Commit 00198dab authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull perf fixes from Ingo Molnar:
 "On the kernel side there's two x86 PMU driver fixes and a uprobes fix,
  plus on the tooling side there's a number of fixes and some late
  updates"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  perf sched timehist: Fix invalid period calculation
  perf sched timehist: Remove hardcoded 'comm_width' check at print_summary
  perf sched timehist: Enlarge default 'comm_width'
  perf sched timehist: Honour 'comm_width' when aligning the headers
  perf/x86: Fix overlap counter scheduling bug
  perf/x86/pebs: Fix handling of PEBS buffer overflows
  samples/bpf: Move open_raw_sock to separate header
  samples/bpf: Remove perf_event_open() declaration
  samples/bpf: Be consistent with bpf_load_program bpf_insn parameter
  tools lib bpf: Add bpf_prog_{attach,detach}
  samples/bpf: Switch over to libbpf
  perf diff: Do not overwrite valid build id
  perf annotate: Don't throw error for zero length symbols
  perf bench futex: Fix lock-pi help string
  perf trace: Check if MAP_32BIT is defined (again)
  samples/bpf: Make perf_event_read() static
  uprobes: Fix uprobes on MIPS, allow for a cache flush after ixol breakpoint creation
  samples/bpf: Make samples more libbpf-centric
  tools lib bpf: Add flags to bpf_create_map()
  tools lib bpf: use __u32 from linux/types.h
  ...
parents 9004fda5 3705b975

arch/x86/events/intel/core.c

+21 −9
Original line number Diff line number Diff line
@@ -2110,6 +2110,27 @@ again: 
		    GLOBAL_STATUS_LBRS_FROZEN);

	if (!status)

		goto done;

	/*

	 * In case multiple PEBS events are sampled at the same time,

	 * it is possible to have GLOBAL_STATUS bit 62 set indicating

	 * PEBS buffer overflow and also seeing at most 3 PEBS counters

	 * having their bits set in the status register. This is a sign

	 * that there was at least one PEBS record pending at the time

	 * of the PMU interrupt. PEBS counters must only be processed

	 * via the drain_pebs() calls and not via the regular sample

	 * processing loop coming after that the function, otherwise

	 * phony regular samples may be generated in the sampling buffer

	 * not marked with the EXACT tag. Another possibility is to have

	 * one PEBS event and at least one non-PEBS event whic hoverflows

	 * while PEBS has armed. In this case, bit 62 of GLOBAL_STATUS will

	 * not be set, yet the overflow status bit for the PEBS counter will

	 * be on Skylake.

	 *

	 * To avoid this problem, we systematically ignore the PEBS-enabled

	 * counters from the GLOBAL_STATUS mask and we always process PEBS

	 * events via drain_pebs().

	 */

	status &= ~cpuc->pebs_enabled;



	/*

	 * PEBS overflow sets bit 62 in the global status register
@@ -2117,15 +2138,6 @@ again: 
	if (__test_and_clear_bit(62, (unsigned long *)&status)) {

		handled++;

		x86_pmu.drain_pebs(regs);

		/*

		 * There are cases where, even though, the PEBS ovfl bit is set

		 * in GLOBAL_OVF_STATUS, the PEBS events may also have their

		 * overflow bits set for their counters. We must clear them

		 * here because they have been processed as exact samples in

		 * the drain_pebs() routine. They must not be processed again

		 * in the for_each_bit_set() loop for regular samples below.

		 */

		status &= ~cpuc->pebs_enabled;

		status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;

	}

arch/x86/events/intel/uncore_snbep.c

+1 −1
Original line number Diff line number Diff line
@@ -669,7 +669,7 @@ static struct event_constraint snbep_uncore_cbox_constraints[] = { 
	UNCORE_EVENT_CONSTRAINT(0x1c, 0xc),

	UNCORE_EVENT_CONSTRAINT(0x1d, 0xc),

	UNCORE_EVENT_CONSTRAINT(0x1e, 0xc),

	EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff),

	UNCORE_EVENT_CONSTRAINT(0x1f, 0xe),

	UNCORE_EVENT_CONSTRAINT(0x21, 0x3),

	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),

	UNCORE_EVENT_CONSTRAINT(0x31, 0x3),

kernel/events/uprobes.c

+1 −1
Original line number Diff line number Diff line
@@ -1194,7 +1194,7 @@ static struct xol_area *__create_xol_area(unsigned long vaddr) 
	/* Reserve the 1st slot for get_trampoline_vaddr() */

	set_bit(0, area->bitmap);

	atomic_set(&area->slot_count, 1);

	copy_to_page(area->pages[0], 0, &insn, UPROBE_SWBP_INSN_SIZE);

	arch_uprobe_copy_ixol(area->pages[0], 0, &insn, UPROBE_SWBP_INSN_SIZE);



	if (!xol_add_vma(mm, area))

		return area;

samples/bpf/Makefile

+38 −32
Original line number Diff line number Diff line
@@ -35,40 +35,43 @@ hostprogs-y += tc_l2_redirect 
hostprogs-y += lwt_len_hist

hostprogs-y += xdp_tx_iptunnel



test_lru_dist-objs := test_lru_dist.o libbpf.o

sock_example-objs := sock_example.o libbpf.o

fds_example-objs := bpf_load.o libbpf.o fds_example.o

sockex1-objs := bpf_load.o libbpf.o sockex1_user.o

sockex2-objs := bpf_load.o libbpf.o sockex2_user.o

sockex3-objs := bpf_load.o libbpf.o sockex3_user.o

tracex1-objs := bpf_load.o libbpf.o tracex1_user.o

tracex2-objs := bpf_load.o libbpf.o tracex2_user.o

tracex3-objs := bpf_load.o libbpf.o tracex3_user.o

tracex4-objs := bpf_load.o libbpf.o tracex4_user.o

tracex5-objs := bpf_load.o libbpf.o tracex5_user.o

tracex6-objs := bpf_load.o libbpf.o tracex6_user.o

test_probe_write_user-objs := bpf_load.o libbpf.o test_probe_write_user_user.o

trace_output-objs := bpf_load.o libbpf.o trace_output_user.o

lathist-objs := bpf_load.o libbpf.o lathist_user.o

offwaketime-objs := bpf_load.o libbpf.o offwaketime_user.o

spintest-objs := bpf_load.o libbpf.o spintest_user.o

map_perf_test-objs := bpf_load.o libbpf.o map_perf_test_user.o

test_overhead-objs := bpf_load.o libbpf.o test_overhead_user.o

test_cgrp2_array_pin-objs := libbpf.o test_cgrp2_array_pin.o

test_cgrp2_attach-objs := libbpf.o test_cgrp2_attach.o

test_cgrp2_attach2-objs := libbpf.o test_cgrp2_attach2.o cgroup_helpers.o

test_cgrp2_sock-objs := libbpf.o test_cgrp2_sock.o

test_cgrp2_sock2-objs := bpf_load.o libbpf.o test_cgrp2_sock2.o

xdp1-objs := bpf_load.o libbpf.o xdp1_user.o

# Libbpf dependencies

LIBBPF := ../../tools/lib/bpf/bpf.o



test_lru_dist-objs := test_lru_dist.o $(LIBBPF)

sock_example-objs := sock_example.o $(LIBBPF)

fds_example-objs := bpf_load.o $(LIBBPF) fds_example.o

sockex1-objs := bpf_load.o $(LIBBPF) sockex1_user.o

sockex2-objs := bpf_load.o $(LIBBPF) sockex2_user.o

sockex3-objs := bpf_load.o $(LIBBPF) sockex3_user.o

tracex1-objs := bpf_load.o $(LIBBPF) tracex1_user.o

tracex2-objs := bpf_load.o $(LIBBPF) tracex2_user.o

tracex3-objs := bpf_load.o $(LIBBPF) tracex3_user.o

tracex4-objs := bpf_load.o $(LIBBPF) tracex4_user.o

tracex5-objs := bpf_load.o $(LIBBPF) tracex5_user.o

tracex6-objs := bpf_load.o $(LIBBPF) tracex6_user.o

test_probe_write_user-objs := bpf_load.o $(LIBBPF) test_probe_write_user_user.o

trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o

lathist-objs := bpf_load.o $(LIBBPF) lathist_user.o

offwaketime-objs := bpf_load.o $(LIBBPF) offwaketime_user.o

spintest-objs := bpf_load.o $(LIBBPF) spintest_user.o

map_perf_test-objs := bpf_load.o $(LIBBPF) map_perf_test_user.o

test_overhead-objs := bpf_load.o $(LIBBPF) test_overhead_user.o

test_cgrp2_array_pin-objs := $(LIBBPF) test_cgrp2_array_pin.o

test_cgrp2_attach-objs := $(LIBBPF) test_cgrp2_attach.o

test_cgrp2_attach2-objs := $(LIBBPF) test_cgrp2_attach2.o cgroup_helpers.o

test_cgrp2_sock-objs := $(LIBBPF) test_cgrp2_sock.o

test_cgrp2_sock2-objs := bpf_load.o $(LIBBPF) test_cgrp2_sock2.o

xdp1-objs := bpf_load.o $(LIBBPF) xdp1_user.o

# reuse xdp1 source intentionally

xdp2-objs := bpf_load.o libbpf.o xdp1_user.o

test_current_task_under_cgroup-objs := bpf_load.o libbpf.o cgroup_helpers.o \

xdp2-objs := bpf_load.o $(LIBBPF) xdp1_user.o

test_current_task_under_cgroup-objs := bpf_load.o $(LIBBPF) cgroup_helpers.o \

				       test_current_task_under_cgroup_user.o

trace_event-objs := bpf_load.o libbpf.o trace_event_user.o

sampleip-objs := bpf_load.o libbpf.o sampleip_user.o

tc_l2_redirect-objs := bpf_load.o libbpf.o tc_l2_redirect_user.o

lwt_len_hist-objs := bpf_load.o libbpf.o lwt_len_hist_user.o

xdp_tx_iptunnel-objs := bpf_load.o libbpf.o xdp_tx_iptunnel_user.o

trace_event-objs := bpf_load.o $(LIBBPF) trace_event_user.o

sampleip-objs := bpf_load.o $(LIBBPF) sampleip_user.o

tc_l2_redirect-objs := bpf_load.o $(LIBBPF) tc_l2_redirect_user.o

lwt_len_hist-objs := bpf_load.o $(LIBBPF) lwt_len_hist_user.o

xdp_tx_iptunnel-objs := bpf_load.o $(LIBBPF) xdp_tx_iptunnel_user.o



# Tell kbuild to always build the programs

always := $(hostprogs-y)
@@ -104,7 +107,10 @@ always += lwt_len_hist_kern.o 
always += xdp_tx_iptunnel_kern.o



HOSTCFLAGS += -I$(objtree)/usr/include

HOSTCFLAGS += -I$(srctree)/tools/lib/

HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/

HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include

HOSTCFLAGS += -I$(srctree)/tools/perf



HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable

HOSTLOADLIBES_fds_example += -lelf

samples/bpf/README.rst

+2 −2
Original line number Diff line number Diff line 
eBPF sample programs

====================



This directory contains a mini eBPF library, test stubs, verifier

test-suite and examples for using eBPF.

This directory contains a test stubs, verifier test-suite and examples

for using eBPF. The examples use libbpf from tools/lib/bpf.



Build dependencies

==================

CRA Git | Maintained and supported by SUSTech CRA and CCSE