linux-stable.git/arch/x86/kernel/cpu/resctrl/monitor.c, branch linux-6.6.y

x86/resctrl: Fix miscount of bandwidth event when reactivating previously unavailable RMID

2025-10-29T13:07:06+00:00

commit 15292f1b4c55a3a7c940dbcb6cb8793871ed3d92 upstream.

Users can create as many monitoring groups as the number of RMIDs supported
by the hardware. However, on AMD systems, only a limited number of RMIDs
are guaranteed to be actively tracked by the hardware. RMIDs that exceed
this limit are placed in an "Unavailable" state.

When a bandwidth counter is read for such an RMID, the hardware sets
MSR_IA32_QM_CTR.Unavailable (bit 62). When such an RMID starts being tracked
again the hardware counter is reset to zero. MSR_IA32_QM_CTR.Unavailable
remains set on first read after tracking re-starts and is clear on all
subsequent reads as long as the RMID is tracked.

resctrl miscounts the bandwidth events after an RMID transitions from the
"Unavailable" state back to being tracked. This happens because when the
hardware starts counting again after resetting the counter to zero, resctrl
in turn compares the new count against the counter value stored from the
previous time the RMID was tracked.

This results in resctrl computing an event value that is either undercounting
(when new counter is more than stored counter) or a mistaken overflow (when
new counter is less than stored counter).

Reset the stored value (arch_mbm_state::prev_msr) of MSR_IA32_QM_CTR to
zero whenever the RMID is in the "Unavailable" state to ensure accurate
counting after the RMID resets to zero when it starts to be tracked again.

Example scenario that results in mistaken overflow
==================================================
1. The resctrl filesystem is mounted, and a task is assigned to a
   monitoring group.

   $mount -t resctrl resctrl /sys/fs/resctrl
   $mkdir /sys/fs/resctrl/mon_groups/test1/
   $echo 1234 > /sys/fs/resctrl/mon_groups/test1/tasks

   $cat /sys/fs/resctrl/mon_groups/test1/mon_data/mon_L3_*/mbm_total_bytes
   21323            <- Total bytes on domain 0
   "Unavailable"    <- Total bytes on domain 1

   Task is running on domain 0. Counter on domain 1 is "Unavailable".

2. The task runs on domain 0 for a while and then moves to domain 1. The
   counter starts incrementing on domain 1.

   $cat /sys/fs/resctrl/mon_groups/test1/mon_data/mon_L3_*/mbm_total_bytes
   7345357          <- Total bytes on domain 0
   4545             <- Total bytes on domain 1

3. At some point, the RMID in domain 0 transitions to the "Unavailable"
   state because the task is no longer executing in that domain.

   $cat /sys/fs/resctrl/mon_groups/test1/mon_data/mon_L3_*/mbm_total_bytes
   "Unavailable"    <- Total bytes on domain 0
   434341           <- Total bytes on domain 1

4.  Since the task continues to migrate between domains, it may eventually
    return to domain 0.

    $cat /sys/fs/resctrl/mon_groups/test1/mon_data/mon_L3_*/mbm_total_bytes
    17592178699059  <- Overflow on domain 0
    3232332         <- Total bytes on domain 1

In this case, the RMID on domain 0 transitions from "Unavailable" state to
active state. The hardware sets MSR_IA32_QM_CTR.Unavailable (bit 62) when
the counter is read and begins tracking the RMID counting from 0.

Subsequent reads succeed but return a value smaller than the previously
saved MSR value (7345357). Consequently, the resctrl's overflow logic is
triggered, it compares the previous value (7345357) with the new, smaller
value and incorrectly interprets this as a counter overflow, adding a large
delta.

In reality, this is a false positive: the counter did not overflow but was
simply reset when the RMID transitioned from "Unavailable" back to active
state.

Here is the text from APM [1] available from [2].

"In PQOS Version 2.0 or higher, the MBM hardware will set the U bit on the
first QM_CTR read when it begins tracking an RMID that it was not
previously tracking. The U bit will be zero for all subsequent reads from
that RMID while it is still tracked by the hardware. Therefore, a QM_CTR
read with the U bit set when that RMID is in use by a processor can be
considered 0 when calculating the difference with a subsequent read."

[1] AMD64 Architecture Programmer's Manual Volume 2: System Programming
    Publication # 24593 Revision 3.41 section 19.3.3 Monitoring L3 Memory
    Bandwidth (MBM).

  [ bp: Split commit message into smaller paragraph chunks for better
    consumption. ]

Fixes: 4d05bf71f157d ("x86/resctrl: Introduce AMD QOS feature")
Signed-off-by: Babu Moger 
Signed-off-by: Borislav Petkov (AMD) 
Reviewed-by: Reinette Chatre 
Tested-by: Reinette Chatre 
Cc: stable@vger.kernel.org # needs adjustments for <= v6.17
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 # [2]
[babu.moger@amd.com: Fix conflict for v6.6 stable]
Signed-off-by: Greg Kroah-Hartman

x86/resctrl: Implement new mba_MBps throttling heuristic

2024-03-26T22:19:19+00:00

[ Upstream commit c2427e70c1630d98966375fffc2b713ab9768a94 ]

The mba_MBps feedback loop increases throttling when a group is using
more bandwidth than the target set by the user in the schemata file, and
decreases throttling when below target.

To avoid possibly stepping throttling up and down on every poll a flag
"delta_comp" is set whenever throttling is changed to indicate that the
actual change in bandwidth should be recorded on the next poll in
"delta_bw". Throttling is only reduced if the current bandwidth plus
delta_bw is below the user target.

This algorithm works well if the workload has steady bandwidth needs.
But it can go badly wrong if the workload moves to a different phase
just as the throttling level changed. E.g. if the workload becomes
essentially idle right as throttling level is increased, the value
calculated for delta_bw will be more or less the old bandwidth level.
If the workload then resumes, Linux may never reduce throttling because
current bandwidth plus delta_bw is above the target set by the user.

Implement a simpler heuristic by assuming that in the worst case the
currently measured bandwidth is being controlled by the current level of
throttling. Compute how much it may increase if throttling is relaxed to
the next higher level. If that is still below the user target, then it
is ok to reduce the amount of throttling.

Fixes: ba0f26d8529c ("x86/intel_rdt/mba_sc: Prepare for feedback loop")
Reported-by: Xiaochen Shen 
Signed-off-by: Tony Luck 
Signed-off-by: Borislav Petkov (AMD) 
Reviewed-by: Reinette Chatre 
Tested-by: Xiaochen Shen 
Link: https://lore.kernel.org/r/20240122180807.70518-1-tony.luck@intel.com
Signed-off-by: Sasha Levin

x86/resctrl: Read supported bandwidth sources from CPUID

2024-03-26T22:19:19+00:00

[ Upstream commit 54e35eb8611cce5550d3d7689679b1a91c864f28 ]

If the BMEC (Bandwidth Monitoring Event Configuration) feature is
supported, the bandwidth events can be configured. The maximum supported
bandwidth bitmask can be read from CPUID:

  CPUID_Fn80000020_ECX_x03 [Platform QoS Monitoring Bandwidth Event Configuration]
  Bits    Description
  31:7    Reserved
   6:0    Identifies the bandwidth sources that can be tracked.

While at it, move the mask checking to mon_config_write() before
iterating over all the domains. Also, print the valid bitmask when the
user tries to configure invalid event configuration value.

The CPUID details are documented in the Processor Programming Reference
(PPR) Vol 1.1 for AMD Family 19h Model 11h B1 - 55901 Rev 0.25 in the
Link tag.

Fixes: dc2a3e857981 ("x86/resctrl: Add interface to read mbm_total_bytes_config")
Signed-off-by: Babu Moger 
Signed-off-by: Borislav Petkov (AMD) 
Reviewed-by: Reinette Chatre 
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537
Link: https://lore.kernel.org/r/669896fa512c7451319fa5ca2fdb6f7e015b5635.1705359148.git.babu.moger@amd.com
Signed-off-by: Sasha Levin

x86/resctrl: Fix kernel-doc warnings

2023-10-08T09:45:16+00:00

The kernel test robot reported kernel-doc warnings here:

  monitor.c:34: warning: Cannot understand  * @rmid_free_lru    A least recently used list of free RMIDs on line 34 - I thought it was a doc line
  monitor.c:41: warning: Cannot understand  * @rmid_limbo_count     count of currently unused but (potentially) on line 41 - I thought it was a doc line
  monitor.c:50: warning: Cannot understand  * @rmid_entry - The entry in the limbo and free lists.  on line 50 - I thought it was a doc line

We don't have a syntax for documenting individual data items via
kernel-doc, so remove the "/**" kernel-doc markers and add a hyphen
for consistency.

Fixes: 6a445edce657 ("x86/intel_rdt/cqm: Add RDT monitoring initialization")
Fixes: 24247aeeabe9 ("x86/intel_rdt/cqm: Improve limbo list processing")
Reported-by: kernel test robot 
Signed-off-by: Randy Dunlap 
Signed-off-by: Ingo Molnar 
Link: https://lore.kernel.org/r/20231006235132.16227-1-rdunlap@infradead.org

Merge tag 'x86_cache_for_6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2023-04-28T16:30:51+00:00

Pull x86 resctrl update from Dave Hansen:
 "Reduce redundant counter reads with resctrl refactoring"

* tag 'x86_cache_for_6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/resctrl: Avoid redundant counter read in __mon_event_count()

docs: move x86 documentation into Documentation/arch/

2023-03-30T18:58:51+00:00

Move the x86 documentation under Documentation/arch/ as a way of cleaning
up the top-level directory and making the structure of our docs more
closely match the structure of the source directories it describes.

All in-kernel references to the old paths have been updated.

Acked-by: Dave Hansen 
Cc: linux-arch@vger.kernel.org
Cc: x86@kernel.org
Cc: Borislav Petkov 
Cc: Thomas Gleixner 
Link: https://lore.kernel.org/lkml/20230315211523.108836-1-corbet@lwn.net/
Signed-off-by: Jonathan Corbet

x86/resctrl: Avoid redundant counter read in __mon_event_count()

2023-03-15T22:44:15+00:00

__mon_event_count() does the per-RMID, per-domain work for
user-initiated event count reads and the initialization of new monitor
groups.

In the initialization case, after resctrl_arch_reset_rmid() calls
__rmid_read() to record an initial count for a new monitor group, it
immediately calls resctrl_arch_rmid_read(). This re-read of the hardware
counter is unnecessary and the following computations are ignored by the
caller during initialization.

Following return from resctrl_arch_reset_rmid(), just clear the
mbm_state and return. This involves moving the mbm_state lookup into the
rr->first case, as it's not needed for regular event count reads: the
QOS_L3_OCCUP_EVENT_ID case was redundant with the accumulating logic at
the end of the function.

Signed-off-by: Peter Newman 
Signed-off-by: Dave Hansen 
Reviewed-by: Reinette Chatre 
Tested-by: Babu Moger 
Link: https://lore.kernel.org/all/20221220164132.443083-2-peternewman%40google.com

x86/resctrl: Add interface to write mbm_total_bytes_config

2023-01-23T16:40:30+00:00

The event configuration for mbm_total_bytes can be changed by the user by
writing to the file /sys/fs/resctrl/info/L3_MON/mbm_total_bytes_config.

The event configuration settings are domain specific and affect all the
CPUs in the domain.

Following are the types of events supported:

  ====  ===========================================================
  Bits   Description
  ====  ===========================================================
  6      Dirty Victims from the QOS domain to all types of memory
  5      Reads to slow memory in the non-local NUMA domain
  4      Reads to slow memory in the local NUMA domain
  3      Non-temporal writes to non-local NUMA domain
  2      Non-temporal writes to local NUMA domain
  1      Reads to memory in the non-local NUMA domain
  0      Reads to memory in the local NUMA domain
  ====  ===========================================================

For example:

To change the mbm_total_bytes to count only reads on domain 0, the bits
0, 1, 4 and 5 needs to be set, which is 110011b (in hex 0x33).
Run the command:

  $echo  0=0x33 > /sys/fs/resctrl/info/L3_MON/mbm_total_bytes_config

To change the mbm_total_bytes to count all the slow memory reads on domain 1,
the bits 4 and 5 needs to be set which is 110000b (in hex 0x30).
Run the command:

  $echo  1=0x30 > /sys/fs/resctrl/info/L3_MON/mbm_total_bytes_config

Signed-off-by: Babu Moger 
Signed-off-by: Borislav Petkov (AMD) 
Reviewed-by: Reinette Chatre 
Link: https://lore.kernel.org/r/20230113152039.770054-12-babu.moger@amd.com

x86/resctrl: Add interface to read mbm_local_bytes_config

2023-01-23T16:40:27+00:00

The event configuration can be viewed by the user by reading the configuration
file /sys/fs/resctrl/info/L3_MON/mbm_local_bytes_config.  The event
configuration settings are domain specific and will affect all the CPUs in the
domain.

Following are the types of events supported:

  ====  ===========================================================
  Bits   Description
  ====  ===========================================================
  6      Dirty Victims from the QOS domain to all types of memory
  5      Reads to slow memory in the non-local NUMA domain
  4      Reads to slow memory in the local NUMA domain
  3      Non-temporal writes to non-local NUMA domain
  2      Non-temporal writes to local NUMA domain
  1      Reads to memory in the non-local NUMA domain
  0      Reads to memory in the local NUMA domain
  ====  ===========================================================

By default, the mbm_local_bytes_config is set to 0x15 to count all the local
event types.

For example:

  $cat /sys/fs/resctrl/info/L3_MON/mbm_local_bytes_config
  0=0x15;1=0x15;2=0x15;3=0x15

In this case, the event mbm_local_bytes is configured with 0x15 on
domains 0 to 3.

Signed-off-by: Babu Moger 
Signed-off-by: Borislav Petkov (AMD) 
Reviewed-by: Reinette Chatre 
Link: https://lore.kernel.org/r/20230113152039.770054-11-babu.moger@amd.com

x86/resctrl: Add interface to read mbm_total_bytes_config

2023-01-23T16:40:24+00:00

The event configuration can be viewed by the user by reading the
configuration file /sys/fs/resctrl/info/L3_MON/mbm_total_bytes_config.  The
event configuration settings are domain specific and will affect all the CPUs in
the domain.

Following are the types of events supported:

  ====  ===========================================================
  Bits   Description
  ====  ===========================================================
  6      Dirty Victims from the QOS domain to all types of memory
  5      Reads to slow memory in the non-local NUMA domain
  4      Reads to slow memory in the local NUMA domain
  3      Non-temporal writes to non-local NUMA domain
  2      Non-temporal writes to local NUMA domain
  1      Reads to memory in the non-local NUMA domain
  0      Reads to memory in the local NUMA domain
  ====  ===========================================================

By default, the mbm_total_bytes_config is set to 0x7f to count all the
event types.

For example:

  $cat /sys/fs/resctrl/info/L3_MON/mbm_total_bytes_config
  0=0x7f;1=0x7f;2=0x7f;3=0x7f

In this case, the event mbm_total_bytes is configured with 0x7f on
domains 0 to 3.

Signed-off-by: Babu Moger 
Signed-off-by: Borislav Petkov (AMD) 
Reviewed-by: Reinette Chatre 
Link: https://lore.kernel.org/r/20230113152039.770054-10-babu.moger@amd.com