Merge tag 'arm64-mmiowb' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull mmiowb removal from Will Deacon:
 "Remove Mysterious Macro Intended to Obscure Weird Behaviours (mmiowb())

  Remove mmiowb() from the kernel memory barrier API and instead, for
  architectures that need it, hide the barrier inside spin_unlock() when
  MMIO has been performed inside the critical section.

  The only relatively recent changes have been addressing review
  comments on the documentation, which is in a much better shape thanks
  to the efforts of Ben and Ingo.

  I was initially planning to split this into two pull requests so that
  you could run the coccinelle script yourself, however it's been plain
  sailing in linux-next so I've just included the whole lot here to keep
  things simple"

* tag 'arm64-mmiowb' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (23 commits)
  docs/memory-barriers.txt: Update I/O section to be clearer about CPU vs thread
  docs/memory-barriers.txt: Fix style, spacing and grammar in I/O section
  arch: Remove dummy mmiowb() definitions from arch code
  net/ethernet/silan/sc92031: Remove stale comment about mmiowb()
  i40iw: Redefine i40iw_mmiowb() to do nothing
  scsi/qla1280: Remove stale comment about mmiowb()
  drivers: Remove explicit invocations of mmiowb()
  drivers: Remove useless trailing comments from mmiowb() invocations
  Documentation: Kill all references to mmiowb()
  riscv/mmiowb: Hook up mmwiob() implementation to asm-generic code
  powerpc/mmiowb: Hook up mmwiob() implementation to asm-generic code
  ia64/mmiowb: Add unconditional mmiowb() to arch_spin_unlock()
  mips/mmiowb: Add unconditional mmiowb() to arch_spin_unlock()
  sh/mmiowb: Add unconditional mmiowb() to arch_spin_unlock()
  m68k/io: Remove useless definition of mmiowb()
  nds32/io: Remove useless definition of mmiowb()
  x86/io: Remove useless definition of mmiowb()
  arm64/io: Remove useless definition of mmiowb()
  ARM/io: Remove useless definition of mmiowb()
  mmiowb: Hook up mmiowb helpers to spinlocks and generic I/O accessors
  ...

11 files changed, 1 insertions, 31 deletions

diff --git a/drivers/scsi/bfa/bfa.h b/drivers/scsi/bfa/bfa.h
index 0e119d838e1b..762cb77253b9 100644
--- a/drivers/scsi/bfa/bfa.h
+++ b/drivers/scsi/bfa/bfa.h
@@ -62,8 +62,7 @@ void bfa_isr_unhandled(struct bfa_s *bfa, struct bfi_msg_s *m);
 			((__bfa)->iocfc.cfg.drvcfg.num_reqq_elems - 1); \
 		writel((__bfa)->iocfc.req_cq_pi[__reqq],		\
 			(__bfa)->iocfc.bfa_regs.cpe_q_pi[__reqq]);	\
-		mmiowb();      \
-	} while (0)
+		} while (0)
 
 #define bfa_rspq_pi(__bfa, __rspq)					\
 	(*(u32 *)((__bfa)->iocfc.rsp_cq_shadow_pi[__rspq].kva))
diff --git a/drivers/scsi/bfa/bfa_hw_cb.c b/drivers/scsi/bfa/bfa_hw_cb.c
index c4a0c0eb88a5..4a0d881b2602 100644
--- a/drivers/scsi/bfa/bfa_hw_cb.c
+++ b/drivers/scsi/bfa/bfa_hw_cb.c
@@ -61,7 +61,6 @@ bfa_hwcb_rspq_ack_msix(struct bfa_s *bfa, int rspq, u32 ci)
 
 	bfa_rspq_ci(bfa, rspq) = ci;
 	writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]);
-	mmiowb();
 }
 
 void
@@ -72,7 +71,6 @@ bfa_hwcb_rspq_ack(struct bfa_s *bfa, int rspq, u32 ci)
 
 	bfa_rspq_ci(bfa, rspq) = ci;
 	writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]);
-	mmiowb();
 }
 
 void
diff --git a/drivers/scsi/bfa/bfa_hw_ct.c b/drivers/scsi/bfa/bfa_hw_ct.c
index b0ff378dece2..b7be5f4f02a5 100644
--- a/drivers/scsi/bfa/bfa_hw_ct.c
+++ b/drivers/scsi/bfa/bfa_hw_ct.c
@@ -81,7 +81,6 @@ bfa_hwct_rspq_ack(struct bfa_s *bfa, int rspq, u32 ci)
 
 	bfa_rspq_ci(bfa, rspq) = ci;
 	writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]);
-	mmiowb();
 }
 
 /*
@@ -94,7 +93,6 @@ bfa_hwct2_rspq_ack(struct bfa_s *bfa, int rspq, u32 ci)
 {
 	bfa_rspq_ci(bfa, rspq) = ci;
 	writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]);
-	mmiowb();
 }
 
 void
diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c
index 039328d9ef13..19734ec7f42e 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c
@@ -991,7 +991,6 @@ void bnx2fc_arm_cq(struct bnx2fc_rport *tgt)
 			FCOE_CQE_TOGGLE_BIT_SHIFT);
 	msg = *((u32 *)rx_db);
 	writel(cpu_to_le32(msg), tgt->ctx_base);
-	mmiowb();
 
 }
 
@@ -1409,7 +1408,6 @@ void bnx2fc_ring_doorbell(struct bnx2fc_rport *tgt)
 				(tgt->sq_curr_toggle_bit << 15);
 	msg = *((u32 *)sq_db);
 	writel(cpu_to_le32(msg), tgt->ctx_base);
-	mmiowb();
 
 }
 
diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c
index fae6f71e677d..12666313b937 100644
--- a/drivers/scsi/bnx2i/bnx2i_hwi.c
+++ b/drivers/scsi/bnx2i/bnx2i_hwi.c
@@ -253,7 +253,6 @@ void bnx2i_put_rq_buf(struct bnx2i_conn *bnx2i_conn, int count)
 		writew(ep->qp.rq_prod_idx,
 		       ep->qp.ctx_base + CNIC_RECV_DOORBELL);
 	}
-	mmiowb();
 }
 
 
@@ -279,8 +278,6 @@ static void bnx2i_ring_sq_dbell(struct bnx2i_conn *bnx2i_conn, int count)
 		bnx2i_ring_577xx_doorbell(bnx2i_conn);
 	} else
 		writew(count, ep->qp.ctx_base + CNIC_SEND_DOORBELL);
-
-	mmiowb(); /* flush posted PCI writes */
 }
 
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 293f5cf524d7..59a6546fd602 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -815,7 +815,6 @@ megasas_fire_cmd_skinny(struct megasas_instance *instance,
 	       &(regs)->inbound_high_queue_port);
 	writel((lower_32_bits(frame_phys_addr) | (frame_count<<1))|1,
 	       &(regs)->inbound_low_queue_port);
-	mmiowb();
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 }
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 1d17128030cd..e35c2b64c145 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -242,7 +242,6 @@ megasas_fire_cmd_fusion(struct megasas_instance *instance,
 		&instance->reg_set->inbound_low_queue_port);
 	writel(le32_to_cpu(req_desc->u.high),
 		&instance->reg_set->inbound_high_queue_port);
-	mmiowb();
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 #endif
 }
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 1d8c584ec1e9..f60b9e0a6ca6 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -3333,7 +3333,6 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr,
 	spin_lock_irqsave(writeq_lock, flags);
 	__raw_writel((u32)(b), addr);
 	__raw_writel((u32)(b >> 32), (addr + 4));
-	mmiowb();
 	spin_unlock_irqrestore(writeq_lock, flags);
 }
 
diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c
index 6ca583bdde23..53e8221f6816 100644
--- a/drivers/scsi/qedf/qedf_io.c
+++ b/drivers/scsi/qedf/qedf_io.c
@@ -807,7 +807,6 @@ void qedf_ring_doorbell(struct qedf_rport *fcport)
 	writel(*(u32 *)&dbell, fcport->p_doorbell);
 	/* Make sure SQ index is updated so f/w prcesses requests in order */
 	wmb();
-	mmiowb();
 }
 
 static void qedf_trace_io(struct qedf_rport *fcport, struct qedf_ioreq *io_req,
diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c
index e2a995a6e8e7..f8f86774f77f 100644
--- a/drivers/scsi/qedi/qedi_fw.c
+++ b/drivers/scsi/qedi/qedi_fw.c
@@ -985,7 +985,6 @@ static void qedi_ring_doorbell(struct qedi_conn *qedi_conn)
 	 * others they are two different assembly operations.
 	 */
 	wmb();
-	mmiowb();
 	QEDI_INFO(&qedi_conn->qedi->dbg_ctx, QEDI_LOG_MP_REQ,
 		  "prod_idx=0x%x, fw_prod_idx=0x%x, cid=0x%x\n",
 		  qedi_conn->ep->sq_prod_idx, qedi_conn->ep->fw_sq_prod_idx,
diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c
index 6856dfdfa473..327eff67a1ee 100644
--- a/drivers/scsi/qla1280.c
+++ b/drivers/scsi/qla1280.c
@@ -3004,8 +3004,6 @@ qla1280_64bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 	sp->flags |= SRB_SENT;
 	ha->actthreads++;
 	WRT_REG_WORD(&reg->mailbox4, ha->req_ring_index);
-	/* Enforce mmio write ordering; see comment in qla1280_isp_cmd(). */
-	mmiowb();
 
  out:
 	if (status)
@@ -3254,8 +3252,6 @@ qla1280_32bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 	sp->flags |= SRB_SENT;
 	ha->actthreads++;
 	WRT_REG_WORD(&reg->mailbox4, ha->req_ring_index);
-	/* Enforce mmio write ordering; see comment in qla1280_isp_cmd(). */
-	mmiowb();
 
 out:
 	if (status)
@@ -3367,19 +3363,8 @@ qla1280_isp_cmd(struct scsi_qla_host *ha)
 
 	/*
 	 * Update request index to mailbox4 (Request Queue In).
-	 * The mmiowb() ensures that this write is ordered with writes by other
-	 * CPUs.  Without the mmiowb(), it is possible for the following:
-	 *    CPUA posts write of index 5 to mailbox4
-	 *    CPUA releases host lock
-	 *    CPUB acquires host lock
-	 *    CPUB posts write of index 6 to mailbox4
-	 *    On PCI bus, order reverses and write of 6 posts, then index 5,
-	 *       causing chip to issue full queue of stale commands
-	 * The mmiowb() prevents future writes from crossing the barrier.
-	 * See Documentation/driver-api/device-io.rst for more information.
 	 */
 	WRT_REG_WORD(&reg->mailbox4, ha->req_ring_index);
-	mmiowb();
 
 	LEAVE("qla1280_isp_cmd");
 }