net/mlx5_core: Add base sriov support

This patch adds SRIOV base support for mlx5 supported devices. The same
driver is used for both PFs and VFs; VFs are identified by the driver
through the flag MLX5_PCI_DEV_IS_VF added to the pci table entries.
Virtual functions are created as usual through writing a value to the
sriov_numvs sysfs file of the PF device. Upon instantiating VFs, they will
all be probed by the driver on the hypervisor. One can gracefully unbind
them through /sys/bus/pci/drivers/mlx5_core/unbind.

mlx5_wait_for_vf_pages() was added to ensure that when a VF dies without
executing proper teardown, the hypervisor driver waits till all of the
pages that were allocated at the hypervisor to maintain its operation
are returned.

In order for the VF to be operational, the PF needs to call enable_hca
for it. This can be done before the VFs are created through a call to
pci_enable_sriov.

If the there are VFs assigned to a VMs when the driver of the PF is
unloaded, all the VF will experience system error and PF driver unloads
cleanly; in this case pci_disable_sriov is not called and the devices
will show when running lspci. Once the PF driver is reloaded, it will
sync its data structures which maintain state on its VFs.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 27 insertions, 1 deletions

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 5c857f2a20d7..efebb87163c8 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -426,6 +426,16 @@ struct mlx5_mr_table {
 	struct radix_tree_root	tree;
 };
 
+struct mlx5_vf_context {
+	int	enabled;
+};
+
+struct mlx5_core_sriov {
+	struct mlx5_vf_context	*vfs_ctx;
+	int			num_vfs;
+	int			enabled_vfs;
+};
+
 struct mlx5_irq_info {
 	cpumask_var_t mask;
 	char name[MLX5_MAX_IRQ_NAME];
@@ -447,6 +457,7 @@ struct mlx5_priv {
 	int			fw_pages;
 	atomic_t		reg_pages;
 	struct list_head	free_list;
+	int			vfs_pages;
 
 	struct mlx5_core_health health;
 
@@ -485,6 +496,8 @@ struct mlx5_priv {
 	struct list_head        dev_list;
 	struct list_head        ctx_list;
 	spinlock_t              ctx_lock;
+	struct mlx5_core_sriov	sriov;
+	unsigned long		pci_dev_data;
 };
 
 enum mlx5_device_state {
@@ -739,6 +752,8 @@ void mlx5_pagealloc_init(struct mlx5_core_dev *dev);
 void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev);
 int mlx5_pagealloc_start(struct mlx5_core_dev *dev);
 void mlx5_pagealloc_stop(struct mlx5_core_dev *dev);
+int mlx5_sriov_init(struct mlx5_core_dev *dev);
+int mlx5_sriov_cleanup(struct mlx5_core_dev *dev);
 void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
 				 s32 npages);
 int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot);
@@ -884,6 +899,15 @@ struct mlx5_profile {
 	} mr_cache[MAX_MR_CACHE_ENTRIES];
 };
 
+enum {
+	MLX5_PCI_DEV_IS_VF		= 1 << 0,
+};
+
+static inline int mlx5_core_is_pf(struct mlx5_core_dev *dev)
+{
+	return !(dev->priv.pci_dev_data & MLX5_PCI_DEV_IS_VF);
+}
+
 static inline int mlx5_get_gid_table_len(u16 param)
 {
 	if (param > 4) {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 1565324eb620..9b76fddd696b 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -665,7 +665,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_17[0x1];
 	u8         ets[0x1];
 	u8         nic_flow_table[0x1];
-	u8         reserved_18[0x4];
+	u8	   reserved_18_0;
+	u8	   early_vf_enable;
+	u8         reserved_18[0x2];
 	u8         local_ca_ack_delay[0x5];
 	u8         reserved_19[0x6];
 	u8         port_type[0x2];