From bce9b042ec73e8662b8119d4ca47e7c78b20d0bf Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 8 Jul 2020 21:28:05 +0200 Subject: x86/traps: Disable interrupts in exc_aligment_check() exc_alignment_check() fails to disable interrupts before returning to the entry code. Fixes: ca4c6a9858c2 ("x86/traps: Make interrupt enable/disable symmetric in C code") Reported-by: syzbot+0889df9502bc0f112b31@syzkaller.appspotmail.com Signed-off-by: Thomas Gleixner Acked-by: Andy Lutomirski Link: https://lkml.kernel.org/r/20200708192934.076519438@linutronix.de --- arch/x86/kernel/traps.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 6ed8cc5fbe8f..4f3a509e5547 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -299,6 +299,8 @@ DEFINE_IDTENTRY_ERRORCODE(exc_alignment_check) do_trap(X86_TRAP_AC, SIGBUS, "alignment check", regs, error_code, BUS_ADRALN, NULL); + + local_irq_disable(); } #ifdef CONFIG_VMAP_STACK -- cgit v1.2.3 From e3beca48a45b5e0e6e6a4e0124276b8248dcc9bb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 9 Jul 2020 11:53:06 +0200 Subject: irqdomain/treewide: Keep firmware node unconditionally allocated Quite some non OF/ACPI users of irqdomains allocate firmware nodes of type IRQCHIP_FWNODE_NAMED or IRQCHIP_FWNODE_NAMED_ID and free them right after creating the irqdomain. The only purpose of these FW nodes is to convey name information. When this was introduced the core code did not store the pointer to the node in the irqdomain. A recent change stored the firmware node pointer in irqdomain for other reasons and missed to notice that the usage sites which do the alloc_fwnode/create_domain/free_fwnode sequence are broken by this. Storing a dangling pointer is dangerous itself, but in case that the domain is destroyed later on this leads to a double free. Remove the freeing of the firmware node after creating the irqdomain from all affected call sites to cure this. Fixes: 711419e504eb ("irqdomain: Add the missing assignment of domain->fwnode for named fwnode") Reported-by: Andy Shevchenko Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Acked-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/873661qakd.fsf@nanos.tec.linutronix.de --- arch/mips/pci/pci-xtalk-bridge.c | 5 +++-- arch/x86/kernel/apic/io_apic.c | 10 +++++----- arch/x86/kernel/apic/msi.c | 18 ++++++++++++------ arch/x86/kernel/apic/vector.c | 1 - arch/x86/platform/uv/uv_irq.c | 3 ++- drivers/iommu/amd/iommu.c | 5 +++-- drivers/iommu/hyperv-iommu.c | 5 ++++- drivers/iommu/intel/irq_remapping.c | 2 +- drivers/mfd/ioc3.c | 5 +++-- drivers/pci/controller/vmd.c | 5 +++-- 10 files changed, 36 insertions(+), 23 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c index 3b2552fb7735..5958217861b8 100644 --- a/arch/mips/pci/pci-xtalk-bridge.c +++ b/arch/mips/pci/pci-xtalk-bridge.c @@ -627,9 +627,10 @@ static int bridge_probe(struct platform_device *pdev) return -ENOMEM; domain = irq_domain_create_hierarchy(parent, 0, 8, fn, &bridge_domain_ops, NULL); - irq_domain_free_fwnode(fn); - if (!domain) + if (!domain) { + irq_domain_free_fwnode(fn); return -ENOMEM; + } pci_set_flags(PCI_PROBE_ONLY); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index ce61e3e7d399..81ffcfbfaef2 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2316,12 +2316,12 @@ static int mp_irqdomain_create(int ioapic) ip->irqdomain = irq_domain_create_linear(fn, hwirqs, cfg->ops, (void *)(long)ioapic); - /* Release fw handle if it was allocated above */ - if (!cfg->dev) - irq_domain_free_fwnode(fn); - - if (!ip->irqdomain) + if (!ip->irqdomain) { + /* Release fw handle if it was allocated above */ + if (!cfg->dev) + irq_domain_free_fwnode(fn); return -ENOMEM; + } ip->irqdomain->parent = parent; diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 5cbaca58af95..c2b2911feeef 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -263,12 +263,13 @@ void __init arch_init_msi_domain(struct irq_domain *parent) msi_default_domain = pci_msi_create_irq_domain(fn, &pci_msi_domain_info, parent); - irq_domain_free_fwnode(fn); } - if (!msi_default_domain) + if (!msi_default_domain) { + irq_domain_free_fwnode(fn); pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n"); - else + } else { msi_default_domain->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK; + } } #ifdef CONFIG_IRQ_REMAP @@ -301,7 +302,8 @@ struct irq_domain *arch_create_remap_msi_irq_domain(struct irq_domain *parent, if (!fn) return NULL; d = pci_msi_create_irq_domain(fn, &pci_msi_ir_domain_info, parent); - irq_domain_free_fwnode(fn); + if (!d) + irq_domain_free_fwnode(fn); return d; } #endif @@ -364,7 +366,8 @@ static struct irq_domain *dmar_get_irq_domain(void) if (fn) { dmar_domain = msi_create_irq_domain(fn, &dmar_msi_domain_info, x86_vector_domain); - irq_domain_free_fwnode(fn); + if (!dmar_domain) + irq_domain_free_fwnode(fn); } out: mutex_unlock(&dmar_lock); @@ -489,7 +492,10 @@ struct irq_domain *hpet_create_irq_domain(int hpet_id) } d = msi_create_irq_domain(fn, domain_info, parent); - irq_domain_free_fwnode(fn); + if (!d) { + irq_domain_free_fwnode(fn); + kfree(domain_info); + } return d; } diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index c48be6e1f676..cc8b16f89dd4 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -709,7 +709,6 @@ int __init arch_early_irq_init(void) x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops, NULL); BUG_ON(x86_vector_domain == NULL); - irq_domain_free_fwnode(fn); irq_set_default_host(x86_vector_domain); arch_init_msi_domain(x86_vector_domain); diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index fc13cbbb2dce..abb6075397f0 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -167,9 +167,10 @@ static struct irq_domain *uv_get_irq_domain(void) goto out; uv_domain = irq_domain_create_tree(fn, &uv_domain_ops, NULL); - irq_domain_free_fwnode(fn); if (uv_domain) uv_domain->parent = x86_vector_domain; + else + irq_domain_free_fwnode(fn); out: mutex_unlock(&uv_lock); diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 74cca1757172..2f22326ee4df 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -3985,9 +3985,10 @@ int amd_iommu_create_irq_domain(struct amd_iommu *iommu) if (!fn) return -ENOMEM; iommu->ir_domain = irq_domain_create_tree(fn, &amd_ir_domain_ops, iommu); - irq_domain_free_fwnode(fn); - if (!iommu->ir_domain) + if (!iommu->ir_domain) { + irq_domain_free_fwnode(fn); return -ENOMEM; + } iommu->ir_domain->parent = arch_get_ir_parent_domain(); iommu->msi_domain = arch_create_remap_msi_irq_domain(iommu->ir_domain, diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c index 3c0c67a99c7b..8919c1c70b68 100644 --- a/drivers/iommu/hyperv-iommu.c +++ b/drivers/iommu/hyperv-iommu.c @@ -155,7 +155,10 @@ static int __init hyperv_prepare_irq_remapping(void) 0, IOAPIC_REMAPPING_ENTRY, fn, &hyperv_ir_domain_ops, NULL); - irq_domain_free_fwnode(fn); + if (!ioapic_ir_domain) { + irq_domain_free_fwnode(fn); + return -ENOMEM; + } /* * Hyper-V doesn't provide irq remapping function for diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 7f8769800815..9564d23d094f 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -563,8 +563,8 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) 0, INTR_REMAP_TABLE_ENTRIES, fn, &intel_ir_domain_ops, iommu); - irq_domain_free_fwnode(fn); if (!iommu->ir_domain) { + irq_domain_free_fwnode(fn); pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id); goto out_free_bitmap; } diff --git a/drivers/mfd/ioc3.c b/drivers/mfd/ioc3.c index 02998d4eb74b..74cee7cb0afc 100644 --- a/drivers/mfd/ioc3.c +++ b/drivers/mfd/ioc3.c @@ -142,10 +142,11 @@ static int ioc3_irq_domain_setup(struct ioc3_priv_data *ipd, int irq) goto err; domain = irq_domain_create_linear(fn, 24, &ioc3_irq_domain_ops, ipd); - if (!domain) + if (!domain) { + irq_domain_free_fwnode(fn); goto err; + } - irq_domain_free_fwnode(fn); ipd->domain = domain; irq_set_chained_handler_and_data(irq, ioc3_irq_handler, domain); diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index e386d4eac407..9a64cf90c291 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -546,9 +546,10 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) vmd->irq_domain = pci_msi_create_irq_domain(fn, &vmd_msi_domain_info, x86_vector_domain); - irq_domain_free_fwnode(fn); - if (!vmd->irq_domain) + if (!vmd->irq_domain) { + irq_domain_free_fwnode(fn); return -ENODEV; + } pci_add_resource(&resources, &vmd->resources[0]); pci_add_resource_offset(&resources, &vmd->resources[1], offset[0]); -- cgit v1.2.3 From baedb87d1b53532f81b4bd0387f83b05d4f7eb9a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 17 Jul 2020 18:00:02 +0200 Subject: genirq/affinity: Handle affinity setting on inactive interrupts correctly Setting interrupt affinity on inactive interrupts is inconsistent when hierarchical irq domains are enabled. The core code should just store the affinity and not call into the irq chip driver for inactive interrupts because the chip drivers may not be in a state to handle such requests. X86 has a hacky workaround for that but all other irq chips have not which causes problems e.g. on GIC V3 ITS. Instead of adding more ugly hacks all over the place, solve the problem in the core code. If the affinity is set on an inactive interrupt then: - Store it in the irq descriptors affinity mask - Update the effective affinity to reflect that so user space has a consistent view - Don't call into the irq chip driver This is the core equivalent of the X86 workaround and works correctly because the affinity setting is established in the irq chip when the interrupt is activated later on. Note, that this is only effective when hierarchical irq domains are enabled by the architecture. Doing it unconditionally would break legacy irq chip implementations. For hierarchial irq domains this works correctly as none of the drivers can have a dependency on affinity setting in inactive state by design. Remove the X86 workaround as it is not longer required. Fixes: 02edee152d6e ("x86/apic/vector: Ignore set_affinity call for inactive interrupts") Reported-by: Ali Saidi Signed-off-by: Thomas Gleixner Tested-by: Ali Saidi Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200529015501.15771-1-alisaidi@amazon.com Link: https://lkml.kernel.org/r/877dv2rv25.fsf@nanos.tec.linutronix.de --- arch/x86/kernel/apic/vector.c | 22 +++++----------------- kernel/irq/manage.c | 37 +++++++++++++++++++++++++++++++++++-- 2 files changed, 40 insertions(+), 19 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index cc8b16f89dd4..7649da2478d8 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -446,12 +446,10 @@ static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd, trace_vector_activate(irqd->irq, apicd->is_managed, apicd->can_reserve, reserve); - /* Nothing to do for fixed assigned vectors */ - if (!apicd->can_reserve && !apicd->is_managed) - return 0; - raw_spin_lock_irqsave(&vector_lock, flags); - if (reserve || irqd_is_managed_and_shutdown(irqd)) + if (!apicd->can_reserve && !apicd->is_managed) + assign_irq_vector_any_locked(irqd); + else if (reserve || irqd_is_managed_and_shutdown(irqd)) vector_assign_managed_shutdown(irqd); else if (apicd->is_managed) ret = activate_managed(irqd); @@ -774,20 +772,10 @@ void lapic_offline(void) static int apic_set_affinity(struct irq_data *irqd, const struct cpumask *dest, bool force) { - struct apic_chip_data *apicd = apic_chip_data(irqd); int err; - /* - * Core code can call here for inactive interrupts. For inactive - * interrupts which use managed or reservation mode there is no - * point in going through the vector assignment right now as the - * activation will assign a vector which fits the destination - * cpumask. Let the core code store the destination mask and be - * done with it. - */ - if (!irqd_is_activated(irqd) && - (apicd->is_managed || apicd->can_reserve)) - return IRQ_SET_MASK_OK; + if (WARN_ON_ONCE(!irqd_is_activated(irqd))) + return -EIO; raw_spin_lock(&vector_lock); cpumask_and(vector_searchmask, dest, cpu_online_mask); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 761911168438..2a9fec53e159 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -195,9 +195,9 @@ void irq_set_thread_affinity(struct irq_desc *desc) set_bit(IRQTF_AFFINITY, &action->thread_flags); } +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK static void irq_validate_effective_affinity(struct irq_data *data) { -#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK const struct cpumask *m = irq_data_get_effective_affinity_mask(data); struct irq_chip *chip = irq_data_get_irq_chip(data); @@ -205,9 +205,19 @@ static void irq_validate_effective_affinity(struct irq_data *data) return; pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n", chip->name, data->irq); -#endif } +static inline void irq_init_effective_affinity(struct irq_data *data, + const struct cpumask *mask) +{ + cpumask_copy(irq_data_get_effective_affinity_mask(data), mask); +} +#else +static inline void irq_validate_effective_affinity(struct irq_data *data) { } +static inline void irq_init_effective_affinity(struct irq_data *data, + const struct cpumask *mask) { } +#endif + int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -304,6 +314,26 @@ static int irq_try_set_affinity(struct irq_data *data, return ret; } +static bool irq_set_affinity_deactivated(struct irq_data *data, + const struct cpumask *mask, bool force) +{ + struct irq_desc *desc = irq_data_to_desc(data); + + /* + * If the interrupt is not yet activated, just store the affinity + * mask and do not call the chip driver at all. On activation the + * driver has to make sure anyway that the interrupt is in a + * useable state so startup works. + */ + if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) || irqd_is_activated(data)) + return false; + + cpumask_copy(desc->irq_common_data.affinity, mask); + irq_init_effective_affinity(data, mask); + irqd_set(data, IRQD_AFFINITY_SET); + return true; +} + int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -314,6 +344,9 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, if (!chip || !chip->irq_set_affinity) return -EINVAL; + if (irq_set_affinity_deactivated(data, mask, force)) + return 0; + if (irq_can_move_pcntxt(data) && !irqd_is_setaffinity_pending(data)) { ret = irq_try_set_affinity(data, mask, force); } else { -- cgit v1.2.3 From cadfad870154e14f745ec845708bc17d166065f2 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Fri, 17 Jul 2020 16:53:55 -0700 Subject: x86/ioperm: Fix io bitmap invalidation on Xen PV tss_invalidate_io_bitmap() wasn't wired up properly through the pvop machinery, so the TSS and Xen's io bitmap would get out of sync whenever disabling a valid io bitmap. Add a new pvop for tss_invalidate_io_bitmap() to fix it. This is XSA-329. Fixes: 22fe5b0439dd ("x86/ioperm: Move TSS bitmap update to exit to user work") Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Juergen Gross Reviewed-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/d53075590e1f91c19f8af705059d3ff99424c020.1595030016.git.luto@kernel.org --- arch/x86/include/asm/io_bitmap.h | 16 ++++++++++++++++ arch/x86/include/asm/paravirt.h | 5 +++++ arch/x86/include/asm/paravirt_types.h | 1 + arch/x86/kernel/paravirt.c | 3 ++- arch/x86/kernel/process.c | 18 ++---------------- arch/x86/xen/enlighten_pv.c | 12 ++++++++++++ 6 files changed, 38 insertions(+), 17 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h index ac1a99ffbd8d..7f080f5c7def 100644 --- a/arch/x86/include/asm/io_bitmap.h +++ b/arch/x86/include/asm/io_bitmap.h @@ -19,12 +19,28 @@ struct task_struct; void io_bitmap_share(struct task_struct *tsk); void io_bitmap_exit(struct task_struct *tsk); +static inline void native_tss_invalidate_io_bitmap(void) +{ + /* + * Invalidate the I/O bitmap by moving io_bitmap_base outside the + * TSS limit so any subsequent I/O access from user space will + * trigger a #GP. + * + * This is correct even when VMEXIT rewrites the TSS limit + * to 0x67 as the only requirement is that the base points + * outside the limit. + */ + this_cpu_write(cpu_tss_rw.x86_tss.io_bitmap_base, + IO_BITMAP_OFFSET_INVALID); +} + void native_tss_update_io_bitmap(void); #ifdef CONFIG_PARAVIRT_XXL #include #else #define tss_update_io_bitmap native_tss_update_io_bitmap +#define tss_invalidate_io_bitmap native_tss_invalidate_io_bitmap #endif #else diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 5ca5d297df75..3d2afecde50c 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -302,6 +302,11 @@ static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g) } #ifdef CONFIG_X86_IOPL_IOPERM +static inline void tss_invalidate_io_bitmap(void) +{ + PVOP_VCALL0(cpu.invalidate_io_bitmap); +} + static inline void tss_update_io_bitmap(void) { PVOP_VCALL0(cpu.update_io_bitmap); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 732f62e04ddb..8dfcb2508e6d 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -141,6 +141,7 @@ struct pv_cpu_ops { void (*load_sp0)(unsigned long sp0); #ifdef CONFIG_X86_IOPL_IOPERM + void (*invalidate_io_bitmap)(void); void (*update_io_bitmap)(void); #endif diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 674a7d66d960..de2138ba38e5 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -324,7 +324,8 @@ struct paravirt_patch_template pv_ops = { .cpu.swapgs = native_swapgs, #ifdef CONFIG_X86_IOPL_IOPERM - .cpu.update_io_bitmap = native_tss_update_io_bitmap, + .cpu.invalidate_io_bitmap = native_tss_invalidate_io_bitmap, + .cpu.update_io_bitmap = native_tss_update_io_bitmap, #endif .cpu.start_context_switch = paravirt_nop, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index f362ce0d5ac0..fe67dbd76e51 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -322,20 +322,6 @@ void arch_setup_new_exec(void) } #ifdef CONFIG_X86_IOPL_IOPERM -static inline void tss_invalidate_io_bitmap(struct tss_struct *tss) -{ - /* - * Invalidate the I/O bitmap by moving io_bitmap_base outside the - * TSS limit so any subsequent I/O access from user space will - * trigger a #GP. - * - * This is correct even when VMEXIT rewrites the TSS limit - * to 0x67 as the only requirement is that the base points - * outside the limit. - */ - tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID; -} - static inline void switch_to_bitmap(unsigned long tifp) { /* @@ -346,7 +332,7 @@ static inline void switch_to_bitmap(unsigned long tifp) * user mode. */ if (tifp & _TIF_IO_BITMAP) - tss_invalidate_io_bitmap(this_cpu_ptr(&cpu_tss_rw)); + tss_invalidate_io_bitmap(); } static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm) @@ -380,7 +366,7 @@ void native_tss_update_io_bitmap(void) u16 *base = &tss->x86_tss.io_bitmap_base; if (!test_thread_flag(TIF_IO_BITMAP)) { - tss_invalidate_io_bitmap(tss); + native_tss_invalidate_io_bitmap(); return; } diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 0d68948c82ad..c46b9f2e732f 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -870,6 +870,17 @@ static void xen_load_sp0(unsigned long sp0) } #ifdef CONFIG_X86_IOPL_IOPERM +static void xen_invalidate_io_bitmap(void) +{ + struct physdev_set_iobitmap iobitmap = { + .bitmap = 0, + .nr_ports = 0, + }; + + native_tss_invalidate_io_bitmap(); + HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap); +} + static void xen_update_io_bitmap(void) { struct physdev_set_iobitmap iobitmap; @@ -1099,6 +1110,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .load_sp0 = xen_load_sp0, #ifdef CONFIG_X86_IOPL_IOPERM + .invalidate_io_bitmap = xen_invalidate_io_bitmap, .update_io_bitmap = xen_update_io_bitmap, #endif .io_delay = xen_io_delay, -- cgit v1.2.3 From 5714ee50bb4375bd586858ad800b1d9772847452 Mon Sep 17 00:00:00 2001 From: Kevin Buettner Date: Sat, 18 Jul 2020 00:20:03 -0700 Subject: copy_xstate_to_kernel: Fix typo which caused GDB regression This fixes a regression encountered while running the gdb.base/corefile.exp test in GDB's test suite. In my testing, the typo prevented the sw_reserved field of struct fxregs_state from being output to the kernel XSAVES area. Thus the correct mask corresponding to XCR0 was not present in the core file for GDB to interrogate, resulting in the following behavior: [kev@f32-1 gdb]$ ./gdb -q testsuite/outputs/gdb.base/corefile/corefile testsuite/outputs/gdb.base/corefile/corefile.core Reading symbols from testsuite/outputs/gdb.base/corefile/corefile... [New LWP 232880] warning: Unexpected size of section `.reg-xstate/232880' in core file. With the typo fixed, the test works again as expected. Signed-off-by: Kevin Buettner Fixes: 9e4636545933 ("copy_xstate_to_kernel(): don't leave parts of destination uninitialized") Cc: Al Viro Cc: Dave Airlie Signed-off-by: Linus Torvalds --- arch/x86/kernel/fpu/xstate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index bda2e5eaca0e..ad3a2b37927d 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1074,7 +1074,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of copy_part(offsetof(struct fxregs_state, st_space), 128, &xsave->i387.st_space, &kbuf, &offset_start, &count); if (header.xfeatures & XFEATURE_MASK_SSE) - copy_part(xstate_offsets[XFEATURE_MASK_SSE], 256, + copy_part(xstate_offsets[XFEATURE_SSE], 256, &xsave->i387.xmm_space, &kbuf, &offset_start, &count); /* * Fill xsave->i387.sw_reserved value for ptrace frame: -- cgit v1.2.3 From de2b41be8fcccb2f5b6c480d35df590476344201 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 21 Jul 2020 11:34:48 +0200 Subject: x86, vmlinux.lds: Page-align end of ..page_aligned sections On x86-32 the idt_table with 256 entries needs only 2048 bytes. It is page-aligned, but the end of the .bss..page_aligned section is not guaranteed to be page-aligned. As a result, objects from other .bss sections may end up on the same 4k page as the idt_table, and will accidentially get mapped read-only during boot, causing unexpected page-faults when the kernel writes to them. This could be worked around by making the objects in the page aligned sections page sized, but that's wrong. Explicit sections which store only page aligned objects have an implicit guarantee that the object is alone in the page in which it is placed. That works for all objects except the last one. That's inconsistent. Enforcing page sized objects for these sections would wreckage memory sanitizers, because the object becomes artificially larger than it should be and out of bound access becomes legit. Align the end of the .bss..page_aligned and .data..page_aligned section on page-size so all objects places in these sections are guaranteed to have their own page. [ tglx: Amended changelog ] Signed-off-by: Joerg Roedel Signed-off-by: Thomas Gleixner Reviewed-by: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20200721093448.10417-1-joro@8bytes.org --- arch/x86/kernel/vmlinux.lds.S | 1 + include/asm-generic/vmlinux.lds.h | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 3bfc8dd8a43d..9a03e5b23135 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -358,6 +358,7 @@ SECTIONS .bss : AT(ADDR(.bss) - LOAD_OFFSET) { __bss_start = .; *(.bss..page_aligned) + . = ALIGN(PAGE_SIZE); *(BSS_MAIN) BSS_DECRYPTED . = ALIGN(PAGE_SIZE); diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index db600ef218d7..052e0f05a984 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -341,7 +341,8 @@ #define PAGE_ALIGNED_DATA(page_align) \ . = ALIGN(page_align); \ - *(.data..page_aligned) + *(.data..page_aligned) \ + . = ALIGN(page_align); #define READ_MOSTLY_DATA(align) \ . = ALIGN(align); \ @@ -737,7 +738,9 @@ . = ALIGN(bss_align); \ .bss : AT(ADDR(.bss) - LOAD_OFFSET) { \ BSS_FIRST_SECTIONS \ + . = ALIGN(PAGE_SIZE); \ *(.bss..page_aligned) \ + . = ALIGN(PAGE_SIZE); \ *(.dynbss) \ *(BSS_MAIN) \ *(COMMON) \ -- cgit v1.2.3 From 372a8eaa05998cd45b3417d0e0ffd3a70978211a Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 17 Jul 2020 09:04:25 -0500 Subject: x86/unwind/orc: Fix ORC for newly forked tasks The ORC unwinder fails to unwind newly forked tasks which haven't yet run on the CPU. It correctly reads the 'ret_from_fork' instruction pointer from the stack, but it incorrectly interprets that value as a call stack address rather than a "signal" one, so the address gets incorrectly decremented in the call to orc_find(), resulting in bad ORC data. Fix it by forcing 'ret_from_fork' frames to be signal frames. Reported-by: Wang ShaoBo Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Tested-by: Wang ShaoBo Link: https://lkml.kernel.org/r/f91a8778dde8aae7f71884b5df2b16d552040441.1594994374.git.jpoimboe@redhat.com --- arch/x86/kernel/unwind_orc.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 7f969b2d240f..ec88bbe08a32 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -440,8 +440,11 @@ bool unwind_next_frame(struct unwind_state *state) /* * Find the orc_entry associated with the text address. * - * Decrement call return addresses by one so they work for sibling - * calls and calls to noreturn functions. + * For a call frame (as opposed to a signal frame), state->ip points to + * the instruction after the call. That instruction's stack layout + * could be different from the call instruction's layout, for example + * if the call was to a noreturn function. So get the ORC data for the + * call instruction itself. */ orc = orc_find(state->signal ? state->ip : state->ip - 1); if (!orc) { @@ -662,6 +665,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, state->sp = task->thread.sp; state->bp = READ_ONCE_NOCHECK(frame->bp); state->ip = READ_ONCE_NOCHECK(frame->ret_addr); + state->signal = (void *)state->ip == ret_from_fork; } if (get_stack_info((unsigned long *)state->sp, state->task, -- cgit v1.2.3 From 039a7a30ec102ec866d382a66f87f6f7654f8140 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 17 Jul 2020 09:04:26 -0500 Subject: x86/stacktrace: Fix reliable check for empty user task stacks If a user task's stack is empty, or if it only has user regs, ORC reports it as a reliable empty stack. But arch_stack_walk_reliable() incorrectly treats it as unreliable. That happens because the only success path for user tasks is inside the loop, which only iterates on non-empty stacks. Generally, a user task must end in a user regs frame, but an empty stack is an exception to that rule. Thanks to commit 71c95825289f ("x86/unwind/orc: Fix error handling in __unwind_start()"), unwind_start() now sets state->error appropriately. So now for both ORC and FP unwinders, unwind_done() and !unwind_error() always means the end of the stack was successfully reached. So the success path for kthreads is no longer needed -- it can also be used for empty user tasks. Reported-by: Wang ShaoBo Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Tested-by: Wang ShaoBo Link: https://lkml.kernel.org/r/f136a4e5f019219cbc4f4da33b30c2f44fa65b84.1594994374.git.jpoimboe@redhat.com --- arch/x86/kernel/stacktrace.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 6ad43fc44556..2fd698e28e4d 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -58,7 +58,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, * or a page fault), which can make frame pointers * unreliable. */ - if (IS_ENABLED(CONFIG_FRAME_POINTER)) return -EINVAL; } @@ -81,10 +80,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, if (unwind_error(&state)) return -EINVAL; - /* Success path for non-user tasks, i.e. kthreads and idle tasks */ - if (!(task->flags & (PF_KTHREAD | PF_IDLE))) - return -EINVAL; - return 0; } -- cgit v1.2.3 From d181d2da0141371bbc360eaea78719203e165e1c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 22 Jul 2020 10:39:54 +0200 Subject: x86/dumpstack: Dump user space code correctly again H.J. reported that post 5.7 a segfault of a user space task does not longer dump the Code bytes when /proc/sys/debug/exception-trace is enabled. It prints 'Code: Bad RIP value.' instead. This was broken by a recent change which made probe_kernel_read() reject non-kernel addresses. Update show_opcodes() so it retrieves user space opcodes via copy_from_user_nmi(). Fixes: 98a23609b103 ("maccess: always use strict semantics for probe_kernel_read") Reported-by: H.J. Lu Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/87h7tz306w.fsf@nanos.tec.linutronix.de --- arch/x86/kernel/dumpstack.c | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index b037cfa7c0c5..7401cc12c3cc 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -71,6 +71,22 @@ static void printk_stack_address(unsigned long address, int reliable, printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address); } +static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src, + unsigned int nbytes) +{ + if (!user_mode(regs)) + return copy_from_kernel_nofault(buf, (u8 *)src, nbytes); + + /* + * Make sure userspace isn't trying to trick us into dumping kernel + * memory by pointing the userspace instruction pointer at it. + */ + if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX)) + return -EINVAL; + + return copy_from_user_nmi(buf, (void __user *)src, nbytes); +} + /* * There are a couple of reasons for the 2/3rd prologue, courtesy of Linus: * @@ -97,17 +113,8 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) #define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE) u8 opcodes[OPCODE_BUFSIZE]; unsigned long prologue = regs->ip - PROLOGUE_SIZE; - bool bad_ip; - - /* - * Make sure userspace isn't trying to trick us into dumping kernel - * memory by pointing the userspace instruction pointer at it. - */ - bad_ip = user_mode(regs) && - __chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX); - if (bad_ip || copy_from_kernel_nofault(opcodes, (u8 *)prologue, - OPCODE_BUFSIZE)) { + if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { printk("%sCode: Bad RIP value.\n", loglvl); } else { printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" -- cgit v1.2.3