diff options
author | FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> | 2008-03-28 14:27:03 -0700 |
---|---|---|
committer | Tony Luck <tony.luck@intel.com> | 2008-04-09 10:37:21 -0700 |
commit | b34eb53cdcb4f49fd31d78d0e385240820ed9063 (patch) | |
tree | fc0bf8ab64fb703bd9a7c104973cd488719f52ab /arch | |
parent | 34e1ceb1881ec895ad9b1b52d073f414f3aa87a9 (diff) |
[IA64] make IOMMU respect the segment boundary limits
IA64's IOMMU implementation allocates memory areas spanning LLD's segment
boundary limit. It forces low level drivers to have a workaround to adjust
scatter lists that the IOMMU builds.
We are in the process of making all the IOMMUs respect the segment boundary
limits to remove such work around in LLDs. This patch is for IA64's IOMMU.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Diffstat (limited to 'arch')
-rw-r--r-- | arch/ia64/Kconfig | 3 | ||||
-rw-r--r-- | arch/ia64/hp/common/sba_iommu.c | 56 |
2 files changed, 42 insertions, 17 deletions
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 8fa3faf5ef1b..1b73ffe746d9 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -611,6 +611,9 @@ config IRQ_PER_CPU bool default y +config IOMMU_HELPER + def_bool (IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB || IA64_GENERIC) + source "arch/ia64/hp/sim/Kconfig" source "arch/ia64/Kconfig.debug" diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index 523eae6d3e49..9409de5c9441 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -35,6 +35,7 @@ #include <linux/nodemask.h> #include <linux/bitops.h> /* hweight64() */ #include <linux/crash_dump.h> +#include <linux/iommu-helper.h> #include <asm/delay.h> /* ia64_get_itc() */ #include <asm/io.h> @@ -460,6 +461,13 @@ get_iovp_order (unsigned long size) return order; } +static unsigned long ptr_to_pide(struct ioc *ioc, unsigned long *res_ptr, + unsigned int bitshiftcnt) +{ + return (((unsigned long)res_ptr - (unsigned long)ioc->res_map) << 3) + + bitshiftcnt; +} + /** * sba_search_bitmap - find free space in IO PDIR resource bitmap * @ioc: IO MMU structure which owns the pdir we are interested in. @@ -471,15 +479,25 @@ get_iovp_order (unsigned long size) * Cool perf optimization: search for log2(size) bits at a time. */ static SBA_INLINE unsigned long -sba_search_bitmap(struct ioc *ioc, unsigned long bits_wanted, int use_hint) +sba_search_bitmap(struct ioc *ioc, struct device *dev, + unsigned long bits_wanted, int use_hint) { unsigned long *res_ptr; unsigned long *res_end = (unsigned long *) &(ioc->res_map[ioc->res_size]); - unsigned long flags, pide = ~0UL; + unsigned long flags, pide = ~0UL, tpide; + unsigned long boundary_size; + unsigned long shift; + int ret; ASSERT(((unsigned long) ioc->res_hint & (sizeof(unsigned long) - 1UL)) == 0); ASSERT(res_ptr < res_end); + boundary_size = (unsigned long long)dma_get_seg_boundary(dev) + 1; + boundary_size = ALIGN(boundary_size, 1ULL << iovp_shift) >> iovp_shift; + + BUG_ON(ioc->ibase & ~iovp_mask); + shift = ioc->ibase >> iovp_shift; + spin_lock_irqsave(&ioc->res_lock, flags); /* Allow caller to force a search through the entire resource space */ @@ -504,9 +522,7 @@ sba_search_bitmap(struct ioc *ioc, unsigned long bits_wanted, int use_hint) if (likely(*res_ptr != ~0UL)) { bitshiftcnt = ffz(*res_ptr); *res_ptr |= (1UL << bitshiftcnt); - pide = ((unsigned long)res_ptr - (unsigned long)ioc->res_map); - pide <<= 3; /* convert to bit address */ - pide += bitshiftcnt; + pide = ptr_to_pide(ioc, res_ptr, bitshiftcnt); ioc->res_bitshift = bitshiftcnt + bits_wanted; goto found_it; } @@ -535,11 +551,13 @@ sba_search_bitmap(struct ioc *ioc, unsigned long bits_wanted, int use_hint) DBG_RES(" %p %lx %lx\n", res_ptr, mask, *res_ptr); ASSERT(0 != mask); for (; mask ; mask <<= o, bitshiftcnt += o) { - if(0 == ((*res_ptr) & mask)) { + tpide = ptr_to_pide(ioc, res_ptr, bitshiftcnt); + ret = iommu_is_span_boundary(tpide, bits_wanted, + shift, + boundary_size); + if ((0 == ((*res_ptr) & mask)) && !ret) { *res_ptr |= mask; /* mark resources busy! */ - pide = ((unsigned long)res_ptr - (unsigned long)ioc->res_map); - pide <<= 3; /* convert to bit address */ - pide += bitshiftcnt; + pide = tpide; ioc->res_bitshift = bitshiftcnt + bits_wanted; goto found_it; } @@ -560,6 +578,11 @@ sba_search_bitmap(struct ioc *ioc, unsigned long bits_wanted, int use_hint) end = res_end - qwords; for (; res_ptr < end; res_ptr++) { + tpide = ptr_to_pide(ioc, res_ptr, 0); + ret = iommu_is_span_boundary(tpide, bits_wanted, + shift, boundary_size); + if (ret) + goto next_ptr; for (i = 0 ; i < qwords ; i++) { if (res_ptr[i] != 0) goto next_ptr; @@ -572,8 +595,7 @@ sba_search_bitmap(struct ioc *ioc, unsigned long bits_wanted, int use_hint) res_ptr[i] = ~0UL; res_ptr[i] |= RESMAP_MASK(bits); - pide = ((unsigned long)res_ptr - (unsigned long)ioc->res_map); - pide <<= 3; /* convert to bit address */ + pide = tpide; res_ptr += qwords; ioc->res_bitshift = bits; goto found_it; @@ -605,7 +627,7 @@ found_it: * resource bit map. */ static int -sba_alloc_range(struct ioc *ioc, size_t size) +sba_alloc_range(struct ioc *ioc, struct device *dev, size_t size) { unsigned int pages_needed = size >> iovp_shift; #ifdef PDIR_SEARCH_TIMING @@ -622,9 +644,9 @@ sba_alloc_range(struct ioc *ioc, size_t size) /* ** "seek and ye shall find"...praying never hurts either... */ - pide = sba_search_bitmap(ioc, pages_needed, 1); + pide = sba_search_bitmap(ioc, dev, pages_needed, 1); if (unlikely(pide >= (ioc->res_size << 3))) { - pide = sba_search_bitmap(ioc, pages_needed, 0); + pide = sba_search_bitmap(ioc, dev, pages_needed, 0); if (unlikely(pide >= (ioc->res_size << 3))) { #if DELAYED_RESOURCE_CNT > 0 unsigned long flags; @@ -653,7 +675,7 @@ sba_alloc_range(struct ioc *ioc, size_t size) } spin_unlock_irqrestore(&ioc->saved_lock, flags); - pide = sba_search_bitmap(ioc, pages_needed, 0); + pide = sba_search_bitmap(ioc, dev, pages_needed, 0); if (unlikely(pide >= (ioc->res_size << 3))) panic(__FILE__ ": I/O MMU @ %p is out of mapping resources\n", ioc->ioc_hpa); @@ -936,7 +958,7 @@ sba_map_single(struct device *dev, void *addr, size_t size, int dir) spin_unlock_irqrestore(&ioc->res_lock, flags); #endif - pide = sba_alloc_range(ioc, size); + pide = sba_alloc_range(ioc, dev, size); iovp = (dma_addr_t) pide << iovp_shift; @@ -1373,7 +1395,7 @@ sba_coalesce_chunks(struct ioc *ioc, struct device *dev, dma_len = (dma_len + dma_offset + ~iovp_mask) & iovp_mask; ASSERT(dma_len <= DMA_CHUNK_SIZE); dma_sg->dma_address = (dma_addr_t) (PIDE_FLAG - | (sba_alloc_range(ioc, dma_len) << iovp_shift) + | (sba_alloc_range(ioc, dev, dma_len) << iovp_shift) | dma_offset); n_mappings++; } |