* [PATCH v7 27/42] powerpc: add interrupt wrapper entry / exit stub functions
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
These will be used by subsequent patches.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 66 ++++++++++++++++++++++++++++
1 file changed, 66 insertions(+)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 5e2526aacc52..3df1921cfda3 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -5,6 +5,50 @@
#include <linux/context_tracking.h>
#include <asm/ftrace.h>
+struct interrupt_state {
+};
+
+static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
+{
+}
+
+/*
+ * Care should be taken to note that interrupt_exit_prepare and
+ * interrupt_async_exit_prepare do not necessarily return immediately to
+ * regs context (e.g., if regs is usermode, we don't necessarily return to
+ * user mode). Other interrupts might be taken between here and return,
+ * context switch / preemption may occur in the exit path after this, or a
+ * signal may be delivered, etc.
+ *
+ * The real interrupt exit code is platform specific, e.g.,
+ * interrupt_exit_user_prepare / interrupt_exit_kernel_prepare for 64s.
+ *
+ * However interrupt_nmi_exit_prepare does return directly to regs, because
+ * NMIs do not do "exit work" or replay soft-masked interrupts.
+ */
+static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
+{
+}
+
+static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
+{
+}
+
+static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
+{
+}
+
+struct interrupt_nmi_state {
+};
+
+static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
+{
+}
+
+static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
+{
+}
+
/**
* DECLARE_INTERRUPT_HANDLER_RAW - Declare raw interrupt handler function
* @func: Function name of the entry point
@@ -71,7 +115,13 @@ static __always_inline void ____##func(struct pt_regs *regs); \
\
__visible noinstr void func(struct pt_regs *regs) \
{ \
+ struct interrupt_state state; \
+ \
+ interrupt_enter_prepare(regs, &state); \
+ \
____##func (regs); \
+ \
+ interrupt_exit_prepare(regs, &state); \
} \
\
static __always_inline void ____##func(struct pt_regs *regs)
@@ -99,10 +149,15 @@ static __always_inline long ____##func(struct pt_regs *regs); \
\
__visible noinstr long func(struct pt_regs *regs) \
{ \
+ struct interrupt_state state; \
long ret; \
\
+ interrupt_enter_prepare(regs, &state); \
+ \
ret = ____##func (regs); \
\
+ interrupt_exit_prepare(regs, &state); \
+ \
return ret; \
} \
\
@@ -129,7 +184,13 @@ static __always_inline void ____##func(struct pt_regs *regs); \
\
__visible noinstr void func(struct pt_regs *regs) \
{ \
+ struct interrupt_state state; \
+ \
+ interrupt_async_enter_prepare(regs, &state); \
+ \
____##func (regs); \
+ \
+ interrupt_async_exit_prepare(regs, &state); \
} \
\
static __always_inline void ____##func(struct pt_regs *regs)
@@ -157,10 +218,15 @@ static __always_inline long ____##func(struct pt_regs *regs); \
\
__visible noinstr long func(struct pt_regs *regs) \
{ \
+ struct interrupt_nmi_state state; \
long ret; \
\
+ interrupt_nmi_enter_prepare(regs, &state); \
+ \
ret = ____##func (regs); \
\
+ interrupt_nmi_exit_prepare(regs, &state); \
+ \
return ret; \
} \
\
--
2.23.0
^ permalink raw reply related
* [PATCH v7 28/42] powerpc: convert interrupt handlers to use wrappers
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/asm-prototypes.h | 29 -------
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 1 -
arch/powerpc/include/asm/debug.h | 3 -
arch/powerpc/include/asm/hw_irq.h | 9 --
arch/powerpc/include/asm/interrupt.h | 66 ++++++++++++++
arch/powerpc/kernel/dbell.c | 6 +-
arch/powerpc/kernel/irq.c | 3 +-
arch/powerpc/kernel/mce.c | 5 +-
arch/powerpc/kernel/process.c | 3 +-
arch/powerpc/kernel/syscall_64.c | 1 +
arch/powerpc/kernel/tau_6xx.c | 2 +-
arch/powerpc/kernel/time.c | 3 +-
arch/powerpc/kernel/traps.c | 86 ++++++++++++-------
arch/powerpc/kernel/watchdog.c | 7 +-
arch/powerpc/kvm/book3s_hv.c | 1 +
arch/powerpc/kvm/book3s_hv_builtin.c | 1 +
arch/powerpc/kvm/booke.c | 1 +
arch/powerpc/mm/book3s64/hash_utils.c | 12 ++-
arch/powerpc/mm/book3s64/slb.c | 7 +-
arch/powerpc/mm/fault.c | 5 +-
arch/powerpc/platforms/cell/ras.c | 6 +-
arch/powerpc/platforms/cell/ras.h | 9 +-
arch/powerpc/platforms/powernv/idle.c | 1 +
23 files changed, 167 insertions(+), 100 deletions(-)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 22c9d08fa3a4..939f3c94c8f3 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -56,35 +56,6 @@ int exit_vmx_usercopy(void);
int enter_vmx_ops(void);
void *exit_vmx_ops(void *dest);
-/* Traps */
-long machine_check_early(struct pt_regs *regs);
-long hmi_exception_realmode(struct pt_regs *regs);
-void SMIException(struct pt_regs *regs);
-void handle_hmi_exception(struct pt_regs *regs);
-void instruction_breakpoint_exception(struct pt_regs *regs);
-void RunModeException(struct pt_regs *regs);
-void single_step_exception(struct pt_regs *regs);
-void program_check_exception(struct pt_regs *regs);
-void alignment_exception(struct pt_regs *regs);
-void StackOverflow(struct pt_regs *regs);
-void stack_overflow_exception(struct pt_regs *regs);
-void kernel_fp_unavailable_exception(struct pt_regs *regs);
-void altivec_unavailable_exception(struct pt_regs *regs);
-void vsx_unavailable_exception(struct pt_regs *regs);
-void fp_unavailable_tm(struct pt_regs *regs);
-void altivec_unavailable_tm(struct pt_regs *regs);
-void vsx_unavailable_tm(struct pt_regs *regs);
-void facility_unavailable_exception(struct pt_regs *regs);
-void TAUException(struct pt_regs *regs);
-void altivec_assist_exception(struct pt_regs *regs);
-void unrecoverable_exception(struct pt_regs *regs);
-void kernel_bad_stack(struct pt_regs *regs);
-void system_reset_exception(struct pt_regs *regs);
-void machine_check_exception(struct pt_regs *regs);
-void emulation_assist_interrupt(struct pt_regs *regs);
-long do_slb_fault(struct pt_regs *regs);
-void do_bad_slb_fault(struct pt_regs *regs);
-
/* signals, syscalls and interrupts */
long sys_swapcontext(struct ucontext __user *old_ctx,
struct ucontext __user *new_ctx,
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index b9968e297da2..066b1d34c7bc 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -454,7 +454,6 @@ static inline unsigned long hpt_hash(unsigned long vpn,
#define HPTE_NOHPTE_UPDATE 0x2
#define HPTE_USE_KERNEL_KEY 0x4
-long do_hash_fault(struct pt_regs *regs);
extern int __hash_page_4K(unsigned long ea, unsigned long access,
unsigned long vsid, pte_t *ptep, unsigned long trap,
unsigned long flags, int ssize, int subpage_prot);
diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h
index 0550eceab3ca..86a14736c76c 100644
--- a/arch/powerpc/include/asm/debug.h
+++ b/arch/powerpc/include/asm/debug.h
@@ -50,9 +50,6 @@ bool ppc_breakpoint_available(void);
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
extern void do_send_trap(struct pt_regs *regs, unsigned long address,
unsigned long error_code, int brkpt);
-#else
-
-void do_break(struct pt_regs *regs);
#endif
#endif /* _ASM_POWERPC_DEBUG_H */
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 75c2b137fc00..614957f74cee 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -50,15 +50,6 @@
#ifndef __ASSEMBLY__
-extern void replay_system_reset(void);
-extern void replay_soft_interrupts(void);
-
-extern void timer_interrupt(struct pt_regs *);
-extern void performance_monitor_exception(struct pt_regs *regs);
-extern void WatchdogException(struct pt_regs *regs);
-extern void unknown_exception(struct pt_regs *regs);
-void unknown_async_exception(struct pt_regs *regs);
-
#ifdef CONFIG_PPC64
#include <asm/paca.h>
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 3df1921cfda3..4ffbd3d75324 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -232,4 +232,70 @@ __visible noinstr long func(struct pt_regs *regs) \
\
static __always_inline long ____##func(struct pt_regs *regs)
+
+/* Interrupt handlers */
+/* kernel/traps.c */
+DECLARE_INTERRUPT_HANDLER_NMI(system_reset_exception);
+#ifdef CONFIG_PPC_BOOK3S_64
+DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception);
+#else
+DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception);
+#endif
+DECLARE_INTERRUPT_HANDLER(SMIException);
+DECLARE_INTERRUPT_HANDLER(handle_hmi_exception);
+DECLARE_INTERRUPT_HANDLER(unknown_exception);
+DECLARE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception);
+DECLARE_INTERRUPT_HANDLER(instruction_breakpoint_exception);
+DECLARE_INTERRUPT_HANDLER(RunModeException);
+DECLARE_INTERRUPT_HANDLER(single_step_exception);
+DECLARE_INTERRUPT_HANDLER(program_check_exception);
+DECLARE_INTERRUPT_HANDLER(emulation_assist_interrupt);
+DECLARE_INTERRUPT_HANDLER(alignment_exception);
+DECLARE_INTERRUPT_HANDLER(StackOverflow);
+DECLARE_INTERRUPT_HANDLER(stack_overflow_exception);
+DECLARE_INTERRUPT_HANDLER(kernel_fp_unavailable_exception);
+DECLARE_INTERRUPT_HANDLER(altivec_unavailable_exception);
+DECLARE_INTERRUPT_HANDLER(vsx_unavailable_exception);
+DECLARE_INTERRUPT_HANDLER(facility_unavailable_exception);
+DECLARE_INTERRUPT_HANDLER(fp_unavailable_tm);
+DECLARE_INTERRUPT_HANDLER(altivec_unavailable_tm);
+DECLARE_INTERRUPT_HANDLER(vsx_unavailable_tm);
+DECLARE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi);
+DECLARE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async);
+DECLARE_INTERRUPT_HANDLER_RAW(performance_monitor_exception);
+DECLARE_INTERRUPT_HANDLER(DebugException);
+DECLARE_INTERRUPT_HANDLER(altivec_assist_exception);
+DECLARE_INTERRUPT_HANDLER(CacheLockingException);
+DECLARE_INTERRUPT_HANDLER(SPEFloatingPointException);
+DECLARE_INTERRUPT_HANDLER(SPEFloatingPointRoundException);
+DECLARE_INTERRUPT_HANDLER(unrecoverable_exception);
+DECLARE_INTERRUPT_HANDLER(WatchdogException);
+DECLARE_INTERRUPT_HANDLER(kernel_bad_stack);
+
+/* slb.c */
+DECLARE_INTERRUPT_HANDLER_RAW(do_slb_fault);
+DECLARE_INTERRUPT_HANDLER(do_bad_slb_fault);
+
+/* hash_utils.c */
+DECLARE_INTERRUPT_HANDLER_RAW(do_hash_fault);
+
+/* fault.c */
+DECLARE_INTERRUPT_HANDLER_RET(do_page_fault);
+DECLARE_INTERRUPT_HANDLER(do_bad_page_fault_segv);
+
+/* process.c */
+DECLARE_INTERRUPT_HANDLER(do_break);
+
+/* time.c */
+DECLARE_INTERRUPT_HANDLER_ASYNC(timer_interrupt);
+
+/* mce.c */
+DECLARE_INTERRUPT_HANDLER_NMI(machine_check_early);
+DECLARE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode);
+
+DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException);
+
+void replay_system_reset(void);
+void replay_soft_interrupts(void);
+
#endif /* _ASM_POWERPC_INTERRUPT_H */
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 52680cf07c9d..6a7ecfca5c3b 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -12,13 +12,14 @@
#include <linux/hardirq.h>
#include <asm/dbell.h>
+#include <asm/interrupt.h>
#include <asm/irq_regs.h>
#include <asm/kvm_ppc.h>
#include <asm/trace.h>
#ifdef CONFIG_SMP
-void doorbell_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
{
struct pt_regs *old_regs = set_irq_regs(regs);
@@ -39,9 +40,8 @@ void doorbell_exception(struct pt_regs *regs)
set_irq_regs(old_regs);
}
#else /* CONFIG_SMP */
-void doorbell_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
{
printk(KERN_WARNING "Received doorbell on non-smp system\n");
}
#endif /* CONFIG_SMP */
-
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index cc7a6271b6b4..90435574b66b 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -54,6 +54,7 @@
#include <linux/pgtable.h>
#include <linux/uaccess.h>
+#include <asm/interrupt.h>
#include <asm/io.h>
#include <asm/irq.h>
#include <asm/cache.h>
@@ -669,7 +670,7 @@ void __do_irq(struct pt_regs *regs)
irq_exit();
}
-void do_IRQ(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
{
struct pt_regs *old_regs = set_irq_regs(regs);
void *cursp, *irqsp, *sirqsp;
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 9f3e133b57b7..54269947113d 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -18,6 +18,7 @@
#include <linux/extable.h>
#include <linux/ftrace.h>
+#include <asm/interrupt.h>
#include <asm/machdep.h>
#include <asm/mce.h>
#include <asm/nmi.h>
@@ -588,7 +589,7 @@ EXPORT_SYMBOL_GPL(machine_check_print_event_info);
*
* regs->nip and regs->msr contains srr0 and ssr1.
*/
-long notrace machine_check_early(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_NMI(machine_check_early)
{
long handled = 0;
u8 ftrace_enabled = this_cpu_get_ftrace_enabled();
@@ -722,7 +723,7 @@ long hmi_handle_debugtrig(struct pt_regs *regs)
/*
* Return values:
*/
-long hmi_exception_realmode(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode)
{
int ret;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 4f0f81e9420b..8520ed5ae144 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -41,6 +41,7 @@
#include <linux/pkeys.h>
#include <linux/seq_buf.h>
+#include <asm/interrupt.h>
#include <asm/io.h>
#include <asm/processor.h>
#include <asm/mmu.h>
@@ -659,7 +660,7 @@ static void do_break_handler(struct pt_regs *regs)
}
}
-void do_break(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(do_break)
{
current->thread.trap_nr = TRAP_HWBKPT;
if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, regs->dsisr,
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index e0eb2a502db3..316c3ba16554 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -5,6 +5,7 @@
#include <asm/kup.h>
#include <asm/cputime.h>
#include <asm/hw_irq.h>
+#include <asm/interrupt.h>
#include <asm/kprobes.h>
#include <asm/paca.h>
#include <asm/ptrace.h>
diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c
index 0b4694b8d248..46b2e5de4ef5 100644
--- a/arch/powerpc/kernel/tau_6xx.c
+++ b/arch/powerpc/kernel/tau_6xx.c
@@ -100,7 +100,7 @@ static void TAUupdate(int cpu)
* with interrupts disabled
*/
-void TAUException(struct pt_regs * regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(TAUException)
{
int cpu = smp_processor_id();
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 67feb3524460..435a251247ed 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -56,6 +56,7 @@
#include <linux/processor.h>
#include <asm/trace.h>
+#include <asm/interrupt.h>
#include <asm/io.h>
#include <asm/nvram.h>
#include <asm/cache.h>
@@ -570,7 +571,7 @@ void arch_irq_work_raise(void)
* timer_interrupt - gets called when the decrementer overflows,
* with interrupts disabled.
*/
-void timer_interrupt(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
{
struct clock_event_device *evt = this_cpu_ptr(&decrementers);
u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index f70d3f6174c8..7ff915aae8ec 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -41,6 +41,7 @@
#include <asm/emulated_ops.h>
#include <linux/uaccess.h>
#include <asm/debugfs.h>
+#include <asm/interrupt.h>
#include <asm/io.h>
#include <asm/machdep.h>
#include <asm/rtas.h>
@@ -430,8 +431,7 @@ void hv_nmi_check_nonrecoverable(struct pt_regs *regs)
regs->msr &= ~MSR_RI;
#endif
}
-
-void system_reset_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
{
unsigned long hsrr0, hsrr1;
bool saved_hsrrs = false;
@@ -519,6 +519,8 @@ void system_reset_exception(struct pt_regs *regs)
this_cpu_set_ftrace_enabled(ftrace_enabled);
/* What should we do here? We could issue a shutdown or hard reset. */
+
+ return 0;
}
NOKPROBE_SYMBOL(system_reset_exception);
@@ -805,7 +807,11 @@ void die_mce(const char *str, struct pt_regs *regs, long err)
}
NOKPROBE_SYMBOL(die_mce);
-void machine_check_exception(struct pt_regs *regs)
+#ifdef CONFIG_PPC_BOOK3S_64
+DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception)
+#else
+DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
+#endif
{
int recover = 0;
@@ -855,10 +861,16 @@ void machine_check_exception(struct pt_regs *regs)
die_mce("Unrecoverable Machine check", regs, SIGBUS);
if (nmi) nmi_exit();
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ return;
+#else
+ return 0;
+#endif
}
NOKPROBE_SYMBOL(machine_check_exception);
-void SMIException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(SMIException) /* async? */
{
die("System Management Interrupt", regs, SIGABRT);
}
@@ -1044,7 +1056,7 @@ static void p9_hmi_special_emu(struct pt_regs *regs)
}
#endif /* CONFIG_VSX */
-void handle_hmi_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
{
struct pt_regs *old_regs;
@@ -1073,7 +1085,7 @@ void handle_hmi_exception(struct pt_regs *regs)
set_irq_regs(old_regs);
}
-void unknown_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(unknown_exception)
{
enum ctx_state prev_state = exception_enter();
@@ -1085,7 +1097,7 @@ void unknown_exception(struct pt_regs *regs)
exception_exit(prev_state);
}
-void unknown_async_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception)
{
enum ctx_state prev_state = exception_enter();
@@ -1097,7 +1109,7 @@ void unknown_async_exception(struct pt_regs *regs)
exception_exit(prev_state);
}
-void instruction_breakpoint_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(instruction_breakpoint_exception)
{
enum ctx_state prev_state = exception_enter();
@@ -1112,12 +1124,12 @@ void instruction_breakpoint_exception(struct pt_regs *regs)
exception_exit(prev_state);
}
-void RunModeException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(RunModeException)
{
_exception(SIGTRAP, regs, TRAP_UNK, 0);
}
-void single_step_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(single_step_exception)
{
enum ctx_state prev_state = exception_enter();
@@ -1462,7 +1474,7 @@ static int emulate_math(struct pt_regs *regs)
static inline int emulate_math(struct pt_regs *regs) { return -1; }
#endif
-void program_check_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(program_check_exception)
{
enum ctx_state prev_state = exception_enter();
unsigned int reason = get_reason(regs);
@@ -1587,14 +1599,14 @@ NOKPROBE_SYMBOL(program_check_exception);
* This occurs when running in hypervisor mode on POWER6 or later
* and an illegal instruction is encountered.
*/
-void emulation_assist_interrupt(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(emulation_assist_interrupt)
{
regs->msr |= REASON_ILLEGAL;
program_check_exception(regs);
}
NOKPROBE_SYMBOL(emulation_assist_interrupt);
-void alignment_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(alignment_exception)
{
enum ctx_state prev_state = exception_enter();
int sig, code, fixed = 0;
@@ -1644,7 +1656,7 @@ void alignment_exception(struct pt_regs *regs)
exception_exit(prev_state);
}
-void StackOverflow(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(StackOverflow)
{
pr_crit("Kernel stack overflow in process %s[%d], r1=%lx\n",
current->comm, task_pid_nr(current), regs->gpr[1]);
@@ -1653,7 +1665,7 @@ void StackOverflow(struct pt_regs *regs)
panic("kernel stack overflow");
}
-void stack_overflow_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(stack_overflow_exception)
{
enum ctx_state prev_state = exception_enter();
@@ -1662,7 +1674,7 @@ void stack_overflow_exception(struct pt_regs *regs)
exception_exit(prev_state);
}
-void kernel_fp_unavailable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(kernel_fp_unavailable_exception)
{
enum ctx_state prev_state = exception_enter();
@@ -1673,7 +1685,7 @@ void kernel_fp_unavailable_exception(struct pt_regs *regs)
exception_exit(prev_state);
}
-void altivec_unavailable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(altivec_unavailable_exception)
{
enum ctx_state prev_state = exception_enter();
@@ -1692,7 +1704,7 @@ void altivec_unavailable_exception(struct pt_regs *regs)
exception_exit(prev_state);
}
-void vsx_unavailable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(vsx_unavailable_exception)
{
if (user_mode(regs)) {
/* A user program has executed an vsx instruction,
@@ -1723,7 +1735,7 @@ static void tm_unavailable(struct pt_regs *regs)
die("Unrecoverable TM Unavailable Exception", regs, SIGABRT);
}
-void facility_unavailable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(facility_unavailable_exception)
{
static char *facility_strings[] = {
[FSCR_FP_LG] = "FPU",
@@ -1843,7 +1855,7 @@ void facility_unavailable_exception(struct pt_regs *regs)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-void fp_unavailable_tm(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(fp_unavailable_tm)
{
/* Note: This does not handle any kind of FP laziness. */
@@ -1876,7 +1888,7 @@ void fp_unavailable_tm(struct pt_regs *regs)
tm_recheckpoint(¤t->thread);
}
-void altivec_unavailable_tm(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(altivec_unavailable_tm)
{
/* See the comments in fp_unavailable_tm(). This function operates
* the same way.
@@ -1891,7 +1903,7 @@ void altivec_unavailable_tm(struct pt_regs *regs)
current->thread.used_vr = 1;
}
-void vsx_unavailable_tm(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(vsx_unavailable_tm)
{
/* See the comments in fp_unavailable_tm(). This works similarly,
* though we're loading both FP and VEC registers in here.
@@ -1916,7 +1928,9 @@ void vsx_unavailable_tm(struct pt_regs *regs)
}
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-static void performance_monitor_exception_nmi(struct pt_regs *regs)
+#ifdef CONFIG_PPC64
+DECLARE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi);
+DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi)
{
nmi_enter();
@@ -1925,9 +1939,13 @@ static void performance_monitor_exception_nmi(struct pt_regs *regs)
perf_irq(regs);
nmi_exit();
+
+ return 0;
}
+#endif
-static void performance_monitor_exception_async(struct pt_regs *regs)
+DECLARE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async);
+DEFINE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async)
{
irq_enter();
@@ -1938,7 +1956,7 @@ static void performance_monitor_exception_async(struct pt_regs *regs)
irq_exit();
}
-void performance_monitor_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_RAW(performance_monitor_exception)
{
/*
* On 64-bit, if perf interrupts hit in a local_irq_disable
@@ -1950,6 +1968,8 @@ void performance_monitor_exception(struct pt_regs *regs)
performance_monitor_exception_nmi(regs);
else
performance_monitor_exception_async(regs);
+
+ return 0;
}
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
@@ -2012,7 +2032,7 @@ static void handle_debug(struct pt_regs *regs, unsigned long debug_status)
mtspr(SPRN_DBCR0, current->thread.debug.dbcr0);
}
-void DebugException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(DebugException)
{
unsigned long debug_status = regs->dsisr;
@@ -2085,7 +2105,7 @@ NOKPROBE_SYMBOL(DebugException);
#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
#ifdef CONFIG_ALTIVEC
-void altivec_assist_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(altivec_assist_exception)
{
int err;
@@ -2119,7 +2139,7 @@ void altivec_assist_exception(struct pt_regs *regs)
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_FSL_BOOKE
-void CacheLockingException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(CacheLockingException)
{
unsigned long error_code = regs->dsisr;
@@ -2134,7 +2154,7 @@ void CacheLockingException(struct pt_regs *regs)
#endif /* CONFIG_FSL_BOOKE */
#ifdef CONFIG_SPE
-void SPEFloatingPointException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(SPEFloatingPointException)
{
extern int do_spe_mathemu(struct pt_regs *regs);
unsigned long spefscr;
@@ -2186,7 +2206,7 @@ void SPEFloatingPointException(struct pt_regs *regs)
return;
}
-void SPEFloatingPointRoundException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(SPEFloatingPointRoundException)
{
extern int speround_handler(struct pt_regs *regs);
int err;
@@ -2228,7 +2248,7 @@ void SPEFloatingPointRoundException(struct pt_regs *regs)
* in the MSR is 0. This indicates that SRR0/1 are live, and that
* we therefore lost state by taking this exception.
*/
-void unrecoverable_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(unrecoverable_exception)
{
pr_emerg("Unrecoverable exception %lx at %lx (msr=%lx)\n",
regs->trap, regs->nip, regs->msr);
@@ -2248,7 +2268,7 @@ void __attribute__ ((weak)) WatchdogHandler(struct pt_regs *regs)
return;
}
-void WatchdogException(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(WatchdogException) /* XXX NMI? async? */
{
printk (KERN_EMERG "PowerPC Book-E Watchdog Exception\n");
WatchdogHandler(regs);
@@ -2259,7 +2279,7 @@ void WatchdogException(struct pt_regs *regs)
* We enter here if we discover during exception entry that we are
* running in supervisor mode with a userspace value in the stack pointer.
*/
-void kernel_bad_stack(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(kernel_bad_stack)
{
printk(KERN_EMERG "Bad kernel stack pointer %lx at %lx\n",
regs->gpr[1], regs->nip);
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index af3c15a1d41e..824b9376ac35 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -26,6 +26,7 @@
#include <linux/delay.h>
#include <linux/smp.h>
+#include <asm/interrupt.h>
#include <asm/paca.h>
/*
@@ -247,14 +248,14 @@ static void watchdog_timer_interrupt(int cpu)
watchdog_smp_panic(cpu, tb);
}
-void soft_nmi_interrupt(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
{
unsigned long flags;
int cpu = raw_smp_processor_id();
u64 tb;
if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
- return;
+ return 0;
nmi_enter();
@@ -291,6 +292,8 @@ void soft_nmi_interrupt(struct pt_regs *regs)
out:
nmi_exit();
+
+ return 0;
}
static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index d348e77cee20..43e64e60ee33 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -53,6 +53,7 @@
#include <asm/cputable.h>
#include <asm/cacheflush.h>
#include <linux/uaccess.h>
+#include <asm/interrupt.h>
#include <asm/io.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 8053efdf7ea7..10fc274bea65 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -17,6 +17,7 @@
#include <asm/asm-prototypes.h>
#include <asm/cputable.h>
+#include <asm/interrupt.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/archrandom.h>
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 288a9820ec01..bd2bb73021d8 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -20,6 +20,7 @@
#include <asm/cputable.h>
#include <linux/uaccess.h>
+#include <asm/interrupt.h>
#include <asm/kvm_ppc.h>
#include <asm/cacheflush.h>
#include <asm/dbell.h>
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index d7d3a80a51d4..cf167f6d825d 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -38,6 +38,7 @@
#include <linux/pgtable.h>
#include <asm/debugfs.h>
+#include <asm/interrupt.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
@@ -1512,7 +1513,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
}
EXPORT_SYMBOL_GPL(hash_page);
-static long __do_hash_fault(struct pt_regs *regs)
+DECLARE_INTERRUPT_HANDLER_RET(__do_hash_fault);
+DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
{
unsigned long ea = regs->dar;
unsigned long dsisr = regs->dsisr;
@@ -1565,7 +1567,11 @@ static long __do_hash_fault(struct pt_regs *regs)
return err;
}
-long do_hash_fault(struct pt_regs *regs)
+/*
+ * The _RAW interrupt entry checks for the in_nmi() case before
+ * running the full handler.
+ */
+DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault)
{
unsigned long dsisr = regs->dsisr;
long err;
@@ -1587,7 +1593,7 @@ long do_hash_fault(struct pt_regs *regs)
* the access, or panic if there isn't a handler.
*/
if (unlikely(in_nmi())) {
- bad_page_fault(regs, SIGSEGV);
+ do_bad_page_fault_segv(regs);
return 0;
}
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index 14c62b685f0c..c91bd85eb90e 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -10,6 +10,7 @@
*/
#include <asm/asm-prototypes.h>
+#include <asm/interrupt.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
#include <asm/paca.h>
@@ -813,7 +814,7 @@ static long slb_allocate_user(struct mm_struct *mm, unsigned long ea)
return slb_insert_entry(ea, context, flags, ssize, false);
}
-long do_slb_fault(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_RAW(do_slb_fault)
{
unsigned long ea = regs->dar;
unsigned long id = get_region_id(ea);
@@ -833,7 +834,7 @@ long do_slb_fault(struct pt_regs *regs)
*/
/*
- * The interrupt state is not reconciled, for performance, so that
+ * This is a raw interrupt handler, for performance, so that
* fast_interrupt_return can be used. The handler must not touch local
* irq state, or schedule. We could test for usermode and upgrade to a
* normal process context (synchronous) interrupt for those, which
@@ -868,7 +869,7 @@ long do_slb_fault(struct pt_regs *regs)
}
}
-void do_bad_slb_fault(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(do_bad_slb_fault)
{
int err = regs->result;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index fef92efad733..f8eb42aaafab 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -34,6 +34,7 @@
#include <linux/uaccess.h>
#include <asm/firmware.h>
+#include <asm/interrupt.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
@@ -540,7 +541,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
}
NOKPROBE_SYMBOL(__do_page_fault);
-long do_page_fault(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
{
const struct exception_table_entry *entry;
enum ctx_state prev_state;
@@ -624,7 +625,7 @@ void bad_page_fault(struct pt_regs *regs, int sig)
}
#ifdef CONFIG_PPC_BOOK3S_64
-void do_bad_page_fault_segv(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(do_bad_page_fault_segv)
{
bad_page_fault(regs, SIGSEGV);
}
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index 6ea480539419..4325c05bedd9 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -49,7 +49,7 @@ static void dump_fir(int cpu)
}
-void cbe_system_error_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(cbe_system_error_exception)
{
int cpu = smp_processor_id();
@@ -58,7 +58,7 @@ void cbe_system_error_exception(struct pt_regs *regs)
dump_stack();
}
-void cbe_maintenance_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(cbe_maintenance_exception)
{
int cpu = smp_processor_id();
@@ -70,7 +70,7 @@ void cbe_maintenance_exception(struct pt_regs *regs)
dump_stack();
}
-void cbe_thermal_exception(struct pt_regs *regs)
+DEFINE_INTERRUPT_HANDLER(cbe_thermal_exception)
{
int cpu = smp_processor_id();
diff --git a/arch/powerpc/platforms/cell/ras.h b/arch/powerpc/platforms/cell/ras.h
index 6c2e6bc0062e..226dbd48efad 100644
--- a/arch/powerpc/platforms/cell/ras.h
+++ b/arch/powerpc/platforms/cell/ras.h
@@ -2,9 +2,12 @@
#ifndef RAS_H
#define RAS_H
-extern void cbe_system_error_exception(struct pt_regs *regs);
-extern void cbe_maintenance_exception(struct pt_regs *regs);
-extern void cbe_thermal_exception(struct pt_regs *regs);
+#include <asm/interrupt.h>
+
+DECLARE_INTERRUPT_HANDLER(cbe_system_error_exception);
+DECLARE_INTERRUPT_HANDLER(cbe_maintenance_exception);
+DECLARE_INTERRUPT_HANDLER(cbe_thermal_exception);
+
extern void cbe_ras_init(void);
#endif /* RAS_H */
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index e6f461812856..999997d9e9a9 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -14,6 +14,7 @@
#include <asm/asm-prototypes.h>
#include <asm/firmware.h>
+#include <asm/interrupt.h>
#include <asm/machdep.h>
#include <asm/opal.h>
#include <asm/cputhreads.h>
--
2.23.0
^ permalink raw reply related
* [PATCH v7 29/42] powerpc: add interrupt_cond_local_irq_enable helper
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
Simple helper for synchronous interrupt handlers (i.e., process-context)
to enable interrupts if it was taken in an interrupts-enabled context.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 7 +++++++
arch/powerpc/kernel/traps.c | 24 +++++++-----------------
arch/powerpc/mm/fault.c | 4 +---
3 files changed, 15 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 4ffbd3d75324..488bdd5bd922 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -3,6 +3,7 @@
#define _ASM_POWERPC_INTERRUPT_H
#include <linux/context_tracking.h>
+#include <linux/hardirq.h>
#include <asm/ftrace.h>
struct interrupt_state {
@@ -298,4 +299,10 @@ DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException);
void replay_system_reset(void);
void replay_soft_interrupts(void);
+static inline void interrupt_cond_local_irq_enable(struct pt_regs *regs)
+{
+ if (!arch_irq_disabled_regs(regs))
+ local_irq_enable();
+}
+
#endif /* _ASM_POWERPC_INTERRUPT_H */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 7ff915aae8ec..da488e62fb5f 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -343,8 +343,8 @@ static bool exception_common(int signr, struct pt_regs *regs, int code,
show_signal_msg(signr, regs, code, addr);
- if (arch_irqs_disabled() && !arch_irq_disabled_regs(regs))
- local_irq_enable();
+ if (arch_irqs_disabled())
+ interrupt_cond_local_irq_enable(regs);
current->thread.trap_nr = code;
@@ -1556,9 +1556,7 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
if (!user_mode(regs))
goto sigill;
- /* We restore the interrupt state now */
- if (!arch_irq_disabled_regs(regs))
- local_irq_enable();
+ interrupt_cond_local_irq_enable(regs);
/* (reason & REASON_ILLEGAL) would be the obvious thing here,
* but there seems to be a hardware bug on the 405GP (RevD)
@@ -1612,9 +1610,7 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
int sig, code, fixed = 0;
unsigned long reason;
- /* We restore the interrupt state now */
- if (!arch_irq_disabled_regs(regs))
- local_irq_enable();
+ interrupt_cond_local_irq_enable(regs);
reason = get_reason(regs);
@@ -1775,9 +1771,7 @@ DEFINE_INTERRUPT_HANDLER(facility_unavailable_exception)
die("Unexpected facility unavailable exception", regs, SIGABRT);
}
- /* We restore the interrupt state now */
- if (!arch_irq_disabled_regs(regs))
- local_irq_enable();
+ interrupt_cond_local_irq_enable(regs);
if (status == FSCR_DSCR_LG) {
/*
@@ -2162,9 +2156,7 @@ DEFINE_INTERRUPT_HANDLER(SPEFloatingPointException)
int code = FPE_FLTUNK;
int err;
- /* We restore the interrupt state now */
- if (!arch_irq_disabled_regs(regs))
- local_irq_enable();
+ interrupt_cond_local_irq_enable(regs);
flush_spe_to_thread(current);
@@ -2211,9 +2203,7 @@ DEFINE_INTERRUPT_HANDLER(SPEFloatingPointRoundException)
extern int speround_handler(struct pt_regs *regs);
int err;
- /* We restore the interrupt state now */
- if (!arch_irq_disabled_regs(regs))
- local_irq_enable();
+ interrupt_cond_local_irq_enable(regs);
preempt_disable();
if (regs->msr & MSR_SPE)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index f8eb42aaafab..8552ab6c008b 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -434,9 +434,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
return bad_area_nosemaphore(regs, address);
}
- /* We restore the interrupt state now */
- if (!arch_irq_disabled_regs(regs))
- local_irq_enable();
+ interrupt_cond_local_irq_enable(regs);
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
--
2.23.0
^ permalink raw reply related
* [PATCH v7 30/42] powerpc/64: context tracking remove _TIF_NOHZ
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
Add context tracking to the system call handler explicitly, and remove
_TIF_NOHZ.
This improves system call performance when nohz_full is enabled. On a
POWER9, gettid scv system call cost on a nohz_full CPU improves from
1129 cycles to 1004 cycles and on a housekeeping CPU from 550 cycles
to 430 cycles.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/Kconfig | 1 -
arch/powerpc/include/asm/thread_info.h | 4 +-
arch/powerpc/kernel/ptrace/ptrace.c | 4 --
arch/powerpc/kernel/signal.c | 4 --
arch/powerpc/kernel/syscall_64.c | 72 ++++++++++++++++----------
5 files changed, 47 insertions(+), 38 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 107bb4319e0e..28d5a1b1510f 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -196,7 +196,6 @@ config PPC
select HAVE_STACKPROTECTOR if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13)
select HAVE_STACKPROTECTOR if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2)
select HAVE_CONTEXT_TRACKING if PPC64
- select HAVE_TIF_NOHZ if PPC64
select HAVE_DEBUG_KMEMLEAK
select HAVE_DEBUG_STACKOVERFLOW
select HAVE_DYNAMIC_FTRACE
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 3d8a47af7a25..386d576673a1 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -94,7 +94,6 @@ void arch_setup_new_exec(void);
#define TIF_PATCH_PENDING 6 /* pending live patching update */
#define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */
#define TIF_SINGLESTEP 8 /* singlestepping active */
-#define TIF_NOHZ 9 /* in adaptive nohz mode */
#define TIF_SECCOMP 10 /* secure computing */
#define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */
#define TIF_NOERROR 12 /* Force successful syscall return */
@@ -128,11 +127,10 @@ void arch_setup_new_exec(void);
#define _TIF_UPROBE (1<<TIF_UPROBE)
#define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT)
#define _TIF_EMULATE_STACK_STORE (1<<TIF_EMULATE_STACK_STORE)
-#define _TIF_NOHZ (1<<TIF_NOHZ)
#define _TIF_SYSCALL_EMU (1<<TIF_SYSCALL_EMU)
#define _TIF_SYSCALL_DOTRACE (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
_TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
- _TIF_NOHZ | _TIF_SYSCALL_EMU)
+ _TIF_SYSCALL_EMU)
#define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
_TIF_NOTIFY_RESUME | _TIF_UPROBE | \
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
index 3d44b73adb83..4f3d4ff3728c 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -262,8 +262,6 @@ long do_syscall_trace_enter(struct pt_regs *regs)
{
u32 flags;
- user_exit();
-
flags = READ_ONCE(current_thread_info()->flags) &
(_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE);
@@ -340,8 +338,6 @@ void do_syscall_trace_leave(struct pt_regs *regs)
step = test_thread_flag(TIF_SINGLESTEP);
if (step || test_thread_flag(TIF_SYSCALL_TRACE))
tracehook_report_syscall_exit(regs, step);
-
- user_enter();
}
void __init pt_regs_check(void);
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 53782aa60ade..9ded046edb0e 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -282,8 +282,6 @@ static void do_signal(struct task_struct *tsk)
void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
{
- user_exit();
-
if (thread_info_flags & _TIF_UPROBE)
uprobe_notify_resume(regs);
@@ -299,8 +297,6 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
tracehook_notify_resume(regs);
rseq_handle_notify_resume(NULL, regs);
}
-
- user_enter();
}
static unsigned long get_tm_stackpointer(struct task_struct *tsk)
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 316c3ba16554..45c4420fe339 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -1,9 +1,11 @@
// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/context_tracking.h>
#include <linux/err.h>
#include <asm/asm-prototypes.h>
#include <asm/kup.h>
#include <asm/cputime.h>
+#include <asm/interrupt.h>
#include <asm/hw_irq.h>
#include <asm/interrupt.h>
#include <asm/kprobes.h>
@@ -28,6 +30,9 @@ notrace long system_call_exception(long r3, long r4, long r5,
if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
+ CT_WARN_ON(ct_state() == CONTEXT_KERNEL);
+ user_exit_irqoff();
+
trace_hardirqs_off(); /* finish reconciling */
if (IS_ENABLED(CONFIG_PPC_BOOK3S))
@@ -144,7 +149,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
* enabled when the interrupt handler returns (indicating a process-context /
* synchronous interrupt) then irqs_enabled should be true.
*/
-static notrace inline bool prep_irq_for_enabled_exit(bool clear_ri, bool irqs_enabled)
+static notrace inline bool __prep_irq_for_enabled_exit(bool clear_ri)
{
/* This must be done with RI=1 because tracing may touch vmaps */
trace_hardirqs_on();
@@ -161,29 +166,6 @@ static notrace inline bool prep_irq_for_enabled_exit(bool clear_ri, bool irqs_en
trace_hardirqs_off();
local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
- /*
- * Must replay pending soft-masked interrupts now. Don't just
- * local_irq_enabe(); local_irq_disable(); because if we are
- * returning from an asynchronous interrupt here, another one
- * might hit after irqs are enabled, and it would exit via this
- * same path allowing another to fire, and so on unbounded.
- *
- * If interrupts were enabled when this interrupt exited,
- * indicating a process context (synchronous) interrupt,
- * local_irq_enable/disable can be used, which will enable
- * interrupts rather than keeping them masked (unclear how
- * much benefit this is over just replaying for all cases,
- * because we immediately disable again, so all we're really
- * doing is allowing hard interrupts to execute directly for
- * a very small time, rather than being masked and replayed).
- */
- if (irqs_enabled) {
- local_irq_enable();
- local_irq_disable();
- } else {
- replay_soft_interrupts();
- }
-
return false;
}
local_paca->irq_happened = 0;
@@ -192,6 +174,37 @@ static notrace inline bool prep_irq_for_enabled_exit(bool clear_ri, bool irqs_en
return true;
}
+static notrace inline bool prep_irq_for_enabled_exit(bool clear_ri, bool irqs_enabled)
+{
+ if (__prep_irq_for_enabled_exit(clear_ri))
+ return true;
+
+ /*
+ * Must replay pending soft-masked interrupts now. Don't just
+ * local_irq_enabe(); local_irq_disable(); because if we are
+ * returning from an asynchronous interrupt here, another one
+ * might hit after irqs are enabled, and it would exit via this
+ * same path allowing another to fire, and so on unbounded.
+ *
+ * If interrupts were enabled when this interrupt exited,
+ * indicating a process context (synchronous) interrupt,
+ * local_irq_enable/disable can be used, which will enable
+ * interrupts rather than keeping them masked (unclear how
+ * much benefit this is over just replaying for all cases,
+ * because we immediately disable again, so all we're really
+ * doing is allowing hard interrupts to execute directly for
+ * a very small time, rather than being masked and replayed).
+ */
+ if (irqs_enabled) {
+ local_irq_enable();
+ local_irq_disable();
+ } else {
+ replay_soft_interrupts();
+ }
+
+ return false;
+}
+
/*
* 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
@@ -209,6 +222,8 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
unsigned long ti_flags;
unsigned long ret = 0;
+ CT_WARN_ON(ct_state() == CONTEXT_USER);
+
kuap_check_amr();
regs->result = r3;
@@ -240,9 +255,9 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
ret |= _TIF_RESTOREALL;
}
+again:
local_irq_disable();
-again:
ti_flags = READ_ONCE(*ti_flagsp);
while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
local_irq_enable();
@@ -286,9 +301,14 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
}
}
+ user_enter_irqoff();
+
/* scv need not set RI=0 because SRRs are not used */
- if (unlikely(!prep_irq_for_enabled_exit(!scv, true)))
+ if (unlikely(!__prep_irq_for_enabled_exit(!scv))) {
+ user_exit_irqoff();
+ local_irq_enable();
goto again;
+ }
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
local_paca->tm_scratch = regs->msr;
--
2.23.0
^ permalink raw reply related
* [PATCH v7 31/42] powerpc/64s/hash: improve context tracking of hash faults
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
This moves the 64s/hash context tracking from hash_page_mm() to
__do_hash_fault(), so it's no longer called by OCXL / SPU
accelerators, which was certainly the wrong thing to be doing,
because those callers are not low level interrupt handlers, so
should have entered a kernel context tracking already.
Then remain in kernel context for the duration of the fault,
rather than enter/exit for the hash fault then enter/exit for
the page fault, which is pointless.
Even still, calling exception_enter/exit in __do_hash_fault seems
questionable because that's touching per-cpu variables, tracing,
etc., which might have been interrupted by this hash fault or
themselves cause hash faults. But maybe I miss something because
hash_page_mm very deliberately calls trace_hash_fault too, for
example. So for now go with it, it's no worse than before, in this
regard.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/bug.h | 1 +
arch/powerpc/mm/book3s64/hash_utils.c | 7 ++---
arch/powerpc/mm/fault.c | 39 +++++++++++++++++++--------
3 files changed, 33 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index c10ae0a9bbaf..d1635ffbb179 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -112,6 +112,7 @@
struct pt_regs;
long do_page_fault(struct pt_regs *);
+long hash__do_page_fault(struct pt_regs *);
void bad_page_fault(struct pt_regs *, int);
void __bad_page_fault(struct pt_regs *regs, int sig);
void do_bad_page_fault_segv(struct pt_regs *regs);
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index cf167f6d825d..d681dc5a7b1c 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1289,7 +1289,6 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
unsigned long flags)
{
bool is_thp;
- enum ctx_state prev_state = exception_enter();
pgd_t *pgdir;
unsigned long vsid;
pte_t *ptep;
@@ -1491,7 +1490,6 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
DBG_LOW(" -> rc=%d\n", rc);
bail:
- exception_exit(prev_state);
return rc;
}
EXPORT_SYMBOL_GPL(hash_page_mm);
@@ -1516,6 +1514,7 @@ EXPORT_SYMBOL_GPL(hash_page);
DECLARE_INTERRUPT_HANDLER_RET(__do_hash_fault);
DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
{
+ enum ctx_state prev_state = exception_enter();
unsigned long ea = regs->dar;
unsigned long dsisr = regs->dsisr;
unsigned long access = _PAGE_PRESENT | _PAGE_READ;
@@ -1564,6 +1563,8 @@ DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
err = 0;
}
+ exception_exit(prev_state);
+
return err;
}
@@ -1600,7 +1601,7 @@ DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault)
err = __do_hash_fault(regs);
if (err) {
page_fault:
- err = do_page_fault(regs);
+ err = hash__do_page_fault(regs);
}
return err;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 8552ab6c008b..9c4220efc20f 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -387,7 +387,7 @@ static void sanity_check_fault(bool is_write, bool is_user,
* The return value is 0 if the fault was handled, or the signal
* number if this is a kernel fault that can't be handled here.
*/
-static int __do_page_fault(struct pt_regs *regs, unsigned long address,
+static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
unsigned long error_code)
{
struct vm_area_struct * vma;
@@ -537,36 +537,53 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
return 0;
}
-NOKPROBE_SYMBOL(__do_page_fault);
+NOKPROBE_SYMBOL(___do_page_fault);
-DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
+static long __do_page_fault(struct pt_regs *regs)
{
const struct exception_table_entry *entry;
- enum ctx_state prev_state;
long err;
- prev_state = exception_enter();
- err = __do_page_fault(regs, regs->dar, regs->dsisr);
+ err = ___do_page_fault(regs, regs->dar, regs->dsisr);
if (likely(!err))
- goto out;
+ return err;
entry = search_exception_tables(regs->nip);
if (likely(entry)) {
instruction_pointer_set(regs, extable_fixup(entry));
- err = 0;
+ return 0;
} else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) {
- /* 32 and 64e handle this in asm */
__bad_page_fault(regs, err);
- err = 0;
+ return 0;
+ } else {
+ /* 32 and 64e handle the bad page fault in asm */
+ return err;
}
+}
+NOKPROBE_SYMBOL(__do_page_fault);
+
+DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
+{
+ enum ctx_state prev_state = exception_enter();
+ long err;
+
+ err = __do_page_fault(regs);
-out:
exception_exit(prev_state);
return err;
}
NOKPROBE_SYMBOL(do_page_fault);
+#ifdef CONFIG_PPC_BOOK3S_64
+/* Same as do_page_fault but interrupt entry has already run in do_hash_fault */
+long hash__do_page_fault(struct pt_regs *regs)
+{
+ return __do_page_fault(regs);
+}
+NOKPROBE_SYMBOL(hash__do_page_fault);
+#endif
+
/*
* bad_page_fault is called when we have a bad access from the kernel.
* It is called from the DSI and ISI handlers in head.S and from some
--
2.23.0
^ permalink raw reply related
* [PATCH v7 32/42] powerpc/64: context tracking move to interrupt wrappers
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
This moves exception_enter/exit calls to wrapper functions for
synchronous interrupts. More interrupt handlers are covered by
this than previously.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 9 ++++
arch/powerpc/kernel/traps.c | 74 ++++++---------------------
arch/powerpc/mm/book3s64/hash_utils.c | 3 --
arch/powerpc/mm/fault.c | 9 +---
4 files changed, 27 insertions(+), 68 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 488bdd5bd922..e65ce3e2b071 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -7,10 +7,16 @@
#include <asm/ftrace.h>
struct interrupt_state {
+#ifdef CONFIG_PPC64
+ enum ctx_state ctx_state;
+#endif
};
static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+#ifdef CONFIG_PPC64
+ state->ctx_state = exception_enter();
+#endif
}
/*
@@ -29,6 +35,9 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
*/
static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+#ifdef CONFIG_PPC64
+ exception_exit(state->ctx_state);
+#endif
}
static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index da488e62fb5f..21fd14828827 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1087,41 +1087,28 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
DEFINE_INTERRUPT_HANDLER(unknown_exception)
{
- enum ctx_state prev_state = exception_enter();
-
printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
regs->nip, regs->msr, regs->trap);
_exception(SIGTRAP, regs, TRAP_UNK, 0);
-
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception)
{
- enum ctx_state prev_state = exception_enter();
-
printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
regs->nip, regs->msr, regs->trap);
_exception(SIGTRAP, regs, TRAP_UNK, 0);
-
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(instruction_breakpoint_exception)
{
- enum ctx_state prev_state = exception_enter();
-
if (notify_die(DIE_IABR_MATCH, "iabr_match", regs, 5,
5, SIGTRAP) == NOTIFY_STOP)
- goto bail;
+ return;
if (debugger_iabr_match(regs))
- goto bail;
+ return;
_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
-
-bail:
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(RunModeException)
@@ -1131,8 +1118,6 @@ DEFINE_INTERRUPT_HANDLER(RunModeException)
DEFINE_INTERRUPT_HANDLER(single_step_exception)
{
- enum ctx_state prev_state = exception_enter();
-
clear_single_step(regs);
clear_br_trace(regs);
@@ -1141,14 +1126,11 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception)
if (notify_die(DIE_SSTEP, "single_step", regs, 5,
5, SIGTRAP) == NOTIFY_STOP)
- goto bail;
+ return;
if (debugger_sstep(regs))
- goto bail;
+ return;
_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
-
-bail:
- exception_exit(prev_state);
}
NOKPROBE_SYMBOL(single_step_exception);
@@ -1476,7 +1458,6 @@ static inline int emulate_math(struct pt_regs *regs) { return -1; }
DEFINE_INTERRUPT_HANDLER(program_check_exception)
{
- enum ctx_state prev_state = exception_enter();
unsigned int reason = get_reason(regs);
/* We can now get here via a FP Unavailable exception if the core
@@ -1485,22 +1466,22 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
if (reason & REASON_FP) {
/* IEEE FP exception */
parse_fpe(regs);
- goto bail;
+ return;
}
if (reason & REASON_TRAP) {
unsigned long bugaddr;
/* Debugger is first in line to stop recursive faults in
* rcu_lock, notify_die, or atomic_notifier_call_chain */
if (debugger_bpt(regs))
- goto bail;
+ return;
if (kprobe_handler(regs))
- goto bail;
+ return;
/* trap exception */
if (notify_die(DIE_BPT, "breakpoint", regs, 5, 5, SIGTRAP)
== NOTIFY_STOP)
- goto bail;
+ return;
bugaddr = regs->nip;
/*
@@ -1512,10 +1493,10 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
if (!(regs->msr & MSR_PR) && /* not user-mode */
report_bug(bugaddr, regs) == BUG_TRAP_TYPE_WARN) {
regs->nip += 4;
- goto bail;
+ return;
}
_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
- goto bail;
+ return;
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
if (reason & REASON_TM) {
@@ -1536,7 +1517,7 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
*/
if (user_mode(regs)) {
_exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
- goto bail;
+ return;
} else {
printk(KERN_EMERG "Unexpected TM Bad Thing exception "
"at %lx (msr 0x%lx) tm_scratch=%llx\n",
@@ -1567,7 +1548,7 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
* pattern to occurrences etc. -dgibson 31/Mar/2003
*/
if (!emulate_math(regs))
- goto bail;
+ return;
/* Try to emulate it if we should. */
if (reason & (REASON_ILLEGAL | REASON_PRIVILEGED)) {
@@ -1575,10 +1556,10 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
case 0:
regs->nip += 4;
emulate_single_step(regs);
- goto bail;
+ return;
case -EFAULT:
_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
- goto bail;
+ return;
}
}
@@ -1587,9 +1568,6 @@ DEFINE_INTERRUPT_HANDLER(program_check_exception)
_exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
else
_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-
-bail:
- exception_exit(prev_state);
}
NOKPROBE_SYMBOL(program_check_exception);
@@ -1606,14 +1584,12 @@ NOKPROBE_SYMBOL(emulation_assist_interrupt);
DEFINE_INTERRUPT_HANDLER(alignment_exception)
{
- enum ctx_state prev_state = exception_enter();
int sig, code, fixed = 0;
unsigned long reason;
interrupt_cond_local_irq_enable(regs);
reason = get_reason(regs);
-
if (reason & REASON_BOUNDARY) {
sig = SIGBUS;
code = BUS_ADRALN;
@@ -1621,7 +1597,7 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
}
if (tm_abort_check(regs, TM_CAUSE_ALIGNMENT | TM_CAUSE_PERSISTENT))
- goto bail;
+ return;
/* we don't implement logging of alignment exceptions */
if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS))
@@ -1631,7 +1607,7 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
/* skip over emulated instruction */
regs->nip += inst_length(reason);
emulate_single_step(regs);
- goto bail;
+ return;
}
/* Operand address was bad */
@@ -1647,9 +1623,6 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
_exception(sig, regs, code, regs->dar);
else
bad_page_fault(regs, sig);
-
-bail:
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(StackOverflow)
@@ -1663,41 +1636,28 @@ DEFINE_INTERRUPT_HANDLER(StackOverflow)
DEFINE_INTERRUPT_HANDLER(stack_overflow_exception)
{
- enum ctx_state prev_state = exception_enter();
-
die("Kernel stack overflow", regs, SIGSEGV);
-
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(kernel_fp_unavailable_exception)
{
- enum ctx_state prev_state = exception_enter();
-
printk(KERN_EMERG "Unrecoverable FP Unavailable Exception "
"%lx at %lx\n", regs->trap, regs->nip);
die("Unrecoverable FP Unavailable Exception", regs, SIGABRT);
-
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(altivec_unavailable_exception)
{
- enum ctx_state prev_state = exception_enter();
-
if (user_mode(regs)) {
/* A user program has executed an altivec instruction,
but this kernel doesn't support altivec. */
_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
- goto bail;
+ return;
}
printk(KERN_EMERG "Unrecoverable VMX/Altivec Unavailable Exception "
"%lx at %lx\n", regs->trap, regs->nip);
die("Unrecoverable VMX/Altivec Unavailable Exception", regs, SIGABRT);
-
-bail:
- exception_exit(prev_state);
}
DEFINE_INTERRUPT_HANDLER(vsx_unavailable_exception)
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index d681dc5a7b1c..fb7c10524bcd 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1514,7 +1514,6 @@ EXPORT_SYMBOL_GPL(hash_page);
DECLARE_INTERRUPT_HANDLER_RET(__do_hash_fault);
DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
{
- enum ctx_state prev_state = exception_enter();
unsigned long ea = regs->dar;
unsigned long dsisr = regs->dsisr;
unsigned long access = _PAGE_PRESENT | _PAGE_READ;
@@ -1563,8 +1562,6 @@ DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
err = 0;
}
- exception_exit(prev_state);
-
return err;
}
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 9c4220efc20f..b26a7643fc6e 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -564,14 +564,7 @@ NOKPROBE_SYMBOL(__do_page_fault);
DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
{
- enum ctx_state prev_state = exception_enter();
- long err;
-
- err = __do_page_fault(regs);
-
- exception_exit(prev_state);
-
- return err;
+ return __do_page_fault(regs);
}
NOKPROBE_SYMBOL(do_page_fault);
--
2.23.0
^ permalink raw reply related
* [PATCH v7 33/42] powerpc/64: add context tracking to asynchronous interrupts
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
Previously context tracking was not done for asynchronous interrupts,
(those that run in interrupt context), and if those would cause a
reschedule when they exit, then scheduling functions (schedule_user,
preempt_schedule_irq) call exception_enter/exit to fix this up and
exit user context.
This is a hack we would like to get away from, so do context tracking
for asynchronous interrupts too.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index e65ce3e2b071..f7f64c3c514d 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -42,10 +42,12 @@ static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt
static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+ interrupt_enter_prepare(regs, state);
}
static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+ interrupt_exit_prepare(regs, state);
}
struct interrupt_nmi_state {
--
2.23.0
^ permalink raw reply related
* [PATCH v7 34/42] powerpc: handle irq_enter/irq_exit in interrupt handler wrappers
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
Move irq_enter/irq_exit into asynchronous interrupt handler wrappers.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 2 ++
arch/powerpc/kernel/dbell.c | 3 +--
arch/powerpc/kernel/irq.c | 4 ----
arch/powerpc/kernel/tau_6xx.c | 3 ---
arch/powerpc/kernel/time.c | 4 ++--
arch/powerpc/kernel/traps.c | 10 +++-------
6 files changed, 8 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index f7f64c3c514d..5a1395499508 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -43,10 +43,12 @@ static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt
static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
interrupt_enter_prepare(regs, state);
+ irq_enter();
}
static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+ irq_exit();
interrupt_exit_prepare(regs, state);
}
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 6a7ecfca5c3b..5545c9cd17c1 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -23,7 +23,6 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
{
struct pt_regs *old_regs = set_irq_regs(regs);
- irq_enter();
trace_doorbell_entry(regs);
ppc_msgsync();
@@ -36,7 +35,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
smp_ipi_demux_relaxed(); /* already performed the barrier */
trace_doorbell_exit(regs);
- irq_exit();
+
set_irq_regs(old_regs);
}
#else /* CONFIG_SMP */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 90435574b66b..0c2cb41d1286 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -645,8 +645,6 @@ void __do_irq(struct pt_regs *regs)
{
unsigned int irq;
- irq_enter();
-
trace_irq_entry(regs);
/*
@@ -666,8 +664,6 @@ void __do_irq(struct pt_regs *regs)
generic_handle_irq(irq);
trace_irq_exit(regs);
-
- irq_exit();
}
DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c
index 46b2e5de4ef5..d864f07bab74 100644
--- a/arch/powerpc/kernel/tau_6xx.c
+++ b/arch/powerpc/kernel/tau_6xx.c
@@ -104,12 +104,9 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(TAUException)
{
int cpu = smp_processor_id();
- irq_enter();
tau[cpu].interrupts++;
TAUupdate(cpu);
-
- irq_exit();
}
#endif /* CONFIG_TAU_INT */
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 435a251247ed..2177defb7884 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -610,7 +610,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
#endif
old_regs = set_irq_regs(regs);
- irq_enter();
+
trace_timer_interrupt_entry(regs);
if (test_irq_work_pending()) {
@@ -635,7 +635,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
}
trace_timer_interrupt_exit(regs);
- irq_exit();
+
set_irq_regs(old_regs);
}
EXPORT_SYMBOL(timer_interrupt);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 21fd14828827..1623400a0a7b 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -801,7 +801,9 @@ void die_mce(const char *str, struct pt_regs *regs, long err)
* do_exit() checks for in_interrupt() and panics in that case, so
* exit the irq/nmi before calling die.
*/
- if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+ irq_exit();
+ else
nmi_exit();
die(str, regs, err);
}
@@ -1061,7 +1063,6 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
struct pt_regs *old_regs;
old_regs = set_irq_regs(regs);
- irq_enter();
#ifdef CONFIG_VSX
/* Real mode flagged P9 special emu is needed */
@@ -1081,7 +1082,6 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
if (ppc_md.handle_hmi_exception)
ppc_md.handle_hmi_exception(regs);
- irq_exit();
set_irq_regs(old_regs);
}
@@ -1901,13 +1901,9 @@ DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi)
DECLARE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async);
DEFINE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async)
{
- irq_enter();
-
__this_cpu_inc(irq_stat.pmu_irqs);
perf_irq(regs);
-
- irq_exit();
}
DEFINE_INTERRUPT_HANDLER_RAW(performance_monitor_exception)
--
2.23.0
^ permalink raw reply related
* [PATCH v7 36/42] powerpc/64s: reconcile interrupts in C
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
There is no need for this to be in asm, use the new intrrupt entry wrapper.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 15 +++++++++++----
arch/powerpc/kernel/exceptions-64s.S | 26 --------------------------
2 files changed, 11 insertions(+), 30 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 1c966e47b36f..e96d215f518a 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -14,11 +14,14 @@ struct interrupt_state {
static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
-#ifdef CONFIG_PPC_BOOK3E_64
- state->ctx_state = exception_enter();
-#endif
-
+ /*
+ * Book3E reconciles irq soft mask in asm
+ */
#ifdef CONFIG_PPC_BOOK3S_64
+ if (irq_soft_mask_set_return(IRQS_ALL_DISABLED) == IRQS_ENABLED)
+ trace_hardirqs_off();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
if (user_mode(regs)) {
CT_WARN_ON(ct_state() != CONTEXT_USER);
user_exit_irqoff();
@@ -31,6 +34,10 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
}
#endif
+
+#ifdef CONFIG_PPC_BOOK3E_64
+ state->ctx_state = exception_enter();
+#endif
}
/*
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index fe33197ea8fb..39630b3f78b0 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -139,7 +139,6 @@ name:
#define IKVM_VIRT .L_IKVM_VIRT_\name\() /* Virt entry tests KVM */
#define ISTACK .L_ISTACK_\name\() /* Set regular kernel stack */
#define __ISTACK(name) .L_ISTACK_ ## name
-#define IRECONCILE .L_IRECONCILE_\name\() /* Do RECONCILE_IRQ_STATE */
#define IKUAP .L_IKUAP_\name\() /* Do KUAP lock */
#define INT_DEFINE_BEGIN(n) \
@@ -203,9 +202,6 @@ do_define_int n
.ifndef ISTACK
ISTACK=1
.endif
- .ifndef IRECONCILE
- IRECONCILE=1
- .endif
.ifndef IKUAP
IKUAP=1
.endif
@@ -653,10 +649,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
.if ISTACK
ACCOUNT_STOLEN_TIME
.endif
-
- .if IRECONCILE
- RECONCILE_IRQ_STATE(r10, r11)
- .endif
.endm
/*
@@ -935,7 +927,6 @@ INT_DEFINE_BEGIN(system_reset)
*/
ISET_RI=0
ISTACK=0
- IRECONCILE=0
IKVM_REAL=1
INT_DEFINE_END(system_reset)
@@ -1123,7 +1114,6 @@ INT_DEFINE_BEGIN(machine_check_early)
ISTACK=0
IDAR=1
IDSISR=1
- IRECONCILE=0
IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
INT_DEFINE_END(machine_check_early)
@@ -1483,7 +1473,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
INT_DEFINE_BEGIN(data_access_slb)
IVEC=0x380
IAREA=PACA_EXSLB
- IRECONCILE=0
IDAR=1
IKVM_SKIP=1
IKVM_REAL=1
@@ -1510,7 +1499,6 @@ MMU_FTR_SECTION_ELSE
li r3,-EFAULT
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
b interrupt_return
@@ -1568,7 +1556,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
INT_DEFINE_BEGIN(instruction_access_slb)
IVEC=0x480
IAREA=PACA_EXSLB
- IRECONCILE=0
IISIDE=1
IDAR=1
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
@@ -1597,7 +1584,6 @@ MMU_FTR_SECTION_ELSE
li r3,-EFAULT
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
b interrupt_return
@@ -1757,7 +1743,6 @@ EXC_COMMON_BEGIN(program_check_common)
*/
INT_DEFINE_BEGIN(fp_unavailable)
IVEC=0x800
- IRECONCILE=0
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
@@ -1772,7 +1757,6 @@ EXC_VIRT_END(fp_unavailable, 0x4800, 0x100)
EXC_COMMON_BEGIN(fp_unavailable_common)
GEN_COMMON fp_unavailable
bne 1f /* if from user, just load it up */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl kernel_fp_unavailable_exception
0: trap
@@ -1791,7 +1775,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
b fast_interrupt_return
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl fp_unavailable_tm
b interrupt_return
@@ -1856,7 +1839,6 @@ INT_DEFINE_BEGIN(hdecrementer)
IVEC=0x980
IHSRR=1
ISTACK=0
- IRECONCILE=0
IKVM_REAL=1
IKVM_VIRT=1
INT_DEFINE_END(hdecrementer)
@@ -2230,7 +2212,6 @@ INT_DEFINE_BEGIN(hmi_exception_early)
IHSRR=1
IREALMODE_COMMON=1
ISTACK=0
- IRECONCILE=0
IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
IKVM_REAL=1
INT_DEFINE_END(hmi_exception_early)
@@ -2404,7 +2385,6 @@ EXC_COMMON_BEGIN(performance_monitor_common)
*/
INT_DEFINE_BEGIN(altivec_unavailable)
IVEC=0xf20
- IRECONCILE=0
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
@@ -2434,7 +2414,6 @@ BEGIN_FTR_SECTION
b fast_interrupt_return
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_tm
b interrupt_return
@@ -2442,7 +2421,6 @@ BEGIN_FTR_SECTION
1:
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_exception
b interrupt_return
@@ -2458,7 +2436,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
*/
INT_DEFINE_BEGIN(vsx_unavailable)
IVEC=0xf40
- IRECONCILE=0
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_REAL=1
#endif
@@ -2487,7 +2464,6 @@ BEGIN_FTR_SECTION
b load_up_vsx
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl vsx_unavailable_tm
b interrupt_return
@@ -2495,7 +2471,6 @@ BEGIN_FTR_SECTION
1:
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
- RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl vsx_unavailable_exception
b interrupt_return
@@ -2830,7 +2805,6 @@ EXC_VIRT_NONE(0x5800, 0x100)
INT_DEFINE_BEGIN(soft_nmi)
IVEC=0x900
ISTACK=0
- IRECONCILE=0 /* Soft-NMI may fire under local_irq_disable */
INT_DEFINE_END(soft_nmi)
/*
--
2.23.0
^ permalink raw reply related
* [PATCH v7 35/42] powerpc/64s: move context tracking exit to interrupt exit path
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
The interrupt handler wrapper functions are not the ideal place to
maintain context tracking because after they return, the low level exit
code must then determine if there are interrupts to replay, or if the
task should be preempted, etc. Those paths (e.g., schedule_user) include
their own exception_enter/exit pairs to fix this up but it's a bit hacky
(see schedule_user() comments).
Ideally context tracking will go to user mode only when there are no
more interrupts or context switches or other exit processing work to
handle.
64e can not do this because it does not use the C interrupt exit code.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 34 +++++++++++++++++++++++++---
arch/powerpc/kernel/syscall_64.c | 18 +++++++++++++--
2 files changed, 47 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 5a1395499508..1c966e47b36f 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -7,16 +7,30 @@
#include <asm/ftrace.h>
struct interrupt_state {
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3E_64
enum ctx_state ctx_state;
#endif
};
static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3E_64
state->ctx_state = exception_enter();
#endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ if (user_mode(regs)) {
+ CT_WARN_ON(ct_state() != CONTEXT_USER);
+ user_exit_irqoff();
+ } else {
+ /*
+ * CT_WARN_ON comes here via program_check_exception,
+ * so avoid recursion.
+ */
+ if (TRAP(regs) != 0x700)
+ CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
+ }
+#endif
}
/*
@@ -35,9 +49,23 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
*/
static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3E_64
exception_exit(state->ctx_state);
#endif
+
+ /*
+ * Book3S exits to user via interrupt_exit_user_prepare(), which does
+ * context tracking, which is a cleaner way to handle PREEMPT=y
+ * and avoid context entry/exit in e.g., preempt_schedule_irq()),
+ * which is likely to be where the core code wants to end up.
+ *
+ * The above comment explains why we can't do the
+ *
+ * if (user_mode(regs))
+ * user_exit_irqoff();
+ *
+ * sequence here.
+ */
}
static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 45c4420fe339..a2102e7a2713 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -255,9 +255,9 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
ret |= _TIF_RESTOREALL;
}
-again:
local_irq_disable();
+again:
ti_flags = READ_ONCE(*ti_flagsp);
while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
local_irq_enable();
@@ -307,6 +307,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
if (unlikely(!__prep_irq_for_enabled_exit(!scv))) {
user_exit_irqoff();
local_irq_enable();
+ local_irq_disable();
goto again;
}
@@ -341,6 +342,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
BUG_ON(!(regs->msr & MSR_PR));
BUG_ON(!FULL_REGS(regs));
BUG_ON(regs->softe != IRQS_ENABLED);
+ CT_WARN_ON(ct_state() == CONTEXT_USER);
/*
* We don't need to restore AMR on the way back to userspace for KUAP.
@@ -383,8 +385,14 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
}
}
- if (unlikely(!prep_irq_for_enabled_exit(true, !irqs_disabled_flags(flags))))
+ user_enter_irqoff();
+
+ if (unlikely(!__prep_irq_for_enabled_exit(true))) {
+ user_exit_irqoff();
+ local_irq_enable();
+ local_irq_disable();
goto again;
+ }
#ifdef CONFIG_PPC_BOOK3E
if (unlikely(ts->debug.dbcr0 & DBCR0_IDM)) {
@@ -425,6 +433,12 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
unrecoverable_exception(regs);
BUG_ON(regs->msr & MSR_PR);
BUG_ON(!FULL_REGS(regs));
+ /*
+ * CT_WARN_ON comes here via program_check_exception,
+ * so avoid recursion.
+ */
+ if (TRAP(regs) != 0x700)
+ CT_WARN_ON(ct_state() == CONTEXT_USER);
amr = kuap_get_and_check_amr();
--
2.23.0
^ permalink raw reply related
* [PATCH v7 37/42] powerpc/64: move account_stolen_time into its own function
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
This will be used by interrupt entry as well.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/cputime.h | 14 ++++++++++++++
arch/powerpc/kernel/syscall_64.c | 10 +---------
2 files changed, 15 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index ed75d1c318e3..504f7fe6711a 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -87,6 +87,17 @@ static notrace inline void account_cpu_user_exit(void)
acct->starttime_user = tb;
}
+static notrace inline void account_stolen_time(void)
+{
+#ifdef CONFIG_PPC_SPLPAR
+ if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+ struct lppaca *lp = local_paca->lppaca_ptr;
+
+ if (unlikely(local_paca->dtl_ridx != be64_to_cpu(lp->dtl_idx)))
+ accumulate_stolen_time();
+ }
+#endif
+}
#endif /* __KERNEL__ */
#else /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
@@ -96,5 +107,8 @@ static inline void account_cpu_user_entry(void)
static inline void account_cpu_user_exit(void)
{
}
+static notrace inline void account_stolen_time(void)
+{
+}
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
#endif /* __POWERPC_CPUTIME_H */
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index a2102e7a2713..d6be4f9a67e5 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -69,15 +69,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
account_cpu_user_entry();
-#ifdef CONFIG_PPC_SPLPAR
- if (IS_ENABLED(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) &&
- firmware_has_feature(FW_FEATURE_SPLPAR)) {
- struct lppaca *lp = local_paca->lppaca_ptr;
-
- if (unlikely(local_paca->dtl_ridx != be64_to_cpu(lp->dtl_idx)))
- accumulate_stolen_time();
- }
-#endif
+ account_stolen_time();
/*
* This is not required for the syscall exit path, but makes the
--
2.23.0
^ permalink raw reply related
* [PATCH v7 38/42] powerpc/64: entry cpu time accounting in C
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
There is no need for this to be in asm, use the new interrupt entry wrapper.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 6 ++++++
arch/powerpc/include/asm/ppc_asm.h | 24 ------------------------
arch/powerpc/kernel/exceptions-64e.S | 1 -
arch/powerpc/kernel/exceptions-64s.S | 5 -----
4 files changed, 6 insertions(+), 30 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index e96d215f518a..ca8e08b18a16 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -4,6 +4,7 @@
#include <linux/context_tracking.h>
#include <linux/hardirq.h>
+#include <asm/cputime.h>
#include <asm/ftrace.h>
struct interrupt_state {
@@ -25,6 +26,9 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
if (user_mode(regs)) {
CT_WARN_ON(ct_state() != CONTEXT_USER);
user_exit_irqoff();
+
+ account_cpu_user_entry();
+ account_stolen_time();
} else {
/*
* CT_WARN_ON comes here via program_check_exception,
@@ -37,6 +41,8 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
#ifdef CONFIG_PPC_BOOK3E_64
state->ctx_state = exception_enter();
+ if (user_mode(regs))
+ account_cpu_user_entry();
#endif
}
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index cc1bca571332..3dceb64fc9af 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -25,7 +25,6 @@
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
#define ACCOUNT_CPU_USER_ENTRY(ptr, ra, rb)
#define ACCOUNT_CPU_USER_EXIT(ptr, ra, rb)
-#define ACCOUNT_STOLEN_TIME
#else
#define ACCOUNT_CPU_USER_ENTRY(ptr, ra, rb) \
MFTB(ra); /* get timebase */ \
@@ -44,29 +43,6 @@
PPC_LL ra, ACCOUNT_SYSTEM_TIME(ptr); \
add ra,ra,rb; /* add on to system time */ \
PPC_STL ra, ACCOUNT_SYSTEM_TIME(ptr)
-
-#ifdef CONFIG_PPC_SPLPAR
-#define ACCOUNT_STOLEN_TIME \
-BEGIN_FW_FTR_SECTION; \
- beq 33f; \
- /* from user - see if there are any DTL entries to process */ \
- ld r10,PACALPPACAPTR(r13); /* get ptr to VPA */ \
- ld r11,PACA_DTL_RIDX(r13); /* get log read index */ \
- addi r10,r10,LPPACA_DTLIDX; \
- LDX_BE r10,0,r10; /* get log write index */ \
- cmpd cr1,r11,r10; \
- beq+ cr1,33f; \
- bl accumulate_stolen_time; \
- ld r12,_MSR(r1); \
- andi. r10,r12,MSR_PR; /* Restore cr0 (coming from user) */ \
-33: \
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
-
-#else /* CONFIG_PPC_SPLPAR */
-#define ACCOUNT_STOLEN_TIME
-
-#endif /* CONFIG_PPC_SPLPAR */
-
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
/*
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 003999c7836c..e8eb9992a270 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -398,7 +398,6 @@ exc_##n##_common: \
std r10,_NIP(r1); /* save SRR0 to stackframe */ \
std r11,_MSR(r1); /* save SRR1 to stackframe */ \
beq 2f; /* if from kernel mode */ \
- ACCOUNT_CPU_USER_ENTRY(r13,r10,r11);/* accounting (uses cr0+eq) */ \
2: ld r3,excf+EX_R10(r13); /* get back r10 */ \
ld r4,excf+EX_R11(r13); /* get back r11 */ \
mfspr r5,scratch; /* get back r13 */ \
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 39630b3f78b0..94b89ea123f3 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -577,7 +577,6 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real)
kuap_save_amr_and_lock r9, r10, cr1, cr0
.endif
beq 101f /* if from kernel mode */
- ACCOUNT_CPU_USER_ENTRY(r13, r9, r10)
BEGIN_FTR_SECTION
ld r9,IAREA+EX_PPR(r13) /* Read PPR from paca */
std r9,_PPR(r1)
@@ -645,10 +644,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
ld r11,exception_marker@toc(r2)
std r10,RESULT(r1) /* clear regs->result */
std r11,STACK_FRAME_OVERHEAD-16(r1) /* mark the frame */
-
- .if ISTACK
- ACCOUNT_STOLEN_TIME
- .endif
.endm
/*
--
2.23.0
^ permalink raw reply related
* [PATCH v7 39/42] powerpc: move NMI entry/exit code into wrapper
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
This moves the common NMI entry and exit code into the interrupt handler
wrappers.
This changes the behaviour of soft-NMI (watchdog) and HMI interrupts, and
also MCE interrupts on 64e, by adding missing parts of the NMI entry to
them.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 28 ++++++++++++++++++++++
arch/powerpc/kernel/mce.c | 11 ---------
arch/powerpc/kernel/traps.c | 35 +++++-----------------------
arch/powerpc/kernel/watchdog.c | 10 ++++----
4 files changed, 38 insertions(+), 46 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index ca8e08b18a16..cd819d42573c 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -94,14 +94,42 @@ static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct int
}
struct interrupt_nmi_state {
+#ifdef CONFIG_PPC64
+ u8 ftrace_enabled;
+#endif
};
static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
{
+#ifdef CONFIG_PPC64
+ /* Allow DEC and PMI to be traced when they are soft-NMI */
+ if (TRAP(regs) != 0x900 && TRAP(regs) != 0xf00 && TRAP(regs) != 0x260) {
+ state->ftrace_enabled = this_cpu_get_ftrace_enabled();
+ this_cpu_set_ftrace_enabled(0);
+ }
+#endif
+
+ /*
+ * Do not use nmi_enter() for pseries hash guest taking a real-mode
+ * NMI because not everything it touches is within the RMA limit.
+ */
+ if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64) ||
+ !firmware_has_feature(FW_FEATURE_LPAR) ||
+ radix_enabled() || (mfmsr() & MSR_DR))
+ nmi_enter();
}
static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
{
+ if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64) ||
+ !firmware_has_feature(FW_FEATURE_LPAR) ||
+ radix_enabled() || (mfmsr() & MSR_DR))
+ nmi_exit();
+
+#ifdef CONFIG_PPC64
+ if (TRAP(regs) != 0x900 && TRAP(regs) != 0xf00 && TRAP(regs) != 0x260)
+ this_cpu_set_ftrace_enabled(state->ftrace_enabled);
+#endif
}
/**
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 54269947113d..51456217ec40 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -592,12 +592,6 @@ EXPORT_SYMBOL_GPL(machine_check_print_event_info);
DEFINE_INTERRUPT_HANDLER_NMI(machine_check_early)
{
long handled = 0;
- u8 ftrace_enabled = this_cpu_get_ftrace_enabled();
-
- this_cpu_set_ftrace_enabled(0);
- /* Do not use nmi_enter/exit for pseries hpte guest */
- if (radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR))
- nmi_enter();
hv_nmi_check_nonrecoverable(regs);
@@ -607,11 +601,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_early)
if (ppc_md.machine_check_early)
handled = ppc_md.machine_check_early(regs);
- if (radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR))
- nmi_exit();
-
- this_cpu_set_ftrace_enabled(ftrace_enabled);
-
return handled;
}
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 1623400a0a7b..e61391f6948f 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -435,11 +435,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
{
unsigned long hsrr0, hsrr1;
bool saved_hsrrs = false;
- u8 ftrace_enabled = this_cpu_get_ftrace_enabled();
-
- this_cpu_set_ftrace_enabled(0);
-
- nmi_enter();
/*
* System reset can interrupt code where HSRRs are live and MSR[RI]=1.
@@ -514,10 +509,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
mtspr(SPRN_HSRR1, hsrr1);
}
- nmi_exit();
-
- this_cpu_set_ftrace_enabled(ftrace_enabled);
-
/* What should we do here? We could issue a shutdown or hard reset. */
return 0;
@@ -809,6 +800,12 @@ void die_mce(const char *str, struct pt_regs *regs, long err)
}
NOKPROBE_SYMBOL(die_mce);
+/*
+ * BOOK3S_64 does not call this handler as a non-maskable interrupt
+ * (it uses its own early real-mode handler to handle the MCE proper
+ * and then raises irq_work to call this handler when interrupts are
+ * enabled).
+ */
#ifdef CONFIG_PPC_BOOK3S_64
DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception)
#else
@@ -817,20 +814,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
{
int recover = 0;
- /*
- * BOOK3S_64 does not call this handler as a non-maskable interrupt
- * (it uses its own early real-mode handler to handle the MCE proper
- * and then raises irq_work to call this handler when interrupts are
- * enabled).
- *
- * This is silly. The BOOK3S_64 should just call a different function
- * rather than expecting semantics to magically change. Something
- * like 'non_nmi_machine_check_exception()', perhaps?
- */
- const bool nmi = !IS_ENABLED(CONFIG_PPC_BOOK3S_64);
-
- if (nmi) nmi_enter();
-
__this_cpu_inc(irq_stat.mce_exceptions);
add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
@@ -862,8 +845,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
if (!(regs->msr & MSR_RI))
die_mce("Unrecoverable Machine check", regs, SIGBUS);
- if (nmi) nmi_exit();
-
#ifdef CONFIG_PPC_BOOK3S_64
return;
#else
@@ -1886,14 +1867,10 @@ DEFINE_INTERRUPT_HANDLER(vsx_unavailable_tm)
DECLARE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi);
DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi)
{
- nmi_enter();
-
__this_cpu_inc(irq_stat.pmu_irqs);
perf_irq(regs);
- nmi_exit();
-
return 0;
}
#endif
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index 824b9376ac35..dc39534836a3 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -254,11 +254,12 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
int cpu = raw_smp_processor_id();
u64 tb;
+ /* should only arrive from kernel, with irqs disabled */
+ WARN_ON_ONCE(!arch_irq_disabled_regs(regs));
+
if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
return 0;
- nmi_enter();
-
__this_cpu_inc(irq_stat.soft_nmi_irqs);
tb = get_tb();
@@ -266,7 +267,7 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
wd_smp_lock(&flags);
if (cpumask_test_cpu(cpu, &wd_smp_cpus_stuck)) {
wd_smp_unlock(&flags);
- goto out;
+ return 0;
}
set_cpu_stuck(cpu, tb);
@@ -290,9 +291,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
if (wd_panic_timeout_tb < 0x7fffffff)
mtspr(SPRN_DEC, wd_panic_timeout_tb);
-out:
- nmi_exit();
-
return 0;
}
--
2.23.0
^ permalink raw reply related
* [PATCH v7 40/42] powerpc/64s: move NMI soft-mask handling to C
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
Saving and restoring soft-mask state can now be done in C using the
interrupt handler wrapper functions.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 25 ++++++++++++
arch/powerpc/kernel/exceptions-64s.S | 60 ----------------------------
2 files changed, 25 insertions(+), 60 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index cd819d42573c..72a585084066 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -95,6 +95,10 @@ static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct int
struct interrupt_nmi_state {
#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
+ u8 irq_soft_mask;
+ u8 irq_happened;
+#endif
u8 ftrace_enabled;
#endif
};
@@ -102,6 +106,20 @@ struct interrupt_nmi_state {
static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
{
#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
+ state->irq_soft_mask = local_paca->irq_soft_mask;
+ state->irq_happened = local_paca->irq_happened;
+
+ /*
+ * Set IRQS_ALL_DISABLED unconditionally so irqs_disabled() does
+ * the right thing, and set IRQ_HARD_DIS. We do not want to reconcile
+ * because that goes through irq tracing which we don't want in NMI.
+ */
+ local_paca->irq_soft_mask = IRQS_ALL_DISABLED;
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+ /* Don't do any per-CPU operations until interrupt state is fixed */
+#endif
/* Allow DEC and PMI to be traced when they are soft-NMI */
if (TRAP(regs) != 0x900 && TRAP(regs) != 0xf00 && TRAP(regs) != 0x260) {
state->ftrace_enabled = this_cpu_get_ftrace_enabled();
@@ -129,6 +147,13 @@ static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct inter
#ifdef CONFIG_PPC64
if (TRAP(regs) != 0x900 && TRAP(regs) != 0xf00 && TRAP(regs) != 0x260)
this_cpu_set_ftrace_enabled(state->ftrace_enabled);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* Check we didn't change the pending interrupt mask. */
+ WARN_ON_ONCE((state->irq_happened | PACA_IRQ_HARD_DIS) != local_paca->irq_happened);
+ local_paca->irq_happened = state->irq_happened;
+ local_paca->irq_soft_mask = state->irq_soft_mask;
+#endif
#endif
}
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 94b89ea123f3..2fca2bad6b02 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1008,20 +1008,6 @@ EXC_COMMON_BEGIN(system_reset_common)
ld r1,PACA_NMI_EMERG_SP(r13)
subi r1,r1,INT_FRAME_SIZE
__GEN_COMMON_BODY system_reset
- /*
- * Set IRQS_ALL_DISABLED unconditionally so irqs_disabled() does
- * the right thing. We do not want to reconcile because that goes
- * through irq tracing which we don't want in NMI.
- *
- * Save PACAIRQHAPPENED to RESULT (otherwise unused), and set HARD_DIS
- * as we are running with MSR[EE]=0.
- */
- li r10,IRQS_ALL_DISABLED
- stb r10,PACAIRQSOFTMASK(r13)
- lbz r10,PACAIRQHAPPENED(r13)
- std r10,RESULT(r1)
- ori r10,r10,PACA_IRQ_HARD_DIS
- stb r10,PACAIRQHAPPENED(r13)
addi r3,r1,STACK_FRAME_OVERHEAD
bl system_reset_exception
@@ -1037,14 +1023,6 @@ EXC_COMMON_BEGIN(system_reset_common)
subi r10,r10,1
sth r10,PACA_IN_NMI(r13)
- /*
- * Restore soft mask settings.
- */
- ld r10,RESULT(r1)
- stb r10,PACAIRQHAPPENED(r13)
- ld r10,SOFTE(r1)
- stb r10,PACAIRQSOFTMASK(r13)
-
kuap_kernel_restore r9, r10
EXCEPTION_RESTORE_REGS
RFI_TO_USER_OR_KERNEL
@@ -1190,30 +1168,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
li r10,MSR_RI
mtmsrd r10,1
- /*
- * Set IRQS_ALL_DISABLED and save PACAIRQHAPPENED (see
- * system_reset_common)
- */
- li r10,IRQS_ALL_DISABLED
- stb r10,PACAIRQSOFTMASK(r13)
- lbz r10,PACAIRQHAPPENED(r13)
- std r10,RESULT(r1)
- ori r10,r10,PACA_IRQ_HARD_DIS
- stb r10,PACAIRQHAPPENED(r13)
-
addi r3,r1,STACK_FRAME_OVERHEAD
bl machine_check_early
std r3,RESULT(r1) /* Save result */
ld r12,_MSR(r1)
- /*
- * Restore soft mask settings.
- */
- ld r10,RESULT(r1)
- stb r10,PACAIRQHAPPENED(r13)
- ld r10,SOFTE(r1)
- stb r10,PACAIRQSOFTMASK(r13)
-
#ifdef CONFIG_PPC_P7_NAP
/*
* Check if thread was in power saving mode. We come here when any
@@ -2818,17 +2777,6 @@ EXC_COMMON_BEGIN(soft_nmi_common)
subi r1,r1,INT_FRAME_SIZE
__GEN_COMMON_BODY soft_nmi
- /*
- * Set IRQS_ALL_DISABLED and save PACAIRQHAPPENED (see
- * system_reset_common)
- */
- li r10,IRQS_ALL_DISABLED
- stb r10,PACAIRQSOFTMASK(r13)
- lbz r10,PACAIRQHAPPENED(r13)
- std r10,RESULT(r1)
- ori r10,r10,PACA_IRQ_HARD_DIS
- stb r10,PACAIRQHAPPENED(r13)
-
addi r3,r1,STACK_FRAME_OVERHEAD
bl soft_nmi_interrupt
@@ -2836,14 +2784,6 @@ EXC_COMMON_BEGIN(soft_nmi_common)
li r9,0
mtmsrd r9,1
- /*
- * Restore soft mask settings.
- */
- ld r10,RESULT(r1)
- stb r10,PACAIRQHAPPENED(r13)
- ld r10,SOFTE(r1)
- stb r10,PACAIRQSOFTMASK(r13)
-
kuap_kernel_restore r9, r10
EXCEPTION_RESTORE_REGS hsrr=0
RFI_TO_KERNEL
--
2.23.0
^ permalink raw reply related
* [PATCH v7 41/42] powerpc/64s: runlatch interrupt handling in C
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
There is no need for this to be in asm, use the new intrrupt entry wrapper.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 7 +++++++
arch/powerpc/kernel/exceptions-64s.S | 18 ------------------
2 files changed, 7 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 72a585084066..4badb3e51c19 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -6,6 +6,7 @@
#include <linux/hardirq.h>
#include <asm/cputime.h>
#include <asm/ftrace.h>
+#include <asm/runlatch.h>
struct interrupt_state {
#ifdef CONFIG_PPC_BOOK3E_64
@@ -83,6 +84,12 @@ static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt
static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
{
+#ifdef CONFIG_PPC_BOOK3S_64
+ if (cpu_has_feature(CPU_FTR_CTRL) &&
+ !test_thread_local_flags(_TLF_RUNLATCH))
+ __ppc64_runlatch_on();
+#endif
+
interrupt_enter_prepare(regs, state);
irq_enter();
}
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 2fca2bad6b02..27351276c54b 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -692,14 +692,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
ld r1,GPR1(r1)
.endm
-#define RUNLATCH_ON \
-BEGIN_FTR_SECTION \
- ld r3, PACA_THREAD_INFO(r13); \
- ld r4,TI_LOCAL_FLAGS(r3); \
- andi. r0,r4,_TLF_RUNLATCH; \
- beql ppc64_runlatch_on_trampoline; \
-END_FTR_SECTION_IFSET(CPU_FTR_CTRL)
-
/*
* When the idle code in power4_idle puts the CPU into NAP mode,
* it has to do so in a loop, and relies on the external interrupt
@@ -1585,7 +1577,6 @@ EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100)
EXC_COMMON_BEGIN(hardware_interrupt_common)
GEN_COMMON hardware_interrupt
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_IRQ
b interrupt_return
@@ -1771,7 +1762,6 @@ EXC_VIRT_END(decrementer, 0x4900, 0x80)
EXC_COMMON_BEGIN(decrementer_common)
GEN_COMMON decrementer
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
bl timer_interrupt
b interrupt_return
@@ -1857,7 +1847,6 @@ EXC_VIRT_END(doorbell_super, 0x4a00, 0x100)
EXC_COMMON_BEGIN(doorbell_super_common)
GEN_COMMON doorbell_super
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_DOORBELL
bl doorbell_exception
@@ -2212,7 +2201,6 @@ EXC_COMMON_BEGIN(hmi_exception_early_common)
EXC_COMMON_BEGIN(hmi_exception_common)
GEN_COMMON hmi_exception
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
bl handle_hmi_exception
b interrupt_return
@@ -2242,7 +2230,6 @@ EXC_VIRT_END(h_doorbell, 0x4e80, 0x20)
EXC_COMMON_BEGIN(h_doorbell_common)
GEN_COMMON h_doorbell
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_DOORBELL
bl doorbell_exception
@@ -2276,7 +2263,6 @@ EXC_VIRT_END(h_virt_irq, 0x4ea0, 0x20)
EXC_COMMON_BEGIN(h_virt_irq_common)
GEN_COMMON h_virt_irq
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_IRQ
b interrupt_return
@@ -2323,7 +2309,6 @@ EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
EXC_COMMON_BEGIN(performance_monitor_common)
GEN_COMMON performance_monitor
FINISH_NAP
- RUNLATCH_ON
addi r3,r1,STACK_FRAME_OVERHEAD
bl performance_monitor_exception
b interrupt_return
@@ -3057,9 +3042,6 @@ kvmppc_skip_Hinterrupt:
* come here.
*/
-EXC_COMMON_BEGIN(ppc64_runlatch_on_trampoline)
- b __ppc64_runlatch_on
-
USE_FIXED_SECTION(virt_trampolines)
/*
* All code below __end_interrupts is treated as soft-masked. If
--
2.23.0
^ permalink raw reply related
* [PATCH v7 42/42] powerpc/64s: power4 nap fixup in C
From: Nicholas Piggin @ 2021-01-30 13:08 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-1-npiggin@gmail.com>
There is no need for this to be in asm, use the new intrrupt entry wrapper.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/interrupt.h | 15 +++++++++
arch/powerpc/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, 26 insertions(+), 45 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 4badb3e51c19..25f2420b1965 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -8,6 +8,16 @@
#include <asm/ftrace.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))) {
+ clear_thread_local_flags(_TLF_NAPPING);
+ regs->nip = (unsigned long)power4_idle_nap_return;
+ }
+#endif
+}
+
struct interrupt_state {
#ifdef CONFIG_PPC_BOOK3E_64
enum ctx_state ctx_state;
@@ -98,6 +108,9 @@ static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct int
{
irq_exit();
interrupt_exit_prepare(regs, state);
+
+ /* Adjust at exit so the main handler sees the true NIA */
+ nap_adjust_return(regs);
}
struct interrupt_nmi_state {
@@ -151,6 +164,8 @@ static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct inter
radix_enabled() || (mfmsr() & MSR_DR))
nmi_exit();
+ nap_adjust_return(regs);
+
#ifdef CONFIG_PPC64
if (TRAP(regs) != 0x900 && TRAP(regs) != 0xf00 && TRAP(regs) != 0x260)
this_cpu_set_ftrace_enabled(state->ftrace_enabled);
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 8acc3590c971..eedc3c775141 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -393,6 +393,7 @@ extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val);
extern unsigned long isa206_idle_insn_mayloss(unsigned long type);
#ifdef CONFIG_PPC_970_NAP
extern void power4_idle_nap(void);
+void power4_idle_nap_return(void);
#endif
extern unsigned long cpuidle_disable;
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 386d576673a1..bf137151100b 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -152,6 +152,12 @@ void arch_setup_new_exec(void);
#ifndef __ASSEMBLY__
+static inline void clear_thread_local_flags(unsigned int flags)
+{
+ struct thread_info *ti = current_thread_info();
+ ti->local_flags &= ~flags;
+}
+
static inline bool test_thread_local_flags(unsigned int flags)
{
struct thread_info *ti = current_thread_info();
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 27351276c54b..5478ffa85603 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -692,25 +692,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
ld r1,GPR1(r1)
.endm
-/*
- * When the idle code in power4_idle puts the CPU into NAP mode,
- * it has to do so in a loop, and relies on the external interrupt
- * and decrementer interrupt entry code to get it out of the loop.
- * It sets the _TLF_NAPPING bit in current_thread_info()->local_flags
- * to signal that it is in the loop and needs help to get out.
- */
-#ifdef CONFIG_PPC_970_NAP
-#define FINISH_NAP \
-BEGIN_FTR_SECTION \
- ld r11, PACA_THREAD_INFO(r13); \
- ld r9,TI_LOCAL_FLAGS(r11); \
- andi. r10,r9,_TLF_NAPPING; \
- bnel power4_fixup_nap; \
-END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
-#else
-#define FINISH_NAP
-#endif
-
/*
* There are a few constraints to be concerned with.
* - Real mode exceptions code/data must be located at their physical location.
@@ -1248,7 +1229,6 @@ EXC_COMMON_BEGIN(machine_check_common)
*/
GEN_COMMON machine_check
- FINISH_NAP
/* Enable MSR_RI when finished with PACA_EXMC */
li r10,MSR_RI
mtmsrd r10,1
@@ -1576,7 +1556,6 @@ EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100)
EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100)
EXC_COMMON_BEGIN(hardware_interrupt_common)
GEN_COMMON hardware_interrupt
- FINISH_NAP
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_IRQ
b interrupt_return
@@ -1761,7 +1740,6 @@ EXC_VIRT_BEGIN(decrementer, 0x4900, 0x80)
EXC_VIRT_END(decrementer, 0x4900, 0x80)
EXC_COMMON_BEGIN(decrementer_common)
GEN_COMMON decrementer
- FINISH_NAP
addi r3,r1,STACK_FRAME_OVERHEAD
bl timer_interrupt
b interrupt_return
@@ -1846,7 +1824,6 @@ EXC_VIRT_BEGIN(doorbell_super, 0x4a00, 0x100)
EXC_VIRT_END(doorbell_super, 0x4a00, 0x100)
EXC_COMMON_BEGIN(doorbell_super_common)
GEN_COMMON doorbell_super
- FINISH_NAP
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_DOORBELL
bl doorbell_exception
@@ -2200,7 +2177,6 @@ EXC_COMMON_BEGIN(hmi_exception_early_common)
EXC_COMMON_BEGIN(hmi_exception_common)
GEN_COMMON hmi_exception
- FINISH_NAP
addi r3,r1,STACK_FRAME_OVERHEAD
bl handle_hmi_exception
b interrupt_return
@@ -2229,7 +2205,6 @@ EXC_VIRT_BEGIN(h_doorbell, 0x4e80, 0x20)
EXC_VIRT_END(h_doorbell, 0x4e80, 0x20)
EXC_COMMON_BEGIN(h_doorbell_common)
GEN_COMMON h_doorbell
- FINISH_NAP
addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_DOORBELL
bl doorbell_exception
@@ -2262,7 +2237,6 @@ EXC_VIRT_BEGIN(h_virt_irq, 0x4ea0, 0x20)
EXC_VIRT_END(h_virt_irq, 0x4ea0, 0x20)
EXC_COMMON_BEGIN(h_virt_irq_common)
GEN_COMMON h_virt_irq
- FINISH_NAP
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_IRQ
b interrupt_return
@@ -2308,7 +2282,6 @@ EXC_VIRT_BEGIN(performance_monitor, 0x4f00, 0x20)
EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
EXC_COMMON_BEGIN(performance_monitor_common)
GEN_COMMON performance_monitor
- FINISH_NAP
addi r3,r1,STACK_FRAME_OVERHEAD
bl performance_monitor_exception
b interrupt_return
@@ -3059,24 +3032,6 @@ USE_FIXED_SECTION(virt_trampolines)
__end_interrupts:
DEFINE_FIXED_SYMBOL(__end_interrupts)
-#ifdef CONFIG_PPC_970_NAP
- /*
- * Called by exception entry code if _TLF_NAPPING was set, this clears
- * the NAPPING flag, and redirects the exception exit to
- * power4_fixup_nap_return.
- */
- .globl power4_fixup_nap
-EXC_COMMON_BEGIN(power4_fixup_nap)
- andc r9,r9,r10
- std r9,TI_LOCAL_FLAGS(r11)
- LOAD_REG_ADDR(r10, power4_idle_nap_return)
- std r10,_NIP(r1)
- blr
-
-power4_idle_nap_return:
- blr
-#endif
-
CLOSE_FIXED_SECTION(real_vectors);
CLOSE_FIXED_SECTION(real_trampolines);
CLOSE_FIXED_SECTION(virt_vectors);
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 22f249b6f58d..27d2e6a72ec9 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -201,4 +201,8 @@ _GLOBAL(power4_idle_nap)
mtmsrd r7
isync
b 1b
+
+ .globl power4_idle_nap_return
+power4_idle_nap_return:
+ blr
#endif
--
2.23.0
^ permalink raw reply related
* Re: [PATCH] powerpc64/idle: Fix SP offsets when saving GPRs
From: Nicholas Piggin @ 2021-01-30 13:44 UTC (permalink / raw)
To: Christopher M. Riedl, linuxppc-dev, Michael Ellerman
In-Reply-To: <87o8h6d5jg.fsf@mpe.ellerman.id.au>
Excerpts from Michael Ellerman's message of January 30, 2021 9:32 pm:
> "Christopher M. Riedl" <cmr@codefail.de> writes:
>> The idle entry/exit code saves/restores GPRs in the stack "red zone"
>> (Protected Zone according to PowerPC64 ELF ABI v2). However, the offset
>> used for the first GPR is incorrect and overwrites the back chain - the
>> Protected Zone actually starts below the current SP. In practice this is
>> probably not an issue, but it's still incorrect so fix it.
>
> Nice catch.
>
> Corrupting the back chain means you can't backtrace from there, which
> could be confusing for debugging one day.
Yeah, we seem to have got away without noticing because the CPU will
wake up and return out of here before it tries to unwind the stack,
but if you tried to walk it by hand if the CPU got stuck in idle or
something, then we'd get confused.
> It does make me wonder why we don't just create a stack frame and use
> the normal macros? It would use a bit more stack space, but we shouldn't
> be short of stack space when going idle.
>
> Nick, was there a particular reason for using the red zone?
I don't recall a particular reason, I think a normal stack frame is
probably a good idea.
Thanks,
Nick
^ permalink raw reply
* Re: [PATCH] powerpc/fault: fix wrong KUAP fault for IO_URING
From: Nicholas Piggin @ 2021-01-30 13:54 UTC (permalink / raw)
To: Aneesh Kumar K.V, Christophe Leroy, Michael Ellerman, Zorro Lang
Cc: Jens Axboe, linuxppc-dev
In-Reply-To: <87r1m2d5z4.fsf@mpe.ellerman.id.au>
Excerpts from Michael Ellerman's message of January 30, 2021 9:22 pm:
> Christophe Leroy <christophe.leroy@csgroup.eu> writes:
>> +Aneesh
>>
>> Le 29/01/2021 à 07:52, Zorro Lang a écrit :
> ..
>>> [ 96.200296] ------------[ cut here ]------------
>>> [ 96.200304] Bug: Read fault blocked by KUAP!
>>> [ 96.200309] WARNING: CPU: 3 PID: 1876 at arch/powerpc/mm/fault.c:229 bad_kernel_fault+0x180/0x310
>>
>>> [ 96.200734] NIP [c000000000849424] fault_in_pages_readable+0x104/0x350
>>> [ 96.200741] LR [c00000000084952c] fault_in_pages_readable+0x20c/0x350
>>> [ 96.200747] --- interrupt: 300
>>
>>
>> Problem happens in a section where userspace access is supposed to be granted, so the patch you
>> proposed is definitely not the right fix.
>>
>> c000000000849408: 2c 01 00 4c isync
>> c00000000084940c: a6 03 3d 7d mtspr 29,r9 <== granting userspace access permission
>> c000000000849410: 2c 01 00 4c isync
>> c000000000849414: 00 00 36 e9 ld r9,0(r22)
>> c000000000849418: 20 00 29 81 lwz r9,32(r9)
>> c00000000084941c: 00 02 29 71 andi. r9,r9,512
>> c000000000849420: 78 d3 5e 7f mr r30,r26
>> ==> c000000000849424: 00 00 bf 8b lbz r29,0(r31) <== accessing userspace
>> c000000000849428: 10 00 82 41 beq c000000000849438 <fault_in_pages_readable+0x118>
>> c00000000084942c: 2c 01 00 4c isync
>> c000000000849430: a6 03 bd 7e mtspr 29,r21 <== clearing userspace access permission
>> c000000000849434: 2c 01 00 4c isync
>>
>> My first guess is that the problem is linked to the following function, see the comment
>>
>> /*
>> * For kernel thread that doesn't have thread.regs return
>> * default AMR/IAMR values.
>> */
>> static inline u64 current_thread_amr(void)
>> {
>> if (current->thread.regs)
>> return current->thread.regs->amr;
>> return AMR_KUAP_BLOCKED;
>> }
>>
>> Above function was introduced by commit 48a8ab4eeb82 ("powerpc/book3s64/pkeys: Don't update SPRN_AMR
>> when in kernel mode")
>
> Yeah that's a bit of a curly one.
>
> At some point io_uring did kthread_use_mm(), which is supposed to mean
> the kthread can operate on behalf of the original process that submitted
> the IO.
>
> But because KUAP is implemented using memory protection keys, it depends
> on the value of the AMR register, which is not part of the mm, it's in
> thread.regs->amr.
>
> And what's worse by the time we're in kthread_use_mm() we no longer have
> access to the thread.regs->amr of the original process that submitted
> the IO.
>
> We also can't simply move the AMR into the mm, precisely because it's
> per thread, not per mm.
>
> So TBH I don't know how we're going to fix this.
>
> I guess we could return AMR=unblocked for kernel threads, but that's
> arguably a bug because it allows a process to circumvent memory keys by
> asking the kernel to do the access.
We shouldn't need to inherit AMR should we? We only need it to be locked
for kernel threads until it's explicitly unlocked -- nothing mm specific
there. I think current_thread_amr could return 0 for kernel threads? Or
I would even avoid using that function for allow_user_access and open
code the kthread case and remove it from current_thread_amr().
Thanks,
Nick
^ permalink raw reply
* Re: [PATCH v2] tpm: ibmvtpm: fix error return code in tpm_ibmvtpm_probe()
From: Jarkko Sakkinen @ 2021-01-30 21:14 UTC (permalink / raw)
To: Stefan Berger, Stefan Berger
Cc: Wang Hai, linux-kernel, Hulk Robot, paulus, linux-integrity,
linuxppc-dev
In-Reply-To: <262c3095-d4c0-f124-c8bc-e99685cbe572@linux.ibm.com>
On Fri, 2021-01-29 at 13:57 -0500, Stefan Berger wrote:
> On 1/29/21 12:35 PM, Jarkko Sakkinen wrote:
> > On Mon, Jan 25, 2021 at 08:47:53PM -0500, Stefan Berger wrote:
> > > From: Stefan Berger <stefanb@linux.ibm.com>
> > >
> > > Return error code -ETIMEDOUT rather than '0' when waiting for the
> > > rtce_buf to be set has timed out.
> > >
> > > Fixes: d8d74ea3c002 ("tpm: ibmvtpm: Wait for buffer to be set before proceeding")
> > > Reported-by: Hulk Robot <hulkci@huawei.com>
> > > Signed-off-by: Wang Hai <wanghai38@huawei.com>
> > > Signed-off-by: Stefan Berger <stefanb@linux.ibm.com>
> > > ---
> > Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
> >
> > Thanks! Should I add
> >
> > Cc: stable@vger.kernel.org to this?
>
> Yes, that would be good! Thank you!
OK, it's applied.
> Stefan
/Jarkko
^ permalink raw reply
* [PATCH 1/2] powerpc/Kconfig: Fix unmet direct dependency on NET
From: Florian Fainelli @ 2021-01-30 22:55 UTC (permalink / raw)
To: linux-kernel, arndb
Cc: Christophe Leroy, Florian Fainelli, kbuild-all, kernel test robot,
Arnd Bergmann, Michal Simek, Paul Mackerras,
open list:LINUX FOR POWERPC EMBEDDED PPC4XX
The kbuild test robot was able to generate a configuration where
ETHERNET and NETDEVICES was selected by the Akenobo platform but not
NET, which resulted in various build failures and these Kconfig
warnings:
WARNING: unmet direct dependencies detected for NETDEVICES
Depends on [n]: NET [=n]
Selected by [y]:
- AKEBONO [=y] && PPC_47x [=y]
WARNING: unmet direct dependencies detected for ETHERNET
Depends on [n]: NETDEVICES [=y] && NET [=n]
Selected by [y]:
- AKEBONO [=y] && PPC_47x [=y]
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
arch/powerpc/platforms/44x/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index 78ac6d67a935..68bd647c878f 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -206,6 +206,7 @@ config AKEBONO
select PPC4xx_HSTA_MSI
select I2C
select I2C_IBM_IIC
+ select NET
select NETDEVICES
select ETHERNET
select NET_VENDOR_IBM
--
2.25.1
^ permalink raw reply related
* Re: [PATCH] powerpc: fix AKEBONO build failures
From: Randy Dunlap @ 2021-01-30 23:21 UTC (permalink / raw)
To: Michael Ellerman, Yury Norov, linuxppc-dev,
Linux Kernel Mailing List
Cc: Paul Mackerras
In-Reply-To: <875z3prcwg.fsf@mpe.ellerman.id.au>
On 1/21/21 5:14 PM, Michael Ellerman wrote:
> Randy Dunlap <rdunlap@infradead.org> writes:
>> On 1/20/21 1:29 PM, Yury Norov wrote:
>>> Hi all,
>>>
>>> I found the power pc build broken on today's
>>> linux-next (647060f3b592).
>>
>> Darn, I was building linux-5.11-rc4.
>>
>> I'll try linux-next after I send this.
>>
>> ---
>> From: Randy Dunlap <rdunlap@infradead.org>
>>
>> Fulfill AKEBONO Kconfig requirements.
>>
>> Fixes these Kconfig warnings (and more) and fixes the subsequent
>> build errors:
>>
>> WARNING: unmet direct dependencies detected for NETDEVICES
>> Depends on [n]: NET [=n]
>> Selected by [y]:
>> - AKEBONO [=y] && PPC_47x [=y]
>>
>> WARNING: unmet direct dependencies detected for MMC_SDHCI
>> Depends on [n]: MMC [=n] && HAS_DMA [=y]
>> Selected by [y]:
>> - AKEBONO [=y] && PPC_47x [=y]
>>
>> Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
>> Cc: Michael Ellerman <mpe@ellerman.id.au>
>> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
>> Cc: Paul Mackerras <paulus@samba.org>
>> Cc: linuxppc-dev@lists.ozlabs.org
>> Cc: Yury Norov <yury.norov@gmail.com>
>> ---
>> arch/powerpc/platforms/44x/Kconfig | 2 ++
>> 1 file changed, 2 insertions(+)
>>
>> --- lnx-511-rc4.orig/arch/powerpc/platforms/44x/Kconfig
>> +++ lnx-511-rc4/arch/powerpc/platforms/44x/Kconfig
>> @@ -206,6 +206,7 @@ config AKEBONO
>> select PPC4xx_HSTA_MSI
>> select I2C
>> select I2C_IBM_IIC
>> + select NET
>> select NETDEVICES
>> select ETHERNET
>> select NET_VENDOR_IBM
>
> I think the problem here is too much use of select, for things that
> should instead be in the defconfig.
>
> The patch below results in the same result for make
> 44x/akebono_defconfig. Does it fix the original issue?
Hi Michael,
Sorry for the delay.
Changing the akebono_defconfig doesn't cause the missing symbols
to be set -- the defconfig is not being used here.
I guess that if you have users who set CONFIG_AKEBONO and expect
it to build cleanly, you will need something like my patch or the
patch that Florian just posted.
Changing the akebono_defconfig also would not help 'make randconfig'
builds to build cleanly if they had happened to enable AKEBONO.
> We don't need to add ETHERNET or NET_VENDOR_IBM to the defconfig because
> they're both default y.
>
> cheers
^ permalink raw reply
* [PATCH] cxl: Simplify bool conversion
From: Yang Li @ 2021-01-29 8:25 UTC (permalink / raw)
To: fbarrat; +Cc: ajd, arnd, gregkh, linux-kernel, Yang Li, linuxppc-dev
Fix the following coccicheck warning:
./drivers/misc/cxl/sysfs.c:181:48-53: WARNING: conversion to bool not
needed here
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
---
drivers/misc/cxl/sysfs.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index d97a243..c173a5e 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -178,7 +178,7 @@ static ssize_t perst_reloads_same_image_store(struct device *device,
if ((rc != 1) || !(val == 1 || val == 0))
return -EINVAL;
- adapter->perst_same_image = (val == 1 ? true : false);
+ adapter->perst_same_image = (val == 1);
return count;
}
--
1.8.3.1
^ permalink raw reply related
* [RFC 00/20] TLB batching consolidation and enhancements
From: Nadav Amit @ 2021-01-31 0:11 UTC (permalink / raw)
To: linux-mm, linux-kernel
Cc: Andrea Arcangeli, linux-s390, x86, Yu Zhao, Will Deacon,
Peter Zijlstra, Mel Gorman, Dave Hansen, linux-csky, Nadav Amit,
Nick Piggin, Andy Lutomirski, Andrew Morton, linuxppc-dev,
Thomas Gleixner
From: Nadav Amit <namit@vmware.com>
There are currently (at least?) 5 different TLB batching schemes in the
kernel:
1. Using mmu_gather (e.g., zap_page_range()).
2. Using {inc|dec}_tlb_flush_pending() to inform other threads on the
ongoing deferred TLB flush and flushing the entire range eventually
(e.g., change_protection_range()).
3. arch_{enter|leave}_lazy_mmu_mode() for sparc and powerpc (and Xen?).
4. Batching per-table flushes (move_ptes()).
5. By setting a flag on that a deferred TLB flush operation takes place,
flushing when (try_to_unmap_one() on x86).
It seems that (1)-(4) can be consolidated. In addition, it seems that
(5) is racy. It also seems there can be many redundant TLB flushes, and
potentially TLB-shootdown storms, for instance during batched
reclamation (using try_to_unmap_one()) if at the same time mmu_gather
defers TLB flushes.
More aggressive TLB batching may be possible, but this patch-set does
not add such batching. The proposed changes would enable such batching
in a later time.
Admittedly, I do not understand how things are not broken today, which
frightens me to make further batching before getting things in order.
For instance, why is ok for zap_pte_range() to batch dirty-PTE flushes
for each page-table (but not in greater granularity). Can't
ClearPageDirty() be called before the flush, causing writes after
ClearPageDirty() and before the flush to be lost?
This patch-set therefore performs the following changes:
1. Change mprotect, task_mmu and mapping_dirty_helpers to use mmu_gather
instead of {inc|dec}_tlb_flush_pending().
2. Avoid TLB flushes if PTE permission is not demoted.
3. Cleans up mmu_gather to be less arch-dependant.
4. Uses mm's generations to track in finer granularity, either per-VMA
or per page-table, whether a pending mmu_gather operation is
outstanding. This should allow to avoid some TLB flushes when KSM or
memory reclamation takes place while another operation such as
munmap() or mprotect() is running.
5. Changes try_to_unmap_one() flushing scheme, as the current seems
broken to track in a bitmap which CPUs have outstanding TLB flushes
instead of having a flag.
Further optimizations are possible, such as changing move_ptes() to use
mmu_gather.
The patches were very very lightly tested. I am looking forward for your
feedback regarding the overall approaches, and whether to split them
into multiple patch-sets.
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: linux-csky@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Nick Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: x86@kernel.org
Cc: Yu Zhao <yuzhao@google.com>
Nadav Amit (20):
mm/tlb: fix fullmm semantics
mm/mprotect: use mmu_gather
mm/mprotect: do not flush on permission promotion
mm/mapping_dirty_helpers: use mmu_gather
mm/tlb: move BATCHED_UNMAP_TLB_FLUSH to tlb.h
fs/task_mmu: use mmu_gather interface of clear-soft-dirty
mm: move x86 tlb_gen to generic code
mm: store completed TLB generation
mm: create pte/pmd_tlb_flush_pending()
mm: add pte_to_page()
mm/tlb: remove arch-specific tlb_start/end_vma()
mm/tlb: save the VMA that is flushed during tlb_start_vma()
mm/tlb: introduce tlb_start_ptes() and tlb_end_ptes()
mm: move inc/dec_tlb_flush_pending() to mmu_gather.c
mm: detect deferred TLB flushes in vma granularity
mm/tlb: per-page table generation tracking
mm/tlb: updated completed deferred TLB flush conditionally
mm: make mm_cpumask() volatile
lib/cpumask: introduce cpumask_atomic_or()
mm/rmap: avoid potential races
arch/arm/include/asm/bitops.h | 4 +-
arch/arm/include/asm/pgtable.h | 4 +-
arch/arm64/include/asm/pgtable.h | 4 +-
arch/csky/Kconfig | 1 +
arch/csky/include/asm/tlb.h | 12 --
arch/powerpc/Kconfig | 1 +
arch/powerpc/include/asm/tlb.h | 2 -
arch/s390/Kconfig | 1 +
arch/s390/include/asm/tlb.h | 3 -
arch/sparc/Kconfig | 1 +
arch/sparc/include/asm/pgtable_64.h | 9 +-
arch/sparc/include/asm/tlb_64.h | 2 -
arch/sparc/mm/init_64.c | 2 +-
arch/x86/Kconfig | 3 +
arch/x86/hyperv/mmu.c | 2 +-
arch/x86/include/asm/mmu.h | 10 -
arch/x86/include/asm/mmu_context.h | 1 -
arch/x86/include/asm/paravirt_types.h | 2 +-
arch/x86/include/asm/pgtable.h | 24 +--
arch/x86/include/asm/tlb.h | 21 +-
arch/x86/include/asm/tlbbatch.h | 15 --
arch/x86/include/asm/tlbflush.h | 61 ++++--
arch/x86/mm/tlb.c | 52 +++--
arch/x86/xen/mmu_pv.c | 2 +-
drivers/firmware/efi/efi.c | 1 +
fs/proc/task_mmu.c | 29 ++-
include/asm-generic/bitops/find.h | 8 +-
include/asm-generic/tlb.h | 291 +++++++++++++++++++++-----
include/linux/bitmap.h | 21 +-
include/linux/cpumask.h | 40 ++--
include/linux/huge_mm.h | 3 +-
include/linux/mm.h | 29 ++-
include/linux/mm_types.h | 166 ++++++++++-----
include/linux/mm_types_task.h | 13 --
include/linux/pgtable.h | 2 +-
include/linux/smp.h | 6 +-
init/Kconfig | 21 ++
kernel/fork.c | 2 +
kernel/smp.c | 8 +-
lib/bitmap.c | 33 ++-
lib/cpumask.c | 8 +-
lib/find_bit.c | 10 +-
mm/huge_memory.c | 6 +-
mm/init-mm.c | 1 +
mm/internal.h | 16 --
mm/ksm.c | 2 +-
mm/madvise.c | 6 +-
mm/mapping_dirty_helpers.c | 52 +++--
mm/memory.c | 2 +
mm/mmap.c | 1 +
mm/mmu_gather.c | 59 +++++-
mm/mprotect.c | 55 ++---
mm/mremap.c | 2 +-
mm/pgtable-generic.c | 2 +-
mm/rmap.c | 42 ++--
mm/vmscan.c | 1 +
56 files changed, 803 insertions(+), 374 deletions(-)
delete mode 100644 arch/x86/include/asm/tlbbatch.h
--
2.25.1
^ permalink raw reply
* [RFC 11/20] mm/tlb: remove arch-specific tlb_start/end_vma()
From: Nadav Amit @ 2021-01-31 0:11 UTC (permalink / raw)
To: linux-mm, linux-kernel
Cc: Andrea Arcangeli, linux-s390, x86, Yu Zhao, Peter Zijlstra,
linuxppc-dev, Dave Hansen, Nick Piggin, Nadav Amit, linux-csky,
Andy Lutomirski, Andrew Morton, Will Deacon, Thomas Gleixner
In-Reply-To: <20210131001132.3368247-1-namit@vmware.com>
From: Nadav Amit <namit@vmware.com>
Architecture-specific tlb_start_vma() and tlb_end_vma() seem
unnecessary. They are currently used for:
1. Avoid per-VMA TLB flushes. This can be determined by introducing
a new config option.
2. Avoid saving information on the vma that is being flushed. Saving
this information, even for architectures that do not need it, is
cheap and we will need it for per-VMA deferred TLB flushing.
3. Avoid calling flush_cache_range().
Remove the architecture specific tlb_start_vma() and tlb_end_vma() in
the following manner, corresponding to the previous requirements:
1. Introduce a new config option -
ARCH_WANT_AGGRESSIVE_TLB_FLUSH_BATCHING - to allow architectures to
define whether they want aggressive TLB flush batching (instead of
flushing mappings of each VMA separately).
2. Save information on the vma regardless of architecture. Saving this
information should have negligible overhead, and they will be
needed for fine granularity TLB flushes.
3. flush_cache_range() is anyhow not defined for the architectures that
implement tlb_start/end_vma().
No functional change intended.
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Nick Piggin <npiggin@gmail.com>
Cc: linux-csky@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Cc: x86@kernel.org
---
arch/csky/Kconfig | 1 +
arch/csky/include/asm/tlb.h | 12 ------------
arch/powerpc/Kconfig | 1 +
arch/powerpc/include/asm/tlb.h | 2 --
arch/s390/Kconfig | 1 +
arch/s390/include/asm/tlb.h | 3 ---
arch/sparc/Kconfig | 1 +
arch/sparc/include/asm/tlb_64.h | 2 --
arch/x86/Kconfig | 1 +
arch/x86/include/asm/tlb.h | 3 ---
include/asm-generic/tlb.h | 15 +++++----------
init/Kconfig | 8 ++++++++
12 files changed, 18 insertions(+), 32 deletions(-)
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 89dd2fcf38fa..924ff5721240 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -8,6 +8,7 @@ config CSKY
select ARCH_HAS_SYNC_DMA_FOR_DEVICE
select ARCH_USE_BUILTIN_BSWAP
select ARCH_USE_QUEUED_RWLOCKS if NR_CPUS>2
+ select ARCH_WANT_AGGRESSIVE_TLB_FLUSH_BATCHING
select ARCH_WANT_FRAME_POINTERS if !CPU_CK610
select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
select COMMON_CLK
diff --git a/arch/csky/include/asm/tlb.h b/arch/csky/include/asm/tlb.h
index fdff9b8d70c8..8130a5f09a6b 100644
--- a/arch/csky/include/asm/tlb.h
+++ b/arch/csky/include/asm/tlb.h
@@ -6,18 +6,6 @@
#include <asm/cacheflush.h>
-#define tlb_start_vma(tlb, vma) \
- do { \
- if (!(tlb)->fullmm) \
- flush_cache_range(vma, (vma)->vm_start, (vma)->vm_end); \
- } while (0)
-
-#define tlb_end_vma(tlb, vma) \
- do { \
- if (!(tlb)->fullmm) \
- flush_tlb_range(vma, (vma)->vm_start, (vma)->vm_end); \
- } while (0)
-
#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
#include <asm-generic/tlb.h>
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 107bb4319e0e..d9761b6f192a 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -151,6 +151,7 @@ config PPC
select ARCH_USE_CMPXCHG_LOCKREF if PPC64
select ARCH_USE_QUEUED_RWLOCKS if PPC_QUEUED_SPINLOCKS
select ARCH_USE_QUEUED_SPINLOCKS if PPC_QUEUED_SPINLOCKS
+ select ARCH_WANT_AGGRESSIVE_TLB_FLUSH_BATCHING
select ARCH_WANT_IPC_PARSE_VERSION
select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
select ARCH_WANT_LD_ORPHAN_WARN
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index 160422a439aa..880b7daf904e 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -19,8 +19,6 @@
#include <linux/pagemap.h>
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
#define __tlb_remove_tlb_entry __tlb_remove_tlb_entry
#define tlb_flush tlb_flush
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index c72874f09741..5b3dc5ca9873 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -113,6 +113,7 @@ config S390
select ARCH_USE_BUILTIN_BSWAP
select ARCH_USE_CMPXCHG_LOCKREF
select ARCH_WANTS_DYNAMIC_TASK_STRUCT
+ select ARCH_WANT_AGGRESSIVE_TLB_FLUSH_BATCHING
select ARCH_WANT_DEFAULT_BPF_JIT
select ARCH_WANT_IPC_PARSE_VERSION
select BUILDTIME_TABLE_SORT
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 954fa8ca6cbd..03f31d59f97c 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -27,9 +27,6 @@ static inline void tlb_flush(struct mmu_gather *tlb);
static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
struct page *page, int page_size);
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-
#define tlb_flush tlb_flush
#define pte_free_tlb pte_free_tlb
#define pmd_free_tlb pmd_free_tlb
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index c9c34dc52b7d..fb46e1b6f177 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -51,6 +51,7 @@ config SPARC
select NEED_DMA_MAP_STATE
select NEED_SG_DMA_LENGTH
select SET_FS
+ select ARCH_WANT_AGGRESSIVE_TLB_FLUSH_BATCHING
config SPARC32
def_bool !64BIT
diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h
index 779a5a0f0608..3037187482db 100644
--- a/arch/sparc/include/asm/tlb_64.h
+++ b/arch/sparc/include/asm/tlb_64.h
@@ -22,8 +22,6 @@ void smp_flush_tlb_mm(struct mm_struct *mm);
void __flush_tlb_pending(unsigned long, unsigned long, unsigned long *);
void flush_tlb_pending(void);
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
#define tlb_flush(tlb) flush_tlb_pending()
/*
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6bd4d626a6b3..d56b0f5cb00c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -101,6 +101,7 @@ config X86
select ARCH_USE_QUEUED_RWLOCKS
select ARCH_USE_QUEUED_SPINLOCKS
select ARCH_USE_SYM_ANNOTATIONS
+ select ARCH_WANT_AGGRESSIVE_TLB_FLUSH_BATCHING
select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
select ARCH_WANT_DEFAULT_BPF_JIT if X86_64
select ARCH_WANTS_DYNAMIC_TASK_STRUCT
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 1bfe979bb9bc..580636cdc257 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -2,9 +2,6 @@
#ifndef _ASM_X86_TLB_H
#define _ASM_X86_TLB_H
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-
#define tlb_flush tlb_flush
static inline void tlb_flush(struct mmu_gather *tlb);
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 427bfcc6cdec..b97136b7010b 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -334,8 +334,8 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
#ifdef CONFIG_MMU_GATHER_NO_RANGE
-#if defined(tlb_flush) || defined(tlb_start_vma) || defined(tlb_end_vma)
-#error MMU_GATHER_NO_RANGE relies on default tlb_flush(), tlb_start_vma() and tlb_end_vma()
+#if defined(tlb_flush)
+#error MMU_GATHER_NO_RANGE relies on default tlb_flush()
#endif
/*
@@ -362,10 +362,6 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
#ifndef tlb_flush
-#if defined(tlb_start_vma) || defined(tlb_end_vma)
-#error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma()
-#endif
-
/*
* When an architecture does not provide its own tlb_flush() implementation
* but does have a reasonably efficient flush_vma_range() implementation
@@ -486,7 +482,6 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
* case where we're doing a full MM flush. When we're doing a munmap,
* the vmas are adjusted to only cover the region to be torn down.
*/
-#ifndef tlb_start_vma
static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
{
if (tlb->fullmm)
@@ -495,14 +490,15 @@ static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *
tlb_update_vma_flags(tlb, vma);
flush_cache_range(vma, vma->vm_start, vma->vm_end);
}
-#endif
-#ifndef tlb_end_vma
static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
{
if (tlb->fullmm)
return;
+ if (IS_ENABLED(CONFIG_ARCH_WANT_AGGRESSIVE_TLB_FLUSH_BATCHING))
+ return;
+
/*
* Do a TLB flush and reset the range at VMA boundaries; this avoids
* the ranges growing with the unused space between consecutive VMAs,
@@ -511,7 +507,6 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
*/
tlb_flush_mmu_tlbonly(tlb);
}
-#endif
#ifdef CONFIG_ARCH_HAS_TLB_GENERATIONS
diff --git a/init/Kconfig b/init/Kconfig
index 3d11a0f7c8cc..14a599a48738 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -849,6 +849,14 @@ config ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
config ARCH_HAS_TLB_GENERATIONS
bool
+#
+# For architectures that prefer to batch TLB flushes aggressively, i.e.,
+# not to flush after changing or removing each VMA. The architecture must
+# provide its own tlb_flush() function.
+config ARCH_WANT_AGGRESSIVE_TLB_FLUSH_BATCHING
+ bool
+ depends on !CONFIG_MMU_GATHER_NO_GATHER
+
config CC_HAS_INT128
def_bool !$(cc-option,$(m64-flag) -D__SIZEOF_INT128__=0) && 64BIT
--
2.25.1
^ permalink raw reply related
* Re: [RFC 00/20] TLB batching consolidation and enhancements
From: Andy Lutomirski @ 2021-01-31 0:39 UTC (permalink / raw)
To: Nadav Amit
Cc: Andrea Arcangeli, linux-s390, X86 ML, Yu Zhao, Will Deacon,
Peter Zijlstra, Mel Gorman, Dave Hansen, LKML, linux-csky,
Linux-MM, Nadav Amit, Nick Piggin, Andy Lutomirski, Andrew Morton,
linuxppc-dev, Thomas Gleixner
In-Reply-To: <20210131001132.3368247-1-namit@vmware.com>
On Sat, Jan 30, 2021 at 4:16 PM Nadav Amit <nadav.amit@gmail.com> wrote:
>
> From: Nadav Amit <namit@vmware.com>
>
> There are currently (at least?) 5 different TLB batching schemes in the
> kernel:
>
> 1. Using mmu_gather (e.g., zap_page_range()).
>
> 2. Using {inc|dec}_tlb_flush_pending() to inform other threads on the
> ongoing deferred TLB flush and flushing the entire range eventually
> (e.g., change_protection_range()).
>
> 3. arch_{enter|leave}_lazy_mmu_mode() for sparc and powerpc (and Xen?).
>
> 4. Batching per-table flushes (move_ptes()).
>
> 5. By setting a flag on that a deferred TLB flush operation takes place,
> flushing when (try_to_unmap_one() on x86).
Are you referring to the arch_tlbbatch_add_mm/flush mechanism?
^ 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