Something went wrong. Try again.
(I'm so sorry!) Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel os linux
Something went wrong. Try again.
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523// SPDX-License-Identifier: GPL-2.0/* * memfd_create system call and file sealing support * * Code was originally included in shmem.c, and broken out to facilitate * use by hugetlbfs as well as tmpfs. */
#include <linux/fs.h>#include <linux/vfs.h>#include <linux/pagemap.h>#include <linux/file.h>#include <linux/mm.h>#include <linux/sched/signal.h>#include <linux/khugepaged.h>#include <linux/syscalls.h>#include <linux/hugetlb.h>#include <linux/shmem_fs.h>#include <linux/memfd.h>#include <linux/pid_namespace.h>#include <uapi/linux/memfd.h>#include "internal.h"#include "swap.h"
/* * We need a tag: a new tag would expand every xa_node by 8 bytes, * so reuse a tag which we firmly believe is never set or cleared on tmpfs * or hugetlbfs because they are memory only filesystems. */#define MEMFD_TAG_PINNED PAGECACHE_TAG_TOWRITE#define LAST_SCAN 4 /* about 150ms max */
static bool memfd_folio_has_extra_refs(struct folio *folio){ return folio_ref_count(folio) != folio_expected_ref_count(folio);}
static void memfd_tag_pins(struct xa_state *xas){ struct folio *folio; int latency = 0;
lru_add_drain();
xas_lock_irq(xas); xas_for_each(xas, folio, ULONG_MAX) { if (!xa_is_value(folio) && memfd_folio_has_extra_refs(folio)) xas_set_mark(xas, MEMFD_TAG_PINNED);
if (++latency < XA_CHECK_SCHED) continue; latency = 0;
xas_pause(xas); xas_unlock_irq(xas); cond_resched(); xas_lock_irq(xas); } xas_unlock_irq(xas);}
/* * This is a helper function used by memfd_pin_user_pages() in GUP (gup.c). * It is mainly called to allocate a folio in a memfd when the caller * (memfd_pin_folios()) cannot find a folio in the page cache at a given * index in the mapping. */struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx){#ifdef CONFIG_HUGETLB_PAGE struct folio *folio; gfp_t gfp_mask;
if (is_file_hugepages(memfd)) { /* * The folio would most likely be accessed by a DMA driver, * therefore, we have zone memory constraints where we can * alloc from. Also, the folio will be pinned for an indefinite * amount of time, so it is not expected to be migrated away. */ struct inode *inode = file_inode(memfd); struct hstate *h = hstate_file(memfd); int err = -ENOMEM; long nr_resv; u32 hash;
gfp_mask = htlb_alloc_mask(h); gfp_mask &= ~(__GFP_HIGHMEM | __GFP_MOVABLE); idx >>= huge_page_order(h);
/* * Serialize hugepage allocation and instantiation to prevent * races with concurrent allocations, as required by all other * callers of hugetlb_add_to_page_cache(). */ hash = hugetlb_fault_mutex_hash(memfd->f_mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]);
nr_resv = hugetlb_reserve_pages(inode, idx, idx + 1, NULL, EMPTY_VMA_FLAGS); if (nr_resv < 0) { err = nr_resv; goto out_unlock; }
folio = alloc_hugetlb_folio_reserve(h, numa_node_id(), NULL, gfp_mask); if (folio) { /* * Zero the folio to prevent information leaks to userspace. * Use folio_zero_user() which is optimized for huge/gigantic * pages. Pass 0 as addr_hint since this is not a faulting path * and we don't have a user virtual address yet. */ folio_zero_user(folio, 0);
/* * Mark the folio uptodate before adding to page cache, * as required by filemap.c and other hugetlb paths. */ __folio_mark_uptodate(folio);
err = hugetlb_add_to_page_cache(folio, memfd->f_mapping, idx); if (err) { folio_put(folio); goto err_unresv; }
hugetlb_set_folio_subpool(folio, subpool_inode(inode)); folio_unlock(folio); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return folio; }err_unresv: if (nr_resv > 0) hugetlb_unreserve_pages(inode, idx, idx + 1, 0);out_unlock: mutex_unlock(&hugetlb_fault_mutex_table[hash]); return ERR_PTR(err); }#endif return shmem_read_folio(memfd->f_mapping, idx);}
/* * Setting SEAL_WRITE requires us to verify there's no pending writer. However, * via get_user_pages(), drivers might have some pending I/O without any active * user-space mappings (eg., direct-IO, AIO). Therefore, we look at all folios * and see whether it has an elevated ref-count. If so, we tag them and wait for * them to be dropped. * The caller must guarantee that no new user will acquire writable references * to those folios to avoid races. */static int memfd_wait_for_pins(struct address_space *mapping){ XA_STATE(xas, &mapping->i_pages, 0); struct folio *folio; int error, scan;
memfd_tag_pins(&xas);
error = 0; for (scan = 0; scan <= LAST_SCAN; scan++) { int latency = 0;
if (!xas_marked(&xas, MEMFD_TAG_PINNED)) break;
if (!scan) lru_add_drain_all(); else if (schedule_timeout_killable((HZ << scan) / 200)) scan = LAST_SCAN;
xas_set(&xas, 0); xas_lock_irq(&xas); xas_for_each_marked(&xas, folio, ULONG_MAX, MEMFD_TAG_PINNED) { bool clear = true;
if (!xa_is_value(folio) && memfd_folio_has_extra_refs(folio)) { /* * On the last scan, we clean up all those tags * we inserted; but make a note that we still * found folios pinned. */ if (scan == LAST_SCAN) error = -EBUSY; else clear = false; } if (clear) xas_clear_mark(&xas, MEMFD_TAG_PINNED);
if (++latency < XA_CHECK_SCHED) continue; latency = 0;
xas_pause(&xas); xas_unlock_irq(&xas); cond_resched(); xas_lock_irq(&xas); } xas_unlock_irq(&xas); }
return error;}
static unsigned int *memfd_file_seals_ptr(struct file *file){ if (shmem_file(file)) return &SHMEM_I(file_inode(file))->seals;
#ifdef CONFIG_HUGETLBFS if (is_file_hugepages(file)) return &HUGETLBFS_I(file_inode(file))->seals;#endif
return NULL;}
#define F_ALL_SEALS (F_SEAL_SEAL | \ F_SEAL_EXEC | \ F_SEAL_SHRINK | \ F_SEAL_GROW | \ F_SEAL_WRITE | \ F_SEAL_FUTURE_WRITE)
int memfd_add_seals(struct file *file, unsigned int seals){ struct inode *inode = file_inode(file); unsigned int *file_seals; int error;
/* * SEALING * Sealing allows multiple parties to share a tmpfs or hugetlbfs file * but restrict access to a specific subset of file operations. Seals * can only be added, but never removed. This way, mutually untrusted * parties can share common memory regions with a well-defined policy. * A malicious peer can thus never perform unwanted operations on a * shared object. * * Seals are only supported on special tmpfs or hugetlbfs files and * always affect the whole underlying inode. Once a seal is set, it * may prevent some kinds of access to the file. Currently, the * following seals are defined: * SEAL_SEAL: Prevent further seals from being set on this file * SEAL_SHRINK: Prevent the file from shrinking * SEAL_GROW: Prevent the file from growing * SEAL_WRITE: Prevent write access to the file * SEAL_EXEC: Prevent modification of the exec bits in the file mode * * As we don't require any trust relationship between two parties, we * must prevent seals from being removed. Therefore, sealing a file * only adds a given set of seals to the file, it never touches * existing seals. Furthermore, the "setting seals"-operation can be * sealed itself, which basically prevents any further seal from being * added. * * Semantics of sealing are only defined on volatile files. Only * anonymous tmpfs and hugetlbfs files support sealing. More * importantly, seals are never written to disk. Therefore, there's * no plan to support it on other file types. */
if (!(file->f_mode & FMODE_WRITE)) return -EPERM; if (seals & ~(unsigned int)F_ALL_SEALS) return -EINVAL;
inode_lock(inode);
file_seals = memfd_file_seals_ptr(file); if (!file_seals) { error = -EINVAL; goto unlock; }
if (*file_seals & F_SEAL_SEAL) { error = -EPERM; goto unlock; }
/* * SEAL_EXEC implies SEAL_WRITE, making W^X from the start. */ if (seals & F_SEAL_EXEC && inode->i_mode & 0111) seals |= F_SEAL_SHRINK|F_SEAL_GROW|F_SEAL_WRITE|F_SEAL_FUTURE_WRITE;
if ((seals & F_SEAL_WRITE) && !(*file_seals & F_SEAL_WRITE)) { error = mapping_deny_writable(file->f_mapping); if (error) goto unlock;
error = memfd_wait_for_pins(file->f_mapping); if (error) { mapping_allow_writable(file->f_mapping); goto unlock; } }
*file_seals |= seals; error = 0;
unlock: inode_unlock(inode); return error;}
int memfd_get_seals(struct file *file){ unsigned int *seals = memfd_file_seals_ptr(file);
return seals ? *seals : -EINVAL;}
long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg){ long error;
switch (cmd) { case F_ADD_SEALS: error = memfd_add_seals(file, arg); break; case F_GET_SEALS: error = memfd_get_seals(file); break; default: error = -EINVAL; break; }
return error;}
#define MFD_NAME_PREFIX "memfd:"#define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1)#define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN)
#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB | MFD_NOEXEC_SEAL | MFD_EXEC)
static int check_sysctl_memfd_noexec(unsigned int *flags){#ifdef CONFIG_SYSCTL struct pid_namespace *ns = task_active_pid_ns(current); int sysctl = pidns_memfd_noexec_scope(ns);
if (!(*flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) { if (sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL) *flags |= MFD_NOEXEC_SEAL; else *flags |= MFD_EXEC; }
if (!(*flags & MFD_NOEXEC_SEAL) && sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED) { pr_err_ratelimited( "%s[%d]: memfd_create() requires MFD_NOEXEC_SEAL with vm.memfd_noexec=%d\n", current->comm, task_pid_nr(current), sysctl); return -EACCES; }#endif return 0;}
static inline bool is_write_sealed(unsigned int seals){ return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE);}
static int check_write_seal(vma_flags_t *vma_flags_ptr){ /* If a private mapping then writability is irrelevant. */ if (!vma_flags_test(vma_flags_ptr, VMA_SHARED_BIT)) return 0;
/* * New PROT_WRITE and MAP_SHARED mmaps are not allowed when * write seals are active. */ if (vma_flags_test(vma_flags_ptr, VMA_WRITE_BIT)) return -EPERM;
/* * This is a read-only mapping, disallow mprotect() from making a * write-sealed mapping writable in future. */ vma_flags_clear(vma_flags_ptr, VMA_MAYWRITE_BIT);
return 0;}
int memfd_check_seals_mmap(struct file *file, vma_flags_t *vma_flags_ptr){ int err = 0; unsigned int *seals_ptr = memfd_file_seals_ptr(file); unsigned int seals = seals_ptr ? *seals_ptr : 0;
if (is_write_sealed(seals)) err = check_write_seal(vma_flags_ptr);
return err;}
static int sanitize_flags(unsigned int *flags_ptr){ unsigned int flags = *flags_ptr;
if (!(flags & MFD_HUGETLB)) { if (flags & ~MFD_ALL_FLAGS) return -EINVAL; } else { /* Allow huge page size encoding in flags. */ if (flags & ~(MFD_ALL_FLAGS | (MFD_HUGE_MASK << MFD_HUGE_SHIFT))) return -EINVAL; }
/* Invalid if both EXEC and NOEXEC_SEAL are set.*/ if ((flags & MFD_EXEC) && (flags & MFD_NOEXEC_SEAL)) return -EINVAL;
return check_sysctl_memfd_noexec(flags_ptr);}
static char *alloc_name(const char __user *uname){ int error; char *name; long len;
name = kmalloc(NAME_MAX + 1, GFP_KERNEL); if (!name) return ERR_PTR(-ENOMEM);
memcpy(name, MFD_NAME_PREFIX, MFD_NAME_PREFIX_LEN); /* returned length does not include terminating zero */ len = strncpy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, MFD_NAME_MAX_LEN + 1); if (len < 0) { error = -EFAULT; goto err_name; } else if (len > MFD_NAME_MAX_LEN) { error = -EINVAL; goto err_name; }
return name;
err_name: kfree(name); return ERR_PTR(error);}
struct file *memfd_alloc_file(const char *name, unsigned int flags){ unsigned int *file_seals; struct file *file; struct inode *inode; int err = 0;
if (flags & MFD_HUGETLB) { file = hugetlb_file_setup(name, 0, mk_vma_flags(VMA_NORESERVE_BIT), HUGETLB_ANONHUGE_INODE, (flags >> MFD_HUGE_SHIFT) & MFD_HUGE_MASK); } else { file = shmem_file_setup(name, 0, mk_vma_flags(VMA_NORESERVE_BIT)); } if (IS_ERR(file)) return file;
inode = file_inode(file); err = security_inode_init_security_anon(inode, &QSTR(MEMFD_ANON_NAME), NULL); if (err) { fput(file); file = ERR_PTR(err); return file; }
file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; file->f_flags |= O_LARGEFILE;
if (flags & MFD_NOEXEC_SEAL) { inode->i_mode &= ~0111; file_seals = memfd_file_seals_ptr(file); if (file_seals) { *file_seals &= ~F_SEAL_SEAL; *file_seals |= F_SEAL_EXEC; } } else if (flags & MFD_ALLOW_SEALING) { /* MFD_EXEC and MFD_ALLOW_SEALING are set */ file_seals = memfd_file_seals_ptr(file); if (file_seals) *file_seals &= ~F_SEAL_SEAL; }
return file;}
SYSCALL_DEFINE2(memfd_create, const char __user *, uname, unsigned int, flags){ char *name __free(kfree) = NULL; unsigned int fd_flags; int error;
error = sanitize_flags(&flags); if (error < 0) return error;
name = alloc_name(uname); if (IS_ERR(name)) return PTR_ERR(name);
fd_flags = (flags & MFD_CLOEXEC) ? O_CLOEXEC : 0; return FD_ADD(fd_flags, memfd_alloc_file(name, flags));}