From a4fa16353108431e7cfdfc3ecf683bac21b50755 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 3 May 2012 11:36:39 +0300 Subject: KVM: ensure async PF event wakes up vcpu from halt If vcpu executes hlt instruction while async PF is waiting to be delivered vcpu can block and deliver async PF only after another even wakes it up. This happens because kvm_check_async_pf_completion() will remove completion event from vcpu->async_pf.done before entering kvm_vcpu_block() and this will make kvm_arch_vcpu_runnable() return false. The solution is to make vcpu runnable when processing completion. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 91a5e989abc..185a2b823a2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6581,6 +6581,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, kvm_inject_page_fault(vcpu, &fault); } vcpu->arch.apf.halted = false; + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) -- cgit v1.2.3 From 62c49cc976af84cb0ffcb5ec07ee88da1a94e222 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Wed, 2 May 2012 15:04:02 +0300 Subject: KVM: Do not take reference to mm during async #PF It turned to be totally unneeded. The reason the code was introduced is so that KVM can prefault swapped in page, but prefault can fail even if mm is pinned since page table can change anyway. KVM handles this situation correctly though and does not inject spurious page faults. Fixes: "INFO: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected" warning while running LTP inside a KVM guest using the recent -next kernel. Reported-by: Sasha Levin Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/kernel/kvm.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b8ba6e4a27e..e554e5ad2fe 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -79,7 +79,6 @@ struct kvm_task_sleep_node { u32 token; int cpu; bool halted; - struct mm_struct *mm; }; static struct kvm_task_sleep_head { @@ -126,9 +125,7 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); - n.mm = current->active_mm; n.halted = idle || preempt_count() > 1; - atomic_inc(&n.mm->mm_count); init_waitqueue_head(&n.wq); hlist_add_head(&n.link, &b->list); spin_unlock(&b->lock); @@ -161,9 +158,6 @@ EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait); static void apf_task_wake_one(struct kvm_task_sleep_node *n) { hlist_del_init(&n->link); - if (!n->mm) - return; - mmdrop(n->mm); if (n->halted) smp_send_reschedule(n->cpu); else if (waitqueue_active(&n->wq)) @@ -207,7 +201,7 @@ again: * async PF was not yet handled. * Add dummy entry for the token. */ - n = kmalloc(sizeof(*n), GFP_ATOMIC); + n = kzalloc(sizeof(*n), GFP_ATOMIC); if (!n) { /* * Allocation failed! Busy wait while other cpu @@ -219,7 +213,6 @@ again: } n->token = token; n->cpu = smp_processor_id(); - n->mm = NULL; init_waitqueue_head(&n->wq); hlist_add_head(&n->link, &b->list); } else -- cgit v1.2.3 From febb72a6e4cc6c8cffcc1ea649a3fb364f1ea432 Mon Sep 17 00:00:00 2001 From: Larry Finger Date: Sun, 6 May 2012 19:40:03 -0500 Subject: IA32 emulation: Fix build problem for modular ia32 a.out support Commit ce7e5d2d19bc ("x86: fix broken TASK_SIZE for ia32_aout") breaks kernel builds when "CONFIG_IA32_AOUT=m" with ERROR: "set_personality_ia32" [arch/x86/ia32/ia32_aout.ko] undefined! make[1]: *** [__modpost] Error 1 The entry point needs to be exported. Signed-off-by: Larry Finger Acked-by: Al Viro Signed-off-by: Linus Torvalds --- arch/x86/kernel/process_64.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 733ca39f367..43d8b48b23e 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -423,6 +423,7 @@ void set_personality_ia32(bool x32) current_thread_info()->status |= TS_COMPAT; } } +EXPORT_SYMBOL_GPL(set_personality_ia32); unsigned long get_wchan(struct task_struct *p) { -- cgit v1.2.3 From 558daa289a402dbcce0c065c6ff3cc2e00ffeac8 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Wed, 2 May 2012 15:04:51 -0400 Subject: xen/apic: Return the APIC ID (and version) for CPU 0. On x86_64 on AMD machines where the first APIC_ID is not zero, we get: ACPI: LAPIC (acpi_id[0x01] lapic_id[0x10] enabled) BIOS bug: APIC version is 0 for CPU 1/0x10, fixing up to 0x10 BIOS bug: APIC version mismatch, boot CPU: 0, CPU 1: version 10 which means that when the ACPI processor driver loads and tries to parse the _Pxx states it fails to do as, as it ends up calling acpi_get_cpuid which does this: for_each_possible_cpu(i) { if (cpu_physical_id(i) == apic_id) return i; } And the bootup CPU, has not been found so it fails and returns -1 for the first CPU - which then subsequently in the loop that "acpi_processor_get_info" does results in returning an error, which means that "acpi_processor_add" failing and per_cpu(processor) is never set (and is NULL). That means that when xen-acpi-processor tries to load (much much later on) and parse the P-states it gets -ENODEV from acpi_processor_register_performance() (which tries to read the per_cpu(processor)) and fails to parse the data. Reported-by-and-Tested-by: Stefan Bader Suggested-by: Boris Ostrovsky [v2: Bit-shift APIC ID by 24 bits] Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/xen/enlighten.c | 35 ++++++++++++++++++++++++++++++++++- 1 file changed, 34 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index a8f8844b8d3..4f437dedbdf 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -809,9 +809,40 @@ static void xen_io_delay(void) } #ifdef CONFIG_X86_LOCAL_APIC +static unsigned long xen_set_apic_id(unsigned int x) +{ + WARN_ON(1); + return x; +} +static unsigned int xen_get_apic_id(unsigned long x) +{ + return ((x)>>24) & 0xFFu; +} static u32 xen_apic_read(u32 reg) { - return 0; + struct xen_platform_op op = { + .cmd = XENPF_get_cpuinfo, + .interface_version = XENPF_INTERFACE_VERSION, + .u.pcpu_info.xen_cpuid = 0, + }; + int ret = 0; + + /* Shouldn't need this as APIC is turned off for PV, and we only + * get called on the bootup processor. But just in case. */ + if (!xen_initial_domain() || smp_processor_id()) + return 0; + + if (reg == APIC_LVR) + return 0x10; + + if (reg != APIC_ID) + return 0; + + ret = HYPERVISOR_dom0_op(&op); + if (ret) + return 0; + + return op.u.pcpu_info.apic_id << 24; } static void xen_apic_write(u32 reg, u32 val) @@ -849,6 +880,8 @@ static void set_xen_basic_apic_ops(void) apic->icr_write = xen_apic_icr_write; apic->wait_icr_idle = xen_apic_wait_icr_idle; apic->safe_wait_icr_idle = xen_safe_apic_wait_icr_idle; + apic->set_apic_id = xen_set_apic_id; + apic->get_apic_id = xen_get_apic_id; } #endif -- cgit v1.2.3 From b7e5ffe5d83fa40d702976d77452004abbe35791 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Thu, 3 May 2012 16:14:14 -0400 Subject: xen/pte: Fix crashes when trying to see non-existent PGD/PMD/PUD/PTEs If I try to do "cat /sys/kernel/debug/kernel_page_tables" I end up with: BUG: unable to handle kernel paging request at ffffc7fffffff000 IP: [] ptdump_show+0x221/0x480 PGD 0 Oops: 0000 [#1] SMP CPU 0 .. snip.. RAX: 0000000000000000 RBX: ffffc00000000fff RCX: 0000000000000000 RDX: 0000800000000000 RSI: 0000000000000000 RDI: ffffc7fffffff000 which is due to the fact we are trying to access a PFN that is not accessible to us. The reason (at least in this case) was that PGD[256] is set to __HYPERVISOR_VIRT_START which was setup (by the hypervisor) to point to a read-only linear map of the MFN->PFN array. During our parsing we would get the MFN (a valid one), try to look it up in the MFN->PFN tree and find it invalid and return ~0 as PFN. Then pte_mfn_to_pfn would happilly feed that in, attach the flags and return it back to the caller. 'ptdump_show' bitshifts it and gets and invalid value that it tries to dereference. Instead of doing all of that, we detect the ~0 case and just return !_PAGE_PRESENT. This bug has been in existence .. at least until 2.6.37 (yikes!) CC: stable@kernel.org Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/xen/mmu.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index b8e279479a6..69f5857660a 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -353,8 +353,13 @@ static pteval_t pte_mfn_to_pfn(pteval_t val) { if (val & _PAGE_PRESENT) { unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; + unsigned long pfn = mfn_to_pfn(mfn); + pteval_t flags = val & PTE_FLAGS_MASK; - val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags; + if (unlikely(pfn == ~0)) + val = flags & ~_PAGE_PRESENT; + else + val = ((pteval_t)pfn << PAGE_SHIFT) | flags; } return val; -- cgit v1.2.3 From 76a8df7b49168509df02461f83fab117a4a86e08 Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Fri, 4 May 2012 14:29:46 +0100 Subject: xen/pci: don't use PCI BIOS service for configuration space accesses The accessing PCI configuration space with the PCI BIOS32 service does not work in PV guests. On systems without MMCONFIG or where the BIOS hasn't marked the MMCONFIG region as reserved in the e820 map, the BIOS service is probed (even though direct access is preferred) and this hangs. CC: stable@kernel.org Acked-by: Jan Beulich Signed-off-by: David Vrabel [v1: Fixed compile error when CONFIG_PCI is not set] Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/xen/enlighten.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 4f437dedbdf..95dccce8e97 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -63,6 +63,7 @@ #include #include #include +#include #ifdef CONFIG_ACPI #include @@ -1398,8 +1399,10 @@ asmlinkage void __init xen_start_kernel(void) /* Make sure ACS will be enabled */ pci_request_acs(); } - - +#ifdef CONFIG_PCI + /* PCI BIOS service won't work from a PV guest. */ + pci_probe &= ~PCI_PROBE_BIOS; +#endif xen_raw_console_write("about to get started...\n"); xen_setup_runstate_info(0); -- cgit v1.2.3 From d5e28005a1d2e67833852f4c9ea8ec206ea3ff85 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 27 Apr 2012 10:54:35 -0700 Subject: percpu, x86: don't use PMD_SIZE as embedded atom_size on 32bit With the embed percpu first chunk allocator, x86 uses either PAGE_SIZE or PMD_SIZE for atom_size. PMD_SIZE is used when CPU supports PSE so that percpu areas are aligned to PMD mappings and possibly allow using PMD mappings in vmalloc areas in the future. Using larger atom_size doesn't waste actual memory; however, it does require larger vmalloc space allocation later on for !first chunks. With reasonably sized vmalloc area, PMD_SIZE shouldn't be a problem but x86_32 at this point is anything but reasonable in terms of address space and using larger atom_size reportedly leads to frequent percpu allocation failures on certain setups. As there is no reason to not use PMD_SIZE on x86_64 as vmalloc space is aplenty and most x86_64 configurations support PSE, fix the issue by always using PMD_SIZE on x86_64 and PAGE_SIZE on x86_32. v2: drop cpu_has_pse test and make x86_64 always use PMD_SIZE and x86_32 PAGE_SIZE as suggested by hpa. Signed-off-by: Tejun Heo Reported-by: Yanmin Zhang Reported-by: ShuoX Liu Acked-by: H. Peter Anvin LKML-Reference: <4F97BA98.6010001@intel.com> Cc: stable@vger.kernel.org --- arch/x86/kernel/setup_percpu.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 71f4727da37..5a98aa27218 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -185,10 +185,22 @@ void __init setup_per_cpu_areas(void) #endif rc = -EINVAL; if (pcpu_chosen_fc != PCPU_FC_PAGE) { - const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE; const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE; + size_t atom_size; + /* + * On 64bit, use PMD_SIZE for atom_size so that embedded + * percpu areas are aligned to PMD. This, in the future, + * can also allow using PMD mappings in vmalloc area. Use + * PAGE_SIZE on 32bit as vmalloc space is highly contended + * and large vmalloc area allocs can easily fail. + */ +#ifdef CONFIG_X86_64 + atom_size = PMD_SIZE; +#else + atom_size = PAGE_SIZE; +#endif rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE, dyn_size, atom_size, pcpu_cpu_distance, -- cgit v1.2.3