powerpc/qspinlock: implement option to yield to previous node

Queued waiters which are not at the head of the queue don't spin on
the lock word but their qnode lock word, waiting for the previous queued
CPU to release them. Add an option which allows these waiters to yield
to the previous CPU if its vCPU is preempted.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221126095932.1234527-9-npiggin@gmail.com

diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c
index 18e21574e6c598e630ca3492da0018bd13dfa708..41afd8e689186060ecc2c49978bb652c88c5a58c 100644 (file)
--- a/arch/powerpc/lib/qspinlock.c
+++ b/arch/powerpc/lib/qspinlock.c
@@ -26,6 +26,7 @@ static bool maybe_stealers __read_mostly = true;
 static int head_spins __read_mostly = (1 << 8);
 
 static bool pv_yield_owner __read_mostly = true;
+static bool pv_yield_prev __read_mostly = true;
 
 static DEFINE_PER_CPU_ALIGNED(struct qnodes, qnodes);
 
@@ -195,6 +196,32 @@ relax:
        cpu_relax();
 }
 
+static __always_inline void yield_to_prev(struct qspinlock *lock, struct qnode *node, u32 val, bool paravirt)
+{
+       int prev_cpu = decode_tail_cpu(val);
+       u32 yield_count;
+
+       if (!paravirt)
+               goto relax;
+
+       if (!pv_yield_prev)
+               goto relax;
+
+       yield_count = yield_count_of(prev_cpu);
+       if ((yield_count & 1) == 0)
+               goto relax; /* owner vcpu is running */
+
+       smp_rmb(); /* See yield_to_locked_owner comment */
+
+       if (!node->locked) {
+               yield_to_preempted(prev_cpu, yield_count);
+               return;
+       }
+
+relax:
+       cpu_relax();
+}
+
 
 static __always_inline bool try_to_steal_lock(struct qspinlock *lock, bool paravirt)
 {
@@ -269,7 +296,7 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 
                /* Wait for mcs node lock to be released */
                while (!node->locked)
-                       cpu_relax();
+                       yield_to_prev(lock, node, old, paravirt);
 
                smp_rmb(); /* acquire barrier for the mcs lock */
        }
@@ -417,12 +444,29 @@ static int pv_yield_owner_get(void *data, u64 *val)
 
 DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_owner, pv_yield_owner_get, pv_yield_owner_set, "%llu\n");
 
+static int pv_yield_prev_set(void *data, u64 val)
+{
+       pv_yield_prev = !!val;
+
+       return 0;
+}
+
+static int pv_yield_prev_get(void *data, u64 *val)
+{
+       *val = pv_yield_prev;
+
+       return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_prev, pv_yield_prev_get, pv_yield_prev_set, "%llu\n");
+
 static __init int spinlock_debugfs_init(void)
 {
        debugfs_create_file("qspl_steal_spins", 0600, arch_debugfs_dir, NULL, &fops_steal_spins);
        debugfs_create_file("qspl_head_spins", 0600, arch_debugfs_dir, NULL, &fops_head_spins);
        if (is_shared_processor()) {
                debugfs_create_file("qspl_pv_yield_owner", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_owner);
+               debugfs_create_file("qspl_pv_yield_prev", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_prev);
        }
 
        return 0;