Merge tag 'v6.18-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "Drivers:
   - Add ciphertext hiding support to ccp
   - Add hashjoin, gather and UDMA data move features to hisilicon
   - Add lz4 and lz77_only to hisilicon
   - Add xilinx hwrng driver
   - Add ti driver with ecb/cbc aes support
   - Add ring buffer idle and command queue telemetry for GEN6 in qat

  Others:
   - Use rcu_dereference_all to stop false alarms in rhashtable
   - Fix CPU number wraparound in padata"

* tag 'v6.18-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (78 commits)
  dt-bindings: rng: hisi-rng: convert to DT schema
  crypto: doc - Add explicit title heading to API docs
  hwrng: ks-sa - fix division by zero in ks_sa_rng_init
  KEYS: X.509: Fix Basic Constraints CA flag parsing
  crypto: anubis - simplify return statement in anubis_mod_init
  crypto: hisilicon/qm - set NULL to qm->debug.qm_diff_regs
  crypto: hisilicon/qm - clear all VF configurations in the hardware
  crypto: hisilicon - enable error reporting again
  crypto: hisilicon/qm - mask axi error before memory init
  crypto: hisilicon/qm - invalidate queues in use
  crypto: qat - Return pointer directly in adf_ctl_alloc_resources
  crypto: aspeed - Fix dma_unmap_sg() direction
  rhashtable: Use rcu_dereference_all and rcu_dereference_all_check
  crypto: comp - Use same definition of context alloc and free ops
  crypto: omap - convert from tasklet to BH workqueue
  crypto: qat - Replace kzalloc() + copy_from_user() with memdup_user()
  crypto: caam - double the entropy delay interval for retry
  padata: WQ_PERCPU added to alloc_workqueue users
  padata: replace use of system_unbound_wq with system_dfl_wq
  crypto: cryptd - WQ_PERCPU added to alloc_workqueue users
  ...

1 files changed, 10 insertions, 5 deletions

diff --git a/kernel/padata.c b/kernel/padata.c
index f85f8bd788d0..f4def028c48c 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -291,8 +291,12 @@ static void padata_reorder(struct padata_priv *padata)
 		struct padata_serial_queue *squeue;
 		int cb_cpu;
 
-		cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu);
 		processed++;
+		/* When sequence wraps around, reset to the first CPU. */
+		if (unlikely(processed == 0))
+			cpu = cpumask_first(pd->cpumask.pcpu);
+		else
+			cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu);
 
 		cb_cpu = padata->cb_cpu;
 		squeue = per_cpu_ptr(pd->squeue, cb_cpu);
@@ -486,9 +490,9 @@ void __init padata_do_multithreaded(struct padata_mt_job *job)
 			do {
 				nid = next_node_in(old_node, node_states[N_CPU]);
 			} while (!atomic_try_cmpxchg(&last_used_nid, &old_node, nid));
-			queue_work_node(nid, system_unbound_wq, &pw->pw_work);
+			queue_work_node(nid, system_dfl_wq, &pw->pw_work);
 		} else {
-			queue_work(system_unbound_wq, &pw->pw_work);
+			queue_work(system_dfl_wq, &pw->pw_work);
 		}
 
 	/* Use the current thread, which saves starting a workqueue worker. */
@@ -963,8 +967,9 @@ struct padata_instance *padata_alloc(const char *name)
 
 	cpus_read_lock();
 
-	pinst->serial_wq = alloc_workqueue("%s_serial", WQ_MEM_RECLAIM |
-					   WQ_CPU_INTENSIVE, 1, name);
+	pinst->serial_wq = alloc_workqueue("%s_serial",
+					   WQ_MEM_RECLAIM | WQ_CPU_INTENSIVE | WQ_PERCPU,
+					   1, name);
 	if (!pinst->serial_wq)
 		goto err_put_cpus;