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

Lots of overlapping changes, mostly trivial in nature.

The mlxsw conflict was resolving using the example
resolution at:

https://github.com/jpirko/linux_mlxsw/blob/combined_queue/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c

Signed-off-by: David S. Miller <davem@davemloft.net>

15 files changed, 114 insertions, 67 deletions

diff --git a/tools/arch/powerpc/include/uapi/asm/unistd.h b/tools/arch/powerpc/include/uapi/asm/unistd.h
index ac5ba55066dd..985534d0b448 100644
--- a/tools/arch/powerpc/include/uapi/asm/unistd.h
+++ b/tools/arch/powerpc/include/uapi/asm/unistd.h
@@ -399,5 +399,6 @@
 #define __NR_pkey_free		385
 #define __NR_pkey_mprotect	386
 #define __NR_rseq		387
+#define __NR_io_pgetevents	388
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/tools/arch/x86/include/asm/mcsafe_test.h b/tools/arch/x86/include/asm/mcsafe_test.h
new file mode 100644
index 000000000000..2ccd588fbad4
--- /dev/null
+++ b/tools/arch/x86/include/asm/mcsafe_test.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MCSAFE_TEST_H_
+#define _MCSAFE_TEST_H_
+
+.macro MCSAFE_TEST_CTL
+.endm
+
+.macro MCSAFE_TEST_SRC reg count target
+.endm
+
+.macro MCSAFE_TEST_DST reg count target
+.endm
+#endif /* _MCSAFE_TEST_H_ */
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 9a53a06e5a3e..298ef1479240 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -3,6 +3,7 @@
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
+#include <asm/mcsafe_test.h>
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
@@ -183,12 +184,15 @@ ENTRY(memcpy_orig)
 ENDPROC(memcpy_orig)
 
 #ifndef CONFIG_UML
+
+MCSAFE_TEST_CTL
+
 /*
- * memcpy_mcsafe_unrolled - memory copy with machine check exception handling
+ * __memcpy_mcsafe - memory copy with machine check exception handling
  * Note that we only catch machine checks when reading the source addresses.
  * Writes to target are posted and don't generate machine checks.
  */
-ENTRY(memcpy_mcsafe_unrolled)
+ENTRY(__memcpy_mcsafe)
 	cmpl $8, %edx
 	/* Less than 8 bytes? Go to byte copy loop */
 	jb .L_no_whole_words
@@ -204,58 +208,33 @@ ENTRY(memcpy_mcsafe_unrolled)
 	subl $8, %ecx
 	negl %ecx
 	subl %ecx, %edx
-.L_copy_leading_bytes:
+.L_read_leading_bytes:
 	movb (%rsi), %al
+	MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes
+	MCSAFE_TEST_DST %rdi 1 .E_leading_bytes
+.L_write_leading_bytes:
 	movb %al, (%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz .L_copy_leading_bytes
+	jnz .L_read_leading_bytes
 
 .L_8byte_aligned:
-	/* Figure out how many whole cache lines (64-bytes) to copy */
-	movl %edx, %ecx
-	andl $63, %edx
-	shrl $6, %ecx
-	jz .L_no_whole_cache_lines
-
-	/* Loop copying whole cache lines */
-.L_cache_w0: movq (%rsi), %r8
-.L_cache_w1: movq 1*8(%rsi), %r9
-.L_cache_w2: movq 2*8(%rsi), %r10
-.L_cache_w3: movq 3*8(%rsi), %r11
-	movq %r8, (%rdi)
-	movq %r9, 1*8(%rdi)
-	movq %r10, 2*8(%rdi)
-	movq %r11, 3*8(%rdi)
-.L_cache_w4: movq 4*8(%rsi), %r8
-.L_cache_w5: movq 5*8(%rsi), %r9
-.L_cache_w6: movq 6*8(%rsi), %r10
-.L_cache_w7: movq 7*8(%rsi), %r11
-	movq %r8, 4*8(%rdi)
-	movq %r9, 5*8(%rdi)
-	movq %r10, 6*8(%rdi)
-	movq %r11, 7*8(%rdi)
-	leaq 64(%rsi), %rsi
-	leaq 64(%rdi), %rdi
-	decl %ecx
-	jnz .L_cache_w0
-
-	/* Are there any trailing 8-byte words? */
-.L_no_whole_cache_lines:
 	movl %edx, %ecx
 	andl $7, %edx
 	shrl $3, %ecx
 	jz .L_no_whole_words
 
-	/* Copy trailing words */
-.L_copy_trailing_words:
+.L_read_words:
 	movq (%rsi), %r8
-	mov %r8, (%rdi)
-	leaq 8(%rsi), %rsi
-	leaq 8(%rdi), %rdi
+	MCSAFE_TEST_SRC %rsi 8 .E_read_words
+	MCSAFE_TEST_DST %rdi 8 .E_write_words
+.L_write_words:
+	movq %r8, (%rdi)
+	addq $8, %rsi
+	addq $8, %rdi
 	decl %ecx
-	jnz .L_copy_trailing_words
+	jnz .L_read_words
 
 	/* Any trailing bytes? */
 .L_no_whole_words:
@@ -264,38 +243,55 @@ ENTRY(memcpy_mcsafe_unrolled)
 
 	/* Copy trailing bytes */
 	movl %edx, %ecx
-.L_copy_trailing_bytes:
+.L_read_trailing_bytes:
 	movb (%rsi), %al
+	MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes
+	MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes
+.L_write_trailing_bytes:
 	movb %al, (%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz .L_copy_trailing_bytes
+	jnz .L_read_trailing_bytes
 
 	/* Copy successful. Return zero */
 .L_done_memcpy_trap:
 	xorq %rax, %rax
 	ret
-ENDPROC(memcpy_mcsafe_unrolled)
-EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
+ENDPROC(__memcpy_mcsafe)
+EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
 
 	.section .fixup, "ax"
-	/* Return -EFAULT for any failure */
-.L_memcpy_mcsafe_fail:
-	mov	$-EFAULT, %rax
+	/*
+	 * Return number of bytes not copied for any failure. Note that
+	 * there is no "tail" handling since the source buffer is 8-byte
+	 * aligned and poison is cacheline aligned.
+	 */
+.E_read_words:
+	shll	$3, %ecx
+.E_leading_bytes:
+	addl	%edx, %ecx
+.E_trailing_bytes:
+	mov	%ecx, %eax
 	ret
 
+	/*
+	 * For write fault handling, given the destination is unaligned,
+	 * we handle faults on multi-byte writes with a byte-by-byte
+	 * copy up to the write-protected page.
+	 */
+.E_write_words:
+	shll	$3, %ecx
+	addl	%edx, %ecx
+	movl	%ecx, %edx
+	jmp mcsafe_handle_tail
+
 	.previous
 
-	_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
+	_ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
+	_ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
+	_ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
+	_ASM_EXTABLE(.L_write_words, .E_write_words)
+	_ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
 #endif
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 9c8191845585..e860ca859b28 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -35,6 +35,7 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <linux/err.h>
+#include <linux/kernel.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -91,7 +92,8 @@ static bool map_is_map_of_progs(__u32 type)
 static void *alloc_value(struct bpf_map_info *info)
 {
 	if (map_is_per_cpu(info->type))
-		return malloc(info->value_size * get_possible_cpus());
+		return malloc(round_up(info->value_size, 8) *
+			      get_possible_cpus());
 	else
 		return malloc(info->value_size);
 }
@@ -273,9 +275,10 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
 			do_dump_btf(&d, info, key, value);
 		}
 	} else {
-		unsigned int i, n;
+		unsigned int i, n, step;
 
 		n = get_possible_cpus();
+		step = round_up(info->value_size, 8);
 
 		jsonw_name(json_wtr, "key");
 		print_hex_data_json(key, info->key_size);
@@ -288,7 +291,7 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
 			jsonw_int_field(json_wtr, "cpu", i);
 
 			jsonw_name(json_wtr, "value");
-			print_hex_data_json(value + i * info->value_size,
+			print_hex_data_json(value + i * step,
 					    info->value_size);
 
 			jsonw_end_object(json_wtr);
@@ -319,9 +322,10 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
 
 		printf("\n");
 	} else {
-		unsigned int i, n;
+		unsigned int i, n, step;
 
 		n = get_possible_cpus();
+		step = round_up(info->value_size, 8);
 
 		printf("key:\n");
 		fprint_hex(stdout, key, info->key_size, " ");
@@ -329,7 +333,7 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
 		for (i = 0; i < n; i++) {
 			printf("value (CPU %02d):%c",
 			       i, info->value_size > 16 ? '\n' : ' ');
-			fprint_hex(stdout, value + i * info->value_size,
+			fprint_hex(stdout, value + i * step,
 				   info->value_size, " ");
 			printf("\n");
 		}
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index b8e288a1f740..eeb787b1c53c 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -143,6 +143,8 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 
 	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
+
+	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63,
 };
 
 /*
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index 63a74c32ddc5..e33ef5bc31c5 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 
 #include "../../util/intel-pt.h"
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 06bae7023a51..950539f9a4f7 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -2,6 +2,7 @@
 #include <stdbool.h>
 #include <errno.h>
 
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 
 #include "../../perf.h"
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index 60bf11943047..eafce1a130a1 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -7,6 +7,7 @@ perf-y += futex-wake-parallel.o
 perf-y += futex-requeue.o
 perf-y += futex-lock-pi.o
 
+perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
 perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o
 
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index b43f8d2a34ec..9ad015a1e202 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -6,6 +6,7 @@
 #define altinstr_replacement text
 #define globl p2align 4; .globl
 #define _ASM_EXTABLE_FAULT(x, y)
+#define _ASM_EXTABLE(x, y)
 
 #include "../../arch/x86/lib/memcpy_64.S"
 /*
diff --git a/tools/perf/bench/mem-memcpy-x86-64-lib.c b/tools/perf/bench/mem-memcpy-x86-64-lib.c
new file mode 100644
index 000000000000..4130734dde84
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-x86-64-lib.c
@@ -0,0 +1,24 @@
+/*
+ * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy
+ * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy'
+ * happy.
+ */
+#include <linux/types.h>
+
+unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt);
+unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len);
+
+unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len)
+{
+	for (; len; --len, to++, from++) {
+		/*
+		 * Call the assembly routine back directly since
+		 * memcpy_mcsafe() may silently fallback to memcpy.
+		 */
+		unsigned long rem = __memcpy_mcsafe(to, from, 1);
+
+		if (rem)
+			break;
+	}
+	return len;
+}
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index a1a97956136f..d215714f48df 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -5,6 +5,7 @@
 #include <time.h>
 #include <stdbool.h>
 #include <linux/types.h>
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 
 extern bool test_attr__enabled;
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 90d4577a92dc..6d7fe44aadc0 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -2,6 +2,7 @@
 #ifndef __PERF_HEADER_H
 #define __PERF_HEADER_H
 
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <sys/types.h>
 #include <stdbool.h>
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index 760558dcfd18..cae1a9a39722 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -10,6 +10,7 @@
 #define __PERF_NAMESPACES_H
 
 #include <sys/types.h>
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <linux/refcount.h>
 #include <linux/types.h>
diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
index 270fa8f49573..785eabf2a593 100755
--- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh
+++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
@@ -115,14 +115,14 @@ ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o
 ip netns exec ns2 ip -6 route add fd00::1 dev veth3 via fb00::43 scope link
 
 ip netns exec ns3 ip -6 route add fc42::1 dev veth5 via fb00::65
-ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF obj test_lwt_seg6local.o sec add_egr_x dev veth4
+ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec add_egr_x dev veth4
 
-ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF obj test_lwt_seg6local.o sec pop_egr dev veth6
+ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec pop_egr dev veth6
 ip netns exec ns4 ip -6 addr add fc42::1 dev lo
 ip netns exec ns4 ip -6 route add fd00::3 dev veth7 via fb00::87
 
 ip netns exec ns5 ip -6 route add fd00::4 table 117 dev veth9 via fb00::109
-ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF obj test_lwt_seg6local.o sec inspect_t dev veth8
+ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec inspect_t dev veth8
 
 ip netns exec ns6 ip -6 addr add fb00::6/16 dev lo
 ip netns exec ns6 ip -6 addr add fd00::4/16 dev lo
diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
index 77f762780199..e8c5dff448eb 100644
--- a/tools/testing/selftests/net/tcp_mmap.c
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -402,7 +402,7 @@ int main(int argc, char *argv[])
 		exit(1);
 	}
 
-	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	fd = socket(cfg_family, SOCK_STREAM, 0);
 	if (fd == -1) {
 		perror("socket");
 		exit(1);