[PATCH v2 02/14] NOT TO BE MERGED - Squash of patches 2-7 of v6 series "powerpc: interrupt wrappers"

From: Christophe Leroy
Date: Fri Jan 22 2021 - 05:11:58 EST


powerpc/32s: move DABR match out of handle_page_fault

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@xxxxxxxxxx>

powerpc/64s: move DABR match out of handle_page_fault

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@xxxxxxxxxx>
Signed-off-by: Nicholas Piggin <npiggin@xxxxxxxxx>

powerpc/64s: move the hash fault handling logic to C

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@xxxxxxxxx>

powerpc: remove arguments from fault handler functions

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@xxxxxxxxx>

powerpc: do_break get registers from regs

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@xxxxxxxxx>

powerpc: bad_page_fault get registers from regs

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@xxxxxxxxx>
Signed-off-by: Christophe Leroy <christophe.leroy@xxxxxxxxxx>
---
arch/powerpc/include/asm/asm-prototypes.h | 4 +-
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 1 +
arch/powerpc/include/asm/bug.h | 7 +-
arch/powerpc/include/asm/debug.h | 3 +-
arch/powerpc/kernel/entry_32.S | 25 +--
arch/powerpc/kernel/exceptions-64e.S | 5 +-
arch/powerpc/kernel/exceptions-64s.S | 164 +++++-------------
arch/powerpc/kernel/head_40x.S | 10 +-
arch/powerpc/kernel/head_8xx.S | 11 +-
arch/powerpc/kernel/head_book3s_32.S | 8 +-
arch/powerpc/kernel/head_booke.h | 4 +-
arch/powerpc/kernel/process.c | 7 +-
arch/powerpc/kernel/traps.c | 2 +-
arch/powerpc/mm/book3s64/hash_utils.c | 79 ++++++---
arch/powerpc/mm/book3s64/slb.c | 11 +-
arch/powerpc/mm/fault.c | 18 +-
arch/powerpc/platforms/8xx/machine_check.c | 2 +-
17 files changed, 142 insertions(+), 219 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 066b1d34c7bc..b9968e297da2 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

+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..8f09ddae9305 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -111,9 +111,10 @@
#ifndef __ASSEMBLY__

struct pt_regs;
-extern int do_page_fault(struct pt_regs *, unsigned long, unsigned long);
-extern void bad_page_fault(struct pt_regs *, unsigned long, int);
-void __bad_page_fault(struct pt_regs *regs, unsigned long address, int sig);
+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/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/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 1c9b0ccc2172..b102b40c4988 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)
@@ -670,10 +665,6 @@ 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
@@ -681,23 +672,11 @@ 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

-#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/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 74d07dc0bb48..52421042a020 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
@@ -1020,9 +1018,8 @@ 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/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e02ad6fefa46..fc793fa3fdf8 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
@@ -1437,15 +1438,30 @@ 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,r4,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: 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

@@ -1487,10 +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
@@ -1502,8 +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
@@ -1538,15 +1551,19 @@ 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
- 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

@@ -1579,10 +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
@@ -1594,8 +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
@@ -2137,9 +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)
@@ -3202,99 +3214,3 @@ 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_DABRMATCH | 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 the DABR check below */
- 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
- beq+ interrupt_return
- mr r5,r3
- addi r3,r1,STACK_FRAME_OVERHEAD
- ld r4,_DAR(r1)
- 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
- */
-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/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..7869db974185 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
@@ -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/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 54140f4927e5..281de00c2ea4 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -371,9 +371,9 @@ BEGIN_MMU_FTR_SECTION
END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
#endif
#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 */
@@ -695,11 +695,13 @@ 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:
+ 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
#ifdef CONFIG_PPC_BOOK3S_604
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/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 */

diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 3ec7b443fe6b..f3f6af3141ee 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 73b06adb6eeb..1a270cc37d97 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1512,16 +1512,42 @@ 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)
+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 = current->mm;
- unsigned int region_id = get_region_id(ea);
+ struct mm_struct *mm;
+ 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;
+ else
+ mm = current->mm;

if (dsisr & DSISR_NOHPTE)
flags |= HPTE_NOHPTE_UPDATE;
@@ -1537,13 +1563,31 @@ 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, SIGBUS);
+ }
+ err = 0;
+
+ } else if (err) {
+page_fault:
+ err = do_page_fault(regs);
+ }
+
+ return err;
}

#ifdef CONFIG_PPC_MM_SLICES
@@ -1843,27 +1887,6 @@ 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)
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index 584567970c11..c581548b533f 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, 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..e476d7701413 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;
@@ -567,7 +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);

@@ -605,7 +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;

@@ -614,5 +613,12 @@ 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);
}
+
+#ifdef CONFIG_PPC_BOOK3S_64
+void do_bad_page_fault_segv(struct pt_regs *regs)
+{
+ bad_page_fault(regs, SIGSEGV);
+}
+#endif
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;
--
2.25.0