Long ago, RCU used the stop-machine mechanism to implement expedited
grace periods, but no longer does so. This commit therefore removes
the no-longer-needed #includes of linux/stop_machine.h.
Link: https://lwn.net/Articles/805317/
Reported-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The ->srcu_last_gp_end field is accessed from any CPU at any time
by synchronize_srcu(), so non-initialization references need to use
READ_ONCE() and WRITE_ONCE(). This commit therefore makes that change.
Reported-by: syzbot+08f3e9d26e5541e1ecf2@syzkaller.appspotmail.com
Acked-by: Marco Elver <elver@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently, force_qs_rnp() uses a for_each_leaf_node_possible_cpu()
loop containing a check of the current CPU's bit in ->qsmask.
This works, but this commit saves three lines by instead using
for_each_leaf_node_cpu_mask(), which combines the functionality of
for_each_leaf_node_possible_cpu() and leaf_node_cpu_bit(). This commit
also replaces the use of the local variable "bit" with rdp->grpmask.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit moves the rcu_{expedited,normal} definitions from
kernel/rcu/update.c to include/linux/rcupdate.h to make sure they are
in sync, and also to avoid the following warning from sparse:
kernel/ksysfs.c:150:5: warning: symbol 'rcu_expedited' was not declared. Should it be static?
kernel/ksysfs.c:167:5: warning: symbol 'rcu_normal' was not declared. Should it be static?
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Only tree_stall.h needs to get name from GP state, so this commit
moves the gp_state_names[] array and the gp_state_getname()
from kernel/rcu/tree.h and kernel/rcu/tree.c, respectively, to
kernel/rcu/tree_stall.h. While moving gp_state_names[], this commit
uses the GCC syntax to ensure that the right string is associated with
the right CPP macro.
Signed-off-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The call_rcu() function is an external RCU API that is declared in
include/linux/rcupdate.h. There is thus no point in redeclaring it
in kernel/rcu/tree.h, so this commit removes that redundant declaration.
Signed-off-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
In the call to trace_rcu_utilization() at the start of the loop in
rcu_cpu_kthread(), "rcu_wait" is incorrect, plus this trace event needs
to be hoisted above the loop to balance with either the "rcu_wait" or
"rcu_yield", depending on how the loop exits. This commit therefore
makes these changes.
Signed-off-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The C preprocessor macros SRCU and TINY_RCU should instead be CONFIG_SRCU
and CONFIG_TINY_RCU, respectively in the #f in kernel/rcu/rcu.h. But
there is no harm when "TINY_RCU" is wrongly used, which are always
non-defined, which makes "!defined(TINY_RCU)" always true, which means
the code block is always included, and the included code block doesn't
cause any compilation error so far in CONFIG_TINY_RCU builds. It is
also the reason this change should not be taken in -stable.
This commit adds the needed "CONFIG_" prefix to both macros.
Not for -stable.
Signed-off-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
In the current code, rcu_nmi_enter_common() might decide to turn on
the tick using tick_dep_set_cpu(), but be delayed just before doing so.
Then the grace-period kthread might notice that the CPU in question had
in fact gone through a quiescent state, thus turning off the tick using
tick_dep_clear_cpu(). The later invocation of tick_dep_set_cpu() would
then incorrectly leave the tick on.
This commit therefore enlists the aid of the leaf rcu_node structure's
->lock to ensure that decisions to enable or disable the tick are
carried out before they can be reversed.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit provides wrapper functions for uses of ->rcu_read_lock_nesting
to improve readability and to ease future changes to support inlining
of __rcu_read_lock() and __rcu_read_unlock().
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_node structure's ->expmask field is updated only when holding the
->lock, but is also accessed locklessly. This means that all ->expmask
updates must use WRITE_ONCE() and all reads carried out without holding
->lock must use READ_ONCE(). This commit therefore changes the lockless
->expmask read in rcu_read_unlock_special() to use READ_ONCE().
Reported-by: syzbot+99f4ddade3c22ab0cf23@syzkaller.appspotmail.com
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Acked-by: Marco Elver <elver@google.com>
In rcu_preempt_deferred_qs_irqrestore(), ->rcu_read_unlock_special is
cleared one piece at a time. Given that the "if" statements in this
function use the copy in "special", this commit removes the clearing
of the individual pieces in favor of clearing ->rcu_read_unlock_special
in one go just after it has been determined to be non-zero.
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently, the .exp_hint flag is cleared in rcu_read_unlock_special(),
which works, but which can also prevent subsequent rcu_read_unlock() calls
from helping expedite the quiescent state needed by an ongoing expedited
RCU grace period. This commit therefore defers clearing of .exp_hint
from rcu_read_unlock_special() to rcu_preempt_deferred_qs_irqrestore(),
thus ensuring that intervening calls to rcu_read_unlock() have a chance
to help end the expedited grace period.
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
CONFIG_PREEMPTION and CONFIG_PREEMPT_RCU are always identical,
but some code depends on CONFIG_PREEMPTION to access to
rcu_preempt functionality. This patch changes CONFIG_PREEMPTION
to CONFIG_PREEMPT_RCU in these cases.
Signed-off-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Now that the kfree_rcu() special-casing has been removed from tree RCU,
this commit removes kfree_call_rcu_nobatch() since it is no longer needed.
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit removes kfree_rcu() special-casing and the lazy-callback
handling from Tree RCU. It moves some of this special casing to Tiny RCU,
the removal of which will be the subject of later commits.
This results in a nice negative delta.
Suggested-by: Paul E. McKenney <paulmck@linux.ibm.com>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
[ paulmck: Add slab.h #include, thanks to kbuild test robot <lkp@intel.com>. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit applies RCU's debug_objects debugging to the new batched
kfree_rcu() implementations. The object is queued at the kfree_rcu()
call and dequeued during reclaim.
Tested that enabling CONFIG_DEBUG_OBJECTS_RCU_HEAD successfully detects
double kfree_rcu() calls.
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
[ paulmck: Fix IRQ per kbuild test robot <lkp@intel.com> feedback. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
During testing, it was observed that amount of memory consumed due
kfree_rcu() batching is 300-400MB. Previously we had only a single
head_free pointer pointing to the list of rcu_head(s) that are to be
freed after a grace period. Until this list is drained, we cannot queue
any more objects on it since such objects may not be ready to be
reclaimed when the worker thread eventually gets to drainin g the
head_free list.
We can do better by maintaining multiple lists as done by this patch.
Testing shows that memory consumption came down by around 100-150MB with
just adding another list. Adding more than 1 additional list did not
show any improvement.
Suggested-by: Paul E. McKenney <paulmck@linux.ibm.com>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
[ paulmck: Code style and initialization handling. ]
[ paulmck: Fix field name, reported by kbuild test robot <lkp@intel.com>. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Because the ->monitor_todo field is always protected by krcp->lock,
this commit downgrades from xchg() to non-atomic unmarked assignment
statements.
Signed-off-by: Joel Fernandes <joel@joelfernandes.org>
[ paulmck: Update to include early-boot kick code. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This test runs kfree_rcu() in a loop to measure performance of the new
kfree_rcu() batching functionality.
The following table shows results when booting with arguments:
rcuperf.kfree_loops=20000 rcuperf.kfree_alloc_num=8000
rcuperf.kfree_rcu_test=1 rcuperf.kfree_no_batch=X
rcuperf.kfree_no_batch=X # Grace Periods Test Duration (s)
X=1 (old behavior) 9133 11.5
X=0 (new behavior) 1732 12.5
On a 16 CPU system with the above boot parameters, we see that the total
number of grace periods that elapse during the test drops from 9133 when
not batching to 1732 when batching (a 5X improvement). The kfree_rcu()
flood itself slows down a bit when batching, though, as shown.
Note that the active memory consumption during the kfree_rcu() flood
does increase to around 200-250MB due to the batching (from around 50MB
without batching). However, this memory consumption is relatively
constant. In other words, the system is able to keep up with the
kfree_rcu() load. The memory consumption comes down considerably if
KFREE_DRAIN_JIFFIES is increased from HZ/50 to HZ/80. A later patch will
reduce memory consumption further by using multiple lists.
Also, when running the test, please disable CONFIG_DEBUG_PREEMPT and
CONFIG_PROVE_RCU for realistic comparisons with/without batching.
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Recently a discussion about stability and performance of a system
involving a high rate of kfree_rcu() calls surfaced on the list [1]
which led to another discussion how to prepare for this situation.
This patch adds basic batching support for kfree_rcu(). It is "basic"
because we do none of the slab management, dynamic allocation, code
moving or any of the other things, some of which previous attempts did
[2]. These fancier improvements can be follow-up patches and there are
different ideas being discussed in those regards. This is an effort to
start simple, and build up from there. In the future, an extension to
use kfree_bulk and possibly per-slab batching could be done to further
improve performance due to cache-locality and slab-specific bulk free
optimizations. By using an array of pointers, the worker thread
processing the work would need to read lesser data since it does not
need to deal with large rcu_head(s) any longer.
Torture tests follow in the next patch and show improvements of around
5x reduction in number of grace periods on a 16 CPU system. More
details and test data are in that patch.
There is an implication with rcu_barrier() with this patch. Since the
kfree_rcu() calls can be batched, and may not be handed yet to the RCU
machinery in fact, the monitor may not have even run yet to do the
queue_rcu_work(), there seems no easy way of implementing rcu_barrier()
to wait for those kfree_rcu()s that are already made. So this means a
kfree_rcu() followed by an rcu_barrier() does not imply that memory will
be freed once rcu_barrier() returns.
Another implication is higher active memory usage (although not
run-away..) until the kfree_rcu() flooding ends, in comparison to
without batching. More details about this are in the second patch which
adds an rcuperf test.
Finally, in the near future we will get rid of kfree_rcu() special casing
within RCU such as in rcu_do_batch and switch everything to just
batching. Currently we don't do that since timer subsystem is not yet up
and we cannot schedule the kfree_rcu() monitor as the timer subsystem's
lock are not initialized. That would also mean getting rid of
kfree_call_rcu_nobatch() entirely.
[1] http://lore.kernel.org/lkml/20190723035725-mutt-send-email-mst@kernel.org
[2] https://lkml.org/lkml/2017/12/19/824
Cc: kernel-team@android.com
Cc: kernel-team@lge.com
Co-developed-by: Byungchul Park <byungchul.park@lge.com>
Signed-off-by: Byungchul Park <byungchul.park@lge.com>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
[ paulmck: Applied 0day and Paul Walmsley feedback on ->monitor_todo. ]
[ paulmck: Make it work during early boot. ]
[ paulmck: Add a crude early boot self-test. ]
[ paulmck: Style adjustments and experimental docbook structure header. ]
Link: https://lore.kernel.org/lkml/alpine.DEB.2.21.9999.1908161931110.32497@viisi.sifive.com/T/#me9956f66cb611b95d26ae92700e1d901f46e8c59
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Pull tracing fixes from Steven Rostedt:
"Various tracing fixes:
- Fix a function comparison warning for a xen trace event macro
- Fix a double perf_event linking to a trace_uprobe_filter for
multiple events
- Fix suspicious RCU warnings in trace event code for using
list_for_each_entry_rcu() when the "_rcu" portion wasn't needed.
- Fix a bug in the histogram code when using the same variable
- Fix a NULL pointer dereference when tracefs lockdown enabled and
calling trace_set_default_clock()
- A fix to a bug found with the double perf_event linking patch"
* tag 'trace-v5.5-rc6-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
tracing/uprobe: Fix to make trace_uprobe_filter alignment safe
tracing: Do not set trace clock if tracefs lockdown is in effect
tracing: Fix histogram code when expression has same var as value
tracing: trigger: Replace unneeded RCU-list traversals
tracing/uprobe: Fix double perf_event linking on multiprobe uprobe
tracing: xen: Ordered comparison of function pointers
Pull power management fix from Rafael Wysocki:
"Prevent the kernel from crashing during resume from hibernation if
free pages contain leftover data from the restore kernel and
init_on_free is set (Alexander Potapenko)"
* tag 'pm-5.5-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
PM: hibernate: fix crashes with init_on_free=1
While working on a tool to convert SQL syntex into the histogram language of
the kernel, I discovered the following bug:
# echo 'first u64 start_time u64 end_time pid_t pid u64 delta' >> synthetic_events
# echo 'hist:keys=pid:start=common_timestamp' > events/sched/sched_waking/trigger
# echo 'hist:keys=next_pid:delta=common_timestamp-$start,start2=$start:onmatch(sched.sched_waking).trace(first,$start2,common_timestamp,next_pid,$delta)' > events/sched/sched_switch/trigger
Would not display any histograms in the sched_switch histogram side.
But if I were to swap the location of
"delta=common_timestamp-$start" with "start2=$start"
Such that the last line had:
# echo 'hist:keys=next_pid:start2=$start,delta=common_timestamp-$start:onmatch(sched.sched_waking).trace(first,$start2,common_timestamp,next_pid,$delta)' > events/sched/sched_switch/trigger
The histogram works as expected.
What I found out is that the expressions clear out the value once it is
resolved. As the variables are resolved in the order listed, when
processing:
delta=common_timestamp-$start
The $start is cleared. When it gets to "start2=$start", it errors out with
"unresolved symbol" (which is silent as this happens at the location of the
trace), and the histogram is dropped.
When processing the histogram for variable references, instead of adding a
new reference for a variable used twice, use the same reference. That way,
not only is it more efficient, but the order will no longer matter in
processing of the variables.
From Tom Zanussi:
"Just to clarify some more about what the problem was is that without
your patch, we would have two separate references to the same variable,
and during resolve_var_refs(), they'd both want to be resolved
separately, so in this case, since the first reference to start wasn't
part of an expression, it wouldn't get the read-once flag set, so would
be read normally, and then the second reference would do the read-once
read and also be read but using read-once. So everything worked and
you didn't see a problem:
from: start2=$start,delta=common_timestamp-$start
In the second case, when you switched them around, the first reference
would be resolved by doing the read-once, and following that the second
reference would try to resolve and see that the variable had already
been read, so failed as unset, which caused it to short-circuit out and
not do the trigger action to generate the synthetic event:
to: delta=common_timestamp-$start,start2=$start
With your patch, we only have the single resolution which happens
correctly the one time it's resolved, so this can't happen."
Link: https://lore.kernel.org/r/20200116154216.58ca08eb@gandalf.local.home
Cc: stable@vger.kernel.org
Fixes: 067fe038e7 ("tracing: Add variable reference handling to hist triggers")
Reviewed-by: Tom Zanuss <zanussi@kernel.org>
Tested-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Pull networking fixes from David Miller:
1) Fix non-blocking connect() in x25, from Martin Schiller.
2) Fix spurious decryption errors in kTLS, from Jakub Kicinski.
3) Netfilter use-after-free in mtype_destroy(), from Cong Wang.
4) Limit size of TSO packets properly in lan78xx driver, from Eric
Dumazet.
5) r8152 probe needs an endpoint sanity check, from Johan Hovold.
6) Prevent looping in tcp_bpf_unhash() during sockmap/tls free, from
John Fastabend.
7) hns3 needs short frames padded on transmit, from Yunsheng Lin.
8) Fix netfilter ICMP header corruption, from Eyal Birger.
9) Fix soft lockup when low on memory in hns3, from Yonglong Liu.
10) Fix NTUPLE firmware command failures in bnxt_en, from Michael Chan.
11) Fix memory leak in act_ctinfo, from Eric Dumazet.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (91 commits)
cxgb4: reject overlapped queues in TC-MQPRIO offload
cxgb4: fix Tx multi channel port rate limit
net: sched: act_ctinfo: fix memory leak
bnxt_en: Do not treat DSN (Digital Serial Number) read failure as fatal.
bnxt_en: Fix ipv6 RFS filter matching logic.
bnxt_en: Fix NTUPLE firmware command failures.
net: systemport: Fixed queue mapping in internal ring map
net: dsa: bcm_sf2: Configure IMP port for 2Gb/sec
net: dsa: sja1105: Don't error out on disabled ports with no phy-mode
net: phy: dp83867: Set FORCE_LINK_GOOD to default after reset
net: hns: fix soft lockup when there is not enough memory
net: avoid updating qdisc_xmit_lock_key in netdev_update_lockdep_key()
net/sched: act_ife: initalize ife->metalist earlier
netfilter: nat: fix ICMP header corruption on ICMP errors
net: wan: lapbether.c: Use built-in RCU list checking
netfilter: nf_tables: fix flowtable list del corruption
netfilter: nf_tables: fix memory leak in nf_tables_parse_netdev_hooks()
netfilter: nf_tables: remove WARN and add NLA_STRING upper limits
netfilter: nft_tunnel: ERSPAN_VERSION must not be null
netfilter: nft_tunnel: fix null-attribute check
...
Pull timer fixes from Ingo Molnar:
"Three fixes: fix link failure on Alpha, fix a Sparse warning and
annotate/robustify a lockless access in the NOHZ code"
* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
tick/sched: Annotate lockless access to last_jiffies_update
lib/vdso: Make __cvdso_clock_getres() static
time/posix-stubs: Provide compat itimer supoprt for alpha
Pull cpu/SMT fix from Ingo Molnar:
"Fix a build bug on CONFIG_HOTPLUG_SMT=y && !CONFIG_SYSFS kernels"
* 'smp-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
cpu/SMT: Fix x86 link error without CONFIG_SYSFS
Pull perf fixes from Ingo Molnar:
"Tooling fixes, three Intel uncore driver fixes, plus an AUX events fix
uncovered by the perf fuzzer"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/intel/uncore: Remove PCIe3 unit for SNR
perf/x86/intel/uncore: Fix missing marker for snr_uncore_imc_freerunning_events
perf/x86/intel/uncore: Add PCI ID of IMC for Xeon E3 V5 Family
perf: Correctly handle failed perf_get_aux_event()
perf hists: Fix variable name's inconsistency in hists__for_each() macro
perf map: Set kmap->kmaps backpointer for main kernel map chunks
perf report: Fix incorrectly added dimensions as switch perf data file
tools lib traceevent: Fix memory leakage in filter_event
Pull locking fixes from Ingo Molnar:
"Three fixes:
- Fix an rwsem spin-on-owner crash, introduced in v5.4
- Fix a lockdep bug when running out of stack_trace entries,
introduced in v5.4
- Docbook fix"
* 'locking-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
locking/rwsem: Fix kernel crash when spinning on RWSEM_OWNER_UNKNOWN
futex: Fix kernel-doc notation warning
locking/lockdep: Fix buffer overrun problem in stack_trace[]
Pull rseq fixes from Ingo Molnar:
"Two rseq bugfixes:
- CLONE_VM !CLONE_THREAD didn't work properly, the kernel would end
up corrupting the TLS of the parent. Technically a change in the
ABI but the previous behavior couldn't resonably have been relied
on by applications so this looks like a valid exception to the ABI
rule.
- Make the RSEQ_FLAG_UNREGISTER ABI behavior consistent with the
handling of other flags. This is not thought to impact any
applications either"
* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
rseq: Unregister rseq for clone CLONE_VM
rseq: Reject unknown flags on rseq unregister
Pull thread fixes from Christian Brauner:
"Here is an urgent fix for ptrace_may_access() permission checking.
Commit 69f594a389 ("ptrace: do not audit capability check when
outputing /proc/pid/stat") introduced the ability to opt out of audit
messages for accesses to various proc files since they are not
violations of policy.
While doing so it switched the check from ns_capable() to
has_ns_capability{_noaudit}(). That means it switched from checking
the subjective credentials (ktask->cred) of the task to using the
objective credentials (ktask->real_cred). This is appears to be wrong.
ptrace_has_cap() is currently only used in ptrace_may_access() And is
used to check whether the calling task (subject) has the
CAP_SYS_PTRACE capability in the provided user namespace to operate on
the target task (object). According to the cred.h comments this means
the subjective credentials of the calling task need to be used.
With this fix we switch ptrace_has_cap() to use security_capable() and
thus back to using the subjective credentials.
As one example where this might be particularly problematic, Jann
pointed out that in combination with the upcoming IORING_OP_OPENAT{2}
feature, this bug might allow unprivileged users to bypass the
capability checks while asynchronously opening files like /proc/*/mem,
because the capability checks for this would be performed against
kernel credentials.
To illustrate on the former point about this being exploitable: When
io_uring creates a new context it records the subjective credentials
of the caller. Later on, when it starts to do work it creates a kernel
thread and registers a callback. The callback runs with kernel creds
for ktask->real_cred and ktask->cred.
To prevent this from becoming a full-blown 0-day io_uring will call
override_cred() and override ktask->cred with the subjective
credentials of the creator of the io_uring instance. With
ptrace_has_cap() currently looking at ktask->real_cred this override
will be ineffective and the caller will be able to open arbitray proc
files as mentioned above.
Luckily, this is currently not exploitable but would be so once
IORING_OP_OPENAT{2} land in v5.6. Let's fix it now.
To minimize potential regressions I successfully ran the criu
testsuite. criu makes heavy use of ptrace() and extensively hits
ptrace_may_access() codepaths and has a good change of detecting any
regressions.
Additionally, I succesfully ran the ptrace and seccomp kernel tests"
* tag 'for-linus-2020-01-18' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
ptrace: reintroduce usage of subjective credentials in ptrace_has_cap()
Commit 69f594a389 ("ptrace: do not audit capability check when outputing /proc/pid/stat")
introduced the ability to opt out of audit messages for accesses to various
proc files since they are not violations of policy. While doing so it
somehow switched the check from ns_capable() to
has_ns_capability{_noaudit}(). That means it switched from checking the
subjective credentials of the task to using the objective credentials. This
is wrong since. ptrace_has_cap() is currently only used in
ptrace_may_access() And is used to check whether the calling task (subject)
has the CAP_SYS_PTRACE capability in the provided user namespace to operate
on the target task (object). According to the cred.h comments this would
mean the subjective credentials of the calling task need to be used.
This switches ptrace_has_cap() to use security_capable(). Because we only
call ptrace_has_cap() in ptrace_may_access() and in there we already have a
stable reference to the calling task's creds under rcu_read_lock() there's
no need to go through another series of dereferences and rcu locking done
in ns_capable{_noaudit}().
As one example where this might be particularly problematic, Jann pointed
out that in combination with the upcoming IORING_OP_OPENAT feature, this
bug might allow unprivileged users to bypass the capability checks while
asynchronously opening files like /proc/*/mem, because the capability
checks for this would be performed against kernel credentials.
To illustrate on the former point about this being exploitable: When
io_uring creates a new context it records the subjective credentials of the
caller. Later on, when it starts to do work it creates a kernel thread and
registers a callback. The callback runs with kernel creds for
ktask->real_cred and ktask->cred. To prevent this from becoming a
full-blown 0-day io_uring will call override_cred() and override
ktask->cred with the subjective credentials of the creator of the io_uring
instance. With ptrace_has_cap() currently looking at ktask->real_cred this
override will be ineffective and the caller will be able to open arbitray
proc files as mentioned above.
Luckily, this is currently not exploitable but will turn into a 0-day once
IORING_OP_OPENAT{2} land in v5.6. Fix it now!
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Eric Paris <eparis@redhat.com>
Cc: stable@vger.kernel.org
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Reviewed-by: Jann Horn <jannh@google.com>
Fixes: 69f594a389 ("ptrace: do not audit capability check when outputing /proc/pid/stat")
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Vince reports a worrying issue:
| so I was tracking down some odd behavior in the perf_fuzzer which turns
| out to be because perf_even_open() sometimes returns 0 (indicating a file
| descriptor of 0) even though as far as I can tell stdin is still open.
... and further the cause:
| error is triggered if aux_sample_size has non-zero value.
|
| seems to be this line in kernel/events/core.c:
|
| if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader))
| goto err_locked;
|
| (note, err is never set)
This seems to be a thinko in commit:
ab43762ef0 ("perf: Allow normal events to output AUX data")
... and we should probably return -EINVAL here, as this should only
happen when the new event is mis-configured or does not have a
compatible aux_event group leader.
Fixes: ab43762ef0 ("perf: Allow normal events to output AUX data")
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Tested-by: Vince Weaver <vincent.weaver@maine.edu>
The commit 91d2a812df ("locking/rwsem: Make handoff writer
optimistically spin on owner") will allow a recently woken up waiting
writer to spin on the owner. Unfortunately, if the owner happens to be
RWSEM_OWNER_UNKNOWN, the code will incorrectly spin on it leading to a
kernel crash. This is fixed by passing the proper non-spinnable bits
to rwsem_spin_on_owner() so that RWSEM_OWNER_UNKNOWN will be treated
as a non-spinnable target.
Fixes: 91d2a812df ("locking/rwsem: Make handoff writer optimistically spin on owner")
Reported-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Christoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20200115154336.8679-1-longman@redhat.com
Upon resuming from hibernation, free pages may contain stale data from
the kernel that initiated the resume. This breaks the invariant
inflicted by init_on_free=1 that freed pages must be zeroed.
To deal with this problem, make clear_free_pages() also clear the free
pages when init_on_free is enabled.
Fixes: 6471384af2 ("mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options")
Reported-by: Johannes Stezenbach <js@sig21.net>
Signed-off-by: Alexander Potapenko <glider@google.com>
Cc: 5.3+ <stable@vger.kernel.org> # 5.3+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Daniel Borkmann says:
====================
pull-request: bpf 2020-01-15
The following pull-request contains BPF updates for your *net* tree.
We've added 12 non-merge commits during the last 9 day(s) which contain
a total of 13 files changed, 95 insertions(+), 43 deletions(-).
The main changes are:
1) Fix refcount leak for TCP time wait and request sockets for socket lookup
related BPF helpers, from Lorenz Bauer.
2) Fix wrong verification of ARSH instruction under ALU32, from Daniel Borkmann.
3) Batch of several sockmap and related TLS fixes found while operating
more complex BPF programs with Cilium and OpenSSL, from John Fastabend.
4) Fix sockmap to read psock's ingress_msg queue before regular sk_receive_queue()
to avoid purging data upon teardown, from Lingpeng Chen.
5) Fix printing incorrect pointer in bpftool's btf_dump_ptr() in order to properly
dump a BPF map's value with BTF, from Martin KaFai Lau.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Anatoly has been fuzzing with kBdysch harness and reported a hang in one
of the outcomes:
0: R1=ctx(id=0,off=0,imm=0) R10=fp0
0: (85) call bpf_get_socket_cookie#46
1: R0_w=invP(id=0) R10=fp0
1: (57) r0 &= 808464432
2: R0_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0
2: (14) w0 -= 810299440
3: R0_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0
3: (c4) w0 s>>= 1
4: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0
4: (76) if w0 s>= 0x30303030 goto pc+216
221: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0
221: (95) exit
processed 6 insns (limit 1000000) [...]
Taking a closer look, the program was xlated as follows:
# ./bpftool p d x i 12
0: (85) call bpf_get_socket_cookie#7800896
1: (bf) r6 = r0
2: (57) r6 &= 808464432
3: (14) w6 -= 810299440
4: (c4) w6 s>>= 1
5: (76) if w6 s>= 0x30303030 goto pc+216
6: (05) goto pc-1
7: (05) goto pc-1
8: (05) goto pc-1
[...]
220: (05) goto pc-1
221: (05) goto pc-1
222: (95) exit
Meaning, the visible effect is very similar to f54c7898ed ("bpf: Fix
precision tracking for unbounded scalars"), that is, the fall-through
branch in the instruction 5 is considered to be never taken given the
conclusion from the min/max bounds tracking in w6, and therefore the
dead-code sanitation rewrites it as goto pc-1. However, real-life input
disagrees with verification analysis since a soft-lockup was observed.
The bug sits in the analysis of the ARSH. The definition is that we shift
the target register value right by K bits through shifting in copies of
its sign bit. In adjust_scalar_min_max_vals(), we do first coerce the
register into 32 bit mode, same happens after simulating the operation.
However, for the case of simulating the actual ARSH, we don't take the
mode into account and act as if it's always 64 bit, but location of sign
bit is different:
dst_reg->smin_value >>= umin_val;
dst_reg->smax_value >>= umin_val;
dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val);
Consider an unknown R0 where bpf_get_socket_cookie() (or others) would
for example return 0xffff. With the above ARSH simulation, we'd see the
following results:
[...]
1: R1=ctx(id=0,off=0,imm=0) R2_w=invP65535 R10=fp0
1: (85) call bpf_get_socket_cookie#46
2: R0_w=invP(id=0) R10=fp0
2: (57) r0 &= 808464432
-> R0_runtime = 0x3030
3: R0_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0
3: (14) w0 -= 810299440
-> R0_runtime = 0xcfb40000
4: R0_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0
(0xffffffff)
4: (c4) w0 s>>= 1
-> R0_runtime = 0xe7da0000
5: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0
(0x67c00000) (0x7ffbfff8)
[...]
In insn 3, we have a runtime value of 0xcfb40000, which is '1100 1111 1011
0100 0000 0000 0000 0000', the result after the shift has 0xe7da0000 that
is '1110 0111 1101 1010 0000 0000 0000 0000', where the sign bit is correctly
retained in 32 bit mode. In insn4, the umax was 0xffffffff, and changed into
0x7ffbfff8 after the shift, that is, '0111 1111 1111 1011 1111 1111 1111 1000'
and means here that the simulation didn't retain the sign bit. With above
logic, the updates happen on the 64 bit min/max bounds and given we coerced
the register, the sign bits of the bounds are cleared as well, meaning, we
need to force the simulation into s32 space for 32 bit alu mode.
Verification after the fix below. We're first analyzing the fall-through branch
on 32 bit signed >= test eventually leading to rejection of the program in this
specific case:
0: R1=ctx(id=0,off=0,imm=0) R10=fp0
0: (b7) r2 = 808464432
1: R1=ctx(id=0,off=0,imm=0) R2_w=invP808464432 R10=fp0
1: (85) call bpf_get_socket_cookie#46
2: R0_w=invP(id=0) R10=fp0
2: (bf) r6 = r0
3: R0_w=invP(id=0) R6_w=invP(id=0) R10=fp0
3: (57) r6 &= 808464432
4: R0_w=invP(id=0) R6_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0
4: (14) w6 -= 810299440
5: R0_w=invP(id=0) R6_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0
5: (c4) w6 s>>= 1
6: R0_w=invP(id=0) R6_w=invP(id=0,umin_value=3888119808,umax_value=4294705144,var_off=(0xe7c00000; 0x183bfff8)) R10=fp0
(0x67c00000) (0xfffbfff8)
6: (76) if w6 s>= 0x30303030 goto pc+216
7: R0_w=invP(id=0) R6_w=invP(id=0,umin_value=3888119808,umax_value=4294705144,var_off=(0xe7c00000; 0x183bfff8)) R10=fp0
7: (30) r0 = *(u8 *)skb[808464432]
BPF_LD_[ABS|IND] uses reserved fields
processed 8 insns (limit 1000000) [...]
Fixes: 9cbe1f5a32 ("bpf/verifier: improve register value range tracking with ARSH")
Reported-by: Anatoly Trosinenko <anatoly.trosinenko@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200115204733.16648-1-daniel@iogearbox.net
With CONFIG_PROVE_RCU_LIST, I had many suspicious RCU warnings
when I ran ftracetest trigger testcases.
-----
# dmesg -c > /dev/null
# ./ftracetest test.d/trigger
...
# dmesg | grep "RCU-list traversed" | cut -f 2 -d ] | cut -f 2 -d " "
kernel/trace/trace_events_hist.c:6070
kernel/trace/trace_events_hist.c:1760
kernel/trace/trace_events_hist.c:5911
kernel/trace/trace_events_trigger.c:504
kernel/trace/trace_events_hist.c:1810
kernel/trace/trace_events_hist.c:3158
kernel/trace/trace_events_hist.c:3105
kernel/trace/trace_events_hist.c:5518
kernel/trace/trace_events_hist.c:5998
kernel/trace/trace_events_hist.c:6019
kernel/trace/trace_events_hist.c:6044
kernel/trace/trace_events_trigger.c:1500
kernel/trace/trace_events_trigger.c:1540
kernel/trace/trace_events_trigger.c:539
kernel/trace/trace_events_trigger.c:584
-----
I investigated those warnings and found that the RCU-list
traversals in event trigger and hist didn't need to use
RCU version because those were called only under event_mutex.
I also checked other RCU-list traversals related to event
trigger list, and found that most of them were called from
event_hist_trigger_func() or hist_unregister_trigger() or
register/unregister functions except for a few cases.
Replace these unneeded RCU-list traversals with normal list
traversal macro and lockdep_assert_held() to check the
event_mutex is held.
Link: http://lkml.kernel.org/r/157680910305.11685.15110237954275915782.stgit@devnote2
Cc: stable@vger.kernel.org
Fixes: 30350d65ac ("tracing: Add variable support to hist triggers")
Reviewed-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Merge misc fixes from David Howells.
Two afs fixes and a key refcounting fix.
* dhowells:
afs: Fix afs_lookup() to not clobber the version on a new dentry
afs: Fix use-after-loss-of-ref
keys: Fix request_key() cache
When the key cached by request_key() and co. is cleaned up on exit(),
the code looks in the wrong task_struct, and so clears the wrong cache.
This leads to anomalies in key refcounting when doing, say, a kernel
build on an afs volume, that then trigger kasan to report a
use-after-free when the key is viewed in /proc/keys.
Fix this by making exit_creds() look in the passed-in task_struct rather
than in current (the task_struct cleanup code is deferred by RCU and
potentially run in another task).
Fixes: 7743c48e54 ("keys: Cache result of request_key*() temporarily in task_struct")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull thread fixes from Christian Brauner:
"This contains a series of patches to fix CLONE_SETTLS when used with
clone3().
The clone3() syscall passes the tls argument through struct clone_args
instead of a register. This means, all architectures that do not
implement copy_thread_tls() but still support CLONE_SETTLS via
copy_thread() expecting the tls to be located in a register argument
based on clone() are currently unfortunately broken. Their tls value
will be garbage.
The patch series fixes this on all architectures that currently define
__ARCH_WANT_SYS_CLONE3. It also adds a compile-time check to ensure
that any architecture that enables clone3() in the future is forced to
also implement copy_thread_tls().
My ultimate goal is to get rid of the copy_thread()/copy_thread_tls()
split and just have copy_thread_tls() at some point in the not too
distant future (Maybe even renaming copy_thread_tls() back to simply
copy_thread() once the old function is ripped from all arches). This
is dependent now on all arches supporting clone3().
While all relevant arches do that now there are still four missing:
ia64, m68k, sh and sparc. They have the system call reserved, but not
implemented. Once they all implement clone3() we can get rid of
ARCH_WANT_SYS_CLONE3 and HAVE_COPY_THREAD_TLS.
This series also includes a minor fix for the arm64 uapi headers which
caused __NR_clone3 to be missing from the exported user headers.
Unfortunately the series came in a little late especially given that
it touches a range of architectures. Due to the holidays not all arch
maintainers responded in time probably due to their backlog. Will and
Arnd have thankfully acked the arm specific changes.
Given that the changes are straightforward and rather minimal combined
with the fact the that clone3() with CLONE_SETTLS is broken I decided
to send them post rc3 nonetheless"
* tag 'clone3-tls-v5.5-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
um: Implement copy_thread_tls
clone3: ensure copy_thread_tls is implemented
xtensa: Implement copy_thread_tls
riscv: Implement copy_thread_tls
parisc: Implement copy_thread_tls
arm: Implement copy_thread_tls
arm64: Implement copy_thread_tls
arm64: Move __ARCH_WANT_SYS_CLONE3 definition to uapi headers
Pull networking fixes from David Miller:
1) Missing netns pointer init in arp_tables, from Florian Westphal.
2) Fix normal tcp SACK being treated as D-SACK, from Pengcheng Yang.
3) Fix divide by zero in sch_cake, from Wen Yang.
4) Len passed to skb_put_padto() is wrong in qrtr code, from Carl
Huang.
5) cmd->obj.chunk is leaked in sctp code error paths, from Xin Long.
6) cgroup bpf programs can be released out of order, fix from Roman
Gushchin.
7) Make sure stmmac debugfs entry name is changed when device name
changes, from Jiping Ma.
8) Fix memory leak in vlan_dev_set_egress_priority(), from Eric
Dumazet.
9) SKB leak in lan78xx usb driver, also from Eric Dumazet.
10) Ridiculous TCA_FQ_QUANTUM values configured can cause loops in fq
packet scheduler, reject them. From Eric Dumazet.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (69 commits)
tipc: fix wrong connect() return code
tipc: fix link overflow issue at socket shutdown
netfilter: ipset: avoid null deref when IPSET_ATTR_LINENO is present
netfilter: conntrack: dccp, sctp: handle null timeout argument
atm: eni: fix uninitialized variable warning
macvlan: do not assume mac_header is set in macvlan_broadcast()
net: sch_prio: When ungrafting, replace with FIFO
mlxsw: spectrum_qdisc: Ignore grafting of invisible FIFO
MAINTAINERS: Remove myself as co-maintainer for qcom-ethqos
gtp: fix bad unlock balance in gtp_encap_enable_socket
pkt_sched: fq: do not accept silly TCA_FQ_QUANTUM
tipc: remove meaningless assignment in Makefile
tipc: do not add socket.o to tipc-y twice
net: stmmac: dwmac-sun8i: Allow all RGMII modes
net: stmmac: dwmac-sunxi: Allow all RGMII modes
net: usb: lan78xx: fix possible skb leak
net: stmmac: Fixed link does not need MDIO Bus
vlan: vlan_changelink() should propagate errors
vlan: fix memory leak in vlan_dev_set_egress_priority
stmmac: debugfs entry name is not be changed when udev rename device name.
...
When CONFIG_SYSFS is disabled, but CONFIG_HOTPLUG_SMT is enabled,
the kernel fails to link:
arch/x86/power/cpu.o: In function `hibernate_resume_nonboot_cpu_disable':
(.text+0x38d): undefined reference to `cpuhp_smt_enable'
arch/x86/power/hibernate.o: In function `arch_resume_nosmt':
hibernate.c:(.text+0x291): undefined reference to `cpuhp_smt_enable'
hibernate.c:(.text+0x29c): undefined reference to `cpuhp_smt_disable'
Move the exported functions out of the #ifdef section into its
own with the correct conditions.
The patch that caused this is marked for stable backports, so
this one may need to be backported as well.
Fixes: ec527c3180 ("x86/power: Fix 'nosmt' vs hibernation triple fault during resume")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jiri Kosina <jkosina@suse.cz>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20191210195614.786555-1-arnd@arndb.de
