[PATCH v4 00/23] powerpc/32: Implement C syscall entry/exit

[PATCH v4 00/23] powerpc/32: Implement C syscall entry/exit

[Christophe Leroy]

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

This series is based on Nick's v6 series "powerpc: interrupt wrappers".

Patch 1 is a bug fix submitted separately but this series depends on it.
Patches 2-4 are an extract from the series "powerpc/32: Reduce head
complexity and re-activate MMU earlier". The changes here are limited
to system calls. That series will be respined to only contain exception
related changes and the syscall changes will remain in this series.
Patches 5-16 are preparatory changes.
Patch 17 is THE patch that changes to C syscall entry/exit
Patches 18-23 are optimisations.

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 is the first mature version.

Christophe Leroy (23):
  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/64s: Make kuap_check_amr() and kuap_get_and_check_amr()
    generic
  powerpc/32s: Create C version of kuap_user/kernel_restore() and
    friends
  powerpc/8xx: Create C version of kuap_user/kernel_restore() and
    friends
  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 syscall.c
  powerpc/syscall: Make syscall.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

 arch/powerpc/include/asm/book3s/32/kup.h      |  33 ++
 arch/powerpc/include/asm/book3s/64/kup.h      |  24 +-
 arch/powerpc/include/asm/hw_irq.h             |  91 ++++--
 arch/powerpc/include/asm/kup.h                |   9 +-
 arch/powerpc/include/asm/nohash/32/kup-8xx.h  |  27 ++
 arch/powerpc/include/asm/reg.h                |   1 +
 arch/powerpc/kernel/Makefile                  |   4 +-
 arch/powerpc/kernel/entry_32.S                | 305 ++----------------
 arch/powerpc/kernel/entry_64.S                |   1 -
 arch/powerpc/kernel/head_32.h                 |  76 +----
 arch/powerpc/kernel/head_booke.h              |  27 +-
 .../kernel/{syscall_64.c => syscall.c}        |  57 ++--
 arch/powerpc/kernel/syscalls/syscall.tbl      |  20 +-
 13 files changed, 225 insertions(+), 450 deletions(-)
 rename arch/powerpc/kernel/{syscall_64.c => syscall.c} (90%)

-- 
2.25.0

[PATCH v4 01/23] powerpc/32s: Add missing call to kuep_lock on syscall entry

[Christophe Leroy]

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

[PATCH v4 02/23] powerpc/32: Always enable data translation on syscall entry

[Christophe Leroy]

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

[PATCH v4 03/23] powerpc/32: On syscall entry, enable instruction translation at the same time as data

[Christophe Leroy]

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

[PATCH v4 04/23] powerpc/32: Reorder instructions to avoid using CTR in syscall entry

[Christophe Leroy]

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

[PATCH v4 05/23] powerpc/64s: Make kuap_check_amr() and kuap_get_and_check_amr() generic

[Christophe Leroy]

In preparation of porting powerpc32 to C syscall entry/exit,
rename kuap_check_amr() and kuap_get_and_check_amr() as kuap_check()
and kuap_get_and_check(), and move in the generic asm/kup.h the stub
for when CONFIG_PPC_KUAP is not selected.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/include/asm/book3s/64/kup.h | 24 ++----------------------
 arch/powerpc/include/asm/kup.h           |  9 ++++++++-
 arch/powerpc/kernel/syscall_64.c         | 12 ++++++------
 3 files changed, 16 insertions(+), 29 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/kup.h b/arch/powerpc/include/asm/book3s/64/kup.h
index f50f72e535aa..1507681ad4ef 100644
--- a/arch/powerpc/include/asm/book3s/64/kup.h
+++ b/arch/powerpc/include/asm/book3s/64/kup.h
@@ -281,7 +281,7 @@ static inline void kuap_kernel_restore(struct pt_regs *regs,
 	 */
 }
 
-static inline unsigned long kuap_get_and_check_amr(void)
+static inline unsigned long kuap_get_and_check(void)
 {
 	if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) {
 		unsigned long amr = mfspr(SPRN_AMR);
@@ -292,27 +292,7 @@ static inline unsigned long kuap_get_and_check_amr(void)
 	return 0;
 }
 
-#else /* CONFIG_PPC_PKEY */
-
-static inline void kuap_user_restore(struct pt_regs *regs)
-{
-}
-
-static inline void kuap_kernel_restore(struct pt_regs *regs, unsigned long amr)
-{
-}
-
-static inline unsigned long kuap_get_and_check_amr(void)
-{
-	return 0;
-}
-
-#endif /* CONFIG_PPC_PKEY */
-
-
-#ifdef CONFIG_PPC_KUAP
-
-static inline void kuap_check_amr(void)
+static inline void kuap_check(void)
 {
 	if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG) && mmu_has_feature(MMU_FTR_BOOK3S_KUAP))
 		WARN_ON_ONCE(mfspr(SPRN_AMR) != AMR_KUAP_BLOCKED);
diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h
index bf221a2a523e..6ef9f9cfbed0 100644
--- a/arch/powerpc/include/asm/kup.h
+++ b/arch/powerpc/include/asm/kup.h
@@ -66,7 +66,14 @@ bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 	return false;
 }
 
-static inline void kuap_check_amr(void) { }
+static inline void kuap_check(void) { }
+static inline void kuap_user_restore(struct pt_regs *regs) { }
+static inline void kuap_kernel_restore(struct pt_regs *regs, unsigned long amr) { }
+
+static inline unsigned long kuap_get_and_check(void)
+{
+	return 0;
+}
 
 /*
  * book3s/64/kup-radix.h defines these functions for the !KUAP case to flush
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 32f72965da26..b627a6384029 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -65,7 +65,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
 			isync();
 	} else
 #endif
-		kuap_check_amr();
+		kuap_check();
 
 	account_cpu_user_entry();
 
@@ -181,7 +181,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 
 	CT_WARN_ON(ct_state() == CONTEXT_USER);
 
-	kuap_check_amr();
+	kuap_check();
 
 	regs->result = r3;
 
@@ -303,7 +303,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
 	 * 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.
 	 */
-	kuap_check_amr();
+	kuap_check();
 
 	local_irq_save(flags);
 
@@ -381,7 +381,7 @@ 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;
-	unsigned long amr;
+	unsigned long kuap;
 
 	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && unlikely(!(regs->msr & MSR_RI)))
 		unrecoverable_exception(regs);
@@ -394,7 +394,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
 	if (TRAP(regs) != 0x700)
 		CT_WARN_ON(ct_state() == CONTEXT_USER);
 
-	amr = kuap_get_and_check_amr();
+	kuap = kuap_get_and_check();
 
 	if (unlikely(*ti_flagsp & _TIF_EMULATE_STACK_STORE)) {
 		clear_bits(_TIF_EMULATE_STACK_STORE, ti_flagsp);
@@ -446,7 +446,7 @@ 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.
 	 */
-	kuap_kernel_restore(regs, amr);
+	kuap_kernel_restore(regs, kuap);
 
 	return ret;
 }
-- 
2.25.0

[PATCH v4 06/23] powerpc/32s: Create C version of kuap_user/kernel_restore() and friends

[Christophe Leroy]

In preparation of porting PPC32 to C syscall entry/exit,
create C version of kuap_user_restore() and kuap_kernel_restore()
and kuap_check() and kuap_get_and_check() on book3s/32.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/include/asm/book3s/32/kup.h | 33 ++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h
index a0117a9d5b06..a3e72e1141c5 100644
--- a/arch/powerpc/include/asm/book3s/32/kup.h
+++ b/arch/powerpc/include/asm/book3s/32/kup.h
@@ -103,6 +103,39 @@ static inline void kuap_update_sr(u32 sr, u32 addr, u32 end)
 	isync();	/* Context sync required after mtsrin() */
 }
 
+static inline void kuap_user_restore(struct pt_regs *regs)
+{
+}
+
+static inline void kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap)
+{
+	u32 addr = kuap & 0xf0000000;
+	u32 end = kuap << 28;
+
+	if (unlikely(!kuap))
+		return;
+
+	current->thread.kuap = 0;
+	kuap_update_sr(mfsrin(addr) & ~SR_KS, addr, end);	/* Clear Ks */
+}
+
+static inline void kuap_check(void)
+{
+	if (!IS_ENABLED(CONFIG_PPC_KUAP_DEBUG))
+		return;
+
+	WARN_ON_ONCE(current->thread.kuap != 0);
+}
+
+static inline unsigned long kuap_get_and_check(void)
+{
+	unsigned long kuap = current->thread.kuap;
+
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_PPC_KUAP_DEBUG) && kuap != 0);
+
+	return kuap;
+}
+
 static __always_inline void allow_user_access(void __user *to, const void __user *from,
 					      u32 size, unsigned long dir)
 {
-- 
2.25.0

[PATCH v4 07/23] powerpc/8xx: Create C version of kuap_user/kernel_restore() and friends

[Christophe Leroy]

In preparation of porting PPC32 to C syscall entry/exit,
create C version of kuap_user_restore() and kuap_kernel_restore()
and kuap_check() and kuap_get_and_check() on 8xx

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/include/asm/nohash/32/kup-8xx.h | 27 ++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h
index 17a4a616436f..5ca6c375f767 100644
--- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h
@@ -34,6 +34,33 @@
 
 #include <asm/reg.h>
 
+static inline void kuap_user_restore(struct pt_regs *regs)
+{
+}
+
+static inline void kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap)
+{
+	mtspr(SPRN_MD_AP, kuap);
+}
+
+static inline void kuap_check(void)
+{
+	if (!IS_ENABLED(CONFIG_PPC_KUAP_DEBUG))
+		return;
+
+	WARN_ON_ONCE(mfspr(SPRN_MD_AP) >> 16 != MD_APG_KUAP >> 16);
+}
+
+static inline unsigned long kuap_get_and_check(void)
+{
+	unsigned long kuap = mfspr(SPRN_MD_AP);
+
+	if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG))
+		WARN_ON_ONCE(mfspr(SPRN_MD_AP) >> 16 != MD_APG_KUAP >> 16);
+
+	return kuap;
+}
+
 static inline void allow_user_access(void __user *to, const void __user *from,
 				     unsigned long size, unsigned long dir)
 {
-- 
2.25.0

[PATCH v4 08/23] powerpc/irq: Add helper to set regs->softe

[Christophe Leroy]

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

[PATCH v4 09/23] powerpc/irq: Rework helpers that manipulate MSR[EE/RI]

[Christophe Leroy]

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 e40a921d78f9..d05dca30604d 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

[PATCH v4 10/23] powerpc/irq: Add stub irq_soft_mask_return() for PPC32

[Christophe Leroy]

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

[PATCH v4 11/23] powerpc/syscall: Rename syscall_64.c into syscall.c

[Christophe Leroy]

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

Rename it syscall.c

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

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index fe2ef598e2ea..1cbc51fc82fd 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -49,7 +49,7 @@ obj-y				:= cputable.o syscalls.o \
 				   hw_breakpoint_constraints.o
 obj-y				+= ptrace/
 obj-$(CONFIG_PPC64)		+= setup_64.o \
-				   paca.o nvram_64.o note.o syscall_64.o
+				   paca.o nvram_64.o note.o syscall.o
 obj-$(CONFIG_COMPAT)		+= sys_ppc32.o signal_32.o
 obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_PPC_WATCHDOG)	+= watchdog.o
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall.c
similarity index 100%
rename from arch/powerpc/kernel/syscall_64.c
rename to arch/powerpc/kernel/syscall.c
-- 
2.25.0

Re: [PATCH v4 11/23] powerpc/syscall: Rename syscall_64.c into syscall.c

[Nicholas Piggin]

Excerpts from Christophe Leroy's message of January 26, 2021 12:48 am:
> syscall_64.c will be reused almost as is for PPC32.
> 
> Rename it syscall.c

Could you rename it to interrupt.c instead? A system call is an 
interrupt, and the file now also has code to return from other
interrupts as well, and it matches the new asm/interrupt.h from
the interrupts series.

Thanks,
Nick

RE: [PATCH v4 11/23] powerpc/syscall: Rename syscall_64.c into syscall.c

[David Laight]

From: Nicholas Piggin
> Sent: 26 January 2021 10:21
> 
> Excerpts from Christophe Leroy's message of January 26, 2021 12:48 am:
> > syscall_64.c will be reused almost as is for PPC32.
> >
> > Rename it syscall.c
> 
> Could you rename it to interrupt.c instead? A system call is an
> interrupt, and the file now also has code to return from other
> interrupts as well, and it matches the new asm/interrupt.h from
> the interrupts series.

Hmmm....

That might make it harder for someone looking for the system call
entry code to find it.

In some sense interrupts are the simpler case.

Especially when comparing with other architectures which have
special instructions for syscall entry.

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)

RE: [PATCH v4 11/23] powerpc/syscall: Rename syscall_64.c into syscall.c

[Nicholas Piggin]

Excerpts from David Laight's message of January 26, 2021 8:28 pm:
> From: Nicholas Piggin
>> Sent: 26 January 2021 10:21
>> 
>> Excerpts from Christophe Leroy's message of January 26, 2021 12:48 am:
>> > syscall_64.c will be reused almost as is for PPC32.
>> >
>> > Rename it syscall.c
>> 
>> Could you rename it to interrupt.c instead? A system call is an
>> interrupt, and the file now also has code to return from other
>> interrupts as well, and it matches the new asm/interrupt.h from
>> the interrupts series.
> 
> Hmmm....
> 
> That might make it harder for someone looking for the system call
> entry code to find it.

It's very grep'able.

> In some sense interrupts are the simpler case.
> 
> Especially when comparing with other architectures which have
> special instructions for syscall entry.

powerpc does have a special instruction for syscall, and it causes a
system call interrupt.

I'm not sure about other architectures, but for powerpc its more 
sensible to call it interrupt.c than syscall.c.

Thanks,
Nick

Re: [PATCH v4 11/23] powerpc/syscall: Rename syscall_64.c into syscall.c

[Christophe Leroy]

Le 28/01/2021 à 00:50, Nicholas Piggin a écrit :
> Excerpts from David Laight's message of January 26, 2021 8:28 pm:
>> From: Nicholas Piggin
>>> Sent: 26 January 2021 10:21
>>>
>>> Excerpts from Christophe Leroy's message of January 26, 2021 12:48 am:
>>>> syscall_64.c will be reused almost as is for PPC32.
>>>>
>>>> Rename it syscall.c
>>>
>>> Could you rename it to interrupt.c instead? A system call is an
>>> interrupt, and the file now also has code to return from other
>>> interrupts as well, and it matches the new asm/interrupt.h from
>>> the interrupts series.
>>
>> Hmmm....
>>
>> That might make it harder for someone looking for the system call
>> entry code to find it.
> 
> It's very grep'able.
> 
>> In some sense interrupts are the simpler case.
>>
>> Especially when comparing with other architectures which have
>> special instructions for syscall entry.
> 
> powerpc does have a special instruction for syscall, and it causes a
> system call interrupt.
> 
> I'm not sure about other architectures, but for powerpc its more
> sensible to call it interrupt.c than syscall.c.

Many other architectures have a syscall.c but for a different purpose: it contains arch specific 
system calls. We have that in powerpc as well, it is called syscalls.c

So to avoid confusion, I'll rename it. But I think "interrupt" is maybe not the right name. An 
interrupt most of the time refers to IRQ. For me system call is not an interrupt in the way it 
doesn't unexpectedly interrupt a program flow. In powerpc manuals it is generally called exceptions, 
no I'm more inclined to call it exception.c

Christophe

Re: [PATCH v4 11/23] powerpc/syscall: Rename syscall_64.c into syscall.c

[Nicholas Piggin]

Excerpts from Christophe Leroy's message of February 2, 2021 4:15 pm:
> 
> 
> Le 28/01/2021 à 00:50, Nicholas Piggin a écrit :
>> Excerpts from David Laight's message of January 26, 2021 8:28 pm:
>>> From: Nicholas Piggin
>>>> Sent: 26 January 2021 10:21
>>>>
>>>> Excerpts from Christophe Leroy's message of January 26, 2021 12:48 am:
>>>>> syscall_64.c will be reused almost as is for PPC32.
>>>>>
>>>>> Rename it syscall.c
>>>>
>>>> Could you rename it to interrupt.c instead? A system call is an
>>>> interrupt, and the file now also has code to return from other
>>>> interrupts as well, and it matches the new asm/interrupt.h from
>>>> the interrupts series.
>>>
>>> Hmmm....
>>>
>>> That might make it harder for someone looking for the system call
>>> entry code to find it.
>> 
>> It's very grep'able.
>> 
>>> In some sense interrupts are the simpler case.
>>>
>>> Especially when comparing with other architectures which have
>>> special instructions for syscall entry.
>> 
>> powerpc does have a special instruction for syscall, and it causes a
>> system call interrupt.
>> 
>> I'm not sure about other architectures, but for powerpc its more
>> sensible to call it interrupt.c than syscall.c.
> 
> Many other architectures have a syscall.c but for a different purpose: it contains arch specific 
> system calls. We have that in powerpc as well, it is called syscalls.c
> 
> So to avoid confusion, I'll rename it. But I think "interrupt" is maybe not the right name. An 
> interrupt most of the time refers to IRQ.

That depends what you mean by interrupt and IRQ.

Linux kind of considers any asynchronous maskable interrupt an irq 
(local_irq_disable()). But if you say irq it's more likely to mean
a device interrupt, and "interrupt" usually refres to the asynch
ones.

But Linux doesn't really assign names to synchronous interrupts in
core code. It doesn't say they aren't interrupts, it just doesn't
really have a convention for them at all.

Other architectures e.g., x86 also have things like interrupt
descriptor table for synchronous interrupts as well. That's where
I got the interrupt wrappers code from actually.

So it's really fine to use the proper arch-specific names for things
in arch code. I'm trying to slowly change names from exception to
interrupt.

> For me system call is not an interrupt in the way it 
> doesn't unexpectedly interrupt a program flow. In powerpc manuals it is generally called exceptions, 
> no I'm more inclined to call it exception.c

Actually that's backwards. Powerpc manuals (at least the one I look at) 
calls them all interrupts including system calls, and also the system
call interrupt is actually the only one that doesn't appear to be
associated with an exception.

Also there is no distinction about expecte/unexpected -- a data storage 
interrupt is expected if you access a location without the right access 
permissions for example, but it is still an interrupt.

These handlers very specifically deal with the change to execution flow
(i.e., the interrupt), they do *not* deal with the exception which may 
be associated with it (that is the job of the handler).

And on the other hand you can deal with exceptions in some cases without
taking an interrupt at all. For example if you had MSR[EE]=0 you could
change the decrementer or execute msgclr or change HMER SPR etc to clear
various exceptions without ever taking the interrupt.

Thanks,
Nick

Re: [PATCH v4 11/23] powerpc/syscall: Rename syscall_64.c into syscall.c

[Christophe Leroy]

Le 02/02/2021 à 07:38, Nicholas Piggin a écrit :
> Excerpts from Christophe Leroy's message of February 2, 2021 4:15 pm:
>>
>>
>> Le 28/01/2021 à 00:50, Nicholas Piggin a écrit :
>>> Excerpts from David Laight's message of January 26, 2021 8:28 pm:
>>>> From: Nicholas Piggin
>>>>> Sent: 26 January 2021 10:21
>>>>>
>>>>> Excerpts from Christophe Leroy's message of January 26, 2021 12:48 am:
>>>>>> syscall_64.c will be reused almost as is for PPC32.
>>>>>>
>>>>>> Rename it syscall.c
>>>>>
>>>>> Could you rename it to interrupt.c instead? A system call is an
>>>>> interrupt, and the file now also has code to return from other
>>>>> interrupts as well, and it matches the new asm/interrupt.h from
>>>>> the interrupts series.
>>>>
>>>> Hmmm....
>>>>
>>>> That might make it harder for someone looking for the system call
>>>> entry code to find it.
>>>
>>> It's very grep'able.
>>>
>>>> In some sense interrupts are the simpler case.
>>>>
>>>> Especially when comparing with other architectures which have
>>>> special instructions for syscall entry.
>>>
>>> powerpc does have a special instruction for syscall, and it causes a
>>> system call interrupt.
>>>
>>> I'm not sure about other architectures, but for powerpc its more
>>> sensible to call it interrupt.c than syscall.c.
>>
>> Many other architectures have a syscall.c but for a different purpose: it contains arch specific
>> system calls. We have that in powerpc as well, it is called syscalls.c
>>
>> So to avoid confusion, I'll rename it. But I think "interrupt" is maybe not the right name. An
>> interrupt most of the time refers to IRQ.
> 
> That depends what you mean by interrupt and IRQ.
> 
> Linux kind of considers any asynchronous maskable interrupt an irq
> (local_irq_disable()). But if you say irq it's more likely to mean
> a device interrupt, and "interrupt" usually refres to the asynch
> ones.
> 
> But Linux doesn't really assign names to synchronous interrupts in
> core code. It doesn't say they aren't interrupts, it just doesn't
> really have a convention for them at all.
> 
> Other architectures e.g., x86 also have things like interrupt
> descriptor table for synchronous interrupts as well. That's where
> I got the interrupt wrappers code from actually.
> 
> So it's really fine to use the proper arch-specific names for things
> in arch code. I'm trying to slowly change names from exception to
> interrupt.
> 
>> For me system call is not an interrupt in the way it
>> doesn't unexpectedly interrupt a program flow. In powerpc manuals it is generally called exceptions,
>> no I'm more inclined to call it exception.c
> 
> Actually that's backwards. Powerpc manuals (at least the one I look at)
> calls them all interrupts including system calls, and also the system
> call interrupt is actually the only one that doesn't appear to be
> associated with an exception.
> 
> Also there is no distinction about expecte/unexpected -- a data storage
> interrupt is expected if you access a location without the right access
> permissions for example, but it is still an interrupt.
> 
> These handlers very specifically deal with the change to execution flow
> (i.e., the interrupt), they do *not* deal with the exception which may
> be associated with it (that is the job of the handler).
> 
> And on the other hand you can deal with exceptions in some cases without
> taking an interrupt at all. For example if you had MSR[EE]=0 you could
> change the decrementer or execute msgclr or change HMER SPR etc to clear
> various exceptions without ever taking the interrupt.
> 

Ok, let's call it interrupt.c then, to be consistant with the interrupt wrapper story.

Christophe

Re: [PATCH v4 11/23] powerpc/syscall: Rename syscall_64.c into syscall.c

[Segher Boessenkool]

On Tue, Feb 02, 2021 at 04:38:31PM +1000, Nicholas Piggin wrote:
> > So to avoid confusion, I'll rename it. But I think "interrupt" is maybe not the right name. An 
> > interrupt most of the time refers to IRQ.
> 
> That depends what you mean by interrupt and IRQ.

In the PowerPC architecture, an exception is an abnormal condition, and
that can often cause an interrupt.  What Christophe colloquially calls
an "IRQ" here is called an external exception c.q. external interrupt.

> But if you say irq it's more likely to mean
> a device interrupt, and "interrupt" usually refres to the asynch
> ones.

Power talks about "instruction-caused interrupts", for one aspect of the
difference here; and "precise" / "imprecise" interrupts for another.

> So it's really fine to use the proper arch-specific names for things
> in arch code. I'm trying to slowly change names from exception to
> interrupt.

Thanks :-)

> > For me system call is not an interrupt in the way it 
> > doesn't unexpectedly interrupt a program flow. In powerpc manuals it is generally called exceptions, 
> > no I'm more inclined to call it exception.c
> 
> Actually that's backwards. Powerpc manuals (at least the one I look at) 
> calls them all interrupts including system calls, and also the system
> call interrupt is actually the only one that doesn't appear to be
> associated with an exception.

Yeah.  You could easily make such an exception, which is set when you
execute a system call instruction, and cleared when the interrupt is
taken, of course; but the architecture doesn't.

> And on the other hand you can deal with exceptions in some cases without
> taking an interrupt at all. For example if you had MSR[EE]=0 you could
> change the decrementer or execute msgclr or change HMER SPR etc to clear
> various exceptions without ever taking the interrupt.

A well-known example is the exception bits in the FPSCR, which do not
cause an interrupt unless the corresponding enable bits are also set.


Segher

Re: [PATCH v4 11/23] powerpc/syscall: Rename syscall_64.c into syscall.c

[Christophe Leroy]

Le 26/01/2021 à 11:21, Nicholas Piggin a écrit :
> Excerpts from Christophe Leroy's message of January 26, 2021 12:48 am:
>> syscall_64.c will be reused almost as is for PPC32.
>>
>> Rename it syscall.c
> 
> Could you rename it to interrupt.c instead? A system call is an
> interrupt, and the file now also has code to return from other
> interrupts as well, and it matches the new asm/interrupt.h from
> the interrupts series.
> 

Done in v5

Christophe

[PATCH v4 12/23] powerpc/syscall: Make syscall.c buildable on PPC32

[Christophe Leroy]

ifdef out specific PPC64 stuff to allow building
syscall.c on PPC32.

Modify Makefile to always build syscall.o

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/Makefile  | 4 ++--
 arch/powerpc/kernel/syscall.c | 9 +++++----
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 1cbc51fc82fd..23c127db0d0c 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -46,10 +46,10 @@ obj-y				:= cputable.o syscalls.o \
 				   prom.o traps.o setup-common.o \
 				   udbg.o misc.o io.o misc_$(BITS).o \
 				   of_platform.o prom_parse.o firmware.o \
-				   hw_breakpoint_constraints.o
+				   hw_breakpoint_constraints.o syscall.o
 obj-y				+= ptrace/
 obj-$(CONFIG_PPC64)		+= setup_64.o \
-				   paca.o nvram_64.o note.o syscall.o
+				   paca.o nvram_64.o note.o
 obj-$(CONFIG_COMPAT)		+= sys_ppc32.o signal_32.o
 obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_PPC_WATCHDOG)	+= watchdog.o
diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
index b627a6384029..bf9bf4b5bc41 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.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)) {
@@ -77,7 +77,7 @@ 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();
 
@@ -147,6 +147,7 @@ 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)
@@ -158,7 +159,7 @@ 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;
 }
 
@@ -281,7 +282,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 	return ret;
 }
 
-#ifdef CONFIG_PPC_BOOK3S /* BOOK3E not yet using this */
+#ifdef CONFIG_PPC_BOOK3S_64 /* BOOK3E not yet using this */
 notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr)
 {
 #ifdef CONFIG_PPC_BOOK3E
-- 
2.25.0

[PATCH v4 13/23] powerpc/syscall: Use is_compat_task()

[Christophe Leroy]

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/syscall.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
index bf9bf4b5bc41..cb415170b8f2 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.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>
@@ -116,7 +118,7 @@ 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

[PATCH v4 14/23] powerpc/syscall: Save r3 in regs->orig_r3

[Christophe Leroy]

Save r3 in regs->orig_r3 in system_call_exception()

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/entry_64.S | 1 -
 arch/powerpc/kernel/syscall.c  | 2 ++
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index aa1af139d947..a562a4240aa6 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -278,7 +278,6 @@ 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/syscall.c b/arch/powerpc/kernel/syscall.c
index cb415170b8f2..b66cfcbcb755 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.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

Re: [PATCH v4 14/23] powerpc/syscall: Save r3 in regs->orig_r3

[Nicholas Piggin]

Excerpts from Christophe Leroy's message of January 26, 2021 12:48 am:
> Save r3 in regs->orig_r3 in system_call_exception()
> 
> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
> ---
>  arch/powerpc/kernel/entry_64.S | 1 -
>  arch/powerpc/kernel/syscall.c  | 2 ++
>  2 files changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
> index aa1af139d947..a562a4240aa6 100644
> --- a/arch/powerpc/kernel/entry_64.S
> +++ b/arch/powerpc/kernel/entry_64.S
> @@ -278,7 +278,6 @@ 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 */

This misses system_call_vectored.

Thanks,
Nick

> diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
> index cb415170b8f2..b66cfcbcb755 100644
> --- a/arch/powerpc/kernel/syscall.c
> +++ b/arch/powerpc/kernel/syscall.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
> 
> 

Re: [PATCH v4 14/23] powerpc/syscall: Save r3 in regs->orig_r3

[Christophe Leroy]

Le 26/01/2021 à 11:18, Nicholas Piggin a écrit :
> Excerpts from Christophe Leroy's message of January 26, 2021 12:48 am:
>> Save r3 in regs->orig_r3 in system_call_exception()
>>
>> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
>> ---
>>   arch/powerpc/kernel/entry_64.S | 1 -
>>   arch/powerpc/kernel/syscall.c  | 2 ++
>>   2 files changed, 2 insertions(+), 1 deletion(-)
>>
>> diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
>> index aa1af139d947..a562a4240aa6 100644
>> --- a/arch/powerpc/kernel/entry_64.S
>> +++ b/arch/powerpc/kernel/entry_64.S
>> @@ -278,7 +278,6 @@ 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 */
> 
> This misses system_call_vectored.

Oops yes, this patch was cooked before SCV where introduced. Fixes in v5.

Thanks
Christophe

[PATCH v4 15/23] powerpc/syscall: Change condition to check MSR_RI

[Christophe Leroy]

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>
---
 arch/powerpc/kernel/syscall.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
index b66cfcbcb755..a3510fa4e641 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.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));
-- 
2.25.0

[PATCH v4 16/23] powerpc/32: Always save non volatile GPRs at syscall entry

[Christophe Leroy]

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

[PATCH v4 17/23] powerpc/syscall: implement system call entry/exit logic in C for PPC32

[Christophe Leroy]

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   | 227 ++++---------------------------
 arch/powerpc/kernel/head_32.h    |  16 ---
 arch/powerpc/kernel/head_booke.h |  15 --
 3 files changed, 29 insertions(+), 229 deletions(-)

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 97dc28a68465..ce5fdb23ed7c 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -329,117 +329,22 @@ 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 */
+	mr	r9,r0
+	addi	r10,r1,STACK_FRAME_OVERHEAD
+	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. */
@@ -453,34 +358,39 @@ 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
-	kuap_check r2, r4
 	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 +398,6 @@ _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 +416,6 @@ 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..c2aa0d8f1f63 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -162,9 +162,6 @@
 	   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 +173,8 @@
 	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..faff094b650e 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -138,7 +138,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 	   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 +156,6 @@ 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

[PATCH v4 18/23] powerpc/32: Remove verification of MSR_PR on syscall in the ASM entry

[Christophe Leroy]

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 ce5fdb23ed7c..9922a04650f7 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -416,36 +416,6 @@ 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 c2aa0d8f1f63..c0de4acbe3f8 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
@@ -176,7 +174,6 @@
 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 faff094b650e..7af84e1e717b 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
@@ -157,7 +155,6 @@ 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

[PATCH v4 19/23] powerpc/syscall: Avoid stack frame in likely part of system_call_exception()

[Christophe Leroy]

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/syscall.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
index a3510fa4e641..476909b11051 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.c
@@ -115,6 +115,9 @@ 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

Re: [PATCH v4 19/23] powerpc/syscall: Avoid stack frame in likely part of system_call_exception()

[Nicholas Piggin]

Excerpts from Christophe Leroy's message of January 26, 2021 12:48 am:
> 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/syscall.c | 3 +++
>  1 file changed, 3 insertions(+)
> 
> diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
> index a3510fa4e641..476909b11051 100644
> --- a/arch/powerpc/kernel/syscall.c
> +++ b/arch/powerpc/kernel/syscall.c
> @@ -115,6 +115,9 @@ 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? */
> -- 

Nice optimisation, great analysis and catch. I'll have to test it on 
ppc64.

Thanks,
Nick

[PATCH v4 20/23] powerpc/syscall: Do not check unsupported scv vector on PPC32

[Christophe Leroy]

Only PPC64 has scv. No need to check the 0x7ff0 trap on PPC32.

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

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/kernel/entry_32.S | 1 -
 arch/powerpc/kernel/syscall.c  | 7 +++++--
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 9922a04650f7..6ae9c7bcb06c 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -343,7 +343,6 @@ 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/syscall.c b/arch/powerpc/kernel/syscall.c
index 476909b11051..30f8a397a522 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.c
@@ -86,7 +86,7 @@ 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 (IS_ENABLED(CONFIG_PPC64) && unlikely(regs->trap == 0x7ff0)) {
 			/* Unsupported scv vector */
 			_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
 			return regs->gpr[3];
@@ -109,7 +109,7 @@ 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 (IS_ENABLED(CONFIG_PPC64) && unlikely(regs->trap == 0x7ff0)) {
 			/* Unsupported scv vector */
 			_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
 			return regs->gpr[3];
@@ -187,6 +187,9 @@ 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);
 
 	kuap_check();
-- 
2.25.0

Re: [PATCH v4 20/23] powerpc/syscall: Do not check unsupported scv vector on PPC32

[Nicholas Piggin]

Excerpts from Christophe Leroy's message of January 26, 2021 12:48 am:
> Only PPC64 has scv. No need to check the 0x7ff0 trap on PPC32.
> 
> And ignore the scv parameter in syscall_exit_prepare (Save 14 cycles
> 346 => 332 cycles)
> 
> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
> ---
>  arch/powerpc/kernel/entry_32.S | 1 -
>  arch/powerpc/kernel/syscall.c  | 7 +++++--
>  2 files changed, 5 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
> index 9922a04650f7..6ae9c7bcb06c 100644
> --- a/arch/powerpc/kernel/entry_32.S
> +++ b/arch/powerpc/kernel/entry_32.S
> @@ -343,7 +343,6 @@ 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/syscall.c b/arch/powerpc/kernel/syscall.c
> index 476909b11051..30f8a397a522 100644
> --- a/arch/powerpc/kernel/syscall.c
> +++ b/arch/powerpc/kernel/syscall.c
> @@ -86,7 +86,7 @@ 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 (IS_ENABLED(CONFIG_PPC64) && unlikely(regs->trap == 0x7ff0)) {
>  			/* Unsupported scv vector */
>  			_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
>  			return regs->gpr[3];
> @@ -109,7 +109,7 @@ 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 (IS_ENABLED(CONFIG_PPC64) && unlikely(regs->trap == 0x7ff0)) {

Perhaps this could be hidden behind a function like trap_is_scv()?

trap_is_unsupported_scv() ?

Thanks,
Nick

Re: [PATCH v4 20/23] powerpc/syscall: Do not check unsupported scv vector on PPC32

[Christophe Leroy]

Le 26/01/2021 à 11:16, Nicholas Piggin a écrit :
> Excerpts from Christophe Leroy's message of January 26, 2021 12:48 am:
>> Only PPC64 has scv. No need to check the 0x7ff0 trap on PPC32.
>>
>> And ignore the scv parameter in syscall_exit_prepare (Save 14 cycles
>> 346 => 332 cycles)
>>
>> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
>> ---
>>   arch/powerpc/kernel/entry_32.S | 1 -
>>   arch/powerpc/kernel/syscall.c  | 7 +++++--
>>   2 files changed, 5 insertions(+), 3 deletions(-)
>>
>> diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
>> index 9922a04650f7..6ae9c7bcb06c 100644
>> --- a/arch/powerpc/kernel/entry_32.S
>> +++ b/arch/powerpc/kernel/entry_32.S
>> @@ -343,7 +343,6 @@ 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/syscall.c b/arch/powerpc/kernel/syscall.c
>> index 476909b11051..30f8a397a522 100644
>> --- a/arch/powerpc/kernel/syscall.c
>> +++ b/arch/powerpc/kernel/syscall.c
>> @@ -86,7 +86,7 @@ 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 (IS_ENABLED(CONFIG_PPC64) && unlikely(regs->trap == 0x7ff0)) {
>>   			/* Unsupported scv vector */
>>   			_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
>>   			return regs->gpr[3];
>> @@ -109,7 +109,7 @@ 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 (IS_ENABLED(CONFIG_PPC64) && unlikely(regs->trap == 0x7ff0)) {
> 
> Perhaps this could be hidden behind a function like trap_is_scv()?
> 
> trap_is_unsupported_scv() ?
> 

Ok, I did that in v5

Thanks
Christophe

[PATCH v4 21/23] powerpc/syscall: Remove FULL_REGS verification in system_call_exception

[Christophe Leroy]

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/syscall.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
index 30f8a397a522..a40775daa88b 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.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

[PATCH v4 22/23] powerpc/syscall: Optimise checks in beginning of system_call_exception()

[Christophe Leroy]

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/syscall.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
index a40775daa88b..47ae55f94d1c 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.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

[PATCH v4 23/23] powerpc/syscall: Avoid storing 'current' in another pointer

[Christophe Leroy]

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>
---
 arch/powerpc/kernel/syscall.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
index 47ae55f94d1c..72e0b18b88d8 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.c
@@ -186,7 +186,6 @@ 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;
 
@@ -202,7 +201,7 @@ 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)))) {
@@ -216,7 +215,7 @@ 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;
 	}
@@ -228,7 +227,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 
 again:
 	local_irq_disable();
-	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) {
@@ -244,7 +243,7 @@ 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)) {
-- 
2.25.0