushed to runqueues that do not already
contain SCHED_DEADLINE tasks.
This patch fixes the issue by checking if dl.dl_nr_running == 0.
Signed-off-by: Luca Abeni <luca.abeni@unitn.it>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wanpeng Li <wanpeng.li@linux.intel.com>
Fixes: 9d51426242 ("sched/deadline: Reduce rq lock contention by eliminating locking of non-feasible target")
Link: http://lkml.kernel.org/r/1444982781-15608-1-git-send-email-luca.abeni@unitn.it
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This reverts:
8cb9764fc8 ("nohz: Set isolcpus when nohz_full is set")
We assumed that full-nohz users always want scheduler isolation on full
dynticks CPUs, therefore we included full-nohz CPUs on cpu_isolated_map.
This means that tasks run by default on CPUs outside the nohz_full range
unless their affinity is explicity overwritten.
This suits pure isolation workloads but when the machine is needed to
run common workloads, the available sets of CPUs to run common tasks
becomes reduced.
We reach an extreme case when CONFIG_NO_HZ_FULL_ALL is enabled as it
leaves only CPU 0 for non-isolation tasks, which makes people think that
their supercomputer regressed to 90's UP - which is true in a sense.
Some full-nohz users appear to be interested in running normal workloads
either before or after an isolation workload. Full-nohz isn't optimized
toward normal workloads but it's still better than UP performance.
We are reaching a limitation in kernel presets here. Lets revert this
cpu_isolated_map inclusion and let userspace do its own scheduler
isolation using cpusets or explicit affinity settings.
Reported-by: Ingo Molnar <mingo@kernel.org>
Reported-by: Mike Galbraith <umgwanakikbuti@gmail.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul E . McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Link: http://lkml.kernel.org/r/1444663283-30068-1-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull irq/timer fixes from Thomas Gleixner:
"irq: a fix for the new hierarchical MSI interrupt handling which
unbreaks PCI=n configurations.
timers: a fix for the new hrtimer clock offset update mechanism to
ensure that the boot time offset is respected"
* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
genirq/msi: Do not use pci_msi_[un]mask_irq as default methods
* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
timekeeping: Increment clock_was_set_seq in timekeeping_init()
timekeeping_init() can set the wall time offset, so we need to
increment the clock_was_set_seq counter. That way hrtimers will pick
up the early offset immediately. Otherwise on a machine which does not
set wall time later in the boot process the hrtimer offset is stale at
0 and wall time timers are going to expire with a delay of 45 years.
Fixes: 868a3e915f "hrtimer: Make offset update smarter"
Reported-and-tested-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Stefan Liebler <stli@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: John Stultz <john.stultz@linaro.org>
