#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/spinlock.h>
+#include <linux/sched.h> /* for show_stack */
#include <linux/string.h>
#include <linux/pci.h>
#include <linux/dma-mapping.h>
#include "plpar_wrappers.h"
+static void tce_invalidate_pSeries_sw(struct iommu_table *tbl,
+ u64 *startp, u64 *endp)
+{
+ u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index;
+ unsigned long start, end, inc;
+
+ start = __pa(startp);
+ end = __pa(endp);
+ inc = L1_CACHE_BYTES; /* invalidate a cacheline of TCEs at a time */
+
+ /* If this is non-zero, change the format. We shift the
+ * address and or in the magic from the device tree. */
+ if (tbl->it_busno) {
+ start <<= 12;
+ end <<= 12;
+ inc <<= 12;
+ start |= tbl->it_busno;
+ end |= tbl->it_busno;
+ }
+
+ end |= inc - 1; /* round up end to be different than start */
+
+ mb(); /* Make sure TCEs in memory are written */
+ while (start <= end) {
+ out_be64(invalidate, start);
+ start += inc;
+ }
+}
+
static int tce_build_pSeries(struct iommu_table *tbl, long index,
long npages, unsigned long uaddr,
enum dma_data_direction direction,
struct dma_attrs *attrs)
{
u64 proto_tce;
- u64 *tcep;
+ u64 *tcep, *tces;
u64 rpn;
proto_tce = TCE_PCI_READ; // Read allowed
if (direction != DMA_TO_DEVICE)
proto_tce |= TCE_PCI_WRITE;
- tcep = ((u64 *)tbl->it_base) + index;
+ tces = tcep = ((u64 *)tbl->it_base) + index;
while (npages--) {
/* can't move this out since we might cross MEMBLOCK boundary */
uaddr += TCE_PAGE_SIZE;
tcep++;
}
+
+ if (tbl->it_type & TCE_PCI_SWINV_CREATE)
+ tce_invalidate_pSeries_sw(tbl, tces, tcep - 1);
return 0;
}
static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages)
{
- u64 *tcep;
+ u64 *tcep, *tces;
- tcep = ((u64 *)tbl->it_base) + index;
+ tces = tcep = ((u64 *)tbl->it_base) + index;
while (npages--)
*(tcep++) = 0;
+
+ if (tbl->it_type & TCE_PCI_SWINV_FREE)
+ tce_invalidate_pSeries_sw(tbl, tces, tcep - 1);
}
static unsigned long tce_get_pseries(struct iommu_table *tbl, long index)
long l, limit;
long tcenum_start = tcenum, npages_start = npages;
int ret = 0;
+ unsigned long flags;
if (npages == 1) {
return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
direction, attrs);
}
+ local_irq_save(flags); /* to protect tcep and the page behind it */
+
tcep = __get_cpu_var(tce_page);
/* This is safe to do since interrupts are off when we're called
tcep = (u64 *)__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, tcenum, npages, uaddr,
direction, attrs);
}
tcenum += limit;
} while (npages > 0 && !rc);
+ local_irq_restore(flags);
+
if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
ret = (int)rc;
tce_freemulti_pSeriesLP(tbl, tcenum_start,
struct iommu_table *tbl)
{
struct device_node *node;
- const unsigned long *basep;
+ const unsigned long *basep, *sw_inval;
const u32 *sizep;
node = phb->dn;
tbl->it_index = 0;
tbl->it_blocksize = 16;
tbl->it_type = TCE_PCI;
+
+ sw_inval = of_get_property(node, "linux,tce-sw-invalidate-info", NULL);
+ if (sw_inval) {
+ /*
+ * This property contains information on how to
+ * invalidate the TCE entry. The first property is
+ * the base MMIO address used to invalidate entries.
+ * The second property tells us the format of the TCE
+ * invalidate (whether it needs to be shifted) and
+ * some magic routing info to add to our invalidate
+ * command.
+ */
+ tbl->it_index = (unsigned long) ioremap(sw_inval[0], 8);
+ tbl->it_busno = sw_inval[1]; /* overload this with magic */
+ tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE;
+ }
}
/*
early_param("disable_ddw", disable_ddw_setup);
+static inline void __remove_ddw(struct device_node *np, const u32 *ddw_avail, u64 liobn)
+{
+ int ret;
+
+ ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn);
+ if (ret)
+ pr_warning("%s: failed to remove DMA window: rtas returned "
+ "%d to ibm,remove-pe-dma-window(%x) %llx\n",
+ np->full_name, ret, ddw_avail[2], liobn);
+ else
+ pr_debug("%s: successfully removed DMA window: rtas returned "
+ "%d to ibm,remove-pe-dma-window(%x) %llx\n",
+ np->full_name, ret, ddw_avail[2], liobn);
+}
+
static void remove_ddw(struct device_node *np)
{
struct dynamic_dma_window_prop *dwp;
pr_debug("%s successfully cleared tces in window.\n",
np->full_name);
- ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn);
- if (ret)
- pr_warning("%s: failed to remove direct window: rtas returned "
- "%d to ibm,remove-pe-dma-window(%x) %llx\n",
- np->full_name, ret, ddw_avail[2], liobn);
- else
- pr_debug("%s: successfully removed direct window: rtas returned "
- "%d to ibm,remove-pe-dma-window(%x) %llx\n",
- np->full_name, ret, ddw_avail[2], liobn);
+ __remove_ddw(np, ddw_avail, liobn);
delprop:
ret = prom_remove_property(np, win64);
static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
struct ddw_query_response *query)
{
- struct device_node *dn;
- struct pci_dn *pcidn;
+ struct eeh_dev *edev;
u32 cfg_addr;
u64 buid;
int ret;
* Retrieve them from the pci device, not the node with the
* dma-window property
*/
- dn = pci_device_to_OF_node(dev);
- pcidn = PCI_DN(dn);
- cfg_addr = pcidn->eeh_config_addr;
- if (pcidn->eeh_pe_config_addr)
- cfg_addr = pcidn->eeh_pe_config_addr;
- buid = pcidn->phb->buid;
+ edev = pci_dev_to_eeh_dev(dev);
+ cfg_addr = edev->config_addr;
+ if (edev->pe_config_addr)
+ cfg_addr = edev->pe_config_addr;
+ buid = edev->phb->buid;
+
ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query,
cfg_addr, BUID_HI(buid), BUID_LO(buid));
dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x"
struct ddw_create_response *create, int page_shift,
int window_shift)
{
- struct device_node *dn;
- struct pci_dn *pcidn;
+ struct eeh_dev *edev;
u32 cfg_addr;
u64 buid;
int ret;
* Retrieve them from the pci device, not the node with the
* dma-window property
*/
- dn = pci_device_to_OF_node(dev);
- pcidn = PCI_DN(dn);
- cfg_addr = pcidn->eeh_config_addr;
- if (pcidn->eeh_pe_config_addr)
- cfg_addr = pcidn->eeh_pe_config_addr;
- buid = pcidn->phb->buid;
+ edev = pci_dev_to_eeh_dev(dev);
+ cfg_addr = edev->config_addr;
+ if (edev->pe_config_addr)
+ cfg_addr = edev->pe_config_addr;
+ buid = edev->phb->buid;
do {
/* extra outputs are LIOBN and dma-addr (hi, lo) */
return ret;
}
+static void restore_default_window(struct pci_dev *dev,
+ u32 ddw_restore_token, unsigned long liobn)
+{
+ struct eeh_dev *edev;
+ 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
+ */
+ edev = pci_dev_to_eeh_dev(dev);
+ cfg_addr = edev->config_addr;
+ if (edev->pe_config_addr)
+ cfg_addr = edev->pe_config_addr;
+ buid = edev->phb->buid;
+
+ do {
+ ret = rtas_call(ddw_restore_token, 3, 1, NULL, cfg_addr,
+ BUID_HI(buid), BUID_LO(buid));
+ } while (rtas_busy_delay(ret));
+ dev_info(&dev->dev,
+ "ibm,reset-pe-dma-windows(%x) %x %x %x returned %d\n",
+ ddw_restore_token, cfg_addr, BUID_HI(buid), BUID_LO(buid), ret);
+}
+
/*
* 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,
u64 dma_addr, max_addr;
struct device_node *dn;
const u32 *uninitialized_var(ddw_avail);
+ const u32 *uninitialized_var(ddw_extensions);
+ u32 ddw_restore_token = 0;
struct direct_window *window;
struct property *win64;
struct dynamic_dma_window_prop *ddwprop;
+ const void *dma_window = NULL;
+ unsigned long liobn, offset, size;
mutex_lock(&direct_window_init_mutex);
if (!ddw_avail || len < 3 * sizeof(u32))
goto out_unlock;
- /*
+ /*
+ * the extensions property is only required to exist in certain
+ * levels of firmware and later
+ * the ibm,ddw-extensions property is a list with the first
+ * element containing the number of extensions and each
+ * subsequent entry is a value corresponding to that extension
+ */
+ ddw_extensions = of_get_property(pdn, "ibm,ddw-extensions", &len);
+ if (ddw_extensions) {
+ /*
+ * each new defined extension length should be added to
+ * the top of the switch so the "earlier" entries also
+ * get picked up
+ */
+ switch (ddw_extensions[0]) {
+ /* ibm,reset-pe-dma-windows */
+ case 1:
+ ddw_restore_token = ddw_extensions[1];
+ break;
+ }
+ }
+
+ /*
+ * Only remove the existing DMA window if we can restore back to
+ * the default state. Removing the existing window maximizes the
+ * resources available to firmware for dynamic window creation.
+ */
+ if (ddw_restore_token) {
+ dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
+ of_parse_dma_window(pdn, dma_window, &liobn, &offset, &size);
+ __remove_ddw(pdn, ddw_avail, liobn);
+ }
+
+ /*
* 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
dn = pci_device_to_OF_node(dev);
ret = query_ddw(dev, ddw_avail, &query);
if (ret != 0)
- goto out_unlock;
+ goto out_restore_window;
if (query.windows_available == 0) {
/*
* trading in for a larger page size.
*/
dev_dbg(&dev->dev, "no free dynamic windows");
- goto out_unlock;
+ goto out_restore_window;
}
if (query.page_size & 4) {
page_shift = 24; /* 16MB */
} else {
dev_dbg(&dev->dev, "no supported direct page size in mask %x",
query.page_size);
- goto out_unlock;
+ goto out_restore_window;
}
/* verify the window * number of ptes will map the partition */
/* check largest block * page size > max memory hotplug addr */
dev_dbg(&dev->dev, "can't map partiton max 0x%llx with %u "
"%llu-sized pages\n", max_addr, query.largest_available_block,
1ULL << page_shift);
- goto out_unlock;
+ goto out_restore_window;
}
len = order_base_2(max_addr);
win64 = kzalloc(sizeof(struct property), GFP_KERNEL);
if (!win64) {
dev_info(&dev->dev,
"couldn't allocate property for 64bit dma window\n");
- goto out_unlock;
+ goto out_restore_window;
}
win64->name = kstrdup(DIRECT64_PROPNAME, GFP_KERNEL);
win64->value = ddwprop = kmalloc(sizeof(*ddwprop), GFP_KERNEL);
if (ret) {
dev_info(&dev->dev, "failed to map direct window for %s: %d\n",
dn->full_name, ret);
- goto out_clear_window;
+ goto out_free_window;
}
ret = prom_add_property(pdn, win64);
if (ret) {
dev_err(&dev->dev, "unable to add dma window property for %s: %d",
pdn->full_name, ret);
- goto out_clear_window;
+ goto out_free_window;
}
window->device = pdn;
dma_addr = of_read_number(&create.addr_hi, 2);
goto out_unlock;
+out_free_window:
+ kfree(window);
+
out_clear_window:
remove_ddw(pdn);
kfree(win64->value);
kfree(win64);
+out_restore_window:
+ if (ddw_restore_token)
+ restore_default_window(dev, ddw_restore_token, liobn);
+
out_unlock:
mutex_unlock(&direct_window_init_mutex);
return dma_addr;
if (!pdn || !PCI_DN(pdn)) {
printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: "
"no DMA window found for pci dev=%s dn=%s\n",
- pci_name(dev), dn? dn->full_name : "<null>");
+ pci_name(dev), of_node_full_name(dn));
return;
}
pr_debug(" parent is %s\n", pdn->full_name);