Re: [dpdk-dev] [PATCH v3 1/6] mem: add function for checking memsegs IOVAs addresses

[Alejandro Lucero <alejandro.lucero@netronome.com>]

On Wed, Oct 10, 2018 at 10:00 AM Tu, Lijuan <lijuan.tu@intel.com> wrote:

> Hi
>
> > -----Original Message-----
> > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Alejandro Lucero
> > Sent: Friday, October 5, 2018 8:45 PM
> > To: dev@dpdk.org
> > Subject: [dpdk-dev] [PATCH v3 1/6] mem: add function for checking
> > memsegs IOVAs addresses
> >
> > A device can suffer addressing limitations. This function checks memsegs
> > have iovas within the supported range based on dma mask.
> >
> > PMDs should use this function during initialization if device suffers
> > addressing limitations, returning an error if this function returns
> memsegs
> > out of range.
> >
> > Another usage is for emulated IOMMU hardware with addressing limitations.
> >
> > It is necessary to save the most restricted dma mask for checking out
> > memory allocated dynamically after initialization.
> >
> > Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
> > Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>
> > ---
> >  doc/guides/rel_notes/release_18_11.rst            | 10 ++++
> >  lib/librte_eal/common/eal_common_memory.c         | 60
> > +++++++++++++++++++++++
> >  lib/librte_eal/common/include/rte_eal_memconfig.h |  3 ++
> >  lib/librte_eal/common/include/rte_memory.h        |  3 ++
> >  lib/librte_eal/common/malloc_heap.c               | 12 +++++
> >  lib/librte_eal/linuxapp/eal/eal.c                 |  2 +
> >  lib/librte_eal/rte_eal_version.map                |  1 +
> >  7 files changed, 91 insertions(+)
> >
> > diff --git a/doc/guides/rel_notes/release_18_11.rst
> > b/doc/guides/rel_notes/release_18_11.rst
> > index 2133a5b..c806dc6 100644
> > --- a/doc/guides/rel_notes/release_18_11.rst
> > +++ b/doc/guides/rel_notes/release_18_11.rst
> > @@ -104,6 +104,14 @@ New Features
> >    the specified port. The port must be stopped before the command call
> in
> > order
> >    to reconfigure queues.
> >
> > +* **Added check for ensuring allocated memory addressable by devices.**
> > +
> > +  Some devices can have addressing limitations so a new function,
> > + ``rte_eal_check_dma_mask``, has been added for checking allocated
> > + memory is  not out of the device range. Because now memory can be
> > + dynamically allocated  after initialization, a dma mask is kept and
> > + any new allocated memory will be  checked out against that dma mask
> > + and rejected if out of range. If more than  one device has addressing
> > limitations, the dma mask is the more restricted one.
> >
> >  API Changes
> >  -----------
> > @@ -156,6 +164,8 @@ ABI Changes
> >         ``rte_config`` structure on account of improving DPDK usability
> > when
> >         using either ``--legacy-mem`` or ``--single-file-segments``
> flags.
> >
> > +* eal: added ``dma_maskbits`` to ``rte_mem_config`` for keeping more
> > restricted
> > +       dma mask based on devices addressing limitations.
> >
> >  Removed Items
> >  -------------
> > diff --git a/lib/librte_eal/common/eal_common_memory.c
> > b/lib/librte_eal/common/eal_common_memory.c
> > index 0b69804..c482f0d 100644
> > --- a/lib/librte_eal/common/eal_common_memory.c
> > +++ b/lib/librte_eal/common/eal_common_memory.c
> > @@ -385,6 +385,66 @@ struct virtiova {
> >       rte_memseg_walk(dump_memseg, f);
> >  }
> >
> > +static int
> > +check_iova(const struct rte_memseg_list *msl __rte_unused,
> > +             const struct rte_memseg *ms, void *arg) {
> > +     uint64_t *mask = arg;
> > +     rte_iova_t iova;
> > +
> > +     /* higher address within segment */
> > +     iova = (ms->iova + ms->len) - 1;
> > +     if (!(iova & *mask))
> > +             return 0;
> > +
> > +     RTE_LOG(DEBUG, EAL, "memseg iova %"PRIx64", len %zx, out of
> > range\n",
> > +                         ms->iova, ms->len);
> > +
> > +     RTE_LOG(DEBUG, EAL, "\tusing dma mask %"PRIx64"\n", *mask);
> > +     return 1;
> > +}
> > +
> > +#if defined(RTE_ARCH_64)
> > +#define MAX_DMA_MASK_BITS 63
> > +#else
> > +#define MAX_DMA_MASK_BITS 31
> > +#endif
> > +
> > +/* check memseg iovas are within the required range based on dma mask
> > +*/ int __rte_experimental rte_eal_check_dma_mask(uint8_t maskbits) {
> > +     struct rte_mem_config *mcfg =
> > rte_eal_get_configuration()->mem_config;
> > +     uint64_t mask;
> > +
> > +     /* sanity check */
> > +     if (maskbits > MAX_DMA_MASK_BITS) {
> > +             RTE_LOG(ERR, EAL, "wrong dma mask size %u (Max: %u)\n",
> > +                                maskbits, MAX_DMA_MASK_BITS);
> > +             return -1;
> > +     }
> > +
> > +     /* create dma mask */
> > +     mask = ~((1ULL << maskbits) - 1);
> > +
> > +     if (rte_memseg_walk(check_iova, &mask))
>
> [Lijuan]In my environment, testpmd halts at rte_memseg_walk() when
> maskbits is 0.
>
>
Can you explain this further?
Who is calling rte_eal_check_dma_mask with mask 0? is this a X86_64 system?
The only explanation I can find is the IOMMU hardware reporting mgaw=0 what
I would say is something completely wrong.


> > +             /*
> > +              * Dma mask precludes hugepage usage.
> > +              * This device can not be used and we do not need to keep
> > +              * the dma mask.
> > +              */
> > +             return 1;
> > +
> > +     /*
> > +      * we need to keep the more restricted maskbit for checking
> > +      * potential dynamic memory allocation in the future.
> > +      */
> > +     mcfg->dma_maskbits = mcfg->dma_maskbits == 0 ? maskbits :
> > +                          RTE_MIN(mcfg->dma_maskbits, maskbits);
> > +
> > +     return 0;
> > +}
> > +
> >  /* return the number of memory channels */  unsigned
> > rte_memory_get_nchannel(void)  { diff --git
> > a/lib/librte_eal/common/include/rte_eal_memconfig.h
> > b/lib/librte_eal/common/include/rte_eal_memconfig.h
> > index 62a21c2..b5dff70 100644
> > --- a/lib/librte_eal/common/include/rte_eal_memconfig.h
> > +++ b/lib/librte_eal/common/include/rte_eal_memconfig.h
> > @@ -81,6 +81,9 @@ struct rte_mem_config {
> >       /* legacy mem and single file segments options are shared */
> >       uint32_t legacy_mem;
> >       uint32_t single_file_segments;
> > +
> > +     /* keeps the more restricted dma mask */
> > +     uint8_t dma_maskbits;
> >  } __attribute__((__packed__));
> >
> >
> > diff --git a/lib/librte_eal/common/include/rte_memory.h
> > b/lib/librte_eal/common/include/rte_memory.h
> > index 14bd277..c349d6c 100644
> > --- a/lib/librte_eal/common/include/rte_memory.h
> > +++ b/lib/librte_eal/common/include/rte_memory.h
> > @@ -454,6 +454,9 @@ typedef int (*rte_memseg_list_walk_t)(const struct
> > rte_memseg_list *msl,
> >   */
> >  unsigned rte_memory_get_nrank(void);
> >
> > +/* check memsegs iovas are within a range based on dma mask */ int
> > +rte_eal_check_dma_mask(uint8_t maskbits);
> > +
> >  /**
> >   * Drivers based on uio will not load unless physical
> >   * addresses are obtainable. It is only possible to get diff --git
> > a/lib/librte_eal/common/malloc_heap.c
> > b/lib/librte_eal/common/malloc_heap.c
> > index ac7bbb3..3b5b2b6 100644
> > --- a/lib/librte_eal/common/malloc_heap.c
> > +++ b/lib/librte_eal/common/malloc_heap.c
> > @@ -259,11 +259,13 @@ struct malloc_elem *
> >               int socket, unsigned int flags, size_t align, size_t bound,
> >               bool contig, struct rte_memseg **ms, int n_segs)  {
> > +     struct rte_mem_config *mcfg =
> > rte_eal_get_configuration()->mem_config;
> >       struct rte_memseg_list *msl;
> >       struct malloc_elem *elem = NULL;
> >       size_t alloc_sz;
> >       int allocd_pages;
> >       void *ret, *map_addr;
> > +     uint64_t mask;
> >
> >       alloc_sz = (size_t)pg_sz * n_segs;
> >
> > @@ -291,6 +293,16 @@ struct malloc_elem *
> >               goto fail;
> >       }
> >
> > +     if (mcfg->dma_maskbits) {
> > +             mask = ~((1ULL << mcfg->dma_maskbits) - 1);
> > +             if (rte_eal_check_dma_mask(mask)) {
> > +                     RTE_LOG(ERR, EAL,
> > +                             "%s(): couldn't allocate memory due to DMA
> mask\n",
> > +                             __func__);
> > +                     goto fail;
> > +             }
> > +     }
> > +
> >       /* add newly minted memsegs to malloc heap */
> >       elem = malloc_heap_add_memory(heap, msl, map_addr, alloc_sz);
> >
> > diff --git a/lib/librte_eal/linuxapp/eal/eal.c
> > b/lib/librte_eal/linuxapp/eal/eal.c
> > index 4a55d3b..dfe1b8c 100644
> > --- a/lib/librte_eal/linuxapp/eal/eal.c
> > +++ b/lib/librte_eal/linuxapp/eal/eal.c
> > @@ -263,6 +263,8 @@ enum rte_iova_mode
> >        * processes could later map the config into this exact location */
> >       rte_config.mem_config->mem_cfg_addr = (uintptr_t)
> > rte_mem_cfg_addr;
> >
> > +     rte_config.mem_config->dma_maskbits = 0;
> > +
> >  }
> >
> >  /* attach to an existing shared memory config */ diff --git
> > a/lib/librte_eal/rte_eal_version.map b/lib/librte_eal/rte_eal_version.map
> > index 73282bb..2baefce 100644
> > --- a/lib/librte_eal/rte_eal_version.map
> > +++ b/lib/librte_eal/rte_eal_version.map
> > @@ -291,6 +291,7 @@ EXPERIMENTAL {
> >       rte_devargs_parsef;
> >       rte_devargs_remove;
> >       rte_devargs_type_count;
> > +     rte_eal_check_dma_mask;
> >       rte_eal_cleanup;
> >       rte_eal_hotplug_add;
> >       rte_eal_hotplug_remove;
> > --
> > 1.9.1
>
>