@@ -9,6 +9,7 @@
#include <linux/pm_domain.h>
#include <linux/pm_opp.h>
#include <soc/qcom/cmd-db.h>
+#include <soc/qcom/tcs.h>
#include <drm/drm_gem.h>
#include "a6xx_gpu.h"
@@ -1287,6 +1288,119 @@ static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu)
return 0;
}
+struct a6xx_bcm_data {
+ u32 buswidth;
+ unsigned int unit;
+ unsigned int width;
+ unsigned int vcd;
+ bool fixed;
+ unsigned int perfmode;
+ unsigned int perfmode_bw;
+};
+
+struct bcm_db {
+ __le32 unit;
+ __le16 width;
+ u8 vcd;
+ u8 reserved;
+};
+
+static int a6xx_gmu_rpmh_get_bcm_data(const struct a6xx_bcm *bcm,
+ struct a6xx_bcm_data *bcm_data)
+{
+ const struct bcm_db *data;
+ size_t count;
+
+ data = cmd_db_read_aux_data(bcm->name, &count);
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
+ if (!count)
+ return -EINVAL;
+
+ bcm_data->unit = le32_to_cpu(data->unit);
+ bcm_data->width = le16_to_cpu(data->width);
+ bcm_data->vcd = data->vcd;
+ bcm_data->fixed = bcm->fixed;
+ bcm_data->perfmode = bcm->perfmode;
+ bcm_data->perfmode_bw = bcm->perfmode_bw;
+ bcm_data->buswidth = bcm->buswidth;
+
+ return 0;
+}
+
+static void a6xx_gmu_rpmh_calc_bw_vote(struct a6xx_bcm_data *bcms,
+ int count, u32 bw, u32 *data)
+{
+ int i;
+
+ for (i = 0; i < count; i++) {
+ bool valid = true;
+ bool commit = false;
+ u64 peak, y;
+
+ if (i == count - 1 || bcms[i].vcd != bcms[i + 1].vcd)
+ commit = true;
+
+ if (bcms[i].fixed) {
+ if (!bw)
+ data[i] = BCM_TCS_CMD(commit, false, 0x0, 0x0);
+ else
+ data[i] = BCM_TCS_CMD(commit, true, 0x0,
+ bw >= bcms[i].perfmode_bw ?
+ bcms[i].perfmode : 0x0);
+ continue;
+ }
+
+ /* Multiple the bandwidth by the width of the connection */
+ peak = (u64)bw * bcms[i].width;
+ do_div(peak, bcms[i].buswidth);
+
+ /* Input bandwidth value is in KBps */
+ y = peak * 1000ULL;
+ do_div(y, bcms[i].unit);
+
+ /*
+ * If a bandwidth value was specified but the calculation ends
+ * rounding down to zero, set a minimum level
+ */
+ if (bw && y == 0)
+ y = 1;
+
+ y = min_t(u64, y, BCM_TCS_CMD_VOTE_MASK);
+ if (!y)
+ valid = false;
+
+ data[i] = BCM_TCS_CMD(commit, valid, y, y);
+ }
+}
+
+static int a6xx_gmu_rpmh_bw_votes_init(const struct a6xx_info *info, struct a6xx_gmu *gmu)
+{
+ struct a6xx_bcm_data bcms[3];
+ unsigned int bcm_count = 0;
+ int ret, index;
+
+ /* Retrieve BCM data from cmd-db and merge with a6xx_info bcm table */
+ for (index = 0; index < 3; index++) {
+ if (!info->bcm[index].name)
+ continue;
+
+ ret = a6xx_gmu_rpmh_get_bcm_data(&info->bcm[index], &bcms[index]);
+ if (ret)
+ return ret;
+
+ ++bcm_count;
+ }
+
+ /* Generate BCM votes values for each bandwidth & bcm */
+ for (index = 0; index < gmu->nr_gpu_bws; index++)
+ a6xx_gmu_rpmh_calc_bw_vote(bcms, bcm_count, gmu->gpu_bw_table[index],
+ gmu->gpu_bw_votes[index]);
+
+ return 0;
+}
+
/* Return the 'arc-level' for the given frequency */
static unsigned int a6xx_gmu_get_arc_level(struct device *dev,
unsigned long freq)
@@ -1390,12 +1504,15 @@ static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes,
* The GMU votes with the RPMh for itself and on behalf of the GPU but we need
* to construct the list of votes on the CPU and send it over. Query the RPMh
* voltage levels and build the votes
+ * The GMU can also vote for DDR interconnects, use the OPP bandwidth entries
+ * and BCM parameters to build the votes.
*/
static int a6xx_gmu_rpmh_votes_init(struct a6xx_gmu *gmu)
{
struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+ const struct a6xx_info *info = adreno_gpu->info->a6xx;
struct msm_gpu *gpu = &adreno_gpu->base;
int ret;
@@ -1407,6 +1524,10 @@ static int a6xx_gmu_rpmh_votes_init(struct a6xx_gmu *gmu)
ret |= a6xx_gmu_rpmh_arc_votes_init(gmu->dev, gmu->cx_arc_votes,
gmu->gmu_freqs, gmu->nr_gmu_freqs, "cx.lvl");
+ /* Build the interconnect votes */
+ if (adreno_gpu->info->quirks & ADRENO_QUIRK_GMU_BW_VOTE)
+ ret |= a6xx_gmu_rpmh_bw_votes_init(info, gmu);
+
return ret;
}
@@ -1442,6 +1563,38 @@ static int a6xx_gmu_build_freq_table(struct device *dev, unsigned long *freqs,
return index;
}
+static int a6xx_gmu_build_bw_table(struct device *dev, unsigned long *bandwidths,
+ u32 size)
+{
+ int count = dev_pm_opp_get_opp_count(dev);
+ struct dev_pm_opp *opp;
+ int i, index = 0;
+ unsigned int bandwidth = 1;
+
+ /*
+ * The OPP table doesn't contain the "off" bandwidth level so we need to
+ * add 1 to the table size to account for it
+ */
+
+ if (WARN(count + 1 > size,
+ "The GMU bandwidth table is being truncated\n"))
+ count = size - 1;
+
+ /* Set the "off" bandwidth */
+ bandwidths[index++] = 0;
+
+ for (i = 0; i < count; i++) {
+ opp = dev_pm_opp_find_bw_ceil(dev, &bandwidth, 0);
+ if (IS_ERR(opp))
+ break;
+
+ dev_pm_opp_put(opp);
+ bandwidths[index++] = bandwidth++;
+ }
+
+ return index;
+}
+
static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu)
{
struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
@@ -1472,6 +1625,16 @@ static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu)
gmu->current_perf_index = gmu->nr_gpu_freqs - 1;
+ /*
+ * The GMU also handles GPU Interconnect Votes so build a list
+ * of DDR bandwidths from the GPU OPP table
+ */
+ if (adreno_gpu->info->quirks & ADRENO_QUIRK_GMU_BW_VOTE)
+ gmu->nr_gpu_bws = a6xx_gmu_build_bw_table(&gpu->pdev->dev,
+ gmu->gpu_bw_table, ARRAY_SIZE(gmu->gpu_bw_table));
+
+ gmu->current_perf_index = gmu->nr_gpu_freqs - 1;
+
/* Build the list of RPMh votes that we'll send to the GMU */
return a6xx_gmu_rpmh_votes_init(gmu);
}
@@ -19,6 +19,14 @@ struct a6xx_gmu_bo {
u64 iova;
};
+struct a6xx_bcm {
+ char *name;
+ unsigned int buswidth;
+ bool fixed;
+ unsigned int perfmode;
+ unsigned int perfmode_bw;
+};
+
/*
* These define the different GMU wake up options - these define how both the
* CPU and the GMU bring up the hardware
@@ -82,6 +90,10 @@ struct a6xx_gmu {
unsigned long gpu_freqs[16];
u32 gx_arc_votes[16];
+ int nr_gpu_bws;
+ unsigned long gpu_bw_table[16];
+ u32 gpu_bw_votes[16][3];
+
int nr_gmu_freqs;
unsigned long gmu_freqs[4];
u32 cx_arc_votes[4];
@@ -44,6 +44,7 @@ struct a6xx_info {
u32 gmu_chipid;
u32 gmu_cgc_mode;
u32 prim_fifo_threshold;
+ const struct a6xx_bcm bcm[3];
};
struct a6xx_gpu {
The Adreno GMU Management Unit (GMU) can also scale DDR Bandwidth along the Frequency and Power Domain level, but by default we leave the OPP core scale the interconnect ddr path. In order to get the vote values to be used by the GPU Management Unit (GMU), we need to parse all the possible OPP Bandwidths and create a vote value to be send to the appropriate Bus Control Modules (BCMs) declared in the GPU info struct. The vote array will be used to dynamically generate the GMU bw_table sent during the GMU power-up. Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org> --- drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 163 ++++++++++++++++++++++++++++++++++ drivers/gpu/drm/msm/adreno/a6xx_gmu.h | 12 +++ drivers/gpu/drm/msm/adreno/a6xx_gpu.h | 1 + 3 files changed, 176 insertions(+)