perf bench mem: Allow mapping of hugepages

Page sizes that can be selected: 4KB, 2MB, 1GB.

Both the reservation and node from which hugepages are allocated
from are expected to be addressed by the user.

An example of page-size selection:

  $ perf bench mem memset -s 4gb -p 2mb
  # Running 'mem/memset' benchmark:
  # function 'default' (Default memset() provided by glibc)
  # Copying 4gb bytes ...

        14.919194 GB/sec
  # function 'x86-64-unrolled' (unrolled memset() in arch/x86/lib/memset_64.S)
  # Copying 4gb bytes ...

        11.514503 GB/sec
  # function 'x86-64-stosq' (movsq-based memset() in arch/x86/lib/memset_64.S)
  # Copying 4gb bytes ...

          12.600568 GB/sec

Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Raghavendra K T <raghavendra.kt@amd.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

Author: terminus

tools/perf/Documentation/perf-bench.txt

@@ -177,11 +177,16 @@ Suite for evaluating performance of simple memory copy in various ways.
 
 Options of *memcpy*
 ^^^^^^^^^^^^^^^^^^^
--l::
+-s::
 --size::
 Specify size of memory to copy (default: 1MB).
 Available units are B, KB, MB, GB and TB (case insensitive).
 
+-p::
+--page::
+Specify page-size for mapping memory buffers (default: 4KB).
+Available values are 4KB, 2MB, 1GB (case insensitive).
+
 -f::
 --function::
 Specify function to copy (default: default).
@@ -201,11 +206,16 @@ Suite for evaluating performance of simple memory set in various ways.
 
 Options of *memset*
 ^^^^^^^^^^^^^^^^^^^
--l::
+-s::
 --size::
 Specify size of memory to set (default: 1MB).
 Available units are B, KB, MB, GB and TB (case insensitive).
 
+-p::
+--page::
+Specify page-size for mapping memory buffers (default: 4KB).
+Available values are 4KB, 2MB, 1GB (case insensitive).
+
 -f::
 --function::
 Specify function to set (default: default).

tools/perf/bench/mem-functions.c

@@ -25,11 +25,17 @@
 #include <sys/mman.h>
 #include <errno.h>
 #include <linux/time64.h>
+#include <linux/log2.h>
 
 #define K 1024
 
+#define PAGE_SHIFT_4KB		12
+#define PAGE_SHIFT_2MB		21
+#define PAGE_SHIFT_1GB		30
+
 static const char	*size_str	= "1MB";
 static const char	*function_str	= "all";
+static const char	*page_size_str	= "4KB";
 static unsigned int	nr_loops	= 1;
 static bool		use_cycles;
 static int		cycles_fd;
@@ -39,6 +45,10 @@ static const struct option options[] = {
 		    "Specify the size of the memory buffers. "
 		    "Available units: B, KB, MB, GB and TB (case insensitive)"),
 
+	OPT_STRING('p', "page", &page_size_str, "4KB",
+		    "Specify page-size for mapping memory buffers. "
+		    "Available sizes: 4KB, 2MB, 1GB (case insensitive)"),
+
 	OPT_STRING('f', "function", &function_str, "all",
 		    "Specify the function to run, \"all\" runs all available functions, \"help\" lists them"),
 
@@ -60,6 +70,7 @@ struct bench_params {
 	size_t		size;
 	size_t		size_total;
 	unsigned int	nr_loops;
+	unsigned int	page_shift;
 };
 
 struct bench_mem_info {
@@ -202,14 +213,16 @@ static void __bench_mem_function(struct bench_mem_info *info, struct bench_param
 	if (r->fn.fini) r->fn.fini(info, p, &src, &dst);
 	return;
 out_init_failed:
-	printf("# Memory allocation failed - maybe size (%s) is too large?\n", size_str);
+	printf("# Memory allocation failed - maybe size (%s) %s?\n", size_str,
+			p->page_shift != PAGE_SHIFT_4KB ? "has insufficient hugepages" : "is too large");
 	goto out_free;
 }
 
 static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *info)
 {
 	int i;
 	struct bench_params p = { 0 };
+	unsigned int page_size;
 
 	argc = parse_options(argc, argv, options, info->usage, 0);
 
@@ -230,6 +243,15 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *
 	}
 	p.size_total = p.size * p.nr_loops;
 
+	page_size = (unsigned int)perf_atoll((char *)page_size_str);
+	if (page_size != (1 << PAGE_SHIFT_4KB) &&
+	    page_size != (1 << PAGE_SHIFT_2MB) &&
+	    page_size != (1 << PAGE_SHIFT_1GB)) {
+		fprintf(stderr, "Invalid page-size:%s\n", page_size_str);
+		return 1;
+	}
+	p.page_shift = ilog2(page_size);
+
 	if (!strncmp(function_str, "all", 3)) {
 		for (i = 0; info->functions[i].name; i++)
 			__bench_mem_function(info, &p, i);
@@ -286,11 +308,14 @@ static int do_memcpy(const struct function *r, struct bench_params *p,
 	return 0;
 }
 
-static void *bench_mmap(size_t size, bool populate)
+static void *bench_mmap(size_t size, bool populate, unsigned int page_shift)
 {
 	void *p;
 	int extra = populate ? MAP_POPULATE : 0;
 
+	if (page_shift != PAGE_SHIFT_4KB)
+		extra |= MAP_HUGETLB | (page_shift << MAP_HUGE_SHIFT);
+
 	p = mmap(NULL, size, PROT_READ|PROT_WRITE,
 		 extra | MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
 
@@ -308,11 +333,11 @@ static bool mem_alloc(struct bench_mem_info *info, struct bench_params *p,
 {
 	bool failed;
 
-	*dst = bench_mmap(p->size, true);
+	*dst = bench_mmap(p->size, true, p->page_shift);
 	failed = *dst == NULL;
 
 	if (info->alloc_src) {
-		*src = bench_mmap(p->size, true);
+		*src = bench_mmap(p->size, true, p->page_shift);
 		failed = failed || *src == NULL;
 	}