[Mesa-dev] [PATCH v2 1/2] mesa: Add KBL PCI IDs and platform information.

[Sarah Sharp]

Add PCI IDs for the Intel Kabylake platforms.  The IDs are taken
directly from the Linux kernel patches, which are under review:

http://lists.freedesktop.org/archives/intel-gfx/2015-October/078967.html
http://cgit.freedesktop.org/~vivijim/drm-intel/log/?h=kbl-upstream-v2

The Kabylake PCI IDs taken from the kernel are rearranged to be in order
of GT type, then PCI ID.

Please note that if this patch is backported, the following fixes will
need to be added before this patch:

commit 28ed1e08e8ba98e "i965/skl: Remove early platform support"
commit c1e38ad37042b0e "i965/skl: Use larger URB size where available."

Thanks to Ben for fixing a bug around setting urb.size, and being
patient with my questions about what the various fields mean.

Signed-off-by: Sarah Sharp <sarah.a.sharp at linux.intel.com>
Suggested-by: Ben Widawsky <benjamin.widawsky at intel.com>
Tested-by: Rodrigo Vivi <rodrigo.vivi at intel.com> (KBL-GT2)
---

v2:
 - reorder the PCI IDs
 - rebase on latest mesa master

 include/pci_ids/i965_pci_ids.h              | 22 +++++++++++
 src/mesa/drivers/dri/i965/brw_device_info.c | 60 +++++++++++++++++++++++++++++
 2 files changed, 82 insertions(+)

diff --git a/include/pci_ids/i965_pci_ids.h b/include/pci_ids/i965_pci_ids.h
index 5891ba6..5139e27 100644
--- a/include/pci_ids/i965_pci_ids.h
+++ b/include/pci_ids/i965_pci_ids.h
@@ -132,6 +132,28 @@ CHIPSET(0x1932, skl_gt4, "Intel(R) Skylake GT4")
 CHIPSET(0x193A, skl_gt4, "Intel(R) Skylake GT4")
 CHIPSET(0x193B, skl_gt4, "Intel(R) Skylake GT4")
 CHIPSET(0x193D, skl_gt4, "Intel(R) Skylake GT4")
+CHIPSET(0x5902, kbl_gt1, "Intel(R) Kabylake GT1")
+CHIPSET(0x5906, kbl_gt1, "Intel(R) Kabylake GT1")
+CHIPSET(0x590A, kbl_gt1, "Intel(R) Kabylake GT1")
+CHIPSET(0x590B, kbl_gt1, "Intel(R) Kabylake GT1")
+CHIPSET(0x590E, kbl_gt1, "Intel(R) Kabylake GT1")
+CHIPSET(0x5913, kbl_gt1_5, "Intel(R) Kabylake GT1.5")
+CHIPSET(0x5915, kbl_gt1_5, "Intel(R) Kabylake GT1.5")
+CHIPSET(0x5917, kbl_gt1_5, "Intel(R) Kabylake GT1.5")
+CHIPSET(0x5912, kbl_gt2, "Intel(R) Kabylake GT2")
+CHIPSET(0x5916, kbl_gt2, "Intel(R) Kabylake GT2")
+CHIPSET(0x591A, kbl_gt2, "Intel(R) Kabylake GT2")
+CHIPSET(0x591B, kbl_gt2, "Intel(R) Kabylake GT2")
+CHIPSET(0x591D, kbl_gt2, "Intel(R) Kabylake GT2")
+CHIPSET(0x591E, kbl_gt2, "Intel(R) Kabylake GT2")
+CHIPSET(0x5921, kbl_gt2, "Intel(R) Kabylake GT2F")
+CHIPSET(0x5926, kbl_gt3, "Intel(R) Kabylake GT3")
+CHIPSET(0x592A, kbl_gt3, "Intel(R) Kabylake GT3")
+CHIPSET(0x592B, kbl_gt3, "Intel(R) Kabylake GT3")
+CHIPSET(0x5932, kbl_gt4, "Intel(R) Kabylake GT4")
+CHIPSET(0x593A, kbl_gt4, "Intel(R) Kabylake GT4")
+CHIPSET(0x593B, kbl_gt4, "Intel(R) Kabylake GT4")
+CHIPSET(0x593D, kbl_gt4, "Intel(R) Kabylake GT4")
 CHIPSET(0x22B0, chv,     "Intel(R) HD Graphics (Cherryview)")
 CHIPSET(0x22B1, chv,     "Intel(R) HD Graphics (Cherryview)")
 CHIPSET(0x22B2, chv,     "Intel(R) HD Graphics (Cherryview)")
diff --git a/src/mesa/drivers/dri/i965/brw_device_info.c b/src/mesa/drivers/dri/i965/brw_device_info.c
index 4550550..c58e4a5 100644
--- a/src/mesa/drivers/dri/i965/brw_device_info.c
+++ b/src/mesa/drivers/dri/i965/brw_device_info.c
@@ -371,6 +371,66 @@ static const struct brw_device_info brw_device_info_bxt = {
    }
 };
 
+/*
+ * Note: for all KBL SKUs, the PRM says SKL for GS entries, not SKL+.
+ * There's no KBL entry. Using the default SKL (GEN9) GS entries value.
+ */
+
+/*
+ * Both SKL and KBL support a maximum of 64 threads per
+ * Pixel Shader Dispatch (PSD) unit.
+ */
+#define  KBL_MAX_THREADS_PER_PSD 64
+
+static const struct brw_device_info brw_device_info_kbl_gt1 = {
+   GEN9_FEATURES,
+   .gt = 1,
+
+   .max_cs_threads = 7 * 6,
+   .max_wm_threads = KBL_MAX_THREADS_PER_PSD * 2,
+   .urb.size = 192,
+};
+
+static const struct brw_device_info brw_device_info_kbl_gt1_5 = {
+   GEN9_FEATURES,
+   .gt = 1,
+
+   .max_cs_threads = 7 * 6,
+   .max_wm_threads = KBL_MAX_THREADS_PER_PSD * 3,
+};
+
+static const struct brw_device_info brw_device_info_kbl_gt2 = {
+   GEN9_FEATURES,
+   .gt = 2,
+
+   .max_wm_threads = KBL_MAX_THREADS_PER_PSD * 3,
+};
+
+static const struct brw_device_info brw_device_info_kbl_gt3 = {
+   GEN9_FEATURES,
+   .gt = 3,
+
+   .max_wm_threads = KBL_MAX_THREADS_PER_PSD * 6,
+};
+
+static const struct brw_device_info brw_device_info_kbl_gt4 = {
+   GEN9_FEATURES,
+   .gt = 4,
+
+   .max_wm_threads = KBL_MAX_THREADS_PER_PSD * 9,
+   /*
+    * From the "L3 Allocation and Programming" documentation:
+    *
+    * "URB is limited to 1008KB due to programming restrictions.  This
+    *  is not a restriction of the L3 implementation, but of the FF and
+    *  other clients.  Therefore, in a GT4 implementation it is
+    *  possible for the programmed allocation of the L3 data array to
+    *  provide 3*384KB=1152KB for URB, but only 1008KB of this
+    *  will be used."
+    */
+   .urb.size = 1008 / 3,
+};
+
 const struct brw_device_info *
 brw_get_device_info(int devid)
 {
-- 
2.3.0