From c0f5eeed0f4cef4f05b74883a7160e7edde58b6a Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 24 Feb 2014 09:39:27 +0100 Subject: i7core_edac: Fix PCI device reference count The reference count changes done by pci_get_device can be a little misleading when the usage diverges from the most common scheme. The reference count of the device passed as the last parameter is always decreased, even if the function returns no new device. So if we are going to try alternative device IDs, we must manually increment the device reference count before each retry. If we don't, we end up decreasing the reference count, and after a few modprobe/rmmod cycles the PCI devices will vanish. In other words and as Alan put it: without this fix the EDAC code corrupts the PCI device list. This fixes kernel bug #50491: https://bugzilla.kernel.org/show_bug.cgi?id=50491 Signed-off-by: Jean Delvare Link: http://lkml.kernel.org/r/20140224093927.7659dd9d@endymion.delvare Reviewed-by: Alan Cox Cc: Mauro Carvalho Chehab Cc: Doug Thompson Cc: stable@vger.kernel.org Signed-off-by: Borislav Petkov --- drivers/edac/i7core_edac.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 87533ca7752e..d871275196f6 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -1334,14 +1334,19 @@ static int i7core_get_onedevice(struct pci_dev **prev, * is at addr 8086:2c40, instead of 8086:2c41. So, we need * to probe for the alternate address in case of failure */ - if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev) + if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev) { + pci_dev_get(*prev); /* pci_get_device will put it */ pdev = pci_get_device(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_I7_NONCORE_ALT, *prev); + } - if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE && !pdev) + if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE && + !pdev) { + pci_dev_get(*prev); /* pci_get_device will put it */ pdev = pci_get_device(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE_ALT, *prev); + } if (!pdev) { if (*prev) { -- cgit v1.2.3-70-g09d2 From 75135da0d68419ef8a925f4c1d5f63d8046e314d Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 25 Feb 2014 09:43:13 +0100 Subject: i7300_edac: Fix device reference count pci_get_device() decrements the reference count of "from" (last argument) so when we break off the loop successfully we have only one device reference - and we don't know which device we have. If we want a reference to each device, we must take them explicitly and let the pci_get_device() walk complete to avoid duplicate references. This is serious, as over-putting device references will cause the device to eventually disappear. Without this fix, the kernel crashes after a few insmod/rmmod cycles. Tested on an Intel S7000FC4UR system with a 7300 chipset. Signed-off-by: Jean Delvare Link: http://lkml.kernel.org/r/20140224111656.09bbb7ed@endymion.delvare Cc: Mauro Carvalho Chehab Cc: Doug Thompson Cc: stable@vger.kernel.org Signed-off-by: Borislav Petkov --- drivers/edac/i7300_edac.c | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c index d63f4798f7d0..57e96a3350f0 100644 --- a/drivers/edac/i7300_edac.c +++ b/drivers/edac/i7300_edac.c @@ -943,33 +943,35 @@ static int i7300_get_devices(struct mem_ctl_info *mci) /* Attempt to 'get' the MCH register we want */ pdev = NULL; - while (!pvt->pci_dev_16_1_fsb_addr_map || - !pvt->pci_dev_16_2_fsb_err_regs) { - pdev = pci_get_device(PCI_VENDOR_ID_INTEL, - PCI_DEVICE_ID_INTEL_I7300_MCH_ERR, pdev); - if (!pdev) { - /* End of list, leave */ - i7300_printk(KERN_ERR, - "'system address,Process Bus' " - "device not found:" - "vendor 0x%x device 0x%x ERR funcs " - "(broken BIOS?)\n", - PCI_VENDOR_ID_INTEL, - PCI_DEVICE_ID_INTEL_I7300_MCH_ERR); - goto error; - } - + while ((pdev = pci_get_device(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_I7300_MCH_ERR, + pdev))) { /* Store device 16 funcs 1 and 2 */ switch (PCI_FUNC(pdev->devfn)) { case 1: - pvt->pci_dev_16_1_fsb_addr_map = pdev; + if (!pvt->pci_dev_16_1_fsb_addr_map) + pvt->pci_dev_16_1_fsb_addr_map = + pci_dev_get(pdev); break; case 2: - pvt->pci_dev_16_2_fsb_err_regs = pdev; + if (!pvt->pci_dev_16_2_fsb_err_regs) + pvt->pci_dev_16_2_fsb_err_regs = + pci_dev_get(pdev); break; } } + if (!pvt->pci_dev_16_1_fsb_addr_map || + !pvt->pci_dev_16_2_fsb_err_regs) { + /* At least one device was not found */ + i7300_printk(KERN_ERR, + "'system address,Process Bus' device not found:" + "vendor 0x%x device 0x%x ERR funcs (broken BIOS?)\n", + PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_I7300_MCH_ERR); + goto error; + } + edac_dbg(1, "System Address, processor bus- PCI Bus ID: %s %x:%x\n", pci_name(pvt->pci_dev_16_0_fsb_ctlr), pvt->pci_dev_16_0_fsb_ctlr->vendor, -- cgit v1.2.3-70-g09d2