From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, Xiaochen Shen <xiaochen.shen@intel.com>,
Borislav Petkov <bp@suse.de>, Tony Luck <tony.luck@intel.com>,
Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Subject: [PATCH 5.9 49/49] x86/resctrl: Fix incorrect local bandwidth when mba_sc is enabled
Date: Sat, 19 Dec 2020 13:58:53 +0100 [thread overview]
Message-ID: <20201219125347.062528303@linuxfoundation.org> (raw)
In-Reply-To: <20201219125344.671832095@linuxfoundation.org>
From: Xiaochen Shen <xiaochen.shen@intel.com>
commit 06c5fe9b12dde1b62821f302f177c972bb1c81f9 upstream
The MBA software controller (mba_sc) is a feedback loop which
periodically reads MBM counters and tries to restrict the bandwidth
below a user-specified value. It tags along the MBM counter overflow
handler to do the updates with 1s interval in mbm_update() and
update_mba_bw().
The purpose of mbm_update() is to periodically read the MBM counters to
make sure that the hardware counter doesn't wrap around more than once
between user samplings. mbm_update() calls __mon_event_count() for local
bandwidth updating when mba_sc is not enabled, but calls mbm_bw_count()
instead when mba_sc is enabled. __mon_event_count() will not be called
for local bandwidth updating in MBM counter overflow handler, but it is
still called when reading MBM local bandwidth counter file
'mbm_local_bytes', the call path is as below:
rdtgroup_mondata_show()
mon_event_read()
mon_event_count()
__mon_event_count()
In __mon_event_count(), m->chunks is updated by delta chunks which is
calculated from previous MSR value (m->prev_msr) and current MSR value.
When mba_sc is enabled, m->chunks is also updated in mbm_update() by
mistake by the delta chunks which is calculated from m->prev_bw_msr
instead of m->prev_msr. But m->chunks is not used in update_mba_bw() in
the mba_sc feedback loop.
When reading MBM local bandwidth counter file, m->chunks was changed
unexpectedly by mbm_bw_count(). As a result, the incorrect local
bandwidth counter which calculated from incorrect m->chunks is shown to
the user.
Fix this by removing incorrect m->chunks updating in mbm_bw_count() in
MBM counter overflow handler, and always calling __mon_event_count() in
mbm_update() to make sure that the hardware local bandwidth counter
doesn't wrap around.
Test steps:
# Run workload with aggressive memory bandwidth (e.g., 10 GB/s)
git clone https://github.com/intel/intel-cmt-cat && cd intel-cmt-cat
&& make
./tools/membw/membw -c 0 -b 10000 --read
# Enable MBA software controller
mount -t resctrl resctrl -o mba_MBps /sys/fs/resctrl
# Create control group c1
mkdir /sys/fs/resctrl/c1
# Set MB throttle to 6 GB/s
echo "MB:0=6000;1=6000" > /sys/fs/resctrl/c1/schemata
# Write PID of the workload to tasks file
echo `pidof membw` > /sys/fs/resctrl/c1/tasks
# Read local bytes counters twice with 1s interval, the calculated
# local bandwidth is not as expected (approaching to 6 GB/s):
local_1=`cat /sys/fs/resctrl/c1/mon_data/mon_L3_00/mbm_local_bytes`
sleep 1
local_2=`cat /sys/fs/resctrl/c1/mon_data/mon_L3_00/mbm_local_bytes`
echo "local b/w (bytes/s):" `expr $local_2 - $local_1`
Before fix:
local b/w (bytes/s): 11076796416
After fix:
local b/w (bytes/s): 5465014272
Fixes: ba0f26d8529c (x86/intel_rdt/mba_sc: Prepare for feedback loop)
Signed-off-by: Xiaochen Shen <xiaochen.shen@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/1607063279-19437-1-git-send-email-xiaochen.shen@intel.com
Signed-off-by: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/x86/kernel/cpu/resctrl/monitor.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -279,7 +279,6 @@ static void mbm_bw_count(u32 rmid, struc
return;
chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width);
- m->chunks += chunks;
cur_bw = (chunks * r->mon_scale) >> 20;
if (m->delta_comp)
@@ -450,15 +449,14 @@ static void mbm_update(struct rdt_resour
}
if (is_mbm_local_enabled()) {
rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
+ __mon_event_count(rmid, &rr);
/*
* Call the MBA software controller only for the
* control groups and when user has enabled
* the software controller explicitly.
*/
- if (!is_mba_sc(NULL))
- __mon_event_count(rmid, &rr);
- else
+ if (is_mba_sc(NULL))
mbm_bw_count(rmid, &rr);
}
}
next prev parent reply other threads:[~2020-12-19 13:00 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-19 12:58 [PATCH 5.9 00/49] 5.9.16-rc1 review Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 01/49] ptrace: Prevent kernel-infoleak in ptrace_get_syscall_info() Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 02/49] net/sched: fq_pie: initialize timer earlier in fq_pie_init() Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 03/49] net: ipa: pass the correct size when freeing DMA memory Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 04/49] ipv4: fix error return code in rtm_to_fib_config() Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 05/49] mac80211: mesh: fix mesh_pathtbl_init() error path Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 06/49] net: bridge: vlan: fix error return code in __vlan_add() Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 07/49] vrf: packets with lladdr src needs dst at input with orig_iif when needs strict Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 08/49] net: mscc: ocelot: fix dropping of unknown IPv4 multicast on Seville Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 09/49] net: hns3: remove a misused pragma packed Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 10/49] udp: fix the proto value passed to ip_protocol_deliver_rcu for the segments Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 11/49] enetc: Fix reporting of h/w packet counters Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 12/49] bridge: Fix a deadlock when enabling multicast snooping Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 13/49] mptcp: print new line in mptcp_seq_show() if mptcp isnt in use Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 14/49] net: stmmac: dwmac-meson8b: fix mask definition of the m250_sel mux Greg Kroah-Hartman
2020-12-19 21:51 ` Pavel Machek
2020-12-19 22:38 ` Martin Blumenstingl
2020-12-19 23:13 ` Pavel Machek
2020-12-21 14:31 ` Martin Blumenstingl
2020-12-19 12:58 ` [PATCH 5.9 15/49] net: stmmac: start phylink instance before stmmac_hw_setup() Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 16/49] net: stmmac: free tx skb buffer in stmmac_resume() Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 17/49] net: stmmac: delete the eee_ctrl_timer after napi disabled Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 18/49] net: stmmac: overwrite the dma_cap.addr64 according to HW design Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 19/49] net: ll_temac: Fix potential NULL dereference in temac_probe() Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 20/49] tcp: select sane initial rcvq_space.space for big MSS Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 21/49] e1000e: fix S0ix flow to allow S0i3.2 subset entry Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 22/49] ethtool: fix stack overflow in ethnl_parse_bitset() Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 23/49] tcp: fix cwnd-limited bug for TSO deferral where we send nothing Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 24/49] net: flow_offload: Fix memory leak for indirect flow block Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 25/49] net/mlx4_en: Avoid scheduling restart task if it is already running Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 26/49] net/mlx4_en: Handle TX error CQE Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 27/49] net: sched: Fix dump of MPLS_OPT_LSE_LABEL attribute in cls_flower Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 28/49] bonding: fix feature flag setting at init time Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 29/49] ch_ktls: fix build warning for ipv4-only config Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 30/49] lan743x: fix for potential NULL pointer dereference with bare card Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 31/49] net: stmmac: increase the timeout for dma reset Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 32/49] net: tipc: prevent possible null deref of link Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 33/49] ktest.pl: If size of log is too big to email, email error message Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 34/49] ktest.pl: Fix the logic for truncating the size of the log file for email Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 35/49] USB: dummy-hcd: Fix uninitialized array use in init() Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 36/49] USB: add RESET_RESUME quirk for Snapscan 1212 Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 37/49] ALSA: usb-audio: Fix potential out-of-bounds shift Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 38/49] ALSA: usb-audio: Fix control access overflow errors from chmap Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 39/49] xhci: Give USB2 ports time to enter U3 in bus suspend Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 40/49] xhci-pci: Allow host runtime PM as default for Intel Alpine Ridge LP Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 41/49] xhci-pci: Allow host runtime PM as default for Intel Maple Ridge xHCI Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 42/49] USB: UAS: introduce a quirk to set no_write_same Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 43/49] USB: sisusbvga: Make console support depend on BROKEN Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 44/49] ALSA: pcm: oss: Fix potential out-of-bounds shift Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 45/49] serial: 8250_omap: Avoid FIFO corruption caused by MDR1 access Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 46/49] KVM: mmu: Fix SPTE encoding of MMIO generation upper half Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 47/49] membarrier: Explicitly sync remote cores when SYNC_CORE is requested Greg Kroah-Hartman
2020-12-19 12:58 ` [PATCH 5.9 48/49] x86/resctrl: Remove unused struct mbm_state::chunks_bw Greg Kroah-Hartman
2020-12-19 12:58 ` Greg Kroah-Hartman [this message]
2020-12-19 21:49 ` [PATCH 5.9 00/49] 5.9.16-rc1 review Guenter Roeck
2020-12-20 3:51 ` Naresh Kamboju
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201219125347.062528303@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=bp@suse.de \
--cc=linux-kernel@vger.kernel.org \
--cc=stable@vger.kernel.org \
--cc=sudipm.mukherjee@gmail.com \
--cc=tony.luck@intel.com \
--cc=xiaochen.shen@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome