Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/um/drivers/Kconfig b/arch/um/drivers/Kconfig
index 388096f..2e7b8e0 100644
--- a/arch/um/drivers/Kconfig
+++ b/arch/um/drivers/Kconfig
@@ -147,7 +147,7 @@
make use of UML networking.
config UML_NET_ETHERTAP
- bool "Ethertap transport"
+ bool "Ethertap transport (obsolete)"
depends on UML_NET
help
The Ethertap User-Mode Linux network transport allows a single
@@ -167,14 +167,13 @@
has examples of the UML command line to use to enable Ethertap
networking.
- If you'd like to set up an IP network with the host and/or the
- outside world, say Y to this, the Daemon Transport and/or the
- Slip Transport. You'll need at least one of them, but may choose
- more than one without conflict. If you don't need UML networking,
- say N.
+ NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
+ migrate to UML_NET_VECTOR.
+
+ If unsure, say N.
config UML_NET_TUNTAP
- bool "TUN/TAP transport"
+ bool "TUN/TAP transport (obsolete)"
depends on UML_NET
help
The UML TUN/TAP network transport allows a UML instance to exchange
@@ -185,8 +184,13 @@
To use this transport, your host kernel must have support for TUN/TAP
devices, either built-in or as a module.
+ NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
+ migrate to UML_NET_VECTOR.
+
+ If unsure, say N.
+
config UML_NET_SLIP
- bool "SLIP transport"
+ bool "SLIP transport (obsolete)"
depends on UML_NET
help
The slip User-Mode Linux network transport allows a running UML to
@@ -201,16 +205,13 @@
has examples of the UML command line to use to enable slip
networking, and details of a few quirks with it.
- The Ethertap Transport is preferred over slip because of its
- limitations. If you prefer slip, however, say Y here. Otherwise
- choose the Multicast transport (to network multiple UMLs on
- multiple hosts), Ethertap (to network with the host and the
- outside world), and/or the Daemon transport (to network multiple
- UMLs on a single host). You may choose more than one without
- conflict. If you don't need UML networking, say N.
+ NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
+ migrate to UML_NET_VECTOR.
+
+ If unsure, say N.
config UML_NET_DAEMON
- bool "Daemon transport"
+ bool "Daemon transport (obsolete)"
depends on UML_NET
help
This User-Mode Linux network transport allows one or more running
@@ -225,17 +226,15 @@
has examples of the UML command line to use to enable Daemon
networking.
- If you'd like to set up a network with other UMLs on a single host,
- say Y. If you need a network between UMLs on multiple physical
- hosts, choose the Multicast Transport. To set up a network with
- the host and/or other IP machines, say Y to the Ethertap or Slip
- transports. You'll need at least one of them, but may choose
- more than one without conflict. If you don't need UML networking,
- say N.
+ NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
+ migrate to UML_NET_VECTOR.
+
+ If unsure, say N.
config UML_NET_VECTOR
bool "Vector I/O high performance network devices"
depends on UML_NET
+ select MAY_HAVE_RUNTIME_DEPS
help
This User-Mode Linux network driver uses multi-message send
and receive functions. The host running the UML guest must have
@@ -245,8 +244,9 @@
drivers.
config UML_NET_VDE
- bool "VDE transport"
+ bool "VDE transport (obsolete)"
depends on UML_NET
+ select MAY_HAVE_RUNTIME_DEPS
help
This User-Mode Linux network transport allows one or more running
UMLs on a single host to communicate with each other and also
@@ -263,11 +263,13 @@
That site has a good overview of what VDE is and also examples
of the UML command line to use to enable VDE networking.
- If you need UML networking with VDE,
- say Y.
+ NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
+ migrate to UML_NET_VECTOR.
+
+ If unsure, say N.
config UML_NET_MCAST
- bool "Multicast transport"
+ bool "Multicast transport (obsolete)"
depends on UML_NET
help
This Multicast User-Mode Linux network transport allows multiple
@@ -284,16 +286,15 @@
has examples of the UML command line to use to enable Multicast
networking, and notes about the security of this approach.
- If you need UMLs on multiple physical hosts to communicate as if
- they shared an Ethernet network, say Y. If you need to communicate
- with other IP machines, make sure you select one of the other
- transports (possibly in addition to Multicast; they're not
- exclusive). If you don't need to network UMLs say N to each of
- the transports.
+ NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
+ migrate to UML_NET_VECTOR.
+
+ If unsure, say N.
config UML_NET_PCAP
- bool "pcap transport"
+ bool "pcap transport (obsolete)"
depends on UML_NET
+ select MAY_HAVE_RUNTIME_DEPS
help
The pcap transport makes a pcap packet stream on the host look
like an ethernet device inside UML. This is useful for making
@@ -304,11 +305,13 @@
<http://user-mode-linux.sourceforge.net/old/networking.html> That site
has examples of the UML command line to use to enable this option.
- If you intend to use UML as a network monitor for the host, say
- Y here. Otherwise, say N.
+ NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
+ migrate to UML_NET_VECTOR.
+
+ If unsure, say N.
config UML_NET_SLIRP
- bool "SLiRP transport"
+ bool "SLiRP transport (obsolete)"
depends on UML_NET
help
The SLiRP User-Mode Linux network transport allows a running UML
@@ -328,9 +331,10 @@
that of a host behind a firewall that masquerades all network
connections passing through it (but is less secure).
- To use this you should first have slirp compiled somewhere
- accessible on the host, and have read its documentation. If you
- don't need UML networking, say N.
+ NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
+ migrate to UML_NET_VECTOR.
+
+ If unsure, say N.
Startup example: "eth0=slirp,FE:FD:01:02:03:04,/usr/local/bin/slirp"
diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile
index a290821..2a249f6 100644
--- a/arch/um/drivers/Makefile
+++ b/arch/um/drivers/Makefile
@@ -18,9 +18,9 @@
port-objs := port_kern.o port_user.o
harddog-objs := harddog_kern.o harddog_user.o
-LDFLAGS_pcap.o := -r $(shell $(CC) $(KBUILD_CFLAGS) -print-file-name=libpcap.a)
+LDFLAGS_pcap.o = $(shell $(CC) $(KBUILD_CFLAGS) -print-file-name=libpcap.a)
-LDFLAGS_vde.o := -r $(shell $(CC) $(CFLAGS) -print-file-name=libvdeplug.a)
+LDFLAGS_vde.o = $(shell $(CC) $(CFLAGS) -print-file-name=libvdeplug.a)
targets := pcap_kern.o pcap_user.o vde_kern.o vde_user.o
diff --git a/arch/um/drivers/chan_user.h b/arch/um/drivers/chan_user.h
index 72222bb..4e51b85 100644
--- a/arch/um/drivers/chan_user.h
+++ b/arch/um/drivers/chan_user.h
@@ -11,7 +11,7 @@
struct chan_opts {
void (*const announce)(char *dev_name, int dev);
char *xterm_title;
- const int raw;
+ int raw;
};
struct chan_ops {
diff --git a/arch/um/drivers/cow.h b/arch/um/drivers/cow.h
index 760c507..103adac 100644
--- a/arch/um/drivers/cow.h
+++ b/arch/um/drivers/cow.h
@@ -11,7 +11,7 @@
extern int file_reader(__u64 offset, char *buf, int len, void *arg);
extern int read_cow_header(int (*reader)(__u64, char *, int, void *),
void *arg, __u32 *version_out,
- char **backing_file_out, time_t *mtime_out,
+ char **backing_file_out, long long *mtime_out,
unsigned long long *size_out, int *sectorsize_out,
__u32 *align_out, int *bitmap_offset_out);
diff --git a/arch/um/drivers/cow_user.c b/arch/um/drivers/cow_user.c
index 74b0c26..29b4658 100644
--- a/arch/um/drivers/cow_user.c
+++ b/arch/um/drivers/cow_user.c
@@ -17,6 +17,7 @@
#define PATH_LEN_V1 256
+/* unsigned time_t works until year 2106 */
typedef __u32 time32_t;
struct cow_header_v1 {
@@ -197,7 +198,7 @@
int sectorsize, int alignment, unsigned long long *size)
{
struct cow_header_v3 *header;
- unsigned long modtime;
+ long long modtime;
int err;
err = cow_seek_file(fd, 0);
@@ -276,7 +277,7 @@
int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
__u32 *version_out, char **backing_file_out,
- time_t *mtime_out, unsigned long long *size_out,
+ long long *mtime_out, unsigned long long *size_out,
int *sectorsize_out, __u32 *align_out,
int *bitmap_offset_out)
{
@@ -363,7 +364,7 @@
/*
* this was used until Dec2005 - 64bits are needed to represent
- * 2038+. I.e. we can safely do this truncating cast.
+ * 2106+. I.e. we can safely do this truncating cast.
*
* Additionally, we must use be32toh() instead of be64toh(), since
* the program used to use the former (tested - I got mtime
diff --git a/arch/um/drivers/daemon_user.c b/arch/um/drivers/daemon_user.c
index 3695821..785baed 100644
--- a/arch/um/drivers/daemon_user.c
+++ b/arch/um/drivers/daemon_user.c
@@ -7,6 +7,7 @@
*/
#include <stdint.h>
+#include <string.h>
#include <unistd.h>
#include <errno.h>
#include <sys/types.h>
diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c
index 000cb69..e6d4f43 100644
--- a/arch/um/drivers/harddog_kern.c
+++ b/arch/um/drivers/harddog_kern.c
@@ -165,6 +165,7 @@
.owner = THIS_MODULE,
.write = harddog_write,
.unlocked_ioctl = harddog_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
.open = harddog_open,
.release = harddog_release,
.llseek = no_llseek,
diff --git a/arch/um/drivers/hostaudio_kern.c b/arch/um/drivers/hostaudio_kern.c
index bf75b1c..d35d3f3 100644
--- a/arch/um/drivers/hostaudio_kern.c
+++ b/arch/um/drivers/hostaudio_kern.c
@@ -298,6 +298,7 @@
.write = hostaudio_write,
.poll = hostaudio_poll,
.unlocked_ioctl = hostaudio_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
.mmap = NULL,
.open = hostaudio_open,
.release = hostaudio_release,
diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
index 4f2a4ac..14ad9f4 100644
--- a/arch/um/drivers/line.c
+++ b/arch/um/drivers/line.c
@@ -184,11 +184,6 @@
line_flush_buffer(tty);
}
-int line_put_char(struct tty_struct *tty, unsigned char ch)
-{
- return line_write(tty, &ch, sizeof(ch));
-}
-
int line_write(struct tty_struct *tty, const unsigned char *buf, int len)
{
struct line *line = tty->driver_data;
diff --git a/arch/um/drivers/line.h b/arch/um/drivers/line.h
index a151ff5..01d21e7 100644
--- a/arch/um/drivers/line.h
+++ b/arch/um/drivers/line.h
@@ -66,7 +66,6 @@
char *init, char *name);
extern int line_write(struct tty_struct *tty, const unsigned char *buf,
int len);
-extern int line_put_char(struct tty_struct *tty, unsigned char ch);
extern void line_set_termios(struct tty_struct *tty, struct ktermios * old);
extern int line_chars_in_buffer(struct tty_struct *tty);
extern void line_flush_buffer(struct tty_struct *tty);
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 0117489..a2e680f 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -36,6 +36,8 @@
#include "mconsole_kern.h"
#include <os.h>
+static struct vfsmount *proc_mnt = NULL;
+
static int do_unlink_socket(struct notifier_block *notifier,
unsigned long what, void *data)
{
@@ -123,7 +125,7 @@
void mconsole_proc(struct mc_request *req)
{
- struct vfsmount *mnt = task_active_pid_ns(current)->proc_mnt;
+ struct vfsmount *mnt = proc_mnt;
char *buf;
int len;
struct file *file;
@@ -134,6 +136,10 @@
ptr += strlen("proc");
ptr = skip_spaces(ptr);
+ if (!mnt) {
+ mconsole_reply(req, "Proc not available", 1, 0);
+ goto out;
+ }
file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY, 0);
if (IS_ERR(file)) {
mconsole_reply(req, "Failed to open file", 1, 0);
@@ -642,7 +648,7 @@
{
struct task_struct *task = arg;
- show_stack(task, NULL);
+ show_stack(task, NULL, KERN_INFO);
}
/*
@@ -683,6 +689,24 @@
with_console(req, stack_proc, to);
}
+static int __init mount_proc(void)
+{
+ struct file_system_type *proc_fs_type;
+ struct vfsmount *mnt;
+
+ proc_fs_type = get_fs_type("proc");
+ if (!proc_fs_type)
+ return -ENODEV;
+
+ mnt = kern_mount(proc_fs_type);
+ put_filesystem(proc_fs_type);
+ if (IS_ERR(mnt))
+ return PTR_ERR(mnt);
+
+ proc_mnt = mnt;
+ return 0;
+}
+
/*
* Changed by mconsole_setup, which is __setup, and called before SMP is
* active.
@@ -696,6 +720,8 @@
int err;
char file[UNIX_PATH_MAX];
+ mount_proc();
+
if (umid_file_name("mconsole", file, sizeof(file)))
return -1;
snprintf(mconsole_socket_name, sizeof(file), "%s", file);
@@ -752,10 +778,9 @@
return count;
}
-static const struct file_operations mconsole_proc_fops = {
- .owner = THIS_MODULE,
- .write = mconsole_proc_write,
- .llseek = noop_llseek,
+static const struct proc_ops mconsole_proc_ops = {
+ .proc_write = mconsole_proc_write,
+ .proc_lseek = noop_llseek,
};
static int create_proc_mconsole(void)
@@ -765,7 +790,7 @@
if (notify_socket == NULL)
return 0;
- ent = proc_create("mconsole", 0200, NULL, &mconsole_proc_fops);
+ ent = proc_create("mconsole", 0200, NULL, &mconsole_proc_ops);
if (ent == NULL) {
printk(KERN_INFO "create_proc_mconsole : proc_create failed\n");
return 0;
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index 327b728..1802cf4 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -247,7 +247,7 @@
return;
}
-static void uml_net_tx_timeout(struct net_device *dev)
+static void uml_net_tx_timeout(struct net_device *dev, unsigned int txqueue)
{
netif_trans_update(dev);
netif_wake_queue(dev);
@@ -266,7 +266,6 @@
struct ethtool_drvinfo *info)
{
strlcpy(info->driver, DRIVER_NAME, sizeof(info->driver));
- strlcpy(info->version, "42", sizeof(info->version));
}
static const struct ethtool_ops uml_net_ethtool_ops = {
@@ -275,17 +274,6 @@
.get_ts_info = ethtool_op_get_ts_info,
};
-static void uml_net_user_timer_expire(struct timer_list *t)
-{
-#ifdef undef
- struct uml_net_private *lp = from_timer(lp, t, tl);
- struct connection *conn = &lp->user;
-
- dprintk(KERN_INFO "uml_net_user_timer_expire [%p]\n", conn);
- do_connect(conn);
-#endif
-}
-
void uml_net_setup_etheraddr(struct net_device *dev, char *str)
{
unsigned char *addr = dev->dev_addr;
@@ -456,7 +444,6 @@
.add_address = transport->user->add_address,
.delete_address = transport->user->delete_address });
- timer_setup(&lp->tl, uml_net_user_timer_expire, 0);
spin_lock_init(&lp->lock);
memcpy(lp->mac, dev->dev_addr, sizeof(lp->mac));
diff --git a/arch/um/drivers/pcap_user.c b/arch/um/drivers/pcap_user.c
index bbd2063..52ddda3 100644
--- a/arch/um/drivers/pcap_user.c
+++ b/arch/um/drivers/pcap_user.c
@@ -32,7 +32,7 @@
return 0;
}
-static int pcap_open(void *data)
+static int pcap_user_open(void *data)
{
struct pcap_data *pri = data;
__u32 netmask;
@@ -44,14 +44,14 @@
if (pri->filter != NULL) {
err = dev_netmask(pri->dev, &netmask);
if (err < 0) {
- printk(UM_KERN_ERR "pcap_open : dev_netmask failed\n");
+ printk(UM_KERN_ERR "pcap_user_open : dev_netmask failed\n");
return -EIO;
}
pri->compiled = uml_kmalloc(sizeof(struct bpf_program),
UM_GFP_KERNEL);
if (pri->compiled == NULL) {
- printk(UM_KERN_ERR "pcap_open : kmalloc failed\n");
+ printk(UM_KERN_ERR "pcap_user_open : kmalloc failed\n");
return -ENOMEM;
}
@@ -59,14 +59,14 @@
(struct bpf_program *) pri->compiled,
pri->filter, pri->optimize, netmask);
if (err < 0) {
- printk(UM_KERN_ERR "pcap_open : pcap_compile failed - "
+ printk(UM_KERN_ERR "pcap_user_open : pcap_compile failed - "
"'%s'\n", pcap_geterr(pri->pcap));
goto out;
}
err = pcap_setfilter(pri->pcap, pri->compiled);
if (err < 0) {
- printk(UM_KERN_ERR "pcap_open : pcap_setfilter "
+ printk(UM_KERN_ERR "pcap_user_open : pcap_setfilter "
"failed - '%s'\n", pcap_geterr(pri->pcap));
goto out;
}
@@ -127,7 +127,7 @@
const struct net_user_info pcap_user_info = {
.init = pcap_user_init,
- .open = pcap_open,
+ .open = pcap_user_open,
.close = NULL,
.remove = pcap_remove,
.add_address = NULL,
diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c
index 1d5d305..e4b9b2c 100644
--- a/arch/um/drivers/random.c
+++ b/arch/um/drivers/random.c
@@ -11,6 +11,7 @@
#include <linux/fs.h>
#include <linux/interrupt.h>
#include <linux/miscdevice.h>
+#include <linux/hw_random.h>
#include <linux/delay.h>
#include <linux/uaccess.h>
#include <init.h>
@@ -18,100 +19,45 @@
#include <os.h>
/*
- * core module and version information
+ * core module information
*/
-#define RNG_VERSION "1.0.0"
#define RNG_MODULE_NAME "hw_random"
-#define RNG_MISCDEV_MINOR 183 /* official */
-
/* Changed at init time, in the non-modular case, and at module load
* time, in the module case. Presumably, the module subsystem
* protects against a module being loaded twice at the same time.
*/
static int random_fd = -1;
-static DECLARE_WAIT_QUEUE_HEAD(host_read_wait);
+static struct hwrng hwrng = { 0, };
+static DECLARE_COMPLETION(have_data);
-static int rng_dev_open (struct inode *inode, struct file *filp)
+static int rng_dev_read(struct hwrng *rng, void *buf, size_t max, bool block)
{
- /* enforce read-only access to this chrdev */
- if ((filp->f_mode & FMODE_READ) == 0)
- return -EINVAL;
- if ((filp->f_mode & FMODE_WRITE) != 0)
- return -EINVAL;
+ int ret;
- return 0;
-}
-
-static atomic_t host_sleep_count = ATOMIC_INIT(0);
-
-static ssize_t rng_dev_read (struct file *filp, char __user *buf, size_t size,
- loff_t *offp)
-{
- u32 data;
- int n, ret = 0, have_data;
-
- while (size) {
- n = os_read_file(random_fd, &data, sizeof(data));
- if (n > 0) {
- have_data = n;
- while (have_data && size) {
- if (put_user((u8) data, buf++)) {
- ret = ret ? : -EFAULT;
- break;
- }
- size--;
- ret++;
- have_data--;
- data >>= 8;
- }
- }
- else if (n == -EAGAIN) {
- DECLARE_WAITQUEUE(wait, current);
-
- if (filp->f_flags & O_NONBLOCK)
- return ret ? : -EAGAIN;
-
- atomic_inc(&host_sleep_count);
+ for (;;) {
+ ret = os_read_file(random_fd, buf, max);
+ if (block && ret == -EAGAIN) {
add_sigio_fd(random_fd);
- add_wait_queue(&host_read_wait, &wait);
- set_current_state(TASK_INTERRUPTIBLE);
+ ret = wait_for_completion_killable(&have_data);
- schedule();
- remove_wait_queue(&host_read_wait, &wait);
+ ignore_sigio_fd(random_fd);
+ deactivate_fd(random_fd, RANDOM_IRQ);
- if (atomic_dec_and_test(&host_sleep_count)) {
- ignore_sigio_fd(random_fd);
- deactivate_fd(random_fd, RANDOM_IRQ);
- }
+ if (ret < 0)
+ break;
+ } else {
+ break;
}
- else
- return n;
-
- if (signal_pending (current))
- return ret ? : -ERESTARTSYS;
}
- return ret;
+
+ return ret != -EAGAIN ? ret : 0;
}
-static const struct file_operations rng_chrdev_ops = {
- .owner = THIS_MODULE,
- .open = rng_dev_open,
- .read = rng_dev_read,
- .llseek = noop_llseek,
-};
-
-/* rng_init shouldn't be called more than once at boot time */
-static struct miscdevice rng_miscdev = {
- RNG_MISCDEV_MINOR,
- RNG_MODULE_NAME,
- &rng_chrdev_ops,
-};
-
static irqreturn_t random_interrupt(int irq, void *data)
{
- wake_up(&host_read_wait);
+ complete(&have_data);
return IRQ_HANDLED;
}
@@ -128,18 +74,19 @@
goto out;
random_fd = err;
-
err = um_request_irq(RANDOM_IRQ, random_fd, IRQ_READ, random_interrupt,
0, "random", NULL);
if (err)
goto err_out_cleanup_hw;
sigio_broken(random_fd, 1);
+ hwrng.name = RNG_MODULE_NAME;
+ hwrng.read = rng_dev_read;
+ hwrng.quality = 1024;
- err = misc_register (&rng_miscdev);
+ err = hwrng_register(&hwrng);
if (err) {
- printk (KERN_ERR RNG_MODULE_NAME ": misc device register "
- "failed\n");
+ pr_err(RNG_MODULE_NAME " registering failed (%d)\n", err);
goto err_out_cleanup_hw;
}
out:
@@ -163,8 +110,8 @@
static void __exit rng_cleanup(void)
{
+ hwrng_unregister(&hwrng);
os_close_file(random_fd);
- misc_deregister (&rng_miscdev);
}
module_init (rng_init);
diff --git a/arch/um/drivers/slip_user.c b/arch/um/drivers/slip_user.c
index 8d736eb..7334019 100644
--- a/arch/um/drivers/slip_user.c
+++ b/arch/um/drivers/slip_user.c
@@ -9,7 +9,7 @@
#include <errno.h>
#include <fcntl.h>
#include <string.h>
-#include <sys/termios.h>
+#include <termios.h>
#include <sys/wait.h>
#include <net_user.h>
#include <os.h>
diff --git a/arch/um/drivers/ssl.c b/arch/um/drivers/ssl.c
index b213201..6476b28 100644
--- a/arch/um/drivers/ssl.c
+++ b/arch/um/drivers/ssl.c
@@ -95,7 +95,6 @@
.open = line_open,
.close = line_close,
.write = line_write,
- .put_char = line_put_char,
.write_room = line_write_room,
.chars_in_buffer = line_chars_in_buffer,
.flush_buffer = line_flush_buffer,
@@ -196,3 +195,11 @@
__setup("ssl", ssl_chan_setup);
__channel_help(ssl_chan_setup, "ssl");
+
+static int ssl_non_raw_setup(char *str)
+{
+ opts.raw = 0;
+ return 1;
+}
+__setup("ssl-non-raw", ssl_non_raw_setup);
+__channel_help(ssl_non_raw_setup, "set serial lines to non-raw mode");
diff --git a/arch/um/drivers/stdio_console.c b/arch/um/drivers/stdio_console.c
index 0021d7f..37b1279 100644
--- a/arch/um/drivers/stdio_console.c
+++ b/arch/um/drivers/stdio_console.c
@@ -102,7 +102,6 @@
.install = con_install,
.close = line_close,
.write = line_write,
- .put_char = line_put_char,
.write_room = line_write_room,
.chars_in_buffer = line_chars_in_buffer,
.flush_buffer = line_flush_buffer,
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 4e59ab8..b12c1b0 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -120,6 +120,7 @@
.open = ubd_open,
.release = ubd_release,
.ioctl = ubd_ioctl,
+ .compat_ioctl = blkdev_compat_ptr_ioctl,
.getgeo = ubd_getgeo,
};
@@ -563,7 +564,7 @@
__u32 version;
__u32 align;
char *backing_file;
- time_t mtime;
+ time64_t mtime;
unsigned long long size;
int sector_size;
int bitmap_offset;
@@ -602,9 +603,9 @@
return 0;
}
-static int backing_file_mismatch(char *file, __u64 size, time_t mtime)
+static int backing_file_mismatch(char *file, __u64 size, time64_t mtime)
{
- unsigned long modtime;
+ time64_t modtime;
unsigned long long actual;
int err;
@@ -630,7 +631,7 @@
return -EINVAL;
}
if (modtime != mtime) {
- printk(KERN_ERR "mtime mismatch (%ld vs %ld) of COW header vs "
+ printk(KERN_ERR "mtime mismatch (%lld vs %lld) of COW header vs "
"backing file\n", mtime, modtime);
return -EINVAL;
}
@@ -673,7 +674,7 @@
unsigned long *bitmap_len_out, int *data_offset_out,
int *create_cow_out)
{
- time_t mtime;
+ time64_t mtime;
unsigned long long size;
__u32 version, align;
char *backing_file;
@@ -1625,11 +1626,11 @@
&io_remainder_size,
UBD_REQ_BUFFER_SIZE
);
- if (n < 0) {
- if (n == -EAGAIN) {
+ if (n <= 0) {
+ if (n == -EAGAIN)
ubd_read_poll(-1);
- continue;
- }
+
+ continue;
}
for (count = 0; count < n/sizeof(struct io_thread_req *); count++) {
diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c
index 769ffbd..555203e 100644
--- a/arch/um/drivers/vector_kern.c
+++ b/arch/um/drivers/vector_kern.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * Copyright (C) 2017 - Cambridge Greys Limited
+ * Copyright (C) 2017 - 2019 Cambridge Greys Limited
* Copyright (C) 2011 - 2014 Cisco Systems Inc
* Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
* Copyright (C) 2001 Lennert Buytenhek (buytenh@gnu.org) and
@@ -21,6 +21,9 @@
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
+#include <linux/firmware.h>
+#include <linux/fs.h>
+#include <uapi/linux/filter.h>
#include <init.h>
#include <irq_kern.h>
#include <irq_user.h>
@@ -43,7 +46,6 @@
#define DRIVER_NAME "uml-vector"
-#define DRIVER_VERSION "01"
struct vector_cmd_line_arg {
struct list_head list;
int unit;
@@ -128,6 +130,23 @@
return ETH_MAX_PACKET;
}
+static char *get_bpf_file(struct arglist *def)
+{
+ return uml_vector_fetch_arg(def, "bpffile");
+}
+
+static bool get_bpf_flash(struct arglist *def)
+{
+ char *allow = uml_vector_fetch_arg(def, "bpfflash");
+ long result;
+
+ if (allow != NULL) {
+ if (kstrtoul(allow, 10, &result) == 0)
+ return (allow > 0);
+ }
+ return false;
+}
+
static int get_depth(struct arglist *def)
{
char *mtu = uml_vector_fetch_arg(def, "depth");
@@ -176,6 +195,10 @@
int vec_rx = VECTOR_RX;
int vec_tx = VECTOR_TX;
long parsed;
+ int result = 0;
+
+ if (transport == NULL)
+ return -EINVAL;
if (vector != NULL) {
if (kstrtoul(vector, 10, &parsed) == 0) {
@@ -186,14 +209,16 @@
}
}
+ if (get_bpf_flash(def))
+ result = VECTOR_BPF_FLASH;
if (strncmp(transport, TRANS_TAP, TRANS_TAP_LEN) == 0)
- return 0;
+ return result;
if (strncmp(transport, TRANS_HYBRID, TRANS_HYBRID_LEN) == 0)
- return (vec_rx | VECTOR_BPF);
+ return (result | vec_rx | VECTOR_BPF);
if (strncmp(transport, TRANS_RAW, TRANS_RAW_LEN) == 0)
- return (vec_rx | vec_tx | VECTOR_QDISC_BYPASS);
- return (vec_rx | vec_tx);
+ return (result | vec_rx | vec_tx | VECTOR_QDISC_BYPASS);
+ return (result | vec_rx | vec_tx);
}
@@ -1139,6 +1164,8 @@
}
tasklet_kill(&vp->tx_poll);
if (vp->fds->rx_fd > 0) {
+ if (vp->bpf)
+ uml_vector_detach_bpf(vp->fds->rx_fd, vp->bpf);
os_close_file(vp->fds->rx_fd);
vp->fds->rx_fd = -1;
}
@@ -1146,7 +1173,10 @@
os_close_file(vp->fds->tx_fd);
vp->fds->tx_fd = -1;
}
+ if (vp->bpf != NULL)
+ kfree(vp->bpf->filter);
kfree(vp->bpf);
+ vp->bpf = NULL;
kfree(vp->fds->remote_addr);
kfree(vp->transport_data);
kfree(vp->header_rxbuffer);
@@ -1181,6 +1211,7 @@
netif_start_queue(vp->dev);
netif_wake_queue(vp->dev);
}
+
static int vector_net_open(struct net_device *dev)
{
struct vector_private *vp = netdev_priv(dev);
@@ -1196,6 +1227,8 @@
vp->opened = true;
spin_unlock_irqrestore(&vp->lock, flags);
+ vp->bpf = uml_vector_user_bpf(get_bpf_file(vp->parsed));
+
vp->fds = uml_vector_user_open(vp->unit, vp->parsed);
if (vp->fds == NULL)
@@ -1267,8 +1300,11 @@
if (!uml_raw_enable_qdisc_bypass(vp->fds->rx_fd))
vp->options |= VECTOR_BPF;
}
- if ((vp->options & VECTOR_BPF) != 0)
- vp->bpf = uml_vector_default_bpf(vp->fds->rx_fd, dev->dev_addr);
+ if (((vp->options & VECTOR_BPF) != 0) && (vp->bpf == NULL))
+ vp->bpf = uml_vector_default_bpf(dev->dev_addr);
+
+ if (vp->bpf != NULL)
+ uml_vector_attach_bpf(vp->fds->rx_fd, vp->bpf);
netif_start_queue(dev);
@@ -1298,7 +1334,7 @@
return;
}
-static void vector_net_tx_timeout(struct net_device *dev)
+static void vector_net_tx_timeout(struct net_device *dev, unsigned int txqueue)
{
struct vector_private *vp = netdev_priv(dev);
@@ -1344,7 +1380,65 @@
struct ethtool_drvinfo *info)
{
strlcpy(info->driver, DRIVER_NAME, sizeof(info->driver));
- strlcpy(info->version, DRIVER_VERSION, sizeof(info->version));
+}
+
+static int vector_net_load_bpf_flash(struct net_device *dev,
+ struct ethtool_flash *efl)
+{
+ struct vector_private *vp = netdev_priv(dev);
+ struct vector_device *vdevice;
+ const struct firmware *fw;
+ int result = 0;
+
+ if (!(vp->options & VECTOR_BPF_FLASH)) {
+ netdev_err(dev, "loading firmware not permitted: %s\n", efl->data);
+ return -1;
+ }
+
+ spin_lock(&vp->lock);
+
+ if (vp->bpf != NULL) {
+ if (vp->opened)
+ uml_vector_detach_bpf(vp->fds->rx_fd, vp->bpf);
+ kfree(vp->bpf->filter);
+ vp->bpf->filter = NULL;
+ } else {
+ vp->bpf = kmalloc(sizeof(struct sock_fprog), GFP_ATOMIC);
+ if (vp->bpf == NULL) {
+ netdev_err(dev, "failed to allocate memory for firmware\n");
+ goto flash_fail;
+ }
+ }
+
+ vdevice = find_device(vp->unit);
+
+ if (request_firmware(&fw, efl->data, &vdevice->pdev.dev))
+ goto flash_fail;
+
+ vp->bpf->filter = kmemdup(fw->data, fw->size, GFP_ATOMIC);
+ if (!vp->bpf->filter)
+ goto free_buffer;
+
+ vp->bpf->len = fw->size / sizeof(struct sock_filter);
+ release_firmware(fw);
+
+ if (vp->opened)
+ result = uml_vector_attach_bpf(vp->fds->rx_fd, vp->bpf);
+
+ spin_unlock(&vp->lock);
+
+ return result;
+
+free_buffer:
+ release_firmware(fw);
+
+flash_fail:
+ spin_unlock(&vp->lock);
+ if (vp->bpf != NULL)
+ kfree(vp->bpf->filter);
+ kfree(vp->bpf);
+ vp->bpf = NULL;
+ return -1;
}
static void vector_get_ringparam(struct net_device *netdev,
@@ -1415,6 +1509,7 @@
}
static const struct ethtool_ops vector_net_ethtool_ops = {
+ .supported_coalesce_params = ETHTOOL_COALESCE_TX_USECS,
.get_drvinfo = vector_net_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_ts_info = ethtool_op_get_ts_info,
@@ -1424,6 +1519,7 @@
.get_ethtool_stats = vector_get_ethtool_stats,
.get_coalesce = vector_get_coalesce,
.set_coalesce = vector_set_coalesce,
+ .flash_device = vector_net_load_bpf_flash,
};
@@ -1528,8 +1624,9 @@
.in_write_poll = false,
.coalesce = 2,
.req_size = get_req_size(def),
- .in_error = false
- });
+ .in_error = false,
+ .bpf = NULL
+ });
dev->features = dev->hw_features = (NETIF_F_SG | NETIF_F_FRAGLIST);
tasklet_init(&vp->tx_poll, vector_tx_poll, (unsigned long)vp);
diff --git a/arch/um/drivers/vector_kern.h b/arch/um/drivers/vector_kern.h
index 4d292e6..8fff93a 100644
--- a/arch/um/drivers/vector_kern.h
+++ b/arch/um/drivers/vector_kern.h
@@ -29,10 +29,13 @@
#define VECTOR_TX (1 << 1)
#define VECTOR_BPF (1 << 2)
#define VECTOR_QDISC_BYPASS (1 << 3)
+#define VECTOR_BPF_FLASH (1 << 4)
#define ETH_MAX_PACKET 1500
#define ETH_HEADER_OTHER 32 /* just in case someone decides to go mad on QnQ */
+#define MAX_FILTER_PROG (2 << 16)
+
struct vector_queue {
struct mmsghdr *mmsg_vector;
void **skbuff_vector;
@@ -118,12 +121,15 @@
bool in_write_poll;
bool in_error;
+ /* guest allowed to use ethtool flash to load bpf */
+ bool bpf_via_flash;
+
/* ethtool stats */
struct vector_estats estats;
- void *bpf;
+ struct sock_fprog *bpf;
- char user[0];
+ char user[];
};
extern int build_transport_data(struct vector_private *vp);
diff --git a/arch/um/drivers/vector_user.c b/arch/um/drivers/vector_user.c
index e2c969b..bae5322 100644
--- a/arch/um/drivers/vector_user.c
+++ b/arch/um/drivers/vector_user.c
@@ -18,9 +18,7 @@
#include <fcntl.h>
#include <sys/socket.h>
#include <sys/un.h>
-#include <net/ethernet.h>
#include <netinet/ip.h>
-#include <netinet/ether.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <sys/wait.h>
@@ -29,6 +27,7 @@
#include <netdb.h>
#include <stdlib.h>
#include <os.h>
+#include <limits.h>
#include <um_malloc.h>
#include "vector_user.h"
@@ -38,18 +37,26 @@
#define ID_MAX 2
#define TOKEN_IFNAME "ifname"
+#define TOKEN_SCRIPT "ifup"
#define TRANS_RAW "raw"
#define TRANS_RAW_LEN strlen(TRANS_RAW)
+#define TRANS_FD "fd"
+#define TRANS_FD_LEN strlen(TRANS_FD)
+
#define VNET_HDR_FAIL "could not enable vnet headers on fd %d"
#define TUN_GET_F_FAIL "tapraw: TUNGETFEATURES failed: %s"
#define L2TPV3_BIND_FAIL "l2tpv3_open : could not bind socket err=%i"
#define UNIX_BIND_FAIL "unix_open : could not bind socket err=%i"
-#define BPF_ATTACH_FAIL "Failed to attach filter size %d to %d, err %d\n"
+#define BPF_ATTACH_FAIL "Failed to attach filter size %d prog %px to %d, err %d\n"
+#define BPF_DETACH_FAIL "Failed to detach filter size %d prog %px to %d, err %d\n"
#define MAX_UN_LEN 107
+static const char padchar[] = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
+static const char *template = "tapXXXXXX";
+
/* This is very ugly and brute force lookup, but it is done
* only once at initialization so not worth doing hashes or
* anything more intelligent
@@ -186,16 +193,21 @@
return err;
}
+
static struct vector_fds *user_init_tap_fds(struct arglist *ifspec)
{
- int fd = -1;
+ int fd = -1, i;
char *iface;
struct vector_fds *result = NULL;
+ bool dynamic = false;
+ char dynamic_ifname[IFNAMSIZ];
+ char *argv[] = {NULL, NULL, NULL, NULL};
iface = uml_vector_fetch_arg(ifspec, TOKEN_IFNAME);
if (iface == NULL) {
- printk(UM_KERN_ERR "uml_tap: failed to parse interface spec\n");
- goto tap_cleanup;
+ dynamic = true;
+ iface = dynamic_ifname;
+ srand(getpid());
}
result = uml_kmalloc(sizeof(struct vector_fds), UM_GFP_KERNEL);
@@ -209,19 +221,34 @@
result->remote_addr_size = 0;
/* TAP */
+ do {
+ if (dynamic) {
+ strcpy(iface, template);
+ for (i = 0; i < strlen(iface); i++) {
+ if (iface[i] == 'X') {
+ iface[i] = padchar[rand() % strlen(padchar)];
+ }
+ }
+ }
+ fd = create_tap_fd(iface);
+ if ((fd < 0) && (!dynamic)) {
+ printk(UM_KERN_ERR "uml_tap: failed to create tun interface\n");
+ goto tap_cleanup;
+ }
+ result->tx_fd = fd;
+ result->rx_fd = fd;
+ } while (fd < 0);
- fd = create_tap_fd(iface);
- if (fd < 0) {
- printk(UM_KERN_ERR "uml_tap: failed to create tun interface\n");
- goto tap_cleanup;
+ argv[0] = uml_vector_fetch_arg(ifspec, TOKEN_SCRIPT);
+ if (argv[0]) {
+ argv[1] = iface;
+ run_helper(NULL, NULL, argv);
}
- result->tx_fd = fd;
- result->rx_fd = fd;
+
return result;
tap_cleanup:
printk(UM_KERN_ERR "user_init_tap: init failed, error %d", fd);
- if (result != NULL)
- kfree(result);
+ kfree(result);
return NULL;
}
@@ -229,6 +256,7 @@
{
char *iface;
struct vector_fds *result = NULL;
+ char *argv[] = {NULL, NULL, NULL, NULL};
iface = uml_vector_fetch_arg(ifspec, TOKEN_IFNAME);
if (iface == NULL) {
@@ -262,11 +290,16 @@
"uml_tap: failed to create paired raw socket: %i\n", result->rx_fd);
goto hybrid_cleanup;
}
+
+ argv[0] = uml_vector_fetch_arg(ifspec, TOKEN_SCRIPT);
+ if (argv[0]) {
+ argv[1] = iface;
+ run_helper(NULL, NULL, argv);
+ }
return result;
hybrid_cleanup:
printk(UM_KERN_ERR "user_init_hybrid: init failed");
- if (result != NULL)
- kfree(result);
+ kfree(result);
return NULL;
}
@@ -329,7 +362,7 @@
}
switch (id) {
case ID_BESS:
- if (connect(fd, remote_addr, sizeof(struct sockaddr_un)) < 0) {
+ if (connect(fd, (const struct sockaddr *) remote_addr, sizeof(struct sockaddr_un)) < 0) {
printk(UM_KERN_ERR "bess open:cannot connect to %s %i", remote_addr->sun_path, -errno);
goto unix_cleanup;
}
@@ -343,10 +376,60 @@
unix_cleanup:
if (fd >= 0)
os_close_file(fd);
- if (remote_addr != NULL)
- kfree(remote_addr);
- if (result != NULL)
- kfree(result);
+ kfree(remote_addr);
+ kfree(result);
+ return NULL;
+}
+
+static int strtofd(const char *nptr)
+{
+ long fd;
+ char *endptr;
+
+ if (nptr == NULL)
+ return -1;
+
+ errno = 0;
+ fd = strtol(nptr, &endptr, 10);
+ if (nptr == endptr ||
+ errno != 0 ||
+ *endptr != '\0' ||
+ fd < 0 ||
+ fd > INT_MAX) {
+ return -1;
+ }
+ return fd;
+}
+
+static struct vector_fds *user_init_fd_fds(struct arglist *ifspec)
+{
+ int fd = -1;
+ char *fdarg = NULL;
+ struct vector_fds *result = NULL;
+
+ fdarg = uml_vector_fetch_arg(ifspec, "fd");
+ fd = strtofd(fdarg);
+ if (fd == -1) {
+ printk(UM_KERN_ERR "fd open: bad or missing fd argument");
+ goto fd_cleanup;
+ }
+
+ result = uml_kmalloc(sizeof(struct vector_fds), UM_GFP_KERNEL);
+ if (result == NULL) {
+ printk(UM_KERN_ERR "fd open: allocation failed");
+ goto fd_cleanup;
+ }
+
+ result->rx_fd = fd;
+ result->tx_fd = fd;
+ result->remote_addr_size = 0;
+ result->remote_addr = NULL;
+ return result;
+
+fd_cleanup:
+ if (fd >= 0)
+ os_close_file(fd);
+ kfree(result);
return NULL;
}
@@ -356,6 +439,7 @@
int err = -ENOMEM;
char *iface;
struct vector_fds *result = NULL;
+ char *argv[] = {NULL, NULL, NULL, NULL};
iface = uml_vector_fetch_arg(ifspec, TOKEN_IFNAME);
if (iface == NULL)
@@ -378,11 +462,15 @@
result->remote_addr = NULL;
result->remote_addr_size = 0;
}
+ argv[0] = uml_vector_fetch_arg(ifspec, TOKEN_SCRIPT);
+ if (argv[0]) {
+ argv[1] = iface;
+ run_helper(NULL, NULL, argv);
+ }
return result;
raw_cleanup:
printk(UM_KERN_ERR "user_init_raw: init failed, error %d", err);
- if (result != NULL)
- kfree(result);
+ kfree(result);
return NULL;
}
@@ -582,6 +670,8 @@
return user_init_socket_fds(parsed, ID_L2TPV3);
if (strncmp(transport, TRANS_BESS, TRANS_BESS_LEN) == 0)
return user_init_unix_fds(parsed, ID_BESS);
+ if (strncmp(transport, TRANS_FD, TRANS_FD_LEN) == 0)
+ return user_init_fd_fds(parsed);
return NULL;
}
@@ -660,31 +750,44 @@
else
return -errno;
}
-int uml_vector_attach_bpf(int fd, void *bpf, int bpf_len)
+int uml_vector_attach_bpf(int fd, void *bpf)
{
- int err = setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, bpf, bpf_len);
+ struct sock_fprog *prog = bpf;
+
+ int err = setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, bpf, sizeof(struct sock_fprog));
if (err < 0)
- printk(KERN_ERR BPF_ATTACH_FAIL, bpf_len, fd, -errno);
+ printk(KERN_ERR BPF_ATTACH_FAIL, prog->len, prog->filter, fd, -errno);
return err;
}
-#define DEFAULT_BPF_LEN 6
+int uml_vector_detach_bpf(int fd, void *bpf)
+{
+ struct sock_fprog *prog = bpf;
-void *uml_vector_default_bpf(int fd, void *mac)
+ int err = setsockopt(fd, SOL_SOCKET, SO_DETACH_FILTER, bpf, sizeof(struct sock_fprog));
+ if (err < 0)
+ printk(KERN_ERR BPF_DETACH_FAIL, prog->len, prog->filter, fd, -errno);
+ return err;
+}
+void *uml_vector_default_bpf(void *mac)
{
struct sock_filter *bpf;
uint32_t *mac1 = (uint32_t *)(mac + 2);
uint16_t *mac2 = (uint16_t *) mac;
- struct sock_fprog bpf_prog = {
- .len = 6,
- .filter = NULL,
- };
+ struct sock_fprog *bpf_prog;
+ bpf_prog = uml_kmalloc(sizeof(struct sock_fprog), UM_GFP_KERNEL);
+ if (bpf_prog) {
+ bpf_prog->len = DEFAULT_BPF_LEN;
+ bpf_prog->filter = NULL;
+ } else {
+ return NULL;
+ }
bpf = uml_kmalloc(
sizeof(struct sock_filter) * DEFAULT_BPF_LEN, UM_GFP_KERNEL);
- if (bpf != NULL) {
- bpf_prog.filter = bpf;
+ if (bpf) {
+ bpf_prog->filter = bpf;
/* ld [8] */
bpf[0] = (struct sock_filter){ 0x20, 0, 0, 0x00000008 };
/* jeq #0xMAC[2-6] jt 2 jf 5*/
@@ -697,12 +800,58 @@
bpf[4] = (struct sock_filter){ 0x6, 0, 0, 0x00000000 };
/* ret #0x40000 */
bpf[5] = (struct sock_filter){ 0x6, 0, 0, 0x00040000 };
- if (uml_vector_attach_bpf(
- fd, &bpf_prog, sizeof(struct sock_fprog)) < 0) {
- kfree(bpf);
- bpf = NULL;
- }
+ } else {
+ kfree(bpf_prog);
+ bpf_prog = NULL;
}
- return bpf;
+ return bpf_prog;
}
+/* Note - this function requires a valid mac being passed as an arg */
+
+void *uml_vector_user_bpf(char *filename)
+{
+ struct sock_filter *bpf;
+ struct sock_fprog *bpf_prog;
+ struct stat statbuf;
+ int res, ffd = -1;
+
+ if (filename == NULL)
+ return NULL;
+
+ if (stat(filename, &statbuf) < 0) {
+ printk(KERN_ERR "Error %d reading bpf file", -errno);
+ return false;
+ }
+ bpf_prog = uml_kmalloc(sizeof(struct sock_fprog), UM_GFP_KERNEL);
+ if (bpf_prog == NULL) {
+ printk(KERN_ERR "Failed to allocate bpf prog buffer");
+ return NULL;
+ }
+ bpf_prog->len = statbuf.st_size / sizeof(struct sock_filter);
+ bpf_prog->filter = NULL;
+ ffd = os_open_file(filename, of_read(OPENFLAGS()), 0);
+ if (ffd < 0) {
+ printk(KERN_ERR "Error %d opening bpf file", -errno);
+ goto bpf_failed;
+ }
+ bpf = uml_kmalloc(statbuf.st_size, UM_GFP_KERNEL);
+ if (bpf == NULL) {
+ printk(KERN_ERR "Failed to allocate bpf buffer");
+ goto bpf_failed;
+ }
+ bpf_prog->filter = bpf;
+ res = os_read_file(ffd, bpf, statbuf.st_size);
+ if (res < statbuf.st_size) {
+ printk(KERN_ERR "Failed to read bpf program %s, error %d", filename, res);
+ kfree(bpf);
+ goto bpf_failed;
+ }
+ os_close_file(ffd);
+ return bpf_prog;
+bpf_failed:
+ if (ffd > 0)
+ os_close_file(ffd);
+ kfree(bpf_prog);
+ return NULL;
+}
diff --git a/arch/um/drivers/vector_user.h b/arch/um/drivers/vector_user.h
index 649ec25..d29d5fd 100644
--- a/arch/um/drivers/vector_user.h
+++ b/arch/um/drivers/vector_user.h
@@ -17,7 +17,7 @@
#define TRANS_TAP_LEN strlen(TRANS_TAP)
#define TRANS_GRE "gre"
-#define TRANS_GRE_LEN strlen(TRANS_RAW)
+#define TRANS_GRE_LEN strlen(TRANS_GRE)
#define TRANS_L2TPV3 "l2tpv3"
#define TRANS_L2TPV3_LEN strlen(TRANS_L2TPV3)
@@ -28,6 +28,8 @@
#define TRANS_BESS "bess"
#define TRANS_BESS_LEN strlen(TRANS_BESS)
+#define DEFAULT_BPF_LEN 6
+
#ifndef IPPROTO_GRE
#define IPPROTO_GRE 0x2F
#endif
@@ -95,8 +97,10 @@
unsigned int vlen,
unsigned int flags
);
-extern void *uml_vector_default_bpf(int fd, void *mac);
-extern int uml_vector_attach_bpf(int fd, void *bpf, int bpf_len);
+extern void *uml_vector_default_bpf(void *mac);
+extern void *uml_vector_user_bpf(char *filename);
+extern int uml_vector_attach_bpf(int fd, void *bpf);
+extern int uml_vector_detach_bpf(int fd, void *bpf);
extern bool uml_raw_enable_qdisc_bypass(int fd);
extern bool uml_raw_enable_vnet_headers(int fd);
extern bool uml_tap_enable_vnet_headers(int fd);
diff --git a/arch/um/drivers/vhost_user.h b/arch/um/drivers/vhost_user.h
index 45ff5ea..6f147cd 100644
--- a/arch/um/drivers/vhost_user.h
+++ b/arch/um/drivers/vhost_user.h
@@ -10,9 +10,10 @@
/* Feature bits */
#define VHOST_USER_F_PROTOCOL_FEATURES 30
/* Protocol feature bits */
-#define VHOST_USER_PROTOCOL_F_REPLY_ACK 3
-#define VHOST_USER_PROTOCOL_F_SLAVE_REQ 5
-#define VHOST_USER_PROTOCOL_F_CONFIG 9
+#define VHOST_USER_PROTOCOL_F_REPLY_ACK 3
+#define VHOST_USER_PROTOCOL_F_SLAVE_REQ 5
+#define VHOST_USER_PROTOCOL_F_CONFIG 9
+#define VHOST_USER_PROTOCOL_F_INBAND_NOTIFICATIONS 14
/* Vring state index masks */
#define VHOST_USER_VRING_INDEX_MASK 0xff
#define VHOST_USER_VRING_POLL_MASK BIT(8)
@@ -24,7 +25,8 @@
/* Supported protocol features */
#define VHOST_USER_SUPPORTED_PROTOCOL_F (BIT_ULL(VHOST_USER_PROTOCOL_F_REPLY_ACK) | \
BIT_ULL(VHOST_USER_PROTOCOL_F_SLAVE_REQ) | \
- BIT_ULL(VHOST_USER_PROTOCOL_F_CONFIG))
+ BIT_ULL(VHOST_USER_PROTOCOL_F_CONFIG) | \
+ BIT_ULL(VHOST_USER_PROTOCOL_F_INBAND_NOTIFICATIONS))
enum vhost_user_request {
VHOST_USER_GET_FEATURES = 1,
@@ -52,12 +54,14 @@
VHOST_USER_SET_VRING_ENDIAN = 23,
VHOST_USER_GET_CONFIG = 24,
VHOST_USER_SET_CONFIG = 25,
+ VHOST_USER_VRING_KICK = 35,
};
enum vhost_user_slave_request {
VHOST_USER_SLAVE_IOTLB_MSG = 1,
VHOST_USER_SLAVE_CONFIG_CHANGE_MSG = 2,
VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG = 3,
+ VHOST_USER_SLAVE_VRING_CALL = 4,
};
struct vhost_user_header {
@@ -74,7 +78,7 @@
u32 offset;
u32 size;
u32 flags;
- u8 payload[0]; /* Variable length */
+ u8 payload[]; /* Variable length */
} __packed;
struct vhost_user_vring_state {
diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c
index 18618af..d5d7681 100644
--- a/arch/um/drivers/virtio_uml.c
+++ b/arch/um/drivers/virtio_uml.c
@@ -26,6 +26,7 @@
#include <linux/virtio.h>
#include <linux/virtio_config.h>
#include <linux/virtio_ring.h>
+#include <linux/time-internal.h>
#include <shared/as-layout.h>
#include <irq_kern.h>
#include <init.h>
@@ -42,24 +43,38 @@
#define to_virtio_uml_device(_vdev) \
container_of(_vdev, struct virtio_uml_device, vdev)
+struct virtio_uml_platform_data {
+ u32 virtio_device_id;
+ const char *socket_path;
+ struct work_struct conn_broken_wk;
+ struct platform_device *pdev;
+};
+
struct virtio_uml_device {
struct virtio_device vdev;
struct platform_device *pdev;
+ spinlock_t sock_lock;
int sock, req_fd;
u64 features;
u64 protocol_features;
u8 status;
+ u8 registered:1;
};
struct virtio_uml_vq_info {
int kick_fd, call_fd;
char name[32];
+#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+ struct virtqueue *vq;
+ vq_callback_t *callback;
+ struct time_travel_event defer;
+#endif
};
extern unsigned long long physmem_size, highmem;
-#define vu_err(vu_dev, ...) dev_err(&(vu_dev)->pdev->dev, __VA_ARGS__)
+#define vu_err(vu_dev, ...) dev_err(&(vu_dev)->pdev->dev, ##__VA_ARGS__)
/* Vhost-user protocol */
@@ -107,12 +122,38 @@
return full_read(fd, msg, sizeof(msg->header), true);
}
-static int vhost_user_recv(int fd, struct vhost_user_msg *msg,
- size_t max_payload_size)
+static int vhost_user_recv(struct virtio_uml_device *vu_dev,
+ int fd, struct vhost_user_msg *msg,
+ size_t max_payload_size, bool wait)
{
size_t size;
- int rc = vhost_user_recv_header(fd, msg);
+ int rc;
+ /*
+ * In virtio time-travel mode, we're handling all the vhost-user
+ * FDs by polling them whenever appropriate. However, we may get
+ * into a situation where we're sending out an interrupt message
+ * to a device (e.g. a net device) and need to handle a simulation
+ * time message while doing so, e.g. one that tells us to update
+ * our idea of how long we can run without scheduling.
+ *
+ * Thus, we need to not just read() from the given fd, but need
+ * to also handle messages for the simulation time - this function
+ * does that for us while waiting for the given fd to be readable.
+ */
+ if (wait)
+ time_travel_wait_readable(fd);
+
+ rc = vhost_user_recv_header(fd, msg);
+
+ if (rc == -ECONNRESET && vu_dev->registered) {
+ struct virtio_uml_platform_data *pdata;
+
+ pdata = vu_dev->pdev->dev.platform_data;
+
+ virtio_break_device(&vu_dev->vdev);
+ schedule_work(&pdata->conn_broken_wk);
+ }
if (rc)
return rc;
size = msg->header.size;
@@ -125,7 +166,8 @@
struct vhost_user_msg *msg,
size_t max_payload_size)
{
- int rc = vhost_user_recv(vu_dev->sock, msg, max_payload_size);
+ int rc = vhost_user_recv(vu_dev, vu_dev->sock, msg,
+ max_payload_size, true);
if (rc)
return rc;
@@ -155,7 +197,8 @@
struct vhost_user_msg *msg,
size_t max_payload_size)
{
- int rc = vhost_user_recv(vu_dev->req_fd, msg, max_payload_size);
+ int rc = vhost_user_recv(vu_dev, vu_dev->req_fd, msg,
+ max_payload_size, false);
if (rc)
return rc;
@@ -172,6 +215,7 @@
int *fds, size_t num_fds)
{
size_t size = sizeof(msg->header) + msg->header.size;
+ unsigned long flags;
bool request_ack;
int rc;
@@ -190,24 +234,28 @@
if (request_ack)
msg->header.flags |= VHOST_USER_FLAG_NEED_REPLY;
+ spin_lock_irqsave(&vu_dev->sock_lock, flags);
rc = full_sendmsg_fds(vu_dev->sock, msg, size, fds, num_fds);
if (rc < 0)
- return rc;
+ goto out;
if (request_ack) {
uint64_t status;
rc = vhost_user_recv_u64(vu_dev, &status);
if (rc)
- return rc;
+ goto out;
if (status) {
vu_err(vu_dev, "slave reports error: %llu\n", status);
- return -EIO;
+ rc = -EIO;
+ goto out;
}
}
- return 0;
+out:
+ spin_unlock_irqrestore(&vu_dev->sock_lock, flags);
+ return rc;
}
static int vhost_user_send_no_payload(struct virtio_uml_device *vu_dev,
@@ -307,6 +355,7 @@
static irqreturn_t vu_req_interrupt(int irq, void *data)
{
struct virtio_uml_device *vu_dev = data;
+ struct virtqueue *vq;
int response = 1;
struct {
struct vhost_user_msg msg;
@@ -326,8 +375,17 @@
virtio_config_changed(&vu_dev->vdev);
response = 0;
break;
+ case VHOST_USER_SLAVE_VRING_CALL:
+ virtio_device_for_each_vq((&vu_dev->vdev), vq) {
+ if (vq->index == msg.msg.payload.vring_state.index) {
+ response = 0;
+ vring_interrupt(0 /* ignored */, vq);
+ break;
+ }
+ }
+ break;
case VHOST_USER_SLAVE_IOTLB_MSG:
- /* not supported - VIRTIO_F_IOMMU_PLATFORM */
+ /* not supported - VIRTIO_F_ACCESS_PLATFORM */
case VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG:
/* not supported - VHOST_USER_PROTOCOL_F_HOST_NOTIFIER */
default:
@@ -667,6 +725,17 @@
const uint64_t n = 1;
int rc;
+ time_travel_propagate_time();
+
+ if (info->kick_fd < 0) {
+ struct virtio_uml_device *vu_dev;
+
+ vu_dev = to_virtio_uml_device(vq->vdev);
+
+ return vhost_user_set_vring_state(vu_dev, VHOST_USER_VRING_KICK,
+ vq->index, 0) == 0;
+ }
+
do {
rc = os_write_file(info->kick_fd, &n, sizeof(n));
} while (rc == -EINTR);
@@ -732,10 +801,13 @@
{
struct virtio_uml_vq_info *info = vq->priv;
- um_free_irq(VIRTIO_IRQ, vq);
+ if (info->call_fd >= 0) {
+ um_free_irq(VIRTIO_IRQ, vq);
+ os_close_file(info->call_fd);
+ }
- os_close_file(info->call_fd);
- os_close_file(info->kick_fd);
+ if (info->kick_fd >= 0)
+ os_close_file(info->kick_fd);
vring_del_virtqueue(vq);
kfree(info);
@@ -765,6 +837,15 @@
int call_fds[2];
int rc;
+ /* no call FD needed/desired in this case */
+ if (vu_dev->protocol_features &
+ BIT_ULL(VHOST_USER_PROTOCOL_F_INBAND_NOTIFICATIONS) &&
+ vu_dev->protocol_features &
+ BIT_ULL(VHOST_USER_PROTOCOL_F_SLAVE_REQ)) {
+ info->call_fd = -1;
+ return 0;
+ }
+
/* Use a pipe for call fd, since SIGIO is not supported for eventfd */
rc = os_pipe(call_fds, true, true);
if (rc < 0)
@@ -793,6 +874,23 @@
return rc;
}
+#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+static void vu_defer_irq_handle(struct time_travel_event *d)
+{
+ struct virtio_uml_vq_info *info;
+
+ info = container_of(d, struct virtio_uml_vq_info, defer);
+ info->callback(info->vq);
+}
+
+static void vu_defer_irq_callback(struct virtqueue *vq)
+{
+ struct virtio_uml_vq_info *info = vq->priv;
+
+ time_travel_add_irq_event(&info->defer);
+}
+#endif
+
static struct virtqueue *vu_setup_vq(struct virtio_device *vdev,
unsigned index, vq_callback_t *callback,
const char *name, bool ctx)
@@ -812,6 +910,19 @@
snprintf(info->name, sizeof(info->name), "%s.%d-%s", pdev->name,
pdev->id, name);
+#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+ /*
+ * When we get an interrupt, we must bounce it through the simulation
+ * calendar (the simtime device), except for the simtime device itself
+ * since that's part of the simulation control.
+ */
+ if (time_travel_mode == TT_MODE_EXTERNAL && callback) {
+ info->callback = callback;
+ callback = vu_defer_irq_callback;
+ time_travel_set_event_fn(&info->defer, vu_defer_irq_handle);
+ }
+#endif
+
vq = vring_create_virtqueue(index, num, PAGE_SIZE, vdev, true, true,
ctx, vu_notify, callback, info->name);
if (!vq) {
@@ -820,11 +931,19 @@
}
vq->priv = info;
num = virtqueue_get_vring_size(vq);
+#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+ info->vq = vq;
+#endif
- rc = os_eventfd(0, 0);
- if (rc < 0)
- goto error_kick;
- info->kick_fd = rc;
+ if (vu_dev->protocol_features &
+ BIT_ULL(VHOST_USER_PROTOCOL_F_INBAND_NOTIFICATIONS)) {
+ info->kick_fd = -1;
+ } else {
+ rc = os_eventfd(0, 0);
+ if (rc < 0)
+ goto error_kick;
+ info->kick_fd = rc;
+ }
rc = vu_setup_vq_call_fd(vu_dev, vq);
if (rc)
@@ -849,10 +968,13 @@
return vq;
error_setup:
- um_free_irq(VIRTIO_IRQ, vq);
- os_close_file(info->call_fd);
+ if (info->call_fd >= 0) {
+ um_free_irq(VIRTIO_IRQ, vq);
+ os_close_file(info->call_fd);
+ }
error_call:
- os_close_file(info->kick_fd);
+ if (info->kick_fd >= 0)
+ os_close_file(info->kick_fd);
error_kick:
vring_del_virtqueue(vq);
error_create:
@@ -891,10 +1013,12 @@
list_for_each_entry(vq, &vdev->vqs, list) {
struct virtio_uml_vq_info *info = vq->priv;
- rc = vhost_user_set_vring_kick(vu_dev, vq->index,
- info->kick_fd);
- if (rc)
- goto error_setup;
+ if (info->kick_fd >= 0) {
+ rc = vhost_user_set_vring_kick(vu_dev, vq->index,
+ info->kick_fd);
+ if (rc)
+ goto error_setup;
+ }
rc = vhost_user_set_vring_enable(vu_dev, vq->index, true);
if (rc)
@@ -952,6 +1076,8 @@
container_of(d, struct virtio_device, dev);
struct virtio_uml_device *vu_dev = to_virtio_uml_device(vdev);
+ time_travel_propagate_time();
+
/* might not have been opened due to not negotiating the feature */
if (vu_dev->req_fd >= 0) {
um_free_irq(VIRTIO_IRQ, vu_dev);
@@ -964,11 +1090,6 @@
/* Platform device */
-struct virtio_uml_platform_data {
- u32 virtio_device_id;
- const char *socket_path;
-};
-
static int virtio_uml_probe(struct platform_device *pdev)
{
struct virtio_uml_platform_data *pdata = pdev->dev.platform_data;
@@ -990,13 +1111,17 @@
vu_dev->pdev = pdev;
vu_dev->req_fd = -1;
+ time_travel_propagate_time();
+
do {
rc = os_connect_socket(pdata->socket_path);
} while (rc == -EINTR);
if (rc < 0)
- return rc;
+ goto error_free;
vu_dev->sock = rc;
+ spin_lock_init(&vu_dev->sock_lock);
+
rc = vhost_user_init(vu_dev);
if (rc)
goto error_init;
@@ -1006,10 +1131,13 @@
rc = register_virtio_device(&vu_dev->vdev);
if (rc)
put_device(&vu_dev->vdev.dev);
+ vu_dev->registered = 1;
return rc;
error_init:
os_close_file(vu_dev->sock);
+error_free:
+ kfree(vu_dev);
return rc;
}
@@ -1035,13 +1163,31 @@
static bool vu_cmdline_parent_registered;
static int vu_cmdline_id;
+static int vu_unregister_cmdline_device(struct device *dev, void *data)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ struct virtio_uml_platform_data *pdata = pdev->dev.platform_data;
+
+ kfree(pdata->socket_path);
+ platform_device_unregister(pdev);
+ return 0;
+}
+
+static void vu_conn_broken(struct work_struct *wk)
+{
+ struct virtio_uml_platform_data *pdata;
+
+ pdata = container_of(wk, struct virtio_uml_platform_data, conn_broken_wk);
+ vu_unregister_cmdline_device(&pdata->pdev->dev, NULL);
+}
+
static int vu_cmdline_set(const char *device, const struct kernel_param *kp)
{
const char *ids = strchr(device, ':');
unsigned int virtio_device_id;
int processed, consumed, err;
char *socket_path;
- struct virtio_uml_platform_data pdata;
+ struct virtio_uml_platform_data pdata, *ppdata;
struct platform_device *pdev;
if (!ids || ids == device)
@@ -1080,6 +1226,11 @@
err = PTR_ERR_OR_ZERO(pdev);
if (err)
goto free;
+
+ ppdata = pdev->dev.platform_data;
+ ppdata->pdev = pdev;
+ INIT_WORK(&ppdata->conn_broken_wk, vu_conn_broken);
+
return 0;
free:
@@ -1122,16 +1273,6 @@
);
-static int vu_unregister_cmdline_device(struct device *dev, void *data)
-{
- struct platform_device *pdev = to_platform_device(dev);
- struct virtio_uml_platform_data *pdata = pdev->dev.platform_data;
-
- kfree(pdata->socket_path);
- platform_device_unregister(pdev);
- return 0;
-}
-
static void vu_unregister_cmdline_devices(void)
{
if (vu_cmdline_parent_registered) {