arm64: add support for folded p4d page tables

Implement primitives necessary for the 4th level folding, add walks of p4d
level where appropriate, replace 5level-fixup.h with pgtable-nop4d.h and
remove __ARCH_USE_5LEVEL_HACK.

[arnd@arndb.de: fix gcc-10 shift warning]
  Link: http://lkml.kernel.org/r/20200429185657.4085975-1-arnd@arndb.deSigned-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Brian Cain <bcain@codeaurora.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Guan Xuetao <gxt@pku.edu.cn>
Cc: James Morse <james.morse@arm.com>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Julien Thierry <julien.thierry.kdev@gmail.com>
Cc: Ley Foon Tan <ley.foon.tan@intel.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/20200414153455.21744-4-rppt@kernel.orgSigned-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/arm64/include/asm/kvm_mmu.h

@@ -172,8 +172,8 @@ void kvm_clear_hyp_idmap(void);
 	__pmd(__phys_to_pmd_val(__pa(ptep)) | PMD_TYPE_TABLE)
 #define kvm_mk_pud(pmdp)					\
 	__pud(__phys_to_pud_val(__pa(pmdp)) | PMD_TYPE_TABLE)
-#define kvm_mk_pgd(pudp)					\
-	__pgd(__phys_to_pgd_val(__pa(pudp)) | PUD_TYPE_TABLE)
+#define kvm_mk_p4d(pmdp)					\
+	__p4d(__phys_to_p4d_val(__pa(pmdp)) | PUD_TYPE_TABLE)
 
 #define kvm_set_pud(pudp, pud)		set_pud(pudp, pud)
 
@@ -299,6 +299,12 @@ static inline bool kvm_s2pud_young(pud_t pud)
 #define hyp_pud_table_empty(pudp) kvm_page_empty(pudp)
 #endif
 
+#ifdef __PAGETABLE_P4D_FOLDED
+#define hyp_p4d_table_empty(p4dp) (0)
+#else
+#define hyp_p4d_table_empty(p4dp) kvm_page_empty(p4dp)
+#endif
+
 struct kvm;
 
 #define kvm_flush_dcache_to_poc(a,l)	__flush_dcache_area((a), (l))

arch/arm64/include/asm/pgalloc.h

@@ -73,17 +73,17 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pudp)
 	free_page((unsigned long)pudp);
 }
 
-static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot)
+static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot)
 {
-	set_pgd(pgdp, __pgd(__phys_to_pgd_val(pudp) | prot));
+	set_p4d(p4dp, __p4d(__phys_to_p4d_val(pudp) | prot));
 }
 
-static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, pud_t *pudp)
+static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp)
 {
-	__pgd_populate(pgdp, __pa(pudp), PUD_TYPE_TABLE);
+	__p4d_populate(p4dp, __pa(pudp), PUD_TYPE_TABLE);
 }
 #else
-static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot)
+static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot)
 {
 	BUILD_BUG();
 }

arch/arm64/include/asm/pgtable-types.h

@@ -14,6 +14,7 @@
 typedef u64 pteval_t;
 typedef u64 pmdval_t;
 typedef u64 pudval_t;
+typedef u64 p4dval_t;
 typedef u64 pgdval_t;
 
 /*
@@ -44,13 +45,11 @@ typedef struct { pteval_t pgprot; } pgprot_t;
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
 #if CONFIG_PGTABLE_LEVELS == 2
-#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 #elif CONFIG_PGTABLE_LEVELS == 3
-#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 #elif CONFIG_PGTABLE_LEVELS == 4
-#include <asm-generic/5level-fixup.h>
+#include <asm-generic/pgtable-nop4d.h>
 #endif
 
 #endif	/* __ASM_PGTABLE_TYPES_H */

arch/arm64/include/asm/pgtable.h

@@ -298,6 +298,11 @@ static inline pte_t pgd_pte(pgd_t pgd)
 	return __pte(pgd_val(pgd));
 }
 
+static inline pte_t p4d_pte(p4d_t p4d)
+{
+	return __pte(p4d_val(p4d));
+}
+
 static inline pte_t pud_pte(pud_t pud)
 {
 	return __pte(pud_val(pud));
@@ -401,6 +406,9 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 
 #define set_pmd_at(mm, addr, pmdp, pmd)	set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
 
+#define __p4d_to_phys(p4d)	__pte_to_phys(p4d_pte(p4d))
+#define __phys_to_p4d_val(phys)	__phys_to_pte_val(phys)
+
 #define __pgd_to_phys(pgd)	__pte_to_phys(pgd_pte(pgd))
 #define __phys_to_pgd_val(phys)	__phys_to_pte_val(phys)
 
@@ -592,49 +600,50 @@ static inline phys_addr_t pud_page_paddr(pud_t pud)
 
 #define pud_ERROR(pud)		__pud_error(__FILE__, __LINE__, pud_val(pud))
 
-#define pgd_none(pgd)		(!pgd_val(pgd))
-#define pgd_bad(pgd)		(!(pgd_val(pgd) & 2))
-#define pgd_present(pgd)	(pgd_val(pgd))
+#define p4d_none(p4d)		(!p4d_val(p4d))
+#define p4d_bad(p4d)		(!(p4d_val(p4d) & 2))
+#define p4d_present(p4d)	(p4d_val(p4d))
 
-static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
+static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
-	if (in_swapper_pgdir(pgdp)) {
-		set_swapper_pgd(pgdp, pgd);
+	if (in_swapper_pgdir(p4dp)) {
+		set_swapper_pgd((pgd_t *)p4dp, __pgd(p4d_val(p4d)));
 		return;
 	}
 
-	WRITE_ONCE(*pgdp, pgd);
+	WRITE_ONCE(*p4dp, p4d);
 	dsb(ishst);
 	isb();
 }
 
-static inline void pgd_clear(pgd_t *pgdp)
+static inline void p4d_clear(p4d_t *p4dp)
 {
-	set_pgd(pgdp, __pgd(0));
+	set_p4d(p4dp, __p4d(0));
 }
 
-static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
+static inline phys_addr_t p4d_page_paddr(p4d_t p4d)
 {
-	return __pgd_to_phys(pgd);
+	return __p4d_to_phys(p4d);
 }
 
 /* Find an entry in the frst-level page table. */
 #define pud_index(addr)		(((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
 
-#define pud_offset_phys(dir, addr)	(pgd_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t))
+#define pud_offset_phys(dir, addr)	(p4d_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t))
 #define pud_offset(dir, addr)		((pud_t *)__va(pud_offset_phys((dir), (addr))))
 
 #define pud_set_fixmap(addr)		((pud_t *)set_fixmap_offset(FIX_PUD, addr))
-#define pud_set_fixmap_offset(pgd, addr)	pud_set_fixmap(pud_offset_phys(pgd, addr))
+#define pud_set_fixmap_offset(p4d, addr)	pud_set_fixmap(pud_offset_phys(p4d, addr))
 #define pud_clear_fixmap()		clear_fixmap(FIX_PUD)
 
-#define pgd_page(pgd)			phys_to_page(__pgd_to_phys(pgd))
+#define p4d_page(p4d)		pfn_to_page(__phys_to_pfn(__p4d_to_phys(p4d)))
 
 /* use ONLY for statically allocated translation tables */
 #define pud_offset_kimg(dir,addr)	((pud_t *)__phys_to_kimg(pud_offset_phys((dir), (addr))))
 
 #else
 
+#define p4d_page_paddr(p4d)	({ BUILD_BUG(); 0;})
 #define pgd_page_paddr(pgd)	({ BUILD_BUG(); 0;})
 
 /* Match pud_offset folding in <asm/generic/pgtable-nopud.h> */

arch/arm64/include/asm/stage2_pgtable.h

@@ -68,41 +68,67 @@ static inline bool kvm_stage2_has_pud(struct kvm *kvm)
 #define S2_PUD_SIZE			(1UL << S2_PUD_SHIFT)
 #define S2_PUD_MASK			(~(S2_PUD_SIZE - 1))
 
-static inline bool stage2_pgd_none(struct kvm *kvm, pgd_t pgd)
+#define stage2_pgd_none(kvm, pgd)		pgd_none(pgd)
+#define stage2_pgd_clear(kvm, pgd)		pgd_clear(pgd)
+#define stage2_pgd_present(kvm, pgd)		pgd_present(pgd)
+#define stage2_pgd_populate(kvm, pgd, p4d)	pgd_populate(NULL, pgd, p4d)
+
+static inline p4d_t *stage2_p4d_offset(struct kvm *kvm,
+				       pgd_t *pgd, unsigned long address)
+{
+	return p4d_offset(pgd, address);
+}
+
+static inline void stage2_p4d_free(struct kvm *kvm, p4d_t *p4d)
+{
+}
+
+static inline bool stage2_p4d_table_empty(struct kvm *kvm, p4d_t *p4dp)
+{
+	return false;
+}
+
+static inline phys_addr_t stage2_p4d_addr_end(struct kvm *kvm,
+					      phys_addr_t addr, phys_addr_t end)
+{
+	return end;
+}
+
+static inline bool stage2_p4d_none(struct kvm *kvm, p4d_t p4d)
 {
 	if (kvm_stage2_has_pud(kvm))
-		return pgd_none(pgd);
+		return p4d_none(p4d);
 	else
 		return 0;
 }
 
-static inline void stage2_pgd_clear(struct kvm *kvm, pgd_t *pgdp)
+static inline void stage2_p4d_clear(struct kvm *kvm, p4d_t *p4dp)
 {
 	if (kvm_stage2_has_pud(kvm))
-		pgd_clear(pgdp);
+		p4d_clear(p4dp);
 }
 
-static inline bool stage2_pgd_present(struct kvm *kvm, pgd_t pgd)
+static inline bool stage2_p4d_present(struct kvm *kvm, p4d_t p4d)
 {
 	if (kvm_stage2_has_pud(kvm))
-		return pgd_present(pgd);
+		return p4d_present(p4d);
 	else
 		return 1;
 }
 
-static inline void stage2_pgd_populate(struct kvm *kvm, pgd_t *pgd, pud_t *pud)
+static inline void stage2_p4d_populate(struct kvm *kvm, p4d_t *p4d, pud_t *pud)
 {
 	if (kvm_stage2_has_pud(kvm))
-		pgd_populate(NULL, pgd, pud);
+		p4d_populate(NULL, p4d, pud);
 }
 
 static inline pud_t *stage2_pud_offset(struct kvm *kvm,
-				       pgd_t *pgd, unsigned long address)
+				       p4d_t *p4d, unsigned long address)
 {
 	if (kvm_stage2_has_pud(kvm))
-		return pud_offset(pgd, address);
+		return pud_offset(p4d, address);
 	else
-		return (pud_t *)pgd;
+		return (pud_t *)p4d;
 }
 
 static inline void stage2_pud_free(struct kvm *kvm, pud_t *pud)

arch/arm64/kernel/hibernate.c

@@ -184,6 +184,7 @@ static int trans_pgd_map_page(pgd_t *trans_pgd, void *page,
 		       pgprot_t pgprot)
 {
 	pgd_t *pgdp;
+	p4d_t *p4dp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
@@ -196,7 +197,15 @@ static int trans_pgd_map_page(pgd_t *trans_pgd, void *page,
 		pgd_populate(&init_mm, pgdp, pudp);
 	}
 
-	pudp = pud_offset(pgdp, dst_addr);
+	p4dp = p4d_offset(pgdp, dst_addr);
+	if (p4d_none(READ_ONCE(*p4dp))) {
+		pudp = (void *)get_safe_page(GFP_ATOMIC);
+		if (!pudp)
+			return -ENOMEM;
+		p4d_populate(&init_mm, p4dp, pudp);
+	}
+
+	pudp = pud_offset(p4dp, dst_addr);
 	if (pud_none(READ_ONCE(*pudp))) {
 		pmdp = (void *)get_safe_page(GFP_ATOMIC);
 		if (!pmdp)
@@ -419,7 +428,7 @@ static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
 	return 0;
 }
 
-static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
+static int copy_pud(p4d_t *dst_p4dp, p4d_t *src_p4dp, unsigned long start,
 		    unsigned long end)
 {
 	pud_t *dst_pudp;
@@ -427,15 +436,15 @@ static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
 	unsigned long next;
 	unsigned long addr = start;
 
-	if (pgd_none(READ_ONCE(*dst_pgdp))) {
+	if (p4d_none(READ_ONCE(*dst_p4dp))) {
 		dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC);
 		if (!dst_pudp)
 			return -ENOMEM;
-		pgd_populate(&init_mm, dst_pgdp, dst_pudp);
+		p4d_populate(&init_mm, dst_p4dp, dst_pudp);
 	}
-	dst_pudp = pud_offset(dst_pgdp, start);
+	dst_pudp = pud_offset(dst_p4dp, start);
 
-	src_pudp = pud_offset(src_pgdp, start);
+	src_pudp = pud_offset(src_p4dp, start);
 	do {
 		pud_t pud = READ_ONCE(*src_pudp);
 
@@ -454,6 +463,27 @@ static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
 	return 0;
 }
 
+static int copy_p4d(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
+		    unsigned long end)
+{
+	p4d_t *dst_p4dp;
+	p4d_t *src_p4dp;
+	unsigned long next;
+	unsigned long addr = start;
+
+	dst_p4dp = p4d_offset(dst_pgdp, start);
+	src_p4dp = p4d_offset(src_pgdp, start);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none(READ_ONCE(*src_p4dp)))
+			continue;
+		if (copy_pud(dst_p4dp, src_p4dp, addr, next))
+			return -ENOMEM;
+	} while (dst_p4dp++, src_p4dp++, addr = next, addr != end);
+
+	return 0;
+}
+
 static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
 			    unsigned long end)
 {
@@ -466,7 +496,7 @@ static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(READ_ONCE(*src_pgdp)))
 			continue;
-		if (copy_pud(dst_pgdp, src_pgdp, addr, next))
+		if (copy_p4d(dst_pgdp, src_pgdp, addr, next))
 			return -ENOMEM;
 	} while (dst_pgdp++, src_pgdp++, addr = next, addr != end);
 

arch/arm64/mm/fault.c

@@ -145,6 +145,7 @@ static void show_pte(unsigned long addr)
 	pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd));
 
 	do {
+		p4d_t *p4dp, p4d;
 		pud_t *pudp, pud;
 		pmd_t *pmdp, pmd;
 		pte_t *ptep, pte;
@@ -152,7 +153,13 @@ static void show_pte(unsigned long addr)
 		if (pgd_none(pgd) || pgd_bad(pgd))
 			break;
 
-		pudp = pud_offset(pgdp, addr);
+		p4dp = p4d_offset(pgdp, addr);
+		p4d = READ_ONCE(*p4dp);
+		pr_cont(", p4d=%016llx", p4d_val(p4d));
+		if (p4d_none(p4d) || p4d_bad(p4d))
+			break;
+
+		pudp = pud_offset(p4dp, addr);
 		pud = READ_ONCE(*pudp);
 		pr_cont(", pud=%016llx", pud_val(pud));
 		if (pud_none(pud) || pud_bad(pud))

arch/arm64/mm/hugetlbpage.c

@@ -67,11 +67,13 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, size_t *pgsize)
 {
 	pgd_t *pgdp = pgd_offset(mm, addr);
+	p4d_t *p4dp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 
 	*pgsize = PAGE_SIZE;
-	pudp = pud_offset(pgdp, addr);
+	p4dp = p4d_offset(pgdp, addr);
+	pudp = pud_offset(p4dp, addr);
 	pmdp = pmd_offset(pudp, addr);
 	if ((pte_t *)pmdp == ptep) {
 		*pgsize = PMD_SIZE;
@@ -217,12 +219,14 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		      unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgdp;
+	p4d_t *p4dp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep = NULL;
 
 	pgdp = pgd_offset(mm, addr);
-	pudp = pud_alloc(mm, pgdp, addr);
+	p4dp = p4d_offset(pgdp, addr);
+	pudp = pud_alloc(mm, p4dp, addr);
 	if (!pudp)
 		return NULL;
 
@@ -261,6 +265,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgdp;
+	p4d_t *p4dp;
 	pud_t *pudp, pud;
 	pmd_t *pmdp, pmd;
 
@@ -268,7 +273,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	if (!pgd_present(READ_ONCE(*pgdp)))
 		return NULL;
 
-	pudp = pud_offset(pgdp, addr);
+	p4dp = p4d_offset(pgdp, addr);
+	if (!p4d_present(READ_ONCE(*p4dp)))
+		return NULL;
+
+	pudp = pud_offset(p4dp, addr);
 	pud = READ_ONCE(*pudp);
 	if (sz != PUD_SIZE && pud_none(pud))
 		return NULL;

arch/arm64/mm/kasan_init.c

@@ -84,17 +84,17 @@ static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node,
 	return early ? pmd_offset_kimg(pudp, addr) : pmd_offset(pudp, addr);
 }
 
-static pud_t *__init kasan_pud_offset(pgd_t *pgdp, unsigned long addr, int node,
+static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node,
 				      bool early)
 {
-	if (pgd_none(READ_ONCE(*pgdp))) {
+	if (p4d_none(READ_ONCE(*p4dp))) {
 		phys_addr_t pud_phys = early ?
 				__pa_symbol(kasan_early_shadow_pud)
 					: kasan_alloc_zeroed_page(node);
-		__pgd_populate(pgdp, pud_phys, PMD_TYPE_TABLE);
+		__p4d_populate(p4dp, pud_phys, PMD_TYPE_TABLE);
 	}
 
-	return early ? pud_offset_kimg(pgdp, addr) : pud_offset(pgdp, addr);
+	return early ? pud_offset_kimg(p4dp, addr) : pud_offset(p4dp, addr);
 }
 
 static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
@@ -126,11 +126,11 @@ static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
 	} while (pmdp++, addr = next, addr != end && pmd_none(READ_ONCE(*pmdp)));
 }
 
-static void __init kasan_pud_populate(pgd_t *pgdp, unsigned long addr,
+static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr,
 				      unsigned long end, int node, bool early)
 {
 	unsigned long next;
-	pud_t *pudp = kasan_pud_offset(pgdp, addr, node, early);
+	pud_t *pudp = kasan_pud_offset(p4dp, addr, node, early);
 
 	do {
 		next = pud_addr_end(addr, end);
@@ -138,6 +138,18 @@ static void __init kasan_pud_populate(pgd_t *pgdp, unsigned long addr,
 	} while (pudp++, addr = next, addr != end && pud_none(READ_ONCE(*pudp)));
 }
 
+static void __init kasan_p4d_populate(pgd_t *pgdp, unsigned long addr,
+				      unsigned long end, int node, bool early)
+{
+	unsigned long next;
+	p4d_t *p4dp = p4d_offset(pgdp, addr);
+
+	do {
+		next = p4d_addr_end(addr, end);
+		kasan_pud_populate(p4dp, addr, next, node, early);
+	} while (p4dp++, addr = next, addr != end);
+}
+
 static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
 				      int node, bool early)
 {
@@ -147,7 +159,7 @@ static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
 	pgdp = pgd_offset_k(addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		kasan_pud_populate(pgdp, addr, next, node, early);
+		kasan_p4d_populate(pgdp, addr, next, node, early);
 	} while (pgdp++, addr = next, addr != end);
 }
 

arch/arm64/mm/mmu.c

@@ -290,18 +290,19 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 {
 	unsigned long next;
 	pud_t *pudp;
-	pgd_t pgd = READ_ONCE(*pgdp);
+	p4d_t *p4dp = p4d_offset(pgdp, addr);
+	p4d_t p4d = READ_ONCE(*p4dp);
 
-	if (pgd_none(pgd)) {
+	if (p4d_none(p4d)) {
 		phys_addr_t pud_phys;
 		BUG_ON(!pgtable_alloc);
 		pud_phys = pgtable_alloc(PUD_SHIFT);
-		__pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE);
-		pgd = READ_ONCE(*pgdp);
+		__p4d_populate(p4dp, pud_phys, PUD_TYPE_TABLE);
+		p4d = READ_ONCE(*p4dp);
 	}
-	BUG_ON(pgd_bad(pgd));
+	BUG_ON(p4d_bad(p4d));
 
-	pudp = pud_set_fixmap_offset(pgdp, addr);
+	pudp = pud_set_fixmap_offset(p4dp, addr);
 	do {
 		pud_t old_pud = READ_ONCE(*pudp);
 
@@ -672,6 +673,7 @@ static void __init map_kernel(pgd_t *pgdp)
 			READ_ONCE(*pgd_offset_k(FIXADDR_START)));
 	} else if (CONFIG_PGTABLE_LEVELS > 3) {
 		pgd_t *bm_pgdp;
+		p4d_t *bm_p4dp;
 		pud_t *bm_pudp;
 		/*
 		 * The fixmap shares its top level pgd entry with the kernel
@@ -681,7 +683,8 @@ static void __init map_kernel(pgd_t *pgdp)
 		 */
 		BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
 		bm_pgdp = pgd_offset_raw(pgdp, FIXADDR_START);
-		bm_pudp = pud_set_fixmap_offset(bm_pgdp, FIXADDR_START);
+		bm_p4dp = p4d_offset(bm_pgdp, FIXADDR_START);
+		bm_pudp = pud_set_fixmap_offset(bm_p4dp, FIXADDR_START);
 		pud_populate(&init_mm, bm_pudp, lm_alias(bm_pmd));
 		pud_clear_fixmap();
 	} else {
@@ -715,6 +718,7 @@ void __init paging_init(void)
 int kern_addr_valid(unsigned long addr)
 {
 	pgd_t *pgdp;
+	p4d_t *p4dp;
 	pud_t *pudp, pud;
 	pmd_t *pmdp, pmd;
 	pte_t *ptep, pte;
@@ -726,7 +730,11 @@ int kern_addr_valid(unsigned long addr)
 	if (pgd_none(READ_ONCE(*pgdp)))
 		return 0;
 
-	pudp = pud_offset(pgdp, addr);
+	p4dp = p4d_offset(pgdp, addr);
+	if (p4d_none(READ_ONCE(*p4dp)))
+		return 0;
+
+	pudp = pud_offset(p4dp, addr);
 	pud = READ_ONCE(*pudp);
 	if (pud_none(pud))
 		return 0;
@@ -1069,6 +1077,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 	unsigned long addr = start;
 	unsigned long next;
 	pgd_t *pgdp;
+	p4d_t *p4dp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 
@@ -1079,7 +1088,11 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		if (!pgdp)
 			return -ENOMEM;
 
-		pudp = vmemmap_pud_populate(pgdp, addr, node);
+		p4dp = vmemmap_p4d_populate(pgdp, addr, node);
+		if (!p4dp)
+			return -ENOMEM;
+
+		pudp = vmemmap_pud_populate(p4dp, addr, node);
 		if (!pudp)
 			return -ENOMEM;
 
@@ -1114,11 +1127,12 @@ void vmemmap_free(unsigned long start, unsigned long end,
 static inline pud_t * fixmap_pud(unsigned long addr)
 {
 	pgd_t *pgdp = pgd_offset_k(addr);
-	pgd_t pgd = READ_ONCE(*pgdp);
+	p4d_t *p4dp = p4d_offset(pgdp, addr);
+	p4d_t p4d = READ_ONCE(*p4dp);
 
-	BUG_ON(pgd_none(pgd) || pgd_bad(pgd));
+	BUG_ON(p4d_none(p4d) || p4d_bad(p4d));
 
-	return pud_offset_kimg(pgdp, addr);
+	return pud_offset_kimg(p4dp, addr);
 }
 
 static inline pmd_t * fixmap_pmd(unsigned long addr)
@@ -1144,25 +1158,27 @@ static inline pte_t * fixmap_pte(unsigned long addr)
  */
 void __init early_fixmap_init(void)
 {
-	pgd_t *pgdp, pgd;
+	pgd_t *pgdp;
+	p4d_t *p4dp, p4d;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	unsigned long addr = FIXADDR_START;
 
 	pgdp = pgd_offset_k(addr);
-	pgd = READ_ONCE(*pgdp);
+	p4dp = p4d_offset(pgdp, addr);
+	p4d = READ_ONCE(*p4dp);
 	if (CONFIG_PGTABLE_LEVELS > 3 &&
-	    !(pgd_none(pgd) || pgd_page_paddr(pgd) == __pa_symbol(bm_pud))) {
+	    !(p4d_none(p4d) || p4d_page_paddr(p4d) == __pa_symbol(bm_pud))) {
 		/*
 		 * We only end up here if the kernel mapping and the fixmap
 		 * share the top level pgd entry, which should only happen on
 		 * 16k/4 levels configurations.
 		 */
 		BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
-		pudp = pud_offset_kimg(pgdp, addr);
+		pudp = pud_offset_kimg(p4dp, addr);
 	} else {
-		if (pgd_none(pgd))
-			__pgd_populate(pgdp, __pa_symbol(bm_pud), PUD_TYPE_TABLE);
+		if (p4d_none(p4d))
+			__p4d_populate(p4dp, __pa_symbol(bm_pud), PUD_TYPE_TABLE);
 		pudp = fixmap_pud(addr);
 	}
 	if (pud_none(READ_ONCE(*pudp)))

arch/arm64/mm/pageattr.c

@@ -198,6 +198,7 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 bool kernel_page_present(struct page *page)
 {
 	pgd_t *pgdp;
+	p4d_t *p4dp;
 	pud_t *pudp, pud;
 	pmd_t *pmdp, pmd;
 	pte_t *ptep;
@@ -210,7 +211,11 @@ bool kernel_page_present(struct page *page)
 	if (pgd_none(READ_ONCE(*pgdp)))
 		return false;
 
-	pudp = pud_offset(pgdp, addr);
+	p4dp = p4d_offset(pgdp, addr);
+	if (p4d_none(READ_ONCE(*p4dp)))
+		return false;
+
+	pudp = pud_offset(p4dp, addr);
 	pud = READ_ONCE(*pudp);
 	if (pud_none(pud))
 		return false;