Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm updates from Ingo Molnar:
 "The main x86 MM changes in this cycle were:

   - continued native kernel PCID support preparation patches to the TLB
     flushing code (Andy Lutomirski)

   - various fixes related to 32-bit compat syscall returning address
     over 4Gb in applications, launched from 64-bit binaries - motivated
     by C/R frameworks such as Virtuozzo. (Dmitry Safonov)

   - continued Intel 5-level paging enablement: in particular the
     conversion of x86 GUP to the generic GUP code. (Kirill A. Shutemov)

   - x86/mpx ABI corner case fixes/enhancements (Joerg Roedel)

   - ... plus misc updates, fixes and cleanups"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (62 commits)
  mm, zone_device: Replace {get, put}_zone_device_page() with a single reference to fix pmem crash
  x86/mm: Fix flush_tlb_page() on Xen
  x86/mm: Make flush_tlb_mm_range() more predictable
  x86/mm: Remove flush_tlb() and flush_tlb_current_task()
  x86/vm86/32: Switch to flush_tlb_mm_range() in mark_screen_rdonly()
  x86/mm/64: Fix crash in remove_pagetable()
  Revert "x86/mm/gup: Switch GUP to the generic get_user_page_fast() implementation"
  x86/boot/e820: Remove a redundant self assignment
  x86/mm: Fix dump pagetables for 4 levels of page tables
  x86/mpx, selftests: Only check bounds-vs-shadow when we keep shadow
  x86/mpx: Correctly report do_mpx_bt_fault() failures to user-space
  Revert "x86/mm/numa: Remove numa_nodemask_from_meminfo()"
  x86/espfix: Add support for 5-level paging
  x86/kasan: Extend KASAN to support 5-level paging
  x86/mm: Add basic defines/helpers for CONFIG_X86_5LEVEL=y
  x86/paravirt: Add 5-level support to the paravirt code
  x86/mm: Define virtual memory map for 5-level paging
  x86/asm: Remove __VIRTUAL_MASK_SHIFT==47 assert
  x86/boot: Detect 5-level paging support
  x86/mm/numa: Remove numa_nodemask_from_meminfo()
  ...

4 files changed, 20 insertions, 11 deletions

diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index 033f49b31fdc..cb0d742fa23f 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -43,6 +43,7 @@ static void dax_pmem_percpu_exit(void *data)
 	struct dax_pmem *dax_pmem = to_dax_pmem(ref);
 
 	dev_dbg(dax_pmem->dev, "%s\n", __func__);
+	wait_for_completion(&dax_pmem->cmp);
 	percpu_ref_exit(ref);
 }
 
@@ -53,7 +54,6 @@ static void dax_pmem_percpu_kill(void *data)
 
 	dev_dbg(dax_pmem->dev, "%s\n", __func__);
 	percpu_ref_kill(ref);
-	wait_for_completion(&dax_pmem->cmp);
 }
 
 static int dax_pmem_probe(struct device *dev)
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index d71f6323ac00..b4f79b923aea 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -504,7 +504,7 @@ void __init lguest_arch_host_init(void)
 		 * byte, not the size, hence the "-1").
 		 */
 		state->host_gdt_desc.size = GDT_SIZE-1;
-		state->host_gdt_desc.address = (long)get_cpu_gdt_table(i);
+		state->host_gdt_desc.address = (long)get_cpu_gdt_rw(i);
 
 		/*
 		 * All CPUs on the Host use the same Interrupt Descriptor
@@ -554,8 +554,8 @@ void __init lguest_arch_host_init(void)
 		 * The Host needs to be able to use the LGUEST segments on this
 		 * CPU, too, so put them in the Host GDT.
 		 */
-		get_cpu_gdt_table(i)[GDT_ENTRY_LGUEST_CS] = FULL_EXEC_SEGMENT;
-		get_cpu_gdt_table(i)[GDT_ENTRY_LGUEST_DS] = FULL_SEGMENT;
+		get_cpu_gdt_rw(i)[GDT_ENTRY_LGUEST_CS] = FULL_EXEC_SEGMENT;
+		get_cpu_gdt_rw(i)[GDT_ENTRY_LGUEST_DS] = FULL_SEGMENT;
 	}
 
 	/*
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 5b536be5a12e..fbc640bf06b0 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -25,6 +25,7 @@
 #include <linux/badblocks.h>
 #include <linux/memremap.h>
 #include <linux/vmalloc.h>
+#include <linux/blk-mq.h>
 #include <linux/pfn_t.h>
 #include <linux/slab.h>
 #include <linux/pmem.h>
@@ -231,6 +232,11 @@ static void pmem_release_queue(void *q)
 	blk_cleanup_queue(q);
 }
 
+static void pmem_freeze_queue(void *q)
+{
+	blk_freeze_queue_start(q);
+}
+
 static void pmem_release_disk(void *disk)
 {
 	del_gendisk(disk);
@@ -284,6 +290,9 @@ static int pmem_attach_disk(struct device *dev,
 	if (!q)
 		return -ENOMEM;
 
+	if (devm_add_action_or_reset(dev, pmem_release_queue, q))
+		return -ENOMEM;
+
 	pmem->pfn_flags = PFN_DEV;
 	if (is_nd_pfn(dev)) {
 		addr = devm_memremap_pages(dev, &pfn_res, &q->q_usage_counter,
@@ -303,10 +312,10 @@ static int pmem_attach_disk(struct device *dev,
 				pmem->size, ARCH_MEMREMAP_PMEM);
 
 	/*
-	 * At release time the queue must be dead before
+	 * At release time the queue must be frozen before
 	 * devm_memremap_pages is unwound
 	 */
-	if (devm_add_action_or_reset(dev, pmem_release_queue, q))
+	if (devm_add_action_or_reset(dev, pmem_freeze_queue, q))
 		return -ENOMEM;
 
 	if (IS_ERR(addr))
diff --git a/drivers/pnp/pnpbios/bioscalls.c b/drivers/pnp/pnpbios/bioscalls.c
index 438d4c72c7b3..ff563db025b3 100644
--- a/drivers/pnp/pnpbios/bioscalls.c
+++ b/drivers/pnp/pnpbios/bioscalls.c
@@ -54,7 +54,7 @@ __asm__(".text			\n"
 
 #define Q2_SET_SEL(cpu, selname, address, size) \
 do { \
-	struct desc_struct *gdt = get_cpu_gdt_table((cpu)); \
+	struct desc_struct *gdt = get_cpu_gdt_rw((cpu)); \
 	set_desc_base(&gdt[(selname) >> 3], (u32)(address)); \
 	set_desc_limit(&gdt[(selname) >> 3], (size) - 1); \
 } while(0)
@@ -95,8 +95,8 @@ static inline u16 call_pnp_bios(u16 func, u16 arg1, u16 arg2, u16 arg3,
 		return PNP_FUNCTION_NOT_SUPPORTED;
 
 	cpu = get_cpu();
-	save_desc_40 = get_cpu_gdt_table(cpu)[0x40 / 8];
-	get_cpu_gdt_table(cpu)[0x40 / 8] = bad_bios_desc;
+	save_desc_40 = get_cpu_gdt_rw(cpu)[0x40 / 8];
+	get_cpu_gdt_rw(cpu)[0x40 / 8] = bad_bios_desc;
 
 	/* On some boxes IRQ's during PnP BIOS calls are deadly.  */
 	spin_lock_irqsave(&pnp_bios_lock, flags);
@@ -134,7 +134,7 @@ static inline u16 call_pnp_bios(u16 func, u16 arg1, u16 arg2, u16 arg3,
 			     :"memory");
 	spin_unlock_irqrestore(&pnp_bios_lock, flags);
 
-	get_cpu_gdt_table(cpu)[0x40 / 8] = save_desc_40;
+	get_cpu_gdt_rw(cpu)[0x40 / 8] = save_desc_40;
 	put_cpu();
 
 	/* If we get here and this is set then the PnP BIOS faulted on us. */
@@ -477,7 +477,7 @@ void pnpbios_calls_init(union pnp_bios_install_struct *header)
 	pnp_bios_callpoint.segment = PNP_CS16;
 
 	for_each_possible_cpu(i) {
-		struct desc_struct *gdt = get_cpu_gdt_table(i);
+		struct desc_struct *gdt = get_cpu_gdt_rw(i);
 		if (!gdt)
 			continue;
 		set_desc_base(&gdt[GDT_ENTRY_PNPBIOS_CS32],