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

Pull x86 perf updates from Ingo Molnar:
 "This series tightens up RDPMC permissions: currently even highly
  sandboxed x86 execution environments (such as seccomp) have permission
  to execute RDPMC, which may leak various perf events / PMU state such
  as timing information and other CPU execution details.

  This 'all is allowed' RDPMC mode is still preserved as the
  (non-default) /sys/devices/cpu/rdpmc=2 setting.  The new default is
  that RDPMC access is only allowed if a perf event is mmap-ed (which is
  needed to correctly interpret RDPMC counter values in any case).

  As a side effect of these changes CR4 handling is cleaned up in the
  x86 code and a shadow copy of the CR4 value is added.

  The extra CR4 manipulation adds ~ <50ns to the context switch cost
  between rdpmc-capable and rdpmc-non-capable mms"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86: Add /sys/devices/cpu/rdpmc=2 to allow rdpmc for all tasks
  perf/x86: Only allow rdpmc if a perf_event is mapped
  perf: Pass the event to arch_perf_update_userpage()
  perf: Add pmu callbacks to track event mapping and unmapping
  x86: Add a comment clarifying LDT context switching
  x86: Store a per-cpu shadow copy of CR4
  x86: Clean up cr4 manipulation

3 files changed, 12 insertions, 6 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index e3ff27a5b634..ede025fb46f1 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -600,7 +600,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code,
 			printk(nx_warning, from_kuid(&init_user_ns, current_uid()));
 		if (pte && pte_present(*pte) && pte_exec(*pte) &&
 				(pgd_flags(*pgd) & _PAGE_USER) &&
-				(read_cr4() & X86_CR4_SMEP))
+				(__read_cr4() & X86_CR4_SMEP))
 			printk(smep_warning, from_kuid(&init_user_ns, current_uid()));
 	}
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 649da47d3827..553c094b9cd7 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -173,11 +173,11 @@ static void __init probe_page_size_mask(void)
 
 	/* Enable PSE if available */
 	if (cpu_has_pse)
-		set_in_cr4(X86_CR4_PSE);
+		cr4_set_bits_and_update_boot(X86_CR4_PSE);
 
 	/* Enable PGE if available */
 	if (cpu_has_pge) {
-		set_in_cr4(X86_CR4_PGE);
+		cr4_set_bits_and_update_boot(X86_CR4_PGE);
 		__supported_pte_mask |= _PAGE_GLOBAL;
 	}
 }
@@ -713,6 +713,15 @@ void __init zone_sizes_init(void)
 	free_area_init_nodes(max_zone_pfns);
 }
 
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
+#ifdef CONFIG_SMP
+	.active_mm = &init_mm,
+	.state = 0,
+#endif
+	.cr4 = ~0UL,	/* fail hard if we screw up cr4 shadow initialization */
+};
+EXPORT_SYMBOL_GPL(cpu_tlbstate);
+
 void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
 {
 	/* entry 0 MUST be WB (hardwired to speed up translations) */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index ee61c36d64f8..3250f2371aea 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -14,9 +14,6 @@
 #include <asm/uv/uv.h>
 #include <linux/debugfs.h>
 
-DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate)
-			= { &init_mm, 0, };
-
 /*
  *	Smarter SMP flushing macros.
  *		c/o Linus Torvalds.