clk: qcom: Add support for RCG to register for DFS

Dynamic Frequency switch is a feature of clock controller by which request
from peripherals allows automatic switching frequency of input clock
without SW intervention. There are various performance levels associated
with a root clock. When the input performance state changes, the source
clocks and division ratios of the new performance state are loaded on to
RCG via HW and the RCG switches to new clock frequency when the RCG is in
DFS HW enabled mode.

Register the root clock generators(RCG) to switch to use the dfs clock ops
in the cases where DFS is enabled. The clk_round_rate() called by the clock
consumer would invoke the dfs determine clock ops and would read the DFS
performance level registers to identify all the frequencies supported and
update the frequency table. The DFS clock consumers would maintain these
frequency mapping and request the desired performance levels.

Signed-off-by: Taniya Das <tdas@codeaurora.org>
[sboyd@kernel.org: Rework registration logic to stop copying, change
recalc_rate() to index directly into the table if possible and fallback
to calculating on the fly with an assumed correct parent]
Signed-off-by: Stephen Boyd <sboyd@kernel.org>

2 files changed, 205 insertions, 0 deletions

diff --git a/drivers/clk/qcom/clk-rcg.h b/drivers/clk/qcom/clk-rcg.h
index dbd5a9e83554..e5eca8a1abe4 100644
--- a/drivers/clk/qcom/clk-rcg.h
+++ b/drivers/clk/qcom/clk-rcg.h
@@ -163,4 +163,15 @@ extern const struct clk_ops clk_pixel_ops;
 extern const struct clk_ops clk_gfx3d_ops;
 extern const struct clk_ops clk_rcg2_shared_ops;
 
+struct clk_rcg_dfs_data {
+        struct clk_rcg2 *rcg;
+        struct clk_init_data *init;
+};
+
+#define DEFINE_RCG_DFS(r) \
+        { .rcg = &r##_src, .init = &r##_init }
+
+extern int qcom_cc_register_rcg_dfs(struct regmap *regmap,
+                                    const struct clk_rcg_dfs_data *rcgs,
+                                    size_t len);
 #endif
diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c
index 52208d4165f4..d5d77f9ad170 100644
--- a/drivers/clk/qcom/clk-rcg2.c
+++ b/drivers/clk/qcom/clk-rcg2.c
@@ -12,6 +12,7 @@
 #include <linux/delay.h>
 #include <linux/regmap.h>
 #include <linux/math64.h>
+#include <linux/slab.h>
 
 #include <asm/div64.h>
 
@@ -40,6 +41,14 @@
 #define N_REG                   0xc
 #define D_REG                   0x10
 
+/* Dynamic Frequency Scaling */
+#define MAX_PERF_LEVEL          8
+#define SE_CMD_DFSR_OFFSET      0x14
+#define SE_CMD_DFS_EN           BIT(0)
+#define SE_PERF_DFSR(level)     (0x1c + 0x4 * (level))
+#define SE_PERF_M_DFSR(level)   (0x5c + 0x4 * (level))
+#define SE_PERF_N_DFSR(level)   (0x9c + 0x4 * (level))
+
 enum freq_policy {
         FLOOR,
         CEIL,
@@ -929,3 +938,188 @@ const struct clk_ops clk_rcg2_shared_ops = {
         .set_rate_and_parent = clk_rcg2_shared_set_rate_and_parent,
 };
 EXPORT_SYMBOL_GPL(clk_rcg2_shared_ops);
+
+/* Common APIs to be used for DFS based RCGR */
+static void clk_rcg2_dfs_populate_freq(struct clk_hw *hw, unsigned int l,
+                                       struct freq_tbl *f)
+{
+        struct clk_rcg2 *rcg = to_clk_rcg2(hw);
+        struct clk_hw *p;
+        unsigned long prate = 0;
+        u32 val, mask, cfg, mode;
+        int i, num_parents;
+
+        regmap_read(rcg->clkr.regmap, rcg->cmd_rcgr + SE_PERF_DFSR(l), &cfg);
+
+        mask = BIT(rcg->hid_width) - 1;
+        f->pre_div = 1;
+        if (cfg & mask)
+                f->pre_div = cfg & mask;
+
+        cfg &= CFG_SRC_SEL_MASK;
+        cfg >>= CFG_SRC_SEL_SHIFT;
+
+        num_parents = clk_hw_get_num_parents(hw);
+        for (i = 0; i < num_parents; i++) {
+                if (cfg == rcg->parent_map[i].cfg) {
+                        f->src = rcg->parent_map[i].src;
+                        p = clk_hw_get_parent_by_index(&rcg->clkr.hw, i);
+                        prate = clk_hw_get_rate(p);
+                }
+        }
+
+        mode = cfg & CFG_MODE_MASK;
+        mode >>= CFG_MODE_SHIFT;
+        if (mode) {
+                mask = BIT(rcg->mnd_width) - 1;
+                regmap_read(rcg->clkr.regmap, rcg->cmd_rcgr + SE_PERF_M_DFSR(l),
+                            &val);
+                val &= mask;
+                f->m = val;
+
+                regmap_read(rcg->clkr.regmap, rcg->cmd_rcgr + SE_PERF_N_DFSR(l),
+                            &val);
+                val = ~val;
+                val &= mask;
+                val += f->m;
+                f->n = val;
+        }
+
+        f->freq = calc_rate(prate, f->m, f->n, mode, f->pre_div);
+}
+
+static int clk_rcg2_dfs_populate_freq_table(struct clk_rcg2 *rcg)
+{
+        struct freq_tbl *freq_tbl;
+        int i;
+
+        freq_tbl = kcalloc(MAX_PERF_LEVEL, sizeof(*freq_tbl), GFP_KERNEL);
+        if (!freq_tbl)
+                return -ENOMEM;
+        rcg->freq_tbl = freq_tbl;
+
+        for (i = 0; i < MAX_PERF_LEVEL; i++)
+                clk_rcg2_dfs_populate_freq(&rcg->clkr.hw, i, freq_tbl + i);
+
+        return 0;
+}
+
+static int clk_rcg2_dfs_determine_rate(struct clk_hw *hw,
+                                   struct clk_rate_request *req)
+{
+        struct clk_rcg2 *rcg = to_clk_rcg2(hw);
+        int ret;
+
+        if (!rcg->freq_tbl) {
+                ret = clk_rcg2_dfs_populate_freq_table(rcg);
+                if (ret) {
+                        pr_err("Failed to update DFS tables for %s\n",
+                                        clk_hw_get_name(hw));
+                        return ret;
+                }
+        }
+
+        return clk_rcg2_determine_rate(hw, req);
+}
+
+static unsigned long
+clk_rcg2_dfs_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
+{
+        struct clk_rcg2 *rcg = to_clk_rcg2(hw);
+        u32 level, mask, cfg, m = 0, n = 0, mode, pre_div;
+
+        regmap_read(rcg->clkr.regmap,
+                    rcg->cmd_rcgr + SE_CMD_DFSR_OFFSET, &level);
+        level &= GENMASK(4, 1);
+        level >>= 1;
+
+        if (rcg->freq_tbl)
+                return rcg->freq_tbl[level].freq;
+
+        /*
+         * Assume that parent_rate is actually the parent because
+         * we can't do any better at figuring it out when the table
+         * hasn't been populated yet. We only populate the table
+         * in determine_rate because we can't guarantee the parents
+         * will be registered with the framework until then.
+         */
+        regmap_read(rcg->clkr.regmap, rcg->cmd_rcgr + SE_PERF_DFSR(level),
+                    &cfg);
+
+        mask = BIT(rcg->hid_width) - 1;
+        pre_div = 1;
+        if (cfg & mask)
+                pre_div = cfg & mask;
+
+        mode = cfg & CFG_MODE_MASK;
+        mode >>= CFG_MODE_SHIFT;
+        if (mode) {
+                mask = BIT(rcg->mnd_width) - 1;
+                regmap_read(rcg->clkr.regmap,
+                            rcg->cmd_rcgr + SE_PERF_M_DFSR(level), &m);
+                m &= mask;
+
+                regmap_read(rcg->clkr.regmap,
+                            rcg->cmd_rcgr + SE_PERF_N_DFSR(level), &n);
+                n = ~n;
+                n &= mask;
+                n += m;
+        }
+
+        return calc_rate(parent_rate, m, n, mode, pre_div);
+}
+
+static const struct clk_ops clk_rcg2_dfs_ops = {
+        .is_enabled = clk_rcg2_is_enabled,
+        .get_parent = clk_rcg2_get_parent,
+        .determine_rate = clk_rcg2_dfs_determine_rate,
+        .recalc_rate = clk_rcg2_dfs_recalc_rate,
+};
+
+static int clk_rcg2_enable_dfs(const struct clk_rcg_dfs_data *data,
+                               struct regmap *regmap)
+{
+        struct clk_rcg2 *rcg = data->rcg;
+        struct clk_init_data *init = data->init;
+        u32 val;
+        int ret;
+
+        ret = regmap_read(regmap, rcg->cmd_rcgr + SE_CMD_DFSR_OFFSET, &val);
+        if (ret)
+                return -EINVAL;
+
+        if (!(val & SE_CMD_DFS_EN))
+                return 0;
+