[POWERPC] Fix mmap of PCI resource with hack for X
The powerpc version of pci_resource_to_user() and associated hooks
used by /proc/bus/pci and /sys/bus/pci mmap have been broken for some
time on machines that don't have a 1:1 mapping of devices (basically
on non-PowerMacs) and have PCI devices above 32 bits.
This attempts to fix it as well as possible.
The rule is supposed to be that pci_resource_to_user() always converts
the resources back into a BAR values since that's what the /proc
interface was supposed to deal with. However, for X to work on
platforms where PCI MMIO is not mapped 1:1, it became a habit of
platforms like powerpc to pass "fixed up" values there since X expects
to be able to use values from /proc/bus/pci/devices as offsets to mmap
of /dev/mem...
So we keep that contraption here, causing also /sys/*/resource to
expose fully absolute MMIO addresses instead of BAR values, which is
ugly, but should still work as long as those are only used to calculate
alignment within a page.
X is still broken when built 32 bits on machines where PCI MMIO can be
above 32-bit space unfortunately.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 2f54cd8..ab5887b 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -1544,7 +1544,7 @@
static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
- unsigned long *offset,
+ resource_size_t *offset,
enum pci_mmap_state mmap_state)
{
struct pci_controller *hose = pci_bus_to_hose(dev->bus->number);
@@ -1556,7 +1556,9 @@
/* If memory, add on the PCI bridge address offset */
if (mmap_state == pci_mmap_mem) {
+#if 0 /* See comment in pci_resource_to_user() for why this is disabled */
*offset += hose->pci_mem_offset;
+#endif
res_bit = IORESOURCE_MEM;
} else {
io_offset = hose->io_base_virt - (void __iomem *)_IO_BASE;
@@ -1624,9 +1626,6 @@
else
prot |= _PAGE_GUARDED;
- printk("PCI map for %s:%llx, prot: %lx\n", pci_name(dev),
- (unsigned long long)rp->start, prot);
-
return __pgprot(prot);
}
@@ -1695,7 +1694,7 @@
enum pci_mmap_state mmap_state,
int write_combine)
{
- unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
+ resource_size_t offset = vma->vm_pgoff << PAGE_SHIFT;
struct resource *rp;
int ret;
@@ -1808,22 +1807,42 @@
resource_size_t *start, resource_size_t *end)
{
struct pci_controller *hose = pci_bus_to_hose(dev->bus->number);
- unsigned long offset = 0;
+ resource_size_t offset = 0;
if (hose == NULL)
return;
if (rsrc->flags & IORESOURCE_IO)
- offset = (void __iomem *)_IO_BASE - hose->io_base_virt
- + hose->io_base_phys;
+ offset = (unsigned long)hose->io_base_virt - _IO_BASE;
- *start = rsrc->start + offset;
- *end = rsrc->end + offset;
+ /* We pass a fully fixed up address to userland for MMIO instead of
+ * a BAR value because X is lame and expects to be able to use that
+ * to pass to /dev/mem !
+ *
+ * That means that we'll have potentially 64 bits values where some
+ * userland apps only expect 32 (like X itself since it thinks only
+ * Sparc has 64 bits MMIO) but if we don't do that, we break it on
+ * 32 bits CHRPs :-(
+ *
+ * Hopefully, the sysfs insterface is immune to that gunk. Once X
+ * has been fixed (and the fix spread enough), we can re-enable the
+ * 2 lines below and pass down a BAR value to userland. In that case
+ * we'll also have to re-enable the matching code in
+ * __pci_mmap_make_offset().
+ *
+ * BenH.
+ */
+#if 0
+ else if (rsrc->flags & IORESOURCE_MEM)
+ offset = hose->pci_mem_offset;
+#endif
+
+ *start = rsrc->start - offset;
+ *end = rsrc->end - offset;
}
-void __init
-pci_init_resource(struct resource *res, unsigned long start, unsigned long end,
- int flags, char *name)
+void __init pci_init_resource(struct resource *res, resource_size_t start,
+ resource_size_t end, int flags, char *name)
{
res->start = start;
res->end = end;
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 6fa9a0a..a6b7692c 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -682,7 +682,7 @@
* Returns negative error code on failure, zero on success.
*/
static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
- unsigned long *offset,
+ resource_size_t *offset,
enum pci_mmap_state mmap_state)
{
struct pci_controller *hose = pci_bus_to_host(dev->bus);
@@ -694,7 +694,9 @@
/* If memory, add on the PCI bridge address offset */
if (mmap_state == pci_mmap_mem) {
+#if 0 /* See comment in pci_resource_to_user() for why this is disabled */
*offset += hose->pci_mem_offset;
+#endif
res_bit = IORESOURCE_MEM;
} else {
io_offset = (unsigned long)hose->io_base_virt - pci_io_base;
@@ -762,9 +764,6 @@
else
prot |= _PAGE_GUARDED;
- printk(KERN_DEBUG "PCI map for %s:%lx, prot: %lx\n", pci_name(dev), rp->start,
- prot);
-
return __pgprot(prot);
}
@@ -832,7 +831,7 @@
int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
enum pci_mmap_state mmap_state, int write_combine)
{
- unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
+ resource_size_t offset = vma->vm_pgoff << PAGE_SHIFT;
struct resource *rp;
int ret;
@@ -1333,20 +1332,41 @@
void pci_resource_to_user(const struct pci_dev *dev, int bar,
const struct resource *rsrc,
- u64 *start, u64 *end)
+ resource_size_t *start, resource_size_t *end)
{
struct pci_controller *hose = pci_bus_to_host(dev->bus);
- unsigned long offset = 0;
+ resource_size_t offset = 0;
if (hose == NULL)
return;
if (rsrc->flags & IORESOURCE_IO)
- offset = pci_io_base - (unsigned long)hose->io_base_virt +
- hose->io_base_phys;
+ offset = (unsigned long)hose->io_base_virt - pci_io_base;
- *start = rsrc->start + offset;
- *end = rsrc->end + offset;
+ /* We pass a fully fixed up address to userland for MMIO instead of
+ * a BAR value because X is lame and expects to be able to use that
+ * to pass to /dev/mem !
+ *
+ * That means that we'll have potentially 64 bits values where some
+ * userland apps only expect 32 (like X itself since it thinks only
+ * Sparc has 64 bits MMIO) but if we don't do that, we break it on
+ * 32 bits CHRPs :-(
+ *
+ * Hopefully, the sysfs insterface is immune to that gunk. Once X
+ * has been fixed (and the fix spread enough), we can re-enable the
+ * 2 lines below and pass down a BAR value to userland. In that case
+ * we'll also have to re-enable the matching code in
+ * __pci_mmap_make_offset().
+ *
+ * BenH.
+ */
+#if 0
+ else if (rsrc->flags & IORESOURCE_MEM)
+ offset = hose->pci_mem_offset;
+#endif
+
+ *start = rsrc->start - offset;
+ *end = rsrc->end - offset;
}
struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node)