[dpdk-dev] [PATCH v2 1/3] eal/arm64: relax the io barrier for aarch64

[Jerin Jacob]

On Fri, Dec 20, 2019 at 8:40 AM Gavin Hu <gavin.hu at arm.com> wrote:
>
> Armv8's peripheral coherence order is a total order on all reads and writes
> to that peripheral.[1]
>
> The peripheral coherence order for a memory-mapped peripheral signifies the
> order in which accesses arrive at the endpoint.  For a read or a write RW1
> and a read or a write RW2 to the same peripheral, then RW1 will appear in
> the peripheral coherence order for the peripheral before RW2 if either of
> the following cases apply:
>  1. RW1 and RW2 are accesses using Non-cacheable or Device attributes and
>     RW1 is Ordered-before RW2.
>  2. RW1 and RW2 are accesses using Device-nGnRE or Device-nGnRnE attributes
>     and RW1 appears in program order before RW2.


This is true if RW1 and RW2 addresses are device memory. i.e the
registers in the  PCI bar address.
If RW1 is DDR address which is been used by the controller(say NIC
ring descriptor) then there will be an issue.
For example Intel i40e driver, the admin queue update in Host DDR
memory and it updates the doorbell.
In such a case, this patch will create an issue. Correct? Have you
checked this patch with ARM64 + XL710 controllers?

Some of the legacy code is missing such barriers, that's the reason
for adding rte_io_* barrier.

>
> On arm platforms, all the PCI resources are mapped to nGnRE device memory
> [2], the above case 2 holds true, that means the peripheral coherence order
> applies here and just a compiler barrier is sufficient for rte io barriers.
>
> [1] Section B2.3.4 of ARMARM, https://developer.arm.com/docs/ddi0487/lates
> t/arm-architecture-reference-manual-armv8-for-armv8-a-architecture-profile
> [2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/
> tree/drivers/pci/pci-sysfs.c#n1204
>
> Signed-off-by: Gavin Hu <gavin.hu at arm.com>
> Reviewed-by: Steve Capper <steve.capper at arm.com>
> Reviewed-by: Phil Yang <phil.yang at arm.com>
> ---
>  lib/librte_eal/common/include/arch/arm/rte_atomic_64.h | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
>
> diff --git a/lib/librte_eal/common/include/arch/arm/rte_atomic_64.h b/lib/librte_eal/common/include/arch/arm/rte_atomic_64.h
> index 859ae12..fd63956 100644
> --- a/lib/librte_eal/common/include/arch/arm/rte_atomic_64.h
> +++ b/lib/librte_eal/common/include/arch/arm/rte_atomic_64.h
> @@ -34,11 +34,11 @@ extern "C" {
>
>  #define rte_smp_rmb() dmb(ishld)
>
> -#define rte_io_mb() rte_mb()
> +#define rte_io_mb() rte_compiler_barrier()
>
> -#define rte_io_wmb() rte_wmb()
> +#define rte_io_wmb() rte_compiler_barrier()
>
> -#define rte_io_rmb() rte_rmb()
> +#define rte_io_rmb() rte_compiler_barrier()
>
>  #define rte_cio_wmb() dmb(oshst)
>
> --
> 2.7.4
>