diff mbox series

[v5,11/11] MIPS: CPS: Boot CPUs in secondary clusters

Message ID 20240711082656.1889440-12-arikalo@gmail.com (mailing list archive)
State Superseded
Headers show
Series MIPS: Support I6500 multi-cluster configuration | expand

Commit Message

Aleksandar Rikalo July 11, 2024, 8:26 a.m. UTC
From: Paul Burton <paulburton@kernel.org>

Probe for & boot CPUs (cores & VPs) in secondary clusters (ie. not the
cluster that began booting Linux) when they are present in systems with
CM 3.5 or higher.

Signed-off-by: Paul Burton <paulburton@kernel.org>
Signed-off-by: Chao-ying Fu <cfu@wavecomp.com>
Signed-off-by: Dragan Mladjenovic <dragan.mladjenovic@syrmia.com>
Signed-off-by: Aleksandar Rikalo <arikalo@gmail.com>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
---
 arch/mips/include/asm/mips-cm.h |  18 +++
 arch/mips/include/asm/smp-cps.h |   1 +
 arch/mips/kernel/mips-cm.c      |   4 +-
 arch/mips/kernel/smp-cps.c      | 208 ++++++++++++++++++++++++++++----
 4 files changed, 207 insertions(+), 24 deletions(-)
diff mbox series

Patch

diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h
index c2930a75b7e4..65a46b35a218 100644
--- a/arch/mips/include/asm/mips-cm.h
+++ b/arch/mips/include/asm/mips-cm.h
@@ -251,6 +251,12 @@  GCR_ACCESSOR_RW(32, 0x130, l2_config)
 GCR_ACCESSOR_RO(32, 0x150, sys_config2)
 #define CM_GCR_SYS_CONFIG2_MAXVPW		GENMASK(3, 0)
 
+/* GCR_L2-RAM_CONFIG - Configuration & status of L2 cache RAMs */
+GCR_ACCESSOR_RW(64, 0x240, l2_ram_config)
+#define CM_GCR_L2_RAM_CONFIG_PRESENT		BIT(31)
+#define CM_GCR_L2_RAM_CONFIG_HCI_DONE		BIT(30)
+#define CM_GCR_L2_RAM_CONFIG_HCI_SUPPORTED	BIT(29)
+
 /* GCR_L2_PFT_CONTROL - Controls hardware L2 prefetching */
 GCR_ACCESSOR_RW(32, 0x300, l2_pft_control)
 #define CM_GCR_L2_PFT_CONTROL_PAGEMASK		GENMASK(31, 12)
@@ -262,6 +268,18 @@  GCR_ACCESSOR_RW(32, 0x308, l2_pft_control_b)
 #define CM_GCR_L2_PFT_CONTROL_B_CEN		BIT(8)
 #define CM_GCR_L2_PFT_CONTROL_B_PORTID		GENMASK(7, 0)
 
+/* GCR_L2_TAG_ADDR - Access addresses in L2 cache tags */
+GCR_ACCESSOR_RW(64, 0x600, l2_tag_addr)
+
+/* GCR_L2_TAG_STATE - Access L2 cache tag state */
+GCR_ACCESSOR_RW(64, 0x608, l2_tag_state)
+
+/* GCR_L2_DATA - Access data in L2 cache lines */
+GCR_ACCESSOR_RW(64, 0x610, l2_data)
+
+/* GCR_L2_ECC - Access ECC information from L2 cache lines */
+GCR_ACCESSOR_RW(64, 0x618, l2_ecc)
+
 /* GCR_L2SM_COP - L2 cache op state machine control */
 GCR_ACCESSOR_RW(32, 0x620, l2sm_cop)
 #define CM_GCR_L2SM_COP_PRESENT			BIT(31)
diff --git a/arch/mips/include/asm/smp-cps.h b/arch/mips/include/asm/smp-cps.h
index a629e948a6fd..10d3ebd890cb 100644
--- a/arch/mips/include/asm/smp-cps.h
+++ b/arch/mips/include/asm/smp-cps.h
@@ -23,6 +23,7 @@  struct core_boot_config {
 };
 
 struct cluster_boot_config {
+	unsigned long *core_power;
 	struct core_boot_config *core_config;
 };
 
diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c
index 3eb2cfb893e1..9854bc2b6895 100644
--- a/arch/mips/kernel/mips-cm.c
+++ b/arch/mips/kernel/mips-cm.c
@@ -308,7 +308,9 @@  void mips_cm_lock_other(unsigned int cluster, unsigned int core,
 		      FIELD_PREP(CM3_GCR_Cx_OTHER_VP, vp);
 
 		if (cm_rev >= CM_REV_CM3_5) {
-			val |= CM_GCR_Cx_OTHER_CLUSTER_EN;
+			if (cluster != cpu_cluster(&current_cpu_data))
+				val |= CM_GCR_Cx_OTHER_CLUSTER_EN;
+			val |= CM_GCR_Cx_OTHER_GIC_EN;
 			val |= FIELD_PREP(CM_GCR_Cx_OTHER_CLUSTER, cluster);
 			val |= FIELD_PREP(CM_GCR_Cx_OTHER_BLOCK, block);
 		} else {
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index 1954c9e912b2..ae814fdb930c 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -36,12 +36,56 @@  enum label_id {
 
 UASM_L_LA(_not_nmi)
 
-static DECLARE_BITMAP(core_power, NR_CPUS);
 static uint32_t core_entry_reg;
 static phys_addr_t cps_vec_pa;
 
 struct cluster_boot_config *mips_cps_cluster_bootcfg;
 
+static void power_up_other_cluster(unsigned int cluster)
+{
+	u32 stat, seq_state;
+	unsigned int timeout;
+
+	mips_cm_lock_other(cluster, CM_GCR_Cx_OTHER_CORE_CM, 0,
+			   CM_GCR_Cx_OTHER_BLOCK_LOCAL);
+	stat = read_cpc_co_stat_conf();
+	mips_cm_unlock_other();
+
+	seq_state = stat & CPC_Cx_STAT_CONF_SEQSTATE;
+	seq_state >>= __ffs(CPC_Cx_STAT_CONF_SEQSTATE);
+	if (seq_state == CPC_Cx_STAT_CONF_SEQSTATE_U5)
+		return;
+
+	/* Set endianness & power up the CM */
+	mips_cm_lock_other(cluster, 0, 0, CM_GCR_Cx_OTHER_BLOCK_GLOBAL);
+	write_cpc_redir_sys_config(IS_ENABLED(CONFIG_CPU_BIG_ENDIAN));
+	write_cpc_redir_pwrup_ctl(1);
+	mips_cm_unlock_other();
+
+	/* Wait for the CM to start up */
+	timeout = 1000;
+	mips_cm_lock_other(cluster, CM_GCR_Cx_OTHER_CORE_CM, 0,
+			   CM_GCR_Cx_OTHER_BLOCK_LOCAL);
+	while (1) {
+		stat = read_cpc_co_stat_conf();
+		seq_state = stat & CPC_Cx_STAT_CONF_SEQSTATE;
+		seq_state >>= __ffs(CPC_Cx_STAT_CONF_SEQSTATE);
+		if (seq_state == CPC_Cx_STAT_CONF_SEQSTATE_U5)
+			break;
+
+		if (timeout) {
+			mdelay(1);
+			timeout--;
+		} else {
+			pr_warn("Waiting for cluster %u CM to power up... STAT_CONF=0x%x\n",
+				cluster, stat);
+			mdelay(1000);
+		}
+	}
+
+	mips_cm_unlock_other();
+}
+
 static unsigned __init core_vpe_count(unsigned int cluster, unsigned core)
 {
 	return min(smp_max_threads, mips_cps_numvps(cluster, core));
@@ -152,6 +196,9 @@  static void __init cps_smp_setup(void)
 			pr_cont(",");
 		pr_cont("{");
 
+		if (mips_cm_revision() >= CM_REV_CM3_5)
+			power_up_other_cluster(cl);
+
 		ncores = mips_cps_numcores(cl);
 		for (c = 0; c < ncores; c++) {
 			core_vpes = core_vpe_count(cl, c);
@@ -179,8 +226,8 @@  static void __init cps_smp_setup(void)
 
 	/* Indicate present CPUs (CPU being synonymous with VPE) */
 	for (v = 0; v < min_t(unsigned, nvpes, NR_CPUS); v++) {
-		set_cpu_possible(v, cpu_cluster(&cpu_data[v]) == 0);
-		set_cpu_present(v, cpu_cluster(&cpu_data[v]) == 0);
+		set_cpu_possible(v, true);
+		set_cpu_present(v, true);
 		__cpu_number_map[v] = v;
 		__cpu_logical_map[v] = v;
 	}
@@ -188,9 +235,6 @@  static void __init cps_smp_setup(void)
 	/* Set a coherent default CCA (CWB) */
 	change_c0_config(CONF_CM_CMASK, 0x5);
 
-	/* Core 0 is powered up (we're running on it) */
-	bitmap_set(core_power, 0, 1);
-
 	/* Initialise core 0 */
 	mips_cps_core_init();
 
@@ -272,6 +316,10 @@  static void __init cps_prepare_cpus(unsigned int max_cpus)
 			goto err_out;
 		mips_cps_cluster_bootcfg[cl].core_config = core_bootcfg;
 
+		mips_cps_cluster_bootcfg[cl].core_power =
+			kcalloc(BITS_TO_LONGS(ncores), sizeof(unsigned long),
+				GFP_KERNEL);
+
 		/* Allocate VPE boot configuration structs */
 		for (c = 0; c < ncores; c++) {
 			core_vpes = core_vpe_count(cl, c);
@@ -283,11 +331,12 @@  static void __init cps_prepare_cpus(unsigned int max_cpus)
 		}
 	}
 
-	/* Mark this CPU as booted */
+	/* Mark this CPU as powered up & booted */
 	cl = cpu_cluster(&current_cpu_data);
 	c = cpu_core(&current_cpu_data);
 	cluster_bootcfg = &mips_cps_cluster_bootcfg[cl];
 	core_bootcfg = &cluster_bootcfg->core_config[c];
+	bitmap_set(cluster_bootcfg->core_power, cpu_core(&current_cpu_data), 1);
 	atomic_set(&core_bootcfg->vpe_mask, 1 << cpu_vpe_id(&current_cpu_data));
 
 	return;
@@ -315,13 +364,118 @@  static void __init cps_prepare_cpus(unsigned int max_cpus)
 	}
 }
 
-static void boot_core(unsigned int core, unsigned int vpe_id)
+static void init_cluster_l2(void)
 {
-	u32 stat, seq_state;
-	unsigned timeout;
+	u32 l2_cfg, l2sm_cop, result;
+
+	while (1) {
+		l2_cfg = read_gcr_redir_l2_ram_config();
+
+		/* If HCI is not supported, use the state machine below */
+		if (!(l2_cfg & CM_GCR_L2_RAM_CONFIG_PRESENT))
+			break;
+		if (!(l2_cfg & CM_GCR_L2_RAM_CONFIG_HCI_SUPPORTED))
+			break;
+
+		/* If the HCI_DONE bit is set, we're finished */
+		if (l2_cfg & CM_GCR_L2_RAM_CONFIG_HCI_DONE)
+			return;
+	}
+
+	l2sm_cop = read_gcr_redir_l2sm_cop();
+	if (WARN(!(l2sm_cop & CM_GCR_L2SM_COP_PRESENT),
+		 "L2 init not supported on this system yet"))
+		return;
+
+	/* Clear L2 tag registers */
+	write_gcr_redir_l2_tag_state(0);
+	write_gcr_redir_l2_ecc(0);
+
+	/* Ensure the L2 tag writes complete before the state machine starts */
+	mb();
+
+	/* Wait for the L2 state machine to be idle */
+	do {
+		l2sm_cop = read_gcr_redir_l2sm_cop();
+	} while (l2sm_cop & CM_GCR_L2SM_COP_RUNNING);
+
+	/* Start a store tag operation */
+	l2sm_cop = CM_GCR_L2SM_COP_TYPE_IDX_STORETAG;
+	l2sm_cop <<= __ffs(CM_GCR_L2SM_COP_TYPE);
+	l2sm_cop |= CM_GCR_L2SM_COP_CMD_START;
+	write_gcr_redir_l2sm_cop(l2sm_cop);
+
+	/* Ensure the state machine starts before we poll for completion */
+	mb();
+
+	/* Wait for the operation to be complete */
+	do {
+		l2sm_cop = read_gcr_redir_l2sm_cop();
+		result = l2sm_cop & CM_GCR_L2SM_COP_RESULT;
+		result >>= __ffs(CM_GCR_L2SM_COP_RESULT);
+	} while (!result);
+
+	WARN(result != CM_GCR_L2SM_COP_RESULT_DONE_OK,
+	     "L2 state machine failed cache init with error %u\n", result);
+}
+
+static void boot_core(unsigned int cluster, unsigned int core,
+		      unsigned int vpe_id)
+{
+	struct cluster_boot_config *cluster_cfg;
+	u32 access, stat, seq_state;
+	unsigned int timeout, ncores;
+
+	cluster_cfg = &mips_cps_cluster_bootcfg[cluster];
+	ncores = mips_cps_numcores(cluster);
+
+	if ((cluster != cpu_cluster(&current_cpu_data)) &&
+	    bitmap_empty(cluster_cfg->core_power, ncores)) {
+		power_up_other_cluster(cluster);
+
+		mips_cm_lock_other(cluster, core, 0,
+				   CM_GCR_Cx_OTHER_BLOCK_GLOBAL);
+
+		/* Ensure cluster GCRs are where we expect */
+		write_gcr_redir_base(read_gcr_base());
+		write_gcr_redir_cpc_base(read_gcr_cpc_base());
+		write_gcr_redir_gic_base(read_gcr_gic_base());
+
+		init_cluster_l2();
+
+		/* Mirror L2 configuration */
+		write_gcr_redir_l2_only_sync_base(read_gcr_l2_only_sync_base());
+		write_gcr_redir_l2_pft_control(read_gcr_l2_pft_control());
+		write_gcr_redir_l2_pft_control_b(read_gcr_l2_pft_control_b());
+
+		/* Mirror ECC/parity setup */
+		write_gcr_redir_err_control(read_gcr_err_control());
+
+		/* Set BEV base */
+		write_gcr_redir_bev_base(core_entry_reg);
+
+		mips_cm_unlock_other();
+	}
+
+	if (cluster != cpu_cluster(&current_cpu_data)) {
+		mips_cm_lock_other(cluster, core, 0,
+				   CM_GCR_Cx_OTHER_BLOCK_GLOBAL);
+
+		/* Ensure the core can access the GCRs */
+		access = read_gcr_redir_access();
+		access |= BIT(core);
+		write_gcr_redir_access(access);
+
+		mips_cm_unlock_other();
+	} else {
+		/* Ensure the core can access the GCRs */
+		access = read_gcr_access();
+		access |= BIT(core);
+		write_gcr_access(access);
+	}
 
 	/* Select the appropriate core */
-	mips_cm_lock_other(0, core, 0, CM_GCR_Cx_OTHER_BLOCK_LOCAL);
+	mips_cm_lock_other(cluster, core, 0, CM_GCR_Cx_OTHER_BLOCK_LOCAL);
 
 	/* Set its reset vector */
 	write_gcr_co_reset_base(core_entry_reg);
@@ -332,9 +486,6 @@  static void boot_core(unsigned int core, unsigned int vpe_id)
 	/* Start it with the legacy memory map and exception base */
 	write_gcr_co_reset_ext_base(CM_GCR_Cx_RESET_EXT_BASE_UEB);
 
-	/* Ensure the core can access the GCRs */
-	set_gcr_access(1 << core);
-
 	if (mips_cpc_present()) {
 		/* Reset the core */
 		mips_cpc_lock_other(core);
@@ -384,7 +535,17 @@  static void boot_core(unsigned int core, unsigned int vpe_id)
 	mips_cm_unlock_other();
 
 	/* The core is now powered up */
-	bitmap_set(core_power, core, 1);
+	bitmap_set(cluster_cfg->core_power, core, 1);
+
+	/*
+	 * Restore CM_PWRUP=0 so that the CM can power down if all the cores in
+	 * the cluster do (eg. if they're all removed via hotplug.
+	 */
+	if (mips_cm_revision() >= CM_REV_CM3_5) {
+		mips_cm_lock_other(cluster, 0, 0, CM_GCR_Cx_OTHER_BLOCK_GLOBAL);
+		write_cpc_redir_pwrup_ctl(0);
+		mips_cm_unlock_other();
+	}
 }
 
 static void remote_vpe_boot(void *dummy)
@@ -410,10 +571,6 @@  static int cps_boot_secondary(int cpu, struct task_struct *idle)
 	unsigned int remote;
 	int err;
 
-	/* We don't yet support booting CPUs in other clusters */
-	if (cpu_cluster(&cpu_data[cpu]) != cpu_cluster(&raw_current_cpu_data))
-		return -ENOSYS;
-
 	vpe_cfg->pc = (unsigned long)&smp_bootstrap;
 	vpe_cfg->sp = __KSTK_TOS(idle);
 	vpe_cfg->gp = (unsigned long)task_thread_info(idle);
@@ -422,14 +579,15 @@  static int cps_boot_secondary(int cpu, struct task_struct *idle)
 
 	preempt_disable();
 
-	if (!test_bit(core, core_power)) {
+	if (!test_bit(core, cluster_cfg->core_power)) {
 		/* Boot a VPE on a powered down core */
-		boot_core(core, vpe_id);
+		boot_core(cluster, core, vpe_id);
 		goto out;
 	}
 
 	if (cpu_has_vp) {
-		mips_cm_lock_other(0, core, vpe_id, CM_GCR_Cx_OTHER_BLOCK_LOCAL);
+		mips_cm_lock_other(cluster, core, vpe_id,
+				   CM_GCR_Cx_OTHER_BLOCK_LOCAL);
 		write_gcr_co_reset_base(core_entry_reg);
 		mips_cm_unlock_other();
 	}
@@ -636,11 +794,15 @@  static void cps_cpu_die(unsigned int cpu) { }
 
 static void cps_cleanup_dead_cpu(unsigned cpu)
 {
+	unsigned int cluster = cpu_cluster(&cpu_data[cpu]);
 	unsigned core = cpu_core(&cpu_data[cpu]);
 	unsigned int vpe_id = cpu_vpe_id(&cpu_data[cpu]);
 	ktime_t fail_time;
 	unsigned stat;
 	int err;
+	struct cluster_boot_config *cluster_cfg;
+
+	cluster_cfg = &mips_cps_cluster_bootcfg[cluster];
 
 	/*
 	 * Now wait for the CPU to actually offline. Without doing this that
@@ -692,7 +854,7 @@  static void cps_cleanup_dead_cpu(unsigned cpu)
 		} while (1);
 
 		/* Indicate the core is powered off */
-		bitmap_clear(core_power, core, 1);
+		bitmap_clear(cluster_cfg->core_power, core, 1);
 	} else if (cpu_has_mipsmt) {
 		/*
 		 * Have a CPU with access to the offlined CPUs registers wait