From 78d7a8be2ae5dd98ce8249c220ae34159272978a Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Wed, 24 Feb 2021 12:04:33 -0800 Subject: mm/memory.c: fix potential pte_unmap_unlock pte error [ Upstream commit 90a3e375d324b2255b83e3dd29e99e2b05d82aaf ] Since commit 42e4089c7890 ("x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings"), when the first pfn modify is not allowed, we would break the loop with pte unchanged. Then the wrong pte - 1 would be passed to pte_unmap_unlock. Andi said: "While the fix is correct, I'm not sure if it actually is a real bug. Is there any architecture that would do something else than unlocking the underlying page? If it's just the underlying page then it should be always the same page, so no bug" Link: https://lkml.kernel.org/r/20210109080118.20885-1-linmiaohe@huawei.com Fixes: 42e4089c789 ("x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings") Signed-off-by: Hongxiang Lou Signed-off-by: Miaohe Lin Cc: Thomas Gleixner Cc: Dave Hansen Cc: Andi Kleen Cc: Josh Poimboeuf Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- mm/memory.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/memory.c b/mm/memory.c index fa752df6dc85..86ca97c24f1d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1686,11 +1686,11 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { - pte_t *pte; + pte_t *pte, *mapped_pte; spinlock_t *ptl; int err = 0; - pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); + mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; arch_enter_lazy_mmu_mode(); @@ -1704,7 +1704,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); - pte_unmap_unlock(pte - 1, ptl); + pte_unmap_unlock(mapped_pte, ptl); return err; } -- cgit v1.2.3 From 6fd892537ab459787d217b35855b974dc2fc0bbe Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Wed, 24 Feb 2021 12:06:50 -0800 Subject: mm/hugetlb: fix potential double free in hugetlb_register_node() error path [ Upstream commit cc2205a67dec5a700227a693fc113441e73e4641 ] In hugetlb_sysfs_add_hstate(), we would do kobject_put() on hstate_kobjs when failed to create sysfs group but forget to set hstate_kobjs to NULL. Then in hugetlb_register_node() error path, we may free it again via hugetlb_unregister_node(). Link: https://lkml.kernel.org/r/20210107123249.36964-1-linmiaohe@huawei.com Fixes: a3437870160c ("hugetlb: new sysfs interface") Signed-off-by: Miaohe Lin Reviewed-by: Mike Kravetz Reviewed-by: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- mm/hugetlb.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index dc877712ef1f..7c3ecac8aeb3 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2485,8 +2485,10 @@ static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, return -ENOMEM; retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group); - if (retval) + if (retval) { kobject_put(hstate_kobjs[hi]); + hstate_kobjs[hi] = NULL; + } return retval; } -- cgit v1.2.3 From ea279e9f078eb581d7f5344c93aeb7076a19fe11 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 4 Feb 2021 18:32:06 -0800 Subject: mm: hugetlb: fix a race between freeing and dissolving the page commit 7ffddd499ba6122b1a07828f023d1d67629aa017 upstream There is a race condition between __free_huge_page() and dissolve_free_huge_page(). CPU0: CPU1: // page_count(page) == 1 put_page(page) __free_huge_page(page) dissolve_free_huge_page(page) spin_lock(&hugetlb_lock) // PageHuge(page) && !page_count(page) update_and_free_page(page) // page is freed to the buddy spin_unlock(&hugetlb_lock) spin_lock(&hugetlb_lock) clear_page_huge_active(page) enqueue_huge_page(page) // It is wrong, the page is already freed spin_unlock(&hugetlb_lock) The race window is between put_page() and dissolve_free_huge_page(). We should make sure that the page is already on the free list when it is dissolved. As a result __free_huge_page would corrupt page(s) already in the buddy allocator. Link: https://lkml.kernel.org/r/20210115124942.46403-4-songmuchun@bytedance.com Fixes: c8721bbbdd36 ("mm: memory-hotplug: enable memory hotplug to handle hugepage") Signed-off-by: Muchun Song Reviewed-by: Mike Kravetz Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Cc: David Hildenbrand Cc: Yang Shi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds [sudip: adjust context] Signed-off-by: Sudip Mukherjee Signed-off-by: Greg Kroah-Hartman --- mm/hugetlb.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'mm') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 7c3ecac8aeb3..13a4f3fe2d91 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -66,6 +66,21 @@ DEFINE_SPINLOCK(hugetlb_lock); static int num_fault_mutexes; struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp; +static inline bool PageHugeFreed(struct page *head) +{ + return page_private(head + 4) == -1UL; +} + +static inline void SetPageHugeFreed(struct page *head) +{ + set_page_private(head + 4, -1UL); +} + +static inline void ClearPageHugeFreed(struct page *head) +{ + set_page_private(head + 4, 0); +} + /* Forward declaration */ static int hugetlb_acct_memory(struct hstate *h, long delta); @@ -841,6 +856,7 @@ static void enqueue_huge_page(struct hstate *h, struct page *page) list_move(&page->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; + SetPageHugeFreed(page); } static struct page *dequeue_huge_page_node(struct hstate *h, int nid) @@ -858,6 +874,7 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid) return NULL; list_move(&page->lru, &h->hugepage_activelist); set_page_refcounted(page); + ClearPageHugeFreed(page); h->free_huge_pages--; h->free_huge_pages_node[nid]--; return page; @@ -1266,6 +1283,7 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) set_hugetlb_cgroup(page, NULL); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; + ClearPageHugeFreed(page); spin_unlock(&hugetlb_lock); put_page(page); /* free it into the hugepage allocator */ } @@ -1424,11 +1442,32 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, */ static void dissolve_free_huge_page(struct page *page) { +retry: spin_lock(&hugetlb_lock); if (PageHuge(page) && !page_count(page)) { struct page *head = compound_head(page); struct hstate *h = page_hstate(head); int nid = page_to_nid(head); + + /* + * We should make sure that the page is already on the free list + * when it is dissolved. + */ + if (unlikely(!PageHugeFreed(head))) { + spin_unlock(&hugetlb_lock); + cond_resched(); + + /* + * Theoretically, we should return -EBUSY when we + * encounter this race. In fact, we have a chance + * to successfully dissolve the page if we do a + * retry. Because the race window is quite small. + * If we seize this opportunity, it is an optimization + * for increasing the success rate of dissolving page. + */ + goto retry; + } + list_del(&head->lru); h->free_huge_pages--; h->free_huge_pages_node[nid]--; -- cgit v1.2.3