linux_dsm_epyc7002/arch/x86/include/asm/irq.h

51 lines
1.2 KiB
C
Raw Normal View History

#ifndef _ASM_X86_IRQ_H
#define _ASM_X86_IRQ_H
/*
* (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
*
* IRQ/IPI changes taken from work by Thomas Radke
* <tomsoft@informatik.tu-chemnitz.de>
*/
#include <asm/apicdef.h>
#include <asm/irq_vectors.h>
static inline int irq_canonicalize(int irq)
{
return ((irq == 2) ? 9 : irq);
}
#ifdef CONFIG_X86_32
extern void irq_ctx_init(int cpu);
#else
# define irq_ctx_init(cpu) do { } while (0)
#endif
#define __ARCH_HAS_DO_SOFTIRQ
#ifdef CONFIG_HOTPLUG_CPU
#include <linux/cpumask.h>
x86: Add check for number of available vectors before CPU down Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=64791 When a cpu is downed on a system, the irqs on the cpu are assigned to other cpus. It is possible, however, that when a cpu is downed there aren't enough free vectors on the remaining cpus to account for the vectors from the cpu that is being downed. This results in an interesting "overflow" condition where irqs are "assigned" to a CPU but are not handled. For example, when downing cpus on a 1-64 logical processor system: <snip> [ 232.021745] smpboot: CPU 61 is now offline [ 238.480275] smpboot: CPU 62 is now offline [ 245.991080] ------------[ cut here ]------------ [ 245.996270] WARNING: CPU: 0 PID: 0 at net/sched/sch_generic.c:264 dev_watchdog+0x246/0x250() [ 246.005688] NETDEV WATCHDOG: p786p1 (ixgbe): transmit queue 0 timed out [ 246.013070] Modules linked in: lockd sunrpc iTCO_wdt iTCO_vendor_support sb_edac ixgbe microcode e1000e pcspkr joydev edac_core lpc_ich ioatdma ptp mdio mfd_core i2c_i801 dca pps_core i2c_core wmi acpi_cpufreq isci libsas scsi_transport_sas [ 246.037633] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.12.0+ #14 [ 246.044451] Hardware name: Intel Corporation S4600LH ........../SVRBD-ROW_T, BIOS SE5C600.86B.01.08.0003.022620131521 02/26/2013 [ 246.057371] 0000000000000009 ffff88081fa03d40 ffffffff8164fbf6 ffff88081fa0ee48 [ 246.065728] ffff88081fa03d90 ffff88081fa03d80 ffffffff81054ecc ffff88081fa13040 [ 246.074073] 0000000000000000 ffff88200cce0000 0000000000000040 0000000000000000 [ 246.082430] Call Trace: [ 246.085174] <IRQ> [<ffffffff8164fbf6>] dump_stack+0x46/0x58 [ 246.091633] [<ffffffff81054ecc>] warn_slowpath_common+0x8c/0xc0 [ 246.098352] [<ffffffff81054fb6>] warn_slowpath_fmt+0x46/0x50 [ 246.104786] [<ffffffff815710d6>] dev_watchdog+0x246/0x250 [ 246.110923] [<ffffffff81570e90>] ? dev_deactivate_queue.constprop.31+0x80/0x80 [ 246.119097] [<ffffffff8106092a>] call_timer_fn+0x3a/0x110 [ 246.125224] [<ffffffff8106280f>] ? update_process_times+0x6f/0x80 [ 246.132137] [<ffffffff81570e90>] ? dev_deactivate_queue.constprop.31+0x80/0x80 [ 246.140308] [<ffffffff81061db0>] run_timer_softirq+0x1f0/0x2a0 [ 246.146933] [<ffffffff81059a80>] __do_softirq+0xe0/0x220 [ 246.152976] [<ffffffff8165fedc>] call_softirq+0x1c/0x30 [ 246.158920] [<ffffffff810045f5>] do_softirq+0x55/0x90 [ 246.164670] [<ffffffff81059d35>] irq_exit+0xa5/0xb0 [ 246.170227] [<ffffffff8166062a>] smp_apic_timer_interrupt+0x4a/0x60 [ 246.177324] [<ffffffff8165f40a>] apic_timer_interrupt+0x6a/0x70 [ 246.184041] <EOI> [<ffffffff81505a1b>] ? cpuidle_enter_state+0x5b/0xe0 [ 246.191559] [<ffffffff81505a17>] ? cpuidle_enter_state+0x57/0xe0 [ 246.198374] [<ffffffff81505b5d>] cpuidle_idle_call+0xbd/0x200 [ 246.204900] [<ffffffff8100b7ae>] arch_cpu_idle+0xe/0x30 [ 246.210846] [<ffffffff810a47b0>] cpu_startup_entry+0xd0/0x250 [ 246.217371] [<ffffffff81646b47>] rest_init+0x77/0x80 [ 246.223028] [<ffffffff81d09e8e>] start_kernel+0x3ee/0x3fb [ 246.229165] [<ffffffff81d0989f>] ? repair_env_string+0x5e/0x5e [ 246.235787] [<ffffffff81d095a5>] x86_64_start_reservations+0x2a/0x2c [ 246.242990] [<ffffffff81d0969f>] x86_64_start_kernel+0xf8/0xfc [ 246.249610] ---[ end trace fb74fdef54d79039 ]--- [ 246.254807] ixgbe 0000:c2:00.0 p786p1: initiating reset due to tx timeout [ 246.262489] ixgbe 0000:c2:00.0 p786p1: Reset adapter Last login: Mon Nov 11 08:35:14 from 10.18.17.119 [root@(none) ~]# [ 246.792676] ixgbe 0000:c2:00.0 p786p1: detected SFP+: 5 [ 249.231598] ixgbe 0000:c2:00.0 p786p1: NIC Link is Up 10 Gbps, Flow Control: RX/TX [ 246.792676] ixgbe 0000:c2:00.0 p786p1: detected SFP+: 5 [ 249.231598] ixgbe 0000:c2:00.0 p786p1: NIC Link is Up 10 Gbps, Flow Control: RX/TX (last lines keep repeating. ixgbe driver is dead until module reload.) If the downed cpu has more vectors than are free on the remaining cpus on the system, it is possible that some vectors are "orphaned" even though they are assigned to a cpu. In this case, since the ixgbe driver had a watchdog, the watchdog fired and notified that something was wrong. This patch adds a function, check_vectors(), to compare the number of vectors on the CPU going down and compares it to the number of vectors available on the system. If there aren't enough vectors for the CPU to go down, an error is returned and propogated back to userspace. v2: Do not need to look at percpu irqs v3: Need to check affinity to prevent counting of MSIs in IOAPIC Lowest Priority Mode v4: Additional changes suggested by Gong Chen. v5/v6/v7/v8: Updated comment text Signed-off-by: Prarit Bhargava <prarit@redhat.com> Link: http://lkml.kernel.org/r/1389613861-3853-1-git-send-email-prarit@redhat.com Reviewed-by: Gong Chen <gong.chen@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Michel Lespinasse <walken@google.com> Cc: Seiji Aguchi <seiji.aguchi@hds.com> Cc: Yang Zhang <yang.z.zhang@Intel.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Janet Morgan <janet.morgan@intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Ruiv Wang <ruiv.wang@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Cc: <stable@vger.kernel.org>
2014-01-13 18:51:01 +07:00
extern int check_irq_vectors_for_cpu_disable(void);
extern void fixup_irqs(void);
extern void irq_force_complete_move(int);
#endif
extern void (*x86_platform_ipi_callback)(void);
extern void native_init_IRQ(void);
extern bool handle_irq(unsigned irq, struct pt_regs *regs);
extern __visible unsigned int do_IRQ(struct pt_regs *regs);
/* Interrupt vector management */
extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
extern int vector_used_by_percpu_irq(unsigned int vector);
extern void init_ISA_irqs(void);
#ifdef CONFIG_X86_LOCAL_APIC
void arch_trigger_all_cpu_backtrace(void);
#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
#endif
#endif /* _ASM_X86_IRQ_H */