powerpc: Enable GENERIC_ENTRY feature

Enable the generic IRQ entry/exit infrastructure on PowerPC by selecting
GENERIC_ENTRY and integrating the architecture-specific interrupt and
syscall handlers with the generic entry/exit APIs.

This change replaces PowerPC’s local interrupt entry/exit handling with
calls to the generic irqentry_* helpers, aligning the architecture with
the common kernel entry model. The macros that define interrupt, async,
and NMI handlers are updated to use irqentry_enter()/irqentry_exit()
and irqentry_nmi_enter()/irqentry_nmi_exit() where applicable also
convert the PowerPC syscall entry and exit paths to use the generic
entry/exit framework and integrating with the common syscall handling
routines.

Key updates include:
 - The architecture now selects GENERIC_ENTRY in Kconfig.
 - Replace interrupt_enter/exit_prepare() with arch_interrupt_* helpers.
 - Integrate irqentry_enter()/exit() in standard and async interrupt paths.
 - Integrate irqentry_nmi_enter()/exit() in NMI handlers.
 - Remove redundant irq_enter()/irq_exit() calls now handled generically.
 - Use irqentry_exit_cond_resched() for preemption checks.
 - interrupt.c and syscall.c are simplified to delegate context
   management and user exit handling to the generic entry path.
 - The new pt_regs field `exit_flags` introduced earlier is now used
   to carry per-syscall exit state flags (e.g. _TIF_RESTOREALL).
 - Remove unused code.

This change establishes the necessary wiring for PowerPC to use the
generic IRQ entry/exit framework while maintaining existing semantics.
This aligns PowerPC with the common entry code used by other
architectures and reduces duplicated logic around syscall tracing,
context tracking, and signal handling.

The performance benchmarks from perf bench basic syscall are below:

perf bench syscall usec/op (-ve is improvement)

| Syscall | Base        | test        | change % |
| ------- | ----------- | ----------- | -------- |
| basic   | 0.093543    | 0.093023    | -0.56    |
| execve  | 446.557781  | 450.107172  | +0.79    |
| fork    | 1142.204391 | 1156.377214 | +1.24    |
| getpgid | 0.097666    | 0.092677    | -5.11    |

perf bench syscall ops/sec (+ve is improvement)

| Syscall | Base     | New      | change % |
| ------- | -------- | -------- | -------- |
| basic   | 10690548 | 10750140 | +0.56    |
| execve  | 2239     | 2221     | -0.80    |
| fork    | 875      | 864      | -1.26    |
| getpgid | 10239026 | 10790324 | +5.38    |

IPI latency benchmark (-ve is improvement)

| Metric         | Base (ns)     | New (ns)      | % Change |
| -------------- | ------------- | ------------- | -------- |
| Dry run        | 583136.56     | 584136.35     | 0.17%    |
| Self IPI       | 4167393.42    | 4149093.90    | -0.44%   |
| Normal IPI     | 61769347.82   | 61753728.39   | -0.03%   |
| Broadcast IPI  | 2235584825.02 | 2227521401.45 | -0.36%   |
| Broadcast lock | 2164964433.31 | 2125658641.76 | -1.82%   |

Thats very close to performance earlier with arch specific handling.

Signed-off-by: Mukesh Kumar Chaurasiya <mkchauras@linux.ibm.com>
Tested-by: Samir M <samir@linux.ibm.com>
Tested-by: David Gow <davidgow@google.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Reviewed-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260427122742.210074-8-mkchauras@gmail.com

4 files changed, 53 insertions, 327 deletions

diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 666eadb589a5..89a999be1352 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 #include <linux/context_tracking.h>
+#include <linux/entry-common.h>
 #include <linux/err.h>
 #include <linux/compat.h>
 #include <linux/rseq.h>
@@ -25,10 +26,6 @@
 unsigned long global_dbcr0[NR_CPUS];
 #endif
 
-#if defined(CONFIG_PREEMPT_DYNAMIC)
-DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
-#endif
-
 #ifdef CONFIG_PPC_BOOK3S_64
 DEFINE_STATIC_KEY_FALSE(interrupt_exit_not_reentrant);
 static inline bool exit_must_hard_disable(void)
@@ -78,181 +75,6 @@ static notrace __always_inline bool prep_irq_for_enabled_exit(bool restartable)
 	return true;
 }
 
-static notrace void booke_load_dbcr0(void)
-{
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-	unsigned long dbcr0 = current->thread.debug.dbcr0;
-
-	if (likely(!(dbcr0 & DBCR0_IDM)))
-		return;
-
-	/*
-	 * Check to see if the dbcr0 register is set up to debug.
-	 * Use the internal debug mode bit to do this.
-	 */
-	mtmsr(mfmsr() & ~MSR_DE);
-	if (IS_ENABLED(CONFIG_PPC32)) {
-		isync();
-		global_dbcr0[smp_processor_id()] = mfspr(SPRN_DBCR0);
-	}
-	mtspr(SPRN_DBCR0, dbcr0);
-	mtspr(SPRN_DBSR, -1);
-#endif
-}
-
-static notrace void check_return_regs_valid(struct pt_regs *regs)
-{
-#ifdef CONFIG_PPC_BOOK3S_64
-	unsigned long trap, srr0, srr1;
-	static bool warned;
-	u8 *validp;
-	char *h;
-
-	if (trap_is_scv(regs))
-		return;
-
-	trap = TRAP(regs);
-	// EE in HV mode sets HSRRs like 0xea0
-	if (cpu_has_feature(CPU_FTR_HVMODE) && trap == INTERRUPT_EXTERNAL)
-		trap = 0xea0;
-
-	switch (trap) {
-	case 0x980:
-	case INTERRUPT_H_DATA_STORAGE:
-	case 0xe20:
-	case 0xe40:
-	case INTERRUPT_HMI:
-	case 0xe80:
-	case 0xea0:
-	case INTERRUPT_H_FAC_UNAVAIL:
-	case 0x1200:
-	case 0x1500:
-	case 0x1600:
-	case 0x1800:
-		validp = &local_paca->hsrr_valid;
-		if (!READ_ONCE(*validp))
-			return;
-
-		srr0 = mfspr(SPRN_HSRR0);
-		srr1 = mfspr(SPRN_HSRR1);
-		h = "H";
-
-		break;
-	default:
-		validp = &local_paca->srr_valid;
-		if (!READ_ONCE(*validp))
-			return;
-
-		srr0 = mfspr(SPRN_SRR0);
-		srr1 = mfspr(SPRN_SRR1);
-		h = "";
-		break;
-	}
-
-	if (srr0 == regs->nip && srr1 == regs->msr)
-		return;
-
-	/*
-	 * A NMI / soft-NMI interrupt may have come in after we found
-	 * srr_valid and before the SRRs are loaded. The interrupt then
-	 * comes in and clobbers SRRs and clears srr_valid. Then we load
-	 * the SRRs here and test them above and find they don't match.
-	 *
-	 * Test validity again after that, to catch such false positives.
-	 *
-	 * This test in general will have some window for false negatives
-	 * and may not catch and fix all such cases if an NMI comes in
-	 * later and clobbers SRRs without clearing srr_valid, but hopefully
-	 * such things will get caught most of the time, statistically
-	 * enough to be able to get a warning out.
-	 */
-	if (!READ_ONCE(*validp))
-		return;
-
-	if (!data_race(warned)) {
-		data_race(warned = true);
-		printk("%sSRR0 was: %lx should be: %lx\n", h, srr0, regs->nip);
-		printk("%sSRR1 was: %lx should be: %lx\n", h, srr1, regs->msr);
-		show_regs(regs);
-	}
-
-	WRITE_ONCE(*validp, 0); /* fixup */
-#endif
-}
-
-static notrace unsigned long
-interrupt_exit_user_prepare_main(unsigned long ret, struct pt_regs *regs)
-{
-	unsigned long ti_flags;
-
-again:
-	ti_flags = read_thread_flags();
-	while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
-		local_irq_enable();
-		if (ti_flags & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) {
-			schedule();
-		} else {
-			/*
-			 * SIGPENDING must restore signal handler function
-			 * argument GPRs, and some non-volatiles (e.g., r1).
-			 * Restore all for now. This could be made lighter.
-			 */
-			if (ti_flags & _TIF_SIGPENDING)
-				ret |= _TIF_RESTOREALL;
-			do_notify_resume(regs, ti_flags);
-		}
-		local_irq_disable();
-		ti_flags = read_thread_flags();
-	}
-
-	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && IS_ENABLED(CONFIG_PPC_FPU)) {
-		if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
-				unlikely((ti_flags & _TIF_RESTORE_TM))) {
-			restore_tm_state(regs);
-		} else {
-			unsigned long mathflags = MSR_FP;
-
-			if (cpu_has_feature(CPU_FTR_VSX))
-				mathflags |= MSR_VEC | MSR_VSX;
-			else if (cpu_has_feature(CPU_FTR_ALTIVEC))
-				mathflags |= MSR_VEC;
-
-			/*
-			 * If userspace MSR has all available FP bits set,
-			 * then they are live and no need to restore. If not,
-			 * it means the regs were given up and restore_math
-			 * may decide to restore them (to avoid taking an FP
-			 * fault).
-			 */
-			if ((regs->msr & mathflags) != mathflags)
-				restore_math(regs);
-		}
-	}
-
-	check_return_regs_valid(regs);
-
-	user_enter_irqoff();
-	if (!prep_irq_for_enabled_exit(true)) {
-		user_exit_irqoff();
-		local_irq_enable();
-		local_irq_disable();
-		goto again;
-	}
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	local_paca->tm_scratch = regs->msr;
-#endif
-
-	booke_load_dbcr0();
-
-	account_cpu_user_exit();
-
-	/* Restore user access locks last */
-	kuap_user_restore(regs);
-
-	return ret;
-}
-
 /*
  * 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
@@ -267,17 +89,12 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 					   long scv)
 {
 	unsigned long ti_flags;
-	unsigned long ret = 0;
 	bool is_not_scv = !IS_ENABLED(CONFIG_PPC_BOOK3S_64) || !scv;
 
-	CT_WARN_ON(ct_state() == CT_STATE_USER);
-
 	kuap_assert_locked();
 
 	regs->result = r3;
-
-	/* Check whether the syscall is issued inside a restartable sequence */
-	rseq_syscall(regs);
+	regs->exit_flags = 0;
 
 	ti_flags = read_thread_flags();
 
@@ -290,7 +107,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 
 	if (unlikely(ti_flags & _TIF_PERSYSCALL_MASK)) {
 		if (ti_flags & _TIF_RESTOREALL)
-			ret = _TIF_RESTOREALL;
+			regs->exit_flags = _TIF_RESTOREALL;
 		else
 			regs->gpr[3] = r3;
 		clear_bits(_TIF_PERSYSCALL_MASK, &current_thread_info()->flags);
@@ -299,18 +116,28 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 	}
 
 	if (unlikely(ti_flags & _TIF_SYSCALL_DOTRACE)) {
-		do_syscall_trace_leave(regs);
-		ret |= _TIF_RESTOREALL;
+		regs->exit_flags |= _TIF_RESTOREALL;
 	}
 
-	local_irq_disable();
-	ret = interrupt_exit_user_prepare_main(ret, regs);
+	syscall_exit_to_user_mode(regs);
+
+again:
+	user_enter_irqoff();
+	if (!prep_irq_for_enabled_exit(true)) {
+		user_exit_irqoff();
+		local_irq_enable();
+		local_irq_disable();
+		goto again;
+	}
+
+	/* Restore user access locks last */
+	kuap_user_restore(regs);
 
 #ifdef CONFIG_PPC64
-	regs->exit_result = ret;
+	regs->exit_result = regs->exit_flags;
 #endif
 
-	return ret;
+	return regs->exit_flags;
 }
 
 #ifdef CONFIG_PPC64
@@ -330,13 +157,16 @@ notrace unsigned long syscall_exit_restart(unsigned long r3, struct pt_regs *reg
 	set_kuap(AMR_KUAP_BLOCKED);
 #endif
 
-	trace_hardirqs_off();
-	user_exit_irqoff();
-	account_cpu_user_entry();
-
-	BUG_ON(!user_mode(regs));
+again:
+	user_enter_irqoff();
+	if (!prep_irq_for_enabled_exit(true)) {
+		user_exit_irqoff();
+		local_irq_enable();
+		local_irq_disable();
+		goto again;
+	}
 
-	regs->exit_result = interrupt_exit_user_prepare_main(regs->exit_result, regs);
+	regs->exit_result |= regs->exit_flags;
 
 	return regs->exit_result;
 }
@@ -348,7 +178,6 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs)
 
 	BUG_ON(regs_is_unrecoverable(regs));
 	BUG_ON(regs_irqs_disabled(regs));
-	CT_WARN_ON(ct_state() == CT_STATE_USER);
 
 	/*
 	 * We don't need to restore AMR on the way back to userspace for KUAP.
@@ -357,8 +186,21 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs)
 	kuap_assert_locked();
 
 	local_irq_disable();
+	regs->exit_flags = 0;
+again:
+	check_return_regs_valid(regs);
+	user_enter_irqoff();
+	if (!prep_irq_for_enabled_exit(true)) {
+		user_exit_irqoff();
+		local_irq_enable();
+		local_irq_disable();
+		goto again;
+	}
+
+	/* Restore user access locks last */
+	kuap_user_restore(regs);
 
-	ret = interrupt_exit_user_prepare_main(0, regs);
+	ret = regs->exit_flags;
 
 #ifdef CONFIG_PPC64
 	regs->exit_result = ret;
@@ -400,13 +242,6 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
 		/* Returning to a kernel context with local irqs enabled. */
 		WARN_ON_ONCE(!(regs->msr & MSR_EE));
 again:
-		if (need_irq_preemption()) {
-			/* Return to preemptible kernel context */
-			if (unlikely(read_thread_flags() & _TIF_NEED_RESCHED)) {
-				if (preempt_count() == 0)
-					preempt_schedule_irq();
-			}
-		}
 
 		check_return_regs_valid(regs);
 
@@ -479,7 +314,6 @@ notrace unsigned long interrupt_exit_user_restart(struct pt_regs *regs)
 #endif
 
 	trace_hardirqs_off();
-	user_exit_irqoff();
 	account_cpu_user_entry();
 
 	BUG_ON(!user_mode(regs));
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
index 2134b6d155ff..f006a03a0211 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -21,9 +21,6 @@
 #include <asm/switch_to.h>
 #include <asm/debug.h>
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/syscalls.h>
-
 #include "ptrace-decl.h"
 
 /*
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index aa17e62f3754..9f1847b4742e 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -6,6 +6,7 @@
  *    Extracted from signal_32.c and signal_64.c
  */
 
+#include <linux/entry-common.h>
 #include <linux/resume_user_mode.h>
 #include <linux/signal.h>
 #include <linux/uprobes.h>
@@ -368,3 +369,10 @@ void signal_fault(struct task_struct *tsk, struct pt_regs *regs,
 		printk_ratelimited(regs->msr & MSR_64BIT ? fm64 : fm32, tsk->comm,
 				   task_pid_nr(tsk), where, ptr, regs->nip, regs->link);
 }
+
+void arch_do_signal_or_restart(struct pt_regs *regs)
+{
+	BUG_ON(regs != current->thread.regs);
+	regs->exit_flags |= _TIF_RESTOREALL;
+	do_signal(current);
+}
diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
index 52d6e10eab22..a9da2af6efa8 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.c
@@ -3,6 +3,7 @@
 #include <linux/compat.h>
 #include <linux/context_tracking.h>
 #include <linux/randomize_kstack.h>
+#include <linux/entry-common.h>
 
 #include <asm/interrupt.h>
 #include <asm/kup.h>
@@ -18,124 +19,10 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
 	long ret;
 	syscall_fn f;
 
-	kuap_lock();
-
-	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
-		BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
-
-	trace_hardirqs_off(); /* finish reconciling */
-
-	CT_WARN_ON(ct_state() == CT_STATE_KERNEL);
-	user_exit_irqoff();
-
 	add_random_kstack_offset();
+	r0 = syscall_enter_from_user_mode(regs, r0);
 
-	BUG_ON(regs_is_unrecoverable(regs));
-	BUG_ON(!user_mode(regs));
-	BUG_ON(regs_irqs_disabled(regs));
-
-#ifdef CONFIG_PPC_PKEY
-	if (mmu_has_feature(MMU_FTR_PKEY)) {
-		unsigned long amr, iamr;
-		bool flush_needed = false;
-		/*
-		 * When entering from userspace we mostly have the AMR/IAMR
-		 * different from kernel default values. Hence don't compare.
-		 */
-		amr = mfspr(SPRN_AMR);
-		iamr = mfspr(SPRN_IAMR);
-		regs->amr  = amr;
-		regs->iamr = iamr;
-		if (mmu_has_feature(MMU_FTR_KUAP)) {
-			mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
-			flush_needed = true;
-		}
-		if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) {
-			mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED);
-			flush_needed = true;
-		}
-		if (flush_needed)
-			isync();
-	} else
-#endif
-		kuap_assert_locked();
-
-	booke_restore_dbcr0();
-
-	account_cpu_user_entry();
-
-	account_stolen_time();
-
-	/*
-	 * This is not required for the syscall exit path, but makes the
-	 * stack frame look nicer. If this was initialised in the first stack
-	 * frame, or if the unwinder was taught the first stack frame always
-	 * returns to user with IRQS_ENABLED, this store could be avoided!
-	 */
-	irq_soft_mask_regs_set_state(regs, IRQS_ENABLED);
-
-	/*
-	 * If system call is called with TM active, set _TIF_RESTOREALL to
-	 * prevent RFSCV being used to return to userspace, because POWER9
-	 * TM implementation has problems with this instruction returning to
-	 * transactional state. Final register values are not relevant because
-	 * the transaction will be aborted upon return anyway. Or in the case
-	 * of unsupported_scv SIGILL fault, the return state does not much
-	 * matter because it's an edge case.
-	 */
-	if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
-			unlikely(MSR_TM_TRANSACTIONAL(regs->msr)))
-		set_bits(_TIF_RESTOREALL, &current_thread_info()->flags);
-
-	/*
-	 * If the system call was made with a transaction active, doom it and
-	 * return without performing the system call. Unless it was an
-	 * unsupported scv vector, in which case it's treated like an illegal
-	 * instruction.
-	 */
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) &&
-	    !trap_is_unsupported_scv(regs)) {
-		/* Enable TM in the kernel, and disable EE (for scv) */
-		hard_irq_disable();
-		mtmsr(mfmsr() | MSR_TM);
-
-		/* tabort, this dooms the transaction, nothing else */
-		asm volatile(".long 0x7c00071d | ((%0) << 16)"
-				:: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT));
-
-		/*
-		 * Userspace will never see the return value. Execution will
-		 * resume after the tbegin. of the aborted transaction with the
-		 * checkpointed register state. A context switch could occur
-		 * or signal delivered to the process before resuming the
-		 * doomed transaction context, but that should all be handled
-		 * as expected.
-		 */
-		return -ENOSYS;
-	}
-#endif // CONFIG_PPC_TRANSACTIONAL_MEM
-
-	local_irq_enable();
-
-	if (unlikely(read_thread_flags() & _TIF_SYSCALL_DOTRACE)) {
-		if (unlikely(trap_is_unsupported_scv(regs))) {
-			/* Unsupported scv vector */
-			_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-			return regs->gpr[3];
-		}
-		/*
-		 * We use the return value of do_syscall_trace_enter() as the
-		 * syscall number. If the syscall was rejected for any reason
-		 * do_syscall_trace_enter() returns an invalid syscall number
-		 * and the test against NR_syscalls will fail and the return
-		 * value to be used is in regs->gpr[3].
-		 */
-		r0 = do_syscall_trace_enter(regs);
-		if (unlikely(r0 >= NR_syscalls))
-			return regs->gpr[3];
-
-	} else if (unlikely(r0 >= NR_syscalls)) {
+	if (unlikely(r0 >= NR_syscalls)) {
 		if (unlikely(trap_is_unsupported_scv(regs))) {
 			/* Unsupported scv vector */
 			_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);