x86/resctrl: Remove the limit on the number of CLOSID

Resctrl allocates and finds free CLOSID values using the bits of a u32.
This restricts the number of control groups that can be created by
user-space.

MPAM has an architectural limit of 2^16 CLOSID values, Intel x86 could
be extended beyond 32 values. There is at least one MPAM platform which
supports more than 32 CLOSID values.

Replace the fixed size bitmap with calls to the bitmap API to allocate
an array of a sufficient size.

ffs() returns '1' for bit 0, hence the existing code subtracts 1 from
the index to get the CLOSID value. find_first_bit() returns the bit
number which does not need adjusting.

  [ morse: fixed the off-by-one in the allocator and the wrong not-found
    value. Removed the limit. Rephrase the commit message. ]

Signed-off-by: Amit Singh Tomar <amitsinght@marvell.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-6-james.morse@arm.com

Author: Amit Singh Tomar

arch/x86/kernel/cpu/resctrl/rdtgroup.c

@@ -130,8 +130,8 @@ static bool resctrl_is_mbm_event(int e)
 }
 
 /*
- * Trivial allocator for CLOSIDs. Since h/w only supports a small number,
- * we can keep a bitmap of free CLOSIDs in a single integer.
+ * Trivial allocator for CLOSIDs. Use BITMAP APIs to manipulate a bitmap
+ * of free CLOSIDs.
  *
  * Using a global CLOSID across all resources has some advantages and
  * some drawbacks:
@@ -144,28 +144,43 @@ static bool resctrl_is_mbm_event(int e)
  * - Our choices on how to configure each resource become progressively more
  *   limited as the number of resources grows.
  */
-static unsigned long closid_free_map;
+static unsigned long *closid_free_map;
 static int closid_free_map_len;
 
 int closids_supported(void)
 {
 	return closid_free_map_len;
 }
 
-static void closid_init(void)
+static int closid_init(void)
 {
 	struct resctrl_schema *s;
-	u32 rdt_min_closid = 32;
+	u32 rdt_min_closid = ~0;
+
+	/* Monitor only platforms still call closid_init() */
+	if (list_empty(&resctrl_schema_all))
+		return 0;
 
 	/* Compute rdt_min_closid across all resources */
 	list_for_each_entry(s, &resctrl_schema_all, list)
 		rdt_min_closid = min(rdt_min_closid, s->num_closid);
 
-	closid_free_map = BIT_MASK(rdt_min_closid) - 1;
+	closid_free_map = bitmap_alloc(rdt_min_closid, GFP_KERNEL);
+	if (!closid_free_map)
+		return -ENOMEM;
+	bitmap_fill(closid_free_map, rdt_min_closid);
 
 	/* RESCTRL_RESERVED_CLOSID is always reserved for the default group */
-	__clear_bit(RESCTRL_RESERVED_CLOSID, &closid_free_map);
+	__clear_bit(RESCTRL_RESERVED_CLOSID, closid_free_map);
 	closid_free_map_len = rdt_min_closid;
+
+	return 0;
+}
+
+static void closid_exit(void)
+{
+	bitmap_free(closid_free_map);
+	closid_free_map = NULL;
 }
 
 static int closid_alloc(void)
@@ -182,12 +197,11 @@ static int closid_alloc(void)
 			return cleanest_closid;
 		closid = cleanest_closid;
 	} else {
-		closid = ffs(closid_free_map);
-		if (closid == 0)
+		closid = find_first_bit(closid_free_map, closid_free_map_len);
+		if (closid == closid_free_map_len)
 			return -ENOSPC;
-		closid--;
 	}
-	__clear_bit(closid, &closid_free_map);
+	__clear_bit(closid, closid_free_map);
 
 	return closid;
 }
@@ -196,7 +210,7 @@ void closid_free(int closid)
 {
 	lockdep_assert_held(&rdtgroup_mutex);
 
-	__set_bit(closid, &closid_free_map);
+	__set_bit(closid, closid_free_map);
 }
 
 /**
@@ -210,7 +224,7 @@ bool closid_allocated(unsigned int closid)
 {
 	lockdep_assert_held(&rdtgroup_mutex);
 
-	return !test_bit(closid, &closid_free_map);
+	return !test_bit(closid, closid_free_map);
 }
 
 /**
@@ -2765,20 +2779,22 @@ static int rdt_get_tree(struct fs_context *fc)
 		goto out_ctx;
 	}
 
-	closid_init();
+	ret = closid_init();
+	if (ret)
+		goto out_schemata_free;
 
 	if (resctrl_arch_mon_capable())
 		flags |= RFTYPE_MON;
 
 	ret = rdtgroup_add_files(rdtgroup_default.kn, flags);
 	if (ret)
-		goto out_schemata_free;
+		goto out_closid_exit;
 
 	kernfs_activate(rdtgroup_default.kn);
 
 	ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
 	if (ret < 0)
-		goto out_schemata_free;
+		goto out_closid_exit;
 
 	if (resctrl_arch_mon_capable()) {
 		ret = mongroup_create_dir(rdtgroup_default.kn,
@@ -2829,6 +2845,8 @@ static int rdt_get_tree(struct fs_context *fc)
 		kernfs_remove(kn_mongrp);
 out_info:
 	kernfs_remove(kn_info);
+out_closid_exit:
+	closid_exit();
 out_schemata_free:
 	schemata_list_destroy();
 out_ctx:
@@ -3076,6 +3094,7 @@ static void rdt_kill_sb(struct super_block *sb)
 	rmdir_all_sub();
 	rdt_pseudo_lock_release();
 	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
+	closid_exit();
 	schemata_list_destroy();
 	rdtgroup_destroy_root();
 	if (resctrl_arch_alloc_capable())