[PATCH v8 2/4] s390/pci: Reuse FMB buffer and preserve state in device re-enablement

[Omar Elghoul]

Don't free the FMB buffer when disabling measurement in
zpci_fmb_disable_device(). Instead, make the buffer persistent for the
lifetime of the device and reuse it across enable/disable cycles. Defer
freeing the buffer until teardown in zpci_release_device().

To support the persistent buffers, add the fmb_enabled bool to struct
zpci_dev to decouple whether FMB is enabled from whether the buffer has
been allocated. Audit the only consumer of zdev->fmb as a liveness check
and update it to reflect this change.

Introduce the function zpci_fmb_reenable_device() to ensure that the FMB
is enabled. If it was already enabled, disable it, zero the counters,
and re-enable it. This allows the function to be used in both first-time
enabling and re-enabling measurement. Call it in zpci_reenable_device()
to preserve the FMB enablement if it had been implicitly disabled by
firmware in zpci_disable_device().

Signed-off-by: Omar Elghoul <oelghoul@xxxxxxxxxxxxx>
---
 arch/s390/include/asm/pci.h |  2 +
 arch/s390/pci/pci.c         | 76 ++++++++++++++++++++++++++++---------
 arch/s390/pci/pci_debug.c   |  2 +-
 3 files changed, 62 insertions(+), 18 deletions(-)

diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 88a125b92bdd..2920de1f9484 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -205,6 +205,7 @@ struct zpci_dev {
 
 	/* Function measurement block */
 	struct mutex fmb_lock;
+	bool fmb_enabled;
 	struct zpci_fmb *fmb;
 	u16		fmb_update;	/* update interval */
 	u16		fmb_length;
@@ -351,6 +352,7 @@ 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_reenable_device(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..ec729be91f97 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -175,13 +175,17 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev)
 
 	lockdep_assert_held(&zdev->fmb_lock);
 
-	if (zdev->fmb || sizeof(*zdev->fmb) < zdev->fmb_length)
+	if (zdev->fmb_enabled || sizeof(*zdev->fmb) < zdev->fmb_length)
 		return -EINVAL;
 
-	zdev->fmb = kmem_cache_zalloc(zdev_fmb_cache, GFP_KERNEL);
-	if (!zdev->fmb)
-		return -ENOMEM;
-	WARN_ON((u64) zdev->fmb & 0xf);
+	if (!zdev->fmb) {
+		zdev->fmb = kmem_cache_zalloc(zdev_fmb_cache, GFP_KERNEL);
+		if (!zdev->fmb)
+			return -ENOMEM;
+	} else {
+		/* reuse the same FMB buffer for as long the zdev lives */
+		memset(zdev->fmb, 0, sizeof(*zdev->fmb));
+	}
 
 	/* reset software counters */
 	spin_lock_irqsave(&zdev->dom_lock, flags);
@@ -199,11 +203,11 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev)
 	fib.fmb_addr = virt_to_phys(zdev->fmb);
 	fib.gd = zdev->gisa;
 	cc = zpci_mod_fc(req, &fib, &status);
-	if (cc) {
-		kmem_cache_free(zdev_fmb_cache, zdev->fmb);
-		zdev->fmb = NULL;
-	}
-	return cc ? -EIO : 0;
+	if (cc)
+		return -EIO;
+
+	zdev->fmb_enabled = true;
+	return 0;
 }
 
 /* Modify PCI: Disable PCI function measurement */
@@ -215,7 +219,7 @@ int zpci_fmb_disable_device(struct zpci_dev *zdev)
 
 	lockdep_assert_held(&zdev->fmb_lock);
 
-	if (!zdev->fmb)
+	if (!zdev->fmb_enabled)
 		return -EINVAL;
 
 	fib.gd = zdev->gisa;
@@ -224,13 +228,39 @@ int zpci_fmb_disable_device(struct zpci_dev *zdev)
 	cc = zpci_mod_fc(req, &fib, &status);
 	if (cc == 3) /* Function already gone. */
 		cc = 0;
+	if (cc)
+		return -EIO;
 
-	if (!cc) {
-		kmem_cache_free(zdev_fmb_cache, zdev->fmb);
-		zdev->fmb = NULL;
-	}
-	return cc ? -EIO : 0;
+	zdev->fmb_enabled = false;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(zpci_fmb_disable_device);
+
+int zpci_fmb_reenable_device(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_SET_MEASURE);
+	struct zpci_fib fib = {0};
+	u8 cc, status;
+
+	lockdep_assert_held(&zdev->fmb_lock);
+
+	if (!zdev->fmb_enabled)
+		return zpci_fmb_enable_device(zdev);
+
+	fib.gd = zdev->gisa;
+	cc = zpci_mod_fc(req, &fib, &status); /* Disable function measurement */
+
+	/* Unlike in zpci_fmb_disable_device(), cc == 3 is not a valid state here
+	 * because we are re-enabling function measurement for the same function
+	 * handle.
+	 */
+	if (cc)
+		return -EIO;
+
+	zdev->fmb_enabled = false;
+	return zpci_fmb_enable_device(zdev);
 }
+EXPORT_SYMBOL_GPL(zpci_fmb_reenable_device);
 
 static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len)
 {
@@ -737,8 +767,14 @@ 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->fmb_enabled)
+		zpci_fmb_reenable_device(zdev);
 
 	return rc;
 }
@@ -1003,6 +1039,12 @@ void zpci_release_device(struct kref *kref)
 	if (zdev->has_resources)
 		zpci_cleanup_bus_resources(zdev);
 
+	if (zdev->fmb) {
+		zdev->fmb_enabled = false;
+		kmem_cache_free(zdev_fmb_cache, zdev->fmb);
+		zdev->fmb = NULL;
+	}
+
 	zpci_bus_device_unregister(zdev);
 	zpci_destroy_iommu(zdev);
 	zpci_dbg(3, "rem fid:%x\n", zdev->fid);
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index c7ed7bf254b5..44f026ead414 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->fmb_enabled) {
 		mutex_unlock(&zdev->fmb_lock);
 		seq_puts(m, "FMB statistics disabled\n");
 		return 0;
-- 
2.55.0