linux-next/arch/s390/kernel/perf_event.c
Linus Torvalds f41dac3efb Performance events changes for v6.13:
- Uprobes:
     - Add BPF session support (Jiri Olsa)
     - Switch to RCU Tasks Trace flavor for better performance (Andrii Nakryiko)
     - Massively increase uretprobe SMP scalability by SRCU-protecting
       the uretprobe lifetime (Andrii Nakryiko)
     - Kill xol_area->slot_count (Oleg Nesterov)
 
  - Core facilities:
     - Implement targeted high-frequency profiling by adding the ability
       for an event to "pause" or "resume" AUX area tracing (Adrian Hunter)
 
  - VM profiling/sampling:
     - Correct perf sampling with guest VMs (Colton Lewis)
 
  - New hardware support:
     - x86/intel: Add PMU support for Intel ArrowLake-H CPUs (Dapeng Mi)
 
  - Misc fixes and enhancements:
     - x86/intel/pt: Fix buffer full but size is 0 case (Adrian Hunter)
     - x86/amd: Warn only on new bits set (Breno Leitao)
     - x86/amd/uncore: Avoid a false positive warning about snprintf
                       truncation in amd_uncore_umc_ctx_init (Jean Delvare)
     - uprobes: Re-order struct uprobe_task to save some space (Christophe JAILLET)
     - x86/rapl: Move the pmu allocation out of CPU hotplug (Kan Liang)
     - x86/rapl: Clean up cpumask and hotplug (Kan Liang)
     - uprobes: Deuglify xol_get_insn_slot/xol_free_insn_slot paths (Oleg Nesterov)
 
 Signed-off-by: Ingo Molnar <mingo@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmc7eKERHG1pbmdvQGtl
 cm5lbC5vcmcACgkQEnMQ0APhK1i57A/+KQ6TrIoICVTE+BPlDfUw8NU+N3DagVb0
 dzoyDxlDRsnsYzeXZipPn+3IitX1w+DrGxBNIojSoiFVCLnHIKgo4uHbj7cVrR7J
 fBTVSnoJ94SGAk5ySebvLwMLce/YhXBeHK2lx6W/pI6acNcxzDfIabjjETeqltUo
 g7hmT9lo10pzZEZyuUfYX9khlWBxda1dKHc9pMIq7baeLe4iz/fCGlJ0K4d4M4z3
 NPZw239Np6iHUwu3Lcs4gNKe4rcDe7Bt47hpedemHe0Y+7c4s2HaPxbXWxvDtE76
 mlsg93i28f8SYxeV83pREn0EOCptXcljhiek+US+GR7NSbltMnV+uUiDfPKIE9+Y
 vYP/DYF9hx73FsOucEFrHxYYcePorn3pne5/khBYWdQU6TnlrBYWpoLQsjgCKTTR
 4JhCFlBZ5cDpc6ihtpwCwVTQ4Q/H7vM1XOlDwx0hPhcIPPHDreaQD/wxo61jBdXf
 PY0EPAxh3BcQxfPYuDS+XiYjQ8qO8MtXMKz5bZyHBZlbHwccV6T4ExjsLKxFk5As
 6BG8pkBWLg7drXAgVdleIY0ux+34w/Zzv7gemdlQxvWLlZrVvpjiG93oU3PTpZeq
 A2UD9eAOuXVD6+HsF/dmn88sFmcLWbrMskFWujkvhEUmCvSGAnz3YSS/mLEawBiT
 2xI8xykNWSY=
 =ItOT
 -----END PGP SIGNATURE-----

Merge tag 'perf-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance events updates from Ingo Molnar:
 "Uprobes:
    - Add BPF session support (Jiri Olsa)
    - Switch to RCU Tasks Trace flavor for better performance (Andrii
      Nakryiko)
    - Massively increase uretprobe SMP scalability by SRCU-protecting
      the uretprobe lifetime (Andrii Nakryiko)
    - Kill xol_area->slot_count (Oleg Nesterov)

  Core facilities:
    - Implement targeted high-frequency profiling by adding the ability
      for an event to "pause" or "resume" AUX area tracing (Adrian
      Hunter)

  VM profiling/sampling:
    - Correct perf sampling with guest VMs (Colton Lewis)

  New hardware support:
    - x86/intel: Add PMU support for Intel ArrowLake-H CPUs (Dapeng Mi)

  Misc fixes and enhancements:
    - x86/intel/pt: Fix buffer full but size is 0 case (Adrian Hunter)
    - x86/amd: Warn only on new bits set (Breno Leitao)
    - x86/amd/uncore: Avoid a false positive warning about snprintf
      truncation in amd_uncore_umc_ctx_init (Jean Delvare)
    - uprobes: Re-order struct uprobe_task to save some space
      (Christophe JAILLET)
    - x86/rapl: Move the pmu allocation out of CPU hotplug (Kan Liang)
    - x86/rapl: Clean up cpumask and hotplug (Kan Liang)
    - uprobes: Deuglify xol_get_insn_slot/xol_free_insn_slot paths (Oleg
      Nesterov)"

* tag 'perf-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
  perf/core: Correct perf sampling with guest VMs
  perf/x86: Refactor misc flag assignments
  perf/powerpc: Use perf_arch_instruction_pointer()
  perf/core: Hoist perf_instruction_pointer() and perf_misc_flags()
  perf/arm: Drop unused functions
  uprobes: Re-order struct uprobe_task to save some space
  perf/x86/amd/uncore: Avoid a false positive warning about snprintf truncation in amd_uncore_umc_ctx_init
  perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling
  perf/x86/intel/pt: Add support for pause / resume
  perf/core: Add aux_pause, aux_resume, aux_start_paused
  perf/x86/intel/pt: Fix buffer full but size is 0 case
  uprobes: SRCU-protect uretprobe lifetime (with timeout)
  uprobes: allow put_uprobe() from non-sleepable softirq context
  perf/x86/rapl: Clean up cpumask and hotplug
  perf/x86/rapl: Move the pmu allocation out of CPU hotplug
  uprobe: Add support for session consumer
  uprobe: Add data pointer to consumer handlers
  perf/x86/amd: Warn only on new bits set
  uprobes: fold xol_take_insn_slot() into xol_get_insn_slot()
  uprobes: kill xol_area->slot_count
  ...
2024-11-19 13:34:06 -08:00

233 lines
5.8 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Performance event support for s390x
*
* Copyright IBM Corp. 2012, 2013
* Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
*/
#define KMSG_COMPONENT "perf"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/kernel.h>
#include <linux/perf_event.h>
#include <linux/kvm_host.h>
#include <linux/percpu.h>
#include <linux/export.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>
#include <linux/uaccess.h>
#include <linux/compat.h>
#include <linux/sysfs.h>
#include <asm/stacktrace.h>
#include <asm/irq.h>
#include <asm/cpu_mf.h>
#include <asm/lowcore.h>
#include <asm/processor.h>
#include <asm/sysinfo.h>
#include <asm/unwind.h>
static struct kvm_s390_sie_block *sie_block(struct pt_regs *regs)
{
struct stack_frame *stack = (struct stack_frame *) regs->gprs[15];
if (!stack)
return NULL;
return (struct kvm_s390_sie_block *)stack->sie_control_block;
}
static bool is_in_guest(struct pt_regs *regs)
{
if (user_mode(regs))
return false;
#if IS_ENABLED(CONFIG_KVM)
return instruction_pointer(regs) == (unsigned long) &sie_exit;
#else
return false;
#endif
}
static unsigned long guest_is_user_mode(struct pt_regs *regs)
{
return sie_block(regs)->gpsw.mask & PSW_MASK_PSTATE;
}
static unsigned long instruction_pointer_guest(struct pt_regs *regs)
{
return sie_block(regs)->gpsw.addr;
}
unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)
{
return is_in_guest(regs) ? instruction_pointer_guest(regs)
: instruction_pointer(regs);
}
static unsigned long perf_misc_guest_flags(struct pt_regs *regs)
{
return guest_is_user_mode(regs) ? PERF_RECORD_MISC_GUEST_USER
: PERF_RECORD_MISC_GUEST_KERNEL;
}
static unsigned long perf_misc_flags_sf(struct pt_regs *regs)
{
struct perf_sf_sde_regs *sde_regs;
unsigned long flags;
sde_regs = (struct perf_sf_sde_regs *) &regs->int_parm_long;
if (sde_regs->in_guest)
flags = user_mode(regs) ? PERF_RECORD_MISC_GUEST_USER
: PERF_RECORD_MISC_GUEST_KERNEL;
else
flags = user_mode(regs) ? PERF_RECORD_MISC_USER
: PERF_RECORD_MISC_KERNEL;
return flags;
}
unsigned long perf_arch_misc_flags(struct pt_regs *regs)
{
/* Check if the cpum_sf PMU has created the pt_regs structure.
* In this case, perf misc flags can be easily extracted. Otherwise,
* do regular checks on the pt_regs content.
*/
if (regs->int_code == 0x1407 && regs->int_parm == CPU_MF_INT_SF_PRA)
if (!regs->gprs[15])
return perf_misc_flags_sf(regs);
if (is_in_guest(regs))
return perf_misc_guest_flags(regs);
return user_mode(regs) ? PERF_RECORD_MISC_USER
: PERF_RECORD_MISC_KERNEL;
}
static void print_debug_cf(void)
{
struct cpumf_ctr_info cf_info;
int cpu = smp_processor_id();
memset(&cf_info, 0, sizeof(cf_info));
if (!qctri(&cf_info))
pr_info("CPU[%i] CPUM_CF: ver=%u.%u A=%04x E=%04x C=%04x\n",
cpu, cf_info.cfvn, cf_info.csvn,
cf_info.auth_ctl, cf_info.enable_ctl, cf_info.act_ctl);
}
static void print_debug_sf(void)
{
struct hws_qsi_info_block si;
int cpu = smp_processor_id();
memset(&si, 0, sizeof(si));
if (qsi(&si))
return;
pr_info("CPU[%i] CPUM_SF: basic=%i diag=%i min=%lu max=%lu cpu_speed=%u\n",
cpu, si.as, si.ad, si.min_sampl_rate, si.max_sampl_rate,
si.cpu_speed);
if (si.as)
pr_info("CPU[%i] CPUM_SF: Basic-sampling: a=%i e=%i c=%i"
" bsdes=%i tear=%016lx dear=%016lx\n", cpu,
si.as, si.es, si.cs, si.bsdes, si.tear, si.dear);
if (si.ad)
pr_info("CPU[%i] CPUM_SF: Diagnostic-sampling: a=%i e=%i c=%i"
" dsdes=%i tear=%016lx dear=%016lx\n", cpu,
si.ad, si.ed, si.cd, si.dsdes, si.tear, si.dear);
}
void perf_event_print_debug(void)
{
unsigned long flags;
local_irq_save(flags);
if (cpum_cf_avail())
print_debug_cf();
if (cpum_sf_avail())
print_debug_sf();
local_irq_restore(flags);
}
/* Service level infrastructure */
static void sl_print_counter(struct seq_file *m)
{
struct cpumf_ctr_info ci;
memset(&ci, 0, sizeof(ci));
if (qctri(&ci))
return;
seq_printf(m, "CPU-MF: Counter facility: version=%u.%u "
"authorization=%04x\n", ci.cfvn, ci.csvn, ci.auth_ctl);
}
static void sl_print_sampling(struct seq_file *m)
{
struct hws_qsi_info_block si;
memset(&si, 0, sizeof(si));
if (qsi(&si))
return;
if (!si.as && !si.ad)
return;
seq_printf(m, "CPU-MF: Sampling facility: min_rate=%lu max_rate=%lu"
" cpu_speed=%u\n", si.min_sampl_rate, si.max_sampl_rate,
si.cpu_speed);
if (si.as)
seq_printf(m, "CPU-MF: Sampling facility: mode=basic"
" sample_size=%u\n", si.bsdes);
if (si.ad)
seq_printf(m, "CPU-MF: Sampling facility: mode=diagnostic"
" sample_size=%u\n", si.dsdes);
}
static void service_level_perf_print(struct seq_file *m,
struct service_level *sl)
{
if (cpum_cf_avail())
sl_print_counter(m);
if (cpum_sf_avail())
sl_print_sampling(m);
}
static struct service_level service_level_perf = {
.seq_print = service_level_perf_print,
};
static int __init service_level_perf_register(void)
{
return register_service_level(&service_level_perf);
}
arch_initcall(service_level_perf_register);
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
struct unwind_state state;
unsigned long addr;
unwind_for_each_frame(&state, current, regs, 0) {
addr = unwind_get_return_address(&state);
if (!addr || perf_callchain_store(entry, addr))
return;
}
}
void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
arch_stack_walk_user_common(NULL, NULL, entry, regs, true);
}
/* Perf definitions for PMU event attributes in sysfs */
ssize_t cpumf_events_sysfs_show(struct device *dev,
struct device_attribute *attr, char *page)
{
struct perf_pmu_events_attr *pmu_attr;
pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
return sysfs_emit(page, "event=0x%04llx\n", pmu_attr->id);
}