* [PATCH v2 10/11] powerpc: remove partial register save logic
From: Nicholas Piggin @ 2021-03-16 10:42 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Scott Wood, Nicholas Piggin
In-Reply-To: <20210316104206.407354-1-npiggin@gmail.com>
All subarchitectures always save all GPRs to pt_regs interrupt frames
now. Remove FULL_REGS and associated bits.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/ptrace.h | 17 ++---------------
arch/powerpc/kernel/align.c | 6 ------
arch/powerpc/kernel/interrupt.c | 3 ---
arch/powerpc/kernel/process.c | 12 ------------
arch/powerpc/kernel/ptrace/ptrace-view.c | 21 ---------------------
arch/powerpc/kernel/ptrace/ptrace.c | 2 --
arch/powerpc/kernel/ptrace/ptrace32.c | 4 ----
arch/powerpc/kernel/signal_32.c | 3 ---
arch/powerpc/kernel/signal_64.c | 2 --
arch/powerpc/kernel/traps.c | 1 -
arch/powerpc/lib/sstep.c | 4 ----
arch/powerpc/xmon/xmon.c | 23 +++++++----------------
12 files changed, 9 insertions(+), 89 deletions(-)
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index c5b3669918f4..91194fdd5d01 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -188,29 +188,16 @@ static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
#ifdef __powerpc64__
#define TRAP_FLAGS_MASK 0x10
#define TRAP(regs) ((regs)->trap & ~TRAP_FLAGS_MASK)
-#define FULL_REGS(regs) true
-#define SET_FULL_REGS(regs) do { } while (0)
-#define CHECK_FULL_REGS(regs) do { } while (0)
-#define NV_REG_POISON 0xdeadbeefdeadbeefUL
#else
/*
- * We use the least-significant bit of the trap field to indicate
- * whether we have saved the full set of registers, or only a
- * partial set. A 1 there means the partial set.
- * On 4xx we use the next bit to indicate whether the exception
+ * On 4xx we use bit 1 in the trap word to indicate whether the exception
* is a critical exception (1 means it is).
*/
-#define TRAP_FLAGS_MASK 0x1F
+#define TRAP_FLAGS_MASK 0x1E
#define TRAP(regs) ((regs)->trap & ~TRAP_FLAGS_MASK)
-#define FULL_REGS(regs) true
-#define SET_FULL_REGS(regs) do { } while (0)
#define IS_CRITICAL_EXC(regs) (((regs)->trap & 2) != 0)
#define IS_MCHECK_EXC(regs) (((regs)->trap & 4) != 0)
#define IS_DEBUG_EXC(regs) (((regs)->trap & 8) != 0)
-#define NV_REG_POISON 0xdeadbeef
-#define CHECK_FULL_REGS(regs) \
-do { \
-} while (0)
#endif /* __powerpc64__ */
static inline void set_trap(struct pt_regs *regs, unsigned long val)
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index c7797eb958c7..ae525397947e 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -299,12 +299,6 @@ int fix_alignment(struct pt_regs *regs)
struct instruction_op op;
int r, type;
- /*
- * We require a complete register set, if not, then our assembly
- * is broken
- */
- CHECK_FULL_REGS(regs);
-
if (unlikely(__get_user_instr(instr, (void __user *)regs->nip)))
return -EFAULT;
if ((regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE)) {
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 1b0e1792ac37..b953bb5027e6 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -51,7 +51,6 @@ notrace long system_call_exception(long r3, long r4, long r5,
if (!IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x))
BUG_ON(!(regs->msr & MSR_RI));
BUG_ON(!(regs->msr & MSR_PR));
- BUG_ON(!FULL_REGS(regs));
BUG_ON(arch_irq_disabled_regs(regs));
#ifdef CONFIG_PPC_PKEY
@@ -365,7 +364,6 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
if (!IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x))
BUG_ON(!(regs->msr & MSR_RI));
BUG_ON(!(regs->msr & MSR_PR));
- BUG_ON(!FULL_REGS(regs));
BUG_ON(arch_irq_disabled_regs(regs));
CT_WARN_ON(ct_state() == CONTEXT_USER);
@@ -445,7 +443,6 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
unlikely(!(regs->msr & MSR_RI)))
unrecoverable_exception(regs);
BUG_ON(regs->msr & MSR_PR);
- BUG_ON(!FULL_REGS(regs));
/*
* CT_WARN_ON comes here via program_check_exception,
* so avoid recursion.
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 7989d9ce468b..1e62a70a29aa 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1447,11 +1447,9 @@ static void print_msr_bits(unsigned long val)
#ifdef CONFIG_PPC64
#define REG "%016lx"
#define REGS_PER_LINE 4
-#define LAST_VOLATILE 13
#else
#define REG "%08lx"
#define REGS_PER_LINE 8
-#define LAST_VOLATILE 12
#endif
static void __show_regs(struct pt_regs *regs)
@@ -1487,8 +1485,6 @@ static void __show_regs(struct pt_regs *regs)
if ((i % REGS_PER_LINE) == 0)
pr_cont("\nGPR%02d: ", i);
pr_cont(REG " ", regs->gpr[i]);
- if (i == LAST_VOLATILE && !FULL_REGS(regs))
- break;
}
pr_cont("\n");
/*
@@ -1691,7 +1687,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
} else {
/* user thread */
struct pt_regs *regs = current_pt_regs();
- CHECK_FULL_REGS(regs);
*childregs = *regs;
if (usp)
childregs->gpr[1] = usp;
@@ -1796,13 +1791,6 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
regs->ccr = 0;
regs->gpr[1] = sp;
- /*
- * We have just cleared all the nonvolatile GPRs, so make
- * FULL_REGS(regs) return true. This is necessary to allow
- * ptrace to examine the thread immediately after exec.
- */
- SET_FULL_REGS(regs);
-
#ifdef CONFIG_PPC32
regs->mq = 0;
regs->nip = start;
diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c
index 2bad8068f598..8eb826aa2a10 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-view.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-view.c
@@ -221,17 +221,9 @@ static int gpr_get(struct task_struct *target, const struct user_regset *regset,
#ifdef CONFIG_PPC64
struct membuf to_softe = membuf_at(&to, offsetof(struct pt_regs, softe));
#endif
- int i;
-
if (target->thread.regs == NULL)
return -EIO;
- if (!FULL_REGS(target->thread.regs)) {
- /* We have a partial register set. Fill 14-31 with bogus values */
- for (i = 14; i < 32; i++)
- target->thread.regs->gpr[i] = NV_REG_POISON;
- }
-
membuf_write(&to, target->thread.regs, sizeof(struct user_pt_regs));
membuf_store(&to_msr, get_user_msr(target));
@@ -252,8 +244,6 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
if (target->thread.regs == NULL)
return -EIO;
- CHECK_FULL_REGS(target->thread.regs);
-
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
target->thread.regs,
0, PT_MSR * sizeof(reg));
@@ -723,19 +713,9 @@ static int gpr32_get(struct task_struct *target,
const struct user_regset *regset,
struct membuf to)
{
- int i;
-
if (target->thread.regs == NULL)
return -EIO;
- if (!FULL_REGS(target->thread.regs)) {
- /*
- * We have a partial register set.
- * Fill 14-31 with bogus values.
- */
- for (i = 14; i < 32; i++)
- target->thread.regs->gpr[i] = NV_REG_POISON;
- }
return gpr32_get_common(target, regset, to,
&target->thread.regs->gpr[0]);
}
@@ -748,7 +728,6 @@ static int gpr32_set(struct task_struct *target,
if (target->thread.regs == NULL)
return -EIO;
- CHECK_FULL_REGS(target->thread.regs);
return gpr32_set_common(target, regset, pos, count, kbuf, ubuf,
&target->thread.regs->gpr[0]);
}
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
index 4f3d4ff3728c..f59883902b35 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -59,7 +59,6 @@ long arch_ptrace(struct task_struct *child, long request,
if ((addr & (sizeof(long) - 1)) || !child->thread.regs)
break;
- CHECK_FULL_REGS(child->thread.regs);
if (index < PT_FPR0)
ret = ptrace_get_reg(child, (int) index, &tmp);
else
@@ -81,7 +80,6 @@ long arch_ptrace(struct task_struct *child, long request,
if ((addr & (sizeof(long) - 1)) || !child->thread.regs)
break;
- CHECK_FULL_REGS(child->thread.regs);
if (index < PT_FPR0)
ret = ptrace_put_reg(child, index, data);
else
diff --git a/arch/powerpc/kernel/ptrace/ptrace32.c b/arch/powerpc/kernel/ptrace/ptrace32.c
index d30b9ad70edc..19c224808982 100644
--- a/arch/powerpc/kernel/ptrace/ptrace32.c
+++ b/arch/powerpc/kernel/ptrace/ptrace32.c
@@ -83,7 +83,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
if ((addr & 3) || (index > PT_FPSCR32))
break;
- CHECK_FULL_REGS(child->thread.regs);
if (index < PT_FPR0) {
ret = ptrace_get_reg(child, index, &tmp);
if (ret)
@@ -133,7 +132,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
if ((addr & 3) || numReg > PT_FPSCR)
break;
- CHECK_FULL_REGS(child->thread.regs);
if (numReg >= PT_FPR0) {
flush_fp_to_thread(child);
/* get 64 bit FPR */
@@ -187,7 +185,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
if ((addr & 3) || (index > PT_FPSCR32))
break;
- CHECK_FULL_REGS(child->thread.regs);
if (index < PT_FPR0) {
ret = ptrace_put_reg(child, index, data);
} else {
@@ -226,7 +223,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
*/
if ((addr & 3) || (numReg > PT_FPSCR))
break;
- CHECK_FULL_REGS(child->thread.regs);
if (numReg < PT_FPR0) {
unsigned long freg;
ret = ptrace_get_reg(child, numReg, &freg);
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 75ee918a120a..73551237de9d 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -99,8 +99,6 @@ save_general_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame)
elf_greg_t64 *gregs = (elf_greg_t64 *)regs;
int val, i;
- WARN_ON(!FULL_REGS(regs));
-
for (i = 0; i <= PT_RESULT; i ++) {
/* Force usr to alway see softe as 1 (interrupts enabled) */
if (i == PT_SOFTE)
@@ -153,7 +151,6 @@ static inline int get_sigset_t(sigset_t *set, const sigset_t __user *uset)
static __always_inline int
save_general_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame)
{
- WARN_ON(!FULL_REGS(regs));
unsafe_copy_to_user(&frame->mc_gregs, regs, GP_REGS_SIZE, failed);
return 0;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index f9e4a1ac440f..0e3637722e97 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -160,7 +160,6 @@ static long setup_sigcontext(struct sigcontext __user *sc,
}
#endif /* CONFIG_VSX */
err |= __put_user(&sc->gp_regs, &sc->regs);
- WARN_ON(!FULL_REGS(regs));
err |= __copy_to_user(&sc->gp_regs, regs, GP_REGS_SIZE);
err |= __put_user(msr, &sc->gp_regs[PT_MSR]);
err |= __put_user(softe, &sc->gp_regs[PT_SOFTE]);
@@ -294,7 +293,6 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc,
err |= __put_user(&sc->gp_regs, &sc->regs);
err |= __put_user(&tm_sc->gp_regs, &tm_sc->regs);
- WARN_ON(!FULL_REGS(regs));
err |= __copy_to_user(&tm_sc->gp_regs, regs, GP_REGS_SIZE);
err |= __copy_to_user(&sc->gp_regs,
&tsk->thread.ckpt_regs, GP_REGS_SIZE);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 97b5f3d83ff7..6c62e4e87979 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1319,7 +1319,6 @@ static int emulate_instruction(struct pt_regs *regs)
if (!user_mode(regs))
return -EINVAL;
- CHECK_FULL_REGS(regs);
if (get_user(instword, (u32 __user *)(regs->nip)))
return -EFAULT;
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 739ea6dc461c..45bda2520755 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1401,10 +1401,6 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
break;
}
- /* Following cases refer to regs->gpr[], so we need all regs */
- if (!FULL_REGS(regs))
- return -1;
-
rd = (word >> 21) & 0x1f;
ra = (word >> 16) & 0x1f;
rb = (word >> 11) & 0x1f;
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 3fe37495f63d..42a2c831d87a 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1815,25 +1815,16 @@ static void prregs(struct pt_regs *fp)
}
#ifdef CONFIG_PPC64
- if (FULL_REGS(fp)) {
- for (n = 0; n < 16; ++n)
- printf("R%.2d = "REG" R%.2d = "REG"\n",
- n, fp->gpr[n], n+16, fp->gpr[n+16]);
- } else {
- for (n = 0; n < 7; ++n)
- printf("R%.2d = "REG" R%.2d = "REG"\n",
- n, fp->gpr[n], n+7, fp->gpr[n+7]);
- }
+#define R_PER_LINE 2
#else
+#define R_PER_LINE 4
+#endif
+
for (n = 0; n < 32; ++n) {
- printf("R%.2d = %.8lx%s", n, fp->gpr[n],
- (n & 3) == 3? "\n": " ");
- if (n == 12 && !FULL_REGS(fp)) {
- printf("\n");
- break;
- }
+ printf("R%.2d = "REG"%s", n, fp->gpr[n],
+ (n % R_PER_LINE) == R_PER_LINE - 1 ? "\n" : " ");
}
-#endif
+
printf("pc = ");
xmon_print_symbol(fp->nip, " ", "\n");
if (!trap_is_syscall(fp) && cpu_has_feature(CPU_FTR_CFAR)) {
--
2.23.0
^ permalink raw reply related
* [PATCH v2 09/11] powerpc: clean up do_page_fault
From: Nicholas Piggin @ 2021-03-16 10:42 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Scott Wood, Nicholas Piggin
In-Reply-To: <20210316104206.407354-1-npiggin@gmail.com>
search_exception_tables + __bad_page_fault can be substituted with
bad_page_fault, do_page_fault no longer needs to return a value
to asm for any sub-architecture, and __bad_page_fault can be static.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/bug.h | 5 +----
arch/powerpc/include/asm/interrupt.h | 2 +-
arch/powerpc/mm/book3s64/hash_utils.c | 16 +++++++---------
arch/powerpc/mm/fault.c | 27 ++++++++-------------------
4 files changed, 17 insertions(+), 33 deletions(-)
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index d1635ffbb179..0b2162890d8b 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -111,11 +111,8 @@
#ifndef __ASSEMBLY__
struct pt_regs;
-long do_page_fault(struct pt_regs *);
-long hash__do_page_fault(struct pt_regs *);
+void hash__do_page_fault(struct pt_regs *);
void bad_page_fault(struct pt_regs *, int);
-void __bad_page_fault(struct pt_regs *regs, int sig);
-void do_bad_page_fault_segv(struct pt_regs *regs);
extern void _exception(int, struct pt_regs *, int, unsigned long);
extern void _exception_pkey(struct pt_regs *, unsigned long, int);
extern void die(const char *, struct pt_regs *, long);
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 94fd8e1ff52c..bd0bd9430f78 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -420,7 +420,7 @@ DECLARE_INTERRUPT_HANDLER(do_bad_slb_fault);
DECLARE_INTERRUPT_HANDLER_RAW(do_hash_fault);
/* fault.c */
-DECLARE_INTERRUPT_HANDLER_RET(do_page_fault);
+DECLARE_INTERRUPT_HANDLER(do_page_fault);
DECLARE_INTERRUPT_HANDLER(do_bad_page_fault_segv);
/* process.c */
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 581b20a2feaf..1c4b0a29f0f5 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1572,10 +1572,11 @@ DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault)
{
unsigned long dsisr = regs->dsisr;
- long err;
- if (unlikely(dsisr & (DSISR_BAD_FAULT_64S | DSISR_KEYFAULT)))
- goto page_fault;
+ if (unlikely(dsisr & (DSISR_BAD_FAULT_64S | DSISR_KEYFAULT))) {
+ hash__do_page_fault(regs);
+ return 0;
+ }
/*
* If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
@@ -1595,13 +1596,10 @@ DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault)
return 0;
}
- err = __do_hash_fault(regs);
- if (err) {
-page_fault:
- err = hash__do_page_fault(regs);
- }
+ if (__do_hash_fault(regs))
+ hash__do_page_fault(regs);
- return err;
+ return 0;
}
#ifdef CONFIG_PPC_MM_SLICES
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 44833660b21d..2c6e9a6bb86f 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -539,36 +539,25 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
}
NOKPROBE_SYMBOL(___do_page_fault);
-static long __do_page_fault(struct pt_regs *regs)
+static __always_inline void __do_page_fault(struct pt_regs *regs)
{
- const struct exception_table_entry *entry;
long err;
err = ___do_page_fault(regs, regs->dar, regs->dsisr);
- if (likely(!err))
- return err;
-
- entry = search_exception_tables(regs->nip);
- if (likely(entry)) {
- instruction_pointer_set(regs, extable_fixup(entry));
- return 0;
- } else {
- __bad_page_fault(regs, err);
- return 0;
- }
+ if (unlikely(err))
+ bad_page_fault(regs, err);
}
-NOKPROBE_SYMBOL(__do_page_fault);
-DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
+DEFINE_INTERRUPT_HANDLER(do_page_fault)
{
- return __do_page_fault(regs);
+ __do_page_fault(regs);
}
#ifdef CONFIG_PPC_BOOK3S_64
/* Same as do_page_fault but interrupt entry has already run in do_hash_fault */
-long hash__do_page_fault(struct pt_regs *regs)
+void hash__do_page_fault(struct pt_regs *regs)
{
- return __do_page_fault(regs);
+ __do_page_fault(regs);
}
NOKPROBE_SYMBOL(hash__do_page_fault);
#endif
@@ -578,7 +567,7 @@ NOKPROBE_SYMBOL(hash__do_page_fault);
* It is called from the DSI and ISI handlers in head.S and from some
* of the procedures in traps.c.
*/
-void __bad_page_fault(struct pt_regs *regs, int sig)
+static void __bad_page_fault(struct pt_regs *regs, int sig)
{
int is_write = page_fault_is_write(regs->dsisr);
--
2.23.0
^ permalink raw reply related
* [PATCH v2 08/11] powerpc/64e/interrupt: handle bad_page_fault in C
From: Nicholas Piggin @ 2021-03-16 10:42 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Scott Wood, Nicholas Piggin
In-Reply-To: <20210316104206.407354-1-npiggin@gmail.com>
With non-volatile registers saved on interrupt, bad_page_fault
can now be called by do_page_fault.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64e.S | 6 ------
arch/powerpc/mm/fault.c | 5 +----
2 files changed, 1 insertion(+), 10 deletions(-)
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 3c222a97f023..7c3654b0d0f4 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -937,12 +937,6 @@ storage_fault_common:
ld r14,PACA_EXGEN+EX_R14(r13)
ld r15,PACA_EXGEN+EX_R15(r13)
bl do_page_fault
- cmpdi r3,0
- bne- 1f
- b interrupt_return
- mr r4,r3
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl __bad_page_fault
b interrupt_return
/*
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 2e54bac99a22..44833660b21d 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -552,12 +552,9 @@ static long __do_page_fault(struct pt_regs *regs)
if (likely(entry)) {
instruction_pointer_set(regs, extable_fixup(entry));
return 0;
- } else if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64)) {
+ } else {
__bad_page_fault(regs, err);
return 0;
- } else {
- /* 32 and 64e handle the bad page fault in asm */
- return err;
}
}
NOKPROBE_SYMBOL(__do_page_fault);
--
2.23.0
^ permalink raw reply related
* [PATCH v2 07/11] powerpc/64e/interrupt: Use new interrupt context tracking scheme
From: Nicholas Piggin @ 2021-03-16 10:42 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Scott Wood, Nicholas Piggin
In-Reply-To: <20210316104206.407354-1-npiggin@gmail.com>
With the new interrupt exit code, context tracking can be managed
more precisely, so remove the last of the 64e workarounds and switch
to the new context tracking code already used by 64s.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 28 ----------------------------
arch/powerpc/kernel/interrupt.c | 16 +---------------
2 files changed, 1 insertion(+), 43 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 29b48d083156..94fd8e1ff52c 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -10,9 +10,6 @@
#include <asm/runlatch.h>
struct interrupt_state {
-#ifdef CONFIG_PPC_BOOK3E_64
- enum ctx_state ctx_state;
-#endif
};
static inline void booke_restore_dbcr0(void)
@@ -45,9 +42,7 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
if (irq_soft_mask_set_return(IRQS_ALL_DISABLED) == IRQS_ENABLED)
trace_hardirqs_off();
local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
-#endif
-#ifdef CONFIG_PPC_BOOK3S_64
if (user_mode(regs)) {
CT_WARN_ON(ct_state() != CONTEXT_USER);
user_exit_irqoff();
@@ -64,12 +59,6 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
}
#endif
-#ifdef CONFIG_PPC_BOOK3E_64
- state->ctx_state = exception_enter();
- if (user_mode(regs))
- account_cpu_user_entry();
-#endif
-
booke_restore_dbcr0();
}
@@ -89,25 +78,8 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
*/
static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
-#ifdef CONFIG_PPC_BOOK3E_64
- exception_exit(state->ctx_state);
-#endif
-
if (user_mode(regs))
kuep_unlock();
- /*
- * Book3S exits to user via interrupt_exit_user_prepare(), which does
- * context tracking, which is a cleaner way to handle PREEMPT=y
- * and avoid context entry/exit in e.g., preempt_schedule_irq()),
- * which is likely to be where the core code wants to end up.
- *
- * The above comment explains why we can't do the
- *
- * if (user_mode(regs))
- * user_exit_irqoff();
- *
- * sequence here.
- */
}
static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 381a618b5b5b..1b0e1792ac37 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -235,10 +235,6 @@ static notrace void booke_load_dbcr0(void)
#endif
}
-/* temporary hack for context tracking, removed in later patch */
-#include <linux/sched/debug.h>
-asmlinkage __visible void __sched schedule_user(void);
-
/*
* This should be called after a syscall returns, with r3 the return value
* from the syscall. If this function returns non-zero, the system call
@@ -296,11 +292,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
local_irq_enable();
if (ti_flags & _TIF_NEED_RESCHED) {
-#ifdef CONFIG_PPC_BOOK3E_64
- schedule_user();
-#else
schedule();
-#endif
} else {
/*
* SIGPENDING must restore signal handler function
@@ -375,9 +367,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
BUG_ON(!(regs->msr & MSR_PR));
BUG_ON(!FULL_REGS(regs));
BUG_ON(arch_irq_disabled_regs(regs));
-#ifdef CONFIG_PPC_BOOK3S_64
CT_WARN_ON(ct_state() == CONTEXT_USER);
-#endif
/*
* We don't need to restore AMR on the way back to userspace for KUAP.
@@ -392,11 +382,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
local_irq_enable(); /* returning to user: may enable */
if (ti_flags & _TIF_NEED_RESCHED) {
-#ifdef CONFIG_PPC_BOOK3E_64
- schedule_user();
-#else
schedule();
-#endif
} else {
if (ti_flags & _TIF_SIGPENDING)
ret |= _TIF_RESTOREALL;
@@ -464,7 +450,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
* CT_WARN_ON comes here via program_check_exception,
* so avoid recursion.
*/
- if (IS_ENABLED(CONFIG_BOOKS) && TRAP(regs) != 0x700)
+ if (TRAP(regs) != 0x700)
CT_WARN_ON(ct_state() == CONTEXT_USER);
kuap = kuap_get_and_assert_locked();
--
2.23.0
^ permalink raw reply related
* [PATCH v2 06/11] powerpc/64e/interrupt: reconcile irq soft-mask state in C
From: Nicholas Piggin @ 2021-03-16 10:42 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Scott Wood, Nicholas Piggin
In-Reply-To: <20210316104206.407354-1-npiggin@gmail.com>
Use existing 64s interrupt entry wrapper code to reconcile irqs in C.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 8 +++---
arch/powerpc/kernel/entry_64.S | 18 ++++++-------
arch/powerpc/kernel/exceptions-64e.S | 39 +---------------------------
3 files changed, 13 insertions(+), 52 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 305d7c17a4cf..29b48d083156 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -40,14 +40,14 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
kuap_save_and_lock(regs);
}
#endif
- /*
- * Book3E reconciles irq soft mask in asm
- */
-#ifdef CONFIG_PPC_BOOK3S_64
+
+#ifdef CONFIG_PPC64
if (irq_soft_mask_set_return(IRQS_ALL_DISABLED) == IRQS_ENABLED)
trace_hardirqs_off();
local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
if (user_mode(regs)) {
CT_WARN_ON(ct_state() != CONTEXT_USER);
user_exit_irqoff();
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 555b3d0a3f38..03727308d8cc 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -117,13 +117,12 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
/*
- * RECONCILE_IRQ_STATE without calling trace_hardirqs_off(), which
- * would clobber syscall parameters. Also we always enter with IRQs
- * enabled and nothing pending. system_call_exception() will call
- * trace_hardirqs_off().
- *
- * scv enters with MSR[EE]=1, so don't set PACA_IRQ_HARD_DIS. The
- * entry vector already sets PACAIRQSOFTMASK to IRQS_ALL_DISABLED.
+ * scv enters with MSR[EE]=1 and is immediately considered soft-masked.
+ * The entry vector already sets PACAIRQSOFTMASK to IRQS_ALL_DISABLED,
+ * and interrupts may be masked and pending already.
+ * system_call_exception() will call trace_hardirqs_off() which means
+ * interrupts could already have been blocked before trace_hardirqs_off,
+ * but this is the best we can do.
*/
/* Calling convention has r9 = orig r0, r10 = regs */
@@ -288,9 +287,8 @@ END_BTB_FLUSH_SECTION
std r11,-16(r10) /* "regshere" marker */
/*
- * RECONCILE_IRQ_STATE without calling trace_hardirqs_off(), which
- * would clobber syscall parameters. Also we always enter with IRQs
- * enabled and nothing pending. system_call_exception() will call
+ * We always enter kernel from userspace with irq soft-mask enabled and
+ * nothing pending. system_call_exception() will call
* trace_hardirqs_off().
*/
li r11,IRQS_ALL_DISABLED
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 18be576fc0b3..3c222a97f023 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -409,28 +409,6 @@ exc_##n##_common: \
#define EXCEPTION_COMMON_DBG(n) \
EXCEPTION_COMMON_LVL(n, SPRN_SPRG_DBG_SCRATCH, PACA_EXDBG)
-/*
- * This is meant for exceptions that don't immediately hard-enable. We
- * set a bit in paca->irq_happened to ensure that a subsequent call to
- * arch_local_irq_restore() will properly hard-enable and avoid the
- * fast-path, and then reconcile irq state.
- */
-#define INTS_DISABLE RECONCILE_IRQ_STATE(r3,r4)
-
-/*
- * This is called by exceptions that don't use INTS_DISABLE (that did not
- * touch irq indicators in the PACA). This will restore MSR:EE to it's
- * previous value
- *
- * XXX In the long run, we may want to open-code it in order to separate the
- * load from the wrtee, thus limiting the latency caused by the dependency
- * but at this point, I'll favor code clarity until we have a near to final
- * implementation
- */
-#define INTS_RESTORE_HARD \
- ld r11,_MSR(r1); \
- wrtee r11;
-
/* XXX FIXME: Restore r14/r15 when necessary */
#define BAD_STACK_TRAMPOLINE(n) \
exc_##n##_bad_stack: \
@@ -479,7 +457,6 @@ exc_##n##_bad_stack: \
START_EXCEPTION(label); \
NORMAL_EXCEPTION_PROLOG(trapnum, intnum, PROLOG_ADDITION_MASKABLE)\
EXCEPTION_COMMON(trapnum) \
- INTS_DISABLE; \
ack(r8); \
CHECK_NAPPING(); \
addi r3,r1,STACK_FRAME_OVERHEAD; \
@@ -559,7 +536,6 @@ __end_interrupts:
mfspr r14,SPRN_DEAR
mfspr r15,SPRN_ESR
EXCEPTION_COMMON(0x300)
- INTS_DISABLE
b storage_fault_common
/* Instruction Storage Interrupt */
@@ -569,7 +545,6 @@ __end_interrupts:
li r15,0
mr r14,r10
EXCEPTION_COMMON(0x400)
- INTS_DISABLE
b storage_fault_common
/* External Input Interrupt */
@@ -591,7 +566,6 @@ __end_interrupts:
PROLOG_ADDITION_1REG)
mfspr r14,SPRN_ESR
EXCEPTION_COMMON(0x700)
- INTS_DISABLE
std r14,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
ld r14,PACA_EXGEN+EX_R14(r13)
@@ -610,8 +584,7 @@ __end_interrupts:
beq- 1f
bl load_up_fpu
b fast_interrupt_return
-1: INTS_DISABLE
- addi r3,r1,STACK_FRAME_OVERHEAD
+1: addi r3,r1,STACK_FRAME_OVERHEAD
bl kernel_fp_unavailable_exception
b interrupt_return
@@ -631,7 +604,6 @@ BEGIN_FTR_SECTION
1:
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
- INTS_DISABLE
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_exception
b interrupt_return
@@ -642,7 +614,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
BOOKE_INTERRUPT_ALTIVEC_ASSIST,
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x220)
- INTS_DISABLE
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
@@ -691,7 +662,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
NORMAL_EXCEPTION_PROLOG(0xf20, BOOKE_INTERRUPT_AP_UNAVAIL,
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0xf20)
- INTS_DISABLE
addi r3,r1,STACK_FRAME_OVERHEAD
bl unknown_exception
b interrupt_return
@@ -827,7 +797,6 @@ kernel_dbg_exc:
*/
mfspr r14,SPRN_DBSR
EXCEPTION_COMMON_DBG(0xd08)
- INTS_DISABLE
std r14,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
ld r14,PACA_EXDBG+EX_R14(r13)
@@ -840,7 +809,6 @@ kernel_dbg_exc:
NORMAL_EXCEPTION_PROLOG(0x260, BOOKE_INTERRUPT_PERFORMANCE_MONITOR,
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x260)
- INTS_DISABLE
CHECK_NAPPING()
addi r3,r1,STACK_FRAME_OVERHEAD
bl performance_monitor_exception
@@ -870,7 +838,6 @@ kernel_dbg_exc:
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x2c0)
addi r3,r1,STACK_FRAME_OVERHEAD
- INTS_RESTORE_HARD
bl unknown_exception
b interrupt_return
@@ -891,7 +858,6 @@ kernel_dbg_exc:
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x310)
addi r3,r1,STACK_FRAME_OVERHEAD
- INTS_RESTORE_HARD
bl unknown_exception
b interrupt_return
@@ -901,7 +867,6 @@ kernel_dbg_exc:
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x320)
addi r3,r1,STACK_FRAME_OVERHEAD
- INTS_RESTORE_HARD
bl unknown_exception
b interrupt_return
@@ -911,7 +876,6 @@ kernel_dbg_exc:
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x340)
addi r3,r1,STACK_FRAME_OVERHEAD
- INTS_RESTORE_HARD
bl unknown_exception
b interrupt_return
@@ -991,7 +955,6 @@ alignment_more:
addi r3,r1,STACK_FRAME_OVERHEAD
ld r14,PACA_EXGEN+EX_R14(r13)
ld r15,PACA_EXGEN+EX_R15(r13)
- INTS_RESTORE_HARD
bl alignment_exception
REST_NVGPRS(r1)
b interrupt_return
--
2.23.0
^ permalink raw reply related
* [PATCH v2 05/11] powerpc/64e/interrupt: NMI save irq soft-mask state in C
From: Nicholas Piggin @ 2021-03-16 10:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Scott Wood, Nicholas Piggin
In-Reply-To: <20210316104206.407354-1-npiggin@gmail.com>
64e non-maskable interrupts save the state of the irq soft-mask in
asm. This can be done in C in interrupt wrappers as 64s does.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
I haven't been able to test this with qemu because it doesn't seem
to cause FSL bookE WDT interrupts.
This makes WatchdogException an NMI interrupt, which affects 32-bit
as well (okay, or create a new handler?)
---
arch/powerpc/include/asm/interrupt.h | 32 +++++++++++++++++--------
arch/powerpc/kernel/exceptions-64e.S | 36 ++++------------------------
arch/powerpc/kernel/traps.c | 13 +++++++++-
3 files changed, 38 insertions(+), 43 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 7c633896d758..305d7c17a4cf 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -130,18 +130,32 @@ static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct int
struct interrupt_nmi_state {
#ifdef CONFIG_PPC64
-#ifdef CONFIG_PPC_BOOK3S_64
u8 irq_soft_mask;
u8 irq_happened;
-#endif
u8 ftrace_enabled;
#endif
};
+static inline bool nmi_disables_ftrace(struct pt_regs *regs)
+{
+ /* Allow DEC and PMI to be traced when they are soft-NMI */
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) {
+ if (TRAP(regs) == 0x900)
+ return false;
+ if (TRAP(regs) == 0xf00)
+ return false;
+ }
+ if (IS_ENABLED(CONFIG_PPC_BOOK3E)) {
+ if (TRAP(regs) == 0x260)
+ return false;
+ }
+
+ return true;
+}
+
static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
{
#ifdef CONFIG_PPC64
-#ifdef CONFIG_PPC_BOOK3S_64
state->irq_soft_mask = local_paca->irq_soft_mask;
state->irq_happened = local_paca->irq_happened;
@@ -154,9 +168,8 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte
local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
/* Don't do any per-CPU operations until interrupt state is fixed */
-#endif
- /* Allow DEC and PMI to be traced when they are soft-NMI */
- if (TRAP(regs) != 0x900 && TRAP(regs) != 0xf00 && TRAP(regs) != 0x260) {
+
+ if (nmi_disables_ftrace(regs)) {
state->ftrace_enabled = this_cpu_get_ftrace_enabled();
this_cpu_set_ftrace_enabled(0);
}
@@ -180,16 +193,14 @@ static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct inter
nmi_exit();
#ifdef CONFIG_PPC64
- if (TRAP(regs) != 0x900 && TRAP(regs) != 0xf00 && TRAP(regs) != 0x260)
+ if (nmi_disables_ftrace(regs))
this_cpu_set_ftrace_enabled(state->ftrace_enabled);
-#ifdef CONFIG_PPC_BOOK3S_64
/* Check we didn't change the pending interrupt mask. */
WARN_ON_ONCE((state->irq_happened | PACA_IRQ_HARD_DIS) != local_paca->irq_happened);
local_paca->irq_happened = state->irq_happened;
local_paca->irq_soft_mask = state->irq_soft_mask;
#endif
-#endif
}
/*
@@ -402,6 +413,7 @@ DECLARE_INTERRUPT_HANDLER(SMIException);
DECLARE_INTERRUPT_HANDLER(handle_hmi_exception);
DECLARE_INTERRUPT_HANDLER(unknown_exception);
DECLARE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception);
+DECLARE_INTERRUPT_HANDLER_NMI(unknown_nmi_exception);
DECLARE_INTERRUPT_HANDLER(instruction_breakpoint_exception);
DECLARE_INTERRUPT_HANDLER(RunModeException);
DECLARE_INTERRUPT_HANDLER(single_step_exception);
@@ -425,7 +437,7 @@ DECLARE_INTERRUPT_HANDLER(altivec_assist_exception);
DECLARE_INTERRUPT_HANDLER(CacheLockingException);
DECLARE_INTERRUPT_HANDLER(SPEFloatingPointException);
DECLARE_INTERRUPT_HANDLER(SPEFloatingPointRoundException);
-DECLARE_INTERRUPT_HANDLER(WatchdogException);
+DECLARE_INTERRUPT_HANDLER_NMI(WatchdogException);
DECLARE_INTERRUPT_HANDLER(kernel_bad_stack);
/* slb.c */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 7a2e7be33092..18be576fc0b3 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -63,9 +63,6 @@
ld reg, (SPECIAL_EXC_##name * 8 + SPECIAL_EXC_FRAME_OFFS)(r1)
special_reg_save:
- lbz r9,PACAIRQHAPPENED(r13)
- RECONCILE_IRQ_STATE(r3,r4)
-
/*
* We only need (or have stack space) to save this stuff if
* we interrupted the kernel.
@@ -119,15 +116,11 @@ BEGIN_FTR_SECTION
mtspr SPRN_MAS5,r10
mtspr SPRN_MAS8,r10
END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
- SPECIAL_EXC_STORE(r9,IRQHAPPENED)
-
mfspr r10,SPRN_DEAR
SPECIAL_EXC_STORE(r10,DEAR)
mfspr r10,SPRN_ESR
SPECIAL_EXC_STORE(r10,ESR)
- lbz r10,PACAIRQSOFTMASK(r13)
- SPECIAL_EXC_STORE(r10,SOFTE)
ld r10,_NIP(r1)
SPECIAL_EXC_STORE(r10,CSRR0)
ld r10,_MSR(r1)
@@ -194,27 +187,6 @@ BEGIN_FTR_SECTION
mtspr SPRN_MAS8,r10
END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
- lbz r6,PACAIRQSOFTMASK(r13)
- ld r5,SOFTE(r1)
-
- /* Interrupts had better not already be enabled... */
- tweqi r6,IRQS_ENABLED
-
- andi. r6,r5,IRQS_DISABLED
- bne 1f
-
- TRACE_ENABLE_INTS
- stb r5,PACAIRQSOFTMASK(r13)
-1:
- /*
- * Restore PACAIRQHAPPENED rather than setting it based on
- * the return MSR[EE], since we could have interrupted
- * interrupt replay or other inconsistent transitory
- * states that must remain that way.
- */
- SPECIAL_EXC_LOAD(r10,IRQHAPPENED)
- stb r10,PACAIRQHAPPENED(r13)
-
SPECIAL_EXC_LOAD(r10,DEAR)
mtspr SPRN_DEAR,r10
SPECIAL_EXC_LOAD(r10,ESR)
@@ -566,7 +538,7 @@ __end_interrupts:
bl special_reg_save
CHECK_NAPPING();
addi r3,r1,STACK_FRAME_OVERHEAD
- bl unknown_exception
+ bl unknown_nmi_exception
b ret_from_crit_except
/* Machine Check Interrupt */
@@ -702,7 +674,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#ifdef CONFIG_BOOKE_WDT
bl WatchdogException
#else
- bl unknown_exception
+ bl unknown_nmi_exception
#endif
b ret_from_crit_except
@@ -886,7 +858,7 @@ kernel_dbg_exc:
bl special_reg_save
CHECK_NAPPING();
addi r3,r1,STACK_FRAME_OVERHEAD
- bl unknown_exception
+ bl unknown_nmi_exception
b ret_from_crit_except
/*
@@ -910,7 +882,7 @@ kernel_dbg_exc:
bl special_reg_save
CHECK_NAPPING();
addi r3,r1,STACK_FRAME_OVERHEAD
- bl unknown_exception
+ bl unknown_nmi_exception
b ret_from_crit_except
/* Hypervisor call */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index c74e7727860a..97b5f3d83ff7 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1079,6 +1079,16 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception)
_exception(SIGTRAP, regs, TRAP_UNK, 0);
}
+DEFINE_INTERRUPT_HANDLER_NMI(unknown_nmi_exception)
+{
+ printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
+ regs->nip, regs->msr, regs->trap);
+
+ _exception(SIGTRAP, regs, TRAP_UNK, 0);
+
+ return 0;
+}
+
DEFINE_INTERRUPT_HANDLER(instruction_breakpoint_exception)
{
if (notify_die(DIE_IABR_MATCH, "iabr_match", regs, 5,
@@ -2183,10 +2193,11 @@ void __attribute__ ((weak)) WatchdogHandler(struct pt_regs *regs)
return;
}
-DEFINE_INTERRUPT_HANDLER(WatchdogException) /* XXX NMI? async? */
+DEFINE_INTERRUPT_HANDLER_NMI(WatchdogException)
{
printk (KERN_EMERG "PowerPC Book-E Watchdog Exception\n");
WatchdogHandler(regs);
+ return 0;
}
#endif
--
2.23.0
^ permalink raw reply related
* [PATCH v2 04/11] powerpc/64e/interrupt: use new interrupt return
From: Nicholas Piggin @ 2021-03-16 10:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Scott Wood, Nicholas Piggin
In-Reply-To: <20210316104206.407354-1-npiggin@gmail.com>
Update the new C and asm interrupt return code to account for 64e
specifics, switch over to use it.
The now-unused old ret_from_except code, that was moved to 64e after the
64s conversion, is removed.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/asm-prototypes.h | 2 -
arch/powerpc/include/asm/ppc_asm.h | 20 --
arch/powerpc/kernel/asm-offsets.c | 10 -
arch/powerpc/kernel/exceptions-64e.S | 321 ++--------------------
arch/powerpc/kernel/irq.c | 76 -----
5 files changed, 25 insertions(+), 404 deletions(-)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 939f3c94c8f3..1c7b75834e04 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -77,8 +77,6 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low,
u32 len_high, u32 len_low);
long sys_switch_endian(void);
-notrace unsigned int __check_irq_replay(void);
-void notrace restore_interrupts(void);
/* prom_init (OpenFirmware) */
unsigned long __init prom_init(unsigned long r3, unsigned long r4,
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 8998122fc7e2..d6739d700f0a 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -15,26 +15,6 @@
#define SZL (BITS_PER_LONG/8)
-/*
- * Stuff for accurate CPU time accounting.
- * These macros handle transitions between user and system state
- * in exception entry and exit and accumulate time to the
- * user_time and system_time fields in the paca.
- */
-
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-#define ACCOUNT_CPU_USER_EXIT(ptr, ra, rb)
-#else
-#define ACCOUNT_CPU_USER_EXIT(ptr, ra, rb) \
- MFTB(ra); /* get timebase */ \
- PPC_LL rb, ACCOUNT_STARTTIME(ptr); \
- PPC_STL ra, ACCOUNT_STARTTIME_USER(ptr); \
- subf rb,rb,ra; /* subtract start value */ \
- PPC_LL ra, ACCOUNT_SYSTEM_TIME(ptr); \
- add ra,ra,rb; /* add on to system time */ \
- PPC_STL ra, ACCOUNT_SYSTEM_TIME(ptr)
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
-
/*
* Macros for storing registers into and loading registers from
* exception frames.
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 85ba2b0bc8d8..c880ad18b851 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -282,21 +282,11 @@ int main(void)
OFFSET(PACAHWCPUID, paca_struct, hw_cpu_id);
OFFSET(PACAKEXECSTATE, paca_struct, kexec_state);
OFFSET(PACA_DSCR_DEFAULT, paca_struct, dscr_default);
- OFFSET(ACCOUNT_STARTTIME, paca_struct, accounting.starttime);
- OFFSET(ACCOUNT_STARTTIME_USER, paca_struct, accounting.starttime_user);
- OFFSET(ACCOUNT_USER_TIME, paca_struct, accounting.utime);
- OFFSET(ACCOUNT_SYSTEM_TIME, paca_struct, accounting.stime);
#ifdef CONFIG_PPC_BOOK3E
OFFSET(PACA_TRAP_SAVE, paca_struct, trap_save);
#endif
OFFSET(PACA_SPRG_VDSO, paca_struct, sprg_vdso);
#else /* CONFIG_PPC64 */
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
- OFFSET(ACCOUNT_STARTTIME, thread_info, accounting.starttime);
- OFFSET(ACCOUNT_STARTTIME_USER, thread_info, accounting.starttime_user);
- OFFSET(ACCOUNT_USER_TIME, thread_info, accounting.utime);
- OFFSET(ACCOUNT_SYSTEM_TIME, thread_info, accounting.stime);
-#endif
#endif /* CONFIG_PPC64 */
/* RTAS */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index a7d9ce9f7fdb..7a2e7be33092 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -139,7 +139,8 @@ ret_from_level_except:
ld r3,_MSR(r1)
andi. r3,r3,MSR_PR
beq 1f
- b ret_from_except
+ REST_NVGPRS(r1)
+ b interrupt_return
1:
LOAD_REG_ADDR(r11,extlb_level_exc)
@@ -208,7 +209,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
/*
* Restore PACAIRQHAPPENED rather than setting it based on
* the return MSR[EE], since we could have interrupted
- * __check_irq_replay() or other inconsistent transitory
+ * interrupt replay or other inconsistent transitory
* states that must remain that way.
*/
SPECIAL_EXC_LOAD(r10,IRQHAPPENED)
@@ -511,7 +512,7 @@ exc_##n##_bad_stack: \
CHECK_NAPPING(); \
addi r3,r1,STACK_FRAME_OVERHEAD; \
bl hdlr; \
- b ret_from_except_lite;
+ b interrupt_return
/* This value is used to mark exception frames on the stack. */
.section ".toc","aw"
@@ -623,7 +624,8 @@ __end_interrupts:
addi r3,r1,STACK_FRAME_OVERHEAD
ld r14,PACA_EXGEN+EX_R14(r13)
bl program_check_exception
- b ret_from_except
+ REST_NVGPRS(r1)
+ b interrupt_return
/* Floating Point Unavailable Interrupt */
START_EXCEPTION(fp_unavailable);
@@ -635,11 +637,11 @@ __end_interrupts:
andi. r0,r12,MSR_PR;
beq- 1f
bl load_up_fpu
- b fast_exception_return
+ b fast_interrupt_return
1: INTS_DISABLE
addi r3,r1,STACK_FRAME_OVERHEAD
bl kernel_fp_unavailable_exception
- b ret_from_except
+ b interrupt_return
/* Altivec Unavailable Interrupt */
START_EXCEPTION(altivec_unavailable);
@@ -653,14 +655,14 @@ BEGIN_FTR_SECTION
andi. r0,r12,MSR_PR;
beq- 1f
bl load_up_altivec
- b fast_exception_return
+ b fast_interrupt_return
1:
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
INTS_DISABLE
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_exception
- b ret_from_except
+ b interrupt_return
/* AltiVec Assist */
START_EXCEPTION(altivec_assist);
@@ -674,10 +676,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
BEGIN_FTR_SECTION
bl altivec_assist_exception
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+ REST_NVGPRS(r1)
#else
bl unknown_exception
#endif
- b ret_from_except
+ b interrupt_return
/* Decrementer Interrupt */
@@ -719,7 +722,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
INTS_DISABLE
addi r3,r1,STACK_FRAME_OVERHEAD
bl unknown_exception
- b ret_from_except
+ b interrupt_return
/* Debug exception as a critical interrupt*/
START_EXCEPTION(debug_crit);
@@ -786,7 +789,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
ld r14,PACA_EXCRIT+EX_R14(r13)
ld r15,PACA_EXCRIT+EX_R15(r13)
bl DebugException
- b ret_from_except
+ REST_NVGPRS(r1)
+ b interrupt_return
kernel_dbg_exc:
b . /* NYI */
@@ -857,7 +861,8 @@ kernel_dbg_exc:
ld r14,PACA_EXDBG+EX_R14(r13)
ld r15,PACA_EXDBG+EX_R15(r13)
bl DebugException
- b ret_from_except
+ REST_NVGPRS(r1)
+ b interrupt_return
START_EXCEPTION(perfmon);
NORMAL_EXCEPTION_PROLOG(0x260, BOOKE_INTERRUPT_PERFORMANCE_MONITOR,
@@ -867,7 +872,7 @@ kernel_dbg_exc:
CHECK_NAPPING()
addi r3,r1,STACK_FRAME_OVERHEAD
bl performance_monitor_exception
- b ret_from_except_lite
+ b interrupt_return
/* Doorbell interrupt */
MASKABLE_EXCEPTION(0x280, BOOKE_INTERRUPT_DOORBELL,
@@ -895,7 +900,7 @@ kernel_dbg_exc:
addi r3,r1,STACK_FRAME_OVERHEAD
INTS_RESTORE_HARD
bl unknown_exception
- b ret_from_except
+ b interrupt_return
/* Guest Doorbell critical Interrupt */
START_EXCEPTION(guest_doorbell_crit);
@@ -916,7 +921,7 @@ kernel_dbg_exc:
addi r3,r1,STACK_FRAME_OVERHEAD
INTS_RESTORE_HARD
bl unknown_exception
- b ret_from_except
+ b interrupt_return
/* Embedded Hypervisor priviledged */
START_EXCEPTION(ehpriv);
@@ -926,7 +931,7 @@ kernel_dbg_exc:
addi r3,r1,STACK_FRAME_OVERHEAD
INTS_RESTORE_HARD
bl unknown_exception
- b ret_from_except
+ b interrupt_return
/* LRAT Error interrupt */
START_EXCEPTION(lrat_error);
@@ -936,7 +941,7 @@ kernel_dbg_exc:
addi r3,r1,STACK_FRAME_OVERHEAD
INTS_RESTORE_HARD
bl unknown_exception
- b ret_from_except
+ b interrupt_return
/*
* An interrupt came in while soft-disabled; We mark paca->irq_happened
@@ -998,11 +1003,11 @@ storage_fault_common:
bl do_page_fault
cmpdi r3,0
bne- 1f
- b ret_from_except_lite
+ b interrupt_return
mr r4,r3
addi r3,r1,STACK_FRAME_OVERHEAD
bl __bad_page_fault
- b ret_from_except
+ b interrupt_return
/*
* Alignment exception doesn't fit entirely in the 0x100 bytes so it
@@ -1016,284 +1021,8 @@ alignment_more:
ld r15,PACA_EXGEN+EX_R15(r13)
INTS_RESTORE_HARD
bl alignment_exception
- b ret_from_except
-
- .align 7
-_GLOBAL(ret_from_except)
REST_NVGPRS(r1)
-
-_GLOBAL(ret_from_except_lite)
- /*
- * Disable interrupts so that current_thread_info()->flags
- * can't change between when we test it and when we return
- * from the interrupt.
- */
- wrteei 0
-
- ld r9, PACA_THREAD_INFO(r13)
- ld r3,_MSR(r1)
- ld r10,PACACURRENT(r13)
- ld r4,TI_FLAGS(r9)
- andi. r3,r3,MSR_PR
- beq resume_kernel
- lwz r3,(THREAD+THREAD_DBCR0)(r10)
-
- /* Check current_thread_info()->flags */
- andi. r0,r4,_TIF_USER_WORK_MASK
- bne 1f
- /*
- * Check to see if the dbcr0 register is set up to debug.
- * Use the internal debug mode bit to do this.
- */
- andis. r0,r3,DBCR0_IDM@h
- beq restore
- mfmsr r0
- rlwinm r0,r0,0,~MSR_DE /* Clear MSR.DE */
- mtmsr r0
- mtspr SPRN_DBCR0,r3
- li r10, -1
- mtspr SPRN_DBSR,r10
- b restore
-1: andi. r0,r4,_TIF_NEED_RESCHED
- beq 2f
- bl restore_interrupts
- SCHEDULE_USER
- b ret_from_except_lite
-2:
- /*
- * Use a non volatile GPR to save and restore our thread_info flags
- * across the call to restore_interrupts.
- */
- mr r30,r4
- bl restore_interrupts
- mr r4,r30
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl do_notify_resume
- b ret_from_except
-
-resume_kernel:
- /* check current_thread_info, _TIF_EMULATE_STACK_STORE */
- andis. r8,r4,_TIF_EMULATE_STACK_STORE@h
- beq+ 1f
-
- addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */
-
- ld r3,GPR1(r1)
- subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */
- mr r4,r1 /* src: current exception frame */
- mr r1,r3 /* Reroute the trampoline frame to r1 */
-
- /* Copy from the original to the trampoline. */
- li r5,INT_FRAME_SIZE/8 /* size: INT_FRAME_SIZE */
- li r6,0 /* start offset: 0 */
- mtctr r5
-2: ldx r0,r6,r4
- stdx r0,r6,r3
- addi r6,r6,8
- bdnz 2b
-
- /* Do real store operation to complete stdu */
- ld r5,GPR1(r1)
- std r8,0(r5)
-
- /* Clear _TIF_EMULATE_STACK_STORE flag */
- lis r11,_TIF_EMULATE_STACK_STORE@h
- addi r5,r9,TI_FLAGS
-0: ldarx r4,0,r5
- andc r4,r4,r11
- stdcx. r4,0,r5
- bne- 0b
-1:
-
-#ifdef CONFIG_PREEMPT
- /* Check if we need to preempt */
- andi. r0,r4,_TIF_NEED_RESCHED
- beq+ restore
- /* Check that preempt_count() == 0 and interrupts are enabled */
- lwz r8,TI_PREEMPT(r9)
- cmpwi cr0,r8,0
- bne restore
- ld r0,SOFTE(r1)
- andi. r0,r0,IRQS_DISABLED
- bne restore
-
- /*
- * Here we are preempting the current task. We want to make
- * sure we are soft-disabled first and reconcile irq state.
- */
- RECONCILE_IRQ_STATE(r3,r4)
- bl preempt_schedule_irq
-
- /*
- * arch_local_irq_restore() from preempt_schedule_irq above may
- * enable hard interrupt but we really should disable interrupts
- * when we return from the interrupt, and so that we don't get
- * interrupted after loading SRR0/1.
- */
- wrteei 0
-#endif /* CONFIG_PREEMPT */
-
-restore:
- /*
- * This is the main kernel exit path. First we check if we
- * are about to re-enable interrupts
- */
- ld r5,SOFTE(r1)
- lbz r6,PACAIRQSOFTMASK(r13)
- andi. r5,r5,IRQS_DISABLED
- bne .Lrestore_irq_off
-
- /* We are enabling, were we already enabled ? Yes, just return */
- andi. r6,r6,IRQS_DISABLED
- beq cr0,fast_exception_return
-
- /*
- * We are about to soft-enable interrupts (we are hard disabled
- * at this point). We check if there's anything that needs to
- * be replayed first.
- */
- lbz r0,PACAIRQHAPPENED(r13)
- cmpwi cr0,r0,0
- bne- .Lrestore_check_irq_replay
-
- /*
- * Get here when nothing happened while soft-disabled, just
- * soft-enable and move-on. We will hard-enable as a side
- * effect of rfi
- */
-.Lrestore_no_replay:
- TRACE_ENABLE_INTS
- li r0,IRQS_ENABLED
- stb r0,PACAIRQSOFTMASK(r13);
-
-/* This is the return from load_up_fpu fast path which could do with
- * less GPR restores in fact, but for now we have a single return path
- */
-fast_exception_return:
- wrteei 0
-1: mr r0,r13
- ld r10,_MSR(r1)
- REST_4GPRS(2, r1)
- andi. r6,r10,MSR_PR
- REST_2GPRS(6, r1)
- beq 1f
- ACCOUNT_CPU_USER_EXIT(r13, r10, r11)
- ld r0,GPR13(r1)
-
-1: stdcx. r0,0,r1 /* to clear the reservation */
-
- ld r8,_CCR(r1)
- ld r9,_LINK(r1)
- ld r10,_CTR(r1)
- ld r11,_XER(r1)
- mtcr r8
- mtlr r9
- mtctr r10
- mtxer r11
- REST_2GPRS(8, r1)
- ld r10,GPR10(r1)
- ld r11,GPR11(r1)
- ld r12,GPR12(r1)
- mtspr SPRN_SPRG_GEN_SCRATCH,r0
-
- std r10,PACA_EXGEN+EX_R10(r13);
- std r11,PACA_EXGEN+EX_R11(r13);
- ld r10,_NIP(r1)
- ld r11,_MSR(r1)
- ld r0,GPR0(r1)
- ld r1,GPR1(r1)
- mtspr SPRN_SRR0,r10
- mtspr SPRN_SRR1,r11
- ld r10,PACA_EXGEN+EX_R10(r13)
- ld r11,PACA_EXGEN+EX_R11(r13)
- mfspr r13,SPRN_SPRG_GEN_SCRATCH
- rfi
-
- /*
- * We are returning to a context with interrupts soft disabled.
- *
- * However, we may also about to hard enable, so we need to
- * make sure that in this case, we also clear PACA_IRQ_HARD_DIS
- * or that bit can get out of sync and bad things will happen
- */
-.Lrestore_irq_off:
- ld r3,_MSR(r1)
- lbz r7,PACAIRQHAPPENED(r13)
- andi. r0,r3,MSR_EE
- beq 1f
- rlwinm r7,r7,0,~PACA_IRQ_HARD_DIS
- stb r7,PACAIRQHAPPENED(r13)
-1:
-#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG)
- /* The interrupt should not have soft enabled. */
- lbz r7,PACAIRQSOFTMASK(r13)
-1: tdeqi r7,IRQS_ENABLED
- EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
-#endif
- b fast_exception_return
-
- /*
- * Something did happen, check if a re-emit is needed
- * (this also clears paca->irq_happened)
- */
-.Lrestore_check_irq_replay:
- /* XXX: We could implement a fast path here where we check
- * for irq_happened being just 0x01, in which case we can
- * clear it and return. That means that we would potentially
- * miss a decrementer having wrapped all the way around.
- *
- * Still, this might be useful for things like hash_page
- */
- bl __check_irq_replay
- cmpwi cr0,r3,0
- beq .Lrestore_no_replay
-
- /*
- * We need to re-emit an interrupt. We do so by re-using our
- * existing exception frame. We first change the trap value,
- * but we need to ensure we preserve the low nibble of it
- */
- ld r4,_TRAP(r1)
- clrldi r4,r4,60
- or r4,r4,r3
- std r4,_TRAP(r1)
-
- /*
- * PACA_IRQ_HARD_DIS won't always be set here, so set it now
- * to reconcile the IRQ state. Tracing is already accounted for.
- */
- lbz r4,PACAIRQHAPPENED(r13)
- ori r4,r4,PACA_IRQ_HARD_DIS
- stb r4,PACAIRQHAPPENED(r13)
-
- /*
- * Then find the right handler and call it. Interrupts are
- * still soft-disabled and we keep them that way.
- */
- cmpwi cr0,r3,0x500
- bne 1f
- addi r3,r1,STACK_FRAME_OVERHEAD;
- bl do_IRQ
- b ret_from_except
-1: cmpwi cr0,r3,0x900
- bne 1f
- addi r3,r1,STACK_FRAME_OVERHEAD;
- bl timer_interrupt
- b ret_from_except
-#ifdef CONFIG_PPC_DOORBELL
-1:
- cmpwi cr0,r3,0x280
- bne 1f
- addi r3,r1,STACK_FRAME_OVERHEAD;
- bl doorbell_exception
-#endif /* CONFIG_PPC_DOORBELL */
-1: b ret_from_except /* What else to do here ? */
-
-_ASM_NOKPROBE_SYMBOL(ret_from_except);
-_ASM_NOKPROBE_SYMBOL(ret_from_except_lite);
-_ASM_NOKPROBE_SYMBOL(resume_kernel);
-_ASM_NOKPROBE_SYMBOL(restore);
-_ASM_NOKPROBE_SYMBOL(fast_exception_return);
+ b interrupt_return
/*
* Trampolines used when spotting a bad kernel stack pointer in
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 5b72abbff96c..08a747b92735 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -104,82 +104,6 @@ static inline notrace unsigned long get_irq_happened(void)
return happened;
}
-#ifdef CONFIG_PPC_BOOK3E
-
-/* This is called whenever we are re-enabling interrupts
- * and returns either 0 (nothing to do) or 500/900/280 if
- * there's an EE, DEC or DBELL to generate.
- *
- * This is called in two contexts: From arch_local_irq_restore()
- * before soft-enabling interrupts, and from the exception exit
- * path when returning from an interrupt from a soft-disabled to
- * a soft enabled context. In both case we have interrupts hard
- * disabled.
- *
- * We take care of only clearing the bits we handled in the
- * PACA irq_happened field since we can only re-emit one at a
- * time and we don't want to "lose" one.
- */
-notrace unsigned int __check_irq_replay(void)
-{
- /*
- * We use local_paca rather than get_paca() to avoid all
- * the debug_smp_processor_id() business in this low level
- * function
- */
- unsigned char happened = local_paca->irq_happened;
-
- /*
- * We are responding to the next interrupt, so interrupt-off
- * latencies should be reset here.
- */
- trace_hardirqs_on();
- trace_hardirqs_off();
-
- if (happened & PACA_IRQ_DEC) {
- local_paca->irq_happened &= ~PACA_IRQ_DEC;
- return 0x900;
- }
-
- if (happened & PACA_IRQ_EE) {
- local_paca->irq_happened &= ~PACA_IRQ_EE;
- return 0x500;
- }
-
- if (happened & PACA_IRQ_DBELL) {
- local_paca->irq_happened &= ~PACA_IRQ_DBELL;
- return 0x280;
- }
-
- if (happened & PACA_IRQ_HARD_DIS)
- local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
-
- /* There should be nothing left ! */
- BUG_ON(local_paca->irq_happened != 0);
-
- return 0;
-}
-
-/*
- * This is specifically called by assembly code to re-enable interrupts
- * if they are currently disabled. This is typically called before
- * schedule() or do_signal() when returning to userspace. We do it
- * in C to avoid the burden of dealing with lockdep etc...
- *
- * NOTE: This is called with interrupts hard disabled but not marked
- * as such in paca->irq_happened, so we need to resync this.
- */
-void notrace restore_interrupts(void)
-{
- if (irqs_disabled()) {
- local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
- local_irq_enable();
- } else
- __hard_irq_enable();
-}
-
-#endif /* CONFIG_PPC_BOOK3E */
-
void replay_soft_interrupts(void)
{
struct pt_regs regs;
--
2.23.0
^ permalink raw reply related
* [PATCH v2 03/11] powerpc/interrupt: update common interrupt code for
From: Nicholas Piggin @ 2021-03-16 10:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Scott Wood, Nicholas Piggin
In-Reply-To: <20210316104206.407354-1-npiggin@gmail.com>
This makes adjustments to 64-bit asm and common C interrupt return
code to be usable by the 64e subarchitecture.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/entry_64.S | 9 +++++++--
arch/powerpc/kernel/interrupt.c | 35 ++++++++++++++++++++-------------
2 files changed, 28 insertions(+), 16 deletions(-)
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 853534b2ae2e..555b3d0a3f38 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -632,7 +632,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
addi r1,r1,SWITCH_FRAME_SIZE
blr
-#ifdef CONFIG_PPC_BOOK3S
/*
* If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not
* touched, no exit work created, then this can be used.
@@ -644,6 +643,7 @@ _ASM_NOKPROBE_SYMBOL(fast_interrupt_return)
kuap_check_amr r3, r4
ld r5,_MSR(r1)
andi. r0,r5,MSR_PR
+#ifdef CONFIG_PPC_BOOK3S
bne .Lfast_user_interrupt_return_amr
kuap_kernel_restore r3, r4
andi. r0,r5,MSR_RI
@@ -652,6 +652,10 @@ _ASM_NOKPROBE_SYMBOL(fast_interrupt_return)
addi r3,r1,STACK_FRAME_OVERHEAD
bl unrecoverable_exception
b . /* should not get here */
+#else
+ bne .Lfast_user_interrupt_return
+ b .Lfast_kernel_interrupt_return
+#endif
.balign IFETCH_ALIGN_BYTES
.globl interrupt_return
@@ -665,8 +669,10 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return)
cmpdi r3,0
bne- .Lrestore_nvgprs
+#ifdef CONFIG_PPC_BOOK3S
.Lfast_user_interrupt_return_amr:
kuap_user_restore r3, r4
+#endif
.Lfast_user_interrupt_return:
ld r11,_NIP(r1)
ld r12,_MSR(r1)
@@ -775,7 +781,6 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
RFI_TO_KERNEL
b . /* prevent speculative execution */
-#endif /* CONFIG_PPC_BOOK3S */
#ifdef CONFIG_PPC_RTAS
/*
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index fbabb49888d3..381a618b5b5b 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -235,6 +235,10 @@ static notrace void booke_load_dbcr0(void)
#endif
}
+/* temporary hack for context tracking, removed in later patch */
+#include <linux/sched/debug.h>
+asmlinkage __visible void __sched schedule_user(void);
+
/*
* This should be called after a syscall returns, with r3 the return value
* from the syscall. If this function returns non-zero, the system call
@@ -292,7 +296,11 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
local_irq_enable();
if (ti_flags & _TIF_NEED_RESCHED) {
+#ifdef CONFIG_PPC_BOOK3E_64
+ schedule_user();
+#else
schedule();
+#endif
} else {
/*
* SIGPENDING must restore signal handler function
@@ -349,18 +357,13 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
account_cpu_user_exit();
-#ifndef CONFIG_PPC_BOOK3E_64 /* BOOK3E not using this */
- /*
- * We do this at the end so that we do context switch with KERNEL AMR
- */
+ /* Restore user access locks last */
kuap_user_restore(regs);
-#endif
kuep_unlock();
return ret;
}
-#ifndef CONFIG_PPC_BOOK3E_64 /* BOOK3E not yet using this */
notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr)
{
unsigned long ti_flags;
@@ -372,7 +375,9 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
BUG_ON(!(regs->msr & MSR_PR));
BUG_ON(!FULL_REGS(regs));
BUG_ON(arch_irq_disabled_regs(regs));
+#ifdef CONFIG_PPC_BOOK3S_64
CT_WARN_ON(ct_state() == CONTEXT_USER);
+#endif
/*
* We don't need to restore AMR on the way back to userspace for KUAP.
@@ -387,7 +392,11 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
local_irq_enable(); /* returning to user: may enable */
if (ti_flags & _TIF_NEED_RESCHED) {
+#ifdef CONFIG_PPC_BOOK3E_64
+ schedule_user();
+#else
schedule();
+#endif
} else {
if (ti_flags & _TIF_SIGPENDING)
ret |= _TIF_RESTOREALL;
@@ -432,10 +441,9 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
account_cpu_user_exit();
- /*
- * We do this at the end so that we do context switch with KERNEL AMR
- */
+ /* Restore user access locks last */
kuap_user_restore(regs);
+
return ret;
}
@@ -456,7 +464,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
* CT_WARN_ON comes here via program_check_exception,
* so avoid recursion.
*/
- if (TRAP(regs) != 0x700)
+ if (IS_ENABLED(CONFIG_BOOKS) && TRAP(regs) != 0x700)
CT_WARN_ON(ct_state() == CONTEXT_USER);
kuap = kuap_get_and_assert_locked();
@@ -497,12 +505,11 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
#endif
/*
- * Don't want to mfspr(SPRN_AMR) here, because this comes after mtmsr,
- * which would cause Read-After-Write stalls. Hence, we take the AMR
- * value from the check above.
+ * 64s does not want to mfspr(SPRN_AMR) here, because this comes after
+ * mtmsr, which would cause Read-After-Write stalls. Hence, take the
+ * AMR value from the check above.
*/
kuap_kernel_restore(regs, kuap);
return ret;
}
-#endif
--
2.23.0
^ permalink raw reply related
* [PATCH v2 02/11] powerpc/64e/interrupt: always save nvgprs on interrupt
From: Nicholas Piggin @ 2021-03-16 10:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Scott Wood, Nicholas Piggin
In-Reply-To: <20210316104206.407354-1-npiggin@gmail.com>
In order to use the C interrupt return, nvgprs must always be saved.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/ptrace.h | 9 +--------
arch/powerpc/kernel/entry_64.S | 13 -------------
arch/powerpc/kernel/exceptions-64e.S | 27 +++------------------------
3 files changed, 4 insertions(+), 45 deletions(-)
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 1aca5fe79285..c5b3669918f4 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -186,18 +186,11 @@ static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
((struct pt_regs *)((unsigned long)task_stack_page(current) + THREAD_SIZE) - 1)
#ifdef __powerpc64__
-#ifdef CONFIG_PPC_BOOK3S
#define TRAP_FLAGS_MASK 0x10
#define TRAP(regs) ((regs)->trap & ~TRAP_FLAGS_MASK)
#define FULL_REGS(regs) true
#define SET_FULL_REGS(regs) do { } while (0)
-#else
-#define TRAP_FLAGS_MASK 0x11
-#define TRAP(regs) ((regs)->trap & ~TRAP_FLAGS_MASK)
-#define FULL_REGS(regs) (((regs)->trap & 1) == 0)
-#define SET_FULL_REGS(regs) ((regs)->trap &= ~1)
-#endif
-#define CHECK_FULL_REGS(regs) BUG_ON(!FULL_REGS(regs))
+#define CHECK_FULL_REGS(regs) do { } while (0)
#define NV_REG_POISON 0xdeadbeefdeadbeefUL
#else
/*
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 6c4d9e276c4d..853534b2ae2e 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -417,19 +417,6 @@ _GLOBAL(ret_from_kernel_thread)
li r3,0
b .Lsyscall_exit
-#ifdef CONFIG_PPC_BOOK3E
-/* Save non-volatile GPRs, if not already saved. */
-_GLOBAL(save_nvgprs)
- ld r11,_TRAP(r1)
- andi. r0,r11,1
- beqlr-
- SAVE_NVGPRS(r1)
- clrrdi r0,r11,1
- std r0,_TRAP(r1)
- blr
-_ASM_NOKPROBE_SYMBOL(save_nvgprs);
-#endif
-
#ifdef CONFIG_PPC_BOOK3S_64
#define FLUSH_COUNT_CACHE \
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index e8eb9992a270..a7d9ce9f7fdb 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -417,14 +417,15 @@ exc_##n##_common: \
std r6,_LINK(r1); \
std r7,_CTR(r1); \
std r8,_XER(r1); \
- li r3,(n)+1; /* indicate partial regs in trap */ \
+ li r3,(n); /* regs.trap vector */ \
std r9,0(r1); /* store stack frame back link */ \
std r10,_CCR(r1); /* store orig CR in stackframe */ \
std r9,GPR1(r1); /* store stack frame back link */ \
std r11,SOFTE(r1); /* and save it to stackframe */ \
std r12,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */ \
std r3,_TRAP(r1); /* set trap number */ \
- std r0,RESULT(r1); /* clear regs->result */
+ std r0,RESULT(r1); /* clear regs->result */ \
+ SAVE_NVGPRS(r1);
#define EXCEPTION_COMMON(n) \
EXCEPTION_COMMON_LVL(n, SPRN_SPRG_GEN_SCRATCH, PACA_EXGEN)
@@ -561,7 +562,6 @@ __end_interrupts:
CRIT_EXCEPTION_PROLOG(0x100, BOOKE_INTERRUPT_CRITICAL,
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON_CRIT(0x100)
- bl save_nvgprs
bl special_reg_save
CHECK_NAPPING();
addi r3,r1,STACK_FRAME_OVERHEAD
@@ -573,7 +573,6 @@ __end_interrupts:
MC_EXCEPTION_PROLOG(0x000, BOOKE_INTERRUPT_MACHINE_CHECK,
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON_MC(0x000)
- bl save_nvgprs
bl special_reg_save
CHECK_NAPPING();
addi r3,r1,STACK_FRAME_OVERHEAD
@@ -623,7 +622,6 @@ __end_interrupts:
std r14,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
ld r14,PACA_EXGEN+EX_R14(r13)
- bl save_nvgprs
bl program_check_exception
b ret_from_except
@@ -639,7 +637,6 @@ __end_interrupts:
bl load_up_fpu
b fast_exception_return
1: INTS_DISABLE
- bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
bl kernel_fp_unavailable_exception
b ret_from_except
@@ -661,7 +658,6 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
INTS_DISABLE
- bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_exception
b ret_from_except
@@ -673,7 +669,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x220)
INTS_DISABLE
- bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
@@ -698,7 +693,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
CRIT_EXCEPTION_PROLOG(0x9f0, BOOKE_INTERRUPT_WATCHDOG,
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON_CRIT(0x9f0)
- bl save_nvgprs
bl special_reg_save
CHECK_NAPPING();
addi r3,r1,STACK_FRAME_OVERHEAD
@@ -723,7 +717,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0xf20)
INTS_DISABLE
- bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
bl unknown_exception
b ret_from_except
@@ -792,7 +785,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
addi r3,r1,STACK_FRAME_OVERHEAD
ld r14,PACA_EXCRIT+EX_R14(r13)
ld r15,PACA_EXCRIT+EX_R15(r13)
- bl save_nvgprs
bl DebugException
b ret_from_except
@@ -864,7 +856,6 @@ kernel_dbg_exc:
addi r3,r1,STACK_FRAME_OVERHEAD
ld r14,PACA_EXDBG+EX_R14(r13)
ld r15,PACA_EXDBG+EX_R15(r13)
- bl save_nvgprs
bl DebugException
b ret_from_except
@@ -887,7 +878,6 @@ kernel_dbg_exc:
CRIT_EXCEPTION_PROLOG(0x2a0, BOOKE_INTERRUPT_DOORBELL_CRITICAL,
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON_CRIT(0x2a0)
- bl save_nvgprs
bl special_reg_save
CHECK_NAPPING();
addi r3,r1,STACK_FRAME_OVERHEAD
@@ -903,7 +893,6 @@ kernel_dbg_exc:
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x2c0)
addi r3,r1,STACK_FRAME_OVERHEAD
- bl save_nvgprs
INTS_RESTORE_HARD
bl unknown_exception
b ret_from_except
@@ -913,7 +902,6 @@ kernel_dbg_exc:
CRIT_EXCEPTION_PROLOG(0x2e0, BOOKE_INTERRUPT_GUEST_DBELL_CRIT,
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON_CRIT(0x2e0)
- bl save_nvgprs
bl special_reg_save
CHECK_NAPPING();
addi r3,r1,STACK_FRAME_OVERHEAD
@@ -926,7 +914,6 @@ kernel_dbg_exc:
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x310)
addi r3,r1,STACK_FRAME_OVERHEAD
- bl save_nvgprs
INTS_RESTORE_HARD
bl unknown_exception
b ret_from_except
@@ -937,7 +924,6 @@ kernel_dbg_exc:
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x320)
addi r3,r1,STACK_FRAME_OVERHEAD
- bl save_nvgprs
INTS_RESTORE_HARD
bl unknown_exception
b ret_from_except
@@ -948,7 +934,6 @@ kernel_dbg_exc:
PROLOG_ADDITION_NONE)
EXCEPTION_COMMON(0x340)
addi r3,r1,STACK_FRAME_OVERHEAD
- bl save_nvgprs
INTS_RESTORE_HARD
bl unknown_exception
b ret_from_except
@@ -1014,7 +999,6 @@ storage_fault_common:
cmpdi r3,0
bne- 1f
b ret_from_except_lite
-1: bl save_nvgprs
mr r4,r3
addi r3,r1,STACK_FRAME_OVERHEAD
bl __bad_page_fault
@@ -1030,16 +1014,12 @@ alignment_more:
addi r3,r1,STACK_FRAME_OVERHEAD
ld r14,PACA_EXGEN+EX_R14(r13)
ld r15,PACA_EXGEN+EX_R15(r13)
- bl save_nvgprs
INTS_RESTORE_HARD
bl alignment_exception
b ret_from_except
.align 7
_GLOBAL(ret_from_except)
- ld r11,_TRAP(r1)
- andi. r0,r11,1
- bne ret_from_except_lite
REST_NVGPRS(r1)
_GLOBAL(ret_from_except_lite)
@@ -1080,7 +1060,6 @@ _GLOBAL(ret_from_except_lite)
SCHEDULE_USER
b ret_from_except_lite
2:
- bl save_nvgprs
/*
* Use a non volatile GPR to save and restore our thread_info flags
* across the call to restore_interrupts.
--
2.23.0
^ permalink raw reply related
* [PATCH v2 01/11] powerpc/syscall: switch user_exit_irqoff and trace_hardirqs_off order
From: Nicholas Piggin @ 2021-03-16 10:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Scott Wood, Nicholas Piggin
In-Reply-To: <20210316104206.407354-1-npiggin@gmail.com>
user_exit_irqoff() -> __context_tracking_exit -> vtime_user_exit
warns in __seqprop_assert due to lockdep thinking preemption is enabled
because trace_hardirqs_off() has not yet been called.
Switch the order of these two calls, which matches their ordering in
interrupt_enter_prepare.
Fixes: 5f0b6ac3905f ("powerpc/64/syscall: Reconcile interrupts")
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/interrupt.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index c4dd4b8f9cfa..fbabb49888d3 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -43,11 +43,11 @@ notrace long system_call_exception(long r3, long r4, long r5,
if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
+ trace_hardirqs_off(); /* finish reconciling */
+
CT_WARN_ON(ct_state() == CONTEXT_KERNEL);
user_exit_irqoff();
- trace_hardirqs_off(); /* finish reconciling */
-
if (!IS_ENABLED(CONFIG_BOOKE) && !IS_ENABLED(CONFIG_40x))
BUG_ON(!(regs->msr & MSR_RI));
BUG_ON(!(regs->msr & MSR_PR));
--
2.23.0
^ permalink raw reply related
* [PATCH v2 00/11] Move 64e to new interrupt return code
From: Nicholas Piggin @ 2021-03-16 10:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Scott Wood, Nicholas Piggin
Since RFC:
- Rebased on Christophe's v3 ppc32 conversion
- Fixed up small details, adds some powerpc-wide cleanups at the end.
Since v1:
- Christophe's review comments accounted for:
- Split common code interrupt changes for 64e from 64e conversion.
- Removed unnecessary ifdef additions from common interrupt code.
- Keep interrupt return context tracking debug check for 64e when
it switches to new context tracing.
- __bad_page_fault is made static in page fault cleanup.
- CPU time accounting asm and asm offsets can be removed with 64e
conversion.
Tested on qemu only (QEMU e500), which is not ideal for interrupt
handling particularly the critical interrupts which I don't know
whether it can generate.
Thanks,
Nick
Nicholas Piggin (11):
powerpc/syscall: switch user_exit_irqoff and trace_hardirqs_off order
powerpc/64e/interrupt: always save nvgprs on interrupt
powerpc/interrupt: update common interrupt code for 64e
powerpc/64e/interrupt: use new interrupt return
powerpc/64e/interrupt: NMI save irq soft-mask state in C
powerpc/64e/interrupt: reconcile irq soft-mask state in C
powerpc/64e/interrupt: Use new interrupt context tracking scheme
powerpc/64e/interrupt: handle bad_page_fault in C
powerpc: clean up do_page_fault
powerpc: remove partial register save logic
powerpc: move norestart trap flag to bit 0
arch/powerpc/include/asm/asm-prototypes.h | 2 -
arch/powerpc/include/asm/bug.h | 5 +-
arch/powerpc/include/asm/interrupt.h | 66 ++--
arch/powerpc/include/asm/ppc_asm.h | 20 -
arch/powerpc/include/asm/ptrace.h | 39 +-
arch/powerpc/kernel/align.c | 6 -
arch/powerpc/kernel/asm-offsets.c | 10 -
arch/powerpc/kernel/entry_64.S | 40 +-
arch/powerpc/kernel/exceptions-64e.S | 425 ++--------------------
arch/powerpc/kernel/interrupt.c | 26 +-
arch/powerpc/kernel/irq.c | 76 ----
arch/powerpc/kernel/process.c | 12 -
arch/powerpc/kernel/ptrace/ptrace-view.c | 21 --
arch/powerpc/kernel/ptrace/ptrace.c | 2 -
arch/powerpc/kernel/ptrace/ptrace32.c | 4 -
arch/powerpc/kernel/signal_32.c | 3 -
arch/powerpc/kernel/signal_64.c | 2 -
arch/powerpc/kernel/traps.c | 14 +-
arch/powerpc/lib/sstep.c | 4 -
arch/powerpc/mm/book3s64/hash_utils.c | 16 +-
arch/powerpc/mm/fault.c | 30 +-
arch/powerpc/xmon/xmon.c | 23 +-
22 files changed, 126 insertions(+), 720 deletions(-)
--
2.23.0
^ permalink raw reply
* [PATCH] ASoC: fsl_spdif: use snd_ctl_boolean_mono_info
From: Shengjiu Wang @ 2021-03-16 9:42 UTC (permalink / raw)
To: timur, nicoleotsuka, Xiubo.Lee, festevam, lgirdwood, broonie,
perex, tiwai, alsa-devel, linuxppc-dev, linux-kernel
From: Viorel Suman <viorel.suman@nxp.com>
Remove redundant code and use snd_ctl_boolean_mono_info
instead.
Signed-off-by: Viorel Suman <viorel.suman@nxp.com>
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
---
sound/soc/fsl/fsl_spdif.c | 30 +++---------------------------
1 file changed, 3 insertions(+), 27 deletions(-)
diff --git a/sound/soc/fsl/fsl_spdif.c b/sound/soc/fsl/fsl_spdif.c
index 174e558224d8..1cd3441d1c03 100644
--- a/sound/soc/fsl/fsl_spdif.c
+++ b/sound/soc/fsl/fsl_spdif.c
@@ -801,18 +801,6 @@ static int fsl_spdif_qget(struct snd_kcontrol *kcontrol,
return ret;
}
-/* Valid bit information */
-static int fsl_spdif_vbit_info(struct snd_kcontrol *kcontrol,
- struct snd_ctl_elem_info *uinfo)
-{
- uinfo->type = SNDRV_CTL_ELEM_TYPE_BOOLEAN;
- uinfo->count = 1;
- uinfo->value.integer.min = 0;
- uinfo->value.integer.max = 1;
-
- return 0;
-}
-
/* Get valid good bit from interrupt status register */
static int fsl_spdif_rx_vbit_get(struct snd_kcontrol *kcontrol,
struct snd_ctl_elem_value *ucontrol)
@@ -925,18 +913,6 @@ static int fsl_spdif_rxrate_get(struct snd_kcontrol *kcontrol,
return 0;
}
-/* User bit sync mode info */
-static int fsl_spdif_usync_info(struct snd_kcontrol *kcontrol,
- struct snd_ctl_elem_info *uinfo)
-{
- uinfo->type = SNDRV_CTL_ELEM_TYPE_BOOLEAN;
- uinfo->count = 1;
- uinfo->value.integer.min = 0;
- uinfo->value.integer.max = 1;
-
- return 0;
-}
-
/*
* User bit sync mode:
* 1 CD User channel subcode
@@ -1018,7 +994,7 @@ static struct snd_kcontrol_new fsl_spdif_ctrls[] = {
.name = "IEC958 RX V-Bit Errors",
.access = SNDRV_CTL_ELEM_ACCESS_READ |
SNDRV_CTL_ELEM_ACCESS_VOLATILE,
- .info = fsl_spdif_vbit_info,
+ .info = snd_ctl_boolean_mono_info,
.get = fsl_spdif_rx_vbit_get,
},
{
@@ -1027,7 +1003,7 @@ static struct snd_kcontrol_new fsl_spdif_ctrls[] = {
.access = SNDRV_CTL_ELEM_ACCESS_READ |
SNDRV_CTL_ELEM_ACCESS_WRITE |
SNDRV_CTL_ELEM_ACCESS_VOLATILE,
- .info = fsl_spdif_vbit_info,
+ .info = snd_ctl_boolean_mono_info,
.get = fsl_spdif_tx_vbit_get,
.put = fsl_spdif_tx_vbit_put,
},
@@ -1047,7 +1023,7 @@ static struct snd_kcontrol_new fsl_spdif_ctrls[] = {
.access = SNDRV_CTL_ELEM_ACCESS_READ |
SNDRV_CTL_ELEM_ACCESS_WRITE |
SNDRV_CTL_ELEM_ACCESS_VOLATILE,
- .info = fsl_spdif_usync_info,
+ .info = snd_ctl_boolean_mono_info,
.get = fsl_spdif_usync_get,
.put = fsl_spdif_usync_put,
},
--
2.27.0
^ permalink raw reply related
* [PATCH] ASoC: fsl_sai: remove reset code from dai_probe
From: Shengjiu Wang @ 2021-03-16 9:27 UTC (permalink / raw)
To: timur, nicoleotsuka, Xiubo.Lee, festevam, lgirdwood, broonie,
perex, tiwai, alsa-devel, linuxppc-dev, linux-kernel
From: Viorel Suman <viorel.suman@nxp.com>
SAI software reset is done in runtime resume,
there is no need to do it in fsl_sai_dai_probe.
Signed-off-by: Viorel Suman <viorel.suman@nxp.com>
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
---
sound/soc/fsl/fsl_sai.c | 7 -------
1 file changed, 7 deletions(-)
diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index 6ef2ce348232..9e7893f91882 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -711,13 +711,6 @@ static int fsl_sai_dai_probe(struct snd_soc_dai *cpu_dai)
struct fsl_sai *sai = dev_get_drvdata(cpu_dai->dev);
unsigned int ofs = sai->soc_data->reg_offset;
- /* Software Reset for both Tx and Rx */
- regmap_write(sai->regmap, FSL_SAI_TCSR(ofs), FSL_SAI_CSR_SR);
- regmap_write(sai->regmap, FSL_SAI_RCSR(ofs), FSL_SAI_CSR_SR);
- /* Clear SR bit to finish the reset */
- regmap_write(sai->regmap, FSL_SAI_TCSR(ofs), 0);
- regmap_write(sai->regmap, FSL_SAI_RCSR(ofs), 0);
-
regmap_update_bits(sai->regmap, FSL_SAI_TCR1(ofs),
FSL_SAI_CR1_RFW_MASK(sai->soc_data->fifo_depth),
sai->soc_data->fifo_depth - FSL_SAI_MAXBURST_TX);
--
2.27.0
^ permalink raw reply related
* RE: [PATCH] powerpc/vdso32: Add missing _restgpr_31_x to fix build failure
From: David Laight @ 2021-03-16 9:35 UTC (permalink / raw)
To: 'Segher Boessenkool'
Cc: Paul Mackerras, linuxppc-dev@lists.ozlabs.org,
linux-kernel@vger.kernel.org, 'Rasmus Villemoes'
In-Reply-To: <20210315235947.GD16691@gate.crashing.org>
From: Segher Boessenkool
> Sent: 16 March 2021 00:00
...
> > Although you may need to disable loop unrolling (often dubious at best)
> > and either force or disable some function inlining.
>
> The cases where GCC does loop unrolling at -O2 always help quite a lot.
> Or, do you have a counter-example? We'd love to see one.
The real problem with loop unrolling is that quite often a modern
out-of-order superscaler processor actually has 'spare' execution
cycles where the loop control can be done 'for free'.
Sometimes you do need to unroll (or interleave) a couple of
times to get enough spare execution cycles.
But the unrolled loop has to read a lot more code into cache
- so unless the code is 'hot cache' (that is usually arranged
for benchmarking) those delays apply as well.
The larger code footprint also displaces other code.
My real annoyance with gcc is unrolling (and vectorizing)
loops that I know are never executed as many times as even one
copy of the unrolled loop.
As an example intel (ivy bridge onwards) cpu execute the
following code (the middle of the ip checksum) at 8 bytes/clock.
(Limited by the carry flag.)
It just doesn't need any further unrolling.
+ "10: jecxz 20f\n"
+ " adc (%[buff], %[len]), %[sum_0]\n"
+ " adc 8(%[buff], %[len]), %[sum_1]\n"
+ " lea 32(%[len]), %[len_tmp]\n"
+ " adc 16(%[buff], %[len]), %[sum_0]\n"
+ " adc 24(%[buff], %[len]), %[sum_1]\n"
+ " mov %[len_tmp], %[len]\n"
+ " jmp 10b\n"
Annoyingly that loop is slow on my 8-core atom.
The existing code only does 4 bytes/clock on intel cpu prior
to either broadwell or haswell (forgotten which) in spite
of much more unroling.
> And yup, inlining is hard. GCC's heuristics there are very good
> nowadays, but any single decision has big effects. Doing the important
> spots manually (always_inline or noinline) has good payoff.
Latest inline gripe was a function replicated about 20 times
when the non-inline version was a register load and 'tail call'.
The inlining is just bloat.
David
-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)
^ permalink raw reply
* Re: [PATCH 03/10] powerpc/64e/interrupt: use new interrupt return
From: Nicholas Piggin @ 2021-03-16 8:14 UTC (permalink / raw)
To: Christophe Leroy, linuxppc-dev; +Cc: Scott Wood
In-Reply-To: <f452729c-6290-17e9-eb96-4c1ebffd4c7e@csgroup.eu>
Excerpts from Christophe Leroy's message of March 16, 2021 5:29 pm:
>
>
> Le 16/03/2021 à 08:25, Nicholas Piggin a écrit :
>> Excerpts from Nicholas Piggin's message of March 16, 2021 5:04 pm:
>>> Excerpts from Christophe Leroy's message of March 15, 2021 11:30 pm:
>>>>
>>>>
>>>> Le 15/03/2021 à 04:17, Nicholas Piggin a écrit :
>>>>> Update the new C and asm interrupt return code to account for 64e
>>>>> specifics, switch over to use it.
>>>>>
>>>>> The now-unused old ret_from_except code, that was moved to 64e after the
>>>>> 64s conversion, is removed.
>>>>>
>>>>> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
>>>>> ---
>>>>> arch/powerpc/include/asm/asm-prototypes.h | 2 -
>>>>> arch/powerpc/kernel/entry_64.S | 9 +-
>>>>> arch/powerpc/kernel/exceptions-64e.S | 321 ++--------------------
>>>>> arch/powerpc/kernel/interrupt.c | 27 +-
>>>>> arch/powerpc/kernel/irq.c | 76 -----
>>>>> 5 files changed, 56 insertions(+), 379 deletions(-)
>>>>>
>>>>> diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
>>>>> index fbabb49888d3..ae7b058b2970 100644
>>>>> --- a/arch/powerpc/kernel/interrupt.c
>>>>> +++ b/arch/powerpc/kernel/interrupt.c
>>>>> @@ -235,6 +235,10 @@ static notrace void booke_load_dbcr0(void)
>>>>> #endif
>>>>> }
>>>>>
>>>>> +/* temporary hack for context tracking, removed in later patch */
>>>>> +#include <linux/sched/debug.h>
>>>>> +asmlinkage __visible void __sched schedule_user(void);
>>>>> +
>>>>> /*
>>>>> * This should be called after a syscall returns, with r3 the return value
>>>>> * from the syscall. If this function returns non-zero, the system call
>>>>> @@ -292,7 +296,11 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
>>>>> while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
>>>>> local_irq_enable();
>>>>> if (ti_flags & _TIF_NEED_RESCHED) {
>>>>> +#ifdef CONFIG_PPC_BOOK3E_64
>>>>> + schedule_user();
>>>>> +#else
>>>>> schedule();
>>>>> +#endif
>>>>> } else {
>>>>> /*
>>>>> * SIGPENDING must restore signal handler function
>>>>> @@ -360,7 +368,6 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
>>>>> return ret;
>>>>> }
>>>>>
>>>>> -#ifndef CONFIG_PPC_BOOK3E_64 /* BOOK3E not yet using this */
>>>>> notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr)
>>>>> {
>>>>> unsigned long ti_flags;
>>>>> @@ -372,7 +379,9 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
>>>>> BUG_ON(!(regs->msr & MSR_PR));
>>>>> BUG_ON(!FULL_REGS(regs));
>>>>> BUG_ON(arch_irq_disabled_regs(regs));
>>>>> +#ifdef CONFIG_PPC_BOOK3S_64
>>>>
>>>> Shouldn't this go away in patch 6 as well ?
>>>> Or is that needed at all ? In syscall_exit_prepare() it is not ifdefed .
>>>
>>> Hmm, not sure. I'll take a look. It probably shouldn't be ifdefed at all
>>> but definitely by the end it should run without warning.
>>
>> Oh I got confused and thought that was the syscall exit. Interrupt exit
>> has to keep this until patch 6 because 64e context tracking does
>> everything in interrupt wrappers, so by the time we get here it will
>> already be set to CONTEXT_USER.
>>
>
> ok, but that it has to go in patch 6 ? At the time being the #ifdef is still there at the end of the
> series
>
Yes, that was an oversight. I'll remove it.
Thanks,
Nick
^ permalink raw reply
* Re: [PATCH 12/14] powerpc/64s: system call avoid setting MSR[RI] until we set MSR[EE]
From: Nicholas Piggin @ 2021-03-16 8:13 UTC (permalink / raw)
To: Christophe Leroy, linuxppc-dev
In-Reply-To: <722aeb8d-507f-6702-dd79-26242f987e3e@csgroup.eu>
Excerpts from Christophe Leroy's message of March 16, 2021 5:21 pm:
>
>
> Le 15/03/2021 à 23:04, Nicholas Piggin a écrit :
>> This extends the MSR[RI]=0 window a little further into the system
>> call in order to pair RI and EE enabling with a single mtmsrd.
>
> Time ago, I proposed to delay that on PPC32 and Michael objected, see
> https://patchwork.ozlabs.org/project/linuxppc-dev/patch/9f9dd859d571e324c7412ed9db9da8cfba678257.1548956511.git.christophe.leroy@c-s.fr/
Yeah, it is a concern. The speedup should be at least 5% I think on
64s (have not measured in isolation yet), so might be worth it.
We'll see.
Thanks,
Nick
^ permalink raw reply
* Re: [PATCH] powerpc/64s: power4 nap fixup in C
From: Nicholas Piggin @ 2021-03-16 8:11 UTC (permalink / raw)
To: Christophe Leroy, linuxppc-dev
In-Reply-To: <6ab2073b-dd10-ef2c-375d-1300f071ae1a@csgroup.eu>
Excerpts from Christophe Leroy's message of March 16, 2021 5:16 pm:
>
>
> Le 12/03/2021 à 02:20, Nicholas Piggin a écrit :
>> There is no need for this to be in asm, use the new intrrupt entry wrapper.
>>
>> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
>> ---
>> Hopefully this works on a real G5 now, but I couldn't reproduce the
>> problem with QEMU.
>>
>> Thanks,
>> Nick
>>
>> arch/powerpc/include/asm/interrupt.h | 19 +++++++++++
>> arch/powerpc/include/asm/processor.h | 1 +
>> arch/powerpc/include/asm/thread_info.h | 6 ++++
>> arch/powerpc/kernel/exceptions-64s.S | 45 --------------------------
>> arch/powerpc/kernel/idle_book3s.S | 4 +++
>> 5 files changed, 30 insertions(+), 45 deletions(-)
>>
>> diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
>> index aedfba29e43a..ef015d3b5e39 100644
>> --- a/arch/powerpc/include/asm/interrupt.h
>> +++ b/arch/powerpc/include/asm/interrupt.h
>> @@ -9,6 +9,17 @@
>> #include <asm/kprobes.h>
>> #include <asm/runlatch.h>
>>
>> +static inline void nap_adjust_return(struct pt_regs *regs)
>> +{
>> +#ifdef CONFIG_PPC_970_NAP
>> + if (unlikely(test_thread_local_flags(_TLF_NAPPING))) {
>> + /* Can avoid a test-and-clear because NMIs do not call this */
>> + clear_thread_local_flags(_TLF_NAPPING);
>> + regs->nip = (unsigned long)power4_idle_nap_return;
>
> Why don't you do regs->nip = regs->link like PPC32 instead of going via an intermediate symbol that
> does nothing else than branching to LR ?
It is supposed to keep the return branch predictor balanced.
I don't know if these CPUs have one, if it gets lost during nap, or if
nap latency is so high it really doesn't matter. But I think it is good
practice to make a habit of keeping things balanced.
Thanks,
Nick
^ permalink raw reply
* [PATCH v1 4/4] powerpc: Fix arch_stack_walk() to have running function as first entry
From: Christophe Leroy @ 2021-03-16 7:57 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <955248c6423cb068c5965923121ba31d4dd2fdde.1615881400.git.christophe.leroy@csgroup.eu>
It seems like other architectures, namely x86 and arm64 and riscv
at least, include the running function as top entry when saving
stack trace with save_stack_trace_regs().
Functionnalities like KFENCE expect it.
Do the same on powerpc, it allows KFENCE and other users to
properly identify the faulting function as depicted below.
Before the patch KFENCE was identifying finish_task_switch.isra
as the faulting function.
[ 14.937370] ==================================================================
[ 14.948692] BUG: KFENCE: invalid read in test_invalid_access+0x54/0x108
[ 14.948692]
[ 14.956814] Invalid read at 0xdf98800a:
[ 14.960664] test_invalid_access+0x54/0x108
[ 14.964876] finish_task_switch.isra.0+0x54/0x23c
[ 14.969606] kunit_try_run_case+0x5c/0xd0
[ 14.973658] kunit_generic_run_threadfn_adapter+0x24/0x30
[ 14.979079] kthread+0x15c/0x174
[ 14.982342] ret_from_kernel_thread+0x14/0x1c
[ 14.986731]
[ 14.988236] CPU: 0 PID: 111 Comm: kunit_try_catch Tainted: G B 5.12.0-rc1-01537-g95f6e2088d7e-dirty #4682
[ 14.999795] NIP: c016ec2c LR: c02f517c CTR: c016ebd8
[ 15.004851] REGS: e2449d90 TRAP: 0301 Tainted: G B (5.12.0-rc1-01537-g95f6e2088d7e-dirty)
[ 15.015274] MSR: 00009032 <EE,ME,IR,DR,RI> CR: 22000004 XER: 00000000
[ 15.022043] DAR: df98800a DSISR: 20000000
[ 15.022043] GPR00: c02f517c e2449e50 c1142080 e100dd24 c084b13c 00000008 c084b32b c016ebd8
[ 15.022043] GPR08: c0850000 df988000 c0d10000 e2449eb0 22000288
[ 15.040581] NIP [c016ec2c] test_invalid_access+0x54/0x108
[ 15.046010] LR [c02f517c] kunit_try_run_case+0x5c/0xd0
[ 15.051181] Call Trace:
[ 15.053637] [e2449e50] [c005a68c] finish_task_switch.isra.0+0x54/0x23c (unreliable)
[ 15.061338] [e2449eb0] [c02f517c] kunit_try_run_case+0x5c/0xd0
[ 15.067215] [e2449ed0] [c02f648c] kunit_generic_run_threadfn_adapter+0x24/0x30
[ 15.074472] [e2449ef0] [c004e7b0] kthread+0x15c/0x174
[ 15.079571] [e2449f30] [c001317c] ret_from_kernel_thread+0x14/0x1c
[ 15.085798] Instruction dump:
[ 15.088784] 8129d608 38e7ebd8 81020280 911f004c 39000000 995f0024 907f0028 90ff001c
[ 15.096613] 3949000a 915f0020 3d40c0d1 3d00c085 <8929000a> 3908adb0 812a4b98 3d40c02f
[ 15.104612] ==================================================================
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Fixes: 35de3b1aa168 ("powerpc: Implement save_stack_trace_regs() to enable kprobe stack tracing")
Acked-by: Marco Elver <elver@google.com>
---
arch/powerpc/kernel/stacktrace.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index 80f92f5b5393..1deb1bf331dd 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -28,6 +28,9 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
{
unsigned long sp;
+ if (regs && !consume_entry(cookie, regs->nip))
+ return;
+
if (regs)
sp = regs->gpr[1];
else if (task == current)
--
2.25.0
^ permalink raw reply related
* [PATCH v1 2/4] powerpc: Rename 'tsk' parameter into 'task'
From: Christophe Leroy @ 2021-03-16 7:57 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <955248c6423cb068c5965923121ba31d4dd2fdde.1615881400.git.christophe.leroy@csgroup.eu>
To better match generic code, rename 'tsk' to 'task' in
some stacktrace functions in preparation of following
patch which converts powerpc to generic ARCH_STACKWALK.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/kernel/stacktrace.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index a2a050551109..5b93650bc16c 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -27,13 +27,13 @@
* Save stack-backtrace addresses into a stack_trace buffer.
*/
static void save_context_stack(struct stack_trace *trace, unsigned long sp,
- struct task_struct *tsk, int savesched)
+ struct task_struct *task, int savesched)
{
for (;;) {
unsigned long *stack = (unsigned long *) sp;
unsigned long newsp, ip;
- if (!validate_sp(sp, tsk, STACK_FRAME_OVERHEAD))
+ if (!validate_sp(sp, task, STACK_FRAME_OVERHEAD))
return;
newsp = stack[0];
@@ -94,18 +94,18 @@ EXPORT_SYMBOL_GPL(save_stack_trace_regs);
*
* If the task is not 'current', the caller *must* ensure the task is inactive.
*/
-static int __save_stack_trace_tsk_reliable(struct task_struct *tsk,
+static int __save_stack_trace_tsk_reliable(struct task_struct *task,
struct stack_trace *trace)
{
unsigned long sp;
unsigned long newsp;
- unsigned long stack_page = (unsigned long)task_stack_page(tsk);
+ unsigned long stack_page = (unsigned long)task_stack_page(task);
unsigned long stack_end;
int graph_idx = 0;
bool firstframe;
stack_end = stack_page + THREAD_SIZE;
- if (!is_idle_task(tsk)) {
+ if (!is_idle_task(task)) {
/*
* For user tasks, this is the SP value loaded on
* kernel entry, see "PACAKSAVE(r13)" in _switch() and
@@ -129,10 +129,10 @@ static int __save_stack_trace_tsk_reliable(struct task_struct *tsk,
stack_end -= STACK_FRAME_OVERHEAD;
}
- if (tsk == current)
+ if (task == current)
sp = current_stack_frame();
else
- sp = tsk->thread.ksp;
+ sp = task->thread.ksp;
if (sp < stack_page + sizeof(struct thread_struct) ||
sp > stack_end - STACK_FRAME_MIN_SIZE) {
@@ -181,7 +181,7 @@ static int __save_stack_trace_tsk_reliable(struct task_struct *tsk,
* FIXME: IMHO these tests do not belong in
* arch-dependent code, they are generic.
*/
- ip = ftrace_graph_ret_addr(tsk, &graph_idx, ip, stack);
+ ip = ftrace_graph_ret_addr(task, &graph_idx, ip, stack);
#ifdef CONFIG_KPROBES
/*
* Mark stacktraces with kretprobed functions on them
--
2.25.0
^ permalink raw reply related
* [PATCH v1 3/4] powerpc: Convert stacktrace to generic ARCH_STACKWALK
From: Christophe Leroy @ 2021-03-16 7:57 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <955248c6423cb068c5965923121ba31d4dd2fdde.1615881400.git.christophe.leroy@csgroup.eu>
This patch converts powerpc stacktrace to the generic ARCH_STACKWALK
implemented by commit 214d8ca6ee85 ("stacktrace: Provide common
infrastructure")
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/Kconfig | 1 +
arch/powerpc/kernel/stacktrace.c | 91 ++++++--------------------------
2 files changed, 17 insertions(+), 75 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index bb7ca6fee885..60827904a816 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -145,6 +145,7 @@ config PPC
select ARCH_MIGHT_HAVE_PC_PARPORT
select ARCH_MIGHT_HAVE_PC_SERIO
select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
+ select ARCH_STACKWALK
select ARCH_SUPPORTS_ATOMIC_RMW
select ARCH_SUPPORTS_DEBUG_PAGEALLOC if PPC32 || PPC_BOOK3S_64
select ARCH_USE_BUILTIN_BSWAP
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index 5b93650bc16c..80f92f5b5393 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -23,12 +23,18 @@
#include <asm/paca.h>
-/*
- * Save stack-backtrace addresses into a stack_trace buffer.
- */
-static void save_context_stack(struct stack_trace *trace, unsigned long sp,
- struct task_struct *task, int savesched)
+void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+ struct task_struct *task, struct pt_regs *regs)
{
+ unsigned long sp;
+
+ if (regs)
+ sp = regs->gpr[1];
+ else if (task == current)
+ sp = current_stack_frame();
+ else
+ sp = task->thread.ksp;
+
for (;;) {
unsigned long *stack = (unsigned long *) sp;
unsigned long newsp, ip;
@@ -39,63 +45,21 @@ static void save_context_stack(struct stack_trace *trace, unsigned long sp,
newsp = stack[0];
ip = stack[STACK_FRAME_LR_SAVE];
- if (savesched || !in_sched_functions(ip)) {
- if (!trace->skip)
- trace->entries[trace->nr_entries++] = ip;
- else
- trace->skip--;
- }
-
- if (trace->nr_entries >= trace->max_entries)
+ if (!consume_entry(cookie, ip))
return;
sp = newsp;
}
}
-void save_stack_trace(struct stack_trace *trace)
-{
- unsigned long sp;
-
- sp = current_stack_frame();
-
- save_context_stack(trace, sp, current, 1);
-}
-EXPORT_SYMBOL_GPL(save_stack_trace);
-
-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_frame();
- else
- sp = tsk->thread.ksp;
-
- save_context_stack(trace, sp, tsk, 0);
-
- put_task_stack(tsk);
-}
-EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
-
-void
-save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
-{
- save_context_stack(trace, regs->gpr[1], current, 0);
-}
-EXPORT_SYMBOL_GPL(save_stack_trace_regs);
-
/*
* This function returns an error if it detects any unreliable features of the
* stack. Otherwise it guarantees that the stack trace is reliable.
*
* If the task is not 'current', the caller *must* ensure the task is inactive.
*/
-static int __save_stack_trace_tsk_reliable(struct task_struct *task,
- struct stack_trace *trace)
+int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
+ void *cookie, struct task_struct *task)
{
unsigned long sp;
unsigned long newsp;
@@ -191,35 +155,12 @@ static int __save_stack_trace_tsk_reliable(struct task_struct *task,
return -EINVAL;
#endif
- if (trace->nr_entries >= trace->max_entries)
- return -E2BIG;
- if (!trace->skip)
- trace->entries[trace->nr_entries++] = ip;
- else
- trace->skip--;
+ if (!consume_entry(cookie, ip))
+ return -EINVAL;
}
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;
-}
-
#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI)
static void handle_backtrace_ipi(struct pt_regs *regs)
{
--
2.25.0
^ permalink raw reply related
* [PATCH v1 1/4] powerpc: Activate HAVE_RELIABLE_STACKTRACE for all
From: Christophe Leroy @ 2021-03-16 7:57 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
CONFIG_HAVE_RELIABLE_STACKTRACE is applicable to all, no
reason to limit it to book3s/64le
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/Kconfig | 2 +-
arch/powerpc/kernel/stacktrace.c | 2 --
2 files changed, 1 insertion(+), 3 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 67c47b60cc84..bb7ca6fee885 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -235,7 +235,7 @@ config PPC
select MMU_GATHER_RCU_TABLE_FREE
select MMU_GATHER_PAGE_SIZE
select HAVE_REGS_AND_STACK_ACCESS_API
- select HAVE_RELIABLE_STACKTRACE if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN
+ select HAVE_RELIABLE_STACKTRACE
select HAVE_SOFTIRQ_ON_OWN_STACK
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_VIRT_CPU_ACCOUNTING
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index b6440657ef92..a2a050551109 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -88,7 +88,6 @@ save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
}
EXPORT_SYMBOL_GPL(save_stack_trace_regs);
-#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
/*
* This function returns an error if it detects any unreliable features of the
* stack. Otherwise it guarantees that the stack trace is reliable.
@@ -220,7 +219,6 @@ int save_stack_trace_tsk_reliable(struct task_struct *tsk,
return ret;
}
-#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */
#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI)
static void handle_backtrace_ipi(struct pt_regs *regs)
--
2.25.0
^ permalink raw reply related
* Re: [PATCH v3 28/32] powerpc/64s: interrupt implement exit logic in C
From: Nicholas Piggin @ 2021-03-16 7:36 UTC (permalink / raw)
To: Christophe Leroy, linuxppc-dev; +Cc: Michal Suchanek
In-Reply-To: <2d68d9ad-c3a2-2372-a5b2-1a1e3fdb41e4@csgroup.eu>
Excerpts from Christophe Leroy's message of March 15, 2021 11:41 pm:
>
>
> Le 25/02/2020 à 18:35, Nicholas Piggin a écrit :
>> Implement the bulk of interrupt return logic in C. The asm return code
>> must handle a few cases: restoring full GPRs, and emulating stack store.
>>
>> The stack store emulation is significantly simplfied, rather than creating
>> a new return frame and switching to that before performing the store, it
>> uses the PACA to keep a scratch register around to perform thestore.
>>
>> The asm return code is moved into 64e for now. The new logic has made
>> allowance for 64e, but I don't have a full environment that works well
>> to test it, and even booting in emulated qemu is not great for stress
>> testing. 64e shouldn't be too far off working with this, given a bit
>> more testing and auditing of the logic.
>>
>> This is slightly faster on a POWER9 (page fault speed increases about
>> 1.1%), probably due to reduced mtmsrd.
>>
>> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
>> Signed-off-by: Michal Suchanek <msuchanek@suse.de>
>> ---
>
> ...
>
>> +notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr)
>> +{
>
> ...
>
>> +
>> +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
>> + local_paca->tm_scratch = regs->msr;
>> +#endif
>
> Could we define a helper for that in asm/tm.h, that voids when CONFIG_PPC_TRANSACTIONAL_MEM is not
> selected ?
Yeah I wanted to do something about that. I don't know what it's used
for here. I guess it saves the return MSR so if that causes a crash then
the next oops would see it, but I wonder if we can just get that from
SRR1 + program check error codes, or if there is something we can't
reconstruct from there. Have to check with someone who knows TM better.
Thanks,
Nick
^ permalink raw reply
* [PATCH] selftests: remove duplicate include
From: menglong8.dong @ 2021-03-16 7:33 UTC (permalink / raw)
To: pbonzini
Cc: kvm, linuxppc-dev, linux-kernel, zhang.yunkai, paulus,
linux-kselftest, akpm, ricardo.canuelo, shuah
From: Zhang Yunkai <zhang.yunkai@zte.com.cn>
'assert.h' included in 'sparsebit.c' is duplicated.
It is also included in the 161th line.
'string.h' included in 'mincore_selftest.c' is duplicated.
It is also included in the 15th line.
'sched.h' included in 'tlbie_test.c' is duplicated.
It is also included in the 33th line.
Signed-off-by: Zhang Yunkai <zhang.yunkai@zte.com.cn>
---
tools/testing/selftests/kvm/lib/sparsebit.c | 1 -
tools/testing/selftests/mincore/mincore_selftest.c | 1 -
tools/testing/selftests/powerpc/mm/tlbie_test.c | 1 -
3 files changed, 3 deletions(-)
diff --git a/tools/testing/selftests/kvm/lib/sparsebit.c b/tools/testing/selftests/kvm/lib/sparsebit.c
index 031ba3c932ed..a0d0c83d83de 100644
--- a/tools/testing/selftests/kvm/lib/sparsebit.c
+++ b/tools/testing/selftests/kvm/lib/sparsebit.c
@@ -1890,7 +1890,6 @@ void sparsebit_validate_internal(struct sparsebit *s)
*/
#include <stdlib.h>
-#include <assert.h>
struct range {
sparsebit_idx_t first, last;
diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c
index 5a1e85ff5d32..e54106643337 100644
--- a/tools/testing/selftests/mincore/mincore_selftest.c
+++ b/tools/testing/selftests/mincore/mincore_selftest.c
@@ -14,7 +14,6 @@
#include <sys/mman.h>
#include <string.h>
#include <fcntl.h>
-#include <string.h>
#include "../kselftest.h"
#include "../kselftest_harness.h"
diff --git a/tools/testing/selftests/powerpc/mm/tlbie_test.c b/tools/testing/selftests/powerpc/mm/tlbie_test.c
index f85a0938ab25..48344a74b212 100644
--- a/tools/testing/selftests/powerpc/mm/tlbie_test.c
+++ b/tools/testing/selftests/powerpc/mm/tlbie_test.c
@@ -33,7 +33,6 @@
#include <sched.h>
#include <time.h>
#include <stdarg.h>
-#include <sched.h>
#include <pthread.h>
#include <signal.h>
#include <sys/prctl.h>
--
2.25.1
^ permalink raw reply related
* Re: [PATCH 03/10] powerpc/64e/interrupt: use new interrupt return
From: Christophe Leroy @ 2021-03-16 7:29 UTC (permalink / raw)
To: Nicholas Piggin, linuxppc-dev; +Cc: Scott Wood
In-Reply-To: <1615879421.ckimzb9u3c.astroid@bobo.none>
Le 16/03/2021 à 08:25, Nicholas Piggin a écrit :
> Excerpts from Nicholas Piggin's message of March 16, 2021 5:04 pm:
>> Excerpts from Christophe Leroy's message of March 15, 2021 11:30 pm:
>>>
>>>
>>> Le 15/03/2021 à 04:17, Nicholas Piggin a écrit :
>>>> Update the new C and asm interrupt return code to account for 64e
>>>> specifics, switch over to use it.
>>>>
>>>> The now-unused old ret_from_except code, that was moved to 64e after the
>>>> 64s conversion, is removed.
>>>>
>>>> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
>>>> ---
>>>> arch/powerpc/include/asm/asm-prototypes.h | 2 -
>>>> arch/powerpc/kernel/entry_64.S | 9 +-
>>>> arch/powerpc/kernel/exceptions-64e.S | 321 ++--------------------
>>>> arch/powerpc/kernel/interrupt.c | 27 +-
>>>> arch/powerpc/kernel/irq.c | 76 -----
>>>> 5 files changed, 56 insertions(+), 379 deletions(-)
>>>>
>>>> diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
>>>> index fbabb49888d3..ae7b058b2970 100644
>>>> --- a/arch/powerpc/kernel/interrupt.c
>>>> +++ b/arch/powerpc/kernel/interrupt.c
>>>> @@ -235,6 +235,10 @@ static notrace void booke_load_dbcr0(void)
>>>> #endif
>>>> }
>>>>
>>>> +/* temporary hack for context tracking, removed in later patch */
>>>> +#include <linux/sched/debug.h>
>>>> +asmlinkage __visible void __sched schedule_user(void);
>>>> +
>>>> /*
>>>> * This should be called after a syscall returns, with r3 the return value
>>>> * from the syscall. If this function returns non-zero, the system call
>>>> @@ -292,7 +296,11 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
>>>> while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
>>>> local_irq_enable();
>>>> if (ti_flags & _TIF_NEED_RESCHED) {
>>>> +#ifdef CONFIG_PPC_BOOK3E_64
>>>> + schedule_user();
>>>> +#else
>>>> schedule();
>>>> +#endif
>>>> } else {
>>>> /*
>>>> * SIGPENDING must restore signal handler function
>>>> @@ -360,7 +368,6 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
>>>> return ret;
>>>> }
>>>>
>>>> -#ifndef CONFIG_PPC_BOOK3E_64 /* BOOK3E not yet using this */
>>>> notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr)
>>>> {
>>>> unsigned long ti_flags;
>>>> @@ -372,7 +379,9 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
>>>> BUG_ON(!(regs->msr & MSR_PR));
>>>> BUG_ON(!FULL_REGS(regs));
>>>> BUG_ON(arch_irq_disabled_regs(regs));
>>>> +#ifdef CONFIG_PPC_BOOK3S_64
>>>
>>> Shouldn't this go away in patch 6 as well ?
>>> Or is that needed at all ? In syscall_exit_prepare() it is not ifdefed .
>>
>> Hmm, not sure. I'll take a look. It probably shouldn't be ifdefed at all
>> but definitely by the end it should run without warning.
>
> Oh I got confused and thought that was the syscall exit. Interrupt exit
> has to keep this until patch 6 because 64e context tracking does
> everything in interrupt wrappers, so by the time we get here it will
> already be set to CONTEXT_USER.
>
ok, but that it has to go in patch 6 ? At the time being the #ifdef is still there at the end of the
series
^ permalink raw reply
* Re: [PATCH 03/10] powerpc/64e/interrupt: use new interrupt return
From: Nicholas Piggin @ 2021-03-16 7:25 UTC (permalink / raw)
To: Christophe Leroy, linuxppc-dev; +Cc: Scott Wood
In-Reply-To: <1615878222.rk6eq5hjpl.astroid@bobo.none>
Excerpts from Nicholas Piggin's message of March 16, 2021 5:04 pm:
> Excerpts from Christophe Leroy's message of March 15, 2021 11:30 pm:
>>
>>
>> Le 15/03/2021 à 04:17, Nicholas Piggin a écrit :
>>> Update the new C and asm interrupt return code to account for 64e
>>> specifics, switch over to use it.
>>>
>>> The now-unused old ret_from_except code, that was moved to 64e after the
>>> 64s conversion, is removed.
>>>
>>> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
>>> ---
>>> arch/powerpc/include/asm/asm-prototypes.h | 2 -
>>> arch/powerpc/kernel/entry_64.S | 9 +-
>>> arch/powerpc/kernel/exceptions-64e.S | 321 ++--------------------
>>> arch/powerpc/kernel/interrupt.c | 27 +-
>>> arch/powerpc/kernel/irq.c | 76 -----
>>> 5 files changed, 56 insertions(+), 379 deletions(-)
>>>
>>> diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
>>> index fbabb49888d3..ae7b058b2970 100644
>>> --- a/arch/powerpc/kernel/interrupt.c
>>> +++ b/arch/powerpc/kernel/interrupt.c
>>> @@ -235,6 +235,10 @@ static notrace void booke_load_dbcr0(void)
>>> #endif
>>> }
>>>
>>> +/* temporary hack for context tracking, removed in later patch */
>>> +#include <linux/sched/debug.h>
>>> +asmlinkage __visible void __sched schedule_user(void);
>>> +
>>> /*
>>> * This should be called after a syscall returns, with r3 the return value
>>> * from the syscall. If this function returns non-zero, the system call
>>> @@ -292,7 +296,11 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
>>> while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
>>> local_irq_enable();
>>> if (ti_flags & _TIF_NEED_RESCHED) {
>>> +#ifdef CONFIG_PPC_BOOK3E_64
>>> + schedule_user();
>>> +#else
>>> schedule();
>>> +#endif
>>> } else {
>>> /*
>>> * SIGPENDING must restore signal handler function
>>> @@ -360,7 +368,6 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
>>> return ret;
>>> }
>>>
>>> -#ifndef CONFIG_PPC_BOOK3E_64 /* BOOK3E not yet using this */
>>> notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr)
>>> {
>>> unsigned long ti_flags;
>>> @@ -372,7 +379,9 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
>>> BUG_ON(!(regs->msr & MSR_PR));
>>> BUG_ON(!FULL_REGS(regs));
>>> BUG_ON(arch_irq_disabled_regs(regs));
>>> +#ifdef CONFIG_PPC_BOOK3S_64
>>
>> Shouldn't this go away in patch 6 as well ?
>> Or is that needed at all ? In syscall_exit_prepare() it is not ifdefed .
>
> Hmm, not sure. I'll take a look. It probably shouldn't be ifdefed at all
> but definitely by the end it should run without warning.
Oh I got confused and thought that was the syscall exit. Interrupt exit
has to keep this until patch 6 because 64e context tracking does
everything in interrupt wrappers, so by the time we get here it will
already be set to CONTEXT_USER.
Thanks,
Nick
^ 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