LinuxPPC-Dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v5 01/22] powerpc/32s: Add missing call to kuep_lock on syscall entry
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

Userspace Execution protection and fast syscall entry were implemented
independently from each other and were both merged in kernel 5.2,
leading to syscall entry missing userspace execution protection.

On syscall entry, execution of user space memory must be
locked in the same way as on exception entry.

Fixes: b86fb88855ea ("powerpc/32: implement fast entry for syscalls on non BOOKE")
Cc: stable@vger.kernel.org
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/entry_32.S | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index b102b40c4988..b1e36602c013 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -351,6 +351,9 @@ trace_syscall_entry_irq_off:
 
 	.globl	transfer_to_syscall
 transfer_to_syscall:
+#ifdef CONFIG_PPC_BOOK3S_32
+	kuep_lock r11, r12
+#endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	andi.	r12,r9,MSR_EE
 	beq-	trace_syscall_entry_irq_off
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 03/22] powerpc/32: On syscall entry, enable instruction translation at the same time as data
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

On 40x and 8xx, kernel text is pinned.
On book3s/32, kernel text is mapped by BATs.

Enable instruction translation at the same time as data translation, it
makes things simpler.

MSR_RI can also be set at the same time because srr0/srr1 are already
saved and r1 is set properly.

On booke, translation is always on, so at the end all PPC32
have translation on early.

This reduces null_syscall benchmark by 13 cycles on 8xx
(296 ==> 283 cycles).

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/head_32.h    | 26 +++++++++-----------------
 arch/powerpc/kernel/head_booke.h |  7 ++-----
 2 files changed, 11 insertions(+), 22 deletions(-)

diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index fdc07beab844..4029c51dce5d 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -125,9 +125,13 @@
 	lwz	r1,TASK_STACK-THREAD(r12)
 	beq-	99f
 	addi	r1, r1, THREAD_SIZE - INT_FRAME_SIZE
-	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~(MSR_IR | MSR_RI)) /* can take DTLB miss */
-	mtmsr	r10
-	isync
+	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL)		/* can take exceptions */
+	mtspr	SPRN_SRR1, r10
+	lis	r10, 1f@h
+	ori	r10, r10, 1f@l
+	mtspr	SPRN_SRR0, r10
+	rfi
+1:
 	tovirt(r12, r12)
 	stw	r11,GPR1(r1)
 	stw	r11,0(r1)
@@ -141,9 +145,6 @@
 	stw	r10,_CCR(r11)		/* save registers */
 #ifdef CONFIG_40x
 	rlwinm	r9,r9,0,14,12		/* clear MSR_WE (necessary?) */
-#else
-	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~MSR_IR) /* can take exceptions */
-	mtmsr	r10			/* (except for mach check in rtas) */
 #endif
 	lis	r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
 	stw	r2,GPR2(r11)
@@ -180,8 +181,6 @@
 #endif
 
 3:
-	lis	r11, transfer_to_syscall@h
-	ori	r11, r11, transfer_to_syscall@l
 #ifdef CONFIG_TRACE_IRQFLAGS
 	/*
 	 * If MSR is changing we need to keep interrupts disabled at this point
@@ -193,15 +192,8 @@
 #else
 	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL | MSR_EE)
 #endif
-#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
-	mtspr	SPRN_NRI, r0
-#endif
-	mtspr	SPRN_SRR1,r10
-	mtspr	SPRN_SRR0,r11
-	rfi				/* jump to handler, enable MMU */
-#ifdef CONFIG_40x
-	b .	/* Prevent prefetch past rfi */
-#endif
+	mtmsr	r10
+	b	transfer_to_syscall		/* jump to handler */
 99:	b	ret_from_kernel_syscall
 .endm
 
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 706cd9368992..b3c502c503a0 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -157,8 +157,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 	stw	r12,4(r11)
 
 3:
-	lis	r11, transfer_to_syscall@h
-	ori	r11, r11, transfer_to_syscall@l
 #ifdef CONFIG_TRACE_IRQFLAGS
 	/*
 	 * If MSR is changing we need to keep interrupts disabled at this point
@@ -172,9 +170,8 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 	lis	r10, (MSR_KERNEL | MSR_EE)@h
 	ori	r10, r10, (MSR_KERNEL | MSR_EE)@l
 #endif
-	mtspr	SPRN_SRR1,r10
-	mtspr	SPRN_SRR0,r11
-	rfi				/* jump to handler, enable MMU */
+	mtmsr	r10
+	b	transfer_to_syscall	/* jump to handler */
 99:	b	ret_from_kernel_syscall
 .endm
 
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 04/22] powerpc/32: Reorder instructions to avoid using CTR in syscall entry
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

Now that we are using rfi instead of mtmsr to reactivate MMU, it is
possible to reorder instructions and avoid the need to use CTR for
stashing SRR0.

null_syscall on 8xx is reduced by 3 cycles (283 => 280 cycles).

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/head_32.h | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index 4029c51dce5d..24dc326e0d56 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -116,30 +116,28 @@
 .endm
 
 .macro SYSCALL_ENTRY trapno
-	mfspr	r12,SPRN_SPRG_THREAD
 	mfspr	r9, SPRN_SRR1
-	mfspr	r11, SPRN_SRR0
-	mtctr	r11
+	mfspr	r10, SPRN_SRR0
 	andi.	r11, r9, MSR_PR
+	beq-	99f
+	LOAD_REG_IMMEDIATE(r11, MSR_KERNEL)		/* can take exceptions */
+	lis	r12, 1f@h
+	ori	r12, r12, 1f@l
+	mtspr	SPRN_SRR1, r11
+	mtspr	SPRN_SRR0, r12
+	mfspr	r12,SPRN_SPRG_THREAD
 	mr	r11, r1
 	lwz	r1,TASK_STACK-THREAD(r12)
-	beq-	99f
+	tovirt(r12, r12)
 	addi	r1, r1, THREAD_SIZE - INT_FRAME_SIZE
-	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL)		/* can take exceptions */
-	mtspr	SPRN_SRR1, r10
-	lis	r10, 1f@h
-	ori	r10, r10, 1f@l
-	mtspr	SPRN_SRR0, r10
 	rfi
 1:
-	tovirt(r12, r12)
 	stw	r11,GPR1(r1)
 	stw	r11,0(r1)
 	mr	r11, r1
+	stw	r10,_NIP(r11)
 	mflr	r10
 	stw	r10, _LINK(r11)
-	mfctr	r10
-	stw	r10,_NIP(r11)
 	mfcr	r10
 	rlwinm	r10,r10,0,4,2	/* Clear SO bit in CR */
 	stw	r10,_CCR(r11)		/* save registers */
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 00/22] powerpc/32: Implement C syscall entry/exit
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel

This series implements C syscall entry/exit for PPC32. It reuses
the work already done for PPC64.

This series is based on today's merge-test (b6f72fc05389e3fc694bf5a5fa1bbd33f61879e0)

In terms on performance we have the following number of cycles on an
8xx running null_syscall benchmark:
- mainline: 296 cycles
- after patch 4: 283 cycles
- after patch 16: 304 cycles
- after patch 17: 348 cycles
- at the end of the series: 320 cycles

So in summary, we have a degradation of performance of 8% on null_syscall.

I think it is not a big degradation, it is worth it.

v4 was the first mature version.

v5:
- Comments from Nick
- Converted booke DBCR0 handling in C
- Removed convertion of KUAP restore in C (will be done as part of interrupt entry/exit porting to C)
- Added a few more changes in preparatory patches to prepare for interrupt entry/exit in C which will follow

Christophe Leroy (22):
  powerpc/32s: Add missing call to kuep_lock on syscall entry
  powerpc/32: Always enable data translation on syscall entry
  powerpc/32: On syscall entry, enable instruction translation at the
    same time as data
  powerpc/32: Reorder instructions to avoid using CTR in syscall entry
  powerpc/irq: Add helper to set regs->softe
  powerpc/irq: Rework helpers that manipulate MSR[EE/RI]
  powerpc/irq: Add stub irq_soft_mask_return() for PPC32
  powerpc/syscall: Rename syscall_64.c into interrupt.c
  powerpc/syscall: Make interrupt.c buildable on PPC32
  powerpc/syscall: Use is_compat_task()
  powerpc/syscall: Save r3 in regs->orig_r3
  powerpc/syscall: Change condition to check MSR_RI
  powerpc/32: Always save non volatile GPRs at syscall entry
  powerpc/syscall: implement system call entry/exit logic in C for PPC32
  powerpc/32: Remove verification of MSR_PR on syscall in the ASM entry
  powerpc/syscall: Avoid stack frame in likely part of
    system_call_exception()
  powerpc/syscall: Do not check unsupported scv vector on PPC32
  powerpc/syscall: Remove FULL_REGS verification in
    system_call_exception
  powerpc/syscall: Optimise checks in beginning of
    system_call_exception()
  powerpc/syscall: Avoid storing 'current' in another pointer
  powerpc/32: Remove the counter in global_dbcr0
  powerpc/32: Handle bookE debugging in C in syscall entry/exit

 arch/powerpc/include/asm/hw_irq.h             |  91 +++--
 arch/powerpc/include/asm/ptrace.h             |   5 +
 arch/powerpc/include/asm/reg.h                |   1 +
 arch/powerpc/include/asm/reg_booke.h          |   3 +
 arch/powerpc/kernel/Makefile                  |   4 +-
 arch/powerpc/kernel/entry_32.S                | 321 ++----------------
 arch/powerpc/kernel/entry_64.S                |   2 -
 arch/powerpc/kernel/head_32.h                 |  96 +-----
 arch/powerpc/kernel/head_booke.h              |  51 +--
 .../kernel/{syscall_64.c => interrupt.c}      | 120 +++++--
 arch/powerpc/kernel/syscalls/syscall.tbl      |  20 +-
 11 files changed, 218 insertions(+), 496 deletions(-)
 rename arch/powerpc/kernel/{syscall_64.c => interrupt.c} (80%)

-- 
2.25.0


^ permalink raw reply

* [PATCH v5 05/22] powerpc/irq: Add helper to set regs->softe
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

regs->softe doesn't exist on PPC32.

Add irq_soft_mask_regs_set_state() helper to set regs->softe.
This helper will void on PPC32.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/include/asm/hw_irq.h | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 614957f74cee..ed0c3b049dfd 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -38,6 +38,8 @@
 #define PACA_IRQ_MUST_HARD_MASK	(PACA_IRQ_EE)
 #endif
 
+#endif /* CONFIG_PPC64 */
+
 /*
  * flags for paca->irq_soft_mask
  */
@@ -46,8 +48,6 @@
 #define IRQS_PMI_DISABLED	2
 #define IRQS_ALL_DISABLED	(IRQS_DISABLED | IRQS_PMI_DISABLED)
 
-#endif /* CONFIG_PPC64 */
-
 #ifndef __ASSEMBLY__
 
 #ifdef CONFIG_PPC64
@@ -287,6 +287,10 @@ extern void irq_set_pending_from_srr1(unsigned long srr1);
 
 extern void force_external_irq_replay(void);
 
+static inline void irq_soft_mask_regs_set_state(struct pt_regs *regs, unsigned long val)
+{
+	regs->softe = val;
+}
 #else /* CONFIG_PPC64 */
 
 static inline unsigned long arch_local_save_flags(void)
@@ -355,6 +359,9 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs)
 
 static inline void may_hard_irq_enable(void) { }
 
+static inline void irq_soft_mask_regs_set_state(struct pt_regs *regs, unsigned long val)
+{
+}
 #endif /* CONFIG_PPC64 */
 
 #define ARCH_IRQ_INIT_FLAGS	IRQ_NOREQUEST
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 02/22] powerpc/32: Always enable data translation on syscall entry
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

If the code can use a stack in vm area, it can also use a
stack in linear space.

Simplify code by removing old non VMAP stack code on PPC32 in syscall.

That means the data translation is now re-enabled early in
syscall entry in all cases, not only when using VMAP stacks.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/head_32.h    | 23 +----------------------
 arch/powerpc/kernel/head_booke.h |  2 --
 2 files changed, 1 insertion(+), 24 deletions(-)

diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index a2f72c966baf..fdc07beab844 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -118,7 +118,6 @@
 .macro SYSCALL_ENTRY trapno
 	mfspr	r12,SPRN_SPRG_THREAD
 	mfspr	r9, SPRN_SRR1
-#ifdef CONFIG_VMAP_STACK
 	mfspr	r11, SPRN_SRR0
 	mtctr	r11
 	andi.	r11, r9, MSR_PR
@@ -126,30 +125,16 @@
 	lwz	r1,TASK_STACK-THREAD(r12)
 	beq-	99f
 	addi	r1, r1, THREAD_SIZE - INT_FRAME_SIZE
-	li	r10, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */
+	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~(MSR_IR | MSR_RI)) /* can take DTLB miss */
 	mtmsr	r10
 	isync
 	tovirt(r12, r12)
 	stw	r11,GPR1(r1)
 	stw	r11,0(r1)
 	mr	r11, r1
-#else
-	andi.	r11, r9, MSR_PR
-	lwz	r11,TASK_STACK-THREAD(r12)
-	beq-	99f
-	addi	r11, r11, THREAD_SIZE - INT_FRAME_SIZE
-	tophys(r11, r11)
-	stw	r1,GPR1(r11)
-	stw	r1,0(r11)
-	tovirt(r1, r11)		/* set new kernel sp */
-#endif
 	mflr	r10
 	stw	r10, _LINK(r11)
-#ifdef CONFIG_VMAP_STACK
 	mfctr	r10
-#else
-	mfspr	r10,SPRN_SRR0
-#endif
 	stw	r10,_NIP(r11)
 	mfcr	r10
 	rlwinm	r10,r10,0,4,2	/* Clear SO bit in CR */
@@ -157,11 +142,7 @@
 #ifdef CONFIG_40x
 	rlwinm	r9,r9,0,14,12		/* clear MSR_WE (necessary?) */
 #else
-#ifdef CONFIG_VMAP_STACK
 	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~MSR_IR) /* can take exceptions */
-#else
-	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~(MSR_IR|MSR_DR)) /* can take exceptions */
-#endif
 	mtmsr	r10			/* (except for mach check in rtas) */
 #endif
 	lis	r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
@@ -190,7 +171,6 @@
 	li	r12,-1			/* clear all pending debug events */
 	mtspr	SPRN_DBSR,r12
 	lis	r11,global_dbcr0@ha
-	tophys(r11,r11)
 	addi	r11,r11,global_dbcr0@l
 	lwz	r12,0(r11)
 	mtspr	SPRN_DBCR0,r12
@@ -200,7 +180,6 @@
 #endif
 
 3:
-	tovirt_novmstack r2, r2 	/* set r2 to current */
 	lis	r11, transfer_to_syscall@h
 	ori	r11, r11, transfer_to_syscall@l
 #ifdef CONFIG_TRACE_IRQFLAGS
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index bf33af714d11..706cd9368992 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -144,7 +144,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 	li	r12,-1			/* clear all pending debug events */
 	mtspr	SPRN_DBSR,r12
 	lis	r11,global_dbcr0@ha
-	tophys(r11,r11)
 	addi	r11,r11,global_dbcr0@l
 #ifdef CONFIG_SMP
 	lwz	r10, TASK_CPU(r2)
@@ -158,7 +157,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 	stw	r12,4(r11)
 
 3:
-	tovirt(r2, r2)			/* set r2 to current */
 	lis	r11, transfer_to_syscall@h
 	ori	r11, r11, transfer_to_syscall@l
 #ifdef CONFIG_TRACE_IRQFLAGS
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 06/22] powerpc/irq: Rework helpers that manipulate MSR[EE/RI]
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

In preparation of porting PPC32 to C syscall entry/exit,
rewrite the following helpers as static inline functions and
add support for PPC32 in them:
	__hard_irq_enable()
	__hard_irq_disable()
	__hard_EE_RI_disable()
	__hard_RI_enable()

Then use them in PPC32 version of arch_local_irq_disable()
and arch_local_irq_enable() to avoid code duplication.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/include/asm/hw_irq.h | 75 +++++++++++++++++++++----------
 arch/powerpc/include/asm/reg.h    |  1 +
 2 files changed, 52 insertions(+), 24 deletions(-)

diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index ed0c3b049dfd..4739f61e632c 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -50,6 +50,55 @@
 
 #ifndef __ASSEMBLY__
 
+static inline void __hard_irq_enable(void)
+{
+	if (IS_ENABLED(CONFIG_BOOKE) || IS_ENABLED(CONFIG_40x))
+		wrtee(MSR_EE);
+	else if (IS_ENABLED(CONFIG_PPC_8xx))
+		wrtspr(SPRN_EIE);
+	else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+		__mtmsrd(MSR_EE | MSR_RI, 1);
+	else
+		mtmsr(mfmsr() | MSR_EE);
+}
+
+static inline void __hard_irq_disable(void)
+{
+	if (IS_ENABLED(CONFIG_BOOKE) || IS_ENABLED(CONFIG_40x))
+		wrtee(0);
+	else if (IS_ENABLED(CONFIG_PPC_8xx))
+		wrtspr(SPRN_EID);
+	else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+		__mtmsrd(MSR_RI, 1);
+	else
+		mtmsr(mfmsr() & ~MSR_EE);
+}
+
+static inline void __hard_EE_RI_disable(void)
+{
+	if (IS_ENABLED(CONFIG_BOOKE) || IS_ENABLED(CONFIG_40x))
+		wrtee(0);
+	else if (IS_ENABLED(CONFIG_PPC_8xx))
+		wrtspr(SPRN_NRI);
+	else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+		__mtmsrd(0, 1);
+	else
+		mtmsr(mfmsr() & ~(MSR_EE | MSR_RI));
+}
+
+static inline void __hard_RI_enable(void)
+{
+	if (IS_ENABLED(CONFIG_BOOKE) || IS_ENABLED(CONFIG_40x))
+		return;
+
+	if (IS_ENABLED(CONFIG_PPC_8xx))
+		wrtspr(SPRN_EID);
+	else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+		__mtmsrd(MSR_RI, 1);
+	else
+		mtmsr(mfmsr() | MSR_RI);
+}
+
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 
@@ -212,18 +261,6 @@ static inline bool arch_irqs_disabled(void)
 
 #endif /* CONFIG_PPC_BOOK3S */
 
-#ifdef CONFIG_PPC_BOOK3E
-#define __hard_irq_enable()	wrtee(MSR_EE)
-#define __hard_irq_disable()	wrtee(0)
-#define __hard_EE_RI_disable()	wrtee(0)
-#define __hard_RI_enable()	do { } while (0)
-#else
-#define __hard_irq_enable()	__mtmsrd(MSR_EE|MSR_RI, 1)
-#define __hard_irq_disable()	__mtmsrd(MSR_RI, 1)
-#define __hard_EE_RI_disable()	__mtmsrd(0, 1)
-#define __hard_RI_enable()	__mtmsrd(MSR_RI, 1)
-#endif
-
 #define hard_irq_disable()	do {					\
 	unsigned long flags;						\
 	__hard_irq_disable();						\
@@ -322,22 +359,12 @@ static inline unsigned long arch_local_irq_save(void)
 
 static inline void arch_local_irq_disable(void)
 {
-	if (IS_ENABLED(CONFIG_BOOKE))
-		wrtee(0);
-	else if (IS_ENABLED(CONFIG_PPC_8xx))
-		wrtspr(SPRN_EID);
-	else
-		mtmsr(mfmsr() & ~MSR_EE);
+	__hard_irq_disable();
 }
 
 static inline void arch_local_irq_enable(void)
 {
-	if (IS_ENABLED(CONFIG_BOOKE))
-		wrtee(MSR_EE);
-	else if (IS_ENABLED(CONFIG_PPC_8xx))
-		wrtspr(SPRN_EIE);
-	else
-		mtmsr(mfmsr() | MSR_EE);
+	__hard_irq_enable();
 }
 
 static inline bool arch_irqs_disabled_flags(unsigned long flags)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index c5a3e856191c..bc4305ba00d0 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1375,6 +1375,7 @@
 #define mtmsr(v)	asm volatile("mtmsr %0" : \
 				     : "r" ((unsigned long)(v)) \
 				     : "memory")
+#define __mtmsrd(v, l)	BUILD_BUG()
 #define __MTMSR		"mtmsr"
 #endif
 
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 08/22] powerpc/syscall: Rename syscall_64.c into interrupt.c
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

syscall_64.c will be reused almost as is for PPC32.

As this file also contains functions to handle other types
of interrupts rename it interrupt.c

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/Makefile                      | 2 +-
 arch/powerpc/kernel/{syscall_64.c => interrupt.c} | 0
 2 files changed, 1 insertion(+), 1 deletion(-)
 rename arch/powerpc/kernel/{syscall_64.c => interrupt.c} (100%)

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index c173efd66c00..26ff8c6e06b7 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -60,7 +60,7 @@ obj-y				:= cputable.o syscalls.o \
 				   hw_breakpoint_constraints.o
 obj-y				+= ptrace/
 obj-$(CONFIG_PPC64)		+= setup_64.o \
-				   paca.o nvram_64.o note.o syscall_64.o
+				   paca.o nvram_64.o note.o interrupt.o
 obj-$(CONFIG_COMPAT)		+= sys_ppc32.o signal_32.o
 obj-$(CONFIG_VDSO32)		+= vdso32_wrapper.o
 obj-$(CONFIG_PPC_WATCHDOG)	+= watchdog.o
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/interrupt.c
similarity index 100%
rename from arch/powerpc/kernel/syscall_64.c
rename to arch/powerpc/kernel/interrupt.c
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 11/22] powerpc/syscall: Save r3 in regs->orig_r3
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

Save r3 in regs->orig_r3 in system_call_exception()

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v5: Removed the assembly one on SCV type system call
---
 arch/powerpc/kernel/entry_64.S  | 2 --
 arch/powerpc/kernel/interrupt.c | 2 ++
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 33ddfeef4fe9..a91c2def165d 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -108,7 +108,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 	li	r11,\trapnr
 	std	r11,_TRAP(r1)
 	std	r12,_CCR(r1)
-	std	r3,ORIG_GPR3(r1)
 	addi	r10,r1,STACK_FRAME_OVERHEAD
 	ld	r11,exception_marker@toc(r2)
 	std	r11,-16(r10)		/* "regshere" marker */
@@ -278,7 +277,6 @@ END_BTB_FLUSH_SECTION
 	std	r10,_LINK(r1)
 	std	r11,_TRAP(r1)
 	std	r12,_CCR(r1)
-	std	r3,ORIG_GPR3(r1)
 	addi	r10,r1,STACK_FRAME_OVERHEAD
 	ld	r11,exception_marker@toc(r2)
 	std	r11,-16(r10)		/* "regshere" marker */
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 46fd195ca659..1a2dec49f811 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -29,6 +29,8 @@ notrace long system_call_exception(long r3, long r4, long r5,
 {
 	syscall_fn f;
 
+	regs->orig_gpr3 = r3;
+
 	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
 		BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
 
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 07/22] powerpc/irq: Add stub irq_soft_mask_return() for PPC32
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

To allow building syscall_64.c smoothly on PPC32, add stub version
of irq_soft_mask_return().

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/include/asm/hw_irq.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 4739f61e632c..56a98936a6a9 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -330,6 +330,11 @@ static inline void irq_soft_mask_regs_set_state(struct pt_regs *regs, unsigned l
 }
 #else /* CONFIG_PPC64 */
 
+static inline notrace unsigned long irq_soft_mask_return(void)
+{
+	return 0;
+}
+
 static inline unsigned long arch_local_save_flags(void)
 {
 	return mfmsr();
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 10/22] powerpc/syscall: Use is_compat_task()
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

Instead of hard comparing task flags with _TIF_32BIT, use
is_compat_task(). The advantage is that it returns 0 on PPC32
allthough _TIF_32BIT is always set.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/interrupt.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 2dac4d2bb1cf..46fd195ca659 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -2,6 +2,8 @@
 
 #include <linux/context_tracking.h>
 #include <linux/err.h>
+#include <linux/compat.h>
+
 #include <asm/asm-prototypes.h>
 #include <asm/kup.h>
 #include <asm/cputime.h>
@@ -118,7 +120,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	/* May be faster to do array_index_nospec? */
 	barrier_nospec();
 
-	if (unlikely(is_32bit_task())) {
+	if (unlikely(is_compat_task())) {
 		f = (void *)compat_sys_call_table[r0];
 
 		r3 &= 0x00000000ffffffffULL;
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 09/22] powerpc/syscall: Make interrupt.c buildable on PPC32
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

To allow building interrupt.c on PPC32, ifdef out specific PPC64
code or use helpers which are available on both PP32 and PPC64

Modify Makefile to always build interrupt.o

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v5:
- Also for interrupt exit preparation
- Opted out kuap related code, ppc32 keeps it in ASM for the time being
---
 arch/powerpc/kernel/Makefile    |  4 ++--
 arch/powerpc/kernel/interrupt.c | 31 ++++++++++++++++++++++++-------
 2 files changed, 26 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 26ff8c6e06b7..163755b1cef4 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -57,10 +57,10 @@ obj-y				:= cputable.o syscalls.o \
 				   prom.o traps.o setup-common.o \
 				   udbg.o misc.o io.o misc_$(BITS).o \
 				   of_platform.o prom_parse.o firmware.o \
-				   hw_breakpoint_constraints.o
+				   hw_breakpoint_constraints.o interrupt.o
 obj-y				+= ptrace/
 obj-$(CONFIG_PPC64)		+= setup_64.o \
-				   paca.o nvram_64.o note.o interrupt.o
+				   paca.o nvram_64.o note.o
 obj-$(CONFIG_COMPAT)		+= sys_ppc32.o signal_32.o
 obj-$(CONFIG_VDSO32)		+= vdso32_wrapper.o
 obj-$(CONFIG_PPC_WATCHDOG)	+= watchdog.o
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index d6be4f9a67e5..2dac4d2bb1cf 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -39,7 +39,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
 		BUG_ON(!(regs->msr & MSR_RI));
 	BUG_ON(!(regs->msr & MSR_PR));
 	BUG_ON(!FULL_REGS(regs));
-	BUG_ON(regs->softe != IRQS_ENABLED);
+	BUG_ON(arch_irq_disabled_regs(regs));
 
 #ifdef CONFIG_PPC_PKEY
 	if (mmu_has_feature(MMU_FTR_PKEY)) {
@@ -65,7 +65,9 @@ notrace long system_call_exception(long r3, long r4, long r5,
 			isync();
 	} else
 #endif
+#ifdef CONFIG_PPC64
 		kuap_check_amr();
+#endif
 
 	account_cpu_user_entry();
 
@@ -77,7 +79,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	 * frame, or if the unwinder was taught the first stack frame always
 	 * returns to user with IRQS_ENABLED, this store could be avoided!
 	 */
-	regs->softe = IRQS_ENABLED;
+	irq_soft_mask_regs_set_state(regs, IRQS_ENABLED);
 
 	local_irq_enable();
 
@@ -151,6 +153,7 @@ static notrace inline bool __prep_irq_for_enabled_exit(bool clear_ri)
 		__hard_EE_RI_disable();
 	else
 		__hard_irq_disable();
+#ifdef CONFIG_PPC64
 	if (unlikely(lazy_irq_pending_nocheck())) {
 		/* Took an interrupt, may have more exit work to do. */
 		if (clear_ri)
@@ -162,7 +165,7 @@ static notrace inline bool __prep_irq_for_enabled_exit(bool clear_ri)
 	}
 	local_paca->irq_happened = 0;
 	irq_soft_mask_set(IRQS_ENABLED);
-
+#endif
 	return true;
 }
 
@@ -216,7 +219,9 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 
 	CT_WARN_ON(ct_state() == CONTEXT_USER);
 
+#ifdef CONFIG_PPC64
 	kuap_check_amr();
+#endif
 
 	regs->result = r3;
 
@@ -309,7 +314,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 
 	account_cpu_user_exit();
 
-#ifdef CONFIG_PPC_BOOK3S /* BOOK3E not yet using this */
+#ifdef CONFIG_PPC_BOOK3S_64 /* BOOK3E and ppc32 not using this */
 	/*
 	 * We do this at the end so that we do context switch with KERNEL AMR
 	 */
@@ -318,7 +323,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 	return ret;
 }
 
-#ifdef CONFIG_PPC_BOOK3S /* BOOK3E not yet using this */
+#ifndef CONFIG_PPC_BOOK3E_64 /* BOOK3E not yet using this */
 notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr)
 {
 #ifdef CONFIG_PPC_BOOK3E
@@ -333,14 +338,16 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
 		BUG_ON(!(regs->msr & MSR_RI));
 	BUG_ON(!(regs->msr & MSR_PR));
 	BUG_ON(!FULL_REGS(regs));
-	BUG_ON(regs->softe != IRQS_ENABLED);
+	BUG_ON(arch_irq_disabled_regs(regs));
 	CT_WARN_ON(ct_state() == CONTEXT_USER);
 
 	/*
 	 * We don't need to restore AMR on the way back to userspace for KUAP.
 	 * AMR can only have been unlocked if we interrupted the kernel.
 	 */
+#ifdef CONFIG_PPC64
 	kuap_check_amr();
+#endif
 
 	local_irq_save(flags);
 
@@ -407,7 +414,9 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
 	/*
 	 * We do this at the end so that we do context switch with KERNEL AMR
 	 */
+#ifdef CONFIG_PPC64
 	kuap_user_restore(regs);
+#endif
 	return ret;
 }
 
@@ -419,7 +428,9 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
 	unsigned long *ti_flagsp = &current_thread_info()->flags;
 	unsigned long flags;
 	unsigned long ret = 0;
+#ifdef CONFIG_PPC64
 	unsigned long amr;
+#endif
 
 	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && unlikely(!(regs->msr & MSR_RI)))
 		unrecoverable_exception(regs);
@@ -432,7 +443,9 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
 	if (TRAP(regs) != 0x700)
 		CT_WARN_ON(ct_state() == CONTEXT_USER);
 
+#ifdef CONFIG_PPC64
 	amr = kuap_get_and_check_amr();
+#endif
 
 	if (unlikely(*ti_flagsp & _TIF_EMULATE_STACK_STORE)) {
 		clear_bits(_TIF_EMULATE_STACK_STORE, ti_flagsp);
@@ -441,7 +454,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
 
 	local_irq_save(flags);
 
-	if (regs->softe == IRQS_ENABLED) {
+	if (!arch_irq_disabled_regs(regs)) {
 		/* Returning to a kernel context with local irqs enabled. */
 		WARN_ON_ONCE(!(regs->msr & MSR_EE));
 again:
@@ -458,8 +471,10 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
 	} else {
 		/* Returning to a kernel context with local irqs disabled. */
 		__hard_EE_RI_disable();
+#ifdef CONFIG_PPC64
 		if (regs->msr & MSR_EE)
 			local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+#endif
 	}
 
 
@@ -472,7 +487,9 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
 	 * which would cause Read-After-Write stalls. Hence, we take the AMR
 	 * value from the check above.
 	 */
+#ifdef CONFIG_PPC64
 	kuap_kernel_restore(regs, amr);
+#endif
 
 	return ret;
 }
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 12/22] powerpc/syscall: Change condition to check MSR_RI
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

In system_call_exception(), MSR_RI also needs to be checked on 8xx.
Only booke and 40x doesn't have MSR_RI.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v5: Also in interrupt exit prepare
---
 arch/powerpc/kernel/interrupt.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 1a2dec49f811..107ec39f05cb 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -39,7 +39,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
 
 	trace_hardirqs_off(); /* finish reconciling */
 
-	if (IS_ENABLED(CONFIG_PPC_BOOK3S))
+	if (!IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x))
 		BUG_ON(!(regs->msr & MSR_RI));
 	BUG_ON(!(regs->msr & MSR_PR));
 	BUG_ON(!FULL_REGS(regs));
@@ -338,7 +338,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
 	unsigned long flags;
 	unsigned long ret = 0;
 
-	if (IS_ENABLED(CONFIG_PPC_BOOK3S))
+	if (!IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x))
 		BUG_ON(!(regs->msr & MSR_RI));
 	BUG_ON(!(regs->msr & MSR_PR));
 	BUG_ON(!FULL_REGS(regs));
@@ -436,7 +436,8 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
 	unsigned long amr;
 #endif
 
-	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && unlikely(!(regs->msr & MSR_RI)))
+	if (!IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x) &&
+	    unlikely(!(regs->msr & MSR_RI)))
 		unrecoverable_exception(regs);
 	BUG_ON(regs->msr & MSR_PR);
 	BUG_ON(!FULL_REGS(regs));
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 14/22] powerpc/syscall: implement system call entry/exit logic in C for PPC32
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

That's port of PPC64 syscall entry/exit logic in C to PPC32.

Performancewise on 8xx:
Before : 304 cycles on null_syscall
After  : 348 cycles on null_syscall

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/entry_32.S   | 224 +++++--------------------------
 arch/powerpc/kernel/head_32.h    |  18 ---
 arch/powerpc/kernel/head_booke.h |  17 ---
 3 files changed, 30 insertions(+), 229 deletions(-)

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 97dc28a68465..bbf7ecea6fe0 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -329,117 +329,23 @@ stack_ovf:
 _ASM_NOKPROBE_SYMBOL(stack_ovf)
 #endif
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-trace_syscall_entry_irq_off:
-	/*
-	 * Syscall shouldn't happen while interrupts are disabled,
-	 * so let's do a warning here.
-	 */
-0:	trap
-	EMIT_BUG_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING
-	bl	trace_hardirqs_on
-
-	/* Now enable for real */
-	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL | MSR_EE)
-	mtmsr	r10
-
-	REST_GPR(0, r1)
-	REST_4GPRS(3, r1)
-	REST_2GPRS(7, r1)
-	b	DoSyscall
-#endif /* CONFIG_TRACE_IRQFLAGS */
-
 	.globl	transfer_to_syscall
 transfer_to_syscall:
 	SAVE_NVGPRS(r1)
 #ifdef CONFIG_PPC_BOOK3S_32
 	kuep_lock r11, r12
 #endif
-#ifdef CONFIG_TRACE_IRQFLAGS
-	andi.	r12,r9,MSR_EE
-	beq-	trace_syscall_entry_irq_off
-#endif /* CONFIG_TRACE_IRQFLAGS */
 
-/*
- * Handle a system call.
- */
-	.stabs	"arch/powerpc/kernel/",N_SO,0,0,0f
-	.stabs	"entry_32.S",N_SO,0,0,0f
-0:
-
-_GLOBAL(DoSyscall)
-	stw	r3,ORIG_GPR3(r1)
-	li	r12,0
-	stw	r12,RESULT(r1)
-#ifdef CONFIG_TRACE_IRQFLAGS
-	/* Make sure interrupts are enabled */
-	mfmsr	r11
-	andi.	r12,r11,MSR_EE
-	/* We came in with interrupts disabled, we WARN and mark them enabled
-	 * for lockdep now */
-0:	tweqi	r12, 0
-	EMIT_BUG_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING
-#endif /* CONFIG_TRACE_IRQFLAGS */
-	lwz	r11,TI_FLAGS(r2)
-	andi.	r11,r11,_TIF_SYSCALL_DOTRACE
-	bne-	syscall_dotrace
-syscall_dotrace_cont:
-	cmplwi	0,r0,NR_syscalls
-	lis	r10,sys_call_table@h
-	ori	r10,r10,sys_call_table@l
-	slwi	r0,r0,2
-	bge-	66f
-
-	barrier_nospec_asm
-	/*
-	 * Prevent the load of the handler below (based on the user-passed
-	 * system call number) being speculatively executed until the test
-	 * against NR_syscalls and branch to .66f above has
-	 * committed.
-	 */
+	/* Calling convention has r9 = orig r0, r10 = regs */
+	addi	r10,r1,STACK_FRAME_OVERHEAD
+	mr	r9,r0
+	stw	r10,THREAD+PT_REGS(r2)
+	bl	system_call_exception
 
-	lwzx	r10,r10,r0	/* Fetch system call handler [ptr] */
-	mtlr	r10
-	addi	r9,r1,STACK_FRAME_OVERHEAD
-	PPC440EP_ERR42
-	blrl			/* Call handler */
-	.globl	ret_from_syscall
 ret_from_syscall:
-#ifdef CONFIG_DEBUG_RSEQ
-	/* Check whether the syscall is issued inside a restartable sequence */
-	stw	r3,GPR3(r1)
-	addi    r3,r1,STACK_FRAME_OVERHEAD
-	bl      rseq_syscall
-	lwz	r3,GPR3(r1)
-#endif
-	mr	r6,r3
-	/* disable interrupts so current_thread_info()->flags can't change */
-	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)	/* doesn't include MSR_EE */
-	/* Note: We don't bother telling lockdep about it */
-	mtmsr	r10
-	lwz	r9,TI_FLAGS(r2)
-	li	r8,-MAX_ERRNO
-	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
-	bne-	syscall_exit_work
-	cmplw	0,r3,r8
-	blt+	syscall_exit_cont
-	lwz	r11,_CCR(r1)			/* Load CR */
-	neg	r3,r3
-	oris	r11,r11,0x1000	/* Set SO bit in CR */
-	stw	r11,_CCR(r1)
-syscall_exit_cont:
-	lwz	r8,_MSR(r1)
-#ifdef CONFIG_TRACE_IRQFLAGS
-	/* If we are going to return from the syscall with interrupts
-	 * off, we trace that here. It shouldn't normally happen.
-	 */
-	andi.	r10,r8,MSR_EE
-	bne+	1f
-	stw	r3,GPR3(r1)
-	bl      trace_hardirqs_off
-	lwz	r3,GPR3(r1)
-1:
-#endif /* CONFIG_TRACE_IRQFLAGS */
+	addi    r4,r1,STACK_FRAME_OVERHEAD
+	li	r5,0
+	bl	syscall_exit_prepare
 #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
 	/* If the process has its own DBCR0 value, load it up.  The internal
 	   debug mode bit tells us that dbcr0 should be loaded. */
@@ -453,12 +359,6 @@ syscall_exit_cont:
 	cmplwi	cr0,r5,0
 	bne-	2f
 #endif /* CONFIG_PPC_47x */
-1:
-BEGIN_FTR_SECTION
-	lwarx	r7,0,r1
-END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
-	stwcx.	r0,0,r1			/* to clear the reservation */
-	ACCOUNT_CPU_USER_EXIT(r2, r5, r7)
 #ifdef CONFIG_PPC_BOOK3S_32
 	kuep_unlock r5, r7
 #endif
@@ -466,21 +366,36 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	lwz	r4,_LINK(r1)
 	lwz	r5,_CCR(r1)
 	mtlr	r4
-	mtcr	r5
 	lwz	r7,_NIP(r1)
-	lwz	r2,GPR2(r1)
-	lwz	r1,GPR1(r1)
+	lwz	r8,_MSR(r1)
+	cmpwi	r3,0
+	lwz	r3,GPR3(r1)
 syscall_exit_finish:
-#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
-	mtspr	SPRN_NRI, r0
-#endif
 	mtspr	SPRN_SRR0,r7
 	mtspr	SPRN_SRR1,r8
+
+	bne	3f
+	mtcr	r5
+
+1:	lwz	r2,GPR2(r1)
+	lwz	r1,GPR1(r1)
 	rfi
 #ifdef CONFIG_40x
 	b .	/* Prevent prefetch past rfi */
 #endif
-_ASM_NOKPROBE_SYMBOL(syscall_exit_finish)
+
+3:	mtcr	r5
+	lwz	r4,_CTR(r1)
+	lwz	r5,_XER(r1)
+	REST_NVGPRS(r1)
+	mtctr	r4
+	mtxer	r5
+	lwz	r0,GPR0(r1)
+	lwz	r3,GPR3(r1)
+	REST_8GPRS(4,r1)
+	lwz	r12,GPR12(r1)
+	b	1b
+
 #ifdef CONFIG_44x
 2:	li	r7,0
 	iccci	r0,r0
@@ -488,9 +403,6 @@ _ASM_NOKPROBE_SYMBOL(syscall_exit_finish)
 	b	1b
 #endif  /* CONFIG_44x */
 
-66:	li	r3,-ENOSYS
-	b	ret_from_syscall
-
 	.globl	ret_from_fork
 ret_from_fork:
 	REST_NVGPRS(r1)
@@ -509,82 +421,6 @@ ret_from_kernel_thread:
 	li	r3,0
 	b	ret_from_syscall
 
-/* Traced system call support */
-syscall_dotrace:
-	SAVE_NVGPRS(r1)
-	li	r0,0xc00
-	stw	r0,_TRAP(r1)
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	do_syscall_trace_enter
-	/*
-	 * Restore argument registers possibly just changed.
-	 * We use the return value of do_syscall_trace_enter
-	 * for call number to look up in the table (r0).
-	 */
-	mr	r0,r3
-	lwz	r3,GPR3(r1)
-	lwz	r4,GPR4(r1)
-	lwz	r5,GPR5(r1)
-	lwz	r6,GPR6(r1)
-	lwz	r7,GPR7(r1)
-	lwz	r8,GPR8(r1)
-	REST_NVGPRS(r1)
-
-	cmplwi	r0,NR_syscalls
-	/* Return code is already in r3 thanks to do_syscall_trace_enter() */
-	bge-	ret_from_syscall
-	b	syscall_dotrace_cont
-
-syscall_exit_work:
-	andi.	r0,r9,_TIF_RESTOREALL
-	beq+	0f
-	REST_NVGPRS(r1)
-	b	2f
-0:	cmplw	0,r3,r8
-	blt+	1f
-	andi.	r0,r9,_TIF_NOERROR
-	bne-	1f
-	lwz	r11,_CCR(r1)			/* Load CR */
-	neg	r3,r3
-	oris	r11,r11,0x1000	/* Set SO bit in CR */
-	stw	r11,_CCR(r1)
-
-1:	stw	r6,RESULT(r1)	/* Save result */
-	stw	r3,GPR3(r1)	/* Update return value */
-2:	andi.	r0,r9,(_TIF_PERSYSCALL_MASK)
-	beq	4f
-
-	/* Clear per-syscall TIF flags if any are set.  */
-
-	li	r11,_TIF_PERSYSCALL_MASK
-	addi	r12,r2,TI_FLAGS
-3:	lwarx	r8,0,r12
-	andc	r8,r8,r11
-	stwcx.	r8,0,r12
-	bne-	3b
-	
-4:	/* Anything which requires enabling interrupts? */
-	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
-	beq	ret_from_except
-
-	/* Re-enable interrupts. There is no need to trace that with
-	 * lockdep as we are supposed to have IRQs on at this point
-	 */
-	ori	r10,r10,MSR_EE
-	mtmsr	r10
-
-	/* Save NVGPRS if they're not saved already */
-	lwz	r4,_TRAP(r1)
-	andi.	r4,r4,1
-	beq	5f
-	SAVE_NVGPRS(r1)
-	li	r4,0xc00
-	stw	r4,_TRAP(r1)
-5:
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	do_syscall_trace_leave
-	b	ret_from_except_full
-
 	/*
 	 * System call was called from kernel. We get here with SRR1 in r9.
 	 * Mark the exception as recoverable once we have retrieved SRR0,
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index 7b12736ec546..fea7fe00a690 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -154,17 +154,12 @@
 	SAVE_GPR(0, r11)
 	SAVE_4GPRS(3, r11)
 	SAVE_2GPRS(7, r11)
-	addi	r11,r1,STACK_FRAME_OVERHEAD
 	addi	r2,r12,-THREAD
-	stw	r11,PT_REGS(r12)
 #if defined(CONFIG_40x)
 	/* Check to see if the dbcr0 register is set up to debug.  Use the
 	   internal debug mode bit to do this. */
 	lwz	r12,THREAD_DBCR0(r12)
 	andis.	r12,r12,DBCR0_IDM@h
-#endif
-	ACCOUNT_CPU_USER_ENTRY(r2, r11, r12)
-#if defined(CONFIG_40x)
 	beq+	3f
 	/* From user and task is ptraced - load up global dbcr0 */
 	li	r12,-1			/* clear all pending debug events */
@@ -176,21 +171,8 @@
 	lwz	r12,4(r11)
 	addi	r12,r12,-1
 	stw	r12,4(r11)
-#endif
-
 3:
-#ifdef CONFIG_TRACE_IRQFLAGS
-	/*
-	 * If MSR is changing we need to keep interrupts disabled at this point
-	 * otherwise we might risk taking an interrupt before we tell lockdep
-	 * they are enabled.
-	 */
-	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL)
-	rlwimi	r10, r9, 0, MSR_EE
-#else
-	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL | MSR_EE)
 #endif
-	mtmsr	r10
 	b	transfer_to_syscall		/* jump to handler */
 99:	b	ret_from_kernel_syscall
 .endm
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 626e716576ce..db931f1167aa 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -131,14 +131,11 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 	SAVE_4GPRS(3, r11)
 	SAVE_2GPRS(7, r11)
 
-	addi	r11,r1,STACK_FRAME_OVERHEAD
 	addi	r2,r10,-THREAD
-	stw	r11,PT_REGS(r10)
 	/* Check to see if the dbcr0 register is set up to debug.  Use the
 	   internal debug mode bit to do this. */
 	lwz	r12,THREAD_DBCR0(r10)
 	andis.	r12,r12,DBCR0_IDM@h
-	ACCOUNT_CPU_USER_ENTRY(r2, r11, r12)
 	beq+	3f
 	/* From user and task is ptraced - load up global dbcr0 */
 	li	r12,-1			/* clear all pending debug events */
@@ -157,20 +154,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 	stw	r12,4(r11)
 
 3:
-#ifdef CONFIG_TRACE_IRQFLAGS
-	/*
-	 * If MSR is changing we need to keep interrupts disabled at this point
-	 * otherwise we might risk taking an interrupt before we tell lockdep
-	 * they are enabled.
-	 */
-	lis	r10, MSR_KERNEL@h
-	ori	r10, r10, MSR_KERNEL@l
-	rlwimi	r10, r9, 0, MSR_EE
-#else
-	lis	r10, (MSR_KERNEL | MSR_EE)@h
-	ori	r10, r10, (MSR_KERNEL | MSR_EE)@l
-#endif
-	mtmsr	r10
 	b	transfer_to_syscall	/* jump to handler */
 99:	b	ret_from_kernel_syscall
 .endm
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 13/22] powerpc/32: Always save non volatile GPRs at syscall entry
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

In preparation for porting syscall entry/exit to C, inconditionally
save non volatile general purpose registers.

Commit 965dd3ad3076 ("powerpc/64/syscall: Remove non-volatile GPR save
optimisation") provides detailed explanation.

This increases the number of cycles by 24 cycles on 8xx with
null_syscall benchmark (280 => 304 cycles)

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/entry_32.S           | 46 +-----------------------
 arch/powerpc/kernel/head_32.h            |  2 +-
 arch/powerpc/kernel/head_booke.h         |  2 +-
 arch/powerpc/kernel/syscalls/syscall.tbl | 20 +++--------
 4 files changed, 8 insertions(+), 62 deletions(-)

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index b1e36602c013..97dc28a68465 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -351,6 +351,7 @@ trace_syscall_entry_irq_off:
 
 	.globl	transfer_to_syscall
 transfer_to_syscall:
+	SAVE_NVGPRS(r1)
 #ifdef CONFIG_PPC_BOOK3S_32
 	kuep_lock r11, r12
 #endif
@@ -614,51 +615,6 @@ ret_from_kernel_syscall:
 #endif
 _ASM_NOKPROBE_SYMBOL(ret_from_kernel_syscall)
 
-/*
- * The fork/clone functions need to copy the full register set into
- * the child process. Therefore we need to save all the nonvolatile
- * registers (r13 - r31) before calling the C code.
- */
-	.globl	ppc_fork
-ppc_fork:
-	SAVE_NVGPRS(r1)
-	lwz	r0,_TRAP(r1)
-	rlwinm	r0,r0,0,0,30		/* clear LSB to indicate full */
-	stw	r0,_TRAP(r1)		/* register set saved */
-	b	sys_fork
-
-	.globl	ppc_vfork
-ppc_vfork:
-	SAVE_NVGPRS(r1)
-	lwz	r0,_TRAP(r1)
-	rlwinm	r0,r0,0,0,30		/* clear LSB to indicate full */
-	stw	r0,_TRAP(r1)		/* register set saved */
-	b	sys_vfork
-
-	.globl	ppc_clone
-ppc_clone:
-	SAVE_NVGPRS(r1)
-	lwz	r0,_TRAP(r1)
-	rlwinm	r0,r0,0,0,30		/* clear LSB to indicate full */
-	stw	r0,_TRAP(r1)		/* register set saved */
-	b	sys_clone
-
-	.globl	ppc_clone3
-ppc_clone3:
-	SAVE_NVGPRS(r1)
-	lwz	r0,_TRAP(r1)
-	rlwinm	r0,r0,0,0,30		/* clear LSB to indicate full */
-	stw	r0,_TRAP(r1)		/* register set saved */
-	b	sys_clone3
-
-	.globl	ppc_swapcontext
-ppc_swapcontext:
-	SAVE_NVGPRS(r1)
-	lwz	r0,_TRAP(r1)
-	rlwinm	r0,r0,0,0,30		/* clear LSB to indicate full */
-	stw	r0,_TRAP(r1)		/* register set saved */
-	b	sys_swapcontext
-
 /*
  * Top-level page fault handling.
  * This is in assembler because if do_page_fault tells us that
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index 24dc326e0d56..7b12736ec546 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -148,7 +148,7 @@
 	stw	r2,GPR2(r11)
 	addi	r10,r10,STACK_FRAME_REGS_MARKER@l
 	stw	r9,_MSR(r11)
-	li	r2, \trapno + 1
+	li	r2, \trapno
 	stw	r10,8(r11)
 	stw	r2,_TRAP(r11)
 	SAVE_GPR(0, r11)
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index b3c502c503a0..626e716576ce 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -124,7 +124,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 	stw	r2,GPR2(r11)
 	addi	r12, r12, STACK_FRAME_REGS_MARKER@l
 	stw	r9,_MSR(r11)
-	li	r2, \trapno + 1
+	li	r2, \trapno
 	stw	r12, 8(r11)
 	stw	r2,_TRAP(r11)
 	SAVE_GPR(0, r11)
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index f744eb5cba88..96b2157f0371 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -9,9 +9,7 @@
 #
 0	nospu	restart_syscall			sys_restart_syscall
 1	nospu	exit				sys_exit
-2	32	fork				ppc_fork			sys_fork
-2	64	fork				sys_fork
-2	spu	fork				sys_ni_syscall
+2	nospu	fork				sys_fork
 3	common	read				sys_read
 4	common	write				sys_write
 5	common	open				sys_open			compat_sys_open
@@ -160,9 +158,7 @@
 119	32	sigreturn			sys_sigreturn			compat_sys_sigreturn
 119	64	sigreturn			sys_ni_syscall
 119	spu	sigreturn			sys_ni_syscall
-120	32	clone				ppc_clone			sys_clone
-120	64	clone				sys_clone
-120	spu	clone				sys_ni_syscall
+120	nospu	clone				sys_clone
 121	common	setdomainname			sys_setdomainname
 122	common	uname				sys_newuname
 123	common	modify_ldt			sys_ni_syscall
@@ -244,9 +240,7 @@
 186	spu	sendfile			sys_sendfile64
 187	common	getpmsg				sys_ni_syscall
 188	common 	putpmsg				sys_ni_syscall
-189	32	vfork				ppc_vfork			sys_vfork
-189	64	vfork				sys_vfork
-189	spu	vfork				sys_ni_syscall
+189	nospu	vfork				sys_vfork
 190	common	ugetrlimit			sys_getrlimit			compat_sys_getrlimit
 191	common	readahead			sys_readahead			compat_sys_readahead
 192	32	mmap2				sys_mmap2			compat_sys_mmap2
@@ -322,9 +316,7 @@
 248	32	clock_nanosleep			sys_clock_nanosleep_time32
 248	64	clock_nanosleep			sys_clock_nanosleep
 248	spu	clock_nanosleep			sys_clock_nanosleep
-249	32	swapcontext			ppc_swapcontext			compat_sys_swapcontext
-249	64	swapcontext			sys_swapcontext
-249	spu	swapcontext			sys_ni_syscall
+249	nospu	swapcontext			sys_swapcontext			compat_sys_swapcontext
 250	common	tgkill				sys_tgkill
 251	32	utimes				sys_utimes_time32
 251	64	utimes				sys_utimes
@@ -522,9 +514,7 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
-435	32	clone3				ppc_clone3			sys_clone3
-435	64	clone3				sys_clone3
-435	spu	clone3				sys_ni_syscall
+435	nospu	clone3				sys_clone3
 436	common	close_range			sys_close_range
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 15/22] powerpc/32: Remove verification of MSR_PR on syscall in the ASM entry
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

system_call_exception() checks MSR_PR and BUGs if a syscall
is issued from kernel mode.

No need to handle it anymore from the ASM entry code.

null_syscall reduction 2 cycles (348 => 346 cycles)

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/entry_32.S   | 30 ------------------------------
 arch/powerpc/kernel/head_32.h    |  3 ---
 arch/powerpc/kernel/head_booke.h |  3 ---
 3 files changed, 36 deletions(-)

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index bbf7ecea6fe0..cffe58e63356 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -421,36 +421,6 @@ ret_from_kernel_thread:
 	li	r3,0
 	b	ret_from_syscall
 
-	/*
-	 * System call was called from kernel. We get here with SRR1 in r9.
-	 * Mark the exception as recoverable once we have retrieved SRR0,
-	 * trap a warning and return ENOSYS with CR[SO] set.
-	 */
-	.globl	ret_from_kernel_syscall
-ret_from_kernel_syscall:
-	mfspr	r9, SPRN_SRR0
-	mfspr	r10, SPRN_SRR1
-#if !defined(CONFIG_4xx) && !defined(CONFIG_BOOKE)
-	LOAD_REG_IMMEDIATE(r11, MSR_KERNEL & ~(MSR_IR|MSR_DR))
-	mtmsr	r11
-#endif
-
-0:	trap
-	EMIT_BUG_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING
-
-	li	r3, ENOSYS
-	crset	so
-#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
-	mtspr	SPRN_NRI, r0
-#endif
-	mtspr	SPRN_SRR0, r9
-	mtspr	SPRN_SRR1, r10
-	rfi
-#ifdef CONFIG_40x
-	b .	/* Prevent prefetch past rfi */
-#endif
-_ASM_NOKPROBE_SYMBOL(ret_from_kernel_syscall)
-
 /*
  * Top-level page fault handling.
  * This is in assembler because if do_page_fault tells us that
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index fea7fe00a690..282d8fd443a9 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -118,8 +118,6 @@
 .macro SYSCALL_ENTRY trapno
 	mfspr	r9, SPRN_SRR1
 	mfspr	r10, SPRN_SRR0
-	andi.	r11, r9, MSR_PR
-	beq-	99f
 	LOAD_REG_IMMEDIATE(r11, MSR_KERNEL)		/* can take exceptions */
 	lis	r12, 1f@h
 	ori	r12, r12, 1f@l
@@ -174,7 +172,6 @@
 3:
 #endif
 	b	transfer_to_syscall		/* jump to handler */
-99:	b	ret_from_kernel_syscall
 .endm
 
 .macro save_dar_dsisr_on_stack reg1, reg2, sp
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index db931f1167aa..bfbd240cc8a2 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -106,10 +106,8 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 #endif
 	mfspr	r9, SPRN_SRR1
 	BOOKE_CLEAR_BTB(r11)
-	andi.	r11, r9, MSR_PR
 	lwz	r11, TASK_STACK - THREAD(r10)
 	rlwinm	r12,r12,0,4,2	/* Clear SO bit in CR */
-	beq-	99f
 	ALLOC_STACK_FRAME(r11, THREAD_SIZE - INT_FRAME_SIZE)
 	stw	r12, _CCR(r11)		/* save various registers */
 	mflr	r12
@@ -155,7 +153,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 
 3:
 	b	transfer_to_syscall	/* jump to handler */
-99:	b	ret_from_kernel_syscall
 .endm
 
 /* To handle the additional exception priority levels on 40x and Book-E
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 16/22] powerpc/syscall: Avoid stack frame in likely part of system_call_exception()
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

When r3 is not modified, reload it from regs->orig_r3 to free
volatile registers. This avoids a stack frame for the likely part
of system_call_exception()

Before the patch:

c000b4d4 <system_call_exception>:
c000b4d4:	7c 08 02 a6 	mflr    r0
c000b4d8:	94 21 ff e0 	stwu    r1,-32(r1)
c000b4dc:	93 e1 00 1c 	stw     r31,28(r1)
c000b4e0:	90 01 00 24 	stw     r0,36(r1)
c000b4e4:	90 6a 00 88 	stw     r3,136(r10)
c000b4e8:	81 6a 00 84 	lwz     r11,132(r10)
c000b4ec:	69 6b 00 02 	xori    r11,r11,2
c000b4f0:	55 6b ff fe 	rlwinm  r11,r11,31,31,31
c000b4f4:	0f 0b 00 00 	twnei   r11,0
c000b4f8:	81 6a 00 a0 	lwz     r11,160(r10)
c000b4fc:	55 6b 07 fe 	clrlwi  r11,r11,31
c000b500:	0f 0b 00 00 	twnei   r11,0
c000b504:	7c 0c 42 e6 	mftb    r0
c000b508:	83 e2 00 08 	lwz     r31,8(r2)
c000b50c:	81 82 00 28 	lwz     r12,40(r2)
c000b510:	90 02 00 24 	stw     r0,36(r2)
c000b514:	7d 8c f8 50 	subf    r12,r12,r31
c000b518:	7c 0c 02 14 	add     r0,r12,r0
c000b51c:	90 02 00 08 	stw     r0,8(r2)
c000b520:	7c 10 13 a6 	mtspr   80,r0
c000b524:	81 62 00 70 	lwz     r11,112(r2)
c000b528:	71 60 86 91 	andi.   r0,r11,34449
c000b52c:	40 82 00 34 	bne     c000b560 <system_call_exception+0x8c>
c000b530:	2b 89 01 b6 	cmplwi  cr7,r9,438
c000b534:	41 9d 00 64 	bgt     cr7,c000b598 <system_call_exception+0xc4>
c000b538:	3d 40 c0 5c 	lis     r10,-16292
c000b53c:	55 29 10 3a 	rlwinm  r9,r9,2,0,29
c000b540:	39 4a 41 e8 	addi    r10,r10,16872
c000b544:	80 01 00 24 	lwz     r0,36(r1)
c000b548:	7d 2a 48 2e 	lwzx    r9,r10,r9
c000b54c:	7c 08 03 a6 	mtlr    r0
c000b550:	7d 29 03 a6 	mtctr   r9
c000b554:	83 e1 00 1c 	lwz     r31,28(r1)
c000b558:	38 21 00 20 	addi    r1,r1,32
c000b55c:	4e 80 04 20 	bctr

After the patch:

c000b4d4 <system_call_exception>:
c000b4d4:	81 6a 00 84 	lwz     r11,132(r10)
c000b4d8:	90 6a 00 88 	stw     r3,136(r10)
c000b4dc:	69 6b 00 02 	xori    r11,r11,2
c000b4e0:	55 6b ff fe 	rlwinm  r11,r11,31,31,31
c000b4e4:	0f 0b 00 00 	twnei   r11,0
c000b4e8:	80 6a 00 a0 	lwz     r3,160(r10)
c000b4ec:	54 63 07 fe 	clrlwi  r3,r3,31
c000b4f0:	0f 03 00 00 	twnei   r3,0
c000b4f4:	7d 6c 42 e6 	mftb    r11
c000b4f8:	81 82 00 08 	lwz     r12,8(r2)
c000b4fc:	80 02 00 28 	lwz     r0,40(r2)
c000b500:	91 62 00 24 	stw     r11,36(r2)
c000b504:	7c 00 60 50 	subf    r0,r0,r12
c000b508:	7d 60 5a 14 	add     r11,r0,r11
c000b50c:	91 62 00 08 	stw     r11,8(r2)
c000b510:	7c 10 13 a6 	mtspr   80,r0
c000b514:	80 62 00 70 	lwz     r3,112(r2)
c000b518:	70 6b 86 91 	andi.   r11,r3,34449
c000b51c:	40 82 00 28 	bne     c000b544 <system_call_exception+0x70>
c000b520:	2b 89 01 b6 	cmplwi  cr7,r9,438
c000b524:	41 9d 00 84 	bgt     cr7,c000b5a8 <system_call_exception+0xd4>
c000b528:	80 6a 00 88 	lwz     r3,136(r10)
c000b52c:	3d 40 c0 5c 	lis     r10,-16292
c000b530:	55 29 10 3a 	rlwinm  r9,r9,2,0,29
c000b534:	39 4a 41 e4 	addi    r10,r10,16868
c000b538:	7d 2a 48 2e 	lwzx    r9,r10,r9
c000b53c:	7d 29 03 a6 	mtctr   r9
c000b540:	4e 80 04 20 	bctr

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/interrupt.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 107ec39f05cb..205902052112 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -117,6 +117,9 @@ notrace long system_call_exception(long r3, long r4, long r5,
 			return regs->gpr[3];
 		}
 		return -ENOSYS;
+	} else {
+		/* Restore r3 from orig_gpr3 to free up a volatile reg */
+		r3 = regs->orig_gpr3;
 	}
 
 	/* May be faster to do array_index_nospec? */
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 17/22] powerpc/syscall: Do not check unsupported scv vector on PPC32
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

Only PPC64 has scv. No need to check the 0x7ff0 trap on PPC32.
For that, add a helper trap_is_unsupported_scv() similar to
trap_is_scv().

And ignore the scv parameter in syscall_exit_prepare (Save 14 cycles
346 => 332 cycles)

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v5: Added a helper trap_is_unsupported_scv()
---
 arch/powerpc/include/asm/ptrace.h | 5 +++++
 arch/powerpc/kernel/entry_32.S    | 1 -
 arch/powerpc/kernel/interrupt.c   | 7 +++++--
 3 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 58f9dc060a7b..2c842b11a924 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -229,6 +229,11 @@ static inline bool trap_is_scv(struct pt_regs *regs)
 	return (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && TRAP(regs) == 0x3000);
 }
 
+static inline bool trap_is_unsupported_scv(struct pt_regs *regs)
+{
+	return (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && TRAP(regs) == 0x7ff0);
+}
+
 static inline bool trap_is_syscall(struct pt_regs *regs)
 {
 	return (trap_is_scv(regs) || TRAP(regs) == 0xc00);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index cffe58e63356..7c824e8928d0 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -344,7 +344,6 @@ transfer_to_syscall:
 
 ret_from_syscall:
 	addi    r4,r1,STACK_FRAME_OVERHEAD
-	li	r5,0
 	bl	syscall_exit_prepare
 #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
 	/* If the process has its own DBCR0 value, load it up.  The internal
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 205902052112..8fafca727b8b 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -88,7 +88,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	local_irq_enable();
 
 	if (unlikely(current_thread_info()->flags & _TIF_SYSCALL_DOTRACE)) {
-		if (unlikely(regs->trap == 0x7ff0)) {
+		if (unlikely(trap_is_unsupported_scv(regs))) {
 			/* Unsupported scv vector */
 			_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
 			return regs->gpr[3];
@@ -111,7 +111,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
 		r8 = regs->gpr[8];
 
 	} else if (unlikely(r0 >= NR_syscalls)) {
-		if (unlikely(regs->trap == 0x7ff0)) {
+		if (unlikely(trap_is_unsupported_scv(regs))) {
 			/* Unsupported scv vector */
 			_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
 			return regs->gpr[3];
@@ -224,6 +224,9 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 	unsigned long ti_flags;
 	unsigned long ret = 0;
 
+	if (IS_ENABLED(CONFIG_PPC32))
+		scv = 0;
+
 	CT_WARN_ON(ct_state() == CONTEXT_USER);
 
 #ifdef CONFIG_PPC64
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 18/22] powerpc/syscall: Remove FULL_REGS verification in system_call_exception
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

For book3s/64, FULL_REGS() is 'true' at all time, so the test voids.
For others, non volatile registers are saved inconditionally.

So the verification is pointless.

Should one fail to do it, it would anyway be caught by the
CHECK_FULL_REGS() in copy_thread() as we have removed the
special versions ppc_fork() and friends.

null_syscall benchmark reduction 4 cycles (332 => 328 cycles)

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/interrupt.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 8fafca727b8b..55e1aa18cdb9 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -42,7 +42,6 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	if (!IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x))
 		BUG_ON(!(regs->msr & MSR_RI));
 	BUG_ON(!(regs->msr & MSR_PR));
-	BUG_ON(!FULL_REGS(regs));
 	BUG_ON(arch_irq_disabled_regs(regs));
 
 #ifdef CONFIG_PPC_PKEY
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 19/22] powerpc/syscall: Optimise checks in beginning of system_call_exception()
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

Combine all tests of regs->msr into a single logical one.

Before the patch:

   0:	81 6a 00 84 	lwz     r11,132(r10)
   4:	90 6a 00 88 	stw     r3,136(r10)
   8:	69 60 00 02 	xori    r0,r11,2
   c:	54 00 ff fe 	rlwinm  r0,r0,31,31,31
  10:	0f 00 00 00 	twnei   r0,0
  14:	69 63 40 00 	xori    r3,r11,16384
  18:	54 63 97 fe 	rlwinm  r3,r3,18,31,31
  1c:	0f 03 00 00 	twnei   r3,0
  20:	69 6b 80 00 	xori    r11,r11,32768
  24:	55 6b 8f fe 	rlwinm  r11,r11,17,31,31
  28:	0f 0b 00 00 	twnei   r11,0

After the patch:

   0:	81 6a 00 84 	lwz     r11,132(r10)
   4:	90 6a 00 88 	stw     r3,136(r10)
   8:	7d 6b 58 f8 	not     r11,r11
   c:	71 6b c0 02 	andi.   r11,r11,49154
  10:	0f 0b 00 00 	twnei   r11,0

6 cycles less on powerpc 8xx (328 => 322 cycles).

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/interrupt.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 55e1aa18cdb9..8c38e8c95be2 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -28,6 +28,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
 				   unsigned long r0, struct pt_regs *regs)
 {
 	syscall_fn f;
+	unsigned long expected_msr;
 
 	regs->orig_gpr3 = r3;
 
@@ -39,10 +40,13 @@ notrace long system_call_exception(long r3, long r4, long r5,
 
 	trace_hardirqs_off(); /* finish reconciling */
 
+	expected_msr = MSR_PR;
 	if (!IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x))
-		BUG_ON(!(regs->msr & MSR_RI));
-	BUG_ON(!(regs->msr & MSR_PR));
-	BUG_ON(arch_irq_disabled_regs(regs));
+		expected_msr |= MSR_RI;
+	if (IS_ENABLED(CONFIG_PPC32))
+		expected_msr |= MSR_EE;
+	BUG_ON((regs->msr & expected_msr) ^ expected_msr);
+	BUG_ON(IS_ENABLED(CONFIG_PPC64) && arch_irq_disabled_regs(regs));
 
 #ifdef CONFIG_PPC_PKEY
 	if (mmu_has_feature(MMU_FTR_PKEY)) {
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 20/22] powerpc/syscall: Avoid storing 'current' in another pointer
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

By saving the pointer pointing to thread_info.flags, gcc copies r2
in a non-volatile register.

We know 'current' doesn't change, so avoid that intermediaite pointer.

Reduces null_syscall benchmark by 2 cycles (322 => 320 cycles)

On PPC64, gcc seems to know that 'current' is not changing, and it keeps
it in a non volatile register to avoid multiple read of 'current' in paca.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v5: Also in interrupt exit prepare
---
 arch/powerpc/kernel/interrupt.c | 28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 8c38e8c95be2..c89a8eac3e24 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -223,7 +223,6 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 					   struct pt_regs *regs,
 					   long scv)
 {
-	unsigned long *ti_flagsp = &current_thread_info()->flags;
 	unsigned long ti_flags;
 	unsigned long ret = 0;
 
@@ -241,7 +240,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 	/* Check whether the syscall is issued inside a restartable sequence */
 	rseq_syscall(regs);
 
-	ti_flags = *ti_flagsp;
+	ti_flags = current_thread_info()->flags;
 
 	if (unlikely(r3 >= (unsigned long)-MAX_ERRNO) && !scv) {
 		if (likely(!(ti_flags & (_TIF_NOERROR | _TIF_RESTOREALL)))) {
@@ -255,7 +254,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 			ret = _TIF_RESTOREALL;
 		else
 			regs->gpr[3] = r3;
-		clear_bits(_TIF_PERSYSCALL_MASK, ti_flagsp);
+		clear_bits(_TIF_PERSYSCALL_MASK, &current_thread_info()->flags);
 	} else {
 		regs->gpr[3] = r3;
 	}
@@ -268,7 +267,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 	local_irq_disable();
 
 again:
-	ti_flags = READ_ONCE(*ti_flagsp);
+	ti_flags = READ_ONCE(current_thread_info()->flags);
 	while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
 		local_irq_enable();
 		if (ti_flags & _TIF_NEED_RESCHED) {
@@ -284,7 +283,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 			do_notify_resume(regs, ti_flags);
 		}
 		local_irq_disable();
-		ti_flags = READ_ONCE(*ti_flagsp);
+		ti_flags = READ_ONCE(current_thread_info()->flags);
 	}
 
 	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && IS_ENABLED(CONFIG_PPC_FPU)) {
@@ -339,10 +338,6 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 #ifndef CONFIG_PPC_BOOK3E_64 /* BOOK3E not yet using this */
 notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr)
 {
-#ifdef CONFIG_PPC_BOOK3E
-	struct thread_struct *ts = &current->thread;
-#endif
-	unsigned long *ti_flagsp = &current_thread_info()->flags;
 	unsigned long ti_flags;
 	unsigned long flags;
 	unsigned long ret = 0;
@@ -365,7 +360,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
 	local_irq_save(flags);
 
 again:
-	ti_flags = READ_ONCE(*ti_flagsp);
+	ti_flags = READ_ONCE(current_thread_info()->flags);
 	while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
 		local_irq_enable(); /* returning to user: may enable */
 		if (ti_flags & _TIF_NEED_RESCHED) {
@@ -376,7 +371,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
 			do_notify_resume(regs, ti_flags);
 		}
 		local_irq_disable();
-		ti_flags = READ_ONCE(*ti_flagsp);
+		ti_flags = READ_ONCE(current_thread_info()->flags);
 	}
 
 	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && IS_ENABLED(CONFIG_PPC_FPU)) {
@@ -407,13 +402,13 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
 	}
 
 #ifdef CONFIG_PPC_BOOK3E
-	if (unlikely(ts->debug.dbcr0 & DBCR0_IDM)) {
+	if (unlikely(current->thread.debug.dbcr0 & DBCR0_IDM)) {
 		/*
 		 * Check to see if the dbcr0 register is set up to debug.
 		 * Use the internal debug mode bit to do this.
 		 */
 		mtmsr(mfmsr() & ~MSR_DE);
-		mtspr(SPRN_DBCR0, ts->debug.dbcr0);
+		mtspr(SPRN_DBCR0, current->thread.debug.dbcr0);
 		mtspr(SPRN_DBSR, -1);
 	}
 #endif
@@ -438,7 +433,6 @@ void preempt_schedule_irq(void);
 
 notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsigned long msr)
 {
-	unsigned long *ti_flagsp = &current_thread_info()->flags;
 	unsigned long flags;
 	unsigned long ret = 0;
 #ifdef CONFIG_PPC64
@@ -461,8 +455,8 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
 	amr = kuap_get_and_check_amr();
 #endif
 
-	if (unlikely(*ti_flagsp & _TIF_EMULATE_STACK_STORE)) {
-		clear_bits(_TIF_EMULATE_STACK_STORE, ti_flagsp);
+	if (unlikely(current_thread_info()->flags & _TIF_EMULATE_STACK_STORE)) {
+		clear_bits(_TIF_EMULATE_STACK_STORE, &current_thread_info()->flags);
 		ret = 1;
 	}
 
@@ -474,7 +468,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
 again:
 		if (IS_ENABLED(CONFIG_PREEMPT)) {
 			/* Return to preemptible kernel context */
-			if (unlikely(*ti_flagsp & _TIF_NEED_RESCHED)) {
+			if (unlikely(current_thread_info()->flags & _TIF_NEED_RESCHED)) {
 				if (preempt_count() == 0)
 					preempt_schedule_irq();
 			}
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 21/22] powerpc/32: Remove the counter in global_dbcr0
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

global_dbcr0 has two parts, 4 bytes to save/restore the
value of SPRN_DBCR0, and 4 bytes that are incremented/decremented
everytime something is saving/loading the above value.

This counter is only incremented/decremented, its value is never
used and never read.

Remove the counter and devide the size of global_dbcr0 by 2.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v5: New
---
 arch/powerpc/kernel/entry_32.S   | 12 +++---------
 arch/powerpc/kernel/head_32.h    |  3 ---
 arch/powerpc/kernel/head_booke.h |  5 +----
 3 files changed, 4 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 7c824e8928d0..a574201b0eb6 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -175,14 +175,11 @@ transfer_to_handler:
 	addi	r11,r11,global_dbcr0@l
 #ifdef CONFIG_SMP
 	lwz	r9,TASK_CPU(r2)
-	slwi	r9,r9,3
+	slwi	r9,r9,2
 	add	r11,r11,r9
 #endif
 	lwz	r12,0(r11)
 	mtspr	SPRN_DBCR0,r12
-	lwz	r12,4(r11)
-	addi	r12,r12,-1
-	stw	r12,4(r11)
 #endif
 
 	b	3f
@@ -980,14 +977,11 @@ load_dbcr0:
 	addi	r11,r11,global_dbcr0@l
 #ifdef CONFIG_SMP
 	lwz	r9,TASK_CPU(r2)
-	slwi	r9,r9,3
+	slwi	r9,r9,2
 	add	r11,r11,r9
 #endif
 	stw	r10,0(r11)
 	mtspr	SPRN_DBCR0,r0
-	lwz	r10,4(r11)
-	addi	r10,r10,1
-	stw	r10,4(r11)
 	li	r11,-1
 	mtspr	SPRN_DBSR,r11	/* clear all pending debug events */
 	blr
@@ -996,7 +990,7 @@ load_dbcr0:
 	.align	4
 	.global global_dbcr0
 global_dbcr0:
-	.space	8*NR_CPUS
+	.space	4*NR_CPUS
 	.previous
 #endif /* !(CONFIG_4xx || CONFIG_BOOKE) */
 
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index 282d8fd443a9..5001c6ecc3ec 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -166,9 +166,6 @@
 	addi	r11,r11,global_dbcr0@l
 	lwz	r12,0(r11)
 	mtspr	SPRN_DBCR0,r12
-	lwz	r12,4(r11)
-	addi	r12,r12,-1
-	stw	r12,4(r11)
 3:
 #endif
 	b	transfer_to_syscall		/* jump to handler */
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index bfbd240cc8a2..5f565232b99d 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -142,14 +142,11 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 	addi	r11,r11,global_dbcr0@l
 #ifdef CONFIG_SMP
 	lwz	r10, TASK_CPU(r2)
-	slwi	r10, r10, 3
+	slwi	r10, r10, 2
 	add	r11, r11, r10
 #endif
 	lwz	r12,0(r11)
 	mtspr	SPRN_DBCR0,r12
-	lwz	r12,4(r11)
-	addi	r12,r12,-1
-	stw	r12,4(r11)
 
 3:
 	b	transfer_to_syscall	/* jump to handler */
-- 
2.25.0


^ permalink raw reply related

* [PATCH v5 22/22] powerpc/32: Handle bookE debugging in C in syscall entry/exit
From: Christophe Leroy @ 2021-02-08 15:10 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
	msuchanek
  Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1612796617.git.christophe.leroy@csgroup.eu>

The handling of SPRN_DBCR0 and other registers can easily
be done in C instead of ASM.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v5: New
---
 arch/powerpc/include/asm/reg_booke.h |  3 +++
 arch/powerpc/kernel/entry_32.S       |  7 -------
 arch/powerpc/kernel/head_32.h        | 15 --------------
 arch/powerpc/kernel/head_booke.h     | 19 ------------------
 arch/powerpc/kernel/interrupt.c      | 29 +++++++++++++++++++++++++++-
 5 files changed, 31 insertions(+), 42 deletions(-)

diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index 262782f08fd4..17b8dcd9a40d 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -691,6 +691,9 @@
 #define mttmr(rn, v)	asm volatile(MTTMR(rn, %0) : \
 				     : "r" ((unsigned long)(v)) \
 				     : "memory")
+
+extern unsigned long global_dbcr0[];
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_POWERPC_REG_BOOKE_H__ */
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index a574201b0eb6..8dea4d3b1d06 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -342,13 +342,6 @@ transfer_to_syscall:
 ret_from_syscall:
 	addi    r4,r1,STACK_FRAME_OVERHEAD
 	bl	syscall_exit_prepare
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
-	/* If the process has its own DBCR0 value, load it up.  The internal
-	   debug mode bit tells us that dbcr0 should be loaded. */
-	lwz	r0,THREAD+THREAD_DBCR0(r2)
-	andis.	r10,r0,DBCR0_IDM@h
-	bnel-	load_dbcr0
-#endif
 #ifdef CONFIG_PPC_47x
 	lis	r4,icache_44x_need_flush@ha
 	lwz	r5,icache_44x_need_flush@l(r4)
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index 5001c6ecc3ec..961b1ce3b6bf 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -153,21 +153,6 @@
 	SAVE_4GPRS(3, r11)
 	SAVE_2GPRS(7, r11)
 	addi	r2,r12,-THREAD
-#if defined(CONFIG_40x)
-	/* Check to see if the dbcr0 register is set up to debug.  Use the
-	   internal debug mode bit to do this. */
-	lwz	r12,THREAD_DBCR0(r12)
-	andis.	r12,r12,DBCR0_IDM@h
-	beq+	3f
-	/* From user and task is ptraced - load up global dbcr0 */
-	li	r12,-1			/* clear all pending debug events */
-	mtspr	SPRN_DBSR,r12
-	lis	r11,global_dbcr0@ha
-	addi	r11,r11,global_dbcr0@l
-	lwz	r12,0(r11)
-	mtspr	SPRN_DBCR0,r12
-3:
-#endif
 	b	transfer_to_syscall		/* jump to handler */
 .endm
 
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 5f565232b99d..47857795f50a 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -130,25 +130,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 	SAVE_2GPRS(7, r11)
 
 	addi	r2,r10,-THREAD
-	/* Check to see if the dbcr0 register is set up to debug.  Use the
-	   internal debug mode bit to do this. */
-	lwz	r12,THREAD_DBCR0(r10)
-	andis.	r12,r12,DBCR0_IDM@h
-	beq+	3f
-	/* From user and task is ptraced - load up global dbcr0 */
-	li	r12,-1			/* clear all pending debug events */
-	mtspr	SPRN_DBSR,r12
-	lis	r11,global_dbcr0@ha
-	addi	r11,r11,global_dbcr0@l
-#ifdef CONFIG_SMP
-	lwz	r10, TASK_CPU(r2)
-	slwi	r10, r10, 2
-	add	r11, r11, r10
-#endif
-	lwz	r12,0(r11)
-	mtspr	SPRN_DBCR0,r12
-
-3:
 	b	transfer_to_syscall	/* jump to handler */
 .endm
 
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index c89a8eac3e24..6111acf61373 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -76,6 +76,13 @@ notrace long system_call_exception(long r3, long r4, long r5,
 		kuap_check_amr();
 #endif
 
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+	if (IS_ENABLED(CONFIG_PPC32) && unlikely(current->thread.debug.dbcr0 & DBCR0_IDM)) {
+		mtspr(SPRN_DBSR, -1);
+		mtspr(SPRN_DBCR0, global_dbcr0[smp_processor_id()]);
+	}
+#endif
+
 	account_cpu_user_entry();
 
 	account_stolen_time();
@@ -324,6 +331,22 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 	local_paca->tm_scratch = regs->msr;
 #endif
 
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+	if (unlikely(current->thread.debug.dbcr0 & DBCR0_IDM)) {
+		/*
+		 * Check to see if the dbcr0 register is set up to debug.
+		 * Use the internal debug mode bit to do this.
+		 */
+		mtmsr(mfmsr() & ~MSR_DE);
+		if (IS_ENABLED(CONFIG_PPC32)) {
+			isync();
+			global_dbcr0[smp_processor_id()] = mfspr(SPRN_DBCR0);
+		}
+		mtspr(SPRN_DBCR0, current->thread.debug.dbcr0);
+		mtspr(SPRN_DBSR, -1);
+	}
+#endif
+
 	account_cpu_user_exit();
 
 #ifdef CONFIG_PPC_BOOK3S_64 /* BOOK3E and ppc32 not using this */
@@ -401,13 +424,17 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
 		goto again;
 	}
 
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	if (unlikely(current->thread.debug.dbcr0 & DBCR0_IDM)) {
 		/*
 		 * Check to see if the dbcr0 register is set up to debug.
 		 * Use the internal debug mode bit to do this.
 		 */
 		mtmsr(mfmsr() & ~MSR_DE);
+		if (IS_ENABLED(CONFIG_PPC32)) {
+			isync();
+			global_dbcr0[smp_processor_id()] = mfspr(SPRN_DBCR0);
+		}
 		mtspr(SPRN_DBCR0, current->thread.debug.dbcr0);
 		mtspr(SPRN_DBSR, -1);
 	}
-- 
2.25.0


^ permalink raw reply related

* Re: [PATCH v2 1/1] powerpc/kvm: Save Timebase Offset to fix sched_clock() while running guest code.
From: Leonardo Bras @ 2021-02-08 16:37 UTC (permalink / raw)
  To: Nicholas Piggin, Aneesh Kumar K.V, Athira Rajeev,
	Benjamin Herrenschmidt, Christophe Leroy, Frederic Weisbecker,
	Geert Uytterhoeven, Jordan Niethe, Michael Ellerman,
	Paul Mackerras, Thomas Gleixner
  Cc: linuxppc-dev, linux-kernel, kvm-ppc
In-Reply-To: <1612579579.ztbklit4un.astroid@bobo.none>

Hello Nick,

On Sat, 2021-02-06 at 13:03 +1000, Nicholas Piggin wrote:
> Excerpts from Leonardo Bras's message of February 5, 2021 5:01 pm:
> > Hey Nick, thanks for reviewing :)
> > 
> > On Fri, 2021-02-05 at 16:28 +1000, Nicholas Piggin wrote:
> > > Excerpts from Leonardo Bras's message of February 5, 2021 4:06 pm:
> > > > Before guest entry, TBU40 register is changed to reflect guest timebase.
> > > > After exitting guest, the register is reverted to it's original value.
> > > > 
> > > > If one tries to get the timestamp from host between those changes, it
> > > > will present an incorrect value.
> > > > 
> > > > An example would be trying to add a tracepoint in
> > > > kvmppc_guest_entry_inject_int(), which depending on last tracepoint
> > > > acquired could actually cause the host to crash.
> > > > 
> > > > Save the Timebase Offset to PACA and use it on sched_clock() to always
> > > > get the correct timestamp.
> > > 
> > > Ouch. Not sure how reasonable it is to half switch into guest registers 
> > > and expect to call into the wider kernel, fixing things up as we go. 
> > > What if mftb is used in other places?
> > 
> > IIUC, the CPU is not supposed to call anything as host between guest
> > entry and guest exit, except guest-related cases, like
> 
> When I say "call", I'm including tracing in that. If a function is not 
> marked as no trace, then it will call into the tracing subsystem.
> 
> > kvmppc_guest_entry_inject_int(), but anyway, if something calls mftb it
> > will still get the same value as before.
> 
> Right, so it'll be out of whack again.
> 
> > This is only supposed to change stuff that depends on sched_clock, like
> > Tracepoints, that can happen in those exceptions.
> 
> If they depend on sched_clock that's one thing. Do they definitely have 
> no dependencies on mftb from other calls?

We could change that on get_tb() or mftb() @ timebase.h, which would
have a broader reach, but would not reach any mftb from asm code.

> > > Especially as it doesn't seem like there is a reason that function _has_
> > > to be called after the timebase is switched to guest, that's just how 
> > > the code is structured.
> > 
> > Correct, but if called, like in rb routines, used by tracepoints, the
> > difference between last tb and current (lower) tb may cause the CPU to
> > trap PROGRAM exception, crashing host. 
> 
> Yes, so I agree with Michael any function that is involved when we begin 
> to switch into guest context (or have not completed switching back to 
> host going the other way) should be marked as no trace (noinstr even, 
> perhaps).

Sure, that would avoid having to get paca->tb_offset for every mftb()
called, and avoid inconsistencies when different ways to get time are
used in code.

On the other hand, it would make it very hard to debug functions like
kvmppc_guest_entry_inject_int() as I am doing right now.

> 
> > > As a local hack to work out a bug okay. If you really need it upstream 
> > > could you put it under a debug config option?
> > 
> > You mean something that is automatically selected whenever those
> > configs are enabled? 
> > 
> > CONFIG_TRACEPOINT && CONFIG_KVM_BOOK3S_HANDLER && CONFIG_PPC_BOOK3S_64
> > 
> > Or something the user need to select himself in menuconfig?
> 
> Yeah I meant a default n thing under powerpc kernel debugging somewhere.

So, IIUC all we can do is split this in 2 changes:
1 - Adding notrace to those functions
2 - Introducing a kernel debug config that reverts (1) and 'fixes' mftb

If that's correct, I have some ideas we can use. 

For debug option, should we add the offset on get_tb() or mftb()?

Another option would be to adding this tb_offset only in the routines
used by tracing. But this could probably mean having to add a function
in arch-generic code, but still an option.

What do you think?

> 
> Thanks,
> Nick

Thank you!
Leonardo Bras


^ permalink raw reply

* Re: [PATCH 2/8] powerpc/signal: Add unsafe_copy_{vsx,fpr}_from_user()
From: Christopher M. Riedl @ 2021-02-08 17:14 UTC (permalink / raw)
  To: Christophe Leroy, linuxppc-dev
In-Reply-To: <1caa3c1e-bf4e-700e-efea-28964005bb12@csgroup.eu>

On Sun Feb 7, 2021 at 4:12 AM CST, Christophe Leroy wrote:
>
>
> Le 06/02/2021 à 18:39, Christopher M. Riedl a écrit :
> > On Sat Feb 6, 2021 at 10:32 AM CST, Christophe Leroy wrote:
> >>
> >>
> >> Le 20/10/2020 à 04:01, Christopher M. Riedl a écrit :
> >>> On Fri Oct 16, 2020 at 10:48 AM CDT, Christophe Leroy wrote:
> >>>>
> >>>>
> >>>> Le 15/10/2020 à 17:01, Christopher M. Riedl a écrit :
> >>>>> Reuse the "safe" implementation from signal.c except for calling
> >>>>> unsafe_copy_from_user() to copy into a local buffer. Unlike the
> >>>>> unsafe_copy_{vsx,fpr}_to_user() functions the "copy from" functions
> >>>>> cannot use unsafe_get_user() directly to bypass the local buffer since
> >>>>> doing so significantly reduces signal handling performance.
> >>>>
> >>>> Why can't the functions use unsafe_get_user(), why does it significantly
> >>>> reduces signal handling
> >>>> performance ? How much significant ? I would expect that not going
> >>>> through an intermediate memory
> >>>> area would be more efficient
> >>>>
> >>>
> >>> Here is a comparison, 'unsafe-signal64-regs' avoids the intermediate buffer:
> >>>
> >>> 	|                      | hash   | radix  |
> >>> 	| -------------------- | ------ | ------ |
> >>> 	| linuxppc/next        | 289014 | 158408 |
> >>> 	| unsafe-signal64      | 298506 | 253053 |
> >>> 	| unsafe-signal64-regs | 254898 | 220831 |
> >>>
> >>> I have not figured out the 'why' yet. As you mentioned in your series,
> >>> technically calling __copy_tofrom_user() is overkill for these
> >>> operations. The only obvious difference between unsafe_put_user() and
> >>> unsafe_get_user() is that we don't have asm-goto for the 'get' variant.
> >>> Instead we wrap with unsafe_op_wrap() which inserts a conditional and
> >>> then goto to the label.
> >>>
> >>> Implemenations:
> >>>
> >>> 	#define unsafe_copy_fpr_from_user(task, from, label)   do {            \
> >>> 	       struct task_struct *__t = task;                                 \
> >>> 	       u64 __user *buf = (u64 __user *)from;                           \
> >>> 	       int i;                                                          \
> >>> 									       \
> >>> 	       for (i = 0; i < ELF_NFPREG - 1; i++)                            \
> >>> 		       unsafe_get_user(__t->thread.TS_FPR(i), &buf[i], label); \
> >>> 	       unsafe_get_user(__t->thread.fp_state.fpscr, &buf[i], label);    \
> >>> 	} while (0)
> >>>
> >>> 	#define unsafe_copy_vsx_from_user(task, from, label)   do {            \
> >>> 	       struct task_struct *__t = task;                                 \
> >>> 	       u64 __user *buf = (u64 __user *)from;                           \
> >>> 	       int i;                                                          \
> >>> 									       \
> >>> 	       for (i = 0; i < ELF_NVSRHALFREG ; i++)                          \
> >>> 		       unsafe_get_user(__t->thread.fp_state.fpr[i][TS_VSRLOWOFFSET], \
> >>> 				       &buf[i], label);                        \
> >>> 	} while (0)
> >>>
> >>
> >> Do you have CONFIG_PROVE_LOCKING or CONFIG_DEBUG_ATOMIC_SLEEP enabled in
> >> your config ?
> > 
> > I don't have these set in my config (ppc64le_defconfig). I think I
> > figured this out - the reason for the lower signal throughput is the
> > barrier_nospec() in __get_user_nocheck(). When looping we incur that
> > cost on every iteration. Commenting it out results in signal performance
> > of ~316K w/ hash on the unsafe-signal64-regs branch. Obviously the
> > barrier is there for a reason but it is quite costly.
>
> Interesting.
>
> Can you try with the patch I just sent out
> https://patchwork.ozlabs.org/project/linuxppc-dev/patch/c72f014730823b413528e90ab6c4d3bcb79f8497.1612692067.git.christophe.leroy@csgroup.eu/

Yeah that patch solves the problem. Using unsafe_get_user() in a loop is
actually faster on radix than using the intermediary buffer step. A
summary of results below (unsafe-signal64-v6 uses unsafe_get_user() and
avoids the local buffer):

        |                                  | hash   | radix  |
        | -------------------------------- | ------ | ------ |
        | unsafe-signal64-v5               | 194533 | 230089 |
        | unsafe-signal64-v6               | 176739 | 202840 |
        | unsafe-signal64-v5+barrier patch | 203037 | 234936 |
        | unsafe-signal64-v6+barrier patch | 205484 | 241030 |

I am still expecting some comments/feedback on my v5 before sending out
v6. Should I include your patch in my series as well?

>
> Thanks
> Christophe


^ permalink raw reply


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