From 5ce97f4ec5e0f8726a5dda1710727b1ee9badcac Mon Sep 17 00:00:00 2001 From: Lennert Buytenhek Date: Mon, 4 Oct 2021 13:07:24 +0300 Subject: iommu/amd: Recover from event log overflow The AMD IOMMU logs I/O page faults and such to a ring buffer in system memory, and this ring buffer can overflow. The AMD IOMMU spec has the following to say about the interrupt status bit that signals this overflow condition: EventOverflow: Event log overflow. RW1C. Reset 0b. 1 = IOMMU event log overflow has occurred. This bit is set when a new event is to be written to the event log and there is no usable entry in the event log, causing the new event information to be discarded. An interrupt is generated when EventOverflow = 1b and MMIO Offset 0018h[EventIntEn] = 1b. No new event log entries are written while this bit is set. Software Note: To resume logging, clear EventOverflow (W1C), and write a 1 to MMIO Offset 0018h[EventLogEn]. The AMD IOMMU driver doesn't currently implement this recovery sequence, meaning that if a ring buffer overflow occurs, logging of EVT/PPR/GA events will cease entirely. This patch implements the spec-mandated reset sequence, with the minor tweak that the hardware seems to want to have a 0 written to MMIO Offset 0018h[EventLogEn] first, before writing an 1 into this field, or the IOMMU won't actually resume logging events. Signed-off-by: Lennert Buytenhek Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/YVrSXEdW2rzEfOvk@wantstofly.org Signed-off-by: Joerg Roedel --- drivers/iommu/amd/amd_iommu.h | 1 + drivers/iommu/amd/amd_iommu_types.h | 1 + drivers/iommu/amd/init.c | 10 ++++++++++ drivers/iommu/amd/iommu.c | 10 ++++++++-- 4 files changed, 20 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 416815a525d6..bb95edf74415 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -14,6 +14,7 @@ extern irqreturn_t amd_iommu_int_thread(int irq, void *data); extern irqreturn_t amd_iommu_int_handler(int irq, void *data); extern void amd_iommu_apply_erratum_63(u16 devid); +extern void amd_iommu_restart_event_logging(struct amd_iommu *iommu); extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu); extern int amd_iommu_init_devices(void); extern void amd_iommu_uninit_devices(void); diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index ffc89c4fb120..47108ed44fbb 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -110,6 +110,7 @@ #define PASID_MASK 0x0000ffff /* MMIO status bits */ +#define MMIO_STATUS_EVT_OVERFLOW_INT_MASK (1 << 0) #define MMIO_STATUS_EVT_INT_MASK (1 << 1) #define MMIO_STATUS_COM_WAIT_INT_MASK (1 << 2) #define MMIO_STATUS_PPR_INT_MASK (1 << 6) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index b10fb52ea442..7bfe37e52e21 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -657,6 +657,16 @@ static int __init alloc_command_buffer(struct amd_iommu *iommu) return iommu->cmd_buf ? 0 : -ENOMEM; } +/* + * This function restarts event logging in case the IOMMU experienced + * an event log buffer overflow. + */ +void amd_iommu_restart_event_logging(struct amd_iommu *iommu) +{ + iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN); + iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN); +} + /* * This function resets the command buffer if the IOMMU stopped fetching * commands from it. diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 461f1844ed1f..a18b549951bb 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -764,7 +764,8 @@ amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu) { } #endif /* !CONFIG_IRQ_REMAP */ #define AMD_IOMMU_INT_MASK \ - (MMIO_STATUS_EVT_INT_MASK | \ + (MMIO_STATUS_EVT_OVERFLOW_INT_MASK | \ + MMIO_STATUS_EVT_INT_MASK | \ MMIO_STATUS_PPR_INT_MASK | \ MMIO_STATUS_GALOG_INT_MASK) @@ -774,7 +775,7 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data) u32 status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET); while (status & AMD_IOMMU_INT_MASK) { - /* Enable EVT and PPR and GA interrupts again */ + /* Enable interrupt sources again */ writel(AMD_IOMMU_INT_MASK, iommu->mmio_base + MMIO_STATUS_OFFSET); @@ -795,6 +796,11 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data) } #endif + if (status & MMIO_STATUS_EVT_OVERFLOW_INT_MASK) { + pr_info_ratelimited("IOMMU event log overflow\n"); + amd_iommu_restart_event_logging(iommu); + } + /* * Hardware bug: ERBT1312 * When re-enabling interrupt (by writing 1 -- cgit v1.2.3 From 6b0b2d9a6a308bcd9300c2d83000a82812c56cea Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 10 Feb 2022 09:47:45 -0600 Subject: iommu/amd: Fix I/O page table memory leak The current logic updates the I/O page table mode for the domain before calling the logic to free memory used for the page table. This results in IOMMU page table memory leak, and can be observed when launching VM w/ pass-through devices. Fix by freeing the memory used for page table before updating the mode. Cc: Joerg Roedel Reported-by: Daniel Jordan Tested-by: Daniel Jordan Signed-off-by: Suravee Suthikulpanit Fixes: e42ba0633064 ("iommu/amd: Restructure code for freeing page table") Link: https://lore.kernel.org/all/20220118194720.urjgi73b7c3tq2o6@oracle.com/ Link: https://lore.kernel.org/r/20220210154745.11524-1-suravee.suthikulpanit@amd.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/io_pgtable.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c index b1bf4125b0f7..6608d1717574 100644 --- a/drivers/iommu/amd/io_pgtable.c +++ b/drivers/iommu/amd/io_pgtable.c @@ -492,18 +492,18 @@ static void v1_free_pgtable(struct io_pgtable *iop) dom = container_of(pgtable, struct protection_domain, iop); - /* Update data structure */ - amd_iommu_domain_clr_pt_root(dom); - - /* Make changes visible to IOMMUs */ - amd_iommu_domain_update(dom); - /* Page-table is not visible to IOMMU anymore, so free it */ BUG_ON(pgtable->mode < PAGE_MODE_NONE || pgtable->mode > PAGE_MODE_6_LEVEL); free_sub_pt(pgtable->root, pgtable->mode, &freelist); + /* Update data structure */ + amd_iommu_domain_clr_pt_root(dom); + + /* Make changes visible to IOMMUs */ + amd_iommu_domain_update(dom); + put_pages_list(&freelist); } -- cgit v1.2.3 From b00833768e170a31af09268f7ab96aecfcca9623 Mon Sep 17 00:00:00 2001 From: Adrian Huang Date: Mon, 21 Feb 2022 13:33:48 +0800 Subject: iommu/vt-d: Fix double list_add when enabling VMD in scalable mode When enabling VMD and IOMMU scalable mode, the following kernel panic call trace/kernel log is shown in Eagle Stream platform (Sapphire Rapids CPU) during booting: pci 0000:59:00.5: Adding to iommu group 42 ... vmd 0000:59:00.5: PCI host bridge to bus 10000:80 pci 10000:80:01.0: [8086:352a] type 01 class 0x060400 pci 10000:80:01.0: reg 0x10: [mem 0x00000000-0x0001ffff 64bit] pci 10000:80:01.0: enabling Extended Tags pci 10000:80:01.0: PME# supported from D0 D3hot D3cold pci 10000:80:01.0: DMAR: Setup RID2PASID failed pci 10000:80:01.0: Failed to add to iommu group 42: -16 pci 10000:80:03.0: [8086:352b] type 01 class 0x060400 pci 10000:80:03.0: reg 0x10: [mem 0x00000000-0x0001ffff 64bit] pci 10000:80:03.0: enabling Extended Tags pci 10000:80:03.0: PME# supported from D0 D3hot D3cold ------------[ cut here ]------------ kernel BUG at lib/list_debug.c:29! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 0 PID: 7 Comm: kworker/0:1 Not tainted 5.17.0-rc3+ #7 Hardware name: Lenovo ThinkSystem SR650V3/SB27A86647, BIOS ESE101Y-1.00 01/13/2022 Workqueue: events work_for_cpu_fn RIP: 0010:__list_add_valid.cold+0x26/0x3f Code: 9a 4a ab ff 4c 89 c1 48 c7 c7 40 0c d9 9e e8 b9 b1 fe ff 0f 0b 48 89 f2 4c 89 c1 48 89 fe 48 c7 c7 f0 0c d9 9e e8 a2 b1 fe ff <0f> 0b 48 89 d1 4c 89 c6 4c 89 ca 48 c7 c7 98 0c d9 9e e8 8b b1 fe RSP: 0000:ff5ad434865b3a40 EFLAGS: 00010246 RAX: 0000000000000058 RBX: ff4d61160b74b880 RCX: ff4d61255e1fffa8 RDX: 0000000000000000 RSI: 00000000fffeffff RDI: ffffffff9fd34f20 RBP: ff4d611d8e245c00 R08: 0000000000000000 R09: ff5ad434865b3888 R10: ff5ad434865b3880 R11: ff4d61257fdc6fe8 R12: ff4d61160b74b8a0 R13: ff4d61160b74b8a0 R14: ff4d611d8e245c10 R15: ff4d611d8001ba70 FS: 0000000000000000(0000) GS:ff4d611d5ea00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ff4d611fa1401000 CR3: 0000000aa0210001 CR4: 0000000000771ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: intel_pasid_alloc_table+0x9c/0x1d0 dmar_insert_one_dev_info+0x423/0x540 ? device_to_iommu+0x12d/0x2f0 intel_iommu_attach_device+0x116/0x290 __iommu_attach_device+0x1a/0x90 iommu_group_add_device+0x190/0x2c0 __iommu_probe_device+0x13e/0x250 iommu_probe_device+0x24/0x150 iommu_bus_notifier+0x69/0x90 blocking_notifier_call_chain+0x5a/0x80 device_add+0x3db/0x7b0 ? arch_memremap_can_ram_remap+0x19/0x50 ? memremap+0x75/0x140 pci_device_add+0x193/0x1d0 pci_scan_single_device+0xb9/0xf0 pci_scan_slot+0x4c/0x110 pci_scan_child_bus_extend+0x3a/0x290 vmd_enable_domain.constprop.0+0x63e/0x820 vmd_probe+0x163/0x190 local_pci_probe+0x42/0x80 work_for_cpu_fn+0x13/0x20 process_one_work+0x1e2/0x3b0 worker_thread+0x1c4/0x3a0 ? rescuer_thread+0x370/0x370 kthread+0xc7/0xf0 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30 Modules linked in: ---[ end trace 0000000000000000 ]--- ... Kernel panic - not syncing: Fatal exception Kernel Offset: 0x1ca00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception ]--- The following 'lspci' output shows devices '10000:80:*' are subdevices of the VMD device 0000:59:00.5: $ lspci ... 0000:59:00.5 RAID bus controller: Intel Corporation Volume Management Device NVMe RAID Controller (rev 20) ... 10000:80:01.0 PCI bridge: Intel Corporation Device 352a (rev 03) 10000:80:03.0 PCI bridge: Intel Corporation Device 352b (rev 03) 10000:80:05.0 PCI bridge: Intel Corporation Device 352c (rev 03) 10000:80:07.0 PCI bridge: Intel Corporation Device 352d (rev 03) 10000:81:00.0 Non-Volatile memory controller: Intel Corporation NVMe Datacenter SSD [3DNAND, Beta Rock Controller] 10000:82:00.0 Non-Volatile memory controller: Intel Corporation NVMe Datacenter SSD [3DNAND, Beta Rock Controller] The symptom 'list_add double add' is caused by the following failure message: pci 10000:80:01.0: DMAR: Setup RID2PASID failed pci 10000:80:01.0: Failed to add to iommu group 42: -16 pci 10000:80:03.0: [8086:352b] type 01 class 0x060400 Device 10000:80:01.0 is the subdevice of the VMD device 0000:59:00.5, so invoking intel_pasid_alloc_table() gets the pasid_table of the VMD device 0000:59:00.5. Here is call path: intel_pasid_alloc_table pci_for_each_dma_alias get_alias_pasid_table search_pasid_table pci_real_dma_dev() in pci_for_each_dma_alias() gets the real dma device which is the VMD device 0000:59:00.5. However, pte of the VMD device 0000:59:00.5 has been configured during this message "pci 0000:59:00.5: Adding to iommu group 42". So, the status -EBUSY is returned when configuring pasid entry for device 10000:80:01.0. It then invokes dmar_remove_one_dev_info() to release 'struct device_domain_info *' from iommu_devinfo_cache. But, the pasid table is not released because of the following statement in __dmar_remove_one_dev_info(): if (info->dev && !dev_is_real_dma_subdevice(info->dev)) { ... intel_pasid_free_table(info->dev); } The subsequent dmar_insert_one_dev_info() operation of device 10000:80:03.0 allocates 'struct device_domain_info *' from iommu_devinfo_cache. The allocated address is the same address that is released previously for device 10000:80:01.0. Finally, invoking device_attach_pasid_table() causes the issue. `git bisect` points to the offending commit 474dd1c65064 ("iommu/vt-d: Fix clearing real DMA device's scalable-mode context entries"), which releases the pasid table if the device is not the subdevice by checking the returned status of dev_is_real_dma_subdevice(). Reverting the offending commit can work around the issue. The solution is to prevent from allocating pasid table if those devices are subdevices of the VMD device. Fixes: 474dd1c65064 ("iommu/vt-d: Fix clearing real DMA device's scalable-mode context entries") Cc: stable@vger.kernel.org # v5.14+ Signed-off-by: Adrian Huang Link: https://lore.kernel.org/r/20220216091307.703-1-adrianhuang0701@gmail.com Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20220221053348.262724-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 92fea3fbbb11..5b196cfe9ed2 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2738,7 +2738,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, spin_unlock_irqrestore(&device_domain_lock, flags); /* PASID table is mandatory for a PCI device in scalable mode. */ - if (dev && dev_is_pci(dev) && sm_supported(iommu)) { + if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) { ret = intel_pasid_alloc_table(dev); if (ret) { dev_err(dev, "PASID table allocation failed\n"); -- cgit v1.2.3 From 9826e393e4a8c3df474e7f9eacd3087266f74005 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Fri, 7 Jan 2022 08:09:11 +0000 Subject: iommu/tegra-smmu: Fix missing put_device() call in tegra_smmu_find The reference taken by 'of_find_device_by_node()' must be released when not needed anymore. Add the corresponding 'put_device()' in the error handling path. Fixes: 765a9d1d02b2 ("iommu/tegra-smmu: Fix mc errors on tegra124-nyan") Signed-off-by: Miaoqian Lin Acked-by: Thierry Reding Link: https://lore.kernel.org/r/20220107080915.12686-1-linmq006@gmail.com Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index e900e3c46903..2561ce8a2ce8 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -808,8 +808,10 @@ static struct tegra_smmu *tegra_smmu_find(struct device_node *np) return NULL; mc = platform_get_drvdata(pdev); - if (!mc) + if (!mc) { + put_device(&pdev->dev); return NULL; + } return mc->smmu; } -- cgit v1.2.3