Merge 4.4.110 into android-4.4

Changes in 4.4.110
	x86/boot: Add early cmdline parsing for options with arguments
	KAISER: Kernel Address Isolation
	kaiser: merged update
	kaiser: do not set _PAGE_NX on pgd_none
	kaiser: stack map PAGE_SIZE at THREAD_SIZE-PAGE_SIZE
	kaiser: fix build and FIXME in alloc_ldt_struct()
	kaiser: KAISER depends on SMP
	kaiser: fix regs to do_nmi() ifndef CONFIG_KAISER
	kaiser: fix perf crashes
	kaiser: ENOMEM if kaiser_pagetable_walk() NULL
	kaiser: tidied up asm/kaiser.h somewhat
	kaiser: tidied up kaiser_add/remove_mapping slightly
	kaiser: kaiser_remove_mapping() move along the pgd
	kaiser: cleanups while trying for gold link
	kaiser: name that 0x1000 KAISER_SHADOW_PGD_OFFSET
	kaiser: delete KAISER_REAL_SWITCH option
	kaiser: vmstat show NR_KAISERTABLE as nr_overhead
	kaiser: enhanced by kernel and user PCIDs
	kaiser: load_new_mm_cr3() let SWITCH_USER_CR3 flush user
	kaiser: PCID 0 for kernel and 128 for user
	kaiser: x86_cr3_pcid_noflush and x86_cr3_pcid_user
	kaiser: paranoid_entry pass cr3 need to paranoid_exit
	kaiser: _pgd_alloc() without __GFP_REPEAT to avoid stalls
	kaiser: fix unlikely error in alloc_ldt_struct()
	kaiser: add "nokaiser" boot option, using ALTERNATIVE
	x86/kaiser: Rename and simplify X86_FEATURE_KAISER handling
	x86/kaiser: Check boottime cmdline params
	kaiser: use ALTERNATIVE instead of x86_cr3_pcid_noflush
	kaiser: drop is_atomic arg to kaiser_pagetable_walk()
	kaiser: asm/tlbflush.h handle noPGE at lower level
	kaiser: kaiser_flush_tlb_on_return_to_user() check PCID
	x86/paravirt: Dont patch flush_tlb_single
	x86/kaiser: Reenable PARAVIRT
	kaiser: disabled on Xen PV
	x86/kaiser: Move feature detection up
	KPTI: Rename to PAGE_TABLE_ISOLATION
	KPTI: Report when enabled
	x86, vdso, pvclock: Simplify and speed up the vdso pvclock reader
	x86/vdso: Get pvclock data from the vvar VMA instead of the fixmap
	x86/kasan: Clear kasan_zero_page after TLB flush
	kaiser: Set _PAGE_NX only if supported
	Linux 4.4.110

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

1 files changed, 35 insertions, 4 deletions

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 7a4cdb632508..7cad01af6dcd 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -6,13 +6,14 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/cpu.h>
+#include <linux/debugfs.h>
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 #include <asm/cache.h>
 #include <asm/apic.h>
 #include <asm/uv/uv.h>
-#include <linux/debugfs.h>
+#include <asm/kaiser.h>
 
 /*
  *	TLB flushing, formerly SMP-only
@@ -34,6 +35,36 @@ struct flush_tlb_info {
 	unsigned long flush_end;
 };
 
+static void load_new_mm_cr3(pgd_t *pgdir)
+{
+	unsigned long new_mm_cr3 = __pa(pgdir);
+
+	if (kaiser_enabled) {
+		/*
+		 * We reuse the same PCID for different tasks, so we must
+		 * flush all the entries for the PCID out when we change tasks.
+		 * Flush KERN below, flush USER when returning to userspace in
+		 * kaiser's SWITCH_USER_CR3 (_SWITCH_TO_USER_CR3) macro.
+		 *
+		 * invpcid_flush_single_context(X86_CR3_PCID_ASID_USER) could
+		 * do it here, but can only be used if X86_FEATURE_INVPCID is
+		 * available - and many machines support pcid without invpcid.
+		 *
+		 * If X86_CR3_PCID_KERN_FLUSH actually added something, then it
+		 * would be needed in the write_cr3() below - if PCIDs enabled.
+		 */
+		BUILD_BUG_ON(X86_CR3_PCID_KERN_FLUSH);
+		kaiser_flush_tlb_on_return_to_user();
+	}
+
+	/*
+	 * Caution: many callers of this function expect
+	 * that load_cr3() is serializing and orders TLB
+	 * fills with respect to the mm_cpumask writes.
+	 */
+	write_cr3(new_mm_cr3);
+}
+
 /*
  * We cannot call mmdrop() because we are in interrupt context,
  * instead update mm->cpu_vm_mask.
@@ -45,7 +76,7 @@ void leave_mm(int cpu)
 		BUG();
 	if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) {
 		cpumask_clear_cpu(cpu, mm_cpumask(active_mm));
-		load_cr3(swapper_pg_dir);
+		load_new_mm_cr3(swapper_pg_dir);
 		/*
 		 * This gets called in the idle path where RCU
 		 * functions differently.  Tracing normally
@@ -105,7 +136,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		 * ordering guarantee we need.
 		 *
 		 */
-		load_cr3(next->pgd);
+		load_new_mm_cr3(next->pgd);
 
 		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 
@@ -152,7 +183,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			 * As above, load_cr3() is serializing and orders TLB
 			 * fills with respect to the mm_cpumask write.
 			 */
-			load_cr3(next->pgd);
+			load_new_mm_cr3(next->pgd);
 			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 			load_mm_cr4(next);
 			load_mm_ldt(next);