Re: [PATCH v11 2/5] s390/pci: Improve function measurement state management

[Gerd Bayer <gbayer@linux.ibm.com>]

On Wed, 2026-10-28 at 11:43 -0400, Omar Elghoul wrote:
> When a zPCI function is disabled and re-enabled, the firmware implicitly
> disables function measurement while the kernel still believes it is
> enabled, leading to a disconnect between the user-visible state and the
> actual device state.
> 
> Add the statistics_on field to struct zpci_dev to track the desired FMB
> state. Introduce the functions zpci_fmb_request_on() and off(), which
> defer to zpci_fmb_enable() or disable() to perform the actual firmware
> change. This decouples the enablement or disablement step from managing
> the user's requested state.
> 
> Preserve the state in pcibios_enable_device(), pcibios_disable_device(),
> and zpci_reenable_device(), so measurement is restored automatically
> after a re-enable. New devices start with measurement on by default,
> unchanged from before.
> 
> Signed-off-by: Omar Elghoul <oelghoul@linux.ibm.com>
> ---
>  arch/s390/include/asm/pci.h |  7 +++--
>  arch/s390/pci/pci.c         | 60 +++++++++++++++++++++++++++++++++----
>  arch/s390/pci/pci_debug.c   |  6 ++--
>  3 files changed, 63 insertions(+), 10 deletions(-)
> 
> diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
> index 88a125b92bdd..dd7a17955362 100644
> --- a/arch/s390/include/asm/pci.h
> +++ b/arch/s390/include/asm/pci.h
> @@ -208,6 +208,7 @@ struct zpci_dev {
>  	struct zpci_fmb *fmb;
>  	u16		fmb_update;	/* update interval */
>  	u16		fmb_length;
> +	bool		statistics_on;	/* desired FMB enablement */
>  
>  	u8		version;
>  	enum pci_bus_speed max_bus_speed;
> @@ -349,8 +350,10 @@ int zpci_create_parent_msi_domain(struct zpci_bus *zbus);
>  void zpci_remove_parent_msi_domain(struct zpci_bus *zbus);
>  
>  /* FMB */
> -int zpci_fmb_enable_device(struct zpci_dev *);
> -int zpci_fmb_disable_device(struct zpci_dev *);
> +int zpci_fmb_request_on(struct zpci_dev *zdev);
> +int zpci_fmb_request_off(struct zpci_dev *zdev);
> +int zpci_fmb_enable(struct zpci_dev *zdev);
> +int zpci_fmb_disable(struct zpci_dev *zdev);
>  
>  /* Debug */
>  int zpci_debug_init(void);
> diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
> index c055a9ad0972..5889dd227009 100644
> --- a/arch/s390/pci/pci.c
> +++ b/arch/s390/pci/pci.c
> @@ -164,8 +164,44 @@ int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas)
>  	return cc;
>  }
>  
> +int zpci_fmb_request_on(struct zpci_dev *zdev)
> +{
> +	int rc;
> +
> +	lockdep_assert_held(&zdev->fmb_lock);
> +
> +	if (zdev->statistics_on)
> +		return -EINVAL;

It's perhaps a question of taste, but is this strict rejection of
double-enable really necessary? Wouldn't it be more defensive if the
enable was just let to pass?
Ah nevermind: That would allocate a new FMB buffer from zdev_fmb_cache
and is a memory leak.


> +
> +	rc = zpci_fmb_enable(zdev);
> +	if (rc)
> +		return rc;
> +
> +	zdev->statistics_on = true;
> +	return 0;
> +}
> +EXPORT_SYMBOL_GPL(zpci_fmb_request_on);
> +
> +int zpci_fmb_request_off(struct zpci_dev *zdev)
> +{
> +	int rc;
> +
> +	lockdep_assert_held(&zdev->fmb_lock);
> +
> +	if (!zdev->statistics_on)
> +		return -EINVAL;

Same question here: Would a double-disable hurt anybody?
Doh: Yeah, you don't want to go down that route...

> +
> +	rc = zpci_fmb_disable(zdev);
> +	if (rc)
> +		return rc;
> +
> +	zdev->statistics_on = false;
> +	return 0;
> +}
> +EXPORT_SYMBOL_GPL(zpci_fmb_request_off);
> +
>  /* Modify PCI: Set PCI function measurement parameters */
> -int zpci_fmb_enable_device(struct zpci_dev *zdev)
> +int zpci_fmb_enable(struct zpci_dev *zdev)
>  {
>  	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_SET_MEASURE);
>  	struct zpci_iommu_ctrs *ctrs;
> @@ -207,7 +243,7 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev)
>  }
>  
>  /* Modify PCI: Disable PCI function measurement */
> -int zpci_fmb_disable_device(struct zpci_dev *zdev)
> +int zpci_fmb_disable(struct zpci_dev *zdev)
>  {
>  	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_SET_MEASURE);
>  	struct zpci_fib fib = {0};
> @@ -644,7 +680,8 @@ int pcibios_enable_device(struct pci_dev *pdev, int mask)
>  
>  	zpci_debug_init_device(zdev, dev_name(&pdev->dev));
>  	mutex_lock(&zdev->fmb_lock);
> -	zpci_fmb_enable_device(zdev);
> +	if (zdev->statistics_on)
> +		zpci_fmb_enable(zdev);
>  	mutex_unlock(&zdev->fmb_lock);
>  
>  	return pci_enable_resources(pdev, mask);
> @@ -655,7 +692,8 @@ void pcibios_disable_device(struct pci_dev *pdev)
>  	struct zpci_dev *zdev = to_zpci(pdev);
>  
>  	mutex_lock(&zdev->fmb_lock);
> -	zpci_fmb_disable_device(zdev);
> +	if (zdev->statistics_on)
> +		zpci_fmb_disable(zdev);
>  	mutex_unlock(&zdev->fmb_lock);
>  	zpci_debug_exit_device(zdev);
>  }
> @@ -737,8 +775,14 @@ int zpci_reenable_device(struct zpci_dev *zdev)
>  	}
>  
>  	rc = zpci_iommu_register_ioat(zdev, &status);
> -	if (rc)
> +	if (rc) {
>  		zpci_disable_device(zdev);
> +		return rc;
> +	}
> +
> +	guard(mutex)(&zdev->fmb_lock);
> +	if (zdev->statistics_on)
> +		zpci_fmb_enable(zdev);

But that discussion about double-enable above makes me wonder:
Would we leak an FMB buffer, here - at least until patch 3 comes to the
rescue? Maybe the two patches are not so independent after all?

So, I experimented a little with patch 1 and 2 applied in an LPAR: I
injected PCI auto-recovery with 'zpcictl --reset-fw' to a NETD PF and a
NVMe PF and was pleasantly surprised that no resources were leaked
*and* statistics were enabled before and after the PCI auto-recovery.

Turns out that both the mlx5 and the nvme drivers pci_error_handlers
callbacks for error_detected() switch off statistics by way of
pci_disable_device() which calls pcibios_disable_device() - and the
callback for slot_reset (mlx5) resp. reset_done (nvme) restore the
statistics setting again by way of pci_enable_device() which calls
pcibios_enable_device().

So one could argue, that at least for the PCI auto-recovery case, this
conditional call to zpci_fmb_enable() is not needed?

>  
>  	return rc;
>  }
> @@ -847,6 +891,12 @@ struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state)
>  		goto error;
>  	zdev->state =  state;
>  
> +	/*
> +	 * Measurement is on by default for new functions, this will be honored
> +	 * by pcibios_enable_device().
> +	 */
> +	zdev->statistics_on = true;
> +
>  	mutex_init(&zdev->state_lock);
>  	mutex_init(&zdev->fmb_lock);
>  	mutex_init(&zdev->kzdev_lock);
> diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
> index c7ed7bf254b5..e479763858cd 100644
> --- a/arch/s390/pci/pci_debug.c
> +++ b/arch/s390/pci/pci_debug.c
> @@ -97,7 +97,7 @@ static int pci_perf_show(struct seq_file *m, void *v)
>  		return 0;
>  
>  	mutex_lock(&zdev->fmb_lock);
> -	if (!zdev->fmb) {
> +	if (!zdev->statistics_on || !zdev->fmb) {
>  		mutex_unlock(&zdev->fmb_lock);
>  		seq_puts(m, "FMB statistics disabled\n");
>  		return 0;
> @@ -156,10 +156,10 @@ static ssize_t pci_perf_seq_write(struct file *file, const char __user *ubuf,
>  	mutex_lock(&zdev->fmb_lock);
>  	switch (val) {
>  	case 0:
> -		rc = zpci_fmb_disable_device(zdev);
> +		rc = zpci_fmb_request_off(zdev);
>  		break;
>  	case 1:
> -		rc = zpci_fmb_enable_device(zdev);
> +		rc = zpci_fmb_request_on(zdev);
>  		break;
>  	}
>  	mutex_unlock(&zdev->fmb_lock);

But overall, this is looking good!
Thanks, Gerd