Re: [PATCH v5 12/24] x86/resctrl: Make resctrl_arch_rmid_read() retry when it is interrupted

[Reinette Chatre]

Hi James,

On 7/28/2023 9:42 AM, James Morse wrote:
> resctrl_arch_rmid_read() could be called by resctrl in process context,
> and then called by the PMU driver from irq context on the same CPU.

The changelog is written as a bug report of current behavior.
This does not seem to describe current but instead planned future behavior.


> This could cause struct arch_mbm_state's prev_msr value to go backwards,
> leading to the chunks value being incremented multiple times.
> 
> The struct arch_mbm_state holds both the previous msr value, and a count
> of the number of chunks. These two fields need to be updated atomically.
> Similarly __rmid_read() must write to one MSR and read from another,
> this must be proteted from re-entrance.

proteted -> protected

> 
> Read the prev_msr before accessing the hardware, and cmpxchg() the value
> back. If the value has changed, the whole thing is re-attempted. To protect
> the MSR, __rmid_read() will retry reads for QM_CTR if QM_EVTSEL has changed
> from the selected value.

The latter part of the sentence does not seem to match with what the
patch does.

> 
> Signed-off-by: James Morse <james.morse@xxxxxxx>
> 
> ---
> Changes since v4:
>  * Added retry loop in __rmid_read() to protect the CPU MSRs.
> ---
>  arch/x86/kernel/cpu/resctrl/internal.h |  5 +--
>  arch/x86/kernel/cpu/resctrl/monitor.c  | 45 ++++++++++++++++++++------
>  2 files changed, 38 insertions(+), 12 deletions(-)
> 
> diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
> index a32d307292a1..7012f42a82ee 100644
> --- a/arch/x86/kernel/cpu/resctrl/internal.h
> +++ b/arch/x86/kernel/cpu/resctrl/internal.h
> @@ -2,6 +2,7 @@
>  #ifndef _ASM_X86_RESCTRL_INTERNAL_H
>  #define _ASM_X86_RESCTRL_INTERNAL_H
>  
> +#include <linux/atomic.h>
>  #include <linux/resctrl.h>
>  #include <linux/sched.h>
>  #include <linux/kernfs.h>
> @@ -338,8 +339,8 @@ struct mbm_state {
>   *		find this struct.
>   */
>  struct arch_mbm_state {
> -	u64	chunks;
> -	u64	prev_msr;
> +	atomic64_t	chunks;
> +	atomic64_t	prev_msr;
>  };
>  
>  /**
> diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
> index f0670795b446..62350bbd23e0 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -16,6 +16,7 @@
>   */
>  
>  #include <linux/module.h>
> +#include <linux/percpu.h>
>  #include <linux/sizes.h>
>  #include <linux/slab.h>
>  
> @@ -24,6 +25,9 @@
>  
>  #include "internal.h"
>  
> +/* Sequence number for writes to IA32 QM_EVTSEL */
> +static DEFINE_PER_CPU(u64, qm_evtsel_seq);
> +
>  struct rmid_entry {
>  	/*
>  	 * Some architectures's resctrl_arch_rmid_read() needs the CLOSID value
> @@ -178,7 +182,7 @@ static inline struct rmid_entry *__rmid_entry(u32 idx)
>  
>  static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
>  {
> -	u64 msr_val;
> +	u64 msr_val, seq;
>  
>  	/*
>  	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
> @@ -187,9 +191,16 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
>  	 * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
>  	 * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
>  	 * are error bits.
> +	 * A per-cpu sequence counter is incremented each time QM_EVTSEL is
> +	 * written. This is used to detect if this function was interrupted by
> +	 * another call without re-reading the MSRs. Retry the MSR read when
> +	 * this happens as the QM_CTR value may belong to a different event.
>  	 */
> -	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
> -	rdmsrl(MSR_IA32_QM_CTR, msr_val);
> +	do {
> +		seq = this_cpu_inc_return(qm_evtsel_seq);
> +		wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
> +		rdmsrl(MSR_IA32_QM_CTR, msr_val);
> +	} while (seq != this_cpu_read(qm_evtsel_seq));
>  
>  	if (msr_val & RMID_VAL_ERROR)
>  		return -EIO;
> @@ -225,13 +236,15 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
>  {
>  	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
>  	struct arch_mbm_state *am;
> +	u64 msr_val;
>  
>  	am = get_arch_mbm_state(hw_dom, rmid, eventid);
>  	if (am) {
>  		memset(am, 0, sizeof(*am));
>  
>  		/* Record any initial, non-zero count value. */
> -		__rmid_read(rmid, eventid, &am->prev_msr);
> +		__rmid_read(rmid, eventid, &msr_val);
> +		atomic64_set(&am->prev_msr, msr_val);
>  	}
>  }
>  
> @@ -266,23 +279,35 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
>  {
>  	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
>  	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
> +	u64 start_msr_val, old_msr_val, msr_val, chunks;
>  	struct arch_mbm_state *am;
> -	u64 msr_val, chunks;
> -	int ret;
> +	int ret = 0;
>  
>  	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
>  		return -EINVAL;
>  
> +interrupted:
> +	am = get_arch_mbm_state(hw_dom, rmid, eventid);
> +	if (am)
> +		start_msr_val = atomic64_read(&am->prev_msr);
> +
>  	ret = __rmid_read(rmid, eventid, &msr_val);
>  	if (ret)
>  		return ret;
>  
>  	am = get_arch_mbm_state(hw_dom, rmid, eventid);
>  	if (am) {
> -		am->chunks += mbm_overflow_count(am->prev_msr, msr_val,
> -						 hw_res->mbm_width);
> -		chunks = get_corrected_mbm_count(rmid, am->chunks);
> -		am->prev_msr = msr_val;
> +		old_msr_val = atomic64_cmpxchg(&am->prev_msr, start_msr_val,
> +					       msr_val);
> +		if (old_msr_val != start_msr_val)
> +			goto interrupted;
> +

hmmm ... what if interruption occurs here? 

> +		chunks = mbm_overflow_count(start_msr_val, msr_val,
> +					    hw_res->mbm_width);
> +		atomic64_add(chunks, &am->chunks);
> +
> +		chunks = get_corrected_mbm_count(rmid,
> +						 atomic64_read(&am->chunks));
>  	} else {
>  		chunks = msr_val;
>  	}

Reinette