hugetlb: pass vma into huge_pte_alloc() and huge_pmd_share()

Patch series "hugetlb: Disable huge pmd unshare for uffd-wp", v4.

This series tries to disable huge pmd unshare of hugetlbfs backed memory
for uffd-wp.  Although uffd-wp of hugetlbfs is still during rfc stage,
the idea of this series may be needed for multiple tasks (Axel's uffd
minor fault series, and Mike's soft dirty series), so I picked it out
from the larger series.

This patch (of 4):

It is a preparation work to be able to behave differently in the per
architecture huge_pte_alloc() according to different VMA attributes.

Pass it deeper into huge_pmd_share() so that we can avoid the find_vma() call.

[peterx@redhat.com: build fix]
  Link: https://lkml.kernel.org/r/20210304164653.GB397383@xz-x1Link: https://lkml.kernel.org/r/20210218230633.15028-1-peterx@redhat.com

Link: https://lkml.kernel.org/r/20210218230633.15028-2-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Suggested-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Price <steven.price@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

11 files changed, 24 insertions, 20 deletions

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 55ecf6de9ff7..6e3bcffe2837 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -252,7 +252,7 @@ void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
 		set_pte(ptep, pte);
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 		      unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgdp;
@@ -286,7 +286,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	} else if (sz == PMD_SIZE) {
 		if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) &&
 		    pud_none(READ_ONCE(*pudp)))
-			ptep = huge_pmd_share(mm, addr, pudp);
+			ptep = huge_pmd_share(mm, vma, addr, pudp);
 		else
 			ptep = (pte_t *)pmd_alloc(mm, pudp, addr);
 	} else if (sz == (CONT_PMD_SIZE)) {
diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index b331f94d20ac..f993cb36c062 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -25,7 +25,8 @@ unsigned int hpage_shift = HPAGE_SHIFT_DEFAULT;
 EXPORT_SYMBOL(hpage_shift);
 
 pte_t *
-huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
+huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+	       unsigned long addr, unsigned long sz)
 {
 	unsigned long taddr = htlbpage_to_page(addr);
 	pgd_t *pgd;
diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c
index b9f76f433617..7eaff5b07873 100644
--- a/arch/mips/mm/hugetlbpage.c
+++ b/arch/mips/mm/hugetlbpage.c
@@ -21,8 +21,8 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr,
-		      unsigned long sz)
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index 43652de5f139..d1d3990b83f6 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -44,7 +44,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 }
 
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index d142b76d507d..9a75ba078e1b 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -106,7 +106,8 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
  * At this point we do the placement change only for BOOK3S 64. This would
  * possibly work on other subarchs.
  */
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, unsigned long sz)
 {
 	pgd_t *pg;
 	p4d_t *p4;
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 3b5a4d25ca9b..da36d13ffc16 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -189,7 +189,7 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 	return pte;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgdp;
diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c
index 220d7bc43d2b..999ab5916e69 100644
--- a/arch/sh/mm/hugetlbpage.c
+++ b/arch/sh/mm/hugetlbpage.c
@@ -21,7 +21,7 @@
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index ad4b42f04988..04d8790f6c32 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -279,7 +279,7 @@ unsigned long pud_leaf_size(pud_t pud) { return 1UL << tte_to_shift(*(pte_t *)&p
 unsigned long pmd_leaf_size(pmd_t pmd) { return 1UL << tte_to_shift(*(pte_t *)&pmd); }
 unsigned long pte_leaf_size(pte_t pte) { return 1UL << tte_to_shift(pte); }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index cccd1aab69dd..653ef322fac9 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -152,7 +152,8 @@ void hugetlb_fix_reserve_counts(struct inode *inode);
 extern struct mutex *hugetlb_fault_mutex_table;
 u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx);
 
-pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
+pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, pud_t *pud);
 
 struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage);
 
@@ -161,7 +162,7 @@ extern struct list_head huge_boot_pages;
 
 /* arch callbacks */
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz);
 pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6c72433bec1e..a02a651088d3 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3795,7 +3795,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		src_pte = huge_pte_offset(src, addr, sz);
 		if (!src_pte)
 			continue;
-		dst_pte = huge_pte_alloc(dst, addr, sz);
+		dst_pte = huge_pte_alloc(dst, vma, addr, sz);
 		if (!dst_pte) {
 			ret = -ENOMEM;
 			break;
@@ -4563,7 +4563,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	mapping = vma->vm_file->f_mapping;
 	i_mmap_lock_read(mapping);
-	ptep = huge_pte_alloc(mm, haddr, huge_page_size(h));
+	ptep = huge_pte_alloc(mm, vma, haddr, huge_page_size(h));
 	if (!ptep) {
 		i_mmap_unlock_read(mapping);
 		return VM_FAULT_OOM;
@@ -5370,9 +5370,9 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
  * if !vma_shareable check at the beginning of the routine. i_mmap_rwsem is
  * only required for subsequent processing.
  */
-pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, pud_t *pud)
 {
-	struct vm_area_struct *vma = find_vma(mm, addr);
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) +
 			vma->vm_pgoff;
@@ -5450,7 +5450,8 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 #define want_pmd_share()	(1)
 #else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
-pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, pud_t *pud)
 {
 	return NULL;
 }
@@ -5469,7 +5470,7 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
 
 #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
@@ -5488,7 +5489,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		} else {
 			BUG_ON(sz != PMD_SIZE);
 			if (want_pmd_share() && pud_none(*pud))
-				pte = huge_pmd_share(mm, addr, pud);
+				pte = huge_pmd_share(mm, vma, addr, pud);
 			else
 				pte = (pte_t *)pmd_alloc(mm, pud, addr);
 		}
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 9a3d451402d7..063cbb17e8d8 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -290,7 +290,7 @@ retry:
 		mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 		err = -ENOMEM;
-		dst_pte = huge_pte_alloc(dst_mm, dst_addr, vma_hpagesize);
+		dst_pte = huge_pte_alloc(dst_mm, dst_vma, dst_addr, vma_hpagesize);
 		if (!dst_pte) {
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			i_mmap_unlock_read(mapping);