git: b5410efe42c5 - stable/13 - buf_ring: Remove old arm-only dequeue code

The branch stable/13 has been updated by andrew:

URL: https://cgit.FreeBSD.org/src/commit/?id=b5410efe42c5bcf78d3f41052266a758e4fd03fc

commit b5410efe42c5bcf78d3f41052266a758e4fd03fc
Author:     Andrew Turner <andrew@FreeBSD.org>
AuthorDate: 2024-08-19 09:07:10 +0000
Commit:     Andrew Turner <andrew@FreeBSD.org>
CommitDate: 2024-09-02 09:11:57 +0000

    buf_ring: Remove old arm-only dequeue code
    
    In the single consumer dequeue the consumer thread controls
    br_cons_head. As such no ordering between this and other data are
    required.
    
    Reviewed by:    alc, imp, kib, markj
    Sponsored by:   Arm Ltd
    Differential Revision:  https://reviews.freebsd.org/D46153
    
    (cherry picked from commit 7eb0fffc7792bc294d6b86546a3923e2e2f83f8a)
---
 sys/sys/buf_ring.h | 29 -----------------------------
 1 file changed, 29 deletions(-)

diff --git a/sys/sys/buf_ring.h b/sys/sys/buf_ring.h
index 9aeb5aa19fa8..ad463fba27cb 100644
--- a/sys/sys/buf_ring.h
+++ b/sys/sys/buf_ring.h
@@ -177,37 +177,8 @@ buf_ring_dequeue_sc(struct buf_ring *br)
 	uint32_t prod_tail, mask;
 	void *buf;
 
-	/*
-	 * This is a workaround to allow using buf_ring on ARM and ARM64.
-	 * ARM64TODO: Fix buf_ring in a generic way.
-	 * REMARKS: It is suspected that br_cons_head does not require
-	 *   load_acq operation, but this change was extensively tested
-	 *   and confirmed it's working. To be reviewed once again in
-	 *   FreeBSD-12.
-	 *
-	 * Preventing following situation:
-
-	 * Core(0) - buf_ring_enqueue()                                       Core(1) - buf_ring_dequeue_sc()
-	 * -----------------------------------------                                       ----------------------------------------------
-	 *
-	 *                                                                                cons_head = br->br_cons_head;
-	 * atomic_cmpset_acq_32(&br->br_prod_head, ...));
-	 *                                                                                buf = br->br_ring[cons_head];     <see <1>>
-	 * br->br_ring[prod_head] = buf;
-	 * atomic_store_rel_32(&br->br_prod_tail, ...);
-	 *                                                                                prod_tail = br->br_prod_tail;
-	 *                                                                                if (cons_head == prod_tail) 
-	 *                                                                                        return (NULL);
-	 *                                                                                <condition is false and code uses invalid(old) buf>`	
-	 *
-	 * <1> Load (on core 1) from br->br_ring[cons_head] can be reordered (speculative readed) by CPU.
-	 */	
 	mask = br->br_cons_mask;
-#if defined(__arm__) || defined(__aarch64__)
-	cons_head = atomic_load_acq_32(&br->br_cons_head);
-#else
 	cons_head = br->br_cons_head;
-#endif
 	prod_tail = atomic_load_acq_32(&br->br_prod_tail);
 
 	cons_next = cons_head + 1;