Re: [PATCH] modify the IO_TLB_SEGSIZE to io_tlb_segsize configurable as flexible requirement about SW-IOMMU.

From: Konrad Rzeszutek Wilk
Date: Thu Feb 05 2015 - 14:33:40 EST

Next message: Paul E. McKenney: "Re: linux-next: Tree for Feb 4"
Previous message: Stephen Boyd: "Re: [PATCH 2/2] clk: Fix OOPS calling hlist_del on an already poisoned hlist."
In reply to: Paul Bolle: "Re: [PATCH] modify the IO_TLB_SEGSIZE to io_tlb_segsize configurable as flexible requirement about SW-IOMMU."
Next in thread: Wang, Xiaoming: "RE: [PATCH] modify the IO_TLB_SEGSIZE to io_tlb_segsize configurable as flexible requirement about SW-IOMMU."
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

On Fri, Feb 06, 2015 at 07:01:14AM +0800, xiaomin1 wrote:
> The maximum of SW-IOMMU is limited to 2^11*128 = 256K.
> While in different platform and different requirements this seems improper.
> So modify the IO_TLB_SEGSIZE to io_tlb_segsize as configurable is make sense.

More details please. What is the issue you are hitting?

>
> Signed-off-by: Chuansheng Liu <chuansheng.liu@xxxxxxxxx>
> Signed-off-by: Zhang Dongxing <dongxing.zhang@xxxxxxxxx>
> Signed-off-by: xiaomin1 <xiaoming.wang@xxxxxxxxx>
> ---
> arch/mips/cavium-octeon/dma-octeon.c | 2 +-
> arch/mips/netlogic/common/nlm-dma.c | 2 +-
> drivers/xen/swiotlb-xen.c | 6 +++---
> include/linux/swiotlb.h | 8 +------
> lib/swiotlb.c | 39 ++++++++++++++++++++++++----------
> 5 files changed, 34 insertions(+), 23 deletions(-)
>
> diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
> index 3778655..a521af6 100644
> --- a/arch/mips/cavium-octeon/dma-octeon.c
> +++ b/arch/mips/cavium-octeon/dma-octeon.c
> @@ -312,7 +312,7 @@ void __init plat_swiotlb_setup(void)
> swiotlbsize = 64 * (1<<20);
> #endif
> swiotlb_nslabs = swiotlbsize >> IO_TLB_SHIFT;
> - swiotlb_nslabs = ALIGN(swiotlb_nslabs, IO_TLB_SEGSIZE);
> + swiotlb_nslabs = ALIGN(swiotlb_nslabs, io_tlb_segsize);
> swiotlbsize = swiotlb_nslabs << IO_TLB_SHIFT;
>
> octeon_swiotlb = alloc_bootmem_low_pages(swiotlbsize);
> diff --git a/arch/mips/netlogic/common/nlm-dma.c b/arch/mips/netlogic/common/nlm-dma.c
> index f3d4ae8..eeffa8f 100644
> --- a/arch/mips/netlogic/common/nlm-dma.c
> +++ b/arch/mips/netlogic/common/nlm-dma.c
> @@ -99,7 +99,7 @@ void __init plat_swiotlb_setup(void)
>
> swiotlbsize = 1 << 20; /* 1 MB for now */
> swiotlb_nslabs = swiotlbsize >> IO_TLB_SHIFT;
> - swiotlb_nslabs = ALIGN(swiotlb_nslabs, IO_TLB_SEGSIZE);
> + swiotlb_nslabs = ALIGN(swiotlb_nslabs, io_tlb_segsize);
> swiotlbsize = swiotlb_nslabs << IO_TLB_SHIFT;
>
> nlm_swiotlb = alloc_bootmem_low_pages(swiotlbsize);
> diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
> index 810ad41..3b3e9fe 100644
> --- a/drivers/xen/swiotlb-xen.c
> +++ b/drivers/xen/swiotlb-xen.c
> @@ -164,11 +164,11 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
> dma_addr_t dma_handle;
> phys_addr_t p = virt_to_phys(buf);
>
> - dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT;
> + dma_bits = get_order(io_tlb_segsize << IO_TLB_SHIFT) + PAGE_SHIFT;
>
> i = 0;
> do {
> - int slabs = min(nslabs - i, (unsigned long)IO_TLB_SEGSIZE);
> + int slabs = min(nslabs - i, (unsigned long)io_tlb_segsize);
>
> do {
> rc = xen_create_contiguous_region(
> @@ -187,7 +187,7 @@ static unsigned long xen_set_nslabs(unsigned long nr_tbl)
> {
> if (!nr_tbl) {
> xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
> - xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
> + xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, io_tlb_segsize);
> } else
> xen_io_tlb_nslabs = nr_tbl;
>
> diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
> index e7a018e..13506db 100644
> --- a/include/linux/swiotlb.h
> +++ b/include/linux/swiotlb.h
> @@ -8,13 +8,7 @@ struct dma_attrs;
> struct scatterlist;
>
> extern int swiotlb_force;
> -
> -/*
> - * Maximum allowable number of contiguous slabs to map,
> - * must be a power of 2. What is the appropriate value ?
> - * The complexity of {map,unmap}_single is linearly dependent on this value.
> - */
> -#define IO_TLB_SEGSIZE 128
> +extern int io_tlb_segsize;
>
> /*
> * log of the size of each IO TLB slab. The number of slabs is command line
> diff --git a/lib/swiotlb.c b/lib/swiotlb.c
> index 4abda07..50c415a 100644
> --- a/lib/swiotlb.c
> +++ b/lib/swiotlb.c
> @@ -56,6 +56,15 @@
> int swiotlb_force;
>
> /*
> + * Maximum allowable number of contiguous slabs to map,
> + * must be a power of 2. What is the appropriate value ?
> + * define io_tlb_segsize as a parameter
> + * which can be changed dynamically in config file for special usage.
> + * The complexity of {map,unmap}_single is linearly dependent on this value.
> + */
> +int io_tlb_segsize = 128;
> +
> +/*
> * Used to do a quick range check in swiotlb_tbl_unmap_single and
> * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
> * API.
> @@ -97,12 +106,20 @@ static DEFINE_SPINLOCK(io_tlb_lock);
> static int late_alloc;
>
> static int __init
> +setup_io_tlb_segsize(char *str)
> +{
> + get_option(&str, &io_tlb_segsize);
> + return 0;
> +}
> +__setup("io_tlb_segsize=", setup_io_tlb_segsize);
> +
> +static int __init
> setup_io_tlb_npages(char *str)
> {
> if (isdigit(*str)) {
> io_tlb_nslabs = simple_strtoul(str, &str, 0);
> - /* avoid tail segment of size < IO_TLB_SEGSIZE */
> - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
> + /* avoid tail segment of size < io_tlb_segsize */
> + io_tlb_nslabs = ALIGN(io_tlb_nslabs, io_tlb_segsize);
> }
> if (*str == ',')
> ++str;
> @@ -183,7 +200,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
>
> /*
> * Allocate and initialize the free list array. This array is used
> - * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
> + * to find contiguous free memory regions of size up to io_tlb_segsize
> * between io_tlb_start and io_tlb_end.
> */
> io_tlb_list = memblock_virt_alloc(
> @@ -193,7 +210,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
> PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)),
> PAGE_SIZE);
> for (i = 0; i < io_tlb_nslabs; i++) {
> - io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
> + io_tlb_list[i] = io_tlb_segsize - OFFSET(i, io_tlb_segsize);
> io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
> }
> io_tlb_index = 0;
> @@ -217,7 +234,7 @@ swiotlb_init(int verbose)
>
> if (!io_tlb_nslabs) {
> io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
> - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
> + io_tlb_nslabs = ALIGN(io_tlb_nslabs, io_tlb_segsize);
> }
>
> bytes = io_tlb_nslabs << IO_TLB_SHIFT;
> @@ -249,7 +266,7 @@ swiotlb_late_init_with_default_size(size_t default_size)
>
> if (!io_tlb_nslabs) {
> io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
> - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
> + io_tlb_nslabs = ALIGN(io_tlb_nslabs, io_tlb_segsize);
> }
>
> /*
> @@ -308,7 +325,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
>
> /*
> * Allocate and initialize the free list array. This array is used
> - * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
> + * to find contiguous free memory regions of size up to io_tlb_segsize
> * between io_tlb_start and io_tlb_end.
> */
> io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL,
> @@ -324,7 +341,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
> goto cleanup4;
>
> for (i = 0; i < io_tlb_nslabs; i++) {
> - io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
> + io_tlb_list[i] = io_tlb_segsize - OFFSET(i, io_tlb_segsize);
> io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
> }
> io_tlb_index = 0;
> @@ -493,7 +510,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
>
> for (i = index; i < (int) (index + nslots); i++)
> io_tlb_list[i] = 0;
> - for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--)
> + for (i = index - 1; (OFFSET(i, io_tlb_segsize) != io_tlb_segsize - 1) && io_tlb_list[i]; i--)
> io_tlb_list[i] = ++count;
> tlb_addr = io_tlb_start + (index << IO_TLB_SHIFT);
>
> @@ -571,7 +588,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
> */
> spin_lock_irqsave(&io_tlb_lock, flags);
> {
> - count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ?
> + count = ((index + nslots) < ALIGN(index + 1, io_tlb_segsize) ?
> io_tlb_list[index + nslots] : 0);
> /*
> * Step 1: return the slots to the free list, merging the
> @@ -585,7 +602,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
> * Step 2: merge the returned slots with the preceding slots,
> * if available (non zero)
> */
> - for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
> + for (i = index - 1; (OFFSET(i, io_tlb_segsize) != io_tlb_segsize -1) && io_tlb_list[i]; i--)
> io_tlb_list[i] = ++count;
> }
> spin_unlock_irqrestore(&io_tlb_lock, flags);
> --
> 1.7.9.5
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Paul E. McKenney: "Re: linux-next: Tree for Feb 4"
Previous message: Stephen Boyd: "Re: [PATCH 2/2] clk: Fix OOPS calling hlist_del on an already poisoned hlist."
In reply to: Paul Bolle: "Re: [PATCH] modify the IO_TLB_SEGSIZE to io_tlb_segsize configurable as flexible requirement about SW-IOMMU."
Next in thread: Wang, Xiaoming: "RE: [PATCH] modify the IO_TLB_SEGSIZE to io_tlb_segsize configurable as flexible requirement about SW-IOMMU."
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]