[xen staging] xen/rwlock: raise the number of possible cpus

[patchbot@xxxxxxx]

commit 77b219f915c54d6029a370c6208ccb1bb965ee1c
Author:     Juergen Gross <jgross@xxxxxxxx>
AuthorDate: Mon Apr 8 09:21:41 2024 +0200
Commit:     Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Mon Apr 8 09:21:41 2024 +0200

    xen/rwlock: raise the number of possible cpus
    
    The rwlock handling is limiting the number of cpus to 4095 today. The
    main reason is the use of the atomic_t data type for the main lock
    handling, which needs 2 bits for the locking state (writer waiting or
    write locked), 12 bits for the id of a possible writer, and a 12 bit
    counter for readers. The limit isn't 4096 due to an off by one sanity
    check.
    
    The atomic_t data type is 32 bits wide, so in theory 15 bits for the
    writer's cpu id and 15 bits for the reader count seem to be fine, but
    via read_trylock() more readers than cpus are possible.
    
    This means that it is possible to raise the number of cpus to 16384
    without changing the rwlock_t data structure. In order to avoid the
    reader count wrapping to zero, don't let read_trylock() succeed in case
    the highest bit of the reader's count is set already. This leaves enough
    headroom for non-recursive readers to enter without risking a wrap.
    
    While at it calculate _QW_CPUMASK and _QR_SHIFT from _QW_SHIFT and
    add a sanity check for not overflowing the atomic_t data type.
    
    Signed-off-by: Juergen Gross <jgross@xxxxxxxx>
    Reviewed-by: Jan Beulich <jbeulich@xxxxxxxx>
---
 xen/include/xen/rwlock.h | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/xen/include/xen/rwlock.h b/xen/include/xen/rwlock.h
index 65d88b0ef4..a2e98cad34 100644
--- a/xen/include/xen/rwlock.h
+++ b/xen/include/xen/rwlock.h
@@ -23,12 +23,12 @@ typedef struct {
 #define rwlock_init(l) (*(l) = (rwlock_t)RW_LOCK_UNLOCKED)
 
 /* Writer states & reader shift and bias. */
-#define    _QW_CPUMASK  0xfffU             /* Writer CPU mask */
-#define    _QW_SHIFT    12                 /* Writer flags shift */
-#define    _QW_WAITING  (1U << _QW_SHIFT)  /* A writer is waiting */
-#define    _QW_LOCKED   (3U << _QW_SHIFT)  /* A writer holds the lock */
-#define    _QW_WMASK    (3U << _QW_SHIFT)  /* Writer mask */
-#define    _QR_SHIFT    14                 /* Reader count shift */
+#define    _QW_SHIFT    14                      /* Writer flags shift */
+#define    _QW_CPUMASK  ((1U << _QW_SHIFT) - 1) /* Writer CPU mask */
+#define    _QW_WAITING  (1U << _QW_SHIFT)       /* A writer is waiting */
+#define    _QW_LOCKED   (3U << _QW_SHIFT)       /* A writer holds the lock */
+#define    _QW_WMASK    (3U << _QW_SHIFT)       /* Writer mask */
+#define    _QR_SHIFT    (_QW_SHIFT + 2)         /* Reader count shift */
 #define    _QR_BIAS     (1U << _QR_SHIFT)
 
 void queue_read_lock_slowpath(rwlock_t *lock);
@@ -36,14 +36,21 @@ void queue_write_lock_slowpath(rwlock_t *lock);
 
 static inline bool _is_write_locked_by_me(unsigned int cnts)
 {
-    BUILD_BUG_ON(_QW_CPUMASK < NR_CPUS);
+    BUILD_BUG_ON((_QW_CPUMASK + 1) < NR_CPUS);
+    BUILD_BUG_ON(NR_CPUS * _QR_BIAS > INT_MAX);
     return (cnts & _QW_WMASK) == _QW_LOCKED &&
            (cnts & _QW_CPUMASK) == smp_processor_id();
 }
 
 static inline bool _can_read_lock(unsigned int cnts)
 {
-    return !(cnts & _QW_WMASK) || _is_write_locked_by_me(cnts);
+    /*
+     * If write locked by the caller, no other readers are possible.
+     * Not allowing the lock holder to read_lock() another
+     * INT_MAX >> _QR_SHIFT times ought to be fine.
+     */
+    return cnts <= INT_MAX &&
+           (!(cnts & _QW_WMASK) || _is_write_locked_by_me(cnts));
 }
 
 /*
--
generated by git-patchbot for /home/xen/git/xen.git#staging