diff mbox series

[4/4] vpci: move lock outside of struct vpci

Message ID 20220201162508.417008-5-andr2000@gmail.com (mailing list archive)
State New, archived
Headers show
Series PCI devices passthrough pre-req patches | expand

Commit Message

Oleksandr Andrushchenko Feb. 1, 2022, 4:25 p.m. UTC
From: Roger Pau Monne <roger.pau@citrix.com>

This way the lock can be used to check whether vpci is present, and
removal can be performed while holding the lock, in order to make
sure there are no accesses to the contents of the vpci struct.
Previously removal could race with vpci_read for example, since the
lock was dropped prior to freeing pdev->vpci.

Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
---
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Julien Grall <julien@xen.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
---
New in v5 of this series: this is an updated version of the patch published at
https://lore.kernel.org/xen-devel/20180717094830.54806-2-roger.pau@citrix.com/

Changes since v5:
 - do not split code into vpci_remove_device_handlers_locked yet
 - move INIT_LIST_HEAD outside the locked region (Jan)
 - stripped out locking optimizations for vpci_{read|write} into a
   dedicated patch
Changes since v2:
 - fixed pdev->vpci = xzalloc(struct vpci); under spin_lock (Jan)
Changes since v1:
 - Assert that vpci_lock is locked in vpci_remove_device_locked.
 - Remove double newline.
 - Shrink critical section in vpci_{read/write}.
---
 tools/tests/vpci/emul.h       |  5 ++-
 tools/tests/vpci/main.c       |  4 +--
 xen/arch/x86/hvm/vmsi.c       |  8 ++---
 xen/drivers/passthrough/pci.c |  1 +
 xen/drivers/vpci/header.c     | 21 ++++++++----
 xen/drivers/vpci/msi.c        | 11 ++++--
 xen/drivers/vpci/msix.c       |  8 ++---
 xen/drivers/vpci/vpci.c       | 63 ++++++++++++++++++++++-------------
 xen/include/xen/pci.h         |  1 +
 xen/include/xen/vpci.h        |  3 +-
 10 files changed, 78 insertions(+), 47 deletions(-)

Comments

Jan Beulich Feb. 2, 2022, 9:22 a.m. UTC | #1
On 01.02.2022 17:25, Oleksandr Andrushchenko wrote:
> From: Roger Pau Monne <roger.pau@citrix.com>
> 
> This way the lock can be used to check whether vpci is present, and
> removal can be performed while holding the lock, in order to make
> sure there are no accesses to the contents of the vpci struct.
> Previously removal could race with vpci_read for example, since the
> lock was dropped prior to freeing pdev->vpci.
> 
> Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
> Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
> ---
> Cc: Andrew Cooper <andrew.cooper3@citrix.com>
> Cc: Jan Beulich <jbeulich@suse.com>
> Cc: Julien Grall <julien@xen.org>
> Cc: Stefano Stabellini <sstabellini@kernel.org>
> ---
> New in v5 of this series: this is an updated version of the patch published at
> https://lore.kernel.org/xen-devel/20180717094830.54806-2-roger.pau@citrix.com/
> 
> Changes since v5:

This is a little odd in a series implicitly tagged as v1.

> --- a/xen/drivers/vpci/header.c
> +++ b/xen/drivers/vpci/header.c
> @@ -142,12 +142,13 @@ bool vpci_process_pending(struct vcpu *v)
>          if ( rc == -ERESTART )
>              return true;
>  
> -        spin_lock(&v->vpci.pdev->vpci->lock);
> -        /* Disable memory decoding unconditionally on failure. */
> -        modify_decoding(v->vpci.pdev,
> -                        rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
> -                        !rc && v->vpci.rom_only);
> -        spin_unlock(&v->vpci.pdev->vpci->lock);
> +        spin_lock(&v->vpci.pdev->vpci_lock);
> +        if ( v->vpci.pdev->vpci )
> +            /* Disable memory decoding unconditionally on failure. */
> +            modify_decoding(v->vpci.pdev,
> +                            rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
> +                            !rc && v->vpci.rom_only);
> +        spin_unlock(&v->vpci.pdev->vpci_lock);

While I certainly see the point, the addition of this if() (and a
few more elsewhere) isn't covered by title or description.

> --- a/xen/drivers/vpci/vpci.c
> +++ b/xen/drivers/vpci/vpci.c
> @@ -35,12 +35,10 @@ 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)
> +static void vpci_remove_device_locked(struct pci_dev *pdev)
>  {
> -    if ( !has_vpci(pdev->domain) )
> -        return;
> +    ASSERT(spin_is_locked(&pdev->vpci_lock));

While, unlike here, ...

> @@ -152,8 +164,6 @@ int vpci_add_register(struct vpci *vpci, vpci_read_t *read_handler,
>      r->offset = offset;
>      r->private = data;
>  
> -    spin_lock(&vpci->lock);

... you did explain why you don't want to add a similar assertion
here, I think in return the function wants to have a comment added
that it's required to be called with the respective lock held. I
notice you did so for the declaration, but I think such a comment
would better be present at the definition as well. Same for
vpci_remove_register() then, obviously.

> @@ -311,7 +316,7 @@ static uint32_t merge_result(uint32_t data, uint32_t new, unsigned int size,
>  uint32_t vpci_read(pci_sbdf_t sbdf, unsigned int reg, unsigned int size)
>  {
>      const struct domain *d = current->domain;
> -    const struct pci_dev *pdev;
> +    struct pci_dev *pdev;
>      const struct vpci_register *r;
>      unsigned int data_offset = 0;
>      uint32_t data = ~(uint32_t)0;
> @@ -327,7 +332,12 @@ uint32_t vpci_read(pci_sbdf_t sbdf, unsigned int reg, unsigned int size)
>      if ( !pdev )
>          return vpci_read_hw(sbdf, reg, size);
>  
> -    spin_lock(&pdev->vpci->lock);
> +    spin_lock(&pdev->vpci_lock);
> +    if ( !pdev->vpci )
> +    {
> +        spin_unlock(&pdev->vpci_lock);
> +        return vpci_read_hw(sbdf, reg, size);
> +    }

In this case as well as in its write counterpart it becomes even more
important to justify (in the description) the new behavior. It is not
obvious at all that the absence of a struct vpci should be taken as
an indication that the underlying device needs accessing instead.
This also cannot be inferred from the "!pdev" case visible in context.
In that case we have no record of a device at this SBDF, and hence the
fallback pretty clearly is a "just in case" one. Yet if we know of a
device, the absence of a struct vpci may mean various possible things.

Jan
Roger Pau Monné Feb. 2, 2022, 9:45 a.m. UTC | #2
On Tue, Feb 01, 2022 at 06:25:08PM +0200, Oleksandr Andrushchenko wrote:
> From: Roger Pau Monne <roger.pau@citrix.com>
> 
> This way the lock can be used to check whether vpci is present, and
> removal can be performed while holding the lock, in order to make
> sure there are no accesses to the contents of the vpci struct.
> Previously removal could race with vpci_read for example, since the
> lock was dropped prior to freeing pdev->vpci.
> 
> Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
> Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
> ---
> Cc: Andrew Cooper <andrew.cooper3@citrix.com>
> Cc: Jan Beulich <jbeulich@suse.com>
> Cc: Julien Grall <julien@xen.org>
> Cc: Stefano Stabellini <sstabellini@kernel.org>
> ---
> New in v5 of this series: this is an updated version of the patch published at
> https://lore.kernel.org/xen-devel/20180717094830.54806-2-roger.pau@citrix.com/
> 
> Changes since v5:
>  - do not split code into vpci_remove_device_handlers_locked yet
>  - move INIT_LIST_HEAD outside the locked region (Jan)
>  - stripped out locking optimizations for vpci_{read|write} into a
>    dedicated patch
> Changes since v2:
>  - fixed pdev->vpci = xzalloc(struct vpci); under spin_lock (Jan)
> Changes since v1:
>  - Assert that vpci_lock is locked in vpci_remove_device_locked.
>  - Remove double newline.
>  - Shrink critical section in vpci_{read/write}.
> ---
>  tools/tests/vpci/emul.h       |  5 ++-
>  tools/tests/vpci/main.c       |  4 +--
>  xen/arch/x86/hvm/vmsi.c       |  8 ++---
>  xen/drivers/passthrough/pci.c |  1 +
>  xen/drivers/vpci/header.c     | 21 ++++++++----
>  xen/drivers/vpci/msi.c        | 11 ++++--
>  xen/drivers/vpci/msix.c       |  8 ++---
>  xen/drivers/vpci/vpci.c       | 63 ++++++++++++++++++++++-------------
>  xen/include/xen/pci.h         |  1 +
>  xen/include/xen/vpci.h        |  3 +-
>  10 files changed, 78 insertions(+), 47 deletions(-)
> 
> diff --git a/tools/tests/vpci/emul.h b/tools/tests/vpci/emul.h
> index 2e1d3057c9d8..d018fb5eef21 100644
> --- a/tools/tests/vpci/emul.h
> +++ b/tools/tests/vpci/emul.h
> @@ -44,6 +44,7 @@ struct domain {
>  };
>  
>  struct pci_dev {
> +    bool vpci_lock;
>      struct vpci *vpci;
>  };
>  
> @@ -53,10 +54,8 @@ struct vcpu
>  };
>  
>  extern const struct vcpu *current;
> -extern const struct pci_dev test_pdev;
> +extern struct pci_dev test_pdev;
>  
> -typedef bool spinlock_t;
> -#define spin_lock_init(l) (*(l) = false)
>  #define spin_lock(l) (*(l) = true)
>  #define spin_unlock(l) (*(l) = false)
>  
> diff --git a/tools/tests/vpci/main.c b/tools/tests/vpci/main.c
> index b9a0a6006bb9..26c95b08b6b1 100644
> --- a/tools/tests/vpci/main.c
> +++ b/tools/tests/vpci/main.c
> @@ -23,7 +23,8 @@ static struct vpci vpci;
>  
>  const static struct domain d;
>  
> -const struct pci_dev test_pdev = {
> +struct pci_dev test_pdev = {
> +    .vpci_lock = false,

Nit: vpci_lock will already be initialized to false by default, so
this is redundant.

>      .vpci = &vpci,
>  };
>  
> @@ -158,7 +159,6 @@ main(int argc, char **argv)
>      int rc;
>  
>      INIT_LIST_HEAD(&vpci.handlers);
> -    spin_lock_init(&vpci.lock);
>  
>      VPCI_ADD_REG(vpci_read32, vpci_write32, 0, 4, r0);
>      VPCI_READ_CHECK(0, 4, r0);
> diff --git a/xen/arch/x86/hvm/vmsi.c b/xen/arch/x86/hvm/vmsi.c
> index 13e2a190b439..1f7a37f78264 100644
> --- a/xen/arch/x86/hvm/vmsi.c
> +++ b/xen/arch/x86/hvm/vmsi.c
> @@ -910,14 +910,14 @@ int vpci_msix_arch_print(const struct vpci_msix *msix)
>          {
>              struct pci_dev *pdev = msix->pdev;
>  
> -            spin_unlock(&msix->pdev->vpci->lock);
> +            spin_unlock(&msix->pdev->vpci_lock);
>              process_pending_softirqs();
>              /* NB: we assume that pdev cannot go away for an alive domain. */
> -            if ( !pdev->vpci || !spin_trylock(&pdev->vpci->lock) )
> +            if ( !spin_trylock(&pdev->vpci_lock) )
>                  return -EBUSY;
> -            if ( pdev->vpci->msix != msix )
> +            if ( !pdev->vpci || pdev->vpci->msix != msix )
>              {
> -                spin_unlock(&pdev->vpci->lock);
> +                spin_unlock(&pdev->vpci_lock);
>                  return -EAGAIN;
>              }
>          }
> diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c
> index 1fad80362f0e..af648c6a19b5 100644
> --- a/xen/drivers/passthrough/pci.c
> +++ b/xen/drivers/passthrough/pci.c
> @@ -328,6 +328,7 @@ static struct pci_dev *alloc_pdev(struct pci_seg *pseg, u8 bus, u8 devfn)
>      *((u8*) &pdev->bus) = bus;
>      *((u8*) &pdev->devfn) = devfn;
>      pdev->domain = NULL;
> +    spin_lock_init(&pdev->vpci_lock);
>  
>      arch_pci_init_pdev(pdev);
>  
> diff --git a/xen/drivers/vpci/header.c b/xen/drivers/vpci/header.c
> index 40ff79c33f8f..bd23c0274d48 100644
> --- a/xen/drivers/vpci/header.c
> +++ b/xen/drivers/vpci/header.c
> @@ -142,12 +142,13 @@ bool vpci_process_pending(struct vcpu *v)
>          if ( rc == -ERESTART )
>              return true;
>  
> -        spin_lock(&v->vpci.pdev->vpci->lock);
> -        /* Disable memory decoding unconditionally on failure. */
> -        modify_decoding(v->vpci.pdev,
> -                        rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
> -                        !rc && v->vpci.rom_only);
> -        spin_unlock(&v->vpci.pdev->vpci->lock);
> +        spin_lock(&v->vpci.pdev->vpci_lock);
> +        if ( v->vpci.pdev->vpci )
> +            /* Disable memory decoding unconditionally on failure. */
> +            modify_decoding(v->vpci.pdev,
> +                            rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
> +                            !rc && v->vpci.rom_only);
> +        spin_unlock(&v->vpci.pdev->vpci_lock);
>  
>          rangeset_destroy(v->vpci.mem);
>          v->vpci.mem = NULL;
> @@ -285,6 +286,12 @@ static int modify_bars(const struct pci_dev *pdev, uint16_t cmd, bool rom_only)
>                  continue;
>          }
>  
> +        spin_lock(&tmp->vpci_lock);
> +        if ( !tmp->vpci )
> +        {
> +            spin_unlock(&tmp->vpci_lock);
> +            continue;
> +        }
>          for ( i = 0; i < ARRAY_SIZE(tmp->vpci->header.bars); i++ )
>          {
>              const struct vpci_bar *bar = &tmp->vpci->header.bars[i];
> @@ -303,12 +310,14 @@ static int modify_bars(const struct pci_dev *pdev, uint16_t cmd, bool rom_only)
>              rc = rangeset_remove_range(mem, start, end);
>              if ( rc )
>              {
> +                spin_unlock(&tmp->vpci_lock);
>                  printk(XENLOG_G_WARNING "Failed to remove [%lx, %lx]: %d\n",
>                         start, end, rc);
>                  rangeset_destroy(mem);
>                  return rc;
>              }
>          }
> +        spin_unlock(&tmp->vpci_lock);
>      }
>  
>      ASSERT(dev);
> diff --git a/xen/drivers/vpci/msi.c b/xen/drivers/vpci/msi.c
> index 5757a7aed20f..e3ce46869dad 100644
> --- a/xen/drivers/vpci/msi.c
> +++ b/xen/drivers/vpci/msi.c
> @@ -270,7 +270,7 @@ void vpci_dump_msi(void)
>      rcu_read_lock(&domlist_read_lock);
>      for_each_domain ( d )
>      {
> -        const struct pci_dev *pdev;
> +        struct pci_dev *pdev;
>  
>          if ( !has_vpci(d) )
>              continue;
> @@ -282,8 +282,13 @@ void vpci_dump_msi(void)
>              const struct vpci_msi *msi;
>              const struct vpci_msix *msix;
>  
> -            if ( !pdev->vpci || !spin_trylock(&pdev->vpci->lock) )
> +            if ( !spin_trylock(&pdev->vpci_lock) )
>                  continue;
> +            if ( !pdev->vpci )
> +            {
> +                spin_unlock(&pdev->vpci_lock);
> +                continue;
> +            }
>  
>              msi = pdev->vpci->msi;
>              if ( msi && msi->enabled )
> @@ -323,7 +328,7 @@ void vpci_dump_msi(void)
>                  }
>              }
>  
> -            spin_unlock(&pdev->vpci->lock);
> +            spin_unlock(&pdev->vpci_lock);
>              process_pending_softirqs();
>          }
>      }
> diff --git a/xen/drivers/vpci/msix.c b/xen/drivers/vpci/msix.c
> index 846f1b8d7038..5310cc3ff520 100644
> --- a/xen/drivers/vpci/msix.c
> +++ b/xen/drivers/vpci/msix.c
> @@ -225,7 +225,7 @@ static int msix_read(struct vcpu *v, unsigned long addr, unsigned int len,

I think you also need to add locking to msix_find, otherwise it will
dereference pdev->vpci without holding the vpci_lock.

It might be a better approach to rename msix_find to msix_get and
return the vpci_msix struct with the vpci_lock taken, so we can assert
it's not going to disappear under our feet. Then you will also need to
add a msix_put function that releases the lock.

>          return X86EMUL_OKAY;
>      }
>  
> -    spin_lock(&msix->pdev->vpci->lock);
> +    spin_lock(&msix->pdev->vpci_lock);
>      entry = get_entry(msix, addr);
>      offset = addr & (PCI_MSIX_ENTRY_SIZE - 1);
>  
> @@ -254,7 +254,7 @@ static int msix_read(struct vcpu *v, unsigned long addr, unsigned int len,
>          ASSERT_UNREACHABLE();
>          break;
>      }
> -    spin_unlock(&msix->pdev->vpci->lock);
> +    spin_unlock(&msix->pdev->vpci_lock);
>  
>      return X86EMUL_OKAY;
>  }
> @@ -297,7 +297,7 @@ static int msix_write(struct vcpu *v, unsigned long addr, unsigned int len,
>          return X86EMUL_OKAY;
>      }
>  
> -    spin_lock(&msix->pdev->vpci->lock);
> +    spin_lock(&msix->pdev->vpci_lock);
>      entry = get_entry(msix, addr);
>      offset = addr & (PCI_MSIX_ENTRY_SIZE - 1);
>  
> @@ -370,7 +370,7 @@ static int msix_write(struct vcpu *v, unsigned long addr, unsigned int len,
>          ASSERT_UNREACHABLE();
>          break;
>      }
> -    spin_unlock(&msix->pdev->vpci->lock);
> +    spin_unlock(&msix->pdev->vpci_lock);
>  
>      return X86EMUL_OKAY;
>  }
> diff --git a/xen/drivers/vpci/vpci.c b/xen/drivers/vpci/vpci.c
> index fb0947179b79..c015a4d77540 100644
> --- a/xen/drivers/vpci/vpci.c
> +++ b/xen/drivers/vpci/vpci.c
> @@ -35,12 +35,10 @@ 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)
> +static void vpci_remove_device_locked(struct pci_dev *pdev)

Nit: since it's a static function you can drop the vpci_ prefix here.

Thanks, Roger.
Oleksandr Andrushchenko Feb. 2, 2022, 10:15 a.m. UTC | #3
Hi, Roger!

On 02.02.22 11:45, Roger Pau Monné wrote:
> On Tue, Feb 01, 2022 at 06:25:08PM +0200, Oleksandr Andrushchenko wrote:
>> From: Roger Pau Monne <roger.pau@citrix.com>
>>
>> This way the lock can be used to check whether vpci is present, and
>> removal can be performed while holding the lock, in order to make
>> sure there are no accesses to the contents of the vpci struct.
>> Previously removal could race with vpci_read for example, since the
>> lock was dropped prior to freeing pdev->vpci.
>>
>> Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
>> Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
>> ---
>> Cc: Andrew Cooper <andrew.cooper3@citrix.com>
>> Cc: Jan Beulich <jbeulich@suse.com>
>> Cc: Julien Grall <julien@xen.org>
>> Cc: Stefano Stabellini <sstabellini@kernel.org>
>> ---
>> New in v5 of this series: this is an updated version of the patch published at
>> https://urldefense.com/v3/__https://lore.kernel.org/xen-devel/20180717094830.54806-2-roger.pau@citrix.com/__;!!GF_29dbcQIUBPA!ilhEn2M-44dKY8rsVO7qGmUSY22vSHwNaGJNUqhwvr-V2kdb-FDYL6f39FS8pKJm3q8HnOzyuA$ [lore[.]kernel[.]org]
>>
>> Changes since v5:
>>   - do not split code into vpci_remove_device_handlers_locked yet
>>   - move INIT_LIST_HEAD outside the locked region (Jan)
>>   - stripped out locking optimizations for vpci_{read|write} into a
>>     dedicated patch
>> Changes since v2:
>>   - fixed pdev->vpci = xzalloc(struct vpci); under spin_lock (Jan)
>> Changes since v1:
>>   - Assert that vpci_lock is locked in vpci_remove_device_locked.
>>   - Remove double newline.
>>   - Shrink critical section in vpci_{read/write}.
>> ---
>>   tools/tests/vpci/emul.h       |  5 ++-
>>   tools/tests/vpci/main.c       |  4 +--
>>   xen/arch/x86/hvm/vmsi.c       |  8 ++---
>>   xen/drivers/passthrough/pci.c |  1 +
>>   xen/drivers/vpci/header.c     | 21 ++++++++----
>>   xen/drivers/vpci/msi.c        | 11 ++++--
>>   xen/drivers/vpci/msix.c       |  8 ++---
>>   xen/drivers/vpci/vpci.c       | 63 ++++++++++++++++++++++-------------
>>   xen/include/xen/pci.h         |  1 +
>>   xen/include/xen/vpci.h        |  3 +-
>>   10 files changed, 78 insertions(+), 47 deletions(-)
>>
>> diff --git a/tools/tests/vpci/emul.h b/tools/tests/vpci/emul.h
>> index 2e1d3057c9d8..d018fb5eef21 100644
>> --- a/tools/tests/vpci/emul.h
>> +++ b/tools/tests/vpci/emul.h
>> @@ -44,6 +44,7 @@ struct domain {
>>   };
>>   
>>   struct pci_dev {
>> +    bool vpci_lock;
>>       struct vpci *vpci;
>>   };
>>   
>> @@ -53,10 +54,8 @@ struct vcpu
>>   };
>>   
>>   extern const struct vcpu *current;
>> -extern const struct pci_dev test_pdev;
>> +extern struct pci_dev test_pdev;
>>   
>> -typedef bool spinlock_t;
>> -#define spin_lock_init(l) (*(l) = false)
>>   #define spin_lock(l) (*(l) = true)
>>   #define spin_unlock(l) (*(l) = false)
>>   
>> diff --git a/tools/tests/vpci/main.c b/tools/tests/vpci/main.c
>> index b9a0a6006bb9..26c95b08b6b1 100644
>> --- a/tools/tests/vpci/main.c
>> +++ b/tools/tests/vpci/main.c
>> @@ -23,7 +23,8 @@ static struct vpci vpci;
>>   
>>   const static struct domain d;
>>   
>> -const struct pci_dev test_pdev = {
>> +struct pci_dev test_pdev = {
>> +    .vpci_lock = false,
> Nit: vpci_lock will already be initialized to false by default, so
> this is redundant.
Will remove
>
>>       .vpci = &vpci,
>>   };
>>   
>> @@ -158,7 +159,6 @@ main(int argc, char **argv)
>>       int rc;
>>   
>>       INIT_LIST_HEAD(&vpci.handlers);
>> -    spin_lock_init(&vpci.lock);
>>   
>>       VPCI_ADD_REG(vpci_read32, vpci_write32, 0, 4, r0);
>>       VPCI_READ_CHECK(0, 4, r0);
>> diff --git a/xen/arch/x86/hvm/vmsi.c b/xen/arch/x86/hvm/vmsi.c
>> index 13e2a190b439..1f7a37f78264 100644
>> --- a/xen/arch/x86/hvm/vmsi.c
>> +++ b/xen/arch/x86/hvm/vmsi.c
>> @@ -910,14 +910,14 @@ int vpci_msix_arch_print(const struct vpci_msix *msix)
>>           {
>>               struct pci_dev *pdev = msix->pdev;
>>   
>> -            spin_unlock(&msix->pdev->vpci->lock);
>> +            spin_unlock(&msix->pdev->vpci_lock);
>>               process_pending_softirqs();
>>               /* NB: we assume that pdev cannot go away for an alive domain. */
>> -            if ( !pdev->vpci || !spin_trylock(&pdev->vpci->lock) )
>> +            if ( !spin_trylock(&pdev->vpci_lock) )
>>                   return -EBUSY;
>> -            if ( pdev->vpci->msix != msix )
>> +            if ( !pdev->vpci || pdev->vpci->msix != msix )
>>               {
>> -                spin_unlock(&pdev->vpci->lock);
>> +                spin_unlock(&pdev->vpci_lock);
>>                   return -EAGAIN;
>>               }
>>           }
>> diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c
>> index 1fad80362f0e..af648c6a19b5 100644
>> --- a/xen/drivers/passthrough/pci.c
>> +++ b/xen/drivers/passthrough/pci.c
>> @@ -328,6 +328,7 @@ static struct pci_dev *alloc_pdev(struct pci_seg *pseg, u8 bus, u8 devfn)
>>       *((u8*) &pdev->bus) = bus;
>>       *((u8*) &pdev->devfn) = devfn;
>>       pdev->domain = NULL;
>> +    spin_lock_init(&pdev->vpci_lock);
>>   
>>       arch_pci_init_pdev(pdev);
>>   
>> diff --git a/xen/drivers/vpci/header.c b/xen/drivers/vpci/header.c
>> index 40ff79c33f8f..bd23c0274d48 100644
>> --- a/xen/drivers/vpci/header.c
>> +++ b/xen/drivers/vpci/header.c
>> @@ -142,12 +142,13 @@ bool vpci_process_pending(struct vcpu *v)
>>           if ( rc == -ERESTART )
>>               return true;
>>   
>> -        spin_lock(&v->vpci.pdev->vpci->lock);
>> -        /* Disable memory decoding unconditionally on failure. */
>> -        modify_decoding(v->vpci.pdev,
>> -                        rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
>> -                        !rc && v->vpci.rom_only);
>> -        spin_unlock(&v->vpci.pdev->vpci->lock);
>> +        spin_lock(&v->vpci.pdev->vpci_lock);
>> +        if ( v->vpci.pdev->vpci )
>> +            /* Disable memory decoding unconditionally on failure. */
>> +            modify_decoding(v->vpci.pdev,
>> +                            rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
>> +                            !rc && v->vpci.rom_only);
>> +        spin_unlock(&v->vpci.pdev->vpci_lock);
>>   
>>           rangeset_destroy(v->vpci.mem);
>>           v->vpci.mem = NULL;
>> @@ -285,6 +286,12 @@ static int modify_bars(const struct pci_dev *pdev, uint16_t cmd, bool rom_only)
>>                   continue;
>>           }
>>   
>> +        spin_lock(&tmp->vpci_lock);
>> +        if ( !tmp->vpci )
>> +        {
>> +            spin_unlock(&tmp->vpci_lock);
>> +            continue;
>> +        }
>>           for ( i = 0; i < ARRAY_SIZE(tmp->vpci->header.bars); i++ )
>>           {
>>               const struct vpci_bar *bar = &tmp->vpci->header.bars[i];
>> @@ -303,12 +310,14 @@ static int modify_bars(const struct pci_dev *pdev, uint16_t cmd, bool rom_only)
>>               rc = rangeset_remove_range(mem, start, end);
>>               if ( rc )
>>               {
>> +                spin_unlock(&tmp->vpci_lock);
>>                   printk(XENLOG_G_WARNING "Failed to remove [%lx, %lx]: %d\n",
>>                          start, end, rc);
>>                   rangeset_destroy(mem);
>>                   return rc;
>>               }
>>           }
>> +        spin_unlock(&tmp->vpci_lock);
>>       }
>>   
>>       ASSERT(dev);
>> diff --git a/xen/drivers/vpci/msi.c b/xen/drivers/vpci/msi.c
>> index 5757a7aed20f..e3ce46869dad 100644
>> --- a/xen/drivers/vpci/msi.c
>> +++ b/xen/drivers/vpci/msi.c
>> @@ -270,7 +270,7 @@ void vpci_dump_msi(void)
>>       rcu_read_lock(&domlist_read_lock);
>>       for_each_domain ( d )
>>       {
>> -        const struct pci_dev *pdev;
>> +        struct pci_dev *pdev;
>>   
>>           if ( !has_vpci(d) )
>>               continue;
>> @@ -282,8 +282,13 @@ void vpci_dump_msi(void)
>>               const struct vpci_msi *msi;
>>               const struct vpci_msix *msix;
>>   
>> -            if ( !pdev->vpci || !spin_trylock(&pdev->vpci->lock) )
>> +            if ( !spin_trylock(&pdev->vpci_lock) )
>>                   continue;
>> +            if ( !pdev->vpci )
>> +            {
>> +                spin_unlock(&pdev->vpci_lock);
>> +                continue;
>> +            }
>>   
>>               msi = pdev->vpci->msi;
>>               if ( msi && msi->enabled )
>> @@ -323,7 +328,7 @@ void vpci_dump_msi(void)
>>                   }
>>               }
>>   
>> -            spin_unlock(&pdev->vpci->lock);
>> +            spin_unlock(&pdev->vpci_lock);
>>               process_pending_softirqs();
>>           }
>>       }
>> diff --git a/xen/drivers/vpci/msix.c b/xen/drivers/vpci/msix.c
>> index 846f1b8d7038..5310cc3ff520 100644
>> --- a/xen/drivers/vpci/msix.c
>> +++ b/xen/drivers/vpci/msix.c
>> @@ -225,7 +225,7 @@ static int msix_read(struct vcpu *v, unsigned long addr, unsigned int len,
> I think you also need to add locking to msix_find, otherwise it will
> dereference pdev->vpci without holding the vpci_lock.
>
> It might be a better approach to rename msix_find to msix_get and
> return the vpci_msix struct with the vpci_lock taken, so we can assert
> it's not going to disappear under our feet. Then you will also need to
> add a msix_put function that releases the lock.
Ok, sounds good: so, I'll implement msix_{get|put} then
>
>>           return X86EMUL_OKAY;
>>       }
>>   
>> -    spin_lock(&msix->pdev->vpci->lock);
>> +    spin_lock(&msix->pdev->vpci_lock);
>>       entry = get_entry(msix, addr);
>>       offset = addr & (PCI_MSIX_ENTRY_SIZE - 1);
>>   
>> @@ -254,7 +254,7 @@ static int msix_read(struct vcpu *v, unsigned long addr, unsigned int len,
>>           ASSERT_UNREACHABLE();
>>           break;
>>       }
>> -    spin_unlock(&msix->pdev->vpci->lock);
>> +    spin_unlock(&msix->pdev->vpci_lock);
>>   
>>       return X86EMUL_OKAY;
>>   }
>> @@ -297,7 +297,7 @@ static int msix_write(struct vcpu *v, unsigned long addr, unsigned int len,
>>           return X86EMUL_OKAY;
>>       }
>>   
>> -    spin_lock(&msix->pdev->vpci->lock);
>> +    spin_lock(&msix->pdev->vpci_lock);
>>       entry = get_entry(msix, addr);
>>       offset = addr & (PCI_MSIX_ENTRY_SIZE - 1);
>>   
>> @@ -370,7 +370,7 @@ static int msix_write(struct vcpu *v, unsigned long addr, unsigned int len,
>>           ASSERT_UNREACHABLE();
>>           break;
>>       }
>> -    spin_unlock(&msix->pdev->vpci->lock);
>> +    spin_unlock(&msix->pdev->vpci_lock);
>>   
>>       return X86EMUL_OKAY;
>>   }
>> diff --git a/xen/drivers/vpci/vpci.c b/xen/drivers/vpci/vpci.c
>> index fb0947179b79..c015a4d77540 100644
>> --- a/xen/drivers/vpci/vpci.c
>> +++ b/xen/drivers/vpci/vpci.c
>> @@ -35,12 +35,10 @@ 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)
>> +static void vpci_remove_device_locked(struct pci_dev *pdev)
> Nit: since it's a static function you can drop the vpci_ prefix here.
This function is going to be used outside later on, but not yet.
So, I can change the name and then change it back once it is
used by others.
What's your preference here?
>
> Thanks, Roger.
Thank you,
Oleksandr
Oleksandr Andrushchenko Feb. 2, 2022, 11:03 a.m. UTC | #4
Hi, Jan!

On 02.02.22 11:22, Jan Beulich wrote:
> On 01.02.2022 17:25, Oleksandr Andrushchenko wrote:
>> From: Roger Pau Monne <roger.pau@citrix.com>
>>
>> This way the lock can be used to check whether vpci is present, and
>> removal can be performed while holding the lock, in order to make
>> sure there are no accesses to the contents of the vpci struct.
>> Previously removal could race with vpci_read for example, since the
>> lock was dropped prior to freeing pdev->vpci.
>>
>> Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
>> Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
>> ---
>> Cc: Andrew Cooper <andrew.cooper3@citrix.com>
>> Cc: Jan Beulich <jbeulich@suse.com>
>> Cc: Julien Grall <julien@xen.org>
>> Cc: Stefano Stabellini <sstabellini@kernel.org>
>> ---
>> New in v5 of this series: this is an updated version of the patch published at
>> https://urldefense.com/v3/__https://lore.kernel.org/xen-devel/20180717094830.54806-2-roger.pau@citrix.com/__;!!GF_29dbcQIUBPA!jmmcewY6y9Ur4rgvOgqscz8gBWaod2JnQOkHvWtYKgnqeU6BoWJTqCN3UDpCw3io8Ynk-wBXhA$ [lore[.]kernel[.]org]
>>
>> Changes since v5:
> This is a little odd in a series implicitly tagged as v1.
>
>> --- a/xen/drivers/vpci/header.c
>> +++ b/xen/drivers/vpci/header.c
>> @@ -142,12 +142,13 @@ bool vpci_process_pending(struct vcpu *v)
>>           if ( rc == -ERESTART )
>>               return true;
>>   
>> -        spin_lock(&v->vpci.pdev->vpci->lock);
>> -        /* Disable memory decoding unconditionally on failure. */
>> -        modify_decoding(v->vpci.pdev,
>> -                        rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
>> -                        !rc && v->vpci.rom_only);
>> -        spin_unlock(&v->vpci.pdev->vpci->lock);
>> +        spin_lock(&v->vpci.pdev->vpci_lock);
>> +        if ( v->vpci.pdev->vpci )
>> +            /* Disable memory decoding unconditionally on failure. */
>> +            modify_decoding(v->vpci.pdev,
>> +                            rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
>> +                            !rc && v->vpci.rom_only);
>> +        spin_unlock(&v->vpci.pdev->vpci_lock);
> While I certainly see the point, the addition of this if() (and a
> few more elsewhere) isn't covered by title or description.
The commit message says:
"This way the lock can be used to check whether vpci is present, and
removal can be performed while holding the lock, in order to make
sure there are no accesses to the contents of the vpci struct."
So, I think this is enough to describe the fact that after you have locked
the protected structure may have gone already and we need to
re-check it is still present.
>
>> --- a/xen/drivers/vpci/vpci.c
>> +++ b/xen/drivers/vpci/vpci.c
>> @@ -35,12 +35,10 @@ 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)
>> +static void vpci_remove_device_locked(struct pci_dev *pdev)
>>   {
>> -    if ( !has_vpci(pdev->domain) )
>> -        return;
>> +    ASSERT(spin_is_locked(&pdev->vpci_lock));
> While, unlike here, ...
>
>> @@ -152,8 +164,6 @@ int vpci_add_register(struct vpci *vpci, vpci_read_t *read_handler,
>>       r->offset = offset;
>>       r->private = data;
>>   
>> -    spin_lock(&vpci->lock);
> ... you did explain why you don't want to add a similar assertion
> here, I think in return the function wants to have a comment added
> that it's required to be called with the respective lock held.
Will add the comments
>   I
> notice you did so for the declaration, but I think such a comment
> would better be present at the definition as well. Same for
> vpci_remove_register() then, obviously.
Ok
>
>> @@ -311,7 +316,7 @@ static uint32_t merge_result(uint32_t data, uint32_t new, unsigned int size,
>>   uint32_t vpci_read(pci_sbdf_t sbdf, unsigned int reg, unsigned int size)
>>   {
>>       const struct domain *d = current->domain;
>> -    const struct pci_dev *pdev;
>> +    struct pci_dev *pdev;
>>       const struct vpci_register *r;
>>       unsigned int data_offset = 0;
>>       uint32_t data = ~(uint32_t)0;
>> @@ -327,7 +332,12 @@ uint32_t vpci_read(pci_sbdf_t sbdf, unsigned int reg, unsigned int size)
>>       if ( !pdev )
>>           return vpci_read_hw(sbdf, reg, size);
>>   
>> -    spin_lock(&pdev->vpci->lock);
>> +    spin_lock(&pdev->vpci_lock);
>> +    if ( !pdev->vpci )
>> +    {
>> +        spin_unlock(&pdev->vpci_lock);
>> +        return vpci_read_hw(sbdf, reg, size);
>> +    }
> In this case as well as in its write counterpart it becomes even more
> important to justify (in the description) the new behavior. It is not
> obvious at all that the absence of a struct vpci should be taken as
> an indication that the underlying device needs accessing instead.
> This also cannot be inferred from the "!pdev" case visible in context.
> In that case we have no record of a device at this SBDF, and hence the
> fallback pretty clearly is a "just in case" one. Yet if we know of a
> device, the absence of a struct vpci may mean various possible things.
Ok, I'll describe this change
>
> Jan
>
Thank you,
Oleksandr
Jan Beulich Feb. 2, 2022, 11:14 a.m. UTC | #5
On 02.02.2022 12:03, Oleksandr Andrushchenko wrote:
> On 02.02.22 11:22, Jan Beulich wrote:
>> On 01.02.2022 17:25, Oleksandr Andrushchenko wrote:
>>> From: Roger Pau Monne <roger.pau@citrix.com>
>>>
>>> This way the lock can be used to check whether vpci is present, and
>>> removal can be performed while holding the lock, in order to make
>>> sure there are no accesses to the contents of the vpci struct.
>>> Previously removal could race with vpci_read for example, since the
>>> lock was dropped prior to freeing pdev->vpci.
>>>
>>> Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
>>> Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
>>> ---
>>> Cc: Andrew Cooper <andrew.cooper3@citrix.com>
>>> Cc: Jan Beulich <jbeulich@suse.com>
>>> Cc: Julien Grall <julien@xen.org>
>>> Cc: Stefano Stabellini <sstabellini@kernel.org>
>>> ---
>>> New in v5 of this series: this is an updated version of the patch published at
>>> https://urldefense.com/v3/__https://lore.kernel.org/xen-devel/20180717094830.54806-2-roger.pau@citrix.com/__;!!GF_29dbcQIUBPA!jmmcewY6y9Ur4rgvOgqscz8gBWaod2JnQOkHvWtYKgnqeU6BoWJTqCN3UDpCw3io8Ynk-wBXhA$ [lore[.]kernel[.]org]
>>>
>>> Changes since v5:
>> This is a little odd in a series implicitly tagged as v1.
>>
>>> --- a/xen/drivers/vpci/header.c
>>> +++ b/xen/drivers/vpci/header.c
>>> @@ -142,12 +142,13 @@ bool vpci_process_pending(struct vcpu *v)
>>>           if ( rc == -ERESTART )
>>>               return true;
>>>   
>>> -        spin_lock(&v->vpci.pdev->vpci->lock);
>>> -        /* Disable memory decoding unconditionally on failure. */
>>> -        modify_decoding(v->vpci.pdev,
>>> -                        rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
>>> -                        !rc && v->vpci.rom_only);
>>> -        spin_unlock(&v->vpci.pdev->vpci->lock);
>>> +        spin_lock(&v->vpci.pdev->vpci_lock);
>>> +        if ( v->vpci.pdev->vpci )
>>> +            /* Disable memory decoding unconditionally on failure. */
>>> +            modify_decoding(v->vpci.pdev,
>>> +                            rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
>>> +                            !rc && v->vpci.rom_only);
>>> +        spin_unlock(&v->vpci.pdev->vpci_lock);
>> While I certainly see the point, the addition of this if() (and a
>> few more elsewhere) isn't covered by title or description.
> The commit message says:
> "This way the lock can be used to check whether vpci is present, and
> removal can be performed while holding the lock, in order to make
> sure there are no accesses to the contents of the vpci struct."
> So, I think this is enough to describe the fact that after you have locked
> the protected structure may have gone already and we need to
> re-check it is still present.

I'm afraid that to me "can be used" describes future behavior, as
opposed to e.g. "is used". If you want to point out both aspects,
maybe "... can be used (and in a few cases is used right away) ..."?

Jan
Oleksandr Andrushchenko Feb. 2, 2022, 11:26 a.m. UTC | #6
On 02.02.22 13:14, Jan Beulich wrote:
> On 02.02.2022 12:03, Oleksandr Andrushchenko wrote:
>> On 02.02.22 11:22, Jan Beulich wrote:
>>> On 01.02.2022 17:25, Oleksandr Andrushchenko wrote:
>>>> From: Roger Pau Monne <roger.pau@citrix.com>
>>>>
>>>> This way the lock can be used to check whether vpci is present, and
>>>> removal can be performed while holding the lock, in order to make
>>>> sure there are no accesses to the contents of the vpci struct.
>>>> Previously removal could race with vpci_read for example, since the
>>>> lock was dropped prior to freeing pdev->vpci.
>>>>
>>>> Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
>>>> Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
>>>> ---
>>>> Cc: Andrew Cooper <andrew.cooper3@citrix.com>
>>>> Cc: Jan Beulich <jbeulich@suse.com>
>>>> Cc: Julien Grall <julien@xen.org>
>>>> Cc: Stefano Stabellini <sstabellini@kernel.org>
>>>> ---
>>>> New in v5 of this series: this is an updated version of the patch published at
>>>> https://urldefense.com/v3/__https://lore.kernel.org/xen-devel/20180717094830.54806-2-roger.pau@citrix.com/__;!!GF_29dbcQIUBPA!jmmcewY6y9Ur4rgvOgqscz8gBWaod2JnQOkHvWtYKgnqeU6BoWJTqCN3UDpCw3io8Ynk-wBXhA$ [lore[.]kernel[.]org]
>>>>
>>>> Changes since v5:
>>> This is a little odd in a series implicitly tagged as v1.
>>>
>>>> --- a/xen/drivers/vpci/header.c
>>>> +++ b/xen/drivers/vpci/header.c
>>>> @@ -142,12 +142,13 @@ bool vpci_process_pending(struct vcpu *v)
>>>>            if ( rc == -ERESTART )
>>>>                return true;
>>>>    
>>>> -        spin_lock(&v->vpci.pdev->vpci->lock);
>>>> -        /* Disable memory decoding unconditionally on failure. */
>>>> -        modify_decoding(v->vpci.pdev,
>>>> -                        rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
>>>> -                        !rc && v->vpci.rom_only);
>>>> -        spin_unlock(&v->vpci.pdev->vpci->lock);
>>>> +        spin_lock(&v->vpci.pdev->vpci_lock);
>>>> +        if ( v->vpci.pdev->vpci )
>>>> +            /* Disable memory decoding unconditionally on failure. */
>>>> +            modify_decoding(v->vpci.pdev,
>>>> +                            rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
>>>> +                            !rc && v->vpci.rom_only);
>>>> +        spin_unlock(&v->vpci.pdev->vpci_lock);
>>> While I certainly see the point, the addition of this if() (and a
>>> few more elsewhere) isn't covered by title or description.
>> The commit message says:
>> "This way the lock can be used to check whether vpci is present, and
>> removal can be performed while holding the lock, in order to make
>> sure there are no accesses to the contents of the vpci struct."
>> So, I think this is enough to describe the fact that after you have locked
>> the protected structure may have gone already and we need to
>> re-check it is still present.
> I'm afraid that to me "can be used" describes future behavior, as
> opposed to e.g. "is used". If you want to point out both aspects,
> maybe "... can be used (and in a few cases is used right away) ..."?
This sounds good to me, thank you for suggesting that
>
> Jan
>

Thank you,
Oleksandr
diff mbox series

Patch

diff --git a/tools/tests/vpci/emul.h b/tools/tests/vpci/emul.h
index 2e1d3057c9d8..d018fb5eef21 100644
--- a/tools/tests/vpci/emul.h
+++ b/tools/tests/vpci/emul.h
@@ -44,6 +44,7 @@  struct domain {
 };
 
 struct pci_dev {
+    bool vpci_lock;
     struct vpci *vpci;
 };
 
@@ -53,10 +54,8 @@  struct vcpu
 };
 
 extern const struct vcpu *current;
-extern const struct pci_dev test_pdev;
+extern struct pci_dev test_pdev;
 
-typedef bool spinlock_t;
-#define spin_lock_init(l) (*(l) = false)
 #define spin_lock(l) (*(l) = true)
 #define spin_unlock(l) (*(l) = false)
 
diff --git a/tools/tests/vpci/main.c b/tools/tests/vpci/main.c
index b9a0a6006bb9..26c95b08b6b1 100644
--- a/tools/tests/vpci/main.c
+++ b/tools/tests/vpci/main.c
@@ -23,7 +23,8 @@  static struct vpci vpci;
 
 const static struct domain d;
 
-const struct pci_dev test_pdev = {
+struct pci_dev test_pdev = {
+    .vpci_lock = false,
     .vpci = &vpci,
 };
 
@@ -158,7 +159,6 @@  main(int argc, char **argv)
     int rc;
 
     INIT_LIST_HEAD(&vpci.handlers);
-    spin_lock_init(&vpci.lock);
 
     VPCI_ADD_REG(vpci_read32, vpci_write32, 0, 4, r0);
     VPCI_READ_CHECK(0, 4, r0);
diff --git a/xen/arch/x86/hvm/vmsi.c b/xen/arch/x86/hvm/vmsi.c
index 13e2a190b439..1f7a37f78264 100644
--- a/xen/arch/x86/hvm/vmsi.c
+++ b/xen/arch/x86/hvm/vmsi.c
@@ -910,14 +910,14 @@  int vpci_msix_arch_print(const struct vpci_msix *msix)
         {
             struct pci_dev *pdev = msix->pdev;
 
-            spin_unlock(&msix->pdev->vpci->lock);
+            spin_unlock(&msix->pdev->vpci_lock);
             process_pending_softirqs();
             /* NB: we assume that pdev cannot go away for an alive domain. */
-            if ( !pdev->vpci || !spin_trylock(&pdev->vpci->lock) )
+            if ( !spin_trylock(&pdev->vpci_lock) )
                 return -EBUSY;
-            if ( pdev->vpci->msix != msix )
+            if ( !pdev->vpci || pdev->vpci->msix != msix )
             {
-                spin_unlock(&pdev->vpci->lock);
+                spin_unlock(&pdev->vpci_lock);
                 return -EAGAIN;
             }
         }
diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c
index 1fad80362f0e..af648c6a19b5 100644
--- a/xen/drivers/passthrough/pci.c
+++ b/xen/drivers/passthrough/pci.c
@@ -328,6 +328,7 @@  static struct pci_dev *alloc_pdev(struct pci_seg *pseg, u8 bus, u8 devfn)
     *((u8*) &pdev->bus) = bus;
     *((u8*) &pdev->devfn) = devfn;
     pdev->domain = NULL;
+    spin_lock_init(&pdev->vpci_lock);
 
     arch_pci_init_pdev(pdev);
 
diff --git a/xen/drivers/vpci/header.c b/xen/drivers/vpci/header.c
index 40ff79c33f8f..bd23c0274d48 100644
--- a/xen/drivers/vpci/header.c
+++ b/xen/drivers/vpci/header.c
@@ -142,12 +142,13 @@  bool vpci_process_pending(struct vcpu *v)
         if ( rc == -ERESTART )
             return true;
 
-        spin_lock(&v->vpci.pdev->vpci->lock);
-        /* Disable memory decoding unconditionally on failure. */
-        modify_decoding(v->vpci.pdev,
-                        rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
-                        !rc && v->vpci.rom_only);
-        spin_unlock(&v->vpci.pdev->vpci->lock);
+        spin_lock(&v->vpci.pdev->vpci_lock);
+        if ( v->vpci.pdev->vpci )
+            /* Disable memory decoding unconditionally on failure. */
+            modify_decoding(v->vpci.pdev,
+                            rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
+                            !rc && v->vpci.rom_only);
+        spin_unlock(&v->vpci.pdev->vpci_lock);
 
         rangeset_destroy(v->vpci.mem);
         v->vpci.mem = NULL;
@@ -285,6 +286,12 @@  static int modify_bars(const struct pci_dev *pdev, uint16_t cmd, bool rom_only)
                 continue;
         }
 
+        spin_lock(&tmp->vpci_lock);
+        if ( !tmp->vpci )
+        {
+            spin_unlock(&tmp->vpci_lock);
+            continue;
+        }
         for ( i = 0; i < ARRAY_SIZE(tmp->vpci->header.bars); i++ )
         {
             const struct vpci_bar *bar = &tmp->vpci->header.bars[i];
@@ -303,12 +310,14 @@  static int modify_bars(const struct pci_dev *pdev, uint16_t cmd, bool rom_only)
             rc = rangeset_remove_range(mem, start, end);
             if ( rc )
             {
+                spin_unlock(&tmp->vpci_lock);
                 printk(XENLOG_G_WARNING "Failed to remove [%lx, %lx]: %d\n",
                        start, end, rc);
                 rangeset_destroy(mem);
                 return rc;
             }
         }
+        spin_unlock(&tmp->vpci_lock);
     }
 
     ASSERT(dev);
diff --git a/xen/drivers/vpci/msi.c b/xen/drivers/vpci/msi.c
index 5757a7aed20f..e3ce46869dad 100644
--- a/xen/drivers/vpci/msi.c
+++ b/xen/drivers/vpci/msi.c
@@ -270,7 +270,7 @@  void vpci_dump_msi(void)
     rcu_read_lock(&domlist_read_lock);
     for_each_domain ( d )
     {
-        const struct pci_dev *pdev;
+        struct pci_dev *pdev;
 
         if ( !has_vpci(d) )
             continue;
@@ -282,8 +282,13 @@  void vpci_dump_msi(void)
             const struct vpci_msi *msi;
             const struct vpci_msix *msix;
 
-            if ( !pdev->vpci || !spin_trylock(&pdev->vpci->lock) )
+            if ( !spin_trylock(&pdev->vpci_lock) )
                 continue;
+            if ( !pdev->vpci )
+            {
+                spin_unlock(&pdev->vpci_lock);
+                continue;
+            }
 
             msi = pdev->vpci->msi;
             if ( msi && msi->enabled )
@@ -323,7 +328,7 @@  void vpci_dump_msi(void)
                 }
             }
 
-            spin_unlock(&pdev->vpci->lock);
+            spin_unlock(&pdev->vpci_lock);
             process_pending_softirqs();
         }
     }
diff --git a/xen/drivers/vpci/msix.c b/xen/drivers/vpci/msix.c
index 846f1b8d7038..5310cc3ff520 100644
--- a/xen/drivers/vpci/msix.c
+++ b/xen/drivers/vpci/msix.c
@@ -225,7 +225,7 @@  static int msix_read(struct vcpu *v, unsigned long addr, unsigned int len,
         return X86EMUL_OKAY;
     }
 
-    spin_lock(&msix->pdev->vpci->lock);
+    spin_lock(&msix->pdev->vpci_lock);
     entry = get_entry(msix, addr);
     offset = addr & (PCI_MSIX_ENTRY_SIZE - 1);
 
@@ -254,7 +254,7 @@  static int msix_read(struct vcpu *v, unsigned long addr, unsigned int len,
         ASSERT_UNREACHABLE();
         break;
     }
-    spin_unlock(&msix->pdev->vpci->lock);
+    spin_unlock(&msix->pdev->vpci_lock);
 
     return X86EMUL_OKAY;
 }
@@ -297,7 +297,7 @@  static int msix_write(struct vcpu *v, unsigned long addr, unsigned int len,
         return X86EMUL_OKAY;
     }
 
-    spin_lock(&msix->pdev->vpci->lock);
+    spin_lock(&msix->pdev->vpci_lock);
     entry = get_entry(msix, addr);
     offset = addr & (PCI_MSIX_ENTRY_SIZE - 1);
 
@@ -370,7 +370,7 @@  static int msix_write(struct vcpu *v, unsigned long addr, unsigned int len,
         ASSERT_UNREACHABLE();
         break;
     }
-    spin_unlock(&msix->pdev->vpci->lock);
+    spin_unlock(&msix->pdev->vpci_lock);
 
     return X86EMUL_OKAY;
 }
diff --git a/xen/drivers/vpci/vpci.c b/xen/drivers/vpci/vpci.c
index fb0947179b79..c015a4d77540 100644
--- a/xen/drivers/vpci/vpci.c
+++ b/xen/drivers/vpci/vpci.c
@@ -35,12 +35,10 @@  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)
+static void vpci_remove_device_locked(struct pci_dev *pdev)
 {
-    if ( !has_vpci(pdev->domain) )
-        return;
+    ASSERT(spin_is_locked(&pdev->vpci_lock));
 
-    spin_lock(&pdev->vpci->lock);
     while ( !list_empty(&pdev->vpci->handlers) )
     {
         struct vpci_register *r = list_first_entry(&pdev->vpci->handlers,
@@ -50,15 +48,26 @@  void vpci_remove_device(struct pci_dev *pdev)
         list_del(&r->node);
         xfree(r);
     }
-    spin_unlock(&pdev->vpci->lock);
     xfree(pdev->vpci->msix);
     xfree(pdev->vpci->msi);
     xfree(pdev->vpci);
     pdev->vpci = NULL;
 }
 
+void vpci_remove_device(struct pci_dev *pdev)
+{
+    if ( !has_vpci(pdev->domain) )
+        return;
+
+    spin_lock(&pdev->vpci_lock);
+    if ( pdev->vpci )
+        vpci_remove_device_locked(pdev);
+    spin_unlock(&pdev->vpci_lock);
+}
+
 int vpci_add_handlers(struct pci_dev *pdev)
 {
+    struct vpci *vpci;
     unsigned int i;
     int rc = 0;
 
@@ -68,12 +77,14 @@  int vpci_add_handlers(struct pci_dev *pdev)
     /* We should not get here twice for the same device. */
     ASSERT(!pdev->vpci);
 
-    pdev->vpci = xzalloc(struct vpci);
-    if ( !pdev->vpci )
+    vpci = xzalloc(struct vpci);
+    if ( !vpci )
         return -ENOMEM;
 
-    INIT_LIST_HEAD(&pdev->vpci->handlers);
-    spin_lock_init(&pdev->vpci->lock);
+    INIT_LIST_HEAD(&vpci->handlers);
+
+    spin_lock(&pdev->vpci_lock);
+    pdev->vpci = vpci;
 
     for ( i = 0; i < NUM_VPCI_INIT; i++ )
     {
@@ -83,7 +94,8 @@  int vpci_add_handlers(struct pci_dev *pdev)
     }
 
     if ( rc )
-        vpci_remove_device(pdev);
+        vpci_remove_device_locked(pdev);
+    spin_unlock(&pdev->vpci_lock);
 
     return rc;
 }
@@ -152,8 +164,6 @@  int vpci_add_register(struct vpci *vpci, vpci_read_t *read_handler,
     r->offset = offset;
     r->private = data;
 
-    spin_lock(&vpci->lock);
-
     /* The list of handlers must be kept sorted at all times. */
     list_for_each ( prev, &vpci->handlers )
     {
@@ -165,14 +175,12 @@  int vpci_add_register(struct vpci *vpci, vpci_read_t *read_handler,
             break;
         if ( cmp == 0 )
         {
-            spin_unlock(&vpci->lock);
             xfree(r);
             return -EEXIST;
         }
     }
 
     list_add_tail(&r->node, prev);
-    spin_unlock(&vpci->lock);
 
     return 0;
 }
@@ -183,7 +191,6 @@  int vpci_remove_register(struct vpci *vpci, unsigned int offset,
     const struct vpci_register r = { .offset = offset, .size = size };
     struct vpci_register *rm;
 
-    spin_lock(&vpci->lock);
     list_for_each_entry ( rm, &vpci->handlers, node )
     {
         int cmp = vpci_register_cmp(&r, rm);
@@ -195,14 +202,12 @@  int vpci_remove_register(struct vpci *vpci, unsigned int offset,
         if ( !cmp && rm->offset == offset && rm->size == size )
         {
             list_del(&rm->node);
-            spin_unlock(&vpci->lock);
             xfree(rm);
             return 0;
         }
         if ( cmp <= 0 )
             break;
     }
-    spin_unlock(&vpci->lock);
 
     return -ENOENT;
 }
@@ -311,7 +316,7 @@  static uint32_t merge_result(uint32_t data, uint32_t new, unsigned int size,
 uint32_t vpci_read(pci_sbdf_t sbdf, unsigned int reg, unsigned int size)
 {
     const struct domain *d = current->domain;
-    const struct pci_dev *pdev;
+    struct pci_dev *pdev;
     const struct vpci_register *r;
     unsigned int data_offset = 0;
     uint32_t data = ~(uint32_t)0;
@@ -327,7 +332,12 @@  uint32_t vpci_read(pci_sbdf_t sbdf, unsigned int reg, unsigned int size)
     if ( !pdev )
         return vpci_read_hw(sbdf, reg, size);
 
-    spin_lock(&pdev->vpci->lock);
+    spin_lock(&pdev->vpci_lock);
+    if ( !pdev->vpci )
+    {
+        spin_unlock(&pdev->vpci_lock);
+        return vpci_read_hw(sbdf, reg, size);
+    }
 
     /* Read from the hardware or the emulated register handlers. */
     list_for_each_entry ( r, &pdev->vpci->handlers, node )
@@ -370,7 +380,7 @@  uint32_t vpci_read(pci_sbdf_t sbdf, unsigned int reg, unsigned int size)
             break;
         ASSERT(data_offset < size);
     }
-    spin_unlock(&pdev->vpci->lock);
+    spin_unlock(&pdev->vpci_lock);
 
     if ( data_offset < size )
     {
@@ -414,7 +424,7 @@  void vpci_write(pci_sbdf_t sbdf, unsigned int reg, unsigned int size,
                 uint32_t data)
 {
     const struct domain *d = current->domain;
-    const struct pci_dev *pdev;
+    struct pci_dev *pdev;
     const struct vpci_register *r;
     unsigned int data_offset = 0;
     const unsigned long *ro_map = pci_get_ro_map(sbdf.seg);
@@ -440,7 +450,14 @@  void vpci_write(pci_sbdf_t sbdf, unsigned int reg, unsigned int size,
         return;
     }
 
-    spin_lock(&pdev->vpci->lock);
+    spin_lock(&pdev->vpci_lock);
+    if ( !pdev->vpci )
+    {
+        spin_unlock(&pdev->vpci_lock);
+        vpci_write_hw(sbdf, reg, size, data);
+        return;
+    }
+
 
     /* Write the value to the hardware or emulated registers. */
     list_for_each_entry ( r, &pdev->vpci->handlers, node )
@@ -475,7 +492,7 @@  void vpci_write(pci_sbdf_t sbdf, unsigned int reg, unsigned int size,
             break;
         ASSERT(data_offset < size);
     }
-    spin_unlock(&pdev->vpci->lock);
+    spin_unlock(&pdev->vpci_lock);
 
     if ( data_offset < size )
         /* Tailing gap, write the remaining. */
diff --git a/xen/include/xen/pci.h b/xen/include/xen/pci.h
index b6d7e454f814..3f60d6c6c6dd 100644
--- a/xen/include/xen/pci.h
+++ b/xen/include/xen/pci.h
@@ -134,6 +134,7 @@  struct pci_dev {
     u64 vf_rlen[6];
 
     /* Data for vPCI. */
+    spinlock_t vpci_lock;
     struct vpci *vpci;
 };
 
diff --git a/xen/include/xen/vpci.h b/xen/include/xen/vpci.h
index 3f32de9d7eb3..d06efc3cea46 100644
--- a/xen/include/xen/vpci.h
+++ b/xen/include/xen/vpci.h
@@ -31,7 +31,7 @@  int __must_check vpci_add_handlers(struct pci_dev *dev);
 /* Remove all handlers and free vpci related structures. */
 void vpci_remove_device(struct pci_dev *pdev);
 
-/* Add/remove a register handler. */
+/* Add/remove a register handler. Must be called holding the vpci_lock. */
 int __must_check vpci_add_register(struct vpci *vpci,
                                    vpci_read_t *read_handler,
                                    vpci_write_t *write_handler,
@@ -60,7 +60,6 @@  bool __must_check vpci_process_pending(struct vcpu *v);
 struct vpci {
     /* List of vPCI handlers for a device. */
     struct list_head handlers;
-    spinlock_t lock;
 
 #ifdef __XEN__
     /* Hide the rest of the vpci struct from the user-space test harness. */