[PATCH v5 7/7] arm64: Add batched versions of ptep_modify_prot_start/commit

[Dev Jain]

Override the generic definition of modify_prot_start_ptes() to use
get_and_clear_full_ptes(). This helper does a TLBI only for the starting
and ending contpte block of the range, whereas the current implementation
will call ptep_get_and_clear() for every contpte block, thus doing a
TLBI on every contpte block. Therefore, we have a performance win.

The arm64 definition of pte_accessible() allows us to batch in the
errata specific case:

#define pte_accessible(mm, pte)	\
	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte))

All ptes are obviously present in the folio batch, and they are also valid.

Override the generic definition of modify_prot_commit_ptes() to simply
use set_ptes() to map the new ptes into the pagetable.

Reviewed-by: Ryan Roberts <ryan.roberts at arm.com>
Signed-off-by: Dev Jain <dev.jain at arm.com>
---
 arch/arm64/include/asm/pgtable.h | 10 ++++++++++
 arch/arm64/mm/mmu.c              | 28 +++++++++++++++++++++++-----
 2 files changed, 33 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index ba63c8736666..abd2dee416b3 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1643,6 +1643,16 @@ extern void ptep_modify_prot_commit(struct vm_area_struct *vma,
 				    unsigned long addr, pte_t *ptep,
 				    pte_t old_pte, pte_t new_pte);
 
+#define modify_prot_start_ptes modify_prot_start_ptes
+extern pte_t modify_prot_start_ptes(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep,
+				    unsigned int nr);
+
+#define modify_prot_commit_ptes modify_prot_commit_ptes
+extern void modify_prot_commit_ptes(struct vm_area_struct *vma, unsigned long addr,
+				    pte_t *ptep, pte_t old_pte, pte_t pte,
+				    unsigned int nr);
+
 #ifdef CONFIG_ARM64_CONTPTE
 
 /*
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 3d5fb37424ab..abd9725796e9 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -26,6 +26,7 @@
 #include <linux/set_memory.h>
 #include <linux/kfence.h>
 #include <linux/pkeys.h>
+#include <linux/mm_inline.h>
 
 #include <asm/barrier.h>
 #include <asm/cputype.h>
@@ -1524,24 +1525,41 @@ static int __init prevent_bootmem_remove_init(void)
 early_initcall(prevent_bootmem_remove_init);
 #endif
 
-pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+pte_t modify_prot_start_ptes(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t *ptep, unsigned int nr)
 {
+	pte_t pte = get_and_clear_full_ptes(vma->vm_mm, addr, ptep, nr, /* full = */ 0);
+
 	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
 		/*
 		 * Break-before-make (BBM) is required for all user space mappings
 		 * when the permission changes from executable to non-executable
 		 * in cases where cpu is affected with errata #2645198.
 		 */
-		if (pte_user_exec(ptep_get(ptep)))
-			return ptep_clear_flush(vma, addr, ptep);
+		if (pte_accessible(vma->vm_mm, pte) && pte_user_exec(pte))
+			__flush_tlb_range(vma, addr, nr * PAGE_SIZE,
+					  PAGE_SIZE, true, 3);
 	}
-	return ptep_get_and_clear(vma->vm_mm, addr, ptep);
+
+	return pte;
+}
+
+pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+	return modify_prot_start_ptes(vma, addr, ptep, 1);
+}
+
+void modify_prot_commit_ptes(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t *ptep, pte_t old_pte, pte_t pte,
+			     unsigned int nr)
+{
+	set_ptes(vma->vm_mm, addr, ptep, pte, nr);
 }
 
 void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
 			     pte_t old_pte, pte_t pte)
 {
-	set_pte_at(vma->vm_mm, addr, ptep, pte);
+	modify_prot_commit_ptes(vma, addr, ptep, old_pte, pte, 1);
 }
 
 /*
-- 
2.30.2