* [PATCH v16 05/21] powerpc: prep stack walkers for THREAD_INFO_IN_TASK
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
[text copied from commit 9bbd4c56b0b6
("arm64: prep stack walkers for THREAD_INFO_IN_TASK")]
When CONFIG_THREAD_INFO_IN_TASK is selected, task stacks may be freed
before a task is destroyed. To account for this, the stacks are
refcounted, and when manipulating the stack of another task, it is
necessary to get/put the stack to ensure it isn't freed and/or re-used
while we do so.
This patch reworks the powerpc stack walking code to account for this.
When CONFIG_THREAD_INFO_IN_TASK is not selected these perform no
refcounting, and this should only be a structural change that does not
affect behaviour.
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/kernel/process.c | 23 +++++++++++++++++++++--
arch/powerpc/kernel/stacktrace.c | 29 ++++++++++++++++++++++++++---
2 files changed, 47 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index ce393df243aa..4ffbb677c9f5 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -2027,7 +2027,7 @@ int validate_sp(unsigned long sp, struct task_struct *p,
EXPORT_SYMBOL(validate_sp);
-unsigned long get_wchan(struct task_struct *p)
+static unsigned long __get_wchan(struct task_struct *p)
{
unsigned long ip, sp;
int count = 0;
@@ -2053,6 +2053,20 @@ unsigned long get_wchan(struct task_struct *p)
return 0;
}
+unsigned long get_wchan(struct task_struct *p)
+{
+ unsigned long ret;
+
+ if (!try_get_task_stack(p))
+ return 0;
+
+ ret = __get_wchan(p);
+
+ put_task_stack(p);
+
+ return ret;
+}
+
static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH;
void show_stack(struct task_struct *tsk, unsigned long *stack)
@@ -2067,6 +2081,9 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
int curr_frame = 0;
#endif
+ if (!try_get_task_stack(tsk))
+ return;
+
sp = (unsigned long) stack;
if (tsk == NULL)
tsk = current;
@@ -2081,7 +2098,7 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
printk("Call Trace:\n");
do {
if (!validate_sp(sp, tsk, STACK_FRAME_OVERHEAD))
- return;
+ break;
stack = (unsigned long *) sp;
newsp = stack[0];
@@ -2121,6 +2138,8 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
sp = newsp;
} while (count++ < kstack_depth_to_print);
+
+ put_task_stack(tsk);
}
#ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index cf31ce6c1f53..f958f3bcba04 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -67,12 +67,17 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
{
unsigned long sp;
+ if (!try_get_task_stack(tsk))
+ return;
+
if (tsk == current)
sp = current_stack_pointer();
else
sp = tsk->thread.ksp;
save_context_stack(trace, sp, tsk, 0);
+
+ put_task_stack(tsk);
}
EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
@@ -90,9 +95,8 @@ EXPORT_SYMBOL_GPL(save_stack_trace_regs);
*
* If the task is not 'current', the caller *must* ensure the task is inactive.
*/
-int
-save_stack_trace_tsk_reliable(struct task_struct *tsk,
- struct stack_trace *trace)
+static int __save_stack_trace_tsk_reliable(struct task_struct *tsk,
+ struct stack_trace *trace)
{
unsigned long sp;
unsigned long newsp;
@@ -197,6 +201,25 @@ save_stack_trace_tsk_reliable(struct task_struct *tsk,
}
return 0;
}
+
+int save_stack_trace_tsk_reliable(struct task_struct *tsk,
+ struct stack_trace *trace)
+{
+ int ret;
+
+ /*
+ * If the task doesn't have a stack (e.g., a zombie), the stack is
+ * "reliably" empty.
+ */
+ if (!try_get_task_stack(tsk))
+ return 0;
+
+ ret = __save_stack_trace_tsk_reliable(tsk, trace);
+
+ put_task_stack(tsk);
+
+ return ret;
+}
EXPORT_SYMBOL_GPL(save_stack_trace_tsk_reliable);
#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */
--
2.20.1
^ permalink raw reply related
* [PATCH v16 06/21] powerpc: Rename THREAD_INFO to TASK_STACK
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
This patch renames THREAD_INFO to TASK_STACK, because it is in fact
the offset of the pointer to the stack in task_struct so this pointer
will not be impacted by the move of THREAD_INFO.
Also make it available on 64-bit, as we'll need it there when we
activate THREAD_INFO_IN_TASK.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Make available on 64-bit]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/kernel/asm-offsets.c | 2 +-
arch/powerpc/kernel/entry_32.S | 2 +-
arch/powerpc/kernel/head_32.S | 2 +-
arch/powerpc/kernel/head_40x.S | 4 ++--
arch/powerpc/kernel/head_8xx.S | 2 +-
arch/powerpc/kernel/head_booke.h | 4 ++--
arch/powerpc/kernel/head_fsl_booke.S | 2 +-
7 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 9ffc72ded73a..b2b52e002a76 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -90,10 +90,10 @@ int main(void)
DEFINE(SIGSEGV, SIGSEGV);
DEFINE(NMI_MASK, NMI_MASK);
#else
- OFFSET(THREAD_INFO, task_struct, stack);
DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
OFFSET(KSP_LIMIT, thread_struct, ksp_limit);
#endif /* CONFIG_PPC64 */
+ OFFSET(TASK_STACK, task_struct, stack);
#ifdef CONFIG_LIVEPATCH
OFFSET(TI_livepatch_sp, thread_info, livepatch_sp);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index d4c6186aa7e8..f1646d845404 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -1168,7 +1168,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
mfspr r9,SPRN_SPRG_THREAD
lwz r10,SAVED_KSP_LIMIT(r1)
stw r10,KSP_LIMIT(r9)
- lwz r9,THREAD_INFO-THREAD(r9)
+ lwz r9,TASK_STACK-THREAD(r9)
CURRENT_THREAD_INFO(r10, r1)
lwz r10,TI_PREEMPT(r10)
stw r10,TI_PREEMPT(r9)
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 05b08db3901d..9268e5e87949 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -261,7 +261,7 @@ _ENTRY(_start);
tophys(r11,r1); /* use tophys(r1) if kernel */ \
beq 1f; \
mfspr r11,SPRN_SPRG_THREAD; \
- lwz r11,THREAD_INFO-THREAD(r11); \
+ lwz r11,TASK_STACK-THREAD(r11); \
addi r11,r11,THREAD_SIZE; \
tophys(r11,r11); \
1: subi r11,r11,INT_FRAME_SIZE /* alloc exc. frame */
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index b19d78410511..3088c9f29f5e 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -115,7 +115,7 @@ _ENTRY(saved_ksp_limit)
andi. r11,r11,MSR_PR; \
beq 1f; \
mfspr r1,SPRN_SPRG_THREAD; /* if from user, start at top of */\
- lwz r1,THREAD_INFO-THREAD(r1); /* this thread's kernel stack */\
+ lwz r1,TASK_STACK-THREAD(r1); /* this thread's kernel stack */\
addi r1,r1,THREAD_SIZE; \
1: subi r1,r1,INT_FRAME_SIZE; /* Allocate an exception frame */\
tophys(r11,r1); \
@@ -158,7 +158,7 @@ _ENTRY(saved_ksp_limit)
beq 1f; \
/* COMING FROM USER MODE */ \
mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\
- lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
+ lwz r11,TASK_STACK-THREAD(r11); /* this thread's kernel stack */\
1: addi r11,r11,THREAD_SIZE-INT_FRAME_SIZE; /* Alloc an excpt frm */\
tophys(r11,r11); \
stw r10,_CCR(r11); /* save various registers */\
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 57deb1e9ffea..5f5f89e87e3a 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -142,7 +142,7 @@ _ENTRY(_start);
tophys(r11,r1); /* use tophys(r1) if kernel */ \
beq 1f; \
mfspr r11,SPRN_SPRG_THREAD; \
- lwz r11,THREAD_INFO-THREAD(r11); \
+ lwz r11,TASK_STACK-THREAD(r11); \
addi r11,r11,THREAD_SIZE; \
tophys(r11,r11); \
1: subi r11,r11,INT_FRAME_SIZE /* alloc exc. frame */
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 306e26c073a0..69e80e6d0d16 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -55,7 +55,7 @@ END_BTB_FLUSH_SECTION
beq 1f; \
BOOKE_CLEAR_BTB(r11) \
/* if from user, start at top of this thread's kernel stack */ \
- lwz r11, THREAD_INFO-THREAD(r10); \
+ lwz r11, TASK_STACK - THREAD(r10); \
ALLOC_STACK_FRAME(r11, THREAD_SIZE); \
1 : subi r11, r11, INT_FRAME_SIZE; /* Allocate exception frame */ \
stw r13, _CCR(r11); /* save various registers */ \
@@ -142,7 +142,7 @@ END_BTB_FLUSH_SECTION
BOOKE_CLEAR_BTB(r10) \
andi. r11,r11,MSR_PR; \
mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\
- lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
+ lwz r11, TASK_STACK - THREAD(r11); /* this thread's kernel stack */\
addi r11,r11,EXC_LVL_FRAME_OVERHEAD; /* allocate stack frame */\
beq 1f; \
/* COMING FROM USER MODE */ \
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 2c21e8642a00..42d8d6fc00cb 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -719,7 +719,7 @@ END_BTB_FLUSH_SECTION
/* Get the next_tlbcam_idx percpu var */
#ifdef CONFIG_SMP
- lwz r12, THREAD_INFO-THREAD(r12)
+ lwz r12, TASK_STACK-THREAD(r12)
lwz r15, TI_CPU(r12)
lis r14, __per_cpu_offset@h
ori r14, r14, __per_cpu_offset@l
--
2.20.1
^ permalink raw reply related
* [PATCH v16 07/21] powerpc: call_do_[soft]irq() takes a pointer to the stack
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
The purpose of the pointer given to call_do_softirq() and
call_do_irq() is to point the new stack. Currently that's the same
thing as the thread_info, but won't be with THREAD_INFO_IN_TASK.
So change the parameter to void* and rename it 'sp'.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Split out of larger patch]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/irq.h | 4 ++--
arch/powerpc/kernel/misc_32.S | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index ee39ce56b2a2..2efbae8d93be 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -63,8 +63,8 @@ extern struct thread_info *hardirq_ctx[NR_CPUS];
extern struct thread_info *softirq_ctx[NR_CPUS];
extern void irq_ctx_init(void);
-extern void call_do_softirq(struct thread_info *tp);
-extern void call_do_irq(struct pt_regs *regs, struct thread_info *tp);
+void call_do_softirq(void *sp);
+void call_do_irq(struct pt_regs *regs, void *sp);
extern void do_IRQ(struct pt_regs *regs);
extern void __init init_IRQ(void);
extern void __do_irq(struct pt_regs *regs);
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 02b8cdd73792..242f0c88010e 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -60,7 +60,7 @@ _GLOBAL(call_do_softirq)
blr
/*
- * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp);
+ * void call_do_irq(struct pt_regs *regs, void *sp);
*/
_GLOBAL(call_do_irq)
mflr r0
--
2.20.1
^ permalink raw reply related
* [PATCH v16 08/21] powerpc: Don't use CURRENT_THREAD_INFO to find the stack
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
A few places use CURRENT_THREAD_INFO, or the C version, to find the
stack. This will no longer work with THREAD_INFO_IN_TASK so change
them to find the stack in other ways.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Split out of larger patch]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/kernel/entry_64.S | 2 +-
arch/powerpc/kernel/irq.c | 2 +-
arch/powerpc/kernel/misc_32.S | 2 +-
3 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index c17c1bed6148..21f1cb4d464e 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -689,7 +689,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
2:
#endif /* CONFIG_PPC_BOOK3S_64 */
- CURRENT_THREAD_INFO(r7, r8) /* base of new stack */
+ clrrdi r7, r8, THREAD_SHIFT /* base of new stack */
/* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE
because we don't need to leave the 288-byte ABI gap at the
top of the kernel stack. */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 4a5dd8800946..531e9ef153c0 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -663,7 +663,7 @@ void do_IRQ(struct pt_regs *regs)
struct thread_info *curtp, *irqtp, *sirqtp;
/* Switch to the irq stack to handle this */
- curtp = current_thread_info();
+ curtp = (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
irqtp = hardirq_ctx[raw_smp_processor_id()];
sirqtp = softirq_ctx[raw_smp_processor_id()];
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 242f0c88010e..b37b50fde828 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -603,7 +603,7 @@ EXPORT_SYMBOL(__bswapdi2)
#ifdef CONFIG_SMP
_GLOBAL(start_secondary_resume)
/* Reset stack */
- CURRENT_THREAD_INFO(r1, r1)
+ rlwinm r1, r1, 0, 0, 31 - THREAD_SHIFT
addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
li r3,0
stw r3,0(r1) /* Zero the stack frame pointer */
--
2.20.1
^ permalink raw reply related
* [PATCH v16 09/21] powerpc: Replace current_thread_info()->task with current
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
We have a few places that use current_thread_info()->task to access
current. This won't work with THREAD_INFO_IN_TASK so fix them now.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Split out of larger patch]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/kernel/process.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 4ffbb677c9f5..21c1e11a06de 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1231,8 +1231,8 @@ struct task_struct *__switch_to(struct task_struct *prev,
batch->active = 1;
}
- if (current_thread_info()->task->thread.regs) {
- restore_math(current_thread_info()->task->thread.regs);
+ if (current->thread.regs) {
+ restore_math(current->thread.regs);
/*
* The copy-paste buffer can only store into foreign real
@@ -1242,7 +1242,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
* mappings, we must issue a cp_abort to clear any state and
* prevent snooping, corruption or a covert channel.
*/
- if (current_thread_info()->task->thread.used_vas)
+ if (current->thread.used_vas)
asm volatile(PPC_CP_ABORT);
}
#endif /* CONFIG_PPC_BOOK3S_64 */
--
2.20.1
^ permalink raw reply related
* [PATCH v16 10/21] powerpc: Update comments in preparation for THREAD_INFO_IN_TASK
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
Update a few comments that talk about current_thread_info() in
preparation for THREAD_INFO_IN_TASK.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Split out of larger patch]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/reg.h | 2 +-
arch/powerpc/kernel/head_32.S | 2 +-
arch/powerpc/kernel/head_44x.S | 2 +-
arch/powerpc/kernel/head_fsl_booke.S | 2 +-
4 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 1c98ef1f2d5b..581e61db2dcf 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1062,7 +1062,7 @@
* - SPRG9 debug exception scratch
*
* All 32-bit:
- * - SPRG3 current thread_info pointer
+ * - SPRG3 current thread_struct physical addr pointer
* (virtual on BookE, physical on others)
*
* 32-bit classic:
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 9268e5e87949..8282d25948ae 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -845,7 +845,7 @@ _ENTRY(copy_and_flush)
bl init_idle_6xx
#endif /* CONFIG_PPC_BOOK3S_32 */
- /* get current_thread_info and current */
+ /* get current's stack and current */
lis r1,secondary_ti@ha
tophys(r1,r1)
lwz r1,secondary_ti@l(r1)
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index bf23c19c92d6..4e8c8bf50413 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -1019,7 +1019,7 @@ _GLOBAL(start_secondary_47x)
/* Now we can get our task struct and real stack pointer */
- /* Get current_thread_info and current */
+ /* Get current's stack and current */
lis r1,secondary_ti@ha
lwz r1,secondary_ti@l(r1)
lwz r2,TI_TASK(r1)
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 42d8d6fc00cb..6301bb24889a 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -1091,7 +1091,7 @@ _GLOBAL(set_context)
mr r4,r24 /* Why? */
bl call_setup_cpu
- /* get current_thread_info and current */
+ /* get current's stack and current */
lis r1,secondary_ti@ha
lwz r1,secondary_ti@l(r1)
lwz r2,TI_TASK(r1)
--
2.20.1
^ permalink raw reply related
* [PATCH v16 11/21] powerpc/64: Use task_stack_page() to initialise paca->kstack
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
Rather than using the thread info use task_stack_page() to initialise
paca->kstack, that way it will work with THREAD_INFO_IN_TASK.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Split out of larger patch]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/kernel/smp.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 3f15edf25a0d..1d3e7cb6704d 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -20,6 +20,7 @@
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/sched/mm.h>
+#include <linux/sched/task_stack.h>
#include <linux/sched/topology.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
@@ -1017,7 +1018,8 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
#ifdef CONFIG_PPC64
paca_ptrs[cpu]->__current = idle;
- paca_ptrs[cpu]->kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD;
+ paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) +
+ THREAD_SIZE - STACK_FRAME_OVERHEAD;
#endif
ti->cpu = cpu;
secondary_ti = current_set[cpu] = ti;
--
2.20.1
^ permalink raw reply related
* [PATCH v16 12/21] powerpc: Use sizeof(struct thread_info) in INIT_SP_LIMIT
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
Currently INIT_SP_LIMIT uses sizeof(init_thread_info), but that symbol
won't exist when we enable THREAD_INFO_IN_TASK. So just use the sizeof
the type which is the same value but will continue to work.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Split out of larger patch]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/processor.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index d9b1503ba0f0..b40b614047e4 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -268,7 +268,7 @@ struct thread_struct {
#define INIT_SP (sizeof(init_stack) + (unsigned long) &init_stack)
#define INIT_SP_LIMIT \
- (_ALIGN_UP(sizeof(init_thread_info), 16) + (unsigned long) &init_stack)
+ (_ALIGN_UP(sizeof(struct thread_info), 16) + (unsigned long)&init_stack)
#ifdef CONFIG_SPE
#define SPEFSCR_INIT \
--
2.20.1
^ permalink raw reply related
* [PATCH v16 13/21] powerpc: Use linux/thread_info.h in processor.h
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
When we enable THREAD_INFO_IN_TASK we will remove our definition of
current_thread_info(). Instead it will come from linux/thread_info.h
So switch processor.h to include the latter, so that it can continue
to find current_thread_info().
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Split out of larger patch]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/processor.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index b40b614047e4..9226fb83a82e 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -40,7 +40,7 @@
#ifndef __ASSEMBLY__
#include <linux/types.h>
-#include <asm/thread_info.h>
+#include <linux/thread_info.h>
#include <asm/ptrace.h>
#include <asm/hw_breakpoint.h>
--
2.20.1
^ permalink raw reply related
* [PATCH v16 14/21] powerpc: Use task_stack_page() in current_pt_regs()
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
Change current_pt_regs() to use task_stack_page() rather than
current_thread_info() so that it keeps working once we enable
THREAD_INFO_IN_TASK.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
[mpe: Split out of large patch]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/ptrace.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 0b8a735b6d85..64271e562fed 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -157,7 +157,7 @@ extern int ptrace_put_reg(struct task_struct *task, int regno,
unsigned long data);
#define current_pt_regs() \
- ((struct pt_regs *)((unsigned long)current_thread_info() + THREAD_SIZE) - 1)
+ ((struct pt_regs *)((unsigned long)task_stack_page(current) + THREAD_SIZE) - 1)
/*
* We use the least-significant bit of the trap field to indicate
* whether we have saved the full set of registers, or only a
--
2.20.1
^ permalink raw reply related
* [PATCH v16 15/21] powerpc/idle/6xx: Use r1 with CURRENT_THREAD_INFO()
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
Make sure CURRENT_THREAD_INFO() is used with r1 which is the virtual
address of the stack, in order to ease the switch to r2 when we enable
THREAD_INFO_IN_TASK, as we have no register having the phys address of
current.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
[mpe: Split out of larger patch]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/kernel/idle_6xx.S | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S
index ff026c9d3cab..d9b6e7e0b5e3 100644
--- a/arch/powerpc/kernel/idle_6xx.S
+++ b/arch/powerpc/kernel/idle_6xx.S
@@ -159,7 +159,8 @@ _GLOBAL(power_save_ppc32_restore)
stw r9,_NIP(r11) /* make it do a blr */
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r12, r11)
+ CURRENT_THREAD_INFO(r12, r1)
+ tophys(r12, r12)
lwz r11,TI_CPU(r12) /* get cpu number * 4 */
slwi r11,r11,2
#else
--
2.20.1
^ permalink raw reply related
* [PATCH v16 16/21] powerpc: Activate CONFIG_THREAD_INFO_IN_TASK
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
This patch activates CONFIG_THREAD_INFO_IN_TASK which
moves the thread_info into task_struct.
Moving thread_info into task_struct has the following advantages:
- It protects thread_info from corruption in the case of stack
overflows.
- Its address is harder to determine if stack addresses are leaked,
making a number of attacks more difficult.
This has the following consequences:
- thread_info is now located at the beginning of task_struct.
- The 'cpu' field is now in task_struct, and only exists when
CONFIG_SMP is active.
- thread_info doesn't have anymore the 'task' field.
This patch:
- Removes all recopy of thread_info struct when the stack changes.
- Changes the CURRENT_THREAD_INFO() macro to point to current.
- Selects CONFIG_THREAD_INFO_IN_TASK.
- Modifies raw_smp_processor_id() to get ->cpu from current without
including linux/sched.h to avoid circular inclusion and without
including asm/asm-offsets.h to avoid symbol names duplication
between ASM constants and C constants.
- Modifies klp_init_thread_info() to take a task_struct pointer
argument.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Add task_stack.h to livepatch.h to fix build fails]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/Kconfig | 1 +
arch/powerpc/Makefile | 7 +++
arch/powerpc/include/asm/irq.h | 4 --
arch/powerpc/include/asm/livepatch.h | 7 ++-
arch/powerpc/include/asm/smp.h | 17 +++++-
arch/powerpc/include/asm/thread_info.h | 17 +-----
arch/powerpc/kernel/asm-offsets.c | 7 ++-
arch/powerpc/kernel/entry_32.S | 9 ++-
arch/powerpc/kernel/exceptions-64e.S | 11 ----
arch/powerpc/kernel/head_32.S | 6 +-
arch/powerpc/kernel/head_44x.S | 4 +-
arch/powerpc/kernel/head_64.S | 1 +
arch/powerpc/kernel/head_booke.h | 8 +--
arch/powerpc/kernel/head_fsl_booke.S | 7 +--
arch/powerpc/kernel/irq.c | 79 +-------------------------
arch/powerpc/kernel/kgdb.c | 28 ---------
arch/powerpc/kernel/machine_kexec_64.c | 6 +-
arch/powerpc/kernel/process.c | 2 +-
arch/powerpc/kernel/setup-common.c | 2 +-
arch/powerpc/kernel/setup_64.c | 21 -------
arch/powerpc/kernel/smp.c | 2 +-
arch/powerpc/net/bpf_jit32.h | 5 +-
22 files changed, 57 insertions(+), 194 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 08908219fba9..3f237ffa0649 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -241,6 +241,7 @@ config PPC
select RTC_LIB
select SPARSE_IRQ
select SYSCTL_EXCEPTION_TRACE
+ select THREAD_INFO_IN_TASK
select VIRT_TO_BUS if !PPC64
#
# Please keep this list sorted alphabetically.
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index ac033341ed55..53ffe935f3b0 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -427,6 +427,13 @@ else
endif
endif
+ifdef CONFIG_SMP
+prepare: task_cpu_prepare
+
+task_cpu_prepare: prepare0
+ $(eval KBUILD_CFLAGS += -D_TASK_CPU=$(shell awk '{if ($$2 == "TI_CPU") print $$3;}' include/generated/asm-offsets.h))
+endif
+
# Check toolchain versions:
# - gcc-4.6 is the minimum kernel-wide version so nothing required.
checkbin:
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 2efbae8d93be..28a7ace0a1b9 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -51,9 +51,6 @@ struct pt_regs;
extern struct thread_info *critirq_ctx[NR_CPUS];
extern struct thread_info *dbgirq_ctx[NR_CPUS];
extern struct thread_info *mcheckirq_ctx[NR_CPUS];
-extern void exc_lvl_ctx_init(void);
-#else
-#define exc_lvl_ctx_init()
#endif
/*
@@ -62,7 +59,6 @@ extern void exc_lvl_ctx_init(void);
extern struct thread_info *hardirq_ctx[NR_CPUS];
extern struct thread_info *softirq_ctx[NR_CPUS];
-extern void irq_ctx_init(void);
void call_do_softirq(void *sp);
void call_do_irq(struct pt_regs *regs, void *sp);
extern void do_IRQ(struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/livepatch.h b/arch/powerpc/include/asm/livepatch.h
index 47a03b9b528b..5070df19d463 100644
--- a/arch/powerpc/include/asm/livepatch.h
+++ b/arch/powerpc/include/asm/livepatch.h
@@ -21,6 +21,7 @@
#include <linux/module.h>
#include <linux/ftrace.h>
+#include <linux/sched/task_stack.h>
#ifdef CONFIG_LIVEPATCH
static inline int klp_check_compiler_support(void)
@@ -43,13 +44,13 @@ static inline unsigned long klp_get_ftrace_location(unsigned long faddr)
return ftrace_location_range(faddr, faddr + 16);
}
-static inline void klp_init_thread_info(struct thread_info *ti)
+static inline void klp_init_thread_info(struct task_struct *p)
{
/* + 1 to account for STACK_END_MAGIC */
- ti->livepatch_sp = (unsigned long *)(ti + 1) + 1;
+ task_thread_info(p)->livepatch_sp = end_of_stack(p) + 1;
}
#else
-static void klp_init_thread_info(struct thread_info *ti) { }
+static inline void klp_init_thread_info(struct task_struct *p) { }
#endif /* CONFIG_LIVEPATCH */
#endif /* _ASM_POWERPC_LIVEPATCH_H */
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 41695745032c..0de717e16dd6 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -83,7 +83,22 @@ int is_cpu_dead(unsigned int cpu);
/* 32-bit */
extern int smp_hw_index[];
-#define raw_smp_processor_id() (current_thread_info()->cpu)
+/*
+ * This is particularly ugly: it appears we can't actually get the definition
+ * of task_struct here, but we need access to the CPU this task is running on.
+ * Instead of using task_struct we're using _TASK_CPU which is extracted from
+ * asm-offsets.h by kbuild to get the current processor ID.
+ *
+ * This also needs to be safeguarded when building asm-offsets.s because at
+ * that time _TASK_CPU is not defined yet. It could have been guarded by
+ * _TASK_CPU itself, but we want the build to fail if _TASK_CPU is missing
+ * when building something else than asm-offsets.s
+ */
+#ifdef GENERATING_ASM_OFFSETS
+#define raw_smp_processor_id() (0)
+#else
+#define raw_smp_processor_id() (*(unsigned int *)((void *)current + _TASK_CPU))
+#endif
#define hard_smp_processor_id() (smp_hw_index[smp_processor_id()])
static inline int get_hard_smp_processor_id(int cpu)
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 544cac0474cb..d91523c2c7d8 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -18,9 +18,9 @@
#define THREAD_SIZE (1 << THREAD_SHIFT)
#ifdef CONFIG_PPC64
-#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(clrrdi dest, sp, THREAD_SHIFT)
+#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(ld dest, PACACURRENT(r13))
#else
-#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(rlwinm dest, sp, 0, 0, 31-THREAD_SHIFT)
+#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(mr dest, r2)
#endif
#ifndef __ASSEMBLY__
@@ -34,8 +34,6 @@
* low level task data.
*/
struct thread_info {
- struct task_struct *task; /* main task structure */
- int cpu; /* cpu we're on */
int preempt_count; /* 0 => preemptable,
<0 => BUG */
unsigned long local_flags; /* private flags for thread */
@@ -58,8 +56,6 @@ struct thread_info {
*/
#define INIT_THREAD_INFO(tsk) \
{ \
- .task = &tsk, \
- .cpu = 0, \
.preempt_count = INIT_PREEMPT_COUNT, \
.flags = 0, \
}
@@ -67,15 +63,6 @@ struct thread_info {
#define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT)
/* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
- unsigned long val;
-
- asm (CURRENT_THREAD_INFO(%0,1) : "=r" (val));
-
- return (struct thread_info *)val;
-}
-
extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
#ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index b2b52e002a76..1fb52206c106 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -13,6 +13,8 @@
* 2 of the License, or (at your option) any later version.
*/
+#define GENERATING_ASM_OFFSETS /* asm/smp.h */
+
#include <linux/compat.h>
#include <linux/signal.h>
#include <linux/sched.h>
@@ -94,6 +96,9 @@ int main(void)
OFFSET(KSP_LIMIT, thread_struct, ksp_limit);
#endif /* CONFIG_PPC64 */
OFFSET(TASK_STACK, task_struct, stack);
+#ifdef CONFIG_SMP
+ OFFSET(TI_CPU, task_struct, cpu);
+#endif
#ifdef CONFIG_LIVEPATCH
OFFSET(TI_livepatch_sp, thread_info, livepatch_sp);
@@ -161,8 +166,6 @@ int main(void)
OFFSET(TI_FLAGS, thread_info, flags);
OFFSET(TI_LOCAL_FLAGS, thread_info, local_flags);
OFFSET(TI_PREEMPT, thread_info, preempt_count);
- OFFSET(TI_TASK, thread_info, task);
- OFFSET(TI_CPU, thread_info, cpu);
#ifdef CONFIG_PPC64
OFFSET(DCACHEL1BLOCKSIZE, ppc64_caches, l1d.block_size);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index f1646d845404..3255c0840beb 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -1168,10 +1168,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
mfspr r9,SPRN_SPRG_THREAD
lwz r10,SAVED_KSP_LIMIT(r1)
stw r10,KSP_LIMIT(r9)
- lwz r9,TASK_STACK-THREAD(r9)
- CURRENT_THREAD_INFO(r10, r1)
- lwz r10,TI_PREEMPT(r10)
- stw r10,TI_PREEMPT(r9)
RESTORE_xSRR(SRR0,SRR1);
RESTORE_xSRR(CSRR0,CSRR1);
RESTORE_MMU_REGS;
@@ -1294,10 +1290,13 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFSET(CPU_FTR_601)
lwz r3,_TRAP(r1)
andi. r0,r3,1
- beq 4f
+ beq 5f
SAVE_NVGPRS(r1)
rlwinm r3,r3,0,0,30
stw r3,_TRAP(r1)
+5: mfspr r2,SPRN_SPRG_THREAD
+ addi r2,r2,-THREAD
+ tovirt(r2,r2) /* set back r2 to current */
4: addi r3,r1,STACK_FRAME_OVERHEAD
bl unrecoverable_exception
/* shouldn't return */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index afb638778f44..20f14996281d 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -77,17 +77,6 @@
andi. r3,r3,MSR_PR
bnelr
- /* Copy info into temporary exception thread info */
- ld r11,PACAKSAVE(r13)
- CURRENT_THREAD_INFO(r11, r11)
- CURRENT_THREAD_INFO(r12, r1)
- ld r10,TI_FLAGS(r11)
- std r10,TI_FLAGS(r12)
- ld r10,TI_PREEMPT(r11)
- std r10,TI_PREEMPT(r12)
- ld r10,TI_TASK(r11)
- std r10,TI_TASK(r12)
-
/*
* Advance to the next TLB exception frame for handler
* types that don't do it automatically.
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 8282d25948ae..309a45779ad5 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -848,9 +848,9 @@ _ENTRY(copy_and_flush)
/* get current's stack and current */
lis r1,secondary_ti@ha
tophys(r1,r1)
- lwz r1,secondary_ti@l(r1)
- tophys(r2,r1)
- lwz r2,TI_TASK(r2)
+ lwz r2,secondary_ti@l(r1)
+ tophys(r1,r2)
+ lwz r1,TASK_STACK(r1)
/* stack */
addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 4e8c8bf50413..f94a93b6c2f2 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -1021,8 +1021,8 @@ _GLOBAL(start_secondary_47x)
/* Get current's stack and current */
lis r1,secondary_ti@ha
- lwz r1,secondary_ti@l(r1)
- lwz r2,TI_TASK(r1)
+ lwz r2,secondary_ti@l(r1)
+ lwz r1,TASK_STACK(r2)
/* Current stack pointer */
addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 4898e9491a1c..c6a9bf7b34bf 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -805,6 +805,7 @@ _GLOBAL(pmac_secondary_start)
LOAD_REG_ADDR(r3, current_set)
sldi r28,r24,3 /* get current_set[cpu#] */
ldx r14,r3,r28
+ ld r14,TASK_STACK(r14)
addi r14,r14,THREAD_SIZE-STACK_FRAME_OVERHEAD
std r14,PACAKSAVE(r13)
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 69e80e6d0d16..1b22a8dea399 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -155,13 +155,7 @@ END_BTB_FLUSH_SECTION
stw r10,GPR11(r11); \
b 2f; \
/* COMING FROM PRIV MODE */ \
-1: lwz r9,TI_FLAGS-EXC_LVL_FRAME_OVERHEAD(r11); \
- lwz r10,TI_PREEMPT-EXC_LVL_FRAME_OVERHEAD(r11); \
- stw r9,TI_FLAGS-EXC_LVL_FRAME_OVERHEAD(r8); \
- stw r10,TI_PREEMPT-EXC_LVL_FRAME_OVERHEAD(r8); \
- lwz r9,TI_TASK-EXC_LVL_FRAME_OVERHEAD(r11); \
- stw r9,TI_TASK-EXC_LVL_FRAME_OVERHEAD(r8); \
- mr r11,r8; \
+1: mr r11, r8; \
2: mfspr r8,SPRN_SPRG_RSCRATCH_##exc_level; \
stw r12,GPR12(r11); /* save various registers */\
mflr r10; \
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 6301bb24889a..11f38adbe020 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -719,8 +719,7 @@ END_BTB_FLUSH_SECTION
/* Get the next_tlbcam_idx percpu var */
#ifdef CONFIG_SMP
- lwz r12, TASK_STACK-THREAD(r12)
- lwz r15, TI_CPU(r12)
+ lwz r15, TI_CPU-THREAD(r12)
lis r14, __per_cpu_offset@h
ori r14, r14, __per_cpu_offset@l
rlwinm r15, r15, 2, 0, 29
@@ -1093,8 +1092,8 @@ _GLOBAL(set_context)
/* get current's stack and current */
lis r1,secondary_ti@ha
- lwz r1,secondary_ti@l(r1)
- lwz r2,TI_TASK(r1)
+ lwz r2,secondary_ti@l(r1)
+ lwz r1,TASK_STACK(r2)
/* stack */
addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 531e9ef153c0..85c48911938a 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -673,24 +673,9 @@ void do_IRQ(struct pt_regs *regs)
set_irq_regs(old_regs);
return;
}
-
- /* Prepare the thread_info in the irq stack */
- irqtp->task = curtp->task;
- irqtp->flags = 0;
-
- /* Copy the preempt_count so that the [soft]irq checks work. */
- irqtp->preempt_count = curtp->preempt_count;
-
/* Switch stack and call */
call_do_irq(regs, irqtp);
- /* Restore stack limit */
- irqtp->task = NULL;
-
- /* Copy back updates to the thread_info */
- if (irqtp->flags)
- set_bits(irqtp->flags, &curtp->flags);
-
set_irq_regs(old_regs);
}
@@ -698,85 +683,23 @@ void __init init_IRQ(void)
{
if (ppc_md.init_IRQ)
ppc_md.init_IRQ();
-
- exc_lvl_ctx_init();
-
- irq_ctx_init();
}
#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
struct thread_info *critirq_ctx[NR_CPUS] __read_mostly;
struct thread_info *dbgirq_ctx[NR_CPUS] __read_mostly;
struct thread_info *mcheckirq_ctx[NR_CPUS] __read_mostly;
-
-void exc_lvl_ctx_init(void)
-{
- struct thread_info *tp;
- int i, cpu_nr;
-
- for_each_possible_cpu(i) {
-#ifdef CONFIG_PPC64
- cpu_nr = i;
-#else
-#ifdef CONFIG_SMP
- cpu_nr = get_hard_smp_processor_id(i);
-#else
- cpu_nr = 0;
-#endif
-#endif
-
- tp = critirq_ctx[cpu_nr];
- tp->cpu = cpu_nr;
- tp->preempt_count = 0;
-
-#ifdef CONFIG_BOOKE
- tp = dbgirq_ctx[cpu_nr];
- tp->cpu = cpu_nr;
- tp->preempt_count = 0;
-
- tp = mcheckirq_ctx[cpu_nr];
- tp->cpu = cpu_nr;
- tp->preempt_count = HARDIRQ_OFFSET;
-#endif
- }
-}
#endif
struct thread_info *softirq_ctx[NR_CPUS] __read_mostly;
struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly;
-void irq_ctx_init(void)
-{
- struct thread_info *tp;
- int i;
-
- for_each_possible_cpu(i) {
- tp = softirq_ctx[i];
- tp->cpu = i;
- klp_init_thread_info(tp);
-
- tp = hardirq_ctx[i];
- tp->cpu = i;
- klp_init_thread_info(tp);
- }
-}
-
void do_softirq_own_stack(void)
{
- struct thread_info *curtp, *irqtp;
+ struct thread_info *irqtp;
- curtp = current_thread_info();
irqtp = softirq_ctx[smp_processor_id()];
- irqtp->task = curtp->task;
- irqtp->flags = 0;
call_do_softirq(irqtp);
- irqtp->task = NULL;
-
- /* Set any flag that may have been set on the
- * alternate stack
- */
- if (irqtp->flags)
- set_bits(irqtp->flags, &curtp->flags);
}
irq_hw_number_t virq_to_hw(unsigned int virq)
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index e1865565f0ae..7dd55eb1259d 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -151,41 +151,13 @@ static int kgdb_handle_breakpoint(struct pt_regs *regs)
return 1;
}
-static DEFINE_PER_CPU(struct thread_info, kgdb_thread_info);
static int kgdb_singlestep(struct pt_regs *regs)
{
- struct thread_info *thread_info, *exception_thread_info;
- struct thread_info *backup_current_thread_info =
- this_cpu_ptr(&kgdb_thread_info);
-
if (user_mode(regs))
return 0;
- /*
- * On Book E and perhaps other processors, singlestep is handled on
- * the critical exception stack. This causes current_thread_info()
- * to fail, since it it locates the thread_info by masking off
- * the low bits of the current stack pointer. We work around
- * this issue by copying the thread_info from the kernel stack
- * before calling kgdb_handle_exception, and copying it back
- * afterwards. On most processors the copy is avoided since
- * exception_thread_info == thread_info.
- */
- thread_info = (struct thread_info *)(regs->gpr[1] & ~(THREAD_SIZE-1));
- exception_thread_info = current_thread_info();
-
- if (thread_info != exception_thread_info) {
- /* Save the original current_thread_info. */
- memcpy(backup_current_thread_info, exception_thread_info, sizeof *thread_info);
- memcpy(exception_thread_info, thread_info, sizeof *thread_info);
- }
-
kgdb_handle_exception(0, SIGTRAP, 0, regs);
- if (thread_info != exception_thread_info)
- /* Restore current_thread_info lastly. */
- memcpy(exception_thread_info, backup_current_thread_info, sizeof *thread_info);
-
return 1;
}
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index a0f6f45005bd..75692c327ba0 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -317,10 +317,8 @@ void default_machine_kexec(struct kimage *image)
* We setup preempt_count to avoid using VMX in memcpy.
* XXX: the task struct will likely be invalid once we do the copy!
*/
- kexec_stack.thread_info.task = current_thread_info()->task;
- kexec_stack.thread_info.flags = 0;
- kexec_stack.thread_info.preempt_count = HARDIRQ_OFFSET;
- kexec_stack.thread_info.cpu = current_thread_info()->cpu;
+ current_thread_info()->flags = 0;
+ current_thread_info()->preempt_count = HARDIRQ_OFFSET;
/* We need a static PACA, too; copy this CPU's PACA over and switch to
* it. Also poison per_cpu_offset and NULL lppaca to catch anyone using
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 21c1e11a06de..d3c8af4c3a61 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1634,7 +1634,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
struct thread_info *ti = task_thread_info(p);
- klp_init_thread_info(ti);
+ klp_init_thread_info(p);
/* Copy registers */
sp -= sizeof(struct pt_regs);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index ca00fbb97cf8..3d0dab1647fe 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -938,7 +938,7 @@ void __init setup_arch(char **cmdline_p)
/* Reserve large chunks of memory for use by CMA for KVM. */
kvm_cma_reserve();
- klp_init_thread_info(&init_thread_info);
+ klp_init_thread_info(&init_task);
init_mm.start_code = (unsigned long)_stext;
init_mm.end_code = (unsigned long) _etext;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 080dd515d587..0912948a8ea6 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -689,24 +689,6 @@ void __init exc_lvl_early_init(void)
}
#endif
-/*
- * Emergency stacks are used for a range of things, from asynchronous
- * NMIs (system reset, machine check) to synchronous, process context.
- * We set preempt_count to zero, even though that isn't necessarily correct. To
- * get the right value we'd need to copy it from the previous thread_info, but
- * doing that might fault causing more problems.
- * TODO: what to do with accounting?
- */
-static void emerg_stack_init_thread_info(struct thread_info *ti, int cpu)
-{
- ti->task = NULL;
- ti->cpu = cpu;
- ti->preempt_count = 0;
- ti->local_flags = 0;
- ti->flags = 0;
- klp_init_thread_info(ti);
-}
-
/*
* Stack space used when we detect a bad kernel stack pointer, and
* early in SMP boots before relocation is enabled. Exclusive emergency
@@ -737,18 +719,15 @@ void __init emergency_stack_init(void)
struct thread_info *ti;
ti = alloc_stack(limit, i);
- emerg_stack_init_thread_info(ti, i);
paca_ptrs[i]->emergency_sp = (void *)ti + THREAD_SIZE;
#ifdef CONFIG_PPC_BOOK3S_64
/* emergency stack for NMI exception handling. */
ti = alloc_stack(limit, i);
- emerg_stack_init_thread_info(ti, i);
paca_ptrs[i]->nmi_emergency_sp = (void *)ti + THREAD_SIZE;
/* emergency stack for machine check exception handling. */
ti = alloc_stack(limit, i);
- emerg_stack_init_thread_info(ti, i);
paca_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE;
#endif
}
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 1d3e7cb6704d..aa4517686f90 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1021,7 +1021,7 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) +
THREAD_SIZE - STACK_FRAME_OVERHEAD;
#endif
- ti->cpu = cpu;
+ idle->cpu = cpu;
secondary_ti = current_set[cpu] = ti;
}
diff --git a/arch/powerpc/net/bpf_jit32.h b/arch/powerpc/net/bpf_jit32.h
index 6f4daacad296..dc50a8d4b3b9 100644
--- a/arch/powerpc/net/bpf_jit32.h
+++ b/arch/powerpc/net/bpf_jit32.h
@@ -106,9 +106,8 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
} while (0)
#else
#define PPC_BPF_LOAD_CPU(r) \
- do { BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, cpu) != 4); \
- PPC_LHZ_OFFS(r, (1 & ~(THREAD_SIZE - 1)), \
- offsetof(struct thread_info, cpu)); \
+ do { BUILD_BUG_ON(FIELD_SIZEOF(struct task_struct, cpu) != 4); \
+ PPC_LHZ_OFFS(r, 2, offsetof(struct task_struct, cpu)); \
} while(0)
#endif
#else
--
2.20.1
^ permalink raw reply related
* [PATCH v16 17/21] powerpc: regain entire stack space
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
thread_info is not anymore in the stack, so the entire stack
can now be used.
There is also no risk anymore of corrupting task_cpu(p) with a
stack overflow so the patch removes the test.
When doing this, an explicit test for NULL stack pointer is
needed in validate_sp() as it is not anymore implicitely covered
by the sizeof(thread_info) gap.
In the meantime, with the previous patch all pointers to the stacks
are not anymore pointers to thread_info so this patch changes them
to void*
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/irq.h | 10 ++++-----
arch/powerpc/include/asm/processor.h | 3 +--
arch/powerpc/kernel/asm-offsets.c | 1 -
arch/powerpc/kernel/entry_32.S | 14 ++++--------
arch/powerpc/kernel/irq.c | 19 ++++++++---------
arch/powerpc/kernel/misc_32.S | 6 ++----
arch/powerpc/kernel/process.c | 32 +++++++++++-----------------
arch/powerpc/kernel/setup_64.c | 8 +++----
8 files changed, 38 insertions(+), 55 deletions(-)
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 28a7ace0a1b9..c91a60cda4fa 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -48,16 +48,16 @@ struct pt_regs;
* Per-cpu stacks for handling critical, debug and machine check
* level interrupts.
*/
-extern struct thread_info *critirq_ctx[NR_CPUS];
-extern struct thread_info *dbgirq_ctx[NR_CPUS];
-extern struct thread_info *mcheckirq_ctx[NR_CPUS];
+extern void *critirq_ctx[NR_CPUS];
+extern void *dbgirq_ctx[NR_CPUS];
+extern void *mcheckirq_ctx[NR_CPUS];
#endif
/*
* Per-cpu stacks for handling hard and soft interrupts.
*/
-extern struct thread_info *hardirq_ctx[NR_CPUS];
-extern struct thread_info *softirq_ctx[NR_CPUS];
+extern void *hardirq_ctx[NR_CPUS];
+extern void *softirq_ctx[NR_CPUS];
void call_do_softirq(void *sp);
void call_do_irq(struct pt_regs *regs, void *sp);
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 9226fb83a82e..ba2f0bc680e4 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -267,8 +267,7 @@ struct thread_struct {
#define ARCH_MIN_TASKALIGN 16
#define INIT_SP (sizeof(init_stack) + (unsigned long) &init_stack)
-#define INIT_SP_LIMIT \
- (_ALIGN_UP(sizeof(struct thread_info), 16) + (unsigned long)&init_stack)
+#define INIT_SP_LIMIT ((unsigned long)&init_stack)
#ifdef CONFIG_SPE
#define SPEFSCR_INIT \
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 1fb52206c106..94ac190a0b16 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -92,7 +92,6 @@ int main(void)
DEFINE(SIGSEGV, SIGSEGV);
DEFINE(NMI_MASK, NMI_MASK);
#else
- DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
OFFSET(KSP_LIMIT, thread_struct, ksp_limit);
#endif /* CONFIG_PPC64 */
OFFSET(TASK_STACK, task_struct, stack);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 3255c0840beb..aea22c7b891f 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -97,14 +97,11 @@
mfspr r0,SPRN_SRR1
stw r0,_SRR1(r11)
- /* set the stack limit to the current stack
- * and set the limit to protect the thread_info
- * struct
- */
+ /* set the stack limit to the current stack */
mfspr r8,SPRN_SPRG_THREAD
lwz r0,KSP_LIMIT(r8)
stw r0,SAVED_KSP_LIMIT(r11)
- rlwimi r0,r1,0,0,(31-THREAD_SHIFT)
+ rlwinm r0,r1,0,0,(31 - THREAD_SHIFT)
stw r0,KSP_LIMIT(r8)
/* fall through */
#endif
@@ -121,14 +118,11 @@
mfspr r0,SPRN_SRR1
stw r0,crit_srr1@l(0)
- /* set the stack limit to the current stack
- * and set the limit to protect the thread_info
- * struct
- */
+ /* set the stack limit to the current stack */
mfspr r8,SPRN_SPRG_THREAD
lwz r0,KSP_LIMIT(r8)
stw r0,saved_ksp_limit@l(0)
- rlwimi r0,r1,0,0,(31-THREAD_SHIFT)
+ rlwinm r0,r1,0,0,(31 - THREAD_SHIFT)
stw r0,KSP_LIMIT(r8)
/* fall through */
#endif
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 85c48911938a..938944c6e2ee 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -618,9 +618,8 @@ static inline void check_stack_overflow(void)
sp = current_stack_pointer() & (THREAD_SIZE-1);
/* check for stack overflow: is there less than 2KB free? */
- if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
- pr_err("do_IRQ: stack overflow: %ld\n",
- sp - sizeof(struct thread_info));
+ if (unlikely(sp < 2048)) {
+ pr_err("do_IRQ: stack overflow: %ld\n", sp);
dump_stack();
}
#endif
@@ -660,7 +659,7 @@ void __do_irq(struct pt_regs *regs)
void do_IRQ(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
- struct thread_info *curtp, *irqtp, *sirqtp;
+ void *curtp, *irqtp, *sirqtp;
/* Switch to the irq stack to handle this */
curtp = (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
@@ -686,17 +685,17 @@ void __init init_IRQ(void)
}
#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
-struct thread_info *critirq_ctx[NR_CPUS] __read_mostly;
-struct thread_info *dbgirq_ctx[NR_CPUS] __read_mostly;
-struct thread_info *mcheckirq_ctx[NR_CPUS] __read_mostly;
+void *critirq_ctx[NR_CPUS] __read_mostly;
+void *dbgirq_ctx[NR_CPUS] __read_mostly;
+void *mcheckirq_ctx[NR_CPUS] __read_mostly;
#endif
-struct thread_info *softirq_ctx[NR_CPUS] __read_mostly;
-struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly;
+void *softirq_ctx[NR_CPUS] __read_mostly;
+void *hardirq_ctx[NR_CPUS] __read_mostly;
void do_softirq_own_stack(void)
{
- struct thread_info *irqtp;
+ void *irqtp;
irqtp = softirq_ctx[smp_processor_id()];
call_do_softirq(irqtp);
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index b37b50fde828..6f6127c3760c 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -46,11 +46,10 @@ _GLOBAL(call_do_softirq)
mflr r0
stw r0,4(r1)
lwz r10,THREAD+KSP_LIMIT(r2)
- addi r11,r3,THREAD_INFO_GAP
+ stw r3, THREAD+KSP_LIMIT(r2)
stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
mr r1,r3
stw r10,8(r1)
- stw r11,THREAD+KSP_LIMIT(r2)
bl __do_softirq
lwz r10,8(r1)
lwz r1,0(r1)
@@ -66,11 +65,10 @@ _GLOBAL(call_do_irq)
mflr r0
stw r0,4(r1)
lwz r10,THREAD+KSP_LIMIT(r2)
- addi r11,r4,THREAD_INFO_GAP
+ stw r4, THREAD+KSP_LIMIT(r2)
stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
mr r1,r4
stw r10,8(r1)
- stw r11,THREAD+KSP_LIMIT(r2)
bl __do_irq
lwz r10,8(r1)
lwz r1,0(r1)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index d3c8af4c3a61..da82ab5dd743 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1691,8 +1691,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
sp -= STACK_FRAME_OVERHEAD;
p->thread.ksp = sp;
#ifdef CONFIG_PPC32
- p->thread.ksp_limit = (unsigned long)task_stack_page(p) +
- _ALIGN_UP(sizeof(struct thread_info), 16);
+ p->thread.ksp_limit = (unsigned long)end_of_stack(p);
#endif
#ifdef CONFIG_HAVE_HW_BREAKPOINT
p->thread.ptrace_bps[0] = NULL;
@@ -1995,21 +1994,14 @@ static inline int valid_irq_stack(unsigned long sp, struct task_struct *p,
unsigned long stack_page;
unsigned long cpu = task_cpu(p);
- /*
- * Avoid crashing if the stack has overflowed and corrupted
- * task_cpu(p), which is in the thread_info struct.
- */
- if (cpu < NR_CPUS && cpu_possible(cpu)) {
- stack_page = (unsigned long) hardirq_ctx[cpu];
- if (sp >= stack_page + sizeof(struct thread_struct)
- && sp <= stack_page + THREAD_SIZE - nbytes)
- return 1;
-
- stack_page = (unsigned long) softirq_ctx[cpu];
- if (sp >= stack_page + sizeof(struct thread_struct)
- && sp <= stack_page + THREAD_SIZE - nbytes)
- return 1;
- }
+ stack_page = (unsigned long)hardirq_ctx[cpu];
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
+ stack_page = (unsigned long)softirq_ctx[cpu];
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
return 0;
}
@@ -2018,8 +2010,10 @@ int validate_sp(unsigned long sp, struct task_struct *p,
{
unsigned long stack_page = (unsigned long)task_stack_page(p);
- if (sp >= stack_page + sizeof(struct thread_struct)
- && sp <= stack_page + THREAD_SIZE - nbytes)
+ if (sp < THREAD_SIZE)
+ return 0;
+
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
return 1;
return valid_irq_stack(sp, p, nbytes);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 0912948a8ea6..2db1c5f7d141 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -716,19 +716,19 @@ void __init emergency_stack_init(void)
limit = min(ppc64_bolted_size(), ppc64_rma_size);
for_each_possible_cpu(i) {
- struct thread_info *ti;
+ void *ti;
ti = alloc_stack(limit, i);
- paca_ptrs[i]->emergency_sp = (void *)ti + THREAD_SIZE;
+ paca_ptrs[i]->emergency_sp = ti + THREAD_SIZE;
#ifdef CONFIG_PPC_BOOK3S_64
/* emergency stack for NMI exception handling. */
ti = alloc_stack(limit, i);
- paca_ptrs[i]->nmi_emergency_sp = (void *)ti + THREAD_SIZE;
+ paca_ptrs[i]->nmi_emergency_sp = ti + THREAD_SIZE;
/* emergency stack for machine check exception handling. */
ti = alloc_stack(limit, i);
- paca_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE;
+ paca_ptrs[i]->mc_emergency_sp = ti + THREAD_SIZE;
#endif
}
}
--
2.20.1
^ permalink raw reply related
* [PATCH v16 18/21] powerpc: 'current_set' is now a table of task_struct pointers
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
The table of pointers 'current_set' has been used for retrieving
the stack and current. They used to be thread_info pointers as
they were pointing to the stack and current was taken from the
'task' field of the thread_info.
Now, the pointers of 'current_set' table are now both pointers
to task_struct and pointers to thread_info.
As they are used to get current, and the stack pointer is
retrieved from current's stack field, this patch changes
their type to task_struct, and renames secondary_ti to
secondary_current.
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/asm-prototypes.h | 4 ++--
arch/powerpc/kernel/head_32.S | 6 +++---
arch/powerpc/kernel/head_44x.S | 4 ++--
arch/powerpc/kernel/head_fsl_booke.S | 4 ++--
arch/powerpc/kernel/smp.c | 10 ++++------
5 files changed, 13 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 1d911f68a23b..1484df6779ab 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -23,8 +23,8 @@
#include <uapi/asm/ucontext.h>
/* SMP */
-extern struct thread_info *current_set[NR_CPUS];
-extern struct thread_info *secondary_ti;
+extern struct task_struct *current_set[NR_CPUS];
+extern struct task_struct *secondary_current;
void start_secondary(void *unused);
/* kexec */
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 309a45779ad5..146385b1c2da 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -846,9 +846,9 @@ _ENTRY(copy_and_flush)
#endif /* CONFIG_PPC_BOOK3S_32 */
/* get current's stack and current */
- lis r1,secondary_ti@ha
- tophys(r1,r1)
- lwz r2,secondary_ti@l(r1)
+ lis r2,secondary_current@ha
+ tophys(r2,r2)
+ lwz r2,secondary_current@l(r2)
tophys(r1,r2)
lwz r1,TASK_STACK(r1)
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index f94a93b6c2f2..37117ab11584 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -1020,8 +1020,8 @@ _GLOBAL(start_secondary_47x)
/* Now we can get our task struct and real stack pointer */
/* Get current's stack and current */
- lis r1,secondary_ti@ha
- lwz r2,secondary_ti@l(r1)
+ lis r2,secondary_current@ha
+ lwz r2,secondary_current@l(r2)
lwz r1,TASK_STACK(r2)
/* Current stack pointer */
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 11f38adbe020..4ed2a7c8e89b 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -1091,8 +1091,8 @@ _GLOBAL(set_context)
bl call_setup_cpu
/* get current's stack and current */
- lis r1,secondary_ti@ha
- lwz r2,secondary_ti@l(r1)
+ lis r2,secondary_current@ha
+ lwz r2,secondary_current@l(r2)
lwz r1,TASK_STACK(r2)
/* stack */
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index aa4517686f90..a41fa8924004 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -76,7 +76,7 @@
static DEFINE_PER_CPU(int, cpu_state) = { 0 };
#endif
-struct thread_info *secondary_ti;
+struct task_struct *secondary_current;
bool has_big_cores;
DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
@@ -664,7 +664,7 @@ void smp_send_stop(void)
}
#endif /* CONFIG_NMI_IPI */
-struct thread_info *current_set[NR_CPUS];
+struct task_struct *current_set[NR_CPUS];
static void smp_store_cpu_info(int id)
{
@@ -929,7 +929,7 @@ void smp_prepare_boot_cpu(void)
paca_ptrs[boot_cpuid]->__current = current;
#endif
set_numa_node(numa_cpu_lookup_table[boot_cpuid]);
- current_set[boot_cpuid] = task_thread_info(current);
+ current_set[boot_cpuid] = current;
}
#ifdef CONFIG_HOTPLUG_CPU
@@ -1014,15 +1014,13 @@ static bool secondaries_inhibited(void)
static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
{
- struct thread_info *ti = task_thread_info(idle);
-
#ifdef CONFIG_PPC64
paca_ptrs[cpu]->__current = idle;
paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) +
THREAD_SIZE - STACK_FRAME_OVERHEAD;
#endif
idle->cpu = cpu;
- secondary_ti = current_set[cpu] = ti;
+ secondary_current = current_set[cpu] = idle;
}
int __cpu_up(unsigned int cpu, struct task_struct *tidle)
--
2.20.1
^ permalink raw reply related
* [PATCH v16 19/21] powerpc/32: Remove CURRENT_THREAD_INFO and rename TI_CPU
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
Now that thread_info is similar to task_struct, its address is in r2
so CURRENT_THREAD_INFO() macro is useless. This patch removes it.
This patch also moves the 'tovirt(r2, r2)' down just before the
reactivation of MMU translation, so that we keep the physical address
of 'current' in r2 until then. It avoids a few calls to tophys().
At the same time, as the 'cpu' field is not anymore in thread_info,
TI_CPU is renamed TASK_CPU by this patch.
It also allows to get rid of a couple of
'#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE' as ACCOUNT_CPU_USER_ENTRY()
and ACCOUNT_CPU_USER_EXIT() are empty when
CONFIG_VIRT_CPU_ACCOUNTING_NATIVE is not defined.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/Makefile | 2 +-
arch/powerpc/include/asm/thread_info.h | 2 -
arch/powerpc/kernel/asm-offsets.c | 2 +-
arch/powerpc/kernel/entry_32.S | 55 +++++++++-----------------
arch/powerpc/kernel/epapr_hcalls.S | 5 +--
arch/powerpc/kernel/head_fsl_booke.S | 5 +--
arch/powerpc/kernel/idle_6xx.S | 9 ++---
arch/powerpc/kernel/idle_e500.S | 8 ++--
arch/powerpc/kernel/misc_32.S | 3 +-
arch/powerpc/mm/hash_low_32.S | 14 +++----
arch/powerpc/sysdev/6xx-suspend.S | 5 +--
11 files changed, 38 insertions(+), 72 deletions(-)
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 53ffe935f3b0..7de49889bd5d 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -431,7 +431,7 @@ ifdef CONFIG_SMP
prepare: task_cpu_prepare
task_cpu_prepare: prepare0
- $(eval KBUILD_CFLAGS += -D_TASK_CPU=$(shell awk '{if ($$2 == "TI_CPU") print $$3;}' include/generated/asm-offsets.h))
+ $(eval KBUILD_CFLAGS += -D_TASK_CPU=$(shell awk '{if ($$2 == "TASK_CPU") print $$3;}' include/generated/asm-offsets.h))
endif
# Check toolchain versions:
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index d91523c2c7d8..c959b8d66cac 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -19,8 +19,6 @@
#ifdef CONFIG_PPC64
#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(ld dest, PACACURRENT(r13))
-#else
-#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(mr dest, r2)
#endif
#ifndef __ASSEMBLY__
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 94ac190a0b16..03439785c2ea 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -96,7 +96,7 @@ int main(void)
#endif /* CONFIG_PPC64 */
OFFSET(TASK_STACK, task_struct, stack);
#ifdef CONFIG_SMP
- OFFSET(TI_CPU, task_struct, cpu);
+ OFFSET(TASK_CPU, task_struct, cpu);
#endif
#ifdef CONFIG_LIVEPATCH
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index aea22c7b891f..a5e2d5585dcb 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -151,7 +151,6 @@
stw r2,_XER(r11)
mfspr r12,SPRN_SPRG_THREAD
addi r2,r12,-THREAD
- tovirt(r2,r2) /* set r2 to current */
beq 2f /* if from user, fix up THREAD.regs */
addi r11,r1,STACK_FRAME_OVERHEAD
stw r11,PT_REGS(r12)
@@ -161,11 +160,7 @@
lwz r12,THREAD_DBCR0(r12)
andis. r12,r12,DBCR0_IDM@h
#endif
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
- CURRENT_THREAD_INFO(r9, r1)
- tophys(r9, r9)
- ACCOUNT_CPU_USER_ENTRY(r9, r11, r12)
-#endif
+ ACCOUNT_CPU_USER_ENTRY(r2, r11, r12)
#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
beq+ 3f
/* From user and task is ptraced - load up global dbcr0 */
@@ -175,8 +170,7 @@
tophys(r11,r11)
addi r11,r11,global_dbcr0@l
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r9, r1)
- lwz r9,TI_CPU(r9)
+ lwz r9,TASK_CPU(r2)
slwi r9,r9,3
add r11,r11,r9
#endif
@@ -197,9 +191,7 @@
ble- stack_ovf /* then the kernel stack overflowed */
5:
#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500)
- CURRENT_THREAD_INFO(r9, r1)
- tophys(r9,r9) /* check local flags */
- lwz r12,TI_LOCAL_FLAGS(r9)
+ lwz r12,TI_LOCAL_FLAGS(r2)
mtcrf 0x01,r12
bt- 31-TLF_NAPPING,4f
bt- 31-TLF_SLEEPING,7f
@@ -208,6 +200,7 @@
transfer_to_handler_cont:
3:
mflr r9
+ tovirt(r2, r2) /* set r2 to current */
lwz r11,0(r9) /* virtual address of handler */
lwz r9,4(r9) /* where to go when done */
#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
@@ -271,11 +264,11 @@ reenable_mmu: /* re-enable mmu so we can */
#if defined (CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500)
4: rlwinm r12,r12,0,~_TLF_NAPPING
- stw r12,TI_LOCAL_FLAGS(r9)
+ stw r12,TI_LOCAL_FLAGS(r2)
b power_save_ppc32_restore
7: rlwinm r12,r12,0,~_TLF_SLEEPING
- stw r12,TI_LOCAL_FLAGS(r9)
+ stw r12,TI_LOCAL_FLAGS(r2)
lwz r9,_MSR(r11) /* if sleeping, clear MSR.EE */
rlwinm r9,r9,0,~MSR_EE
lwz r12,_LINK(r11) /* and return to address in LR */
@@ -347,8 +340,7 @@ _GLOBAL(DoSyscall)
mtmsr r11
1:
#endif /* CONFIG_TRACE_IRQFLAGS */
- CURRENT_THREAD_INFO(r10, r1)
- lwz r11,TI_FLAGS(r10)
+ lwz r11,TI_FLAGS(r2)
andi. r11,r11,_TIF_SYSCALL_DOTRACE
bne- syscall_dotrace
syscall_dotrace_cont:
@@ -381,13 +373,12 @@ _GLOBAL(DoSyscall)
lwz r3,GPR3(r1)
#endif
mr r6,r3
- CURRENT_THREAD_INFO(r12, r1)
/* disable interrupts so current_thread_info()->flags can't change */
LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */
/* Note: We don't bother telling lockdep about it */
SYNC
MTMSRD(r10)
- lwz r9,TI_FLAGS(r12)
+ 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
@@ -434,8 +425,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
andi. r4,r8,MSR_PR
beq 3f
- CURRENT_THREAD_INFO(r4, r1)
- ACCOUNT_CPU_USER_EXIT(r4, r5, r7)
+ ACCOUNT_CPU_USER_EXIT(r2, r5, r7)
3:
#endif
lwz r4,_LINK(r1)
@@ -528,7 +518,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
/* Clear per-syscall TIF flags if any are set. */
li r11,_TIF_PERSYSCALL_MASK
- addi r12,r12,TI_FLAGS
+ addi r12,r2,TI_FLAGS
3: lwarx r8,0,r12
andc r8,r8,r11
#ifdef CONFIG_IBM405_ERR77
@@ -536,7 +526,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
#endif
stwcx. r8,0,r12
bne- 3b
- subi r12,r12,TI_FLAGS
4: /* Anything which requires enabling interrupts? */
andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
@@ -815,8 +804,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_601)
user_exc_return: /* r10 contains MSR_KERNEL here */
/* Check current_thread_info()->flags */
- CURRENT_THREAD_INFO(r9, r1)
- lwz r9,TI_FLAGS(r9)
+ lwz r9,TI_FLAGS(r2)
andi. r0,r9,_TIF_USER_WORK_MASK
bne do_work
@@ -828,18 +816,14 @@ user_exc_return: /* r10 contains MSR_KERNEL here */
andis. r10,r0,DBCR0_IDM@h
bnel- load_dbcr0
#endif
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
- CURRENT_THREAD_INFO(r9, r1)
- ACCOUNT_CPU_USER_EXIT(r9, r10, r11)
-#endif
+ ACCOUNT_CPU_USER_EXIT(r2, r10, r11)
b restore
/* N.B. the only way to get here is from the beq following ret_from_except. */
resume_kernel:
/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
- CURRENT_THREAD_INFO(r9, r1)
- lwz r8,TI_FLAGS(r9)
+ lwz r8,TI_FLAGS(r2)
andis. r0,r8,_TIF_EMULATE_STACK_STORE@h
beq+ 1f
@@ -865,7 +849,7 @@ user_exc_return: /* r10 contains MSR_KERNEL here */
/* Clear _TIF_EMULATE_STACK_STORE flag */
lis r11,_TIF_EMULATE_STACK_STORE@h
- addi r5,r9,TI_FLAGS
+ addi r5,r2,TI_FLAGS
0: lwarx r8,0,r5
andc r8,r8,r11
#ifdef CONFIG_IBM405_ERR77
@@ -877,7 +861,7 @@ user_exc_return: /* r10 contains MSR_KERNEL here */
#ifdef CONFIG_PREEMPT
/* check current_thread_info->preempt_count */
- lwz r0,TI_PREEMPT(r9)
+ lwz r0,TI_PREEMPT(r2)
cmpwi 0,r0,0 /* if non-zero, just restore regs and return */
bne restore
andi. r8,r8,_TIF_NEED_RESCHED
@@ -893,8 +877,7 @@ user_exc_return: /* r10 contains MSR_KERNEL here */
bl trace_hardirqs_off
#endif
1: bl preempt_schedule_irq
- CURRENT_THREAD_INFO(r9, r1)
- lwz r3,TI_FLAGS(r9)
+ lwz r3,TI_FLAGS(r2)
andi. r0,r3,_TIF_NEED_RESCHED
bne- 1b
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -1193,8 +1176,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
lis r11,global_dbcr0@ha
addi r11,r11,global_dbcr0@l
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r9, r1)
- lwz r9,TI_CPU(r9)
+ lwz r9,TASK_CPU(r2)
slwi r9,r9,3
add r11,r11,r9
#endif
@@ -1234,8 +1216,7 @@ do_resched: /* r10 contains MSR_KERNEL here */
LOAD_MSR_KERNEL(r10,MSR_KERNEL)
SYNC
MTMSRD(r10) /* disable interrupts */
- CURRENT_THREAD_INFO(r9, r1)
- lwz r9,TI_FLAGS(r9)
+ lwz r9,TI_FLAGS(r2)
andi. r0,r9,_TIF_NEED_RESCHED
bne- do_resched
andi. r0,r9,_TIF_USER_WORK_MASK
diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S
index 52ca2471ee1a..d252f4663a23 100644
--- a/arch/powerpc/kernel/epapr_hcalls.S
+++ b/arch/powerpc/kernel/epapr_hcalls.S
@@ -21,10 +21,9 @@
#ifndef CONFIG_PPC64
/* epapr_ev_idle() was derived from e500_idle() */
_GLOBAL(epapr_ev_idle)
- CURRENT_THREAD_INFO(r3, r1)
- PPC_LL r4, TI_LOCAL_FLAGS(r3) /* set napping bit */
+ PPC_LL r4, TI_LOCAL_FLAGS(r2) /* set napping bit */
ori r4, r4,_TLF_NAPPING /* so when we take an exception */
- PPC_STL r4, TI_LOCAL_FLAGS(r3) /* it will return to our caller */
+ PPC_STL r4, TI_LOCAL_FLAGS(r2) /* it will return to our caller */
wrteei 1
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 4ed2a7c8e89b..1881127682e9 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -244,8 +244,7 @@ _ENTRY(__early_start)
stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r22, r1)
- stw r24, TI_CPU(r22)
+ stw r24, TASK_CPU(r2)
#endif
bl early_init
@@ -719,7 +718,7 @@ END_BTB_FLUSH_SECTION
/* Get the next_tlbcam_idx percpu var */
#ifdef CONFIG_SMP
- lwz r15, TI_CPU-THREAD(r12)
+ lwz r15, TASK_CPU-THREAD(r12)
lis r14, __per_cpu_offset@h
ori r14, r14, __per_cpu_offset@l
rlwinm r15, r15, 2, 0, 29
diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S
index d9b6e7e0b5e3..5e69fefcd9c4 100644
--- a/arch/powerpc/kernel/idle_6xx.S
+++ b/arch/powerpc/kernel/idle_6xx.S
@@ -136,10 +136,9 @@ BEGIN_FTR_SECTION
DSSALL
sync
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
- CURRENT_THREAD_INFO(r9, r1)
- lwz r8,TI_LOCAL_FLAGS(r9) /* set napping bit */
+ lwz r8,TI_LOCAL_FLAGS(r2) /* set napping bit */
ori r8,r8,_TLF_NAPPING /* so when we take an exception */
- stw r8,TI_LOCAL_FLAGS(r9) /* it will return to our caller */
+ stw r8,TI_LOCAL_FLAGS(r2) /* it will return to our caller */
mfmsr r7
ori r7,r7,MSR_EE
oris r7,r7,MSR_POW@h
@@ -159,9 +158,7 @@ _GLOBAL(power_save_ppc32_restore)
stw r9,_NIP(r11) /* make it do a blr */
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r12, r1)
- tophys(r12, r12)
- lwz r11,TI_CPU(r12) /* get cpu number * 4 */
+ lwz r11,TI_CPU(r2) /* get cpu number * 4 */
slwi r11,r11,2
#else
li r11,0
diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_e500.S
index 583e55ac7d26..69dfcd2ca011 100644
--- a/arch/powerpc/kernel/idle_e500.S
+++ b/arch/powerpc/kernel/idle_e500.S
@@ -22,10 +22,9 @@
.text
_GLOBAL(e500_idle)
- CURRENT_THREAD_INFO(r3, r1)
- lwz r4,TI_LOCAL_FLAGS(r3) /* set napping bit */
+ lwz r4,TI_LOCAL_FLAGS(r2) /* set napping bit */
ori r4,r4,_TLF_NAPPING /* so when we take an exception */
- stw r4,TI_LOCAL_FLAGS(r3) /* it will return to our caller */
+ stw r4,TI_LOCAL_FLAGS(r2) /* it will return to our caller */
#ifdef CONFIG_PPC_E500MC
wrteei 1
@@ -88,8 +87,7 @@ _GLOBAL(power_save_ppc32_restore)
stw r9,_NIP(r11) /* make it do a blr */
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r12, r1)
- lwz r11,TI_CPU(r12) /* get cpu number * 4 */
+ lwz r11,TASK_CPU(r2) /* get cpu number * 4 */
slwi r11,r11,2
#else
li r11,0
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 6f6127c3760c..0dda4f8e3d7a 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -183,8 +183,7 @@ _GLOBAL(low_choose_750fx_pll)
#ifdef CONFIG_SMP
/* Store new HID1 image */
- CURRENT_THREAD_INFO(r6, r1)
- lwz r6,TI_CPU(r6)
+ lwz r6,TASK_CPU(r2)
slwi r6,r6,2
#else
li r6, 0
diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S
index 1e2df3e9f9ea..5bee2d982959 100644
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/hash_low_32.S
@@ -186,8 +186,7 @@ _GLOBAL(add_hash_page)
add r3,r3,r0 /* note create_hpte trims to 24 bits */
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r8, r1) /* use cpu number to make tag */
- lwz r8,TI_CPU(r8) /* to go in mmu_hash_lock */
+ lwz r8,TASK_CPU(r2) /* to go in mmu_hash_lock */
oris r8,r8,12
#endif /* CONFIG_SMP */
@@ -549,9 +548,8 @@ _GLOBAL(flush_hash_pages)
#ifdef CONFIG_SMP
addis r9,r7,mmu_hash_lock@ha
addi r9,r9,mmu_hash_lock@l
- CURRENT_THREAD_INFO(r8, r1)
- add r8,r8,r7
- lwz r8,TI_CPU(r8)
+ add r8,r2,r7
+ lwz r8,TASK_CPU(r8)
oris r8,r8,9
10: lwarx r0,0,r9
cmpi 0,r0,0
@@ -646,8 +644,7 @@ EXPORT_SYMBOL(flush_hash_pages)
*/
_GLOBAL(_tlbie)
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r8, r1)
- lwz r8,TI_CPU(r8)
+ lwz r8,TASK_CPU(r2)
oris r8,r8,11
mfmsr r10
SYNC
@@ -684,8 +681,7 @@ _GLOBAL(_tlbie)
*/
_GLOBAL(_tlbia)
#if defined(CONFIG_SMP)
- CURRENT_THREAD_INFO(r8, r1)
- lwz r8,TI_CPU(r8)
+ lwz r8,TASK_CPU(r2)
oris r8,r8,10
mfmsr r10
SYNC
diff --git a/arch/powerpc/sysdev/6xx-suspend.S b/arch/powerpc/sysdev/6xx-suspend.S
index cf48e9cb2575..6c4aec25c4ba 100644
--- a/arch/powerpc/sysdev/6xx-suspend.S
+++ b/arch/powerpc/sysdev/6xx-suspend.S
@@ -29,10 +29,9 @@ _GLOBAL(mpc6xx_enter_standby)
ori r5, r5, ret_from_standby@l
mtlr r5
- CURRENT_THREAD_INFO(r5, r1)
- lwz r6, TI_LOCAL_FLAGS(r5)
+ lwz r6, TI_LOCAL_FLAGS(r2)
ori r6, r6, _TLF_SLEEPING
- stw r6, TI_LOCAL_FLAGS(r5)
+ stw r6, TI_LOCAL_FLAGS(r2)
mfmsr r5
ori r5, r5, MSR_EE
--
2.20.1
^ permalink raw reply related
* [PATCH v16 20/21] powerpc/64: Replace CURRENT_THREAD_INFO with PACA_CURRENT_TI
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
Now that current_thread_info is located at the beginning of 'current'
task struct, CURRENT_THREAD_INFO macro is not really needed any more.
This patch replaces it by loads of the value at PACA_CURRENT_TI(r13).
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
[mpe: Add PACA_CURRENT_TI rather than using PACACURRENT]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/exception-64s.h | 4 ++--
arch/powerpc/include/asm/thread_info.h | 4 ----
arch/powerpc/kernel/asm-offsets.c | 2 ++
arch/powerpc/kernel/entry_64.S | 10 +++++-----
arch/powerpc/kernel/exceptions-64e.S | 2 +-
arch/powerpc/kernel/exceptions-64s.S | 2 +-
arch/powerpc/kernel/idle_book3e.S | 2 +-
arch/powerpc/kernel/idle_power4.S | 2 +-
arch/powerpc/kernel/trace/ftrace_64_mprofile.S | 6 +++---
9 files changed, 16 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 3b4767ed3ec5..f0f0ff192e87 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -671,7 +671,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
#define RUNLATCH_ON \
BEGIN_FTR_SECTION \
- CURRENT_THREAD_INFO(r3, r1); \
+ ld r3, PACA_CURRENT_TI(r13); \
ld r4,TI_LOCAL_FLAGS(r3); \
andi. r0,r4,_TLF_RUNLATCH; \
beql ppc64_runlatch_on_trampoline; \
@@ -721,7 +721,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CTRL)
#ifdef CONFIG_PPC_970_NAP
#define FINISH_NAP \
BEGIN_FTR_SECTION \
- CURRENT_THREAD_INFO(r11, r1); \
+ ld r11, PACA_CURRENT_TI(r13); \
ld r9,TI_LOCAL_FLAGS(r11); \
andi. r10,r9,_TLF_NAPPING; \
bnel power4_fixup_nap; \
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index c959b8d66cac..8e1d0195ac36 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -17,10 +17,6 @@
#define THREAD_SIZE (1 << THREAD_SHIFT)
-#ifdef CONFIG_PPC64
-#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(ld dest, PACACURRENT(r13))
-#endif
-
#ifndef __ASSEMBLY__
#include <linux/cache.h>
#include <asm/processor.h>
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 03439785c2ea..7a1b93c5af63 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -179,6 +179,8 @@ int main(void)
OFFSET(PACAPROCSTART, paca_struct, cpu_start);
OFFSET(PACAKSAVE, paca_struct, kstack);
OFFSET(PACACURRENT, paca_struct, __current);
+ DEFINE(PACA_CURRENT_TI, offsetof(struct paca_struct, __current) +
+ offsetof(struct task_struct, thread_info));
OFFSET(PACASAVEDMSR, paca_struct, saved_msr);
OFFSET(PACAR1, paca_struct, saved_r1);
OFFSET(PACATOC, paca_struct, kernel_toc);
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 21f1cb4d464e..259fcc82ec75 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -166,7 +166,7 @@ system_call: /* label this so stack traces look sane */
li r10,IRQS_ENABLED
std r10,SOFTE(r1)
- CURRENT_THREAD_INFO(r11, r1)
+ ld r11, PACA_CURRENT_TI(r13)
ld r10,TI_FLAGS(r11)
andi. r11,r10,_TIF_SYSCALL_DOTRACE
bne .Lsyscall_dotrace /* does not return */
@@ -213,7 +213,7 @@ system_call: /* label this so stack traces look sane */
ld r3,RESULT(r1)
#endif
- CURRENT_THREAD_INFO(r12, r1)
+ ld r12, PACA_CURRENT_TI(r13)
ld r8,_MSR(r1)
#ifdef CONFIG_PPC_BOOK3S
@@ -346,7 +346,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
/* Repopulate r9 and r10 for the syscall path */
addi r9,r1,STACK_FRAME_OVERHEAD
- CURRENT_THREAD_INFO(r10, r1)
+ ld r10, PACA_CURRENT_TI(r13)
ld r10,TI_FLAGS(r10)
cmpldi r0,NR_syscalls
@@ -740,7 +740,7 @@ _GLOBAL(ret_from_except_lite)
mtmsrd r10,1 /* Update machine state */
#endif /* CONFIG_PPC_BOOK3E */
- CURRENT_THREAD_INFO(r9, r1)
+ ld r9, PACA_CURRENT_TI(r13)
ld r3,_MSR(r1)
#ifdef CONFIG_PPC_BOOK3E
ld r10,PACACURRENT(r13)
@@ -854,7 +854,7 @@ _GLOBAL(ret_from_except_lite)
1: bl preempt_schedule_irq
/* Re-test flags and eventually loop */
- CURRENT_THREAD_INFO(r9, r1)
+ ld r9, PACA_CURRENT_TI(r13)
ld r4,TI_FLAGS(r9)
andi. r0,r4,_TIF_NEED_RESCHED
bne 1b
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 20f14996281d..92d5ded2b290 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -493,7 +493,7 @@ exc_##n##_bad_stack: \
* interrupts happen before the wait instruction.
*/
#define CHECK_NAPPING() \
- CURRENT_THREAD_INFO(r11, r1); \
+ ld r11, PACA_CURRENT_TI(r13); \
ld r10,TI_LOCAL_FLAGS(r11); \
andi. r9,r10,_TLF_NAPPING; \
beq+ 1f; \
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 9e253ce27e08..83be18d478b8 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1629,7 +1629,7 @@ USE_TEXT_SECTION()
ori r0,r0,DSISR_BAD_FAULT_64S@l
and. r0,r4,r0 /* weird error? */
bne- handle_page_fault /* if not, try to insert a HPTE */
- CURRENT_THREAD_INFO(r11, r1)
+ ld r11, PACA_CURRENT_TI(r13)
lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */
andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */
bne 77f /* then don't call hash_page now */
diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S
index 4e0d94d02030..31e732c378ad 100644
--- a/arch/powerpc/kernel/idle_book3e.S
+++ b/arch/powerpc/kernel/idle_book3e.S
@@ -63,7 +63,7 @@ _GLOBAL(\name)
1: /* Let's set the _TLF_NAPPING flag so interrupts make us return
* to the right spot
*/
- CURRENT_THREAD_INFO(r11, r1)
+ ld r11, PACACURRENT(r13)
ld r10,TI_LOCAL_FLAGS(r11)
ori r10,r10,_TLF_NAPPING
std r10,TI_LOCAL_FLAGS(r11)
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
index a09b3c7ca176..b4c849f9f0e2 100644
--- a/arch/powerpc/kernel/idle_power4.S
+++ b/arch/powerpc/kernel/idle_power4.S
@@ -68,7 +68,7 @@ BEGIN_FTR_SECTION
DSSALL
sync
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
- CURRENT_THREAD_INFO(r9, r1)
+ ld r9, PACA_CURRENT_TI(r13)
ld r8,TI_LOCAL_FLAGS(r9) /* set napping bit */
ori r8,r8,_TLF_NAPPING /* so when we take an exception */
std r8,TI_LOCAL_FLAGS(r9) /* it will return to our caller */
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index 32476a6e4e9c..17ec02cb2f58 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -229,7 +229,7 @@ _GLOBAL(ftrace_caller)
* - r0, r11 & r12 are free
*/
livepatch_handler:
- CURRENT_THREAD_INFO(r12, r1)
+ ld r12, PACA_CURRENT_TI(r13)
/* Allocate 3 x 8 bytes */
ld r11, TI_livepatch_sp(r12)
@@ -256,7 +256,7 @@ _GLOBAL(ftrace_caller)
* restore it.
*/
- CURRENT_THREAD_INFO(r12, r1)
+ ld r12, PACA_CURRENT_TI(r13)
ld r11, TI_livepatch_sp(r12)
@@ -273,7 +273,7 @@ _GLOBAL(ftrace_caller)
ld r2, -24(r11)
/* Pop livepatch stack frame */
- CURRENT_THREAD_INFO(r12, r1)
+ ld r12, PACA_CURRENT_TI(r13)
subi r11, r11, 24
std r11, TI_livepatch_sp(r12)
--
2.20.1
^ permalink raw reply related
* [PATCH v16 21/21] powerpc: clean stack pointers naming
From: Michael Ellerman @ 2019-02-05 11:32 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190205113219.17903-1-mpe@ellerman.id.au>
From: Christophe Leroy <christophe.leroy@c-s.fr>
Some stack pointers used to also be thread_info pointers
and were called tp. Now that they are only stack pointers,
rename them sp.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/kernel/irq.c | 17 +++++++----------
arch/powerpc/kernel/setup_64.c | 11 +++--------
2 files changed, 10 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 938944c6e2ee..8a936723c791 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -659,21 +659,21 @@ void __do_irq(struct pt_regs *regs)
void do_IRQ(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
- void *curtp, *irqtp, *sirqtp;
+ void *cursp, *irqsp, *sirqsp;
/* Switch to the irq stack to handle this */
- curtp = (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
- irqtp = hardirq_ctx[raw_smp_processor_id()];
- sirqtp = softirq_ctx[raw_smp_processor_id()];
+ cursp = (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
+ irqsp = hardirq_ctx[raw_smp_processor_id()];
+ sirqsp = softirq_ctx[raw_smp_processor_id()];
/* Already there ? */
- if (unlikely(curtp == irqtp || curtp == sirqtp)) {
+ if (unlikely(cursp == irqsp || cursp == sirqsp)) {
__do_irq(regs);
set_irq_regs(old_regs);
return;
}
/* Switch stack and call */
- call_do_irq(regs, irqtp);
+ call_do_irq(regs, irqsp);
set_irq_regs(old_regs);
}
@@ -695,10 +695,7 @@ void *hardirq_ctx[NR_CPUS] __read_mostly;
void do_softirq_own_stack(void)
{
- void *irqtp;
-
- irqtp = softirq_ctx[smp_processor_id()];
- call_do_softirq(irqtp);
+ call_do_softirq(softirq_ctx[smp_processor_id()]);
}
irq_hw_number_t virq_to_hw(unsigned int virq)
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 2db1c5f7d141..daa361fc6a24 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -716,19 +716,14 @@ void __init emergency_stack_init(void)
limit = min(ppc64_bolted_size(), ppc64_rma_size);
for_each_possible_cpu(i) {
- void *ti;
-
- ti = alloc_stack(limit, i);
- paca_ptrs[i]->emergency_sp = ti + THREAD_SIZE;
+ paca_ptrs[i]->emergency_sp = alloc_stack(limit, i) + THREAD_SIZE;
#ifdef CONFIG_PPC_BOOK3S_64
/* emergency stack for NMI exception handling. */
- ti = alloc_stack(limit, i);
- paca_ptrs[i]->nmi_emergency_sp = ti + THREAD_SIZE;
+ paca_ptrs[i]->nmi_emergency_sp = alloc_stack(limit, i) + THREAD_SIZE;
/* emergency stack for machine check exception handling. */
- ti = alloc_stack(limit, i);
- paca_ptrs[i]->mc_emergency_sp = ti + THREAD_SIZE;
+ paca_ptrs[i]->mc_emergency_sp = alloc_stack(limit, i) + THREAD_SIZE;
#endif
}
}
--
2.20.1
^ permalink raw reply related
* Re: [PATCH] hugetlb: allow to free gigantic pages regardless of the configuration
From: Alex Ghiti @ 2019-02-05 11:35 UTC (permalink / raw)
To: Michael Ellerman
Cc: linux-s390, x86, Heiko Carstens, linux-mm, Catalin Marinas,
H . Peter Anvin, Will Deacon, linux-kernel, hch, linux-fsdevel,
Ingo Molnar, Paul Mackerras, Alexander Viro, Martin Schwidefsky,
Borislav Petkov, linux-riscv, linuxppc-dev, Thomas Gleixner,
linux-arm-kernel, Mike Kravetz
In-Reply-To: <87ef8mmqbc.fsf@concordia.ellerman.id.au>
On 2/5/19 6:23 AM, Michael Ellerman wrote:
> Alexandre Ghiti <aghiti@upmem.com> writes:
>
>> From: Alexandre Ghiti <alex@ghiti.fr>
>>
>> On systems without CMA or (MEMORY_ISOLATION && COMPACTION) activated but
>> that support gigantic pages, boottime reserved gigantic pages can not be
>> freed at all. This patchs simply enables the possibility to hand back
>> those pages to memory allocator.
>>
>> This commit then renames gigantic_page_supported and
>> ARCH_HAS_GIGANTIC_PAGE to make them more accurate. Indeed, those values
>> being false does not mean that the system cannot use gigantic pages: it
>> just means that runtime allocation of gigantic pages is not supported,
>> one can still allocate boottime gigantic pages if the architecture supports
>> it.
>>
>> Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
>> ---
>>
>> - Compiled on all architectures
>> - Tested on riscv architecture
>>
>> arch/arm64/Kconfig | 2 +-
>> arch/arm64/include/asm/hugetlb.h | 7 +++--
>> arch/powerpc/include/asm/book3s/64/hugetlb.h | 4 +--
>> arch/powerpc/platforms/Kconfig.cputype | 2 +-
> The powerpc parts look fine.
>
> Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Thank you Michael,
Alex
>
> cheers
>
>> arch/s390/Kconfig | 2 +-
>> arch/s390/include/asm/hugetlb.h | 7 +++--
>> arch/x86/Kconfig | 2 +-
>> arch/x86/include/asm/hugetlb.h | 7 +++--
>> fs/Kconfig | 2 +-
>> include/linux/gfp.h | 2 +-
>> mm/hugetlb.c | 43 +++++++++++++++-------------
>> mm/page_alloc.c | 4 +--
>> 12 files changed, 48 insertions(+), 36 deletions(-)
>>
>> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
>> index a4168d366127..18239cbd7fcd 100644
>> --- a/arch/arm64/Kconfig
>> +++ b/arch/arm64/Kconfig
>> @@ -18,7 +18,7 @@ config ARM64
>> select ARCH_HAS_FAST_MULTIPLIER
>> select ARCH_HAS_FORTIFY_SOURCE
>> select ARCH_HAS_GCOV_PROFILE_ALL
>> - select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
>> + select ARCH_HAS_GIGANTIC_PAGE_RUNTIME_ALLOCATION if (MEMORY_ISOLATION && COMPACTION) || CMA
>> select ARCH_HAS_KCOV
>> select ARCH_HAS_MEMBARRIER_SYNC_CORE
>> select ARCH_HAS_PTE_SPECIAL
>> diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
>> index fb6609875455..797fc77eabcd 100644
>> --- a/arch/arm64/include/asm/hugetlb.h
>> +++ b/arch/arm64/include/asm/hugetlb.h
>> @@ -65,8 +65,11 @@ extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
>>
>> #include <asm-generic/hugetlb.h>
>>
>> -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
>> -static inline bool gigantic_page_supported(void) { return true; }
>> +#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE_RUNTIME_ALLOCATION
>> +static inline bool gigantic_page_runtime_allocation_supported(void)
>> +{
>> + return true;
>> +}
>> #endif
>>
>> #endif /* __ASM_HUGETLB_H */
>> diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
>> index 5b0177733994..7711f0e2c7e5 100644
>> --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
>> +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
>> @@ -32,8 +32,8 @@ static inline int hstate_get_psize(struct hstate *hstate)
>> }
>> }
>>
>> -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
>> -static inline bool gigantic_page_supported(void)
>> +#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE_RUNTIME_ALLOCATION
>> +static inline bool gigantic_page_runtime_allocation_supported(void)
>> {
>> return true;
>> }
>> diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
>> index 8c7464c3f27f..779e06bac697 100644
>> --- a/arch/powerpc/platforms/Kconfig.cputype
>> +++ b/arch/powerpc/platforms/Kconfig.cputype
>> @@ -319,7 +319,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
>> config PPC_RADIX_MMU
>> bool "Radix MMU Support"
>> depends on PPC_BOOK3S_64
>> - select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
>> + select ARCH_HAS_GIGANTIC_PAGE_RUNTIME_ALLOCATION if (MEMORY_ISOLATION && COMPACTION) || CMA
>> default y
>> help
>> Enable support for the Power ISA 3.0 Radix style MMU. Currently this
>> diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
>> index ed554b09eb3f..6776eef6a9ae 100644
>> --- a/arch/s390/Kconfig
>> +++ b/arch/s390/Kconfig
>> @@ -69,7 +69,7 @@ config S390
>> select ARCH_HAS_ELF_RANDOMIZE
>> select ARCH_HAS_FORTIFY_SOURCE
>> select ARCH_HAS_GCOV_PROFILE_ALL
>> - select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
>> + select ARCH_HAS_GIGANTIC_PAGE_RUNTIME_ALLOCATION if (MEMORY_ISOLATION && COMPACTION) || CMA
>> select ARCH_HAS_KCOV
>> select ARCH_HAS_PTE_SPECIAL
>> select ARCH_HAS_SET_MEMORY
>> diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
>> index 2d1afa58a4b6..57c952f5388e 100644
>> --- a/arch/s390/include/asm/hugetlb.h
>> +++ b/arch/s390/include/asm/hugetlb.h
>> @@ -116,7 +116,10 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
>> return pte_modify(pte, newprot);
>> }
>>
>> -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
>> -static inline bool gigantic_page_supported(void) { return true; }
>> +#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE_RUNTIME_ALLOCATION
>> +static inline bool gigantic_page_runtime_allocation_supported(void)
>> +{
>> + return true;
>> +}
>> #endif
>> #endif /* _ASM_S390_HUGETLB_H */
>> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
>> index 6185d4f33296..a88f5a4311c9 100644
>> --- a/arch/x86/Kconfig
>> +++ b/arch/x86/Kconfig
>> @@ -23,7 +23,7 @@ config X86_64
>> def_bool y
>> depends on 64BIT
>> # Options that are inherently 64-bit kernel only:
>> - select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
>> + select ARCH_HAS_GIGANTIC_PAGE_RUNTIME_ALLOCATION if (MEMORY_ISOLATION && COMPACTION) || CMA
>> select ARCH_SUPPORTS_INT128
>> select ARCH_USE_CMPXCHG_LOCKREF
>> select HAVE_ARCH_SOFT_DIRTY
>> diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
>> index 7469d321f072..5a5e7119ced4 100644
>> --- a/arch/x86/include/asm/hugetlb.h
>> +++ b/arch/x86/include/asm/hugetlb.h
>> @@ -17,8 +17,11 @@ static inline void arch_clear_hugepage_flags(struct page *page)
>> {
>> }
>>
>> -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
>> -static inline bool gigantic_page_supported(void) { return true; }
>> +#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE_RUNTIME_ALLOCATION
>> +static inline bool gigantic_page_runtime_allocation_supported(void)
>> +{
>> + return true;
>> +}
>> #endif
>>
>> #endif /* _ASM_X86_HUGETLB_H */
>> diff --git a/fs/Kconfig b/fs/Kconfig
>> index ac474a61be37..4192d1fde0f0 100644
>> --- a/fs/Kconfig
>> +++ b/fs/Kconfig
>> @@ -207,7 +207,7 @@ config HUGETLB_PAGE
>> config MEMFD_CREATE
>> def_bool TMPFS || HUGETLBFS
>>
>> -config ARCH_HAS_GIGANTIC_PAGE
>> +config ARCH_HAS_GIGANTIC_PAGE_RUNTIME_ALLOCATION
>> bool
>>
>> source "fs/configfs/Kconfig"
>> diff --git a/include/linux/gfp.h b/include/linux/gfp.h
>> index 5f5e25fd6149..79ff86fabd42 100644
>> --- a/include/linux/gfp.h
>> +++ b/include/linux/gfp.h
>> @@ -589,8 +589,8 @@ static inline bool pm_suspended_storage(void)
>> /* The below functions must be run on a range from a single zone. */
>> extern int alloc_contig_range(unsigned long start, unsigned long end,
>> unsigned migratetype, gfp_t gfp_mask);
>> -extern void free_contig_range(unsigned long pfn, unsigned nr_pages);
>> #endif
>> +extern void free_contig_range(unsigned long pfn, unsigned int nr_pages);
>>
>> #ifdef CONFIG_CMA
>> /* CMA stuff */
>> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
>> index 745088810965..9893ba26b3b8 100644
>> --- a/mm/hugetlb.c
>> +++ b/mm/hugetlb.c
>> @@ -1035,7 +1035,6 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
>> ((node = hstate_next_node_to_free(hs, mask)) || 1); \
>> nr_nodes--)
>>
>> -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
>> static void destroy_compound_gigantic_page(struct page *page,
>> unsigned int order)
>> {
>> @@ -1058,6 +1057,7 @@ static void free_gigantic_page(struct page *page, unsigned int order)
>> free_contig_range(page_to_pfn(page), 1 << order);
>> }
>>
>> +#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE_RUNTIME_ALLOCATION
>> static int __alloc_gigantic_page(unsigned long start_pfn,
>> unsigned long nr_pages, gfp_t gfp_mask)
>> {
>> @@ -1143,22 +1143,19 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
>> static void prep_new_huge_page(struct hstate *h, struct page *page, int nid);
>> static void prep_compound_gigantic_page(struct page *page, unsigned int order);
>>
>> -#else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */
>> -static inline bool gigantic_page_supported(void) { return false; }
>> +#else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE_RUNTIME_ALLOCATION */
>> +static inline bool gigantic_page_runtime_allocation_supported(void)
>> +{
>> + return false;
>> +}
>> static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
>> int nid, nodemask_t *nodemask) { return NULL; }
>> -static inline void free_gigantic_page(struct page *page, unsigned int order) { }
>> -static inline void destroy_compound_gigantic_page(struct page *page,
>> - unsigned int order) { }
>> #endif
>>
>> static void update_and_free_page(struct hstate *h, struct page *page)
>> {
>> int i;
>>
>> - if (hstate_is_gigantic(h) && !gigantic_page_supported())
>> - return;
>> -
>> h->nr_huge_pages--;
>> h->nr_huge_pages_node[page_to_nid(page)]--;
>> for (i = 0; i < pages_per_huge_page(h); i++) {
>> @@ -2276,13 +2273,20 @@ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
>> }
>>
>> #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
>> -static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
>> +static int set_max_huge_pages(struct hstate *h, unsigned long count,
>> nodemask_t *nodes_allowed)
>> {
>> unsigned long min_count, ret;
>>
>> - if (hstate_is_gigantic(h) && !gigantic_page_supported())
>> - return h->max_huge_pages;
>> + if (hstate_is_gigantic(h) &&
>> + !gigantic_page_runtime_allocation_supported()) {
>> + spin_lock(&hugetlb_lock);
>> + if (count > persistent_huge_pages(h)) {
>> + spin_unlock(&hugetlb_lock);
>> + return -EINVAL;
>> + }
>> + goto decrease_pool;
>> + }
>>
>> /*
>> * Increase the pool size
>> @@ -2322,6 +2326,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
>> goto out;
>> }
>>
>> +decrease_pool:
>> /*
>> * Decrease the pool size
>> * First return free pages to the buddy allocator (being careful
>> @@ -2350,9 +2355,10 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
>> break;
>> }
>> out:
>> - ret = persistent_huge_pages(h);
>> + h->max_huge_pages = persistent_huge_pages(h);
>> spin_unlock(&hugetlb_lock);
>> - return ret;
>> +
>> + return 0;
>> }
>>
>> #define HSTATE_ATTR_RO(_name) \
>> @@ -2404,11 +2410,6 @@ static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
>> int err;
>> NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY);
>>
>> - if (hstate_is_gigantic(h) && !gigantic_page_supported()) {
>> - err = -EINVAL;
>> - goto out;
>> - }
>> -
>> if (nid == NUMA_NO_NODE) {
>> /*
>> * global hstate attribute
>> @@ -2428,7 +2429,9 @@ static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
>> } else
>> nodes_allowed = &node_states[N_MEMORY];
>>
>> - h->max_huge_pages = set_max_huge_pages(h, count, nodes_allowed);
>> + err = set_max_huge_pages(h, count, nodes_allowed);
>> + if (err)
>> + goto out;
>>
>> if (nodes_allowed != &node_states[N_MEMORY])
>> NODEMASK_FREE(nodes_allowed);
>> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
>> index cde5dac6229a..81b931db85a1 100644
>> --- a/mm/page_alloc.c
>> +++ b/mm/page_alloc.c
>> @@ -8241,8 +8241,9 @@ int alloc_contig_range(unsigned long start, unsigned long end,
>> pfn_max_align_up(end), migratetype);
>> return ret;
>> }
>> +#endif
>>
>> -void free_contig_range(unsigned long pfn, unsigned nr_pages)
>> +void free_contig_range(unsigned long pfn, unsigned int nr_pages)
>> {
>> unsigned int count = 0;
>>
>> @@ -8254,7 +8255,6 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
>> }
>> WARN(count != 0, "%d pages are still in use!\n", count);
>> }
>> -#endif
>>
>> #ifdef CONFIG_MEMORY_HOTPLUG
>> /*
>> --
>> 2.16.2
^ permalink raw reply
* Re: [PATCH 17/19] KVM: PPC: Book3S HV: add get/set accessors for the VP XIVE state
From: Cédric Le Goater @ 2019-02-05 11:58 UTC (permalink / raw)
To: David Gibson; +Cc: kvm, kvm-ppc, Paul Mackerras, linuxppc-dev
In-Reply-To: <20190205053331.GH22661@umbus.fritz.box>
On 2/5/19 6:33 AM, David Gibson wrote:
> On Mon, Feb 04, 2019 at 07:57:26PM +0100, Cédric Le Goater wrote:
>> On 2/4/19 6:26 AM, David Gibson wrote:
>>> On Mon, Jan 07, 2019 at 08:10:04PM +0100, Cédric Le Goater wrote:
>>>> At a VCPU level, the state of the thread context interrupt management
>>>> registers needs to be collected. These registers are cached under the
>>>> 'xive_saved_state.w01' field of the VCPU when the VPCU context is
>>>> pulled from the HW thread. An OPAL call retrieves the backup of the
>>>> IPB register in the NVT structure and merges it in the KVM state.
>>>>
>>>> The structures of the interface between QEMU and KVM provisions some
>>>> extra room (two u64) for further extensions if more state needs to be
>>>> transferred back to QEMU.
>>>>
>>>> Signed-off-by: Cédric Le Goater <clg@kaod.org>
>>>> ---
>>>> arch/powerpc/include/asm/kvm_ppc.h | 5 ++
>>>> arch/powerpc/include/uapi/asm/kvm.h | 2 +
>>>> arch/powerpc/kvm/book3s.c | 24 +++++++++
>>>> arch/powerpc/kvm/book3s_xive_native.c | 78 +++++++++++++++++++++++++++
>>>> 4 files changed, 109 insertions(+)
>>>>
>>>> diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
>>>> index 4cc897039485..49c488af168c 100644
>>>> --- a/arch/powerpc/include/asm/kvm_ppc.h
>>>> +++ b/arch/powerpc/include/asm/kvm_ppc.h
>>>> @@ -270,6 +270,7 @@ union kvmppc_one_reg {
>>>> u64 addr;
>>>> u64 length;
>>>> } vpaval;
>>>> + u64 xive_timaval[4];
>>>> };
>>>>
>>>> struct kvmppc_ops {
>>>> @@ -603,6 +604,8 @@ extern void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu);
>>>> extern void kvmppc_xive_native_init_module(void);
>>>> extern void kvmppc_xive_native_exit_module(void);
>>>> extern int kvmppc_xive_native_hcall(struct kvm_vcpu *vcpu, u32 cmd);
>>>> +extern int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val);
>>>> +extern int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val);
>>>>
>>>> #else
>>>> static inline int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
>>>> @@ -637,6 +640,8 @@ static inline void kvmppc_xive_native_init_module(void) { }
>>>> static inline void kvmppc_xive_native_exit_module(void) { }
>>>> static inline int kvmppc_xive_native_hcall(struct kvm_vcpu *vcpu, u32 cmd)
>>>> { return 0; }
>>>> +static inline int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val) { return 0; }
>>>> +static inline int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val) { return -ENOENT; }
>>>
>>> IIRC "VP" is the old name for "TCTX". Since we're using tctx in the
>>> rest of the XIVE code, can we use it here as well.
>>
>> OK. The state we are getting or setting is indeed related to the thread
>> interrupt context registers.
>>
>> The name VP is related to an identifier to some interrupt context under
>> OPAL (NVT in HW to be precise).
>
> Oh, sorry, "NVT" was the name I was looking for, not "TCTX". But in
> any case, please lets standardize on one.
There is some confusion in the naming for :
- VP Virtual Processor (XIVE 1)
- VPD Virtual Processor Descriptor (XIVE 1)
- TCTX Thread interrupt context registers
- NVT Notify Virtual Target. Former VP.
- NVTS Notify Virtual Target Structure. Where the TCTX regs are cached.
I am fine with using NVT because this is indeed the name of the XIVE
structure where the HW caches the thread interrupt context registers.
But the XIVE native layer and the XICS-over-XIVE KVM device use the
name VP (the old one). I don't think we want to change these now.
C.
^ permalink raw reply
* Re: [RFC/WIP] powerpc: Fix 32-bit handling of MSR_EE on exceptions
From: Christophe Leroy @ 2019-02-05 12:14 UTC (permalink / raw)
To: Benjamin Herrenschmidt, linuxppc-dev@lists.ozlabs.org
Cc: Diana Craciun, Scott Wood, Nick Piggin, Laurentiu Tudor
In-Reply-To: <fe3a79e078c644d9c1379ef5f8c431d787b6d0c8.camel@kernel.crashing.org>
Le 20/12/2018 à 06:40, Benjamin Herrenschmidt a écrit :
> Hi folks !
>
> Why trying to figure out why we had occasionally lockdep barf about
> interrupt state on ppc32 (440 in my case but I could reproduce on e500
> as well using qemu), I realized that we are still doing something
> rather gothic and wrong on 32-bit which we stopped doing on 64-bit
> a while ago.
>
> We have that thing where some handlers "copy" the EE value from the
> original stack frame into the new MSR before transferring to the
> handler.
>
> Thus for a number of exceptions, we enter the handlers with interrupts
> enabled.
>
> This is rather fishy, some of the stuff that handlers might do early
> on such as irq_enter/exit or user_exit, context tracking, etc... should
> be run with interrupts off afaik.
>
> Generally our handlers know when to re-enable interrupts if needed
> (though some of the FSL specific SPE ones don't).
>
> The problem we were having is that we assumed these interrupts would
> return with interrupts enabled. However that isn't the case.
>
> Instead, this changes things so that we always enter exception handlers
> with interrupts *off* with the notable exception of syscalls which are
> special (and get a fast path).
>
> Currently, the patch only changes BookE (440 and E5xx tested in qemu),
> the same recipe needs to be applied to 6xx, 8xx and 40x.
>
> Also I'm not sure whether we need to create a stack frame around some
> of the calls to trace_hardirqs_* in asm. ppc64 does it, due to problems
> with the irqsoff tracer, but I haven't managed to reproduce those
> issues. We need to look into it a bit more.
>
> I'll work more on this in the next few days, comments appreciated.
>
> Not-signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
>
> ---
> arch/powerpc/kernel/entry_32.S | 113 ++++++++++++++++++++++-------------
> arch/powerpc/kernel/head_44x.S | 9 +--
> arch/powerpc/kernel/head_booke.h | 34 ++++-------
> arch/powerpc/kernel/head_fsl_booke.S | 28 ++++-----
> arch/powerpc/kernel/traps.c | 8 +++
> 5 files changed, 111 insertions(+), 81 deletions(-)
>
> diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
> index 3841d74..39b4cb5 100644
> --- a/arch/powerpc/kernel/entry_32.S
> +++ b/arch/powerpc/kernel/entry_32.S
> @@ -34,6 +34,9 @@
> #include <asm/ftrace.h>
> #include <asm/ptrace.h>
> #include <asm/export.h>
> +#include <asm/feature-fixups.h>
> +#include <asm/barrier.h>
> +#include <asm/bug.h>
>
> /*
> * MSR_KERNEL is > 0x10000 on 4xx/Book-E since it include MSR_CE.
> @@ -205,20 +208,46 @@ transfer_to_handler_cont:
> mflr r9
> lwz r11,0(r9) /* virtual address of handler */
> lwz r9,4(r9) /* where to go when done */
> +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
> + mtspr SPRN_NRI, r0
> +#endif
> +
> #ifdef CONFIG_TRACE_IRQFLAGS
> + /*
> + * When tracing IRQ state (lockdep) we enable the MMU before we call
> + * the IRQ tracing functions as they might access vmalloc space or
> + * perform IOs for console output.
> + *
> + * To speed up the syscall path where interrupts stay on, let's check
> + * first if we are changing the MSR value at all.
> + */
> + lwz r12,_MSR(r1)
This one cannot work. MMU is not reenabled yet, so r1 cannot be used.
And r11 now has the virt address of handler, so can't be used either.
Christophe
> + xor r0,r10,r12
> + andi. r0,r0,MSR_EE
> + bne 1f
> +
> + /* MSR isn't changing, just transition directly */
> + lwz r0,GPR0(r1)
> + mtspr SPRN_SRR0,r11
> + mtspr SPRN_SRR1,r10
> + mtlr r9
> + SYNC
> + RFI
> +
> +1: /* MSR is changing, re-enable MMU so we can notify lockdep. We need to
> + * keep interrupts disabled at this point otherwise we might risk
> + * taking an interrupt before we tell lockdep they are enabled.
> + */
> lis r12,reenable_mmu@h
> ori r12,r12,reenable_mmu@l
> + lis r0,MSR_KERNEL@h
> + ori r0,r0,MSR_KERNEL@l
> mtspr SPRN_SRR0,r12
> - mtspr SPRN_SRR1,r10
> + mtspr SPRN_SRR1,r0
> SYNC
> RFI
> -reenable_mmu: /* re-enable mmu so we can */
> - mfmsr r10
> - lwz r12,_MSR(r1)
> - xor r10,r10,r12
> - andi. r10,r10,MSR_EE /* Did EE change? */
> - beq 1f
>
> +reenable_mmu:
> /*
> * The trace_hardirqs_off will use CALLER_ADDR0 and CALLER_ADDR1.
> * If from user mode there is only one stack frame on the stack, and
> @@ -239,8 +268,29 @@ reenable_mmu: /* re-enable mmu so we can */
> stw r3,16(r1)
> stw r4,20(r1)
> stw r5,24(r1)
> - bl trace_hardirqs_off
> - lwz r5,24(r1)
> +
> + /* Are we enabling or disabling interrupts ? */
> + andi. r0,r10,MSR_EE
> + beq 1f
> +
> + /* If we are enabling interrupt, this is a syscall. They 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 */
> + mfmsr r10
> + ori r10,r10,MSR_EE
> + mtmsr r10
> + b 2f
> +
> + /* If we are disabling interrupts (normal case), simply log it with
> + * lockdep
> + */
> +1: bl trace_hardirqs_off
> +2: lwz r5,24(r1)
> lwz r4,20(r1)
> lwz r3,16(r1)
> lwz r11,12(r1)
> @@ -250,7 +300,7 @@ reenable_mmu: /* re-enable mmu so we can */
> lwz r6,GPR6(r1)
> lwz r7,GPR7(r1)
> lwz r8,GPR8(r1)
> -1: mtctr r11
> + mtctr r11
> mtlr r9
> bctr /* jump to handler */
> #else /* CONFIG_TRACE_IRQFLAGS */
> @@ -312,31 +362,19 @@ _GLOBAL(DoSyscall)
> lwz r11,_CCR(r1) /* Clear SO bit in CR */
> rlwinm r11,r11,0,4,2
> stw r11,_CCR(r1)
> +
> #ifdef CONFIG_TRACE_IRQFLAGS
> - /* Return from syscalls can (and generally will) hard enable
> - * interrupts. You aren't supposed to call a syscall with
> - * interrupts disabled in the first place. However, to ensure
> - * that we get it right vs. lockdep if it happens, we force
> - * that hard enable here with appropriate tracing if we see
> - * that we have been called with interrupts off
> - */
> + /* Make sure interrupts are enabled */
> mfmsr r11
> andi. r12,r11,MSR_EE
> bne+ 1f
> - /* We came in with interrupts disabled, we enable them now */
> - bl trace_hardirqs_on
> - mfmsr r11
> - lwz r0,GPR0(r1)
> - lwz r3,GPR3(r1)
> - lwz r4,GPR4(r1)
> - ori r11,r11,MSR_EE
> - lwz r5,GPR5(r1)
> - lwz r6,GPR6(r1)
> - lwz r7,GPR7(r1)
> - lwz r8,GPR8(r1)
> - mtmsr r11
> + /* We came in with interrupts disabled, we WARN and mark them enabled
> + * for lockdep now */
> +0: trap
> + EMIT_BUG_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING
> 1:
> #endif /* CONFIG_TRACE_IRQFLAGS */
> +
> CURRENT_THREAD_INFO(r10, r1)
> lwz r11,TI_FLAGS(r10)
> andi. r11,r11,_TIF_SYSCALL_DOTRACE
> @@ -375,8 +413,7 @@ 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 happen though but we
> - * want to catch the bugger if it does right ?
> + * off, we trace that here. It shouldn't normally happen.
> */
> andi. r10,r8,MSR_EE
> bne+ 1f
> @@ -881,13 +918,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_47x)
> * off in this assembly code while peeking at TI_FLAGS() and such. However
> * we need to inform it if the exception turned interrupts off, and we
> * are about to trun them back on.
> - *
> - * The problem here sadly is that we don't know whether the exceptions was
> - * one that turned interrupts off or not. So we always tell lockdep about
> - * turning them on here when we go back to wherever we came from with EE
> - * on, even if that may meen some redudant calls being tracked. Maybe later
> - * we could encode what the exception did somewhere or test the exception
> - * type in the pt_regs but that sounds overkill
> */
> andi. r10,r9,MSR_EE
> beq 1f
> @@ -1175,9 +1205,10 @@ do_work: /* r10 contains MSR_KERNEL here */
> beq do_user_signal
>
> do_resched: /* r10 contains MSR_KERNEL here */
> - /* Note: We don't need to inform lockdep that we are enabling
> - * interrupts here. As far as it knows, they are already enabled
> - */
> +#ifdef CONFIG_TRACE_IRQFLAGS
> + bl trace_hardirqs_on
> + mfmsr r10
> +#endif
> ori r10,r10,MSR_EE
> SYNC
> MTMSRD(r10) /* hard-enable interrupts */
> diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
> index 37e4a7c..891a048 100644
> --- a/arch/powerpc/kernel/head_44x.S
> +++ b/arch/powerpc/kernel/head_44x.S
> @@ -40,6 +40,7 @@
> #include <asm/ptrace.h>
> #include <asm/synch.h>
> #include <asm/export.h>
> +
> #include "head_booke.h"
>
>
> @@ -277,16 +278,16 @@ interrupt_base:
> FP_UNAVAILABLE_EXCEPTION
> #else
> EXCEPTION(0x2010, BOOKE_INTERRUPT_FP_UNAVAIL, \
> - FloatingPointUnavailable, unknown_exception, EXC_XFER_EE)
> + FloatingPointUnavailable, unknown_exception, EXC_XFER_STD)
> #endif
> /* System Call Interrupt */
> START_EXCEPTION(SystemCall)
> NORMAL_EXCEPTION_PROLOG(BOOKE_INTERRUPT_SYSCALL)
> - EXC_XFER_EE_LITE(0x0c00, DoSyscall)
> + EXC_XFER_SYS(0x0c00, DoSyscall)
>
> /* Auxiliary Processor Unavailable Interrupt */
> EXCEPTION(0x2020, BOOKE_INTERRUPT_AP_UNAVAIL, \
> - AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE)
> + AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_STD)
>
> /* Decrementer Interrupt */
> DECREMENTER_EXCEPTION
> @@ -294,7 +295,7 @@ interrupt_base:
> /* Fixed Internal Timer Interrupt */
> /* TODO: Add FIT support */
> EXCEPTION(0x1010, BOOKE_INTERRUPT_FIT, FixedIntervalTimer, \
> - unknown_exception, EXC_XFER_EE)
> + unknown_exception, EXC_XFER_STD)
>
> /* Watchdog Timer Interrupt */
> /* TODO: Add watchdog support */
> diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
> index a620203..46be533 100644
> --- a/arch/powerpc/kernel/head_booke.h
> +++ b/arch/powerpc/kernel/head_booke.h
> @@ -210,8 +210,7 @@
> CRITICAL_EXCEPTION_PROLOG(intno); \
> addi r3,r1,STACK_FRAME_OVERHEAD; \
> EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
> - NOCOPY, crit_transfer_to_handler, \
> - ret_from_crit_exc)
> + crit_transfer_to_handler, ret_from_crit_exc)
>
> #define MCHECK_EXCEPTION(n, label, hdlr) \
> START_EXCEPTION(label); \
> @@ -220,36 +219,27 @@
> stw r5,_ESR(r11); \
> addi r3,r1,STACK_FRAME_OVERHEAD; \
> EXC_XFER_TEMPLATE(hdlr, n+4, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
> - NOCOPY, mcheck_transfer_to_handler, \
> - ret_from_mcheck_exc)
> + mcheck_transfer_to_handler, ret_from_mcheck_exc)
>
> -#define EXC_XFER_TEMPLATE(hdlr, trap, msr, copyee, tfer, ret) \
> +#define EXC_XFER_TEMPLATE(hdlr, trap, msr, tfer, ret) \
> li r10,trap; \
> stw r10,_TRAP(r11); \
> lis r10,msr@h; \
> ori r10,r10,msr@l; \
> - copyee(r10, r9); \
> bl tfer; \
> .long hdlr; \
> .long ret
>
> -#define COPY_EE(d, s) rlwimi d,s,0,16,16
> -#define NOCOPY(d, s)
> -
> #define EXC_XFER_STD(n, hdlr) \
> - EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, NOCOPY, transfer_to_handler_full, \
> + EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, transfer_to_handler_full, \
> ret_from_except_full)
>
> -#define EXC_XFER_LITE(n, hdlr) \
> - EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, NOCOPY, transfer_to_handler, \
> +#define EXC_XFER_SYS(n, hdlr) \
> + EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL | MSR_EE, transfer_to_handler, \
> ret_from_except)
>
> -#define EXC_XFER_EE(n, hdlr) \
> - EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, COPY_EE, transfer_to_handler_full, \
> - ret_from_except_full)
> -
> -#define EXC_XFER_EE_LITE(n, hdlr) \
> - EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, COPY_EE, transfer_to_handler, \
> +#define EXC_XFER_LITE(n, hdlr) \
> + EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, transfer_to_handler, \
> ret_from_except)
>
> /* Check for a single step debug exception while in an exception
> @@ -316,7 +306,7 @@
> /* continue normal handling for a debug exception... */ \
> 2: mfspr r4,SPRN_DBSR; \
> addi r3,r1,STACK_FRAME_OVERHEAD; \
> - EXC_XFER_TEMPLATE(DebugException, 0x2008, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), NOCOPY, debug_transfer_to_handler, ret_from_debug_exc)
> + EXC_XFER_TEMPLATE(DebugException, 0x2008, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), debug_transfer_to_handler, ret_from_debug_exc)
>
> #define DEBUG_CRIT_EXCEPTION \
> START_EXCEPTION(DebugCrit); \
> @@ -369,7 +359,7 @@
> /* continue normal handling for a critical exception... */ \
> 2: mfspr r4,SPRN_DBSR; \
> addi r3,r1,STACK_FRAME_OVERHEAD; \
> - EXC_XFER_TEMPLATE(DebugException, 0x2002, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), NOCOPY, crit_transfer_to_handler, ret_from_crit_exc)
> + EXC_XFER_TEMPLATE(DebugException, 0x2002, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), crit_transfer_to_handler, ret_from_crit_exc)
>
> #define DATA_STORAGE_EXCEPTION \
> START_EXCEPTION(DataStorage) \
> @@ -394,7 +384,7 @@
> mfspr r4,SPRN_DEAR; /* Grab the DEAR and save it */ \
> stw r4,_DEAR(r11); \
> addi r3,r1,STACK_FRAME_OVERHEAD; \
> - EXC_XFER_EE(0x0600, alignment_exception)
> + EXC_XFER_STD(0x0600, alignment_exception)
>
> #define PROGRAM_EXCEPTION \
> START_EXCEPTION(Program) \
> @@ -419,7 +409,7 @@
> bl load_up_fpu; /* if from user, just load it up */ \
> b fast_exception_return; \
> 1: addi r3,r1,STACK_FRAME_OVERHEAD; \
> - EXC_XFER_EE_LITE(0x800, kernel_fp_unavailable_exception)
> + EXC_XFER_STD(0x800, kernel_fp_unavailable_exception)
>
> #ifndef __ASSEMBLY__
> struct exception_regs {
> diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
> index bf4c602..556cffb 100644
> --- a/arch/powerpc/kernel/head_fsl_booke.S
> +++ b/arch/powerpc/kernel/head_fsl_booke.S
> @@ -385,7 +385,7 @@ interrupt_base:
> EXC_XFER_LITE(0x0300, handle_page_fault)
> 1:
> addi r3,r1,STACK_FRAME_OVERHEAD
> - EXC_XFER_EE_LITE(0x0300, CacheLockingException)
> + EXC_XFER_LITE(0x0300, CacheLockingException)
>
> /* Instruction Storage Interrupt */
> INSTRUCTION_STORAGE_EXCEPTION
> @@ -406,21 +406,21 @@ interrupt_base:
> #ifdef CONFIG_E200
> /* E200 treats 'normal' floating point instructions as FP Unavail exception */
> EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, \
> - program_check_exception, EXC_XFER_EE)
> + program_check_exception, EXC_XFER_STD)
> #else
> EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, \
> - unknown_exception, EXC_XFER_EE)
> + unknown_exception, EXC_XFER_STD)
> #endif
> #endif
>
> /* System Call Interrupt */
> START_EXCEPTION(SystemCall)
> NORMAL_EXCEPTION_PROLOG(SYSCALL)
> - EXC_XFER_EE_LITE(0x0c00, DoSyscall)
> + EXC_XFER_SYS(0x0c00, DoSyscall)
>
> /* Auxiliary Processor Unavailable Interrupt */
> EXCEPTION(0x2900, AP_UNAVAIL, AuxillaryProcessorUnavailable, \
> - unknown_exception, EXC_XFER_EE)
> + unknown_exception, EXC_XFER_STD)
>
> /* Decrementer Interrupt */
> DECREMENTER_EXCEPTION
> @@ -428,7 +428,7 @@ interrupt_base:
> /* Fixed Internal Timer Interrupt */
> /* TODO: Add FIT support */
> EXCEPTION(0x3100, FIT, FixedIntervalTimer, \
> - unknown_exception, EXC_XFER_EE)
> + unknown_exception, EXC_XFER_STD)
>
> /* Watchdog Timer Interrupt */
> #ifdef CONFIG_BOOKE_WDT
> @@ -623,25 +623,25 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
> bl load_up_spe
> b fast_exception_return
> 1: addi r3,r1,STACK_FRAME_OVERHEAD
> - EXC_XFER_EE_LITE(0x2010, KernelSPE)
> + EXC_XFER_LITE(0x2010, KernelSPE)
> #elif defined(CONFIG_SPE_POSSIBLE)
> EXCEPTION(0x2020, SPE_UNAVAIL, SPEUnavailable, \
> - unknown_exception, EXC_XFER_EE)
> + unknown_exception, EXC_XFER_STD)
> #endif /* CONFIG_SPE_POSSIBLE */
>
> /* SPE Floating Point Data */
> #ifdef CONFIG_SPE
> EXCEPTION(0x2030, SPE_FP_DATA, SPEFloatingPointData,
> - SPEFloatingPointException, EXC_XFER_EE)
> + SPEFloatingPointException, EXC_XFER_STD)
>
> /* SPE Floating Point Round */
> EXCEPTION(0x2050, SPE_FP_ROUND, SPEFloatingPointRound, \
> - SPEFloatingPointRoundException, EXC_XFER_EE)
> + SPEFloatingPointRoundException, EXC_XFER_STD)
> #elif defined(CONFIG_SPE_POSSIBLE)
> EXCEPTION(0x2040, SPE_FP_DATA, SPEFloatingPointData,
> - unknown_exception, EXC_XFER_EE)
> + unknown_exception, EXC_XFER_STD)
> EXCEPTION(0x2050, SPE_FP_ROUND, SPEFloatingPointRound, \
> - unknown_exception, EXC_XFER_EE)
> + unknown_exception, EXC_XFER_STD)
> #endif /* CONFIG_SPE_POSSIBLE */
>
>
> @@ -664,10 +664,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
> unknown_exception)
>
> /* Hypercall */
> - EXCEPTION(0, HV_SYSCALL, Hypercall, unknown_exception, EXC_XFER_EE)
> + EXCEPTION(0, HV_SYSCALL, Hypercall, unknown_exception, EXC_XFER_STD)
>
> /* Embedded Hypervisor Privilege */
> - EXCEPTION(0, HV_PRIV, Ehvpriv, unknown_exception, EXC_XFER_EE)
> + EXCEPTION(0, HV_PRIV, Ehvpriv, unknown_exception, EXC_XFER_STD)
>
> interrupt_end:
>
> diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
> index 023a462..5ee0b90 100644
> --- a/arch/powerpc/kernel/traps.c
> +++ b/arch/powerpc/kernel/traps.c
> @@ -1858,6 +1858,10 @@ void SPEFloatingPointException(struct pt_regs *regs)
> int code = 0;
> int err;
>
> + /* We restore the interrupt state now */
> + if (!arch_irq_disabled_regs(regs))
> + local_irq_enable();
> +
> flush_spe_to_thread(current);
>
> spefscr = current->thread.spefscr;
> @@ -1903,6 +1907,10 @@ void SPEFloatingPointRoundException(struct pt_regs *regs)
> extern int speround_handler(struct pt_regs *regs);
> int err;
>
> + /* We restore the interrupt state now */
> + if (!arch_irq_disabled_regs(regs))
> + local_irq_enable();
> +
> preempt_disable();
> if (regs->msr & MSR_SPE)
> giveup_spe(current);
>
^ permalink raw reply
* Re: [RFC/WIP] powerpc: Fix 32-bit handling of MSR_EE on exceptions
From: Benjamin Herrenschmidt @ 2019-02-05 12:19 UTC (permalink / raw)
To: Christophe Leroy, linuxppc-dev@lists.ozlabs.org
Cc: Diana Craciun, Scott Wood, Nick Piggin, Laurentiu Tudor
In-Reply-To: <5a97253c-0ec4-d61f-fa9e-ea5da8590f32@c-s.fr>
On Tue, 2019-02-05 at 10:45 +0100, Christophe Leroy wrote:
> > > I tested it on the 8xx with the below changes in addition. No issue seen
> > > so far.
> >
> > Thanks !
> >
> > I'll merge that in.
>
> I'm currently working on a refactorisation and simplification of
> exception and syscall entry on ppc32.
>
> I plan to take your patch in my serie as it helps quite a bit. I hope
> you don't mind. I expect to come out with a series this week.
Ah ok, you want to take over the series then ? We still need to convert
all the other CPU variants... to be honest I've been distracted, and
taking some time off. I'll be leaving IBM by the end of next week, so I
don't really see myself finishing this work properly.
> > The main obscure area is that business with the irqsoff tracer and thus
> > the need to create stack frames around calls to trace_hardirqs_* ... we
> > do it in some places and not others, but I've not managed to make it
> > crash either. I need to get to the bottom of that, and possibly provide
> > proper macro helpers like ppc64 has to do it.
>
> I can't see anything special around this in ppc32 code. As far as I
> understand, a stack frame is put in place when there is a need to
> save and restore some volatile registers. At the places where nothing
> needs to be saved, nothing is done. I think that's the normal way for
> any function call, isn't it ?
Not exactly. There's an issue with one of the tracers using
__bultin_return_address(1) which can crash afaik if we don't have
"enough" stack frames on the stack, so there are cases where we need to
create one explicitly around the tracing calls bcs there's only one on
the actual stack.
I don't know the full details, I was planning on doing a bunch of tests
in sim to figure out exactly what happens and what needs to be done
(and whether our existing code is correct or not), but didn't get to it
so far.
Cheers,
Ben.
^ permalink raw reply
* Re: [PATCH 15/19] KVM: PPC: Book3S HV: add get/set accessors for the source configuration
From: Cédric Le Goater @ 2019-02-05 13:03 UTC (permalink / raw)
To: David Gibson; +Cc: kvm, kvm-ppc, Paul Mackerras, linuxppc-dev
In-Reply-To: <20190205053233.GG22661@umbus.fritz.box>
On 2/5/19 6:32 AM, David Gibson wrote:
> On Mon, Feb 04, 2019 at 05:07:28PM +0100, Cédric Le Goater wrote:
>> On 2/4/19 6:21 AM, David Gibson wrote:
>>> On Mon, Jan 07, 2019 at 07:43:27PM +0100, Cédric Le Goater wrote:
>>>> Theses are use to capure the XIVE EAS table of the KVM device, the
>>>> configuration of the source targets.
>>>>
>>>> Signed-off-by: Cédric Le Goater <clg@kaod.org>
>>>> ---
>>>> arch/powerpc/include/uapi/asm/kvm.h | 11 ++++
>>>> arch/powerpc/kvm/book3s_xive_native.c | 87 +++++++++++++++++++++++++++
>>>> 2 files changed, 98 insertions(+)
>>>>
>>>> diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
>>>> index 1a8740629acf..faf024f39858 100644
>>>> --- a/arch/powerpc/include/uapi/asm/kvm.h
>>>> +++ b/arch/powerpc/include/uapi/asm/kvm.h
>>>> @@ -683,9 +683,20 @@ struct kvm_ppc_cpu_char {
>>>> #define KVM_DEV_XIVE_SAVE_EQ_PAGES 4
>>>> #define KVM_DEV_XIVE_GRP_SOURCES 2 /* 64-bit source attributes */
>>>> #define KVM_DEV_XIVE_GRP_SYNC 3 /* 64-bit source attributes */
>>>> +#define KVM_DEV_XIVE_GRP_EAS 4 /* 64-bit eas attributes */
>>>>
>>>> /* Layout of 64-bit XIVE source attribute values */
>>>> #define KVM_XIVE_LEVEL_SENSITIVE (1ULL << 0)
>>>> #define KVM_XIVE_LEVEL_ASSERTED (1ULL << 1)
>>>>
>>>> +/* Layout of 64-bit eas attribute values */
>>>> +#define KVM_XIVE_EAS_PRIORITY_SHIFT 0
>>>> +#define KVM_XIVE_EAS_PRIORITY_MASK 0x7
>>>> +#define KVM_XIVE_EAS_SERVER_SHIFT 3
>>>> +#define KVM_XIVE_EAS_SERVER_MASK 0xfffffff8ULL
>>>> +#define KVM_XIVE_EAS_MASK_SHIFT 32
>>>> +#define KVM_XIVE_EAS_MASK_MASK 0x100000000ULL
>>>> +#define KVM_XIVE_EAS_EISN_SHIFT 33
>>>> +#define KVM_XIVE_EAS_EISN_MASK 0xfffffffe00000000ULL
>>>> +
>>>> #endif /* __LINUX_KVM_POWERPC_H */
>>>> diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
>>>> index f2de1bcf3b35..0468b605baa7 100644
>>>> --- a/arch/powerpc/kvm/book3s_xive_native.c
>>>> +++ b/arch/powerpc/kvm/book3s_xive_native.c
>>>> @@ -525,6 +525,88 @@ static int kvmppc_xive_native_sync(struct kvmppc_xive *xive, long irq, u64 addr)
>>>> return 0;
>>>> }
>>>>
>>>> +static int kvmppc_xive_native_set_eas(struct kvmppc_xive *xive, long irq,
>>>> + u64 addr)
>>>
>>> I'd prefer to avoid the name "EAS" here. IIUC these aren't "raw" EAS
>>> values, but rather essentially the "source config" in the terminology
>>> of the PAPR hcalls. Which, yes, is basically implemented by setting
>>> the EAS, but since it's the PAPR architected state that we need to
>>> preserve across migration, I'd prefer to stick as close as we can to
>>> the PAPR terminology.
>>
>> But we don't have an equivalent name in the PAPR specs for the tuple
>> (prio, server). We could use the generic 'target' name may be ? even
>> if this is usually referring to a CPU number.
>
> Um.. what? That's about terminology for one of the fields in this
> thing, not about the name for the thing itself.
>
>> Or, IVE (Interrupt Vector Entry) ? which makes some sense.
>> This is was the former name in HW. I think we recycle it for KVM.
>
> That's a terrible idea, which will make a confusing situation even
> more confusing.
Let's use SOURCE_CONFIG and QUEUE_CONFIG. The KVM ioctls are very
similar to the hcalls anyhow.
C.
^ permalink raw reply
* Re: [PATCH 06/19] KVM: PPC: Book3S HV: add a GET_ESB_FD control to the XIVE native device
From: Cédric Le Goater @ 2019-02-05 12:55 UTC (permalink / raw)
To: David Gibson; +Cc: kvm, kvm-ppc, Paul Mackerras, linuxppc-dev
In-Reply-To: <20190205052822.GE22661@umbus.fritz.box>
On 2/5/19 6:28 AM, David Gibson wrote:
> On Mon, Feb 04, 2019 at 12:30:39PM +0100, Cédric Le Goater wrote:
>> On 2/4/19 5:45 AM, David Gibson wrote:
>>> On Mon, Jan 07, 2019 at 07:43:18PM +0100, Cédric Le Goater wrote:
>>>> This will let the guest create a memory mapping to expose the ESB MMIO
>>>> regions used to control the interrupt sources, to trigger events, to
>>>> EOI or to turn off the sources.
>>>>
>>>> Signed-off-by: Cédric Le Goater <clg@kaod.org>
>>>> ---
>>>> arch/powerpc/include/uapi/asm/kvm.h | 4 ++
>>>> arch/powerpc/kvm/book3s_xive_native.c | 97 +++++++++++++++++++++++++++
>>>> 2 files changed, 101 insertions(+)
>>>>
>>>> diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
>>>> index 8c876c166ef2..6bb61ba141c2 100644
>>>> --- a/arch/powerpc/include/uapi/asm/kvm.h
>>>> +++ b/arch/powerpc/include/uapi/asm/kvm.h
>>>> @@ -675,4 +675,8 @@ struct kvm_ppc_cpu_char {
>>>> #define KVM_XICS_PRESENTED (1ULL << 43)
>>>> #define KVM_XICS_QUEUED (1ULL << 44)
>>>>
>>>> +/* POWER9 XIVE Native Interrupt Controller */
>>>> +#define KVM_DEV_XIVE_GRP_CTRL 1
>>>> +#define KVM_DEV_XIVE_GET_ESB_FD 1
>>>
>>> Introducing a new FD for ESB and TIMA seems overkill. Can't you get
>>> to both with an mmap() directly on the xive device fd? Using the
>>> offset to distinguish which one to map, obviously.
>>
>> The page offset would define some sort of user API. It seems feasible.
>> But I am not sure this would be practical in the future if we need to
>> tune the length.
>
> Um.. why not? I mean, yes the XIVE supports rather a lot of
> interrupts, but we have 64-bits of offset we can play with - we can
> leave room for billions of ESB slots and still have room for billions
> of VPs.
So the first 4 pages could be the TIMA pages and then would come
the pages for the interrupt ESBs. I think that we can have different
vm_fault handler for each mapping.
I wonder how this will work out with pass-through. As Paul said in
a previous email, it would be better to let QEMU request a new
mapping to handle the ESB pages of the device being passed through.
I guess this is not a special case, just another offset and length.
I will give it a try.
Thanks,
C.
^ permalink raw reply
* Re: [PATCH 09/19] KVM: PPC: Book3S HV: add a SET_SOURCE control to the XIVE native device
From: Cédric Le Goater @ 2019-02-05 13:39 UTC (permalink / raw)
To: David Gibson; +Cc: kvm, kvm-ppc, Paul Mackerras, linuxppc-dev
In-Reply-To: <20190205053554.GI22661@umbus.fritz.box>
On 2/5/19 6:35 AM, David Gibson wrote:
> On Mon, Feb 04, 2019 at 08:07:20PM +0100, Cédric Le Goater wrote:
>> On 2/4/19 5:57 AM, David Gibson wrote:
>>> On Mon, Jan 07, 2019 at 07:43:21PM +0100, Cédric Le Goater wrote:
> [snip]
>>>> + sb = kvmppc_xive_create_src_block(xive, irq);
>>>> + if (!sb) {
>>>> + pr_err("Failed to create block...\n");
>>>> + return -ENOMEM;
>>>> + }
>>>> + }
>>>> + state = &sb->irq_state[idx];
>>>> +
>>>> + if (get_user(val, ubufp)) {
>>>> + pr_err("fault getting user info !\n");
>>>> + return -EFAULT;
>>>> + }
>>>> +
>>>> + /*
>>>> + * If the source doesn't already have an IPI, allocate
>>>> + * one and get the corresponding data
>>>> + */
>>>> + if (!state->ipi_number) {
>>>> + state->ipi_number = xive_native_alloc_irq();
>>>> + if (state->ipi_number == 0) {
>>>> + pr_err("Failed to allocate IRQ !\n");
>>>> + return -ENOMEM;
>>>> + }
>>>
>>> Am I right in thinking this is the point at which a specific guest irq
>>> number gets bound to a specific host irq number?
>>
>> yes. the XIVE IRQ state caches this information and 'state' should be
>> protected before being assigned, indeed ... The XICS-over-XIVE device
>> also has the same race issue.
>>
>> It's not showing because where initializing the KVM device sequentially
>> from QEMU and only once.
>
> Ok.
>
> So, for the passthrough case, what's the point at which we know that a
> particular guest interrupt needs to be bound to a specific real
> hardware interrupt, rather than a generic IPI?
when the guest driver requests MSIs, VFIO requests a mapping of the
HW irqs in the guest IRQ space. This is very briefly said as VFIO is
a huge framework.
Patch 18 adds some initial support to handle the ESB pages but this
should be done at the QEMU level.
C.
^ permalink raw reply
* Re: [PATCH] powerpc/prom_init: add __init markers to all functions
From: Masahiro Yamada @ 2019-02-05 13:57 UTC (permalink / raw)
To: Michael Ellerman
Cc: Mathieu Malaterre, Linux Kernel Mailing List, Paul Mackerras,
Aneesh Kumar K.V, linuxppc-dev
In-Reply-To: <87k1iemsvz.fsf@concordia.ellerman.id.au>
On Tue, Feb 5, 2019 at 7:33 PM Michael Ellerman <mpe@ellerman.id.au> wrote:
>
> Masahiro Yamada <yamada.masahiro@socionext.com> writes:
>
> > It is fragile to rely on the compiler's optimization to avoid the
> > section mismatch. Some functions may not be necessarily inlined
> > when the compiler's inlining heuristic changes.
> >
> > Add __init markers consistently.
> >
> > As for prom_getprop() and prom_getproplen(), they are marked as
> > 'inline', so inlining is guaranteed because PowerPC never enables
> > CONFIG_OPTIMIZE_INLINING. However, it would be better to leave the
> > inlining decision to the compiler. I replaced 'inline' with __init.
>
> I'm going to drop that part because it breaks the build in some
> configurations (as reported by the build robot).
If you drop this part, my motivation for this patch is lost.
My motivation is to allow all architectures to enable
CONFIG_OPTIMIZE_INLINING.
(Currently, only x86 can enable it, but I see nothing arch-dependent
in this feature.)
When I tested it in 0-day bot, it reported
section mismatches from prom_getprop() and prom_getproplen().
So, I want to fix the section mismatches without
relying on 'inline'.
My suggestion is this:
static int __init __maybe_unused prom_getproplen(phandle node,
const char *pname)
{
return call_prom("getproplen", 2, 1, node, ADDR(pname));
}
It is true you can use the side-effect of 'inline'
to hide the unused function warnings, but I prefer
as less inline markers as possible in *.c files.
> > diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
> > index f33ff41..85b0719 100644
> > --- a/arch/powerpc/kernel/prom_init.c
> > +++ b/arch/powerpc/kernel/prom_init.c
> > @@ -501,19 +501,19 @@ static int __init prom_next_node(phandle *nodep)
> > }
> > }
> >
> > -static inline int prom_getprop(phandle node, const char *pname,
> > +static int __init prom_getprop(phandle node, const char *pname,
> > void *value, size_t valuelen)
> > {
> > return call_prom("getprop", 4, 1, node, ADDR(pname),
> > (u32)(unsigned long) value, (u32) valuelen);
> > }
> >
> > -static inline int prom_getproplen(phandle node, const char *pname)
> > +static int __init prom_getproplen(phandle node, const char *pname)
> > {
> > return call_prom("getproplen", 2, 1, node, ADDR(pname));
> > }
> >
> > -static void add_string(char **str, const char *q)
> > +static void __init add_string(char **str, const char *q)
> > {
> > char *p = *str;
> >
> > @@ -523,7 +523,7 @@ static void add_string(char **str, const char *q)
> > *str = p;
> > }
> >
> > -static char *tohex(unsigned int x)
> > +static char __init *tohex(unsigned int x)
> > {
> > static const char digits[] __initconst = "0123456789abcdef";
> > static char result[9] __prombss;
> > @@ -570,7 +570,7 @@ static int __init prom_setprop(phandle node, const char *nodename,
> > #define islower(c) ('a' <= (c) && (c) <= 'z')
> > #define toupper(c) (islower(c) ? ((c) - 'a' + 'A') : (c))
> >
> > -static unsigned long prom_strtoul(const char *cp, const char **endp)
> > +static unsigned long __init prom_strtoul(const char *cp, const char **endp)
> > {
> > unsigned long result = 0, base = 10, value;
> >
> > @@ -595,7 +595,7 @@ static unsigned long prom_strtoul(const char *cp, const char **endp)
> > return result;
> > }
> >
> > -static unsigned long prom_memparse(const char *ptr, const char **retptr)
> > +static unsigned long __init prom_memparse(const char *ptr, const char **retptr)
> > {
> > unsigned long ret = prom_strtoul(ptr, retptr);
> > int shift = 0;
> > @@ -2924,7 +2924,7 @@ static void __init fixup_device_tree_pasemi(void)
> > prom_setprop(iob, name, "device_type", "isa", sizeof("isa"));
> > }
> > #else /* !CONFIG_PPC_PASEMI_NEMO */
> > -static inline void fixup_device_tree_pasemi(void) { }
> > +static inline void __init fixup_device_tree_pasemi(void) { }
>
> I don't think we need __init for an empty static inline.
I prefer 'static __init' to 'static inline',
but I can drop this if you are uncomfortable with it.
My work will not be blocked by this.
> > #endif
> >
> > static void __init fixup_device_tree(void)
> > @@ -2986,15 +2986,15 @@ static void __init prom_check_initrd(unsigned long r3, unsigned long r4)
> >
> > #ifdef CONFIG_PPC64
> > #ifdef CONFIG_RELOCATABLE
> > -static void reloc_toc(void)
> > +static void __init reloc_toc(void)
> > {
> > }
> >
> > -static void unreloc_toc(void)
> > +static void __init unreloc_toc(void)
> > {
> > }
>
> Those should be empty static inlines, I'll fix them up.
As I said above, I believe 'static inline' is mostly useful in headers,
but this is up to you.
BTW, I have v2 in hand already.
Do you need it if it is convenient for you?
I added __init to enter_prom() as well,
but you may not be comfortable with
replacing inline with __init.
> > #else
> > -static void __reloc_toc(unsigned long offset, unsigned long nr_entries)
> > +static void __init __reloc_toc(unsigned long offset, unsigned long nr_entries)
> > {
> > unsigned long i;
> > unsigned long *toc_entry;
> > @@ -3008,7 +3008,7 @@ static void __reloc_toc(unsigned long offset, unsigned long nr_entries)
> > }
> > }
> >
> > -static void reloc_toc(void)
> > +static void __init reloc_toc(void)
> > {
> > unsigned long offset = reloc_offset();
> > unsigned long nr_entries =
> > @@ -3019,7 +3019,7 @@ static void reloc_toc(void)
> > mb();
> > }
> >
> > -static void unreloc_toc(void)
> > +static void __init unreloc_toc(void)
> > {
> > unsigned long offset = reloc_offset();
> > unsigned long nr_entries =
>
>
> cheers
--
Best Regards
Masahiro Yamada
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox