[v12,03/15] vpci: add hooks for PCI device assign/de-assign

Commit Message

Stewart Hildebrand Jan. 9, 2024, 9:51 p.m. UTC

From: Oleksandr Andrushchenko <[e-mail]>

When a PCI device gets assigned/de-assigned we need to
initialize/de-initialize vPCI state for the device.

Also, rename vpci_add_handlers() to vpci_assign_device() and
vpci_remove_device() to vpci_deassign_device() to better reflect role
of the functions.

Signed-off-by: Oleksandr Andrushchenko <[e-mail]>
Signed-off-by: Volodymyr Babchuk <[e-mail]>
Reviewed-by: Roger Pau Monné <[e-mail]>
Signed-off-by: Stewart Hildebrand <[e-mail]>
---
In v12:
 - Add Roger's R-b
 - Clean up comment in xen/include/xen/vpci.h
 - Add comment in xen/drivers/passthrough/pci.c:deassign_device() to
   clarify vpci_assign_device() call
In v11:
- Call vpci_assign_device() in "deassign_device" if IOMMU call
"reassign_device" was successful.
In v10:
- removed HAS_VPCI_GUEST_SUPPORT checks
- HAS_VPCI_GUEST_SUPPORT config option (in Kconfig) as it is not used
  anywhere
In v9:
- removed previous  vpci_[de]assign_device function and renamed
  existing handlers
- dropped attempts to handle errors in assign_device() function
- do not call vpci_assign_device for dom_io
- use d instead of pdev->domain
- use IS_ENABLED macro
In v8:
- removed vpci_deassign_device
In v6:
- do not pass struct domain to vpci_{assign|deassign}_device as
  pdev->domain can be used
- do not leave the device assigned (pdev->domain == new domain) in case
  vpci_assign_device fails: try to de-assign and if this also fails, then
  crash the domain
In v5:
- do not split code into run_vpci_init
- do not check for is_system_domain in vpci_{de}assign_device
- do not use vpci_remove_device_handlers_locked and re-allocate
  pdev->vpci completely
- make vpci_deassign_device void
In v4:
 - de-assign vPCI from the previous domain on device assignment
 - do not remove handlers in vpci_assign_device as those must not
   exist at that point
In v3:
 - remove toolstack roll-back description from the commit message
   as error are to be handled with proper cleanup in Xen itself
 - remove __must_check
 - remove redundant rc check while assigning devices
 - fix redundant CONFIG_HAS_VPCI check for CONFIG_HAS_VPCI_GUEST_SUPPORT
 - use REGISTER_VPCI_INIT machinery to run required steps on device
   init/assign: add run_vpci_init helper
In v2:
- define CONFIG_HAS_VPCI_GUEST_SUPPORT so dead code is not compiled
  for x86
In v1:
 - constify struct pci_dev where possible
 - do not open code is_system_domain()
 - extended the commit message
---
 xen/drivers/passthrough/pci.c | 25 +++++++++++++++++++++----
 xen/drivers/vpci/header.c     |  2 +-
 xen/drivers/vpci/vpci.c       |  6 +++---
 xen/include/xen/vpci.h        | 10 +++++-----
 4 files changed, 30 insertions(+), 13 deletions(-)

Comments

Jan Beulich Jan. 23, 2024, 2:36 p.m. UTC | #1

On 09.01.2024 22:51, Stewart Hildebrand wrote:
> From: Oleksandr Andrushchenko <[e-mail]>
> 
> When a PCI device gets assigned/de-assigned we need to
> initialize/de-initialize vPCI state for the device.
> 
> Also, rename vpci_add_handlers() to vpci_assign_device() and
> vpci_remove_device() to vpci_deassign_device() to better reflect role
> of the functions.
> 
> Signed-off-by: Oleksandr Andrushchenko <[e-mail]>
> Signed-off-by: Volodymyr Babchuk <[e-mail]>
> Reviewed-by: Roger Pau Monné <[e-mail]>
> Signed-off-by: Stewart Hildebrand <[e-mail]>

Acked-by: Jan Beulich <[e-mail]>

Stewart Hildebrand Jan. 30, 2024, 7:22 p.m. UTC | #2

On 1/9/24 16:51, Stewart Hildebrand wrote:
> diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c
> index 3a973324bca1..a902de6a8693 100644
> --- a/xen/drivers/passthrough/pci.c
> +++ b/xen/drivers/passthrough/pci.c
> @@ -1476,6 +1485,10 @@ static int assign_device(struct domain *d, u16 seg, u8 bus, u8 devfn, u32 flag)
>      if ( pdev->broken && d != hardware_domain && d != dom_io )
>          goto done;
>  
> +    write_lock(&pdev->domain->pci_lock);
> +    vpci_deassign_device(pdev);
> +    write_unlock(&pdev->domain->pci_lock);
> +
>      rc = pdev_msix_assign(d, pdev);
>      if ( rc )
>          goto done;
> @@ -1502,6 +1515,10 @@ static int assign_device(struct domain *d, u16 seg, u8 bus, u8 devfn, u32 flag)
>                          pci_to_dev(pdev), flag);
>      }
>  

After rebasing this on the following commit:

  cb4ecb3cc17b ("pci: fail device assignment if phantom functions cannot be assigned")

I'll add this here:

    if ( rc )
        goto done;

I'll plan on retaining Roger's R-b tag and and Jan's A-b tags for v13.

> +    write_lock(&d->pci_lock);
> +    rc = vpci_assign_device(pdev);
> +    write_unlock(&d->pci_lock);
> +
>   done:
>      if ( rc )
>          printk(XENLOG_G_WARNING "%pd: assign (%pp) failed (%d)\n",

Patch

diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c
index 3a973324bca1..a902de6a8693 100644
--- a/xen/drivers/passthrough/pci.c
+++ b/xen/drivers/passthrough/pci.c
@@ -755,7 +755,7 @@  int pci_add_device(u16 seg, u8 bus, u8 devfn,
          * For devices not discovered by Xen during boot, add vPCI handlers
          * when Dom0 first informs Xen about such devices.
          */
-        ret = vpci_add_handlers(pdev);
+        ret = vpci_assign_device(pdev);
         if ( ret )
         {
             list_del(&pdev->domain_list);
@@ -769,7 +769,7 @@  int pci_add_device(u16 seg, u8 bus, u8 devfn,
         if ( ret )
         {
             write_lock(&hardware_domain->pci_lock);
-            vpci_remove_device(pdev);
+            vpci_deassign_device(pdev);
             list_del(&pdev->domain_list);
             write_unlock(&hardware_domain->pci_lock);
             pdev->domain = NULL;
@@ -817,7 +817,7 @@  int pci_remove_device(u16 seg, u8 bus, u8 devfn)
     list_for_each_entry ( pdev, &pseg->alldevs_list, alldevs_list )
         if ( pdev->bus == bus && pdev->devfn == devfn )
         {
-            vpci_remove_device(pdev);
+            vpci_deassign_device(pdev);
             pci_cleanup_msi(pdev);
             ret = iommu_remove_device(pdev);
             if ( pdev->domain )
@@ -875,6 +875,10 @@  static int deassign_device(struct domain *d, uint16_t seg, uint8_t bus,
             goto out;
     }
 
+    write_lock(&d->pci_lock);
+    vpci_deassign_device(pdev);
+    write_unlock(&d->pci_lock);
+
     devfn = pdev->devfn;
     ret = iommu_call(hd->platform_ops, reassign_device, d, target, devfn,
                      pci_to_dev(pdev));
@@ -886,6 +890,11 @@  static int deassign_device(struct domain *d, uint16_t seg, uint8_t bus,
 
     pdev->fault.count = 0;
 
+    write_lock(&target->pci_lock);
+    /* Re-assign back to hardware_domain */
+    ret = vpci_assign_device(pdev);
+    write_unlock(&target->pci_lock);
+
  out:
     if ( ret )
         printk(XENLOG_G_ERR "%pd: deassign (%pp) failed (%d)\n",
@@ -1146,7 +1155,7 @@  static void __hwdom_init setup_one_hwdom_device(const struct setup_hwdom *ctxt,
               PCI_SLOT(devfn) == PCI_SLOT(pdev->devfn) );
 
     write_lock(&ctxt->d->pci_lock);
-    err = vpci_add_handlers(pdev);
+    err = vpci_assign_device(pdev);
     write_unlock(&ctxt->d->pci_lock);
     if ( err )
         printk(XENLOG_ERR "setup of vPCI for d%d failed: %d\n",
@@ -1476,6 +1485,10 @@  static int assign_device(struct domain *d, u16 seg, u8 bus, u8 devfn, u32 flag)
     if ( pdev->broken && d != hardware_domain && d != dom_io )
         goto done;
 
+    write_lock(&pdev->domain->pci_lock);
+    vpci_deassign_device(pdev);
+    write_unlock(&pdev->domain->pci_lock);
+
     rc = pdev_msix_assign(d, pdev);
     if ( rc )
         goto done;
@@ -1502,6 +1515,10 @@  static int assign_device(struct domain *d, u16 seg, u8 bus, u8 devfn, u32 flag)
                         pci_to_dev(pdev), flag);
     }
 
+    write_lock(&d->pci_lock);
+    rc = vpci_assign_device(pdev);
+    write_unlock(&d->pci_lock);
+
  done:
     if ( rc )
         printk(XENLOG_G_WARNING "%pd: assign (%pp) failed (%d)\n",
diff --git a/xen/drivers/vpci/header.c b/xen/drivers/vpci/header.c
index 8f5850b8cf6d..2f2d98ada012 100644
--- a/xen/drivers/vpci/header.c
+++ b/xen/drivers/vpci/header.c
@@ -191,7 +191,7 @@  bool vpci_process_pending(struct vcpu *v)
              * killed in order to avoid leaking stale p2m mappings on
              * failure.
              */
-            vpci_remove_device(v->vpci.pdev);
+            vpci_deassign_device(v->vpci.pdev);
         write_unlock(&v->domain->pci_lock);
     }
 
diff --git a/xen/drivers/vpci/vpci.c b/xen/drivers/vpci/vpci.c
index e98693e1dc3e..42eac85106a3 100644
--- a/xen/drivers/vpci/vpci.c
+++ b/xen/drivers/vpci/vpci.c
@@ -40,7 +40,7 @@  extern vpci_register_init_t *const __start_vpci_array[];
 extern vpci_register_init_t *const __end_vpci_array[];
 #define NUM_VPCI_INIT (__end_vpci_array - __start_vpci_array)
 
-void vpci_remove_device(struct pci_dev *pdev)
+void vpci_deassign_device(struct pci_dev *pdev)
 {
     ASSERT(rw_is_write_locked(&pdev->domain->pci_lock));
 
@@ -73,7 +73,7 @@  void vpci_remove_device(struct pci_dev *pdev)
     pdev->vpci = NULL;
 }
 
-int vpci_add_handlers(struct pci_dev *pdev)
+int vpci_assign_device(struct pci_dev *pdev)
 {
     unsigned int i;
     const unsigned long *ro_map;
@@ -107,7 +107,7 @@  int vpci_add_handlers(struct pci_dev *pdev)
     }
 
     if ( rc )
-        vpci_remove_device(pdev);
+        vpci_deassign_device(pdev);
 
     return rc;
 }
diff --git a/xen/include/xen/vpci.h b/xen/include/xen/vpci.h
index d20c301a3db3..99fe76f08ace 100644
--- a/xen/include/xen/vpci.h
+++ b/xen/include/xen/vpci.h
@@ -25,11 +25,11 @@  typedef int vpci_register_init_t(struct pci_dev *dev);
   static vpci_register_init_t *const x##_entry  \
                __used_section(".data.vpci." p) = x
 
-/* Add vPCI handlers to device. */
-int __must_check vpci_add_handlers(struct pci_dev *pdev);
+/* Assign vPCI to device by adding handlers. */
+int __must_check vpci_assign_device(struct pci_dev *pdev);
 
 /* Remove all handlers and free vpci related structures. */
-void vpci_remove_device(struct pci_dev *pdev);
+void vpci_deassign_device(struct pci_dev *pdev);
 
 /* Add/remove a register handler. */
 int __must_check vpci_add_register_mask(struct vpci *vpci,
@@ -255,12 +255,12 @@  bool vpci_ecam_read(pci_sbdf_t sbdf, unsigned int reg, unsigned int len,
 #else /* !CONFIG_HAS_VPCI */
 struct vpci_vcpu {};
 
-static inline int vpci_add_handlers(struct pci_dev *pdev)
+static inline int vpci_assign_device(struct pci_dev *pdev)
 {
     return 0;
 }
 
-static inline void vpci_remove_device(struct pci_dev *pdev) { }
+static inline void vpci_deassign_device(struct pci_dev *pdev) { }
 
 static inline void vpci_dump_msi(void) { }