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
  ...

drivers/infiniband/hw/hfi1/chip.c

@@ -8365,7 +8365,6 @@ static inline void clear_recv_intr(struct hfi1_ctxtdata *rcd)
 	struct hfi1_devdata *dd = rcd->dd;
 	u32 addr = CCE_INT_CLEAR + (8 * rcd->ireg);
 
-	mmiowb();	/* make sure everything before is written */
 	write_csr(dd, addr, rcd->imask);
 	/* force the above write on the chip and get a value back */
 	(void)read_csr(dd, addr);
@@ -11803,12 +11802,10 @@ void update_usrhead(struct hfi1_ctxtdata *rcd, u32 hd, u32 updegr, u32 egrhd,
 			<< RCV_EGR_INDEX_HEAD_HEAD_SHIFT;
 		write_uctxt_csr(dd, ctxt, RCV_EGR_INDEX_HEAD, reg);
 	}
-	mmiowb();
 	reg = ((u64)rcv_intr_count << RCV_HDR_HEAD_COUNTER_SHIFT) |
 		(((u64)hd & RCV_HDR_HEAD_HEAD_MASK)
 			<< RCV_HDR_HEAD_HEAD_SHIFT);
 	write_uctxt_csr(dd, ctxt, RCV_HDR_HEAD, reg);
-	mmiowb();
 }
 
 u32 hdrqempty(struct hfi1_ctxtdata *rcd)

drivers/infiniband/hw/hfi1/pio.c

@@ -1578,7 +1578,6 @@ void hfi1_sc_wantpiobuf_intr(struct send_context *sc, u32 needint)
 		sc_del_credit_return_intr(sc);
 	trace_hfi1_wantpiointr(sc, needint, sc->credit_ctrl);
 	if (needint) {
-		mmiowb();
 		sc_return_credits(sc);
 	}
 }

drivers/infiniband/hw/hns/hns_roce_hw_v1.c

@@ -1750,8 +1750,6 @@ static int hns_roce_v1_post_mbox(struct hns_roce_dev *hr_dev, u64 in_param,
 
 	writel(val, hcr + 5);
 
-	mmiowb();
-
 	return 0;
 }
 

drivers/infiniband/hw/i40iw/i40iw_osdep.h

@@ -211,7 +211,7 @@ enum i40iw_status_code i40iw_hw_manage_vf_pble_bp(struct i40iw_device *iwdev,
 struct i40iw_sc_vsi;
 void i40iw_hw_stats_start_timer(struct i40iw_sc_vsi *vsi);
 void i40iw_hw_stats_stop_timer(struct i40iw_sc_vsi *vsi);
-#define i40iw_mmiowb() mmiowb()
+#define i40iw_mmiowb() do { } while (0)
 void i40iw_wr32(struct i40iw_hw *hw, u32 reg, u32 value);
 u32  i40iw_rd32(struct i40iw_hw *hw, u32 reg);
 #endif				/* _I40IW_OSDEP_H_ */

drivers/infiniband/hw/mlx4/qp.c

@@ -3744,12 +3744,6 @@ out:
 		writel_relaxed(qp->doorbell_qpn,
 			to_mdev(ibqp->device)->uar_map + MLX4_SEND_DOORBELL);
 
-		/*
-		 * Make sure doorbells don't leak out of SQ spinlock
-		 * and reach the HCA out of order.
-		 */
-		mmiowb();
-
 		stamp_send_wqe(qp, ind + qp->sq_spare_wqes - 1);
 
 		qp->sq_next_wqe = ind;

drivers/infiniband/hw/mlx5/qp.c

@@ -5126,7 +5126,6 @@ out:
 		/* Make sure doorbells don't leak out of SQ spinlock
 		 * and reach the HCA out of order.
 		 */
-		mmiowb();
 		bf->offset ^= bf->buf_size;
 	}
 

drivers/infiniband/hw/mthca/mthca_cmd.c

@@ -292,12 +292,6 @@ static int mthca_cmd_post(struct mthca_dev *dev,
 		err = mthca_cmd_post_hcr(dev, in_param, out_param, in_modifier,
 					 op_modifier, op, token, event);
 
-	/*
-	 * Make sure that our HCR writes don't get mixed in with
-	 * writes from another CPU starting a FW command.
-	 */
-	mmiowb();
-
 	mutex_unlock(&dev->cmd.hcr_mutex);
 	return err;
 }

drivers/infiniband/hw/mthca/mthca_cq.c

@@ -211,11 +211,6 @@ static inline void update_cons_index(struct mthca_dev *dev, struct mthca_cq *cq,
 		mthca_write64(MTHCA_TAVOR_CQ_DB_INC_CI | cq->cqn, incr - 1,
 			      dev->kar + MTHCA_CQ_DOORBELL,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
-		/*
-		 * Make sure doorbells don't leak out of CQ spinlock
-		 * and reach the HCA out of order:
-		 */
-		mmiowb();
 	}
 }
 

drivers/infiniband/hw/mthca/mthca_qp.c

@@ -1809,11 +1809,6 @@ out:
 			      (qp->qpn << 8) | size0,
 			      dev->kar + MTHCA_SEND_DOORBELL,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
-		/*
-		 * Make sure doorbells don't leak out of SQ spinlock
-		 * and reach the HCA out of order:
-		 */
-		mmiowb();
 	}
 
 	qp->sq.next_ind = ind;
@@ -1924,12 +1919,6 @@ out:
 	qp->rq.next_ind = ind;
 	qp->rq.head    += nreq;
 
-	/*
-	 * Make sure doorbells don't leak out of RQ spinlock and reach
-	 * the HCA out of order:
-	 */
-	mmiowb();
-
 	spin_unlock_irqrestore(&qp->rq.lock, flags);
 	return err;
 }
@@ -2164,12 +2153,6 @@ out:
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
 	}
 
-	/*
-	 * Make sure doorbells don't leak out of SQ spinlock and reach
-	 * the HCA out of order:
-	 */
-	mmiowb();
-
 	spin_unlock_irqrestore(&qp->sq.lock, flags);
 	return err;
 }

drivers/infiniband/hw/mthca/mthca_srq.c

@@ -570,12 +570,6 @@ int mthca_tavor_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
 	}
 
-	/*
-	 * Make sure doorbells don't leak out of SRQ spinlock and
-	 * reach the HCA out of order:
-	 */
-	mmiowb();
-
 	spin_unlock_irqrestore(&srq->lock, flags);
 	return err;
 }

drivers/infiniband/hw/qedr/verbs.c

@@ -773,9 +773,6 @@ static void doorbell_cq(struct qedr_cq *cq, u32 cons, u8 flags)
 	cq->db.data.agg_flags = flags;
 	cq->db.data.value = cpu_to_le32(cons);
 	writeq(cq->db.raw, cq->db_addr);
-
-	/* Make sure write would stick */
-	mmiowb();
 }
 
 int qedr_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
@@ -2084,8 +2081,6 @@ static int qedr_update_qp_state(struct qedr_dev *dev,
 
 			if (rdma_protocol_roce(&dev->ibdev, 1)) {
 				writel(qp->rq.db_data.raw, qp->rq.db);
-				/* Make sure write takes effect */
-				mmiowb();
 			}
 			break;
 		case QED_ROCE_QP_STATE_ERR:
@@ -3502,9 +3497,6 @@ int qedr_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 	smp_wmb();
 	writel(qp->sq.db_data.raw, qp->sq.db);
 
-	/* Make sure write sticks */
-	mmiowb();
-
 	spin_unlock_irqrestore(&qp->q_lock, flags);
 
 	return rc;
@@ -3695,12 +3687,8 @@ int qedr_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
 
 		writel(qp->rq.db_data.raw, qp->rq.db);
 
-		/* Make sure write sticks */
-		mmiowb();
-
 		if (rdma_protocol_iwarp(&dev->ibdev, 1)) {
 			writel(qp->rq.iwarp_db2_data.raw, qp->rq.iwarp_db2);
-			mmiowb();	/* for second doorbell */
 		}
 
 		wr = wr->next;

drivers/infiniband/hw/qib/qib_iba6120.c

@@ -1884,7 +1884,6 @@ static void qib_6120_put_tid(struct qib_devdata *dd, u64 __iomem *tidptr,
 	qib_write_kreg(dd, kr_scratch, 0xfeeddeaf);
 	writel(pa, tidp32);
 	qib_write_kreg(dd, kr_scratch, 0xdeadbeef);
-	mmiowb();
 	spin_unlock_irqrestore(tidlockp, flags);
 }
 
@@ -1928,7 +1927,6 @@ static void qib_6120_put_tid_2(struct qib_devdata *dd, u64 __iomem *tidptr,
 			pa |= 2 << 29;
 	}
 	writel(pa, tidp32);
-	mmiowb();
 }
 
 
@@ -2053,9 +2051,7 @@ static void qib_update_6120_usrhead(struct qib_ctxtdata *rcd, u64 hd,
 {
 	if (updegr)
 		qib_write_ureg(rcd->dd, ur_rcvegrindexhead, egrhd, rcd->ctxt);
-	mmiowb();
 	qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt);
-	mmiowb();
 }
 
 static u32 qib_6120_hdrqempty(struct qib_ctxtdata *rcd)

drivers/infiniband/hw/qib/qib_iba7220.c

@@ -2175,7 +2175,6 @@ static void qib_7220_put_tid(struct qib_devdata *dd, u64 __iomem *tidptr,
 		pa = chippa;
 	}
 	writeq(pa, tidptr);
-	mmiowb();
 }
 
 /**
@@ -2704,9 +2703,7 @@ static void qib_update_7220_usrhead(struct qib_ctxtdata *rcd, u64 hd,
 {
 	if (updegr)
 		qib_write_ureg(rcd->dd, ur_rcvegrindexhead, egrhd, rcd->ctxt);
-	mmiowb();
 	qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt);
-	mmiowb();
 }
 
 static u32 qib_7220_hdrqempty(struct qib_ctxtdata *rcd)

drivers/infiniband/hw/qib/qib_iba7322.c

@@ -3793,7 +3793,6 @@ static void qib_7322_put_tid(struct qib_devdata *dd, u64 __iomem *tidptr,
 		pa = chippa;
 	}
 	writeq(pa, tidptr);
-	mmiowb();
 }
 
 /**
@@ -4440,10 +4439,8 @@ static void qib_update_7322_usrhead(struct qib_ctxtdata *rcd, u64 hd,
 		adjust_rcv_timeout(rcd, npkts);
 	if (updegr)
 		qib_write_ureg(rcd->dd, ur_rcvegrindexhead, egrhd, rcd->ctxt);
-	mmiowb();
 	qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt);
 	qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt);
-	mmiowb();
 }
 
 static u32 qib_7322_hdrqempty(struct qib_ctxtdata *rcd)

drivers/infiniband/hw/qib/qib_sd7220.c

@@ -1068,7 +1068,6 @@ static int qib_sd_setvals(struct qib_devdata *dd)
 	for (idx = 0; idx < NUM_DDS_REGS; ++idx) {
 		data = ((dds_reg_map & 0xF) << 4) | TX_FAST_ELT;
 		writeq(data, iaddr + idx);
-		mmiowb();
 		qib_read_kreg32(dd, kr_scratch);
 		dds_reg_map >>= 4;
 		for (midx = 0; midx < DDS_ROWS; ++midx) {
@@ -1076,7 +1075,6 @@ static int qib_sd_setvals(struct qib_devdata *dd)
 
 			data = dds_init_vals[midx].reg_vals[idx];
 			writeq(data, daddr);
-			mmiowb();
 			qib_read_kreg32(dd, kr_scratch);
 		} /* End inner for (vals for this reg, each row) */
 	} /* end outer for (regs to be stored) */
@@ -1098,13 +1096,11 @@ static int qib_sd_setvals(struct qib_devdata *dd)
 		didx = idx + min_idx;
 		/* Store the next RXEQ register address */
 		writeq(rxeq_init_vals[idx].rdesc, iaddr + didx);
-		mmiowb();
 		qib_read_kreg32(dd, kr_scratch);
 		/* Iterate through RXEQ values */
 		for (vidx = 0; vidx < 4; vidx++) {
 			data = rxeq_init_vals[idx].rdata[vidx];
 			writeq(data, taddr + (vidx << 6) + idx);
-			mmiowb();
 			qib_read_kreg32(dd, kr_scratch);
 		}
 	} /* end outer for (Reg-writes for RXEQ) */