| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <aQj5mGZ6_BBlAm3B@shell.ilvokhin.com>
Date: Mon, 3 Nov 2025 18:51:04 +0000
From: Dmitry Ilvokhin <d@...okhin.com>
To: Thomas Gleixner <tglx@...utronix.de>, Ingo Molnar <mingo@...hat.com>,
Borislav Petkov <bp@...en8.de>,
Dave Hansen <dave.hansen@...ux.intel.com>, x86@...nel.org,
"H. Peter Anvin" <hpa@...or.com>
Cc: linux-kernel@...r.kernel.org, kernel-team@...a.com
Subject: [PATCH v2] x86/irq: Optimize interrupts decimals printing
Monitoring tools (such as Prometheus [1] or dynolog [2]) periodically
pull /proc/interrupts to export metrics as a timeseries for future
analysis and investigation.
In large fleets, /proc/interrupts is polled (often every few seconds) on
every machine. The cumulative overhead adds up quickly across thousands
of nodes, so reducing the cost of generating these stats does have a
measurable operational impact. With the ongoing trend toward higher core
counts per machine, this cost becomes even more noticeable over time,
since interrupt counters are per-CPU. In Meta's fleet, we have observed
this overhead at scale.
Although a binary /proc interface would be a better long-term solution
due to lower formatting (kernel side) and parsing (userspace side)
overhead, the text interface will remain in use for some time, even if
better solutions will be available. Optimizing the /proc/interrupts
printing code is therefore still beneficial.
Function seq_printf() supports rich format string for decimals printing,
but it doesn't required for printing /proc/interrupts per CPU counters,
seq_put_decimal_ull_width() function can be used instead to print per
CPU counters, because very limited formatting is required for this case.
Similar optimization idea is already used in show_interrupts().
Performance counter stats (truncated) for 'sh -c cat /proc/interrupts
>/dev/null' (1000 runs) before and after applying the patch below.
Before:
3.42 msec task-clock # 0.802 CPUs utilized ( +- 0.05% )
1 context-switches # 291.991 /sec ( +- 0.74% )
0 cpu-migrations # 0.000 /sec
343 page-faults # 100.153 K/sec ( +- 0.01% )
8,932,242 instructions # 1.66 insn per cycle ( +- 0.34% )
5,374,427 cycles # 1.569 GHz ( +- 0.04% )
1,483,154 branches # 433.068 M/sec ( +- 0.22% )
28,768 branch-misses # 1.94% of all branches ( +- 0.31% )
0.00427182 +- 0.00000215 seconds time elapsed ( +- 0.05% )
After:
2.39 msec task-clock # 0.796 CPUs utilized ( +- 0.06% )
1 context-switches # 418.541 /sec ( +- 0.70% )
0 cpu-migrations # 0.000 /sec
343 page-faults # 143.560 K/sec ( +- 0.01% )
7,020,982 instructions # 1.30 insn per cycle ( +- 0.52% )
5,397,266 cycles # 2.259 GHz ( +- 0.06% )
1,569,648 branches # 656.962 M/sec ( +- 0.08% )
25,419 branch-misses # 1.62% of all branches ( +- 0.72% )
0.00299996 +- 0.00000206 seconds time elapsed ( +- 0.07% )
Relative speed up in time elapsed is around 29%.
[1]: https://github.com/prometheus/prometheus
[2]: https://github.com/facebookincubator/dynolog
Signed-off-by: Dmitry Ilvokhin <d@...okhin.com>
---
Changes v2:
- Expanded commit message: add more rationale for the proposed change.
- Renamed helper put_spaced_decimal() -> put_decimal() primarely to make
checkpatch.pl --strict pass.
arch/x86/kernel/irq.c | 107 ++++++++++++++++++++++--------------------
1 file changed, 57 insertions(+), 50 deletions(-)
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 10721a125226..4a8bac31be70 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -61,6 +61,18 @@ void ack_bad_irq(unsigned int irq)
apic_eoi();
}
+/*
+ * A helper routine for putting space and decimal number without overhead
+ * from rich format of printf().
+ */
+static void put_decimal(struct seq_file *p, unsigned long long num)
+{
+ const char *delimiter = " ";
+ unsigned int width = 10;
+
+ seq_put_decimal_ull_width(p, delimiter, num, width);
+}
+
#define irq_stats(x) (&per_cpu(irq_stat, x))
/*
* /proc/interrupts printing for arch specific interrupts
@@ -69,103 +81,101 @@ int arch_show_interrupts(struct seq_file *p, int prec)
{
int j;
- seq_printf(p, "%*s: ", prec, "NMI");
+ seq_printf(p, "%*s:", prec, "NMI");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->__nmi_count);
+ put_decimal(p, irq_stats(j)->__nmi_count);
seq_puts(p, " Non-maskable interrupts\n");
#ifdef CONFIG_X86_LOCAL_APIC
- seq_printf(p, "%*s: ", prec, "LOC");
+ seq_printf(p, "%*s:", prec, "LOC");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->apic_timer_irqs);
+ put_decimal(p, irq_stats(j)->apic_timer_irqs);
seq_puts(p, " Local timer interrupts\n");
- seq_printf(p, "%*s: ", prec, "SPU");
+ seq_printf(p, "%*s:", prec, "SPU");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count);
+ put_decimal(p, irq_stats(j)->irq_spurious_count);
seq_puts(p, " Spurious interrupts\n");
- seq_printf(p, "%*s: ", prec, "PMI");
+ seq_printf(p, "%*s:", prec, "PMI");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs);
+ put_decimal(p, irq_stats(j)->apic_perf_irqs);
seq_puts(p, " Performance monitoring interrupts\n");
- seq_printf(p, "%*s: ", prec, "IWI");
+ seq_printf(p, "%*s:", prec, "IWI");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->apic_irq_work_irqs);
+ put_decimal(p, irq_stats(j)->apic_irq_work_irqs);
seq_puts(p, " IRQ work interrupts\n");
- seq_printf(p, "%*s: ", prec, "RTR");
+ seq_printf(p, "%*s:", prec, "RTR");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->icr_read_retry_count);
+ put_decimal(p, irq_stats(j)->icr_read_retry_count);
seq_puts(p, " APIC ICR read retries\n");
if (x86_platform_ipi_callback) {
- seq_printf(p, "%*s: ", prec, "PLT");
+ seq_printf(p, "%*s:", prec, "PLT");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->x86_platform_ipis);
+ put_decimal(p, irq_stats(j)->x86_platform_ipis);
seq_puts(p, " Platform interrupts\n");
}
#endif
#ifdef CONFIG_SMP
- seq_printf(p, "%*s: ", prec, "RES");
+ seq_printf(p, "%*s:", prec, "RES");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->irq_resched_count);
+ put_decimal(p, irq_stats(j)->irq_resched_count);
seq_puts(p, " Rescheduling interrupts\n");
- seq_printf(p, "%*s: ", prec, "CAL");
+ seq_printf(p, "%*s:", prec, "CAL");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->irq_call_count);
+ put_decimal(p, irq_stats(j)->irq_call_count);
seq_puts(p, " Function call interrupts\n");
- seq_printf(p, "%*s: ", prec, "TLB");
+ seq_printf(p, "%*s:", prec, "TLB");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count);
+ put_decimal(p, irq_stats(j)->irq_tlb_count);
seq_puts(p, " TLB shootdowns\n");
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
- seq_printf(p, "%*s: ", prec, "TRM");
+ seq_printf(p, "%*s:", prec, "TRM");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->irq_thermal_count);
+ put_decimal(p, irq_stats(j)->irq_thermal_count);
seq_puts(p, " Thermal event interrupts\n");
#endif
#ifdef CONFIG_X86_MCE_THRESHOLD
- seq_printf(p, "%*s: ", prec, "THR");
+ seq_printf(p, "%*s:", prec, "THR");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count);
+ put_decimal(p, irq_stats(j)->irq_threshold_count);
seq_puts(p, " Threshold APIC interrupts\n");
#endif
#ifdef CONFIG_X86_MCE_AMD
- seq_printf(p, "%*s: ", prec, "DFR");
+ seq_printf(p, "%*s:", prec, "DFR");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->irq_deferred_error_count);
+ put_decimal(p, irq_stats(j)->irq_deferred_error_count);
seq_puts(p, " Deferred Error APIC interrupts\n");
#endif
#ifdef CONFIG_X86_MCE
- seq_printf(p, "%*s: ", prec, "MCE");
+ seq_printf(p, "%*s:", prec, "MCE");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", per_cpu(mce_exception_count, j));
+ put_decimal(p, per_cpu(mce_exception_count, j));
seq_puts(p, " Machine check exceptions\n");
- seq_printf(p, "%*s: ", prec, "MCP");
+ seq_printf(p, "%*s:", prec, "MCP");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", per_cpu(mce_poll_count, j));
+ put_decimal(p, per_cpu(mce_poll_count, j));
seq_puts(p, " Machine check polls\n");
#endif
#ifdef CONFIG_X86_HV_CALLBACK_VECTOR
if (test_bit(HYPERVISOR_CALLBACK_VECTOR, system_vectors)) {
- seq_printf(p, "%*s: ", prec, "HYP");
+ seq_printf(p, "%*s:", prec, "HYP");
for_each_online_cpu(j)
- seq_printf(p, "%10u ",
- irq_stats(j)->irq_hv_callback_count);
+ put_decimal(p, irq_stats(j)->irq_hv_callback_count);
seq_puts(p, " Hypervisor callback interrupts\n");
}
#endif
#if IS_ENABLED(CONFIG_HYPERV)
if (test_bit(HYPERV_REENLIGHTENMENT_VECTOR, system_vectors)) {
- seq_printf(p, "%*s: ", prec, "HRE");
+ seq_printf(p, "%*s:", prec, "HRE");
for_each_online_cpu(j)
- seq_printf(p, "%10u ",
- irq_stats(j)->irq_hv_reenlightenment_count);
+ put_decimal(p,
+ irq_stats(j)->irq_hv_reenlightenment_count);
seq_puts(p, " Hyper-V reenlightenment interrupts\n");
}
if (test_bit(HYPERV_STIMER0_VECTOR, system_vectors)) {
- seq_printf(p, "%*s: ", prec, "HVS");
+ seq_printf(p, "%*s:", prec, "HVS");
for_each_online_cpu(j)
- seq_printf(p, "%10u ",
- irq_stats(j)->hyperv_stimer0_count);
+ put_decimal(p, irq_stats(j)->hyperv_stimer0_count);
seq_puts(p, " Hyper-V stimer0 interrupts\n");
}
#endif
@@ -174,28 +184,25 @@ int arch_show_interrupts(struct seq_file *p, int prec)
seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
#endif
#if IS_ENABLED(CONFIG_KVM)
- seq_printf(p, "%*s: ", prec, "PIN");
+ seq_printf(p, "%*s:", prec, "PIN");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis);
+ put_decimal(p, irq_stats(j)->kvm_posted_intr_ipis);
seq_puts(p, " Posted-interrupt notification event\n");
- seq_printf(p, "%*s: ", prec, "NPI");
+ seq_printf(p, "%*s:", prec, "NPI");
for_each_online_cpu(j)
- seq_printf(p, "%10u ",
- irq_stats(j)->kvm_posted_intr_nested_ipis);
+ put_decimal(p, irq_stats(j)->kvm_posted_intr_nested_ipis);
seq_puts(p, " Nested posted-interrupt event\n");
- seq_printf(p, "%*s: ", prec, "PIW");
+ seq_printf(p, "%*s:", prec, "PIW");
for_each_online_cpu(j)
- seq_printf(p, "%10u ",
- irq_stats(j)->kvm_posted_intr_wakeup_ipis);
+ put_decimal(p, irq_stats(j)->kvm_posted_intr_wakeup_ipis);
seq_puts(p, " Posted-interrupt wakeup event\n");
#endif
#ifdef CONFIG_X86_POSTED_MSI
- seq_printf(p, "%*s: ", prec, "PMN");
+ seq_printf(p, "%*s:", prec, "PMN");
for_each_online_cpu(j)
- seq_printf(p, "%10u ",
- irq_stats(j)->posted_msi_notification_count);
+ put_decimal(p, irq_stats(j)->posted_msi_notification_count);
seq_puts(p, " Posted MSI notification event\n");
#endif
return 0;
--
2.47.3
Powered by blists - more mailing lists