summaryrefslogtreecommitdiff
path: root/tools/arch
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2019-10-22 01:15:45 +0200
committerIngo Molnar <mingo@kernel.org>2019-10-22 01:15:45 +0200
commit27a0a90d6301dd883a748538e4db692a5fb923e1 (patch)
tree326b7d0970cab693343c5a808fbecb7b878402e9 /tools/arch
parentaa7a7b72974a4612a85bb395a4b23b973ffc7d2b (diff)
parent27198a893ba074407e7a87e346252b3e6fab454f (diff)
Merge tag 'perf-core-for-mingo-5.5-20191021' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: perf trace: - Add syscall failure stats to -s/--summary and -S/--with-summary, works in combination with specifying just a set of syscalls, see below first with -s/--summary, then with -S/--with-summary just for the syscalls we saw failing with -s: # perf trace -s sleep 1 Summary of events: sleep (16218), 80 events, 93.0% syscall calls errors total min avg max stddev (msec) (msec) (msec) (msec) (%) ----------- ----- ------ -------- -------- -------- -------- ------ nanosleep 1 0 1000.091 1000.091 1000.091 1000.091 0.00% mmap 8 0 0.045 0.005 0.006 0.008 7.09% mprotect 4 0 0.028 0.005 0.007 0.009 11.38% openat 3 0 0.021 0.005 0.007 0.009 14.07% munmap 1 0 0.017 0.017 0.017 0.017 0.00% brk 4 0 0.010 0.001 0.002 0.004 23.15% read 4 0 0.009 0.002 0.002 0.003 8.13% close 5 0 0.008 0.001 0.002 0.002 10.83% fstat 3 0 0.006 0.002 0.002 0.002 6.97% access 1 1 0.006 0.006 0.006 0.006 0.00% lseek 3 0 0.005 0.001 0.002 0.002 7.37% arch_prctl 2 1 0.004 0.001 0.002 0.002 17.64% execve 1 0 0.000 0.000 0.000 0.000 0.00% # perf trace -e access,arch_prctl -S sleep 1 0.000 ( 0.006 ms): sleep/19503 arch_prctl(option: 0x3001, arg2: 0x7fff165996b0) = -1 EINVAL (Invalid argument) 0.024 ( 0.006 ms): sleep/19503 access(filename: 0x2177e510, mode: R) = -1 ENOENT (No such file or directory) 0.136 ( 0.002 ms): sleep/19503 arch_prctl(option: SET_FS, arg2: 0x7f9421737580) = 0 Summary of events: sleep (19503), 6 events, 50.0% syscall calls errors total min avg max stddev (msec) (msec) (msec) (msec) (%) ---------- ----- ------ ------ ------ ------ ------ ------ arch_prctl 2 1 0.008 0.002 0.004 0.006 57.22% access 1 1 0.006 0.006 0.006 0.006 0.00% # - Introduce --errno-summary, to drill down a bit more in the errno stats: # perf trace --errno-summary -e access,arch_prctl -S sleep 1 0.000 ( 0.006 ms): sleep/5587 arch_prctl(option: 0x3001, arg2: 0x7ffd6ba6aa00) = -1 EINVAL (Invalid argument) 0.028 ( 0.007 ms): sleep/5587 access(filename: 0xb83d9510, mode: R) = -1 ENOENT (No such file or directory) 0.172 ( 0.003 ms): sleep/5587 arch_prctl(option: SET_FS, arg2: 0x7f45b8392580) = 0 Summary of events: sleep (5587), 6 events, 50.0% syscall calls errors total min avg max stddev (msec) (msec) (msec) (msec) (%) ---------- ----- ------ ------ ------ ------ ------ ------ arch_prctl 2 1 0.009 0.003 0.005 0.006 38.90% EINVAL: 1 access 1 1 0.007 0.007 0.007 0.007 0.00% ENOENT: 1 # - Filter own pid to avoid a feedback look in 'perf trace record -a' - Add the glue for the auto generated x86 IRQ vector array. - Show error message when not finding a field used in a filter expression # perf trace --max-events=4 -e syscalls:sys_enter_write --filter="cnt>32767" Failed to set filter "(cnt>32767) && (common_pid != 19938 && common_pid != 8922)" on event syscalls:sys_enter_write with 22 (Invalid argument) # # perf trace --max-events=4 -e syscalls:sys_enter_write --filter="count>32767" 0.000 python3.5/17535 syscalls:sys_enter_write(fd: 3, buf: 0x564b0dc53600, count: 172086) 12.641 python3.5.post/17535 syscalls:sys_enter_write(fd: 3, buf: 0x564b0db63660, count: 75994) 27.738 python3.5.post/17535 syscalls:sys_enter_write(fd: 3, buf: 0x564b0db4b1e0, count: 41635) 136.070 python3.5.post/17535 syscalls:sys_enter_write(fd: 3, buf: 0x564b0dbab510, count: 62232) # - Add a generator for x86's IRQ vectors -> strings - Introduce stroul() (string -> number) methods for the strarray and strarrays classes, also strtoul_flags, allowing to go from both strings and or-ed strings to numbers, allowing things like: # perf trace -e syscalls:sys_enter_mmap --filter="flags==DENYWRITE|PRIVATE|FIXED" sleep 1 0.000 sleep/22588 syscalls:sys_enter_mmap(addr: 0x7f42d2aa5000, len: 1363968, prot: READ|EXEC, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x22000) 0.011 sleep/22588 syscalls:sys_enter_mmap(addr: 0x7f42d2bf2000, len: 311296, prot: READ, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x16f000) 0.015 sleep/22588 syscalls:sys_enter_mmap(addr: 0x7f42d2c3f000, len: 24576, prot: READ|WRITE, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x1bb000) # Allowing to narrow down from the complete set of mmap calls for that workload: # perf trace -e syscalls:sys_enter_mmap sleep 1 0.000 sleep/22695 syscalls:sys_enter_mmap(len: 134773, prot: READ, flags: PRIVATE, fd: 3) 0.041 sleep/22695 syscalls:sys_enter_mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS) 0.053 sleep/22695 syscalls:sys_enter_mmap(len: 1857472, prot: READ, flags: PRIVATE|DENYWRITE, fd: 3) 0.069 sleep/22695 syscalls:sys_enter_mmap(addr: 0x7fd23ffb6000, len: 1363968, prot: READ|EXEC, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x22000) 0.077 sleep/22695 syscalls:sys_enter_mmap(addr: 0x7fd240103000, len: 311296, prot: READ, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x16f000) 0.083 sleep/22695 syscalls:sys_enter_mmap(addr: 0x7fd240150000, len: 24576, prot: READ|WRITE, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x1bb000) 0.095 sleep/22695 syscalls:sys_enter_mmap(addr: 0x7fd240156000, len: 14272, prot: READ|WRITE, flags: PRIVATE|FIXED|ANONYMOUS) 0.339 sleep/22695 syscalls:sys_enter_mmap(len: 217750512, prot: READ, flags: PRIVATE, fd: 3) # Works with all targets, so, for system wide, looking at who calls mmap with flags set to just "PRIVATE": # perf trace --max-events=5 -e syscalls:sys_enter_mmap --filter="flags==PRIVATE" 0.000 pool/2242 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 14) 0.050 pool/2242 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 14) 0.062 pool/2242 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 14) 0.145 goa-identity-s/2240 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 18) 0.183 goa-identity-s/2240 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 18) # # perf trace --max-events=2 -e syscalls:sys_enter_lseek --filter="whence==SET && offset != 0" 0.000 Cache2 I/O/12047 syscalls:sys_enter_lseek(fd: 277, offset: 43, whence: SET) 1142.070 mozStorage #5/12302 syscalls:sys_enter_lseek(fd: 44</home/acme/.mozilla/firefox/ina67tev.default/cookies.sqlite-wal>, offset: 393536, whence: SET) # perf annotate: - Fix objdump --no-show-raw-insn flag to work with goth gcc and clang. - Streamline objdump execution, preserving the right error codes for better reporting to user. perf report: - Add warning when libunwind not compiled in. perf stat: Jin Yao: - Support --all-kernel/--all-user, to match options available in 'perf record', asking that all the events specified work just with kernel or user events. perf list: Jin Yao: - Hide deprecated events by default, allow showing them with --deprecated. libbperf: Jiri Olsa: - Allow to build with -ltcmalloc. - Finish mmap interface, getting more stuff from tools/perf while adding abstractions to avoid pulling too much stuff, to get libperf to grow as tools needs things like auxtrace, etc. perf scripting engines: Steven Rostedt (VMware): - Iterate on tep event arrays directly, fixing script generation with '-g python' when having multiple tracepoints in a perf.data file. core: - Allow to build with -ltcmalloc. perf test: Leo Yan: - Report failure for mmap events. - Avoid infinite loop for task exit case. - Remove needless headers for bp_account test. - Add dedicated checking helper is_supported(). - Disable bp_signal testing for arm64. Vendor events: arm64: John Garry: - Fix Hisi hip08 DDRC PMU eventname. - Add some missing events for Hisi hip08 DDRC, L3C and HHA PMUs. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'tools/arch')
-rw-r--r--tools/arch/x86/include/asm/irq_vectors.h146
1 files changed, 146 insertions, 0 deletions
diff --git a/tools/arch/x86/include/asm/irq_vectors.h b/tools/arch/x86/include/asm/irq_vectors.h
new file mode 100644
index 000000000000..889f8b1b5b7f
--- /dev/null
+++ b/tools/arch/x86/include/asm/irq_vectors.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_IRQ_VECTORS_H
+#define _ASM_X86_IRQ_VECTORS_H
+
+#include <linux/threads.h>
+/*
+ * Linux IRQ vector layout.
+ *
+ * There are 256 IDT entries (per CPU - each entry is 8 bytes) which can
+ * be defined by Linux. They are used as a jump table by the CPU when a
+ * given vector is triggered - by a CPU-external, CPU-internal or
+ * software-triggered event.
+ *
+ * Linux sets the kernel code address each entry jumps to early during
+ * bootup, and never changes them. This is the general layout of the
+ * IDT entries:
+ *
+ * Vectors 0 ... 31 : system traps and exceptions - hardcoded events
+ * Vectors 32 ... 127 : device interrupts
+ * Vector 128 : legacy int80 syscall interface
+ * Vectors 129 ... LOCAL_TIMER_VECTOR-1
+ * Vectors LOCAL_TIMER_VECTOR ... 255 : special interrupts
+ *
+ * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table.
+ *
+ * This file enumerates the exact layout of them:
+ */
+
+#define NMI_VECTOR 0x02
+#define MCE_VECTOR 0x12
+
+/*
+ * IDT vectors usable for external interrupt sources start at 0x20.
+ * (0x80 is the syscall vector, 0x30-0x3f are for ISA)
+ */
+#define FIRST_EXTERNAL_VECTOR 0x20
+
+/*
+ * Reserve the lowest usable vector (and hence lowest priority) 0x20 for
+ * triggering cleanup after irq migration. 0x21-0x2f will still be used
+ * for device interrupts.
+ */
+#define IRQ_MOVE_CLEANUP_VECTOR FIRST_EXTERNAL_VECTOR
+
+#define IA32_SYSCALL_VECTOR 0x80
+
+/*
+ * Vectors 0x30-0x3f are used for ISA interrupts.
+ * round up to the next 16-vector boundary
+ */
+#define ISA_IRQ_VECTOR(irq) (((FIRST_EXTERNAL_VECTOR + 16) & ~15) + irq)
+
+/*
+ * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
+ *
+ * some of the following vectors are 'rare', they are merged
+ * into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
+ * TLB, reschedule and local APIC vectors are performance-critical.
+ */
+
+#define SPURIOUS_APIC_VECTOR 0xff
+/*
+ * Sanity check
+ */
+#if ((SPURIOUS_APIC_VECTOR & 0x0F) != 0x0F)
+# error SPURIOUS_APIC_VECTOR definition error
+#endif
+
+#define ERROR_APIC_VECTOR 0xfe
+#define RESCHEDULE_VECTOR 0xfd
+#define CALL_FUNCTION_VECTOR 0xfc
+#define CALL_FUNCTION_SINGLE_VECTOR 0xfb
+#define THERMAL_APIC_VECTOR 0xfa
+#define THRESHOLD_APIC_VECTOR 0xf9
+#define REBOOT_VECTOR 0xf8
+
+/*
+ * Generic system vector for platform specific use
+ */
+#define X86_PLATFORM_IPI_VECTOR 0xf7
+
+/*
+ * IRQ work vector:
+ */
+#define IRQ_WORK_VECTOR 0xf6
+
+#define UV_BAU_MESSAGE 0xf5
+#define DEFERRED_ERROR_VECTOR 0xf4
+
+/* Vector on which hypervisor callbacks will be delivered */
+#define HYPERVISOR_CALLBACK_VECTOR 0xf3
+
+/* Vector for KVM to deliver posted interrupt IPI */
+#ifdef CONFIG_HAVE_KVM
+#define POSTED_INTR_VECTOR 0xf2
+#define POSTED_INTR_WAKEUP_VECTOR 0xf1
+#define POSTED_INTR_NESTED_VECTOR 0xf0
+#endif
+
+#define MANAGED_IRQ_SHUTDOWN_VECTOR 0xef
+
+#if IS_ENABLED(CONFIG_HYPERV)
+#define HYPERV_REENLIGHTENMENT_VECTOR 0xee
+#define HYPERV_STIMER0_VECTOR 0xed
+#endif
+
+#define LOCAL_TIMER_VECTOR 0xec
+
+#define NR_VECTORS 256
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#define FIRST_SYSTEM_VECTOR LOCAL_TIMER_VECTOR
+#else
+#define FIRST_SYSTEM_VECTOR NR_VECTORS
+#endif
+
+/*
+ * Size the maximum number of interrupts.
+ *
+ * If the irq_desc[] array has a sparse layout, we can size things
+ * generously - it scales up linearly with the maximum number of CPUs,
+ * and the maximum number of IO-APICs, whichever is higher.
+ *
+ * In other cases we size more conservatively, to not create too large
+ * static arrays.
+ */
+
+#define NR_IRQS_LEGACY 16
+
+#define CPU_VECTOR_LIMIT (64 * NR_CPUS)
+#define IO_APIC_VECTOR_LIMIT (32 * MAX_IO_APICS)
+
+#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_PCI_MSI)
+#define NR_IRQS \
+ (CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ? \
+ (NR_VECTORS + CPU_VECTOR_LIMIT) : \
+ (NR_VECTORS + IO_APIC_VECTOR_LIMIT))
+#elif defined(CONFIG_X86_IO_APIC)
+#define NR_IRQS (NR_VECTORS + IO_APIC_VECTOR_LIMIT)
+#elif defined(CONFIG_PCI_MSI)
+#define NR_IRQS (NR_VECTORS + CPU_VECTOR_LIMIT)
+#else
+#define NR_IRQS NR_IRQS_LEGACY
+#endif
+
+#endif /* _ASM_X86_IRQ_VECTORS_H */