[PATCH] vfio/pci: Revert nvlink removal uAPI breakage

Alex Williamson posted 1 patch 4 days, 7 hours ago
Failed in applying to current master (apply log)
include/uapi/linux/vfio.h |   46 +++++++++++++++++++++++++++++++++++++++++----
1 file changed, 42 insertions(+), 4 deletions(-)

[PATCH] vfio/pci: Revert nvlink removal uAPI breakage

Posted by Alex Williamson 4 days, 7 hours ago
Revert the uAPI changes from the below commit with notice that these
regions and capabilities are no longer provided.

Fixes: b392a1989170 ("vfio/pci: remove vfio_pci_nvlink2")
Reported-by: Greg Kurz <groug@kaod.org>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---

Greg (Kurz), please double check this resolves the issue.  Thanks!

 include/uapi/linux/vfio.h |   46 +++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 42 insertions(+), 4 deletions(-)

diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 34b1f53a3901..ef33ea002b0b 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -333,10 +333,21 @@ struct vfio_region_info_cap_type {
 #define VFIO_REGION_SUBTYPE_INTEL_IGD_LPC_CFG	(3)
 
 /* 10de vendor PCI sub-types */
-/* subtype 1 was VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM, don't use */
+/*
+ * NVIDIA GPU NVlink2 RAM is coherent RAM mapped onto the host address space.
+ *
+ * Deprecated, region no longer provided
+ */
+#define VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM	(1)
 
 /* 1014 vendor PCI sub-types */
-/* subtype 1 was VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD, don't use */
+/*
+ * IBM NPU NVlink2 ATSD (Address Translation Shootdown) register of NPU
+ * to do TLB invalidation on a GPU.
+ *
+ * Deprecated, region no longer provided
+ */
+#define VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD	(1)
 
 /* sub-types for VFIO_REGION_TYPE_GFX */
 #define VFIO_REGION_SUBTYPE_GFX_EDID            (1)
@@ -630,9 +641,36 @@ struct vfio_device_migration_info {
  */
 #define VFIO_REGION_INFO_CAP_MSIX_MAPPABLE	3
 
-/* subtype 4 was VFIO_REGION_INFO_CAP_NVLINK2_SSATGT, don't use */
+/*
+ * Capability with compressed real address (aka SSA - small system address)
+ * where GPU RAM is mapped on a system bus. Used by a GPU for DMA routing
+ * and by the userspace to associate a NVLink bridge with a GPU.
+ *
+ * Deprecated, capability no longer provided
+ */
+#define VFIO_REGION_INFO_CAP_NVLINK2_SSATGT	4
+
+struct vfio_region_info_cap_nvlink2_ssatgt {
+	struct vfio_info_cap_header header;
+	__u64 tgt;
+};
 
-/* subtype 5 was VFIO_REGION_INFO_CAP_NVLINK2_LNKSPD, don't use */
+/*
+ * Capability with an NVLink link speed. The value is read by
+ * the NVlink2 bridge driver from the bridge's "ibm,nvlink-speed"
+ * property in the device tree. The value is fixed in the hardware
+ * and failing to provide the correct value results in the link
+ * not working with no indication from the driver why.
+ *
+ * Deprecated, capability no longer provided
+ */
+#define VFIO_REGION_INFO_CAP_NVLINK2_LNKSPD	5
+
+struct vfio_region_info_cap_nvlink2_lnkspd {
+	struct vfio_info_cap_header header;
+	__u32 link_speed;
+	__u32 __pad;
+};
 
 /**
  * VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9,



Re: [PATCH] vfio/pci: Revert nvlink removal uAPI breakage

Posted by Christoph Hellwig 3 days, 17 hours ago
Looks good,

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH] vfio/pci: Revert nvlink removal uAPI breakage

Posted by Greg Kurz 4 days, 7 hours ago
On Tue, 04 May 2021 09:52:02 -0600
Alex Williamson <alex.williamson@redhat.com> wrote:

> Revert the uAPI changes from the below commit with notice that these
> regions and capabilities are no longer provided.
> 
> Fixes: b392a1989170 ("vfio/pci: remove vfio_pci_nvlink2")
> Reported-by: Greg Kurz <groug@kaod.org>
> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
> ---
> 
> Greg (Kurz), please double check this resolves the issue.  Thanks!
> 

It does. Feel free to add:

Reviewed-by: Greg Kurz <groug@kaod.org>

and

Tested-by: Greg Kurz <groug@kaod.org>

Thanks for the quick fix.

Cheers,

--
Greg

>  include/uapi/linux/vfio.h |   46 +++++++++++++++++++++++++++++++++++++++++----
>  1 file changed, 42 insertions(+), 4 deletions(-)
> 
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index 34b1f53a3901..ef33ea002b0b 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -333,10 +333,21 @@ struct vfio_region_info_cap_type {
>  #define VFIO_REGION_SUBTYPE_INTEL_IGD_LPC_CFG	(3)
>  
>  /* 10de vendor PCI sub-types */
> -/* subtype 1 was VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM, don't use */
> +/*
> + * NVIDIA GPU NVlink2 RAM is coherent RAM mapped onto the host address space.
> + *
> + * Deprecated, region no longer provided
> + */
> +#define VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM	(1)
>  
>  /* 1014 vendor PCI sub-types */
> -/* subtype 1 was VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD, don't use */
> +/*
> + * IBM NPU NVlink2 ATSD (Address Translation Shootdown) register of NPU
> + * to do TLB invalidation on a GPU.
> + *
> + * Deprecated, region no longer provided
> + */
> +#define VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD	(1)
>  
>  /* sub-types for VFIO_REGION_TYPE_GFX */
>  #define VFIO_REGION_SUBTYPE_GFX_EDID            (1)
> @@ -630,9 +641,36 @@ struct vfio_device_migration_info {
>   */
>  #define VFIO_REGION_INFO_CAP_MSIX_MAPPABLE	3
>  
> -/* subtype 4 was VFIO_REGION_INFO_CAP_NVLINK2_SSATGT, don't use */
> +/*
> + * Capability with compressed real address (aka SSA - small system address)
> + * where GPU RAM is mapped on a system bus. Used by a GPU for DMA routing
> + * and by the userspace to associate a NVLink bridge with a GPU.
> + *
> + * Deprecated, capability no longer provided
> + */
> +#define VFIO_REGION_INFO_CAP_NVLINK2_SSATGT	4
> +
> +struct vfio_region_info_cap_nvlink2_ssatgt {
> +	struct vfio_info_cap_header header;
> +	__u64 tgt;
> +};
>  
> -/* subtype 5 was VFIO_REGION_INFO_CAP_NVLINK2_LNKSPD, don't use */
> +/*
> + * Capability with an NVLink link speed. The value is read by
> + * the NVlink2 bridge driver from the bridge's "ibm,nvlink-speed"
> + * property in the device tree. The value is fixed in the hardware
> + * and failing to provide the correct value results in the link
> + * not working with no indication from the driver why.
> + *
> + * Deprecated, capability no longer provided
> + */
> +#define VFIO_REGION_INFO_CAP_NVLINK2_LNKSPD	5
> +
> +struct vfio_region_info_cap_nvlink2_lnkspd {
> +	struct vfio_info_cap_header header;
> +	__u32 link_speed;
> +	__u32 __pad;
> +};
>  
>  /**
>   * VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9,
> 
> 


Re: [PATCH] vfio/pci: Revert nvlink removal uAPI breakage

Posted by Cornelia Huck 4 days, 7 hours ago
On Tue, 04 May 2021 09:52:02 -0600
Alex Williamson <alex.williamson@redhat.com> wrote:

> Revert the uAPI changes from the below commit with notice that these
> regions and capabilities are no longer provided.
> 
> Fixes: b392a1989170 ("vfio/pci: remove vfio_pci_nvlink2")
> Reported-by: Greg Kurz <groug@kaod.org>
> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
> ---
> 
> Greg (Kurz), please double check this resolves the issue.  Thanks!
> 
>  include/uapi/linux/vfio.h |   46 +++++++++++++++++++++++++++++++++++++++++----
>  1 file changed, 42 insertions(+), 4 deletions(-)

I had already hacked up a QEMU patch that moved the definitions into
local headers, but this one is less of a hassle. (Code compiles fine
after doing a headers update.)

Reviewed-by: Cornelia Huck <cohuck@redhat.com>