* Re: [PATCH 04/13] module: use RCU to synchronize find_module
From: Thiago Jung Bauermann @ 2021-01-29 21:29 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Petr Mladek, Jiri Kosina, Andrew Donnellan, linux-kbuild,
David Airlie, Masahiro Yamada, Josh Poimboeuf, Maarten Lankhorst,
linux-kernel, Maxime Ripard, live-patching, Michal Marek,
Joe Lawrence, dri-devel, Thomas Zimmermann, Jessica Yu,
Frederic Barrat, Daniel Vetter, Miroslav Benes, linuxppc-dev
In-Reply-To: <20210129051012.GA2053@lst.de>
Christoph Hellwig <hch@lst.de> writes:
> On Thu, Jan 28, 2021 at 05:50:56PM -0300, Thiago Jung Bauermann wrote:
>> > struct module *find_module(const char *name)
>> > {
>> > - module_assert_mutex();
>>
>> Does it make sense to replace the assert above with the warn below (untested)?
>>
>> RCU_LOCKDEP_WARN(rcu_read_lock_sched_held());
>
> One caller actually holds module_mutex still. And find_module_all,
> which implements the actual logic already asserts that either
> module_mutex is held or rcu_read_lock, so I don't tink we need an
> extra one here.
Ok, thanks for the clarification.
--
Thiago Jung Bauermann
IBM Linux Technology Center
^ permalink raw reply
* Re: [PATCH] powerpc: remove unneeded semicolons
From: Chengyang Fan @ 2021-01-30 1:31 UTC (permalink / raw)
To: Michael Ellerman; +Cc: joe, linuxppc-dev
In-Reply-To: <87v9bgc6al.fsf@mpe.ellerman.id.au>
Although they are harmless, I think we should keep the consistency of
kernel coding style.
Thanks
On 2021/1/29 19:48, Michael Ellerman wrote:
> Chengyang Fan <cy.fan@huawei.com> writes:
>> Remove superfluous semicolons after function definitions.
> Is there a good reason why?
>
> I realise they're superfluous, but they're also harmless as far as I'm
> aware.
>
> cheers
>
>> arch/powerpc/include/asm/book3s/32/mmu-hash.h | 2 +-
>> arch/powerpc/include/asm/book3s/64/mmu.h | 2 +-
>> arch/powerpc/include/asm/book3s/64/tlbflush-radix.h | 2 +-
>> arch/powerpc/include/asm/book3s/64/tlbflush.h | 2 +-
>> arch/powerpc/include/asm/firmware.h | 2 +-
>> arch/powerpc/include/asm/kvm_ppc.h | 6 +++---
>> arch/powerpc/include/asm/paca.h | 6 +++---
>> arch/powerpc/include/asm/rtas.h | 2 +-
>> arch/powerpc/include/asm/setup.h | 6 +++---
>> arch/powerpc/include/asm/simple_spinlock.h | 4 ++--
>> arch/powerpc/include/asm/smp.h | 2 +-
>> arch/powerpc/include/asm/xmon.h | 4 ++--
>> arch/powerpc/kernel/prom.c | 2 +-
>> arch/powerpc/kernel/setup.h | 12 ++++++------
>> arch/powerpc/platforms/powernv/subcore.h | 2 +-
>> arch/powerpc/platforms/pseries/pseries.h | 2 +-
>> 16 files changed, 29 insertions(+), 29 deletions(-)
> .
^ permalink raw reply
* [PATCH] powerpc64/idle: Fix SP offsets when saving GPRs
From: Christopher M. Riedl @ 2021-01-30 3:04 UTC (permalink / raw)
To: linuxppc-dev
The idle entry/exit code saves/restores GPRs in the stack "red zone"
(Protected Zone according to PowerPC64 ELF ABI v2). However, the offset
used for the first GPR is incorrect and overwrites the back chain - the
Protected Zone actually starts below the current SP. In practice this is
probably not an issue, but it's still incorrect so fix it.
Signed-off-by: Christopher M. Riedl <cmr@codefail.de>
---
arch/powerpc/kernel/idle_book3s.S | 126 +++++++++++++++---------------
1 file changed, 63 insertions(+), 63 deletions(-)
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 22f249b6f58d..80cf35183e9d 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -53,27 +53,27 @@ _GLOBAL(isa300_idle_stop_mayloss)
mflr r4
mfcr r5
/* use stack red zone rather than a new frame for saving regs */
- std r2,-8*0(r1)
- std r14,-8*1(r1)
- std r15,-8*2(r1)
- std r16,-8*3(r1)
- std r17,-8*4(r1)
- std r18,-8*5(r1)
- std r19,-8*6(r1)
- std r20,-8*7(r1)
- std r21,-8*8(r1)
- std r22,-8*9(r1)
- std r23,-8*10(r1)
- std r24,-8*11(r1)
- std r25,-8*12(r1)
- std r26,-8*13(r1)
- std r27,-8*14(r1)
- std r28,-8*15(r1)
- std r29,-8*16(r1)
- std r30,-8*17(r1)
- std r31,-8*18(r1)
- std r4,-8*19(r1)
- std r5,-8*20(r1)
+ std r2,-8*1(r1)
+ std r14,-8*2(r1)
+ std r15,-8*3(r1)
+ std r16,-8*4(r1)
+ std r17,-8*5(r1)
+ std r18,-8*6(r1)
+ std r19,-8*7(r1)
+ std r20,-8*8(r1)
+ std r21,-8*9(r1)
+ std r22,-8*10(r1)
+ std r23,-8*11(r1)
+ std r24,-8*12(r1)
+ std r25,-8*13(r1)
+ std r26,-8*14(r1)
+ std r27,-8*15(r1)
+ std r28,-8*16(r1)
+ std r29,-8*17(r1)
+ std r30,-8*18(r1)
+ std r31,-8*19(r1)
+ std r4,-8*20(r1)
+ std r5,-8*21(r1)
/* 168 bytes */
PPC_STOP
b . /* catch bugs */
@@ -89,8 +89,8 @@ _GLOBAL(isa300_idle_stop_mayloss)
*/
_GLOBAL(idle_return_gpr_loss)
ld r1,PACAR1(r13)
- ld r4,-8*19(r1)
- ld r5,-8*20(r1)
+ ld r4,-8*20(r1)
+ ld r5,-8*21(r1)
mtlr r4
mtcr r5
/*
@@ -98,25 +98,25 @@ _GLOBAL(idle_return_gpr_loss)
* from PACATOC. This could be avoided for that less common case
* if KVM saved its r2.
*/
- ld r2,-8*0(r1)
- ld r14,-8*1(r1)
- ld r15,-8*2(r1)
- ld r16,-8*3(r1)
- ld r17,-8*4(r1)
- ld r18,-8*5(r1)
- ld r19,-8*6(r1)
- ld r20,-8*7(r1)
- ld r21,-8*8(r1)
- ld r22,-8*9(r1)
- ld r23,-8*10(r1)
- ld r24,-8*11(r1)
- ld r25,-8*12(r1)
- ld r26,-8*13(r1)
- ld r27,-8*14(r1)
- ld r28,-8*15(r1)
- ld r29,-8*16(r1)
- ld r30,-8*17(r1)
- ld r31,-8*18(r1)
+ ld r2,-8*1(r1)
+ ld r14,-8*2(r1)
+ ld r15,-8*3(r1)
+ ld r16,-8*4(r1)
+ ld r17,-8*5(r1)
+ ld r18,-8*6(r1)
+ ld r19,-8*7(r1)
+ ld r20,-8*8(r1)
+ ld r21,-8*9(r1)
+ ld r22,-8*10(r1)
+ ld r23,-8*11(r1)
+ ld r24,-8*12(r1)
+ ld r25,-8*13(r1)
+ ld r26,-8*14(r1)
+ ld r27,-8*15(r1)
+ ld r28,-8*16(r1)
+ ld r29,-8*17(r1)
+ ld r30,-8*18(r1)
+ ld r31,-8*19(r1)
blr
/*
@@ -155,27 +155,27 @@ _GLOBAL(isa206_idle_insn_mayloss)
mflr r4
mfcr r5
/* use stack red zone rather than a new frame for saving regs */
- std r2,-8*0(r1)
- std r14,-8*1(r1)
- std r15,-8*2(r1)
- std r16,-8*3(r1)
- std r17,-8*4(r1)
- std r18,-8*5(r1)
- std r19,-8*6(r1)
- std r20,-8*7(r1)
- std r21,-8*8(r1)
- std r22,-8*9(r1)
- std r23,-8*10(r1)
- std r24,-8*11(r1)
- std r25,-8*12(r1)
- std r26,-8*13(r1)
- std r27,-8*14(r1)
- std r28,-8*15(r1)
- std r29,-8*16(r1)
- std r30,-8*17(r1)
- std r31,-8*18(r1)
- std r4,-8*19(r1)
- std r5,-8*20(r1)
+ std r2,-8*1(r1)
+ std r14,-8*2(r1)
+ std r15,-8*3(r1)
+ std r16,-8*4(r1)
+ std r17,-8*5(r1)
+ std r18,-8*6(r1)
+ std r19,-8*7(r1)
+ std r20,-8*8(r1)
+ std r21,-8*9(r1)
+ std r22,-8*10(r1)
+ std r23,-8*11(r1)
+ std r24,-8*12(r1)
+ std r25,-8*13(r1)
+ std r26,-8*14(r1)
+ std r27,-8*15(r1)
+ std r28,-8*16(r1)
+ std r29,-8*17(r1)
+ std r30,-8*18(r1)
+ std r31,-8*19(r1)
+ std r4,-8*20(r1)
+ std r5,-8*21(r1)
cmpwi r3,PNV_THREAD_NAP
bne 1f
IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP)
--
2.26.1
^ permalink raw reply related
* Re: [PATCH] powerpc/fault: fix wrong KUAP fault for IO_URING
From: Michael Ellerman @ 2021-01-30 11:22 UTC (permalink / raw)
To: Christophe Leroy, Zorro Lang, Aneesh Kumar K.V
Cc: Jens Axboe, linuxppc-dev, Nicholas Piggin
In-Reply-To: <18dd441b-440a-fe95-0907-d8cec5b49410@csgroup.eu>
Christophe Leroy <christophe.leroy@csgroup.eu> writes:
> +Aneesh
>
> Le 29/01/2021 à 07:52, Zorro Lang a écrit :
..
>> [ 96.200296] ------------[ cut here ]------------
>> [ 96.200304] Bug: Read fault blocked by KUAP!
>> [ 96.200309] WARNING: CPU: 3 PID: 1876 at arch/powerpc/mm/fault.c:229 bad_kernel_fault+0x180/0x310
>
>> [ 96.200734] NIP [c000000000849424] fault_in_pages_readable+0x104/0x350
>> [ 96.200741] LR [c00000000084952c] fault_in_pages_readable+0x20c/0x350
>> [ 96.200747] --- interrupt: 300
>
>
> Problem happens in a section where userspace access is supposed to be granted, so the patch you
> proposed is definitely not the right fix.
>
> c000000000849408: 2c 01 00 4c isync
> c00000000084940c: a6 03 3d 7d mtspr 29,r9 <== granting userspace access permission
> c000000000849410: 2c 01 00 4c isync
> c000000000849414: 00 00 36 e9 ld r9,0(r22)
> c000000000849418: 20 00 29 81 lwz r9,32(r9)
> c00000000084941c: 00 02 29 71 andi. r9,r9,512
> c000000000849420: 78 d3 5e 7f mr r30,r26
> ==> c000000000849424: 00 00 bf 8b lbz r29,0(r31) <== accessing userspace
> c000000000849428: 10 00 82 41 beq c000000000849438 <fault_in_pages_readable+0x118>
> c00000000084942c: 2c 01 00 4c isync
> c000000000849430: a6 03 bd 7e mtspr 29,r21 <== clearing userspace access permission
> c000000000849434: 2c 01 00 4c isync
>
> My first guess is that the problem is linked to the following function, see the comment
>
> /*
> * For kernel thread that doesn't have thread.regs return
> * default AMR/IAMR values.
> */
> static inline u64 current_thread_amr(void)
> {
> if (current->thread.regs)
> return current->thread.regs->amr;
> return AMR_KUAP_BLOCKED;
> }
>
> Above function was introduced by commit 48a8ab4eeb82 ("powerpc/book3s64/pkeys: Don't update SPRN_AMR
> when in kernel mode")
Yeah that's a bit of a curly one.
At some point io_uring did kthread_use_mm(), which is supposed to mean
the kthread can operate on behalf of the original process that submitted
the IO.
But because KUAP is implemented using memory protection keys, it depends
on the value of the AMR register, which is not part of the mm, it's in
thread.regs->amr.
And what's worse by the time we're in kthread_use_mm() we no longer have
access to the thread.regs->amr of the original process that submitted
the IO.
We also can't simply move the AMR into the mm, precisely because it's
per thread, not per mm.
So TBH I don't know how we're going to fix this.
I guess we could return AMR=unblocked for kernel threads, but that's
arguably a bug because it allows a process to circumvent memory keys by
asking the kernel to do the access.
cheers
^ permalink raw reply
* Re: [PATCH] powerpc64/idle: Fix SP offsets when saving GPRs
From: Michael Ellerman @ 2021-01-30 11:32 UTC (permalink / raw)
To: Christopher M. Riedl, linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210130030430.11369-1-cmr@codefail.de>
"Christopher M. Riedl" <cmr@codefail.de> writes:
> The idle entry/exit code saves/restores GPRs in the stack "red zone"
> (Protected Zone according to PowerPC64 ELF ABI v2). However, the offset
> used for the first GPR is incorrect and overwrites the back chain - the
> Protected Zone actually starts below the current SP. In practice this is
> probably not an issue, but it's still incorrect so fix it.
Nice catch.
Corrupting the back chain means you can't backtrace from there, which
could be confusing for debugging one day.
It does make me wonder why we don't just create a stack frame and use
the normal macros? It would use a bit more stack space, but we shouldn't
be short of stack space when going idle.
Nick, was there a particular reason for using the red zone?
cheers
> diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
> index 22f249b6f58d..80cf35183e9d 100644
> --- a/arch/powerpc/kernel/idle_book3s.S
> +++ b/arch/powerpc/kernel/idle_book3s.S
> @@ -53,27 +53,27 @@ _GLOBAL(isa300_idle_stop_mayloss)
> mflr r4
> mfcr r5
> /* use stack red zone rather than a new frame for saving regs */
> - std r2,-8*0(r1)
> - std r14,-8*1(r1)
> - std r15,-8*2(r1)
> - std r16,-8*3(r1)
> - std r17,-8*4(r1)
> - std r18,-8*5(r1)
> - std r19,-8*6(r1)
> - std r20,-8*7(r1)
> - std r21,-8*8(r1)
> - std r22,-8*9(r1)
> - std r23,-8*10(r1)
> - std r24,-8*11(r1)
> - std r25,-8*12(r1)
> - std r26,-8*13(r1)
> - std r27,-8*14(r1)
> - std r28,-8*15(r1)
> - std r29,-8*16(r1)
> - std r30,-8*17(r1)
> - std r31,-8*18(r1)
> - std r4,-8*19(r1)
> - std r5,-8*20(r1)
> + std r2,-8*1(r1)
> + std r14,-8*2(r1)
> + std r15,-8*3(r1)
> + std r16,-8*4(r1)
> + std r17,-8*5(r1)
> + std r18,-8*6(r1)
> + std r19,-8*7(r1)
> + std r20,-8*8(r1)
> + std r21,-8*9(r1)
> + std r22,-8*10(r1)
> + std r23,-8*11(r1)
> + std r24,-8*12(r1)
> + std r25,-8*13(r1)
> + std r26,-8*14(r1)
> + std r27,-8*15(r1)
> + std r28,-8*16(r1)
> + std r29,-8*17(r1)
> + std r30,-8*18(r1)
> + std r31,-8*19(r1)
> + std r4,-8*20(r1)
> + std r5,-8*21(r1)
> /* 168 bytes */
> PPC_STOP
> b . /* catch bugs */
> @@ -89,8 +89,8 @@ _GLOBAL(isa300_idle_stop_mayloss)
> */
> _GLOBAL(idle_return_gpr_loss)
> ld r1,PACAR1(r13)
> - ld r4,-8*19(r1)
> - ld r5,-8*20(r1)
> + ld r4,-8*20(r1)
> + ld r5,-8*21(r1)
> mtlr r4
> mtcr r5
> /*
> @@ -98,25 +98,25 @@ _GLOBAL(idle_return_gpr_loss)
> * from PACATOC. This could be avoided for that less common case
> * if KVM saved its r2.
> */
> - ld r2,-8*0(r1)
> - ld r14,-8*1(r1)
> - ld r15,-8*2(r1)
> - ld r16,-8*3(r1)
> - ld r17,-8*4(r1)
> - ld r18,-8*5(r1)
> - ld r19,-8*6(r1)
> - ld r20,-8*7(r1)
> - ld r21,-8*8(r1)
> - ld r22,-8*9(r1)
> - ld r23,-8*10(r1)
> - ld r24,-8*11(r1)
> - ld r25,-8*12(r1)
> - ld r26,-8*13(r1)
> - ld r27,-8*14(r1)
> - ld r28,-8*15(r1)
> - ld r29,-8*16(r1)
> - ld r30,-8*17(r1)
> - ld r31,-8*18(r1)
> + ld r2,-8*1(r1)
> + ld r14,-8*2(r1)
> + ld r15,-8*3(r1)
> + ld r16,-8*4(r1)
> + ld r17,-8*5(r1)
> + ld r18,-8*6(r1)
> + ld r19,-8*7(r1)
> + ld r20,-8*8(r1)
> + ld r21,-8*9(r1)
> + ld r22,-8*10(r1)
> + ld r23,-8*11(r1)
> + ld r24,-8*12(r1)
> + ld r25,-8*13(r1)
> + ld r26,-8*14(r1)
> + ld r27,-8*15(r1)
> + ld r28,-8*16(r1)
> + ld r29,-8*17(r1)
> + ld r30,-8*18(r1)
> + ld r31,-8*19(r1)
> blr
>
> /*
> @@ -155,27 +155,27 @@ _GLOBAL(isa206_idle_insn_mayloss)
> mflr r4
> mfcr r5
> /* use stack red zone rather than a new frame for saving regs */
> - std r2,-8*0(r1)
> - std r14,-8*1(r1)
> - std r15,-8*2(r1)
> - std r16,-8*3(r1)
> - std r17,-8*4(r1)
> - std r18,-8*5(r1)
> - std r19,-8*6(r1)
> - std r20,-8*7(r1)
> - std r21,-8*8(r1)
> - std r22,-8*9(r1)
> - std r23,-8*10(r1)
> - std r24,-8*11(r1)
> - std r25,-8*12(r1)
> - std r26,-8*13(r1)
> - std r27,-8*14(r1)
> - std r28,-8*15(r1)
> - std r29,-8*16(r1)
> - std r30,-8*17(r1)
> - std r31,-8*18(r1)
> - std r4,-8*19(r1)
> - std r5,-8*20(r1)
> + std r2,-8*1(r1)
> + std r14,-8*2(r1)
> + std r15,-8*3(r1)
> + std r16,-8*4(r1)
> + std r17,-8*5(r1)
> + std r18,-8*6(r1)
> + std r19,-8*7(r1)
> + std r20,-8*8(r1)
> + std r21,-8*9(r1)
> + std r22,-8*10(r1)
> + std r23,-8*11(r1)
> + std r24,-8*12(r1)
> + std r25,-8*13(r1)
> + std r26,-8*14(r1)
> + std r27,-8*15(r1)
> + std r28,-8*16(r1)
> + std r29,-8*17(r1)
> + std r30,-8*18(r1)
> + std r31,-8*19(r1)
> + std r4,-8*20(r1)
> + std r5,-8*21(r1)
> cmpwi r3,PNV_THREAD_NAP
> bne 1f
> IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP)
> --
> 2.26.1
^ permalink raw reply
* [PATCH v7 00/42] powerpc: interrupt wrappers
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
This adds interrupt handler wrapper functions, similar to the
generic / x86 code, and moves several common operations into them
from either asm or open coded in the individual handlers.
This series is based on powerpc fixes-test tree, there's another
unrelated pending fix in patch 1 of the series which clashes a
bit.
This includes more changes and fixes suggested by Christophe,
a few minor bug fixes and compile fix noticed by kbuild, and
some NMI changes Athira asked about -- PMI interrupts don't
block tracing when they are soft-NMI.
Since v1:
- Fixed a couple of compile issues
- Fixed perf weirdness (sometimes NMI, sometimes not)
- Also move irq_enter/exit into wrappers
Since v2:
- Rebased upstream
- Took code in patch 3 from Christophe
- Fixed some compile errors from 0day
Since v3:
- Rebased
- Split Christophe's 32s DABR patch into its own patch
- Fixed missing asm from 32s on patch 3 noticed by Christophe.
- Moved changes around, split out one more patch (patch 9) to make
changes more logical and atomic.
- Add comments explaining _RAW handlers (SLB, HPTE) interrupts better
Since v4:
- Rebased (on top of scv fallback flush fix)
- Rearranged a few changes into different patches from Christophe,
e.g., the ___do_page_fault change from patch 2 to 10. I didn't
do everything (e.g., splitting to update __hash_page to drop the
msr argument before the bulk of patch 2 seemed like churn without
much improvement), and also other things like removing the new
___do_page_fault variant if we can change hash fault context tracking
I didn't get time to completely investigate and implement. I think
this shouldn't be a showstopper though we can make more improvements
as we go.
Since v5:
- Lots of good review suggestions from Christophe, see v5 email threads.
- Major change being do_break is left in asm and selected early as an
alternate interrupt handler now, which is a smaller step and matches
other subarchs better.
- Rearranged patches, split, moved things, bug fixes, etc.
- Converted a few more missed exception handlers for debug and ras
Since v6:
- Move related interrupt handler de-argify patches together [Christophe]
- Split do_bad_page_fault patch [Christophe]
- Change do_page_fault cleanup patch [Christophe]
- entry_32.S can't avoid saving r4/r5 until later in the series [Christophe]
- Soft-NMI decrementer and perf don't block ftrace [Athira]
- Rebased on some fixes
- Fixed mismerge / duplicate line in patch 40
- Fix kbuild hash missing declaration bug
Christophe Leroy (1):
powerpc/32s: move DABR match out of handle_page_fault
Nicholas Piggin (41):
powerpc/64s: interrupt exit improve bounding of interrupt recursion
KVM: PPC: Book3S HV: Context tracking exit guest context before
enabling irqs
powerpc/64s: move DABR match out of handle_page_fault
powerpc/64s: move the hash fault handling logic to C
powerpc: remove arguments from fault handler functions
powerpc/fsl_booke/32: CacheLockingException remove args
powerpc: do_break get registers from regs
powerpc: DebugException remove args
powerpc/32: transfer can avoid saving r4/r5 over trace call
powerpc: bad_page_fault get registers from regs
powerpc/64s: add do_bad_page_fault_segv handler
powerpc: rearrange do_page_fault error case to be inside
exception_enter
powerpc/64s: move bad_page_fault handling to C
powerpc/64s: split do_hash_fault
powerpc/mm: Remove stale do_page_fault comment referring to SLB faults
powerpc/64s: slb comment update
powerpc/traps: add NOKPROBE_SYMBOL for sreset and mce
powerpc/perf: move perf irq/nmi handling details into traps.c
powerpc/time: move timer_broadcast_interrupt prototype to asm/time.h
powerpc: add and use unknown_async_exception
powerpc/cell: tidy up pervasive declarations
powerpc: introduce die_mce
powerpc/mce: ensure machine check handler always tests RI
powerpc: improve handling of unrecoverable system reset
powerpc: interrupt handler wrapper functions
powerpc: add interrupt wrapper entry / exit stub functions
powerpc: convert interrupt handlers to use wrappers
powerpc: add interrupt_cond_local_irq_enable helper
powerpc/64: context tracking remove _TIF_NOHZ
powerpc/64s/hash: improve context tracking of hash faults
powerpc/64: context tracking move to interrupt wrappers
powerpc/64: add context tracking to asynchronous interrupts
powerpc: handle irq_enter/irq_exit in interrupt handler wrappers
powerpc/64s: move context tracking exit to interrupt exit path
powerpc/64s: reconcile interrupts in C
powerpc/64: move account_stolen_time into its own function
powerpc/64: entry cpu time accounting in C
powerpc: move NMI entry/exit code into wrapper
powerpc/64s: move NMI soft-mask handling to C
powerpc/64s: runlatch interrupt handling in C
powerpc/64s: power4 nap fixup in C
arch/powerpc/Kconfig | 1 -
arch/powerpc/include/asm/asm-prototypes.h | 29 --
arch/powerpc/include/asm/bug.h | 9 +-
arch/powerpc/include/asm/cputime.h | 14 +
arch/powerpc/include/asm/debug.h | 4 -
arch/powerpc/include/asm/hw_irq.h | 9 -
arch/powerpc/include/asm/interrupt.h | 437 +++++++++++++++++++++
arch/powerpc/include/asm/ppc_asm.h | 24 --
arch/powerpc/include/asm/processor.h | 1 +
arch/powerpc/include/asm/thread_info.h | 10 +-
arch/powerpc/include/asm/time.h | 2 +
arch/powerpc/kernel/dbell.c | 9 +-
arch/powerpc/kernel/entry_32.S | 25 +-
arch/powerpc/kernel/exceptions-64e.S | 8 +-
arch/powerpc/kernel/exceptions-64s.S | 310 ++-------------
arch/powerpc/kernel/head_40x.S | 11 +-
arch/powerpc/kernel/head_8xx.S | 11 +-
arch/powerpc/kernel/head_book3s_32.S | 14 +-
arch/powerpc/kernel/head_booke.h | 6 +-
arch/powerpc/kernel/head_fsl_booke.S | 6 +-
arch/powerpc/kernel/idle_book3s.S | 4 +
arch/powerpc/kernel/irq.c | 7 +-
arch/powerpc/kernel/mce.c | 16 +-
arch/powerpc/kernel/process.c | 8 +-
arch/powerpc/kernel/ptrace/ptrace.c | 4 -
arch/powerpc/kernel/signal.c | 4 -
arch/powerpc/kernel/syscall_64.c | 90 +++--
arch/powerpc/kernel/tau_6xx.c | 5 +-
arch/powerpc/kernel/time.c | 7 +-
arch/powerpc/kernel/traps.c | 265 ++++++-------
arch/powerpc/kernel/watchdog.c | 15 +-
arch/powerpc/kvm/book3s_hv.c | 7 +-
arch/powerpc/kvm/book3s_hv_builtin.c | 1 +
arch/powerpc/kvm/booke.c | 1 +
arch/powerpc/mm/book3s64/hash_utils.c | 97 +++--
arch/powerpc/mm/book3s64/slb.c | 40 +-
arch/powerpc/mm/fault.c | 76 ++--
arch/powerpc/perf/core-book3s.c | 35 +-
arch/powerpc/perf/core-fsl-emb.c | 25 --
arch/powerpc/platforms/8xx/machine_check.c | 2 +-
arch/powerpc/platforms/cell/pervasive.c | 1 +
arch/powerpc/platforms/cell/pervasive.h | 3 -
arch/powerpc/platforms/cell/ras.c | 6 +-
arch/powerpc/platforms/cell/ras.h | 9 +-
arch/powerpc/platforms/powernv/idle.c | 1 +
arch/powerpc/platforms/powernv/opal.c | 2 +-
arch/powerpc/platforms/pseries/ras.c | 2 +-
47 files changed, 914 insertions(+), 759 deletions(-)
create mode 100644 arch/powerpc/include/asm/interrupt.h
--
2.23.0
^ permalink raw reply
* [PATCH v7 01/42] powerpc/64s: interrupt exit improve bounding of interrupt recursion
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
When replaying pending soft-masked interrupts when an interrupt returns
to an irqs-enabled context, there is a special case required if this was
an asynchronous interrupt to avoid unbounded interrupt recursion.
This case was not tested for in the case the asynchronous interrupt hit
in user context, because a subsequent nested interrupt would by definition
hit in kernel mode, which then exits via the kernel path which does test
this case.
There is no reason to allow this for such interrupts. While recursion is
bounded at the next level, it's simpler and uses less stack to apply the
replay logic consistently.
This also expands the comment which was really pretty poor and didn't
explain the problem (I can say that because I wrote it).
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/syscall_64.c | 55 +++++++++++++++++++-------------
1 file changed, 33 insertions(+), 22 deletions(-)
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 7c85ed04a164..e0eb2a502db3 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -138,8 +138,12 @@ notrace long system_call_exception(long r3, long r4, long r5,
/*
* local irqs must be disabled. Returns false if the caller must re-enable
* them, check for new work, and try again.
+ *
+ * This should be called with local irqs disabled, but if they were previously
+ * enabled when the interrupt handler returns (indicating a process-context /
+ * synchronous interrupt) then irqs_enabled should be true.
*/
-static notrace inline bool prep_irq_for_enabled_exit(bool clear_ri)
+static notrace inline bool prep_irq_for_enabled_exit(bool clear_ri, bool irqs_enabled)
{
/* This must be done with RI=1 because tracing may touch vmaps */
trace_hardirqs_on();
@@ -156,6 +160,29 @@ static notrace inline bool prep_irq_for_enabled_exit(bool clear_ri)
trace_hardirqs_off();
local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+ /*
+ * Must replay pending soft-masked interrupts now. Don't just
+ * local_irq_enabe(); local_irq_disable(); because if we are
+ * returning from an asynchronous interrupt here, another one
+ * might hit after irqs are enabled, and it would exit via this
+ * same path allowing another to fire, and so on unbounded.
+ *
+ * If interrupts were enabled when this interrupt exited,
+ * indicating a process context (synchronous) interrupt,
+ * local_irq_enable/disable can be used, which will enable
+ * interrupts rather than keeping them masked (unclear how
+ * much benefit this is over just replaying for all cases,
+ * because we immediately disable again, so all we're really
+ * doing is allowing hard interrupts to execute directly for
+ * a very small time, rather than being masked and replayed).
+ */
+ if (irqs_enabled) {
+ local_irq_enable();
+ local_irq_disable();
+ } else {
+ replay_soft_interrupts();
+ }
+
return false;
}
local_paca->irq_happened = 0;
@@ -212,8 +239,9 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
ret |= _TIF_RESTOREALL;
}
-again:
local_irq_disable();
+
+again:
ti_flags = READ_ONCE(*ti_flagsp);
while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
local_irq_enable();
@@ -258,10 +286,8 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
}
/* scv need not set RI=0 because SRRs are not used */
- if (unlikely(!prep_irq_for_enabled_exit(!scv))) {
- local_irq_enable();
+ if (unlikely(!prep_irq_for_enabled_exit(!scv, true)))
goto again;
- }
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
local_paca->tm_scratch = regs->msr;
@@ -336,11 +362,8 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
}
}
- if (unlikely(!prep_irq_for_enabled_exit(true))) {
- local_irq_enable();
- local_irq_disable();
+ if (unlikely(!prep_irq_for_enabled_exit(true, !irqs_disabled_flags(flags))))
goto again;
- }
#ifdef CONFIG_PPC_BOOK3E
if (unlikely(ts->debug.dbcr0 & DBCR0_IDM)) {
@@ -403,20 +426,8 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
}
}
- if (unlikely(!prep_irq_for_enabled_exit(true))) {
- /*
- * Can't local_irq_restore to replay if we were in
- * interrupt context. Must replay directly.
- */
- if (irqs_disabled_flags(flags)) {
- replay_soft_interrupts();
- } else {
- local_irq_restore(flags);
- local_irq_save(flags);
- }
- /* Took an interrupt, may have more exit work to do. */
+ if (unlikely(!prep_irq_for_enabled_exit(true, !irqs_disabled_flags(flags))))
goto again;
- }
} else {
/* Returning to a kernel context with local irqs disabled. */
__hard_EE_RI_disable();
--
2.23.0
^ permalink raw reply related
* [PATCH v7 02/42] KVM: PPC: Book3S HV: Context tracking exit guest context before enabling irqs
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
Interrupts that occur in kernel mode expect that context tracking
is set to kernel. Enabling local irqs before context tracking
switches from guest to host means interrupts can come in and trigger
warnings about wrong context, and possibly worse.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6f612d240392..d348e77cee20 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3407,8 +3407,9 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
kvmppc_set_host_core(pcpu);
+ guest_exit_irqoff();
+
local_irq_enable();
- guest_exit();
/* Let secondaries go back to the offline loop */
for (i = 0; i < controlled_threads; ++i) {
@@ -4217,8 +4218,9 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
kvmppc_set_host_core(pcpu);
+ guest_exit_irqoff();
+
local_irq_enable();
- guest_exit();
cpumask_clear_cpu(pcpu, &kvm->arch.cpu_in_guest);
--
2.23.0
^ permalink raw reply related
* [PATCH v7 03/42] powerpc/32s: move DABR match out of handle_page_fault
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
From: Christophe Leroy <christophe.leroy@csgroup.eu>
handle_page_fault() has some code dedicated to book3s/32 to
call do_break() when the DSI is a DABR match.
On other platforms, do_break() is handled separately.
Do the same for book3s/32, do it earlier in the process of DSI.
This change also avoid doing the test on ISI.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/kernel/entry_32.S | 15 ---------------
arch/powerpc/kernel/head_book3s_32.S | 3 +++
2 files changed, 3 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 1c9b0ccc2172..238eacfda7b0 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -670,10 +670,6 @@ ppc_swapcontext:
.globl handle_page_fault
handle_page_fault:
addi r3,r1,STACK_FRAME_OVERHEAD
-#ifdef CONFIG_PPC_BOOK3S_32
- andis. r0,r5,DSISR_DABRMATCH@h
- bne- handle_dabr_fault
-#endif
bl do_page_fault
cmpwi r3,0
beq+ ret_from_except
@@ -687,17 +683,6 @@ handle_page_fault:
bl __bad_page_fault
b ret_from_except_full
-#ifdef CONFIG_PPC_BOOK3S_32
- /* We have a data breakpoint exception - handle it */
-handle_dabr_fault:
- SAVE_NVGPRS(r1)
- lwz r0,_TRAP(r1)
- clrrwi r0,r0,1
- stw r0,_TRAP(r1)
- bl do_break
- b ret_from_except_full
-#endif
-
/*
* This routine switches between two different tasks. The process
* state of one is saved on its kernel stack. Then the state
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 858fbc8b19f3..6d411b8fd5d3 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -689,7 +689,10 @@ handle_page_fault_tramp_1:
lwz r5, _DSISR(r11)
/* fall through */
handle_page_fault_tramp_2:
+ andis. r0, r5, DSISR_DABRMATCH@h
+ bne- 1f
EXC_XFER_LITE(0x300, handle_page_fault)
+1: EXC_XFER_STD(0x300, do_break)
#ifdef CONFIG_VMAP_STACK
.macro save_regs_thread thread
--
2.23.0
^ permalink raw reply related
* [PATCH v7 04/42] powerpc/64s: move DABR match out of handle_page_fault
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
Similar to the 32/s change, move the test and call to the do_break
handler to the DSI.
Suggested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64s.S | 34 +++++++++++++---------------
1 file changed, 16 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 6e53f7638737..a6333b986a57 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1439,6 +1439,8 @@ EXC_COMMON_BEGIN(data_access_common)
GEN_COMMON data_access
ld r4,_DAR(r1)
ld r5,_DSISR(r1)
+ andis. r0,r5,DSISR_DABRMATCH@h
+ bne- 1f
BEGIN_MMU_FTR_SECTION
ld r6,_MSR(r1)
li r3,0x300
@@ -1447,6 +1449,18 @@ MMU_FTR_SECTION_ELSE
b handle_page_fault
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+1: /* We have a data breakpoint exception - handle it */
+ ld r4,_DAR(r1)
+ ld r5,_DSISR(r1)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl do_break
+ /*
+ * do_break() may have changed the NV GPRS while handling a breakpoint.
+ * If so, we need to restore them with their updated values.
+ */
+ REST_NVGPRS(r1)
+ b interrupt_return
+
GEN_KVM data_access
@@ -3228,7 +3242,7 @@ disable_machine_check:
.balign IFETCH_ALIGN_BYTES
do_hash_page:
#ifdef CONFIG_PPC_BOOK3S_64
- lis r0,(DSISR_BAD_FAULT_64S | DSISR_DABRMATCH | DSISR_KEYFAULT)@h
+ lis r0,(DSISR_BAD_FAULT_64S | DSISR_KEYFAULT)@h
ori r0,r0,DSISR_BAD_FAULT_64S@l
and. r0,r5,r0 /* weird error? */
bne- handle_page_fault /* if not, try to insert a HPTE */
@@ -3262,15 +3276,13 @@ do_hash_page:
/* Error */
blt- 13f
- /* Reload DAR/DSISR into r4/r5 for the DABR check below */
+ /* Reload DAR/DSISR into r4/r5 for handle_page_fault */
ld r4,_DAR(r1)
ld r5,_DSISR(r1)
#endif /* CONFIG_PPC_BOOK3S_64 */
/* Here we have a page fault that hash_page can't handle. */
handle_page_fault:
-11: andis. r0,r5,DSISR_DABRMATCH@h
- bne- handle_dabr_fault
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_page_fault
cmpdi r3,0
@@ -3281,20 +3293,6 @@ handle_page_fault:
bl __bad_page_fault
b interrupt_return
-/* We have a data breakpoint exception - handle it */
-handle_dabr_fault:
- ld r4,_DAR(r1)
- ld r5,_DSISR(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_break
- /*
- * do_break() may have changed the NV GPRS while handling a breakpoint.
- * If so, we need to restore them with their updated values.
- */
- REST_NVGPRS(r1)
- b interrupt_return
-
-
#ifdef CONFIG_PPC_BOOK3S_64
/* We have a page fault that hash_page could handle but HV refused
* the PTE insertion
--
2.23.0
^ permalink raw reply related
* [PATCH v7 05/42] powerpc/64s: move the hash fault handling logic to C
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
The fault handling still has some complex logic particularly around
hash table handling, in asm. Implement most of this in C.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 1 +
arch/powerpc/kernel/exceptions-64s.S | 127 ++++--------------
arch/powerpc/mm/book3s64/hash_utils.c | 77 +++++++----
3 files changed, 78 insertions(+), 127 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 066b1d34c7bc..60a669379aa0 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -454,6 +454,7 @@ static inline unsigned long hpt_hash(unsigned long vpn,
#define HPTE_NOHPTE_UPDATE 0x2
#define HPTE_USE_KERNEL_KEY 0x4
+int do_hash_fault(struct pt_regs *regs, unsigned long ea, unsigned long dsisr);
extern int __hash_page_4K(unsigned long ea, unsigned long access,
unsigned long vsid, pte_t *ptep, unsigned long trap,
unsigned long flags, int ssize, int subpage_prot);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index a6333b986a57..07aba8af99d3 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1401,14 +1401,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
*
* Handling:
* - Hash MMU
- * Go to do_hash_page first to see if the HPT can be filled from an entry in
- * the Linux page table. Hash faults can hit in kernel mode in a fairly
+ * Go to do_hash_fault, which attempts to fill the HPT from an entry in the
+ * Linux page table. Hash faults can hit in kernel mode in a fairly
* arbitrary state (e.g., interrupts disabled, locks held) when accessing
* "non-bolted" regions, e.g., vmalloc space. However these should always be
- * backed by Linux page tables.
+ * backed by Linux page table entries.
*
- * If none is found, do a Linux page fault. Linux page faults can happen in
- * kernel mode due to user copy operations of course.
+ * If no entry is found the Linux page fault handler is invoked (by
+ * do_hash_fault). Linux page faults can happen in kernel mode due to user
+ * copy operations of course.
*
* KVM: The KVM HDSI handler may perform a load with MSR[DR]=1 in guest
* MMU context, which may cause a DSI in the host, which must go to the
@@ -1439,27 +1440,29 @@ EXC_COMMON_BEGIN(data_access_common)
GEN_COMMON data_access
ld r4,_DAR(r1)
ld r5,_DSISR(r1)
+ addi r3,r1,STACK_FRAME_OVERHEAD
andis. r0,r5,DSISR_DABRMATCH@h
bne- 1f
BEGIN_MMU_FTR_SECTION
- ld r6,_MSR(r1)
- li r3,0x300
- b do_hash_page /* Try to handle as hpte fault */
+ bl do_hash_fault
MMU_FTR_SECTION_ELSE
- b handle_page_fault
+ bl do_page_fault
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+ cmpdi r3,0
+ beq+ interrupt_return
+ mr r5,r3
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ ld r4,_DAR(r1)
+ bl __bad_page_fault
+ b interrupt_return
-1: /* We have a data breakpoint exception - handle it */
- ld r4,_DAR(r1)
- ld r5,_DSISR(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_break
+1: bl do_break
/*
* do_break() may have changed the NV GPRS while handling a breakpoint.
* If so, we need to restore them with their updated values.
*/
REST_NVGPRS(r1)
- b interrupt_return
+ b interrupt_return
GEN_KVM data_access
@@ -1554,13 +1557,19 @@ EXC_COMMON_BEGIN(instruction_access_common)
GEN_COMMON instruction_access
ld r4,_DAR(r1)
ld r5,_DSISR(r1)
+ addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
- ld r6,_MSR(r1)
- li r3,0x400
- b do_hash_page /* Try to handle as hpte fault */
+ bl do_hash_fault
MMU_FTR_SECTION_ELSE
- b handle_page_fault
+ bl do_page_fault
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+ cmpdi r3,0
+ beq+ interrupt_return
+ mr r5,r3
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ ld r4,_DAR(r1)
+ bl __bad_page_fault
+ b interrupt_return
GEN_KVM instruction_access
@@ -3235,83 +3244,3 @@ disable_machine_check:
RFI_TO_KERNEL
1: mtlr r0
blr
-
-/*
- * Hash table stuff
- */
- .balign IFETCH_ALIGN_BYTES
-do_hash_page:
-#ifdef CONFIG_PPC_BOOK3S_64
- lis r0,(DSISR_BAD_FAULT_64S | DSISR_KEYFAULT)@h
- ori r0,r0,DSISR_BAD_FAULT_64S@l
- and. r0,r5,r0 /* weird error? */
- bne- handle_page_fault /* if not, try to insert a HPTE */
-
- /*
- * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
- * don't call hash_page, just fail the fault. This is required to
- * prevent re-entrancy problems in the hash code, namely perf
- * interrupts hitting while something holds H_PAGE_BUSY, and taking a
- * hash fault. See the comment in hash_preload().
- */
- ld r11, PACA_THREAD_INFO(r13)
- lwz r0,TI_PREEMPT(r11)
- andis. r0,r0,NMI_MASK@h
- bne 77f
-
- /*
- * r3 contains the trap number
- * r4 contains the faulting address
- * r5 contains dsisr
- * r6 msr
- *
- * at return r3 = 0 for success, 1 for page fault, negative for error
- */
- bl __hash_page /* build HPTE if possible */
- cmpdi r3,0 /* see if __hash_page succeeded */
-
- /* Success */
- beq interrupt_return /* Return from exception on success */
-
- /* Error */
- blt- 13f
-
- /* Reload DAR/DSISR into r4/r5 for handle_page_fault */
- ld r4,_DAR(r1)
- ld r5,_DSISR(r1)
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
-/* Here we have a page fault that hash_page can't handle. */
-handle_page_fault:
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_page_fault
- cmpdi r3,0
- beq+ interrupt_return
- mr r5,r3
- addi r3,r1,STACK_FRAME_OVERHEAD
- ld r4,_DAR(r1)
- bl __bad_page_fault
- b interrupt_return
-
-#ifdef CONFIG_PPC_BOOK3S_64
-/* We have a page fault that hash_page could handle but HV refused
- * the PTE insertion
- */
-13: mr r5,r3
- addi r3,r1,STACK_FRAME_OVERHEAD
- ld r4,_DAR(r1)
- bl low_hash_fault
- b interrupt_return
-#endif
-
-/*
- * We come here as a result of a DSI at a point where we don't want
- * to call hash_page, such as when we are accessing memory (possibly
- * user memory) inside a PMU interrupt that occurred while interrupts
- * were soft-disabled. We want to invoke the exception handler for
- * the access, or panic if there isn't a handler.
- */
-77: addi r3,r1,STACK_FRAME_OVERHEAD
- li r5,SIGSEGV
- bl bad_page_fault
- b interrupt_return
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 73b06adb6eeb..e866cae57e2f 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1512,16 +1512,40 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
}
EXPORT_SYMBOL_GPL(hash_page);
-int __hash_page(unsigned long trap, unsigned long ea, unsigned long dsisr,
- unsigned long msr)
+int do_hash_fault(struct pt_regs *regs, unsigned long ea, unsigned long dsisr)
{
unsigned long access = _PAGE_PRESENT | _PAGE_READ;
unsigned long flags = 0;
- struct mm_struct *mm = current->mm;
- unsigned int region_id = get_region_id(ea);
+ struct mm_struct *mm;
+ unsigned int region_id;
+ int err;
+
+ if (unlikely(dsisr & (DSISR_BAD_FAULT_64S | DSISR_KEYFAULT)))
+ goto page_fault;
+
+ /*
+ * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
+ * don't call hash_page, just fail the fault. This is required to
+ * prevent re-entrancy problems in the hash code, namely perf
+ * interrupts hitting while something holds H_PAGE_BUSY, and taking a
+ * hash fault. See the comment in hash_preload().
+ *
+ * We come here as a result of a DSI at a point where we don't want
+ * to call hash_page, such as when we are accessing memory (possibly
+ * user memory) inside a PMU interrupt that occurred while interrupts
+ * were soft-disabled. We want to invoke the exception handler for
+ * the access, or panic if there isn't a handler.
+ */
+ if (unlikely(in_nmi())) {
+ bad_page_fault(regs, ea, SIGSEGV);
+ return 0;
+ }
+ region_id = get_region_id(ea);
if ((region_id == VMALLOC_REGION_ID) || (region_id == IO_REGION_ID))
mm = &init_mm;
+ else
+ mm = current->mm;
if (dsisr & DSISR_NOHPTE)
flags |= HPTE_NOHPTE_UPDATE;
@@ -1537,13 +1561,31 @@ int __hash_page(unsigned long trap, unsigned long ea, unsigned long dsisr,
* 2) user space access kernel space.
*/
access |= _PAGE_PRIVILEGED;
- if ((msr & MSR_PR) || (region_id == USER_REGION_ID))
+ if (user_mode(regs) || (region_id == USER_REGION_ID))
access &= ~_PAGE_PRIVILEGED;
- if (trap == 0x400)
+ if (regs->trap == 0x400)
access |= _PAGE_EXEC;
- return hash_page_mm(mm, ea, access, trap, flags);
+ err = hash_page_mm(mm, ea, access, regs->trap, flags);
+ if (unlikely(err < 0)) {
+ // failed to instert a hash PTE due to an hypervisor error
+ if (user_mode(regs)) {
+ if (IS_ENABLED(CONFIG_PPC_SUBPAGE_PROT) && err == -2)
+ _exception(SIGSEGV, regs, SEGV_ACCERR, ea);
+ else
+ _exception(SIGBUS, regs, BUS_ADRERR, ea);
+ } else {
+ bad_page_fault(regs, ea, SIGBUS);
+ }
+ err = 0;
+
+ } else if (err) {
+page_fault:
+ err = do_page_fault(regs, ea, dsisr);
+ }
+
+ return err;
}
#ifdef CONFIG_PPC_MM_SLICES
@@ -1843,27 +1885,6 @@ void flush_hash_range(unsigned long number, int local)
}
}
-/*
- * low_hash_fault is called when we the low level hash code failed
- * to instert a PTE due to an hypervisor error
- */
-void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc)
-{
- enum ctx_state prev_state = exception_enter();
-
- if (user_mode(regs)) {
-#ifdef CONFIG_PPC_SUBPAGE_PROT
- if (rc == -2)
- _exception(SIGSEGV, regs, SEGV_ACCERR, address);
- else
-#endif
- _exception(SIGBUS, regs, BUS_ADRERR, address);
- } else
- bad_page_fault(regs, address, SIGBUS);
-
- exception_exit(prev_state);
-}
-
long hpte_insert_repeating(unsigned long hash, unsigned long vpn,
unsigned long pa, unsigned long rflags,
unsigned long vflags, int psize, int ssize)
--
2.23.0
^ permalink raw reply related
* [PATCH v7 06/42] powerpc: remove arguments from fault handler functions
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
Make mm fault handlers all just take the pt_regs * argument and load
DAR/DSISR from that. Make those that return a value return long.
This is done to make the function signatures match other handlers, which
will help with a future patch to add wrappers. Explicit arguments could
be added for performance but that would require more wrapper macro
variants.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/asm-prototypes.h | 4 ++--
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 2 +-
arch/powerpc/include/asm/bug.h | 2 +-
arch/powerpc/kernel/exceptions-64e.S | 2 --
arch/powerpc/kernel/exceptions-64s.S | 17 ++++-------------
arch/powerpc/kernel/head_40x.S | 10 +++++-----
arch/powerpc/kernel/head_8xx.S | 6 +++---
arch/powerpc/kernel/head_book3s_32.S | 5 ++---
arch/powerpc/kernel/head_booke.h | 4 +---
arch/powerpc/mm/book3s64/hash_utils.c | 8 +++++---
arch/powerpc/mm/book3s64/slb.c | 11 +++++++----
arch/powerpc/mm/fault.c | 5 ++---
12 files changed, 33 insertions(+), 43 deletions(-)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index d0b832cbbec8..22c9d08fa3a4 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -82,8 +82,8 @@ void kernel_bad_stack(struct pt_regs *regs);
void system_reset_exception(struct pt_regs *regs);
void machine_check_exception(struct pt_regs *regs);
void emulation_assist_interrupt(struct pt_regs *regs);
-long do_slb_fault(struct pt_regs *regs, unsigned long ea);
-void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err);
+long do_slb_fault(struct pt_regs *regs);
+void do_bad_slb_fault(struct pt_regs *regs);
/* signals, syscalls and interrupts */
long sys_swapcontext(struct ucontext __user *old_ctx,
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 60a669379aa0..b9968e297da2 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -454,7 +454,7 @@ static inline unsigned long hpt_hash(unsigned long vpn,
#define HPTE_NOHPTE_UPDATE 0x2
#define HPTE_USE_KERNEL_KEY 0x4
-int do_hash_fault(struct pt_regs *regs, unsigned long ea, unsigned long dsisr);
+long do_hash_fault(struct pt_regs *regs);
extern int __hash_page_4K(unsigned long ea, unsigned long access,
unsigned long vsid, pte_t *ptep, unsigned long trap,
unsigned long flags, int ssize, int subpage_prot);
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 464f8ca8a5c9..f7827e993196 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -111,7 +111,7 @@
#ifndef __ASSEMBLY__
struct pt_regs;
-extern int do_page_fault(struct pt_regs *, unsigned long, unsigned long);
+long do_page_fault(struct pt_regs *);
extern void bad_page_fault(struct pt_regs *, unsigned long, int);
void __bad_page_fault(struct pt_regs *regs, unsigned long address, int sig);
extern void _exception(int, struct pt_regs *, int, unsigned long);
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 74d07dc0bb48..43e71d86dcbf 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -1011,8 +1011,6 @@ storage_fault_common:
std r14,_DAR(r1)
std r15,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
- mr r4,r14
- mr r5,r15
ld r14,PACA_EXGEN+EX_R14(r13)
ld r15,PACA_EXGEN+EX_R15(r13)
bl do_page_fault
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 07aba8af99d3..839dcb94eea7 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1438,10 +1438,9 @@ EXC_VIRT_BEGIN(data_access, 0x4300, 0x80)
EXC_VIRT_END(data_access, 0x4300, 0x80)
EXC_COMMON_BEGIN(data_access_common)
GEN_COMMON data_access
- ld r4,_DAR(r1)
- ld r5,_DSISR(r1)
+ ld r4,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
- andis. r0,r5,DSISR_DABRMATCH@h
+ andis. r0,r4,DSISR_DABRMATCH@h
bne- 1f
BEGIN_MMU_FTR_SECTION
bl do_hash_fault
@@ -1504,10 +1503,9 @@ EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80)
EXC_VIRT_END(data_access_slb, 0x4380, 0x80)
EXC_COMMON_BEGIN(data_access_slb_common)
GEN_COMMON data_access_slb
- ld r4,_DAR(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
/* HPT case, do SLB fault */
+ addi r3,r1,STACK_FRAME_OVERHEAD
bl do_slb_fault
cmpdi r3,0
bne- 1f
@@ -1519,8 +1517,6 @@ MMU_FTR_SECTION_ELSE
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
RECONCILE_IRQ_STATE(r10, r11)
- ld r4,_DAR(r1)
- ld r5,RESULT(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
b interrupt_return
@@ -1555,8 +1551,6 @@ EXC_VIRT_BEGIN(instruction_access, 0x4400, 0x80)
EXC_VIRT_END(instruction_access, 0x4400, 0x80)
EXC_COMMON_BEGIN(instruction_access_common)
GEN_COMMON instruction_access
- ld r4,_DAR(r1)
- ld r5,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
bl do_hash_fault
@@ -1602,10 +1596,9 @@ EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80)
EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80)
EXC_COMMON_BEGIN(instruction_access_slb_common)
GEN_COMMON instruction_access_slb
- ld r4,_DAR(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
/* HPT case, do SLB fault */
+ addi r3,r1,STACK_FRAME_OVERHEAD
bl do_slb_fault
cmpdi r3,0
bne- 1f
@@ -1617,8 +1610,6 @@ MMU_FTR_SECTION_ELSE
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
RECONCILE_IRQ_STATE(r10, r11)
- ld r4,_DAR(r1)
- ld r5,RESULT(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
b interrupt_return
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index a1ae00689e0f..3c5577ac4dc8 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -179,9 +179,9 @@ _ENTRY(saved_ksp_limit)
*/
START_EXCEPTION(0x0300, DataStorage)
EXCEPTION_PROLOG
- mfspr r5, SPRN_ESR /* Grab the ESR, save it, pass arg3 */
+ mfspr r5, SPRN_ESR /* Grab the ESR, save it */
stw r5, _ESR(r11)
- mfspr r4, SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */
+ mfspr r4, SPRN_DEAR /* Grab the DEAR, save it */
stw r4, _DEAR(r11)
EXC_XFER_LITE(0x300, handle_page_fault)
@@ -191,9 +191,9 @@ _ENTRY(saved_ksp_limit)
*/
START_EXCEPTION(0x0400, InstructionAccess)
EXCEPTION_PROLOG
- mr r4,r12 /* Pass SRR0 as arg2 */
- stw r4, _DEAR(r11)
- li r5,0 /* Pass zero as arg3 */
+ li r5,0
+ stw r5, _ESR(r11) /* Zero ESR */
+ stw r12, _DEAR(r11) /* SRR0 as DEAR */
EXC_XFER_LITE(0x400, handle_page_fault)
/* 0x0500 - External Interrupt Exception */
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 52702f3db6df..0b2c247cfdff 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -312,14 +312,14 @@ DataStoreTLBMiss:
. = 0x1300
InstructionTLBError:
EXCEPTION_PROLOG
- mr r4,r12
andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */
andis. r10,r9,SRR1_ISI_NOPT@h
beq+ .Litlbie
- tlbie r4
+ tlbie r12
/* 0x400 is InstructionAccess exception, needed by bad_page_fault() */
.Litlbie:
- stw r4, _DAR(r11)
+ stw r12, _DAR(r11)
+ stw r5, _DSISR(r11)
EXC_XFER_LITE(0x400, handle_page_fault)
/* This is the data TLB error on the MPC8xx. This could be due to
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 6d411b8fd5d3..1f808e1aa051 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -361,9 +361,9 @@ BEGIN_MMU_FTR_SECTION
bl hash_page
END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
#endif /* CONFIG_VMAP_STACK */
-1: mr r4,r12
andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */
- stw r4, _DAR(r11)
+ stw r5, _DSISR(r11)
+ stw r12, _DAR(r11)
EXC_XFER_LITE(0x400, handle_page_fault)
/* External interrupt */
@@ -685,7 +685,6 @@ handle_page_fault_tramp_1:
#ifdef CONFIG_VMAP_STACK
EXCEPTION_PROLOG_2 handle_dar_dsisr=1
#endif
- lwz r4, _DAR(r11)
lwz r5, _DSISR(r11)
/* fall through */
handle_page_fault_tramp_2:
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 74e230c200fb..0fbdacc7fab7 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -476,9 +476,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
NORMAL_EXCEPTION_PROLOG(INST_STORAGE); \
mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \
stw r5,_ESR(r11); \
- mr r4,r12; /* Pass SRR0 as arg2 */ \
- stw r4, _DEAR(r11); \
- li r5,0; /* Pass zero as arg3 */ \
+ stw r12, _DEAR(r11); /* Pass SRR0 as arg2 */ \
EXC_XFER_LITE(0x0400, handle_page_fault)
#define ALIGNMENT_EXCEPTION \
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index e866cae57e2f..9a499af3eebf 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1512,13 +1512,15 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
}
EXPORT_SYMBOL_GPL(hash_page);
-int do_hash_fault(struct pt_regs *regs, unsigned long ea, unsigned long dsisr)
+long do_hash_fault(struct pt_regs *regs)
{
+ unsigned long ea = regs->dar;
+ unsigned long dsisr = regs->dsisr;
unsigned long access = _PAGE_PRESENT | _PAGE_READ;
unsigned long flags = 0;
struct mm_struct *mm;
unsigned int region_id;
- int err;
+ long err;
if (unlikely(dsisr & (DSISR_BAD_FAULT_64S | DSISR_KEYFAULT)))
goto page_fault;
@@ -1582,7 +1584,7 @@ int do_hash_fault(struct pt_regs *regs, unsigned long ea, unsigned long dsisr)
} else if (err) {
page_fault:
- err = do_page_fault(regs, ea, dsisr);
+ err = do_page_fault(regs);
}
return err;
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index 584567970c11..985902ce0272 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -813,8 +813,9 @@ static long slb_allocate_user(struct mm_struct *mm, unsigned long ea)
return slb_insert_entry(ea, context, flags, ssize, false);
}
-long do_slb_fault(struct pt_regs *regs, unsigned long ea)
+long do_slb_fault(struct pt_regs *regs)
{
+ unsigned long ea = regs->dar;
unsigned long id = get_region_id(ea);
/* IRQs are not reconciled here, so can't check irqs_disabled */
@@ -865,13 +866,15 @@ long do_slb_fault(struct pt_regs *regs, unsigned long ea)
}
}
-void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err)
+void do_bad_slb_fault(struct pt_regs *regs)
{
+ int err = regs->result;
+
if (err == -EFAULT) {
if (user_mode(regs))
- _exception(SIGSEGV, regs, SEGV_BNDERR, ea);
+ _exception(SIGSEGV, regs, SEGV_BNDERR, regs->dar);
else
- bad_page_fault(regs, ea, SIGSEGV);
+ bad_page_fault(regs, regs->dar, SIGSEGV);
} else if (err == -EINVAL) {
unrecoverable_exception(regs);
} else {
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 8961b44f350c..273ff845eccf 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -542,12 +542,11 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
}
NOKPROBE_SYMBOL(__do_page_fault);
-int do_page_fault(struct pt_regs *regs, unsigned long address,
- unsigned long error_code)
+long do_page_fault(struct pt_regs *regs)
{
const struct exception_table_entry *entry;
enum ctx_state prev_state = exception_enter();
- int rc = __do_page_fault(regs, address, error_code);
+ int rc = __do_page_fault(regs, regs->dar, regs->dsisr);
exception_exit(prev_state);
if (likely(!rc))
return 0;
--
2.23.0
^ permalink raw reply related
* [PATCH v7 07/42] powerpc/fsl_booke/32: CacheLockingException remove args
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
Like other interrupt handler conversions, switch to getting registers
from the pt_regs argument.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/head_fsl_booke.S | 6 +++---
arch/powerpc/kernel/traps.c | 5 +++--
2 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index fdd4d274c245..0d4d9a6fcca1 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -364,12 +364,12 @@ interrupt_base:
/* Data Storage Interrupt */
START_EXCEPTION(DataStorage)
NORMAL_EXCEPTION_PROLOG(DATA_STORAGE)
- mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */
+ mfspr r5,SPRN_ESR /* Grab the ESR, save it3 */
stw r5,_ESR(r11)
- mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */
+ mfspr r4,SPRN_DEAR /* Grab the DEAR, save it */
+ stw r4, _DEAR(r11)
andis. r10,r5,(ESR_ILK|ESR_DLK)@h
bne 1f
- stw r4, _DEAR(r11)
EXC_XFER_LITE(0x0300, handle_page_fault)
1:
addi r3,r1,STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 3ec7b443fe6b..1c77b1a8f7c9 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -2062,9 +2062,10 @@ void altivec_assist_exception(struct pt_regs *regs)
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_FSL_BOOKE
-void CacheLockingException(struct pt_regs *regs, unsigned long address,
- unsigned long error_code)
+void CacheLockingException(struct pt_regs *regs)
{
+ unsigned long error_code = regs->dsisr;
+
/* We treat cache locking instructions from the user
* as priv ops, in the future we could try to do
* something smarter
--
2.23.0
^ permalink raw reply related
* [PATCH v7 08/42] powerpc: do_break get registers from regs
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
Similar to the previous patch this makes interrupt handler function
types more regular so they can be wrapped with the next patch.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/debug.h | 3 +--
arch/powerpc/kernel/head_8xx.S | 5 ++---
arch/powerpc/kernel/process.c | 7 +++----
3 files changed, 6 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h
index ec57daf87f40..0550eceab3ca 100644
--- a/arch/powerpc/include/asm/debug.h
+++ b/arch/powerpc/include/asm/debug.h
@@ -52,8 +52,7 @@ extern void do_send_trap(struct pt_regs *regs, unsigned long address,
unsigned long error_code, int brkpt);
#else
-extern void do_break(struct pt_regs *regs, unsigned long address,
- unsigned long error_code);
+void do_break(struct pt_regs *regs);
#endif
#endif /* _ASM_POWERPC_DEBUG_H */
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 0b2c247cfdff..7869db974185 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -364,10 +364,9 @@ do_databreakpoint:
addi r3,r1,STACK_FRAME_OVERHEAD
mfspr r4,SPRN_BAR
stw r4,_DAR(r11)
-#ifdef CONFIG_VMAP_STACK
- lwz r5,_DSISR(r11)
-#else
+#ifndef CONFIG_VMAP_STACK
mfspr r5,SPRN_DSISR
+ stw r5,_DSISR(r11)
#endif
EXC_XFER_STD(0x1c00, do_break)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index a66f435dabbf..4f0f81e9420b 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -659,11 +659,10 @@ static void do_break_handler(struct pt_regs *regs)
}
}
-void do_break (struct pt_regs *regs, unsigned long address,
- unsigned long error_code)
+void do_break(struct pt_regs *regs)
{
current->thread.trap_nr = TRAP_HWBKPT;
- if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code,
+ if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, regs->dsisr,
11, SIGSEGV) == NOTIFY_STOP)
return;
@@ -681,7 +680,7 @@ void do_break (struct pt_regs *regs, unsigned long address,
do_break_handler(regs);
/* Deliver the signal to userspace */
- force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)address);
+ force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)regs->dar);
}
#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
--
2.23.0
^ permalink raw reply related
* [PATCH v7 09/42] powerpc: DebugException remove args
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
Like other interrupt handler conversions, switch to getting registers
from the pt_regs argument.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64e.S | 2 --
arch/powerpc/kernel/head_40x.S | 1 +
arch/powerpc/kernel/head_booke.h | 2 ++
arch/powerpc/kernel/traps.c | 4 +++-
4 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 43e71d86dcbf..1a7291daadfd 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -791,7 +791,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
EXCEPTION_COMMON_CRIT(0xd00)
std r14,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
- mr r4,r14
ld r14,PACA_EXCRIT+EX_R14(r13)
ld r15,PACA_EXCRIT+EX_R15(r13)
bl save_nvgprs
@@ -864,7 +863,6 @@ kernel_dbg_exc:
INTS_DISABLE
std r14,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
- mr r4,r14
ld r14,PACA_EXDBG+EX_R14(r13)
ld r15,PACA_EXDBG+EX_R15(r13)
bl save_nvgprs
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 3c5577ac4dc8..24724a7dad49 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -476,6 +476,7 @@ _ENTRY(saved_ksp_limit)
/* continue normal handling for a critical exception... */
2: mfspr r4,SPRN_DBSR
+ stw r4,_ESR(r11) /* DebugException takes DBSR in _ESR */
addi r3,r1,STACK_FRAME_OVERHEAD
EXC_XFER_TEMPLATE(DebugException, 0x2002, \
(MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 0fbdacc7fab7..bf33af714d11 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -406,6 +406,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
\
/* continue normal handling for a debug exception... */ \
2: mfspr r4,SPRN_DBSR; \
+ stw r4,_ESR(r11); /* DebugException takes DBSR in _ESR */\
addi r3,r1,STACK_FRAME_OVERHEAD; \
EXC_XFER_TEMPLATE(DebugException, 0x2008, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), debug_transfer_to_handler, ret_from_debug_exc)
@@ -459,6 +460,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
\
/* continue normal handling for a critical exception... */ \
2: mfspr r4,SPRN_DBSR; \
+ stw r4,_ESR(r11); /* DebugException takes DBSR in _ESR */\
addi r3,r1,STACK_FRAME_OVERHEAD; \
EXC_XFER_TEMPLATE(DebugException, 0x2002, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), crit_transfer_to_handler, ret_from_crit_exc)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 1c77b1a8f7c9..dfb0d3325f4b 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1957,8 +1957,10 @@ static void handle_debug(struct pt_regs *regs, unsigned long debug_status)
mtspr(SPRN_DBCR0, current->thread.debug.dbcr0);
}
-void DebugException(struct pt_regs *regs, unsigned long debug_status)
+void DebugException(struct pt_regs *regs)
{
+ unsigned long debug_status = regs->dsisr;
+
current->thread.debug.dbsr = debug_status;
/* Hack alert: On BookE, Branch Taken stops on the branch itself, while
--
2.23.0
^ permalink raw reply related
* [PATCH v7 10/42] powerpc/32: transfer can avoid saving r4/r5 over trace call
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
Now that handlers get all registers from pt_regs, r4 and r5 are no
longer live here and may be clobbered.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/entry_32.S | 7 +------
1 file changed, 1 insertion(+), 6 deletions(-)
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 238eacfda7b0..d6ea3f2d6cc0 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -276,8 +276,7 @@ reenable_mmu:
* We save a bunch of GPRs,
* r3 can be different from GPR3(r1) at this point, r9 and r11
* contains the old MSR and handler address respectively,
- * r4 & r5 can contain page fault arguments that need to be passed
- * along as well. r0, r6-r8, r12, CCR, CTR, XER etc... are left
+ * r0, r4-r8, r12, CCR, CTR, XER etc... are left
* clobbered as they aren't useful past this point.
*/
@@ -285,15 +284,11 @@ reenable_mmu:
stw r9,8(r1)
stw r11,12(r1)
stw r3,16(r1)
- stw r4,20(r1)
- stw r5,24(r1)
/* If we are disabling interrupts (normal case), simply log it with
* lockdep
*/
1: bl trace_hardirqs_off
- lwz r5,24(r1)
- lwz r4,20(r1)
lwz r3,16(r1)
lwz r11,12(r1)
lwz r9,8(r1)
--
2.23.0
^ permalink raw reply related
* [PATCH v7 11/42] powerpc: bad_page_fault get registers from regs
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
Similar to the previous patch this makes interrupt handler function
types more regular so they can be wrapped with the next patch.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/bug.h | 4 ++--
arch/powerpc/kernel/entry_32.S | 3 +--
arch/powerpc/kernel/exceptions-64e.S | 3 +--
arch/powerpc/kernel/traps.c | 2 +-
arch/powerpc/mm/book3s64/hash_utils.c | 4 ++--
arch/powerpc/mm/book3s64/slb.c | 2 +-
arch/powerpc/mm/fault.c | 6 +++---
arch/powerpc/platforms/8xx/machine_check.c | 2 +-
8 files changed, 12 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index f7827e993196..4220789b9a97 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -112,8 +112,8 @@
struct pt_regs;
long do_page_fault(struct pt_regs *);
-extern void bad_page_fault(struct pt_regs *, unsigned long, int);
-void __bad_page_fault(struct pt_regs *regs, unsigned long address, int sig);
+void bad_page_fault(struct pt_regs *, int);
+void __bad_page_fault(struct pt_regs *regs, int sig);
extern void _exception(int, struct pt_regs *, int, unsigned long);
extern void _exception_pkey(struct pt_regs *, unsigned long, int);
extern void die(const char *, struct pt_regs *, long);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index d6ea3f2d6cc0..b102b40c4988 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -672,9 +672,8 @@ handle_page_fault:
lwz r0,_TRAP(r1)
clrrwi r0,r0,1
stw r0,_TRAP(r1)
- mr r5,r3
+ mr r4,r3 /* err arg for bad_page_fault */
addi r3,r1,STACK_FRAME_OVERHEAD
- lwz r4,_DAR(r1)
bl __bad_page_fault
b ret_from_except_full
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 1a7291daadfd..003999c7836c 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -1016,9 +1016,8 @@ storage_fault_common:
bne- 1f
b ret_from_except_lite
1: bl save_nvgprs
- mr r5,r3
+ mr r4,r3
addi r3,r1,STACK_FRAME_OVERHEAD
- ld r4,_DAR(r1)
bl __bad_page_fault
b ret_from_except
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index dfb0d3325f4b..f7370145be19 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1612,7 +1612,7 @@ void alignment_exception(struct pt_regs *regs)
if (user_mode(regs))
_exception(sig, regs, code, regs->dar);
else
- bad_page_fault(regs, regs->dar, sig);
+ bad_page_fault(regs, sig);
bail:
exception_exit(prev_state);
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 9a499af3eebf..1a270cc37d97 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1539,7 +1539,7 @@ long do_hash_fault(struct pt_regs *regs)
* the access, or panic if there isn't a handler.
*/
if (unlikely(in_nmi())) {
- bad_page_fault(regs, ea, SIGSEGV);
+ bad_page_fault(regs, SIGSEGV);
return 0;
}
@@ -1578,7 +1578,7 @@ long do_hash_fault(struct pt_regs *regs)
else
_exception(SIGBUS, regs, BUS_ADRERR, ea);
} else {
- bad_page_fault(regs, ea, SIGBUS);
+ bad_page_fault(regs, SIGBUS);
}
err = 0;
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index 985902ce0272..c581548b533f 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -874,7 +874,7 @@ void do_bad_slb_fault(struct pt_regs *regs)
if (user_mode(regs))
_exception(SIGSEGV, regs, SEGV_BNDERR, regs->dar);
else
- bad_page_fault(regs, regs->dar, SIGSEGV);
+ bad_page_fault(regs, SIGSEGV);
} else if (err == -EINVAL) {
unrecoverable_exception(regs);
} else {
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 273ff845eccf..5dd3248b47c7 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -566,7 +566,7 @@ NOKPROBE_SYMBOL(do_page_fault);
* It is called from the DSI and ISI handlers in head.S and from some
* of the procedures in traps.c.
*/
-void __bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
+void __bad_page_fault(struct pt_regs *regs, int sig)
{
int is_write = page_fault_is_write(regs->dsisr);
@@ -604,7 +604,7 @@ void __bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
die("Kernel access of bad area", regs, sig);
}
-void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
+void bad_page_fault(struct pt_regs *regs, int sig)
{
const struct exception_table_entry *entry;
@@ -613,5 +613,5 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
if (entry)
instruction_pointer_set(regs, extable_fixup(entry));
else
- __bad_page_fault(regs, address, sig);
+ __bad_page_fault(regs, sig);
}
diff --git a/arch/powerpc/platforms/8xx/machine_check.c b/arch/powerpc/platforms/8xx/machine_check.c
index 88dedf38eccd..656365975895 100644
--- a/arch/powerpc/platforms/8xx/machine_check.c
+++ b/arch/powerpc/platforms/8xx/machine_check.c
@@ -26,7 +26,7 @@ int machine_check_8xx(struct pt_regs *regs)
* to deal with that than having a wart in the mcheck handler.
* -- BenH
*/
- bad_page_fault(regs, regs->dar, SIGBUS);
+ bad_page_fault(regs, SIGBUS);
return 1;
#else
return 0;
--
2.23.0
^ permalink raw reply related
* [PATCH v7 12/42] powerpc/64s: add do_bad_page_fault_segv handler
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
This function acts like an interrupt handler so it needs to follow
the standard interrupt handler function signature which will be
introduced in a future change.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/bug.h | 1 +
arch/powerpc/kernel/exceptions-64s.S | 4 +---
arch/powerpc/mm/fault.c | 7 +++++++
3 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 4220789b9a97..8f09ddae9305 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -114,6 +114,7 @@ struct pt_regs;
long do_page_fault(struct pt_regs *);
void bad_page_fault(struct pt_regs *, int);
void __bad_page_fault(struct pt_regs *regs, int sig);
+void do_bad_page_fault_segv(struct pt_regs *regs);
extern void _exception(int, struct pt_regs *, int, unsigned long);
extern void _exception_pkey(struct pt_regs *, unsigned long, int);
extern void die(const char *, struct pt_regs *, long);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 839dcb94eea7..b90d3cde14cf 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -2151,9 +2151,7 @@ EXC_COMMON_BEGIN(h_data_storage_common)
GEN_COMMON h_data_storage
addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
- ld r4,_DAR(r1)
- li r5,SIGSEGV
- bl bad_page_fault
+ bl do_bad_page_fault_segv
MMU_FTR_SECTION_ELSE
bl unknown_exception
ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 5dd3248b47c7..e476d7701413 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -615,3 +615,10 @@ void bad_page_fault(struct pt_regs *regs, int sig)
else
__bad_page_fault(regs, sig);
}
+
+#ifdef CONFIG_PPC_BOOK3S_64
+void do_bad_page_fault_segv(struct pt_regs *regs)
+{
+ bad_page_fault(regs, SIGSEGV);
+}
+#endif
--
2.23.0
^ permalink raw reply related
* [PATCH v7 13/42] powerpc: rearrange do_page_fault error case to be inside exception_enter
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
This keeps the context tracking over the entire interrupt handler which
helps later with moving context tracking into interrupt wrappers.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/mm/fault.c | 23 ++++++++++++++---------
1 file changed, 14 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index e476d7701413..970ac317e018 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -545,19 +545,24 @@ NOKPROBE_SYMBOL(__do_page_fault);
long do_page_fault(struct pt_regs *regs)
{
const struct exception_table_entry *entry;
- enum ctx_state prev_state = exception_enter();
- int rc = __do_page_fault(regs, regs->dar, regs->dsisr);
- exception_exit(prev_state);
- if (likely(!rc))
- return 0;
+ enum ctx_state prev_state;
+ long err;
+
+ prev_state = exception_enter();
+ err = __do_page_fault(regs, regs->dar, regs->dsisr);
+ if (likely(!err))
+ goto out;
entry = search_exception_tables(regs->nip);
- if (unlikely(!entry))
- return rc;
+ if (likely(entry)) {
+ instruction_pointer_set(regs, extable_fixup(entry));
+ err = 0;
+ }
- instruction_pointer_set(regs, extable_fixup(entry));
+out:
+ exception_exit(prev_state);
- return 0;
+ return err;
}
NOKPROBE_SYMBOL(do_page_fault);
--
2.23.0
^ permalink raw reply related
* [PATCH v7 14/42] powerpc/64s: move bad_page_fault handling to C
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
This simplifies code, and it is also useful when introducing
interrupt handler wrappers when introducing wrapper functionality
that doesn't cope with asm entry code calling into more than one
handler function.
32-bit and 64e still have some such cases, which limits some ways
they can use interrupt wrappers.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64s.S | 12 ------------
arch/powerpc/mm/fault.c | 4 ++++
2 files changed, 4 insertions(+), 12 deletions(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index b90d3cde14cf..e69a912c2cc6 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1447,12 +1447,6 @@ BEGIN_MMU_FTR_SECTION
MMU_FTR_SECTION_ELSE
bl do_page_fault
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
- cmpdi r3,0
- beq+ interrupt_return
- mr r5,r3
- addi r3,r1,STACK_FRAME_OVERHEAD
- ld r4,_DAR(r1)
- bl __bad_page_fault
b interrupt_return
1: bl do_break
@@ -1557,12 +1551,6 @@ BEGIN_MMU_FTR_SECTION
MMU_FTR_SECTION_ELSE
bl do_page_fault
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
- cmpdi r3,0
- beq+ interrupt_return
- mr r5,r3
- addi r3,r1,STACK_FRAME_OVERHEAD
- ld r4,_DAR(r1)
- bl __bad_page_fault
b interrupt_return
GEN_KVM instruction_access
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 970ac317e018..fc2d9a27c649 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -557,6 +557,10 @@ long do_page_fault(struct pt_regs *regs)
if (likely(entry)) {
instruction_pointer_set(regs, extable_fixup(entry));
err = 0;
+ } else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) {
+ /* 32 and 64e handle this in asm */
+ __bad_page_fault(regs, err);
+ err = 0;
}
out:
--
2.23.0
^ permalink raw reply related
* [PATCH v7 15/42] powerpc/64s: split do_hash_fault
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
This is required for subsequent interrupt wrapper implementation.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/mm/book3s64/hash_utils.c | 56 ++++++++++++++++-----------
1 file changed, 33 insertions(+), 23 deletions(-)
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 1a270cc37d97..d7d3a80a51d4 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1512,7 +1512,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
}
EXPORT_SYMBOL_GPL(hash_page);
-long do_hash_fault(struct pt_regs *regs)
+static long __do_hash_fault(struct pt_regs *regs)
{
unsigned long ea = regs->dar;
unsigned long dsisr = regs->dsisr;
@@ -1522,27 +1522,6 @@ long do_hash_fault(struct pt_regs *regs)
unsigned int region_id;
long err;
- if (unlikely(dsisr & (DSISR_BAD_FAULT_64S | DSISR_KEYFAULT)))
- goto page_fault;
-
- /*
- * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
- * don't call hash_page, just fail the fault. This is required to
- * prevent re-entrancy problems in the hash code, namely perf
- * interrupts hitting while something holds H_PAGE_BUSY, and taking a
- * hash fault. See the comment in hash_preload().
- *
- * We come here as a result of a DSI at a point where we don't want
- * to call hash_page, such as when we are accessing memory (possibly
- * user memory) inside a PMU interrupt that occurred while interrupts
- * were soft-disabled. We want to invoke the exception handler for
- * the access, or panic if there isn't a handler.
- */
- if (unlikely(in_nmi())) {
- bad_page_fault(regs, SIGSEGV);
- return 0;
- }
-
region_id = get_region_id(ea);
if ((region_id == VMALLOC_REGION_ID) || (region_id == IO_REGION_ID))
mm = &init_mm;
@@ -1581,8 +1560,39 @@ long do_hash_fault(struct pt_regs *regs)
bad_page_fault(regs, SIGBUS);
}
err = 0;
+ }
+
+ return err;
+}
+
+long do_hash_fault(struct pt_regs *regs)
+{
+ unsigned long dsisr = regs->dsisr;
+ long err;
+
+ if (unlikely(dsisr & (DSISR_BAD_FAULT_64S | DSISR_KEYFAULT)))
+ goto page_fault;
+
+ /*
+ * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
+ * don't call hash_page, just fail the fault. This is required to
+ * prevent re-entrancy problems in the hash code, namely perf
+ * interrupts hitting while something holds H_PAGE_BUSY, and taking a
+ * hash fault. See the comment in hash_preload().
+ *
+ * We come here as a result of a DSI at a point where we don't want
+ * to call hash_page, such as when we are accessing memory (possibly
+ * user memory) inside a PMU interrupt that occurred while interrupts
+ * were soft-disabled. We want to invoke the exception handler for
+ * the access, or panic if there isn't a handler.
+ */
+ if (unlikely(in_nmi())) {
+ bad_page_fault(regs, SIGSEGV);
+ return 0;
+ }
- } else if (err) {
+ err = __do_hash_fault(regs);
+ if (err) {
page_fault:
err = do_page_fault(regs);
}
--
2.23.0
^ permalink raw reply related
* [PATCH v7 16/42] powerpc/mm: Remove stale do_page_fault comment referring to SLB faults
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
SLB faults no longer call do_page_fault, this was removed somewhere
between 2.6.0 and 2.6.12.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/mm/fault.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index fc2d9a27c649..fef92efad733 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -377,13 +377,11 @@ static void sanity_check_fault(bool is_write, bool is_user,
/*
* For 600- and 800-family processors, the error_code parameter is DSISR
- * for a data fault, SRR1 for an instruction fault. For 400-family processors
- * the error_code parameter is ESR for a data fault, 0 for an instruction
- * fault.
- * For 64-bit processors, the error_code parameter is
- * - DSISR for a non-SLB data access fault,
- * - SRR1 & 0x08000000 for a non-SLB instruction access fault
- * - 0 any SLB fault.
+ * for a data fault, SRR1 for an instruction fault.
+ * For 400-family processors the error_code parameter is ESR for a data fault,
+ * 0 for an instruction fault.
+ * For 64-bit processors, the error_code parameter is DSISR for a data access
+ * fault, SRR1 & 0x08000000 for an instruction access fault.
*
* The return value is 0 if the fault was handled, or the signal
* number if this is a kernel fault that can't be handled here.
--
2.23.0
^ permalink raw reply related
* [PATCH v7 17/42] powerpc/64s: slb comment update
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
This makes a small improvement to the description of the SLB interrupt
environment. Move the memory access restrictions into one paragraph,
and the interrupt restrictions into the next rather than mix them.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/mm/book3s64/slb.c | 28 +++++++++++++++-------------
1 file changed, 15 insertions(+), 13 deletions(-)
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index c581548b533f..14c62b685f0c 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -825,19 +825,21 @@ long do_slb_fault(struct pt_regs *regs)
return -EINVAL;
/*
- * SLB kernel faults must be very careful not to touch anything
- * that is not bolted. E.g., PACA and global variables are okay,
- * mm->context stuff is not.
- *
- * SLB user faults can access all of kernel memory, but must be
- * careful not to touch things like IRQ state because it is not
- * "reconciled" here. The difficulty is that we must use
- * fast_exception_return to return from kernel SLB faults without
- * looking at possible non-bolted memory. We could test user vs
- * kernel faults in the interrupt handler asm and do a full fault,
- * reconcile, ret_from_except for user faults which would make them
- * first class kernel code. But for performance it's probably nicer
- * if they go via fast_exception_return too.
+ * SLB kernel faults must be very careful not to touch anything that is
+ * not bolted. E.g., PACA and global variables are okay, mm->context
+ * stuff is not. SLB user faults may access all of memory (and induce
+ * one recursive SLB kernel fault), so the kernel fault must not
+ * trample on the user fault state at those points.
+ */
+
+ /*
+ * The interrupt state is not reconciled, for performance, so that
+ * fast_interrupt_return can be used. The handler must not touch local
+ * irq state, or schedule. We could test for usermode and upgrade to a
+ * normal process context (synchronous) interrupt for those, which
+ * would make them first-class kernel code and able to be traced and
+ * instrumented, although performance would suffer a bit, it would
+ * probably be a good tradeoff.
*/
if (id >= LINEAR_MAP_REGION_ID) {
long err;
--
2.23.0
^ permalink raw reply related
* [PATCH v7 18/42] powerpc/traps: add NOKPROBE_SYMBOL for sreset and mce
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
These NMIs could fire any time including inside kprobe code, so
exclude them from kprobes.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/traps.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index f7370145be19..4349b25807cf 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -517,6 +517,7 @@ void system_reset_exception(struct pt_regs *regs)
/* What should we do here? We could issue a shutdown or hard reset. */
}
+NOKPROBE_SYMBOL(system_reset_exception);
/*
* I/O accesses can cause machine checks on powermacs.
@@ -843,6 +844,7 @@ void machine_check_exception(struct pt_regs *regs)
bail:
if (nmi) nmi_exit();
}
+NOKPROBE_SYMBOL(machine_check_exception);
void SMIException(struct pt_regs *regs)
{
--
2.23.0
^ permalink raw reply related
* [PATCH v7 19/42] powerpc/perf: move perf irq/nmi handling details into traps.c
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
This is required in order to allow more significant differences between
NMI type interrupt handlers and regular asynchronous handlers.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/traps.c | 31 +++++++++++++++++++++++++++-
arch/powerpc/perf/core-book3s.c | 35 ++------------------------------
arch/powerpc/perf/core-fsl-emb.c | 25 -----------------------
3 files changed, 32 insertions(+), 59 deletions(-)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 4349b25807cf..6da3a3642dfb 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1892,11 +1892,40 @@ void vsx_unavailable_tm(struct pt_regs *regs)
}
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-void performance_monitor_exception(struct pt_regs *regs)
+static void performance_monitor_exception_nmi(struct pt_regs *regs)
+{
+ nmi_enter();
+
+ __this_cpu_inc(irq_stat.pmu_irqs);
+
+ perf_irq(regs);
+
+ nmi_exit();
+}
+
+static void performance_monitor_exception_async(struct pt_regs *regs)
{
+ irq_enter();
+
__this_cpu_inc(irq_stat.pmu_irqs);
perf_irq(regs);
+
+ irq_exit();
+}
+
+void performance_monitor_exception(struct pt_regs *regs)
+{
+ /*
+ * On 64-bit, if perf interrupts hit in a local_irq_disable
+ * (soft-masked) region, we consider them as NMIs. This is required to
+ * prevent hash faults on user addresses when reading callchains (and
+ * looks better from an irq tracing perspective).
+ */
+ if (IS_ENABLED(CONFIG_PPC64) && unlikely(arch_irq_disabled_regs(regs)))
+ performance_monitor_exception_nmi(regs);
+ else
+ performance_monitor_exception_async(regs);
}
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 28206b1fe172..9fd06010e8b6 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -110,10 +110,6 @@ static inline void perf_read_regs(struct pt_regs *regs)
{
regs->result = 0;
}
-static inline int perf_intr_is_nmi(struct pt_regs *regs)
-{
- return 0;
-}
static inline int siar_valid(struct pt_regs *regs)
{
@@ -353,15 +349,6 @@ static inline void perf_read_regs(struct pt_regs *regs)
regs->result = use_siar;
}
-/*
- * If interrupts were soft-disabled when a PMU interrupt occurs, treat
- * it as an NMI.
- */
-static inline int perf_intr_is_nmi(struct pt_regs *regs)
-{
- return (regs->softe & IRQS_DISABLED);
-}
-
/*
* On processors like P7+ that have the SIAR-Valid bit, marked instructions
* must be sampled only if the SIAR-valid bit is set.
@@ -2279,7 +2266,6 @@ static void __perf_event_interrupt(struct pt_regs *regs)
struct perf_event *event;
unsigned long val[8];
int found, active;
- int nmi;
if (cpuhw->n_limited)
freeze_limited_counters(cpuhw, mfspr(SPRN_PMC5),
@@ -2287,18 +2273,6 @@ static void __perf_event_interrupt(struct pt_regs *regs)
perf_read_regs(regs);
- /*
- * If perf interrupts hit in a local_irq_disable (soft-masked) region,
- * we consider them as NMIs. This is required to prevent hash faults on
- * user addresses when reading callchains. See the NMI test in
- * do_hash_page.
- */
- nmi = perf_intr_is_nmi(regs);
- if (nmi)
- nmi_enter();
- else
- irq_enter();
-
/* Read all the PMCs since we'll need them a bunch of times */
for (i = 0; i < ppmu->n_counter; ++i)
val[i] = read_pmc(i + 1);
@@ -2344,8 +2318,8 @@ static void __perf_event_interrupt(struct pt_regs *regs)
}
}
}
- if (!found && !nmi && printk_ratelimit())
- printk(KERN_WARNING "Can't find PMC that caused IRQ\n");
+ if (unlikely(!found) && !arch_irq_disabled_regs(regs))
+ printk_ratelimited(KERN_WARNING "Can't find PMC that caused IRQ\n");
/*
* Reset MMCR0 to its normal value. This will set PMXE and
@@ -2355,11 +2329,6 @@ static void __perf_event_interrupt(struct pt_regs *regs)
* we get back out of this interrupt.
*/
write_mmcr0(cpuhw, cpuhw->mmcr.mmcr0);
-
- if (nmi)
- nmi_exit();
- else
- irq_exit();
}
static void perf_event_interrupt(struct pt_regs *regs)
diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c
index e0e7e276bfd2..ee721f420a7b 100644
--- a/arch/powerpc/perf/core-fsl-emb.c
+++ b/arch/powerpc/perf/core-fsl-emb.c
@@ -31,19 +31,6 @@ static atomic_t num_events;
/* Used to avoid races in calling reserve/release_pmc_hardware */
static DEFINE_MUTEX(pmc_reserve_mutex);
-/*
- * If interrupts were soft-disabled when a PMU interrupt occurs, treat
- * it as an NMI.
- */
-static inline int perf_intr_is_nmi(struct pt_regs *regs)
-{
-#ifdef __powerpc64__
- return (regs->softe & IRQS_DISABLED);
-#else
- return 0;
-#endif
-}
-
static void perf_event_interrupt(struct pt_regs *regs);
/*
@@ -659,13 +646,6 @@ static void perf_event_interrupt(struct pt_regs *regs)
struct perf_event *event;
unsigned long val;
int found = 0;
- int nmi;
-
- nmi = perf_intr_is_nmi(regs);
- if (nmi)
- nmi_enter();
- else
- irq_enter();
for (i = 0; i < ppmu->n_counter; ++i) {
event = cpuhw->event[i];
@@ -690,11 +670,6 @@ static void perf_event_interrupt(struct pt_regs *regs)
mtmsr(mfmsr() | MSR_PMM);
mtpmr(PMRN_PMGC0, PMGC0_PMIE | PMGC0_FCECE);
isync();
-
- if (nmi)
- nmi_exit();
- else
- irq_exit();
}
void hw_perf_event_setup(int cpu)
--
2.23.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox