um: add support for folded p4d page tables

The UML port uses 4 and 5 level fixups to support higher level page
table directories in the generic VM code.

Implement primitives necessary for the 4th level folding, add walks of
p4d level where appropriate and drop usage of __ARCH_USE_5LEVEL_HACK.

Link: http://lkml.kernel.org/r/1572938135-31886-13-git-send-email-rppt@kernel.org
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Anatoly Pugachev <matorola@gmail.com>
Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Greg Ungerer <gerg@linux-m68k.org>
Cc: Helge Deller <deller@gmx.de>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Mark Salter <msalter@redhat.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Peter Rosin <peda@axentia.se>
Cc: Richard Weinberger <richard@nod.at>
Cc: Rolf Eike Beer <eike-kernel@sf-tec.de>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Russell King <rmk+kernel@armlinux.org.uk>
Cc: Sam Creasey <sammy@sammy.net>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Vineet Gupta <Vineet.Gupta1@synopsys.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 75 insertions, 12 deletions

diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index 417ff647fb37..30885d0b94ac 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -96,6 +96,7 @@ static void __init fixrange_init(unsigned long start, unsigned long end,
 				 pgd_t *pgd_base)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	int i, j;
@@ -107,7 +108,8 @@ static void __init fixrange_init(unsigned long start, unsigned long end,
 	pgd = pgd_base + i;
 
 	for ( ; (i < PTRS_PER_PGD) && (vaddr < end); pgd++, i++) {
-		pud = pud_offset(pgd, vaddr);
+		p4d = p4d_offset(pgd, vaddr);
+		pud = pud_offset(p4d, vaddr);
 		if (pud_none(*pud))
 			one_md_table_init(pud);
 		pmd = pmd_offset(pud, vaddr);
@@ -124,6 +126,7 @@ static void __init fixaddr_user_init( void)
 #ifdef CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA
 	long size = FIXADDR_USER_END - FIXADDR_USER_START;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -144,7 +147,8 @@ static void __init fixaddr_user_init( void)
 	for ( ; size > 0; size -= PAGE_SIZE, vaddr += PAGE_SIZE,
 		      p += PAGE_SIZE) {
 		pgd = swapper_pg_dir + pgd_index(vaddr);
-		pud = pud_offset(pgd, vaddr);
+		p4d = p4d_offset(pgd, vaddr);
+		pud = pud_offset(p4d, vaddr);
 		pmd = pmd_offset(pud, vaddr);
 		pte = pte_offset_kernel(pmd, vaddr);
 		pte_set_val(*pte, p, PAGE_READONLY);
diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c
index b5e3d91fc9c2..3f0d9a573fd6 100644
--- a/arch/um/kernel/skas/mmu.c
+++ b/arch/um/kernel/skas/mmu.c
@@ -19,15 +19,21 @@ static int init_stub_pte(struct mm_struct *mm, unsigned long proc,
 			 unsigned long kernel)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 
 	pgd = pgd_offset(mm, proc);
-	pud = pud_alloc(mm, pgd, proc);
-	if (!pud)
+
+	p4d = p4d_alloc(mm, pgd, proc);
+	if (!p4d)
 		goto out;
 
+	pud = pud_alloc(mm, p4d, proc);
+	if (!pud)
+		goto out_pud;
+
 	pmd = pmd_alloc(mm, pud, proc);
 	if (!pmd)
 		goto out_pmd;
@@ -44,6 +50,8 @@ static int init_stub_pte(struct mm_struct *mm, unsigned long proc,
 	pmd_free(mm, pmd);
  out_pmd:
 	pud_free(mm, pud);
+ out_pud:
+	p4d_free(mm, p4d);
  out:
 	return -ENOMEM;
 }
diff --git a/arch/um/kernel/skas/uaccess.c b/arch/um/kernel/skas/uaccess.c
index 3236052f20e6..d617f8dc9c19 100644
--- a/arch/um/kernel/skas/uaccess.c
+++ b/arch/um/kernel/skas/uaccess.c
@@ -17,6 +17,7 @@
 pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -27,7 +28,11 @@ pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr)
 	if (!pgd_present(*pgd))
 		return NULL;
 
-	pud = pud_offset(pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	if (!p4d_present(*p4d))
+		return NULL;
+
+	pud = pud_offset(p4d, addr);
 	if (!pud_present(*pud))
 		return NULL;
 
diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c
index 8425a22142b7..80a358c6d652 100644
--- a/arch/um/kernel/tlb.c
+++ b/arch/um/kernel/tlb.c
@@ -277,7 +277,7 @@ static inline int update_pmd_range(pud_t *pud, unsigned long addr,
 	return ret;
 }
 
-static inline int update_pud_range(pgd_t *pgd, unsigned long addr,
+static inline int update_pud_range(p4d_t *p4d, unsigned long addr,
 				   unsigned long end,
 				   struct host_vm_change *hvc)
 {
@@ -285,7 +285,7 @@ static inline int update_pud_range(pgd_t *pgd, unsigned long addr,
 	unsigned long next;
 	int ret = 0;
 
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (!pud_present(*pud)) {
@@ -299,6 +299,28 @@ static inline int update_pud_range(pgd_t *pgd, unsigned long addr,
 	return ret;
 }
 
+static inline int update_p4d_range(pgd_t *pgd, unsigned long addr,
+				   unsigned long end,
+				   struct host_vm_change *hvc)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	int ret = 0;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (!p4d_present(*p4d)) {
+			if (hvc->force || p4d_newpage(*p4d)) {
+				ret = add_munmap(addr, next - addr, hvc);
+				p4d_mkuptodate(*p4d);
+			}
+		} else
+			ret = update_pud_range(p4d, addr, next, hvc);
+	} while (p4d++, addr = next, ((addr < end) && !ret));
+	return ret;
+}
+
 void fix_range_common(struct mm_struct *mm, unsigned long start_addr,
 		      unsigned long end_addr, int force)
 {
@@ -316,8 +338,8 @@ void fix_range_common(struct mm_struct *mm, unsigned long start_addr,
 				ret = add_munmap(addr, next - addr, &hvc);
 				pgd_mkuptodate(*pgd);
 			}
-		}
-		else ret = update_pud_range(pgd, addr, next, &hvc);
+		} else
+			ret = update_p4d_range(pgd, addr, next, &hvc);
 	} while (pgd++, addr = next, ((addr < end_addr) && !ret));
 
 	if (!ret)
@@ -338,6 +360,7 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
 {
 	struct mm_struct *mm;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -364,7 +387,23 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
 			continue;
 		}
 
-		pud = pud_offset(pgd, addr);
+		p4d = p4d_offset(pgd, addr);
+		if (!p4d_present(*p4d)) {
+			last = ADD_ROUND(addr, P4D_SIZE);
+			if (last > end)
+				last = end;
+			if (p4d_newpage(*p4d)) {
+				updated = 1;
+				err = add_munmap(addr, last - addr, &hvc);
+				if (err < 0)
+					panic("munmap failed, errno = %d\n",
+					      -err);
+			}
+			addr = last;
+			continue;
+		}
+
+		pud = pud_offset(p4d, addr);
 		if (!pud_present(*pud)) {
 			last = ADD_ROUND(addr, PUD_SIZE);
 			if (last > end)
@@ -424,6 +463,7 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long address)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -437,7 +477,11 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long address)
 	if (!pgd_present(*pgd))
 		goto kill;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (!p4d_present(*p4d))
+		goto kill;
+
+	pud = pud_offset(p4d, address);
 	if (!pud_present(*pud))
 		goto kill;
 
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index e62296c66c95..818553064f04 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -28,6 +28,7 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -104,7 +105,8 @@ good_area:
 		}
 
 		pgd = pgd_offset(mm, address);
-		pud = pud_offset(pgd, address);
+		p4d = p4d_offset(pgd, address);
+		pud = pud_offset(p4d, address);
 		pmd = pmd_offset(pud, address);
 		pte = pte_offset_kernel(pmd, address);
 	} while (!pte_present(*pte));