| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
[ Upstream commit 63dee5df43a31f3844efabc58972f0a206ca4534 ]
We have powerpc specific logic in our page fault handling to decide if
an access to an unmapped address below the stack pointer should expand
the stack VMA.
The code was originally added in 2004 "ported from 2.4". The rough
logic is that the stack is allowed to grow to 1MB with no extra
checking. Over 1MB the access must be within 2048 bytes of the stack
pointer, or be from a user instruction that updates the stack pointer.
The 2048 byte allowance below the stack pointer is there to cover the
288 byte "red zone" as well as the "about 1.5kB" needed by the signal
delivery code.
Unfortunately since then the signal frame has expanded, and is now
4224 bytes on 64-bit kernels with transactional memory enabled. This
means if a process has consumed more than 1MB of stack, and its stack
pointer lies less than 4224 bytes from the next page boundary, signal
delivery will fault when trying to expand the stack and the process
will see a SEGV.
The total size of the signal frame is the size of struct rt_sigframe
(which includes the red zone) plus __SIGNAL_FRAMESIZE (128 bytes on
64-bit).
The 2048 byte allowance was correct until 2008 as the signal frame
was:
struct rt_sigframe {
struct ucontext uc; /* 0 1440 */
/* --- cacheline 11 boundary (1408 bytes) was 32 bytes ago --- */
long unsigned int _unused[2]; /* 1440 16 */
unsigned int tramp[6]; /* 1456 24 */
struct siginfo * pinfo; /* 1480 8 */
void * puc; /* 1488 8 */
struct siginfo info; /* 1496 128 */
/* --- cacheline 12 boundary (1536 bytes) was 88 bytes ago --- */
char abigap[288]; /* 1624 288 */
/* size: 1920, cachelines: 15, members: 7 */
/* padding: 8 */
};
1920 + 128 = 2048
Then in commit ce48b2100785 ("powerpc: Add VSX context save/restore,
ptrace and signal support") (Jul 2008) the signal frame expanded to
2304 bytes:
struct rt_sigframe {
struct ucontext uc; /* 0 1696 */ <--
/* --- cacheline 13 boundary (1664 bytes) was 32 bytes ago --- */
long unsigned int _unused[2]; /* 1696 16 */
unsigned int tramp[6]; /* 1712 24 */
struct siginfo * pinfo; /* 1736 8 */
void * puc; /* 1744 8 */
struct siginfo info; /* 1752 128 */
/* --- cacheline 14 boundary (1792 bytes) was 88 bytes ago --- */
char abigap[288]; /* 1880 288 */
/* size: 2176, cachelines: 17, members: 7 */
/* padding: 8 */
};
2176 + 128 = 2304
At this point we should have been exposed to the bug, though as far as
I know it was never reported. I no longer have a system old enough to
easily test on.
Then in 2010 commit 320b2b8de126 ("mm: keep a guard page below a
grow-down stack segment") caused our stack expansion code to never
trigger, as there was always a VMA found for a write up to PAGE_SIZE
below r1.
That meant the bug was hidden as we continued to expand the signal
frame in commit 2b0a576d15e0 ("powerpc: Add new transactional memory
state to the signal context") (Feb 2013):
struct rt_sigframe {
struct ucontext uc; /* 0 1696 */
/* --- cacheline 13 boundary (1664 bytes) was 32 bytes ago --- */
struct ucontext uc_transact; /* 1696 1696 */ <--
/* --- cacheline 26 boundary (3328 bytes) was 64 bytes ago --- */
long unsigned int _unused[2]; /* 3392 16 */
unsigned int tramp[6]; /* 3408 24 */
struct siginfo * pinfo; /* 3432 8 */
void * puc; /* 3440 8 */
struct siginfo info; /* 3448 128 */
/* --- cacheline 27 boundary (3456 bytes) was 120 bytes ago --- */
char abigap[288]; /* 3576 288 */
/* size: 3872, cachelines: 31, members: 8 */
/* padding: 8 */
/* last cacheline: 32 bytes */
};
3872 + 128 = 4000
And commit 573ebfa6601f ("powerpc: Increase stack redzone for 64-bit
userspace to 512 bytes") (Feb 2014):
struct rt_sigframe {
struct ucontext uc; /* 0 1696 */
/* --- cacheline 13 boundary (1664 bytes) was 32 bytes ago --- */
struct ucontext uc_transact; /* 1696 1696 */
/* --- cacheline 26 boundary (3328 bytes) was 64 bytes ago --- */
long unsigned int _unused[2]; /* 3392 16 */
unsigned int tramp[6]; /* 3408 24 */
struct siginfo * pinfo; /* 3432 8 */
void * puc; /* 3440 8 */
struct siginfo info; /* 3448 128 */
/* --- cacheline 27 boundary (3456 bytes) was 120 bytes ago --- */
char abigap[512]; /* 3576 512 */ <--
/* size: 4096, cachelines: 32, members: 8 */
/* padding: 8 */
};
4096 + 128 = 4224
Then finally in 2017, commit 1be7107fbe18 ("mm: larger stack guard
gap, between vmas") exposed us to the existing bug, because it changed
the stack VMA to be the correct/real size, meaning our stack expansion
code is now triggered.
Fix it by increasing the allowance to 4224 bytes.
Hard-coding 4224 is obviously unsafe against future expansions of the
signal frame in the same way as the existing code. We can't easily use
sizeof() because the signal frame structure is not in a header. We
will either fix that, or rip out all the custom stack expansion
checking logic entirely.
Fixes: ce48b2100785 ("powerpc: Add VSX context save/restore, ptrace and signal support")
Cc: stable@vger.kernel.org # v2.6.27+
Reported-by: Tom Lane <tgl@sss.pgh.pa.us>
Tested-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200724092528.1578671-2-mpe@ellerman.id.au
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 0e36b0d12501e278686634712975b785bae11641 ]
Commit a7a9dcd882a67 ("powerpc: Avoid taking a data miss on every
userspace instruction miss") has shown that limiting the read of
faulting instruction to likely cases improves performance.
This patch goes further into this direction by limiting the read
of the faulting instruction to the only cases where it is likely
needed.
On an MPC885, with the same benchmark app as in the commit referred
above, we see a reduction of about 3900 dTLB misses (approx 3%):
Before the patch:
Performance counter stats for './fault 500' (10 runs):
683033312 cpu-cycles ( +- 0.03% )
134538 dTLB-load-misses ( +- 0.03% )
46099 iTLB-load-misses ( +- 0.02% )
19681 faults ( +- 0.02% )
5.389747878 seconds time elapsed ( +- 0.06% )
With the patch:
Performance counter stats for './fault 500' (10 runs):
682112862 cpu-cycles ( +- 0.03% )
130619 dTLB-load-misses ( +- 0.03% )
46073 iTLB-load-misses ( +- 0.05% )
19681 faults ( +- 0.01% )
5.381342641 seconds time elapsed ( +- 0.07% )
The proper work of the huge stack expansion was tested with the
following app:
int main(int argc, char **argv)
{
char buf[1024 * 1025];
sprintf(buf, "Hello world !\n");
printf(buf);
exit(0);
}
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Add include of pagemap.h to fix build errors]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit aa4113340ae6c2811e046f08c2bc21011d20a072 ]
In the current implementation, the call to loadcam_multi() is wrapped
between switch_to_as1() and restore_to_as0() calls so, when it tries
to create its own temporary AS=1 TLB1 entry, it ends up duplicating
the existing one created by switch_to_as1(). Add a check to skip
creating the temporary entry if already running in AS=1.
Fixes: d9e1831a4202 ("powerpc/85xx: Load all early TLB entries at once")
Cc: stable@vger.kernel.org # v4.4+
Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Scott Wood <oss@buserror.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200123111914.2565-1-laurentiu.tudor@nxp.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 790845e2f12709d273d08ea7a2af7c2593689519 ]
We were always calling base_hpte_find() with primary = true,
even when we wanted to check the secondary table.
mpe: I broke this when refactoring Rashmica's original patch.
Fixes: 1515ab932156 ("powerpc/mm: Dump hash table")
Signed-off-by: Rashmica Gupta <rashmica.g@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 8fabc623238e68b3ac63c0dd1657bf86c1fa33af ]
Some powerpc platforms (e.g. 85xx) limit DMA-able memory way below 4G.
If a system has more physical memory than this limit, the swiotlb
buffer is not addressable because it is allocated from memblock using
top-down mode.
Force memblock to bottom-up mode before calling swiotlb_init() to
ensure that the swiotlb buffer is DMA-able.
Reported-by: Christian Zigotzky <chzigotzky@xenosoft.de>
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191204123524.22919-1-rppt@kernel.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 16f6b67cf03cb43db7104acb2ca877bdc2606c92 ]
With large memory (8TB and more) hotplug, we can get soft lockup
warnings as below. These were caused by a long loop without any
explicit cond_resched which is a problem for !PREEMPT kernels.
Avoid this using cond_resched() while inserting hash page table
entries. We already do similar cond_resched() in __add_pages(), see
commit f64ac5e6e306 ("mm, memory_hotplug: add scheduling point to
__add_pages").
rcu: 3-....: (24002 ticks this GP) idle=13e/1/0x4000000000000002 softirq=722/722 fqs=12001
(t=24003 jiffies g=4285 q=2002)
NMI backtrace for cpu 3
CPU: 3 PID: 3870 Comm: ndctl Not tainted 5.3.0-197.18-default+ #2
Call Trace:
dump_stack+0xb0/0xf4 (unreliable)
nmi_cpu_backtrace+0x124/0x130
nmi_trigger_cpumask_backtrace+0x1ac/0x1f0
arch_trigger_cpumask_backtrace+0x28/0x3c
rcu_dump_cpu_stacks+0xf8/0x154
rcu_sched_clock_irq+0x878/0xb40
update_process_times+0x48/0x90
tick_sched_handle.isra.16+0x4c/0x80
tick_sched_timer+0x68/0xe0
__hrtimer_run_queues+0x180/0x430
hrtimer_interrupt+0x110/0x300
timer_interrupt+0x108/0x2f0
decrementer_common+0x114/0x120
--- interrupt: 901 at arch_add_memory+0xc0/0x130
LR = arch_add_memory+0x74/0x130
memremap_pages+0x494/0x650
devm_memremap_pages+0x3c/0xa0
pmem_attach_disk+0x188/0x750
nvdimm_bus_probe+0xac/0x2c0
really_probe+0x148/0x570
driver_probe_device+0x19c/0x1d0
device_driver_attach+0xcc/0x100
bind_store+0x134/0x1c0
drv_attr_store+0x44/0x60
sysfs_kf_write+0x64/0x90
kernfs_fop_write+0x1a0/0x270
__vfs_write+0x3c/0x70
vfs_write+0xd0/0x260
ksys_write+0xdc/0x130
system_call+0x5c/0x68
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191001084656.31277-1-aneesh.kumar@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 75838a3290cd4ebbd1f567f310ba04b6ef017ce4 ]
If the hypervisor returned H_PTEG_FULL for H_ENTER hcall, retry a hash page table
insert by removing a random entry from the group.
After some runtime, it is very well possible to find all the 8 hash page table
entry slot in the hpte group used for mapping. Don't fail a bolted entry insert
in that case. With Storage class memory a user can find this error easily since
a namespace enable/disable is equivalent to memory add/remove.
This results in failures as reported below:
$ ndctl create-namespace -r region1 -t pmem -m devdax -a 65536 -s 100M
libndctl: ndctl_dax_enable: dax1.3: failed to enable
Error: namespace1.2: failed to enable
failed to create namespace: No such device or address
In kernel log we find the details as below:
Unable to create mapping for hot added memory 0xc000042006000000..0xc00004200d000000: -1
dax_pmem: probe of dax1.3 failed with error -14
This indicates that we failed to create a bolted hash table entry for direct-map
address backing the namespace.
We also observe failures such that not all namespaces will be enabled with
ndctl enable-namespace all command.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191024093542.29777-2-aneesh.kumar@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 49a502ea23bf9dec47f8f3c3960909ff409cd1bb ]
As several other arches including x86, this patch makes it explicit
that a bad page fault is a NULL pointer dereference when the fault
address is lower than PAGE_SIZE
In the mean time, this page makes all bad_page_fault() messages
shorter so that they remain on one single line. And it prefixes them
by "BUG: " so that they get easily grepped.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
[mpe: Avoid pr_cont()]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit e93ba1b7eb5b188c749052df7af1c90821c5f320 ]
This patch fixes the loop in p_block_mapped() and v_block_mapped()
to scan the entire bat_addrs[] array.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 09b4438db13fa83b6219aee5993711a2aa2a0c64 ]
This causes SLB alloation to start 1 beyond the start of the SLB.
There is no real problem because after it wraps it stats behaving
properly, it's just surprisig to see when looking at SLB traces.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
commit 047e6575aec71d75b765c22111820c4776cd1c43 upstream.
On POWER9, under some circumstances, a broadcast TLB invalidation will
fail to invalidate the ERAT cache on some threads when there are
parallel mtpidr/mtlpidr happening on other threads of the same core.
This can cause stores to continue to go to a page after it's unmapped.
The workaround is to force an ERAT flush using PID=0 or LPID=0 tlbie
flush. This additional TLB flush will cause the ERAT cache
invalidation. Since we are using PID=0 or LPID=0, we don't get
filtered out by the TLB snoop filtering logic.
We need to still follow this up with another tlbie to take care of
store vs tlbie ordering issue explained in commit:
a5d4b5891c2f ("powerpc/mm: Fixup tlbie vs store ordering issue on
POWER9"). The presence of ERAT cache implies we can still get new
stores and they may miss store queue marking flush.
Cc: stable@vger.kernel.org # v4.14
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190924035254.24612-3-aneesh.kumar@linux.ibm.com
[sandipan: Backported to v4.14]
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 09ce98cacd51fcd0fa0af2f79d1e1d3192f4cbb0 upstream.
Rename the #define to indicate this is related to store vs tlbie
ordering issue. In the next patch, we will be adding another feature
flag that is used to handles ERAT flush vs tlbie ordering issue.
Cc: stable@vger.kernel.org # v4.14
Fixes: a5d4b5891c2f ("powerpc/mm: Fixup tlbie vs store ordering issue on POWER9")
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190924035254.24612-2-aneesh.kumar@linux.ibm.com
[sandipan: Backported to v4.14]
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit a5d4b5891c2f1f865a2def1eb0030f534e77ff86 upstream.
On POWER9, under some circumstances, a broadcast TLB invalidation
might complete before all previous stores have drained, potentially
allowing stale stores from becoming visible after the invalidation.
This works around it by doubling up those TLB invalidations which was
verified by HW to be sufficient to close the risk window.
This will be documented in a yet-to-be-published errata.
Cc: stable@vger.kernel.org # v4.14
Fixes: 1a472c9dba6b ("powerpc/mm/radix: Add tlbflush routines")
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[mpe: Enable the feature in the DT CPU features code for all Power9,
rename the feature to CPU_FTR_P9_TLBIE_BUG per benh.]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20180323045627.16800-3-aneesh.kumar@linux.vnet.ibm.com/
[sandipan: Backported to v4.14]
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
[ Upstream commit c784be435d5dae28d3b03db31753dd7a18733f0c ]
The calls to arch_add_memory()/arch_remove_memory() are always made
with the read-side cpu_hotplug_lock acquired via memory_hotplug_begin().
On pSeries, arch_add_memory()/arch_remove_memory() eventually call
resize_hpt() which in turn calls stop_machine() which acquires the
read-side cpu_hotplug_lock again, thereby resulting in the recursive
acquisition of this lock.
In the absence of CONFIG_PROVE_LOCKING, we hadn't observed a system
lockup during a memory hotplug operation because cpus_read_lock() is a
per-cpu rwsem read, which, in the fast-path (in the absence of the
writer, which in our case is a CPU-hotplug operation) simply
increments the read_count on the semaphore. Thus a recursive read in
the fast-path doesn't cause any problems.
However, we can hit this problem in practice if there is a concurrent
CPU-Hotplug operation in progress which is waiting to acquire the
write-side of the lock. This will cause the second recursive read to
block until the writer finishes. While the writer is blocked since the
first read holds the lock. Thus both the reader as well as the writers
fail to make any progress thereby blocking both CPU-Hotplug as well as
Memory Hotplug operations.
Memory-Hotplug CPU-Hotplug
CPU 0 CPU 1
------ ------
1. down_read(cpu_hotplug_lock.rw_sem)
[memory_hotplug_begin]
2. down_write(cpu_hotplug_lock.rw_sem)
[cpu_up/cpu_down]
3. down_read(cpu_hotplug_lock.rw_sem)
[stop_machine()]
Lockdep complains as follows in these code-paths.
swapper/0/1 is trying to acquire lock:
(____ptrval____) (cpu_hotplug_lock.rw_sem){++++}, at: stop_machine+0x2c/0x60
but task is already holding lock:
(____ptrval____) (cpu_hotplug_lock.rw_sem){++++}, at: mem_hotplug_begin+0x20/0x50
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(cpu_hotplug_lock.rw_sem);
lock(cpu_hotplug_lock.rw_sem);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by swapper/0/1:
#0: (____ptrval____) (&dev->mutex){....}, at: __driver_attach+0x12c/0x1b0
#1: (____ptrval____) (cpu_hotplug_lock.rw_sem){++++}, at: mem_hotplug_begin+0x20/0x50
#2: (____ptrval____) (mem_hotplug_lock.rw_sem){++++}, at: percpu_down_write+0x54/0x1a0
stack backtrace:
CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.0.0-rc5-58373-gbc99402235f3-dirty #166
Call Trace:
dump_stack+0xe8/0x164 (unreliable)
__lock_acquire+0x1110/0x1c70
lock_acquire+0x240/0x290
cpus_read_lock+0x64/0xf0
stop_machine+0x2c/0x60
pseries_lpar_resize_hpt+0x19c/0x2c0
resize_hpt_for_hotplug+0x70/0xd0
arch_add_memory+0x58/0xfc
devm_memremap_pages+0x5e8/0x8f0
pmem_attach_disk+0x764/0x830
nvdimm_bus_probe+0x118/0x240
really_probe+0x230/0x4b0
driver_probe_device+0x16c/0x1e0
__driver_attach+0x148/0x1b0
bus_for_each_dev+0x90/0x130
driver_attach+0x34/0x50
bus_add_driver+0x1a8/0x360
driver_register+0x108/0x170
__nd_driver_register+0xd0/0xf0
nd_pmem_driver_init+0x34/0x48
do_one_initcall+0x1e0/0x45c
kernel_init_freeable+0x540/0x64c
kernel_init+0x2c/0x160
ret_from_kernel_thread+0x5c/0x68
Fix this issue by
1) Requiring all the calls to pseries_lpar_resize_hpt() be made
with cpu_hotplug_lock held.
2) In pseries_lpar_resize_hpt() invoke stop_machine_cpuslocked()
as a consequence of 1)
3) To satisfy 1), in hpt_order_set(), call mmu_hash_ops.resize_hpt()
with cpu_hotplug_lock held.
Fixes: dbcf929c0062 ("powerpc/pseries: Add support for hash table resizing")
Cc: stable@vger.kernel.org # v4.11+
Reported-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1557906352-29048-1-git-send-email-ego@linux.vnet.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
commit 89a3496e0664577043666791ec07fb731d57c950 upstream.
We use mmu_vmemmap_psize to find the page size for mapping the vmmemap area.
With radix translation, we are suboptimally setting this value to PAGE_SIZE.
We do check for 2M page size support and update mmu_vmemap_psize to use
hugepage size but we suboptimally reset the value to PAGE_SIZE in
radix__early_init_mmu(). This resulted in always mapping vmemmap area with
64K page size.
Fixes: 2bfd65e45e87 ("powerpc/mm/radix: Add radix callbacks for early init routines")
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
[ Upstream commit 2d4d9b308f8f8dec68f6dbbff18c68ec7c6bd26f ]
When booted with "topology_updates=no", or when "off" is written to
/proc/powerpc/topology_updates, NUMA reassignments are inhibited for
PRRN and VPHN events. However, migration and suspend unconditionally
re-enable reassignments via start_topology_update(). This is
incoherent.
Check the topology_updates_enabled flag in
start/stop_topology_update() so that callers of those APIs need not be
aware of whether reassignments are enabled. This allows the
administrative decision on reassignments to remain in force across
migrations and suspensions.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
search
commit 3b4d07d2674f6b4a9281031f99d1f7efd325b16d upstream.
When doing top-down search the low_limit is not PAGE_SIZE but rather
max(PAGE_SIZE, mmap_min_addr). This handle cases in which mmap_min_addr >
PAGE_SIZE.
Fixes: fba2369e6ceb ("mm: use vm_unmapped_area() on powerpc architecture")
Reviewed-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
[ Upstream commit 81b61324922c67f73813d8a9c175f3c153f6a1c6 ]
On pseries systems, performing a partition migration can result in
altering the nodes a CPU is assigned to on the destination system. For
exampl, pre-migration on the source system CPUs are in node 1 and 3,
post-migration on the destination system CPUs are in nodes 2 and 3.
Handling the node change for a CPU can cause corruption in the slab
cache if we hit a timing where a CPUs node is changed while cache_reap()
is invoked. The corruption occurs because the slab cache code appears
to rely on the CPU and slab cache pages being on the same node.
The current dynamic updating of a CPUs node done in arch/powerpc/mm/numa.c
does not prevent us from hitting this scenario.
Changing the device tree property update notification handler that
recognizes an affinity change for a CPU to do a full DLPAR remove and
add of the CPU instead of dynamically changing its node resolves this
issue.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Michael W. Bringmann <mwb@linux.vnet.ibm.com>
Tested-by: Michael W. Bringmann <mwb@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 5330367fa300742a97e20e953b1f77f48392faae ]
After we ALIGN up the address we need to make sure we didn't overflow
and resulted in zero address. In that case, we need to make sure that
the returned address is greater than mmap_min_addr.
This fixes selftest va_128TBswitch --run-hugetlb reporting failures when
run as non root user for
mmap(-1, MAP_HUGETLB)
The bug is that a non-root user requesting address -1 will be given address 0
which will then fail, whereas they should have been given something else that
would have succeeded.
We also avoid the first mmap(-1, MAP_HUGETLB) returning NULL address as mmap address
with this change. So we think this is not a security issue, because it only affects
whether we choose an address below mmap_min_addr, not whether we
actually allow that address to be mapped. ie. there are existing capability
checks to prevent a user mapping below mmap_min_addr and those will still be
honoured even without this fix.
Fixes: 484837601d4d ("powerpc/mm: Add radix support for hugetlb")
Reviewed-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
commit 10c5e83afd4a3f01712d97d3bb1ae34d5b74a185 upstream.
In order to protect against speculation attacks on
indirect branches, the branch predictor is flushed at
kernel entry to protect for the following situations:
- userspace process attacking another userspace process
- userspace process attacking the kernel
Basically when the privillege level change (i.e. the
kernel is entered), the branch predictor state is flushed.
Signed-off-by: Diana Craciun <diana.craciun@nxp.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
[ Upstream commit ffca395b11c4a5a6df6d6345f794b0e3d578e2d0 ]
On the 8xx, no-execute is set via PPP bits in the PTE. Therefore
a no-exec fault generates DSISR_PROTFAULT error bits,
not DSISR_NOEXEC_OR_G.
This patch adds DSISR_PROTFAULT in the test mask.
Fixes: d3ca587404b3 ("powerpc/mm: Fix reporting of kernel execute faults")
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 462951cd32e1496dc64b00051dfb777efc8ae5d8 ]
For some configs the build fails with:
arch/powerpc/mm/dump_linuxpagetables.c: In function 'populate_markers':
arch/powerpc/mm/dump_linuxpagetables.c:306:39: error: 'PKMAP_BASE' undeclared (first use in this function)
arch/powerpc/mm/dump_linuxpagetables.c:314:50: error: 'LAST_PKMAP' undeclared (first use in this function)
These come from highmem.h, including that fixes the build.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 437ccdc8ce629470babdda1a7086e2f477048cbd ]
When VPHN function is not supported and during cpu hotplug event,
kernel prints message 'VPHN function not supported. Disabling
polling...'. Currently it prints on every hotplug event, it floods
dmesg when a KVM guest tries to hotplug huge number of vcpus, let's
just print once and suppress further kernel prints.
Signed-off-by: Satheesh Rajendran <sathnaga@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 803d690e68f0c5230183f1a42c7d50a41d16e380 ]
When a process allocates a hugepage, the following leak is
reported by kmemleak. This is a false positive which is
due to the pointer to the table being stored in the PGD
as physical memory address and not virtual memory pointer.
unreferenced object 0xc30f8200 (size 512):
comm "mmap", pid 374, jiffies 4872494 (age 627.630s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace:
[<e32b68da>] huge_pte_alloc+0xdc/0x1f8
[<9e0df1e1>] hugetlb_fault+0x560/0x8f8
[<7938ec6c>] follow_hugetlb_page+0x14c/0x44c
[<afbdb405>] __get_user_pages+0x1c4/0x3dc
[<b8fd7cd9>] __mm_populate+0xac/0x140
[<3215421e>] vm_mmap_pgoff+0xb4/0xb8
[<c148db69>] ksys_mmap_pgoff+0xcc/0x1fc
[<4fcd760f>] ret_from_syscall+0x0/0x38
See commit a984506c542e2 ("powerpc/mm: Don't report PUDs as
memory leaks when using kmemleak") for detailed explanation.
To fix that, this patch tells kmemleak to ignore the allocated
hugepage table.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
[ Upstream commit f5e284803a7206d43e26f9ffcae5de9626d95e37 ]
When enumerating page size definitions to check hardware support,
we construct a constant which is (1U << (def->shift - 10)).
However, the array of page size definitions is only initalised for
various MMU_PAGE_* constants, so it contains a number of 0-initialised
elements with def->shift == 0. This means we end up shifting by a
very large number, which gives the following UBSan splat:
================================================================================
UBSAN: Undefined behaviour in /home/dja/dev/linux/linux/arch/powerpc/mm/tlb_nohash.c:506:21
shift exponent 4294967286 is too large for 32-bit type 'unsigned int'
CPU: 0 PID: 0 Comm: swapper Not tainted 4.19.0-rc3-00045-ga604f927b012-dirty #6
Call Trace:
[c00000000101bc20] [c000000000a13d54] .dump_stack+0xa8/0xec (unreliable)
[c00000000101bcb0] [c0000000004f20a8] .ubsan_epilogue+0x18/0x64
[c00000000101bd30] [c0000000004f2b10] .__ubsan_handle_shift_out_of_bounds+0x110/0x1a4
[c00000000101be20] [c000000000d21760] .early_init_mmu+0x1b4/0x5a0
[c00000000101bf10] [c000000000d1ba28] .early_setup+0x100/0x130
[c00000000101bf90] [c000000000000528] start_here_multiplatform+0x68/0x80
================================================================================
Fix this by first checking if the element exists (shift != 0) before
constructing the constant.
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
[ Upstream commit 0d923962ab69c27cca664a2d535e90ef655110ca ]
When we're running on Book3S with the Radix MMU enabled the page table
dump currently prints the wrong addresses because it uses the wrong
start address.
Fix it to use PAGE_OFFSET rather than KERN_VIRT_START.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 51c3c62b58b357e8d35e4cc32f7b4ec907426fe3 upstream.
This stops us from doing code patching in init sections after they've
been freed.
In this chain:
kvm_guest_init() ->
kvm_use_magic_page() ->
fault_in_pages_readable() ->
__get_user() ->
__get_user_nocheck() ->
barrier_nospec();
We have a code patching location at barrier_nospec() and
kvm_guest_init() is an init function. This whole chain gets inlined,
so when we free the init section (hence kvm_guest_init()), this code
goes away and hence should no longer be patched.
We seen this as userspace memory corruption when using a memory
checker while doing partition migration testing on powervm (this
starts the code patching post migration via
/sys/kernel/mobility/migration). In theory, it could also happen when
using /sys/kernel/debug/powerpc/barrier_nospec.
Cc: stable@vger.kernel.org # 4.13+
Signed-off-by: Michael Neuling <mikey@neuling.org>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 8cfbdbdc24815417a3ab35101ccf706b9a23ff17 upstream.
Commit 76fa4975f3ed ("KVM: PPC: Check if IOMMU page is contained in
the pinned physical page", 2018-07-17) added some checks to ensure
that guest DMA mappings don't attempt to map more than the guest is
entitled to access. However, errors in the logic mean that legitimate
guest requests to map pages for DMA are being denied in some
situations. Specifically, if the first page of the range passed to
mm_iommu_get() is mapped with a normal page, and subsequent pages are
mapped with transparent huge pages, we end up with mem->pageshift ==
0. That means that the page size checks in mm_iommu_ua_to_hpa() and
mm_iommu_up_to_hpa_rm() will always fail for every page in that
region, and thus the guest can never map any memory in that region for
DMA, typically leading to a flood of error messages like this:
qemu-system-ppc64: VFIO_MAP_DMA: -22
qemu-system-ppc64: vfio_dma_map(0x10005f47780, 0x800000000000000, 0x10000, 0x7fff63ff0000) = -22 (Invalid argument)
The logic errors in mm_iommu_get() are:
(a) use of 'ua' not 'ua + (i << PAGE_SHIFT)' in the find_linux_pte()
call (meaning that find_linux_pte() returns the pte for the
first address in the range, not the address we are currently up
to);
(b) use of 'pageshift' as the variable to receive the hugepage shift
returned by find_linux_pte() - for a normal page this gets set
to 0, leading to us setting mem->pageshift to 0 when we conclude
that the pte returned by find_linux_pte() didn't match the page
we were looking at;
(c) comparing 'compshift', which is a page order, i.e. log base 2 of
the number of pages, with 'pageshift', which is a log base 2 of
the number of bytes.
To fix these problems, this patch introduces 'cur_ua' to hold the
current user address and uses that in the find_linux_pte() call;
introduces 'pteshift' to hold the hugepage shift found by
find_linux_pte(); and compares 'pteshift' with 'compshift +
PAGE_SHIFT' rather than 'compshift'.
The patch also moves the local_irq_restore to the point after the PTE
pointer returned by find_linux_pte() has been dereferenced because
otherwise the PTE could change underneath us, and adds a check to
avoid doing the find_linux_pte() call once mem->pageshift has been
reduced to PAGE_SHIFT, as an optimization.
Fixes: 76fa4975f3ed ("KVM: PPC: Check if IOMMU page is contained in the pinned physical page")
Cc: stable@vger.kernel.org # v4.12+
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
[ Upstream commit 926bc2f100c24d4842b3064b5af44ae964c1d81c ]
The stores to update the SLB shadow area must be made as they appear
in the C code, so that the hypervisor does not see an entry with
mismatched vsid and esid. Use WRITE_ONCE for this.
GCC has been observed to elide the first store to esid in the update,
which means that if the hypervisor interrupts the guest after storing
to vsid, it could see an entry with old esid and new vsid, which may
possibly result in memory corruption.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 76fa4975f3ed12d15762bc979ca44078598ed8ee upstream.
A VM which has:
- a DMA capable device passed through to it (eg. network card);
- running a malicious kernel that ignores H_PUT_TCE failure;
- capability of using IOMMU pages bigger that physical pages
can create an IOMMU mapping that exposes (for example) 16MB of
the host physical memory to the device when only 64K was allocated to the VM.
The remaining 16MB - 64K will be some other content of host memory, possibly
including pages of the VM, but also pages of host kernel memory, host
programs or other VMs.
The attacking VM does not control the location of the page it can map,
and is only allowed to map as many pages as it has pages of RAM.
We already have a check in drivers/vfio/vfio_iommu_spapr_tce.c that
an IOMMU page is contained in the physical page so the PCI hardware won't
get access to unassigned host memory; however this check is missing in
the KVM fastpath (H_PUT_TCE accelerated code). We were lucky so far and
did not hit this yet as the very first time when the mapping happens
we do not have tbl::it_userspace allocated yet and fall back to
the userspace which in turn calls VFIO IOMMU driver, this fails and
the guest does not retry,
This stores the smallest preregistered page size in the preregistered
region descriptor and changes the mm_iommu_xxx API to check this against
the IOMMU page size.
This calculates maximum page size as a minimum of the natural region
alignment and compound page size. For the page shift this uses the shift
returned by find_linux_pte() which indicates how the page is mapped to
the current userspace - if the page is huge and this is not a zero, then
it is a leaf pte and the page is mapped within the range.
Fixes: 121f80ba68f1 ("KVM: PPC: VFIO: Add in-kernel acceleration for VFIO")
Cc: stable@vger.kernel.org # v4.12+
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit aa0ab02ba992eb956934b21373e0138211486ddd upstream.
On the 8xx, the page size is set in the PMD entry and applies to
all pages of the page table pointed by the said PMD entry.
When an app has some regular pages allocated (e.g. see below) and tries
to mmap() a huge page at a hint address covered by the same PMD entry,
the kernel accepts the hint allthough the 8xx cannot handle different
page sizes in the same PMD entry.
10000000-10001000 r-xp 00000000 00:0f 2597 /root/malloc
10010000-10011000 rwxp 00000000 00:0f 2597 /root/malloc
mmap(0x10080000, 524288, PROT_READ|PROT_WRITE,
MAP_PRIVATE|MAP_ANONYMOUS|0x40000, -1, 0) = 0x10080000
This results the app remaining forever in do_page_fault()/hugetlb_fault()
and when interrupting that app, we get the following warning:
[162980.035629] WARNING: CPU: 0 PID: 2777 at arch/powerpc/mm/hugetlbpage.c:354 hugetlb_free_pgd_range+0xc8/0x1e4
[162980.035699] CPU: 0 PID: 2777 Comm: malloc Tainted: G W 4.14.6 #85
[162980.035744] task: c67e2c00 task.stack: c668e000
[162980.035783] NIP: c000fe18 LR: c00e1eec CTR: c00f90c0
[162980.035830] REGS: c668fc20 TRAP: 0700 Tainted: G W (4.14.6)
[162980.035854] MSR: 00029032 <EE,ME,IR,DR,RI> CR: 24044224 XER: 20000000
[162980.036003]
[162980.036003] GPR00: c00e1eec c668fcd0 c67e2c00 00000010 c6869410 10080000 00000000 77fb4000
[162980.036003] GPR08: ffff0001 0683c001 00000000 ffffff80 44028228 10018a34 00004008 418004fc
[162980.036003] GPR16: c668e000 00040100 c668e000 c06c0000 c668fe78 c668e000 c6835ba0 c668fd48
[162980.036003] GPR24: 00000000 73ffffff 74000000 00000001 77fb4000 100fffff 10100000 10100000
[162980.036743] NIP [c000fe18] hugetlb_free_pgd_range+0xc8/0x1e4
[162980.036839] LR [c00e1eec] free_pgtables+0x12c/0x150
[162980.036861] Call Trace:
[162980.036939] [c668fcd0] [c00f0774] unlink_anon_vmas+0x1c4/0x214 (unreliable)
[162980.037040] [c668fd10] [c00e1eec] free_pgtables+0x12c/0x150
[162980.037118] [c668fd40] [c00eabac] exit_mmap+0xe8/0x1b4
[162980.037210] [c668fda0] [c0019710] mmput.part.9+0x20/0xd8
[162980.037301] [c668fdb0] [c001ecb0] do_exit+0x1f0/0x93c
[162980.037386] [c668fe00] [c001f478] do_group_exit+0x40/0xcc
[162980.037479] [c668fe10] [c002a76c] get_signal+0x47c/0x614
[162980.037570] [c668fe70] [c0007840] do_signal+0x54/0x244
[162980.037654] [c668ff30] [c0007ae8] do_notify_resume+0x34/0x88
[162980.037744] [c668ff40] [c000dae8] do_user_signal+0x74/0xc4
[162980.037781] Instruction dump:
[162980.037821] 7fdff378 81370000 54a3463a 80890020 7d24182e 7c841a14 712a0004 4082ff94
[162980.038014] 2f890000 419e0010 712a0ff0 408200e0 <0fe00000> 54a9000a 7f984840 419d0094
[162980.038216] ---[ end trace c0ceeca8e7a5800a ]---
[162980.038754] BUG: non-zero nr_ptes on freeing mm: 1
[162985.363322] BUG: non-zero nr_ptes on freeing mm: -1
In order to fix this, this patch uses the address space "slices"
implemented for BOOK3S/64 and enhanced to support PPC32 by the
preceding patch.
This patch modifies the context.id on the 8xx to be in the range
[1:16] instead of [0:15] in order to identify context.id == 0 as
not initialised contexts as done on BOOK3S
This patch activates CONFIG_PPC_MM_SLICES when CONFIG_HUGETLB_PAGE is
selected for the 8xx
Alltough we could in theory have as many slices as PMD entries, the
current slices implementation limits the number of low slices to 16.
This limitation is not preventing us to fix the initial issue allthough
it is suboptimal. It will be cured in a subsequent patch.
Fixes: 4b91428699477 ("powerpc/8xx: Implement support of hugepages")
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit db3a528db41caaa6dfd4c64e9f5efb1c81a80467 upstream.
In preparation for the following patch which will fix an issue on
the 8xx by re-using the 'slices', this patch enhances the
'slices' implementation to support 32 bits CPUs.
On PPC32, the address space is limited to 4Gbytes, hence only the low
slices will be used.
The high slices use bitmaps. As bitmap functions are not prepared to
handle bitmaps of size 0, this patch ensures that bitmap functions
are called only when SLICE_NUM_HIGH is not nul.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 326691ad4f179e6edc7eb1271e618dd673e4736d upstream.
bitmap_or() and bitmap_andnot() can work properly with dst identical
to src1 or src2. There is no need of an intermediate result bitmap
that is copied back to dst in a second step.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit fb5924fddf9ee31db04da7ad4e8c3434a387101b upstream.
This patch adds support for flushing potentially dirty cache lines
when memory is hot-plugged/hot-un-plugged. The support is currently
limited to 64 bit systems.
The bug was exposed when mappings for a device were actually
hot-unplugged and plugged in back later. A similar issue was observed
during the development of memtrace, but memtrace does it's own
flushing of region via a custom routine.
These patches do a flush both on hotplug/unplug to clear any stale
data in the cache w.r.t mappings, there is a small race window where a
clean cache line may be created again just prior to tearing down the
mapping.
The patches were tested by disabling the flush routines in memtrace
and doing I/O on the trace file. The system immediately
checkstops (quite reliablly if prior to the hot-unplug of the memtrace
region, we memset the regions we are about to hot unplug). After these
patches no custom flushing is needed in the memtrace code.
Fixes: 9d5171a8f248 ("powerpc/powernv: Enable removal of memory for in memory tracing")
Cc: stable@vger.kernel.org # v4.14+
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
Acked-by: Reza Arbab <arbab@linux.ibm.com>
Reviewed-by: Rashmica Gupta <rashmica.g@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
[ Upstream commit ea05ba7c559c8e5a5946c3a94a2a266e9a6680a6 ]
This patch fixes some problems encountered at runtime with
configurations that support memory-less nodes, or that hot-add CPUs
into nodes that are memoryless during system execution after boot. The
problems of interest include:
* Nodes known to powerpc to be memoryless at boot, but to have CPUs in
them are allowed to be 'possible' and 'online'. Memory allocations
for those nodes are taken from another node that does have memory
until and if memory is hot-added to the node.
* Nodes which have no resources assigned at boot, but which may still
be referenced subsequently by affinity or associativity attributes,
are kept in the list of 'possible' nodes for powerpc. Hot-add of
memory or CPUs to the system can reference these nodes and bring
them online instead of redirecting the references to one of the set
of nodes known to have memory at boot.
Note that this software operates under the context of CPU hotplug. We
are not doing memory hotplug in this code, but rather updating the
kernel's CPU topology (i.e. arch_update_cpu_topology /
numa_update_cpu_topology). We are initializing a node that may be used
by CPUs or memory before it can be referenced as invalid by a CPU
hotplug operation. CPU hotplug operations are protected by a range of
APIs including cpu_maps_update_begin/cpu_maps_update_done,
cpus_read/write_lock / cpus_read/write_unlock, device locks, and more.
Memory hotplug operations, including try_online_node, are protected by
mem_hotplug_begin/mem_hotplug_done, device locks, and more. In the
case of CPUs being hot-added to a previously memoryless node, the
try_online_node operation occurs wholly within the CPU locks with no
overlap. Using HMC hot-add/hot-remove operations, we have been able to
add and remove CPUs to any possible node without failures. HMC
operations involve a degree self-serialization, though.
Signed-off-by: Michael Bringmann <mwb@linux.vnet.ibm.com>
Reviewed-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
[ Upstream commit a346137e9142b039fd13af2e59696e3d40c487ef ]
On powerpc systems which allow 'hot-add' of CPU or memory resources,
it may occur that the new resources are to be inserted into nodes that
were not used for these resources at bootup. In the kernel, any node
that is used must be defined and initialized. These empty nodes may
occur when,
* Dedicated vs. shared resources. Shared resources require information
such as the VPHN hcall for CPU assignment to nodes. Associativity
decisions made based on dedicated resource rules, such as
associativity properties in the device tree, may vary from decisions
made using the values returned by the VPHN hcall.
* memoryless nodes at boot. Nodes need to be defined as 'possible' at
boot for operation with other code modules. Previously, the powerpc
code would limit the set of possible nodes to those which have
memory assigned at boot, and were thus online. Subsequent add/remove
of CPUs or memory would only work with this subset of possible
nodes.
* memoryless nodes with CPUs at boot. Due to the previous restriction
on nodes, nodes that had CPUs but no memory were being collapsed
into other nodes that did have memory at boot. In practice this
meant that the node assignment presented by the runtime kernel
differed from the affinity and associativity attributes presented by
the device tree or VPHN hcalls. Nodes that might be known to the
pHyp were not 'possible' in the runtime kernel because they did not
have memory at boot.
This patch ensures that sufficient nodes are defined to support
configuration requirements after boot, as well as at boot. This patch
set fixes a couple of problems.
* Nodes known to powerpc to be memoryless at boot, but to have CPUs in
them are allowed to be 'possible' and 'online'. Memory allocations
for those nodes are taken from another node that does have memory
until and if memory is hot-added to the node. * Nodes which have no
resources assigned at boot, but which may still be referenced
subsequently by affinity or associativity attributes, are kept in
the list of 'possible' nodes for powerpc. Hot-add of memory or CPUs
to the system can reference these nodes and bring them online
instead of redirecting to one of the set of nodes that were known to
have memory at boot.
This patch extracts the value of the lowest domain level (number of
allocable resources) from the device tree property
"ibm,max-associativity-domains" to use as the maximum number of nodes
to setup as possibly available in the system. This new setting will
override the instruction:
nodes_and(node_possible_map, node_possible_map, node_online_map);
presently seen in the function arch/powerpc/mm/numa.c:initmem_init().
If the "ibm,max-associativity-domains" property is not present at
boot, no operation will be performed to define or enable additional
nodes, or enable the above 'nodes_and()'.
Signed-off-by: Michael Bringmann <mwb@linux.vnet.ibm.com>
Reviewed-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit dbfcf3cb9c681aa0c5d0bb46068f98d5b1823dd3 upstream.
On POWER9, since commit cc3d2940133d ("powerpc/64: Enable use of radix
MMU under hypervisor on POWER9", 2017-01-30), we set both the radix and
HPT bits in the client-architecture-support (CAS) vector, which tells
the hypervisor that we can do either radix or HPT. According to PAPR,
if we use this combination we are promising to do a H_REGISTER_PROC_TBL
hcall later on to let the hypervisor know whether we are doing radix
or HPT. We currently do this call if we are doing radix but not if
we are doing HPT. If the hypervisor is able to support both radix
and HPT guests, it would be entitled to defer allocation of the HPT
until the H_REGISTER_PROC_TBL call, and to fail any attempts to create
HPTEs until the H_REGISTER_PROC_TBL call. Thus we need to do a
H_REGISTER_PROC_TBL call when we are doing HPT; otherwise we may
crash at boot time.
This adds the code to call H_REGISTER_PROC_TBL in this case, before
we attempt to create any HPT entries using H_ENTER.
Fixes: cc3d2940133d ("powerpc/64: Enable use of radix MMU under hypervisor on POWER9")
Cc: stable@vger.kernel.org # v4.11+
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Reviewed-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 4dd5f8a99e791a8c6500e3592f3ce81ae7edcde1 upstream.
This patch splits the linear mapping if the hot-unplug range is
smaller than the mapping size. The code detects if the mapping needs
to be split into a smaller size and if so, uses the stop machine
infrastructure to clear the existing mapping and then remap the
remaining range using a smaller page size.
The code will skip any region of the mapping that overlaps with kernel
text and warn about it once. We don't want to remove a mapping where
the kernel text and the LMB we intend to remove overlap in the same
TLB mapping as it may affect the currently executing code.
I've tested these changes under a kvm guest with 2 vcpus, from a split
mapping point of view, some of the caveats mentioned above applied to
the testing I did.
Fixes: 4b5d62ca17a1 ("powerpc/mm: add radix__remove_section_mapping()")
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
[mpe: Tweak change log to match updated behaviour]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 62e984ddfd6b056d399e24113f5e6a7145e579d8 upstream.
Radix guests do normally invalidate process-scoped translations when a
new pid is allocated but migrated guests do not invalidate these so
migrated guests crash sometime, especially easy to reproduce with
migration happening within first 10 seconds after the guest boot start
on the same machine.
This adds the "Invalidate process-scoped translations" flush to fix
radix guests migration.
Fixes: 2ee13be34b13 ("KVM: PPC: Book3S HV: Update kvmppc_set_arch_compat() for ISA v3.00")
Cc: stable@vger.kernel.org # v4.10+
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Tested-by: Daniel Henrique Barboza <danielhb@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 1d9a090783bef19fe8cdec878620d22f05191316 upstream.
When DLPAR removing a CPU, the unmapping of the cpu from a node in
unmap_cpu_from_node() should also invalidate the CPUs entry in the
numa_cpu_lookup_table. There is not a guarantee that on a subsequent
DLPAR add of the CPU the associativity will be the same and thus
could be in a different node. Invalidating the entry in the
numa_cpu_lookup_table causes the associativity to be read from the
device tree at the time of the add.
The current behavior of not invalidating the CPUs entry in the
numa_cpu_lookup_table can result in scenarios where the the topology
layout of CPUs in the partition does not match the device tree
or the topology reported by the HMC.
This bug looks like it was introduced in 2004 in the commit titled
"ppc64: cpu hotplug notifier for numa", which is 6b15e4e87e32 in the
linux-fullhist tree. Hence tag it for all stable releases.
Cc: stable@vger.kernel.org
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Reviewed-by: Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 8d81296cfcce89013a714feb8d25004a156f8181 upstream.
radix__flush_tlb_all() is called only in kexec path in real mode and any
tracepoints at this stage will make kexec to fail if enabled.
To verify enable tlbie trace before kexec.
$ echo 1 > /sys/kernel/debug/tracing/events/powerpc/tlbie/enable
== kexec into new kernel and kexec fails.
Fix this by not calling trace_tlbie from radix__flush_tlb_all().
Fixes: 0428491cba92 ("powerpc/mm: Trace tlbie(l) instructions")
Cc: stable@vger.kernel.org # v4.13+
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Acked-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit ecb101aed86156ec7cd71e5dca668e09146e6994 upstream.
The recent refactoring of the powerpc page fault handler in commit
c3350602e876 ("powerpc/mm: Make bad_area* helper functions") caused
access to protected memory regions to indicate SEGV_MAPERR instead of
the traditional SEGV_ACCERR in the si_code field of a user-space
signal handler. This can confuse debug libraries that temporarily
change the protection of memory regions, and expect to use SEGV_ACCERR
as an indication to restore access to a region.
This commit restores the previous behavior. The following program
exhibits the issue:
$ ./repro read || echo "FAILED"
$ ./repro write || echo "FAILED"
$ ./repro exec || echo "FAILED"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <signal.h>
#include <sys/mman.h>
#include <assert.h>
static void segv_handler(int n, siginfo_t *info, void *arg) {
_exit(info->si_code == SEGV_ACCERR ? 0 : 1);
}
int main(int argc, char **argv)
{
void *p = NULL;
struct sigaction act = {
.sa_sigaction = segv_handler,
.sa_flags = SA_SIGINFO,
};
assert(argc == 2);
p = mmap(NULL, getpagesize(),
(strcmp(argv[1], "write") == 0) ? PROT_READ : 0,
MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
assert(p != MAP_FAILED);
assert(sigaction(SIGSEGV, &act, NULL) == 0);
if (strcmp(argv[1], "read") == 0)
printf("%c", *(unsigned char *)p);
else if (strcmp(argv[1], "write") == 0)
*(unsigned char *)p = 0;
else if (strcmp(argv[1], "exec") == 0)
((void (*)(void))p)();
return 1; /* failed to generate SEGV */
}
Fixes: c3350602e876 ("powerpc/mm: Make bad_area* helper functions")
Signed-off-by: John Sperbeck <jsperbeck@google.com>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
[mpe: Add commit references in change log]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit a3961f824cdbe7eb431254dc7d8f6f6767f474aa upstream.
Rebooting into a new kernel with kexec fails in trace_tlbie() which is
called from native_hpte_clear(). This happens if the running kernel
has CONFIG_LOCKDEP enabled. With lockdep enabled, the tracepoints
always execute few RCU checks regardless of whether tracing is on or
off. We are already in the last phase of kexec sequence in real mode
with HILE_BE set. At this point the RCU check ends up in
RCU_LOCKDEP_WARN and causes kexec to fail.
Fix this by not calling trace_tlbie() from native_hpte_clear().
mpe: It's not safe to call trace points at this point in the kexec
path, even if we could avoid the RCU checks/warnings. The only
solution is to not call them.
Fixes: 0428491cba92 ("powerpc/mm: Trace tlbie(l) instructions")
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Reported-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Suggested-by: Michael Ellerman <mpe@ellerman.id.au>
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 35602f82d0c765f991420e319c8d3a596c921eb8 upstream.
While mapping hints with a length that cross 128TB are disallowed,
MAP_FIXED allocations that cross 128TB are allowed. These are failing
on hash (on radix they succeed). Add an additional case for fixed
mappings to expand the addr_limit when crossing 128TB.
Fixes: f4ea6dcb08ea ("powerpc/mm: Enable mappings above 128TB")
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit effc1b25088502fbd30305c79773de2d1f7470a6 upstream.
Hash unconditionally resets the addr_limit to default (128TB) when the
mm context is initialised. If a process has > 128TB mappings when it
forks, the child will not get the 512TB addr_limit, so accesses to
valid > 128TB mappings will fail in the child.
Fix this by only resetting the addr_limit to default if it was 0. Non
zero indicates it was duplicated from the parent (0 means exec()).
Fixes: f4ea6dcb08ea ("powerpc/mm: Enable mappings above 128TB")
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 6a72dc038b615229a1b285829d6c8378d15c2347 upstream.
When allocating VA space with a hint that crosses 128TB, the SLB
addr_limit variable is not expanded if addr is not > 128TB, but the
slice allocation looks at task_size, which is 512TB. This results in
slice_check_fit() incorrectly succeeding because the slice_count
truncates off bit 128 of the requested mask, so the comparison to the
available mask succeeds.
Fix this by using mm->context.addr_limit instead of mm->task_size for
testing allocation limits. This causes such allocations to fail.
Fixes: f4ea6dcb08ea ("powerpc/mm: Enable mappings above 128TB")
Reported-by: Florian Weimer <fweimer@redhat.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 7ece370996b694ae263025e056ad785afc1be5ab upstream.
Currently userspace is able to request mmap() search between 128T-512T
by specifying a hint address that is greater than 128T. But that means
a hint of 128T exactly will return an address below 128T, which is
confusing and wrong.
So fix the logic to check the hint is greater than *or equal* to 128T.
Fixes: f4ea6dcb08ea ("powerpc/mm: Enable mappings above 128TB")
Suggested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Suggested-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Split out of Nick's bigger patch]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 85e3f1adcb9d49300b0a943bb93f9604be375bfb upstream.
Radix VA space allocations test addresses against mm->task_size which
is 512TB, even in cases where the intention is to limit allocation to
below 128TB.
This results in mmap with a hint address below 128TB but address +
length above 128TB succeeding when it should fail (as hash does after
the previous patch).
Set the high address limit to be considered up front, and base
subsequent allocation checks on that consistently.
Fixes: f4ea6dcb08ea ("powerpc/mm: Enable mappings above 128TB")
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit f79ad50ea3c73fb1ea5b09e95c864e5bb263adfb upstream.
When using the radix MMU on Power9 DD1, to work around a hardware
problem, radix__pte_update() is required to do a two stage update of
the PTE. First we write a zero value into the PTE, then we flush the
TLB, and then we write the new PTE value.
In the normal case that works OK, but it does not work if we're
updating the PTE that maps the code we're executing, because the
mapping is removed by the TLB flush and we can no longer execute from
it. Unfortunately the STRICT_RWX code needs to do exactly that.
The exact symptoms when we hit this case vary, sometimes we print an
oops and then get stuck after that, but I've also seen a machine just
get stuck continually page faulting with no oops printed. The variance
is presumably due to the exact layout of the text and the page size
used for the mappings. In all cases we are unable to boot to a shell.
There are possible solutions such as creating a second mapping of the
TLB flush code, executing from that, and then jumping back to the
original. However we don't want to add that level of complexity for a
DD1 work around.
So just detect that we're running on Power9 DD1 and refrain from
changing the permissions, effectively disabling STRICT_RWX on Power9
DD1.
Fixes: 7614ff3272a1 ("powerpc/mm/radix: Implement STRICT_RWX/mark_rodata_ro() for Radix")
Reported-by: Andrew Jeffery <andrew@aj.id.au>
[Changelog as suggested by Michael Ellerman <mpe@ellerman.id.au>]
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc fixes from Michael Ellerman:
"Some more powerpc fixes for 4.14.
This is bigger than I like to send at rc7, but that's at least partly
because I didn't send any fixes last week. If it wasn't for the IMC
driver, which is new and getting heavy testing, the diffstat would
look a bit better. I've also added ftrace on big endian to my test
suite, so we shouldn't break that again in future.
- A fix to the handling of misaligned paste instructions (P9 only),
where a change to a #define has caused the check for the
instruction to always fail.
- The preempt handling was unbalanced in the radix THP flush (P9
only). Though we don't generally use preempt we want to keep it
working as much as possible.
- Two fixes for IMC (P9 only), one when booting with restricted
number of CPUs and one in the error handling when initialisation
fails due to firmware etc.
- A revert to fix function_graph on big endian machines, and then a
rework of the reverted patch to fix kprobes blacklist handling on
big endian machines.
Thanks to: Anju T Sudhakar, Guilherme G. Piccoli, Madhavan Srinivasan,
Naveen N. Rao, Nicholas Piggin, Paul Mackerras"
* tag 'powerpc-4.14-6' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
powerpc/perf: Fix core-imc hotplug callback failure during imc initialization
powerpc/kprobes: Dereference function pointers only if the address does not belong to kernel text
Revert "powerpc64/elfv1: Only dereference function descriptor for non-text symbols"
powerpc/64s/radix: Fix preempt imbalance in TLB flush
powerpc: Fix check for copy/paste instructions in alignment handler
powerpc/perf: Fix IMC allocation routine
|
