Merge branch 'akpm' (patches from Andrew)

Merge patch-bomb from Andrew Morton:

 - a few misc things

 - Andy's "ambient capabilities"

 - fs/nofity updates

 - the ocfs2 queue

 - kernel/watchdog.c updates and feature work.

 - some of MM.  Includes Andrea's userfaultfd feature.

[ Hadn't noticed that userfaultfd was 'default y' when applying the
  patches, so that got fixed in this merge instead.  We do _not_ mark
  new features that nobody uses yet 'default y'   - Linus ]

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (118 commits)
  mm/hugetlb.c: make vma_has_reserves() return bool
  mm/madvise.c: make madvise_behaviour_valid() return bool
  mm/memory.c: make tlb_next_batch() return bool
  mm/dmapool.c: change is_page_busy() return from int to bool
  mm: remove struct node_active_region
  mremap: simplify the "overlap" check in mremap_to()
  mremap: don't do uneccesary checks if new_len == old_len
  mremap: don't do mm_populate(new_addr) on failure
  mm: move ->mremap() from file_operations to vm_operations_struct
  mremap: don't leak new_vma if f_op->mremap() fails
  mm/hugetlb.c: make vma_shareable() return bool
  mm: make GUP handle pfn mapping unless FOLL_GET is requested
  mm: fix status code which move_pages() returns for zero page
  mm: memcontrol: bring back the VM_BUG_ON() in mem_cgroup_swapout()
  genalloc: add support of multiple gen_pools per device
  genalloc: add name arg to gen_pool_get() and devm_gen_pool_create()
  mm/memblock: WARN_ON when nid differs from overlap region
  Documentation/features/vm: add feature description and arch support status for batched TLB flush after unmap
  mm: defer flush of writable TLB entries
  mm: send one IPI per CPU to TLB flush all entries after unmapping pages
  ...

6 files changed, 16 insertions, 3 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 48f7433dac6f..117e2f373e50 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -41,6 +41,7 @@ config X86
 	select ARCH_USE_CMPXCHG_LOCKREF		if X86_64
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
+	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP
 	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_IPC_PARSE_VERSION	if X86_32
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 25e3cf1cd8fd..477bfa6db370 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -380,3 +380,4 @@
 371	i386	recvfrom		sys_recvfrom			compat_sys_recvfrom
 372	i386	recvmsg			sys_recvmsg			compat_sys_recvmsg
 373	i386	shutdown		sys_shutdown
+374	i386	userfaultfd		sys_userfaultfd
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 9ef32d5f1b19..81c490634db9 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -329,6 +329,7 @@
 320	common	kexec_file_load		sys_kexec_file_load
 321	common	bpf			sys_bpf
 322	64	execveat		stub_execveat
+323	common	userfaultfd		sys_userfaultfd
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index cd791948b286..6df2029405a3 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -261,6 +261,12 @@ static inline void reset_lazy_tlbstate(void)
 
 #endif	/* SMP */
 
+/* Not inlined due to inc_irq_stat not being defined yet */
+#define flush_tlb_local() {		\
+	inc_irq_stat(irq_tlb_count);	\
+	local_flush_tlb();		\
+}
+
 #ifndef CONFIG_PARAVIRT
 #define flush_tlb_others(mask, mm, start, end)	\
 	native_flush_tlb_others(mask, mm, start, end)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3f124d553c5a..cd9b6d0b10bf 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -12,7 +12,7 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/export.h>
-#include <linux/watchdog.h>
+#include <linux/nmi.h>
 
 #include <asm/cpufeature.h>
 #include <asm/hardirq.h>
@@ -3627,7 +3627,10 @@ static __init int fixup_ht_bug(void)
 		return 0;
 	}
 
-	watchdog_nmi_disable_all();
+	if (lockup_detector_suspend() != 0) {
+		pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n");
+		return 0;
+	}
 
 	x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED);
 
@@ -3635,7 +3638,7 @@ static __init int fixup_ht_bug(void)
 	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.stop_scheduling = NULL;
 
-	watchdog_nmi_enable_all();
+	lockup_detector_resume();
 
 	get_online_cpus();
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 90b924acd982..8ddb5d0d66fb 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -140,6 +140,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 	info.flush_end = end;
 
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
+	trace_tlb_flush(TLB_REMOTE_SEND_IPI, end - start);
 	if (is_uv_system()) {
 		unsigned int cpu;