6.6 build check

.github/workflows/pull-request.yml

@@ -11,10 +11,10 @@ on:
 
 jobs:
   StaticCheck:
-    uses: bytedance/kernel/.github/workflows/static.yml@5.4.143-velinux
+    uses: mistachio/kernel/.github/workflows/static.yml@5.4.143-velinux
     secrets:
       ssh_key: ${{ secrets.SSH_KEY }}
   BuildAndTestKernel:
-    uses: bytedance/kernel/.github/workflows/build-and-test.yml@5.4.143-velinux
+    uses: mistachio/kernel/.github/workflows/build-and-test.yml@5.4.143-velinux
     secrets:
-      ssh_key: ${{ secrets.SSH_KEY }}
+      ssh_key: ${{ secrets.SSH_KEY }} 

Documentation/arch/x86/resctrl.rst

@@ -35,7 +35,7 @@ about the feature from resctrl's info directory.
 
 To use the feature mount the file system::
 
- # mount -t resctrl resctrl [-o cdp[,cdpl2][,mba_MBps]] /sys/fs/resctrl
+ # mount -t resctrl resctrl [-o cdp[,cdpl2][,mba_MBps][,debug]] /sys/fs/resctrl
 
 mount options are:
 
@@ -45,7 +45,10 @@ mount options are:
 	Enable code/data prioritization in L2 cache allocations.
 "mba_MBps":
 	Enable the MBA Software Controller(mba_sc) to specify MBA
-	bandwidth in MBps
+	bandwidth in MiBps
+"debug":
+	Make debug files accessible. Available debug files are annotated with
+	"Available only with debug option".
 
 L2 and L3 CDP are controlled separately.
 
@@ -306,7 +309,14 @@ All groups contain the following files:
 "tasks":
 	Reading this file shows the list of all tasks that belong to
 	this group. Writing a task id to the file will add a task to the
-	group. If the group is a CTRL_MON group the task is removed from
+	group. Multiple tasks can be added by separating the task ids
+	with commas. Tasks will be assigned sequentially. Multiple
+	failures are not supported. A single failure encountered while
+	attempting to assign a task will cause the operation to abort and
+	already added tasks before the failure will remain in the group.
+	Failures will be logged to /sys/fs/resctrl/info/last_cmd_status.
+
+	If the group is a CTRL_MON group the task is removed from
 	whichever previous CTRL_MON group owned the task and also from
 	any MON group that owned the task. If the group is a MON group,
 	then the task must already belong to the CTRL_MON parent of this
@@ -349,6 +359,10 @@ When control is enabled all CTRL_MON groups will also contain:
 	file. On successful pseudo-locked region creation the mode will
 	automatically change to "pseudo-locked".
 
+"ctrl_hw_id":
+	Available only with debug option. The identifier used by hardware
+	for the control group. On x86 this is the CLOSID.
+
 When monitoring is enabled all MON groups will also contain:
 
 "mon_data":
@@ -361,6 +375,14 @@ When monitoring is enabled all MON groups will also contain:
 	all tasks in the group. In CTRL_MON groups these files provide
 	the sum for all tasks in the CTRL_MON group and all tasks in
 	MON groups. Please see example section for more details on usage.
+	On systems with Sub-NUMA Cluster (SNC) enabled there are extra
+	directories for each node (located within the "mon_L3_XX" directory
+	for the L3 cache they occupy). These are named "mon_sub_L3_YY"
+	where "YY" is the node number.
+
+"mon_hw_id":
+	Available only with debug option. The identifier used by hardware
+	for the monitor group. On x86 this is the RMID.
 
 Resource allocation rules
 -------------------------
@@ -428,6 +450,12 @@ during mkdir.
 max_threshold_occupancy is a user configurable value to determine the
 occupancy at which an RMID can be freed.
 
+The mon_llc_occupancy_limbo tracepoint gives the precise occupancy in bytes
+for a subset of RMID that are not immediately available for allocation.
+This can't be relied on to produce output every second, it may be necessary
+to attempt to create an empty monitor group to force an update. Output may
+only be produced if creation of a control or monitor group fails.
+
 Schemata files - general concepts
 ---------------------------------
 Each line in the file describes one resource. The line starts with
@@ -460,6 +488,29 @@ if non-contiguous 1s value is supported. On a system with a 20-bit mask
 each bit represents 5% of the capacity of the cache. You could partition
 the cache into four equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
 
+Notes on Sub-NUMA Cluster mode
+==============================
+When SNC mode is enabled, Linux may load balance tasks between Sub-NUMA
+nodes much more readily than between regular NUMA nodes since the CPUs
+on Sub-NUMA nodes share the same L3 cache and the system may report
+the NUMA distance between Sub-NUMA nodes with a lower value than used
+for regular NUMA nodes.
+
+The top-level monitoring files in each "mon_L3_XX" directory provide
+the sum of data across all SNC nodes sharing an L3 cache instance.
+Users who bind tasks to the CPUs of a specific Sub-NUMA node can read
+the "llc_occupancy", "mbm_total_bytes", and "mbm_local_bytes" in the
+"mon_sub_L3_YY" directories to get node local data.
+
+Memory bandwidth allocation is still performed at the L3 cache
+level. I.e. throttling controls are applied to all SNC nodes.
+
+L3 cache allocation bitmaps also apply to all SNC nodes. But note that
+the amount of L3 cache represented by each bit is divided by the number
+of SNC nodes per L3 cache. E.g. with a 100MB cache on a system with 10-bit
+allocation masks each bit normally represents 10MB. With SNC mode enabled
+with two SNC nodes per L3 cache, each bit only represents 5MB.
+
 Memory bandwidth Allocation and monitoring
 ==========================================
 
@@ -508,7 +559,7 @@ threads start using more cores in an rdtgroup, the actual bandwidth may
 increase or vary although user specified bandwidth percentage is same.
 
 In order to mitigate this and make the interface more user friendly,
-resctrl added support for specifying the bandwidth in MBps as well.  The
+resctrl added support for specifying the bandwidth in MiBps as well.  The
 kernel underneath would use a software feedback mechanism or a "Software
 Controller(mba_sc)" which reads the actual bandwidth using MBM counters
 and adjust the memory bandwidth percentages to ensure::
@@ -555,13 +606,13 @@ Memory b/w domain is L3 cache.
 
 	MB:<cache_id0>=bandwidth0;<cache_id1>=bandwidth1;...
 
-Memory bandwidth Allocation specified in MBps
+Memory bandwidth Allocation specified in MiBps
 ---------------------------------------------
 
 Memory bandwidth domain is L3 cache.
 ::
 
-	MB:<cache_id0>=bw_MBps0;<cache_id1>=bw_MBps1;...
+	MB:<cache_id0>=bw_MiBps0;<cache_id1>=bw_MiBps1;...
 
 Slow Memory Bandwidth Allocation (SMBA)
 ---------------------------------------

arch/x86/include/asm/msr-index.h

@@ -1127,6 +1127,7 @@
 #define MSR_IA32_QM_CTR			0xc8e
 #define MSR_IA32_PQR_ASSOC		0xc8f
 #define MSR_IA32_L3_CBM_BASE		0xc90
+#define MSR_RMID_SNC_CONFIG		0xca0
 #define MSR_IA32_L2_CBM_BASE		0xd10
 #define MSR_IA32_MBA_THRTL_BASE		0xd50
 

arch/x86/include/asm/resctrl.h

@@ -7,6 +7,13 @@
 #include <linux/sched.h>
 #include <linux/jump_label.h>
 
+/*
+ * This value can never be a valid CLOSID, and is used when mapping a
+ * (closid, rmid) pair to an index and back. On x86 only the RMID is
+ * needed. The index is a software defined value.
+ */
+#define X86_RESCTRL_EMPTY_CLOSID         ((u32)~0)
+
 /**
  * struct resctrl_pqr_state - State cache for the PQR MSR
  * @cur_rmid:		The cached Resource Monitoring ID
@@ -31,10 +38,47 @@ struct resctrl_pqr_state {
 
 DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state);
 
+extern bool rdt_alloc_capable;
+extern bool rdt_mon_capable;
+
 DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
 DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key);
 
+static inline bool resctrl_arch_alloc_capable(void)
+{
+	return rdt_alloc_capable;
+}
+
+static inline void resctrl_arch_enable_alloc(void)
+{
+	static_branch_enable_cpuslocked(&rdt_alloc_enable_key);
+	static_branch_inc_cpuslocked(&rdt_enable_key);
+}
+
+static inline void resctrl_arch_disable_alloc(void)
+{
+	static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
+	static_branch_dec_cpuslocked(&rdt_enable_key);
+}
+
+static inline bool resctrl_arch_mon_capable(void)
+{
+	return rdt_mon_capable;
+}
+
+static inline void resctrl_arch_enable_mon(void)
+{
+	static_branch_enable_cpuslocked(&rdt_mon_enable_key);
+	static_branch_inc_cpuslocked(&rdt_enable_key);
+}
+
+static inline void resctrl_arch_disable_mon(void)
+{
+	static_branch_disable_cpuslocked(&rdt_mon_enable_key);
+	static_branch_dec_cpuslocked(&rdt_enable_key);
+}
+
 /*
  * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR
  *
@@ -88,12 +132,52 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val)
 	return val * scale;
 }
 
+static inline void resctrl_arch_set_closid_rmid(struct task_struct *tsk,
+						u32 closid, u32 rmid)
+{
+	WRITE_ONCE(tsk->closid, closid);
+	WRITE_ONCE(tsk->rmid, rmid);
+}
+
+static inline bool resctrl_arch_match_closid(struct task_struct *tsk, u32 closid)
+{
+	return READ_ONCE(tsk->closid) == closid;
+}
+
+static inline bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 ignored,
+					   u32 rmid)
+{
+	return READ_ONCE(tsk->rmid) == rmid;
+}
+
 static inline void resctrl_sched_in(struct task_struct *tsk)
 {
 	if (static_branch_likely(&rdt_enable_key))
 		__resctrl_sched_in(tsk);
 }
 
+static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid)
+{
+	*rmid = idx;
+	*closid = X86_RESCTRL_EMPTY_CLOSID;
+}
+
+static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid)
+{
+	return rmid;
+}
+
+/* x86 can always read an rmid, nothing needs allocating */
+struct rdt_resource;
+static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid)
+{
+	might_sleep();
+	return NULL;
+};
+
+static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid,
+					     void *ctx) { };
+
 void resctrl_cpu_detect(struct cpuinfo_x86 *c);
 
 #else