From 017ffe64e8b8c8db0f50433a71da41c6a4e12710 Mon Sep 17 00:00:00 2001 From: Yijing Wang Date: Fri, 17 Jul 2015 17:16:32 +0800 Subject: PCI: Hold pci_slot_mutex while searching bus->slots list Previously, pci_setup_device() and similar functions searched the pci_bus->slots list without any locking. It was possible for another thread to update the list while we searched it. Add pci_dev_assign_slot() to search the list while holding pci_slot_mutex. [bhelgaas: changelog, fold in CONFIG_SYSFS fix] Tested-by: Guenter Roeck Signed-off-by: Yijing Wang Signed-off-by: Bjorn Helgaas --- drivers/pci/probe.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'drivers/pci/probe.c') diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index cefd636681b6..2a9ce16cb374 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1133,7 +1133,6 @@ int pci_setup_device(struct pci_dev *dev) { u32 class; u8 hdr_type; - struct pci_slot *slot; int pos = 0; struct pci_bus_region region; struct resource *res; @@ -1149,10 +1148,7 @@ int pci_setup_device(struct pci_dev *dev) dev->error_state = pci_channel_io_normal; set_pcie_port_type(dev); - list_for_each_entry(slot, &dev->bus->slots, list) - if (PCI_SLOT(dev->devfn) == slot->number) - dev->slot = slot; - + pci_dev_assign_slot(dev); /* Assume 32-bit PCI; let 64-bit PCI cards (which are far rarer) set this higher, assuming the system even supports it. */ dev->dma_mask = 0xffffffff; -- cgit v1.2.3-59-g8ed1b From edc90fee916b4f0d14af9c6b5c08666747488ef8 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 17 Jul 2015 15:05:46 -0500 Subject: PCI: Allocate ATS struct during enumeration Previously, we allocated pci_ats structures when an IOMMU driver called pci_enable_ats(). An SR-IOV VF shares the STU setting with its PF, so when enabling ATS on the VF, we allocated a pci_ats struct for the PF if it didn't already have one. We held the sriov->lock to serialize threads concurrently enabling ATS on several VFS so only one would allocate the PF pci_ats. Gregor reported a deadlock here: pci_enable_sriov sriov_enable virtfn_add mutex_lock(dev->sriov->lock) # acquire sriov->lock pci_device_add device_add BUS_NOTIFY_ADD_DEVICE notifier chain iommu_bus_notifier amd_iommu_add_device # iommu_ops.add_device init_iommu_group iommu_group_get_for_dev iommu_group_add_device __iommu_attach_device amd_iommu_attach_device # iommu_ops.attach_device attach_device pci_enable_ats mutex_lock(dev->sriov->lock) # deadlock There's no reason to delay allocating the pci_ats struct, and if we allocate it for each device at enumeration-time, there's no need for locking in pci_enable_ats(). Allocate pci_ats struct during enumeration, when we initialize other capabilities. Note that this implementation requires ATS to be enabled on the PF first, before on any of the VFs because the PF controls the STU for all the VFs. Link: http://permalink.gmane.org/gmane.linux.kernel.iommu/9433 Reported-by: Gregor Dick Signed-off-by: Bjorn Helgaas Reviewed-by: Joerg Roedel --- drivers/pci/ats.c | 98 +++++++++++++++++++++---------------------------- drivers/pci/probe.c | 3 ++ drivers/pci/remove.c | 1 + include/linux/pci-ats.h | 2 +- include/linux/pci.h | 9 +++++ 5 files changed, 56 insertions(+), 57 deletions(-) (limited to 'drivers/pci/probe.c') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index a8099d4d0c9d..2026f5388796 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -17,7 +17,7 @@ #include "pci.h" -static int ats_alloc_one(struct pci_dev *dev, int ps) +static void ats_alloc_one(struct pci_dev *dev) { int pos; u16 cap; @@ -25,20 +25,19 @@ static int ats_alloc_one(struct pci_dev *dev, int ps) pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ATS); if (!pos) - return -ENODEV; + return; ats = kzalloc(sizeof(*ats), GFP_KERNEL); - if (!ats) - return -ENOMEM; + if (!ats) { + dev_warn(&dev->dev, "can't allocate space for ATS state\n"); + return; + } ats->pos = pos; - ats->stu = ps; pci_read_config_word(dev, pos + PCI_ATS_CAP, &cap); ats->qdep = PCI_ATS_CAP_QDEP(cap) ? PCI_ATS_CAP_QDEP(cap) : PCI_ATS_MAX_QDEP; dev->ats = ats; - - return 0; } static void ats_free_one(struct pci_dev *dev) @@ -47,6 +46,16 @@ static void ats_free_one(struct pci_dev *dev) dev->ats = NULL; } +void pci_ats_init(struct pci_dev *dev) +{ + ats_alloc_one(dev); +} + +void pci_ats_free(struct pci_dev *dev) +{ + ats_free_one(dev); +} + /** * pci_enable_ats - enable the ATS capability * @dev: the PCI device @@ -56,43 +65,35 @@ static void ats_free_one(struct pci_dev *dev) */ int pci_enable_ats(struct pci_dev *dev, int ps) { - int rc; u16 ctrl; BUG_ON(dev->ats && dev->ats->is_enabled); + if (!dev->ats) + return -EINVAL; + if (ps < PCI_ATS_MIN_STU) return -EINVAL; - if (dev->is_physfn || dev->is_virtfn) { - struct pci_dev *pdev = dev->is_physfn ? dev : dev->physfn; + /* + * Note that enabling ATS on a VF fails unless it's already enabled + * with the same STU on the PF. + */ + ctrl = PCI_ATS_CTRL_ENABLE; + if (dev->is_virtfn) { + struct pci_dev *pdev = dev->physfn; - mutex_lock(&pdev->sriov->lock); - if (pdev->ats) - rc = pdev->ats->stu == ps ? 0 : -EINVAL; - else - rc = ats_alloc_one(pdev, ps); + if (pdev->ats->stu != ps) + return -EINVAL; - if (!rc) - pdev->ats->ref_cnt++; - mutex_unlock(&pdev->sriov->lock); - if (rc) - return rc; - } - - if (!dev->is_physfn) { - rc = ats_alloc_one(dev, ps); - if (rc) - return rc; + atomic_inc(&pdev->ats->ref_cnt); /* count enabled VFs */ + } else { + dev->ats->stu = ps; + ctrl |= PCI_ATS_CTRL_STU(dev->ats->stu - PCI_ATS_MIN_STU); } - - ctrl = PCI_ATS_CTRL_ENABLE; - if (!dev->is_virtfn) - ctrl |= PCI_ATS_CTRL_STU(ps - PCI_ATS_MIN_STU); pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl); dev->ats->is_enabled = 1; - return 0; } EXPORT_SYMBOL_GPL(pci_enable_ats); @@ -107,24 +108,20 @@ void pci_disable_ats(struct pci_dev *dev) BUG_ON(!dev->ats || !dev->ats->is_enabled); + if (atomic_read(&dev->ats->ref_cnt)) + return; /* VFs still enabled */ + + if (dev->is_virtfn) { + struct pci_dev *pdev = dev->physfn; + + atomic_dec(&pdev->ats->ref_cnt); + } + pci_read_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, &ctrl); ctrl &= ~PCI_ATS_CTRL_ENABLE; pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl); dev->ats->is_enabled = 0; - - if (dev->is_physfn || dev->is_virtfn) { - struct pci_dev *pdev = dev->is_physfn ? dev : dev->physfn; - - mutex_lock(&pdev->sriov->lock); - pdev->ats->ref_cnt--; - if (!pdev->ats->ref_cnt) - ats_free_one(pdev); - mutex_unlock(&pdev->sriov->lock); - } - - if (!dev->is_physfn) - ats_free_one(dev); } EXPORT_SYMBOL_GPL(pci_disable_ats); @@ -140,7 +137,6 @@ void pci_restore_ats_state(struct pci_dev *dev) ctrl = PCI_ATS_CTRL_ENABLE; if (!dev->is_virtfn) ctrl |= PCI_ATS_CTRL_STU(dev->ats->stu - PCI_ATS_MIN_STU); - pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl); } EXPORT_SYMBOL_GPL(pci_restore_ats_state); @@ -159,23 +155,13 @@ EXPORT_SYMBOL_GPL(pci_restore_ats_state); */ int pci_ats_queue_depth(struct pci_dev *dev) { - int pos; - u16 cap; - if (dev->is_virtfn) return 0; if (dev->ats) return dev->ats->qdep; - pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ATS); - if (!pos) - return -ENODEV; - - pci_read_config_word(dev, pos + PCI_ATS_CAP, &cap); - - return PCI_ATS_CAP_QDEP(cap) ? PCI_ATS_CAP_QDEP(cap) : - PCI_ATS_MAX_QDEP; + return -ENODEV; } EXPORT_SYMBOL_GPL(pci_ats_queue_depth); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index cefd636681b6..c206398ca67e 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1540,6 +1540,9 @@ static void pci_init_capabilities(struct pci_dev *dev) /* Single Root I/O Virtualization */ pci_iov_init(dev); + /* Address Translation Services */ + pci_ats_init(dev); + /* Enable ACS P2P upstream forwarding */ pci_enable_acs(dev); } diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 8a280e9c2ad1..27617b862ca8 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -26,6 +26,7 @@ static void pci_stop_dev(struct pci_dev *dev) dev->is_added = 0; } + pci_ats_free(dev); if (dev->bus->self) pcie_aspm_exit_link_state(dev); } diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index 72031785fe1d..e2dcc2ff3d0e 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -8,7 +8,7 @@ struct pci_ats { int pos; /* capability position */ int stu; /* Smallest Translation Unit */ int qdep; /* Invalidate Queue Depth */ - int ref_cnt; /* Physical Function reference count */ + atomic_t ref_cnt; /* number of VFs with ATS enabled */ unsigned int is_enabled:1; /* Enable bit is set */ }; diff --git a/include/linux/pci.h b/include/linux/pci.h index 8a0321a8fb59..1817819ba57b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1294,6 +1294,15 @@ int ht_create_irq(struct pci_dev *dev, int idx); void ht_destroy_irq(unsigned int irq); #endif /* CONFIG_HT_IRQ */ +#ifdef CONFIG_PCI_ATS +/* Address Translation Service */ +void pci_ats_init(struct pci_dev *dev); +void pci_ats_free(struct pci_dev *dev); +#else +static inline void pci_ats_init(struct pci_dev *dev) { } +static inline void pci_ats_free(struct pci_dev *dev) { } +#endif + void pci_cfg_access_lock(struct pci_dev *dev); bool pci_cfg_access_trylock(struct pci_dev *dev); void pci_cfg_access_unlock(struct pci_dev *dev); -- cgit v1.2.3-59-g8ed1b