Merge tag 'x86_misc_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull misc x86 updates from Borislav Petkov:

 - Remove the local symbols prefix of the get/put_user() exception
   handling symbols so that tools do not get confused by the presence of
   code belonging to the wrong symbol/not belonging to any symbol

 - Improve csum_partial()'s performance

 - Some improvements to the kcpuid tool

* tag 'x86_misc_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/lib: Make get/put_user() exception handling a visible symbol
  x86/csum: Fix clang -Wuninitialized in csum_partial()
  x86/csum: Improve performance of `csum_partial`
  tools/x86/kcpuid: Add .gitignore
  tools/x86/kcpuid: Dump the correct CPUID function in error

arch/x86/lib/csum-partial_64.c

@@ -5,22 +5,34 @@
  * This file contains network checksum routines that are better done
  * in an architecture-specific manner due to speed.
  */
- 
+
 #include <linux/compiler.h>
 #include <linux/export.h>
 #include <asm/checksum.h>
 #include <asm/word-at-a-time.h>
 
-static inline unsigned short from32to16(unsigned a) 
+static inline unsigned short from32to16(unsigned a)
 {
-	unsigned short b = a >> 16; 
+	unsigned short b = a >> 16;
 	asm("addw %w2,%w0\n\t"
-	    "adcw $0,%w0\n" 
+	    "adcw $0,%w0\n"
 	    : "=r" (b)
 	    : "0" (b), "r" (a));
 	return b;
 }
 
+static inline __wsum csum_tail(u64 temp64, int odd)
+{
+	unsigned int result;
+
+	result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff);
+	if (unlikely(odd)) {
+		result = from32to16(result);
+		result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
+	}
+	return (__force __wsum)result;
+}
+
 /*
  * Do a checksum on an arbitrary memory area.
  * Returns a 32bit checksum.
@@ -35,7 +47,7 @@ static inline unsigned short from32to16(unsigned a)
 __wsum csum_partial(const void *buff, int len, __wsum sum)
 {
 	u64 temp64 = (__force u64)sum;
-	unsigned odd, result;
+	unsigned odd;
 
 	odd = 1 & (unsigned long) buff;
 	if (unlikely(odd)) {
@@ -47,21 +59,52 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
 		buff++;
 	}
 
-	while (unlikely(len >= 64)) {
+	/*
+	 * len == 40 is the hot case due to IPv6 headers, but annotating it likely()
+	 * has noticeable negative affect on codegen for all other cases with
+	 * minimal performance benefit here.
+	 */
+	if (len == 40) {
 		asm("addq 0*8(%[src]),%[res]\n\t"
 		    "adcq 1*8(%[src]),%[res]\n\t"
 		    "adcq 2*8(%[src]),%[res]\n\t"
 		    "adcq 3*8(%[src]),%[res]\n\t"
 		    "adcq 4*8(%[src]),%[res]\n\t"
-		    "adcq 5*8(%[src]),%[res]\n\t"
-		    "adcq 6*8(%[src]),%[res]\n\t"
-		    "adcq 7*8(%[src]),%[res]\n\t"
 		    "adcq $0,%[res]"
-		    : [res] "+r" (temp64)
-		    : [src] "r" (buff)
-		    : "memory");
-		buff += 64;
-		len -= 64;
+		    : [res] "+r"(temp64)
+		    : [src] "r"(buff), "m"(*(const char(*)[40])buff));
+		return csum_tail(temp64, odd);
+	}
+	if (unlikely(len >= 64)) {
+		/*
+		 * Extra accumulators for better ILP in the loop.
+		 */
+		u64 tmp_accum, tmp_carries;
+
+		asm("xorl %k[tmp_accum],%k[tmp_accum]\n\t"
+		    "xorl %k[tmp_carries],%k[tmp_carries]\n\t"
+		    "subl $64, %[len]\n\t"
+		    "1:\n\t"
+		    "addq 0*8(%[src]),%[res]\n\t"
+		    "adcq 1*8(%[src]),%[res]\n\t"
+		    "adcq 2*8(%[src]),%[res]\n\t"
+		    "adcq 3*8(%[src]),%[res]\n\t"
+		    "adcl $0,%k[tmp_carries]\n\t"
+		    "addq 4*8(%[src]),%[tmp_accum]\n\t"
+		    "adcq 5*8(%[src]),%[tmp_accum]\n\t"
+		    "adcq 6*8(%[src]),%[tmp_accum]\n\t"
+		    "adcq 7*8(%[src]),%[tmp_accum]\n\t"
+		    "adcl $0,%k[tmp_carries]\n\t"
+		    "addq $64, %[src]\n\t"
+		    "subl $64, %[len]\n\t"
+		    "jge 1b\n\t"
+		    "addq %[tmp_accum],%[res]\n\t"
+		    "adcq %[tmp_carries],%[res]\n\t"
+		    "adcq $0,%[res]"
+		    : [tmp_accum] "=&r"(tmp_accum),
+		      [tmp_carries] "=&r"(tmp_carries), [res] "+r"(temp64),
+		      [len] "+r"(len), [src] "+r"(buff)
+		    : "m"(*(const char *)buff));
 	}
 
 	if (len & 32) {
@@ -70,45 +113,37 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
 		    "adcq 2*8(%[src]),%[res]\n\t"
 		    "adcq 3*8(%[src]),%[res]\n\t"
 		    "adcq $0,%[res]"
-			: [res] "+r" (temp64)
-			: [src] "r" (buff)
-			: "memory");
+		    : [res] "+r"(temp64)
+		    : [src] "r"(buff), "m"(*(const char(*)[32])buff));
 		buff += 32;
 	}
 	if (len & 16) {
 		asm("addq 0*8(%[src]),%[res]\n\t"
 		    "adcq 1*8(%[src]),%[res]\n\t"
 		    "adcq $0,%[res]"
-			: [res] "+r" (temp64)
-			: [src] "r" (buff)
-			: "memory");
+		    : [res] "+r"(temp64)
+		    : [src] "r"(buff), "m"(*(const char(*)[16])buff));
 		buff += 16;
 	}
 	if (len & 8) {
 		asm("addq 0*8(%[src]),%[res]\n\t"
 		    "adcq $0,%[res]"
-			: [res] "+r" (temp64)
-			: [src] "r" (buff)
-			: "memory");
+		    : [res] "+r"(temp64)
+		    : [src] "r"(buff), "m"(*(const char(*)[8])buff));
 		buff += 8;
 	}
 	if (len & 7) {
-		unsigned int shift = (8 - (len & 7)) * 8;
+		unsigned int shift = (-len << 3) & 63;
 		unsigned long trail;
 
 		trail = (load_unaligned_zeropad(buff) << shift) >> shift;
 
 		asm("addq %[trail],%[res]\n\t"
 		    "adcq $0,%[res]"
-			: [res] "+r" (temp64)
-			: [trail] "r" (trail));
+		    : [res] "+r"(temp64)
+		    : [trail] "r"(trail));
 	}
-	result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff);
-	if (unlikely(odd)) {
-		result = from32to16(result);
-		result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
-	}
-	return (__force __wsum)result;
+	return csum_tail(temp64, odd);
 }
 EXPORT_SYMBOL(csum_partial);
 
@@ -118,6 +153,6 @@ EXPORT_SYMBOL(csum_partial);
  */
 __sum16 ip_compute_csum(const void *buff, int len)
 {
-	return csum_fold(csum_partial(buff,len,0));
+	return csum_fold(csum_partial(buff, len, 0));
 }
 EXPORT_SYMBOL(ip_compute_csum);

arch/x86/lib/getuser.S

@@ -143,43 +143,43 @@ SYM_FUNC_END(__get_user_nocheck_8)
 EXPORT_SYMBOL(__get_user_nocheck_8)
 
 
-SYM_CODE_START_LOCAL(.Lbad_get_user_clac)
+SYM_CODE_START_LOCAL(__get_user_handle_exception)
 	ASM_CLAC
 .Lbad_get_user:
 	xor %edx,%edx
 	mov $(-EFAULT),%_ASM_AX
 	RET
-SYM_CODE_END(.Lbad_get_user_clac)
+SYM_CODE_END(__get_user_handle_exception)
 
 #ifdef CONFIG_X86_32
-SYM_CODE_START_LOCAL(.Lbad_get_user_8_clac)
+SYM_CODE_START_LOCAL(__get_user_8_handle_exception)
 	ASM_CLAC
 bad_get_user_8:
 	xor %edx,%edx
 	xor %ecx,%ecx
 	mov $(-EFAULT),%_ASM_AX
 	RET
-SYM_CODE_END(.Lbad_get_user_8_clac)
+SYM_CODE_END(__get_user_8_handle_exception)
 #endif
 
 /* get_user */
-	_ASM_EXTABLE(1b, .Lbad_get_user_clac)
-	_ASM_EXTABLE(2b, .Lbad_get_user_clac)
-	_ASM_EXTABLE(3b, .Lbad_get_user_clac)
+	_ASM_EXTABLE(1b, __get_user_handle_exception)
+	_ASM_EXTABLE(2b, __get_user_handle_exception)
+	_ASM_EXTABLE(3b, __get_user_handle_exception)
 #ifdef CONFIG_X86_64
-	_ASM_EXTABLE(4b, .Lbad_get_user_clac)
+	_ASM_EXTABLE(4b, __get_user_handle_exception)
 #else
-	_ASM_EXTABLE(4b, .Lbad_get_user_8_clac)
-	_ASM_EXTABLE(5b, .Lbad_get_user_8_clac)
+	_ASM_EXTABLE(4b, __get_user_8_handle_exception)
+	_ASM_EXTABLE(5b, __get_user_8_handle_exception)
 #endif
 
 /* __get_user */
-	_ASM_EXTABLE(6b, .Lbad_get_user_clac)
-	_ASM_EXTABLE(7b, .Lbad_get_user_clac)
-	_ASM_EXTABLE(8b, .Lbad_get_user_clac)
+	_ASM_EXTABLE(6b, __get_user_handle_exception)
+	_ASM_EXTABLE(7b, __get_user_handle_exception)
+	_ASM_EXTABLE(8b, __get_user_handle_exception)
 #ifdef CONFIG_X86_64
-	_ASM_EXTABLE(9b, .Lbad_get_user_clac)
+	_ASM_EXTABLE(9b, __get_user_handle_exception)
 #else
-	_ASM_EXTABLE(9b, .Lbad_get_user_8_clac)
-	_ASM_EXTABLE(10b, .Lbad_get_user_8_clac)
+	_ASM_EXTABLE(9b, __get_user_8_handle_exception)
+	_ASM_EXTABLE(10b, __get_user_8_handle_exception)
 #endif

arch/x86/lib/putuser.S

@@ -131,22 +131,22 @@ SYM_FUNC_START(__put_user_nocheck_8)
 SYM_FUNC_END(__put_user_nocheck_8)
 EXPORT_SYMBOL(__put_user_nocheck_8)
 
-SYM_CODE_START_LOCAL(.Lbad_put_user_clac)
+SYM_CODE_START_LOCAL(__put_user_handle_exception)
 	ASM_CLAC
 .Lbad_put_user:
 	movl $-EFAULT,%ecx
 	RET
-SYM_CODE_END(.Lbad_put_user_clac)
+SYM_CODE_END(__put_user_handle_exception)
 
-	_ASM_EXTABLE(1b, .Lbad_put_user_clac)
-	_ASM_EXTABLE(2b, .Lbad_put_user_clac)
-	_ASM_EXTABLE(3b, .Lbad_put_user_clac)
-	_ASM_EXTABLE(4b, .Lbad_put_user_clac)
-	_ASM_EXTABLE(5b, .Lbad_put_user_clac)
-	_ASM_EXTABLE(6b, .Lbad_put_user_clac)
-	_ASM_EXTABLE(7b, .Lbad_put_user_clac)
-	_ASM_EXTABLE(9b, .Lbad_put_user_clac)
+	_ASM_EXTABLE(1b, __put_user_handle_exception)
+	_ASM_EXTABLE(2b, __put_user_handle_exception)
+	_ASM_EXTABLE(3b, __put_user_handle_exception)
+	_ASM_EXTABLE(4b, __put_user_handle_exception)
+	_ASM_EXTABLE(5b, __put_user_handle_exception)
+	_ASM_EXTABLE(6b, __put_user_handle_exception)
+	_ASM_EXTABLE(7b, __put_user_handle_exception)
+	_ASM_EXTABLE(9b, __put_user_handle_exception)
 #ifdef CONFIG_X86_32
-	_ASM_EXTABLE(8b, .Lbad_put_user_clac)
-	_ASM_EXTABLE(10b, .Lbad_put_user_clac)
+	_ASM_EXTABLE(8b, __put_user_handle_exception)
+	_ASM_EXTABLE(10b, __put_user_handle_exception)
 #endif

lib/Kconfig.debug

@@ -2453,6 +2453,23 @@ config BITFIELD_KUNIT
 
 	  If unsure, say N.
 
+config CHECKSUM_KUNIT
+	tristate "KUnit test checksum functions at runtime" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  Enable this option to test the checksum functions at boot.
+
+	  KUnit tests run during boot and output the results to the debug log
+	  in TAP format (http://testanything.org/). Only useful for kernel devs
+	  running the KUnit test harness, and not intended for inclusion into a
+	  production build.
+
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
 config HASH_KUNIT_TEST
 	tristate "KUnit Test for integer hash functions" if !KUNIT_ALL_TESTS
 	depends on KUNIT

lib/Makefile

@@ -377,6 +377,7 @@ obj-$(CONFIG_PLDMFW) += pldmfw/
 # KUnit tests
 CFLAGS_bitfield_kunit.o := $(DISABLE_STRUCTLEAK_PLUGIN)
 obj-$(CONFIG_BITFIELD_KUNIT) += bitfield_kunit.o
+obj-$(CONFIG_CHECKSUM_KUNIT) += checksum_kunit.o
 obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o
 obj-$(CONFIG_HASHTABLE_KUNIT_TEST) += hashtable_test.o
 obj-$(CONFIG_LINEAR_RANGES_TEST) += test_linear_ranges.o

tools/arch/x86/kcpuid/.gitignore

+kcpuid

tools/arch/x86/kcpuid/kcpuid.c

@@ -517,15 +517,16 @@ static void show_range(struct cpuid_range *range)
 static inline struct cpuid_func *index_to_func(u32 index)
 {
 	struct cpuid_range *range;
+	u32 func_idx;
 
 	range = (index & 0x80000000) ? leafs_ext : leafs_basic;
-	index &= 0x7FFFFFFF;
+	func_idx = index & 0xffff;
 
-	if (((index & 0xFFFF) + 1) > (u32)range->nr) {
+	if ((func_idx + 1) > (u32)range->nr) {
 		printf("ERR: invalid input index (0x%x)\n", index);
 		return NULL;
 	}
-	return &range->funcs[index];
+	return &range->funcs[func_idx];
 }
 
 static void show_info(void)