CLEANUP: use the automatic alignment feature

- Use the automatic alignment feature instead of hardcoding 64 all over
  the code.
- This also converts a few bare __attribute__((aligned(X))) to using the
  ALIGNED macro.

dev/haring/haring.c

@@ -59,9 +59,9 @@ struct ring_v2 {
 struct ring_v2a {
 	size_t size;         // storage size
 	size_t rsvd;         // header length (used for file-backed maps)
-	size_t tail __attribute__((aligned(64)));         // storage tail
-	size_t head __attribute__((aligned(64)));         // storage head
-	char area[0] __attribute__((aligned(64)));        // storage area begins immediately here
+	size_t tail ALIGNED(64);         // storage tail
+	size_t head ALIGNED(64);         // storage head
+	char area[0] ALIGNED(64);        // storage area begins immediately here
 };
 
 /* display the message and exit with the code */

include/haproxy/bug.h

@@ -537,7 +537,7 @@ struct mem_stats {
 	size_t size;
 	struct ha_caller caller;
 	const void *extra; // extra info specific to this call (e.g. pool ptr)
-} __attribute__((aligned(sizeof(void*))));
+} ALIGNED(sizeof(void*));
 
 #undef calloc
 #define calloc(x,y)  ({							\

include/haproxy/connection-t.h

@@ -796,7 +796,7 @@ struct idle_conns {
 	struct mt_list toremove_conns;
 	struct task *cleanup_task;
 	__decl_thread(HA_SPINLOCK_T idle_conns_lock);
-} THREAD_ALIGNED(64);
+} THREAD_ALIGNED();
 
 
 /* Termination events logs:

include/haproxy/fd-t.h

@@ -202,7 +202,7 @@ struct fdtab {
 #ifdef DEBUG_FD
 	unsigned int event_count;            /* number of events reported */
 #endif
-} THREAD_ALIGNED(64);
+} THREAD_ALIGNED();
 
 /* polled mask, one bit per thread and per direction for each FD */
 struct polled_mask {

include/haproxy/htx-t.h

@@ -270,7 +270,7 @@ struct htx {
 	/* XXX 4 bytes unused */
 
 	/* Blocks representing the HTTP message itself */
-	char blocks[VAR_ARRAY] __attribute__((aligned(8)));
+	char blocks[VAR_ARRAY] ALIGNED(8);
 };
 
 #endif /* _HAPROXY_HTX_T_H */

include/haproxy/listener-t.h

@@ -309,7 +309,7 @@ struct bind_kw_list {
 struct accept_queue_ring {
 	uint32_t idx;             /* (head << 16) | tail */
 	struct tasklet *tasklet;  /* tasklet of the thread owning this ring */
-	struct connection *entry[ACCEPT_QUEUE_SIZE] __attribute((aligned(64)));
+	struct connection *entry[ACCEPT_QUEUE_SIZE] THREAD_ALIGNED();
 };
 
 

include/haproxy/pattern-t.h

@@ -116,7 +116,7 @@ struct pat_ref {
 	int unique_id; /* Each pattern reference have unique id. */
 	unsigned long long revision; /* updated for each update */
 	unsigned long long entry_cnt; /* the total number of entries */
-	THREAD_ALIGN(64);
+	THREAD_ALIGN();
 	__decl_thread(HA_RWLOCK_T lock); /* Lock used to protect pat ref elements */
 	event_hdl_sub_list e_subs;       /* event_hdl: pat_ref's subscribers list (atomically updated) */
 };

include/haproxy/pool-t.h

@@ -63,7 +63,7 @@ struct pool_cache_head {
 	unsigned int tid;    /* thread id, for debugging only */
 	struct pool_head *pool; /* assigned pool, for debugging only */
 	ulong fill_pattern;  /* pattern used to fill the area on free */
-} THREAD_ALIGNED(64);
+} THREAD_ALIGNED();
 
 /* This describes a pool registration, which is what was passed to
  * create_pool() and that might have been merged with an existing pool.
@@ -139,7 +139,7 @@ struct pool_head {
 	struct list regs;       /* registrations: alt names for this pool */
 
 	/* heavily read-write part */
-	THREAD_ALIGN(64);
+	THREAD_ALIGN();
 
 	/* these entries depend on the pointer value, they're used to reduce
 	 * the contention on fast-changing values. The alignment here is
@@ -148,7 +148,7 @@ struct pool_head {
 	 * just meant to shard elements and there are no per-free_list stats.
 	 */
 	struct {
-		THREAD_ALIGN(64);
+		THREAD_ALIGN();
 		struct pool_item *free_list; /* list of free shared objects */
 		unsigned int allocated;	/* how many chunks have been allocated */
 		unsigned int used;	/* how many chunks are currently in use */

include/haproxy/proxy-t.h

@@ -304,7 +304,7 @@ struct error_snapshot {
 struct proxy_per_tgroup {
 	struct queue queue;
 	struct lbprm_per_tgrp lbprm;
-} THREAD_ALIGNED(64);
+} THREAD_ALIGNED();
 
 struct proxy {
 	enum obj_type obj_type;                 /* object type == OBJ_TYPE_PROXY */
@@ -505,7 +505,7 @@ struct proxy {
 	EXTRA_COUNTERS(extra_counters_fe);
 	EXTRA_COUNTERS(extra_counters_be);
 
-	THREAD_ALIGN(64);
+	THREAD_ALIGN();
 	unsigned int queueslength;		/* Sum of the length of each queue */
 	int served;				/* # of active sessions currently being served */
 	int totpend;				/* total number of pending connections on this instance (for stats) */

include/haproxy/ring-t.h

@@ -130,11 +130,11 @@ struct ring_wait_cell {
 struct ring_storage {
 	size_t size;         // storage size
 	size_t rsvd;         // header length (used for file-backed maps)
-	THREAD_ALIGN(64);
+	THREAD_ALIGN();
 	size_t tail;         // storage tail
-	THREAD_ALIGN(64);
+	THREAD_ALIGN();
 	size_t head;         // storage head
-	THREAD_ALIGN(64);
+	THREAD_ALIGN();
 	char area[0];        // storage area begins immediately here
 };
 
@@ -149,7 +149,7 @@ struct ring {
 
 	/* keep the queue in a separate cache line below */
 	struct {
-		THREAD_ALIGN(64);
+		THREAD_ALIGN();
 		struct ring_wait_cell *ptr;
 	} queue[RING_WAIT_QUEUES + 1]; // wait queue + 1 spacer
 };

include/haproxy/server-t.h

@@ -294,7 +294,7 @@ struct srv_per_tgroup {
 	struct eb_root *lb_tree;                 /* For LB algos with split between thread groups, the tree to be used, for each group */
 	unsigned npos, lpos;			/* next and last positions in the LB tree, protected by LB lock */
 	unsigned rweight;			/* remainder of weight in the current LB tree */
-} THREAD_ALIGNED(64);
+} THREAD_ALIGNED();
 
 /* Configure the protocol selection for websocket */
 enum __attribute__((__packed__)) srv_ws_mode {
@@ -396,7 +396,7 @@ struct server {
 	/* The elements below may be changed on every single request by any
 	 * thread, and generally at the same time.
 	 */
-	THREAD_ALIGN(64);
+	THREAD_ALIGN();
 	struct eb32_node idle_node;             /* When to next do cleanup in the idle connections */
 	unsigned int curr_idle_conns;           /* Current number of orphan idling connections, both the idle and the safe lists */
 	unsigned int curr_idle_nb;              /* Current number of connections in the idle list */
@@ -414,7 +414,7 @@ struct server {
 	/* Element below are usd by LB algorithms and must be doable in
 	 * parallel to other threads reusing connections above.
 	 */
-	THREAD_ALIGN(64);
+	THREAD_ALIGN();
 	__decl_thread(HA_SPINLOCK_T lock);      /* may enclose the proxy's lock, must not be taken under */
 	union {
 		struct eb32_node lb_node;       /* node used for tree-based load balancing */
@@ -428,7 +428,7 @@ struct server {
 	};
 
 	/* usually atomically updated by any thread during parsing or on end of request */
-	THREAD_ALIGN(64);
+	THREAD_ALIGN();
 	int cur_sess;				/* number of currently active sessions (including syn_sent) */
 	int served;				/* # of active sessions currently being served (ie not pending) */
 	int consecutive_errors;			/* current number of consecutive errors */
@@ -436,7 +436,7 @@ struct server {
 	struct be_counters counters;		/* statistics counters */
 
 	/* Below are some relatively stable settings, only changed under the lock */
-	THREAD_ALIGN(64);
+	THREAD_ALIGN();
 
 	struct eb_root *lb_tree;                /* we want to know in what tree the server is */
 	struct tree_occ *lb_nodes;              /* lb_nodes_tot * struct tree_occ */

include/haproxy/stick_table-t.h

@@ -206,7 +206,7 @@ struct stktable {
 		void *ptr;          /* generic ptr to check if set or not */
 	} write_to; /* updates received on the source table will also update write_to */
 
-	THREAD_ALIGN(64);
+	THREAD_ALIGN();
 
 	struct {
 		struct eb_root keys;      /* head of sticky session tree */
@@ -221,7 +221,7 @@ struct stktable {
 	unsigned int refcnt;     /* number of local peer over all peers sections
 				    attached to this table */
 	unsigned int current;     /* number of sticky sessions currently in table */
-	THREAD_ALIGN(64);
+	THREAD_ALIGN();
 
 	struct eb_root updates;   /* head of sticky updates sequence tree, uses updt_lock */
 	struct mt_list *pend_updts; /* list of updates to be added to the update sequence tree, one per thread-group */
@@ -229,7 +229,7 @@ struct stktable {
 	unsigned int localupdate; /* uses updt_lock */
 	struct tasklet *updt_task;/* tasklet responsible for pushing the pending updates into the tree */
 
-	THREAD_ALIGN(64);
+	THREAD_ALIGN();
 	/* this lock is heavily used and must be on its own cache line */
 	__decl_thread(HA_RWLOCK_T updt_lock); /* lock protecting the updates part */
 

include/haproxy/task.h

@@ -91,7 +91,7 @@ extern struct pool_head *pool_head_task;
 extern struct pool_head *pool_head_tasklet;
 extern struct pool_head *pool_head_notification;
 
-__decl_thread(extern HA_RWLOCK_T wq_lock THREAD_ALIGNED(64));
+__decl_thread(extern HA_RWLOCK_T wq_lock THREAD_ALIGNED());
 
 void __tasklet_wakeup_on(struct tasklet *tl, int thr);
 struct list *__tasklet_wakeup_after(struct list *head, struct tasklet *tl);

include/haproxy/thread-t.h

@@ -51,7 +51,7 @@
 
 /* declare a self-initializing spinlock, aligned on a cache line */
 #define __decl_aligned_spinlock(lock)                          \
-	HA_SPINLOCK_T (lock) __attribute__((aligned(64))) = 0;
+	HA_SPINLOCK_T (lock) ALIGNED(64) = 0;
 
 /* declare a self-initializing rwlock */
 #define __decl_rwlock(lock)                                    \
@@ -59,7 +59,7 @@
 
 /* declare a self-initializing rwlock, aligned on a cache line */
 #define __decl_aligned_rwlock(lock)                            \
-	HA_RWLOCK_T   (lock) __attribute__((aligned(64))) = 0;
+	HA_RWLOCK_T   (lock) ALIGNED(64) = 0;
 
 #else /* !USE_THREAD */
 

src/clock.c

@@ -35,7 +35,7 @@ volatile uint                    _global_now_ms;   /* locally stored common mono
 volatile uint			*global_now_ms;    /* common monotonic date in milliseconds (may wrap), may point to _global_now_ms or shared memory */
 
 /* when CLOCK_MONOTONIC is supported, the offset is applied from th_ctx->prev_mono_time instead */
-THREAD_ALIGNED(64) static llong  now_offset;      /* global offset between system time and global time in ns */
+THREAD_ALIGNED() static llong  now_offset;        /* global offset between system time and global time in ns */
 
 THREAD_LOCAL ullong              now_ns;          /* internal monotonic date derived from real clock, in ns (wraps every 585 yr) */
 THREAD_LOCAL uint                now_ms;          /* internal monotonic date in milliseconds (may wrap) */

src/hlua.c

@@ -676,7 +676,7 @@ struct hlua_mem_allocator {
 	size_t limit;
 };
 
-static struct hlua_mem_allocator hlua_global_allocator THREAD_ALIGNED(64);
+static struct hlua_mem_allocator hlua_global_allocator THREAD_ALIGNED();
 
 /* hlua event subscription */
 struct hlua_event_sub {

src/vars.c

@@ -27,7 +27,7 @@
 DECLARE_STATIC_TYPED_POOL(var_pool, "vars", struct var);
 
 /* list of variables for the process scope. */
-struct vars proc_vars THREAD_ALIGNED(64);
+struct vars proc_vars THREAD_ALIGNED();
 
 /* This array of int contains the system limits per context. */
 static unsigned int var_global_limit = 0;