From e656c7a9e59607d1672d85ffa9a89031876ffe67 Mon Sep 17 00:00:00 2001 From: Prakash Sangappa Date: Tue, 23 Jan 2024 12:04:42 -0800 Subject: mm: hugetlb pages should not be reserved by shmat() if SHM_NORESERVE For shared memory of type SHM_HUGETLB, hugetlb pages are reserved in shmget() call. If SHM_NORESERVE flags is specified then the hugetlb pages are not reserved. However when the shared memory is attached with the shmat() call the hugetlb pages are getting reserved incorrectly for SHM_HUGETLB shared memory created with SHM_NORESERVE which is a bug. ------------------------------- Following test shows the issue. $cat shmhtb.c int main() { int shmflags = 0660 | IPC_CREAT | SHM_HUGETLB | SHM_NORESERVE; int shmid; shmid = shmget(SKEY, SHMSZ, shmflags); if (shmid < 0) { printf("shmat: shmget() failed, %d\n", errno); return 1; } printf("After shmget()\n"); system("cat /proc/meminfo | grep -i hugepages_"); shmat(shmid, NULL, 0); printf("\nAfter shmat()\n"); system("cat /proc/meminfo | grep -i hugepages_"); shmctl(shmid, IPC_RMID, NULL); return 0; } #sysctl -w vm.nr_hugepages=20 #./shmhtb After shmget() HugePages_Total: 20 HugePages_Free: 20 HugePages_Rsvd: 0 HugePages_Surp: 0 After shmat() HugePages_Total: 20 HugePages_Free: 20 HugePages_Rsvd: 5 <-- HugePages_Surp: 0 -------------------------------- Fix is to ensure that hugetlb pages are not reserved for SHM_HUGETLB shared memory in the shmat() call. Link: https://lkml.kernel.org/r/1706040282-12388-1-git-send-email-prakash.sangappa@oracle.com Signed-off-by: Prakash Sangappa Acked-by: Muchun Song Cc: Signed-off-by: Andrew Morton --- fs/hugetlbfs/inode.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'fs/hugetlbfs') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 671664fed307..ee13c2ca8ad2 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -100,6 +100,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); + vm_flags_t vm_flags; /* * vma address alignment (but not the pgoff alignment) has @@ -141,10 +142,20 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) file_accessed(file); ret = -ENOMEM; + + vm_flags = vma->vm_flags; + /* + * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip + * reserving here. Note: only for SHM hugetlbfs file, the inode + * flag S_PRIVATE is set. + */ + if (inode->i_flags & S_PRIVATE) + vm_flags |= VM_NORESERVE; + if (!hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), len >> huge_page_shift(h), vma, - vma->vm_flags)) + vm_flags)) goto out; ret = 0; -- cgit v1.2.3