fs/resctrl: Update bit_usage to reflect io_alloc

The "shareable_bits" and "bit_usage" resctrl files associated with cache
resources give insight into how instances of a cache is used.

Update the annotated capacity bitmasks displayed by "bit_usage" to include the
cache portions allocated for I/O via the "io_alloc" feature. "shareable_bits"
is a global bitmask of shareable cache with I/O and can thus not present the
per-domain I/O allocations possible with the "io_alloc" feature. Revise the
"shareable_bits" documentation to direct users to "bit_usage" for accurate
cache usage information.

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://patch.msgid.link/e02a0d424129fd7f3e45822a559b1c614ae4652a.1762995456.git.babu.moger@amd.com

Documentation/filesystems/resctrl.rst

@@ -96,12 +96,19 @@ related to allocation:
 		must be set when writing a mask.
 
 "shareable_bits":
-		Bitmask of shareable resource with other executing
+		Bitmask of shareable resource with other executing entities
-		entities (e.g. I/O). User can use this when
+		(e.g. I/O). Applies to all instances of this resource. User
-		setting up exclusive cache partitions. Note that
+		can use this when setting up exclusive cache partitions.
-		some platforms support devices that have their
+		Note that some platforms support devices that have their
-		own settings for cache use which can over-ride
+		own settings for cache use which can over-ride these bits.
-		these bits.
+
+		When "io_alloc" is enabled, a portion of each cache instance can
+		be configured for shared use between hardware and software.
+		"bit_usage" should be used to see which portions of each cache
+		instance is configured for hardware use via "io_alloc" feature
+		because every cache instance can have its "io_alloc" bitmask
+		configured independently via "io_alloc_cbm".
+
 "bit_usage":
 		Annotated capacity bitmasks showing how all
 		instances of the resource are used. The legend is:
@@ -115,16 +122,16 @@ related to allocation:
 			"H":
 			      Corresponding region is used by hardware only
 			      but available for software use. If a resource
-			      has bits set in "shareable_bits" but not all
+			      has bits set in "shareable_bits" or "io_alloc_cbm"
-			      of these bits appear in the resource groups'
+			      but not all of these bits appear in the resource
-			      schematas then the bits appearing in
+			      groups' schemata then the bits appearing in
-			      "shareable_bits" but no resource group will
+			      "shareable_bits" or "io_alloc_cbm" but no
-			      be marked as "H".
+			      resource group will be marked as "H".
 			"X":
 			      Corresponding region is available for sharing and
-			      used by hardware and software. These are the
+			      used by hardware and software. These are the bits
-			      bits that appear in "shareable_bits" as
+			      that appear in "shareable_bits" or "io_alloc_cbm"
-			      well as a resource group's allocation.
+			      as well as a resource group's allocation.
 			"S":
 			      Corresponding region is used by software
 			      and available for sharing.

fs/resctrl/ctrlmondata.c

@@ -750,7 +750,7 @@ static int resctrl_io_alloc_init_cbm(struct resctrl_schema *s, u32 closid)
  * resource. Note that if Code Data Prioritization (CDP) is enabled, the number
  * of available CLOSIDs is reduced by half.
  */
-static u32 resctrl_io_alloc_closid(struct rdt_resource *r)
+u32 resctrl_io_alloc_closid(struct rdt_resource *r)
 {
 	if (resctrl_arch_get_cdp_enabled(r->rid))
 		return resctrl_arch_get_num_closid(r) / 2  - 1;

fs/resctrl/internal.h

@@ -442,6 +442,7 @@ int resctrl_io_alloc_cbm_show(struct kernfs_open_file *of, struct seq_file *seq,
 			      void *v);
 ssize_t resctrl_io_alloc_cbm_write(struct kernfs_open_file *of, char *buf,
 				   size_t nbytes, loff_t off);
+u32 resctrl_io_alloc_closid(struct rdt_resource *r);
 
 #ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK
 int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);

fs/resctrl/rdtgroup.c

@@ -1062,15 +1062,17 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 
 	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
-	hw_shareable = r->cache.shareable_bits;
 	list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
 		if (sep)
 			seq_putc(seq, ';');
+		hw_shareable = r->cache.shareable_bits;
 		sw_shareable = 0;
 		exclusive = 0;
 		seq_printf(seq, "%d=", dom->hdr.id);
 		for (i = 0; i < closids_supported(); i++) {
-			if (!closid_allocated(i))
+			if (!closid_allocated(i) ||
+			    (resctrl_arch_get_io_alloc_enabled(r) &&
+			     i == resctrl_io_alloc_closid(r)))
 				continue;
 			ctrl_val = resctrl_arch_get_config(r, dom, i,
 							   s->conf_type);
@@ -1098,6 +1100,21 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 				break;
 			}
 		}
+
+		/*
+		 * When the "io_alloc" feature is enabled, a portion of the cache
+		 * is configured for shared use between hardware and software.
+		 * Also, when CDP is enabled the CBMs of CDP_CODE and CDP_DATA
+		 * resources are kept in sync. So, the CBMs for "io_alloc" can
+		 * be accessed through either resource.
+		 */
+		if (resctrl_arch_get_io_alloc_enabled(r)) {
+			ctrl_val = resctrl_arch_get_config(r, dom,
+							   resctrl_io_alloc_closid(r),
+							   s->conf_type);
+			hw_shareable |= ctrl_val;
+		}
+
 		for (i = r->cache.cbm_len - 1; i >= 0; i--) {
 			pseudo_locked = dom->plr ? dom->plr->cbm : 0;
 			hwb = test_bit(i, &hw_shareable);