4 files changed, 136 insertions, 42 deletions

diff --git a/arch/um/drivers/ubd_user.c b/arch/um/drivers/ubd_user.c
index b4f8b8e60564..592b899820d6 100644
--- a/arch/um/drivers/ubd_user.c
+++ b/arch/um/drivers/ubd_user.c
@@ -41,7 +41,7 @@ int start_io_thread(unsigned long sp, int *fd_out)
 	*fd_out = fds[1];
 
 	err = os_set_fd_block(*fd_out, 0);
-	err = os_set_fd_block(kernel_fd, 0);
+	err |= os_set_fd_block(kernel_fd, 0);
 	if (err) {
 		printk("start_io_thread - failed to set nonblocking I/O.\n");
 		goto out_close;
diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c
index 64c09db392c1..7a88b13d289f 100644
--- a/arch/um/drivers/vector_kern.c
+++ b/arch/um/drivers/vector_kern.c
@@ -1592,35 +1592,19 @@ static void vector_eth_configure(
 
 	device->dev = dev;
 
-	*vp = ((struct vector_private)
-		{
-		.list			= LIST_HEAD_INIT(vp->list),
-		.dev			= dev,
-		.unit			= n,
-		.options		= get_transport_options(def),
-		.rx_irq			= 0,
-		.tx_irq			= 0,
-		.parsed			= def,
-		.max_packet		= get_mtu(def) + ETH_HEADER_OTHER,
-		/* TODO - we need to calculate headroom so that ip header
-		 * is 16 byte aligned all the time
-		 */
-		.headroom		= get_headroom(def),
-		.form_header		= NULL,
-		.verify_header		= NULL,
-		.header_rxbuffer	= NULL,
-		.header_txbuffer	= NULL,
-		.header_size		= 0,
-		.rx_header_size		= 0,
-		.rexmit_scheduled	= false,
-		.opened			= false,
-		.transport_data		= NULL,
-		.in_write_poll		= false,
-		.coalesce		= 2,
-		.req_size		= get_req_size(def),
-		.in_error		= false,
-		.bpf			= NULL
-	});
+	INIT_LIST_HEAD(&vp->list);
+	vp->dev		= dev;
+	vp->unit	= n;
+	vp->options	= get_transport_options(def);
+	vp->parsed	= def;
+	vp->max_packet	= get_mtu(def) + ETH_HEADER_OTHER;
+	/*
+	 * TODO - we need to calculate headroom so that ip header
+	 * is 16 byte aligned all the time
+	 */
+	vp->headroom	= get_headroom(def);
+	vp->coalesce	= 2;
+	vp->req_size	= get_req_size(def);
 
 	dev->features = dev->hw_features = (NETIF_F_SG | NETIF_F_FRAGLIST);
 	INIT_WORK(&vp->reset_tx, vector_reset_tx);
diff --git a/arch/um/include/asm/asm-prototypes.h b/arch/um/include/asm/asm-prototypes.h
index 5898a26daa0d..408b31d59127 100644
--- a/arch/um/include/asm/asm-prototypes.h
+++ b/arch/um/include/asm/asm-prototypes.h
@@ -1 +1,6 @@
 #include <asm-generic/asm-prototypes.h>
+#include <asm/checksum.h>
+
+#ifdef CONFIG_UML_X86
+extern void cmpxchg8b_emu(void);
+#endif
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 97c8df9c4401..9077bdb26cc3 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -18,6 +18,122 @@
 #include <skas.h>
 
 /*
+ * NOTE: UML does not have exception tables. As such, this is almost a copy
+ * of the code in mm/memory.c, only adjusting the logic to simply check whether
+ * we are coming from the kernel instead of doing an additional lookup in the
+ * exception table.
+ * We can do this simplification because we never get here if the exception was
+ * fixable.
+ */
+static inline bool get_mmap_lock_carefully(struct mm_struct *mm, bool is_user)
+{
+	if (likely(mmap_read_trylock(mm)))
+		return true;
+
+	if (!is_user)
+		return false;
+
+	return !mmap_read_lock_killable(mm);
+}
+
+static inline bool mmap_upgrade_trylock(struct mm_struct *mm)
+{
+	/*
+	 * We don't have this operation yet.
+	 *
+	 * It should be easy enough to do: it's basically a
+	 *    atomic_long_try_cmpxchg_acquire()
+	 * from RWSEM_READER_BIAS -> RWSEM_WRITER_LOCKED, but
+	 * it also needs the proper lockdep magic etc.
+	 */
+	return false;
+}
+
+static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, bool is_user)
+{
+	mmap_read_unlock(mm);
+	if (!is_user)
+		return false;
+
+	return !mmap_write_lock_killable(mm);
+}
+
+/*
+ * Helper for page fault handling.
+ *
+ * This is kind of equivalend to "mmap_read_lock()" followed
+ * by "find_extend_vma()", except it's a lot more careful about
+ * the locking (and will drop the lock on failure).
+ *
+ * For example, if we have a kernel bug that causes a page
+ * fault, we don't want to just use mmap_read_lock() to get
+ * the mm lock, because that would deadlock if the bug were
+ * to happen while we're holding the mm lock for writing.
+ *
+ * So this checks the exception tables on kernel faults in
+ * order to only do this all for instructions that are actually
+ * expected to fault.
+ *
+ * We can also actually take the mm lock for writing if we
+ * need to extend the vma, which helps the VM layer a lot.
+ */
+static struct vm_area_struct *
+um_lock_mm_and_find_vma(struct mm_struct *mm,
+			unsigned long addr, bool is_user)
+{
+	struct vm_area_struct *vma;
+
+	if (!get_mmap_lock_carefully(mm, is_user))
+		return NULL;
+
+	vma = find_vma(mm, addr);
+	if (likely(vma && (vma->vm_start <= addr)))
+		return vma;
+
+	/*
+	 * Well, dang. We might still be successful, but only
+	 * if we can extend a vma to do so.
+	 */
+	if (!vma || !(vma->vm_flags & VM_GROWSDOWN)) {
+		mmap_read_unlock(mm);
+		return NULL;
+	}
+
+	/*
+	 * We can try to upgrade the mmap lock atomically,
+	 * in which case we can continue to use the vma
+	 * we already looked up.
+	 *
+	 * Otherwise we'll have to drop the mmap lock and
+	 * re-take it, and also look up the vma again,
+	 * re-checking it.
+	 */
+	if (!mmap_upgrade_trylock(mm)) {
+		if (!upgrade_mmap_lock_carefully(mm, is_user))
+			return NULL;
+
+		vma = find_vma(mm, addr);
+		if (!vma)
+			goto fail;
+		if (vma->vm_start <= addr)
+			goto success;
+		if (!(vma->vm_flags & VM_GROWSDOWN))
+			goto fail;
+	}
+
+	if (expand_stack_locked(vma, addr))
+		goto fail;
+
+success:
+	mmap_write_downgrade(mm);
+	return vma;
+
+fail:
+	mmap_write_unlock(mm);
+	return NULL;
+}
+
+/*
  * Note this is constrained to return 0, -EFAULT, -EACCES, -ENOMEM by
  * segv().
  */
@@ -43,21 +159,10 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	if (is_user)
 		flags |= FAULT_FLAG_USER;
 retry:
-	mmap_read_lock(mm);
-	vma = find_vma(mm, address);
-	if (!vma)
-		goto out;
-	if (vma->vm_start <= address)
-		goto good_area;
-	if (!(vma->vm_flags & VM_GROWSDOWN))
-		goto out;
-	if (is_user && !ARCH_IS_STACKGROW(address))
-		goto out;
-	vma = expand_stack(mm, address);
+	vma = um_lock_mm_and_find_vma(mm, address, is_user);
 	if (!vma)
 		goto out_nosemaphore;
 
-good_area:
 	*code_out = SEGV_ACCERR;
 	if (is_write) {
 		if (!(vma->vm_flags & VM_WRITE))