| Age | Commit message (Collapse) | Author |
|---|
|
The PAUSE instruction is currently used in the retpoline and RSB filling
macros as a speculation trap. The use of PAUSE was originally suggested
because it showed a very, very small difference in the amount of
cycles/time used to execute the retpoline as compared to LFENCE. On AMD,
the PAUSE instruction is not a serializing instruction, so the pause/jmp
loop will use excess power as it is speculated over waiting for return
to mispredict to the correct target.
The RSB filling macro is applicable to AMD, and, if software is unable to
verify that LFENCE is serializing on AMD (possible when running under a
hypervisor), the generic retpoline support will be used and, so, is also
applicable to AMD. Keep the current usage of PAUSE for Intel, but add an
LFENCE instruction to the speculation trap for AMD.
The same sequence has been adopted by GCC for the GCC generated retpolines.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@alien8.de>
Acked-by: David Woodhouse <dwmw@amazon.co.uk>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Kees Cook <keescook@google.com>
Link: https://lkml.kernel.org/r/20180113232730.31060.36287.stgit@tlendack-t1.amdoffice.net
|
|
On context switch from a shallow call stack to a deeper one, as the CPU
does 'ret' up the deeper side it may encounter RSB entries (predictions for
where the 'ret' goes to) which were populated in userspace.
This is problematic if neither SMEP nor KPTI (the latter of which marks
userspace pages as NX for the kernel) are active, as malicious code in
userspace may then be executed speculatively.
Overwrite the CPU's return prediction stack with calls which are predicted
to return to an infinite loop, to "capture" speculation if this
happens. This is required both for retpoline, and also in conjunction with
IBRS for !SMEP && !KPTI.
On Skylake+ the problem is slightly different, and an *underflow* of the
RSB may cause errant branch predictions to occur. So there it's not so much
overwrite, as *filling* the RSB to attempt to prevent it getting
empty. This is only a partial solution for Skylake+ since there are many
other conditions which may result in the RSB becoming empty. The full
solution on Skylake+ is to use IBRS, which will prevent the problem even
when the RSB becomes empty. With IBRS, the RSB-stuffing will not be
required on context switch.
[ tglx: Added missing vendor check and slighty massaged comments and
changelog ]
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: thomas.lendacky@amd.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Link: https://lkml.kernel.org/r/1515779365-9032-1-git-send-email-dwmw@amazon.co.uk
|
|
Currently KASAN doesn't panic in case it don't have enough memory
to boot. Instead, it crashes in some random place:
kernel BUG at arch/x86/mm/physaddr.c:27!
RIP: 0010:__phys_addr+0x268/0x276
Call Trace:
kasan_populate_shadow+0x3f2/0x497
kasan_init+0x12e/0x2b2
setup_arch+0x2825/0x2a2c
start_kernel+0xc8/0x15f4
x86_64_start_reservations+0x2a/0x2c
x86_64_start_kernel+0x72/0x75
secondary_startup_64+0xa5/0xb0
Use memblock_virt_alloc_try_nid() for allocations without failure
fallback. It will panic with an out of memory message.
Reported-by: kernel test robot <xiaolong.ye@intel.com>
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Dmitry Vyukov <dvyukov@google.com>
Cc: kasan-dev@googlegroups.com
Cc: Alexander Potapenko <glider@google.com>
Cc: lkp@01.org
Link: https://lkml.kernel.org/r/20180110153602.18919-1-aryabinin@virtuozzo.com
|
|
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fixlet from Thomas Gleixner.
Remove a warning about lack of compiler support for retpoline that most
people can't do anything about, so it just annoys them needlessly.
* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/retpoline: Remove compile time warning
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc fixes from Michael Ellerman:
"One fix for an oops at boot if we take a hotplug interrupt before we
are ready to handle it.
The bulk is patches to implement mitigation for Meltdown, see the
change logs for more details.
Thanks to: Nicholas Piggin, Michael Neuling, Oliver O'Halloran, Jon
Masters, Jose Ricardo Ziviani, David Gibson"
* tag 'powerpc-4.15-7' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
powerpc/powernv: Check device-tree for RFI flush settings
powerpc/pseries: Query hypervisor for RFI flush settings
powerpc/64s: Support disabling RFI flush with no_rfi_flush and nopti
powerpc/64s: Add support for RFI flush of L1-D cache
powerpc/64s: Convert slb_miss_common to use RFI_TO_USER/KERNEL
powerpc/64: Convert fast_exception_return to use RFI_TO_USER/KERNEL
powerpc/64: Convert the syscall exit path to use RFI_TO_USER/KERNEL
powerpc/64s: Simple RFI macro conversions
powerpc/64: Add macros for annotating the destination of rfid/hrfid
powerpc/pseries: Add H_GET_CPU_CHARACTERISTICS flags & wrapper
powerpc/pseries: Make RAS IRQ explicitly dependent on DLPAR WQ
|
|
Jakub Kicinski says:
====================
This set adds support for creating maps on networking devices. BPF is
programs+maps, the pure program offload has been around for quite some
time, this patchset adds the map part of the equation.
Maps are allocated on the target device from the start. There is no
host copy when map is created on the device. Device maps are represented
by struct bpf_offloaded_map, regardless of type. Host programs can't
access such maps, access is only possible from a program also loaded
to the same device and/or via the BPF syscall.
Offloaded programs are currently only allowed to perform lookups,
control plane is responsible for populating the maps.
For brevity only infrastructure and basic NFP patches are included.
Target device reporting, netdevsim and tests will follow up as well as
some further optimizations to the NFP code.
v2:
- leave out the array maps, we will add them trivially later to avoid
merge conflicts with ongoing spectere&meltdown mitigations.
====================
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
Plug in to the stack's map offload callbacks for BPF map offload.
Get next call needs some special handling on the FW side, since
we can't send a NULL pointer to the FW there is a get first entry
FW command.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
Map memory needs to use 40 bit addressing. Add handling of such
accesses. Since 40 bit addresses are formed by using both 32 bit
operands we need to pre-calculate the actual address instead of
adding in the offset inside the instruction, like we did in 32 bit
mode.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
Verify our current constraints on the location of the key are
met and generate the code for calling map lookup on the datapath.
New relocation types have to be added - for helpers and return
addresses.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
Immediate loads are used to load the return address of a helper.
We need to be able to update those loads for relocations.
Immediate loads can be slightly more complex and spread over
two instructions in general, but here we only care about simple
loads of small (< 65k) constants, so complex cases are not handled.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
Parse helper function and supported map FW TLV capabilities.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
Implement calls for FW map communication.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
For map support we will need to send and receive control messages.
Add basic support for sending a message to FW, and waiting for a
reply.
Control messages are tagged with a 16 bit ID. Add a simple ID
allocator and make sure we don't allow too many messages in flight,
to avoid request <> reply mismatches.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
To be able to split code into reasonable chunks we need to add
the map data structures already. Later patches will add code
piece by piece.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
BPF map offload follow similar path to program offload. At creation
time users may specify ifindex of the device on which they want to
create the map. Map will be validated by the kernel's
.map_alloc_check callback and device driver will be called for the
actual allocation. Map will have an empty set of operations
associated with it (save for alloc and free callbacks). The real
device callbacks are kept in map->offload->dev_ops because they
have slightly different signatures. Map operations are called in
process context so the driver may communicate with HW freely,
msleep(), wait() etc.
Map alloc and free callbacks are muxed via existing .ndo_bpf, and
are always called with rtnl lock held. Maps and programs are
guaranteed to be destroyed before .ndo_uninit (i.e. before
unregister_netdev() returns). Map callbacks are invoked with
bpf_devs_lock *read* locked, drivers must take care of exclusive
locking if necessary.
All offload-specific branches are marked with unlikely() (through
bpf_map_is_dev_bound()), given that branch penalty will be
negligible compared to IO anyway, and we don't want to penalize
SW path unnecessarily.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
Add a helper to check if netdev could be found and whether it
has .ndo_bpf callback. There is no need to check the callback
every time it's invoked, ndos can't reasonably be swapped for
a set without .ndp_bpf while program is loaded.
bpf_dev_offload_check() will also be used by map offload.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
With map offload coming, we need to call program offload structure
something less ambiguous. Pure rename, no functional changes.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
All map types reimplement the field-by-field copy of union bpf_attr
members into struct bpf_map. Add a helper to perform this operation.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
Use the new callback to perform allocation checks for hash maps.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
Number of attribute checks are currently performed after hashtab
is already allocated. Move them to be able to split them out to
the check function later on. Checks have to now be performed on
the attr union directly instead of the members of bpf_map, since
bpf_map will be allocated later. No functional changes.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
.map_alloc callbacks contain a number of checks validating user-
-provided map attributes against constraints of a particular map
type. For offloaded maps we will need to check map attributes
without actually allocating any memory on the host. Add a new
callback for validating attributes before any memory is allocated.
This callback can be selectively implemented by map types for
sharing code with offloads, or simply to separate the logical
steps of validation and allocation.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
When the timer base is checked for expired timers then the deferrable base
must be checked as well. This was missed when making the deferrable base
independent of base::nohz_active.
Fixes: ced6d5c11d3e ("timers: Use deferrable base independent of base::nohz_active")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Anna-Maria Gleixner <anna-maria@linutronix.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
Cc: stable@vger.kernel.org
Cc: rt@linutronix.de
|
|
due to some JITs doing if (src_reg == 0) check in 64-bit mode
for div/mod operations mask upper 32-bits of src register
before doing the check
Fixes: 622582786c9e ("net: filter: x86: internal BPF JIT")
Fixes: 7a12b5031c6b ("sparc64: Add eBPF JIT.")
Reported-by: syzbot+48340bb518e88849e2e3@syzkaller.appspotmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
Remove the compile time warning when CONFIG_RETPOLINE=y and the compiler
does not have retpoline support. Linus rationale for this is:
It's wrong because it will just make people turn off RETPOLINE, and the
asm updates - and return stack clearing - that are independent of the
compiler are likely the most important parts because they are likely the
ones easiest to target.
And it's annoying because most people won't be able to do anything about
it. The number of people building their own compiler? Very small. So if
their distro hasn't got a compiler yet (and pretty much nobody does), the
warning is just annoying crap.
It is already properly reported as part of the sysfs interface. The
compile-time warning only encourages bad things.
Fixes: 76b043848fd2 ("x86/retpoline: Add initial retpoline support")
Requested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: David Woodhouse <dwmw@amazon.co.uk>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: thomas.lendacky@amd.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Link: https://lkml.kernel.org/r/CA+55aFzWgquv4i6Mab6bASqYXg3ErV3XDFEYf=GEcCDQg5uAtw@mail.gmail.com
|
|
const variables must use __initconst, not __initdata.
Fix this up for the IDT tables, which got it consistently wrong.
Fixes: 16bc18d895ce ("x86/idt: Move 32-bit idt_descr to C code")
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20171222001821.2157-7-andi@firstfloor.org
|
|
Pull NVMe fix from Jens Axboe:
"Just a single fix for nvme over fabrics that should go into 4.15"
* 'for-linus' of git://git.kernel.dk/linux-block:
nvme-fabrics: initialize default host->id in nvmf_host_default()
|
|
UBSAN reports signed integer overflow in kernel/futex.c:
UBSAN: Undefined behaviour in kernel/futex.c:2041:18
signed integer overflow:
0 - -2147483648 cannot be represented in type 'int'
Add a sanity check to catch negative values of nr_wake and nr_requeue.
Signed-off-by: Li Jinyue <lijinyue@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: peterz@infradead.org
Cc: dvhart@infradead.org
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/1513242294-31786-1-git-send-email-lijinyue@huawei.com
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 pti updates from Thomas Gleixner:
"This contains:
- a PTI bugfix to avoid setting reserved CR3 bits when PCID is
disabled. This seems to cause issues on a virtual machine at least
and is incorrect according to the AMD manual.
- a PTI bugfix which disables the perf BTS facility if PTI is
enabled. The BTS AUX buffer is not globally visible and causes the
CPU to fault when the mapping disappears on switching CR3 to user
space. A full fix which restores BTS on PTI is non trivial and will
be worked on.
- PTI bugfixes for EFI and trusted boot which make sure that the user
space visible page table entries have the NX bit cleared
- removal of dead code in the PTI pagetable setup functions
- add PTI documentation
- add a selftest for vsyscall to verify that the kernel actually
implements what it advertises.
- a sysfs interface to expose vulnerability and mitigation
information so there is a coherent way for users to retrieve the
status.
- the initial spectre_v2 mitigations, aka retpoline:
+ The necessary ASM thunk and compiler support
+ The ASM variants of retpoline and the conversion of affected ASM
code
+ Make LFENCE serializing on AMD so it can be used as speculation
trap
+ The RSB fill after vmexit
- initial objtool support for retpoline
As I said in the status mail this is the most of the set of patches
which should go into 4.15 except two straight forward patches still on
hold:
- the retpoline add on of LFENCE which waits for ACKs
- the RSB fill after context switch
Both should be ready to go early next week and with that we'll have
covered the major holes of spectre_v2 and go back to normality"
* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (28 commits)
x86,perf: Disable intel_bts when PTI
security/Kconfig: Correct the Documentation reference for PTI
x86/pti: Fix !PCID and sanitize defines
selftests/x86: Add test_vsyscall
x86/retpoline: Fill return stack buffer on vmexit
x86/retpoline/irq32: Convert assembler indirect jumps
x86/retpoline/checksum32: Convert assembler indirect jumps
x86/retpoline/xen: Convert Xen hypercall indirect jumps
x86/retpoline/hyperv: Convert assembler indirect jumps
x86/retpoline/ftrace: Convert ftrace assembler indirect jumps
x86/retpoline/entry: Convert entry assembler indirect jumps
x86/retpoline/crypto: Convert crypto assembler indirect jumps
x86/spectre: Add boot time option to select Spectre v2 mitigation
x86/retpoline: Add initial retpoline support
objtool: Allow alternatives to be ignored
objtool: Detect jumps to retpoline thunks
x86/pti: Make unpoison of pgd for trusted boot work for real
x86/alternatives: Fix optimize_nops() checking
sysfs/cpu: Fix typos in vulnerability documentation
x86/cpu/AMD: Use LFENCE_RDTSC in preference to MFENCE_RDTSC
...
|
|
Julia reported futex state corruption in the following scenario:
waiter waker stealer (prio > waiter)
futex(WAIT_REQUEUE_PI, uaddr, uaddr2,
timeout=[N ms])
futex_wait_requeue_pi()
futex_wait_queue_me()
freezable_schedule()
<scheduled out>
futex(LOCK_PI, uaddr2)
futex(CMP_REQUEUE_PI, uaddr,
uaddr2, 1, 0)
/* requeues waiter to uaddr2 */
futex(UNLOCK_PI, uaddr2)
wake_futex_pi()
cmp_futex_value_locked(uaddr2, waiter)
wake_up_q()
<woken by waker>
<hrtimer_wakeup() fires,
clears sleeper->task>
futex(LOCK_PI, uaddr2)
__rt_mutex_start_proxy_lock()
try_to_take_rt_mutex() /* steals lock */
rt_mutex_set_owner(lock, stealer)
<preempted>
<scheduled in>
rt_mutex_wait_proxy_lock()
__rt_mutex_slowlock()
try_to_take_rt_mutex() /* fails, lock held by stealer */
if (timeout && !timeout->task)
return -ETIMEDOUT;
fixup_owner()
/* lock wasn't acquired, so,
fixup_pi_state_owner skipped */
return -ETIMEDOUT;
/* At this point, we've returned -ETIMEDOUT to userspace, but the
* futex word shows waiter to be the owner, and the pi_mutex has
* stealer as the owner */
futex_lock(LOCK_PI, uaddr2)
-> bails with EDEADLK, futex word says we're owner.
And suggested that what commit:
73d786bd043e ("futex: Rework inconsistent rt_mutex/futex_q state")
removes from fixup_owner() looks to be just what is needed. And indeed
it is -- I completely missed that requeue_pi could also result in this
case. So we need to restore that, except that subsequent patches, like
commit:
16ffa12d7425 ("futex: Pull rt_mutex_futex_unlock() out from under hb->lock")
changed all the locking rules. Even without that, the sequence:
- if (rt_mutex_futex_trylock(&q->pi_state->pi_mutex)) {
- locked = 1;
- goto out;
- }
- raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock);
- owner = rt_mutex_owner(&q->pi_state->pi_mutex);
- if (!owner)
- owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
- raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock);
- ret = fixup_pi_state_owner(uaddr, q, owner);
already suggests there were races; otherwise we'd never have to look
at next_owner.
So instead of doing 3 consecutive wait_lock sections with who knows
what races, we do it all in a single section. Additionally, the usage
of pi_state->owner in fixup_owner() was only safe because only the
rt_mutex owner would modify it, which this additional case wrecks.
Luckily the values can only change away and not to the value we're
testing, this means we can do a speculative test and double check once
we have the wait_lock.
Fixes: 73d786bd043e ("futex: Rework inconsistent rt_mutex/futex_q state")
Reported-by: Julia Cartwright <julia@ni.com>
Reported-by: Gratian Crisan <gratian.crisan@ni.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Julia Cartwright <julia@ni.com>
Tested-by: Gratian Crisan <gratian.crisan@ni.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20171208124939.7livp7no2ov65rrc@hirez.programming.kicks-ass.net
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says:
====================
10GbE Intel Wired LAN Driver Updates 2018-01-12
This series contains updates to ixgbe, fm10k and net core.
Alex updates the driver to remove a duplicate MAC address check and
verifies that we have not run out of resources to configure a MAC rule
in our filter table. Also do not assume that dev->num_tc was populated
and configured with the driver, since it can be configured via mqprio
without any hardware coordination. Fixed the recording of stats for
MACVLAN in ixgbe and fm10k instead of recording the receive queue on
MACVLAN offloaded frames. When handling a MACVLAN offload, we should
be stopping/starting traffic on our own queues instead of the upper
devices transmit queues. Fixed possible race conditions with the
MACVLAN cleanup with the interface cleanup on shutdown. With the
recent fixes to ixgbe, we can cap the number of queues regardless of
accel_priv being in use or not, since the actual number of queues are
being reported via real_num_tx_queues.
Tony fixes up the kernel documentation for ixgbe and ixgbevf to resolve
warnings when W=1 is used.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Jiri Pirko says:
====================
mlxsw: Offload PRIO qdisc
Nogah says:
Add an offload support for PRIO qdisc for mlxsw driver.
PRIO qdisc is being offloaded by using ndo_setup_tc. It has three
commands, to set or tune the qdisc, to remove it and to get its stats.
Like RED offloading, offloading this qdisc is not enforced on the driver
and determining its offload state is done in the dump action, when the
stats are being updated.
In the driver, offloading of PRIO is supported as root qdisc only. It
supports only priorities 0-7 (the range that is used by the current static
mapping of DSCP to skb prio and by 1:1 PCP values mapping) and up to 8
bands.
Patches 1-2 offload DSCP to priority mapping in the mlxsw_sp driver.
Patch 3 adds offload support for PRIO qdisc.
Patches 4-5 Add PRIO offload support in the mlxsw_sp driver.
---
v1->v2:
- Patch 1/5:
- Rewrite patch msg
- Patch 3/5:
- Send all the qstats in the replace command (and not just backlog)
- Patch 5/5:
- Align with the changes from 3/5
- Move backlog to the generic qdisc stats struct
- Delete extra newline
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Support basic stats for PRIO qdisc, which includes tx packets and bytes
count, drops count and backlog size. The rest of the stats are irrelevant
for this qdisc offload.
Since backlog is not only incremental but reflecting momentary value, in
case of a qdisc that stops being offloaded but is not destroyed, backlog
value needs to be updated about the un-offloading.
For that reason an unoffload function is being added to the ops struct.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Reviewed-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add support for offloading PRIO qdisc as root qdisc.
The support is for up to 8 bands.
Routed packets priority is determined by the DSCP field with the default
translations. Bridged packets priority is determined by the PCP field, if
exist, otherwise it is set to 0.
Since both options have only priorities 0-7, higher priorities mapping are
being ignored.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Reviewed-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add the ability to offload PRIO qdisc by using ndo_setup_tc.
There are three commands for PRIO offloading:
* TC_PRIO_REPLACE: handles set and tune
* TC_PRIO_DESTROY: handles qdisc destroy
* TC_PRIO_STATS: updates the qdiscs counters (given as reference)
Like RED qdisc, the indication of whether PRIO is being offloaded is being
set and updated as part of the dump function. It is so because the driver
could decide to offload or not based on the qdisc parent, which could
change without notifying the qdisc.
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Reviewed-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When routing ip packets, the kernel is setting the SKB's priority
based on the tos field of the packet.
Imitate this behavior in the mlxsw router, having the internal
switch priority of a routed packet determined according to its DS
field.
Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add rdpm definition - router DSCP to priority mapping register.
This register will be utilized later to align the default mapping between
packet DSCP and switch-priority to the kernel's mapping between
packet priority and skb priority.
This is the first non-bit indexed register where the entries are arranged
in descending order, i.e., entry at offset 0 matches configuration for
dscp[63]. As a result, the item's step is converted into a signed variable
to support descending arrays [where step would be negative].
Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Andrew Lunn says:
====================
mv88e6xxx: ATU and VTU interrupts
Both the ATU and VTU of Mavell switches can generate interrupts when
violations occur. Trap this interrupts and print what violation
occurred.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When there is a problem with the VTU, an interrupt can be
generated. Trap this interrupt and decode the registers to determine
what the problem was, then log the error.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When there is a problem with the ATU, an interrupt can be
generated. Trap this interrupt and decode the registers to determine
what the problem was, then log the error.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Since commit eb789980d0aa ("mlxsw: spectrum_router: Populate adjacency
entries according to weights") the driver includes support for
non-equal-cost multipath, but IPv4 nexthops were the only user.
Now that the kernel supports weighted IPv6 nexthops, we can extend the
driver to support it as well.
This is done by assigning each nexthop its configured weight, so that it
will be populated accordingly in the device's adjacency table. The
`weight` parameter is also taken into account when comparing nexthop
groups in order not to consolidate non-identical groups.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Divides by zero are not nice, lets avoid them if possible.
Also do_div() seems not needed when dealing with 32bit operands,
but this seems a minor detail.
Fixes: bd4cf0ed331a ("net: filter: rework/optimize internal BPF interpreter's instruction set")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
On targets that have different sizes for phys_addr_t and dma_addr_t,
we get a type mismatch error:
drivers/net/ethernet/socionext/netsec.c: In function 'netsec_alloc_dring':
drivers/net/ethernet/socionext/netsec.c:970:9: error: passing argument 3 of 'dma_zalloc_coherent' from incompatible pointer type [-Werror=incompatible-pointer-types]
The code is otherwise correct, as the address is never actually used as a
physical address but only passed into a DMA register. For consistently,
I'm changing the variable name as well, to clarify that this is a DMA
address.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Daniel Borkmann says:
====================
pull-request: bpf 2018-01-13
The following pull-request contains BPF updates for your *net* tree.
The main changes are:
1) Follow-up fix to the recent BPF out-of-bounds speculation
fix that prevents max_entries overflows and an undefined
behavior on 32 bit archs on index_mask calculation, from
Daniel.
2) Reject unsupported BPF_ARSH opcode in 32 bit ALU mode that
was otherwise throwing an unknown opcode warning in the
interpreter, from Daniel.
3) Typo fix in one of the user facing verbose() messages that
was added during the BPF out-of-bounds speculation fix,
from Colin.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This reverts commit b371ae0d4a194b178817b0edfb6a7395c7aec37a. It causes
boot hangs on old P3/P4 systems when the local APIC is enforced in UP mode.
Reported-by: Meelis Roos <mroos@linux.ee>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Dou Liyang <douly.fnst@cn.fujitsu.com>
Cc: yinghai@kernel.org
Cc: bhe@redhat.com
Link: https://lkml.kernel.org/r/20171128145350.21560-1-ville.syrjala@linux.intel.com
|
|
SEGV_PKUERR is a signal specific si_code which happens to have the same
numeric value as several others: BUS_MCEERR_AR, ILL_ILLTRP, FPE_FLTOVF,
TRAP_HWBKPT, CLD_TRAPPED, POLL_ERR, SEGV_THREAD_ID, as such it is not safe
to just test the si_code the signal number must also be tested to prevent a
false positive in fill_sig_info_pkey.
This error was by inspection, and BUS_MCEERR_AR appears to be a real
candidate for confusion. So pass in si_signo and check for SIG_SEGV to
verify that it is actually a SEGV_PKUERR
Fixes: 019132ff3daf ("x86/mm/pkeys: Fill in pkey field in siginfo")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20180112203135.4669-2-ebiederm@xmission.com
|
|
If CPU and TSC frequency are the same the printout of the CPU frequency is
valid for the TSC as well:
tsc: Detected 2900.000 MHz processor
If the TSC frequency is different there is no information in dmesg. Add a
conditional printout:
tsc: Detected 2904.000 MHz TSC
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: peterz@infradead.org
Link: https://lkml.kernel.org/r/537b342debcd8e8aebc8d631015dcdf9f9ba8a26.1513920414.git.len.brown@intel.com
|
|
The INTEL_FAM6_SKYLAKE_X hardcoded crystal_khz value of 25MHZ is
problematic:
- SKX workstations (with same model # as server variants) use a 24 MHz
crystal. This results in a -4.0% time drift rate on SKX workstations.
- SKX servers subject the crystal to an EMI reduction circuit that reduces its
actual frequency by (approximately) -0.25%. This results in -1 second per
10 minute time drift as compared to network time.
This issue can also trigger a timer and power problem, on configurations
that use the LAPIC timer (versus the TSC deadline timer). Clock ticks
scheduled with the LAPIC timer arrive a few usec before the time they are
expected (according to the slow TSC). This causes Linux to poll-idle, when
it should be in an idle power saving state. The idle and clock code do not
graciously recover from this error, sometimes resulting in significant
polling and measurable power impact.
Stop using native_calibrate_tsc() for INTEL_FAM6_SKYLAKE_X.
native_calibrate_tsc() will return 0, boot will run with tsc_khz = cpu_khz,
and the TSC refined calibration will update tsc_khz to correct for the
difference.
[ tglx: Sanitized change log ]
Fixes: 6baf3d61821f ("x86/tsc: Add additional Intel CPU models to the crystal quirk list")
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: peterz@infradead.org
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/ff6dcea166e8ff8f2f6a03c17beab2cb436aa779.1513920414.git.len.brown@intel.com
|
|
If the crystal frequency cannot be determined via CPUID(15).crystal_khz or
the built-in table then native_calibrate_tsc() will still set the
X86_FEATURE_TSC_KNOWN_FREQ flag which prevents the refined TSC calibration.
As a consequence such systems use cpu_khz for the TSC frequency which is
incorrect when cpu_khz != tsc_khz resulting in time drift.
Return early when the crystal frequency cannot be retrieved without setting
the X86_FEATURE_TSC_KNOWN_FREQ flag. This ensures that the refined TSC
calibration is invoked.
[ tglx: Steam-blastered changelog. Sigh ]
Fixes: 4ca4df0b7eb0 ("x86/tsc: Mark TSC frequency determined by CPUID as known")
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: peterz@infradead.org
Cc: Bin Gao <bin.gao@intel.com>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/0fe2503aa7d7fc69137141fc705541a78101d2b9.1513920414.git.len.brown@intel.com
|
|
The intel_bts driver does not use the 'normal' BTS buffer which is exposed
through the cpu_entry_area but instead uses the memory allocated for the
perf AUX buffer.
This obviously comes apart when using PTI because then the kernel mapping;
which includes that AUX buffer memory; disappears. Fixing this requires to
expose a mapping which is visible in all context and that's not trivial.
As a quick fix disable this driver when PTI is enabled to prevent
malfunction.
Fixes: 385ce0ea4c07 ("x86/mm/pti: Add Kconfig")
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Reported-by: Robert Święcki <robert@swiecki.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: greg@kroah.com
Cc: hughd@google.com
Cc: luto@amacapital.net
Cc: Vince Weaver <vince@deater.net>
Cc: torvalds@linux-foundation.org
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20180114102713.GB6166@worktop.programming.kicks-ass.net
|
