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:
 "Various x86 low level modifications:

   - preparatory work to support virtually mapped kernel stacks (Andy
     Lutomirski)

   - support for 64-bit __get_user() on 32-bit kernels (Benjamin
     LaHaise)

   - (involved) workaround for Knights Landing CPU erratum (Dave Hansen)

   - MPX enhancements (Dave Hansen)

   - mremap() extension to allow remapping of the special VDSO vma, for
     purposes of user level context save/restore (Dmitry Safonov)

   - hweight and entry code cleanups (Borislav Petkov)

   - bitops code generation optimizations and cleanups with modern GCC
     (H. Peter Anvin)

   - syscall entry code optimizations (Paolo Bonzini)"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (43 commits)
  x86/mm/cpa: Add missing comment in populate_pdg()
  x86/mm/cpa: Fix populate_pgd(): Stop trying to deallocate failed PUDs
  x86/syscalls: Add compat_sys_preadv64v2/compat_sys_pwritev64v2
  x86/smp: Remove unnecessary initialization of thread_info::cpu
  x86/smp: Remove stack_smp_processor_id()
  x86/uaccess: Move thread_info::addr_limit to thread_struct
  x86/dumpstack: Rename thread_struct::sig_on_uaccess_error to sig_on_uaccess_err
  x86/uaccess: Move thread_info::uaccess_err and thread_info::sig_on_uaccess_err to thread_struct
  x86/dumpstack: When OOPSing, rewind the stack before do_exit()
  x86/mm/64: In vmalloc_fault(), use CR3 instead of current->active_mm
  x86/dumpstack/64: Handle faults when printing the "Stack: " part of an OOPS
  x86/dumpstack: Try harder to get a call trace on stack overflow
  x86/mm: Remove kernel_unmap_pages_in_pgd() and efi_cleanup_page_tables()
  x86/mm/cpa: In populate_pgd(), don't set the PGD entry until it's populated
  x86/mm/hotplug: Don't remove PGD entries in remove_pagetable()
  x86/mm: Use pte_none() to test for empty PTE
  x86/mm: Disallow running with 32-bit PTEs to work around erratum
  x86/mm: Ignore A/D bits in pte/pmd/pud_none()
  x86/mm: Move swap offset/type up in PTE to work around erratum
  x86/entry: Inline enter_from_user_mode()
  ...

7 files changed, 99 insertions, 21 deletions

diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 72a576752a7e..ec969cc3eb20 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -25,7 +25,7 @@ lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o
 
-obj-y += msr.o msr-reg.o msr-reg-export.o
+obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
 
 ifeq ($(CONFIG_X86_32),y)
         obj-y += atomic64_32.o
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 2b0ef26da0bd..bf603ebbfd8e 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -17,11 +17,11 @@
 
 /* Standard copy_to_user with segment limit checking */
 ENTRY(_copy_to_user)
-	GET_THREAD_INFO(%rax)
+	mov PER_CPU_VAR(current_task), %rax
 	movq %rdi,%rcx
 	addq %rdx,%rcx
 	jc bad_to_user
-	cmpq TI_addr_limit(%rax),%rcx
+	cmpq TASK_addr_limit(%rax),%rcx
 	ja bad_to_user
 	ALTERNATIVE_2 "jmp copy_user_generic_unrolled",		\
 		      "jmp copy_user_generic_string",		\
@@ -32,11 +32,11 @@ ENDPROC(_copy_to_user)
 
 /* Standard copy_from_user with segment limit checking */
 ENTRY(_copy_from_user)
-	GET_THREAD_INFO(%rax)
+	mov PER_CPU_VAR(current_task), %rax
 	movq %rsi,%rcx
 	addq %rdx,%rcx
 	jc bad_from_user
-	cmpq TI_addr_limit(%rax),%rcx
+	cmpq TASK_addr_limit(%rax),%rcx
 	ja bad_from_user
 	ALTERNATIVE_2 "jmp copy_user_generic_unrolled",		\
 		      "jmp copy_user_generic_string",		\
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index 28a6654f0d08..b6fcb9a9ddbc 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -6,6 +6,7 @@
  */
 #include <asm/checksum.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 #include <asm/smap.h>
 
 /**
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 46668cda4ffd..0ef5128c2de8 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -35,8 +35,8 @@
 
 	.text
 ENTRY(__get_user_1)
-	GET_THREAD_INFO(%_ASM_DX)
-	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
+	mov PER_CPU_VAR(current_task), %_ASM_DX
+	cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
 	ASM_STAC
 1:	movzbl (%_ASM_AX),%edx
@@ -48,8 +48,8 @@ ENDPROC(__get_user_1)
 ENTRY(__get_user_2)
 	add $1,%_ASM_AX
 	jc bad_get_user
-	GET_THREAD_INFO(%_ASM_DX)
-	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
+	mov PER_CPU_VAR(current_task), %_ASM_DX
+	cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
 	ASM_STAC
 2:	movzwl -1(%_ASM_AX),%edx
@@ -61,8 +61,8 @@ ENDPROC(__get_user_2)
 ENTRY(__get_user_4)
 	add $3,%_ASM_AX
 	jc bad_get_user
-	GET_THREAD_INFO(%_ASM_DX)
-	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
+	mov PER_CPU_VAR(current_task), %_ASM_DX
+	cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
 	ASM_STAC
 3:	movl -3(%_ASM_AX),%edx
@@ -75,8 +75,8 @@ ENTRY(__get_user_8)
 #ifdef CONFIG_X86_64
 	add $7,%_ASM_AX
 	jc bad_get_user
-	GET_THREAD_INFO(%_ASM_DX)
-	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
+	mov PER_CPU_VAR(current_task), %_ASM_DX
+	cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
 	ASM_STAC
 4:	movq -7(%_ASM_AX),%rdx
@@ -86,8 +86,8 @@ ENTRY(__get_user_8)
 #else
 	add $7,%_ASM_AX
 	jc bad_get_user_8
-	GET_THREAD_INFO(%_ASM_DX)
-	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
+	mov PER_CPU_VAR(current_task), %_ASM_DX
+	cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user_8
 	ASM_STAC
 4:	movl -7(%_ASM_AX),%edx
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
new file mode 100644
index 000000000000..02de3d74d2c5
--- /dev/null
+++ b/arch/x86/lib/hweight.S
@@ -0,0 +1,77 @@
+#include <linux/linkage.h>
+
+#include <asm/asm.h>
+
+/*
+ * unsigned int __sw_hweight32(unsigned int w)
+ * %rdi: w
+ */
+ENTRY(__sw_hweight32)
+
+#ifdef CONFIG_X86_64
+	movl %edi, %eax				# w
+#endif
+	__ASM_SIZE(push,) %__ASM_REG(dx)
+	movl %eax, %edx				# w -> t
+	shrl %edx				# t >>= 1
+	andl $0x55555555, %edx			# t &= 0x55555555
+	subl %edx, %eax				# w -= t
+
+	movl %eax, %edx				# w -> t
+	shrl $2, %eax				# w_tmp >>= 2
+	andl $0x33333333, %edx			# t	&= 0x33333333
+	andl $0x33333333, %eax			# w_tmp &= 0x33333333
+	addl %edx, %eax				# w = w_tmp + t
+
+	movl %eax, %edx				# w -> t
+	shrl $4, %edx				# t >>= 4
+	addl %edx, %eax				# w_tmp += t
+	andl  $0x0f0f0f0f, %eax			# w_tmp &= 0x0f0f0f0f
+	imull $0x01010101, %eax, %eax		# w_tmp *= 0x01010101
+	shrl $24, %eax				# w = w_tmp >> 24
+	__ASM_SIZE(pop,) %__ASM_REG(dx)
+	ret
+ENDPROC(__sw_hweight32)
+
+ENTRY(__sw_hweight64)
+#ifdef CONFIG_X86_64
+	pushq   %rdx
+
+	movq    %rdi, %rdx                      # w -> t
+	movabsq $0x5555555555555555, %rax
+	shrq    %rdx                            # t >>= 1
+	andq    %rdx, %rax                      # t &= 0x5555555555555555
+	movabsq $0x3333333333333333, %rdx
+	subq    %rax, %rdi                      # w -= t
+
+	movq    %rdi, %rax                      # w -> t
+	shrq    $2, %rdi                        # w_tmp >>= 2
+	andq    %rdx, %rax                      # t     &= 0x3333333333333333
+	andq    %rdi, %rdx                      # w_tmp &= 0x3333333333333333
+	addq    %rdx, %rax                      # w = w_tmp + t
+
+	movq    %rax, %rdx                      # w -> t
+	shrq    $4, %rdx                        # t >>= 4
+	addq    %rdx, %rax                      # w_tmp += t
+	movabsq $0x0f0f0f0f0f0f0f0f, %rdx
+	andq    %rdx, %rax                      # w_tmp &= 0x0f0f0f0f0f0f0f0f
+	movabsq $0x0101010101010101, %rdx
+	imulq   %rdx, %rax                      # w_tmp *= 0x0101010101010101
+	shrq    $56, %rax                       # w = w_tmp >> 56
+
+	popq    %rdx
+	ret
+#else /* CONFIG_X86_32 */
+	/* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */
+	pushl   %ecx
+
+	call    __sw_hweight32
+	movl    %eax, %ecx                      # stash away result
+	movl    %edx, %eax                      # second part of input
+	call    __sw_hweight32
+	addl    %ecx, %eax                      # result
+
+	popl    %ecx
+	ret
+#endif
+ENDPROC(__sw_hweight64)
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index e0817a12d323..c891ece81e5b 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -29,14 +29,14 @@
  * as they get called from within inline assembly.
  */
 
-#define ENTER	GET_THREAD_INFO(%_ASM_BX)
+#define ENTER	mov PER_CPU_VAR(current_task), %_ASM_BX
 #define EXIT	ASM_CLAC ;	\
 		ret
 
 .text
 ENTRY(__put_user_1)
 	ENTER
-	cmp TI_addr_limit(%_ASM_BX),%_ASM_CX
+	cmp TASK_addr_limit(%_ASM_BX),%_ASM_CX
 	jae bad_put_user
 	ASM_STAC
 1:	movb %al,(%_ASM_CX)
@@ -46,7 +46,7 @@ ENDPROC(__put_user_1)
 
 ENTRY(__put_user_2)
 	ENTER
-	mov TI_addr_limit(%_ASM_BX),%_ASM_BX
+	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
 	sub $1,%_ASM_BX
 	cmp %_ASM_BX,%_ASM_CX
 	jae bad_put_user
@@ -58,7 +58,7 @@ ENDPROC(__put_user_2)
 
 ENTRY(__put_user_4)
 	ENTER
-	mov TI_addr_limit(%_ASM_BX),%_ASM_BX
+	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
 	sub $3,%_ASM_BX
 	cmp %_ASM_BX,%_ASM_CX
 	jae bad_put_user
@@ -70,7 +70,7 @@ ENDPROC(__put_user_4)
 
 ENTRY(__put_user_8)
 	ENTER
-	mov TI_addr_limit(%_ASM_BX),%_ASM_BX
+	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
 	sub $7,%_ASM_BX
 	cmp %_ASM_BX,%_ASM_CX
 	jae bad_put_user
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 0a42327a59d7..9f760cdcaf40 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -6,7 +6,7 @@
  * Copyright 2002 Andi Kleen <ak@suse.de>
  */
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * Zero Userspace