aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/irq.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-08-06 16:38:17 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-08-06 16:38:17 -0700
commitcae4199f9319f42534ee2e2e4aadf183b9bb7f73 (patch)
treeb0028cbba73deaaf842fcb72e7c0dc0a0e0a9923 /arch/powerpc/kernel/irq.c
parent4d1044fcb996e8de9b9ab392f4a767890e45202d (diff)
parent4cfa6ff24a9744ba484521c38bea613134fbfcb3 (diff)
downloadlinux-cae4199f9319f42534ee2e2e4aadf183b9bb7f73.tar.gz
Merge tag 'powerpc-6.0-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman: - Add support for syscall stack randomization - Add support for atomic operations to the 32 & 64-bit BPF JIT - Full support for KASAN on 64-bit Book3E - Add a watchdog driver for the new PowerVM hypervisor watchdog - Add a number of new selftests for the Power10 PMU support - Add a driver for the PowerVM Platform KeyStore - Increase the NMI watchdog timeout during live partition migration, to avoid timeouts due to increased memory access latency - Add support for using the 'linux,pci-domain' device tree property for PCI domain assignment - Many other small features and fixes Thanks to Alexey Kardashevskiy, Andy Shevchenko, Arnd Bergmann, Athira Rajeev, Bagas Sanjaya, Christophe Leroy, Erhard Furtner, Fabiano Rosas, Greg Kroah-Hartman, Greg Kurz, Haowen Bai, Hari Bathini, Jason A. Donenfeld, Jason Wang, Jiang Jian, Joel Stanley, Juerg Haefliger, Kajol Jain, Kees Cook, Laurent Dufour, Madhavan Srinivasan, Masahiro Yamada, Maxime Bizon, Miaoqian Lin, Murilo Opsfelder Araújo, Nathan Lynch, Naveen N. Rao, Nayna Jain, Nicholas Piggin, Ning Qiang, Pali Rohár, Petr Mladek, Rashmica Gupta, Sachin Sant, Scott Cheloha, Segher Boessenkool, Stephen Rothwell, Uwe Kleine-König, Wolfram Sang, Xiu Jianfeng, and Zhouyi Zhou. * tag 'powerpc-6.0-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (191 commits) powerpc/64e: Fix kexec build error EDAC/ppc_4xx: Include required of_irq header directly powerpc/pci: Fix PHB numbering when using opal-phbid powerpc/64: Init jump labels before parse_early_param() selftests/powerpc: Avoid GCC 12 uninitialised variable warning powerpc/cell/axon_msi: Fix refcount leak in setup_msi_msg_address powerpc/xive: Fix refcount leak in xive_get_max_prio powerpc/spufs: Fix refcount leak in spufs_init_isolated_loader powerpc/perf: Include caps feature for power10 DD1 version powerpc: add support for syscall stack randomization powerpc: Move system_call_exception() to syscall.c powerpc/powernv: rename remaining rng powernv_ functions to pnv_ powerpc/powernv/kvm: Use darn for H_RANDOM on Power9 powerpc/powernv: Avoid crashing if rng is NULL selftests/powerpc: Fix matrix multiply assist test powerpc/signal: Update comment for clarity powerpc: make facility_unavailable_exception 64s powerpc/platforms/83xx/suspend: Remove write-only global variable powerpc/platforms/83xx/suspend: Prevent unloading the driver powerpc/platforms/83xx/suspend: Reorder to get rid of a forward declaration ...
Diffstat (limited to 'arch/powerpc/kernel/irq.c')
-rw-r--r--arch/powerpc/kernel/irq.c496
1 files changed, 36 insertions, 460 deletions
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 0822a274a549c8..0f17268c1f0bbd 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -65,13 +65,8 @@
#include <asm/smp.h>
#include <asm/hw_irq.h>
#include <asm/softirq_stack.h>
+#include <asm/ppc_asm.h>
-#ifdef CONFIG_PPC64
-#include <asm/paca.h>
-#include <asm/firmware.h>
-#include <asm/lv1call.h>
-#include <asm/dbell.h>
-#endif
#define CREATE_TRACE_POINTS
#include <asm/trace.h>
#include <asm/cpu_has_feature.h>
@@ -88,411 +83,6 @@ u32 tau_interrupts(unsigned long cpu);
#endif
#endif /* CONFIG_PPC32 */
-#ifdef CONFIG_PPC64
-
-int distribute_irqs = 1;
-
-static inline notrace unsigned long get_irq_happened(void)
-{
- unsigned long happened;
-
- __asm__ __volatile__("lbz %0,%1(13)"
- : "=r" (happened) : "i" (offsetof(struct paca_struct, irq_happened)));
-
- return happened;
-}
-
-void replay_soft_interrupts(void)
-{
- struct pt_regs regs;
-
- /*
- * Be careful here, calling these interrupt handlers can cause
- * softirqs to be raised, which they may run when calling irq_exit,
- * which will cause local_irq_enable() to be run, which can then
- * recurse into this function. Don't keep any state across
- * interrupt handler calls which may change underneath us.
- *
- * We use local_paca rather than get_paca() to avoid all the
- * debug_smp_processor_id() business in this low level function.
- */
-
- ppc_save_regs(&regs);
- regs.softe = IRQS_ENABLED;
- regs.msr |= MSR_EE;
-
-again:
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
- WARN_ON_ONCE(mfmsr() & MSR_EE);
-
- /*
- * Force the delivery of pending soft-disabled interrupts on PS3.
- * Any HV call will have this side effect.
- */
- if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
- u64 tmp, tmp2;
- lv1_get_version_info(&tmp, &tmp2);
- }
-
- /*
- * Check if an hypervisor Maintenance interrupt happened.
- * This is a higher priority interrupt than the others, so
- * replay it first.
- */
- if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_HMI)) {
- local_paca->irq_happened &= ~PACA_IRQ_HMI;
- regs.trap = INTERRUPT_HMI;
- handle_hmi_exception(&regs);
- if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
- hard_irq_disable();
- }
-
- if (local_paca->irq_happened & PACA_IRQ_DEC) {
- local_paca->irq_happened &= ~PACA_IRQ_DEC;
- regs.trap = INTERRUPT_DECREMENTER;
- timer_interrupt(&regs);
- if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
- hard_irq_disable();
- }
-
- if (local_paca->irq_happened & PACA_IRQ_EE) {
- local_paca->irq_happened &= ~PACA_IRQ_EE;
- regs.trap = INTERRUPT_EXTERNAL;
- do_IRQ(&regs);
- if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
- hard_irq_disable();
- }
-
- if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (local_paca->irq_happened & PACA_IRQ_DBELL)) {
- local_paca->irq_happened &= ~PACA_IRQ_DBELL;
- regs.trap = INTERRUPT_DOORBELL;
- doorbell_exception(&regs);
- if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
- hard_irq_disable();
- }
-
- /* Book3E does not support soft-masking PMI interrupts */
- if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_PMI)) {
- local_paca->irq_happened &= ~PACA_IRQ_PMI;
- regs.trap = INTERRUPT_PERFMON;
- performance_monitor_exception(&regs);
- if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
- hard_irq_disable();
- }
-
- if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) {
- /*
- * We are responding to the next interrupt, so interrupt-off
- * latencies should be reset here.
- */
- trace_hardirqs_on();
- trace_hardirqs_off();
- goto again;
- }
-}
-
-#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP)
-static inline void replay_soft_interrupts_irqrestore(void)
-{
- unsigned long kuap_state = get_kuap();
-
- /*
- * Check if anything calls local_irq_enable/restore() when KUAP is
- * disabled (user access enabled). We handle that case here by saving
- * and re-locking AMR but we shouldn't get here in the first place,
- * hence the warning.
- */
- kuap_assert_locked();
-
- if (kuap_state != AMR_KUAP_BLOCKED)
- set_kuap(AMR_KUAP_BLOCKED);
-
- replay_soft_interrupts();
-
- if (kuap_state != AMR_KUAP_BLOCKED)
- set_kuap(kuap_state);
-}
-#else
-#define replay_soft_interrupts_irqrestore() replay_soft_interrupts()
-#endif
-
-notrace void arch_local_irq_restore(unsigned long mask)
-{
- unsigned char irq_happened;
-
- /* Write the new soft-enabled value if it is a disable */
- if (mask) {
- irq_soft_mask_set(mask);
- return;
- }
-
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
- WARN_ON_ONCE(in_nmi() || in_hardirq());
-
- /*
- * After the stb, interrupts are unmasked and there are no interrupts
- * pending replay. The restart sequence makes this atomic with
- * respect to soft-masked interrupts. If this was just a simple code
- * sequence, a soft-masked interrupt could become pending right after
- * the comparison and before the stb.
- *
- * This allows interrupts to be unmasked without hard disabling, and
- * also without new hard interrupts coming in ahead of pending ones.
- */
- asm_volatile_goto(
-"1: \n"
-" lbz 9,%0(13) \n"
-" cmpwi 9,0 \n"
-" bne %l[happened] \n"
-" stb 9,%1(13) \n"
-"2: \n"
- RESTART_TABLE(1b, 2b, 1b)
- : : "i" (offsetof(struct paca_struct, irq_happened)),
- "i" (offsetof(struct paca_struct, irq_soft_mask))
- : "cr0", "r9"
- : happened);
-
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
- WARN_ON_ONCE(!(mfmsr() & MSR_EE));
-
- return;
-
-happened:
- irq_happened = get_irq_happened();
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
- WARN_ON_ONCE(!irq_happened);
-
- if (irq_happened == PACA_IRQ_HARD_DIS) {
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
- WARN_ON_ONCE(mfmsr() & MSR_EE);
- irq_soft_mask_set(IRQS_ENABLED);
- local_paca->irq_happened = 0;
- __hard_irq_enable();
- return;
- }
-
- /* Have interrupts to replay, need to hard disable first */
- if (!(irq_happened & PACA_IRQ_HARD_DIS)) {
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
- if (!(mfmsr() & MSR_EE)) {
- /*
- * An interrupt could have come in and cleared
- * MSR[EE] and set IRQ_HARD_DIS, so check
- * IRQ_HARD_DIS again and warn if it is still
- * clear.
- */
- irq_happened = get_irq_happened();
- WARN_ON_ONCE(!(irq_happened & PACA_IRQ_HARD_DIS));
- }
- }
- __hard_irq_disable();
- local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
- } else {
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
- if (WARN_ON_ONCE(mfmsr() & MSR_EE))
- __hard_irq_disable();
- }
- }
-
- /*
- * Disable preempt here, so that the below preempt_enable will
- * perform resched if required (a replayed interrupt may set
- * need_resched).
- */
- preempt_disable();
- irq_soft_mask_set(IRQS_ALL_DISABLED);
- trace_hardirqs_off();
-
- replay_soft_interrupts_irqrestore();
- local_paca->irq_happened = 0;
-
- trace_hardirqs_on();
- irq_soft_mask_set(IRQS_ENABLED);
- __hard_irq_enable();
- preempt_enable();
-}
-EXPORT_SYMBOL(arch_local_irq_restore);
-
-/*
- * This is a helper to use when about to go into idle low-power
- * when the latter has the side effect of re-enabling interrupts
- * (such as calling H_CEDE under pHyp).
- *
- * You call this function with interrupts soft-disabled (this is
- * already the case when ppc_md.power_save is called). The function
- * will return whether to enter power save or just return.
- *
- * In the former case, it will have notified lockdep of interrupts
- * being re-enabled and generally sanitized the lazy irq state,
- * and in the latter case it will leave with interrupts hard
- * disabled and marked as such, so the local_irq_enable() call
- * in arch_cpu_idle() will properly re-enable everything.
- */
-bool prep_irq_for_idle(void)
-{
- /*
- * First we need to hard disable to ensure no interrupt
- * occurs before we effectively enter the low power state
- */
- __hard_irq_disable();
- local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
-
- /*
- * If anything happened while we were soft-disabled,
- * we return now and do not enter the low power state.
- */
- if (lazy_irq_pending())
- return false;
-
- /* Tell lockdep we are about to re-enable */
- trace_hardirqs_on();
-
- /*
- * Mark interrupts as soft-enabled and clear the
- * PACA_IRQ_HARD_DIS from the pending mask since we
- * are about to hard enable as well as a side effect
- * of entering the low power state.
- */
- local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
- irq_soft_mask_set(IRQS_ENABLED);
-
- /* Tell the caller to enter the low power state */
- return true;
-}
-
-#ifdef CONFIG_PPC_BOOK3S
-/*
- * This is for idle sequences that return with IRQs off, but the
- * idle state itself wakes on interrupt. Tell the irq tracer that
- * IRQs are enabled for the duration of idle so it does not get long
- * off times. Must be paired with fini_irq_for_idle_irqsoff.
- */
-bool prep_irq_for_idle_irqsoff(void)
-{
- WARN_ON(!irqs_disabled());
-
- /*
- * First we need to hard disable to ensure no interrupt
- * occurs before we effectively enter the low power state
- */
- __hard_irq_disable();
- local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
-
- /*
- * If anything happened while we were soft-disabled,
- * we return now and do not enter the low power state.
- */
- if (lazy_irq_pending())
- return false;
-
- /* Tell lockdep we are about to re-enable */
- trace_hardirqs_on();
-
- return true;
-}
-
-/*
- * Take the SRR1 wakeup reason, index into this table to find the
- * appropriate irq_happened bit.
- *
- * Sytem reset exceptions taken in idle state also come through here,
- * but they are NMI interrupts so do not need to wait for IRQs to be
- * restored, and should be taken as early as practical. These are marked
- * with 0xff in the table. The Power ISA specifies 0100b as the system
- * reset interrupt reason.
- */
-#define IRQ_SYSTEM_RESET 0xff
-
-static const u8 srr1_to_lazyirq[0x10] = {
- 0, 0, 0,
- PACA_IRQ_DBELL,
- IRQ_SYSTEM_RESET,
- PACA_IRQ_DBELL,
- PACA_IRQ_DEC,
- 0,
- PACA_IRQ_EE,
- PACA_IRQ_EE,
- PACA_IRQ_HMI,
- 0, 0, 0, 0, 0 };
-
-void replay_system_reset(void)
-{
- struct pt_regs regs;
-
- ppc_save_regs(&regs);
- regs.trap = 0x100;
- get_paca()->in_nmi = 1;
- system_reset_exception(&regs);
- get_paca()->in_nmi = 0;
-}
-EXPORT_SYMBOL_GPL(replay_system_reset);
-
-void irq_set_pending_from_srr1(unsigned long srr1)
-{
- unsigned int idx = (srr1 & SRR1_WAKEMASK_P8) >> 18;
- u8 reason = srr1_to_lazyirq[idx];
-
- /*
- * Take the system reset now, which is immediately after registers
- * are restored from idle. It's an NMI, so interrupts need not be
- * re-enabled before it is taken.
- */
- if (unlikely(reason == IRQ_SYSTEM_RESET)) {
- replay_system_reset();
- return;
- }
-
- if (reason == PACA_IRQ_DBELL) {
- /*
- * When doorbell triggers a system reset wakeup, the message
- * is not cleared, so if the doorbell interrupt is replayed
- * and the IPI handled, the doorbell interrupt would still
- * fire when EE is enabled.
- *
- * To avoid taking the superfluous doorbell interrupt,
- * execute a msgclr here before the interrupt is replayed.
- */
- ppc_msgclr(PPC_DBELL_MSGTYPE);
- }
-
- /*
- * The 0 index (SRR1[42:45]=b0000) must always evaluate to 0,
- * so this can be called unconditionally with the SRR1 wake
- * reason as returned by the idle code, which uses 0 to mean no
- * interrupt.
- *
- * If a future CPU was to designate this as an interrupt reason,
- * then a new index for no interrupt must be assigned.
- */
- local_paca->irq_happened |= reason;
-}
-#endif /* CONFIG_PPC_BOOK3S */
-
-/*
- * Force a replay of the external interrupt handler on this CPU.
- */
-void force_external_irq_replay(void)
-{
- /*
- * This must only be called with interrupts soft-disabled,
- * the replay will happen when re-enabling.
- */
- WARN_ON(!arch_irqs_disabled());
-
- /*
- * Interrupts must always be hard disabled before irq_happened is
- * modified (to prevent lost update in case of interrupt between
- * load and store).
- */
- __hard_irq_disable();
- local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
-
- /* Indicate in the PACA that we have an interrupt to replay */
- local_paca->irq_happened |= PACA_IRQ_EE;
-}
-
-#endif /* CONFIG_PPC64 */
-
int arch_show_interrupts(struct seq_file *p, int prec)
{
int j;
@@ -595,17 +185,15 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
return sum;
}
-static inline void check_stack_overflow(void)
+static inline void check_stack_overflow(unsigned long sp)
{
- long sp;
-
if (!IS_ENABLED(CONFIG_DEBUG_STACKOVERFLOW))
return;
- sp = current_stack_pointer & (THREAD_SIZE - 1);
+ sp &= THREAD_SIZE - 1;
- /* check for stack overflow: is there less than 2KB free? */
- if (unlikely(sp < 2048)) {
+ /* check for stack overflow: is there less than 1/4th free? */
+ if (unlikely(sp < THREAD_SIZE / 4)) {
pr_err("do_IRQ: stack overflow: %ld\n", sp);
dump_stack();
}
@@ -632,36 +220,16 @@ static __always_inline void call_do_softirq(const void *sp)
}
#endif
-static __always_inline void call_do_irq(struct pt_regs *regs, void *sp)
-{
- register unsigned long r3 asm("r3") = (unsigned long)regs;
-
- /* Temporarily switch r1 to sp, call __do_irq() then restore r1. */
- asm volatile (
- PPC_STLU " %%r1, %[offset](%[sp]) ;"
- "mr %%r1, %[sp] ;"
- "bl %[callee] ;"
- PPC_LL " %%r1, 0(%%r1) ;"
- : // Outputs
- "+r" (r3)
- : // Inputs
- [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_OVERHEAD),
- [callee] "i" (__do_irq)
- : // Clobbers
- "lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6",
- "cr7", "r0", "r4", "r5", "r6", "r7", "r8", "r9", "r10",
- "r11", "r12"
- );
-}
-
DEFINE_STATIC_CALL_RET0(ppc_get_irq, *ppc_md.get_irq);
-void __do_irq(struct pt_regs *regs)
+static void __do_irq(struct pt_regs *regs, unsigned long oldsp)
{
unsigned int irq;
trace_irq_entry(regs);
+ check_stack_overflow(oldsp);
+
/*
* Query the platform PIC for the interrupt & ack it.
*
@@ -682,6 +250,29 @@ void __do_irq(struct pt_regs *regs)
trace_irq_exit(regs);
}
+static __always_inline void call_do_irq(struct pt_regs *regs, void *sp)
+{
+ register unsigned long r3 asm("r3") = (unsigned long)regs;
+
+ /* Temporarily switch r1 to sp, call __do_irq() then restore r1. */
+ asm volatile (
+ PPC_STLU " %%r1, %[offset](%[sp]) ;"
+ "mr %%r4, %%r1 ;"
+ "mr %%r1, %[sp] ;"
+ "bl %[callee] ;"
+ PPC_LL " %%r1, 0(%%r1) ;"
+ : // Outputs
+ "+r" (r3)
+ : // Inputs
+ [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_OVERHEAD),
+ [callee] "i" (__do_irq)
+ : // Clobbers
+ "lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6",
+ "cr7", "r0", "r4", "r5", "r6", "r7", "r8", "r9", "r10",
+ "r11", "r12"
+ );
+}
+
void __do_IRQ(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
@@ -692,16 +283,11 @@ void __do_IRQ(struct pt_regs *regs)
irqsp = hardirq_ctx[raw_smp_processor_id()];
sirqsp = softirq_ctx[raw_smp_processor_id()];
- check_stack_overflow();
-
- /* Already there ? */
- if (unlikely(cursp == irqsp || cursp == sirqsp)) {
- __do_irq(regs);
- set_irq_regs(old_regs);
- return;
- }
- /* Switch stack and call */
- call_do_irq(regs, irqsp);
+ /* Already there ? If not switch stack and call */
+ if (unlikely(cursp == irqsp || cursp == sirqsp))
+ __do_irq(regs, current_stack_pointer);
+ else
+ call_do_irq(regs, irqsp);
set_irq_regs(old_regs);
}
@@ -798,13 +384,3 @@ int irq_choose_cpu(const struct cpumask *mask)
return hard_smp_processor_id();
}
#endif
-
-#ifdef CONFIG_PPC64
-static int __init setup_noirqdistrib(char *str)
-{
- distribute_irqs = 0;
- return 1;
-}
-
-__setup("noirqdistrib", setup_noirqdistrib);
-#endif /* CONFIG_PPC64 */