From 0e18dd12064e07519f7cbff4149ca7fff620cbed Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Wed, 15 Nov 2017 08:47:02 +0300 Subject: perf/core: Fix memory leak triggered by perf --namespace perf with --namespace key leaks various memory objects including namespaces 4.14.0+ pid_namespace 1 12 2568 12 8 user_namespace 1 39 824 39 8 net_namespace 1 5 6272 5 8 This happen because perf_fill_ns_link_info() struct patch ns_path: during initialization ns_path incremented counters on related mnt and dentry, but without lost path_put nobody decremented them back. Leaked dentry is name of related namespace, and its leak does not allow to free unused namespace. Signed-off-by: Vasily Averin Acked-by: Peter Zijlstra Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Hari Bathini Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Thomas Gleixner Fixes: commit e422267322cd ("perf: Add PERF_RECORD_NAMESPACES to include namespaces related info") Link: http://lkml.kernel.org/r/c510711b-3904-e5e1-d296-61273d21118d@virtuozzo.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 10cdb9c26b5d..ab5ac84f82e2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6756,6 +6756,7 @@ static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info, ns_inode = ns_path.dentry->d_inode; ns_link_info->dev = new_encode_dev(ns_inode->i_sb->s_dev); ns_link_info->ino = ns_inode->i_ino; + path_put(&ns_path); } } -- cgit v1.2.3 From 46febd37f9c758b05cd25feae8512f22584742fe Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 28 Nov 2017 21:19:53 +0800 Subject: smp/hotplug: Move step CPUHP_AP_SMPCFD_DYING to the correct place Commit 31487f8328f2 ("smp/cfd: Convert core to hotplug state machine") accidently put this step on the wrong place. The step should be at the cpuhp_ap_states[] rather than the cpuhp_bp_states[]. grep smpcfd /sys/devices/system/cpu/hotplug/states 40: smpcfd:prepare 129: smpcfd:dying "smpcfd:dying" was missing before. So was the invocation of the function smpcfd_dying_cpu(). Fixes: 31487f8328f2 ("smp/cfd: Convert core to hotplug state machine") Signed-off-by: Lai Jiangshan Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Richard Weinberger Cc: Sebastian Andrzej Siewior Cc: stable@vger.kernel.org Cc: Boris Ostrovsky Link: https://lkml.kernel.org/r/20171128131954.81229-1-jiangshanlai@gmail.com --- kernel/cpu.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/cpu.c b/kernel/cpu.c index 04892a82f6ac..7891aecc6aec 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1289,11 +1289,6 @@ static struct cpuhp_step cpuhp_bp_states[] = { .teardown.single = NULL, .cant_stop = true, }, - [CPUHP_AP_SMPCFD_DYING] = { - .name = "smpcfd:dying", - .startup.single = NULL, - .teardown.single = smpcfd_dying_cpu, - }, /* * Handled on controll processor until the plugged processor manages * this itself. @@ -1335,6 +1330,11 @@ static struct cpuhp_step cpuhp_ap_states[] = { .startup.single = NULL, .teardown.single = rcutree_dying_cpu, }, + [CPUHP_AP_SMPCFD_DYING] = { + .name = "smpcfd:dying", + .startup.single = NULL, + .teardown.single = smpcfd_dying_cpu, + }, /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { -- cgit v1.2.3 From 34900ec5c9577cc1b0f22887ac7349f458ba8ac2 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 9 Aug 2017 18:14:06 +0200 Subject: perf: Fix header.size for namespace events Reset header size for namespace events, otherwise it only gets bigger in ctx iterations. Signed-off-by: Jiri Olsa Acked-by: Peter Zijlstra (Intel) Fixes: e422267322cd ("perf: Add PERF_RECORD_NAMESPACES to include namespaces related info") Link: http://lkml.kernel.org/n/tip-nlo4gonz9d4guyb8153ukzt0@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- kernel/events/core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 4c39c05e029a..799bb352d99f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6640,6 +6640,7 @@ static void perf_event_namespaces_output(struct perf_event *event, struct perf_namespaces_event *namespaces_event = data; struct perf_output_handle handle; struct perf_sample_data sample; + u16 header_size = namespaces_event->event_id.header.size; int ret; if (!perf_event_namespaces_match(event)) @@ -6650,7 +6651,7 @@ static void perf_event_namespaces_output(struct perf_event *event, ret = perf_output_begin(&handle, event, namespaces_event->event_id.header.size); if (ret) - return; + goto out; namespaces_event->event_id.pid = perf_event_pid(event, namespaces_event->task); @@ -6662,6 +6663,8 @@ static void perf_event_namespaces_output(struct perf_event *event, perf_event__output_id_sample(event, &handle, &sample); perf_output_end(&handle); +out: + namespaces_event->event_id.header.size = header_size; } static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info, -- cgit v1.2.3 From bb5c43428252f27b875c764451321a83a531d6e5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 28 Nov 2017 15:40:33 +0100 Subject: genirq/matrix: Fix the precedence fix for real The previous commit which made the operator precedence in irq_matrix_available() explicit made the implicit brokenness explicitely wrong. It was wrong in the original commit already. The overworked maintainer did not notice it either when merging the patch. Replace the confusing '?' construct by a simple and obvious if (). Fixes: 75f1133873d6 ("genirq/matrix: Make - vs ?: Precedence explicit") Reported-by: Rasmus Villemoes Signed-off-by: Thomas Gleixner Cc: Kees Cook --- kernel/irq/matrix.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index 7df2480005f8..0ba0dd8863a7 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -384,7 +384,9 @@ unsigned int irq_matrix_available(struct irq_matrix *m, bool cpudown) { struct cpumap *cm = this_cpu_ptr(m->maps); - return (m->global_available - cpudown) ? cm->available : 0; + if (!cpudown) + return m->global_available; + return m->global_available - cm->available; } /** -- cgit v1.2.3 From c895f6f703ad7dd2f99e751d9884b0aa5d0eea25 Mon Sep 17 00:00:00 2001 From: Hendrik Brueckner Date: Mon, 4 Dec 2017 10:56:44 +0100 Subject: bpf: correct broken uapi for BPF_PROG_TYPE_PERF_EVENT program type Commit 0515e5999a466dfe ("bpf: introduce BPF_PROG_TYPE_PERF_EVENT program type") introduced the bpf_perf_event_data structure which exports the pt_regs structure. This is OK for multiple architectures but fail for s390 and arm64 which do not export pt_regs. Programs using them, for example, the bpf selftest fail to compile on these architectures. For s390, exporting the pt_regs is not an option because s390 wants to allow changes to it. For arm64, there is a user_pt_regs structure that covers parts of the pt_regs structure for use by user space. To solve the broken uapi for s390 and arm64, introduce an abstract type for pt_regs and add an asm/bpf_perf_event.h file that concretes the type. An asm-generic header file covers the architectures that export pt_regs today. The arch-specific enablement for s390 and arm64 follows in separate commits. Reported-by: Thomas Richter Fixes: 0515e5999a466dfe ("bpf: introduce BPF_PROG_TYPE_PERF_EVENT program type") Signed-off-by: Hendrik Brueckner Reviewed-and-tested-by: Thomas Richter Acked-by: Alexei Starovoitov Cc: Arnaldo Carvalho de Melo Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Arnd Bergmann Cc: Daniel Borkmann Signed-off-by: Daniel Borkmann --- arch/alpha/include/uapi/asm/Kbuild | 2 ++ arch/arc/include/uapi/asm/Kbuild | 1 + arch/arm/include/uapi/asm/Kbuild | 1 + arch/blackfin/include/uapi/asm/Kbuild | 1 + arch/c6x/include/uapi/asm/Kbuild | 1 + arch/cris/include/uapi/asm/Kbuild | 1 + arch/frv/include/uapi/asm/Kbuild | 2 ++ arch/h8300/include/uapi/asm/Kbuild | 1 + arch/hexagon/include/uapi/asm/Kbuild | 1 + arch/ia64/include/uapi/asm/Kbuild | 1 + arch/m32r/include/uapi/asm/Kbuild | 1 + arch/m68k/include/uapi/asm/Kbuild | 1 + arch/metag/include/uapi/asm/Kbuild | 1 + arch/microblaze/include/uapi/asm/Kbuild | 1 + arch/mips/include/uapi/asm/Kbuild | 1 + arch/mn10300/include/uapi/asm/Kbuild | 1 + arch/nios2/include/uapi/asm/Kbuild | 1 + arch/openrisc/include/uapi/asm/Kbuild | 1 + arch/parisc/include/uapi/asm/Kbuild | 1 + arch/powerpc/include/uapi/asm/Kbuild | 1 + arch/riscv/include/uapi/asm/Kbuild | 1 + arch/score/include/uapi/asm/Kbuild | 1 + arch/sh/include/uapi/asm/Kbuild | 1 + arch/sparc/include/uapi/asm/Kbuild | 1 + arch/tile/include/uapi/asm/Kbuild | 1 + arch/unicore32/include/uapi/asm/Kbuild | 1 + arch/x86/include/uapi/asm/Kbuild | 1 + arch/xtensa/include/uapi/asm/Kbuild | 1 + include/linux/perf_event.h | 6 +++++- include/uapi/asm-generic/bpf_perf_event.h | 9 +++++++++ include/uapi/linux/bpf_perf_event.h | 5 ++--- kernel/events/core.c | 2 +- 32 files changed, 47 insertions(+), 5 deletions(-) create mode 100644 include/uapi/asm-generic/bpf_perf_event.h (limited to 'kernel') diff --git a/arch/alpha/include/uapi/asm/Kbuild b/arch/alpha/include/uapi/asm/Kbuild index b15bf6bc0e94..14a2e9af97e9 100644 --- a/arch/alpha/include/uapi/asm/Kbuild +++ b/arch/alpha/include/uapi/asm/Kbuild @@ -1,2 +1,4 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm + +generic-y += bpf_perf_event.h diff --git a/arch/arc/include/uapi/asm/Kbuild b/arch/arc/include/uapi/asm/Kbuild index fa6d0ff4ff89..170b5db64afe 100644 --- a/arch/arc/include/uapi/asm/Kbuild +++ b/arch/arc/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/arm/include/uapi/asm/Kbuild b/arch/arm/include/uapi/asm/Kbuild index 4d53de308ee0..4d1cc1847edf 100644 --- a/arch/arm/include/uapi/asm/Kbuild +++ b/arch/arm/include/uapi/asm/Kbuild @@ -7,6 +7,7 @@ generated-y += unistd-oabi.h generated-y += unistd-eabi.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += ioctl.h generic-y += ipcbuf.h diff --git a/arch/blackfin/include/uapi/asm/Kbuild b/arch/blackfin/include/uapi/asm/Kbuild index aa624b4ab655..2240b38c2915 100644 --- a/arch/blackfin/include/uapi/asm/Kbuild +++ b/arch/blackfin/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += ioctl.h generic-y += ipcbuf.h diff --git a/arch/c6x/include/uapi/asm/Kbuild b/arch/c6x/include/uapi/asm/Kbuild index 67ee896a76a7..26644e15d854 100644 --- a/arch/c6x/include/uapi/asm/Kbuild +++ b/arch/c6x/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/cris/include/uapi/asm/Kbuild b/arch/cris/include/uapi/asm/Kbuild index 3687b54bb18e..3470c6e9c7b9 100644 --- a/arch/cris/include/uapi/asm/Kbuild +++ b/arch/cris/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/frv/include/uapi/asm/Kbuild b/arch/frv/include/uapi/asm/Kbuild index b15bf6bc0e94..14a2e9af97e9 100644 --- a/arch/frv/include/uapi/asm/Kbuild +++ b/arch/frv/include/uapi/asm/Kbuild @@ -1,2 +1,4 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm + +generic-y += bpf_perf_event.h diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild index 187aed820e71..2f65f78792cb 100644 --- a/arch/h8300/include/uapi/asm/Kbuild +++ b/arch/h8300/include/uapi/asm/Kbuild @@ -2,6 +2,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/hexagon/include/uapi/asm/Kbuild b/arch/hexagon/include/uapi/asm/Kbuild index cb5df3aad3a8..41a176dbb53e 100644 --- a/arch/hexagon/include/uapi/asm/Kbuild +++ b/arch/hexagon/include/uapi/asm/Kbuild @@ -2,6 +2,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/ia64/include/uapi/asm/Kbuild b/arch/ia64/include/uapi/asm/Kbuild index 13a97aa2285f..f5c6967a93bb 100644 --- a/arch/ia64/include/uapi/asm/Kbuild +++ b/arch/ia64/include/uapi/asm/Kbuild @@ -1,4 +1,5 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += kvm_para.h diff --git a/arch/m32r/include/uapi/asm/Kbuild b/arch/m32r/include/uapi/asm/Kbuild index 1c44d3b3eba0..451bf6071c6e 100644 --- a/arch/m32r/include/uapi/asm/Kbuild +++ b/arch/m32r/include/uapi/asm/Kbuild @@ -1,5 +1,6 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += kvm_para.h generic-y += siginfo.h diff --git a/arch/m68k/include/uapi/asm/Kbuild b/arch/m68k/include/uapi/asm/Kbuild index 3717b64a620d..c2e26a44c482 100644 --- a/arch/m68k/include/uapi/asm/Kbuild +++ b/arch/m68k/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += ioctl.h generic-y += ipcbuf.h diff --git a/arch/metag/include/uapi/asm/Kbuild b/arch/metag/include/uapi/asm/Kbuild index 6ac763d9a3e3..f9eaf07d29f8 100644 --- a/arch/metag/include/uapi/asm/Kbuild +++ b/arch/metag/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild index 06609ca36115..2c6a6bffea32 100644 --- a/arch/microblaze/include/uapi/asm/Kbuild +++ b/arch/microblaze/include/uapi/asm/Kbuild @@ -2,6 +2,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/mips/include/uapi/asm/Kbuild b/arch/mips/include/uapi/asm/Kbuild index a0266feba9e6..7a4becd8963a 100644 --- a/arch/mips/include/uapi/asm/Kbuild +++ b/arch/mips/include/uapi/asm/Kbuild @@ -1,4 +1,5 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += ipcbuf.h diff --git a/arch/mn10300/include/uapi/asm/Kbuild b/arch/mn10300/include/uapi/asm/Kbuild index c94ee54210bc..81271d3af47c 100644 --- a/arch/mn10300/include/uapi/asm/Kbuild +++ b/arch/mn10300/include/uapi/asm/Kbuild @@ -1,4 +1,5 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += siginfo.h diff --git a/arch/nios2/include/uapi/asm/Kbuild b/arch/nios2/include/uapi/asm/Kbuild index ffca24da7647..13a3d77b4d7b 100644 --- a/arch/nios2/include/uapi/asm/Kbuild +++ b/arch/nios2/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/openrisc/include/uapi/asm/Kbuild b/arch/openrisc/include/uapi/asm/Kbuild index 62286dbeb904..130c16ccba0a 100644 --- a/arch/openrisc/include/uapi/asm/Kbuild +++ b/arch/openrisc/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/parisc/include/uapi/asm/Kbuild b/arch/parisc/include/uapi/asm/Kbuild index 196d2a4efb31..286ef5a5904b 100644 --- a/arch/parisc/include/uapi/asm/Kbuild +++ b/arch/parisc/include/uapi/asm/Kbuild @@ -2,6 +2,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h +generic-y += bpf_perf_event.h generic-y += kvm_para.h generic-y += param.h generic-y += poll.h diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild index 0d960ef78a9a..1a6ed5919ffd 100644 --- a/arch/powerpc/include/uapi/asm/Kbuild +++ b/arch/powerpc/include/uapi/asm/Kbuild @@ -1,6 +1,7 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += param.h generic-y += poll.h generic-y += resource.h diff --git a/arch/riscv/include/uapi/asm/Kbuild b/arch/riscv/include/uapi/asm/Kbuild index 5ded96b06352..7e91f4850475 100644 --- a/arch/riscv/include/uapi/asm/Kbuild +++ b/arch/riscv/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += setup.h generic-y += unistd.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/score/include/uapi/asm/Kbuild b/arch/score/include/uapi/asm/Kbuild index c94ee54210bc..81271d3af47c 100644 --- a/arch/score/include/uapi/asm/Kbuild +++ b/arch/score/include/uapi/asm/Kbuild @@ -1,4 +1,5 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += siginfo.h diff --git a/arch/sh/include/uapi/asm/Kbuild b/arch/sh/include/uapi/asm/Kbuild index e28531333efa..ba4d39cb321d 100644 --- a/arch/sh/include/uapi/asm/Kbuild +++ b/arch/sh/include/uapi/asm/Kbuild @@ -2,6 +2,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/sparc/include/uapi/asm/Kbuild b/arch/sparc/include/uapi/asm/Kbuild index 2178c78c7c1a..4680ba246b55 100644 --- a/arch/sparc/include/uapi/asm/Kbuild +++ b/arch/sparc/include/uapi/asm/Kbuild @@ -1,4 +1,5 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += types.h diff --git a/arch/tile/include/uapi/asm/Kbuild b/arch/tile/include/uapi/asm/Kbuild index 5711de0a1b5e..cc439612bcd5 100644 --- a/arch/tile/include/uapi/asm/Kbuild +++ b/arch/tile/include/uapi/asm/Kbuild @@ -1,6 +1,7 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild index 759a71411169..8611ef980554 100644 --- a/arch/unicore32/include/uapi/asm/Kbuild +++ b/arch/unicore32/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild index da1489cb64dc..1e901e421f2d 100644 --- a/arch/x86/include/uapi/asm/Kbuild +++ b/arch/x86/include/uapi/asm/Kbuild @@ -1,6 +1,7 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bpf_perf_event.h generated-y += unistd_32.h generated-y += unistd_64.h generated-y += unistd_x32.h diff --git a/arch/xtensa/include/uapi/asm/Kbuild b/arch/xtensa/include/uapi/asm/Kbuild index a5bcdfb890f1..837d4dd76785 100644 --- a/arch/xtensa/include/uapi/asm/Kbuild +++ b/arch/xtensa/include/uapi/asm/Kbuild @@ -2,6 +2,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += bitsperlong.h +generic-y += bpf_perf_event.h generic-y += errno.h generic-y += fcntl.h generic-y += ioctl.h diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2c9c87d8a0c1..7546822a1d74 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -15,6 +15,7 @@ #define _LINUX_PERF_EVENT_H #include +#include /* * Kernel-internal data types and definitions: @@ -787,7 +788,7 @@ struct perf_output_handle { }; struct bpf_perf_event_data_kern { - struct pt_regs *regs; + bpf_user_pt_regs_t *regs; struct perf_sample_data *data; struct perf_event *event; }; @@ -1177,6 +1178,9 @@ extern void perf_bp_event(struct perf_event *event, void *data); (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) # define perf_instruction_pointer(regs) instruction_pointer(regs) #endif +#ifndef perf_arch_bpf_user_pt_regs +# define perf_arch_bpf_user_pt_regs(regs) regs +#endif static inline bool has_branch_stack(struct perf_event *event) { diff --git a/include/uapi/asm-generic/bpf_perf_event.h b/include/uapi/asm-generic/bpf_perf_event.h new file mode 100644 index 000000000000..53815d2cd047 --- /dev/null +++ b/include/uapi/asm-generic/bpf_perf_event.h @@ -0,0 +1,9 @@ +#ifndef _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ +#define _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ + +#include + +/* Export kernel pt_regs structure */ +typedef struct pt_regs bpf_user_pt_regs_t; + +#endif /* _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ */ diff --git a/include/uapi/linux/bpf_perf_event.h b/include/uapi/linux/bpf_perf_event.h index af549d4ecf1b..8f95303f9d80 100644 --- a/include/uapi/linux/bpf_perf_event.h +++ b/include/uapi/linux/bpf_perf_event.h @@ -8,11 +8,10 @@ #ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__ #define _UAPI__LINUX_BPF_PERF_EVENT_H__ -#include -#include +#include struct bpf_perf_event_data { - struct pt_regs regs; + bpf_user_pt_regs_t regs; __u64 sample_period; }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 16beab4767e1..ba957b9812b3 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7987,11 +7987,11 @@ static void bpf_overflow_handler(struct perf_event *event, { struct bpf_perf_event_data_kern ctx = { .data = data, - .regs = regs, .event = event, }; int ret = 0; + ctx.regs = perf_arch_bpf_user_pt_regs(regs); preempt_disable(); if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) goto out; -- cgit v1.2.3 From b7ad7ef742a99c148631d38a98da72e7db8f6fd0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 5 Dec 2017 08:23:20 -0800 Subject: remove task and stack pointer printout from oops dump Geert Uytterhoeven reported a NFS oops, and pointed out that some of the numbers were hashed and useless. We could just turn them from '%p' into '%px', but those numbers are really just legacy, and useless even when not hashed. So just remove them entirely. Reported-by: Geert Uytterhoeven Signed-off-by: Linus Torvalds --- kernel/printk/printk.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 5d81206a572d..b9006617710f 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3141,9 +3141,6 @@ void dump_stack_print_info(const char *log_lvl) void show_regs_print_info(const char *log_lvl) { dump_stack_print_info(log_lvl); - - printk("%stask: %p task.stack: %p\n", - log_lvl, current, task_stack_page(current)); } #endif -- cgit v1.2.3 From 5b1ead6800cb2241aeadcba32736c5836e59c7e1 Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Wed, 6 Dec 2017 10:59:11 +0000 Subject: cpu/hotplug: Fix state name in takedown_cpu() comment CPUHP_AP_SCHED_MIGRATE_DYING doesn't exist, it looks like this was supposed to refer to CPUHP_AP_SCHED_STARTING's teardown callback, i.e. sched_cpu_dying(). Signed-off-by: Brendan Jackman Cc: Boris Ostrovsky Cc: Dietmar Eggemann Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Quentin Perret Cc: Sebastian Andrzej Siewior Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20171206105911.28093-1-brendan.jackman@arm.com Signed-off-by: Ingo Molnar --- kernel/cpu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cpu.c b/kernel/cpu.c index 04892a82f6ac..2a885c5f2429 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -780,8 +780,8 @@ static int takedown_cpu(unsigned int cpu) BUG_ON(cpu_online(cpu)); /* - * The CPUHP_AP_SCHED_MIGRATE_DYING callback will have removed all - * runnable tasks from the cpu, there's only the idle task left now + * The teardown callback for CPUHP_AP_SCHED_STARTING will have removed + * all runnable tasks from the CPU, there's only the idle task left now * that the migration thread is done doing the stop_machine thing. * * Wait for the stop thread to go away. -- cgit v1.2.3 From 5e351ad106997e06b2dc3da9c6b939b95f67fb88 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 6 Dec 2017 17:32:47 +0100 Subject: locking/lockdep: Fix possible NULL deref We can't invalidate xhlocks when we've not yet allocated any. Reported-by: Dmitry Vyukov Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Fixes: f52be5708076 ("locking/lockdep: Untangle xhlock history save/restore from task independence") Signed-off-by: Ingo Molnar --- kernel/locking/lockdep.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 9776da8db180..670d8d7d8087 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -4790,7 +4790,8 @@ void lockdep_invariant_state(bool force) * Verify the former, enforce the latter. */ WARN_ON_ONCE(!force && current->lockdep_depth); - invalidate_xhlock(&xhlock(current->xhlock_idx)); + if (current->xhlocks) + invalidate_xhlock(&xhlock(current->xhlock_idx)); } static int cross_lock(struct lockdep_map *lock) -- cgit v1.2.3 From c6b9d9a33029014446bd9ed84c1688f6d3d4eab9 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Tue, 5 Dec 2017 23:15:31 -0800 Subject: sched/wait: Fix add_wait_queue() behavioral change The following cleanup commit: 50816c48997a ("sched/wait: Standardize internal naming of wait-queue entries") ... unintentionally changed the behavior of add_wait_queue() from inserting the wait entry at the head of the wait queue to the tail of the wait queue. Beyond a negative performance impact this change in behavior theoretically also breaks wait queues which mix exclusive and non-exclusive waiters, as non-exclusive waiters will not be woken up if they are queued behind enough exclusive waiters. Signed-off-by: Omar Sandoval Reviewed-by: Jens Axboe Acked-by: Peter Zijlstra Cc: Linus Torvalds Cc: Thomas Gleixner Cc: kernel-team@fb.com Fixes: ("sched/wait: Standardize internal naming of wait-queue entries") Link: http://lkml.kernel.org/r/a16c8ccffd39bd08fdaa45a5192294c784b803a7.1512544324.git.osandov@fb.com Signed-off-by: Ingo Molnar --- kernel/sched/wait.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 98feab7933c7..929ecb7d6b78 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -27,7 +27,7 @@ void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE; spin_lock_irqsave(&wq_head->lock, flags); - __add_wait_queue_entry_tail(wq_head, wq_entry); + __add_wait_queue(wq_head, wq_entry); spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(add_wait_queue); -- cgit v1.2.3 From a4c3c04974d648ee6e1a09ef4131eb32a02ab494 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Thu, 16 Nov 2017 15:21:52 +0100 Subject: sched/fair: Update and fix the runnable propagation rule Unlike running, the runnable part can't be directly propagated through the hierarchy when we migrate a task. The main reason is that runnable time can be shared with other sched_entities that stay on the rq and this runnable time will also remain on prev cfs_rq and must not be removed. Instead, we can estimate what should be the new runnable of the prev cfs_rq and check that this estimation stay in a possible range. The prop_runnable_sum is a good estimation when adding runnable_sum but fails most often when we remove it. Instead, we could use the formula below instead: gcfs_rq's runnable_sum = gcfs_rq->avg.load_sum / gcfs_rq->load.weight which assumes that tasks are equally runnable which is not true but easy to compute. Beside these estimates, we have several simple rules that help us to filter out wrong ones: - ge->avg.runnable_sum <= than LOAD_AVG_MAX - ge->avg.runnable_sum >= ge->avg.running_sum (ge->avg.util_sum << LOAD_AVG_MAX) - ge->avg.runnable_sum can't increase when we detach a task The effect of these fixes is better cgroups balancing. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Cc: Ben Segall Cc: Chris Mason Cc: Dietmar Eggemann Cc: Josef Bacik Cc: Linus Torvalds Cc: Mike Galbraith Cc: Morten Rasmussen Cc: Paul Turner Cc: Peter Zijlstra Cc: Tejun Heo Cc: Thomas Gleixner Cc: Yuyang Du Link: http://lkml.kernel.org/r/1510842112-21028-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 102 +++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 73 insertions(+), 29 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 4037e19bbca2..2fe3aa853e4d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3413,9 +3413,9 @@ void set_task_rq_fair(struct sched_entity *se, * _IFF_ we look at the pure running and runnable sums. Because they * represent the very same entity, just at different points in the hierarchy. * - * - * Per the above update_tg_cfs_util() is trivial (and still 'wrong') and - * simply copies the running sum over. + * Per the above update_tg_cfs_util() is trivial and simply copies the running + * sum over (but still wrong, because the group entity and group rq do not have + * their PELT windows aligned). * * However, update_tg_cfs_runnable() is more complex. So we have: * @@ -3424,11 +3424,11 @@ void set_task_rq_fair(struct sched_entity *se, * And since, like util, the runnable part should be directly transferable, * the following would _appear_ to be the straight forward approach: * - * grq->avg.load_avg = grq->load.weight * grq->avg.running_avg (3) + * grq->avg.load_avg = grq->load.weight * grq->avg.runnable_avg (3) * * And per (1) we have: * - * ge->avg.running_avg == grq->avg.running_avg + * ge->avg.runnable_avg == grq->avg.runnable_avg * * Which gives: * @@ -3447,27 +3447,28 @@ void set_task_rq_fair(struct sched_entity *se, * to (shortly) return to us. This only works by keeping the weights as * integral part of the sum. We therefore cannot decompose as per (3). * - * OK, so what then? + * Another reason this doesn't work is that runnable isn't a 0-sum entity. + * Imagine a rq with 2 tasks that each are runnable 2/3 of the time. Then the + * rq itself is runnable anywhere between 2/3 and 1 depending on how the + * runnable section of these tasks overlap (or not). If they were to perfectly + * align the rq as a whole would be runnable 2/3 of the time. If however we + * always have at least 1 runnable task, the rq as a whole is always runnable. * + * So we'll have to approximate.. :/ * - * Another way to look at things is: + * Given the constraint: * - * grq->avg.load_avg = \Sum se->avg.load_avg + * ge->avg.running_sum <= ge->avg.runnable_sum <= LOAD_AVG_MAX * - * Therefore, per (2): + * We can construct a rule that adds runnable to a rq by assuming minimal + * overlap. * - * grq->avg.load_avg = \Sum se->load.weight * se->avg.runnable_avg + * On removal, we'll assume each task is equally runnable; which yields: * - * And the very thing we're propagating is a change in that sum (someone - * joined/left). So we can easily know the runnable change, which would be, per - * (2) the already tracked se->load_avg divided by the corresponding - * se->weight. + * grq->avg.runnable_sum = grq->avg.load_sum / grq->load.weight * - * Basically (4) but in differential form: + * XXX: only do this for the part of runnable > running ? * - * d(runnable_avg) += se->avg.load_avg / se->load.weight - * (5) - * ge->avg.load_avg += ge->load.weight * d(runnable_avg) */ static inline void @@ -3479,6 +3480,14 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq if (!delta) return; + /* + * The relation between sum and avg is: + * + * LOAD_AVG_MAX - 1024 + sa->period_contrib + * + * however, the PELT windows are not aligned between grq and gse. + */ + /* Set new sched_entity's utilization */ se->avg.util_avg = gcfs_rq->avg.util_avg; se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX; @@ -3491,33 +3500,68 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq static inline void update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long runnable_sum = gcfs_rq->prop_runnable_sum; - long runnable_load_avg, load_avg; - s64 runnable_load_sum, load_sum; + long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum; + unsigned long runnable_load_avg, load_avg; + u64 runnable_load_sum, load_sum = 0; + s64 delta_sum; if (!runnable_sum) return; gcfs_rq->prop_runnable_sum = 0; + if (runnable_sum >= 0) { + /* + * Add runnable; clip at LOAD_AVG_MAX. Reflects that until + * the CPU is saturated running == runnable. + */ + runnable_sum += se->avg.load_sum; + runnable_sum = min(runnable_sum, (long)LOAD_AVG_MAX); + } else { + /* + * Estimate the new unweighted runnable_sum of the gcfs_rq by + * assuming all tasks are equally runnable. + */ + if (scale_load_down(gcfs_rq->load.weight)) { + load_sum = div_s64(gcfs_rq->avg.load_sum, + scale_load_down(gcfs_rq->load.weight)); + } + + /* But make sure to not inflate se's runnable */ + runnable_sum = min(se->avg.load_sum, load_sum); + } + + /* + * runnable_sum can't be lower than running_sum + * As running sum is scale with cpu capacity wehreas the runnable sum + * is not we rescale running_sum 1st + */ + running_sum = se->avg.util_sum / + arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq))); + runnable_sum = max(runnable_sum, running_sum); + load_sum = (s64)se_weight(se) * runnable_sum; load_avg = div_s64(load_sum, LOAD_AVG_MAX); - add_positive(&se->avg.load_sum, runnable_sum); - add_positive(&se->avg.load_avg, load_avg); + delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum; + delta_avg = load_avg - se->avg.load_avg; - add_positive(&cfs_rq->avg.load_avg, load_avg); - add_positive(&cfs_rq->avg.load_sum, load_sum); + se->avg.load_sum = runnable_sum; + se->avg.load_avg = load_avg; + add_positive(&cfs_rq->avg.load_avg, delta_avg); + add_positive(&cfs_rq->avg.load_sum, delta_sum); runnable_load_sum = (s64)se_runnable(se) * runnable_sum; runnable_load_avg = div_s64(runnable_load_sum, LOAD_AVG_MAX); + delta_sum = runnable_load_sum - se_weight(se) * se->avg.runnable_load_sum; + delta_avg = runnable_load_avg - se->avg.runnable_load_avg; - add_positive(&se->avg.runnable_load_sum, runnable_sum); - add_positive(&se->avg.runnable_load_avg, runnable_load_avg); + se->avg.runnable_load_sum = runnable_sum; + se->avg.runnable_load_avg = runnable_load_avg; if (se->on_rq) { - add_positive(&cfs_rq->avg.runnable_load_avg, runnable_load_avg); - add_positive(&cfs_rq->avg.runnable_load_sum, runnable_load_sum); + add_positive(&cfs_rq->avg.runnable_load_avg, delta_avg); + add_positive(&cfs_rq->avg.runnable_load_sum, delta_sum); } } -- cgit v1.2.3 From c07d35338081d107e57cf37572d8cc931a8e32e2 Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Mon, 2 Mar 2015 14:13:36 +0000 Subject: kdb: Fix handling of kallsyms_symbol_next() return value kallsyms_symbol_next() returns a boolean (true on success). Currently kdb_read() tests the return value with an inequality that unconditionally evaluates to true. This is fixed in the obvious way and, since the conditional branch is supposed to be unreachable, we also add a WARN_ON(). Reported-by: Dan Carpenter Signed-off-by: Daniel Thompson Cc: linux-stable Signed-off-by: Jason Wessel --- kernel/debug/kdb/kdb_io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index e74be38245ad..ed5d34925ad0 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -350,7 +350,7 @@ poll_again: } kdb_printf("\n"); for (i = 0; i < count; i++) { - if (kallsyms_symbol_next(p_tmp, i) < 0) + if (WARN_ON(!kallsyms_symbol_next(p_tmp, i))) break; kdb_printf("%s ", p_tmp); *(p_tmp + len) = '\0'; -- cgit v1.2.3