From: Matthew Auld <matthew.auld@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: Filip Hazubski <filip.hazubski@intel.com>,
Lucas De Marchi <lucas.demarchi@intel.com>,
Carl Zhang <carl.zhang@intel.com>, Effie Yu <effie.yu@intel.com>,
Matt Roper <matthew.d.roper@intel.com>
Subject: [Intel-xe] [PATCH v7 4/5] drm/xe/pat: annotate pat_index with coherency mode
Date: Thu, 5 Oct 2023 16:46:58 +0100 [thread overview]
Message-ID: <20231005154653.466804-11-matthew.auld@intel.com> (raw)
In-Reply-To: <20231005154653.466804-7-matthew.auld@intel.com>
Future uapi needs to give userspace the ability to select the pat_index
for a given vm_bind. However we need to be able to extract the coherency
mode from the provided pat_index to ensure it matches the coherency mode
set at object creation. There are various security reasons for why this
matters. However the pat_index itself is very platform specific, so
seems reasonable to annotate each platform definition of the pat table.
On some older platforms there is no explicit coherency mode, so we just
pick whatever makes sense.
v2:
- Simplify with COH_AT_LEAST_1_WAY
- Add some kernel-doc
v3 (Matt Roper):
- Some small tweaks
v4:
- Rebase
Bspec: 45101, 44235 #xe
Bspec: 70552, 71582, 59400 #xe2
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Pallavi Mishra <pallavi.mishra@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: Filip Hazubski <filip.hazubski@intel.com>
Cc: Carl Zhang <carl.zhang@intel.com>
Cc: Effie Yu <effie.yu@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Pallavi Mishra <pallavi.mishra@intel.com>
---
drivers/gpu/drm/xe/xe_device_types.h | 2 +-
drivers/gpu/drm/xe/xe_pat.c | 64 +++++++++++++++++-----------
drivers/gpu/drm/xe/xe_pat.h | 28 ++++++++++++
3 files changed, 67 insertions(+), 27 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index fd87fbb6306f..11214c274394 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -338,7 +338,7 @@ struct xe_device {
/** Internal operations to abstract platforms */
const struct xe_pat_ops *ops;
/** PAT table to program in the HW */
- const u32 *table;
+ const struct xe_pat_table_entry *table;
/** Number of PAT entries */
int n_entries;
u32 idx[__XE_CACHE_LEVEL_COUNT];
diff --git a/drivers/gpu/drm/xe/xe_pat.c b/drivers/gpu/drm/xe/xe_pat.c
index 36b79d675e54..3e9d253ac1ff 100644
--- a/drivers/gpu/drm/xe/xe_pat.c
+++ b/drivers/gpu/drm/xe/xe_pat.c
@@ -5,6 +5,8 @@
#include "xe_pat.h"
+#include <drm/xe_drm.h>
+
#include "regs/xe_reg_defs.h"
#include "xe_gt.h"
#include "xe_gt_mcr.h"
@@ -33,51 +35,60 @@
#define XELP_PAT_UC REG_FIELD_PREP(XELP_MEM_TYPE_MASK, 0)
struct xe_pat_ops {
- void (*program_graphics)(struct xe_gt *gt, const u32 table[], int n_entries);
- void (*program_media)(struct xe_gt *gt, const u32 table[], int n_entries);
+ void (*program_graphics)(struct xe_gt *gt, const struct xe_pat_table_entry table[],
+ int n_entries);
+ void (*program_media)(struct xe_gt *gt, const struct xe_pat_table_entry table[],
+ int n_entries);
};
-static const u32 xelp_pat_table[] = {
- [0] = XELP_PAT_WB,
- [1] = XELP_PAT_WC,
- [2] = XELP_PAT_WT,
- [3] = XELP_PAT_UC,
+static const struct xe_pat_table_entry xelp_pat_table[] = {
+ [0] = { XELP_PAT_WB, DRM_XE_GEM_COH_AT_LEAST_1WAY },
+ [1] = { XELP_PAT_WC, DRM_XE_GEM_COH_NONE },
+ [2] = { XELP_PAT_WT, DRM_XE_GEM_COH_NONE },
+ [3] = { XELP_PAT_UC, DRM_XE_GEM_COH_NONE },
};
-static const u32 xehpc_pat_table[] = {
- [0] = XELP_PAT_UC,
- [1] = XELP_PAT_WC,
- [2] = XELP_PAT_WT,
- [3] = XELP_PAT_WB,
- [4] = XEHPC_PAT_CLOS(1) | XELP_PAT_WT,
- [5] = XEHPC_PAT_CLOS(1) | XELP_PAT_WB,
- [6] = XEHPC_PAT_CLOS(2) | XELP_PAT_WT,
- [7] = XEHPC_PAT_CLOS(2) | XELP_PAT_WB,
+static const struct xe_pat_table_entry xehpc_pat_table[] = {
+ [0] = { XELP_PAT_UC, DRM_XE_GEM_COH_NONE },
+ [1] = { XELP_PAT_WC, DRM_XE_GEM_COH_NONE },
+ [2] = { XELP_PAT_WT, DRM_XE_GEM_COH_NONE },
+ [3] = { XELP_PAT_WB, DRM_XE_GEM_COH_AT_LEAST_1WAY },
+ [4] = { XEHPC_PAT_CLOS(1) | XELP_PAT_WT, DRM_XE_GEM_COH_NONE },
+ [5] = { XEHPC_PAT_CLOS(1) | XELP_PAT_WB, DRM_XE_GEM_COH_AT_LEAST_1WAY },
+ [6] = { XEHPC_PAT_CLOS(2) | XELP_PAT_WT, DRM_XE_GEM_COH_NONE },
+ [7] = { XEHPC_PAT_CLOS(2) | XELP_PAT_WB, DRM_XE_GEM_COH_AT_LEAST_1WAY },
};
-static const u32 xelpg_pat_table[] = {
- [0] = XELPG_PAT_0_WB,
- [1] = XELPG_PAT_1_WT,
- [2] = XELPG_PAT_3_UC,
- [3] = XELPG_PAT_0_WB | XELPG_2_COH_1W,
- [4] = XELPG_PAT_0_WB | XELPG_3_COH_2W,
+static const struct xe_pat_table_entry xelpg_pat_table[] = {
+ [0] = { XELPG_PAT_0_WB, DRM_XE_GEM_COH_NONE },
+ [1] = { XELPG_PAT_1_WT, DRM_XE_GEM_COH_NONE },
+ [2] = { XELPG_PAT_3_UC, DRM_XE_GEM_COH_NONE },
+ [3] = { XELPG_PAT_0_WB | XELPG_2_COH_1W, DRM_XE_GEM_COH_AT_LEAST_1WAY },
+ [4] = { XELPG_PAT_0_WB | XELPG_3_COH_2W, DRM_XE_GEM_COH_AT_LEAST_1WAY },
};
-static void program_pat(struct xe_gt *gt, const u32 table[], int n_entries)
+u16 xe_pat_index_get_coh_mode(struct xe_device *xe, u16 pat_index)
+{
+ WARN_ON(pat_index >= xe->pat.n_entries);
+ return xe->pat.table[pat_index].coh_mode;
+}
+
+static void program_pat(struct xe_gt *gt, const struct xe_pat_table_entry table[], int n_entries)
{
for (int i = 0; i < n_entries; i++) {
struct xe_reg reg = XE_REG(_PAT_INDEX(i));
- xe_mmio_write32(gt, reg, table[i]);
+ xe_mmio_write32(gt, reg, table[i].value);
}
}
-static void program_pat_mcr(struct xe_gt *gt, const u32 table[], int n_entries)
+static void program_pat_mcr(struct xe_gt *gt, const struct xe_pat_table_entry table[],
+ int n_entries)
{
for (int i = 0; i < n_entries; i++) {
struct xe_reg_mcr reg_mcr = XE_REG_MCR(_PAT_INDEX(i));
- xe_gt_mcr_multicast_write(gt, reg_mcr, table[i]);
+ xe_gt_mcr_multicast_write(gt, reg_mcr, table[i].value);
}
}
@@ -126,6 +137,7 @@ void xe_pat_init_early(struct xe_device *xe)
xe->pat.idx[XE_CACHE_WT] = 2;
xe->pat.idx[XE_CACHE_WB] = 0;
} else if (GRAPHICS_VERx100(xe) <= 1210) {
+ WARN_ON_ONCE(!IS_DGFX(xe) && !xe->info.has_llc);
xe->pat.ops = &xelp_pat_ops;
xe->pat.table = xelp_pat_table;
xe->pat.n_entries = ARRAY_SIZE(xelp_pat_table);
diff --git a/drivers/gpu/drm/xe/xe_pat.h b/drivers/gpu/drm/xe/xe_pat.h
index 168e80e63809..a4fe9d5466bc 100644
--- a/drivers/gpu/drm/xe/xe_pat.h
+++ b/drivers/gpu/drm/xe/xe_pat.h
@@ -6,9 +6,29 @@
#ifndef _XE_PAT_H_
#define _XE_PAT_H_
+#include <linux/types.h>
+
struct xe_gt;
struct xe_device;
+/**
+ * struct xe_pat_table_entry - The pat_index encoding and other meta information.
+ */
+struct xe_pat_table_entry {
+ /**
+ * @value: The platform specific value encoding the various memory
+ * attributes (this maps to some fixed pat_index). So things like
+ * caching, coherency, compression etc can be encoded here.
+ */
+ u32 value;
+
+ /**
+ * @coh_mode: The GPU coherency mode that @value maps to. Either
+ * DRM_XE_GEM_COH_NONE or DRM_XE_GEM_COH_AT_LEAST_1WAY.
+ */
+ u16 coh_mode;
+};
+
/**
* xe_pat_init_early - SW initialization, setting up data based on device
* @xe: xe device
@@ -21,4 +41,12 @@ void xe_pat_init_early(struct xe_device *xe);
*/
void xe_pat_init(struct xe_gt *gt);
+/**
+ * xe_pat_index_get_coh_mode - Extract the coherency mode for the given
+ * pat_index.
+ * @xe: xe device
+ * @pat_index: The pat_index to query
+ */
+u16 xe_pat_index_get_coh_mode(struct xe_device *xe, u16 pat_index);
+
#endif
--
2.41.0
next prev parent reply other threads:[~2023-10-05 15:47 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-05 15:46 [Intel-xe] [PATCH v7 0/5] PAT and cache coherency support Matthew Auld
2023-10-05 15:46 ` [Intel-xe] [PATCH v7 1/5] drm/xe/pat: trim the xelp PAT table Matthew Auld
2023-10-05 15:46 ` [Intel-xe] [PATCH v7 2/5] drm/xe: directly use pat_index for pte_encode Matthew Auld
2023-10-05 15:46 ` [Intel-xe] [PATCH v7 3/5] drm/xe/uapi: Add support for cache and coherency mode Matthew Auld
2023-10-05 15:46 ` Matthew Auld [this message]
2023-10-05 15:46 ` [Intel-xe] [PATCH v7 5/5] drm/xe/uapi: support pat_index selection with vm_bind Matthew Auld
2023-10-05 19:34 ` [Intel-xe] ✓ CI.Patch_applied: success for PAT and cache coherency support (rev9) Patchwork
2023-10-05 19:34 ` [Intel-xe] ✓ CI.checkpatch: " Patchwork
2023-10-05 19:35 ` [Intel-xe] ✓ CI.KUnit: " Patchwork
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20231005154653.466804-11-matthew.auld@intel.com \
--to=matthew.auld@intel.com \
--cc=carl.zhang@intel.com \
--cc=effie.yu@intel.com \
--cc=filip.hazubski@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=lucas.demarchi@intel.com \
--cc=matthew.d.roper@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox