[PATCH v3 2/2] drivers/vfio: Support EEH error injection
Gavin Shan
gwshan at linux.vnet.ibm.com
Tue Mar 24 13:41:36 AEDT 2015
On Tue, Mar 24, 2015 at 12:22:25PM +1100, David Gibson wrote:
>On Tue, Mar 24, 2015 at 09:47:54AM +1100, Gavin Shan wrote:
>> On Mon, Mar 23, 2015 at 10:14:59AM -0600, Alex Williamson wrote:
>> >On Mon, 2015-03-23 at 16:20 +1100, Gavin Shan wrote:
>> >> On Mon, Mar 23, 2015 at 04:10:20PM +1100, David Gibson wrote:
>> >> >On Mon, Mar 23, 2015 at 04:03:59PM +1100, Gavin Shan wrote:
>> >> >> On Mon, Mar 23, 2015 at 02:43:03PM +1100, David Gibson wrote:
>> >> >> >On Mon, Mar 23, 2015 at 12:56:36PM +1100, Gavin Shan wrote:
>> >> >> >> On Mon, Mar 23, 2015 at 12:39:45PM +1100, David Gibson wrote:
>> >> >> >> >On Sat, Mar 21, 2015 at 06:58:45AM +1100, Gavin Shan wrote:
>> >> >> >> >> The patch adds one more EEH sub-command (VFIO_EEH_PE_INJECT_ERR)
>> >> >> >> >> to inject the specified EEH error, which is represented by
>> >> >> >> >> (struct vfio_eeh_pe_err), to the indicated PE for testing purpose.
>> >> >> >> >>
>> >> >> >> >> Signed-off-by: Gavin Shan <gwshan at linux.vnet.ibm.com>
>> >> >> >> >
>> >> >> >> >Reviewed-by: David Gibson <david at gibson.dropbear.id.au>
>> >> >> >> >
>> >> >> >> >> ---
>> >> >> >> >> Documentation/vfio.txt | 12 ++++++++++++
>> >> >> >> >> drivers/vfio/vfio_spapr_eeh.c | 10 ++++++++++
>> >> >> >> >> include/uapi/linux/vfio.h | 36 +++++++++++++++++++++++++++++++++++-
>> >> >> >> >> 3 files changed, 57 insertions(+), 1 deletion(-)
>> >> >> >> >>
>> >> >> >> >> diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt
>> >> >> >> >> index 96978ec..c6e11a3 100644
>> >> >> >> >> --- a/Documentation/vfio.txt
>> >> >> >> >> +++ b/Documentation/vfio.txt
>> >> >> >> >> @@ -385,6 +385,18 @@ The code flow from the example above should be slightly changed:
>> >> >> >> >>
>> >> >> >> >> ....
>> >> >> >> >>
>> >> >> >> >> + /* Inject EEH error, which is expected to be caused by 32-bits
>> >> >> >> >> + * config load.
>> >> >> >> >> + */
>> >> >> >> >> + pe_op.op = VFIO_EEH_PE_INJECT_ERR;
>> >> >> >> >> + pe_op.err.type = VFIO_EEH_ERR_TYPE_32;
>> >> >> >> >> + pe_op.err.func = VFIO_EEH_ERR_FUNC_LD_CFG_ADDR;
>> >> >> >> >> + pe_op.err.addr = 0ul;
>> >> >> >> >> + pe_op.err.mask = 0ul;
>> >> >> >> >> + ioctl(container, VFIO_EEH_PE_OP, &pe_op);
>> >> >> >> >> +
>> >> >> >> >> + ....
>> >> >> >> >> +
>> >> >> >> >> /* When 0xFF's returned from reading PCI config space or IO BARs
>> >> >> >> >> * of the PCI device. Check the PE's state to see if that has been
>> >> >> >> >> * frozen.
>> >> >> >> >> diff --git a/drivers/vfio/vfio_spapr_eeh.c b/drivers/vfio/vfio_spapr_eeh.c
>> >> >> >> >> index 5fa42db..38edeb4 100644
>> >> >> >> >> --- a/drivers/vfio/vfio_spapr_eeh.c
>> >> >> >> >> +++ b/drivers/vfio/vfio_spapr_eeh.c
>> >> >> >> >> @@ -85,6 +85,16 @@ long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
>> >> >> >> >> case VFIO_EEH_PE_CONFIGURE:
>> >> >> >> >> ret = eeh_pe_configure(pe);
>> >> >> >> >> break;
>> >> >> >> >> + case VFIO_EEH_PE_INJECT_ERR:
>> >> >> >> >> + minsz = offsetofend(struct vfio_eeh_pe_op, err.mask);
>> >> >> >> >> + if (op.argsz < minsz)
>> >> >> >> >> + return -EINVAL;
>> >> >> >> >> + if (copy_from_user(&op, (void __user *)arg, minsz))
>> >> >> >> >> + return -EFAULT;
>> >> >> >> >> +
>> >> >> >> >> + ret = eeh_pe_inject_err(pe, op.err.type, op.err.func,
>> >> >> >> >> + op.err.addr, op.err.mask);
>> >> >> >> >> + break;
>> >> >> >> >> default:
>> >> >> >> >> ret = -EINVAL;
>> >> >> >> >> }
>> >> >> >> >> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
>> >> >> >> >> index 82889c3..f68e962 100644
>> >> >> >> >> --- a/include/uapi/linux/vfio.h
>> >> >> >> >> +++ b/include/uapi/linux/vfio.h
>> >> >> >> >> @@ -468,12 +468,23 @@ struct vfio_iommu_spapr_tce_info {
>> >> >> >> >> * - unfreeze IO/DMA for frozen PE;
>> >> >> >> >> * - read PE state;
>> >> >> >> >> * - reset PE;
>> >> >> >> >> - * - configure PE.
>> >> >> >> >> + * - configure PE;
>> >> >> >> >> + * - inject EEH error.
>> >> >> >> >> */
>> >> >> >> >> +struct vfio_eeh_pe_err {
>> >> >> >> >> + __u32 type;
>> >> >> >> >> + __u32 func;
>> >> >> >> >> + __u64 addr;
>> >> >> >> >> + __u64 mask;
>> >> >> >> >> +};
>> >> >> >> >> +
>> >> >> >> >> struct vfio_eeh_pe_op {
>> >> >> >> >> __u32 argsz;
>> >> >> >> >> __u32 flags;
>> >> >> >> >> __u32 op;
>> >> >> >> >> + union {
>> >> >> >> >> + struct vfio_eeh_pe_err err;
>> >> >> >> >> + };
>> >> >> >> >> };
>> >> >> >> >>
>> >> >> >> >> #define VFIO_EEH_PE_DISABLE 0 /* Disable EEH functionality */
>> >> >> >> >> @@ -490,6 +501,29 @@ struct vfio_eeh_pe_op {
>> >> >> >> >> #define VFIO_EEH_PE_RESET_HOT 6 /* Assert hot reset */
>> >> >> >> >> #define VFIO_EEH_PE_RESET_FUNDAMENTAL 7 /* Assert fundamental reset */
>> >> >> >> >> #define VFIO_EEH_PE_CONFIGURE 8 /* PE configuration */
>> >> >> >> >> +#define VFIO_EEH_PE_INJECT_ERR 9 /* Inject EEH error */
>> >> >> >> >> +#define VFIO_EEH_ERR_TYPE_32 0 /* 32-bits EEH error type */
>> >> >> >> >> +#define VFIO_EEH_ERR_TYPE_64 1 /* 64-bits EEH error type */
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_LD_MEM_ADDR 0 /* Memory load */
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_LD_MEM_DATA 1
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_LD_IO_ADDR 2 /* IO load */
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_LD_IO_DATA 3
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_LD_CFG_ADDR 4 /* Config load */
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_LD_CFG_DATA 5
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_ST_MEM_ADDR 6 /* Memory store */
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_ST_MEM_DATA 7
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_ST_IO_ADDR 8 /* IO store */
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_ST_IO_DATA 9
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_ST_CFG_ADDR 10 /* Config store */
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_ST_CFG_DATA 11
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_DMA_RD_ADDR 12 /* DMA read */
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_DMA_RD_DATA 13
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_DMA_RD_MASTER 14
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_DMA_RD_TARGET 15
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_DMA_WR_ADDR 16 /* DMA write */
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_DMA_WR_DATA 17
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_DMA_WR_MASTER 18
>> >> >> >> >> +#define VFIO_EEH_ERR_FUNC_DMA_WR_TARGET 19
>> >> >> >> >
>> >> >> >> >These all seem to duplicate (under slightly different names) the
>> >> >> >> >defines you just added in arch/powerpc/include/asm/eeh.h. It would
>> >> >> >> >make more sense to only have the uapi copy, surely.
>> >> >> >> >
>> >> >> >>
>> >> >> >> David, Thanks for your time. The defines in eeh.h is used not only
>> >> >> >> for mapping those constants defined in vfio.h, but also for validating
>> >> >> >> arguments from debugfs entry "err_injct". So it'd better to keep
>> >> >> >> them separate: one set is used by userspace, another set is used
>> >> >> >> by host kernel.
>> >> >> >
>> >> >> >I don't understand why this is an argument for duplicating them. They
>> >> >> >have the same meanings and values, why can't you use the uapi versions
>> >> >> >everywhere?
>> >> >> >
>> >> >>
>> >> >> We can drop the constants defined in eeh.h and just use those defines
>> >> >> in vfio.h. But I prefer separate constants for some ovbious reasons
>> >> >> except the one I mentioned above :)
>> >> >>
>> >> >> - We already had separate sets of constants for EEH and VFIO. For example,
>> >> >> VFIO_EEH_PE_STATE_* in include/uapi/vfio.h always have counter part in
>> >> >> arch/powerpc/asm/include/eeh.h
>> >> >
>> >> >Oh.. I see your point.
>> >> >
>> >> >Yes, the EEH internal code shouldn't need to use the VFIO defined
>> >> >constants.
>> >> >
>> >> >But it's still silly to duplicate, I think the correct think would be
>> >> >to expose the EEH constants in uapi, and use those for VFIO as well.
>> >> >
>> >>
>> >> I'm not sure. If Alex.W agree on this, I can have one patch to address
>> >> it in future :-)
>> >
>> >I agree with David, there should be a uapi eeh header and the vfio
>> >documentation should define that as the valid set of functions.
>> >
>> >> >> - The UAPI interface is expected to be stable, or back-compatible when
>> >> >> introducing changes to it. The defines (at least their names) in eeh.h
>> >> >> doesn't have to be stable.
>> >> >
>> >> >But is there any reason not to make them stable. The VFIO case shows
>> >> >that we need to lock down an interface somewhere. I don't see that
>> >> >there's an advantage to having a not locked down interface in addition
>> >> >to a locked down one.
>> >> >
>> >>
>> >> I was saying that the UAPI interace should be stable. I don't see
>> >> there're any reasons the UAPI interface will be changed in near
>> >> future :)
>> >
>> >When I asked previously whether a translation layer was needed between
>> >the vfio uapi and kernel internal eeh api I was told that the values
>> >were defined by the spapr spec and therefore not changeable. If that's
>> >true, we shouldn't need to worry about exporting them via uapi. Thanks,
>> >
>>
>> Well. It sounds a good idea. I'll add one separate patch, which would be
>> PATCH[3/3] in next revision to address it. Currently, there are not
>> too much constants, which can be put into arch/powerpc/include/uapi/asm/eeh.h.
>> The following list are the candidates from include/api/vfio.h, which can be
>> moved to uapi/asm/eeh.h. The names of those constants will be changed from
>> "VFIO_EEH_*" to "EEH_*" and then user space will have some code as folows
>> to use them. That looks a bit weird. Do we really want moving those constants
>> to uapi/asm/eeh.h and rename them accordingly?
>
>I think so, yes. I think the patch series will be cleaner if you do
>the exporting of the EEH constants in 1/3 then build your other
>patches on top of that.
>
Thanks for confirm, David. I'll have one patch (1/3) to address this
in next revision.
Thanks,
Gavin
>> #include <stdio.h>
>> #include <sys/ioctl.h>
>> #include <eeh.h>
>> #include <vfio.h>
>>
>> struct vfio_eeh_pe_op pe_op = { .argsz = sizeof(pe_op), .flags = 0 };
>>
>> pe_op.op = VFIO_EEH_PE_INJECT_ERR; /* Its prefix is "VFIO_EEH_* */
>> pe_op.err.type = EEH_ERR_TYPE_32; /* It starts with "EEH_*" */
>
>I think that's fine.
>
>> pe_op.err.func = EEH_ERR_FUNC_LD_CFG_ADDR;
>> pe_op.err.addr = 0ul;
>> pe_op.err.mask = 0ul;
>> ioctl(container, VFIO_EEH_PE_OP, &pe_op);
>>
>> ---
>>
>> #define VFIO_EEH_PE_STATE_NORMAL 0 /* PE in functional state */
>> #define VFIO_EEH_PE_STATE_RESET 1 /* PE reset in progress */
>> #define VFIO_EEH_PE_STATE_STOPPED 2 /* Stopped DMA and IO */
>> #define VFIO_EEH_PE_STATE_STOPPED_DMA 4 /* Stopped DMA only */
>> #define VFIO_EEH_PE_STATE_UNAVAIL 5 /* State unavailable */
>>
>> #define VFIO_EEH_ERR_TYPE_32 0 /* 32-bits EEH error type */
>> #define VFIO_EEH_ERR_TYPE_64 1 /* 64-bits EEH error type */
>> #define VFIO_EEH_ERR_FUNC_LD_MEM_ADDR 0 /* Memory load */
>> #define VFIO_EEH_ERR_FUNC_LD_MEM_DATA 1
>> #define VFIO_EEH_ERR_FUNC_LD_IO_ADDR 2 /* IO load */
>> #define VFIO_EEH_ERR_FUNC_LD_IO_DATA 3
>> #define VFIO_EEH_ERR_FUNC_LD_CFG_ADDR 4 /* Config load */
>> #define VFIO_EEH_ERR_FUNC_LD_CFG_DATA 5
>> #define VFIO_EEH_ERR_FUNC_ST_MEM_ADDR 6 /* Memory store */
>> #define VFIO_EEH_ERR_FUNC_ST_MEM_DATA 7
>> #define VFIO_EEH_ERR_FUNC_ST_IO_ADDR 8 /* IO store */
>> #define VFIO_EEH_ERR_FUNC_ST_IO_DATA 9
>> #define VFIO_EEH_ERR_FUNC_ST_CFG_ADDR 10 /* Config store */
>> #define VFIO_EEH_ERR_FUNC_ST_CFG_DATA 11
>> #define VFIO_EEH_ERR_FUNC_DMA_RD_ADDR 12 /* DMA read */
>> #define VFIO_EEH_ERR_FUNC_DMA_RD_DATA 13
>> #define VFIO_EEH_ERR_FUNC_DMA_RD_MASTER 14
>> #define VFIO_EEH_ERR_FUNC_DMA_RD_TARGET 15
>> #define VFIO_EEH_ERR_FUNC_DMA_WR_ADDR 16 /* DMA write */
>> #define VFIO_EEH_ERR_FUNC_DMA_WR_DATA 17
>> #define VFIO_EEH_ERR_FUNC_DMA_WR_MASTER 18
>> #define VFIO_EEH_ERR_FUNC_DMA_WR_TARGET 19
>>
>> Thanks,
>> Gavin
>>
>> >Alex
>> >
>> >> >> - I would like keep the code between EEH/VFIO independent to each other
>> >> >> enough.
>> >> >>
>> >> >> Thanks,
>> >> >> Gavin
>> >> >>
>> >> >> >> By the way, Alex Williamson, could you please ACK this if you don't
>> >> >> >> find obvious errors in the patch. I really want this to be merged
>> >> >> >> to 4.1.
>> >> >> >>
>> >> >> >> Thanks,
>> >> >> >> Gavin
>> >> >> >>
>> >> >> >>
>> >> >> >>
>> >> >> >
>> >> >>
>> >> >>
>> >> >
>> >>
>> >>
>> >
>> >
>> >
>> >_______________________________________________
>> >Linuxppc-dev mailing list
>> >Linuxppc-dev at lists.ozlabs.org
>> >https://lists.ozlabs.org/listinfo/linuxppc-dev
>>
>
>--
>David Gibson | I'll have my music baroque, and my code
>david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
> | _way_ _around_!
>http://www.ozlabs.org/~dgibson
More information about the Linuxppc-dev
mailing list