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
  ...

3 files changed, 0 insertions, 18 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index c81d15bf259c..87e90b5d4d7d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -129,10 +129,6 @@ static int mlx4_reset_slave(struct mlx4_dev *dev)
 	comm_flags = rst_req << COM_CHAN_RST_REQ_OFFSET;
 	__raw_writel((__force u32)cpu_to_be32(comm_flags),
 		     (__iomem char *)priv->mfunc.comm + MLX4_COMM_CHAN_FLAGS);
-	/* Make sure that our comm channel write doesn't
-	 * get mixed in with writes from another CPU.
-	 */
-	mmiowb();
 
 	end = msecs_to_jiffies(MLX4_COMM_TIME) + jiffies;
 	while (time_before(jiffies, end)) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index a5d5d6fc1da0..c678344d22a2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -281,7 +281,6 @@ static int mlx4_comm_cmd_post(struct mlx4_dev *dev, u8 cmd, u16 param)
 	val = param | (cmd << 16) | (priv->cmd.comm_toggle << 31);
 	__raw_writel((__force u32) cpu_to_be32(val),
 		     &priv->mfunc.comm->slave_write);
-	mmiowb();
 	mutex_unlock(&dev->persist->device_state_mutex);
 	return 0;
 }
@@ -496,12 +495,6 @@ static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param,
 					       (op_modifier << HCR_OPMOD_SHIFT) |
 					       op), hcr + 6);
 
-	/*
-	 * Make sure that our HCR writes don't get mixed in with
-	 * writes from another CPU starting a FW command.
-	 */
-	mmiowb();
-
 	cmd->toggle = cmd->toggle ^ 1;
 
 	ret = 0;
@@ -2206,7 +2199,6 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
 	}
 	__raw_writel((__force u32) cpu_to_be32(reply),
 		     &priv->mfunc.comm[slave].slave_read);
-	mmiowb();
 
 	return;
 
@@ -2410,7 +2402,6 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 				     &priv->mfunc.comm[i].slave_write);
 			__raw_writel((__force u32) 0,
 				     &priv->mfunc.comm[i].slave_read);
-			mmiowb();
 			for (port = 1; port <= MLX4_MAX_PORTS; port++) {
 				struct mlx4_vport_state *admin_vport;
 				struct mlx4_vport_state *oper_vport;
@@ -2576,10 +2567,6 @@ void mlx4_report_internal_err_comm_event(struct mlx4_dev *dev)
 		slave_read |= (u32)COMM_CHAN_EVENT_INTERNAL_ERR;
 		__raw_writel((__force u32)cpu_to_be32(slave_read),
 			     &priv->mfunc.comm[slave].slave_read);
-		/* Make sure that our comm channel write doesn't
-		 * get mixed in with writes from another CPU.
-		 */
-		mmiowb();
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index be48c6440251..c087d1014b09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -917,7 +917,6 @@ static void cmd_work_handler(struct work_struct *work)
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
 	wmb();
 	iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell);
-	mmiowb();
 	/* if not in polling don't use ent after this point */
 	if (cmd_mode == CMD_MODE_POLLING || poll_cmd) {
 		poll_timeout(ent);