From: Ankit Agrawal The memory failure handling implementation for the PFNMAP memory with no struct pages is faulty. The VA of the mapping is determined based on the the PFN. It should instead be based on the file mapping offset. At the occurrence of poison, the memory_failure_pfn is triggered on the poisoned PFN. Introduce a callback function that allows mm to translate the PFN to the corresponding file page offset. The kernel module using the registration API must implement the callback function and provide the translation. The translated value is then used to determine the VA information and sending the SIGBUS to the usermode process mapped to the poisoned PFN. The callback is also useful for the driver to be notified of the poisoned PFN, which may then track it. Fixes: 2ec41967189c ("mm: handle poisoning of pfn without struct pages") Suggested-by: Jason Gunthorpe Signed-off-by: Ankit Agrawal --- include/linux/memory-failure.h | 2 ++ mm/memory-failure.c | 29 ++++++++++++++++++----------- 2 files changed, 20 insertions(+), 11 deletions(-) diff --git a/include/linux/memory-failure.h b/include/linux/memory-failure.h index bc326503d2d2..7b5e11cf905f 100644 --- a/include/linux/memory-failure.h +++ b/include/linux/memory-failure.h @@ -9,6 +9,8 @@ struct pfn_address_space; struct pfn_address_space { struct interval_tree_node node; struct address_space *mapping; + int (*pfn_to_vma_pgoff)(struct vm_area_struct *vma, + unsigned long pfn, pgoff_t *pgoff); }; int register_pfn_address_space(struct pfn_address_space *pfn_space); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index fbc5a01260c8..c80c2907da33 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2161,6 +2161,9 @@ int register_pfn_address_space(struct pfn_address_space *pfn_space) { guard(mutex)(&pfn_space_lock); + if (!pfn_space->pfn_to_vma_pgoff) + return -EINVAL; + if (interval_tree_iter_first(&pfn_space_itree, pfn_space->node.start, pfn_space->node.last)) @@ -2183,10 +2186,10 @@ void unregister_pfn_address_space(struct pfn_address_space *pfn_space) } 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) +static void add_to_kill_pgoff(struct task_struct *tsk, + struct vm_area_struct *vma, + struct list_head *to_kill, + pgoff_t pgoff) { struct to_kill *tk; @@ -2197,12 +2200,12 @@ static void add_to_kill_pfn(struct task_struct *tsk, } /* Check for pgoff not backed by struct page */ - tk->addr = vma_address(vma, pfn, 1); + tk->addr = vma_address(vma, pgoff, 1); tk->size_shift = PAGE_SHIFT; if (tk->addr == -EFAULT) pr_info("Unable to find address %lx in %s\n", - pfn, tsk->comm); + pgoff, tsk->comm); get_task_struct(tsk); tk->tsk = tsk; @@ -2212,11 +2215,12 @@ static void add_to_kill_pfn(struct task_struct *tsk, /* * Collect processes when the error hit a PFN not backed by struct page. */ -static void collect_procs_pfn(struct address_space *mapping, +static void collect_procs_pfn(struct pfn_address_space *pfn_space, unsigned long pfn, struct list_head *to_kill) { struct vm_area_struct *vma; struct task_struct *tsk; + struct address_space *mapping = pfn_space->mapping; i_mmap_lock_read(mapping); rcu_read_lock(); @@ -2226,9 +2230,12 @@ static void collect_procs_pfn(struct address_space *mapping, 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); + vma_interval_tree_foreach(vma, &mapping->i_mmap, 0, ULONG_MAX) { + pgoff_t pgoff; + + if (vma->vm_mm == t->mm && + !pfn_space->pfn_to_vma_pgoff(vma, pfn, &pgoff)) + add_to_kill_pgoff(t, vma, to_kill, pgoff); } } rcu_read_unlock(); @@ -2264,7 +2271,7 @@ static int memory_failure_pfn(unsigned long pfn, int flags) struct pfn_address_space *pfn_space = container_of(node, struct pfn_address_space, node); - collect_procs_pfn(pfn_space->mapping, pfn, &tokill); + collect_procs_pfn(pfn_space, pfn, &tokill); mf_handled = true; } -- 2.34.1