Re: [dpdk-dev] [PATCH] eal: map PCI memory resources after hugepages

["XU Liang" <liang.xu@cinfotech.cn>]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset="UTF-8", Size: 7580 bytes --]

It is a default value when the requested_addr isn't exist, not an overide. When the pci_map_resource is called at the primary process, the requested_addr is NULL. The default value will be provided by default_map_addr.
When the pci_map_resource is called at the secondery process, the requested_addr is exist. Then everything isn't be changed.------------------------------------------------------------------From:Burakov, Anatoly <anatoly.burakov@intel.com>Time:2014 Nov 10 (Mon) 17 : 54To:徐亮 <liang.xu@cinfotech.cn>, dev@dpdk.org <dev@dpdk.org>Cc:thomas.monjalon@6wind.com <thomas.monjalon@6wind.com>Subject:RE: [PATCH] eal: map PCI memory resources after hugepages
Hi Liang

I don't think that overriding the value passed to pci_map_resource as argument is the way to go. While it results in less code, it looks weird, in my opinion at least, as I believe tracking the correctness of address being requested should be the responsibility of the caller, i.e. either UIO or VFIO code. Which is why I keep insisting that you make requested_pci_addr global to linuxapp EAL PCI section and put it into include/eal_pci_init.h. Would you mind if I made a patch for this issue based on your code?

Thanks,
Anatoly

-----Original Message-----
From: Liang Xu [mailto:liang.xu@cinfotech.cn] 
Sent: Saturday, November 8, 2014 3:32 AM
To: dev@dpdk.org
Cc: Burakov, Anatoly; thomas.monjalon@6wind.com
Subject: [PATCH] eal: map PCI memory resources after hugepages

A multiple process DPDK application must mmap hugepages and pci resources into same virtual addresses. By default the virtual addresses chosen by the primary process automatically when calling the mmap. But sometime the chosen virtual addresses isn't usable at secondary process. Such as the secondary process linked with more libraries than primary process. The library has been mapped into this virtual address. The command line parameter 'base-virtaddr' has been added for this situation. If it's configured, the hugepages will be mapped into this base address. But the virtual address of pci resources mapped still does not refer to the parameter. In that case "EAL: pci_map_resource(): cannot mmap" 
will be got.

This patch try to map pci resources after hugepages. So the error can be resolved by set base-virtaddr into free virtual address space.

Signed-off-by: Liang Xu <liang.xu@cinfotech.cn>
---
 lib/librte_eal/linuxapp/eal/eal_pci.c | 32 +++++++++++++++++++++++++++++++-
 1 file changed, 31 insertions(+), 1 deletion(-)

diff --git a/lib/librte_eal/linuxapp/eal/eal_pci.c b/lib/librte_eal/linuxapp/eal/eal_pci.c
index ddb0535..502eef2 100644
--- a/lib/librte_eal/linuxapp/eal/eal_pci.c
+++ b/lib/librte_eal/linuxapp/eal/eal_pci.c
@@ -97,14 +97,42 @@ error:
 	return -1;
 }
 
+static void *
+pci_find_max_end_va(void)
+{
+	const struct rte_memseg *seg = rte_eal_get_physmem_layout();
+	const struct rte_memseg *last = seg;
+	unsigned i = 0;
+
+	for (i = 0; i < RTE_MAX_MEMSEG; i++, seg++) {
+		if (seg->addr == NULL)
+			break;
+
+		if (seg->addr > last->addr)
+			last = seg;
+
+	}
+	return RTE_PTR_ADD(last->addr, last->len); }
+
 /* map a particular resource from a file */  void *  pci_map_resource(void *requested_addr, int fd, off_t offset, size_t size)  {
 	void *mapaddr;
 
+	/* By default the PCI memory resource will be mapped after hugepages */
+	static void *default_map_addr;
+	if (NULL == requested_addr) {
+		if (NULL == default_map_addr)
+			default_map_addr = pci_find_max_end_va();
+		mapaddr = default_map_addr;
+	} else {
+	    mapaddr = requested_addr;
+	}
+
 	/* Map the PCI memory resource of device */
-	mapaddr = mmap(requested_addr, size, PROT_READ | PROT_WRITE,
+	mapaddr = mmap(mapaddr, size, PROT_READ | PROT_WRITE,
 			MAP_SHARED, fd, offset);
 	if (mapaddr == MAP_FAILED ||
 			(requested_addr != NULL && mapaddr != requested_addr)) { @@ -114,6 +142,8 @@ pci_map_resource(void *requested_addr, int fd, off_t offset, size_t size)
 			strerror(errno), mapaddr);
 		goto fail;
 	}
+	if (NULL == requested_addr)
+		default_map_addr = RTE_PTR_ADD(mapaddr, size);
 
 	RTE_LOG(DEBUG, EAL, "  PCI memory mapped at %p\n", mapaddr);
 
--
1.9.1
From thomas.monjalon@6wind.com  Mon Nov 10 10:54:11 2014
Return-Path: <thomas.monjalon@6wind.com>
Received: from mail-wi0-f172.google.com (mail-wi0-f172.google.com
 [209.85.212.172]) by dpdk.org (Postfix) with ESMTP id C38582E89
 for <dev@dpdk.org>; Mon, 10 Nov 2014 10:54:11 +0100 (CET)
Received: by mail-wi0-f172.google.com with SMTP id bs8so9734150wib.11
 for <dev@dpdk.org>; Mon, 10 Nov 2014 02:03:56 -0800 (PST)
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
 d\x1e100.net; s 130820;
 h=x-gm-message-state:from:to:cc:subject:date:message-id:organization
 :user-agent:in-reply-to:references:mime-version
 :content-transfer-encoding:content-type;
 bh=boS8myAu9T2LhsGLlflh1gTZs6fn3na8zppnVl5Nkt0=;
 b=IaJOJUS/JrF4U3PkAUw2VydRtST+peS3IpSMmXPLNsuEZYzxeO43UJso5BOmcI/mMq
 QzHhckAcg6gVVNbR3zSknV5t95rBtKFzqMOBSZkBNp5zx6lraLSV7cOWsxz69QSTn5aa
 IJScbNMrzQ4oFhnBddxnewYwgjrbYfZCKkMlb1aXAmD0oowSG9fNpwqPNsiBjfKCdIni
 r1qNErpwflVOVCJD3Cd8Fg/ZEbkrnS0fgSp4bdJqzIDLIYxnlWX/iRhPQ28Er+mIWKUA
 WdoZgxmnG7FNDPwINoehsEZy2Jk0gj01APXuEO6fotBAxBcy9cgGjNBS0YFnOgefwHtX
 WKew=X-Gm-Message-State: ALoCoQlQQ/m8Xk75za5kGhi2XnYX3zSCMpPf7ucHc7ycV0rAJmgo0ezWQbkZpGOT69QBzeeh1O1E
X-Received: by 10.180.19.164 with SMTP id g4mr28712962wie.51.1415613836517;
 Mon, 10 Nov 2014 02:03:56 -0800 (PST)
Received: from xps13.localnet (136-92-190-109.dsl.ovh.fr. [109.190.92.136])
 by mx.google.com with ESMTPSA id hk9sm22516289wjb.46.2014.11.10.02.03.55
 for <multiple recipients>
 (version=TLSv1.2 cipherìDHE-RSA-AES128-GCM-SHA256 bits\x128/128);
 Mon, 10 Nov 2014 02:03:55 -0800 (PST)
From: Thomas Monjalon <thomas.monjalon@6wind.com>
To: "Sujith Sankar (ssujith)" <ssujith@cisco.com>
Date: Mon, 10 Nov 2014 11:03:37 +0100
Message-ID: <2661634.q9QAmChB5I@xps13>
Organization: 6WIND
User-Agent: KMail/4.14.2 (Linux/3.17.2-1-ARCH; KDE/4.14.2; x86_64; ; )
In-Reply-To: <D08682B4.27321%ssujith@cisco.com>
References: <1415390747-9532-1-git-send-email-ssujith@cisco.com>
 <1794590.eegJuKmrRB@xps13> <D08682B4.27321%ssujith@cisco.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7Bit
Content-Type: text/plain; charset="us-ascii"
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH 0/7] Cisco Systems Inc. VIC Ethernet PMD -
	ENIC PMD
X-BeenThere: dev@dpdk.org
X-Mailman-Version: 2.1.15
Precedence: list
List-Id: patches and discussions about DPDK <dev.dpdk.org>
List-Unsubscribe: <http://dpdk.org/ml/options/dev>,
 <mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://dpdk.org/ml/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <http://dpdk.org/ml/listinfo/dev>,
 <mailto:dev-request@dpdk.org?subject=subscribe>
X-List-Received-Date: Mon, 10 Nov 2014 09:54:12 -0000

2014-11-10 09:27, Sujith Sankar:
> On 07/11/14 9:17 pm, "Thomas Monjalon" <thomas.monjalon@6wind.com> wrote:
> >It seems that this PMD is based on DPDK 1.7.
> >Could you rebase it on HEAD?
>
> This patch is based on 1.7.1.  Thought that is the latest.  And I got the
> diff from origin.
> What made you feel that the patch is from 1.7?

By saying 1.7, I meant 1.7.0 or 1.7.1.
In current HEAD (future 1.8.0), there is a lot of changes which make your PMD
incompatible. That's why the rule is to base the patches on the latest HEAD.

Thanks for your efforts.
--
Thomas