perf/x86/intel/uncore: Parse uncore discovery tables

A self-describing mechanism for the uncore PerfMon hardware has been
introduced with the latest Intel platforms. By reading through an MMIO
page worth of information, perf can 'discover' all the standard uncore
PerfMon registers in a machine.

The discovery mechanism relies on BIOS's support. With a proper BIOS,
a PCI device with the unique capability ID 0x23 can be found on each
die. Perf can retrieve the information of all available uncore PerfMons
from the device via MMIO. The information is composed of one global
discovery table and several unit discovery tables.
- The global discovery table includes global uncore information of the
  die, e.g., the address of the global control register, the offset of
  the global status register, the number of uncore units, the offset of
  unit discovery tables, etc.
- The unit discovery table includes generic uncore unit information,
  e.g., the access type, the counter width, the address of counters,
  the address of the counter control, the unit ID, the unit type, etc.
  The unit is also called "box" in the code.
Perf can provide basic uncore support based on this information
with the following patches.

To locate the PCI device with the discovery tables, check the generic
PCI ID first. If it doesn't match, go through the entire PCI device tree
and locate the device with the unique capability ID.

The uncore information is similar among dies. To save parsing time and
space, only completely parse and store the discovery tables on the first
die and the first box of each die. The parsed information is stored in
an
RB tree structure, intel_uncore_discovery_type. The size of the stored
discovery tables varies among platforms. It's around 4KB for a Sapphire
Rapids server.

If a BIOS doesn't support the 'discovery' mechanism, the uncore driver
will exit with -ENODEV. There is nothing changed.

Add a module parameter to disable the discovery feature. If a BIOS gets
the discovery tables wrong, users can have an option to disable the
feature. For the current patchset, the uncore driver will exit with
-ENODEV. In the future, it may fall back to the hardcode uncore driver
on a known platform.

Signed-off-by: Kan Liang <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

Author: Kan Liang

arch/x86/events/intel/Makefile

@@ -3,6 +3,6 @@ obj-$(CONFIG_CPU_SUP_INTEL)		+= core.o bts.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= ds.o knc.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= lbr.o p4.o p6.o pt.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel-uncore.o
-intel-uncore-objs			:= uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o
+intel-uncore-objs			:= uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o uncore_discovery.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE)	+= intel-cstate.o
 intel-cstate-objs			:= cstate.o

arch/x86/events/intel/uncore.c

@@ -4,7 +4,12 @@
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
 #include "uncore.h"
+#include "uncore_discovery.h"
 
+static bool uncore_no_discover;
+module_param(uncore_no_discover, bool, 0);
+MODULE_PARM_DESC(uncore_no_discover, "Don't enable the Intel uncore PerfMon discovery mechanism "
+				     "(default: enable the discovery mechanism).");
 static struct intel_uncore_type *empty_uncore[] = { NULL, };
 struct intel_uncore_type **uncore_msr_uncores = empty_uncore;
 struct intel_uncore_type **uncore_pci_uncores = empty_uncore;
@@ -1637,6 +1642,9 @@ static const struct intel_uncore_init_fun snr_uncore_init __initconst = {
 	.mmio_init = snr_uncore_mmio_init,
 };
 
+static const struct intel_uncore_init_fun generic_uncore_init __initconst = {
+};
+
 static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP,		&nhm_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM,		&nhm_uncore_init),
@@ -1684,17 +1692,21 @@ static int __init intel_uncore_init(void)
 	struct intel_uncore_init_fun *uncore_init;
 	int pret = 0, cret = 0, mret = 0, ret;
 
-	id = x86_match_cpu(intel_uncore_match);
-	if (!id)
-		return -ENODEV;
-
 	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return -ENODEV;
 
 	__uncore_max_dies =
 		topology_max_packages() * topology_max_die_per_package();
 
-	uncore_init = (struct intel_uncore_init_fun *)id->driver_data;
+	id = x86_match_cpu(intel_uncore_match);
+	if (!id) {
+		if (!uncore_no_discover && intel_uncore_has_discovery_tables())
+			uncore_init = (struct intel_uncore_init_fun *)&generic_uncore_init;
+		else
+			return -ENODEV;
+	} else
+		uncore_init = (struct intel_uncore_init_fun *)id->driver_data;
+
 	if (uncore_init->pci_init) {
 		pret = uncore_init->pci_init();
 		if (!pret)
@@ -1711,8 +1723,10 @@ static int __init intel_uncore_init(void)
 		mret = uncore_mmio_init();
 	}
 
-	if (cret && pret && mret)
-		return -ENODEV;
+	if (cret && pret && mret) {
+		ret = -ENODEV;
+		goto free_discovery;
+	}
 
 	/* Install hotplug callbacks to setup the targets for each package */
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
@@ -1727,6 +1741,8 @@ static int __init intel_uncore_init(void)
 	uncore_types_exit(uncore_msr_uncores);
 	uncore_types_exit(uncore_mmio_uncores);
 	uncore_pci_exit();
+free_discovery:
+	intel_uncore_clear_discovery_tables();
 	return ret;
 }
 module_init(intel_uncore_init);
@@ -1737,5 +1753,6 @@ static void __exit intel_uncore_exit(void)
 	uncore_types_exit(uncore_msr_uncores);
 	uncore_types_exit(uncore_mmio_uncores);
 	uncore_pci_exit();
+	intel_uncore_clear_discovery_tables();
 }
 module_exit(intel_uncore_exit);