Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Nadav Amit <nadav.amit@gmail.com>
To:     Andrew Morton <akpm@linux-foundation.org>
Cc:     LKML <linux-kernel@vger.kernel.org>, Linux-MM <linux-mm@kvack.org>,
        Peter Xu <peterx@redhat.com>, Nadav Amit <namit@vmware.com>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Andrew Cooper <andrew.cooper3@citrix.com>,
        Andy Lutomirski <luto@kernel.org>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Will Deacon <will@kernel.org>, Yu Zhao <yuzhao@google.com>,
        Nick Piggin <npiggin@gmail.com>, x86@kernel.org
Subject: [PATCH 1/2] mm/mprotect: use mmu_gather
Date:   Sat, 25 Sep 2021 13:54:22 -0700
Message-Id: <20210925205423.168858-2-namit@vmware.com>
In-Reply-To: <20210925205423.168858-1-namit@vmware.com>
References: <20210925205423.168858-1-namit@vmware.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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 opportunities to avoid TLB flushes or perform them
in finer granularity.

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

Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.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
Signed-off-by: Nadav Amit <namit@vmware.com>
---
 mm/mprotect.c | 50 ++++++++++++++++++++++++++++----------------------
 1 file changed, 28 insertions(+), 22 deletions(-)

diff --git a/mm/mprotect.c b/mm/mprotect.c
index 883e2cc85cad..075ff94aa51c 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);
@@ -219,9 +221,9 @@ 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;
@@ -261,6 +263,10 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 			if (next - addr != HPAGE_PMD_SIZE) {
 				__split_huge_pmd(vma, pmd, addr, false, NULL);
 			} else {
+				/*
+				 * change_huge_pmd() does not defer TLB flushes,
+				 * so no need to propagate the tlb argument.
+				 */
 				int nr_ptes = change_huge_pmd(vma, pmd, addr,
 							      newprot, cp_flags);
 
@@ -276,8 +282,8 @@ 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();
@@ -291,9 +297,9 @@ 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;
@@ -304,16 +310,16 @@ 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;
@@ -324,7 +330,7 @@ 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);
 
@@ -338,25 +344,25 @@ 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