From: Ankit Agrawal The GHES code allows calling of memory_failure() on the PFNs that pass the pfn_valid() check. This contract is broken for the remapped PFNs which fails the check and ghes_do_memory_failure() returns without triggering memory_failure(). Update code to allow memory_failure() call on PFNs failing pfn_valid(). Reviewed-by: Shuai Xue Signed-off-by: Ankit Agrawal --- drivers/acpi/apei/ghes.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index a0d54993edb3..bc4d0f2b3e9d 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -505,12 +505,6 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags) return false; pfn = PHYS_PFN(physical_addr); - if (!pfn_valid(pfn) && !arch_is_platform_page(physical_addr)) { - pr_warn_ratelimited(FW_WARN GHES_PFX - "Invalid address in generic error data: %#llx\n", - physical_addr); - return false; - } if (flags == MF_ACTION_REQUIRED && current->mm) { twcb = (void *)gen_pool_alloc(ghes_estatus_pool, sizeof(*twcb)); -- 2.34.1 From: Ankit Agrawal Poison (or ECC) errors can be very common on a large size cluster. The kernel MM currently does not handle ECC errors / poison on a memory region that is not backed by struct pages. If a memory region mapped using remap_pfn_range() for example, but not added to the kernel, MM will not have associated struct pages. Add a new mechanism to handle memory failure on such memory. Make kernel MM expose a function to allow modules managing the device memory to register the device memory SPA and the address space associated it. MM maintains this information as an interval tree. On poison, MM can search for the range that the poisoned PFN belong and use the address_space to determine the mapping VMA. In this implementation, kernel MM follows the following sequence that is largely similar to the memory_failure() handler for struct page backed memory: 1. memory_failure() is triggered on reception of a poison error. An absence of struct page is detected and consequently memory_failure_pfn() is executed. 2. memory_failure_pfn() collects the processes mapped to the PFN. 3. memory_failure_pfn() sends SIGBUS to all the processes mapping the faulty PFN using kill_procs(). Note that there is one primary difference versus the handling of the poison on struct pages, which is to skip unmapping to the faulty PFN. This is done to handle the huge PFNMAP support added recently [1] that enables VM_PFNMAP vmas to map at PMD or PUD level. A poison to a PFN mapped in such as way would need breaking the PMD/PUD mapping into PTEs that will get mirrored into the S2. This can greatly increase the cost of table walks and have a major performance impact. Link: https://lore.kernel.org/all/20240826204353.2228736-1-peterx@redhat.com/ [1] Signed-off-by: Ankit Agrawal --- MAINTAINERS | 1 + include/linux/memory-failure.h | 17 ++++ include/linux/mm.h | 1 + include/ras/ras_event.h | 1 + mm/Kconfig | 1 + mm/memory-failure.c | 145 ++++++++++++++++++++++++++++++++- 6 files changed, 165 insertions(+), 1 deletion(-) create mode 100644 include/linux/memory-failure.h diff --git a/MAINTAINERS b/MAINTAINERS index 520fb4e379a3..463d062d0386 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11359,6 +11359,7 @@ M: Miaohe Lin R: Naoya Horiguchi L: linux-mm@kvack.org S: Maintained +F: include/linux/memory-failure.h F: mm/hwpoison-inject.c F: mm/memory-failure.c diff --git a/include/linux/memory-failure.h b/include/linux/memory-failure.h new file mode 100644 index 000000000000..bc326503d2d2 --- /dev/null +++ b/include/linux/memory-failure.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_MEMORY_FAILURE_H +#define _LINUX_MEMORY_FAILURE_H + +#include + +struct pfn_address_space; + +struct pfn_address_space { + struct interval_tree_node node; + struct address_space *mapping; +}; + +int register_pfn_address_space(struct pfn_address_space *pfn_space); +void unregister_pfn_address_space(struct pfn_address_space *pfn_space); + +#endif /* _LINUX_MEMORY_FAILURE_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 1ae97a0b8ec7..0ab4ea82ce9e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4006,6 +4006,7 @@ enum mf_action_page_type { MF_MSG_DAX, MF_MSG_UNSPLIT_THP, MF_MSG_ALREADY_POISONED, + MF_MSG_PFN_MAP, MF_MSG_UNKNOWN, }; diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index c8cd0f00c845..fecfeb7c8be7 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -375,6 +375,7 @@ TRACE_EVENT(aer_event, EM ( MF_MSG_DAX, "dax page" ) \ EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" ) \ EM ( MF_MSG_ALREADY_POISONED, "already poisoned" ) \ + EM ( MF_MSG_PFN_MAP, "non struct page pfn" ) \ EMe ( MF_MSG_UNKNOWN, "unknown page" ) /* diff --git a/mm/Kconfig b/mm/Kconfig index e443fe8cd6cf..0b07219390b9 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -777,6 +777,7 @@ config MEMORY_FAILURE depends on ARCH_SUPPORTS_MEMORY_FAILURE bool "Enable recovery from hardware memory errors" select MEMORY_ISOLATION + select INTERVAL_TREE select RAS help Enables code to recover from some memory failures on systems diff --git a/mm/memory-failure.c b/mm/memory-failure.c index df6ee59527dd..03e4249a9f8f 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -38,6 +38,7 @@ #include #include +#include #include #include #include @@ -154,6 +155,10 @@ static const struct ctl_table memory_failure_table[] = { } }; +static struct rb_root_cached pfn_space_itree = RB_ROOT_CACHED; + +static DEFINE_MUTEX(pfn_space_lock); + /* * Return values: * 1: the page is dissolved (if needed) and taken off from buddy, @@ -957,6 +962,7 @@ static const char * const action_page_types[] = { [MF_MSG_DAX] = "dax page", [MF_MSG_UNSPLIT_THP] = "unsplit thp", [MF_MSG_ALREADY_POISONED] = "already poisoned page", + [MF_MSG_PFN_MAP] = "non struct page pfn", [MF_MSG_UNKNOWN] = "unknown page", }; @@ -1349,7 +1355,7 @@ static int action_result(unsigned long pfn, enum mf_action_page_type type, { trace_memory_failure_event(pfn, type, result); - if (type != MF_MSG_ALREADY_POISONED) { + if (type != MF_MSG_ALREADY_POISONED && type != MF_MSG_PFN_MAP) { num_poisoned_pages_inc(pfn); update_per_node_mf_stats(pfn, result); } @@ -2216,6 +2222,135 @@ static void kill_procs_now(struct page *p, unsigned long pfn, int flags, kill_procs(&tokill, true, pfn, flags); } +int register_pfn_address_space(struct pfn_address_space *pfn_space) +{ + guard(mutex)(&pfn_space_lock); + + if (interval_tree_iter_first(&pfn_space_itree, + pfn_space->node.start, + pfn_space->node.last)) + return -EBUSY; + + interval_tree_insert(&pfn_space->node, &pfn_space_itree); + + return 0; +} +EXPORT_SYMBOL_GPL(register_pfn_address_space); + +void unregister_pfn_address_space(struct pfn_address_space *pfn_space) +{ + guard(mutex)(&pfn_space_lock); + + if (interval_tree_iter_first(&pfn_space_itree, + pfn_space->node.start, + pfn_space->node.last)) + interval_tree_remove(&pfn_space->node, &pfn_space_itree); +} +EXPORT_SYMBOL_GPL(unregister_pfn_address_space); + +static void add_to_kill_pfn(struct task_struct *tsk, + struct vm_area_struct *vma, + struct list_head *to_kill, + unsigned long pfn) +{ + struct to_kill *tk; + + tk = kmalloc(sizeof(*tk), GFP_ATOMIC); + if (!tk) { + pr_info("Unable to kill proc %d\n", tsk->pid); + return; + } + + /* Check for pgoff not backed by struct page */ + tk->addr = vma_address(vma, pfn, 1); + tk->size_shift = PAGE_SHIFT; + + if (tk->addr == -EFAULT) + pr_info("Unable to find address %lx in %s\n", + pfn, tsk->comm); + + get_task_struct(tsk); + tk->tsk = tsk; + list_add_tail(&tk->nd, to_kill); +} + +/* + * Collect processes when the error hit a PFN not backed by struct page. + */ +static void collect_procs_pfn(struct address_space *mapping, + unsigned long pfn, struct list_head *to_kill) +{ + struct vm_area_struct *vma; + struct task_struct *tsk; + + i_mmap_lock_read(mapping); + rcu_read_lock(); + for_each_process(tsk) { + struct task_struct *t = tsk; + + t = task_early_kill(tsk, true); + if (!t) + continue; + vma_interval_tree_foreach(vma, &mapping->i_mmap, pfn, pfn) { + if (vma->vm_mm == t->mm) + add_to_kill_pfn(t, vma, to_kill, pfn); + } + } + rcu_read_unlock(); + i_mmap_unlock_read(mapping); +} + +/** + * memory_failure_pfn - Handle memory failure on a page not backed by + * struct page. + * @pfn: Page Number of the corrupted page + * @flags: fine tune action taken + * + * Return: + * 0 - success, + * -EBUSY - Page PFN does not belong to any address space mapping. + */ +static int memory_failure_pfn(unsigned long pfn, int flags) +{ + struct interval_tree_node *node; + LIST_HEAD(tokill); + + scoped_guard(mutex, &pfn_space_lock) { + bool mf_handled = false; + + /* + * Modules registers with MM the address space mapping to + * the device memory they manage. Iterate to identify + * exactly which address space has mapped to this failing + * PFN. + */ + for (node = interval_tree_iter_first(&pfn_space_itree, pfn, pfn); node; + node = interval_tree_iter_next(node, pfn, pfn)) { + struct pfn_address_space *pfn_space = + container_of(node, struct pfn_address_space, node); + + collect_procs_pfn(pfn_space->mapping, pfn, &tokill); + + mf_handled = true; + } + + if (!mf_handled) + return action_result(pfn, MF_MSG_PFN_MAP, MF_IGNORED); + } + + /* + * Unlike System-RAM there is no possibility to swap in a different + * physical page at a given virtual address, so all userspace + * consumption of direct PFN memory necessitates SIGBUS (i.e. + * MF_MUST_KILL) + */ + flags |= MF_ACTION_REQUIRED | MF_MUST_KILL; + + kill_procs(&tokill, true, pfn, flags); + + return action_result(pfn, MF_MSG_PFN_MAP, MF_RECOVERED); +} + /** * memory_failure - Handle memory failure of a page. * @pfn: Page Number of the corrupted page @@ -2265,6 +2400,14 @@ int memory_failure(unsigned long pfn, int flags) if (res == 0) goto unlock_mutex; + if (!pfn_valid(pfn) && !arch_is_platform_page(PFN_PHYS(pfn))) { + /* + * The PFN is not backed by struct page. + */ + res = memory_failure_pfn(pfn, flags); + goto unlock_mutex; + } + if (pfn_valid(pfn)) { pgmap = get_dev_pagemap(pfn, NULL); put_ref_page(pfn, flags); -- 2.34.1 From: Ankit Agrawal The nvgrace-gpu-vfio-pci module [1] maps the device memory to the user VA (Qemu) using remap_pfn_range() without adding the memory to the kernel. The device memory pages are not backed by struct page. The previous patch implements the mechanism to handle ECC/poison on memory page without struct page. This new mechanism is being used here. The module registers its memory region and the address_space with the kernel MM for ECC handling using the register_pfn_address_space() registration API exposed by the kernel. Link: https://lore.kernel.org/all/20240220115055.23546-1-ankita@nvidia.com/ [1] Signed-off-by: Ankit Agrawal --- drivers/vfio/pci/nvgrace-gpu/main.c | 45 ++++++++++++++++++++++++++++- 1 file changed, 44 insertions(+), 1 deletion(-) diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c index d95761dcdd58..80b3ed63c682 100644 --- a/drivers/vfio/pci/nvgrace-gpu/main.c +++ b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -8,6 +8,10 @@ #include #include +#ifdef CONFIG_MEMORY_FAILURE +#include +#endif + /* * The device memory usable to the workloads running in the VM is cached * and showcased as a 64b device BAR (comprising of BAR4 and BAR5 region) @@ -47,6 +51,9 @@ struct mem_region { void *memaddr; void __iomem *ioaddr; }; /* Base virtual address of the region */ +#ifdef CONFIG_MEMORY_FAILURE + struct pfn_address_space pfn_address_space; +#endif }; struct nvgrace_gpu_pci_core_device { @@ -60,6 +67,28 @@ struct nvgrace_gpu_pci_core_device { bool has_mig_hw_bug; }; +#ifdef CONFIG_MEMORY_FAILURE + +static int +nvgrace_gpu_vfio_pci_register_pfn_range(struct mem_region *region, + struct vm_area_struct *vma) +{ + unsigned long nr_pages; + int ret = 0; + + nr_pages = region->memlength >> PAGE_SHIFT; + + region->pfn_address_space.node.start = vma->vm_pgoff; + region->pfn_address_space.node.last = vma->vm_pgoff + nr_pages - 1; + region->pfn_address_space.mapping = vma->vm_file->f_mapping; + + ret = register_pfn_address_space(®ion->pfn_address_space); + + return ret; +} + +#endif + static void nvgrace_gpu_init_fake_bar_emu_regs(struct vfio_device *core_vdev) { struct nvgrace_gpu_pci_core_device *nvdev = @@ -127,6 +156,13 @@ static void nvgrace_gpu_close_device(struct vfio_device *core_vdev) mutex_destroy(&nvdev->remap_lock); +#ifdef CONFIG_MEMORY_FAILURE + if (nvdev->resmem.memlength) + unregister_pfn_address_space(&nvdev->resmem.pfn_address_space); + + unregister_pfn_address_space(&nvdev->usemem.pfn_address_space); +#endif + vfio_pci_core_close_device(core_vdev); } @@ -202,7 +238,14 @@ static int nvgrace_gpu_mmap(struct vfio_device *core_vdev, vma->vm_pgoff = start_pfn; - return 0; +#ifdef CONFIG_MEMORY_FAILURE + if (nvdev->resmem.memlength && index == VFIO_PCI_BAR2_REGION_INDEX) + ret = nvgrace_gpu_vfio_pci_register_pfn_range(&nvdev->resmem, vma); + else if (index == VFIO_PCI_BAR4_REGION_INDEX) + ret = nvgrace_gpu_vfio_pci_register_pfn_range(&nvdev->usemem, vma); +#endif + + return ret; } static long -- 2.34.1