RE: [RFC PATCH v8 10/10] ras: scrub: ACPI RAS2: Add memory ACPI RAS2 driver

[Shiju Jose]

Hi Daniel,

Thanks for the feedback.

>-----Original Message-----
>From: Daniel Ferguson <danielf@xxxxxxxxxxxxxxxxxxxxxx>
>Sent: 05 June 2024 22:33
>To: Shiju Jose <shiju.jose@xxxxxxxxxx>
>Cc: linux-edac@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx;
>david@xxxxxxxxxx; Vilas.Sridharan@xxxxxxx; leo.duran@xxxxxxx;
>Yazen.Ghannam@xxxxxxx; rientjes@xxxxxxxxxx; jiaqiyan@xxxxxxxxxx;
>tony.luck@xxxxxxxxx; Jon.Grimm@xxxxxxx; dave.hansen@xxxxxxxxxxxxxxx;
>rafael@xxxxxxxxxx; lenb@xxxxxxxxxx; naoya.horiguchi@xxxxxxx;
>james.morse@xxxxxxx; jthoughton@xxxxxxxxxx; somasundaram.a@xxxxxxx;
>erdemaktas@xxxxxxxxxx; pgonda@xxxxxxxxxx; duenwen@xxxxxxxxxx;
>mike.malvestuto@xxxxxxxxx; gthelen@xxxxxxxxxx;
>wschwartz@xxxxxxxxxxxxxxxxxxx; dferguson@xxxxxxxxxxxxxxxxxxx;
>wbs@xxxxxxxxxxxxxxxxxxxxxx; nifan.cxl@xxxxxxxxx; tanxiaofei
><tanxiaofei@xxxxxxxxxx>; Zengtao (B) <prime.zeng@xxxxxxxxxxxxx>;
>kangkang.shen@xxxxxxxxxxxxx; wanghuiqiang <wanghuiqiang@xxxxxxxxxx>;
>Linuxarm <linuxarm@xxxxxxxxxx>; ira.weiny@xxxxxxxxx;
>vishal.l.verma@xxxxxxxxx; alison.schofield@xxxxxxxxx; dave.jiang@xxxxxxxxx;
>Jonathan Cameron <jonathan.cameron@xxxxxxxxxx>; dave@xxxxxxxxxxxx;
>dan.j.williams@xxxxxxxxx; linux-mm@xxxxxxxxx; linux-acpi@xxxxxxxxxxxxxxx;
>linux-cxl@xxxxxxxxxxxxxxx
>Subject: Re: [RFC PATCH v8 10/10] ras: scrub: ACPI RAS2: Add memory ACPI
>RAS2 driver
>
>> +/* Context - lock must be held */
>> +static int ras2_get_patrol_scrub_running(struct ras2_scrub_ctx *ras2_ctx,
>> +					 bool *running)
>> +{
>> +	struct acpi_ras2_ps_shared_mem __iomem *ps_sm = (void *)
>> +					ras2_ctx->pcc_subspace-
>>pcc_comm_addr;
>> +	int ret;
>> +
>> +	if (ras2_ctx->bg)
>> +		*running = true;
>> +
>> +	ps_sm->common.set_capabilities[0] =
>RAS2_SUPPORT_HW_PARTOL_SCRUB;
>> +	ps_sm->params.patrol_scrub_command =
>RAS2_GET_PATROL_PARAMETERS;
>
>Need to reset the address range (base and size). A user may have previously
>called "Enable Background" where the code zeros out these parameters.
>	ps_sm->params.requested_address_range[0] = ras2_ctx->base;
>	ps_sm->params.requested_address_range[1] = ras2_ctx->size;
The address range is being set to the above in the ras2_hw_scrub_set_enabled_od(), because they are
valid for on-demand scrubbing only. 

However the ras2_ctx->base and ras2_ctx->size are set to the  
ras2_ctx->base = ps_sm->params.actual_address_range[0];
ras2_ctx->size = ps_sm->params.actual_address_range[1];
in the ras2_update_patrol_scrub_params_cache(), which is called after enabling bg scrub and on-demand scrub. 
Thus ras2_ctx->base and ras2_ctx->size may have a 0 or garbage value for bg scrub because address range is not valid for bg scrubbing as perc ACPI specification. I will add checks to retain the cached address range if bg scrub is enabled. 
>
>
>> +
>> +	ret = ras2_send_pcc_cmd(ras2_ctx, RAS2_PCC_CMD_EXEC);
>> +	if (ret) {
>> +		dev_err(ras2_ctx->dev, "failed to read parameters\n");
>> +		return ret;
>> +	}
>> +
>> +	*running = ps_sm->params.flags &
>> +RAS2_PATROL_SCRUB_FLAG_SCRUBBER_RUNNING;
>> +
>> +	return 0;
>> +}
>> +
>> +static int ras2_hw_scrub_write_rate(struct device *dev, u64 rate) {
>> +	struct ras2_scrub_ctx *ras2_ctx = dev_get_drvdata(dev);
>> +	bool running;
>> +	int ret;
>> +
>> +	guard(mutex)(&ras2_ctx->lock);
>> +	ret = ras2_get_patrol_scrub_running(ras2_ctx, &running);
>> +	if (ret)
>> +		return ret;
>> +
>> +	if (running)
>> +		return -EBUSY;
>
>
>I suggest we do not check if the patrol scrub is running when we are merely
>updating cached values. More importantly, if we had previously wrote an invalid
>value (that is only invalidated by firmware after executing a command), then
>when we try to write a correct value, this "ras2_get_patrol_scrub_running"
>check will always fail, therefore preventing us from correcting our error.

In our opinion, write the rate and range etc, though updating the cached values, should be allowed only when the scrub is NOT running to avoid confusion thinking they are actually set in the running scrubber, when read them back in the userspace.
>
>> +
>> +	if (rate < ras2_ctx->rate_min || rate > ras2_ctx->rate_max)
>> +		return -EINVAL;
>> +
>> +	ras2_ctx->rate = rate;
>> +
>> +	return 0;
>> +}
>> +
>> +static int ras2_hw_scrub_read_rate(struct device *dev, u64 *rate) {
>> +	struct ras2_scrub_ctx *ras2_ctx = dev_get_drvdata(dev);
>> +
>> +	*rate = ras2_ctx->rate;
>> +
>> +	return 0;
>> +}
>> +
>> +static int ras2_hw_scrub_read_rate_avail(struct device *dev, u64
>> +*min, u64 *max) {
>> +	struct ras2_scrub_ctx *ras2_ctx = dev_get_drvdata(dev);
>> +
>> +	*min = ras2_ctx->rate_min;
>> +	*max = ras2_ctx->rate_max;
>> +
>> +	return 0;
>> +}
>> +
>> +static int ras2_hw_scrub_read_range(struct device *dev, u64 *base,
>> +u64 *size) {
>> +	struct ras2_scrub_ctx *ras2_ctx = dev_get_drvdata(dev);
>> +
>> +	*base = ras2_ctx->base;
>> +	*size = ras2_ctx->size;
>> +
>> +	return 0;
>> +}
>> +
>> +static int ras2_hw_scrub_write_range(struct device *dev, u64 base,
>> +u64 size) {
>> +	struct ras2_scrub_ctx *ras2_ctx = dev_get_drvdata(dev);
>> +	bool running;
>> +	int ret;
>> +
>> +	guard(mutex)(&ras2_ctx->lock);
>> +	ret = ras2_get_patrol_scrub_running(ras2_ctx, &running);
>> +	if (ret)
>> +		return ret;
>> +
>> +	if (running)
>> +		return -EBUSY;
>
>I suggest we do not check if the patrol scrub is running. See previous comment
>above.
Same as above.

>
>> +
>> +	ras2_ctx->base = base;
>> +	ras2_ctx->size = size;
>> +
>> +	return 0;
>> +}
>> +
>> +static int ras2_hw_scrub_set_enabled_bg(struct device *dev, bool
>> +enable) {
>> +	struct ras2_scrub_ctx *ras2_ctx = dev_get_drvdata(dev);
>> +	struct acpi_ras2_ps_shared_mem __iomem *ps_sm = (void *)
>> +					ras2_ctx->pcc_subspace-
>>pcc_comm_addr;
>> +	int ret;
>> +
>> +	guard(mutex)(&ras2_ctx->lock);
>> +	ps_sm->common.set_capabilities[0] =
>RAS2_SUPPORT_HW_PARTOL_SCRUB;
>> +	if (enable) {
>> +		ps_sm->params.requested_address_range[0] = 0;
>> +		ps_sm->params.requested_address_range[1] = 0;
>> +		ps_sm->params.scrub_params_in &=
>~RAS2_PATROL_SCRUB_RATE_IN_MASK;
>> +		ps_sm->params.scrub_params_in |=
>FIELD_PREP(RAS2_PATROL_SCRUB_RATE_IN_MASK,
>> +							    ras2_ctx->rate);
>> +		ps_sm->params.patrol_scrub_command =
>RAS2_START_PATROL_SCRUBBER;
>> +	} else {
>> +		ps_sm->params.patrol_scrub_command =
>RAS2_STOP_PATROL_SCRUBBER;
>> +	}
>> +	ps_sm->params.scrub_params_in &=
>~RAS2_PATROL_SCRUB_EN_BACKGROUND;
>> +	ps_sm->params.scrub_params_in |=
>FIELD_PREP(RAS2_PATROL_SCRUB_EN_BACKGROUND,
>> +						    enable);
>> +
>> +	ret = ras2_send_pcc_cmd(ras2_ctx, RAS2_PCC_CMD_EXEC);
>> +	if (ret) {
>> +		dev_err(ras2_ctx->dev, "%s: failed to enable(%d) background
>scrubbing\n",
>> +			__func__, enable);
>> +		return ret;
>> +	}
>> +	ras2_ctx->bg = true;
>> +
>> +	/* Update the cache to account for rounding of supplied parameters and
>similar */
>> +	return ras2_update_patrol_scrub_params_cache(ras2_ctx);
>> +}
>> +
>> +static int ras2_hw_scrub_get_enabled_bg(struct device *dev, bool
>> +*enabled) {
>> +	struct ras2_scrub_ctx *ras2_ctx = dev_get_drvdata(dev);
>> +
>> +	*enabled = ras2_ctx->bg;
>> +
>> +	return 0;
>> +}
>> +
>> +static int ras2_hw_scrub_set_enabled_od(struct device *dev, bool
>> +enable) {
>> +	struct ras2_scrub_ctx *ras2_ctx = dev_get_drvdata(dev);
>> +	struct acpi_ras2_ps_shared_mem __iomem *ps_sm = (void *)
>> +					ras2_ctx->pcc_subspace-
>>pcc_comm_addr;
>> +	bool enabled;
>> +	int ret;
>> +
>> +	guard(mutex)(&ras2_ctx->lock);
>> +	ps_sm->common.set_capabilities[0] =
>RAS2_SUPPORT_HW_PARTOL_SCRUB;
>> +	if (enable) {
>> +		if (!ras2_ctx->size) {
>> +			dev_warn(ras2_ctx->dev,
>> +				 "%s: Invalid requested address range,
>requested_address_range[0]=0x%llx "
>> +				 "requested_address_range[1]=0x%llx\n",
>__func__,
>> +				 ps_sm->params.requested_address_range[0],
>> +				 ps_sm->params.requested_address_range[1]);
>> +			return -ERANGE;
>> +		}
>> +		ret = ras2_get_patrol_scrub_running(ras2_ctx, &enabled);
>> +		if (ret)
>> +			return ret;
>> +
>> +		if (enabled)
>> +			return 0;
>> +
>> +		ps_sm->params.scrub_params_in &=
>~RAS2_PATROL_SCRUB_RATE_IN_MASK;
>> +		ps_sm->params.scrub_params_in |=
>FIELD_PREP(RAS2_PATROL_SCRUB_RATE_IN_MASK,
>> +							    ras2_ctx->rate);
>> +		ps_sm->params.requested_address_range[0] = ras2_ctx->base;
>> +		ps_sm->params.requested_address_range[1] = ras2_ctx->size;
>
>
>We need to clear the RAS2_PATROL_SCRUB_EN_BACKGROUND bit in the input
>parameters.
>This is in case "Enable Background" was previously called, and this bit was set.
>
>		ps_sm->params.scrub_params_in &=
>~RAS2_PATROL_SCRUB_EN_BACKGROUND;
We need to stop background scrub if it is already running before start an on-demand scrubbing. 
The RAS2_PATROL_SCRUB_EN_BACKGROUND bit would be cleared with disable  bg scrub
with the following code
in ras2_hw_scrub_set_enabled_bg() when disable background scrub('enable' is 0 in this case).
ps_sm->params.scrub_params_in &= ~RAS2_PATROL_SCRUB_EN_BACKGROUND;
ps_sm->params.scrub_params_in |= FIELD_PREP(RAS2_PATROL_SCRUB_EN_BACKGROUND,
						    enable);
Hope it make sense?
>
>
>> +		ps_sm->params.patrol_scrub_command =
>RAS2_START_PATROL_SCRUBBER;
>> +	} else {
>> +		ps_sm->params.patrol_scrub_command =
>RAS2_STOP_PATROL_SCRUBBER;
>> +	}
>> +
>> +	ret = ras2_send_pcc_cmd(ras2_ctx, RAS2_PCC_CMD_EXEC);
>> +	if (ret) {
>> +		dev_err(ras2_ctx->dev, "failed to enable(%d) the demand
>scrubbing\n", enable);
>> +		return ret;
>> +	}
>> +	ras2_ctx->bg = false;
>> +
>> +	return ras2_update_patrol_scrub_params_cache(ras2_ctx);
>> +}
>
>
Thanks,
Shiju