Merge tag 'for-linus-5.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml
Pull UML updates from Richard Weinberger:
- Fixes for our new virtio code
- Fix for the irqflags tracer
- Kconfig coding style fixes
- Allow BPF firmware loading in our vector driver
* tag 'for-linus-5.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml:
um: Loadable BPF "Firmware" for vector drivers
um: Fix Kconfig indentation
um: virtio_uml: Disallow modular build
um: virtio: Keep reading on -EAGAIN
um: virtio: Remove device on disconnect
um: Don't trace irqflags during shutdown
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index fec6b4c..2a6d04fc 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -153,7 +153,7 @@
It is possible to reduce the stack to 1 for 64BIT and 0 for 32BIT on
older (pre-2017) CPUs. It is not recommended on newer CPUs due to the
increase in the size of the state which needs to be saved when handling
- signals.
+ signals.
config MMAPPER
tristate "iomem emulation driver"
diff --git a/arch/um/drivers/Kconfig b/arch/um/drivers/Kconfig
index fea5a0d..388096f 100644
--- a/arch/um/drivers/Kconfig
+++ b/arch/um/drivers/Kconfig
@@ -337,7 +337,7 @@
endmenu
config VIRTIO_UML
- tristate "UML driver for virtio devices"
+ bool "UML driver for virtio devices"
select VIRTIO
help
This driver provides support for virtio based paravirtual device
diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c
index 769ffbd..92617e1 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>
@@ -128,6 +131,23 @@
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 +196,7 @@
int vec_rx = VECTOR_RX;
int vec_tx = VECTOR_TX;
long parsed;
+ int result = 0;
if (vector != NULL) {
if (kstrtoul(vector, 10, &parsed) == 0) {
@@ -186,14 +207,16 @@
}
}
+ 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 +1162,8 @@
}
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 +1171,10 @@
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 +1209,7 @@
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 +1225,8 @@
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 +1298,11 @@
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);
@@ -1347,6 +1381,65 @@
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_KERNEL);
+ 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_KERNEL);
+ 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,
struct ethtool_ringparam *ring)
{
@@ -1424,6 +1517,7 @@
.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 +1622,9 @@
.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..d015908 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;
@@ -118,10 +121,13 @@
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];
};
diff --git a/arch/um/drivers/vector_user.c b/arch/um/drivers/vector_user.c
index e2c969b..ddcd917 100644
--- a/arch/um/drivers/vector_user.c
+++ b/arch/um/drivers/vector_user.c
@@ -46,7 +46,8 @@
#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
@@ -660,31 +661,44 @@
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 +711,56 @@
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) {
+ 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..91f35b2 100644
--- a/arch/um/drivers/vector_user.h
+++ b/arch/um/drivers/vector_user.h
@@ -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/virtio_uml.c b/arch/um/drivers/virtio_uml.c
index fc8c52c..023ced2 100644
--- a/arch/um/drivers/virtio_uml.c
+++ b/arch/um/drivers/virtio_uml.c
@@ -4,12 +4,12 @@
*
* Copyright(c) 2019 Intel Corporation
*
- * This module allows virtio devices to be used over a vhost-user socket.
+ * This driver allows virtio devices to be used over a vhost-user socket.
*
* Guest devices can be instantiated by kernel module or command line
* parameters. One device will be created for each parameter. Syntax:
*
- * [virtio_uml.]device=<socket>:<virtio_id>[:<platform_id>]
+ * virtio_uml.device=<socket>:<virtio_id>[:<platform_id>]
* where:
* <socket> := vhost-user socket path to connect
* <virtio_id> := virtio device id (as in virtio_ids.h)
@@ -42,6 +42,13 @@
#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;
@@ -50,6 +57,7 @@
u64 features;
u64 protocol_features;
u8 status;
+ u8 registered:1;
};
struct virtio_uml_vq_info {
@@ -83,7 +91,7 @@
return 0;
}
-static int full_read(int fd, void *buf, int len)
+static int full_read(int fd, void *buf, int len, bool abortable)
{
int rc;
@@ -93,7 +101,7 @@
buf += rc;
len -= rc;
}
- } while (len && (rc > 0 || rc == -EINTR));
+ } while (len && (rc > 0 || rc == -EINTR || (!abortable && rc == -EAGAIN)));
if (rc < 0)
return rc;
@@ -104,28 +112,37 @@
static int vhost_user_recv_header(int fd, struct vhost_user_msg *msg)
{
- return full_read(fd, msg, sizeof(msg->header));
+ return full_read(fd, msg, sizeof(msg->header), true);
}
-static int vhost_user_recv(int fd, struct vhost_user_msg *msg,
+static int vhost_user_recv(struct virtio_uml_device *vu_dev,
+ int fd, struct vhost_user_msg *msg,
size_t max_payload_size)
{
size_t size;
int 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;
if (size > max_payload_size)
return -EPROTO;
- return full_read(fd, &msg->payload, size);
+ return full_read(fd, &msg->payload, size, false);
}
static int vhost_user_recv_resp(struct virtio_uml_device *vu_dev,
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);
if (rc)
return rc;
@@ -155,7 +172,7 @@
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);
if (rc)
return rc;
@@ -963,11 +980,6 @@
/* 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;
@@ -1005,6 +1017,7 @@
rc = register_virtio_device(&vu_dev->vdev);
if (rc)
put_device(&vu_dev->vdev.dev);
+ vu_dev->registered = 1;
return rc;
error_init:
@@ -1034,13 +1047,31 @@
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)
@@ -1079,6 +1110,11 @@
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:
@@ -1121,16 +1157,6 @@
);
-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) {
diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c
index 8014dfa..c8a42ec 100644
--- a/arch/um/os-Linux/main.c
+++ b/arch/um/os-Linux/main.c
@@ -170,7 +170,7 @@
* that they won't be delivered after the exec, when
* they are definitely not expected.
*/
- unblock_signals_trace();
+ unblock_signals();
os_info("\n");
/* Reboot */
