[POWERPC] Use 4kB iommu pages even on 64kB-page systems
The 10Gigabit ethernet device drivers appear to be able to chew
up all 256MB of TCE mappings on pSeries systems, as evidenced by
numerous error messages:
iommu_alloc failed, tbl c0000000010d5c48 vaddr c0000000d875eff0 npages 1
Some experimentation indicates that this is essentially because
one 1500 byte ethernet MTU gets mapped as a 64K DMA region when
the large 64K pages are enabled. Thus, it doesn't take much to
exhaust all of the available DMA mappings for a high-speed card.
This patch changes the iommu allocator to work with its own
unique, distinct page size. Although the patch is long, its
actually quite simple: it just #defines a distinct IOMMU_PAGE_SIZE
and then uses this in all the places that matter.
As a side effect, it also dramatically improves network performance
on platforms with H-calls on iommu translation inserts/removes (since
we no longer call it 16 times for a 1500 bytes packet when the iommu HW
is still 4k).
In the future, we might want to make the IOMMU_PAGE_SIZE a variable
in the iommu_table instance, thus allowing support for different HW
page sizes in the iommu itself.
Signed-off-by: Linas Vepstas <linas@austin.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Olof Johansson <olof@lixom.net>
Acked-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index f88a2a6..ba6b725 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -47,6 +47,17 @@
static int novmerge = 1;
#endif
+static inline unsigned long iommu_num_pages(unsigned long vaddr,
+ unsigned long slen)
+{
+ unsigned long npages;
+
+ npages = IOMMU_PAGE_ALIGN(vaddr + slen) - (vaddr & IOMMU_PAGE_MASK);
+ npages >>= IOMMU_PAGE_SHIFT;
+
+ return npages;
+}
+
static int __init setup_iommu(char *str)
{
if (!strcmp(str, "novmerge"))
@@ -178,10 +189,10 @@
}
entry += tbl->it_offset; /* Offset into real TCE table */
- ret = entry << PAGE_SHIFT; /* Set the return dma address */
+ ret = entry << IOMMU_PAGE_SHIFT; /* Set the return dma address */
/* Put the TCEs in the HW table */
- ppc_md.tce_build(tbl, entry, npages, (unsigned long)page & PAGE_MASK,
+ ppc_md.tce_build(tbl, entry, npages, (unsigned long)page & IOMMU_PAGE_MASK,
direction);
@@ -203,7 +214,7 @@
unsigned long entry, free_entry;
unsigned long i;
- entry = dma_addr >> PAGE_SHIFT;
+ entry = dma_addr >> IOMMU_PAGE_SHIFT;
free_entry = entry - tbl->it_offset;
if (((free_entry + npages) > tbl->it_size) ||
@@ -270,7 +281,7 @@
/* Init first segment length for backout at failure */
outs->dma_length = 0;
- DBG("mapping %d elements:\n", nelems);
+ DBG("sg mapping %d elements:\n", nelems);
spin_lock_irqsave(&(tbl->it_lock), flags);
@@ -285,9 +296,8 @@
}
/* Allocate iommu entries for that segment */
vaddr = (unsigned long)page_address(s->page) + s->offset;
- npages = PAGE_ALIGN(vaddr + slen) - (vaddr & PAGE_MASK);
- npages >>= PAGE_SHIFT;
- entry = iommu_range_alloc(tbl, npages, &handle, mask >> PAGE_SHIFT, 0);
+ npages = iommu_num_pages(vaddr, slen);
+ entry = iommu_range_alloc(tbl, npages, &handle, mask >> IOMMU_PAGE_SHIFT, 0);
DBG(" - vaddr: %lx, size: %lx\n", vaddr, slen);
@@ -301,14 +311,14 @@
/* Convert entry to a dma_addr_t */
entry += tbl->it_offset;
- dma_addr = entry << PAGE_SHIFT;
- dma_addr |= s->offset;
+ dma_addr = entry << IOMMU_PAGE_SHIFT;
+ dma_addr |= (s->offset & ~IOMMU_PAGE_MASK);
- DBG(" - %lx pages, entry: %lx, dma_addr: %lx\n",
+ DBG(" - %lu pages, entry: %lx, dma_addr: %lx\n",
npages, entry, dma_addr);
/* Insert into HW table */
- ppc_md.tce_build(tbl, entry, npages, vaddr & PAGE_MASK, direction);
+ ppc_md.tce_build(tbl, entry, npages, vaddr & IOMMU_PAGE_MASK, direction);
/* If we are in an open segment, try merging */
if (segstart != s) {
@@ -323,7 +333,7 @@
DBG(" can't merge, new segment.\n");
} else {
outs->dma_length += s->length;
- DBG(" merged, new len: %lx\n", outs->dma_length);
+ DBG(" merged, new len: %ux\n", outs->dma_length);
}
}
@@ -367,9 +377,8 @@
if (s->dma_length != 0) {
unsigned long vaddr, npages;
- vaddr = s->dma_address & PAGE_MASK;
- npages = (PAGE_ALIGN(s->dma_address + s->dma_length) - vaddr)
- >> PAGE_SHIFT;
+ vaddr = s->dma_address & IOMMU_PAGE_MASK;
+ npages = iommu_num_pages(s->dma_address, s->dma_length);
__iommu_free(tbl, vaddr, npages);
s->dma_address = DMA_ERROR_CODE;
s->dma_length = 0;
@@ -398,8 +407,7 @@
if (sglist->dma_length == 0)
break;
- npages = (PAGE_ALIGN(dma_handle + sglist->dma_length)
- - (dma_handle & PAGE_MASK)) >> PAGE_SHIFT;
+ npages = iommu_num_pages(dma_handle,sglist->dma_length);
__iommu_free(tbl, dma_handle, npages);
sglist++;
}
@@ -532,12 +540,11 @@
BUG_ON(direction == DMA_NONE);
uaddr = (unsigned long)vaddr;
- npages = PAGE_ALIGN(uaddr + size) - (uaddr & PAGE_MASK);
- npages >>= PAGE_SHIFT;
+ npages = iommu_num_pages(uaddr, size);
if (tbl) {
dma_handle = iommu_alloc(tbl, vaddr, npages, direction,
- mask >> PAGE_SHIFT, 0);
+ mask >> IOMMU_PAGE_SHIFT, 0);
if (dma_handle == DMA_ERROR_CODE) {
if (printk_ratelimit()) {
printk(KERN_INFO "iommu_alloc failed, "
@@ -545,7 +552,7 @@
tbl, vaddr, npages);
}
} else
- dma_handle |= (uaddr & ~PAGE_MASK);
+ dma_handle |= (uaddr & ~IOMMU_PAGE_MASK);
}
return dma_handle;
@@ -554,11 +561,14 @@
void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle,
size_t size, enum dma_data_direction direction)
{
+ unsigned int npages;
+
BUG_ON(direction == DMA_NONE);
- if (tbl)
- iommu_free(tbl, dma_handle, (PAGE_ALIGN(dma_handle + size) -
- (dma_handle & PAGE_MASK)) >> PAGE_SHIFT);
+ if (tbl) {
+ npages = iommu_num_pages(dma_handle, size);
+ iommu_free(tbl, dma_handle, npages);
+ }
}
/* Allocates a contiguous real buffer and creates mappings over it.
@@ -570,11 +580,11 @@
{
void *ret = NULL;
dma_addr_t mapping;
- unsigned int npages, order;
+ unsigned int order;
+ unsigned int nio_pages, io_order;
struct page *page;
size = PAGE_ALIGN(size);
- npages = size >> PAGE_SHIFT;
order = get_order(size);
/*
@@ -598,8 +608,10 @@
memset(ret, 0, size);
/* Set up tces to cover the allocated range */
- mapping = iommu_alloc(tbl, ret, npages, DMA_BIDIRECTIONAL,
- mask >> PAGE_SHIFT, order);
+ nio_pages = size >> IOMMU_PAGE_SHIFT;
+ io_order = get_iommu_order(size);
+ mapping = iommu_alloc(tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
+ mask >> IOMMU_PAGE_SHIFT, io_order);
if (mapping == DMA_ERROR_CODE) {
free_pages((unsigned long)ret, order);
return NULL;
@@ -611,12 +623,13 @@
void iommu_free_coherent(struct iommu_table *tbl, size_t size,
void *vaddr, dma_addr_t dma_handle)
{
- unsigned int npages;
-
if (tbl) {
+ unsigned int nio_pages;
+
size = PAGE_ALIGN(size);
- npages = size >> PAGE_SHIFT;
- iommu_free(tbl, dma_handle, npages);
+ nio_pages = size >> IOMMU_PAGE_SHIFT;
+ iommu_free(tbl, dma_handle, nio_pages);
+ size = PAGE_ALIGN(size);
free_pages((unsigned long)vaddr, get_order(size));
}
}