if (!res->flags || !res->parent)
continue;
- if (!pnv_pci_is_mem_pref_64(res->flags))
- continue;
-
/*
* The actual IOV BAR range is determined by the start address
* and the actual size for num_vfs VFs BAR. This check is to
if (!res->flags || !res->parent)
continue;
- if (!pnv_pci_is_mem_pref_64(res->flags))
- continue;
-
size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES);
res2 = *res;
res->start += size * offset;
}
#ifdef CONFIG_PCI_IOV
-static int pnv_pci_vf_release_m64(struct pci_dev *pdev)
+static int pnv_pci_vf_release_m64(struct pci_dev *pdev, u16 num_vfs)
{
struct pci_bus *bus;
struct pci_controller *hose;
struct pnv_phb *phb;
struct pci_dn *pdn;
int i, j;
+ int m64_bars;
bus = pdev->bus;
hose = pci_bus_to_host(bus);
phb = hose->private_data;
pdn = pci_get_pdn(pdev);
+ if (pdn->m64_single_mode)
+ m64_bars = num_vfs;
+ else
+ m64_bars = 1;
+
for (i = 0; i < PCI_SRIOV_NUM_BARS; i++)
- for (j = 0; j < M64_PER_IOV; j++) {
- if (pdn->m64_wins[i][j] == IODA_INVALID_M64)
+ for (j = 0; j < m64_bars; j++) {
+ if (pdn->m64_map[j][i] == IODA_INVALID_M64)
continue;
opal_pci_phb_mmio_enable(phb->opal_id,
- OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 0);
- clear_bit(pdn->m64_wins[i][j], &phb->ioda.m64_bar_alloc);
- pdn->m64_wins[i][j] = IODA_INVALID_M64;
+ OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 0);
+ clear_bit(pdn->m64_map[j][i], &phb->ioda.m64_bar_alloc);
+ pdn->m64_map[j][i] = IODA_INVALID_M64;
}
+ kfree(pdn->m64_map);
return 0;
}
int total_vfs;
resource_size_t size, start;
int pe_num;
- int vf_groups;
- int vf_per_group;
+ int m64_bars;
bus = pdev->bus;
hose = pci_bus_to_host(bus);
pdn = pci_get_pdn(pdev);
total_vfs = pci_sriov_get_totalvfs(pdev);
- /* Initialize the m64_wins to IODA_INVALID_M64 */
- for (i = 0; i < PCI_SRIOV_NUM_BARS; i++)
- for (j = 0; j < M64_PER_IOV; j++)
- pdn->m64_wins[i][j] = IODA_INVALID_M64;
+ if (pdn->m64_single_mode)
+ m64_bars = num_vfs;
+ else
+ m64_bars = 1;
+
+ pdn->m64_map = kmalloc(sizeof(*pdn->m64_map) * m64_bars, GFP_KERNEL);
+ if (!pdn->m64_map)
+ return -ENOMEM;
+ /* Initialize the m64_map to IODA_INVALID_M64 */
+ for (i = 0; i < m64_bars ; i++)
+ for (j = 0; j < PCI_SRIOV_NUM_BARS; j++)
+ pdn->m64_map[i][j] = IODA_INVALID_M64;
- if (pdn->m64_per_iov == M64_PER_IOV) {
- vf_groups = (num_vfs <= M64_PER_IOV) ? num_vfs: M64_PER_IOV;
- vf_per_group = (num_vfs <= M64_PER_IOV)? 1:
- roundup_pow_of_two(num_vfs) / pdn->m64_per_iov;
- } else {
- vf_groups = 1;
- vf_per_group = 1;
- }
for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
res = &pdev->resource[i + PCI_IOV_RESOURCES];
if (!res->flags || !res->parent)
continue;
- if (!pnv_pci_is_mem_pref_64(res->flags))
- continue;
-
- for (j = 0; j < vf_groups; j++) {
+ for (j = 0; j < m64_bars; j++) {
do {
win = find_next_zero_bit(&phb->ioda.m64_bar_alloc,
phb->ioda.m64_bar_idx + 1, 0);
goto m64_failed;
} while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc));
- pdn->m64_wins[i][j] = win;
+ pdn->m64_map[j][i] = win;
- if (pdn->m64_per_iov == M64_PER_IOV) {
+ if (pdn->m64_single_mode) {
size = pci_iov_resource_size(pdev,
PCI_IOV_RESOURCES + i);
- size = size * vf_per_group;
start = res->start + size * j;
} else {
size = resource_size(res);
}
/* Map the M64 here */
- if (pdn->m64_per_iov == M64_PER_IOV) {
- pe_num = pdn->offset + j;
+ if (pdn->m64_single_mode) {
+ pe_num = pdn->pe_num_map[j];
rc = opal_pci_map_pe_mmio_window(phb->opal_id,
pe_num, OPAL_M64_WINDOW_TYPE,
- pdn->m64_wins[i][j], 0);
+ pdn->m64_map[j][i], 0);
}
rc = opal_pci_set_phb_mem_window(phb->opal_id,
OPAL_M64_WINDOW_TYPE,
- pdn->m64_wins[i][j],
+ pdn->m64_map[j][i],
start,
0, /* unused */
size);
goto m64_failed;
}
- if (pdn->m64_per_iov == M64_PER_IOV)
+ if (pdn->m64_single_mode)
rc = opal_pci_phb_mmio_enable(phb->opal_id,
- OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 2);
+ OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 2);
else
rc = opal_pci_phb_mmio_enable(phb->opal_id,
- OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 1);
+ OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 1);
if (rc != OPAL_SUCCESS) {
dev_err(&pdev->dev, "Failed to enable M64 window #%d: %llx\n",
return 0;
m64_failed:
- pnv_pci_vf_release_m64(pdev);
+ pnv_pci_vf_release_m64(pdev, num_vfs);
return -EBUSY;
}
iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
}
-static void pnv_ioda_release_vf_PE(struct pci_dev *pdev, u16 num_vfs)
+static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
{
struct pci_bus *bus;
struct pci_controller *hose;
struct pnv_phb *phb;
struct pnv_ioda_pe *pe, *pe_n;
struct pci_dn *pdn;
- u16 vf_index;
- int64_t rc;
bus = pdev->bus;
hose = pci_bus_to_host(bus);
if (!pdev->is_physfn)
return;
- if (pdn->m64_per_iov == M64_PER_IOV && num_vfs > M64_PER_IOV) {
- int vf_group;
- int vf_per_group;
- int vf_index1;
-
- vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov;
-
- for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++)
- for (vf_index = vf_group * vf_per_group;
- vf_index < (vf_group + 1) * vf_per_group &&
- vf_index < num_vfs;
- vf_index++)
- for (vf_index1 = vf_group * vf_per_group;
- vf_index1 < (vf_group + 1) * vf_per_group &&
- vf_index1 < num_vfs;
- vf_index1++){
-
- rc = opal_pci_set_peltv(phb->opal_id,
- pdn->offset + vf_index,
- pdn->offset + vf_index1,
- OPAL_REMOVE_PE_FROM_DOMAIN);
-
- if (rc)
- dev_warn(&pdev->dev, "%s: Failed to unlink same group PE#%d(%lld)\n",
- __func__,
- pdn->offset + vf_index1, rc);
- }
- }
-
list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) {
if (pe->parent_dev != pdev)
continue;
struct pnv_phb *phb;
struct pci_dn *pdn;
struct pci_sriov *iov;
- u16 num_vfs;
+ u16 num_vfs, i;
bus = pdev->bus;
hose = pci_bus_to_host(bus);
num_vfs = pdn->num_vfs;
/* Release VF PEs */
- pnv_ioda_release_vf_PE(pdev, num_vfs);
+ pnv_ioda_release_vf_PE(pdev);
if (phb->type == PNV_PHB_IODA2) {
- if (pdn->m64_per_iov == 1)
- pnv_pci_vf_resource_shift(pdev, -pdn->offset);
+ if (!pdn->m64_single_mode)
+ pnv_pci_vf_resource_shift(pdev, -*pdn->pe_num_map);
/* Release M64 windows */
- pnv_pci_vf_release_m64(pdev);
+ pnv_pci_vf_release_m64(pdev, num_vfs);
/* Release PE numbers */
- bitmap_clear(phb->ioda.pe_alloc, pdn->offset, num_vfs);
- pdn->offset = 0;
+ if (pdn->m64_single_mode) {
+ for (i = 0; i < num_vfs; i++) {
+ if (pdn->pe_num_map[i] != IODA_INVALID_PE)
+ pnv_ioda_free_pe(phb, pdn->pe_num_map[i]);
+ }
+ } else
+ bitmap_clear(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs);
+ /* Releasing pe_num_map */
+ kfree(pdn->pe_num_map);
}
}
int pe_num;
u16 vf_index;
struct pci_dn *pdn;
- int64_t rc;
bus = pdev->bus;
hose = pci_bus_to_host(bus);
/* Reserve PE for each VF */
for (vf_index = 0; vf_index < num_vfs; vf_index++) {
- pe_num = pdn->offset + vf_index;
+ if (pdn->m64_single_mode)
+ pe_num = pdn->pe_num_map[vf_index];
+ else
+ pe_num = *pdn->pe_num_map + vf_index;
pe = &phb->ioda.pe_array[pe_num];
pe->pe_number = pe_num;
pnv_pci_ioda2_setup_dma_pe(phb, pe);
}
-
- if (pdn->m64_per_iov == M64_PER_IOV && num_vfs > M64_PER_IOV) {
- int vf_group;
- int vf_per_group;
- int vf_index1;
-
- vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov;
-
- for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++) {
- for (vf_index = vf_group * vf_per_group;
- vf_index < (vf_group + 1) * vf_per_group &&
- vf_index < num_vfs;
- vf_index++) {
- for (vf_index1 = vf_group * vf_per_group;
- vf_index1 < (vf_group + 1) * vf_per_group &&
- vf_index1 < num_vfs;
- vf_index1++) {
-
- rc = opal_pci_set_peltv(phb->opal_id,
- pdn->offset + vf_index,
- pdn->offset + vf_index1,
- OPAL_ADD_PE_TO_DOMAIN);
-
- if (rc)
- dev_warn(&pdev->dev, "%s: Failed to link same group PE#%d(%lld)\n",
- __func__,
- pdn->offset + vf_index1, rc);
- }
- }
- }
- }
}
int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
struct pnv_phb *phb;
struct pci_dn *pdn;
int ret;
+ u16 i;
bus = pdev->bus;
hose = pci_bus_to_host(bus);
pdn = pci_get_pdn(pdev);
if (phb->type == PNV_PHB_IODA2) {
+ if (!pdn->vfs_expanded) {
+ dev_info(&pdev->dev, "don't support this SRIOV device"
+ " with non 64bit-prefetchable IOV BAR\n");
+ return -ENOSPC;
+ }
+
+ /*
+ * When M64 BARs functions in Single PE mode, the number of VFs
+ * could be enabled must be less than the number of M64 BARs.
+ */
+ if (pdn->m64_single_mode && num_vfs > phb->ioda.m64_bar_idx) {
+ dev_info(&pdev->dev, "Not enough M64 BAR for VFs\n");
+ return -EBUSY;
+ }
+
+ /* Allocating pe_num_map */
+ if (pdn->m64_single_mode)
+ pdn->pe_num_map = kmalloc(sizeof(*pdn->pe_num_map) * num_vfs,
+ GFP_KERNEL);
+ else
+ pdn->pe_num_map = kmalloc(sizeof(*pdn->pe_num_map), GFP_KERNEL);
+
+ if (!pdn->pe_num_map)
+ return -ENOMEM;
+
+ if (pdn->m64_single_mode)
+ for (i = 0; i < num_vfs; i++)
+ pdn->pe_num_map[i] = IODA_INVALID_PE;
+
/* Calculate available PE for required VFs */
- mutex_lock(&phb->ioda.pe_alloc_mutex);
- pdn->offset = bitmap_find_next_zero_area(
- phb->ioda.pe_alloc, phb->ioda.total_pe,
- 0, num_vfs, 0);
- if (pdn->offset >= phb->ioda.total_pe) {
+ if (pdn->m64_single_mode) {
+ for (i = 0; i < num_vfs; i++) {
+ pdn->pe_num_map[i] = pnv_ioda_alloc_pe(phb);
+ if (pdn->pe_num_map[i] == IODA_INVALID_PE) {
+ ret = -EBUSY;
+ goto m64_failed;
+ }
+ }
+ } else {
+ mutex_lock(&phb->ioda.pe_alloc_mutex);
+ *pdn->pe_num_map = bitmap_find_next_zero_area(
+ phb->ioda.pe_alloc, phb->ioda.total_pe,
+ 0, num_vfs, 0);
+ if (*pdn->pe_num_map >= phb->ioda.total_pe) {
+ mutex_unlock(&phb->ioda.pe_alloc_mutex);
+ dev_info(&pdev->dev, "Failed to enable VF%d\n", num_vfs);
+ kfree(pdn->pe_num_map);
+ return -EBUSY;
+ }
+ bitmap_set(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs);
mutex_unlock(&phb->ioda.pe_alloc_mutex);
- dev_info(&pdev->dev, "Failed to enable VF%d\n", num_vfs);
- pdn->offset = 0;
- return -EBUSY;
}
- bitmap_set(phb->ioda.pe_alloc, pdn->offset, num_vfs);
pdn->num_vfs = num_vfs;
- mutex_unlock(&phb->ioda.pe_alloc_mutex);
/* Assign M64 window accordingly */
ret = pnv_pci_vf_assign_m64(pdev, num_vfs);
* the IOV BAR according to the PE# allocated to the VFs.
* Otherwise, the PE# for the VF will conflict with others.
*/
- if (pdn->m64_per_iov == 1) {
- ret = pnv_pci_vf_resource_shift(pdev, pdn->offset);
+ if (!pdn->m64_single_mode) {
+ ret = pnv_pci_vf_resource_shift(pdev, *pdn->pe_num_map);
if (ret)
goto m64_failed;
}
return 0;
m64_failed:
- bitmap_clear(phb->ioda.pe_alloc, pdn->offset, num_vfs);
- pdn->offset = 0;
+ if (pdn->m64_single_mode) {
+ for (i = 0; i < num_vfs; i++) {
+ if (pdn->pe_num_map[i] != IODA_INVALID_PE)
+ pnv_ioda_free_pe(phb, pdn->pe_num_map[i]);
+ }
+ } else
+ bitmap_clear(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs);
+
+ /* Releasing pe_num_map */
+ kfree(pdn->pe_num_map);
return ret;
}
/* Allocate PCI data */
add_dev_pci_data(pdev);
- pnv_pci_sriov_enable(pdev, num_vfs);
- return 0;
+ return pnv_pci_sriov_enable(pdev, num_vfs);
}
#endif /* CONFIG_PCI_IOV */
#ifdef CONFIG_PCI_IOV
static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
{
- struct pci_controller *hose;
- struct pnv_phb *phb;
+ struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+ struct pnv_phb *phb = hose->private_data;
+ const resource_size_t gate = phb->ioda.m64_segsize >> 2;
struct resource *res;
int i;
- resource_size_t size;
+ resource_size_t size, total_vf_bar_sz;
struct pci_dn *pdn;
int mul, total_vfs;
if (!pdev->is_physfn || pdev->is_added)
return;
- hose = pci_bus_to_host(pdev->bus);
- phb = hose->private_data;
-
pdn = pci_get_pdn(pdev);
pdn->vfs_expanded = 0;
+ pdn->m64_single_mode = false;
total_vfs = pci_sriov_get_totalvfs(pdev);
- pdn->m64_per_iov = 1;
mul = phb->ioda.total_pe;
+ total_vf_bar_sz = 0;
for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
res = &pdev->resource[i + PCI_IOV_RESOURCES];
if (!res->flags || res->parent)
continue;
if (!pnv_pci_is_mem_pref_64(res->flags)) {
- dev_warn(&pdev->dev, " non M64 VF BAR%d: %pR\n",
+ dev_warn(&pdev->dev, "Don't support SR-IOV with"
+ " non M64 VF BAR%d: %pR. \n",
i, res);
- continue;
+ goto truncate_iov;
}
- size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES);
+ total_vf_bar_sz += pci_iov_resource_size(pdev,
+ i + PCI_IOV_RESOURCES);
- /* bigger than 64M */
- if (size > (1 << 26)) {
- dev_info(&pdev->dev, "PowerNV: VF BAR%d: %pR IOV size is bigger than 64M, roundup power2\n",
- i, res);
- pdn->m64_per_iov = M64_PER_IOV;
+ /*
+ * If bigger than quarter of M64 segment size, just round up
+ * power of two.
+ *
+ * Generally, one M64 BAR maps one IOV BAR. To avoid conflict
+ * with other devices, IOV BAR size is expanded to be
+ * (total_pe * VF_BAR_size). When VF_BAR_size is half of M64
+ * segment size , the expanded size would equal to half of the
+ * whole M64 space size, which will exhaust the M64 Space and
+ * limit the system flexibility. This is a design decision to
+ * set the boundary to quarter of the M64 segment size.
+ */
+ if (total_vf_bar_sz > gate) {
mul = roundup_pow_of_two(total_vfs);
+ dev_info(&pdev->dev,
+ "VF BAR Total IOV size %llx > %llx, roundup to %d VFs\n",
+ total_vf_bar_sz, gate, mul);
+ pdn->m64_single_mode = true;
break;
}
}
res = &pdev->resource[i + PCI_IOV_RESOURCES];
if (!res->flags || res->parent)
continue;
- if (!pnv_pci_is_mem_pref_64(res->flags)) {
- dev_warn(&pdev->dev, "Skipping expanding VF BAR%d: %pR\n",
- i, res);
- continue;
- }
- dev_dbg(&pdev->dev, " Fixing VF BAR%d: %pR to\n", i, res);
size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES);
+ /*
+ * On PHB3, the minimum size alignment of M64 BAR in single
+ * mode is 32MB.
+ */
+ if (pdn->m64_single_mode && (size < SZ_32M))
+ goto truncate_iov;
+ dev_dbg(&pdev->dev, " Fixing VF BAR%d: %pR to\n", i, res);
res->end = res->start + size * mul - 1;
dev_dbg(&pdev->dev, " %pR\n", res);
dev_info(&pdev->dev, "VF BAR%d: %pR (expanded to %d VFs for PE alignment)",
i, res, mul);
}
pdn->vfs_expanded = mul;
+
+ return;
+
+truncate_iov:
+ /* To save MMIO space, IOV BAR is truncated. */
+ for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+ res = &pdev->resource[i + PCI_IOV_RESOURCES];
+ res->flags = 0;
+ res->end = res->start - 1;
+ }
}
#endif /* CONFIG_PCI_IOV */
static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev,
int resno)
{
+ struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+ struct pnv_phb *phb = hose->private_data;
struct pci_dn *pdn = pci_get_pdn(pdev);
- resource_size_t align, iov_align;
-
- iov_align = resource_size(&pdev->resource[resno]);
- if (iov_align)
- return iov_align;
+ resource_size_t align;
+ /*
+ * On PowerNV platform, IOV BAR is mapped by M64 BAR to enable the
+ * SR-IOV. While from hardware perspective, the range mapped by M64
+ * BAR should be size aligned.
+ *
+ * When IOV BAR is mapped with M64 BAR in Single PE mode, the extra
+ * powernv-specific hardware restriction is gone. But if just use the
+ * VF BAR size as the alignment, PF BAR / VF BAR may be allocated with
+ * in one segment of M64 #15, which introduces the PE conflict between
+ * PF and VF. Based on this, the minimum alignment of an IOV BAR is
+ * m64_segsize.
+ *
+ * This function returns the total IOV BAR size if M64 BAR is in
+ * Shared PE mode or just VF BAR size if not.
+ * If the M64 BAR is in Single PE mode, return the VF BAR size or
+ * M64 segment size if IOV BAR size is less.
+ */
align = pci_iov_resource_size(pdev, resno);
- if (pdn->vfs_expanded)
- return pdn->vfs_expanded * align;
+ if (!pdn->vfs_expanded)
+ return align;
+ if (pdn->m64_single_mode)
+ return max(align, (resource_size_t)phb->ioda.m64_segsize);
- return align;
+ return pdn->vfs_expanded * align;
}
#endif /* CONFIG_PCI_IOV */
static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
.dma_dev_setup = pnv_pci_dma_dev_setup,
+ .dma_bus_setup = pnv_pci_dma_bus_setup,
#ifdef CONFIG_PCI_MSI
.setup_msi_irqs = pnv_setup_msi_irqs,
.teardown_msi_irqs = pnv_teardown_msi_irqs,
projects / cascardo / linux.git / blobdiff