#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
static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl);
-static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
+void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
const char *fmt, ...)
{
struct va_format vaf;
va_end(args);
}
-#define pe_err(pe, fmt, ...) \
- pe_level_printk(pe, KERN_ERR, fmt, ##__VA_ARGS__)
-#define pe_warn(pe, fmt, ...) \
- pe_level_printk(pe, KERN_WARNING, fmt, ##__VA_ARGS__)
-#define pe_info(pe, fmt, ...) \
- pe_level_printk(pe, KERN_INFO, fmt, ##__VA_ARGS__)
-
static bool pnv_iommu_bypass_disabled __read_mostly;
static int __init iommu_setup(char *str)
(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_num)) {
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 unsigned 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;
pe = find_next_zero_bit(phb->ioda.pe_alloc,
phb->ioda.total_pe_num, 0);
if (pe >= phb->ioda.total_pe_num)
- return IODA_INVALID_PE;
+ 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;
- memset(&phb->ioda.pe_array[pe], 0, sizeof(struct pnv_ioda_pe));
- clear_bit(pe, phb->ioda.pe_alloc);
+ WARN_ON(pe->pdev);
+
+ 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 */
}
}
+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)
}
}
-static unsigned int pnv_ioda_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_num / 8, sizeof(unsigned long));
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 */
*/
if (bitmap_empty(pe_alloc, phb->ioda.total_pe_num)) {
kfree(pe_alloc);
- return IODA_INVALID_PE;
+ return NULL;
}
/*
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;
}
/* Use last M64 BAR to cover M64 window */
phb->ioda.m64_bar_idx = 15;
- phb->init_m64 = pnv_ioda2_init_m64;
+ 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;
}
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)
{
struct pnv_phb *phb = hose->private_data;
struct pci_dn *pdn = pci_get_pdn(dev);
struct pnv_ioda_pe *pe;
- unsigned 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;
- unsigned 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)
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 */
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, i;
/* Release PE numbers */
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]);
+ 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);
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;
}
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;
/* Calculate available PE for required VFs */
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) {
+ 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);
m64_failed:
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]);
+ 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);
struct pnv_ioda_pe *pe;
uint64_t top;
bool bypass = false;
- struct pci_dev *linked_npu_dev;
- int i;
if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
return -ENODEV;;
*pdev->dev.dma_mask = dma_mask;
/* Update peer npu devices */
- if (pe->flags & PNV_IODA_PE_PEER)
- for (i = 0; i < PNV_IODA_MAX_PEER_PES; i++) {
- if (!pe->peers[i])
- continue;
-
- linked_npu_dev = pe->peers[i]->pdev;
- if (dma_get_mask(&linked_npu_dev->dev) != dma_mask)
- dma_set_mask(&linked_npu_dev->dev, dma_mask);
- }
+ pnv_npu_try_dma_set_bypass(pdev, bypass);
return 0;
}
.get = pnv_tce_get,
};
-static inline void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_ioda_pe *pe)
+#define TCE_KILL_INVAL_ALL PPC_BIT(0)
+#define TCE_KILL_INVAL_PE PPC_BIT(1)
+#define TCE_KILL_INVAL_TCE PPC_BIT(2)
+
+void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
+{
+ const unsigned long val = TCE_KILL_INVAL_ALL;
+
+ mb(); /* Ensure previous TCE table stores are visible */
+ if (rm)
+ __raw_rm_writeq(cpu_to_be64(val),
+ (__be64 __iomem *)
+ phb->ioda.tce_inval_reg_phys);
+ else
+ __raw_writeq(cpu_to_be64(val), phb->ioda.tce_inval_reg);
+}
+
+static inline void pnv_pci_ioda2_tce_invalidate_pe(struct pnv_ioda_pe *pe)
{
/* 01xb - invalidate TCEs that match the specified PE# */
- unsigned long val = (0x4ull << 60) | (pe->pe_number & 0xFF);
+ unsigned long val = TCE_KILL_INVAL_PE | (pe->pe_number & 0xFF);
struct pnv_phb *phb = pe->phb;
- struct pnv_ioda_pe *npe;
- int i;
if (!phb->ioda.tce_inval_reg)
return;
mb(); /* Ensure above stores are visible */
__raw_writeq(cpu_to_be64(val), phb->ioda.tce_inval_reg);
-
- if (pe->flags & PNV_IODA_PE_PEER)
- for (i = 0; i < PNV_IODA_MAX_PEER_PES; i++) {
- npe = pe->peers[i];
- if (!npe || npe->phb->type != PNV_PHB_NPU)
- continue;
-
- pnv_npu_tce_invalidate_entire(npe);
- }
}
static void pnv_pci_ioda2_do_tce_invalidate(unsigned pe_number, bool rm,
unsigned long start, end, inc;
/* We'll invalidate DMA address in PE scope */
- start = 0x2ull << 60;
+ start = TCE_KILL_INVAL_TCE;
start |= (pe_number & 0xFF);
end = start;
struct iommu_table_group_link *tgl;
list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) {
- struct pnv_ioda_pe *npe;
struct pnv_ioda_pe *pe = container_of(tgl->table_group,
struct pnv_ioda_pe, table_group);
__be64 __iomem *invalidate = rm ?
(__be64 __iomem *)pe->phb->ioda.tce_inval_reg_phys :
pe->phb->ioda.tce_inval_reg;
- int i;
+ if (pe->phb->type == PNV_PHB_NPU) {
+ /*
+ * The NVLink hardware does not support TCE kill
+ * per TCE entry so we have to invalidate
+ * the entire cache for it.
+ */
+ pnv_pci_ioda2_tce_invalidate_entire(pe->phb, rm);
+ continue;
+ }
pnv_pci_ioda2_do_tce_invalidate(pe->pe_number, rm,
invalidate, tbl->it_page_shift,
index, npages);
-
- if (pe->flags & PNV_IODA_PE_PEER)
- /* Invalidate PEs using the same TCE table */
- for (i = 0; i < PNV_IODA_MAX_PEER_PES; i++) {
- npe = pe->peers[i];
- if (!npe || npe->phb->type != PNV_PHB_NPU)
- continue;
-
- pnv_npu_tce_invalidate(npe, tbl, index,
- npages, rm);
- }
}
}
.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;
+
+ /*
+ * 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++;
+ }
- /* We shouldn't already have a 32-bit DMA associated */
- if (WARN_ON(pe->tce32_seg >= 0))
+ 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");
pnv_pci_link_table_and_group(phb->hose->node, num,
tbl, &pe->table_group);
- pnv_pci_ioda2_tce_invalidate_entire(pe);
+ pnv_pci_ioda2_tce_invalidate_pe(pe);
return 0;
}
if (ret)
pe_warn(pe, "Unmapping failed, ret = %ld\n", ret);
else
- pnv_pci_ioda2_tce_invalidate_entire(pe);
+ pnv_pci_ioda2_tce_invalidate_pe(pe);
pnv_pci_unlink_table_and_group(table_group->tables[num], table_group);
.take_ownership = pnv_ioda2_take_ownership,
.release_ownership = pnv_ioda2_release_ownership,
};
+
+static int gpe_table_group_to_npe_cb(struct device *dev, void *opaque)
+{
+ struct pci_controller *hose;
+ struct pnv_phb *phb;
+ struct pnv_ioda_pe **ptmppe = opaque;
+ struct pci_dev *pdev = container_of(dev, struct pci_dev, dev);
+ struct pci_dn *pdn = pci_get_pdn(pdev);
+
+ if (!pdn || pdn->pe_number == IODA_INVALID_PE)
+ return 0;
+
+ hose = pci_bus_to_host(pdev->bus);
+ phb = hose->private_data;
+ if (phb->type != PNV_PHB_NPU)
+ return 0;
+
+ *ptmppe = &phb->ioda.pe_array[pdn->pe_number];
+
+ return 1;
+}
+
+/*
+ * This returns PE of associated NPU.
+ * This assumes that NPU is in the same IOMMU group with GPU and there is
+ * no other PEs.
+ */
+static struct pnv_ioda_pe *gpe_table_group_to_npe(
+ struct iommu_table_group *table_group)
+{
+ struct pnv_ioda_pe *npe = NULL;
+ int ret = iommu_group_for_each_dev(table_group->group, &npe,
+ gpe_table_group_to_npe_cb);
+
+ BUG_ON(!ret || !npe);
+
+ return npe;
+}
+
+static long pnv_pci_ioda2_npu_set_window(struct iommu_table_group *table_group,
+ int num, struct iommu_table *tbl)
+{
+ long ret = pnv_pci_ioda2_set_window(table_group, num, tbl);
+
+ if (ret)
+ return ret;
+
+ ret = pnv_npu_set_window(gpe_table_group_to_npe(table_group), num, tbl);
+ if (ret)
+ pnv_pci_ioda2_unset_window(table_group, num);
+
+ return ret;
+}
+
+static long pnv_pci_ioda2_npu_unset_window(
+ struct iommu_table_group *table_group,
+ int num)
+{
+ long ret = pnv_pci_ioda2_unset_window(table_group, num);
+
+ if (ret)
+ return ret;
+
+ return pnv_npu_unset_window(gpe_table_group_to_npe(table_group), num);
+}
+
+static void pnv_ioda2_npu_take_ownership(struct iommu_table_group *table_group)
+{
+ /*
+ * Detach NPU first as pnv_ioda2_take_ownership() will destroy
+ * the iommu_table if 32bit DMA is enabled.
+ */
+ pnv_npu_take_ownership(gpe_table_group_to_npe(table_group));
+ pnv_ioda2_take_ownership(table_group);
+}
+
+static struct iommu_table_group_ops pnv_pci_ioda2_npu_ops = {
+ .get_table_size = pnv_pci_ioda2_get_table_size,
+ .create_table = pnv_pci_ioda2_create_table,
+ .set_window = pnv_pci_ioda2_npu_set_window,
+ .unset_window = pnv_pci_ioda2_npu_unset_window,
+ .take_ownership = pnv_ioda2_npu_take_ownership,
+ .release_ownership = pnv_ioda2_release_ownership,
+};
+
+static void pnv_pci_ioda_setup_iommu_api(void)
+{
+ struct pci_controller *hose, *tmp;
+ struct pnv_phb *phb;
+ struct pnv_ioda_pe *pe, *gpe;
+
+ /*
+ * Now we have all PHBs discovered, time to add NPU devices to
+ * the corresponding IOMMU groups.
+ */
+ 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_list, list) {
+ gpe = pnv_pci_npu_setup_iommu(pe);
+ if (gpe)
+ gpe->table_group.ops = &pnv_pci_ioda2_npu_ops;
+ }
+ }
+}
+#else /* !CONFIG_IOMMU_API */
+static void pnv_pci_ioda_setup_iommu_api(void) { };
#endif
static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb)
{
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)
- continue;
- if (!remaining) {
- pe_warn(pe, "No DMA32 resources available\n");
+ /* 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;
- }
- 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;
}
}
phb = hose->private_data;
phb->initialized = 1;
}
+
+ pnv_pci_ioda_setup_iommu_api();
}
static void pnv_pci_ioda_create_dbgfs(void)
#endif /* CONFIG_DEBUG_FS */
}
-static void pnv_npu_ioda_fixup(void)
-{
- bool enable_bypass;
- struct pci_controller *hose, *tmp;
- struct pnv_phb *phb;
- struct pnv_ioda_pe *pe;
-
- 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) {
- enable_bypass = dma_get_mask(&pe->pdev->dev) ==
- DMA_BIT_MASK(64);
- pnv_npu_init_dma_pe(pe);
- pnv_npu_dma_set_bypass(pe, enable_bypass);
- }
- }
-}
-
static void pnv_pci_ioda_fixup(void)
{
pnv_pci_ioda_setup_PEs();
eeh_init();
eeh_addr_cache_build();
#endif
-
- /* Link NPU IODA tables to their PCI devices. */
- pnv_npu_ioda_fixup();
}
/*
.shutdown = pnv_pci_ioda_shutdown,
};
+static int pnv_npu_dma_set_mask(struct pci_dev *npdev, u64 dma_mask)
+{
+ dev_err_once(&npdev->dev,
+ "%s operation unsupported for NVLink devices\n",
+ __func__);
+ return -EPERM;
+}
+
static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
.dma_dev_setup = pnv_pci_dma_dev_setup,
#ifdef CONFIG_PCI_MSI
{
struct pci_controller *hose;
struct pnv_phb *phb;
- unsigned long size, m64map_off, 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;
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_num / 8, sizeof(unsigned long));
m64map_off = size;
if (phb->type == PNV_PHB_IODA1) {
iomap_off = size;
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_num * sizeof(struct pnv_ioda_pe);
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_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,
phb->freeze_pe = pnv_ioda_freeze_pe;
phb->unfreeze_pe = pnv_ioda_unfreeze_pe;
- /* Setup TCEs */
- phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
-
/* Setup MSI support */
pnv_pci_init_ioda_msis(phb);
*/
ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
- if (phb->type == PNV_PHB_NPU)
+ if (phb->type == PNV_PHB_NPU) {
hose->controller_ops = pnv_npu_ioda_controller_ops;
- else
+ } else {
+ phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
hose->controller_ops = pnv_pci_ioda_controller_ops;
+ }
#ifdef CONFIG_PCI_IOV
ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;