Updates for UML for this cycle, notably:

- proper nofault accesses and read-only rodata
  - hostfs fix for host inode number reuse
  - fixes for host errno handling
  - various cleanups/small fixes
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEpeA8sTs3M8SN2hR410qiO8sPaAAFAmfs6R0ACgkQ10qiO8sP
 aAC6VxAAoIqPoyeOqH5DRnHQZQuZOE2lelhKCKckH3xg8peXqHdBl5Mx3kE2j851
 S+ufysSJkbZIYfPw/B59ZzpQg7d1JmrCoDCvleH/LdWhi6sosqe9F7Zwxk2p9STA
 swCifnACaIZc0iir70MrCAd/1/bBZq7PG8BWO1XFDrqNBLBGQxtSiMCmzBWsKjuj
 33uocQMi5PvVikBRxfz2uo4PJuJumhGs3sWAoFlA61ogHP4JrwKjW/HvuHJGaHKV
 YgaObr/JPhDkbGn7bXdQpLT+Qz7FwBeZFt9AUHOk+IibcwQY126ArXD11zzAAPkT
 3Q9H8eNV+MpieGtpA2+3Gwe//QsNjEOj3ACfV+S7veQ0Vxk+Bd/wMSDBKLF+z71g
 qpFqFeO0wS/XmwFI6RVN+GW6rZZ6mR3c7r/5mtAOa5+iJTnqDadyE/4oouQht2of
 IrS4LugnTB0KCgRZZDmtTOFT8lGOjey3e+AO42Qi+Z64oolI6zKUakTdBWvywmk4
 V9w9OUmEZAy64a0luvavYfxx+6WoTHURyQ/L99Ysk6ns9BrUk7U+hpfsLZBWZiyT
 3jfOlRGgt4N7iHaVqQwB6l6/Q/FtrdVK7SrTtsGzURhuCSy3SP0HZxWh9qhaL/2j
 Af8Qz5OAOEBYmTaN9lLYsHXp02NyM+4hlsR1DvEcNGuWQsyepIw=
 =MSjq
 -----END PGP SIGNATURE-----

Merge tag 'uml-for-linux-6.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/uml/linux

Pull UML updates from Johannes Berg:

 - proper nofault accesses and read-only rodata

 - hostfs fix for host inode number reuse

 - fixes for host errno handling

 - various cleanups/small fixes

* tag 'uml-for-linux-6.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/uml/linux:
  um: Rewrite the sigio workaround based on epoll and tgkill
  um: Prohibit the VM_CLONE flag in run_helper_thread()
  um: Switch to the pthread-based helper in sigio workaround
  um: ubd: Switch to the pthread-based helper
  um: Add pthread-based helper support
  um: x86: clean up elf specific definitions
  um: Store full CSGSFS and SS register from mcontext
  um: virt-pci: Refactor virtio_pcidev into its own module
  um: work around sched_yield not yielding in time-travel mode
  um/locking: Remove semicolon from "lock" prefix
  um: Update min_low_pfn to match changes in uml_reserved
  um: use str_yes_no() to remove hardcoded "yes" and "no"
  um: hostfs: avoid issues on inode number reuse by host
  um: Allocate vdso page pointer statically
  um: remove copy_from_kernel_nofault_allowed
  um: mark rodata read-only and implement _nofault accesses
  um: Pass the correct Rust target and options with gcc

arch/um/Kconfig

@@ -12,6 +12,7 @@ config UML
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_STRNCPY_FROM_USER
 	select ARCH_HAS_STRNLEN_USER
+	select ARCH_HAS_STRICT_KERNEL_RWX
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_KASAN if X86_64
 	select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN

arch/um/drivers/Kconfig

@@ -345,16 +345,20 @@ config UML_RTC
 	  by providing a fake RTC clock that causes a wakeup at the right
 	  time.
 
-config UML_PCI_OVER_VIRTIO
+config UML_PCI
-	bool "Enable PCI over VIRTIO device simulation"
+	bool
-	# in theory, just VIRTIO is enough, but that causes recursion
-	depends on VIRTIO_UML
 	select FORCE_PCI
 	select UML_IOMEM_EMULATION
 	select UML_DMA_EMULATION
 	select PCI_MSI
 	select PCI_LOCKLESS_CONFIG
 
+config UML_PCI_OVER_VIRTIO
+	bool "Enable PCI over VIRTIO device simulation"
+	# in theory, just VIRTIO is enough, but that causes recursion
+	depends on VIRTIO_UML
+	select UML_PCI
+
 config UML_PCI_OVER_VIRTIO_DEVICE_ID
 	int "set the virtio device ID for PCI emulation"
 	default -1

arch/um/drivers/Makefile

@@ -60,7 +60,8 @@ obj-$(CONFIG_BLK_DEV_COW_COMMON) += cow_user.o
 obj-$(CONFIG_UML_RANDOM) += random.o
 obj-$(CONFIG_VIRTIO_UML) += virtio_uml.o
 obj-$(CONFIG_UML_RTC) += rtc.o
-obj-$(CONFIG_UML_PCI_OVER_VIRTIO) += virt-pci.o
+obj-$(CONFIG_UML_PCI) += virt-pci.o
+obj-$(CONFIG_UML_PCI_OVER_VIRTIO) += virtio_pcidev.o
 
 # pcap_user.o must be added explicitly.
 USER_OBJS := fd.o null.o pty.o tty.o xterm.o slip_common.o vde_user.o vector_user.o

arch/um/drivers/random.c

@@ -79,7 +79,7 @@ static int __init rng_init (void)
 	if (err < 0)
 		goto err_out_cleanup_hw;
 
-	sigio_broken(random_fd);
+	sigio_broken();
 	hwrng.name = RNG_MODULE_NAME;
 	hwrng.read = rng_dev_read;
 

arch/um/drivers/rtc_user.c

@@ -39,7 +39,7 @@ int uml_rtc_start(bool timetravel)
 		}
 
 		/* apparently timerfd won't send SIGIO, use workaround */
-		sigio_broken(uml_rtc_irq_fds[0]);
+		sigio_broken();
 		err = add_sigio_fd(uml_rtc_irq_fds[0]);
 		if (err < 0) {
 			close(uml_rtc_irq_fds[0]);

arch/um/drivers/ubd.h

@@ -7,8 +7,10 @@
 #ifndef __UM_UBD_USER_H
 #define __UM_UBD_USER_H
 
-extern int start_io_thread(unsigned long sp, int *fds_out);
+#include <os.h>
-extern int io_thread(void *arg);
+
+int start_io_thread(struct os_helper_thread **td_out, int *fd_out);
+void *io_thread(void *arg);
 extern int kernel_fd;
 
 extern int ubd_read_poll(int timeout);

arch/um/drivers/ubd_kern.c

@@ -474,12 +474,12 @@ static irqreturn_t ubd_intr(int irq, void *dev)
 }
 
 /* Only changed by ubd_init, which is an initcall. */
-static int io_pid = -1;
+static struct os_helper_thread *io_td;
 
 static void kill_io_thread(void)
 {
-	if(io_pid != -1)
+	if (io_td)
-		os_kill_process(io_pid, 1);
+		os_kill_helper_thread(io_td);
 }
 
 __uml_exitcall(kill_io_thread);
@@ -1104,8 +1104,8 @@ static int __init ubd_init(void)
 
 late_initcall(ubd_init);
 
-static int __init ubd_driver_init(void){
+static int __init ubd_driver_init(void)
-	unsigned long stack;
+{
 	int err;
 
 	/* Set by CONFIG_BLK_DEV_UBD_SYNC or ubd=sync.*/
@@ -1114,13 +1114,11 @@ static int __init ubd_driver_init(void){
 		/* Letting ubd=sync be like using ubd#s= instead of ubd#= is
 		 * enough. So use anyway the io thread. */
 	}
-	stack = alloc_stack(0, 0);
+	err = start_io_thread(&io_td, &thread_fd);
-	io_pid = start_io_thread(stack + PAGE_SIZE, &thread_fd);
+	if (err < 0) {
-	if(io_pid < 0){
 		printk(KERN_ERR
 		       "ubd : Failed to start I/O thread (errno = %d) - "
-		       "falling back to synchronous I/O\n", -io_pid);
+		       "falling back to synchronous I/O\n", -err);
-		io_pid = -1;
 		return 0;
 	}
 	err = um_request_irq(UBD_IRQ, thread_fd, IRQ_READ, ubd_intr,
@@ -1496,12 +1494,11 @@ int kernel_fd = -1;
 /* Only changed by the io thread. XXX: currently unused. */
 static int io_count;
 
-int io_thread(void *arg)
+void *io_thread(void *arg)
 {
 	int n, count, written, res;
 
-	os_set_pdeathsig();
+	os_fix_helper_thread_signals();
-	os_fix_helper_signals();
 
 	while(1){
 		n = bulk_req_safe_read(
@@ -1543,5 +1540,5 @@ int io_thread(void *arg)
 		} while (written < n);
 	}
 
-	return 0;
+	return NULL;
 }

arch/um/drivers/ubd_user.c

@@ -25,9 +25,9 @@
 
 static struct pollfd kernel_pollfd;
 
-int start_io_thread(unsigned long sp, int *fd_out)
+int start_io_thread(struct os_helper_thread **td_out, int *fd_out)
 {
-	int pid, fds[2], err;
+	int fds[2], err;
 
 	err = os_pipe(fds, 1, 1);
 	if(err < 0){
@@ -47,14 +47,14 @@ int start_io_thread(unsigned long sp, int *fd_out)
 		goto out_close;
 	}
 
-	pid = clone(io_thread, (void *) sp, CLONE_FILES | CLONE_VM, NULL);
+	err = os_run_helper_thread(td_out, io_thread, NULL);
-	if(pid < 0){
+	if (err < 0) {
-		err = -errno;
+		printk("%s - failed to run helper thread, err = %d\n",
-		printk("start_io_thread - clone failed : errno = %d\n", errno);
+		       __func__, -err);
 		goto out_close;
 	}
 
-	return(pid);
+	return 0;
 
  out_close:
 	os_close_file(fds[0]);

arch/um/drivers/virt-pci.c

@@ -5,52 +5,19 @@
  */
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/virtio.h>
-#include <linux/virtio_config.h>
 #include <linux/logic_iomem.h>
 #include <linux/of_platform.h>
 #include <linux/irqdomain.h>
-#include <linux/virtio_pcidev.h>
-#include <linux/virtio-uml.h>
-#include <linux/delay.h>
 #include <linux/msi.h>
 #include <linux/unaligned.h>
 #include <irq_kern.h>
 
+#include "virt-pci.h"
+
 #define MAX_DEVICES 8
 #define MAX_MSI_VECTORS 32
 #define CFG_SPACE_SIZE 4096
 
-/* for MSI-X we have a 32-bit payload */
-#define MAX_IRQ_MSG_SIZE (sizeof(struct virtio_pcidev_msg) + sizeof(u32))
-#define NUM_IRQ_MSGS	10
-
-struct um_pci_message_buffer {
-	struct virtio_pcidev_msg hdr;
-	u8 data[8];
-};
-
-struct um_pci_device {
-	struct virtio_device *vdev;
-
-	/* for now just standard BARs */
-	u8 resptr[PCI_STD_NUM_BARS];
-
-	struct virtqueue *cmd_vq, *irq_vq;
-
-#define UM_PCI_WRITE_BUFS	20
-	struct um_pci_message_buffer bufs[UM_PCI_WRITE_BUFS + 1];
-	void *extra_ptrs[UM_PCI_WRITE_BUFS + 1];
-	DECLARE_BITMAP(used_bufs, UM_PCI_WRITE_BUFS);
-
-#define UM_PCI_STAT_WAITING	0
-	unsigned long status;
-
-	int irq;
-
-	bool platform;
-};
-
 struct um_pci_device_reg {
 	struct um_pci_device *dev;
 	void __iomem *iomem;
@@ -65,179 +32,15 @@ static struct irq_domain *um_pci_inner_domain;
 static struct irq_domain *um_pci_msi_domain;
 static unsigned long um_pci_msi_used[BITS_TO_LONGS(MAX_MSI_VECTORS)];
 
-static unsigned int um_pci_max_delay_us = 40000;
-module_param_named(max_delay_us, um_pci_max_delay_us, uint, 0644);
-
-static int um_pci_get_buf(struct um_pci_device *dev, bool *posted)
-{
-	int i;
-
-	for (i = 0; i < UM_PCI_WRITE_BUFS; i++) {
-		if (!test_and_set_bit(i, dev->used_bufs))
-			return i;
-	}
-
-	*posted = false;
-	return UM_PCI_WRITE_BUFS;
-}
-
-static void um_pci_free_buf(struct um_pci_device *dev, void *buf)
-{
-	int i;
-
-	if (buf == &dev->bufs[UM_PCI_WRITE_BUFS]) {
-		kfree(dev->extra_ptrs[UM_PCI_WRITE_BUFS]);
-		dev->extra_ptrs[UM_PCI_WRITE_BUFS] = NULL;
-		return;
-	}
-
-	for (i = 0; i < UM_PCI_WRITE_BUFS; i++) {
-		if (buf == &dev->bufs[i]) {
-			kfree(dev->extra_ptrs[i]);
-			dev->extra_ptrs[i] = NULL;
-			WARN_ON(!test_and_clear_bit(i, dev->used_bufs));
-			return;
-		}
-	}
-
-	WARN_ON(1);
-}
-
-static int um_pci_send_cmd(struct um_pci_device *dev,
-			   struct virtio_pcidev_msg *cmd,
-			   unsigned int cmd_size,
-			   const void *extra, unsigned int extra_size,
-			   void *out, unsigned int out_size)
-{
-	struct scatterlist out_sg, extra_sg, in_sg;
-	struct scatterlist *sgs_list[] = {
-		[0] = &out_sg,
-		[1] = extra ? &extra_sg : &in_sg,
-		[2] = extra ? &in_sg : NULL,
-	};
-	struct um_pci_message_buffer *buf;
-	int delay_count = 0;
-	bool bounce_out;
-	int ret, len;
-	int buf_idx;
-	bool posted;
-
-	if (WARN_ON(cmd_size < sizeof(*cmd) || cmd_size > sizeof(*buf)))
-		return -EINVAL;
-
-	switch (cmd->op) {
-	case VIRTIO_PCIDEV_OP_CFG_WRITE:
-	case VIRTIO_PCIDEV_OP_MMIO_WRITE:
-	case VIRTIO_PCIDEV_OP_MMIO_MEMSET:
-		/* in PCI, writes are posted, so don't wait */
-		posted = !out;
-		WARN_ON(!posted);
-		break;
-	default:
-		posted = false;
-		break;
-	}
-
-	bounce_out = !posted && cmd_size <= sizeof(*cmd) &&
-		     out && out_size <= sizeof(buf->data);
-
-	buf_idx = um_pci_get_buf(dev, &posted);
-	buf = &dev->bufs[buf_idx];
-	memcpy(buf, cmd, cmd_size);
-
-	if (posted && extra && extra_size > sizeof(buf) - cmd_size) {
-		dev->extra_ptrs[buf_idx] = kmemdup(extra, extra_size,
-						   GFP_ATOMIC);
-
-		if (!dev->extra_ptrs[buf_idx]) {
-			um_pci_free_buf(dev, buf);
-			return -ENOMEM;
-		}
-		extra = dev->extra_ptrs[buf_idx];
-	} else if (extra && extra_size <= sizeof(buf) - cmd_size) {
-		memcpy((u8 *)buf + cmd_size, extra, extra_size);
-		cmd_size += extra_size;
-		extra_size = 0;
-		extra = NULL;
-		cmd = (void *)buf;
-	} else {
-		cmd = (void *)buf;
-	}
-
-	sg_init_one(&out_sg, cmd, cmd_size);
-	if (extra)
-		sg_init_one(&extra_sg, extra, extra_size);
-	/* allow stack for small buffers */
-	if (bounce_out)
-		sg_init_one(&in_sg, buf->data, out_size);
-	else if (out)
-		sg_init_one(&in_sg, out, out_size);
-
-	/* add to internal virtio queue */
-	ret = virtqueue_add_sgs(dev->cmd_vq, sgs_list,
-				extra ? 2 : 1,
-				out ? 1 : 0,
-				cmd, GFP_ATOMIC);
-	if (ret) {
-		um_pci_free_buf(dev, buf);
-		return ret;
-	}
-
-	if (posted) {
-		virtqueue_kick(dev->cmd_vq);
-		return 0;
-	}
-
-	/* kick and poll for getting a response on the queue */
-	set_bit(UM_PCI_STAT_WAITING, &dev->status);
-	virtqueue_kick(dev->cmd_vq);
-	ret = 0;
-
-	while (1) {
-		void *completed = virtqueue_get_buf(dev->cmd_vq, &len);
-
-		if (completed == buf)
-			break;
-
-		if (completed)
-			um_pci_free_buf(dev, completed);
-
-		if (WARN_ONCE(virtqueue_is_broken(dev->cmd_vq) ||
-			      ++delay_count > um_pci_max_delay_us,
-			      "um virt-pci delay: %d", delay_count)) {
-			ret = -EIO;
-			break;
-		}
-		udelay(1);
-	}
-	clear_bit(UM_PCI_STAT_WAITING, &dev->status);
-
-	if (bounce_out)
-		memcpy(out, buf->data, out_size);
-
-	um_pci_free_buf(dev, buf);
-
-	return ret;
-}
-
 static unsigned long um_pci_cfgspace_read(void *priv, unsigned int offset,
 					  int size)
 {
 	struct um_pci_device_reg *reg = priv;
 	struct um_pci_device *dev = reg->dev;
-	struct virtio_pcidev_msg hdr = {
-		.op = VIRTIO_PCIDEV_OP_CFG_READ,
-		.size = size,
-		.addr = offset,
-	};
-	/* max 8, we might not use it all */
-	u8 data[8];
 
 	if (!dev)
 		return ULONG_MAX;
 
-	memset(data, 0xff, sizeof(data));
-
 	switch (size) {
 	case 1:
 	case 2:
@@ -251,23 +54,7 @@ static unsigned long um_pci_cfgspace_read(void *priv, unsigned int offset,
 		return ULONG_MAX;
 	}
 
-	if (um_pci_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, data, size))
+	return dev->ops->cfgspace_read(dev, offset, size);
-		return ULONG_MAX;
-
-	switch (size) {
-	case 1:
-		return data[0];
-	case 2:
-		return le16_to_cpup((void *)data);
-	case 4:
-		return le32_to_cpup((void *)data);
-#ifdef CONFIG_64BIT
-	case 8:
-		return le64_to_cpup((void *)data);
-#endif
-	default:
-		return ULONG_MAX;
-	}
 }
 
 static void um_pci_cfgspace_write(void *priv, unsigned int offset, int size,
@@ -275,42 +62,24 @@ static void um_pci_cfgspace_write(void *priv, unsigned int offset, int size,
 {
 	struct um_pci_device_reg *reg = priv;
 	struct um_pci_device *dev = reg->dev;
-	struct {
-		struct virtio_pcidev_msg hdr;
-		/* maximum size - we may only use parts of it */
-		u8 data[8];
-	} msg = {
-		.hdr = {
-			.op = VIRTIO_PCIDEV_OP_CFG_WRITE,
-			.size = size,
-			.addr = offset,
-		},
-	};
 
 	if (!dev)
 		return;
 
 	switch (size) {
 	case 1:
-		msg.data[0] = (u8)val;
-		break;
 	case 2:
-		put_unaligned_le16(val, (void *)msg.data);
-		break;
 	case 4:
-		put_unaligned_le32(val, (void *)msg.data);
-		break;
 #ifdef CONFIG_64BIT
 	case 8:
-		put_unaligned_le64(val, (void *)msg.data);
-		break;
 #endif
+		break;
 	default:
 		WARN(1, "invalid config space write size %d\n", size);
 		return;
 	}
 
-	WARN_ON(um_pci_send_cmd(dev, &msg.hdr, sizeof(msg), NULL, 0, NULL, 0));
+	dev->ops->cfgspace_write(dev, offset, size, val);
 }
 
 static const struct logic_iomem_ops um_pci_device_cfgspace_ops = {
@@ -318,6 +87,56 @@ static const struct logic_iomem_ops um_pci_device_cfgspace_ops = {
 	.write = um_pci_cfgspace_write,
 };
 
+static unsigned long um_pci_bar_read(void *priv, unsigned int offset,
+				     int size)
+{
+	u8 *resptr = priv;
+	struct um_pci_device *dev = container_of(resptr - *resptr,
+						 struct um_pci_device,
+						 resptr[0]);
+	u8 bar = *resptr;
+
+	switch (size) {
+	case 1:
+	case 2:
+	case 4:
+#ifdef CONFIG_64BIT
+	case 8:
+#endif
+		break;
+	default:
+		WARN(1, "invalid bar read size %d\n", size);
+		return ULONG_MAX;
+	}
+
+	return dev->ops->bar_read(dev, bar, offset, size);
+}
+
+static void um_pci_bar_write(void *priv, unsigned int offset, int size,
+			     unsigned long val)
+{
+	u8 *resptr = priv;
+	struct um_pci_device *dev = container_of(resptr - *resptr,
+						 struct um_pci_device,
+						 resptr[0]);
+	u8 bar = *resptr;
+
+	switch (size) {
+	case 1:
+	case 2:
+	case 4:
+#ifdef CONFIG_64BIT
+	case 8:
+#endif
+		break;
+	default:
+		WARN(1, "invalid bar write size %d\n", size);
+		return;
+	}
+
+	dev->ops->bar_write(dev, bar, offset, size, val);
+}
+
 static void um_pci_bar_copy_from(void *priv, void *buffer,
 				 unsigned int offset, int size)
 {
@@ -325,53 +144,9 @@ static void um_pci_bar_copy_from(void *priv, void *buffer,
 	struct um_pci_device *dev = container_of(resptr - *resptr,
 						 struct um_pci_device,
 						 resptr[0]);
-	struct virtio_pcidev_msg hdr = {
+	u8 bar = *resptr;
-		.op = VIRTIO_PCIDEV_OP_MMIO_READ,
-		.bar = *resptr,
-		.size = size,
-		.addr = offset,
-	};
 
-	memset(buffer, 0xff, size);
+	dev->ops->bar_copy_from(dev, bar, buffer, offset, size);
-
-	um_pci_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, buffer, size);
-}
-
-static unsigned long um_pci_bar_read(void *priv, unsigned int offset,
-				     int size)
-{
-	/* 8 is maximum size - we may only use parts of it */
-	u8 data[8];
-
-	switch (size) {
-	case 1:
-	case 2:
-	case 4:
-#ifdef CONFIG_64BIT
-	case 8:
-#endif
-		break;
-	default:
-		WARN(1, "invalid config space read size %d\n", size);
-		return ULONG_MAX;
-	}
-
-	um_pci_bar_copy_from(priv, data, offset, size);
-
-	switch (size) {
-	case 1:
-		return data[0];
-	case 2:
-		return le16_to_cpup((void *)data);
-	case 4:
-		return le32_to_cpup((void *)data);
-#ifdef CONFIG_64BIT
-	case 8:
-		return le64_to_cpup((void *)data);
-#endif
-	default:
-		return ULONG_MAX;
-	}
 }
 
 static void um_pci_bar_copy_to(void *priv, unsigned int offset,
@@ -381,43 +156,9 @@ static void um_pci_bar_copy_to(void *priv, unsigned int offset,
 	struct um_pci_device *dev = container_of(resptr - *resptr,
 						 struct um_pci_device,
 						 resptr[0]);
-	struct virtio_pcidev_msg hdr = {
+	u8 bar = *resptr;
-		.op = VIRTIO_PCIDEV_OP_MMIO_WRITE,
-		.bar = *resptr,
-		.size = size,
-		.addr = offset,
-	};
 
-	um_pci_send_cmd(dev, &hdr, sizeof(hdr), buffer, size, NULL, 0);
+	dev->ops->bar_copy_to(dev, bar, offset, buffer, size);
-}
-
-static void um_pci_bar_write(void *priv, unsigned int offset, int size,
-			     unsigned long val)
-{
-	/* maximum size - we may only use parts of it */
-	u8 data[8];
-
-	switch (size) {
-	case 1:
-		data[0] = (u8)val;
-		break;
-	case 2:
-		put_unaligned_le16(val, (void *)data);
-		break;
-	case 4:
-		put_unaligned_le32(val, (void *)data);
-		break;
-#ifdef CONFIG_64BIT
-	case 8:
-		put_unaligned_le64(val, (void *)data);
-		break;
-#endif
-	default:
-		WARN(1, "invalid config space write size %d\n", size);
-		return;
-	}
-
-	um_pci_bar_copy_to(priv, offset, data, size);
 }
 
 static void um_pci_bar_set(void *priv, unsigned int offset, u8 value, int size)
@@ -426,20 +167,9 @@ static void um_pci_bar_set(void *priv, unsigned int offset, u8 value, int size)
 	struct um_pci_device *dev = container_of(resptr - *resptr,
 						 struct um_pci_device,
 						 resptr[0]);
-	struct {
+	u8 bar = *resptr;
-		struct virtio_pcidev_msg hdr;
-		u8 data;
-	} msg = {
-		.hdr = {
-			.op = VIRTIO_PCIDEV_OP_CFG_WRITE,
-			.bar = *resptr,
-			.size = size,
-			.addr = offset,
-		},
-		.data = value,
-	};
 
-	um_pci_send_cmd(dev, &msg.hdr, sizeof(msg), NULL, 0, NULL, 0);
+	dev->ops->bar_set(dev, bar, offset, value, size);
 }
 
 static const struct logic_iomem_ops um_pci_device_bar_ops = {
@@ -486,76 +216,6 @@ static void um_pci_rescan(void)
 	pci_unlock_rescan_remove();
 }
 
-static void um_pci_irq_vq_addbuf(struct virtqueue *vq, void *buf, bool kick)
-{
-	struct scatterlist sg[1];
-
-	sg_init_one(sg, buf, MAX_IRQ_MSG_SIZE);
-	if (virtqueue_add_inbuf(vq, sg, 1, buf, GFP_ATOMIC))
-		kfree(buf);
-	else if (kick)
-		virtqueue_kick(vq);
-}
-
-static void um_pci_handle_irq_message(struct virtqueue *vq,
-				      struct virtio_pcidev_msg *msg)
-{
-	struct virtio_device *vdev = vq->vdev;
-	struct um_pci_device *dev = vdev->priv;
-
-	if (!dev->irq)
-		return;
-
-	/* we should properly chain interrupts, but on ARCH=um we don't care */
-
-	switch (msg->op) {
-	case VIRTIO_PCIDEV_OP_INT:
-		generic_handle_irq(dev->irq);
-		break;
-	case VIRTIO_PCIDEV_OP_MSI:
-		/* our MSI message is just the interrupt number */
-		if (msg->size == sizeof(u32))
-			generic_handle_irq(le32_to_cpup((void *)msg->data));
-		else
-			generic_handle_irq(le16_to_cpup((void *)msg->data));
-		break;
-	case VIRTIO_PCIDEV_OP_PME:
-		/* nothing to do - we already woke up due to the message */
-		break;
-	default:
-		dev_err(&vdev->dev, "unexpected virt-pci message %d\n", msg->op);
-		break;
-	}
-}
-
-static void um_pci_cmd_vq_cb(struct virtqueue *vq)
-{
-	struct virtio_device *vdev = vq->vdev;
-	struct um_pci_device *dev = vdev->priv;
-	void *cmd;
-	int len;
-
-	if (test_bit(UM_PCI_STAT_WAITING, &dev->status))
-		return;
-
-	while ((cmd = virtqueue_get_buf(vq, &len)))
-		um_pci_free_buf(dev, cmd);
-}
-
-static void um_pci_irq_vq_cb(struct virtqueue *vq)
-{
-	struct virtio_pcidev_msg *msg;
-	int len;
-
-	while ((msg = virtqueue_get_buf(vq, &len))) {
-		if (len >= sizeof(*msg))
-			um_pci_handle_irq_message(vq, msg);
-
-		/* recycle the message buffer */
-		um_pci_irq_vq_addbuf(vq, msg, true);
-	}
-}
-
 #ifdef CONFIG_OF
 /* Copied from arch/x86/kernel/devicetree.c */
 struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus)
@@ -577,200 +237,6 @@ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus)
 }
 #endif
 
-static int um_pci_init_vqs(struct um_pci_device *dev)
-{
-	struct virtqueue_info vqs_info[] = {
-		{ "cmd", um_pci_cmd_vq_cb },
-		{ "irq", um_pci_irq_vq_cb },
-	};
-	struct virtqueue *vqs[2];
-	int err, i;
-
-	err = virtio_find_vqs(dev->vdev, 2, vqs, vqs_info, NULL);
-	if (err)
-		return err;
-
-	dev->cmd_vq = vqs[0];
-	dev->irq_vq = vqs[1];
-
-	virtio_device_ready(dev->vdev);
-
-	for (i = 0; i < NUM_IRQ_MSGS; i++) {
-		void *msg = kzalloc(MAX_IRQ_MSG_SIZE, GFP_KERNEL);
-
-		if (msg)
-			um_pci_irq_vq_addbuf(dev->irq_vq, msg, false);
-	}
-
-	virtqueue_kick(dev->irq_vq);
-
-	return 0;
-}
-
-static void __um_pci_virtio_platform_remove(struct virtio_device *vdev,
-					    struct um_pci_device *dev)
-{
-	virtio_reset_device(vdev);
-	vdev->config->del_vqs(vdev);
-
-	mutex_lock(&um_pci_mtx);
-	um_pci_platform_device = NULL;
-	mutex_unlock(&um_pci_mtx);
-
-	kfree(dev);
-}
-
-static int um_pci_virtio_platform_probe(struct virtio_device *vdev,
-					struct um_pci_device *dev)
-{
-	int ret;
-
-	dev->platform = true;
-
-	mutex_lock(&um_pci_mtx);
-
-	if (um_pci_platform_device) {
-		mutex_unlock(&um_pci_mtx);
-		ret = -EBUSY;
-		goto out_free;
-	}
-
-	ret = um_pci_init_vqs(dev);
-	if (ret) {
-		mutex_unlock(&um_pci_mtx);
-		goto out_free;
-	}
-
-	um_pci_platform_device = dev;
-
-	mutex_unlock(&um_pci_mtx);
-
-	ret = of_platform_default_populate(vdev->dev.of_node, NULL, &vdev->dev);
-	if (ret)
-		__um_pci_virtio_platform_remove(vdev, dev);
-
-	return ret;
-
-out_free:
-	kfree(dev);
-	return ret;
-}
-
-static int um_pci_virtio_probe(struct virtio_device *vdev)
-{
-	struct um_pci_device *dev;
-	int i, free = -1;
-	int err = -ENOSPC;
-
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-	if (!dev)
-		return -ENOMEM;
-
-	dev->vdev = vdev;
-	vdev->priv = dev;
-
-	if (of_device_is_compatible(vdev->dev.of_node, "simple-bus"))
-		return um_pci_virtio_platform_probe(vdev, dev);
-
-	mutex_lock(&um_pci_mtx);
-	for (i = 0; i < MAX_DEVICES; i++) {
-		if (um_pci_devices[i].dev)
-			continue;
-		free = i;
-		break;
-	}
-
-	if (free < 0)
-		goto error;
-
-	err = um_pci_init_vqs(dev);
-	if (err)
-		goto error;
-
-	dev->irq = irq_alloc_desc(numa_node_id());
-	if (dev->irq < 0) {
-		err = dev->irq;
-		goto err_reset;
-	}
-	um_pci_devices[free].dev = dev;
-	vdev->priv = dev;
-
-	mutex_unlock(&um_pci_mtx);
-
-	device_set_wakeup_enable(&vdev->dev, true);
-
-	/*
-	 * In order to do suspend-resume properly, don't allow VQs
-	 * to be suspended.
-	 */
-	virtio_uml_set_no_vq_suspend(vdev, true);
-
-	um_pci_rescan();
-	return 0;
-err_reset:
-	virtio_reset_device(vdev);
-	vdev->config->del_vqs(vdev);
-error:
-	mutex_unlock(&um_pci_mtx);
-	kfree(dev);
-	return err;
-}
-
-static void um_pci_virtio_remove(struct virtio_device *vdev)
-{
-	struct um_pci_device *dev = vdev->priv;
-	int i;
-
-	if (dev->platform) {
-		of_platform_depopulate(&vdev->dev);
-		__um_pci_virtio_platform_remove(vdev, dev);
-		return;
-	}
-
-	device_set_wakeup_enable(&vdev->dev, false);
-
-	mutex_lock(&um_pci_mtx);
-	for (i = 0; i < MAX_DEVICES; i++) {
-		if (um_pci_devices[i].dev != dev)
-			continue;
-
-		um_pci_devices[i].dev = NULL;
-		irq_free_desc(dev->irq);
-
-		break;
-	}
-	mutex_unlock(&um_pci_mtx);
-
-	if (i < MAX_DEVICES) {
-		struct pci_dev *pci_dev;
-
-		pci_dev = pci_get_slot(bridge->bus, i);
-		if (pci_dev)
-			pci_stop_and_remove_bus_device_locked(pci_dev);
-	}
-
-	/* Stop all virtqueues */
-	virtio_reset_device(vdev);
-	dev->cmd_vq = NULL;
-	dev->irq_vq = NULL;
-	vdev->config->del_vqs(vdev);
-
-	kfree(dev);
-}
-
-static struct virtio_device_id id_table[] = {
-	{ CONFIG_UML_PCI_OVER_VIRTIO_DEVICE_ID, VIRTIO_DEV_ANY_ID },
-	{ 0 },
-};
-MODULE_DEVICE_TABLE(virtio, id_table);
-
-static struct virtio_driver um_pci_virtio_driver = {
-	.driver.name = "virtio-pci",
-	.id_table = id_table,
-	.probe = um_pci_virtio_probe,
-	.remove = um_pci_virtio_remove,
-};
-
 static struct resource virt_cfgspace_resource = {
 	.name = "PCI config space",
 	.start = 0xf0000000 - MAX_DEVICES * CFG_SPACE_SIZE,
@@ -889,7 +355,7 @@ static void um_pci_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 }
 
 static struct irq_chip um_pci_msi_bottom_irq_chip = {
-	.name = "UM virtio MSI",
+	.name = "UM virtual MSI",
 	.irq_compose_msi_msg = um_pci_compose_msi_msg,
 };
 
@@ -939,7 +405,7 @@ static const struct irq_domain_ops um_pci_inner_domain_ops = {
 };
 
 static struct irq_chip um_pci_msi_irq_chip = {
-	.name = "UM virtio PCIe MSI",
+	.name = "UM virtual PCIe MSI",
 	.irq_mask = pci_msi_mask_irq,
 	.irq_unmask = pci_msi_unmask_irq,
 };
@@ -998,6 +464,78 @@ static struct resource virt_platform_resource = {
 	.flags = IORESOURCE_MEM,
 };
 
+int um_pci_device_register(struct um_pci_device *dev)
+{
+	int i, free = -1;
+	int err = 0;
+
+	mutex_lock(&um_pci_mtx);
+	for (i = 0; i < MAX_DEVICES; i++) {
+		if (um_pci_devices[i].dev)
+			continue;
+		free = i;
+		break;
+	}
+
+	if (free < 0) {
+		err = -ENOSPC;
+		goto out;
+	}
+
+	dev->irq = irq_alloc_desc(numa_node_id());
+	if (dev->irq < 0) {
+		err = dev->irq;
+		goto out;
+	}
+
+	um_pci_devices[free].dev = dev;
+
+out:
+	mutex_unlock(&um_pci_mtx);
+	if (!err)
+		um_pci_rescan();
+	return err;
+}
+
+void um_pci_device_unregister(struct um_pci_device *dev)
+{
+	int i;
+
+	mutex_lock(&um_pci_mtx);
+	for (i = 0; i < MAX_DEVICES; i++) {
+		if (um_pci_devices[i].dev != dev)
+			continue;
+		um_pci_devices[i].dev = NULL;
+		irq_free_desc(dev->irq);
+		break;
+	}
+	mutex_unlock(&um_pci_mtx);
+
+	if (i < MAX_DEVICES) {
+		struct pci_dev *pci_dev;
+
+		pci_dev = pci_get_slot(bridge->bus, i);
+		if (pci_dev)
+			pci_stop_and_remove_bus_device_locked(pci_dev);
+	}
+}
+
+int um_pci_platform_device_register(struct um_pci_device *dev)
+{
+	guard(mutex)(&um_pci_mtx);
+	if (um_pci_platform_device)
+		return -EBUSY;
+	um_pci_platform_device = dev;
+	return 0;
+}
+
+void um_pci_platform_device_unregister(struct um_pci_device *dev)
+{
+	guard(mutex)(&um_pci_mtx);
+	if (um_pci_platform_device == dev)
+		um_pci_platform_device = NULL;
+}
+
 static int __init um_pci_init(void)
 {
 	struct irq_domain_info inner_domain_info = {
@@ -1014,10 +552,6 @@ static int __init um_pci_init(void)
 	WARN_ON(logic_iomem_add_region(&virt_platform_resource,
 				       &um_pci_platform_ops));
 
-	if (WARN(CONFIG_UML_PCI_OVER_VIRTIO_DEVICE_ID < 0,
-		 "No virtio device ID configured for PCI - no PCI support\n"))
-		return 0;
-
 	bridge = pci_alloc_host_bridge(0);
 	if (!bridge) {
 		err = -ENOMEM;
@@ -1065,10 +599,8 @@ static int __init um_pci_init(void)
 	if (err)
 		goto free;
 
-	err = register_virtio_driver(&um_pci_virtio_driver);
-	if (err)
-		goto free;
 	return 0;
+
 free:
 	if (!IS_ERR_OR_NULL(um_pci_inner_domain))
 		irq_domain_remove(um_pci_inner_domain);
@@ -1080,11 +612,10 @@ static int __init um_pci_init(void)
 	}
 	return err;
 }
-module_init(um_pci_init);
+device_initcall(um_pci_init);
 
 static void __exit um_pci_exit(void)
 {
-	unregister_virtio_driver(&um_pci_virtio_driver);
 	irq_domain_remove(um_pci_msi_domain);
 	irq_domain_remove(um_pci_inner_domain);
 	pci_free_resource_list(&bridge->windows);

arch/um/drivers/virt-pci.h

@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __UM_VIRT_PCI_H
+#define __UM_VIRT_PCI_H
+
+#include <linux/pci.h>
+
+struct um_pci_device {
+	const struct um_pci_ops *ops;
+
+	/* for now just standard BARs */
+	u8 resptr[PCI_STD_NUM_BARS];
+
+	int irq;
+};
+
+struct um_pci_ops {
+	unsigned long (*cfgspace_read)(struct um_pci_device *dev,
+				       unsigned int offset, int size);
+	void (*cfgspace_write)(struct um_pci_device *dev, unsigned int offset,
+			       int size, unsigned long val);
+
+	unsigned long (*bar_read)(struct um_pci_device *dev, int bar,
+				  unsigned int offset, int size);
+	void (*bar_write)(struct um_pci_device *dev, int bar,
+			  unsigned int offset, int size, unsigned long val);
+
+	void (*bar_copy_from)(struct um_pci_device *dev, int bar, void *buffer,
+			      unsigned int offset, int size);
+	void (*bar_copy_to)(struct um_pci_device *dev, int bar,
+			    unsigned int offset, const void *buffer, int size);
+	void (*bar_set)(struct um_pci_device *dev, int bar,
+			unsigned int offset, u8 value, int size);
+};
+
+int um_pci_device_register(struct um_pci_device *dev);
+void um_pci_device_unregister(struct um_pci_device *dev);
+
+int um_pci_platform_device_register(struct um_pci_device *dev);
+void um_pci_platform_device_unregister(struct um_pci_device *dev);
+
+#endif /* __UM_VIRT_PCI_H */

arch/um/drivers/virtio_pcidev.c

@@ -0,0 +1,628 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Intel Corporation
+ * Author: Johannes Berg <johannes@sipsolutions.net>
+ */
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/logic_iomem.h>
+#include <linux/of_platform.h>
+#include <linux/irqdomain.h>
+#include <linux/virtio_pcidev.h>
+#include <linux/virtio-uml.h>
+#include <linux/delay.h>
+#include <linux/msi.h>
+#include <linux/unaligned.h>
+#include <irq_kern.h>
+
+#include "virt-pci.h"
+
+#define to_virtio_pcidev(_pdev) \
+	container_of(_pdev, struct virtio_pcidev_device, pdev)
+
+/* for MSI-X we have a 32-bit payload */
+#define MAX_IRQ_MSG_SIZE (sizeof(struct virtio_pcidev_msg) + sizeof(u32))
+#define NUM_IRQ_MSGS	10
+
+struct virtio_pcidev_message_buffer {
+	struct virtio_pcidev_msg hdr;
+	u8 data[8];
+};
+
+struct virtio_pcidev_device {
+	struct um_pci_device pdev;
+	struct virtio_device *vdev;
+
+	struct virtqueue *cmd_vq, *irq_vq;
+
+#define VIRTIO_PCIDEV_WRITE_BUFS	20
+	struct virtio_pcidev_message_buffer bufs[VIRTIO_PCIDEV_WRITE_BUFS + 1];
+	void *extra_ptrs[VIRTIO_PCIDEV_WRITE_BUFS + 1];
+	DECLARE_BITMAP(used_bufs, VIRTIO_PCIDEV_WRITE_BUFS);
+
+#define UM_PCI_STAT_WAITING	0
+	unsigned long status;
+
+	bool platform;
+};
+
+static unsigned int virtio_pcidev_max_delay_us = 40000;
+module_param_named(max_delay_us, virtio_pcidev_max_delay_us, uint, 0644);
+
+static int virtio_pcidev_get_buf(struct virtio_pcidev_device *dev, bool *posted)
+{
+	int i;
+
+	for (i = 0; i < VIRTIO_PCIDEV_WRITE_BUFS; i++) {
+		if (!test_and_set_bit(i, dev->used_bufs))
+			return i;
+	}
+
+	*posted = false;
+	return VIRTIO_PCIDEV_WRITE_BUFS;
+}
+
+static void virtio_pcidev_free_buf(struct virtio_pcidev_device *dev, void *buf)
+{
+	int i;
+
+	if (buf == &dev->bufs[VIRTIO_PCIDEV_WRITE_BUFS]) {
+		kfree(dev->extra_ptrs[VIRTIO_PCIDEV_WRITE_BUFS]);
+		dev->extra_ptrs[VIRTIO_PCIDEV_WRITE_BUFS] = NULL;
+		return;
+	}
+
+	for (i = 0; i < VIRTIO_PCIDEV_WRITE_BUFS; i++) {
+		if (buf == &dev->bufs[i]) {
+			kfree(dev->extra_ptrs[i]);
+			dev->extra_ptrs[i] = NULL;
+			WARN_ON(!test_and_clear_bit(i, dev->used_bufs));
+			return;
+		}
+	}
+
+	WARN_ON(1);
+}
+
+static int virtio_pcidev_send_cmd(struct virtio_pcidev_device *dev,
+				  struct virtio_pcidev_msg *cmd,
+				  unsigned int cmd_size,
+				  const void *extra, unsigned int extra_size,
+				  void *out, unsigned int out_size)
+{
+	struct scatterlist out_sg, extra_sg, in_sg;
+	struct scatterlist *sgs_list[] = {
+		[0] = &out_sg,
+		[1] = extra ? &extra_sg : &in_sg,
+		[2] = extra ? &in_sg : NULL,
+	};
+	struct virtio_pcidev_message_buffer *buf;
+	int delay_count = 0;
+	bool bounce_out;
+	int ret, len;
+	int buf_idx;
+	bool posted;
+
+	if (WARN_ON(cmd_size < sizeof(*cmd) || cmd_size > sizeof(*buf)))
+		return -EINVAL;
+
+	switch (cmd->op) {
+	case VIRTIO_PCIDEV_OP_CFG_WRITE:
+	case VIRTIO_PCIDEV_OP_MMIO_WRITE:
+	case VIRTIO_PCIDEV_OP_MMIO_MEMSET:
+		/* in PCI, writes are posted, so don't wait */
+		posted = !out;
+		WARN_ON(!posted);
+		break;
+	default:
+		posted = false;
+		break;
+	}
+
+	bounce_out = !posted && cmd_size <= sizeof(*cmd) &&
+		     out && out_size <= sizeof(buf->data);
+
+	buf_idx = virtio_pcidev_get_buf(dev, &posted);
+	buf = &dev->bufs[buf_idx];
+	memcpy(buf, cmd, cmd_size);
+
+	if (posted && extra && extra_size > sizeof(buf) - cmd_size) {
+		dev->extra_ptrs[buf_idx] = kmemdup(extra, extra_size,
+						   GFP_ATOMIC);
+
+		if (!dev->extra_ptrs[buf_idx]) {
+			virtio_pcidev_free_buf(dev, buf);
+			return -ENOMEM;
+		}
+		extra = dev->extra_ptrs[buf_idx];
+	} else if (extra && extra_size <= sizeof(buf) - cmd_size) {
+		memcpy((u8 *)buf + cmd_size, extra, extra_size);
+		cmd_size += extra_size;
+		extra_size = 0;
+		extra = NULL;
+		cmd = (void *)buf;
+	} else {
+		cmd = (void *)buf;
+	}
+
+	sg_init_one(&out_sg, cmd, cmd_size);
+	if (extra)
+		sg_init_one(&extra_sg, extra, extra_size);
+	/* allow stack for small buffers */
+	if (bounce_out)
+		sg_init_one(&in_sg, buf->data, out_size);
+	else if (out)
+		sg_init_one(&in_sg, out, out_size);
+
+	/* add to internal virtio queue */
+	ret = virtqueue_add_sgs(dev->cmd_vq, sgs_list,
+				extra ? 2 : 1,
+				out ? 1 : 0,
+				cmd, GFP_ATOMIC);
+	if (ret) {
+		virtio_pcidev_free_buf(dev, buf);
+		return ret;
+	}
+
+	if (posted) {
+		virtqueue_kick(dev->cmd_vq);
+		return 0;
+	}
+
+	/* kick and poll for getting a response on the queue */
+	set_bit(UM_PCI_STAT_WAITING, &dev->status);
+	virtqueue_kick(dev->cmd_vq);
+	ret = 0;
+
+	while (1) {
+		void *completed = virtqueue_get_buf(dev->cmd_vq, &len);
+
+		if (completed == buf)
+			break;
+
+		if (completed)
+			virtio_pcidev_free_buf(dev, completed);
+
+		if (WARN_ONCE(virtqueue_is_broken(dev->cmd_vq) ||
+			      ++delay_count > virtio_pcidev_max_delay_us,
+			      "um virt-pci delay: %d", delay_count)) {
+			ret = -EIO;
+			break;
+		}
+		udelay(1);
+	}
+	clear_bit(UM_PCI_STAT_WAITING, &dev->status);
+
+	if (bounce_out)
+		memcpy(out, buf->data, out_size);
+
+	virtio_pcidev_free_buf(dev, buf);
+
+	return ret;
+}
+
+static unsigned long virtio_pcidev_cfgspace_read(struct um_pci_device *pdev,
+						 unsigned int offset, int size)
+{
+	struct virtio_pcidev_device *dev = to_virtio_pcidev(pdev);
+	struct virtio_pcidev_msg hdr = {
+		.op = VIRTIO_PCIDEV_OP_CFG_READ,
+		.size = size,
+		.addr = offset,
+	};
+	/* max 8, we might not use it all */
+	u8 data[8];
+
+	memset(data, 0xff, sizeof(data));
+
+	/* size has been checked in um_pci_cfgspace_read() */
+	if (virtio_pcidev_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, data, size))
+		return ULONG_MAX;
+
+	switch (size) {
+	case 1:
+		return data[0];
+	case 2:
+		return le16_to_cpup((void *)data);
+	case 4:
+		return le32_to_cpup((void *)data);
+#ifdef CONFIG_64BIT
+	case 8:
+		return le64_to_cpup((void *)data);
+#endif
+	default:
+		return ULONG_MAX;
+	}
+}
+
+static void virtio_pcidev_cfgspace_write(struct um_pci_device *pdev,
+					 unsigned int offset, int size,
+					 unsigned long val)
+{
+	struct virtio_pcidev_device *dev = to_virtio_pcidev(pdev);
+	struct {
+		struct virtio_pcidev_msg hdr;
+		/* maximum size - we may only use parts of it */
+		u8 data[8];
+	} msg = {
+		.hdr = {
+			.op = VIRTIO_PCIDEV_OP_CFG_WRITE,
+			.size = size,
+			.addr = offset,
+		},
+	};
+
+	/* size has been checked in um_pci_cfgspace_write() */
+	switch (size) {
+	case 1:
+		msg.data[0] = (u8)val;
+		break;
+	case 2:
+		put_unaligned_le16(val, (void *)msg.data);
+		break;
+	case 4:
+		put_unaligned_le32(val, (void *)msg.data);
+		break;
+#ifdef CONFIG_64BIT
+	case 8:
+		put_unaligned_le64(val, (void *)msg.data);
+		break;
+#endif
+	}
+
+	WARN_ON(virtio_pcidev_send_cmd(dev, &msg.hdr, sizeof(msg), NULL, 0, NULL, 0));
+}
+
+static void virtio_pcidev_bar_copy_from(struct um_pci_device *pdev,
+					int bar, void *buffer,
+					unsigned int offset, int size)
+{
+	struct virtio_pcidev_device *dev = to_virtio_pcidev(pdev);
+	struct virtio_pcidev_msg hdr = {
+		.op = VIRTIO_PCIDEV_OP_MMIO_READ,
+		.bar = bar,
+		.size = size,
+		.addr = offset,
+	};
+
+	memset(buffer, 0xff, size);
+
+	virtio_pcidev_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, buffer, size);
+}
+
+static unsigned long virtio_pcidev_bar_read(struct um_pci_device *pdev, int bar,
+					    unsigned int offset, int size)
+{
+	/* 8 is maximum size - we may only use parts of it */
+	u8 data[8];
+
+	/* size has been checked in um_pci_bar_read() */
+	virtio_pcidev_bar_copy_from(pdev, bar, data, offset, size);
+
+	switch (size) {
+	case 1:
+		return data[0];
+	case 2:
+		return le16_to_cpup((void *)data);
+	case 4:
+		return le32_to_cpup((void *)data);
+#ifdef CONFIG_64BIT
+	case 8:
+		return le64_to_cpup((void *)data);
+#endif
+	default:
+		return ULONG_MAX;
+	}
+}
+
+static void virtio_pcidev_bar_copy_to(struct um_pci_device *pdev,
+				      int bar, unsigned int offset,
+				      const void *buffer, int size)
+{
+	struct virtio_pcidev_device *dev = to_virtio_pcidev(pdev);
+	struct virtio_pcidev_msg hdr = {
+		.op = VIRTIO_PCIDEV_OP_MMIO_WRITE,
+		.bar = bar,
+		.size = size,
+		.addr = offset,
+	};
+
+	virtio_pcidev_send_cmd(dev, &hdr, sizeof(hdr), buffer, size, NULL, 0);
+}
+
+static void virtio_pcidev_bar_write(struct um_pci_device *pdev, int bar,
+				    unsigned int offset, int size,
+				    unsigned long val)
+{
+	/* maximum size - we may only use parts of it */
+	u8 data[8];
+
+	/* size has been checked in um_pci_bar_write() */
+	switch (size) {
+	case 1:
+		data[0] = (u8)val;
+		break;
+	case 2:
+		put_unaligned_le16(val, (void *)data);
+		break;
+	case 4:
+		put_unaligned_le32(val, (void *)data);
+		break;
+#ifdef CONFIG_64BIT
+	case 8:
+		put_unaligned_le64(val, (void *)data);
+		break;
+#endif
+	}
+
+	virtio_pcidev_bar_copy_to(pdev, bar, offset, data, size);
+}
+
+static void virtio_pcidev_bar_set(struct um_pci_device *pdev, int bar,
+				  unsigned int offset, u8 value, int size)
+{
+	struct virtio_pcidev_device *dev = to_virtio_pcidev(pdev);
+	struct {
+		struct virtio_pcidev_msg hdr;
+		u8 data;
+	} msg = {
+		.hdr = {
+			.op = VIRTIO_PCIDEV_OP_CFG_WRITE,
+			.bar = bar,
+			.size = size,
+			.addr = offset,
+		},
+		.data = value,
+	};
+
+	virtio_pcidev_send_cmd(dev, &msg.hdr, sizeof(msg), NULL, 0, NULL, 0);
+}
+
+static const struct um_pci_ops virtio_pcidev_um_pci_ops = {
+	.cfgspace_read	= virtio_pcidev_cfgspace_read,
+	.cfgspace_write	= virtio_pcidev_cfgspace_write,
+	.bar_read	= virtio_pcidev_bar_read,
+	.bar_write	= virtio_pcidev_bar_write,
+	.bar_copy_from	= virtio_pcidev_bar_copy_from,
+	.bar_copy_to	= virtio_pcidev_bar_copy_to,
+	.bar_set	= virtio_pcidev_bar_set,
+};
+
+static void virtio_pcidev_irq_vq_addbuf(struct virtqueue *vq, void *buf, bool kick)
+{
+	struct scatterlist sg[1];
+
+	sg_init_one(sg, buf, MAX_IRQ_MSG_SIZE);
+	if (virtqueue_add_inbuf(vq, sg, 1, buf, GFP_ATOMIC))
+		kfree(buf);
+	else if (kick)
+		virtqueue_kick(vq);
+}
+
+static void virtio_pcidev_handle_irq_message(struct virtqueue *vq,
+					     struct virtio_pcidev_msg *msg)
+{
+	struct virtio_device *vdev = vq->vdev;
+	struct virtio_pcidev_device *dev = vdev->priv;
+
+	if (!dev->pdev.irq)
+		return;
+
+	/* we should properly chain interrupts, but on ARCH=um we don't care */
+
+	switch (msg->op) {
+	case VIRTIO_PCIDEV_OP_INT:
+		generic_handle_irq(dev->pdev.irq);
+		break;
+	case VIRTIO_PCIDEV_OP_MSI:
+		/* our MSI message is just the interrupt number */
+		if (msg->size == sizeof(u32))
+			generic_handle_irq(le32_to_cpup((void *)msg->data));
+		else
+			generic_handle_irq(le16_to_cpup((void *)msg->data));
+		break;
+	case VIRTIO_PCIDEV_OP_PME:
+		/* nothing to do - we already woke up due to the message */
+		break;
+	default:
+		dev_err(&vdev->dev, "unexpected virt-pci message %d\n", msg->op);
+		break;
+	}
+}
+
+static void virtio_pcidev_cmd_vq_cb(struct virtqueue *vq)
+{
+	struct virtio_device *vdev = vq->vdev;
+	struct virtio_pcidev_device *dev = vdev->priv;
+	void *cmd;
+	int len;
+
+	if (test_bit(UM_PCI_STAT_WAITING, &dev->status))
+		return;
+
+	while ((cmd = virtqueue_get_buf(vq, &len)))
+		virtio_pcidev_free_buf(dev, cmd);
+}
+
+static void virtio_pcidev_irq_vq_cb(struct virtqueue *vq)
+{
+	struct virtio_pcidev_msg *msg;
+	int len;
+
+	while ((msg = virtqueue_get_buf(vq, &len))) {
+		if (len >= sizeof(*msg))
+			virtio_pcidev_handle_irq_message(vq, msg);
+
+		/* recycle the message buffer */
+		virtio_pcidev_irq_vq_addbuf(vq, msg, true);
+	}
+}
+
+static int virtio_pcidev_init_vqs(struct virtio_pcidev_device *dev)
+{
+	struct virtqueue_info vqs_info[] = {
+		{ "cmd", virtio_pcidev_cmd_vq_cb },
+		{ "irq", virtio_pcidev_irq_vq_cb },
+	};
+	struct virtqueue *vqs[2];
+	int err, i;
+
+	err = virtio_find_vqs(dev->vdev, 2, vqs, vqs_info, NULL);
+	if (err)
+		return err;
+
+	dev->cmd_vq = vqs[0];
+	dev->irq_vq = vqs[1];
+
+	virtio_device_ready(dev->vdev);
+
+	for (i = 0; i < NUM_IRQ_MSGS; i++) {
+		void *msg = kzalloc(MAX_IRQ_MSG_SIZE, GFP_KERNEL);
+
+		if (msg)
+			virtio_pcidev_irq_vq_addbuf(dev->irq_vq, msg, false);
+	}
+
+	virtqueue_kick(dev->irq_vq);
+
+	return 0;
+}
+
+static void __virtio_pcidev_virtio_platform_remove(struct virtio_device *vdev,
+						   struct virtio_pcidev_device *dev)
+{
+	um_pci_platform_device_unregister(&dev->pdev);
+
+	virtio_reset_device(vdev);
+	vdev->config->del_vqs(vdev);
+
+	kfree(dev);
+}
+
+static int virtio_pcidev_virtio_platform_probe(struct virtio_device *vdev,
+					       struct virtio_pcidev_device *dev)
+{
+	int err;
+
+	dev->platform = true;
+
+	err = virtio_pcidev_init_vqs(dev);
+	if (err)
+		goto err_free;
+
+	err = um_pci_platform_device_register(&dev->pdev);
+	if (err)
+		goto err_reset;
+
+	err = of_platform_default_populate(vdev->dev.of_node, NULL, &vdev->dev);
+	if (err)
+		goto err_unregister;
+
+	return 0;
+
+err_unregister:
+	um_pci_platform_device_unregister(&dev->pdev);
+err_reset:
+	virtio_reset_device(vdev);
+	vdev->config->del_vqs(vdev);
+err_free:
+	kfree(dev);
+	return err;
+}
+
+static int virtio_pcidev_virtio_probe(struct virtio_device *vdev)
+{
+	struct virtio_pcidev_device *dev;
+	int err;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	dev->vdev = vdev;
+	vdev->priv = dev;
+
+	dev->pdev.ops = &virtio_pcidev_um_pci_ops;
+
+	if (of_device_is_compatible(vdev->dev.of_node, "simple-bus"))
+		return virtio_pcidev_virtio_platform_probe(vdev, dev);
+
+	err = virtio_pcidev_init_vqs(dev);
+	if (err)
+		goto err_free;
+
+	err = um_pci_device_register(&dev->pdev);
+	if (err)
+		goto err_reset;
+
+	device_set_wakeup_enable(&vdev->dev, true);
+
+	/*
+	 * In order to do suspend-resume properly, don't allow VQs
+	 * to be suspended.
+	 */
+	virtio_uml_set_no_vq_suspend(vdev, true);
+
+	return 0;
+
+err_reset:
+	virtio_reset_device(vdev);
+	vdev->config->del_vqs(vdev);
+err_free:
+	kfree(dev);
+	return err;
+}
+
+static void virtio_pcidev_virtio_remove(struct virtio_device *vdev)
+{
+	struct virtio_pcidev_device *dev = vdev->priv;
+
+	if (dev->platform) {
+		of_platform_depopulate(&vdev->dev);
+		__virtio_pcidev_virtio_platform_remove(vdev, dev);
+		return;
+	}
+
+	device_set_wakeup_enable(&vdev->dev, false);
+
+	um_pci_device_unregister(&dev->pdev);
+
+	/* Stop all virtqueues */
+	virtio_reset_device(vdev);
+	dev->cmd_vq = NULL;
+	dev->irq_vq = NULL;
+	vdev->config->del_vqs(vdev);
+
+	kfree(dev);
+}
+
+static struct virtio_device_id id_table[] = {
+	{ CONFIG_UML_PCI_OVER_VIRTIO_DEVICE_ID, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+MODULE_DEVICE_TABLE(virtio, id_table);
+
+static struct virtio_driver virtio_pcidev_virtio_driver = {
+	.driver.name = "virtio-pci",
+	.id_table = id_table,
+	.probe = virtio_pcidev_virtio_probe,
+	.remove = virtio_pcidev_virtio_remove,
+};
+
+static int __init virtio_pcidev_init(void)
+{
+	if (WARN(CONFIG_UML_PCI_OVER_VIRTIO_DEVICE_ID < 0,
+		 "No virtio device ID configured for PCI - no PCI support\n"))
+		return 0;
+
+	return register_virtio_driver(&virtio_pcidev_virtio_driver);
+}
+late_initcall(virtio_pcidev_init);
+
+static void __exit virtio_pcidev_exit(void)
+{
+	unregister_virtio_driver(&virtio_pcidev_virtio_driver);
+}
+module_exit(virtio_pcidev_exit);

arch/um/include/asm/Kbuild

@@ -13,6 +13,7 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += mcs_spinlock.h
 generic-y += mmiowb.h
+generic-y += module.h
 generic-y += module.lds.h
 generic-y += param.h
 generic-y += parport.h

arch/um/include/asm/processor-generic.h

@@ -31,6 +31,8 @@ struct thread_struct {
 		} thread;
 	} request;
 
+	void *segv_continue;
+
 	/* Contains variable sized FP registers */
 	struct pt_regs regs;
 };

arch/um/include/asm/uaccess.h

@@ -9,6 +9,7 @@
 
 #include <asm/elf.h>
 #include <linux/unaligned.h>
+#include <sysdep/faultinfo.h>
 
 #define __under_task_size(addr, size) \
 	(((unsigned long) (addr) < TASK_SIZE) && \
@@ -44,19 +45,28 @@ static inline int __access_ok(const void __user *ptr, unsigned long size)
 		 __access_ok_vsyscall(addr, size));
 }
 
-/* no pagefaults for kernel addresses in um */
 #define __get_kernel_nofault(dst, src, type, err_label)			\
 do {									\
-	*((type *)dst) = get_unaligned((type *)(src));			\
+	int __faulted;							\
-	if (0) /* make sure the label looks used to the compiler */	\
+									\
+	___backtrack_faulted(__faulted);				\
+	if (__faulted) {						\
+		*((type *)dst) = (type) 0;				\
 		goto err_label;						\
+	}								\
+	*((type *)dst) = get_unaligned((type *)(src));			\
+	current->thread.segv_continue = NULL;				\
 } while (0)
 
 #define __put_kernel_nofault(dst, src, type, err_label)			\
 do {									\
-	put_unaligned(*((type *)src), (type *)(dst));			\
+	int __faulted;							\
-	if (0) /* make sure the label looks used to the compiler */	\
+									\
+	___backtrack_faulted(__faulted);				\
+	if (__faulted)							\
 		goto err_label;						\
+	put_unaligned(*((type *)src), (type *)(dst));			\
+	current->thread.segv_continue = NULL;				\
 } while (0)
 
 #endif

arch/um/include/linux/time-internal.h

@@ -83,6 +83,8 @@ extern void time_travel_not_configured(void);
 #define time_travel_del_event(...) time_travel_not_configured()
 #endif /* CONFIG_UML_TIME_TRAVEL_SUPPORT */
 
+extern unsigned long tt_extra_sched_jiffies;
+
 /*
  * Without CONFIG_UML_TIME_TRAVEL_SUPPORT this is a linker error if used,
  * which is intentional since we really shouldn't link it in that case.

arch/um/include/shared/arch.h

@@ -12,4 +12,6 @@ extern void arch_check_bugs(void);
 extern int arch_fixup(unsigned long address, struct uml_pt_regs *regs);
 extern void arch_examine_signal(int sig, struct uml_pt_regs *regs);
 
+void mc_set_rip(void *_mc, void *target);
+
 #endif

arch/um/include/shared/as-layout.h

@@ -50,7 +50,7 @@ extern int linux_main(int argc, char **argv, char **envp);
 extern void uml_finishsetup(void);
 
 struct siginfo;
-extern void (*sig_info[])(int, struct siginfo *si, struct uml_pt_regs *);
+extern void (*sig_info[])(int, struct siginfo *si, struct uml_pt_regs *, void *);
 
 #endif
 

arch/um/include/shared/irq_user.h

@@ -15,7 +15,8 @@ enum um_irq_type {
 };
 
 struct siginfo;
-extern void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs);
+extern void sigio_handler(int sig, struct siginfo *unused_si,
+			  struct uml_pt_regs *regs, void *mc);
 void sigio_run_timetravel_handlers(void);
 extern void free_irq_by_fd(int fd);
 extern void deactivate_fd(int fd, int irqnum);

arch/um/include/shared/kern_util.h

@@ -24,10 +24,12 @@ extern void free_stack(unsigned long stack, int order);
 struct pt_regs;
 extern void do_signal(struct pt_regs *regs);
 extern void interrupt_end(void);
-extern void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs);
+extern void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs,
+			 void *mc);
 
 extern unsigned long segv(struct faultinfo fi, unsigned long ip,
-			  int is_user, struct uml_pt_regs *regs);
+			  int is_user, struct uml_pt_regs *regs,
+			  void *mc);
 extern int handle_page_fault(unsigned long address, unsigned long ip,
 			     int is_write, int is_user, int *code_out);
 
@@ -59,8 +61,10 @@ extern unsigned long from_irq_stack(int nested);
 
 extern int singlestepping(void);
 
-extern void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs);
+extern void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs,
-extern void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs);
+			 void *mc);
+extern void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs,
+		  void *mc);
 extern void fatal_sigsegv(void) __attribute__ ((noreturn));
 
 void um_idle_sleep(void);

arch/um/include/shared/os.h

@@ -213,7 +213,6 @@ extern int os_protect_memory(void *addr, unsigned long len,
 extern int os_unmap_memory(void *addr, int len);
 extern int os_drop_memory(void *addr, int length);
 extern int can_drop_memory(void);
-extern int os_mincore(void *addr, unsigned long len);
 
 void os_set_pdeathsig(void);
 
@@ -225,6 +224,11 @@ extern int run_helper_thread(int (*proc)(void *), void *arg,
 			     unsigned int flags, unsigned long *stack_out);
 extern int helper_wait(int pid);
 
+struct os_helper_thread;
+int os_run_helper_thread(struct os_helper_thread **td_out,
+			 void *(*routine)(void *), void *arg);
+void os_kill_helper_thread(struct os_helper_thread *td);
+void os_fix_helper_thread_signals(void);
 
 /* umid.c */
 extern int umid_file_name(char *name, char *buf, int len);
@@ -310,7 +314,7 @@ extern void um_irqs_resume(void);
 extern int add_sigio_fd(int fd);
 extern int ignore_sigio_fd(int fd);
 extern void maybe_sigio_broken(int fd);
-extern void sigio_broken(int fd);
+extern void sigio_broken(void);
 /*
  * unlocked versions for IRQ controller code.
  *

arch/um/include/shared/sigio.h

@@ -6,7 +6,6 @@
 #ifndef __SIGIO_H__
 #define __SIGIO_H__
 
-extern int write_sigio_irq(int fd);
 extern void sigio_lock(void);
 extern void sigio_unlock(void);
 

arch/um/kernel/Makefile

@@ -17,7 +17,7 @@ extra-y := vmlinux.lds
 obj-y = config.o exec.o exitcode.o irq.o ksyms.o mem.o \
 	physmem.o process.o ptrace.o reboot.o sigio.o \
 	signal.o sysrq.o time.o tlb.o trap.o \
-	um_arch.o umid.o maccess.o kmsg_dump.o capflags.o skas/
+	um_arch.o umid.o kmsg_dump.o capflags.o skas/
 obj-y += load_file.o
 
 obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o

arch/um/kernel/irq.c

@@ -236,7 +236,8 @@ static void _sigio_handler(struct uml_pt_regs *regs,
 		free_irqs();
 }
 
-void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
+void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs,
+		   void *mc)
 {
 	preempt_disable();
 	_sigio_handler(regs, irqs_suspended);

arch/um/kernel/maccess.c

@@ -1,19 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2013 Richard Weinberger <richrd@nod.at>
- */
-
-#include <linux/uaccess.h>
-#include <linux/kernel.h>
-#include <os.h>
-
-bool copy_from_kernel_nofault_allowed(const void *src, size_t size)
-{
-	void *psrc = (void *)rounddown((unsigned long)src, PAGE_SIZE);
-
-	if ((unsigned long)src < PAGE_SIZE || size <= 0)
-		return false;
-	if (os_mincore(psrc, size + src - psrc) <= 0)
-		return false;
-	return true;
-}

arch/um/kernel/mem.c

@@ -9,6 +9,8 @@
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
+#include <linux/init.h>
+#include <asm/sections.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <as-layout.h>
@@ -66,6 +68,7 @@ void __init arch_mm_preinit(void)
 	map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0);
 	memblock_free((void *)brk_end, uml_reserved - brk_end);
 	uml_reserved = brk_end;
+	min_low_pfn = PFN_UP(__pa(uml_reserved));
 	max_pfn = max_low_pfn;
 }
 
@@ -242,3 +245,11 @@ static const pgprot_t protection_map[16] = {
 	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= PAGE_SHARED
 };
 DECLARE_VM_GET_PAGE_PROT
+
+void mark_rodata_ro(void)
+{
+	unsigned long rodata_start = PFN_ALIGN(__start_rodata);
+	unsigned long rodata_end = PFN_ALIGN(__end_rodata);
+
+	os_protect_memory((void *)rodata_start, rodata_end - rodata_start, 1, 0, 0);
+}

arch/um/kernel/sigio.c

@@ -8,32 +8,6 @@
 #include <os.h>
 #include <sigio.h>
 
-/* Protected by sigio_lock() called from write_sigio_workaround */
-static int sigio_irq_fd = -1;
-
-static irqreturn_t sigio_interrupt(int irq, void *data)
-{
-	char c;
-
-	os_read_file(sigio_irq_fd, &c, sizeof(c));
-	return IRQ_HANDLED;
-}
-
-int write_sigio_irq(int fd)
-{
-	int err;
-
-	err = um_request_irq(SIGIO_WRITE_IRQ, fd, IRQ_READ, sigio_interrupt,
-			     0, "write sigio", NULL);
-	if (err < 0) {
-		printk(KERN_ERR "write_sigio_irq : um_request_irq failed, "
-		       "err = %d\n", err);
-		return -1;
-	}
-	sigio_irq_fd = fd;
-	return 0;
-}
-
 /* These are called from os-Linux/sigio.c to protect its pollfds arrays. */
 static DEFINE_MUTEX(sigio_mutex);
 

arch/um/kernel/skas/syscall.c

@@ -31,6 +31,17 @@ void handle_syscall(struct uml_pt_regs *r)
 		goto out;
 
 	syscall = UPT_SYSCALL_NR(r);
+
+	/*
+	 * If no time passes, then sched_yield may not actually yield, causing
+	 * broken spinlock implementations in userspace (ASAN) to hang for long
+	 * periods of time.
+	 */
+	if ((time_travel_mode == TT_MODE_INFCPU ||
+	     time_travel_mode == TT_MODE_EXTERNAL) &&
+	    syscall == __NR_sched_yield)
+		tt_extra_sched_jiffies += 1;
+
 	if (syscall >= 0 && syscall < __NR_syscalls) {
 		unsigned long ret = EXECUTE_SYSCALL(syscall, regs);
 

arch/um/kernel/trap.c

@@ -16,6 +16,7 @@
 #include <kern_util.h>
 #include <os.h>
 #include <skas.h>
+#include <arch.h>
 
 /*
  * Note this is constrained to return 0, -EFAULT, -EACCES, -ENOMEM by
@@ -175,12 +176,14 @@ void fatal_sigsegv(void)
  * @sig:	the signal number
  * @unused_si:	the signal info struct; unused in this handler
  * @regs:	the ptrace register information
+ * @mc:		the mcontext of the signal
  *
  * The handler first extracts the faultinfo from the UML ptrace regs struct.
  * If the userfault did not happen in an UML userspace process, bad_segv is called.
  * Otherwise the signal did happen in a cloned userspace process, handle it.
  */
-void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
+void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs,
+		  void *mc)
 {
 	struct faultinfo * fi = UPT_FAULTINFO(regs);
 
@@ -189,7 +192,7 @@ void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
 		bad_segv(*fi, UPT_IP(regs));
 		return;
 	}
-	segv(*fi, UPT_IP(regs), UPT_IS_USER(regs), regs);
+	segv(*fi, UPT_IP(regs), UPT_IS_USER(regs), regs, mc);
 }
 
 /*
@@ -199,7 +202,7 @@ void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
  * give us bad data!
  */
 unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
-		   struct uml_pt_regs *regs)
+		   struct uml_pt_regs *regs, void *mc)
 {
 	int si_code;
 	int err;
@@ -223,6 +226,19 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
 		goto out;
 	}
 	else if (current->mm == NULL) {
+		if (current->pagefault_disabled) {
+			if (!mc) {
+				show_regs(container_of(regs, struct pt_regs, regs));
+				panic("Segfault with pagefaults disabled but no mcontext");
+			}
+			if (!current->thread.segv_continue) {
+				show_regs(container_of(regs, struct pt_regs, regs));
+				panic("Segfault without recovery target");
+			}
+			mc_set_rip(mc, current->thread.segv_continue);
+			current->thread.segv_continue = NULL;
+			goto out;
+		}
 		show_regs(container_of(regs, struct pt_regs, regs));
 		panic("Segfault with no mm");
 	}
@@ -274,7 +290,8 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
 	return 0;
 }
 
-void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs)
+void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs,
+		  void *mc)
 {
 	int code, err;
 	if (!UPT_IS_USER(regs)) {
@@ -302,7 +319,8 @@ void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs)
 	}
 }
 
-void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
+void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs,
+	   void *mc)
 {
 	do_IRQ(WINCH_IRQ, regs);
 }

arch/um/kernel/um_arch.c

@@ -12,6 +12,7 @@
 #include <linux/panic_notifier.h>
 #include <linux/seq_file.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/utsname.h>
 #include <linux/sched.h>
 #include <linux/sched/task.h>
@@ -78,7 +79,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	seq_printf(m, "model name\t: UML\n");
 	seq_printf(m, "mode\t\t: skas\n");
 	seq_printf(m, "host\t\t: %s\n", host_info);
-	seq_printf(m, "fpu\t\t: %s\n", cpu_has(&boot_cpu_data, X86_FEATURE_FPU) ? "yes" : "no");
+	seq_printf(m, "fpu\t\t: %s\n", str_yes_no(cpu_has(&boot_cpu_data, X86_FEATURE_FPU)));
 	seq_printf(m, "flags\t\t:");
 	for (i = 0; i < 32*NCAPINTS; i++)
 		if (cpu_has(&boot_cpu_data, i) && (x86_cap_flags[i] != NULL))

arch/um/os-Linux/helper.c

@@ -8,6 +8,7 @@
 #include <unistd.h>
 #include <errno.h>
 #include <sched.h>
+#include <pthread.h>
 #include <linux/limits.h>
 #include <sys/socket.h>
 #include <sys/wait.h>
@@ -121,6 +122,10 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags,
 	unsigned long stack, sp;
 	int pid, status, err;
 
+	/* To share memory space, use os_run_helper_thread() instead. */
+	if (flags & CLONE_VM)
+		return -EINVAL;
+
 	stack = alloc_stack(0, __uml_cant_sleep());
 	if (stack == 0)
 		return -ENOMEM;
@@ -167,3 +172,65 @@ int helper_wait(int pid)
 	} else
 		return 0;
 }
+
+struct os_helper_thread {
+	pthread_t handle;
+};
+
+int os_run_helper_thread(struct os_helper_thread **td_out,
+			 void *(*routine)(void *), void *arg)
+{
+	struct os_helper_thread *td;
+	sigset_t sigset, oset;
+	int err, flags;
+
+	flags = __uml_cant_sleep() ? UM_GFP_ATOMIC : UM_GFP_KERNEL;
+	td = uml_kmalloc(sizeof(*td), flags);
+	if (!td)
+		return -ENOMEM;
+
+	sigfillset(&sigset);
+	if (sigprocmask(SIG_SETMASK, &sigset, &oset) < 0) {
+		err = -errno;
+		kfree(td);
+		return err;
+	}
+
+	err = pthread_create(&td->handle, NULL, routine, arg);
+
+	if (sigprocmask(SIG_SETMASK, &oset, NULL) < 0)
+		panic("Failed to restore the signal mask: %d", errno);
+
+	if (err != 0)
+		kfree(td);
+	else
+		*td_out = td;
+
+	return -err;
+}
+
+void os_kill_helper_thread(struct os_helper_thread *td)
+{
+	pthread_cancel(td->handle);
+	pthread_join(td->handle, NULL);
+	kfree(td);
+}
+
+void os_fix_helper_thread_signals(void)
+{
+	sigset_t sigset;
+
+	sigemptyset(&sigset);
+
+	sigaddset(&sigset, SIGWINCH);
+	sigaddset(&sigset, SIGPIPE);
+	sigaddset(&sigset, SIGPROF);
+	sigaddset(&sigset, SIGINT);
+	sigaddset(&sigset, SIGTERM);
+	sigaddset(&sigset, SIGCHLD);
+	sigaddset(&sigset, SIGALRM);
+	sigaddset(&sigset, SIGIO);
+	sigaddset(&sigset, SIGUSR1);
+
+	pthread_sigmask(SIG_SETMASK, &sigset, NULL);
+}

arch/um/os-Linux/process.c

@@ -142,57 +142,6 @@ int __init can_drop_memory(void)
 	return ok;
 }
 
-static int os_page_mincore(void *addr)
-{
-	char vec[2];
-	int ret;
-
-	ret = mincore(addr, UM_KERN_PAGE_SIZE, vec);
-	if (ret < 0) {
-		if (errno == ENOMEM || errno == EINVAL)
-			return 0;
-		else
-			return -errno;
-	}
-
-	return vec[0] & 1;
-}
-
-int os_mincore(void *addr, unsigned long len)
-{
-	char *vec;
-	int ret, i;
-
-	if (len <= UM_KERN_PAGE_SIZE)
-		return os_page_mincore(addr);
-
-	vec = calloc(1, (len + UM_KERN_PAGE_SIZE - 1) / UM_KERN_PAGE_SIZE);
-	if (!vec)
-		return -ENOMEM;
-
-	ret = mincore(addr, UM_KERN_PAGE_SIZE, vec);
-	if (ret < 0) {
-		if (errno == ENOMEM || errno == EINVAL)
-			ret = 0;
-		else
-			ret = -errno;
-
-		goto out;
-	}
-
-	for (i = 0; i < ((len + UM_KERN_PAGE_SIZE - 1) / UM_KERN_PAGE_SIZE); i++) {
-		if (!(vec[i] & 1)) {
-			ret = 0;
-			goto out;
-		}
-	}
-
-	ret = 1;
-out:
-	free(vec);
-	return ret;
-}
-
 void init_new_thread_signals(void)
 {
 	set_handler(SIGSEGV);

arch/um/os-Linux/sigio.c

@@ -11,6 +11,7 @@
 #include <sched.h>
 #include <signal.h>
 #include <string.h>
+#include <sys/epoll.h>
 #include <kern_util.h>
 #include <init.h>
 #include <os.h>
@@ -21,184 +22,51 @@
  * Protected by sigio_lock(), also used by sigio_cleanup, which is an
  * exitcall.
  */
-static int write_sigio_pid = -1;
+static struct os_helper_thread *write_sigio_td;
-static unsigned long write_sigio_stack;
 
-/*
+static int epollfd = -1;
- * These arrays are initialized before the sigio thread is started, and
- * the descriptors closed after it is killed.  So, it can't see them change.
- * On the UML side, they are changed under the sigio_lock.
- */
-#define SIGIO_FDS_INIT {-1, -1}
 
-static int write_sigio_fds[2] = SIGIO_FDS_INIT;
+#define MAX_EPOLL_EVENTS 64
-static int sigio_private[2] = SIGIO_FDS_INIT;
 
-struct pollfds {
+static struct epoll_event epoll_events[MAX_EPOLL_EVENTS];
-	struct pollfd *poll;
-	int size;
-	int used;
-};
 
-/*
+static void *write_sigio_thread(void *unused)
- * Protected by sigio_lock().  Used by the sigio thread, but the UML thread
- * synchronizes with it.
- */
-static struct pollfds current_poll;
-static struct pollfds next_poll;
-static struct pollfds all_sigio_fds;
-
-static int write_sigio_thread(void *unused)
 {
-	struct pollfds *fds, tmp;
+	int pid = getpid();
-	struct pollfd *p;
+	int r;
-	int i, n, respond_fd;
+
-	char c;
+	os_fix_helper_thread_signals();
 
-	os_set_pdeathsig();
-	os_fix_helper_signals();
-	fds = &current_poll;
 	while (1) {
-		n = poll(fds->poll, fds->used, -1);
+		r = epoll_wait(epollfd, epoll_events, MAX_EPOLL_EVENTS, -1);
-		if (n < 0) {
+		if (r < 0) {
 			if (errno == EINTR)
 				continue;
-			printk(UM_KERN_ERR "write_sigio_thread : poll returned "
+			printk(UM_KERN_ERR "%s: epoll_wait failed, errno = %d\n",
-			       "%d, errno = %d\n", n, errno);
+			       __func__, errno);
 		}
-		for (i = 0; i < fds->used; i++) {
-			p = &fds->poll[i];
-			if (p->revents == 0)
-				continue;
-			if (p->fd == sigio_private[1]) {
-				CATCH_EINTR(n = read(sigio_private[1], &c,
-						     sizeof(c)));
-				if (n != sizeof(c))
-					printk(UM_KERN_ERR
-					       "write_sigio_thread : "
-					       "read on socket failed, "
-					       "err = %d\n", errno);
-				tmp = current_poll;
-				current_poll = next_poll;
-				next_poll = tmp;
-				respond_fd = sigio_private[1];
-			}
-			else {
-				respond_fd = write_sigio_fds[1];
-				fds->used--;
-				memmove(&fds->poll[i], &fds->poll[i + 1],
-					(fds->used - i) * sizeof(*fds->poll));
-			}
 
-			CATCH_EINTR(n = write(respond_fd, &c, sizeof(c)));
+		CATCH_EINTR(r = tgkill(pid, pid, SIGIO));
-			if (n != sizeof(c))
+		if (r < 0)
-				printk(UM_KERN_ERR "write_sigio_thread : "
+			printk(UM_KERN_ERR "%s: tgkill failed, errno = %d\n",
-				       "write on socket failed, err = %d\n",
+			       __func__, errno);
-				       errno);
-		}
 	}
 
-	return 0;
+	return NULL;
-}
-
-static int need_poll(struct pollfds *polls, int n)
-{
-	struct pollfd *new;
-
-	if (n <= polls->size)
-		return 0;
-
-	new = uml_kmalloc(n * sizeof(struct pollfd), UM_GFP_ATOMIC);
-	if (new == NULL) {
-		printk(UM_KERN_ERR "need_poll : failed to allocate new "
-		       "pollfds\n");
-		return -ENOMEM;
-	}
-
-	memcpy(new, polls->poll, polls->used * sizeof(struct pollfd));
-	kfree(polls->poll);
-
-	polls->poll = new;
-	polls->size = n;
-	return 0;
-}
-
-/*
- * Must be called with sigio_lock held, because it's needed by the marked
- * critical section.
- */
-static void update_thread(void)
-{
-	unsigned long flags;
-	int n;
-	char c;
-
-	flags = um_set_signals_trace(0);
-	CATCH_EINTR(n = write(sigio_private[0], &c, sizeof(c)));
-	if (n != sizeof(c)) {
-		printk(UM_KERN_ERR "update_thread : write failed, err = %d\n",
-		       errno);
-		goto fail;
-	}
-
-	CATCH_EINTR(n = read(sigio_private[0], &c, sizeof(c)));
-	if (n != sizeof(c)) {
-		printk(UM_KERN_ERR "update_thread : read failed, err = %d\n",
-		       errno);
-		goto fail;
-	}
-
-	um_set_signals_trace(flags);
-	return;
- fail:
-	/* Critical section start */
-	if (write_sigio_pid != -1) {
-		os_kill_process(write_sigio_pid, 1);
-		free_stack(write_sigio_stack, 0);
-	}
-	write_sigio_pid = -1;
-	close(sigio_private[0]);
-	close(sigio_private[1]);
-	close(write_sigio_fds[0]);
-	close(write_sigio_fds[1]);
-	/* Critical section end */
-	um_set_signals_trace(flags);
 }
 
 int __add_sigio_fd(int fd)
 {
-	struct pollfd *p;
+	struct epoll_event event = {
-	int err, i, n;
+		.data.fd = fd,
+		.events = EPOLLIN | EPOLLET,
+	};
+	int r;
 
-	for (i = 0; i < all_sigio_fds.used; i++) {
+	CATCH_EINTR(r = epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &event));
-		if (all_sigio_fds.poll[i].fd == fd)
+	return r < 0 ? -errno : 0;
-			break;
-	}
-	if (i == all_sigio_fds.used)
-		return -ENOSPC;
-
-	p = &all_sigio_fds.poll[i];
-
-	for (i = 0; i < current_poll.used; i++) {
-		if (current_poll.poll[i].fd == fd)
-			return 0;
-	}
-
-	n = current_poll.used;
-	err = need_poll(&next_poll, n + 1);
-	if (err)
-		return err;
-
-	memcpy(next_poll.poll, current_poll.poll,
-	       current_poll.used * sizeof(struct pollfd));
-	next_poll.poll[n] = *p;
-	next_poll.used = n + 1;
-	update_thread();
-
-	return 0;
 }
 
-
 int add_sigio_fd(int fd)
 {
 	int err;
@@ -212,38 +80,11 @@ int add_sigio_fd(int fd)
 
 int __ignore_sigio_fd(int fd)
 {
-	struct pollfd *p;
+	struct epoll_event event;
-	int err, i, n = 0;
+	int r;
 
-	/*
+	CATCH_EINTR(r = epoll_ctl(epollfd, EPOLL_CTL_DEL, fd, &event));
-	 * This is called from exitcalls elsewhere in UML - if
+	return r < 0 ? -errno : 0;
-	 * sigio_cleanup has already run, then update_thread will hang
-	 * or fail because the thread is no longer running.
-	 */
-	if (write_sigio_pid == -1)
-		return -EIO;
-
-	for (i = 0; i < current_poll.used; i++) {
-		if (current_poll.poll[i].fd == fd)
-			break;
-	}
-	if (i == current_poll.used)
-		return -ENOENT;
-
-	err = need_poll(&next_poll, current_poll.used - 1);
-	if (err)
-		return err;
-
-	for (i = 0; i < current_poll.used; i++) {
-		p = &current_poll.poll[i];
-		if (p->fd != fd)
-			next_poll.poll[n++] = *p;
-	}
-	next_poll.used = current_poll.used - 1;
-
-	update_thread();
-
-	return 0;
 }
 
 int ignore_sigio_fd(int fd)
@@ -257,127 +98,39 @@ int ignore_sigio_fd(int fd)
 	return err;
 }
 
-static struct pollfd *setup_initial_poll(int fd)
-{
-	struct pollfd *p;
-
-	p = uml_kmalloc(sizeof(struct pollfd), UM_GFP_KERNEL);
-	if (p == NULL) {
-		printk(UM_KERN_ERR "setup_initial_poll : failed to allocate "
-		       "poll\n");
-		return NULL;
-	}
-	*p = ((struct pollfd) { .fd		= fd,
-				.events 	= POLLIN,
-				.revents 	= 0 });
-	return p;
-}
-
 static void write_sigio_workaround(void)
-{
-	struct pollfd *p;
-	int err;
-	int l_write_sigio_fds[2];
-	int l_sigio_private[2];
-	int l_write_sigio_pid;
-
-	/* We call this *tons* of times - and most ones we must just fail. */
-	sigio_lock();
-	l_write_sigio_pid = write_sigio_pid;
-	sigio_unlock();
-
-	if (l_write_sigio_pid != -1)
-		return;
-
-	err = os_pipe(l_write_sigio_fds, 1, 1);
-	if (err < 0) {
-		printk(UM_KERN_ERR "write_sigio_workaround - os_pipe 1 failed, "
-		       "err = %d\n", -err);
-		return;
-	}
-	err = os_pipe(l_sigio_private, 1, 1);
-	if (err < 0) {
-		printk(UM_KERN_ERR "write_sigio_workaround - os_pipe 2 failed, "
-		       "err = %d\n", -err);
-		goto out_close1;
-	}
-
-	p = setup_initial_poll(l_sigio_private[1]);
-	if (!p)
-		goto out_close2;
-
-	sigio_lock();
-
-	/*
-	 * Did we race? Don't try to optimize this, please, it's not so likely
-	 * to happen, and no more than once at the boot.
-	 */
-	if (write_sigio_pid != -1)
-		goto out_free;
-
-	current_poll = ((struct pollfds) { .poll 	= p,
-					   .used 	= 1,
-					   .size 	= 1 });
-
-	if (write_sigio_irq(l_write_sigio_fds[0]))
-		goto out_clear_poll;
-
-	memcpy(write_sigio_fds, l_write_sigio_fds, sizeof(l_write_sigio_fds));
-	memcpy(sigio_private, l_sigio_private, sizeof(l_sigio_private));
-
-	write_sigio_pid = run_helper_thread(write_sigio_thread, NULL,
-					    CLONE_FILES | CLONE_VM,
-					    &write_sigio_stack);
-
-	if (write_sigio_pid < 0)
-		goto out_clear;
-
-	sigio_unlock();
-	return;
-
-out_clear:
-	write_sigio_pid = -1;
-	write_sigio_fds[0] = -1;
-	write_sigio_fds[1] = -1;
-	sigio_private[0] = -1;
-	sigio_private[1] = -1;
-out_clear_poll:
-	current_poll = ((struct pollfds) { .poll	= NULL,
-					   .size	= 0,
-					   .used	= 0 });
-out_free:
-	sigio_unlock();
-	kfree(p);
-out_close2:
-	close(l_sigio_private[0]);
-	close(l_sigio_private[1]);
-out_close1:
-	close(l_write_sigio_fds[0]);
-	close(l_write_sigio_fds[1]);
-}
-
-void sigio_broken(int fd)
 {
 	int err;
 
-	write_sigio_workaround();
-
 	sigio_lock();
-	err = need_poll(&all_sigio_fds, all_sigio_fds.used + 1);
+	if (write_sigio_td)
-	if (err) {
+		goto out;
-		printk(UM_KERN_ERR "maybe_sigio_broken - failed to add pollfd "
+
-		       "for descriptor %d\n", fd);
+	epollfd = epoll_create(MAX_EPOLL_EVENTS);
+	if (epollfd < 0) {
+		printk(UM_KERN_ERR "%s: epoll_create failed, errno = %d\n",
+		       __func__, errno);
+		goto out;
+	}
+
+	err = os_run_helper_thread(&write_sigio_td, write_sigio_thread, NULL);
+	if (err < 0) {
+		printk(UM_KERN_ERR "%s: os_run_helper_thread failed, errno = %d\n",
+		       __func__, -err);
+		close(epollfd);
+		epollfd = -1;
 		goto out;
 	}
 
-	all_sigio_fds.poll[all_sigio_fds.used++] =
-		((struct pollfd) { .fd  	= fd,
-				   .events 	= POLLIN,
-				   .revents 	= 0 });
 out:
 	sigio_unlock();
 }
 
+void sigio_broken(void)
+{
+	write_sigio_workaround();
+}
+
 /* Changed during early boot */
 static int pty_output_sigio;
 
@@ -389,17 +142,16 @@ void maybe_sigio_broken(int fd)
 	if (pty_output_sigio)
 		return;
 
-	sigio_broken(fd);
+	sigio_broken();
 }
 
 static void sigio_cleanup(void)
 {
-	if (write_sigio_pid == -1)
+	if (!write_sigio_td)
 		return;
 
-	os_kill_process(write_sigio_pid, 1);
+	os_kill_helper_thread(write_sigio_td);
-	free_stack(write_sigio_stack, 0);
+	write_sigio_td = NULL;
-	write_sigio_pid = -1;
 }
 
 __uml_exitcall(sigio_cleanup);

arch/um/os-Linux/signal.c

@@ -21,7 +21,7 @@
 #include <sys/ucontext.h>
 #include <timetravel.h>
 
-void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *) = {
+void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *, void *mc) = {
 	[SIGTRAP]	= relay_signal,
 	[SIGFPE]	= relay_signal,
 	[SIGILL]	= relay_signal,
@@ -47,7 +47,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
 	if ((sig != SIGIO) && (sig != SIGWINCH))
 		unblock_signals_trace();
 
-	(*sig_info[sig])(sig, si, &r);
+	(*sig_info[sig])(sig, si, &r, mc);
 
 	errno = save_errno;
 }

arch/um/os-Linux/skas/process.c

@@ -166,7 +166,7 @@ static void get_skas_faultinfo(int pid, struct faultinfo *fi)
 static void handle_segv(int pid, struct uml_pt_regs *regs)
 {
 	get_skas_faultinfo(pid, &regs->faultinfo);
-	segv(regs->faultinfo, 0, 1, NULL);
+	segv(regs->faultinfo, 0, 1, NULL, NULL);
 }
 
 static void handle_trap(int pid, struct uml_pt_regs *regs)
@@ -525,7 +525,7 @@ void userspace(struct uml_pt_regs *regs)
 					get_skas_faultinfo(pid,
 							   &regs->faultinfo);
 					(*sig_info[SIGSEGV])(SIGSEGV, (struct siginfo *)&si,
-							     regs);
+							     regs, NULL);
 				}
 				else handle_segv(pid, regs);
 				break;
@@ -533,7 +533,7 @@ void userspace(struct uml_pt_regs *regs)
 				handle_trap(pid, regs);
 				break;
 			case SIGTRAP:
-				relay_signal(SIGTRAP, (struct siginfo *)&si, regs);
+				relay_signal(SIGTRAP, (struct siginfo *)&si, regs, NULL);
 				break;
 			case SIGALRM:
 				break;
@@ -543,7 +543,7 @@ void userspace(struct uml_pt_regs *regs)
 			case SIGFPE:
 			case SIGWINCH:
 				block_signals_trace();
-				(*sig_info[sig])(sig, (struct siginfo *)&si, regs);
+				(*sig_info[sig])(sig, (struct siginfo *)&si, regs, NULL);
 				unblock_signals_trace();
 				break;
 			default:

arch/x86/Makefile.um

@@ -7,12 +7,13 @@ core-y += arch/x86/crypto/
 # GCC versions < 11. See:
 # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=99652
 #
-ifeq ($(CONFIG_CC_IS_CLANG),y)
+ifeq ($(call gcc-min-version, 110000)$(CONFIG_CC_IS_CLANG),y)
-KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx
+KBUILD_CFLAGS +=  -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx
-KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json
 KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2
 endif
 
+KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json
+
 ifeq ($(CONFIG_X86_32),y)
 START := 0x8048000
 

arch/x86/um/asm/barrier.h

@@ -12,9 +12,9 @@
  */
 #ifdef CONFIG_X86_32
 
-#define mb()	alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
+#define mb()	alternative("lock addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb()	alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
+#define rmb()	alternative("lock addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb()	alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+#define wmb()	alternative("lock addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
 
 #else /* CONFIG_X86_32 */
 

arch/x86/um/asm/module.h

@@ -1,24 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __UM_MODULE_H
-#define __UM_MODULE_H
-
-/* UML is simple */
-struct mod_arch_specific
-{
-};
-
-#ifdef CONFIG_X86_32
-
-#define Elf_Shdr Elf32_Shdr
-#define Elf_Sym Elf32_Sym
-#define Elf_Ehdr Elf32_Ehdr
-
-#else
-
-#define Elf_Shdr Elf64_Shdr
-#define Elf_Sym Elf64_Sym
-#define Elf_Ehdr Elf64_Ehdr
-
-#endif
-
-#endif

arch/x86/um/os-Linux/mcontext.c

@@ -4,6 +4,7 @@
 #include <asm/ptrace.h>
 #include <sysdep/ptrace.h>
 #include <sysdep/mcontext.h>
+#include <arch.h>
 
 void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc)
 {
@@ -27,7 +28,17 @@ void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc)
 	COPY(RIP);
 	COPY2(EFLAGS, EFL);
 	COPY2(CS, CSGSFS);
-	regs->gp[CS / sizeof(unsigned long)] &= 0xffff;
+	regs->gp[SS / sizeof(unsigned long)] = mc->gregs[REG_CSGSFS] >> 48;
-	regs->gp[CS / sizeof(unsigned long)] |= 3;
+#endif
+}
+
+void mc_set_rip(void *_mc, void *target)
+{
+	mcontext_t *mc = _mc;
+
+#ifdef __i386__
+	mc->gregs[REG_EIP] = (unsigned long)target;
+#else
+	mc->gregs[REG_RIP] = (unsigned long)target;
 #endif
 }

arch/x86/um/shared/sysdep/faultinfo_32.h

@@ -29,4 +29,16 @@ struct faultinfo {
 
 #define PTRACE_FULL_FAULTINFO 0
 
+#define ___backtrack_faulted(_faulted)					\
+	asm volatile (							\
+		"mov $0, %0\n"						\
+		"movl $__get_kernel_nofault_faulted_%=,%1\n"		\
+		"jmp _end_%=\n"						\
+		"__get_kernel_nofault_faulted_%=:\n"			\
+		"mov $1, %0;"						\
+		"_end_%=:"						\
+		: "=r" (_faulted),					\
+		  "=m" (current->thread.segv_continue) ::		\
+	)
+
 #endif

arch/x86/um/shared/sysdep/faultinfo_64.h

@@ -29,4 +29,16 @@ struct faultinfo {
 
 #define PTRACE_FULL_FAULTINFO 1
 
+#define ___backtrack_faulted(_faulted)					\
+	asm volatile (							\
+		"mov $0, %0\n"						\
+		"movq $__get_kernel_nofault_faulted_%=,%1\n"		\
+		"jmp _end_%=\n"						\
+		"__get_kernel_nofault_faulted_%=:\n"			\
+		"mov $1, %0;"						\
+		"_end_%=:"						\
+		: "=r" (_faulted),					\
+		  "=m" (current->thread.segv_continue) ::		\
+	)
+
 #endif

arch/x86/um/vdso/vma.c

@@ -12,33 +12,22 @@
 
 static unsigned int __read_mostly vdso_enabled = 1;
 unsigned long um_vdso_addr;
+static struct page *um_vdso;
 
 extern unsigned long task_size;
 extern char vdso_start[], vdso_end[];
 
-static struct page **vdsop;
-
 static int __init init_vdso(void)
 {
-	struct page *um_vdso;
-
 	BUG_ON(vdso_end - vdso_start > PAGE_SIZE);
 
 	um_vdso_addr = task_size - PAGE_SIZE;
 
-	vdsop = kmalloc(sizeof(struct page *), GFP_KERNEL);
-	if (!vdsop)
-		goto oom;
-
 	um_vdso = alloc_page(GFP_KERNEL);
-	if (!um_vdso) {
+	if (!um_vdso)
-		kfree(vdsop);
-
 		goto oom;
-	}
 
 	copy_page(page_address(um_vdso), vdso_start);
-	*vdsop = um_vdso;
 
 	return 0;
 
@@ -56,6 +45,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	struct mm_struct *mm = current->mm;
 	static struct vm_special_mapping vdso_mapping = {
 		.name = "[vdso]",
+		.pages = &um_vdso,
 	};
 
 	if (!vdso_enabled)
@@ -64,7 +54,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 
-	vdso_mapping.pages = vdsop;
 	vma = _install_special_mapping(mm, um_vdso_addr, PAGE_SIZE,
 		VM_READ|VM_EXEC|
 		VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,

fs/hostfs/hostfs.h

@@ -60,7 +60,7 @@ struct hostfs_stat {
 	unsigned int uid;
 	unsigned int gid;
 	unsigned long long size;
-	struct hostfs_timespec atime, mtime, ctime;
+	struct hostfs_timespec atime, mtime, ctime, btime;
 	unsigned int blksize;
 	unsigned long long blocks;
 	struct {

fs/hostfs/hostfs_kern.c

@@ -33,6 +33,7 @@ struct hostfs_inode_info {
 	struct inode vfs_inode;
 	struct mutex open_mutex;
 	dev_t dev;
+	struct hostfs_timespec btime;
 };
 
 static inline struct hostfs_inode_info *HOSTFS_I(struct inode *inode)
@@ -547,6 +548,7 @@ static int hostfs_inode_set(struct inode *ino, void *data)
 	}
 
 	HOSTFS_I(ino)->dev = dev;
+	HOSTFS_I(ino)->btime = st->btime;
 	ino->i_ino = st->ino;
 	ino->i_mode = st->mode;
 	return hostfs_inode_update(ino, st);
@@ -557,7 +559,10 @@ static int hostfs_inode_test(struct inode *inode, void *data)
 	const struct hostfs_stat *st = data;
 	dev_t dev = MKDEV(st->dev.maj, st->dev.min);
 
-	return inode->i_ino == st->ino && HOSTFS_I(inode)->dev == dev;
+	return inode->i_ino == st->ino && HOSTFS_I(inode)->dev == dev &&
+	       (inode->i_mode & S_IFMT) == (st->mode & S_IFMT) &&
+	       HOSTFS_I(inode)->btime.tv_sec == st->btime.tv_sec &&
+	       HOSTFS_I(inode)->btime.tv_nsec == st->btime.tv_nsec;
 }
 
 static struct inode *hostfs_iget(struct super_block *sb, char *name)

fs/hostfs/hostfs_user.c

@@ -18,39 +18,48 @@
 #include "hostfs.h"
 #include <utime.h>
 
-static void stat64_to_hostfs(const struct stat64 *buf, struct hostfs_stat *p)
+static void statx_to_hostfs(const struct statx *buf, struct hostfs_stat *p)
 {
-	p->ino = buf->st_ino;
+	p->ino = buf->stx_ino;
-	p->mode = buf->st_mode;
+	p->mode = buf->stx_mode;
-	p->nlink = buf->st_nlink;
+	p->nlink = buf->stx_nlink;
-	p->uid = buf->st_uid;
+	p->uid = buf->stx_uid;
-	p->gid = buf->st_gid;
+	p->gid = buf->stx_gid;
-	p->size = buf->st_size;
+	p->size = buf->stx_size;
-	p->atime.tv_sec = buf->st_atime;
+	p->atime.tv_sec = buf->stx_atime.tv_sec;
-	p->atime.tv_nsec = 0;
+	p->atime.tv_nsec = buf->stx_atime.tv_nsec;
-	p->ctime.tv_sec = buf->st_ctime;
+	p->ctime.tv_sec = buf->stx_ctime.tv_sec;
-	p->ctime.tv_nsec = 0;
+	p->ctime.tv_nsec = buf->stx_ctime.tv_nsec;
-	p->mtime.tv_sec = buf->st_mtime;
+	p->mtime.tv_sec = buf->stx_mtime.tv_sec;
-	p->mtime.tv_nsec = 0;
+	p->mtime.tv_nsec = buf->stx_mtime.tv_nsec;
-	p->blksize = buf->st_blksize;
+	if (buf->stx_mask & STATX_BTIME) {
-	p->blocks = buf->st_blocks;
+		p->btime.tv_sec = buf->stx_btime.tv_sec;
-	p->rdev.maj = os_major(buf->st_rdev);
+		p->btime.tv_nsec = buf->stx_btime.tv_nsec;
-	p->rdev.min = os_minor(buf->st_rdev);
+	} else {
-	p->dev.maj = os_major(buf->st_dev);
+		memset(&p->btime, 0, sizeof(p->btime));
-	p->dev.min = os_minor(buf->st_dev);
+	}
+	p->blksize = buf->stx_blksize;
+	p->blocks = buf->stx_blocks;
+	p->rdev.maj = buf->stx_rdev_major;
+	p->rdev.min = buf->stx_rdev_minor;
+	p->dev.maj = buf->stx_dev_major;
+	p->dev.min = buf->stx_dev_minor;
 }
 
 int stat_file(const char *path, struct hostfs_stat *p, int fd)
 {
-	struct stat64 buf;
+	struct statx buf;
+	int flags = AT_SYMLINK_NOFOLLOW;
 
 	if (fd >= 0) {
-		if (fstat64(fd, &buf) < 0)
+		flags |= AT_EMPTY_PATH;
-			return -errno;
+		path = "";
-	} else if (lstat64(path, &buf) < 0) {
-		return -errno;
 	}
-	stat64_to_hostfs(&buf, p);
+
+	if ((statx(fd, path, flags, STATX_BASIC_STATS | STATX_BTIME, &buf)) < 0)
+		return -errno;
+
+	statx_to_hostfs(&buf, p);
 	return 0;
 }