linux-kernel - Re: [BISECTED] Regression: Solidrun Clearfog Base won't boot since "PCI: mvebu: Only remap I/O space if configured"

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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <20180924151040.5e57462b@windsurf>
Date:   Mon, 24 Sep 2018 15:10:40 +0200
From:   Thomas Petazzoni <thomas.petazzoni@...tlin.com>
To:     Lorenzo Pieralisi <lorenzo.pieralisi@....com>
Cc:     Russell King - ARM Linux <linux@...linux.org.uk>,
        Jan Kundr??t <jan.kundrat@...net.cz>,
        Baruch Siach <baruch@...s.co.il>,
        Jason Cooper <jason@...edaemon.net>, linux-pci@...r.kernel.org,
        linux-kernel@...r.kernel.org, Bjorn Helgaas <bhelgaas@...gle.com>,
        linux-arm-kernel@...ts.infradead.org
Subject: Re: [BISECTED] Regression: Solidrun Clearfog Base won't boot since
 "PCI: mvebu: Only remap I/O space if configured"

Hello,

On Mon, 24 Sep 2018 13:46:29 +0100, Lorenzo Pieralisi wrote:

> What I think you can do short term, given that AFAICS MVEBU is not
> removable, instead of using pci_host_probe() you move part of its code
> into the driver and make sure that you remap IO as last operation before
> probe completion (ie after scanning the host bridge) so that you do not
> need to unmap it on failure; write a commit log summarising/linking this
> thread please and when v4.20 lands we will give this a more thorough
> look as Russell requested.
> 
> How does that sound ?

The only thing that can fail in pci_host_probe() is:

	ret = pci_scan_root_bus_bridge(bridge);
	if (ret < 0) {
		dev_err(bridge->dev.parent, "Scanning root bridge
	failed"); return ret;
	}

In the pci-mvebu driver prior to the conversion to pci_host_probe(),
the code flow at the end of ->probe() was:

  mvebu_pcie_enable()
    pci_common_init_dev()
      pcibios_init_hw()

and pcibios_init_hw() calls pci_scan_root_bus_bridge(), without doing
much about the return value other than issuing a warning:

                                ret = pci_scan_root_bus_bridge(bridge);
                        }

                        if (WARN(ret < 0, "PCI: unable to scan bus!")) {
                                pci_free_host_bridge(bridge);
                                break;
                        }

I.e, even before the conversion to pci_host_probe(), in case of
failure in pci_scan_root_bus_bridge(), we would have the I/O mapping in
place, but the PCI controller not registered.

We could keep the same (not great) behavior by doing:

diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index 50eb0729385b..487492f0c5f7 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -1179,9 +1179,6 @@ static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie)
                                         resource_size(&pcie->io) - 1);
                pcie->realio.name = "PCI I/O";
 
-               for (i = 0; i < resource_size(&pcie->realio); i += SZ_64K)
-                       pci_ioremap_io(i, pcie->io.start + i);
-
                pci_add_resource(&pcie->resources, &pcie->realio);
        }
 
@@ -1197,7 +1194,7 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
        struct device_node *child;
        int num, i, ret;
 
-       bridge = devm_pci_alloc_host_bridge(dev, sizeof(struct mvebu_pcie));
+       bridge = pci_alloc_host_bridge(sizeof(struct mvebu_pcie));
        if (!bridge)
                return -ENOMEM;
 
@@ -1212,8 +1209,10 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
        num = of_get_available_child_count(np);
 
        pcie->ports = devm_kcalloc(dev, num, sizeof(*pcie->ports), GFP_KERNEL);
-       if (!pcie->ports)
-               return -ENOMEM;
+       if (!pcie->ports) {
+               ret = -ENOMEM;
+               goto free_host_bridge;
+       }
 
        i = 0;
        for_each_available_child_of_node(np, child) {
@@ -1222,7 +1221,7 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
                ret = mvebu_pcie_parse_port(pcie, port, child);
                if (ret < 0) {
                        of_node_put(child);
-                       return ret;
+                       goto free_host_bridge;
                } else if (ret == 0) {
                        continue;
                }
@@ -1268,7 +1267,21 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
        bridge->align_resource = mvebu_pcie_align_resource;
        bridge->msi = pcie->msi;
 
-       return pci_host_probe(bridge);
+       if (resource_size(&pcie->io) != 0) {
+               for (i = 0; i < resource_size(&pcie->realio); i += SZ_64K)
+                       pci_ioremap_io(i, pcie->io.start + i);
+       }
+
+       ret = pci_host_probe(bridge);
+       if (ret)
+               pci_free_host_bridge(bridge);
+
+       /* Yes, when pci_host_probe() returns a failure, we don't care */
+       return 0;
+
+free_host_bridge:
+       pci_free_host_bridge(bridge);
+       return ret;
 }
 
 static const struct of_device_id mvebu_pcie_of_match_table[] = {

I.e, we simply ignore the failure of pci_host_probe().

To be honest, I really prefer the option of introducing pci_unmap_io().

Best regards,

Thomas
-- 
Thomas Petazzoni, CTO, Bootlin
Embedded Linux and Kernel engineering
https://bootlin.com