Changes representative of linux-4.18.0-240.8.1.el8_3.tar.xz

Documentation/filesystems/porting

@@ -607,3 +607,8 @@ in your dentry operations instead.
 	->clone_file_range() and ->dedupe_file_range have been replaced with
 	->remap_file_range().  See Documentation/filesystems/vfs.txt for more
 	information.
+--
+[mandatory]
+	DCACHE_RCUACCESS is gone; having an RCU delay on dentry freeing is the
+	default.  DCACHE_NORCU opts out, and only d_alloc_pseudo() has any
+	business doing so.

Makefile.rhelver

@@ -12,7 +12,7 @@ RHEL_MINOR = 3
 #
 # Use this spot to avoid future merge conflicts.
 # Do not trim this comment.
-RHEL_RELEASE = 240.1.1
+RHEL_RELEASE = 240.8.1
 
 #
 # Early y+1 numbering

arch/arm64/kernel/paravirt.c

@@ -57,16 +57,19 @@ static u64 pv_steal_clock(int cpu)
 	struct pv_time_stolen_time_region *reg;
 
 	reg = per_cpu_ptr(&stolen_time_region, cpu);
-	if (!reg->kaddr) {
-		pr_warn_once("stolen time enabled but not configured for cpu %d\n",
-			     cpu);
+
+	/*
+	 * paravirt_steal_clock() may be called before the CPU
+	 * online notification callback runs. Until the callback
+	 * has run we just return zero.
+	 */
+	if (!reg->kaddr)
 		return 0;
-	}
 
 	return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time));
 }
 
-static int stolen_time_dying_cpu(unsigned int cpu)
+static int stolen_time_cpu_down_prepare(unsigned int cpu)
 {
 	struct pv_time_stolen_time_region *reg;
 
@@ -80,7 +83,7 @@ static int stolen_time_dying_cpu(unsigned int cpu)
 	return 0;
 }
 
-static int init_stolen_time_cpu(unsigned int cpu)
+static int stolen_time_cpu_online(unsigned int cpu)
 {
 	struct pv_time_stolen_time_region *reg;
 	struct arm_smccc_res res;
@@ -110,19 +113,20 @@ static int init_stolen_time_cpu(unsigned int cpu)
 	return 0;
 }
 
-static int pv_time_init_stolen_time(void)
+static int __init pv_time_init_stolen_time(void)
 {
 	int ret;
 
-	ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING,
-				"hypervisor/arm/pvtime:starting",
-				init_stolen_time_cpu, stolen_time_dying_cpu);
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				"hypervisor/arm/pvtime:online",
+				stolen_time_cpu_online,
+				stolen_time_cpu_down_prepare);
 	if (ret < 0)
 		return ret;
 	return 0;
 }
 
-static bool has_pv_steal_clock(void)
+static bool __init has_pv_steal_clock(void)
 {
 	struct arm_smccc_res res;
 

arch/powerpc/kernel/traps.c

@@ -762,7 +762,7 @@ static void p9_hmi_special_emu(struct pt_regs *regs)
 {
 	unsigned int ra, rb, t, i, sel, instr, rc;
 	const void __user *addr;
-	u8 vbuf[16], *vdst;
+	u8 vbuf[16] __aligned(16), *vdst;
 	unsigned long ea, msr, msr_mask;
 	bool swap;
 

arch/s390/include/asm/pgtable.h

@@ -1271,25 +1271,43 @@ static inline pgd_t *pgd_offset_raw(pgd_t *pgd, unsigned long address)
 #define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address)
 #define pgd_offset_k(address) pgd_offset(&init_mm, address)
 
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long address)
 {
-	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
-		return (p4d_t *) pgd_deref(*pgd) + p4d_index(address);
-	return (p4d_t *) pgd;
+	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
+		return (p4d_t *) pgd_deref(pgd) + p4d_index(address);
+	return (p4d_t *) pgdp;
 }
+#define p4d_offset_lockless p4d_offset_lockless
 
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long address)
 {
-	if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
-		return (pud_t *) p4d_deref(*p4d) + pud_index(address);
-	return (pud_t *) p4d;
+	return p4d_offset_lockless(pgdp, *pgdp, address);
 }
 
-static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
+static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long address)
 {
-	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
-		return (pmd_t *) pud_deref(*pud) + pmd_index(address);
-	return (pmd_t *) pud;
+	if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
+		return (pud_t *) p4d_deref(p4d) + pud_index(address);
+	return (pud_t *) p4dp;
+}
+#define pud_offset_lockless pud_offset_lockless
+
+static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long address)
+{
+	return pud_offset_lockless(p4dp, *p4dp, address);
+}
+
+static inline pmd_t *pmd_offset_lockless(pud_t *pudp, pud_t pud, unsigned long address)
+{
+	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
+		return (pmd_t *) pud_deref(pud) + pmd_index(address);
+	return (pmd_t *) pudp;
+}
+#define pmd_offset_lockless pmd_offset_lockless
+
+static inline pmd_t *pmd_offset(pud_t *pudp, unsigned long address)
+{
+	return pmd_offset_lockless(pudp, *pudp, address);
 }
 
 static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address)

arch/x86/kvm/svm/svm.c

@@ -3402,14 +3402,6 @@ static fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	 */
 	x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
 
-	/*
-	 * Tell context tracking that this CPU is about to enter guest
-	 * mode. This has to be after x86_spec_ctrl_set_guest() because
-	 * that can take locks (lockdep needs RCU) and calls into world and
-	 * some more.
-	 */
-	guest_enter_irqoff();
-
 	__svm_vcpu_run(svm->vmcb_pa, (unsigned long *)&svm->vcpu.arch.regs);
 
 #ifdef CONFIG_X86_64
@@ -3420,14 +3412,6 @@ static fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	loadsegment(gs, svm->host.gs);
 #endif
 #endif
-	/*
-	 * Tell context tracking that this CPU is back.
-	 *
-	 * This needs to be done before the below as native_read_msr()
-	 * contains a tracepoint and x86_spec_ctrl_restore_host() calls
-	 * into world and some more.
-	 */
-	guest_exit_irqoff();
 
 	/*
 	 * We do not use IBRS in the kernel. If this vCPU has used the

arch/x86/kvm/vmx/vmx.c

@@ -6711,11 +6711,6 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 */
 	x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
 
-	/*
-	 * Tell context tracking that this CPU is about to enter guest mode.
-	 */
-	guest_enter_irqoff();
-
 	/* L1D Flush includes CPU buffer clear to mitigate MDS */
 	if (static_branch_unlikely(&vmx_l1d_should_flush))
 		vmx_l1d_flush(vcpu);
@@ -6730,11 +6725,6 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.cr2 = read_cr2();
 
-	/*
-	 * Tell context tracking that this CPU is back.
-	 */
-	guest_exit_irqoff();
-
 	/*
 	 * We do not use IBRS in the kernel. If this vCPU has used the
 	 * SPEC_CTRL MSR it may have left it on; save the value and

arch/x86/kvm/x86.c

@@ -8433,6 +8433,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	}
 
 	trace_kvm_entry(vcpu->vcpu_id);
+	guest_enter_irqoff();
 
 	fpregs_assert_state_consistent();
 	if (test_thread_flag(TIF_NEED_FPU_LOAD))
@@ -8494,6 +8495,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	local_irq_disable();
 	kvm_after_interrupt(vcpu);
 
+	guest_exit_irqoff();
 	if (lapic_in_kernel(vcpu)) {
 		s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta;
 		if (delta != S64_MIN) {

block/blk-settings.c

@@ -205,15 +205,13 @@ EXPORT_SYMBOL(blk_queue_max_hw_sectors);
  *
  * Description:
  *    If a driver doesn't want IOs to cross a given chunk size, it can set
- *    this limit and prevent merging across chunks. Note that the chunk size
- *    must currently be a power-of-2 in sectors. Also note that the block
- *    layer must accept a page worth of data at any offset. So if the
- *    crossing of chunks is a hard limitation in the driver, it must still be
- *    prepared to split single page bios.
+ *    this limit and prevent merging across chunks. Note that the block layer
+ *    must accept a page worth of data at any offset. So if the crossing of
+ *    chunks is a hard limitation in the driver, it must still be prepared
+ *    to split single page bios.
  **/
 void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors)
 {
-	BUG_ON(!is_power_of_2(chunk_sectors));
 	q->limits.chunk_sectors = chunk_sectors;
 }
 EXPORT_SYMBOL(blk_queue_chunk_sectors);
@@ -546,6 +544,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 	t->io_min = max(t->io_min, b->io_min);
 	t->io_opt = lcm_not_zero(t->io_opt, b->io_opt);
+	t->chunk_sectors = lcm_not_zero(t->chunk_sectors, b->chunk_sectors);
 
 	t->cluster &= b->cluster;
 
@@ -570,6 +569,13 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		ret = -1;
 	}
 
+	/* chunk_sectors a multiple of the physical block size? */
+	if ((t->chunk_sectors << 9) & (t->physical_block_size - 1)) {
+		t->chunk_sectors = 0;
+		t->misaligned = 1;
+		ret = -1;
+	}
+
 	t->raid_partial_stripes_expensive =
 		max(t->raid_partial_stripes_expensive,
 		    b->raid_partial_stripes_expensive);
@@ -608,10 +614,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 			t->discard_granularity;
 	}
 
-	if (b->chunk_sectors)
-		t->chunk_sectors = min_not_zero(t->chunk_sectors,
-						b->chunk_sectors);
-
 	return ret;
 }
 EXPORT_SYMBOL(blk_stack_limits);

crypto/testmgr.c

@@ -2782,6 +2782,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 #endif
 		.alg = "cts(cbc(aes))",
 		.test = alg_test_skcipher,
+		.fips_allowed = 1,
 		.suite = {
 			.cipher = __VECS(cts_mode_tv_template)
 		}

drivers/char/random.c

@@ -1265,6 +1265,7 @@ void add_interrupt_randomness(int irq, int irq_flags)
 
 	fast_mix(fast_pool);
 	add_interrupt_bench(cycles);
+	this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]);
 
 	if (unlikely(crng_init == 0)) {
 		if ((fast_pool->count >= 64) &&

drivers/hv/vmbus_drv.c

@@ -2232,7 +2232,10 @@ static int vmbus_bus_suspend(struct device *dev)
 	if (atomic_read(&vmbus_connection.nr_chan_close_on_suspend) > 0)
 		wait_for_completion(&vmbus_connection.ready_for_suspend_event);
 
-	WARN_ON(atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) != 0);
+	if (atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) != 0) {
+		pr_err("Can not suspend due to a previous failed resuming\n");
+		return -EBUSY;
+	}
 
 	mutex_lock(&vmbus_connection.channel_mutex);
 
@@ -2305,7 +2308,9 @@ static int vmbus_bus_resume(struct device *dev)
 
 	vmbus_request_offers();
 
-	wait_for_completion(&vmbus_connection.ready_for_resume_event);
+	if (wait_for_completion_timeout(
+		&vmbus_connection.ready_for_resume_event, 10 * HZ) == 0)
+		pr_err("Some vmbus device is missing after suspending?\n");
 
 	/* Reset the event for the next suspend. */
 	reinit_completion(&vmbus_connection.ready_for_suspend_event);

drivers/iommu/amd_iommu_init.c

@@ -1124,25 +1124,6 @@ static int __init add_early_maps(void)
 	return 0;
 }
 
-/*
- * Reads the device exclusion range from ACPI and initializes the IOMMU with
- * it
- */
-static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m)
-{
-	if (!(m->flags & IVMD_FLAG_EXCL_RANGE))
-		return;
-
-	/*
-	 * Treat per-device exclusion ranges as r/w unity-mapped regions
-	 * since some buggy BIOSes might lead to the overwritten exclusion
-	 * range (exclusion_start and exclusion_length members). This
-	 * happens when there are multiple exclusion ranges (IVMD entries)
-	 * defined in ACPI table.
-	 */
-	m->flags = (IVMD_FLAG_IW | IVMD_FLAG_IR | IVMD_FLAG_UNITY_MAP);
-}
-
 /*
  * Takes a pointer to an AMD IOMMU entry in the ACPI table and
  * initializes the hardware and our data structures with it.
@@ -2077,30 +2058,6 @@ static void __init free_unity_maps(void)
 	}
 }
 
-/* called when we find an exclusion range definition in ACPI */
-static int __init init_exclusion_range(struct ivmd_header *m)
-{
-	int i;
-
-	switch (m->type) {
-	case ACPI_IVMD_TYPE:
-		set_device_exclusion_range(m->devid, m);
-		break;
-	case ACPI_IVMD_TYPE_ALL:
-		for (i = 0; i <= amd_iommu_last_bdf; ++i)
-			set_device_exclusion_range(i, m);
-		break;
-	case ACPI_IVMD_TYPE_RANGE:
-		for (i = m->devid; i <= m->aux; ++i)
-			set_device_exclusion_range(i, m);
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-}
-
 /* called for unity map ACPI definition */
 static int __init init_unity_map_range(struct ivmd_header *m)
 {
@@ -2111,9 +2068,6 @@ static int __init init_unity_map_range(struct ivmd_header *m)
 	if (e == NULL)
 		return -ENOMEM;
 
-	if (m->flags & IVMD_FLAG_EXCL_RANGE)
-		init_exclusion_range(m);
-
 	switch (m->type) {
 	default:
 		kfree(e);
@@ -2137,6 +2091,16 @@ static int __init init_unity_map_range(struct ivmd_header *m)
 	e->address_end = e->address_start + PAGE_ALIGN(m->range_length);
 	e->prot = m->flags >> 1;
 
+	/*
+	 * Treat per-device exclusion ranges as r/w unity-mapped regions
+	 * since some buggy BIOSes might lead to the overwritten exclusion
+	 * range (exclusion_start and exclusion_length members). This
+	 * happens when there are multiple exclusion ranges (IVMD entries)
+	 * defined in ACPI table.
+	 */
+	if (m->flags & IVMD_FLAG_EXCL_RANGE)
+		e->prot = (IVMD_FLAG_IW | IVMD_FLAG_IR) >> 1;
+
 	DUMP_printk("%s devid_start: %02x:%02x.%x devid_end: %02x:%02x.%x"
 		    " range_start: %016llx range_end: %016llx flags: %x\n", s,
 		    PCI_BUS_NUM(e->devid_start), PCI_SLOT(e->devid_start),