Merge tag 'x86_mm_for_6.2_v2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm updates from Dave Hansen:
 "New Feature:

   - Randomize the per-cpu entry areas

  Cleanups:

   - Have CR3_ADDR_MASK use PHYSICAL_PAGE_MASK instead of open coding it

   - Move to "native" set_memory_rox() helper

   - Clean up pmd_get_atomic() and i386-PAE

   - Remove some unused page table size macros"

* tag 'x86_mm_for_6.2_v2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (35 commits)
  x86/mm: Ensure forced page table splitting
  x86/kasan: Populate shadow for shared chunk of the CPU entry area
  x86/kasan: Add helpers to align shadow addresses up and down
  x86/kasan: Rename local CPU_ENTRY_AREA variables to shorten names
  x86/mm: Populate KASAN shadow for entire per-CPU range of CPU entry area
  x86/mm: Recompute physical address for every page of per-CPU CEA mapping
  x86/mm: Rename __change_page_attr_set_clr(.checkalias)
  x86/mm: Inhibit _PAGE_NX changes from cpa_process_alias()
  x86/mm: Untangle __change_page_attr_set_clr(.checkalias)
  x86/mm: Add a few comments
  x86/mm: Fix CR3_ADDR_MASK
  x86/mm: Remove P*D_PAGE_MASK and P*D_PAGE_SIZE macros
  mm: Convert __HAVE_ARCH_P..P_GET to the new style
  mm: Remove pointless barrier() after pmdp_get_lockless()
  x86/mm/pae: Get rid of set_64bit()
  x86_64: Remove pointless set_64bit() usage
  x86/mm/pae: Be consistent with pXXp_get_and_clear()
  x86/mm/pae: Use WRITE_ONCE()
  x86/mm/pae: Don't (ab)use atomic64
  mm/gup: Fix the lockless PMD access
  ...

12 files changed, 60 insertions, 188 deletions

diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index 215f5a65790f..6ba80ce9438d 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -7,34 +7,6 @@
  *       you need to test for the feature in boot_cpu_data.
  */
 
-/*
- * CMPXCHG8B only writes to the target if we had the previous
- * value in registers, otherwise it acts as a read and gives us the
- * "new previous" value.  That is why there is a loop.  Preloading
- * EDX:EAX is a performance optimization: in the common case it means
- * we need only one locked operation.
- *
- * A SIMD/3DNOW!/MMX/FPU 64-bit store here would require at the very
- * least an FPU save and/or %cr0.ts manipulation.
- *
- * cmpxchg8b must be used with the lock prefix here to allow the
- * instruction to be executed atomically.  We need to have the reader
- * side to see the coherent 64bit value.
- */
-static inline void set_64bit(volatile u64 *ptr, u64 value)
-{
-	u32 low  = value;
-	u32 high = value >> 32;
-	u64 prev = *ptr;
-
-	asm volatile("\n1:\t"
-		     LOCK_PREFIX "cmpxchg8b %0\n\t"
-		     "jnz 1b"
-		     : "=m" (*ptr), "+A" (prev)
-		     : "b" (low), "c" (high)
-		     : "memory");
-}
-
 #ifdef CONFIG_X86_CMPXCHG64
 #define arch_cmpxchg64(ptr, o, n)					\
 	((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 250187ac8248..0d3beb27b7fe 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -2,11 +2,6 @@
 #ifndef _ASM_X86_CMPXCHG_64_H
 #define _ASM_X86_CMPXCHG_64_H
 
-static inline void set_64bit(volatile u64 *ptr, u64 val)
-{
-	*ptr = val;
-}
-
 #define arch_cmpxchg64(ptr, o, n)					\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index 75efc4c6f076..462fc34f1317 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -130,10 +130,6 @@ struct cpu_entry_area {
 };
 
 #define CPU_ENTRY_AREA_SIZE		(sizeof(struct cpu_entry_area))
-#define CPU_ENTRY_AREA_ARRAY_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
-
-/* Total size includes the readonly IDT mapping page as well: */
-#define CPU_ENTRY_AREA_TOTAL_SIZE	(CPU_ENTRY_AREA_ARRAY_SIZE + PAGE_SIZE)
 
 DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
 DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks);
diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h
index 13e70da38bed..de75306b932e 100644
--- a/arch/x86/include/asm/kasan.h
+++ b/arch/x86/include/asm/kasan.h
@@ -28,9 +28,12 @@
 #ifdef CONFIG_KASAN
 void __init kasan_early_init(void);
 void __init kasan_init(void);
+void __init kasan_populate_shadow_for_vaddr(void *va, size_t size, int nid);
 #else
 static inline void kasan_early_init(void) { }
 static inline void kasan_init(void) { }
+static inline void kasan_populate_shadow_for_vaddr(void *va, size_t size,
+						   int nid) { }
 #endif
 
 #endif
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index a506a411474d..86bd4311daf8 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -11,20 +11,14 @@
 #define PAGE_SIZE		(_AC(1,UL) << PAGE_SHIFT)
 #define PAGE_MASK		(~(PAGE_SIZE-1))
 
-#define PMD_PAGE_SIZE		(_AC(1, UL) << PMD_SHIFT)
-#define PMD_PAGE_MASK		(~(PMD_PAGE_SIZE-1))
-
-#define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
-#define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))
-
 #define __VIRTUAL_MASK		((1UL << __VIRTUAL_MASK_SHIFT) - 1)
 
-/* Cast *PAGE_MASK to a signed type so that it is sign-extended if
+/* Cast P*D_MASK to a signed type so that it is sign-extended if
    virtual addresses are 32-bits but physical addresses are larger
    (ie, 32-bit PAE). */
 #define PHYSICAL_PAGE_MASK	(((signed long)PAGE_MASK) & __PHYSICAL_MASK)
-#define PHYSICAL_PMD_PAGE_MASK	(((signed long)PMD_PAGE_MASK) & __PHYSICAL_MASK)
-#define PHYSICAL_PUD_PAGE_MASK	(((signed long)PUD_PAGE_MASK) & __PHYSICAL_MASK)
+#define PHYSICAL_PMD_PAGE_MASK	(((signed long)PMD_MASK) & __PHYSICAL_MASK)
+#define PHYSICAL_PUD_PAGE_MASK	(((signed long)PUD_MASK) & __PHYSICAL_MASK)
 
 #define HPAGE_SHIFT		PMD_SHIFT
 #define HPAGE_SIZE		(_AC(1,UL) << HPAGE_SHIFT)
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 28421a887209..967b135fa2c0 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -2,8 +2,6 @@
 #ifndef _ASM_X86_PGTABLE_3LEVEL_H
 #define _ASM_X86_PGTABLE_3LEVEL_H
 
-#include <asm/atomic64_32.h>
-
 /*
  * Intel Physical Address Extension (PAE) Mode - three-level page
  * tables on PPro+ CPUs.
@@ -21,7 +19,15 @@
 	pr_err("%s:%d: bad pgd %p(%016Lx)\n",				\
 	       __FILE__, __LINE__, &(e), pgd_val(e))
 
-/* Rules for using set_pte: the pte being assigned *must* be
+#define pxx_xchg64(_pxx, _ptr, _val) ({					\
+	_pxx##val_t *_p = (_pxx##val_t *)_ptr;				\
+	_pxx##val_t _o = *_p;						\
+	do { } while (!try_cmpxchg64(_p, &_o, (_val)));			\
+	native_make_##_pxx(_o);						\
+})
+
+/*
+ * Rules for using set_pte: the pte being assigned *must* be
  * either not present or in a state where the hardware will
  * not attempt to update the pte.  In places where this is
  * not possible, use pte_get_and_clear to obtain the old pte
@@ -29,75 +35,19 @@
  */
 static inline void native_set_pte(pte_t *ptep, pte_t pte)
 {
-	ptep->pte_high = pte.pte_high;
+	WRITE_ONCE(ptep->pte_high, pte.pte_high);
 	smp_wmb();
-	ptep->pte_low = pte.pte_low;
-}
-
-#define pmd_read_atomic pmd_read_atomic
-/*
- * pte_offset_map_lock() on 32-bit PAE kernels was reading the pmd_t with
- * a "*pmdp" dereference done by GCC. Problem is, in certain places
- * where pte_offset_map_lock() is called, concurrent page faults are
- * allowed, if the mmap_lock is hold for reading. An example is mincore
- * vs page faults vs MADV_DONTNEED. On the page fault side
- * pmd_populate() rightfully does a set_64bit(), but if we're reading the
- * pmd_t with a "*pmdp" on the mincore side, a SMP race can happen
- * because GCC will not read the 64-bit value of the pmd atomically.
- *
- * To fix this all places running pte_offset_map_lock() while holding the
- * mmap_lock in read mode, shall read the pmdp pointer using this
- * function to know if the pmd is null or not, and in turn to know if
- * they can run pte_offset_map_lock() or pmd_trans_huge() or other pmd
- * operations.
- *
- * Without THP if the mmap_lock is held for reading, the pmd can only
- * transition from null to not null while pmd_read_atomic() runs. So
- * we can always return atomic pmd values with this function.
- *
- * With THP if the mmap_lock is held for reading, the pmd can become
- * trans_huge or none or point to a pte (and in turn become "stable")
- * at any time under pmd_read_atomic(). We could read it truly
- * atomically here with an atomic64_read() for the THP enabled case (and
- * it would be a whole lot simpler), but to avoid using cmpxchg8b we
- * only return an atomic pmdval if the low part of the pmdval is later
- * found to be stable (i.e. pointing to a pte). We are also returning a
- * 'none' (zero) pmdval if the low part of the pmd is zero.
- *
- * In some cases the high and low part of the pmdval returned may not be
- * consistent if THP is enabled (the low part may point to previously
- * mapped hugepage, while the high part may point to a more recently
- * mapped hugepage), but pmd_none_or_trans_huge_or_clear_bad() only
- * needs the low part of the pmd to be read atomically to decide if the
- * pmd is unstable or not, with the only exception when the low part
- * of the pmd is zero, in which case we return a 'none' pmd.
- */
-static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
-{
-	pmdval_t ret;
-	u32 *tmp = (u32 *)pmdp;
-
-	ret = (pmdval_t) (*tmp);
-	if (ret) {
-		/*
-		 * If the low part is null, we must not read the high part
-		 * or we can end up with a partial pmd.
-		 */
-		smp_rmb();
-		ret |= ((pmdval_t)*(tmp + 1)) << 32;
-	}
-
-	return (pmd_t) { ret };
+	WRITE_ONCE(ptep->pte_low, pte.pte_low);
 }
 
 static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
 {
-	set_64bit((unsigned long long *)(ptep), native_pte_val(pte));
+	pxx_xchg64(pte, ptep, native_pte_val(pte));
 }
 
 static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
-	set_64bit((unsigned long long *)(pmdp), native_pmd_val(pmd));
+	pxx_xchg64(pmd, pmdp, native_pmd_val(pmd));
 }
 
 static inline void native_set_pud(pud_t *pudp, pud_t pud)
@@ -105,7 +55,7 @@ static inline void native_set_pud(pud_t *pudp, pud_t pud)
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 	pud.p4d.pgd = pti_set_user_pgtbl(&pudp->p4d.pgd, pud.p4d.pgd);
 #endif
-	set_64bit((unsigned long long *)(pudp), native_pud_val(pud));
+	pxx_xchg64(pud, pudp, native_pud_val(pud));
 }
 
 /*
@@ -116,17 +66,16 @@ static inline void native_set_pud(pud_t *pudp, pud_t pud)
 static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
 				    pte_t *ptep)
 {
-	ptep->pte_low = 0;
+	WRITE_ONCE(ptep->pte_low, 0);
 	smp_wmb();
-	ptep->pte_high = 0;
+	WRITE_ONCE(ptep->pte_high, 0);
 }
 
-static inline void native_pmd_clear(pmd_t *pmd)
+static inline void native_pmd_clear(pmd_t *pmdp)
 {
-	u32 *tmp = (u32 *)pmd;
-	*tmp = 0;
+	WRITE_ONCE(pmdp->pmd_low, 0);
 	smp_wmb();
-	*(tmp + 1) = 0;
+	WRITE_ONCE(pmdp->pmd_high, 0);
 }
 
 static inline void native_pud_clear(pud_t *pudp)
@@ -149,41 +98,26 @@ static inline void pud_clear(pud_t *pudp)
 	 */
 }
 
+
 #ifdef CONFIG_SMP
 static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
 {
-	pte_t res;
-
-	res.pte = (pteval_t)arch_atomic64_xchg((atomic64_t *)ptep, 0);
-
-	return res;
+	return pxx_xchg64(pte, ptep, 0ULL);
 }
-#else
-#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
-#endif
 
-union split_pmd {
-	struct {
-		u32 pmd_low;
-		u32 pmd_high;
-	};
-	pmd_t pmd;
-};
-
-#ifdef CONFIG_SMP
 static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
 {
-	union split_pmd res, *orig = (union split_pmd *)pmdp;
-
-	/* xchg acts as a barrier before setting of the high bits */
-	res.pmd_low = xchg(&orig->pmd_low, 0);
-	res.pmd_high = orig->pmd_high;
-	orig->pmd_high = 0;
+	return pxx_xchg64(pmd, pmdp, 0ULL);
+}
 
-	return res.pmd;
+static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
+{
+	return pxx_xchg64(pud, pudp, 0ULL);
 }
 #else
+#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
 #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
+#define native_pudp_get_and_clear(xp) native_local_pudp_get_and_clear(xp)
 #endif
 
 #ifndef pmdp_establish
@@ -199,53 +133,16 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 	 * anybody.
 	 */
 	if (!(pmd_val(pmd) & _PAGE_PRESENT)) {
-		union split_pmd old, new, *ptr;
-
-		ptr = (union split_pmd *)pmdp;
-
-		new.pmd = pmd;
-
 		/* xchg acts as a barrier before setting of the high bits */
-		old.pmd_low = xchg(&ptr->pmd_low, new.pmd_low);
-		old.pmd_high = ptr->pmd_high;
-		ptr->pmd_high = new.pmd_high;
-		return old.pmd;
-	}
-
-	do {
-		old = *pmdp;
-	} while (cmpxchg64(&pmdp->pmd, old.pmd, pmd.pmd) != old.pmd);
-
-	return old;
-}
-#endif
-
-#ifdef CONFIG_SMP
-union split_pud {
-	struct {
-		u32 pud_low;
-		u32 pud_high;
-	};
-	pud_t pud;
-};
-
-static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
-{
-	union split_pud res, *orig = (union split_pud *)pudp;
+		old.pmd_low = xchg(&pmdp->pmd_low, pmd.pmd_low);
+		old.pmd_high = READ_ONCE(pmdp->pmd_high);
+		WRITE_ONCE(pmdp->pmd_high, pmd.pmd_high);
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-	pti_set_user_pgtbl(&pudp->p4d.pgd, __pgd(0));
-#endif
-
-	/* xchg acts as a barrier before setting of the high bits */
-	res.pud_low = xchg(&orig->pud_low, 0);
-	res.pud_high = orig->pud_high;
-	orig->pud_high = 0;
+		return old;
+	}
 
-	return res.pud;
+	return pxx_xchg64(pmd, pmdp, pmd.pmd);
 }
-#else
-#define native_pudp_get_and_clear(xp) native_local_pudp_get_and_clear(xp)
 #endif
 
 /* Encode and de-code a swap entry */
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index 56baf43befb4..80911349519e 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -18,6 +18,13 @@ typedef union {
 	};
 	pteval_t pte;
 } pte_t;
+
+typedef union {
+	struct {
+		unsigned long pmd_low, pmd_high;
+	};
+	pmdval_t pmd;
+} pmd_t;
 #endif	/* !__ASSEMBLY__ */
 
 #define SHARED_KERNEL_PMD	(!static_cpu_has(X86_FEATURE_PTI))
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 04f36063ad54..38bf837e3554 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -19,6 +19,7 @@ typedef unsigned long	pgdval_t;
 typedef unsigned long	pgprotval_t;
 
 typedef struct { pteval_t pte; } pte_t;
+typedef struct { pmdval_t pmd; } pmd_t;
 
 #ifdef CONFIG_X86_5LEVEL
 extern unsigned int __pgtable_l5_enabled;
diff --git a/arch/x86/include/asm/pgtable_areas.h b/arch/x86/include/asm/pgtable_areas.h
index d34cce1b995c..4f056fb88174 100644
--- a/arch/x86/include/asm/pgtable_areas.h
+++ b/arch/x86/include/asm/pgtable_areas.h
@@ -11,6 +11,12 @@
 
 #define CPU_ENTRY_AREA_RO_IDT_VADDR	((void *)CPU_ENTRY_AREA_RO_IDT)
 
-#define CPU_ENTRY_AREA_MAP_SIZE		(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_ARRAY_SIZE - CPU_ENTRY_AREA_BASE)
+#ifdef CONFIG_X86_32
+#define CPU_ENTRY_AREA_MAP_SIZE		(CPU_ENTRY_AREA_PER_CPU +		\
+					 (CPU_ENTRY_AREA_SIZE * NR_CPUS) -	\
+					 CPU_ENTRY_AREA_BASE)
+#else
+#define CPU_ENTRY_AREA_MAP_SIZE		P4D_SIZE
+#endif
 
 #endif /* _ASM_X86_PGTABLE_AREAS_H */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index aa174fed3a71..447d4bee25c4 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -361,11 +361,9 @@ static inline pudval_t native_pud_val(pud_t pud)
 #endif
 
 #if CONFIG_PGTABLE_LEVELS > 2
-typedef struct { pmdval_t pmd; } pmd_t;
-
 static inline pmd_t native_make_pmd(pmdval_t val)
 {
-	return (pmd_t) { val };
+	return (pmd_t) { .pmd = val };
 }
 
 static inline pmdval_t native_pmd_val(pmd_t pmd)
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index 02c2cbda4a74..a7f3d9100adb 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -35,7 +35,7 @@
  */
 #ifdef CONFIG_X86_64
 /* Mask off the address space ID and SME encryption bits. */
-#define CR3_ADDR_MASK	__sme_clr(0x7FFFFFFFFFFFF000ull)
+#define CR3_ADDR_MASK	__sme_clr(PHYSICAL_PAGE_MASK)
 #define CR3_PCID_MASK	0xFFFull
 #define CR3_NOFLUSH	BIT_ULL(63)
 
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index b45c4d27fd46..a5e89641bd2d 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -6,6 +6,9 @@
 #include <asm/page.h>
 #include <asm-generic/set_memory.h>
 
+#define set_memory_rox set_memory_rox
+int set_memory_rox(unsigned long addr, int numpages);
+
 /*
  * The set_memory_* API can be used to change various attributes of a virtual
  * address range. The attributes include: