diff --git a/drivers/char/mem.c b/drivers/char/mem.c index d633974e7f8b1d82914743e0a27bda495e1ff5af..a33163dbb913541ad6649de8e9a43f8256e1742a 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -657,6 +658,28 @@ static int mmap_zero(struct file *file, struct vm_area_struct *vma) return 0; } +static unsigned long get_unmapped_area_zero(struct file *file, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ +#ifdef CONFIG_MMU + if (flags & MAP_SHARED) { + /* + * mmap_zero() will call shmem_zero_setup() to create a file, + * so use shmem's get_unmapped_area in case it can be huge; + * and pass NULL for file as in mmap.c's get_unmapped_area(), + * so as not to confuse shmem with our handle on "/dev/zero". + */ + return shmem_get_unmapped_area(NULL, addr, len, pgoff, flags); + } + + /* Otherwise flags & MAP_PRIVATE: with no shmem object beneath it */ + return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); +#else + return -ENOSYS; +#endif +} + static ssize_t write_full(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -764,6 +787,7 @@ static const struct file_operations zero_fops = { .read_iter = read_iter_zero, .write_iter = write_iter_zero, .mmap = mmap_zero, + .get_unmapped_area = get_unmapped_area_zero, #ifndef CONFIG_MMU .mmap_capabilities = zero_mmap_capabilities, #endif diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 466f18c73a495eb52ce8a18ad0b453578082dc64..ff2de4bab61f12823e2f8e69fbf1709013500390 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -50,6 +50,8 @@ extern struct file *shmem_file_setup(const char *name, extern struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); +extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); extern bool shmem_mapping(struct address_space *mapping); extern void shmem_unlock_mapping(struct address_space *mapping); diff --git a/ipc/shm.c b/ipc/shm.c index 13282510bc0da71aa9789ff72ba015bede5c96e7..7fa5cbebbf19f75fd33caadd12327b60c6276ae9 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -476,13 +476,15 @@ static const struct file_operations shm_file_operations = { .mmap = shm_mmap, .fsync = shm_fsync, .release = shm_release, -#ifndef CONFIG_MMU .get_unmapped_area = shm_get_unmapped_area, -#endif .llseek = noop_llseek, .fallocate = shm_fallocate, }; +/* + * shm_file_operations_huge is now identical to shm_file_operations, + * but we keep it distinct for the sake of is_file_shm_hugepages(). + */ static const struct file_operations shm_file_operations_huge = { .mmap = shm_mmap, .fsync = shm_fsync, diff --git a/mm/mmap.c b/mm/mmap.c index a41872c8f2af09994e6728cc7d282984e7851bea..86b18f334f4f759d8342a5220f8ac850c770ab03 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -1897,8 +1898,19 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, return -ENOMEM; get_area = current->mm->get_unmapped_area; - if (file && file->f_op->get_unmapped_area) - get_area = file->f_op->get_unmapped_area; + if (file) { + if (file->f_op->get_unmapped_area) + get_area = file->f_op->get_unmapped_area; + } else if (flags & MAP_SHARED) { + /* + * mmap_region() will call shmem_zero_setup() to create a file, + * so use shmem's get_unmapped_area in case it can be huge. + * do_mmap_pgoff() will clear pgoff, so match alignment. + */ + pgoff = 0; + get_area = shmem_get_unmapped_area; + } + addr = get_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) return addr; diff --git a/mm/shmem.c b/mm/shmem.c index fd374f74d99fa82adf948ba282525be8fac97ab9..ab02b5bb5553694464449395ff6bf436c0c1040b 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1513,6 +1513,94 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return ret; } +unsigned long shmem_get_unmapped_area(struct file *file, + unsigned long uaddr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + unsigned long (*get_area)(struct file *, + unsigned long, unsigned long, unsigned long, unsigned long); + unsigned long addr; + unsigned long offset; + unsigned long inflated_len; + unsigned long inflated_addr; + unsigned long inflated_offset; + + if (len > TASK_SIZE) + return -ENOMEM; + + get_area = current->mm->get_unmapped_area; + addr = get_area(file, uaddr, len, pgoff, flags); + + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return addr; + if (IS_ERR_VALUE(addr)) + return addr; + if (addr & ~PAGE_MASK) + return addr; + if (addr > TASK_SIZE - len) + return addr; + + if (shmem_huge == SHMEM_HUGE_DENY) + return addr; + if (len < HPAGE_PMD_SIZE) + return addr; + if (flags & MAP_FIXED) + return addr; + /* + * Our priority is to support MAP_SHARED mapped hugely; + * and support MAP_PRIVATE mapped hugely too, until it is COWed. + * But if caller specified an address hint, respect that as before. + */ + if (uaddr) + return addr; + + if (shmem_huge != SHMEM_HUGE_FORCE) { + struct super_block *sb; + + if (file) { + VM_BUG_ON(file->f_op != &shmem_file_operations); + sb = file_inode(file)->i_sb; + } else { + /* + * Called directly from mm/mmap.c, or drivers/char/mem.c + * for "/dev/zero", to create a shared anonymous object. + */ + if (IS_ERR(shm_mnt)) + return addr; + sb = shm_mnt->mnt_sb; + } + if (SHMEM_SB(sb)->huge != SHMEM_HUGE_NEVER) + return addr; + } + + offset = (pgoff << PAGE_SHIFT) & (HPAGE_PMD_SIZE-1); + if (offset && offset + len < 2 * HPAGE_PMD_SIZE) + return addr; + if ((addr & (HPAGE_PMD_SIZE-1)) == offset) + return addr; + + inflated_len = len + HPAGE_PMD_SIZE - PAGE_SIZE; + if (inflated_len > TASK_SIZE) + return addr; + if (inflated_len < len) + return addr; + + inflated_addr = get_area(NULL, 0, inflated_len, 0, flags); + if (IS_ERR_VALUE(inflated_addr)) + return addr; + if (inflated_addr & ~PAGE_MASK) + return addr; + + inflated_offset = inflated_addr & (HPAGE_PMD_SIZE-1); + inflated_addr += offset - inflated_offset; + if (inflated_offset > offset) + inflated_addr += HPAGE_PMD_SIZE; + + if (inflated_addr > TASK_SIZE - len) + return addr; + return inflated_addr; +} + #ifdef CONFIG_NUMA static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol) { @@ -3261,6 +3349,7 @@ static const struct address_space_operations shmem_aops = { static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, + .get_unmapped_area = shmem_get_unmapped_area, #ifdef CONFIG_TMPFS .llseek = shmem_file_llseek, .read_iter = shmem_file_read_iter, @@ -3496,6 +3585,15 @@ void shmem_unlock_mapping(struct address_space *mapping) { } +#ifdef CONFIG_MMU +unsigned long shmem_get_unmapped_area(struct file *file, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); +} +#endif + void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { truncate_inode_pages_range(inode->i_mapping, lstart, lend);