linux_dsm_epyc7002/drivers/gpu/drm/i915/i915_query.c

126 lines
3.3 KiB
C
Raw Normal View History

drm/i915: add query uAPI There are a number of information that are readable from hardware registers and that we would like to make accessible to userspace. One particular example is the topology of the execution units (how are execution units grouped in subslices and slices and also which ones have been fused off for die recovery). At the moment the GET_PARAM ioctl covers some basic needs, but generally is only able to return a single value for each defined parameter. This is a bit problematic with topology descriptions which are array/maps of available units. This change introduces a new ioctl that can deal with requests to fill structures of potentially variable lengths. The user is expected fill a query with length fields set at 0 on the first call, the kernel then sets the length fields to the their expected values. A second call to the kernel with length fields at their expected values will trigger a copy of the data to the pointed memory locations. The scope of this uAPI is only to provide information to userspace, not to allow configuration of the device. v2: Simplify dispatcher code iteration (Tvrtko) Tweak uapi drm_i915_query_item structure (Tvrtko) v3: Rename pad fields into flags (Chris) Return error on flags field != 0 (Chris) Only copy length back to userspace in drm_i915_query_item (Chris) v4: Use array of functions instead of switch (Chris) v5: More comments in uapi (Tvrtko) Return query item errors in length field (All) v6: Tweak uapi comments style to match the coding style (Lionel) v7: Add i915_query.h (Joonas) v8: (Lionel) Change the behavior of the item iterator to report invalid queries into the query item rather than stopping the iteration. This enables userspace applications to query newer items on older kernels and only have failure on the items that are not supported. v9: Edit copyright headers (Joonas) v10: Typos & comments in uapi (Joonas) Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Acked-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20180306122857.27317-6-lionel.g.landwerlin@intel.com
2018-03-06 19:28:56 +07:00
/*
* SPDX-License-Identifier: MIT
*
* Copyright © 2018 Intel Corporation
*/
#include "i915_drv.h"
#include "i915_query.h"
#include <uapi/drm/i915_drm.h>
drm/i915: expose rcs topology through query uAPI With the introduction of asymmetric slices in CNL, we cannot rely on the previous SUBSLICE_MASK getparam to tell userspace what subslices are available. Here we introduce a more detailed way of querying the Gen's GPU topology that doesn't aggregate numbers. This is essential for monitoring parts of the GPU with the OA unit, because counters need to be normalized to the number of EUs/subslices/slices. The current aggregated numbers like EU_TOTAL do not gives us sufficient information. The Mesa series making use of this API is : https://patchwork.freedesktop.org/series/38795/ As a bonus we can draw representations of the GPU : https://imgur.com/a/vuqpa v2: Rename uapi struct s/_mask/_info/ (Tvrtko) Report max_slice/subslice/eus_per_subslice rather than strides (Tvrtko) Add uapi macros to read data from *_info structs (Tvrtko) v3: Use !!(v & DRM_I915_BIT()) for uapi macros instead of custom shifts (Tvrtko) v4: factorize query item writting (Tvrtko) tweak uapi struct/define names (Tvrtko) v5: Replace ALIGN() macro (Chris) v6: Updated uapi comments (Tvrtko) Moved flags != 0 checks into vfuncs (Tvrtko) v7: Use access_ok() before copying anything, to avoid overflows (Chris) Switch BUG_ON() to GEM_WARN_ON() (Tvrtko) v8: Tweak uapi comments style to match the coding style (Lionel) v9: Fix error in comment about computation of enabled subslice (Tvrtko) v10: Fix/update comments in uAPI (Sagar) v11: Drop drm_i915_query_(slice|subslice|eu)_info in favor of a single drm_i915_query_topology_info (Joonas) v12: Add subslice_stride/eu_stride in drm_i915_query_topology_info (Joonas) v13: Fix comment in uAPI (Joonas) Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Acked-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20180306122857.27317-7-lionel.g.landwerlin@intel.com
2018-03-06 19:28:57 +07:00
static int query_topology_info(struct drm_i915_private *dev_priv,
struct drm_i915_query_item *query_item)
{
const struct sseu_dev_info *sseu = &INTEL_INFO(dev_priv)->sseu;
struct drm_i915_query_topology_info topo;
u32 slice_length, subslice_length, eu_length, total_length;
if (query_item->flags != 0)
return -EINVAL;
if (sseu->max_slices == 0)
return -ENODEV;
BUILD_BUG_ON(sizeof(u8) != sizeof(sseu->slice_mask));
slice_length = sizeof(sseu->slice_mask);
subslice_length = sseu->max_slices *
DIV_ROUND_UP(sseu->max_subslices,
sizeof(sseu->subslice_mask[0]) * BITS_PER_BYTE);
eu_length = sseu->max_slices * sseu->max_subslices *
DIV_ROUND_UP(sseu->max_eus_per_subslice, BITS_PER_BYTE);
total_length = sizeof(topo) + slice_length + subslice_length + eu_length;
if (query_item->length == 0)
return total_length;
if (query_item->length < total_length)
return -EINVAL;
if (copy_from_user(&topo, u64_to_user_ptr(query_item->data_ptr),
sizeof(topo)))
return -EFAULT;
if (topo.flags != 0)
return -EINVAL;
if (!access_ok(VERIFY_WRITE, u64_to_user_ptr(query_item->data_ptr),
total_length))
return -EFAULT;
memset(&topo, 0, sizeof(topo));
topo.max_slices = sseu->max_slices;
topo.max_subslices = sseu->max_subslices;
topo.max_eus_per_subslice = sseu->max_eus_per_subslice;
topo.subslice_offset = slice_length;
topo.subslice_stride = DIV_ROUND_UP(sseu->max_subslices, BITS_PER_BYTE);
topo.eu_offset = slice_length + subslice_length;
topo.eu_stride =
DIV_ROUND_UP(sseu->max_eus_per_subslice, BITS_PER_BYTE);
if (__copy_to_user(u64_to_user_ptr(query_item->data_ptr),
&topo, sizeof(topo)))
return -EFAULT;
if (__copy_to_user(u64_to_user_ptr(query_item->data_ptr + sizeof(topo)),
&sseu->slice_mask, slice_length))
return -EFAULT;
if (__copy_to_user(u64_to_user_ptr(query_item->data_ptr +
sizeof(topo) + slice_length),
sseu->subslice_mask, subslice_length))
return -EFAULT;
if (__copy_to_user(u64_to_user_ptr(query_item->data_ptr +
sizeof(topo) +
slice_length + subslice_length),
sseu->eu_mask, eu_length))
return -EFAULT;
return total_length;
}
drm/i915: add query uAPI There are a number of information that are readable from hardware registers and that we would like to make accessible to userspace. One particular example is the topology of the execution units (how are execution units grouped in subslices and slices and also which ones have been fused off for die recovery). At the moment the GET_PARAM ioctl covers some basic needs, but generally is only able to return a single value for each defined parameter. This is a bit problematic with topology descriptions which are array/maps of available units. This change introduces a new ioctl that can deal with requests to fill structures of potentially variable lengths. The user is expected fill a query with length fields set at 0 on the first call, the kernel then sets the length fields to the their expected values. A second call to the kernel with length fields at their expected values will trigger a copy of the data to the pointed memory locations. The scope of this uAPI is only to provide information to userspace, not to allow configuration of the device. v2: Simplify dispatcher code iteration (Tvrtko) Tweak uapi drm_i915_query_item structure (Tvrtko) v3: Rename pad fields into flags (Chris) Return error on flags field != 0 (Chris) Only copy length back to userspace in drm_i915_query_item (Chris) v4: Use array of functions instead of switch (Chris) v5: More comments in uapi (Tvrtko) Return query item errors in length field (All) v6: Tweak uapi comments style to match the coding style (Lionel) v7: Add i915_query.h (Joonas) v8: (Lionel) Change the behavior of the item iterator to report invalid queries into the query item rather than stopping the iteration. This enables userspace applications to query newer items on older kernels and only have failure on the items that are not supported. v9: Edit copyright headers (Joonas) v10: Typos & comments in uapi (Joonas) Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Acked-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20180306122857.27317-6-lionel.g.landwerlin@intel.com
2018-03-06 19:28:56 +07:00
static int (* const i915_query_funcs[])(struct drm_i915_private *dev_priv,
struct drm_i915_query_item *query_item) = {
drm/i915: expose rcs topology through query uAPI With the introduction of asymmetric slices in CNL, we cannot rely on the previous SUBSLICE_MASK getparam to tell userspace what subslices are available. Here we introduce a more detailed way of querying the Gen's GPU topology that doesn't aggregate numbers. This is essential for monitoring parts of the GPU with the OA unit, because counters need to be normalized to the number of EUs/subslices/slices. The current aggregated numbers like EU_TOTAL do not gives us sufficient information. The Mesa series making use of this API is : https://patchwork.freedesktop.org/series/38795/ As a bonus we can draw representations of the GPU : https://imgur.com/a/vuqpa v2: Rename uapi struct s/_mask/_info/ (Tvrtko) Report max_slice/subslice/eus_per_subslice rather than strides (Tvrtko) Add uapi macros to read data from *_info structs (Tvrtko) v3: Use !!(v & DRM_I915_BIT()) for uapi macros instead of custom shifts (Tvrtko) v4: factorize query item writting (Tvrtko) tweak uapi struct/define names (Tvrtko) v5: Replace ALIGN() macro (Chris) v6: Updated uapi comments (Tvrtko) Moved flags != 0 checks into vfuncs (Tvrtko) v7: Use access_ok() before copying anything, to avoid overflows (Chris) Switch BUG_ON() to GEM_WARN_ON() (Tvrtko) v8: Tweak uapi comments style to match the coding style (Lionel) v9: Fix error in comment about computation of enabled subslice (Tvrtko) v10: Fix/update comments in uAPI (Sagar) v11: Drop drm_i915_query_(slice|subslice|eu)_info in favor of a single drm_i915_query_topology_info (Joonas) v12: Add subslice_stride/eu_stride in drm_i915_query_topology_info (Joonas) v13: Fix comment in uAPI (Joonas) Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Acked-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20180306122857.27317-7-lionel.g.landwerlin@intel.com
2018-03-06 19:28:57 +07:00
query_topology_info,
drm/i915: add query uAPI There are a number of information that are readable from hardware registers and that we would like to make accessible to userspace. One particular example is the topology of the execution units (how are execution units grouped in subslices and slices and also which ones have been fused off for die recovery). At the moment the GET_PARAM ioctl covers some basic needs, but generally is only able to return a single value for each defined parameter. This is a bit problematic with topology descriptions which are array/maps of available units. This change introduces a new ioctl that can deal with requests to fill structures of potentially variable lengths. The user is expected fill a query with length fields set at 0 on the first call, the kernel then sets the length fields to the their expected values. A second call to the kernel with length fields at their expected values will trigger a copy of the data to the pointed memory locations. The scope of this uAPI is only to provide information to userspace, not to allow configuration of the device. v2: Simplify dispatcher code iteration (Tvrtko) Tweak uapi drm_i915_query_item structure (Tvrtko) v3: Rename pad fields into flags (Chris) Return error on flags field != 0 (Chris) Only copy length back to userspace in drm_i915_query_item (Chris) v4: Use array of functions instead of switch (Chris) v5: More comments in uapi (Tvrtko) Return query item errors in length field (All) v6: Tweak uapi comments style to match the coding style (Lionel) v7: Add i915_query.h (Joonas) v8: (Lionel) Change the behavior of the item iterator to report invalid queries into the query item rather than stopping the iteration. This enables userspace applications to query newer items on older kernels and only have failure on the items that are not supported. v9: Edit copyright headers (Joonas) v10: Typos & comments in uapi (Joonas) Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Acked-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20180306122857.27317-6-lionel.g.landwerlin@intel.com
2018-03-06 19:28:56 +07:00
};
int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
{
struct drm_i915_private *dev_priv = to_i915(dev);
struct drm_i915_query *args = data;
struct drm_i915_query_item __user *user_item_ptr =
u64_to_user_ptr(args->items_ptr);
u32 i;
if (args->flags != 0)
return -EINVAL;
for (i = 0; i < args->num_items; i++, user_item_ptr++) {
struct drm_i915_query_item item;
u64 func_idx;
int ret;
if (copy_from_user(&item, user_item_ptr, sizeof(item)))
return -EFAULT;
if (item.query_id == 0)
return -EINVAL;
func_idx = item.query_id - 1;
if (func_idx < ARRAY_SIZE(i915_query_funcs))
ret = i915_query_funcs[func_idx](dev_priv, &item);
else
ret = -EINVAL;
/* Only write the length back to userspace if they differ. */
if (ret != item.length && put_user(ret, &user_item_ptr->length))
return -EFAULT;
}
return 0;
}