[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>

3 files changed, 95 insertions, 33 deletions

diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 2f54cd81dea5..ab5887bff02a 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -1544,7 +1544,7 @@ pci_resource_to_bus(struct pci_dev *pdev, struct resource *res)
 
 
 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 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
 
         /* 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 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
         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 @@ 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;
 
@@ -1808,22 +1807,42 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
                           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;
+
+        /* 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;
+        *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 6fa9a0a5c8db..a6b7692c7269 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -682,7 +682,7 @@ int pci_proc_domain(struct pci_bus *bus)
  * 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 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
 
         /* 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 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
         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 @@ pgprot_t pci_phys_mem_access_prot(struct file *file,
 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 @@ EXPORT_SYMBOL(pci_read_irq_line);
 
 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;
+
+        /* 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;
+        *start = rsrc->start - offset;
+        *end = rsrc->end - offset;
 }
 
 struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node)
diff --git a/arch/ppc/kernel/pci.c b/arch/ppc/kernel/pci.c
index 63808e01cb0b..5e723c4c2571 100644
--- a/arch/ppc/kernel/pci.c
+++ b/arch/ppc/kernel/pci.c
@@ -879,7 +879,7 @@ pci_resource_to_bus(struct pci_dev *pdev, struct resource *res)
 
 
 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);
@@ -891,7 +891,9 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
 
         /* 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 - ___IO_BASE;
@@ -1030,7 +1032,7 @@ 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;
 
@@ -1132,21 +1134,42 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
                           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 = ___IO_BASE - hose->io_base_virt + hose->io_base_phys;
+                offset = (unsigned long)hose->io_base_virt - _IO_BASE;
+
+        /* 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;
+        *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;