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

Pull perf updates from Ingo Molnar:
 "The main updates in this cycle were:

   - Lots of perf tooling changes too voluminous to list (big perf trace
     and perf stat improvements, lots of libtraceevent reorganization,
     etc.), so I'll list the authors and refer to the changelog for
     details:

       Benjamin Peterson, Jérémie Galarneau, Kim Phillips, Peter
       Zijlstra, Ravi Bangoria, Sangwon Hong, Sean V Kelley, Steven
       Rostedt, Thomas Gleixner, Ding Xiang, Eduardo Habkost, Thomas
       Richter, Andi Kleen, Sanskriti Sharma, Adrian Hunter, Tzvetomir
       Stoyanov, Arnaldo Carvalho de Melo, Jiri Olsa.

     ... with the bulk of the changes written by Jiri Olsa, Tzvetomir
     Stoyanov and Arnaldo Carvalho de Melo.

   - Continued intel_rdt work with a focus on playing well with perf
     events. This also imported some non-perf RDT work due to
     dependencies. (Reinette Chatre)

   - Implement counter freezing for Arch Perfmon v4 (Skylake and newer).
     This allows to speed up the PMI handler by avoiding unnecessary MSR
     writes and make it more accurate. (Andi Kleen)

   - kprobes cleanups and simplification (Masami Hiramatsu)

   - Intel Goldmont PMU updates (Kan Liang)

   - ... plus misc other fixes and updates"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (155 commits)
  kprobes/x86: Use preempt_enable() in optimized_callback()
  x86/intel_rdt: Prevent pseudo-locking from using stale pointers
  kprobes, x86/ptrace.h: Make regs_get_kernel_stack_nth() not fault on bad stack
  perf/x86/intel: Export mem events only if there's PEBS support
  x86/cpu: Drop pointless static qualifier in punit_dev_state_show()
  x86/intel_rdt: Fix initial allocation to consider CDP
  x86/intel_rdt: CBM overlap should also check for overlap with CDP peer
  x86/intel_rdt: Introduce utility to obtain CDP peer
  tools lib traceevent, perf tools: Move struct tep_handler definition in a local header file
  tools lib traceevent: Separate out tep_strerror() for strerror_r() issues
  perf python: More portable way to make CFLAGS work with clang
  perf python: Make clang_has_option() work on Python 3
  perf tools: Free temporary 'sys' string in read_event_files()
  perf tools: Avoid double free in read_event_file()
  perf tools: Free 'printk' string in parse_ftrace_printk()
  perf tools: Cleanup trace-event-info 'tdata' leak
  perf strbuf: Match va_{add,copy} with va_end
  perf test: S390 does not support watchpoints in test 22
  perf auxtrace: Include missing asm/bitsperlong.h to get BITS_PER_LONG
  tools include: Adopt linux/bits.h
  ...

4 files changed, 54 insertions, 23 deletions

diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 7ed08a7c3398..0dd6b0f4000e 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -8,9 +8,6 @@
  * The "_X" parts are generally the EP and EX Xeons, or the
  * "Extreme" ones, like Broadwell-E.
  *
- * Things ending in "2" are usually because we have no better
- * name for them.  There's no processor called "SILVERMONT2".
- *
  * While adding a new CPUID for a new microarchitecture, add a new
  * group to keep logically sorted out in chronological order. Within
  * that group keep the CPUID for the variants sorted by model number.
@@ -57,19 +54,23 @@
 
 /* "Small Core" Processors (Atom) */
 
-#define INTEL_FAM6_ATOM_PINEVIEW	0x1C
-#define INTEL_FAM6_ATOM_LINCROFT	0x26
-#define INTEL_FAM6_ATOM_PENWELL		0x27
-#define INTEL_FAM6_ATOM_CLOVERVIEW	0x35
-#define INTEL_FAM6_ATOM_CEDARVIEW	0x36
-#define INTEL_FAM6_ATOM_SILVERMONT1	0x37 /* BayTrail/BYT / Valleyview */
-#define INTEL_FAM6_ATOM_SILVERMONT2	0x4D /* Avaton/Rangely */
-#define INTEL_FAM6_ATOM_AIRMONT		0x4C /* CherryTrail / Braswell */
-#define INTEL_FAM6_ATOM_MERRIFIELD	0x4A /* Tangier */
-#define INTEL_FAM6_ATOM_MOOREFIELD	0x5A /* Anniedale */
-#define INTEL_FAM6_ATOM_GOLDMONT	0x5C
-#define INTEL_FAM6_ATOM_DENVERTON	0x5F /* Goldmont Microserver */
-#define INTEL_FAM6_ATOM_GEMINI_LAKE	0x7A
+#define INTEL_FAM6_ATOM_BONNELL		0x1C /* Diamondville, Pineview */
+#define INTEL_FAM6_ATOM_BONNELL_MID	0x26 /* Silverthorne, Lincroft */
+
+#define INTEL_FAM6_ATOM_SALTWELL	0x36 /* Cedarview */
+#define INTEL_FAM6_ATOM_SALTWELL_MID	0x27 /* Penwell */
+#define INTEL_FAM6_ATOM_SALTWELL_TABLET	0x35 /* Cloverview */
+
+#define INTEL_FAM6_ATOM_SILVERMONT	0x37 /* Bay Trail, Valleyview */
+#define INTEL_FAM6_ATOM_SILVERMONT_X	0x4D /* Avaton, Rangely */
+#define INTEL_FAM6_ATOM_SILVERMONT_MID	0x4A /* Merriefield */
+
+#define INTEL_FAM6_ATOM_AIRMONT		0x4C /* Cherry Trail, Braswell */
+#define INTEL_FAM6_ATOM_AIRMONT_MID	0x5A /* Moorefield */
+
+#define INTEL_FAM6_ATOM_GOLDMONT	0x5C /* Apollo Lake */
+#define INTEL_FAM6_ATOM_GOLDMONT_X	0x5F /* Denverton */
+#define INTEL_FAM6_ATOM_GOLDMONT_PLUS	0x7A /* Gemini Lake */
 
 /* Xeon Phi */
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4731f0cf97c5..80f4a4f38c79 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -164,6 +164,7 @@
 #define DEBUGCTLMSR_BTS_OFF_OS		(1UL <<  9)
 #define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
 #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
+#define DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI	(1UL << 12)
 #define DEBUGCTLMSR_FREEZE_IN_SMM_BIT	14
 #define DEBUGCTLMSR_FREEZE_IN_SMM	(1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 78241b736f2a..8bdf74902293 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -278,6 +278,7 @@ struct perf_guest_switch_msr {
 extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
 extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
 extern void perf_check_microcode(void);
+extern int x86_perf_rdpmc_index(struct perf_event *event);
 #else
 static inline struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
 {
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 5e58a74bfd3a..25f49af1b13c 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -239,23 +239,51 @@ static inline int regs_within_kernel_stack(struct pt_regs *regs,
 }
 
 /**
+ * regs_get_kernel_stack_nth_addr() - get the address of the Nth entry on stack
+ * @regs:	pt_regs which contains kernel stack pointer.
+ * @n:		stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns the address of the @n th entry of the
+ * kernel stack which is specified by @regs. If the @n th entry is NOT in
+ * the kernel stack, this returns NULL.
+ */
+static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n)
+{
+	unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
+
+	addr += n;
+	if (regs_within_kernel_stack(regs, (unsigned long)addr))
+		return addr;
+	else
+		return NULL;
+}
+
+/* To avoid include hell, we can't include uaccess.h */
+extern long probe_kernel_read(void *dst, const void *src, size_t size);
+
+/**
  * regs_get_kernel_stack_nth() - get Nth entry of the stack
  * @regs:	pt_regs which contains kernel stack pointer.
  * @n:		stack entry number.
  *
  * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
- * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack
  * this returns 0.
  */
 static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 						      unsigned int n)
 {
-	unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
-	addr += n;
-	if (regs_within_kernel_stack(regs, (unsigned long)addr))
-		return *addr;
-	else
-		return 0;
+	unsigned long *addr;
+	unsigned long val;
+	long ret;
+
+	addr = regs_get_kernel_stack_nth_addr(regs, n);
+	if (addr) {
+		ret = probe_kernel_read(&val, addr, sizeof(val));
+		if (!ret)
+			return val;
+	}
+	return 0;
 }
 
 #define arch_has_single_step()	(1)