[tip: x86/mm] x86/mm/pae: Get rid of set_64bit()

[tip-bot2 for Peter Zijlstra]

The following commit has been merged into the x86/mm branch of tip:

Commit-ID:     d4a72e7fe61a1ea9ad4accf3532411ca685eaead
Gitweb:        https://git.kernel.org/tip/d4a72e7fe61a1ea9ad4accf3532411ca685eaead
Author:        Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate:    Fri, 21 Oct 2022 13:36:24 +02:00
Committer:     Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
CommitterDate: Thu, 15 Dec 2022 10:37:27 -08:00

x86/mm/pae: Get rid of set_64bit()

Recognise that set_64bit() is a special case of our previously
introduced pxx_xchg64(), so use that and get rid of set_64bit().

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20221022114425.233481884%40infradead.org
---
 arch/x86/include/asm/cmpxchg_32.h     | 28 +--------------------------
 arch/x86/include/asm/pgtable-3level.h | 23 ++++++++++-----------
 2 files changed, 12 insertions(+), 39 deletions(-)

diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index 215f5a6..6ba80ce 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/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 93c82c6..967b135 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -19,7 +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
@@ -34,12 +42,12 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte)
 
 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)
@@ -47,7 +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));
 }
 
 /*
@@ -91,13 +99,6 @@ static inline void pud_clear(pud_t *pudp)
 }
 
 
-#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);						\
-})
-
 #ifdef CONFIG_SMP
 static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
 {