IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an
email to Administrator. User accounts are meant only to access repo
and report issues and/or generate pull requests.
This is a purpose-specific Git hosting for
BaseALT
projects. Thank you for your understanding!
Только зарегистрированные пользователи имеют доступ к сервису!
Для получения аккаунта, обратитесь к администратору.
All 32 and 64-bit builds that don't have CONFIG_TAU_INT enabled (all
of them), get a definition of TAUException() in traps.c.
On 64-bit it's completely useless, and just wastes ~120 bytes of text.
On 32-bit it allows the kernel to link because head_32.S calls it
unconditionally.
Instead follow the example of altivec_assist_exception(), and if
CONFIG_TAU_INT is not enabled just point it at unknown_exception using
the preprocessor.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200724131728.1643966-6-mpe@ellerman.id.au
We have two uses of CONFIG_BOOK3S_601, which doesn't exist. Fix them
to use CONFIG_PPC_BOOK3S_601 which is the correct symbol.
Fixes: 12c3f1fd87bf ("powerpc/32s: get rid of CPU_FTR_601 feature")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200724131728.1643966-5-mpe@ellerman.id.au
This code was merged 11 years ago in commit 13363ab9b9d0 ("powerpc:
Add definitions used by exception handling on 64-bit Book3E") but was
never able to be built because CONFIG_BOOK3E_MMU_TLB_STATS never
existed. Remove it.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200724131728.1643966-4-mpe@ellerman.id.au
There's a comment in lite5200_sleep.S that refers to "CONFIG_BDI*".
This confuses scripts/checkkconfigsymbols.py, which thinks it should
be able to find CONFIG_BDI.
Change the comment to refer to CONFIG_BDI_SWITCH which is presumably
roughly what it was referring to. AFAICS there never has been a
CONFIG_BDI.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200724131728.1643966-3-mpe@ellerman.id.au
During memory hotplug and unplug, resize_hpt_for_hotplug() gets called
for both hash and radix guests but it should be called only for hash
guests. Though the call does nothing in the radix guest case, it is
cleaner to push this call into hash specific memory hotplug routines.
Reported-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200727095704.1432916-1-bharata@linux.ibm.com
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 logic aims to prevent userspace from doing bad accesses below the
stack pointer. However as long as the stack is < 1MB in size, we allow
all accesses without further checks. Adding some debug I see that I
can do a full kernel build and LTP run, and not a single process has
used more than 1MB of stack. So for the majority of processes the
logic never even fires.
We also recently found a nasty bug in this code which could cause
userspace programs to be killed during signal delivery. It went
unnoticed presumably because most processes use < 1MB of stack.
The generic mm code has also grown support for stack guard pages since
this code was originally written, so the most heinous case of the
stack expanding into other mappings is now handled for us.
Finally although some other arches have special logic in this path,
from what I can tell none of x86, arm64, arm and s390 impose any extra
checks other than those in expand_stack().
So drop our complicated logic and like other architectures just let
the stack expand as long as its within the rlimit.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Tested-by: Daniel Axtens <dja@axtens.net>
Link: https://lore.kernel.org/r/20200724092528.1578671-4-mpe@ellerman.id.au
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
KVM guests have certain restrictions and performance quirks when using
doorbells. This patch moves the EPAPR KVM guest test so it can be shared
with PSERIES, and uses that in doorbell setup code to apply the KVM
guest quirks and improves IPI performance for two cases:
- PowerVM guests may now use doorbells even if they are secure.
- KVM guests no longer use doorbells if XIVE is available.
There is a valid complaint that "KVM guest" is not a very reasonable
thing to test for, it's preferable for the hypervisor to advertise
particular behaviours to the guest so they could change if the
hypervisor implementation or configuration changes. However in this case
we were already assuming a KVM guest worst case, so this patch is about
containing those quirks. If KVM later advertises fast doorbells, we
should test for that and override the quirks.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Tested-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200726035155.1424103-4-npiggin@gmail.com
KVM supports msgsndp in guests by trapping and emulating the
instruction, so it was decided to always use XIVE for IPIs if it is
available. However on PowerVM systems, msgsndp can be used and gives
better performance. On large systems, high XIVE interrupt rates can
have sub-linear scaling, and using msgsndp can reduce the load on
the interrupt controller.
So switch to using core local doorbells even if XIVE is available.
This reduces performance for KVM guests with an SMT topology by
about 50% for ping-pong context switching between SMT vCPUs. An
option vector (or dt-cpu-ftrs) could be defined to disable msgsndp
to get KVM performance back.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Tested-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200726035155.1424103-3-npiggin@gmail.com
These are only called in one place for a given platform, so inline
them for performance.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Tested-by: Cédric Le Goater <clg@kaod.org>
[mpe: Fix build errors related to KVM]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200726035155.1424103-2-npiggin@gmail.com
Commit 9908c826d5ed ("powerpc/perf: Add Power10 PMU feature to DT CPU
features") defines MMCRA_BHRB_DISABLE as `0x2000000000UL`. Binutils
version less than 2.28 doesn't support UL suffix.
arch/powerpc/kernel/cpu_setup_power.S: Assembler messages:
arch/powerpc/kernel/cpu_setup_power.S:250: Error: found 'L', expected: ')'
arch/powerpc/kernel/cpu_setup_power.S:250: Error: junk at end of line, first unrecognized character is `L'
arch/powerpc/kernel/cpu_setup_power.S:250: Error: found 'L', expected: ')'
arch/powerpc/kernel/cpu_setup_power.S:250: Error: found 'L', expected: ')'
arch/powerpc/kernel/cpu_setup_power.S:250: Error: junk at end of line, first unrecognized character is `L'
arch/powerpc/kernel/cpu_setup_power.S:250: Error: found 'L', expected: ')'
arch/powerpc/kernel/cpu_setup_power.S:250: Error: found 'L', expected: ')'
arch/powerpc/kernel/cpu_setup_power.S:250: Error: operand out of range (0x0000002000000000 is not between 0xffffffffffff8000 and 0x000000000000ffff)
Fix this by wrapping it with the `_UL` macro.
Fixes: 9908c826d5ed ("Add Power10 PMU feature to DT CPU features")
Suggested-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Reviewed-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1595996214-5833-1-git-send-email-atrajeev@linux.vnet.ibm.com
The src_owner field in struct migrate_vma is being used for two purposes,
it acts as a selection filter for which types of pages are to be migrated
and it identifies device private pages owned by the caller.
Split this into separate parameters so the src_owner field can be used
just to identify device private pages owned by the caller of
migrate_vma_setup().
Rename the src_owner field to pgmap_owner to reflect it is now used only
to identify which device private pages to migrate.
Link: https://lore.kernel.org/r/20200723223004.9586-3-rcampbell@nvidia.com
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
When a secure memslot is dropped, all the pages backed in the secure
device (aka really backed by secure memory by the Ultravisor)
should be paged out to a normal page. Previously, this was
achieved by triggering the page fault mechanism which is calling
kvmppc_svm_page_out() on each pages.
This can't work when hot unplugging a memory slot because the memory
slot is flagged as invalid and gfn_to_pfn() is then not trying to access
the page, so the page fault mechanism is not triggered.
Since the final goal is to make a call to kvmppc_svm_page_out() it seems
simpler to call directly instead of triggering such a mechanism. This
way kvmppc_uvmem_drop_pages() can be called even when hot unplugging a
memslot.
Since kvmppc_uvmem_drop_pages() is already holding kvm->arch.uvmem_lock,
the call to __kvmppc_svm_page_out() is made. As
__kvmppc_svm_page_out needs the vma pointer to migrate the pages,
the VMA is fetched in a lazy way, to not trigger find_vma() all
the time. In addition, the mmap_sem is held in read mode during
that time, not in write mode since the virual memory layout is not
impacted, and kvm->arch.uvmem_lock prevents concurrent operation
on the secure device.
Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
[modified check on the VMA in kvmppc_uvmem_drop_pages]
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
[modified the changelog description]
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
kvmppc_svm_page_out() will need to be called by kvmppc_uvmem_drop_pages()
so move it up earlier in this file.
Furthermore it will be interesting to call this function when already
holding the kvm->arch.uvmem_lock, so prefix the original function with __
and remove the locking in it, and introduce a wrapper which call that
function with the lock held.
There is no functional change.
Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
When a memory slot is hot plugged to a SVM, PFNs associated with the
GFNs in that slot must be migrated to the secure-PFNs, aka device-PFNs.
Call kvmppc_uv_migrate_mem_slot() to accomplish this.
Disable page-merge for all pages in the memory slot.
Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
[rearranged the code, and modified the commit log]
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
The Ultravisor is expected to explicitly call H_SVM_PAGE_IN for all the
pages of the SVM before calling H_SVM_INIT_DONE. This causes a huge
delay in tranistioning the VM to SVM. The Ultravisor is only interested
in the pages that contain the kernel, initrd and other important data
structures. The rest contain throw-away content.
However if not all pages are requested by the Ultravisor, the Hypervisor
continues to consider the GFNs corresponding to the non-requested pages
as normal GFNs. This can lead to data-corruption and undefined behavior.
In H_SVM_INIT_DONE handler, move all the PFNs associated with the SVM's
GFNs to secure-PFNs. Skip the GFNs that are already Paged-in or Shared
or Paged-in followed by a Paged-out.
Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
During the life of SVM, its GFNs transition through normal, secure and
shared states. Since the kernel does not track GFNs that are shared, it
is not possible to disambiguate a shared GFN from a GFN whose PFN has
not yet been migrated to a secure-PFN. Also it is not possible to
disambiguate a secure-GFN from a GFN whose GFN has been pagedout from
the ultravisor.
The ability to identify the state of a GFN is needed to skip migration
of its PFN to secure-PFN during ESM transition.
The code is re-organized to track the states of a GFN as explained
below.
************************************************************************
1. States of a GFN
---------------
The GFN can be in one of the following states.
(a) Secure - The GFN is secure. The GFN is associated with
a Secure VM, the contents of the GFN is not accessible
to the Hypervisor. This GFN can be backed by a secure-PFN,
or can be backed by a normal-PFN with contents encrypted.
The former is true when the GFN is paged-in into the
ultravisor. The latter is true when the GFN is paged-out
of the ultravisor.
(b) Shared - The GFN is shared. The GFN is associated with a
a secure VM. The contents of the GFN is accessible to
Hypervisor. This GFN is backed by a normal-PFN and its
content is un-encrypted.
(c) Normal - The GFN is a normal. The GFN is associated with
a normal VM. The contents of the GFN is accesible to
the Hypervisor. Its content is never encrypted.
2. States of a VM.
---------------
(a) Normal VM: A VM whose contents are always accessible to
the hypervisor. All its GFNs are normal-GFNs.
(b) Secure VM: A VM whose contents are not accessible to the
hypervisor without the VM's consent. Its GFNs are
either Shared-GFN or Secure-GFNs.
(c) Transient VM: A Normal VM that is transitioning to secure VM.
The transition starts on successful return of
H_SVM_INIT_START, and ends on successful return
of H_SVM_INIT_DONE. This transient VM, can have GFNs
in any of the three states; i.e Secure-GFN, Shared-GFN,
and Normal-GFN. The VM never executes in this state
in supervisor-mode.
3. Memory slot State.
------------------
The state of a memory slot mirrors the state of the
VM the memory slot is associated with.
4. VM State transition.
--------------------
A VM always starts in Normal Mode.
H_SVM_INIT_START moves the VM into transient state. During this
time the Ultravisor may request some of its GFNs to be shared or
secured. So its GFNs can be in one of the three GFN states.
H_SVM_INIT_DONE moves the VM entirely from transient state to
secure-state. At this point any left-over normal-GFNs are
transitioned to Secure-GFN.
H_SVM_INIT_ABORT moves the transient VM back to normal VM.
All its GFNs are moved to Normal-GFNs.
UV_TERMINATE transitions the secure-VM back to normal-VM. All
the secure-GFN and shared-GFNs are tranistioned to normal-GFN
Note: The contents of the normal-GFN is undefined at this point.
5. GFN state implementation:
-------------------------
Secure GFN is associated with a secure-PFN; also called uvmem_pfn,
when the GFN is paged-in. Its pfn[] has KVMPPC_GFN_UVMEM_PFN flag
set, and contains the value of the secure-PFN.
It is associated with a normal-PFN; also called mem_pfn, when
the GFN is pagedout. Its pfn[] has KVMPPC_GFN_MEM_PFN flag set.
The value of the normal-PFN is not tracked.
Shared GFN is associated with a normal-PFN. Its pfn[] has
KVMPPC_UVMEM_SHARED_PFN flag set. The value of the normal-PFN
is not tracked.
Normal GFN is associated with normal-PFN. Its pfn[] has
no flag set. The value of the normal-PFN is not tracked.
6. Life cycle of a GFN
--------------------
--------------------------------------------------------------
| | Share | Unshare | SVM |H_SVM_INIT_DONE|
| |operation |operation | abort/ | |
| | | | terminate | |
-------------------------------------------------------------
| | | | | |
| Secure | Shared | Secure |Normal |Secure |
| | | | | |
| Shared | Shared | Secure |Normal |Shared |
| | | | | |
| Normal | Shared | Secure |Normal |Secure |
--------------------------------------------------------------
7. Life cycle of a VM
--------------------
--------------------------------------------------------------------
| | start | H_SVM_ |H_SVM_ |H_SVM_ |UV_SVM_ |
| | VM |INIT_START|INIT_DONE|INIT_ABORT |TERMINATE |
| | | | | | |
--------- ----------------------------------------------------------
| | | | | | |
| Normal | Normal | Transient|Error |Error |Normal |
| | | | | | |
| Secure | Error | Error |Error |Error |Normal |
| | | | | | |
|Transient| N/A | Error |Secure |Normal |Normal |
--------------------------------------------------------------------
************************************************************************
Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Page-merging of pages in memory-slots associated with a Secure VM
is disabled in H_SVM_PAGE_IN handler.
This operation should have been done the much earlier; the moment the VM
is initiated for secure-transition. Delaying this operation increases
the probability for those pages to acquire new references, making it
impossible to migrate those pages in H_SVM_PAGE_IN handler.
Disable page-migration in H_SVM_INIT_START handling.
Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Without this fix, git is confused. It generates wrong
function context for code changes in subsequent patches.
Weird, but true.
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Note: compat variant of REGSET_TM_CGPR is almost certainly wrong;
it claims to be 48*64bit, but just as compat REGSET_GPR it stores
44*32bit of (truncated) registers + 4 32bit zeros... followed by
48 more 32bit zeroes. Might be too late to change - it's a userland
ABI, after all ;-/
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
all uses are conditional upon ELF_CORE_COPY_XFPREGS, which has not
been defined on any architecture since 2010
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
skiroot_defconfig fails:
arch/powerpc/kernel/fadump.c:48:17: error: ‘cpus_in_fadump’ defined but not used
48 | static atomic_t cpus_in_fadump;
Fix it by moving the definition into the #ifdef where it's used.
Fixes: ba608c4fa12c ("powerpc/fadump: fix race between pstore write and fadump crash trigger")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200727070341.595634-1-mpe@ellerman.id.au
Commit 2f92447f9f96 ("powerpc/book3s64/hash: Use the pte_t address from the
caller") removed the local_irq_disable from hash_preload, but it was
required for more than just the page table walk: the hash pte busy bit is
effectively a lock which may be taken in interrupt context, and the local
update flag test must not be preempted before it's used.
This solves apparent lockups with perf interrupting __hash_page_64K. If
get_perf_callchain then also takes a hash fault on the same page while it
is already locked, it will loop forever taking hash faults, which looks like
this:
cpu 0x49e: Vector: 100 (System Reset) at [c00000001a4f7d70]
pc: c000000000072dc8: hash_page_mm+0x8/0x800
lr: c00000000000c5a4: do_hash_page+0x24/0x38
sp: c0002ac1cc69ac70
msr: 8000000000081033
current = 0xc0002ac1cc602e00
paca = 0xc00000001de1f280 irqmask: 0x03 irq_happened: 0x01
pid = 20118, comm = pread2_processe
Linux version 5.8.0-rc6-00345-g1fad14f18bc6
49e:mon> t
[c0002ac1cc69ac70] c00000000000c5a4 do_hash_page+0x24/0x38 (unreliable)
--- Exception: 300 (Data Access) at c00000000008fa60 __copy_tofrom_user_power7+0x20c/0x7ac
[link register ] c000000000335d10 copy_from_user_nofault+0xf0/0x150
[c0002ac1cc69af70] c00032bf9fa3c880 (unreliable)
[c0002ac1cc69afa0] c000000000109df0 read_user_stack_64+0x70/0xf0
[c0002ac1cc69afd0] c000000000109fcc perf_callchain_user_64+0x15c/0x410
[c0002ac1cc69b060] c000000000109c00 perf_callchain_user+0x20/0x40
[c0002ac1cc69b080] c00000000031c6cc get_perf_callchain+0x25c/0x360
[c0002ac1cc69b120] c000000000316b50 perf_callchain+0x70/0xa0
[c0002ac1cc69b140] c000000000316ddc perf_prepare_sample+0x25c/0x790
[c0002ac1cc69b1a0] c000000000317350 perf_event_output_forward+0x40/0xb0
[c0002ac1cc69b220] c000000000306138 __perf_event_overflow+0x88/0x1a0
[c0002ac1cc69b270] c00000000010cf70 record_and_restart+0x230/0x750
[c0002ac1cc69b620] c00000000010d69c perf_event_interrupt+0x20c/0x510
[c0002ac1cc69b730] c000000000027d9c performance_monitor_exception+0x4c/0x60
[c0002ac1cc69b750] c00000000000b2f8 performance_monitor_common_virt+0x1b8/0x1c0
--- Exception: f00 (Performance Monitor) at c0000000000cb5b0 pSeries_lpar_hpte_insert+0x0/0x160
[link register ] c0000000000846f0 __hash_page_64K+0x210/0x540
[c0002ac1cc69ba50] 0000000000000000 (unreliable)
[c0002ac1cc69bb00] c000000000073ae0 update_mmu_cache+0x390/0x3a0
[c0002ac1cc69bb70] c00000000037f024 wp_page_copy+0x364/0xce0
[c0002ac1cc69bc20] c00000000038272c do_wp_page+0xdc/0xa60
[c0002ac1cc69bc70] c0000000003857bc handle_mm_fault+0xb9c/0x1b60
[c0002ac1cc69bd50] c00000000006c434 __do_page_fault+0x314/0xc90
[c0002ac1cc69be20] c00000000000c5c8 handle_page_fault+0x10/0x2c
--- Exception: 300 (Data Access) at 00007fff8c861fe8
SP (7ffff6b19660) is in userspace
Fixes: 2f92447f9f96 ("powerpc/book3s64/hash: Use the pte_t address from the caller")
Reported-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Reported-by: Anton Blanchard <anton@ozlabs.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-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/20200727060947.10060-1-npiggin@gmail.com
In note_page(), the pg_state is updated the same way in two places.
Add note_page_update_state() to do it.
Also include the display of boundary markers there as it is missing
"no level" leg, leading to a mismatch when the first two markers
are at the same address and the first displayed area uses that
address.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/a284a809f01c705bbaab303b06fda216f147a99a.1593429426.git.christophe.leroy@csgroup.eu
When STRICT_KERNEL_RWX is set, we want to set NX bit on vmalloc
segments. But modules require exec.
Use a dedicated segment for modules. There is not much space
above kernel, and we don't waste vmalloc space to do alignment.
Therefore, we take the segment before PAGE_OFFSET for modules.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/eb8faba9148b6cf17c696ba776b4e8ee2f6313bf.1593428200.git.christophe.leroy@csgroup.eu
User space stops at TASK_SIZE. At the moment, kernel space starts
at PAGE_OFFSET.
In order to use space between TASK_SIZE and PAGE_OFFSET for modules,
make TASK_SIZE the limit between user and kernel space.
Note that fault.c already considers TASK_SIZE as the boundary between
user and kernel space.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/b38b52cd8dabbb56fbd6f9219d6f3cdccbb43b44.1593428200.git.christophe.leroy@csgroup.eu
In order to allow allocation of modules outside of vmalloc space,
use MODULES_VADDR and MODULES_END when MODULES_VADDR is defined.
Redefine module_alloc() when MODULES_VADDR defined.
Unmap corresponding KASAN shadow memory.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/7ecf5fff1eef67d450e73fc412b6ec3818483d75.1593428200.git.christophe.leroy@csgroup.eu
The sparse tool complains as follows:
arch/powerpc/platforms/pseries/papr_scm.c:97:1: warning:
symbol 'papr_nd_regions' was not declared. Should it be static?
arch/powerpc/platforms/pseries/papr_scm.c:98:1: warning:
symbol 'papr_ndr_lock' was not declared. Should it be static?
Those variables are not used outside of papr_scm.c, so this
commit marks them static.
Fixes: 85343a8da2d9 ("powerpc/papr/scm: Add bad memory ranges to nvdimm bad ranges")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200725091949.75234-1-weiyongjun1@huawei.com
Clang's objdump emits slightly different output from GNU's objdump,
causing a list of warnings to be emitted during relocatable builds.
E.g., clang's objdump emits this:
c000000000000004: 2c 00 00 48 b 0xc000000000000030
...
c000000000005c6c: 10 00 82 40 bf 2, 0xc000000000005c7c
while GNU objdump emits:
c000000000000004: 2c 00 00 48 b c000000000000030 <__start+0x30>
...
c000000000005c6c: 10 00 82 40 bne c000000000005c7c <masked_interrupt+0x3c>
Adjust llvm-objdump's output to remove the extraneous '0x' and convert
'bf' and 'bt' to 'bne' and 'beq' resp. to more closely match GNU
objdump's output.
Note that clang's objdump doesn't yet output the relocation symbols on
PPC.
Signed-off-by: Bill Wendling <morbo@google.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/191c67db31264b69cf6b566fd69851beb3dd0abb.1595630874.git.morbo@google.com
This implements smp_cond_load_relaxed() with the slowpath busy loop
using the preferred SMT priority pattern.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Waiman Long <longman@redhat.com>
[mpe: Make it 64-bit only to fix build errors on 32-bit]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200724131423.1362108-7-npiggin@gmail.com
This brings the behaviour of the uncontended fast path back to roughly
equivalent to simple spinlocks -- a single atomic op with lock hint.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Waiman Long <longman@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200724131423.1362108-6-npiggin@gmail.com
This implements the generic paravirt qspinlocks using H_PROD and
H_CONFER to kick and wait.
This uses an un-directed yield to any CPU rather than the directed
yield to a pre-empted lock holder that paravirtualised simple
spinlocks use, that requires no kick hcall. This is something that
could be investigated and improved in future.
Performance results can be found in the commit which added queued
spinlocks.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200724131423.1362108-5-npiggin@gmail.com
These have shown significantly improved performance and fairness when
spinlock contention is moderate to high on very large systems.
With this series including subsequent patches, on a 16 socket 1536
thread POWER9, a stress test such as same-file open/close from all
CPUs gets big speedups, 11620op/s aggregate with simple spinlocks vs
384158op/s (33x faster), where the difference in throughput between
the fastest and slowest thread goes from 7x to 1.4x.
Thanks to the fast path being identical in terms of atomics and
barriers (after a subsequent optimisation patch), single threaded
performance is not changed (no measurable difference).
On smaller systems, performance and fairness seems to be generally
improved. Using dbench on tmpfs as a test (that starts to run into
kernel spinlock contention), a 2-socket OpenPOWER POWER9 system was
tested with bare metal and KVM guest configurations. Results can be
found here:
https://github.com/linuxppc/issues/issues/305#issuecomment-663487453
Observations are:
- Queued spinlocks are equal when contention is insignificant, as
expected and as measured with microbenchmarks.
- When there is contention, on bare metal queued spinlocks have better
throughput and max latency at all points.
- When virtualised, queued spinlocks are slightly worse approaching
peak throughput, but significantly better throughput and max latency
at all points beyond peak, until queued spinlock maximum latency
rises when clients are 2x vCPUs.
The regressions haven't been analysed very well yet, there are a lot
of things that can be tuned, particularly the paravirtualised locking,
but the numbers already look like a good net win even on relatively
small systems.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200724131423.1362108-4-npiggin@gmail.com
