CLEANUP: more conversions and cleanups for alignment

- Convert additional cases to use the automatic alignment feature for
  the THREAD_ALIGN(ED) macros. This includes some cases that are less
  obviously correct where it seems we wanted to align only in the
  USE_THREAD case but were not using the thread specific macros.
- Also move some alignment requirements to the structure definition
  instead of having it on variable declaration.

include/haproxy/activity-t.h

@@ -125,8 +125,8 @@ struct activity {
 	unsigned int ctr2;         // general purposee debug counter
 #endif
 	char __pad[0]; // unused except to check remaining room
-	char __end[0] __attribute__((aligned(64))); // align size to 64.
-};
+	char __end[0] THREAD_ALIGNED();
+} THREAD_ALIGNED();
 
 /* 256 entries for callers * callees should be highly sufficient (~45 seen usually) */
 #define SCHED_ACT_HASH_BITS 8
@@ -146,7 +146,7 @@ struct sched_activity {
 	uint64_t lkw_time; /* lock waiting time */
 	uint64_t lkd_time; /* locked time */
 	uint64_t mem_time; /* memory ops wait time */
-};
+} THREAD_ALIGNED();
 
 #endif /* _HAPROXY_ACTIVITY_T_H */
 

include/haproxy/listener.h

@@ -231,7 +231,7 @@ const char *listener_state_str(const struct listener *l);
 struct task *accept_queue_process(struct task *t, void *context, unsigned int state);
 struct task *manage_global_listener_queue(struct task *t, void *context, unsigned int state);
 
-extern struct accept_queue_ring accept_queue_rings[MAX_THREADS] __attribute__((aligned(64)));
+extern struct accept_queue_ring accept_queue_rings[MAX_THREADS] THREAD_ALIGNED();
 
 extern const char* li_status_st[LI_STATE_COUNT];
 enum li_status get_li_status(struct listener *l);

include/haproxy/pool-t.h

@@ -156,8 +156,8 @@ struct pool_head {
 		unsigned int failed;	/* failed allocations (indexed by hash of TID) */
 	} buckets[CONFIG_HAP_POOL_BUCKETS];
 
-	struct pool_cache_head cache[MAX_THREADS] THREAD_ALIGNED(64); /* pool caches */
-} __attribute__((aligned(64)));
+	struct pool_cache_head cache[MAX_THREADS] THREAD_ALIGNED(); /* pool caches */
+} THREAD_ALIGNED();
 
 #endif /* _HAPROXY_POOL_T_H */
 

include/haproxy/thread-t.h

@@ -72,7 +72,7 @@
 
 /* declare a self-initializing spinlock, aligned on a cache line */
 #define __decl_aligned_spinlock(lock)                       \
-	HA_SPINLOCK_T (lock) __attribute__((aligned(64)));  \
+	HA_SPINLOCK_T (lock) THREAD_ALIGNED();              \
 	INITCALL1(STG_LOCK, ha_spin_init, &(lock))
 
 /* declare a self-initializing rwlock */
@@ -82,7 +82,7 @@
 
 /* declare a self-initializing rwlock, aligned on a cache line */
 #define __decl_aligned_rwlock(lock)                         \
-	HA_RWLOCK_T   (lock) __attribute__((aligned(64)));  \
+	HA_RWLOCK_T   (lock) THREAD_ALIGNED();              \
 	INITCALL1(STG_LOCK, ha_rwlock_init, &(lock))
 
 #endif /* USE_THREAD */

include/haproxy/tinfo-t.h

@@ -86,7 +86,7 @@ struct tgroup_info {
 
 	/* pad to cache line (64B) */
 	char __pad[0];            /* unused except to check remaining room */
-	char __end[0] __attribute__((aligned(64)));
+	char __end[0] THREAD_ALIGNED();
 };
 
 /* This structure describes the group-specific context (e.g. active threads
@@ -103,7 +103,7 @@ struct tgroup_ctx {
 
 	/* pad to cache line (64B) */
 	char __pad[0];                    /* unused except to check remaining room */
-	char __end[0] __attribute__((aligned(64)));
+	char __end[0] THREAD_ALIGNED();
 };
 
 /* This structure describes all the per-thread info we need. When threads are
@@ -124,7 +124,7 @@ struct thread_info {
 
 	/* pad to cache line (64B) */
 	char __pad[0];                    /* unused except to check remaining room */
-	char __end[0] __attribute__((aligned(64)));
+	char __end[0] THREAD_ALIGNED();
 };
 
 /* This structure describes all the per-thread context we need. This is

src/activity.c

@@ -60,10 +60,10 @@ uint64_t prof_mem_start_ns = 0;
 uint64_t prof_mem_stop_ns = 0;
 
 /* One struct per thread containing all collected measurements */
-struct activity activity[MAX_THREADS] __attribute__((aligned(64))) = { };
+struct activity activity[MAX_THREADS] = { };
 
 /* One struct per function pointer hash entry (SCHED_ACT_HASH_BUCKETS values, 0=collision) */
-struct sched_activity sched_activity[SCHED_ACT_HASH_BUCKETS] __attribute__((aligned(64))) = { };
+struct sched_activity sched_activity[SCHED_ACT_HASH_BUCKETS] = { };
 
 
 #ifdef USE_MEMORY_PROFILING
@@ -949,7 +949,7 @@ struct sched_activity *sched_activity_entry(struct sched_activity *array, const
 static int cli_io_handler_show_profiling(struct appctx *appctx)
 {
 	struct show_prof_ctx *ctx = appctx->svcctx;
-	struct sched_activity tmp_activity[SCHED_ACT_HASH_BUCKETS] __attribute__((aligned(64)));
+	struct sched_activity tmp_activity[SCHED_ACT_HASH_BUCKETS];
 #ifdef USE_MEMORY_PROFILING
 	struct memprof_stats tmp_memstats[MEMPROF_HASH_BUCKETS + 1];
 	unsigned long long tot_alloc_calls, tot_free_calls;
@@ -1329,7 +1329,7 @@ static int cli_parse_show_profiling(char **args, char *payload, struct appctx *a
  */
 static int cli_io_handler_show_tasks(struct appctx *appctx)
 {
-	struct sched_activity tmp_activity[SCHED_ACT_HASH_BUCKETS] __attribute__((aligned(64)));
+	struct sched_activity tmp_activity[SCHED_ACT_HASH_BUCKETS];
 	struct buffer *name_buffer = get_trash_chunk();
 	struct sched_activity *entry;
 	const struct tasklet *tl;

src/listener.c

@@ -66,7 +66,7 @@ const char* li_status_st[LI_STATE_COUNT] = {
 
 #if defined(USE_THREAD)
 
-struct accept_queue_ring accept_queue_rings[MAX_THREADS] __attribute__((aligned(64))) = { };
+struct accept_queue_ring accept_queue_rings[MAX_THREADS] THREAD_ALIGNED();
 
 /* dequeue and process a pending connection from the local accept queue (single
  * consumer). Returns the accepted connection or NULL if none was found.

src/task.c

@@ -44,7 +44,7 @@ __decl_aligned_rwlock(wq_lock);
 
 /* used to detect if the scheduler looks stuck (for warnings) */
 static struct {
-	int sched_stuck ALIGNED(64);
+	int sched_stuck THREAD_ALIGNED();
 } sched_ctx[MAX_THREADS];
 
 /* Flags the task <t> for immediate destruction and puts it into its first