[PATCH v8 4/7] x86/mm: Simplify clear_page_*

[Ankur Arora <ankur.a.arora@oracle.com>]

clear_page_rep() and clear_page_erms() are wrappers around "REP; STOS"
variations. Inlining gets rid of an unnecessary CALL/RET (which isn't
free when using RETHUNK speculative execution mitigations.)
Fixup and rename clear_page_orig() to adapt to the changed calling
convention.

Also add a comment from Dave Hansen detailing various clearing mechanisms
used in clear_page().

Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Tested-by: Raghavendra K T <raghavendra.kt@amd.com>
---
 arch/x86/include/asm/page_32.h |  6 +++++
 arch/x86/include/asm/page_64.h | 46 +++++++++++++++++++++++++---------
 arch/x86/lib/clear_page_64.S   | 39 ++++++----------------------
 3 files changed, 48 insertions(+), 43 deletions(-)

diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h
index 0c623706cb7e..19fddb002cc9 100644
--- a/arch/x86/include/asm/page_32.h
+++ b/arch/x86/include/asm/page_32.h
@@ -17,6 +17,12 @@ extern unsigned long __phys_addr(unsigned long);
 
 #include <linux/string.h>
 
+/**
+ * clear_page() - clear a page using a kernel virtual address.
+ * @page: address of kernel page
+ *
+ * Does absolutely no exception handling.
+ */
 static inline void clear_page(void *page)
 {
 	memset(page, 0, PAGE_SIZE);
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index 015d23f3e01f..df528cff90ef 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -40,23 +40,45 @@ extern unsigned long __phys_addr_symbol(unsigned long);
 
 #define __phys_reloc_hide(x)	(x)
 
-void clear_page_orig(void *page);
-void clear_page_rep(void *page);
-void clear_page_erms(void *page);
+void memzero_page_aligned_unrolled(void *addr, u64 len);
 
-static inline void clear_page(void *page)
+/**
+ * clear_page() - clear a page using a kernel virtual address.
+ * @addr: address of kernel page
+ *
+ * Switch between three implementations of page clearing based on CPU
+ * capabilities:
+ *
+ *  - memzero_page_aligned_unrolled(): the oldest, slowest and universally
+ *    supported method. Zeroes via 8-byte MOV instructions unrolled 8x
+ *    to write a 64-byte cacheline in each loop iteration..
+ *
+ *  - "rep stosq": really old CPUs had crummy REP implementations.
+ *    Vendor CPU setup code sets 'REP_GOOD' on CPUs where REP can be
+ *    trusted. The instruction writes 8-byte per REP iteration but
+ *    CPUs can internally batch these together and do larger writes.
+ *
+ *  - "rep stosb": CPUs that enumerate 'ERMS' have an improved STOS
+ *    implementation that is less picky about alignment and where
+ *    STOSB (1-byte at a time) is actually faster than STOSQ (8-bytes
+ *    at a time.)
+ *
+ * Does absolutely no exception handling.
+ */
+static inline void clear_page(void *addr)
 {
+	u64 len = PAGE_SIZE;
 	/*
 	 * Clean up KMSAN metadata for the page being cleared. The assembly call
-	 * below clobbers @page, so we perform unpoisoning before it.
+	 * below clobbers @addr, so we perform unpoisoning before it.
 	 */
-	kmsan_unpoison_memory(page, PAGE_SIZE);
-	alternative_call_2(clear_page_orig,
-			   clear_page_rep, X86_FEATURE_REP_GOOD,
-			   clear_page_erms, X86_FEATURE_ERMS,
-			   "=D" (page),
-			   "D" (page),
-			   "cc", "memory", "rax", "rcx");
+	kmsan_unpoison_memory(addr, len);
+	asm volatile(ALTERNATIVE_2("call memzero_page_aligned_unrolled",
+				   "shrq $3, %%rcx; rep stosq", X86_FEATURE_REP_GOOD,
+				   "rep stosb", X86_FEATURE_ERMS)
+			: "+c" (len), "+D" (addr), ASM_CALL_CONSTRAINT
+			: "a" (0)
+			: "cc", "memory");
 }
 
 void copy_page(void *to, void *from);
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index a508e4a8c66a..27debe0c018c 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -6,30 +6,15 @@
 #include <asm/asm.h>
 
 /*
- * Most CPUs support enhanced REP MOVSB/STOSB instructions. It is
- * recommended to use this when possible and we do use them by default.
- * If enhanced REP MOVSB/STOSB is not available, try to use fast string.
- * Otherwise, use original.
+ * Zero page aligned region.
+ * %rdi	- dest
+ * %rcx	- length
  */
-
-/*
- * Zero a page.
- * %rdi	- page
- */
-SYM_TYPED_FUNC_START(clear_page_rep)
-	movl $4096/8,%ecx
-	xorl %eax,%eax
-	rep stosq
-	RET
-SYM_FUNC_END(clear_page_rep)
-EXPORT_SYMBOL_GPL(clear_page_rep)
-
-SYM_TYPED_FUNC_START(clear_page_orig)
-	xorl   %eax,%eax
-	movl   $4096/64,%ecx
+SYM_TYPED_FUNC_START(memzero_page_aligned_unrolled)
+	shrq   $6, %rcx
 	.p2align 4
 .Lloop:
-	decl	%ecx
+	decq	%rcx
 #define PUT(x) movq %rax,x*8(%rdi)
 	movq %rax,(%rdi)
 	PUT(1)
@@ -43,16 +28,8 @@ SYM_TYPED_FUNC_START(clear_page_orig)
 	jnz	.Lloop
 	nop
 	RET
-SYM_FUNC_END(clear_page_orig)
-EXPORT_SYMBOL_GPL(clear_page_orig)
-
-SYM_TYPED_FUNC_START(clear_page_erms)
-	movl $4096,%ecx
-	xorl %eax,%eax
-	rep stosb
-	RET
-SYM_FUNC_END(clear_page_erms)
-EXPORT_SYMBOL_GPL(clear_page_erms)
+SYM_FUNC_END(memzero_page_aligned_unrolled)
+EXPORT_SYMBOL_GPL(memzero_page_aligned_unrolled)
 
 /*
  * Default clear user-space.
-- 
2.43.5