perf/x86/intel/uncore: Add domain global init callback

In the Intel uncore self-describing mechanism, the Global Control
Register freeze_all bit is SoC-wide and propagates to all uncore PMUs.

On Diamond Rapids, this bit is set at power-on, unlike some prior
platforms.  Add a global_init callback to unfreeze all PMON units.

Signed-off-by: Zide Chen <zide.chen@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://patch.msgid.link/20251231224233.113839-7-zide.chen@intel.com

arch/x86/events/intel/uncore.c

@@ -1697,6 +1697,21 @@ static int __init uncore_mmio_init(void)
 	return ret;
 }
 
+static int uncore_mmio_global_init(u64 ctl)
+{
+	void __iomem *io_addr;
+
+	io_addr = ioremap(ctl, sizeof(ctl));
+	if (!io_addr)
+		return -ENOMEM;
+
+	/* Clear freeze bit (0) to enable all counters. */
+	writel(0, io_addr);
+
+	iounmap(io_addr);
+	return 0;
+}
+
 static const struct uncore_plat_init nhm_uncore_init __initconst = {
 	.cpu_init = nhm_uncore_cpu_init,
 };
@@ -1839,6 +1854,7 @@ static const struct uncore_plat_init dmr_uncore_init __initconst = {
 	.domain[0].units_ignore = dmr_uncore_imh_units_ignore,
 	.domain[1].discovery_base = CBB_UNCORE_DISCOVERY_MSR,
 	.domain[1].units_ignore = dmr_uncore_cbb_units_ignore,
+	.domain[1].global_init = uncore_mmio_global_init,
 };
 
 static const struct uncore_plat_init generic_uncore_init __initconst = {

arch/x86/events/intel/uncore.h

@@ -51,6 +51,8 @@ struct uncore_discovery_domain {
 	/* MSR address or PCI device used as the discovery base */
 	u32	discovery_base;
 	bool	base_is_pci;
+	int	(*global_init)(u64 ctl);
+
 	/* The units in the discovery table should be ignored. */
 	int	*units_ignore;
 };

arch/x86/events/intel/uncore_discovery.c

@@ -286,6 +286,9 @@ static int __parse_discovery_table(struct uncore_discovery_domain *domain,
 	if (!io_addr)
 		return -ENOMEM;
 
+	if (domain->global_init && domain->global_init(global.ctl))
+		return -ENODEV;
+
 	/* Parsing Unit Discovery State */
 	for (i = 0; i < global.max_units; i++) {
 		memcpy_fromio(&unit, io_addr + (i + 1) * (global.stride * 8),