[RFC 02/20] mm/mprotect: use mmu_gather

[Nadav Amit <nadav.amit@gmail.com>]

From: Nadav Amit <namit@vmware.com>

change_pXX_range() currently does not use mmu_gather, but instead
implements its own deferred TLB flushes scheme. This both complicates
the code, as developers need to be aware of different invalidation
schemes, and prevents.

Use mmu_gather in change_pXX_range(). As the pages are not released,
only record the flushed range using tlb_flush_pXX_range().

Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Nick Piggin <npiggin@gmail.com>
Cc: x86@kernel.org
---
 include/linux/huge_mm.h |  3 ++-
 mm/huge_memory.c        |  4 +++-
 mm/mprotect.c           | 51 ++++++++++++++++++++---------------------
 3 files changed, 30 insertions(+), 28 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 6a19f35f836b..6eff7f59a778 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -37,7 +37,8 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud,
 bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		   unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd);
 int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr,
-		    pgprot_t newprot, unsigned long cp_flags);
+		    pgprot_t newprot, unsigned long cp_flags,
+		    struct mmu_gather *tlb);
 vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn,
 				   pgprot_t pgprot, bool write);
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9237976abe72..c345b8b06183 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1797,7 +1797,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
  *  - HPAGE_PMD_NR is protections changed and TLB flush necessary
  */
 int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, pgprot_t newprot, unsigned long cp_flags)
+		unsigned long addr, pgprot_t newprot, unsigned long cp_flags,
+		struct mmu_gather *tlb)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	spinlock_t *ptl;
@@ -1885,6 +1886,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		entry = pmd_clear_uffd_wp(entry);
 	}
 	ret = HPAGE_PMD_NR;
+	tlb_flush_pmd_range(tlb, addr, HPAGE_PMD_SIZE);
 	set_pmd_at(mm, addr, pmd, entry);
 	BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry));
 unlock:
diff --git a/mm/mprotect.c b/mm/mprotect.c
index ab709023e9aa..632d5a677d3f 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -32,12 +32,13 @@
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
+#include <asm/tlb.h>
 
 #include "internal.h"
 
-static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, unsigned long end, pgprot_t newprot,
-		unsigned long cp_flags)
+static unsigned long change_pte_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
@@ -138,6 +139,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				ptent = pte_mkwrite(ptent);
 			}
 			ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
+			tlb_flush_pte_range(tlb, addr, PAGE_SIZE);
 			pages++;
 		} else if (is_swap_pte(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
@@ -209,9 +211,9 @@ static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd)
 	return 0;
 }
 
-static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
-		pud_t *pud, unsigned long addr, unsigned long end,
-		pgprot_t newprot, unsigned long cp_flags)
+static inline unsigned long change_pmd_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pud_t *pud, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -252,7 +254,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 				__split_huge_pmd(vma, pmd, addr, false, NULL);
 			} else {
 				int nr_ptes = change_huge_pmd(vma, pmd, addr,
-							      newprot, cp_flags);
+							      newprot, cp_flags, tlb);
 
 				if (nr_ptes) {
 					if (nr_ptes == HPAGE_PMD_NR) {
@@ -266,8 +268,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 			}
 			/* fall through, the trans huge pmd just split */
 		}
-		this_pages = change_pte_range(vma, pmd, addr, next, newprot,
-					      cp_flags);
+		this_pages = change_pte_range(tlb, vma, pmd, addr, next,
+					      newprot, cp_flags);
 		pages += this_pages;
 next:
 		cond_resched();
@@ -281,9 +283,9 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 	return pages;
 }
 
-static inline unsigned long change_pud_range(struct vm_area_struct *vma,
-		p4d_t *p4d, unsigned long addr, unsigned long end,
-		pgprot_t newprot, unsigned long cp_flags)
+static inline unsigned long change_pud_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -294,16 +296,16 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma,
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
 			continue;
-		pages += change_pmd_range(vma, pud, addr, next, newprot,
+		pages += change_pmd_range(tlb, vma, pud, addr, next, newprot,
 					  cp_flags);
 	} while (pud++, addr = next, addr != end);
 
 	return pages;
 }
 
-static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
-		pgd_t *pgd, unsigned long addr, unsigned long end,
-		pgprot_t newprot, unsigned long cp_flags)
+static inline unsigned long change_p4d_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	p4d_t *p4d;
 	unsigned long next;
@@ -314,7 +316,7 @@ static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
 		next = p4d_addr_end(addr, end);
 		if (p4d_none_or_clear_bad(p4d))
 			continue;
-		pages += change_pud_range(vma, p4d, addr, next, newprot,
+		pages += change_pud_range(tlb, vma, p4d, addr, next, newprot,
 					  cp_flags);
 	} while (p4d++, addr = next, addr != end);
 
@@ -328,25 +330,22 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
 	unsigned long next;
-	unsigned long start = addr;
 	unsigned long pages = 0;
+	struct mmu_gather tlb;
 
 	BUG_ON(addr >= end);
 	pgd = pgd_offset(mm, addr);
-	flush_cache_range(vma, addr, end);
-	inc_tlb_flush_pending(mm);
+	tlb_gather_mmu(&tlb, mm);
+	tlb_start_vma(&tlb, vma);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		pages += change_p4d_range(vma, pgd, addr, next, newprot,
+		pages += change_p4d_range(&tlb, vma, pgd, addr, next, newprot,
 					  cp_flags);
 	} while (pgd++, addr = next, addr != end);
-
-	/* Only flush the TLB if we actually modified any entries: */
-	if (pages)
-		flush_tlb_range(vma, start, end);
-	dec_tlb_flush_pending(mm);
+	tlb_end_vma(&tlb, vma);
+	tlb_finish_mmu(&tlb);
 
 	return pages;
 }
-- 
2.25.1