public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc r12-8259] libgomp: Fix up two non-GOMP_USE_ALIGNED_WORK_SHARES related issues [PR105358]
@ 2022-04-26  7:15 Jakub Jelinek
  0 siblings, 0 replies; only message in thread
From: Jakub Jelinek @ 2022-04-26  7:15 UTC (permalink / raw)
  To: gcc-cvs

https://gcc.gnu.org/g:57a957cb71c004de80b0fd30c8db3cc67576e0ce

commit r12-8259-g57a957cb71c004de80b0fd30c8db3cc67576e0ce
Author: Jakub Jelinek <jakub@redhat.com>
Date:   Tue Apr 26 08:57:17 2022 +0200

    libgomp: Fix up two non-GOMP_USE_ALIGNED_WORK_SHARES related issues [PR105358]
    
    Last fall I've changed struct gomp_work_share, so that it doesn't have
    __attribute__((aligned (64))) lock member in the middle unless the target has
    non-emulated aligned allocator, otherwise it just makes sure the first and
    second halves are 64 bytes appart for cache line reasons, but doesn't make
    the struct 64-byte aligned itself and so we can use normal allocators for it.
    
    When the struct isn't 64-byte aligned, the amount of tail padding significantly
    decreases, to 0 or 4 bytes or so.  The library uses that tail padding when
    the ordered_teams_ids array (array of uints) and/or the memory for lastprivate
    conditional temporaries (the latter wants to guarantee long long alignment).
    The problem with it on ia32 darwin9 is that while the struct contains
    long long members, long long is just 4 byte aligned while __alignof__(long long)
    is 8.  That causes problems in gomp_init_work_share, where we currently rely on
    if offsetof (struct gomp_work_share, inline_ordered_team_ids) is long long
    aligned, then that tail array will be aligned at runtime and so no extra
    memory for dynamic realignment will be needed (that is false when the whole
    struct doesn't have long long alignment).  And also in the remaining hunks
    causes another problem, where we compute INLINE_ORDERED_TEAM_IDS_OFF
    as the above offsetof aligned up to long long boundary and subtract
    sizeof (struct gomp_work_share) and INLINE_ORDERED_TEAM_IDS_OFF.
    When unlucky, the former isn't multiple of 8 and the latter is 4 bigger
    than that and as the subtraction is done in size_t, we end up with (size_t) -4,
    so the comparison doesn't really work.
    
    The fixes add additional conditions to make it work properly, but all of them
    should be evaluated at compile time when optimizing and so shouldn't slow
    anything.
    
    2022-04-26  Jakub Jelinek  <jakub@redhat.com>
    
            PR libgomp/105358
            * work.c (gomp_init_work_share): Don't mask of adjustment for
            dynamic long long realignment if struct gomp_work_share has smaller
            alignof than long long.
            * loop.c (GOMP_loop_start): Don't use inline_ordered_team_ids if
            struct gomp_work_share has smaller alignof than long long or if
            sizeof (struct gomp_work_share) is smaller than
            INLINE_ORDERED_TEAM_IDS_OFF.
            * loop_ull.c (GOMP_loop_ull_start): Likewise.
            * sections.c (GOMP_sections2_start): Likewise.

Diff:
---
 libgomp/loop.c     | 7 +++++--
 libgomp/loop_ull.c | 7 +++++--
 libgomp/sections.c | 7 +++++--
 libgomp/work.c     | 4 +++-
 4 files changed, 18 insertions(+), 7 deletions(-)

diff --git a/libgomp/loop.c b/libgomp/loop.c
index 682df39a4ed..be85162bb1e 100644
--- a/libgomp/loop.c
+++ b/libgomp/loop.c
@@ -270,8 +270,11 @@ GOMP_loop_start (long start, long end, long incr, long sched,
 #define INLINE_ORDERED_TEAM_IDS_OFF \
   ((offsetof (struct gomp_work_share, inline_ordered_team_ids)		\
     + __alignof__ (long long) - 1) & ~(__alignof__ (long long) - 1))
-	  if (size > (sizeof (struct gomp_work_share)
-		      - INLINE_ORDERED_TEAM_IDS_OFF))
+	  if (sizeof (struct gomp_work_share)
+	      <= INLINE_ORDERED_TEAM_IDS_OFF
+	      || __alignof__ (struct gomp_work_share) < __alignof__ (long long)
+	      || size > (sizeof (struct gomp_work_share)
+			- INLINE_ORDERED_TEAM_IDS_OFF))
 	    *mem
 	      = (void *) (thr->ts.work_share->ordered_team_ids
 			  = gomp_malloc_cleared (size));
diff --git a/libgomp/loop_ull.c b/libgomp/loop_ull.c
index 2aaa34e3bca..602737296d4 100644
--- a/libgomp/loop_ull.c
+++ b/libgomp/loop_ull.c
@@ -269,8 +269,11 @@ GOMP_loop_ull_start (bool up, gomp_ull start, gomp_ull end,
 #define INLINE_ORDERED_TEAM_IDS_OFF \
   ((offsetof (struct gomp_work_share, inline_ordered_team_ids)		\
     + __alignof__ (long long) - 1) & ~(__alignof__ (long long) - 1))
-	  if (size > (sizeof (struct gomp_work_share)
-		      - INLINE_ORDERED_TEAM_IDS_OFF))
+	  if (sizeof (struct gomp_work_share)
+	      <= INLINE_ORDERED_TEAM_IDS_OFF
+	      || __alignof__ (struct gomp_work_share) < __alignof__ (long long)
+	      || size > (sizeof (struct gomp_work_share)
+			- INLINE_ORDERED_TEAM_IDS_OFF))
 	    *mem
 	      = (void *) (thr->ts.work_share->ordered_team_ids
 			  = gomp_malloc_cleared (size));
diff --git a/libgomp/sections.c b/libgomp/sections.c
index e9d99e434ac..7751d5aac83 100644
--- a/libgomp/sections.c
+++ b/libgomp/sections.c
@@ -121,8 +121,11 @@ GOMP_sections2_start (unsigned count, uintptr_t *reductions, void **mem)
 #define INLINE_ORDERED_TEAM_IDS_OFF \
   ((offsetof (struct gomp_work_share, inline_ordered_team_ids)		\
     + __alignof__ (long long) - 1) & ~(__alignof__ (long long) - 1))
-	  if (size > (sizeof (struct gomp_work_share)
-		      - INLINE_ORDERED_TEAM_IDS_OFF))
+	  if (sizeof (struct gomp_work_share)
+	      <= INLINE_ORDERED_TEAM_IDS_OFF
+	      || __alignof__ (struct gomp_work_share) < __alignof__ (long long)
+	      || size > (sizeof (struct gomp_work_share)
+			- INLINE_ORDERED_TEAM_IDS_OFF))
 	    *mem
 	      = (void *) (thr->ts.work_share->ordered_team_ids
 			  = gomp_malloc_cleared (size));
diff --git a/libgomp/work.c b/libgomp/work.c
index a88409dc78b..c53625afe2c 100644
--- a/libgomp/work.c
+++ b/libgomp/work.c
@@ -113,7 +113,9 @@ gomp_init_work_share (struct gomp_work_share *ws, size_t ordered,
 	  size_t o = nthreads * sizeof (*ws->ordered_team_ids);
 	  o += __alignof__ (long long) - 1;
 	  if ((offsetof (struct gomp_work_share, inline_ordered_team_ids)
-	       & (__alignof__ (long long) - 1)) == 0)
+	       & (__alignof__ (long long) - 1)) == 0
+	      && __alignof__ (struct gomp_work_share)
+		 >= __alignof__ (long long))
 	    o &= ~(__alignof__ (long long) - 1);
 	  ordered += o - 1;
 	}


^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2022-04-26  7:15 UTC | newest]

Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-04-26  7:15 [gcc r12-8259] libgomp: Fix up two non-GOMP_USE_ALIGNED_WORK_SHARES related issues [PR105358] Jakub Jelinek

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).