Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

5 files changed, 87 insertions, 54 deletions

diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
index 1cd792db15ef..1eab79c9ac48 100644
--- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S
+++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
@@ -117,11 +117,10 @@
 	.set T1, REG_T1
 .endm
 
-#define K_BASE		%r8
 #define HASH_PTR	%r9
+#define BLOCKS_CTR	%r8
 #define BUFFER_PTR	%r10
 #define BUFFER_PTR2	%r13
-#define BUFFER_END	%r11
 
 #define PRECALC_BUF	%r14
 #define WK_BUF		%r15
@@ -205,14 +204,14 @@
 		 * blended AVX2 and ALU instruction scheduling
 		 * 1 vector iteration per 8 rounds
 		 */
-		vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP
+		vmovdqu (i * 2)(BUFFER_PTR), W_TMP
 	.elseif ((i & 7) == 1)
-		vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\
+		vinsertf128 $1, ((i-1) * 2)(BUFFER_PTR2),\
 			 WY_TMP, WY_TMP
 	.elseif ((i & 7) == 2)
 		vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY
 	.elseif ((i & 7) == 4)
-		vpaddd  K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 	.elseif ((i & 7) == 7)
 		vmovdqu  WY_TMP, PRECALC_WK(i&~7)
 
@@ -255,7 +254,7 @@
 		vpxor	WY, WY_TMP, WY_TMP
 	.elseif ((i & 7) == 7)
 		vpxor	WY_TMP2, WY_TMP, WY
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -291,7 +290,7 @@
 		vpsrld	$30, WY, WY
 		vpor	WY, WY_TMP, WY
 	.elseif ((i & 7) == 7)
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -446,6 +445,16 @@
 
 .endm
 
+/* Add constant only if (%2 > %3) condition met (uses RTA as temp)
+ * %1 + %2 >= %3 ? %4 : 0
+ */
+.macro ADD_IF_GE a, b, c, d
+	mov     \a, RTA
+	add     $\d, RTA
+	cmp     $\c, \b
+	cmovge  RTA, \a
+.endm
+
 /*
  * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining
  */
@@ -463,13 +472,16 @@
 	lea	(2*4*80+32)(%rsp), WK_BUF
 
 	# Precalc WK for first 2 blocks
-	PRECALC_OFFSET = 0
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 2, 64
 	.set i, 0
 	.rept    160
 		PRECALC i
 		.set i, i + 1
 	.endr
-	PRECALC_OFFSET = 128
+
+	/* Go to next block if needed */
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 3, 128
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 	xchg	WK_BUF, PRECALC_BUF
 
 	.align 32
@@ -479,8 +491,8 @@ _loop:
 	 * we use K_BASE value as a signal of a last block,
 	 * it is set below by: cmovae BUFFER_PTR, K_BASE
 	 */
-	cmp	K_BASE, BUFFER_PTR
-	jne	_begin
+	test BLOCKS_CTR, BLOCKS_CTR
+	jnz _begin
 	.align 32
 	jmp	_end
 	.align 32
@@ -512,10 +524,10 @@ _loop0:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR       /* move to next odd-64-byte block */
-	cmp	BUFFER_END, BUFFER_PTR    /* is current block the last one? */
-	cmovae	K_BASE, BUFFER_PTR	/* signal the last iteration smartly */
-
+	/* Update Counter */
+	sub $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 4, 128
 	/*
 	 * rounds
 	 * 60,62,64,66,68
@@ -532,8 +544,8 @@ _loop0:
 	UPDATE_HASH	12(HASH_PTR), D
 	UPDATE_HASH	16(HASH_PTR), E
 
-	cmp	K_BASE, BUFFER_PTR	/* is current block the last one? */
-	je	_loop
+	test	BLOCKS_CTR, BLOCKS_CTR
+	jz	_loop
 
 	mov	TB, B
 
@@ -575,10 +587,10 @@ _loop2:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR2      /* move to next even-64-byte block */
-
-	cmp	BUFFER_END, BUFFER_PTR2   /* is current block the last one */
-	cmovae	K_BASE, BUFFER_PTR       /* signal the last iteration smartly */
+	/* update counter */
+	sub     $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 
 	jmp	_loop3
 _loop3:
@@ -641,19 +653,12 @@ _loop3:
 
 	avx2_zeroupper
 
-	lea	K_XMM_AR(%rip), K_BASE
-
+	/* Setup initial values */
 	mov	CTX, HASH_PTR
 	mov	BUF, BUFFER_PTR
-	lea	64(BUF), BUFFER_PTR2
-
-	shl	$6, CNT			/* mul by 64 */
-	add	BUF, CNT
-	add	$64, CNT
-	mov	CNT, BUFFER_END
 
-	cmp	BUFFER_END, BUFFER_PTR2
-	cmovae	K_BASE, BUFFER_PTR2
+	mov	BUF, BUFFER_PTR2
+	mov	CNT, BLOCKS_CTR
 
 	xmm_mov	BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP
 
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index f960a043cdeb..fc61739150e7 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -201,7 +201,7 @@ asmlinkage void sha1_transform_avx2(u32 *digest, const char *data,
 
 static bool avx2_usable(void)
 {
-	if (false && avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
+	if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
 		&& boot_cpu_has(X86_FEATURE_BMI1)
 		&& boot_cpu_has(X86_FEATURE_BMI2))
 		return true;
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 21126155a739..0ead9dbb9130 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -43,6 +43,9 @@ struct hypervisor_x86 {
 
 	/* pin current vcpu to specified physical cpu (run rarely) */
 	void		(*pin_vcpu)(int);
+
+	/* called during init_mem_mapping() to setup early mappings. */
+	void		(*init_mem_mapping)(void);
 };
 
 extern const struct hypervisor_x86 *x86_hyper;
@@ -57,8 +60,15 @@ extern const struct hypervisor_x86 x86_hyper_kvm;
 extern void init_hypervisor_platform(void);
 extern bool hypervisor_x2apic_available(void);
 extern void hypervisor_pin_vcpu(int cpu);
+
+static inline void hypervisor_init_mem_mapping(void)
+{
+	if (x86_hyper && x86_hyper->init_mem_mapping)
+		x86_hyper->init_mem_mapping();
+}
 #else
 static inline void init_hypervisor_platform(void) { }
 static inline bool hypervisor_x2apic_available(void) { return false; }
+static inline void hypervisor_init_mem_mapping(void) { }
 #endif /* CONFIG_HYPERVISOR_GUEST */
 #endif /* _ASM_X86_HYPERVISOR_H */
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 673541eb3b3f..bf3f1065d6ad 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -18,6 +18,7 @@
 #include <asm/dma.h>		/* for MAX_DMA_PFN */
 #include <asm/microcode.h>
 #include <asm/kaslr.h>
+#include <asm/hypervisor.h>
 
 /*
  * We need to define the tracepoints somewhere, and tlb.c
@@ -636,6 +637,8 @@ void __init init_mem_mapping(void)
 	load_cr3(swapper_pg_dir);
 	__flush_tlb_all();
 
+	hypervisor_init_mem_mapping();
+
 	early_memtest(0, max_pfn_mapped << PAGE_SHIFT);
 }
 
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 87d791356ea9..de503c225ae1 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -12,6 +12,7 @@
 #include <asm/setup.h>
 #include <asm/hypervisor.h>
 #include <asm/e820/api.h>
+#include <asm/early_ioremap.h>
 
 #include <asm/xen/cpuid.h>
 #include <asm/xen/hypervisor.h>
@@ -21,38 +22,50 @@
 #include "mmu.h"
 #include "smp.h"
 
-void __ref xen_hvm_init_shared_info(void)
+static unsigned long shared_info_pfn;
+
+void xen_hvm_init_shared_info(void)
 {
 	struct xen_add_to_physmap xatp;
-	u64 pa;
-
-	if (HYPERVISOR_shared_info == &xen_dummy_shared_info) {
-		/*
-		 * Search for a free page starting at 4kB physical address.
-		 * Low memory is preferred to avoid an EPT large page split up
-		 * by the mapping.
-		 * Starting below X86_RESERVE_LOW (usually 64kB) is fine as
-		 * the BIOS used for HVM guests is well behaved and won't
-		 * clobber memory other than the first 4kB.
-		 */
-		for (pa = PAGE_SIZE;
-		     !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) ||
-		     memblock_is_reserved(pa);
-		     pa += PAGE_SIZE)
-			;
-
-		memblock_reserve(pa, PAGE_SIZE);
-		HYPERVISOR_shared_info = __va(pa);
-	}
 
 	xatp.domid = DOMID_SELF;
 	xatp.idx = 0;
 	xatp.space = XENMAPSPACE_shared_info;
-	xatp.gpfn = virt_to_pfn(HYPERVISOR_shared_info);
+	xatp.gpfn = shared_info_pfn;
 	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
 		BUG();
 }
 
+static void __init reserve_shared_info(void)
+{
+	u64 pa;
+
+	/*
+	 * Search for a free page starting at 4kB physical address.
+	 * Low memory is preferred to avoid an EPT large page split up
+	 * by the mapping.
+	 * Starting below X86_RESERVE_LOW (usually 64kB) is fine as
+	 * the BIOS used for HVM guests is well behaved and won't
+	 * clobber memory other than the first 4kB.
+	 */
+	for (pa = PAGE_SIZE;
+	     !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) ||
+	     memblock_is_reserved(pa);
+	     pa += PAGE_SIZE)
+		;
+
+	shared_info_pfn = PHYS_PFN(pa);
+
+	memblock_reserve(pa, PAGE_SIZE);
+	HYPERVISOR_shared_info = early_memremap(pa, PAGE_SIZE);
+}
+
+static void __init xen_hvm_init_mem_mapping(void)
+{
+	early_memunmap(HYPERVISOR_shared_info, PAGE_SIZE);
+	HYPERVISOR_shared_info = __va(PFN_PHYS(shared_info_pfn));
+}
+
 static void __init init_hvm_pv_info(void)
 {
 	int major, minor;
@@ -153,6 +166,7 @@ static void __init xen_hvm_guest_init(void)
 
 	init_hvm_pv_info();
 
+	reserve_shared_info();
 	xen_hvm_init_shared_info();
 
 	/*
@@ -218,5 +232,6 @@ const struct hypervisor_x86 x86_hyper_xen_hvm = {
 	.init_platform          = xen_hvm_guest_init,
 	.pin_vcpu               = xen_pin_vcpu,
 	.x2apic_available       = xen_x2apic_para_available,
+	.init_mem_mapping	= xen_hvm_init_mem_mapping,
 };
 EXPORT_SYMBOL(x86_hyper_xen_hvm);