Merge: Fix for CSB.V bit never becomes valid for NX Gzip job during LPAR migration

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/1632

Bugzilla: https://bugzilla.redhat.com/2130348

Build Info: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=50152615

Tested: Tested with LPM

Signed-off-by: Mukesh Chaurasiya <mchauras@redhat.com>

Approved-by: Waiman Long <longman@redhat.com>
Approved-by: Steve Best <sbest@redhat.com>

Signed-off-by: Herton R. Krzesinski <herton@redhat.com>

Author: Herton R. Krzesinski

arch/powerpc/include/asm/mmu.h

@@ -129,6 +129,9 @@
  */
 #define MMU_FTR_1T_SEGMENT		ASM_CONST(0x40000000)
 
+// NX paste RMA reject in DSI
+#define MMU_FTR_NX_DSI			ASM_CONST(0x80000000)
+
 /* MMU feature bit sets for various CPUs */
 #define MMU_FTRS_DEFAULT_HPTE_ARCH_V2	(MMU_FTR_HPTE_TABLE | MMU_FTR_TLBIEL | MMU_FTR_16M_PAGE)
 #define MMU_FTRS_POWER		MMU_FTRS_DEFAULT_HPTE_ARCH_V2
@@ -193,7 +196,7 @@ enum {
 #endif
 #ifdef CONFIG_PPC_RADIX_MMU
 		MMU_FTR_TYPE_RADIX |
-		MMU_FTR_GTSE |
+		MMU_FTR_GTSE | MMU_FTR_NX_DSI |
 #endif /* CONFIG_PPC_RADIX_MMU */
 #endif
 #ifdef CONFIG_PPC_KUAP

arch/powerpc/kernel/prom.c

@@ -138,7 +138,7 @@ static void __init move_device_tree(void)
 }
 
 /*
- * ibm,pa-features is a per-cpu property that contains a string of
+ * ibm,pa/pi-features is a per-cpu property that contains a string of
  * attribute descriptors, each of which has a 2 byte header plus up
  * to 254 bytes worth of processor attribute bits.  First header
  * byte specifies the number of bytes following the header.
@@ -150,15 +150,17 @@ static void __init move_device_tree(void)
  * is supported/not supported.  Note that the bit numbers are
  * big-endian to match the definition in PAPR.
  */
-static struct ibm_pa_feature {
+struct ibm_feature {
 	unsigned long	cpu_features;	/* CPU_FTR_xxx bit */
 	unsigned long	mmu_features;	/* MMU_FTR_xxx bit */
 	unsigned int	cpu_user_ftrs;	/* PPC_FEATURE_xxx bit */
 	unsigned int	cpu_user_ftrs2;	/* PPC_FEATURE2_xxx bit */
-	unsigned char	pabyte;		/* byte number in ibm,pa-features */
+	unsigned char	pabyte;		/* byte number in ibm,pa/pi-features */
 	unsigned char	pabit;		/* bit number (big-endian) */
 	unsigned char	invert;		/* if 1, pa bit set => clear feature */
-} ibm_pa_features[] __initdata = {
+};
+
+static struct ibm_feature ibm_pa_features[] __initdata = {
 	{ .pabyte = 0,  .pabit = 0, .cpu_user_ftrs = PPC_FEATURE_HAS_MMU },
 	{ .pabyte = 0,  .pabit = 1, .cpu_user_ftrs = PPC_FEATURE_HAS_FPU },
 	{ .pabyte = 0,  .pabit = 3, .cpu_features  = CPU_FTR_CTRL },
@@ -180,9 +182,19 @@ static struct ibm_pa_feature {
 	{ .pabyte = 64, .pabit = 0, .cpu_features = CPU_FTR_DAWR1 },
 };
 
+/*
+ * ibm,pi-features property provides the support of processor specific
+ * options not described in ibm,pa-features. Right now use byte 0, bit 3
+ * which indicates the occurrence of DSI interrupt when the paste operation
+ * on the suspended NX window.
+ */
+static struct ibm_feature ibm_pi_features[] __initdata = {
+	{ .pabyte = 0, .pabit = 3, .mmu_features  = MMU_FTR_NX_DSI },
+};
+
 static void __init scan_features(unsigned long node, const unsigned char *ftrs,
 				 unsigned long tablelen,
-				 struct ibm_pa_feature *fp,
+				 struct ibm_feature *fp,
 				 unsigned long ft_size)
 {
 	unsigned long i, len, bit;
@@ -219,17 +231,18 @@ static void __init scan_features(unsigned long node, const unsigned char *ftrs,
 	}
 }
 
-static void __init check_cpu_pa_features(unsigned long node)
+static void __init check_cpu_features(unsigned long node, char *name,
+				      struct ibm_feature *fp,
+				      unsigned long size)
 {
 	const unsigned char *pa_ftrs;
 	int tablelen;
 
-	pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen);
+	pa_ftrs = of_get_flat_dt_prop(node, name, &tablelen);
 	if (pa_ftrs == NULL)
 		return;
 
-	scan_features(node, pa_ftrs, tablelen,
-		      ibm_pa_features, ARRAY_SIZE(ibm_pa_features));
+	scan_features(node, pa_ftrs, tablelen, fp, size);
 }
 
 #ifdef CONFIG_PPC_64S_HASH_MMU
@@ -383,7 +396,10 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 			identify_cpu(0, be32_to_cpup(prop));
 
 		check_cpu_feature_properties(node);
-		check_cpu_pa_features(node);
+		check_cpu_features(node, "ibm,pa-features", ibm_pa_features,
+				   ARRAY_SIZE(ibm_pa_features));
+		check_cpu_features(node, "ibm,pi-features", ibm_pi_features,
+				   ARRAY_SIZE(ibm_pi_features));
 	}
 
 	identical_pvr_fixup(node);

arch/powerpc/mm/fault.c

@@ -368,7 +368,22 @@ static void sanity_check_fault(bool is_write, bool is_user,
 #elif defined(CONFIG_PPC_8xx)
 #define page_fault_is_bad(__err)	((__err) & DSISR_NOEXEC_OR_G)
 #elif defined(CONFIG_PPC64)
-#define page_fault_is_bad(__err)	((__err) & DSISR_BAD_FAULT_64S)
+static int page_fault_is_bad(unsigned long err)
+{
+	unsigned long flag = DSISR_BAD_FAULT_64S;
+
+	/*
+	 * PAPR+ v2.11 § 14.15.3.4.1 (unreleased)
+	 * If byte 0, bit 3 of pi-attribute-specifier-type in
+	 * ibm,pi-features property is defined, ignore the DSI error
+	 * which is caused by the paste instruction on the
+	 * suspended NX window.
+	 */
+	if (mmu_has_feature(MMU_FTR_NX_DSI))
+		flag &= ~DSISR_BAD_COPYPASTE;
+
+	return err & flag;
+}
 #else
 #define page_fault_is_bad(__err)	((__err) & DSISR_BAD_FAULT_32S)
 #endif

arch/powerpc/platforms/pseries/mobility.c

@@ -740,11 +740,19 @@ static int pseries_migrate_partition(u64 handle)
 #ifdef CONFIG_PPC_WATCHDOG
 	factor = nmi_wd_lpm_factor;
 #endif
+	/*
+	 * When the migration is initiated, the hypervisor changes VAS
+	 * mappings to prepare before OS gets the notification and
+	 * closes all VAS windows. NX generates continuous faults during
+	 * this time and the user space can not differentiate these
+	 * faults from the migration event. So reduce this time window
+	 * by closing VAS windows at the beginning of this function.
+	 */
+	vas_migration_handler(VAS_SUSPEND);
+
 	ret = wait_for_vasi_session_suspending(handle);
 	if (ret)
-		return ret;
-
-	vas_migration_handler(VAS_SUSPEND);
+		goto out;
 
 	if (factor)
 		watchdog_nmi_set_timeout_pct(factor);
@@ -765,6 +773,7 @@ static int pseries_migrate_partition(u64 handle)
 	if (factor)
 		watchdog_nmi_set_timeout_pct(0);
 
+out:
 	vas_migration_handler(VAS_RESUME);
 
 	return ret;

arch/powerpc/platforms/pseries/vas-sysfs.c

@@ -74,26 +74,26 @@ struct vas_sysfs_entry {
 
 /*
  * Create sysfs interface:
- * /sys/devices/vas/vas0/gzip/default_capabilities
+ * /sys/devices/virtual/misc/vas/vas0/gzip/default_capabilities
  *	This directory contains the following VAS GZIP capabilities
  *	for the defaule credit type.
- * /sys/devices/vas/vas0/gzip/default_capabilities/nr_total_credits
+ * /sys/devices/virtual/misc/vas/vas0/gzip/default_capabilities/nr_total_credits
  *	Total number of default credits assigned to the LPAR which
  *	can be changed with DLPAR operation.
- * /sys/devices/vas/vas0/gzip/default_capabilities/nr_used_credits
+ * /sys/devices/virtual/misc/vas/vas0/gzip/default_capabilities/nr_used_credits
  *	Number of credits used by the user space. One credit will
  *	be assigned for each window open.
  *
- * /sys/devices/vas/vas0/gzip/qos_capabilities
+ * /sys/devices/virtual/misc/vas/vas0/gzip/qos_capabilities
  *	This directory contains the following VAS GZIP capabilities
  *	for the Quality of Service (QoS) credit type.
- * /sys/devices/vas/vas0/gzip/qos_capabilities/nr_total_credits
+ * /sys/devices/virtual/misc/vas/vas0/gzip/qos_capabilities/nr_total_credits
  *	Total number of QoS credits assigned to the LPAR. The user
  *	has to define this value using HMC interface. It can be
  *	changed dynamically by the user.
- * /sys/devices/vas/vas0/gzip/qos_capabilities/nr_used_credits
+ * /sys/devices/virtual/misc/vas/vas0/gzip/qos_capabilities/nr_used_credits
  *	Number of credits used by the user space.
- * /sys/devices/vas/vas0/gzip/qos_capabilities/update_total_credits
+ * /sys/devices/virtual/misc/vas/vas0/gzip/qos_capabilities/update_total_credits
  *	Update total QoS credits dynamically
  */
 
@@ -108,13 +108,15 @@ static struct attribute *vas_def_capab_attrs[] = {
 	&nr_used_credits_attribute.attr,
 	NULL,
 };
+ATTRIBUTE_GROUPS(vas_def_capab);
 
 static struct attribute *vas_qos_capab_attrs[] = {
 	&nr_total_credits_attribute.attr,
 	&nr_used_credits_attribute.attr,
 	&update_total_credits_attribute.attr,
 	NULL,
 };
+ATTRIBUTE_GROUPS(vas_qos_capab);
 
 static ssize_t vas_type_show(struct kobject *kobj, struct attribute *attr,
 			     char *buf)
@@ -163,13 +165,13 @@ static const struct sysfs_ops vas_sysfs_ops = {
 static struct kobj_type vas_def_attr_type = {
 		.release	=	vas_type_release,
 		.sysfs_ops      =       &vas_sysfs_ops,
-		.default_attrs  =       vas_def_capab_attrs,
+		.default_groups	=	vas_def_capab_groups,
 };
 
 static struct kobj_type vas_qos_attr_type = {
 		.release	=	vas_type_release,
 		.sysfs_ops	=	&vas_sysfs_ops,
-		.default_attrs	=	vas_qos_capab_attrs,
+		.default_groups	=	vas_qos_capab_groups,
 };
 
 static char *vas_caps_kobj_name(struct vas_caps_entry *centry,

arch/powerpc/platforms/pseries/vas.c

@@ -192,16 +192,41 @@ irqreturn_t pseries_vas_fault_thread_fn(int irq, void *data)
 	struct vas_user_win_ref *tsk_ref;
 	int rc;
 
-	rc = h_get_nx_fault(txwin->vas_win.winid, (u64)virt_to_phys(&crb));
-	if (!rc) {
-		tsk_ref = &txwin->vas_win.task_ref;
-		vas_dump_crb(&crb);
-		vas_update_csb(&crb, tsk_ref);
+	while (atomic_read(&txwin->pending_faults)) {
+		rc = h_get_nx_fault(txwin->vas_win.winid, (u64)virt_to_phys(&crb));
+		if (!rc) {
+			tsk_ref = &txwin->vas_win.task_ref;
+			vas_dump_crb(&crb);
+			vas_update_csb(&crb, tsk_ref);
+		}
+		atomic_dec(&txwin->pending_faults);
 	}
 
 	return IRQ_HANDLED;
 }
 
+/*
+ * irq_default_primary_handler() can be used only with IRQF_ONESHOT
+ * which disables IRQ before executing the thread handler and enables
+ * it after. But this disabling interrupt sets the VAS IRQ OFF
+ * state in the hypervisor. If the NX generates fault interrupt
+ * during this window, the hypervisor will not deliver this
+ * interrupt to the LPAR. So use VAS specific IRQ handler instead
+ * of calling the default primary handler.
+ */
+static irqreturn_t pseries_vas_irq_handler(int irq, void *data)
+{
+	struct pseries_vas_window *txwin = data;
+
+	/*
+	 * The thread hanlder will process this interrupt if it is
+	 * already running.
+	 */
+	atomic_inc(&txwin->pending_faults);
+
+	return IRQ_WAKE_THREAD;
+}
+
 /*
  * Allocate window and setup IRQ mapping.
  */
@@ -232,8 +257,9 @@ static int allocate_setup_window(struct pseries_vas_window *txwin,
 		goto out_irq;
 	}
 
-	rc = request_threaded_irq(txwin->fault_virq, NULL,
-				  pseries_vas_fault_thread_fn, IRQF_ONESHOT,
+	rc = request_threaded_irq(txwin->fault_virq,
+				  pseries_vas_irq_handler,
+				  pseries_vas_fault_thread_fn, 0,
 				  txwin->name, txwin);
 	if (rc) {
 		pr_err("VAS-Window[%d]: Request IRQ(%u) failed with %d\n",

arch/powerpc/platforms/pseries/vas.h

@@ -132,6 +132,7 @@ struct pseries_vas_window {
 	u64 flags;
 	char *name;
 	int fault_virq;
+	atomic_t pending_faults; /* Number of pending faults */
 };
 
 int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps);