Skip to contentSkip to conversation

pds-vfio-pci driver

PATCH Superseded Brett Creeley 5 participants 28 messages Jul 19, 2023 – Jul 25, 2023

Subsystems (9)

v12 of 14 Superseded Latest is v14 →

lore
Share & tools
lore

Brett Creeley

author maintainer
#0 lore raw

v12 cover pds-vfio-pci driver

This is a patchset for a new vendor specific VFIO driver (pds-vfio-pci) for use with the AMD/Pensando Distributed Services Card (DSC). This driver makes use of the pds_core driver.

This driver will use the pds_core device's adminq as the VFIO control path to the DSC. In order to make adminq calls, the VFIO instance makes use of functions exported by the pds_core driver.

In order to receive events from pds_core, the pds-vfio-pci driver registers to a private notifier. This is needed for various events that come from the device.

An ASCII diagram of a VFIO instance looks something like this and can be used with the VFIO subsystem to provide the VF device VFIO and live migration support.

                               .------.  .-----------------------.
                               | QEMU |--|  VM  .-------------.  |
                               '......'  |      |   Eth VF    |  |
                                  |      |      .-------------.  |
                                  |      |      |  SR-IOV VF  |  |
                                  |      |      '-------------'  |
                                  |      '------------||---------'
                               .--------------.       ||
                               |/dev/<vfio_fd>|       ||
                               '--------------'       ||
Host Userspace                         |              ||
===================================================   ||
Host Kernel                            |              ||
                                  .--------.          ||
                                  |vfio-pci|          ||
                                  '--------'          ||
       .------------------.           ||              ||
       |   | exported API |<----+     ||              ||
       |   '--------------|     |     ||              ||
       |                  |    .--------------.       ||
       |     pds_core     |--->| pds-vfio-pci |       ||
       '------------------' |  '--------------'       ||
               ||           |         ||              ||
             09:00.0     notifier    09:00.1          ||
== PCI ===============================================||=====
               ||                     ||              ||
          .----------.          .----------.          ||
    ,-----|    PF    |----------|    VF    |-------------------,
    |     '----------'         |'----------'         VF        |
    |                     DSC  |                 data/control  |
    |                          |                     path      |
    -----------------------------------------------------------

The pds-vfio-pci driver is targeted to reside in drivers/vfio/pci/pds. It makes use of and introduces new files in the common include/linux/pds include directory.

Note: This series is based on the latest linux-next tree. I did not base it on the Alex Williamson's vfio/next because it has not yet pulled in the latest changes which include the pds_vdpa driver. The pds_vdpa driver has conflicts with the pds-vfio-pci driver that needed to be resolved, which is why this series is based on the latest linux-next tree.

Changes:

v12:
- Fix htmldocs issue reported by Simon Horman

v11:
https://lore.kernel.org/netdev/[email protected]/
- Various fixes/suggestions by Kevin Tian:
- Update commit message on patch 1/7 to mention ethernet VF
- Fix formatting
- Check return of pci_iov_vf_id() for error
- Update MODULE_AUTHOR to be myself
- Remove double print of pci_id
- Set fast_poll=true for PDS_LM_CMD_RESUME
- Update comments around SUSPEND and SUSPEND_STATUS operations
- Get rid of pds_vfio_deferred_reset() and just perform the operations inline to the only caller
- Rework pds_vfio_state_mutex_unlock() to be simpler
- Rework comments in pds_vfio_recovery()
- Append "vfio" to the end of PDS_LM_DEV_NAME
- Remove req_len from pds_vfio_client_adminq_cmd()
- Remove unused completion structures in pds_adminq.h
- Fix comment above creating VFs to specify pds_core as the PF device
- Various fixes/suggestions by Alex Williamson:
- Removed cached pci_id from pds_vfio_device structure
- Rename from pds_vfio to pds-vfio-pci
- Various fixes/suggestions by Shameerali Kolothum Thodi:
- Fix checking return of pds_client_register()
- Use bool argument for flags instead of u64 on pds_vfio_client_adminq_cmd()
- Fix support for VFIO_MIGRATION_P2P
- Improve member name alignment in pds_adminq.h
- Rework Kconfig based on latest changes from Alex Williamson

v10:
https://lore.kernel.org/netdev/[email protected]/
- Various fixes/suggestions by Jason Gunthorpe
- Simplify pds_vfio_get_lm_file() based on fpga_mgr_buf_load()
- Clean-ups/fixes based on clang-format
- Remove any double goto labels
- Name goto labels baesed on what needs to be cleaned/freed instead of a "call from" scheme
- Fix any goto unwind ordering issues
- Make sure call dma_map_single() after data is written to memory in pds_vfio_dma_map_lm_file()
- Don't use bitmap_zalloc() for the dirty bitmaps
- Use vzalloc() for dirty bitmaps and refactor how the bitmaps are DMA'd to and from the device in pds_vfio_dirty_seq_ack()
- Remove unnecessary goto in pds_vfio_dirty_disable()

v9:
https://lore.kernel.org/netdev/[email protected]/
- Various fixes/suggestions by Alex Williamson
- Fix how ID is generated in client registration
- Add helper functions to get the VF's struct device and struct pci_dev pointers instead of caching the struct pci dev
- Remove redundant pds_vfio_lm_state() function and remove any places this was being called
- Fix multi-line comments to follow standard convention
- Remove confusing comments in pds_vfio_step_device_state_locked() since the driver's migration states align with the VFIO documentation
- Validate pdsc returned from pdsc_get_pf_struct()
- Various fixes/suggestions by Jason Gunthorpe
- Use struct pdsc instead of void *
- Use {} instead of {0} for structure initialization
- Use unions on the stack instead of casting to the union when sending AQ commands, which required including pds_lm.h in pds_adminq.h
- Replace use of dma_alloc_coherent() when creating the sgl DMA entries for the LM file
- Remove cached struct device *coredev and instead use pci_physfn() to get the pds_core's struct device pointer
- Drop the recovery work item and call pds_vfio_recovery() directly from the notifier callback
- Remove unnecessary #define for "pds_vfio_lm" and just use the string inline to the anon_inode_getfile() argument
- Fix LM file reference counting
- Move initialization of some struct members to when the struct is being initialized for AQ commands
- Make use of GFP_KERNEL_ACCOUNT where it makes sense
- Replace PDS_VFIO_DRV_NAME with KBUILD_MODNAME
- Update to latest pds_core exported functions
- Remove duplicated prototypes for pds_vfio_dma_logging_[start|stop|report] from lm.h
- Hold pds_vfio->state_mutex while starting, stopping, and reporting dirty page tracking in pds_vfio_dma_logging_[start|stop|report]
- Remove duplicate PDS_DEV_TYPE_LM_STR define from pds_lm.h that's already included in pds_common.h
- Replace use of dma_alloc_coherent() when creating the sgl DMA entries for the dirty bitmaps

v8:
https://lore.kernel.org/netdev/[email protected]/
- provide default iommufd callbacks for bind_iommufd, unbind_iommufd, and attach_ioas for the VFIO device as suggested by Shameerali Kolothum Thodi

v7:
https://lore.kernel.org/netdev/[email protected]/
- Disable and clean up dirty page tracking when the VFIO device is closed
- Various improvements suggested by Simon Horman:
- Fix RCT in vfio_combine_iova_ranges()
- Simplify function exit paths by removing unnecessary goto labels
- Cleanup pds_vifo_print_guest_region_info() by adding a goto label for freeing memory, which allowed for reduced indentation on a for loop
- Where possible use C99 style for loops

v6:
https://lore.kernel.org/netdev/[email protected]/
- As suggested by Alex Williamson, use pci_domain_nr() macro to make sure the pds_vfio client's devname is unique
- Remove unnecessary forward declaration and include
- Fix copyright comment to use correct company name
- Remove "." from struct documentation for consistency

v5:
https://lore.kernel.org/netdev/[email protected]/
- Fix SPDX comments in .h files
- Remove adminqcq argument from pdsc_post_adminq() uses
- Unregister client on vfio_pci_core_register_device() failure
- Other minor checkpatch issues

v4:
https://lore.kernel.org/netdev/[email protected]/
- Update cover letter ASCII diagram to reflect new driver architecture
- Remove auxiliary driver implementation
- Use pds_core's exported functions to communicate with the device
- Implement and register notifier for events from the device/pds_core
- Use module_pci_driver() macro since auxiliary driver configuration is no longer needed in __init/__exit

v3:
https://lore.kernel.org/netdev/[email protected]/
- Update copyright year to 2023 and use "Advanced Micro Devices, Inc." for the company name
- Clarify the fact that AMD/Pensando's VFIO solution is device type agnostic, which aligns with other current VFIO solutions
- Add line in drivers/vfio/pci/Makefile to build pds_vfio
- Move documentation to amd sub-directory
- Remove some dead code due to the pds_core implementation of listening to BIND/UNBIND events
- Move a dev_dbg() to a previous patch in the series
- Add implementation for vfio_migration_ops.migration_get_data_size to return the maximum possible device state size

RFC to v2:
https://lore.kernel.org/all/[email protected]/
- Implement state transitions for VFIO_MIGRATION_P2P flag
- Improve auxiliary driver probe by returning EPROBE_DEFER when the PCI driver is not set up correctly
- Add pointer to docs in Documentation/networking/device_drivers/ethernet/index.rst

RFC:
https://lore.kernel.org/all/[email protected]/

Brett Creeley (7):
vfio: Commonize combine_ranges for use in other VFIO drivers vfio/pds: Initial support for pds VFIO driver vfio/pds: register with the pds_core PF
vfio/pds: Add VFIO live migration support vfio/pds: Add support for dirty page tracking vfio/pds: Add support for firmware recovery vfio/pds: Add Kconfig and documentation

 .../ethernet/amd/pds_vfio_pci.rst             |  79 +++
 .../device_drivers/ethernet/index.rst         |   1 +
 MAINTAINERS                                   |   7 +
 drivers/vfio/pci/Kconfig                      |   2 +
 drivers/vfio/pci/Makefile                     |   2 +
 drivers/vfio/pci/mlx5/cmd.c                   |  48 +-
 drivers/vfio/pci/pds/Kconfig                  |  19 +
 drivers/vfio/pci/pds/Makefile                 |  11 +
 drivers/vfio/pci/pds/cmds.c                   | 493 +++++++++++++++
 drivers/vfio/pci/pds/cmds.h                   |  25 +
 drivers/vfio/pci/pds/dirty.c                  | 576 ++++++++++++++++++
 drivers/vfio/pci/pds/dirty.h                  |  39 ++
 drivers/vfio/pci/pds/lm.c                     | 434 +++++++++++++
 drivers/vfio/pci/pds/lm.h                     |  41 ++
 drivers/vfio/pci/pds/pci_drv.c                | 214 +++++++
 drivers/vfio/pci/pds/pci_drv.h                |   9 +
 drivers/vfio/pci/pds/vfio_dev.c               | 227 +++++++
 drivers/vfio/pci/pds/vfio_dev.h               |  42 ++
 drivers/vfio/vfio_main.c                      |  47 ++
 include/linux/pds/pds_adminq.h                | 375 ++++++++++++
 include/linux/pds/pds_common.h                |   3 +-
 include/linux/vfio.h                          |   3 +
 22 files changed, 2649 insertions(+), 48 deletions(-)
 create mode 100644 Documentation/networking/device_drivers/ethernet/amd/pds_vfio_pci.rst
 create mode 100644 drivers/vfio/pci/pds/Kconfig
 create mode 100644 drivers/vfio/pci/pds/Makefile
 create mode 100644 drivers/vfio/pci/pds/cmds.c
 create mode 100644 drivers/vfio/pci/pds/cmds.h
 create mode 100644 drivers/vfio/pci/pds/dirty.c
 create mode 100644 drivers/vfio/pci/pds/dirty.h
 create mode 100644 drivers/vfio/pci/pds/lm.c
 create mode 100644 drivers/vfio/pci/pds/lm.h
 create mode 100644 drivers/vfio/pci/pds/pci_drv.c
 create mode 100644 drivers/vfio/pci/pds/pci_drv.h
 create mode 100644 drivers/vfio/pci/pds/vfio_dev.c
 create mode 100644 drivers/vfio/pci/pds/vfio_dev.h
Signature · 1 line
2.17.1
author maintainer
#1 lore raw

PATCH v12 1/7 vfio: Commonize combine_ranges for use in other VFIO drivers

Currently only Mellanox uses the combine_ranges function. The new pds_vfio driver also needs this function. So, move it to a common location for other vendor drivers to use.

Also, Simon Harmon noticed that RCT ordering was not followed for vfio_combin_iova_ranges(), so fix that.

---
 drivers/vfio/pci/mlx5/cmd.c | 48 +------------------------------------
 drivers/vfio/vfio_main.c    | 47 ++++++++++++++++++++++++++++++++++++
 include/linux/vfio.h        |  3 +++
 3 files changed, 51 insertions(+), 47 deletions(-)
drivers/vfio/pci/mlx5/cmd.c +1 -47
index deed156e6165..7f6c51992a15 100644
@@ -732,52 +732,6 @@ void mlx5fv_cmd_clean_migf_resources(struct mlx5_vf_migration_file *migf)
 	mlx5vf_cmd_dealloc_pd(migf);
 }
 
-static void combine_ranges(struct rb_root_cached *root, u32 cur_nodes,
-			   u32 req_nodes)
-{
-	struct interval_tree_node *prev, *curr, *comb_start, *comb_end;
-	unsigned long min_gap;
-	unsigned long curr_gap;
-
-	/* Special shortcut when a single range is required */
-	if (req_nodes == 1) {
-		unsigned long last;
-
-		curr = comb_start = interval_tree_iter_first(root, 0, ULONG_MAX);
-		while (curr) {
-			last = curr->last;
-			prev = curr;
-			curr = interval_tree_iter_next(curr, 0, ULONG_MAX);
-			if (prev != comb_start)
-				interval_tree_remove(prev, root);
-		}
-		comb_start->last = last;
-		return;
-	}
-
-	/* Combine ranges which have the smallest gap */
-	while (cur_nodes > req_nodes) {
-		prev = NULL;
-		min_gap = ULONG_MAX;
-		curr = interval_tree_iter_first(root, 0, ULONG_MAX);
-		while (curr) {
-			if (prev) {
-				curr_gap = curr->start - prev->last;
-				if (curr_gap < min_gap) {
-					min_gap = curr_gap;
-					comb_start = prev;
-					comb_end = curr;
-				}
-			}
-			prev = curr;
-			curr = interval_tree_iter_next(curr, 0, ULONG_MAX);
-		}
-		comb_start->last = comb_end->last;
-		interval_tree_remove(comb_end, root);
-		cur_nodes--;
-	}
-}
-
 static int mlx5vf_create_tracker(struct mlx5_core_dev *mdev,
 				 struct mlx5vf_pci_core_device *mvdev,
 				 struct rb_root_cached *ranges, u32 nnodes)
@@ -800,7 +754,7 @@ static int mlx5vf_create_tracker(struct mlx5_core_dev *mdev,
 	int i;
 
 	if (num_ranges > max_num_range) {
-		combine_ranges(ranges, nnodes, max_num_range);
+		vfio_combine_iova_ranges(ranges, nnodes, max_num_range);
 		num_ranges = max_num_range;
 	}
 
drivers/vfio/vfio_main.c +47 -0

53 lines not on this page · raw message

include/linux/vfio.h +3 -0
index 2c137ea94a3e..f49933b63ac3 100644
@@ -245,6 +245,9 @@ int vfio_mig_get_next_state(struct vfio_device *device,
 			    enum vfio_device_mig_state new_fsm,
 			    enum vfio_device_mig_state *next_fsm);
 
+void vfio_combine_iova_ranges(struct rb_root_cached *root, u32 cur_nodes,
+			      u32 req_nodes);
+
 /*
  * External user API
  */
Signature · 1 line
2.17.1
reviewer
#2 lore raw

RE: [PATCH v12 vfio 1/7] vfio: Commonize combine_ranges for use in other VFIO drivers

Quoted 10 lines

From: Brett Creeley <[email protected]>
Sent: Thursday, July 20, 2023 6:35 AM

Currently only Mellanox uses the combine_ranges function. The new pds_vfio driver also needs this function. So, move it to a common location for other vendor drivers to use.

Also, Simon Harmon noticed that RCT ordering was not followed for vfio_combin_iova_ranges(), so fix that.

It's not common practice to put name in the commit msg. Just describe what is changed.

#3 lore raw

Re: [PATCH v12 vfio 1/7] vfio: Commonize combine_ranges for use in other VFIO drivers

Quoted 10 lines · Kevin

Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.

Quoted 7 lines

From: Brett Creeley <[email protected]>
Sent: Thursday, July 20, 2023 6:35 AM

Currently only Mellanox uses the combine_ranges function. The new pds_vfio driver also needs this function. So, move it to a common location for other vendor drivers to use.

Quoted 6 lines
Quoted 3 lines

Also, Simon Harmon noticed that RCT ordering was not followed for vfio_combin_iova_ranges(), so fix that.

It's not common practice to put name in the commit msg. Just describe what is changed.

Okay, I will keep that in mind in the future. Based on your other comments there are some minor tweaks that need to be done for a v13, so I will make sure to update this while I'm at it.

Thanks for the review.

Brett

author maintainer
#4 lore raw

PATCH v12 2/7 vfio/pds: Initial support for pds VFIO driver

In reply to Brett Creeley

This is the initial framework for the new pds-vfio-pci device driver. This does the very basics of registering the PDS PCI device and configuring it as a VFIO PCI device.

With this change, the VF device can be bound to the pds-vfio-pci driver on the host and presented to the VM as an ethernet VF.

---
 drivers/vfio/pci/Makefile       |  2 +
 drivers/vfio/pci/pds/Makefile   |  8 ++++
 drivers/vfio/pci/pds/pci_drv.c  | 68 ++++++++++++++++++++++++++++++
 drivers/vfio/pci/pds/vfio_dev.c | 75 +++++++++++++++++++++++++++++++++
 drivers/vfio/pci/pds/vfio_dev.h | 19 +++++++++
 5 files changed, 172 insertions(+)
 create mode 100644 drivers/vfio/pci/pds/Makefile
 create mode 100644 drivers/vfio/pci/pds/pci_drv.c
 create mode 100644 drivers/vfio/pci/pds/vfio_dev.c
 create mode 100644 drivers/vfio/pci/pds/vfio_dev.h
drivers/vfio/pci/Makefile +2 -0
index 24c524224da5..45167be462d8 100644
@@ -11,3 +11,5 @@ obj-$(CONFIG_VFIO_PCI) += vfio-pci.o
 obj-$(CONFIG_MLX5_VFIO_PCI)           += mlx5/
 
 obj-$(CONFIG_HISI_ACC_VFIO_PCI) += hisilicon/
+
+obj-$(CONFIG_PDS_VFIO_PCI) += pds/
drivers/vfio/pci/pds/Makefile new file +8 -0
new file mode 100644
index 000000000000..e5e53a6d86d1
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2023 Advanced Micro Devices, Inc.
+
+obj-$(CONFIG_PDS_VFIO_PCI) += pds-vfio-pci.o
+
+pds-vfio-pci-y := \
+	pci_drv.o	\
+	vfio_dev.o
drivers/vfio/pci/pds/pci_drv.c new file +68 -0

68 lines not on this page · raw message

drivers/vfio/pci/pds/vfio_dev.c new file +75 -0

75 lines not on this page · raw message

drivers/vfio/pci/pds/vfio_dev.h new file +19 -0
new file mode 100644
index 000000000000..a4d4b65778d1
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2023 Advanced Micro Devices, Inc. */
+
+#ifndef _VFIO_DEV_H_
+#define _VFIO_DEV_H_
+
+#include <linux/pci.h>
+#include <linux/vfio_pci_core.h>
+
+struct pds_vfio_pci_device {
+	struct vfio_pci_core_device vfio_coredev;
+
+	int vf_id;
+};
+
+const struct vfio_device_ops *pds_vfio_ops_info(void);
+struct pds_vfio_pci_device *pds_vfio_pci_drvdata(struct pci_dev *pdev);
+
+#endif /* _VFIO_DEV_H_ */
Signature · 1 line
2.17.1
reviewer
#5 lore raw

RE: [PATCH v12 vfio 2/7] vfio/pds: Initial support for pds VFIO driver

Quoted 9 lines

From: Brett Creeley <[email protected]>
Sent: Thursday, July 20, 2023 6:35 AM

drivers/vfio/pci/pds/vfio_dev.c new file +6 -0
+
+static int pds_vfio_init_device(struct vfio_device *vdev)
+{
+	struct pds_vfio_pci_device *pds_vfio =
+		container_of(vdev, struct pds_vfio_pci_device,
+			     vfio_coredev.vdev);

drivers/vfio/pci/pds/vfio_dev.c line 31

Quoted 10 lines
drivers/vfio/pci/pds/vfio_dev.c new file +10 -0
+	struct pci_dev *pdev = to_pci_dev(vdev->dev);
+	int err, vf_id;
+
+	err = vfio_pci_core_init_dev(vdev);
+	if (err)
+		return err;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;

this returns w/o reverting what vfio_pci_core_init_dev() does.

A simpler way is to move it to the start.

#6 lore raw

Re: [PATCH v12 vfio 2/7] vfio/pds: Initial support for pds VFIO driver

Quoted 25 lines · Kevin

Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.

Quoted 9 lines

From: Brett Creeley <[email protected]>
Sent: Thursday, July 20, 2023 6:35 AM

drivers/vfio/pci/pds/vfio_dev.c new file +6 -0
+
+static int pds_vfio_init_device(struct vfio_device *vdev)
+{
+     struct pds_vfio_pci_device *pds_vfio =
+             container_of(vdev, struct pds_vfio_pci_device,
+                          vfio_coredev.vdev);

drivers/vfio/pci/pds/vfio_dev.c line 31

Quoted 10 lines
drivers/vfio/pci/pds/vfio_dev.c new file +10 -0
+     struct pci_dev *pdev = to_pci_dev(vdev->dev);
+     int err, vf_id;
+
+     err = vfio_pci_core_init_dev(vdev);
+     if (err)
+             return err;
+
+     vf_id = pci_iov_vf_id(pdev);
+     if (vf_id < 0)
+             return vf_id;

this returns w/o reverting what vfio_pci_core_init_dev() does.

Quoted 2 lines

A simpler way is to move it to the start.

Yeah, this is a good catch/suggestion. I will fix this up in the next revision.

Brett

author maintainer
#7 lore raw

PATCH v12 3/7 vfio/pds: register with the pds_core PF

In reply to Brett Creeley

The pds_core driver will supply adminq services, so find the PF and register with the DSC services.

Use the following commands to enable a VF:
echo 1 > /sys/bus/pci/drivers/pds_core/$PF_BDF/sriov_numvfs

---
 drivers/vfio/pci/pds/Makefile   |  1 +
 drivers/vfio/pci/pds/cmds.c     | 44 +++++++++++++++++++++++++++++++++
 drivers/vfio/pci/pds/cmds.h     | 10 ++++++++
 drivers/vfio/pci/pds/pci_drv.c  | 19 ++++++++++++++
 drivers/vfio/pci/pds/pci_drv.h  |  9 +++++++
 drivers/vfio/pci/pds/vfio_dev.c | 13 +++++++++-
 drivers/vfio/pci/pds/vfio_dev.h |  6 +++++
 include/linux/pds/pds_common.h  |  3 ++-
 8 files changed, 103 insertions(+), 2 deletions(-)
 create mode 100644 drivers/vfio/pci/pds/cmds.c
 create mode 100644 drivers/vfio/pci/pds/cmds.h
 create mode 100644 drivers/vfio/pci/pds/pci_drv.h
drivers/vfio/pci/pds/Makefile +1 -0
index e5e53a6d86d1..91587c7fe8f9 100644
@@ -4,5 +4,6 @@
 obj-$(CONFIG_PDS_VFIO_PCI) += pds-vfio-pci.o
 
 pds-vfio-pci-y := \
+	cmds.o		\
 	pci_drv.o	\
 	vfio_dev.o
drivers/vfio/pci/pds/cmds.c new file +44 -0

44 lines not on this page · raw message

drivers/vfio/pci/pds/cmds.h new file +10 -0
new file mode 100644
index 000000000000..4c592afccf89
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2023 Advanced Micro Devices, Inc. */
+
+#ifndef _CMDS_H_
+#define _CMDS_H_
+
+int pds_vfio_register_client_cmd(struct pds_vfio_pci_device *pds_vfio);
+void pds_vfio_unregister_client_cmd(struct pds_vfio_pci_device *pds_vfio);
+
+#endif /* _CMDS_H_ */
drivers/vfio/pci/pds/pci_drv.c +19 -0
index 4670ddda603a..928903a84f27 100644
@@ -8,9 +8,13 @@
 #include <linux/types.h>
 #include <linux/vfio.h>
 
+#include <linux/pds/pds_common.h>
 #include <linux/pds/pds_core_if.h>
+#include <linux/pds/pds_adminq.h>
 
 #include "vfio_dev.h"
+#include "pci_drv.h"
+#include "cmds.h"
 
 #define PDS_VFIO_DRV_DESCRIPTION	"AMD/Pensando VFIO Device Driver"
 #define PCI_VENDOR_ID_PENSANDO		0x1dd8
@@ -27,13 +31,27 @@ static int pds_vfio_pci_probe(struct pci_dev *pdev,
 		return PTR_ERR(pds_vfio);
 
 	dev_set_drvdata(&pdev->dev, &pds_vfio->vfio_coredev);
+	pds_vfio->pdsc = pdsc_get_pf_struct(pdev);
+	if (IS_ERR_OR_NULL(pds_vfio->pdsc)) {
+		err = PTR_ERR(pds_vfio->pdsc) ?: -ENODEV;
+		goto out_put_vdev;
+	}
 
 	err = vfio_pci_core_register_device(&pds_vfio->vfio_coredev);
 	if (err)
 		goto out_put_vdev;
 
+	err = pds_vfio_register_client_cmd(pds_vfio);
+	if (err) {
+		dev_err(&pdev->dev, "failed to register as client: %pe\n",
+			ERR_PTR(err));
+		goto out_unregister_coredev;
+	}
+
 	return 0;
 
+out_unregister_coredev:
+	vfio_pci_core_unregister_device(&pds_vfio->vfio_coredev);
 out_put_vdev:
 	vfio_put_device(&pds_vfio->vfio_coredev.vdev);
 	return err;
@@ -43,6 +61,7 @@ static void pds_vfio_pci_remove(struct pci_dev *pdev)
 {
 	struct pds_vfio_pci_device *pds_vfio = pds_vfio_pci_drvdata(pdev);
 
+	pds_vfio_unregister_client_cmd(pds_vfio);
 	vfio_pci_core_unregister_device(&pds_vfio->vfio_coredev);
 	vfio_put_device(&pds_vfio->vfio_coredev.vdev);
 }
drivers/vfio/pci/pds/pci_drv.h new file +9 -0
new file mode 100644
index 000000000000..e79bed12ed14
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2023 Advanced Micro Devices, Inc. */
+
+#ifndef _PCI_DRV_H
+#define _PCI_DRV_H
+
+#include <linux/pci.h>
+
+#endif /* _PCI_DRV_H */
drivers/vfio/pci/pds/vfio_dev.c +12 -1
index 7c125643f5d9..5299cfb262d5 100644
@@ -6,6 +6,11 @@
 
 #include "vfio_dev.h"
 
+struct pci_dev *pds_vfio_to_pci_dev(struct pds_vfio_pci_device *pds_vfio)
+{
+	return pds_vfio->vfio_coredev.pdev;
+}
+
 struct pds_vfio_pci_device *pds_vfio_pci_drvdata(struct pci_dev *pdev)
 {
 	struct vfio_pci_core_device *core_device = dev_get_drvdata(&pdev->dev);
@@ -20,7 +25,7 @@ static int pds_vfio_init_device(struct vfio_device *vdev)
 		container_of(vdev, struct pds_vfio_pci_device,
 			     vfio_coredev.vdev);
 	struct pci_dev *pdev = to_pci_dev(vdev->dev);
-	int err, vf_id;
+	int err, vf_id, pci_id;
 
 	err = vfio_pci_core_init_dev(vdev);
 	if (err)
@@ -32,6 +37,12 @@ static int pds_vfio_init_device(struct vfio_device *vdev)
 
 	pds_vfio->vf_id = vf_id;
 
+	pci_id = PCI_DEVID(pdev->bus->number, pdev->devfn);
+	dev_dbg(&pdev->dev,
+		"%s: PF %#04x VF %#04x vf_id %d domain %d pds_vfio %p\n",
+		__func__, pci_dev_id(pdev->physfn), pci_id, vf_id,
+		pci_domain_nr(pdev->bus), pds_vfio);
+
 	return 0;
 }
 
drivers/vfio/pci/pds/vfio_dev.h +6 -0
index a4d4b65778d1..824832aa1513 100644
@@ -7,13 +7,19 @@
 #include <linux/pci.h>
 #include <linux/vfio_pci_core.h>
 
+struct pdsc;
+
 struct pds_vfio_pci_device {
 	struct vfio_pci_core_device vfio_coredev;
+	struct pdsc *pdsc;
 
 	int vf_id;
+	u16 client_id;
 };
 
 const struct vfio_device_ops *pds_vfio_ops_info(void);
 struct pds_vfio_pci_device *pds_vfio_pci_drvdata(struct pci_dev *pdev);
 
+struct pci_dev *pds_vfio_to_pci_dev(struct pds_vfio_pci_device *pds_vfio);
+
 #endif /* _VFIO_DEV_H_ */
include/linux/pds/pds_common.h +2 -1
index 435c8e8161c2..255c7c186bf5 100644
@@ -34,12 +34,13 @@ enum pds_core_vif_types {
 
 #define PDS_DEV_TYPE_CORE_STR	"Core"
 #define PDS_DEV_TYPE_VDPA_STR	"vDPA"
-#define PDS_DEV_TYPE_VFIO_STR	"VFio"
+#define PDS_DEV_TYPE_VFIO_STR	"vfio"
 #define PDS_DEV_TYPE_ETH_STR	"Eth"
 #define PDS_DEV_TYPE_RDMA_STR	"RDMA"
 #define PDS_DEV_TYPE_LM_STR	"LM"
 
 #define PDS_VDPA_DEV_NAME	PDS_CORE_DRV_NAME "." PDS_DEV_TYPE_VDPA_STR
+#define PDS_LM_DEV_NAME		PDS_CORE_DRV_NAME "." PDS_DEV_TYPE_LM_STR "." PDS_DEV_TYPE_VFIO_STR
 
 int pdsc_register_notify(struct notifier_block *nb);
 void pdsc_unregister_notify(struct notifier_block *nb);
Signature · 1 line
2.17.1
reviewer
#8 lore raw

RE: [PATCH v12 vfio 3/7] vfio/pds: register with the pds_core PF

drivers/vfio/pci/pds/cmds.c line 41

Quoted 12 lines

From: Brett Creeley <[email protected]>
Sent: Thursday, July 20, 2023 6:35 AM

drivers/vfio/pci/pds/cmds.c new file +9 -0
+void pds_vfio_unregister_client_cmd(struct pds_vfio_pci_device *pds_vfio)
+{
+	struct pci_dev *pdev = pds_vfio_to_pci_dev(pds_vfio);
+	int err;
+
+	err = pds_client_unregister(pci_physfn(pdev), pds_vfio->client_id);
+	if (err)
+		dev_err(&pdev->dev, "unregister from DSC failed: %pe\n",
+			ERR_PTR(err));

Why using ERR_PTR() here? it looks a common pattern used cross this series.

Quoted 11 lines
include/linux/pds/pds_common.h +1 -1
@@ -34,12 +34,13 @@ enum pds_core_vif_types {
 
 #define PDS_DEV_TYPE_CORE_STR	"Core"
 #define PDS_DEV_TYPE_VDPA_STR	"vDPA"
-#define PDS_DEV_TYPE_VFIO_STR	"VFio"
+#define PDS_DEV_TYPE_VFIO_STR	"vfio"
 #define PDS_DEV_TYPE_ETH_STR	"Eth"
 #define PDS_DEV_TYPE_RDMA_STR	"RDMA"
 #define PDS_DEV_TYPE_LM_STR	"LM"
 
 #define PDS_VDPA_DEV_NAME	 "."
Quoted 4 lines

PDS_DEV_TYPE_VDPA_STR
+#define PDS_LM_DEV_NAME PDS_CORE_DRV_NAME "."
PDS_DEV_TYPE_LM_STR "." PDS_DEV_TYPE_VFIO_STR

then should the name be changed to PDS_VFIO_LM_DEV_NAME?

Or is mentioning *LM* important? what would be the problem to just use "pds_core.vfio"?

#9 lore raw

Re: [PATCH v12 vfio 3/7] vfio/pds: register with the pds_core PF

Quoted 6 lines · Kevin

Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.

Quoted 3 lines

From: Brett Creeley <[email protected]>
Sent: Thursday, July 20, 2023 6:35 AM

Quoted 12 lines

drivers/vfio/pci/pds/cmds.c line 41

Quoted 9 lines
drivers/vfio/pci/pds/cmds.c new file +9 -0
+void pds_vfio_unregister_client_cmd(struct pds_vfio_pci_device *pds_vfio)
+{
+     struct pci_dev *pdev = pds_vfio_to_pci_dev(pds_vfio);
+     int err;
+
+     err = pds_client_unregister(pci_physfn(pdev), pds_vfio->client_id);
+     if (err)
+             dev_err(&pdev->dev, "unregister from DSC failed: %pe\n",
+                     ERR_PTR(err));

Why using ERR_PTR() here? it looks a common pattern used cross this series.

Yes, this is intentional. This is more readable than just printing out the error value.

Quoted 19 lines
Quoted 12 lines
include/linux/pds/pds_common.h +1 -1
@@ -34,12 +34,13 @@ enum pds_core_vif_types {
 
  #define PDS_DEV_TYPE_CORE_STR        "Core"
  #define PDS_DEV_TYPE_VDPA_STR        "vDPA"
-#define PDS_DEV_TYPE_VFIO_STR        "VFio"
+#define PDS_DEV_TYPE_VFIO_STR        "vfio"
  #define PDS_DEV_TYPE_ETH_STR "Eth"
  #define PDS_DEV_TYPE_RDMA_STR        "RDMA"
  #define PDS_DEV_TYPE_LM_STR  "LM"
 
  #define PDS_VDPA_DEV_NAME     "."
Quoted 4 lines

PDS_DEV_TYPE_VDPA_STR
+#define PDS_LM_DEV_NAME PDS_CORE_DRV_NAME "."
PDS_DEV_TYPE_LM_STR "." PDS_DEV_TYPE_VFIO_STR

then should the name be changed to PDS_VFIO_LM_DEV_NAME?

Quoted 2 lines

Or is mentioning *LM* important? what would be the problem to just use "pds_core.vfio"?

LM is important for the device. I don't plan to change this.

reviewer
#10 lore raw

RE: [PATCH v12 vfio 3/7] vfio/pds: register with the pds_core PF

Quoted 29 lines

From: Brett Creeley <[email protected]>
Sent: Saturday, July 22, 2023 3:10 PM

Quoted 1 line · Kevin

Caution: This message originated from an External Source. Use proper

caution when opening attachments, clicking links, or responding.

Quoted 23 lines
Quoted 16 lines

From: Brett Creeley <[email protected]>
Sent: Thursday, July 20, 2023 6:35 AM

include/linux/pds/pds_common.h +1 -1
@@ -34,12 +34,13 @@ enum pds_core_vif_types {
 
  #define PDS_DEV_TYPE_CORE_STR        "Core"
  #define PDS_DEV_TYPE_VDPA_STR        "vDPA"
-#define PDS_DEV_TYPE_VFIO_STR        "VFio"
+#define PDS_DEV_TYPE_VFIO_STR        "vfio"
  #define PDS_DEV_TYPE_ETH_STR "Eth"
  #define PDS_DEV_TYPE_RDMA_STR        "RDMA"
  #define PDS_DEV_TYPE_LM_STR  "LM"
 
  #define PDS_VDPA_DEV_NAME     "."
Quoted 4 lines

PDS_DEV_TYPE_VDPA_STR
+#define PDS_LM_DEV_NAME PDS_CORE_DRV_NAME "."
PDS_DEV_TYPE_LM_STR "." PDS_DEV_TYPE_VFIO_STR

then should the name be changed to PDS_VFIO_LM_DEV_NAME?

Quoted 4 lines
Quoted 2 lines

Or is mentioning *LM* important? what would be the problem to just use "pds_core.vfio"?

LM is important for the device. I don't plan to change this.

What about in the future VDPA also wants to gain migration support? with VFIO_STR in the name does it make more sense to at least define the name as PDS_VFIO_LM_DEV_NAME?

#11 lore raw

Re: [PATCH v12 vfio 3/7] vfio/pds: register with the pds_core PF

Quoted 32 lines · Kevin

Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.

Quoted 29 lines

From: Brett Creeley <[email protected]>
Sent: Saturday, July 22, 2023 3:10 PM

Quoted 1 line · Kevin

Caution: This message originated from an External Source. Use proper

caution when opening attachments, clicking links, or responding.

Quoted 23 lines
Quoted 16 lines

From: Brett Creeley <[email protected]>
Sent: Thursday, July 20, 2023 6:35 AM

include/linux/pds/pds_common.h +1 -1
@@ -34,12 +34,13 @@ enum pds_core_vif_types {
 
   #define PDS_DEV_TYPE_CORE_STR        "Core"
   #define PDS_DEV_TYPE_VDPA_STR        "vDPA"
-#define PDS_DEV_TYPE_VFIO_STR        "VFio"
+#define PDS_DEV_TYPE_VFIO_STR        "vfio"
   #define PDS_DEV_TYPE_ETH_STR "Eth"
   #define PDS_DEV_TYPE_RDMA_STR        "RDMA"
   #define PDS_DEV_TYPE_LM_STR  "LM"
 
   #define PDS_VDPA_DEV_NAME     "."
Quoted 4 lines

PDS_DEV_TYPE_VDPA_STR
+#define PDS_LM_DEV_NAME PDS_CORE_DRV_NAME "."
PDS_DEV_TYPE_LM_STR "." PDS_DEV_TYPE_VFIO_STR

then should the name be changed to PDS_VFIO_LM_DEV_NAME?

Quoted 8 lines
Quoted 4 lines
Quoted 2 lines

Or is mentioning *LM* important? what would be the problem to just use "pds_core.vfio"?

LM is important for the device. I don't plan to change this.

What about in the future VDPA also wants to gain migration support? with VFIO_STR in the name does it make more sense to at least define the name as PDS_VFIO_LM_DEV_NAME?

Sure I can rename the define that way.

#12 lore raw

Re: [PATCH v12 vfio 3/7] vfio/pds: register with the pds_core PF

In reply to Brett Creeley
Quoted 20 lines · Brett Creeley
Quoted 6 lines · Kevin

Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.

Quoted 3 lines

From: Brett Creeley <[email protected]>
Sent: Thursday, July 20, 2023 6:35 AM

Quoted 12 lines

drivers/vfio/pci/pds/cmds.c line 41

Quoted 9 lines
drivers/vfio/pci/pds/cmds.c new file +9 -0
+void pds_vfio_unregister_client_cmd(struct pds_vfio_pci_device *pds_vfio)
+{
+     struct pci_dev *pdev = pds_vfio_to_pci_dev(pds_vfio);
+     int err;
+
+     err = pds_client_unregister(pci_physfn(pdev), pds_vfio->client_id);
+     if (err)
+             dev_err(&pdev->dev, "unregister from DSC failed: %pe\n",
+                     ERR_PTR(err));

Why using ERR_PTR() here? it looks a common pattern used cross this series.

Quoted 2 lines

Yes, this is intentional. This is more readable than just printing out the error value.

That seems like a hack, it would be nicer if printk could format errnos natively

Jason

#13 lore raw

Re: [PATCH v12 vfio 3/7] vfio/pds: register with the pds_core PF

Quoted 24 lines · Jason Gunthorpe

Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.

Quoted 20 lines · Brett Creeley
Quoted 18 lines · Kevin

Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.

drivers/vfio/pci/pds/cmds.c line 41

Quoted 12 lines

From: Brett Creeley <[email protected]>
Sent: Thursday, July 20, 2023 6:35 AM

drivers/vfio/pci/pds/cmds.c new file +9 -0
+void pds_vfio_unregister_client_cmd(struct pds_vfio_pci_device *pds_vfio)
+{
+     struct pci_dev *pdev = pds_vfio_to_pci_dev(pds_vfio);
+     int err;
+
+     err = pds_client_unregister(pci_physfn(pdev), pds_vfio->client_id);
+     if (err)
+             dev_err(&pdev->dev, "unregister from DSC failed: %pe\n",
+                     ERR_PTR(err));

Why using ERR_PTR() here? it looks a common pattern used cross this series.

Quoted 5 lines
Quoted 2 lines

Yes, this is intentional. This is more readable than just printing out the error value.

That seems like a hack, it would be nicer if printk could format errnos natively

This is already being used all over the driver hierarchy.

Quoted 2 lines

Jason

#14 lore raw

Re: [PATCH v12 vfio 3/7] vfio/pds: register with the pds_core PF

Quoted 25 lines · Brett Creeley
Quoted 24 lines · Jason Gunthorpe

Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.

Quoted 20 lines · Brett Creeley
Quoted 18 lines · Kevin

Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.

drivers/vfio/pci/pds/cmds.c line 41

Quoted 12 lines

From: Brett Creeley <[email protected]>
Sent: Thursday, July 20, 2023 6:35 AM

drivers/vfio/pci/pds/cmds.c new file +9 -0
+void pds_vfio_unregister_client_cmd(struct pds_vfio_pci_device *pds_vfio)
+{
+     struct pci_dev *pdev = pds_vfio_to_pci_dev(pds_vfio);
+     int err;
+
+     err = pds_client_unregister(pci_physfn(pdev), pds_vfio->client_id);
+     if (err)
+             dev_err(&pdev->dev, "unregister from DSC failed: %pe\n",
+                     ERR_PTR(err));

Why using ERR_PTR() here? it looks a common pattern used cross this series.

Quoted 7 lines
Quoted 5 lines
Quoted 2 lines

Yes, this is intentional. This is more readable than just printing out the error value.

That seems like a hack, it would be nicer if printk could format errnos natively

This is already being used all over the driver hierarchy.

That seems like an overstatement. The 100 places it is already used would all be better as some '%de' instead.

Jason

author maintainer
#15 lore raw

PATCH v12 4/7 vfio/pds: Add VFIO live migration support

In reply to Brett Creeley

Add live migration support via the VFIO subsystem. The migration implementation aligns with the definition from uapi/vfio.h and uses the pds_core PF's adminq for device configuration.

The ability to suspend, resume, and transfer VF device state data is included along with the required admin queue command structures and implementations.

PDS_LM_CMD_SUSPEND and PDS_LM_CMD_SUSPEND_STATUS are added to support the VF device suspend operation.

PDS_LM_CMD_RESUME is added to support the VF device resume operation.

PDS_LM_CMD_STATUS is added to determine the exact size of the VF device state data.

PDS_LM_CMD_SAVE is added to get the VF device state data.

PDS_LM_CMD_RESTORE is added to restore the VF device with the previously saved data from PDS_LM_CMD_SAVE.

PDS_LM_CMD_HOST_VF_STATUS is added to notify the DSC/firmware when a migration is in/not-in progress from the host's perspective. The DSC/firmware can use this to clear/setup any necessary state related to a migration.

---
 drivers/vfio/pci/pds/Makefile   |   1 +
 drivers/vfio/pci/pds/cmds.c     | 324 ++++++++++++++++++++++++
 drivers/vfio/pci/pds/cmds.h     |   8 +-
 drivers/vfio/pci/pds/lm.c       | 434 ++++++++++++++++++++++++++++++++
 drivers/vfio/pci/pds/lm.h       |  41 +++
 drivers/vfio/pci/pds/pci_drv.c  |  13 +
 drivers/vfio/pci/pds/vfio_dev.c | 120 ++++++++-
 drivers/vfio/pci/pds/vfio_dev.h |  11 +
 include/linux/pds/pds_adminq.h  | 197 +++++++++++++++
 9 files changed, 1147 insertions(+), 2 deletions(-)
 create mode 100644 drivers/vfio/pci/pds/lm.c
 create mode 100644 drivers/vfio/pci/pds/lm.h
drivers/vfio/pci/pds/Makefile +1 -0
index 91587c7fe8f9..47750bb31ea2 100644
@@ -5,5 +5,6 @@ obj-$(CONFIG_PDS_VFIO_PCI) += pds-vfio-pci.o
 
 pds-vfio-pci-y := \
 	cmds.o		\
+	lm.o		\
 	pci_drv.o	\
 	vfio_dev.o
drivers/vfio/pci/pds/cmds.c +324 -0

339 lines not on this page · raw message

drivers/vfio/pci/pds/cmds.h +7 -1
index 4c592afccf89..1097e96d3c11 100644
@@ -6,5 +6,11 @@
 
 int pds_vfio_register_client_cmd(struct pds_vfio_pci_device *pds_vfio);
 void pds_vfio_unregister_client_cmd(struct pds_vfio_pci_device *pds_vfio);
-
+int pds_vfio_suspend_device_cmd(struct pds_vfio_pci_device *pds_vfio, u8 type);
+int pds_vfio_resume_device_cmd(struct pds_vfio_pci_device *pds_vfio, u8 type);
+int pds_vfio_get_lm_status_cmd(struct pds_vfio_pci_device *pds_vfio, u64 *size);
+int pds_vfio_get_lm_state_cmd(struct pds_vfio_pci_device *pds_vfio);
+int pds_vfio_set_lm_state_cmd(struct pds_vfio_pci_device *pds_vfio);
+void pds_vfio_send_host_vf_lm_status_cmd(struct pds_vfio_pci_device *pds_vfio,
+					 enum pds_lm_host_vf_status vf_status);
 #endif /* _CMDS_H_ */
drivers/vfio/pci/pds/lm.c new file +434 -0

434 lines not on this page · raw message

drivers/vfio/pci/pds/lm.h new file +41 -0

41 lines not on this page · raw message

drivers/vfio/pci/pds/pci_drv.c +13 -0
index 928903a84f27..c1739edd261a 100644
@@ -72,11 +72,24 @@ static const struct pci_device_id pds_vfio_pci_table[] = {
 };
 MODULE_DEVICE_TABLE(pci, pds_vfio_pci_table);
 
+static void pds_vfio_pci_aer_reset_done(struct pci_dev *pdev)
+{
+	struct pds_vfio_pci_device *pds_vfio = pds_vfio_pci_drvdata(pdev);
+
+	pds_vfio_reset(pds_vfio);
+}
+
+static const struct pci_error_handlers pds_vfio_pci_err_handlers = {
+	.reset_done = pds_vfio_pci_aer_reset_done,
+	.error_detected = vfio_pci_core_aer_err_detected,
+};
+
 static struct pci_driver pds_vfio_pci_driver = {
 	.name = KBUILD_MODNAME,
 	.id_table = pds_vfio_pci_table,
 	.probe = pds_vfio_pci_probe,
 	.remove = pds_vfio_pci_remove,
+	.err_handler = &pds_vfio_pci_err_handlers,
 	.driver_managed_dma = true,
 };
 
drivers/vfio/pci/pds/vfio_dev.c +119 -1

160 lines not on this page · raw message

drivers/vfio/pci/pds/vfio_dev.h +11 -0
index 824832aa1513..31bd14de0c91 100644
@@ -7,19 +7,30 @@
 #include <linux/pci.h>
 #include <linux/vfio_pci_core.h>
 
+#include "lm.h"
+
 struct pdsc;
 
 struct pds_vfio_pci_device {
 	struct vfio_pci_core_device vfio_coredev;
 	struct pdsc *pdsc;
 
+	struct pds_vfio_lm_file *save_file;
+	struct pds_vfio_lm_file *restore_file;
+	struct mutex state_mutex; /* protect migration state */
+	enum vfio_device_mig_state state;
+	spinlock_t reset_lock; /* protect reset_done flow */
+	u8 deferred_reset;
+
 	int vf_id;
 	u16 client_id;
 };
 
 const struct vfio_device_ops *pds_vfio_ops_info(void);
 struct pds_vfio_pci_device *pds_vfio_pci_drvdata(struct pci_dev *pdev);
+void pds_vfio_reset(struct pds_vfio_pci_device *pds_vfio);
 
 struct pci_dev *pds_vfio_to_pci_dev(struct pds_vfio_pci_device *pds_vfio);
+struct device *pds_vfio_to_dev(struct pds_vfio_pci_device *pds_vfio);
 
 #endif /* _VFIO_DEV_H_ */
include/linux/pds/pds_adminq.h +197 -0

215 lines not on this page · raw message

Signature · 1 line
2.17.1
reviewer
#16 lore raw

RE: [PATCH v12 vfio 4/7] vfio/pds: Add VFIO live migration support

Quoted 5 lines

From: Brett Creeley <[email protected]>
Sent: Thursday, July 20, 2023 6:35 AM

PDS_LM_CMD_STATUS is added to determine the exact size of the VF device state data.

based on the description PDS_LM_CMD_STATE_SIZE is clearer.

drivers/vfio/pci/pds/Makefile obj-$(CONFIG_PDS_VFIO_PCI) += pds-vfio-pci.o · line 8

Quoted 7 lines
drivers/vfio/pci/pds/Makefile +1 -0
@@ -5,5 +5,6 @@ obj-$(CONFIG_PDS_VFIO_PCI) += pds-vfio-pci.o
 
 pds-vfio-pci-y := \
 	cmds.o		\
+	lm.o		\

nit. "migration.o" is more readable.

Quoted 8 lines
drivers/vfio/pci/pds/Makefile +8 -0
+static int pds_vfio_client_adminq_cmd(struct pds_vfio_pci_device *pds_vfio,
+				      union pds_core_adminq_cmd *req,
+				      union pds_core_adminq_comp *resp,
+				      bool fast_poll)
+{
+	union pds_core_adminq_cmd cmd = {};
+	int err;
+

drivers/vfio/pci/pds/Makefile obj-$(CONFIG_PDS_VFIO_PCI) += pds-vfio-pci.o

Quoted 10 lines
drivers/vfio/pci/pds/Makefile +10 -0
+	/* Wrap the client request */
+	cmd.client_request.opcode = PDS_AQ_CMD_CLIENT_CMD;
+	cmd.client_request.client_id = cpu_to_le16(pds_vfio->client_id);
+	memcpy(cmd.client_request.client_cmd, req,
+	       sizeof(cmd.client_request.client_cmd));
+
+	err = pdsc_adminq_post(pds_vfio->pdsc, &cmd, resp, fast_poll);
+	if (err && err != -EAGAIN)
+		dev_info(pds_vfio_to_dev(pds_vfio),
+			 "client admin cmd failed: %pe\n", ERR_PTR(err));

dev_err()

Quoted 14 lines

+void pds_vfio_send_host_vf_lm_status_cmd(struct pds_vfio_pci_device *pds_vfio,

drivers/vfio/pci/pds/Makefile +1 -0
+					 enum pds_lm_host_vf_status

vf_status)

drivers/vfio/pci/pds/Makefile +10 -0
+{
+	union pds_core_adminq_cmd cmd = {
+		.lm_host_vf_status = {
+			.opcode = PDS_LM_CMD_HOST_VF_STATUS,
+			.vf_id = cpu_to_le16(pds_vfio->vf_id),
+			.status = vf_status,
+		},
+	};
+	struct device *dev = pds_vfio_to_dev(pds_vfio);
+	union pds_core_adminq_comp comp = {};

drivers/vfio/pci/pds/Makefile

Quoted 10 lines
drivers/vfio/pci/pds/Makefile +10 -0
+	int err;
+
+	dev_dbg(dev, "vf%u: Set host VF LM status: %u", pds_vfio->vf_id,
+		vf_status);
+	if (vf_status != PDS_LM_STA_IN_PROGRESS &&
+	    vf_status != PDS_LM_STA_NONE) {
+		dev_warn(dev, "Invalid host VF migration status, %d\n",
+			 vf_status);
+		return;
+	}

WARN_ON() as it's a driver bug if passing in unsupported status code.

Quoted 67 lines
drivers/vfio/pci/pds/Makefile +67 -0
+
+static struct pds_vfio_lm_file *
+pds_vfio_get_lm_file(const struct file_operations *fops, int flags, u64 size)
+{
+	struct pds_vfio_lm_file *lm_file = NULL;
+	unsigned long long npages;
+	struct page **pages;
+	void *page_mem;
+	const void *p;
+
+	if (!size)
+		return NULL;
+
+	/* Alloc file structure */
+	lm_file = kzalloc(sizeof(*lm_file), GFP_KERNEL);
+	if (!lm_file)
+		return NULL;
+
+	/* Create file */
+	lm_file->filep =
+		anon_inode_getfile("pds_vfio_lm", fops, lm_file, flags);
+	if (!lm_file->filep)
+		goto out_free_file;
+
+	stream_open(lm_file->filep->f_inode, lm_file->filep);
+	mutex_init(&lm_file->lock);
+
+	/* prevent file from being released before we are done with it */
+	get_file(lm_file->filep);
+
+	/* Allocate memory for file pages */
+	npages = DIV_ROUND_UP_ULL(size, PAGE_SIZE);
+	pages = kmalloc_array(npages, sizeof(*pages), GFP_KERNEL);
+	if (!pages)
+		goto out_put_file;
+
+	page_mem = kvzalloc(ALIGN(size, PAGE_SIZE), GFP_KERNEL);
+	if (!page_mem)
+		goto out_free_pages_array;
+
+	p = page_mem - offset_in_page(page_mem);
+	for (unsigned long long i = 0; i < npages; i++) {
+		if (is_vmalloc_addr(p))
+			pages[i] = vmalloc_to_page(p);
+		else
+			pages[i] = kmap_to_page((void *)p);
+		if (!pages[i])
+			goto out_free_page_mem;
+
+		p += PAGE_SIZE;
+	}
+
+	/* Create scatterlist of file pages to use for DMA mapping later */
+	if (sg_alloc_table_from_pages(&lm_file->sg_table, pages, npages, 0,
+				      size, GFP_KERNEL))
+		goto out_free_page_mem;
+
+	lm_file->size = size;
+	lm_file->pages = pages;
+	lm_file->npages = npages;
+	lm_file->page_mem = page_mem;
+	lm_file->alloc_size = npages * PAGE_SIZE;
+
+	return lm_file;
+
+out_free_page_mem:
+	kvfree(page_mem);

drivers/vfio/pci/pds/Makefile

Quoted 10 lines
drivers/vfio/pci/pds/Makefile +10 -0
+out_free_pages_array:
+	kfree(pages);
+out_put_file:
+	fput(lm_file->filep);
+	mutex_destroy(&lm_file->lock);
+out_free_file:
+	kfree(lm_file);
+
+	return NULL;
+}

I wonder whether the logic about migration file can be generalized. It's not very maintainable to have every migration driver implementing their own code for similar functions.

Did I overlook any device specific setup required here?

#17 lore raw

Re: [PATCH v12 vfio 4/7] vfio/pds: Add VFIO live migration support

Quoted 10 lines · Kevin

Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.

Quoted 5 lines

From: Brett Creeley <[email protected]>
Sent: Thursday, July 20, 2023 6:35 AM

PDS_LM_CMD_STATUS is added to determine the exact size of the VF device state data.

based on the description PDS_LM_CMD_STATE_SIZE is clearer.

I will take another look at this and see what makes the most sense.

Quoted 10 lines

drivers/vfio/pci/pds/Makefile obj-$(CONFIG_PDS_VFIO_PCI) += pds-vfio-pci.o · line 8

Quoted 8 lines
drivers/vfio/pci/pds/Makefile +1 -0
@@ -5,5 +5,6 @@ obj-$(CONFIG_PDS_VFIO_PCI) += pds-vfio-pci.o
 
  pds-vfio-pci-y := \
       cmds.o          \
+     lm.o            \

nit. "migration.o" is more readable.

I'd prefer to just leave it lm.o as I don't see a big benefit changing it to migration.o.

Quoted 40 lines
Quoted 9 lines
drivers/vfio/pci/pds/Makefile +8 -0
+static int pds_vfio_client_adminq_cmd(struct pds_vfio_pci_device *pds_vfio,
+                                   union pds_core_adminq_cmd *req,
+                                   union pds_core_adminq_comp *resp,
+                                   bool fast_poll)
+{
+     union pds_core_adminq_cmd cmd = {};
+     int err;
+

drivers/vfio/pci/pds/Makefile obj-$(CONFIG_PDS_VFIO_PCI) += pds-vfio-pci.o

Quoted 10 lines
drivers/vfio/pci/pds/Makefile +10 -0
+     /* Wrap the client request */
+     cmd.client_request.opcode = PDS_AQ_CMD_CLIENT_CMD;
+     cmd.client_request.client_id = cpu_to_le16(pds_vfio->client_id);
+     memcpy(cmd.client_request.client_cmd, req,
+            sizeof(cmd.client_request.client_cmd));
+
+     err = pdsc_adminq_post(pds_vfio->pdsc, &cmd, resp, fast_poll);
+     if (err && err != -EAGAIN)
+             dev_info(pds_vfio_to_dev(pds_vfio),
+                      "client admin cmd failed: %pe\n", ERR_PTR(err));

dev_err()

Quoted 18 lines

+void pds_vfio_send_host_vf_lm_status_cmd(struct pds_vfio_pci_device *pds_vfio,
+ enum pds_lm_host_vf_status
vf_status)

drivers/vfio/pci/pds/Makefile +14 -0
+{
+     union pds_core_adminq_cmd cmd = {
+             .lm_host_vf_status = {
+                     .opcode = PDS_LM_CMD_HOST_VF_STATUS,
+                     .vf_id = cpu_to_le16(pds_vfio->vf_id),
+                     .status = vf_status,
+             },
+     };
+     struct device *dev = pds_vfio_to_dev(pds_vfio);
+     union pds_core_adminq_comp comp = {};
+     int err;
+
+     dev_dbg(dev, "vf%u: Set host VF LM status: %u", pds_vfio->vf_id,
+             vf_status);
Quoted 8 lines

drivers/vfio/pci/pds/Makefile

Quoted 6 lines
drivers/vfio/pci/pds/Makefile +6 -0
+     if (vf_status != PDS_LM_STA_IN_PROGRESS &&
+         vf_status != PDS_LM_STA_NONE) {
+             dev_warn(dev, "Invalid host VF migration status, %d\n",
+                      vf_status);
+             return;
+     }

WARN_ON() as it's a driver bug if passing in unsupported status code.

IMO dev_warn() is good enough here. I don't plan on changing this.

Quoted 83 lines
Quoted 68 lines
drivers/vfio/pci/pds/Makefile +67 -0
+
+static struct pds_vfio_lm_file *
+pds_vfio_get_lm_file(const struct file_operations *fops, int flags, u64 size)
+{
+     struct pds_vfio_lm_file *lm_file = NULL;
+     unsigned long long npages;
+     struct page **pages;
+     void *page_mem;
+     const void *p;
+
+     if (!size)
+             return NULL;
+
+     /* Alloc file structure */
+     lm_file = kzalloc(sizeof(*lm_file), GFP_KERNEL);
+     if (!lm_file)
+             return NULL;
+
+     /* Create file */
+     lm_file->filep =
+             anon_inode_getfile("pds_vfio_lm", fops, lm_file, flags);
+     if (!lm_file->filep)
+             goto out_free_file;
+
+     stream_open(lm_file->filep->f_inode, lm_file->filep);
+     mutex_init(&lm_file->lock);
+
+     /* prevent file from being released before we are done with it */
+     get_file(lm_file->filep);
+
+     /* Allocate memory for file pages */
+     npages = DIV_ROUND_UP_ULL(size, PAGE_SIZE);
+     pages = kmalloc_array(npages, sizeof(*pages), GFP_KERNEL);
+     if (!pages)
+             goto out_put_file;
+
+     page_mem = kvzalloc(ALIGN(size, PAGE_SIZE), GFP_KERNEL);
+     if (!page_mem)
+             goto out_free_pages_array;
+
+     p = page_mem - offset_in_page(page_mem);
+     for (unsigned long long i = 0; i < npages; i++) {
+             if (is_vmalloc_addr(p))
+                     pages[i] = vmalloc_to_page(p);
+             else
+                     pages[i] = kmap_to_page((void *)p);
+             if (!pages[i])
+                     goto out_free_page_mem;
+
+             p += PAGE_SIZE;
+     }
+
+     /* Create scatterlist of file pages to use for DMA mapping later */
+     if (sg_alloc_table_from_pages(&lm_file->sg_table, pages, npages, 0,
+                                   size, GFP_KERNEL))
+             goto out_free_page_mem;
+
+     lm_file->size = size;
+     lm_file->pages = pages;
+     lm_file->npages = npages;
+     lm_file->page_mem = page_mem;
+     lm_file->alloc_size = npages * PAGE_SIZE;
+
+     return lm_file;
+
+out_free_page_mem:
+     kvfree(page_mem);

drivers/vfio/pci/pds/Makefile

Quoted 10 lines
drivers/vfio/pci/pds/Makefile +10 -0
+out_free_pages_array:
+     kfree(pages);
+out_put_file:
+     fput(lm_file->filep);
+     mutex_destroy(&lm_file->lock);
+out_free_file:
+     kfree(lm_file);
+
+     return NULL;
+}

I wonder whether the logic about migration file can be generalized. It's not very maintainable to have every migration driver implementing their own code for similar functions.

Quoted 1 line

Did I overlook any device specific setup required here?

There isn't device specific setup, but the other drivers were different enough that it wasn't a straight forward task. I think it might be possible to refactor the drivers to some common functionality here, but IMO this seems like a task that can be further explored once this series is merged.

Thanks for the review.

Brett

reviewer
#18 lore raw

RE: [PATCH v12 vfio 4/7] vfio/pds: Add VFIO live migration support

Quoted 13 lines

From: Brett Creeley <[email protected]>
Sent: Saturday, July 22, 2023 3:18 PM

Quoted 3 lines

drivers/vfio/pci/pds/lm.c

Quoted 3 lines
drivers/vfio/pci/pds/lm.c new file +3 -0
+
+static struct pds_vfio_lm_file *
+pds_vfio_get_lm_file(const struct file_operations *fops, int flags, u64

size)

Quoted 7 lines
Quoted 7 lines
drivers/vfio/pci/pds/lm.c new file +7 -0
+{
+     struct pds_vfio_lm_file *lm_file = NULL;
+     unsigned long long npages;
+     struct page **pages;
+     void *page_mem;
+     const void *p;
+

[...]

Quoted 5 lines
Quoted 5 lines

I wonder whether the logic about migration file can be generalized. It's not very maintainable to have every migration driver implementing their own code for similar functions.

Quoted 8 lines
Quoted 1 line

Did I overlook any device specific setup required here?

There isn't device specific setup, but the other drivers were different enough that it wasn't a straight forward task. I think it might be possible to refactor the drivers to some common functionality here, but IMO this seems like a task that can be further explored once this series is merged.

If there is no device specific setup I don't see a reason to further proliferate the code duplication. At least it's an increasing review burden to me.

I'd like to hear opinions from other reviewers.

#19 lore raw

Re: [PATCH v12 vfio 4/7] vfio/pds: Add VFIO live migration support

In reply to Brett Creeley
Quoted 10 lines · Brett Creeley
Quoted 5 lines

I wonder whether the logic about migration file can be generalized. It's not very maintainable to have every migration driver implementing their own code for similar functions.

Did I overlook any device specific setup required here?

There isn't device specific setup, but the other drivers were different enough that it wasn't a straight forward task. I think it might be possible to refactor the drivers to some common functionality here, but IMO this seems like a task that can be further explored once this series is merged.

You keep saying that but, things seem to be getting worse. There are alot of migration drivers being posted right now with alot of copy and paste from mlx5.

Jason

#20 lore raw

Re: [PATCH v12 vfio 4/7] vfio/pds: Add VFIO live migration support

Quoted 10 lines · Jason Gunthorpe

Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.

Quoted 6 lines · Brett Creeley
Quoted 5 lines

I wonder whether the logic about migration file can be generalized. It's not very maintainable to have every migration driver implementing their own code for similar functions.

Did I overlook any device specific setup required here?

Quoted 8 lines
Quoted 4 lines

There isn't device specific setup, but the other drivers were different enough that it wasn't a straight forward task. I think it might be possible to refactor the drivers to some common functionality here, but IMO this seems like a task that can be further explored once this series is merged.

You keep saying that but, things seem to be getting worse. There are alot of migration drivers being posted right now with alot of copy and paste from mlx5.

I understand and agree with what you guys are saying. However, I was also asked to simplify this code for our use case in v9, which I have done. I’d like to get this finalized so that I have a chance to get to the next step and maybe work with all involved to define what can be commonized and how to get there.

Brett

Quoted 2 lines

Jason

#21 lore raw

Re: [PATCH v12 vfio 4/7] vfio/pds: Add VFIO live migration support

In reply to Brett Creeley

On Wed, Jul 19, 2023 at 03:35:24PM -0700, Brett Creeley wrote:

...

Quoted 1 line
drivers/vfio/pci/pds/lm.c +0 -0

...

drivers/vfio/pci/pds/lm.c line 238

Quoted 6 lines
drivers/vfio/pci/pds/lm.c +6 -0
+static int pds_vfio_get_save_file(struct pds_vfio_pci_device *pds_vfio)
+{
+	struct device *dev = &pds_vfio->vfio_coredev.pdev->dev;
+	struct pds_vfio_lm_file *lm_file;
+	int err;
+	u64 size;

Hi Brett,

please use reverse xmas tree - longest line to shortest - for these local variable declarations.

https://github.com/ecree-solarflare/xmastree is your friend here.

#22 lore raw

Re: [PATCH v12 vfio 4/7] vfio/pds: Add VFIO live migration support

Quoted 20 lines · Simon Horman

Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.

On Wed, Jul 19, 2023 at 03:35:24PM -0700, Brett Creeley wrote:

...

Quoted 1 line
drivers/vfio/pci/pds/lm.c +0 -0

...

drivers/vfio/pci/pds/lm.c line 238

Quoted 6 lines
drivers/vfio/pci/pds/lm.c +6 -0
+static int pds_vfio_get_save_file(struct pds_vfio_pci_device *pds_vfio)
+{
+     struct device *dev = &pds_vfio->vfio_coredev.pdev->dev;
+     struct pds_vfio_lm_file *lm_file;
+     int err;
+     u64 size;

Hi Brett,

Quoted 4 lines

please use reverse xmas tree - longest line to shortest - for these local variable declarations.

https://github.com/ecree-solarflare/xmastree is your friend here.

Ah, good catch and thanks for the reference. Will fix on v13.

author maintainer
#23 lore raw

PATCH v12 5/7 vfio/pds: Add support for dirty page tracking

In reply to Brett Creeley

In order to support dirty page tracking, the driver has to implement the VFIO subsystem's vfio_log_ops. This includes log_start, log_stop, and log_read_and_clear.

All of the tracker resources are allocated and dirty tracking on the device is started during log_start. The resources are cleaned up and dirty tracking on the device is stopped during log_stop. The dirty pages are determined and reported during log_read_and_clear.

In order to support these callbacks admin queue commands are used. All of the adminq queue command structures and implementations are included as part of this patch.

PDS_LM_CMD_DIRTY_STATUS is added to query the current status of dirty tracking on the device. This includes if it's enabled (i.e. number of regions being tracked from the device's perspective) and the maximum number of regions supported from the device's perspective.

PDS_LM_CMD_DIRTY_ENABLE is added to enable dirty tracking on the specified number of regions and their iova ranges.

PDS_LM_CMD_DIRTY_DISABLE is added to disable dirty tracking for all regions on the device.

PDS_LM_CMD_READ_SEQ and PDS_LM_CMD_DIRTY_WRITE_ACK are added to support reading and acknowledging the currently dirtied pages.

---
 drivers/vfio/pci/pds/Makefile   |   1 +
 drivers/vfio/pci/pds/cmds.c     | 125 +++++++
 drivers/vfio/pci/pds/cmds.h     |   9 +
 drivers/vfio/pci/pds/dirty.c    | 576 ++++++++++++++++++++++++++++++++
 drivers/vfio/pci/pds/dirty.h    |  39 +++
 drivers/vfio/pci/pds/lm.c       |   2 +-
 drivers/vfio/pci/pds/vfio_dev.c |  12 +-
 drivers/vfio/pci/pds/vfio_dev.h |   4 +
 include/linux/pds/pds_adminq.h  | 178 ++++++++++
 9 files changed, 944 insertions(+), 2 deletions(-)
 create mode 100644 drivers/vfio/pci/pds/dirty.c
 create mode 100644 drivers/vfio/pci/pds/dirty.h
drivers/vfio/pci/pds/Makefile +1 -0
index 47750bb31ea2..d5a06d81634f 100644
@@ -5,6 +5,7 @@ obj-$(CONFIG_PDS_VFIO_PCI) += pds-vfio-pci.o
 
 pds-vfio-pci-y := \
 	cmds.o		\
+	dirty.o		\
 	lm.o		\
 	pci_drv.o	\
 	vfio_dev.o
drivers/vfio/pci/pds/cmds.c +125 -0

128 lines not on this page · raw message

drivers/vfio/pci/pds/cmds.h +9 -0
index 1097e96d3c11..8d20118fb4a6 100644
@@ -13,4 +13,13 @@ int pds_vfio_get_lm_state_cmd(struct pds_vfio_pci_device *pds_vfio);
 int pds_vfio_set_lm_state_cmd(struct pds_vfio_pci_device *pds_vfio);
 void pds_vfio_send_host_vf_lm_status_cmd(struct pds_vfio_pci_device *pds_vfio,
 					 enum pds_lm_host_vf_status vf_status);
+int pds_vfio_dirty_status_cmd(struct pds_vfio_pci_device *pds_vfio,
+			      u64 regions_dma, u8 *max_regions,
+			      u8 *num_regions);
+int pds_vfio_dirty_enable_cmd(struct pds_vfio_pci_device *pds_vfio,
+			      u64 regions_dma, u8 num_regions);
+int pds_vfio_dirty_disable_cmd(struct pds_vfio_pci_device *pds_vfio);
+int pds_vfio_dirty_seq_ack_cmd(struct pds_vfio_pci_device *pds_vfio,
+			       u64 sgl_dma, u16 num_sge, u32 offset,
+			       u32 total_len, bool read_seq);
 #endif /* _CMDS_H_ */
drivers/vfio/pci/pds/dirty.c new file +576 -0

576 lines not on this page · raw message

drivers/vfio/pci/pds/dirty.h new file +39 -0
new file mode 100644
index 000000000000..f78da25d75ca
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2023 Advanced Micro Devices, Inc. */
+
+#ifndef _DIRTY_H_
+#define _DIRTY_H_
+
+struct pds_vfio_bmp_info {
+	unsigned long *bmp;
+	u32 bmp_bytes;
+	struct pds_lm_sg_elem *sgl;
+	dma_addr_t sgl_addr;
+	u16 num_sge;
+};
+
+struct pds_vfio_dirty {
+	struct pds_vfio_bmp_info host_seq;
+	struct pds_vfio_bmp_info host_ack;
+	u64 region_size;
+	u64 region_start;
+	u64 region_page_size;
+	bool is_enabled;
+};
+
+struct pds_vfio_pci_device;
+
+bool pds_vfio_dirty_is_enabled(struct pds_vfio_pci_device *pds_vfio);
+void pds_vfio_dirty_set_enabled(struct pds_vfio_pci_device *pds_vfio);
+void pds_vfio_dirty_set_disabled(struct pds_vfio_pci_device *pds_vfio);
+void pds_vfio_dirty_disable(struct pds_vfio_pci_device *pds_vfio,
+			    bool send_cmd);
+
+int pds_vfio_dma_logging_report(struct vfio_device *vdev, unsigned long iova,
+				unsigned long length,
+				struct iova_bitmap *dirty);
+int pds_vfio_dma_logging_start(struct vfio_device *vdev,
+			       struct rb_root_cached *ranges, u32 nnodes,
+			       u64 *page_size);
+int pds_vfio_dma_logging_stop(struct vfio_device *vdev);
+#endif /* _DIRTY_H_ */
drivers/vfio/pci/pds/lm.c +1 -1
index 10c051d46851..a8745877a2fd 100644
@@ -371,7 +371,7 @@ pds_vfio_step_device_state_locked(struct pds_vfio_pci_device *pds_vfio,
 
 	if (cur == VFIO_DEVICE_STATE_STOP_COPY && next == VFIO_DEVICE_STATE_STOP) {
 		pds_vfio_put_save_file(pds_vfio);
-		pds_vfio_send_host_vf_lm_status_cmd(pds_vfio, PDS_LM_STA_NONE);
+		pds_vfio_dirty_disable(pds_vfio, true);
 		return NULL;
 	}
 
drivers/vfio/pci/pds/vfio_dev.c +11 -1
index f4dfd5d5ba09..eb832af39545 100644
@@ -5,6 +5,7 @@
 #include <linux/vfio_pci_core.h>
 
 #include "lm.h"
+#include "dirty.h"
 #include "vfio_dev.h"
 
 struct pci_dev *pds_vfio_to_pci_dev(struct pds_vfio_pci_device *pds_vfio)
@@ -25,7 +26,7 @@ struct pds_vfio_pci_device *pds_vfio_pci_drvdata(struct pci_dev *pdev)
 			    vfio_coredev);
 }
 
-static void pds_vfio_state_mutex_unlock(struct pds_vfio_pci_device *pds_vfio)
+void pds_vfio_state_mutex_unlock(struct pds_vfio_pci_device *pds_vfio)
 {
 again:
 	spin_lock(&pds_vfio->reset_lock);
@@ -35,6 +36,7 @@ static void pds_vfio_state_mutex_unlock(struct pds_vfio_pci_device *pds_vfio)
 			pds_vfio->state = VFIO_DEVICE_STATE_RUNNING;
 			pds_vfio_put_restore_file(pds_vfio);
 			pds_vfio_put_save_file(pds_vfio);
+			pds_vfio_dirty_disable(pds_vfio, false);
 		}
 		spin_unlock(&pds_vfio->reset_lock);
 		goto again;
@@ -117,6 +119,12 @@ static const struct vfio_migration_ops pds_vfio_lm_ops = {
 	.migration_get_data_size = pds_vfio_get_device_state_size
 };
 
+static const struct vfio_log_ops pds_vfio_log_ops = {
+	.log_start = pds_vfio_dma_logging_start,
+	.log_stop = pds_vfio_dma_logging_stop,
+	.log_read_and_clear = pds_vfio_dma_logging_report,
+};
+
 static int pds_vfio_init_device(struct vfio_device *vdev)
 {
 	struct pds_vfio_pci_device *pds_vfio =
@@ -137,6 +145,7 @@ static int pds_vfio_init_device(struct vfio_device *vdev)
 
 	vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P;
 	vdev->mig_ops = &pds_vfio_lm_ops;
+	vdev->log_ops = &pds_vfio_log_ops;
 
 	pci_id = PCI_DEVID(pdev->bus->number, pdev->devfn);
 	dev_dbg(&pdev->dev,
@@ -175,6 +184,7 @@ static void pds_vfio_close_device(struct vfio_device *vdev)
 	mutex_lock(&pds_vfio->state_mutex);
 	pds_vfio_put_restore_file(pds_vfio);
 	pds_vfio_put_save_file(pds_vfio);
+	pds_vfio_dirty_disable(pds_vfio, true);
 	mutex_unlock(&pds_vfio->state_mutex);
 	mutex_destroy(&pds_vfio->state_mutex);
 	vfio_pci_core_close_device(vdev);
drivers/vfio/pci/pds/vfio_dev.h +4 -0
index 31bd14de0c91..8109fe101694 100644
@@ -7,6 +7,7 @@
 #include <linux/pci.h>
 #include <linux/vfio_pci_core.h>
 
+#include "dirty.h"
 #include "lm.h"
 
 struct pdsc;
@@ -17,6 +18,7 @@ struct pds_vfio_pci_device {
 
 	struct pds_vfio_lm_file *save_file;
 	struct pds_vfio_lm_file *restore_file;
+	struct pds_vfio_dirty dirty;
 	struct mutex state_mutex; /* protect migration state */
 	enum vfio_device_mig_state state;
 	spinlock_t reset_lock; /* protect reset_done flow */
@@ -26,6 +28,8 @@ struct pds_vfio_pci_device {
 	u16 client_id;
 };
 
+void pds_vfio_state_mutex_unlock(struct pds_vfio_pci_device *pds_vfio);
+
 const struct vfio_device_ops *pds_vfio_ops_info(void);
 struct pds_vfio_pci_device *pds_vfio_pci_drvdata(struct pci_dev *pdev);
 void pds_vfio_reset(struct pds_vfio_pci_device *pds_vfio);
include/linux/pds/pds_adminq.h +178 -0

202 lines not on this page · raw message

Signature · 1 line
2.17.1
#24 lore raw

Re: [PATCH v12 vfio 5/7] vfio/pds: Add support for dirty page tracking

On Wed, Jul 19, 2023 at 03:35:25PM -0700, Brett Creeley wrote:

...

drivers/vfio/pci/pds/dirty.c line 99

Quoted 6 lines
drivers/vfio/pci/pds/dirty.c new file +6 -0
+static void pds_vfio_dirty_free_bitmaps(struct pds_vfio_dirty *dirty)
+{
+	if (dirty->host_seq.bmp)
+		vfree(dirty->host_seq.bmp);
+	if (dirty->host_ack.bmp)
+		vfree(dirty->host_ack.bmp);

Hi Brett,

I don't think there is a need to guard these vfree calls, as I think they will be no-ops with NULL arguments.

Quoted 4 lines
drivers/vfio/pci/pds/dirty.c new file +4 -0
+
+	dirty->host_seq.bmp = NULL;
+	dirty->host_ack.bmp = NULL;
+}

...

#25 lore raw

Re: [PATCH v12 vfio 5/7] vfio/pds: Add support for dirty page tracking

Quoted 16 lines · Simon Horman

Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.

On Wed, Jul 19, 2023 at 03:35:25PM -0700, Brett Creeley wrote:

...

drivers/vfio/pci/pds/dirty.c line 99

Quoted 6 lines
drivers/vfio/pci/pds/dirty.c new file +6 -0
+static void pds_vfio_dirty_free_bitmaps(struct pds_vfio_dirty *dirty)
+{
+     if (dirty->host_seq.bmp)
+             vfree(dirty->host_seq.bmp);
+     if (dirty->host_ack.bmp)
+             vfree(dirty->host_ack.bmp);

Hi Brett,

Quoted 2 lines

I don't think there is a need to guard these vfree calls, as I think they will be no-ops with NULL arguments.

Another good catch. I will also fix this for v13. Thanks for the review.

Brett

Quoted 8 lines
Quoted 5 lines
drivers/vfio/pci/pds/dirty.c new file +4 -0
+
+     dirty->host_seq.bmp = NULL;
+     dirty->host_ack.bmp = NULL;
+}

...

author maintainer
#26 lore raw

PATCH v12 6/7 vfio/pds: Add support for firmware recovery

In reply to Brett Creeley

It's possible that the device firmware crashes and is able to recover due to some configuration and/or other issue. If a live migration is in progress while the firmware crashes, the live migration will fail. However, the VF PCI device should still be functional post crash recovery and subsequent migrations should go through as expected.

When the pds_core device notices that firmware crashes it sends an event to all its client drivers. When the pds_vfio driver receives this event while migration is in progress it will request a deferred reset on the next migration state transition. This state transition will report failure as well as any subsequent state transition requests from the VMM/VFIO. Based on uapi/vfio.h the only way out of VFIO_DEVICE_STATE_ERROR is by issuing VFIO_DEVICE_RESET. Once this reset is done, the migration state will be reset to VFIO_DEVICE_STATE_RUNNING and migration can be performed.

If the event is received while no migration is in progress (i.e. the VM is in normal operating mode), then no actions are taken and the migration state remains VFIO_DEVICE_STATE_RUNNING.

---
 drivers/vfio/pci/pds/pci_drv.c  | 114 ++++++++++++++++++++++++++++++++
 drivers/vfio/pci/pds/vfio_dev.c |  17 ++++-
 drivers/vfio/pci/pds/vfio_dev.h |   2 +
 3 files changed, 131 insertions(+), 2 deletions(-)
drivers/vfio/pci/pds/pci_drv.c +114 -0
index c1739edd261a..a03b7d5a3e60 100644
@@ -19,6 +19,113 @@
 #define PDS_VFIO_DRV_DESCRIPTION	"AMD/Pensando VFIO Device Driver"
 #define PCI_VENDOR_ID_PENSANDO		0x1dd8
 
+static void pds_vfio_recovery(struct pds_vfio_pci_device *pds_vfio)
+{
+	bool deferred_reset_needed = false;
+
+	/*
+	 * Documentation states that the kernel migration driver must not
+	 * generate asynchronous device state transitions outside of
+	 * manipulation by the user or the VFIO_DEVICE_RESET ioctl.
+	 *
+	 * Since recovery is an asynchronous event received from the device,
+	 * initiate a deferred reset. Issue a deferred reset in the following
+	 * situations:
+	 *   1. Migration is in progress, which will cause the next step of
+	 *	the migration to fail.
+	 *   2. If the device is in a state that will be set to
+	 *	VFIO_DEVICE_STATE_RUNNING on the next action (i.e. VM is
+	 *	shutdown and device is in VFIO_DEVICE_STATE_STOP).
+	 */
+	mutex_lock(&pds_vfio->state_mutex);
+	if ((pds_vfio->state != VFIO_DEVICE_STATE_RUNNING &&
+	     pds_vfio->state != VFIO_DEVICE_STATE_ERROR) ||
+	    (pds_vfio->state == VFIO_DEVICE_STATE_RUNNING &&
+	     pds_vfio_dirty_is_enabled(pds_vfio)))
+		deferred_reset_needed = true;
+	mutex_unlock(&pds_vfio->state_mutex);
+
+	/*
+	 * On the next user initiated state transition, the device will
+	 * transition to the VFIO_DEVICE_STATE_ERROR. At this point it's the user's
+	 * responsibility to reset the device.
+	 *
+	 * If a VFIO_DEVICE_RESET is requested post recovery and before the next
+	 * state transition, then the deferred reset state will be set to
+	 * VFIO_DEVICE_STATE_RUNNING.
+	 */
+	if (deferred_reset_needed) {
+		spin_lock(&pds_vfio->reset_lock);
+		pds_vfio->deferred_reset = true;
+		pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_ERROR;
+		spin_unlock(&pds_vfio->reset_lock);
+	}
+}
+
+static int pds_vfio_pci_notify_handler(struct notifier_block *nb,
+				       unsigned long ecode, void *data)
+{
+	struct pds_vfio_pci_device *pds_vfio =
+		container_of(nb, struct pds_vfio_pci_device, nb);
+	struct device *dev = pds_vfio_to_dev(pds_vfio);
+	union pds_core_notifyq_comp *event = data;
+
+	dev_dbg(dev, "%s: event code %lu\n", __func__, ecode);
+
+	/*
+	 * We don't need to do anything for RESET state==0 as there is no notify
+	 * or feedback mechanism available, and it is possible that we won't
+	 * even see a state==0 event since the pds_core recovery is pending.
+	 *
+	 * Any requests from VFIO while state==0 will fail, which will return
+	 * error and may cause migration to fail.
+	 */
+	if (ecode == PDS_EVENT_RESET) {
+		dev_info(dev, "%s: PDS_EVENT_RESET event received, state==%d\n",
+			 __func__, event->reset.state);
+		/*
+		 * pds_core device finished recovery and sent us the
+		 * notification (state == 1) to allow us to recover
+		 */
+		if (event->reset.state == 1)
+			pds_vfio_recovery(pds_vfio);
+	}
+
+	return 0;
+}
+
+static int
+pds_vfio_pci_register_event_handler(struct pds_vfio_pci_device *pds_vfio)
+{
+	struct device *dev = pds_vfio_to_dev(pds_vfio);
+	struct notifier_block *nb = &pds_vfio->nb;
+	int err;
+
+	if (!nb->notifier_call) {
+		nb->notifier_call = pds_vfio_pci_notify_handler;
+		err = pdsc_register_notify(nb);
+		if (err) {
+			nb->notifier_call = NULL;
+			dev_err(dev,
+				"failed to register pds event handler: %pe\n",
+				ERR_PTR(err));
+			return -EINVAL;
+		}
+		dev_dbg(dev, "pds event handler registered\n");
+	}
+
+	return 0;
+}
+
+static void
+pds_vfio_pci_unregister_event_handler(struct pds_vfio_pci_device *pds_vfio)
+{
+	if (pds_vfio->nb.notifier_call) {
+		pdsc_unregister_notify(&pds_vfio->nb);
+		pds_vfio->nb.notifier_call = NULL;
+	}
+}
+
 static int pds_vfio_pci_probe(struct pci_dev *pdev,
 			      const struct pci_device_id *id)
 {
@@ -48,8 +155,14 @@ static int pds_vfio_pci_probe(struct pci_dev *pdev,
 		goto out_unregister_coredev;
 	}
 
+	err = pds_vfio_pci_register_event_handler(pds_vfio);
+	if (err)
+		goto out_unregister_client;
+
 	return 0;
 
+out_unregister_client:
+	pds_vfio_unregister_client_cmd(pds_vfio);
 out_unregister_coredev:
 	vfio_pci_core_unregister_device(&pds_vfio->vfio_coredev);
 out_put_vdev:
@@ -61,6 +174,7 @@ static void pds_vfio_pci_remove(struct pci_dev *pdev)
 {
 	struct pds_vfio_pci_device *pds_vfio = pds_vfio_pci_drvdata(pdev);
 
+	pds_vfio_pci_unregister_event_handler(pds_vfio);
 	pds_vfio_unregister_client_cmd(pds_vfio);
 	vfio_pci_core_unregister_device(&pds_vfio->vfio_coredev);
 	vfio_put_device(&pds_vfio->vfio_coredev.vdev);
drivers/vfio/pci/pds/vfio_dev.c +15 -2
index eb832af39545..b38c66bf28a4 100644
@@ -33,11 +33,12 @@ void pds_vfio_state_mutex_unlock(struct pds_vfio_pci_device *pds_vfio)
 	if (pds_vfio->deferred_reset) {
 		pds_vfio->deferred_reset = false;
 		if (pds_vfio->state == VFIO_DEVICE_STATE_ERROR) {
-			pds_vfio->state = VFIO_DEVICE_STATE_RUNNING;
 			pds_vfio_put_restore_file(pds_vfio);
 			pds_vfio_put_save_file(pds_vfio);
 			pds_vfio_dirty_disable(pds_vfio, false);
 		}
+		pds_vfio->state = pds_vfio->deferred_reset_state;
+		pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
 		spin_unlock(&pds_vfio->reset_lock);
 		goto again;
 	}
@@ -49,6 +50,7 @@ void pds_vfio_reset(struct pds_vfio_pci_device *pds_vfio)
 {
 	spin_lock(&pds_vfio->reset_lock);
 	pds_vfio->deferred_reset = true;
+	pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
 	if (!mutex_trylock(&pds_vfio->state_mutex)) {
 		spin_unlock(&pds_vfio->reset_lock);
 		return;
@@ -67,7 +69,14 @@ pds_vfio_set_device_state(struct vfio_device *vdev,
 	struct file *res = NULL;
 
 	mutex_lock(&pds_vfio->state_mutex);
-	while (new_state != pds_vfio->state) {
+	/*
+	 * only way to transition out of VFIO_DEVICE_STATE_ERROR is via
+	 * VFIO_DEVICE_RESET, so prevent the state machine from running since
+	 * vfio_mig_get_next_state() will throw a WARN_ON() when transitioning
+	 * from VFIO_DEVICE_STATE_ERROR to any other state
+	 */
+	while (pds_vfio->state != VFIO_DEVICE_STATE_ERROR &&
+	       new_state != pds_vfio->state) {
 		enum vfio_device_mig_state next_state;
 
 		int err = vfio_mig_get_next_state(vdev, pds_vfio->state,
@@ -89,6 +98,9 @@ pds_vfio_set_device_state(struct vfio_device *vdev,
 		}
 	}
 	pds_vfio_state_mutex_unlock(pds_vfio);
+	/* still waiting on a deferred_reset */
+	if (pds_vfio->state == VFIO_DEVICE_STATE_ERROR)
+		res = ERR_PTR(-EIO);
 
 	return res;
 }
@@ -169,6 +181,7 @@ static int pds_vfio_open_device(struct vfio_device *vdev)
 
 	mutex_init(&pds_vfio->state_mutex);
 	pds_vfio->state = VFIO_DEVICE_STATE_RUNNING;
+	pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
 
 	vfio_pci_core_finish_enable(&pds_vfio->vfio_coredev);
 
drivers/vfio/pci/pds/vfio_dev.h +2 -0
index 8109fe101694..30a7d22f48eb 100644
@@ -23,6 +23,8 @@ struct pds_vfio_pci_device {
 	enum vfio_device_mig_state state;
 	spinlock_t reset_lock; /* protect reset_done flow */
 	u8 deferred_reset;
+	enum vfio_device_mig_state deferred_reset_state;
+	struct notifier_block nb;
 
 	int vf_id;
 	u16 client_id;
Signature · 1 line
2.17.1
author maintainer
#27 lore raw

PATCH v12 7/7 vfio/pds: Add Kconfig and documentation

In reply to Brett Creeley

Add Kconfig entries and pds-vfio-pci.rst. Also, add an entry in the MAINTAINERS file for this new driver.

It's not clear where documentation for vendor specific VFIO drivers should live, so just re-use the current amd ethernet location.

---
 .../ethernet/amd/pds_vfio_pci.rst             | 79 +++++++++++++++++++
 .../device_drivers/ethernet/index.rst         |  1 +
 MAINTAINERS                                   |  7 ++
 drivers/vfio/pci/Kconfig                      |  2 +
 drivers/vfio/pci/pds/Kconfig                  | 19 +++++
 5 files changed, 108 insertions(+)
 create mode 100644 Documentation/networking/device_drivers/ethernet/amd/pds_vfio_pci.rst
 create mode 100644 drivers/vfio/pci/pds/Kconfig
Documentation/networking/device_drivers/ethernet/amd/pds_vfio_pci.rst new file +79 -0
new file mode 100644
index 000000000000..7a6bc848a2b2
@@ -0,0 +1,79 @@
+.. SPDX-License-Identifier: GPL-2.0+
+.. note: can be edited and viewed with /usr/bin/formiko-vim
+
+==========================================================
+PCI VFIO driver for the AMD/Pensando(R) DSC adapter family
+==========================================================
+
+AMD/Pensando Linux VFIO PCI Device Driver
+Copyright(c) 2023 Advanced Micro Devices, Inc.
+
+Overview
+========
+
+The ``pds-vfio-pci`` module is a PCI driver that supports Live Migration
+capable Virtual Function (VF) devices in the DSC hardware.
+
+Using the device
+================
+
+The pds-vfio-pci device is enabled via multiple configuration steps and
+depends on the ``pds_core`` driver to create and enable SR-IOV Virtual
+Function devices.
+
+Shown below are the steps to bind the driver to a VF and also to the
+associated auxiliary device created by the ``pds_core`` driver. This
+example assumes the pds_core and pds-vfio-pci modules are already
+loaded.
+
+.. code-block:: bash
+  :name: example-setup-script
+
+  #!/bin/bash
+
+  PF_BUS="0000:60"
+  PF_BDF="0000:60:00.0"
+  VF_BDF="0000:60:00.1"
+
+  # Prevent non-vfio VF driver from probing the VF device
+  echo 0 > /sys/class/pci_bus/$PF_BUS/device/$PF_BDF/sriov_drivers_autoprobe
+
+  # Create single VF for Live Migration via pds_core
+  echo 1 > /sys/bus/pci/drivers/pds_core/$PF_BDF/sriov_numvfs
+
+  # Allow the VF to be bound to the pds-vfio-pci driver
+  echo "pds-vfio-pci" > /sys/class/pci_bus/$PF_BUS/device/$VF_BDF/driver_override
+
+  # Bind the VF to the pds-vfio-pci driver
+  echo "$VF_BDF" > /sys/bus/pci/drivers/pds-vfio-pci/bind
+
+After performing the steps above, a file in /dev/vfio/<iommu_group>
+should have been created.
+
+
+Enabling the driver
+===================
+
+The driver is enabled via the standard kernel configuration system,
+using the make command::
+
+  make oldconfig/menuconfig/etc.
+
+The driver is located in the menu structure at:
+
+  -> Device Drivers
+    -> VFIO Non-Privileged userspace driver framework
+      -> VFIO support for PDS PCI devices
+
+Support
+=======
+
+For general Linux networking support, please use the netdev mailing
+list, which is monitored by Pensando personnel::
+
+  [email protected]
+
+For more specific support needs, please use the Pensando driver support
+email::
+
+  [email protected]
Documentation/networking/device_drivers/ethernet/index.rst +1 -0
index 94ecb67c0885..9827e816084b 100644
@@ -16,6 +16,7 @@ Contents:
    altera/altera_tse
    amd/pds_core
    amd/pds_vdpa
+   amd/pds_vfio_pci
    aquantia/atlantic
    chelsio/cxgb
    cirrus/cs89x0
MAINTAINERS +7 -0
index d30f622ed7b9..d320d76aaf7b 100644
@@ -22423,6 +22423,13 @@ S:	Maintained
 P:	Documentation/driver-api/vfio-pci-device-specific-driver-acceptance.rst
 F:	drivers/vfio/pci/*/
 
+VFIO PDS PCI DRIVER
+M:	Brett Creeley <[email protected]>
+L:	[email protected]
+S:	Maintained
+F:	Documentation/networking/device_drivers/ethernet/amd/pds_vfio_pci.rst
+F:	drivers/vfio/pci/pds/
+
 VFIO PLATFORM DRIVER
 M:	Eric Auger <[email protected]>
 L:	[email protected]
drivers/vfio/pci/Kconfig +2 -0
index 86bb7835cf3c..8125e5f37832 100644
@@ -63,4 +63,6 @@ source "drivers/vfio/pci/mlx5/Kconfig"
 
 source "drivers/vfio/pci/hisilicon/Kconfig"
 
+source "drivers/vfio/pci/pds/Kconfig"
+
 endmenu
drivers/vfio/pci/pds/Kconfig new file +19 -0
new file mode 100644
index 000000000000..407b3fd32733
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2023 Advanced Micro Devices, Inc.
+
+config PDS_VFIO_PCI
+	tristate "VFIO support for PDS PCI devices"
+	depends on PDS_CORE
+	select VFIO_PCI_CORE
+	help
+	  This provides generic PCI support for PDS devices using the VFIO
+	  framework.
+
+	  More specific information on this driver can be
+	  found in
+	  <file:Documentation/networking/device_drivers/ethernet/amd/pds_vfio_pci.rst>.
+
+	  To compile this driver as a module, choose M here. The module
+	  will be called pds-vfio-pci.
+
+	  If you don't know what to do here, say N.
Signature · 1 line
2.17.1