[PATCHv3 0/7] x86: 5-level paging enabling for v4.12, Part 3

[PATCHv3 0/7] x86: 5-level paging enabling for v4.12, Part 3

[Kirill A. Shutemov]

Here's the third bunch of patches of 5-level patchset.

This time we prepare code to handle non-folded version of the additional page
table level.

v3:
 - rebased onto tip/master;
v2:
 - address Ingo's and Peter's feedback;

Kirill A. Shutemov (7):
  x86/boot: Detect 5-level paging support
  x86/asm: Remove __VIRTUAL_MASK_SHIFT==47 assert
  x86/mm: Define virtual memory map for 5-level paging
  x86/paravirt: Make paravirt code support 5-level paging
  x86/mm: Add basic defines/helpers for CONFIG_X86_5LEVEL
  x86/kasan: Extend to support 5-level paging
  x86/espfix: Add support 5-level paging

 Documentation/x86/x86_64/mm.txt          | 33 +++++++++++++++++++++++++---
 arch/x86/Kconfig                         |  1 +
 arch/x86/boot/cpucheck.c                 |  9 ++++++++
 arch/x86/boot/cpuflags.c                 | 12 +++++++++--
 arch/x86/entry/entry_64.S                |  7 ++----
 arch/x86/include/asm/disabled-features.h |  8 ++++++-
 arch/x86/include/asm/kasan.h             |  9 +++++---
 arch/x86/include/asm/page_64_types.h     | 10 +++++++++
 arch/x86/include/asm/paravirt.h          | 37 ++++++++++++++++++++++----------
 arch/x86/include/asm/paravirt_types.h    |  7 +++++-
 arch/x86/include/asm/pgalloc.h           |  2 ++
 arch/x86/include/asm/pgtable_64.h        | 11 ++++++++++
 arch/x86/include/asm/pgtable_64_types.h  | 28 +++++++++++++++++++++++-
 arch/x86/include/asm/pgtable_types.h     | 10 ++++++++-
 arch/x86/include/asm/required-features.h |  8 ++++++-
 arch/x86/include/asm/sparsemem.h         |  9 ++++++--
 arch/x86/kernel/espfix_64.c              | 12 ++++++-----
 arch/x86/kernel/paravirt.c               |  9 ++++++--
 arch/x86/mm/kasan_init_64.c              | 18 ++++++++++++++--
 arch/x86/mm/pgtable.c                    | 32 ++++++++++++++++++++++++++-
 20 files changed, 231 insertions(+), 41 deletions(-)

-- 
2.11.0

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCHv3 1/7] x86/boot: Detect 5-level paging support

[Kirill A. Shutemov]

5-level paging support is required from hardware when compiled with
CONFIG_X86_5LEVEL=y.

We will implement boot-time switch between 4- and 5-level paging later.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/boot/cpucheck.c                 |  9 +++++++++
 arch/x86/boot/cpuflags.c                 | 12 ++++++++++--
 arch/x86/include/asm/disabled-features.h |  8 +++++++-
 arch/x86/include/asm/required-features.h |  8 +++++++-
 4 files changed, 33 insertions(+), 4 deletions(-)

diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index 4ad7d70e8739..8f0c4c9fc904 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -44,6 +44,15 @@ static const u32 req_flags[NCAPINTS] =
 	0, /* REQUIRED_MASK5 not implemented in this file */
 	REQUIRED_MASK6,
 	0, /* REQUIRED_MASK7 not implemented in this file */
+	0, /* REQUIRED_MASK8 not implemented in this file */
+	0, /* REQUIRED_MASK9 not implemented in this file */
+	0, /* REQUIRED_MASK10 not implemented in this file */
+	0, /* REQUIRED_MASK11 not implemented in this file */
+	0, /* REQUIRED_MASK12 not implemented in this file */
+	0, /* REQUIRED_MASK13 not implemented in this file */
+	0, /* REQUIRED_MASK14 not implemented in this file */
+	0, /* REQUIRED_MASK15 not implemented in this file */
+	REQUIRED_MASK16,
 };
 
 #define A32(a, b, c, d) (((d) << 24)+((c) << 16)+((b) << 8)+(a))
diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
index 6687ab953257..9e77c23c2422 100644
--- a/arch/x86/boot/cpuflags.c
+++ b/arch/x86/boot/cpuflags.c
@@ -70,16 +70,19 @@ int has_eflag(unsigned long mask)
 # define EBX_REG "=b"
 #endif
 
-static inline void cpuid(u32 id, u32 *a, u32 *b, u32 *c, u32 *d)
+static inline void cpuid_count(u32 id, u32 count,
+		u32 *a, u32 *b, u32 *c, u32 *d)
 {
 	asm volatile(".ifnc %%ebx,%3 ; movl  %%ebx,%3 ; .endif	\n\t"
 		     "cpuid					\n\t"
 		     ".ifnc %%ebx,%3 ; xchgl %%ebx,%3 ; .endif	\n\t"
 		    : "=a" (*a), "=c" (*c), "=d" (*d), EBX_REG (*b)
-		    : "a" (id)
+		    : "a" (id), "c" (count)
 	);
 }
 
+#define cpuid(id, a, b, c, d) cpuid_count(id, 0, a, b, c, d)
+
 void get_cpuflags(void)
 {
 	u32 max_intel_level, max_amd_level;
@@ -108,6 +111,11 @@ void get_cpuflags(void)
 				cpu.model += ((tfms >> 16) & 0xf) << 4;
 		}
 
+		if (max_intel_level >= 0x00000007) {
+			cpuid_count(0x00000007, 0, &ignored, &ignored,
+					&cpu.flags[16], &ignored);
+		}
+
 		cpuid(0x80000000, &max_amd_level, &ignored, &ignored,
 		      &ignored);
 
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 85599ad4d024..5dff775af7cd 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -36,6 +36,12 @@
 # define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE & 31))
 #endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
 
+#ifdef CONFIG_X86_5LEVEL
+# define DISABLE_LA57	0
+#else
+# define DISABLE_LA57	(1<<(X86_FEATURE_LA57 & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -55,7 +61,7 @@
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
+#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57)
 #define DISABLED_MASK17	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index fac9a5c0abe9..d91ba04dd007 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -53,6 +53,12 @@
 # define NEED_MOVBE	0
 #endif
 
+#ifdef CONFIG_X86_5LEVEL
+# define NEED_LA57	(1<<(X86_FEATURE_LA57 & 31))
+#else
+# define NEED_LA57	0
+#endif
+
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT
 /* Paravirtualized systems may not have PSE or PGE available */
@@ -98,7 +104,7 @@
 #define REQUIRED_MASK13	0
 #define REQUIRED_MASK14	0
 #define REQUIRED_MASK15	0
-#define REQUIRED_MASK16	0
+#define REQUIRED_MASK16	(NEED_LA57)
 #define REQUIRED_MASK17	0
 #define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
-- 
2.11.0

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCHv3 2/7] x86/asm: Remove __VIRTUAL_MASK_SHIFT==47 assert

[Kirill A. Shutemov]

We don't need the assert anymore. 17be0aec74fb ("x86/asm/entry/64:
Implement better check for canonical addresses") made canonical
address check generic wrt. address width.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/entry/entry_64.S | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d2b2a2948ffe..607d72c4a485 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -265,12 +265,9 @@ return_from_SYSCALL_64:
 	 *
 	 * If width of "canonical tail" ever becomes variable, this will need
 	 * to be updated to remain correct on both old and new CPUs.
+	 *
+	 * Change top 16 bits to be the sign-extension of 47th bit
 	 */
-	.ifne __VIRTUAL_MASK_SHIFT - 47
-	.error "virtual address width changed -- SYSRET checks need update"
-	.endif
-
-	/* Change top 16 bits to be the sign-extension of 47th bit */
 	shl	$(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
 	sar	$(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
 
-- 
2.11.0

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCHv3 3/7] x86/mm: Define virtual memory map for 5-level paging

[Kirill A. Shutemov]

The first part of memory map (up to %esp fixup) simply scales existing
map for 4-level paging by factor of 9 -- number of bits addressed by
additional page table level.

The rest of the map is unchanged.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 Documentation/x86/x86_64/mm.txt         | 33 ++++++++++++++++++++++++++++++---
 arch/x86/Kconfig                        |  1 +
 arch/x86/include/asm/kasan.h            |  9 ++++++---
 arch/x86/include/asm/page_64_types.h    | 10 ++++++++++
 arch/x86/include/asm/pgtable_64_types.h |  6 ++++++
 arch/x86/include/asm/sparsemem.h        |  9 +++++++--
 6 files changed, 60 insertions(+), 8 deletions(-)

diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index ee3f9c30957c..b0798e281aa6 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -4,7 +4,7 @@
 Virtual memory map with 4 level page tables:
 
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
-hole caused by [48:63] sign extension
+hole caused by [47:63] sign extension
 ffff800000000000 - ffff87ffffffffff (=43 bits) guard hole, reserved for hypervisor
 ffff880000000000 - ffffc7ffffffffff (=64 TB) direct mapping of all phys. memory
 ffffc80000000000 - ffffc8ffffffffff (=40 bits) hole
@@ -23,12 +23,39 @@ ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space (variable)
 ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
 ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
 
+Virtual memory map with 5 level page tables:
+
+0000000000000000 - 00ffffffffffffff (=56 bits) user space, different per mm
+hole caused by [56:63] sign extension
+ff00000000000000 - ff0fffffffffffff (=52 bits) guard hole, reserved for hypervisor
+ff10000000000000 - ff8fffffffffffff (=55 bits) direct mapping of all phys. memory
+ff90000000000000 - ff91ffffffffffff (=49 bits) hole
+ff92000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space
+ffd2000000000000 - ffd3ffffffffffff (=49 bits) hole
+ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
+... unused hole ...
+ffd8000000000000 - fff7ffffffffffff (=53 bits) kasan shadow memory (8PB)
+... unused hole ...
+ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
+... unused hole ...
+ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
+... unused hole ...
+ffffffff80000000 - ffffffff9fffffff (=512 MB)  kernel text mapping, from phys 0
+ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space
+ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
+ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
+
+Architecture defines a 64-bit virtual address. Implementations can support
+less. Currently supported are 48- and 57-bit virtual addresses. Bits 63
+through to the most-significant implemented bit are set to either all ones
+or all zero. This causes hole between user space and kernel addresses.
+
 The direct mapping covers all memory in the system up to the highest
 memory address (this means in some cases it can also include PCI memory
 holes).
 
-vmalloc space is lazily synchronized into the different PML4 pages of
-the processes using the page fault handler, with init_level4_pgt as
+vmalloc space is lazily synchronized into the different PML4/PML5 pages of
+the processes using the page fault handler, with init_top_pgt as
 reference.
 
 Current X86-64 implementations support up to 46 bits of address space (64 TB),
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e63d50fd698c..4e153e93273f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -291,6 +291,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN
+	default 0xdff8000000000000 if X86_5LEVEL
 	default 0xdffffc0000000000
 
 config HAVE_INTEL_TXT
diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h
index 1410b567ecde..f527b02a0ee3 100644
--- a/arch/x86/include/asm/kasan.h
+++ b/arch/x86/include/asm/kasan.h
@@ -11,9 +11,12 @@
  * 'kernel address space start' >> KASAN_SHADOW_SCALE_SHIFT
  */
 #define KASAN_SHADOW_START      (KASAN_SHADOW_OFFSET + \
-					(0xffff800000000000ULL >> 3))
-/* 47 bits for kernel address -> (47 - 3) bits for shadow */
-#define KASAN_SHADOW_END        (KASAN_SHADOW_START + (1ULL << (47 - 3)))
+					((-1UL << __VIRTUAL_MASK_SHIFT) >> 3))
+/*
+ * 47 bits for kernel address -> (47 - 3) bits for shadow
+ * 56 bits for kernel address -> (56 - 3) bits for shadow
+ */
+#define KASAN_SHADOW_END        (KASAN_SHADOW_START + (1ULL << (__VIRTUAL_MASK_SHIFT - 3)))
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 9215e0527647..3f5f08b010d0 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -36,7 +36,12 @@
  * hypervisor to fit.  Choosing 16 slots here is arbitrary, but it's
  * what Xen requires.
  */
+#ifdef CONFIG_X86_5LEVEL
+#define __PAGE_OFFSET_BASE      _AC(0xff10000000000000, UL)
+#else
 #define __PAGE_OFFSET_BASE      _AC(0xffff880000000000, UL)
+#endif
+
 #ifdef CONFIG_RANDOMIZE_MEMORY
 #define __PAGE_OFFSET           page_offset_base
 #else
@@ -46,8 +51,13 @@
 #define __START_KERNEL_map	_AC(0xffffffff80000000, UL)
 
 /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
+#ifdef CONFIG_X86_5LEVEL
+#define __PHYSICAL_MASK_SHIFT	52
+#define __VIRTUAL_MASK_SHIFT	56
+#else
 #define __PHYSICAL_MASK_SHIFT	46
 #define __VIRTUAL_MASK_SHIFT	47
+#endif
 
 /*
  * Kernel image size is limited to 1GiB due to the fixmap living in the
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 516593e66bd6..4edc97917382 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -56,9 +56,15 @@ typedef struct { pteval_t pte; } pte_t;
 
 /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
 #define MAXMEM		_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+#ifdef CONFIG_X86_5LEVEL
+#define VMALLOC_SIZE_TB _AC(16384, UL)
+#define __VMALLOC_BASE	_AC(0xff92000000000000, UL)
+#define __VMEMMAP_BASE	_AC(0xffd4000000000000, UL)
+#else
 #define VMALLOC_SIZE_TB	_AC(32, UL)
 #define __VMALLOC_BASE	_AC(0xffffc90000000000, UL)
 #define __VMEMMAP_BASE	_AC(0xffffea0000000000, UL)
+#endif
 #ifdef CONFIG_RANDOMIZE_MEMORY
 #define VMALLOC_START	vmalloc_base
 #define VMEMMAP_START	vmemmap_base
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 4517d6b93188..1f5bee2c202f 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -26,8 +26,13 @@
 # endif
 #else /* CONFIG_X86_32 */
 # define SECTION_SIZE_BITS	27 /* matt - 128 is convenient right now */
-# define MAX_PHYSADDR_BITS	44
-# define MAX_PHYSMEM_BITS	46
+# ifdef CONFIG_X86_5LEVEL
+#  define MAX_PHYSADDR_BITS	52
+#  define MAX_PHYSMEM_BITS	52
+# else
+#  define MAX_PHYSADDR_BITS	44
+#  define MAX_PHYSMEM_BITS	46
+# endif
 #endif
 
 #endif /* CONFIG_SPARSEMEM */
-- 
2.11.0

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCHv3 4/7] x86/paravirt: Make paravirt code support 5-level paging

[Kirill A. Shutemov]

Add operations to allocate/release p4ds.

Xen requires more work. We will need to come back to it.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/include/asm/paravirt.h       | 37 ++++++++++++++++++++++++-----------
 arch/x86/include/asm/paravirt_types.h |  7 ++++++-
 arch/x86/include/asm/pgalloc.h        |  2 ++
 arch/x86/kernel/paravirt.c            |  9 +++++++--
 4 files changed, 41 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 158d877ce9e9..55fa56fe4e45 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -357,6 +357,16 @@ static inline void paravirt_release_pud(unsigned long pfn)
 	PVOP_VCALL1(pv_mmu_ops.release_pud, pfn);
 }
 
+static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn)
+{
+	PVOP_VCALL2(pv_mmu_ops.alloc_p4d, mm, pfn);
+}
+
+static inline void paravirt_release_p4d(unsigned long pfn)
+{
+	PVOP_VCALL1(pv_mmu_ops.release_p4d, pfn);
+}
+
 static inline void pte_update(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep)
 {
@@ -582,25 +592,25 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 			    val);
 }
 
-static inline void p4d_clear(p4d_t *p4dp)
+#if CONFIG_PGTABLE_LEVELS >= 5
+
+static inline p4d_t __p4d(p4dval_t val)
 {
-	set_p4d(p4dp, __p4d(0));
-}
+	p4dval_t ret = PVOP_CALLEE1(p4dval_t, pv_mmu_ops.make_p4d, val);
 
-#if CONFIG_PGTABLE_LEVELS >= 5
+	return (p4d_t) { ret };
+}
 
-#error FIXME
+static inline p4dval_t p4d_val(p4d_t p4d)
+{
+	return PVOP_CALLEE1(p4dval_t, pv_mmu_ops.p4d_val, p4d.p4d);
+}
 
 static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
 	pgdval_t val = native_pgd_val(pgd);
 
-	if (sizeof(pgdval_t) > sizeof(long))
-		PVOP_VCALL3(pv_mmu_ops.set_pgd, pgdp,
-			    val, (u64)val >> 32);
-	else
-		PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp,
-			    val);
+	PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, val);
 }
 
 static inline void pgd_clear(pgd_t *pgdp)
@@ -610,6 +620,11 @@ static inline void pgd_clear(pgd_t *pgdp)
 
 #endif  /* CONFIG_PGTABLE_LEVELS == 5 */
 
+static inline void p4d_clear(p4d_t *p4dp)
+{
+	set_p4d(p4dp, __p4d(0));
+}
+
 #endif	/* CONFIG_PGTABLE_LEVELS == 4 */
 
 #endif	/* CONFIG_PGTABLE_LEVELS >= 3 */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 93c49cf09b63..7465d6fe336f 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -238,9 +238,11 @@ struct pv_mmu_ops {
 	void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn);
 	void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn);
 	void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn);
+	void (*alloc_p4d)(struct mm_struct *mm, unsigned long pfn);
 	void (*release_pte)(unsigned long pfn);
 	void (*release_pmd)(unsigned long pfn);
 	void (*release_pud)(unsigned long pfn);
+	void (*release_p4d)(unsigned long pfn);
 
 	/* Pagetable manipulation functions */
 	void (*set_pte)(pte_t *ptep, pte_t pteval);
@@ -286,7 +288,10 @@ struct pv_mmu_ops {
 	void (*set_p4d)(p4d_t *p4dp, p4d_t p4dval);
 
 #if CONFIG_PGTABLE_LEVELS >= 5
-#error FIXME
+	struct paravirt_callee_save p4d_val;
+	struct paravirt_callee_save make_p4d;
+
+	void (*set_pgd)(pgd_t *pgdp, pgd_t pgdval);
 #endif	/* CONFIG_PGTABLE_LEVELS >= 5 */
 
 #endif	/* CONFIG_PGTABLE_LEVELS >= 4 */
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 2f585054c63c..b2d0cd8288aa 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -17,9 +17,11 @@ static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)	{
 static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
 					    unsigned long start, unsigned long count) {}
 static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn)	{}
+static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn)	{}
 static inline void paravirt_release_pte(unsigned long pfn) {}
 static inline void paravirt_release_pmd(unsigned long pfn) {}
 static inline void paravirt_release_pud(unsigned long pfn) {}
+static inline void paravirt_release_p4d(unsigned long pfn) {}
 #endif
 
 /*
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 110daf22f5c7..3586996fc50d 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -405,9 +405,11 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
 	.alloc_pte = paravirt_nop,
 	.alloc_pmd = paravirt_nop,
 	.alloc_pud = paravirt_nop,
+	.alloc_p4d = paravirt_nop,
 	.release_pte = paravirt_nop,
 	.release_pmd = paravirt_nop,
 	.release_pud = paravirt_nop,
+	.release_p4d = paravirt_nop,
 
 	.set_pte = native_set_pte,
 	.set_pte_at = native_set_pte_at,
@@ -437,8 +439,11 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
 	.set_p4d = native_set_p4d,
 
 #if CONFIG_PGTABLE_LEVELS >= 5
-#error FIXME
-#endif /* CONFIG_PGTABLE_LEVELS >= 4 */
+	.p4d_val = PTE_IDENT,
+	.make_p4d = PTE_IDENT,
+
+	.set_pgd = native_set_pgd,
+#endif /* CONFIG_PGTABLE_LEVELS >= 5 */
 #endif /* CONFIG_PGTABLE_LEVELS >= 4 */
 #endif /* CONFIG_PGTABLE_LEVELS >= 3 */
 
-- 
2.11.0

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCHv3 5/7] x86/mm: Add basic defines/helpers for CONFIG_X86_5LEVEL

[Kirill A. Shutemov]

Extends pagetable headers to support new paging mode.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/include/asm/pgtable_64.h       | 11 +++++++++++
 arch/x86/include/asm/pgtable_64_types.h | 20 ++++++++++++++++++++
 arch/x86/include/asm/pgtable_types.h    | 10 +++++++++-
 arch/x86/mm/pgtable.c                   | 32 +++++++++++++++++++++++++++++++-
 4 files changed, 71 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 0593a1ae7573..12ea31274eb6 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -35,6 +35,13 @@ extern void paging_init(void);
 #define pud_ERROR(e)					\
 	pr_err("%s:%d: bad pud %p(%016lx)\n",		\
 	       __FILE__, __LINE__, &(e), pud_val(e))
+
+#if CONFIG_PGTABLE_LEVELS >= 5
+#define p4d_ERROR(e)					\
+	pr_err("%s:%d: bad p4d %p(%016lx)\n",		\
+	       __FILE__, __LINE__, &(e), p4d_val(e))
+#endif
+
 #define pgd_ERROR(e)					\
 	pr_err("%s:%d: bad pgd %p(%016lx)\n",		\
 	       __FILE__, __LINE__, &(e), pgd_val(e))
@@ -128,7 +135,11 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 
 static inline void native_p4d_clear(p4d_t *p4d)
 {
+#ifdef CONFIG_X86_5LEVEL
+	native_set_p4d(p4d, native_make_p4d(0));
+#else
 	native_set_p4d(p4d, (p4d_t) { .pgd = native_make_pgd(0)});
+#endif
 }
 
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 4edc97917382..adc3e7b107ee 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -23,12 +23,32 @@ typedef struct { pteval_t pte; } pte_t;
 
 #define SHARED_KERNEL_PMD	0
 
+#ifdef CONFIG_X86_5LEVEL
+
+/*
+ * PGDIR_SHIFT determines what a top-level page table entry can map
+ */
+#define PGDIR_SHIFT	48
+#define PTRS_PER_PGD	512
+
+/*
+ * 4th level page in 5-level paging case
+ */
+#define P4D_SHIFT	39
+#define PTRS_PER_P4D	512
+#define P4D_SIZE	(_AC(1, UL) << P4D_SHIFT)
+#define P4D_MASK	(~(P4D_SIZE - 1))
+
+#else /* CONFIG_X86_5LEVEL */
+
 /*
  * PGDIR_SHIFT determines what a top-level page table entry can map
  */
 #define PGDIR_SHIFT	39
 #define PTRS_PER_PGD	512
 
+#endif /* CONFIG_X86_5LEVEL */
+
 /*
  * 3rd level page
  */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 4930afe9df0a..bf9638e1ee42 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -273,9 +273,17 @@ static inline pgdval_t pgd_flags(pgd_t pgd)
 }
 
 #if CONFIG_PGTABLE_LEVELS > 4
+typedef struct { p4dval_t p4d; } p4d_t;
 
-#error FIXME
+static inline p4d_t native_make_p4d(pudval_t val)
+{
+	return (p4d_t) { val };
+}
 
+static inline p4dval_t native_p4d_val(p4d_t p4d)
+{
+	return p4d.p4d;
+}
 #else
 #include <asm-generic/pgtable-nop4d.h>
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 38b6daf72deb..508a708eb9a6 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -81,6 +81,14 @@ void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
 	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
 	tlb_remove_page(tlb, virt_to_page(pud));
 }
+
+#if CONFIG_PGTABLE_LEVELS > 4
+void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d)
+{
+	paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT);
+	tlb_remove_page(tlb, virt_to_page(p4d));
+}
+#endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 2 */
 
@@ -120,7 +128,7 @@ static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd)
 	   references from swapper_pg_dir. */
 	if (CONFIG_PGTABLE_LEVELS == 2 ||
 	    (CONFIG_PGTABLE_LEVELS == 3 && SHARED_KERNEL_PMD) ||
-	    CONFIG_PGTABLE_LEVELS == 4) {
+	    CONFIG_PGTABLE_LEVELS >= 4) {
 		clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
 				swapper_pg_dir + KERNEL_PGD_BOUNDARY,
 				KERNEL_PGD_PTRS);
@@ -582,6 +590,28 @@ void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys,
 }
 
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+#ifdef CONFIG_X86_5LEVEL
+/**
+ * p4d_set_huge - setup kernel P4D mapping
+ *
+ * No 512GB pages yet -- always return 0
+ */
+int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
+
+/**
+ * p4d_clear_huge - clear kernel P4D mapping when it is set
+ *
+ * No 512GB pages yet -- always return 0
+ */
+int p4d_clear_huge(p4d_t *p4d)
+{
+	return 0;
+}
+#endif
+
 /**
  * pud_set_huge - setup kernel PUD mapping
  *
-- 
2.11.0

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCHv3 6/7] x86/kasan: Extend to support 5-level paging

[Kirill A. Shutemov]

This patch bring support for non-folded additional page table level.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
---
 arch/x86/mm/kasan_init_64.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 864950994371..0c7d8129bed6 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -56,8 +56,18 @@ static void __init kasan_map_early_shadow(pgd_t *pgd)
 	unsigned long end = KASAN_SHADOW_END;
 
 	for (i = pgd_index(start); start < end; i++) {
-		pgd[i] = __pgd(__pa_nodebug(kasan_zero_pud)
-				| _KERNPG_TABLE);
+		switch (CONFIG_PGTABLE_LEVELS) {
+		case 4:
+			pgd[i] = __pgd(__pa_nodebug(kasan_zero_pud) |
+					_KERNPG_TABLE);
+			break;
+		case 5:
+			pgd[i] = __pgd(__pa_nodebug(kasan_zero_p4d) |
+					_KERNPG_TABLE);
+			break;
+		default:
+			BUILD_BUG();
+		}
 		start += PGDIR_SIZE;
 	}
 }
@@ -85,6 +95,7 @@ void __init kasan_early_init(void)
 	pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL;
 	pmdval_t pmd_val = __pa_nodebug(kasan_zero_pte) | _KERNPG_TABLE;
 	pudval_t pud_val = __pa_nodebug(kasan_zero_pmd) | _KERNPG_TABLE;
+	p4dval_t p4d_val = __pa_nodebug(kasan_zero_pud) | _KERNPG_TABLE;
 
 	for (i = 0; i < PTRS_PER_PTE; i++)
 		kasan_zero_pte[i] = __pte(pte_val);
@@ -95,6 +106,9 @@ void __init kasan_early_init(void)
 	for (i = 0; i < PTRS_PER_PUD; i++)
 		kasan_zero_pud[i] = __pud(pud_val);
 
+	for (i = 0; CONFIG_PGTABLE_LEVELS >= 5 && i < PTRS_PER_P4D; i++)
+		kasan_zero_p4d[i] = __p4d(p4d_val);
+
 	kasan_map_early_shadow(early_level4_pgt);
 	kasan_map_early_shadow(init_level4_pgt);
 }
-- 
2.11.0

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCHv3 7/7] x86/espfix: Add support 5-level paging

[Kirill A. Shutemov]

We don't need extra virtual address space for ESPFIX, so it stays within
one PUD page table for both 4- and 5-level paging.

Redefining ESPFIX_BASE_ADDR using P4D_SHIFT instead of PGDIR_SHIFT would
make it stay in the same place regarding of paging mode.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/include/asm/pgtable_64_types.h |  2 +-
 arch/x86/kernel/espfix_64.c             | 12 +++++++-----
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index adc3e7b107ee..06470da156ba 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -98,7 +98,7 @@ typedef struct { pteval_t pte; } pte_t;
 #define MODULES_END   __fix_to_virt(__end_of_fixed_addresses + 1)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
 #define ESPFIX_PGD_ENTRY _AC(-2, UL)
-#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT)
+#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT)
 #define EFI_VA_START	 ( -4 * (_AC(1, UL) << 30))
 #define EFI_VA_END	 (-68 * (_AC(1, UL) << 30))
 
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 04f89caef9c4..8e598a1ad986 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -50,11 +50,11 @@
 #define ESPFIX_STACKS_PER_PAGE	(PAGE_SIZE/ESPFIX_STACK_SIZE)
 
 /* There is address space for how many espfix pages? */
-#define ESPFIX_PAGE_SPACE	(1UL << (PGDIR_SHIFT-PAGE_SHIFT-16))
+#define ESPFIX_PAGE_SPACE	(1UL << (P4D_SHIFT-PAGE_SHIFT-16))
 
 #define ESPFIX_MAX_CPUS		(ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE)
 #if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS
-# error "Need more than one PGD for the ESPFIX hack"
+# error "Need more virtual address space for the ESPFIX hack"
 #endif
 
 #define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
@@ -121,11 +121,13 @@ static void init_espfix_random(void)
 
 void __init init_espfix_bsp(void)
 {
-	pgd_t *pgd_p;
+	pgd_t *pgd;
+	p4d_t *p4d;
 
 	/* Install the espfix pud into the kernel page directory */
-	pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
-	pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
+	pgd = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
+	p4d = p4d_alloc(&init_mm, pgd, ESPFIX_BASE_ADDR);
+	p4d_populate(&init_mm, p4d, espfix_pud_page);
 
 	/* Randomize the locations */
 	init_espfix_random();
-- 
2.11.0

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>