Re: [BUG] Bad page map in process ibv_devinfo

[Lukas Razik <linux-GLgANOly0l1BDLzU/O5InQ@public.gmane.org>]

David Miller <davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org> wrote:

> Can someone with the effected hardware please test this?
> 
> --------------------
> [PATCH] sparc: Kill custom io_remap_pfn_range().
> 
> To handle the large physical addresses, just make a simple wrapper
> around remap_pfn_range() like MIPS does.
> 
> Signed-off-by: David S. Miller <davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org>
> ---
> arch/sparc/include/asm/pgtable_32.h |   20 ++++-
> arch/sparc/include/asm/pgtable_64.h |   20 ++++-
> arch/sparc/mm/Makefile              |    1 -
> arch/sparc/mm/generic_32.c          |   99 ---------------------
> arch/sparc/mm/generic_64.c          |  165 -----------------------------------
> 5 files changed, 32 insertions(+), 273 deletions(-)
> delete mode 100644 arch/sparc/mm/generic_32.c
> delete mode 100644 arch/sparc/mm/generic_64.c
> 
> diff --git a/arch/sparc/include/asm/pgtable_32.h 
> b/arch/sparc/include/asm/pgtable_32.h
> index 5b31a8e..a790cc6 100644
> --- a/arch/sparc/include/asm/pgtable_32.h
> +++ b/arch/sparc/include/asm/pgtable_32.h
> @@ -431,10 +431,6 @@ extern unsigned long *sparc_valid_addr_bitmap;
> #define kern_addr_valid(addr) \
>     (test_bit(__pa((unsigned long)(addr))>>20, sparc_valid_addr_bitmap))
> 
> -extern int io_remap_pfn_range(struct vm_area_struct *vma,
> -                  unsigned long from, unsigned long pfn,
> -                  unsigned long size, pgprot_t prot);
> -
> /*
>   * For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> 
> in
>   * its high 4 bits.  These macros/functions put it there or get it from there.
> @@ -443,6 +439,22 @@ extern int io_remap_pfn_range(struct vm_area_struct *vma,
> #define GET_IOSPACE(pfn)        (pfn >> (BITS_PER_LONG - 4))
> #define GET_PFN(pfn)            (pfn & 0x0fffffffUL)
> 
> +extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned 
> long,
> +               unsigned long, pgprot_t);
> +
> +static inline int io_remap_pfn_range(struct vm_area_struct *vma,
> +                     unsigned long from, unsigned long pfn,
> +                     unsigned long size, pgprot_t prot)
> +{
> +    unsigned long long offset, space, phys_base;
> +
> +    offset = ((unsigned long long) GET_PFN(pfn)) << PAGE_SHIFT;
> +    space = GET_IOSPACE(pfn);
> +    phys_base = offset | (space << 32ULL);
> +
> +    return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, 
> prot);
> +}
> +
> #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
> #define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
> ({                                      \
> diff --git a/arch/sparc/include/asm/pgtable_64.h 
> b/arch/sparc/include/asm/pgtable_64.h
> index adf8932..38ebb2c 100644
> --- a/arch/sparc/include/asm/pgtable_64.h
> +++ b/arch/sparc/include/asm/pgtable_64.h
> @@ -757,10 +757,6 @@ static inline bool kern_addr_valid(unsigned long addr)
> 
> extern int page_in_phys_avail(unsigned long paddr);
> 
> -extern int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
> -                   unsigned long pfn,
> -                   unsigned long size, pgprot_t prot);
> -
> /*
>   * For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> 
> in
>   * its high 4 bits.  These macros/functions put it there or get it from there.
> @@ -769,6 +765,22 @@ extern int io_remap_pfn_range(struct vm_area_struct *vma, 
> unsigned long from,
> #define GET_IOSPACE(pfn)        (pfn >> (BITS_PER_LONG - 4))
> #define GET_PFN(pfn)            (pfn & 0x0fffffffffffffffUL)
> 
> +extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned 
> long,
> +               unsigned long, pgprot_t);
> +
> +static inline int io_remap_pfn_range(struct vm_area_struct *vma,
> +                     unsigned long from, unsigned long pfn,
> +                     unsigned long size, pgprot_t prot)
> +{
> +    unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
> +    int space = GET_IOSPACE(pfn);
> +    unsigned long phys_base;
> +
> +    phys_base = offset | (((unsigned long) space) << 32UL);
> +
> +    return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, 
> prot);
> +}
> +
> #include <asm-generic/pgtable.h>
> 
> /* We provide our own get_unmapped_area to cope with VA holes and
> diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
> index e3cda21..301421c 100644
> --- a/arch/sparc/mm/Makefile
> +++ b/arch/sparc/mm/Makefile
> @@ -8,7 +8,6 @@ obj-$(CONFIG_SPARC64)   += ultra.o tlb.o tsb.o gup.o
> obj-y                   += fault_$(BITS).o
> obj-y                   += init_$(BITS).o
> obj-$(CONFIG_SPARC32)   += loadmmu.o
> -obj-y                   += generic_$(BITS).o
> obj-$(CONFIG_SPARC32)   += extable.o btfixup.o srmmu.o iommu.o io-unit.o
> obj-$(CONFIG_SPARC32)   += hypersparc.o viking.o tsunami.o swift.o
> obj-$(CONFIG_SPARC_LEON)+= leon_mm.o
> diff --git a/arch/sparc/mm/generic_32.c b/arch/sparc/mm/generic_32.c
> deleted file mode 100644
> index 6ca39a6..0000000
> --- a/arch/sparc/mm/generic_32.c
> +++ /dev/null
> @@ -1,99 +0,0 @@
> -/*
> - * generic.c: Generic Sparc mm routines that are not dependent upon
> - *            MMU type but are Sparc specific.
> - *
> - * Copyright (C) 1996 David S. Miller (davem-CVlFQpJstH5+CIkdHa1UOg@public.gmane.org)
> - */
> -
> -#include <linux/kernel.h>
> -#include <linux/mm.h>
> -#include <linux/swap.h>
> -#include <linux/pagemap.h>
> -#include <linux/export.h>
> -
> -#include <asm/pgalloc.h>
> -#include <asm/pgtable.h>
> -#include <asm/page.h>
> -#include <asm/cacheflush.h>
> -#include <asm/tlbflush.h>
> -
> -/* Remap IO memory, the same way as remap_pfn_range(), but use
> - * the obio memory space.
> - *
> - * They use a pgprot that sets PAGE_IO and does not check the
> - * mem_map table as this is independent of normal memory.
> - */
> -static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte, 
> unsigned long address, unsigned long size,
> -    unsigned long offset, pgprot_t prot, int space)
> -{
> -    unsigned long end;
> -
> -    address &= ~PMD_MASK;
> -    end = address + size;
> -    if (end > PMD_SIZE)
> -        end = PMD_SIZE;
> -    do {
> -        set_pte_at(mm, address, pte, mk_pte_io(offset, prot, space));
> -        address += PAGE_SIZE;
> -        offset += PAGE_SIZE;
> -        pte++;
> -    } while (address < end);
> -}
> -
> -static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, 
> unsigned long address, unsigned long size,
> -    unsigned long offset, pgprot_t prot, int space)
> -{
> -    unsigned long end;
> -
> -    address &= ~PGDIR_MASK;
> -    end = address + size;
> -    if (end > PGDIR_SIZE)
> -        end = PGDIR_SIZE;
> -    offset -= address;
> -    do {
> -        pte_t *pte = pte_alloc_map(mm, NULL, pmd, address);
> -        if (!pte)
> -            return -ENOMEM;
> -        io_remap_pte_range(mm, pte, address, end - address, address + offset, 
> prot, space);
> -        address = (address + PMD_SIZE) & PMD_MASK;
> -        pmd++;
> -    } while (address < end);
> -    return 0;
> -}
> -
> -int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
> -               unsigned long pfn, unsigned long size, pgprot_t prot)
> -{
> -    int error = 0;
> -    pgd_t * dir;
> -    unsigned long beg = from;
> -    unsigned long end = from + size;
> -    struct mm_struct *mm = vma->vm_mm;
> -    int space = GET_IOSPACE(pfn);
> -    unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
> -
> -    /* See comment in mm/memory.c remap_pfn_range */
> -    vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
> -    vma->vm_pgoff = (offset >> PAGE_SHIFT) |
> -        ((unsigned long)space << 28UL);
> -
> -    offset -= from;
> -    dir = pgd_offset(mm, from);
> -    flush_cache_range(vma, beg, end);
> -
> -    while (from < end) {
> -        pmd_t *pmd = pmd_alloc(mm, dir, from);
> -        error = -ENOMEM;
> -        if (!pmd)
> -            break;
> -        error = io_remap_pmd_range(mm, pmd, from, end - from, offset + from, 
> prot, space);
> -        if (error)
> -            break;
> -        from = (from + PGDIR_SIZE) & PGDIR_MASK;
> -        dir++;
> -    }
> -
> -    flush_tlb_range(vma, beg, end);
> -    return error;
> -}
> -EXPORT_SYMBOL(io_remap_pfn_range);
> diff --git a/arch/sparc/mm/generic_64.c b/arch/sparc/mm/generic_64.c
> deleted file mode 100644
> index 9b357dd..0000000
> --- a/arch/sparc/mm/generic_64.c
> +++ /dev/null
> @@ -1,165 +0,0 @@
> -/*
> - * generic.c: Generic Sparc mm routines that are not dependent upon
> - *            MMU type but are Sparc specific.
> - *
> - * Copyright (C) 1996 David S. Miller (davem-CVlFQpJstH5+CIkdHa1UOg@public.gmane.org)
> - */
> -
> -#include <linux/kernel.h>
> -#include <linux/mm.h>
> -#include <linux/swap.h>
> -#include <linux/export.h>
> -#include <linux/pagemap.h>
> -
> -#include <asm/pgalloc.h>
> -#include <asm/pgtable.h>
> -#include <asm/page.h>
> -#include <asm/tlbflush.h>
> -
> -/* Remap IO memory, the same way as remap_pfn_range(), but use
> - * the obio memory space.
> - *
> - * They use a pgprot that sets PAGE_IO and does not check the
> - * mem_map table as this is independent of normal memory.
> - */
> -static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte,
> -                      unsigned long address,
> -                      unsigned long size,
> -                      unsigned long offset, pgprot_t prot,
> -                      int space)
> -{
> -    unsigned long end;
> -
> -    /* clear hack bit that was used as a write_combine side-effect flag */
> -    offset &= ~0x1UL;
> -    address &= ~PMD_MASK;
> -    end = address + size;
> -    if (end > PMD_SIZE)
> -        end = PMD_SIZE;
> -    do {
> -        pte_t entry;
> -        unsigned long curend = address + PAGE_SIZE;
> -        
> -        entry = mk_pte_io(offset, prot, space, PAGE_SIZE);
> -        if (!(address & 0xffff)) {
> -            if (PAGE_SIZE < (4 * 1024 * 1024) &&
> -                !(address & 0x3fffff) &&
> -                !(offset & 0x3ffffe) &&
> -                end >= address + 0x400000) {
> -                entry = mk_pte_io(offset, prot, space,
> -                          4 * 1024 * 1024);
> -                curend = address + 0x400000;
> -                offset += 0x400000;
> -            } else if (PAGE_SIZE < (512 * 1024) &&
> -                   !(address & 0x7ffff) &&
> -                   !(offset & 0x7fffe) &&
> -                   end >= address + 0x80000) {
> -                entry = mk_pte_io(offset, prot, space,
> -                          512 * 1024 * 1024);
> -                curend = address + 0x80000;
> -                offset += 0x80000;
> -            } else if (PAGE_SIZE < (64 * 1024) &&
> -                   !(offset & 0xfffe) &&
> -                   end >= address + 0x10000) {
> -                entry = mk_pte_io(offset, prot, space,
> -                          64 * 1024);
> -                curend = address + 0x10000;
> -                offset += 0x10000;
> -            } else
> -                offset += PAGE_SIZE;
> -        } else
> -            offset += PAGE_SIZE;
> -
> -        if (pte_write(entry))
> -            entry = pte_mkdirty(entry);
> -        do {
> -            BUG_ON(!pte_none(*pte));
> -            set_pte_at(mm, address, pte, entry);
> -            address += PAGE_SIZE;
> -            pte_val(entry) += PAGE_SIZE;
> -            pte++;
> -        } while (address < curend);
> -    } while (address < end);
> -}
> -
> -static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, 
> unsigned long address, unsigned long size,
> -    unsigned long offset, pgprot_t prot, int space)
> -{
> -    unsigned long end;
> -
> -    address &= ~PGDIR_MASK;
> -    end = address + size;
> -    if (end > PGDIR_SIZE)
> -        end = PGDIR_SIZE;
> -    offset -= address;
> -    do {
> -        pte_t *pte = pte_alloc_map(mm, NULL, pmd, address);
> -        if (!pte)
> -            return -ENOMEM;
> -        io_remap_pte_range(mm, pte, address, end - address, address + offset, 
> prot, space);
> -        pte_unmap(pte);
> -        address = (address + PMD_SIZE) & PMD_MASK;
> -        pmd++;
> -    } while (address < end);
> -    return 0;
> -}
> -
> -static inline int io_remap_pud_range(struct mm_struct *mm, pud_t * pud, 
> unsigned long address, unsigned long size,
> -    unsigned long offset, pgprot_t prot, int space)
> -{
> -    unsigned long end;
> -
> -    address &= ~PUD_MASK;
> -    end = address + size;
> -    if (end > PUD_SIZE)
> -        end = PUD_SIZE;
> -    offset -= address;
> -    do {
> -        pmd_t *pmd = pmd_alloc(mm, pud, address);
> -        if (!pud)
> -            return -ENOMEM;
> -        io_remap_pmd_range(mm, pmd, address, end - address, address + offset, 
> prot, space);
> -        address = (address + PUD_SIZE) & PUD_MASK;
> -        pud++;
> -    } while (address < end);
> -    return 0;
> -}
> -
> -int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
> -        unsigned long pfn, unsigned long size, pgprot_t prot)
> -{
> -    int error = 0;
> -    pgd_t * dir;
> -    unsigned long beg = from;
> -    unsigned long end = from + size;
> -    struct mm_struct *mm = vma->vm_mm;
> -    int space = GET_IOSPACE(pfn);
> -    unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
> -    unsigned long phys_base;
> -
> -    phys_base = offset | (((unsigned long) space) << 32UL);
> -
> -    /* See comment in mm/memory.c remap_pfn_range */
> -    vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
> -    vma->vm_pgoff = phys_base >> PAGE_SHIFT;
> -
> -    offset -= from;
> -    dir = pgd_offset(mm, from);
> -    flush_cache_range(vma, beg, end);
> -
> -    while (from < end) {
> -        pud_t *pud = pud_alloc(mm, dir, from);
> -        error = -ENOMEM;
> -        if (!pud)
> -            break;
> -        error = io_remap_pud_range(mm, pud, from, end - from, offset + from, 
> prot, space);
> -        if (error)
> -            break;
> -        from = (from + PGDIR_SIZE) & PGDIR_MASK;
> -        dir++;
> -    }
> -
> -    flush_tlb_range(vma, beg, end);
> -    return error;
> -}
> -EXPORT_SYMBOL(io_remap_pfn_range);
> -- 
> 1.7.6.401.g6a319
> 

I'll try them immediately and write back ASAP.
Thanks once already!

Regards,
Lukas
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html