xen/pvhvm: If xen_platform_pci=0 is set don't blow up (v4).

The user has the option of disabling the platform driver:
00:02.0 Unassigned class [ff80]: XenSource, Inc. Xen Platform Device (rev 01)

which is used to unplug the emulated drivers (IDE, Realtek 8169, etc)
and allow the PV drivers to take over. If the user wishes
to disable that they can set:

  xen_platform_pci=0
  (in the guest config file)

or
  xen_emul_unplug=never
  (on the Linux command line)

except it does not work properly. The PV drivers still try to
load and since the Xen platform driver is not run - and it
has not initialized the grant tables, most of the PV drivers
stumble upon:

input: Xen Virtual Keyboard as /devices/virtual/input/input5
input: Xen Virtual Pointer as /devices/virtual/input/input6M
------------[ cut here ]------------
kernel BUG at /home/konrad/ssd/konrad/linux/drivers/xen/grant-table.c:1206!
invalid opcode: 0000 [#1] SMP
Modules linked in: xen_kbdfront(+) xenfs xen_privcmd
CPU: 6 PID: 1389 Comm: modprobe Not tainted 3.13.0-rc1upstream-00021-ga6c892b-dirty #1
Hardware name: Xen HVM domU, BIOS 4.4-unstable 11/26/2013
RIP: 0010:[<ffffffff813ddc40>]  [<ffffffff813ddc40>] get_free_entries+0x2e0/0x300
Call Trace:
 [<ffffffff8150d9a3>] ? evdev_connect+0x1e3/0x240
 [<ffffffff813ddd0e>] gnttab_grant_foreign_access+0x2e/0x70
 [<ffffffffa0010081>] xenkbd_connect_backend+0x41/0x290 [xen_kbdfront]
 [<ffffffffa0010a12>] xenkbd_probe+0x2f2/0x324 [xen_kbdfront]
 [<ffffffff813e5757>] xenbus_dev_probe+0x77/0x130
 [<ffffffff813e7217>] xenbus_frontend_dev_probe+0x47/0x50
 [<ffffffff8145e9a9>] driver_probe_device+0x89/0x230
 [<ffffffff8145ebeb>] __driver_attach+0x9b/0xa0
 [<ffffffff8145eb50>] ? driver_probe_device+0x230/0x230
 [<ffffffff8145eb50>] ? driver_probe_device+0x230/0x230
 [<ffffffff8145cf1c>] bus_for_each_dev+0x8c/0xb0
 [<ffffffff8145e7d9>] driver_attach+0x19/0x20
 [<ffffffff8145e260>] bus_add_driver+0x1a0/0x220
 [<ffffffff8145f1ff>] driver_register+0x5f/0xf0
 [<ffffffff813e55c5>] xenbus_register_driver_common+0x15/0x20
 [<ffffffff813e76b3>] xenbus_register_frontend+0x23/0x40
 [<ffffffffa0015000>] ? 0xffffffffa0014fff
 [<ffffffffa001502b>] xenkbd_init+0x2b/0x1000 [xen_kbdfront]
 [<ffffffff81002049>] do_one_initcall+0x49/0x170

.. snip..

which is hardly nice. This patch fixes this by having each
PV driver check for:
 - if running in PV, then it is fine to execute (as that is their
   native environment).
 - if running in HVM, check if user wanted 'xen_emul_unplug=never',
   in which case bail out and don't load any PV drivers.
 - if running in HVM, and if PCI device 5853:0001 (xen_platform_pci)
   does not exist, then bail out and not load PV drivers.
 - (v2) if running in HVM, and if the user wanted 'xen_emul_unplug=ide-disks',
   then bail out for all PV devices _except_ the block one.
   Ditto for the network one ('nics').
 - (v2) if running in HVM, and if the user wanted 'xen_emul_unplug=unnecessary'
   then load block PV driver, and also setup the legacy IDE paths.
   In (v3) make it actually load PV drivers.

Reported-by: Sander Eikelenboom <[email protected]
Reported-by: Anthony PERARD <[email protected]>
Reported-and-Tested-by: Fabio Fantoni <[email protected]>
Signed-off-by: Konrad Rzeszutek Wilk <[email protected]>
[v2: Add extra logic to handle the myrid ways 'xen_emul_unplug'
can be used per Ian and Stefano suggestion]
[v3: Make the unnecessary case work properly]
[v4: s/disks/ide-disks/ spotted by Fabio]
Reviewed-by: Stefano Stabellini <[email protected]>
Acked-by: Bjorn Helgaas <[email protected]> [for PCI parts]
CC: [email protected]

Author: konradwilk

arch/x86/xen/platform-pci-unplug.c

@@ -69,6 +69,80 @@ static int check_platform_magic(void)
 	return 0;
 }
 
+bool xen_has_pv_devices()
+{
+	if (!xen_domain())
+		return false;
+
+	/* PV domains always have them. */
+	if (xen_pv_domain())
+		return true;
+
+	/* And user has xen_platform_pci=0 set in guest config as
+	 * driver did not modify the value. */
+	if (xen_platform_pci_unplug == 0)
+		return false;
+
+	if (xen_platform_pci_unplug & XEN_UNPLUG_NEVER)
+		return false;
+
+	if (xen_platform_pci_unplug & XEN_UNPLUG_ALL)
+		return true;
+
+	/* This is an odd one - we are going to run legacy
+	 * and PV drivers at the same time. */
+	if (xen_platform_pci_unplug & XEN_UNPLUG_UNNECESSARY)
+		return true;
+
+	/* And the caller has to follow with xen_pv_{disk,nic}_devices
+	 * to be certain which driver can load. */
+	return false;
+}
+EXPORT_SYMBOL_GPL(xen_has_pv_devices);
+
+static bool __xen_has_pv_device(int state)
+{
+	/* HVM domains might or might not */
+	if (xen_hvm_domain() && (xen_platform_pci_unplug & state))
+		return true;
+
+	return xen_has_pv_devices();
+}
+
+bool xen_has_pv_nic_devices(void)
+{
+	return __xen_has_pv_device(XEN_UNPLUG_ALL_NICS | XEN_UNPLUG_ALL);
+}
+EXPORT_SYMBOL_GPL(xen_has_pv_nic_devices);
+
+bool xen_has_pv_disk_devices(void)
+{
+	return __xen_has_pv_device(XEN_UNPLUG_ALL_IDE_DISKS |
+				   XEN_UNPLUG_AUX_IDE_DISKS | XEN_UNPLUG_ALL);
+}
+EXPORT_SYMBOL_GPL(xen_has_pv_disk_devices);
+
+/*
+ * This one is odd - it determines whether you want to run PV _and_
+ * legacy (IDE) drivers together. This combination is only possible
+ * under HVM.
+ */
+bool xen_has_pv_and_legacy_disk_devices(void)
+{
+	if (!xen_domain())
+		return false;
+
+	/* N.B. This is only ever used in HVM mode */
+	if (xen_pv_domain())
+		return false;
+
+	if (xen_platform_pci_unplug & XEN_UNPLUG_UNNECESSARY)
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(xen_has_pv_and_legacy_disk_devices);
+
 void xen_unplug_emulated_devices(void)
 {
 	int r;

drivers/block/xen-blkfront.c

@@ -1356,7 +1356,7 @@ static int blkfront_probe(struct xenbus_device *dev,
 		char *type;
 		int len;
 		/* no unplug has been done: do not hook devices != xen vbds */
-		if (xen_platform_pci_unplug & XEN_UNPLUG_UNNECESSARY) {
+		if (xen_has_pv_and_legacy_disk_devices()) {
 			int major;
 
 			if (!VDEV_IS_EXTENDED(vdevice))
@@ -2079,7 +2079,7 @@ static int __init xlblk_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
-	if (xen_hvm_domain() && !xen_platform_pci_unplug)
+	if (!xen_has_pv_disk_devices())
 		return -ENODEV;
 
 	if (register_blkdev(XENVBD_MAJOR, DEV_NAME)) {

drivers/char/tpm/xen-tpmfront.c

@@ -17,6 +17,7 @@
 #include <xen/xenbus.h>
 #include <xen/page.h>
 #include "tpm.h"
+#include <xen/platform_pci.h>
 
 struct tpm_private {
 	struct tpm_chip *chip;
@@ -421,6 +422,9 @@ static int __init xen_tpmfront_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
+	if (!xen_has_pv_devices())
+		return -ENODEV;
+
 	return xenbus_register_frontend(&tpmfront_driver);
 }
 module_init(xen_tpmfront_init);

drivers/input/misc/xen-kbdfront.c

@@ -29,6 +29,7 @@
 #include <xen/interface/io/fbif.h>
 #include <xen/interface/io/kbdif.h>
 #include <xen/xenbus.h>
+#include <xen/platform_pci.h>
 
 struct xenkbd_info {
 	struct input_dev *kbd;
@@ -380,6 +381,9 @@ static int __init xenkbd_init(void)
 	if (xen_initial_domain())
 		return -ENODEV;
 
+	if (!xen_has_pv_devices())
+		return -ENODEV;
+
 	return xenbus_register_frontend(&xenkbd_driver);
 }
 

drivers/net/xen-netfront.c

@@ -2115,7 +2115,7 @@ static int __init netif_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
-	if (xen_hvm_domain() && !xen_platform_pci_unplug)
+	if (!xen_has_pv_nic_devices())
 		return -ENODEV;
 
 	pr_info("Initialising Xen virtual ethernet driver\n");

drivers/pci/xen-pcifront.c

@@ -20,6 +20,7 @@
 #include <linux/workqueue.h>
 #include <linux/bitops.h>
 #include <linux/time.h>
+#include <xen/platform_pci.h>
 
 #include <asm/xen/swiotlb-xen.h>
 #define INVALID_GRANT_REF (0)
@@ -1138,6 +1139,9 @@ static int __init pcifront_init(void)
 	if (!xen_pv_domain() || xen_initial_domain())
 		return -ENODEV;
 
+	if (!xen_has_pv_devices())
+		return -ENODEV;
+
 	pci_frontend_registrar(1 /* enable */);
 
 	return xenbus_register_frontend(&xenpci_driver);

drivers/video/xen-fbfront.c

@@ -35,6 +35,7 @@
 #include <xen/interface/io/fbif.h>
 #include <xen/interface/io/protocols.h>
 #include <xen/xenbus.h>
+#include <xen/platform_pci.h>
 
 struct xenfb_info {
 	unsigned char		*fb;
@@ -699,6 +700,9 @@ static int __init xenfb_init(void)
 	if (xen_initial_domain())
 		return -ENODEV;
 
+	if (!xen_has_pv_devices())
+		return -ENODEV;
+
 	return xenbus_register_frontend(&xenfb_driver);
 }
 

drivers/xen/xenbus/xenbus_probe_frontend.c

@@ -496,7 +496,7 @@ subsys_initcall(xenbus_probe_frontend_init);
 #ifndef MODULE
 static int __init boot_wait_for_devices(void)
 {
-	if (xen_hvm_domain() && !xen_platform_pci_unplug)
+	if (!xen_has_pv_devices())
 		return -ENODEV;
 
 	ready_to_wait_for_devices = 1;

include/xen/platform_pci.h

@@ -48,4 +48,27 @@ static inline int xen_must_unplug_disks(void) {
 
 extern int xen_platform_pci_unplug;
 
+#if defined(CONFIG_XEN_PVHVM)
+extern bool xen_has_pv_devices(void);
+extern bool xen_has_pv_disk_devices(void);
+extern bool xen_has_pv_nic_devices(void);
+extern bool xen_has_pv_and_legacy_disk_devices(void);
+#else
+static inline bool xen_has_pv_devices(void)
+{
+	return IS_ENABLED(CONFIG_XEN);
+}
+static inline bool xen_has_pv_disk_devices(void)
+{
+	return IS_ENABLED(CONFIG_XEN);
+}
+static inline bool xen_has_pv_nic_devices(void)
+{
+	return IS_ENABLED(CONFIG_XEN);
+}
+static inline bool xen_has_pv_and_legacy_disk_devices(void)
+{
+	return false;
+}
+#endif
 #endif /* _XEN_PLATFORM_PCI_H */