Linux 3.4.78

commit b50c259e25 upstream.

If we discover a bad block when reading we split the request and
potentially read some of it from a different device.

The code path of this has two bugs in RAID10.
1/ we get a spin_lock with _irq, but unlock without _irq!!
2/ The calculation of 'sectors_handled' is wrong, as can be clearly
   seen by comparison with raid1.c

This leads to at least 2 warnings and a probable crash is a RAID10
ever had known bad blocks.

Fixes: 856e08e237
Reported-by: Damian Nowak <spam@nowaker.net>
URL: https://bugzilla.kernel.org/show_bug.cgi?id=68181
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 4
-SUBLEVEL = 77
+SUBLEVEL = 78
 EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 

arch/x86/kernel/cpu/perf_event_amd_ibs.c

@@ -9,6 +9,7 @@
 #include <linux/perf_event.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/apic.h>
 
@@ -209,6 +210,18 @@ out:
 	return ret;
 }
 
+static void ibs_eilvt_setup(void)
+{
+	/*
+	 * Force LVT offset assignment for family 10h: The offsets are
+	 * not assigned by the BIOS for this family, so the OS is
+	 * responsible for doing it. If the OS assignment fails, fall
+	 * back to BIOS settings and try to setup this.
+	 */
+	if (boot_cpu_data.x86 == 0x10)
+		force_ibs_eilvt_setup();
+}
+
 static inline int get_ibs_lvt_offset(void)
 {
 	u64 val;
@@ -244,6 +257,36 @@ static void clear_APIC_ibs(void *dummy)
 		setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
 }
 
+#ifdef CONFIG_PM
+
+static int perf_ibs_suspend(void)
+{
+	clear_APIC_ibs(NULL);
+	return 0;
+}
+
+static void perf_ibs_resume(void)
+{
+	ibs_eilvt_setup();
+	setup_APIC_ibs(NULL);
+}
+
+static struct syscore_ops perf_ibs_syscore_ops = {
+	.resume		= perf_ibs_resume,
+	.suspend	= perf_ibs_suspend,
+};
+
+static void perf_ibs_pm_init(void)
+{
+	register_syscore_ops(&perf_ibs_syscore_ops);
+}
+
+#else
+
+static inline void perf_ibs_pm_init(void) { }
+
+#endif
+
 static int __cpuinit
 perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 {
@@ -270,18 +313,12 @@ static __init int amd_ibs_init(void)
 	if (!caps)
 		return -ENODEV;	/* ibs not supported by the cpu */
 
-	/*
-	 * Force LVT offset assignment for family 10h: The offsets are
-	 * not assigned by the BIOS for this family, so the OS is
-	 * responsible for doing it. If the OS assignment fails, fall
-	 * back to BIOS settings and try to setup this.
-	 */
-	if (boot_cpu_data.x86 == 0x10)
-		force_ibs_eilvt_setup();
+	ibs_eilvt_setup();
 
 	if (!ibs_eilvt_valid())
 		goto out;
 
+	perf_ibs_pm_init();
 	get_online_cpus();
 	ibs_caps = caps;
 	/* make ibs_caps visible to other cpus: */

arch/x86/kvm/lapic.c

@@ -1278,14 +1278,12 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
 {
 	u32 data;
-	void *vapic;
 
 	if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr)
 		return;
 
-	vapic = kmap_atomic(vcpu->arch.apic->vapic_page);
-	data = *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr));
-	kunmap_atomic(vapic);
+	kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+			      sizeof(u32));
 
 	apic_set_tpr(vcpu->arch.apic, data & 0xff);
 }
@@ -1295,7 +1293,6 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
 	u32 data, tpr;
 	int max_irr, max_isr;
 	struct kvm_lapic *apic;
-	void *vapic;
 
 	if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr)
 		return;
@@ -1310,17 +1307,24 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
 		max_isr = 0;
 	data = (tpr & 0xff) | ((max_isr & 0xf0) << 8) | (max_irr << 24);
 
-	vapic = kmap_atomic(vcpu->arch.apic->vapic_page);
-	*(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr)) = data;
-	kunmap_atomic(vapic);
+	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+			       sizeof(u32));
 }
 
-void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
+int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
 {
 	if (!irqchip_in_kernel(vcpu->kvm))
-		return;
+		return -EINVAL;
+
+	if (vapic_addr) {
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+					&vcpu->arch.apic->vapic_cache,
+					vapic_addr, sizeof(u32)))
+			return -EINVAL;
+       }
 
 	vcpu->arch.apic->vapic_addr = vapic_addr;
+	return 0;
 }
 
 int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)

arch/x86/kvm/lapic.h

@@ -15,7 +15,7 @@ struct kvm_lapic {
 	bool irr_pending;
 	void *regs;
 	gpa_t vapic_addr;
-	struct page *vapic_page;
+	struct gfn_to_hva_cache vapic_cache;
 };
 int kvm_create_lapic(struct kvm_vcpu *vcpu);
 void kvm_free_lapic(struct kvm_vcpu *vcpu);
@@ -46,7 +46,7 @@ int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
 u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu);
 void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data);
 
-void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
+int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
 void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu);
 

arch/x86/kvm/x86.c

@@ -2728,8 +2728,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&va, argp, sizeof va))
 			goto out;
-		r = 0;
-		kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+		r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
 		break;
 	}
 	case KVM_X86_SETUP_MCE: {
@@ -5075,33 +5074,6 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 			!kvm_event_needs_reinjection(vcpu);
 }
 
-static void vapic_enter(struct kvm_vcpu *vcpu)
-{
-	struct kvm_lapic *apic = vcpu->arch.apic;
-	struct page *page;
-
-	if (!apic || !apic->vapic_addr)
-		return;
-
-	page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
-
-	vcpu->arch.apic->vapic_page = page;
-}
-
-static void vapic_exit(struct kvm_vcpu *vcpu)
-{
-	struct kvm_lapic *apic = vcpu->arch.apic;
-	int idx;
-
-	if (!apic || !apic->vapic_addr)
-		return;
-
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	kvm_release_page_dirty(apic->vapic_page);
-	mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-}
-
 static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 {
 	int max_irr, tpr;
@@ -5385,7 +5357,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	}
 
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
-	vapic_enter(vcpu);
 
 	r = 1;
 	while (r > 0) {
@@ -5442,8 +5413,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 
 	srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
 
-	vapic_exit(vcpu);
-
 	return r;
 }
 

drivers/hwmon/coretemp.c

@@ -53,7 +53,7 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 
 #define BASE_SYSFS_ATTR_NO	2	/* Sysfs Base attr no for coretemp */
 #define NUM_REAL_CORES		32	/* Number of Real cores per cpu */
-#define CORETEMP_NAME_LENGTH	17	/* String Length of attrs */
+#define CORETEMP_NAME_LENGTH	19	/* String Length of attrs */
 #define MAX_CORE_ATTRS		4	/* Maximum no of basic attrs */
 #define TOTAL_ATTRS		(MAX_CORE_ATTRS + 1)
 #define MAX_CORE_DATA		(NUM_REAL_CORES + BASE_SYSFS_ATTR_NO)

drivers/md/raid10.c

@@ -1117,7 +1117,7 @@ read_again:
 			/* Could not read all from this device, so we will
 			 * need another r10_bio.
 			 */
-			sectors_handled = (r10_bio->sectors + max_sectors
+			sectors_handled = (r10_bio->sector + max_sectors
 					   - bio->bi_sector);
 			r10_bio->sectors = max_sectors;
 			spin_lock_irq(&conf->device_lock);
@@ -1125,7 +1125,7 @@ read_again:
 				bio->bi_phys_segments = 2;
 			else
 				bio->bi_phys_segments++;
-			spin_unlock(&conf->device_lock);
+			spin_unlock_irq(&conf->device_lock);
 			/* Cannot call generic_make_request directly
 			 * as that will be queued in __generic_make_request
 			 * and subsequent mempool_alloc might block
@@ -2943,10 +2943,6 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 			if (j == conf->copies) {
 				/* Cannot recover, so abort the recovery or
 				 * record a bad block */
-				put_buf(r10_bio);
-				if (rb2)
-					atomic_dec(&rb2->remaining);
-				r10_bio = rb2;
 				if (any_working) {
 					/* problem is that there are bad blocks
 					 * on other device(s)
@@ -2978,6 +2974,10 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 					mirror->recovery_disabled
 						= mddev->recovery_disabled;
 				}
+				put_buf(r10_bio);
+				if (rb2)
+					atomic_dec(&rb2->remaining);
+				r10_bio = rb2;
 				break;
 			}
 		}

drivers/staging/comedi/drivers/cb_pcidio.c

@@ -56,10 +56,6 @@ struct pcidio_board {
 	const char *name;	/*  name of the board */
 	int dev_id;
 	int n_8255;		/*  number of 8255 chips on board */
-
-	/*  indices of base address regions */
-	int pcicontroler_badrindex;
-	int dioregs_badrindex;
 };
 
 static const struct pcidio_board pcidio_boards[] = {
@@ -67,22 +63,16 @@ static const struct pcidio_board pcidio_boards[] = {
 	 .name = "pci-dio24",
 	 .dev_id = 0x0028,
 	 .n_8255 = 1,
-	 .pcicontroler_badrindex = 1,
-	 .dioregs_badrindex = 2,
 	 },
 	{
 	 .name = "pci-dio24h",
 	 .dev_id = 0x0014,
 	 .n_8255 = 1,
-	 .pcicontroler_badrindex = 1,
-	 .dioregs_badrindex = 2,
 	 },
 	{
 	 .name = "pci-dio48h",
 	 .dev_id = 0x000b,
 	 .n_8255 = 2,
-	 .pcicontroler_badrindex = 0,
-	 .dioregs_badrindex = 1,
 	 },
 };
 
@@ -239,10 +229,15 @@ found:
 	if (comedi_pci_enable(pcidev, thisboard->name))
 		return -EIO;
 
-	devpriv->dio_reg_base
-	    =
+	/*
+	 * Use PCI BAR 2 region if non-zero length, else use PCI BAR 1 region.
+	 * PCI BAR 1 is only used for older PCI-DIO48H boards.  At some point
+	 * the PCI-DIO48H was redesigned to use the same PCI interface chip
+	 * (and same PCI BAR region) as the other boards.
+	 */
+	devpriv->dio_reg_base =
 	    pci_resource_start(devpriv->pci_dev,
-			       pcidio_boards[index].dioregs_badrindex);
+			       (pci_resource_len(pcidev, 2) ? 2 : 1));
 
 /*
  * Allocate the subdevice structures.  alloc_subdevice() is a

fs/nilfs2/segment.c

@@ -1436,17 +1436,19 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci,
 
 		nilfs_clear_logs(&sci->sc_segbufs);
 
-		err = nilfs_segctor_extend_segments(sci, nilfs, nadd);
-		if (unlikely(err))
-			return err;
-
 		if (sci->sc_stage.flags & NILFS_CF_SUFREED) {
 			err = nilfs_sufile_cancel_freev(nilfs->ns_sufile,
 							sci->sc_freesegs,
 							sci->sc_nfreesegs,
 							NULL);
 			WARN_ON(err); /* do not happen */
+			sci->sc_stage.flags &= ~NILFS_CF_SUFREED;
 		}
+
+		err = nilfs_segctor_extend_segments(sci, nilfs, nadd);
+		if (unlikely(err))
+			return err;
+
 		nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA);
 		sci->sc_stage = prev_stage;
 	}

mm/memory-failure.c

@@ -1447,10 +1447,18 @@ static int soft_offline_huge_page(struct page *page, int flags)
 		return ret;
 	}
 done:
-	if (!PageHWPoison(hpage))
-		atomic_long_add(1 << compound_trans_order(hpage), &mce_bad_pages);
-	set_page_hwpoison_huge_page(hpage);
-	dequeue_hwpoisoned_huge_page(hpage);
+	/* overcommit hugetlb page will be freed to buddy */
+	if (PageHuge(hpage)) {
+		if (!PageHWPoison(hpage))
+			atomic_long_add(1 << compound_trans_order(hpage),
+					&mce_bad_pages);
+		set_page_hwpoison_huge_page(hpage);
+		dequeue_hwpoisoned_huge_page(hpage);
+	} else {
+		SetPageHWPoison(page);
+		atomic_long_inc(&mce_bad_pages);
+	}
+
 	/* keep elevated page count for bad page */
 	return ret;
 }

security/selinux/hooks.c

@@ -218,6 +218,14 @@ static int inode_alloc_security(struct inode *inode)
 	return 0;
 }
 
+static void inode_free_rcu(struct rcu_head *head)
+{
+	struct inode_security_struct *isec;
+
+	isec = container_of(head, struct inode_security_struct, rcu);
+	kmem_cache_free(sel_inode_cache, isec);
+}
+
 static void inode_free_security(struct inode *inode)
 {
 	struct inode_security_struct *isec = inode->i_security;
@@ -228,8 +236,16 @@ static void inode_free_security(struct inode *inode)
 		list_del_init(&isec->list);
 	spin_unlock(&sbsec->isec_lock);
 
-	inode->i_security = NULL;
-	kmem_cache_free(sel_inode_cache, isec);
+	/*
+	 * The inode may still be referenced in a path walk and
+	 * a call to selinux_inode_permission() can be made
+	 * after inode_free_security() is called. Ideally, the VFS
+	 * wouldn't do this, but fixing that is a much harder
+	 * job. For now, simply free the i_security via RCU, and
+	 * leave the current inode->i_security pointer intact.
+	 * The inode will be freed after the RCU grace period too.
+	 */
+	call_rcu(&isec->rcu, inode_free_rcu);
 }
 
 static int file_alloc_security(struct file *file)

security/selinux/include/objsec.h

@@ -38,7 +38,10 @@ struct task_security_struct {
 
 struct inode_security_struct {
 	struct inode *inode;	/* back pointer to inode object */
-	struct list_head list;	/* list of inode_security_struct */
+	union {
+		struct list_head list;	/* list of inode_security_struct */
+		struct rcu_head rcu;	/* for freeing the inode_security_struct */
+	};
 	u32 task_sid;		/* SID of creating task */
 	u32 sid;		/* SID of this object */
 	u16 sclass;		/* security class of this object */