table_group->tables[0] = iommu_pseries_alloc_table(node); if (table_group->tables[0]) return table_group;
kfree(table_group); return NULL;
}
staticvoid iommu_pseries_free_group(struct iommu_table_group *table_group, constchar *node_name)
{ if (!table_group) return;
#ifdef CONFIG_IOMMU_API if (table_group->group) {
iommu_group_put(table_group->group);
BUG_ON(table_group->group);
} #endif
/* Default DMA window table is at index 0, while DDW at 1. SR-IOV * adapters only have table on index 0(if not direct mapped).
*/ if (table_group->tables[0])
iommu_tce_table_put(table_group->tables[0]);
if (table_group->tables[1])
iommu_tce_table_put(table_group->tables[1]);
local_irq_save(flags); /* to protect tcep and the page behind it */
tcep = __this_cpu_read(tce_page);
/* This is safe to do since interrupts are off when we're called * from iommu_alloc{,_sg}()
*/ if (!tcep) {
tcep = (__be64 *)__get_free_page(GFP_ATOMIC); /* If allocation fails, fall back to the loop implementation */ if (!tcep) {
local_irq_restore(flags); return tce_build_pSeriesLP(tbl->it_index, tcenum,
tceshift,
npages, uaddr, direction, attrs);
}
__this_cpu_write(tce_page, tcep);
}
/* We can map max one pageful of TCEs at a time */ do { /* * Set up the page with TCE data, looping through and setting * the values.
*/
limit = min_t(long, npages, 4096 / TCE_ENTRY_SIZE);
for (l = 0; l < limit; l++) {
tcep[l] = cpu_to_be64(proto_tce | rpn << tceshift);
rpn++;
}
/* round back to the beginning of the tce page size */
num_tce += next & (tce_size - 1);
next &= ~(tce_size - 1);
/* covert to number of tces */
num_tce |= tce_size - 1;
num_tce >>= tce_shift;
do { /* * Set up the page with TCE data, looping through and setting * the values.
*/
limit = min_t(long, num_tce, 512);
dma_offset = next + be64_to_cpu(maprange->dma_base);
/* round back to the beginning of the tce page size */
num_tce += next & (tce_size - 1);
next &= ~(tce_size - 1);
/* covert to number of tces */
num_tce |= tce_size - 1;
num_tce >>= tce_shift;
/* We can map max one pageful of TCEs at a time */ do { /* * Set up the page with TCE data, looping through and setting * the values.
*/
limit = min_t(long, num_tce, 4096 / TCE_ENTRY_SIZE);
dma_offset = next + be64_to_cpu(maprange->dma_base);
for (l = 0; l < limit; l++) {
tcep[l] = cpu_to_be64(proto_tce | next);
next += tce_size;
}
/* Test if we are going over 2GB of DMA space */ if (phb->dma_window_base_cur + phb->dma_window_size > SZ_2G) {
udbg_printf("PCI_DMA: Unexpected number of IOAs under this PHB.\n");
panic("PCI_DMA: Unexpected number of IOAs under this PHB.\n");
}
pr_debug("pci_dma_bus_setup_pSeries: setting up bus %pOF\n", dn);
if (bus->self) { /* This is not a root bus, any setup will be done for the * device-side of the bridge in iommu_dev_setup_pSeries().
*/ return;
}
pci = PCI_DN(dn);
/* Check if the ISA bus on the system is under * this PHB.
*/
isa_dn = isa_dn_orig = of_find_node_by_type(NULL, "isa");
while (isa_dn && isa_dn != dn)
isa_dn = isa_dn->parent;
of_node_put(isa_dn_orig);
/* Count number of direct PCI children of the PHB. */ for (children = 0, tmp = dn->child; tmp; tmp = tmp->sibling)
children++;
pr_debug("Children: %d\n", children);
/* Calculate amount of DMA window per slot. Each window must be * a power of two (due to pci_alloc_consistent requirements). * * Keep 256MB aside for PHBs with ISA.
*/
if (!isa_dn) { /* No ISA/IDE - just set window size and return */
pci->phb->dma_window_size = 0x80000000ul; /* To be divided */
while (pci->phb->dma_window_size * children > 0x80000000ul)
pci->phb->dma_window_size >>= 1;
pr_debug("No ISA/IDE, window size is 0x%llx\n",
pci->phb->dma_window_size);
pci->phb->dma_window_base_cur = 0;
return;
}
/* If we have ISA, then we probably have an IDE * controller too. Allocate a 128MB table but * skip the first 128MB to avoid stepping on ISA * space.
*/
pci->phb->dma_window_size = 0x8000000ul;
pci->phb->dma_window_base_cur = 0x8000000ul;
if (!iommu_init_table(tbl, pci->phb->node, 0, 0))
panic("Failed to initialize iommu table");
/* Divide the rest (1.75GB) among the children */
pci->phb->dma_window_size = 0x80000000ul; while (pci->phb->dma_window_size * children > 0x70000000ul)
pci->phb->dma_window_size >>= 1;
pr_debug("ISA/IDE, window size is 0x%llx\n", pci->phb->dma_window_size);
}
#ifdef CONFIG_IOMMU_API staticint tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned long *tce, enum dma_data_direction *direction)
{ long rc; unsignedlong ioba = (unsignedlong) index << tbl->it_page_shift; unsignedlong flags, oldtce = 0;
u64 proto_tce = iommu_direction_to_tce_perm(*direction); unsignedlong newtce = *tce | proto_tce;
#ifdef CONFIG_IOMMU_API /* * When the DMA window properties might have been removed, * the parent node has the table_group setup on it.
*/ staticstruct device_node *pci_dma_find_parent_node(struct pci_dev *dev, struct iommu_table_group *table_group)
{ struct device_node *dn = pci_device_to_OF_node(dev); struct pci_dn *rpdn;
/* At least found default window, which is the case for normal boot */ if (default_win) break;
}
/* For PCI devices there will always be a DMA window, either on the device * or parent bus
*/
WARN_ON(!(default_win | ddw_win));
/* caller doesn't want to get DMA window property */ if (!prop) return rdn;
/* parse DMA window property. During normal system boot, only default * DMA window is passed in OF. But, for kdump, a dedicated adapter might * have both default and DDW in FDT. In this scenario, DDW takes precedence * over default window.
*/ if (ddw_win) { struct dynamic_dma_window_prop *p;
pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n",
dn);
pdn = pci_dma_find(dn, &prop);
/* In PPC architecture, there will always be DMA window on bus or one of the * parent bus. During reboot, there will be ibm,dma-window property to * define DMA window. For kdump, there will at least be default window or DDW * or both. * There is an exception to the above. In case the PE goes into frozen * state, firmware may not provide ibm,dma-window property at the time * of LPAR boot up.
*/
if (!pdn) {
pr_debug(" no ibm,dma-window property !\n"); return;
}
ppci = PCI_DN(pdn);
pr_debug(" parent is %pOF, iommu_table: 0x%p\n",
pdn, ppci->table_group);
if (!ppci->table_group) {
ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node);
tbl = ppci->table_group->tables[0];
/* If we're the direct child of a root bus, then we need to allocate * an iommu table ourselves. The bus setup code should have setup * the window sizes already.
*/ if (!dev->bus->self) { struct pci_controller *phb = PCI_DN(dn)->phb;
pr_debug(" --> first child, no bridge. Allocating iommu table.\n");
PCI_DN(dn)->table_group = iommu_pseries_alloc_group(phb->node);
tbl = PCI_DN(dn)->table_group->tables[0];
iommu_table_setparms(phb, dn, tbl);
if (!iommu_init_table(tbl, phb->node, 0, 0))
panic("Failed to initialize iommu table");
set_iommu_table_base(&dev->dev, tbl); return;
}
/* If this device is further down the bus tree, search upwards until * an already allocated iommu table is found and use that.
*/
staticint remove_dma_window_named(struct device_node *np, bool remove_prop, constchar *win_name, bool cleanup)
{ struct property *win;
u32 ddw_avail[DDW_APPLICABLE_SIZE]; int ret = 0;
win = of_find_property(np, win_name, NULL); if (!win) return -EINVAL;
ret = of_property_read_u32_array(np, "ibm,ddw-applicable",
&ddw_avail[0], DDW_APPLICABLE_SIZE); if (ret) return 0;
if (win->length >= sizeof(struct dynamic_dma_window_prop))
remove_dma_window(np, ddw_avail, win, cleanup);
if (!remove_prop) return 0;
/* Default window property if removed is lost as reset-pe doesn't restore it. * Though FDT has a copy of it, the DLPAR hotplugged devices will not have a * node on FDT until next reboot. So, back it up.
*/ if ((strcmp(win_name, "ibm,dma-window") == 0) &&
!of_find_property(np, "ibm,dma-window-saved", NULL))
copy_property(np, win_name, "ibm,dma-window-saved");
ret = of_remove_property(np, win); if (ret)
pr_warn("%pOF: failed to remove DMA window property: %d\n",
np, ret); return 0;
}
spin_lock(&dma_win_list_lock); /* check if we already created a window and dupe that config if so */
list_for_each_entry(window, &dma_win_list, list) { if (window->device == pdn) {
dma64 = window->prop;
*dma_addr = be64_to_cpu(dma64->dma_base);
*window_shift = be32_to_cpu(dma64->window_shift);
*direct_mapping = window->direct;
found = true; break;
}
}
spin_unlock(&dma_win_list_lock);
/* If at the time of system initialization, there are DDWs in OF, * it means this is during kexec. DDW could be direct or dynamic. * We will just mark DDWs as "dynamic" since this is kdump path, * no need to worry about perforance. ddw_list_new_entry() will * set window->direct = false.
*/
window = ddw_list_new_entry(pdn, dma64); if (!window) {
of_node_put(pdn); break;
}
/** * ddw_read_ext - Get the value of an DDW extension * @np: device node from which the extension value is to be read. * @extnum: index number of the extension. * @value: pointer to return value, modified when extension is available. * * Checks if "ibm,ddw-extensions" exists for this node, and get the value * on index 'extnum'. * It can be used only to check if a property exists, passing value == NULL. * * Returns: * 0 if extension successfully read * -EINVAL if the "ibm,ddw-extensions" does not exist, * -ENODATA if "ibm,ddw-extensions" does not have a value, and * -EOVERFLOW if "ibm,ddw-extensions" does not contain this extension.
*/ staticinlineint ddw_read_ext(conststruct device_node *np, int extnum,
u32 *value)
{ staticconstchar propname[] = "ibm,ddw-extensions";
u32 count; int ret;
ret = of_property_read_u32_index(np, propname, DDW_EXT_SIZE, &count); if (ret) return ret;
/* * From LoPAR level 2.8, "ibm,ddw-extensions" index 3 can rule how many * output parameters ibm,query-pe-dma-windows will have, ranging from * 5 to 6.
*/
ret = ddw_read_ext(parent, DDW_EXT_QUERY_OUT_SIZE, &ext_query); if (!ret && ext_query == 1)
out_sz = 6; else
out_sz = 5;
/* * Get the config address and phb buid of the PE window. * Rely on eeh to retrieve this for us. * Retrieve them from the pci device, not the node with the * dma-window property
*/
dn = pci_device_to_OF_node(dev);
pdn = PCI_DN(dn);
buid = pdn->phb->buid;
cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
ret = rtas_call(ddw_avail[DDW_QUERY_PE_DMA_WIN], 3, out_sz, query_out,
cfg_addr, BUID_HI(buid), BUID_LO(buid));
staticint create_ddw(struct pci_dev *dev, const u32 *ddw_avail, struct ddw_create_response *create, int page_shift, int window_shift)
{ struct device_node *dn; struct pci_dn *pdn;
u32 cfg_addr;
u64 buid; int ret;
/* * Get the config address and phb buid of the PE window. * Rely on eeh to retrieve this for us. * Retrieve them from the pci device, not the node with the * dma-window property
*/
dn = pci_device_to_OF_node(dev);
pdn = PCI_DN(dn);
buid = pdn->phb->buid;
cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
do { /* extra outputs are LIOBN and dma-addr (hi, lo) */
ret = rtas_call(ddw_avail[DDW_CREATE_PE_DMA_WIN], 5, 4,
(u32 *)create, cfg_addr, BUID_HI(buid),
BUID_LO(buid), page_shift, window_shift);
} while (rtas_busy_delay(ret));
dev_info(&dev->dev, "ibm,create-pe-dma-window(%x) %x %x %x %x %x returned %d " "(liobn = 0x%x starting addr = %x %x)\n",
ddw_avail[DDW_CREATE_PE_DMA_WIN], cfg_addr, BUID_HI(buid),
BUID_LO(buid), page_shift, window_shift, ret, create->liobn,
create->addr_hi, create->addr_lo);
/* * Platforms supporting the DDW option starting with LoPAR level 2.7 implement * ibm,ddw-extensions, which carries the rtas token for * ibm,reset-pe-dma-windows. * That rtas-call can be used to restore the default DMA window for the device.
*/ staticvoid reset_dma_window(struct pci_dev *dev, struct device_node *par_dn)
{ int ret;
u32 cfg_addr, reset_dma_win;
u64 buid; struct device_node *dn; struct pci_dn *pdn;
ret = ddw_read_ext(par_dn, DDW_EXT_RESET_DMA_WIN, &reset_dma_win); if (ret) return;
ret = rtas_call(reset_dma_win, 3, 1, NULL, cfg_addr, BUID_HI(buid),
BUID_LO(buid)); if (ret)
dev_info(&dev->dev, "ibm,reset-pe-dma-windows(%x) %x %x %x returned %d ",
reset_dma_win, cfg_addr, BUID_HI(buid), BUID_LO(buid),
ret);
}
/* * Platforms support placing PHB in limited address mode starting with LoPAR * level 2.13 implement. In this mode, the DMA address returned by DDW is over * 4GB but, less than 64-bits. This benefits IO adapters that don't support * 64-bits for DMA addresses.
*/ staticint limited_dma_window(struct pci_dev *dev, struct device_node *par_dn)
{ int ret;
u32 cfg_addr, reset_dma_win, las_supported;
u64 buid; struct device_node *dn; struct pci_dn *pdn;
ret = ddw_read_ext(par_dn, DDW_EXT_RESET_DMA_WIN, &reset_dma_win); if (ret) goto out;
ret = ddw_read_ext(par_dn, DDW_EXT_LIMITED_ADDR_MODE, &las_supported);
/* Limited Address Space extension available on the platform but DDW in * limited addressing mode not supported
*/ if (!ret && !las_supported)
ret = -EPROTO;
if (ret) {
dev_info(&dev->dev, "Limited Address Space for DDW not Supported, err: %d", ret); goto out;
}
ret = rtas_call(reset_dma_win, 4, 1, NULL, cfg_addr, BUID_HI(buid),
BUID_LO(buid), 1); if (ret)
dev_info(&dev->dev, "ibm,reset-pe-dma-windows(%x) for Limited Addr Support: %x %x %x returned %d ",
reset_dma_win, cfg_addr, BUID_HI(buid), BUID_LO(buid),
ret);
out: return ret;
}
/* Return largest page shift based on "IO Page Sizes" output of ibm,query-pe-dma-window. */ staticint iommu_get_page_shift(u32 query_page_size)
{ /* Supported IO page-sizes according to LoPAR, note that 2M is out of order */ constint shift[] = {
__builtin_ctzll(SZ_4K), __builtin_ctzll(SZ_64K), __builtin_ctzll(SZ_16M),
__builtin_ctzll(SZ_32M), __builtin_ctzll(SZ_64M), __builtin_ctzll(SZ_128M),
__builtin_ctzll(SZ_256M), __builtin_ctzll(SZ_16G), __builtin_ctzll(SZ_2M)
};
int i = ARRAY_SIZE(shift) - 1; int ret = 0;
/* * On LoPAR, ibm,query-pe-dma-window outputs "IO Page Sizes" using a bit field: * - bit 31 means 4k pages are supported, * - bit 30 means 64k pages are supported, and so on. * Larger pagesizes map more memory with the same amount of TCEs, so start probing them.
*/ for (; i >= 0 ; i--) { if (query_page_size & (1 << i))
ret = max(ret, shift[i]);
}
/* * If the PE supports dynamic dma windows, and there is space for a table * that can map all pages in a linear offset, then setup such a table, * and record the dma-offset in the struct device. * * dev: the pci device we are checking * pdn: the parent pe node with the ibm,dma_window property * Future: also check if we can remap the base window for our base page size * * returns true if can map all pages (direct mapping), false otherwise..
*/ staticbool enable_ddw(struct pci_dev *dev, struct device_node *pdn, u64 dma_mask)
{ int len = 0, ret; int max_ram_len = order_base_2(ddw_memory_hotplug_max()); struct ddw_query_response query; struct ddw_create_response create; int page_shift;
u64 win_addr, dynamic_offset = 0; constchar *win_name; struct device_node *dn;
u32 ddw_avail[DDW_APPLICABLE_SIZE]; struct dma_win *window; struct property *win64; struct failed_ddw_pdn *fpdn; bool default_win_removed = false, direct_mapping = false; bool dynamic_mapping = false; bool pmem_present; struct pci_dn *pci = PCI_DN(pdn); struct property *default_win = NULL; bool limited_addr_req = false, limited_addr_enabled = false; int dev_max_ddw; int ddw_sz;
if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len, &direct_mapping)) goto out_unlock;
/* * If we already went through this for a previous function of * the same device and failed, we don't want to muck with the * DMA window again, as it will race with in-flight operations * and can lead to EEHs. The above mutex protects access to the * list.
*/
list_for_each_entry(fpdn, &failed_ddw_pdn_list, list) { if (fpdn->pdn == pdn) goto out_unlock;
}
/* * the ibm,ddw-applicable property holds the tokens for: * ibm,query-pe-dma-window * ibm,create-pe-dma-window * for the given node in that order. * the property is actually in the parent, not the PE
*/
ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
&ddw_avail[0], DDW_APPLICABLE_SIZE); if (ret) goto out_failed;
/* * Query if there is a second window of size to map the * whole partition. Query returns number of windows, largest * block assigned to PE (partition endpoint), and two bitmasks * of page sizes: supported and supported for migrate-dma.
*/
dn = pci_device_to_OF_node(dev);
ret = query_ddw(dev, ddw_avail, &query, pdn); if (ret != 0) goto out_failed;
/* DMA Limited Addressing required? This is when the driver has * requested to create DDW but supports mask which is less than 64-bits
*/
limited_addr_req = (dma_mask != DMA_BIT_MASK(64));
/* place the PHB in Limited Addressing mode */ if (limited_addr_req) { if (limited_dma_window(dev, pdn)) goto out_failed;
/* PHB is in Limited address mode */
limited_addr_enabled = true;
}
/* * If there is no window available, remove the default DMA window, * if it's present. This will make all the resources available to the * new DDW window. * If anything fails after this, we need to restore it, so also check * for extensions presence.
*/ if (query.windows_available == 0) { int reset_win_ext;
/* DDW + IOMMU on single window may fail if there is any allocation */ if (iommu_table_in_use(pci->table_group->tables[0])) {
dev_warn(&dev->dev, "current IOMMU table in use, can't be replaced.\n"); goto out_failed;
}
default_win = of_find_property(pdn, "ibm,dma-window", NULL); if (!default_win) goto out_failed;
reset_win_ext = ddw_read_ext(pdn, DDW_EXT_RESET_DMA_WIN, NULL); if (reset_win_ext) goto out_failed;
/* Query again, to check if the window is available */
ret = query_ddw(dev, ddw_avail, &query, pdn); if (ret != 0) goto out_failed;
if (query.windows_available == 0) { /* no windows are available for this device. */
dev_dbg(&dev->dev, "no free dynamic windows"); goto out_failed;
}
}
page_shift = iommu_get_page_shift(query.page_size); if (!page_shift) {
dev_dbg(&dev->dev, "no supported page size in mask %x",
query.page_size); goto out_failed;
}
/* Maximum DMA window size that the device can address (in log2) */
dev_max_ddw = fls64(dma_mask);
/* If the device DMA mask is less than 64-bits, make sure the DMA window * size is not bigger than what the device can access
*/
ddw_sz = min(order_base_2(query.largest_available_block << page_shift),
dev_max_ddw);
/* * The "ibm,pmemory" can appear anywhere in the address space. * Assuming it is still backed by page structs, try MAX_PHYSMEM_BITS * for the upper limit and fallback to max RAM otherwise but this * disables device::dma_ops_bypass.
*/
len = max_ram_len; if (pmem_present) { if (ddw_sz >= MAX_PHYSMEM_BITS)
len = MAX_PHYSMEM_BITS; else
dev_info(&dev->dev, "Skipping ibm,pmemory");
}
/* check if the available block * number of ptes will map everything */ if (ddw_sz < len) {
dev_dbg(&dev->dev, "can't map partition max 0x%llx with %llu %llu-sized pages\n",
1ULL << len,
query.largest_available_block,
1ULL << page_shift);
/* DDW is big enough to direct map RAM. If there is vPMEM, check * if enough space is left in DDW where we can dynamically * allocate TCEs for vPMEM. For now, this Hybrid sharing of DDW * is only for SR-IOV devices.
*/ if (default_win_removed && pmem_present && !direct_mapping) { /* DDW is big enough to be split */ if ((1ULL << ddw_sz) >=
MIN_DDW_VPMEM_DMA_WINDOW + (1ULL << max_ram_len)) {
direct_mapping = true;
/* offset of the Dynamic part of DDW */
dynamic_offset = 1ULL << max_ram_len;
}
/* DDW will at least have dynamic allocation */
dynamic_mapping = true;
/* create max size DDW possible */
len = ddw_sz;
}
}
/* Even if the DDW is split into both direct mapped RAM and dynamically * mapped vPMEM, the DDW property in OF will be marked as Direct.
*/
win_name = direct_mapping ? DIRECT64_PROPNAME : DMA64_PROPNAME;
ret = create_ddw(dev, ddw_avail, &create, page_shift, len); if (ret != 0) goto out_failed;
dev_dbg(&dev->dev, "created tce table LIOBN 0x%x for %pOF\n",
create.liobn, dn);
if (!win64) {
dev_info(&dev->dev, "couldn't allocate property, property name, or value\n"); goto out_remove_win;
}
ret = of_add_property(pdn, win64); if (ret) {
dev_err(&dev->dev, "unable to add DMA window property for %pOF: %d",
pdn, ret); goto out_free_prop;
}
window = ddw_list_new_entry(pdn, win64->value); if (!window) goto out_del_prop;
window->direct = direct_mapping;
if (direct_mapping) { /* DDW maps the whole partition, so enable direct DMA mapping */
ret = walk_system_ram_range(0, ddw_memory_hotplug_max() >> PAGE_SHIFT,
win64->value, tce_setrange_multi_pSeriesLP_walk); if (ret) {
dev_info(&dev->dev, "failed to map DMA window for %pOF: %d\n",
dn, ret);
/* Make sure to clean DDW if any TCE was set*/
clean_dma_window(pdn, win64->value); goto out_del_list;
} if (default_win_removed) {
iommu_tce_table_put(pci->table_group->tables[0]);
pci->table_group->tables[0] = NULL;
set_iommu_table_base(&dev->dev, NULL);
}
}
if (dynamic_mapping) { struct iommu_table *newtbl; int i; unsignedlong start = 0, end = 0;
u64 dynamic_addr, dynamic_len;
for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) { constunsignedlong mask = IORESOURCE_MEM_64 | IORESOURCE_MEM;
/* Look for MMIO32 */ if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) {
start = pci->phb->mem_resources[i].start;
end = pci->phb->mem_resources[i].end; break;
}
}
/* New table for using DDW instead of the default DMA window */
newtbl = iommu_pseries_alloc_table(pci->phb->node); if (!newtbl) {
dev_dbg(&dev->dev, "couldn't create new IOMMU table\n"); goto out_del_list;
}
/* If the DDW is split between directly mapped RAM and Dynamic * mapped for TCES, offset into the DDW where the dynamic part * begins.
*/
dynamic_addr = win_addr + dynamic_offset;
dynamic_len = (1UL << len) - dynamic_offset;
iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn,
dynamic_addr, dynamic_len, page_shift, NULL,
&iommu_table_lpar_multi_ops);
iommu_init_table(newtbl, pci->phb->node,
start >> page_shift, end >> page_shift);
/* If we have persistent memory and the window size is not big enough * to directly map both RAM and vPMEM, then we need to set DMA limit.
*/ if (pmem_present && direct_mapping && len != MAX_PHYSMEM_BITS)
dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset +
(1ULL << max_ram_len);
/* Only for normal boot with default window. Doesn't matter during * kdump, since these will not be used during kdump.
*/ if (is_kdump_kernel()) return;
if (table_group->max_dynamic_windows_supported != 0) return; /* already initialized */
/* dev setup for LPAR is a little tricky, since the device tree might * contain the dma-window properties per-device and not necessarily * for the bus. So we need to search upwards in the tree until we * either hit a dma-window property, OR find a parent with a table * already allocated.
*/
dn = pci_device_to_OF_node(dev);
pr_debug(" node is %pOF\n", dn);
pdn = pci_dma_find(dn, &prop); if (!pdn || !PCI_DN(pdn)) {
printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: " "no DMA window found for pci dev=%s dn=%pOF\n",
pci_name(dev), dn); return;
}
pr_debug(" parent is %pOF\n", pdn);
/* For DDW, DMA mask should be more than 32-bits. For mask more then * 32-bits but less then 64-bits, DMA addressing is supported in * Limited Addressing mode.
*/ if (dma_mask <= DMA_BIT_MASK(32)) returnfalse;
dev_dbg(&pdev->dev, "node is %pOF\n", dn);
/* * the device tree might contain the dma-window properties * per-device and not necessarily for the bus. So we need to * search upwards in the tree until we either hit a dma-window * property, OR find a parent with a table already allocated.
*/
pdn = pci_dma_find(dn, NULL); if (pdn && PCI_DN(pdn)) return enable_ddw(pdev, pdn, dma_mask);
returnfalse;
}
#ifdef CONFIG_IOMMU_API /* * A simple iommu_table_group_ops which only allows reusing the existing * iommu_table. This handles VFIO for POWER7 or the nested KVM. * The ops does not allow creating windows and only allows reusing the existing * one if it matches table_group->tce32_start/tce32_size/page_shift.
*/ staticunsignedlong spapr_tce_get_table_size(__u32 page_shift,
__u64 window_size, __u32 levels)
{ unsignedlong size;
pdn = pci_dma_find_parent_node(pdev, table_group); if (!pdn || !PCI_DN(pdn)) {
dev_warn(&pdev->dev, "No table_group configured for the node %pOF\n", pdn); return -1;
}
pci = PCI_DN(pdn);
/* The default window is restored if not present already on removal of DDW. * However, if used by VFIO SPAPR sub driver, the user's order of removal of * windows might have been different to not leading to auto restoration, * suppose the DDW was removed first followed by the default one. * So, restore the default window with reset-pe-dma call explicitly.
*/
restore_default_dma_window(pdev, pdn);
if (!is_power_of_2(window_size) || levels > 1) return -EINVAL;
window_shift = order_base_2(window_size);
mutex_lock(&dma_win_init_mutex);
ret = -ENODEV;
pdn = pci_dma_find_parent_node(pdev, table_group); if (!pdn || !PCI_DN(pdn)) { /* Niether of 32s|64-bit exist! */
dev_warn(&pdev->dev, "No dma-windows exist for the node %pOF\n", pdn); goto out_failed;
}
pci = PCI_DN(pdn);
/* If the enable DDW failed for the pdn, dont retry! */
list_for_each_entry(fpdn, &failed_ddw_pdn_list, list) { if (fpdn->pdn == pdn) {
dev_info(&pdev->dev, "%pOF in failed DDW device list\n", pdn); goto out_unlock;
}
}
tbl = iommu_pseries_alloc_table(pci->phb->node); if (!tbl) {
dev_dbg(&pdev->dev, "couldn't create new IOMMU table\n"); goto out_unlock;
}
if (num == 0) { bool direct_mapping; /* The request is not for default window? Ensure there is no DDW window already */ if (!is_default_window_request(table_group, page_shift, window_size)) { if (find_existing_ddw(pdn, &pdev->dev.archdata.dma_offset, &len,
&direct_mapping)) {
dev_warn(&pdev->dev, "%pOF: 64-bit window already present.", pdn);
ret = -EPERM; goto out_unlock;
}
} else { /* Request is for Default window, ensure there is no DDW if there is a * need to reset. reset-pe otherwise removes the DDW also
*/
default_prop = of_get_property(pdn, "ibm,dma-window", NULL); if (!default_prop) { if (find_existing_ddw(pdn, &pdev->dev.archdata.dma_offset, &len,
&direct_mapping)) {
dev_warn(&pdev->dev, "%pOF: Attempt to create window#0 when 64-bit window is present. Preventing the attempt as that would destroy the 64-bit window",
pdn);
ret = -EPERM; goto out_unlock;
}
ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
&ddw_avail[0], DDW_APPLICABLE_SIZE); if (ret) {
dev_info(&pdev->dev, "ibm,ddw-applicable not found\n"); goto out_failed;
}
ret = -ENODEV;
pr_err("%s: Calling query %pOF\n", __func__, pdn);
ret = query_ddw(pdev, ddw_avail, &query, pdn); if (ret) goto out_failed;
ret = -ENODEV;
len = window_shift; if (query.largest_available_block < (1ULL << (len - page_shift))) {
dev_dbg(&pdev->dev, "can't map window 0x%llx with %llu %llu-sized pages\n",
1ULL << len, query.largest_available_block,
1ULL << page_shift);
ret = -EINVAL; /* Retry with smaller window size */ goto out_unlock;
}
ret = of_add_property(pdn, win64); if (ret) {
dev_err(&pdev->dev, "unable to add DMA window property for %pOF: %ld", pdn, ret); goto free_property;
}
ret = -ENODEV;
window = ddw_list_new_entry(pdn, win64->value); if (!window) goto remove_property;
window->direct = false;
for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) { constunsignedlong mask = IORESOURCE_MEM_64 | IORESOURCE_MEM;
/* Look for MMIO32 */ if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) {
start = pci->phb->mem_resources[i].start;
end = pci->phb->mem_resources[i].end; break;
}
}
/* New table for using DDW instead of the default DMA window */
iommu_table_setparms_common(tbl, pci->phb->bus->number, create.liobn, win_addr,
1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops);
iommu_init_table(tbl, pci->phb->node, start >> page_shift, end >> page_shift);
pdn = pci_dma_find(dn, NULL); if (!pdn || !PCI_DN(pdn)) { /* Niether of 32s|64-bit exist! */
dev_warn(&pdev->dev, "No dma-windows exist for the node %pOF\n", pdn); goto out_failed;
}
/* Dont clear the TCEs, User should have done it */ if (remove_dma_window_named(pdn, true, win_name, false)) {
pr_err("%s: The existing DDW removal failed for node %pOF\n", __func__, pdn); goto out_failed; /* Could not remove it either! */
}
/* SRIOV VFs using direct map by the host driver OR multifunction devices * where the ownership was taken on the attempt by the first function
*/ if (!tbl && (table_group->max_dynamic_windows_supported != 1)) return 0;
mutex_lock(&dma_win_init_mutex);
pdn = pci_dma_find(dn, NULL); if (!pdn || !PCI_DN(pdn)) { /* Niether of 32s|64-bit exist! */
dev_warn(&pdev->dev, "No dma-windows exist for the node %pOF\n", pdn);
mutex_unlock(&dma_win_init_mutex); return -1;
}
/* * Though rtas call reset-pe removes the DDW, it doesn't clear the entries on the table * if there are any. In case of direct map, the entries will be left over, which * is fine for PEs with 2 DMA windows where the second window is created with create-pe * at which point the table is cleared. However, on VFs having only one DMA window, the * default window would end up seeing the entries left over from the direct map done * on the second window. So, remove the ddw explicitly so that clean_dma_window() * cleans up the entries if any.
*/ if (remove_dynamic_dma_windows(pdev, pdn)) {
dev_warn(&pdev->dev, "The existing DDW removal failed for node %pOF\n", pdn);
mutex_unlock(&dma_win_init_mutex); return -1;
}
/* The table_group->tables[0] is not null now, it must be the default window
--> --------------------
--> maximum size reached
--> --------------------
Messung V0.5
¤ Dauer der Verarbeitung: 0.22 Sekunden
(vorverarbeitet)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.