From mboxrd@z Thu Jan 1 00:00:00 1970 From: sbranden@broadcom.com (Scott Branden) Date: Mon, 30 Mar 2015 20:40:43 -0700 Subject: [PATCH] dmaengine: pl330: fix the race condition in pl330 driver. In-Reply-To: <20150330172546.GI7192@intel.com> References: <1427414105-3480-1-git-send-email-sbranden@broadcom.com> <20150330172546.GI7192@intel.com> Message-ID: <551A173B.4010704@broadcom.com> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org Hi Vinod, Jassi, Some details on the problem encountered. On 15-03-30 10:25 AM, Vinod Koul wrote: > On Mon, Mar 30, 2015 at 10:17:17PM +0530, Jassi Brar wrote: >> On Fri, Mar 27, 2015 at 5:25 AM, Scott Branden wrote: >>> From: ismail >>> >>> Update the thread running index before issuing the >>> GO command to the DMAC. >>> >>> Tested-by: Mohamed Ismail Abdul Packir Mohamed >>> Reviewed-by: Ray Jui >>> Reviewed-by: Arun Parameswaran >>> Reviewed-by: Scott Branden >>> Signed-off-by: Scott Branden >>> Signed-off-by: Mohamed Ismail Abdul Packir Mohamed >>> --- >>> drivers/dma/pl330.c | 4 ++-- >>> 1 file changed, 2 insertions(+), 2 deletions(-) >>> >>> diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c >>> index 0e1f567..631642d 100644 >>> --- a/drivers/dma/pl330.c >>> +++ b/drivers/dma/pl330.c >>> @@ -1072,11 +1072,11 @@ static bool _trigger(struct pl330_thread *thrd) >>> /* Set to generate interrupts for SEV */ >>> writel(readl(regs + INTEN) | (1 << thrd->ev), regs + INTEN); >>> >>> + thrd->req_running = idx; >>> + >>> /* Only manager can execute GO */ >>> _execute_DBGINSN(thrd, insn, true); >>> >>> - thrd->req_running = idx; >>> - >> It would help to know what the behavior looks like before and after >> the patch. If anything we should look at locking rather the >> reordering. > Yes that ia fair request, looking at changelog it is hard to understand the > issue seen? > We encountered this problem as we modified the driver to make SMC calls to a TZ handler. This slowed down the driver to the point where DMA transactions easily failed. I believe the same could be accomplished by adding a delay between the GOCMD and update of the req_running and running the built in dmatest. The DMA transaction is broken if the interrupt occurs before the thrd->req_running is updated. The pl330 issues a GOCMD (in _trigger function) to start a new transfer. The issue of GOCMD generates an interrupt and the IRQ handler will call the pl330_update function to process the interrupt. The pl330_update function will verify the thread running index and break the transaction, if the thread running index is not set. Regards, Scott From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751634AbbCaDks (ORCPT ); Mon, 30 Mar 2015 23:40:48 -0400 Received: from mail-gw1-out.broadcom.com ([216.31.210.62]:3880 "EHLO mail-gw1-out.broadcom.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750930AbbCaDkq (ORCPT ); Mon, 30 Mar 2015 23:40:46 -0400 X-IronPort-AV: E=Sophos;i="5.11,498,1422950400"; d="scan'208";a="60977924" Message-ID: <551A173B.4010704@broadcom.com> Date: Mon, 30 Mar 2015 20:40:43 -0700 From: Scott Branden User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.5.0 MIME-Version: 1.0 To: Vinod Koul , Jassi Brar CC: Dan Williams , Linux Kernel Mailing List , ismail , Anatol Pomazao , Dmitry Torokhov , , "linux-arm-kernel@lists.infradead.org" Subject: Re: [PATCH] dmaengine: pl330: fix the race condition in pl330 driver. References: <1427414105-3480-1-git-send-email-sbranden@broadcom.com> <20150330172546.GI7192@intel.com> In-Reply-To: <20150330172546.GI7192@intel.com> Content-Type: text/plain; charset="windows-1252"; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Vinod, Jassi, Some details on the problem encountered. On 15-03-30 10:25 AM, Vinod Koul wrote: > On Mon, Mar 30, 2015 at 10:17:17PM +0530, Jassi Brar wrote: >> On Fri, Mar 27, 2015 at 5:25 AM, Scott Branden wrote: >>> From: ismail >>> >>> Update the thread running index before issuing the >>> GO command to the DMAC. >>> >>> Tested-by: Mohamed Ismail Abdul Packir Mohamed >>> Reviewed-by: Ray Jui >>> Reviewed-by: Arun Parameswaran >>> Reviewed-by: Scott Branden >>> Signed-off-by: Scott Branden >>> Signed-off-by: Mohamed Ismail Abdul Packir Mohamed >>> --- >>> drivers/dma/pl330.c | 4 ++-- >>> 1 file changed, 2 insertions(+), 2 deletions(-) >>> >>> diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c >>> index 0e1f567..631642d 100644 >>> --- a/drivers/dma/pl330.c >>> +++ b/drivers/dma/pl330.c >>> @@ -1072,11 +1072,11 @@ static bool _trigger(struct pl330_thread *thrd) >>> /* Set to generate interrupts for SEV */ >>> writel(readl(regs + INTEN) | (1 << thrd->ev), regs + INTEN); >>> >>> + thrd->req_running = idx; >>> + >>> /* Only manager can execute GO */ >>> _execute_DBGINSN(thrd, insn, true); >>> >>> - thrd->req_running = idx; >>> - >> It would help to know what the behavior looks like before and after >> the patch. If anything we should look at locking rather the >> reordering. > Yes that ia fair request, looking at changelog it is hard to understand the > issue seen? > We encountered this problem as we modified the driver to make SMC calls to a TZ handler. This slowed down the driver to the point where DMA transactions easily failed. I believe the same could be accomplished by adding a delay between the GOCMD and update of the req_running and running the built in dmatest. The DMA transaction is broken if the interrupt occurs before the thrd->req_running is updated. The pl330 issues a GOCMD (in _trigger function) to start a new transfer. The issue of GOCMD generates an interrupt and the IRQ handler will call the pl330_update function to process the interrupt. The pl330_update function will verify the thread running index and break the transaction, if the thread running index is not set. Regards, Scott