[03/17] libgomp, openmp: Add ompx_pinned_mem_alloc

Message ID d148064484d92246255382c7aa00e4869c57c12b.1657188329.git.ams@codesourcery.com
State Superseded
Headers
Series openmp, nvptx, amdgcn: 5.0 Memory Allocators |

Commit Message

Andrew Stubbs July 7, 2022, 10:34 a.m. UTC
  This creates a new predefined allocator as a shortcut for using pinned
memory with OpenMP.  The name uses the OpenMP extension space and is
intended to be consistent with other OpenMP implementations currently in
development.

The allocator is equivalent to using a custom allocator with the pinned
trait and the null fallback trait.

libgomp/ChangeLog:

	* allocator.c (omp_max_predefined_alloc): Update.
	(omp_aligned_alloc): Support ompx_pinned_mem_alloc.
	(omp_free): Likewise.
	(omp_aligned_calloc): Likewise.
	(omp_realloc): Likewise.
	* omp.h.in (omp_allocator_handle_t): Add ompx_pinned_mem_alloc.
	* omp_lib.f90.in: Add ompx_pinned_mem_alloc.
	* testsuite/libgomp.c/alloc-pinned-5.c: New test.
	* testsuite/libgomp.c/alloc-pinned-6.c: New test.
	* testsuite/libgomp.fortran/alloc-pinned-1.f90: New test.
---
 libgomp/allocator.c                           |  60 +++++++----
 libgomp/omp.h.in                              |   1 +
 libgomp/omp_lib.f90.in                        |   2 +
 libgomp/testsuite/libgomp.c/alloc-pinned-5.c  |  90 ++++++++++++++++
 libgomp/testsuite/libgomp.c/alloc-pinned-6.c  | 101 ++++++++++++++++++
 .../libgomp.fortran/alloc-pinned-1.f90        |  16 +++
 6 files changed, 252 insertions(+), 18 deletions(-)
 create mode 100644 libgomp/testsuite/libgomp.c/alloc-pinned-5.c
 create mode 100644 libgomp/testsuite/libgomp.c/alloc-pinned-6.c
 create mode 100644 libgomp/testsuite/libgomp.fortran/alloc-pinned-1.f90
  

Patch

diff --git a/libgomp/allocator.c b/libgomp/allocator.c
index 54310ab93ca..029d0d40a36 100644
--- a/libgomp/allocator.c
+++ b/libgomp/allocator.c
@@ -35,7 +35,7 @@ 
 #include <dlfcn.h>
 #endif
 
-#define omp_max_predefined_alloc omp_thread_mem_alloc
+#define omp_max_predefined_alloc ompx_pinned_mem_alloc
 
 /* These macros may be overridden in config/<target>/allocator.c.  */
 #ifndef MEMSPACE_ALLOC
@@ -67,6 +67,7 @@  static const omp_memspace_handle_t predefined_alloc_mapping[] = {
   omp_low_lat_mem_space,   /* omp_cgroup_mem_alloc. */
   omp_low_lat_mem_space,   /* omp_pteam_mem_alloc. */
   omp_low_lat_mem_space,   /* omp_thread_mem_alloc. */
+  omp_default_mem_space,   /* ompx_pinned_mem_alloc. */
 };
 
 enum gomp_memkind_kind
@@ -512,8 +513,11 @@  retry:
 	    = (allocator_data
 	       ? allocator_data->memspace
 	       : predefined_alloc_mapping[allocator]);
-	  ptr = MEMSPACE_ALLOC (memspace, new_size,
-				allocator_data && allocator_data->pinned);
+	  int pinned __attribute__((unused))
+	    = (allocator_data
+	       ? allocator_data->pinned
+	       : allocator == ompx_pinned_mem_alloc);
+	  ptr = MEMSPACE_ALLOC (memspace, new_size, pinned);
 	}
       if (ptr == NULL)
 	goto fail;
@@ -534,7 +538,8 @@  retry:
 fail:
   int fallback = (allocator_data
 		  ? allocator_data->fallback
-		  : allocator == omp_default_mem_alloc
+		  : (allocator == omp_default_mem_alloc
+		     || allocator == ompx_pinned_mem_alloc)
 		  ? omp_atv_null_fb
 		  : omp_atv_default_mem_fb);
   switch (fallback)
@@ -653,6 +658,7 @@  omp_free (void *ptr, omp_allocator_handle_t allocator)
 #endif
 
       memspace = predefined_alloc_mapping[data->allocator];
+      pinned = (data->allocator == ompx_pinned_mem_alloc);
     }
 
   MEMSPACE_FREE (memspace, data->ptr, data->size, pinned);
@@ -802,8 +808,11 @@  retry:
 	    = (allocator_data
 	       ? allocator_data->memspace
 	       : predefined_alloc_mapping[allocator]);
-	  ptr = MEMSPACE_CALLOC (memspace, new_size,
-				 allocator_data && allocator_data->pinned);
+	  int pinned __attribute__((unused))
+	    = (allocator_data
+	       ? allocator_data->pinned
+	       : allocator == ompx_pinned_mem_alloc);
+	  ptr = MEMSPACE_CALLOC (memspace, new_size, pinned);
 	}
       if (ptr == NULL)
 	goto fail;
@@ -824,7 +833,8 @@  retry:
 fail:
   int fallback = (allocator_data
 		  ? allocator_data->fallback
-		  : allocator == omp_default_mem_alloc
+		  : (allocator == omp_default_mem_alloc
+		     || allocator == ompx_pinned_mem_alloc)
 		  ? omp_atv_null_fb
 		  : omp_atv_default_mem_fb);
   switch (fallback)
@@ -1026,11 +1036,15 @@  retry:
       else
 #endif
       if (prev_size)
-	new_ptr = MEMSPACE_REALLOC (allocator_data->memspace, data->ptr,
-				    data->size, new_size,
-				    (free_allocator_data
-				     && free_allocator_data->pinned),
-				    allocator_data->pinned);
+	{
+	  int was_pinned __attribute__((unused))
+	    = (free_allocator_data
+	       ? free_allocator_data->pinned
+	       : free_allocator == ompx_pinned_mem_alloc);
+	  new_ptr = MEMSPACE_REALLOC (allocator_data->memspace, data->ptr,
+				      data->size, new_size, was_pinned,
+				      allocator_data->pinned);
+	}
       else
 	new_ptr = MEMSPACE_ALLOC (allocator_data->memspace, new_size,
 				  allocator_data->pinned);
@@ -1079,10 +1093,16 @@  retry:
 	    = (allocator_data
 	       ? allocator_data->memspace
 	       : predefined_alloc_mapping[allocator]);
+	  int was_pinned __attribute__((unused))
+	    = (free_allocator_data
+	       ? free_allocator_data->pinned
+	       : free_allocator == ompx_pinned_mem_alloc);
+	  int pinned __attribute__((unused))
+	    = (allocator_data
+	       ? allocator_data->pinned
+	       : allocator == ompx_pinned_mem_alloc);
 	  new_ptr = MEMSPACE_REALLOC (memspace, data->ptr, data->size, new_size,
-				      (free_allocator_data
-				       && free_allocator_data->pinned),
-				      allocator_data && allocator_data->pinned);
+				      was_pinned, pinned);
 	}
       if (new_ptr == NULL)
 	goto fail;
@@ -1109,8 +1129,11 @@  retry:
 	    = (allocator_data
 	       ? allocator_data->memspace
 	       : predefined_alloc_mapping[allocator]);
-	  new_ptr = MEMSPACE_ALLOC (memspace, new_size,
-				    allocator_data && allocator_data->pinned);
+	  int pinned __attribute__((unused))
+	    = (allocator_data
+	       ? allocator_data->pinned
+	       : allocator == ompx_pinned_mem_alloc);
+	  new_ptr = MEMSPACE_ALLOC (memspace, new_size, pinned);
 	}
       if (new_ptr == NULL)
 	goto fail;
@@ -1156,7 +1179,8 @@  retry:
 fail:
   int fallback = (allocator_data
 		  ? allocator_data->fallback
-		  : allocator == omp_default_mem_alloc
+		  : (allocator == omp_default_mem_alloc
+		     || allocator == ompx_pinned_mem_alloc)
 		  ? omp_atv_null_fb
 		  : omp_atv_default_mem_fb);
   switch (fallback)
diff --git a/libgomp/omp.h.in b/libgomp/omp.h.in
index 925a650135e..eb071aa2e00 100644
--- a/libgomp/omp.h.in
+++ b/libgomp/omp.h.in
@@ -134,6 +134,7 @@  typedef enum omp_allocator_handle_t __GOMP_UINTPTR_T_ENUM
   omp_cgroup_mem_alloc = 6,
   omp_pteam_mem_alloc = 7,
   omp_thread_mem_alloc = 8,
+  ompx_pinned_mem_alloc = 9,
   __omp_allocator_handle_t_max__ = __UINTPTR_MAX__
 } omp_allocator_handle_t;
 
diff --git a/libgomp/omp_lib.f90.in b/libgomp/omp_lib.f90.in
index 7ba115f3a1a..10610d64cfe 100644
--- a/libgomp/omp_lib.f90.in
+++ b/libgomp/omp_lib.f90.in
@@ -158,6 +158,8 @@ 
                  parameter :: omp_pteam_mem_alloc = 7
         integer (kind=omp_allocator_handle_kind), &
                  parameter :: omp_thread_mem_alloc = 8
+        integer (kind=omp_allocator_handle_kind), &
+                 parameter :: ompx_pinned_mem_alloc = 9
         integer (omp_memspace_handle_kind), &
                  parameter :: omp_default_mem_space = 0
         integer (omp_memspace_handle_kind), &
diff --git a/libgomp/testsuite/libgomp.c/alloc-pinned-5.c b/libgomp/testsuite/libgomp.c/alloc-pinned-5.c
new file mode 100644
index 00000000000..315c7161a39
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/alloc-pinned-5.c
@@ -0,0 +1,90 @@ 
+/* { dg-do run } */
+
+/* { dg-xfail-run-if "Pinning not implemented on this host" { ! *-*-linux-gnu } } */
+
+/* Test that ompx_pinned_mem_alloc works.  */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#ifdef __linux__
+#include <sys/types.h>
+#include <unistd.h>
+
+#include <sys/mman.h>
+#include <sys/resource.h>
+
+#define PAGE_SIZE sysconf(_SC_PAGESIZE)
+#define CHECK_SIZE(SIZE) { \
+  struct rlimit limit; \
+  if (getrlimit (RLIMIT_MEMLOCK, &limit) \
+      || limit.rlim_cur <= SIZE) \
+    fprintf (stderr, "unsufficient lockable memory; please increase ulimit\n"); \
+  }
+
+int
+get_pinned_mem ()
+{
+  int pid = getpid ();
+  char buf[100];
+  sprintf (buf, "/proc/%d/status", pid);
+
+  FILE *proc = fopen (buf, "r");
+  if (!proc)
+    abort ();
+  while (fgets (buf, 100, proc))
+    {
+      int val;
+      if (sscanf (buf, "VmLck: %d", &val))
+	{
+	  fclose (proc);
+	  return val;
+	}
+    }
+  abort ();
+}
+#else
+#define PAGE_SIZE 1 /* unknown */
+#define CHECK_SIZE(SIZE) fprintf (stderr, "OS unsupported\n");
+
+int
+get_pinned_mem ()
+{
+  return 0;
+}
+#endif
+
+#include <omp.h>
+
+int
+main ()
+{
+  /* Allocate at least a page each time, but stay within the ulimit.  */
+  const int SIZE = PAGE_SIZE;
+  CHECK_SIZE (SIZE*3);
+
+  // Sanity check
+  if (get_pinned_mem () != 0)
+    abort ();
+
+  void *p = omp_alloc (SIZE, ompx_pinned_mem_alloc);
+  if (!p)
+    abort ();
+
+  int amount = get_pinned_mem ();
+  if (amount == 0)
+    abort ();
+
+  p = omp_realloc (p, SIZE*2, ompx_pinned_mem_alloc, ompx_pinned_mem_alloc);
+
+  int amount2 = get_pinned_mem ();
+  if (amount2 <= amount)
+    abort ();
+
+  p = omp_calloc (1, SIZE, ompx_pinned_mem_alloc);
+
+  if (get_pinned_mem () <= amount2)
+    abort ();
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/alloc-pinned-6.c b/libgomp/testsuite/libgomp.c/alloc-pinned-6.c
new file mode 100644
index 00000000000..bbe20c04875
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/alloc-pinned-6.c
@@ -0,0 +1,101 @@ 
+/* { dg-do run } */
+
+/* Test that ompx_pinned_mem_alloc fails correctly.  */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#ifdef __linux__
+#include <sys/types.h>
+#include <unistd.h>
+
+#include <sys/mman.h>
+#include <sys/resource.h>
+
+#define PAGE_SIZE sysconf(_SC_PAGESIZE)
+
+int
+get_pinned_mem ()
+{
+  int pid = getpid ();
+  char buf[100];
+  sprintf (buf, "/proc/%d/status", pid);
+
+  FILE *proc = fopen (buf, "r");
+  if (!proc)
+    abort ();
+  while (fgets (buf, 100, proc))
+    {
+      int val;
+      if (sscanf (buf, "VmLck: %d", &val))
+	{
+	  fclose (proc);
+	  return val;
+	}
+    }
+  abort ();
+}
+
+void
+set_pin_limit (int size)
+{
+  struct rlimit limit;
+  if (getrlimit (RLIMIT_MEMLOCK, &limit))
+    abort ();
+  limit.rlim_cur = (limit.rlim_max < size ? limit.rlim_max : size);
+  if (setrlimit (RLIMIT_MEMLOCK, &limit))
+    abort ();
+}
+#else
+#define PAGE_SIZE 10000*1024 /* unknown */
+
+int
+get_pinned_mem ()
+{
+  return 0;
+}
+
+void
+set_pin_limit ()
+{
+}
+#endif
+
+#include <omp.h>
+
+int
+main ()
+{
+  /* Allocate at least a page each time, but stay within the ulimit.  */
+  const int SIZE = PAGE_SIZE*4;
+
+  /* Ensure that the limit is smaller than the allocation.  */
+  set_pin_limit (SIZE/2);
+
+  // Sanity check
+  if (get_pinned_mem () != 0)
+    abort ();
+
+  // Should fail
+  void *p = omp_alloc (SIZE, ompx_pinned_mem_alloc);
+  if (p)
+    abort ();
+
+  // Should fail
+  p = omp_calloc (1, SIZE, ompx_pinned_mem_alloc);
+  if (p)
+    abort ();
+
+  // Should fail to realloc
+  void *notpinned = omp_alloc (SIZE, omp_default_mem_alloc);
+  p = omp_realloc (notpinned, SIZE, ompx_pinned_mem_alloc, omp_default_mem_alloc);
+  if (!notpinned || p)
+    abort ();
+
+  // No memory should have been pinned
+  int amount = get_pinned_mem ();
+  if (amount != 0)
+    abort ();
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.fortran/alloc-pinned-1.f90 b/libgomp/testsuite/libgomp.fortran/alloc-pinned-1.f90
new file mode 100644
index 00000000000..798dc3d5a12
--- /dev/null
+++ b/libgomp/testsuite/libgomp.fortran/alloc-pinned-1.f90
@@ -0,0 +1,16 @@ 
+! Ensure that the ompx_pinned_mem_alloc predefined allocator is present and
+! accepted.  The majority of the functionality testing lives in the C tests.
+!
+! { dg-xfail-run-if "Pinning not implemented on this host" { ! *-*-linux-gnu } }
+
+program main
+  use omp_lib
+  use ISO_C_Binding
+  implicit none (external, type)
+
+  type(c_ptr) :: p
+
+  p = omp_alloc (10_c_size_t, ompx_pinned_mem_alloc);
+  if (.not. c_associated (p)) stop 1
+  call omp_free (p, ompx_pinned_mem_alloc);
+end program main