QEMU-Devel Archive on lore.kernel.org
 help / color / Atom feed
From: Alex Williamson <alex.williamson@redhat.com>
To: Kirti Wankhede <kwankhede@nvidia.com>
Cc: "Zhengxiao.zx@Alibaba-inc.com" <Zhengxiao.zx@Alibaba-inc.com>,
	"Tian, Kevin" <kevin.tian@intel.com>,
	"Liu, Yi L" <yi.l.liu@intel.com>,
	"cjia@nvidia.com" <cjia@nvidia.com>,
	"eskultet@redhat.com" <eskultet@redhat.com>,
	"Yang, Ziye" <ziye.yang@intel.com>,
	"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>,
	"cohuck@redhat.com" <cohuck@redhat.com>,
	"shuangtai.tst@alibaba-inc.com" <shuangtai.tst@alibaba-inc.com>,
	"dgilbert@redhat.com" <dgilbert@redhat.com>,
	"Wang, Zhi A" <zhi.a.wang@intel.com>,
	"mlevitsk@redhat.com" <mlevitsk@redhat.com>,
	"pasic@linux.ibm.com" <pasic@linux.ibm.com>,
	"aik@ozlabs.ru" <aik@ozlabs.ru>,
	"eauger@redhat.com" <eauger@redhat.com>,
	"felipe@nutanix.com" <felipe@nutanix.com>,
	"jonathan.davies@nutanix.com" <jonathan.davies@nutanix.com>,
	Yan Zhao <yan.y.zhao@intel.com>,
	"Liu, Changpeng" <changpeng.liu@intel.com>,
	"Ken.Xue@amd.com" <Ken.Xue@amd.com>
Subject: Re: [PATCH v16 QEMU 04/16] vfio: Add save and load functions for VFIO PCI devices
Date: Wed, 6 May 2020 14:03:14 -0600
Message-ID: <20200506140314.618f054d@w520.home> (raw)
In-Reply-To: <8a120b05-adf9-cd16-7497-f9f533f53117@nvidia.com>

On Thu, 7 May 2020 01:18:19 +0530
Kirti Wankhede <kwankhede@nvidia.com> wrote:

> On 5/6/2020 11:41 AM, Yan Zhao wrote:
> > On Tue, May 05, 2020 at 12:37:11PM +0800, Alex Williamson wrote:  
> >> On Tue, 5 May 2020 04:48:37 +0530
> >> Kirti Wankhede <kwankhede@nvidia.com> wrote:
> >>  
> >>> On 3/26/2020 1:26 AM, Alex Williamson wrote:  
> >>>> On Wed, 25 Mar 2020 02:39:02 +0530
> >>>> Kirti Wankhede <kwankhede@nvidia.com> wrote:
> >>>>      
> >>>>> These functions save and restore PCI device specific data - config
> >>>>> space of PCI device.
> >>>>> Tested save and restore with MSI and MSIX type.
> >>>>>
> >>>>> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
> >>>>> Reviewed-by: Neo Jia <cjia@nvidia.com>
> >>>>> ---
> >>>>>    hw/vfio/pci.c                 | 163 ++++++++++++++++++++++++++++++++++++++++++
> >>>>>    include/hw/vfio/vfio-common.h |   2 +
> >>>>>    2 files changed, 165 insertions(+)
> >>>>>
> >>>>> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
> >>>>> index 6c77c12e44b9..8deb11e87ef7 100644
> >>>>> --- a/hw/vfio/pci.c
> >>>>> +++ b/hw/vfio/pci.c
> >>>>> @@ -41,6 +41,7 @@
> >>>>>    #include "trace.h"
> >>>>>    #include "qapi/error.h"
> >>>>>    #include "migration/blocker.h"
> >>>>> +#include "migration/qemu-file.h"
> >>>>>    
> >>>>>    #define TYPE_VFIO_PCI "vfio-pci"
> >>>>>    #define PCI_VFIO(obj)    OBJECT_CHECK(VFIOPCIDevice, obj, TYPE_VFIO_PCI)
> >>>>> @@ -1632,6 +1633,50 @@ static void vfio_bars_prepare(VFIOPCIDevice *vdev)
> >>>>>        }
> >>>>>    }
> >>>>>    
> >>>>> +static int vfio_bar_validate(VFIOPCIDevice *vdev, int nr)
> >>>>> +{
> >>>>> +    PCIDevice *pdev = &vdev->pdev;
> >>>>> +    VFIOBAR *bar = &vdev->bars[nr];
> >>>>> +    uint64_t addr;
> >>>>> +    uint32_t addr_lo, addr_hi = 0;
> >>>>> +
> >>>>> +    /* Skip unimplemented BARs and the upper half of 64bit BARS. */
> >>>>> +    if (!bar->size) {
> >>>>> +        return 0;
> >>>>> +    }
> >>>>> +
> >>>>> +    addr_lo = pci_default_read_config(pdev, PCI_BASE_ADDRESS_0 + nr * 4, 4);
> >>>>> +
> >>>>> +    addr_lo = addr_lo & (bar->ioport ? PCI_BASE_ADDRESS_IO_MASK :
> >>>>> +                                       PCI_BASE_ADDRESS_MEM_MASK);  
> >>>>
> >>>> Nit, &= or combine with previous set.
> >>>>      
> >>>>> +    if (bar->type == PCI_BASE_ADDRESS_MEM_TYPE_64) {
> >>>>> +        addr_hi = pci_default_read_config(pdev,
> >>>>> +                                         PCI_BASE_ADDRESS_0 + (nr + 1) * 4, 4);
> >>>>> +    }
> >>>>> +
> >>>>> +    addr = ((uint64_t)addr_hi << 32) | addr_lo;  
> >>>>
> >>>> Could we use a union?
> >>>>      
> >>>>> +
> >>>>> +    if (!QEMU_IS_ALIGNED(addr, bar->size)) {
> >>>>> +        return -EINVAL;
> >>>>> +    }  
> >>>>
> >>>> What specifically are we validating here?  This should be true no
> >>>> matter what we wrote to the BAR or else BAR emulation is broken.  The
> >>>> bits that could make this unaligned are not implemented in the BAR.
> >>>>      
> >>>>> +
> >>>>> +    return 0;
> >>>>> +}
> >>>>> +
> >>>>> +static int vfio_bars_validate(VFIOPCIDevice *vdev)
> >>>>> +{
> >>>>> +    int i, ret;
> >>>>> +
> >>>>> +    for (i = 0; i < PCI_ROM_SLOT; i++) {
> >>>>> +        ret = vfio_bar_validate(vdev, i);
> >>>>> +        if (ret) {
> >>>>> +            error_report("vfio: BAR address %d validation failed", i);
> >>>>> +            return ret;
> >>>>> +        }
> >>>>> +    }
> >>>>> +    return 0;
> >>>>> +}
> >>>>> +
> >>>>>    static void vfio_bar_register(VFIOPCIDevice *vdev, int nr)
> >>>>>    {
> >>>>>        VFIOBAR *bar = &vdev->bars[nr];
> >>>>> @@ -2414,11 +2459,129 @@ static Object *vfio_pci_get_object(VFIODevice *vbasedev)
> >>>>>        return OBJECT(vdev);
> >>>>>    }
> >>>>>    
> >>>>> +static void vfio_pci_save_config(VFIODevice *vbasedev, QEMUFile *f)
> >>>>> +{
> >>>>> +    VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
> >>>>> +    PCIDevice *pdev = &vdev->pdev;
> >>>>> +    uint16_t pci_cmd;
> >>>>> +    int i;
> >>>>> +
> >>>>> +    for (i = 0; i < PCI_ROM_SLOT; i++) {
> >>>>> +        uint32_t bar;
> >>>>> +
> >>>>> +        bar = pci_default_read_config(pdev, PCI_BASE_ADDRESS_0 + i * 4, 4);
> >>>>> +        qemu_put_be32(f, bar);
> >>>>> +    }
> >>>>> +
> >>>>> +    qemu_put_be32(f, vdev->interrupt);
> >>>>> +    if (vdev->interrupt == VFIO_INT_MSI) {
> >>>>> +        uint32_t msi_flags, msi_addr_lo, msi_addr_hi = 0, msi_data;
> >>>>> +        bool msi_64bit;
> >>>>> +
> >>>>> +        msi_flags = pci_default_read_config(pdev, pdev->msi_cap + PCI_MSI_FLAGS,
> >>>>> +                                            2);
> >>>>> +        msi_64bit = (msi_flags & PCI_MSI_FLAGS_64BIT);
> >>>>> +
> >>>>> +        msi_addr_lo = pci_default_read_config(pdev,
> >>>>> +                                         pdev->msi_cap + PCI_MSI_ADDRESS_LO, 4);
> >>>>> +        qemu_put_be32(f, msi_addr_lo);
> >>>>> +
> >>>>> +        if (msi_64bit) {
> >>>>> +            msi_addr_hi = pci_default_read_config(pdev,
> >>>>> +                                             pdev->msi_cap + PCI_MSI_ADDRESS_HI,
> >>>>> +                                             4);
> >>>>> +        }
> >>>>> +        qemu_put_be32(f, msi_addr_hi);
> >>>>> +
> >>>>> +        msi_data = pci_default_read_config(pdev,
> >>>>> +                pdev->msi_cap + (msi_64bit ? PCI_MSI_DATA_64 : PCI_MSI_DATA_32),
> >>>>> +                2);
> >>>>> +        qemu_put_be32(f, msi_data);  
> >>>>
> >>>> Isn't the data field only a u16?
> >>>>      
> >>>
> >>> Yes, fixing it.
> >>>  
> >>>>> +    } else if (vdev->interrupt == VFIO_INT_MSIX) {
> >>>>> +        uint16_t offset;
> >>>>> +
> >>>>> +        /* save enable bit and maskall bit */
> >>>>> +        offset = pci_default_read_config(pdev,
> >>>>> +                                       pdev->msix_cap + PCI_MSIX_FLAGS + 1, 2);
> >>>>> +        qemu_put_be16(f, offset);
> >>>>> +        msix_save(pdev, f);
> >>>>> +    }
> >>>>> +    pci_cmd = pci_default_read_config(pdev, PCI_COMMAND, 2);
> >>>>> +    qemu_put_be16(f, pci_cmd);
> >>>>> +}
> >>>>> +
> >>>>> +static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)
> >>>>> +{
> >>>>> +    VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
> >>>>> +    PCIDevice *pdev = &vdev->pdev;
> >>>>> +    uint32_t interrupt_type;
> >>>>> +    uint32_t msi_flags, msi_addr_lo, msi_addr_hi = 0, msi_data;
> >>>>> +    uint16_t pci_cmd;
> >>>>> +    bool msi_64bit;
> >>>>> +    int i, ret;
> >>>>> +
> >>>>> +    /* retore pci bar configuration */
> >>>>> +    pci_cmd = pci_default_read_config(pdev, PCI_COMMAND, 2);
> >>>>> +    vfio_pci_write_config(pdev, PCI_COMMAND,
> >>>>> +                        pci_cmd & (!(PCI_COMMAND_IO | PCI_COMMAND_MEMORY)), 2);
> >>>>> +    for (i = 0; i < PCI_ROM_SLOT; i++) {
> >>>>> +        uint32_t bar = qemu_get_be32(f);
> >>>>> +
> >>>>> +        vfio_pci_write_config(pdev, PCI_BASE_ADDRESS_0 + i * 4, bar, 4);
> >>>>> +    }
> >>>>> +
> >>>>> +    ret = vfio_bars_validate(vdev);
> >>>>> +    if (ret) {
> >>>>> +        return ret;
> >>>>> +    }
> >>>>> +
> >>>>> +    interrupt_type = qemu_get_be32(f);
> >>>>> +
> >>>>> +    if (interrupt_type == VFIO_INT_MSI) {
> >>>>> +        /* restore msi configuration */
> >>>>> +        msi_flags = pci_default_read_config(pdev,
> >>>>> +                                            pdev->msi_cap + PCI_MSI_FLAGS, 2);
> >>>>> +        msi_64bit = (msi_flags & PCI_MSI_FLAGS_64BIT);
> >>>>> +
> >>>>> +        vfio_pci_write_config(pdev, pdev->msi_cap + PCI_MSI_FLAGS,
> >>>>> +                              msi_flags & (!PCI_MSI_FLAGS_ENABLE), 2);
> >>>>> +
> >>>>> +        msi_addr_lo = qemu_get_be32(f);
> >>>>> +        vfio_pci_write_config(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_LO,
> >>>>> +                              msi_addr_lo, 4);
> >>>>> +
> >>>>> +        msi_addr_hi = qemu_get_be32(f);
> >>>>> +        if (msi_64bit) {
> >>>>> +            vfio_pci_write_config(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI,
> >>>>> +                                  msi_addr_hi, 4);
> >>>>> +        }
> >>>>> +        msi_data = qemu_get_be32(f);
> >>>>> +        vfio_pci_write_config(pdev,
> >>>>> +                pdev->msi_cap + (msi_64bit ? PCI_MSI_DATA_64 : PCI_MSI_DATA_32),
> >>>>> +                msi_data, 2);
> >>>>> +
> >>>>> +        vfio_pci_write_config(pdev, pdev->msi_cap + PCI_MSI_FLAGS,
> >>>>> +                              msi_flags | PCI_MSI_FLAGS_ENABLE, 2);
> >>>>> +    } else if (interrupt_type == VFIO_INT_MSIX) {
> >>>>> +        uint16_t offset = qemu_get_be16(f);
> >>>>> +
> >>>>> +        /* load enable bit and maskall bit */
> >>>>> +        vfio_pci_write_config(pdev, pdev->msix_cap + PCI_MSIX_FLAGS + 1,
> >>>>> +                              offset, 2);
> >>>>> +        msix_load(pdev, f);
> >>>>> +    }
> >>>>> +    pci_cmd = qemu_get_be16(f);
> >>>>> +    vfio_pci_write_config(pdev, PCI_COMMAND, pci_cmd, 2);
> >>>>> +    return 0;
> >>>>> +}  
> >>>>
> >>>> It always seems like there should be a lot more state than this, and I
> >>>> probably sound like a broken record because I ask every time, but maybe
> >>>> that's a good indication that we (or at least I) need a comment
> >>>> explaining why we only care about these.  For example, what if we
> >>>> migrate a device in the D3 power state, don't we need to account for
> >>>> the state stored in the PM capability or does the device wake up into
> >>>> D0 auto-magically after migration?  I think we could repeat that
> >>>> question for every capability that can be modified.  Even for the MSI/X
> >>>> cases, the interrupt may not be active, but there could be state in
> >>>> virtual config space that would be different on the target.  For
> >>>> example, if we migrate with a device in INTx mode where the guest had
> >>>> written vector fields on the source, but only writes the enable bit on
> >>>> the target, can we seamlessly figure out the rest?  For other
> >>>> capabilities, that state may represent config space changes written
> >>>> through to the physical device and represent a functional difference on
> >>>> the target.  Thanks,
> >>>>     
> >>>
> >>> These are very basic set of registers from config state. Other are more
> >>> of vendor specific which vendor driver can save and restore in their own
> >>> data. I don't think we have to take care of all those vendor specific
> >>> fields here.  
> >>
> >> That had not been clear to me.  Intel folks, is this your understanding
> >> regarding the responsibility of the user to save and restore config
> >> space of the device as part of the vendor provided migration stream
> >> data?  Thanks,
> >>  
> > Currently, the code works for us. but I agree with you that there should
> > be more states to save, at least for emulated config bits.
> > I think we should call pci_device_save() to serve that purpose.
> >   
> 
> If vendor driver can restore all vendor specific config space, then 
> adding it again in QEMU might be redundant. As an example, I had mailed 
> mtty sample code, in which config space has vendor specific information 
> and that is restored in easy way.

The redundancy is implementing it in each vendor driver.  Thanks,

Alex



  reply index

Thread overview: 74+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-24 21:08 [PATCH v16 QEMU 00/16] Add migration support for VFIO devices Kirti Wankhede
2020-03-24 21:08 ` [PATCH v16 QEMU 01/16] vfio: KABI for migration interface - Kernel header placeholder Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 02/16] vfio: Add function to unmap VFIO region Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 03/16] vfio: Add vfio_get_object callback to VFIODeviceOps Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 04/16] vfio: Add save and load functions for VFIO PCI devices Kirti Wankhede
2020-03-25 19:56   ` Alex Williamson
2020-03-26 17:29     ` Dr. David Alan Gilbert
2020-03-26 17:38       ` Alex Williamson
2020-05-04 23:18     ` Kirti Wankhede
2020-05-05  4:37       ` Alex Williamson
2020-05-06  6:11         ` Yan Zhao
2020-05-06 19:48           ` Kirti Wankhede
2020-05-06 20:03             ` Alex Williamson [this message]
2020-05-07  5:40               ` Kirti Wankhede
2020-05-07 18:14                 ` Alex Williamson
2020-03-26 17:46   ` Dr. David Alan Gilbert
2020-05-04 23:19     ` Kirti Wankhede
2020-04-07  4:10   ` Longpeng (Mike, Cloud Infrastructure Service Product Dept.)
2020-05-04 23:21     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 05/16] vfio: Add migration region initialization and finalize function Kirti Wankhede
2020-03-26 17:52   ` Dr. David Alan Gilbert
2020-05-04 23:19     ` Kirti Wankhede
2020-05-19 19:32       ` Dr. David Alan Gilbert
2020-03-24 21:09 ` [PATCH v16 QEMU 06/16] vfio: Add VM state change handler to know state of VM Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 07/16] vfio: Add migration state change notifier Kirti Wankhede
2020-04-01 11:27   ` Dr. David Alan Gilbert
2020-05-04 23:20     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 08/16] vfio: Register SaveVMHandlers for VFIO device Kirti Wankhede
2020-03-25 21:02   ` Alex Williamson
2020-05-04 23:19     ` Kirti Wankhede
2020-05-05  4:37       ` Alex Williamson
2020-05-06  6:38         ` Yan Zhao
2020-05-06  9:58           ` Cornelia Huck
2020-05-06 16:53             ` Dr. David Alan Gilbert
2020-05-06 19:30               ` Kirti Wankhede
2020-05-07  6:37                 ` Cornelia Huck
2020-05-07 20:29                 ` Alex Williamson
2020-04-01 17:36   ` Dr. David Alan Gilbert
2020-05-04 23:20     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 09/16] vfio: Add save state functions to SaveVMHandlers Kirti Wankhede
2020-03-25 22:03   ` Alex Williamson
2020-05-04 23:18     ` Kirti Wankhede
2020-05-05  4:37       ` Alex Williamson
2020-05-11  9:53         ` Kirti Wankhede
2020-05-11 15:59           ` Alex Williamson
2020-05-12  2:06           ` Yan Zhao
2020-05-09  5:31   ` Yan Zhao
2020-05-11 10:22     ` Kirti Wankhede
2020-05-12  0:50       ` Yan Zhao
2020-03-24 21:09 ` [PATCH v16 QEMU 10/16] vfio: Add load " Kirti Wankhede
2020-03-25 22:36   ` Alex Williamson
2020-04-01 18:58   ` Dr. David Alan Gilbert
2020-05-04 23:20     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 11/16] iommu: add callback to get address limit IOMMU supports Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 12/16] memory: Set DIRTY_MEMORY_MIGRATION when IOMMU is enabled Kirti Wankhede
2020-04-01 19:00   ` Dr. David Alan Gilbert
2020-04-01 19:42     ` Alex Williamson
2020-03-24 21:09 ` [PATCH v16 QEMU 13/16] vfio: Add function to start and stop dirty pages tracking Kirti Wankhede
2020-03-26 19:10   ` Alex Williamson
2020-05-04 23:20     ` Kirti Wankhede
2020-04-01 19:03   ` Dr. David Alan Gilbert
2020-05-04 23:21     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 14/16] vfio: Add vfio_listener_log_sync to mark dirty pages Kirti Wankhede
2020-03-25  2:19   ` Yan Zhao
2020-03-26 19:46   ` Alex Williamson
2020-04-01 19:08     ` Dr. David Alan Gilbert
2020-04-01  5:50   ` Yan Zhao
2020-04-03 20:11     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 15/16] vfio: Add ioctl to get dirty pages bitmap during dma unmap Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 16/16] vfio: Make vfio-pci device migration capable Kirti Wankhede
2020-03-24 23:36 ` [PATCH v16 QEMU 00/16] Add migration support for VFIO devices no-reply
2020-03-31 18:34 ` Alex Williamson
2020-04-01  6:41   ` Yan Zhao
2020-04-01 18:34     ` Alex Williamson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200506140314.618f054d@w520.home \
    --to=alex.williamson@redhat.com \
    --cc=Ken.Xue@amd.com \
    --cc=Zhengxiao.zx@Alibaba-inc.com \
    --cc=aik@ozlabs.ru \
    --cc=changpeng.liu@intel.com \
    --cc=cjia@nvidia.com \
    --cc=cohuck@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=eauger@redhat.com \
    --cc=eskultet@redhat.com \
    --cc=felipe@nutanix.com \
    --cc=jonathan.davies@nutanix.com \
    --cc=kevin.tian@intel.com \
    --cc=kwankhede@nvidia.com \
    --cc=mlevitsk@redhat.com \
    --cc=pasic@linux.ibm.com \
    --cc=qemu-devel@nongnu.org \
    --cc=shuangtai.tst@alibaba-inc.com \
    --cc=yan.y.zhao@intel.com \
    --cc=yi.l.liu@intel.com \
    --cc=zhi.a.wang@intel.com \
    --cc=ziye.yang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

QEMU-Devel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/qemu-devel/0 qemu-devel/git/0.git
	git clone --mirror https://lore.kernel.org/qemu-devel/1 qemu-devel/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 qemu-devel qemu-devel/ https://lore.kernel.org/qemu-devel \
		qemu-devel@nongnu.org
	public-inbox-index qemu-devel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.nongnu.qemu-devel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git