Merge tag 'powerpc-4.3-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:
 - Re-enable CONFIG_SCSI_DH in our defconfigs
 - Remove unused os_area_db_id_video_mode
 - cxl: fix leak of IRQ names in cxl_free_afu_irqs() from Andrew
 - cxl: fix leak of ctx->irq_bitmap when releasing context via kernel API from Andrew
 - cxl: fix leak of ctx->mapping when releasing kernel API contexts from Andrew
 - cxl: Workaround malformed pcie packets on some cards from Philippe
 - cxl: Fix number of allocated pages in SPA from Christophe Lombard
 - Fix checkstop in native_hpte_clear() with lockdep from Cyril
 - Panic on unhandled Machine Check on powernv from Daniel
 - selftests/powerpc: Fix build failure of load_unaligned_zeropad test

* tag 'powerpc-4.3-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  selftests/powerpc: Fix build failure of load_unaligned_zeropad test
  powerpc/powernv: Panic on unhandled Machine Check
  powerpc: Fix checkstop in native_hpte_clear() with lockdep
  cxl: Fix number of allocated pages in SPA
  cxl: Workaround malformed pcie packets on some cards
  cxl: fix leak of ctx->mapping when releasing kernel API contexts
  cxl: fix leak of ctx->irq_bitmap when releasing context via kernel API
  cxl: fix leak of IRQ names in cxl_free_afu_irqs()
  powerpc/ps3: Remove unused os_area_db_id_video_mode
  powerpc/configs: Re-enable CONFIG_SCSI_DH

arch/powerpc/configs/ppc64_defconfig

@@ -111,7 +111,7 @@ CONFIG_SCSI_QLA_FC=m
 CONFIG_SCSI_QLA_ISCSI=m
 CONFIG_SCSI_LPFC=m
 CONFIG_SCSI_VIRTIO=m
-CONFIG_SCSI_DH=m
+CONFIG_SCSI_DH=y
 CONFIG_SCSI_DH_RDAC=m
 CONFIG_SCSI_DH_ALUA=m
 CONFIG_ATA=y

arch/powerpc/configs/pseries_defconfig

@@ -114,7 +114,7 @@ CONFIG_SCSI_QLA_FC=m
 CONFIG_SCSI_QLA_ISCSI=m
 CONFIG_SCSI_LPFC=m
 CONFIG_SCSI_VIRTIO=m
-CONFIG_SCSI_DH=m
+CONFIG_SCSI_DH=y
 CONFIG_SCSI_DH_RDAC=m
 CONFIG_SCSI_DH_ALUA=m
 CONFIG_ATA=y

arch/powerpc/include/asm/machdep.h

@@ -61,8 +61,13 @@ struct machdep_calls {
 					       unsigned long addr,
 					       unsigned char *hpte_slot_array,
 					       int psize, int ssize, int local);
-	/* special for kexec, to be called in real mode, linear mapping is
-	 * destroyed as well */
+	/*
+	 * Special for kexec.
+	 * To be called in real mode with interrupts disabled. No locks are
+	 * taken as such, concurrent access on pre POWER5 hardware could result
+	 * in a deadlock.
+	 * The linear mapping is destroyed as well.
+	 */
 	void		(*hpte_clear_all)(void);
 
 	void __iomem *	(*ioremap)(phys_addr_t addr, unsigned long size,

arch/powerpc/mm/hash_native_64.c

@@ -582,13 +582,21 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
  * be when they isi), and we are the only one left.  We rely on our kernel
  * mapping being 0xC0's and the hardware ignoring those two real bits.
  *
+ * This must be called with interrupts disabled.
+ *
+ * Taking the native_tlbie_lock is unsafe here due to the possibility of
+ * lockdep being on. On pre POWER5 hardware, not taking the lock could
+ * cause deadlock. POWER5 and newer not taking the lock is fine. This only
+ * gets called during boot before secondary CPUs have come up and during
+ * crashdump and all bets are off anyway.
+ *
  * TODO: add batching support when enabled.  remember, no dynamic memory here,
  * athough there is the control page available...
  */
 static void native_hpte_clear(void)
 {
 	unsigned long vpn = 0;
-	unsigned long slot, slots, flags;
+	unsigned long slot, slots;
 	struct hash_pte *hptep = htab_address;
 	unsigned long hpte_v;
 	unsigned long pteg_count;
@@ -596,13 +604,6 @@ static void native_hpte_clear(void)
 
 	pteg_count = htab_hash_mask + 1;
 
-	local_irq_save(flags);
-
-	/* we take the tlbie lock and hold it.  Some hardware will
-	 * deadlock if we try to tlbie from two processors at once.
-	 */
-	raw_spin_lock(&native_tlbie_lock);
-
 	slots = pteg_count * HPTES_PER_GROUP;
 
 	for (slot = 0; slot < slots; slot++, hptep++) {
@@ -614,8 +615,8 @@ static void native_hpte_clear(void)
 		hpte_v = be64_to_cpu(hptep->v);
 
 		/*
-		 * Call __tlbie() here rather than tlbie() since we
-		 * already hold the native_tlbie_lock.
+		 * Call __tlbie() here rather than tlbie() since we can't take the
+		 * native_tlbie_lock.
 		 */
 		if (hpte_v & HPTE_V_VALID) {
 			hpte_decode(hptep, slot, &psize, &apsize, &ssize, &vpn);
@@ -625,8 +626,6 @@ static void native_hpte_clear(void)
 	}
 
 	asm volatile("eieio; tlbsync; ptesync":::"memory");
-	raw_spin_unlock(&native_tlbie_lock);
-	local_irq_restore(flags);
 }
 
 /*

arch/powerpc/platforms/powernv/opal.c

@@ -487,9 +487,12 @@ int opal_machine_check(struct pt_regs *regs)
 	 *    PRD component would have already got notified about this
 	 *    error through other channels.
 	 *
-	 * In any case, let us just fall through. We anyway heading
-	 * down to panic path.
+	 * If hardware marked this as an unrecoverable MCE, we are
+	 * going to panic anyway. Even if it didn't, it's not safe to
+	 * continue at this point, so we should explicitly panic.
 	 */
+
+	panic("PowerNV Unrecovered Machine Check");
 	return 0;
 }
 

arch/powerpc/platforms/ps3/os-area.c

@@ -194,11 +194,6 @@ static const struct os_area_db_id os_area_db_id_rtc_diff = {
 	.key = OS_AREA_DB_KEY_RTC_DIFF
 };
 
-static const struct os_area_db_id os_area_db_id_video_mode = {
-	.owner = OS_AREA_DB_OWNER_LINUX,
-	.key = OS_AREA_DB_KEY_VIDEO_MODE
-};
-
 #define SECONDS_FROM_1970_TO_2000 946684800LL
 
 /**

drivers/misc/cxl/api.c

@@ -105,6 +105,7 @@ EXPORT_SYMBOL_GPL(cxl_allocate_afu_irqs);
 
 void cxl_free_afu_irqs(struct cxl_context *ctx)
 {
+	afu_irq_name_free(ctx);
 	cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter);
 }
 EXPORT_SYMBOL_GPL(cxl_free_afu_irqs);

drivers/misc/cxl/context.c

@@ -275,6 +275,9 @@ static void reclaim_ctx(struct rcu_head *rcu)
 	if (ctx->kernelapi)
 		kfree(ctx->mapping);
 
+	if (ctx->irq_bitmap)
+		kfree(ctx->irq_bitmap);
+
 	kfree(ctx);
 }
 

drivers/misc/cxl/cxl.h

@@ -677,6 +677,7 @@ int cxl_register_serr_irq(struct cxl_afu *afu);
 void cxl_release_serr_irq(struct cxl_afu *afu);
 int afu_register_irqs(struct cxl_context *ctx, u32 count);
 void afu_release_irqs(struct cxl_context *ctx, void *cookie);
+void afu_irq_name_free(struct cxl_context *ctx);
 irqreturn_t cxl_slice_irq_err(int irq, void *data);
 
 int cxl_debugfs_init(void);

drivers/misc/cxl/file.c

@@ -120,9 +120,16 @@ int afu_release(struct inode *inode, struct file *file)
 		 __func__, ctx->pe);
 	cxl_context_detach(ctx);
 
+
+	/*
+	 * Delete the context's mapping pointer, unless it's created by the
+	 * kernel API, in which case leave it so it can be freed by reclaim_ctx()
+	 */
+	if (!ctx->kernelapi) {
 		mutex_lock(&ctx->mapping_lock);
 		ctx->mapping = NULL;
 		mutex_unlock(&ctx->mapping_lock);
+	}
 
 	put_device(&ctx->afu->dev);
 

drivers/misc/cxl/irq.c

@@ -414,7 +414,7 @@ void cxl_release_psl_irq(struct cxl_afu *afu)
 	kfree(afu->psl_irq_name);
 }
 
-static void afu_irq_name_free(struct cxl_context *ctx)
+void afu_irq_name_free(struct cxl_context *ctx)
 {
 	struct cxl_irq_name *irq_name, *tmp;
 
@@ -524,7 +524,5 @@ void afu_release_irqs(struct cxl_context *ctx, void *cookie)
 	afu_irq_name_free(ctx);
 	cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter);
 
-	kfree(ctx->irq_bitmap);
-	ctx->irq_bitmap = NULL;
 	ctx->irq_count = 0;
 }

drivers/misc/cxl/native.c

@@ -457,6 +457,7 @@ static int activate_afu_directed(struct cxl_afu *afu)
 
 	dev_info(&afu->dev, "Activating AFU directed mode\n");
 
+	afu->num_procs = afu->max_procs_virtualised;
 	if (afu->spa == NULL) {
 		if (cxl_alloc_spa(afu))
 			return -ENOMEM;
@@ -468,7 +469,6 @@ static int activate_afu_directed(struct cxl_afu *afu)
 	cxl_p1n_write(afu, CXL_PSL_ID_An, CXL_PSL_ID_An_F | CXL_PSL_ID_An_L);
 
 	afu->current_mode = CXL_MODE_DIRECTED;
-	afu->num_procs = afu->max_procs_virtualised;
 
 	if ((rc = cxl_chardev_m_afu_add(afu)))
 		return rc;

drivers/misc/cxl/pci.c

@@ -1035,6 +1035,32 @@ static int cxl_read_vsec(struct cxl *adapter, struct pci_dev *dev)
 	return 0;
 }
 
+/*
+ * Workaround a PCIe Host Bridge defect on some cards, that can cause
+ * malformed Transaction Layer Packet (TLP) errors to be erroneously
+ * reported. Mask this error in the Uncorrectable Error Mask Register.
+ *
+ * The upper nibble of the PSL revision is used to distinguish between
+ * different cards. The affected ones have it set to 0.
+ */
+static void cxl_fixup_malformed_tlp(struct cxl *adapter, struct pci_dev *dev)
+{
+	int aer;
+	u32 data;
+
+	if (adapter->psl_rev & 0xf000)
+		return;
+	if (!(aer = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR)))
+		return;
+	pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_MASK, &data);
+	if (data & PCI_ERR_UNC_MALF_TLP)
+		if (data & PCI_ERR_UNC_INTN)
+			return;
+	data |= PCI_ERR_UNC_MALF_TLP;
+	data |= PCI_ERR_UNC_INTN;
+	pci_write_config_dword(dev, aer + PCI_ERR_UNCOR_MASK, data);
+}
+
 static int cxl_vsec_looks_ok(struct cxl *adapter, struct pci_dev *dev)
 {
 	if (adapter->vsec_status & CXL_STATUS_SECOND_PORT)
@@ -1134,6 +1160,8 @@ static int cxl_configure_adapter(struct cxl *adapter, struct pci_dev *dev)
 	if ((rc = cxl_vsec_looks_ok(adapter, dev)))
 	        return rc;
 
+	cxl_fixup_malformed_tlp(adapter, dev);
+
 	if ((rc = setup_cxl_bars(dev)))
 		return rc;
 

tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c

@@ -25,10 +25,19 @@
 
 #define FIXUP_SECTION ".ex_fixup"
 
+static inline unsigned long __fls(unsigned long x);
+
 #include "word-at-a-time.h"
 
 #include "utils.h"
 
+static inline unsigned long __fls(unsigned long x)
+{
+	int lz;
+
+	asm (PPC_CNTLZL "%0,%1" : "=r" (lz) : "r" (x));
+	return sizeof(unsigned long) - 1 - lz;
+}
 
 static int page_size;
 static char *mem_region;