Merge branch 'x86/urgent' into x86/mm, to pick up dependent fix

Signed-off-by: Ingo Molnar <mingo@kernel.org>

7 files changed, 93 insertions, 50 deletions

diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index ae9a37b..6d5eb59 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -9,6 +9,7 @@
 #include <linux/vmstat.h>
 #include <linux/highmem.h>
 #include <linux/swap.h>
+#include <linux/memremap.h>
 
 #include <asm/pgtable.h>
 
@@ -63,6 +64,16 @@ retry:
 #endif
 }
 
+static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages)
+{
+	while ((*nr) - nr_start) {
+		struct page *page = pages[--(*nr)];
+
+		ClearPageReferenced(page);
+		put_page(page);
+	}
+}
+
 /*
  * The performance critical leaf functions are made noinline otherwise gcc
  * inlines everything into a single function which results in too much
@@ -71,7 +82,9 @@ retry:
 static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
+	struct dev_pagemap *pgmap = NULL;
 	unsigned long mask;
+	int nr_start = *nr;
 	pte_t *ptep;
 
 	mask = _PAGE_PRESENT|_PAGE_USER;
@@ -89,13 +102,21 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 			return 0;
 		}
 
-		if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
+		page = pte_page(pte);
+		if (pte_devmap(pte)) {
+			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
+			if (unlikely(!pgmap)) {
+				undo_dev_pagemap(nr, nr_start, pages);
+				pte_unmap(ptep);
+				return 0;
+			}
+		} else if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
 			pte_unmap(ptep);
 			return 0;
 		}
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-		page = pte_page(pte);
 		get_page(page);
+		put_dev_pagemap(pgmap);
 		SetPageReferenced(page);
 		pages[*nr] = page;
 		(*nr)++;
@@ -114,6 +135,32 @@ static inline void get_head_page_multiple(struct page *page, int nr)
 	SetPageReferenced(page);
 }
 
+static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr,
+		unsigned long end, struct page **pages, int *nr)
+{
+	int nr_start = *nr;
+	unsigned long pfn = pmd_pfn(pmd);
+	struct dev_pagemap *pgmap = NULL;
+
+	pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;
+	do {
+		struct page *page = pfn_to_page(pfn);
+
+		pgmap = get_dev_pagemap(pfn, pgmap);
+		if (unlikely(!pgmap)) {
+			undo_dev_pagemap(nr, nr_start, pages);
+			return 0;
+		}
+		SetPageReferenced(page);
+		pages[*nr] = page;
+		get_page(page);
+		put_dev_pagemap(pgmap);
+		(*nr)++;
+		pfn++;
+	} while (addr += PAGE_SIZE, addr != end);
+	return 1;
+}
+
 static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
@@ -126,9 +173,13 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 		mask |= _PAGE_RW;
 	if ((pmd_flags(pmd) & mask) != mask)
 		return 0;
+
+	VM_BUG_ON(!pfn_valid(pmd_pfn(pmd)));
+	if (pmd_devmap(pmd))
+		return __gup_device_huge_pmd(pmd, addr, end, pages, nr);
+
 	/* hugepages are never "special" */
 	VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL);
-	VM_BUG_ON(!pfn_valid(pmd_pfn(pmd)));
 
 	refs = 0;
 	head = pmd_page(pmd);
@@ -136,8 +187,6 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
-		if (PageTail(page))
-			get_huge_page_tail(page);
 		(*nr)++;
 		page++;
 		refs++;
@@ -158,18 +207,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		pmd_t pmd = *pmdp;
 
 		next = pmd_addr_end(addr, end);
-		/*
-		 * The pmd_trans_splitting() check below explains why
-		 * pmdp_splitting_flush has to flush the tlb, to stop
-		 * this gup-fast code from running while we set the
-		 * splitting bit in the pmd. Returning zero will take
-		 * the slow path that will call wait_split_huge_page()
-		 * if the pmd is still in splitting state. gup-fast
-		 * can't because it has irq disabled and
-		 * wait_split_huge_page() would never return as the
-		 * tlb flush IPI wouldn't run.
-		 */
-		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
+		if (pmd_none(pmd))
 			return 0;
 		if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) {
 			/*
@@ -212,8 +250,6 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr,
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
-		if (PageTail(page))
-			get_huge_page_tail(page);
 		(*nr)++;
 		page++;
 		refs++;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 8f18fec..9686535 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -30,6 +30,7 @@
 #include <linux/module.h>
 #include <linux/memory.h>
 #include <linux/memory_hotplug.h>
+#include <linux/memremap.h>
 #include <linux/nmi.h>
 #include <linux/gfp.h>
 #include <linux/kcore.h>
@@ -715,6 +716,12 @@ static void __meminit free_pagetable(struct page *page, int order)
 {
 	unsigned long magic;
 	unsigned int nr_pages = 1 << order;
+	struct vmem_altmap *altmap = to_vmem_altmap((unsigned long) page);
+
+	if (altmap) {
+		vmem_altmap_free(altmap, nr_pages);
+		return;
+	}
 
 	/* bootmem page has reserved flag */
 	if (PageReserved(page)) {
@@ -1018,13 +1025,19 @@ int __ref arch_remove_memory(u64 start, u64 size)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
+	struct page *page = pfn_to_page(start_pfn);
+	struct vmem_altmap *altmap;
 	struct zone *zone;
 	int ret;
 
-	zone = page_zone(pfn_to_page(start_pfn));
-	kernel_physical_mapping_remove(start, start + size);
+	/* With altmap the first mapped page is offset from @start */
+	altmap = to_vmem_altmap((unsigned long) page);
+	if (altmap)
+		page += vmem_altmap_offset(altmap);
+	zone = page_zone(page);
 	ret = __remove_pages(zone, start_pfn, nr_pages);
 	WARN_ON_ONCE(ret);
+	kernel_physical_mapping_remove(start, start + size);
 
 	return ret;
 }
@@ -1223,7 +1236,7 @@ static void __meminitdata *p_start, *p_end;
 static int __meminitdata node_start;
 
 static int __meminit vmemmap_populate_hugepages(unsigned long start,
-						unsigned long end, int node)
+		unsigned long end, int node, struct vmem_altmap *altmap)
 {
 	unsigned long addr;
 	unsigned long next;
@@ -1246,7 +1259,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start,
 		if (pmd_none(*pmd)) {
 			void *p;
 
-			p = vmemmap_alloc_block_buf(PMD_SIZE, node);
+			p = __vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
 			if (p) {
 				pte_t entry;
 
@@ -1267,7 +1280,8 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start,
 				addr_end = addr + PMD_SIZE;
 				p_end = p + PMD_SIZE;
 				continue;
-			}
+			} else if (altmap)
+				return -ENOMEM; /* no fallback */
 		} else if (pmd_large(*pmd)) {
 			vmemmap_verify((pte_t *)pmd, node, addr, next);
 			continue;
@@ -1281,11 +1295,16 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start,
 
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 {
+	struct vmem_altmap *altmap = to_vmem_altmap(start);
 	int err;
 
 	if (cpu_has_pse)
-		err = vmemmap_populate_hugepages(start, end, node);
-	else
+		err = vmemmap_populate_hugepages(start, end, node, altmap);
+	else if (altmap) {
+		pr_err_once("%s: no cpu support for altmap allocations\n",
+				__func__);
+		err = -ENOMEM;
+	} else
 		err = vmemmap_populate_basepages(start, end, node);
 	if (!err)
 		sync_global_pgds(start, end - 1, 0);
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 844b06d..96bd1e2 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -69,14 +69,14 @@ unsigned long arch_mmap_rnd(void)
 {
 	unsigned long rnd;
 
-	/*
-	 *  8 bits of randomness in 32bit mmaps, 20 address space bits
-	 * 28 bits of randomness in 64bit mmaps, 40 address space bits
-	 */
 	if (mmap_is_ia32())
-		rnd = (unsigned long)get_random_int() % (1<<8);
+#ifdef CONFIG_COMPAT
+		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1);
+#else
+		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1);
+#endif
 	else
-		rnd = (unsigned long)get_random_int() % (1<<28);
+		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1);
 
 	return rnd << PAGE_SHIFT;
 }
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index c3b3f65..d04f809 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -469,7 +469,7 @@ static void __init numa_clear_kernel_node_hotplug(void)
 {
 	int i, nid;
 	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
-	unsigned long start, end;
+	phys_addr_t start, end;
 	struct memblock_region *r;
 
 	/*
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index fc6a4c8..2440814 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -33,7 +33,7 @@ struct cpa_data {
 	pgd_t		*pgd;
 	pgprot_t	mask_set;
 	pgprot_t	mask_clr;
-	int		numpages;
+	unsigned long	numpages;
 	int		flags;
 	unsigned long	pfn;
 	unsigned	force_split : 1;
@@ -1350,7 +1350,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
 		 * CPA operation. Either a large page has been
 		 * preserved or a single page update happened.
 		 */
-		BUG_ON(cpa->numpages > numpages);
+		BUG_ON(cpa->numpages > numpages || !cpa->numpages);
 		numpages -= cpa->numpages;
 		if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY))
 			cpa->curpage++;
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 031782e..f4ae536 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -12,6 +12,7 @@
 #include <linux/debugfs.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/pfn_t.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
@@ -949,7 +950,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 }
 
 int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
-		     unsigned long pfn)
+		     pfn_t pfn)
 {
 	enum page_cache_mode pcm;
 
@@ -957,7 +958,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
 		return 0;
 
 	/* Set prot based on lookup */
-	pcm = lookup_memtype((resource_size_t)pfn << PAGE_SHIFT);
+	pcm = lookup_memtype(pfn_t_to_phys(pfn));
 	*prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
 			 cachemode2protval(pcm));
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index ee9c2e3..4eb287e 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -505,19 +505,6 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma,
 
 	return young;
 }
-
-void pmdp_splitting_flush(struct vm_area_struct *vma,
-			  unsigned long address, pmd_t *pmdp)
-{
-	int set;
-	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	set = !test_and_set_bit(_PAGE_BIT_SPLITTING,
-				(unsigned long *)pmdp);
-	if (set) {
-		/* need tlb flush only to serialize against gup-fast */
-		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
-	}
-}
 #endif
 
 /**