linux-kernel - [PATCH] dmaengine: dw-edma: Remove runtime PM support

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20220512083612.122824-1-manivannan.sadhasivam@linaro.org>
Date:   Thu, 12 May 2022 14:06:12 +0530
From:   Manivannan Sadhasivam <manivannan.sadhasivam@...aro.org>
To:     gustavo.pimentel@...opsys.com, vkoul@...nel.org
Cc:     dmaengine@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-arm-msm@...r.kernel.org,
        Manivannan Sadhasivam <manivannan.sadhasivam@...aro.org>,
        Serge Semin <fancer.lancer@...il.com>,
        Frank Li <Frank.Li@....com>
Subject: [PATCH] dmaengine: dw-edma: Remove runtime PM support

Currently, the dw-edma driver enables the runtime_pm for parent device
(chip->dev) and increments/decrements the refcount during alloc/free
chan resources callbacks.

This leads to a problem when the eDMA driver has been probed, but the
channels were not used. This scenario can happen when the DW PCIe driver
probes eDMA driver successfully, but the PCI EPF driver decides not to
use eDMA channels and use iATU instead for PCI transfers.

In this case, the underlying device would be runtime suspended due to
pm_runtime_enable() in dw_edma_probe() and the PCI EPF driver would have
no knowledge of it.

Ideally, the eDMA driver should not be the one doing the runtime PM of
the parent device. The responsibility should instead belong to the client
drivers like PCI EPF.

So let's remove the runtime PM support from eDMA driver.

Cc: Serge Semin <fancer.lancer@...il.com>
Cc: Frank Li <Frank.Li@....com>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@...aro.org>
---

Note: This patch is made on top of Frank and Serge's edma work, but should
be applicable independently also.

[PATCH v10 0/9] Enable designware PCI EP EDMA locally
[PATCH v2 00/26] dmaengine: dw-edma: Add RP/EP local DMA controllers support

 drivers/dma/dw-edma/dw-edma-core.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index 561686b51915..b2b5077d380b 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -9,7 +9,6 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
-#include <linux/pm_runtime.h>
 #include <linux/dmaengine.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
@@ -731,15 +730,12 @@ static int dw_edma_alloc_chan_resources(struct dma_chan *dchan)
 		dchan->dev->chan_dma_dev = false;
 	}
 
-	pm_runtime_get(chan->dw->chip->dev);
-
 	return 0;
 }
 
 static void dw_edma_free_chan_resources(struct dma_chan *dchan)
 {
 	unsigned long timeout = jiffies + msecs_to_jiffies(5000);
-	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
 	int ret;
 
 	while (time_before(jiffies, timeout)) {
@@ -752,8 +748,6 @@ static void dw_edma_free_chan_resources(struct dma_chan *dchan)
 
 		cpu_relax();
 	}
-
-	pm_runtime_put(chan->dw->chip->dev);
 }
 
 static int dw_edma_channel_setup(struct dw_edma *dw, u32 wr_alloc, u32 rd_alloc)
@@ -1010,9 +1004,6 @@ int dw_edma_probe(struct dw_edma_chip *chip)
 	if (err)
 		goto err_irq_free;
 
-	/* Power management */
-	pm_runtime_enable(dev);
-
 	/* Turn debugfs on */
 	dw_edma_v0_core_debugfs_on(dw);
 
@@ -1046,9 +1037,6 @@ int dw_edma_remove(struct dw_edma_chip *chip)
 	for (i = (dw->nr_irqs - 1); i >= 0; i--)
 		free_irq(chip->ops->irq_vector(dev, i), &dw->irq[i]);
 
-	/* Power management */
-	pm_runtime_disable(dev);
-
 	/* Deregister eDMA device */
 	dma_async_device_unregister(&dw->dma);
 	list_for_each_entry_safe(chan, _chan, &dw->dma.channels,
-- 
2.25.1