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()
  ...

6 files changed, 17 insertions, 70 deletions

diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 4bb53b8..0f90cc2 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -37,7 +37,7 @@ bool ex_handler_ext(const struct exception_table_entry *fixup,
 		   struct pt_regs *regs, int trapnr)
 {
 	/* Special hack for uaccess_err */
-	current_thread_info()->uaccess_err = 1;
+	current->thread.uaccess_err = 1;
 	regs->ip = ex_fixup_addr(fixup);
 	return true;
 }
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 7d1fa7c..d22161a 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -439,7 +439,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	 * happen within a race in page table update. In the later
 	 * case just flush:
 	 */
-	pgd = pgd_offset(current->active_mm, address);
+	pgd = (pgd_t *)__va(read_cr3()) + pgd_index(address);
 	pgd_ref = pgd_offset_k(address);
 	if (pgd_none(*pgd_ref))
 		return -1;
@@ -737,7 +737,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 		 * In this case we need to make sure we're not recursively
 		 * faulting through the emulate_vsyscall() logic.
 		 */
-		if (current_thread_info()->sig_on_uaccess_error && signal) {
+		if (current->thread.sig_on_uaccess_err && signal) {
 			tsk->thread.trap_nr = X86_TRAP_PF;
 			tsk->thread.error_code = error_code | PF_USER;
 			tsk->thread.cr2 = address;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index bce2e5d..e14f870 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -354,7 +354,7 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
 		 * pagetable pages as RO. So assume someone who pre-setup
 		 * these mappings are more intelligent.
 		 */
-		if (pte_val(*pte)) {
+		if (!pte_none(*pte)) {
 			if (!after_bootmem)
 				pages++;
 			continue;
@@ -396,7 +396,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 			continue;
 		}
 
-		if (pmd_val(*pmd)) {
+		if (!pmd_none(*pmd)) {
 			if (!pmd_large(*pmd)) {
 				spin_lock(&init_mm.page_table_lock);
 				pte = (pte_t *)pmd_page_vaddr(*pmd);
@@ -470,7 +470,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 			continue;
 		}
 
-		if (pud_val(*pud)) {
+		if (!pud_none(*pud)) {
 			if (!pud_large(*pud)) {
 				pmd = pmd_offset(pud, 0);
 				last_map_addr = phys_pmd_init(pmd, addr, end,
@@ -673,7 +673,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
 
 	for (i = 0; i < PTRS_PER_PTE; i++) {
 		pte = pte_start + i;
-		if (pte_val(*pte))
+		if (!pte_none(*pte))
 			return;
 	}
 
@@ -691,7 +691,7 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
 
 	for (i = 0; i < PTRS_PER_PMD; i++) {
 		pmd = pmd_start + i;
-		if (pmd_val(*pmd))
+		if (!pmd_none(*pmd))
 			return;
 	}
 
@@ -702,27 +702,6 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
 	spin_unlock(&init_mm.page_table_lock);
 }
 
-/* Return true if pgd is changed, otherwise return false. */
-static bool __meminit free_pud_table(pud_t *pud_start, pgd_t *pgd)
-{
-	pud_t *pud;
-	int i;
-
-	for (i = 0; i < PTRS_PER_PUD; i++) {
-		pud = pud_start + i;
-		if (pud_val(*pud))
-			return false;
-	}
-
-	/* free a pud table */
-	free_pagetable(pgd_page(*pgd), 0);
-	spin_lock(&init_mm.page_table_lock);
-	pgd_clear(pgd);
-	spin_unlock(&init_mm.page_table_lock);
-
-	return true;
-}
-
 static void __meminit
 remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
 		 bool direct)
@@ -913,7 +892,6 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct)
 	unsigned long addr;
 	pgd_t *pgd;
 	pud_t *pud;
-	bool pgd_changed = false;
 
 	for (addr = start; addr < end; addr = next) {
 		next = pgd_addr_end(addr, end);
@@ -924,13 +902,8 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct)
 
 		pud = (pud_t *)pgd_page_vaddr(*pgd);
 		remove_pud_table(pud, addr, next, direct);
-		if (free_pud_table(pud, pgd))
-			pgd_changed = true;
 	}
 
-	if (pgd_changed)
-		sync_global_pgds(start, end - 1, 1);
-
 	flush_tlb_all();
 }
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 7a1f7bb..47870a5 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -746,18 +746,6 @@ static bool try_to_free_pmd_page(pmd_t *pmd)
 	return true;
 }
 
-static bool try_to_free_pud_page(pud_t *pud)
-{
-	int i;
-
-	for (i = 0; i < PTRS_PER_PUD; i++)
-		if (!pud_none(pud[i]))
-			return false;
-
-	free_page((unsigned long)pud);
-	return true;
-}
-
 static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
 {
 	pte_t *pte = pte_offset_kernel(pmd, start);
@@ -871,16 +859,6 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
 	 */
 }
 
-static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end)
-{
-	pgd_t *pgd_entry = root + pgd_index(addr);
-
-	unmap_pud_range(pgd_entry, addr, end);
-
-	if (try_to_free_pud_page((pud_t *)pgd_page_vaddr(*pgd_entry)))
-		pgd_clear(pgd_entry);
-}
-
 static int alloc_pte_page(pmd_t *pmd)
 {
 	pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
@@ -1113,7 +1091,12 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 
 	ret = populate_pud(cpa, addr, pgd_entry, pgprot);
 	if (ret < 0) {
-		unmap_pgd_range(cpa->pgd, addr,
+		/*
+		 * Leave the PUD page in place in case some other CPU or thread
+		 * already found it, but remove any useless entries we just
+		 * added to it.
+		 */
+		unmap_pud_range(pgd_entry, addr,
 				addr + (cpa->numpages << PAGE_SHIFT));
 		return ret;
 	}
@@ -1185,7 +1168,7 @@ repeat:
 		return __cpa_process_fault(cpa, address, primary);
 
 	old_pte = *kpte;
-	if (!pte_val(old_pte))
+	if (pte_none(old_pte))
 		return __cpa_process_fault(cpa, address, primary);
 
 	if (level == PG_LEVEL_4K) {
@@ -1991,12 +1974,6 @@ out:
 	return retval;
 }
 
-void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
-			       unsigned numpages)
-{
-	unmap_pgd_range(root, address, address + (numpages << PAGE_SHIFT));
-}
-
 /*
  * The testcases use internal knowledge of the implementation that shouldn't
  * be exposed to the rest of the kernel. Include these directly here.
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index fb0604f..db00e3e 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -755,11 +755,8 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 		return 1;
 
 	while (cursor < to) {
-		if (!devmem_is_allowed(pfn)) {
-			pr_info("x86/PAT: Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n",
-				current->comm, from, to - 1);
+		if (!devmem_is_allowed(pfn))
 			return 0;
-		}
 		cursor += PAGE_SIZE;
 		pfn++;
 	}
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 75cc097..e67ae0e6 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -47,7 +47,7 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
 		return;
 	}
 	pte = pte_offset_kernel(pmd, vaddr);
-	if (pte_val(pteval))
+	if (!pte_none(pteval))
 		set_pte_at(&init_mm, vaddr, pte, pteval);
 	else
 		pte_clear(&init_mm, vaddr, pte);