Merge tag 'perf-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf event updates from Ingo Molnar:

 - Improve Intel uncore PMU support:

     - Parse uncore 'discovery tables' - a new hardware capability
       enumeration method introduced on the latest Intel platforms. This
       table is in a well-defined PCI namespace location and is read via
       MMIO. It is organized in an rbtree.

       These uncore tables will allow the discovery of standard counter
       blocks, but fancier counters still need to be enumerated
       explicitly.

     - Add Alder Lake support

     - Improve IIO stacks to PMON mapping support on Skylake servers

 - Add Intel Alder Lake PMU support - which requires the introduction of
   'hybrid' CPUs and PMUs. Alder Lake is a mix of Golden Cove ('big')
   and Gracemont ('small' - Atom derived) cores.

   The CPU-side feature set is entirely symmetrical - but on the PMU
   side there's core type dependent PMU functionality.

 - Reduce data loss with CPU level hardware tracing on Intel PT / AUX
   profiling, by fixing the AUX allocation watermark logic.

 - Improve ring buffer allocation on NUMA systems

 - Put 'struct perf_event' into their separate kmem_cache pool

 - Add support for synchronous signals for select perf events. The
   immediate motivation is to support low-overhead sampling-based race
   detection for user-space code. The feature consists of the following
   main changes:

     - Add thread-only event inheritance via
       perf_event_attr::inherit_thread, which limits inheritance of
       events to CLONE_THREAD.

     - Add the ability for events to not leak through exec(), via
       perf_event_attr::remove_on_exec.

     - Allow the generation of SIGTRAP via perf_event_attr::sigtrap,
       extend siginfo with an u64 ::si_perf, and add the breakpoint
       information to ::si_addr and ::si_perf if the event is
       PERF_TYPE_BREAKPOINT.

   The siginfo support is adequate for breakpoints right now - but the
   new field can be used to introduce support for other types of
   metadata passed over siginfo as well.

 - Misc fixes, cleanups and smaller updates.

* tag 'perf-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
  signal, perf: Add missing TRAP_PERF case in siginfo_layout()
  signal, perf: Fix siginfo_t by avoiding u64 on 32-bit architectures
  perf/x86: Allow for 8<num_fixed_counters<16
  perf/x86/rapl: Add support for Intel Alder Lake
  perf/x86/cstate: Add Alder Lake CPU support
  perf/x86/msr: Add Alder Lake CPU support
  perf/x86/intel/uncore: Add Alder Lake support
  perf: Extend PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE
  perf/x86/intel: Add Alder Lake Hybrid support
  perf/x86: Support filter_match callback
  perf/x86/intel: Add attr_update for Hybrid PMUs
  perf/x86: Add structures for the attributes of Hybrid PMUs
  perf/x86: Register hybrid PMUs
  perf/x86: Factor out x86_pmu_show_pmu_cap
  perf/x86: Remove temporary pmu assignment in event_init
  perf/x86/intel: Factor out intel_pmu_check_extra_regs
  perf/x86/intel: Factor out intel_pmu_check_event_constraints
  perf/x86/intel: Factor out intel_pmu_check_num_counters
  perf/x86: Hybrid PMU support for extra_regs
  perf/x86: Hybrid PMU support for event constraints
  ...

6 files changed, 84 insertions, 35 deletions

diff --git a/include/linux/compat.h b/include/linux/compat.h
index 6e65be753603..f0d2dd35d408 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -236,6 +236,8 @@ typedef struct compat_siginfo {
 					char _dummy_pkey[__COMPAT_ADDR_BND_PKEY_PAD];
 					u32 _pkey;
 				} _addr_pkey;
+				/* used when si_code=TRAP_PERF */
+				compat_ulong_t _perf;
 			};
 		} _sigfault;
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 3f7f89ea5e51..a763928a0e41 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -260,15 +260,16 @@ struct perf_event;
 /**
  * pmu::capabilities flags
  */
-#define PERF_PMU_CAP_NO_INTERRUPT		0x01
-#define PERF_PMU_CAP_NO_NMI			0x02
-#define PERF_PMU_CAP_AUX_NO_SG			0x04
-#define PERF_PMU_CAP_EXTENDED_REGS		0x08
-#define PERF_PMU_CAP_EXCLUSIVE			0x10
-#define PERF_PMU_CAP_ITRACE			0x20
-#define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x40
-#define PERF_PMU_CAP_NO_EXCLUDE			0x80
-#define PERF_PMU_CAP_AUX_OUTPUT			0x100
+#define PERF_PMU_CAP_NO_INTERRUPT		0x0001
+#define PERF_PMU_CAP_NO_NMI			0x0002
+#define PERF_PMU_CAP_AUX_NO_SG			0x0004
+#define PERF_PMU_CAP_EXTENDED_REGS		0x0008
+#define PERF_PMU_CAP_EXCLUSIVE			0x0010
+#define PERF_PMU_CAP_ITRACE			0x0020
+#define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x0040
+#define PERF_PMU_CAP_NO_EXCLUDE			0x0080
+#define PERF_PMU_CAP_AUX_OUTPUT			0x0100
+#define PERF_PMU_CAP_EXTENDED_HW_TYPE		0x0200
 
 struct perf_output_handle;
 
@@ -607,6 +608,7 @@ struct swevent_hlist {
 #define PERF_ATTACH_TASK_DATA	0x08
 #define PERF_ATTACH_ITRACE	0x10
 #define PERF_ATTACH_SCHED_CB	0x20
+#define PERF_ATTACH_CHILD	0x40
 
 struct perf_cgroup;
 struct perf_buffer;
@@ -734,6 +736,7 @@ struct perf_event {
 	int				pending_wakeup;
 	int				pending_kill;
 	int				pending_disable;
+	unsigned long			pending_addr;	/* SIGTRAP */
 	struct irq_work			pending;
 
 	atomic_t			event_limit;
@@ -957,7 +960,7 @@ extern void __perf_event_task_sched_in(struct task_struct *prev,
 				       struct task_struct *task);
 extern void __perf_event_task_sched_out(struct task_struct *prev,
 					struct task_struct *next);
-extern int perf_event_init_task(struct task_struct *child);
+extern int perf_event_init_task(struct task_struct *child, u64 clone_flags);
 extern void perf_event_exit_task(struct task_struct *child);
 extern void perf_event_free_task(struct task_struct *task);
 extern void perf_event_delayed_put(struct task_struct *task);
@@ -1176,30 +1179,24 @@ DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]);
  * which is guaranteed by us not actually scheduling inside other swevents
  * because those disable preemption.
  */
-static __always_inline void
-perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
+static __always_inline void __perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
 {
-	if (static_key_false(&perf_swevent_enabled[event_id])) {
-		struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
+	struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
 
-		perf_fetch_caller_regs(regs);
-		___perf_sw_event(event_id, nr, regs, addr);
-	}
+	perf_fetch_caller_regs(regs);
+	___perf_sw_event(event_id, nr, regs, addr);
 }
 
 extern struct static_key_false perf_sched_events;
 
-static __always_inline bool
-perf_sw_migrate_enabled(void)
+static __always_inline bool __perf_sw_enabled(int swevt)
 {
-	if (static_key_false(&perf_swevent_enabled[PERF_COUNT_SW_CPU_MIGRATIONS]))
-		return true;
-	return false;
+	return static_key_false(&perf_swevent_enabled[swevt]);
 }
 
 static inline void perf_event_task_migrate(struct task_struct *task)
 {
-	if (perf_sw_migrate_enabled())
+	if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS))
 		task->sched_migrated = 1;
 }
 
@@ -1209,11 +1206,9 @@ static inline void perf_event_task_sched_in(struct task_struct *prev,
 	if (static_branch_unlikely(&perf_sched_events))
 		__perf_event_task_sched_in(prev, task);
 
-	if (perf_sw_migrate_enabled() && task->sched_migrated) {
-		struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
-
-		perf_fetch_caller_regs(regs);
-		___perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, regs, 0);
+	if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS) &&
+	    task->sched_migrated) {
+		__perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
 		task->sched_migrated = 0;
 	}
 }
@@ -1221,7 +1216,15 @@ static inline void perf_event_task_sched_in(struct task_struct *prev,
 static inline void perf_event_task_sched_out(struct task_struct *prev,
 					     struct task_struct *next)
 {
-	perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0);
+	if (__perf_sw_enabled(PERF_COUNT_SW_CONTEXT_SWITCHES))
+		__perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0);
+
+#ifdef CONFIG_CGROUP_PERF
+	if (__perf_sw_enabled(PERF_COUNT_SW_CGROUP_SWITCHES) &&
+	    perf_cgroup_from_task(prev, NULL) !=
+	    perf_cgroup_from_task(next, NULL))
+		__perf_sw_event_sched(PERF_COUNT_SW_CGROUP_SWITCHES, 1, 0);
+#endif
 
 	if (static_branch_unlikely(&perf_sched_events))
 		__perf_event_task_sched_out(prev, next);
@@ -1448,7 +1451,8 @@ perf_event_task_sched_in(struct task_struct *prev,
 static inline void
 perf_event_task_sched_out(struct task_struct *prev,
 			  struct task_struct *next)			{ }
-static inline int perf_event_init_task(struct task_struct *child)	{ return 0; }
+static inline int perf_event_init_task(struct task_struct *child,
+				       u64 clone_flags)			{ return 0; }
 static inline void perf_event_exit_task(struct task_struct *child)	{ }
 static inline void perf_event_free_task(struct task_struct *task)	{ }
 static inline void perf_event_delayed_put(struct task_struct *task)	{ }
@@ -1477,8 +1481,6 @@ static inline int perf_event_refresh(struct perf_event *event, int refresh)
 static inline void
 perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)	{ }
 static inline void
-perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)			{ }
-static inline void
 perf_bp_event(struct perf_event *event, void *data)			{ }
 
 static inline int perf_register_guest_info_callbacks
@@ -1548,6 +1550,18 @@ struct perf_pmu_events_ht_attr {
 	const char				*event_str_noht;
 };
 
+struct perf_pmu_events_hybrid_attr {
+	struct device_attribute			attr;
+	u64					id;
+	const char				*event_str;
+	u64					pmu_type;
+};
+
+struct perf_pmu_format_hybrid_attr {
+	struct device_attribute			attr;
+	u64					pmu_type;
+};
+
 ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr,
 			      char *page);
 
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 205526c4003a..1e98548d7cf6 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -43,6 +43,7 @@ enum siginfo_layout {
 	SIL_FAULT_MCEERR,
 	SIL_FAULT_BNDERR,
 	SIL_FAULT_PKUERR,
+	SIL_PERF_EVENT,
 	SIL_CHLD,
 	SIL_RT,
 	SIL_SYS,
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index d2597000407a..03d6f6d2c1fe 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -91,6 +91,8 @@ union __sifields {
 				char _dummy_pkey[__ADDR_BND_PKEY_PAD];
 				__u32 _pkey;
 			} _addr_pkey;
+			/* used when si_code=TRAP_PERF */
+			unsigned long _perf;
 		};
 	} _sigfault;
 
@@ -155,6 +157,7 @@ typedef struct siginfo {
 #define si_lower	_sifields._sigfault._addr_bnd._lower
 #define si_upper	_sifields._sigfault._addr_bnd._upper
 #define si_pkey		_sifields._sigfault._addr_pkey._pkey
+#define si_perf		_sifields._sigfault._perf
 #define si_band		_sifields._sigpoll._band
 #define si_fd		_sifields._sigpoll._fd
 #define si_call_addr	_sifields._sigsys._call_addr
@@ -253,7 +256,8 @@ typedef struct siginfo {
 #define TRAP_BRANCH     3	/* process taken branch trap */
 #define TRAP_HWBKPT     4	/* hardware breakpoint/watchpoint */
 #define TRAP_UNK	5	/* undiagnosed trap */
-#define NSIGTRAP	5
+#define TRAP_PERF	6	/* perf event with sigtrap=1 */
+#define NSIGTRAP	6
 
 /*
  * There is an additional set of SIGTRAP si_codes used by ptrace
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index ad15e40d7f5d..e54e639248c8 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -38,6 +38,21 @@ enum perf_type_id {
 };
 
 /*
+ * attr.config layout for type PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE
+ * PERF_TYPE_HARDWARE:			0xEEEEEEEE000000AA
+ *					AA: hardware event ID
+ *					EEEEEEEE: PMU type ID
+ * PERF_TYPE_HW_CACHE:			0xEEEEEEEE00DDCCBB
+ *					BB: hardware cache ID
+ *					CC: hardware cache op ID
+ *					DD: hardware cache op result ID
+ *					EEEEEEEE: PMU type ID
+ * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied.
+ */
+#define PERF_PMU_TYPE_SHIFT		32
+#define PERF_HW_EVENT_MASK		0xffffffff
+
+/*
  * Generalized performance event event_id types, used by the
  * attr.event_id parameter of the sys_perf_event_open()
  * syscall:
@@ -112,6 +127,7 @@ enum perf_sw_ids {
 	PERF_COUNT_SW_EMULATION_FAULTS		= 8,
 	PERF_COUNT_SW_DUMMY			= 9,
 	PERF_COUNT_SW_BPF_OUTPUT		= 10,
+	PERF_COUNT_SW_CGROUP_SWITCHES		= 11,
 
 	PERF_COUNT_SW_MAX,			/* non-ABI */
 };
@@ -311,6 +327,7 @@ enum perf_event_read_format {
 #define PERF_ATTR_SIZE_VER4	104	/* add: sample_regs_intr */
 #define PERF_ATTR_SIZE_VER5	112	/* add: aux_watermark */
 #define PERF_ATTR_SIZE_VER6	120	/* add: aux_sample_size */
+#define PERF_ATTR_SIZE_VER7	128	/* add: sig_data */
 
 /*
  * Hardware event_id to monitor via a performance monitoring event:
@@ -389,7 +406,10 @@ struct perf_event_attr {
 				cgroup         :  1, /* include cgroup events */
 				text_poke      :  1, /* include text poke events */
 				build_id       :  1, /* use build id in mmap2 events */
-				__reserved_1   : 29;
+				inherit_thread :  1, /* children only inherit if cloned with CLONE_THREAD */
+				remove_on_exec :  1, /* event is removed from task on exec */
+				sigtrap        :  1, /* send synchronous SIGTRAP on event */
+				__reserved_1   : 26;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -441,6 +461,12 @@ struct perf_event_attr {
 	__u16	__reserved_2;
 	__u32	aux_sample_size;
 	__u32	__reserved_3;
+
+	/*
+	 * User provided data if sigtrap=1, passed back to user via
+	 * siginfo_t::si_perf, e.g. to permit user to identify the event.
+	 */
+	__u64	sig_data;
 };
 
 /*
diff --git a/include/uapi/linux/signalfd.h b/include/uapi/linux/signalfd.h
index 83429a05b698..7e333042c7e3 100644
--- a/include/uapi/linux/signalfd.h
+++ b/include/uapi/linux/signalfd.h
@@ -39,6 +39,8 @@ struct signalfd_siginfo {
 	__s32 ssi_syscall;
 	__u64 ssi_call_addr;
 	__u32 ssi_arch;
+	__u32 __pad3;
+	__u64 ssi_perf;
 
 	/*
 	 * Pad strcture to 128 bytes. Remember to update the
@@ -49,7 +51,7 @@ struct signalfd_siginfo {
 	 * comes out of a read(2) and we really don't want to have
 	 * a compat on read(2).
 	 */
-	__u8 __pad[28];
+	__u8 __pad[16];
 };