#include "powernv.h"
#include "pci.h"
-/* 256M DMA window, 4K TCE pages, 8 bytes TCE */
-#define TCE32_TABLE_SIZE ((0x10000000 / 0x1000) * 8)
+#define PNV_IODA1_M64_NUM 16 /* Number of M64 BARs */
+#define PNV_IODA1_M64_SEGS 8 /* Segments per M64 BAR */
+#define PNV_IODA1_DMA32_SEGSIZE 0x10000000
#define POWERNV_IOMMU_DEFAULT_LEVELS 1
#define POWERNV_IOMMU_MAX_LEVELS 5
(IORESOURCE_MEM_64 | IORESOURCE_PREFETCH));
}
+static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no)
+{
+ phb->ioda.pe_array[pe_no].phb = phb;
+ phb->ioda.pe_array[pe_no].pe_number = pe_no;
+
+ return &phb->ioda.pe_array[pe_no];
+}
+
static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no)
{
- if (!(pe_no >= 0 && pe_no < phb->ioda.total_pe)) {
+ if (!(pe_no >= 0 && pe_no < phb->ioda.total_pe_num)) {
pr_warn("%s: Invalid PE %d on PHB#%x\n",
__func__, pe_no, phb->hose->global_number);
return;
pr_debug("%s: PE %d was reserved on PHB#%x\n",
__func__, pe_no, phb->hose->global_number);
- phb->ioda.pe_array[pe_no].phb = phb;
- phb->ioda.pe_array[pe_no].pe_number = pe_no;
+ pnv_ioda_init_pe(phb, pe_no);
}
-static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
+static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb)
{
unsigned long pe;
do {
pe = find_next_zero_bit(phb->ioda.pe_alloc,
- phb->ioda.total_pe, 0);
- if (pe >= phb->ioda.total_pe)
- return IODA_INVALID_PE;
+ phb->ioda.total_pe_num, 0);
+ if (pe >= phb->ioda.total_pe_num)
+ return NULL;
} while(test_and_set_bit(pe, phb->ioda.pe_alloc));
- phb->ioda.pe_array[pe].phb = phb;
- phb->ioda.pe_array[pe].pe_number = pe;
- return pe;
+ return pnv_ioda_init_pe(phb, pe);
}
-static void pnv_ioda_free_pe(struct pnv_phb *phb, int pe)
+static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
{
- WARN_ON(phb->ioda.pe_array[pe].pdev);
+ struct pnv_phb *phb = pe->phb;
+
+ WARN_ON(pe->pdev);
- memset(&phb->ioda.pe_array[pe], 0, sizeof(struct pnv_ioda_pe));
- clear_bit(pe, phb->ioda.pe_alloc);
+ memset(pe, 0, sizeof(struct pnv_ioda_pe));
+ clear_bit(pe->pe_number, phb->ioda.pe_alloc);
}
/* The default M64 BAR is shared by all PEs */
* expected to be 0 or last one of PE capabicity.
*/
r = &phb->hose->mem_resources[1];
- if (phb->ioda.reserved_pe == 0)
+ if (phb->ioda.reserved_pe_idx == 0)
r->start += phb->ioda.m64_segsize;
- else if (phb->ioda.reserved_pe == (phb->ioda.total_pe - 1))
+ else if (phb->ioda.reserved_pe_idx == (phb->ioda.total_pe_num - 1))
r->end -= phb->ioda.m64_segsize;
else
pr_warn(" Cannot strip M64 segment for reserved PE#%d\n",
- phb->ioda.reserved_pe);
+ phb->ioda.reserved_pe_idx);
return 0;
return -EIO;
}
-static void pnv_ioda2_reserve_dev_m64_pe(struct pci_dev *pdev,
+static void pnv_ioda_reserve_dev_m64_pe(struct pci_dev *pdev,
unsigned long *pe_bitmap)
{
struct pci_controller *hose = pci_bus_to_host(pdev->bus);
}
}
-static void pnv_ioda2_reserve_m64_pe(struct pci_bus *bus,
- unsigned long *pe_bitmap,
- bool all)
+static int pnv_ioda1_init_m64(struct pnv_phb *phb)
+{
+ struct resource *r;
+ int index;
+
+ /*
+ * There are 16 M64 BARs, each of which has 8 segments. So
+ * there are as many M64 segments as the maximum number of
+ * PEs, which is 128.
+ */
+ for (index = 0; index < PNV_IODA1_M64_NUM; index++) {
+ unsigned long base, segsz = phb->ioda.m64_segsize;
+ int64_t rc;
+
+ base = phb->ioda.m64_base +
+ index * PNV_IODA1_M64_SEGS * segsz;
+ rc = opal_pci_set_phb_mem_window(phb->opal_id,
+ OPAL_M64_WINDOW_TYPE, index, base, 0,
+ PNV_IODA1_M64_SEGS * segsz);
+ if (rc != OPAL_SUCCESS) {
+ pr_warn(" Error %lld setting M64 PHB#%d-BAR#%d\n",
+ rc, phb->hose->global_number, index);
+ goto fail;
+ }
+
+ rc = opal_pci_phb_mmio_enable(phb->opal_id,
+ OPAL_M64_WINDOW_TYPE, index,
+ OPAL_ENABLE_M64_SPLIT);
+ if (rc != OPAL_SUCCESS) {
+ pr_warn(" Error %lld enabling M64 PHB#%d-BAR#%d\n",
+ rc, phb->hose->global_number, index);
+ goto fail;
+ }
+ }
+
+ /*
+ * Exclude the segment used by the reserved PE, which
+ * is expected to be 0 or last supported PE#.
+ */
+ r = &phb->hose->mem_resources[1];
+ if (phb->ioda.reserved_pe_idx == 0)
+ r->start += phb->ioda.m64_segsize;
+ else if (phb->ioda.reserved_pe_idx == (phb->ioda.total_pe_num - 1))
+ r->end -= phb->ioda.m64_segsize;
+ else
+ WARN(1, "Wrong reserved PE#%d on PHB#%d\n",
+ phb->ioda.reserved_pe_idx, phb->hose->global_number);
+
+ return 0;
+
+fail:
+ for ( ; index >= 0; index--)
+ opal_pci_phb_mmio_enable(phb->opal_id,
+ OPAL_M64_WINDOW_TYPE, index, OPAL_DISABLE_M64);
+
+ return -EIO;
+}
+
+static void pnv_ioda_reserve_m64_pe(struct pci_bus *bus,
+ unsigned long *pe_bitmap,
+ bool all)
{
struct pci_dev *pdev;
list_for_each_entry(pdev, &bus->devices, bus_list) {
- pnv_ioda2_reserve_dev_m64_pe(pdev, pe_bitmap);
+ pnv_ioda_reserve_dev_m64_pe(pdev, pe_bitmap);
if (all && pdev->subordinate)
- pnv_ioda2_reserve_m64_pe(pdev->subordinate,
- pe_bitmap, all);
+ pnv_ioda_reserve_m64_pe(pdev->subordinate,
+ pe_bitmap, all);
}
}
-static int pnv_ioda2_pick_m64_pe(struct pci_bus *bus, bool all)
+static struct pnv_ioda_pe *pnv_ioda_pick_m64_pe(struct pci_bus *bus, bool all)
{
struct pci_controller *hose = pci_bus_to_host(bus);
struct pnv_phb *phb = hose->private_data;
/* Root bus shouldn't use M64 */
if (pci_is_root_bus(bus))
- return IODA_INVALID_PE;
+ return NULL;
/* Allocate bitmap */
- size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long));
+ size = _ALIGN_UP(phb->ioda.total_pe_num / 8, sizeof(unsigned long));
pe_alloc = kzalloc(size, GFP_KERNEL);
if (!pe_alloc) {
pr_warn("%s: Out of memory !\n",
__func__);
- return IODA_INVALID_PE;
+ return NULL;
}
/* Figure out reserved PE numbers by the PE */
- pnv_ioda2_reserve_m64_pe(bus, pe_alloc, all);
+ pnv_ioda_reserve_m64_pe(bus, pe_alloc, all);
/*
* the current bus might not own M64 window and that's all
* contributed by its child buses. For the case, we needn't
* pick M64 dependent PE#.
*/
- if (bitmap_empty(pe_alloc, phb->ioda.total_pe)) {
+ if (bitmap_empty(pe_alloc, phb->ioda.total_pe_num)) {
kfree(pe_alloc);
- return IODA_INVALID_PE;
+ return NULL;
}
/*
*/
master_pe = NULL;
i = -1;
- while ((i = find_next_bit(pe_alloc, phb->ioda.total_pe, i + 1)) <
- phb->ioda.total_pe) {
+ while ((i = find_next_bit(pe_alloc, phb->ioda.total_pe_num, i + 1)) <
+ phb->ioda.total_pe_num) {
pe = &phb->ioda.pe_array[i];
+ phb->ioda.m64_segmap[pe->pe_number] = pe->pe_number;
if (!master_pe) {
pe->flags |= PNV_IODA_PE_MASTER;
INIT_LIST_HEAD(&pe->slaves);
pe->master = master_pe;
list_add_tail(&pe->list, &master_pe->slaves);
}
+
+ /*
+ * P7IOC supports M64DT, which helps mapping M64 segment
+ * to one particular PE#. However, PHB3 has fixed mapping
+ * between M64 segment and PE#. In order to have same logic
+ * for P7IOC and PHB3, we enforce fixed mapping between M64
+ * segment and PE# on P7IOC.
+ */
+ if (phb->type == PNV_PHB_IODA1) {
+ int64_t rc;
+
+ rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+ pe->pe_number, OPAL_M64_WINDOW_TYPE,
+ pe->pe_number / PNV_IODA1_M64_SEGS,
+ pe->pe_number % PNV_IODA1_M64_SEGS);
+ if (rc != OPAL_SUCCESS)
+ pr_warn("%s: Error %lld mapping M64 for PHB#%d-PE#%d\n",
+ __func__, rc, phb->hose->global_number,
+ pe->pe_number);
+ }
}
kfree(pe_alloc);
- return master_pe->pe_number;
+ return master_pe;
}
static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
const u32 *r;
u64 pci_addr;
- /* FIXME: Support M64 for P7IOC */
- if (phb->type != PNV_PHB_IODA2) {
+ if (phb->type != PNV_PHB_IODA1 && phb->type != PNV_PHB_IODA2) {
pr_info(" Not support M64 window\n");
return;
}
hose->mem_offset[1] = res->start - pci_addr;
phb->ioda.m64_size = resource_size(res);
- phb->ioda.m64_segsize = phb->ioda.m64_size / phb->ioda.total_pe;
+ phb->ioda.m64_segsize = phb->ioda.m64_size / phb->ioda.total_pe_num;
phb->ioda.m64_base = pci_addr;
pr_info(" MEM64 0x%016llx..0x%016llx -> 0x%016llx\n",
/* Use last M64 BAR to cover M64 window */
phb->ioda.m64_bar_idx = 15;
- phb->init_m64 = pnv_ioda2_init_m64;
- phb->reserve_m64_pe = pnv_ioda2_reserve_m64_pe;
- phb->pick_m64_pe = pnv_ioda2_pick_m64_pe;
+ if (phb->type == PNV_PHB_IODA1)
+ phb->init_m64 = pnv_ioda1_init_m64;
+ else
+ phb->init_m64 = pnv_ioda2_init_m64;
+ phb->reserve_m64_pe = pnv_ioda_reserve_m64_pe;
+ phb->pick_m64_pe = pnv_ioda_pick_m64_pe;
}
static void pnv_ioda_freeze_pe(struct pnv_phb *phb, int pe_no)
s64 rc;
/* Sanity check on PE number */
- if (pe_no < 0 || pe_no >= phb->ioda.total_pe)
+ if (pe_no < 0 || pe_no >= phb->ioda.total_pe_num)
return OPAL_EEH_STOPPED_PERM_UNAVAIL;
/*
return 0;
}
-static void pnv_ioda_link_pe_by_weight(struct pnv_phb *phb,
- struct pnv_ioda_pe *pe)
-{
- struct pnv_ioda_pe *lpe;
-
- list_for_each_entry(lpe, &phb->ioda.pe_dma_list, dma_link) {
- if (lpe->dma_weight < pe->dma_weight) {
- list_add_tail(&pe->dma_link, &lpe->dma_link);
- return;
- }
- }
- list_add_tail(&pe->dma_link, &phb->ioda.pe_dma_list);
-}
-
-static unsigned int pnv_ioda_dma_weight(struct pci_dev *dev)
-{
- /* This is quite simplistic. The "base" weight of a device
- * is 10. 0 means no DMA is to be accounted for it.
- */
-
- /* If it's a bridge, no DMA */
- if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL)
- return 0;
-
- /* Reduce the weight of slow USB controllers */
- if (dev->class == PCI_CLASS_SERIAL_USB_UHCI ||
- dev->class == PCI_CLASS_SERIAL_USB_OHCI ||
- dev->class == PCI_CLASS_SERIAL_USB_EHCI)
- return 3;
-
- /* Increase the weight of RAID (includes Obsidian) */
- if ((dev->class >> 8) == PCI_CLASS_STORAGE_RAID)
- return 15;
-
- /* Default */
- return 10;
-}
-
#ifdef CONFIG_PCI_IOV
static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset)
{
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;
struct pnv_phb *phb = hose->private_data;
struct pci_dn *pdn = pci_get_pdn(dev);
struct pnv_ioda_pe *pe;
- int pe_num;
if (!pdn) {
pr_err("%s: Device tree node not associated properly\n",
if (pdn->pe_number != IODA_INVALID_PE)
return NULL;
- pe_num = pnv_ioda_alloc_pe(phb);
- if (pe_num == IODA_INVALID_PE) {
+ pe = pnv_ioda_alloc_pe(phb);
+ if (!pe) {
pr_warning("%s: Not enough PE# available, disabling device\n",
pci_name(dev));
return NULL;
*
* At some point we want to remove the PDN completely anyways
*/
- pe = &phb->ioda.pe_array[pe_num];
pci_dev_get(dev);
pdn->pcidev = dev;
- pdn->pe_number = pe_num;
+ pdn->pe_number = pe->pe_number;
pe->flags = PNV_IODA_PE_DEV;
pe->pdev = dev;
pe->pbus = NULL;
- pe->tce32_seg = -1;
pe->mve_number = -1;
pe->rid = dev->bus->number << 8 | pdn->devfn;
if (pnv_ioda_configure_pe(phb, pe)) {
/* XXX What do we do here ? */
- if (pe_num)
- pnv_ioda_free_pe(phb, pe_num);
+ pnv_ioda_free_pe(pe);
pdn->pe_number = IODA_INVALID_PE;
pe->pdev = NULL;
pci_dev_put(dev);
return NULL;
}
- /* Assign a DMA weight to the device */
- pe->dma_weight = pnv_ioda_dma_weight(dev);
- if (pe->dma_weight != 0) {
- phb->ioda.dma_weight += pe->dma_weight;
- phb->ioda.dma_pe_count++;
- }
-
- /* Link the PE */
- pnv_ioda_link_pe_by_weight(phb, pe);
-
return pe;
}
}
pdn->pcidev = dev;
pdn->pe_number = pe->pe_number;
- pe->dma_weight += pnv_ioda_dma_weight(dev);
if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
pnv_ioda_setup_same_PE(dev->subordinate, pe);
}
* subordinate PCI devices and buses. The second type of PE is normally
* orgiriated by PCIe-to-PCI bridge or PLX switch downstream ports.
*/
-static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
+static struct pnv_ioda_pe *pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
{
struct pci_controller *hose = pci_bus_to_host(bus);
struct pnv_phb *phb = hose->private_data;
- struct pnv_ioda_pe *pe;
- int pe_num = IODA_INVALID_PE;
+ struct pnv_ioda_pe *pe = NULL;
/* Check if PE is determined by M64 */
if (phb->pick_m64_pe)
- pe_num = phb->pick_m64_pe(bus, all);
+ pe = phb->pick_m64_pe(bus, all);
/* The PE number isn't pinned by M64 */
- if (pe_num == IODA_INVALID_PE)
- pe_num = pnv_ioda_alloc_pe(phb);
+ if (!pe)
+ pe = pnv_ioda_alloc_pe(phb);
- if (pe_num == IODA_INVALID_PE) {
+ if (!pe) {
pr_warning("%s: Not enough PE# available for PCI bus %04x:%02x\n",
__func__, pci_domain_nr(bus), bus->number);
- return;
+ return NULL;
}
- pe = &phb->ioda.pe_array[pe_num];
pe->flags |= (all ? PNV_IODA_PE_BUS_ALL : PNV_IODA_PE_BUS);
pe->pbus = bus;
pe->pdev = NULL;
- pe->tce32_seg = -1;
pe->mve_number = -1;
pe->rid = bus->busn_res.start << 8;
- pe->dma_weight = 0;
if (all)
pe_info(pe, "Secondary bus %d..%d associated with PE#%d\n",
- bus->busn_res.start, bus->busn_res.end, pe_num);
+ bus->busn_res.start, bus->busn_res.end, pe->pe_number);
else
pe_info(pe, "Secondary bus %d associated with PE#%d\n",
- bus->busn_res.start, pe_num);
+ bus->busn_res.start, pe->pe_number);
if (pnv_ioda_configure_pe(phb, pe)) {
/* XXX What do we do here ? */
- if (pe_num)
- pnv_ioda_free_pe(phb, pe_num);
+ pnv_ioda_free_pe(pe);
pe->pbus = NULL;
- return;
+ return NULL;
}
/* Associate it with all child devices */
/* Put PE to the list */
list_add_tail(&pe->list, &phb->ioda.pe_list);
- /* Account for one DMA PE if at least one DMA capable device exist
- * below the bridge
- */
- if (pe->dma_weight != 0) {
- phb->ioda.dma_weight += pe->dma_weight;
- phb->ioda.dma_pe_count++;
- }
-
- /* Link the PE */
- pnv_ioda_link_pe_by_weight(phb, pe);
+ return pe;
}
static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
* same GPU get assigned the same PE.
*/
gpu_pdev = pnv_pci_get_gpu_dev(npu_pdev);
- for (pe_num = 0; pe_num < phb->ioda.total_pe; pe_num++) {
+ for (pe_num = 0; pe_num < phb->ioda.total_pe_num; pe_num++) {
pe = &phb->ioda.pe_array[pe_num];
if (!pe->pdev)
continue;
rid = npu_pdev->bus->number << 8 | npu_pdn->devfn;
npu_pdn->pcidev = npu_pdev;
npu_pdn->pe_number = pe_num;
- pe->dma_weight += pnv_ioda_dma_weight(npu_pdev);
phb->ioda.pe_rmap[rid] = pe->pe_number;
/* Map the PE to this link */
}
#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;
pnv_ioda_deconfigure_pe(phb, pe);
- pnv_ioda_free_pe(phb, pe->pe_number);
+ pnv_ioda_free_pe(pe);
}
}
struct pci_bus *bus;
struct pci_controller *hose;
struct pnv_phb *phb;
+ struct pnv_ioda_pe *pe;
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)
+ continue;
+
+ pe = &phb->ioda.pe_array[pdn->pe_num_map[i]];
+ pnv_ioda_free_pe(pe);
+ }
+ } 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;
pe->flags = PNV_IODA_PE_VF;
pe->pbus = NULL;
pe->parent_dev = pdev;
- pe->tce32_seg = -1;
pe->mve_number = -1;
pe->rid = (pci_iov_virtfn_bus(pdev, vf_index) << 8) |
pci_iov_virtfn_devfn(pdev, vf_index);
if (pnv_ioda_configure_pe(phb, pe)) {
/* XXX What do we do here ? */
- if (pe_num)
- pnv_ioda_free_pe(phb, pe_num);
+ pnv_ioda_free_pe(pe);
pe->pdev = NULL;
continue;
}
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 pci_bus *bus;
struct pci_controller *hose;
struct pnv_phb *phb;
+ struct pnv_ioda_pe *pe;
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++) {
+ pe = pnv_ioda_alloc_pe(phb);
+ if (!pe) {
+ ret = -EBUSY;
+ goto m64_failed;
+ }
+
+ pdn->pe_num_map[i] = pe->pe_number;
+ }
+ } 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_num,
+ 0, num_vfs, 0);
+ if (*pdn->pe_num_map >= phb->ioda.total_pe_num) {
+ 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)
+ continue;
+
+ pe = &phb->ioda.pe_array[pdn->pe_num_map[i]];
+ pnv_ioda_free_pe(pe);
+ }
+ } 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 */
.free = pnv_ioda2_table_free,
};
-static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
- struct pnv_ioda_pe *pe, unsigned int base,
- unsigned int segs)
+static int pnv_pci_ioda_dev_dma_weight(struct pci_dev *dev, void *data)
+{
+ unsigned int *weight = (unsigned int *)data;
+
+ /* This is quite simplistic. The "base" weight of a device
+ * is 10. 0 means no DMA is to be accounted for it.
+ */
+ if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL)
+ return 0;
+
+ if (dev->class == PCI_CLASS_SERIAL_USB_UHCI ||
+ dev->class == PCI_CLASS_SERIAL_USB_OHCI ||
+ dev->class == PCI_CLASS_SERIAL_USB_EHCI)
+ *weight += 3;
+ else if ((dev->class >> 8) == PCI_CLASS_STORAGE_RAID)
+ *weight += 15;
+ else
+ *weight += 10;
+
+ return 0;
+}
+
+static unsigned int pnv_pci_ioda_pe_dma_weight(struct pnv_ioda_pe *pe)
+{
+ unsigned int weight = 0;
+
+ /* SRIOV VF has same DMA32 weight as its PF */
+#ifdef CONFIG_PCI_IOV
+ if ((pe->flags & PNV_IODA_PE_VF) && pe->parent_dev) {
+ pnv_pci_ioda_dev_dma_weight(pe->parent_dev, &weight);
+ return weight;
+ }
+#endif
+
+ if ((pe->flags & PNV_IODA_PE_DEV) && pe->pdev) {
+ pnv_pci_ioda_dev_dma_weight(pe->pdev, &weight);
+ } else if ((pe->flags & PNV_IODA_PE_BUS) && pe->pbus) {
+ struct pci_dev *pdev;
+
+ list_for_each_entry(pdev, &pe->pbus->devices, bus_list)
+ pnv_pci_ioda_dev_dma_weight(pdev, &weight);
+ } else if ((pe->flags & PNV_IODA_PE_BUS_ALL) && pe->pbus) {
+ pci_walk_bus(pe->pbus, pnv_pci_ioda_dev_dma_weight, &weight);
+ }
+
+ return weight;
+}
+
+static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
+ struct pnv_ioda_pe *pe)
{
struct page *tce_mem = NULL;
struct iommu_table *tbl;
- unsigned int i;
+ unsigned int weight, total_weight = 0;
+ unsigned int tce32_segsz, base, segs, avail, i;
int64_t rc;
void *addr;
/* XXX FIXME: Handle 64-bit only DMA devices */
/* XXX FIXME: Provide 64-bit DMA facilities & non-4K TCE tables etc.. */
/* XXX FIXME: Allocate multi-level tables on PHB3 */
+ weight = pnv_pci_ioda_pe_dma_weight(pe);
+ if (!weight)
+ return;
+
+ pci_walk_bus(phb->hose->bus, pnv_pci_ioda_dev_dma_weight,
+ &total_weight);
+ segs = (weight * phb->ioda.dma32_count) / total_weight;
+ if (!segs)
+ segs = 1;
- /* We shouldn't already have a 32-bit DMA associated */
- if (WARN_ON(pe->tce32_seg >= 0))
+ /*
+ * Allocate contiguous DMA32 segments. We begin with the expected
+ * number of segments. With one more attempt, the number of DMA32
+ * segments to be allocated is decreased by one until one segment
+ * is allocated successfully.
+ */
+ do {
+ for (base = 0; base <= phb->ioda.dma32_count - segs; base++) {
+ for (avail = 0, i = base; i < base + segs; i++) {
+ if (phb->ioda.dma32_segmap[i] ==
+ IODA_INVALID_PE)
+ avail++;
+ }
+
+ if (avail == segs)
+ goto found;
+ }
+ } while (--segs);
+
+ if (!segs) {
+ pe_warn(pe, "No available DMA32 segments\n");
return;
+ }
+found:
tbl = pnv_pci_table_alloc(phb->hose->node);
iommu_register_group(&pe->table_group, phb->hose->global_number,
pe->pe_number);
pnv_pci_link_table_and_group(phb->hose->node, 0, tbl, &pe->table_group);
/* Grab a 32-bit TCE table */
- pe->tce32_seg = base;
+ pe_info(pe, "DMA weight %d (%d), assigned (%d) %d DMA32 segments\n",
+ weight, total_weight, base, segs);
pe_info(pe, " Setting up 32-bit TCE table at %08x..%08x\n",
- (base << 28), ((base + segs) << 28) - 1);
+ base * PNV_IODA1_DMA32_SEGSIZE,
+ (base + segs) * PNV_IODA1_DMA32_SEGSIZE - 1);
/* XXX Currently, we allocate one big contiguous table for the
* TCEs. We only really need one chunk per 256M of TCE space
* (ie per segment) but that's an optimization for later, it
* requires some added smarts with our get/put_tce implementation
+ *
+ * Each TCE page is 4KB in size and each TCE entry occupies 8
+ * bytes
*/
+ tce32_segsz = PNV_IODA1_DMA32_SEGSIZE >> (IOMMU_PAGE_SHIFT_4K - 3);
tce_mem = alloc_pages_node(phb->hose->node, GFP_KERNEL,
- get_order(TCE32_TABLE_SIZE * segs));
+ get_order(tce32_segsz * segs));
if (!tce_mem) {
pe_err(pe, " Failed to allocate a 32-bit TCE memory\n");
goto fail;
}
addr = page_address(tce_mem);
- memset(addr, 0, TCE32_TABLE_SIZE * segs);
+ memset(addr, 0, tce32_segsz * segs);
/* Configure HW */
for (i = 0; i < segs; i++) {
rc = opal_pci_map_pe_dma_window(phb->opal_id,
pe->pe_number,
base + i, 1,
- __pa(addr) + TCE32_TABLE_SIZE * i,
- TCE32_TABLE_SIZE, 0x1000);
+ __pa(addr) + tce32_segsz * i,
+ tce32_segsz, IOMMU_PAGE_SIZE_4K);
if (rc) {
pe_err(pe, " Failed to configure 32-bit TCE table,"
" err %ld\n", rc);
}
}
+ /* Setup DMA32 segment mapping */
+ for (i = base; i < base + segs; i++)
+ phb->ioda.dma32_segmap[i] = pe->pe_number;
+
/* Setup linux iommu table */
- pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs,
- base << 28, IOMMU_PAGE_SHIFT_4K);
+ pnv_pci_setup_iommu_table(tbl, addr, tce32_segsz * segs,
+ base * PNV_IODA1_DMA32_SEGSIZE,
+ IOMMU_PAGE_SHIFT_4K);
/* OPAL variant of P7IOC SW invalidated TCEs */
if (phb->ioda.tce_inval_reg)
return;
fail:
/* XXX Failure: Try to fallback to 64-bit only ? */
- if (pe->tce32_seg >= 0)
- pe->tce32_seg = -1;
if (tce_mem)
- __free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs));
+ __free_pages(tce_mem, get_order(tce32_segsz * segs));
if (tbl) {
pnv_pci_unlink_table_and_group(tbl, &pe->table_group);
iommu_free_table(tbl, "pnv");
{
int64_t rc;
- /* We shouldn't already have a 32-bit DMA associated */
- if (WARN_ON(pe->tce32_seg >= 0))
- return;
-
/* TVE #1 is selected by PCI address bit 59 */
pe->tce_bypass_base = 1ull << 59;
pe->pe_number);
/* The PE will reserve all possible 32-bits space */
- pe->tce32_seg = 0;
pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n",
phb->ioda.m32_pci_base);
#endif
rc = pnv_pci_ioda2_setup_default_config(pe);
- if (rc) {
- if (pe->tce32_seg >= 0)
- pe->tce32_seg = -1;
+ if (rc)
return;
- }
if (pe->flags & PNV_IODA_PE_DEV)
iommu_add_device(&pe->pdev->dev);
static void pnv_ioda_setup_dma(struct pnv_phb *phb)
{
struct pci_controller *hose = phb->hose;
- unsigned int residual, remaining, segs, tw, base;
struct pnv_ioda_pe *pe;
+ unsigned int weight;
/* If we have more PE# than segments available, hand out one
* per PE until we run out and let the rest fail. If not,
* then we assign at least one segment per PE, plus more based
* on the amount of devices under that PE
*/
- if (phb->ioda.dma_pe_count > phb->ioda.tce32_count)
- residual = 0;
- else
- residual = phb->ioda.tce32_count -
- phb->ioda.dma_pe_count;
-
- pr_info("PCI: Domain %04x has %ld available 32-bit DMA segments\n",
- hose->global_number, phb->ioda.tce32_count);
- pr_info("PCI: %d PE# for a total weight of %d\n",
- phb->ioda.dma_pe_count, phb->ioda.dma_weight);
+ pr_info("PCI: Domain %04x has %d available 32-bit DMA segments\n",
+ hose->global_number, phb->ioda.dma32_count);
pnv_pci_ioda_setup_opal_tce_kill(phb);
- /* Walk our PE list and configure their DMA segments, hand them
- * out one base segment plus any residual segments based on
- * weight
- */
- remaining = phb->ioda.tce32_count;
- tw = phb->ioda.dma_weight;
- base = 0;
- list_for_each_entry(pe, &phb->ioda.pe_dma_list, dma_link) {
- if (!pe->dma_weight)
+ /* Walk our PE list and configure their DMA segments */
+ list_for_each_entry(pe, &phb->ioda.pe_list, list) {
+ weight = pnv_pci_ioda_pe_dma_weight(pe);
+ if (!weight)
continue;
- if (!remaining) {
- pe_warn(pe, "No DMA32 resources available\n");
- continue;
- }
- segs = 1;
- if (residual) {
- segs += ((pe->dma_weight * residual) + (tw / 2)) / tw;
- if (segs > remaining)
- segs = remaining;
- }
/*
* For IODA2 compliant PHB3, we needn't care about the weight.
* the specific PE.
*/
if (phb->type == PNV_PHB_IODA1) {
- pe_info(pe, "DMA weight %d, assigned %d DMA32 segments\n",
- pe->dma_weight, segs);
- pnv_pci_ioda_setup_dma_pe(phb, pe, base, segs);
+ pnv_pci_ioda1_setup_dma_pe(phb, pe);
} else if (phb->type == PNV_PHB_IODA2) {
pe_info(pe, "Assign DMA32 space\n");
- segs = 0;
pnv_pci_ioda2_setup_dma_pe(phb, pe);
} else if (phb->type == PNV_PHB_NPU) {
/*
* as the PHB3 TVT.
*/
}
-
- remaining -= segs;
- base += segs;
}
}
#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;
+ mul = phb->ioda.total_pe_num;
+ 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 void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe,
+ struct resource *res)
+{
+ struct pnv_phb *phb = pe->phb;
+ struct pci_bus_region region;
+ int index;
+ int64_t rc;
+
+ if (!res || !res->flags || res->start > res->end)
+ return;
+
+ if (res->flags & IORESOURCE_IO) {
+ region.start = res->start - phb->ioda.io_pci_base;
+ region.end = res->end - phb->ioda.io_pci_base;
+ index = region.start / phb->ioda.io_segsize;
+
+ while (index < phb->ioda.total_pe_num &&
+ region.start <= region.end) {
+ phb->ioda.io_segmap[index] = pe->pe_number;
+ rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+ pe->pe_number, OPAL_IO_WINDOW_TYPE, 0, index);
+ if (rc != OPAL_SUCCESS) {
+ pr_err("%s: Error %lld mapping IO segment#%d to PE#%d\n",
+ __func__, rc, index, pe->pe_number);
+ break;
+ }
+
+ region.start += phb->ioda.io_segsize;
+ index++;
+ }
+ } else if ((res->flags & IORESOURCE_MEM) &&
+ !pnv_pci_is_mem_pref_64(res->flags)) {
+ region.start = res->start -
+ phb->hose->mem_offset[0] -
+ phb->ioda.m32_pci_base;
+ region.end = res->end -
+ phb->hose->mem_offset[0] -
+ phb->ioda.m32_pci_base;
+ index = region.start / phb->ioda.m32_segsize;
+
+ while (index < phb->ioda.total_pe_num &&
+ region.start <= region.end) {
+ phb->ioda.m32_segmap[index] = pe->pe_number;
+ rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+ pe->pe_number, OPAL_M32_WINDOW_TYPE, 0, index);
+ if (rc != OPAL_SUCCESS) {
+ pr_err("%s: Error %lld mapping M32 segment#%d to PE#%d",
+ __func__, rc, index, pe->pe_number);
+ break;
+ }
+
+ region.start += phb->ioda.m32_segsize;
+ index++;
+ }
+ }
+}
+
/*
* This function is supposed to be called on basis of PE from top
* to bottom style. So the the I/O or MMIO segment assigned to
* parent PE could be overrided by its child PEs if necessary.
*/
-static void pnv_ioda_setup_pe_seg(struct pci_controller *hose,
- struct pnv_ioda_pe *pe)
+static void pnv_ioda_setup_pe_seg(struct pnv_ioda_pe *pe)
{
- struct pnv_phb *phb = hose->private_data;
- struct pci_bus_region region;
- struct resource *res;
- int i, index;
- int rc;
+ struct pci_dev *pdev;
+ int i;
/*
* NOTE: We only care PCI bus based PE for now. For PCI
*/
BUG_ON(!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)));
- pci_bus_for_each_resource(pe->pbus, res, i) {
- if (!res || !res->flags ||
- res->start > res->end)
- continue;
-
- if (res->flags & IORESOURCE_IO) {
- region.start = res->start - phb->ioda.io_pci_base;
- region.end = res->end - phb->ioda.io_pci_base;
- index = region.start / phb->ioda.io_segsize;
-
- while (index < phb->ioda.total_pe &&
- region.start <= region.end) {
- phb->ioda.io_segmap[index] = pe->pe_number;
- rc = opal_pci_map_pe_mmio_window(phb->opal_id,
- pe->pe_number, OPAL_IO_WINDOW_TYPE, 0, index);
- if (rc != OPAL_SUCCESS) {
- pr_err("%s: OPAL error %d when mapping IO "
- "segment #%d to PE#%d\n",
- __func__, rc, index, pe->pe_number);
- break;
- }
-
- region.start += phb->ioda.io_segsize;
- index++;
- }
- } else if ((res->flags & IORESOURCE_MEM) &&
- !pnv_pci_is_mem_pref_64(res->flags)) {
- region.start = res->start -
- hose->mem_offset[0] -
- phb->ioda.m32_pci_base;
- region.end = res->end -
- hose->mem_offset[0] -
- phb->ioda.m32_pci_base;
- index = region.start / phb->ioda.m32_segsize;
-
- while (index < phb->ioda.total_pe &&
- region.start <= region.end) {
- phb->ioda.m32_segmap[index] = pe->pe_number;
- rc = opal_pci_map_pe_mmio_window(phb->opal_id,
- pe->pe_number, OPAL_M32_WINDOW_TYPE, 0, index);
- if (rc != OPAL_SUCCESS) {
- pr_err("%s: OPAL error %d when mapping M32 "
- "segment#%d to PE#%d",
- __func__, rc, index, pe->pe_number);
- break;
- }
+ list_for_each_entry(pdev, &pe->pbus->devices, bus_list) {
+ for (i = 0; i <= PCI_ROM_RESOURCE; i++)
+ pnv_ioda_setup_pe_res(pe, &pdev->resource[i]);
- region.start += phb->ioda.m32_segsize;
- index++;
- }
- }
+ /*
+ * If the PE contains all subordinate PCI buses, the
+ * windows of the child bridges should be mapped to
+ * the PE as well.
+ */
+ if (!(pe->flags & PNV_IODA_PE_BUS_ALL) || !pci_is_bridge(pdev))
+ continue;
+ for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++)
+ pnv_ioda_setup_pe_res(pe,
+ &pdev->resource[PCI_BRIDGE_RESOURCES + i]);
}
}
continue;
list_for_each_entry(pe, &phb->ioda.pe_list, list) {
- pnv_ioda_setup_pe_seg(hose, pe);
+ pnv_ioda_setup_pe_seg(pe);
}
}
}
struct pci_controller *hose, *tmp;
struct pnv_phb *phb;
struct pnv_ioda_pe *pe;
+ unsigned int weight;
list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
phb = hose->private_data;
if (phb->type != PNV_PHB_NPU)
continue;
- list_for_each_entry(pe, &phb->ioda.pe_dma_list, dma_link) {
+ list_for_each_entry(pe, &phb->ioda.pe_list, list) {
+ weight = pnv_pci_ioda_pe_dma_weight(pe);
+ if (WARN_ON(!weight))
+ continue;
+
enable_bypass = dma_get_mask(&pe->pdev->dev) ==
DMA_BIT_MASK(64);
pnv_npu_init_dma_pe(pe);
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 */
return true;
}
-static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus,
- u32 devfn)
-{
- return phb->ioda.pe_rmap[(bus->number << 8) | devfn];
-}
-
static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
{
struct pnv_phb *phb = hose->private_data;
}
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,
+ .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,
+ .setup_msi_irqs = pnv_setup_msi_irqs,
+ .teardown_msi_irqs = pnv_teardown_msi_irqs,
#endif
- .enable_device_hook = pnv_pci_enable_device_hook,
- .window_alignment = pnv_pci_window_alignment,
- .reset_secondary_bus = pnv_pci_reset_secondary_bus,
- .dma_set_mask = pnv_pci_ioda_dma_set_mask,
- .dma_get_required_mask = pnv_pci_ioda_dma_get_required_mask,
- .shutdown = pnv_pci_ioda_shutdown,
+ .enable_device_hook = pnv_pci_enable_device_hook,
+ .window_alignment = pnv_pci_window_alignment,
+ .reset_secondary_bus = pnv_pci_reset_secondary_bus,
+ .dma_set_mask = pnv_pci_ioda_dma_set_mask,
+ .dma_get_required_mask = pnv_pci_ioda_dma_get_required_mask,
+ .shutdown = pnv_pci_ioda_shutdown,
};
static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
- .dma_dev_setup = pnv_pci_dma_dev_setup,
+ .dma_dev_setup = pnv_pci_dma_dev_setup,
#ifdef CONFIG_PCI_MSI
- .setup_msi_irqs = pnv_setup_msi_irqs,
- .teardown_msi_irqs = pnv_teardown_msi_irqs,
+ .setup_msi_irqs = pnv_setup_msi_irqs,
+ .teardown_msi_irqs = pnv_teardown_msi_irqs,
#endif
- .enable_device_hook = pnv_pci_enable_device_hook,
- .window_alignment = pnv_pci_window_alignment,
- .reset_secondary_bus = pnv_pci_reset_secondary_bus,
- .dma_set_mask = pnv_npu_dma_set_mask,
- .shutdown = pnv_pci_ioda_shutdown,
+ .enable_device_hook = pnv_pci_enable_device_hook,
+ .window_alignment = pnv_pci_window_alignment,
+ .reset_secondary_bus = pnv_pci_reset_secondary_bus,
+ .dma_set_mask = pnv_npu_dma_set_mask,
+ .shutdown = pnv_pci_ioda_shutdown,
};
static void __init pnv_pci_init_ioda_phb(struct device_node *np,
{
struct pci_controller *hose;
struct pnv_phb *phb;
- unsigned long size, m32map_off, pemap_off, iomap_off = 0;
+ unsigned long size, m64map_off, m32map_off, pemap_off;
+ unsigned long iomap_off = 0, dma32map_off = 0;
const __be64 *prop64;
const __be32 *prop32;
int len;
+ unsigned int segno;
u64 phb_id;
void *aux;
long rc;
pr_err(" Failed to map registers !\n");
/* Initialize more IODA stuff */
- phb->ioda.total_pe = 1;
+ phb->ioda.total_pe_num = 1;
prop32 = of_get_property(np, "ibm,opal-num-pes", NULL);
if (prop32)
- phb->ioda.total_pe = be32_to_cpup(prop32);
+ phb->ioda.total_pe_num = be32_to_cpup(prop32);
prop32 = of_get_property(np, "ibm,opal-reserved-pe", NULL);
if (prop32)
- phb->ioda.reserved_pe = be32_to_cpup(prop32);
+ phb->ioda.reserved_pe_idx = be32_to_cpup(prop32);
/* Parse 64-bit MMIO range */
pnv_ioda_parse_m64_window(phb);
/* FW Has already off top 64k of M32 space (MSI space) */
phb->ioda.m32_size += 0x10000;
- phb->ioda.m32_segsize = phb->ioda.m32_size / phb->ioda.total_pe;
+ phb->ioda.m32_segsize = phb->ioda.m32_size / phb->ioda.total_pe_num;
phb->ioda.m32_pci_base = hose->mem_resources[0].start - hose->mem_offset[0];
phb->ioda.io_size = hose->pci_io_size;
- phb->ioda.io_segsize = phb->ioda.io_size / phb->ioda.total_pe;
+ phb->ioda.io_segsize = phb->ioda.io_size / phb->ioda.total_pe_num;
phb->ioda.io_pci_base = 0; /* XXX calculate this ? */
+ /* Calculate how many 32-bit TCE segments we have */
+ phb->ioda.dma32_count = phb->ioda.m32_pci_base /
+ PNV_IODA1_DMA32_SEGSIZE;
+
/* Allocate aux data & arrays. We don't have IO ports on PHB3 */
- size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long));
+ size = _ALIGN_UP(phb->ioda.total_pe_num / 8, sizeof(unsigned long));
+ m64map_off = size;
+ size += phb->ioda.total_pe_num * sizeof(phb->ioda.m64_segmap[0]);
m32map_off = size;
- size += phb->ioda.total_pe * sizeof(phb->ioda.m32_segmap[0]);
+ size += phb->ioda.total_pe_num * sizeof(phb->ioda.m32_segmap[0]);
if (phb->type == PNV_PHB_IODA1) {
iomap_off = size;
- size += phb->ioda.total_pe * sizeof(phb->ioda.io_segmap[0]);
+ size += phb->ioda.total_pe_num * sizeof(phb->ioda.io_segmap[0]);
+ dma32map_off = size;
+ size += phb->ioda.dma32_count *
+ sizeof(phb->ioda.dma32_segmap[0]);
}
pemap_off = size;
- size += phb->ioda.total_pe * sizeof(struct pnv_ioda_pe);
+ size += phb->ioda.total_pe_num * sizeof(struct pnv_ioda_pe);
aux = memblock_virt_alloc(size, 0);
phb->ioda.pe_alloc = aux;
+ phb->ioda.m64_segmap = aux + m64map_off;
phb->ioda.m32_segmap = aux + m32map_off;
- if (phb->type == PNV_PHB_IODA1)
+ for (segno = 0; segno < phb->ioda.total_pe_num; segno++) {
+ phb->ioda.m64_segmap[segno] = IODA_INVALID_PE;
+ phb->ioda.m32_segmap[segno] = IODA_INVALID_PE;
+ }
+ if (phb->type == PNV_PHB_IODA1) {
phb->ioda.io_segmap = aux + iomap_off;
+ for (segno = 0; segno < phb->ioda.total_pe_num; segno++)
+ phb->ioda.io_segmap[segno] = IODA_INVALID_PE;
+
+ phb->ioda.dma32_segmap = aux + dma32map_off;
+ for (segno = 0; segno < phb->ioda.dma32_count; segno++)
+ phb->ioda.dma32_segmap[segno] = IODA_INVALID_PE;
+ }
phb->ioda.pe_array = aux + pemap_off;
- set_bit(phb->ioda.reserved_pe, phb->ioda.pe_alloc);
+ set_bit(phb->ioda.reserved_pe_idx, phb->ioda.pe_alloc);
- INIT_LIST_HEAD(&phb->ioda.pe_dma_list);
INIT_LIST_HEAD(&phb->ioda.pe_list);
mutex_init(&phb->ioda.pe_list_mutex);
/* Calculate how many 32-bit TCE segments we have */
- phb->ioda.tce32_count = phb->ioda.m32_pci_base >> 28;
+ phb->ioda.dma32_count = phb->ioda.m32_pci_base /
+ PNV_IODA1_DMA32_SEGSIZE;
#if 0 /* We should really do that ... */
rc = opal_pci_set_phb_mem_window(opal->phb_id,
#endif
pr_info(" %03d (%03d) PE's M32: 0x%x [segment=0x%x]\n",
- phb->ioda.total_pe, phb->ioda.reserved_pe,
+ phb->ioda.total_pe_num, phb->ioda.reserved_pe_idx,
phb->ioda.m32_size, phb->ioda.m32_segsize);
if (phb->ioda.m64_size)
pr_info(" M64: 0x%lx [segment=0x%lx]\n",
phb->freeze_pe = pnv_ioda_freeze_pe;
phb->unfreeze_pe = pnv_ioda_unfreeze_pe;
- /* Setup RID -> PE mapping function */
- phb->bdfn_to_pe = pnv_ioda_bdfn_to_pe;
-
/* Setup TCEs */
phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;