To handle the difference between wakeups for regular sleeping locks (mutex,
rtmutex, rw_semaphore) and the wakeups for 'sleeping' spin/rwlocks on
PREEMPT_RT enabled kernels correctly, it is required to provide a
wake_q_head construct which allows to keep them separate.
Provide a wrapper around wake_q_head and the required helpers, which will be
extended with the state handling later.
No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211303.139337655@linutronix.de
Regular sleeping locks like mutexes, rtmutexes and rw_semaphores are always
entering and leaving a blocking section with task state == TASK_RUNNING.
On a non-RT kernel spinlocks and rwlocks never affect the task state, but
on RT kernels these locks are converted to rtmutex based 'sleeping' locks.
So in case of contention the task goes to block, which requires to carefully
preserve the task state, and restore it after acquiring the lock taking
regular wakeups for the task into account, which happened while the task was
blocked. This state preserving is achieved by having a separate task state
for blocking on a RT spin/rwlock and a saved_state field in task_struct
along with careful handling of these wakeup scenarios in try_to_wake_up().
To avoid conditionals in the rtmutex code, store the wake state which has
to be used for waking a lock waiter in rt_mutex_waiter which allows to
handle the regular and RT spin/rwlocks by handing it to wake_up_state().
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211303.079800739@linutronix.de
The RT specific R/W semaphore implementation used to restrict the number of
readers to one, because a writer cannot block on multiple readers and
inherit its priority or budget.
The single reader restricting was painful in various ways:
- Performance bottleneck for multi-threaded applications in the page fault
path (mmap sem)
- Progress blocker for drivers which are carefully crafted to avoid the
potential reader/writer deadlock in mainline.
The analysis of the writer code paths shows that properly written RT tasks
should not take them. Syscalls like mmap(), file access which take mmap sem
write locked have unbound latencies, which are completely unrelated to mmap
sem. Other R/W sem users like graphics drivers are not suitable for RT tasks
either.
So there is little risk to hurt RT tasks when the RT rwsem implementation is
done in the following way:
- Allow concurrent readers
- Make writers block until the last reader left the critical section. This
blocking is not subject to priority/budget inheritance.
- Readers blocked on a writer inherit their priority/budget in the normal
way.
There is a drawback with this scheme: R/W semaphores become writer unfair
though the applications which have triggered writer starvation (mostly on
mmap_sem) in the past are not really the typical workloads running on a RT
system. So while it's unlikely to hit writer starvation, it's possible. If
there are unexpected workloads on RT systems triggering it, the problem
has to be revisited.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211303.016885947@linutronix.de
On PREEMPT_RT, rw_semaphores and rwlocks are substituted with an rtmutex and
a reader count. The implementation is writer unfair, as it is not feasible
to do priority inheritance on multiple readers, but experience has shown
that real-time workloads are not the typical workloads which are sensitive
to writer starvation.
The inner workings of rw_semaphores and rwlocks on RT are almost identical
except for the task state and signal handling. rw_semaphores are not state
preserving over a contention, they are expected to enter and leave with state
== TASK_RUNNING. rwlocks have a mechanism to preserve the state of the task
at entry and restore it after unblocking taking potential non-lock related
wakeups into account. rw_semaphores can also be subject to signal handling
interrupting a blocked state, while rwlocks ignore signals.
To avoid code duplication, provide a shared implementation which takes the
small difference vs. state and signals into account. The code is included
into the relevant rw_semaphore/rwlock base code and compiled for each use
case separately.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.957920571@linutronix.de
Split the inner workings of rt_mutex_slowlock() out into a separate
function, which can be reused by the upcoming RT lock substitutions,
e.g. for rw_semaphores.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.841971086@linutronix.de
RT builds substitutions for rwsem, mutex, spinlock and rwlock around
rtmutexes. Split the inner working out so each lock substitution can use
them with the appropriate lockdep annotations. This avoids having an extra
unused lockdep map in the wrapped rtmutex.
No functional change.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.784739994@linutronix.de
Prepare for reusing the inner functions of rtmutex for RT lock
substitutions: introduce kernel/locking/rtmutex_api.c and move
them there.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.726560996@linutronix.de
Allows the compiler to generate better code depending on the architecture.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.668958502@linutronix.de
Inlines are type-safe...
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.610830960@linutronix.de
RT enabled kernels substitute spin/rwlocks with 'sleeping' variants based
on rtmutexes. Blocking on such a lock is similar to preemption versus:
- I/O scheduling and worker handling, because these functions might block
on another substituted lock, or come from a lock contention within these
functions.
- RCU considers this like a preemption, because the task might be in a read
side critical section.
Add a separate scheduling point for this, and hand a new scheduling mode
argument to __schedule() which allows, along with separate mode masks, to
handle this gracefully from within the scheduler, without proliferating that
to other subsystems like RCU.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.372319055@linutronix.de
PREEMPT_RT needs to hand a special state into __schedule() when a task
blocks on a 'sleeping' spin/rwlock. This is required to handle
rcu_note_context_switch() correctly without having special casing in the
RCU code. From an RCU point of view the blocking on the sleeping spinlock
is equivalent to preemption, because the task might be in a read side
critical section.
schedule_debug() also has a check which would trigger with the !preempt
case, but that could be handled differently.
To avoid adding another argument and extra checks which cannot be optimized
out by the compiler, the following solution has been chosen:
- Replace the boolean 'preempt' argument with an unsigned integer
'sched_mode' argument and define constants to hand in:
(0 == no preemption, 1 = preemption).
- Add two masks to apply on that mode: one for the debug/rcu invocations,
and one for the actual scheduling decision.
For a non RT kernel these masks are UINT_MAX, i.e. all bits are set,
which allows the compiler to optimize the AND operation out, because it is
not masking out anything. IOW, it's not different from the boolean.
RT enabled kernels will define these masks separately.
No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.315473019@linutronix.de
Waiting for spinlocks and rwlocks on non RT enabled kernels is task::state
preserving. Any wakeup which matches the state is valid.
RT enabled kernels substitutes them with 'sleeping' spinlocks. This creates
an issue vs. task::__state.
In order to block on the lock, the task has to overwrite task::__state and a
consecutive wakeup issued by the unlocker sets the state back to
TASK_RUNNING. As a consequence the task loses the state which was set
before the lock acquire and also any regular wakeup targeted at the task
while it is blocked on the lock.
To handle this gracefully, add a 'saved_state' member to task_struct which
is used in the following way:
1) When a task blocks on a 'sleeping' spinlock, the current state is saved
in task::saved_state before it is set to TASK_RTLOCK_WAIT.
2) When the task unblocks and after acquiring the lock, it restores the saved
state.
3) When a regular wakeup happens for a task while it is blocked then the
state change of that wakeup is redirected to operate on task::saved_state.
This is also required when the task state is running because the task
might have been woken up from the lock wait and has not yet restored
the saved state.
To make it complete, provide the necessary helpers to save and restore the
saved state along with the necessary documentation how the RT lock blocking
is supposed to work.
For non-RT kernels there is no functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.258751046@linutronix.de
RT kernels have a slightly more complicated handling of wakeups due to
'sleeping' spin/rwlocks. If a task is blocked on such a lock then the
original state of the task is preserved over the blocking period, and
any regular (non lock related) wakeup has to be targeted at the
saved state to ensure that these wakeups are not lost.
Once the task acquires the lock it restores the task state from the saved state.
To avoid cluttering try_to_wake_up() with that logic, split the wakeup
state check out into an inline helper and use it at both places where
task::__state is checked against the state argument of try_to_wake_up().
No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.088945085@linutronix.de
RT mutexes belong to the LD_WAIT_SLEEP class. Make them so.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211302.031014562@linutronix.de
- Mask all MSI-X entries when enabling MSI-X otherwise stale unmasked
entries stay around e.g. when a crashkernel is booted.
- Enforce masking of a MSI-X table entry when updating it, which mandatory
according to speification
- Ensure that writes to MSI[-X} tables are flushed.
- Prevent invalid bits being set in the MSI mask register
- Properly serialize modifications to the mask cache and the mask register
for multi-MSI.
- Cure the violation of the affinity setting rules on X86 during interrupt
startup which can cause lost and stale interrupts. Move the initial
affinity setting ahead of actualy enabling the interrupt.
- Ensure that MSI interrupts are completely torn down before freeing them
in the error handling case.
- Prevent an array out of bounds access in the irq timings code.
-----BEGIN PGP SIGNATURE-----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=yf3u
-----END PGP SIGNATURE-----
Merge tag 'irq-urgent-2021-08-15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull irq fixes from Thomas Gleixner:
"A set of fixes for PCI/MSI and x86 interrupt startup:
- Mask all MSI-X entries when enabling MSI-X otherwise stale unmasked
entries stay around e.g. when a crashkernel is booted.
- Enforce masking of a MSI-X table entry when updating it, which
mandatory according to speification
- Ensure that writes to MSI[-X} tables are flushed.
- Prevent invalid bits being set in the MSI mask register
- Properly serialize modifications to the mask cache and the mask
register for multi-MSI.
- Cure the violation of the affinity setting rules on X86 during
interrupt startup which can cause lost and stale interrupts. Move
the initial affinity setting ahead of actualy enabling the
interrupt.
- Ensure that MSI interrupts are completely torn down before freeing
them in the error handling case.
- Prevent an array out of bounds access in the irq timings code"
* tag 'irq-urgent-2021-08-15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
driver core: Add missing kernel doc for device::msi_lock
genirq/msi: Ensure deactivation on teardown
genirq/timings: Prevent potential array overflow in __irq_timings_store()
x86/msi: Force affinity setup before startup
x86/ioapic: Force affinity setup before startup
genirq: Provide IRQCHIP_AFFINITY_PRE_STARTUP
PCI/MSI: Protect msi_desc::masked for multi-MSI
PCI/MSI: Use msi_mask_irq() in pci_msi_shutdown()
PCI/MSI: Correct misleading comments
PCI/MSI: Do not set invalid bits in MSI mask
PCI/MSI: Enforce MSI[X] entry updates to be visible
PCI/MSI: Enforce that MSI-X table entry is masked for update
PCI/MSI: Mask all unused MSI-X entries
PCI/MSI: Enable and mask MSI-X early
can and ieee802154.
Current release - regressions:
- r8169: fix ASPM-related link-up regressions
- bridge: fix flags interpretation for extern learn fdb entries
- phy: micrel: fix link detection on ksz87xx switch
- Revert "tipc: Return the correct errno code"
- ptp: fix possible memory leak caused by invalid cast
Current release - new code bugs:
- bpf: add missing bpf_read_[un]lock_trace() for syscall program
- bpf: fix potentially incorrect results with bpf_get_local_storage()
- page_pool: mask the page->signature before the checking, avoid
dma mapping leaks
- netfilter: nfnetlink_hook: 5 fixes to information in netlink dumps
- bnxt_en: fix firmware interface issues with PTP
- mlx5: Bridge, fix ageing time
Previous releases - regressions:
- linkwatch: fix failure to restore device state across suspend/resume
- bareudp: fix invalid read beyond skb's linear data
Previous releases - always broken:
- bpf: fix integer overflow involving bucket_size
- ppp: fix issues when desired interface name is specified via netlink
- wwan: mhi_wwan_ctrl: fix possible deadlock
- dsa: microchip: ksz8795: fix number of VLAN related bugs
- dsa: drivers: fix broken backpressure in .port_fdb_dump
- dsa: qca: ar9331: make proper initial port defaults
Misc:
- bpf: add lockdown check for probe_write_user helper
- netfilter: conntrack: remove offload_pickup sysctl before 5.14 is out
- netfilter: conntrack: collect all entries in one cycle,
heuristically slow down garbage collection scans
on idle systems to prevent frequent wake ups
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----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=hzDl
-----END PGP SIGNATURE-----
Merge tag 'net-5.14-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Networking fixes, including fixes from netfilter, bpf, can and
ieee802154.
The size of this is pretty normal, but we got more fixes for 5.14
changes this week than last week. Nothing major but the trend is the
opposite of what we like. We'll see how the next week goes..
Current release - regressions:
- r8169: fix ASPM-related link-up regressions
- bridge: fix flags interpretation for extern learn fdb entries
- phy: micrel: fix link detection on ksz87xx switch
- Revert "tipc: Return the correct errno code"
- ptp: fix possible memory leak caused by invalid cast
Current release - new code bugs:
- bpf: add missing bpf_read_[un]lock_trace() for syscall program
- bpf: fix potentially incorrect results with bpf_get_local_storage()
- page_pool: mask the page->signature before the checking, avoid dma
mapping leaks
- netfilter: nfnetlink_hook: 5 fixes to information in netlink dumps
- bnxt_en: fix firmware interface issues with PTP
- mlx5: Bridge, fix ageing time
Previous releases - regressions:
- linkwatch: fix failure to restore device state across
suspend/resume
- bareudp: fix invalid read beyond skb's linear data
Previous releases - always broken:
- bpf: fix integer overflow involving bucket_size
- ppp: fix issues when desired interface name is specified via
netlink
- wwan: mhi_wwan_ctrl: fix possible deadlock
- dsa: microchip: ksz8795: fix number of VLAN related bugs
- dsa: drivers: fix broken backpressure in .port_fdb_dump
- dsa: qca: ar9331: make proper initial port defaults
Misc:
- bpf: add lockdown check for probe_write_user helper
- netfilter: conntrack: remove offload_pickup sysctl before 5.14 is
out
- netfilter: conntrack: collect all entries in one cycle,
heuristically slow down garbage collection scans on idle systems to
prevent frequent wake ups"
* tag 'net-5.14-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (87 commits)
vsock/virtio: avoid potential deadlock when vsock device remove
wwan: core: Avoid returning NULL from wwan_create_dev()
net: dsa: sja1105: unregister the MDIO buses during teardown
Revert "tipc: Return the correct errno code"
net: mscc: Fix non-GPL export of regmap APIs
net: igmp: increase size of mr_ifc_count
MAINTAINERS: switch to my OMP email for Renesas Ethernet drivers
tcp_bbr: fix u32 wrap bug in round logic if bbr_init() called after 2B packets
net: pcs: xpcs: fix error handling on failed to allocate memory
net: linkwatch: fix failure to restore device state across suspend/resume
net: bridge: fix memleak in br_add_if()
net: switchdev: zero-initialize struct switchdev_notifier_fdb_info emitted by drivers towards the bridge
net: bridge: fix flags interpretation for extern learn fdb entries
net: dsa: sja1105: fix broken backpressure in .port_fdb_dump
net: dsa: lantiq: fix broken backpressure in .port_fdb_dump
net: dsa: lan9303: fix broken backpressure in .port_fdb_dump
net: dsa: hellcreek: fix broken backpressure in .port_fdb_dump
bpf, core: Fix kernel-doc notation
net: igmp: fix data-race in igmp_ifc_timer_expire()
net: Fix memory leak in ieee802154_raw_deliver
...
Pull ucounts fix from Eric Biederman:
"This fixes the ucount sysctls on big endian architectures.
The counts were expanded to be longs instead of ints, and the sysctl
code was overlooked, so only the low 32bit were being processed. On
litte endian just processing the low 32bits is fine, but on 64bit big
endian processing just the low 32bits results in the high order bits
instead of the low order bits being processed and nothing works
proper.
This change took a little bit to mature as we have the SYSCTL_ZERO,
and SYSCTL_INT_MAX macros that are only usable for sysctls operating
on ints, but unfortunately are not obviously broken. Which resulted in
the versions of this change working on big endian and not on little
endian, because the int SYSCTL_ZERO when extended 64bit wound up being
0x100000000. So we only allowed values greater than 0x100000000 and
less than 0faff. Which unfortunately broken everything that tried to
set the sysctls. (First reported with the windows subsystem for
linux).
I have tested this on x86_64 64bit after first reproducing the
problems with the earlier version of this change, and then verifying
the problems do not exist when we use appropriate long min and max
values for extra1 and extra2"
* 'for-v5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
ucounts: add missing data type changes
msi_domain_alloc_irqs() invokes irq_domain_activate_irq(), but
msi_domain_free_irqs() does not enforce deactivation before tearing down
the interrupts.
This happens when PCI/MSI interrupts are set up and never used before being
torn down again, e.g. in error handling pathes. The only place which cleans
that up is the error handling path in msi_domain_alloc_irqs().
Move the cleanup from msi_domain_alloc_irqs() into msi_domain_free_irqs()
to cure that.
Fixes: f3b0946d62 ("genirq/msi: Make sure PCI MSIs are activated early")
Signed-off-by: Bixuan Cui <cuibixuan@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20210518033117.78104-1-cuibixuan@huawei.com
When the interrupt interval is greater than 2 ^ PREDICTION_BUFFER_SIZE *
PREDICTION_FACTOR us and less than 1s, the calculated index will be greater
than the length of irqs->ema_time[]. Check the calculated index before
using it to prevent array overflow.
Fixes: 23aa3b9a6b ("genirq/timings: Encapsulate storing function")
Signed-off-by: Ben Dai <ben.dai@unisoc.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20210425150903.25456-1-ben.dai9703@gmail.com
Fix kernel-doc warnings in kernel/bpf/core.c (found by scripts/kernel-doc
and W=1 builds). That is, correct a function name in a comment and add
return descriptions for 2 functions.
Fixes these kernel-doc warnings:
kernel/bpf/core.c:1372: warning: expecting prototype for __bpf_prog_run(). Prototype was for ___bpf_prog_run() instead
kernel/bpf/core.c:1372: warning: No description found for return value of '___bpf_prog_run'
kernel/bpf/core.c:1883: warning: No description found for return value of 'bpf_prog_select_runtime'
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210809215229.7556-1-rdunlap@infradead.org
X86 IO/APIC and MSI interrupts (when used without interrupts remapping)
require that the affinity setup on startup is done before the interrupt is
enabled for the first time as the non-remapped operation mode cannot safely
migrate enabled interrupts from arbitrary contexts. Provide a new irq chip
flag which allows affected hardware to request this.
This has to be opt-in because there have been reports in the past that some
interrupt chips cannot handle affinity setting before startup.
Fixes: 1840475676 ("genirq: Expose default irq affinity mask (take 3)")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20210729222542.779791738@linutronix.de
Commit b910eaaaa4 ("bpf: Fix NULL pointer dereference in bpf_get_local_storage()
helper") fixed a bug for bpf_get_local_storage() helper so different tasks
won't mess up with each other's percpu local storage.
The percpu data contains 8 slots so it can hold up to 8 contexts (same or
different tasks), for 8 different program runs, at the same time. This in
general is sufficient. But our internal testing showed the following warning
multiple times:
[...]
warning: WARNING: CPU: 13 PID: 41661 at include/linux/bpf-cgroup.h:193
__cgroup_bpf_run_filter_sock_ops+0x13e/0x180
RIP: 0010:__cgroup_bpf_run_filter_sock_ops+0x13e/0x180
<IRQ>
tcp_call_bpf.constprop.99+0x93/0xc0
tcp_conn_request+0x41e/0xa50
? tcp_rcv_state_process+0x203/0xe00
tcp_rcv_state_process+0x203/0xe00
? sk_filter_trim_cap+0xbc/0x210
? tcp_v6_inbound_md5_hash.constprop.41+0x44/0x160
tcp_v6_do_rcv+0x181/0x3e0
tcp_v6_rcv+0xc65/0xcb0
ip6_protocol_deliver_rcu+0xbd/0x450
ip6_input_finish+0x11/0x20
ip6_input+0xb5/0xc0
ip6_sublist_rcv_finish+0x37/0x50
ip6_sublist_rcv+0x1dc/0x270
ipv6_list_rcv+0x113/0x140
__netif_receive_skb_list_core+0x1a0/0x210
netif_receive_skb_list_internal+0x186/0x2a0
gro_normal_list.part.170+0x19/0x40
napi_complete_done+0x65/0x150
mlx5e_napi_poll+0x1ae/0x680
__napi_poll+0x25/0x120
net_rx_action+0x11e/0x280
__do_softirq+0xbb/0x271
irq_exit_rcu+0x97/0xa0
common_interrupt+0x7f/0xa0
</IRQ>
asm_common_interrupt+0x1e/0x40
RIP: 0010:bpf_prog_1835a9241238291a_tw_egress+0x5/0xbac
? __cgroup_bpf_run_filter_skb+0x378/0x4e0
? do_softirq+0x34/0x70
? ip6_finish_output2+0x266/0x590
? ip6_finish_output+0x66/0xa0
? ip6_output+0x6c/0x130
? ip6_xmit+0x279/0x550
? ip6_dst_check+0x61/0xd0
[...]
Using drgn [0] to dump the percpu buffer contents showed that on this CPU
slot 0 is still available, but slots 1-7 are occupied and those tasks in
slots 1-7 mostly don't exist any more. So we might have issues in
bpf_cgroup_storage_unset().
Further debugging confirmed that there is a bug in bpf_cgroup_storage_unset().
Currently, it tries to unset "current" slot with searching from the start.
So the following sequence is possible:
1. A task is running and claims slot 0
2. Running BPF program is done, and it checked slot 0 has the "task"
and ready to reset it to NULL (not yet).
3. An interrupt happens, another BPF program runs and it claims slot 1
with the *same* task.
4. The unset() in interrupt context releases slot 0 since it matches "task".
5. Interrupt is done, the task in process context reset slot 0.
At the end, slot 1 is not reset and the same process can continue to occupy
slots 2-7 and finally, when the above step 1-5 is repeated again, step 3 BPF
program won't be able to claim an empty slot and a warning will be issued.
To fix the issue, for unset() function, we should traverse from the last slot
to the first. This way, the above issue can be avoided.
The same reverse traversal should also be done in bpf_get_local_storage() helper
itself. Otherwise, incorrect local storage may be returned to BPF program.
[0] https://github.com/osandov/drgn
Fixes: b910eaaaa4 ("bpf: Fix NULL pointer dereference in bpf_get_local_storage() helper")
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210810010413.1976277-1-yhs@fb.com
Back then, commit 96ae522795 ("bpf: Add bpf_probe_write_user BPF helper
to be called in tracers") added the bpf_probe_write_user() helper in order
to allow to override user space memory. Its original goal was to have a
facility to "debug, divert, and manipulate execution of semi-cooperative
processes" under CAP_SYS_ADMIN. Write to kernel was explicitly disallowed
since it would otherwise tamper with its integrity.
One use case was shown in cf9b1199de ("samples/bpf: Add test/example of
using bpf_probe_write_user bpf helper") where the program DNATs traffic
at the time of connect(2) syscall, meaning, it rewrites the arguments to
a syscall while they're still in userspace, and before the syscall has a
chance to copy the argument into kernel space. These days we have better
mechanisms in BPF for achieving the same (e.g. for load-balancers), but
without having to write to userspace memory.
Of course the bpf_probe_write_user() helper can also be used to abuse
many other things for both good or bad purpose. Outside of BPF, there is
a similar mechanism for ptrace(2) such as PTRACE_PEEK{TEXT,DATA} and
PTRACE_POKE{TEXT,DATA}, but would likely require some more effort.
Commit 96ae522795 explicitly dedicated the helper for experimentation
purpose only. Thus, move the helper's availability behind a newly added
LOCKDOWN_BPF_WRITE_USER lockdown knob so that the helper is disabled under
the "integrity" mode. More fine-grained control can be implemented also
from LSM side with this change.
Fixes: 96ae522795 ("bpf: Add bpf_probe_write_user BPF helper to be called in tracers")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Pull cgroup fix from Tejun Heo:
"One commit to fix a possible A-A deadlock around u64_stats_sync on
32bit machines caused by updating it without disabling IRQ when it may
be read from IRQ context"
* 'for-5.14-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cgroup: rstat: fix A-A deadlock on 32bit around u64_stats_sync
Rename LOCKDOWN_BPF_READ into LOCKDOWN_BPF_READ_KERNEL so we have naming
more consistent with a LOCKDOWN_BPF_WRITE_USER option that we are adding.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
- Prevent a memory ordering issue in the timer expiry code which makes it
possible to observe falsely that the callback has been executed already
while that's not the case, which violates the guarantee of del_timer_sync().
-----BEGIN PGP SIGNATURE-----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=JQWW
-----END PGP SIGNATURE-----
Merge tag 'timers-urgent-2021-08-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull timer fix from Thomas Gleixner:
"A single timer fix:
- Prevent a memory ordering issue in the timer expiry code which
makes it possible to observe falsely that the callback has been
executed already while that's not the case, which violates the
guarantee of del_timer_sync()"
* tag 'timers-urgent-2021-08-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
timers: Move clearing of base::timer_running under base:: Lock
- Prevent a double enqueue caused by rt_effective_prio() being invoked
twice in __sched_setscheduler().
-----BEGIN PGP SIGNATURE-----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=EZjT
-----END PGP SIGNATURE-----
Merge tag 'sched-urgent-2021-08-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler fix from Thomas Gleixner:
"A single scheduler fix:
- Prevent a double enqueue caused by rt_effective_prio() being
invoked twice in __sched_setscheduler()"
* tag 'sched-urgent-2021-08-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/rt: Fix double enqueue caused by rt_effective_prio
- Correct the permission checks for perf event which send SIGTRAP to a
different process and clean up that code to be more readable.
- Prevent an out of bound MSR access in the x86 perf code which happened
due to an incomplete limiting to the actually available hardware
counters.
- Prevent access to the AMD64_EVENTSEL_HOSTONLY bit when running inside a
guest.
- Handle small core counter re-enabling correctly by issuing an ACK right
before reenabling it to prevent a stale PEBS record being kept around.
-----BEGIN PGP SIGNATURE-----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=hhv+
-----END PGP SIGNATURE-----
Merge tag 'perf-urgent-2021-08-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf fixes from Thomas Gleixner:
"A set of perf fixes:
- Correct the permission checks for perf event which send SIGTRAP to
a different process and clean up that code to be more readable.
- Prevent an out of bound MSR access in the x86 perf code which
happened due to an incomplete limiting to the actually available
hardware counters.
- Prevent access to the AMD64_EVENTSEL_HOSTONLY bit when running
inside a guest.
- Handle small core counter re-enabling correctly by issuing an ACK
right before reenabling it to prevent a stale PEBS record being
kept around"
* tag 'perf-urgent-2021-08-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/intel: Apply mid ACK for small core
perf/x86/amd: Don't touch the AMD64_EVENTSEL_HOSTONLY bit inside the guest
perf/x86: Fix out of bound MSR access
perf: Refactor permissions check into perf_check_permission()
perf: Fix required permissions if sigtrap is requested
Daniel Borkmann says:
====================
pull-request: bpf 2021-08-07
The following pull-request contains BPF updates for your *net* tree.
We've added 4 non-merge commits during the last 9 day(s) which contain
a total of 4 files changed, 8 insertions(+), 7 deletions(-).
The main changes are:
1) Fix integer overflow in htab's lookup + delete batch op, from Tatsuhiko Yasumatsu.
2) Fix invalid fd 0 close in libbpf if BTF parsing failed, from Daniel Xu.
3) Fix libbpf feature probe for BPF_PROG_TYPE_CGROUP_SOCKOPT, from Robin Gögge.
4) Fix minor libbpf doc warning regarding code-block language, from Randy Dunlap.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
In __htab_map_lookup_and_delete_batch(), hash buckets are iterated
over to count the number of elements in each bucket (bucket_size).
If bucket_size is large enough, the multiplication to calculate
kvmalloc() size could overflow, resulting in out-of-bounds write
as reported by KASAN:
[...]
[ 104.986052] BUG: KASAN: vmalloc-out-of-bounds in __htab_map_lookup_and_delete_batch+0x5ce/0xb60
[ 104.986489] Write of size 4194224 at addr ffffc9010503be70 by task crash/112
[ 104.986889]
[ 104.987193] CPU: 0 PID: 112 Comm: crash Not tainted 5.14.0-rc4 #13
[ 104.987552] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014
[ 104.988104] Call Trace:
[ 104.988410] dump_stack_lvl+0x34/0x44
[ 104.988706] print_address_description.constprop.0+0x21/0x140
[ 104.988991] ? __htab_map_lookup_and_delete_batch+0x5ce/0xb60
[ 104.989327] ? __htab_map_lookup_and_delete_batch+0x5ce/0xb60
[ 104.989622] kasan_report.cold+0x7f/0x11b
[ 104.989881] ? __htab_map_lookup_and_delete_batch+0x5ce/0xb60
[ 104.990239] kasan_check_range+0x17c/0x1e0
[ 104.990467] memcpy+0x39/0x60
[ 104.990670] __htab_map_lookup_and_delete_batch+0x5ce/0xb60
[ 104.990982] ? __wake_up_common+0x4d/0x230
[ 104.991256] ? htab_of_map_free+0x130/0x130
[ 104.991541] bpf_map_do_batch+0x1fb/0x220
[...]
In hashtable, if the elements' keys have the same jhash() value, the
elements will be put into the same bucket. By putting a lot of elements
into a single bucket, the value of bucket_size can be increased to
trigger the integer overflow.
Triggering the overflow is possible for both callers with CAP_SYS_ADMIN
and callers without CAP_SYS_ADMIN.
It will be trivial for a caller with CAP_SYS_ADMIN to intentionally
reach this overflow by enabling BPF_F_ZERO_SEED. As this flag will set
the random seed passed to jhash() to 0, it will be easy for the caller
to prepare keys which will be hashed into the same value, and thus put
all the elements into the same bucket.
If the caller does not have CAP_SYS_ADMIN, BPF_F_ZERO_SEED cannot be
used. However, it will be still technically possible to trigger the
overflow, by guessing the random seed value passed to jhash() (32bit)
and repeating the attempt to trigger the overflow. In this case,
the probability to trigger the overflow will be low and will take
a very long time.
Fix the integer overflow by calling kvmalloc_array() instead of
kvmalloc() to allocate memory.
Fixes: 057996380a ("bpf: Add batch ops to all htab bpf map")
Signed-off-by: Tatsuhiko Yasumatsu <th.yasumatsu@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210806150419.109658-1-th.yasumatsu@gmail.com
As callbacks to a tracepoint are paired with the data that is passed in when
the callback is registered to the tracepoint, it must have that data passed
to the callback when the tracepoint is triggered, else bad things will
happen. To keep the two together, they are both assigned to a tracepoint
structure and added to an array. The tracepoint call site will dereference
the structure (via RCU) and call the callback in that structure along with
the data in that structure. This keeps the callback and data tightly
coupled.
Because of the overhead that retpolines have on tracepoint callbacks, if
there's only one callback attached to a tracepoint (a common case), then it
is called via a static call (code modified to do a direct call instead of an
indirect call). But to implement this, the data had to be decoupled from the
callback, as now the callback is implemented via a direct call from the
static call and not an indirect call from the dereferenced structure.
Note, the static call only calls a callback used when there's a single
callback attached to the tracepoint. If more than one callback is attached
to the same tracepoint, then the static call will call an iterator
function that goes back to dereferencing the structure keeping the callback
and its data tightly coupled again.
Issues can arise when going from 0 callbacks to one, as the static call is
assigned to the callback, and it must take care that the data passed to it
is loaded before the static call calls the callback. Going from 1 to 2
callbacks is not an issue, as long as the static call is updated to the
iterator before the tracepoint structure array is updated via RCU. Going
from 2 to more or back down to 2 is not an issue as the iterator can handle
all theses cases. But going from 2 to 1, care must be taken as the static
call is now calling a callback and the data that is loaded must be the data
for that callback.
Care was taken to ensure the callback and data would be in-sync, but after
a bug was reported, it became clear that not enough was done to make sure
that was the case. These changes address this.
The first change is to compare the old and new data instead of the old and
new callback, as it's the data that can corrupt the callback, even if the
callback is the same (something getting freed).
The next change is to convert these transitions into states, to make it
easier to know when a synchronization is needed, and to perform those
synchronizations. The problem with this patch is that it slows down
disabling all events from under a second, to making it take over 10 seconds
to do the same work. But that is addressed in the final patch.
The final patch uses the RCU state functions to keep track of the RCU state
between the transitions, and only needs to perform the synchronization if an
RCU synchronization hasn't been done already. This brings the performance of
disabling all events back to its original value. That's because no
synchronization is required between disabling tracepoints but is required
when enabling a tracepoint after its been disabled. If an RCU
synchronization happens after the tracepoint is disabled, and before it is
re-enabled, there's no need to do the synchronization again.
Both the second and third patch have subtle complexities that they are
separated into two patches. But because the second patch causes such a
regression in performance, the third patch adds a "Fixes" tag to the second
patch, such that the two must be backported together and not just the second
patch.
-----BEGIN PGP SIGNATURE-----
iIoEABYIADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCYQ15TBQccm9zdGVkdEBn
b29kbWlzLm9yZwAKCRAp5XQQmuv6qnmmAP4hoA34CDr5hrd8mYLeKptW63f5Nd1w
fVZjprfa1wJhZAEAq39OeRCT4Fb2hIeZNBNUnLU90f+J6NH5QFDEhW+CkAI=
=JcZS
-----END PGP SIGNATURE-----
Merge tag 'trace-v5.14-rc4-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull tracing fixes from Steven Rostedt:
"Fix tracepoint race between static_call and callback data
As callbacks to a tracepoint are paired with the data that is passed
in when the callback is registered to the tracepoint, it must have
that data passed to the callback when the tracepoint is triggered,
else bad things will happen. To keep the two together, they are both
assigned to a tracepoint structure and added to an array. The
tracepoint call site will dereference the structure (via RCU) and call
the callback in that structure along with the data in that structure.
This keeps the callback and data tightly coupled.
Because of the overhead that retpolines have on tracepoint callbacks,
if there's only one callback attached to a tracepoint (a common case),
then it is called via a static call (code modified to do a direct call
instead of an indirect call). But to implement this, the data had to
be decoupled from the callback, as now the callback is implemented via
a direct call from the static call and not an indirect call from the
dereferenced structure.
Note, the static call only calls a callback used when there's a single
callback attached to the tracepoint. If more than one callback is
attached to the same tracepoint, then the static call will call an
iterator function that goes back to dereferencing the structure
keeping the callback and its data tightly coupled again.
Issues can arise when going from 0 callbacks to one, as the static
call is assigned to the callback, and it must take care that the data
passed to it is loaded before the static call calls the callback.
Going from 1 to 2 callbacks is not an issue, as long as the static
call is updated to the iterator before the tracepoint structure array
is updated via RCU. Going from 2 to more or back down to 2 is not an
issue as the iterator can handle all theses cases. But going from 2 to
1, care must be taken as the static call is now calling a callback and
the data that is loaded must be the data for that callback.
Care was taken to ensure the callback and data would be in-sync, but
after a bug was reported, it became clear that not enough was done to
make sure that was the case. These changes address this.
The first change is to compare the old and new data instead of the old
and new callback, as it's the data that can corrupt the callback, even
if the callback is the same (something getting freed).
The next change is to convert these transitions into states, to make
it easier to know when a synchronization is needed, and to perform
those synchronizations. The problem with this patch is that it slows
down disabling all events from under a second, to making it take over
10 seconds to do the same work. But that is addressed in the final
patch.
The final patch uses the RCU state functions to keep track of the RCU
state between the transitions, and only needs to perform the
synchronization if an RCU synchronization hasn't been done already.
This brings the performance of disabling all events back to its
original value. That's because no synchronization is required between
disabling tracepoints but is required when enabling a tracepoint after
its been disabled. If an RCU synchronization happens after the
tracepoint is disabled, and before it is re-enabled, there's no need
to do the synchronization again.
Both the second and third patch have subtle complexities that they are
separated into two patches. But because the second patch causes such a
regression in performance, the third patch adds a "Fixes" tag to the
second patch, such that the two must be backported together and not
just the second patch"
* tag 'trace-v5.14-rc4-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
tracepoint: Use rcu get state and cond sync for static call updates
tracepoint: Fix static call function vs data state mismatch
tracepoint: static call: Compare data on transition from 2->1 callees
State transitions from 1->0->1 and N->2->1 callbacks require RCU
synchronization. Rather than performing the RCU synchronization every
time the state change occurs, which is quite slow when many tracepoints
are registered in batch, instead keep a snapshot of the RCU state on the
most recent transitions which belong to a chain, and conditionally wait
for a grace period on the last transition of the chain if one g.p. has
not elapsed since the last snapshot.
This applies to both RCU and SRCU.
This brings the performance regression caused by commit 231264d692
("Fix: tracepoint: static call function vs data state mismatch") back to
what it was originally.
Before this commit:
# trace-cmd start -e all
# time trace-cmd start -p nop
real 0m10.593s
user 0m0.017s
sys 0m0.259s
After this commit:
# trace-cmd start -e all
# time trace-cmd start -p nop
real 0m0.878s
user 0m0.000s
sys 0m0.103s
Link: https://lkml.kernel.org/r/20210805192954.30688-1-mathieu.desnoyers@efficios.com
Link: https://lore.kernel.org/io-uring/4ebea8f0-58c9-e571-fd30-0ce4f6f09c70@samba.org/
Cc: stable@vger.kernel.org
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Stefan Metzmacher <metze@samba.org>
Fixes: 231264d692 ("Fix: tracepoint: static call function vs data state mismatch")
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
On a 1->0->1 callbacks transition, there is an issue with the new
callback using the old callback's data.
Considering __DO_TRACE_CALL:
do { \
struct tracepoint_func *it_func_ptr; \
void *__data; \
it_func_ptr = \
rcu_dereference_raw((&__tracepoint_##name)->funcs); \
if (it_func_ptr) { \
__data = (it_func_ptr)->data; \
----> [ delayed here on one CPU (e.g. vcpu preempted by the host) ]
static_call(tp_func_##name)(__data, args); \
} \
} while (0)
It has loaded the tp->funcs of the old callback, so it will try to use the old
data. This can be fixed by adding a RCU sync anywhere in the 1->0->1
transition chain.
On a N->2->1 transition, we need an rcu-sync because you may have a
sequence of 3->2->1 (or 1->2->1) where the element 0 data is unchanged
between 2->1, but was changed from 3->2 (or from 1->2), which may be
observed by the static call. This can be fixed by adding an
unconditional RCU sync in transition 2->1.
Note, this fixes a correctness issue at the cost of adding a tremendous
performance regression to the disabling of tracepoints.
Before this commit:
# trace-cmd start -e all
# time trace-cmd start -p nop
real 0m0.778s
user 0m0.000s
sys 0m0.061s
After this commit:
# trace-cmd start -e all
# time trace-cmd start -p nop
real 0m10.593s
user 0m0.017s
sys 0m0.259s
A follow up fix will introduce a more lightweight scheme based on RCU
get_state and cond_sync, that will return the performance back to what it
was. As both this change and the lightweight versions are complex on their
own, for bisecting any issues that this may cause, they are kept as two
separate changes.
Link: https://lkml.kernel.org/r/20210805132717.23813-3-mathieu.desnoyers@efficios.com
Link: https://lore.kernel.org/io-uring/4ebea8f0-58c9-e571-fd30-0ce4f6f09c70@samba.org/
Cc: stable@vger.kernel.org
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Stefan Metzmacher <metze@samba.org>
Fixes: d25e37d89d ("tracepoint: Optimize using static_call()")
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
On transition from 2->1 callees, we should be comparing .data rather
than .func, because the same callback can be registered twice with
different data, and what we care about here is that the data of array
element 0 is unchanged to skip rcu sync.
Link: https://lkml.kernel.org/r/20210805132717.23813-2-mathieu.desnoyers@efficios.com
Link: https://lore.kernel.org/io-uring/4ebea8f0-58c9-e571-fd30-0ce4f6f09c70@samba.org/
Cc: stable@vger.kernel.org
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Stefan Metzmacher <metze@samba.org>
Fixes: 547305a646 ("tracepoint: Fix out of sync data passing by static caller")
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Pull ucounts fix from Eric Biederman:
"Fix a subtle locking versus reference counting bug in the ucount
changes, found by syzbot"
* 'for-v5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
ucounts: Fix race condition between alloc_ucounts and put_ucounts
- Fix NULL pointer dereference caused by an error path
- Give histogram calculation fields a size, otherwise it breaks synthetic
creation based on them.
- Reject strings being used for number calculations.
- Fix recordmcount.pl warning on llvm building RISC-V allmodconfig
- Fix the draw_functrace.py script to handle the new trace output
- Fix warning of smp_processor_id() in preemptible code
-----BEGIN PGP SIGNATURE-----
iIoEABYIADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCYQwR+xQccm9zdGVkdEBn
b29kbWlzLm9yZwAKCRAp5XQQmuv6qtHOAQD7gBn1cRK0T3Eolf5HRd14PLDVUZ1B
iMZuTJZzJUWLSAD/ec3ezcOafNlPKmG1ta8UxrWP5VzHOC5qTIAJYc1d5AA=
=7FNB
-----END PGP SIGNATURE-----
Merge tag 'trace-v5.14-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull tracing fixes from Steven Rostedt:
"Various tracing fixes:
- Fix NULL pointer dereference caused by an error path
- Give histogram calculation fields a size, otherwise it breaks
synthetic creation based on them.
- Reject strings being used for number calculations.
- Fix recordmcount.pl warning on llvm building RISC-V allmodconfig
- Fix the draw_functrace.py script to handle the new trace output
- Fix warning of smp_processor_id() in preemptible code"
* tag 'trace-v5.14-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
tracing: Quiet smp_processor_id() use in preemptable warning in hwlat
scripts/tracing: fix the bug that can't parse raw_trace_func
scripts/recordmcount.pl: Remove check_objcopy() and $can_use_local
tracing: Reject string operand in the histogram expression
tracing / histogram: Give calculation hist_fields a size
tracing: Fix NULL pointer dereference in start_creating
The hardware latency detector (hwlat) has a mode that it runs one thread
across CPUs. The logic to move from the currently running CPU to the next
one in the list does a smp_processor_id() to find where it currently is.
Unfortunately, it's done with preemption enabled, and this triggers a
warning for using smp_processor_id() in a preempt enabled section.
As it is only using smp_processor_id() to get information on where it
currently is in order to simply move it to the next CPU, it doesn't really
care if it got moved in the mean time. It will simply balance out later if
such a case arises.
Switch smp_processor_id() to raw_smp_processor_id() to quiet that warning.
Link: https://lkml.kernel.org/r/20210804141848.79edadc0@oasis.local.home
Acked-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Fixes: 8fa826b734 ("trace/hwlat: Implement the mode config option")
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Since the string type can not be the target of the addition / subtraction
operation, it must be rejected. Without this fix, the string type silently
converted to digits.
Link: https://lkml.kernel.org/r/162742654278.290973.1523000673366456634.stgit@devnote2
Cc: stable@vger.kernel.org
Fixes: 100719dcef ("tracing: Add simple expression support to hist triggers")
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
When working on my user space applications, I found a bug in the synthetic
event code where the automated synthetic event field was not matching the
event field calculation it was attached to. Looking deeper into it, it was
because the calculation hist_field was not given a size.
The synthetic event fields are matched to their hist_fields either by
having the field have an identical string type, or if that does not match,
then the size and signed values are used to match the fields.
The problem arose when I tried to match a calculation where the fields
were "unsigned int". My tool created a synthetic event of type "u32". But
it failed to match. The string was:
diff=field1-field2:onmatch(event).trace(synth,$diff)
Adding debugging into the kernel, I found that the size of "diff" was 0.
And since it was given "unsigned int" as a type, the histogram fallback
code used size and signed. The signed matched, but the size of u32 (4) did
not match zero, and the event failed to be created.
This can be worse if the field you want to match is not one of the
acceptable fields for a synthetic event. As event fields can have any type
that is supported in Linux, this can cause an issue. For example, if a
type is an enum. Then there's no way to use that with any calculations.
Have the calculation field simply take on the size of what it is
calculating.
Link: https://lkml.kernel.org/r/20210730171951.59c7743f@oasis.local.home
Cc: Tom Zanussi <zanussi@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: stable@vger.kernel.org
Fixes: 100719dcef ("tracing: Add simple expression support to hist triggers")
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Double enqueues in rt runqueues (list) have been reported while running
a simple test that spawns a number of threads doing a short sleep/run
pattern while being concurrently setscheduled between rt and fair class.
WARNING: CPU: 3 PID: 2825 at kernel/sched/rt.c:1294 enqueue_task_rt+0x355/0x360
CPU: 3 PID: 2825 Comm: setsched__13
RIP: 0010:enqueue_task_rt+0x355/0x360
Call Trace:
__sched_setscheduler+0x581/0x9d0
_sched_setscheduler+0x63/0xa0
do_sched_setscheduler+0xa0/0x150
__x64_sys_sched_setscheduler+0x1a/0x30
do_syscall_64+0x33/0x40
entry_SYSCALL_64_after_hwframe+0x44/0xae
list_add double add: new=ffff9867cb629b40, prev=ffff9867cb629b40,
next=ffff98679fc67ca0.
kernel BUG at lib/list_debug.c:31!
invalid opcode: 0000 [#1] PREEMPT_RT SMP PTI
CPU: 3 PID: 2825 Comm: setsched__13
RIP: 0010:__list_add_valid+0x41/0x50
Call Trace:
enqueue_task_rt+0x291/0x360
__sched_setscheduler+0x581/0x9d0
_sched_setscheduler+0x63/0xa0
do_sched_setscheduler+0xa0/0x150
__x64_sys_sched_setscheduler+0x1a/0x30
do_syscall_64+0x33/0x40
entry_SYSCALL_64_after_hwframe+0x44/0xae
__sched_setscheduler() uses rt_effective_prio() to handle proper queuing
of priority boosted tasks that are setscheduled while being boosted.
rt_effective_prio() is however called twice per each
__sched_setscheduler() call: first directly by __sched_setscheduler()
before dequeuing the task and then by __setscheduler() to actually do
the priority change. If the priority of the pi_top_task is concurrently
being changed however, it might happen that the two calls return
different results. If, for example, the first call returned the same rt
priority the task was running at and the second one a fair priority, the
task won't be removed by the rt list (on_list still set) and then
enqueued in the fair runqueue. When eventually setscheduled back to rt
it will be seen as enqueued already and the WARNING/BUG be issued.
Fix this by calling rt_effective_prio() only once and then reusing the
return value. While at it refactor code as well for clarity. Concurrent
priority inheritance handling is still safe and will eventually converge
to a new state by following the inheritance chain(s).
Fixes: 0782e63bc6 ("sched: Handle priority boosted tasks proper in setscheduler()")
[squashed Peterz changes; added changelog]
Reported-by: Mark Simmons <msimmons@redhat.com>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210803104501.38333-1-juri.lelli@redhat.com
and netfilter trees.
Current release - regressions:
- mac80211: fix starting aggregation sessions on mesh interfaces
Current release - new code bugs:
- sctp: send pmtu probe only if packet loss in Search Complete state
- bnxt_en: add missing periodic PHC overflow check
- devlink: fix phys_port_name of virtual port and merge error
- hns3: change the method of obtaining default ptp cycle
- can: mcba_usb_start(): add missing urb->transfer_dma initialization
Previous releases - regressions:
- set true network header for ECN decapsulation
- mlx5e: RX, avoid possible data corruption w/ relaxed ordering and LRO
- phy: re-add check for PHY_BRCM_DIS_TXCRXC_NOENRGY on the BCM54811 PHY
- sctp: fix return value check in __sctp_rcv_asconf_lookup
Previous releases - always broken:
- bpf:
- more spectre corner case fixes, introduce a BPF nospec
instruction for mitigating Spectre v4
- fix OOB read when printing XDP link fdinfo
- sockmap: fix cleanup related races
- mac80211: fix enabling 4-address mode on a sta vif after assoc
- can:
- raw: raw_setsockopt(): fix raw_rcv panic for sock UAF
- j1939: j1939_session_deactivate(): clarify lifetime of
session object, avoid UAF
- fix number of identical memory leaks in USB drivers
- tipc:
- do not blindly write skb_shinfo frags when doing decryption
- fix sleeping in tipc accept routine
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----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=sKPI
-----END PGP SIGNATURE-----
Merge tag 'net-5.14-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Networking fixes for 5.14-rc4, including fixes from bpf, can, WiFi
(mac80211) and netfilter trees.
Current release - regressions:
- mac80211: fix starting aggregation sessions on mesh interfaces
Current release - new code bugs:
- sctp: send pmtu probe only if packet loss in Search Complete state
- bnxt_en: add missing periodic PHC overflow check
- devlink: fix phys_port_name of virtual port and merge error
- hns3: change the method of obtaining default ptp cycle
- can: mcba_usb_start(): add missing urb->transfer_dma initialization
Previous releases - regressions:
- set true network header for ECN decapsulation
- mlx5e: RX, avoid possible data corruption w/ relaxed ordering and
LRO
- phy: re-add check for PHY_BRCM_DIS_TXCRXC_NOENRGY on the BCM54811
PHY
- sctp: fix return value check in __sctp_rcv_asconf_lookup
Previous releases - always broken:
- bpf:
- more spectre corner case fixes, introduce a BPF nospec
instruction for mitigating Spectre v4
- fix OOB read when printing XDP link fdinfo
- sockmap: fix cleanup related races
- mac80211: fix enabling 4-address mode on a sta vif after assoc
- can:
- raw: raw_setsockopt(): fix raw_rcv panic for sock UAF
- j1939: j1939_session_deactivate(): clarify lifetime of session
object, avoid UAF
- fix number of identical memory leaks in USB drivers
- tipc:
- do not blindly write skb_shinfo frags when doing decryption
- fix sleeping in tipc accept routine"
* tag 'net-5.14-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (91 commits)
gve: Update MAINTAINERS list
can: esd_usb2: fix memory leak
can: ems_usb: fix memory leak
can: usb_8dev: fix memory leak
can: mcba_usb_start(): add missing urb->transfer_dma initialization
can: hi311x: fix a signedness bug in hi3110_cmd()
MAINTAINERS: add Yasushi SHOJI as reviewer for the Microchip CAN BUS Analyzer Tool driver
bpf: Fix leakage due to insufficient speculative store bypass mitigation
bpf: Introduce BPF nospec instruction for mitigating Spectre v4
sis900: Fix missing pci_disable_device() in probe and remove
net: let flow have same hash in two directions
nfc: nfcsim: fix use after free during module unload
tulip: windbond-840: Fix missing pci_disable_device() in probe and remove
sctp: fix return value check in __sctp_rcv_asconf_lookup
nfc: s3fwrn5: fix undefined parameter values in dev_err()
net/mlx5: Fix mlx5_vport_tbl_attr chain from u16 to u32
net/mlx5e: Fix nullptr in mlx5e_hairpin_get_mdev()
net/mlx5: Unload device upon firmware fatal error
net/mlx5e: Fix page allocation failure for ptp-RQ over SF
net/mlx5e: Fix page allocation failure for trap-RQ over SF
...
The event_trace_add_tracer() can fail. In this case, it leads to a crash
in start_creating with below call stack. Handle the error scenario
properly in trace_array_create_dir.
Call trace:
down_write+0x7c/0x204
start_creating.25017+0x6c/0x194
tracefs_create_file+0xc4/0x2b4
init_tracer_tracefs+0x5c/0x940
trace_array_create_dir+0x58/0xb4
trace_array_create+0x1bc/0x2b8
trace_array_get_by_name+0xdc/0x18c
Link: https://lkml.kernel.org/r/1627651386-21315-1-git-send-email-kamaagra@codeaurora.org
Cc: stable@vger.kernel.org
Fixes: 4114fbfd02 ("tracing: Enable creating new instance early boot")
Signed-off-by: Kamal Agrawal <kamaagra@codeaurora.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Daniel Borkmann says:
====================
pull-request: bpf 2021-07-29
The following pull-request contains BPF updates for your *net* tree.
We've added 9 non-merge commits during the last 14 day(s) which contain
a total of 20 files changed, 446 insertions(+), 138 deletions(-).
The main changes are:
1) Fix UBSAN out-of-bounds splat for showing XDP link fdinfo, from Lorenz Bauer.
2) Fix insufficient Spectre v4 mitigation in BPF runtime, from Daniel Borkmann,
Piotr Krysiuk and Benedict Schlueter.
3) Batch of fixes for BPF sockmap found under stress testing, from John Fastabend.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Spectre v4 gadgets make use of memory disambiguation, which is a set of
techniques that execute memory access instructions, that is, loads and
stores, out of program order; Intel's optimization manual, section 2.4.4.5:
A load instruction micro-op may depend on a preceding store. Many
microarchitectures block loads until all preceding store addresses are
known. The memory disambiguator predicts which loads will not depend on
any previous stores. When the disambiguator predicts that a load does
not have such a dependency, the load takes its data from the L1 data
cache. Eventually, the prediction is verified. If an actual conflict is
detected, the load and all succeeding instructions are re-executed.
af86ca4e30 ("bpf: Prevent memory disambiguation attack") tried to mitigate
this attack by sanitizing the memory locations through preemptive "fast"
(low latency) stores of zero prior to the actual "slow" (high latency) store
of a pointer value such that upon dependency misprediction the CPU then
speculatively executes the load of the pointer value and retrieves the zero
value instead of the attacker controlled scalar value previously stored at
that location, meaning, subsequent access in the speculative domain is then
redirected to the "zero page".
The sanitized preemptive store of zero prior to the actual "slow" store is
done through a simple ST instruction based on r10 (frame pointer) with
relative offset to the stack location that the verifier has been tracking
on the original used register for STX, which does not have to be r10. Thus,
there are no memory dependencies for this store, since it's only using r10
and immediate constant of zero; hence af86ca4e30 /assumed/ a low latency
operation.
However, a recent attack demonstrated that this mitigation is not sufficient
since the preemptive store of zero could also be turned into a "slow" store
and is thus bypassed as well:
[...]
// r2 = oob address (e.g. scalar)
// r7 = pointer to map value
31: (7b) *(u64 *)(r10 -16) = r2
// r9 will remain "fast" register, r10 will become "slow" register below
32: (bf) r9 = r10
// JIT maps BPF reg to x86 reg:
// r9 -> r15 (callee saved)
// r10 -> rbp
// train store forward prediction to break dependency link between both r9
// and r10 by evicting them from the predictor's LRU table.
33: (61) r0 = *(u32 *)(r7 +24576)
34: (63) *(u32 *)(r7 +29696) = r0
35: (61) r0 = *(u32 *)(r7 +24580)
36: (63) *(u32 *)(r7 +29700) = r0
37: (61) r0 = *(u32 *)(r7 +24584)
38: (63) *(u32 *)(r7 +29704) = r0
39: (61) r0 = *(u32 *)(r7 +24588)
40: (63) *(u32 *)(r7 +29708) = r0
[...]
543: (61) r0 = *(u32 *)(r7 +25596)
544: (63) *(u32 *)(r7 +30716) = r0
// prepare call to bpf_ringbuf_output() helper. the latter will cause rbp
// to spill to stack memory while r13/r14/r15 (all callee saved regs) remain
// in hardware registers. rbp becomes slow due to push/pop latency. below is
// disasm of bpf_ringbuf_output() helper for better visual context:
//
// ffffffff8117ee20: 41 54 push r12
// ffffffff8117ee22: 55 push rbp
// ffffffff8117ee23: 53 push rbx
// ffffffff8117ee24: 48 f7 c1 fc ff ff ff test rcx,0xfffffffffffffffc
// ffffffff8117ee2b: 0f 85 af 00 00 00 jne ffffffff8117eee0 <-- jump taken
// [...]
// ffffffff8117eee0: 49 c7 c4 ea ff ff ff mov r12,0xffffffffffffffea
// ffffffff8117eee7: 5b pop rbx
// ffffffff8117eee8: 5d pop rbp
// ffffffff8117eee9: 4c 89 e0 mov rax,r12
// ffffffff8117eeec: 41 5c pop r12
// ffffffff8117eeee: c3 ret
545: (18) r1 = map[id:4]
547: (bf) r2 = r7
548: (b7) r3 = 0
549: (b7) r4 = 4
550: (85) call bpf_ringbuf_output#194288
// instruction 551 inserted by verifier \
551: (7a) *(u64 *)(r10 -16) = 0 | /both/ are now slow stores here
// storing map value pointer r7 at fp-16 | since value of r10 is "slow".
552: (7b) *(u64 *)(r10 -16) = r7 /
// following "fast" read to the same memory location, but due to dependency
// misprediction it will speculatively execute before insn 551/552 completes.
553: (79) r2 = *(u64 *)(r9 -16)
// in speculative domain contains attacker controlled r2. in non-speculative
// domain this contains r7, and thus accesses r7 +0 below.
554: (71) r3 = *(u8 *)(r2 +0)
// leak r3
As can be seen, the current speculative store bypass mitigation which the
verifier inserts at line 551 is insufficient since /both/, the write of
the zero sanitation as well as the map value pointer are a high latency
instruction due to prior memory access via push/pop of r10 (rbp) in contrast
to the low latency read in line 553 as r9 (r15) which stays in hardware
registers. Thus, architecturally, fp-16 is r7, however, microarchitecturally,
fp-16 can still be r2.
Initial thoughts to address this issue was to track spilled pointer loads
from stack and enforce their load via LDX through r10 as well so that /both/
the preemptive store of zero /as well as/ the load use the /same/ register
such that a dependency is created between the store and load. However, this
option is not sufficient either since it can be bypassed as well under
speculation. An updated attack with pointer spill/fills now _all_ based on
r10 would look as follows:
[...]
// r2 = oob address (e.g. scalar)
// r7 = pointer to map value
[...]
// longer store forward prediction training sequence than before.
2062: (61) r0 = *(u32 *)(r7 +25588)
2063: (63) *(u32 *)(r7 +30708) = r0
2064: (61) r0 = *(u32 *)(r7 +25592)
2065: (63) *(u32 *)(r7 +30712) = r0
2066: (61) r0 = *(u32 *)(r7 +25596)
2067: (63) *(u32 *)(r7 +30716) = r0
// store the speculative load address (scalar) this time after the store
// forward prediction training.
2068: (7b) *(u64 *)(r10 -16) = r2
// preoccupy the CPU store port by running sequence of dummy stores.
2069: (63) *(u32 *)(r7 +29696) = r0
2070: (63) *(u32 *)(r7 +29700) = r0
2071: (63) *(u32 *)(r7 +29704) = r0
2072: (63) *(u32 *)(r7 +29708) = r0
2073: (63) *(u32 *)(r7 +29712) = r0
2074: (63) *(u32 *)(r7 +29716) = r0
2075: (63) *(u32 *)(r7 +29720) = r0
2076: (63) *(u32 *)(r7 +29724) = r0
2077: (63) *(u32 *)(r7 +29728) = r0
2078: (63) *(u32 *)(r7 +29732) = r0
2079: (63) *(u32 *)(r7 +29736) = r0
2080: (63) *(u32 *)(r7 +29740) = r0
2081: (63) *(u32 *)(r7 +29744) = r0
2082: (63) *(u32 *)(r7 +29748) = r0
2083: (63) *(u32 *)(r7 +29752) = r0
2084: (63) *(u32 *)(r7 +29756) = r0
2085: (63) *(u32 *)(r7 +29760) = r0
2086: (63) *(u32 *)(r7 +29764) = r0
2087: (63) *(u32 *)(r7 +29768) = r0
2088: (63) *(u32 *)(r7 +29772) = r0
2089: (63) *(u32 *)(r7 +29776) = r0
2090: (63) *(u32 *)(r7 +29780) = r0
2091: (63) *(u32 *)(r7 +29784) = r0
2092: (63) *(u32 *)(r7 +29788) = r0
2093: (63) *(u32 *)(r7 +29792) = r0
2094: (63) *(u32 *)(r7 +29796) = r0
2095: (63) *(u32 *)(r7 +29800) = r0
2096: (63) *(u32 *)(r7 +29804) = r0
2097: (63) *(u32 *)(r7 +29808) = r0
2098: (63) *(u32 *)(r7 +29812) = r0
// overwrite scalar with dummy pointer; same as before, also including the
// sanitation store with 0 from the current mitigation by the verifier.
2099: (7a) *(u64 *)(r10 -16) = 0 | /both/ are now slow stores here
2100: (7b) *(u64 *)(r10 -16) = r7 | since store unit is still busy.
// load from stack intended to bypass stores.
2101: (79) r2 = *(u64 *)(r10 -16)
2102: (71) r3 = *(u8 *)(r2 +0)
// leak r3
[...]
Looking at the CPU microarchitecture, the scheduler might issue loads (such
as seen in line 2101) before stores (line 2099,2100) because the load execution
units become available while the store execution unit is still busy with the
sequence of dummy stores (line 2069-2098). And so the load may use the prior
stored scalar from r2 at address r10 -16 for speculation. The updated attack
may work less reliable on CPU microarchitectures where loads and stores share
execution resources.
This concludes that the sanitizing with zero stores from af86ca4e30 ("bpf:
Prevent memory disambiguation attack") is insufficient. Moreover, the detection
of stack reuse from af86ca4e30 where previously data (STACK_MISC) has been
written to a given stack slot where a pointer value is now to be stored does
not have sufficient coverage as precondition for the mitigation either; for
several reasons outlined as follows:
1) Stack content from prior program runs could still be preserved and is
therefore not "random", best example is to split a speculative store
bypass attack between tail calls, program A would prepare and store the
oob address at a given stack slot and then tail call into program B which
does the "slow" store of a pointer to the stack with subsequent "fast"
read. From program B PoV such stack slot type is STACK_INVALID, and
therefore also must be subject to mitigation.
2) The STACK_SPILL must not be coupled to register_is_const(&stack->spilled_ptr)
condition, for example, the previous content of that memory location could
also be a pointer to map or map value. Without the fix, a speculative
store bypass is not mitigated in such precondition and can then lead to
a type confusion in the speculative domain leaking kernel memory near
these pointer types.
While brainstorming on various alternative mitigation possibilities, we also
stumbled upon a retrospective from Chrome developers [0]:
[...] For variant 4, we implemented a mitigation to zero the unused memory
of the heap prior to allocation, which cost about 1% when done concurrently
and 4% for scavenging. Variant 4 defeats everything we could think of. We
explored more mitigations for variant 4 but the threat proved to be more
pervasive and dangerous than we anticipated. For example, stack slots used
by the register allocator in the optimizing compiler could be subject to
type confusion, leading to pointer crafting. Mitigating type confusion for
stack slots alone would have required a complete redesign of the backend of
the optimizing compiler, perhaps man years of work, without a guarantee of
completeness. [...]
From BPF side, the problem space is reduced, however, options are rather
limited. One idea that has been explored was to xor-obfuscate pointer spills
to the BPF stack:
[...]
// preoccupy the CPU store port by running sequence of dummy stores.
[...]
2106: (63) *(u32 *)(r7 +29796) = r0
2107: (63) *(u32 *)(r7 +29800) = r0
2108: (63) *(u32 *)(r7 +29804) = r0
2109: (63) *(u32 *)(r7 +29808) = r0
2110: (63) *(u32 *)(r7 +29812) = r0
// overwrite scalar with dummy pointer; xored with random 'secret' value
// of 943576462 before store ...
2111: (b4) w11 = 943576462
2112: (af) r11 ^= r7
2113: (7b) *(u64 *)(r10 -16) = r11
2114: (79) r11 = *(u64 *)(r10 -16)
2115: (b4) w2 = 943576462
2116: (af) r2 ^= r11
// ... and restored with the same 'secret' value with the help of AX reg.
2117: (71) r3 = *(u8 *)(r2 +0)
[...]
While the above would not prevent speculation, it would make data leakage
infeasible by directing it to random locations. In order to be effective
and prevent type confusion under speculation, such random secret would have
to be regenerated for each store. The additional complexity involved for a
tracking mechanism that prevents jumps such that restoring spilled pointers
would not get corrupted is not worth the gain for unprivileged. Hence, the
fix in here eventually opted for emitting a non-public BPF_ST | BPF_NOSPEC
instruction which the x86 JIT translates into a lfence opcode. Inserting the
latter in between the store and load instruction is one of the mitigations
options [1]. The x86 instruction manual notes:
[...] An LFENCE that follows an instruction that stores to memory might
complete before the data being stored have become globally visible. [...]
The latter meaning that the preceding store instruction finished execution
and the store is at minimum guaranteed to be in the CPU's store queue, but
it's not guaranteed to be in that CPU's L1 cache at that point (globally
visible). The latter would only be guaranteed via sfence. So the load which
is guaranteed to execute after the lfence for that local CPU would have to
rely on store-to-load forwarding. [2], in section 2.3 on store buffers says:
[...] For every store operation that is added to the ROB, an entry is
allocated in the store buffer. This entry requires both the virtual and
physical address of the target. Only if there is no free entry in the store
buffer, the frontend stalls until there is an empty slot available in the
store buffer again. Otherwise, the CPU can immediately continue adding
subsequent instructions to the ROB and execute them out of order. On Intel
CPUs, the store buffer has up to 56 entries. [...]
One small upside on the fix is that it lifts constraints from af86ca4e30
where the sanitize_stack_off relative to r10 must be the same when coming
from different paths. The BPF_ST | BPF_NOSPEC gets emitted after a BPF_STX
or BPF_ST instruction. This happens either when we store a pointer or data
value to the BPF stack for the first time, or upon later pointer spills.
The former needs to be enforced since otherwise stale stack data could be
leaked under speculation as outlined earlier. For non-x86 JITs the BPF_ST |
BPF_NOSPEC mapping is currently optimized away, but others could emit a
speculation barrier as well if necessary. For real-world unprivileged
programs e.g. generated by LLVM, pointer spill/fill is only generated upon
register pressure and LLVM only tries to do that for pointers which are not
used often. The program main impact will be the initial BPF_ST | BPF_NOSPEC
sanitation for the STACK_INVALID case when the first write to a stack slot
occurs e.g. upon map lookup. In future we might refine ways to mitigate
the latter cost.
[0] https://arxiv.org/pdf/1902.05178.pdf
[1] https://msrc-blog.microsoft.com/2018/05/21/analysis-and-mitigation-of-speculative-store-bypass-cve-2018-3639/
[2] https://arxiv.org/pdf/1905.05725.pdf
Fixes: af86ca4e30 ("bpf: Prevent memory disambiguation attack")
Fixes: f7cf25b202 ("bpf: track spill/fill of constants")
Co-developed-by: Piotr Krysiuk <piotras@gmail.com>
Co-developed-by: Benedict Schlueter <benedict.schlueter@rub.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Piotr Krysiuk <piotras@gmail.com>
Signed-off-by: Benedict Schlueter <benedict.schlueter@rub.de>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Thomas Gleixner