@@ -208,6 +208,7 @@ config ARM64
select SWIOTLB
select SYSCTL_EXCEPTION_TRACE
select THREAD_INFO_IN_TASK
+ select HAVE_ARCH_USERFAULTFD_MINOR if USERFAULTFD
help
ARM 64-bit (AArch64) Linux support.
@@ -164,6 +164,7 @@ config X86
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
select HAVE_ARCH_USERFAULTFD_WP if X86_64 && USERFAULTFD
+ select HAVE_ARCH_USERFAULTFD_MINOR if X86_64 && USERFAULTFD
select HAVE_ARCH_VMAP_STACK if X86_64
select HAVE_ARCH_WITHIN_STACK_FRAMES
select HAVE_ASM_MODVERSIONS
@@ -661,6 +661,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
[ilog2(VM_PKEY_BIT4)] = "",
#endif
#endif /* CONFIG_ARCH_HAS_PKEYS */
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+ [ilog2(VM_UFFD_MINOR)] = "ui",
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
};
size_t i;
@@ -197,24 +197,21 @@ static inline struct uffd_msg userfault_msg(unsigned long address,
msg_init(&msg);
msg.event = UFFD_EVENT_PAGEFAULT;
msg.arg.pagefault.address = address;
+ /*
+ * These flags indicate why the userfault occurred:
+ * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault.
+ * - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault.
+ * - Neither of these flags being set indicates a MISSING fault.
+ *
+ * Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write
+ * fault. Otherwise, it was a read fault.
+ */
if (flags & FAULT_FLAG_WRITE)
- /*
- * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the
- * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WRITE
- * was not set in a UFFD_EVENT_PAGEFAULT, it means it
- * was a read fault, otherwise if set it means it's
- * a write fault.
- */
msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE;
if (reason & VM_UFFD_WP)
- /*
- * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the
- * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WP was
- * not set in a UFFD_EVENT_PAGEFAULT, it means it was
- * a missing fault, otherwise if set it means it's a
- * write protect fault.
- */
msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP;
+ if (reason & VM_UFFD_MINOR)
+ msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR;
if (features & UFFD_FEATURE_THREAD_ID)
msg.arg.pagefault.feat.ptid = task_pid_vnr(current);
return msg;
@@ -401,8 +398,10 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
BUG_ON(ctx->mm != mm);
- VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP));
- VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP));
+ /* Any unrecognized flag is a bug. */
+ VM_BUG_ON(reason & ~__VM_UFFD_FLAGS);
+ /* 0 or > 1 flags set is a bug; we expect exactly 1. */
+ VM_BUG_ON(!reason || (reason & (reason - 1)));
if (ctx->features & UFFD_FEATURE_SIGBUS)
goto out;
@@ -612,7 +611,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
for (vma = mm->mmap; vma; vma = vma->vm_next)
if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+ vma->vm_flags &= ~__VM_UFFD_FLAGS;
}
mmap_write_unlock(mm);
@@ -644,7 +643,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
octx = vma->vm_userfaultfd_ctx.ctx;
if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+ vma->vm_flags &= ~__VM_UFFD_FLAGS;
return 0;
}
@@ -726,7 +725,7 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma,
} else {
/* Drop uffd context if remap feature not enabled */
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+ vma->vm_flags &= ~__VM_UFFD_FLAGS;
}
}
@@ -867,12 +866,12 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
for (vma = mm->mmap; vma; vma = vma->vm_next) {
cond_resched();
BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^
- !!(vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
+ !!(vma->vm_flags & __VM_UFFD_FLAGS));
if (vma->vm_userfaultfd_ctx.ctx != ctx) {
prev = vma;
continue;
}
- new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
+ new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
new_flags, vma->anon_vma,
vma->vm_file, vma->vm_pgoff,
@@ -1262,9 +1261,19 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
unsigned long vm_flags)
{
/* FIXME: add WP support to hugetlbfs and shmem */
- return vma_is_anonymous(vma) ||
- ((is_vm_hugetlb_page(vma) || vma_is_shmem(vma)) &&
- !(vm_flags & VM_UFFD_WP));
+ if (vm_flags & VM_UFFD_WP) {
+ if (is_vm_hugetlb_page(vma) || vma_is_shmem(vma))
+ return false;
+ }
+
+ if (vm_flags & VM_UFFD_MINOR) {
+ /* FIXME: Add minor fault interception for shmem. */
+ if (!is_vm_hugetlb_page(vma))
+ return false;
+ }
+
+ return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
+ vma_is_shmem(vma);
}
static int userfaultfd_register(struct userfaultfd_ctx *ctx,
@@ -1290,14 +1299,19 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
ret = -EINVAL;
if (!uffdio_register.mode)
goto out;
- if (uffdio_register.mode & ~(UFFDIO_REGISTER_MODE_MISSING|
- UFFDIO_REGISTER_MODE_WP))
+ if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES)
goto out;
vm_flags = 0;
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING)
vm_flags |= VM_UFFD_MISSING;
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)
vm_flags |= VM_UFFD_WP;
+ if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) {
+#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+ goto out;
+#endif
+ vm_flags |= VM_UFFD_MINOR;
+ }
ret = validate_range(mm, &uffdio_register.range.start,
uffdio_register.range.len);
@@ -1341,7 +1355,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
cond_resched();
BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
- !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
+ !!(cur->vm_flags & __VM_UFFD_FLAGS));
/* check not compatible vmas */
ret = -EINVAL;
@@ -1421,8 +1435,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
start = vma->vm_start;
vma_end = min(end, vma->vm_end);
- new_flags = (vma->vm_flags &
- ~(VM_UFFD_MISSING|VM_UFFD_WP)) | vm_flags;
+ new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags;
prev = vma_merge(mm, prev, start, vma_end, new_flags,
vma->anon_vma, vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
@@ -1544,7 +1557,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
cond_resched();
BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
- !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
+ !!(cur->vm_flags & __VM_UFFD_FLAGS));
/*
* Check not compatible vmas, not strictly required
@@ -1595,7 +1608,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range);
}
- new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
+ new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
prev = vma_merge(mm, prev, start, vma_end, new_flags,
vma->anon_vma, vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
@@ -1863,6 +1876,9 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
goto err_out;
/* report all available features and ioctls to userland */
uffdio_api.features = UFFD_API_FEATURES;
+#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+ uffdio_api.features &= ~UFFD_FEATURE_MINOR_HUGETLBFS;
+#endif
uffdio_api.ioctls = UFFD_API_IOCTLS;
ret = -EFAULT;
if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
@@ -362,6 +362,13 @@ extern unsigned int kobjsize(const void *objp);
# define VM_GROWSUP VM_NONE
#endif
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+# define VM_UFFD_MINOR_BIT 37
+# define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */
+#else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
+# define VM_UFFD_MINOR VM_NONE
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
+
/* Bits set in the VMA until the stack is in its final location */
#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ)
@@ -17,6 +17,9 @@
#include <linux/mm.h>
#include <asm-generic/pgtable_uffd.h>
+/* The set of all possible UFFD-related VM flags. */
+#define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR)
+
/*
* CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
* new flags, since they might collide with O_* ones. We want
@@ -71,6 +74,11 @@ static inline bool userfaultfd_wp(struct vm_area_struct *vma)
return vma->vm_flags & VM_UFFD_WP;
}
+static inline bool userfaultfd_minor(struct vm_area_struct *vma)
+{
+ return vma->vm_flags & VM_UFFD_MINOR;
+}
+
static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma,
pte_t pte)
{
@@ -85,7 +93,7 @@ static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma,
static inline bool userfaultfd_armed(struct vm_area_struct *vma)
{
- return vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP);
+ return vma->vm_flags & __VM_UFFD_FLAGS;
}
extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *);
@@ -132,6 +140,11 @@ static inline bool userfaultfd_wp(struct vm_area_struct *vma)
return false;
}
+static inline bool userfaultfd_minor(struct vm_area_struct *vma)
+{
+ return false;
+}
+
static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma,
pte_t pte)
{
@@ -137,6 +137,12 @@ IF_HAVE_PG_ARCH_2(PG_arch_2, "arch_2" )
#define IF_HAVE_VM_SOFTDIRTY(flag,name)
#endif
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+# define IF_HAVE_UFFD_MINOR(flag, name) {flag, name},
+#else
+# define IF_HAVE_UFFD_MINOR(flag, name)
+#endif
+
#define __def_vmaflag_names \
{VM_READ, "read" }, \
{VM_WRITE, "write" }, \
@@ -148,6 +154,7 @@ IF_HAVE_PG_ARCH_2(PG_arch_2, "arch_2" )
{VM_MAYSHARE, "mayshare" }, \
{VM_GROWSDOWN, "growsdown" }, \
{VM_UFFD_MISSING, "uffd_missing" }, \
+IF_HAVE_UFFD_MINOR(VM_UFFD_MINOR, "uffd_minor" ) \
{VM_PFNMAP, "pfnmap" }, \
{VM_DENYWRITE, "denywrite" }, \
{VM_UFFD_WP, "uffd_wp" }, \
@@ -19,15 +19,19 @@
* means the userland is reading).
*/
#define UFFD_API ((__u64)0xAA)
+#define UFFD_API_REGISTER_MODES (UFFDIO_REGISTER_MODE_MISSING | \
+ UFFDIO_REGISTER_MODE_WP | \
+ UFFDIO_REGISTER_MODE_MINOR)
#define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \
UFFD_FEATURE_EVENT_FORK | \
UFFD_FEATURE_EVENT_REMAP | \
- UFFD_FEATURE_EVENT_REMOVE | \
+ UFFD_FEATURE_EVENT_REMOVE | \
UFFD_FEATURE_EVENT_UNMAP | \
UFFD_FEATURE_MISSING_HUGETLBFS | \
UFFD_FEATURE_MISSING_SHMEM | \
UFFD_FEATURE_SIGBUS | \
- UFFD_FEATURE_THREAD_ID)
+ UFFD_FEATURE_THREAD_ID | \
+ UFFD_FEATURE_MINOR_HUGETLBFS)
#define UFFD_API_IOCTLS \
((__u64)1 << _UFFDIO_REGISTER | \
(__u64)1 << _UFFDIO_UNREGISTER | \
@@ -127,6 +131,7 @@ struct uffd_msg {
/* flags for UFFD_EVENT_PAGEFAULT */
#define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */
#define UFFD_PAGEFAULT_FLAG_WP (1<<1) /* If reason is VM_UFFD_WP */
+#define UFFD_PAGEFAULT_FLAG_MINOR (1<<2) /* If reason is VM_UFFD_MINOR */
struct uffdio_api {
/* userland asks for an API number and the features to enable */
@@ -171,6 +176,10 @@ struct uffdio_api {
*
* UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will
* be returned, if feature is not requested 0 will be returned.
+ *
+ * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults
+ * can be intercepted (via REGISTER_MODE_MINOR) for
+ * hugetlbfs-backed pages.
*/
#define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0)
#define UFFD_FEATURE_EVENT_FORK (1<<1)
@@ -181,6 +190,7 @@ struct uffdio_api {
#define UFFD_FEATURE_EVENT_UNMAP (1<<6)
#define UFFD_FEATURE_SIGBUS (1<<7)
#define UFFD_FEATURE_THREAD_ID (1<<8)
+#define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9)
__u64 features;
__u64 ioctls;
@@ -195,6 +205,7 @@ struct uffdio_register {
struct uffdio_range range;
#define UFFDIO_REGISTER_MODE_MISSING ((__u64)1<<0)
#define UFFDIO_REGISTER_MODE_WP ((__u64)1<<1)
+#define UFFDIO_REGISTER_MODE_MINOR ((__u64)1<<2)
__u64 mode;
/*
@@ -1628,6 +1628,11 @@ config HAVE_ARCH_USERFAULTFD_WP
help
Arch has userfaultfd write protection support
+config HAVE_ARCH_USERFAULTFD_MINOR
+ bool
+ help
+ Arch has userfaultfd minor fault support
+
config MEMBARRIER
bool "Enable membarrier() system call" if EXPERT
default y
@@ -4230,6 +4230,44 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
return 0;
}
+static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma,
+ struct address_space *mapping,
+ pgoff_t idx,
+ unsigned int flags,
+ unsigned long haddr,
+ unsigned long reason)
+{
+ vm_fault_t ret;
+ u32 hash;
+ struct vm_fault vmf = {
+ .vma = vma,
+ .address = haddr,
+ .flags = flags,
+
+ /*
+ * Hard to debug if it ends up being
+ * used by a callee that assumes
+ * something about the other
+ * uninitialized fields... same as in
+ * memory.c
+ */
+ };
+
+ /*
+ * hugetlb_fault_mutex and i_mmap_rwsem must be
+ * dropped before handling userfault. Reacquire
+ * after handling fault to make calling code simpler.
+ */
+ hash = hugetlb_fault_mutex_hash(mapping, idx);
+ mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+ i_mmap_unlock_read(mapping);
+ ret = handle_userfault(&vmf, reason);
+ i_mmap_lock_read(mapping);
+ mutex_lock(&hugetlb_fault_mutex_table[hash]);
+
+ return ret;
+}
+
static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
struct vm_area_struct *vma,
struct address_space *mapping, pgoff_t idx,
@@ -4268,35 +4306,11 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
retry:
page = find_lock_page(mapping, idx);
if (!page) {
- /*
- * Check for page in userfault range
- */
+ /* Check for page in userfault range */
if (userfaultfd_missing(vma)) {
- u32 hash;
- struct vm_fault vmf = {
- .vma = vma,
- .address = haddr,
- .flags = flags,
- /*
- * Hard to debug if it ends up being
- * used by a callee that assumes
- * something about the other
- * uninitialized fields... same as in
- * memory.c
- */
- };
-
- /*
- * hugetlb_fault_mutex and i_mmap_rwsem must be
- * dropped before handling userfault. Reacquire
- * after handling fault to make calling code simpler.
- */
- hash = hugetlb_fault_mutex_hash(mapping, idx);
- mutex_unlock(&hugetlb_fault_mutex_table[hash]);
- i_mmap_unlock_read(mapping);
- ret = handle_userfault(&vmf, VM_UFFD_MISSING);
- i_mmap_lock_read(mapping);
- mutex_lock(&hugetlb_fault_mutex_table[hash]);
+ ret = hugetlb_handle_userfault(vma, mapping, idx,
+ flags, haddr,
+ VM_UFFD_MISSING);
goto out;
}
@@ -4355,6 +4369,15 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
VM_FAULT_SET_HINDEX(hstate_index(h));
goto backout_unlocked;
}
+
+ /* Check for page in userfault range. */
+ if (userfaultfd_minor(vma)) {
+ unlock_page(page);
+ ret = hugetlb_handle_userfault(vma, mapping, idx,
+ flags, haddr,
+ VM_UFFD_MINOR);
+ goto out;
+ }
}
/*