LinuxPPC-Dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v6 13/39] powerpc/traps: add NOKPROBE_SYMBOL for sreset and mce
From: Nicholas Piggin @ 2021-01-15 16:49 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-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 f3f6af3141ee..738370519937 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 v6 14/39] powerpc/perf: move perf irq/nmi handling details into traps.c
From: Nicholas Piggin @ 2021-01-15 16:49 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-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 738370519937..bd55f201115b 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

* [PATCH v6 15/39] powerpc/time: move timer_broadcast_interrupt prototype to asm/time.h
From: Nicholas Piggin @ 2021-01-15 16:49 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

Interrupt handler prototypes are going to be rearranged in a
future patch, so tidy this out of the way first.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/hw_irq.h | 1 -
 arch/powerpc/include/asm/time.h   | 2 ++
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 0363734ff56e..e5def36212cf 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -54,7 +54,6 @@ extern void replay_system_reset(void);
 extern void replay_soft_interrupts(void);
 
 extern void timer_interrupt(struct pt_regs *);
-extern void timer_broadcast_interrupt(void);
 extern void performance_monitor_exception(struct pt_regs *regs);
 extern void WatchdogException(struct pt_regs *regs);
 extern void unknown_exception(struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 8f789b597bae..8dd3cdb25338 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -102,6 +102,8 @@ DECLARE_PER_CPU(u64, decrementers_next_tb);
 /* Convert timebase ticks to nanoseconds */
 unsigned long long tb_to_ns(unsigned long long tb_ticks);
 
+void timer_broadcast_interrupt(void);
+
 /* SPLPAR */
 void accumulate_stolen_time(void);
 
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 16/39] powerpc: add and use unknown_async_exception
From: Nicholas Piggin @ 2021-01-15 16:49 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

This is currently the same as unknown_exception, but it will diverge
after interrupt wrappers are added and code moved out of asm into the
wrappers (e.g., async handlers will check FINISH_NAP).

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/hw_irq.h    |  1 +
 arch/powerpc/kernel/exceptions-64s.S |  4 ++--
 arch/powerpc/kernel/head_book3s_32.S |  6 +++---
 arch/powerpc/kernel/traps.c          | 12 ++++++++++++
 4 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index e5def36212cf..75c2b137fc00 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -57,6 +57,7 @@ extern void timer_interrupt(struct pt_regs *);
 extern void performance_monitor_exception(struct pt_regs *regs);
 extern void WatchdogException(struct pt_regs *regs);
 extern void unknown_exception(struct pt_regs *regs);
+void unknown_async_exception(struct pt_regs *regs);
 
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e69a912c2cc6..fe33197ea8fb 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1926,7 +1926,7 @@ EXC_COMMON_BEGIN(doorbell_super_common)
 #ifdef CONFIG_PPC_DOORBELL
 	bl	doorbell_exception
 #else
-	bl	unknown_exception
+	bl	unknown_async_exception
 #endif
 	b	interrupt_return
 
@@ -2312,7 +2312,7 @@ EXC_COMMON_BEGIN(h_doorbell_common)
 #ifdef CONFIG_PPC_DOORBELL
 	bl	doorbell_exception
 #else
-	bl	unknown_exception
+	bl	unknown_async_exception
 #endif
 	b	interrupt_return
 
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 94ad1372c490..9b4d5432e2db 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -238,8 +238,8 @@ __secondary_hold_acknowledge:
 
 /* System reset */
 /* core99 pmac starts the seconary here by changing the vector, and
-   putting it back to what it was (unknown_exception) when done.  */
-	EXCEPTION(0x100, Reset, unknown_exception, EXC_XFER_STD)
+   putting it back to what it was (unknown_async_exception) when done.  */
+	EXCEPTION(0x100, Reset, unknown_async_exception, EXC_XFER_STD)
 
 /* Machine check */
 /*
@@ -631,7 +631,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
 #endif
 
 #ifndef CONFIG_TAU_INT
-#define TAUException	unknown_exception
+#define TAUException	unknown_async_exception
 #endif
 
 	EXCEPTION(0x1300, Trap_13, instruction_breakpoint_exception, EXC_XFER_STD)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index bd55f201115b..639bcafbad5e 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1073,6 +1073,18 @@ void unknown_exception(struct pt_regs *regs)
 	exception_exit(prev_state);
 }
 
+void unknown_async_exception(struct pt_regs *regs)
+{
+	enum ctx_state prev_state = exception_enter();
+
+	printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
+	       regs->nip, regs->msr, regs->trap);
+
+	_exception(SIGTRAP, regs, TRAP_UNK, 0);
+
+	exception_exit(prev_state);
+}
+
 void instruction_breakpoint_exception(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 17/39] powerpc/fsl_booke/32: CacheLockingException remove args
From: Nicholas Piggin @ 2021-01-15 16:49 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-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 639bcafbad5e..1af52a4bce1f 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -2105,9 +2105,10 @@ 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 v6 18/39] powerpc: DebugException remove args
From: Nicholas Piggin @ 2021-01-15 16:49 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-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 52421042a020..003999c7836c 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 1af52a4bce1f..6691774fe1fb 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -2000,8 +2000,10 @@ 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 v6 19/39] powerpc/cell: tidy up pervasive declarations
From: Nicholas Piggin @ 2021-01-15 16:49 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

These are declared in ras.h and defined in ras.c so remove them from
pervasive.h

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/platforms/cell/pervasive.c | 1 +
 arch/powerpc/platforms/cell/pervasive.h | 3 ---
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/powerpc/platforms/cell/pervasive.c b/arch/powerpc/platforms/cell/pervasive.c
index 9068edef71f7..5b9a7e9f144b 100644
--- a/arch/powerpc/platforms/cell/pervasive.c
+++ b/arch/powerpc/platforms/cell/pervasive.c
@@ -25,6 +25,7 @@
 #include <asm/cpu_has_feature.h>
 
 #include "pervasive.h"
+#include "ras.h"
 
 static void cbe_power_save(void)
 {
diff --git a/arch/powerpc/platforms/cell/pervasive.h b/arch/powerpc/platforms/cell/pervasive.h
index c6fccad6caee..0da74ab10716 100644
--- a/arch/powerpc/platforms/cell/pervasive.h
+++ b/arch/powerpc/platforms/cell/pervasive.h
@@ -13,9 +13,6 @@
 #define PERVASIVE_H
 
 extern void cbe_pervasive_init(void);
-extern void cbe_system_error_exception(struct pt_regs *regs);
-extern void cbe_maintenance_exception(struct pt_regs *regs);
-extern void cbe_thermal_exception(struct pt_regs *regs);
 
 #ifdef CONFIG_PPC_IBM_CELL_RESETBUTTON
 extern int cbe_sysreset_hack(void);
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 20/39] powerpc: introduce die_mce
From: Nicholas Piggin @ 2021-01-15 16:49 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

As explained by commit daf00ae71dad ("powerpc/traps: restore
recoverability of machine_check interrupts"), die() can't be called from
within nmi_enter to nicely kill a process context that was interrupted.
nmi_exit must be called first.

This adds a function die_mce which takes care of this for machine check
handlers.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/bug.h        |  1 +
 arch/powerpc/kernel/traps.c           | 21 +++++++++++++++------
 arch/powerpc/platforms/powernv/opal.c |  2 +-
 arch/powerpc/platforms/pseries/ras.c  |  2 +-
 4 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 8f09ddae9305..c10ae0a9bbaf 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -118,6 +118,7 @@ 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);
+void die_mce(const char *str, struct pt_regs *regs, long err);
 extern bool die_will_crash(void);
 extern void panic_flush_kmsg_start(void);
 extern void panic_flush_kmsg_end(void);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 6691774fe1fb..f9ef183a5454 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -789,6 +789,19 @@ int machine_check_generic(struct pt_regs *regs)
 }
 #endif /* everything else */
 
+void die_mce(const char *str, struct pt_regs *regs, long err)
+{
+	/*
+	 * The machine check wants to kill the interrupted context, but
+	 * do_exit() checks for in_interrupt() and panics in that case, so
+	 * exit the irq/nmi before calling die.
+	 */
+	if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+		nmi_exit();
+	die(str, regs, err);
+}
+NOKPROBE_SYMBOL(die_mce);
+
 void machine_check_exception(struct pt_regs *regs)
 {
 	int recover = 0;
@@ -831,15 +844,11 @@ void machine_check_exception(struct pt_regs *regs)
 	if (check_io_access(regs))
 		goto bail;
 
-	if (nmi) nmi_exit();
-
-	die("Machine check", regs, SIGBUS);
+	die_mce("Machine check", regs, SIGBUS);
 
 	/* Must die if the interrupt is not recoverable */
 	if (!(regs->msr & MSR_RI))
-		die("Unrecoverable Machine check", regs, SIGBUS);
-
-	return;
+		die_mce("Unrecoverable Machine check", regs, SIGBUS);
 
 bail:
 	if (nmi) nmi_exit();
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index c61c3b62c8c6..303d7c775740 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -624,7 +624,7 @@ static int opal_recover_mce(struct pt_regs *regs,
 			 */
 			recovered = 0;
 		} else {
-			die("Machine check", regs, SIGBUS);
+			die_mce("Machine check", regs, SIGBUS);
 			recovered = 1;
 		}
 	}
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 149cec2212e6..2d9f985fd13a 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -813,7 +813,7 @@ static int recover_mce(struct pt_regs *regs, struct machine_check_event *evt)
 			 */
 			recovered = 0;
 		} else {
-			die("Machine check", regs, SIGBUS);
+			die_mce("Machine check", regs, SIGBUS);
 			recovered = 1;
 		}
 	}
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 21/39] powerpc/mce: ensure machine check handler always tests RI
From: Nicholas Piggin @ 2021-01-15 16:49 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

A machine check that is handled must still check MSR[RI] for
recoverability of the interrupted context. Without this patch
it's possible for a handled machine check to return to a
context where it has clobbered live registers.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/traps.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index f9ef183a5454..3a8699995a77 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -846,11 +846,11 @@ void machine_check_exception(struct pt_regs *regs)
 
 	die_mce("Machine check", regs, SIGBUS);
 
+bail:
 	/* Must die if the interrupt is not recoverable */
 	if (!(regs->msr & MSR_RI))
 		die_mce("Unrecoverable Machine check", regs, SIGBUS);
 
-bail:
 	if (nmi) nmi_exit();
 }
 NOKPROBE_SYMBOL(machine_check_exception);
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 22/39] powerpc: improve handling of unrecoverable system reset
From: Nicholas Piggin @ 2021-01-15 16:49 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

If an unrecoverable system reset hits in process context, the system
does not have to panic. Similar to machine check, call nmi_exit()
before die().

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/traps.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 3a8699995a77..f70d3f6174c8 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -503,8 +503,11 @@ void system_reset_exception(struct pt_regs *regs)
 		die("Unrecoverable nested System Reset", regs, SIGABRT);
 #endif
 	/* Must die if the interrupt is not recoverable */
-	if (!(regs->msr & MSR_RI))
+	if (!(regs->msr & MSR_RI)) {
+		/* For the reason explained in die_mce, nmi_exit before die */
+		nmi_exit();
 		die("Unrecoverable System Reset", regs, SIGABRT);
+	}
 
 	if (saved_hsrrs) {
 		mtspr(SPRN_HSRR0, hsrr0);
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 23/39] powerpc: interrupt handler wrapper functions
From: Nicholas Piggin @ 2021-01-15 16:49 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

Add wrapper functions (derived from x86 macros) for interrupt handler
functions. This allows interrupt entry code to be written in C.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/interrupt.h | 169 +++++++++++++++++++++++++++
 1 file changed, 169 insertions(+)
 create mode 100644 arch/powerpc/include/asm/interrupt.h

diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
new file mode 100644
index 000000000000..5e2526aacc52
--- /dev/null
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -0,0 +1,169 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ASM_POWERPC_INTERRUPT_H
+#define _ASM_POWERPC_INTERRUPT_H
+
+#include <linux/context_tracking.h>
+#include <asm/ftrace.h>
+
+/**
+ * DECLARE_INTERRUPT_HANDLER_RAW - Declare raw interrupt handler function
+ * @func:	Function name of the entry point
+ * @returns:	Returns a value back to asm caller
+ */
+#define DECLARE_INTERRUPT_HANDLER_RAW(func)				\
+	__visible long func(struct pt_regs *regs)
+
+/**
+ * DEFINE_INTERRUPT_HANDLER_RAW - Define raw interrupt handler function
+ * @func:	Function name of the entry point
+ * @returns:	Returns a value back to asm caller
+ *
+ * @func is called from ASM entry code.
+ *
+ * This is a plain function which does no tracing, reconciling, etc.
+ * The macro is written so it acts as function definition. Append the
+ * body with a pair of curly brackets.
+ *
+ * raw interrupt handlers must not enable or disable interrupts, or
+ * schedule, tracing and instrumentation (ftrace, lockdep, etc) would
+ * not be advisable either, although may be possible in a pinch, the
+ * trace will look odd at least.
+ *
+ * A raw handler may call one of the other interrupt handler functions
+ * to be converted into that interrupt context without these restrictions.
+ *
+ * On PPC64, _RAW handlers may return with fast_interrupt_return.
+ *
+ * Specific handlers may have additional restrictions.
+ */
+#define DEFINE_INTERRUPT_HANDLER_RAW(func)				\
+static __always_inline long ____##func(struct pt_regs *regs);		\
+									\
+__visible noinstr long func(struct pt_regs *regs)			\
+{									\
+	long ret;							\
+									\
+	ret = ____##func (regs);					\
+									\
+	return ret;							\
+}									\
+									\
+static __always_inline long ____##func(struct pt_regs *regs)
+
+/**
+ * DECLARE_INTERRUPT_HANDLER - Declare synchronous interrupt handler function
+ * @func:	Function name of the entry point
+ */
+#define DECLARE_INTERRUPT_HANDLER(func)					\
+	__visible void func(struct pt_regs *regs)
+
+/**
+ * DEFINE_INTERRUPT_HANDLER - Define synchronous interrupt handler function
+ * @func:	Function name of the entry point
+ *
+ * @func is called from ASM entry code.
+ *
+ * The macro is written so it acts as function definition. Append the
+ * body with a pair of curly brackets.
+ */
+#define DEFINE_INTERRUPT_HANDLER(func)					\
+static __always_inline void ____##func(struct pt_regs *regs);		\
+									\
+__visible noinstr void func(struct pt_regs *regs)			\
+{									\
+	____##func (regs);						\
+}									\
+									\
+static __always_inline void ____##func(struct pt_regs *regs)
+
+/**
+ * DECLARE_INTERRUPT_HANDLER_RET - Declare synchronous interrupt handler function
+ * @func:	Function name of the entry point
+ * @returns:	Returns a value back to asm caller
+ */
+#define DECLARE_INTERRUPT_HANDLER_RET(func)				\
+	__visible long func(struct pt_regs *regs)
+
+/**
+ * DEFINE_INTERRUPT_HANDLER_RET - Define synchronous interrupt handler function
+ * @func:	Function name of the entry point
+ * @returns:	Returns a value back to asm caller
+ *
+ * @func is called from ASM entry code.
+ *
+ * The macro is written so it acts as function definition. Append the
+ * body with a pair of curly brackets.
+ */
+#define DEFINE_INTERRUPT_HANDLER_RET(func)				\
+static __always_inline long ____##func(struct pt_regs *regs);		\
+									\
+__visible noinstr long func(struct pt_regs *regs)			\
+{									\
+	long ret;							\
+									\
+	ret = ____##func (regs);					\
+									\
+	return ret;							\
+}									\
+									\
+static __always_inline long ____##func(struct pt_regs *regs)
+
+/**
+ * DECLARE_INTERRUPT_HANDLER_ASYNC - Declare asynchronous interrupt handler function
+ * @func:	Function name of the entry point
+ */
+#define DECLARE_INTERRUPT_HANDLER_ASYNC(func)				\
+	__visible void func(struct pt_regs *regs)
+
+/**
+ * DEFINE_INTERRUPT_HANDLER_ASYNC - Define asynchronous interrupt handler function
+ * @func:	Function name of the entry point
+ *
+ * @func is called from ASM entry code.
+ *
+ * The macro is written so it acts as function definition. Append the
+ * body with a pair of curly brackets.
+ */
+#define DEFINE_INTERRUPT_HANDLER_ASYNC(func)				\
+static __always_inline void ____##func(struct pt_regs *regs);		\
+									\
+__visible noinstr void func(struct pt_regs *regs)			\
+{									\
+	____##func (regs);						\
+}									\
+									\
+static __always_inline void ____##func(struct pt_regs *regs)
+
+/**
+ * DECLARE_INTERRUPT_HANDLER_NMI - Declare NMI interrupt handler function
+ * @func:	Function name of the entry point
+ * @returns:	Returns a value back to asm caller
+ */
+#define DECLARE_INTERRUPT_HANDLER_NMI(func)				\
+	__visible long func(struct pt_regs *regs)
+
+/**
+ * DEFINE_INTERRUPT_HANDLER_NMI - Define NMI interrupt handler function
+ * @func:	Function name of the entry point
+ * @returns:	Returns a value back to asm caller
+ *
+ * @func is called from ASM entry code.
+ *
+ * The macro is written so it acts as function definition. Append the
+ * body with a pair of curly brackets.
+ */
+#define DEFINE_INTERRUPT_HANDLER_NMI(func)				\
+static __always_inline long ____##func(struct pt_regs *regs);		\
+									\
+__visible noinstr long func(struct pt_regs *regs)			\
+{									\
+	long ret;							\
+									\
+	ret = ____##func (regs);					\
+									\
+	return ret;							\
+}									\
+									\
+static __always_inline long ____##func(struct pt_regs *regs)
+
+#endif /* _ASM_POWERPC_INTERRUPT_H */
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 24/39] powerpc: add interrupt wrapper entry / exit stub functions
From: Nicholas Piggin @ 2021-01-15 16:49 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

These will be used by subsequent patches.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/interrupt.h | 66 ++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)

diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 5e2526aacc52..3df1921cfda3 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -5,6 +5,50 @@
 #include <linux/context_tracking.h>
 #include <asm/ftrace.h>
 
+struct interrupt_state {
+};
+
+static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
+{
+}
+
+/*
+ * Care should be taken to note that interrupt_exit_prepare and
+ * interrupt_async_exit_prepare do not necessarily return immediately to
+ * regs context (e.g., if regs is usermode, we don't necessarily return to
+ * user mode). Other interrupts might be taken between here and return,
+ * context switch / preemption may occur in the exit path after this, or a
+ * signal may be delivered, etc.
+ *
+ * The real interrupt exit code is platform specific, e.g.,
+ * interrupt_exit_user_prepare / interrupt_exit_kernel_prepare for 64s.
+ *
+ * However interrupt_nmi_exit_prepare does return directly to regs, because
+ * NMIs do not do "exit work" or replay soft-masked interrupts.
+ */
+static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
+{
+}
+
+static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
+{
+}
+
+static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
+{
+}
+
+struct interrupt_nmi_state {
+};
+
+static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
+{
+}
+
+static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
+{
+}
+
 /**
  * DECLARE_INTERRUPT_HANDLER_RAW - Declare raw interrupt handler function
  * @func:	Function name of the entry point
@@ -71,7 +115,13 @@ static __always_inline void ____##func(struct pt_regs *regs);		\
 									\
 __visible noinstr void func(struct pt_regs *regs)			\
 {									\
+	struct interrupt_state state;					\
+									\
+	interrupt_enter_prepare(regs, &state);				\
+									\
 	____##func (regs);						\
+									\
+	interrupt_exit_prepare(regs, &state);				\
 }									\
 									\
 static __always_inline void ____##func(struct pt_regs *regs)
@@ -99,10 +149,15 @@ static __always_inline long ____##func(struct pt_regs *regs);		\
 									\
 __visible noinstr long func(struct pt_regs *regs)			\
 {									\
+	struct interrupt_state state;					\
 	long ret;							\
 									\
+	interrupt_enter_prepare(regs, &state);				\
+									\
 	ret = ____##func (regs);					\
 									\
+	interrupt_exit_prepare(regs, &state);				\
+									\
 	return ret;							\
 }									\
 									\
@@ -129,7 +184,13 @@ static __always_inline void ____##func(struct pt_regs *regs);		\
 									\
 __visible noinstr void func(struct pt_regs *regs)			\
 {									\
+	struct interrupt_state state;					\
+									\
+	interrupt_async_enter_prepare(regs, &state);			\
+									\
 	____##func (regs);						\
+									\
+	interrupt_async_exit_prepare(regs, &state);			\
 }									\
 									\
 static __always_inline void ____##func(struct pt_regs *regs)
@@ -157,10 +218,15 @@ static __always_inline long ____##func(struct pt_regs *regs);		\
 									\
 __visible noinstr long func(struct pt_regs *regs)			\
 {									\
+	struct interrupt_nmi_state state;				\
 	long ret;							\
 									\
+	interrupt_nmi_enter_prepare(regs, &state);			\
+									\
 	ret = ____##func (regs);					\
 									\
+	interrupt_nmi_exit_prepare(regs, &state);			\
+									\
 	return ret;							\
 }									\
 									\
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 25/39] powerpc: convert interrupt handlers to use wrappers
From: Nicholas Piggin @ 2021-01-15 16:49 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/asm-prototypes.h     | 29 -------
 arch/powerpc/include/asm/book3s/64/mmu-hash.h |  1 -
 arch/powerpc/include/asm/debug.h              |  3 -
 arch/powerpc/include/asm/hw_irq.h             |  9 --
 arch/powerpc/include/asm/interrupt.h          | 66 +++++++++++++++
 arch/powerpc/kernel/dbell.c                   |  6 +-
 arch/powerpc/kernel/irq.c                     |  3 +-
 arch/powerpc/kernel/mce.c                     |  5 +-
 arch/powerpc/kernel/process.c                 |  3 +-
 arch/powerpc/kernel/syscall_64.c              |  1 +
 arch/powerpc/kernel/tau_6xx.c                 |  2 +-
 arch/powerpc/kernel/time.c                    |  3 +-
 arch/powerpc/kernel/traps.c                   | 84 +++++++++++--------
 arch/powerpc/kernel/watchdog.c                |  7 +-
 arch/powerpc/kvm/book3s_hv.c                  |  1 +
 arch/powerpc/kvm/book3s_hv_builtin.c          |  1 +
 arch/powerpc/kvm/booke.c                      |  1 +
 arch/powerpc/mm/book3s64/hash_utils.c         | 11 ++-
 arch/powerpc/mm/book3s64/slb.c                |  7 +-
 arch/powerpc/mm/fault.c                       |  5 +-
 arch/powerpc/platforms/cell/ras.c             |  6 +-
 arch/powerpc/platforms/cell/ras.h             |  9 +-
 arch/powerpc/platforms/powernv/idle.c         |  1 +
 23 files changed, 164 insertions(+), 100 deletions(-)

diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 22c9d08fa3a4..939f3c94c8f3 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -56,35 +56,6 @@ int exit_vmx_usercopy(void);
 int enter_vmx_ops(void);
 void *exit_vmx_ops(void *dest);
 
-/* Traps */
-long machine_check_early(struct pt_regs *regs);
-long hmi_exception_realmode(struct pt_regs *regs);
-void SMIException(struct pt_regs *regs);
-void handle_hmi_exception(struct pt_regs *regs);
-void instruction_breakpoint_exception(struct pt_regs *regs);
-void RunModeException(struct pt_regs *regs);
-void single_step_exception(struct pt_regs *regs);
-void program_check_exception(struct pt_regs *regs);
-void alignment_exception(struct pt_regs *regs);
-void StackOverflow(struct pt_regs *regs);
-void stack_overflow_exception(struct pt_regs *regs);
-void kernel_fp_unavailable_exception(struct pt_regs *regs);
-void altivec_unavailable_exception(struct pt_regs *regs);
-void vsx_unavailable_exception(struct pt_regs *regs);
-void fp_unavailable_tm(struct pt_regs *regs);
-void altivec_unavailable_tm(struct pt_regs *regs);
-void vsx_unavailable_tm(struct pt_regs *regs);
-void facility_unavailable_exception(struct pt_regs *regs);
-void TAUException(struct pt_regs *regs);
-void altivec_assist_exception(struct pt_regs *regs);
-void unrecoverable_exception(struct pt_regs *regs);
-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);
-void do_bad_slb_fault(struct pt_regs *regs);
-
 /* signals, syscalls and interrupts */
 long sys_swapcontext(struct ucontext __user *old_ctx,
 		    struct ucontext __user *new_ctx,
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index b9968e297da2..066b1d34c7bc 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -454,7 +454,6 @@ 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/debug.h b/arch/powerpc/include/asm/debug.h
index 0550eceab3ca..86a14736c76c 100644
--- a/arch/powerpc/include/asm/debug.h
+++ b/arch/powerpc/include/asm/debug.h
@@ -50,9 +50,6 @@ bool ppc_breakpoint_available(void);
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 extern void do_send_trap(struct pt_regs *regs, unsigned long address,
 			 unsigned long error_code, int brkpt);
-#else
-
-void do_break(struct pt_regs *regs);
 #endif
 
 #endif /* _ASM_POWERPC_DEBUG_H */
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 75c2b137fc00..614957f74cee 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -50,15 +50,6 @@
 
 #ifndef __ASSEMBLY__
 
-extern void replay_system_reset(void);
-extern void replay_soft_interrupts(void);
-
-extern void timer_interrupt(struct pt_regs *);
-extern void performance_monitor_exception(struct pt_regs *regs);
-extern void WatchdogException(struct pt_regs *regs);
-extern void unknown_exception(struct pt_regs *regs);
-void unknown_async_exception(struct pt_regs *regs);
-
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 3df1921cfda3..4ffbd3d75324 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -232,4 +232,70 @@ __visible noinstr long func(struct pt_regs *regs)			\
 									\
 static __always_inline long ____##func(struct pt_regs *regs)
 
+
+/* Interrupt handlers */
+/* kernel/traps.c */
+DECLARE_INTERRUPT_HANDLER_NMI(system_reset_exception);
+#ifdef CONFIG_PPC_BOOK3S_64
+DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception);
+#else
+DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception);
+#endif
+DECLARE_INTERRUPT_HANDLER(SMIException);
+DECLARE_INTERRUPT_HANDLER(handle_hmi_exception);
+DECLARE_INTERRUPT_HANDLER(unknown_exception);
+DECLARE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception);
+DECLARE_INTERRUPT_HANDLER(instruction_breakpoint_exception);
+DECLARE_INTERRUPT_HANDLER(RunModeException);
+DECLARE_INTERRUPT_HANDLER(single_step_exception);
+DECLARE_INTERRUPT_HANDLER(program_check_exception);
+DECLARE_INTERRUPT_HANDLER(emulation_assist_interrupt);
+DECLARE_INTERRUPT_HANDLER(alignment_exception);
+DECLARE_INTERRUPT_HANDLER(StackOverflow);
+DECLARE_INTERRUPT_HANDLER(stack_overflow_exception);
+DECLARE_INTERRUPT_HANDLER(kernel_fp_unavailable_exception);
+DECLARE_INTERRUPT_HANDLER(altivec_unavailable_exception);
+DECLARE_INTERRUPT_HANDLER(vsx_unavailable_exception);
+DECLARE_INTERRUPT_HANDLER(facility_unavailable_exception);
+DECLARE_INTERRUPT_HANDLER(fp_unavailable_tm);
+DECLARE_INTERRUPT_HANDLER(altivec_unavailable_tm);
+DECLARE_INTERRUPT_HANDLER(vsx_unavailable_tm);
+DECLARE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi);
+DECLARE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async);
+DECLARE_INTERRUPT_HANDLER_RAW(performance_monitor_exception);
+DECLARE_INTERRUPT_HANDLER(DebugException);
+DECLARE_INTERRUPT_HANDLER(altivec_assist_exception);
+DECLARE_INTERRUPT_HANDLER(CacheLockingException);
+DECLARE_INTERRUPT_HANDLER(SPEFloatingPointException);
+DECLARE_INTERRUPT_HANDLER(SPEFloatingPointRoundException);
+DECLARE_INTERRUPT_HANDLER(unrecoverable_exception);
+DECLARE_INTERRUPT_HANDLER(WatchdogException);
+DECLARE_INTERRUPT_HANDLER(kernel_bad_stack);
+
+/* slb.c */
+DECLARE_INTERRUPT_HANDLER_RAW(do_slb_fault);
+DECLARE_INTERRUPT_HANDLER(do_bad_slb_fault);
+
+/* hash_utils.c */
+DECLARE_INTERRUPT_HANDLER_RAW(do_hash_fault);
+
+/* fault.c */
+DECLARE_INTERRUPT_HANDLER_RET(do_page_fault);
+DECLARE_INTERRUPT_HANDLER(do_bad_page_fault_segv);
+
+/* process.c */
+DECLARE_INTERRUPT_HANDLER(do_break);
+
+/* time.c */
+DECLARE_INTERRUPT_HANDLER_ASYNC(timer_interrupt);
+
+/* mce.c */
+DECLARE_INTERRUPT_HANDLER_NMI(machine_check_early);
+DECLARE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode);
+
+DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException);
+
+void replay_system_reset(void);
+void replay_soft_interrupts(void);
+
 #endif /* _ASM_POWERPC_INTERRUPT_H */
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 52680cf07c9d..6a7ecfca5c3b 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -12,13 +12,14 @@
 #include <linux/hardirq.h>
 
 #include <asm/dbell.h>
+#include <asm/interrupt.h>
 #include <asm/irq_regs.h>
 #include <asm/kvm_ppc.h>
 #include <asm/trace.h>
 
 #ifdef CONFIG_SMP
 
-void doorbell_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
@@ -39,9 +40,8 @@ void doorbell_exception(struct pt_regs *regs)
 	set_irq_regs(old_regs);
 }
 #else /* CONFIG_SMP */
-void doorbell_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
 {
 	printk(KERN_WARNING "Received doorbell on non-smp system\n");
 }
 #endif /* CONFIG_SMP */
-
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 6b1eca53e36c..2055d204d08e 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -54,6 +54,7 @@
 #include <linux/pgtable.h>
 
 #include <linux/uaccess.h>
+#include <asm/interrupt.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/cache.h>
@@ -665,7 +666,7 @@ void __do_irq(struct pt_regs *regs)
 	irq_exit();
 }
 
-void do_IRQ(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	void *cursp, *irqsp, *sirqsp;
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 9f3e133b57b7..54269947113d 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -18,6 +18,7 @@
 #include <linux/extable.h>
 #include <linux/ftrace.h>
 
+#include <asm/interrupt.h>
 #include <asm/machdep.h>
 #include <asm/mce.h>
 #include <asm/nmi.h>
@@ -588,7 +589,7 @@ EXPORT_SYMBOL_GPL(machine_check_print_event_info);
  *
  * regs->nip and regs->msr contains srr0 and ssr1.
  */
-long notrace machine_check_early(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_NMI(machine_check_early)
 {
 	long handled = 0;
 	u8 ftrace_enabled = this_cpu_get_ftrace_enabled();
@@ -722,7 +723,7 @@ long hmi_handle_debugtrig(struct pt_regs *regs)
 /*
  * Return values:
  */
-long hmi_exception_realmode(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode)
 {	
 	int ret;
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 4f0f81e9420b..8520ed5ae144 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -41,6 +41,7 @@
 #include <linux/pkeys.h>
 #include <linux/seq_buf.h>
 
+#include <asm/interrupt.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
@@ -659,7 +660,7 @@ static void do_break_handler(struct pt_regs *regs)
 	}
 }
 
-void do_break(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(do_break)
 {
 	current->thread.trap_nr = TRAP_HWBKPT;
 	if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, regs->dsisr,
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 7c85ed04a164..dd87b2118620 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -5,6 +5,7 @@
 #include <asm/kup.h>
 #include <asm/cputime.h>
 #include <asm/hw_irq.h>
+#include <asm/interrupt.h>
 #include <asm/kprobes.h>
 #include <asm/paca.h>
 #include <asm/ptrace.h>
diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c
index 0b4694b8d248..46b2e5de4ef5 100644
--- a/arch/powerpc/kernel/tau_6xx.c
+++ b/arch/powerpc/kernel/tau_6xx.c
@@ -100,7 +100,7 @@ static void TAUupdate(int cpu)
  * with interrupts disabled
  */
 
-void TAUException(struct pt_regs * regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(TAUException)
 {
 	int cpu = smp_processor_id();
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 67feb3524460..435a251247ed 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -56,6 +56,7 @@
 #include <linux/processor.h>
 #include <asm/trace.h>
 
+#include <asm/interrupt.h>
 #include <asm/io.h>
 #include <asm/nvram.h>
 #include <asm/cache.h>
@@ -570,7 +571,7 @@ void arch_irq_work_raise(void)
  * timer_interrupt - gets called when the decrementer overflows,
  * with interrupts disabled.
  */
-void timer_interrupt(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
 {
 	struct clock_event_device *evt = this_cpu_ptr(&decrementers);
 	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index f70d3f6174c8..b000956cde3f 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -41,6 +41,7 @@
 #include <asm/emulated_ops.h>
 #include <linux/uaccess.h>
 #include <asm/debugfs.h>
+#include <asm/interrupt.h>
 #include <asm/io.h>
 #include <asm/machdep.h>
 #include <asm/rtas.h>
@@ -430,8 +431,7 @@ void hv_nmi_check_nonrecoverable(struct pt_regs *regs)
 	regs->msr &= ~MSR_RI;
 #endif
 }
-
-void system_reset_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
 {
 	unsigned long hsrr0, hsrr1;
 	bool saved_hsrrs = false;
@@ -519,6 +519,8 @@ void system_reset_exception(struct pt_regs *regs)
 	this_cpu_set_ftrace_enabled(ftrace_enabled);
 
 	/* What should we do here? We could issue a shutdown or hard reset. */
+
+	return 0;
 }
 NOKPROBE_SYMBOL(system_reset_exception);
 
@@ -805,7 +807,11 @@ void die_mce(const char *str, struct pt_regs *regs, long err)
 }
 NOKPROBE_SYMBOL(die_mce);
 
-void machine_check_exception(struct pt_regs *regs)
+#ifdef CONFIG_PPC_BOOK3S_64
+DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception)
+#else
+DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
+#endif
 {
 	int recover = 0;
 
@@ -855,10 +861,16 @@ void machine_check_exception(struct pt_regs *regs)
 		die_mce("Unrecoverable Machine check", regs, SIGBUS);
 
 	if (nmi) nmi_exit();
+
+#ifdef CONFIG_PPC_BOOK3S_64
+	return;
+#else
+	return 0;
+#endif
 }
 NOKPROBE_SYMBOL(machine_check_exception);
 
-void SMIException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(SMIException) /* async? */
 {
 	die("System Management Interrupt", regs, SIGABRT);
 }
@@ -1044,7 +1056,7 @@ static void p9_hmi_special_emu(struct pt_regs *regs)
 }
 #endif /* CONFIG_VSX */
 
-void handle_hmi_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
 {
 	struct pt_regs *old_regs;
 
@@ -1073,7 +1085,7 @@ void handle_hmi_exception(struct pt_regs *regs)
 	set_irq_regs(old_regs);
 }
 
-void unknown_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(unknown_exception)
 {
 	enum ctx_state prev_state = exception_enter();
 
@@ -1085,7 +1097,7 @@ void unknown_exception(struct pt_regs *regs)
 	exception_exit(prev_state);
 }
 
-void unknown_async_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception)
 {
 	enum ctx_state prev_state = exception_enter();
 
@@ -1097,7 +1109,7 @@ void unknown_async_exception(struct pt_regs *regs)
 	exception_exit(prev_state);
 }
 
-void instruction_breakpoint_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(instruction_breakpoint_exception)
 {
 	enum ctx_state prev_state = exception_enter();
 
@@ -1112,12 +1124,12 @@ void instruction_breakpoint_exception(struct pt_regs *regs)
 	exception_exit(prev_state);
 }
 
-void RunModeException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(RunModeException)
 {
 	_exception(SIGTRAP, regs, TRAP_UNK, 0);
 }
 
-void single_step_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(single_step_exception)
 {
 	enum ctx_state prev_state = exception_enter();
 
@@ -1462,7 +1474,7 @@ static int emulate_math(struct pt_regs *regs)
 static inline int emulate_math(struct pt_regs *regs) { return -1; }
 #endif
 
-void program_check_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(program_check_exception)
 {
 	enum ctx_state prev_state = exception_enter();
 	unsigned int reason = get_reason(regs);
@@ -1587,14 +1599,14 @@ NOKPROBE_SYMBOL(program_check_exception);
  * This occurs when running in hypervisor mode on POWER6 or later
  * and an illegal instruction is encountered.
  */
-void emulation_assist_interrupt(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(emulation_assist_interrupt)
 {
 	regs->msr |= REASON_ILLEGAL;
 	program_check_exception(regs);
 }
 NOKPROBE_SYMBOL(emulation_assist_interrupt);
 
-void alignment_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(alignment_exception)
 {
 	enum ctx_state prev_state = exception_enter();
 	int sig, code, fixed = 0;
@@ -1644,7 +1656,7 @@ void alignment_exception(struct pt_regs *regs)
 	exception_exit(prev_state);
 }
 
-void StackOverflow(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(StackOverflow)
 {
 	pr_crit("Kernel stack overflow in process %s[%d], r1=%lx\n",
 		current->comm, task_pid_nr(current), regs->gpr[1]);
@@ -1653,7 +1665,7 @@ void StackOverflow(struct pt_regs *regs)
 	panic("kernel stack overflow");
 }
 
-void stack_overflow_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(stack_overflow_exception)
 {
 	enum ctx_state prev_state = exception_enter();
 
@@ -1662,7 +1674,7 @@ void stack_overflow_exception(struct pt_regs *regs)
 	exception_exit(prev_state);
 }
 
-void kernel_fp_unavailable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(kernel_fp_unavailable_exception)
 {
 	enum ctx_state prev_state = exception_enter();
 
@@ -1673,7 +1685,7 @@ void kernel_fp_unavailable_exception(struct pt_regs *regs)
 	exception_exit(prev_state);
 }
 
-void altivec_unavailable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(altivec_unavailable_exception)
 {
 	enum ctx_state prev_state = exception_enter();
 
@@ -1692,7 +1704,7 @@ void altivec_unavailable_exception(struct pt_regs *regs)
 	exception_exit(prev_state);
 }
 
-void vsx_unavailable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(vsx_unavailable_exception)
 {
 	if (user_mode(regs)) {
 		/* A user program has executed an vsx instruction,
@@ -1723,7 +1735,7 @@ static void tm_unavailable(struct pt_regs *regs)
 	die("Unrecoverable TM Unavailable Exception", regs, SIGABRT);
 }
 
-void facility_unavailable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(facility_unavailable_exception)
 {
 	static char *facility_strings[] = {
 		[FSCR_FP_LG] = "FPU",
@@ -1843,7 +1855,7 @@ void facility_unavailable_exception(struct pt_regs *regs)
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 
-void fp_unavailable_tm(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(fp_unavailable_tm)
 {
 	/* Note:  This does not handle any kind of FP laziness. */
 
@@ -1876,7 +1888,7 @@ void fp_unavailable_tm(struct pt_regs *regs)
 	tm_recheckpoint(&current->thread);
 }
 
-void altivec_unavailable_tm(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(altivec_unavailable_tm)
 {
 	/* See the comments in fp_unavailable_tm().  This function operates
 	 * the same way.
@@ -1891,7 +1903,7 @@ void altivec_unavailable_tm(struct pt_regs *regs)
 	current->thread.used_vr = 1;
 }
 
-void vsx_unavailable_tm(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(vsx_unavailable_tm)
 {
 	/* See the comments in fp_unavailable_tm().  This works similarly,
 	 * though we're loading both FP and VEC registers in here.
@@ -1916,7 +1928,8 @@ void vsx_unavailable_tm(struct pt_regs *regs)
 }
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 
-static void performance_monitor_exception_nmi(struct pt_regs *regs)
+#ifdef CONFIG_PPC64
+DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi)
 {
 	nmi_enter();
 
@@ -1925,9 +1938,12 @@ static void performance_monitor_exception_nmi(struct pt_regs *regs)
 	perf_irq(regs);
 
 	nmi_exit();
+
+	return 0;
 }
+#endif
 
-static void performance_monitor_exception_async(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async)
 {
 	irq_enter();
 
@@ -1938,7 +1954,7 @@ static void performance_monitor_exception_async(struct pt_regs *regs)
 	irq_exit();
 }
 
-void performance_monitor_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_RAW(performance_monitor_exception)
 {
 	/*
 	 * On 64-bit, if perf interrupts hit in a local_irq_disable
@@ -1950,6 +1966,8 @@ void performance_monitor_exception(struct pt_regs *regs)
 		performance_monitor_exception_nmi(regs);
 	else
 		performance_monitor_exception_async(regs);
+
+	return 0;
 }
 
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
@@ -2012,7 +2030,7 @@ 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)
+DEFINE_INTERRUPT_HANDLER(DebugException)
 {
 	unsigned long debug_status = regs->dsisr;
 
@@ -2085,7 +2103,7 @@ NOKPROBE_SYMBOL(DebugException);
 #endif /* CONFIG_PPC_ADV_DEBUG_REGS */
 
 #ifdef CONFIG_ALTIVEC
-void altivec_assist_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(altivec_assist_exception)
 {
 	int err;
 
@@ -2119,7 +2137,7 @@ void altivec_assist_exception(struct pt_regs *regs)
 #endif /* CONFIG_ALTIVEC */
 
 #ifdef CONFIG_FSL_BOOKE
-void CacheLockingException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(CacheLockingException)
 {
 	unsigned long error_code = regs->dsisr;
 
@@ -2134,7 +2152,7 @@ void CacheLockingException(struct pt_regs *regs)
 #endif /* CONFIG_FSL_BOOKE */
 
 #ifdef CONFIG_SPE
-void SPEFloatingPointException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(SPEFloatingPointException)
 {
 	extern int do_spe_mathemu(struct pt_regs *regs);
 	unsigned long spefscr;
@@ -2186,7 +2204,7 @@ void SPEFloatingPointException(struct pt_regs *regs)
 	return;
 }
 
-void SPEFloatingPointRoundException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(SPEFloatingPointRoundException)
 {
 	extern int speround_handler(struct pt_regs *regs);
 	int err;
@@ -2228,7 +2246,7 @@ void SPEFloatingPointRoundException(struct pt_regs *regs)
  * in the MSR is 0.  This indicates that SRR0/1 are live, and that
  * we therefore lost state by taking this exception.
  */
-void unrecoverable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(unrecoverable_exception)
 {
 	pr_emerg("Unrecoverable exception %lx at %lx (msr=%lx)\n",
 		 regs->trap, regs->nip, regs->msr);
@@ -2248,7 +2266,7 @@ void __attribute__ ((weak)) WatchdogHandler(struct pt_regs *regs)
 	return;
 }
 
-void WatchdogException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(WatchdogException) /* XXX NMI? async? */
 {
 	printk (KERN_EMERG "PowerPC Book-E Watchdog Exception\n");
 	WatchdogHandler(regs);
@@ -2259,7 +2277,7 @@ void WatchdogException(struct pt_regs *regs)
  * We enter here if we discover during exception entry that we are
  * running in supervisor mode with a userspace value in the stack pointer.
  */
-void kernel_bad_stack(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(kernel_bad_stack)
 {
 	printk(KERN_EMERG "Bad kernel stack pointer %lx at %lx\n",
 	       regs->gpr[1], regs->nip);
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index af3c15a1d41e..824b9376ac35 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -26,6 +26,7 @@
 #include <linux/delay.h>
 #include <linux/smp.h>
 
+#include <asm/interrupt.h>
 #include <asm/paca.h>
 
 /*
@@ -247,14 +248,14 @@ static void watchdog_timer_interrupt(int cpu)
 		watchdog_smp_panic(cpu, tb);
 }
 
-void soft_nmi_interrupt(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
 {
 	unsigned long flags;
 	int cpu = raw_smp_processor_id();
 	u64 tb;
 
 	if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
-		return;
+		return 0;
 
 	nmi_enter();
 
@@ -291,6 +292,8 @@ void soft_nmi_interrupt(struct pt_regs *regs)
 
 out:
 	nmi_exit();
+
+	return 0;
 }
 
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index d348e77cee20..43e64e60ee33 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -53,6 +53,7 @@
 #include <asm/cputable.h>
 #include <asm/cacheflush.h>
 #include <linux/uaccess.h>
+#include <asm/interrupt.h>
 #include <asm/io.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 8053efdf7ea7..10fc274bea65 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -17,6 +17,7 @@
 
 #include <asm/asm-prototypes.h>
 #include <asm/cputable.h>
+#include <asm/interrupt.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 #include <asm/archrandom.h>
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 288a9820ec01..bd2bb73021d8 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -20,6 +20,7 @@
 
 #include <asm/cputable.h>
 #include <linux/uaccess.h>
+#include <asm/interrupt.h>
 #include <asm/kvm_ppc.h>
 #include <asm/cacheflush.h>
 #include <asm/dbell.h>
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index d7d3a80a51d4..824fcb2627e4 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -38,6 +38,7 @@
 #include <linux/pgtable.h>
 
 #include <asm/debugfs.h>
+#include <asm/interrupt.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
@@ -1512,7 +1513,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
 }
 EXPORT_SYMBOL_GPL(hash_page);
 
-static long __do_hash_fault(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
 {
 	unsigned long ea = regs->dar;
 	unsigned long dsisr = regs->dsisr;
@@ -1565,7 +1566,11 @@ static long __do_hash_fault(struct pt_regs *regs)
 	return err;
 }
 
-long do_hash_fault(struct pt_regs *regs)
+/*
+ * The _RAW interrupt entry checks for the in_nmi() case before
+ * running the full handler.
+ */
+DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault)
 {
 	unsigned long dsisr = regs->dsisr;
 	long err;
@@ -1587,7 +1592,7 @@ 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, SIGSEGV);
+		do_bad_page_fault_segv(regs);
 		return 0;
 	}
 
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index 14c62b685f0c..c91bd85eb90e 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -10,6 +10,7 @@
  */
 
 #include <asm/asm-prototypes.h>
+#include <asm/interrupt.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/paca.h>
@@ -813,7 +814,7 @@ 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)
+DEFINE_INTERRUPT_HANDLER_RAW(do_slb_fault)
 {
 	unsigned long ea = regs->dar;
 	unsigned long id = get_region_id(ea);
@@ -833,7 +834,7 @@ long do_slb_fault(struct pt_regs *regs)
 	 */
 
 	/*
-	 * The interrupt state is not reconciled, for performance, so that
+	 * This is a raw interrupt handler, 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
@@ -868,7 +869,7 @@ long do_slb_fault(struct pt_regs *regs)
 	}
 }
 
-void do_bad_slb_fault(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(do_bad_slb_fault)
 {
 	int err = regs->result;
 
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 900901d0038e..b84794d53664 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -34,6 +34,7 @@
 #include <linux/uaccess.h>
 
 #include <asm/firmware.h>
+#include <asm/interrupt.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
@@ -540,7 +541,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 }
 NOKPROBE_SYMBOL(__do_page_fault);
 
-long do_page_fault(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
 {
 	enum ctx_state prev_state;
 	long err;
@@ -623,7 +624,7 @@ void bad_page_fault(struct pt_regs *regs, int sig)
 }
 
 #ifdef CONFIG_PPC_BOOK3S_64
-void do_bad_page_fault_segv(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(do_bad_page_fault_segv)
 {
 	bad_page_fault(regs, SIGSEGV);
 }
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index 6ea480539419..4325c05bedd9 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -49,7 +49,7 @@ static void dump_fir(int cpu)
 
 }
 
-void cbe_system_error_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(cbe_system_error_exception)
 {
 	int cpu = smp_processor_id();
 
@@ -58,7 +58,7 @@ void cbe_system_error_exception(struct pt_regs *regs)
 	dump_stack();
 }
 
-void cbe_maintenance_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(cbe_maintenance_exception)
 {
 	int cpu = smp_processor_id();
 
@@ -70,7 +70,7 @@ void cbe_maintenance_exception(struct pt_regs *regs)
 	dump_stack();
 }
 
-void cbe_thermal_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(cbe_thermal_exception)
 {
 	int cpu = smp_processor_id();
 
diff --git a/arch/powerpc/platforms/cell/ras.h b/arch/powerpc/platforms/cell/ras.h
index 6c2e6bc0062e..226dbd48efad 100644
--- a/arch/powerpc/platforms/cell/ras.h
+++ b/arch/powerpc/platforms/cell/ras.h
@@ -2,9 +2,12 @@
 #ifndef RAS_H
 #define RAS_H
 
-extern void cbe_system_error_exception(struct pt_regs *regs);
-extern void cbe_maintenance_exception(struct pt_regs *regs);
-extern void cbe_thermal_exception(struct pt_regs *regs);
+#include <asm/interrupt.h>
+
+DECLARE_INTERRUPT_HANDLER(cbe_system_error_exception);
+DECLARE_INTERRUPT_HANDLER(cbe_maintenance_exception);
+DECLARE_INTERRUPT_HANDLER(cbe_thermal_exception);
+
 extern void cbe_ras_init(void);
 
 #endif /* RAS_H */
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index e6f461812856..999997d9e9a9 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -14,6 +14,7 @@
 
 #include <asm/asm-prototypes.h>
 #include <asm/firmware.h>
+#include <asm/interrupt.h>
 #include <asm/machdep.h>
 #include <asm/opal.h>
 #include <asm/cputhreads.h>
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 26/39] powerpc: add interrupt_cond_local_irq_enable helper
From: Nicholas Piggin @ 2021-01-15 16:49 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

Simple helper for synchronous interrupt handlers (i.e., process-context)
to enable interrupts if it was taken in an interrupts-enabled context.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/interrupt.h |  7 +++++++
 arch/powerpc/kernel/traps.c          | 24 +++++++-----------------
 arch/powerpc/mm/fault.c              |  4 +---
 3 files changed, 15 insertions(+), 20 deletions(-)

diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 4ffbd3d75324..488bdd5bd922 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -3,6 +3,7 @@
 #define _ASM_POWERPC_INTERRUPT_H
 
 #include <linux/context_tracking.h>
+#include <linux/hardirq.h>
 #include <asm/ftrace.h>
 
 struct interrupt_state {
@@ -298,4 +299,10 @@ DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException);
 void replay_system_reset(void);
 void replay_soft_interrupts(void);
 
+static inline void interrupt_cond_local_irq_enable(struct pt_regs *regs)
+{
+	if (!arch_irq_disabled_regs(regs))
+		local_irq_enable();
+}
+
 #endif /* _ASM_POWERPC_INTERRUPT_H */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index b000956cde3f..076e5ff75cf7 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -343,8 +343,8 @@ static bool exception_common(int signr, struct pt_regs *regs, int code,
 
 	show_signal_msg(signr, regs, code, addr);
 
-	if (arch_irqs_disabled() && !arch_irq_disabled_regs(regs))
-		local_irq_enable();
+	if (arch_irqs_disabled())
+		interrupt_cond_local_irq_enable(regs);
 
 	current->thread.trap_nr = code;
 
@@ -1556,9 +1556,7 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
 	if (!user_mode(regs))
 		goto sigill;
 
-	/* We restore the interrupt state now */
-	if (!arch_irq_disabled_regs(regs))
-		local_irq_enable();
+	interrupt_cond_local_irq_enable(regs);
 
 	/* (reason & REASON_ILLEGAL) would be the obvious thing here,
 	 * but there seems to be a hardware bug on the 405GP (RevD)
@@ -1612,9 +1610,7 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
 	int sig, code, fixed = 0;
 	unsigned long  reason;
 
-	/* We restore the interrupt state now */
-	if (!arch_irq_disabled_regs(regs))
-		local_irq_enable();
+	interrupt_cond_local_irq_enable(regs);
 
 	reason = get_reason(regs);
 
@@ -1775,9 +1771,7 @@ DEFINE_INTERRUPT_HANDLER(facility_unavailable_exception)
 		die("Unexpected facility unavailable exception", regs, SIGABRT);
 	}
 
-	/* We restore the interrupt state now */
-	if (!arch_irq_disabled_regs(regs))
-		local_irq_enable();
+	interrupt_cond_local_irq_enable(regs);
 
 	if (status == FSCR_DSCR_LG) {
 		/*
@@ -2160,9 +2154,7 @@ DEFINE_INTERRUPT_HANDLER(SPEFloatingPointException)
 	int code = FPE_FLTUNK;
 	int err;
 
-	/* We restore the interrupt state now */
-	if (!arch_irq_disabled_regs(regs))
-		local_irq_enable();
+	interrupt_cond_local_irq_enable(regs);
 
 	flush_spe_to_thread(current);
 
@@ -2209,9 +2201,7 @@ DEFINE_INTERRUPT_HANDLER(SPEFloatingPointRoundException)
 	extern int speround_handler(struct pt_regs *regs);
 	int err;
 
-	/* We restore the interrupt state now */
-	if (!arch_irq_disabled_regs(regs))
-		local_irq_enable();
+	interrupt_cond_local_irq_enable(regs);
 
 	preempt_disable();
 	if (regs->msr & MSR_SPE)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index b84794d53664..eef7281507f9 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -434,9 +434,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 		return bad_area_nosemaphore(regs, address);
 	}
 
-	/* We restore the interrupt state now */
-	if (!arch_irq_disabled_regs(regs))
-		local_irq_enable();
+	interrupt_cond_local_irq_enable(regs);
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 27/39] powerpc/64: context tracking remove _TIF_NOHZ
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

Add context tracking to the system call handler explicitly, and remove
_TIF_NOHZ.

This improves system call performance when nohz_full is enabled. On a
POWER9, gettid scv system call cost on a nohz_full CPU improves from
1129 cycles to 1004 cycles and on a housekeeping CPU from 550 cycles
to 430 cycles.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/Kconfig                   |  1 -
 arch/powerpc/include/asm/thread_info.h |  4 +---
 arch/powerpc/kernel/ptrace/ptrace.c    |  4 ----
 arch/powerpc/kernel/signal.c           |  4 ----
 arch/powerpc/kernel/syscall_64.c       | 10 ++++++++++
 5 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 107bb4319e0e..28d5a1b1510f 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -196,7 +196,6 @@ config PPC
 	select HAVE_STACKPROTECTOR		if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13)
 	select HAVE_STACKPROTECTOR		if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2)
 	select HAVE_CONTEXT_TRACKING		if PPC64
-	select HAVE_TIF_NOHZ			if PPC64
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DYNAMIC_FTRACE
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 3d8a47af7a25..386d576673a1 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -94,7 +94,6 @@ void arch_setup_new_exec(void);
 #define TIF_PATCH_PENDING	6	/* pending live patching update */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SINGLESTEP		8	/* singlestepping active */
-#define TIF_NOHZ		9	/* in adaptive nohz mode */
 #define TIF_SECCOMP		10	/* secure computing */
 #define TIF_RESTOREALL		11	/* Restore all regs (implies NOERROR) */
 #define TIF_NOERROR		12	/* Force successful syscall return */
@@ -128,11 +127,10 @@ void arch_setup_new_exec(void);
 #define _TIF_UPROBE		(1<<TIF_UPROBE)
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_EMULATE_STACK_STORE	(1<<TIF_EMULATE_STACK_STORE)
-#define _TIF_NOHZ		(1<<TIF_NOHZ)
 #define _TIF_SYSCALL_EMU	(1<<TIF_SYSCALL_EMU)
 #define _TIF_SYSCALL_DOTRACE	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
-				 _TIF_NOHZ | _TIF_SYSCALL_EMU)
+				 _TIF_SYSCALL_EMU)
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
 				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
index 3d44b73adb83..4f3d4ff3728c 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -262,8 +262,6 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 {
 	u32 flags;
 
-	user_exit();
-
 	flags = READ_ONCE(current_thread_info()->flags) &
 		(_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE);
 
@@ -340,8 +338,6 @@ void do_syscall_trace_leave(struct pt_regs *regs)
 	step = test_thread_flag(TIF_SINGLESTEP);
 	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, step);
-
-	user_enter();
 }
 
 void __init pt_regs_check(void);
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 53782aa60ade..9ded046edb0e 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -282,8 +282,6 @@ static void do_signal(struct task_struct *tsk)
 
 void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 {
-	user_exit();
-
 	if (thread_info_flags & _TIF_UPROBE)
 		uprobe_notify_resume(regs);
 
@@ -299,8 +297,6 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 		tracehook_notify_resume(regs);
 		rseq_handle_notify_resume(NULL, regs);
 	}
-
-	user_enter();
 }
 
 static unsigned long get_tm_stackpointer(struct task_struct *tsk)
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index dd87b2118620..d7d256a7a41f 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -1,9 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include <linux/context_tracking.h>
 #include <linux/err.h>
 #include <asm/asm-prototypes.h>
 #include <asm/kup.h>
 #include <asm/cputime.h>
+#include <asm/interrupt.h>
 #include <asm/hw_irq.h>
 #include <asm/interrupt.h>
 #include <asm/kprobes.h>
@@ -28,6 +30,9 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
 		BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
 
+	CT_WARN_ON(ct_state() == CONTEXT_KERNEL);
+	user_exit_irqoff();
+
 	trace_hardirqs_off(); /* finish reconciling */
 
 	if (IS_ENABLED(CONFIG_PPC_BOOK3S))
@@ -182,6 +187,8 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 	unsigned long ti_flags;
 	unsigned long ret = 0;
 
+	CT_WARN_ON(ct_state() == CONTEXT_USER);
+
 	kuap_check_amr();
 
 	regs->result = r3;
@@ -258,8 +265,11 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 		}
 	}
 
+	user_enter_irqoff();
+
 	/* scv need not set RI=0 because SRRs are not used */
 	if (unlikely(!prep_irq_for_enabled_exit(!scv))) {
+		user_exit_irqoff();
 		local_irq_enable();
 		goto again;
 	}
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 28/39] powerpc/64s/hash: improve context tracking of hash faults
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

This moves the 64s/hash context tracking from hash_page_mm() to
__do_hash_fault(), so it's no longer called by OCXL / SPU
accelerators, which was certainly the wrong thing to be doing,
because those callers are not low level interrupt handlers, so
should have entered a kernel context tracking already.

Then remain in kernel context for the duration of the fault,
rather than enter/exit for the hash fault then enter/exit for
the page fault, which is pointless.

Even still, calling exception_enter/exit in __do_hash_fault seems
questionable because that's touching per-cpu variables, tracing,
etc., which might have been interrupted by this hash fault or
themselves cause hash faults. But maybe I miss something because
hash_page_mm very deliberately calls trace_hash_fault too, for
example. So for now go with it, it's no worse than before, in this
regard.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/bug.h        |  1 +
 arch/powerpc/mm/book3s64/hash_utils.c |  7 ++++---
 arch/powerpc/mm/fault.c               | 30 +++++++++++++++++++++------
 3 files changed, 29 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index c10ae0a9bbaf..d1635ffbb179 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -112,6 +112,7 @@
 
 struct pt_regs;
 long do_page_fault(struct pt_regs *);
+long hash__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);
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 824fcb2627e4..b7b78aeea3eb 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1289,7 +1289,6 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 		 unsigned long flags)
 {
 	bool is_thp;
-	enum ctx_state prev_state = exception_enter();
 	pgd_t *pgdir;
 	unsigned long vsid;
 	pte_t *ptep;
@@ -1491,7 +1490,6 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 	DBG_LOW(" -> rc=%d\n", rc);
 
 bail:
-	exception_exit(prev_state);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(hash_page_mm);
@@ -1515,6 +1513,7 @@ EXPORT_SYMBOL_GPL(hash_page);
 
 DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
 {
+	enum ctx_state prev_state = exception_enter();
 	unsigned long ea = regs->dar;
 	unsigned long dsisr = regs->dsisr;
 	unsigned long access = _PAGE_PRESENT | _PAGE_READ;
@@ -1563,6 +1562,8 @@ DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
 		err = 0;
 	}
 
+	exception_exit(prev_state);
+
 	return err;
 }
 
@@ -1599,7 +1600,7 @@ DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault)
 	err = __do_hash_fault(regs);
 	if (err) {
 page_fault:
-		err = do_page_fault(regs);
+		err = hash__do_page_fault(regs);
 	}
 
 	return err;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index eef7281507f9..620ff623b2c6 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -387,7 +387,7 @@ static void sanity_check_fault(bool is_write, bool is_user,
  * 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.
  */
-static int __do_page_fault(struct pt_regs *regs, unsigned long address,
+static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 			   unsigned long error_code)
 {
 	struct vm_area_struct * vma;
@@ -537,15 +537,13 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	return 0;
 }
-NOKPROBE_SYMBOL(__do_page_fault);
+NOKPROBE_SYMBOL(___do_page_fault);
 
-DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
+static long __do_page_fault(struct pt_regs *regs)
 {
-	enum ctx_state prev_state;
 	long err;
 
-	prev_state = exception_enter();
-	err = __do_page_fault(regs, regs->dar, regs->dsisr);
+	err = ___do_page_fault(regs, regs->dar, regs->dsisr);
 	if (unlikely(err)) {
 		const struct exception_table_entry *entry;
 
@@ -560,12 +558,32 @@ DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
 		}
 	}
 
+	return err;
+}
+NOKPROBE_SYMBOL(__do_page_fault);
+
+DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
+{
+	enum ctx_state prev_state = exception_enter();
+	long err;
+
+	err = __do_page_fault(regs);
+
 	exception_exit(prev_state);
 
 	return err;
 }
 NOKPROBE_SYMBOL(do_page_fault);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+/* Same as do_page_fault but interrupt entry has already run in do_hash_fault */
+long hash__do_page_fault(struct pt_regs *regs)
+{
+	return __do_page_fault(regs);
+}
+NOKPROBE_SYMBOL(hash__do_page_fault);
+#endif
+
 /*
  * bad_page_fault is called when we have a bad access from the kernel.
  * It is called from the DSI and ISI handlers in head.S and from some
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 29/39] powerpc/64: context tracking move to interrupt wrappers
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

This moves exception_enter/exit calls to wrapper functions for
synchronous interrupts. More interrupt handlers are covered by
this than previously.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/interrupt.h  |  9 ++++
 arch/powerpc/kernel/traps.c           | 74 ++++++---------------------
 arch/powerpc/mm/book3s64/hash_utils.c |  3 --
 arch/powerpc/mm/fault.c               |  9 +---
 4 files changed, 27 insertions(+), 68 deletions(-)

diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 488bdd5bd922..e65ce3e2b071 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -7,10 +7,16 @@
 #include <asm/ftrace.h>
 
 struct interrupt_state {
+#ifdef CONFIG_PPC64
+	enum ctx_state ctx_state;
+#endif
 };
 
 static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
 {
+#ifdef CONFIG_PPC64
+	state->ctx_state = exception_enter();
+#endif
 }
 
 /*
@@ -29,6 +35,9 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
  */
 static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
 {
+#ifdef CONFIG_PPC64
+	exception_exit(state->ctx_state);
+#endif
 }
 
 static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 076e5ff75cf7..d3892f402b0e 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1087,41 +1087,28 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
 
 DEFINE_INTERRUPT_HANDLER(unknown_exception)
 {
-	enum ctx_state prev_state = exception_enter();
-
 	printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
 	       regs->nip, regs->msr, regs->trap);
 
 	_exception(SIGTRAP, regs, TRAP_UNK, 0);
-
-	exception_exit(prev_state);
 }
 
 DEFINE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception)
 {
-	enum ctx_state prev_state = exception_enter();
-
 	printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
 	       regs->nip, regs->msr, regs->trap);
 
 	_exception(SIGTRAP, regs, TRAP_UNK, 0);
-
-	exception_exit(prev_state);
 }
 
 DEFINE_INTERRUPT_HANDLER(instruction_breakpoint_exception)
 {
-	enum ctx_state prev_state = exception_enter();
-
 	if (notify_die(DIE_IABR_MATCH, "iabr_match", regs, 5,
 					5, SIGTRAP) == NOTIFY_STOP)
-		goto bail;
+		return;
 	if (debugger_iabr_match(regs))
-		goto bail;
+		return;
 	_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
-
-bail:
-	exception_exit(prev_state);
 }
 
 DEFINE_INTERRUPT_HANDLER(RunModeException)
@@ -1131,8 +1118,6 @@ DEFINE_INTERRUPT_HANDLER(RunModeException)
 
 DEFINE_INTERRUPT_HANDLER(single_step_exception)
 {
-	enum ctx_state prev_state = exception_enter();
-
 	clear_single_step(regs);
 	clear_br_trace(regs);
 
@@ -1141,14 +1126,11 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception)
 
 	if (notify_die(DIE_SSTEP, "single_step", regs, 5,
 					5, SIGTRAP) == NOTIFY_STOP)
-		goto bail;
+		return;
 	if (debugger_sstep(regs))
-		goto bail;
+		return;
 
 	_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
-
-bail:
-	exception_exit(prev_state);
 }
 NOKPROBE_SYMBOL(single_step_exception);
 
@@ -1476,7 +1458,6 @@ static inline int emulate_math(struct pt_regs *regs) { return -1; }
 
 DEFINE_INTERRUPT_HANDLER(program_check_exception)
 {
-	enum ctx_state prev_state = exception_enter();
 	unsigned int reason = get_reason(regs);
 
 	/* We can now get here via a FP Unavailable exception if the core
@@ -1485,22 +1466,22 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
 	if (reason & REASON_FP) {
 		/* IEEE FP exception */
 		parse_fpe(regs);
-		goto bail;
+		return;
 	}
 	if (reason & REASON_TRAP) {
 		unsigned long bugaddr;
 		/* Debugger is first in line to stop recursive faults in
 		 * rcu_lock, notify_die, or atomic_notifier_call_chain */
 		if (debugger_bpt(regs))
-			goto bail;
+			return;
 
 		if (kprobe_handler(regs))
-			goto bail;
+			return;
 
 		/* trap exception */
 		if (notify_die(DIE_BPT, "breakpoint", regs, 5, 5, SIGTRAP)
 				== NOTIFY_STOP)
-			goto bail;
+			return;
 
 		bugaddr = regs->nip;
 		/*
@@ -1512,10 +1493,10 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
 		if (!(regs->msr & MSR_PR) &&  /* not user-mode */
 		    report_bug(bugaddr, regs) == BUG_TRAP_TYPE_WARN) {
 			regs->nip += 4;
-			goto bail;
+			return;
 		}
 		_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
-		goto bail;
+		return;
 	}
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (reason & REASON_TM) {
@@ -1536,7 +1517,7 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
 		 */
 		if (user_mode(regs)) {
 			_exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
-			goto bail;
+			return;
 		} else {
 			printk(KERN_EMERG "Unexpected TM Bad Thing exception "
 			       "at %lx (msr 0x%lx) tm_scratch=%llx\n",
@@ -1567,7 +1548,7 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
 	 * pattern to occurrences etc. -dgibson 31/Mar/2003
 	 */
 	if (!emulate_math(regs))
-		goto bail;
+		return;
 
 	/* Try to emulate it if we should. */
 	if (reason & (REASON_ILLEGAL | REASON_PRIVILEGED)) {
@@ -1575,10 +1556,10 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
 		case 0:
 			regs->nip += 4;
 			emulate_single_step(regs);
-			goto bail;
+			return;
 		case -EFAULT:
 			_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
-			goto bail;
+			return;
 		}
 	}
 
@@ -1587,9 +1568,6 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
 		_exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
 	else
 		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-
-bail:
-	exception_exit(prev_state);
 }
 NOKPROBE_SYMBOL(program_check_exception);
 
@@ -1606,14 +1584,12 @@ NOKPROBE_SYMBOL(emulation_assist_interrupt);
 
 DEFINE_INTERRUPT_HANDLER(alignment_exception)
 {
-	enum ctx_state prev_state = exception_enter();
 	int sig, code, fixed = 0;
 	unsigned long  reason;
 
 	interrupt_cond_local_irq_enable(regs);
 
 	reason = get_reason(regs);
-
 	if (reason & REASON_BOUNDARY) {
 		sig = SIGBUS;
 		code = BUS_ADRALN;
@@ -1621,7 +1597,7 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
 	}
 
 	if (tm_abort_check(regs, TM_CAUSE_ALIGNMENT | TM_CAUSE_PERSISTENT))
-		goto bail;
+		return;
 
 	/* we don't implement logging of alignment exceptions */
 	if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS))
@@ -1631,7 +1607,7 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
 		/* skip over emulated instruction */
 		regs->nip += inst_length(reason);
 		emulate_single_step(regs);
-		goto bail;
+		return;
 	}
 
 	/* Operand address was bad */
@@ -1647,9 +1623,6 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
 		_exception(sig, regs, code, regs->dar);
 	else
 		bad_page_fault(regs, sig);
-
-bail:
-	exception_exit(prev_state);
 }
 
 DEFINE_INTERRUPT_HANDLER(StackOverflow)
@@ -1663,41 +1636,28 @@ DEFINE_INTERRUPT_HANDLER(StackOverflow)
 
 DEFINE_INTERRUPT_HANDLER(stack_overflow_exception)
 {
-	enum ctx_state prev_state = exception_enter();
-
 	die("Kernel stack overflow", regs, SIGSEGV);
-
-	exception_exit(prev_state);
 }
 
 DEFINE_INTERRUPT_HANDLER(kernel_fp_unavailable_exception)
 {
-	enum ctx_state prev_state = exception_enter();
-
 	printk(KERN_EMERG "Unrecoverable FP Unavailable Exception "
 			  "%lx at %lx\n", regs->trap, regs->nip);
 	die("Unrecoverable FP Unavailable Exception", regs, SIGABRT);
-
-	exception_exit(prev_state);
 }
 
 DEFINE_INTERRUPT_HANDLER(altivec_unavailable_exception)
 {
-	enum ctx_state prev_state = exception_enter();
-
 	if (user_mode(regs)) {
 		/* A user program has executed an altivec instruction,
 		   but this kernel doesn't support altivec. */
 		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-		goto bail;
+		return;
 	}
 
 	printk(KERN_EMERG "Unrecoverable VMX/Altivec Unavailable Exception "
 			"%lx at %lx\n", regs->trap, regs->nip);
 	die("Unrecoverable VMX/Altivec Unavailable Exception", regs, SIGABRT);
-
-bail:
-	exception_exit(prev_state);
 }
 
 DEFINE_INTERRUPT_HANDLER(vsx_unavailable_exception)
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index b7b78aeea3eb..176f05ad3065 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1513,7 +1513,6 @@ EXPORT_SYMBOL_GPL(hash_page);
 
 DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
 {
-	enum ctx_state prev_state = exception_enter();
 	unsigned long ea = regs->dar;
 	unsigned long dsisr = regs->dsisr;
 	unsigned long access = _PAGE_PRESENT | _PAGE_READ;
@@ -1562,8 +1561,6 @@ DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
 		err = 0;
 	}
 
-	exception_exit(prev_state);
-
 	return err;
 }
 
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 620ff623b2c6..24dcaea2b512 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -564,14 +564,7 @@ NOKPROBE_SYMBOL(__do_page_fault);
 
 DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
 {
-	enum ctx_state prev_state = exception_enter();
-	long err;
-
-	err = __do_page_fault(regs);
-
-	exception_exit(prev_state);
-
-	return err;
+	return __do_page_fault(regs);
 }
 NOKPROBE_SYMBOL(do_page_fault);
 
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 30/39] powerpc/64: add context tracking to asynchronous interrupts
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

Previously context tracking was not done for asynchronous interrupts,
(those that run in interrupt context), and if those would cause a
reschedule when they exit, then scheduling functions (schedule_user,
preempt_schedule_irq) call exception_enter/exit to fix this up and
exit user context.

This is a hack we would like to get away from, so do context tracking
for asynchronous interrupts too.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/interrupt.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index e65ce3e2b071..f7f64c3c514d 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -42,10 +42,12 @@ static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt
 
 static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
 {
+	interrupt_enter_prepare(regs, state);
 }
 
 static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
 {
+	interrupt_exit_prepare(regs, state);
 }
 
 struct interrupt_nmi_state {
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 31/39] powerpc: handle irq_enter/irq_exit in interrupt handler wrappers
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

Move irq_enter/irq_exit into asynchronous interrupt handler wrappers.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/interrupt.h |  2 ++
 arch/powerpc/kernel/dbell.c          |  3 +--
 arch/powerpc/kernel/irq.c            |  4 ----
 arch/powerpc/kernel/tau_6xx.c        |  3 ---
 arch/powerpc/kernel/time.c           |  4 ++--
 arch/powerpc/kernel/traps.c          | 10 +++-------
 6 files changed, 8 insertions(+), 18 deletions(-)

diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index f7f64c3c514d..5a1395499508 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -43,10 +43,12 @@ static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt
 static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
 {
 	interrupt_enter_prepare(regs, state);
+	irq_enter();
 }
 
 static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
 {
+	irq_exit();
 	interrupt_exit_prepare(regs, state);
 }
 
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 6a7ecfca5c3b..5545c9cd17c1 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -23,7 +23,6 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	irq_enter();
 	trace_doorbell_entry(regs);
 
 	ppc_msgsync();
@@ -36,7 +35,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
 	smp_ipi_demux_relaxed(); /* already performed the barrier */
 
 	trace_doorbell_exit(regs);
-	irq_exit();
+
 	set_irq_regs(old_regs);
 }
 #else /* CONFIG_SMP */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 2055d204d08e..681abb7c0507 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -641,8 +641,6 @@ void __do_irq(struct pt_regs *regs)
 {
 	unsigned int irq;
 
-	irq_enter();
-
 	trace_irq_entry(regs);
 
 	/*
@@ -662,8 +660,6 @@ void __do_irq(struct pt_regs *regs)
 		generic_handle_irq(irq);
 
 	trace_irq_exit(regs);
-
-	irq_exit();
 }
 
 DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c
index 46b2e5de4ef5..d864f07bab74 100644
--- a/arch/powerpc/kernel/tau_6xx.c
+++ b/arch/powerpc/kernel/tau_6xx.c
@@ -104,12 +104,9 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(TAUException)
 {
 	int cpu = smp_processor_id();
 
-	irq_enter();
 	tau[cpu].interrupts++;
 
 	TAUupdate(cpu);
-
-	irq_exit();
 }
 #endif /* CONFIG_TAU_INT */
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 435a251247ed..2177defb7884 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -610,7 +610,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
 #endif
 
 	old_regs = set_irq_regs(regs);
-	irq_enter();
+
 	trace_timer_interrupt_entry(regs);
 
 	if (test_irq_work_pending()) {
@@ -635,7 +635,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
 	}
 
 	trace_timer_interrupt_exit(regs);
-	irq_exit();
+
 	set_irq_regs(old_regs);
 }
 EXPORT_SYMBOL(timer_interrupt);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index d3892f402b0e..f37583d57442 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -801,7 +801,9 @@ void die_mce(const char *str, struct pt_regs *regs, long err)
 	 * do_exit() checks for in_interrupt() and panics in that case, so
 	 * exit the irq/nmi before calling die.
 	 */
-	if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+		irq_exit();
+	else
 		nmi_exit();
 	die(str, regs, err);
 }
@@ -1061,7 +1063,6 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
 	struct pt_regs *old_regs;
 
 	old_regs = set_irq_regs(regs);
-	irq_enter();
 
 #ifdef CONFIG_VSX
 	/* Real mode flagged P9 special emu is needed */
@@ -1081,7 +1082,6 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
 	if (ppc_md.handle_hmi_exception)
 		ppc_md.handle_hmi_exception(regs);
 
-	irq_exit();
 	set_irq_regs(old_regs);
 }
 
@@ -1899,13 +1899,9 @@ DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi)
 
 DEFINE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async)
 {
-	irq_enter();
-
 	__this_cpu_inc(irq_stat.pmu_irqs);
 
 	perf_irq(regs);
-
-	irq_exit();
 }
 
 DEFINE_INTERRUPT_HANDLER_RAW(performance_monitor_exception)
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 32/39] powerpc/64s: move context tracking exit to interrupt exit path
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

The interrupt handler wrapper functions are not the ideal place to
maintain context tracking because after they return, the low level exit
code must then determine if there are interrupts to replay, or if the
task should be preempted, etc. Those paths (e.g., schedule_user) include
their own exception_enter/exit pairs to fix this up but it's a bit hacky
(see schedule_user() comments).

Ideally context tracking will go to user mode only when there are no
more interrupts or context switches or other exit processing work to
handle.

64e can not do this because it does not use the C interrupt exit code.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/interrupt.h | 34 +++++++++++++++++++++++++---
 arch/powerpc/kernel/syscall_64.c     |  9 ++++++++
 2 files changed, 40 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 5a1395499508..1c966e47b36f 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -7,16 +7,30 @@
 #include <asm/ftrace.h>
 
 struct interrupt_state {
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3E_64
 	enum ctx_state ctx_state;
 #endif
 };
 
 static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
 {
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3E_64
 	state->ctx_state = exception_enter();
 #endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (user_mode(regs)) {
+		CT_WARN_ON(ct_state() != CONTEXT_USER);
+		user_exit_irqoff();
+	} else {
+		/*
+		 * CT_WARN_ON comes here via program_check_exception,
+		 * so avoid recursion.
+		 */
+		if (TRAP(regs) != 0x700)
+			CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
+	}
+#endif
 }
 
 /*
@@ -35,9 +49,23 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
  */
 static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
 {
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3E_64
 	exception_exit(state->ctx_state);
 #endif
+
+	/*
+	 * Book3S exits to user via interrupt_exit_user_prepare(), which does
+	 * context tracking, which is a cleaner way to handle PREEMPT=y
+	 * and avoid context entry/exit in e.g., preempt_schedule_irq()),
+	 * which is likely to be where the core code wants to end up.
+	 *
+	 * The above comment explains why we can't do the
+	 *
+	 *     if (user_mode(regs))
+	 *         user_exit_irqoff();
+	 *
+	 * sequence here.
+	 */
 }
 
 static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index d7d256a7a41f..42f0ad4b2fbb 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -305,6 +305,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
 	BUG_ON(!(regs->msr & MSR_PR));
 	BUG_ON(!FULL_REGS(regs));
 	BUG_ON(regs->softe != IRQS_ENABLED);
+	CT_WARN_ON(ct_state() == CONTEXT_USER);
 
 	/*
 	 * We don't need to restore AMR on the way back to userspace for KUAP.
@@ -347,7 +348,9 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
 		}
 	}
 
+	user_enter_irqoff();
 	if (unlikely(!prep_irq_for_enabled_exit(true))) {
+		user_exit_irqoff();
 		local_irq_enable();
 		local_irq_disable();
 		goto again;
@@ -392,6 +395,12 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
 		unrecoverable_exception(regs);
 	BUG_ON(regs->msr & MSR_PR);
 	BUG_ON(!FULL_REGS(regs));
+	/*
+	 * CT_WARN_ON comes here via program_check_exception,
+	 * so avoid recursion.
+	 */
+	if (TRAP(regs) != 0x700)
+		CT_WARN_ON(ct_state() == CONTEXT_USER);
 
 	amr = kuap_get_and_check_amr();
 
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 33/39] powerpc/64s: reconcile interrupts in C
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

There is no need for this to be in asm, use the new intrrupt entry wrapper.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/interrupt.h | 15 +++++++++++----
 arch/powerpc/kernel/exceptions-64s.S | 26 --------------------------
 2 files changed, 11 insertions(+), 30 deletions(-)

diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 1c966e47b36f..e96d215f518a 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -14,11 +14,14 @@ struct interrupt_state {
 
 static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
 {
-#ifdef CONFIG_PPC_BOOK3E_64
-	state->ctx_state = exception_enter();
-#endif
-
+	/*
+	 * Book3E reconciles irq soft mask in asm
+	 */
 #ifdef CONFIG_PPC_BOOK3S_64
+	if (irq_soft_mask_set_return(IRQS_ALL_DISABLED) == IRQS_ENABLED)
+		trace_hardirqs_off();
+	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
 	if (user_mode(regs)) {
 		CT_WARN_ON(ct_state() != CONTEXT_USER);
 		user_exit_irqoff();
@@ -31,6 +34,10 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
 			CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
 	}
 #endif
+
+#ifdef CONFIG_PPC_BOOK3E_64
+	state->ctx_state = exception_enter();
+#endif
 }
 
 /*
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index fe33197ea8fb..39630b3f78b0 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -139,7 +139,6 @@ name:
 #define IKVM_VIRT	.L_IKVM_VIRT_\name\()	/* Virt entry tests KVM */
 #define ISTACK		.L_ISTACK_\name\()	/* Set regular kernel stack */
 #define __ISTACK(name)	.L_ISTACK_ ## name
-#define IRECONCILE	.L_IRECONCILE_\name\()	/* Do RECONCILE_IRQ_STATE */
 #define IKUAP		.L_IKUAP_\name\()	/* Do KUAP lock */
 
 #define INT_DEFINE_BEGIN(n)						\
@@ -203,9 +202,6 @@ do_define_int n
 	.ifndef ISTACK
 		ISTACK=1
 	.endif
-	.ifndef IRECONCILE
-		IRECONCILE=1
-	.endif
 	.ifndef IKUAP
 		IKUAP=1
 	.endif
@@ -653,10 +649,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	.if ISTACK
 	ACCOUNT_STOLEN_TIME
 	.endif
-
-	.if IRECONCILE
-	RECONCILE_IRQ_STATE(r10, r11)
-	.endif
 .endm
 
 /*
@@ -935,7 +927,6 @@ INT_DEFINE_BEGIN(system_reset)
 	 */
 	ISET_RI=0
 	ISTACK=0
-	IRECONCILE=0
 	IKVM_REAL=1
 INT_DEFINE_END(system_reset)
 
@@ -1123,7 +1114,6 @@ INT_DEFINE_BEGIN(machine_check_early)
 	ISTACK=0
 	IDAR=1
 	IDSISR=1
-	IRECONCILE=0
 	IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
 INT_DEFINE_END(machine_check_early)
 
@@ -1483,7 +1473,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 INT_DEFINE_BEGIN(data_access_slb)
 	IVEC=0x380
 	IAREA=PACA_EXSLB
-	IRECONCILE=0
 	IDAR=1
 	IKVM_SKIP=1
 	IKVM_REAL=1
@@ -1510,7 +1499,6 @@ MMU_FTR_SECTION_ELSE
 	li	r3,-EFAULT
 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 	std	r3,RESULT(r1)
-	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_bad_slb_fault
 	b	interrupt_return
@@ -1568,7 +1556,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 INT_DEFINE_BEGIN(instruction_access_slb)
 	IVEC=0x480
 	IAREA=PACA_EXSLB
-	IRECONCILE=0
 	IISIDE=1
 	IDAR=1
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
@@ -1597,7 +1584,6 @@ MMU_FTR_SECTION_ELSE
 	li	r3,-EFAULT
 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 	std	r3,RESULT(r1)
-	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_bad_slb_fault
 	b	interrupt_return
@@ -1757,7 +1743,6 @@ EXC_COMMON_BEGIN(program_check_common)
  */
 INT_DEFINE_BEGIN(fp_unavailable)
 	IVEC=0x800
-	IRECONCILE=0
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 	IKVM_REAL=1
 #endif
@@ -1772,7 +1757,6 @@ EXC_VIRT_END(fp_unavailable, 0x4800, 0x100)
 EXC_COMMON_BEGIN(fp_unavailable_common)
 	GEN_COMMON fp_unavailable
 	bne	1f			/* if from user, just load it up */
-	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	kernel_fp_unavailable_exception
 0:	trap
@@ -1791,7 +1775,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 	b	fast_interrupt_return
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	fp_unavailable_tm
 	b	interrupt_return
@@ -1856,7 +1839,6 @@ INT_DEFINE_BEGIN(hdecrementer)
 	IVEC=0x980
 	IHSRR=1
 	ISTACK=0
-	IRECONCILE=0
 	IKVM_REAL=1
 	IKVM_VIRT=1
 INT_DEFINE_END(hdecrementer)
@@ -2230,7 +2212,6 @@ INT_DEFINE_BEGIN(hmi_exception_early)
 	IHSRR=1
 	IREALMODE_COMMON=1
 	ISTACK=0
-	IRECONCILE=0
 	IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
 	IKVM_REAL=1
 INT_DEFINE_END(hmi_exception_early)
@@ -2404,7 +2385,6 @@ EXC_COMMON_BEGIN(performance_monitor_common)
  */
 INT_DEFINE_BEGIN(altivec_unavailable)
 	IVEC=0xf20
-	IRECONCILE=0
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 	IKVM_REAL=1
 #endif
@@ -2434,7 +2414,6 @@ BEGIN_FTR_SECTION
 	b	fast_interrupt_return
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	altivec_unavailable_tm
 	b	interrupt_return
@@ -2442,7 +2421,6 @@ BEGIN_FTR_SECTION
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
-	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	altivec_unavailable_exception
 	b	interrupt_return
@@ -2458,7 +2436,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
  */
 INT_DEFINE_BEGIN(vsx_unavailable)
 	IVEC=0xf40
-	IRECONCILE=0
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 	IKVM_REAL=1
 #endif
@@ -2487,7 +2464,6 @@ BEGIN_FTR_SECTION
 	b	load_up_vsx
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	vsx_unavailable_tm
 	b	interrupt_return
@@ -2495,7 +2471,6 @@ BEGIN_FTR_SECTION
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 #endif
-	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	vsx_unavailable_exception
 	b	interrupt_return
@@ -2830,7 +2805,6 @@ EXC_VIRT_NONE(0x5800, 0x100)
 INT_DEFINE_BEGIN(soft_nmi)
 	IVEC=0x900
 	ISTACK=0
-	IRECONCILE=0	/* Soft-NMI may fire under local_irq_disable */
 INT_DEFINE_END(soft_nmi)
 
 /*
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 34/39] powerpc/64: move account_stolen_time into its own function
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

This will be used by interrupt entry as well.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/cputime.h | 14 ++++++++++++++
 arch/powerpc/kernel/syscall_64.c   | 10 +---------
 2 files changed, 15 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index ed75d1c318e3..504f7fe6711a 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -87,6 +87,17 @@ static notrace inline void account_cpu_user_exit(void)
 	acct->starttime_user = tb;
 }
 
+static notrace inline void account_stolen_time(void)
+{
+#ifdef CONFIG_PPC_SPLPAR
+	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+		struct lppaca *lp = local_paca->lppaca_ptr;
+
+		if (unlikely(local_paca->dtl_ridx != be64_to_cpu(lp->dtl_idx)))
+			accumulate_stolen_time();
+	}
+#endif
+}
 
 #endif /* __KERNEL__ */
 #else /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
@@ -96,5 +107,8 @@ static inline void account_cpu_user_entry(void)
 static inline void account_cpu_user_exit(void)
 {
 }
+static notrace inline void account_stolen_time(void)
+{
+}
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 #endif /* __POWERPC_CPUTIME_H */
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 42f0ad4b2fbb..32f72965da26 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -69,15 +69,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
 
 	account_cpu_user_entry();
 
-#ifdef CONFIG_PPC_SPLPAR
-	if (IS_ENABLED(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) &&
-	    firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		struct lppaca *lp = local_paca->lppaca_ptr;
-
-		if (unlikely(local_paca->dtl_ridx != be64_to_cpu(lp->dtl_idx)))
-			accumulate_stolen_time();
-	}
-#endif
+	account_stolen_time();
 
 	/*
 	 * This is not required for the syscall exit path, but makes the
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 35/39] powerpc/64: entry cpu time accounting in C
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

There is no need for this to be in asm, use the new interrupt entry wrapper.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/interrupt.h |  6 ++++++
 arch/powerpc/include/asm/ppc_asm.h   | 24 ------------------------
 arch/powerpc/kernel/exceptions-64e.S |  1 -
 arch/powerpc/kernel/exceptions-64s.S |  5 -----
 4 files changed, 6 insertions(+), 30 deletions(-)

diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index e96d215f518a..ca8e08b18a16 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -4,6 +4,7 @@
 
 #include <linux/context_tracking.h>
 #include <linux/hardirq.h>
+#include <asm/cputime.h>
 #include <asm/ftrace.h>
 
 struct interrupt_state {
@@ -25,6 +26,9 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
 	if (user_mode(regs)) {
 		CT_WARN_ON(ct_state() != CONTEXT_USER);
 		user_exit_irqoff();
+
+		account_cpu_user_entry();
+		account_stolen_time();
 	} else {
 		/*
 		 * CT_WARN_ON comes here via program_check_exception,
@@ -37,6 +41,8 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
 
 #ifdef CONFIG_PPC_BOOK3E_64
 	state->ctx_state = exception_enter();
+	if (user_mode(regs))
+		account_cpu_user_entry();
 #endif
 }
 
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index cc1bca571332..3dceb64fc9af 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -25,7 +25,6 @@
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 #define ACCOUNT_CPU_USER_ENTRY(ptr, ra, rb)
 #define ACCOUNT_CPU_USER_EXIT(ptr, ra, rb)
-#define ACCOUNT_STOLEN_TIME
 #else
 #define ACCOUNT_CPU_USER_ENTRY(ptr, ra, rb)				\
 	MFTB(ra);			/* get timebase */		\
@@ -44,29 +43,6 @@
 	PPC_LL	ra, ACCOUNT_SYSTEM_TIME(ptr);				\
 	add	ra,ra,rb;		/* add on to system time */	\
 	PPC_STL	ra, ACCOUNT_SYSTEM_TIME(ptr)
-
-#ifdef CONFIG_PPC_SPLPAR
-#define ACCOUNT_STOLEN_TIME						\
-BEGIN_FW_FTR_SECTION;							\
-	beq	33f;							\
-	/* from user - see if there are any DTL entries to process */	\
-	ld	r10,PACALPPACAPTR(r13);	/* get ptr to VPA */		\
-	ld	r11,PACA_DTL_RIDX(r13);	/* get log read index */	\
-	addi	r10,r10,LPPACA_DTLIDX;					\
-	LDX_BE	r10,0,r10;		/* get log write index */	\
-	cmpd	cr1,r11,r10;						\
-	beq+	cr1,33f;						\
-	bl	accumulate_stolen_time;				\
-	ld	r12,_MSR(r1);						\
-	andi.	r10,r12,MSR_PR;		/* Restore cr0 (coming from user) */ \
-33:									\
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
-
-#else  /* CONFIG_PPC_SPLPAR */
-#define ACCOUNT_STOLEN_TIME
-
-#endif /* CONFIG_PPC_SPLPAR */
-
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 /*
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 003999c7836c..e8eb9992a270 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -398,7 +398,6 @@ exc_##n##_common:							    \
 	std	r10,_NIP(r1);		/* save SRR0 to stackframe */	    \
 	std	r11,_MSR(r1);		/* save SRR1 to stackframe */	    \
 	beq	2f;			/* if from kernel mode */	    \
-	ACCOUNT_CPU_USER_ENTRY(r13,r10,r11);/* accounting (uses cr0+eq) */  \
 2:	ld	r3,excf+EX_R10(r13);	/* get back r10 */		    \
 	ld	r4,excf+EX_R11(r13);	/* get back r11 */		    \
 	mfspr	r5,scratch;		/* get back r13 */		    \
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 39630b3f78b0..94b89ea123f3 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -577,7 +577,6 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real)
 	kuap_save_amr_and_lock r9, r10, cr1, cr0
 	.endif
 	beq	101f			/* if from kernel mode		*/
-	ACCOUNT_CPU_USER_ENTRY(r13, r9, r10)
 BEGIN_FTR_SECTION
 	ld	r9,IAREA+EX_PPR(r13)	/* Read PPR from paca		*/
 	std	r9,_PPR(r1)
@@ -645,10 +644,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	ld	r11,exception_marker@toc(r2)
 	std	r10,RESULT(r1)		/* clear regs->result		*/
 	std	r11,STACK_FRAME_OVERHEAD-16(r1) /* mark the frame	*/
-
-	.if ISTACK
-	ACCOUNT_STOLEN_TIME
-	.endif
 .endm
 
 /*
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 36/39] powerpc: move NMI entry/exit code into wrapper
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

This moves the common NMI entry and exit code into the interrupt handler
wrappers.

This changes the behaviour of soft-NMI (watchdog) and HMI interrupts, and
also MCE interrupts on 64e, by adding missing parts of the NMI entry to
them.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/interrupt.h | 24 +++++++++++++++++++
 arch/powerpc/kernel/mce.c            | 11 ---------
 arch/powerpc/kernel/traps.c          | 35 +++++-----------------------
 arch/powerpc/kernel/watchdog.c       | 10 ++++----
 4 files changed, 34 insertions(+), 46 deletions(-)

diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index ca8e08b18a16..879a0b2705d6 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -94,14 +94,38 @@ static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct int
 }
 
 struct interrupt_nmi_state {
+#ifdef CONFIG_PPC64
+	u8 ftrace_enabled;
+#endif
 };
 
 static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
 {
+#ifdef CONFIG_PPC64
+	state->ftrace_enabled = this_cpu_get_ftrace_enabled();
+	this_cpu_set_ftrace_enabled(0);
+#endif
+
+	/*
+	 * Do not use nmi_enter() for pseries hash guest taking a real-mode
+	 * NMI because not everything it touches is within the RMA limit.
+	 */
+	if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64) ||
+			!firmware_has_feature(FW_FEATURE_LPAR) ||
+			radix_enabled() || (mfmsr() & MSR_DR))
+		nmi_enter();
 }
 
 static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
 {
+	if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64) ||
+			!firmware_has_feature(FW_FEATURE_LPAR) ||
+			radix_enabled() || (mfmsr() & MSR_DR))
+		nmi_exit();
+
+#ifdef CONFIG_PPC64
+	this_cpu_set_ftrace_enabled(state->ftrace_enabled);
+#endif
 }
 
 /**
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 54269947113d..51456217ec40 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -592,12 +592,6 @@ EXPORT_SYMBOL_GPL(machine_check_print_event_info);
 DEFINE_INTERRUPT_HANDLER_NMI(machine_check_early)
 {
 	long handled = 0;
-	u8 ftrace_enabled = this_cpu_get_ftrace_enabled();
-
-	this_cpu_set_ftrace_enabled(0);
-	/* Do not use nmi_enter/exit for pseries hpte guest */
-	if (radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR))
-		nmi_enter();
 
 	hv_nmi_check_nonrecoverable(regs);
 
@@ -607,11 +601,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_early)
 	if (ppc_md.machine_check_early)
 		handled = ppc_md.machine_check_early(regs);
 
-	if (radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR))
-		nmi_exit();
-
-	this_cpu_set_ftrace_enabled(ftrace_enabled);
-
 	return handled;
 }
 
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index f37583d57442..9e5574756689 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -435,11 +435,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
 {
 	unsigned long hsrr0, hsrr1;
 	bool saved_hsrrs = false;
-	u8 ftrace_enabled = this_cpu_get_ftrace_enabled();
-
-	this_cpu_set_ftrace_enabled(0);
-
-	nmi_enter();
 
 	/*
 	 * System reset can interrupt code where HSRRs are live and MSR[RI]=1.
@@ -514,10 +509,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
 		mtspr(SPRN_HSRR1, hsrr1);
 	}
 
-	nmi_exit();
-
-	this_cpu_set_ftrace_enabled(ftrace_enabled);
-
 	/* What should we do here? We could issue a shutdown or hard reset. */
 
 	return 0;
@@ -809,6 +800,12 @@ void die_mce(const char *str, struct pt_regs *regs, long err)
 }
 NOKPROBE_SYMBOL(die_mce);
 
+/*
+ * BOOK3S_64 does not call this handler as a non-maskable interrupt
+ * (it uses its own early real-mode handler to handle the MCE proper
+ * and then raises irq_work to call this handler when interrupts are
+ * enabled).
+ */
 #ifdef CONFIG_PPC_BOOK3S_64
 DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception)
 #else
@@ -817,20 +814,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
 {
 	int recover = 0;
 
-	/*
-	 * BOOK3S_64 does not call this handler as a non-maskable interrupt
-	 * (it uses its own early real-mode handler to handle the MCE proper
-	 * and then raises irq_work to call this handler when interrupts are
-	 * enabled).
-	 *
-	 * This is silly. The BOOK3S_64 should just call a different function
-	 * rather than expecting semantics to magically change. Something
-	 * like 'non_nmi_machine_check_exception()', perhaps?
-	 */
-	const bool nmi = !IS_ENABLED(CONFIG_PPC_BOOK3S_64);
-
-	if (nmi) nmi_enter();
-
 	__this_cpu_inc(irq_stat.mce_exceptions);
 
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
@@ -862,8 +845,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
 	if (!(regs->msr & MSR_RI))
 		die_mce("Unrecoverable Machine check", regs, SIGBUS);
 
-	if (nmi) nmi_exit();
-
 #ifdef CONFIG_PPC_BOOK3S_64
 	return;
 #else
@@ -1885,14 +1866,10 @@ DEFINE_INTERRUPT_HANDLER(vsx_unavailable_tm)
 #ifdef CONFIG_PPC64
 DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi)
 {
-	nmi_enter();
-
 	__this_cpu_inc(irq_stat.pmu_irqs);
 
 	perf_irq(regs);
 
-	nmi_exit();
-
 	return 0;
 }
 #endif
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index 824b9376ac35..dc39534836a3 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -254,11 +254,12 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
 	int cpu = raw_smp_processor_id();
 	u64 tb;
 
+	/* should only arrive from kernel, with irqs disabled */
+	WARN_ON_ONCE(!arch_irq_disabled_regs(regs));
+
 	if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
 		return 0;
 
-	nmi_enter();
-
 	__this_cpu_inc(irq_stat.soft_nmi_irqs);
 
 	tb = get_tb();
@@ -266,7 +267,7 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
 		wd_smp_lock(&flags);
 		if (cpumask_test_cpu(cpu, &wd_smp_cpus_stuck)) {
 			wd_smp_unlock(&flags);
-			goto out;
+			return 0;
 		}
 		set_cpu_stuck(cpu, tb);
 
@@ -290,9 +291,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
 	if (wd_panic_timeout_tb < 0x7fffffff)
 		mtspr(SPRN_DEC, wd_panic_timeout_tb);
 
-out:
-	nmi_exit();
-
 	return 0;
 }
 
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 37/39] powerpc/64s: move NMI soft-mask handling to C
From: Nicholas Piggin @ 2021-01-15 16:50 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin
In-Reply-To: <20210115165012.1260253-1-npiggin@gmail.com>

Saving and restoring soft-mask state can now be done in C using the
interrupt handler wrapper functions.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/interrupt.h | 26 ++++++++++++
 arch/powerpc/kernel/exceptions-64s.S | 60 ----------------------------
 2 files changed, 26 insertions(+), 60 deletions(-)

diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 879a0b2705d6..5f4e304a98d9 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -95,6 +95,10 @@ static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct int
 
 struct interrupt_nmi_state {
 #ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
+	u8 irq_soft_mask;
+	u8 irq_happened;
+#endif
 	u8 ftrace_enabled;
 #endif
 };
@@ -102,6 +106,21 @@ struct interrupt_nmi_state {
 static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
 {
 #ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
+	state->irq_soft_mask = local_paca->irq_soft_mask;
+	state->irq_happened = local_paca->irq_happened;
+
+	/*
+	 * Set IRQS_ALL_DISABLED unconditionally so irqs_disabled() does
+	 * the right thing, and set IRQ_HARD_DIS. We do not want to reconcile
+	 * because that goes through irq tracing which we don't want in NMI.
+	 */
+	local_paca->irq_soft_mask = IRQS_ALL_DISABLED;
+	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+	/* Don't do any per-CPU operations until interrupt state is fixed */
+	state->ftrace_enabled = this_cpu_get_ftrace_enabled();
+#endif
 	state->ftrace_enabled = this_cpu_get_ftrace_enabled();
 	this_cpu_set_ftrace_enabled(0);
 #endif
@@ -125,6 +144,13 @@ static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct inter
 
 #ifdef CONFIG_PPC64
 	this_cpu_set_ftrace_enabled(state->ftrace_enabled);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+	/* Check we didn't change the pending interrupt mask. */
+	WARN_ON_ONCE((state->irq_happened | PACA_IRQ_HARD_DIS) != local_paca->irq_happened);
+	local_paca->irq_happened = state->irq_happened;
+	local_paca->irq_soft_mask = state->irq_soft_mask;
+#endif
 #endif
 }
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 94b89ea123f3..2fca2bad6b02 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1008,20 +1008,6 @@ EXC_COMMON_BEGIN(system_reset_common)
 	ld	r1,PACA_NMI_EMERG_SP(r13)
 	subi	r1,r1,INT_FRAME_SIZE
 	__GEN_COMMON_BODY system_reset
-	/*
-	 * Set IRQS_ALL_DISABLED unconditionally so irqs_disabled() does
-	 * the right thing. We do not want to reconcile because that goes
-	 * through irq tracing which we don't want in NMI.
-	 *
-	 * Save PACAIRQHAPPENED to RESULT (otherwise unused), and set HARD_DIS
-	 * as we are running with MSR[EE]=0.
-	 */
-	li	r10,IRQS_ALL_DISABLED
-	stb	r10,PACAIRQSOFTMASK(r13)
-	lbz	r10,PACAIRQHAPPENED(r13)
-	std	r10,RESULT(r1)
-	ori	r10,r10,PACA_IRQ_HARD_DIS
-	stb	r10,PACAIRQHAPPENED(r13)
 
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	system_reset_exception
@@ -1037,14 +1023,6 @@ EXC_COMMON_BEGIN(system_reset_common)
 	subi	r10,r10,1
 	sth	r10,PACA_IN_NMI(r13)
 
-	/*
-	 * Restore soft mask settings.
-	 */
-	ld	r10,RESULT(r1)
-	stb	r10,PACAIRQHAPPENED(r13)
-	ld	r10,SOFTE(r1)
-	stb	r10,PACAIRQSOFTMASK(r13)
-
 	kuap_kernel_restore r9, r10
 	EXCEPTION_RESTORE_REGS
 	RFI_TO_USER_OR_KERNEL
@@ -1190,30 +1168,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	li	r10,MSR_RI
 	mtmsrd	r10,1
 
-	/*
-	 * Set IRQS_ALL_DISABLED and save PACAIRQHAPPENED (see
-	 * system_reset_common)
-	 */
-	li	r10,IRQS_ALL_DISABLED
-	stb	r10,PACAIRQSOFTMASK(r13)
-	lbz	r10,PACAIRQHAPPENED(r13)
-	std	r10,RESULT(r1)
-	ori	r10,r10,PACA_IRQ_HARD_DIS
-	stb	r10,PACAIRQHAPPENED(r13)
-
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	machine_check_early
 	std	r3,RESULT(r1)	/* Save result */
 	ld	r12,_MSR(r1)
 
-	/*
-	 * Restore soft mask settings.
-	 */
-	ld	r10,RESULT(r1)
-	stb	r10,PACAIRQHAPPENED(r13)
-	ld	r10,SOFTE(r1)
-	stb	r10,PACAIRQSOFTMASK(r13)
-
 #ifdef CONFIG_PPC_P7_NAP
 	/*
 	 * Check if thread was in power saving mode. We come here when any
@@ -2818,17 +2777,6 @@ EXC_COMMON_BEGIN(soft_nmi_common)
 	subi	r1,r1,INT_FRAME_SIZE
 	__GEN_COMMON_BODY soft_nmi
 
-	/*
-	 * Set IRQS_ALL_DISABLED and save PACAIRQHAPPENED (see
-	 * system_reset_common)
-	 */
-	li	r10,IRQS_ALL_DISABLED
-	stb	r10,PACAIRQSOFTMASK(r13)
-	lbz	r10,PACAIRQHAPPENED(r13)
-	std	r10,RESULT(r1)
-	ori	r10,r10,PACA_IRQ_HARD_DIS
-	stb	r10,PACAIRQHAPPENED(r13)
-
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	soft_nmi_interrupt
 
@@ -2836,14 +2784,6 @@ EXC_COMMON_BEGIN(soft_nmi_common)
 	li	r9,0
 	mtmsrd	r9,1
 
-	/*
-	 * Restore soft mask settings.
-	 */
-	ld	r10,RESULT(r1)
-	stb	r10,PACAIRQHAPPENED(r13)
-	ld	r10,SOFTE(r1)
-	stb	r10,PACAIRQSOFTMASK(r13)
-
 	kuap_kernel_restore r9, r10
 	EXCEPTION_RESTORE_REGS hsrr=0
 	RFI_TO_KERNEL
-- 
2.23.0


^ permalink raw reply related


This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox