From 05dd7da76986937fb288b4213b1fa10dbe0d1b33 Mon Sep 17 00:00:00 2001 From: Frederic Barrat Date: Thu, 21 Nov 2019 14:49:08 +0100 Subject: [PATCH] powerpc/powernv/ioda: Fix ref count for devices with their own PE The pci_dn structure used to store a pointer to the struct pci_dev, so taking a reference on the device was required. However, the pci_dev pointer was later removed from the pci_dn structure, but the reference was kept for the npu device. See commit 902bdc57451c ("powerpc/powernv/idoa: Remove unnecessary pcidev from pci_dn"). We don't need to take a reference on the device when assigning the PE as the struct pnv_ioda_pe is cleaned up at the same time as the (physical) device is released. Doing so prevents the device from being released, which is a problem for opencapi devices, since we want to be able to remove them through PCI hotplug. Now the ugly part: nvlink npu devices are not meant to be released. Because of the above, we've always leaked a reference and simply removing it now is dangerous and would likely require more work. There's currently no release device callback for nvlink devices for example. So to be safe, this patch leaks a reference on the npu device, but only for nvlink and not opencapi. Signed-off-by: Frederic Barrat Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20191121134918.7155-2-fbarrat@linux.ibm.com --- arch/powerpc/platforms/powernv/pci-ioda.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 62f17c0..82e81fe 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1062,14 +1062,13 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) return NULL; } - /* NOTE: We get only one ref to the pci_dev for the pdn, not for the - * pointer in the PE data structure, both should be destroyed at the - * same time. However, this needs to be looked at more closely again - * once we actually start removing things (Hotplug, SR-IOV, ...) + /* NOTE: We don't get a reference for the pointer in the PE + * data structure, both the device and PE structures should be + * destroyed at the same time. However, removing nvlink + * devices will need some work. * * At some point we want to remove the PDN completely anyways */ - pci_dev_get(dev); pdn->pe_number = pe->pe_number; pe->flags = PNV_IODA_PE_DEV; pe->pdev = dev; @@ -1084,7 +1083,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) pnv_ioda_free_pe(pe); pdn->pe_number = IODA_INVALID_PE; pe->pdev = NULL; - pci_dev_put(dev); return NULL; } @@ -1206,6 +1204,14 @@ static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev) struct pnv_phb *phb = hose->private_data; /* + * Intentionally leak a reference on the npu device (for + * nvlink only; this is not an opencapi path) to make sure it + * never goes away, as it's been the case all along and some + * work is needed otherwise. + */ + pci_dev_get(npu_pdev); + + /* * Due to a hardware errata PE#0 on the NPU is reserved for * error handling. This means we only have three PEs remaining * which need to be assigned to four links, implying some @@ -1228,7 +1234,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev) */ dev_info(&npu_pdev->dev, "Associating to existing PE %x\n", pe_num); - pci_dev_get(npu_pdev); npu_pdn = pci_get_pdn(npu_pdev); rid = npu_pdev->bus->number << 8 | npu_pdn->devfn; npu_pdn->pe_number = pe_num; -- 2.7.4