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

Pull perf events changes for v3.4 from Ingo Molnar:

 - New "hardware based branch profiling" feature both on the kernel and
   the tooling side, on CPUs that support it.  (modern x86 Intel CPUs
   with the 'LBR' hardware feature currently.)

   This new feature is basically a sophisticated 'magnifying glass' for
   branch execution - something that is pretty difficult to extract from
   regular, function histogram centric profiles.

   The simplest mode is activated via 'perf record -b', and the result
   looks like this in perf report:

	$ perf record -b any_call,u -e cycles:u branchy

	$ perf report -b --sort=symbol
	    52.34%  [.] main                   [.] f1
	    24.04%  [.] f1                     [.] f3
	    23.60%  [.] f1                     [.] f2
	     0.01%  [k] _IO_new_file_xsputn    [k] _IO_file_overflow
	     0.01%  [k] _IO_vfprintf_internal  [k] _IO_new_file_xsputn
	     0.01%  [k] _IO_vfprintf_internal  [k] strchrnul
	     0.01%  [k] __printf               [k] _IO_vfprintf_internal
	     0.01%  [k] main                   [k] __printf

   This output shows from/to branch columns and shows the highest
   percentage (from,to) jump combinations - i.e.  the most likely taken
   branches in the system.  "branches" can also include function calls
   and any other synchronous and asynchronous transitions of the
   instruction pointer that are not 'next instruction' - such as system
   calls, traps, interrupts, etc.

   This feature comes with (hopefully intuitive) flat ascii and TUI
   support in perf report.

 - Various 'perf annotate' visual improvements for us assembly junkies.
   It will now recognize function calls in the TUI and by hitting enter
   you can follow the call (recursively) and back, amongst other
   improvements.

 - Multiple threads/processes recording support in perf record, perf
   stat, perf top - which is activated via a comma-list of PIDs:

	perf top -p 21483,21485
	perf stat -p 21483,21485 -ddd
	perf record -p 21483,21485

 - Support for per UID views, via the --uid paramter to perf top, perf
   report, etc.  For example 'perf top --uid mingo' will only show the
   tasks that I am running, excluding other users, root, etc.

 - Jump label restructurings and improvements - this includes the
   factoring out of the (hopefully much clearer) include/linux/static_key.h
   generic facility:

	struct static_key key = STATIC_KEY_INIT_FALSE;

	...

	if (static_key_false(&key))
	        do unlikely code
	else
	        do likely code

	...
	static_key_slow_inc();
	...
	static_key_slow_inc();
	...

   The static_key_false() branch will be generated into the code with as
   little impact to the likely code path as possible.  the
   static_key_slow_*() APIs flip the branch via live kernel code patching.

   This facility can now be used more widely within the kernel to
   micro-optimize hot branches whose likelihood matches the static-key
   usage and fast/slow cost patterns.

 - SW function tracer improvements: perf support and filtering support.

 - Various hardenings of the perf.data ABI, to make older perf.data's
   smoother on newer tool versions, to make new features integrate more
   smoothly, to support cross-endian recording/analyzing workflows
   better, etc.

 - Restructuring of the kprobes code, the splitting out of 'optprobes',
   and a corner case bugfix.

 - Allow the tracing of kernel console output (printk).

 - Improvements/fixes to user-space RDPMC support, allowing user-space
   self-profiling code to extract PMU counts without performing any
   system calls, while playing nice with the kernel side.

 - 'perf bench' improvements

 - ... and lots of internal restructurings, cleanups and fixes that made
   these features possible.  And, as usual this list is incomplete as
   there were also lots of other improvements

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits)
  perf report: Fix annotate double quit issue in branch view mode
  perf report: Remove duplicate annotate choice in branch view mode
  perf/x86: Prettify pmu config literals
  perf report: Enable TUI in branch view mode
  perf report: Auto-detect branch stack sampling mode
  perf record: Add HEADER_BRANCH_STACK tag
  perf record: Provide default branch stack sampling mode option
  perf tools: Make perf able to read files from older ABIs
  perf tools: Fix ABI compatibility bug in print_event_desc()
  perf tools: Enable reading of perf.data files from different ABI rev
  perf: Add ABI reference sizes
  perf report: Add support for taken branch sampling
  perf record: Add support for sampling taken branch
  perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK
  x86/kprobes: Split out optprobe related code to kprobes-opt.c
  x86/kprobes: Fix a bug which can modify kernel code permanently
  x86/kprobes: Fix instruction recovery on optimized path
  perf: Add callback to flush branch_stack on context switch
  perf: Disable PERF_SAMPLE_BRANCH_* when not supported
  perf/x86: Add LBR software filter support for Intel CPUs
  ...

6 files changed, 24 insertions, 24 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 6ca32f6b310..6982bfd6a78 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -134,7 +134,7 @@
 #include <linux/inetdevice.h>
 #include <linux/cpu_rmap.h>
 #include <linux/net_tstamp.h>
-#include <linux/jump_label.h>
+#include <linux/static_key.h>
 #include <net/flow_keys.h>
 
 #include "net-sysfs.h"
@@ -1441,11 +1441,11 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
 }
 EXPORT_SYMBOL(call_netdevice_notifiers);
 
-static struct jump_label_key netstamp_needed __read_mostly;
+static struct static_key netstamp_needed __read_mostly;
 #ifdef HAVE_JUMP_LABEL
-/* We are not allowed to call jump_label_dec() from irq context
+/* We are not allowed to call static_key_slow_dec() from irq context
  * If net_disable_timestamp() is called from irq context, defer the
- * jump_label_dec() calls.
+ * static_key_slow_dec() calls.
  */
 static atomic_t netstamp_needed_deferred;
 #endif
@@ -1457,12 +1457,12 @@ void net_enable_timestamp(void)
 
 	if (deferred) {
 		while (--deferred)
-			jump_label_dec(&netstamp_needed);
+			static_key_slow_dec(&netstamp_needed);
 		return;
 	}
 #endif
 	WARN_ON(in_interrupt());
-	jump_label_inc(&netstamp_needed);
+	static_key_slow_inc(&netstamp_needed);
 }
 EXPORT_SYMBOL(net_enable_timestamp);
 
@@ -1474,19 +1474,19 @@ void net_disable_timestamp(void)
 		return;
 	}
 #endif
-	jump_label_dec(&netstamp_needed);
+	static_key_slow_dec(&netstamp_needed);
 }
 EXPORT_SYMBOL(net_disable_timestamp);
 
 static inline void net_timestamp_set(struct sk_buff *skb)
 {
 	skb->tstamp.tv64 = 0;
-	if (static_branch(&netstamp_needed))
+	if (static_key_false(&netstamp_needed))
 		__net_timestamp(skb);
 }
 
 #define net_timestamp_check(COND, SKB)			\
-	if (static_branch(&netstamp_needed)) {		\
+	if (static_key_false(&netstamp_needed)) {		\
 		if ((COND) && !(SKB)->tstamp.tv64)	\
 			__net_timestamp(SKB);		\
 	}						\
@@ -2660,7 +2660,7 @@ EXPORT_SYMBOL(__skb_get_rxhash);
 struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly;
 EXPORT_SYMBOL(rps_sock_flow_table);
 
-struct jump_label_key rps_needed __read_mostly;
+struct static_key rps_needed __read_mostly;
 
 static struct rps_dev_flow *
 set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
@@ -2945,7 +2945,7 @@ int netif_rx(struct sk_buff *skb)
 
 	trace_netif_rx(skb);
 #ifdef CONFIG_RPS
-	if (static_branch(&rps_needed))	{
+	if (static_key_false(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
 		int cpu;
 
@@ -3309,7 +3309,7 @@ int netif_receive_skb(struct sk_buff *skb)
 		return NET_RX_SUCCESS;
 
 #ifdef CONFIG_RPS
-	if (static_branch(&rps_needed)) {
+	if (static_key_false(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
 		int cpu, ret;
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index a1727cda03d..495586232aa 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -608,10 +608,10 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue,
 	spin_unlock(&rps_map_lock);
 
 	if (map)
-		jump_label_inc(&rps_needed);
+		static_key_slow_inc(&rps_needed);
 	if (old_map) {
 		kfree_rcu(old_map, rcu);
-		jump_label_dec(&rps_needed);
+		static_key_slow_dec(&rps_needed);
 	}
 	free_cpumask_var(mask);
 	return len;
diff --git a/net/core/sock.c b/net/core/sock.c
index 02f8dfe320b..95aff9c7419 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -111,7 +111,7 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/user_namespace.h>
-#include <linux/jump_label.h>
+#include <linux/static_key.h>
 #include <linux/memcontrol.h>
 
 #include <asm/uaccess.h>
@@ -184,7 +184,7 @@ void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss)
 static struct lock_class_key af_family_keys[AF_MAX];
 static struct lock_class_key af_family_slock_keys[AF_MAX];
 
-struct jump_label_key memcg_socket_limit_enabled;
+struct static_key memcg_socket_limit_enabled;
 EXPORT_SYMBOL(memcg_socket_limit_enabled);
 
 /*
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index d05559d4d9c..0c285087425 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -69,9 +69,9 @@ static int rps_sock_flow_sysctl(ctl_table *table, int write,
 		if (sock_table != orig_sock_table) {
 			rcu_assign_pointer(rps_sock_flow_table, sock_table);
 			if (sock_table)
-				jump_label_inc(&rps_needed);
+				static_key_slow_inc(&rps_needed);
 			if (orig_sock_table) {
-				jump_label_dec(&rps_needed);
+				static_key_slow_dec(&rps_needed);
 				synchronize_rcu();
 				vfree(orig_sock_table);
 			}
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 49978788a9d..602fb305365 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -111,7 +111,7 @@ void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
 	val = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
 
 	if (val != RESOURCE_MAX)
-		jump_label_dec(&memcg_socket_limit_enabled);
+		static_key_slow_dec(&memcg_socket_limit_enabled);
 }
 EXPORT_SYMBOL(tcp_destroy_cgroup);
 
@@ -143,9 +143,9 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 					     net->ipv4.sysctl_tcp_mem[i]);
 
 	if (val == RESOURCE_MAX && old_lim != RESOURCE_MAX)
-		jump_label_dec(&memcg_socket_limit_enabled);
+		static_key_slow_dec(&memcg_socket_limit_enabled);
 	else if (old_lim == RESOURCE_MAX && val != RESOURCE_MAX)
-		jump_label_inc(&memcg_socket_limit_enabled);
+		static_key_slow_inc(&memcg_socket_limit_enabled);
 
 	return 0;
 }
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index b4e8ff05b30..e1b7e051332 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -56,7 +56,7 @@ struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS] __read_mostly;
 EXPORT_SYMBOL(nf_hooks);
 
 #if defined(CONFIG_JUMP_LABEL)
-struct jump_label_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
+struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
 EXPORT_SYMBOL(nf_hooks_needed);
 #endif
 
@@ -77,7 +77,7 @@ int nf_register_hook(struct nf_hook_ops *reg)
 	list_add_rcu(&reg->list, elem->list.prev);
 	mutex_unlock(&nf_hook_mutex);
 #if defined(CONFIG_JUMP_LABEL)
-	jump_label_inc(&nf_hooks_needed[reg->pf][reg->hooknum]);
+	static_key_slow_inc(&nf_hooks_needed[reg->pf][reg->hooknum]);
 #endif
 	return 0;
 }
@@ -89,7 +89,7 @@ void nf_unregister_hook(struct nf_hook_ops *reg)
 	list_del_rcu(&reg->list);
 	mutex_unlock(&nf_hook_mutex);
 #if defined(CONFIG_JUMP_LABEL)
-	jump_label_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
+	static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
 #endif
 	synchronize_net();
 }