1 files changed, 89 insertions, 31 deletions

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b46e54c2399b..094374c82db0 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -42,6 +42,8 @@
 #include <asm/cmpxchg.h>
 #include <asm/fixmap.h>
 #include <linux/mmdebug.h>
+#include <linux/mm_types.h>
+#include <linux/sched.h>
 
 extern void __pte_error(const char *file, int line, unsigned long val);
 extern void __pmd_error(const char *file, int line, unsigned long val);
@@ -57,9 +59,22 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
 #define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte_val(pte))
 
-#define pte_pfn(pte)		((pte_val(pte) & PHYS_MASK) >> PAGE_SHIFT)
+/*
+ * Macros to convert between a physical address and its placement in a
+ * page table entry, taking care of 52-bit addresses.
+ */
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define __pte_to_phys(pte)	\
+	((pte_val(pte) & PTE_ADDR_LOW) | ((pte_val(pte) & PTE_ADDR_HIGH) << 36))
+#define __phys_to_pte_val(phys)	(((phys) | ((phys) >> 36)) & PTE_ADDR_MASK)
+#else
+#define __pte_to_phys(pte)	(pte_val(pte) & PTE_ADDR_MASK)
+#define __phys_to_pte_val(phys)	(phys)
+#endif
 
-#define pfn_pte(pfn,prot)	(__pte(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define pte_pfn(pte)		(__pte_to_phys(pte) >> PAGE_SHIFT)
+#define pfn_pte(pfn,prot)	\
+	__pte(__phys_to_pte_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 
 #define pte_none(pte)		(!pte_val(pte))
 #define pte_clear(mm,addr,ptep)	set_pte(ptep, __pte(0))
@@ -98,6 +113,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 	((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN))
 #define pte_valid_young(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
+#define pte_valid_user(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
 
 /*
  * Could the pte be present in the TLB? We must check mm_tlb_flush_pending
@@ -107,6 +124,18 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_accessible(mm, pte)	\
 	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte))
 
+/*
+ * p??_access_permitted() is true for valid user mappings (subject to the
+ * write permission check) other than user execute-only which do not have the
+ * PTE_USER bit set. PROT_NONE mappings do not have the PTE_VALID bit set.
+ */
+#define pte_access_permitted(pte, write) \
+	(pte_valid_user(pte) && (!(write) || pte_write(pte)))
+#define pmd_access_permitted(pmd, write) \
+	(pte_access_permitted(pmd_pte(pmd), (write)))
+#define pud_access_permitted(pud, write) \
+	(pte_access_permitted(pud_pte(pud), (write)))
+
 static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot)
 {
 	pte_val(pte) &= ~pgprot_val(prot);
@@ -135,12 +164,20 @@ static inline pte_t pte_mkwrite(pte_t pte)
 
 static inline pte_t pte_mkclean(pte_t pte)
 {
-	return clear_pte_bit(pte, __pgprot(PTE_DIRTY));
+	pte = clear_pte_bit(pte, __pgprot(PTE_DIRTY));
+	pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
+
+	return pte;
 }
 
 static inline pte_t pte_mkdirty(pte_t pte)
 {
-	return set_pte_bit(pte, __pgprot(PTE_DIRTY));
+	pte = set_pte_bit(pte, __pgprot(PTE_DIRTY));
+
+	if (pte_write(pte))
+		pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY));
+
+	return pte;
 }
 
 static inline pte_t pte_mkold(pte_t pte)
@@ -193,9 +230,6 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 	}
 }
 
-struct mm_struct;
-struct vm_area_struct;
-
 extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
 
 /*
@@ -224,7 +258,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 * hardware updates of the pte (ptep_set_access_flags safely changes
 	 * valid ptes without going through an invalid entry).
 	 */
-	if (pte_valid(*ptep) && pte_valid(pte)) {
+	if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(*ptep) && pte_valid(pte) &&
+	   (mm == current->active_mm || atomic_read(&mm->mm_users) > 1)) {
 		VM_WARN_ONCE(!pte_young(pte),
 			     "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
 			     __func__, pte_val(*ptep), pte_val(pte));
@@ -270,6 +305,11 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b)
 
 #define __HAVE_ARCH_PTE_SPECIAL
 
+static inline pte_t pgd_pte(pgd_t pgd)
+{
+	return __pte(pgd_val(pgd));
+}
+
 static inline pte_t pud_pte(pud_t pud)
 {
 	return __pte(pud_val(pud));
@@ -331,20 +371,28 @@ static inline int pmd_protnone(pmd_t pmd)
 
 #define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))
 
-#define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
 
-#define pmd_pfn(pmd)		(((pmd_val(pmd) & PMD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
-#define pfn_pmd(pfn,prot)	(__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define __pmd_to_phys(pmd)	__pte_to_phys(pmd_pte(pmd))
+#define __phys_to_pmd_val(phys)	__phys_to_pte_val(phys)
+#define pmd_pfn(pmd)		((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT)
+#define pfn_pmd(pfn,prot)	__pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 #define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
 #define pud_write(pud)		pte_write(pud_pte(pud))
-#define pud_pfn(pud)		(((pud_val(pud) & PUD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
+
+#define __pud_to_phys(pud)	__pte_to_phys(pud_pte(pud))
+#define __phys_to_pud_val(phys)	__phys_to_pte_val(phys)
+#define pud_pfn(pud)		((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
+#define pfn_pud(pfn,prot)	__pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 
 #define set_pmd_at(mm, addr, pmdp, pmd)	set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
 
+#define __pgd_to_phys(pgd)	__pte_to_phys(pgd_pte(pgd))
+#define __phys_to_pgd_val(phys)	__phys_to_pte_val(phys)
+
 #define __pgprot_modify(prot,mask,bits) \
 	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
 
@@ -395,7 +443,7 @@ static inline void pmd_clear(pmd_t *pmdp)
 
 static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
 {
-	return pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK;
+	return __pmd_to_phys(pmd);
 }
 
 /* Find an entry in the third-level page table. */
@@ -413,7 +461,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
 #define pte_set_fixmap_offset(pmd, addr)	pte_set_fixmap(pte_offset_phys(pmd, addr))
 #define pte_clear_fixmap()		clear_fixmap(FIX_PTE)
 
-#define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
+#define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(__pmd_to_phys(pmd)))
 
 /* use ONLY for statically allocated translation tables */
 #define pte_offset_kimg(dir,addr)	((pte_t *)__phys_to_kimg(pte_offset_phys((dir), (addr))))
@@ -446,7 +494,7 @@ static inline void pud_clear(pud_t *pudp)
 
 static inline phys_addr_t pud_page_paddr(pud_t pud)
 {
-	return pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK;
+	return __pud_to_phys(pud);
 }
 
 /* Find an entry in the second-level page table. */
@@ -459,7 +507,7 @@ static inline phys_addr_t pud_page_paddr(pud_t pud)
 #define pmd_set_fixmap_offset(pud, addr)	pmd_set_fixmap(pmd_offset_phys(pud, addr))
 #define pmd_clear_fixmap()		clear_fixmap(FIX_PMD)
 
-#define pud_page(pud)		pfn_to_page(__phys_to_pfn(pud_val(pud) & PHYS_MASK))
+#define pud_page(pud)		pfn_to_page(__phys_to_pfn(__pud_to_phys(pud)))
 
 /* use ONLY for statically allocated translation tables */
 #define pmd_offset_kimg(dir,addr)	((pmd_t *)__phys_to_kimg(pmd_offset_phys((dir), (addr))))
@@ -498,7 +546,7 @@ static inline void pgd_clear(pgd_t *pgdp)
 
 static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
 {
-	return pgd_val(pgd) & PHYS_MASK & (s32)PAGE_MASK;
+	return __pgd_to_phys(pgd);
 }
 
 /* Find an entry in the frst-level page table. */
@@ -511,7 +559,7 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
 #define pud_set_fixmap_offset(pgd, addr)	pud_set_fixmap(pud_offset_phys(pgd, addr))
 #define pud_clear_fixmap()		clear_fixmap(FIX_PUD)
 
-#define pgd_page(pgd)		pfn_to_page(__phys_to_pfn(pgd_val(pgd) & PHYS_MASK))
+#define pgd_page(pgd)		pfn_to_page(__phys_to_pfn(__pgd_to_phys(pgd)))
 
 /* use ONLY for statically allocated translation tables */
 #define pud_offset_kimg(dir,addr)	((pud_t *)__phys_to_kimg(pud_offset_phys((dir), (addr))))
@@ -628,28 +676,23 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 /*
- * ptep_set_wrprotect - mark read-only while preserving the hardware update of
- * the Access Flag.
+ * ptep_set_wrprotect - mark read-only while trasferring potential hardware
+ * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit.
  */
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
 {
 	pte_t old_pte, pte;
 
-	/*
-	 * ptep_set_wrprotect() is only called on CoW mappings which are
-	 * private (!VM_SHARED) with the pte either read-only (!PTE_WRITE &&
-	 * PTE_RDONLY) or writable and software-dirty (PTE_WRITE &&
-	 * !PTE_RDONLY && PTE_DIRTY); see is_cow_mapping() and
-	 * protection_map[]. There is no race with the hardware update of the
-	 * dirty state: clearing of PTE_RDONLY when PTE_WRITE (a.k.a. PTE_DBM)
-	 * is set.
-	 */
-	VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(*ptep),
-		     "%s: potential race with hardware DBM", __func__);
 	pte = READ_ONCE(*ptep);
 	do {
 		old_pte = pte;
+		/*
+		 * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY
+		 * clear), set the PTE_DIRTY bit.
+		 */
+		if (pte_hw_dirty(pte))
+			pte = pte_mkdirty(pte);
 		pte = pte_wrprotect(pte);
 		pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
 					       pte_val(old_pte), pte_val(pte));
@@ -663,10 +706,19 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 {
 	ptep_set_wrprotect(mm, address, (pte_t *)pmdp);
 }
+
+#define pmdp_establish pmdp_establish
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+	return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd)));
+}
 #endif
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+extern pgd_t swapper_pg_end[];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
+extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
 
 /*
  * Encode and decode a swap entry:
@@ -720,6 +772,12 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 #define kc_vaddr_to_offset(v)	((v) & ~VA_START)
 #define kc_offset_to_vaddr(o)	((o) | VA_START)
 
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define phys_to_ttbr(addr)	(((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52)
+#else
+#define phys_to_ttbr(addr)	(addr)
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_PGTABLE_H */