[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [PATCH for-4.21 03/10] x86/HPET: use single, global, low-priority vector for broadcast IRQ
Using dynamically allocated / maintained vectors has several downsides: - possible nesting of IRQs due to the effects of IRQ migration, - reduction of vectors available for devices, - IRQs not moving as intended if there's shortage of vectors, - higher runtime overhead. As the vector also doesn't need to be of any priority (first and foremost it really shouldn't be of higher or same priority as the timer IRQ, as that raises TIMER_SOFTIRQ anyway), avoid any "ordinary" vectors altogther and use a vector from the 0x10...0x1f exception vector space. Exception vs interrupt can easily be distinguished by checking for the presence of an error code. Fixes: 996576b965cc ("xen: allow up to 16383 cpus") Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx> --- This is an alternative proposal to https://lists.xen.org/archives/html/xen-devel/2014-03/msg00399.html. The Fixes: tag indicates where the problem got signficantly worse; in principle it was there already before (crashing at perhaps 6 or 7 levels of nested IRQs). --- a/xen/arch/x86/hpet.c +++ b/xen/arch/x86/hpet.c @@ -9,17 +9,19 @@ #include <xen/timer.h> #include <xen/smp.h> #include <xen/softirq.h> +#include <xen/cpuidle.h> #include <xen/irq.h> #include <xen/numa.h> #include <xen/param.h> #include <xen/sched.h> #include <asm/apic.h> -#include <asm/fixmap.h> #include <asm/div64.h> +#include <asm/fixmap.h> +#include <asm/genapic.h> #include <asm/hpet.h> +#include <asm/irq-vectors.h> #include <asm/msi.h> -#include <xen/cpuidle.h> #define MAX_DELTA_NS MILLISECS(10*1000) #define MIN_DELTA_NS MICROSECS(20) @@ -307,15 +309,13 @@ static void cf_check hpet_msi_set_affini struct hpet_event_channel *ch = desc->action->dev_id; struct msi_msg msg = ch->msi.msg; - msg.dest32 = set_desc_affinity(desc, mask); - if ( msg.dest32 == BAD_APICID ) - return; + /* This really is only for dump_irqs(). */ + cpumask_copy(desc->arch.cpu_mask, mask); - msg.data &= ~MSI_DATA_VECTOR_MASK; - msg.data |= MSI_DATA_VECTOR(desc->arch.vector); + msg.dest32 = cpu_mask_to_apicid(mask); msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; msg.address_lo |= MSI_ADDR_DEST_ID(msg.dest32); - if ( msg.data != ch->msi.msg.data || msg.dest32 != ch->msi.msg.dest32 ) + if ( msg.dest32 != ch->msi.msg.dest32 ) hpet_msi_write(ch, &msg); } @@ -328,7 +328,7 @@ static hw_irq_controller hpet_msi_type = .shutdown = hpet_msi_shutdown, .enable = hpet_msi_unmask, .disable = hpet_msi_mask, - .ack = ack_nonmaskable_msi_irq, + .ack = irq_actor_none, .end = end_nonmaskable_irq, .set_affinity = hpet_msi_set_affinity, }; @@ -347,6 +347,12 @@ static int __init hpet_setup_msi_irq(str u32 cfg = hpet_read32(HPET_Tn_CFG(ch->idx)); irq_desc_t *desc = irq_to_desc(ch->msi.irq); + clear_irq_vector(ch->msi.irq); + ret = bind_irq_vector(ch->msi.irq, HPET_BROADCAST_VECTOR, &cpu_online_map); + if ( ret ) + return ret; + cpumask_setall(desc->affinity); + if ( iommu_intremap != iommu_intremap_off ) { ch->msi.hpet_id = hpet_blockid; @@ -457,7 +463,7 @@ static struct hpet_event_channel *hpet_g /* * Try the least recently used channel first. It may still have its IRQ's * affinity set to the desired CPU. This way we also limit having multiple - * of our IRQs raised on the same CPU, in possibly a nested manner. + * of our IRQs raised on the same CPU. */ ch = per_cpu(lru_channel, cpu); if ( ch && !test_and_set_bit(HPET_EVT_USED_BIT, &ch->flags) ) @@ -497,6 +503,7 @@ static void set_channel_irq_affinity(str spin_lock(&desc->lock); hpet_msi_mask(desc); hpet_msi_set_affinity(desc, cpumask_of(ch->cpu)); + per_cpu(vector_irq, ch->cpu)[HPET_BROADCAST_VECTOR] = ch->msi.irq; hpet_msi_unmask(desc); spin_unlock(&desc->lock); --- a/xen/arch/x86/include/asm/irq-vectors.h +++ b/xen/arch/x86/include/asm/irq-vectors.h @@ -18,6 +18,15 @@ /* IRQ0 (timer) is statically allocated but must be high priority. */ #define IRQ0_VECTOR 0xf0 +/* + * Low-priority (for now statically allocated) vectors, sharing entry + * points with exceptions in the 0x10 ... 0x1f range, as long as the + * respective exception has an error code. + */ +#define FIRST_LOPRIORITY_VECTOR 0x10 +#define HPET_BROADCAST_VECTOR X86_EXC_AC +#define LAST_LOPRIORITY_VECTOR 0x1f + /* Legacy PIC uses vectors 0x20-0x2f. */ #define FIRST_LEGACY_VECTOR FIRST_DYNAMIC_VECTOR #define LAST_LEGACY_VECTOR (FIRST_LEGACY_VECTOR + 0xf) @@ -40,7 +49,7 @@ /* There's no IRQ2 at the PIC. */ #define IRQ_MOVE_CLEANUP_VECTOR (FIRST_LEGACY_VECTOR + 2) -#define FIRST_IRQ_VECTOR FIRST_DYNAMIC_VECTOR +#define FIRST_IRQ_VECTOR FIRST_LOPRIORITY_VECTOR #define LAST_IRQ_VECTOR LAST_HIPRIORITY_VECTOR #endif /* _ASM_IRQ_VECTORS_H */ --- a/xen/arch/x86/irq.c +++ b/xen/arch/x86/irq.c @@ -755,8 +755,9 @@ void setup_vector_irq(unsigned int cpu) if ( !irq_desc_initialized(desc) ) continue; vector = irq_to_vector(irq); - if ( vector >= FIRST_HIPRIORITY_VECTOR && - vector <= LAST_HIPRIORITY_VECTOR ) + if ( vector <= (vector >= FIRST_HIPRIORITY_VECTOR + ? LAST_HIPRIORITY_VECTOR + : LAST_LOPRIORITY_VECTOR) ) cpumask_set_cpu(cpu, desc->arch.cpu_mask); else if ( !cpumask_test_cpu(cpu, desc->arch.cpu_mask) ) continue; --- a/xen/arch/x86/msi.c +++ b/xen/arch/x86/msi.c @@ -158,7 +158,7 @@ void msi_compose_msg(unsigned vector, co { memset(msg, 0, sizeof(*msg)); - if ( vector < FIRST_DYNAMIC_VECTOR ) + if ( vector < FIRST_LOPRIORITY_VECTOR ) return; if ( cpu_mask ) --- a/xen/arch/x86/x86_64/entry.S +++ b/xen/arch/x86/x86_64/entry.S @@ -1045,7 +1045,13 @@ END(entry_GP) FUNC(entry_AC) ENDBR64 + /* #AC shares its entry point with the HPET broadcast interrupt. */ + test $8, %spl + jz .Lac + push $0 +.Lac: movb $X86_EXC_AC, EFRAME_entry_vector(%rsp) + jnz common_interrupt jmp handle_exception END(entry_AC)
|
![]() |
Lists.xenproject.org is hosted with RackSpace, monitoring our |