Re: [PATCH 6/9] swiotlb: refactor swiotlb_tbl_map_single
On Mon, Feb 22, 2021 at 02:29:37PM -0500, Konrad Rzeszutek Wilk wrote: > > 'max_slots' should be 'unsigned long' here. Breaks SWIOTLB on RPi4. Do you > > want > > me to send a fix or you prefer editing the patch? > > I can roll it in. Thx! Thanks to both of you! ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
Re: [PATCH 6/9] swiotlb: refactor swiotlb_tbl_map_single
> > +static int find_slots(struct device *dev, size_t alloc_size) > > +{ > > + unsigned long boundary_mask = dma_get_seg_boundary(dev); > > + dma_addr_t tbl_dma_addr = > > + phys_to_dma_unencrypted(dev, io_tlb_start) & boundary_mask; > > + unsigned int max_slots = get_max_slots(boundary_mask); > > 'max_slots' should be 'unsigned long' here. Breaks SWIOTLB on RPi4. Do you > want > me to send a fix or you prefer editing the patch? I can roll it in. Thx! ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
Re: [PATCH 6/9] swiotlb: refactor swiotlb_tbl_map_single
Hi Christoph, On Sun, 2021-02-07 at 17:03 +0100, Christoph Hellwig wrote: > Split out a bunch of a self-contained helpers to make the function easier > to follow. > > Signed-off-by: Christoph Hellwig > --- > kernel/dma/swiotlb.c | 179 +-- > 1 file changed, 89 insertions(+), 90 deletions(-) > > diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c > index b38b1553c4663a..381c24ef1ac1d0 100644 > --- a/kernel/dma/swiotlb.c > +++ b/kernel/dma/swiotlb.c > @@ -468,134 +468,133 @@ static void swiotlb_bounce(phys_addr_t orig_addr, > phys_addr_t tlb_addr, > } > } > > > -phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t > orig_addr, > - size_t mapping_size, size_t alloc_size, > - enum dma_data_direction dir, unsigned long attrs) > -{ > - dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start); > - unsigned long flags; > - phys_addr_t tlb_addr; > - unsigned int nslots, stride, index, wrap; > - int i; > - unsigned long mask; > - unsigned long offset_slots; > - unsigned long max_slots; > - unsigned long tmp_io_tlb_used; > - > - if (no_iotlb_memory) > - panic("Can not allocate SWIOTLB buffer earlier and can't now > provide you with the DMA bounce buffer"); > - > - if (mem_encrypt_active()) > - pr_warn_once("Memory encryption is active and system is using > DMA bounce buffers\n"); > +#define slot_addr(start, idx)((start) + ((idx) << IO_TLB_SHIFT)) > > > - if (mapping_size > alloc_size) { > - dev_warn_once(hwdev, "Invalid sizes (mapping: %zd bytes, alloc: > %zd bytes)", > - mapping_size, alloc_size); > - return (phys_addr_t)DMA_MAPPING_ERROR; > - } > - > - mask = dma_get_seg_boundary(hwdev); > +/* > + * Carefully handle integer overflow which can occur when boundary_mask == > ~0UL. > + */ > +static inline unsigned long get_max_slots(unsigned long boundary_mask) > +{ > + if (boundary_mask == ~0UL) > + return 1UL << (BITS_PER_LONG - IO_TLB_SHIFT); > + return nr_slots(boundary_mask + 1); > +} > > > - tbl_dma_addr &= mask; > +static unsigned int wrap_index(unsigned int index) > +{ > + if (index >= io_tlb_nslabs) > + return 0; > + return index; > +} > > > - offset_slots = nr_slots(tbl_dma_addr); > +/* > + * Find a suitable number of IO TLB entries size that will fit this request > and > + * allocate a buffer from that IO TLB pool. > + */ > +static int find_slots(struct device *dev, size_t alloc_size) > +{ > + unsigned long boundary_mask = dma_get_seg_boundary(dev); > + dma_addr_t tbl_dma_addr = > + phys_to_dma_unencrypted(dev, io_tlb_start) & boundary_mask; > + unsigned int max_slots = get_max_slots(boundary_mask); 'max_slots' should be 'unsigned long' here. Breaks SWIOTLB on RPi4. Do you want me to send a fix or you prefer editing the patch? Regards, Nicolas signature.asc Description: This is a digitally signed message part ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH 6/9] swiotlb: refactor swiotlb_tbl_map_single
Split out a bunch of a self-contained helpers to make the function easier to follow. Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 179 +-- 1 file changed, 89 insertions(+), 90 deletions(-) diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index b38b1553c4663a..381c24ef1ac1d0 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -468,134 +468,133 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr, } } -phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr, - size_t mapping_size, size_t alloc_size, - enum dma_data_direction dir, unsigned long attrs) -{ - dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start); - unsigned long flags; - phys_addr_t tlb_addr; - unsigned int nslots, stride, index, wrap; - int i; - unsigned long mask; - unsigned long offset_slots; - unsigned long max_slots; - unsigned long tmp_io_tlb_used; - - if (no_iotlb_memory) - panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer"); - - if (mem_encrypt_active()) - pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n"); +#define slot_addr(start, idx) ((start) + ((idx) << IO_TLB_SHIFT)) - if (mapping_size > alloc_size) { - dev_warn_once(hwdev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)", - mapping_size, alloc_size); - return (phys_addr_t)DMA_MAPPING_ERROR; - } - - mask = dma_get_seg_boundary(hwdev); +/* + * Carefully handle integer overflow which can occur when boundary_mask == ~0UL. + */ +static inline unsigned long get_max_slots(unsigned long boundary_mask) +{ + if (boundary_mask == ~0UL) + return 1UL << (BITS_PER_LONG - IO_TLB_SHIFT); + return nr_slots(boundary_mask + 1); +} - tbl_dma_addr &= mask; +static unsigned int wrap_index(unsigned int index) +{ + if (index >= io_tlb_nslabs) + return 0; + return index; +} - offset_slots = nr_slots(tbl_dma_addr); +/* + * Find a suitable number of IO TLB entries size that will fit this request and + * allocate a buffer from that IO TLB pool. + */ +static int find_slots(struct device *dev, size_t alloc_size) +{ + unsigned long boundary_mask = dma_get_seg_boundary(dev); + dma_addr_t tbl_dma_addr = + phys_to_dma_unencrypted(dev, io_tlb_start) & boundary_mask; + unsigned int max_slots = get_max_slots(boundary_mask); + unsigned int nslots = nr_slots(alloc_size), stride = 1; + unsigned int index, wrap, count = 0, i; + unsigned long flags; - /* -* Carefully handle integer overflow which can occur when mask == ~0UL. -*/ - max_slots = mask + 1 - ? nr_slots(mask + 1) - : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT); + BUG_ON(!nslots); /* * For mappings greater than or equal to a page, we limit the stride * (and hence alignment) to a page size. */ - nslots = nr_slots(alloc_size); if (alloc_size >= PAGE_SIZE) - stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT)); - else - stride = 1; + stride <<= (PAGE_SHIFT - IO_TLB_SHIFT); - BUG_ON(!nslots); - - /* -* Find suitable number of IO TLB entries size that will fit this -* request and allocate a buffer from that IO TLB pool. -*/ spin_lock_irqsave(&io_tlb_lock, flags); - if (unlikely(nslots > io_tlb_nslabs - io_tlb_used)) goto not_found; - index = ALIGN(io_tlb_index, stride); - if (index >= io_tlb_nslabs) - index = 0; - wrap = index; - + index = wrap = wrap_index(ALIGN(io_tlb_index, stride)); do { - while (iommu_is_span_boundary(index, nslots, offset_slots, - max_slots)) { - index += stride; - if (index >= io_tlb_nslabs) - index = 0; - if (index == wrap) - goto not_found; - } - /* * If we find a slot that indicates we have 'nslots' number of * contiguous buffers, we allocate the buffers from that slot * and mark the entries as '0' indicating unavailable. */ - if (io_tlb_list[index] >= nslots) { - int count = 0; - - for (i = index; i < (int) (index + nslots); i++) - io_tlb_list[i] = 0; - for (i = index - 1; -io_tlb_offset(i) != IO_TLB_SEGSIZ