qed: Add CONFIG_QED_SRIOV

Add support for a new Kconfig option for qed* driver which would allow
[eventually] the support in VFs.

This patch adds the necessary logic in the PF to learn about the possible
VFs it will have to support [Based on PCI configuration space and HW],
and prepare a database with an entry per-VF as infrastructure for future
interaction with said VFs.

Signed-off-by: Yuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 366 insertions, 0 deletions

diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
new file mode 100644
index 000000000000..685e3fa7bc52
--- /dev/null
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -0,0 +1,366 @@
+/* QLogic qed NIC Driver
+ * Copyright (c) 2015 QLogic Corporation
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include "qed_hw.h"
+#include "qed_int.h"
+#include "qed_reg_addr.h"
+#include "qed_sriov.h"
+#include "qed_vf.h"
+
+bool qed_iov_is_valid_vfid(struct qed_hwfn *p_hwfn,
+			   int rel_vf_id, bool b_enabled_only)
+{
+	if (!p_hwfn->pf_iov_info) {
+		DP_NOTICE(p_hwfn->cdev, "No iov info\n");
+		return false;
+	}
+
+	if ((rel_vf_id >= p_hwfn->cdev->p_iov_info->total_vfs) ||
+	    (rel_vf_id < 0))
+		return false;
+
+	if ((!p_hwfn->pf_iov_info->vfs_array[rel_vf_id].b_init) &&
+	    b_enabled_only)
+		return false;
+
+	return true;
+}
+
+static int qed_iov_pci_cfg_info(struct qed_dev *cdev)
+{
+	struct qed_hw_sriov_info *iov = cdev->p_iov_info;
+	int pos = iov->pos;
+
+	DP_VERBOSE(cdev, QED_MSG_IOV, "sriov ext pos %d\n", pos);
+	pci_read_config_word(cdev->pdev, pos + PCI_SRIOV_CTRL, &iov->ctrl);
+
+	pci_read_config_word(cdev->pdev,
+			     pos + PCI_SRIOV_TOTAL_VF, &iov->total_vfs);
+	pci_read_config_word(cdev->pdev,
+			     pos + PCI_SRIOV_INITIAL_VF, &iov->initial_vfs);
+
+	pci_read_config_word(cdev->pdev, pos + PCI_SRIOV_NUM_VF, &iov->num_vfs);
+	if (iov->num_vfs) {
+		DP_VERBOSE(cdev,
+			   QED_MSG_IOV,
+			   "Number of VFs are already set to non-zero value. Ignoring PCI configuration value\n");
+		iov->num_vfs = 0;
+	}
+
+	pci_read_config_word(cdev->pdev,
+			     pos + PCI_SRIOV_VF_OFFSET, &iov->offset);
+
+	pci_read_config_word(cdev->pdev,
+			     pos + PCI_SRIOV_VF_STRIDE, &iov->stride);
+
+	pci_read_config_word(cdev->pdev,
+			     pos + PCI_SRIOV_VF_DID, &iov->vf_device_id);
+
+	pci_read_config_dword(cdev->pdev,
+			      pos + PCI_SRIOV_SUP_PGSIZE, &iov->pgsz);
+
+	pci_read_config_dword(cdev->pdev, pos + PCI_SRIOV_CAP, &iov->cap);
+
+	pci_read_config_byte(cdev->pdev, pos + PCI_SRIOV_FUNC_LINK, &iov->link);
+
+	DP_VERBOSE(cdev,
+		   QED_MSG_IOV,
+		   "IOV info: nres %d, cap 0x%x, ctrl 0x%x, total %d, initial %d, num vfs %d, offset %d, stride %d, page size 0x%x\n",
+		   iov->nres,
+		   iov->cap,
+		   iov->ctrl,
+		   iov->total_vfs,
+		   iov->initial_vfs,
+		   iov->nr_virtfn, iov->offset, iov->stride, iov->pgsz);
+
+	/* Some sanity checks */
+	if (iov->num_vfs > NUM_OF_VFS(cdev) ||
+	    iov->total_vfs > NUM_OF_VFS(cdev)) {
+		/* This can happen only due to a bug. In this case we set
+		 * num_vfs to zero to avoid memory corruption in the code that
+		 * assumes max number of vfs
+		 */
+		DP_NOTICE(cdev,
+			  "IOV: Unexpected number of vfs set: %d setting num_vf to zero\n",
+			  iov->num_vfs);
+
+		iov->num_vfs = 0;
+		iov->total_vfs = 0;
+	}
+
+	return 0;
+}
+
+static void qed_iov_clear_vf_igu_blocks(struct qed_hwfn *p_hwfn,
+					struct qed_ptt *p_ptt)
+{
+	struct qed_igu_block *p_sb;
+	u16 sb_id;
+	u32 val;
+
+	if (!p_hwfn->hw_info.p_igu_info) {
+		DP_ERR(p_hwfn,
+		       "qed_iov_clear_vf_igu_blocks IGU Info not initialized\n");
+		return;
+	}
+
+	for (sb_id = 0; sb_id < QED_MAPPING_MEMORY_SIZE(p_hwfn->cdev);
+	     sb_id++) {
+		p_sb = &p_hwfn->hw_info.p_igu_info->igu_map.igu_blocks[sb_id];
+		if ((p_sb->status & QED_IGU_STATUS_FREE) &&
+		    !(p_sb->status & QED_IGU_STATUS_PF)) {
+			val = qed_rd(p_hwfn, p_ptt,
+				     IGU_REG_MAPPING_MEMORY + sb_id * 4);
+			SET_FIELD(val, IGU_MAPPING_LINE_VALID, 0);
+			qed_wr(p_hwfn, p_ptt,
+			       IGU_REG_MAPPING_MEMORY + 4 * sb_id, val);
+		}
+	}
+}
+
+static void qed_iov_setup_vfdb(struct qed_hwfn *p_hwfn)
+{
+	struct qed_hw_sriov_info *p_iov = p_hwfn->cdev->p_iov_info;
+	struct qed_pf_iov *p_iov_info = p_hwfn->pf_iov_info;
+	struct qed_bulletin_content *p_bulletin_virt;
+	dma_addr_t req_p, rply_p, bulletin_p;
+	union pfvf_tlvs *p_reply_virt_addr;
+	union vfpf_tlvs *p_req_virt_addr;
+	u8 idx = 0;
+
+	memset(p_iov_info->vfs_array, 0, sizeof(p_iov_info->vfs_array));
+
+	p_req_virt_addr = p_iov_info->mbx_msg_virt_addr;
+	req_p = p_iov_info->mbx_msg_phys_addr;
+	p_reply_virt_addr = p_iov_info->mbx_reply_virt_addr;
+	rply_p = p_iov_info->mbx_reply_phys_addr;
+	p_bulletin_virt = p_iov_info->p_bulletins;
+	bulletin_p = p_iov_info->bulletins_phys;
+	if (!p_req_virt_addr || !p_reply_virt_addr || !p_bulletin_virt) {
+		DP_ERR(p_hwfn,
+		       "qed_iov_setup_vfdb called without allocating mem first\n");
+		return;
+	}
+
+	for (idx = 0; idx < p_iov->total_vfs; idx++) {
+		struct qed_vf_info *vf = &p_iov_info->vfs_array[idx];
+		u32 concrete;
+
+		vf->vf_mbx.req_virt = p_req_virt_addr + idx;
+		vf->vf_mbx.req_phys = req_p + idx * sizeof(union vfpf_tlvs);
+		vf->vf_mbx.reply_virt = p_reply_virt_addr + idx;
+		vf->vf_mbx.reply_phys = rply_p + idx * sizeof(union pfvf_tlvs);
+
+		vf->state = VF_STOPPED;
+		vf->b_init = false;
+
+		vf->bulletin.phys = idx *
+				    sizeof(struct qed_bulletin_content) +
+				    bulletin_p;
+		vf->bulletin.p_virt = p_bulletin_virt + idx;
+		vf->bulletin.size = sizeof(struct qed_bulletin_content);
+
+		vf->relative_vf_id = idx;
+		vf->abs_vf_id = idx + p_iov->first_vf_in_pf;
+		concrete = qed_vfid_to_concrete(p_hwfn, vf->abs_vf_id);
+		vf->concrete_fid = concrete;
+		vf->opaque_fid = (p_hwfn->hw_info.opaque_fid & 0xff) |
+				 (vf->abs_vf_id << 8);
+		vf->vport_id = idx + 1;
+	}
+}
+
+static int qed_iov_allocate_vfdb(struct qed_hwfn *p_hwfn)
+{
+	struct qed_pf_iov *p_iov_info = p_hwfn->pf_iov_info;
+	void **p_v_addr;
+	u16 num_vfs = 0;
+
+	num_vfs = p_hwfn->cdev->p_iov_info->total_vfs;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+		   "qed_iov_allocate_vfdb for %d VFs\n", num_vfs);
+
+	/* Allocate PF Mailbox buffer (per-VF) */
+	p_iov_info->mbx_msg_size = sizeof(union vfpf_tlvs) * num_vfs;
+	p_v_addr = &p_iov_info->mbx_msg_virt_addr;
+	*p_v_addr = dma_alloc_coherent(&p_hwfn->cdev->pdev->dev,
+				       p_iov_info->mbx_msg_size,
+				       &p_iov_info->mbx_msg_phys_addr,
+				       GFP_KERNEL);
+	if (!*p_v_addr)
+		return -ENOMEM;
+
+	/* Allocate PF Mailbox Reply buffer (per-VF) */
+	p_iov_info->mbx_reply_size = sizeof(union pfvf_tlvs) * num_vfs;
+	p_v_addr = &p_iov_info->mbx_reply_virt_addr;
+	*p_v_addr = dma_alloc_coherent(&p_hwfn->cdev->pdev->dev,
+				       p_iov_info->mbx_reply_size,
+				       &p_iov_info->mbx_reply_phys_addr,
+				       GFP_KERNEL);
+	if (!*p_v_addr)
+		return -ENOMEM;
+
+	p_iov_info->bulletins_size = sizeof(struct qed_bulletin_content) *
+				     num_vfs;
+	p_v_addr = &p_iov_info->p_bulletins;
+	*p_v_addr = dma_alloc_coherent(&p_hwfn->cdev->pdev->dev,
+				       p_iov_info->bulletins_size,
+				       &p_iov_info->bulletins_phys,
+				       GFP_KERNEL);
+	if (!*p_v_addr)
+		return -ENOMEM;
+
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_IOV,
+		   "PF's Requests mailbox [%p virt 0x%llx phys],  Response mailbox [%p virt 0x%llx phys] Bulletins [%p virt 0x%llx phys]\n",
+		   p_iov_info->mbx_msg_virt_addr,
+		   (u64) p_iov_info->mbx_msg_phys_addr,
+		   p_iov_info->mbx_reply_virt_addr,
+		   (u64) p_iov_info->mbx_reply_phys_addr,
+		   p_iov_info->p_bulletins, (u64) p_iov_info->bulletins_phys);
+
+	return 0;
+}
+
+static void qed_iov_free_vfdb(struct qed_hwfn *p_hwfn)
+{
+	struct qed_pf_iov *p_iov_info = p_hwfn->pf_iov_info;
+
+	if (p_hwfn->pf_iov_info->mbx_msg_virt_addr)
+		dma_free_coherent(&p_hwfn->cdev->pdev->dev,
+				  p_iov_info->mbx_msg_size,
+				  p_iov_info->mbx_msg_virt_addr,
+				  p_iov_info->mbx_msg_phys_addr);
+
+	if (p_hwfn->pf_iov_info->mbx_reply_virt_addr)
+		dma_free_coherent(&p_hwfn->cdev->pdev->dev,
+				  p_iov_info->mbx_reply_size,
+				  p_iov_info->mbx_reply_virt_addr,
+				  p_iov_info->mbx_reply_phys_addr);
+
+	if (p_iov_info->p_bulletins)
+		dma_free_coherent(&p_hwfn->cdev->pdev->dev,
+				  p_iov_info->bulletins_size,
+				  p_iov_info->p_bulletins,
+				  p_iov_info->bulletins_phys);
+}
+
+int qed_iov_alloc(struct qed_hwfn *p_hwfn)
+{
+	struct qed_pf_iov *p_sriov;
+
+	if (!IS_PF_SRIOV(p_hwfn)) {
+		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+			   "No SR-IOV - no need for IOV db\n");
+		return 0;
+	}
+
+	p_sriov = kzalloc(sizeof(*p_sriov), GFP_KERNEL);
+	if (!p_sriov) {
+		DP_NOTICE(p_hwfn, "Failed to allocate `struct qed_sriov'\n");
+		return -ENOMEM;
+	}
+
+	p_hwfn->pf_iov_info = p_sriov;
+
+	return qed_iov_allocate_vfdb(p_hwfn);
+}
+
+void qed_iov_setup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	if (!IS_PF_SRIOV(p_hwfn) || !IS_PF_SRIOV_ALLOC(p_hwfn))
+		return;
+
+	qed_iov_setup_vfdb(p_hwfn);
+	qed_iov_clear_vf_igu_blocks(p_hwfn, p_ptt);
+}
+
+void qed_iov_free(struct qed_hwfn *p_hwfn)
+{
+	if (IS_PF_SRIOV_ALLOC(p_hwfn)) {
+		qed_iov_free_vfdb(p_hwfn);
+		kfree(p_hwfn->pf_iov_info);
+	}
+}
+
+void qed_iov_free_hw_info(struct qed_dev *cdev)
+{
+	kfree(cdev->p_iov_info);
+	cdev->p_iov_info = NULL;
+}
+
+int qed_iov_hw_info(struct qed_hwfn *p_hwfn)
+{
+	struct qed_dev *cdev = p_hwfn->cdev;
+	int pos;
+	int rc;
+
+	/* Learn the PCI configuration */
+	pos = pci_find_ext_capability(p_hwfn->cdev->pdev,
+				      PCI_EXT_CAP_ID_SRIOV);
+	if (!pos) {
+		DP_VERBOSE(p_hwfn, QED_MSG_IOV, "No PCIe IOV support\n");
+		return 0;
+	}
+
+	/* Allocate a new struct for IOV information */
+	cdev->p_iov_info = kzalloc(sizeof(*cdev->p_iov_info), GFP_KERNEL);
+	if (!cdev->p_iov_info) {
+		DP_NOTICE(p_hwfn, "Can't support IOV due to lack of memory\n");
+		return -ENOMEM;
+	}
+	cdev->p_iov_info->pos = pos;
+
+	rc = qed_iov_pci_cfg_info(cdev);
+	if (rc)
+		return rc;
+
+	/* We want PF IOV to be synonemous with the existance of p_iov_info;
+	 * In case the capability is published but there are no VFs, simply
+	 * de-allocate the struct.
+	 */
+	if (!cdev->p_iov_info->total_vfs) {
+		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+			   "IOV capabilities, but no VFs are published\n");
+		kfree(cdev->p_iov_info);
+		cdev->p_iov_info = NULL;
+		return 0;
+	}
+
+	/* Calculate the first VF index - this is a bit tricky; Basically,
+	 * VFs start at offset 16 relative to PF0, and 2nd engine VFs begin
+	 * after the first engine's VFs.
+	 */
+	cdev->p_iov_info->first_vf_in_pf = p_hwfn->cdev->p_iov_info->offset +
+					   p_hwfn->abs_pf_id - 16;
+	if (QED_PATH_ID(p_hwfn))
+		cdev->p_iov_info->first_vf_in_pf -= MAX_NUM_VFS_BB;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+		   "First VF in hwfn 0x%08x\n",
+		   cdev->p_iov_info->first_vf_in_pf);
+
+	return 0;
+}
+
+u16 qed_iov_get_next_active_vf(struct qed_hwfn *p_hwfn, u16 rel_vf_id)
+{
+	struct qed_hw_sriov_info *p_iov = p_hwfn->cdev->p_iov_info;
+	u16 i;
+
+	if (!p_iov)
+		goto out;
+
+	for (i = rel_vf_id; i < p_iov->total_vfs; i++)
+		if (qed_iov_is_valid_vfid(p_hwfn, rel_vf_id, true))
+			return i;
+
+out:
+	return MAX_NUM_VFS;
+}