diff options
| author | Stephen Rothwell <sfr@canb.auug.org.au> | 2010-04-27 10:35:37 +1000 |
|---|---|---|
| committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2010-04-27 10:35:37 +1000 |
| commit | b20d462a62dc9240bc7e1e020c77848bd13047c6 (patch) | |
| tree | e213d10c123b2972418d39ca0c523e5f92ef8a22 | |
| parent | 30fdcc97d59af43425e036e4b026ded2694f32be (diff) | |
| parent | 2ae7122934cbce8f30e83673df14333f3daf956e (diff) | |
Merge remote branch 'kvm/linux-next'
222 files changed, 18447 insertions, 9173 deletions
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt index 2f9115c0ae62..61c291cddf18 100644 --- a/Documentation/kprobes.txt +++ b/Documentation/kprobes.txt @@ -165,8 +165,8 @@ the user entry_handler invocation is also skipped. 1.4 How Does Jump Optimization Work? -If you configured your kernel with CONFIG_OPTPROBES=y (currently -this option is supported on x86/x86-64, non-preemptive kernel) and +If your kernel is built with CONFIG_OPTPROBES=y (currently this flag +is automatically set 'y' on x86/x86-64, non-preemptive kernel) and the "debug.kprobes_optimization" kernel parameter is set to 1 (see sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump instruction instead of a breakpoint instruction at each probepoint. @@ -271,8 +271,6 @@ tweak the kernel's execution path, you need to suppress optimization, using one of the following techniques: - Specify an empty function for the kprobe's post_handler or break_handler. or -- Config CONFIG_OPTPROBES=n. - or - Execute 'sysctl -w debug.kprobes_optimization=n' 2. Architectures Supported @@ -307,10 +305,6 @@ it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO), so you can use "objdump -d -l vmlinux" to see the source-to-object code mapping. -If you want to reduce probing overhead, set "Kprobes jump optimization -support" (CONFIG_OPTPROBES) to "y". You can find this option under the -"Kprobes" line. - 4. API Reference The Kprobes API includes a "register" function and an "unregister" diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt index c6416a398163..baa8fde8bd16 100644 --- a/Documentation/kvm/api.txt +++ b/Documentation/kvm/api.txt @@ -656,6 +656,7 @@ struct kvm_clock_data { 4.29 KVM_GET_VCPU_EVENTS Capability: KVM_CAP_VCPU_EVENTS +Extended by: KVM_CAP_INTR_SHADOW Architectures: x86 Type: vm ioctl Parameters: struct kvm_vcpu_event (out) @@ -676,7 +677,7 @@ struct kvm_vcpu_events { __u8 injected; __u8 nr; __u8 soft; - __u8 pad; + __u8 shadow; } interrupt; struct { __u8 injected; @@ -688,9 +689,13 @@ struct kvm_vcpu_events { __u32 flags; }; +KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that +interrupt.shadow contains a valid state. Otherwise, this field is undefined. + 4.30 KVM_SET_VCPU_EVENTS Capability: KVM_CAP_VCPU_EVENTS +Extended by: KVM_CAP_INTR_SHADOW Architectures: x86 Type: vm ioctl Parameters: struct kvm_vcpu_event (in) @@ -709,6 +714,139 @@ current in-kernel state. The bits are: KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector +If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in +the flags field to signal that interrupt.shadow contains a valid state and +shall be written into the VCPU. + +4.32 KVM_GET_DEBUGREGS + +Capability: KVM_CAP_DEBUGREGS +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_debugregs (out) +Returns: 0 on success, -1 on error + +Reads debug registers from the vcpu. + +struct kvm_debugregs { + __u64 db[4]; + __u64 dr6; + __u64 dr7; + __u64 flags; + __u64 reserved[9]; +}; + +4.33 KVM_SET_DEBUGREGS + +Capability: KVM_CAP_DEBUGREGS +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_debugregs (in) +Returns: 0 on success, -1 on error + +Writes debug registers into the vcpu. + +See KVM_GET_DEBUGREGS for the data structure. The flags field is unused +yet and must be cleared on entry. + +4.34 KVM_SET_USER_MEMORY_REGION + +Capability: KVM_CAP_USER_MEM +Architectures: all +Type: vm ioctl +Parameters: struct kvm_userspace_memory_region (in) +Returns: 0 on success, -1 on error + +struct kvm_userspace_memory_region { + __u32 slot; + __u32 flags; + __u64 guest_phys_addr; + __u64 memory_size; /* bytes */ + __u64 userspace_addr; /* start of the userspace allocated memory */ +}; + +/* for kvm_memory_region::flags */ +#define KVM_MEM_LOG_DIRTY_PAGES 1UL + +This ioctl allows the user to create or modify a guest physical memory +slot. When changing an existing slot, it may be moved in the guest +physical memory space, or its flags may be modified. It may not be +resized. Slots may not overlap in guest physical address space. + +Memory for the region is taken starting at the address denoted by the +field userspace_addr, which must point at user addressable memory for +the entire memory slot size. Any object may back this memory, including +anonymous memory, ordinary files, and hugetlbfs. + +It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr +be identical. This allows large pages in the guest to be backed by large +pages in the host. + +The flags field supports just one flag, KVM_MEM_LOG_DIRTY_PAGES, which +instructs kvm to keep track of writes to memory within the slot. See +the KVM_GET_DIRTY_LOG ioctl. + +When the KVM_CAP_SYNC_MMU capability, changes in the backing of the memory +region are automatically reflected into the guest. For example, an mmap() +that affects the region will be made visible immediately. Another example +is madvise(MADV_DROP). + +It is recommended to use this API instead of the KVM_SET_MEMORY_REGION ioctl. +The KVM_SET_MEMORY_REGION does not allow fine grained control over memory +allocation and is deprecated. + +4.35 KVM_SET_TSS_ADDR + +Capability: KVM_CAP_SET_TSS_ADDR +Architectures: x86 +Type: vm ioctl +Parameters: unsigned long tss_address (in) +Returns: 0 on success, -1 on error + +This ioctl defines the physical address of a three-page region in the guest +physical address space. The region must be within the first 4GB of the +guest physical address space and must not conflict with any memory slot +or any mmio address. The guest may malfunction if it accesses this memory +region. + +This ioctl is required on Intel-based hosts. This is needed on Intel hardware +because of a quirk in the virtualization implementation (see the internals +documentation when it pops into existence). + +4.36 KVM_ENABLE_CAP + +Capability: KVM_CAP_ENABLE_CAP +Architectures: ppc +Type: vcpu ioctl +Parameters: struct kvm_enable_cap (in) +Returns: 0 on success; -1 on error + ++Not all extensions are enabled by default. Using this ioctl the application +can enable an extension, making it available to the guest. + +On systems that do not support this ioctl, it always fails. On systems that +do support it, it only works for extensions that are supported for enablement. + +To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should +be used. + +struct kvm_enable_cap { + /* in */ + __u32 cap; + +The capability that is supposed to get enabled. + + __u32 flags; + +A bitfield indicating future enhancements. Has to be 0 for now. + + __u64 args[4]; + +Arguments for enabling a feature. If a feature needs initial values to +function properly, this is the place to put them. + + __u8 pad[64]; +}; 5. The kvm_run structure @@ -820,6 +958,13 @@ executed a memory-mapped I/O instruction which could not be satisfied by kvm. The 'data' member contains the written data if 'is_write' is true, and should be filled by application code otherwise. +NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO and KVM_EXIT_OSI, the corresponding +operations are complete (and guest state is consistent) only after userspace +has re-entered the kernel with KVM_RUN. The kernel side will first finish +incomplete operations and then check for pending signals. Userspace +can re-enter the guest with an unmasked signal pending to complete +pending operations. + /* KVM_EXIT_HYPERCALL */ struct { __u64 nr; @@ -829,7 +974,9 @@ true, and should be filled by application code otherwise. __u32 pad; } hypercall; -Unused. +Unused. This was once used for 'hypercall to userspace'. To implement +such functionality, use KVM_EXIT_IO (x86) or KVM_EXIT_MMIO (all except s390). +Note KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO. /* KVM_EXIT_TPR_ACCESS */ struct { @@ -870,6 +1017,19 @@ s390 specific. powerpc specific. + /* KVM_EXIT_OSI */ + struct { + __u64 gprs[32]; + } osi; + +MOL uses a special hypercall interface it calls 'OSI'. To enable it, we catch +hypercalls and exit with this exit struct that contains all the guest gprs. + +If exit_reason is KVM_EXIT_OSI, then the vcpu has triggered such a hypercall. +Userspace can now handle the hypercall and when it's done modify the gprs as +necessary. Upon guest entry all guest GPRs will then be replaced by the values +in this struct. + /* Fix the size of the union. */ char padding[256]; }; diff --git a/Documentation/kvm/mmu.txt b/Documentation/kvm/mmu.txt new file mode 100644 index 000000000000..da046711362d --- /dev/null +++ b/Documentation/kvm/mmu.txt @@ -0,0 +1,302 @@ +The x86 kvm shadow mmu +====================== + +The mmu (in arch/x86/kvm, files mmu.[ch] and paging_tmpl.h) is responsible +for presenting a standard x86 mmu to the guest, while translating guest +physical addresses to host physical addresses. + +The mmu code attempts to satisfy the following requirements: + +- correctness: the guest should not be able to determine that it is running + on an emulated mmu except for timing (we attempt to comply + with the specification, not emulate the characteristics of + a particular implementation such as tlb size) +- security: the guest must not be able to touch host memory not assigned + to it +- performance: minimize the performance penalty imposed by the mmu +- scaling: need to scale to large memory and large vcpu guests +- hardware: support the full range of x86 virtualization hardware +- integration: Linux memory management code must be in control of guest memory + so that swapping, page migration, page merging, transparent + hugepages, and similar features work without change +- dirty tracking: report writes to guest memory to enable live migration + and framebuffer-based displays +- footprint: keep the amount of pinned kernel memory low (most memory + should be shrinkable) +- reliablity: avoid multipage or GFP_ATOMIC allocations + +Acronyms +======== + +pfn host page frame number +hpa host physical address +hva host virtual address +gfn guest frame number +gpa guest physical address +gva guest virtual address +ngpa nested guest physical address +ngva nested guest virtual address +pte page table entry (used also to refer generically to paging structure + entries) +gpte guest pte (referring to gfns) +spte shadow pte (referring to pfns) +tdp two dimensional paging (vendor neutral term for NPT and EPT) + +Virtual and real hardware supported +=================================== + +The mmu supports first-generation mmu hardware, which allows an atomic switch +of the current paging mode and cr3 during guest entry, as well as +two-dimensional paging (AMD's NPT and Intel's EPT). The emulated hardware +it exposes is the traditional 2/3/4 level x86 mmu, with support for global +pages, pae, pse, pse36, cr0.wp, and 1GB pages. Work is in progress to support +exposing NPT capable hardware on NPT capable hosts. + +Translation +=========== + +The primary job of the mmu is to program the processor's mmu to translate +addresses for the guest. Different translations are required at different +times: + +- when guest paging is disabled, we translate guest physical addresses to + host physical addresses (gpa->hpa) +- when guest paging is enabled, we translate guest virtual addresses, to + guest physical addresses, to host physical addresses (gva->gpa->hpa) +- when the guest launches a guest of its own, we translate nested guest + virtual addresses, to nested guest physical addresses, to guest physical + addresses, to host physical addresses (ngva->ngpa->gpa->hpa) + +The primary challenge is to encode between 1 and 3 translations into hardware +that support only 1 (traditional) and 2 (tdp) translations. When the +number of required translations matches the hardware, the mmu operates in +direct mode; otherwise it operates in shadow mode (see below). + +Memory +====== + +Guest memory (gpa) is part of user address space of the process that is using +kvm. Userspace defines the translation between guest addresses and user +addresses (gpa->hva); note that two gpas may alias to the same gva, but not +vice versa. + +These gvas may be backed using any method available to the host: anonymous +memory, file backed memory, and device memory. Memory might be paged by the +host at any time. + +Events +====== + +The mmu is driven by events, some from the guest, some from the host. + +Guest generated events: +- writes to control registers (especially cr3) +- invlpg/invlpga instruction execution +- access to missing or protected translations + +Host generated events: +- changes in the gpa->hpa translation (either through gpa->hva changes or + through hva->hpa changes) +- memory pressure (the shrinker) + +Shadow pages +============ + +The principal data structure is the shadow page, 'struct kvm_mmu_page'. A +shadow page contains 512 sptes, which can be either leaf or nonleaf sptes. A +shadow page may contain a mix of leaf and nonleaf sptes. + +A nonleaf spte allows the hardware mmu to reach the leaf pages and +is not related to a translation directly. It points to other shadow pages. + +A leaf spte corresponds to either one or two translations encoded into +one paging structure entry. These are always the lowest level of the +translation stack, with an optional higher level translations left to NPT/EPT. +Leaf ptes point at guest pages. + +The following table shows translations encoded by leaf ptes, with higher-level +translations in parentheses: + + Non-nested guests: + nonpaging: gpa->hpa + paging: gva->gpa->hpa + paging, tdp: (gva->)gpa->hpa + Nested guests: + non-tdp: ngva->gpa->hpa (*) + tdp: (ngva->)ngpa->gpa->hpa + +(*) the guest hypervisor will encode the ngva->gpa translation into its page + tables if npt is not present + +Shadow pages contain the following information: + role.level: + The level in the shadow paging hierarchy that this shadow page belongs to. + 1=4k sptes, 2=2M sptes, 3=1G sptes, etc. + role.direct: + If set, leaf sptes reachable from this page are for a linear range. + Examples include real mode translation, large guest pages backed by small + host pages, and gpa->hpa translations when NPT or EPT is active. + The linear range starts at (gfn << PAGE_SHIFT) and its size is determined + by role.level (2MB for first level, 1GB for second level, 0.5TB for third + level, 256TB for fourth level) + If clear, this page corresponds to a guest page table denoted by the gfn + field. + role.quadrant: + When role.cr4_pae=0, the guest uses 32-bit gptes while the host uses 64-bit + sptes. That means a guest page table contains more ptes than the host, + so multiple shadow pages are needed to shadow one guest page. + For first-level shadow pages, role.quadrant can be 0 or 1 and denotes the + first or second 512-gpte block in the guest page table. For second-level + page tables, each 32-bit gpte is converted to two 64-bit sptes + (since each first-level guest page is shadowed by two first-level + shadow pages) so role.quadrant takes values in the range 0..3. Each + quadrant maps 1GB virtual address space. + role.access: + Inherited guest access permissions in the form uwx. Note execute + permission is positive, not negative. + role.invalid: + The page is invalid and should not be used. It is a root page that is + currently pinned (by a cpu hardware register pointing to it); once it is + unpinned it will be destroyed. + role.cr4_pae: + Contains the value of cr4.pae for which the page is valid (e.g. whether + 32-bit or 64-bit gptes are in use). + role.cr4_nxe: + Contains the value of efer.nxe for which the page is valid. + gfn: + Either the guest page table containing the translations shadowed by this + page, or the base page frame for linear translations. See role.direct. + spt: + A pageful of 64-bit sptes containig the translations for this page. + Accessed by both kvm and hardware. + The page pointed to by spt will have its page->private pointing back + at the shadow page structure. + sptes in spt point either at guest pages, or at lower-level shadow pages. + Specifically, if sp1 and sp2 are shadow pages, then sp1->spt[n] may point + at __pa(sp2->spt). sp2 will point back at sp1 through parent_pte. + The spt array forms a DAG structure with the shadow page as a node, and + guest pages as leaves. + gfns: + An array of 512 guest frame numbers, one for each present pte. Used to + perform a reverse map from a pte to a gfn. + slot_bitmap: + A bitmap containing one bit per memory slot. If the page contains a pte + mapping a page from memory slot n, then bit n of slot_bitmap will be set + (if a page is aliased among several slots, then it is not guaranteed that + all slots will be marked). + Used during dirty logging to avoid scanning a shadow page if none if its + pages need tracking. + root_count: + A counter keeping track of how many hardware registers (guest cr3 or + pdptrs) are now pointing at the page. While this counter is nonzero, the + page cannot be destroyed. See role.invalid. + multimapped: + Whether there exist multiple sptes pointing at this page. + parent_pte/parent_ptes: + If multimapped is zero, parent_pte points at the single spte that points at + this page's spt. Otherwise, parent_ptes points at a data structure + with a list of parent_ptes. + unsync: + If true, then the translations in this page may not match the guest's + translation. This is equivalent to the state of the tlb when a pte is + changed but before the tlb entry is flushed. Accordingly, unsync ptes + are synchronized when the guest executes invlpg or flushes its tlb by + other means. Valid for leaf pages. + unsync_children: + How many sptes in the page point at pages that are unsync (or have + unsynchronized children). + unsync_child_bitmap: + A bitmap indicating which sptes in spt point (directly or indirectly) at + pages that may be unsynchronized. Used to quickly locate all unsychronized + pages reachable from a given page. + +Reverse map +=========== + +The mmu maintains a reverse mapping whereby all ptes mapping a page can be +reached given its gfn. This is used, for example, when swapping out a page. + +Synchronized and unsynchronized pages +===================================== + +The guest uses two events to synchronize its tlb and page tables: tlb flushes +and page invalidations (invlpg). + +A tlb flush means that we need to synchronize all sptes reachable from the +guest's cr3. This is expensive, so we keep all guest page tables write +protected, and synchronize sptes to gptes when a gpte is written. + +A special case is when a guest page table is reachable from the current +guest cr3. In this case, the guest is obliged to issue an invlpg instruction +before using the translation. We take advantage of that by removing write +protection from the guest page, and allowing the guest to modify it freely. +We synchronize modified gptes when the guest invokes invlpg. This reduces +the amount of emulation we have to do when the guest modifies multiple gptes, +or when the a guest page is no longer used as a page table and is used for +random guest data. + +As a side effect we have resynchronize all reachable unsynchronized shadow +pages on a tlb flush. + + +Reaction to events +================== + +- guest page fault (or npt page fault, or ept violation) + +This is the most complicated event. The cause of a page fault can be: + + - a true guest fault (the guest translation won't allow the access) (*) + - access to a missing translation + - access to a protected translation + - when logging dirty pages, memory is write protected + - synchronized shadow pages are write protected (*) + - access to untranslatable memory (mmio) + + (*) not applicable in direct mode + +Handling a page fault is performed as follows: + + - if needed, walk the guest page tables to determine the guest translation + (gva->gpa or ngpa->gpa) + - if permissions are insufficient, reflect the fault back to the guest + - determine the host page + - if this is an mmio request, there is no host page; call the emulator + to emulate the instruction instead + - walk the shadow page table to find the spte for the translation, + instantiating missing intermediate page tables as necessary + - try to unsynchronize the page + - if successful, we can let the guest continue and modify the gpte + - emulate the instruction + - if failed, unshadow the page and let the guest continue + - update any translations that were modified by the instruction + +invlpg handling: + + - walk the shadow page hierarchy and drop affected translations + - try to reinstantiate the indicated translation in the hope that the + guest will use it in the near future + +Guest control register updates: + +- mov to cr3 + - look up new shadow roots + - synchronize newly reachable shadow pages + +- mov to cr0/cr4/efer + - set up mmu context for new paging mode + - look up new shadow roots + - synchronize newly reachable shadow pages + +Host translation updates: + + - mmu notifier called with updated hva + - look up affected sptes through reverse map + - drop (or update) translations + +Further reading +=============== + +- NPT presentation from KVM Forum 2008 + http://www.linux-kvm.org/wiki/images/c/c8/KvmForum2008%24kdf2008_21.pdf + diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt index a9100b28eb84..ec94748ae65b 100644 --- a/Documentation/trace/kprobetrace.txt +++ b/Documentation/trace/kprobetrace.txt @@ -40,7 +40,9 @@ Synopsis of kprobe_events $stack : Fetch stack address. $retval : Fetch return value.(*) +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**) - NAME=FETCHARG: Set NAME as the argument name of FETCHARG. + NAME=FETCHARG : Set NAME as the argument name of FETCHARG. + FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types + (u8/u16/u32/u64/s8/s16/s32/s64) are supported. (*) only for return probe. (**) this is useful for fetching a field of data structures. diff --git a/MAINTAINERS b/MAINTAINERS index 31286aa21bf4..47aa7a1a1d76 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4358,13 +4358,13 @@ M: Paul Mackerras <paulus@samba.org> M: Ingo Molnar <mingo@elte.hu> M: Arnaldo Carvalho de Melo <acme@redhat.com> S: Supported -F: kernel/perf_event.c +F: kernel/perf_event*.c F: include/linux/perf_event.h -F: arch/*/kernel/perf_event.c -F: arch/*/kernel/*/perf_event.c -F: arch/*/kernel/*/*/perf_event.c +F: arch/*/kernel/perf_event*.c +F: arch/*/kernel/*/perf_event*.c +F: arch/*/kernel/*/*/perf_event*.c F: arch/*/include/asm/perf_event.h -F: arch/*/lib/perf_event.c +F: arch/*/lib/perf_event*.c F: arch/*/kernel/perf_callchain.c F: tools/perf/ diff --git a/arch/Kconfig b/arch/Kconfig index e5eb1337a537..f06010fb4838 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -42,15 +42,10 @@ config KPROBES If in doubt, say "N". config OPTPROBES - bool "Kprobes jump optimization support (EXPERIMENTAL)" - default y - depends on KPROBES + def_bool y + depends on KPROBES && HAVE_OPTPROBES depends on !PREEMPT - depends on HAVE_OPTPROBES select KALLSYMS_ALL - help - This option will allow kprobes to optimize breakpoint to - a jump for reducing its overhead. config HAVE_EFFICIENT_UNALIGNED_ACCESS bool diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 7f3c0a2e60cd..d5f4e9161201 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -979,11 +979,13 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&irq_event, argp, sizeof irq_event)) goto out; + r = -ENXIO; if (irqchip_in_kernel(kvm)) { __s32 status; status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); if (ioctl == KVM_IRQ_LINE_STATUS) { + r = -EFAULT; irq_event.status = status; if (copy_to_user(argp, &irq_event, sizeof irq_event)) @@ -1379,7 +1381,7 @@ static void kvm_release_vm_pages(struct kvm *kvm) int i, j; unsigned long base_gfn; - slots = rcu_dereference(kvm->memslots); + slots = kvm_memslots(kvm); for (i = 0; i < slots->nmemslots; i++) { memslot = &slots->memslots[i]; base_gfn = memslot->base_gfn; @@ -1535,8 +1537,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, goto out; if (copy_to_user(user_stack, stack, - sizeof(struct kvm_ia64_vcpu_stack))) + sizeof(struct kvm_ia64_vcpu_stack))) { + r = -EFAULT; goto out; + } break; } diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h index a9b91ed3d4b9..2048a6aeea91 100644 --- a/arch/powerpc/include/asm/asm-compat.h +++ b/arch/powerpc/include/asm/asm-compat.h @@ -21,6 +21,7 @@ /* operations for longs and pointers */ #define PPC_LL stringify_in_c(ld) #define PPC_STL stringify_in_c(std) +#define PPC_STLU stringify_in_c(stdu) #define PPC_LCMPI stringify_in_c(cmpdi) #define PPC_LONG stringify_in_c(.llong) #define PPC_LONG_ALIGN stringify_in_c(.balign 8) @@ -44,6 +45,7 @@ /* operations for longs and pointers */ #define PPC_LL stringify_in_c(lwz) #define PPC_STL stringify_in_c(stw) +#define PPC_STLU stringify_in_c(stwu) #define PPC_LCMPI stringify_in_c(cmpwi) #define PPC_LONG stringify_in_c(.long) #define PPC_LONG_ALIGN stringify_in_c(.balign 4) diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h index 81f3b0b5601e..6c5547d82bbe 100644 --- a/arch/powerpc/include/asm/kvm.h +++ b/arch/powerpc/include/asm/kvm.h @@ -77,4 +77,14 @@ struct kvm_debug_exit_arch { struct kvm_guest_debug_arch { }; +#define KVM_REG_MASK 0x001f +#define KVM_REG_EXT_MASK 0xffe0 +#define KVM_REG_GPR 0x0000 +#define KVM_REG_FPR 0x0020 +#define KVM_REG_QPR 0x0040 +#define KVM_REG_FQPR 0x0060 + +#define KVM_INTERRUPT_SET -1U +#define KVM_INTERRUPT_UNSET -2U + #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index aadf2dd6f84e..c5ea4cda34b3 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -88,6 +88,8 @@ #define BOOK3S_HFLAG_DCBZ32 0x1 #define BOOK3S_HFLAG_SLB 0x2 +#define BOOK3S_HFLAG_PAIRED_SINGLE 0x4 +#define BOOK3S_HFLAG_NATIVE_PS 0x8 #define RESUME_FLAG_NV (1<<0) /* Reload guest nonvolatile state? */ #define RESUME_FLAG_HOST (1<<1) /* Resume host? */ diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index db7db0a96967..6f74d93725a0 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -22,46 +22,47 @@ #include <linux/types.h> #include <linux/kvm_host.h> -#include <asm/kvm_book3s_64_asm.h> +#include <asm/kvm_book3s_asm.h> struct kvmppc_slb { u64 esid; u64 vsid; u64 orige; u64 origv; - bool valid; - bool Ks; - bool Kp; - bool nx; - bool large; /* PTEs are 16MB */ - bool tb; /* 1TB segment */ - bool class; + bool valid : 1; + bool Ks : 1; + bool Kp : 1; + bool nx : 1; + bool large : 1; /* PTEs are 16MB */ + bool tb : 1; /* 1TB segment */ + bool class : 1; }; struct kvmppc_sr { u32 raw; u32 vsid; - bool Ks; - bool Kp; - bool nx; + bool Ks : 1; + bool Kp : 1; + bool nx : 1; + bool valid : 1; }; struct kvmppc_bat { u64 raw; u32 bepi; u32 bepi_mask; - bool vs; - bool vp; u32 brpn; u8 wimg; u8 pp; + bool vs : 1; + bool vp : 1; }; struct kvmppc_sid_map { u64 guest_vsid; u64 guest_esid; u64 host_vsid; - bool valid; + bool valid : 1; }; #define SID_MAP_BITS 9 @@ -70,7 +71,7 @@ struct kvmppc_sid_map { struct kvmppc_vcpu_book3s { struct kvm_vcpu vcpu; - struct kvmppc_book3s_shadow_vcpu shadow_vcpu; + struct kvmppc_book3s_shadow_vcpu *shadow_vcpu; struct kvmppc_sid_map sid_map[SID_MAP_NUM]; struct kvmppc_slb slb[64]; struct { @@ -82,9 +83,10 @@ struct kvmppc_vcpu_book3s { struct kvmppc_bat ibat[8]; struct kvmppc_bat dbat[8]; u64 hid[6]; + u64 gqr[8]; int slb_nr; + u32 dsisr; u64 sdr1; - u64 dsisr; u64 hior; u64 msr_mask; u64 vsid_first; @@ -98,15 +100,15 @@ struct kvmppc_vcpu_book3s { #define CONTEXT_GUEST 1 #define CONTEXT_GUEST_END 2 -#define VSID_REAL 0xfffffffffff00000 -#define VSID_REAL_DR 0xffffffffffe00000 -#define VSID_REAL_IR 0xffffffffffd00000 -#define VSID_BAT 0xffffffffffc00000 -#define VSID_PR 0x8000000000000000 +#define VSID_REAL 0x1fffffffffc00000ULL +#define VSID_BAT 0x1fffffffffb00000ULL +#define VSID_REAL_DR 0x2000000000000000ULL +#define VSID_REAL_IR 0x4000000000000000ULL +#define VSID_PR 0x8000000000000000ULL -extern void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, u64 ea, u64 ea_mask); +extern void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong ea, ulong ea_mask); extern void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 vp, u64 vp_mask); -extern void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, u64 pa_start, u64 pa_end); +extern void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end); extern void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 new_msr); extern void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu); extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu); @@ -114,11 +116,13 @@ extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte); extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr); extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu); extern struct kvmppc_pte *kvmppc_mmu_find_pte(struct kvm_vcpu *vcpu, u64 ea, bool data); -extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr, bool data); -extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr); +extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); +extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec); extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper, u32 val); +extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr); +extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu); extern u32 kvmppc_trampoline_lowmem; extern u32 kvmppc_trampoline_enter; @@ -126,6 +130,8 @@ extern void kvmppc_rmcall(ulong srr0, ulong srr1); extern void kvmppc_load_up_fpu(void); extern void kvmppc_load_up_altivec(void); extern void kvmppc_load_up_vsx(void); +extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst); +extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst); static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) { @@ -140,7 +146,108 @@ static inline ulong dsisr(void) } extern void kvm_return_point(void); +static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu); + +static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) +{ + if ( num < 14 ) { + to_svcpu(vcpu)->gpr[num] = val; + to_book3s(vcpu)->shadow_vcpu->gpr[num] = val; + } else + vcpu->arch.gpr[num] = val; +} + +static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) +{ + if ( num < 14 ) + return to_svcpu(vcpu)->gpr[num]; + else + return vcpu->arch.gpr[num]; +} + +static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) +{ + to_svcpu(vcpu)->cr = val; + to_book3s(vcpu)->shadow_vcpu->cr = val; +} + +static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) +{ + return to_svcpu(vcpu)->cr; +} + +static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val) +{ + to_svcpu(vcpu)->xer = val; + to_book3s(vcpu)->shadow_vcpu->xer = val; +} + +static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu) +{ + return to_svcpu(vcpu)->xer; +} + +static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val) +{ + to_svcpu(vcpu)->ctr = val; +} + +static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu) +{ + return to_svcpu(vcpu)->ctr; +} + +static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val) +{ + to_svcpu(vcpu)->lr = val; +} + +static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu) +{ + return to_svcpu(vcpu)->lr; +} + +static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val) +{ + to_svcpu(vcpu)->pc = val; +} + +static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu) +{ + return to_svcpu(vcpu)->pc; +} + +static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu) +{ + ulong pc = kvmppc_get_pc(vcpu); + struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu); + + /* Load the instruction manually if it failed to do so in the + * exit path */ + if (svcpu->last_inst == KVM_INST_FETCH_FAILED) + kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false); + + return svcpu->last_inst; +} + +static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) +{ + return to_svcpu(vcpu)->fault_dar; +} + +/* Magic register values loaded into r3 and r4 before the 'sc' assembly + * instruction for the OSI hypercalls */ +#define OSI_SC_MAGIC_R3 0x113724FA +#define OSI_SC_MAGIC_R4 0x77810F9B #define INS_DCBZ 0x7c0007ec +/* Also add subarch specific defines */ + +#ifdef CONFIG_PPC_BOOK3S_32 +#include <asm/kvm_book3s_32.h> +#else +#include <asm/kvm_book3s_64.h> +#endif + #endif /* __ASM_KVM_BOOK3S_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_32.h b/arch/powerpc/include/asm/kvm_book3s_32.h new file mode 100644 index 000000000000..de604db135f5 --- /dev/null +++ b/arch/powerpc/include/asm/kvm_book3s_32.h @@ -0,0 +1,42 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright SUSE Linux Products GmbH 2010 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +#ifndef __ASM_KVM_BOOK3S_32_H__ +#define __ASM_KVM_BOOK3S_32_H__ + +static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu) +{ + return to_book3s(vcpu)->shadow_vcpu; +} + +#define PTE_SIZE 12 +#define VSID_ALL 0 +#define SR_INVALID 0x00000001 /* VSID 1 should always be unused */ +#define SR_KP 0x20000000 +#define PTE_V 0x80000000 +#define PTE_SEC 0x00000040 +#define PTE_M 0x00000010 +#define PTE_R 0x00000100 +#define PTE_C 0x00000080 + +#define SID_SHIFT 28 +#define ESID_MASK 0xf0000000 +#define VSID_MASK 0x00fffffff0000000ULL + +#endif /* __ASM_KVM_BOOK3S_32_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h new file mode 100644 index 000000000000..4cadd612d575 --- /dev/null +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -0,0 +1,28 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright SUSE Linux Products GmbH 2010 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +#ifndef __ASM_KVM_BOOK3S_64_H__ +#define __ASM_KVM_BOOK3S_64_H__ + +static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu) +{ + return &get_paca()->shadow_vcpu; +} + +#endif /* __ASM_KVM_BOOK3S_64_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_64_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index 183461b48407..36fdb3aff30b 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -22,7 +22,7 @@ #ifdef __ASSEMBLY__ -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +#ifdef CONFIG_KVM_BOOK3S_HANDLER #include <asm/kvm_asm.h> @@ -55,7 +55,7 @@ kvmppc_resume_\intno: .macro DO_KVM intno .endm -#endif /* CONFIG_KVM_BOOK3S_64_HANDLER */ +#endif /* CONFIG_KVM_BOOK3S_HANDLER */ #else /*__ASSEMBLY__ */ @@ -63,12 +63,33 @@ struct kvmppc_book3s_shadow_vcpu { ulong gpr[14]; u32 cr; u32 xer; + + u32 fault_dsisr; + u32 last_inst; + ulong ctr; + ulong lr; + ulong pc; + ulong shadow_srr1; + ulong fault_dar; + ulong host_r1; ulong host_r2; ulong handler; ulong scratch0; ulong scratch1; ulong vmhandler; + u8 in_guest; + +#ifdef CONFIG_PPC_BOOK3S_32 + u32 sr[16]; /* Guest SRs */ +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + u8 slb_max; /* highest used guest slb entry */ + struct { + u64 esid; + u64 vsid; + } slb[64]; /* guest SLB */ +#endif }; #endif /*__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h new file mode 100644 index 000000000000..9c9ba3d59b1b --- /dev/null +++ b/arch/powerpc/include/asm/kvm_booke.h @@ -0,0 +1,96 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright SUSE Linux Products GmbH 2010 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +#ifndef __ASM_KVM_BOOKE_H__ +#define __ASM_KVM_BOOKE_H__ + +#include <linux/types.h> +#include <linux/kvm_host.h> + +static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) +{ + vcpu->arch.gpr[num] = val; +} + +static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) +{ + return vcpu->arch.gpr[num]; +} + +static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) +{ + vcpu->arch.cr = val; +} + +static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.cr; +} + +static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val) +{ + vcpu->arch.xer = val; +} + +static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.xer; +} + +static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.last_inst; +} + +static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val) +{ + vcpu->arch.ctr = val; +} + +static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.ctr; +} + +static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val) +{ + vcpu->arch.lr = val; +} + +static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.lr; +} + +static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val) +{ + vcpu->arch.pc = val; +} + +static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.pc; +} + +static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.fault_dear; +} + +#endif /* __ASM_KVM_BOOKE_H__ */ diff --git a/arch/powerpc/include/asm/kvm_fpu.h b/arch/powerpc/include/asm/kvm_fpu.h new file mode 100644 index 000000000000..94f05de9ad04 --- /dev/null +++ b/arch/powerpc/include/asm/kvm_fpu.h @@ -0,0 +1,85 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright Novell Inc. 2010 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +#ifndef __ASM_KVM_FPU_H__ +#define __ASM_KVM_FPU_H__ + +#include <linux/types.h> + +extern void fps_fres(struct thread_struct *t, u32 *dst, u32 *src1); +extern void fps_frsqrte(struct thread_struct *t, u32 *dst, u32 *src1); +extern void fps_fsqrts(struct thread_struct *t, u32 *dst, u32 *src1); + +extern void fps_fadds(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2); +extern void fps_fdivs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2); +extern void fps_fmuls(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2); +extern void fps_fsubs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2); + +extern void fps_fmadds(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2, + u32 *src3); +extern void fps_fmsubs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2, + u32 *src3); +extern void fps_fnmadds(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2, + u32 *src3); +extern void fps_fnmsubs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2, + u32 *src3); +extern void fps_fsel(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2, + u32 *src3); + +#define FPD_ONE_IN(name) extern void fpd_ ## name(u64 *fpscr, u32 *cr, \ + u64 *dst, u64 *src1); +#define FPD_TWO_IN(name) extern void fpd_ ## name(u64 *fpscr, u32 *cr, \ + u64 *dst, u64 *src1, u64 *src2); +#define FPD_THREE_IN(name) extern void fpd_ ## name(u64 *fpscr, u32 *cr, \ + u64 *dst, u64 *src1, u64 *src2, u64 *src3); + +extern void fpd_fcmpu(u64 *fpscr, u32 *cr, u64 *src1, u64 *src2); +extern void fpd_fcmpo(u64 *fpscr, u32 *cr, u64 *src1, u64 *src2); + +FPD_ONE_IN(fsqrts) +FPD_ONE_IN(frsqrtes) +FPD_ONE_IN(fres) +FPD_ONE_IN(frsp) +FPD_ONE_IN(fctiw) +FPD_ONE_IN(fctiwz) +FPD_ONE_IN(fsqrt) +FPD_ONE_IN(fre) +FPD_ONE_IN(frsqrte) +FPD_ONE_IN(fneg) +FPD_ONE_IN(fabs) +FPD_TWO_IN(fadds) +FPD_TWO_IN(fsubs) +FPD_TWO_IN(fdivs) +FPD_TWO_IN(fmuls) +FPD_TWO_IN(fcpsgn) +FPD_TWO_IN(fdiv) +FPD_TWO_IN(fadd) +FPD_TWO_IN(fmul) +FPD_TWO_IN(fsub) +FPD_THREE_IN(fmsubs) +FPD_THREE_IN(fmadds) +FPD_THREE_IN(fnmsubs) +FPD_THREE_IN(fnmadds) +FPD_THREE_IN(fsel) +FPD_THREE_IN(fmsub) +FPD_THREE_IN(fmadd) +FPD_THREE_IN(fnmsub) +FPD_THREE_IN(fnmadd) + +#endif diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 5e5bae7e152f..0c9ad869decd 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -66,7 +66,7 @@ struct kvm_vcpu_stat { u32 dec_exits; u32 ext_intr_exits; u32 halt_wakeup; -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S u32 pf_storage; u32 pf_instruc; u32 sp_storage; @@ -124,12 +124,12 @@ struct kvm_arch { }; struct kvmppc_pte { - u64 eaddr; + ulong eaddr; u64 vpage; - u64 raddr; - bool may_read; - bool may_write; - bool may_execute; + ulong raddr; + bool may_read : 1; + bool may_write : 1; + bool may_execute : 1; }; struct kvmppc_mmu { @@ -145,7 +145,7 @@ struct kvmppc_mmu { int (*xlate)(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *pte, bool data); void (*reset_msr)(struct kvm_vcpu *vcpu); void (*tlbie)(struct kvm_vcpu *vcpu, ulong addr, bool large); - int (*esid_to_vsid)(struct kvm_vcpu *vcpu, u64 esid, u64 *vsid); + int (*esid_to_vsid)(struct kvm_vcpu *vcpu, ulong esid, u64 *vsid); u64 (*ea_to_vp)(struct kvm_vcpu *vcpu, gva_t eaddr, bool data); bool (*is_dcbz32)(struct kvm_vcpu *vcpu); }; @@ -160,7 +160,7 @@ struct hpte_cache { struct kvm_vcpu_arch { ulong host_stack; u32 host_pid; -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S ulong host_msr; ulong host_r2; void *host_retip; @@ -175,7 +175,7 @@ struct kvm_vcpu_arch { ulong gpr[32]; u64 fpr[32]; - u32 fpscr; + u64 fpscr; #ifdef CONFIG_ALTIVEC vector128 vr[32]; @@ -186,19 +186,23 @@ struct kvm_vcpu_arch { u64 vsr[32]; #endif +#ifdef CONFIG_PPC_BOOK3S + /* For Gekko paired singles */ + u32 qpr[32]; +#endif + +#ifdef CONFIG_BOOKE ulong pc; ulong ctr; ulong lr; -#ifdef CONFIG_BOOKE ulong xer; u32 cr; #endif ulong msr; -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S ulong shadow_msr; - ulong shadow_srr1; ulong hflags; ulong guest_owned_ext; #endif @@ -253,20 +257,22 @@ struct kvm_vcpu_arch { struct dentry *debugfs_exit_timing; #endif +#ifdef CONFIG_BOOKE u32 last_inst; -#ifdef CONFIG_PPC64 - ulong fault_dsisr; -#endif ulong fault_dear; ulong fault_esr; ulong queued_dear; ulong queued_esr; +#endif gpa_t paddr_accessed; u8 io_gpr; /* GPR used as IO source/target */ u8 mmio_is_bigendian; + u8 mmio_sign_extend; u8 dcr_needed; u8 dcr_is_write; + u8 osi_needed; + u8 osi_enabled; u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */ @@ -275,7 +281,7 @@ struct kvm_vcpu_arch { u64 dec_jiffies; unsigned long pending_exceptions; -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S struct hpte_cache hpte_cache[HPTEG_CACHE_NUM]; int hpte_cache_offset; #endif diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index e2642829e435..18d139ec2d22 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -30,6 +30,8 @@ #include <linux/kvm_host.h> #ifdef CONFIG_PPC_BOOK3S #include <asm/kvm_book3s.h> +#else +#include <asm/kvm_booke.h> #endif enum emulation_result { @@ -37,6 +39,7 @@ enum emulation_result { EMULATE_DO_MMIO, /* kvm_run filled with MMIO request */ EMULATE_DO_DCR, /* kvm_run filled with DCR request */ EMULATE_FAIL, /* can't emulate this instruction */ + EMULATE_AGAIN, /* something went wrong. go again */ }; extern int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); @@ -48,8 +51,11 @@ extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu); extern int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int rt, unsigned int bytes, int is_bigendian); +extern int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int rt, unsigned int bytes, + int is_bigendian); extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, - u32 val, unsigned int bytes, int is_bigendian); + u64 val, unsigned int bytes, int is_bigendian); extern int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu); @@ -63,6 +69,7 @@ extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr, extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode); extern void kvmppc_mmu_switch_pid(struct kvm_vcpu *vcpu, u32 pid); extern void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu); +extern int kvmppc_mmu_init(struct kvm_vcpu *vcpu); extern int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr); extern int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr); extern gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index, @@ -88,6 +95,8 @@ extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu); extern void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu); extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq); +extern void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu, + struct kvm_interrupt *irq); extern int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int op, int *advance); @@ -99,81 +108,37 @@ extern void kvmppc_booke_exit(void); extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu); -#ifdef CONFIG_PPC_BOOK3S - -/* We assume we're always acting on the current vcpu */ - -static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) -{ - if ( num < 14 ) { - get_paca()->shadow_vcpu.gpr[num] = val; - to_book3s(vcpu)->shadow_vcpu.gpr[num] = val; - } else - vcpu->arch.gpr[num] = val; -} - -static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) -{ - if ( num < 14 ) - return get_paca()->shadow_vcpu.gpr[num]; - else - return vcpu->arch.gpr[num]; -} - -static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) -{ - get_paca()->shadow_vcpu.cr = val; - to_book3s(vcpu)->shadow_vcpu.cr = val; -} - -static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) -{ - return get_paca()->shadow_vcpu.cr; -} - -static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val) -{ - get_paca()->shadow_vcpu.xer = val; - to_book3s(vcpu)->shadow_vcpu.xer = val; -} - -static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu) +/* + * Cuts out inst bits with ordering according to spec. + * That means the leftmost bit is zero. All given bits are included. + */ +static inline u32 kvmppc_get_field(u64 inst, int msb, int lsb) { - return get_paca()->shadow_vcpu.xer; -} + u32 r; + u32 mask; -#else + BUG_ON(msb > lsb); -static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) -{ - vcpu->arch.gpr[num] = val; -} + mask = (1 << (lsb - msb + 1)) - 1; + r = (inst >> (63 - lsb)) & mask; -static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) -{ - return vcpu->arch.gpr[num]; + return r; } -static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) +/* + * Replaces inst bits with ordering according to spec. + */ +static inline u32 kvmppc_set_field(u64 inst, int msb, int lsb, int value) { - vcpu->arch.cr = val; -} + u32 r; + u32 mask; -static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.cr; -} + BUG_ON(msb > lsb); -static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val) -{ - vcpu->arch.xer = val; -} + mask = ((1 << (lsb - msb + 1)) - 1) << (63 - lsb); + r = (inst & ~mask) | ((value << (63 - lsb)) & mask); -static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.xer; + return r; } -#endif - #endif /* __POWERPC_KVM_PPC_H__ */ diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 26383e0778aa..81fb41289d6c 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -27,6 +27,8 @@ extern int __init_new_context(void); extern void __destroy_context(int context_id); static inline void mmu_context_init(void) { } #else +extern unsigned long __init_new_context(void); +extern void __destroy_context(unsigned long context_id); extern void mmu_context_init(void); #endif diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index a011603d4079..224eb371ca1d 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -23,7 +23,7 @@ #include <asm/page.h> #include <asm/exception-64e.h> #ifdef CONFIG_KVM_BOOK3S_64_HANDLER -#include <asm/kvm_book3s_64_asm.h> +#include <asm/kvm_book3s_asm.h> #endif register struct paca_struct *local_paca asm("r13"); @@ -136,15 +136,9 @@ struct paca_struct { u64 startpurr; /* PURR/TB value snapshot */ u64 startspurr; /* SPURR value snapshot */ -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER - struct { - u64 esid; - u64 vsid; - } kvm_slb[64]; /* guest SLB */ +#ifdef CONFIG_KVM_BOOK3S_HANDLER /* We use this to store guest state in */ struct kvmppc_book3s_shadow_vcpu shadow_vcpu; - u8 kvm_slb_max; /* highest used guest slb entry */ - u8 kvm_in_guest; /* are we inside the guest? */ #endif }; diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 221ba6240464..7492fe8ad6e4 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -229,6 +229,9 @@ struct thread_struct { unsigned long spefscr; /* SPE & eFP status */ int used_spe; /* set if process has used spe */ #endif /* CONFIG_SPE */ +#ifdef CONFIG_KVM_BOOK3S_32_HANDLER + void* kvm_shadow_vcpu; /* KVM internal data */ +#endif /* CONFIG_KVM_BOOK3S_32_HANDLER */ }; #define ARCH_MIN_TASKALIGN 16 diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 5572e86223f4..8a69a39a10b1 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -293,10 +293,12 @@ #define HID1_ABE (1<<10) /* 7450 Address Broadcast Enable */ #define HID1_PS (1<<16) /* 750FX PLL selection */ #define SPRN_HID2 0x3F8 /* Hardware Implementation Register 2 */ +#define SPRN_HID2_GEKKO 0x398 /* Gekko HID2 Register */ #define SPRN_IABR 0x3F2 /* Instruction Address Breakpoint Register */ #define SPRN_IABR2 0x3FA /* 83xx */ #define SPRN_IBCR 0x135 /* 83xx Insn Breakpoint Control Reg */ #define SPRN_HID4 0x3F4 /* 970 HID4 */ +#define SPRN_HID4_GEKKO 0x3F3 /* Gekko HID4 */ #define SPRN_HID5 0x3F6 /* 970 HID5 */ #define SPRN_HID6 0x3F9 /* BE HID 6 */ #define HID6_LB (0x0F<<12) /* Concurrent Large Page Modes */ @@ -465,6 +467,14 @@ #define SPRN_VRSAVE 0x100 /* Vector Register Save Register */ #define SPRN_XER 0x001 /* Fixed Point Exception Register */ +#define SPRN_MMCR0_GEKKO 0x3B8 /* Gekko Monitor Mode Control Register 0 */ +#define SPRN_MMCR1_GEKKO 0x3BC /* Gekko Monitor Mode Control Register 1 */ +#define SPRN_PMC1_GEKKO 0x3B9 /* Gekko Performance Monitor Control 1 */ +#define SPRN_PMC2_GEKKO 0x3BA /* Gekko Performance Monitor Control 2 */ +#define SPRN_PMC3_GEKKO 0x3BD /* Gekko Performance Monitor Control 3 */ +#define SPRN_PMC4_GEKKO 0x3BE /* Gekko Performance Monitor Control 4 */ +#define SPRN_WPAR_GEKKO 0x399 /* Gekko Write Pipe Address Register */ + #define SPRN_SCOMC 0x114 /* SCOM Access Control */ #define SPRN_SCOMD 0x115 /* SCOM Access DATA */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 957ceb7059c5..2716c51906d6 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -50,6 +50,9 @@ #endif #ifdef CONFIG_KVM #include <linux/kvm_host.h> +#ifndef CONFIG_BOOKE +#include <asm/kvm_book3s.h> +#endif #endif #ifdef CONFIG_PPC32 @@ -105,6 +108,9 @@ int main(void) DEFINE(THREAD_USED_SPE, offsetof(struct thread_struct, used_spe)); #endif /* CONFIG_SPE */ #endif /* CONFIG_PPC64 */ +#ifdef CONFIG_KVM_BOOK3S_32_HANDLER + DEFINE(THREAD_KVM_SVCPU, offsetof(struct thread_struct, kvm_shadow_vcpu)); +#endif DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags)); @@ -191,33 +197,9 @@ int main(void) DEFINE(PACA_DATA_OFFSET, offsetof(struct paca_struct, data_offset)); DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save)); #ifdef CONFIG_KVM_BOOK3S_64_HANDLER - DEFINE(PACA_KVM_IN_GUEST, offsetof(struct paca_struct, kvm_in_guest)); - DEFINE(PACA_KVM_SLB, offsetof(struct paca_struct, kvm_slb)); - DEFINE(PACA_KVM_SLB_MAX, offsetof(struct paca_struct, kvm_slb_max)); - DEFINE(PACA_KVM_CR, offsetof(struct paca_struct, shadow_vcpu.cr)); - DEFINE(PACA_KVM_XER, offsetof(struct paca_struct, shadow_vcpu.xer)); - DEFINE(PACA_KVM_R0, offsetof(struct paca_struct, shadow_vcpu.gpr[0])); - DEFINE(PACA_KVM_R1, offsetof(struct paca_struct, shadow_vcpu.gpr[1])); - DEFINE(PACA_KVM_R2, offsetof(struct paca_struct, shadow_vcpu.gpr[2])); - DEFINE(PACA_KVM_R3, offsetof(struct paca_struct, shadow_vcpu.gpr[3])); - DEFINE(PACA_KVM_R4, offsetof(struct paca_struct, shadow_vcpu.gpr[4])); - DEFINE(PACA_KVM_R5, offsetof(struct paca_struct, shadow_vcpu.gpr[5])); - DEFINE(PACA_KVM_R6, offsetof(struct paca_struct, shadow_vcpu.gpr[6])); - DEFINE(PACA_KVM_R7, offsetof(struct paca_struct, shadow_vcpu.gpr[7])); - DEFINE(PACA_KVM_R8, offsetof(struct paca_struct, shadow_vcpu.gpr[8])); - DEFINE(PACA_KVM_R9, offsetof(struct paca_struct, shadow_vcpu.gpr[9])); - DEFINE(PACA_KVM_R10, offsetof(struct paca_struct, shadow_vcpu.gpr[10])); - DEFINE(PACA_KVM_R11, offsetof(struct paca_struct, shadow_vcpu.gpr[11])); - DEFINE(PACA_KVM_R12, offsetof(struct paca_struct, shadow_vcpu.gpr[12])); - DEFINE(PACA_KVM_R13, offsetof(struct paca_struct, shadow_vcpu.gpr[13])); - DEFINE(PACA_KVM_HOST_R1, offsetof(struct paca_struct, shadow_vcpu.host_r1)); - DEFINE(PACA_KVM_HOST_R2, offsetof(struct paca_struct, shadow_vcpu.host_r2)); - DEFINE(PACA_KVM_VMHANDLER, offsetof(struct paca_struct, - shadow_vcpu.vmhandler)); - DEFINE(PACA_KVM_SCRATCH0, offsetof(struct paca_struct, - shadow_vcpu.scratch0)); - DEFINE(PACA_KVM_SCRATCH1, offsetof(struct paca_struct, - shadow_vcpu.scratch1)); + DEFINE(PACA_KVM_SVCPU, offsetof(struct paca_struct, shadow_vcpu)); + DEFINE(SVCPU_SLB, offsetof(struct kvmppc_book3s_shadow_vcpu, slb)); + DEFINE(SVCPU_SLB_MAX, offsetof(struct kvmppc_book3s_shadow_vcpu, slb_max)); #endif #endif /* CONFIG_PPC64 */ @@ -228,8 +210,8 @@ int main(void) /* Interrupt register frame */ DEFINE(STACK_FRAME_OVERHEAD, STACK_FRAME_OVERHEAD); DEFINE(INT_FRAME_SIZE, STACK_INT_FRAME_SIZE); -#ifdef CONFIG_PPC64 DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs)); +#ifdef CONFIG_PPC64 /* Create extra stack space for SRR0 and SRR1 when calling prom/rtas. */ DEFINE(PROM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16); DEFINE(RTAS_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16); @@ -412,9 +394,6 @@ int main(void) DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack)); DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid)); DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr)); - DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); - DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr)); - DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc)); DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.msr)); DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4)); DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5)); @@ -422,27 +401,68 @@ int main(void) DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7)); DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid)); - DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst)); - DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear)); - DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr)); - - /* book3s_64 */ -#ifdef CONFIG_PPC64 - DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr)); + /* book3s */ +#ifdef CONFIG_PPC_BOOK3S DEFINE(VCPU_HOST_RETIP, offsetof(struct kvm_vcpu, arch.host_retip)); - DEFINE(VCPU_HOST_R2, offsetof(struct kvm_vcpu, arch.host_r2)); DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr)); DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr)); - DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1)); DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem)); DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter)); DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler)); DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall)); DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags)); + DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) - + offsetof(struct kvmppc_vcpu_book3s, vcpu)); + DEFINE(SVCPU_CR, offsetof(struct kvmppc_book3s_shadow_vcpu, cr)); + DEFINE(SVCPU_XER, offsetof(struct kvmppc_book3s_shadow_vcpu, xer)); + DEFINE(SVCPU_CTR, offsetof(struct kvmppc_book3s_shadow_vcpu, ctr)); + DEFINE(SVCPU_LR, offsetof(struct kvmppc_book3s_shadow_vcpu, lr)); + DEFINE(SVCPU_PC, offsetof(struct kvmppc_book3s_shadow_vcpu, pc)); + DEFINE(SVCPU_R0, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[0])); + DEFINE(SVCPU_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[1])); + DEFINE(SVCPU_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[2])); + DEFINE(SVCPU_R3, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[3])); + DEFINE(SVCPU_R4, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[4])); + DEFINE(SVCPU_R5, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[5])); + DEFINE(SVCPU_R6, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[6])); + DEFINE(SVCPU_R7, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[7])); + DEFINE(SVCPU_R8, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[8])); + DEFINE(SVCPU_R9, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[9])); + DEFINE(SVCPU_R10, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[10])); + DEFINE(SVCPU_R11, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[11])); + DEFINE(SVCPU_R12, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[12])); + DEFINE(SVCPU_R13, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[13])); + DEFINE(SVCPU_HOST_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r1)); + DEFINE(SVCPU_HOST_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r2)); + DEFINE(SVCPU_VMHANDLER, offsetof(struct kvmppc_book3s_shadow_vcpu, + vmhandler)); + DEFINE(SVCPU_SCRATCH0, offsetof(struct kvmppc_book3s_shadow_vcpu, + scratch0)); + DEFINE(SVCPU_SCRATCH1, offsetof(struct kvmppc_book3s_shadow_vcpu, + scratch1)); + DEFINE(SVCPU_IN_GUEST, offsetof(struct kvmppc_book3s_shadow_vcpu, + in_guest)); + DEFINE(SVCPU_FAULT_DSISR, offsetof(struct kvmppc_book3s_shadow_vcpu, + fault_dsisr)); + DEFINE(SVCPU_FAULT_DAR, offsetof(struct kvmppc_book3s_shadow_vcpu, + fault_dar)); + DEFINE(SVCPU_LAST_INST, offsetof(struct kvmppc_book3s_shadow_vcpu, + last_inst)); + DEFINE(SVCPU_SHADOW_SRR1, offsetof(struct kvmppc_book3s_shadow_vcpu, + shadow_srr1)); +#ifdef CONFIG_PPC_BOOK3S_32 + DEFINE(SVCPU_SR, offsetof(struct kvmppc_book3s_shadow_vcpu, sr)); +#endif #else DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer)); -#endif /* CONFIG_PPC64 */ + DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); + DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr)); + DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc)); + DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst)); + DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear)); + DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr)); +#endif /* CONFIG_PPC_BOOK3S */ #endif #ifdef CONFIG_44x DEFINE(PGD_T_LOG2, PGD_T_LOG2); diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index e025e89fe93e..98c4b29a56f4 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -33,6 +33,7 @@ #include <asm/asm-offsets.h> #include <asm/ptrace.h> #include <asm/bug.h> +#include <asm/kvm_book3s_asm.h> /* 601 only have IBAT; cr0.eq is set on 601 when using this macro */ #define LOAD_BAT(n, reg, RA, RB) \ @@ -303,6 +304,7 @@ __secondary_hold_acknowledge: */ #define EXCEPTION(n, label, hdlr, xfer) \ . = n; \ + DO_KVM n; \ label: \ EXCEPTION_PROLOG; \ addi r3,r1,STACK_FRAME_OVERHEAD; \ @@ -358,6 +360,7 @@ i##n: \ * -- paulus. */ . = 0x200 + DO_KVM 0x200 mtspr SPRN_SPRG_SCRATCH0,r10 mtspr SPRN_SPRG_SCRATCH1,r11 mfcr r10 @@ -381,6 +384,7 @@ i##n: \ /* Data access exception. */ . = 0x300 + DO_KVM 0x300 DataAccess: EXCEPTION_PROLOG mfspr r10,SPRN_DSISR @@ -397,6 +401,7 @@ DataAccess: /* Instruction access exception. */ . = 0x400 + DO_KVM 0x400 InstructionAccess: EXCEPTION_PROLOG andis. r0,r9,0x4000 /* no pte found? */ @@ -413,6 +418,7 @@ InstructionAccess: /* Alignment exception */ . = 0x600 + DO_KVM 0x600 Alignment: EXCEPTION_PROLOG mfspr r4,SPRN_DAR @@ -427,6 +433,7 @@ Alignment: /* Floating-point unavailable */ . = 0x800 + DO_KVM 0x800 FPUnavailable: BEGIN_FTR_SECTION /* @@ -450,6 +457,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_FPU_UNAVAILABLE) /* System call */ . = 0xc00 + DO_KVM 0xc00 SystemCall: EXCEPTION_PROLOG EXC_XFER_EE_LITE(0xc00, DoSyscall) @@ -467,9 +475,11 @@ SystemCall: * by executing an altivec instruction. */ . = 0xf00 + DO_KVM 0xf00 b PerformanceMonitor . = 0xf20 + DO_KVM 0xf20 b AltiVecUnavailable /* @@ -882,6 +892,10 @@ __secondary_start: RFI #endif /* CONFIG_SMP */ +#ifdef CONFIG_KVM_BOOK3S_HANDLER +#include "../kvm/book3s_rmhandlers.S" +#endif + /* * Those generic dummy functions are kept for CPUs not * included in CONFIG_6xx diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index bed9a29ee383..844a44b64472 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -37,7 +37,7 @@ #include <asm/firmware.h> #include <asm/page_64.h> #include <asm/irqflags.h> -#include <asm/kvm_book3s_64_asm.h> +#include <asm/kvm_book3s_asm.h> /* The physical memory is layed out such that the secondary processor * spin code sits at 0x0000...0x00ff. On server, the vectors follow @@ -169,7 +169,7 @@ exception_marker: /* KVM trampoline code needs to be close to the interrupt handlers */ #ifdef CONFIG_KVM_BOOK3S_64_HANDLER -#include "../kvm/book3s_64_rmhandlers.S" +#include "../kvm/book3s_rmhandlers.S" #endif _GLOBAL(generic_secondary_thread_init) diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index ab3e392ac63c..bc9f39d2598b 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -101,6 +101,10 @@ EXPORT_SYMBOL(pci_dram_offset); EXPORT_SYMBOL(start_thread); EXPORT_SYMBOL(kernel_thread); +#ifndef CONFIG_BOOKE +EXPORT_SYMBOL_GPL(cvt_df); +EXPORT_SYMBOL_GPL(cvt_fd); +#endif EXPORT_SYMBOL(giveup_fpu); #ifdef CONFIG_ALTIVEC EXPORT_SYMBOL(giveup_altivec); diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 60624cc9f4d4..b7baff78f90c 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -22,12 +22,34 @@ config KVM select ANON_INODES select KVM_MMIO +config KVM_BOOK3S_HANDLER + bool + +config KVM_BOOK3S_32_HANDLER + bool + select KVM_BOOK3S_HANDLER + config KVM_BOOK3S_64_HANDLER bool + select KVM_BOOK3S_HANDLER + +config KVM_BOOK3S_32 + tristate "KVM support for PowerPC book3s_32 processors" + depends on EXPERIMENTAL && PPC_BOOK3S_32 && !SMP && !PTE_64BIT + select KVM + select KVM_BOOK3S_32_HANDLER + ---help--- + Support running unmodified book3s_32 guest kernels + in virtual machines on book3s_32 host processors. + + This module provides access to the hardware capabilities through + a character device node named /dev/kvm. + + If unsure, say N. config KVM_BOOK3S_64 tristate "KVM support for PowerPC book3s_64 processors" - depends on EXPERIMENTAL && PPC64 + depends on EXPERIMENTAL && PPC_BOOK3S_64 select KVM select KVM_BOOK3S_64_HANDLER ---help--- diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 56484d652377..ff436066bf77 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -14,7 +14,7 @@ CFLAGS_emulate.o := -I. common-objs-y += powerpc.o emulate.o obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o -obj-$(CONFIG_KVM_BOOK3S_64_HANDLER) += book3s_64_exports.o +obj-$(CONFIG_KVM_BOOK3S_HANDLER) += book3s_exports.o AFLAGS_booke_interrupts.o := -I$(obj) @@ -40,17 +40,31 @@ kvm-objs-$(CONFIG_KVM_E500) := $(kvm-e500-objs) kvm-book3s_64-objs := \ $(common-objs-y) \ + fpu.o \ + book3s_paired_singles.o \ book3s.o \ - book3s_64_emulate.o \ - book3s_64_interrupts.o \ + book3s_emulate.o \ + book3s_interrupts.o \ book3s_64_mmu_host.o \ book3s_64_mmu.o \ book3s_32_mmu.o kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-objs) +kvm-book3s_32-objs := \ + $(common-objs-y) \ + fpu.o \ + book3s_paired_singles.o \ + book3s.o \ + book3s_emulate.o \ + book3s_interrupts.o \ + book3s_32_mmu_host.o \ + book3s_32_mmu.o +kvm-objs-$(CONFIG_KVM_BOOK3S_32) := $(kvm-book3s_32-objs) + kvm-objs := $(kvm-objs-m) $(kvm-objs-y) obj-$(CONFIG_KVM_440) += kvm.o obj-$(CONFIG_KVM_E500) += kvm.o obj-$(CONFIG_KVM_BOOK3S_64) += kvm.o +obj-$(CONFIG_KVM_BOOK3S_32) += kvm.o diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 604af29b71ed..9f97dbe25e4e 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -29,6 +29,7 @@ #include <linux/gfp.h> #include <linux/sched.h> #include <linux/vmalloc.h> +#include <linux/highmem.h> #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU @@ -36,7 +37,15 @@ /* #define EXIT_DEBUG_SIMPLE */ /* #define DEBUG_EXT */ -static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr); +static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr, + ulong msr); + +/* Some compatibility defines */ +#ifdef CONFIG_PPC_BOOK3S_32 +#define MSR_USER32 MSR_USER +#define MSR_USER64 MSR_USER +#define HW_PAGE_SIZE PAGE_SIZE +#endif struct kvm_stats_debugfs_item debugfs_entries[] = { { "exits", VCPU_STAT(sum_exits) }, @@ -69,18 +78,26 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu) void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { - memcpy(get_paca()->kvm_slb, to_book3s(vcpu)->slb_shadow, sizeof(get_paca()->kvm_slb)); - memcpy(&get_paca()->shadow_vcpu, &to_book3s(vcpu)->shadow_vcpu, +#ifdef CONFIG_PPC_BOOK3S_64 + memcpy(to_svcpu(vcpu)->slb, to_book3s(vcpu)->slb_shadow, sizeof(to_svcpu(vcpu)->slb)); + memcpy(&get_paca()->shadow_vcpu, to_book3s(vcpu)->shadow_vcpu, sizeof(get_paca()->shadow_vcpu)); - get_paca()->kvm_slb_max = to_book3s(vcpu)->slb_shadow_max; + to_svcpu(vcpu)->slb_max = to_book3s(vcpu)->slb_shadow_max; +#endif + +#ifdef CONFIG_PPC_BOOK3S_32 + current->thread.kvm_shadow_vcpu = to_book3s(vcpu)->shadow_vcpu; +#endif } void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) { - memcpy(to_book3s(vcpu)->slb_shadow, get_paca()->kvm_slb, sizeof(get_paca()->kvm_slb)); - memcpy(&to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu, +#ifdef CONFIG_PPC_BOOK3S_64 + memcpy(to_book3s(vcpu)->slb_shadow, to_svcpu(vcpu)->slb, sizeof(to_svcpu(vcpu)->slb)); + memcpy(to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu, sizeof(get_paca()->shadow_vcpu)); - to_book3s(vcpu)->slb_shadow_max = get_paca()->kvm_slb_max; + to_book3s(vcpu)->slb_shadow_max = to_svcpu(vcpu)->slb_max; +#endif kvmppc_giveup_ext(vcpu, MSR_FP); kvmppc_giveup_ext(vcpu, MSR_VEC); @@ -131,18 +148,22 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr) } } - if (((vcpu->arch.msr & (MSR_IR|MSR_DR)) != (old_msr & (MSR_IR|MSR_DR))) || - (vcpu->arch.msr & MSR_PR) != (old_msr & MSR_PR)) { + if ((vcpu->arch.msr & (MSR_PR|MSR_IR|MSR_DR)) != + (old_msr & (MSR_PR|MSR_IR|MSR_DR))) { kvmppc_mmu_flush_segments(vcpu); - kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc); + kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)); } + + /* Preload FPU if it's enabled */ + if (vcpu->arch.msr & MSR_FP) + kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP); } void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags) { - vcpu->arch.srr0 = vcpu->arch.pc; + vcpu->arch.srr0 = kvmppc_get_pc(vcpu); vcpu->arch.srr1 = vcpu->arch.msr | flags; - vcpu->arch.pc = to_book3s(vcpu)->hior + vec; + kvmppc_set_pc(vcpu, to_book3s(vcpu)->hior + vec); vcpu->arch.mmu.reset_msr(vcpu); } @@ -218,6 +239,12 @@ void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL); } +void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu, + struct kvm_interrupt *irq) +{ + kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL); +} + int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority) { int deliver = 1; @@ -302,7 +329,7 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu) printk(KERN_EMERG "KVM: Check pending: %lx\n", vcpu->arch.pending_exceptions); #endif priority = __ffs(*pending); - while (priority <= (sizeof(unsigned int) * 8)) { + while (priority < BOOK3S_IRQPRIO_MAX) { if (kvmppc_book3s_irqprio_deliver(vcpu, priority) && (priority != BOOK3S_IRQPRIO_DECREMENTER)) { /* DEC interrupts get cleared by mtdec */ @@ -318,13 +345,18 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu) void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) { + u32 host_pvr; + vcpu->arch.hflags &= ~BOOK3S_HFLAG_SLB; vcpu->arch.pvr = pvr; +#ifdef CONFIG_PPC_BOOK3S_64 if ((pvr >= 0x330000) && (pvr < 0x70330000)) { kvmppc_mmu_book3s_64_init(vcpu); to_book3s(vcpu)->hior = 0xfff00000; to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL; - } else { + } else +#endif + { kvmppc_mmu_book3s_32_init(vcpu); to_book3s(vcpu)->hior = 0; to_book3s(vcpu)->msr_mask = 0xffffffffULL; @@ -337,6 +369,32 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) !strcmp(cur_cpu_spec->platform, "ppc970")) vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32; + /* Cell performs badly if MSR_FEx are set. So let's hope nobody + really needs them in a VM on Cell and force disable them. */ + if (!strcmp(cur_cpu_spec->platform, "ppc-cell-be")) + to_book3s(vcpu)->msr_mask &= ~(MSR_FE0 | MSR_FE1); + +#ifdef CONFIG_PPC_BOOK3S_32 + /* 32 bit Book3S always has 32 byte dcbz */ + vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32; +#endif + + /* On some CPUs we can execute paired single operations natively */ + asm ( "mfpvr %0" : "=r"(host_pvr)); + switch (host_pvr) { + case 0x00080200: /* lonestar 2.0 */ + case 0x00088202: /* lonestar 2.2 */ + case 0x70000100: /* gekko 1.0 */ + case 0x00080100: /* gekko 2.0 */ + case 0x00083203: /* gekko 2.3a */ + case 0x00083213: /* gekko 2.3b */ + case 0x00083204: /* gekko 2.4 */ + case 0x00083214: /* gekko 2.4e (8SE) - retail HW2 */ + case 0x00087200: /* broadway */ + vcpu->arch.hflags |= BOOK3S_HFLAG_NATIVE_PS; + /* Enable HID2.PSE - in case we need it later */ + mtspr(SPRN_HID2_GEKKO, mfspr(SPRN_HID2_GEKKO) | (1 << 29)); + } } /* Book3s_32 CPUs always have 32 bytes cache line size, which Linux assumes. To @@ -350,34 +408,29 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) */ static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte) { - bool touched = false; - hva_t hpage; + struct page *hpage; + u64 hpage_offset; u32 *page; int i; - hpage = gfn_to_hva(vcpu->kvm, pte->raddr >> PAGE_SHIFT); - if (kvm_is_error_hva(hpage)) + hpage = gfn_to_page(vcpu->kvm, pte->raddr >> PAGE_SHIFT); + if (is_error_page(hpage)) return; - hpage |= pte->raddr & ~PAGE_MASK; - hpage &= ~0xFFFULL; - - page = vmalloc(HW_PAGE_SIZE); - - if (copy_from_user(page, (void __user *)hpage, HW_PAGE_SIZE)) - goto out; + hpage_offset = pte->raddr & ~PAGE_MASK; + hpage_offset &= ~0xFFFULL; + hpage_offset /= 4; - for (i=0; i < HW_PAGE_SIZE / 4; i++) - if ((page[i] & 0xff0007ff) == INS_DCBZ) { - page[i] &= 0xfffffff7; // reserved instruction, so we trap - touched = true; - } + get_page(hpage); + page = kmap_atomic(hpage, KM_USER0); - if (touched) - copy_to_user((void __user *)hpage, page, HW_PAGE_SIZE); + /* patch dcbz into reserved instruction, so we trap */ + for (i=hpage_offset; i < hpage_offset + (HW_PAGE_SIZE / 4); i++) + if ((page[i] & 0xff0007ff) == INS_DCBZ) + page[i] &= 0xfffffff7; -out: - vfree(page); + kunmap_atomic(page, KM_USER0); + put_page(hpage); } static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data, @@ -391,15 +444,7 @@ static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data, } else { pte->eaddr = eaddr; pte->raddr = eaddr & 0xffffffff; - pte->vpage = eaddr >> 12; - switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) { - case 0: - pte->vpage |= VSID_REAL; - case MSR_DR: - pte->vpage |= VSID_REAL_DR; - case MSR_IR: - pte->vpage |= VSID_REAL_IR; - } + pte->vpage = VSID_REAL | eaddr >> 12; pte->may_read = true; pte->may_write = true; pte->may_execute = true; @@ -434,55 +479,55 @@ err: return kvmppc_bad_hva(); } -int kvmppc_st(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr) +int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, + bool data) { struct kvmppc_pte pte; - hva_t hva = eaddr; vcpu->stat.st++; - if (kvmppc_xlate(vcpu, eaddr, false, &pte)) - goto err; + if (kvmppc_xlate(vcpu, *eaddr, data, &pte)) + return -ENOENT; - hva = kvmppc_pte_to_hva(vcpu, &pte, false); - if (kvm_is_error_hva(hva)) - goto err; + *eaddr = pte.raddr; - if (copy_to_user((void __user *)hva, ptr, size)) { - printk(KERN_INFO "kvmppc_st at 0x%lx failed\n", hva); - goto err; - } + if (!pte.may_write) + return -EPERM; - return 0; + if (kvm_write_guest(vcpu->kvm, pte.raddr, ptr, size)) + return EMULATE_DO_MMIO; -err: - return -ENOENT; + return EMULATE_DONE; } -int kvmppc_ld(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr, +int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data) { struct kvmppc_pte pte; - hva_t hva = eaddr; + hva_t hva = *eaddr; vcpu->stat.ld++; - if (kvmppc_xlate(vcpu, eaddr, data, &pte)) - goto err; + if (kvmppc_xlate(vcpu, *eaddr, data, &pte)) + goto nopte; + + *eaddr = pte.raddr; hva = kvmppc_pte_to_hva(vcpu, &pte, true); if (kvm_is_error_hva(hva)) - goto err; + goto mmio; if (copy_from_user(ptr, (void __user *)hva, size)) { printk(KERN_INFO "kvmppc_ld at 0x%lx failed\n", hva); - goto err; + goto mmio; } - return 0; + return EMULATE_DONE; -err: +nopte: return -ENOENT; +mmio: + return EMULATE_DO_MMIO; } static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) @@ -499,12 +544,11 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, int page_found = 0; struct kvmppc_pte pte; bool is_mmio = false; + bool dr = (vcpu->arch.msr & MSR_DR) ? true : false; + bool ir = (vcpu->arch.msr & MSR_IR) ? true : false; + u64 vsid; - if ( vec == BOOK3S_INTERRUPT_DATA_STORAGE ) { - relocated = (vcpu->arch.msr & MSR_DR); - } else { - relocated = (vcpu->arch.msr & MSR_IR); - } + relocated = data ? dr : ir; /* Resolve real address if translation turned on */ if (relocated) { @@ -516,14 +560,25 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, pte.raddr = eaddr & 0xffffffff; pte.eaddr = eaddr; pte.vpage = eaddr >> 12; - switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) { - case 0: - pte.vpage |= VSID_REAL; - case MSR_DR: - pte.vpage |= VSID_REAL_DR; - case MSR_IR: - pte.vpage |= VSID_REAL_IR; - } + } + + switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) { + case 0: + pte.vpage |= ((u64)VSID_REAL << (SID_SHIFT - 12)); + break; + case MSR_DR: + case MSR_IR: + vcpu->arch.mmu.esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid); + + if ((vcpu->arch.msr & (MSR_DR|MSR_IR)) == MSR_DR) + pte.vpage |= ((u64)VSID_REAL_DR << (SID_SHIFT - 12)); + else + pte.vpage |= ((u64)VSID_REAL_IR << (SID_SHIFT - 12)); + pte.vpage |= vsid; + + if (vsid == -1) + page_found = -EINVAL; + break; } if (vcpu->arch.mmu.is_dcbz32(vcpu) && @@ -538,20 +593,20 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, if (page_found == -ENOENT) { /* Page not found in guest PTE entries */ - vcpu->arch.dear = vcpu->arch.fault_dear; - to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr; - vcpu->arch.msr |= (vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL); + vcpu->arch.dear = kvmppc_get_fault_dar(vcpu); + to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr; + vcpu->arch.msr |= (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL); kvmppc_book3s_queue_irqprio(vcpu, vec); } else if (page_found == -EPERM) { /* Storage protection */ - vcpu->arch.dear = vcpu->arch.fault_dear; - to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr & ~DSISR_NOHPTE; + vcpu->arch.dear = kvmppc_get_fault_dar(vcpu); + to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE; to_book3s(vcpu)->dsisr |= DSISR_PROTFAULT; - vcpu->arch.msr |= (vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL); + vcpu->arch.msr |= (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL); kvmppc_book3s_queue_irqprio(vcpu, vec); } else if (page_found == -EINVAL) { /* Page not found in guest SLB */ - vcpu->arch.dear = vcpu->arch.fault_dear; + vcpu->arch.dear = kvmppc_get_fault_dar(vcpu); kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80); } else if (!is_mmio && kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) { @@ -583,11 +638,13 @@ static inline int get_fpr_index(int i) } /* Give up external provider (FPU, Altivec, VSX) */ -static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr) +void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr) { struct thread_struct *t = ¤t->thread; u64 *vcpu_fpr = vcpu->arch.fpr; +#ifdef CONFIG_VSX u64 *vcpu_vsx = vcpu->arch.vsr; +#endif u64 *thread_fpr = (u64*)t->fpr; int i; @@ -629,21 +686,65 @@ static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr) kvmppc_recalc_shadow_msr(vcpu); } +static int kvmppc_read_inst(struct kvm_vcpu *vcpu) +{ + ulong srr0 = kvmppc_get_pc(vcpu); + u32 last_inst = kvmppc_get_last_inst(vcpu); + int ret; + + ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false); + if (ret == -ENOENT) { + vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 33, 33, 1); + vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 34, 36, 0); + vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 42, 47, 0); + kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_STORAGE); + return EMULATE_AGAIN; + } + + return EMULATE_DONE; +} + +static int kvmppc_check_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr) +{ + + /* Need to do paired single emulation? */ + if (!(vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)) + return EMULATE_DONE; + + /* Read out the instruction */ + if (kvmppc_read_inst(vcpu) == EMULATE_DONE) + /* Need to emulate */ + return EMULATE_FAIL; + + return EMULATE_AGAIN; +} + /* Handle external providers (FPU, Altivec, VSX) */ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr, ulong msr) { struct thread_struct *t = ¤t->thread; u64 *vcpu_fpr = vcpu->arch.fpr; +#ifdef CONFIG_VSX u64 *vcpu_vsx = vcpu->arch.vsr; +#endif u64 *thread_fpr = (u64*)t->fpr; int i; + /* When we have paired singles, we emulate in software */ + if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE) + return RESUME_GUEST; + if (!(vcpu->arch.msr & msr)) { kvmppc_book3s_queue_irqprio(vcpu, exit_nr); return RESUME_GUEST; } + /* We already own the ext */ + if (vcpu->arch.guest_owned_ext & msr) { + return RESUME_GUEST; + } + #ifdef DEBUG_EXT printk(KERN_INFO "Loading up ext 0x%lx\n", msr); #endif @@ -696,21 +797,33 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, run->ready_for_interrupt_injection = 1; #ifdef EXIT_DEBUG printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | dec=0x%x | msr=0x%lx\n", - exit_nr, vcpu->arch.pc, vcpu->arch.fault_dear, - kvmppc_get_dec(vcpu), vcpu->arch.msr); + exit_nr, kvmppc_get_pc(vcpu), kvmppc_get_fault_dar(vcpu), + kvmppc_get_dec(vcpu), to_svcpu(vcpu)->shadow_srr1); #elif defined (EXIT_DEBUG_SIMPLE) if ((exit_nr != 0x900) && (exit_nr != 0x500)) printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | msr=0x%lx\n", - exit_nr, vcpu->arch.pc, vcpu->arch.fault_dear, + exit_nr, kvmppc_get_pc(vcpu), kvmppc_get_fault_dar(vcpu), vcpu->arch.msr); #endif kvm_resched(vcpu); switch (exit_nr) { case BOOK3S_INTERRUPT_INST_STORAGE: vcpu->stat.pf_instruc++; + +#ifdef CONFIG_PPC_BOOK3S_32 + /* We set segments as unused segments when invalidating them. So + * treat the respective fault as segment fault. */ + if (to_svcpu(vcpu)->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT] + == SR_INVALID) { + kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)); + r = RESUME_GUEST; + break; + } +#endif + /* only care about PTEG not found errors, but leave NX alone */ - if (vcpu->arch.shadow_srr1 & 0x40000000) { - r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.pc, exit_nr); + if (to_svcpu(vcpu)->shadow_srr1 & 0x40000000) { + r = kvmppc_handle_pagefault(run, vcpu, kvmppc_get_pc(vcpu), exit_nr); vcpu->stat.sp_instruc++; } else if (vcpu->arch.mmu.is_dcbz32(vcpu) && (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) { @@ -719,37 +832,52 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, * so we can't use the NX bit inside the guest. Let's cross our fingers, * that no guest that needs the dcbz hack does NX. */ - kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL); + kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL); + r = RESUME_GUEST; } else { - vcpu->arch.msr |= vcpu->arch.shadow_srr1 & 0x58000000; + vcpu->arch.msr |= to_svcpu(vcpu)->shadow_srr1 & 0x58000000; kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL); + kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL); r = RESUME_GUEST; } break; case BOOK3S_INTERRUPT_DATA_STORAGE: + { + ulong dar = kvmppc_get_fault_dar(vcpu); vcpu->stat.pf_storage++; + +#ifdef CONFIG_PPC_BOOK3S_32 + /* We set segments as unused segments when invalidating them. So + * treat the respective fault as segment fault. */ + if ((to_svcpu(vcpu)->sr[dar >> SID_SHIFT]) == SR_INVALID) { + kvmppc_mmu_map_segment(vcpu, dar); + r = RESUME_GUEST; + break; + } +#endif + /* The only case we need to handle is missing shadow PTEs */ - if (vcpu->arch.fault_dsisr & DSISR_NOHPTE) { - r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.fault_dear, exit_nr); + if (to_svcpu(vcpu)->fault_dsisr & DSISR_NOHPTE) { + r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr); } else { - vcpu->arch.dear = vcpu->arch.fault_dear; - to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr; + vcpu->arch.dear = dar; + to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr; kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - kvmppc_mmu_pte_flush(vcpu, vcpu->arch.dear, ~0xFFFULL); + kvmppc_mmu_pte_flush(vcpu, vcpu->arch.dear, ~0xFFFUL); r = RESUME_GUEST; } break; + } case BOOK3S_INTERRUPT_DATA_SEGMENT: - if (kvmppc_mmu_map_segment(vcpu, vcpu->arch.fault_dear) < 0) { - vcpu->arch.dear = vcpu->arch.fault_dear; + if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_fault_dar(vcpu)) < 0) { + vcpu->arch.dear = kvmppc_get_fault_dar(vcpu); kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_SEGMENT); } r = RESUME_GUEST; break; case BOOK3S_INTERRUPT_INST_SEGMENT: - if (kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc) < 0) { + if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)) < 0) { kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_SEGMENT); } @@ -764,18 +892,22 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->stat.ext_intr_exits++; r = RESUME_GUEST; break; + case BOOK3S_INTERRUPT_PERFMON: + r = RESUME_GUEST; + break; case BOOK3S_INTERRUPT_PROGRAM: { enum emulation_result er; ulong flags; - flags = vcpu->arch.shadow_srr1 & 0x1f0000ull; +program_interrupt: + flags = to_svcpu(vcpu)->shadow_srr1 & 0x1f0000ull; if (vcpu->arch.msr & MSR_PR) { #ifdef EXIT_DEBUG - printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", vcpu->arch.pc, vcpu->arch.last_inst); + printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu)); #endif - if ((vcpu->arch.last_inst & 0xff0007ff) != + if ((kvmppc_get_last_inst(vcpu) & 0xff0007ff) != (INS_DCBZ & 0xfffffff7)) { kvmppc_core_queue_program(vcpu, flags); r = RESUME_GUEST; @@ -789,33 +921,80 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, case EMULATE_DONE: r = RESUME_GUEST_NV; break; + case EMULATE_AGAIN: + r = RESUME_GUEST; + break; case EMULATE_FAIL: printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n", - __func__, vcpu->arch.pc, vcpu->arch.last_inst); + __func__, kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu)); kvmppc_core_queue_program(vcpu, flags); r = RESUME_GUEST; break; + case EMULATE_DO_MMIO: + run->exit_reason = KVM_EXIT_MMIO; + r = RESUME_HOST_NV; + break; default: BUG(); } break; } case BOOK3S_INTERRUPT_SYSCALL: -#ifdef EXIT_DEBUG - printk(KERN_INFO "Syscall Nr %d\n", (int)kvmppc_get_gpr(vcpu, 0)); -#endif - vcpu->stat.syscall_exits++; - kvmppc_book3s_queue_irqprio(vcpu, exit_nr); - r = RESUME_GUEST; + // XXX make user settable + if (vcpu->arch.osi_enabled && + (((u32)kvmppc_get_gpr(vcpu, 3)) == OSI_SC_MAGIC_R3) && + (((u32)kvmppc_get_gpr(vcpu, 4)) == OSI_SC_MAGIC_R4)) { + u64 *gprs = run->osi.gprs; + int i; + + run->exit_reason = KVM_EXIT_OSI; + for (i = 0; i < 32; i++) + gprs[i] = kvmppc_get_gpr(vcpu, i); + vcpu->arch.osi_needed = 1; + r = RESUME_HOST_NV; + + } else { + vcpu->stat.syscall_exits++; + kvmppc_book3s_queue_irqprio(vcpu, exit_nr); + r = RESUME_GUEST; + } break; case BOOK3S_INTERRUPT_FP_UNAVAIL: - r = kvmppc_handle_ext(vcpu, exit_nr, MSR_FP); - break; case BOOK3S_INTERRUPT_ALTIVEC: - r = kvmppc_handle_ext(vcpu, exit_nr, MSR_VEC); - break; case BOOK3S_INTERRUPT_VSX: - r = kvmppc_handle_ext(vcpu, exit_nr, MSR_VSX); + { + int ext_msr = 0; + + switch (exit_nr) { + case BOOK3S_INTERRUPT_FP_UNAVAIL: ext_msr = MSR_FP; break; + case BOOK3S_INTERRUPT_ALTIVEC: ext_msr = MSR_VEC; break; + case BOOK3S_INTERRUPT_VSX: ext_msr = MSR_VSX; break; + } + + switch (kvmppc_check_ext(vcpu, exit_nr)) { + case EMULATE_DONE: + /* everything ok - let's enable the ext */ + r = kvmppc_handle_ext(vcpu, exit_nr, ext_msr); + break; + case EMULATE_FAIL: + /* we need to emulate this instruction */ + goto program_interrupt; + break; + default: + /* nothing to worry about - go again */ + break; + } + break; + } + case BOOK3S_INTERRUPT_ALIGNMENT: + if (kvmppc_read_inst(vcpu) == EMULATE_DONE) { + to_book3s(vcpu)->dsisr = kvmppc_alignment_dsisr(vcpu, + kvmppc_get_last_inst(vcpu)); + vcpu->arch.dear = kvmppc_alignment_dar(vcpu, + kvmppc_get_last_inst(vcpu)); + kvmppc_book3s_queue_irqprio(vcpu, exit_nr); + } + r = RESUME_GUEST; break; case BOOK3S_INTERRUPT_MACHINE_CHECK: case BOOK3S_INTERRUPT_TRACE: @@ -825,7 +1004,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, default: /* Ugh - bork here! What did we get? */ printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n", - exit_nr, vcpu->arch.pc, vcpu->arch.shadow_srr1); + exit_nr, kvmppc_get_pc(vcpu), to_svcpu(vcpu)->shadow_srr1); r = RESUME_HOST; BUG(); break; @@ -852,7 +1031,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, } #ifdef EXIT_DEBUG - printk(KERN_EMERG "KVM exit: vcpu=0x%p pc=0x%lx r=0x%x\n", vcpu, vcpu->arch.pc, r); + printk(KERN_EMERG "KVM exit: vcpu=0x%p pc=0x%lx r=0x%x\n", vcpu, kvmppc_get_pc(vcpu), r); #endif return r; @@ -867,10 +1046,12 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; - regs->pc = vcpu->arch.pc; + vcpu_load(vcpu); + + regs->pc = kvmppc_get_pc(vcpu); regs->cr = kvmppc_get_cr(vcpu); - regs->ctr = vcpu->arch.ctr; - regs->lr = vcpu->arch.lr; + regs->ctr = kvmppc_get_ctr(vcpu); + regs->lr = kvmppc_get_lr(vcpu); regs->xer = kvmppc_get_xer(vcpu); regs->msr = vcpu->arch.msr; regs->srr0 = vcpu->arch.srr0; @@ -887,6 +1068,8 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) regs->gpr[i] = kvmppc_get_gpr(vcpu, i); + vcpu_put(vcpu); + return 0; } @@ -894,10 +1077,12 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; - vcpu->arch.pc = regs->pc; + vcpu_load(vcpu); + + kvmppc_set_pc(vcpu, regs->pc); kvmppc_set_cr(vcpu, regs->cr); - vcpu->arch.ctr = regs->ctr; - vcpu->arch.lr = regs->lr; + kvmppc_set_ctr(vcpu, regs->ctr); + kvmppc_set_lr(vcpu, regs->lr); kvmppc_set_xer(vcpu, regs->xer); kvmppc_set_msr(vcpu, regs->msr); vcpu->arch.srr0 = regs->srr0; @@ -913,6 +1098,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) kvmppc_set_gpr(vcpu, i, regs->gpr[i]); + vcpu_put(vcpu); + return 0; } @@ -1042,24 +1229,33 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) { struct kvmppc_vcpu_book3s *vcpu_book3s; struct kvm_vcpu *vcpu; - int err; + int err = -ENOMEM; - vcpu_book3s = (struct kvmppc_vcpu_book3s *)__get_free_pages( GFP_KERNEL | __GFP_ZERO, - get_order(sizeof(struct kvmppc_vcpu_book3s))); - if (!vcpu_book3s) { - err = -ENOMEM; + vcpu_book3s = vmalloc(sizeof(struct kvmppc_vcpu_book3s)); + if (!vcpu_book3s) goto out; - } + + memset(vcpu_book3s, 0, sizeof(struct kvmppc_vcpu_book3s)); + + vcpu_book3s->shadow_vcpu = (struct kvmppc_book3s_shadow_vcpu *) + kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL); + if (!vcpu_book3s->shadow_vcpu) + goto free_vcpu; vcpu = &vcpu_book3s->vcpu; err = kvm_vcpu_init(vcpu, kvm, id); if (err) - goto free_vcpu; + goto free_shadow_vcpu; vcpu->arch.host_retip = kvm_return_point; vcpu->arch.host_msr = mfmsr(); +#ifdef CONFIG_PPC_BOOK3S_64 /* default to book3s_64 (970fx) */ vcpu->arch.pvr = 0x3C0301; +#else + /* default to book3s_32 (750) */ + vcpu->arch.pvr = 0x84202; +#endif kvmppc_set_pvr(vcpu, vcpu->arch.pvr); vcpu_book3s->slb_nr = 64; @@ -1067,23 +1263,24 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) vcpu->arch.trampoline_lowmem = kvmppc_trampoline_lowmem; vcpu->arch.trampoline_enter = kvmppc_trampoline_enter; vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem; +#ifdef CONFIG_PPC_BOOK3S_64 vcpu->arch.rmcall = *(ulong*)kvmppc_rmcall; +#else + vcpu->arch.rmcall = (ulong)kvmppc_rmcall; +#endif vcpu->arch.shadow_msr = MSR_USER64; - err = __init_new_context(); + err = kvmppc_mmu_init(vcpu); if (err < 0) - goto free_vcpu; - vcpu_book3s->context_id = err; - - vcpu_book3s->vsid_max = ((vcpu_book3s->context_id + 1) << USER_ESID_BITS) - 1; - vcpu_book3s->vsid_first = vcpu_book3s->context_id << USER_ESID_BITS; - vcpu_book3s->vsid_next = vcpu_book3s->vsid_first; + goto free_shadow_vcpu; return vcpu; +free_shadow_vcpu: + kfree(vcpu_book3s->shadow_vcpu); free_vcpu: - free_pages((long)vcpu_book3s, get_order(sizeof(struct kvmppc_vcpu_book3s))); + vfree(vcpu_book3s); out: return ERR_PTR(err); } @@ -1092,9 +1289,9 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); - __destroy_context(vcpu_book3s->context_id); kvm_vcpu_uninit(vcpu); - free_pages((long)vcpu_book3s, get_order(sizeof(struct kvmppc_vcpu_book3s))); + kfree(vcpu_book3s->shadow_vcpu); + vfree(vcpu_book3s); } extern int __kvmppc_vcpu_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); @@ -1102,8 +1299,12 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) { int ret; struct thread_struct ext_bkp; +#ifdef CONFIG_ALTIVEC bool save_vec = current->thread.used_vr; +#endif +#ifdef CONFIG_VSX bool save_vsx = current->thread.used_vsr; +#endif ulong ext_msr; /* No need to go into the guest when all we do is going out */ @@ -1144,6 +1345,10 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) /* XXX we get called with irq disabled - change that! */ local_irq_enable(); + /* Preload FPU if it's enabled */ + if (vcpu->arch.msr & MSR_FP) + kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP); + ret = __kvmppc_vcpu_entry(kvm_run, vcpu); local_irq_disable(); diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index faf99f20d993..0b10503c8a4a 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -37,7 +37,7 @@ #define dprintk(X...) do { } while(0) #endif -#ifdef DEBUG_PTE +#ifdef DEBUG_MMU_PTE #define dprintk_pte(X...) printk(KERN_INFO X) #else #define dprintk_pte(X...) do { } while(0) @@ -45,6 +45,9 @@ #define PTEG_FLAG_ACCESSED 0x00000100 #define PTEG_FLAG_DIRTY 0x00000080 +#ifndef SID_SHIFT +#define SID_SHIFT 28 +#endif static inline bool check_debug_ip(struct kvm_vcpu *vcpu) { @@ -57,6 +60,8 @@ static inline bool check_debug_ip(struct kvm_vcpu *vcpu) static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *pte, bool data); +static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid, + u64 *vsid); static struct kvmppc_sr *find_sr(struct kvmppc_vcpu_book3s *vcpu_book3s, gva_t eaddr) { @@ -66,13 +71,14 @@ static struct kvmppc_sr *find_sr(struct kvmppc_vcpu_book3s *vcpu_book3s, gva_t e static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr, bool data) { - struct kvmppc_sr *sre = find_sr(to_book3s(vcpu), eaddr); + u64 vsid; struct kvmppc_pte pte; if (!kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, &pte, data)) return pte.vpage; - return (((u64)eaddr >> 12) & 0xffff) | (((u64)sre->vsid) << 16); + kvmppc_mmu_book3s_32_esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid); + return (((u64)eaddr >> 12) & 0xffff) | (vsid << 16); } static void kvmppc_mmu_book3s_32_reset_msr(struct kvm_vcpu *vcpu) @@ -142,8 +148,13 @@ static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr, bat->bepi_mask); } if ((eaddr & bat->bepi_mask) == bat->bepi) { + u64 vsid; + kvmppc_mmu_book3s_32_esid_to_vsid(vcpu, + eaddr >> SID_SHIFT, &vsid); + vsid <<= 16; + pte->vpage = (((u64)eaddr >> 12) & 0xffff) | vsid; + pte->raddr = bat->brpn | (eaddr & ~bat->bepi_mask); - pte->vpage = (eaddr >> 12) | VSID_BAT; pte->may_read = bat->pp; pte->may_write = bat->pp > 1; pte->may_execute = true; @@ -172,7 +183,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_sr *sre; hva_t ptegp; u32 pteg[16]; - u64 ptem = 0; + u32 ptem = 0; int i; int found = 0; @@ -302,6 +313,7 @@ static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum, /* And then put in the new SR */ sre->raw = value; sre->vsid = (value & 0x0fffffff); + sre->valid = (value & 0x80000000) ? false : true; sre->Ks = (value & 0x40000000) ? true : false; sre->Kp = (value & 0x20000000) ? true : false; sre->nx = (value & 0x10000000) ? true : false; @@ -312,36 +324,48 @@ static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum, static void kvmppc_mmu_book3s_32_tlbie(struct kvm_vcpu *vcpu, ulong ea, bool large) { - kvmppc_mmu_pte_flush(vcpu, ea, ~0xFFFULL); + kvmppc_mmu_pte_flush(vcpu, ea, 0x0FFFF000); } -static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, u64 esid, +static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid, u64 *vsid) { + ulong ea = esid << SID_SHIFT; + struct kvmppc_sr *sr; + u64 gvsid = esid; + + if (vcpu->arch.msr & (MSR_DR|MSR_IR)) { + sr = find_sr(to_book3s(vcpu), ea); + if (sr->valid) + gvsid = sr->vsid; + } + /* In case we only have one of MSR_IR or MSR_DR set, let's put that in the real-mode context (and hope RM doesn't access high memory) */ switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) { case 0: - *vsid = (VSID_REAL >> 16) | esid; + *vsid = VSID_REAL | esid; break; case MSR_IR: - *vsid = (VSID_REAL_IR >> 16) | esid; + *vsid = VSID_REAL_IR | gvsid; break; case MSR_DR: - *vsid = (VSID_REAL_DR >> 16) | esid; + *vsid = VSID_REAL_DR | gvsid; break; case MSR_DR|MSR_IR: - { - ulong ea; - ea = esid << SID_SHIFT; - *vsid = find_sr(to_book3s(vcpu), ea)->vsid; + if (!sr->valid) + return -1; + + *vsid = sr->vsid; break; - } default: BUG(); } + if (vcpu->arch.msr & MSR_PR) + *vsid |= VSID_PR; + return 0; } diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c new file mode 100644 index 000000000000..0bb66005338f --- /dev/null +++ b/arch/powerpc/kvm/book3s_32_mmu_host.c @@ -0,0 +1,483 @@ +/* + * Copyright (C) 2010 SUSE Linux Products GmbH. All rights reserved. + * + * Authors: + * Alexander Graf <agraf@suse.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#include <linux/kvm_host.h> + +#include <asm/kvm_ppc.h> +#include <asm/kvm_book3s.h> +#include <asm/mmu-hash32.h> +#include <asm/machdep.h> +#include <asm/mmu_context.h> +#include <asm/hw_irq.h> + +/* #define DEBUG_MMU */ +/* #define DEBUG_SR */ + +#ifdef DEBUG_MMU +#define dprintk_mmu(a, ...) printk(KERN_INFO a, __VA_ARGS__) +#else +#define dprintk_mmu(a, ...) do { } while(0) +#endif + +#ifdef DEBUG_SR +#define dprintk_sr(a, ...) printk(KERN_INFO a, __VA_ARGS__) +#else +#define dprintk_sr(a, ...) do { } while(0) +#endif + +#if PAGE_SHIFT != 12 +#error Unknown page size +#endif + +#ifdef CONFIG_SMP +#error XXX need to grab mmu_hash_lock +#endif + +#ifdef CONFIG_PTE_64BIT +#error Only 32 bit pages are supported for now +#endif + +static ulong htab; +static u32 htabmask; + +static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte) +{ + volatile u32 *pteg; + + dprintk_mmu("KVM: Flushing SPTE: 0x%llx (0x%llx) -> 0x%llx\n", + pte->pte.eaddr, pte->pte.vpage, pte->host_va); + + pteg = (u32*)pte->slot; + + pteg[0] = 0; + asm volatile ("sync"); + asm volatile ("tlbie %0" : : "r" (pte->pte.eaddr) : "memory"); + asm volatile ("sync"); + asm volatile ("tlbsync"); + + pte->host_va = 0; + + if (pte->pte.may_write) + kvm_release_pfn_dirty(pte->pfn); + else + kvm_release_pfn_clean(pte->pfn); +} + +void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask) +{ + int i; + + dprintk_mmu("KVM: Flushing %d Shadow PTEs: 0x%x & 0x%x\n", + vcpu->arch.hpte_cache_offset, guest_ea, ea_mask); + BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM); + + guest_ea &= ea_mask; + for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) { + struct hpte_cache *pte; + + pte = &vcpu->arch.hpte_cache[i]; + if (!pte->host_va) + continue; + + if ((pte->pte.eaddr & ea_mask) == guest_ea) { + invalidate_pte(vcpu, pte); + } + } + + /* Doing a complete flush -> start from scratch */ + if (!ea_mask) + vcpu->arch.hpte_cache_offset = 0; +} + +void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask) +{ + int i; + + dprintk_mmu("KVM: Flushing %d Shadow vPTEs: 0x%llx & 0x%llx\n", + vcpu->arch.hpte_cache_offset, guest_vp, vp_mask); + BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM); + + guest_vp &= vp_mask; + for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) { + struct hpte_cache *pte; + + pte = &vcpu->arch.hpte_cache[i]; + if (!pte->host_va) + continue; + + if ((pte->pte.vpage & vp_mask) == guest_vp) { + invalidate_pte(vcpu, pte); + } + } +} + +void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end) +{ + int i; + + dprintk_mmu("KVM: Flushing %d Shadow pPTEs: 0x%llx & 0x%llx\n", + vcpu->arch.hpte_cache_offset, pa_start, pa_end); + BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM); + + for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) { + struct hpte_cache *pte; + + pte = &vcpu->arch.hpte_cache[i]; + if (!pte->host_va) + continue; + + if ((pte->pte.raddr >= pa_start) && + (pte->pte.raddr < pa_end)) { + invalidate_pte(vcpu, pte); + } + } +} + +struct kvmppc_pte *kvmppc_mmu_find_pte(struct kvm_vcpu *vcpu, u64 ea, bool data) +{ + int i; + u64 guest_vp; + + guest_vp = vcpu->arch.mmu.ea_to_vp(vcpu, ea, false); + for (i=0; i<vcpu->arch.hpte_cache_offset; i++) { + struct hpte_cache *pte; + + pte = &vcpu->arch.hpte_cache[i]; + if (!pte->host_va) + continue; + + if (pte->pte.vpage == guest_vp) + return &pte->pte; + } + + return NULL; +} + +static int kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.hpte_cache_offset == HPTEG_CACHE_NUM) + kvmppc_mmu_pte_flush(vcpu, 0, 0); + + return vcpu->arch.hpte_cache_offset++; +} + +/* We keep 512 gvsid->hvsid entries, mapping the guest ones to the array using + * a hash, so we don't waste cycles on looping */ +static u16 kvmppc_sid_hash(struct kvm_vcpu *vcpu, u64 gvsid) +{ + return (u16)(((gvsid >> (SID_MAP_BITS * 7)) & SID_MAP_MASK) ^ + ((gvsid >> (SID_MAP_BITS * 6)) & SID_MAP_MASK) ^ + ((gvsid >> (SID_MAP_BITS * 5)) & SID_MAP_MASK) ^ + ((gvsid >> (SID_MAP_BITS * 4)) & SID_MAP_MASK) ^ + ((gvsid >> (SID_MAP_BITS * 3)) & SID_MAP_MASK) ^ + ((gvsid >> (SID_MAP_BITS * 2)) & SID_MAP_MASK) ^ + ((gvsid >> (SID_MAP_BITS * 1)) & SID_MAP_MASK) ^ + ((gvsid >> (SID_MAP_BITS * 0)) & SID_MAP_MASK)); +} + + +static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid) +{ + struct kvmppc_sid_map *map; + u16 sid_map_mask; + + if (vcpu->arch.msr & MSR_PR) + gvsid |= VSID_PR; + + sid_map_mask = kvmppc_sid_hash(vcpu, gvsid); + map = &to_book3s(vcpu)->sid_map[sid_map_mask]; + if (map->guest_vsid == gvsid) { + dprintk_sr("SR: Searching 0x%llx -> 0x%llx\n", + gvsid, map->host_vsid); + return map; + } + + map = &to_book3s(vcpu)->sid_map[SID_MAP_MASK - sid_map_mask]; + if (map->guest_vsid == gvsid) { + dprintk_sr("SR: Searching 0x%llx -> 0x%llx\n", + gvsid, map->host_vsid); + return map; + } + + dprintk_sr("SR: Searching 0x%llx -> not found\n", gvsid); + return NULL; +} + +static u32 *kvmppc_mmu_get_pteg(struct kvm_vcpu *vcpu, u32 vsid, u32 eaddr, + bool primary) +{ + u32 page, hash; + ulong pteg = htab; + + page = (eaddr & ~ESID_MASK) >> 12; + + hash = ((vsid ^ page) << 6); + if (!primary) + hash = ~hash; + + hash &= htabmask; + + pteg |= hash; + + dprintk_mmu("htab: %lx | hash: %x | htabmask: %x | pteg: %lx\n", + htab, hash, htabmask, pteg); + + return (u32*)pteg; +} + +extern char etext[]; + +int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte) +{ + pfn_t hpaddr; + u64 va; + u64 vsid; + struct kvmppc_sid_map *map; + volatile u32 *pteg; + u32 eaddr = orig_pte->eaddr; + u32 pteg0, pteg1; + register int rr = 0; + bool primary = false; + bool evict = false; + int hpte_id; + struct hpte_cache *pte; + + /* Get host physical address for gpa */ + hpaddr = gfn_to_pfn(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT); + if (kvm_is_error_hva(hpaddr)) { + printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", + orig_pte->eaddr); + return -EINVAL; + } + hpaddr <<= PAGE_SHIFT; + + /* and write the mapping ea -> hpa into the pt */ + vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid); + map = find_sid_vsid(vcpu, vsid); + if (!map) { + kvmppc_mmu_map_segment(vcpu, eaddr); + map = find_sid_vsid(vcpu, vsid); + } + BUG_ON(!map); + + vsid = map->host_vsid; + va = (vsid << SID_SHIFT) | (eaddr & ~ESID_MASK); + +next_pteg: + if (rr == 16) { + primary = !primary; + evict = true; + rr = 0; + } + + pteg = kvmppc_mmu_get_pteg(vcpu, vsid, eaddr, primary); + + /* not evicting yet */ + if (!evict && (pteg[rr] & PTE_V)) { + rr += 2; + goto next_pteg; + } + + dprintk_mmu("KVM: old PTEG: %p (%d)\n", pteg, rr); + dprintk_mmu("KVM: %08x - %08x\n", pteg[0], pteg[1]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[2], pteg[3]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[4], pteg[5]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[6], pteg[7]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[8], pteg[9]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[10], pteg[11]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[12], pteg[13]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[14], pteg[15]); + + pteg0 = ((eaddr & 0x0fffffff) >> 22) | (vsid << 7) | PTE_V | + (primary ? 0 : PTE_SEC); + pteg1 = hpaddr | PTE_M | PTE_R | PTE_C; + + if (orig_pte->may_write) { + pteg1 |= PP_RWRW; + mark_page_dirty(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT); + } else { + pteg1 |= PP_RWRX; + } + + local_irq_disable(); + + if (pteg[rr]) { + pteg[rr] = 0; + asm volatile ("sync"); + } + pteg[rr + 1] = pteg1; + pteg[rr] = pteg0; + asm volatile ("sync"); + + local_irq_enable(); + + dprintk_mmu("KVM: new PTEG: %p\n", pteg); + dprintk_mmu("KVM: %08x - %08x\n", pteg[0], pteg[1]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[2], pteg[3]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[4], pteg[5]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[6], pteg[7]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[8], pteg[9]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[10], pteg[11]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[12], pteg[13]); + dprintk_mmu("KVM: %08x - %08x\n", pteg[14], pteg[15]); + + + /* Now tell our Shadow PTE code about the new page */ + + hpte_id = kvmppc_mmu_hpte_cache_next(vcpu); + pte = &vcpu->arch.hpte_cache[hpte_id]; + + dprintk_mmu("KVM: %c%c Map 0x%llx: [%lx] 0x%llx (0x%llx) -> %lx\n", + orig_pte->may_write ? 'w' : '-', + orig_pte->may_execute ? 'x' : '-', + orig_pte->eaddr, (ulong)pteg, va, + orig_pte->vpage, hpaddr); + + pte->slot = (ulong)&pteg[rr]; + pte->host_va = va; + pte->pte = *orig_pte; + pte->pfn = hpaddr >> PAGE_SHIFT; + + return 0; +} + +static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid) +{ + struct kvmppc_sid_map *map; + struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); + u16 sid_map_mask; + static int backwards_map = 0; + + if (vcpu->arch.msr & MSR_PR) + gvsid |= VSID_PR; + + /* We might get collisions that trap in preceding order, so let's + map them differently */ + + sid_map_mask = kvmppc_sid_hash(vcpu, gvsid); + if (backwards_map) + sid_map_mask = SID_MAP_MASK - sid_map_mask; + + map = &to_book3s(vcpu)->sid_map[sid_map_mask]; + + /* Make sure we're taking the other map next time */ + backwards_map = !backwards_map; + + /* Uh-oh ... out of mappings. Let's flush! */ + if (vcpu_book3s->vsid_next >= vcpu_book3s->vsid_max) { + vcpu_book3s->vsid_next = vcpu_book3s->vsid_first; + memset(vcpu_book3s->sid_map, 0, + sizeof(struct kvmppc_sid_map) * SID_MAP_NUM); + kvmppc_mmu_pte_flush(vcpu, 0, 0); + kvmppc_mmu_flush_segments(vcpu); + } + map->host_vsid = vcpu_book3s->vsid_next; + + /* Would have to be 111 to be completely aligned with the rest of + Linux, but that is just way too little space! */ + vcpu_book3s->vsid_next+=1; + + map->guest_vsid = gvsid; + map->valid = true; + + return map; +} + +int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr) +{ + u32 esid = eaddr >> SID_SHIFT; + u64 gvsid; + u32 sr; + struct kvmppc_sid_map *map; + struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu); + + if (vcpu->arch.mmu.esid_to_vsid(vcpu, esid, &gvsid)) { + /* Invalidate an entry */ + svcpu->sr[esid] = SR_INVALID; + return -ENOENT; + } + + map = find_sid_vsid(vcpu, gvsid); + if (!map) + map = create_sid_map(vcpu, gvsid); + + map->guest_esid = esid; + sr = map->host_vsid | SR_KP; + svcpu->sr[esid] = sr; + + dprintk_sr("MMU: mtsr %d, 0x%x\n", esid, sr); + + return 0; +} + +void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu) +{ + int i; + struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu); + + dprintk_sr("MMU: flushing all segments (%d)\n", ARRAY_SIZE(svcpu->sr)); + for (i = 0; i < ARRAY_SIZE(svcpu->sr); i++) + svcpu->sr[i] = SR_INVALID; +} + +void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) +{ + kvmppc_mmu_pte_flush(vcpu, 0, 0); + preempt_disable(); + __destroy_context(to_book3s(vcpu)->context_id); + preempt_enable(); +} + +/* From mm/mmu_context_hash32.c */ +#define CTX_TO_VSID(ctx) (((ctx) * (897 * 16)) & 0xffffff) + +int kvmppc_mmu_init(struct kvm_vcpu *vcpu) +{ + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); + int err; + ulong sdr1; + + err = __init_new_context(); + if (err < 0) + return -1; + vcpu3s->context_id = err; + + vcpu3s->vsid_max = CTX_TO_VSID(vcpu3s->context_id + 1) - 1; + vcpu3s->vsid_first = CTX_TO_VSID(vcpu3s->context_id); + +#if 0 /* XXX still doesn't guarantee uniqueness */ + /* We could collide with the Linux vsid space because the vsid + * wraps around at 24 bits. We're safe if we do our own space + * though, so let's always set the highest bit. */ + + vcpu3s->vsid_max |= 0x00800000; + vcpu3s->vsid_first |= 0x00800000; +#endif + BUG_ON(vcpu3s->vsid_max < vcpu3s->vsid_first); + + vcpu3s->vsid_next = vcpu3s->vsid_first; + + /* Remember where the HTAB is */ + asm ( "mfsdr1 %0" : "=r"(sdr1) ); + htabmask = ((sdr1 & 0x1FF) << 16) | 0xFFC0; + htab = (ulong)__va(sdr1 & 0xffff0000); + + return 0; +} diff --git a/arch/powerpc/kvm/book3s_32_sr.S b/arch/powerpc/kvm/book3s_32_sr.S new file mode 100644 index 000000000000..3608471ad2d8 --- /dev/null +++ b/arch/powerpc/kvm/book3s_32_sr.S @@ -0,0 +1,143 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright SUSE Linux Products GmbH 2009 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +/****************************************************************************** + * * + * Entry code * + * * + *****************************************************************************/ + +.macro LOAD_GUEST_SEGMENTS + + /* Required state: + * + * MSR = ~IR|DR + * R1 = host R1 + * R2 = host R2 + * R3 = shadow vcpu + * all other volatile GPRS = free + * SVCPU[CR] = guest CR + * SVCPU[XER] = guest XER + * SVCPU[CTR] = guest CTR + * SVCPU[LR] = guest LR + */ + +#define XCHG_SR(n) lwz r9, (SVCPU_SR+(n*4))(r3); \ + mtsr n, r9 + + XCHG_SR(0) + XCHG_SR(1) + XCHG_SR(2) + XCHG_SR(3) + XCHG_SR(4) + XCHG_SR(5) + XCHG_SR(6) + XCHG_SR(7) + XCHG_SR(8) + XCHG_SR(9) + XCHG_SR(10) + XCHG_SR(11) + XCHG_SR(12) + XCHG_SR(13) + XCHG_SR(14) + XCHG_SR(15) + + /* Clear BATs. */ + +#define KVM_KILL_BAT(n, reg) \ + mtspr SPRN_IBAT##n##U,reg; \ + mtspr SPRN_IBAT##n##L,reg; \ + mtspr SPRN_DBAT##n##U,reg; \ + mtspr SPRN_DBAT##n##L,reg; \ + + li r9, 0 + KVM_KILL_BAT(0, r9) + KVM_KILL_BAT(1, r9) + KVM_KILL_BAT(2, r9) + KVM_KILL_BAT(3, r9) + +.endm + +/****************************************************************************** + * * + * Exit code * + * * + *****************************************************************************/ + +.macro LOAD_HOST_SEGMENTS + + /* Register usage at this point: + * + * R1 = host R1 + * R2 = host R2 + * R12 = exit handler id + * R13 = shadow vcpu - SHADOW_VCPU_OFF + * SVCPU.* = guest * + * SVCPU[CR] = guest CR + * SVCPU[XER] = guest XER + * SVCPU[CTR] = guest CTR + * SVCPU[LR] = guest LR + * + */ + + /* Restore BATs */ + + /* We only overwrite the upper part, so we only restoree + the upper part. */ +#define KVM_LOAD_BAT(n, reg, RA, RB) \ + lwz RA,(n*16)+0(reg); \ + lwz RB,(n*16)+4(reg); \ + mtspr SPRN_IBAT##n##U,RA; \ + mtspr SPRN_IBAT##n##L,RB; \ + lwz RA,(n*16)+8(reg); \ + lwz RB,(n*16)+12(reg); \ + mtspr SPRN_DBAT##n##U,RA; \ + mtspr SPRN_DBAT##n##L,RB; \ + + lis r9, BATS@ha + addi r9, r9, BATS@l + tophys(r9, r9) + KVM_LOAD_BAT(0, r9, r10, r11) + KVM_LOAD_BAT(1, r9, r10, r11) + KVM_LOAD_BAT(2, r9, r10, r11) + KVM_LOAD_BAT(3, r9, r10, r11) + + /* Restore Segment Registers */ + + /* 0xc - 0xf */ + + li r0, 4 + mtctr r0 + LOAD_REG_IMMEDIATE(r3, 0x20000000 | (0x111 * 0xc)) + lis r4, 0xc000 +3: mtsrin r3, r4 + addi r3, r3, 0x111 /* increment VSID */ + addis r4, r4, 0x1000 /* address of next segment */ + bdnz 3b + + /* 0x0 - 0xb */ + + /* 'current->mm' needs to be in r4 */ + tophys(r4, r2) + lwz r4, MM(r4) + tophys(r4, r4) + /* This only clobbers r0, r3, r4 and r5 */ + bl switch_mmu_context + +.endm diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index 512dcff77554..4025ea26b3c1 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -232,7 +232,7 @@ do_second: } dprintk("KVM MMU: Translated 0x%lx [0x%llx] -> 0x%llx " - "-> 0x%llx\n", + "-> 0x%lx\n", eaddr, avpn, gpte->vpage, gpte->raddr); found = true; break; @@ -383,7 +383,7 @@ static void kvmppc_mmu_book3s_64_slbia(struct kvm_vcpu *vcpu) if (vcpu->arch.msr & MSR_IR) { kvmppc_mmu_flush_segments(vcpu); - kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc); + kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)); } } @@ -439,37 +439,43 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va, kvmppc_mmu_pte_vflush(vcpu, va >> 12, mask); } -static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, u64 esid, +static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid, u64 *vsid) { + ulong ea = esid << SID_SHIFT; + struct kvmppc_slb *slb; + u64 gvsid = esid; + + if (vcpu->arch.msr & (MSR_DR|MSR_IR)) { + slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), ea); + if (slb) + gvsid = slb->vsid; + } + switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) { case 0: - *vsid = (VSID_REAL >> 16) | esid; + *vsid = VSID_REAL | esid; break; case MSR_IR: - *vsid = (VSID_REAL_IR >> 16) | esid; + *vsid = VSID_REAL_IR | gvsid; break; case MSR_DR: - *vsid = (VSID_REAL_DR >> 16) | esid; + *vsid = VSID_REAL_DR | gvsid; break; case MSR_DR|MSR_IR: - { - ulong ea; - struct kvmppc_slb *slb; - ea = esid << SID_SHIFT; - slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), ea); - if (slb) - *vsid = slb->vsid; - else + if (!slb) return -ENOENT; + *vsid = gvsid; break; - } default: BUG(); break; } + if (vcpu->arch.msr & MSR_PR) + *vsid |= VSID_PR; + return 0; } diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index f2899b297ffd..e4b5744977f6 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -48,21 +48,25 @@ static void invalidate_pte(struct hpte_cache *pte) { - dprintk_mmu("KVM: Flushing SPT %d: 0x%llx (0x%llx) -> 0x%llx\n", - i, pte->pte.eaddr, pte->pte.vpage, pte->host_va); + dprintk_mmu("KVM: Flushing SPT: 0x%lx (0x%llx) -> 0x%llx\n", + pte->pte.eaddr, pte->pte.vpage, pte->host_va); ppc_md.hpte_invalidate(pte->slot, pte->host_va, MMU_PAGE_4K, MMU_SEGSIZE_256M, false); pte->host_va = 0; - kvm_release_pfn_dirty(pte->pfn); + + if (pte->pte.may_write) + kvm_release_pfn_dirty(pte->pfn); + else + kvm_release_pfn_clean(pte->pfn); } -void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, u64 guest_ea, u64 ea_mask) +void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask) { int i; - dprintk_mmu("KVM: Flushing %d Shadow PTEs: 0x%llx & 0x%llx\n", + dprintk_mmu("KVM: Flushing %d Shadow PTEs: 0x%lx & 0x%lx\n", vcpu->arch.hpte_cache_offset, guest_ea, ea_mask); BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM); @@ -106,12 +110,12 @@ void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask) } } -void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, u64 pa_start, u64 pa_end) +void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end) { int i; - dprintk_mmu("KVM: Flushing %d Shadow pPTEs: 0x%llx & 0x%llx\n", - vcpu->arch.hpte_cache_offset, guest_pa, pa_mask); + dprintk_mmu("KVM: Flushing %d Shadow pPTEs: 0x%lx & 0x%lx\n", + vcpu->arch.hpte_cache_offset, pa_start, pa_end); BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM); for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) { @@ -182,7 +186,7 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid) sid_map_mask = kvmppc_sid_hash(vcpu, gvsid); map = &to_book3s(vcpu)->sid_map[sid_map_mask]; if (map->guest_vsid == gvsid) { - dprintk_slb("SLB: Searching 0x%llx -> 0x%llx\n", + dprintk_slb("SLB: Searching: 0x%llx -> 0x%llx\n", gvsid, map->host_vsid); return map; } @@ -194,7 +198,8 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid) return map; } - dprintk_slb("SLB: Searching 0x%llx -> not found\n", gvsid); + dprintk_slb("SLB: Searching %d/%d: 0x%llx -> not found\n", + sid_map_mask, SID_MAP_MASK - sid_map_mask, gvsid); return NULL; } @@ -212,7 +217,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte) /* Get host physical address for gpa */ hpaddr = gfn_to_pfn(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT); if (kvm_is_error_hva(hpaddr)) { - printk(KERN_INFO "Couldn't get guest page for gfn %llx!\n", orig_pte->eaddr); + printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr); return -EINVAL; } hpaddr <<= PAGE_SHIFT; @@ -227,10 +232,16 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte) vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid); map = find_sid_vsid(vcpu, vsid); if (!map) { - kvmppc_mmu_map_segment(vcpu, orig_pte->eaddr); + ret = kvmppc_mmu_map_segment(vcpu, orig_pte->eaddr); + WARN_ON(ret < 0); map = find_sid_vsid(vcpu, vsid); } - BUG_ON(!map); + if (!map) { + printk(KERN_ERR "KVM: Segment map for 0x%llx (0x%lx) failed\n", + vsid, orig_pte->eaddr); + WARN_ON(true); + return -EINVAL; + } vsid = map->host_vsid; va = hpt_va(orig_pte->eaddr, vsid, MMU_SEGSIZE_256M); @@ -257,26 +268,26 @@ map_again: if (ret < 0) { /* If we couldn't map a primary PTE, try a secondary */ -#ifdef USE_SECONDARY hash = ~hash; + vflags ^= HPTE_V_SECONDARY; attempt++; - if (attempt % 2) - vflags = HPTE_V_SECONDARY; - else - vflags = 0; -#else - attempt = 2; -#endif goto map_again; } else { int hpte_id = kvmppc_mmu_hpte_cache_next(vcpu); struct hpte_cache *pte = &vcpu->arch.hpte_cache[hpte_id]; - dprintk_mmu("KVM: %c%c Map 0x%llx: [%lx] 0x%lx (0x%llx) -> %lx\n", + dprintk_mmu("KVM: %c%c Map 0x%lx: [%lx] 0x%lx (0x%llx) -> %lx\n", ((rflags & HPTE_R_PP) == 3) ? '-' : 'w', (rflags & HPTE_R_N) ? '-' : 'x', orig_pte->eaddr, hpteg, va, orig_pte->vpage, hpaddr); + /* The ppc_md code may give us a secondary entry even though we + asked for a primary. Fix up. */ + if ((ret & _PTEIDX_SECONDARY) && !(vflags & HPTE_V_SECONDARY)) { + hash = ~hash; + hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); + } + pte->slot = hpteg + (ret & 7); pte->host_va = va; pte->pte = *orig_pte; @@ -321,6 +332,9 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid) map->guest_vsid = gvsid; map->valid = true; + dprintk_slb("SLB: New mapping at %d: 0x%llx -> 0x%llx\n", + sid_map_mask, gvsid, map->host_vsid); + return map; } @@ -331,14 +345,14 @@ static int kvmppc_mmu_next_segment(struct kvm_vcpu *vcpu, ulong esid) int found_inval = -1; int r; - if (!get_paca()->kvm_slb_max) - get_paca()->kvm_slb_max = 1; + if (!to_svcpu(vcpu)->slb_max) + to_svcpu(vcpu)->slb_max = 1; /* Are we overwriting? */ - for (i = 1; i < get_paca()->kvm_slb_max; i++) { - if (!(get_paca()->kvm_slb[i].esid & SLB_ESID_V)) + for (i = 1; i < to_svcpu(vcpu)->slb_max; i++) { + if (!(to_svcpu(vcpu)->slb[i].esid & SLB_ESID_V)) found_inval = i; - else if ((get_paca()->kvm_slb[i].esid & ESID_MASK) == esid) + else if ((to_svcpu(vcpu)->slb[i].esid & ESID_MASK) == esid) return i; } @@ -352,11 +366,11 @@ static int kvmppc_mmu_next_segment(struct kvm_vcpu *vcpu, ulong esid) max_slb_size = mmu_slb_size; /* Overflowing -> purge */ - if ((get_paca()->kvm_slb_max) == max_slb_size) + if ((to_svcpu(vcpu)->slb_max) == max_slb_size) kvmppc_mmu_flush_segments(vcpu); - r = get_paca()->kvm_slb_max; - get_paca()->kvm_slb_max++; + r = to_svcpu(vcpu)->slb_max; + to_svcpu(vcpu)->slb_max++; return r; } @@ -374,7 +388,7 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr) if (vcpu->arch.mmu.esid_to_vsid(vcpu, esid, &gvsid)) { /* Invalidate an entry */ - get_paca()->kvm_slb[slb_index].esid = 0; + to_svcpu(vcpu)->slb[slb_index].esid = 0; return -ENOENT; } @@ -388,8 +402,8 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr) slb_vsid &= ~SLB_VSID_KP; slb_esid |= slb_index; - get_paca()->kvm_slb[slb_index].esid = slb_esid; - get_paca()->kvm_slb[slb_index].vsid = slb_vsid; + to_svcpu(vcpu)->slb[slb_index].esid = slb_esid; + to_svcpu(vcpu)->slb[slb_index].vsid = slb_vsid; dprintk_slb("slbmte %#llx, %#llx\n", slb_vsid, slb_esid); @@ -398,11 +412,29 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr) void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu) { - get_paca()->kvm_slb_max = 1; - get_paca()->kvm_slb[0].esid = 0; + to_svcpu(vcpu)->slb_max = 1; + to_svcpu(vcpu)->slb[0].esid = 0; } void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) { kvmppc_mmu_pte_flush(vcpu, 0, 0); + __destroy_context(to_book3s(vcpu)->context_id); +} + +int kvmppc_mmu_init(struct kvm_vcpu *vcpu) +{ + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); + int err; + + err = __init_new_context(); + if (err < 0) + return -1; + vcpu3s->context_id = err; + + vcpu3s->vsid_max = ((vcpu3s->context_id + 1) << USER_ESID_BITS) - 1; + vcpu3s->vsid_first = vcpu3s->context_id << USER_ESID_BITS; + vcpu3s->vsid_next = vcpu3s->vsid_first; + + return 0; } diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S index 35b762722187..04e7d3bbfe8b 100644 --- a/arch/powerpc/kvm/book3s_64_slb.S +++ b/arch/powerpc/kvm/book3s_64_slb.S @@ -44,8 +44,7 @@ slb_exit_skip_ ## num: * * *****************************************************************************/ -.global kvmppc_handler_trampoline_enter -kvmppc_handler_trampoline_enter: +.macro LOAD_GUEST_SEGMENTS /* Required state: * @@ -53,20 +52,14 @@ kvmppc_handler_trampoline_enter: * R13 = PACA * R1 = host R1 * R2 = host R2 - * R9 = guest IP - * R10 = guest MSR - * all other GPRS = free - * PACA[KVM_CR] = guest CR - * PACA[KVM_XER] = guest XER + * R3 = shadow vcpu + * all other volatile GPRS = free + * SVCPU[CR] = guest CR + * SVCPU[XER] = guest XER + * SVCPU[CTR] = guest CTR + * SVCPU[LR] = guest LR */ - mtsrr0 r9 - mtsrr1 r10 - - /* Activate guest mode, so faults get handled by KVM */ - li r11, KVM_GUEST_MODE_GUEST - stb r11, PACA_KVM_IN_GUEST(r13) - /* Remove LPAR shadow entries */ #if SLB_NUM_BOLTED == 3 @@ -101,14 +94,14 @@ kvmppc_handler_trampoline_enter: /* Fill SLB with our shadow */ - lbz r12, PACA_KVM_SLB_MAX(r13) + lbz r12, SVCPU_SLB_MAX(r3) mulli r12, r12, 16 - addi r12, r12, PACA_KVM_SLB - add r12, r12, r13 + addi r12, r12, SVCPU_SLB + add r12, r12, r3 /* for (r11 = kvm_slb; r11 < kvm_slb + kvm_slb_size; r11+=slb_entry) */ - li r11, PACA_KVM_SLB - add r11, r11, r13 + li r11, SVCPU_SLB + add r11, r11, r3 slb_loop_enter: @@ -127,34 +120,7 @@ slb_loop_enter_skip: slb_do_enter: - /* Enter guest */ - - ld r0, (PACA_KVM_R0)(r13) - ld r1, (PACA_KVM_R1)(r13) - ld r2, (PACA_KVM_R2)(r13) - ld r3, (PACA_KVM_R3)(r13) - ld r4, (PACA_KVM_R4)(r13) - ld r5, (PACA_KVM_R5)(r13) - ld r6, (PACA_KVM_R6)(r13) - ld r7, (PACA_KVM_R7)(r13) - ld r8, (PACA_KVM_R8)(r13) - ld r9, (PACA_KVM_R9)(r13) - ld r10, (PACA_KVM_R10)(r13) - ld r12, (PACA_KVM_R12)(r13) - - lwz r11, (PACA_KVM_CR)(r13) - mtcr r11 - - ld r11, (PACA_KVM_XER)(r13) - mtxer r11 - - ld r11, (PACA_KVM_R11)(r13) - ld r13, (PACA_KVM_R13)(r13) - - RFI -kvmppc_handler_trampoline_enter_end: - - +.endm /****************************************************************************** * * @@ -162,99 +128,22 @@ kvmppc_handler_trampoline_enter_end: * * *****************************************************************************/ -.global kvmppc_handler_trampoline_exit -kvmppc_handler_trampoline_exit: +.macro LOAD_HOST_SEGMENTS /* Register usage at this point: * - * SPRG_SCRATCH0 = guest R13 - * R12 = exit handler id - * R13 = PACA - * PACA.KVM.SCRATCH0 = guest R12 - * PACA.KVM.SCRATCH1 = guest CR + * R1 = host R1 + * R2 = host R2 + * R12 = exit handler id + * R13 = shadow vcpu - SHADOW_VCPU_OFF [=PACA on PPC64] + * SVCPU.* = guest * + * SVCPU[CR] = guest CR + * SVCPU[XER] = guest XER + * SVCPU[CTR] = guest CTR + * SVCPU[LR] = guest LR * */ - /* Save registers */ - - std r0, PACA_KVM_R0(r13) - std r1, PACA_KVM_R1(r13) - std r2, PACA_KVM_R2(r13) - std r3, PACA_KVM_R3(r13) - std r4, PACA_KVM_R4(r13) - std r5, PACA_KVM_R5(r13) - std r6, PACA_KVM_R6(r13) - std r7, PACA_KVM_R7(r13) - std r8, PACA_KVM_R8(r13) - std r9, PACA_KVM_R9(r13) - std r10, PACA_KVM_R10(r13) - std r11, PACA_KVM_R11(r13) - - /* Restore R1/R2 so we can handle faults */ - ld r1, PACA_KVM_HOST_R1(r13) - ld r2, PACA_KVM_HOST_R2(r13) - - /* Save guest PC and MSR in GPRs */ - mfsrr0 r3 - mfsrr1 r4 - - /* Get scratch'ed off registers */ - mfspr r9, SPRN_SPRG_SCRATCH0 - std r9, PACA_KVM_R13(r13) - - ld r8, PACA_KVM_SCRATCH0(r13) - std r8, PACA_KVM_R12(r13) - - lwz r7, PACA_KVM_SCRATCH1(r13) - stw r7, PACA_KVM_CR(r13) - - /* Save more register state */ - - mfxer r6 - stw r6, PACA_KVM_XER(r13) - - mfdar r5 - mfdsisr r6 - - /* - * In order for us to easily get the last instruction, - * we got the #vmexit at, we exploit the fact that the - * virtual layout is still the same here, so we can just - * ld from the guest's PC address - */ - - /* We only load the last instruction when it's safe */ - cmpwi r12, BOOK3S_INTERRUPT_DATA_STORAGE - beq ld_last_inst - cmpwi r12, BOOK3S_INTERRUPT_PROGRAM - beq ld_last_inst - - b no_ld_last_inst - -ld_last_inst: - /* Save off the guest instruction we're at */ - - /* Set guest mode to 'jump over instruction' so if lwz faults - * we'll just continue at the next IP. */ - li r9, KVM_GUEST_MODE_SKIP - stb r9, PACA_KVM_IN_GUEST(r13) - - /* 1) enable paging for data */ - mfmsr r9 - ori r11, r9, MSR_DR /* Enable paging for data */ - mtmsr r11 - /* 2) fetch the instruction */ - li r0, KVM_INST_FETCH_FAILED /* In case lwz faults */ - lwz r0, 0(r3) - /* 3) disable paging again */ - mtmsr r9 - -no_ld_last_inst: - - /* Unset guest mode */ - li r9, KVM_GUEST_MODE_NONE - stb r9, PACA_KVM_IN_GUEST(r13) - /* Restore bolted entries from the shadow and fix it along the way */ /* We don't store anything in entry 0, so we don't need to take care of it */ @@ -275,28 +164,4 @@ no_ld_last_inst: slb_do_exit: - /* Register usage at this point: - * - * R0 = guest last inst - * R1 = host R1 - * R2 = host R2 - * R3 = guest PC - * R4 = guest MSR - * R5 = guest DAR - * R6 = guest DSISR - * R12 = exit handler id - * R13 = PACA - * PACA.KVM.* = guest * - * - */ - - /* RFI into the highmem handler */ - mfmsr r7 - ori r7, r7, MSR_IR|MSR_DR|MSR_RI /* Enable paging */ - mtsrr1 r7 - ld r8, PACA_KVM_VMHANDLER(r13) /* Highmem handler address */ - mtsrr0 r8 - - RFI -kvmppc_handler_trampoline_exit_end: - +.endm diff --git a/arch/powerpc/kvm/book3s_64_emulate.c b/arch/powerpc/kvm/book3s_emulate.c index 2b0ee7e040c9..c85f906038ce 100644 --- a/arch/powerpc/kvm/book3s_64_emulate.c +++ b/arch/powerpc/kvm/book3s_emulate.c @@ -28,13 +28,16 @@ #define OP_31_XOP_MFMSR 83 #define OP_31_XOP_MTMSR 146 #define OP_31_XOP_MTMSRD 178 +#define OP_31_XOP_MTSR 210 #define OP_31_XOP_MTSRIN 242 #define OP_31_XOP_TLBIEL 274 #define OP_31_XOP_TLBIE 306 #define OP_31_XOP_SLBMTE 402 #define OP_31_XOP_SLBIE 434 #define OP_31_XOP_SLBIA 498 +#define OP_31_XOP_MFSR 595 #define OP_31_XOP_MFSRIN 659 +#define OP_31_XOP_DCBA 758 #define OP_31_XOP_SLBMFEV 851 #define OP_31_XOP_EIOIO 854 #define OP_31_XOP_SLBMFEE 915 @@ -42,6 +45,24 @@ /* DCBZ is actually 1014, but we patch it to 1010 so we get a trap */ #define OP_31_XOP_DCBZ 1010 +#define OP_LFS 48 +#define OP_LFD 50 +#define OP_STFS 52 +#define OP_STFD 54 + +#define SPRN_GQR0 912 +#define SPRN_GQR1 913 +#define SPRN_GQR2 914 +#define SPRN_GQR3 915 +#define SPRN_GQR4 916 +#define SPRN_GQR5 917 +#define SPRN_GQR6 918 +#define SPRN_GQR7 919 + +/* Book3S_32 defines mfsrin(v) - but that messes up our abstract + * function pointers, so let's just disable the define. */ +#undef mfsrin + int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int inst, int *advance) { @@ -52,7 +73,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, switch (get_xop(inst)) { case OP_19_XOP_RFID: case OP_19_XOP_RFI: - vcpu->arch.pc = vcpu->arch.srr0; + kvmppc_set_pc(vcpu, vcpu->arch.srr0); kvmppc_set_msr(vcpu, vcpu->arch.srr1); *advance = 0; break; @@ -80,6 +101,18 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, case OP_31_XOP_MTMSR: kvmppc_set_msr(vcpu, kvmppc_get_gpr(vcpu, get_rs(inst))); break; + case OP_31_XOP_MFSR: + { + int srnum; + + srnum = kvmppc_get_field(inst, 12 + 32, 15 + 32); + if (vcpu->arch.mmu.mfsrin) { + u32 sr; + sr = vcpu->arch.mmu.mfsrin(vcpu, srnum); + kvmppc_set_gpr(vcpu, get_rt(inst), sr); + } + break; + } case OP_31_XOP_MFSRIN: { int srnum; @@ -92,6 +125,11 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, } break; } + case OP_31_XOP_MTSR: + vcpu->arch.mmu.mtsrin(vcpu, + (inst >> 16) & 0xf, + kvmppc_get_gpr(vcpu, get_rs(inst))); + break; case OP_31_XOP_MTSRIN: vcpu->arch.mmu.mtsrin(vcpu, (kvmppc_get_gpr(vcpu, get_rb(inst)) >> 28) & 0xf, @@ -150,12 +188,17 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, kvmppc_set_gpr(vcpu, get_rt(inst), t); } break; + case OP_31_XOP_DCBA: + /* Gets treated as NOP */ + break; case OP_31_XOP_DCBZ: { ulong rb = kvmppc_get_gpr(vcpu, get_rb(inst)); ulong ra = 0; - ulong addr; + ulong addr, vaddr; u32 zeros[8] = { 0, 0, 0, 0, 0, 0, 0, 0 }; + u32 dsisr; + int r; if (get_ra(inst)) ra = kvmppc_get_gpr(vcpu, get_ra(inst)); @@ -163,15 +206,25 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, addr = (ra + rb) & ~31ULL; if (!(vcpu->arch.msr & MSR_SF)) addr &= 0xffffffff; + vaddr = addr; + + r = kvmppc_st(vcpu, &addr, 32, zeros, true); + if ((r == -ENOENT) || (r == -EPERM)) { + *advance = 0; + vcpu->arch.dear = vaddr; + to_svcpu(vcpu)->fault_dar = vaddr; + + dsisr = DSISR_ISSTORE; + if (r == -ENOENT) + dsisr |= DSISR_NOHPTE; + else if (r == -EPERM) + dsisr |= DSISR_PROTFAULT; + + to_book3s(vcpu)->dsisr = dsisr; + to_svcpu(vcpu)->fault_dsisr = dsisr; - if (kvmppc_st(vcpu, addr, 32, zeros)) { - vcpu->arch.dear = addr; - vcpu->arch.fault_dear = addr; - to_book3s(vcpu)->dsisr = DSISR_PROTFAULT | - DSISR_ISSTORE; kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE); - kvmppc_mmu_pte_flush(vcpu, addr, ~0xFFFULL); } break; @@ -184,6 +237,9 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, emulated = EMULATE_FAIL; } + if (emulated == EMULATE_FAIL) + emulated = kvmppc_emulate_paired_single(run, vcpu); + return emulated; } @@ -207,6 +263,34 @@ void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper, } } +static u32 kvmppc_read_bat(struct kvm_vcpu *vcpu, int sprn) +{ + struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); + struct kvmppc_bat *bat; + + switch (sprn) { + case SPRN_IBAT0U ... SPRN_IBAT3L: + bat = &vcpu_book3s->ibat[(sprn - SPRN_IBAT0U) / 2]; + break; + case SPRN_IBAT4U ... SPRN_IBAT7L: + bat = &vcpu_book3s->ibat[4 + ((sprn - SPRN_IBAT4U) / 2)]; + break; + case SPRN_DBAT0U ... SPRN_DBAT3L: + bat = &vcpu_book3s->dbat[(sprn - SPRN_DBAT0U) / 2]; + break; + case SPRN_DBAT4U ... SPRN_DBAT7L: + bat = &vcpu_book3s->dbat[4 + ((sprn - SPRN_DBAT4U) / 2)]; + break; + default: + BUG(); + } + + if (sprn % 2) + return bat->raw >> 32; + else + return bat->raw; +} + static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u32 val) { struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); @@ -217,13 +301,13 @@ static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u32 val) bat = &vcpu_book3s->ibat[(sprn - SPRN_IBAT0U) / 2]; break; case SPRN_IBAT4U ... SPRN_IBAT7L: - bat = &vcpu_book3s->ibat[(sprn - SPRN_IBAT4U) / 2]; + bat = &vcpu_book3s->ibat[4 + ((sprn - SPRN_IBAT4U) / 2)]; break; case SPRN_DBAT0U ... SPRN_DBAT3L: bat = &vcpu_book3s->dbat[(sprn - SPRN_DBAT0U) / 2]; break; case SPRN_DBAT4U ... SPRN_DBAT7L: - bat = &vcpu_book3s->dbat[(sprn - SPRN_DBAT4U) / 2]; + bat = &vcpu_book3s->dbat[4 + ((sprn - SPRN_DBAT4U) / 2)]; break; default: BUG(); @@ -258,6 +342,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) /* BAT writes happen so rarely that we're ok to flush * everything here */ kvmppc_mmu_pte_flush(vcpu, 0, 0); + kvmppc_mmu_flush_segments(vcpu); break; case SPRN_HID0: to_book3s(vcpu)->hid[0] = spr_val; @@ -268,7 +353,32 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) case SPRN_HID2: to_book3s(vcpu)->hid[2] = spr_val; break; + case SPRN_HID2_GEKKO: + to_book3s(vcpu)->hid[2] = spr_val; + /* HID2.PSE controls paired single on gekko */ + switch (vcpu->arch.pvr) { + case 0x00080200: /* lonestar 2.0 */ + case 0x00088202: /* lonestar 2.2 */ + case 0x70000100: /* gekko 1.0 */ + case 0x00080100: /* gekko 2.0 */ + case 0x00083203: /* gekko 2.3a */ + case 0x00083213: /* gekko 2.3b */ + case 0x00083204: /* gekko 2.4 */ + case 0x00083214: /* gekko 2.4e (8SE) - retail HW2 */ + case 0x00087200: /* broadway */ + if (vcpu->arch.hflags & BOOK3S_HFLAG_NATIVE_PS) { + /* Native paired singles */ + } else if (spr_val & (1 << 29)) { /* HID2.PSE */ + vcpu->arch.hflags |= BOOK3S_HFLAG_PAIRED_SINGLE; + kvmppc_giveup_ext(vcpu, MSR_FP); + } else { + vcpu->arch.hflags &= ~BOOK3S_HFLAG_PAIRED_SINGLE; + } + break; + } + break; case SPRN_HID4: + case SPRN_HID4_GEKKO: to_book3s(vcpu)->hid[4] = spr_val; break; case SPRN_HID5: @@ -278,12 +388,30 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) (mfmsr() & MSR_HV)) vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32; break; + case SPRN_GQR0: + case SPRN_GQR1: + case SPRN_GQR2: + case SPRN_GQR3: + case SPRN_GQR4: + case SPRN_GQR5: + case SPRN_GQR6: + case SPRN_GQR7: + to_book3s(vcpu)->gqr[sprn - SPRN_GQR0] = spr_val; + break; case SPRN_ICTC: case SPRN_THRM1: case SPRN_THRM2: case SPRN_THRM3: case SPRN_CTRLF: case SPRN_CTRLT: + case SPRN_L2CR: + case SPRN_MMCR0_GEKKO: + case SPRN_MMCR1_GEKKO: + case SPRN_PMC1_GEKKO: + case SPRN_PMC2_GEKKO: + case SPRN_PMC3_GEKKO: + case SPRN_PMC4_GEKKO: + case SPRN_WPAR_GEKKO: break; default: printk(KERN_INFO "KVM: invalid SPR write: %d\n", sprn); @@ -301,6 +429,12 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) int emulated = EMULATE_DONE; switch (sprn) { + case SPRN_IBAT0U ... SPRN_IBAT3L: + case SPRN_IBAT4U ... SPRN_IBAT7L: + case SPRN_DBAT0U ... SPRN_DBAT3L: + case SPRN_DBAT4U ... SPRN_DBAT7L: + kvmppc_set_gpr(vcpu, rt, kvmppc_read_bat(vcpu, sprn)); + break; case SPRN_SDR1: kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->sdr1); break; @@ -320,19 +454,40 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[1]); break; case SPRN_HID2: + case SPRN_HID2_GEKKO: kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[2]); break; case SPRN_HID4: + case SPRN_HID4_GEKKO: kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[4]); break; case SPRN_HID5: kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[5]); break; + case SPRN_GQR0: + case SPRN_GQR1: + case SPRN_GQR2: + case SPRN_GQR3: + case SPRN_GQR4: + case SPRN_GQR5: + case SPRN_GQR6: + case SPRN_GQR7: + kvmppc_set_gpr(vcpu, rt, + to_book3s(vcpu)->gqr[sprn - SPRN_GQR0]); + break; case SPRN_THRM1: case SPRN_THRM2: case SPRN_THRM3: case SPRN_CTRLF: case SPRN_CTRLT: + case SPRN_L2CR: + case SPRN_MMCR0_GEKKO: + case SPRN_MMCR1_GEKKO: + case SPRN_PMC1_GEKKO: + case SPRN_PMC2_GEKKO: + case SPRN_PMC3_GEKKO: + case SPRN_PMC4_GEKKO: + case SPRN_WPAR_GEKKO: kvmppc_set_gpr(vcpu, rt, 0); break; default: @@ -346,3 +501,73 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) return emulated; } +u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst) +{ + u32 dsisr = 0; + + /* + * This is what the spec says about DSISR bits (not mentioned = 0): + * + * 12:13 [DS] Set to bits 30:31 + * 15:16 [X] Set to bits 29:30 + * 17 [X] Set to bit 25 + * [D/DS] Set to bit 5 + * 18:21 [X] Set to bits 21:24 + * [D/DS] Set to bits 1:4 + * 22:26 Set to bits 6:10 (RT/RS/FRT/FRS) + * 27:31 Set to bits 11:15 (RA) + */ + + switch (get_op(inst)) { + /* D-form */ + case OP_LFS: + case OP_LFD: + case OP_STFD: + case OP_STFS: + dsisr |= (inst >> 12) & 0x4000; /* bit 17 */ + dsisr |= (inst >> 17) & 0x3c00; /* bits 18:21 */ + break; + /* X-form */ + case 31: + dsisr |= (inst << 14) & 0x18000; /* bits 15:16 */ + dsisr |= (inst << 8) & 0x04000; /* bit 17 */ + dsisr |= (inst << 3) & 0x03c00; /* bits 18:21 */ + break; + default: + printk(KERN_INFO "KVM: Unaligned instruction 0x%x\n", inst); + break; + } + + dsisr |= (inst >> 16) & 0x03ff; /* bits 22:31 */ + + return dsisr; +} + +ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst) +{ + ulong dar = 0; + ulong ra; + + switch (get_op(inst)) { + case OP_LFS: + case OP_LFD: + case OP_STFD: + case OP_STFS: + ra = get_ra(inst); + if (ra) + dar = kvmppc_get_gpr(vcpu, ra); + dar += (s32)((s16)inst); + break; + case 31: + ra = get_ra(inst); + if (ra) + dar = kvmppc_get_gpr(vcpu, ra); + dar += kvmppc_get_gpr(vcpu, get_rb(inst)); + break; + default: + printk(KERN_INFO "KVM: Unaligned instruction 0x%x\n", inst); + break; + } + + return dar; +} diff --git a/arch/powerpc/kvm/book3s_64_exports.c b/arch/powerpc/kvm/book3s_exports.c index 1dd5a1ddfd0d..1dd5a1ddfd0d 100644 --- a/arch/powerpc/kvm/book3s_64_exports.c +++ b/arch/powerpc/kvm/book3s_exports.c diff --git a/arch/powerpc/kvm/book3s_64_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index c1584d0cbce8..2f0bc928b08a 100644 --- a/arch/powerpc/kvm/book3s_64_interrupts.S +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -24,36 +24,56 @@ #include <asm/asm-offsets.h> #include <asm/exception-64s.h> -#define KVMPPC_HANDLE_EXIT .kvmppc_handle_exit -#define ULONG_SIZE 8 -#define VCPU_GPR(n) (VCPU_GPRS + (n * ULONG_SIZE)) +#if defined(CONFIG_PPC_BOOK3S_64) -.macro DISABLE_INTERRUPTS - mfmsr r0 - rldicl r0,r0,48,1 - rotldi r0,r0,16 - mtmsrd r0,1 -.endm +#define ULONG_SIZE 8 +#define FUNC(name) GLUE(.,name) +#define GET_SHADOW_VCPU(reg) \ + addi reg, r13, PACA_KVM_SVCPU + +#define DISABLE_INTERRUPTS \ + mfmsr r0; \ + rldicl r0,r0,48,1; \ + rotldi r0,r0,16; \ + mtmsrd r0,1; \ + +#elif defined(CONFIG_PPC_BOOK3S_32) + +#define ULONG_SIZE 4 +#define FUNC(name) name + +#define GET_SHADOW_VCPU(reg) \ + lwz reg, (THREAD + THREAD_KVM_SVCPU)(r2) + +#define DISABLE_INTERRUPTS \ + mfmsr r0; \ + rlwinm r0,r0,0,17,15; \ + mtmsr r0; \ + +#endif /* CONFIG_PPC_BOOK3S_XX */ + + +#define VCPU_GPR(n) (VCPU_GPRS + (n * ULONG_SIZE)) #define VCPU_LOAD_NVGPRS(vcpu) \ - ld r14, VCPU_GPR(r14)(vcpu); \ - ld r15, VCPU_GPR(r15)(vcpu); \ - ld r16, VCPU_GPR(r16)(vcpu); \ - ld r17, VCPU_GPR(r17)(vcpu); \ - ld r18, VCPU_GPR(r18)(vcpu); \ - ld r19, VCPU_GPR(r19)(vcpu); \ - ld r20, VCPU_GPR(r20)(vcpu); \ - ld r21, VCPU_GPR(r21)(vcpu); \ - ld r22, VCPU_GPR(r22)(vcpu); \ - ld r23, VCPU_GPR(r23)(vcpu); \ - ld r24, VCPU_GPR(r24)(vcpu); \ - ld r25, VCPU_GPR(r25)(vcpu); \ - ld r26, VCPU_GPR(r26)(vcpu); \ - ld r27, VCPU_GPR(r27)(vcpu); \ - ld r28, VCPU_GPR(r28)(vcpu); \ - ld r29, VCPU_GPR(r29)(vcpu); \ - ld r30, VCPU_GPR(r30)(vcpu); \ - ld r31, VCPU_GPR(r31)(vcpu); \ + PPC_LL r14, VCPU_GPR(r14)(vcpu); \ + PPC_LL r15, VCPU_GPR(r15)(vcpu); \ + PPC_LL r16, VCPU_GPR(r16)(vcpu); \ + PPC_LL r17, VCPU_GPR(r17)(vcpu); \ + PPC_LL r18, VCPU_GPR(r18)(vcpu); \ + PPC_LL r19, VCPU_GPR(r19)(vcpu); \ + PPC_LL r20, VCPU_GPR(r20)(vcpu); \ + PPC_LL r21, VCPU_GPR(r21)(vcpu); \ + PPC_LL r22, VCPU_GPR(r22)(vcpu); \ + PPC_LL r23, VCPU_GPR(r23)(vcpu); \ + PPC_LL r24, VCPU_GPR(r24)(vcpu); \ + PPC_LL r25, VCPU_GPR(r25)(vcpu); \ + PPC_LL r26, VCPU_GPR(r26)(vcpu); \ + PPC_LL r27, VCPU_GPR(r27)(vcpu); \ + PPC_LL r28, VCPU_GPR(r28)(vcpu); \ + PPC_LL r29, VCPU_GPR(r29)(vcpu); \ + PPC_LL r30, VCPU_GPR(r30)(vcpu); \ + PPC_LL r31, VCPU_GPR(r31)(vcpu); \ /***************************************************************************** * * @@ -69,11 +89,11 @@ _GLOBAL(__kvmppc_vcpu_entry) kvm_start_entry: /* Write correct stack frame */ - mflr r0 - std r0,16(r1) + mflr r0 + PPC_STL r0,PPC_LR_STKOFF(r1) /* Save host state to the stack */ - stdu r1, -SWITCH_FRAME_SIZE(r1) + PPC_STLU r1, -SWITCH_FRAME_SIZE(r1) /* Save r3 (kvm_run) and r4 (vcpu) */ SAVE_2GPRS(3, r1) @@ -82,33 +102,28 @@ kvm_start_entry: SAVE_NVGPRS(r1) /* Save LR */ - std r0, _LINK(r1) + PPC_STL r0, _LINK(r1) /* Load non-volatile guest state from the vcpu */ VCPU_LOAD_NVGPRS(r4) + GET_SHADOW_VCPU(r5) + /* Save R1/R2 in the PACA */ - std r1, PACA_KVM_HOST_R1(r13) - std r2, PACA_KVM_HOST_R2(r13) + PPC_STL r1, SVCPU_HOST_R1(r5) + PPC_STL r2, SVCPU_HOST_R2(r5) /* XXX swap in/out on load? */ - ld r3, VCPU_HIGHMEM_HANDLER(r4) - std r3, PACA_KVM_VMHANDLER(r13) + PPC_LL r3, VCPU_HIGHMEM_HANDLER(r4) + PPC_STL r3, SVCPU_VMHANDLER(r5) kvm_start_lightweight: - ld r9, VCPU_PC(r4) /* r9 = vcpu->arch.pc */ - ld r10, VCPU_SHADOW_MSR(r4) /* r10 = vcpu->arch.shadow_msr */ - - /* Load some guest state in the respective registers */ - ld r5, VCPU_CTR(r4) /* r5 = vcpu->arch.ctr */ - /* will be swapped in by rmcall */ - - ld r3, VCPU_LR(r4) /* r3 = vcpu->arch.lr */ - mtlr r3 /* LR = r3 */ + PPC_LL r10, VCPU_SHADOW_MSR(r4) /* r10 = vcpu->arch.shadow_msr */ DISABLE_INTERRUPTS +#ifdef CONFIG_PPC_BOOK3S_64 /* Some guests may need to have dcbz set to 32 byte length. * * Usually we ensure that by patching the guest's instructions @@ -118,7 +133,7 @@ kvm_start_lightweight: * because that's a lot faster. */ - ld r3, VCPU_HFLAGS(r4) + PPC_LL r3, VCPU_HFLAGS(r4) rldicl. r3, r3, 0, 63 /* CR = ((r3 & 1) == 0) */ beq no_dcbz32_on @@ -128,13 +143,15 @@ kvm_start_lightweight: no_dcbz32_on: - ld r6, VCPU_RMCALL(r4) +#endif /* CONFIG_PPC_BOOK3S_64 */ + + PPC_LL r6, VCPU_RMCALL(r4) mtctr r6 - ld r3, VCPU_TRAMPOLINE_ENTER(r4) + PPC_LL r3, VCPU_TRAMPOLINE_ENTER(r4) LOAD_REG_IMMEDIATE(r4, MSR_KERNEL & ~(MSR_IR | MSR_DR)) - /* Jump to SLB patching handlder and into our guest */ + /* Jump to segment patching handler and into our guest */ bctr /* @@ -149,31 +166,20 @@ kvmppc_handler_highmem: /* * Register usage at this point: * - * R0 = guest last inst - * R1 = host R1 - * R2 = host R2 - * R3 = guest PC - * R4 = guest MSR - * R5 = guest DAR - * R6 = guest DSISR - * R13 = PACA - * PACA.KVM.* = guest * + * R1 = host R1 + * R2 = host R2 + * R12 = exit handler id + * R13 = PACA + * SVCPU.* = guest * * */ /* R7 = vcpu */ - ld r7, GPR4(r1) + PPC_LL r7, GPR4(r1) - /* Now save the guest state */ +#ifdef CONFIG_PPC_BOOK3S_64 - stw r0, VCPU_LAST_INST(r7) - - std r3, VCPU_PC(r7) - std r4, VCPU_SHADOW_SRR1(r7) - std r5, VCPU_FAULT_DEAR(r7) - std r6, VCPU_FAULT_DSISR(r7) - - ld r5, VCPU_HFLAGS(r7) + PPC_LL r5, VCPU_HFLAGS(r7) rldicl. r5, r5, 0, 63 /* CR = ((r5 & 1) == 0) */ beq no_dcbz32_off @@ -184,35 +190,29 @@ kvmppc_handler_highmem: no_dcbz32_off: - std r14, VCPU_GPR(r14)(r7) - std r15, VCPU_GPR(r15)(r7) - std r16, VCPU_GPR(r16)(r7) - std r17, VCPU_GPR(r17)(r7) - std r18, VCPU_GPR(r18)(r7) - std r19, VCPU_GPR(r19)(r7) - std r20, VCPU_GPR(r20)(r7) - std r21, VCPU_GPR(r21)(r7) - std r22, VCPU_GPR(r22)(r7) - std r23, VCPU_GPR(r23)(r7) - std r24, VCPU_GPR(r24)(r7) - std r25, VCPU_GPR(r25)(r7) - std r26, VCPU_GPR(r26)(r7) - std r27, VCPU_GPR(r27)(r7) - std r28, VCPU_GPR(r28)(r7) - std r29, VCPU_GPR(r29)(r7) - std r30, VCPU_GPR(r30)(r7) - std r31, VCPU_GPR(r31)(r7) - - /* Save guest CTR */ - mfctr r5 - std r5, VCPU_CTR(r7) - - /* Save guest LR */ - mflr r5 - std r5, VCPU_LR(r7) +#endif /* CONFIG_PPC_BOOK3S_64 */ + + PPC_STL r14, VCPU_GPR(r14)(r7) + PPC_STL r15, VCPU_GPR(r15)(r7) + PPC_STL r16, VCPU_GPR(r16)(r7) + PPC_STL r17, VCPU_GPR(r17)(r7) + PPC_STL r18, VCPU_GPR(r18)(r7) + PPC_STL r19, VCPU_GPR(r19)(r7) + PPC_STL r20, VCPU_GPR(r20)(r7) + PPC_STL r21, VCPU_GPR(r21)(r7) + PPC_STL r22, VCPU_GPR(r22)(r7) + PPC_STL r23, VCPU_GPR(r23)(r7) + PPC_STL r24, VCPU_GPR(r24)(r7) + PPC_STL r25, VCPU_GPR(r25)(r7) + PPC_STL r26, VCPU_GPR(r26)(r7) + PPC_STL r27, VCPU_GPR(r27)(r7) + PPC_STL r28, VCPU_GPR(r28)(r7) + PPC_STL r29, VCPU_GPR(r29)(r7) + PPC_STL r30, VCPU_GPR(r30)(r7) + PPC_STL r31, VCPU_GPR(r31)(r7) /* Restore host msr -> SRR1 */ - ld r6, VCPU_HOST_MSR(r7) + PPC_LL r6, VCPU_HOST_MSR(r7) /* * For some interrupts, we need to call the real Linux @@ -228,9 +228,12 @@ no_dcbz32_off: beq call_linux_handler cmpwi r12, BOOK3S_INTERRUPT_DECREMENTER beq call_linux_handler + cmpwi r12, BOOK3S_INTERRUPT_PERFMON + beq call_linux_handler /* Back to EE=1 */ mtmsr r6 + sync b kvm_return_point call_linux_handler: @@ -249,14 +252,14 @@ call_linux_handler: */ /* Restore host IP -> SRR0 */ - ld r5, VCPU_HOST_RETIP(r7) + PPC_LL r5, VCPU_HOST_RETIP(r7) /* XXX Better move to a safe function? * What if we get an HTAB flush in between mtsrr0 and mtsrr1? */ mtlr r12 - ld r4, VCPU_TRAMPOLINE_LOWMEM(r7) + PPC_LL r4, VCPU_TRAMPOLINE_LOWMEM(r7) mtsrr0 r4 LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR)) mtsrr1 r3 @@ -274,7 +277,7 @@ kvm_return_point: /* Restore r3 (kvm_run) and r4 (vcpu) */ REST_2GPRS(3, r1) - bl KVMPPC_HANDLE_EXIT + bl FUNC(kvmppc_handle_exit) /* If RESUME_GUEST, get back in the loop */ cmpwi r3, RESUME_GUEST @@ -285,7 +288,7 @@ kvm_return_point: kvm_exit_loop: - ld r4, _LINK(r1) + PPC_LL r4, _LINK(r1) mtlr r4 /* Restore non-volatile host registers (r14 - r31) */ @@ -296,8 +299,8 @@ kvm_exit_loop: kvm_loop_heavyweight: - ld r4, _LINK(r1) - std r4, (16 + SWITCH_FRAME_SIZE)(r1) + PPC_LL r4, _LINK(r1) + PPC_STL r4, (PPC_LR_STKOFF + SWITCH_FRAME_SIZE)(r1) /* Load vcpu and cpu_run */ REST_2GPRS(3, r1) @@ -315,4 +318,3 @@ kvm_loop_lightweight: /* Jump back into the beginning of this function */ b kvm_start_lightweight - diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c new file mode 100644 index 000000000000..a9f66abafcb3 --- /dev/null +++ b/arch/powerpc/kvm/book3s_paired_singles.c @@ -0,0 +1,1289 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright Novell Inc 2010 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +#include <asm/kvm.h> +#include <asm/kvm_ppc.h> +#include <asm/disassemble.h> +#include <asm/kvm_book3s.h> +#include <asm/kvm_fpu.h> +#include <asm/reg.h> +#include <asm/cacheflush.h> +#include <linux/vmalloc.h> + +/* #define DEBUG */ + +#ifdef DEBUG +#define dprintk printk +#else +#define dprintk(...) do { } while(0); +#endif + +#define OP_LFS 48 +#define OP_LFSU 49 +#define OP_LFD 50 +#define OP_LFDU 51 +#define OP_STFS 52 +#define OP_STFSU 53 +#define OP_STFD 54 +#define OP_STFDU 55 +#define OP_PSQ_L 56 +#define OP_PSQ_LU 57 +#define OP_PSQ_ST 60 +#define OP_PSQ_STU 61 + +#define OP_31_LFSX 535 +#define OP_31_LFSUX 567 +#define OP_31_LFDX 599 +#define OP_31_LFDUX 631 +#define OP_31_STFSX 663 +#define OP_31_STFSUX 695 +#define OP_31_STFX 727 +#define OP_31_STFUX 759 +#define OP_31_LWIZX 887 +#define OP_31_STFIWX 983 + +#define OP_59_FADDS 21 +#define OP_59_FSUBS 20 +#define OP_59_FSQRTS 22 +#define OP_59_FDIVS 18 +#define OP_59_FRES 24 +#define OP_59_FMULS 25 +#define OP_59_FRSQRTES 26 +#define OP_59_FMSUBS 28 +#define OP_59_FMADDS 29 +#define OP_59_FNMSUBS 30 +#define OP_59_FNMADDS 31 + +#define OP_63_FCMPU 0 +#define OP_63_FCPSGN 8 +#define OP_63_FRSP 12 +#define OP_63_FCTIW 14 +#define OP_63_FCTIWZ 15 +#define OP_63_FDIV 18 +#define OP_63_FADD 21 +#define OP_63_FSQRT 22 +#define OP_63_FSEL 23 +#define OP_63_FRE 24 +#define OP_63_FMUL 25 +#define OP_63_FRSQRTE 26 +#define OP_63_FMSUB 28 +#define OP_63_FMADD 29 +#define OP_63_FNMSUB 30 +#define OP_63_FNMADD 31 +#define OP_63_FCMPO 32 +#define OP_63_MTFSB1 38 // XXX +#define OP_63_FSUB 20 +#define OP_63_FNEG 40 +#define OP_63_MCRFS 64 +#define OP_63_MTFSB0 70 +#define OP_63_FMR 72 +#define OP_63_MTFSFI 134 +#define OP_63_FABS 264 +#define OP_63_MFFS 583 +#define OP_63_MTFSF 711 + +#define OP_4X_PS_CMPU0 0 +#define OP_4X_PSQ_LX 6 +#define OP_4XW_PSQ_STX 7 +#define OP_4A_PS_SUM0 10 +#define OP_4A_PS_SUM1 11 +#define OP_4A_PS_MULS0 12 +#define OP_4A_PS_MULS1 13 +#define OP_4A_PS_MADDS0 14 +#define OP_4A_PS_MADDS1 15 +#define OP_4A_PS_DIV 18 +#define OP_4A_PS_SUB 20 +#define OP_4A_PS_ADD 21 +#define OP_4A_PS_SEL 23 +#define OP_4A_PS_RES 24 +#define OP_4A_PS_MUL 25 +#define OP_4A_PS_RSQRTE 26 +#define OP_4A_PS_MSUB 28 +#define OP_4A_PS_MADD 29 +#define OP_4A_PS_NMSUB 30 +#define OP_4A_PS_NMADD 31 +#define OP_4X_PS_CMPO0 32 +#define OP_4X_PSQ_LUX 38 +#define OP_4XW_PSQ_STUX 39 +#define OP_4X_PS_NEG 40 +#define OP_4X_PS_CMPU1 64 +#define OP_4X_PS_MR 72 +#define OP_4X_PS_CMPO1 96 +#define OP_4X_PS_NABS 136 +#define OP_4X_PS_ABS 264 +#define OP_4X_PS_MERGE00 528 +#define OP_4X_PS_MERGE01 560 +#define OP_4X_PS_MERGE10 592 +#define OP_4X_PS_MERGE11 624 + +#define SCALAR_NONE 0 +#define SCALAR_HIGH (1 << 0) +#define SCALAR_LOW (1 << 1) +#define SCALAR_NO_PS0 (1 << 2) +#define SCALAR_NO_PS1 (1 << 3) + +#define GQR_ST_TYPE_MASK 0x00000007 +#define GQR_ST_TYPE_SHIFT 0 +#define GQR_ST_SCALE_MASK 0x00003f00 +#define GQR_ST_SCALE_SHIFT 8 +#define GQR_LD_TYPE_MASK 0x00070000 +#define GQR_LD_TYPE_SHIFT 16 +#define GQR_LD_SCALE_MASK 0x3f000000 +#define GQR_LD_SCALE_SHIFT 24 + +#define GQR_QUANTIZE_FLOAT 0 +#define GQR_QUANTIZE_U8 4 +#define GQR_QUANTIZE_U16 5 +#define GQR_QUANTIZE_S8 6 +#define GQR_QUANTIZE_S16 7 + +#define FPU_LS_SINGLE 0 +#define FPU_LS_DOUBLE 1 +#define FPU_LS_SINGLE_LOW 2 + +static inline void kvmppc_sync_qpr(struct kvm_vcpu *vcpu, int rt) +{ + struct thread_struct t; + + t.fpscr.val = vcpu->arch.fpscr; + cvt_df((double*)&vcpu->arch.fpr[rt], (float*)&vcpu->arch.qpr[rt], &t); +} + +static void kvmppc_inject_pf(struct kvm_vcpu *vcpu, ulong eaddr, bool is_store) +{ + u64 dsisr; + + vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 33, 36, 0); + vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 42, 47, 0); + vcpu->arch.dear = eaddr; + /* Page Fault */ + dsisr = kvmppc_set_field(0, 33, 33, 1); + if (is_store) + to_book3s(vcpu)->dsisr = kvmppc_set_field(dsisr, 38, 38, 1); + kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE); +} + +static int kvmppc_emulate_fpr_load(struct kvm_run *run, struct kvm_vcpu *vcpu, + int rs, ulong addr, int ls_type) +{ + int emulated = EMULATE_FAIL; + struct thread_struct t; + int r; + char tmp[8]; + int len = sizeof(u32); + + if (ls_type == FPU_LS_DOUBLE) + len = sizeof(u64); + + t.fpscr.val = vcpu->arch.fpscr; + + /* read from memory */ + r = kvmppc_ld(vcpu, &addr, len, tmp, true); + vcpu->arch.paddr_accessed = addr; + + if (r < 0) { + kvmppc_inject_pf(vcpu, addr, false); + goto done_load; + } else if (r == EMULATE_DO_MMIO) { + emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FPR | rs, len, 1); + goto done_load; + } + + emulated = EMULATE_DONE; + + /* put in registers */ + switch (ls_type) { + case FPU_LS_SINGLE: + cvt_fd((float*)tmp, (double*)&vcpu->arch.fpr[rs], &t); + vcpu->arch.qpr[rs] = *((u32*)tmp); + break; + case FPU_LS_DOUBLE: + vcpu->arch.fpr[rs] = *((u64*)tmp); + break; + } + + dprintk(KERN_INFO "KVM: FPR_LD [0x%llx] at 0x%lx (%d)\n", *(u64*)tmp, + addr, len); + +done_load: + return emulated; +} + +static int kvmppc_emulate_fpr_store(struct kvm_run *run, struct kvm_vcpu *vcpu, + int rs, ulong addr, int ls_type) +{ + int emulated = EMULATE_FAIL; + struct thread_struct t; + int r; + char tmp[8]; + u64 val; + int len; + + t.fpscr.val = vcpu->arch.fpscr; + + switch (ls_type) { + case FPU_LS_SINGLE: + cvt_df((double*)&vcpu->arch.fpr[rs], (float*)tmp, &t); + val = *((u32*)tmp); + len = sizeof(u32); + break; + case FPU_LS_SINGLE_LOW: + *((u32*)tmp) = vcpu->arch.fpr[rs]; + val = vcpu->arch.fpr[rs] & 0xffffffff; + len = sizeof(u32); + break; + case FPU_LS_DOUBLE: + *((u64*)tmp) = vcpu->arch.fpr[rs]; + val = vcpu->arch.fpr[rs]; + len = sizeof(u64); + break; + default: + val = 0; + len = 0; + } + + r = kvmppc_st(vcpu, &addr, len, tmp, true); + vcpu->arch.paddr_accessed = addr; + if (r < 0) { + kvmppc_inject_pf(vcpu, addr, true); + } else if (r == EMULATE_DO_MMIO) { + emulated = kvmppc_handle_store(run, vcpu, val, len, 1); + } else { + emulated = EMULATE_DONE; + } + + dprintk(KERN_INFO "KVM: FPR_ST [0x%llx] at 0x%lx (%d)\n", + val, addr, len); + + return emulated; +} + +static int kvmppc_emulate_psq_load(struct kvm_run *run, struct kvm_vcpu *vcpu, + int rs, ulong addr, bool w, int i) +{ + int emulated = EMULATE_FAIL; + struct thread_struct t; + int r; + float one = 1.0; + u32 tmp[2]; + + t.fpscr.val = vcpu->arch.fpscr; + + /* read from memory */ + if (w) { + r = kvmppc_ld(vcpu, &addr, sizeof(u32), tmp, true); + memcpy(&tmp[1], &one, sizeof(u32)); + } else { + r = kvmppc_ld(vcpu, &addr, sizeof(u32) * 2, tmp, true); + } + vcpu->arch.paddr_accessed = addr; + if (r < 0) { + kvmppc_inject_pf(vcpu, addr, false); + goto done_load; + } else if ((r == EMULATE_DO_MMIO) && w) { + emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FPR | rs, 4, 1); + vcpu->arch.qpr[rs] = tmp[1]; + goto done_load; + } else if (r == EMULATE_DO_MMIO) { + emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FQPR | rs, 8, 1); + goto done_load; + } + + emulated = EMULATE_DONE; + + /* put in registers */ + cvt_fd((float*)&tmp[0], (double*)&vcpu->arch.fpr[rs], &t); + vcpu->arch.qpr[rs] = tmp[1]; + + dprintk(KERN_INFO "KVM: PSQ_LD [0x%x, 0x%x] at 0x%lx (%d)\n", tmp[0], + tmp[1], addr, w ? 4 : 8); + +done_load: + return emulated; +} + +static int kvmppc_emulate_psq_store(struct kvm_run *run, struct kvm_vcpu *vcpu, + int rs, ulong addr, bool w, int i) +{ + int emulated = EMULATE_FAIL; + struct thread_struct t; + int r; + u32 tmp[2]; + int len = w ? sizeof(u32) : sizeof(u64); + + t.fpscr.val = vcpu->arch.fpscr; + + cvt_df((double*)&vcpu->arch.fpr[rs], (float*)&tmp[0], &t); + tmp[1] = vcpu->arch.qpr[rs]; + + r = kvmppc_st(vcpu, &addr, len, tmp, true); + vcpu->arch.paddr_accessed = addr; + if (r < 0) { + kvmppc_inject_pf(vcpu, addr, true); + } else if ((r == EMULATE_DO_MMIO) && w) { + emulated = kvmppc_handle_store(run, vcpu, tmp[0], 4, 1); + } else if (r == EMULATE_DO_MMIO) { + u64 val = ((u64)tmp[0] << 32) | tmp[1]; + emulated = kvmppc_handle_store(run, vcpu, val, 8, 1); + } else { + emulated = EMULATE_DONE; + } + + dprintk(KERN_INFO "KVM: PSQ_ST [0x%x, 0x%x] at 0x%lx (%d)\n", + tmp[0], tmp[1], addr, len); + + return emulated; +} + +/* + * Cuts out inst bits with ordering according to spec. + * That means the leftmost bit is zero. All given bits are included. + */ +static inline u32 inst_get_field(u32 inst, int msb, int lsb) +{ + return kvmppc_get_field(inst, msb + 32, lsb + 32); +} + +/* + * Replaces inst bits with ordering according to spec. + */ +static inline u32 inst_set_field(u32 inst, int msb, int lsb, int value) +{ + return kvmppc_set_field(inst, msb + 32, lsb + 32, value); +} + +bool kvmppc_inst_is_paired_single(struct kvm_vcpu *vcpu, u32 inst) +{ + if (!(vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)) + return false; + + switch (get_op(inst)) { + case OP_PSQ_L: + case OP_PSQ_LU: + case OP_PSQ_ST: + case OP_PSQ_STU: + case OP_LFS: + case OP_LFSU: + case OP_LFD: + case OP_LFDU: + case OP_STFS: + case OP_STFSU: + case OP_STFD: + case OP_STFDU: + return true; + case 4: + /* X form */ + switch (inst_get_field(inst, 21, 30)) { + case OP_4X_PS_CMPU0: + case OP_4X_PSQ_LX: + case OP_4X_PS_CMPO0: + case OP_4X_PSQ_LUX: + case OP_4X_PS_NEG: + case OP_4X_PS_CMPU1: + case OP_4X_PS_MR: + case OP_4X_PS_CMPO1: + case OP_4X_PS_NABS: + case OP_4X_PS_ABS: + case OP_4X_PS_MERGE00: + case OP_4X_PS_MERGE01: + case OP_4X_PS_MERGE10: + case OP_4X_PS_MERGE11: + return true; + } + /* XW form */ + switch (inst_get_field(inst, 25, 30)) { + case OP_4XW_PSQ_STX: + case OP_4XW_PSQ_STUX: + return true; + } + /* A form */ + switch (inst_get_field(inst, 26, 30)) { + case OP_4A_PS_SUM1: + case OP_4A_PS_SUM0: + case OP_4A_PS_MULS0: + case OP_4A_PS_MULS1: + case OP_4A_PS_MADDS0: + case OP_4A_PS_MADDS1: + case OP_4A_PS_DIV: + case OP_4A_PS_SUB: + case OP_4A_PS_ADD: + case OP_4A_PS_SEL: + case OP_4A_PS_RES: + case OP_4A_PS_MUL: + case OP_4A_PS_RSQRTE: + case OP_4A_PS_MSUB: + case OP_4A_PS_MADD: + case OP_4A_PS_NMSUB: + case OP_4A_PS_NMADD: + return true; + } + break; + case 59: + switch (inst_get_field(inst, 21, 30)) { + case OP_59_FADDS: + case OP_59_FSUBS: + case OP_59_FDIVS: + case OP_59_FRES: + case OP_59_FRSQRTES: + return true; + } + switch (inst_get_field(inst, 26, 30)) { + case OP_59_FMULS: + case OP_59_FMSUBS: + case OP_59_FMADDS: + case OP_59_FNMSUBS: + case OP_59_FNMADDS: + return true; + } + break; + case 63: + switch (inst_get_field(inst, 21, 30)) { + case OP_63_MTFSB0: + case OP_63_MTFSB1: + case OP_63_MTFSF: + case OP_63_MTFSFI: + case OP_63_MCRFS: + case OP_63_MFFS: + case OP_63_FCMPU: + case OP_63_FCMPO: + case OP_63_FNEG: + case OP_63_FMR: + case OP_63_FABS: + case OP_63_FRSP: + case OP_63_FDIV: + case OP_63_FADD: + case OP_63_FSUB: + case OP_63_FCTIW: + case OP_63_FCTIWZ: + case OP_63_FRSQRTE: + case OP_63_FCPSGN: + return true; + } + switch (inst_get_field(inst, 26, 30)) { + case OP_63_FMUL: + case OP_63_FSEL: + case OP_63_FMSUB: + case OP_63_FMADD: + case OP_63_FNMSUB: + case OP_63_FNMADD: + return true; + } + break; + case 31: + switch (inst_get_field(inst, 21, 30)) { + case OP_31_LFSX: + case OP_31_LFSUX: + case OP_31_LFDX: + case OP_31_LFDUX: + case OP_31_STFSX: + case OP_31_STFSUX: + case OP_31_STFX: + case OP_31_STFUX: + case OP_31_STFIWX: + return true; + } + break; + } + + return false; +} + +static int get_d_signext(u32 inst) +{ + int d = inst & 0x8ff; + + if (d & 0x800) + return -(d & 0x7ff); + + return (d & 0x7ff); +} + +static int kvmppc_ps_three_in(struct kvm_vcpu *vcpu, bool rc, + int reg_out, int reg_in1, int reg_in2, + int reg_in3, int scalar, + void (*func)(struct thread_struct *t, + u32 *dst, u32 *src1, + u32 *src2, u32 *src3)) +{ + u32 *qpr = vcpu->arch.qpr; + u64 *fpr = vcpu->arch.fpr; + u32 ps0_out; + u32 ps0_in1, ps0_in2, ps0_in3; + u32 ps1_in1, ps1_in2, ps1_in3; + struct thread_struct t; + t.fpscr.val = vcpu->arch.fpscr; + + /* RC */ + WARN_ON(rc); + + /* PS0 */ + cvt_df((double*)&fpr[reg_in1], (float*)&ps0_in1, &t); + cvt_df((double*)&fpr[reg_in2], (float*)&ps0_in2, &t); + cvt_df((double*)&fpr[reg_in3], (float*)&ps0_in3, &t); + + if (scalar & SCALAR_LOW) + ps0_in2 = qpr[reg_in2]; + + func(&t, &ps0_out, &ps0_in1, &ps0_in2, &ps0_in3); + + dprintk(KERN_INFO "PS3 ps0 -> f(0x%x, 0x%x, 0x%x) = 0x%x\n", + ps0_in1, ps0_in2, ps0_in3, ps0_out); + + if (!(scalar & SCALAR_NO_PS0)) + cvt_fd((float*)&ps0_out, (double*)&fpr[reg_out], &t); + + /* PS1 */ + ps1_in1 = qpr[reg_in1]; + ps1_in2 = qpr[reg_in2]; + ps1_in3 = qpr[reg_in3]; + + if (scalar & SCALAR_HIGH) + ps1_in2 = ps0_in2; + + if (!(scalar & SCALAR_NO_PS1)) + func(&t, &qpr[reg_out], &ps1_in1, &ps1_in2, &ps1_in3); + + dprintk(KERN_INFO "PS3 ps1 -> f(0x%x, 0x%x, 0x%x) = 0x%x\n", + ps1_in1, ps1_in2, ps1_in3, qpr[reg_out]); + + return EMULATE_DONE; +} + +static int kvmppc_ps_two_in(struct kvm_vcpu *vcpu, bool rc, + int reg_out, int reg_in1, int reg_in2, + int scalar, + void (*func)(struct thread_struct *t, + u32 *dst, u32 *src1, + u32 *src2)) +{ + u32 *qpr = vcpu->arch.qpr; + u64 *fpr = vcpu->arch.fpr; + u32 ps0_out; + u32 ps0_in1, ps0_in2; + u32 ps1_out; + u32 ps1_in1, ps1_in2; + struct thread_struct t; + t.fpscr.val = vcpu->arch.fpscr; + + /* RC */ + WARN_ON(rc); + + /* PS0 */ + cvt_df((double*)&fpr[reg_in1], (float*)&ps0_in1, &t); + + if (scalar & SCALAR_LOW) + ps0_in2 = qpr[reg_in2]; + else + cvt_df((double*)&fpr[reg_in2], (float*)&ps0_in2, &t); + + func(&t, &ps0_out, &ps0_in1, &ps0_in2); + + if (!(scalar & SCALAR_NO_PS0)) { + dprintk(KERN_INFO "PS2 ps0 -> f(0x%x, 0x%x) = 0x%x\n", + ps0_in1, ps0_in2, ps0_out); + + cvt_fd((float*)&ps0_out, (double*)&fpr[reg_out], &t); + } + + /* PS1 */ + ps1_in1 = qpr[reg_in1]; + ps1_in2 = qpr[reg_in2]; + + if (scalar & SCALAR_HIGH) + ps1_in2 = ps0_in2; + + func(&t, &ps1_out, &ps1_in1, &ps1_in2); + + if (!(scalar & SCALAR_NO_PS1)) { + qpr[reg_out] = ps1_out; + + dprintk(KERN_INFO "PS2 ps1 -> f(0x%x, 0x%x) = 0x%x\n", + ps1_in1, ps1_in2, qpr[reg_out]); + } + + return EMULATE_DONE; +} + +static int kvmppc_ps_one_in(struct kvm_vcpu *vcpu, bool rc, + int reg_out, int reg_in, + void (*func)(struct thread_struct *t, + u32 *dst, u32 *src1)) +{ + u32 *qpr = vcpu->arch.qpr; + u64 *fpr = vcpu->arch.fpr; + u32 ps0_out, ps0_in; + u32 ps1_in; + struct thread_struct t; + t.fpscr.val = vcpu->arch.fpscr; + + /* RC */ + WARN_ON(rc); + + /* PS0 */ + cvt_df((double*)&fpr[reg_in], (float*)&ps0_in, &t); + func(&t, &ps0_out, &ps0_in); + + dprintk(KERN_INFO "PS1 ps0 -> f(0x%x) = 0x%x\n", + ps0_in, ps0_out); + + cvt_fd((float*)&ps0_out, (double*)&fpr[reg_out], &t); + + /* PS1 */ + ps1_in = qpr[reg_in]; + func(&t, &qpr[reg_out], &ps1_in); + + dprintk(KERN_INFO "PS1 ps1 -> f(0x%x) = 0x%x\n", + ps1_in, qpr[reg_out]); + + return EMULATE_DONE; +} + +int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu) +{ + u32 inst = kvmppc_get_last_inst(vcpu); + enum emulation_result emulated = EMULATE_DONE; + + int ax_rd = inst_get_field(inst, 6, 10); + int ax_ra = inst_get_field(inst, 11, 15); + int ax_rb = inst_get_field(inst, 16, 20); + int ax_rc = inst_get_field(inst, 21, 25); + short full_d = inst_get_field(inst, 16, 31); + + u64 *fpr_d = &vcpu->arch.fpr[ax_rd]; + u64 *fpr_a = &vcpu->arch.fpr[ax_ra]; + u64 *fpr_b = &vcpu->arch.fpr[ax_rb]; + u64 *fpr_c = &vcpu->arch.fpr[ax_rc]; + + bool rcomp = (inst & 1) ? true : false; + u32 cr = kvmppc_get_cr(vcpu); + struct thread_struct t; +#ifdef DEBUG + int i; +#endif + + t.fpscr.val = vcpu->arch.fpscr; + + if (!kvmppc_inst_is_paired_single(vcpu, inst)) + return EMULATE_FAIL; + + if (!(vcpu->arch.msr & MSR_FP)) { + kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL); + return EMULATE_AGAIN; + } + + kvmppc_giveup_ext(vcpu, MSR_FP); + preempt_disable(); + enable_kernel_fp(); + /* Do we need to clear FE0 / FE1 here? Don't think so. */ + +#ifdef DEBUG + for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) { + u32 f; + cvt_df((double*)&vcpu->arch.fpr[i], (float*)&f, &t); + dprintk(KERN_INFO "FPR[%d] = 0x%x / 0x%llx QPR[%d] = 0x%x\n", + i, f, vcpu->arch.fpr[i], i, vcpu->arch.qpr[i]); + } +#endif + + switch (get_op(inst)) { + case OP_PSQ_L: + { + ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0; + bool w = inst_get_field(inst, 16, 16) ? true : false; + int i = inst_get_field(inst, 17, 19); + + addr += get_d_signext(inst); + emulated = kvmppc_emulate_psq_load(run, vcpu, ax_rd, addr, w, i); + break; + } + case OP_PSQ_LU: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra); + bool w = inst_get_field(inst, 16, 16) ? true : false; + int i = inst_get_field(inst, 17, 19); + + addr += get_d_signext(inst); + emulated = kvmppc_emulate_psq_load(run, vcpu, ax_rd, addr, w, i); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_PSQ_ST: + { + ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0; + bool w = inst_get_field(inst, 16, 16) ? true : false; + int i = inst_get_field(inst, 17, 19); + + addr += get_d_signext(inst); + emulated = kvmppc_emulate_psq_store(run, vcpu, ax_rd, addr, w, i); + break; + } + case OP_PSQ_STU: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra); + bool w = inst_get_field(inst, 16, 16) ? true : false; + int i = inst_get_field(inst, 17, 19); + + addr += get_d_signext(inst); + emulated = kvmppc_emulate_psq_store(run, vcpu, ax_rd, addr, w, i); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case 4: + /* X form */ + switch (inst_get_field(inst, 21, 30)) { + case OP_4X_PS_CMPU0: + /* XXX */ + emulated = EMULATE_FAIL; + break; + case OP_4X_PSQ_LX: + { + ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0; + bool w = inst_get_field(inst, 21, 21) ? true : false; + int i = inst_get_field(inst, 22, 24); + + addr += kvmppc_get_gpr(vcpu, ax_rb); + emulated = kvmppc_emulate_psq_load(run, vcpu, ax_rd, addr, w, i); + break; + } + case OP_4X_PS_CMPO0: + /* XXX */ + emulated = EMULATE_FAIL; + break; + case OP_4X_PSQ_LUX: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra); + bool w = inst_get_field(inst, 21, 21) ? true : false; + int i = inst_get_field(inst, 22, 24); + + addr += kvmppc_get_gpr(vcpu, ax_rb); + emulated = kvmppc_emulate_psq_load(run, vcpu, ax_rd, addr, w, i); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_4X_PS_NEG: + vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb]; + vcpu->arch.fpr[ax_rd] ^= 0x8000000000000000ULL; + vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; + vcpu->arch.qpr[ax_rd] ^= 0x80000000; + break; + case OP_4X_PS_CMPU1: + /* XXX */ + emulated = EMULATE_FAIL; + break; + case OP_4X_PS_MR: + WARN_ON(rcomp); + vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb]; + vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; + break; + case OP_4X_PS_CMPO1: + /* XXX */ + emulated = EMULATE_FAIL; + break; + case OP_4X_PS_NABS: + WARN_ON(rcomp); + vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb]; + vcpu->arch.fpr[ax_rd] |= 0x8000000000000000ULL; + vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; + vcpu->arch.qpr[ax_rd] |= 0x80000000; + break; + case OP_4X_PS_ABS: + WARN_ON(rcomp); + vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb]; + vcpu->arch.fpr[ax_rd] &= ~0x8000000000000000ULL; + vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; + vcpu->arch.qpr[ax_rd] &= ~0x80000000; + break; + case OP_4X_PS_MERGE00: + WARN_ON(rcomp); + vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_ra]; + /* vcpu->arch.qpr[ax_rd] = vcpu->arch.fpr[ax_rb]; */ + cvt_df((double*)&vcpu->arch.fpr[ax_rb], + (float*)&vcpu->arch.qpr[ax_rd], &t); + break; + case OP_4X_PS_MERGE01: + WARN_ON(rcomp); + vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_ra]; + vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; + break; + case OP_4X_PS_MERGE10: + WARN_ON(rcomp); + /* vcpu->arch.fpr[ax_rd] = vcpu->arch.qpr[ax_ra]; */ + cvt_fd((float*)&vcpu->arch.qpr[ax_ra], + (double*)&vcpu->arch.fpr[ax_rd], &t); + /* vcpu->arch.qpr[ax_rd] = vcpu->arch.fpr[ax_rb]; */ + cvt_df((double*)&vcpu->arch.fpr[ax_rb], + (float*)&vcpu->arch.qpr[ax_rd], &t); + break; + case OP_4X_PS_MERGE11: + WARN_ON(rcomp); + /* vcpu->arch.fpr[ax_rd] = vcpu->arch.qpr[ax_ra]; */ + cvt_fd((float*)&vcpu->arch.qpr[ax_ra], + (double*)&vcpu->arch.fpr[ax_rd], &t); + vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; + break; + } + /* XW form */ + switch (inst_get_field(inst, 25, 30)) { + case OP_4XW_PSQ_STX: + { + ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0; + bool w = inst_get_field(inst, 21, 21) ? true : false; + int i = inst_get_field(inst, 22, 24); + + addr += kvmppc_get_gpr(vcpu, ax_rb); + emulated = kvmppc_emulate_psq_store(run, vcpu, ax_rd, addr, w, i); + break; + } + case OP_4XW_PSQ_STUX: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra); + bool w = inst_get_field(inst, 21, 21) ? true : false; + int i = inst_get_field(inst, 22, 24); + + addr += kvmppc_get_gpr(vcpu, ax_rb); + emulated = kvmppc_emulate_psq_store(run, vcpu, ax_rd, addr, w, i); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + } + /* A form */ + switch (inst_get_field(inst, 26, 30)) { + case OP_4A_PS_SUM1: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_rb, ax_ra, SCALAR_NO_PS0 | SCALAR_HIGH, fps_fadds); + vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rc]; + break; + case OP_4A_PS_SUM0: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rb, SCALAR_NO_PS1 | SCALAR_LOW, fps_fadds); + vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rc]; + break; + case OP_4A_PS_MULS0: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, SCALAR_HIGH, fps_fmuls); + break; + case OP_4A_PS_MULS1: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, SCALAR_LOW, fps_fmuls); + break; + case OP_4A_PS_MADDS0: + emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, ax_rb, SCALAR_HIGH, fps_fmadds); + break; + case OP_4A_PS_MADDS1: + emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, ax_rb, SCALAR_LOW, fps_fmadds); + break; + case OP_4A_PS_DIV: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rb, SCALAR_NONE, fps_fdivs); + break; + case OP_4A_PS_SUB: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rb, SCALAR_NONE, fps_fsubs); + break; + case OP_4A_PS_ADD: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rb, SCALAR_NONE, fps_fadds); + break; + case OP_4A_PS_SEL: + emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fsel); + break; + case OP_4A_PS_RES: + emulated = kvmppc_ps_one_in(vcpu, rcomp, ax_rd, + ax_rb, fps_fres); + break; + case OP_4A_PS_MUL: + emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, SCALAR_NONE, fps_fmuls); + break; + case OP_4A_PS_RSQRTE: + emulated = kvmppc_ps_one_in(vcpu, rcomp, ax_rd, + ax_rb, fps_frsqrte); + break; + case OP_4A_PS_MSUB: + emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fmsubs); + break; + case OP_4A_PS_MADD: + emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fmadds); + break; + case OP_4A_PS_NMSUB: + emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fnmsubs); + break; + case OP_4A_PS_NMADD: + emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd, + ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fnmadds); + break; + } + break; + + /* Real FPU operations */ + + case OP_LFS: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + full_d; + + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, addr, + FPU_LS_SINGLE); + break; + } + case OP_LFSU: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + full_d; + + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, addr, + FPU_LS_SINGLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_LFD: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + full_d; + + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, addr, + FPU_LS_DOUBLE); + break; + } + case OP_LFDU: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + full_d; + + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, addr, + FPU_LS_DOUBLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_STFS: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + full_d; + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, addr, + FPU_LS_SINGLE); + break; + } + case OP_STFSU: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + full_d; + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, addr, + FPU_LS_SINGLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_STFD: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + full_d; + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, addr, + FPU_LS_DOUBLE); + break; + } + case OP_STFDU: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + full_d; + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, addr, + FPU_LS_DOUBLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case 31: + switch (inst_get_field(inst, 21, 30)) { + case OP_31_LFSX: + { + ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0; + + addr += kvmppc_get_gpr(vcpu, ax_rb); + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, + addr, FPU_LS_SINGLE); + break; + } + case OP_31_LFSUX: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, + addr, FPU_LS_SINGLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_31_LFDX: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, + addr, FPU_LS_DOUBLE); + break; + } + case OP_31_LFDUX: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, + addr, FPU_LS_DOUBLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_31_STFSX: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, + addr, FPU_LS_SINGLE); + break; + } + case OP_31_STFSUX: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, + addr, FPU_LS_SINGLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_31_STFX: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, + addr, FPU_LS_DOUBLE); + break; + } + case OP_31_STFUX: + { + ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, + addr, FPU_LS_DOUBLE); + + if (emulated == EMULATE_DONE) + kvmppc_set_gpr(vcpu, ax_ra, addr); + break; + } + case OP_31_STFIWX: + { + ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + + kvmppc_get_gpr(vcpu, ax_rb); + + emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, + addr, + FPU_LS_SINGLE_LOW); + break; + } + break; + } + break; + case 59: + switch (inst_get_field(inst, 21, 30)) { + case OP_59_FADDS: + fpd_fadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FSUBS: + fpd_fsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FDIVS: + fpd_fdivs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FRES: + fpd_fres(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FRSQRTES: + fpd_frsqrtes(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + } + switch (inst_get_field(inst, 26, 30)) { + case OP_59_FMULS: + fpd_fmuls(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FMSUBS: + fpd_fmsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FMADDS: + fpd_fmadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FNMSUBS: + fpd_fnmsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_59_FNMADDS: + fpd_fnmadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + } + break; + case 63: + switch (inst_get_field(inst, 21, 30)) { + case OP_63_MTFSB0: + case OP_63_MTFSB1: + case OP_63_MCRFS: + case OP_63_MTFSFI: + /* XXX need to implement */ + break; + case OP_63_MFFS: + /* XXX missing CR */ + *fpr_d = vcpu->arch.fpscr; + break; + case OP_63_MTFSF: + /* XXX missing fm bits */ + /* XXX missing CR */ + vcpu->arch.fpscr = *fpr_b; + break; + case OP_63_FCMPU: + { + u32 tmp_cr; + u32 cr0_mask = 0xf0000000; + u32 cr_shift = inst_get_field(inst, 6, 8) * 4; + + fpd_fcmpu(&vcpu->arch.fpscr, &tmp_cr, fpr_a, fpr_b); + cr &= ~(cr0_mask >> cr_shift); + cr |= (cr & cr0_mask) >> cr_shift; + break; + } + case OP_63_FCMPO: + { + u32 tmp_cr; + u32 cr0_mask = 0xf0000000; + u32 cr_shift = inst_get_field(inst, 6, 8) * 4; + + fpd_fcmpo(&vcpu->arch.fpscr, &tmp_cr, fpr_a, fpr_b); + cr &= ~(cr0_mask >> cr_shift); + cr |= (cr & cr0_mask) >> cr_shift; + break; + } + case OP_63_FNEG: + fpd_fneg(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + break; + case OP_63_FMR: + *fpr_d = *fpr_b; + break; + case OP_63_FABS: + fpd_fabs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + break; + case OP_63_FCPSGN: + fpd_fcpsgn(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + break; + case OP_63_FDIV: + fpd_fdiv(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + break; + case OP_63_FADD: + fpd_fadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + break; + case OP_63_FSUB: + fpd_fsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + break; + case OP_63_FCTIW: + fpd_fctiw(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + break; + case OP_63_FCTIWZ: + fpd_fctiwz(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + break; + case OP_63_FRSP: + fpd_frsp(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + kvmppc_sync_qpr(vcpu, ax_rd); + break; + case OP_63_FRSQRTE: + { + double one = 1.0f; + + /* fD = sqrt(fB) */ + fpd_fsqrt(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + /* fD = 1.0f / fD */ + fpd_fdiv(&vcpu->arch.fpscr, &cr, fpr_d, (u64*)&one, fpr_d); + break; + } + } + switch (inst_get_field(inst, 26, 30)) { + case OP_63_FMUL: + fpd_fmul(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c); + break; + case OP_63_FSEL: + fpd_fsel(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + break; + case OP_63_FMSUB: + fpd_fmsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + break; + case OP_63_FMADD: + fpd_fmadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + break; + case OP_63_FNMSUB: + fpd_fnmsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + break; + case OP_63_FNMADD: + fpd_fnmadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + break; + } + break; + } + +#ifdef DEBUG + for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) { + u32 f; + cvt_df((double*)&vcpu->arch.fpr[i], (float*)&f, &t); + dprintk(KERN_INFO "FPR[%d] = 0x%x\n", i, f); + } +#endif + + if (rcomp) + kvmppc_set_cr(vcpu, cr); + + preempt_enable(); + + return emulated; +} diff --git a/arch/powerpc/kvm/book3s_64_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index c83c60ad96c5..506d5c316c96 100644 --- a/arch/powerpc/kvm/book3s_64_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -22,7 +22,10 @@ #include <asm/reg.h> #include <asm/page.h> #include <asm/asm-offsets.h> + +#ifdef CONFIG_PPC_BOOK3S_64 #include <asm/exception-64s.h> +#endif /***************************************************************************** * * @@ -30,6 +33,39 @@ * * ****************************************************************************/ +#if defined(CONFIG_PPC_BOOK3S_64) + +#define LOAD_SHADOW_VCPU(reg) \ + mfspr reg, SPRN_SPRG_PACA + +#define SHADOW_VCPU_OFF PACA_KVM_SVCPU +#define MSR_NOIRQ MSR_KERNEL & ~(MSR_IR | MSR_DR) +#define FUNC(name) GLUE(.,name) + +#elif defined(CONFIG_PPC_BOOK3S_32) + +#define LOAD_SHADOW_VCPU(reg) \ + mfspr reg, SPRN_SPRG_THREAD; \ + lwz reg, THREAD_KVM_SVCPU(reg); \ + /* PPC32 can have a NULL pointer - let's check for that */ \ + mtspr SPRN_SPRG_SCRATCH1, r12; /* Save r12 */ \ + mfcr r12; \ + cmpwi reg, 0; \ + bne 1f; \ + mfspr reg, SPRN_SPRG_SCRATCH0; \ + mtcr r12; \ + mfspr r12, SPRN_SPRG_SCRATCH1; \ + b kvmppc_resume_\intno; \ +1:; \ + mtcr r12; \ + mfspr r12, SPRN_SPRG_SCRATCH1; \ + tophys(reg, reg) + +#define SHADOW_VCPU_OFF 0 +#define MSR_NOIRQ MSR_KERNEL +#define FUNC(name) name + +#endif .macro INTERRUPT_TRAMPOLINE intno @@ -42,19 +78,19 @@ kvmppc_trampoline_\intno: * First thing to do is to find out if we're coming * from a KVM guest or a Linux process. * - * To distinguish, we check a magic byte in the PACA + * To distinguish, we check a magic byte in the PACA/current */ - mfspr r13, SPRN_SPRG_PACA /* r13 = PACA */ - std r12, PACA_KVM_SCRATCH0(r13) + LOAD_SHADOW_VCPU(r13) + PPC_STL r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) mfcr r12 - stw r12, PACA_KVM_SCRATCH1(r13) - lbz r12, PACA_KVM_IN_GUEST(r13) + stw r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) + lbz r12, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13) cmpwi r12, KVM_GUEST_MODE_NONE bne ..kvmppc_handler_hasmagic_\intno /* No KVM guest? Then jump back to the Linux handler! */ - lwz r12, PACA_KVM_SCRATCH1(r13) + lwz r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) mtcr r12 - ld r12, PACA_KVM_SCRATCH0(r13) + PPC_LL r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) mfspr r13, SPRN_SPRG_SCRATCH0 /* r13 = original r13 */ b kvmppc_resume_\intno /* Get back original handler */ @@ -76,9 +112,7 @@ kvmppc_trampoline_\intno: INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_SYSTEM_RESET INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_MACHINE_CHECK INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_DATA_STORAGE -INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_DATA_SEGMENT INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_INST_STORAGE -INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_INST_SEGMENT INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_EXTERNAL INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_ALIGNMENT INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_PROGRAM @@ -88,7 +122,14 @@ INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_SYSCALL INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_TRACE INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_PERFMON INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_ALTIVEC + +/* Those are only available on 64 bit machines */ + +#ifdef CONFIG_PPC_BOOK3S_64 +INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_DATA_SEGMENT +INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_INST_SEGMENT INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_VSX +#endif /* * Bring us back to the faulting code, but skip the @@ -99,11 +140,11 @@ INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_VSX * * Input Registers: * - * R12 = free - * R13 = PACA - * PACA.KVM.SCRATCH0 = guest R12 - * PACA.KVM.SCRATCH1 = guest CR - * SPRG_SCRATCH0 = guest R13 + * R12 = free + * R13 = Shadow VCPU (PACA) + * SVCPU.SCRATCH0 = guest R12 + * SVCPU.SCRATCH1 = guest CR + * SPRG_SCRATCH0 = guest R13 * */ kvmppc_handler_skip_ins: @@ -114,9 +155,9 @@ kvmppc_handler_skip_ins: mtsrr0 r12 /* Clean up all state */ - lwz r12, PACA_KVM_SCRATCH1(r13) + lwz r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) mtcr r12 - ld r12, PACA_KVM_SCRATCH0(r13) + PPC_LL r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) mfspr r13, SPRN_SPRG_SCRATCH0 /* And get back into the code */ @@ -147,41 +188,48 @@ kvmppc_handler_lowmem_trampoline_end: * * R3 = function * R4 = MSR - * R5 = CTR + * R5 = scratch register * */ _GLOBAL(kvmppc_rmcall) - mtmsr r4 /* Disable relocation, so mtsrr + LOAD_REG_IMMEDIATE(r5, MSR_NOIRQ) + mtmsr r5 /* Disable relocation and interrupts, so mtsrr doesn't get interrupted */ - mtctr r5 + sync mtsrr0 r3 mtsrr1 r4 RFI +#if defined(CONFIG_PPC_BOOK3S_32) +#define STACK_LR INT_FRAME_SIZE+4 +#elif defined(CONFIG_PPC_BOOK3S_64) +#define STACK_LR _LINK +#endif + /* * Activate current's external feature (FPU/Altivec/VSX) */ -#define define_load_up(what) \ - \ -_GLOBAL(kvmppc_load_up_ ## what); \ - subi r1, r1, INT_FRAME_SIZE; \ - mflr r3; \ - std r3, _LINK(r1); \ - mfmsr r4; \ - std r31, GPR3(r1); \ - mr r31, r4; \ - li r5, MSR_DR; \ - oris r5, r5, MSR_EE@h; \ - andc r4, r4, r5; \ - mtmsr r4; \ - \ - bl .load_up_ ## what; \ - \ - mtmsr r31; \ - ld r3, _LINK(r1); \ - ld r31, GPR3(r1); \ - addi r1, r1, INT_FRAME_SIZE; \ - mtlr r3; \ +#define define_load_up(what) \ + \ +_GLOBAL(kvmppc_load_up_ ## what); \ + PPC_STLU r1, -INT_FRAME_SIZE(r1); \ + mflr r3; \ + PPC_STL r3, STACK_LR(r1); \ + PPC_STL r20, _NIP(r1); \ + mfmsr r20; \ + LOAD_REG_IMMEDIATE(r3, MSR_DR|MSR_EE); \ + andc r3,r20,r3; /* Disable DR,EE */ \ + mtmsr r3; \ + sync; \ + \ + bl FUNC(load_up_ ## what); \ + \ + mtmsr r20; /* Enable DR,EE */ \ + sync; \ + PPC_LL r3, STACK_LR(r1); \ + PPC_LL r20, _NIP(r1); \ + mtlr r3; \ + addi r1, r1, INT_FRAME_SIZE; \ blr define_load_up(fpu) @@ -194,11 +242,10 @@ define_load_up(vsx) .global kvmppc_trampoline_lowmem kvmppc_trampoline_lowmem: - .long kvmppc_handler_lowmem_trampoline - _stext + .long kvmppc_handler_lowmem_trampoline - CONFIG_KERNEL_START .global kvmppc_trampoline_enter kvmppc_trampoline_enter: - .long kvmppc_handler_trampoline_enter - _stext - -#include "book3s_64_slb.S" + .long kvmppc_handler_trampoline_enter - CONFIG_KERNEL_START +#include "book3s_segment.S" diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S new file mode 100644 index 000000000000..7c52ed0b7051 --- /dev/null +++ b/arch/powerpc/kvm/book3s_segment.S @@ -0,0 +1,259 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright SUSE Linux Products GmbH 2010 + * + * Authors: Alexander Graf <agraf@suse.de> + */ + +/* Real mode helpers */ + +#if defined(CONFIG_PPC_BOOK3S_64) + +#define GET_SHADOW_VCPU(reg) \ + addi reg, r13, PACA_KVM_SVCPU + +#elif defined(CONFIG_PPC_BOOK3S_32) + +#define GET_SHADOW_VCPU(reg) \ + tophys(reg, r2); \ + lwz reg, (THREAD + THREAD_KVM_SVCPU)(reg); \ + tophys(reg, reg) + +#endif + +/* Disable for nested KVM */ +#define USE_QUICK_LAST_INST + + +/* Get helper functions for subarch specific functionality */ + +#if defined(CONFIG_PPC_BOOK3S_64) +#include "book3s_64_slb.S" +#elif defined(CONFIG_PPC_BOOK3S_32) +#include "book3s_32_sr.S" +#endif + +/****************************************************************************** + * * + * Entry code * + * * + *****************************************************************************/ + +.global kvmppc_handler_trampoline_enter +kvmppc_handler_trampoline_enter: + + /* Required state: + * + * MSR = ~IR|DR + * R13 = PACA + * R1 = host R1 + * R2 = host R2 + * R10 = guest MSR + * all other volatile GPRS = free + * SVCPU[CR] = guest CR + * SVCPU[XER] = guest XER + * SVCPU[CTR] = guest CTR + * SVCPU[LR] = guest LR + */ + + /* r3 = shadow vcpu */ + GET_SHADOW_VCPU(r3) + + /* Move SRR0 and SRR1 into the respective regs */ + PPC_LL r9, SVCPU_PC(r3) + mtsrr0 r9 + mtsrr1 r10 + + /* Activate guest mode, so faults get handled by KVM */ + li r11, KVM_GUEST_MODE_GUEST + stb r11, SVCPU_IN_GUEST(r3) + + /* Switch to guest segment. This is subarch specific. */ + LOAD_GUEST_SEGMENTS + + /* Enter guest */ + + PPC_LL r4, (SVCPU_CTR)(r3) + PPC_LL r5, (SVCPU_LR)(r3) + lwz r6, (SVCPU_CR)(r3) + lwz r7, (SVCPU_XER)(r3) + + mtctr r4 + mtlr r5 + mtcr r6 + mtxer r7 + + PPC_LL r0, (SVCPU_R0)(r3) + PPC_LL r1, (SVCPU_R1)(r3) + PPC_LL r2, (SVCPU_R2)(r3) + PPC_LL r4, (SVCPU_R4)(r3) + PPC_LL r5, (SVCPU_R5)(r3) + PPC_LL r6, (SVCPU_R6)(r3) + PPC_LL r7, (SVCPU_R7)(r3) + PPC_LL r8, (SVCPU_R8)(r3) + PPC_LL r9, (SVCPU_R9)(r3) + PPC_LL r10, (SVCPU_R10)(r3) + PPC_LL r11, (SVCPU_R11)(r3) + PPC_LL r12, (SVCPU_R12)(r3) + PPC_LL r13, (SVCPU_R13)(r3) + + PPC_LL r3, (SVCPU_R3)(r3) + + RFI +kvmppc_handler_trampoline_enter_end: + + + +/****************************************************************************** + * * + * Exit code * + * * + *****************************************************************************/ + +.global kvmppc_handler_trampoline_exit +kvmppc_handler_trampoline_exit: + + /* Register usage at this point: + * + * SPRG_SCRATCH0 = guest R13 + * R12 = exit handler id + * R13 = shadow vcpu - SHADOW_VCPU_OFF [=PACA on PPC64] + * SVCPU.SCRATCH0 = guest R12 + * SVCPU.SCRATCH1 = guest CR + * + */ + + /* Save registers */ + + PPC_STL r0, (SHADOW_VCPU_OFF + SVCPU_R0)(r13) + PPC_STL r1, (SHADOW_VCPU_OFF + SVCPU_R1)(r13) + PPC_STL r2, (SHADOW_VCPU_OFF + SVCPU_R2)(r13) + PPC_STL r3, (SHADOW_VCPU_OFF + SVCPU_R3)(r13) + PPC_STL r4, (SHADOW_VCPU_OFF + SVCPU_R4)(r13) + PPC_STL r5, (SHADOW_VCPU_OFF + SVCPU_R5)(r13) + PPC_STL r6, (SHADOW_VCPU_OFF + SVCPU_R6)(r13) + PPC_STL r7, (SHADOW_VCPU_OFF + SVCPU_R7)(r13) + PPC_STL r8, (SHADOW_VCPU_OFF + SVCPU_R8)(r13) + PPC_STL r9, (SHADOW_VCPU_OFF + SVCPU_R9)(r13) + PPC_STL r10, (SHADOW_VCPU_OFF + SVCPU_R10)(r13) + PPC_STL r11, (SHADOW_VCPU_OFF + SVCPU_R11)(r13) + + /* Restore R1/R2 so we can handle faults */ + PPC_LL r1, (SHADOW_VCPU_OFF + SVCPU_HOST_R1)(r13) + PPC_LL r2, (SHADOW_VCPU_OFF + SVCPU_HOST_R2)(r13) + + /* Save guest PC and MSR */ + mfsrr0 r3 + mfsrr1 r4 + + PPC_STL r3, (SHADOW_VCPU_OFF + SVCPU_PC)(r13) + PPC_STL r4, (SHADOW_VCPU_OFF + SVCPU_SHADOW_SRR1)(r13) + + /* Get scratch'ed off registers */ + mfspr r9, SPRN_SPRG_SCRATCH0 + PPC_LL r8, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13) + lwz r7, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13) + + PPC_STL r9, (SHADOW_VCPU_OFF + SVCPU_R13)(r13) + PPC_STL r8, (SHADOW_VCPU_OFF + SVCPU_R12)(r13) + stw r7, (SHADOW_VCPU_OFF + SVCPU_CR)(r13) + + /* Save more register state */ + + mfxer r5 + mfdar r6 + mfdsisr r7 + mfctr r8 + mflr r9 + + stw r5, (SHADOW_VCPU_OFF + SVCPU_XER)(r13) + PPC_STL r6, (SHADOW_VCPU_OFF + SVCPU_FAULT_DAR)(r13) + stw r7, (SHADOW_VCPU_OFF + SVCPU_FAULT_DSISR)(r13) + PPC_STL r8, (SHADOW_VCPU_OFF + SVCPU_CTR)(r13) + PPC_STL r9, (SHADOW_VCPU_OFF + SVCPU_LR)(r13) + + /* + * In order for us to easily get the last instruction, + * we got the #vmexit at, we exploit the fact that the + * virtual layout is still the same here, so we can just + * ld from the guest's PC address + */ + + /* We only load the last instruction when it's safe */ + cmpwi r12, BOOK3S_INTERRUPT_DATA_STORAGE + beq ld_last_inst + cmpwi r12, BOOK3S_INTERRUPT_PROGRAM + beq ld_last_inst + cmpwi r12, BOOK3S_INTERRUPT_ALIGNMENT + beq- ld_last_inst + + b no_ld_last_inst + +ld_last_inst: + /* Save off the guest instruction we're at */ + + /* In case lwz faults */ + li r0, KVM_INST_FETCH_FAILED + +#ifdef USE_QUICK_LAST_INST + + /* Set guest mode to 'jump over instruction' so if lwz faults + * we'll just continue at the next IP. */ + li r9, KVM_GUEST_MODE_SKIP + stb r9, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13) + + /* 1) enable paging for data */ + mfmsr r9 + ori r11, r9, MSR_DR /* Enable paging for data */ + mtmsr r11 + sync + /* 2) fetch the instruction */ + lwz r0, 0(r3) + /* 3) disable paging again */ + mtmsr r9 + sync + +#endif + stw r0, (SHADOW_VCPU_OFF + SVCPU_LAST_INST)(r13) + +no_ld_last_inst: + + /* Unset guest mode */ + li r9, KVM_GUEST_MODE_NONE + stb r9, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13) + + /* Switch back to host MMU */ + LOAD_HOST_SEGMENTS + + /* Register usage at this point: + * + * R1 = host R1 + * R2 = host R2 + * R12 = exit handler id + * R13 = shadow vcpu - SHADOW_VCPU_OFF [=PACA on PPC64] + * SVCPU.* = guest * + * + */ + + /* RFI into the highmem handler */ + mfmsr r7 + ori r7, r7, MSR_IR|MSR_DR|MSR_RI|MSR_ME /* Enable paging */ + mtsrr1 r7 + /* Load highmem handler address */ + PPC_LL r8, (SHADOW_VCPU_OFF + SVCPU_VMHANDLER)(r13) + mtsrr0 r8 + + RFI +kvmppc_handler_trampoline_exit_end: diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 2a3a1953d4bd..c92224071021 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -133,6 +133,12 @@ void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_EXTERNAL); } +void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu, + struct kvm_interrupt *irq) +{ + clear_bit(BOOKE_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions); +} + /* Deliver the interrupt of the corresponding priority, if possible. */ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority) diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index cb72a65f4ecc..4568ec386c2a 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -38,10 +38,12 @@ #define OP_31_XOP_LBZX 87 #define OP_31_XOP_STWX 151 #define OP_31_XOP_STBX 215 +#define OP_31_XOP_LBZUX 119 #define OP_31_XOP_STBUX 247 #define OP_31_XOP_LHZX 279 #define OP_31_XOP_LHZUX 311 #define OP_31_XOP_MFSPR 339 +#define OP_31_XOP_LHAX 343 #define OP_31_XOP_STHX 407 #define OP_31_XOP_STHUX 439 #define OP_31_XOP_MTSPR 467 @@ -62,10 +64,12 @@ #define OP_STBU 39 #define OP_LHZ 40 #define OP_LHZU 41 +#define OP_LHA 42 +#define OP_LHAU 43 #define OP_STH 44 #define OP_STHU 45 -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S static int kvmppc_dec_enabled(struct kvm_vcpu *vcpu) { return 1; @@ -82,7 +86,7 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu) unsigned long dec_nsec; pr_debug("mtDEC: %x\n", vcpu->arch.dec); -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S /* mtdec lowers the interrupt line when positive. */ kvmppc_core_dequeue_dec(vcpu); @@ -128,7 +132,7 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu) * from opcode tables in the future. */ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) { - u32 inst = vcpu->arch.last_inst; + u32 inst = kvmppc_get_last_inst(vcpu); u32 ea; int ra; int rb; @@ -143,13 +147,9 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) pr_debug(KERN_INFO "Emulating opcode %d / %d\n", get_op(inst), get_xop(inst)); - /* Try again next time */ - if (inst == KVM_INST_FETCH_FAILED) - return EMULATE_DONE; - switch (get_op(inst)) { case OP_TRAP: -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S case OP_TRAP_64: kvmppc_core_queue_program(vcpu, SRR1_PROGTRAP); #else @@ -171,6 +171,19 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1); break; + case OP_31_XOP_LBZUX: + rt = get_rt(inst); + ra = get_ra(inst); + rb = get_rb(inst); + + ea = kvmppc_get_gpr(vcpu, rb); + if (ra) + ea += kvmppc_get_gpr(vcpu, ra); + + emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1); + kvmppc_set_gpr(vcpu, ra, ea); + break; + case OP_31_XOP_STWX: rs = get_rs(inst); emulated = kvmppc_handle_store(run, vcpu, @@ -200,6 +213,11 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) kvmppc_set_gpr(vcpu, rs, ea); break; + case OP_31_XOP_LHAX: + rt = get_rt(inst); + emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1); + break; + case OP_31_XOP_LHZX: rt = get_rt(inst); emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1); @@ -450,6 +468,18 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed); break; + case OP_LHA: + rt = get_rt(inst); + emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1); + break; + + case OP_LHAU: + ra = get_ra(inst); + rt = get_rt(inst); + emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed); + break; + case OP_STH: rs = get_rs(inst); emulated = kvmppc_handle_store(run, vcpu, @@ -472,7 +502,9 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) if (emulated == EMULATE_FAIL) { emulated = kvmppc_core_emulate_op(run, vcpu, inst, &advance); - if (emulated == EMULATE_FAIL) { + if (emulated == EMULATE_AGAIN) { + advance = 0; + } else if (emulated == EMULATE_FAIL) { advance = 0; printk(KERN_ERR "Couldn't emulate instruction 0x%08x " "(op %d xop %d)\n", inst, get_op(inst), get_xop(inst)); @@ -480,10 +512,11 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) } } - trace_kvm_ppc_instr(inst, vcpu->arch.pc, emulated); + trace_kvm_ppc_instr(inst, kvmppc_get_pc(vcpu), emulated); + /* Advance past emulated instruction. */ if (advance) - vcpu->arch.pc += 4; /* Advance past emulated instruction. */ + kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4); return emulated; } diff --git a/arch/powerpc/kvm/fpu.S b/arch/powerpc/kvm/fpu.S new file mode 100644 index 000000000000..2b340a3eee90 --- /dev/null +++ b/arch/powerpc/kvm/fpu.S @@ -0,0 +1,273 @@ +/* + * FPU helper code to use FPU operations from inside the kernel + * + * Copyright (C) 2010 Alexander Graf (agraf@suse.de) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include <asm/reg.h> +#include <asm/page.h> +#include <asm/mmu.h> +#include <asm/pgtable.h> +#include <asm/cputable.h> +#include <asm/cache.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> + +/* Instructions operating on single parameters */ + +/* + * Single operation with one input operand + * + * R3 = (double*)&fpscr + * R4 = (short*)&result + * R5 = (short*)¶m1 + */ +#define FPS_ONE_IN(name) \ +_GLOBAL(fps_ ## name); \ + lfd 0,0(r3); /* load up fpscr value */ \ + MTFSF_L(0); \ + lfs 0,0(r5); \ + \ + name 0,0; \ + \ + stfs 0,0(r4); \ + mffs 0; \ + stfd 0,0(r3); /* save new fpscr value */ \ + blr + +/* + * Single operation with two input operands + * + * R3 = (double*)&fpscr + * R4 = (short*)&result + * R5 = (short*)¶m1 + * R6 = (short*)¶m2 + */ +#define FPS_TWO_IN(name) \ +_GLOBAL(fps_ ## name); \ + lfd 0,0(r3); /* load up fpscr value */ \ + MTFSF_L(0); \ + lfs 0,0(r5); \ + lfs 1,0(r6); \ + \ + name 0,0,1; \ + \ + stfs 0,0(r4); \ + mffs 0; \ + stfd 0,0(r3); /* save new fpscr value */ \ + blr + +/* + * Single operation with three input operands + * + * R3 = (double*)&fpscr + * R4 = (short*)&result + * R5 = (short*)¶m1 + * R6 = (short*)¶m2 + * R7 = (short*)¶m3 + */ +#define FPS_THREE_IN(name) \ +_GLOBAL(fps_ ## name); \ + lfd 0,0(r3); /* load up fpscr value */ \ + MTFSF_L(0); \ + lfs 0,0(r5); \ + lfs 1,0(r6); \ + lfs 2,0(r7); \ + \ + name 0,0,1,2; \ + \ + stfs 0,0(r4); \ + mffs 0; \ + stfd 0,0(r3); /* save new fpscr value */ \ + blr + +FPS_ONE_IN(fres) +FPS_ONE_IN(frsqrte) +FPS_ONE_IN(fsqrts) +FPS_TWO_IN(fadds) +FPS_TWO_IN(fdivs) +FPS_TWO_IN(fmuls) +FPS_TWO_IN(fsubs) +FPS_THREE_IN(fmadds) +FPS_THREE_IN(fmsubs) +FPS_THREE_IN(fnmadds) +FPS_THREE_IN(fnmsubs) +FPS_THREE_IN(fsel) + + +/* Instructions operating on double parameters */ + +/* + * Beginning of double instruction processing + * + * R3 = (double*)&fpscr + * R4 = (u32*)&cr + * R5 = (double*)&result + * R6 = (double*)¶m1 + * R7 = (double*)¶m2 [load_two] + * R8 = (double*)¶m3 [load_three] + * LR = instruction call function + */ +fpd_load_three: + lfd 2,0(r8) /* load param3 */ +fpd_load_two: + lfd 1,0(r7) /* load param2 */ +fpd_load_one: + lfd 0,0(r6) /* load param1 */ +fpd_load_none: + lfd 3,0(r3) /* load up fpscr value */ + MTFSF_L(3) + lwz r6, 0(r4) /* load cr */ + mtcr r6 + blr + +/* + * End of double instruction processing + * + * R3 = (double*)&fpscr + * R4 = (u32*)&cr + * R5 = (double*)&result + * LR = caller of instruction call function + */ +fpd_return: + mfcr r6 + stfd 0,0(r5) /* save result */ + mffs 0 + stfd 0,0(r3) /* save new fpscr value */ + stw r6,0(r4) /* save new cr value */ + blr + +/* + * Double operation with no input operand + * + * R3 = (double*)&fpscr + * R4 = (u32*)&cr + * R5 = (double*)&result + */ +#define FPD_NONE_IN(name) \ +_GLOBAL(fpd_ ## name); \ + mflr r12; \ + bl fpd_load_none; \ + mtlr r12; \ + \ + name. 0; /* call instruction */ \ + b fpd_return + +/* + * Double operation with one input operand + * + * R3 = (double*)&fpscr + * R4 = (u32*)&cr + * R5 = (double*)&result + * R6 = (double*)¶m1 + */ +#define FPD_ONE_IN(name) \ +_GLOBAL(fpd_ ## name); \ + mflr r12; \ + bl fpd_load_one; \ + mtlr r12; \ + \ + name. 0,0; /* call instruction */ \ + b fpd_return + +/* + * Double operation with two input operands + * + * R3 = (double*)&fpscr + * R4 = (u32*)&cr + * R5 = (double*)&result + * R6 = (double*)¶m1 + * R7 = (double*)¶m2 + * R8 = (double*)¶m3 + */ +#define FPD_TWO_IN(name) \ +_GLOBAL(fpd_ ## name); \ + mflr r12; \ + bl fpd_load_two; \ + mtlr r12; \ + \ + name. 0,0,1; /* call instruction */ \ + b fpd_return + +/* + * CR Double operation with two input operands + * + * R3 = (double*)&fpscr + * R4 = (u32*)&cr + * R5 = (double*)¶m1 + * R6 = (double*)¶m2 + * R7 = (double*)¶m3 + */ +#define FPD_TWO_IN_CR(name) \ +_GLOBAL(fpd_ ## name); \ + lfd 1,0(r6); /* load param2 */ \ + lfd 0,0(r5); /* load param1 */ \ + lfd 3,0(r3); /* load up fpscr value */ \ + MTFSF_L(3); \ + lwz r6, 0(r4); /* load cr */ \ + mtcr r6; \ + \ + name 0,0,1; /* call instruction */ \ + mfcr r6; \ + mffs 0; \ + stfd 0,0(r3); /* save new fpscr value */ \ + stw r6,0(r4); /* save new cr value */ \ + blr + +/* + * Double operation with three input operands + * + * R3 = (double*)&fpscr + * R4 = (u32*)&cr + * R5 = (double*)&result + * R6 = (double*)¶m1 + * R7 = (double*)¶m2 + * R8 = (double*)¶m3 + */ +#define FPD_THREE_IN(name) \ +_GLOBAL(fpd_ ## name); \ + mflr r12; \ + bl fpd_load_three; \ + mtlr r12; \ + \ + name. 0,0,1,2; /* call instruction */ \ + b fpd_return + +FPD_ONE_IN(fsqrts) +FPD_ONE_IN(frsqrtes) +FPD_ONE_IN(fres) +FPD_ONE_IN(frsp) +FPD_ONE_IN(fctiw) +FPD_ONE_IN(fctiwz) +FPD_ONE_IN(fsqrt) +FPD_ONE_IN(fre) +FPD_ONE_IN(frsqrte) +FPD_ONE_IN(fneg) +FPD_ONE_IN(fabs) +FPD_TWO_IN(fadds) +FPD_TWO_IN(fsubs) +FPD_TWO_IN(fdivs) +FPD_TWO_IN(fmuls) +FPD_TWO_IN_CR(fcmpu) +FPD_TWO_IN(fcpsgn) +FPD_TWO_IN(fdiv) +FPD_TWO_IN(fadd) +FPD_TWO_IN(fmul) +FPD_TWO_IN_CR(fcmpo) +FPD_TWO_IN(fsub) +FPD_THREE_IN(fmsubs) +FPD_THREE_IN(fmadds) +FPD_THREE_IN(fnmsubs) +FPD_THREE_IN(fnmadds) +FPD_THREE_IN(fsel) +FPD_THREE_IN(fmsub) +FPD_THREE_IN(fmadd) +FPD_THREE_IN(fnmsub) +FPD_THREE_IN(fnmadd) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 297fcd2ff7d0..9b8683f39e05 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -70,7 +70,7 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu) case EMULATE_FAIL: /* XXX Deliver Program interrupt to guest. */ printk(KERN_EMERG "%s: emulation failed (%08x)\n", __func__, - vcpu->arch.last_inst); + kvmppc_get_last_inst(vcpu)); r = RESUME_HOST; break; default: @@ -148,6 +148,10 @@ int kvm_dev_ioctl_check_extension(long ext) switch (ext) { case KVM_CAP_PPC_SEGSTATE: + case KVM_CAP_PPC_PAIRED_SINGLES: + case KVM_CAP_PPC_UNSET_IRQ: + case KVM_CAP_ENABLE_CAP: + case KVM_CAP_PPC_OSI: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -193,12 +197,17 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) { struct kvm_vcpu *vcpu; vcpu = kvmppc_core_vcpu_create(kvm, id); - kvmppc_create_vcpu_debugfs(vcpu, id); + if (!IS_ERR(vcpu)) + kvmppc_create_vcpu_debugfs(vcpu, id); return vcpu; } void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { + /* Make sure we're not using the vcpu anymore */ + hrtimer_cancel(&vcpu->arch.dec_timer); + tasklet_kill(&vcpu->arch.tasklet); + kvmppc_remove_vcpu_debugfs(vcpu); kvmppc_core_vcpu_free(vcpu); } @@ -278,7 +287,7 @@ static void kvmppc_complete_dcr_load(struct kvm_vcpu *vcpu, static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run) { - ulong gpr; + u64 gpr; if (run->mmio.len > sizeof(gpr)) { printk(KERN_ERR "bad MMIO length: %d\n", run->mmio.len); @@ -287,6 +296,7 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, if (vcpu->arch.mmio_is_bigendian) { switch (run->mmio.len) { + case 8: gpr = *(u64 *)run->mmio.data; break; case 4: gpr = *(u32 *)run->mmio.data; break; case 2: gpr = *(u16 *)run->mmio.data; break; case 1: gpr = *(u8 *)run->mmio.data; break; @@ -300,7 +310,43 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, } } + if (vcpu->arch.mmio_sign_extend) { + switch (run->mmio.len) { +#ifdef CONFIG_PPC64 + case 4: + gpr = (s64)(s32)gpr; + break; +#endif + case 2: + gpr = (s64)(s16)gpr; + break; + case 1: + gpr = (s64)(s8)gpr; + break; + } + } + kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr); + + switch (vcpu->arch.io_gpr & KVM_REG_EXT_MASK) { + case KVM_REG_GPR: + kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr); + break; + case KVM_REG_FPR: + vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr; + break; +#ifdef CONFIG_PPC_BOOK3S + case KVM_REG_QPR: + vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr; + break; + case KVM_REG_FQPR: + vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr; + vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr; + break; +#endif + default: + BUG(); + } } int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, @@ -319,12 +365,25 @@ int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->arch.mmio_is_bigendian = is_bigendian; vcpu->mmio_needed = 1; vcpu->mmio_is_write = 0; + vcpu->arch.mmio_sign_extend = 0; return EMULATE_DO_MMIO; } +/* Same as above, but sign extends */ +int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int rt, unsigned int bytes, int is_bigendian) +{ + int r; + + r = kvmppc_handle_load(run, vcpu, rt, bytes, is_bigendian); + vcpu->arch.mmio_sign_extend = 1; + + return r; +} + int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, - u32 val, unsigned int bytes, int is_bigendian) + u64 val, unsigned int bytes, int is_bigendian) { void *data = run->mmio.data; @@ -342,6 +401,7 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, /* Store the value at the lowest bytes in 'data'. */ if (is_bigendian) { switch (bytes) { + case 8: *(u64 *)data = val; break; case 4: *(u32 *)data = val; break; case 2: *(u16 *)data = val; break; case 1: *(u8 *)data = val; break; @@ -376,6 +436,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) if (!vcpu->arch.dcr_is_write) kvmppc_complete_dcr_load(vcpu, run); vcpu->arch.dcr_needed = 0; + } else if (vcpu->arch.osi_needed) { + u64 *gprs = run->osi.gprs; + int i; + + for (i = 0; i < 32; i++) + kvmppc_set_gpr(vcpu, i, gprs[i]); + vcpu->arch.osi_needed = 0; } kvmppc_core_deliver_interrupts(vcpu); @@ -396,7 +463,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { - kvmppc_core_queue_external(vcpu, irq); + if (irq->irq == KVM_INTERRUPT_UNSET) + kvmppc_core_dequeue_external(vcpu, irq); + else + kvmppc_core_queue_external(vcpu, irq); if (waitqueue_active(&vcpu->wq)) { wake_up_interruptible(&vcpu->wq); @@ -406,6 +476,27 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) return 0; } +static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, + struct kvm_enable_cap *cap) +{ + int r; + + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_PPC_OSI: + r = 0; + vcpu->arch.osi_enabled = true; + break; + default: + r = -EINVAL; + break; + } + + return r; +} + int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { @@ -434,6 +525,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_interrupt(vcpu, &irq); break; } + case KVM_ENABLE_CAP: + { + struct kvm_enable_cap cap; + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + goto out; + r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); + break; + } default: r = -EINVAL; } diff --git a/arch/powerpc/mm/mmu_context_hash32.c b/arch/powerpc/mm/mmu_context_hash32.c index 0dfba2bf7f31..d0ee554e86e4 100644 --- a/arch/powerpc/mm/mmu_context_hash32.c +++ b/arch/powerpc/mm/mmu_context_hash32.c @@ -60,11 +60,7 @@ static unsigned long next_mmu_context; static unsigned long context_map[LAST_CONTEXT / BITS_PER_LONG + 1]; - -/* - * Set up the context for a new address space. - */ -int init_new_context(struct task_struct *t, struct mm_struct *mm) +unsigned long __init_new_context(void) { unsigned long ctx = next_mmu_context; @@ -74,19 +70,38 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm) ctx = 0; } next_mmu_context = (ctx + 1) & LAST_CONTEXT; - mm->context.id = ctx; + + return ctx; +} +EXPORT_SYMBOL_GPL(__init_new_context); + +/* + * Set up the context for a new address space. + */ +int init_new_context(struct task_struct *t, struct mm_struct *mm) +{ + mm->context.id = __init_new_context(); return 0; } /* + * Free a context ID. Make sure to call this with preempt disabled! + */ +void __destroy_context(unsigned long ctx) +{ + clear_bit(ctx, context_map); +} +EXPORT_SYMBOL_GPL(__destroy_context); + +/* * We're finished using the context for an address space. */ void destroy_context(struct mm_struct *mm) { preempt_disable(); if (mm->context.id != NO_CONTEXT) { - clear_bit(mm->context.id, context_map); + __destroy_context(mm->context.id); mm->context.id = NO_CONTEXT; } preempt_enable(); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 49292869a5cd..ee7c713686ce 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -341,11 +341,13 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, rc = kvm_vcpu_init(vcpu, kvm, id); if (rc) - goto out_free_cpu; + goto out_free_sie_block; VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu, vcpu->arch.sie_block); return vcpu; +out_free_sie_block: + free_page((unsigned long)(vcpu->arch.sie_block)); out_free_cpu: kfree(vcpu); out_nomem: diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 60f09ab3672c..cfa9d1777457 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -72,7 +72,7 @@ static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu) struct kvm_memslots *memslots; idx = srcu_read_lock(&vcpu->kvm->srcu); - memslots = rcu_dereference(vcpu->kvm->memslots); + memslots = kvm_memslots(vcpu->kvm); mem = &memslots->memslots[0]; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9458685902bd..97a95dfd1181 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -58,6 +58,9 @@ config X86 select HAVE_ARCH_KMEMCHECK select HAVE_USER_RETURN_NOTIFIER +config INSTRUCTION_DECODER + def_bool (KPROBES || PERF_EVENTS) + config OUTPUT_FORMAT string default "elf32-i386" if X86_32 diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index a19829374e6a..918fbb1855cc 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -502,23 +502,3 @@ config CPU_SUP_UMC_32 CPU might render the kernel unbootable. If unsure, say N. - -config X86_DS - def_bool X86_PTRACE_BTS - depends on X86_DEBUGCTLMSR - select HAVE_HW_BRANCH_TRACER - -config X86_PTRACE_BTS - bool "Branch Trace Store" - default y - depends on X86_DEBUGCTLMSR - depends on BROKEN - ---help--- - This adds a ptrace interface to the hardware's branch trace store. - - Debuggers may use it to collect an execution trace of the debugged - application in order to answer the question 'how did I get here?'. - Debuggers may trace user mode as well as kernel mode. - - Say Y unless there is no application development on this machine - and you want to save a small amount of code size. diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index bc01e3ebfeb2..bd58c8abbfbd 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -174,15 +174,6 @@ config IOMMU_LEAK Add a simple leak tracer to the IOMMU code. This is useful when you are debugging a buggy device driver that leaks IOMMU mappings. -config X86_DS_SELFTEST - bool "DS selftest" - default y - depends on DEBUG_KERNEL - depends on X86_DS - ---help--- - Perform Debug Store selftests at boot time. - If in doubt, say "N". - config HAVE_MMIOTRACE_SUPPORT def_bool y diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index b4ac2cdcb64f..1fa03e04ae44 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -373,6 +373,7 @@ extern atomic_t init_deasserted; extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip); #endif +#ifdef CONFIG_X86_LOCAL_APIC static inline u32 apic_read(u32 reg) { return apic->read(reg); @@ -403,10 +404,19 @@ static inline u32 safe_apic_wait_icr_idle(void) return apic->safe_wait_icr_idle(); } +#else /* CONFIG_X86_LOCAL_APIC */ + +static inline u32 apic_read(u32 reg) { return 0; } +static inline void apic_write(u32 reg, u32 val) { } +static inline u64 apic_icr_read(void) { return 0; } +static inline void apic_icr_write(u32 low, u32 high) { } +static inline void apic_wait_icr_idle(void) { } +static inline u32 safe_apic_wait_icr_idle(void) { return 0; } + +#endif /* CONFIG_X86_LOCAL_APIC */ static inline void ack_APIC_irq(void) { -#ifdef CONFIG_X86_LOCAL_APIC /* * ack_APIC_irq() actually gets compiled as a single instruction * ... yummie. @@ -414,7 +424,6 @@ static inline void ack_APIC_irq(void) /* Docs say use 0 for future compatibility */ apic_write(APIC_EOI, 0); -#endif } static inline unsigned default_get_apic_id(unsigned long x) diff --git a/arch/x86/include/asm/ds.h b/arch/x86/include/asm/ds.h deleted file mode 100644 index 70dac199b093..000000000000 --- a/arch/x86/include/asm/ds.h +++ /dev/null @@ -1,302 +0,0 @@ -/* - * Debug Store (DS) support - * - * This provides a low-level interface to the hardware's Debug Store - * feature that is used for branch trace store (BTS) and - * precise-event based sampling (PEBS). - * - * It manages: - * - DS and BTS hardware configuration - * - buffer overflow handling (to be done) - * - buffer access - * - * It does not do: - * - security checking (is the caller allowed to trace the task) - * - buffer allocation (memory accounting) - * - * - * Copyright (C) 2007-2009 Intel Corporation. - * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009 - */ - -#ifndef _ASM_X86_DS_H -#define _ASM_X86_DS_H - - -#include <linux/types.h> -#include <linux/init.h> -#include <linux/err.h> - - -#ifdef CONFIG_X86_DS - -struct task_struct; -struct ds_context; -struct ds_tracer; -struct bts_tracer; -struct pebs_tracer; - -typedef void (*bts_ovfl_callback_t)(struct bts_tracer *); -typedef void (*pebs_ovfl_callback_t)(struct pebs_tracer *); - - -/* - * A list of features plus corresponding macros to talk about them in - * the ds_request function's flags parameter. - * - * We use the enum to index an array of corresponding control bits; - * we use the macro to index a flags bit-vector. - */ -enum ds_feature { - dsf_bts = 0, - dsf_bts_kernel, -#define BTS_KERNEL (1 << dsf_bts_kernel) - /* trace kernel-mode branches */ - - dsf_bts_user, -#define BTS_USER (1 << dsf_bts_user) - /* trace user-mode branches */ - - dsf_bts_overflow, - dsf_bts_max, - dsf_pebs = dsf_bts_max, - - dsf_pebs_max, - dsf_ctl_max = dsf_pebs_max, - dsf_bts_timestamps = dsf_ctl_max, -#define BTS_TIMESTAMPS (1 << dsf_bts_timestamps) - /* add timestamps into BTS trace */ - -#define BTS_USER_FLAGS (BTS_KERNEL | BTS_USER | BTS_TIMESTAMPS) -}; - - -/* - * Request BTS or PEBS - * - * Due to alignement constraints, the actual buffer may be slightly - * smaller than the requested or provided buffer. - * - * Returns a pointer to a tracer structure on success, or - * ERR_PTR(errcode) on failure. - * - * The interrupt threshold is independent from the overflow callback - * to allow users to use their own overflow interrupt handling mechanism. - * - * The function might sleep. - * - * task: the task to request recording for - * cpu: the cpu to request recording for - * base: the base pointer for the (non-pageable) buffer; - * size: the size of the provided buffer in bytes - * ovfl: pointer to a function to be called on buffer overflow; - * NULL if cyclic buffer requested - * th: the interrupt threshold in records from the end of the buffer; - * -1 if no interrupt threshold is requested. - * flags: a bit-mask of the above flags - */ -extern struct bts_tracer *ds_request_bts_task(struct task_struct *task, - void *base, size_t size, - bts_ovfl_callback_t ovfl, - size_t th, unsigned int flags); -extern struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size, - bts_ovfl_callback_t ovfl, - size_t th, unsigned int flags); -extern struct pebs_tracer *ds_request_pebs_task(struct task_struct *task, - void *base, size_t size, - pebs_ovfl_callback_t ovfl, - size_t th, unsigned int flags); -extern struct pebs_tracer *ds_request_pebs_cpu(int cpu, - void *base, size_t size, - pebs_ovfl_callback_t ovfl, - size_t th, unsigned int flags); - -/* - * Release BTS or PEBS resources - * Suspend and resume BTS or PEBS tracing - * - * Must be called with irq's enabled. - * - * tracer: the tracer handle returned from ds_request_~() - */ -extern void ds_release_bts(struct bts_tracer *tracer); -extern void ds_suspend_bts(struct bts_tracer *tracer); -extern void ds_resume_bts(struct bts_tracer *tracer); -extern void ds_release_pebs(struct pebs_tracer *tracer); -extern void ds_suspend_pebs(struct pebs_tracer *tracer); -extern void ds_resume_pebs(struct pebs_tracer *tracer); - -/* - * Release BTS or PEBS resources - * Suspend and resume BTS or PEBS tracing - * - * Cpu tracers must call this on the traced cpu. - * Task tracers must call ds_release_~_noirq() for themselves. - * - * May be called with irq's disabled. - * - * Returns 0 if successful; - * -EPERM if the cpu tracer does not trace the current cpu. - * -EPERM if the task tracer does not trace itself. - * - * tracer: the tracer handle returned from ds_request_~() - */ -extern int ds_release_bts_noirq(struct bts_tracer *tracer); -extern int ds_suspend_bts_noirq(struct bts_tracer *tracer); -extern int ds_resume_bts_noirq(struct bts_tracer *tracer); -extern int ds_release_pebs_noirq(struct pebs_tracer *tracer); -extern int ds_suspend_pebs_noirq(struct pebs_tracer *tracer); -extern int ds_resume_pebs_noirq(struct pebs_tracer *tracer); - - -/* - * The raw DS buffer state as it is used for BTS and PEBS recording. - * - * This is the low-level, arch-dependent interface for working - * directly on the raw trace data. - */ -struct ds_trace { - /* the number of bts/pebs records */ - size_t n; - /* the size of a bts/pebs record in bytes */ - size_t size; - /* pointers into the raw buffer: - - to the first entry */ - void *begin; - /* - one beyond the last entry */ - void *end; - /* - one beyond the newest entry */ - void *top; - /* - the interrupt threshold */ - void *ith; - /* flags given on ds_request() */ - unsigned int flags; -}; - -/* - * An arch-independent view on branch trace data. - */ -enum bts_qualifier { - bts_invalid, -#define BTS_INVALID bts_invalid - - bts_branch, -#define BTS_BRANCH bts_branch - - bts_task_arrives, -#define BTS_TASK_ARRIVES bts_task_arrives - - bts_task_departs, -#define BTS_TASK_DEPARTS bts_task_departs - - bts_qual_bit_size = 4, - bts_qual_max = (1 << bts_qual_bit_size), -}; - -struct bts_struct { - __u64 qualifier; - union { - /* BTS_BRANCH */ - struct { - __u64 from; - __u64 to; - } lbr; - /* BTS_TASK_ARRIVES or BTS_TASK_DEPARTS */ - struct { - __u64 clock; - pid_t pid; - } event; - } variant; -}; - - -/* - * The BTS state. - * - * This gives access to the raw DS state and adds functions to provide - * an arch-independent view of the BTS data. - */ -struct bts_trace { - struct ds_trace ds; - - int (*read)(struct bts_tracer *tracer, const void *at, - struct bts_struct *out); - int (*write)(struct bts_tracer *tracer, const struct bts_struct *in); -}; - - -/* - * The PEBS state. - * - * This gives access to the raw DS state and the PEBS-specific counter - * reset value. - */ -struct pebs_trace { - struct ds_trace ds; - - /* the number of valid counters in the below array */ - unsigned int counters; - -#define MAX_PEBS_COUNTERS 4 - /* the counter reset value */ - unsigned long long counter_reset[MAX_PEBS_COUNTERS]; -}; - - -/* - * Read the BTS or PEBS trace. - * - * Returns a view on the trace collected for the parameter tracer. - * - * The view remains valid as long as the traced task is not running or - * the tracer is suspended. - * Writes into the trace buffer are not reflected. - * - * tracer: the tracer handle returned from ds_request_~() - */ -extern const struct bts_trace *ds_read_bts(struct bts_tracer *tracer); -extern const struct pebs_trace *ds_read_pebs(struct pebs_tracer *tracer); - - -/* - * Reset the write pointer of the BTS/PEBS buffer. - * - * Returns 0 on success; -Eerrno on error - * - * tracer: the tracer handle returned from ds_request_~() - */ -extern int ds_reset_bts(struct bts_tracer *tracer); -extern int ds_reset_pebs(struct pebs_tracer *tracer); - -/* - * Set the PEBS counter reset value. - * - * Returns 0 on success; -Eerrno on error - * - * tracer: the tracer handle returned from ds_request_pebs() - * counter: the index of the counter - * value: the new counter reset value - */ -extern int ds_set_pebs_reset(struct pebs_tracer *tracer, - unsigned int counter, u64 value); - -/* - * Initialization - */ -struct cpuinfo_x86; -extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *); - -/* - * Context switch work - */ -extern void ds_switch_to(struct task_struct *prev, struct task_struct *next); - -#else /* CONFIG_X86_DS */ - -struct cpuinfo_x86; -static inline void __cpuinit ds_init_intel(struct cpuinfo_x86 *ignored) {} -static inline void ds_switch_to(struct task_struct *prev, - struct task_struct *next) {} - -#endif /* CONFIG_X86_DS */ -#endif /* _ASM_X86_DS_H */ diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index 96c2e0ad04ca..88c765e16410 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -68,6 +68,8 @@ struct insn { const insn_byte_t *next_byte; }; +#define MAX_INSN_SIZE 16 + #define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6) #define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3) #define X86_MODRM_RM(modrm) ((modrm) & 0x07) diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 4ffa345a8ccb..547882539157 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -24,6 +24,7 @@ #include <linux/types.h> #include <linux/ptrace.h> #include <linux/percpu.h> +#include <asm/insn.h> #define __ARCH_WANT_KPROBES_INSN_SLOT @@ -36,7 +37,6 @@ typedef u8 kprobe_opcode_t; #define RELATIVEJUMP_SIZE 5 #define RELATIVECALL_OPCODE 0xe8 #define RELATIVE_ADDR_SIZE 4 -#define MAX_INSN_SIZE 16 #define MAX_STACK_SIZE 64 #define MIN_STACK_SIZE(ADDR) \ (((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \ diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index f46b79f6c16c..ff90055c7f0b 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -21,6 +21,7 @@ #define __KVM_HAVE_PIT_STATE2 #define __KVM_HAVE_XEN_HVM #define __KVM_HAVE_VCPU_EVENTS +#define __KVM_HAVE_DEBUGREGS /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 @@ -257,6 +258,11 @@ struct kvm_reinject_control { /* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */ #define KVM_VCPUEVENT_VALID_NMI_PENDING 0x00000001 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002 +#define KVM_VCPUEVENT_VALID_SHADOW 0x00000004 + +/* Interrupt shadow states */ +#define KVM_X86_SHADOW_INT_MOV_SS 0x01 +#define KVM_X86_SHADOW_INT_STI 0x02 /* for KVM_GET/SET_VCPU_EVENTS */ struct kvm_vcpu_events { @@ -271,7 +277,7 @@ struct kvm_vcpu_events { __u8 injected; __u8 nr; __u8 soft; - __u8 pad; + __u8 shadow; } interrupt; struct { __u8 injected; @@ -284,4 +290,13 @@ struct kvm_vcpu_events { __u32 reserved[10]; }; +/* for KVM_GET/SET_DEBUGREGS */ +struct kvm_debugregs { + __u64 db[4]; + __u64 dr6; + __u64 dr7; + __u64 flags; + __u64 reserved[9]; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 7a6f54fa13ba..0b2729bf2070 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -11,6 +11,8 @@ #ifndef _ASM_X86_KVM_X86_EMULATE_H #define _ASM_X86_KVM_X86_EMULATE_H +#include <asm/desc_defs.h> + struct x86_emulate_ctxt; /* @@ -63,6 +65,15 @@ struct x86_emulate_ops { unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error); /* + * write_std: Write bytes of standard (non-emulated/special) memory. + * Used for descriptor writing. + * @addr: [IN ] Linear address to which to write. + * @val: [OUT] Value write to memory, zero-extended to 'u_long'. + * @bytes: [IN ] Number of bytes to write to memory. + */ + int (*write_std)(unsigned long addr, void *val, + unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error); + /* * fetch: Read bytes of standard (non-emulated/special) memory. * Used for instruction fetch. * @addr: [IN ] Linear address from which to read. @@ -109,6 +120,23 @@ struct x86_emulate_ops { unsigned int bytes, struct kvm_vcpu *vcpu); + int (*pio_in_emulated)(int size, unsigned short port, void *val, + unsigned int count, struct kvm_vcpu *vcpu); + + int (*pio_out_emulated)(int size, unsigned short port, const void *val, + unsigned int count, struct kvm_vcpu *vcpu); + + bool (*get_cached_descriptor)(struct desc_struct *desc, + int seg, struct kvm_vcpu *vcpu); + void (*set_cached_descriptor)(struct desc_struct *desc, + int seg, struct kvm_vcpu *vcpu); + u16 (*get_segment_selector)(int seg, struct kvm_vcpu *vcpu); + void (*set_segment_selector)(u16 sel, int seg, struct kvm_vcpu *vcpu); + void (*get_gdt)(struct desc_ptr *dt, struct kvm_vcpu *vcpu); + ulong (*get_cr)(int cr, struct kvm_vcpu *vcpu); + void (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu); + int (*cpl)(struct kvm_vcpu *vcpu); + void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); }; /* Type, address-of, and value of an instruction's operand. */ @@ -124,6 +152,12 @@ struct fetch_cache { unsigned long end; }; +struct read_cache { + u8 data[1024]; + unsigned long pos; + unsigned long end; +}; + struct decode_cache { u8 twobyte; u8 b; @@ -139,7 +173,7 @@ struct decode_cache { u8 seg_override; unsigned int d; unsigned long regs[NR_VCPU_REGS]; - unsigned long eip, eip_orig; + unsigned long eip; /* modrm */ u8 modrm; u8 modrm_mod; @@ -151,16 +185,15 @@ struct decode_cache { void *modrm_ptr; unsigned long modrm_val; struct fetch_cache fetch; + struct read_cache io_read; }; -#define X86_SHADOW_INT_MOV_SS 1 -#define X86_SHADOW_INT_STI 2 - struct x86_emulate_ctxt { /* Register state before/after emulation. */ struct kvm_vcpu *vcpu; unsigned long eflags; + unsigned long eip; /* eip before instruction emulation */ /* Emulated execution mode, represented by an X86EMUL_MODE value. */ int mode; u32 cs_base; @@ -168,6 +201,7 @@ struct x86_emulate_ctxt { /* interruptibility state, as a result of execution of STI or MOV SS */ int interruptibility; + bool restart; /* restart string instruction after writeback */ /* decode cache */ struct decode_cache decode; }; @@ -194,5 +228,9 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops); int x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops); +int emulator_task_switch(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 tss_selector, int reason, + bool has_error_code, u32 error_code); #endif /* _ASM_X86_KVM_X86_EMULATE_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 06d9e79ca37d..3f0007b076da 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -171,14 +171,13 @@ struct kvm_pte_chain { union kvm_mmu_page_role { unsigned word; struct { - unsigned glevels:4; unsigned level:4; + unsigned cr4_pae:1; unsigned quadrant:2; unsigned pad_for_nice_hex_output:6; unsigned direct:1; unsigned access:3; unsigned invalid:1; - unsigned cr4_pge:1; unsigned nxe:1; }; }; @@ -187,8 +186,6 @@ struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; - struct list_head oos_link; - /* * The following two entries are used to key the shadow page in the * hash table. @@ -204,9 +201,9 @@ struct kvm_mmu_page { * in this shadow page. */ DECLARE_BITMAP(slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS); - int multimapped; /* More than one parent_pte? */ - int root_count; /* Currently serving as active root */ + bool multimapped; /* More than one parent_pte? */ bool unsync; + int root_count; /* Currently serving as active root */ unsigned int unsync_children; union { u64 *parent_pte; /* !multimapped */ @@ -224,14 +221,9 @@ struct kvm_pv_mmu_op_buffer { struct kvm_pio_request { unsigned long count; - int cur_count; - gva_t guest_gva; int in; int port; int size; - int string; - int down; - int rep; }; /* @@ -320,6 +312,7 @@ struct kvm_vcpu_arch { struct kvm_queued_exception { bool pending; bool has_error_code; + bool reinject; u8 nr; u32 error_code; } exception; @@ -362,8 +355,8 @@ struct kvm_vcpu_arch { u64 *mce_banks; /* used for guest single stepping over the given code position */ - u16 singlestep_cs; unsigned long singlestep_rip; + /* fields used by HYPER-V emulation */ u64 hv_vapic; }; @@ -389,6 +382,7 @@ struct kvm_arch { unsigned int n_free_mmu_pages; unsigned int n_requested_mmu_pages; unsigned int n_alloc_mmu_pages; + atomic_t invlpg_counter; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; /* * Hash table of struct kvm_mmu_page. @@ -461,11 +455,6 @@ struct kvm_vcpu_stat { u32 nmi_injections; }; -struct descriptor_table { - u16 limit; - unsigned long base; -} __attribute__((packed)); - struct kvm_x86_ops { int (*cpu_has_kvm_support)(void); /* __init */ int (*disabled_by_bios)(void); /* __init */ @@ -503,12 +492,11 @@ struct kvm_x86_ops { void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer); - void (*get_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); - void (*set_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); - void (*get_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); - void (*set_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); - int (*get_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long *dest); - int (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value); + void (*get_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); + void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); + void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); + void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); + void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); @@ -527,7 +515,8 @@ struct kvm_x86_ops { void (*set_irq)(struct kvm_vcpu *vcpu); void (*set_nmi)(struct kvm_vcpu *vcpu); void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr, - bool has_error_code, u32 error_code); + bool has_error_code, u32 error_code, + bool reinject); int (*interrupt_allowed)(struct kvm_vcpu *vcpu); int (*nmi_allowed)(struct kvm_vcpu *vcpu); bool (*get_nmi_mask)(struct kvm_vcpu *vcpu); @@ -541,6 +530,8 @@ struct kvm_x86_ops { int (*get_lpage_level)(void); bool (*rdtscp_supported)(void); + void (*set_supported_cpuid)(u32 func, struct kvm_cpuid_entry2 *entry); + const struct trace_print_flags *exit_reasons_str; }; @@ -587,23 +578,14 @@ int emulate_instruction(struct kvm_vcpu *vcpu, void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context); void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); -void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, - unsigned long *rflags); -unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr); -void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value, - unsigned long *rflags); void kvm_enable_efer_bits(u64); int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data); int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); struct x86_emulate_ctxt; -int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, - int size, unsigned port); -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in, - int size, unsigned long count, int down, - gva_t address, int rep, unsigned port); +int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port); void kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address); @@ -616,12 +598,15 @@ int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg); -int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason); +int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, + bool has_error_code, u32 error_code); void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8); +int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val); +int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val); unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu); void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw); void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); @@ -634,6 +619,8 @@ void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); +void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr); +void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2, u32 error_code); bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl); @@ -649,8 +636,6 @@ int emulator_write_emulated(unsigned long addr, unsigned int bytes, struct kvm_vcpu *vcpu); -unsigned long segment_base(u16 selector); - void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu); void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes, @@ -675,7 +660,6 @@ void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_enable_tdp(void); void kvm_disable_tdp(void); -int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); int complete_pio(struct kvm_vcpu *vcpu); bool kvm_check_iopl(struct kvm_vcpu *vcpu); @@ -724,23 +708,6 @@ static inline void kvm_load_ldt(u16 sel) asm("lldt %0" : : "rm"(sel)); } -static inline void kvm_get_idt(struct descriptor_table *table) -{ - asm("sidt %0" : "=m"(*table)); -} - -static inline void kvm_get_gdt(struct descriptor_table *table) -{ - asm("sgdt %0" : "=m"(*table)); -} - -static inline unsigned long kvm_read_tr_base(void) -{ - u16 tr; - asm("str %0" : "=g"(tr)); - return segment_base(tr); -} - #ifdef CONFIG_X86_64 static inline unsigned long read_msr(unsigned long msr) { @@ -826,4 +793,6 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_define_shared_msr(unsigned index, u32 msr); void kvm_set_shared_msr(unsigned index, u64 val, u64 mask); +bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 4604e6a54d36..bc473acfa7f9 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -71,11 +71,14 @@ #define MSR_IA32_LASTINTTOIP 0x000001de /* DEBUGCTLMSR bits (others vary by model): */ -#define _DEBUGCTLMSR_LBR 0 /* last branch recording */ -#define _DEBUGCTLMSR_BTF 1 /* single-step on branches */ - -#define DEBUGCTLMSR_LBR (1UL << _DEBUGCTLMSR_LBR) -#define DEBUGCTLMSR_BTF (1UL << _DEBUGCTLMSR_BTF) +#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ +#define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ +#define DEBUGCTLMSR_TR (1UL << 6) +#define DEBUGCTLMSR_BTS (1UL << 7) +#define DEBUGCTLMSR_BTINT (1UL << 8) +#define DEBUGCTLMSR_BTS_OFF_OS (1UL << 9) +#define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10) +#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11) #define MSR_IA32_MC0_CTL 0x00000400 #define MSR_IA32_MC0_STATUS 0x00000401 @@ -359,6 +362,8 @@ #define MSR_P4_U2L_ESCR0 0x000003b0 #define MSR_P4_U2L_ESCR1 0x000003b1 +#define MSR_P4_PEBS_MATRIX_VERT 0x000003f2 + /* Intel Core-based CPU performance counters */ #define MSR_CORE_PERF_FIXED_CTR0 0x00000309 #define MSR_CORE_PERF_FIXED_CTR1 0x0000030a diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index db6109a885a7..254883d0c7e0 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -5,7 +5,7 @@ * Performance event hw details: */ -#define X86_PMC_MAX_GENERIC 8 +#define X86_PMC_MAX_GENERIC 32 #define X86_PMC_MAX_FIXED 3 #define X86_PMC_IDX_GENERIC 0 @@ -18,39 +18,31 @@ #define MSR_ARCH_PERFMON_EVENTSEL0 0x186 #define MSR_ARCH_PERFMON_EVENTSEL1 0x187 -#define ARCH_PERFMON_EVENTSEL_ENABLE (1 << 22) -#define ARCH_PERFMON_EVENTSEL_ANY (1 << 21) -#define ARCH_PERFMON_EVENTSEL_INT (1 << 20) -#define ARCH_PERFMON_EVENTSEL_OS (1 << 17) -#define ARCH_PERFMON_EVENTSEL_USR (1 << 16) - -/* - * Includes eventsel and unit mask as well: - */ - - -#define INTEL_ARCH_EVTSEL_MASK 0x000000FFULL -#define INTEL_ARCH_UNIT_MASK 0x0000FF00ULL -#define INTEL_ARCH_EDGE_MASK 0x00040000ULL -#define INTEL_ARCH_INV_MASK 0x00800000ULL -#define INTEL_ARCH_CNT_MASK 0xFF000000ULL -#define INTEL_ARCH_EVENT_MASK (INTEL_ARCH_UNIT_MASK|INTEL_ARCH_EVTSEL_MASK) - -/* - * filter mask to validate fixed counter events. - * the following filters disqualify for fixed counters: - * - inv - * - edge - * - cnt-mask - * The other filters are supported by fixed counters. - * The any-thread option is supported starting with v3. - */ -#define INTEL_ARCH_FIXED_MASK \ - (INTEL_ARCH_CNT_MASK| \ - INTEL_ARCH_INV_MASK| \ - INTEL_ARCH_EDGE_MASK|\ - INTEL_ARCH_UNIT_MASK|\ - INTEL_ARCH_EVENT_MASK) +#define ARCH_PERFMON_EVENTSEL_EVENT 0x000000FFULL +#define ARCH_PERFMON_EVENTSEL_UMASK 0x0000FF00ULL +#define ARCH_PERFMON_EVENTSEL_USR (1ULL << 16) +#define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17) +#define ARCH_PERFMON_EVENTSEL_EDGE (1ULL << 18) +#define ARCH_PERFMON_EVENTSEL_INT (1ULL << 20) +#define ARCH_PERFMON_EVENTSEL_ANY (1ULL << 21) +#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22) +#define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23) +#define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL + +#define AMD64_EVENTSEL_EVENT \ + (ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32)) +#define INTEL_ARCH_EVENT_MASK \ + (ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT) + +#define X86_RAW_EVENT_MASK \ + (ARCH_PERFMON_EVENTSEL_EVENT | \ + ARCH_PERFMON_EVENTSEL_UMASK | \ + ARCH_PERFMON_EVENTSEL_EDGE | \ + ARCH_PERFMON_EVENTSEL_INV | \ + ARCH_PERFMON_EVENTSEL_CMASK) +#define AMD64_RAW_EVENT_MASK \ + (X86_RAW_EVENT_MASK | \ + AMD64_EVENTSEL_EVENT) #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8) @@ -67,7 +59,7 @@ union cpuid10_eax { struct { unsigned int version_id:8; - unsigned int num_events:8; + unsigned int num_counters:8; unsigned int bit_width:8; unsigned int mask_length:8; } split; @@ -76,7 +68,7 @@ union cpuid10_eax { union cpuid10_edx { struct { - unsigned int num_events_fixed:4; + unsigned int num_counters_fixed:4; unsigned int reserved:28; } split; unsigned int full; @@ -136,6 +128,18 @@ extern void perf_events_lapic_init(void); #define PERF_EVENT_INDEX_OFFSET 0 +/* + * Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups. + * This flag is otherwise unused and ABI specified to be 0, so nobody should + * care what we do with it. + */ +#define PERF_EFLAGS_EXACT (1UL << 3) + +struct pt_regs; +extern unsigned long perf_instruction_pointer(struct pt_regs *regs); +extern unsigned long perf_misc_flags(struct pt_regs *regs); +#define perf_misc_flags(regs) perf_misc_flags(regs) + #else static inline void init_hw_perf_events(void) { } static inline void perf_events_lapic_init(void) { } diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h new file mode 100644 index 000000000000..b05400a542ff --- /dev/null +++ b/arch/x86/include/asm/perf_event_p4.h @@ -0,0 +1,794 @@ +/* + * Netburst Perfomance Events (P4, old Xeon) + */ + +#ifndef PERF_EVENT_P4_H +#define PERF_EVENT_P4_H + +#include <linux/cpu.h> +#include <linux/bitops.h> + +/* + * NetBurst has perfomance MSRs shared between + * threads if HT is turned on, ie for both logical + * processors (mem: in turn in Atom with HT support + * perf-MSRs are not shared and every thread has its + * own perf-MSRs set) + */ +#define ARCH_P4_TOTAL_ESCR (46) +#define ARCH_P4_RESERVED_ESCR (2) /* IQ_ESCR(0,1) not always present */ +#define ARCH_P4_MAX_ESCR (ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR) +#define ARCH_P4_MAX_CCCR (18) +#define ARCH_P4_MAX_COUNTER (ARCH_P4_MAX_CCCR / 2) + +#define P4_ESCR_EVENT_MASK 0x7e000000U +#define P4_ESCR_EVENT_SHIFT 25 +#define P4_ESCR_EVENTMASK_MASK 0x01fffe00U +#define P4_ESCR_EVENTMASK_SHIFT 9 +#define P4_ESCR_TAG_MASK 0x000001e0U +#define P4_ESCR_TAG_SHIFT 5 +#define P4_ESCR_TAG_ENABLE 0x00000010U +#define P4_ESCR_T0_OS 0x00000008U +#define P4_ESCR_T0_USR 0x00000004U +#define P4_ESCR_T1_OS 0x00000002U +#define P4_ESCR_T1_USR 0x00000001U + +#define P4_ESCR_EVENT(v) ((v) << P4_ESCR_EVENT_SHIFT) +#define P4_ESCR_EMASK(v) ((v) << P4_ESCR_EVENTMASK_SHIFT) +#define P4_ESCR_TAG(v) ((v) << P4_ESCR_TAG_SHIFT) + +/* Non HT mask */ +#define P4_ESCR_MASK \ + (P4_ESCR_EVENT_MASK | \ + P4_ESCR_EVENTMASK_MASK | \ + P4_ESCR_TAG_MASK | \ + P4_ESCR_TAG_ENABLE | \ + P4_ESCR_T0_OS | \ + P4_ESCR_T0_USR) + +/* HT mask */ +#define P4_ESCR_MASK_HT \ + (P4_ESCR_MASK | P4_ESCR_T1_OS | P4_ESCR_T1_USR) + +#define P4_CCCR_OVF 0x80000000U +#define P4_CCCR_CASCADE 0x40000000U +#define P4_CCCR_OVF_PMI_T0 0x04000000U +#define P4_CCCR_OVF_PMI_T1 0x08000000U +#define P4_CCCR_FORCE_OVF 0x02000000U +#define P4_CCCR_EDGE 0x01000000U +#define P4_CCCR_THRESHOLD_MASK 0x00f00000U +#define P4_CCCR_THRESHOLD_SHIFT 20 +#define P4_CCCR_COMPLEMENT 0x00080000U +#define P4_CCCR_COMPARE 0x00040000U +#define P4_CCCR_ESCR_SELECT_MASK 0x0000e000U +#define P4_CCCR_ESCR_SELECT_SHIFT 13 +#define P4_CCCR_ENABLE 0x00001000U +#define P4_CCCR_THREAD_SINGLE 0x00010000U +#define P4_CCCR_THREAD_BOTH 0x00020000U +#define P4_CCCR_THREAD_ANY 0x00030000U +#define P4_CCCR_RESERVED 0x00000fffU + +#define P4_CCCR_THRESHOLD(v) ((v) << P4_CCCR_THRESHOLD_SHIFT) +#define P4_CCCR_ESEL(v) ((v) << P4_CCCR_ESCR_SELECT_SHIFT) + +/* Custom bits in reerved CCCR area */ +#define P4_CCCR_CACHE_OPS_MASK 0x0000003fU + + +/* Non HT mask */ +#define P4_CCCR_MASK \ + (P4_CCCR_OVF | \ + P4_CCCR_CASCADE | \ + P4_CCCR_OVF_PMI_T0 | \ + P4_CCCR_FORCE_OVF | \ + P4_CCCR_EDGE | \ + P4_CCCR_THRESHOLD_MASK | \ + P4_CCCR_COMPLEMENT | \ + P4_CCCR_COMPARE | \ + P4_CCCR_ESCR_SELECT_MASK | \ + P4_CCCR_ENABLE) + +/* HT mask */ +#define P4_CCCR_MASK_HT (P4_CCCR_MASK | P4_CCCR_THREAD_ANY) + +#define P4_GEN_ESCR_EMASK(class, name, bit) \ + class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT) +#define P4_ESCR_EMASK_BIT(class, name) class##__##name + +/* + * config field is 64bit width and consists of + * HT << 63 | ESCR << 32 | CCCR + * where HT is HyperThreading bit (since ESCR + * has it reserved we may use it for own purpose) + * + * note that this is NOT the addresses of respective + * ESCR and CCCR but rather an only packed value should + * be unpacked and written to a proper addresses + * + * the base idea is to pack as much info as + * possible + */ +#define p4_config_pack_escr(v) (((u64)(v)) << 32) +#define p4_config_pack_cccr(v) (((u64)(v)) & 0xffffffffULL) +#define p4_config_unpack_escr(v) (((u64)(v)) >> 32) +#define p4_config_unpack_cccr(v) (((u64)(v)) & 0xffffffffULL) + +#define p4_config_unpack_emask(v) \ + ({ \ + u32 t = p4_config_unpack_escr((v)); \ + t = t & P4_ESCR_EVENTMASK_MASK; \ + t = t >> P4_ESCR_EVENTMASK_SHIFT; \ + t; \ + }) + +#define p4_config_unpack_event(v) \ + ({ \ + u32 t = p4_config_unpack_escr((v)); \ + t = t & P4_ESCR_EVENT_MASK; \ + t = t >> P4_ESCR_EVENT_SHIFT; \ + t; \ + }) + +#define p4_config_unpack_cache_event(v) (((u64)(v)) & P4_CCCR_CACHE_OPS_MASK) + +#define P4_CONFIG_HT_SHIFT 63 +#define P4_CONFIG_HT (1ULL << P4_CONFIG_HT_SHIFT) + +static inline bool p4_is_event_cascaded(u64 config) +{ + u32 cccr = p4_config_unpack_cccr(config); + return !!(cccr & P4_CCCR_CASCADE); +} + +static inline int p4_ht_config_thread(u64 config) +{ + return !!(config & P4_CONFIG_HT); +} + +static inline u64 p4_set_ht_bit(u64 config) +{ + return config | P4_CONFIG_HT; +} + +static inline u64 p4_clear_ht_bit(u64 config) +{ + return config & ~P4_CONFIG_HT; +} + +static inline int p4_ht_active(void) +{ +#ifdef CONFIG_SMP + return smp_num_siblings > 1; +#endif + return 0; +} + +static inline int p4_ht_thread(int cpu) +{ +#ifdef CONFIG_SMP + if (smp_num_siblings == 2) + return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map)); +#endif + return 0; +} + +static inline int p4_should_swap_ts(u64 config, int cpu) +{ + return p4_ht_config_thread(config) ^ p4_ht_thread(cpu); +} + +static inline u32 p4_default_cccr_conf(int cpu) +{ + /* + * Note that P4_CCCR_THREAD_ANY is "required" on + * non-HT machines (on HT machines we count TS events + * regardless the state of second logical processor + */ + u32 cccr = P4_CCCR_THREAD_ANY; + + if (!p4_ht_thread(cpu)) + cccr |= P4_CCCR_OVF_PMI_T0; + else + cccr |= P4_CCCR_OVF_PMI_T1; + + return cccr; +} + +static inline u32 p4_default_escr_conf(int cpu, int exclude_os, int exclude_usr) +{ + u32 escr = 0; + + if (!p4_ht_thread(cpu)) { + if (!exclude_os) + escr |= P4_ESCR_T0_OS; + if (!exclude_usr) + escr |= P4_ESCR_T0_USR; + } else { + if (!exclude_os) + escr |= P4_ESCR_T1_OS; + if (!exclude_usr) + escr |= P4_ESCR_T1_USR; + } + + return escr; +} + +enum P4_EVENTS { + P4_EVENT_TC_DELIVER_MODE, + P4_EVENT_BPU_FETCH_REQUEST, + P4_EVENT_ITLB_REFERENCE, + P4_EVENT_MEMORY_CANCEL, + P4_EVENT_MEMORY_COMPLETE, + P4_EVENT_LOAD_PORT_REPLAY, + P4_EVENT_STORE_PORT_REPLAY, + P4_EVENT_MOB_LOAD_REPLAY, + P4_EVENT_PAGE_WALK_TYPE, + P4_EVENT_BSQ_CACHE_REFERENCE, + P4_EVENT_IOQ_ALLOCATION, + P4_EVENT_IOQ_ACTIVE_ENTRIES, + P4_EVENT_FSB_DATA_ACTIVITY, + P4_EVENT_BSQ_ALLOCATION, + P4_EVENT_BSQ_ACTIVE_ENTRIES, + P4_EVENT_SSE_INPUT_ASSIST, + P4_EVENT_PACKED_SP_UOP, + P4_EVENT_PACKED_DP_UOP, + P4_EVENT_SCALAR_SP_UOP, + P4_EVENT_SCALAR_DP_UOP, + P4_EVENT_64BIT_MMX_UOP, + P4_EVENT_128BIT_MMX_UOP, + P4_EVENT_X87_FP_UOP, + P4_EVENT_TC_MISC, + P4_EVENT_GLOBAL_POWER_EVENTS, + P4_EVENT_TC_MS_XFER, + P4_EVENT_UOP_QUEUE_WRITES, + P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, + P4_EVENT_RETIRED_BRANCH_TYPE, + P4_EVENT_RESOURCE_STALL, + P4_EVENT_WC_BUFFER, + P4_EVENT_B2B_CYCLES, + P4_EVENT_BNR, + P4_EVENT_SNOOP, + P4_EVENT_RESPONSE, + P4_EVENT_FRONT_END_EVENT, + P4_EVENT_EXECUTION_EVENT, + P4_EVENT_REPLAY_EVENT, + P4_EVENT_INSTR_RETIRED, + P4_EVENT_UOPS_RETIRED, + P4_EVENT_UOP_TYPE, + P4_EVENT_BRANCH_RETIRED, + P4_EVENT_MISPRED_BRANCH_RETIRED, + P4_EVENT_X87_ASSIST, + P4_EVENT_MACHINE_CLEAR, + P4_EVENT_INSTR_COMPLETED, +}; + +#define P4_OPCODE(event) event##_OPCODE +#define P4_OPCODE_ESEL(opcode) ((opcode & 0x00ff) >> 0) +#define P4_OPCODE_EVNT(opcode) ((opcode & 0xff00) >> 8) +#define P4_OPCODE_PACK(event, sel) (((event) << 8) | sel) + +/* + * Comments below the event represent ESCR restriction + * for this event and counter index per ESCR + * + * MSR_P4_IQ_ESCR0 and MSR_P4_IQ_ESCR1 are available only on early + * processor builds (family 0FH, models 01H-02H). These MSRs + * are not available on later versions, so that we don't use + * them completely + * + * Also note that CCCR1 do not have P4_CCCR_ENABLE bit properly + * working so that we should not use this CCCR and respective + * counter as result + */ +enum P4_EVENT_OPCODES { + P4_OPCODE(P4_EVENT_TC_DELIVER_MODE) = P4_OPCODE_PACK(0x01, 0x01), + /* + * MSR_P4_TC_ESCR0: 4, 5 + * MSR_P4_TC_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST) = P4_OPCODE_PACK(0x03, 0x00), + /* + * MSR_P4_BPU_ESCR0: 0, 1 + * MSR_P4_BPU_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_ITLB_REFERENCE) = P4_OPCODE_PACK(0x18, 0x03), + /* + * MSR_P4_ITLB_ESCR0: 0, 1 + * MSR_P4_ITLB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_MEMORY_CANCEL) = P4_OPCODE_PACK(0x02, 0x05), + /* + * MSR_P4_DAC_ESCR0: 8, 9 + * MSR_P4_DAC_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_MEMORY_COMPLETE) = P4_OPCODE_PACK(0x08, 0x02), + /* + * MSR_P4_SAAT_ESCR0: 8, 9 + * MSR_P4_SAAT_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY) = P4_OPCODE_PACK(0x04, 0x02), + /* + * MSR_P4_SAAT_ESCR0: 8, 9 + * MSR_P4_SAAT_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY) = P4_OPCODE_PACK(0x05, 0x02), + /* + * MSR_P4_SAAT_ESCR0: 8, 9 + * MSR_P4_SAAT_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY) = P4_OPCODE_PACK(0x03, 0x02), + /* + * MSR_P4_MOB_ESCR0: 0, 1 + * MSR_P4_MOB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE) = P4_OPCODE_PACK(0x01, 0x04), + /* + * MSR_P4_PMH_ESCR0: 0, 1 + * MSR_P4_PMH_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE) = P4_OPCODE_PACK(0x0c, 0x07), + /* + * MSR_P4_BSU_ESCR0: 0, 1 + * MSR_P4_BSU_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_IOQ_ALLOCATION) = P4_OPCODE_PACK(0x03, 0x06), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES) = P4_OPCODE_PACK(0x1a, 0x06), + /* + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY) = P4_OPCODE_PACK(0x17, 0x06), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_BSQ_ALLOCATION) = P4_OPCODE_PACK(0x05, 0x07), + /* + * MSR_P4_BSU_ESCR0: 0, 1 + */ + + P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES) = P4_OPCODE_PACK(0x06, 0x07), + /* + * NOTE: no ESCR name in docs, it's guessed + * MSR_P4_BSU_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST) = P4_OPCODE_PACK(0x34, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_PACKED_SP_UOP) = P4_OPCODE_PACK(0x08, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_PACKED_DP_UOP) = P4_OPCODE_PACK(0x0c, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_SCALAR_SP_UOP) = P4_OPCODE_PACK(0x0a, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_SCALAR_DP_UOP) = P4_OPCODE_PACK(0x0e, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_64BIT_MMX_UOP) = P4_OPCODE_PACK(0x02, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_128BIT_MMX_UOP) = P4_OPCODE_PACK(0x1a, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_X87_FP_UOP) = P4_OPCODE_PACK(0x04, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_TC_MISC) = P4_OPCODE_PACK(0x06, 0x01), + /* + * MSR_P4_TC_ESCR0: 4, 5 + * MSR_P4_TC_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS) = P4_OPCODE_PACK(0x13, 0x06), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_TC_MS_XFER) = P4_OPCODE_PACK(0x05, 0x00), + /* + * MSR_P4_MS_ESCR0: 4, 5 + * MSR_P4_MS_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES) = P4_OPCODE_PACK(0x09, 0x00), + /* + * MSR_P4_MS_ESCR0: 4, 5 + * MSR_P4_MS_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE) = P4_OPCODE_PACK(0x05, 0x02), + /* + * MSR_P4_TBPU_ESCR0: 4, 5 + * MSR_P4_TBPU_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE) = P4_OPCODE_PACK(0x04, 0x02), + /* + * MSR_P4_TBPU_ESCR0: 4, 5 + * MSR_P4_TBPU_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_RESOURCE_STALL) = P4_OPCODE_PACK(0x01, 0x01), + /* + * MSR_P4_ALF_ESCR0: 12, 13, 16 + * MSR_P4_ALF_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_WC_BUFFER) = P4_OPCODE_PACK(0x05, 0x05), + /* + * MSR_P4_DAC_ESCR0: 8, 9 + * MSR_P4_DAC_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_B2B_CYCLES) = P4_OPCODE_PACK(0x16, 0x03), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_BNR) = P4_OPCODE_PACK(0x08, 0x03), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_SNOOP) = P4_OPCODE_PACK(0x06, 0x03), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_RESPONSE) = P4_OPCODE_PACK(0x04, 0x03), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_FRONT_END_EVENT) = P4_OPCODE_PACK(0x08, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_EXECUTION_EVENT) = P4_OPCODE_PACK(0x0c, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_REPLAY_EVENT) = P4_OPCODE_PACK(0x09, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_INSTR_RETIRED) = P4_OPCODE_PACK(0x02, 0x04), + /* + * MSR_P4_CRU_ESCR0: 12, 13, 16 + * MSR_P4_CRU_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_UOPS_RETIRED) = P4_OPCODE_PACK(0x01, 0x04), + /* + * MSR_P4_CRU_ESCR0: 12, 13, 16 + * MSR_P4_CRU_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_UOP_TYPE) = P4_OPCODE_PACK(0x02, 0x02), + /* + * MSR_P4_RAT_ESCR0: 12, 13, 16 + * MSR_P4_RAT_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_BRANCH_RETIRED) = P4_OPCODE_PACK(0x06, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED) = P4_OPCODE_PACK(0x03, 0x04), + /* + * MSR_P4_CRU_ESCR0: 12, 13, 16 + * MSR_P4_CRU_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_X87_ASSIST) = P4_OPCODE_PACK(0x03, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_MACHINE_CLEAR) = P4_OPCODE_PACK(0x02, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_INSTR_COMPLETED) = P4_OPCODE_PACK(0x07, 0x04), + /* + * MSR_P4_CRU_ESCR0: 12, 13, 16 + * MSR_P4_CRU_ESCR1: 14, 15, 17 + */ +}; + +/* + * a caller should use P4_ESCR_EMASK_NAME helper to + * pick the EventMask needed, for example + * + * P4_ESCR_EMASK_NAME(P4_EVENT_TC_DELIVER_MODE, DD) + */ +enum P4_ESCR_EMASKS { + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DD, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DB, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DI, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BD, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BB, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BI, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, ID, 6), + + P4_GEN_ESCR_EMASK(P4_EVENT_BPU_FETCH_REQUEST, TCMISS, 0), + + P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, HIT, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, MISS, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, HIT_UK, 2), + + P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_CANCEL, ST_RB_FULL, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_CANCEL, 64K_CONF, 3), + + P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_COMPLETE, LSC, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_COMPLETE, SSC, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_LOAD_PORT_REPLAY, SPLIT_LD, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_STORE_PORT_REPLAY, SPLIT_ST, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, NO_STA, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, NO_STD, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, PARTIAL_DATA, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, UNALGN_ADDR, 5), + + P4_GEN_ESCR_EMASK(P4_EVENT_PAGE_WALK_TYPE, DTMISS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_PAGE_WALK_TYPE, ITMISS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS, 10), + + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, DEFAULT, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, ALL_READ, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, ALL_WRITE, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_UC, 7), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WC, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WT, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WP, 10), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WB, 11), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, OWN, 13), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, OTHER, 14), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, PREFETCH, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, DEFAULT, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_READ, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_WRITE, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_UC, 7), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WC, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WT, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WP, 10), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WB, 11), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, OWN, 13), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, OTHER, 14), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, PREFETCH, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OTHER, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_DRV, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OWN, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OTHER, 5), + + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE0, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE1, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LEN0, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LEN1, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_IO_TYPE, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LOCK_TYPE, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_CACHE_TYPE, 7), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_SPLIT_TYPE, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_DEM_TYPE, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_ORD_TYPE, 10), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE0, 11), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE1, 12), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE2, 13), + + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE0, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE1, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN0, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN1, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_IO_TYPE, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LOCK_TYPE, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_CACHE_TYPE, 7), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_SPLIT_TYPE, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_DEM_TYPE, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_ORD_TYPE, 10), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE0, 11), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE1, 12), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE2, 13), + + P4_GEN_ESCR_EMASK(P4_EVENT_SSE_INPUT_ASSIST, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_PACKED_SP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_PACKED_DP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_SCALAR_SP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_SCALAR_DP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_64BIT_MMX_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_128BIT_MMX_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_X87_FP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_TC_MISC, FLUSH, 4), + + P4_GEN_ESCR_EMASK(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING, 0), + + P4_GEN_ESCR_EMASK(P4_EVENT_TC_MS_XFER, CISC, 0), + + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_BUILD, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_DELIVER, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_ROM, 2), + + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CONDITIONAL, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CALL, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, RETURN, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, INDIRECT, 4), + + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, CALL, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT, 4), + + P4_GEN_ESCR_EMASK(P4_EVENT_RESOURCE_STALL, SBFULL, 5), + + P4_GEN_ESCR_EMASK(P4_EVENT_WC_BUFFER, WCB_EVICTS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_WC_BUFFER, WCB_FULL_EVICTS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_FRONT_END_EVENT, NBOGUS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_FRONT_END_EVENT, BOGUS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS0, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS1, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS2, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS3, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS0, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS1, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS2, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS3, 7), + + P4_GEN_ESCR_EMASK(P4_EVENT_REPLAY_EVENT, NBOGUS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_REPLAY_EVENT, BOGUS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, NBOGUSTAG, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, BOGUSNTAG, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, BOGUSTAG, 3), + + P4_GEN_ESCR_EMASK(P4_EVENT_UOPS_RETIRED, NBOGUS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_UOPS_RETIRED, BOGUS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_TYPE, TAGLOADS, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_TYPE, TAGSTORES, 2), + + P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMNP, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMNM, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMTP, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMTM, 3), + + P4_GEN_ESCR_EMASK(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS, 0), + + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, FPSU, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, FPSO, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, POAO, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, POAU, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, PREA, 4), + + P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, CLEAR, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, MOCLEAR, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, SMCLEAR, 2), + + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, NBOGUS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, BOGUS, 1), +}; + +/* P4 PEBS: stale for a while */ +#define P4_PEBS_METRIC_MASK 0x00001fffU +#define P4_PEBS_UOB_TAG 0x01000000U +#define P4_PEBS_ENABLE 0x02000000U + +/* Replay metrics for MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT */ +#define P4_PEBS__1stl_cache_load_miss_retired 0x3000001 +#define P4_PEBS__2ndl_cache_load_miss_retired 0x3000002 +#define P4_PEBS__dtlb_load_miss_retired 0x3000004 +#define P4_PEBS__dtlb_store_miss_retired 0x3000004 +#define P4_PEBS__dtlb_all_miss_retired 0x3000004 +#define P4_PEBS__tagged_mispred_branch 0x3018000 +#define P4_PEBS__mob_load_replay_retired 0x3000200 +#define P4_PEBS__split_load_retired 0x3000400 +#define P4_PEBS__split_store_retired 0x3000400 + +#define P4_VERT__1stl_cache_load_miss_retired 0x0000001 +#define P4_VERT__2ndl_cache_load_miss_retired 0x0000001 +#define P4_VERT__dtlb_load_miss_retired 0x0000001 +#define P4_VERT__dtlb_store_miss_retired 0x0000002 +#define P4_VERT__dtlb_all_miss_retired 0x0000003 +#define P4_VERT__tagged_mispred_branch 0x0000010 +#define P4_VERT__mob_load_replay_retired 0x0000001 +#define P4_VERT__split_load_retired 0x0000001 +#define P4_VERT__split_store_retired 0x0000002 + +enum P4_CACHE_EVENTS { + P4_CACHE__NONE, + + P4_CACHE__1stl_cache_load_miss_retired, + P4_CACHE__2ndl_cache_load_miss_retired, + P4_CACHE__dtlb_load_miss_retired, + P4_CACHE__dtlb_store_miss_retired, + P4_CACHE__itlb_reference_hit, + P4_CACHE__itlb_reference_miss, + + P4_CACHE__MAX +}; + +#endif /* PERF_EVENT_P4_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index b753ea59703a..32428b410b55 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -21,7 +21,6 @@ struct mm_struct; #include <asm/msr.h> #include <asm/desc_defs.h> #include <asm/nops.h> -#include <asm/ds.h> #include <linux/personality.h> #include <linux/cpumask.h> @@ -29,6 +28,7 @@ struct mm_struct; #include <linux/threads.h> #include <linux/math64.h> #include <linux/init.h> +#include <linux/err.h> #define HBP_NUM 4 /* @@ -473,10 +473,6 @@ struct thread_struct { unsigned long iopl; /* Max allowed port in the bitmap, in bytes: */ unsigned io_bitmap_max; -/* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set. */ - unsigned long debugctlmsr; - /* Debug Store context; see asm/ds.h */ - struct ds_context *ds_ctx; }; static inline unsigned long native_get_debugreg(int regno) @@ -803,7 +799,7 @@ extern void cpu_init(void); static inline unsigned long get_debugctlmsr(void) { - unsigned long debugctlmsr = 0; + unsigned long debugctlmsr = 0; #ifndef CONFIG_X86_DEBUGCTLMSR if (boot_cpu_data.x86 < 6) @@ -811,21 +807,6 @@ static inline unsigned long get_debugctlmsr(void) #endif rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); - return debugctlmsr; -} - -static inline unsigned long get_debugctlmsr_on_cpu(int cpu) -{ - u64 debugctlmsr = 0; - u32 val1, val2; - -#ifndef CONFIG_X86_DEBUGCTLMSR - if (boot_cpu_data.x86 < 6) - return 0; -#endif - rdmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, &val1, &val2); - debugctlmsr = val1 | ((u64)val2 << 32); - return debugctlmsr; } @@ -838,18 +819,6 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr) wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); } -static inline void update_debugctlmsr_on_cpu(int cpu, - unsigned long debugctlmsr) -{ -#ifndef CONFIG_X86_DEBUGCTLMSR - if (boot_cpu_data.x86 < 6) - return; -#endif - wrmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, - (u32)((u64)debugctlmsr), - (u32)((u64)debugctlmsr >> 32)); -} - /* * from system description table in BIOS. Mostly for MCA use, but * others may find it useful: diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h index 86723035a515..52b098a6eebb 100644 --- a/arch/x86/include/asm/ptrace-abi.h +++ b/arch/x86/include/asm/ptrace-abi.h @@ -82,61 +82,6 @@ #ifndef __ASSEMBLY__ #include <linux/types.h> - -/* configuration/status structure used in PTRACE_BTS_CONFIG and - PTRACE_BTS_STATUS commands. -*/ -struct ptrace_bts_config { - /* requested or actual size of BTS buffer in bytes */ - __u32 size; - /* bitmask of below flags */ - __u32 flags; - /* buffer overflow signal */ - __u32 signal; - /* actual size of bts_struct in bytes */ - __u32 bts_size; -}; -#endif /* __ASSEMBLY__ */ - -#define PTRACE_BTS_O_TRACE 0x1 /* branch trace */ -#define PTRACE_BTS_O_SCHED 0x2 /* scheduling events w/ jiffies */ -#define PTRACE_BTS_O_SIGNAL 0x4 /* send SIG<signal> on buffer overflow - instead of wrapping around */ -#define PTRACE_BTS_O_ALLOC 0x8 /* (re)allocate buffer */ - -#define PTRACE_BTS_CONFIG 40 -/* Configure branch trace recording. - ADDR points to a struct ptrace_bts_config. - DATA gives the size of that buffer. - A new buffer is allocated, if requested in the flags. - An overflow signal may only be requested for new buffers. - Returns the number of bytes read. -*/ -#define PTRACE_BTS_STATUS 41 -/* Return the current configuration in a struct ptrace_bts_config - pointed to by ADDR; DATA gives the size of that buffer. - Returns the number of bytes written. -*/ -#define PTRACE_BTS_SIZE 42 -/* Return the number of available BTS records for draining. - DATA and ADDR are ignored. -*/ -#define PTRACE_BTS_GET 43 -/* Get a single BTS record. - DATA defines the index into the BTS array, where 0 is the newest - entry, and higher indices refer to older entries. - ADDR is pointing to struct bts_struct (see asm/ds.h). -*/ -#define PTRACE_BTS_CLEAR 44 -/* Clear the BTS buffer. - DATA and ADDR are ignored. -*/ -#define PTRACE_BTS_DRAIN 45 -/* Read all available BTS records and clear the buffer. - ADDR points to an array of struct bts_struct. - DATA gives the size of that buffer. - BTS records are read from oldest to newest. - Returns number of BTS records drained. -*/ +#endif #endif /* _ASM_X86_PTRACE_ABI_H */ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 69a686a7dff0..78cd1ea94500 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -289,12 +289,6 @@ extern int do_get_thread_area(struct task_struct *p, int idx, extern int do_set_thread_area(struct task_struct *p, int idx, struct user_desc __user *info, int can_allocate); -#ifdef CONFIG_X86_PTRACE_BTS -extern void ptrace_bts_untrace(struct task_struct *tsk); - -#define arch_ptrace_untrace(tsk) ptrace_bts_untrace(tsk) -#endif /* CONFIG_X86_PTRACE_BTS */ - #endif /* __KERNEL__ */ #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 38638cd2fa4c..0e831059ac5a 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -81,7 +81,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u32 event_inj_err; u64 nested_cr3; u64 lbr_ctl; - u8 reserved_5[832]; + u64 reserved_5; + u64 next_rip; + u8 reserved_6[816]; }; @@ -115,6 +117,10 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT) #define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT) +#define SVM_VM_CR_VALID_MASK 0x001fULL +#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL +#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL + struct __attribute__ ((__packed__)) vmcb_seg { u16 selector; u16 attrib; @@ -238,6 +244,7 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_EXITINFOSHIFT_TS_REASON_IRET 36 #define SVM_EXITINFOSHIFT_TS_REASON_JMP 38 +#define SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE 44 #define SVM_EXIT_READ_CR0 0x000 #define SVM_EXIT_READ_CR3 0x003 diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index e0d28901e969..d017ed5502e2 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -92,8 +92,7 @@ struct thread_info { #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ #define TIF_FREEZE 23 /* is freezing for suspend */ #define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ -#define TIF_DEBUGCTLMSR 25 /* uses thread_struct.debugctlmsr */ -#define TIF_DS_AREA_MSR 26 /* uses thread_struct.ds_area_msr */ +#define TIF_BLOCKSTEP 25 /* set when we want DEBUGCTLMSR_BTF */ #define TIF_LAZY_MMU_UPDATES 27 /* task is updating the mmu lazily */ #define TIF_SYSCALL_TRACEPOINT 28 /* syscall tracepoint instrumentation */ @@ -115,8 +114,7 @@ struct thread_info { #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_FREEZE (1 << TIF_FREEZE) #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) -#define _TIF_DEBUGCTLMSR (1 << TIF_DEBUGCTLMSR) -#define _TIF_DS_AREA_MSR (1 << TIF_DS_AREA_MSR) +#define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP) #define _TIF_LAZY_MMU_UPDATES (1 << TIF_LAZY_MMU_UPDATES) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) @@ -147,7 +145,7 @@ struct thread_info { /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ - (_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_NOTSC) + (_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP) #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG) diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 4c58352209e0..e77b22083721 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -47,8 +47,6 @@ obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o obj-y += process.o obj-y += i387.o xsave.o obj-y += ptrace.o -obj-$(CONFIG_X86_DS) += ds.o -obj-$(CONFIG_X86_DS_SELFTEST) += ds_selftest.o obj-$(CONFIG_X86_32) += tls.o obj-$(CONFIG_IA32_EMULATION) += tls.o obj-y += step.o diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 7e1cca13af35..d72377c41c76 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -12,7 +12,6 @@ #include <asm/processor.h> #include <asm/pgtable.h> #include <asm/msr.h> -#include <asm/ds.h> #include <asm/bugs.h> #include <asm/cpu.h> @@ -367,7 +366,6 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_BTS); if (!(l1 & (1<<12))) set_cpu_cap(c, X86_FEATURE_PEBS); - ds_init_intel(c); } if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index db5bdc8addf8..7de70613e6c3 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -31,46 +31,51 @@ #include <asm/nmi.h> #include <asm/compat.h> -static u64 perf_event_mask __read_mostly; +#if 0 +#undef wrmsrl +#define wrmsrl(msr, val) \ +do { \ + trace_printk("wrmsrl(%lx, %lx)\n", (unsigned long)(msr),\ + (unsigned long)(val)); \ + native_write_msr((msr), (u32)((u64)(val)), \ + (u32)((u64)(val) >> 32)); \ +} while (0) +#endif -/* The maximal number of PEBS events: */ -#define MAX_PEBS_EVENTS 4 +/* + * best effort, GUP based copy_from_user() that assumes IRQ or NMI context + */ +static unsigned long +copy_from_user_nmi(void *to, const void __user *from, unsigned long n) +{ + unsigned long offset, addr = (unsigned long)from; + int type = in_nmi() ? KM_NMI : KM_IRQ0; + unsigned long size, len = 0; + struct page *page; + void *map; + int ret; -/* The size of a BTS record in bytes: */ -#define BTS_RECORD_SIZE 24 + do { + ret = __get_user_pages_fast(addr, 1, 0, &page); + if (!ret) + break; -/* The size of a per-cpu BTS buffer in bytes: */ -#define BTS_BUFFER_SIZE (BTS_RECORD_SIZE * 2048) + offset = addr & (PAGE_SIZE - 1); + size = min(PAGE_SIZE - offset, n - len); -/* The BTS overflow threshold in bytes from the end of the buffer: */ -#define BTS_OVFL_TH (BTS_RECORD_SIZE * 128) + map = kmap_atomic(page, type); + memcpy(to, map+offset, size); + kunmap_atomic(map, type); + put_page(page); + len += size; + to += size; + addr += size; -/* - * Bits in the debugctlmsr controlling branch tracing. - */ -#define X86_DEBUGCTL_TR (1 << 6) -#define X86_DEBUGCTL_BTS (1 << 7) -#define X86_DEBUGCTL_BTINT (1 << 8) -#define X86_DEBUGCTL_BTS_OFF_OS (1 << 9) -#define X86_DEBUGCTL_BTS_OFF_USR (1 << 10) + } while (len < n); -/* - * A debug store configuration. - * - * We only support architectures that use 64bit fields. - */ -struct debug_store { - u64 bts_buffer_base; - u64 bts_index; - u64 bts_absolute_maximum; - u64 bts_interrupt_threshold; - u64 pebs_buffer_base; - u64 pebs_index; - u64 pebs_absolute_maximum; - u64 pebs_interrupt_threshold; - u64 pebs_event_reset[MAX_PEBS_EVENTS]; -}; + return len; +} struct event_constraint { union { @@ -89,18 +94,39 @@ struct amd_nb { struct event_constraint event_constraints[X86_PMC_IDX_MAX]; }; +#define MAX_LBR_ENTRIES 16 + struct cpu_hw_events { + /* + * Generic x86 PMC bits + */ struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */ unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; - unsigned long interrupts; int enabled; - struct debug_store *ds; int n_events; int n_added; int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ u64 tags[X86_PMC_IDX_MAX]; struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */ + + /* + * Intel DebugStore bits + */ + struct debug_store *ds; + u64 pebs_enabled; + + /* + * Intel LBR bits + */ + int lbr_users; + void *lbr_context; + struct perf_branch_stack lbr_stack; + struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; + + /* + * AMD specific bits + */ struct amd_nb *amd_nb; }; @@ -114,11 +140,31 @@ struct cpu_hw_events { #define EVENT_CONSTRAINT(c, n, m) \ __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n)) +/* + * Constraint on the Event code. + */ #define INTEL_EVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVTSEL_MASK) + EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT) +/* + * Constraint on the Event code + UMask + fixed-mask + * + * filter mask to validate fixed counter events. + * the following filters disqualify for fixed counters: + * - inv + * - edge + * - cnt-mask + * The other filters are supported by fixed counters. + * The any-thread option is supported starting with v3. + */ #define FIXED_EVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, (1ULL << (32+n)), INTEL_ARCH_FIXED_MASK) + EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK) + +/* + * Constraint on the Event code + UMask + */ +#define PEBS_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) #define EVENT_CONSTRAINT_END \ EVENT_CONSTRAINT(0, 0, 0) @@ -126,32 +172,43 @@ struct cpu_hw_events { #define for_each_event_constraint(e, c) \ for ((e) = (c); (e)->cmask; (e)++) +union perf_capabilities { + struct { + u64 lbr_format : 6; + u64 pebs_trap : 1; + u64 pebs_arch_reg : 1; + u64 pebs_format : 4; + u64 smm_freeze : 1; + }; + u64 capabilities; +}; + /* * struct x86_pmu - generic x86 pmu */ struct x86_pmu { + /* + * Generic x86 PMC bits + */ const char *name; int version; int (*handle_irq)(struct pt_regs *); void (*disable_all)(void); - void (*enable_all)(void); + void (*enable_all)(int added); void (*enable)(struct perf_event *); void (*disable)(struct perf_event *); + int (*hw_config)(struct perf_event *event); + int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); unsigned eventsel; unsigned perfctr; u64 (*event_map)(int); - u64 (*raw_event)(u64); int max_events; - int num_events; - int num_events_fixed; - int event_bits; - u64 event_mask; + int num_counters; + int num_counters_fixed; + int cntval_bits; + u64 cntval_mask; int apic; u64 max_period; - u64 intel_ctrl; - void (*enable_bts)(u64 config); - void (*disable_bts)(void); - struct event_constraint * (*get_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); @@ -159,11 +216,32 @@ struct x86_pmu { void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); struct event_constraint *event_constraints; + void (*quirks)(void); int (*cpu_prepare)(int cpu); void (*cpu_starting)(int cpu); void (*cpu_dying)(int cpu); void (*cpu_dead)(int cpu); + + /* + * Intel Arch Perfmon v2+ + */ + u64 intel_ctrl; + union perf_capabilities intel_cap; + + /* + * Intel DebugStore bits + */ + int bts, pebs; + int pebs_record_size; + void (*drain_pebs)(struct pt_regs *regs); + struct event_constraint *pebs_constraints; + + /* + * Intel LBR + */ + unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */ + int lbr_nr; /* hardware stack size */ }; static struct x86_pmu x86_pmu __read_mostly; @@ -198,7 +276,7 @@ static u64 x86_perf_event_update(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - int shift = 64 - x86_pmu.event_bits; + int shift = 64 - x86_pmu.cntval_bits; u64 prev_raw_count, new_raw_count; int idx = hwc->idx; s64 delta; @@ -241,33 +319,32 @@ again: static atomic_t active_events; static DEFINE_MUTEX(pmc_reserve_mutex); +#ifdef CONFIG_X86_LOCAL_APIC + static bool reserve_pmc_hardware(void) { -#ifdef CONFIG_X86_LOCAL_APIC int i; if (nmi_watchdog == NMI_LOCAL_APIC) disable_lapic_nmi_watchdog(); - for (i = 0; i < x86_pmu.num_events; i++) { + for (i = 0; i < x86_pmu.num_counters; i++) { if (!reserve_perfctr_nmi(x86_pmu.perfctr + i)) goto perfctr_fail; } - for (i = 0; i < x86_pmu.num_events; i++) { + for (i = 0; i < x86_pmu.num_counters; i++) { if (!reserve_evntsel_nmi(x86_pmu.eventsel + i)) goto eventsel_fail; } -#endif return true; -#ifdef CONFIG_X86_LOCAL_APIC eventsel_fail: for (i--; i >= 0; i--) release_evntsel_nmi(x86_pmu.eventsel + i); - i = x86_pmu.num_events; + i = x86_pmu.num_counters; perfctr_fail: for (i--; i >= 0; i--) @@ -277,128 +354,36 @@ perfctr_fail: enable_lapic_nmi_watchdog(); return false; -#endif } static void release_pmc_hardware(void) { -#ifdef CONFIG_X86_LOCAL_APIC int i; - for (i = 0; i < x86_pmu.num_events; i++) { + for (i = 0; i < x86_pmu.num_counters; i++) { release_perfctr_nmi(x86_pmu.perfctr + i); release_evntsel_nmi(x86_pmu.eventsel + i); } if (nmi_watchdog == NMI_LOCAL_APIC) enable_lapic_nmi_watchdog(); -#endif -} - -static inline bool bts_available(void) -{ - return x86_pmu.enable_bts != NULL; -} - -static void init_debug_store_on_cpu(int cpu) -{ - struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; - - if (!ds) - return; - - wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, - (u32)((u64)(unsigned long)ds), - (u32)((u64)(unsigned long)ds >> 32)); -} - -static void fini_debug_store_on_cpu(int cpu) -{ - if (!per_cpu(cpu_hw_events, cpu).ds) - return; - - wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0); } -static void release_bts_hardware(void) -{ - int cpu; - - if (!bts_available()) - return; - - get_online_cpus(); - - for_each_online_cpu(cpu) - fini_debug_store_on_cpu(cpu); - - for_each_possible_cpu(cpu) { - struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; - - if (!ds) - continue; - - per_cpu(cpu_hw_events, cpu).ds = NULL; - - kfree((void *)(unsigned long)ds->bts_buffer_base); - kfree(ds); - } - - put_online_cpus(); -} - -static int reserve_bts_hardware(void) -{ - int cpu, err = 0; - - if (!bts_available()) - return 0; - - get_online_cpus(); - - for_each_possible_cpu(cpu) { - struct debug_store *ds; - void *buffer; - - err = -ENOMEM; - buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL); - if (unlikely(!buffer)) - break; - - ds = kzalloc(sizeof(*ds), GFP_KERNEL); - if (unlikely(!ds)) { - kfree(buffer); - break; - } - - ds->bts_buffer_base = (u64)(unsigned long)buffer; - ds->bts_index = ds->bts_buffer_base; - ds->bts_absolute_maximum = - ds->bts_buffer_base + BTS_BUFFER_SIZE; - ds->bts_interrupt_threshold = - ds->bts_absolute_maximum - BTS_OVFL_TH; - - per_cpu(cpu_hw_events, cpu).ds = ds; - err = 0; - } +#else - if (err) - release_bts_hardware(); - else { - for_each_online_cpu(cpu) - init_debug_store_on_cpu(cpu); - } +static bool reserve_pmc_hardware(void) { return true; } +static void release_pmc_hardware(void) {} - put_online_cpus(); +#endif - return err; -} +static int reserve_ds_buffers(void); +static void release_ds_buffers(void); static void hw_perf_event_destroy(struct perf_event *event) { if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) { release_pmc_hardware(); - release_bts_hardware(); + release_ds_buffers(); mutex_unlock(&pmc_reserve_mutex); } } @@ -441,6 +426,28 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr) return 0; } +static int x86_pmu_hw_config(struct perf_event *event) +{ + /* + * Generate PMC IRQs: + * (keep 'enabled' bit clear for now) + */ + event->hw.config = ARCH_PERFMON_EVENTSEL_INT; + + /* + * Count user and OS events unless requested not to + */ + if (!event->attr.exclude_user) + event->hw.config |= ARCH_PERFMON_EVENTSEL_USR; + if (!event->attr.exclude_kernel) + event->hw.config |= ARCH_PERFMON_EVENTSEL_OS; + + if (event->attr.type == PERF_TYPE_RAW) + event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK; + + return 0; +} + /* * Setup the hardware configuration for a given attr_type */ @@ -460,8 +467,11 @@ static int __hw_perf_event_init(struct perf_event *event) if (atomic_read(&active_events) == 0) { if (!reserve_pmc_hardware()) err = -EBUSY; - else - err = reserve_bts_hardware(); + else { + err = reserve_ds_buffers(); + if (err) + release_pmc_hardware(); + } } if (!err) atomic_inc(&active_events); @@ -472,23 +482,14 @@ static int __hw_perf_event_init(struct perf_event *event) event->destroy = hw_perf_event_destroy; - /* - * Generate PMC IRQs: - * (keep 'enabled' bit clear for now) - */ - hwc->config = ARCH_PERFMON_EVENTSEL_INT; - hwc->idx = -1; hwc->last_cpu = -1; hwc->last_tag = ~0ULL; - /* - * Count user and OS events unless requested not to. - */ - if (!attr->exclude_user) - hwc->config |= ARCH_PERFMON_EVENTSEL_USR; - if (!attr->exclude_kernel) - hwc->config |= ARCH_PERFMON_EVENTSEL_OS; + /* Processor specifics */ + err = x86_pmu.hw_config(event); + if (err) + return err; if (!hwc->sample_period) { hwc->sample_period = x86_pmu.max_period; @@ -505,16 +506,8 @@ static int __hw_perf_event_init(struct perf_event *event) return -EOPNOTSUPP; } - /* - * Raw hw_event type provide the config in the hw_event structure - */ - if (attr->type == PERF_TYPE_RAW) { - hwc->config |= x86_pmu.raw_event(attr->config); - if ((hwc->config & ARCH_PERFMON_EVENTSEL_ANY) && - perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) - return -EACCES; + if (attr->type == PERF_TYPE_RAW) return 0; - } if (attr->type == PERF_TYPE_HW_CACHE) return set_ext_hw_attr(hwc, attr); @@ -539,11 +532,11 @@ static int __hw_perf_event_init(struct perf_event *event) if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) && (hwc->sample_period == 1)) { /* BTS is not supported by this architecture. */ - if (!bts_available()) + if (!x86_pmu.bts) return -EOPNOTSUPP; /* BTS is currently only allowed for user-mode. */ - if (hwc->config & ARCH_PERFMON_EVENTSEL_OS) + if (!attr->exclude_kernel) return -EOPNOTSUPP; } @@ -557,7 +550,7 @@ static void x86_pmu_disable_all(void) struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx; - for (idx = 0; idx < x86_pmu.num_events; idx++) { + for (idx = 0; idx < x86_pmu.num_counters; idx++) { u64 val; if (!test_bit(idx, cpuc->active_mask)) @@ -587,12 +580,12 @@ void hw_perf_disable(void) x86_pmu.disable_all(); } -static void x86_pmu_enable_all(void) +static void x86_pmu_enable_all(int added) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx; - for (idx = 0; idx < x86_pmu.num_events; idx++) { + for (idx = 0; idx < x86_pmu.num_counters; idx++) { struct perf_event *event = cpuc->events[idx]; u64 val; @@ -667,14 +660,14 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) * assign events to counters starting with most * constrained events. */ - wmax = x86_pmu.num_events; + wmax = x86_pmu.num_counters; /* * when fixed event counters are present, * wmax is incremented by 1 to account * for one more choice */ - if (x86_pmu.num_events_fixed) + if (x86_pmu.num_counters_fixed) wmax++; for (w = 1, num = n; num && w <= wmax; w++) { @@ -724,7 +717,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, struct perf_event *event; int n, max_count; - max_count = x86_pmu.num_events + x86_pmu.num_events_fixed; + max_count = x86_pmu.num_counters + x86_pmu.num_counters_fixed; /* current number of events already accepted */ n = cpuc->n_events; @@ -795,7 +788,7 @@ void hw_perf_enable(void) struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct perf_event *event; struct hw_perf_event *hwc; - int i; + int i, added = cpuc->n_added; if (!x86_pmu_initialized()) return; @@ -847,19 +840,20 @@ void hw_perf_enable(void) cpuc->enabled = 1; barrier(); - x86_pmu.enable_all(); + x86_pmu.enable_all(added); } static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc) { - (void)checking_wrmsrl(hwc->config_base + hwc->idx, + wrmsrl(hwc->config_base + hwc->idx, hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE); } static inline void x86_pmu_disable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - (void)checking_wrmsrl(hwc->config_base + hwc->idx, hwc->config); + + wrmsrl(hwc->config_base + hwc->idx, hwc->config); } static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); @@ -874,7 +868,7 @@ x86_perf_event_set_period(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; s64 left = atomic64_read(&hwc->period_left); s64 period = hwc->sample_period; - int err, ret = 0, idx = hwc->idx; + int ret = 0, idx = hwc->idx; if (idx == X86_PMC_IDX_FIXED_BTS) return 0; @@ -912,8 +906,8 @@ x86_perf_event_set_period(struct perf_event *event) */ atomic64_set(&hwc->prev_count, (u64)-left); - err = checking_wrmsrl(hwc->event_base + idx, - (u64)(-left) & x86_pmu.event_mask); + wrmsrl(hwc->event_base + idx, + (u64)(-left) & x86_pmu.cntval_mask); perf_event_update_userpage(event); @@ -950,7 +944,7 @@ static int x86_pmu_enable(struct perf_event *event) if (n < 0) return n; - ret = x86_schedule_events(cpuc, n, assign); + ret = x86_pmu.schedule_events(cpuc, n, assign); if (ret) return ret; /* @@ -991,11 +985,12 @@ static void x86_pmu_unthrottle(struct perf_event *event) void perf_event_print_debug(void) { u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed; + u64 pebs; struct cpu_hw_events *cpuc; unsigned long flags; int cpu, idx; - if (!x86_pmu.num_events) + if (!x86_pmu.num_counters) return; local_irq_save(flags); @@ -1008,16 +1003,18 @@ void perf_event_print_debug(void) rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status); rdmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow); rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed); + rdmsrl(MSR_IA32_PEBS_ENABLE, pebs); pr_info("\n"); pr_info("CPU#%d: ctrl: %016llx\n", cpu, ctrl); pr_info("CPU#%d: status: %016llx\n", cpu, status); pr_info("CPU#%d: overflow: %016llx\n", cpu, overflow); pr_info("CPU#%d: fixed: %016llx\n", cpu, fixed); + pr_info("CPU#%d: pebs: %016llx\n", cpu, pebs); } - pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask); + pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask); - for (idx = 0; idx < x86_pmu.num_events; idx++) { + for (idx = 0; idx < x86_pmu.num_counters; idx++) { rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl); rdmsrl(x86_pmu.perfctr + idx, pmc_count); @@ -1030,7 +1027,7 @@ void perf_event_print_debug(void) pr_info("CPU#%d: gen-PMC%d left: %016llx\n", cpu, idx, prev_left); } - for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) { + for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) { rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count); pr_info("CPU#%d: fixed-PMC%d count: %016llx\n", @@ -1095,7 +1092,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) cpuc = &__get_cpu_var(cpu_hw_events); - for (idx = 0; idx < x86_pmu.num_events; idx++) { + for (idx = 0; idx < x86_pmu.num_counters; idx++) { if (!test_bit(idx, cpuc->active_mask)) continue; @@ -1103,7 +1100,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) hwc = &event->hw; val = x86_perf_event_update(event); - if (val & (1ULL << (x86_pmu.event_bits - 1))) + if (val & (1ULL << (x86_pmu.cntval_bits - 1))) continue; /* @@ -1146,7 +1143,6 @@ void set_perf_event_pending(void) void perf_events_lapic_init(void) { -#ifdef CONFIG_X86_LOCAL_APIC if (!x86_pmu.apic || !x86_pmu_initialized()) return; @@ -1154,7 +1150,6 @@ void perf_events_lapic_init(void) * Always use NMI for PMU */ apic_write(APIC_LVTPC, APIC_DM_NMI); -#endif } static int __kprobes @@ -1178,9 +1173,7 @@ perf_event_nmi_handler(struct notifier_block *self, regs = args->regs; -#ifdef CONFIG_X86_LOCAL_APIC apic_write(APIC_LVTPC, APIC_DM_NMI); -#endif /* * Can't rely on the handled return value to say it was our NMI, two * events could trigger 'simultaneously' raising two back-to-back NMIs. @@ -1274,12 +1267,15 @@ int hw_perf_group_sched_in(struct perf_event *leader, int assign[X86_PMC_IDX_MAX]; int n0, n1, ret; + if (!x86_pmu_initialized()) + return 0; + /* n0 = total number of events */ n0 = collect_events(cpuc, leader, true); if (n0 < 0) return n0; - ret = x86_schedule_events(cpuc, n0, assign); + ret = x86_pmu.schedule_events(cpuc, n0, assign); if (ret) return ret; @@ -1329,6 +1325,9 @@ undo: #include "perf_event_amd.c" #include "perf_event_p6.c" +#include "perf_event_p4.c" +#include "perf_event_intel_lbr.c" +#include "perf_event_intel_ds.c" #include "perf_event_intel.c" static int __cpuinit @@ -1402,48 +1401,50 @@ void __init init_hw_perf_events(void) pr_cont("%s PMU driver.\n", x86_pmu.name); - if (x86_pmu.num_events > X86_PMC_MAX_GENERIC) { + if (x86_pmu.quirks) + x86_pmu.quirks(); + + if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) { WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!", - x86_pmu.num_events, X86_PMC_MAX_GENERIC); - x86_pmu.num_events = X86_PMC_MAX_GENERIC; + x86_pmu.num_counters, X86_PMC_MAX_GENERIC); + x86_pmu.num_counters = X86_PMC_MAX_GENERIC; } - perf_event_mask = (1 << x86_pmu.num_events) - 1; - perf_max_events = x86_pmu.num_events; + x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1; + perf_max_events = x86_pmu.num_counters; - if (x86_pmu.num_events_fixed > X86_PMC_MAX_FIXED) { + if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) { WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!", - x86_pmu.num_events_fixed, X86_PMC_MAX_FIXED); - x86_pmu.num_events_fixed = X86_PMC_MAX_FIXED; + x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED); + x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED; } - perf_event_mask |= - ((1LL << x86_pmu.num_events_fixed)-1) << X86_PMC_IDX_FIXED; - x86_pmu.intel_ctrl = perf_event_mask; + x86_pmu.intel_ctrl |= + ((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED; perf_events_lapic_init(); register_die_notifier(&perf_event_nmi_notifier); unconstrained = (struct event_constraint) - __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_events) - 1, - 0, x86_pmu.num_events); + __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1, + 0, x86_pmu.num_counters); if (x86_pmu.event_constraints) { for_each_event_constraint(c, x86_pmu.event_constraints) { - if (c->cmask != INTEL_ARCH_FIXED_MASK) + if (c->cmask != X86_RAW_EVENT_MASK) continue; - c->idxmsk64 |= (1ULL << x86_pmu.num_events) - 1; - c->weight += x86_pmu.num_events; + c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; + c->weight += x86_pmu.num_counters; } } pr_info("... version: %d\n", x86_pmu.version); - pr_info("... bit width: %d\n", x86_pmu.event_bits); - pr_info("... generic registers: %d\n", x86_pmu.num_events); - pr_info("... value mask: %016Lx\n", x86_pmu.event_mask); + pr_info("... bit width: %d\n", x86_pmu.cntval_bits); + pr_info("... generic registers: %d\n", x86_pmu.num_counters); + pr_info("... value mask: %016Lx\n", x86_pmu.cntval_mask); pr_info("... max period: %016Lx\n", x86_pmu.max_period); - pr_info("... fixed-purpose events: %d\n", x86_pmu.num_events_fixed); - pr_info("... event mask: %016Lx\n", perf_event_mask); + pr_info("... fixed-purpose events: %d\n", x86_pmu.num_counters_fixed); + pr_info("... event mask: %016Lx\n", x86_pmu.intel_ctrl); perf_cpu_notifier(x86_pmu_notifier); } @@ -1463,6 +1464,32 @@ static const struct pmu pmu = { }; /* + * validate that we can schedule this event + */ +static int validate_event(struct perf_event *event) +{ + struct cpu_hw_events *fake_cpuc; + struct event_constraint *c; + int ret = 0; + + fake_cpuc = kmalloc(sizeof(*fake_cpuc), GFP_KERNEL | __GFP_ZERO); + if (!fake_cpuc) + return -ENOMEM; + + c = x86_pmu.get_event_constraints(fake_cpuc, event); + + if (!c || !c->weight) + ret = -ENOSPC; + + if (x86_pmu.put_event_constraints) + x86_pmu.put_event_constraints(fake_cpuc, event); + + kfree(fake_cpuc); + + return ret; +} + +/* * validate a single event group * * validation include: @@ -1502,7 +1529,7 @@ static int validate_group(struct perf_event *event) fake_cpuc->n_events = n; - ret = x86_schedule_events(fake_cpuc, n, NULL); + ret = x86_pmu.schedule_events(fake_cpuc, n, NULL); out_free: kfree(fake_cpuc); @@ -1527,6 +1554,8 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) if (event->group_leader != event) err = validate_group(event); + else + err = validate_event(event); event->pmu = tmp; } @@ -1574,8 +1603,7 @@ static void backtrace_address(void *data, unsigned long addr, int reliable) { struct perf_callchain_entry *entry = data; - if (reliable) - callchain_store(entry, addr); + callchain_store(entry, addr); } static const struct stacktrace_ops backtrace_ops = { @@ -1597,41 +1625,6 @@ perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry) dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry); } -/* - * best effort, GUP based copy_from_user() that assumes IRQ or NMI context - */ -static unsigned long -copy_from_user_nmi(void *to, const void __user *from, unsigned long n) -{ - unsigned long offset, addr = (unsigned long)from; - int type = in_nmi() ? KM_NMI : KM_IRQ0; - unsigned long size, len = 0; - struct page *page; - void *map; - int ret; - - do { - ret = __get_user_pages_fast(addr, 1, 0, &page); - if (!ret) - break; - - offset = addr & (PAGE_SIZE - 1); - size = min(PAGE_SIZE - offset, n - len); - - map = kmap_atomic(page, type); - memcpy(to, map+offset, size); - kunmap_atomic(map, type); - put_page(page); - - len += size; - to += size; - addr += size; - - } while (len < n); - - return len; -} - #ifdef CONFIG_COMPAT static inline int perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) @@ -1727,6 +1720,11 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) { struct perf_callchain_entry *entry; + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + /* TODO: We don't support guest os callchain now */ + return NULL; + } + if (in_nmi()) entry = &__get_cpu_var(pmc_nmi_entry); else @@ -1750,3 +1748,37 @@ void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int ski regs->cs = __KERNEL_CS; local_save_flags(regs->flags); } + +unsigned long perf_instruction_pointer(struct pt_regs *regs) +{ + unsigned long ip; + + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) + ip = perf_guest_cbs->get_guest_ip(); + else + ip = instruction_pointer(regs); + + return ip; +} + +unsigned long perf_misc_flags(struct pt_regs *regs) +{ + int misc = 0; + + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + if (perf_guest_cbs->is_user_mode()) + misc |= PERF_RECORD_MISC_GUEST_USER; + else + misc |= PERF_RECORD_MISC_GUEST_KERNEL; + } else { + if (user_mode(regs)) + misc |= PERF_RECORD_MISC_USER; + else + misc |= PERF_RECORD_MISC_KERNEL; + } + + if (regs->flags & PERF_EFLAGS_EXACT) + misc |= PERF_RECORD_MISC_EXACT; + + return misc; +} diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index db6f7d4056e1..611df11ba15e 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -2,7 +2,7 @@ static DEFINE_RAW_SPINLOCK(amd_nb_lock); -static __initconst u64 amd_hw_cache_event_ids +static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -111,22 +111,19 @@ static u64 amd_pmu_event_map(int hw_event) return amd_perfmon_event_map[hw_event]; } -static u64 amd_pmu_raw_event(u64 hw_event) +static int amd_pmu_hw_config(struct perf_event *event) { -#define K7_EVNTSEL_EVENT_MASK 0xF000000FFULL -#define K7_EVNTSEL_UNIT_MASK 0x00000FF00ULL -#define K7_EVNTSEL_EDGE_MASK 0x000040000ULL -#define K7_EVNTSEL_INV_MASK 0x000800000ULL -#define K7_EVNTSEL_REG_MASK 0x0FF000000ULL - -#define K7_EVNTSEL_MASK \ - (K7_EVNTSEL_EVENT_MASK | \ - K7_EVNTSEL_UNIT_MASK | \ - K7_EVNTSEL_EDGE_MASK | \ - K7_EVNTSEL_INV_MASK | \ - K7_EVNTSEL_REG_MASK) - - return hw_event & K7_EVNTSEL_MASK; + int ret = x86_pmu_hw_config(event); + + if (ret) + return ret; + + if (event->attr.type != PERF_TYPE_RAW) + return 0; + + event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK; + + return 0; } /* @@ -165,7 +162,7 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc, * be removed on one CPU at a time AND PMU is disabled * when we come here */ - for (i = 0; i < x86_pmu.num_events; i++) { + for (i = 0; i < x86_pmu.num_counters; i++) { if (nb->owners[i] == event) { cmpxchg(nb->owners+i, event, NULL); break; @@ -215,7 +212,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) struct hw_perf_event *hwc = &event->hw; struct amd_nb *nb = cpuc->amd_nb; struct perf_event *old = NULL; - int max = x86_pmu.num_events; + int max = x86_pmu.num_counters; int i, j, k = -1; /* @@ -293,7 +290,7 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id) /* * initialize all possible NB constraints */ - for (i = 0; i < x86_pmu.num_events; i++) { + for (i = 0; i < x86_pmu.num_counters; i++) { __set_bit(i, nb->event_constraints[i].idxmsk); nb->event_constraints[i].weight = 1; } @@ -371,21 +368,22 @@ static void amd_pmu_cpu_dead(int cpu) raw_spin_unlock(&amd_nb_lock); } -static __initconst struct x86_pmu amd_pmu = { +static __initconst const struct x86_pmu amd_pmu = { .name = "AMD", .handle_irq = x86_pmu_handle_irq, .disable_all = x86_pmu_disable_all, .enable_all = x86_pmu_enable_all, .enable = x86_pmu_enable_event, .disable = x86_pmu_disable_event, + .hw_config = amd_pmu_hw_config, + .schedule_events = x86_schedule_events, .eventsel = MSR_K7_EVNTSEL0, .perfctr = MSR_K7_PERFCTR0, .event_map = amd_pmu_event_map, - .raw_event = amd_pmu_raw_event, .max_events = ARRAY_SIZE(amd_perfmon_event_map), - .num_events = 4, - .event_bits = 48, - .event_mask = (1ULL << 48) - 1, + .num_counters = 4, + .cntval_bits = 48, + .cntval_mask = (1ULL << 48) - 1, .apic = 1, /* use highest bit to detect overflow */ .max_period = (1ULL << 47) - 1, diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 9c794ac87837..a099df96f916 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -88,7 +88,7 @@ static u64 intel_pmu_event_map(int hw_event) return intel_perfmon_event_map[hw_event]; } -static __initconst u64 westmere_hw_cache_event_ids +static __initconst const u64 westmere_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -179,7 +179,7 @@ static __initconst u64 westmere_hw_cache_event_ids }, }; -static __initconst u64 nehalem_hw_cache_event_ids +static __initconst const u64 nehalem_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -270,7 +270,7 @@ static __initconst u64 nehalem_hw_cache_event_ids }, }; -static __initconst u64 core2_hw_cache_event_ids +static __initconst const u64 core2_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -361,7 +361,7 @@ static __initconst u64 core2_hw_cache_event_ids }, }; -static __initconst u64 atom_hw_cache_event_ids +static __initconst const u64 atom_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -452,60 +452,6 @@ static __initconst u64 atom_hw_cache_event_ids }, }; -static u64 intel_pmu_raw_event(u64 hw_event) -{ -#define CORE_EVNTSEL_EVENT_MASK 0x000000FFULL -#define CORE_EVNTSEL_UNIT_MASK 0x0000FF00ULL -#define CORE_EVNTSEL_EDGE_MASK 0x00040000ULL -#define CORE_EVNTSEL_INV_MASK 0x00800000ULL -#define CORE_EVNTSEL_REG_MASK 0xFF000000ULL - -#define CORE_EVNTSEL_MASK \ - (INTEL_ARCH_EVTSEL_MASK | \ - INTEL_ARCH_UNIT_MASK | \ - INTEL_ARCH_EDGE_MASK | \ - INTEL_ARCH_INV_MASK | \ - INTEL_ARCH_CNT_MASK) - - return hw_event & CORE_EVNTSEL_MASK; -} - -static void intel_pmu_enable_bts(u64 config) -{ - unsigned long debugctlmsr; - - debugctlmsr = get_debugctlmsr(); - - debugctlmsr |= X86_DEBUGCTL_TR; - debugctlmsr |= X86_DEBUGCTL_BTS; - debugctlmsr |= X86_DEBUGCTL_BTINT; - - if (!(config & ARCH_PERFMON_EVENTSEL_OS)) - debugctlmsr |= X86_DEBUGCTL_BTS_OFF_OS; - - if (!(config & ARCH_PERFMON_EVENTSEL_USR)) - debugctlmsr |= X86_DEBUGCTL_BTS_OFF_USR; - - update_debugctlmsr(debugctlmsr); -} - -static void intel_pmu_disable_bts(void) -{ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - unsigned long debugctlmsr; - - if (!cpuc->ds) - return; - - debugctlmsr = get_debugctlmsr(); - - debugctlmsr &= - ~(X86_DEBUGCTL_TR | X86_DEBUGCTL_BTS | X86_DEBUGCTL_BTINT | - X86_DEBUGCTL_BTS_OFF_OS | X86_DEBUGCTL_BTS_OFF_USR); - - update_debugctlmsr(debugctlmsr); -} - static void intel_pmu_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -514,12 +460,17 @@ static void intel_pmu_disable_all(void) if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) intel_pmu_disable_bts(); + + intel_pmu_pebs_disable_all(); + intel_pmu_lbr_disable_all(); } -static void intel_pmu_enable_all(void) +static void intel_pmu_enable_all(int added) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + intel_pmu_pebs_enable_all(); + intel_pmu_lbr_enable_all(); wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl); if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) { @@ -533,6 +484,41 @@ static void intel_pmu_enable_all(void) } } +/* + * Workaround for: + * Intel Errata AAK100 (model 26) + * Intel Errata AAP53 (model 30) + * Intel Errata BD53 (model 44) + * + * These chips need to be 'reset' when adding counters by programming + * the magic three (non counting) events 0x4300D2, 0x4300B1 and 0x4300B5 + * either in sequence on the same PMC or on different PMCs. + */ +static void intel_pmu_nhm_enable_all(int added) +{ + if (added) { + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int i; + + wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 0, 0x4300D2); + wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x4300B1); + wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x4300B5); + + wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x3); + wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0); + + for (i = 0; i < 3; i++) { + struct perf_event *event = cpuc->events[i]; + + if (!event) + continue; + + __x86_pmu_enable_event(&event->hw); + } + } + intel_pmu_enable_all(added); +} + static inline u64 intel_pmu_get_status(void) { u64 status; @@ -547,8 +533,7 @@ static inline void intel_pmu_ack_status(u64 ack) wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack); } -static inline void -intel_pmu_disable_fixed(struct hw_perf_event *hwc) +static void intel_pmu_disable_fixed(struct hw_perf_event *hwc) { int idx = hwc->idx - X86_PMC_IDX_FIXED; u64 ctrl_val, mask; @@ -557,71 +542,10 @@ intel_pmu_disable_fixed(struct hw_perf_event *hwc) rdmsrl(hwc->config_base, ctrl_val); ctrl_val &= ~mask; - (void)checking_wrmsrl(hwc->config_base, ctrl_val); -} - -static void intel_pmu_drain_bts_buffer(void) -{ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct debug_store *ds = cpuc->ds; - struct bts_record { - u64 from; - u64 to; - u64 flags; - }; - struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS]; - struct bts_record *at, *top; - struct perf_output_handle handle; - struct perf_event_header header; - struct perf_sample_data data; - struct pt_regs regs; - - if (!event) - return; - - if (!ds) - return; - - at = (struct bts_record *)(unsigned long)ds->bts_buffer_base; - top = (struct bts_record *)(unsigned long)ds->bts_index; - - if (top <= at) - return; - - ds->bts_index = ds->bts_buffer_base; - - perf_sample_data_init(&data, 0); - - data.period = event->hw.last_period; - regs.ip = 0; - - /* - * Prepare a generic sample, i.e. fill in the invariant fields. - * We will overwrite the from and to address before we output - * the sample. - */ - perf_prepare_sample(&header, &data, event, ®s); - - if (perf_output_begin(&handle, event, - header.size * (top - at), 1, 1)) - return; - - for (; at < top; at++) { - data.ip = at->from; - data.addr = at->to; - - perf_output_sample(&handle, &header, &data, event); - } - - perf_output_end(&handle); - - /* There's new data available. */ - event->hw.interrupts++; - event->pending_kill = POLL_IN; + wrmsrl(hwc->config_base, ctrl_val); } -static inline void -intel_pmu_disable_event(struct perf_event *event) +static void intel_pmu_disable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -637,14 +561,15 @@ intel_pmu_disable_event(struct perf_event *event) } x86_pmu_disable_event(event); + + if (unlikely(event->attr.precise)) + intel_pmu_pebs_disable(event); } -static inline void -intel_pmu_enable_fixed(struct hw_perf_event *hwc) +static void intel_pmu_enable_fixed(struct hw_perf_event *hwc) { int idx = hwc->idx - X86_PMC_IDX_FIXED; u64 ctrl_val, bits, mask; - int err; /* * Enable IRQ generation (0x8), @@ -669,7 +594,7 @@ intel_pmu_enable_fixed(struct hw_perf_event *hwc) rdmsrl(hwc->config_base, ctrl_val); ctrl_val &= ~mask; ctrl_val |= bits; - err = checking_wrmsrl(hwc->config_base, ctrl_val); + wrmsrl(hwc->config_base, ctrl_val); } static void intel_pmu_enable_event(struct perf_event *event) @@ -689,6 +614,9 @@ static void intel_pmu_enable_event(struct perf_event *event) return; } + if (unlikely(event->attr.precise)) + intel_pmu_pebs_enable(event); + __x86_pmu_enable_event(hwc); } @@ -708,20 +636,20 @@ static void intel_pmu_reset(void) unsigned long flags; int idx; - if (!x86_pmu.num_events) + if (!x86_pmu.num_counters) return; local_irq_save(flags); printk("clearing PMU state on CPU#%d\n", smp_processor_id()); - for (idx = 0; idx < x86_pmu.num_events; idx++) { + for (idx = 0; idx < x86_pmu.num_counters; idx++) { checking_wrmsrl(x86_pmu.eventsel + idx, 0ull); checking_wrmsrl(x86_pmu.perfctr + idx, 0ull); } - for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) { + for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull); - } + if (ds) ds->bts_index = ds->bts_buffer_base; @@ -747,7 +675,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) intel_pmu_drain_bts_buffer(); status = intel_pmu_get_status(); if (!status) { - intel_pmu_enable_all(); + intel_pmu_enable_all(0); return 0; } @@ -762,6 +690,15 @@ again: inc_irq_stat(apic_perf_irqs); ack = status; + + intel_pmu_lbr_read(); + + /* + * PEBS overflow sets bit 62 in the global status register + */ + if (__test_and_clear_bit(62, (unsigned long *)&status)) + x86_pmu.drain_pebs(regs); + for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) { struct perf_event *event = cpuc->events[bit]; @@ -787,26 +724,22 @@ again: goto again; done: - intel_pmu_enable_all(); + intel_pmu_enable_all(0); return 1; } -static struct event_constraint bts_constraint = - EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0); - static struct event_constraint * -intel_special_constraints(struct perf_event *event) +intel_bts_constraints(struct perf_event *event) { - unsigned int hw_event; - - hw_event = event->hw.config & INTEL_ARCH_EVENT_MASK; + struct hw_perf_event *hwc = &event->hw; + unsigned int hw_event, bts_event; - if (unlikely((hw_event == - x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) && - (event->hw.sample_period == 1))) { + hw_event = hwc->config & INTEL_ARCH_EVENT_MASK; + bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS); + if (unlikely(hw_event == bts_event && hwc->sample_period == 1)) return &bts_constraint; - } + return NULL; } @@ -815,24 +748,53 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event { struct event_constraint *c; - c = intel_special_constraints(event); + c = intel_bts_constraints(event); + if (c) + return c; + + c = intel_pebs_constraints(event); if (c) return c; return x86_get_event_constraints(cpuc, event); } -static __initconst struct x86_pmu core_pmu = { +static int intel_pmu_hw_config(struct perf_event *event) +{ + int ret = x86_pmu_hw_config(event); + + if (ret) + return ret; + + if (event->attr.type != PERF_TYPE_RAW) + return 0; + + if (!(event->attr.config & ARCH_PERFMON_EVENTSEL_ANY)) + return 0; + + if (x86_pmu.version < 3) + return -EINVAL; + + if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) + return -EACCES; + + event->hw.config |= ARCH_PERFMON_EVENTSEL_ANY; + + return 0; +} + +static __initconst const struct x86_pmu core_pmu = { .name = "core", .handle_irq = x86_pmu_handle_irq, .disable_all = x86_pmu_disable_all, .enable_all = x86_pmu_enable_all, .enable = x86_pmu_enable_event, .disable = x86_pmu_disable_event, + .hw_config = x86_pmu_hw_config, + .schedule_events = x86_schedule_events, .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, .perfctr = MSR_ARCH_PERFMON_PERFCTR0, .event_map = intel_pmu_event_map, - .raw_event = intel_pmu_raw_event, .max_events = ARRAY_SIZE(intel_perfmon_event_map), .apic = 1, /* @@ -845,17 +807,32 @@ static __initconst struct x86_pmu core_pmu = { .event_constraints = intel_core_event_constraints, }; -static __initconst struct x86_pmu intel_pmu = { +static void intel_pmu_cpu_starting(int cpu) +{ + init_debug_store_on_cpu(cpu); + /* + * Deal with CPUs that don't clear their LBRs on power-up. + */ + intel_pmu_lbr_reset(); +} + +static void intel_pmu_cpu_dying(int cpu) +{ + fini_debug_store_on_cpu(cpu); +} + +static __initconst const struct x86_pmu intel_pmu = { .name = "Intel", .handle_irq = intel_pmu_handle_irq, .disable_all = intel_pmu_disable_all, .enable_all = intel_pmu_enable_all, .enable = intel_pmu_enable_event, .disable = intel_pmu_disable_event, + .hw_config = intel_pmu_hw_config, + .schedule_events = x86_schedule_events, .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, .perfctr = MSR_ARCH_PERFMON_PERFCTR0, .event_map = intel_pmu_event_map, - .raw_event = intel_pmu_raw_event, .max_events = ARRAY_SIZE(intel_perfmon_event_map), .apic = 1, /* @@ -864,14 +841,38 @@ static __initconst struct x86_pmu intel_pmu = { * the generic event period: */ .max_period = (1ULL << 31) - 1, - .enable_bts = intel_pmu_enable_bts, - .disable_bts = intel_pmu_disable_bts, .get_event_constraints = intel_get_event_constraints, - .cpu_starting = init_debug_store_on_cpu, - .cpu_dying = fini_debug_store_on_cpu, + .cpu_starting = intel_pmu_cpu_starting, + .cpu_dying = intel_pmu_cpu_dying, }; +static void intel_clovertown_quirks(void) +{ + /* + * PEBS is unreliable due to: + * + * AJ67 - PEBS may experience CPL leaks + * AJ68 - PEBS PMI may be delayed by one event + * AJ69 - GLOBAL_STATUS[62] will only be set when DEBUGCTL[12] + * AJ106 - FREEZE_LBRS_ON_PMI doesn't work in combination with PEBS + * + * AJ67 could be worked around by restricting the OS/USR flags. + * AJ69 could be worked around by setting PMU_FREEZE_ON_PMI. + * + * AJ106 could possibly be worked around by not allowing LBR + * usage from PEBS, including the fixup. + * AJ68 could possibly be worked around by always programming + * a pebs_event_reset[0] value and coping with the lost events. + * + * But taken together it might just make sense to not enable PEBS on + * these chips. + */ + printk(KERN_WARNING "PEBS disabled due to CPU errata.\n"); + x86_pmu.pebs = 0; + x86_pmu.pebs_constraints = NULL; +} + static __init int intel_pmu_init(void) { union cpuid10_edx edx; @@ -881,12 +882,13 @@ static __init int intel_pmu_init(void) int version; if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { - /* check for P6 processor family */ - if (boot_cpu_data.x86 == 6) { - return p6_pmu_init(); - } else { + switch (boot_cpu_data.x86) { + case 0x6: + return p6_pmu_init(); + case 0xf: + return p4_pmu_init(); + } return -ENODEV; - } } /* @@ -904,16 +906,28 @@ static __init int intel_pmu_init(void) x86_pmu = intel_pmu; x86_pmu.version = version; - x86_pmu.num_events = eax.split.num_events; - x86_pmu.event_bits = eax.split.bit_width; - x86_pmu.event_mask = (1ULL << eax.split.bit_width) - 1; + x86_pmu.num_counters = eax.split.num_counters; + x86_pmu.cntval_bits = eax.split.bit_width; + x86_pmu.cntval_mask = (1ULL << eax.split.bit_width) - 1; /* * Quirk: v2 perfmon does not report fixed-purpose events, so * assume at least 3 events: */ if (version > 1) - x86_pmu.num_events_fixed = max((int)edx.split.num_events_fixed, 3); + x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3); + + /* + * v2 and above have a perf capabilities MSR + */ + if (version > 1) { + u64 capabilities; + + rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities); + x86_pmu.intel_cap.capabilities = capabilities; + } + + intel_ds_init(); /* * Install the hw-cache-events table: @@ -924,12 +938,15 @@ static __init int intel_pmu_init(void) break; case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ + x86_pmu.quirks = intel_clovertown_quirks; case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */ case 29: /* six-core 45 nm xeon "Dunnington" */ memcpy(hw_cache_event_ids, core2_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + intel_pmu_lbr_init_core(); + x86_pmu.event_constraints = intel_core2_event_constraints; pr_cont("Core2 events, "); break; @@ -940,13 +957,19 @@ static __init int intel_pmu_init(void) memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + intel_pmu_lbr_init_nhm(); + x86_pmu.event_constraints = intel_nehalem_event_constraints; - pr_cont("Nehalem/Corei7 events, "); + x86_pmu.enable_all = intel_pmu_nhm_enable_all; + pr_cont("Nehalem events, "); break; + case 28: /* Atom */ memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + intel_pmu_lbr_init_atom(); + x86_pmu.event_constraints = intel_gen_event_constraints; pr_cont("Atom events, "); break; @@ -956,7 +979,10 @@ static __init int intel_pmu_init(void) memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + intel_pmu_lbr_init_nhm(); + x86_pmu.event_constraints = intel_westmere_event_constraints; + x86_pmu.enable_all = intel_pmu_nhm_enable_all; pr_cont("Westmere events, "); break; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c new file mode 100644 index 000000000000..ec8b2e12e104 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -0,0 +1,664 @@ +#ifdef CONFIG_CPU_SUP_INTEL + +/* The maximal number of PEBS events: */ +#define MAX_PEBS_EVENTS 4 + +/* The size of a BTS record in bytes: */ +#define BTS_RECORD_SIZE 24 + +#define BTS_BUFFER_SIZE (PAGE_SIZE << 4) +#define PEBS_BUFFER_SIZE PAGE_SIZE + +/* + * pebs_record_32 for p4 and core not supported + +struct pebs_record_32 { + u32 flags, ip; + u32 ax, bc, cx, dx; + u32 si, di, bp, sp; +}; + + */ + +struct pebs_record_core { + u64 flags, ip; + u64 ax, bx, cx, dx; + u64 si, di, bp, sp; + u64 r8, r9, r10, r11; + u64 r12, r13, r14, r15; +}; + +struct pebs_record_nhm { + u64 flags, ip; + u64 ax, bx, cx, dx; + u64 si, di, bp, sp; + u64 r8, r9, r10, r11; + u64 r12, r13, r14, r15; + u64 status, dla, dse, lat; +}; + +/* + * A debug store configuration. + * + * We only support architectures that use 64bit fields. + */ +struct debug_store { + u64 bts_buffer_base; + u64 bts_index; + u64 bts_absolute_maximum; + u64 bts_interrupt_threshold; + u64 pebs_buffer_base; + u64 pebs_index; + u64 pebs_absolute_maximum; + u64 pebs_interrupt_threshold; + u64 pebs_event_reset[MAX_PEBS_EVENTS]; +}; + +static void init_debug_store_on_cpu(int cpu) +{ + struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; + + if (!ds) + return; + + wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, + (u32)((u64)(unsigned long)ds), + (u32)((u64)(unsigned long)ds >> 32)); +} + +static void fini_debug_store_on_cpu(int cpu) +{ + if (!per_cpu(cpu_hw_events, cpu).ds) + return; + + wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0); +} + +static void release_ds_buffers(void) +{ + int cpu; + + if (!x86_pmu.bts && !x86_pmu.pebs) + return; + + get_online_cpus(); + + for_each_online_cpu(cpu) + fini_debug_store_on_cpu(cpu); + + for_each_possible_cpu(cpu) { + struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; + + if (!ds) + continue; + + per_cpu(cpu_hw_events, cpu).ds = NULL; + + kfree((void *)(unsigned long)ds->pebs_buffer_base); + kfree((void *)(unsigned long)ds->bts_buffer_base); + kfree(ds); + } + + put_online_cpus(); +} + +static int reserve_ds_buffers(void) +{ + int cpu, err = 0; + + if (!x86_pmu.bts && !x86_pmu.pebs) + return 0; + + get_online_cpus(); + + for_each_possible_cpu(cpu) { + struct debug_store *ds; + void *buffer; + int max, thresh; + + err = -ENOMEM; + ds = kzalloc(sizeof(*ds), GFP_KERNEL); + if (unlikely(!ds)) + break; + per_cpu(cpu_hw_events, cpu).ds = ds; + + if (x86_pmu.bts) { + buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL); + if (unlikely(!buffer)) + break; + + max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE; + thresh = max / 16; + + ds->bts_buffer_base = (u64)(unsigned long)buffer; + ds->bts_index = ds->bts_buffer_base; + ds->bts_absolute_maximum = ds->bts_buffer_base + + max * BTS_RECORD_SIZE; + ds->bts_interrupt_threshold = ds->bts_absolute_maximum - + thresh * BTS_RECORD_SIZE; + } + + if (x86_pmu.pebs) { + buffer = kzalloc(PEBS_BUFFER_SIZE, GFP_KERNEL); + if (unlikely(!buffer)) + break; + + max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size; + + ds->pebs_buffer_base = (u64)(unsigned long)buffer; + ds->pebs_index = ds->pebs_buffer_base; + ds->pebs_absolute_maximum = ds->pebs_buffer_base + + max * x86_pmu.pebs_record_size; + /* + * Always use single record PEBS + */ + ds->pebs_interrupt_threshold = ds->pebs_buffer_base + + x86_pmu.pebs_record_size; + } + + err = 0; + } + + if (err) + release_ds_buffers(); + else { + for_each_online_cpu(cpu) + init_debug_store_on_cpu(cpu); + } + + put_online_cpus(); + + return err; +} + +/* + * BTS + */ + +static struct event_constraint bts_constraint = + EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0); + +static void intel_pmu_enable_bts(u64 config) +{ + unsigned long debugctlmsr; + + debugctlmsr = get_debugctlmsr(); + + debugctlmsr |= DEBUGCTLMSR_TR; + debugctlmsr |= DEBUGCTLMSR_BTS; + debugctlmsr |= DEBUGCTLMSR_BTINT; + + if (!(config & ARCH_PERFMON_EVENTSEL_OS)) + debugctlmsr |= DEBUGCTLMSR_BTS_OFF_OS; + + if (!(config & ARCH_PERFMON_EVENTSEL_USR)) + debugctlmsr |= DEBUGCTLMSR_BTS_OFF_USR; + + update_debugctlmsr(debugctlmsr); +} + +static void intel_pmu_disable_bts(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + unsigned long debugctlmsr; + + if (!cpuc->ds) + return; + + debugctlmsr = get_debugctlmsr(); + + debugctlmsr &= + ~(DEBUGCTLMSR_TR | DEBUGCTLMSR_BTS | DEBUGCTLMSR_BTINT | + DEBUGCTLMSR_BTS_OFF_OS | DEBUGCTLMSR_BTS_OFF_USR); + + update_debugctlmsr(debugctlmsr); +} + +static void intel_pmu_drain_bts_buffer(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct debug_store *ds = cpuc->ds; + struct bts_record { + u64 from; + u64 to; + u64 flags; + }; + struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS]; + struct bts_record *at, *top; + struct perf_output_handle handle; + struct perf_event_header header; + struct perf_sample_data data; + struct pt_regs regs; + + if (!event) + return; + + if (!ds) + return; + + at = (struct bts_record *)(unsigned long)ds->bts_buffer_base; + top = (struct bts_record *)(unsigned long)ds->bts_index; + + if (top <= at) + return; + + ds->bts_index = ds->bts_buffer_base; + + perf_sample_data_init(&data, 0); + data.period = event->hw.last_period; + regs.ip = 0; + + /* + * Prepare a generic sample, i.e. fill in the invariant fields. + * We will overwrite the from and to address before we output + * the sample. + */ + perf_prepare_sample(&header, &data, event, ®s); + + if (perf_output_begin(&handle, event, header.size * (top - at), 1, 1)) + return; + + for (; at < top; at++) { + data.ip = at->from; + data.addr = at->to; + + perf_output_sample(&handle, &header, &data, event); + } + + perf_output_end(&handle); + + /* There's new data available. */ + event->hw.interrupts++; + event->pending_kill = POLL_IN; +} + +/* + * PEBS + */ + +static struct event_constraint intel_core_pebs_events[] = { + PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INSTR_RETIRED.ANY */ + PEBS_EVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */ + PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ + PEBS_EVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ + PEBS_EVENT_CONSTRAINT(0x01cb, 0x1), /* MEM_LOAD_RETIRED.L1D_MISS */ + PEBS_EVENT_CONSTRAINT(0x02cb, 0x1), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */ + PEBS_EVENT_CONSTRAINT(0x04cb, 0x1), /* MEM_LOAD_RETIRED.L2_MISS */ + PEBS_EVENT_CONSTRAINT(0x08cb, 0x1), /* MEM_LOAD_RETIRED.L2_LINE_MISS */ + PEBS_EVENT_CONSTRAINT(0x10cb, 0x1), /* MEM_LOAD_RETIRED.DTLB_MISS */ + EVENT_CONSTRAINT_END +}; + +static struct event_constraint intel_nehalem_pebs_events[] = { + PEBS_EVENT_CONSTRAINT(0x00c0, 0xf), /* INSTR_RETIRED.ANY */ + PEBS_EVENT_CONSTRAINT(0xfec1, 0xf), /* X87_OPS_RETIRED.ANY */ + PEBS_EVENT_CONSTRAINT(0x00c5, 0xf), /* BR_INST_RETIRED.MISPRED */ + PEBS_EVENT_CONSTRAINT(0x1fc7, 0xf), /* SIMD_INST_RETURED.ANY */ + PEBS_EVENT_CONSTRAINT(0x01cb, 0xf), /* MEM_LOAD_RETIRED.L1D_MISS */ + PEBS_EVENT_CONSTRAINT(0x02cb, 0xf), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */ + PEBS_EVENT_CONSTRAINT(0x04cb, 0xf), /* MEM_LOAD_RETIRED.L2_MISS */ + PEBS_EVENT_CONSTRAINT(0x08cb, 0xf), /* MEM_LOAD_RETIRED.L2_LINE_MISS */ + PEBS_EVENT_CONSTRAINT(0x10cb, 0xf), /* MEM_LOAD_RETIRED.DTLB_MISS */ + EVENT_CONSTRAINT_END +}; + +static struct event_constraint * +intel_pebs_constraints(struct perf_event *event) +{ + struct event_constraint *c; + + if (!event->attr.precise) + return NULL; + + if (x86_pmu.pebs_constraints) { + for_each_event_constraint(c, x86_pmu.pebs_constraints) { + if ((event->hw.config & c->cmask) == c->code) + return c; + } + } + + return &emptyconstraint; +} + +static void intel_pmu_pebs_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + + hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; + + cpuc->pebs_enabled |= 1ULL << hwc->idx; + WARN_ON_ONCE(cpuc->enabled); + + if (x86_pmu.intel_cap.pebs_trap) + intel_pmu_lbr_enable(event); +} + +static void intel_pmu_pebs_disable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + + cpuc->pebs_enabled &= ~(1ULL << hwc->idx); + if (cpuc->enabled) + wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); + + hwc->config |= ARCH_PERFMON_EVENTSEL_INT; + + if (x86_pmu.intel_cap.pebs_trap) + intel_pmu_lbr_disable(event); +} + +static void intel_pmu_pebs_enable_all(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (cpuc->pebs_enabled) + wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); +} + +static void intel_pmu_pebs_disable_all(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (cpuc->pebs_enabled) + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); +} + +#include <asm/insn.h> + +static inline bool kernel_ip(unsigned long ip) +{ +#ifdef CONFIG_X86_32 + return ip > PAGE_OFFSET; +#else + return (long)ip < 0; +#endif +} + +static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + unsigned long from = cpuc->lbr_entries[0].from; + unsigned long old_to, to = cpuc->lbr_entries[0].to; + unsigned long ip = regs->ip; + + /* + * We don't need to fixup if the PEBS assist is fault like + */ + if (!x86_pmu.intel_cap.pebs_trap) + return 1; + + /* + * No LBR entry, no basic block, no rewinding + */ + if (!cpuc->lbr_stack.nr || !from || !to) + return 0; + + /* + * Basic blocks should never cross user/kernel boundaries + */ + if (kernel_ip(ip) != kernel_ip(to)) + return 0; + + /* + * unsigned math, either ip is before the start (impossible) or + * the basic block is larger than 1 page (sanity) + */ + if ((ip - to) > PAGE_SIZE) + return 0; + + /* + * We sampled a branch insn, rewind using the LBR stack + */ + if (ip == to) { + regs->ip = from; + return 1; + } + + do { + struct insn insn; + u8 buf[MAX_INSN_SIZE]; + void *kaddr; + + old_to = to; + if (!kernel_ip(ip)) { + int bytes, size = MAX_INSN_SIZE; + + bytes = copy_from_user_nmi(buf, (void __user *)to, size); + if (bytes != size) + return 0; + + kaddr = buf; + } else + kaddr = (void *)to; + + kernel_insn_init(&insn, kaddr); + insn_get_length(&insn); + to += insn.length; + } while (to < ip); + + if (to == ip) { + regs->ip = old_to; + return 1; + } + + /* + * Even though we decoded the basic block, the instruction stream + * never matched the given IP, either the TO or the IP got corrupted. + */ + return 0; +} + +static int intel_pmu_save_and_restart(struct perf_event *event); + +static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct debug_store *ds = cpuc->ds; + struct perf_event *event = cpuc->events[0]; /* PMC0 only */ + struct pebs_record_core *at, *top; + struct perf_sample_data data; + struct perf_raw_record raw; + struct pt_regs regs; + int n; + + if (!ds || !x86_pmu.pebs) + return; + + at = (struct pebs_record_core *)(unsigned long)ds->pebs_buffer_base; + top = (struct pebs_record_core *)(unsigned long)ds->pebs_index; + + /* + * Whatever else happens, drain the thing + */ + ds->pebs_index = ds->pebs_buffer_base; + + if (!test_bit(0, cpuc->active_mask)) + return; + + WARN_ON_ONCE(!event); + + if (!event->attr.precise) + return; + + n = top - at; + if (n <= 0) + return; + + if (!intel_pmu_save_and_restart(event)) + return; + + /* + * Should not happen, we program the threshold at 1 and do not + * set a reset value. + */ + WARN_ON_ONCE(n > 1); + at += n - 1; + + perf_sample_data_init(&data, 0); + data.period = event->hw.last_period; + + if (event->attr.sample_type & PERF_SAMPLE_RAW) { + raw.size = x86_pmu.pebs_record_size; + raw.data = at; + data.raw = &raw; + } + + /* + * We use the interrupt regs as a base because the PEBS record + * does not contain a full regs set, specifically it seems to + * lack segment descriptors, which get used by things like + * user_mode(). + * + * In the simple case fix up only the IP and BP,SP regs, for + * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly. + * A possible PERF_SAMPLE_REGS will have to transfer all regs. + */ + regs = *iregs; + regs.ip = at->ip; + regs.bp = at->bp; + regs.sp = at->sp; + + if (intel_pmu_pebs_fixup_ip(®s)) + regs.flags |= PERF_EFLAGS_EXACT; + else + regs.flags &= ~PERF_EFLAGS_EXACT; + + if (perf_event_overflow(event, 1, &data, ®s)) + x86_pmu_stop(event); +} + +static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct debug_store *ds = cpuc->ds; + struct pebs_record_nhm *at, *top; + struct perf_sample_data data; + struct perf_event *event = NULL; + struct perf_raw_record raw; + struct pt_regs regs; + u64 status = 0; + int bit, n; + + if (!ds || !x86_pmu.pebs) + return; + + at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; + top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; + + ds->pebs_index = ds->pebs_buffer_base; + + n = top - at; + if (n <= 0) + return; + + /* + * Should not happen, we program the threshold at 1 and do not + * set a reset value. + */ + WARN_ON_ONCE(n > MAX_PEBS_EVENTS); + + for ( ; at < top; at++) { + for_each_set_bit(bit, (unsigned long *)&at->status, MAX_PEBS_EVENTS) { + event = cpuc->events[bit]; + if (!test_bit(bit, cpuc->active_mask)) + continue; + + WARN_ON_ONCE(!event); + + if (!event->attr.precise) + continue; + + if (__test_and_set_bit(bit, (unsigned long *)&status)) + continue; + + break; + } + + if (!event || bit >= MAX_PEBS_EVENTS) + continue; + + if (!intel_pmu_save_and_restart(event)) + continue; + + perf_sample_data_init(&data, 0); + data.period = event->hw.last_period; + + if (event->attr.sample_type & PERF_SAMPLE_RAW) { + raw.size = x86_pmu.pebs_record_size; + raw.data = at; + data.raw = &raw; + } + + /* + * See the comment in intel_pmu_drain_pebs_core() + */ + regs = *iregs; + regs.ip = at->ip; + regs.bp = at->bp; + regs.sp = at->sp; + + if (intel_pmu_pebs_fixup_ip(®s)) + regs.flags |= PERF_EFLAGS_EXACT; + else + regs.flags &= ~PERF_EFLAGS_EXACT; + + if (perf_event_overflow(event, 1, &data, ®s)) + x86_pmu_stop(event); + } +} + +/* + * BTS, PEBS probe and setup + */ + +static void intel_ds_init(void) +{ + /* + * No support for 32bit formats + */ + if (!boot_cpu_has(X86_FEATURE_DTES64)) + return; + + x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS); + x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS); + if (x86_pmu.pebs) { + char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-'; + int format = x86_pmu.intel_cap.pebs_format; + + switch (format) { + case 0: + printk(KERN_CONT "PEBS fmt0%c, ", pebs_type); + x86_pmu.pebs_record_size = sizeof(struct pebs_record_core); + x86_pmu.drain_pebs = intel_pmu_drain_pebs_core; + x86_pmu.pebs_constraints = intel_core_pebs_events; + break; + + case 1: + printk(KERN_CONT "PEBS fmt1%c, ", pebs_type); + x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm); + x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; + x86_pmu.pebs_constraints = intel_nehalem_pebs_events; + break; + + default: + printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type); + x86_pmu.pebs = 0; + break; + } + } +} + +#else /* CONFIG_CPU_SUP_INTEL */ + +static int reserve_ds_buffers(void) +{ + return 0; +} + +static void release_ds_buffers(void) +{ +} + +#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c new file mode 100644 index 000000000000..d202c1bece1a --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -0,0 +1,218 @@ +#ifdef CONFIG_CPU_SUP_INTEL + +enum { + LBR_FORMAT_32 = 0x00, + LBR_FORMAT_LIP = 0x01, + LBR_FORMAT_EIP = 0x02, + LBR_FORMAT_EIP_FLAGS = 0x03, +}; + +/* + * We only support LBR implementations that have FREEZE_LBRS_ON_PMI + * otherwise it becomes near impossible to get a reliable stack. + */ + +static void __intel_pmu_lbr_enable(void) +{ + u64 debugctl; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); +} + +static void __intel_pmu_lbr_disable(void) +{ + u64 debugctl; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); +} + +static void intel_pmu_lbr_reset_32(void) +{ + int i; + + for (i = 0; i < x86_pmu.lbr_nr; i++) + wrmsrl(x86_pmu.lbr_from + i, 0); +} + +static void intel_pmu_lbr_reset_64(void) +{ + int i; + + for (i = 0; i < x86_pmu.lbr_nr; i++) { + wrmsrl(x86_pmu.lbr_from + i, 0); + wrmsrl(x86_pmu.lbr_to + i, 0); + } +} + +static void intel_pmu_lbr_reset(void) +{ + if (!x86_pmu.lbr_nr) + return; + + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32) + intel_pmu_lbr_reset_32(); + else + intel_pmu_lbr_reset_64(); +} + +static void intel_pmu_lbr_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (!x86_pmu.lbr_nr) + return; + + WARN_ON_ONCE(cpuc->enabled); + + /* + * Reset the LBR stack if we changed task context to + * avoid data leaks. + */ + + if (event->ctx->task && cpuc->lbr_context != event->ctx) { + intel_pmu_lbr_reset(); + cpuc->lbr_context = event->ctx; + } + + cpuc->lbr_users++; +} + +static void intel_pmu_lbr_disable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (!x86_pmu.lbr_nr) + return; + + cpuc->lbr_users--; + WARN_ON_ONCE(cpuc->lbr_users < 0); + + if (cpuc->enabled && !cpuc->lbr_users) + __intel_pmu_lbr_disable(); +} + +static void intel_pmu_lbr_enable_all(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (cpuc->lbr_users) + __intel_pmu_lbr_enable(); +} + +static void intel_pmu_lbr_disable_all(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (cpuc->lbr_users) + __intel_pmu_lbr_disable(); +} + +static inline u64 intel_pmu_lbr_tos(void) +{ + u64 tos; + + rdmsrl(x86_pmu.lbr_tos, tos); + + return tos; +} + +static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) +{ + unsigned long mask = x86_pmu.lbr_nr - 1; + u64 tos = intel_pmu_lbr_tos(); + int i; + + for (i = 0; i < x86_pmu.lbr_nr; i++) { + unsigned long lbr_idx = (tos - i) & mask; + union { + struct { + u32 from; + u32 to; + }; + u64 lbr; + } msr_lastbranch; + + rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr); + + cpuc->lbr_entries[i].from = msr_lastbranch.from; + cpuc->lbr_entries[i].to = msr_lastbranch.to; + cpuc->lbr_entries[i].flags = 0; + } + cpuc->lbr_stack.nr = i; +} + +#define LBR_FROM_FLAG_MISPRED (1ULL << 63) + +/* + * Due to lack of segmentation in Linux the effective address (offset) + * is the same as the linear address, allowing us to merge the LIP and EIP + * LBR formats. + */ +static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) +{ + unsigned long mask = x86_pmu.lbr_nr - 1; + int lbr_format = x86_pmu.intel_cap.lbr_format; + u64 tos = intel_pmu_lbr_tos(); + int i; + + for (i = 0; i < x86_pmu.lbr_nr; i++) { + unsigned long lbr_idx = (tos - i) & mask; + u64 from, to, flags = 0; + + rdmsrl(x86_pmu.lbr_from + lbr_idx, from); + rdmsrl(x86_pmu.lbr_to + lbr_idx, to); + + if (lbr_format == LBR_FORMAT_EIP_FLAGS) { + flags = !!(from & LBR_FROM_FLAG_MISPRED); + from = (u64)((((s64)from) << 1) >> 1); + } + + cpuc->lbr_entries[i].from = from; + cpuc->lbr_entries[i].to = to; + cpuc->lbr_entries[i].flags = flags; + } + cpuc->lbr_stack.nr = i; +} + +static void intel_pmu_lbr_read(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (!cpuc->lbr_users) + return; + + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32) + intel_pmu_lbr_read_32(cpuc); + else + intel_pmu_lbr_read_64(cpuc); +} + +static void intel_pmu_lbr_init_core(void) +{ + x86_pmu.lbr_nr = 4; + x86_pmu.lbr_tos = 0x01c9; + x86_pmu.lbr_from = 0x40; + x86_pmu.lbr_to = 0x60; +} + +static void intel_pmu_lbr_init_nhm(void) +{ + x86_pmu.lbr_nr = 16; + x86_pmu.lbr_tos = 0x01c9; + x86_pmu.lbr_from = 0x680; + x86_pmu.lbr_to = 0x6c0; +} + +static void intel_pmu_lbr_init_atom(void) +{ + x86_pmu.lbr_nr = 8; + x86_pmu.lbr_tos = 0x01c9; + x86_pmu.lbr_from = 0x40; + x86_pmu.lbr_to = 0x60; +} + +#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c new file mode 100644 index 000000000000..15367cce66bd --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -0,0 +1,834 @@ +/* + * Netburst Perfomance Events (P4, old Xeon) + * + * Copyright (C) 2010 Parallels, Inc., Cyrill Gorcunov <gorcunov@openvz.org> + * Copyright (C) 2010 Intel Corporation, Lin Ming <ming.m.lin@intel.com> + * + * For licencing details see kernel-base/COPYING + */ + +#ifdef CONFIG_CPU_SUP_INTEL + +#include <asm/perf_event_p4.h> + +#define P4_CNTR_LIMIT 3 +/* + * array indices: 0,1 - HT threads, used with HT enabled cpu + */ +struct p4_event_bind { + unsigned int opcode; /* Event code and ESCR selector */ + unsigned int escr_msr[2]; /* ESCR MSR for this event */ + unsigned char cntr[2][P4_CNTR_LIMIT]; /* counter index (offset), -1 on abscence */ +}; + +struct p4_cache_event_bind { + unsigned int metric_pebs; + unsigned int metric_vert; +}; + +#define P4_GEN_CACHE_EVENT_BIND(name) \ + [P4_CACHE__##name] = { \ + .metric_pebs = P4_PEBS__##name, \ + .metric_vert = P4_VERT__##name, \ + } + +static struct p4_cache_event_bind p4_cache_event_bind_map[] = { + P4_GEN_CACHE_EVENT_BIND(1stl_cache_load_miss_retired), + P4_GEN_CACHE_EVENT_BIND(2ndl_cache_load_miss_retired), + P4_GEN_CACHE_EVENT_BIND(dtlb_load_miss_retired), + P4_GEN_CACHE_EVENT_BIND(dtlb_store_miss_retired), +}; + +/* + * Note that we don't use CCCR1 here, there is an + * exception for P4_BSQ_ALLOCATION but we just have + * no workaround + * + * consider this binding as resources which particular + * event may borrow, it doesn't contain EventMask, + * Tags and friends -- they are left to a caller + */ +static struct p4_event_bind p4_event_bind_map[] = { + [P4_EVENT_TC_DELIVER_MODE] = { + .opcode = P4_OPCODE(P4_EVENT_TC_DELIVER_MODE), + .escr_msr = { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 }, + .cntr = { {4, 5, -1}, {6, 7, -1} }, + }, + [P4_EVENT_BPU_FETCH_REQUEST] = { + .opcode = P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST), + .escr_msr = { MSR_P4_BPU_ESCR0, MSR_P4_BPU_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_ITLB_REFERENCE] = { + .opcode = P4_OPCODE(P4_EVENT_ITLB_REFERENCE), + .escr_msr = { MSR_P4_ITLB_ESCR0, MSR_P4_ITLB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_MEMORY_CANCEL] = { + .opcode = P4_OPCODE(P4_EVENT_MEMORY_CANCEL), + .escr_msr = { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_MEMORY_COMPLETE] = { + .opcode = P4_OPCODE(P4_EVENT_MEMORY_COMPLETE), + .escr_msr = { MSR_P4_SAAT_ESCR0 , MSR_P4_SAAT_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_LOAD_PORT_REPLAY] = { + .opcode = P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY), + .escr_msr = { MSR_P4_SAAT_ESCR0, MSR_P4_SAAT_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_STORE_PORT_REPLAY] = { + .opcode = P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY), + .escr_msr = { MSR_P4_SAAT_ESCR0 , MSR_P4_SAAT_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_MOB_LOAD_REPLAY] = { + .opcode = P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY), + .escr_msr = { MSR_P4_MOB_ESCR0, MSR_P4_MOB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_PAGE_WALK_TYPE] = { + .opcode = P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE), + .escr_msr = { MSR_P4_PMH_ESCR0, MSR_P4_PMH_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_BSQ_CACHE_REFERENCE] = { + .opcode = P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE), + .escr_msr = { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_IOQ_ALLOCATION] = { + .opcode = P4_OPCODE(P4_EVENT_IOQ_ALLOCATION), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_IOQ_ACTIVE_ENTRIES] = { /* shared ESCR */ + .opcode = P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES), + .escr_msr = { MSR_P4_FSB_ESCR1, MSR_P4_FSB_ESCR1 }, + .cntr = { {2, -1, -1}, {3, -1, -1} }, + }, + [P4_EVENT_FSB_DATA_ACTIVITY] = { + .opcode = P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_BSQ_ALLOCATION] = { /* shared ESCR, broken CCCR1 */ + .opcode = P4_OPCODE(P4_EVENT_BSQ_ALLOCATION), + .escr_msr = { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR0 }, + .cntr = { {0, -1, -1}, {1, -1, -1} }, + }, + [P4_EVENT_BSQ_ACTIVE_ENTRIES] = { /* shared ESCR */ + .opcode = P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES), + .escr_msr = { MSR_P4_BSU_ESCR1 , MSR_P4_BSU_ESCR1 }, + .cntr = { {2, -1, -1}, {3, -1, -1} }, + }, + [P4_EVENT_SSE_INPUT_ASSIST] = { + .opcode = P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_PACKED_SP_UOP] = { + .opcode = P4_OPCODE(P4_EVENT_PACKED_SP_UOP), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_PACKED_DP_UOP] = { + .opcode = P4_OPCODE(P4_EVENT_PACKED_DP_UOP), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_SCALAR_SP_UOP] = { + .opcode = P4_OPCODE(P4_EVENT_SCALAR_SP_UOP), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_SCALAR_DP_UOP] = { + .opcode = P4_OPCODE(P4_EVENT_SCALAR_DP_UOP), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_64BIT_MMX_UOP] = { + .opcode = P4_OPCODE(P4_EVENT_64BIT_MMX_UOP), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_128BIT_MMX_UOP] = { + .opcode = P4_OPCODE(P4_EVENT_128BIT_MMX_UOP), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_X87_FP_UOP] = { + .opcode = P4_OPCODE(P4_EVENT_X87_FP_UOP), + .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_TC_MISC] = { + .opcode = P4_OPCODE(P4_EVENT_TC_MISC), + .escr_msr = { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 }, + .cntr = { {4, 5, -1}, {6, 7, -1} }, + }, + [P4_EVENT_GLOBAL_POWER_EVENTS] = { + .opcode = P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_TC_MS_XFER] = { + .opcode = P4_OPCODE(P4_EVENT_TC_MS_XFER), + .escr_msr = { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 }, + .cntr = { {4, 5, -1}, {6, 7, -1} }, + }, + [P4_EVENT_UOP_QUEUE_WRITES] = { + .opcode = P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES), + .escr_msr = { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 }, + .cntr = { {4, 5, -1}, {6, 7, -1} }, + }, + [P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE] = { + .opcode = P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE), + .escr_msr = { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR0 }, + .cntr = { {4, 5, -1}, {6, 7, -1} }, + }, + [P4_EVENT_RETIRED_BRANCH_TYPE] = { + .opcode = P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE), + .escr_msr = { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR1 }, + .cntr = { {4, 5, -1}, {6, 7, -1} }, + }, + [P4_EVENT_RESOURCE_STALL] = { + .opcode = P4_OPCODE(P4_EVENT_RESOURCE_STALL), + .escr_msr = { MSR_P4_ALF_ESCR0, MSR_P4_ALF_ESCR1 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_WC_BUFFER] = { + .opcode = P4_OPCODE(P4_EVENT_WC_BUFFER), + .escr_msr = { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 }, + .cntr = { {8, 9, -1}, {10, 11, -1} }, + }, + [P4_EVENT_B2B_CYCLES] = { + .opcode = P4_OPCODE(P4_EVENT_B2B_CYCLES), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_BNR] = { + .opcode = P4_OPCODE(P4_EVENT_BNR), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_SNOOP] = { + .opcode = P4_OPCODE(P4_EVENT_SNOOP), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_RESPONSE] = { + .opcode = P4_OPCODE(P4_EVENT_RESPONSE), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { {0, -1, -1}, {2, -1, -1} }, + }, + [P4_EVENT_FRONT_END_EVENT] = { + .opcode = P4_OPCODE(P4_EVENT_FRONT_END_EVENT), + .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_EXECUTION_EVENT] = { + .opcode = P4_OPCODE(P4_EVENT_EXECUTION_EVENT), + .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_REPLAY_EVENT] = { + .opcode = P4_OPCODE(P4_EVENT_REPLAY_EVENT), + .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_INSTR_RETIRED] = { + .opcode = P4_OPCODE(P4_EVENT_INSTR_RETIRED), + .escr_msr = { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_UOPS_RETIRED] = { + .opcode = P4_OPCODE(P4_EVENT_UOPS_RETIRED), + .escr_msr = { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_UOP_TYPE] = { + .opcode = P4_OPCODE(P4_EVENT_UOP_TYPE), + .escr_msr = { MSR_P4_RAT_ESCR0, MSR_P4_RAT_ESCR1 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_BRANCH_RETIRED] = { + .opcode = P4_OPCODE(P4_EVENT_BRANCH_RETIRED), + .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_MISPRED_BRANCH_RETIRED] = { + .opcode = P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED), + .escr_msr = { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_X87_ASSIST] = { + .opcode = P4_OPCODE(P4_EVENT_X87_ASSIST), + .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_MACHINE_CLEAR] = { + .opcode = P4_OPCODE(P4_EVENT_MACHINE_CLEAR), + .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, + [P4_EVENT_INSTR_COMPLETED] = { + .opcode = P4_OPCODE(P4_EVENT_INSTR_COMPLETED), + .escr_msr = { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 }, + .cntr = { {12, 13, 16}, {14, 15, 17} }, + }, +}; + +#define P4_GEN_CACHE_EVENT(event, bit, cache_event) \ + p4_config_pack_escr(P4_ESCR_EVENT(event) | \ + P4_ESCR_EMASK_BIT(event, bit)) | \ + p4_config_pack_cccr(cache_event | \ + P4_CCCR_ESEL(P4_OPCODE_ESEL(P4_OPCODE(event)))) + +static __initconst const u64 p4_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, + P4_CACHE__1stl_cache_load_miss_retired), + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, + P4_CACHE__2ndl_cache_load_miss_retired), + }, +}, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, + P4_CACHE__dtlb_load_miss_retired), + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, + P4_CACHE__dtlb_store_miss_retired), + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, HIT, + P4_CACHE__itlb_reference_hit), + [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, MISS, + P4_CACHE__itlb_reference_miss), + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + +static u64 p4_general_events[PERF_COUNT_HW_MAX] = { + /* non-halted CPU clocks */ + [PERF_COUNT_HW_CPU_CYCLES] = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_GLOBAL_POWER_EVENTS) | + P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING)), + + /* + * retired instructions + * in a sake of simplicity we don't use the FSB tagging + */ + [PERF_COUNT_HW_INSTRUCTIONS] = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_INSTR_RETIRED) | + P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG) | + P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, BOGUSNTAG)), + + /* cache hits */ + [PERF_COUNT_HW_CACHE_REFERENCES] = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_BSQ_CACHE_REFERENCE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM)), + + /* cache misses */ + [PERF_COUNT_HW_CACHE_MISSES] = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_BSQ_CACHE_REFERENCE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS)), + + /* branch instructions retired */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_RETIRED_BRANCH_TYPE) | + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL) | + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CALL) | + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN) | + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT)), + + /* mispredicted branches retired */ + [PERF_COUNT_HW_BRANCH_MISSES] = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_MISPRED_BRANCH_RETIRED) | + P4_ESCR_EMASK_BIT(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS)), + + /* bus ready clocks (cpu is driving #DRDY_DRV\#DRDY_OWN): */ + [PERF_COUNT_HW_BUS_CYCLES] = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_FSB_DATA_ACTIVITY) | + P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV) | + P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN)) | + p4_config_pack_cccr(P4_CCCR_EDGE | P4_CCCR_COMPARE), +}; + +static struct p4_event_bind *p4_config_get_bind(u64 config) +{ + unsigned int evnt = p4_config_unpack_event(config); + struct p4_event_bind *bind = NULL; + + if (evnt < ARRAY_SIZE(p4_event_bind_map)) + bind = &p4_event_bind_map[evnt]; + + return bind; +} + +static u64 p4_pmu_event_map(int hw_event) +{ + struct p4_event_bind *bind; + unsigned int esel; + u64 config; + + if (hw_event > ARRAY_SIZE(p4_general_events)) { + printk_once(KERN_ERR "P4 PMU: Bad index: %i\n", hw_event); + return 0; + } + + config = p4_general_events[hw_event]; + bind = p4_config_get_bind(config); + esel = P4_OPCODE_ESEL(bind->opcode); + config |= p4_config_pack_cccr(P4_CCCR_ESEL(esel)); + + return config; +} + +static int p4_hw_config(struct perf_event *event) +{ + int cpu = raw_smp_processor_id(); + u32 escr, cccr; + + /* + * the reason we use cpu that early is that: if we get scheduled + * first time on the same cpu -- we will not need swap thread + * specific flags in config (and will save some cpu cycles) + */ + + cccr = p4_default_cccr_conf(cpu); + escr = p4_default_escr_conf(cpu, event->attr.exclude_kernel, + event->attr.exclude_user); + event->hw.config = p4_config_pack_escr(escr) | + p4_config_pack_cccr(cccr); + + if (p4_ht_active() && p4_ht_thread(cpu)) + event->hw.config = p4_set_ht_bit(event->hw.config); + + if (event->attr.type != PERF_TYPE_RAW) + return 0; + + /* + * We don't control raw events so it's up to the caller + * to pass sane values (and we don't count the thread number + * on HT machine but allow HT-compatible specifics to be + * passed on) + * + * XXX: HT wide things should check perf_paranoid_cpu() && + * CAP_SYS_ADMIN + */ + event->hw.config |= event->attr.config & + (p4_config_pack_escr(P4_ESCR_MASK_HT) | + p4_config_pack_cccr(P4_CCCR_MASK_HT)); + + return 0; +} + +static inline void p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc) +{ + unsigned long dummy; + + rdmsrl(hwc->config_base + hwc->idx, dummy); + if (dummy & P4_CCCR_OVF) { + (void)checking_wrmsrl(hwc->config_base + hwc->idx, + ((u64)dummy) & ~P4_CCCR_OVF); + } +} + +static inline void p4_pmu_disable_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + /* + * If event gets disabled while counter is in overflowed + * state we need to clear P4_CCCR_OVF, otherwise interrupt get + * asserted again and again + */ + (void)checking_wrmsrl(hwc->config_base + hwc->idx, + (u64)(p4_config_unpack_cccr(hwc->config)) & + ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED); +} + +static void p4_pmu_disable_all(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int idx; + + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + struct perf_event *event = cpuc->events[idx]; + if (!test_bit(idx, cpuc->active_mask)) + continue; + p4_pmu_disable_event(event); + } +} + +static void p4_pmu_enable_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + int thread = p4_ht_config_thread(hwc->config); + u64 escr_conf = p4_config_unpack_escr(p4_clear_ht_bit(hwc->config)); + unsigned int idx = p4_config_unpack_event(hwc->config); + unsigned int idx_cache = p4_config_unpack_cache_event(hwc->config); + struct p4_event_bind *bind; + struct p4_cache_event_bind *bind_cache; + u64 escr_addr, cccr; + + bind = &p4_event_bind_map[idx]; + escr_addr = (u64)bind->escr_msr[thread]; + + /* + * - we dont support cascaded counters yet + * - and counter 1 is broken (erratum) + */ + WARN_ON_ONCE(p4_is_event_cascaded(hwc->config)); + WARN_ON_ONCE(hwc->idx == 1); + + /* we need a real Event value */ + escr_conf &= ~P4_ESCR_EVENT_MASK; + escr_conf |= P4_ESCR_EVENT(P4_OPCODE_EVNT(bind->opcode)); + + cccr = p4_config_unpack_cccr(hwc->config); + + /* + * it could be Cache event so that we need to + * set metrics into additional MSRs + */ + BUILD_BUG_ON(P4_CACHE__MAX > P4_CCCR_CACHE_OPS_MASK); + if (idx_cache > P4_CACHE__NONE && + idx_cache < ARRAY_SIZE(p4_cache_event_bind_map)) { + bind_cache = &p4_cache_event_bind_map[idx_cache]; + (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)bind_cache->metric_pebs); + (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)bind_cache->metric_vert); + } + + (void)checking_wrmsrl(escr_addr, escr_conf); + (void)checking_wrmsrl(hwc->config_base + hwc->idx, + (cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE); +} + +static void p4_pmu_enable_all(int added) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int idx; + + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + struct perf_event *event = cpuc->events[idx]; + if (!test_bit(idx, cpuc->active_mask)) + continue; + p4_pmu_enable_event(event); + } +} + +static int p4_pmu_handle_irq(struct pt_regs *regs) +{ + struct perf_sample_data data; + struct cpu_hw_events *cpuc; + struct perf_event *event; + struct hw_perf_event *hwc; + int idx, handled = 0; + u64 val; + + data.addr = 0; + data.raw = NULL; + + cpuc = &__get_cpu_var(cpu_hw_events); + + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + + if (!test_bit(idx, cpuc->active_mask)) + continue; + + event = cpuc->events[idx]; + hwc = &event->hw; + + WARN_ON_ONCE(hwc->idx != idx); + + /* + * FIXME: Redundant call, actually not needed + * but just to check if we're screwed + */ + p4_pmu_clear_cccr_ovf(hwc); + + val = x86_perf_event_update(event); + if (val & (1ULL << (x86_pmu.cntval_bits - 1))) + continue; + + /* + * event overflow + */ + handled = 1; + data.period = event->hw.last_period; + + if (!x86_perf_event_set_period(event)) + continue; + if (perf_event_overflow(event, 1, &data, regs)) + p4_pmu_disable_event(event); + } + + if (handled) { + /* p4 quirk: unmask it again */ + apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED); + inc_irq_stat(apic_perf_irqs); + } + + return handled; +} + +/* + * swap thread specific fields according to a thread + * we are going to run on + */ +static void p4_pmu_swap_config_ts(struct hw_perf_event *hwc, int cpu) +{ + u32 escr, cccr; + + /* + * we either lucky and continue on same cpu or no HT support + */ + if (!p4_should_swap_ts(hwc->config, cpu)) + return; + + /* + * the event is migrated from an another logical + * cpu, so we need to swap thread specific flags + */ + + escr = p4_config_unpack_escr(hwc->config); + cccr = p4_config_unpack_cccr(hwc->config); + + if (p4_ht_thread(cpu)) { + cccr &= ~P4_CCCR_OVF_PMI_T0; + cccr |= P4_CCCR_OVF_PMI_T1; + if (escr & P4_ESCR_T0_OS) { + escr &= ~P4_ESCR_T0_OS; + escr |= P4_ESCR_T1_OS; + } + if (escr & P4_ESCR_T0_USR) { + escr &= ~P4_ESCR_T0_USR; + escr |= P4_ESCR_T1_USR; + } + hwc->config = p4_config_pack_escr(escr); + hwc->config |= p4_config_pack_cccr(cccr); + hwc->config |= P4_CONFIG_HT; + } else { + cccr &= ~P4_CCCR_OVF_PMI_T1; + cccr |= P4_CCCR_OVF_PMI_T0; + if (escr & P4_ESCR_T1_OS) { + escr &= ~P4_ESCR_T1_OS; + escr |= P4_ESCR_T0_OS; + } + if (escr & P4_ESCR_T1_USR) { + escr &= ~P4_ESCR_T1_USR; + escr |= P4_ESCR_T0_USR; + } + hwc->config = p4_config_pack_escr(escr); + hwc->config |= p4_config_pack_cccr(cccr); + hwc->config &= ~P4_CONFIG_HT; + } +} + +/* ESCRs are not sequential in memory so we need a map */ +static const unsigned int p4_escr_map[ARCH_P4_TOTAL_ESCR] = { + MSR_P4_ALF_ESCR0, /* 0 */ + MSR_P4_ALF_ESCR1, /* 1 */ + MSR_P4_BPU_ESCR0, /* 2 */ + MSR_P4_BPU_ESCR1, /* 3 */ + MSR_P4_BSU_ESCR0, /* 4 */ + MSR_P4_BSU_ESCR1, /* 5 */ + MSR_P4_CRU_ESCR0, /* 6 */ + MSR_P4_CRU_ESCR1, /* 7 */ + MSR_P4_CRU_ESCR2, /* 8 */ + MSR_P4_CRU_ESCR3, /* 9 */ + MSR_P4_CRU_ESCR4, /* 10 */ + MSR_P4_CRU_ESCR5, /* 11 */ + MSR_P4_DAC_ESCR0, /* 12 */ + MSR_P4_DAC_ESCR1, /* 13 */ + MSR_P4_FIRM_ESCR0, /* 14 */ + MSR_P4_FIRM_ESCR1, /* 15 */ + MSR_P4_FLAME_ESCR0, /* 16 */ + MSR_P4_FLAME_ESCR1, /* 17 */ + MSR_P4_FSB_ESCR0, /* 18 */ + MSR_P4_FSB_ESCR1, /* 19 */ + MSR_P4_IQ_ESCR0, /* 20 */ + MSR_P4_IQ_ESCR1, /* 21 */ + MSR_P4_IS_ESCR0, /* 22 */ + MSR_P4_IS_ESCR1, /* 23 */ + MSR_P4_ITLB_ESCR0, /* 24 */ + MSR_P4_ITLB_ESCR1, /* 25 */ + MSR_P4_IX_ESCR0, /* 26 */ + MSR_P4_IX_ESCR1, /* 27 */ + MSR_P4_MOB_ESCR0, /* 28 */ + MSR_P4_MOB_ESCR1, /* 29 */ + MSR_P4_MS_ESCR0, /* 30 */ + MSR_P4_MS_ESCR1, /* 31 */ + MSR_P4_PMH_ESCR0, /* 32 */ + MSR_P4_PMH_ESCR1, /* 33 */ + MSR_P4_RAT_ESCR0, /* 34 */ + MSR_P4_RAT_ESCR1, /* 35 */ + MSR_P4_SAAT_ESCR0, /* 36 */ + MSR_P4_SAAT_ESCR1, /* 37 */ + MSR_P4_SSU_ESCR0, /* 38 */ + MSR_P4_SSU_ESCR1, /* 39 */ + MSR_P4_TBPU_ESCR0, /* 40 */ + MSR_P4_TBPU_ESCR1, /* 41 */ + MSR_P4_TC_ESCR0, /* 42 */ + MSR_P4_TC_ESCR1, /* 43 */ + MSR_P4_U2L_ESCR0, /* 44 */ + MSR_P4_U2L_ESCR1, /* 45 */ +}; + +static int p4_get_escr_idx(unsigned int addr) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(p4_escr_map); i++) { + if (addr == p4_escr_map[i]) + return i; + } + + return -1; +} + +static int p4_next_cntr(int thread, unsigned long *used_mask, + struct p4_event_bind *bind) +{ + int i = 0, j; + + for (i = 0; i < P4_CNTR_LIMIT; i++) { + j = bind->cntr[thread][i++]; + if (j == -1 || !test_bit(j, used_mask)) + return j; + } + + return -1; +} + +static int p4_pmu_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) +{ + unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + unsigned long escr_mask[BITS_TO_LONGS(ARCH_P4_TOTAL_ESCR)]; + int cpu = raw_smp_processor_id(); + struct hw_perf_event *hwc; + struct p4_event_bind *bind; + unsigned int i, thread, num; + int cntr_idx, escr_idx; + + bitmap_zero(used_mask, X86_PMC_IDX_MAX); + bitmap_zero(escr_mask, ARCH_P4_TOTAL_ESCR); + + for (i = 0, num = n; i < n; i++, num--) { + + hwc = &cpuc->event_list[i]->hw; + thread = p4_ht_thread(cpu); + bind = p4_config_get_bind(hwc->config); + escr_idx = p4_get_escr_idx(bind->escr_msr[thread]); + + if (hwc->idx != -1 && !p4_should_swap_ts(hwc->config, cpu)) { + cntr_idx = hwc->idx; + if (assign) + assign[i] = hwc->idx; + goto reserve; + } + + cntr_idx = p4_next_cntr(thread, used_mask, bind); + if (cntr_idx == -1 || test_bit(escr_idx, escr_mask)) + goto done; + + p4_pmu_swap_config_ts(hwc, cpu); + if (assign) + assign[i] = cntr_idx; +reserve: + set_bit(cntr_idx, used_mask); + set_bit(escr_idx, escr_mask); + } + +done: + return num ? -ENOSPC : 0; +} + +static __initconst const struct x86_pmu p4_pmu = { + .name = "Netburst P4/Xeon", + .handle_irq = p4_pmu_handle_irq, + .disable_all = p4_pmu_disable_all, + .enable_all = p4_pmu_enable_all, + .enable = p4_pmu_enable_event, + .disable = p4_pmu_disable_event, + .eventsel = MSR_P4_BPU_CCCR0, + .perfctr = MSR_P4_BPU_PERFCTR0, + .event_map = p4_pmu_event_map, + .max_events = ARRAY_SIZE(p4_general_events), + .get_event_constraints = x86_get_event_constraints, + /* + * IF HT disabled we may need to use all + * ARCH_P4_MAX_CCCR counters simulaneously + * though leave it restricted at moment assuming + * HT is on + */ + .num_counters = ARCH_P4_MAX_CCCR, + .apic = 1, + .cntval_bits = 40, + .cntval_mask = (1ULL << 40) - 1, + .max_period = (1ULL << 39) - 1, + .hw_config = p4_hw_config, + .schedule_events = p4_pmu_schedule_events, +}; + +static __init int p4_pmu_init(void) +{ + unsigned int low, high; + + /* If we get stripped -- indexig fails */ + BUILD_BUG_ON(ARCH_P4_MAX_CCCR > X86_PMC_MAX_GENERIC); + + rdmsr(MSR_IA32_MISC_ENABLE, low, high); + if (!(low & (1 << 7))) { + pr_cont("unsupported Netburst CPU model %d ", + boot_cpu_data.x86_model); + return -ENODEV; + } + + memcpy(hw_cache_event_ids, p4_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + + pr_cont("Netburst events, "); + + x86_pmu = p4_pmu; + + return 0; +} + +#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index a330485d14da..34ba07be2cda 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -27,24 +27,6 @@ static u64 p6_pmu_event_map(int hw_event) */ #define P6_NOP_EVENT 0x0000002EULL -static u64 p6_pmu_raw_event(u64 hw_event) -{ -#define P6_EVNTSEL_EVENT_MASK 0x000000FFULL -#define P6_EVNTSEL_UNIT_MASK 0x0000FF00ULL -#define P6_EVNTSEL_EDGE_MASK 0x00040000ULL -#define P6_EVNTSEL_INV_MASK 0x00800000ULL -#define P6_EVNTSEL_REG_MASK 0xFF000000ULL - -#define P6_EVNTSEL_MASK \ - (P6_EVNTSEL_EVENT_MASK | \ - P6_EVNTSEL_UNIT_MASK | \ - P6_EVNTSEL_EDGE_MASK | \ - P6_EVNTSEL_INV_MASK | \ - P6_EVNTSEL_REG_MASK) - - return hw_event & P6_EVNTSEL_MASK; -} - static struct event_constraint p6_event_constraints[] = { INTEL_EVENT_CONSTRAINT(0xc1, 0x1), /* FLOPS */ @@ -66,7 +48,7 @@ static void p6_pmu_disable_all(void) wrmsrl(MSR_P6_EVNTSEL0, val); } -static void p6_pmu_enable_all(void) +static void p6_pmu_enable_all(int added) { unsigned long val; @@ -102,22 +84,23 @@ static void p6_pmu_enable_event(struct perf_event *event) (void)checking_wrmsrl(hwc->config_base + hwc->idx, val); } -static __initconst struct x86_pmu p6_pmu = { +static __initconst const struct x86_pmu p6_pmu = { .name = "p6", .handle_irq = x86_pmu_handle_irq, .disable_all = p6_pmu_disable_all, .enable_all = p6_pmu_enable_all, .enable = p6_pmu_enable_event, .disable = p6_pmu_disable_event, + .hw_config = x86_pmu_hw_config, + .schedule_events = x86_schedule_events, .eventsel = MSR_P6_EVNTSEL0, .perfctr = MSR_P6_PERFCTR0, .event_map = p6_pmu_event_map, - .raw_event = p6_pmu_raw_event, .max_events = ARRAY_SIZE(p6_perfmon_event_map), .apic = 1, .max_period = (1ULL << 31) - 1, .version = 0, - .num_events = 2, + .num_counters = 2, /* * Events have 40 bits implemented. However they are designed such * that bits [32-39] are sign extensions of bit 31. As such the @@ -125,8 +108,8 @@ static __initconst struct x86_pmu p6_pmu = { * * See IA-32 Intel Architecture Software developer manual Vol 3B */ - .event_bits = 32, - .event_mask = (1ULL << 32) - 1, + .cntval_bits = 32, + .cntval_mask = (1ULL << 32) - 1, .get_event_constraints = x86_get_event_constraints, .event_constraints = p6_event_constraints, }; diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c deleted file mode 100644 index 1c47390dd0e5..000000000000 --- a/arch/x86/kernel/ds.c +++ /dev/null @@ -1,1437 +0,0 @@ -/* - * Debug Store support - * - * This provides a low-level interface to the hardware's Debug Store - * feature that is used for branch trace store (BTS) and - * precise-event based sampling (PEBS). - * - * It manages: - * - DS and BTS hardware configuration - * - buffer overflow handling (to be done) - * - buffer access - * - * It does not do: - * - security checking (is the caller allowed to trace the task) - * - buffer allocation (memory accounting) - * - * - * Copyright (C) 2007-2009 Intel Corporation. - * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009 - */ - -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/mm.h> -#include <linux/trace_clock.h> - -#include <asm/ds.h> - -#include "ds_selftest.h" - -/* - * The configuration for a particular DS hardware implementation: - */ -struct ds_configuration { - /* The name of the configuration: */ - const char *name; - - /* The size of pointer-typed fields in DS, BTS, and PEBS: */ - unsigned char sizeof_ptr_field; - - /* The size of a BTS/PEBS record in bytes: */ - unsigned char sizeof_rec[2]; - - /* The number of pebs counter reset values in the DS structure. */ - unsigned char nr_counter_reset; - - /* Control bit-masks indexed by enum ds_feature: */ - unsigned long ctl[dsf_ctl_max]; -}; -static struct ds_configuration ds_cfg __read_mostly; - - -/* Maximal size of a DS configuration: */ -#define MAX_SIZEOF_DS 0x80 - -/* Maximal size of a BTS record: */ -#define MAX_SIZEOF_BTS (3 * 8) - -/* BTS and PEBS buffer alignment: */ -#define DS_ALIGNMENT (1 << 3) - -/* Number of buffer pointers in DS: */ -#define NUM_DS_PTR_FIELDS 8 - -/* Size of a pebs reset value in DS: */ -#define PEBS_RESET_FIELD_SIZE 8 - -/* Mask of control bits in the DS MSR register: */ -#define BTS_CONTROL \ - ( ds_cfg.ctl[dsf_bts] | \ - ds_cfg.ctl[dsf_bts_kernel] | \ - ds_cfg.ctl[dsf_bts_user] | \ - ds_cfg.ctl[dsf_bts_overflow] ) - -/* - * A BTS or PEBS tracer. - * - * This holds the configuration of the tracer and serves as a handle - * to identify tracers. - */ -struct ds_tracer { - /* The DS context (partially) owned by this tracer. */ - struct ds_context *context; - /* The buffer provided on ds_request() and its size in bytes. */ - void *buffer; - size_t size; -}; - -struct bts_tracer { - /* The common DS part: */ - struct ds_tracer ds; - - /* The trace including the DS configuration: */ - struct bts_trace trace; - - /* Buffer overflow notification function: */ - bts_ovfl_callback_t ovfl; - - /* Active flags affecting trace collection. */ - unsigned int flags; -}; - -struct pebs_tracer { - /* The common DS part: */ - struct ds_tracer ds; - - /* The trace including the DS configuration: */ - struct pebs_trace trace; - - /* Buffer overflow notification function: */ - pebs_ovfl_callback_t ovfl; -}; - -/* - * Debug Store (DS) save area configuration (see Intel64 and IA32 - * Architectures Software Developer's Manual, section 18.5) - * - * The DS configuration consists of the following fields; different - * architetures vary in the size of those fields. - * - * - double-word aligned base linear address of the BTS buffer - * - write pointer into the BTS buffer - * - end linear address of the BTS buffer (one byte beyond the end of - * the buffer) - * - interrupt pointer into BTS buffer - * (interrupt occurs when write pointer passes interrupt pointer) - * - double-word aligned base linear address of the PEBS buffer - * - write pointer into the PEBS buffer - * - end linear address of the PEBS buffer (one byte beyond the end of - * the buffer) - * - interrupt pointer into PEBS buffer - * (interrupt occurs when write pointer passes interrupt pointer) - * - value to which counter is reset following counter overflow - * - * Later architectures use 64bit pointers throughout, whereas earlier - * architectures use 32bit pointers in 32bit mode. - * - * - * We compute the base address for the first 8 fields based on: - * - the field size stored in the DS configuration - * - the relative field position - * - an offset giving the start of the respective region - * - * This offset is further used to index various arrays holding - * information for BTS and PEBS at the respective index. - * - * On later 32bit processors, we only access the lower 32bit of the - * 64bit pointer fields. The upper halves will be zeroed out. - */ - -enum ds_field { - ds_buffer_base = 0, - ds_index, - ds_absolute_maximum, - ds_interrupt_threshold, -}; - -enum ds_qualifier { - ds_bts = 0, - ds_pebs -}; - -static inline unsigned long -ds_get(const unsigned char *base, enum ds_qualifier qual, enum ds_field field) -{ - base += (ds_cfg.sizeof_ptr_field * (field + (4 * qual))); - return *(unsigned long *)base; -} - -static inline void -ds_set(unsigned char *base, enum ds_qualifier qual, enum ds_field field, - unsigned long value) -{ - base += (ds_cfg.sizeof_ptr_field * (field + (4 * qual))); - (*(unsigned long *)base) = value; -} - - -/* - * Locking is done only for allocating BTS or PEBS resources. - */ -static DEFINE_SPINLOCK(ds_lock); - -/* - * We either support (system-wide) per-cpu or per-thread allocation. - * We distinguish the two based on the task_struct pointer, where a - * NULL pointer indicates per-cpu allocation for the current cpu. - * - * Allocations are use-counted. As soon as resources are allocated, - * further allocations must be of the same type (per-cpu or - * per-thread). We model this by counting allocations (i.e. the number - * of tracers of a certain type) for one type negatively: - * =0 no tracers - * >0 number of per-thread tracers - * <0 number of per-cpu tracers - * - * Tracers essentially gives the number of ds contexts for a certain - * type of allocation. - */ -static atomic_t tracers = ATOMIC_INIT(0); - -static inline int get_tracer(struct task_struct *task) -{ - int error; - - spin_lock_irq(&ds_lock); - - if (task) { - error = -EPERM; - if (atomic_read(&tracers) < 0) - goto out; - atomic_inc(&tracers); - } else { - error = -EPERM; - if (atomic_read(&tracers) > 0) - goto out; - atomic_dec(&tracers); - } - - error = 0; -out: - spin_unlock_irq(&ds_lock); - return error; -} - -static inline void put_tracer(struct task_struct *task) -{ - if (task) - atomic_dec(&tracers); - else - atomic_inc(&tracers); -} - -/* - * The DS context is either attached to a thread or to a cpu: - * - in the former case, the thread_struct contains a pointer to the - * attached context. - * - in the latter case, we use a static array of per-cpu context - * pointers. - * - * Contexts are use-counted. They are allocated on first access and - * deallocated when the last user puts the context. - */ -struct ds_context { - /* The DS configuration; goes into MSR_IA32_DS_AREA: */ - unsigned char ds[MAX_SIZEOF_DS]; - - /* The owner of the BTS and PEBS configuration, respectively: */ - struct bts_tracer *bts_master; - struct pebs_tracer *pebs_master; - - /* Use count: */ - unsigned long count; - - /* Pointer to the context pointer field: */ - struct ds_context **this; - - /* The traced task; NULL for cpu tracing: */ - struct task_struct *task; - - /* The traced cpu; only valid if task is NULL: */ - int cpu; -}; - -static DEFINE_PER_CPU(struct ds_context *, cpu_ds_context); - - -static struct ds_context *ds_get_context(struct task_struct *task, int cpu) -{ - struct ds_context **p_context = - (task ? &task->thread.ds_ctx : &per_cpu(cpu_ds_context, cpu)); - struct ds_context *context = NULL; - struct ds_context *new_context = NULL; - - /* Chances are small that we already have a context. */ - new_context = kzalloc(sizeof(*new_context), GFP_KERNEL); - if (!new_context) - return NULL; - - spin_lock_irq(&ds_lock); - - context = *p_context; - if (likely(!context)) { - context = new_context; - - context->this = p_context; - context->task = task; - context->cpu = cpu; - context->count = 0; - - *p_context = context; - } - - context->count++; - - spin_unlock_irq(&ds_lock); - - if (context != new_context) - kfree(new_context); - - return context; -} - -static void ds_put_context(struct ds_context *context) -{ - struct task_struct *task; - unsigned long irq; - - if (!context) - return; - - spin_lock_irqsave(&ds_lock, irq); - - if (--context->count) { - spin_unlock_irqrestore(&ds_lock, irq); - return; - } - - *(context->this) = NULL; - - task = context->task; - - if (task) - clear_tsk_thread_flag(task, TIF_DS_AREA_MSR); - - /* - * We leave the (now dangling) pointer to the DS configuration in - * the DS_AREA msr. This is as good or as bad as replacing it with - * NULL - the hardware would crash if we enabled tracing. - * - * This saves us some problems with having to write an msr on a - * different cpu while preventing others from doing the same for the - * next context for that same cpu. - */ - - spin_unlock_irqrestore(&ds_lock, irq); - - /* The context might still be in use for context switching. */ - if (task && (task != current)) - wait_task_context_switch(task); - - kfree(context); -} - -static void ds_install_ds_area(struct ds_context *context) -{ - unsigned long ds; - - ds = (unsigned long)context->ds; - - /* - * There is a race between the bts master and the pebs master. - * - * The thread/cpu access is synchronized via get/put_cpu() for - * task tracing and via wrmsr_on_cpu for cpu tracing. - * - * If bts and pebs are collected for the same task or same cpu, - * the same confiuration is written twice. - */ - if (context->task) { - get_cpu(); - if (context->task == current) - wrmsrl(MSR_IA32_DS_AREA, ds); - set_tsk_thread_flag(context->task, TIF_DS_AREA_MSR); - put_cpu(); - } else - wrmsr_on_cpu(context->cpu, MSR_IA32_DS_AREA, - (u32)((u64)ds), (u32)((u64)ds >> 32)); -} - -/* - * Call the tracer's callback on a buffer overflow. - * - * context: the ds context - * qual: the buffer type - */ -static void ds_overflow(struct ds_context *context, enum ds_qualifier qual) -{ - switch (qual) { - case ds_bts: - if (context->bts_master && - context->bts_master->ovfl) - context->bts_master->ovfl(context->bts_master); - break; - case ds_pebs: - if (context->pebs_master && - context->pebs_master->ovfl) - context->pebs_master->ovfl(context->pebs_master); - break; - } -} - - -/* - * Write raw data into the BTS or PEBS buffer. - * - * The remainder of any partially written record is zeroed out. - * - * context: the DS context - * qual: the buffer type - * record: the data to write - * size: the size of the data - */ -static int ds_write(struct ds_context *context, enum ds_qualifier qual, - const void *record, size_t size) -{ - int bytes_written = 0; - - if (!record) - return -EINVAL; - - while (size) { - unsigned long base, index, end, write_end, int_th; - unsigned long write_size, adj_write_size; - - /* - * Write as much as possible without producing an - * overflow interrupt. - * - * Interrupt_threshold must either be - * - bigger than absolute_maximum or - * - point to a record between buffer_base and absolute_maximum - * - * Index points to a valid record. - */ - base = ds_get(context->ds, qual, ds_buffer_base); - index = ds_get(context->ds, qual, ds_index); - end = ds_get(context->ds, qual, ds_absolute_maximum); - int_th = ds_get(context->ds, qual, ds_interrupt_threshold); - - write_end = min(end, int_th); - - /* - * If we are already beyond the interrupt threshold, - * we fill the entire buffer. - */ - if (write_end <= index) - write_end = end; - - if (write_end <= index) - break; - - write_size = min((unsigned long) size, write_end - index); - memcpy((void *)index, record, write_size); - - record = (const char *)record + write_size; - size -= write_size; - bytes_written += write_size; - - adj_write_size = write_size / ds_cfg.sizeof_rec[qual]; - adj_write_size *= ds_cfg.sizeof_rec[qual]; - - /* Zero out trailing bytes. */ - memset((char *)index + write_size, 0, - adj_write_size - write_size); - index += adj_write_size; - - if (index >= end) - index = base; - ds_set(context->ds, qual, ds_index, index); - - if (index >= int_th) - ds_overflow(context, qual); - } - - return bytes_written; -} - - -/* - * Branch Trace Store (BTS) uses the following format. Different - * architectures vary in the size of those fields. - * - source linear address - * - destination linear address - * - flags - * - * Later architectures use 64bit pointers throughout, whereas earlier - * architectures use 32bit pointers in 32bit mode. - * - * We compute the base address for the fields based on: - * - the field size stored in the DS configuration - * - the relative field position - * - * In order to store additional information in the BTS buffer, we use - * a special source address to indicate that the record requires - * special interpretation. - * - * Netburst indicated via a bit in the flags field whether the branch - * was predicted; this is ignored. - * - * We use two levels of abstraction: - * - the raw data level defined here - * - an arch-independent level defined in ds.h - */ - -enum bts_field { - bts_from, - bts_to, - bts_flags, - - bts_qual = bts_from, - bts_clock = bts_to, - bts_pid = bts_flags, - - bts_qual_mask = (bts_qual_max - 1), - bts_escape = ((unsigned long)-1 & ~bts_qual_mask) -}; - -static inline unsigned long bts_get(const char *base, unsigned long field) -{ - base += (ds_cfg.sizeof_ptr_field * field); - return *(unsigned long *)base; -} - -static inline void bts_set(char *base, unsigned long field, unsigned long val) -{ - base += (ds_cfg.sizeof_ptr_field * field); - (*(unsigned long *)base) = val; -} - - -/* - * The raw BTS data is architecture dependent. - * - * For higher-level users, we give an arch-independent view. - * - ds.h defines struct bts_struct - * - bts_read translates one raw bts record into a bts_struct - * - bts_write translates one bts_struct into the raw format and - * writes it into the top of the parameter tracer's buffer. - * - * return: bytes read/written on success; -Eerrno, otherwise - */ -static int -bts_read(struct bts_tracer *tracer, const void *at, struct bts_struct *out) -{ - if (!tracer) - return -EINVAL; - - if (at < tracer->trace.ds.begin) - return -EINVAL; - - if (tracer->trace.ds.end < (at + tracer->trace.ds.size)) - return -EINVAL; - - memset(out, 0, sizeof(*out)); - if ((bts_get(at, bts_qual) & ~bts_qual_mask) == bts_escape) { - out->qualifier = (bts_get(at, bts_qual) & bts_qual_mask); - out->variant.event.clock = bts_get(at, bts_clock); - out->variant.event.pid = bts_get(at, bts_pid); - } else { - out->qualifier = bts_branch; - out->variant.lbr.from = bts_get(at, bts_from); - out->variant.lbr.to = bts_get(at, bts_to); - - if (!out->variant.lbr.from && !out->variant.lbr.to) - out->qualifier = bts_invalid; - } - - return ds_cfg.sizeof_rec[ds_bts]; -} - -static int bts_write(struct bts_tracer *tracer, const struct bts_struct *in) -{ - unsigned char raw[MAX_SIZEOF_BTS]; - - if (!tracer) - return -EINVAL; - - if (MAX_SIZEOF_BTS < ds_cfg.sizeof_rec[ds_bts]) - return -EOVERFLOW; - - switch (in->qualifier) { - case bts_invalid: - bts_set(raw, bts_from, 0); - bts_set(raw, bts_to, 0); - bts_set(raw, bts_flags, 0); - break; - case bts_branch: - bts_set(raw, bts_from, in->variant.lbr.from); - bts_set(raw, bts_to, in->variant.lbr.to); - bts_set(raw, bts_flags, 0); - break; - case bts_task_arrives: - case bts_task_departs: - bts_set(raw, bts_qual, (bts_escape | in->qualifier)); - bts_set(raw, bts_clock, in->variant.event.clock); - bts_set(raw, bts_pid, in->variant.event.pid); - break; - default: - return -EINVAL; - } - - return ds_write(tracer->ds.context, ds_bts, raw, - ds_cfg.sizeof_rec[ds_bts]); -} - - -static void ds_write_config(struct ds_context *context, - struct ds_trace *cfg, enum ds_qualifier qual) -{ - unsigned char *ds = context->ds; - - ds_set(ds, qual, ds_buffer_base, (unsigned long)cfg->begin); - ds_set(ds, qual, ds_index, (unsigned long)cfg->top); - ds_set(ds, qual, ds_absolute_maximum, (unsigned long)cfg->end); - ds_set(ds, qual, ds_interrupt_threshold, (unsigned long)cfg->ith); -} - -static void ds_read_config(struct ds_context *context, - struct ds_trace *cfg, enum ds_qualifier qual) -{ - unsigned char *ds = context->ds; - - cfg->begin = (void *)ds_get(ds, qual, ds_buffer_base); - cfg->top = (void *)ds_get(ds, qual, ds_index); - cfg->end = (void *)ds_get(ds, qual, ds_absolute_maximum); - cfg->ith = (void *)ds_get(ds, qual, ds_interrupt_threshold); -} - -static void ds_init_ds_trace(struct ds_trace *trace, enum ds_qualifier qual, - void *base, size_t size, size_t ith, - unsigned int flags) { - unsigned long buffer, adj; - - /* - * Adjust the buffer address and size to meet alignment - * constraints: - * - buffer is double-word aligned - * - size is multiple of record size - * - * We checked the size at the very beginning; we have enough - * space to do the adjustment. - */ - buffer = (unsigned long)base; - - adj = ALIGN(buffer, DS_ALIGNMENT) - buffer; - buffer += adj; - size -= adj; - - trace->n = size / ds_cfg.sizeof_rec[qual]; - trace->size = ds_cfg.sizeof_rec[qual]; - - size = (trace->n * trace->size); - - trace->begin = (void *)buffer; - trace->top = trace->begin; - trace->end = (void *)(buffer + size); - /* - * The value for 'no threshold' is -1, which will set the - * threshold outside of the buffer, just like we want it. - */ - ith *= ds_cfg.sizeof_rec[qual]; - trace->ith = (void *)(buffer + size - ith); - - trace->flags = flags; -} - - -static int ds_request(struct ds_tracer *tracer, struct ds_trace *trace, - enum ds_qualifier qual, struct task_struct *task, - int cpu, void *base, size_t size, size_t th) -{ - struct ds_context *context; - int error; - size_t req_size; - - error = -EOPNOTSUPP; - if (!ds_cfg.sizeof_rec[qual]) - goto out; - - error = -EINVAL; - if (!base) - goto out; - - req_size = ds_cfg.sizeof_rec[qual]; - /* We might need space for alignment adjustments. */ - if (!IS_ALIGNED((unsigned long)base, DS_ALIGNMENT)) - req_size += DS_ALIGNMENT; - - error = -EINVAL; - if (size < req_size) - goto out; - - if (th != (size_t)-1) { - th *= ds_cfg.sizeof_rec[qual]; - - error = -EINVAL; - if (size <= th) - goto out; - } - - tracer->buffer = base; - tracer->size = size; - - error = -ENOMEM; - context = ds_get_context(task, cpu); - if (!context) - goto out; - tracer->context = context; - - /* - * Defer any tracer-specific initialization work for the context until - * context ownership has been clarified. - */ - - error = 0; - out: - return error; -} - -static struct bts_tracer *ds_request_bts(struct task_struct *task, int cpu, - void *base, size_t size, - bts_ovfl_callback_t ovfl, size_t th, - unsigned int flags) -{ - struct bts_tracer *tracer; - int error; - - /* Buffer overflow notification is not yet implemented. */ - error = -EOPNOTSUPP; - if (ovfl) - goto out; - - error = get_tracer(task); - if (error < 0) - goto out; - - error = -ENOMEM; - tracer = kzalloc(sizeof(*tracer), GFP_KERNEL); - if (!tracer) - goto out_put_tracer; - tracer->ovfl = ovfl; - - /* Do some more error checking and acquire a tracing context. */ - error = ds_request(&tracer->ds, &tracer->trace.ds, - ds_bts, task, cpu, base, size, th); - if (error < 0) - goto out_tracer; - - /* Claim the bts part of the tracing context we acquired above. */ - spin_lock_irq(&ds_lock); - - error = -EPERM; - if (tracer->ds.context->bts_master) - goto out_unlock; - tracer->ds.context->bts_master = tracer; - - spin_unlock_irq(&ds_lock); - - /* - * Now that we own the bts part of the context, let's complete the - * initialization for that part. - */ - ds_init_ds_trace(&tracer->trace.ds, ds_bts, base, size, th, flags); - ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts); - ds_install_ds_area(tracer->ds.context); - - tracer->trace.read = bts_read; - tracer->trace.write = bts_write; - - /* Start tracing. */ - ds_resume_bts(tracer); - - return tracer; - - out_unlock: - spin_unlock_irq(&ds_lock); - ds_put_context(tracer->ds.context); - out_tracer: - kfree(tracer); - out_put_tracer: - put_tracer(task); - out: - return ERR_PTR(error); -} - -struct bts_tracer *ds_request_bts_task(struct task_struct *task, - void *base, size_t size, - bts_ovfl_callback_t ovfl, - size_t th, unsigned int flags) -{ - return ds_request_bts(task, 0, base, size, ovfl, th, flags); -} - -struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size, - bts_ovfl_callback_t ovfl, - size_t th, unsigned int flags) -{ - return ds_request_bts(NULL, cpu, base, size, ovfl, th, flags); -} - -static struct pebs_tracer *ds_request_pebs(struct task_struct *task, int cpu, - void *base, size_t size, - pebs_ovfl_callback_t ovfl, size_t th, - unsigned int flags) -{ - struct pebs_tracer *tracer; - int error; - - /* Buffer overflow notification is not yet implemented. */ - error = -EOPNOTSUPP; - if (ovfl) - goto out; - - error = get_tracer(task); - if (error < 0) - goto out; - - error = -ENOMEM; - tracer = kzalloc(sizeof(*tracer), GFP_KERNEL); - if (!tracer) - goto out_put_tracer; - tracer->ovfl = ovfl; - - /* Do some more error checking and acquire a tracing context. */ - error = ds_request(&tracer->ds, &tracer->trace.ds, - ds_pebs, task, cpu, base, size, th); - if (error < 0) - goto out_tracer; - - /* Claim the pebs part of the tracing context we acquired above. */ - spin_lock_irq(&ds_lock); - - error = -EPERM; - if (tracer->ds.context->pebs_master) - goto out_unlock; - tracer->ds.context->pebs_master = tracer; - - spin_unlock_irq(&ds_lock); - - /* - * Now that we own the pebs part of the context, let's complete the - * initialization for that part. - */ - ds_init_ds_trace(&tracer->trace.ds, ds_pebs, base, size, th, flags); - ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_pebs); - ds_install_ds_area(tracer->ds.context); - - /* Start tracing. */ - ds_resume_pebs(tracer); - - return tracer; - - out_unlock: - spin_unlock_irq(&ds_lock); - ds_put_context(tracer->ds.context); - out_tracer: - kfree(tracer); - out_put_tracer: - put_tracer(task); - out: - return ERR_PTR(error); -} - -struct pebs_tracer *ds_request_pebs_task(struct task_struct *task, - void *base, size_t size, - pebs_ovfl_callback_t ovfl, - size_t th, unsigned int flags) -{ - return ds_request_pebs(task, 0, base, size, ovfl, th, flags); -} - -struct pebs_tracer *ds_request_pebs_cpu(int cpu, void *base, size_t size, - pebs_ovfl_callback_t ovfl, - size_t th, unsigned int flags) -{ - return ds_request_pebs(NULL, cpu, base, size, ovfl, th, flags); -} - -static void ds_free_bts(struct bts_tracer *tracer) -{ - struct task_struct *task; - - task = tracer->ds.context->task; - - WARN_ON_ONCE(tracer->ds.context->bts_master != tracer); - tracer->ds.context->bts_master = NULL; - - /* Make sure tracing stopped and the tracer is not in use. */ - if (task && (task != current)) - wait_task_context_switch(task); - - ds_put_context(tracer->ds.context); - put_tracer(task); - - kfree(tracer); -} - -void ds_release_bts(struct bts_tracer *tracer) -{ - might_sleep(); - - if (!tracer) - return; - - ds_suspend_bts(tracer); - ds_free_bts(tracer); -} - -int ds_release_bts_noirq(struct bts_tracer *tracer) -{ - struct task_struct *task; - unsigned long irq; - int error; - - if (!tracer) - return 0; - - task = tracer->ds.context->task; - - local_irq_save(irq); - - error = -EPERM; - if (!task && - (tracer->ds.context->cpu != smp_processor_id())) - goto out; - - error = -EPERM; - if (task && (task != current)) - goto out; - - ds_suspend_bts_noirq(tracer); - ds_free_bts(tracer); - - error = 0; - out: - local_irq_restore(irq); - return error; -} - -static void update_task_debugctlmsr(struct task_struct *task, - unsigned long debugctlmsr) -{ - task->thread.debugctlmsr = debugctlmsr; - - get_cpu(); - if (task == current) - update_debugctlmsr(debugctlmsr); - put_cpu(); -} - -void ds_suspend_bts(struct bts_tracer *tracer) -{ - struct task_struct *task; - unsigned long debugctlmsr; - int cpu; - - if (!tracer) - return; - - tracer->flags = 0; - - task = tracer->ds.context->task; - cpu = tracer->ds.context->cpu; - - WARN_ON(!task && irqs_disabled()); - - debugctlmsr = (task ? - task->thread.debugctlmsr : - get_debugctlmsr_on_cpu(cpu)); - debugctlmsr &= ~BTS_CONTROL; - - if (task) - update_task_debugctlmsr(task, debugctlmsr); - else - update_debugctlmsr_on_cpu(cpu, debugctlmsr); -} - -int ds_suspend_bts_noirq(struct bts_tracer *tracer) -{ - struct task_struct *task; - unsigned long debugctlmsr, irq; - int cpu, error = 0; - - if (!tracer) - return 0; - - tracer->flags = 0; - - task = tracer->ds.context->task; - cpu = tracer->ds.context->cpu; - - local_irq_save(irq); - - error = -EPERM; - if (!task && (cpu != smp_processor_id())) - goto out; - - debugctlmsr = (task ? - task->thread.debugctlmsr : - get_debugctlmsr()); - debugctlmsr &= ~BTS_CONTROL; - - if (task) - update_task_debugctlmsr(task, debugctlmsr); - else - update_debugctlmsr(debugctlmsr); - - error = 0; - out: - local_irq_restore(irq); - return error; -} - -static unsigned long ds_bts_control(struct bts_tracer *tracer) -{ - unsigned long control; - - control = ds_cfg.ctl[dsf_bts]; - if (!(tracer->trace.ds.flags & BTS_KERNEL)) - control |= ds_cfg.ctl[dsf_bts_kernel]; - if (!(tracer->trace.ds.flags & BTS_USER)) - control |= ds_cfg.ctl[dsf_bts_user]; - - return control; -} - -void ds_resume_bts(struct bts_tracer *tracer) -{ - struct task_struct *task; - unsigned long debugctlmsr; - int cpu; - - if (!tracer) - return; - - tracer->flags = tracer->trace.ds.flags; - - task = tracer->ds.context->task; - cpu = tracer->ds.context->cpu; - - WARN_ON(!task && irqs_disabled()); - - debugctlmsr = (task ? - task->thread.debugctlmsr : - get_debugctlmsr_on_cpu(cpu)); - debugctlmsr |= ds_bts_control(tracer); - - if (task) - update_task_debugctlmsr(task, debugctlmsr); - else - update_debugctlmsr_on_cpu(cpu, debugctlmsr); -} - -int ds_resume_bts_noirq(struct bts_tracer *tracer) -{ - struct task_struct *task; - unsigned long debugctlmsr, irq; - int cpu, error = 0; - - if (!tracer) - return 0; - - tracer->flags = tracer->trace.ds.flags; - - task = tracer->ds.context->task; - cpu = tracer->ds.context->cpu; - - local_irq_save(irq); - - error = -EPERM; - if (!task && (cpu != smp_processor_id())) - goto out; - - debugctlmsr = (task ? - task->thread.debugctlmsr : - get_debugctlmsr()); - debugctlmsr |= ds_bts_control(tracer); - - if (task) - update_task_debugctlmsr(task, debugctlmsr); - else - update_debugctlmsr(debugctlmsr); - - error = 0; - out: - local_irq_restore(irq); - return error; -} - -static void ds_free_pebs(struct pebs_tracer *tracer) -{ - struct task_struct *task; - - task = tracer->ds.context->task; - - WARN_ON_ONCE(tracer->ds.context->pebs_master != tracer); - tracer->ds.context->pebs_master = NULL; - - ds_put_context(tracer->ds.context); - put_tracer(task); - - kfree(tracer); -} - -void ds_release_pebs(struct pebs_tracer *tracer) -{ - might_sleep(); - - if (!tracer) - return; - - ds_suspend_pebs(tracer); - ds_free_pebs(tracer); -} - -int ds_release_pebs_noirq(struct pebs_tracer *tracer) -{ - struct task_struct *task; - unsigned long irq; - int error; - - if (!tracer) - return 0; - - task = tracer->ds.context->task; - - local_irq_save(irq); - - error = -EPERM; - if (!task && - (tracer->ds.context->cpu != smp_processor_id())) - goto out; - - error = -EPERM; - if (task && (task != current)) - goto out; - - ds_suspend_pebs_noirq(tracer); - ds_free_pebs(tracer); - - error = 0; - out: - local_irq_restore(irq); - return error; -} - -void ds_suspend_pebs(struct pebs_tracer *tracer) -{ - -} - -int ds_suspend_pebs_noirq(struct pebs_tracer *tracer) -{ - return 0; -} - -void ds_resume_pebs(struct pebs_tracer *tracer) -{ - -} - -int ds_resume_pebs_noirq(struct pebs_tracer *tracer) -{ - return 0; -} - -const struct bts_trace *ds_read_bts(struct bts_tracer *tracer) -{ - if (!tracer) - return NULL; - - ds_read_config(tracer->ds.context, &tracer->trace.ds, ds_bts); - return &tracer->trace; -} - -const struct pebs_trace *ds_read_pebs(struct pebs_tracer *tracer) -{ - if (!tracer) - return NULL; - - ds_read_config(tracer->ds.context, &tracer->trace.ds, ds_pebs); - - tracer->trace.counters = ds_cfg.nr_counter_reset; - memcpy(tracer->trace.counter_reset, - tracer->ds.context->ds + - (NUM_DS_PTR_FIELDS * ds_cfg.sizeof_ptr_field), - ds_cfg.nr_counter_reset * PEBS_RESET_FIELD_SIZE); - - return &tracer->trace; -} - -int ds_reset_bts(struct bts_tracer *tracer) -{ - if (!tracer) - return -EINVAL; - - tracer->trace.ds.top = tracer->trace.ds.begin; - - ds_set(tracer->ds.context->ds, ds_bts, ds_index, - (unsigned long)tracer->trace.ds.top); - - return 0; -} - -int ds_reset_pebs(struct pebs_tracer *tracer) -{ - if (!tracer) - return -EINVAL; - - tracer->trace.ds.top = tracer->trace.ds.begin; - - ds_set(tracer->ds.context->ds, ds_pebs, ds_index, - (unsigned long)tracer->trace.ds.top); - - return 0; -} - -int ds_set_pebs_reset(struct pebs_tracer *tracer, - unsigned int counter, u64 value) -{ - if (!tracer) - return -EINVAL; - - if (ds_cfg.nr_counter_reset < counter) - return -EINVAL; - - *(u64 *)(tracer->ds.context->ds + - (NUM_DS_PTR_FIELDS * ds_cfg.sizeof_ptr_field) + - (counter * PEBS_RESET_FIELD_SIZE)) = value; - - return 0; -} - -static const struct ds_configuration ds_cfg_netburst = { - .name = "Netburst", - .ctl[dsf_bts] = (1 << 2) | (1 << 3), - .ctl[dsf_bts_kernel] = (1 << 5), - .ctl[dsf_bts_user] = (1 << 6), - .nr_counter_reset = 1, -}; -static const struct ds_configuration ds_cfg_pentium_m = { - .name = "Pentium M", - .ctl[dsf_bts] = (1 << 6) | (1 << 7), - .nr_counter_reset = 1, -}; -static const struct ds_configuration ds_cfg_core2_atom = { - .name = "Core 2/Atom", - .ctl[dsf_bts] = (1 << 6) | (1 << 7), - .ctl[dsf_bts_kernel] = (1 << 9), - .ctl[dsf_bts_user] = (1 << 10), - .nr_counter_reset = 1, -}; -static const struct ds_configuration ds_cfg_core_i7 = { - .name = "Core i7", - .ctl[dsf_bts] = (1 << 6) | (1 << 7), - .ctl[dsf_bts_kernel] = (1 << 9), - .ctl[dsf_bts_user] = (1 << 10), - .nr_counter_reset = 4, -}; - -static void -ds_configure(const struct ds_configuration *cfg, - struct cpuinfo_x86 *cpu) -{ - unsigned long nr_pebs_fields = 0; - - printk(KERN_INFO "[ds] using %s configuration\n", cfg->name); - -#ifdef __i386__ - nr_pebs_fields = 10; -#else - nr_pebs_fields = 18; -#endif - - /* - * Starting with version 2, architectural performance - * monitoring supports a format specifier. - */ - if ((cpuid_eax(0xa) & 0xff) > 1) { - unsigned long perf_capabilities, format; - - rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_capabilities); - - format = (perf_capabilities >> 8) & 0xf; - - switch (format) { - case 0: - nr_pebs_fields = 18; - break; - case 1: - nr_pebs_fields = 22; - break; - default: - printk(KERN_INFO - "[ds] unknown PEBS format: %lu\n", format); - nr_pebs_fields = 0; - break; - } - } - - memset(&ds_cfg, 0, sizeof(ds_cfg)); - ds_cfg = *cfg; - - ds_cfg.sizeof_ptr_field = - (cpu_has(cpu, X86_FEATURE_DTES64) ? 8 : 4); - - ds_cfg.sizeof_rec[ds_bts] = ds_cfg.sizeof_ptr_field * 3; - ds_cfg.sizeof_rec[ds_pebs] = ds_cfg.sizeof_ptr_field * nr_pebs_fields; - - if (!cpu_has(cpu, X86_FEATURE_BTS)) { - ds_cfg.sizeof_rec[ds_bts] = 0; - printk(KERN_INFO "[ds] bts not available\n"); - } - if (!cpu_has(cpu, X86_FEATURE_PEBS)) { - ds_cfg.sizeof_rec[ds_pebs] = 0; - printk(KERN_INFO "[ds] pebs not available\n"); - } - - printk(KERN_INFO "[ds] sizes: address: %u bit, ", - 8 * ds_cfg.sizeof_ptr_field); - printk("bts/pebs record: %u/%u bytes\n", - ds_cfg.sizeof_rec[ds_bts], ds_cfg.sizeof_rec[ds_pebs]); - - WARN_ON_ONCE(MAX_PEBS_COUNTERS < ds_cfg.nr_counter_reset); -} - -void __cpuinit ds_init_intel(struct cpuinfo_x86 *c) -{ - /* Only configure the first cpu. Others are identical. */ - if (ds_cfg.name) - return; - - switch (c->x86) { - case 0x6: - switch (c->x86_model) { - case 0x9: - case 0xd: /* Pentium M */ - ds_configure(&ds_cfg_pentium_m, c); - break; - case 0xf: - case 0x17: /* Core2 */ - case 0x1c: /* Atom */ - ds_configure(&ds_cfg_core2_atom, c); - break; - case 0x1a: /* Core i7 */ - ds_configure(&ds_cfg_core_i7, c); - break; - default: - /* Sorry, don't know about them. */ - break; - } - break; - case 0xf: - switch (c->x86_model) { - case 0x0: - case 0x1: - case 0x2: /* Netburst */ - ds_configure(&ds_cfg_netburst, c); - break; - default: - /* Sorry, don't know about them. */ - break; - } - break; - default: - /* Sorry, don't know about them. */ - break; - } -} - -static inline void ds_take_timestamp(struct ds_context *context, - enum bts_qualifier qualifier, - struct task_struct *task) -{ - struct bts_tracer *tracer = context->bts_master; - struct bts_struct ts; - - /* Prevent compilers from reading the tracer pointer twice. */ - barrier(); - - if (!tracer || !(tracer->flags & BTS_TIMESTAMPS)) - return; - - memset(&ts, 0, sizeof(ts)); - ts.qualifier = qualifier; - ts.variant.event.clock = trace_clock_global(); - ts.variant.event.pid = task->pid; - - bts_write(tracer, &ts); -} - -/* - * Change the DS configuration from tracing prev to tracing next. - */ -void ds_switch_to(struct task_struct *prev, struct task_struct *next) -{ - struct ds_context *prev_ctx = prev->thread.ds_ctx; - struct ds_context *next_ctx = next->thread.ds_ctx; - unsigned long debugctlmsr = next->thread.debugctlmsr; - - /* Make sure all data is read before we start. */ - barrier(); - - if (prev_ctx) { - update_debugctlmsr(0); - - ds_take_timestamp(prev_ctx, bts_task_departs, prev); - } - - if (next_ctx) { - ds_take_timestamp(next_ctx, bts_task_arrives, next); - - wrmsrl(MSR_IA32_DS_AREA, (unsigned long)next_ctx->ds); - } - - update_debugctlmsr(debugctlmsr); -} - -static __init int ds_selftest(void) -{ - if (ds_cfg.sizeof_rec[ds_bts]) { - int error; - - error = ds_selftest_bts(); - if (error) { - WARN(1, "[ds] selftest failed. disabling bts.\n"); - ds_cfg.sizeof_rec[ds_bts] = 0; - } - } - - if (ds_cfg.sizeof_rec[ds_pebs]) { - int error; - - error = ds_selftest_pebs(); - if (error) { - WARN(1, "[ds] selftest failed. disabling pebs.\n"); - ds_cfg.sizeof_rec[ds_pebs] = 0; - } - } - - return 0; -} -device_initcall(ds_selftest); diff --git a/arch/x86/kernel/ds_selftest.c b/arch/x86/kernel/ds_selftest.c deleted file mode 100644 index 6bc7c199ab99..000000000000 --- a/arch/x86/kernel/ds_selftest.c +++ /dev/null @@ -1,408 +0,0 @@ -/* - * Debug Store support - selftest - * - * - * Copyright (C) 2009 Intel Corporation. - * Markus Metzger <markus.t.metzger@intel.com>, 2009 - */ - -#include "ds_selftest.h" - -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/smp.h> -#include <linux/cpu.h> - -#include <asm/ds.h> - - -#define BUFFER_SIZE 521 /* Intentionally chose an odd size. */ -#define SMALL_BUFFER_SIZE 24 /* A single bts entry. */ - -struct ds_selftest_bts_conf { - struct bts_tracer *tracer; - int error; - int (*suspend)(struct bts_tracer *); - int (*resume)(struct bts_tracer *); -}; - -static int ds_selftest_bts_consistency(const struct bts_trace *trace) -{ - int error = 0; - - if (!trace) { - printk(KERN_CONT "failed to access trace..."); - /* Bail out. Other tests are pointless. */ - return -1; - } - - if (!trace->read) { - printk(KERN_CONT "bts read not available..."); - error = -1; - } - - /* Do some sanity checks on the trace configuration. */ - if (!trace->ds.n) { - printk(KERN_CONT "empty bts buffer..."); - error = -1; - } - if (!trace->ds.size) { - printk(KERN_CONT "bad bts trace setup..."); - error = -1; - } - if (trace->ds.end != - (char *)trace->ds.begin + (trace->ds.n * trace->ds.size)) { - printk(KERN_CONT "bad bts buffer setup..."); - error = -1; - } - /* - * We allow top in [begin; end], since its not clear when the - * overflow adjustment happens: after the increment or before the - * write. - */ - if ((trace->ds.top < trace->ds.begin) || - (trace->ds.end < trace->ds.top)) { - printk(KERN_CONT "bts top out of bounds..."); - error = -1; - } - - return error; -} - -static int ds_selftest_bts_read(struct bts_tracer *tracer, - const struct bts_trace *trace, - const void *from, const void *to) -{ - const unsigned char *at; - - /* - * Check a few things which do not belong to this test. - * They should be covered by other tests. - */ - if (!trace) - return -1; - - if (!trace->read) - return -1; - - if (to < from) - return -1; - - if (from < trace->ds.begin) - return -1; - - if (trace->ds.end < to) - return -1; - - if (!trace->ds.size) - return -1; - - /* Now to the test itself. */ - for (at = from; (void *)at < to; at += trace->ds.size) { - struct bts_struct bts; - unsigned long index; - int error; - - if (((void *)at - trace->ds.begin) % trace->ds.size) { - printk(KERN_CONT - "read from non-integer index..."); - return -1; - } - index = ((void *)at - trace->ds.begin) / trace->ds.size; - - memset(&bts, 0, sizeof(bts)); - error = trace->read(tracer, at, &bts); - if (error < 0) { - printk(KERN_CONT - "error reading bts trace at [%lu] (0x%p)...", - index, at); - return error; - } - - switch (bts.qualifier) { - case BTS_BRANCH: - break; - default: - printk(KERN_CONT - "unexpected bts entry %llu at [%lu] (0x%p)...", - bts.qualifier, index, at); - return -1; - } - } - - return 0; -} - -static void ds_selftest_bts_cpu(void *arg) -{ - struct ds_selftest_bts_conf *conf = arg; - const struct bts_trace *trace; - void *top; - - if (IS_ERR(conf->tracer)) { - conf->error = PTR_ERR(conf->tracer); - conf->tracer = NULL; - - printk(KERN_CONT - "initialization failed (err: %d)...", conf->error); - return; - } - - /* We should meanwhile have enough trace. */ - conf->error = conf->suspend(conf->tracer); - if (conf->error < 0) - return; - - /* Let's see if we can access the trace. */ - trace = ds_read_bts(conf->tracer); - - conf->error = ds_selftest_bts_consistency(trace); - if (conf->error < 0) - return; - - /* If everything went well, we should have a few trace entries. */ - if (trace->ds.top == trace->ds.begin) { - /* - * It is possible but highly unlikely that we got a - * buffer overflow and end up at exactly the same - * position we started from. - * Let's issue a warning, but continue. - */ - printk(KERN_CONT "no trace/overflow..."); - } - - /* Let's try to read the trace we collected. */ - conf->error = - ds_selftest_bts_read(conf->tracer, trace, - trace->ds.begin, trace->ds.top); - if (conf->error < 0) - return; - - /* - * Let's read the trace again. - * Since we suspended tracing, we should get the same result. - */ - top = trace->ds.top; - - trace = ds_read_bts(conf->tracer); - conf->error = ds_selftest_bts_consistency(trace); - if (conf->error < 0) - return; - - if (top != trace->ds.top) { - printk(KERN_CONT "suspend not working..."); - conf->error = -1; - return; - } - - /* Let's collect some more trace - see if resume is working. */ - conf->error = conf->resume(conf->tracer); - if (conf->error < 0) - return; - - conf->error = conf->suspend(conf->tracer); - if (conf->error < 0) - return; - - trace = ds_read_bts(conf->tracer); - - conf->error = ds_selftest_bts_consistency(trace); - if (conf->error < 0) - return; - - if (trace->ds.top == top) { - /* - * It is possible but highly unlikely that we got a - * buffer overflow and end up at exactly the same - * position we started from. - * Let's issue a warning and check the full trace. - */ - printk(KERN_CONT - "no resume progress/overflow..."); - - conf->error = - ds_selftest_bts_read(conf->tracer, trace, - trace->ds.begin, trace->ds.end); - } else if (trace->ds.top < top) { - /* - * We had a buffer overflow - the entire buffer should - * contain trace records. - */ - conf->error = - ds_selftest_bts_read(conf->tracer, trace, - trace->ds.begin, trace->ds.end); - } else { - /* - * It is quite likely that the buffer did not overflow. - * Let's just check the delta trace. - */ - conf->error = - ds_selftest_bts_read(conf->tracer, trace, top, - trace->ds.top); - } - if (conf->error < 0) - return; - - conf->error = 0; -} - -static int ds_suspend_bts_wrap(struct bts_tracer *tracer) -{ - ds_suspend_bts(tracer); - return 0; -} - -static int ds_resume_bts_wrap(struct bts_tracer *tracer) -{ - ds_resume_bts(tracer); - return 0; -} - -static void ds_release_bts_noirq_wrap(void *tracer) -{ - (void)ds_release_bts_noirq(tracer); -} - -static int ds_selftest_bts_bad_release_noirq(int cpu, - struct bts_tracer *tracer) -{ - int error = -EPERM; - - /* Try to release the tracer on the wrong cpu. */ - get_cpu(); - if (cpu != smp_processor_id()) { - error = ds_release_bts_noirq(tracer); - if (error != -EPERM) - printk(KERN_CONT "release on wrong cpu..."); - } - put_cpu(); - - return error ? 0 : -1; -} - -static int ds_selftest_bts_bad_request_cpu(int cpu, void *buffer) -{ - struct bts_tracer *tracer; - int error; - - /* Try to request cpu tracing while task tracing is active. */ - tracer = ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE, NULL, - (size_t)-1, BTS_KERNEL); - error = PTR_ERR(tracer); - if (!IS_ERR(tracer)) { - ds_release_bts(tracer); - error = 0; - } - - if (error != -EPERM) - printk(KERN_CONT "cpu/task tracing overlap..."); - - return error ? 0 : -1; -} - -static int ds_selftest_bts_bad_request_task(void *buffer) -{ - struct bts_tracer *tracer; - int error; - - /* Try to request cpu tracing while task tracing is active. */ - tracer = ds_request_bts_task(current, buffer, BUFFER_SIZE, NULL, - (size_t)-1, BTS_KERNEL); - error = PTR_ERR(tracer); - if (!IS_ERR(tracer)) { - error = 0; - ds_release_bts(tracer); - } - - if (error != -EPERM) - printk(KERN_CONT "task/cpu tracing overlap..."); - - return error ? 0 : -1; -} - -int ds_selftest_bts(void) -{ - struct ds_selftest_bts_conf conf; - unsigned char buffer[BUFFER_SIZE], *small_buffer; - unsigned long irq; - int cpu; - - printk(KERN_INFO "[ds] bts selftest..."); - conf.error = 0; - - small_buffer = (unsigned char *)ALIGN((unsigned long)buffer, 8) + 8; - - get_online_cpus(); - for_each_online_cpu(cpu) { - conf.suspend = ds_suspend_bts_wrap; - conf.resume = ds_resume_bts_wrap; - conf.tracer = - ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE, - NULL, (size_t)-1, BTS_KERNEL); - ds_selftest_bts_cpu(&conf); - if (conf.error >= 0) - conf.error = ds_selftest_bts_bad_request_task(buffer); - ds_release_bts(conf.tracer); - if (conf.error < 0) - goto out; - - conf.suspend = ds_suspend_bts_noirq; - conf.resume = ds_resume_bts_noirq; - conf.tracer = - ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE, - NULL, (size_t)-1, BTS_KERNEL); - smp_call_function_single(cpu, ds_selftest_bts_cpu, &conf, 1); - if (conf.error >= 0) { - conf.error = - ds_selftest_bts_bad_release_noirq(cpu, - conf.tracer); - /* We must not release the tracer twice. */ - if (conf.error < 0) - conf.tracer = NULL; - } - if (conf.error >= 0) - conf.error = ds_selftest_bts_bad_request_task(buffer); - smp_call_function_single(cpu, ds_release_bts_noirq_wrap, - conf.tracer, 1); - if (conf.error < 0) - goto out; - } - - conf.suspend = ds_suspend_bts_wrap; - conf.resume = ds_resume_bts_wrap; - conf.tracer = - ds_request_bts_task(current, buffer, BUFFER_SIZE, - NULL, (size_t)-1, BTS_KERNEL); - ds_selftest_bts_cpu(&conf); - if (conf.error >= 0) - conf.error = ds_selftest_bts_bad_request_cpu(0, buffer); - ds_release_bts(conf.tracer); - if (conf.error < 0) - goto out; - - conf.suspend = ds_suspend_bts_noirq; - conf.resume = ds_resume_bts_noirq; - conf.tracer = - ds_request_bts_task(current, small_buffer, SMALL_BUFFER_SIZE, - NULL, (size_t)-1, BTS_KERNEL); - local_irq_save(irq); - ds_selftest_bts_cpu(&conf); - if (conf.error >= 0) - conf.error = ds_selftest_bts_bad_request_cpu(0, buffer); - ds_release_bts_noirq(conf.tracer); - local_irq_restore(irq); - if (conf.error < 0) - goto out; - - conf.error = 0; - out: - put_online_cpus(); - printk(KERN_CONT "%s.\n", (conf.error ? "failed" : "passed")); - - return conf.error; -} - -int ds_selftest_pebs(void) -{ - return 0; -} diff --git a/arch/x86/kernel/ds_selftest.h b/arch/x86/kernel/ds_selftest.h deleted file mode 100644 index 2ba8745c6663..000000000000 --- a/arch/x86/kernel/ds_selftest.h +++ /dev/null @@ -1,15 +0,0 @@ -/* - * Debug Store support - selftest - * - * - * Copyright (C) 2009 Intel Corporation. - * Markus Metzger <markus.t.metzger@intel.com>, 2009 - */ - -#ifdef CONFIG_X86_DS_SELFTEST -extern int ds_selftest_bts(void); -extern int ds_selftest_pebs(void); -#else -static inline int ds_selftest_bts(void) { return 0; } -static inline int ds_selftest_pebs(void) { return 0; } -#endif diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 6d817554780a..c89a386930b7 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -224,11 +224,6 @@ unsigned __kprobes long oops_begin(void) int cpu; unsigned long flags; - /* notify the hw-branch tracer so it may disable tracing and - add the last trace to the trace buffer - - the earlier this happens, the more useful the trace. */ - trace_hw_branch_oops(); - oops_enter(); /* racy, but better than risking deadlock. */ diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index b43bbaebe2c0..f2f56c0967b6 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -422,14 +422,22 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, static void __kprobes clear_btf(void) { - if (test_thread_flag(TIF_DEBUGCTLMSR)) - update_debugctlmsr(0); + if (test_thread_flag(TIF_BLOCKSTEP)) { + unsigned long debugctl = get_debugctlmsr(); + + debugctl &= ~DEBUGCTLMSR_BTF; + update_debugctlmsr(debugctl); + } } static void __kprobes restore_btf(void) { - if (test_thread_flag(TIF_DEBUGCTLMSR)) - update_debugctlmsr(current->thread.debugctlmsr); + if (test_thread_flag(TIF_BLOCKSTEP)) { + unsigned long debugctl = get_debugctlmsr(); + + debugctl |= DEBUGCTLMSR_BTF; + update_debugctlmsr(debugctl); + } } void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 28ad9f4d8b94..eccdb57094e3 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -20,7 +20,6 @@ #include <asm/idle.h> #include <asm/uaccess.h> #include <asm/i387.h> -#include <asm/ds.h> #include <asm/debugreg.h> unsigned long idle_halt; @@ -50,8 +49,6 @@ void free_thread_xstate(struct task_struct *tsk) kmem_cache_free(task_xstate_cachep, tsk->thread.xstate); tsk->thread.xstate = NULL; } - - WARN(tsk->thread.ds_ctx, "leaking DS context\n"); } void free_thread_info(struct thread_info *ti) @@ -198,11 +195,16 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, prev = &prev_p->thread; next = &next_p->thread; - if (test_tsk_thread_flag(next_p, TIF_DS_AREA_MSR) || - test_tsk_thread_flag(prev_p, TIF_DS_AREA_MSR)) - ds_switch_to(prev_p, next_p); - else if (next->debugctlmsr != prev->debugctlmsr) - update_debugctlmsr(next->debugctlmsr); + if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^ + test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) { + unsigned long debugctl = get_debugctlmsr(); + + debugctl &= ~DEBUGCTLMSR_BTF; + if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) + debugctl |= DEBUGCTLMSR_BTF; + + update_debugctlmsr(debugctl); + } if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ test_tsk_thread_flag(next_p, TIF_NOTSC)) { diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index f6c62667e30c..75090c589b7a 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -55,7 +55,6 @@ #include <asm/cpu.h> #include <asm/idle.h> #include <asm/syscalls.h> -#include <asm/ds.h> #include <asm/debugreg.h> asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); @@ -238,13 +237,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, kfree(p->thread.io_bitmap_ptr); p->thread.io_bitmap_max = 0; } - - clear_tsk_thread_flag(p, TIF_DS_AREA_MSR); - p->thread.ds_ctx = NULL; - - clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR); - p->thread.debugctlmsr = 0; - return err; } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index dc9690b4c4cc..cc4258f2beb5 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -49,7 +49,6 @@ #include <asm/ia32.h> #include <asm/idle.h> #include <asm/syscalls.h> -#include <asm/ds.h> #include <asm/debugreg.h> asmlinkage extern void ret_from_fork(void); @@ -313,13 +312,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, if (err) goto out; } - - clear_tsk_thread_flag(p, TIF_DS_AREA_MSR); - p->thread.ds_ctx = NULL; - - clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR); - p->thread.debugctlmsr = 0; - err = 0; out: if (err && p->thread.io_bitmap_ptr) { diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 2e9b55027b7e..055be0afd330 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -2,9 +2,6 @@ /* * Pentium III FXSR, SSE support * Gareth Hughes <gareth@valinux.com>, May 2000 - * - * BTS tracing - * Markus Metzger <markus.t.metzger@intel.com>, Dec 2007 */ #include <linux/kernel.h> @@ -22,7 +19,6 @@ #include <linux/audit.h> #include <linux/seccomp.h> #include <linux/signal.h> -#include <linux/workqueue.h> #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> @@ -36,7 +32,6 @@ #include <asm/desc.h> #include <asm/prctl.h> #include <asm/proto.h> -#include <asm/ds.h> #include <asm/hw_breakpoint.h> #include "tls.h" @@ -789,342 +784,6 @@ static int ioperm_get(struct task_struct *target, 0, IO_BITMAP_BYTES); } -#ifdef CONFIG_X86_PTRACE_BTS -/* - * A branch trace store context. - * - * Contexts may only be installed by ptrace_bts_config() and only for - * ptraced tasks. - * - * Contexts are destroyed when the tracee is detached from the tracer. - * The actual destruction work requires interrupts enabled, so the - * work is deferred and will be scheduled during __ptrace_unlink(). - * - * Contexts hold an additional task_struct reference on the traced - * task, as well as a reference on the tracer's mm. - * - * Ptrace already holds a task_struct for the duration of ptrace operations, - * but since destruction is deferred, it may be executed after both - * tracer and tracee exited. - */ -struct bts_context { - /* The branch trace handle. */ - struct bts_tracer *tracer; - - /* The buffer used to store the branch trace and its size. */ - void *buffer; - unsigned int size; - - /* The mm that paid for the above buffer. */ - struct mm_struct *mm; - - /* The task this context belongs to. */ - struct task_struct *task; - - /* The signal to send on a bts buffer overflow. */ - unsigned int bts_ovfl_signal; - - /* The work struct to destroy a context. */ - struct work_struct work; -}; - -static int alloc_bts_buffer(struct bts_context *context, unsigned int size) -{ - void *buffer = NULL; - int err = -ENOMEM; - - err = account_locked_memory(current->mm, current->signal->rlim, size); - if (err < 0) - return err; - - buffer = kzalloc(size, GFP_KERNEL); - if (!buffer) - goto out_refund; - - context->buffer = buffer; - context->size = size; - context->mm = get_task_mm(current); - - return 0; - - out_refund: - refund_locked_memory(current->mm, size); - return err; -} - -static inline void free_bts_buffer(struct bts_context *context) -{ - if (!context->buffer) - return; - - kfree(context->buffer); - context->buffer = NULL; - - refund_locked_memory(context->mm, context->size); - context->size = 0; - - mmput(context->mm); - context->mm = NULL; -} - -static void free_bts_context_work(struct work_struct *w) -{ - struct bts_context *context; - - context = container_of(w, struct bts_context, work); - - ds_release_bts(context->tracer); - put_task_struct(context->task); - free_bts_buffer(context); - kfree(context); -} - -static inline void free_bts_context(struct bts_context *context) -{ - INIT_WORK(&context->work, free_bts_context_work); - schedule_work(&context->work); -} - -static inline struct bts_context *alloc_bts_context(struct task_struct *task) -{ - struct bts_context *context = kzalloc(sizeof(*context), GFP_KERNEL); - if (context) { - context->task = task; - task->bts = context; - - get_task_struct(task); - } - - return context; -} - -static int ptrace_bts_read_record(struct task_struct *child, size_t index, - struct bts_struct __user *out) -{ - struct bts_context *context; - const struct bts_trace *trace; - struct bts_struct bts; - const unsigned char *at; - int error; - - context = child->bts; - if (!context) - return -ESRCH; - - trace = ds_read_bts(context->tracer); - if (!trace) - return -ESRCH; - - at = trace->ds.top - ((index + 1) * trace->ds.size); - if ((void *)at < trace->ds.begin) - at += (trace->ds.n * trace->ds.size); - - if (!trace->read) - return -EOPNOTSUPP; - - error = trace->read(context->tracer, at, &bts); - if (error < 0) - return error; - - if (copy_to_user(out, &bts, sizeof(bts))) - return -EFAULT; - - return sizeof(bts); -} - -static int ptrace_bts_drain(struct task_struct *child, - long size, - struct bts_struct __user *out) -{ - struct bts_context *context; - const struct bts_trace *trace; - const unsigned char *at; - int error, drained = 0; - - context = child->bts; - if (!context) - return -ESRCH; - - trace = ds_read_bts(context->tracer); - if (!trace) - return -ESRCH; - - if (!trace->read) - return -EOPNOTSUPP; - - if (size < (trace->ds.top - trace->ds.begin)) - return -EIO; - - for (at = trace->ds.begin; (void *)at < trace->ds.top; - out++, drained++, at += trace->ds.size) { - struct bts_struct bts; - - error = trace->read(context->tracer, at, &bts); - if (error < 0) - return error; - - if (copy_to_user(out, &bts, sizeof(bts))) - return -EFAULT; - } - - memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size); - - error = ds_reset_bts(context->tracer); - if (error < 0) - return error; - - return drained; -} - -static int ptrace_bts_config(struct task_struct *child, - long cfg_size, - const struct ptrace_bts_config __user *ucfg) -{ - struct bts_context *context; - struct ptrace_bts_config cfg; - unsigned int flags = 0; - - if (cfg_size < sizeof(cfg)) - return -EIO; - - if (copy_from_user(&cfg, ucfg, sizeof(cfg))) - return -EFAULT; - - context = child->bts; - if (!context) - context = alloc_bts_context(child); - if (!context) - return -ENOMEM; - - if (cfg.flags & PTRACE_BTS_O_SIGNAL) { - if (!cfg.signal) - return -EINVAL; - - return -EOPNOTSUPP; - context->bts_ovfl_signal = cfg.signal; - } - - ds_release_bts(context->tracer); - context->tracer = NULL; - - if ((cfg.flags & PTRACE_BTS_O_ALLOC) && (cfg.size != context->size)) { - int err; - - free_bts_buffer(context); - if (!cfg.size) - return 0; - - err = alloc_bts_buffer(context, cfg.size); - if (err < 0) - return err; - } - - if (cfg.flags & PTRACE_BTS_O_TRACE) - flags |= BTS_USER; - - if (cfg.flags & PTRACE_BTS_O_SCHED) - flags |= BTS_TIMESTAMPS; - - context->tracer = - ds_request_bts_task(child, context->buffer, context->size, - NULL, (size_t)-1, flags); - if (unlikely(IS_ERR(context->tracer))) { - int error = PTR_ERR(context->tracer); - - free_bts_buffer(context); - context->tracer = NULL; - return error; - } - - return sizeof(cfg); -} - -static int ptrace_bts_status(struct task_struct *child, - long cfg_size, - struct ptrace_bts_config __user *ucfg) -{ - struct bts_context *context; - const struct bts_trace *trace; - struct ptrace_bts_config cfg; - - context = child->bts; - if (!context) - return -ESRCH; - - if (cfg_size < sizeof(cfg)) - return -EIO; - - trace = ds_read_bts(context->tracer); - if (!trace) - return -ESRCH; - - memset(&cfg, 0, sizeof(cfg)); - cfg.size = trace->ds.end - trace->ds.begin; - cfg.signal = context->bts_ovfl_signal; - cfg.bts_size = sizeof(struct bts_struct); - - if (cfg.signal) - cfg.flags |= PTRACE_BTS_O_SIGNAL; - - if (trace->ds.flags & BTS_USER) - cfg.flags |= PTRACE_BTS_O_TRACE; - - if (trace->ds.flags & BTS_TIMESTAMPS) - cfg.flags |= PTRACE_BTS_O_SCHED; - - if (copy_to_user(ucfg, &cfg, sizeof(cfg))) - return -EFAULT; - - return sizeof(cfg); -} - -static int ptrace_bts_clear(struct task_struct *child) -{ - struct bts_context *context; - const struct bts_trace *trace; - - context = child->bts; - if (!context) - return -ESRCH; - - trace = ds_read_bts(context->tracer); - if (!trace) - return -ESRCH; - - memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size); - - return ds_reset_bts(context->tracer); -} - -static int ptrace_bts_size(struct task_struct *child) -{ - struct bts_context *context; - const struct bts_trace *trace; - - context = child->bts; - if (!context) - return -ESRCH; - - trace = ds_read_bts(context->tracer); - if (!trace) - return -ESRCH; - - return (trace->ds.top - trace->ds.begin) / trace->ds.size; -} - -/* - * Called from __ptrace_unlink() after the child has been moved back - * to its original parent. - */ -void ptrace_bts_untrace(struct task_struct *child) -{ - if (unlikely(child->bts)) { - free_bts_context(child->bts); - child->bts = NULL; - } -} -#endif /* CONFIG_X86_PTRACE_BTS */ - /* * Called by kernel/ptrace.c when detaching.. * @@ -1252,39 +911,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) break; #endif - /* - * These bits need more cooking - not enabled yet: - */ -#ifdef CONFIG_X86_PTRACE_BTS - case PTRACE_BTS_CONFIG: - ret = ptrace_bts_config - (child, data, (struct ptrace_bts_config __user *)addr); - break; - - case PTRACE_BTS_STATUS: - ret = ptrace_bts_status - (child, data, (struct ptrace_bts_config __user *)addr); - break; - - case PTRACE_BTS_SIZE: - ret = ptrace_bts_size(child); - break; - - case PTRACE_BTS_GET: - ret = ptrace_bts_read_record - (child, data, (struct bts_struct __user *) addr); - break; - - case PTRACE_BTS_CLEAR: - ret = ptrace_bts_clear(child); - break; - - case PTRACE_BTS_DRAIN: - ret = ptrace_bts_drain - (child, data, (struct bts_struct __user *) addr); - break; -#endif /* CONFIG_X86_PTRACE_BTS */ - default: ret = ptrace_request(child, request, addr, data); break; @@ -1544,14 +1170,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, case PTRACE_GET_THREAD_AREA: case PTRACE_SET_THREAD_AREA: -#ifdef CONFIG_X86_PTRACE_BTS - case PTRACE_BTS_CONFIG: - case PTRACE_BTS_STATUS: - case PTRACE_BTS_SIZE: - case PTRACE_BTS_GET: - case PTRACE_BTS_CLEAR: - case PTRACE_BTS_DRAIN: -#endif /* CONFIG_X86_PTRACE_BTS */ return arch_ptrace(child, request, addr, data); default: diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 3149032ff107..58de45ee08b6 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -158,22 +158,6 @@ static int enable_single_step(struct task_struct *child) } /* - * Install this value in MSR_IA32_DEBUGCTLMSR whenever child is running. - */ -static void write_debugctlmsr(struct task_struct *child, unsigned long val) -{ - if (child->thread.debugctlmsr == val) - return; - - child->thread.debugctlmsr = val; - - if (child != current) - return; - - update_debugctlmsr(val); -} - -/* * Enable single or block step. */ static void enable_step(struct task_struct *child, bool block) @@ -186,15 +170,17 @@ static void enable_step(struct task_struct *child, bool block) * that uses user-mode single stepping itself. */ if (enable_single_step(child) && block) { - set_tsk_thread_flag(child, TIF_DEBUGCTLMSR); - write_debugctlmsr(child, - child->thread.debugctlmsr | DEBUGCTLMSR_BTF); - } else { - write_debugctlmsr(child, - child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF); - - if (!child->thread.debugctlmsr) - clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR); + unsigned long debugctl = get_debugctlmsr(); + + debugctl |= DEBUGCTLMSR_BTF; + update_debugctlmsr(debugctl); + set_tsk_thread_flag(child, TIF_BLOCKSTEP); + } else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) { + unsigned long debugctl = get_debugctlmsr(); + + debugctl &= ~DEBUGCTLMSR_BTF; + update_debugctlmsr(debugctl); + clear_tsk_thread_flag(child, TIF_BLOCKSTEP); } } @@ -213,11 +199,13 @@ void user_disable_single_step(struct task_struct *child) /* * Make sure block stepping (BTF) is disabled. */ - write_debugctlmsr(child, - child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF); + if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) { + unsigned long debugctl = get_debugctlmsr(); - if (!child->thread.debugctlmsr) - clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR); + debugctl &= ~DEBUGCTLMSR_BTF; + update_debugctlmsr(debugctl); + clear_tsk_thread_flag(child, TIF_BLOCKSTEP); + } /* Always clear TIF_SINGLESTEP... */ clear_tsk_thread_flag(child, TIF_SINGLESTEP); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1168e4454188..36f1bd9f8e76 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -543,11 +543,11 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) /* DR6 may or may not be cleared by the CPU */ set_debugreg(0, 6); + /* * The processor cleared BTF, so don't mark that we need it set. */ - clear_tsk_thread_flag(tsk, TIF_DEBUGCTLMSR); - tsk->thread.debugctlmsr = 0; + clear_tsk_thread_flag(tsk, TIF_BLOCKSTEP); /* Store the virtualized DR6 value */ tsk->thread.debugreg6 = dr6; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 4dade6ac0827..5ac0bb465ed6 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -33,6 +33,7 @@ #include <asm/kvm_emulate.h> #include "x86.h" +#include "tss.h" /* * Opcode effective-address decode tables. @@ -50,6 +51,8 @@ #define DstReg (2<<1) /* Register operand. */ #define DstMem (3<<1) /* Memory operand. */ #define DstAcc (4<<1) /* Destination Accumulator */ +#define DstDI (5<<1) /* Destination is in ES:(E)DI */ +#define DstMem64 (6<<1) /* 64bit memory operand */ #define DstMask (7<<1) /* Source operand type. */ #define SrcNone (0<<4) /* No source operand. */ @@ -63,6 +66,7 @@ #define SrcOne (7<<4) /* Implied '1' */ #define SrcImmUByte (8<<4) /* 8-bit unsigned immediate operand. */ #define SrcImmU (9<<4) /* Immediate operand, unsigned */ +#define SrcSI (0xa<<4) /* Source is in the DS:RSI */ #define SrcMask (0xf<<4) /* Generic ModRM decode. */ #define ModRM (1<<8) @@ -85,6 +89,9 @@ #define Src2ImmByte (2<<29) #define Src2One (3<<29) #define Src2Imm16 (4<<29) +#define Src2Mem16 (5<<29) /* Used for Ep encoding. First argument has to be + in memory and second argument is located + immediately after the first one in memory. */ #define Src2Mask (7<<29) enum { @@ -147,8 +154,8 @@ static u32 opcode_table[256] = { 0, 0, 0, 0, /* 0x68 - 0x6F */ SrcImm | Mov | Stack, 0, SrcImmByte | Mov | Stack, 0, - SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* insb, insw/insd */ - SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* outsb, outsw/outsd */ + DstDI | ByteOp | Mov | String, DstDI | Mov | String, /* insb, insw/insd */ + SrcSI | ByteOp | ImplicitOps | String, SrcSI | ImplicitOps | String, /* outsb, outsw/outsd */ /* 0x70 - 0x77 */ SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, @@ -173,12 +180,12 @@ static u32 opcode_table[256] = { /* 0xA0 - 0xA7 */ ByteOp | DstReg | SrcMem | Mov | MemAbs, DstReg | SrcMem | Mov | MemAbs, ByteOp | DstMem | SrcReg | Mov | MemAbs, DstMem | SrcReg | Mov | MemAbs, - ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String, - ByteOp | ImplicitOps | String, ImplicitOps | String, + ByteOp | SrcSI | DstDI | Mov | String, SrcSI | DstDI | Mov | String, + ByteOp | SrcSI | DstDI | String, SrcSI | DstDI | String, /* 0xA8 - 0xAF */ - 0, 0, ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String, - ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String, - ByteOp | ImplicitOps | String, ImplicitOps | String, + 0, 0, ByteOp | DstDI | Mov | String, DstDI | Mov | String, + ByteOp | SrcSI | DstAcc | Mov | String, SrcSI | DstAcc | Mov | String, + ByteOp | DstDI | String, DstDI | String, /* 0xB0 - 0xB7 */ ByteOp | DstReg | SrcImm | Mov, ByteOp | DstReg | SrcImm | Mov, ByteOp | DstReg | SrcImm | Mov, ByteOp | DstReg | SrcImm | Mov, @@ -204,13 +211,13 @@ static u32 opcode_table[256] = { 0, 0, 0, 0, 0, 0, 0, 0, /* 0xE0 - 0xE7 */ 0, 0, 0, 0, - ByteOp | SrcImmUByte, SrcImmUByte, - ByteOp | SrcImmUByte, SrcImmUByte, + ByteOp | SrcImmUByte | DstAcc, SrcImmUByte | DstAcc, + ByteOp | SrcImmUByte | DstAcc, SrcImmUByte | DstAcc, /* 0xE8 - 0xEF */ SrcImm | Stack, SrcImm | ImplicitOps, SrcImmU | Src2Imm16 | No64, SrcImmByte | ImplicitOps, - SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, - SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, + SrcNone | ByteOp | DstAcc, SrcNone | DstAcc, + SrcNone | ByteOp | DstAcc, SrcNone | DstAcc, /* 0xF0 - 0xF7 */ 0, 0, 0, 0, ImplicitOps | Priv, ImplicitOps, Group | Group3_Byte, Group | Group3, @@ -343,7 +350,8 @@ static u32 group_table[] = { [Group5*8] = DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM, SrcMem | ModRM | Stack, 0, - SrcMem | ModRM | Stack, 0, SrcMem | ModRM | Stack, 0, + SrcMem | ModRM | Stack, SrcMem | ModRM | Src2Mem16 | ImplicitOps, + SrcMem | ModRM | Stack, 0, [Group7*8] = 0, 0, ModRM | SrcMem | Priv, ModRM | SrcMem | Priv, SrcNone | ModRM | DstMem | Mov, 0, @@ -353,14 +361,14 @@ static u32 group_table[] = { DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM | Lock, DstMem | SrcImmByte | ModRM | Lock, DstMem | SrcImmByte | ModRM | Lock, [Group9*8] = - 0, ImplicitOps | ModRM | Lock, 0, 0, 0, 0, 0, 0, + 0, DstMem64 | ModRM | Lock, 0, 0, 0, 0, 0, 0, }; static u32 group2_table[] = { [Group7*8] = - SrcNone | ModRM | Priv, 0, 0, SrcNone | ModRM, + SrcNone | ModRM | Priv, 0, 0, SrcNone | ModRM | Priv, SrcNone | ModRM | DstMem | Mov, 0, - SrcMem16 | ModRM | Mov, 0, + SrcMem16 | ModRM | Mov | Priv, 0, [Group9*8] = 0, 0, 0, 0, 0, 0, 0, 0, }; @@ -562,7 +570,7 @@ static u32 group2_table[] = { #define insn_fetch(_type, _size, _eip) \ ({ unsigned long _x; \ rc = do_insn_fetch(ctxt, ops, (_eip), &_x, (_size)); \ - if (rc != 0) \ + if (rc != X86EMUL_CONTINUE) \ goto done; \ (_eip) += (_size); \ (_type)_x; \ @@ -638,40 +646,40 @@ static unsigned long ss_base(struct x86_emulate_ctxt *ctxt) static int do_fetch_insn_byte(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, - unsigned long linear, u8 *dest) + unsigned long eip, u8 *dest) { struct fetch_cache *fc = &ctxt->decode.fetch; int rc; - int size; + int size, cur_size; - if (linear < fc->start || linear >= fc->end) { - size = min(15UL, PAGE_SIZE - offset_in_page(linear)); - rc = ops->fetch(linear, fc->data, size, ctxt->vcpu, NULL); - if (rc) + if (eip == fc->end) { + cur_size = fc->end - fc->start; + size = min(15UL - cur_size, PAGE_SIZE - offset_in_page(eip)); + rc = ops->fetch(ctxt->cs_base + eip, fc->data + cur_size, + size, ctxt->vcpu, NULL); + if (rc != X86EMUL_CONTINUE) return rc; - fc->start = linear; - fc->end = linear + size; + fc->end += size; } - *dest = fc->data[linear - fc->start]; - return 0; + *dest = fc->data[eip - fc->start]; + return X86EMUL_CONTINUE; } static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, unsigned long eip, void *dest, unsigned size) { - int rc = 0; + int rc; /* x86 instructions are limited to 15 bytes. */ - if (eip + size - ctxt->decode.eip_orig > 15) + if (eip + size - ctxt->eip > 15) return X86EMUL_UNHANDLEABLE; - eip += ctxt->cs_base; while (size--) { rc = do_fetch_insn_byte(ctxt, ops, eip++, dest++); - if (rc) + if (rc != X86EMUL_CONTINUE) return rc; } - return 0; + return X86EMUL_CONTINUE; } /* @@ -702,7 +710,7 @@ static int read_descriptor(struct x86_emulate_ctxt *ctxt, *address = 0; rc = ops->read_std((unsigned long)ptr, (unsigned long *)size, 2, ctxt->vcpu, NULL); - if (rc) + if (rc != X86EMUL_CONTINUE) return rc; rc = ops->read_std((unsigned long)ptr + 2, address, op_bytes, ctxt->vcpu, NULL); @@ -782,7 +790,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, struct decode_cache *c = &ctxt->decode; u8 sib; int index_reg = 0, base_reg = 0, scale; - int rc = 0; + int rc = X86EMUL_CONTINUE; if (c->rex_prefix) { c->modrm_reg = (c->rex_prefix & 4) << 1; /* REX.R */ @@ -895,7 +903,7 @@ static int decode_abs(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc = 0; + int rc = X86EMUL_CONTINUE; switch (c->ad_bytes) { case 2: @@ -916,14 +924,18 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc = 0; + int rc = X86EMUL_CONTINUE; int mode = ctxt->mode; int def_op_bytes, def_ad_bytes, group; - /* Shadow copy of register state. Committed on successful emulation. */ + /* we cannot decode insn before we complete previous rep insn */ + WARN_ON(ctxt->restart); + + /* Shadow copy of register state. Committed on successful emulation. */ memset(c, 0, sizeof(struct decode_cache)); - c->eip = c->eip_orig = kvm_rip_read(ctxt->vcpu); + c->eip = ctxt->eip; + c->fetch.start = c->fetch.end = c->eip; ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS); memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs); @@ -1015,11 +1027,6 @@ done_prefixes: } } - if (mode == X86EMUL_MODE_PROT64 && (c->d & No64)) { - kvm_report_emulation_failure(ctxt->vcpu, "invalid x86/64 instruction"); - return -1; - } - if (c->d & Group) { group = c->d & GroupMask; c->modrm = insn_fetch(u8, 1, c->eip); @@ -1046,7 +1053,7 @@ done_prefixes: rc = decode_modrm(ctxt, ops); else if (c->d & MemAbs) rc = decode_abs(ctxt, ops); - if (rc) + if (rc != X86EMUL_CONTINUE) goto done; if (!c->has_seg_override) @@ -1057,6 +1064,10 @@ done_prefixes: if (c->ad_bytes != 8) c->modrm_ea = (u32)c->modrm_ea; + + if (c->rip_relative) + c->modrm_ea += c->eip; + /* * Decode and fetch the source operand: register, memory * or immediate. @@ -1091,6 +1102,8 @@ done_prefixes: break; } c->src.type = OP_MEM; + c->src.ptr = (unsigned long *)c->modrm_ea; + c->src.val = 0; break; case SrcImm: case SrcImmU: @@ -1139,6 +1152,14 @@ done_prefixes: c->src.bytes = 1; c->src.val = 1; break; + case SrcSI: + c->src.type = OP_MEM; + c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->src.ptr = (unsigned long *) + register_address(c, seg_override_base(ctxt, c), + c->regs[VCPU_REGS_RSI]); + c->src.val = 0; + break; } /* @@ -1168,6 +1189,12 @@ done_prefixes: c->src2.bytes = 1; c->src2.val = 1; break; + case Src2Mem16: + c->src2.type = OP_MEM; + c->src2.bytes = 2; + c->src2.ptr = (unsigned long *)(c->modrm_ea + c->src.bytes); + c->src2.val = 0; + break; } /* Decode and fetch the destination operand: register or memory. */ @@ -1180,6 +1207,7 @@ done_prefixes: c->twobyte && (c->b == 0xb6 || c->b == 0xb7)); break; case DstMem: + case DstMem64: if ((c->d & ModRM) && c->modrm_mod == 3) { c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; c->dst.type = OP_REG; @@ -1188,12 +1216,24 @@ done_prefixes: break; } c->dst.type = OP_MEM; + c->dst.ptr = (unsigned long *)c->modrm_ea; + if ((c->d & DstMask) == DstMem64) + c->dst.bytes = 8; + else + c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->dst.val = 0; + if (c->d & BitOp) { + unsigned long mask = ~(c->dst.bytes * 8 - 1); + + c->dst.ptr = (void *)c->dst.ptr + + (c->src.val & mask) / 8; + } break; case DstAcc: c->dst.type = OP_REG; - c->dst.bytes = c->op_bytes; + c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; c->dst.ptr = &c->regs[VCPU_REGS_RAX]; - switch (c->op_bytes) { + switch (c->dst.bytes) { case 1: c->dst.val = *(u8 *)c->dst.ptr; break; @@ -1203,18 +1243,248 @@ done_prefixes: case 4: c->dst.val = *(u32 *)c->dst.ptr; break; + case 8: + c->dst.val = *(u64 *)c->dst.ptr; + break; } c->dst.orig_val = c->dst.val; break; + case DstDI: + c->dst.type = OP_MEM; + c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->dst.ptr = (unsigned long *) + register_address(c, es_base(ctxt), + c->regs[VCPU_REGS_RDI]); + c->dst.val = 0; + break; } - if (c->rip_relative) - c->modrm_ea += c->eip; - done: return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0; } +static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + unsigned int size, unsigned short port, + void *dest) +{ + struct read_cache *rc = &ctxt->decode.io_read; + + if (rc->pos == rc->end) { /* refill pio read ahead */ + struct decode_cache *c = &ctxt->decode; + unsigned int in_page, n; + unsigned int count = c->rep_prefix ? + address_mask(c, c->regs[VCPU_REGS_RCX]) : 1; + in_page = (ctxt->eflags & EFLG_DF) ? + offset_in_page(c->regs[VCPU_REGS_RDI]) : + PAGE_SIZE - offset_in_page(c->regs[VCPU_REGS_RDI]); + n = min(min(in_page, (unsigned int)sizeof(rc->data)) / size, + count); + if (n == 0) + n = 1; + rc->pos = rc->end = 0; + if (!ops->pio_in_emulated(size, port, rc->data, n, ctxt->vcpu)) + return 0; + rc->end = n * size; + } + + memcpy(dest, rc->data + rc->pos, size); + rc->pos += size; + return 1; +} + +static u32 desc_limit_scaled(struct desc_struct *desc) +{ + u32 limit = get_desc_limit(desc); + + return desc->g ? (limit << 12) | 0xfff : limit; +} + +static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 selector, struct desc_ptr *dt) +{ + if (selector & 1 << 2) { + struct desc_struct desc; + memset (dt, 0, sizeof *dt); + if (!ops->get_cached_descriptor(&desc, VCPU_SREG_LDTR, ctxt->vcpu)) + return; + + dt->size = desc_limit_scaled(&desc); /* what if limit > 65535? */ + dt->address = get_desc_base(&desc); + } else + ops->get_gdt(dt, ctxt->vcpu); +} + +/* allowed just for 8 bytes segments */ +static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 selector, struct desc_struct *desc) +{ + struct desc_ptr dt; + u16 index = selector >> 3; + int ret; + u32 err; + ulong addr; + + get_descriptor_table_ptr(ctxt, ops, selector, &dt); + + if (dt.size < index * 8 + 7) { + kvm_inject_gp(ctxt->vcpu, selector & 0xfffc); + return X86EMUL_PROPAGATE_FAULT; + } + addr = dt.address + index * 8; + ret = ops->read_std(addr, desc, sizeof *desc, ctxt->vcpu, &err); + if (ret == X86EMUL_PROPAGATE_FAULT) + kvm_inject_page_fault(ctxt->vcpu, addr, err); + + return ret; +} + +/* allowed just for 8 bytes segments */ +static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 selector, struct desc_struct *desc) +{ + struct desc_ptr dt; + u16 index = selector >> 3; + u32 err; + ulong addr; + int ret; + + get_descriptor_table_ptr(ctxt, ops, selector, &dt); + + if (dt.size < index * 8 + 7) { + kvm_inject_gp(ctxt->vcpu, selector & 0xfffc); + return X86EMUL_PROPAGATE_FAULT; + } + + addr = dt.address + index * 8; + ret = ops->write_std(addr, desc, sizeof *desc, ctxt->vcpu, &err); + if (ret == X86EMUL_PROPAGATE_FAULT) + kvm_inject_page_fault(ctxt->vcpu, addr, err); + + return ret; +} + +static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 selector, int seg) +{ + struct desc_struct seg_desc; + u8 dpl, rpl, cpl; + unsigned err_vec = GP_VECTOR; + u32 err_code = 0; + bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */ + int ret; + + memset(&seg_desc, 0, sizeof seg_desc); + + if ((seg <= VCPU_SREG_GS && ctxt->mode == X86EMUL_MODE_VM86) + || ctxt->mode == X86EMUL_MODE_REAL) { + /* set real mode segment descriptor */ + set_desc_base(&seg_desc, selector << 4); + set_desc_limit(&seg_desc, 0xffff); + seg_desc.type = 3; + seg_desc.p = 1; + seg_desc.s = 1; + goto load; + } + + /* NULL selector is not valid for TR, CS and SS */ + if ((seg == VCPU_SREG_CS || seg == VCPU_SREG_SS || seg == VCPU_SREG_TR) + && null_selector) + goto exception; + + /* TR should be in GDT only */ + if (seg == VCPU_SREG_TR && (selector & (1 << 2))) + goto exception; + + if (null_selector) /* for NULL selector skip all following checks */ + goto load; + + ret = read_segment_descriptor(ctxt, ops, selector, &seg_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + + err_code = selector & 0xfffc; + err_vec = GP_VECTOR; + + /* can't load system descriptor into segment selecor */ + if (seg <= VCPU_SREG_GS && !seg_desc.s) + goto exception; + + if (!seg_desc.p) { + err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR; + goto exception; + } + + rpl = selector & 3; + dpl = seg_desc.dpl; + cpl = ops->cpl(ctxt->vcpu); + + switch (seg) { + case VCPU_SREG_SS: + /* + * segment is not a writable data segment or segment + * selector's RPL != CPL or segment selector's RPL != CPL + */ + if (rpl != cpl || (seg_desc.type & 0xa) != 0x2 || dpl != cpl) + goto exception; + break; + case VCPU_SREG_CS: + if (!(seg_desc.type & 8)) + goto exception; + + if (seg_desc.type & 4) { + /* conforming */ + if (dpl > cpl) + goto exception; + } else { + /* nonconforming */ + if (rpl > cpl || dpl != cpl) + goto exception; + } + /* CS(RPL) <- CPL */ + selector = (selector & 0xfffc) | cpl; + break; + case VCPU_SREG_TR: + if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9)) + goto exception; + break; + case VCPU_SREG_LDTR: + if (seg_desc.s || seg_desc.type != 2) + goto exception; + break; + default: /* DS, ES, FS, or GS */ + /* + * segment is not a data or readable code segment or + * ((segment is a data or nonconforming code segment) + * and (both RPL and CPL > DPL)) + */ + if ((seg_desc.type & 0xa) == 0x8 || + (((seg_desc.type & 0xc) != 0xc) && + (rpl > dpl && cpl > dpl))) + goto exception; + break; + } + + if (seg_desc.s) { + /* mark segment as accessed */ + seg_desc.type |= 1; + ret = write_segment_descriptor(ctxt, ops, selector, &seg_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + } +load: + ops->set_segment_selector(selector, seg, ctxt->vcpu); + ops->set_cached_descriptor(&seg_desc, seg, ctxt->vcpu); + return X86EMUL_CONTINUE; +exception: + kvm_queue_exception_e(ctxt->vcpu, err_vec, err_code); + return X86EMUL_PROPAGATE_FAULT; +} + static inline void emulate_push(struct x86_emulate_ctxt *ctxt) { struct decode_cache *c = &ctxt->decode; @@ -1251,7 +1521,7 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt, int rc; unsigned long val, change_mask; int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; - int cpl = kvm_x86_ops->get_cpl(ctxt->vcpu); + int cpl = ops->cpl(ctxt->vcpu); rc = emulate_pop(ctxt, ops, &val, len); if (rc != X86EMUL_CONTINUE) @@ -1306,10 +1576,10 @@ static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, int rc; rc = emulate_pop(ctxt, ops, &selector, c->op_bytes); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) return rc; - rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)selector, seg); + rc = load_segment_descriptor(ctxt, ops, (u16)selector, seg); return rc; } @@ -1332,7 +1602,7 @@ static int emulate_popa(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc = 0; + int rc = X86EMUL_CONTINUE; int reg = VCPU_REGS_RDI; while (reg >= VCPU_REGS_RAX) { @@ -1343,7 +1613,7 @@ static int emulate_popa(struct x86_emulate_ctxt *ctxt, } rc = emulate_pop(ctxt, ops, &c->regs[reg], c->op_bytes); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) break; --reg; } @@ -1354,12 +1624,8 @@ static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc; - rc = emulate_pop(ctxt, ops, &c->dst.val, c->dst.bytes); - if (rc != 0) - return rc; - return 0; + return emulate_pop(ctxt, ops, &c->dst.val, c->dst.bytes); } static inline void emulate_grp2(struct x86_emulate_ctxt *ctxt) @@ -1395,7 +1661,6 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc = 0; switch (c->modrm_reg) { case 0 ... 1: /* test */ @@ -1408,11 +1673,9 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt, emulate_1op("neg", c->dst, ctxt->eflags); break; default: - DPRINTF("Cannot emulate %02x\n", c->b); - rc = X86EMUL_UNHANDLEABLE; - break; + return 0; } - return rc; + return 1; } static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt, @@ -1442,20 +1705,14 @@ static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt, emulate_push(ctxt); break; } - return 0; + return X86EMUL_CONTINUE; } static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops, - unsigned long memop) + struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - u64 old, new; - int rc; - - rc = ops->read_emulated(memop, &old, 8, ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - return rc; + u64 old = c->dst.orig_val; if (((u32) (old >> 0) != (u32) c->regs[VCPU_REGS_RAX]) || ((u32) (old >> 32) != (u32) c->regs[VCPU_REGS_RDX])) { @@ -1463,17 +1720,13 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt, c->regs[VCPU_REGS_RAX] = (u32) (old >> 0); c->regs[VCPU_REGS_RDX] = (u32) (old >> 32); ctxt->eflags &= ~EFLG_ZF; - } else { - new = ((u64)c->regs[VCPU_REGS_RCX] << 32) | + c->dst.val = ((u64)c->regs[VCPU_REGS_RCX] << 32) | (u32) c->regs[VCPU_REGS_RBX]; - rc = ops->cmpxchg_emulated(memop, &old, &new, 8, ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - return rc; ctxt->eflags |= EFLG_ZF; } - return 0; + return X86EMUL_CONTINUE; } static int emulate_ret_far(struct x86_emulate_ctxt *ctxt, @@ -1484,14 +1737,14 @@ static int emulate_ret_far(struct x86_emulate_ctxt *ctxt, unsigned long cs; rc = emulate_pop(ctxt, ops, &c->eip, c->op_bytes); - if (rc) + if (rc != X86EMUL_CONTINUE) return rc; if (c->op_bytes == 4) c->eip = (u32)c->eip; rc = emulate_pop(ctxt, ops, &cs, c->op_bytes); - if (rc) + if (rc != X86EMUL_CONTINUE) return rc; - rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)cs, VCPU_SREG_CS); + rc = load_segment_descriptor(ctxt, ops, (u16)cs, VCPU_SREG_CS); return rc; } @@ -1544,7 +1797,7 @@ static inline int writeback(struct x86_emulate_ctxt *ctxt, default: break; } - return 0; + return X86EMUL_CONTINUE; } static void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask) @@ -1598,8 +1851,11 @@ emulate_syscall(struct x86_emulate_ctxt *ctxt) u64 msr_data; /* syscall is not available in real mode */ - if (ctxt->mode == X86EMUL_MODE_REAL || ctxt->mode == X86EMUL_MODE_VM86) - return X86EMUL_UNHANDLEABLE; + if (ctxt->mode == X86EMUL_MODE_REAL || + ctxt->mode == X86EMUL_MODE_VM86) { + kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + return X86EMUL_PROPAGATE_FAULT; + } setup_syscalls_segments(ctxt, &cs, &ss); @@ -1649,14 +1905,16 @@ emulate_sysenter(struct x86_emulate_ctxt *ctxt) /* inject #GP if in real mode */ if (ctxt->mode == X86EMUL_MODE_REAL) { kvm_inject_gp(ctxt->vcpu, 0); - return X86EMUL_UNHANDLEABLE; + return X86EMUL_PROPAGATE_FAULT; } /* XXX sysenter/sysexit have not been tested in 64bit mode. * Therefore, we inject an #UD. */ - if (ctxt->mode == X86EMUL_MODE_PROT64) - return X86EMUL_UNHANDLEABLE; + if (ctxt->mode == X86EMUL_MODE_PROT64) { + kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + return X86EMUL_PROPAGATE_FAULT; + } setup_syscalls_segments(ctxt, &cs, &ss); @@ -1711,7 +1969,7 @@ emulate_sysexit(struct x86_emulate_ctxt *ctxt) if (ctxt->mode == X86EMUL_MODE_REAL || ctxt->mode == X86EMUL_MODE_VM86) { kvm_inject_gp(ctxt->vcpu, 0); - return X86EMUL_UNHANDLEABLE; + return X86EMUL_PROPAGATE_FAULT; } setup_syscalls_segments(ctxt, &cs, &ss); @@ -1756,7 +2014,8 @@ emulate_sysexit(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt) +static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) { int iopl; if (ctxt->mode == X86EMUL_MODE_REAL) @@ -1764,7 +2023,7 @@ static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt) if (ctxt->mode == X86EMUL_MODE_VM86) return true; iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; - return kvm_x86_ops->get_cpl(ctxt->vcpu) > iopl; + return ops->cpl(ctxt->vcpu) > iopl; } static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt, @@ -1801,22 +2060,419 @@ static bool emulator_io_permited(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, u16 port, u16 len) { - if (emulator_bad_iopl(ctxt)) + if (emulator_bad_iopl(ctxt, ops)) if (!emulator_io_port_access_allowed(ctxt, ops, port, len)) return false; return true; } +static u32 get_cached_descriptor_base(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + int seg) +{ + struct desc_struct desc; + if (ops->get_cached_descriptor(&desc, seg, ctxt->vcpu)) + return get_desc_base(&desc); + else + return ~0; +} + +static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + struct tss_segment_16 *tss) +{ + struct decode_cache *c = &ctxt->decode; + + tss->ip = c->eip; + tss->flag = ctxt->eflags; + tss->ax = c->regs[VCPU_REGS_RAX]; + tss->cx = c->regs[VCPU_REGS_RCX]; + tss->dx = c->regs[VCPU_REGS_RDX]; + tss->bx = c->regs[VCPU_REGS_RBX]; + tss->sp = c->regs[VCPU_REGS_RSP]; + tss->bp = c->regs[VCPU_REGS_RBP]; + tss->si = c->regs[VCPU_REGS_RSI]; + tss->di = c->regs[VCPU_REGS_RDI]; + + tss->es = ops->get_segment_selector(VCPU_SREG_ES, ctxt->vcpu); + tss->cs = ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu); + tss->ss = ops->get_segment_selector(VCPU_SREG_SS, ctxt->vcpu); + tss->ds = ops->get_segment_selector(VCPU_SREG_DS, ctxt->vcpu); + tss->ldt = ops->get_segment_selector(VCPU_SREG_LDTR, ctxt->vcpu); +} + +static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + struct tss_segment_16 *tss) +{ + struct decode_cache *c = &ctxt->decode; + int ret; + + c->eip = tss->ip; + ctxt->eflags = tss->flag | 2; + c->regs[VCPU_REGS_RAX] = tss->ax; + c->regs[VCPU_REGS_RCX] = tss->cx; + c->regs[VCPU_REGS_RDX] = tss->dx; + c->regs[VCPU_REGS_RBX] = tss->bx; + c->regs[VCPU_REGS_RSP] = tss->sp; + c->regs[VCPU_REGS_RBP] = tss->bp; + c->regs[VCPU_REGS_RSI] = tss->si; + c->regs[VCPU_REGS_RDI] = tss->di; + + /* + * SDM says that segment selectors are loaded before segment + * descriptors + */ + ops->set_segment_selector(tss->ldt, VCPU_SREG_LDTR, ctxt->vcpu); + ops->set_segment_selector(tss->es, VCPU_SREG_ES, ctxt->vcpu); + ops->set_segment_selector(tss->cs, VCPU_SREG_CS, ctxt->vcpu); + ops->set_segment_selector(tss->ss, VCPU_SREG_SS, ctxt->vcpu); + ops->set_segment_selector(tss->ds, VCPU_SREG_DS, ctxt->vcpu); + + /* + * Now load segment descriptors. If fault happenes at this stage + * it is handled in a context of new task + */ + ret = load_segment_descriptor(ctxt, ops, tss->ldt, VCPU_SREG_LDTR); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->es, VCPU_SREG_ES); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->cs, VCPU_SREG_CS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->ss, VCPU_SREG_SS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->ds, VCPU_SREG_DS); + if (ret != X86EMUL_CONTINUE) + return ret; + + return X86EMUL_CONTINUE; +} + +static int task_switch_16(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 tss_selector, u16 old_tss_sel, + ulong old_tss_base, struct desc_struct *new_desc) +{ + struct tss_segment_16 tss_seg; + int ret; + u32 err, new_tss_base = get_desc_base(new_desc); + + ret = ops->read_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err); + return ret; + } + + save_state_to_tss16(ctxt, ops, &tss_seg); + + ret = ops->write_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err); + return ret; + } + + ret = ops->read_std(new_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err); + return ret; + } + + if (old_tss_sel != 0xffff) { + tss_seg.prev_task_link = old_tss_sel; + + ret = ops->write_std(new_tss_base, + &tss_seg.prev_task_link, + sizeof tss_seg.prev_task_link, + ctxt->vcpu, &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err); + return ret; + } + } + + return load_state_from_tss16(ctxt, ops, &tss_seg); +} + +static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + struct tss_segment_32 *tss) +{ + struct decode_cache *c = &ctxt->decode; + + tss->cr3 = ops->get_cr(3, ctxt->vcpu); + tss->eip = c->eip; + tss->eflags = ctxt->eflags; + tss->eax = c->regs[VCPU_REGS_RAX]; + tss->ecx = c->regs[VCPU_REGS_RCX]; + tss->edx = c->regs[VCPU_REGS_RDX]; + tss->ebx = c->regs[VCPU_REGS_RBX]; + tss->esp = c->regs[VCPU_REGS_RSP]; + tss->ebp = c->regs[VCPU_REGS_RBP]; + tss->esi = c->regs[VCPU_REGS_RSI]; + tss->edi = c->regs[VCPU_REGS_RDI]; + + tss->es = ops->get_segment_selector(VCPU_SREG_ES, ctxt->vcpu); + tss->cs = ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu); + tss->ss = ops->get_segment_selector(VCPU_SREG_SS, ctxt->vcpu); + tss->ds = ops->get_segment_selector(VCPU_SREG_DS, ctxt->vcpu); + tss->fs = ops->get_segment_selector(VCPU_SREG_FS, ctxt->vcpu); + tss->gs = ops->get_segment_selector(VCPU_SREG_GS, ctxt->vcpu); + tss->ldt_selector = ops->get_segment_selector(VCPU_SREG_LDTR, ctxt->vcpu); +} + +static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + struct tss_segment_32 *tss) +{ + struct decode_cache *c = &ctxt->decode; + int ret; + + ops->set_cr(3, tss->cr3, ctxt->vcpu); + c->eip = tss->eip; + ctxt->eflags = tss->eflags | 2; + c->regs[VCPU_REGS_RAX] = tss->eax; + c->regs[VCPU_REGS_RCX] = tss->ecx; + c->regs[VCPU_REGS_RDX] = tss->edx; + c->regs[VCPU_REGS_RBX] = tss->ebx; + c->regs[VCPU_REGS_RSP] = tss->esp; + c->regs[VCPU_REGS_RBP] = tss->ebp; + c->regs[VCPU_REGS_RSI] = tss->esi; + c->regs[VCPU_REGS_RDI] = tss->edi; + + /* + * SDM says that segment selectors are loaded before segment + * descriptors + */ + ops->set_segment_selector(tss->ldt_selector, VCPU_SREG_LDTR, ctxt->vcpu); + ops->set_segment_selector(tss->es, VCPU_SREG_ES, ctxt->vcpu); + ops->set_segment_selector(tss->cs, VCPU_SREG_CS, ctxt->vcpu); + ops->set_segment_selector(tss->ss, VCPU_SREG_SS, ctxt->vcpu); + ops->set_segment_selector(tss->ds, VCPU_SREG_DS, ctxt->vcpu); + ops->set_segment_selector(tss->fs, VCPU_SREG_FS, ctxt->vcpu); + ops->set_segment_selector(tss->gs, VCPU_SREG_GS, ctxt->vcpu); + + /* + * Now load segment descriptors. If fault happenes at this stage + * it is handled in a context of new task + */ + ret = load_segment_descriptor(ctxt, ops, tss->ldt_selector, VCPU_SREG_LDTR); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->es, VCPU_SREG_ES); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->cs, VCPU_SREG_CS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->ss, VCPU_SREG_SS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->ds, VCPU_SREG_DS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->fs, VCPU_SREG_FS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->gs, VCPU_SREG_GS); + if (ret != X86EMUL_CONTINUE) + return ret; + + return X86EMUL_CONTINUE; +} + +static int task_switch_32(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 tss_selector, u16 old_tss_sel, + ulong old_tss_base, struct desc_struct *new_desc) +{ + struct tss_segment_32 tss_seg; + int ret; + u32 err, new_tss_base = get_desc_base(new_desc); + + ret = ops->read_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err); + return ret; + } + + save_state_to_tss32(ctxt, ops, &tss_seg); + + ret = ops->write_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err); + return ret; + } + + ret = ops->read_std(new_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err); + return ret; + } + + if (old_tss_sel != 0xffff) { + tss_seg.prev_task_link = old_tss_sel; + + ret = ops->write_std(new_tss_base, + &tss_seg.prev_task_link, + sizeof tss_seg.prev_task_link, + ctxt->vcpu, &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err); + return ret; + } + } + + return load_state_from_tss32(ctxt, ops, &tss_seg); +} + +static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 tss_selector, int reason, + bool has_error_code, u32 error_code) +{ + struct desc_struct curr_tss_desc, next_tss_desc; + int ret; + u16 old_tss_sel = ops->get_segment_selector(VCPU_SREG_TR, ctxt->vcpu); + ulong old_tss_base = + get_cached_descriptor_base(ctxt, ops, VCPU_SREG_TR); + u32 desc_limit; + + /* FIXME: old_tss_base == ~0 ? */ + + ret = read_segment_descriptor(ctxt, ops, tss_selector, &next_tss_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = read_segment_descriptor(ctxt, ops, old_tss_sel, &curr_tss_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + + /* FIXME: check that next_tss_desc is tss */ + + if (reason != TASK_SWITCH_IRET) { + if ((tss_selector & 3) > next_tss_desc.dpl || + ops->cpl(ctxt->vcpu) > next_tss_desc.dpl) { + kvm_inject_gp(ctxt->vcpu, 0); + return X86EMUL_PROPAGATE_FAULT; + } + } + + desc_limit = desc_limit_scaled(&next_tss_desc); + if (!next_tss_desc.p || + ((desc_limit < 0x67 && (next_tss_desc.type & 8)) || + desc_limit < 0x2b)) { + kvm_queue_exception_e(ctxt->vcpu, TS_VECTOR, + tss_selector & 0xfffc); + return X86EMUL_PROPAGATE_FAULT; + } + + if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) { + curr_tss_desc.type &= ~(1 << 1); /* clear busy flag */ + write_segment_descriptor(ctxt, ops, old_tss_sel, + &curr_tss_desc); + } + + if (reason == TASK_SWITCH_IRET) + ctxt->eflags = ctxt->eflags & ~X86_EFLAGS_NT; + + /* set back link to prev task only if NT bit is set in eflags + note that old_tss_sel is not used afetr this point */ + if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE) + old_tss_sel = 0xffff; + + if (next_tss_desc.type & 8) + ret = task_switch_32(ctxt, ops, tss_selector, old_tss_sel, + old_tss_base, &next_tss_desc); + else + ret = task_switch_16(ctxt, ops, tss_selector, old_tss_sel, + old_tss_base, &next_tss_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + + if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) + ctxt->eflags = ctxt->eflags | X86_EFLAGS_NT; + + if (reason != TASK_SWITCH_IRET) { + next_tss_desc.type |= (1 << 1); /* set busy flag */ + write_segment_descriptor(ctxt, ops, tss_selector, + &next_tss_desc); + } + + ops->set_cr(0, ops->get_cr(0, ctxt->vcpu) | X86_CR0_TS, ctxt->vcpu); + ops->set_cached_descriptor(&next_tss_desc, VCPU_SREG_TR, ctxt->vcpu); + ops->set_segment_selector(tss_selector, VCPU_SREG_TR, ctxt->vcpu); + + if (has_error_code) { + struct decode_cache *c = &ctxt->decode; + + c->op_bytes = c->ad_bytes = (next_tss_desc.type & 8) ? 4 : 2; + c->lock_prefix = 0; + c->src.val = (unsigned long) error_code; + emulate_push(ctxt); + } + + return ret; +} + +int emulator_task_switch(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 tss_selector, int reason, + bool has_error_code, u32 error_code) +{ + struct decode_cache *c = &ctxt->decode; + int rc; + + memset(c, 0, sizeof(struct decode_cache)); + c->eip = ctxt->eip; + memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs); + c->dst.type = OP_NONE; + + rc = emulator_do_task_switch(ctxt, ops, tss_selector, reason, + has_error_code, error_code); + + if (rc == X86EMUL_CONTINUE) { + memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs); + kvm_rip_write(ctxt->vcpu, c->eip); + rc = writeback(ctxt, ops); + } + + return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0; +} + +static void string_addr_inc(struct x86_emulate_ctxt *ctxt, unsigned long base, + int reg, struct operand *op) +{ + struct decode_cache *c = &ctxt->decode; + int df = (ctxt->eflags & EFLG_DF) ? -1 : 1; + + register_address_increment(c, &c->regs[reg], df * op->bytes); + op->ptr = (unsigned long *)register_address(c, base, c->regs[reg]); +} + int x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { - unsigned long memop = 0; u64 msr_data; - unsigned long saved_eip = 0; struct decode_cache *c = &ctxt->decode; - unsigned int port; - int io_dir_in; - int rc = 0; + int rc = X86EMUL_CONTINUE; + int saved_dst_type = c->dst.type; ctxt->interruptibility = 0; @@ -1826,26 +2482,30 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) */ memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs); - saved_eip = c->eip; + + if (ctxt->mode == X86EMUL_MODE_PROT64 && (c->d & No64)) { + kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + goto done; + } /* LOCK prefix is allowed only with some instructions */ - if (c->lock_prefix && !(c->d & Lock)) { + if (c->lock_prefix && (!(c->d & Lock) || c->dst.type != OP_MEM)) { kvm_queue_exception(ctxt->vcpu, UD_VECTOR); goto done; } /* Privileged instruction can be executed only in CPL=0 */ - if ((c->d & Priv) && kvm_x86_ops->get_cpl(ctxt->vcpu)) { + if ((c->d & Priv) && ops->cpl(ctxt->vcpu)) { kvm_inject_gp(ctxt->vcpu, 0); goto done; } - if (((c->d & ModRM) && (c->modrm_mod != 3)) || (c->d & MemAbs)) - memop = c->modrm_ea; - if (c->rep_prefix && (c->d & String)) { + ctxt->restart = true; /* All REP prefixes have the same first termination condition */ - if (c->regs[VCPU_REGS_RCX] == 0) { + if (address_mask(c, c->regs[VCPU_REGS_RCX]) == 0) { + string_done: + ctxt->restart = false; kvm_rip_write(ctxt->vcpu, c->eip); goto done; } @@ -1857,25 +2517,18 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) * - if REPNE/REPNZ and ZF = 1 then done */ if ((c->b == 0xa6) || (c->b == 0xa7) || - (c->b == 0xae) || (c->b == 0xaf)) { + (c->b == 0xae) || (c->b == 0xaf)) { if ((c->rep_prefix == REPE_PREFIX) && - ((ctxt->eflags & EFLG_ZF) == 0)) { - kvm_rip_write(ctxt->vcpu, c->eip); - goto done; - } + ((ctxt->eflags & EFLG_ZF) == 0)) + goto string_done; if ((c->rep_prefix == REPNE_PREFIX) && - ((ctxt->eflags & EFLG_ZF) == EFLG_ZF)) { - kvm_rip_write(ctxt->vcpu, c->eip); - goto done; - } + ((ctxt->eflags & EFLG_ZF) == EFLG_ZF)) + goto string_done; } - c->regs[VCPU_REGS_RCX]--; - c->eip = kvm_rip_read(ctxt->vcpu); + c->eip = ctxt->eip; } if (c->src.type == OP_MEM) { - c->src.ptr = (unsigned long *)memop; - c->src.val = 0; rc = ops->read_emulated((unsigned long)c->src.ptr, &c->src.val, c->src.bytes, @@ -1885,29 +2538,25 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) c->src.orig_val = c->src.val; } + if (c->src2.type == OP_MEM) { + rc = ops->read_emulated((unsigned long)c->src2.ptr, + &c->src2.val, + c->src2.bytes, + ctxt->vcpu); + if (rc != X86EMUL_CONTINUE) + goto done; + } + if ((c->d & DstMask) == ImplicitOps) goto special_insn; - if (c->dst.type == OP_MEM) { - c->dst.ptr = (unsigned long *)memop; - c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->dst.val = 0; - if (c->d & BitOp) { - unsigned long mask = ~(c->dst.bytes * 8 - 1); - - c->dst.ptr = (void *)c->dst.ptr + - (c->src.val & mask) / 8; - } - if (!(c->d & Mov)) { - /* optimisation - avoid slow emulated read */ - rc = ops->read_emulated((unsigned long)c->dst.ptr, - &c->dst.val, - c->dst.bytes, - ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - goto done; - } + if ((c->dst.type == OP_MEM) && !(c->d & Mov)) { + /* optimisation - avoid slow emulated read if Mov */ + rc = ops->read_emulated((unsigned long)c->dst.ptr, &c->dst.val, + c->dst.bytes, ctxt->vcpu); + if (rc != X86EMUL_CONTINUE) + goto done; } c->dst.orig_val = c->dst.val; @@ -1926,7 +2575,7 @@ special_insn: break; case 0x07: /* pop es */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_ES); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0x08 ... 0x0d: @@ -1945,7 +2594,7 @@ special_insn: break; case 0x17: /* pop ss */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_SS); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0x18 ... 0x1d: @@ -1957,7 +2606,7 @@ special_insn: break; case 0x1f: /* pop ds */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_DS); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0x20 ... 0x25: @@ -1988,7 +2637,7 @@ special_insn: case 0x58 ... 0x5f: /* pop reg */ pop_instruction: rc = emulate_pop(ctxt, ops, &c->dst.val, c->op_bytes); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0x60: /* pusha */ @@ -1996,7 +2645,7 @@ special_insn: break; case 0x61: /* popa */ rc = emulate_popa(ctxt, ops); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0x63: /* movsxd */ @@ -2010,47 +2659,29 @@ special_insn: break; case 0x6c: /* insb */ case 0x6d: /* insw/insd */ + c->dst.bytes = min(c->dst.bytes, 4u); if (!emulator_io_permited(ctxt, ops, c->regs[VCPU_REGS_RDX], - (c->d & ByteOp) ? 1 : c->op_bytes)) { + c->dst.bytes)) { kvm_inject_gp(ctxt->vcpu, 0); goto done; } - if (kvm_emulate_pio_string(ctxt->vcpu, - 1, - (c->d & ByteOp) ? 1 : c->op_bytes, - c->rep_prefix ? - address_mask(c, c->regs[VCPU_REGS_RCX]) : 1, - (ctxt->eflags & EFLG_DF), - register_address(c, es_base(ctxt), - c->regs[VCPU_REGS_RDI]), - c->rep_prefix, - c->regs[VCPU_REGS_RDX]) == 0) { - c->eip = saved_eip; - return -1; - } - return 0; + if (!pio_in_emulated(ctxt, ops, c->dst.bytes, + c->regs[VCPU_REGS_RDX], &c->dst.val)) + goto done; /* IO is needed, skip writeback */ + break; case 0x6e: /* outsb */ case 0x6f: /* outsw/outsd */ + c->src.bytes = min(c->src.bytes, 4u); if (!emulator_io_permited(ctxt, ops, c->regs[VCPU_REGS_RDX], - (c->d & ByteOp) ? 1 : c->op_bytes)) { + c->src.bytes)) { kvm_inject_gp(ctxt->vcpu, 0); goto done; } - if (kvm_emulate_pio_string(ctxt->vcpu, - 0, - (c->d & ByteOp) ? 1 : c->op_bytes, - c->rep_prefix ? - address_mask(c, c->regs[VCPU_REGS_RCX]) : 1, - (ctxt->eflags & EFLG_DF), - register_address(c, - seg_override_base(ctxt, c), - c->regs[VCPU_REGS_RSI]), - c->rep_prefix, - c->regs[VCPU_REGS_RDX]) == 0) { - c->eip = saved_eip; - return -1; - } - return 0; + ops->pio_out_emulated(c->src.bytes, c->regs[VCPU_REGS_RDX], + &c->src.val, 1, ctxt->vcpu); + + c->dst.type = OP_NONE; /* nothing to writeback */ + break; case 0x70 ... 0x7f: /* jcc (short) */ if (test_cc(c->b, ctxt->eflags)) jmp_rel(c, c->src.val); @@ -2107,12 +2738,11 @@ special_insn: case 0x8c: { /* mov r/m, sreg */ struct kvm_segment segreg; - if (c->modrm_reg <= 5) + if (c->modrm_reg <= VCPU_SREG_GS) kvm_get_segment(ctxt->vcpu, &segreg, c->modrm_reg); else { - printk(KERN_INFO "0x8c: Invalid segreg in modrm byte 0x%02x\n", - c->modrm); - goto cannot_emulate; + kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + goto done; } c->dst.val = segreg.selector; break; @@ -2132,16 +2762,16 @@ special_insn: } if (c->modrm_reg == VCPU_SREG_SS) - toggle_interruptibility(ctxt, X86_SHADOW_INT_MOV_SS); + toggle_interruptibility(ctxt, KVM_X86_SHADOW_INT_MOV_SS); - rc = kvm_load_segment_descriptor(ctxt->vcpu, sel, c->modrm_reg); + rc = load_segment_descriptor(ctxt, ops, sel, c->modrm_reg); c->dst.type = OP_NONE; /* Disable writeback. */ break; } case 0x8f: /* pop (sole member of Grp1a) */ rc = emulate_grp1a(ctxt, ops); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0x90: /* nop / xchg r8,rax */ @@ -2175,89 +2805,16 @@ special_insn: c->dst.val = (unsigned long)c->regs[VCPU_REGS_RAX]; break; case 0xa4 ... 0xa5: /* movs */ - c->dst.type = OP_MEM; - c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->dst.ptr = (unsigned long *)register_address(c, - es_base(ctxt), - c->regs[VCPU_REGS_RDI]); - rc = ops->read_emulated(register_address(c, - seg_override_base(ctxt, c), - c->regs[VCPU_REGS_RSI]), - &c->dst.val, - c->dst.bytes, ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - goto done; - register_address_increment(c, &c->regs[VCPU_REGS_RSI], - (ctxt->eflags & EFLG_DF) ? -c->dst.bytes - : c->dst.bytes); - register_address_increment(c, &c->regs[VCPU_REGS_RDI], - (ctxt->eflags & EFLG_DF) ? -c->dst.bytes - : c->dst.bytes); - break; + goto mov; case 0xa6 ... 0xa7: /* cmps */ - c->src.type = OP_NONE; /* Disable writeback. */ - c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->src.ptr = (unsigned long *)register_address(c, - seg_override_base(ctxt, c), - c->regs[VCPU_REGS_RSI]); - rc = ops->read_emulated((unsigned long)c->src.ptr, - &c->src.val, - c->src.bytes, - ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - goto done; - c->dst.type = OP_NONE; /* Disable writeback. */ - c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->dst.ptr = (unsigned long *)register_address(c, - es_base(ctxt), - c->regs[VCPU_REGS_RDI]); - rc = ops->read_emulated((unsigned long)c->dst.ptr, - &c->dst.val, - c->dst.bytes, - ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - goto done; - DPRINTF("cmps: mem1=0x%p mem2=0x%p\n", c->src.ptr, c->dst.ptr); - - emulate_2op_SrcV("cmp", c->src, c->dst, ctxt->eflags); - - register_address_increment(c, &c->regs[VCPU_REGS_RSI], - (ctxt->eflags & EFLG_DF) ? -c->src.bytes - : c->src.bytes); - register_address_increment(c, &c->regs[VCPU_REGS_RDI], - (ctxt->eflags & EFLG_DF) ? -c->dst.bytes - : c->dst.bytes); - - break; + goto cmp; case 0xaa ... 0xab: /* stos */ - c->dst.type = OP_MEM; - c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->dst.ptr = (unsigned long *)register_address(c, - es_base(ctxt), - c->regs[VCPU_REGS_RDI]); c->dst.val = c->regs[VCPU_REGS_RAX]; - register_address_increment(c, &c->regs[VCPU_REGS_RDI], - (ctxt->eflags & EFLG_DF) ? -c->dst.bytes - : c->dst.bytes); break; case 0xac ... 0xad: /* lods */ - c->dst.type = OP_REG; - c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->dst.ptr = (unsigned long *)&c->regs[VCPU_REGS_RAX]; - rc = ops->read_emulated(register_address(c, - seg_override_base(ctxt, c), - c->regs[VCPU_REGS_RSI]), - &c->dst.val, - c->dst.bytes, - ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - goto done; - register_address_increment(c, &c->regs[VCPU_REGS_RSI], - (ctxt->eflags & EFLG_DF) ? -c->dst.bytes - : c->dst.bytes); - break; + goto mov; case 0xae ... 0xaf: /* scas */ DPRINTF("Urk! I don't handle SCAS.\n"); goto cannot_emulate; @@ -2277,7 +2834,7 @@ special_insn: break; case 0xcb: /* ret far */ rc = emulate_ret_far(ctxt, ops); - if (rc) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0xd0 ... 0xd1: /* Grp2 */ @@ -2290,14 +2847,10 @@ special_insn: break; case 0xe4: /* inb */ case 0xe5: /* in */ - port = c->src.val; - io_dir_in = 1; - goto do_io; + goto do_io_in; case 0xe6: /* outb */ case 0xe7: /* out */ - port = c->src.val; - io_dir_in = 0; - goto do_io; + goto do_io_out; case 0xe8: /* call (near) */ { long int rel = c->src.val; c->src.val = (unsigned long) c->eip; @@ -2308,8 +2861,9 @@ special_insn: case 0xe9: /* jmp rel */ goto jmp; case 0xea: /* jmp far */ - if (kvm_load_segment_descriptor(ctxt->vcpu, c->src2.val, - VCPU_SREG_CS)) + jump_far: + if (load_segment_descriptor(ctxt, ops, c->src2.val, + VCPU_SREG_CS)) goto done; c->eip = c->src.val; @@ -2321,25 +2875,29 @@ special_insn: break; case 0xec: /* in al,dx */ case 0xed: /* in (e/r)ax,dx */ - port = c->regs[VCPU_REGS_RDX]; - io_dir_in = 1; - goto do_io; + c->src.val = c->regs[VCPU_REGS_RDX]; + do_io_in: + c->dst.bytes = min(c->dst.bytes, 4u); + if (!emulator_io_permited(ctxt, ops, c->src.val, c->dst.bytes)) { + kvm_inject_gp(ctxt->vcpu, 0); + goto done; + } + if (!pio_in_emulated(ctxt, ops, c->dst.bytes, c->src.val, + &c->dst.val)) + goto done; /* IO is needed */ + break; case 0xee: /* out al,dx */ case 0xef: /* out (e/r)ax,dx */ - port = c->regs[VCPU_REGS_RDX]; - io_dir_in = 0; - do_io: - if (!emulator_io_permited(ctxt, ops, port, - (c->d & ByteOp) ? 1 : c->op_bytes)) { + c->src.val = c->regs[VCPU_REGS_RDX]; + do_io_out: + c->dst.bytes = min(c->dst.bytes, 4u); + if (!emulator_io_permited(ctxt, ops, c->src.val, c->dst.bytes)) { kvm_inject_gp(ctxt->vcpu, 0); goto done; } - if (kvm_emulate_pio(ctxt->vcpu, io_dir_in, - (c->d & ByteOp) ? 1 : c->op_bytes, - port) != 0) { - c->eip = saved_eip; - goto cannot_emulate; - } + ops->pio_out_emulated(c->dst.bytes, c->src.val, &c->dst.val, 1, + ctxt->vcpu); + c->dst.type = OP_NONE; /* Disable writeback. */ break; case 0xf4: /* hlt */ ctxt->vcpu->arch.halt_request = 1; @@ -2350,16 +2908,15 @@ special_insn: c->dst.type = OP_NONE; /* Disable writeback. */ break; case 0xf6 ... 0xf7: /* Grp3 */ - rc = emulate_grp3(ctxt, ops); - if (rc != 0) - goto done; + if (!emulate_grp3(ctxt, ops)) + goto cannot_emulate; break; case 0xf8: /* clc */ ctxt->eflags &= ~EFLG_CF; c->dst.type = OP_NONE; /* Disable writeback. */ break; case 0xfa: /* cli */ - if (emulator_bad_iopl(ctxt)) + if (emulator_bad_iopl(ctxt, ops)) kvm_inject_gp(ctxt->vcpu, 0); else { ctxt->eflags &= ~X86_EFLAGS_IF; @@ -2367,10 +2924,10 @@ special_insn: } break; case 0xfb: /* sti */ - if (emulator_bad_iopl(ctxt)) + if (emulator_bad_iopl(ctxt, ops)) kvm_inject_gp(ctxt->vcpu, 0); else { - toggle_interruptibility(ctxt, X86_SHADOW_INT_STI); + toggle_interruptibility(ctxt, KVM_X86_SHADOW_INT_STI); ctxt->eflags |= X86_EFLAGS_IF; c->dst.type = OP_NONE; /* Disable writeback. */ } @@ -2383,28 +2940,55 @@ special_insn: ctxt->eflags |= EFLG_DF; c->dst.type = OP_NONE; /* Disable writeback. */ break; - case 0xfe ... 0xff: /* Grp4/Grp5 */ + case 0xfe: /* Grp4 */ + grp45: rc = emulate_grp45(ctxt, ops); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; + case 0xff: /* Grp5 */ + if (c->modrm_reg == 5) + goto jump_far; + goto grp45; } writeback: rc = writeback(ctxt, ops); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; + /* + * restore dst type in case the decoding will be reused + * (happens for string instruction ) + */ + c->dst.type = saved_dst_type; + + if ((c->d & SrcMask) == SrcSI) + string_addr_inc(ctxt, seg_override_base(ctxt, c), VCPU_REGS_RSI, + &c->src); + + if ((c->d & DstMask) == DstDI) + string_addr_inc(ctxt, es_base(ctxt), VCPU_REGS_RDI, &c->dst); + + if (c->rep_prefix && (c->d & String)) { + struct read_cache *rc = &ctxt->decode.io_read; + register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1); + /* + * Re-enter guest when pio read ahead buffer is empty or, + * if it is not used, after each 1024 iteration. + */ + if ((rc->end == 0 && !(c->regs[VCPU_REGS_RCX] & 0x3ff)) || + (rc->end != 0 && rc->end == rc->pos)) + ctxt->restart = false; + } + /* Commit shadow register state. */ memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs); kvm_rip_write(ctxt->vcpu, c->eip); + ops->set_rflags(ctxt->vcpu, ctxt->eflags); done: - if (rc == X86EMUL_UNHANDLEABLE) { - c->eip = saved_eip; - return -1; - } - return 0; + return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0; twobyte_insn: switch (c->b) { @@ -2418,18 +3002,18 @@ twobyte_insn: goto cannot_emulate; rc = kvm_fix_hypercall(ctxt->vcpu); - if (rc) + if (rc != X86EMUL_CONTINUE) goto done; /* Let the processor re-execute the fixed hypercall */ - c->eip = kvm_rip_read(ctxt->vcpu); + c->eip = ctxt->eip; /* Disable writeback. */ c->dst.type = OP_NONE; break; case 2: /* lgdt */ rc = read_descriptor(ctxt, ops, c->src.ptr, &size, &address, c->op_bytes); - if (rc) + if (rc != X86EMUL_CONTINUE) goto done; realmode_lgdt(ctxt->vcpu, size, address); /* Disable writeback. */ @@ -2440,7 +3024,7 @@ twobyte_insn: switch (c->modrm_rm) { case 1: rc = kvm_fix_hypercall(ctxt->vcpu); - if (rc) + if (rc != X86EMUL_CONTINUE) goto done; break; default: @@ -2450,7 +3034,7 @@ twobyte_insn: rc = read_descriptor(ctxt, ops, c->src.ptr, &size, &address, c->op_bytes); - if (rc) + if (rc != X86EMUL_CONTINUE) goto done; realmode_lidt(ctxt->vcpu, size, address); } @@ -2459,15 +3043,18 @@ twobyte_insn: break; case 4: /* smsw */ c->dst.bytes = 2; - c->dst.val = realmode_get_cr(ctxt->vcpu, 0); + c->dst.val = ops->get_cr(0, ctxt->vcpu); break; case 6: /* lmsw */ - realmode_lmsw(ctxt->vcpu, (u16)c->src.val, - &ctxt->eflags); + ops->set_cr(0, (ops->get_cr(0, ctxt->vcpu) & ~0x0ful) | + (c->src.val & 0x0f), ctxt->vcpu); c->dst.type = OP_NONE; break; + case 5: /* not defined */ + kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + goto done; case 7: /* invlpg*/ - emulate_invlpg(ctxt->vcpu, memop); + emulate_invlpg(ctxt->vcpu, c->modrm_ea); /* Disable writeback. */ c->dst.type = OP_NONE; break; @@ -2493,54 +3080,54 @@ twobyte_insn: c->dst.type = OP_NONE; break; case 0x20: /* mov cr, reg */ - if (c->modrm_mod != 3) - goto cannot_emulate; - c->regs[c->modrm_rm] = - realmode_get_cr(ctxt->vcpu, c->modrm_reg); + switch (c->modrm_reg) { + case 1: + case 5 ... 7: + case 9 ... 15: + kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + goto done; + } + c->regs[c->modrm_rm] = ops->get_cr(c->modrm_reg, ctxt->vcpu); c->dst.type = OP_NONE; /* no writeback */ break; case 0x21: /* mov from dr to reg */ - if (c->modrm_mod != 3) - goto cannot_emulate; - rc = emulator_get_dr(ctxt, c->modrm_reg, &c->regs[c->modrm_rm]); - if (rc) - goto cannot_emulate; + if ((ops->get_cr(4, ctxt->vcpu) & X86_CR4_DE) && + (c->modrm_reg == 4 || c->modrm_reg == 5)) { + kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + goto done; + } + emulator_get_dr(ctxt, c->modrm_reg, &c->regs[c->modrm_rm]); c->dst.type = OP_NONE; /* no writeback */ break; case 0x22: /* mov reg, cr */ - if (c->modrm_mod != 3) - goto cannot_emulate; - realmode_set_cr(ctxt->vcpu, - c->modrm_reg, c->modrm_val, &ctxt->eflags); + ops->set_cr(c->modrm_reg, c->modrm_val, ctxt->vcpu); c->dst.type = OP_NONE; break; case 0x23: /* mov from reg to dr */ - if (c->modrm_mod != 3) - goto cannot_emulate; - rc = emulator_set_dr(ctxt, c->modrm_reg, - c->regs[c->modrm_rm]); - if (rc) - goto cannot_emulate; + if ((ops->get_cr(4, ctxt->vcpu) & X86_CR4_DE) && + (c->modrm_reg == 4 || c->modrm_reg == 5)) { + kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + goto done; + } + emulator_set_dr(ctxt, c->modrm_reg, c->regs[c->modrm_rm]); c->dst.type = OP_NONE; /* no writeback */ break; case 0x30: /* wrmsr */ msr_data = (u32)c->regs[VCPU_REGS_RAX] | ((u64)c->regs[VCPU_REGS_RDX] << 32); - rc = kvm_set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data); - if (rc) { + if (kvm_set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data)) { kvm_inject_gp(ctxt->vcpu, 0); - c->eip = kvm_rip_read(ctxt->vcpu); + goto done; } rc = X86EMUL_CONTINUE; c->dst.type = OP_NONE; break; case 0x32: /* rdmsr */ - rc = kvm_get_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], &msr_data); - if (rc) { + if (kvm_get_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], &msr_data)) { kvm_inject_gp(ctxt->vcpu, 0); - c->eip = kvm_rip_read(ctxt->vcpu); + goto done; } else { c->regs[VCPU_REGS_RAX] = (u32)msr_data; c->regs[VCPU_REGS_RDX] = msr_data >> 32; @@ -2577,7 +3164,7 @@ twobyte_insn: break; case 0xa1: /* pop fs */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_FS); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0xa3: @@ -2596,7 +3183,7 @@ twobyte_insn: break; case 0xa9: /* pop gs */ rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_GS); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) goto done; break; case 0xab: @@ -2668,16 +3255,14 @@ twobyte_insn: (u64) c->src.val; break; case 0xc7: /* Grp9 (cmpxchg8b) */ - rc = emulate_grp9(ctxt, ops, memop); - if (rc != 0) + rc = emulate_grp9(ctxt, ops); + if (rc != X86EMUL_CONTINUE) goto done; - c->dst.type = OP_NONE; break; } goto writeback; cannot_emulate: DPRINTF("Cannot emulate %02x\n", c->b); - c->eip = saved_eip; return -1; } diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index a790fa128a9f..93825ff3338f 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -33,6 +33,29 @@ #include <linux/kvm_host.h> #include "trace.h" +static void pic_lock(struct kvm_pic *s) + __acquires(&s->lock) +{ + raw_spin_lock(&s->lock); +} + +static void pic_unlock(struct kvm_pic *s) + __releases(&s->lock) +{ + bool wakeup = s->wakeup_needed; + struct kvm_vcpu *vcpu; + + s->wakeup_needed = false; + + raw_spin_unlock(&s->lock); + + if (wakeup) { + vcpu = s->kvm->bsp_vcpu; + if (vcpu) + kvm_vcpu_kick(vcpu); + } +} + static void pic_clear_isr(struct kvm_kpic_state *s, int irq) { s->isr &= ~(1 << irq); @@ -45,19 +68,19 @@ static void pic_clear_isr(struct kvm_kpic_state *s, int irq) * Other interrupt may be delivered to PIC while lock is dropped but * it should be safe since PIC state is already updated at this stage. */ - raw_spin_unlock(&s->pics_state->lock); + pic_unlock(s->pics_state); kvm_notify_acked_irq(s->pics_state->kvm, SELECT_PIC(irq), irq); - raw_spin_lock(&s->pics_state->lock); + pic_lock(s->pics_state); } void kvm_pic_clear_isr_ack(struct kvm *kvm) { struct kvm_pic *s = pic_irqchip(kvm); - raw_spin_lock(&s->lock); + pic_lock(s); s->pics[0].isr_ack = 0xff; s->pics[1].isr_ack = 0xff; - raw_spin_unlock(&s->lock); + pic_unlock(s); } /* @@ -158,9 +181,9 @@ static void pic_update_irq(struct kvm_pic *s) void kvm_pic_update_irq(struct kvm_pic *s) { - raw_spin_lock(&s->lock); + pic_lock(s); pic_update_irq(s); - raw_spin_unlock(&s->lock); + pic_unlock(s); } int kvm_pic_set_irq(void *opaque, int irq, int level) @@ -168,14 +191,14 @@ int kvm_pic_set_irq(void *opaque, int irq, int level) struct kvm_pic *s = opaque; int ret = -1; - raw_spin_lock(&s->lock); + pic_lock(s); if (irq >= 0 && irq < PIC_NUM_PINS) { ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level); pic_update_irq(s); trace_kvm_pic_set_irq(irq >> 3, irq & 7, s->pics[irq >> 3].elcr, s->pics[irq >> 3].imr, ret == 0); } - raw_spin_unlock(&s->lock); + pic_unlock(s); return ret; } @@ -205,7 +228,7 @@ int kvm_pic_read_irq(struct kvm *kvm) int irq, irq2, intno; struct kvm_pic *s = pic_irqchip(kvm); - raw_spin_lock(&s->lock); + pic_lock(s); irq = pic_get_irq(&s->pics[0]); if (irq >= 0) { pic_intack(&s->pics[0], irq); @@ -230,7 +253,7 @@ int kvm_pic_read_irq(struct kvm *kvm) intno = s->pics[0].irq_base + irq; } pic_update_irq(s); - raw_spin_unlock(&s->lock); + pic_unlock(s); return intno; } @@ -444,7 +467,7 @@ static int picdev_write(struct kvm_io_device *this, printk(KERN_ERR "PIC: non byte write\n"); return 0; } - raw_spin_lock(&s->lock); + pic_lock(s); switch (addr) { case 0x20: case 0x21: @@ -457,7 +480,7 @@ static int picdev_write(struct kvm_io_device *this, elcr_ioport_write(&s->pics[addr & 1], addr, data); break; } - raw_spin_unlock(&s->lock); + pic_unlock(s); return 0; } @@ -474,7 +497,7 @@ static int picdev_read(struct kvm_io_device *this, printk(KERN_ERR "PIC: non byte read\n"); return 0; } - raw_spin_lock(&s->lock); + pic_lock(s); switch (addr) { case 0x20: case 0x21: @@ -488,7 +511,7 @@ static int picdev_read(struct kvm_io_device *this, break; } *(unsigned char *)val = data; - raw_spin_unlock(&s->lock); + pic_unlock(s); return 0; } @@ -505,7 +528,7 @@ static void pic_irq_request(void *opaque, int level) s->output = level; if (vcpu && level && (s->pics[0].isr_ack & (1 << irq))) { s->pics[0].isr_ack &= ~(1 << irq); - kvm_vcpu_kick(vcpu); + s->wakeup_needed = true; } } diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 34b15915754d..cd1f362f413d 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -63,6 +63,7 @@ struct kvm_kpic_state { struct kvm_pic { raw_spinlock_t lock; + bool wakeup_needed; unsigned pending_acks; struct kvm *kvm; struct kvm_kpic_state pics[2]; /* 0 is master pic, 1 is slave pic */ diff --git a/arch/x86/kvm/kvm_timer.h b/arch/x86/kvm/kvm_timer.h index 55c7524dda54..64bc6ea78d90 100644 --- a/arch/x86/kvm/kvm_timer.h +++ b/arch/x86/kvm/kvm_timer.h @@ -10,9 +10,7 @@ struct kvm_timer { }; struct kvm_timer_ops { - bool (*is_periodic)(struct kvm_timer *); + bool (*is_periodic)(struct kvm_timer *); }; - enum hrtimer_restart kvm_timer_fn(struct hrtimer *data); - diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 19a8906bcaa2..ddfa8658fb6d 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -148,7 +148,6 @@ module_param(oos_shadow, bool, 0644); #include <trace/events/kvm.h> -#undef TRACE_INCLUDE_FILE #define CREATE_TRACE_POINTS #include "mmutrace.h" @@ -174,12 +173,7 @@ struct kvm_shadow_walk_iterator { shadow_walk_okay(&(_walker)); \ shadow_walk_next(&(_walker))) - -struct kvm_unsync_walk { - int (*entry) (struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk); -}; - -typedef int (*mmu_parent_walk_fn) (struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp); +typedef int (*mmu_parent_walk_fn) (struct kvm_mmu_page *sp); static struct kmem_cache *pte_chain_cache; static struct kmem_cache *rmap_desc_cache; @@ -327,7 +321,6 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache, page = alloc_page(GFP_KERNEL); if (!page) return -ENOMEM; - set_page_private(page, 0); cache->objects[cache->nobjs++] = page_address(page); } return 0; @@ -438,9 +431,9 @@ static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn) int i; gfn = unalias_gfn(kvm, gfn); + slot = gfn_to_memslot_unaliased(kvm, gfn); for (i = PT_DIRECTORY_LEVEL; i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { - slot = gfn_to_memslot_unaliased(kvm, gfn); write_count = slot_largepage_idx(gfn, slot, i); *write_count -= 1; WARN_ON(*write_count < 0); @@ -654,7 +647,6 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte) { struct kvm_rmap_desc *desc; - struct kvm_rmap_desc *prev_desc; u64 *prev_spte; int i; @@ -666,7 +658,6 @@ static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte) return NULL; } desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul); - prev_desc = NULL; prev_spte = NULL; while (desc) { for (i = 0; i < RMAP_EXT && desc->sptes[i]; ++i) { @@ -794,7 +785,7 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, int retval = 0; struct kvm_memslots *slots; - slots = rcu_dereference(kvm->memslots); + slots = kvm_memslots(kvm); for (i = 0; i < slots->nmemslots; i++) { struct kvm_memory_slot *memslot = &slots->memslots[i]; @@ -925,7 +916,6 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); - INIT_LIST_HEAD(&sp->oos_link); bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS); sp->multimapped = 0; sp->parent_pte = parent_pte; @@ -1009,8 +999,7 @@ static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp, } -static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - mmu_parent_walk_fn fn) +static void mmu_parent_walk(struct kvm_mmu_page *sp, mmu_parent_walk_fn fn) { struct kvm_pte_chain *pte_chain; struct hlist_node *node; @@ -1019,8 +1008,8 @@ static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, if (!sp->multimapped && sp->parent_pte) { parent_sp = page_header(__pa(sp->parent_pte)); - fn(vcpu, parent_sp); - mmu_parent_walk(vcpu, parent_sp, fn); + fn(parent_sp); + mmu_parent_walk(parent_sp, fn); return; } hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link) @@ -1028,8 +1017,8 @@ static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, if (!pte_chain->parent_ptes[i]) break; parent_sp = page_header(__pa(pte_chain->parent_ptes[i])); - fn(vcpu, parent_sp); - mmu_parent_walk(vcpu, parent_sp, fn); + fn(parent_sp); + mmu_parent_walk(parent_sp, fn); } } @@ -1066,16 +1055,15 @@ static void kvm_mmu_update_parents_unsync(struct kvm_mmu_page *sp) } } -static int unsync_walk_fn(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +static int unsync_walk_fn(struct kvm_mmu_page *sp) { kvm_mmu_update_parents_unsync(sp); return 1; } -static void kvm_mmu_mark_parents_unsync(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp) +static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp) { - mmu_parent_walk(vcpu, sp, unsync_walk_fn); + mmu_parent_walk(sp, unsync_walk_fn); kvm_mmu_update_parents_unsync(sp); } @@ -1209,7 +1197,7 @@ static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp); static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { - if (sp->role.glevels != vcpu->arch.mmu.root_level) { + if (sp->role.cr4_pae != !!is_pae(vcpu)) { kvm_mmu_zap_page(vcpu->kvm, sp); return 1; } @@ -1331,6 +1319,8 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, role = vcpu->arch.mmu.base_role; role.level = level; role.direct = direct; + if (role.direct) + role.cr4_pae = 0; role.access = access; if (vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) { quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level)); @@ -1351,7 +1341,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, mmu_page_add_parent_pte(vcpu, sp, parent_pte); if (sp->unsync_children) { set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests); - kvm_mmu_mark_parents_unsync(vcpu, sp); + kvm_mmu_mark_parents_unsync(sp); } trace_kvm_mmu_get_page(sp, false); return sp; @@ -1573,13 +1563,14 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) r = 0; index = kvm_page_table_hashfn(gfn); bucket = &kvm->arch.mmu_page_hash[index]; +restart: hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) if (sp->gfn == gfn && !sp->role.direct) { pgprintk("%s: gfn %lx role %x\n", __func__, gfn, sp->role.word); r = 1; if (kvm_mmu_zap_page(kvm, sp)) - n = bucket->first; + goto restart; } return r; } @@ -1593,13 +1584,14 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn) index = kvm_page_table_hashfn(gfn); bucket = &kvm->arch.mmu_page_hash[index]; +restart: hlist_for_each_entry_safe(sp, node, nn, bucket, hash_link) { if (sp->gfn == gfn && !sp->role.direct && !sp->role.invalid) { pgprintk("%s: zap %lx %x\n", __func__, gfn, sp->role.word); if (kvm_mmu_zap_page(kvm, sp)) - nn = bucket->first; + goto restart; } } } @@ -1626,20 +1618,6 @@ static void mmu_convert_notrap(struct kvm_mmu_page *sp) } } -struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva) -{ - struct page *page; - - gpa_t gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); - - if (gpa == UNMAPPED_GVA) - return NULL; - - page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); - - return page; -} - /* * The function is based on mtrr_type_lookup() in * arch/x86/kernel/cpu/mtrr/generic.c @@ -1765,7 +1743,7 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) ++vcpu->kvm->stat.mmu_unsync; sp->unsync = 1; - kvm_mmu_mark_parents_unsync(vcpu, sp); + kvm_mmu_mark_parents_unsync(sp); mmu_convert_notrap(sp); return 0; @@ -2299,13 +2277,19 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level) /* no rsvd bits for 2 level 4K page table entries */ context->rsvd_bits_mask[0][1] = 0; context->rsvd_bits_mask[0][0] = 0; + context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; + + if (!is_pse(vcpu)) { + context->rsvd_bits_mask[1][1] = 0; + break; + } + if (is_cpuid_PSE36()) /* 36bits PSE 4MB page */ context->rsvd_bits_mask[1][1] = rsvd_bits(17, 21); else /* 32 bits PSE 4MB page */ context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21); - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0]; break; case PT32E_ROOT_LEVEL: context->rsvd_bits_mask[0][2] = @@ -2318,7 +2302,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level) context->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62) | rsvd_bits(13, 20); /* large page */ - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0]; + context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; break; case PT64_ROOT_LEVEL: context->rsvd_bits_mask[0][3] = exb_bit_rsvd | @@ -2336,7 +2320,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level) context->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51) | rsvd_bits(13, 20); /* large page */ - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0]; + context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; break; } } @@ -2438,7 +2422,7 @@ static int init_kvm_softmmu(struct kvm_vcpu *vcpu) else r = paging32_init_context(vcpu); - vcpu->arch.mmu.base_role.glevels = vcpu->arch.mmu.root_level; + vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu); return r; } @@ -2527,7 +2511,7 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, } ++vcpu->kvm->stat.mmu_pte_updated; - if (sp->role.glevels == PT32_ROOT_LEVEL) + if (!sp->role.cr4_pae) paging32_update_pte(vcpu, sp, spte, new); else paging64_update_pte(vcpu, sp, spte, new); @@ -2562,36 +2546,11 @@ static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu) } static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *new, int bytes) + u64 gpte) { gfn_t gfn; - int r; - u64 gpte = 0; pfn_t pfn; - if (bytes != 4 && bytes != 8) - return; - - /* - * Assume that the pte write on a page table of the same type - * as the current vcpu paging mode. This is nearly always true - * (might be false while changing modes). Note it is verified later - * by update_pte(). - */ - if (is_pae(vcpu)) { - /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ - if ((bytes == 4) && (gpa % 4 == 0)) { - r = kvm_read_guest(vcpu->kvm, gpa & ~(u64)7, &gpte, 8); - if (r) - return; - memcpy((void *)&gpte + (gpa % 8), new, 4); - } else if ((bytes == 8) && (gpa % 8 == 0)) { - memcpy((void *)&gpte, new, 8); - } - } else { - if ((bytes == 4) && (gpa % 4 == 0)) - memcpy((void *)&gpte, new, 4); - } if (!is_present_gpte(gpte)) return; gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; @@ -2640,10 +2599,46 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, int flooded = 0; int npte; int r; + int invlpg_counter; pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); - mmu_guess_page_from_pte_write(vcpu, gpa, new, bytes); + + invlpg_counter = atomic_read(&vcpu->kvm->arch.invlpg_counter); + + /* + * Assume that the pte write on a page table of the same type + * as the current vcpu paging mode. This is nearly always true + * (might be false while changing modes). Note it is verified later + * by update_pte(). + */ + if ((is_pae(vcpu) && bytes == 4) || !new) { + /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ + if (is_pae(vcpu)) { + gpa &= ~(gpa_t)7; + bytes = 8; + } + r = kvm_read_guest(vcpu->kvm, gpa, &gentry, min(bytes, 8)); + if (r) + gentry = 0; + new = (const u8 *)&gentry; + } + + switch (bytes) { + case 4: + gentry = *(const u32 *)new; + break; + case 8: + gentry = *(const u64 *)new; + break; + default: + gentry = 0; + break; + } + + mmu_guess_page_from_pte_write(vcpu, gpa, gentry); spin_lock(&vcpu->kvm->mmu_lock); + if (atomic_read(&vcpu->kvm->arch.invlpg_counter) != invlpg_counter) + gentry = 0; kvm_mmu_access_page(vcpu, gfn); kvm_mmu_free_some_pages(vcpu); ++vcpu->kvm->stat.mmu_pte_write; @@ -2662,10 +2657,12 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, } index = kvm_page_table_hashfn(gfn); bucket = &vcpu->kvm->arch.mmu_page_hash[index]; + +restart: hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) { if (sp->gfn != gfn || sp->role.direct || sp->role.invalid) continue; - pte_size = sp->role.glevels == PT32_ROOT_LEVEL ? 4 : 8; + pte_size = sp->role.cr4_pae ? 8 : 4; misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); misaligned |= bytes < 4; if (misaligned || flooded) { @@ -2682,14 +2679,14 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, pgprintk("misaligned: gpa %llx bytes %d role %x\n", gpa, bytes, sp->role.word); if (kvm_mmu_zap_page(vcpu->kvm, sp)) - n = bucket->first; + goto restart; ++vcpu->kvm->stat.mmu_flooded; continue; } page_offset = offset; level = sp->role.level; npte = 1; - if (sp->role.glevels == PT32_ROOT_LEVEL) { + if (!sp->role.cr4_pae) { page_offset <<= 1; /* 32->64 */ /* * A 32-bit pde maps 4MB while the shadow pdes map @@ -2707,20 +2704,11 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, continue; } spte = &sp->spt[page_offset / sizeof(*spte)]; - if ((gpa & (pte_size - 1)) || (bytes < pte_size)) { - gentry = 0; - r = kvm_read_guest_atomic(vcpu->kvm, - gpa & ~(u64)(pte_size - 1), - &gentry, pte_size); - new = (const void *)&gentry; - if (r < 0) - new = NULL; - } while (npte--) { entry = *spte; mmu_pte_write_zap_pte(vcpu, sp, spte); - if (new) - mmu_pte_write_new_pte(vcpu, sp, spte, new); + if (gentry) + mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); mmu_pte_write_flush_tlb(vcpu, entry, *spte); ++spte; } @@ -2900,10 +2888,11 @@ void kvm_mmu_zap_all(struct kvm *kvm) struct kvm_mmu_page *sp, *node; spin_lock(&kvm->mmu_lock); +restart: list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) if (kvm_mmu_zap_page(kvm, sp)) - node = container_of(kvm->arch.active_mmu_pages.next, - struct kvm_mmu_page, link); + goto restart; + spin_unlock(&kvm->mmu_lock); kvm_flush_remote_tlbs(kvm); @@ -3011,7 +3000,8 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) unsigned int nr_pages = 0; struct kvm_memslots *slots; - slots = rcu_dereference(kvm->memslots); + slots = kvm_memslots(kvm); + for (i = 0; i < slots->nmemslots; i++) nr_pages += slots->memslots[i].npages; @@ -3174,8 +3164,7 @@ static gva_t canonicalize(gva_t gva) } -typedef void (*inspect_spte_fn) (struct kvm *kvm, struct kvm_mmu_page *sp, - u64 *sptep); +typedef void (*inspect_spte_fn) (struct kvm *kvm, u64 *sptep); static void __mmu_spte_walk(struct kvm *kvm, struct kvm_mmu_page *sp, inspect_spte_fn fn) @@ -3191,7 +3180,7 @@ static void __mmu_spte_walk(struct kvm *kvm, struct kvm_mmu_page *sp, child = page_header(ent & PT64_BASE_ADDR_MASK); __mmu_spte_walk(kvm, child, fn); } else - fn(kvm, sp, &sp->spt[i]); + fn(kvm, &sp->spt[i]); } } } @@ -3282,11 +3271,13 @@ static void audit_mappings(struct kvm_vcpu *vcpu) static int count_rmaps(struct kvm_vcpu *vcpu) { + struct kvm *kvm = vcpu->kvm; + struct kvm_memslots *slots; int nmaps = 0; int i, j, k, idx; idx = srcu_read_lock(&kvm->srcu); - slots = rcu_dereference(kvm->memslots); + slots = kvm_memslots(kvm); for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { struct kvm_memory_slot *m = &slots->memslots[i]; struct kvm_rmap_desc *d; @@ -3315,7 +3306,7 @@ static int count_rmaps(struct kvm_vcpu *vcpu) return nmaps; } -void inspect_spte_has_rmap(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *sptep) +void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) { unsigned long *rmapp; struct kvm_mmu_page *rev_sp; @@ -3331,14 +3322,14 @@ void inspect_spte_has_rmap(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *sptep) printk(KERN_ERR "%s: no memslot for gfn %ld\n", audit_msg, gfn); printk(KERN_ERR "%s: index %ld of sp (gfn=%lx)\n", - audit_msg, sptep - rev_sp->spt, + audit_msg, (long int)(sptep - rev_sp->spt), rev_sp->gfn); dump_stack(); return; } rmapp = gfn_to_rmap(kvm, rev_sp->gfns[sptep - rev_sp->spt], - is_large_pte(*sptep)); + rev_sp->role.level); if (!*rmapp) { if (!printk_ratelimit()) return; @@ -3373,7 +3364,7 @@ static void check_writable_mappings_rmap(struct kvm_vcpu *vcpu) continue; if (!(ent & PT_WRITABLE_MASK)) continue; - inspect_spte_has_rmap(vcpu->kvm, sp, &pt[i]); + inspect_spte_has_rmap(vcpu->kvm, &pt[i]); } } return; diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 3e4a5c6ca2a9..bc4f7f0be2b1 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -6,8 +6,6 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvmmmu -#define TRACE_INCLUDE_PATH . -#define TRACE_INCLUDE_FILE mmutrace #define KVM_MMU_PAGE_FIELDS \ __field(__u64, gfn) \ @@ -30,14 +28,14 @@ \ role.word = __entry->role; \ \ - trace_seq_printf(p, "sp gfn %llx %u/%u q%u%s %s%s %spge" \ + trace_seq_printf(p, "sp gfn %llx %u%s q%u%s %s%s" \ " %snxe root %u %s%c", \ - __entry->gfn, role.level, role.glevels, \ + __entry->gfn, role.level, \ + role.cr4_pae ? " pae" : "", \ role.quadrant, \ role.direct ? " direct" : "", \ access_str[role.access], \ role.invalid ? " invalid" : "", \ - role.cr4_pge ? "" : "!", \ role.nxe ? "" : "!", \ __entry->root_count, \ __entry->unsync ? "unsync" : "sync", 0); \ @@ -216,5 +214,10 @@ TRACE_EVENT( #endif /* _TRACE_KVMMMU_H */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE mmutrace + /* This part must be outside protection */ #include <trace/define_trace.h> diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 81eab9a50e6a..d0cc07eb6eda 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -170,7 +170,7 @@ walk: goto access_error; #if PTTYPE == 64 - if (fetch_fault && is_nx(vcpu) && (pte & PT64_NX_MASK)) + if (fetch_fault && (pte & PT64_NX_MASK)) goto access_error; #endif @@ -190,10 +190,10 @@ walk: if ((walker->level == PT_PAGE_TABLE_LEVEL) || ((walker->level == PT_DIRECTORY_LEVEL) && - (pte & PT_PAGE_SIZE_MASK) && + is_large_pte(pte) && (PTTYPE == 64 || is_pse(vcpu))) || ((walker->level == PT_PDPE_LEVEL) && - (pte & PT_PAGE_SIZE_MASK) && + is_large_pte(pte) && is_long_mode(vcpu))) { int lvl = walker->level; @@ -258,11 +258,17 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, pt_element_t gpte; unsigned pte_access; pfn_t pfn; + u64 new_spte; gpte = *(const pt_element_t *)pte; if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) { - if (!is_present_gpte(gpte)) - __set_spte(spte, shadow_notrap_nonpresent_pte); + if (!is_present_gpte(gpte)) { + if (page->unsync) + new_spte = shadow_trap_nonpresent_pte; + else + new_spte = shadow_notrap_nonpresent_pte; + __set_spte(spte, new_spte); + } return; } pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte); @@ -457,6 +463,7 @@ out_unlock: static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) { struct kvm_shadow_walk_iterator iterator; + gpa_t pte_gpa = -1; int level; u64 *sptep; int need_flush = 0; @@ -470,6 +477,10 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) if (level == PT_PAGE_TABLE_LEVEL || ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) || ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) { + struct kvm_mmu_page *sp = page_header(__pa(sptep)); + + pte_gpa = (sp->gfn << PAGE_SHIFT); + pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t); if (is_shadow_present_pte(*sptep)) { rmap_remove(vcpu->kvm, sptep); @@ -487,7 +498,17 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) if (need_flush) kvm_flush_remote_tlbs(vcpu->kvm); + + atomic_inc(&vcpu->kvm->arch.invlpg_counter); + spin_unlock(&vcpu->kvm->mmu_lock); + + if (pte_gpa == -1) + return; + + if (mmu_topup_memory_caches(vcpu)) + return; + kvm_mmu_pte_write(vcpu, pte_gpa, NULL, sizeof(pt_element_t), 0); } static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, @@ -551,12 +572,15 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { int i, offset, nr_present; bool reset_host_protection; + gpa_t first_pte_gpa; offset = nr_present = 0; if (PTTYPE == 32) offset = sp->role.quadrant << PT64_LEVEL_BITS; + first_pte_gpa = gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t); + for (i = 0; i < PT64_ENT_PER_PAGE; i++) { unsigned pte_access; pt_element_t gpte; @@ -566,8 +590,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) if (!is_shadow_present_pte(sp->spt[i])) continue; - pte_gpa = gfn_to_gpa(sp->gfn); - pte_gpa += (i+offset) * sizeof(pt_element_t); + pte_gpa = first_pte_gpa + i * sizeof(pt_element_t); if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte, sizeof(pt_element_t))) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 2ba58206812a..889f66022e57 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -44,10 +44,11 @@ MODULE_LICENSE("GPL"); #define SEG_TYPE_LDT 2 #define SEG_TYPE_BUSY_TSS16 3 -#define SVM_FEATURE_NPT (1 << 0) -#define SVM_FEATURE_LBRV (1 << 1) -#define SVM_FEATURE_SVML (1 << 2) -#define SVM_FEATURE_PAUSE_FILTER (1 << 10) +#define SVM_FEATURE_NPT (1 << 0) +#define SVM_FEATURE_LBRV (1 << 1) +#define SVM_FEATURE_SVML (1 << 2) +#define SVM_FEATURE_NRIP (1 << 3) +#define SVM_FEATURE_PAUSE_FILTER (1 << 10) #define NESTED_EXIT_HOST 0 /* Exit handled on host level */ #define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */ @@ -70,6 +71,7 @@ struct kvm_vcpu; struct nested_state { struct vmcb *hsave; u64 hsave_msr; + u64 vm_cr_msr; u64 vmcb; /* These are the merged vectors */ @@ -77,6 +79,7 @@ struct nested_state { /* gpa pointers to the real vectors */ u64 vmcb_msrpm; + u64 vmcb_iopm; /* A VMEXIT is required but not yet emulated */ bool exit_required; @@ -91,6 +94,9 @@ struct nested_state { }; +#define MSRPM_OFFSETS 16 +static u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; + struct vcpu_svm { struct kvm_vcpu vcpu; struct vmcb *vmcb; @@ -110,13 +116,39 @@ struct vcpu_svm { struct nested_state nested; bool nmi_singlestep; + + unsigned int3_injected; + unsigned long int3_rip; +}; + +#define MSR_INVALID 0xffffffffU + +static struct svm_direct_access_msrs { + u32 index; /* Index of the MSR */ + bool always; /* True if intercept is always on */ +} direct_access_msrs[] = { + { .index = MSR_K6_STAR, .always = true }, + { .index = MSR_IA32_SYSENTER_CS, .always = true }, +#ifdef CONFIG_X86_64 + { .index = MSR_GS_BASE, .always = true }, + { .index = MSR_FS_BASE, .always = true }, + { .index = MSR_KERNEL_GS_BASE, .always = true }, + { .index = MSR_LSTAR, .always = true }, + { .index = MSR_CSTAR, .always = true }, + { .index = MSR_SYSCALL_MASK, .always = true }, +#endif + { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, + { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, + { .index = MSR_IA32_LASTINTFROMIP, .always = false }, + { .index = MSR_IA32_LASTINTTOIP, .always = false }, + { .index = MSR_INVALID, .always = false }, }; /* enable NPT for AMD64 and X86 with PAE */ #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) static bool npt_enabled = true; #else -static bool npt_enabled = false; +static bool npt_enabled; #endif static int npt = 1; @@ -129,6 +161,7 @@ static void svm_flush_tlb(struct kvm_vcpu *vcpu); static void svm_complete_interrupts(struct vcpu_svm *svm); static int nested_svm_exit_handled(struct vcpu_svm *svm); +static int nested_svm_intercept(struct vcpu_svm *svm); static int nested_svm_vmexit(struct vcpu_svm *svm); static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); @@ -163,8 +196,8 @@ static unsigned long iopm_base; struct kvm_ldttss_desc { u16 limit0; u16 base0; - unsigned base1 : 8, type : 5, dpl : 2, p : 1; - unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8; + unsigned base1:8, type:5, dpl:2, p:1; + unsigned limit1:4, zero0:3, g:1, base2:8; u32 base3; u32 zero1; } __attribute__((packed)); @@ -194,6 +227,27 @@ static u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; #define MSRS_RANGE_SIZE 2048 #define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2) +static u32 svm_msrpm_offset(u32 msr) +{ + u32 offset; + int i; + + for (i = 0; i < NUM_MSR_MAPS; i++) { + if (msr < msrpm_ranges[i] || + msr >= msrpm_ranges[i] + MSRS_IN_RANGE) + continue; + + offset = (msr - msrpm_ranges[i]) / 4; /* 4 msrs per u8 */ + offset += (i * MSRS_RANGE_SIZE); /* add range offset */ + + /* Now we have the u8 offset - but need the u32 offset */ + return offset / 4; + } + + /* MSR not in any range */ + return MSR_INVALID; +} + #define MAX_INST_SIZE 15 static inline u32 svm_has(u32 feat) @@ -213,7 +267,7 @@ static inline void stgi(void) static inline void invlpga(unsigned long addr, u32 asid) { - asm volatile (__ex(SVM_INVLPGA) :: "a"(addr), "c"(asid)); + asm volatile (__ex(SVM_INVLPGA) : : "a"(addr), "c"(asid)); } static inline void force_new_asid(struct kvm_vcpu *vcpu) @@ -235,23 +289,6 @@ static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) vcpu->arch.efer = efer; } -static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, - bool has_error_code, u32 error_code) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - /* If we are within a nested VM we'd better #VMEXIT and let the - guest handle the exception */ - if (nested_svm_check_exception(svm, nr, has_error_code, error_code)) - return; - - svm->vmcb->control.event_inj = nr - | SVM_EVTINJ_VALID - | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0) - | SVM_EVTINJ_TYPE_EXEPT; - svm->vmcb->control.event_inj_err = error_code; -} - static int is_external_interrupt(u32 info) { info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID; @@ -264,7 +301,7 @@ static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) u32 ret = 0; if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) - ret |= X86_SHADOW_INT_STI | X86_SHADOW_INT_MOV_SS; + ret |= KVM_X86_SHADOW_INT_STI | KVM_X86_SHADOW_INT_MOV_SS; return ret & mask; } @@ -283,6 +320,9 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + if (svm->vmcb->control.next_rip != 0) + svm->next_rip = svm->vmcb->control.next_rip; + if (!svm->next_rip) { if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) != EMULATE_DONE) @@ -297,6 +337,43 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) svm_set_interrupt_shadow(vcpu, 0); } +static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, + bool has_error_code, u32 error_code, + bool reinject) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * If we are within a nested VM we'd better #VMEXIT and let the guest + * handle the exception + */ + if (!reinject && + nested_svm_check_exception(svm, nr, has_error_code, error_code)) + return; + + if (nr == BP_VECTOR && !svm_has(SVM_FEATURE_NRIP)) { + unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu); + + /* + * For guest debugging where we have to reinject #BP if some + * INT3 is guest-owned: + * Emulate nRIP by moving RIP forward. Will fail if injection + * raises a fault that is not intercepted. Still better than + * failing in all cases. + */ + skip_emulated_instruction(&svm->vcpu); + rip = kvm_rip_read(&svm->vcpu); + svm->int3_rip = rip + svm->vmcb->save.cs.base; + svm->int3_injected = rip - old_rip; + } + + svm->vmcb->control.event_inj = nr + | SVM_EVTINJ_VALID + | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0) + | SVM_EVTINJ_TYPE_EXEPT; + svm->vmcb->control.event_inj_err = error_code; +} + static int has_svm(void) { const char *msg; @@ -319,7 +396,7 @@ static int svm_hardware_enable(void *garbage) struct svm_cpu_data *sd; uint64_t efer; - struct descriptor_table gdt_descr; + struct desc_ptr gdt_descr; struct desc_struct *gdt; int me = raw_smp_processor_id(); @@ -344,8 +421,8 @@ static int svm_hardware_enable(void *garbage) sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; sd->next_asid = sd->max_asid + 1; - kvm_get_gdt(&gdt_descr); - gdt = (struct desc_struct *)gdt_descr.base; + native_store_gdt(&gdt_descr); + gdt = (struct desc_struct *)gdt_descr.address; sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); wrmsrl(MSR_EFER, efer | EFER_SVME); @@ -391,42 +468,98 @@ err_1: } +static bool valid_msr_intercept(u32 index) +{ + int i; + + for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) + if (direct_access_msrs[i].index == index) + return true; + + return false; +} + static void set_msr_interception(u32 *msrpm, unsigned msr, int read, int write) { + u8 bit_read, bit_write; + unsigned long tmp; + u32 offset; + + /* + * If this warning triggers extend the direct_access_msrs list at the + * beginning of the file + */ + WARN_ON(!valid_msr_intercept(msr)); + + offset = svm_msrpm_offset(msr); + bit_read = 2 * (msr & 0x0f); + bit_write = 2 * (msr & 0x0f) + 1; + tmp = msrpm[offset]; + + BUG_ON(offset == MSR_INVALID); + + read ? clear_bit(bit_read, &tmp) : set_bit(bit_read, &tmp); + write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp); + + msrpm[offset] = tmp; +} + +static void svm_vcpu_init_msrpm(u32 *msrpm) +{ int i; - for (i = 0; i < NUM_MSR_MAPS; i++) { - if (msr >= msrpm_ranges[i] && - msr < msrpm_ranges[i] + MSRS_IN_RANGE) { - u32 msr_offset = (i * MSRS_IN_RANGE + msr - - msrpm_ranges[i]) * 2; - - u32 *base = msrpm + (msr_offset / 32); - u32 msr_shift = msr_offset % 32; - u32 mask = ((write) ? 0 : 2) | ((read) ? 0 : 1); - *base = (*base & ~(0x3 << msr_shift)) | - (mask << msr_shift); + memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER)); + + for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) { + if (!direct_access_msrs[i].always) + continue; + + set_msr_interception(msrpm, direct_access_msrs[i].index, 1, 1); + } +} + +static void add_msr_offset(u32 offset) +{ + int i; + + for (i = 0; i < MSRPM_OFFSETS; ++i) { + + /* Offset already in list? */ + if (msrpm_offsets[i] == offset) return; - } + + /* Slot used by another offset? */ + if (msrpm_offsets[i] != MSR_INVALID) + continue; + + /* Add offset to list */ + msrpm_offsets[i] = offset; + + return; } + + /* + * If this BUG triggers the msrpm_offsets table has an overflow. Just + * increase MSRPM_OFFSETS in this case. + */ BUG(); } -static void svm_vcpu_init_msrpm(u32 *msrpm) +static void init_msrpm_offsets(void) { - memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER)); + int i; -#ifdef CONFIG_X86_64 - set_msr_interception(msrpm, MSR_GS_BASE, 1, 1); - set_msr_interception(msrpm, MSR_FS_BASE, 1, 1); - set_msr_interception(msrpm, MSR_KERNEL_GS_BASE, 1, 1); - set_msr_interception(msrpm, MSR_LSTAR, 1, 1); - set_msr_interception(msrpm, MSR_CSTAR, 1, 1); - set_msr_interception(msrpm, MSR_SYSCALL_MASK, 1, 1); -#endif - set_msr_interception(msrpm, MSR_K6_STAR, 1, 1); - set_msr_interception(msrpm, MSR_IA32_SYSENTER_CS, 1, 1); + memset(msrpm_offsets, 0xff, sizeof(msrpm_offsets)); + + for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) { + u32 offset; + + offset = svm_msrpm_offset(direct_access_msrs[i].index); + BUG_ON(offset == MSR_INVALID); + + add_msr_offset(offset); + } } static void svm_enable_lbrv(struct vcpu_svm *svm) @@ -467,6 +600,8 @@ static __init int svm_hardware_setup(void) memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER)); iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT; + init_msrpm_offsets(); + if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); @@ -523,7 +658,7 @@ static void init_seg(struct vmcb_seg *seg) { seg->selector = 0; seg->attrib = SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK | - SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */ + SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */ seg->limit = 0xffff; seg->base = 0; } @@ -543,16 +678,16 @@ static void init_vmcb(struct vcpu_svm *svm) svm->vcpu.fpu_active = 1; - control->intercept_cr_read = INTERCEPT_CR0_MASK | + control->intercept_cr_read = INTERCEPT_CR0_MASK | INTERCEPT_CR3_MASK | INTERCEPT_CR4_MASK; - control->intercept_cr_write = INTERCEPT_CR0_MASK | + control->intercept_cr_write = INTERCEPT_CR0_MASK | INTERCEPT_CR3_MASK | INTERCEPT_CR4_MASK | INTERCEPT_CR8_MASK; - control->intercept_dr_read = INTERCEPT_DR0_MASK | + control->intercept_dr_read = INTERCEPT_DR0_MASK | INTERCEPT_DR1_MASK | INTERCEPT_DR2_MASK | INTERCEPT_DR3_MASK | @@ -561,7 +696,7 @@ static void init_vmcb(struct vcpu_svm *svm) INTERCEPT_DR6_MASK | INTERCEPT_DR7_MASK; - control->intercept_dr_write = INTERCEPT_DR0_MASK | + control->intercept_dr_write = INTERCEPT_DR0_MASK | INTERCEPT_DR1_MASK | INTERCEPT_DR2_MASK | INTERCEPT_DR3_MASK | @@ -575,7 +710,7 @@ static void init_vmcb(struct vcpu_svm *svm) (1 << MC_VECTOR); - control->intercept = (1ULL << INTERCEPT_INTR) | + control->intercept = (1ULL << INTERCEPT_INTR) | (1ULL << INTERCEPT_NMI) | (1ULL << INTERCEPT_SMI) | (1ULL << INTERCEPT_SELECTIVE_CR0) | @@ -636,7 +771,8 @@ static void init_vmcb(struct vcpu_svm *svm) save->rip = 0x0000fff0; svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip; - /* This is the guest-visible cr0 value. + /* + * This is the guest-visible cr0 value. * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0. */ svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; @@ -729,6 +865,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm_vcpu_init_msrpm(svm->msrpm); svm->nested.msrpm = page_address(nested_msrpm_pages); + svm_vcpu_init_msrpm(svm->nested.msrpm); svm->vmcb = page_address(page); clear_page(svm->vmcb); @@ -882,7 +1019,8 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1; var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1; - /* AMD's VMCB does not have an explicit unusable field, so emulate it + /* + * AMD's VMCB does not have an explicit unusable field, so emulate it * for cross vendor migration purposes by "not present" */ var->unusable = !var->present || (var->type == 0); @@ -918,7 +1056,8 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, var->type |= 0x1; break; case VCPU_SREG_SS: - /* On AMD CPUs sometimes the DB bit in the segment + /* + * On AMD CPUs sometimes the DB bit in the segment * descriptor is left as 1, although the whole segment has * been made unusable. Clear it here to pass an Intel VMX * entry check when cross vendor migrating. @@ -936,36 +1075,36 @@ static int svm_get_cpl(struct kvm_vcpu *vcpu) return save->cpl; } -static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void svm_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { struct vcpu_svm *svm = to_svm(vcpu); - dt->limit = svm->vmcb->save.idtr.limit; - dt->base = svm->vmcb->save.idtr.base; + dt->size = svm->vmcb->save.idtr.limit; + dt->address = svm->vmcb->save.idtr.base; } -static void svm_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void svm_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->save.idtr.limit = dt->limit; - svm->vmcb->save.idtr.base = dt->base ; + svm->vmcb->save.idtr.limit = dt->size; + svm->vmcb->save.idtr.base = dt->address ; } -static void svm_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void svm_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { struct vcpu_svm *svm = to_svm(vcpu); - dt->limit = svm->vmcb->save.gdtr.limit; - dt->base = svm->vmcb->save.gdtr.base; + dt->size = svm->vmcb->save.gdtr.limit; + dt->address = svm->vmcb->save.gdtr.base; } -static void svm_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->save.gdtr.limit = dt->limit; - svm->vmcb->save.gdtr.base = dt->base ; + svm->vmcb->save.gdtr.limit = dt->size; + svm->vmcb->save.gdtr.base = dt->address ; } static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) @@ -978,6 +1117,7 @@ static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) static void update_cr0_intercept(struct vcpu_svm *svm) { + struct vmcb *vmcb = svm->vmcb; ulong gcr0 = svm->vcpu.arch.cr0; u64 *hcr0 = &svm->vmcb->save.cr0; @@ -989,11 +1129,25 @@ static void update_cr0_intercept(struct vcpu_svm *svm) if (gcr0 == *hcr0 && svm->vcpu.fpu_active) { - svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK; - svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK; + vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK; + vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK; + if (is_nested(svm)) { + struct vmcb *hsave = svm->nested.hsave; + + hsave->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK; + hsave->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK; + vmcb->control.intercept_cr_read |= svm->nested.intercept_cr_read; + vmcb->control.intercept_cr_write |= svm->nested.intercept_cr_write; + } } else { svm->vmcb->control.intercept_cr_read |= INTERCEPT_CR0_MASK; svm->vmcb->control.intercept_cr_write |= INTERCEPT_CR0_MASK; + if (is_nested(svm)) { + struct vmcb *hsave = svm->nested.hsave; + + hsave->control.intercept_cr_read |= INTERCEPT_CR0_MASK; + hsave->control.intercept_cr_write |= INTERCEPT_CR0_MASK; + } } } @@ -1001,6 +1155,27 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_svm *svm = to_svm(vcpu); + if (is_nested(svm)) { + /* + * We are here because we run in nested mode, the host kvm + * intercepts cr0 writes but the l1 hypervisor does not. + * But the L1 hypervisor may intercept selective cr0 writes. + * This needs to be checked here. + */ + unsigned long old, new; + + /* Remove bits that would trigger a real cr0 write intercept */ + old = vcpu->arch.cr0 & SVM_CR0_SELECTIVE_MASK; + new = cr0 & SVM_CR0_SELECTIVE_MASK; + + if (old == new) { + /* cr0 write with ts and mp unchanged */ + svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE; + if (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE) + return; + } + } + #ifdef CONFIG_X86_64 if (vcpu->arch.efer & EFER_LME) { if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { @@ -1134,70 +1309,11 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) svm->vmcb->control.asid = sd->next_asid++; } -static int svm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *dest) +static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value) { struct vcpu_svm *svm = to_svm(vcpu); - switch (dr) { - case 0 ... 3: - *dest = vcpu->arch.db[dr]; - break; - case 4: - if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) - return EMULATE_FAIL; /* will re-inject UD */ - /* fall through */ - case 6: - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) - *dest = vcpu->arch.dr6; - else - *dest = svm->vmcb->save.dr6; - break; - case 5: - if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) - return EMULATE_FAIL; /* will re-inject UD */ - /* fall through */ - case 7: - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) - *dest = vcpu->arch.dr7; - else - *dest = svm->vmcb->save.dr7; - break; - } - - return EMULATE_DONE; -} - -static int svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - switch (dr) { - case 0 ... 3: - vcpu->arch.db[dr] = value; - if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) - vcpu->arch.eff_db[dr] = value; - break; - case 4: - if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) - return EMULATE_FAIL; /* will re-inject UD */ - /* fall through */ - case 6: - vcpu->arch.dr6 = (value & DR6_VOLATILE) | DR6_FIXED_1; - break; - case 5: - if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) - return EMULATE_FAIL; /* will re-inject UD */ - /* fall through */ - case 7: - vcpu->arch.dr7 = (value & DR7_VOLATILE) | DR7_FIXED_1; - if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { - svm->vmcb->save.dr7 = vcpu->arch.dr7; - vcpu->arch.switch_db_regs = (value & DR7_BP_EN_MASK); - } - break; - } - - return EMULATE_DONE; + svm->vmcb->save.dr7 = value; } static int pf_interception(struct vcpu_svm *svm) @@ -1234,7 +1350,7 @@ static int db_interception(struct vcpu_svm *svm) } if (svm->vcpu.guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)){ + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) { kvm_run->exit_reason = KVM_EXIT_DEBUG; kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; @@ -1268,7 +1384,22 @@ static int ud_interception(struct vcpu_svm *svm) static void svm_fpu_activate(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); + u32 excp; + + if (is_nested(svm)) { + u32 h_excp, n_excp; + + h_excp = svm->nested.hsave->control.intercept_exceptions; + n_excp = svm->nested.intercept_exceptions; + h_excp &= ~(1 << NM_VECTOR); + excp = h_excp | n_excp; + } else { + excp = svm->vmcb->control.intercept_exceptions; + excp &= ~(1 << NM_VECTOR); + } + + svm->vmcb->control.intercept_exceptions = excp; + svm->vcpu.fpu_active = 1; update_cr0_intercept(svm); } @@ -1309,29 +1440,23 @@ static int shutdown_interception(struct vcpu_svm *svm) static int io_interception(struct vcpu_svm *svm) { + struct kvm_vcpu *vcpu = &svm->vcpu; u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */ int size, in, string; unsigned port; ++svm->vcpu.stat.io_exits; - - svm->next_rip = svm->vmcb->control.exit_info_2; - string = (io_info & SVM_IOIO_STR_MASK) != 0; - - if (string) { - if (emulate_instruction(&svm->vcpu, - 0, 0, 0) == EMULATE_DO_MMIO) - return 0; - return 1; - } - in = (io_info & SVM_IOIO_TYPE_MASK) != 0; + if (string || in) + return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO); + port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; - + svm->next_rip = svm->vmcb->control.exit_info_2; skip_emulated_instruction(&svm->vcpu); - return kvm_emulate_pio(&svm->vcpu, in, size, port); + + return kvm_fast_pio_out(vcpu, size, port); } static int nmi_interception(struct vcpu_svm *svm) @@ -1384,6 +1509,8 @@ static int nested_svm_check_permissions(struct vcpu_svm *svm) static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code) { + int vmexit; + if (!is_nested(svm)) return 0; @@ -1392,21 +1519,28 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, svm->vmcb->control.exit_info_1 = error_code; svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; - return nested_svm_exit_handled(svm); + vmexit = nested_svm_intercept(svm); + if (vmexit == NESTED_EXIT_DONE) + svm->nested.exit_required = true; + + return vmexit; } -static inline int nested_svm_intr(struct vcpu_svm *svm) +/* This function returns true if it is save to enable the irq window */ +static inline bool nested_svm_intr(struct vcpu_svm *svm) { if (!is_nested(svm)) - return 0; + return true; if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) - return 0; + return true; if (!(svm->vcpu.arch.hflags & HF_HIF_MASK)) - return 0; + return false; - svm->vmcb->control.exit_code = SVM_EXIT_INTR; + svm->vmcb->control.exit_code = SVM_EXIT_INTR; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; if (svm->nested.intercept & 1ULL) { /* @@ -1417,21 +1551,40 @@ static inline int nested_svm_intr(struct vcpu_svm *svm) */ svm->nested.exit_required = true; trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); - return 1; + return false; } - return 0; + return true; +} + +/* This function returns true if it is save to enable the nmi window */ +static inline bool nested_svm_nmi(struct vcpu_svm *svm) +{ + if (!is_nested(svm)) + return true; + + if (!(svm->nested.intercept & (1ULL << INTERCEPT_NMI))) + return true; + + svm->vmcb->control.exit_code = SVM_EXIT_NMI; + svm->nested.exit_required = true; + + return false; } -static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, enum km_type idx) +static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page) { struct page *page; + might_sleep(); + page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT); if (is_error_page(page)) goto error; - return kmap_atomic(page, idx); + *_page = page; + + return kmap(page); error: kvm_release_page_clean(page); @@ -1440,61 +1593,55 @@ error: return NULL; } -static void nested_svm_unmap(void *addr, enum km_type idx) +static void nested_svm_unmap(struct page *page) { - struct page *page; + kunmap(page); + kvm_release_page_dirty(page); +} - if (!addr) - return; +static int nested_svm_intercept_ioio(struct vcpu_svm *svm) +{ + unsigned port; + u8 val, bit; + u64 gpa; - page = kmap_atomic_to_page(addr); + if (!(svm->nested.intercept & (1ULL << INTERCEPT_IOIO_PROT))) + return NESTED_EXIT_HOST; - kunmap_atomic(addr, idx); - kvm_release_page_dirty(page); + port = svm->vmcb->control.exit_info_1 >> 16; + gpa = svm->nested.vmcb_iopm + (port / 8); + bit = port % 8; + val = 0; + + if (kvm_read_guest(svm->vcpu.kvm, gpa, &val, 1)) + val &= (1 << bit); + + return val ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; } -static bool nested_svm_exit_handled_msr(struct vcpu_svm *svm) +static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) { - u32 param = svm->vmcb->control.exit_info_1 & 1; - u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; - bool ret = false; - u32 t0, t1; - u8 *msrpm; + u32 offset, msr, value; + int write, mask; if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT))) - return false; - - msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0); + return NESTED_EXIT_HOST; - if (!msrpm) - goto out; + msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + offset = svm_msrpm_offset(msr); + write = svm->vmcb->control.exit_info_1 & 1; + mask = 1 << ((2 * (msr & 0xf)) + write); - switch (msr) { - case 0 ... 0x1fff: - t0 = (msr * 2) % 8; - t1 = msr / 8; - break; - case 0xc0000000 ... 0xc0001fff: - t0 = (8192 + msr - 0xc0000000) * 2; - t1 = (t0 / 8); - t0 %= 8; - break; - case 0xc0010000 ... 0xc0011fff: - t0 = (16384 + msr - 0xc0010000) * 2; - t1 = (t0 / 8); - t0 %= 8; - break; - default: - ret = true; - goto out; - } + if (offset == MSR_INVALID) + return NESTED_EXIT_DONE; - ret = msrpm[t1] & ((1 << param) << t0); + /* Offset is in 32 bit units but need in 8 bit units */ + offset *= 4; -out: - nested_svm_unmap(msrpm, KM_USER0); + if (kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + offset, &value, 4)) + return NESTED_EXIT_DONE; - return ret; + return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; } static int nested_svm_exit_special(struct vcpu_svm *svm) @@ -1504,17 +1651,21 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) switch (exit_code) { case SVM_EXIT_INTR: case SVM_EXIT_NMI: + case SVM_EXIT_EXCP_BASE + MC_VECTOR: return NESTED_EXIT_HOST; - /* For now we are always handling NPFs when using them */ case SVM_EXIT_NPF: + /* For now we are always handling NPFs when using them */ if (npt_enabled) return NESTED_EXIT_HOST; break; - /* When we're shadowing, trap PFs */ case SVM_EXIT_EXCP_BASE + PF_VECTOR: + /* When we're shadowing, trap PFs */ if (!npt_enabled) return NESTED_EXIT_HOST; break; + case SVM_EXIT_EXCP_BASE + NM_VECTOR: + nm_interception(svm); + break; default: break; } @@ -1525,7 +1676,7 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) /* * If this function returns true, this #vmexit was already handled */ -static int nested_svm_exit_handled(struct vcpu_svm *svm) +static int nested_svm_intercept(struct vcpu_svm *svm) { u32 exit_code = svm->vmcb->control.exit_code; int vmexit = NESTED_EXIT_HOST; @@ -1534,6 +1685,9 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm) case SVM_EXIT_MSR: vmexit = nested_svm_exit_handled_msr(svm); break; + case SVM_EXIT_IOIO: + vmexit = nested_svm_intercept_ioio(svm); + break; case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: { u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0); if (svm->nested.intercept_cr_read & cr_bits) @@ -1564,6 +1718,10 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm) vmexit = NESTED_EXIT_DONE; break; } + case SVM_EXIT_ERR: { + vmexit = NESTED_EXIT_DONE; + break; + } default: { u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR); if (svm->nested.intercept & exit_bits) @@ -1571,9 +1729,17 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm) } } - if (vmexit == NESTED_EXIT_DONE) { + return vmexit; +} + +static int nested_svm_exit_handled(struct vcpu_svm *svm) +{ + int vmexit; + + vmexit = nested_svm_intercept(svm); + + if (vmexit == NESTED_EXIT_DONE) nested_svm_vmexit(svm); - } return vmexit; } @@ -1615,6 +1781,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) struct vmcb *nested_vmcb; struct vmcb *hsave = svm->nested.hsave; struct vmcb *vmcb = svm->vmcb; + struct page *page; trace_kvm_nested_vmexit_inject(vmcb->control.exit_code, vmcb->control.exit_info_1, @@ -1622,10 +1789,13 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) vmcb->control.exit_int_info, vmcb->control.exit_int_info_err); - nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, KM_USER0); + nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, &page); if (!nested_vmcb) return 1; + /* Exit nested SVM mode */ + svm->nested.vmcb = 0; + /* Give the current vmcb to the guest */ disable_gif(svm); @@ -1635,9 +1805,10 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) nested_vmcb->save.ds = vmcb->save.ds; nested_vmcb->save.gdtr = vmcb->save.gdtr; nested_vmcb->save.idtr = vmcb->save.idtr; - if (npt_enabled) - nested_vmcb->save.cr3 = vmcb->save.cr3; + nested_vmcb->save.cr0 = kvm_read_cr0(&svm->vcpu); + nested_vmcb->save.cr3 = svm->vcpu.arch.cr3; nested_vmcb->save.cr2 = vmcb->save.cr2; + nested_vmcb->save.cr4 = svm->vcpu.arch.cr4; nested_vmcb->save.rflags = vmcb->save.rflags; nested_vmcb->save.rip = vmcb->save.rip; nested_vmcb->save.rsp = vmcb->save.rsp; @@ -1709,10 +1880,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) svm->vmcb->save.cpl = 0; svm->vmcb->control.exit_int_info = 0; - /* Exit nested SVM mode */ - svm->nested.vmcb = 0; - - nested_svm_unmap(nested_vmcb, KM_USER0); + nested_svm_unmap(page); kvm_mmu_reset_context(&svm->vcpu); kvm_mmu_load(&svm->vcpu); @@ -1722,19 +1890,33 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) { - u32 *nested_msrpm; + /* + * This function merges the msr permission bitmaps of kvm and the + * nested vmcb. It is omptimized in that it only merges the parts where + * the kvm msr permission bitmap may contain zero bits + */ int i; - nested_msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0); - if (!nested_msrpm) - return false; + if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT))) + return true; - for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++) - svm->nested.msrpm[i] = svm->msrpm[i] | nested_msrpm[i]; + for (i = 0; i < MSRPM_OFFSETS; i++) { + u32 value, p; + u64 offset; - svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm); + if (msrpm_offsets[i] == 0xffffffff) + break; + + p = msrpm_offsets[i]; + offset = svm->nested.vmcb_msrpm + (p * 4); + + if (kvm_read_guest(svm->vcpu.kvm, offset, &value, 4)) + return false; - nested_svm_unmap(nested_msrpm, KM_USER0); + svm->nested.msrpm[p] = svm->msrpm[p] | value; + } + + svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm); return true; } @@ -1744,26 +1926,34 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) struct vmcb *nested_vmcb; struct vmcb *hsave = svm->nested.hsave; struct vmcb *vmcb = svm->vmcb; + struct page *page; + u64 vmcb_gpa; + + vmcb_gpa = svm->vmcb->save.rax; - nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0); + nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); if (!nested_vmcb) return false; - /* nested_vmcb is our indicator if nested SVM is activated */ - svm->nested.vmcb = svm->vmcb->save.rax; - - trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb, + trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, vmcb_gpa, nested_vmcb->save.rip, nested_vmcb->control.int_ctl, nested_vmcb->control.event_inj, nested_vmcb->control.nested_ctl); + trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr_read, + nested_vmcb->control.intercept_cr_write, + nested_vmcb->control.intercept_exceptions, + nested_vmcb->control.intercept); + /* Clear internal status */ kvm_clear_exception_queue(&svm->vcpu); kvm_clear_interrupt_queue(&svm->vcpu); - /* Save the old vmcb, so we don't need to pick what we save, but - can restore everything when a VMEXIT occurs */ + /* + * Save the old vmcb, so we don't need to pick what we save, but can + * restore everything when a VMEXIT occurs + */ hsave->save.es = vmcb->save.es; hsave->save.cs = vmcb->save.cs; hsave->save.ss = vmcb->save.ss; @@ -1803,14 +1993,17 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) if (npt_enabled) { svm->vmcb->save.cr3 = nested_vmcb->save.cr3; svm->vcpu.arch.cr3 = nested_vmcb->save.cr3; - } else { + } else kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3); - kvm_mmu_reset_context(&svm->vcpu); - } + + /* Guest paging mode is active - reset mmu */ + kvm_mmu_reset_context(&svm->vcpu); + svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2; kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax); kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp); kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip); + /* In case we don't even reach vcpu_run, the fields are not updated */ svm->vmcb->save.rax = nested_vmcb->save.rax; svm->vmcb->save.rsp = nested_vmcb->save.rsp; @@ -1819,22 +2012,8 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) svm->vmcb->save.dr6 = nested_vmcb->save.dr6; svm->vmcb->save.cpl = nested_vmcb->save.cpl; - /* We don't want a nested guest to be more powerful than the guest, - so all intercepts are ORed */ - svm->vmcb->control.intercept_cr_read |= - nested_vmcb->control.intercept_cr_read; - svm->vmcb->control.intercept_cr_write |= - nested_vmcb->control.intercept_cr_write; - svm->vmcb->control.intercept_dr_read |= - nested_vmcb->control.intercept_dr_read; - svm->vmcb->control.intercept_dr_write |= - nested_vmcb->control.intercept_dr_write; - svm->vmcb->control.intercept_exceptions |= - nested_vmcb->control.intercept_exceptions; - - svm->vmcb->control.intercept |= nested_vmcb->control.intercept; - - svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa; + svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa & ~0x0fffULL; + svm->nested.vmcb_iopm = nested_vmcb->control.iopm_base_pa & ~0x0fffULL; /* cache intercepts */ svm->nested.intercept_cr_read = nested_vmcb->control.intercept_cr_read; @@ -1851,13 +2030,40 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) else svm->vcpu.arch.hflags &= ~HF_VINTR_MASK; + if (svm->vcpu.arch.hflags & HF_VINTR_MASK) { + /* We only want the cr8 intercept bits of the guest */ + svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR8_MASK; + svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK; + } + + /* + * We don't want a nested guest to be more powerful than the guest, so + * all intercepts are ORed + */ + svm->vmcb->control.intercept_cr_read |= + nested_vmcb->control.intercept_cr_read; + svm->vmcb->control.intercept_cr_write |= + nested_vmcb->control.intercept_cr_write; + svm->vmcb->control.intercept_dr_read |= + nested_vmcb->control.intercept_dr_read; + svm->vmcb->control.intercept_dr_write |= + nested_vmcb->control.intercept_dr_write; + svm->vmcb->control.intercept_exceptions |= + nested_vmcb->control.intercept_exceptions; + + svm->vmcb->control.intercept |= nested_vmcb->control.intercept; + + svm->vmcb->control.lbr_ctl = nested_vmcb->control.lbr_ctl; svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; svm->vmcb->control.int_state = nested_vmcb->control.int_state; svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset; svm->vmcb->control.event_inj = nested_vmcb->control.event_inj; svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err; - nested_svm_unmap(nested_vmcb, KM_USER0); + nested_svm_unmap(page); + + /* nested_vmcb is our indicator if nested SVM is activated */ + svm->nested.vmcb = vmcb_gpa; enable_gif(svm); @@ -1883,6 +2089,7 @@ static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) static int vmload_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; + struct page *page; if (nested_svm_check_permissions(svm)) return 1; @@ -1890,12 +2097,12 @@ static int vmload_interception(struct vcpu_svm *svm) svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); - nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0); + nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); if (!nested_vmcb) return 1; nested_svm_vmloadsave(nested_vmcb, svm->vmcb); - nested_svm_unmap(nested_vmcb, KM_USER0); + nested_svm_unmap(page); return 1; } @@ -1903,6 +2110,7 @@ static int vmload_interception(struct vcpu_svm *svm) static int vmsave_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; + struct page *page; if (nested_svm_check_permissions(svm)) return 1; @@ -1910,12 +2118,12 @@ static int vmsave_interception(struct vcpu_svm *svm) svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); - nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0); + nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); if (!nested_vmcb) return 1; nested_svm_vmloadsave(svm->vmcb, nested_vmcb); - nested_svm_unmap(nested_vmcb, KM_USER0); + nested_svm_unmap(page); return 1; } @@ -2018,6 +2226,8 @@ static int task_switch_interception(struct vcpu_svm *svm) svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_TYPE_MASK; uint32_t idt_v = svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_VALID; + bool has_error_code = false; + u32 error_code = 0; tss_selector = (u16)svm->vmcb->control.exit_info_1; @@ -2038,6 +2248,12 @@ static int task_switch_interception(struct vcpu_svm *svm) svm->vcpu.arch.nmi_injected = false; break; case SVM_EXITINTINFO_TYPE_EXEPT: + if (svm->vmcb->control.exit_info_2 & + (1ULL << SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE)) { + has_error_code = true; + error_code = + (u32)svm->vmcb->control.exit_info_2; + } kvm_clear_exception_queue(&svm->vcpu); break; case SVM_EXITINTINFO_TYPE_INTR: @@ -2054,7 +2270,14 @@ static int task_switch_interception(struct vcpu_svm *svm) (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) skip_emulated_instruction(&svm->vcpu); - return kvm_task_switch(&svm->vcpu, tss_selector, reason); + if (kvm_task_switch(&svm->vcpu, tss_selector, reason, + has_error_code, error_code) == EMULATE_FAIL) { + svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + svm->vcpu.run->internal.ndata = 0; + return 0; + } + return 1; } static int cpuid_interception(struct vcpu_svm *svm) @@ -2145,9 +2368,11 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) case MSR_IA32_SYSENTER_ESP: *data = svm->sysenter_esp; break; - /* Nobody will change the following 5 values in the VMCB so - we can safely return them on rdmsr. They will always be 0 - until LBRV is implemented. */ + /* + * Nobody will change the following 5 values in the VMCB so we can + * safely return them on rdmsr. They will always be 0 until LBRV is + * implemented. + */ case MSR_IA32_DEBUGCTLMSR: *data = svm->vmcb->save.dbgctl; break; @@ -2167,7 +2392,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) *data = svm->nested.hsave_msr; break; case MSR_VM_CR: - *data = 0; + *data = svm->nested.vm_cr_msr; break; case MSR_IA32_UCODE_REV: *data = 0x01000065; @@ -2197,6 +2422,31 @@ static int rdmsr_interception(struct vcpu_svm *svm) return 1; } +static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int svm_dis, chg_mask; + + if (data & ~SVM_VM_CR_VALID_MASK) + return 1; + + chg_mask = SVM_VM_CR_VALID_MASK; + + if (svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK) + chg_mask &= ~(SVM_VM_CR_SVM_LOCK_MASK | SVM_VM_CR_SVM_DIS_MASK); + + svm->nested.vm_cr_msr &= ~chg_mask; + svm->nested.vm_cr_msr |= (data & chg_mask); + + svm_dis = svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK; + + /* check for svm_disable while efer.svme is set */ + if (svm_dis && (vcpu->arch.efer & EFER_SVME)) + return 1; + + return 0; +} + static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) { struct vcpu_svm *svm = to_svm(vcpu); @@ -2263,6 +2513,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) svm->nested.hsave_msr = data; break; case MSR_VM_CR: + return svm_set_vm_cr(vcpu, data); case MSR_VM_IGNNE: pr_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; @@ -2326,16 +2577,16 @@ static int pause_interception(struct vcpu_svm *svm) } static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { - [SVM_EXIT_READ_CR0] = emulate_on_interception, - [SVM_EXIT_READ_CR3] = emulate_on_interception, - [SVM_EXIT_READ_CR4] = emulate_on_interception, - [SVM_EXIT_READ_CR8] = emulate_on_interception, + [SVM_EXIT_READ_CR0] = emulate_on_interception, + [SVM_EXIT_READ_CR3] = emulate_on_interception, + [SVM_EXIT_READ_CR4] = emulate_on_interception, + [SVM_EXIT_READ_CR8] = emulate_on_interception, [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, - [SVM_EXIT_WRITE_CR0] = emulate_on_interception, - [SVM_EXIT_WRITE_CR3] = emulate_on_interception, - [SVM_EXIT_WRITE_CR4] = emulate_on_interception, - [SVM_EXIT_WRITE_CR8] = cr8_write_interception, - [SVM_EXIT_READ_DR0] = emulate_on_interception, + [SVM_EXIT_WRITE_CR0] = emulate_on_interception, + [SVM_EXIT_WRITE_CR3] = emulate_on_interception, + [SVM_EXIT_WRITE_CR4] = emulate_on_interception, + [SVM_EXIT_WRITE_CR8] = cr8_write_interception, + [SVM_EXIT_READ_DR0] = emulate_on_interception, [SVM_EXIT_READ_DR1] = emulate_on_interception, [SVM_EXIT_READ_DR2] = emulate_on_interception, [SVM_EXIT_READ_DR3] = emulate_on_interception, @@ -2354,15 +2605,14 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_EXCP_BASE + DB_VECTOR] = db_interception, [SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception, [SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception, - [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, - [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, - [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception, - [SVM_EXIT_INTR] = intr_interception, + [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, + [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, + [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception, + [SVM_EXIT_INTR] = intr_interception, [SVM_EXIT_NMI] = nmi_interception, [SVM_EXIT_SMI] = nop_on_interception, [SVM_EXIT_INIT] = nop_on_interception, [SVM_EXIT_VINTR] = interrupt_window_interception, - /* [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, */ [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, [SVM_EXIT_INVD] = emulate_on_interception, @@ -2370,7 +2620,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_HLT] = halt_interception, [SVM_EXIT_INVLPG] = invlpg_interception, [SVM_EXIT_INVLPGA] = invlpga_interception, - [SVM_EXIT_IOIO] = io_interception, + [SVM_EXIT_IOIO] = io_interception, [SVM_EXIT_MSR] = msr_interception, [SVM_EXIT_TASK_SWITCH] = task_switch_interception, [SVM_EXIT_SHUTDOWN] = shutdown_interception, @@ -2393,7 +2643,12 @@ static int handle_exit(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; - trace_kvm_exit(exit_code, svm->vmcb->save.rip); + trace_kvm_exit(exit_code, vcpu); + + if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK)) + vcpu->arch.cr0 = svm->vmcb->save.cr0; + if (npt_enabled) + vcpu->arch.cr3 = svm->vmcb->save.cr3; if (unlikely(svm->nested.exit_required)) { nested_svm_vmexit(svm); @@ -2422,11 +2677,6 @@ static int handle_exit(struct kvm_vcpu *vcpu) svm_complete_interrupts(svm); - if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK)) - vcpu->arch.cr0 = svm->vmcb->save.cr0; - if (npt_enabled) - vcpu->arch.cr3 = svm->vmcb->save.cr3; - if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) { kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; kvm_run->fail_entry.hardware_entry_failure_reason @@ -2511,6 +2761,9 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vcpu_svm *svm = to_svm(vcpu); + if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK)) + return; + if (irr == -1) return; @@ -2522,8 +2775,12 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - return !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) && - !(svm->vcpu.arch.hflags & HF_NMI_MASK); + int ret; + ret = !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) && + !(svm->vcpu.arch.hflags & HF_NMI_MASK); + ret = ret && gif_set(svm) && nested_svm_nmi(svm); + + return ret; } static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) @@ -2568,13 +2825,13 @@ static void enable_irq_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - nested_svm_intr(svm); - - /* In case GIF=0 we can't rely on the CPU to tell us when - * GIF becomes 1, because that's a separate STGI/VMRUN intercept. - * The next time we get that intercept, this function will be - * called again though and we'll get the vintr intercept. */ - if (gif_set(svm)) { + /* + * In case GIF=0 we can't rely on the CPU to tell us when GIF becomes + * 1, because that's a separate STGI/VMRUN intercept. The next time we + * get that intercept, this function will be called again though and + * we'll get the vintr intercept. + */ + if (gif_set(svm) && nested_svm_intr(svm)) { svm_set_vintr(svm); svm_inject_irq(svm, 0x0); } @@ -2588,9 +2845,10 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) == HF_NMI_MASK) return; /* IRET will cause a vm exit */ - /* Something prevents NMI from been injected. Single step over - possible problem (IRET or exception injection or interrupt - shadow) */ + /* + * Something prevents NMI from been injected. Single step over possible + * problem (IRET or exception injection or interrupt shadow) + */ svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); update_db_intercept(vcpu); @@ -2614,6 +2872,9 @@ static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK)) + return; + if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR8_MASK)) { int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK; kvm_set_cr8(vcpu, cr8); @@ -2625,6 +2886,9 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); u64 cr8; + if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK)) + return; + cr8 = kvm_get_cr8(vcpu); svm->vmcb->control.int_ctl &= ~V_TPR_MASK; svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK; @@ -2635,6 +2899,9 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) u8 vector; int type; u32 exitintinfo = svm->vmcb->control.exit_int_info; + unsigned int3_injected = svm->int3_injected; + + svm->int3_injected = 0; if (svm->vcpu.arch.hflags & HF_IRET_MASK) svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK); @@ -2654,18 +2921,25 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) svm->vcpu.arch.nmi_injected = true; break; case SVM_EXITINTINFO_TYPE_EXEPT: - /* In case of software exception do not reinject an exception - vector, but re-execute and instruction instead */ - if (is_nested(svm)) - break; - if (kvm_exception_is_soft(vector)) + /* + * In case of software exceptions, do not reinject the vector, + * but re-execute the instruction instead. Rewind RIP first + * if we emulated INT3 before. + */ + if (kvm_exception_is_soft(vector)) { + if (vector == BP_VECTOR && int3_injected && + kvm_is_linear_rip(&svm->vcpu, svm->int3_rip)) + kvm_rip_write(&svm->vcpu, + kvm_rip_read(&svm->vcpu) - + int3_injected); break; + } if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) { u32 err = svm->vmcb->control.exit_int_info_err; - kvm_queue_exception_e(&svm->vcpu, vector, err); + kvm_requeue_exception_e(&svm->vcpu, vector, err); } else - kvm_queue_exception(&svm->vcpu, vector); + kvm_requeue_exception(&svm->vcpu, vector); break; case SVM_EXITINTINFO_TYPE_INTR: kvm_queue_interrupt(&svm->vcpu, vector, false); @@ -2688,6 +2962,10 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) u16 gs_selector; u16 ldt_selector; + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; + svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; + svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; + /* * A vmexit emulation is required before the vcpu can be executed * again. @@ -2695,10 +2973,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->nested.exit_required)) return; - svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; - svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; - svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; - pre_svm_run(svm); sync_lapic_to_cr8(vcpu); @@ -2879,25 +3153,39 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) { } +static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) +{ + switch (func) { + case 0x8000000A: + entry->eax = 1; /* SVM revision 1 */ + entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper + ASID emulation to nested SVM */ + entry->ecx = 0; /* Reserved */ + entry->edx = 0; /* Do not support any additional features */ + + break; + } +} + static const struct trace_print_flags svm_exit_reasons_str[] = { - { SVM_EXIT_READ_CR0, "read_cr0" }, - { SVM_EXIT_READ_CR3, "read_cr3" }, - { SVM_EXIT_READ_CR4, "read_cr4" }, - { SVM_EXIT_READ_CR8, "read_cr8" }, - { SVM_EXIT_WRITE_CR0, "write_cr0" }, - { SVM_EXIT_WRITE_CR3, "write_cr3" }, - { SVM_EXIT_WRITE_CR4, "write_cr4" }, - { SVM_EXIT_WRITE_CR8, "write_cr8" }, - { SVM_EXIT_READ_DR0, "read_dr0" }, - { SVM_EXIT_READ_DR1, "read_dr1" }, - { SVM_EXIT_READ_DR2, "read_dr2" }, - { SVM_EXIT_READ_DR3, "read_dr3" }, - { SVM_EXIT_WRITE_DR0, "write_dr0" }, - { SVM_EXIT_WRITE_DR1, "write_dr1" }, - { SVM_EXIT_WRITE_DR2, "write_dr2" }, - { SVM_EXIT_WRITE_DR3, "write_dr3" }, - { SVM_EXIT_WRITE_DR5, "write_dr5" }, - { SVM_EXIT_WRITE_DR7, "write_dr7" }, + { SVM_EXIT_READ_CR0, "read_cr0" }, + { SVM_EXIT_READ_CR3, "read_cr3" }, + { SVM_EXIT_READ_CR4, "read_cr4" }, + { SVM_EXIT_READ_CR8, "read_cr8" }, + { SVM_EXIT_WRITE_CR0, "write_cr0" }, + { SVM_EXIT_WRITE_CR3, "write_cr3" }, + { SVM_EXIT_WRITE_CR4, "write_cr4" }, + { SVM_EXIT_WRITE_CR8, "write_cr8" }, + { SVM_EXIT_READ_DR0, "read_dr0" }, + { SVM_EXIT_READ_DR1, "read_dr1" }, + { SVM_EXIT_READ_DR2, "read_dr2" }, + { SVM_EXIT_READ_DR3, "read_dr3" }, + { SVM_EXIT_WRITE_DR0, "write_dr0" }, + { SVM_EXIT_WRITE_DR1, "write_dr1" }, + { SVM_EXIT_WRITE_DR2, "write_dr2" }, + { SVM_EXIT_WRITE_DR3, "write_dr3" }, + { SVM_EXIT_WRITE_DR5, "write_dr5" }, + { SVM_EXIT_WRITE_DR7, "write_dr7" }, { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, @@ -2946,8 +3234,10 @@ static void svm_fpu_deactivate(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - update_cr0_intercept(svm); svm->vmcb->control.intercept_exceptions |= 1 << NM_VECTOR; + if (is_nested(svm)) + svm->nested.hsave->control.intercept_exceptions |= 1 << NM_VECTOR; + update_cr0_intercept(svm); } static struct kvm_x86_ops svm_x86_ops = { @@ -2986,8 +3276,7 @@ static struct kvm_x86_ops svm_x86_ops = { .set_idt = svm_set_idt, .get_gdt = svm_get_gdt, .set_gdt = svm_set_gdt, - .get_dr = svm_get_dr, - .set_dr = svm_set_dr, + .set_dr7 = svm_set_dr7, .cache_reg = svm_cache_reg, .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, @@ -3023,6 +3312,8 @@ static struct kvm_x86_ops svm_x86_ops = { .cpuid_update = svm_cpuid_update, .rdtscp_supported = svm_rdtscp_supported, + + .set_supported_cpuid = svm_set_supported_cpuid, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/timer.c b/arch/x86/kvm/timer.c index eea40439066c..4ddadb1a5ffe 100644 --- a/arch/x86/kvm/timer.c +++ b/arch/x86/kvm/timer.c @@ -12,7 +12,8 @@ static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer) /* * There is a race window between reading and incrementing, but we do * not care about potentially loosing timer events in the !reinject - * case anyway. + * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked + * in vcpu_enter_guest. */ if (ktimer->reinject || !atomic_read(&ktimer->pending)) { atomic_inc(&ktimer->pending); diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 6ad30a29f044..a6544b8e7c0f 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -5,8 +5,6 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm -#define TRACE_INCLUDE_PATH arch/x86/kvm -#define TRACE_INCLUDE_FILE trace /* * Tracepoint for guest mode entry. @@ -184,8 +182,8 @@ TRACE_EVENT(kvm_apic, * Tracepoint for kvm guest exit: */ TRACE_EVENT(kvm_exit, - TP_PROTO(unsigned int exit_reason, unsigned long guest_rip), - TP_ARGS(exit_reason, guest_rip), + TP_PROTO(unsigned int exit_reason, struct kvm_vcpu *vcpu), + TP_ARGS(exit_reason, vcpu), TP_STRUCT__entry( __field( unsigned int, exit_reason ) @@ -194,7 +192,7 @@ TRACE_EVENT(kvm_exit, TP_fast_assign( __entry->exit_reason = exit_reason; - __entry->guest_rip = guest_rip; + __entry->guest_rip = kvm_rip_read(vcpu); ), TP_printk("reason %s rip 0x%lx", @@ -221,6 +219,38 @@ TRACE_EVENT(kvm_inj_virq, TP_printk("irq %u", __entry->irq) ); +#define EXS(x) { x##_VECTOR, "#" #x } + +#define kvm_trace_sym_exc \ + EXS(DE), EXS(DB), EXS(BP), EXS(OF), EXS(BR), EXS(UD), EXS(NM), \ + EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF), \ + EXS(MF), EXS(MC) + +/* + * Tracepoint for kvm interrupt injection: + */ +TRACE_EVENT(kvm_inj_exception, + TP_PROTO(unsigned exception, bool has_error, unsigned error_code), + TP_ARGS(exception, has_error, error_code), + + TP_STRUCT__entry( + __field( u8, exception ) + __field( u8, has_error ) + __field( u32, error_code ) + ), + + TP_fast_assign( + __entry->exception = exception; + __entry->has_error = has_error; + __entry->error_code = error_code; + ), + + TP_printk("%s (0x%x)", + __print_symbolic(__entry->exception, kvm_trace_sym_exc), + /* FIXME: don't print error_code if not present */ + __entry->has_error ? __entry->error_code : 0) +); + /* * Tracepoint for page fault. */ @@ -413,12 +443,34 @@ TRACE_EVENT(kvm_nested_vmrun, ), TP_printk("rip: 0x%016llx vmcb: 0x%016llx nrip: 0x%016llx int_ctl: 0x%08x " - "event_inj: 0x%08x npt: %s\n", + "event_inj: 0x%08x npt: %s", __entry->rip, __entry->vmcb, __entry->nested_rip, __entry->int_ctl, __entry->event_inj, __entry->npt ? "on" : "off") ); +TRACE_EVENT(kvm_nested_intercepts, + TP_PROTO(__u16 cr_read, __u16 cr_write, __u32 exceptions, __u64 intercept), + TP_ARGS(cr_read, cr_write, exceptions, intercept), + + TP_STRUCT__entry( + __field( __u16, cr_read ) + __field( __u16, cr_write ) + __field( __u32, exceptions ) + __field( __u64, intercept ) + ), + + TP_fast_assign( + __entry->cr_read = cr_read; + __entry->cr_write = cr_write; + __entry->exceptions = exceptions; + __entry->intercept = intercept; + ), + + TP_printk("cr_read: %04x cr_write: %04x excp: %08x intercept: %016llx", + __entry->cr_read, __entry->cr_write, __entry->exceptions, + __entry->intercept) +); /* * Tracepoint for #VMEXIT while nested */ @@ -447,7 +499,7 @@ TRACE_EVENT(kvm_nested_vmexit, __entry->exit_int_info_err = exit_int_info_err; ), TP_printk("rip: 0x%016llx reason: %s ext_inf1: 0x%016llx " - "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n", + "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x", __entry->rip, ftrace_print_symbols_seq(p, __entry->exit_code, kvm_x86_ops->exit_reasons_str), @@ -482,7 +534,7 @@ TRACE_EVENT(kvm_nested_vmexit_inject, ), TP_printk("reason: %s ext_inf1: 0x%016llx " - "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n", + "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x", ftrace_print_symbols_seq(p, __entry->exit_code, kvm_x86_ops->exit_reasons_str), __entry->exit_info1, __entry->exit_info2, @@ -504,7 +556,7 @@ TRACE_EVENT(kvm_nested_intr_vmexit, __entry->rip = rip ), - TP_printk("rip: 0x%016llx\n", __entry->rip) + TP_printk("rip: 0x%016llx", __entry->rip) ); /* @@ -526,7 +578,7 @@ TRACE_EVENT(kvm_invlpga, __entry->address = address; ), - TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx\n", + TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx", __entry->rip, __entry->asid, __entry->address) ); @@ -547,11 +599,102 @@ TRACE_EVENT(kvm_skinit, __entry->slb = slb; ), - TP_printk("rip: 0x%016llx slb: 0x%08x\n", + TP_printk("rip: 0x%016llx slb: 0x%08x", __entry->rip, __entry->slb) ); +#define __print_insn(insn, ilen) ({ \ + int i; \ + const char *ret = p->buffer + p->len; \ + \ + for (i = 0; i < ilen; ++i) \ + trace_seq_printf(p, " %02x", insn[i]); \ + trace_seq_printf(p, "%c", 0); \ + ret; \ + }) + +#define KVM_EMUL_INSN_F_CR0_PE (1 << 0) +#define KVM_EMUL_INSN_F_EFL_VM (1 << 1) +#define KVM_EMUL_INSN_F_CS_D (1 << 2) +#define KVM_EMUL_INSN_F_CS_L (1 << 3) + +#define kvm_trace_symbol_emul_flags \ + { 0, "real" }, \ + { KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_EFL_VM, "vm16" }, \ + { KVM_EMUL_INSN_F_CR0_PE, "prot16" }, \ + { KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_CS_D, "prot32" }, \ + { KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_CS_L, "prot64" } + +#define kei_decode_mode(mode) ({ \ + u8 flags = 0xff; \ + switch (mode) { \ + case X86EMUL_MODE_REAL: \ + flags = 0; \ + break; \ + case X86EMUL_MODE_VM86: \ + flags = KVM_EMUL_INSN_F_EFL_VM; \ + break; \ + case X86EMUL_MODE_PROT16: \ + flags = KVM_EMUL_INSN_F_CR0_PE; \ + break; \ + case X86EMUL_MODE_PROT32: \ + flags = KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_CS_D; \ + break; \ + case X86EMUL_MODE_PROT64: \ + flags = KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_CS_L; \ + break; \ + } \ + flags; \ + }) + +TRACE_EVENT(kvm_emulate_insn, + TP_PROTO(struct kvm_vcpu *vcpu, __u8 failed), + TP_ARGS(vcpu, failed), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u32, csbase ) + __field( __u8, len ) + __array( __u8, insn, 15 ) + __field( __u8, flags ) + __field( __u8, failed ) + ), + + TP_fast_assign( + __entry->rip = vcpu->arch.emulate_ctxt.decode.fetch.start; + __entry->csbase = kvm_x86_ops->get_segment_base(vcpu, VCPU_SREG_CS); + __entry->len = vcpu->arch.emulate_ctxt.decode.eip + - vcpu->arch.emulate_ctxt.decode.fetch.start; + memcpy(__entry->insn, + vcpu->arch.emulate_ctxt.decode.fetch.data, + 15); + __entry->flags = kei_decode_mode(vcpu->arch.emulate_ctxt.mode); + __entry->failed = failed; + ), + + TP_printk("%x:%llx:%s (%s)%s", + __entry->csbase, __entry->rip, + __print_insn(__entry->insn, __entry->len), + __print_symbolic(__entry->flags, + kvm_trace_symbol_emul_flags), + __entry->failed ? " failed" : "" + ) + ); + +#define trace_kvm_emulate_insn_start(vcpu) trace_kvm_emulate_insn(vcpu, 0) +#define trace_kvm_emulate_insn_failed(vcpu) trace_kvm_emulate_insn(vcpu, 1) + #endif /* _TRACE_KVM_H */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH arch/x86/kvm +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + /* This part must be outside protection */ #include <trace/define_trace.h> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index bc933cfb4e66..875b785228f6 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -234,56 +234,56 @@ static const u32 vmx_msr_index[] = { }; #define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index) -static inline int is_page_fault(u32 intr_info) +static inline bool is_page_fault(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == (INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK); } -static inline int is_no_device(u32 intr_info) +static inline bool is_no_device(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == (INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK); } -static inline int is_invalid_opcode(u32 intr_info) +static inline bool is_invalid_opcode(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == (INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK); } -static inline int is_external_interrupt(u32 intr_info) +static inline bool is_external_interrupt(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) == (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK); } -static inline int is_machine_check(u32 intr_info) +static inline bool is_machine_check(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == (INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK); } -static inline int cpu_has_vmx_msr_bitmap(void) +static inline bool cpu_has_vmx_msr_bitmap(void) { return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS; } -static inline int cpu_has_vmx_tpr_shadow(void) +static inline bool cpu_has_vmx_tpr_shadow(void) { return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW; } -static inline int vm_need_tpr_shadow(struct kvm *kvm) +static inline bool vm_need_tpr_shadow(struct kvm *kvm) { return (cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm)); } -static inline int cpu_has_secondary_exec_ctrls(void) +static inline bool cpu_has_secondary_exec_ctrls(void) { return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; @@ -303,80 +303,80 @@ static inline bool cpu_has_vmx_flexpriority(void) static inline bool cpu_has_vmx_ept_execute_only(void) { - return !!(vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT); + return vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT; } static inline bool cpu_has_vmx_eptp_uncacheable(void) { - return !!(vmx_capability.ept & VMX_EPTP_UC_BIT); + return vmx_capability.ept & VMX_EPTP_UC_BIT; } static inline bool cpu_has_vmx_eptp_writeback(void) { - return !!(vmx_capability.ept & VMX_EPTP_WB_BIT); + return vmx_capability.ept & VMX_EPTP_WB_BIT; } static inline bool cpu_has_vmx_ept_2m_page(void) { - return !!(vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT); + return vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT; } static inline bool cpu_has_vmx_ept_1g_page(void) { - return !!(vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT); + return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT; } -static inline int cpu_has_vmx_invept_individual_addr(void) +static inline bool cpu_has_vmx_invept_individual_addr(void) { - return !!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT); + return vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT; } -static inline int cpu_has_vmx_invept_context(void) +static inline bool cpu_has_vmx_invept_context(void) { - return !!(vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT); + return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT; } -static inline int cpu_has_vmx_invept_global(void) +static inline bool cpu_has_vmx_invept_global(void) { - return !!(vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT); + return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT; } -static inline int cpu_has_vmx_ept(void) +static inline bool cpu_has_vmx_ept(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_EPT; } -static inline int cpu_has_vmx_unrestricted_guest(void) +static inline bool cpu_has_vmx_unrestricted_guest(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_UNRESTRICTED_GUEST; } -static inline int cpu_has_vmx_ple(void) +static inline bool cpu_has_vmx_ple(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_PAUSE_LOOP_EXITING; } -static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm) +static inline bool vm_need_virtualize_apic_accesses(struct kvm *kvm) { return flexpriority_enabled && irqchip_in_kernel(kvm); } -static inline int cpu_has_vmx_vpid(void) +static inline bool cpu_has_vmx_vpid(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_VPID; } -static inline int cpu_has_vmx_rdtscp(void) +static inline bool cpu_has_vmx_rdtscp(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_RDTSCP; } -static inline int cpu_has_virtual_nmis(void) +static inline bool cpu_has_virtual_nmis(void) { return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS; } @@ -600,11 +600,11 @@ static void reload_tss(void) /* * VT restores TR but not its size. Useless. */ - struct descriptor_table gdt; + struct desc_ptr gdt; struct desc_struct *descs; - kvm_get_gdt(&gdt); - descs = (void *)gdt.base; + native_store_gdt(&gdt); + descs = (void *)gdt.address; descs[GDT_ENTRY_TSS].type = 9; /* available TSS */ load_TR_desc(); } @@ -634,6 +634,43 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) return true; } +static unsigned long segment_base(u16 selector) +{ + struct desc_ptr gdt; + struct desc_struct *d; + unsigned long table_base; + unsigned long v; + + if (!(selector & ~3)) + return 0; + + native_store_gdt(&gdt); + table_base = gdt.address; + + if (selector & 4) { /* from ldt */ + u16 ldt_selector = kvm_read_ldt(); + + if (!(ldt_selector & ~3)) + return 0; + + table_base = segment_base(ldt_selector); + } + d = (struct desc_struct *)(table_base + (selector & ~7)); + v = get_desc_base(d); +#ifdef CONFIG_X86_64 + if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11)) + v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32; +#endif + return v; +} + +static inline unsigned long kvm_read_tr_base(void) +{ + u16 tr; + asm("str %0" : "=g"(tr)); + return segment_base(tr); +} + static void vmx_save_host_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -758,7 +795,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } if (vcpu->cpu != cpu) { - struct descriptor_table dt; + struct desc_ptr dt; unsigned long sysenter_esp; vcpu->cpu = cpu; @@ -767,8 +804,8 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) * processors. */ vmcs_writel(HOST_TR_BASE, kvm_read_tr_base()); /* 22.2.4 */ - kvm_get_gdt(&dt); - vmcs_writel(HOST_GDTR_BASE, dt.base); /* 22.2.4 */ + native_store_gdt(&dt); + vmcs_writel(HOST_GDTR_BASE, dt.address); /* 22.2.4 */ rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ @@ -846,9 +883,9 @@ static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) int ret = 0; if (interruptibility & GUEST_INTR_STATE_STI) - ret |= X86_SHADOW_INT_STI; + ret |= KVM_X86_SHADOW_INT_STI; if (interruptibility & GUEST_INTR_STATE_MOV_SS) - ret |= X86_SHADOW_INT_MOV_SS; + ret |= KVM_X86_SHADOW_INT_MOV_SS; return ret & mask; } @@ -860,9 +897,9 @@ static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS); - if (mask & X86_SHADOW_INT_MOV_SS) + if (mask & KVM_X86_SHADOW_INT_MOV_SS) interruptibility |= GUEST_INTR_STATE_MOV_SS; - if (mask & X86_SHADOW_INT_STI) + else if (mask & KVM_X86_SHADOW_INT_STI) interruptibility |= GUEST_INTR_STATE_STI; if ((interruptibility != interruptibility_old)) @@ -882,7 +919,8 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) } static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, - bool has_error_code, u32 error_code) + bool has_error_code, u32 error_code, + bool reinject) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 intr_info = nr | INTR_INFO_VALID_MASK; @@ -1521,7 +1559,7 @@ static gva_t rmode_tss_base(struct kvm *kvm) struct kvm_memslots *slots; gfn_t base_gfn; - slots = rcu_dereference(kvm->memslots); + slots = kvm_memslots(kvm); base_gfn = kvm->memslots->memslots[0].base_gfn + kvm->memslots->memslots[0].npages - 3; return base_gfn << PAGE_SHIFT; @@ -1934,28 +1972,28 @@ static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) *l = (ar >> 13) & 1; } -static void vmx_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { - dt->limit = vmcs_read32(GUEST_IDTR_LIMIT); - dt->base = vmcs_readl(GUEST_IDTR_BASE); + dt->size = vmcs_read32(GUEST_IDTR_LIMIT); + dt->address = vmcs_readl(GUEST_IDTR_BASE); } -static void vmx_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { - vmcs_write32(GUEST_IDTR_LIMIT, dt->limit); - vmcs_writel(GUEST_IDTR_BASE, dt->base); + vmcs_write32(GUEST_IDTR_LIMIT, dt->size); + vmcs_writel(GUEST_IDTR_BASE, dt->address); } -static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { - dt->limit = vmcs_read32(GUEST_GDTR_LIMIT); - dt->base = vmcs_readl(GUEST_GDTR_BASE); + dt->size = vmcs_read32(GUEST_GDTR_LIMIT); + dt->address = vmcs_readl(GUEST_GDTR_BASE); } -static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { - vmcs_write32(GUEST_GDTR_LIMIT, dt->limit); - vmcs_writel(GUEST_GDTR_BASE, dt->base); + vmcs_write32(GUEST_GDTR_LIMIT, dt->size); + vmcs_writel(GUEST_GDTR_BASE, dt->address); } static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg) @@ -2296,6 +2334,16 @@ static void allocate_vpid(struct vcpu_vmx *vmx) spin_unlock(&vmx_vpid_lock); } +static void free_vpid(struct vcpu_vmx *vmx) +{ + if (!enable_vpid) + return; + spin_lock(&vmx_vpid_lock); + if (vmx->vpid != 0) + __clear_bit(vmx->vpid, vmx_vpid_bitmap); + spin_unlock(&vmx_vpid_lock); +} + static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr) { int f = sizeof(unsigned long); @@ -2334,7 +2382,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) u32 junk; u64 host_pat, tsc_this, tsc_base; unsigned long a; - struct descriptor_table dt; + struct desc_ptr dt; int i; unsigned long kvm_vmx_return; u32 exec_control; @@ -2415,8 +2463,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */ - kvm_get_idt(&dt); - vmcs_writel(HOST_IDTR_BASE, dt.base); /* 22.2.4 */ + native_store_idt(&dt); + vmcs_writel(HOST_IDTR_BASE, dt.address); /* 22.2.4 */ asm("mov $.Lkvm_vmx_return, %0" : "=r"(kvm_vmx_return)); vmcs_writel(HOST_RIP, kvm_vmx_return); /* 22.2.5 */ @@ -2948,22 +2996,20 @@ static int handle_io(struct kvm_vcpu *vcpu) int size, in, string; unsigned port; - ++vcpu->stat.io_exits; exit_qualification = vmcs_readl(EXIT_QUALIFICATION); string = (exit_qualification & 16) != 0; + in = (exit_qualification & 8) != 0; - if (string) { - if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO) - return 0; - return 1; - } + ++vcpu->stat.io_exits; - size = (exit_qualification & 7) + 1; - in = (exit_qualification & 8) != 0; - port = exit_qualification >> 16; + if (string || in) + return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO); + port = exit_qualification >> 16; + size = (exit_qualification & 7) + 1; skip_emulated_instruction(vcpu); - return kvm_emulate_pio(vcpu, in, size, port); + + return kvm_fast_pio_out(vcpu, size, port); } static void @@ -3054,19 +3100,9 @@ static int handle_cr(struct kvm_vcpu *vcpu) return 0; } -static int check_dr_alias(struct kvm_vcpu *vcpu) -{ - if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) { - kvm_queue_exception(vcpu, UD_VECTOR); - return -1; - } - return 0; -} - static int handle_dr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; - unsigned long val; int dr, reg; /* Do not handle if the CPL > 0, will trigger GP on re-entry */ @@ -3101,67 +3137,20 @@ static int handle_dr(struct kvm_vcpu *vcpu) dr = exit_qualification & DEBUG_REG_ACCESS_NUM; reg = DEBUG_REG_ACCESS_REG(exit_qualification); if (exit_qualification & TYPE_MOV_FROM_DR) { - switch (dr) { - case 0 ... 3: - val = vcpu->arch.db[dr]; - break; - case 4: - if (check_dr_alias(vcpu) < 0) - return 1; - /* fall through */ - case 6: - val = vcpu->arch.dr6; - break; - case 5: - if (check_dr_alias(vcpu) < 0) - return 1; - /* fall through */ - default: /* 7 */ - val = vcpu->arch.dr7; - break; - } - kvm_register_write(vcpu, reg, val); - } else { - val = vcpu->arch.regs[reg]; - switch (dr) { - case 0 ... 3: - vcpu->arch.db[dr] = val; - if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) - vcpu->arch.eff_db[dr] = val; - break; - case 4: - if (check_dr_alias(vcpu) < 0) - return 1; - /* fall through */ - case 6: - if (val & 0xffffffff00000000ULL) { - kvm_inject_gp(vcpu, 0); - return 1; - } - vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1; - break; - case 5: - if (check_dr_alias(vcpu) < 0) - return 1; - /* fall through */ - default: /* 7 */ - if (val & 0xffffffff00000000ULL) { - kvm_inject_gp(vcpu, 0); - return 1; - } - vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; - if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { - vmcs_writel(GUEST_DR7, vcpu->arch.dr7); - vcpu->arch.switch_db_regs = - (val & DR7_BP_EN_MASK); - } - break; - } - } + unsigned long val; + if (!kvm_get_dr(vcpu, dr, &val)) + kvm_register_write(vcpu, reg, val); + } else + kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg]); skip_emulated_instruction(vcpu); return 1; } +static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) +{ + vmcs_writel(GUEST_DR7, val); +} + static int handle_cpuid(struct kvm_vcpu *vcpu) { kvm_emulate_cpuid(vcpu); @@ -3293,6 +3282,8 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qualification; + bool has_error_code = false; + u32 error_code = 0; u16 tss_selector; int reason, type, idt_v; @@ -3315,6 +3306,13 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) kvm_clear_interrupt_queue(vcpu); break; case INTR_TYPE_HARD_EXCEPTION: + if (vmx->idt_vectoring_info & + VECTORING_INFO_DELIVER_CODE_MASK) { + has_error_code = true; + error_code = + vmcs_read32(IDT_VECTORING_ERROR_CODE); + } + /* fall through */ case INTR_TYPE_SOFT_EXCEPTION: kvm_clear_exception_queue(vcpu); break; @@ -3329,8 +3327,13 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) type != INTR_TYPE_NMI_INTR)) skip_emulated_instruction(vcpu); - if (!kvm_task_switch(vcpu, tss_selector, reason)) + if (kvm_task_switch(vcpu, tss_selector, reason, + has_error_code, error_code) == EMULATE_FAIL) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; return 0; + } /* clear all local breakpoint enable flags */ vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55); @@ -3575,7 +3578,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; - trace_kvm_exit(exit_reason, kvm_rip_read(vcpu)); + trace_kvm_exit(exit_reason, vcpu); /* If guest state is invalid, start emulating */ if (vmx->emulation_required && emulate_invalid_guest_state) @@ -3660,8 +3663,11 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx) /* We need to handle NMIs before interrupts are enabled */ if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR && - (exit_intr_info & INTR_INFO_VALID_MASK)) + (exit_intr_info & INTR_INFO_VALID_MASK)) { + kvm_before_handle_nmi(&vmx->vcpu); asm("int $2"); + kvm_after_handle_nmi(&vmx->vcpu); + } idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK; @@ -3921,10 +3927,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - spin_lock(&vmx_vpid_lock); - if (vmx->vpid != 0) - __clear_bit(vmx->vpid, vmx_vpid_bitmap); - spin_unlock(&vmx_vpid_lock); + free_vpid(vmx); vmx_free_vmcs(vcpu); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); @@ -3986,6 +3989,7 @@ free_msrs: uninit_vcpu: kvm_vcpu_uninit(&vmx->vcpu); free_vcpu: + free_vpid(vmx); kmem_cache_free(kvm_vcpu_cache, vmx); return ERR_PTR(err); } @@ -4116,6 +4120,10 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) } } +static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) +{ +} + static struct kvm_x86_ops vmx_x86_ops = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -4152,6 +4160,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .set_idt = vmx_set_idt, .get_gdt = vmx_get_gdt, .set_gdt = vmx_set_gdt, + .set_dr7 = vmx_set_dr7, .cache_reg = vmx_cache_reg, .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, @@ -4187,6 +4196,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .cpuid_update = vmx_cpuid_update, .rdtscp_supported = vmx_rdtscp_supported, + + .set_supported_cpuid = vmx_set_supported_cpuid, }; static int __init vmx_init(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3c4ca98ad27f..6b2ce1d2d748 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -40,8 +40,9 @@ #include <linux/user-return-notifier.h> #include <linux/srcu.h> #include <linux/slab.h> +#include <linux/perf_event.h> #include <trace/events/kvm.h> -#undef TRACE_INCLUDE_FILE + #define CREATE_TRACE_POINTS #include "trace.h" @@ -223,34 +224,6 @@ static void drop_user_return_notifiers(void *ignore) kvm_on_user_return(&smsr->urn); } -unsigned long segment_base(u16 selector) -{ - struct descriptor_table gdt; - struct desc_struct *d; - unsigned long table_base; - unsigned long v; - - if (selector == 0) - return 0; - - kvm_get_gdt(&gdt); - table_base = gdt.base; - - if (selector & 4) { /* from ldt */ - u16 ldt_selector = kvm_read_ldt(); - - table_base = segment_base(ldt_selector); - } - d = (struct desc_struct *)(table_base + (selector & ~7)); - v = get_desc_base(d); -#ifdef CONFIG_X86_64 - if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11)) - v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32; -#endif - return v; -} -EXPORT_SYMBOL_GPL(segment_base); - u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) { if (irqchip_in_kernel(vcpu->kvm)) @@ -292,7 +265,8 @@ static int exception_class(int vector) } static void kvm_multiple_exception(struct kvm_vcpu *vcpu, - unsigned nr, bool has_error, u32 error_code) + unsigned nr, bool has_error, u32 error_code, + bool reinject) { u32 prev_nr; int class1, class2; @@ -303,6 +277,7 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, vcpu->arch.exception.has_error_code = has_error; vcpu->arch.exception.nr = nr; vcpu->arch.exception.error_code = error_code; + vcpu->arch.exception.reinject = true; return; } @@ -331,10 +306,16 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr) { - kvm_multiple_exception(vcpu, nr, false, 0); + kvm_multiple_exception(vcpu, nr, false, 0, false); } EXPORT_SYMBOL_GPL(kvm_queue_exception); +void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr) +{ + kvm_multiple_exception(vcpu, nr, false, 0, true); +} +EXPORT_SYMBOL_GPL(kvm_requeue_exception); + void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr, u32 error_code) { @@ -351,10 +332,16 @@ EXPORT_SYMBOL_GPL(kvm_inject_nmi); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) { - kvm_multiple_exception(vcpu, nr, true, error_code); + kvm_multiple_exception(vcpu, nr, true, error_code, false); } EXPORT_SYMBOL_GPL(kvm_queue_exception_e); +void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) +{ + kvm_multiple_exception(vcpu, nr, true, error_code, true); +} +EXPORT_SYMBOL_GPL(kvm_requeue_exception_e); + /* * Checks if cpl <= required_cpl; if true, return true. Otherwise queue * a #GP and return false. @@ -475,7 +462,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } kvm_x86_ops->set_cr0(vcpu, cr0); - vcpu->arch.cr0 = cr0; kvm_mmu_reset_context(vcpu); return; @@ -516,7 +502,6 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) } kvm_x86_ops->set_cr4(vcpu, cr4); vcpu->arch.cr4 = cr4; - vcpu->arch.mmu.base_role.cr4_pge = (cr4 & X86_CR4_PGE) && !tdp_enabled; kvm_mmu_reset_context(vcpu); } EXPORT_SYMBOL_GPL(kvm_set_cr4); @@ -591,6 +576,80 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_get_cr8); +int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) +{ + switch (dr) { + case 0 ... 3: + vcpu->arch.db[dr] = val; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) + vcpu->arch.eff_db[dr] = val; + break; + case 4: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + /* fall through */ + case 6: + if (val & 0xffffffff00000000ULL) { + kvm_inject_gp(vcpu, 0); + return 1; + } + vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1; + break; + case 5: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + /* fall through */ + default: /* 7 */ + if (val & 0xffffffff00000000ULL) { + kvm_inject_gp(vcpu, 0); + return 1; + } + vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { + kvm_x86_ops->set_dr7(vcpu, vcpu->arch.dr7); + vcpu->arch.switch_db_regs = (val & DR7_BP_EN_MASK); + } + break; + } + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_set_dr); + +int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) +{ + switch (dr) { + case 0 ... 3: + *val = vcpu->arch.db[dr]; + break; + case 4: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + /* fall through */ + case 6: + *val = vcpu->arch.dr6; + break; + case 5: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + /* fall through */ + default: /* 7 */ + *val = vcpu->arch.dr7; + break; + } + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_get_dr); + static inline u32 bit(int bitno) { return 1 << (bitno & 31); @@ -1090,6 +1149,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) break; case MSR_K7_HWCR: data &= ~(u64)0x40; /* ignore flush filter disable */ + data &= ~(u64)0x100; /* ignore ignne emulation enable */ if (data != 0) { pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", data); @@ -1548,6 +1608,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: case KVM_CAP_PCI_SEGMENT: + case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: r = 1; break; @@ -1913,6 +1974,9 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx &= kvm_supported_word6_x86_features; break; } + + kvm_x86_ops->set_supported_cpuid(function, entry); + put_cpu(); } @@ -2100,14 +2164,20 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, { vcpu_load(vcpu); - events->exception.injected = vcpu->arch.exception.pending; + events->exception.injected = + vcpu->arch.exception.pending && + !kvm_exception_is_soft(vcpu->arch.exception.nr); events->exception.nr = vcpu->arch.exception.nr; events->exception.has_error_code = vcpu->arch.exception.has_error_code; events->exception.error_code = vcpu->arch.exception.error_code; - events->interrupt.injected = vcpu->arch.interrupt.pending; + events->interrupt.injected = + vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft; events->interrupt.nr = vcpu->arch.interrupt.nr; - events->interrupt.soft = vcpu->arch.interrupt.soft; + events->interrupt.soft = 0; + events->interrupt.shadow = + kvm_x86_ops->get_interrupt_shadow(vcpu, + KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI); events->nmi.injected = vcpu->arch.nmi_injected; events->nmi.pending = vcpu->arch.nmi_pending; @@ -2116,7 +2186,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->sipi_vector = vcpu->arch.sipi_vector; events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING - | KVM_VCPUEVENT_VALID_SIPI_VECTOR); + | KVM_VCPUEVENT_VALID_SIPI_VECTOR + | KVM_VCPUEVENT_VALID_SHADOW); vcpu_put(vcpu); } @@ -2125,7 +2196,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING - | KVM_VCPUEVENT_VALID_SIPI_VECTOR)) + | KVM_VCPUEVENT_VALID_SIPI_VECTOR + | KVM_VCPUEVENT_VALID_SHADOW)) return -EINVAL; vcpu_load(vcpu); @@ -2140,6 +2212,9 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.interrupt.soft = events->interrupt.soft; if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm)) kvm_pic_clear_isr_ack(vcpu->kvm); + if (events->flags & KVM_VCPUEVENT_VALID_SHADOW) + kvm_x86_ops->set_interrupt_shadow(vcpu, + events->interrupt.shadow); vcpu->arch.nmi_injected = events->nmi.injected; if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) @@ -2154,6 +2229,36 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, return 0; } +static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, + struct kvm_debugregs *dbgregs) +{ + vcpu_load(vcpu); + + memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); + dbgregs->dr6 = vcpu->arch.dr6; + dbgregs->dr7 = vcpu->arch.dr7; + dbgregs->flags = 0; + + vcpu_put(vcpu); +} + +static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, + struct kvm_debugregs *dbgregs) +{ + if (dbgregs->flags) + return -EINVAL; + + vcpu_load(vcpu); + + memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); + vcpu->arch.dr6 = dbgregs->dr6; + vcpu->arch.dr7 = dbgregs->dr7; + + vcpu_put(vcpu); + + return 0; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2332,6 +2437,29 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events); break; } + case KVM_GET_DEBUGREGS: { + struct kvm_debugregs dbgregs; + + kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs); + + r = -EFAULT; + if (copy_to_user(argp, &dbgregs, + sizeof(struct kvm_debugregs))) + break; + r = 0; + break; + } + case KVM_SET_DEBUGREGS: { + struct kvm_debugregs dbgregs; + + r = -EFAULT; + if (copy_from_user(&dbgregs, argp, + sizeof(struct kvm_debugregs))) + break; + + r = kvm_vcpu_ioctl_x86_set_debugregs(vcpu, &dbgregs); + break; + } default: r = -EINVAL; } @@ -2385,7 +2513,7 @@ gfn_t unalias_gfn_instantiation(struct kvm *kvm, gfn_t gfn) struct kvm_mem_alias *alias; struct kvm_mem_aliases *aliases; - aliases = rcu_dereference(kvm->arch.aliases); + aliases = kvm_aliases(kvm); for (i = 0; i < aliases->naliases; ++i) { alias = &aliases->aliases[i]; @@ -2404,7 +2532,7 @@ gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) struct kvm_mem_alias *alias; struct kvm_mem_aliases *aliases; - aliases = rcu_dereference(kvm->arch.aliases); + aliases = kvm_aliases(kvm); for (i = 0; i < aliases->naliases; ++i) { alias = &aliases->aliases[i]; @@ -2799,11 +2927,13 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&irq_event, argp, sizeof irq_event)) goto out; + r = -ENXIO; if (irqchip_in_kernel(kvm)) { __s32 status; status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); if (ioctl == KVM_IRQ_LINE_STATUS) { + r = -EFAULT; irq_event.status = status; if (copy_to_user(argp, &irq_event, sizeof irq_event)) @@ -3019,6 +3149,18 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) return kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, len, v); } +static void kvm_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + kvm_x86_ops->set_segment(vcpu, var, seg); +} + +void kvm_get_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + kvm_x86_ops->get_segment(vcpu, var, seg); +} + gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error) { u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; @@ -3099,14 +3241,17 @@ static int kvm_read_guest_virt_system(gva_t addr, void *val, unsigned int bytes, return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, error); } -static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes, - struct kvm_vcpu *vcpu, u32 *error) +static int kvm_write_guest_virt_system(gva_t addr, void *val, + unsigned int bytes, + struct kvm_vcpu *vcpu, + u32 *error) { void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { - gpa_t gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, error); + gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr, + PFERR_WRITE_MASK, error); unsigned offset = addr & (PAGE_SIZE-1); unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; @@ -3129,7 +3274,6 @@ out: return r; } - static int emulator_read_emulated(unsigned long addr, void *val, unsigned int bytes, @@ -3232,9 +3376,9 @@ mmio: } int emulator_write_emulated(unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) + const void *val, + unsigned int bytes, + struct kvm_vcpu *vcpu) { /* Crossing a page boundary? */ if (((addr + bytes - 1) ^ addr) & PAGE_MASK) { @@ -3252,45 +3396,150 @@ int emulator_write_emulated(unsigned long addr, } EXPORT_SYMBOL_GPL(emulator_write_emulated); +#define CMPXCHG_TYPE(t, ptr, old, new) \ + (cmpxchg((t *)(ptr), *(t *)(old), *(t *)(new)) == *(t *)(old)) + +#ifdef CONFIG_X86_64 +# define CMPXCHG64(ptr, old, new) CMPXCHG_TYPE(u64, ptr, old, new) +#else +# define CMPXCHG64(ptr, old, new) \ + (cmpxchg64((u64 *)(ptr), *(u64 *)(old), *(u64 *)(new)) == *(u64 *)(old)) +#endif + static int emulator_cmpxchg_emulated(unsigned long addr, const void *old, const void *new, unsigned int bytes, struct kvm_vcpu *vcpu) { - printk_once(KERN_WARNING "kvm: emulating exchange as write\n"); -#ifndef CONFIG_X86_64 - /* guests cmpxchg8b have to be emulated atomically */ - if (bytes == 8) { - gpa_t gpa; - struct page *page; - char *kaddr; - u64 val; + gpa_t gpa; + struct page *page; + char *kaddr; + bool exchanged; - gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL); + /* guests cmpxchg8b have to be emulated atomically */ + if (bytes > 8 || (bytes & (bytes - 1))) + goto emul_write; - if (gpa == UNMAPPED_GVA || - (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) - goto emul_write; + gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL); - if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) - goto emul_write; + if (gpa == UNMAPPED_GVA || + (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + goto emul_write; - val = *(u64 *)new; + if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) + goto emul_write; - page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); - kaddr = kmap_atomic(page, KM_USER0); - set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val); - kunmap_atomic(kaddr, KM_USER0); - kvm_release_page_dirty(page); + kaddr = kmap_atomic(page, KM_USER0); + kaddr += offset_in_page(gpa); + switch (bytes) { + case 1: + exchanged = CMPXCHG_TYPE(u8, kaddr, old, new); + break; + case 2: + exchanged = CMPXCHG_TYPE(u16, kaddr, old, new); + break; + case 4: + exchanged = CMPXCHG_TYPE(u32, kaddr, old, new); + break; + case 8: + exchanged = CMPXCHG64(kaddr, old, new); + break; + default: + BUG(); } + kunmap_atomic(kaddr, KM_USER0); + kvm_release_page_dirty(page); + + if (!exchanged) + return X86EMUL_CMPXCHG_FAILED; + + kvm_mmu_pte_write(vcpu, gpa, new, bytes, 1); + + return X86EMUL_CONTINUE; + emul_write: -#endif + printk_once(KERN_WARNING "kvm: emulating exchange as write\n"); return emulator_write_emulated(addr, new, bytes, vcpu); } +static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) +{ + /* TODO: String I/O for in kernel device */ + int r; + + if (vcpu->arch.pio.in) + r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port, + vcpu->arch.pio.size, pd); + else + r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, + vcpu->arch.pio.port, vcpu->arch.pio.size, + pd); + return r; +} + + +static int emulator_pio_in_emulated(int size, unsigned short port, void *val, + unsigned int count, struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.pio.count) + goto data_avail; + + trace_kvm_pio(1, port, size, 1); + + vcpu->arch.pio.port = port; + vcpu->arch.pio.in = 1; + vcpu->arch.pio.count = count; + vcpu->arch.pio.size = size; + + if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { + data_avail: + memcpy(val, vcpu->arch.pio_data, size * count); + vcpu->arch.pio.count = 0; + return 1; + } + + vcpu->run->exit_reason = KVM_EXIT_IO; + vcpu->run->io.direction = KVM_EXIT_IO_IN; + vcpu->run->io.size = size; + vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; + vcpu->run->io.count = count; + vcpu->run->io.port = port; + + return 0; +} + +static int emulator_pio_out_emulated(int size, unsigned short port, + const void *val, unsigned int count, + struct kvm_vcpu *vcpu) +{ + trace_kvm_pio(0, port, size, 1); + + vcpu->arch.pio.port = port; + vcpu->arch.pio.in = 0; + vcpu->arch.pio.count = count; + vcpu->arch.pio.size = size; + + memcpy(vcpu->arch.pio_data, val, size * count); + + if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { + vcpu->arch.pio.count = 0; + return 1; + } + + vcpu->run->exit_reason = KVM_EXIT_IO; + vcpu->run->io.direction = KVM_EXIT_IO_OUT; + vcpu->run->io.size = size; + vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; + vcpu->run->io.count = count; + vcpu->run->io.port = port; + + return 0; +} + static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) { return kvm_x86_ops->get_segment_base(vcpu, seg); @@ -3311,14 +3560,14 @@ int emulate_clts(struct kvm_vcpu *vcpu) int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest) { - return kvm_x86_ops->get_dr(ctxt->vcpu, dr, dest); + return kvm_get_dr(ctxt->vcpu, dr, dest); } int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) { unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U; - return kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask); + return kvm_set_dr(ctxt->vcpu, dr, value & mask); } void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) @@ -3339,12 +3588,167 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) } EXPORT_SYMBOL_GPL(kvm_report_emulation_failure); +static u64 mk_cr_64(u64 curr_cr, u32 new_val) +{ + return (curr_cr & ~((1ULL << 32) - 1)) | new_val; +} + +static unsigned long emulator_get_cr(int cr, struct kvm_vcpu *vcpu) +{ + unsigned long value; + + switch (cr) { + case 0: + value = kvm_read_cr0(vcpu); + break; + case 2: + value = vcpu->arch.cr2; + break; + case 3: + value = vcpu->arch.cr3; + break; + case 4: + value = kvm_read_cr4(vcpu); + break; + case 8: + value = kvm_get_cr8(vcpu); + break; + default: + vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); + return 0; + } + + return value; +} + +static void emulator_set_cr(int cr, unsigned long val, struct kvm_vcpu *vcpu) +{ + switch (cr) { + case 0: + kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val)); + break; + case 2: + vcpu->arch.cr2 = val; + break; + case 3: + kvm_set_cr3(vcpu, val); + break; + case 4: + kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val)); + break; + case 8: + kvm_set_cr8(vcpu, val & 0xfUL); + break; + default: + vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); + } +} + +static int emulator_get_cpl(struct kvm_vcpu *vcpu) +{ + return kvm_x86_ops->get_cpl(vcpu); +} + +static void emulator_get_gdt(struct desc_ptr *dt, struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->get_gdt(vcpu, dt); +} + +static bool emulator_get_cached_descriptor(struct desc_struct *desc, int seg, + struct kvm_vcpu *vcpu) +{ + struct kvm_segment var; + + kvm_get_segment(vcpu, &var, seg); + + if (var.unusable) + return false; + + if (var.g) + var.limit >>= 12; + set_desc_limit(desc, var.limit); + set_desc_base(desc, (unsigned long)var.base); + desc->type = var.type; + desc->s = var.s; + desc->dpl = var.dpl; + desc->p = var.present; + desc->avl = var.avl; + desc->l = var.l; + desc->d = var.db; + desc->g = var.g; + + return true; +} + +static void emulator_set_cached_descriptor(struct desc_struct *desc, int seg, + struct kvm_vcpu *vcpu) +{ + struct kvm_segment var; + + /* needed to preserve selector */ + kvm_get_segment(vcpu, &var, seg); + + var.base = get_desc_base(desc); + var.limit = get_desc_limit(desc); + if (desc->g) + var.limit = (var.limit << 12) | 0xfff; + var.type = desc->type; + var.present = desc->p; + var.dpl = desc->dpl; + var.db = desc->d; + var.s = desc->s; + var.l = desc->l; + var.g = desc->g; + var.avl = desc->avl; + var.present = desc->p; + var.unusable = !var.present; + var.padding = 0; + + kvm_set_segment(vcpu, &var, seg); + return; +} + +static u16 emulator_get_segment_selector(int seg, struct kvm_vcpu *vcpu) +{ + struct kvm_segment kvm_seg; + + kvm_get_segment(vcpu, &kvm_seg, seg); + return kvm_seg.selector; +} + +static void emulator_set_segment_selector(u16 sel, int seg, + struct kvm_vcpu *vcpu) +{ + struct kvm_segment kvm_seg; + + kvm_get_segment(vcpu, &kvm_seg, seg); + kvm_seg.selector = sel; + kvm_set_segment(vcpu, &kvm_seg, seg); +} + +static void emulator_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + kvm_x86_ops->set_rflags(vcpu, rflags); +} + static struct x86_emulate_ops emulate_ops = { .read_std = kvm_read_guest_virt_system, + .write_std = kvm_write_guest_virt_system, .fetch = kvm_fetch_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, .cmpxchg_emulated = emulator_cmpxchg_emulated, + .pio_in_emulated = emulator_pio_in_emulated, + .pio_out_emulated = emulator_pio_out_emulated, + .get_cached_descriptor = emulator_get_cached_descriptor, + .set_cached_descriptor = emulator_set_cached_descriptor, + .get_segment_selector = emulator_get_segment_selector, + .set_segment_selector = emulator_set_segment_selector, + .get_gdt = emulator_get_gdt, + .get_cr = emulator_get_cr, + .set_cr = emulator_set_cr, + .cpl = emulator_get_cpl, + .set_rflags = emulator_set_rflags, }; static void cache_all_regs(struct kvm_vcpu *vcpu) @@ -3375,14 +3779,14 @@ int emulate_instruction(struct kvm_vcpu *vcpu, cache_all_regs(vcpu); vcpu->mmio_is_write = 0; - vcpu->arch.pio.string = 0; if (!(emulation_type & EMULTYPE_NO_DECODE)) { int cs_db, cs_l; kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); vcpu->arch.emulate_ctxt.vcpu = vcpu; - vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(vcpu); + vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu); + vcpu->arch.emulate_ctxt.eip = kvm_rip_read(vcpu); vcpu->arch.emulate_ctxt.mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM) @@ -3391,6 +3795,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu, ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; r = x86_decode_insn(&vcpu->arch.emulate_ctxt, &emulate_ops); + trace_kvm_emulate_insn_start(vcpu); /* Only allow emulation of specific instructions on #UD * (namely VMMCALL, sysenter, sysexit, syscall)*/ @@ -3423,6 +3828,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu, ++vcpu->stat.insn_emulation; if (r) { ++vcpu->stat.insn_emulation_fail; + trace_kvm_emulate_insn_failed(vcpu); if (kvm_mmu_unprotect_page_virt(vcpu, cr2)) return EMULATE_DONE; return EMULATE_FAIL; @@ -3434,16 +3840,20 @@ int emulate_instruction(struct kvm_vcpu *vcpu, return EMULATE_DONE; } +restart: r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops); shadow_mask = vcpu->arch.emulate_ctxt.interruptibility; if (r == 0) kvm_x86_ops->set_interrupt_shadow(vcpu, shadow_mask); - if (vcpu->arch.pio.string) + if (vcpu->arch.pio.count) { + if (!vcpu->arch.pio.in) + vcpu->arch.pio.count = 0; return EMULATE_DO_MMIO; + } - if ((r || vcpu->mmio_is_write) && run) { + if (r || vcpu->mmio_is_write) { run->exit_reason = KVM_EXIT_MMIO; run->mmio.phys_addr = vcpu->mmio_phys_addr; memcpy(run->mmio.data, vcpu->mmio_data, 8); @@ -3453,222 +3863,41 @@ int emulate_instruction(struct kvm_vcpu *vcpu, if (r) { if (kvm_mmu_unprotect_page_virt(vcpu, cr2)) - return EMULATE_DONE; + goto done; if (!vcpu->mmio_needed) { + ++vcpu->stat.insn_emulation_fail; + trace_kvm_emulate_insn_failed(vcpu); kvm_report_emulation_failure(vcpu, "mmio"); return EMULATE_FAIL; } return EMULATE_DO_MMIO; } - kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); - if (vcpu->mmio_is_write) { vcpu->mmio_needed = 0; return EMULATE_DO_MMIO; } - return EMULATE_DONE; -} -EXPORT_SYMBOL_GPL(emulate_instruction); - -static int pio_copy_data(struct kvm_vcpu *vcpu) -{ - void *p = vcpu->arch.pio_data; - gva_t q = vcpu->arch.pio.guest_gva; - unsigned bytes; - int ret; - u32 error_code; - - bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count; - if (vcpu->arch.pio.in) - ret = kvm_write_guest_virt(q, p, bytes, vcpu, &error_code); - else - ret = kvm_read_guest_virt(q, p, bytes, vcpu, &error_code); - - if (ret == X86EMUL_PROPAGATE_FAULT) - kvm_inject_page_fault(vcpu, q, error_code); - - return ret; -} - -int complete_pio(struct kvm_vcpu *vcpu) -{ - struct kvm_pio_request *io = &vcpu->arch.pio; - long delta; - int r; - unsigned long val; - - if (!io->string) { - if (io->in) { - val = kvm_register_read(vcpu, VCPU_REGS_RAX); - memcpy(&val, vcpu->arch.pio_data, io->size); - kvm_register_write(vcpu, VCPU_REGS_RAX, val); - } - } else { - if (io->in) { - r = pio_copy_data(vcpu); - if (r) - goto out; - } - - delta = 1; - if (io->rep) { - delta *= io->cur_count; - /* - * The size of the register should really depend on - * current address size. - */ - val = kvm_register_read(vcpu, VCPU_REGS_RCX); - val -= delta; - kvm_register_write(vcpu, VCPU_REGS_RCX, val); - } - if (io->down) - delta = -delta; - delta *= io->size; - if (io->in) { - val = kvm_register_read(vcpu, VCPU_REGS_RDI); - val += delta; - kvm_register_write(vcpu, VCPU_REGS_RDI, val); - } else { - val = kvm_register_read(vcpu, VCPU_REGS_RSI); - val += delta; - kvm_register_write(vcpu, VCPU_REGS_RSI, val); - } - } -out: - io->count -= io->cur_count; - io->cur_count = 0; - - return 0; -} +done: + if (vcpu->arch.exception.pending) + vcpu->arch.emulate_ctxt.restart = false; -static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) -{ - /* TODO: String I/O for in kernel device */ - int r; + if (vcpu->arch.emulate_ctxt.restart) + goto restart; - if (vcpu->arch.pio.in) - r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port, - vcpu->arch.pio.size, pd); - else - r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, - vcpu->arch.pio.port, vcpu->arch.pio.size, - pd); - return r; -} - -static int pio_string_write(struct kvm_vcpu *vcpu) -{ - struct kvm_pio_request *io = &vcpu->arch.pio; - void *pd = vcpu->arch.pio_data; - int i, r = 0; - - for (i = 0; i < io->cur_count; i++) { - if (kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, - io->port, io->size, pd)) { - r = -EOPNOTSUPP; - break; - } - pd += io->size; - } - return r; -} - -int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port) -{ - unsigned long val; - - trace_kvm_pio(!in, port, size, 1); - - vcpu->run->exit_reason = KVM_EXIT_IO; - vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; - vcpu->run->io.size = vcpu->arch.pio.size = size; - vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; - vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = 1; - vcpu->run->io.port = vcpu->arch.pio.port = port; - vcpu->arch.pio.in = in; - vcpu->arch.pio.string = 0; - vcpu->arch.pio.down = 0; - vcpu->arch.pio.rep = 0; - - if (!vcpu->arch.pio.in) { - val = kvm_register_read(vcpu, VCPU_REGS_RAX); - memcpy(vcpu->arch.pio_data, &val, 4); - } - - if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { - complete_pio(vcpu); - return 1; - } - return 0; + return EMULATE_DONE; } -EXPORT_SYMBOL_GPL(kvm_emulate_pio); +EXPORT_SYMBOL_GPL(emulate_instruction); -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in, - int size, unsigned long count, int down, - gva_t address, int rep, unsigned port) +int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) { - unsigned now, in_page; - int ret = 0; - - trace_kvm_pio(!in, port, size, count); - - vcpu->run->exit_reason = KVM_EXIT_IO; - vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; - vcpu->run->io.size = vcpu->arch.pio.size = size; - vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; - vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count; - vcpu->run->io.port = vcpu->arch.pio.port = port; - vcpu->arch.pio.in = in; - vcpu->arch.pio.string = 1; - vcpu->arch.pio.down = down; - vcpu->arch.pio.rep = rep; - - if (!count) { - kvm_x86_ops->skip_emulated_instruction(vcpu); - return 1; - } - - if (!down) - in_page = PAGE_SIZE - offset_in_page(address); - else - in_page = offset_in_page(address) + size; - now = min(count, (unsigned long)in_page / size); - if (!now) - now = 1; - if (down) { - /* - * String I/O in reverse. Yuck. Kill the guest, fix later. - */ - pr_unimpl(vcpu, "guest string pio down\n"); - kvm_inject_gp(vcpu, 0); - return 1; - } - vcpu->run->io.count = now; - vcpu->arch.pio.cur_count = now; - - if (vcpu->arch.pio.cur_count == vcpu->arch.pio.count) - kvm_x86_ops->skip_emulated_instruction(vcpu); - - vcpu->arch.pio.guest_gva = address; - - if (!vcpu->arch.pio.in) { - /* string PIO write */ - ret = pio_copy_data(vcpu); - if (ret == X86EMUL_PROPAGATE_FAULT) - return 1; - if (ret == 0 && !pio_string_write(vcpu)) { - complete_pio(vcpu); - if (vcpu->arch.pio.count == 0) - ret = 1; - } - } - /* no string PIO read support yet */ - + unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX); + int ret = emulator_pio_out_emulated(size, port, &val, 1, vcpu); + /* do not return to emulator after return from userspace */ + vcpu->arch.pio.count = 0; return ret; } -EXPORT_SYMBOL_GPL(kvm_emulate_pio_string); +EXPORT_SYMBOL_GPL(kvm_fast_pio_out); static void bounce_off(void *info) { @@ -3743,6 +3972,51 @@ static void kvm_timer_init(void) } } +static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu); + +static int kvm_is_in_guest(void) +{ + return percpu_read(current_vcpu) != NULL; +} + +static int kvm_is_user_mode(void) +{ + int user_mode = 3; + + if (percpu_read(current_vcpu)) + user_mode = kvm_x86_ops->get_cpl(percpu_read(current_vcpu)); + + return user_mode != 0; +} + +static unsigned long kvm_get_guest_ip(void) +{ + unsigned long ip = 0; + + if (percpu_read(current_vcpu)) + ip = kvm_rip_read(percpu_read(current_vcpu)); + + return ip; +} + +static struct perf_guest_info_callbacks kvm_guest_cbs = { + .is_in_guest = kvm_is_in_guest, + .is_user_mode = kvm_is_user_mode, + .get_guest_ip = kvm_get_guest_ip, +}; + +void kvm_before_handle_nmi(struct kvm_vcpu *vcpu) +{ + percpu_write(current_vcpu, vcpu); +} +EXPORT_SYMBOL_GPL(kvm_before_handle_nmi); + +void kvm_after_handle_nmi(struct kvm_vcpu *vcpu) +{ + percpu_write(current_vcpu, NULL); +} +EXPORT_SYMBOL_GPL(kvm_after_handle_nmi); + int kvm_arch_init(void *opaque) { int r; @@ -3779,6 +4053,8 @@ int kvm_arch_init(void *opaque) kvm_timer_init(); + perf_register_guest_info_callbacks(&kvm_guest_cbs); + return 0; out: @@ -3787,6 +4063,8 @@ out: void kvm_arch_exit(void) { + perf_unregister_guest_info_callbacks(&kvm_guest_cbs); + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); @@ -3942,85 +4220,20 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu) return emulator_write_emulated(rip, instruction, 3, vcpu); } -static u64 mk_cr_64(u64 curr_cr, u32 new_val) -{ - return (curr_cr & ~((1ULL << 32) - 1)) | new_val; -} - void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) { - struct descriptor_table dt = { limit, base }; + struct desc_ptr dt = { limit, base }; kvm_x86_ops->set_gdt(vcpu, &dt); } void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) { - struct descriptor_table dt = { limit, base }; + struct desc_ptr dt = { limit, base }; kvm_x86_ops->set_idt(vcpu, &dt); } -void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, - unsigned long *rflags) -{ - kvm_lmsw(vcpu, msw); - *rflags = kvm_get_rflags(vcpu); -} - -unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) -{ - unsigned long value; - - switch (cr) { - case 0: - value = kvm_read_cr0(vcpu); - break; - case 2: - value = vcpu->arch.cr2; - break; - case 3: - value = vcpu->arch.cr3; - break; - case 4: - value = kvm_read_cr4(vcpu); - break; - case 8: - value = kvm_get_cr8(vcpu); - break; - default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); - return 0; - } - - return value; -} - -void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val, - unsigned long *rflags) -{ - switch (cr) { - case 0: - kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val)); - *rflags = kvm_get_rflags(vcpu); - break; - case 2: - vcpu->arch.cr2 = val; - break; - case 3: - kvm_set_cr3(vcpu, val); - break; - case 4: - kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val)); - break; - case 8: - kvm_set_cr8(vcpu, val & 0xfUL); - break; - default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); - } -} - static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) { struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; @@ -4084,9 +4297,13 @@ int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; + best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0); + if (!best || best->eax < 0x80000008) + goto not_found; best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); if (best) return best->eax & 0xff; +not_found: return 36; } @@ -4200,9 +4417,13 @@ static void inject_pending_event(struct kvm_vcpu *vcpu) { /* try to reinject previous events if any */ if (vcpu->arch.exception.pending) { + trace_kvm_inj_exception(vcpu->arch.exception.nr, + vcpu->arch.exception.has_error_code, + vcpu->arch.exception.error_code); kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr, vcpu->arch.exception.has_error_code, - vcpu->arch.exception.error_code); + vcpu->arch.exception.error_code, + vcpu->arch.exception.reinject); return; } @@ -4460,26 +4681,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (!irqchip_in_kernel(vcpu->kvm)) kvm_set_cr8(vcpu, kvm_run->cr8); - if (vcpu->arch.pio.cur_count) { - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = complete_pio(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - if (r) - goto out; - } - if (vcpu->mmio_needed) { - memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); - vcpu->mmio_read_completed = 1; - vcpu->mmio_needed = 0; - + if (vcpu->arch.pio.count || vcpu->mmio_needed || + vcpu->arch.emulate_ctxt.restart) { + if (vcpu->mmio_needed) { + memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); + vcpu->mmio_read_completed = 1; + vcpu->mmio_needed = 0; + } vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = emulate_instruction(vcpu, vcpu->arch.mmio_fault_cr2, 0, - EMULTYPE_NO_DECODE); + r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (r == EMULATE_DO_MMIO) { - /* - * Read-modify-write. Back to userspace. - */ r = 0; goto out; } @@ -4562,12 +4774,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) return 0; } -void kvm_get_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - kvm_x86_ops->get_segment(vcpu, var, seg); -} - void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) { struct kvm_segment cs; @@ -4581,7 +4787,7 @@ EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits); int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - struct descriptor_table dt; + struct desc_ptr dt; vcpu_load(vcpu); @@ -4596,11 +4802,11 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); kvm_x86_ops->get_idt(vcpu, &dt); - sregs->idt.limit = dt.limit; - sregs->idt.base = dt.base; + sregs->idt.limit = dt.size; + sregs->idt.base = dt.address; kvm_x86_ops->get_gdt(vcpu, &dt); - sregs->gdt.limit = dt.limit; - sregs->gdt.base = dt.base; + sregs->gdt.limit = dt.size; + sregs->gdt.base = dt.address; sregs->cr0 = kvm_read_cr0(vcpu); sregs->cr2 = vcpu->arch.cr2; @@ -4639,563 +4845,33 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, return 0; } -static void kvm_set_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - kvm_x86_ops->set_segment(vcpu, var, seg); -} - -static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector, - struct kvm_segment *kvm_desct) -{ - kvm_desct->base = get_desc_base(seg_desc); - kvm_desct->limit = get_desc_limit(seg_desc); - if (seg_desc->g) { - kvm_desct->limit <<= 12; - kvm_desct->limit |= 0xfff; - } - kvm_desct->selector = selector; - kvm_desct->type = seg_desc->type; - kvm_desct->present = seg_desc->p; - kvm_desct->dpl = seg_desc->dpl; - kvm_desct->db = seg_desc->d; - kvm_desct->s = seg_desc->s; - kvm_desct->l = seg_desc->l; - kvm_desct->g = seg_desc->g; - kvm_desct->avl = seg_desc->avl; - if (!selector) - kvm_desct->unusable = 1; - else - kvm_desct->unusable = 0; - kvm_desct->padding = 0; -} - -static void get_segment_descriptor_dtable(struct kvm_vcpu *vcpu, - u16 selector, - struct descriptor_table *dtable) -{ - if (selector & 1 << 2) { - struct kvm_segment kvm_seg; - - kvm_get_segment(vcpu, &kvm_seg, VCPU_SREG_LDTR); - - if (kvm_seg.unusable) - dtable->limit = 0; - else - dtable->limit = kvm_seg.limit; - dtable->base = kvm_seg.base; - } - else - kvm_x86_ops->get_gdt(vcpu, dtable); -} - -/* allowed just for 8 bytes segments */ -static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, - struct desc_struct *seg_desc) -{ - struct descriptor_table dtable; - u16 index = selector >> 3; - int ret; - u32 err; - gva_t addr; - - get_segment_descriptor_dtable(vcpu, selector, &dtable); - - if (dtable.limit < index * 8 + 7) { - kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc); - return X86EMUL_PROPAGATE_FAULT; - } - addr = dtable.base + index * 8; - ret = kvm_read_guest_virt_system(addr, seg_desc, sizeof(*seg_desc), - vcpu, &err); - if (ret == X86EMUL_PROPAGATE_FAULT) - kvm_inject_page_fault(vcpu, addr, err); - - return ret; -} - -/* allowed just for 8 bytes segments */ -static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, - struct desc_struct *seg_desc) -{ - struct descriptor_table dtable; - u16 index = selector >> 3; - - get_segment_descriptor_dtable(vcpu, selector, &dtable); - - if (dtable.limit < index * 8 + 7) - return 1; - return kvm_write_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu, NULL); -} - -static gpa_t get_tss_base_addr_write(struct kvm_vcpu *vcpu, - struct desc_struct *seg_desc) -{ - u32 base_addr = get_desc_base(seg_desc); - - return kvm_mmu_gva_to_gpa_write(vcpu, base_addr, NULL); -} - -static gpa_t get_tss_base_addr_read(struct kvm_vcpu *vcpu, - struct desc_struct *seg_desc) -{ - u32 base_addr = get_desc_base(seg_desc); - - return kvm_mmu_gva_to_gpa_read(vcpu, base_addr, NULL); -} - -static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg) -{ - struct kvm_segment kvm_seg; - - kvm_get_segment(vcpu, &kvm_seg, seg); - return kvm_seg.selector; -} - -static int kvm_load_realmode_segment(struct kvm_vcpu *vcpu, u16 selector, int seg) -{ - struct kvm_segment segvar = { - .base = selector << 4, - .limit = 0xffff, - .selector = selector, - .type = 3, - .present = 1, - .dpl = 3, - .db = 0, - .s = 1, - .l = 0, - .g = 0, - .avl = 0, - .unusable = 0, - }; - kvm_x86_ops->set_segment(vcpu, &segvar, seg); - return X86EMUL_CONTINUE; -} - -static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg) -{ - return (seg != VCPU_SREG_LDTR) && - (seg != VCPU_SREG_TR) && - (kvm_get_rflags(vcpu) & X86_EFLAGS_VM); -} - -int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg) +int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, + bool has_error_code, u32 error_code) { - struct kvm_segment kvm_seg; - struct desc_struct seg_desc; - u8 dpl, rpl, cpl; - unsigned err_vec = GP_VECTOR; - u32 err_code = 0; - bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */ - int ret; + int cs_db, cs_l, ret; + cache_all_regs(vcpu); - if (is_vm86_segment(vcpu, seg) || !is_protmode(vcpu)) - return kvm_load_realmode_segment(vcpu, selector, seg); + kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); - /* NULL selector is not valid for TR, CS and SS */ - if ((seg == VCPU_SREG_CS || seg == VCPU_SREG_SS || seg == VCPU_SREG_TR) - && null_selector) - goto exception; + vcpu->arch.emulate_ctxt.vcpu = vcpu; + vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu); + vcpu->arch.emulate_ctxt.eip = kvm_rip_read(vcpu); + vcpu->arch.emulate_ctxt.mode = + (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : + (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM) + ? X86EMUL_MODE_VM86 : cs_l + ? X86EMUL_MODE_PROT64 : cs_db + ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - /* TR should be in GDT only */ - if (seg == VCPU_SREG_TR && (selector & (1 << 2))) - goto exception; + ret = emulator_task_switch(&vcpu->arch.emulate_ctxt, &emulate_ops, + tss_selector, reason, has_error_code, + error_code); - ret = load_guest_segment_descriptor(vcpu, selector, &seg_desc); if (ret) - return ret; - - seg_desct_to_kvm_desct(&seg_desc, selector, &kvm_seg); - - if (null_selector) { /* for NULL selector skip all following checks */ - kvm_seg.unusable = 1; - goto load; - } - - err_code = selector & 0xfffc; - err_vec = GP_VECTOR; - - /* can't load system descriptor into segment selecor */ - if (seg <= VCPU_SREG_GS && !kvm_seg.s) - goto exception; - - if (!kvm_seg.present) { - err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR; - goto exception; - } - - rpl = selector & 3; - dpl = kvm_seg.dpl; - cpl = kvm_x86_ops->get_cpl(vcpu); - - switch (seg) { - case VCPU_SREG_SS: - /* - * segment is not a writable data segment or segment - * selector's RPL != CPL or segment selector's RPL != CPL - */ - if (rpl != cpl || (kvm_seg.type & 0xa) != 0x2 || dpl != cpl) - goto exception; - break; - case VCPU_SREG_CS: - if (!(kvm_seg.type & 8)) - goto exception; - - if (kvm_seg.type & 4) { - /* conforming */ - if (dpl > cpl) - goto exception; - } else { - /* nonconforming */ - if (rpl > cpl || dpl != cpl) - goto exception; - } - /* CS(RPL) <- CPL */ - selector = (selector & 0xfffc) | cpl; - break; - case VCPU_SREG_TR: - if (kvm_seg.s || (kvm_seg.type != 1 && kvm_seg.type != 9)) - goto exception; - break; - case VCPU_SREG_LDTR: - if (kvm_seg.s || kvm_seg.type != 2) - goto exception; - break; - default: /* DS, ES, FS, or GS */ - /* - * segment is not a data or readable code segment or - * ((segment is a data or nonconforming code segment) - * and (both RPL and CPL > DPL)) - */ - if ((kvm_seg.type & 0xa) == 0x8 || - (((kvm_seg.type & 0xc) != 0xc) && (rpl > dpl && cpl > dpl))) - goto exception; - break; - } - - if (!kvm_seg.unusable && kvm_seg.s) { - /* mark segment as accessed */ - kvm_seg.type |= 1; - seg_desc.type |= 1; - save_guest_segment_descriptor(vcpu, selector, &seg_desc); - } -load: - kvm_set_segment(vcpu, &kvm_seg, seg); - return X86EMUL_CONTINUE; -exception: - kvm_queue_exception_e(vcpu, err_vec, err_code); - return X86EMUL_PROPAGATE_FAULT; -} - -static void save_state_to_tss32(struct kvm_vcpu *vcpu, - struct tss_segment_32 *tss) -{ - tss->cr3 = vcpu->arch.cr3; - tss->eip = kvm_rip_read(vcpu); - tss->eflags = kvm_get_rflags(vcpu); - tss->eax = kvm_register_read(vcpu, VCPU_REGS_RAX); - tss->ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); - tss->edx = kvm_register_read(vcpu, VCPU_REGS_RDX); - tss->ebx = kvm_register_read(vcpu, VCPU_REGS_RBX); - tss->esp = kvm_register_read(vcpu, VCPU_REGS_RSP); - tss->ebp = kvm_register_read(vcpu, VCPU_REGS_RBP); - tss->esi = kvm_register_read(vcpu, VCPU_REGS_RSI); - tss->edi = kvm_register_read(vcpu, VCPU_REGS_RDI); - tss->es = get_segment_selector(vcpu, VCPU_SREG_ES); - tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS); - tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS); - tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS); - tss->fs = get_segment_selector(vcpu, VCPU_SREG_FS); - tss->gs = get_segment_selector(vcpu, VCPU_SREG_GS); - tss->ldt_selector = get_segment_selector(vcpu, VCPU_SREG_LDTR); -} - -static void kvm_load_segment_selector(struct kvm_vcpu *vcpu, u16 sel, int seg) -{ - struct kvm_segment kvm_seg; - kvm_get_segment(vcpu, &kvm_seg, seg); - kvm_seg.selector = sel; - kvm_set_segment(vcpu, &kvm_seg, seg); -} - -static int load_state_from_tss32(struct kvm_vcpu *vcpu, - struct tss_segment_32 *tss) -{ - kvm_set_cr3(vcpu, tss->cr3); - - kvm_rip_write(vcpu, tss->eip); - kvm_set_rflags(vcpu, tss->eflags | 2); - - kvm_register_write(vcpu, VCPU_REGS_RAX, tss->eax); - kvm_register_write(vcpu, VCPU_REGS_RCX, tss->ecx); - kvm_register_write(vcpu, VCPU_REGS_RDX, tss->edx); - kvm_register_write(vcpu, VCPU_REGS_RBX, tss->ebx); - kvm_register_write(vcpu, VCPU_REGS_RSP, tss->esp); - kvm_register_write(vcpu, VCPU_REGS_RBP, tss->ebp); - kvm_register_write(vcpu, VCPU_REGS_RSI, tss->esi); - kvm_register_write(vcpu, VCPU_REGS_RDI, tss->edi); - - /* - * SDM says that segment selectors are loaded before segment - * descriptors - */ - kvm_load_segment_selector(vcpu, tss->ldt_selector, VCPU_SREG_LDTR); - kvm_load_segment_selector(vcpu, tss->es, VCPU_SREG_ES); - kvm_load_segment_selector(vcpu, tss->cs, VCPU_SREG_CS); - kvm_load_segment_selector(vcpu, tss->ss, VCPU_SREG_SS); - kvm_load_segment_selector(vcpu, tss->ds, VCPU_SREG_DS); - kvm_load_segment_selector(vcpu, tss->fs, VCPU_SREG_FS); - kvm_load_segment_selector(vcpu, tss->gs, VCPU_SREG_GS); - - /* - * Now load segment descriptors. If fault happenes at this stage - * it is handled in a context of new task - */ - if (kvm_load_segment_descriptor(vcpu, tss->ldt_selector, VCPU_SREG_LDTR)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->es, VCPU_SREG_ES)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->cs, VCPU_SREG_CS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->ss, VCPU_SREG_SS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->ds, VCPU_SREG_DS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->fs, VCPU_SREG_FS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->gs, VCPU_SREG_GS)) - return 1; - return 0; -} - -static void save_state_to_tss16(struct kvm_vcpu *vcpu, - struct tss_segment_16 *tss) -{ - tss->ip = kvm_rip_read(vcpu); - tss->flag = kvm_get_rflags(vcpu); - tss->ax = kvm_register_read(vcpu, VCPU_REGS_RAX); - tss->cx = kvm_register_read(vcpu, VCPU_REGS_RCX); - tss->dx = kvm_register_read(vcpu, VCPU_REGS_RDX); - tss->bx = kvm_register_read(vcpu, VCPU_REGS_RBX); - tss->sp = kvm_register_read(vcpu, VCPU_REGS_RSP); - tss->bp = kvm_register_read(vcpu, VCPU_REGS_RBP); - tss->si = kvm_register_read(vcpu, VCPU_REGS_RSI); - tss->di = kvm_register_read(vcpu, VCPU_REGS_RDI); - - tss->es = get_segment_selector(vcpu, VCPU_SREG_ES); - tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS); - tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS); - tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS); - tss->ldt = get_segment_selector(vcpu, VCPU_SREG_LDTR); -} - -static int load_state_from_tss16(struct kvm_vcpu *vcpu, - struct tss_segment_16 *tss) -{ - kvm_rip_write(vcpu, tss->ip); - kvm_set_rflags(vcpu, tss->flag | 2); - kvm_register_write(vcpu, VCPU_REGS_RAX, tss->ax); - kvm_register_write(vcpu, VCPU_REGS_RCX, tss->cx); - kvm_register_write(vcpu, VCPU_REGS_RDX, tss->dx); - kvm_register_write(vcpu, VCPU_REGS_RBX, tss->bx); - kvm_register_write(vcpu, VCPU_REGS_RSP, tss->sp); - kvm_register_write(vcpu, VCPU_REGS_RBP, tss->bp); - kvm_register_write(vcpu, VCPU_REGS_RSI, tss->si); - kvm_register_write(vcpu, VCPU_REGS_RDI, tss->di); - - /* - * SDM says that segment selectors are loaded before segment - * descriptors - */ - kvm_load_segment_selector(vcpu, tss->ldt, VCPU_SREG_LDTR); - kvm_load_segment_selector(vcpu, tss->es, VCPU_SREG_ES); - kvm_load_segment_selector(vcpu, tss->cs, VCPU_SREG_CS); - kvm_load_segment_selector(vcpu, tss->ss, VCPU_SREG_SS); - kvm_load_segment_selector(vcpu, tss->ds, VCPU_SREG_DS); - - /* - * Now load segment descriptors. If fault happenes at this stage - * it is handled in a context of new task - */ - if (kvm_load_segment_descriptor(vcpu, tss->ldt, VCPU_SREG_LDTR)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->es, VCPU_SREG_ES)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->cs, VCPU_SREG_CS)) - return 1; + return EMULATE_FAIL; - if (kvm_load_segment_descriptor(vcpu, tss->ss, VCPU_SREG_SS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->ds, VCPU_SREG_DS)) - return 1; - return 0; -} - -static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector, - u16 old_tss_sel, u32 old_tss_base, - struct desc_struct *nseg_desc) -{ - struct tss_segment_16 tss_segment_16; - int ret = 0; - - if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_16, - sizeof tss_segment_16)) - goto out; - - save_state_to_tss16(vcpu, &tss_segment_16); - - if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_16, - sizeof tss_segment_16)) - goto out; - - if (kvm_read_guest(vcpu->kvm, get_tss_base_addr_read(vcpu, nseg_desc), - &tss_segment_16, sizeof tss_segment_16)) - goto out; - - if (old_tss_sel != 0xffff) { - tss_segment_16.prev_task_link = old_tss_sel; - - if (kvm_write_guest(vcpu->kvm, - get_tss_base_addr_write(vcpu, nseg_desc), - &tss_segment_16.prev_task_link, - sizeof tss_segment_16.prev_task_link)) - goto out; - } - - if (load_state_from_tss16(vcpu, &tss_segment_16)) - goto out; - - ret = 1; -out: - return ret; -} - -static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector, - u16 old_tss_sel, u32 old_tss_base, - struct desc_struct *nseg_desc) -{ - struct tss_segment_32 tss_segment_32; - int ret = 0; - - if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_32, - sizeof tss_segment_32)) - goto out; - - save_state_to_tss32(vcpu, &tss_segment_32); - - if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_32, - sizeof tss_segment_32)) - goto out; - - if (kvm_read_guest(vcpu->kvm, get_tss_base_addr_read(vcpu, nseg_desc), - &tss_segment_32, sizeof tss_segment_32)) - goto out; - - if (old_tss_sel != 0xffff) { - tss_segment_32.prev_task_link = old_tss_sel; - - if (kvm_write_guest(vcpu->kvm, - get_tss_base_addr_write(vcpu, nseg_desc), - &tss_segment_32.prev_task_link, - sizeof tss_segment_32.prev_task_link)) - goto out; - } - - if (load_state_from_tss32(vcpu, &tss_segment_32)) - goto out; - - ret = 1; -out: - return ret; -} - -int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) -{ - struct kvm_segment tr_seg; - struct desc_struct cseg_desc; - struct desc_struct nseg_desc; - int ret = 0; - u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR); - u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR); - u32 desc_limit; - - old_tss_base = kvm_mmu_gva_to_gpa_write(vcpu, old_tss_base, NULL); - - /* FIXME: Handle errors. Failure to read either TSS or their - * descriptors should generate a pagefault. - */ - if (load_guest_segment_descriptor(vcpu, tss_selector, &nseg_desc)) - goto out; - - if (load_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc)) - goto out; - - if (reason != TASK_SWITCH_IRET) { - int cpl; - - cpl = kvm_x86_ops->get_cpl(vcpu); - if ((tss_selector & 3) > nseg_desc.dpl || cpl > nseg_desc.dpl) { - kvm_queue_exception_e(vcpu, GP_VECTOR, 0); - return 1; - } - } - - desc_limit = get_desc_limit(&nseg_desc); - if (!nseg_desc.p || - ((desc_limit < 0x67 && (nseg_desc.type & 8)) || - desc_limit < 0x2b)) { - kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc); - return 1; - } - - if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) { - cseg_desc.type &= ~(1 << 1); //clear the B flag - save_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc); - } - - if (reason == TASK_SWITCH_IRET) { - u32 eflags = kvm_get_rflags(vcpu); - kvm_set_rflags(vcpu, eflags & ~X86_EFLAGS_NT); - } - - /* set back link to prev task only if NT bit is set in eflags - note that old_tss_sel is not used afetr this point */ - if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE) - old_tss_sel = 0xffff; - - if (nseg_desc.type & 8) - ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_sel, - old_tss_base, &nseg_desc); - else - ret = kvm_task_switch_16(vcpu, tss_selector, old_tss_sel, - old_tss_base, &nseg_desc); - - if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) { - u32 eflags = kvm_get_rflags(vcpu); - kvm_set_rflags(vcpu, eflags | X86_EFLAGS_NT); - } - - if (reason != TASK_SWITCH_IRET) { - nseg_desc.type |= (1 << 1); - save_guest_segment_descriptor(vcpu, tss_selector, - &nseg_desc); - } - - kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0(vcpu) | X86_CR0_TS); - seg_desct_to_kvm_desct(&nseg_desc, tss_selector, &tr_seg); - tr_seg.type = 11; - kvm_set_segment(vcpu, &tr_seg, VCPU_SREG_TR); -out: - return ret; + kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + return EMULATE_DONE; } EXPORT_SYMBOL_GPL(kvm_task_switch); @@ -5204,15 +4880,15 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, { int mmu_reset_needed = 0; int pending_vec, max_bits; - struct descriptor_table dt; + struct desc_ptr dt; vcpu_load(vcpu); - dt.limit = sregs->idt.limit; - dt.base = sregs->idt.base; + dt.size = sregs->idt.limit; + dt.address = sregs->idt.base; kvm_x86_ops->set_idt(vcpu, &dt); - dt.limit = sregs->gdt.limit; - dt.base = sregs->gdt.base; + dt.size = sregs->gdt.limit; + dt.address = sregs->gdt.base; kvm_x86_ops->set_gdt(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; @@ -5311,11 +4987,9 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK); } - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { - vcpu->arch.singlestep_cs = - get_segment_selector(vcpu, VCPU_SREG_CS); - vcpu->arch.singlestep_rip = kvm_rip_read(vcpu); - } + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) + + get_segment_base(vcpu, VCPU_SREG_CS); /* * Trigger an rflags update that will inject or remove the trace @@ -5806,13 +5480,22 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) return kvm_x86_ops->interrupt_allowed(vcpu); } +bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip) +{ + unsigned long current_rip = kvm_rip_read(vcpu) + + get_segment_base(vcpu, VCPU_SREG_CS); + + return current_rip == linear_rip; +} +EXPORT_SYMBOL_GPL(kvm_is_linear_rip); + unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) { unsigned long rflags; rflags = kvm_x86_ops->get_rflags(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - rflags &= ~(unsigned long)(X86_EFLAGS_TF | X86_EFLAGS_RF); + rflags &= ~X86_EFLAGS_TF; return rflags; } EXPORT_SYMBOL_GPL(kvm_get_rflags); @@ -5820,10 +5503,8 @@ EXPORT_SYMBOL_GPL(kvm_get_rflags); void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && - vcpu->arch.singlestep_cs == - get_segment_selector(vcpu, VCPU_SREG_CS) && - vcpu->arch.singlestep_rip == kvm_rip_read(vcpu)) - rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; + kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip)) + rflags |= X86_EFLAGS_TF; kvm_x86_ops->set_rflags(vcpu, rflags); } EXPORT_SYMBOL_GPL(kvm_set_rflags); @@ -5839,3 +5520,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 2d101639bd8d..f4b54458285b 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -65,4 +65,14 @@ static inline int is_paging(struct kvm_vcpu *vcpu) return kvm_read_cr0_bits(vcpu, X86_CR0_PG); } +static inline struct kvm_mem_aliases *kvm_aliases(struct kvm *kvm) +{ + return rcu_dereference_check(kvm->arch.aliases, + srcu_read_lock_held(&kvm->srcu) + || lockdep_is_held(&kvm->slots_lock)); +} + +void kvm_before_handle_nmi(struct kvm_vcpu *vcpu); +void kvm_after_handle_nmi(struct kvm_vcpu *vcpu); + #endif diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 419386c24b82..cbaf8f2b83df 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -20,7 +20,7 @@ lib-y := delay.o lib-y += thunk_$(BITS).o lib-y += usercopy_$(BITS).o getuser.o putuser.o lib-y += memcpy_$(BITS).o -lib-$(CONFIG_KPROBES) += insn.o inat.o +lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o obj-y += msr.o msr-reg.o msr-reg-export.o diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index 2bf90fafa7b5..c8abc4d1bf35 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -239,11 +239,11 @@ static void arch_perfmon_setup_counters(void) if (eax.split.version_id == 0 && current_cpu_data.x86 == 6 && current_cpu_data.x86_model == 15) { eax.split.version_id = 2; - eax.split.num_events = 2; + eax.split.num_counters = 2; eax.split.bit_width = 40; } - num_counters = eax.split.num_events; + num_counters = eax.split.num_counters; op_arch_perfmon_spec.num_counters = num_counters; op_arch_perfmon_spec.num_controls = num_counters; diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 01e6adea07ec..cc12b3c556b3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -504,18 +504,6 @@ extern int ftrace_dump_on_oops; #define INIT_TRACE_RECURSION #endif -#ifdef CONFIG_HW_BRANCH_TRACER - -void trace_hw_branch(u64 from, u64 to); -void trace_hw_branch_oops(void); - -#else /* CONFIG_HW_BRANCH_TRACER */ - -static inline void trace_hw_branch(u64 from, u64 to) {} -static inline void trace_hw_branch_oops(void) {} - -#endif /* CONFIG_HW_BRANCH_TRACER */ - #ifdef CONFIG_FTRACE_SYSCALLS unsigned long arch_syscall_addr(int nr); diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 60df9c84ecae..23ea02253900 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -160,6 +160,7 @@ struct kvm_pit_config { #define KVM_EXIT_DCR 15 #define KVM_EXIT_NMI 16 #define KVM_EXIT_INTERNAL_ERROR 17 +#define KVM_EXIT_OSI 18 /* For KVM_EXIT_INTERNAL_ERROR */ #define KVM_INTERNAL_ERROR_EMULATION 1 @@ -259,6 +260,10 @@ struct kvm_run { __u32 ndata; __u64 data[16]; } internal; + /* KVM_EXIT_OSI */ + struct { + __u64 gprs[32]; + } osi; /* Fix the size of the union. */ char padding[256]; }; @@ -400,6 +405,15 @@ struct kvm_ioeventfd { __u8 pad[36]; }; +/* for KVM_ENABLE_CAP */ +struct kvm_enable_cap { + /* in */ + __u32 cap; + __u32 flags; + __u64 args[4]; + __u8 pad[64]; +}; + #define KVMIO 0xAE /* @@ -501,7 +515,15 @@ struct kvm_ioeventfd { #define KVM_CAP_HYPERV_VAPIC 45 #define KVM_CAP_HYPERV_SPIN 46 #define KVM_CAP_PCI_SEGMENT 47 +#define KVM_CAP_PPC_PAIRED_SINGLES 48 +#define KVM_CAP_INTR_SHADOW 49 +#ifdef __KVM_HAVE_DEBUGREGS +#define KVM_CAP_DEBUGREGS 50 +#endif #define KVM_CAP_X86_ROBUST_SINGLESTEP 51 +#define KVM_CAP_PPC_OSI 52 +#define KVM_CAP_PPC_UNSET_IRQ 53 +#define KVM_CAP_ENABLE_CAP 54 #ifdef KVM_CAP_IRQ_ROUTING @@ -688,6 +710,10 @@ struct kvm_clock_data { /* Available with KVM_CAP_VCPU_EVENTS */ #define KVM_GET_VCPU_EVENTS _IOR(KVMIO, 0x9f, struct kvm_vcpu_events) #define KVM_SET_VCPU_EVENTS _IOW(KVMIO, 0xa0, struct kvm_vcpu_events) +/* Available with KVM_CAP_DEBUGREGS */ +#define KVM_GET_DEBUGREGS _IOR(KVMIO, 0xa1, struct kvm_debugregs) +#define KVM_SET_DEBUGREGS _IOW(KVMIO, 0xa2, struct kvm_debugregs) +#define KVM_ENABLE_CAP _IOW(KVMIO, 0xa3, struct kvm_enable_cap) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 169d07758ee5..ce027d518096 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -105,6 +105,12 @@ struct kvm_vcpu { struct kvm_vcpu_arch arch; }; +/* + * Some of the bitops functions do not support too long bitmaps. + * This number must be determined not to exceed such limits. + */ +#define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) + struct kvm_memory_slot { gfn_t base_gfn; unsigned long npages; @@ -244,10 +250,16 @@ void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); +static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) +{ + return rcu_dereference_check(kvm->memslots, + srcu_read_lock_held(&kvm->srcu) + || lockdep_is_held(&kvm->slots_lock)); +} + #define HPA_MSB ((sizeof(hpa_t) * 8) - 1) #define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB) static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; } -struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva); extern struct page *bad_page; extern pfn_t bad_pfn; diff --git a/include/linux/mm.h b/include/linux/mm.h index 462acaf36f3a..fb19bb92b809 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -19,7 +19,6 @@ struct anon_vma; struct file_ra_state; struct user_struct; struct writeback_control; -struct rlimit; #ifndef CONFIG_DISCONTIGMEM /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; @@ -1449,9 +1448,6 @@ int vmemmap_populate_basepages(struct page *start_page, int vmemmap_populate(struct page *start_page, unsigned long pages, int node); void vmemmap_populate_print_last(void); -extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim, - size_t size); -extern void refund_locked_memory(struct mm_struct *mm, size_t size); enum mf_flags { MF_COUNT_INCREASED = 1 << 0, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index c8e375440403..ace31fbac513 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -203,8 +203,9 @@ struct perf_event_attr { enable_on_exec : 1, /* next exec enables */ task : 1, /* trace fork/exit */ watermark : 1, /* wakeup_watermark */ + precise : 1, /* OoO invariant counter */ - __reserved_1 : 49; + __reserved_1 : 48; union { __u32 wakeup_events; /* wakeup every n events */ @@ -287,11 +288,19 @@ struct perf_event_mmap_page { __u64 data_tail; /* user-space written tail */ }; -#define PERF_RECORD_MISC_CPUMODE_MASK (3 << 0) +#define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0) #define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0) #define PERF_RECORD_MISC_KERNEL (1 << 0) #define PERF_RECORD_MISC_USER (2 << 0) #define PERF_RECORD_MISC_HYPERVISOR (3 << 0) +#define PERF_RECORD_MISC_GUEST_KERNEL (4 << 0) +#define PERF_RECORD_MISC_GUEST_USER (5 << 0) + +#define PERF_RECORD_MISC_EXACT (1 << 14) +/* + * Reserve the last bit to indicate some extended misc field + */ +#define PERF_RECORD_MISC_EXT_RESERVED (1 << 15) struct perf_event_header { __u32 type; @@ -439,6 +448,12 @@ enum perf_callchain_context { # include <asm/perf_event.h> #endif +struct perf_guest_info_callbacks { + int (*is_in_guest) (void); + int (*is_user_mode) (void); + unsigned long (*get_guest_ip) (void); +}; + #ifdef CONFIG_HAVE_HW_BREAKPOINT #include <asm/hw_breakpoint.h> #endif @@ -468,6 +483,17 @@ struct perf_raw_record { void *data; }; +struct perf_branch_entry { + __u64 from; + __u64 to; + __u64 flags; +}; + +struct perf_branch_stack { + __u64 nr; + struct perf_branch_entry entries[0]; +}; + struct task_struct; /** @@ -571,6 +597,14 @@ enum perf_group_flag { PERF_GROUP_SOFTWARE = 0x1, }; +#define SWEVENT_HLIST_BITS 8 +#define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) + +struct swevent_hlist { + struct hlist_head heads[SWEVENT_HLIST_SIZE]; + struct rcu_head rcu_head; +}; + /** * struct perf_event - performance event kernel representation: */ @@ -579,6 +613,7 @@ struct perf_event { struct list_head group_entry; struct list_head event_entry; struct list_head sibling_list; + struct hlist_node hlist_entry; int nr_siblings; int group_flags; struct perf_event *group_leader; @@ -726,6 +761,9 @@ struct perf_cpu_context { int active_oncpu; int max_pertask; int exclusive; + struct swevent_hlist *swevent_hlist; + struct mutex hlist_mutex; + int hlist_refcount; /* * Recursion avoidance: @@ -902,6 +940,10 @@ static inline void perf_event_mmap(struct vm_area_struct *vma) __perf_event_mmap(vma); } +extern struct perf_guest_info_callbacks *perf_guest_cbs; +extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); +extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); + extern void perf_event_comm(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); @@ -971,6 +1013,11 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, static inline void perf_bp_event(struct perf_event *event, void *data) { } +static inline int perf_register_guest_info_callbacks +(struct perf_guest_info_callbacks *callbacks) { return 0; } +static inline int perf_unregister_guest_info_callbacks +(struct perf_guest_info_callbacks *callbacks) { return 0; } + static inline void perf_event_mmap(struct vm_area_struct *vma) { } static inline void perf_event_comm(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index e1fb60729979..4272521e29e9 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -345,18 +345,6 @@ static inline void user_single_step_siginfo(struct task_struct *tsk, #define arch_ptrace_stop(code, info) do { } while (0) #endif -#ifndef arch_ptrace_untrace -/* - * Do machine-specific work before untracing child. - * - * This is called for a normal detach as well as from ptrace_exit() - * when the tracing task dies. - * - * Called with write_lock(&tasklist_lock) held. - */ -#define arch_ptrace_untrace(task) do { } while (0) -#endif - extern int task_current_syscall(struct task_struct *target, long *callno, unsigned long args[6], unsigned int maxargs, unsigned long *sp, unsigned long *pc); diff --git a/include/linux/sched.h b/include/linux/sched.h index dad7f668ebf7..e0447c64af6a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -99,7 +99,6 @@ struct futex_pi_state; struct robust_list_head; struct bio_list; struct fs_struct; -struct bts_context; struct perf_event_context; /* @@ -1272,12 +1271,6 @@ struct task_struct { struct list_head ptraced; struct list_head ptrace_entry; - /* - * This is the tracer handle for the ptrace BTS extension. - * This field actually belongs to the ptracer task. - */ - struct bts_context *bts; - /* PID/PID hash table linkage. */ struct pid_link pids[PIDTYPE_MAX]; struct list_head thread_group; @@ -2123,10 +2116,8 @@ extern void set_task_comm(struct task_struct *tsk, char *from); extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP -extern void wait_task_context_switch(struct task_struct *p); extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else -static inline void wait_task_context_switch(struct task_struct *p) {} static inline unsigned long wait_task_inactive(struct task_struct *p, long match_state) { diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index b17d49dfc3ef..6dd3a51ab1cb 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -5,7 +5,6 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm -#define TRACE_INCLUDE_FILE kvm #if defined(__KVM_HAVE_IOAPIC) TRACE_EVENT(kvm_set_irq, diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index ea6f9d4a20e9..882c64832ffe 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -758,13 +758,12 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ static notrace void \ perf_trace_templ_##call(struct ftrace_event_call *event_call, \ - proto) \ + struct pt_regs *__regs, proto) \ { \ struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\ struct ftrace_raw_##call *entry; \ u64 __addr = 0, __count = 1; \ unsigned long irq_flags; \ - struct pt_regs *__regs; \ int __entry_size; \ int __data_size; \ int rctx; \ @@ -785,20 +784,22 @@ perf_trace_templ_##call(struct ftrace_event_call *event_call, \ \ { assign; } \ \ - __regs = &__get_cpu_var(perf_trace_regs); \ - perf_fetch_caller_regs(__regs, 2); \ - \ perf_trace_buf_submit(entry, __entry_size, rctx, __addr, \ __count, irq_flags, __regs); \ } #undef DEFINE_EVENT -#define DEFINE_EVENT(template, call, proto, args) \ -static notrace void perf_trace_##call(proto) \ -{ \ - struct ftrace_event_call *event_call = &event_##call; \ - \ - perf_trace_templ_##template(event_call, args); \ +#define DEFINE_EVENT(template, call, proto, args) \ +static notrace void perf_trace_##call(proto) \ +{ \ + struct ftrace_event_call *event_call = &event_##call; \ + struct pt_regs *__regs = &get_cpu_var(perf_trace_regs); \ + \ + perf_fetch_caller_regs(__regs, 1); \ + \ + perf_trace_templ_##template(event_call, __regs, args); \ + \ + put_cpu_var(perf_trace_regs); \ } #undef DEFINE_EVENT_PRINT diff --git a/kernel/fork.c b/kernel/fork.c index 44b0791b0a2e..5d3592deaf71 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1111,9 +1111,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->memcg_batch.do_batch = 0; p->memcg_batch.memcg = NULL; #endif - - p->bts = NULL; - p->stack_start = stack_start; /* Perform scheduler related setup. Assign this task to a CPU. */ diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 2f3fbf84215a..9dbe8cdaf145 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -16,6 +16,7 @@ #include <linux/file.h> #include <linux/poll.h> #include <linux/slab.h> +#include <linux/hash.h> #include <linux/sysfs.h> #include <linux/dcache.h> #include <linux/percpu.h> @@ -1367,6 +1368,8 @@ void perf_event_task_sched_in(struct task_struct *task) if (cpuctx->task_ctx == ctx) return; + perf_disable(); + /* * We want to keep the following priority order: * cpu pinned (that don't need to move), task pinned, @@ -1379,6 +1382,8 @@ void perf_event_task_sched_in(struct task_struct *task) ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE); cpuctx->task_ctx = ctx; + + perf_enable(); } #define MAX_INTERRUPTS (~0ULL) @@ -2642,6 +2647,7 @@ static int perf_fasync(int fd, struct file *filp, int on) } static const struct file_operations perf_fops = { + .llseek = no_llseek, .release = perf_release, .read = perf_read, .poll = perf_poll, @@ -2792,6 +2798,27 @@ void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int ski /* + * We assume there is only KVM supporting the callbacks. + * Later on, we might change it to a list if there is + * another virtualization implementation supporting the callbacks. + */ +struct perf_guest_info_callbacks *perf_guest_cbs; + +int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) +{ + perf_guest_cbs = cbs; + return 0; +} +EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks); + +int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) +{ + perf_guest_cbs = NULL; + return 0; +} +EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks); + +/* * Output */ static bool perf_output_space(struct perf_mmap_data *data, unsigned long tail, @@ -3743,7 +3770,7 @@ void __perf_event_mmap(struct vm_area_struct *vma) .event_id = { .header = { .type = PERF_RECORD_MMAP, - .misc = 0, + .misc = PERF_RECORD_MISC_USER, /* .size */ }, /* .pid */ @@ -3961,36 +3988,6 @@ static void perf_swevent_add(struct perf_event *event, u64 nr, perf_swevent_overflow(event, 0, nmi, data, regs); } -static int perf_swevent_is_counting(struct perf_event *event) -{ - /* - * The event is active, we're good! - */ - if (event->state == PERF_EVENT_STATE_ACTIVE) - return 1; - - /* - * The event is off/error, not counting. - */ - if (event->state != PERF_EVENT_STATE_INACTIVE) - return 0; - - /* - * The event is inactive, if the context is active - * we're part of a group that didn't make it on the 'pmu', - * not counting. - */ - if (event->ctx->is_active) - return 0; - - /* - * We're inactive and the context is too, this means the - * task is scheduled out, we're counting events that happen - * to us, like migration events. - */ - return 1; -} - static int perf_tp_event_match(struct perf_event *event, struct perf_sample_data *data); @@ -4014,12 +4011,6 @@ static int perf_swevent_match(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { - if (event->cpu != -1 && event->cpu != smp_processor_id()) - return 0; - - if (!perf_swevent_is_counting(event)) - return 0; - if (event->attr.type != type) return 0; @@ -4036,18 +4027,53 @@ static int perf_swevent_match(struct perf_event *event, return 1; } -static void perf_swevent_ctx_event(struct perf_event_context *ctx, - enum perf_type_id type, - u32 event_id, u64 nr, int nmi, - struct perf_sample_data *data, - struct pt_regs *regs) +static inline u64 swevent_hash(u64 type, u32 event_id) +{ + u64 val = event_id | (type << 32); + + return hash_64(val, SWEVENT_HLIST_BITS); +} + +static struct hlist_head * +find_swevent_head(struct perf_cpu_context *ctx, u64 type, u32 event_id) { + u64 hash; + struct swevent_hlist *hlist; + + hash = swevent_hash(type, event_id); + + hlist = rcu_dereference(ctx->swevent_hlist); + if (!hlist) + return NULL; + + return &hlist->heads[hash]; +} + +static void do_perf_sw_event(enum perf_type_id type, u32 event_id, + u64 nr, int nmi, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct perf_cpu_context *cpuctx; struct perf_event *event; + struct hlist_node *node; + struct hlist_head *head; - list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { + cpuctx = &__get_cpu_var(perf_cpu_context); + + rcu_read_lock(); + + head = find_swevent_head(cpuctx, type, event_id); + + if (!head) + goto end; + + hlist_for_each_entry_rcu(event, node, head, hlist_entry) { if (perf_swevent_match(event, type, event_id, data, regs)) perf_swevent_add(event, nr, nmi, data, regs); } +end: + rcu_read_unlock(); } int perf_swevent_get_recursion_context(void) @@ -4085,27 +4111,6 @@ void perf_swevent_put_recursion_context(int rctx) } EXPORT_SYMBOL_GPL(perf_swevent_put_recursion_context); -static void do_perf_sw_event(enum perf_type_id type, u32 event_id, - u64 nr, int nmi, - struct perf_sample_data *data, - struct pt_regs *regs) -{ - struct perf_cpu_context *cpuctx; - struct perf_event_context *ctx; - - cpuctx = &__get_cpu_var(perf_cpu_context); - rcu_read_lock(); - perf_swevent_ctx_event(&cpuctx->ctx, type, event_id, - nr, nmi, data, regs); - /* - * doesn't really matter which of the child contexts the - * events ends up in. - */ - ctx = rcu_dereference(current->perf_event_ctxp); - if (ctx) - perf_swevent_ctx_event(ctx, type, event_id, nr, nmi, data, regs); - rcu_read_unlock(); -} void __perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) @@ -4131,16 +4136,28 @@ static void perf_swevent_read(struct perf_event *event) static int perf_swevent_enable(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; + struct perf_cpu_context *cpuctx; + struct hlist_head *head; + + cpuctx = &__get_cpu_var(perf_cpu_context); if (hwc->sample_period) { hwc->last_period = hwc->sample_period; perf_swevent_set_period(event); } + + head = find_swevent_head(cpuctx, event->attr.type, event->attr.config); + if (WARN_ON_ONCE(!head)) + return -EINVAL; + + hlist_add_head_rcu(&event->hlist_entry, head); + return 0; } static void perf_swevent_disable(struct perf_event *event) { + hlist_del_rcu(&event->hlist_entry); } static const struct pmu perf_ops_generic = { @@ -4168,15 +4185,8 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) perf_sample_data_init(&data, 0); data.period = event->hw.last_period; regs = get_irq_regs(); - /* - * In case we exclude kernel IPs or are somehow not in interrupt - * context, provide the next best thing, the user IP. - */ - if ((event->attr.exclude_kernel || !regs) && - !event->attr.exclude_user) - regs = task_pt_regs(current); - if (regs) { + if (regs && !perf_exclude_event(event, regs)) { if (!(event->attr.exclude_idle && current->pid == 0)) if (perf_event_overflow(event, 0, &data, regs)) ret = HRTIMER_NORESTART; @@ -4324,6 +4334,105 @@ static const struct pmu perf_ops_task_clock = { .read = task_clock_perf_event_read, }; +static void swevent_hlist_release_rcu(struct rcu_head *rcu_head) +{ + struct swevent_hlist *hlist; + + hlist = container_of(rcu_head, struct swevent_hlist, rcu_head); + kfree(hlist); +} + +static void swevent_hlist_release(struct perf_cpu_context *cpuctx) +{ + struct swevent_hlist *hlist; + + if (!cpuctx->swevent_hlist) + return; + + hlist = cpuctx->swevent_hlist; + rcu_assign_pointer(cpuctx->swevent_hlist, NULL); + call_rcu(&hlist->rcu_head, swevent_hlist_release_rcu); +} + +static void swevent_hlist_put_cpu(struct perf_event *event, int cpu) +{ + struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu); + + mutex_lock(&cpuctx->hlist_mutex); + + if (!--cpuctx->hlist_refcount) + swevent_hlist_release(cpuctx); + + mutex_unlock(&cpuctx->hlist_mutex); +} + +static void swevent_hlist_put(struct perf_event *event) +{ + int cpu; + + if (event->cpu != -1) { + swevent_hlist_put_cpu(event, event->cpu); + return; + } + + for_each_possible_cpu(cpu) + swevent_hlist_put_cpu(event, cpu); +} + +static int swevent_hlist_get_cpu(struct perf_event *event, int cpu) +{ + struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu); + int err = 0; + + mutex_lock(&cpuctx->hlist_mutex); + + if (!cpuctx->swevent_hlist && cpu_online(cpu)) { + struct swevent_hlist *hlist; + + hlist = kzalloc(sizeof(*hlist), GFP_KERNEL); + if (!hlist) { + err = -ENOMEM; + goto exit; + } + rcu_assign_pointer(cpuctx->swevent_hlist, hlist); + } + cpuctx->hlist_refcount++; + exit: + mutex_unlock(&cpuctx->hlist_mutex); + + return err; +} + +static int swevent_hlist_get(struct perf_event *event) +{ + int err; + int cpu, failed_cpu; + + if (event->cpu != -1) + return swevent_hlist_get_cpu(event, event->cpu); + + get_online_cpus(); + for_each_possible_cpu(cpu) { + err = swevent_hlist_get_cpu(event, cpu); + if (err) { + failed_cpu = cpu; + goto fail; + } + } + put_online_cpus(); + + return 0; + fail: + for_each_possible_cpu(cpu) { + if (cpu == failed_cpu) + break; + swevent_hlist_put_cpu(event, cpu); + } + + put_online_cpus(); + return err; +} + #ifdef CONFIG_EVENT_TRACING void perf_tp_event(int event_id, u64 addr, u64 count, void *record, @@ -4357,10 +4466,13 @@ static int perf_tp_event_match(struct perf_event *event, static void tp_perf_event_destroy(struct perf_event *event) { perf_trace_disable(event->attr.config); + swevent_hlist_put(event); } static const struct pmu *tp_perf_event_init(struct perf_event *event) { + int err; + /* * Raw tracepoint data is a severe data leak, only allow root to * have these. @@ -4374,6 +4486,11 @@ static const struct pmu *tp_perf_event_init(struct perf_event *event) return NULL; event->destroy = tp_perf_event_destroy; + err = swevent_hlist_get(event); + if (err) { + perf_trace_disable(event->attr.config); + return ERR_PTR(err); + } return &perf_ops_generic; } @@ -4474,6 +4591,7 @@ static void sw_perf_event_destroy(struct perf_event *event) WARN_ON(event->parent); atomic_dec(&perf_swevent_enabled[event_id]); + swevent_hlist_put(event); } static const struct pmu *sw_perf_event_init(struct perf_event *event) @@ -4512,6 +4630,12 @@ static const struct pmu *sw_perf_event_init(struct perf_event *event) case PERF_COUNT_SW_ALIGNMENT_FAULTS: case PERF_COUNT_SW_EMULATION_FAULTS: if (!event->parent) { + int err; + + err = swevent_hlist_get(event); + if (err) + return ERR_PTR(err); + atomic_inc(&perf_swevent_enabled[event_id]); event->destroy = sw_perf_event_destroy; } @@ -5384,6 +5508,7 @@ static void __init perf_event_init_all_cpus(void) for_each_possible_cpu(cpu) { cpuctx = &per_cpu(perf_cpu_context, cpu); + mutex_init(&cpuctx->hlist_mutex); __perf_event_init_context(&cpuctx->ctx, NULL); } } @@ -5397,6 +5522,16 @@ static void __cpuinit perf_event_init_cpu(int cpu) spin_lock(&perf_resource_lock); cpuctx->max_pertask = perf_max_events - perf_reserved_percpu; spin_unlock(&perf_resource_lock); + + mutex_lock(&cpuctx->hlist_mutex); + if (cpuctx->hlist_refcount > 0) { + struct swevent_hlist *hlist; + + hlist = kzalloc(sizeof(*hlist), GFP_KERNEL); + WARN_ON_ONCE(!hlist); + rcu_assign_pointer(cpuctx->swevent_hlist, hlist); + } + mutex_unlock(&cpuctx->hlist_mutex); } #ifdef CONFIG_HOTPLUG_CPU @@ -5416,6 +5551,10 @@ static void perf_event_exit_cpu(int cpu) struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu); struct perf_event_context *ctx = &cpuctx->ctx; + mutex_lock(&cpuctx->hlist_mutex); + swevent_hlist_release(cpuctx); + mutex_unlock(&cpuctx->hlist_mutex); + mutex_lock(&ctx->mutex); smp_call_function_single(cpu, __perf_event_exit_cpu, NULL, 1); mutex_unlock(&ctx->mutex); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 42ad8ae729a0..9fb51237b18c 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -76,7 +76,6 @@ void __ptrace_unlink(struct task_struct *child) child->parent = child->real_parent; list_del_init(&child->ptrace_entry); - arch_ptrace_untrace(child); if (task_is_traced(child)) ptrace_untrace(child); } diff --git a/kernel/sched.c b/kernel/sched.c index 6af210a7de70..b0bbadc24955 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2078,49 +2078,6 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req) } /* - * wait_task_context_switch - wait for a thread to complete at least one - * context switch. - * - * @p must not be current. - */ -void wait_task_context_switch(struct task_struct *p) -{ - unsigned long nvcsw, nivcsw, flags; - int running; - struct rq *rq; - - nvcsw = p->nvcsw; - nivcsw = p->nivcsw; - for (;;) { - /* - * The runqueue is assigned before the actual context - * switch. We need to take the runqueue lock. - * - * We could check initially without the lock but it is - * very likely that we need to take the lock in every - * iteration. - */ - rq = task_rq_lock(p, &flags); - running = task_running(rq, p); - task_rq_unlock(rq, &flags); - - if (likely(!running)) - break; - /* - * The switch count is incremented before the actual - * context switch. We thus wait for two switches to be - * sure at least one completed. - */ - if ((p->nvcsw - nvcsw) > 1) - break; - if ((p->nivcsw - nivcsw) > 1) - break; - - cpu_relax(); - } -} - -/* * wait_task_inactive - wait for a thread to unschedule. * * If @match_state is nonzero, it's the @p->state value just checked and diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 13e13d428cd3..8b1797c4545b 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -44,9 +44,6 @@ config HAVE_FTRACE_MCOUNT_RECORD help See Documentation/trace/ftrace-design.txt -config HAVE_HW_BRANCH_TRACER - bool - config HAVE_SYSCALL_TRACEPOINTS bool help @@ -374,14 +371,6 @@ config STACK_TRACER Say N if unsure. -config HW_BRANCH_TRACER - depends on HAVE_HW_BRANCH_TRACER - bool "Trace hw branches" - select GENERIC_TRACER - help - This tracer records all branches on the system in a circular - buffer, giving access to the last N branches for each cpu. - config KMEMTRACE bool "Trace SLAB allocations" select GENERIC_TRACER diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 78edc6490038..ffb1a5b0550e 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -41,7 +41,6 @@ obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o obj-$(CONFIG_BOOT_TRACER) += trace_boot.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o -obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o obj-$(CONFIG_KMEMTRACE) += kmemtrace.o obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 2825ef2c0b15..3ebdb6bd2362 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -34,7 +34,6 @@ enum trace_type { TRACE_GRAPH_RET, TRACE_GRAPH_ENT, TRACE_USER_STACK, - TRACE_HW_BRANCHES, TRACE_KMEM_ALLOC, TRACE_KMEM_FREE, TRACE_BLK, @@ -103,29 +102,17 @@ struct syscall_trace_exit { long ret; }; -struct kprobe_trace_entry { +struct kprobe_trace_entry_head { struct trace_entry ent; unsigned long ip; - int nargs; - unsigned long args[]; }; -#define SIZEOF_KPROBE_TRACE_ENTRY(n) \ - (offsetof(struct kprobe_trace_entry, args) + \ - (sizeof(unsigned long) * (n))) - -struct kretprobe_trace_entry { +struct kretprobe_trace_entry_head { struct trace_entry ent; unsigned long func; unsigned long ret_ip; - int nargs; - unsigned long args[]; }; -#define SIZEOF_KRETPROBE_TRACE_ENTRY(n) \ - (offsetof(struct kretprobe_trace_entry, args) + \ - (sizeof(unsigned long) * (n))) - /* * trace_flag_type is an enumeration that holds different * states when a trace occurs. These are: @@ -229,7 +216,6 @@ extern void __ftrace_bad_type(void); TRACE_GRAPH_ENT); \ IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry, \ TRACE_GRAPH_RET); \ - IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\ IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry, \ TRACE_KMEM_ALLOC); \ IF_ASSIGN(var, ent, struct kmemtrace_free_entry, \ @@ -467,8 +453,6 @@ extern int trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr); -extern int trace_selftest_startup_hw_branches(struct tracer *trace, - struct trace_array *tr); extern int trace_selftest_startup_ksym(struct tracer *trace, struct trace_array *tr); #endif /* CONFIG_FTRACE_STARTUP_TEST */ diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index c16a08f399df..dc008c1240da 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -318,18 +318,6 @@ FTRACE_ENTRY(branch, trace_branch, __entry->func, __entry->file, __entry->correct) ); -FTRACE_ENTRY(hw_branch, hw_branch_entry, - - TRACE_HW_BRANCHES, - - F_STRUCT( - __field( u64, from ) - __field( u64, to ) - ), - - F_printk("from: %llx to: %llx", __entry->from, __entry->to) -); - FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry, TRACE_KMEM_ALLOC, diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c deleted file mode 100644 index 7b97000745f5..000000000000 --- a/kernel/trace/trace_hw_branches.c +++ /dev/null @@ -1,312 +0,0 @@ -/* - * h/w branch tracer for x86 based on BTS - * - * Copyright (C) 2008-2009 Intel Corporation. - * Markus Metzger <markus.t.metzger@gmail.com>, 2008-2009 - */ -#include <linux/kallsyms.h> -#include <linux/debugfs.h> -#include <linux/ftrace.h> -#include <linux/module.h> -#include <linux/cpu.h> -#include <linux/smp.h> -#include <linux/fs.h> - -#include <asm/ds.h> - -#include "trace_output.h" -#include "trace.h" - - -#define BTS_BUFFER_SIZE (1 << 13) - -static DEFINE_PER_CPU(struct bts_tracer *, hwb_tracer); -static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], hwb_buffer); - -#define this_tracer per_cpu(hwb_tracer, smp_processor_id()) - -static int trace_hw_branches_enabled __read_mostly; -static int trace_hw_branches_suspended __read_mostly; -static struct trace_array *hw_branch_trace __read_mostly; - - -static void bts_trace_init_cpu(int cpu) -{ - per_cpu(hwb_tracer, cpu) = - ds_request_bts_cpu(cpu, per_cpu(hwb_buffer, cpu), - BTS_BUFFER_SIZE, NULL, (size_t)-1, - BTS_KERNEL); - - if (IS_ERR(per_cpu(hwb_tracer, cpu))) - per_cpu(hwb_tracer, cpu) = NULL; -} - -static int bts_trace_init(struct trace_array *tr) -{ - int cpu; - - hw_branch_trace = tr; - trace_hw_branches_enabled = 0; - - get_online_cpus(); - for_each_online_cpu(cpu) { - bts_trace_init_cpu(cpu); - - if (likely(per_cpu(hwb_tracer, cpu))) - trace_hw_branches_enabled = 1; - } - trace_hw_branches_suspended = 0; - put_online_cpus(); - - /* If we could not enable tracing on a single cpu, we fail. */ - return trace_hw_branches_enabled ? 0 : -EOPNOTSUPP; -} - -static void bts_trace_reset(struct trace_array *tr) -{ - int cpu; - - get_online_cpus(); - for_each_online_cpu(cpu) { - if (likely(per_cpu(hwb_tracer, cpu))) { - ds_release_bts(per_cpu(hwb_tracer, cpu)); - per_cpu(hwb_tracer, cpu) = NULL; - } - } - trace_hw_branches_enabled = 0; - trace_hw_branches_suspended = 0; - put_online_cpus(); -} - -static void bts_trace_start(struct trace_array *tr) -{ - int cpu; - - get_online_cpus(); - for_each_online_cpu(cpu) - if (likely(per_cpu(hwb_tracer, cpu))) - ds_resume_bts(per_cpu(hwb_tracer, cpu)); - trace_hw_branches_suspended = 0; - put_online_cpus(); -} - -static void bts_trace_stop(struct trace_array *tr) -{ - int cpu; - - get_online_cpus(); - for_each_online_cpu(cpu) - if (likely(per_cpu(hwb_tracer, cpu))) - ds_suspend_bts(per_cpu(hwb_tracer, cpu)); - trace_hw_branches_suspended = 1; - put_online_cpus(); -} - -static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb, - unsigned long action, void *hcpu) -{ - int cpu = (long)hcpu; - - switch (action) { - case CPU_ONLINE: - case CPU_DOWN_FAILED: - /* The notification is sent with interrupts enabled. */ - if (trace_hw_branches_enabled) { - bts_trace_init_cpu(cpu); - - if (trace_hw_branches_suspended && - likely(per_cpu(hwb_tracer, cpu))) - ds_suspend_bts(per_cpu(hwb_tracer, cpu)); - } - break; - - case CPU_DOWN_PREPARE: - /* The notification is sent with interrupts enabled. */ - if (likely(per_cpu(hwb_tracer, cpu))) { - ds_release_bts(per_cpu(hwb_tracer, cpu)); - per_cpu(hwb_tracer, cpu) = NULL; - } - } - - return NOTIFY_DONE; -} - -static struct notifier_block bts_hotcpu_notifier __cpuinitdata = { - .notifier_call = bts_hotcpu_handler -}; - -static void bts_trace_print_header(struct seq_file *m) -{ - seq_puts(m, "# CPU# TO <- FROM\n"); -} - -static enum print_line_t bts_trace_print_line(struct trace_iterator *iter) -{ - unsigned long symflags = TRACE_ITER_SYM_OFFSET; - struct trace_entry *entry = iter->ent; - struct trace_seq *seq = &iter->seq; - struct hw_branch_entry *it; - - trace_assign_type(it, entry); - - if (entry->type == TRACE_HW_BRANCHES) { - if (trace_seq_printf(seq, "%4d ", iter->cpu) && - seq_print_ip_sym(seq, it->to, symflags) && - trace_seq_printf(seq, "\t <- ") && - seq_print_ip_sym(seq, it->from, symflags) && - trace_seq_printf(seq, "\n")) - return TRACE_TYPE_HANDLED; - return TRACE_TYPE_PARTIAL_LINE; - } - return TRACE_TYPE_UNHANDLED; -} - -void trace_hw_branch(u64 from, u64 to) -{ - struct ftrace_event_call *call = &event_hw_branch; - struct trace_array *tr = hw_branch_trace; - struct ring_buffer_event *event; - struct ring_buffer *buf; - struct hw_branch_entry *entry; - unsigned long irq1; - int cpu; - - if (unlikely(!tr)) - return; - - if (unlikely(!trace_hw_branches_enabled)) - return; - - local_irq_save(irq1); - cpu = raw_smp_processor_id(); - if (atomic_inc_return(&tr->data[cpu]->disabled) != 1) - goto out; - - buf = tr->buffer; - event = trace_buffer_lock_reserve(buf, TRACE_HW_BRANCHES, - sizeof(*entry), 0, 0); - if (!event) - goto out; - entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, 0, from); - entry->ent.type = TRACE_HW_BRANCHES; - entry->from = from; - entry->to = to; - if (!filter_check_discard(call, entry, buf, event)) - trace_buffer_unlock_commit(buf, event, 0, 0); - - out: - atomic_dec(&tr->data[cpu]->disabled); - local_irq_restore(irq1); -} - -static void trace_bts_at(const struct bts_trace *trace, void *at) -{ - struct bts_struct bts; - int err = 0; - - WARN_ON_ONCE(!trace->read); - if (!trace->read) - return; - - err = trace->read(this_tracer, at, &bts); - if (err < 0) - return; - - switch (bts.qualifier) { - case BTS_BRANCH: - trace_hw_branch(bts.variant.lbr.from, bts.variant.lbr.to); - break; - } -} - -/* - * Collect the trace on the current cpu and write it into the ftrace buffer. - * - * pre: tracing must be suspended on the current cpu - */ -static void trace_bts_cpu(void *arg) -{ - struct trace_array *tr = (struct trace_array *)arg; - const struct bts_trace *trace; - unsigned char *at; - - if (unlikely(!tr)) - return; - - if (unlikely(atomic_read(&tr->data[raw_smp_processor_id()]->disabled))) - return; - - if (unlikely(!this_tracer)) - return; - - trace = ds_read_bts(this_tracer); - if (!trace) - return; - - for (at = trace->ds.top; (void *)at < trace->ds.end; - at += trace->ds.size) - trace_bts_at(trace, at); - - for (at = trace->ds.begin; (void *)at < trace->ds.top; - at += trace->ds.size) - trace_bts_at(trace, at); -} - -static void trace_bts_prepare(struct trace_iterator *iter) -{ - int cpu; - - get_online_cpus(); - for_each_online_cpu(cpu) - if (likely(per_cpu(hwb_tracer, cpu))) - ds_suspend_bts(per_cpu(hwb_tracer, cpu)); - /* - * We need to collect the trace on the respective cpu since ftrace - * implicitly adds the record for the current cpu. - * Once that is more flexible, we could collect the data from any cpu. - */ - on_each_cpu(trace_bts_cpu, iter->tr, 1); - - for_each_online_cpu(cpu) - if (likely(per_cpu(hwb_tracer, cpu))) - ds_resume_bts(per_cpu(hwb_tracer, cpu)); - put_online_cpus(); -} - -static void trace_bts_close(struct trace_iterator *iter) -{ - tracing_reset_online_cpus(iter->tr); -} - -void trace_hw_branch_oops(void) -{ - if (this_tracer) { - ds_suspend_bts_noirq(this_tracer); - trace_bts_cpu(hw_branch_trace); - ds_resume_bts_noirq(this_tracer); - } -} - -struct tracer bts_tracer __read_mostly = -{ - .name = "hw-branch-tracer", - .init = bts_trace_init, - .reset = bts_trace_reset, - .print_header = bts_trace_print_header, - .print_line = bts_trace_print_line, - .start = bts_trace_start, - .stop = bts_trace_stop, - .open = trace_bts_prepare, - .close = trace_bts_close, -#ifdef CONFIG_FTRACE_SELFTEST - .selftest = trace_selftest_startup_hw_branches, -#endif /* CONFIG_FTRACE_SELFTEST */ -}; - -__init static int init_bts_trace(void) -{ - register_hotcpu_notifier(&bts_hotcpu_notifier); - return register_tracer(&bts_tracer); -} -device_initcall(init_bts_trace); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 1251e367bae9..a7514326052b 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -29,6 +29,8 @@ #include <linux/ctype.h> #include <linux/ptrace.h> #include <linux/perf_event.h> +#include <linux/stringify.h> +#include <asm/bitsperlong.h> #include "trace.h" #include "trace_output.h" @@ -40,7 +42,6 @@ /* Reserved field names */ #define FIELD_STRING_IP "__probe_ip" -#define FIELD_STRING_NARGS "__probe_nargs" #define FIELD_STRING_RETIP "__probe_ret_ip" #define FIELD_STRING_FUNC "__probe_func" @@ -52,56 +53,102 @@ const char *reserved_field_names[] = { "common_tgid", "common_lock_depth", FIELD_STRING_IP, - FIELD_STRING_NARGS, FIELD_STRING_RETIP, FIELD_STRING_FUNC, }; -struct fetch_func { - unsigned long (*func)(struct pt_regs *, void *); +/* Printing function type */ +typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *); +#define PRINT_TYPE_FUNC_NAME(type) print_type_##type +#define PRINT_TYPE_FMT_NAME(type) print_type_format_##type + +/* Printing in basic type function template */ +#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt, cast) \ +static __kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \ + const char *name, void *data)\ +{ \ + return trace_seq_printf(s, " %s=" fmt, name, (cast)*(type *)data);\ +} \ +static const char PRINT_TYPE_FMT_NAME(type)[] = fmt; + +DEFINE_BASIC_PRINT_TYPE_FUNC(u8, "%x", unsigned int) +DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "%x", unsigned int) +DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "%lx", unsigned long) +DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "%llx", unsigned long long) +DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d", int) +DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d", int) +DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%ld", long) +DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%lld", long long) + +/* Data fetch function type */ +typedef void (*fetch_func_t)(struct pt_regs *, void *, void *); + +struct fetch_param { + fetch_func_t fn; void *data; }; -static __kprobes unsigned long call_fetch(struct fetch_func *f, - struct pt_regs *regs) +static __kprobes void call_fetch(struct fetch_param *fprm, + struct pt_regs *regs, void *dest) { - return f->func(regs, f->data); + return fprm->fn(regs, fprm->data, dest); } -/* fetch handlers */ -static __kprobes unsigned long fetch_register(struct pt_regs *regs, - void *offset) -{ - return regs_get_register(regs, (unsigned int)((unsigned long)offset)); +#define FETCH_FUNC_NAME(kind, type) fetch_##kind##_##type +/* + * Define macro for basic types - we don't need to define s* types, because + * we have to care only about bitwidth at recording time. + */ +#define DEFINE_BASIC_FETCH_FUNCS(kind) \ +DEFINE_FETCH_##kind(u8) \ +DEFINE_FETCH_##kind(u16) \ +DEFINE_FETCH_##kind(u32) \ +DEFINE_FETCH_##kind(u64) + +#define CHECK_BASIC_FETCH_FUNCS(kind, fn) \ + ((FETCH_FUNC_NAME(kind, u8) == fn) || \ + (FETCH_FUNC_NAME(kind, u16) == fn) || \ + (FETCH_FUNC_NAME(kind, u32) == fn) || \ + (FETCH_FUNC_NAME(kind, u64) == fn)) + +/* Data fetch function templates */ +#define DEFINE_FETCH_reg(type) \ +static __kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, \ + void *offset, void *dest) \ +{ \ + *(type *)dest = (type)regs_get_register(regs, \ + (unsigned int)((unsigned long)offset)); \ } - -static __kprobes unsigned long fetch_stack(struct pt_regs *regs, - void *num) -{ - return regs_get_kernel_stack_nth(regs, - (unsigned int)((unsigned long)num)); +DEFINE_BASIC_FETCH_FUNCS(reg) + +#define DEFINE_FETCH_stack(type) \ +static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\ + void *offset, void *dest) \ +{ \ + *(type *)dest = (type)regs_get_kernel_stack_nth(regs, \ + (unsigned int)((unsigned long)offset)); \ } +DEFINE_BASIC_FETCH_FUNCS(stack) -static __kprobes unsigned long fetch_memory(struct pt_regs *regs, void *addr) -{ - unsigned long retval; - - if (probe_kernel_address(addr, retval)) - return 0; - return retval; +#define DEFINE_FETCH_retval(type) \ +static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\ + void *dummy, void *dest) \ +{ \ + *(type *)dest = (type)regs_return_value(regs); \ } - -static __kprobes unsigned long fetch_retvalue(struct pt_regs *regs, - void *dummy) -{ - return regs_return_value(regs); -} - -static __kprobes unsigned long fetch_stack_address(struct pt_regs *regs, - void *dummy) -{ - return kernel_stack_pointer(regs); +DEFINE_BASIC_FETCH_FUNCS(retval) + +#define DEFINE_FETCH_memory(type) \ +static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\ + void *addr, void *dest) \ +{ \ + type retval; \ + if (probe_kernel_address(addr, retval)) \ + *(type *)dest = 0; \ + else \ + *(type *)dest = retval; \ } +DEFINE_BASIC_FETCH_FUNCS(memory) /* Memory fetching by symbol */ struct symbol_cache { @@ -145,51 +192,126 @@ static struct symbol_cache *alloc_symbol_cache(const char *sym, long offset) return sc; } -static __kprobes unsigned long fetch_symbol(struct pt_regs *regs, void *data) -{ - struct symbol_cache *sc = data; - - if (sc->addr) - return fetch_memory(regs, (void *)sc->addr); - else - return 0; +#define DEFINE_FETCH_symbol(type) \ +static __kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,\ + void *data, void *dest) \ +{ \ + struct symbol_cache *sc = data; \ + if (sc->addr) \ + fetch_memory_##type(regs, (void *)sc->addr, dest); \ + else \ + *(type *)dest = 0; \ } +DEFINE_BASIC_FETCH_FUNCS(symbol) -/* Special indirect memory access interface */ -struct indirect_fetch_data { - struct fetch_func orig; +/* Dereference memory access function */ +struct deref_fetch_param { + struct fetch_param orig; long offset; }; -static __kprobes unsigned long fetch_indirect(struct pt_regs *regs, void *data) -{ - struct indirect_fetch_data *ind = data; - unsigned long addr; - - addr = call_fetch(&ind->orig, regs); - if (addr) { - addr += ind->offset; - return fetch_memory(regs, (void *)addr); - } else - return 0; +#define DEFINE_FETCH_deref(type) \ +static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\ + void *data, void *dest) \ +{ \ + struct deref_fetch_param *dprm = data; \ + unsigned long addr; \ + call_fetch(&dprm->orig, regs, &addr); \ + if (addr) { \ + addr += dprm->offset; \ + fetch_memory_##type(regs, (void *)addr, dest); \ + } else \ + *(type *)dest = 0; \ } +DEFINE_BASIC_FETCH_FUNCS(deref) -static __kprobes void free_indirect_fetch_data(struct indirect_fetch_data *data) +static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data) { - if (data->orig.func == fetch_indirect) - free_indirect_fetch_data(data->orig.data); - else if (data->orig.func == fetch_symbol) + if (CHECK_BASIC_FETCH_FUNCS(deref, data->orig.fn)) + free_deref_fetch_param(data->orig.data); + else if (CHECK_BASIC_FETCH_FUNCS(symbol, data->orig.fn)) free_symbol_cache(data->orig.data); kfree(data); } +/* Default (unsigned long) fetch type */ +#define __DEFAULT_FETCH_TYPE(t) u##t +#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t) +#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG) +#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE) + +#define ASSIGN_FETCH_FUNC(kind, type) \ + .kind = FETCH_FUNC_NAME(kind, type) + +#define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \ + {.name = #ptype, \ + .size = sizeof(ftype), \ + .is_signed = sign, \ + .print = PRINT_TYPE_FUNC_NAME(ptype), \ + .fmt = PRINT_TYPE_FMT_NAME(ptype), \ +ASSIGN_FETCH_FUNC(reg, ftype), \ +ASSIGN_FETCH_FUNC(stack, ftype), \ +ASSIGN_FETCH_FUNC(retval, ftype), \ +ASSIGN_FETCH_FUNC(memory, ftype), \ +ASSIGN_FETCH_FUNC(symbol, ftype), \ +ASSIGN_FETCH_FUNC(deref, ftype), \ + } + +/* Fetch type information table */ +static const struct fetch_type { + const char *name; /* Name of type */ + size_t size; /* Byte size of type */ + int is_signed; /* Signed flag */ + print_type_func_t print; /* Print functions */ + const char *fmt; /* Fromat string */ + /* Fetch functions */ + fetch_func_t reg; + fetch_func_t stack; + fetch_func_t retval; + fetch_func_t memory; + fetch_func_t symbol; + fetch_func_t deref; +} fetch_type_table[] = { + ASSIGN_FETCH_TYPE(u8, u8, 0), + ASSIGN_FETCH_TYPE(u16, u16, 0), + ASSIGN_FETCH_TYPE(u32, u32, 0), + ASSIGN_FETCH_TYPE(u64, u64, 0), + ASSIGN_FETCH_TYPE(s8, u8, 1), + ASSIGN_FETCH_TYPE(s16, u16, 1), + ASSIGN_FETCH_TYPE(s32, u32, 1), + ASSIGN_FETCH_TYPE(s64, u64, 1), +}; + +static const struct fetch_type *find_fetch_type(const char *type) +{ + int i; + + if (!type) + type = DEFAULT_FETCH_TYPE_STR; + + for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++) + if (strcmp(type, fetch_type_table[i].name) == 0) + return &fetch_type_table[i]; + return NULL; +} + +/* Special function : only accept unsigned long */ +static __kprobes void fetch_stack_address(struct pt_regs *regs, + void *dummy, void *dest) +{ + *(unsigned long *)dest = kernel_stack_pointer(regs); +} + /** * Kprobe event core functions */ struct probe_arg { - struct fetch_func fetch; - const char *name; + struct fetch_param fetch; + unsigned int offset; /* Offset from argument entry */ + const char *name; /* Name of this argument */ + const char *comm; /* Command of this argument */ + const struct fetch_type *type; /* Type of this argument */ }; /* Flags for trace_probe */ @@ -204,6 +326,7 @@ struct trace_probe { const char *symbol; /* symbol name */ struct ftrace_event_call call; struct trace_event event; + ssize_t size; /* trace entry size */ unsigned int nr_args; struct probe_arg args[]; }; @@ -212,6 +335,7 @@ struct trace_probe { (offsetof(struct trace_probe, args) + \ (sizeof(struct probe_arg) * (n))) + static __kprobes int probe_is_return(struct trace_probe *tp) { return tp->rp.handler != NULL; @@ -222,49 +346,6 @@ static __kprobes const char *probe_symbol(struct trace_probe *tp) return tp->symbol ? tp->symbol : "unknown"; } -static int probe_arg_string(char *buf, size_t n, struct fetch_func *ff) -{ - int ret = -EINVAL; - - if (ff->func == fetch_register) { - const char *name; - name = regs_query_register_name((unsigned int)((long)ff->data)); - ret = snprintf(buf, n, "%%%s", name); - } else if (ff->func == fetch_stack) - ret = snprintf(buf, n, "$stack%lu", (unsigned long)ff->data); - else if (ff->func == fetch_memory) - ret = snprintf(buf, n, "@0x%p", ff->data); - else if (ff->func == fetch_symbol) { - struct symbol_cache *sc = ff->data; - if (sc->offset) - ret = snprintf(buf, n, "@%s%+ld", sc->symbol, - sc->offset); - else - ret = snprintf(buf, n, "@%s", sc->symbol); - } else if (ff->func == fetch_retvalue) - ret = snprintf(buf, n, "$retval"); - else if (ff->func == fetch_stack_address) - ret = snprintf(buf, n, "$stack"); - else if (ff->func == fetch_indirect) { - struct indirect_fetch_data *id = ff->data; - size_t l = 0; - ret = snprintf(buf, n, "%+ld(", id->offset); - if (ret >= n) - goto end; - l += ret; - ret = probe_arg_string(buf + l, n - l, &id->orig); - if (ret < 0) - goto end; - l += ret; - ret = snprintf(buf + l, n - l, ")"); - ret += l; - } -end: - if (ret >= n) - return -ENOSPC; - return ret; -} - static int register_probe_event(struct trace_probe *tp); static void unregister_probe_event(struct trace_probe *tp); @@ -347,11 +428,12 @@ error: static void free_probe_arg(struct probe_arg *arg) { - if (arg->fetch.func == fetch_symbol) + if (CHECK_BASIC_FETCH_FUNCS(deref, arg->fetch.fn)) + free_deref_fetch_param(arg->fetch.data); + else if (CHECK_BASIC_FETCH_FUNCS(symbol, arg->fetch.fn)) free_symbol_cache(arg->fetch.data); - else if (arg->fetch.func == fetch_indirect) - free_indirect_fetch_data(arg->fetch.data); kfree(arg->name); + kfree(arg->comm); } static void free_trace_probe(struct trace_probe *tp) @@ -457,28 +539,30 @@ static int split_symbol_offset(char *symbol, unsigned long *offset) #define PARAM_MAX_ARGS 16 #define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long)) -static int parse_probe_vars(char *arg, struct fetch_func *ff, int is_return) +static int parse_probe_vars(char *arg, const struct fetch_type *t, + struct fetch_param *f, int is_return) { int ret = 0; unsigned long param; if (strcmp(arg, "retval") == 0) { - if (is_return) { - ff->func = fetch_retvalue; - ff->data = NULL; - } else + if (is_return) + f->fn = t->retval; + else ret = -EINVAL; } else if (strncmp(arg, "stack", 5) == 0) { if (arg[5] == '\0') { - ff->func = fetch_stack_address; - ff->data = NULL; + if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR) == 0) + f->fn = fetch_stack_address; + else + ret = -EINVAL; } else if (isdigit(arg[5])) { ret = strict_strtoul(arg + 5, 10, ¶m); if (ret || param > PARAM_MAX_STACK) ret = -EINVAL; else { - ff->func = fetch_stack; - ff->data = (void *)param; + f->fn = t->stack; + f->data = (void *)param; } } else ret = -EINVAL; @@ -488,7 +572,8 @@ static int parse_probe_vars(char *arg, struct fetch_func *ff, int is_return) } /* Recursive argument parser */ -static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return) +static int __parse_probe_arg(char *arg, const struct fetch_type *t, + struct fetch_param *f, int is_return) { int ret = 0; unsigned long param; @@ -497,13 +582,13 @@ static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return) switch (arg[0]) { case '$': - ret = parse_probe_vars(arg + 1, ff, is_return); + ret = parse_probe_vars(arg + 1, t, f, is_return); break; case '%': /* named register */ ret = regs_query_register_offset(arg + 1); if (ret >= 0) { - ff->func = fetch_register; - ff->data = (void *)(unsigned long)ret; + f->fn = t->reg; + f->data = (void *)(unsigned long)ret; ret = 0; } break; @@ -512,26 +597,22 @@ static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return) ret = strict_strtoul(arg + 1, 0, ¶m); if (ret) break; - ff->func = fetch_memory; - ff->data = (void *)param; + f->fn = t->memory; + f->data = (void *)param; } else { ret = split_symbol_offset(arg + 1, &offset); if (ret) break; - ff->data = alloc_symbol_cache(arg + 1, offset); - if (ff->data) - ff->func = fetch_symbol; - else - ret = -EINVAL; + f->data = alloc_symbol_cache(arg + 1, offset); + if (f->data) + f->fn = t->symbol; } break; - case '+': /* indirect memory */ + case '+': /* deref memory */ case '-': tmp = strchr(arg, '('); - if (!tmp) { - ret = -EINVAL; + if (!tmp) break; - } *tmp = '\0'; ret = strict_strtol(arg + 1, 0, &offset); if (ret) @@ -541,38 +622,58 @@ static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return) arg = tmp + 1; tmp = strrchr(arg, ')'); if (tmp) { - struct indirect_fetch_data *id; + struct deref_fetch_param *dprm; + const struct fetch_type *t2 = find_fetch_type(NULL); *tmp = '\0'; - id = kzalloc(sizeof(struct indirect_fetch_data), - GFP_KERNEL); - if (!id) + dprm = kzalloc(sizeof(struct deref_fetch_param), + GFP_KERNEL); + if (!dprm) return -ENOMEM; - id->offset = offset; - ret = __parse_probe_arg(arg, &id->orig, is_return); + dprm->offset = offset; + ret = __parse_probe_arg(arg, t2, &dprm->orig, + is_return); if (ret) - kfree(id); + kfree(dprm); else { - ff->func = fetch_indirect; - ff->data = (void *)id; + f->fn = t->deref; + f->data = (void *)dprm; } - } else - ret = -EINVAL; + } break; - default: - /* TODO: support custom handler */ - ret = -EINVAL; } + if (!ret && !f->fn) + ret = -EINVAL; return ret; } /* String length checking wrapper */ -static int parse_probe_arg(char *arg, struct fetch_func *ff, int is_return) +static int parse_probe_arg(char *arg, struct trace_probe *tp, + struct probe_arg *parg, int is_return) { + const char *t; + if (strlen(arg) > MAX_ARGSTR_LEN) { pr_info("Argument is too long.: %s\n", arg); return -ENOSPC; } - return __parse_probe_arg(arg, ff, is_return); + parg->comm = kstrdup(arg, GFP_KERNEL); + if (!parg->comm) { + pr_info("Failed to allocate memory for command '%s'.\n", arg); + return -ENOMEM; + } + t = strchr(parg->comm, ':'); + if (t) { + arg[t - parg->comm] = '\0'; + t++; + } + parg->type = find_fetch_type(t); + if (!parg->type) { + pr_info("Unsupported type: %s\n", t); + return -EINVAL; + } + parg->offset = tp->size; + tp->size += parg->type->size; + return __parse_probe_arg(arg, parg->type, &parg->fetch, is_return); } /* Return 1 if name is reserved or already used by another argument */ @@ -602,15 +703,18 @@ static int create_trace_probe(int argc, char **argv) * @ADDR : fetch memory at ADDR (ADDR should be in kernel) * @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol) * %REG : fetch register REG - * Indirect memory fetch: + * Dereferencing memory fetch: * +|-offs(ARG) : fetch memory at ARG +|- offs address. * Alias name of args: * NAME=FETCHARG : set NAME as alias of FETCHARG. + * Type of args: + * FETCHARG:TYPE : use TYPE instead of unsigned long. */ struct trace_probe *tp; int i, ret = 0; int is_return = 0, is_delete = 0; - char *symbol = NULL, *event = NULL, *arg = NULL, *group = NULL; + char *symbol = NULL, *event = NULL, *group = NULL; + char *arg, *tmp; unsigned long offset = 0; void *addr = NULL; char buf[MAX_EVENT_NAME_LEN]; @@ -723,13 +827,6 @@ static int create_trace_probe(int argc, char **argv) else arg = argv[i]; - if (conflict_field_name(argv[i], tp->args, i)) { - pr_info("Argument%d name '%s' conflicts with " - "another field.\n", i, argv[i]); - ret = -EINVAL; - goto error; - } - tp->args[i].name = kstrdup(argv[i], GFP_KERNEL); if (!tp->args[i].name) { pr_info("Failed to allocate argument%d name '%s'.\n", @@ -737,9 +834,19 @@ static int create_trace_probe(int argc, char **argv) ret = -ENOMEM; goto error; } + tmp = strchr(tp->args[i].name, ':'); + if (tmp) + *tmp = '_'; /* convert : to _ */ + + if (conflict_field_name(tp->args[i].name, tp->args, i)) { + pr_info("Argument%d name '%s' conflicts with " + "another field.\n", i, argv[i]); + ret = -EINVAL; + goto error; + } /* Parse fetch argument */ - ret = parse_probe_arg(arg, &tp->args[i].fetch, is_return); + ret = parse_probe_arg(arg, tp, &tp->args[i], is_return); if (ret) { pr_info("Parse error at argument%d. (%d)\n", i, ret); kfree(tp->args[i].name); @@ -794,8 +901,7 @@ static void probes_seq_stop(struct seq_file *m, void *v) static int probes_seq_show(struct seq_file *m, void *v) { struct trace_probe *tp = v; - int i, ret; - char buf[MAX_ARGSTR_LEN + 1]; + int i; seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p'); seq_printf(m, ":%s/%s", tp->call.system, tp->call.name); @@ -807,15 +913,10 @@ static int probes_seq_show(struct seq_file *m, void *v) else seq_printf(m, " %s", probe_symbol(tp)); - for (i = 0; i < tp->nr_args; i++) { - ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i].fetch); - if (ret < 0) { - pr_warning("Argument%d decoding error(%d).\n", i, ret); - return ret; - } - seq_printf(m, " %s=%s", tp->args[i].name, buf); - } + for (i = 0; i < tp->nr_args; i++) + seq_printf(m, " %s=%s", tp->args[i].name, tp->args[i].comm); seq_printf(m, "\n"); + return 0; } @@ -945,9 +1046,10 @@ static const struct file_operations kprobe_profile_ops = { static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs) { struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp); - struct kprobe_trace_entry *entry; + struct kprobe_trace_entry_head *entry; struct ring_buffer_event *event; struct ring_buffer *buffer; + u8 *data; int size, i, pc; unsigned long irq_flags; struct ftrace_event_call *call = &tp->call; @@ -957,7 +1059,7 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs) local_save_flags(irq_flags); pc = preempt_count(); - size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args); + size = sizeof(*entry) + tp->size; event = trace_current_buffer_lock_reserve(&buffer, call->id, size, irq_flags, pc); @@ -965,10 +1067,10 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs) return; entry = ring_buffer_event_data(event); - entry->nargs = tp->nr_args; entry->ip = (unsigned long)kp->addr; + data = (u8 *)&entry[1]; for (i = 0; i < tp->nr_args; i++) - entry->args[i] = call_fetch(&tp->args[i].fetch, regs); + call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset); if (!filter_current_check_discard(buffer, call, entry, event)) trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc); @@ -979,9 +1081,10 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri, struct pt_regs *regs) { struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp); - struct kretprobe_trace_entry *entry; + struct kretprobe_trace_entry_head *entry; struct ring_buffer_event *event; struct ring_buffer *buffer; + u8 *data; int size, i, pc; unsigned long irq_flags; struct ftrace_event_call *call = &tp->call; @@ -989,7 +1092,7 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri, local_save_flags(irq_flags); pc = preempt_count(); - size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args); + size = sizeof(*entry) + tp->size; event = trace_current_buffer_lock_reserve(&buffer, call->id, size, irq_flags, pc); @@ -997,11 +1100,11 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri, return; entry = ring_buffer_event_data(event); - entry->nargs = tp->nr_args; entry->func = (unsigned long)tp->rp.kp.addr; entry->ret_ip = (unsigned long)ri->ret_addr; + data = (u8 *)&entry[1]; for (i = 0; i < tp->nr_args; i++) - entry->args[i] = call_fetch(&tp->args[i].fetch, regs); + call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset); if (!filter_current_check_discard(buffer, call, entry, event)) trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc); @@ -1011,13 +1114,14 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri, enum print_line_t print_kprobe_event(struct trace_iterator *iter, int flags) { - struct kprobe_trace_entry *field; + struct kprobe_trace_entry_head *field; struct trace_seq *s = &iter->seq; struct trace_event *event; struct trace_probe *tp; + u8 *data; int i; - field = (struct kprobe_trace_entry *)iter->ent; + field = (struct kprobe_trace_entry_head *)iter->ent; event = ftrace_find_event(field->ent.type); tp = container_of(event, struct trace_probe, event); @@ -1030,9 +1134,10 @@ print_kprobe_event(struct trace_iterator *iter, int flags) if (!trace_seq_puts(s, ")")) goto partial; - for (i = 0; i < field->nargs; i++) - if (!trace_seq_printf(s, " %s=%lx", - tp->args[i].name, field->args[i])) + data = (u8 *)&field[1]; + for (i = 0; i < tp->nr_args; i++) + if (!tp->args[i].type->print(s, tp->args[i].name, + data + tp->args[i].offset)) goto partial; if (!trace_seq_puts(s, "\n")) @@ -1046,13 +1151,14 @@ partial: enum print_line_t print_kretprobe_event(struct trace_iterator *iter, int flags) { - struct kretprobe_trace_entry *field; + struct kretprobe_trace_entry_head *field; struct trace_seq *s = &iter->seq; struct trace_event *event; struct trace_probe *tp; + u8 *data; int i; - field = (struct kretprobe_trace_entry *)iter->ent; + field = (struct kretprobe_trace_entry_head *)iter->ent; event = ftrace_find_event(field->ent.type); tp = container_of(event, struct trace_probe, event); @@ -1071,9 +1177,10 @@ print_kretprobe_event(struct trace_iterator *iter, int flags) if (!trace_seq_puts(s, ")")) goto partial; - for (i = 0; i < field->nargs; i++) - if (!trace_seq_printf(s, " %s=%lx", - tp->args[i].name, field->args[i])) + data = (u8 *)&field[1]; + for (i = 0; i < tp->nr_args; i++) + if (!tp->args[i].type->print(s, tp->args[i].name, + data + tp->args[i].offset)) goto partial; if (!trace_seq_puts(s, "\n")) @@ -1129,29 +1236,43 @@ static int probe_event_raw_init(struct ftrace_event_call *event_call) static int kprobe_event_define_fields(struct ftrace_event_call *event_call) { int ret, i; - struct kprobe_trace_entry field; + struct kprobe_trace_entry_head field; struct trace_probe *tp = (struct trace_probe *)event_call->data; DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0); - DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1); /* Set argument names as fields */ - for (i = 0; i < tp->nr_args; i++) - DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0); + for (i = 0; i < tp->nr_args; i++) { + ret = trace_define_field(event_call, tp->args[i].type->name, + tp->args[i].name, + sizeof(field) + tp->args[i].offset, + tp->args[i].type->size, + tp->args[i].type->is_signed, + FILTER_OTHER); + if (ret) + return ret; + } return 0; } static int kretprobe_event_define_fields(struct ftrace_event_call *event_call) { int ret, i; - struct kretprobe_trace_entry field; + struct kretprobe_trace_entry_head field; struct trace_probe *tp = (struct trace_probe *)event_call->data; DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0); DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0); - DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1); /* Set argument names as fields */ - for (i = 0; i < tp->nr_args; i++) - DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0); + for (i = 0; i < tp->nr_args; i++) { + ret = trace_define_field(event_call, tp->args[i].type->name, + tp->args[i].name, + sizeof(field) + tp->args[i].offset, + tp->args[i].type->size, + tp->args[i].type->is_signed, + FILTER_OTHER); + if (ret) + return ret; + } return 0; } @@ -1176,8 +1297,8 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len) pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt); for (i = 0; i < tp->nr_args; i++) { - pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%%lx", - tp->args[i].name); + pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s", + tp->args[i].name, tp->args[i].type->fmt); } pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg); @@ -1219,12 +1340,13 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp, { struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp); struct ftrace_event_call *call = &tp->call; - struct kprobe_trace_entry *entry; + struct kprobe_trace_entry_head *entry; + u8 *data; int size, __size, i; unsigned long irq_flags; int rctx; - __size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args); + __size = sizeof(*entry) + tp->size; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, @@ -1235,10 +1357,10 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp, if (!entry) return; - entry->nargs = tp->nr_args; entry->ip = (unsigned long)kp->addr; + data = (u8 *)&entry[1]; for (i = 0; i < tp->nr_args; i++) - entry->args[i] = call_fetch(&tp->args[i].fetch, regs); + call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset); perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs); } @@ -1249,12 +1371,13 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, { struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp); struct ftrace_event_call *call = &tp->call; - struct kretprobe_trace_entry *entry; + struct kretprobe_trace_entry_head *entry; + u8 *data; int size, __size, i; unsigned long irq_flags; int rctx; - __size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args); + __size = sizeof(*entry) + tp->size; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, @@ -1265,11 +1388,11 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, if (!entry) return; - entry->nargs = tp->nr_args; entry->func = (unsigned long)tp->rp.kp.addr; entry->ret_ip = (unsigned long)ri->ret_addr; + data = (u8 *)&entry[1]; for (i = 0; i < tp->nr_args; i++) - entry->args[i] = call_fetch(&tp->args[i].fetch, regs); + call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset); perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, irq_flags, regs); diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 81003b4d617f..1cc9858258b3 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -17,7 +17,6 @@ static inline int trace_valid_entry(struct trace_entry *entry) case TRACE_BRANCH: case TRACE_GRAPH_ENT: case TRACE_GRAPH_RET: - case TRACE_HW_BRANCHES: case TRACE_KSYM: return 1; } @@ -755,62 +754,6 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr) } #endif /* CONFIG_BRANCH_TRACER */ -#ifdef CONFIG_HW_BRANCH_TRACER -int -trace_selftest_startup_hw_branches(struct tracer *trace, - struct trace_array *tr) -{ - struct trace_iterator *iter; - struct tracer tracer; - unsigned long count; - int ret; - - if (!trace->open) { - printk(KERN_CONT "missing open function..."); - return -1; - } - - ret = tracer_init(trace, tr); - if (ret) { - warn_failed_init_tracer(trace, ret); - return ret; - } - - /* - * The hw-branch tracer needs to collect the trace from the various - * cpu trace buffers - before tracing is stopped. - */ - iter = kzalloc(sizeof(*iter), GFP_KERNEL); - if (!iter) - return -ENOMEM; - - memcpy(&tracer, trace, sizeof(tracer)); - - iter->trace = &tracer; - iter->tr = tr; - iter->pos = -1; - mutex_init(&iter->mutex); - - trace->open(iter); - - mutex_destroy(&iter->mutex); - kfree(iter); - - tracing_stop(); - - ret = trace_test_buffer(tr, &count); - trace->reset(tr); - tracing_start(); - - if (!ret && !count) { - printk(KERN_CONT "no entries found.."); - ret = -1; - } - - return ret; -} -#endif /* CONFIG_HW_BRANCH_TRACER */ - #ifdef CONFIG_KSYM_TRACER static int ksym_selftest_dummy; diff --git a/mm/mlock.c b/mm/mlock.c index 8f4e2dfceec1..3f82720e0515 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -607,44 +607,3 @@ void user_shm_unlock(size_t size, struct user_struct *user) spin_unlock(&shmlock_user_lock); free_uid(user); } - -int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim, - size_t size) -{ - unsigned long lim, vm, pgsz; - int error = -ENOMEM; - - pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT; - - down_write(&mm->mmap_sem); - - lim = ACCESS_ONCE(rlim[RLIMIT_AS].rlim_cur) >> PAGE_SHIFT; - vm = mm->total_vm + pgsz; - if (lim < vm) - goto out; - - lim = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur) >> PAGE_SHIFT; - vm = mm->locked_vm + pgsz; - if (lim < vm) - goto out; - - mm->total_vm += pgsz; - mm->locked_vm += pgsz; - - error = 0; - out: - up_write(&mm->mmap_sem); - return error; -} - -void refund_locked_memory(struct mm_struct *mm, size_t size) -{ - unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT; - - down_write(&mm->mmap_sem); - - mm->total_vm -= pgsz; - mm->locked_vm -= pgsz; - - up_write(&mm->mmap_sem); -} diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt index ae525ac5a2ce..0181dddf6b61 100644 --- a/tools/perf/Documentation/perf-bench.txt +++ b/tools/perf/Documentation/perf-bench.txt @@ -19,12 +19,12 @@ COMMON OPTIONS -f:: --format=:: Specify format style. -Current available format styles are, +Current available format styles are: 'default':: Default style. This is mainly for human reading. --------------------- -% perf bench sched pipe # with no style specify +% perf bench sched pipe # with no style specified (executing 1000000 pipe operations between two tasks) Total time:5.855 sec 5.855061 usecs/op @@ -79,7 +79,7 @@ options (20 sender and receiver processes per group) Total time:0.308 sec -% perf bench sched messaging -t -g 20 # be multi-thread,with 20 groups +% perf bench sched messaging -t -g 20 # be multi-thread, with 20 groups (20 sender and receiver threads per group) (20 groups == 800 threads run) diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt new file mode 100644 index 000000000000..93400a0f17f0 --- /dev/null +++ b/tools/perf/Documentation/perf-kvm.txt @@ -0,0 +1,67 @@ +perf-kvm(1) +============== + +NAME +---- +perf-kvm - Tool to trace/measure kvm guest os + +SYNOPSIS +-------- +[verse] +'perf kvm' [--host] [--guest] [--guestmount=<path> + [--guestkallsyms=<path> --guestmodules=<path> | --guestvmlinux=<path>]] + {top|record|report|diff|buildid-list} +'perf kvm' [--host] [--guest] [--guestkallsyms=<path> --guestmodules=<path> + | --guestvmlinux=<path>] {top|record|report|diff|buildid-list} + +DESCRIPTION +----------- +There are a couple of variants of perf kvm: + + 'perf kvm [options] top <command>' to generates and displays + a performance counter profile of guest os in realtime + of an arbitrary workload. + + 'perf kvm record <command>' to record the performance couinter profile + of an arbitrary workload and save it into a perf data file. If both + --host and --guest are input, the perf data file name is perf.data.kvm. + If there is no --host but --guest, the file name is perf.data.guest. + If there is no --guest but --host, the file name is perf.data.host. + + 'perf kvm report' to display the performance counter profile information + recorded via perf kvm record. + + 'perf kvm diff' to displays the performance difference amongst two perf.data + files captured via perf record. + + 'perf kvm buildid-list' to display the buildids found in a perf data file, + so that other tools can be used to fetch packages with matching symbol tables + for use by perf report. + +OPTIONS +------- +--host=:: + Collect host side perforamnce profile. +--guest=:: + Collect guest side perforamnce profile. +--guestmount=<path>:: + Guest os root file system mount directory. Users mounts guest os + root directories under <path> by a specific filesystem access method, + typically, sshfs. For example, start 2 guest os. The one's pid is 8888 + and the other's is 9999. + #mkdir ~/guestmount; cd ~/guestmount + #sshfs -o allow_other,direct_io -p 5551 localhost:/ 8888/ + #sshfs -o allow_other,direct_io -p 5552 localhost:/ 9999/ + #perf kvm --host --guest --guestmount=~/guestmount top +--guestkallsyms=<path>:: + Guest os /proc/kallsyms file copy. 'perf' kvm' reads it to get guest + kernel symbols. Users copy it out from guest os. +--guestmodules=<path>:: + Guest os /proc/modules file copy. 'perf' kvm' reads it to get guest + kernel module information. Users copy it out from guest os. +--guestvmlinux=<path>:: + Guest os kernel vmlinux. + +SEE ALSO +-------- +linkperf:perf-top[1] perf-record[1] perf-report[1] perf-diff[1] perf-buildid-list[1] diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 34202b1be0bb..63c25d304880 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -57,6 +57,11 @@ OPTIONS --force:: Forcibly add events with existing name. +-n:: +--dry-run:: + Dry run. With this option, --add and --del doesn't execute actual + adding and removal operations. + PROBE SYNTAX ------------ Probe points are defined by following syntax. @@ -74,13 +79,22 @@ Probe points are defined by following syntax. 'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. Currently, event group name is set as 'probe'. 'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition. In addition, '@SRC' specifies a source file which has that function. It is also possible to specify a probe point by the source line number or lazy matching by using 'SRC:ALN' or 'SRC;PTN' syntax, where 'SRC' is the source file path, ':ALN' is the line number and ';PTN' is the lazy matching pattern. -'ARG' specifies the arguments of this probe point. You can use the name of local variable, or kprobe-tracer argument format (e.g. $retval, %ax, etc). +'ARG' specifies the arguments of this probe point, (see PROBE ARGUMENT). + +PROBE ARGUMENT +-------------- +Each probe argument follows below syntax. + + [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE] + +'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.) +'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. LINE SYNTAX ----------- Line range is descripted by following syntax. - "FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]" + "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]" FUNC specifies the function name of showing lines. 'RLN' is the start line number from function entry line, and 'RLN2' is the end line number. As same as diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index fc46c0b40f6e..020d871c7934 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -58,7 +58,7 @@ OPTIONS -f:: --force:: - Overwrite existing data file. + Overwrite existing data file. (deprecated) -c:: --count=:: @@ -101,7 +101,7 @@ OPTIONS -R:: --raw-samples:: -Collect raw sample records from all opened counters (typically for tracepoint counters). +Collect raw sample records from all opened counters (default for tracepoint counters). SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt index 1ce79198997b..8417644a6166 100644 --- a/tools/perf/Documentation/perf-sched.txt +++ b/tools/perf/Documentation/perf-sched.txt @@ -12,7 +12,7 @@ SYNOPSIS DESCRIPTION ----------- -There's four variants of perf sched: +There are four variants of perf sched: 'perf sched record <command>' to record the scheduling events of an arbitrary workload. @@ -27,7 +27,7 @@ There's four variants of perf sched: via perf sched record. (this is done by starting up mockup threads that mimic the workload based on the events in the trace. These threads can then replay the timings (CPU runtime and sleep patterns) - of the workload as it occured when it was recorded - and can repeat + of the workload as it occurred when it was recorded - and can repeat it a number of times, measuring its performance.) OPTIONS diff --git a/tools/perf/Makefile b/tools/perf/Makefile index bc0f670a8338..3cb3449a9645 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -1,3 +1,7 @@ +ifeq ("$(origin O)", "command line") + OUTPUT := $(O)/ +endif + # The default target of this Makefile is... all:: @@ -150,10 +154,17 @@ all:: # Define LDFLAGS=-static to build a static binary. # # Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds. +# +# Define NO_DWARF if you do not want debug-info analysis feature at all. -PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE - @$(SHELL_PATH) util/PERF-VERSION-GEN --include PERF-VERSION-FILE +$(shell sh -c 'mkdir -p $(OUTPUT)scripts/python/Perf-Trace-Util/' 2> /dev/null) +$(shell sh -c 'mkdir -p $(OUTPUT)scripts/perl/Perf-Trace-Util/' 2> /dev/null) +$(shell sh -c 'mkdir -p $(OUTPUT)util/scripting-engines/' 2> /dev/null) +$(shell sh -c 'mkdir $(OUTPUT)bench' 2> /dev/null) + +$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE + @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) +-include $(OUTPUT)PERF-VERSION-FILE uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not') uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not') @@ -308,7 +319,7 @@ PROGRAMS += $(EXTRA_PROGRAMS) # # Single 'perf' binary right now: # -PROGRAMS += perf +PROGRAMS += $(OUTPUT)perf # List built-in command $C whose implementation cmd_$C() is not in # builtin-$C.o but is linked in as part of some other command. @@ -318,7 +329,7 @@ PROGRAMS += perf ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS) # what 'all' will build but not install in perfexecdir -OTHER_PROGRAMS = perf$X +OTHER_PROGRAMS = $(OUTPUT)perf$X # Set paths to tools early so that they can be used for version tests. ifndef SHELL_PATH @@ -330,7 +341,7 @@ endif export PERL_PATH -LIB_FILE=libperf.a +LIB_FILE=$(OUTPUT)libperf.a LIB_H += ../../include/linux/perf_event.h LIB_H += ../../include/linux/rbtree.h @@ -375,7 +386,6 @@ LIB_H += util/header.h LIB_H += util/help.h LIB_H += util/session.h LIB_H += util/strbuf.h -LIB_H += util/string.h LIB_H += util/strlist.h LIB_H += util/svghelper.h LIB_H += util/run-command.h @@ -391,77 +401,78 @@ LIB_H += util/probe-finder.h LIB_H += util/probe-event.h LIB_H += util/cpumap.h -LIB_OBJS += util/abspath.o -LIB_OBJS += util/alias.o -LIB_OBJS += util/build-id.o -LIB_OBJS += util/config.o -LIB_OBJS += util/ctype.o -LIB_OBJS += util/debugfs.o -LIB_OBJS += util/environment.o -LIB_OBJS += util/event.o -LIB_OBJS += util/exec_cmd.o -LIB_OBJS += util/help.o -LIB_OBJS += util/levenshtein.o -LIB_OBJS += util/parse-options.o -LIB_OBJS += util/parse-events.o -LIB_OBJS += util/path.o -LIB_OBJS += util/rbtree.o -LIB_OBJS += util/bitmap.o -LIB_OBJS += util/hweight.o -LIB_OBJS += util/find_next_bit.o -LIB_OBJS += util/run-command.o -LIB_OBJS += util/quote.o -LIB_OBJS += util/strbuf.o -LIB_OBJS += util/string.o -LIB_OBJS += util/strlist.o -LIB_OBJS += util/usage.o -LIB_OBJS += util/wrapper.o -LIB_OBJS += util/sigchain.o -LIB_OBJS += util/symbol.o -LIB_OBJS += util/color.o -LIB_OBJS += util/pager.o -LIB_OBJS += util/header.o -LIB_OBJS += util/callchain.o -LIB_OBJS += util/values.o -LIB_OBJS += util/debug.o -LIB_OBJS += util/map.o -LIB_OBJS += util/session.o -LIB_OBJS += util/thread.o -LIB_OBJS += util/trace-event-parse.o -LIB_OBJS += util/trace-event-read.o -LIB_OBJS += util/trace-event-info.o -LIB_OBJS += util/trace-event-scripting.o -LIB_OBJS += util/svghelper.o -LIB_OBJS += util/sort.o -LIB_OBJS += util/hist.o -LIB_OBJS += util/probe-event.o -LIB_OBJS += util/util.o -LIB_OBJS += util/cpumap.o - -BUILTIN_OBJS += builtin-annotate.o - -BUILTIN_OBJS += builtin-bench.o +LIB_OBJS += $(OUTPUT)util/abspath.o +LIB_OBJS += $(OUTPUT)util/alias.o +LIB_OBJS += $(OUTPUT)util/build-id.o +LIB_OBJS += $(OUTPUT)util/config.o +LIB_OBJS += $(OUTPUT)util/ctype.o +LIB_OBJS += $(OUTPUT)util/debugfs.o +LIB_OBJS += $(OUTPUT)util/environment.o +LIB_OBJS += $(OUTPUT)util/event.o +LIB_OBJS += $(OUTPUT)util/exec_cmd.o +LIB_OBJS += $(OUTPUT)util/help.o +LIB_OBJS += $(OUTPUT)util/levenshtein.o +LIB_OBJS += $(OUTPUT)util/parse-options.o +LIB_OBJS += $(OUTPUT)util/parse-events.o +LIB_OBJS += $(OUTPUT)util/path.o +LIB_OBJS += $(OUTPUT)util/rbtree.o +LIB_OBJS += $(OUTPUT)util/bitmap.o +LIB_OBJS += $(OUTPUT)util/hweight.o +LIB_OBJS += $(OUTPUT)util/find_next_bit.o +LIB_OBJS += $(OUTPUT)util/run-command.o +LIB_OBJS += $(OUTPUT)util/quote.o +LIB_OBJS += $(OUTPUT)util/strbuf.o +LIB_OBJS += $(OUTPUT)util/string.o +LIB_OBJS += $(OUTPUT)util/strlist.o +LIB_OBJS += $(OUTPUT)util/usage.o +LIB_OBJS += $(OUTPUT)util/wrapper.o +LIB_OBJS += $(OUTPUT)util/sigchain.o +LIB_OBJS += $(OUTPUT)util/symbol.o +LIB_OBJS += $(OUTPUT)util/color.o +LIB_OBJS += $(OUTPUT)util/pager.o +LIB_OBJS += $(OUTPUT)util/header.o +LIB_OBJS += $(OUTPUT)util/callchain.o +LIB_OBJS += $(OUTPUT)util/values.o +LIB_OBJS += $(OUTPUT)util/debug.o +LIB_OBJS += $(OUTPUT)util/map.o +LIB_OBJS += $(OUTPUT)util/session.o +LIB_OBJS += $(OUTPUT)util/thread.o +LIB_OBJS += $(OUTPUT)util/trace-event-parse.o +LIB_OBJS += $(OUTPUT)util/trace-event-read.o +LIB_OBJS += $(OUTPUT)util/trace-event-info.o +LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o +LIB_OBJS += $(OUTPUT)util/svghelper.o +LIB_OBJS += $(OUTPUT)util/sort.o +LIB_OBJS += $(OUTPUT)util/hist.o +LIB_OBJS += $(OUTPUT)util/probe-event.o +LIB_OBJS += $(OUTPUT)util/util.o +LIB_OBJS += $(OUTPUT)util/cpumap.o + +BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o + +BUILTIN_OBJS += $(OUTPUT)builtin-bench.o # Benchmark modules -BUILTIN_OBJS += bench/sched-messaging.o -BUILTIN_OBJS += bench/sched-pipe.o -BUILTIN_OBJS += bench/mem-memcpy.o - -BUILTIN_OBJS += builtin-diff.o -BUILTIN_OBJS += builtin-help.o -BUILTIN_OBJS += builtin-sched.o -BUILTIN_OBJS += builtin-buildid-list.o -BUILTIN_OBJS += builtin-buildid-cache.o -BUILTIN_OBJS += builtin-list.o -BUILTIN_OBJS += builtin-record.o -BUILTIN_OBJS += builtin-report.o -BUILTIN_OBJS += builtin-stat.o -BUILTIN_OBJS += builtin-timechart.o -BUILTIN_OBJS += builtin-top.o -BUILTIN_OBJS += builtin-trace.o -BUILTIN_OBJS += builtin-probe.o -BUILTIN_OBJS += builtin-kmem.o -BUILTIN_OBJS += builtin-lock.o +BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o +BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o +BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o + +BUILTIN_OBJS += $(OUTPUT)builtin-diff.o +BUILTIN_OBJS += $(OUTPUT)builtin-help.o +BUILTIN_OBJS += $(OUTPUT)builtin-sched.o +BUILTIN_OBJS += $(OUTPUT)builtin-buildid-list.o +BUILTIN_OBJS += $(OUTPUT)builtin-buildid-cache.o +BUILTIN_OBJS += $(OUTPUT)builtin-list.o +BUILTIN_OBJS += $(OUTPUT)builtin-record.o +BUILTIN_OBJS += $(OUTPUT)builtin-report.o +BUILTIN_OBJS += $(OUTPUT)builtin-stat.o +BUILTIN_OBJS += $(OUTPUT)builtin-timechart.o +BUILTIN_OBJS += $(OUTPUT)builtin-top.o +BUILTIN_OBJS += $(OUTPUT)builtin-trace.o +BUILTIN_OBJS += $(OUTPUT)builtin-probe.o +BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o +BUILTIN_OBJS += $(OUTPUT)builtin-lock.o +BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o PERFLIBS = $(LIB_FILE) @@ -492,6 +503,10 @@ ifeq ($(uname_S),Darwin) PTHREAD_LIBS = endif +ifneq ($(OUTPUT),) + BASIC_CFLAGS += -I$(OUTPUT) +endif + ifeq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y) ifneq ($(shell sh -c "(echo '\#include <gnu/libc-version.h>'; echo 'int main(void) { const char * version = gnu_get_libc_version(); return (long)version; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y) msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); @@ -506,11 +521,20 @@ endif ifneq ($(shell sh -c "(echo '\#include <dwarf.h>'; echo '\#include <libdw.h>'; echo 'int main(void) { Dwarf *dbg; dbg = dwarf_begin(0, DWARF_C_READ); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -I/usr/include/elfutils -ldw -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y) msg := $(warning No libdw.h found or old libdw.h found, disables dwarf support. Please install elfutils-devel/elfutils-dev); - BASIC_CFLAGS += -DNO_DWARF_SUPPORT else - BASIC_CFLAGS += -I/usr/include/elfutils +ifndef NO_DWARF + BASIC_CFLAGS += -I/usr/include/elfutils -DDWARF_SUPPORT EXTLIBS += -lelf -ldw - LIB_OBJS += util/probe-finder.o + LIB_OBJS += $(OUTPUT)util/probe-finder.o +endif +endif + +ifneq ($(shell sh -c "(echo '\#include <newt.h>'; echo 'int main(void) { newtInit(); newtCls(); return newtFinished(); }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -lnewt -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y) + msg := $(warning newt not found, disables TUI support. Please install newt-devel or libnewt-dev); + BASIC_CFLAGS += -DNO_NEWT_SUPPORT +else + EXTLIBS += -lnewt + LIB_OBJS += $(OUTPUT)util/newt.o endif ifndef NO_LIBPERL @@ -522,8 +546,8 @@ ifneq ($(shell sh -c "(echo '\#include <EXTERN.h>'; echo '\#include <perl.h>'; e BASIC_CFLAGS += -DNO_LIBPERL else ALL_LDFLAGS += $(PERL_EMBED_LDOPTS) - LIB_OBJS += util/scripting-engines/trace-event-perl.o - LIB_OBJS += scripts/perl/Perf-Trace-Util/Context.o + LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o + LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o endif ifndef NO_LIBPYTHON @@ -531,12 +555,12 @@ PYTHON_EMBED_LDOPTS = `python-config --ldflags 2>/dev/null` PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null` endif -ifneq ($(shell sh -c "(echo '\#include <Python.h>'; echo 'int main(void) { Py_Initialize(); return 0; }') | $(CC) -x c - $(PYTHON_EMBED_CCOPTS) -o /dev/null $(PYTHON_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y) +ifneq ($(shell sh -c "(echo '\#include <Python.h>'; echo 'int main(void) { Py_Initialize(); return 0; }') | $(CC) -x c - $(PYTHON_EMBED_CCOPTS) -o $(BITBUCKET) $(PYTHON_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y) BASIC_CFLAGS += -DNO_LIBPYTHON else ALL_LDFLAGS += $(PYTHON_EMBED_LDOPTS) - LIB_OBJS += util/scripting-engines/trace-event-python.o - LIB_OBJS += scripts/python/Perf-Trace-Util/Context.o + LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o + LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o endif ifdef NO_DEMANGLE @@ -607,53 +631,53 @@ ifdef NO_C99_FORMAT endif ifdef SNPRINTF_RETURNS_BOGUS COMPAT_CFLAGS += -DSNPRINTF_RETURNS_BOGUS - COMPAT_OBJS += compat/snprintf.o + COMPAT_OBJS += $(OUTPUT)compat/snprintf.o endif ifdef FREAD_READS_DIRECTORIES COMPAT_CFLAGS += -DFREAD_READS_DIRECTORIES - COMPAT_OBJS += compat/fopen.o + COMPAT_OBJS += $(OUTPUT)compat/fopen.o endif ifdef NO_SYMLINK_HEAD BASIC_CFLAGS += -DNO_SYMLINK_HEAD endif ifdef NO_STRCASESTR COMPAT_CFLAGS += -DNO_STRCASESTR - COMPAT_OBJS += compat/strcasestr.o + COMPAT_OBJS += $(OUTPUT)compat/strcasestr.o endif ifdef NO_STRTOUMAX COMPAT_CFLAGS += -DNO_STRTOUMAX - COMPAT_OBJS += compat/strtoumax.o + COMPAT_OBJS += $(OUTPUT)compat/strtoumax.o endif ifdef NO_STRTOULL COMPAT_CFLAGS += -DNO_STRTOULL endif ifdef NO_SETENV COMPAT_CFLAGS += -DNO_SETENV - COMPAT_OBJS += compat/setenv.o + COMPAT_OBJS += $(OUTPUT)compat/setenv.o endif ifdef NO_MKDTEMP COMPAT_CFLAGS += -DNO_MKDTEMP - COMPAT_OBJS += compat/mkdtemp.o + COMPAT_OBJS += $(OUTPUT)compat/mkdtemp.o endif ifdef NO_UNSETENV COMPAT_CFLAGS += -DNO_UNSETENV - COMPAT_OBJS += compat/unsetenv.o + COMPAT_OBJS += $(OUTPUT)compat/unsetenv.o endif ifdef NO_SYS_SELECT_H BASIC_CFLAGS += -DNO_SYS_SELECT_H endif ifdef NO_MMAP COMPAT_CFLAGS += -DNO_MMAP - COMPAT_OBJS += compat/mmap.o + COMPAT_OBJS += $(OUTPUT)compat/mmap.o else ifdef USE_WIN32_MMAP COMPAT_CFLAGS += -DUSE_WIN32_MMAP - COMPAT_OBJS += compat/win32mmap.o + COMPAT_OBJS += $(OUTPUT)compat/win32mmap.o endif endif ifdef NO_PREAD COMPAT_CFLAGS += -DNO_PREAD - COMPAT_OBJS += compat/pread.o + COMPAT_OBJS += $(OUTPUT)compat/pread.o endif ifdef NO_FAST_WORKING_DIRECTORY BASIC_CFLAGS += -DNO_FAST_WORKING_DIRECTORY @@ -675,10 +699,10 @@ else endif endif ifdef NO_INET_NTOP - LIB_OBJS += compat/inet_ntop.o + LIB_OBJS += $(OUTPUT)compat/inet_ntop.o endif ifdef NO_INET_PTON - LIB_OBJS += compat/inet_pton.o + LIB_OBJS += $(OUTPUT)compat/inet_pton.o endif ifdef NO_ICONV @@ -695,15 +719,15 @@ endif ifdef PPC_SHA1 SHA1_HEADER = "ppc/sha1.h" - LIB_OBJS += ppc/sha1.o ppc/sha1ppc.o + LIB_OBJS += $(OUTPUT)ppc/sha1.o ppc/sha1ppc.o else ifdef ARM_SHA1 SHA1_HEADER = "arm/sha1.h" - LIB_OBJS += arm/sha1.o arm/sha1_arm.o + LIB_OBJS += $(OUTPUT)arm/sha1.o $(OUTPUT)arm/sha1_arm.o else ifdef MOZILLA_SHA1 SHA1_HEADER = "mozilla-sha1/sha1.h" - LIB_OBJS += mozilla-sha1/sha1.o + LIB_OBJS += $(OUTPUT)mozilla-sha1/sha1.o else SHA1_HEADER = <openssl/sha.h> EXTLIBS += $(LIB_4_CRYPTO) @@ -715,15 +739,15 @@ ifdef NO_PERL_MAKEMAKER endif ifdef NO_HSTRERROR COMPAT_CFLAGS += -DNO_HSTRERROR - COMPAT_OBJS += compat/hstrerror.o + COMPAT_OBJS += $(OUTPUT)compat/hstrerror.o endif ifdef NO_MEMMEM COMPAT_CFLAGS += -DNO_MEMMEM - COMPAT_OBJS += compat/memmem.o + COMPAT_OBJS += $(OUTPUT)compat/memmem.o endif ifdef INTERNAL_QSORT COMPAT_CFLAGS += -DINTERNAL_QSORT - COMPAT_OBJS += compat/qsort.o + COMPAT_OBJS += $(OUTPUT)compat/qsort.o endif ifdef RUNTIME_PREFIX COMPAT_CFLAGS += -DRUNTIME_PREFIX @@ -803,7 +827,7 @@ export TAR INSTALL DESTDIR SHELL_PATH SHELL = $(SHELL_PATH) -all:: .perf.dev.null shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) PERF-BUILD-OPTIONS +all:: .perf.dev.null shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) $(OUTPUT)PERF-BUILD-OPTIONS ifneq (,$X) $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), test '$p' -ef '$p$X' || $(RM) '$p';) endif @@ -815,39 +839,39 @@ please_set_SHELL_PATH_to_a_more_modern_shell: shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell -strip: $(PROGRAMS) perf$X - $(STRIP) $(STRIP_OPTS) $(PROGRAMS) perf$X +strip: $(PROGRAMS) $(OUTPUT)perf$X + $(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf$X -perf.o: perf.c common-cmds.h PERF-CFLAGS +$(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -DPERF_VERSION='"$(PERF_VERSION)"' \ '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ - $(ALL_CFLAGS) -c $(filter %.c,$^) + $(ALL_CFLAGS) -c $(filter %.c,$^) -o $@ -perf$X: perf.o $(BUILTIN_OBJS) $(PERFLIBS) - $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ perf.o \ +$(OUTPUT)perf$X: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS) + $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(OUTPUT)perf.o \ $(BUILTIN_OBJS) $(ALL_LDFLAGS) $(LIBS) -builtin-help.o: builtin-help.c common-cmds.h PERF-CFLAGS - $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \ +$(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \ '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ '-DPERF_MAN_PATH="$(mandir_SQ)"' \ '-DPERF_INFO_PATH="$(infodir_SQ)"' $< -builtin-timechart.o: builtin-timechart.c common-cmds.h PERF-CFLAGS - $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \ +$(OUTPUT)builtin-timechart.o: builtin-timechart.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \ '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ '-DPERF_MAN_PATH="$(mandir_SQ)"' \ '-DPERF_INFO_PATH="$(infodir_SQ)"' $< -$(BUILT_INS): perf$X +$(BUILT_INS): $(OUTPUT)perf$X $(QUIET_BUILT_IN)$(RM) $@ && \ ln perf$X $@ 2>/dev/null || \ ln -s perf$X $@ 2>/dev/null || \ cp perf$X $@ -common-cmds.h: util/generate-cmdlist.sh command-list.txt +$(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt -common-cmds.h: $(wildcard Documentation/perf-*.txt) +$(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt) $(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@ $(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh @@ -859,7 +883,7 @@ $(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh -e 's/@@NO_CURL@@/$(NO_CURL)/g' \ $@.sh >$@+ && \ chmod +x $@+ && \ - mv $@+ $@ + mv $@+ $(OUTPUT)$@ configure: configure.ac $(QUIET_GEN)$(RM) $@ $<+ && \ @@ -869,60 +893,60 @@ configure: configure.ac $(RM) $<+ # These can record PERF_VERSION -perf.o perf.spec \ +$(OUTPUT)perf.o perf.spec \ $(patsubst %.sh,%,$(SCRIPT_SH)) \ $(patsubst %.perl,%,$(SCRIPT_PERL)) \ - : PERF-VERSION-FILE + : $(OUTPUT)PERF-VERSION-FILE -%.o: %.c PERF-CFLAGS - $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) $< -%.s: %.c PERF-CFLAGS +$(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $< +$(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $< -%.o: %.S - $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) $< +$(OUTPUT)%.o: %.S + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $< -util/exec_cmd.o: util/exec_cmd.c PERF-CFLAGS - $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \ +$(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \ '-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \ '-DBINDIR="$(bindir_relative_SQ)"' \ '-DPREFIX="$(prefix_SQ)"' \ $< -builtin-init-db.o: builtin-init-db.c PERF-CFLAGS - $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) -DDEFAULT_PERF_TEMPLATE_DIR='"$(template_dir_SQ)"' $< +$(OUTPUT)builtin-init-db.o: builtin-init-db.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DDEFAULT_PERF_TEMPLATE_DIR='"$(template_dir_SQ)"' $< -util/config.o: util/config.c PERF-CFLAGS - $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< +$(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< -util/rbtree.o: ../../lib/rbtree.c PERF-CFLAGS - $(QUIET_CC)$(CC) -o util/rbtree.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< +$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< # some perf warning policies can't fit to lib/bitmap.c, eg: it warns about variable shadowing # from <string.h> that comes from kernel headers wrapping. KBITMAP_FLAGS=`echo $(ALL_CFLAGS) | sed s/-Wshadow// | sed s/-Wswitch-default// | sed s/-Wextra//` -util/bitmap.o: ../../lib/bitmap.c PERF-CFLAGS - $(QUIET_CC)$(CC) -o util/bitmap.o -c $(KBITMAP_FLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< +$(OUTPUT)util/bitmap.o: ../../lib/bitmap.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(KBITMAP_FLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< -util/hweight.o: ../../lib/hweight.c PERF-CFLAGS - $(QUIET_CC)$(CC) -o util/hweight.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< +$(OUTPUT)util/hweight.o: ../../lib/hweight.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< -util/find_next_bit.o: ../../lib/find_next_bit.c PERF-CFLAGS - $(QUIET_CC)$(CC) -o util/find_next_bit.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< +$(OUTPUT)util/find_next_bit.o: ../../lib/find_next_bit.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< -util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c PERF-CFLAGS - $(QUIET_CC)$(CC) -o util/scripting-engines/trace-event-perl.o -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $< +$(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $< -scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c PERF-CFLAGS - $(QUIET_CC)$(CC) -o scripts/perl/Perf-Trace-Util/Context.o -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $< +$(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $< -util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c PERF-CFLAGS - $(QUIET_CC)$(CC) -o util/scripting-engines/trace-event-python.o -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $< +$(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $< -scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c PERF-CFLAGS - $(QUIET_CC)$(CC) -o scripts/python/Perf-Trace-Util/Context.o -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $< +$(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $< -perf-%$X: %.o $(PERFLIBS) +$(OUTPUT)perf-%$X: %.o $(PERFLIBS) $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H) @@ -963,17 +987,17 @@ cscope: TRACK_CFLAGS = $(subst ','\'',$(ALL_CFLAGS)):\ $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ) -PERF-CFLAGS: .FORCE-PERF-CFLAGS +$(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS @FLAGS='$(TRACK_CFLAGS)'; \ - if test x"$$FLAGS" != x"`cat PERF-CFLAGS 2>/dev/null`" ; then \ + if test x"$$FLAGS" != x"`cat $(OUTPUT)PERF-CFLAGS 2>/dev/null`" ; then \ echo 1>&2 " * new build flags or prefix"; \ - echo "$$FLAGS" >PERF-CFLAGS; \ + echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \ fi # We need to apply sq twice, once to protect from the shell -# that runs PERF-BUILD-OPTIONS, and then again to protect it +# that runs $(OUTPUT)PERF-BUILD-OPTIONS, and then again to protect it # and the first level quoting from the shell that runs "echo". -PERF-BUILD-OPTIONS: .FORCE-PERF-BUILD-OPTIONS +$(OUTPUT)PERF-BUILD-OPTIONS: .FORCE-PERF-BUILD-OPTIONS @echo SHELL_PATH=\''$(subst ','\'',$(SHELL_PATH_SQ))'\' >$@ @echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@ @echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@ @@ -994,7 +1018,7 @@ all:: $(TEST_PROGRAMS) export NO_SVN_TESTS -check: common-cmds.h +check: $(OUTPUT)common-cmds.h if sparse; \ then \ for i in *.c */*.c; \ @@ -1028,10 +1052,10 @@ export perfexec_instdir install: all $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)' - $(INSTALL) perf$X '$(DESTDIR_SQ)$(bindir_SQ)' + $(INSTALL) $(OUTPUT)perf$X '$(DESTDIR_SQ)$(bindir_SQ)' $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace' $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin' - $(INSTALL) perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' + $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' $(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace' $(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl' $(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin' @@ -1045,7 +1069,7 @@ ifdef BUILT_INS $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' $(INSTALL) $(BUILT_INS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' ifneq (,$X) - $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), $(RM) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$p';) + $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) $(OUTPUT)perf$X)), $(RM) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$p';) endif endif @@ -1129,14 +1153,14 @@ clean: $(RM) *.o */*.o */*/*.o */*/*/*.o $(LIB_FILE) $(RM) $(ALL_PROGRAMS) $(BUILT_INS) perf$X $(RM) $(TEST_PROGRAMS) - $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo common-cmds.h TAGS tags cscope* + $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(RM) -r autom4te.cache $(RM) config.log config.mak.autogen config.mak.append config.status config.cache $(RM) -r $(PERF_TARNAME) .doc-tmp-dir $(RM) $(PERF_TARNAME).tar.gz perf-core_$(PERF_VERSION)-*.tar.gz $(RM) $(htmldocs).tar.gz $(manpages).tar.gz $(MAKE) -C Documentation/ clean - $(RM) PERF-VERSION-FILE PERF-CFLAGS PERF-BUILD-OPTIONS + $(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-BUILD-OPTIONS .PHONY: all install clean strip .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c index 89773178e894..38dae7465142 100644 --- a/tools/perf/bench/mem-memcpy.c +++ b/tools/perf/bench/mem-memcpy.c @@ -10,7 +10,6 @@ #include "../perf.h" #include "../util/util.h" #include "../util/parse-options.h" -#include "../util/string.h" #include "../util/header.h" #include "bench.h" @@ -24,7 +23,7 @@ static const char *length_str = "1MB"; static const char *routine = "default"; -static int use_clock = 0; +static bool use_clock = false; static int clock_fd; static const struct option options[] = { diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c index 81cee78181fa..da1b2e9f01ff 100644 --- a/tools/perf/bench/sched-messaging.c +++ b/tools/perf/bench/sched-messaging.c @@ -31,9 +31,9 @@ #define DATASIZE 100 -static int use_pipes = 0; +static bool use_pipes = false; static unsigned int loops = 100; -static unsigned int thread_mode = 0; +static bool thread_mode = false; static unsigned int num_groups = 10; struct sender_context { diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index 4f77c7c27640..d9ab3ce446ac 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -93,7 +93,7 @@ int bench_sched_pipe(int argc, const char **argv, switch (bench_format) { case BENCH_FORMAT_DEFAULT: - printf("# Extecuted %d pipe operations between two tasks\n\n", + printf("# Executed %d pipe operations between two tasks\n\n", loops); result_usec = diff.tv_sec * 1000000; diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 6ad7148451c5..f924b4332be6 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -14,7 +14,6 @@ #include "util/cache.h" #include <linux/rbtree.h> #include "util/symbol.h" -#include "util/string.h" #include "perf.h" #include "util/debug.h" @@ -29,11 +28,11 @@ static char const *input_name = "perf.data"; -static int force; +static bool force; -static int full_paths; +static bool full_paths; -static int print_line; +static bool print_line; struct sym_hist { u64 sum; @@ -69,13 +68,13 @@ static int sym__alloc_hist(struct symbol *self) static int annotate__hist_hit(struct hist_entry *he, u64 ip) { unsigned int sym_size, offset; - struct symbol *sym = he->sym; + struct symbol *sym = he->ms.sym; struct sym_priv *priv; struct sym_hist *h; he->count++; - if (!sym || !he->map) + if (!sym || !he->ms.map) return 0; priv = symbol__priv(sym); @@ -85,7 +84,7 @@ static int annotate__hist_hit(struct hist_entry *he, u64 ip) sym_size = sym->end - sym->start; offset = ip - sym->start; - pr_debug3("%s: ip=%#Lx\n", __func__, he->map->unmap_ip(he->map, ip)); + pr_debug3("%s: ip=%#Lx\n", __func__, he->ms.map->unmap_ip(he->ms.map, ip)); if (offset >= sym_size) return 0; @@ -94,8 +93,8 @@ static int annotate__hist_hit(struct hist_entry *he, u64 ip) h->sum++; h->ip[offset]++; - pr_debug3("%#Lx %s: count++ [ip: %#Lx, %#Lx] => %Ld\n", he->sym->start, - he->sym->name, ip, ip - he->sym->start, h->ip[offset]); + pr_debug3("%#Lx %s: count++ [ip: %#Lx, %#Lx] => %Ld\n", he->ms.sym->start, + he->ms.sym->name, ip, ip - he->ms.sym->start, h->ip[offset]); return 0; } @@ -187,7 +186,7 @@ static struct objdump_line *objdump__get_next_ip_line(struct list_head *head, static int parse_line(FILE *file, struct hist_entry *he, struct list_head *head) { - struct symbol *sym = he->sym; + struct symbol *sym = he->ms.sym; struct objdump_line *objdump_line; char *line = NULL, *tmp, *tmp2; size_t line_len; @@ -226,7 +225,7 @@ static int parse_line(FILE *file, struct hist_entry *he, } if (line_ip != -1) { - u64 start = map__rip_2objdump(he->map, sym->start); + u64 start = map__rip_2objdump(he->ms.map, sym->start); offset = line_ip - start; } @@ -244,7 +243,7 @@ static int objdump_line__print(struct objdump_line *self, struct list_head *head, struct hist_entry *he, u64 len) { - struct symbol *sym = he->sym; + struct symbol *sym = he->ms.sym; static const char *prev_line; static const char *prev_color; @@ -327,7 +326,7 @@ static void insert_source_line(struct sym_ext *sym_ext) static void free_source_line(struct hist_entry *he, int len) { - struct sym_priv *priv = symbol__priv(he->sym); + struct sym_priv *priv = symbol__priv(he->ms.sym); struct sym_ext *sym_ext = priv->ext; int i; @@ -346,7 +345,7 @@ static void free_source_line(struct hist_entry *he, int len) static void get_source_line(struct hist_entry *he, int len, const char *filename) { - struct symbol *sym = he->sym; + struct symbol *sym = he->ms.sym; u64 start; int i; char cmd[PATH_MAX * 2]; @@ -361,7 +360,7 @@ get_source_line(struct hist_entry *he, int len, const char *filename) if (!priv->ext) return; - start = he->map->unmap_ip(he->map, sym->start); + start = he->ms.map->unmap_ip(he->ms.map, sym->start); for (i = 0; i < len; i++) { char *path = NULL; @@ -425,7 +424,7 @@ static void print_summary(const char *filename) static void hist_entry__print_hits(struct hist_entry *self) { - struct symbol *sym = self->sym; + struct symbol *sym = self->ms.sym; struct sym_priv *priv = symbol__priv(sym); struct sym_hist *h = priv->hist; u64 len = sym->end - sym->start, offset; @@ -439,9 +438,9 @@ static void hist_entry__print_hits(struct hist_entry *self) static void annotate_sym(struct hist_entry *he) { - struct map *map = he->map; + struct map *map = he->ms.map; struct dso *dso = map->dso; - struct symbol *sym = he->sym; + struct symbol *sym = he->ms.sym; const char *filename = dso->long_name, *d_filename; u64 len; char command[PATH_MAX*2]; @@ -452,6 +451,16 @@ static void annotate_sym(struct hist_entry *he) if (!filename) return; + if (dso->origin == DSO__ORIG_KERNEL) { + if (dso->annotate_warned) + return; + dso->annotate_warned = 1; + pr_err("Can't annotate %s: No vmlinux file was found in the " + "path:\n", sym->name); + vmlinux_path__fprintf(stderr); + return; + } + pr_debug("%s: filename=%s, sym=%s, start=%#Lx, end=%#Lx\n", __func__, filename, sym->name, map->unmap_ip(map, sym->start), map->unmap_ip(map, sym->end)); @@ -516,17 +525,17 @@ static void perf_session__find_annotations(struct perf_session *self) struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node); struct sym_priv *priv; - if (he->sym == NULL) + if (he->ms.sym == NULL) continue; - priv = symbol__priv(he->sym); + priv = symbol__priv(he->ms.sym); if (priv->hist == NULL) continue; annotate_sym(he); /* * Since we have a hist_entry per IP for the same symbol, free - * he->sym->hist to signal we already processed this symbol. + * he->ms.sym->hist to signal we already processed this symbol. */ free(priv->hist); priv->hist = NULL; @@ -562,7 +571,7 @@ static int __cmd_annotate(void) perf_session__fprintf(session, stdout); if (verbose > 2) - dsos__fprintf(stdout); + dsos__fprintf(&session->kerninfo_root, stdout); perf_session__collapse_resort(&session->hists); perf_session__output_resort(&session->hists, session->event_total[0]); @@ -581,10 +590,12 @@ static const char * const annotate_usage[] = { static const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), + OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]", + "only consider symbols in these dsos"), OPT_STRING('s', "symbol", &sym_hist_filter, "symbol", "symbol to annotate"), OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), - OPT_BOOLEAN('v', "verbose", &verbose, + OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 30a05f552c96..f8e3d1852029 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -27,7 +27,7 @@ static const struct option buildid_cache_options[] = { "file list", "file(s) to add"), OPT_STRING('r', "remove", &remove_name_list_str, "file list", "file(s) to remove"), - OPT_BOOLEAN('v', "verbose", &verbose, "be more verbose"), + OPT_INCR('v', "verbose", &verbose, "be more verbose"), OPT_END() }; diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index d0675c02f81e..623afe3fdcb8 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -16,7 +16,7 @@ #include "util/symbol.h" static char const *input_name = "perf.data"; -static int force; +static bool force; static bool with_hits; static const char * const buildid_list_usage[] = { @@ -29,7 +29,7 @@ static const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), - OPT_BOOLEAN('v', "verbose", &verbose, + OPT_INCR('v', "verbose", &verbose, "be more verbose"), OPT_END() }; @@ -46,7 +46,7 @@ static int __cmd_buildid_list(void) if (with_hits) perf_session__process_events(session, &build_id__mark_dso_hit_ops); - dsos__fprintf_buildid(stdout, with_hits); + dsos__fprintf_buildid(&session->kerninfo_root, stdout, with_hits); perf_session__delete(session); return err; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 1ea15d8aeed1..207e860591e2 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -19,7 +19,7 @@ static char const *input_old = "perf.data.old", *input_new = "perf.data"; static char diff__default_sort_order[] = "dso,symbol"; -static int force; +static bool force; static bool show_displacement; static int perf_session__add_hist_entry(struct perf_session *self, @@ -33,7 +33,7 @@ static int perf_session__add_hist_entry(struct perf_session *self, return -ENOMEM; if (hit) - he->count += count; + __perf_session__add_count(he, al, count); return 0; } @@ -188,7 +188,7 @@ static const char * const diff_usage[] = { }; static const struct option options[] = { - OPT_BOOLEAN('v', "verbose", &verbose, + OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('m', "displacement", &show_displacement, "Show position displacement relative to baseline"), @@ -225,6 +225,10 @@ int cmd_diff(int argc, const char **argv, const char *prefix __used) input_new = argv[1]; } else input_new = argv[0]; + } else if (symbol_conf.default_guest_vmlinux_name || + symbol_conf.default_guest_kallsyms) { + input_old = "perf.data.host"; + input_new = "perf.data.guest"; } symbol_conf.exclude_other = false; diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 215b584007b1..81e3ecc40fc7 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -29,7 +29,7 @@ enum help_format { HELP_FORMAT_WEB, }; -static int show_all = 0; +static bool show_all = false; static enum help_format help_format = HELP_FORMAT_MAN; static struct option builtin_help_options[] = { OPT_BOOLEAN('a', "all", &show_all, "print all available commands"), diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 924a9518931a..db474bbf3322 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -351,6 +351,7 @@ static void __print_result(struct rb_root *root, struct perf_session *session, int n_lines, int is_caller) { struct rb_node *next; + struct kernel_info *kerninfo; printf("%.102s\n", graph_dotted_line); printf(" %-34s |", is_caller ? "Callsite": "Alloc Ptr"); @@ -359,23 +360,31 @@ static void __print_result(struct rb_root *root, struct perf_session *session, next = rb_first(root); + kerninfo = kerninfo__findhost(&session->kerninfo_root); + if (!kerninfo) { + pr_err("__print_result: couldn't find kernel information\n"); + return; + } while (next && n_lines--) { struct alloc_stat *data = rb_entry(next, struct alloc_stat, node); struct symbol *sym = NULL; + struct map_groups *kmaps = &kerninfo->kmaps; + struct map *map; char buf[BUFSIZ]; u64 addr; if (is_caller) { addr = data->call_site; if (!raw_ip) - sym = map_groups__find_function(&session->kmaps, addr, NULL); + sym = map_groups__find_function(kmaps, addr, + &map, NULL); } else addr = data->ptr; if (sym != NULL) snprintf(buf, sizeof(buf), "%s+%Lx", sym->name, - addr - sym->start); + addr - map->unmap_ip(map, sym->start)); else snprintf(buf, sizeof(buf), "%#Lx", addr); printf(" %-34s |", buf); @@ -488,6 +497,9 @@ static int __cmd_kmem(void) if (session == NULL) return -ENOMEM; + if (perf_session__create_kernel_maps(session) < 0) + goto out_delete; + if (!perf_session__has_traces(session, "kmem record")) goto out_delete; diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c new file mode 100644 index 000000000000..a4c7cae45024 --- /dev/null +++ b/tools/perf/builtin-kvm.c @@ -0,0 +1,144 @@ +#include "builtin.h" +#include "perf.h" + +#include "util/util.h" +#include "util/cache.h" +#include "util/symbol.h" +#include "util/thread.h" +#include "util/header.h" +#include "util/session.h" + +#include "util/parse-options.h" +#include "util/trace-event.h" + +#include "util/debug.h" + +#include <sys/prctl.h> + +#include <semaphore.h> +#include <pthread.h> +#include <math.h> + +static char *file_name; +static char name_buffer[256]; + +int perf_host = 1; +int perf_guest; + +static const char * const kvm_usage[] = { + "perf kvm [<options>] {top|record|report|diff|buildid-list}", + NULL +}; + +static const struct option kvm_options[] = { + OPT_STRING('i', "input", &file_name, "file", + "Input file name"), + OPT_STRING('o', "output", &file_name, "file", + "Output file name"), + OPT_BOOLEAN(0, "guest", &perf_guest, + "Collect guest os data"), + OPT_BOOLEAN(0, "host", &perf_host, + "Collect guest os data"), + OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory", + "guest mount directory under which every guest os" + " instance has a subdir"), + OPT_STRING(0, "guestvmlinux", &symbol_conf.default_guest_vmlinux_name, + "file", "file saving guest os vmlinux"), + OPT_STRING(0, "guestkallsyms", &symbol_conf.default_guest_kallsyms, + "file", "file saving guest os /proc/kallsyms"), + OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules, + "file", "file saving guest os /proc/modules"), + OPT_END() +}; + +static int __cmd_record(int argc, const char **argv) +{ + int rec_argc, i = 0, j; + const char **rec_argv; + + rec_argc = argc + 2; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); + rec_argv[i++] = strdup("record"); + rec_argv[i++] = strdup("-o"); + rec_argv[i++] = strdup(file_name); + for (j = 1; j < argc; j++, i++) + rec_argv[i] = argv[j]; + + BUG_ON(i != rec_argc); + + return cmd_record(i, rec_argv, NULL); +} + +static int __cmd_report(int argc, const char **argv) +{ + int rec_argc, i = 0, j; + const char **rec_argv; + + rec_argc = argc + 2; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); + rec_argv[i++] = strdup("report"); + rec_argv[i++] = strdup("-i"); + rec_argv[i++] = strdup(file_name); + for (j = 1; j < argc; j++, i++) + rec_argv[i] = argv[j]; + + BUG_ON(i != rec_argc); + + return cmd_report(i, rec_argv, NULL); +} + +static int __cmd_buildid_list(int argc, const char **argv) +{ + int rec_argc, i = 0, j; + const char **rec_argv; + + rec_argc = argc + 2; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); + rec_argv[i++] = strdup("buildid-list"); + rec_argv[i++] = strdup("-i"); + rec_argv[i++] = strdup(file_name); + for (j = 1; j < argc; j++, i++) + rec_argv[i] = argv[j]; + + BUG_ON(i != rec_argc); + + return cmd_buildid_list(i, rec_argv, NULL); +} + +int cmd_kvm(int argc, const char **argv, const char *prefix __used) +{ + perf_host = perf_guest = 0; + + argc = parse_options(argc, argv, kvm_options, kvm_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + if (!argc) + usage_with_options(kvm_usage, kvm_options); + + if (!perf_host) + perf_guest = 1; + + if (!file_name) { + if (perf_host && !perf_guest) + sprintf(name_buffer, "perf.data.host"); + else if (!perf_host && perf_guest) + sprintf(name_buffer, "perf.data.guest"); + else + sprintf(name_buffer, "perf.data.kvm"); + file_name = name_buffer; + } + + if (!strncmp(argv[0], "rec", 3)) + return __cmd_record(argc, argv); + else if (!strncmp(argv[0], "rep", 3)) + return __cmd_report(argc, argv); + else if (!strncmp(argv[0], "diff", 4)) + return cmd_diff(argc, argv, NULL); + else if (!strncmp(argv[0], "top", 3)) + return cmd_top(argc, argv, NULL); + else if (!strncmp(argv[0], "buildid-list", 12)) + return __cmd_buildid_list(argc, argv); + else + usage_with_options(kvm_usage, kvm_options); + + return 0; +} diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index e12c844df1e2..6c38e4febf9f 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -744,7 +744,7 @@ static const char * const lock_usage[] = { static const struct option lock_options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), - OPT_BOOLEAN('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), + OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_END() }; diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 152d6c9b1fa4..c1e54035e8cf 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -36,13 +36,10 @@ #include "builtin.h" #include "util/util.h" #include "util/strlist.h" -#include "util/event.h" +#include "util/symbol.h" #include "util/debug.h" #include "util/debugfs.h" -#include "util/symbol.h" -#include "util/thread.h" #include "util/parse-options.h" -#include "util/parse-events.h" /* For debugfs_path */ #include "util/probe-finder.h" #include "util/probe-event.h" @@ -50,103 +47,83 @@ /* Session management structure */ static struct { - bool need_dwarf; bool list_events; bool force_add; bool show_lines; - int nr_probe; - struct probe_point probes[MAX_PROBES]; + int nevents; + struct perf_probe_event events[MAX_PROBES]; struct strlist *dellist; - struct map_groups kmap_groups; - struct map *kmaps[MAP__NR_TYPES]; struct line_range line_range; -} session; +} params; /* Parse an event definition. Note that any error must die. */ -static void parse_probe_event(const char *str) +static int parse_probe_event(const char *str) { - struct probe_point *pp = &session.probes[session.nr_probe]; + struct perf_probe_event *pev = ¶ms.events[params.nevents]; + int ret; - pr_debug("probe-definition(%d): %s\n", session.nr_probe, str); - if (++session.nr_probe == MAX_PROBES) + pr_debug("probe-definition(%d): %s\n", params.nevents, str); + if (++params.nevents == MAX_PROBES) die("Too many probes (> %d) are specified.", MAX_PROBES); - /* Parse perf-probe event into probe_point */ - parse_perf_probe_event(str, pp, &session.need_dwarf); + /* Parse a perf-probe command into event */ + ret = parse_perf_probe_command(str, pev); + pr_debug("%d arguments\n", pev->nargs); - pr_debug("%d arguments\n", pp->nr_args); + return ret; } -static void parse_probe_event_argv(int argc, const char **argv) +static int parse_probe_event_argv(int argc, const char **argv) { - int i, len; + int i, len, ret; char *buf; /* Bind up rest arguments */ len = 0; for (i = 0; i < argc; i++) len += strlen(argv[i]) + 1; - buf = zalloc(len + 1); - if (!buf) - die("Failed to allocate memory for binding arguments."); + buf = xzalloc(len + 1); len = 0; for (i = 0; i < argc; i++) len += sprintf(&buf[len], "%s ", argv[i]); - parse_probe_event(buf); + ret = parse_probe_event(buf); free(buf); + return ret; } static int opt_add_probe_event(const struct option *opt __used, const char *str, int unset __used) { if (str) - parse_probe_event(str); - return 0; + return parse_probe_event(str); + else + return 0; } static int opt_del_probe_event(const struct option *opt __used, const char *str, int unset __used) { if (str) { - if (!session.dellist) - session.dellist = strlist__new(true, NULL); - strlist__add(session.dellist, str); + if (!params.dellist) + params.dellist = strlist__new(true, NULL); + strlist__add(params.dellist, str); } return 0; } -/* Currently just checking function name from symbol map */ -static void evaluate_probe_point(struct probe_point *pp) -{ - struct symbol *sym; - sym = map__find_symbol_by_name(session.kmaps[MAP__FUNCTION], - pp->function, NULL); - if (!sym) - die("Kernel symbol \'%s\' not found - probe not added.", - pp->function); -} - -#ifndef NO_DWARF_SUPPORT -static int open_vmlinux(void) -{ - if (map__load(session.kmaps[MAP__FUNCTION], NULL) < 0) { - pr_debug("Failed to load kernel map.\n"); - return -EINVAL; - } - pr_debug("Try to open %s\n", - session.kmaps[MAP__FUNCTION]->dso->long_name); - return open(session.kmaps[MAP__FUNCTION]->dso->long_name, O_RDONLY); -} - +#ifdef DWARF_SUPPORT static int opt_show_lines(const struct option *opt __used, const char *str, int unset __used) { + int ret = 0; + if (str) - parse_line_range_desc(str, &session.line_range); - INIT_LIST_HEAD(&session.line_range.line_list); - session.show_lines = true; - return 0; + ret = parse_line_range_desc(str, ¶ms.line_range); + INIT_LIST_HEAD(¶ms.line_range.line_list); + params.show_lines = true; + + return ret; } #endif @@ -155,29 +132,25 @@ static const char * const probe_usage[] = { "perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]", "perf probe [<options>] --del '[GROUP:]EVENT' ...", "perf probe --list", -#ifndef NO_DWARF_SUPPORT +#ifdef DWARF_SUPPORT "perf probe --line 'LINEDESC'", #endif NULL }; static const struct option options[] = { - OPT_BOOLEAN('v', "verbose", &verbose, + OPT_INCR('v', "verbose", &verbose, "be more verbose (show parsed arguments, etc)"), -#ifndef NO_DWARF_SUPPORT - OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, - "file", "vmlinux pathname"), -#endif - OPT_BOOLEAN('l', "list", &session.list_events, + OPT_BOOLEAN('l', "list", ¶ms.list_events, "list up current probe events"), OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.", opt_del_probe_event), OPT_CALLBACK('a', "add", NULL, -#ifdef NO_DWARF_SUPPORT - "[EVENT=]FUNC[+OFF|%return] [ARG ...]", -#else +#ifdef DWARF_SUPPORT "[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT" - " [ARG ...]", + " [[NAME=]ARG ...]", +#else + "[EVENT=]FUNC[+OFF|%return] [[NAME=]ARG ...]", #endif "probe point definition, where\n" "\t\tGROUP:\tGroup name (optional)\n" @@ -185,51 +158,33 @@ static const struct option options[] = { "\t\tFUNC:\tFunction name\n" "\t\tOFF:\tOffset from function entry (in byte)\n" "\t\t%return:\tPut the probe at function return\n" -#ifdef NO_DWARF_SUPPORT - "\t\tARG:\tProbe argument (only \n" -#else +#ifdef DWARF_SUPPORT "\t\tSRC:\tSource code path\n" "\t\tRL:\tRelative line number from function entry.\n" "\t\tAL:\tAbsolute line number in file.\n" "\t\tPT:\tLazy expression of line code.\n" "\t\tARG:\tProbe argument (local variable name or\n" -#endif "\t\t\tkprobe-tracer argument format.)\n", +#else + "\t\tARG:\tProbe argument (kprobe-tracer argument format.)\n", +#endif opt_add_probe_event), - OPT_BOOLEAN('f', "force", &session.force_add, "forcibly add events" + OPT_BOOLEAN('f', "force", ¶ms.force_add, "forcibly add events" " with existing name"), -#ifndef NO_DWARF_SUPPORT +#ifdef DWARF_SUPPORT OPT_CALLBACK('L', "line", NULL, - "FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]", + "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]", "Show source code lines.", opt_show_lines), + OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, + "file", "vmlinux pathname"), #endif + OPT__DRY_RUN(&probe_event_dry_run), OPT_END() }; -/* Initialize symbol maps for vmlinux */ -static void init_vmlinux(void) -{ - symbol_conf.sort_by_name = true; - if (symbol_conf.vmlinux_name == NULL) - symbol_conf.try_vmlinux_path = true; - else - pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name); - if (symbol__init() < 0) - die("Failed to init symbol map."); - - map_groups__init(&session.kmap_groups); - if (map_groups__create_kernel_maps(&session.kmap_groups, - session.kmaps) < 0) - die("Failed to create kernel maps."); -} - int cmd_probe(int argc, const char **argv, const char *prefix __used) { - int i, ret; -#ifndef NO_DWARF_SUPPORT - int fd; -#endif - struct probe_point *pp; + int ret; argc = parse_options(argc, argv, options, probe_usage, PARSE_OPT_STOP_AT_NON_OPTION); @@ -238,123 +193,65 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used) pr_warning(" Error: '-' is not supported.\n"); usage_with_options(probe_usage, options); } - parse_probe_event_argv(argc, argv); + ret = parse_probe_event_argv(argc, argv); + if (ret < 0) { + pr_err(" Error: Parse Error. (%d)\n", ret); + return ret; + } } - if ((!session.nr_probe && !session.dellist && !session.list_events && - !session.show_lines)) + if ((!params.nevents && !params.dellist && !params.list_events && + !params.show_lines)) usage_with_options(probe_usage, options); - if (debugfs_valid_mountpoint(debugfs_path) < 0) - die("Failed to find debugfs path."); - - if (session.list_events) { - if (session.nr_probe != 0 || session.dellist) { - pr_warning(" Error: Don't use --list with" - " --add/--del.\n"); + if (params.list_events) { + if (params.nevents != 0 || params.dellist) { + pr_err(" Error: Don't use --list with --add/--del.\n"); usage_with_options(probe_usage, options); } - if (session.show_lines) { - pr_warning(" Error: Don't use --list with --line.\n"); + if (params.show_lines) { + pr_err(" Error: Don't use --list with --line.\n"); usage_with_options(probe_usage, options); } - show_perf_probe_events(); - return 0; + ret = show_perf_probe_events(); + if (ret < 0) + pr_err(" Error: Failed to show event list. (%d)\n", + ret); + return ret; } -#ifndef NO_DWARF_SUPPORT - if (session.show_lines) { - if (session.nr_probe != 0 || session.dellist) { +#ifdef DWARF_SUPPORT + if (params.show_lines) { + if (params.nevents != 0 || params.dellist) { pr_warning(" Error: Don't use --line with" " --add/--del.\n"); usage_with_options(probe_usage, options); } - init_vmlinux(); - fd = open_vmlinux(); - if (fd < 0) - die("Could not open debuginfo file."); - ret = find_line_range(fd, &session.line_range); - if (ret <= 0) - die("Source line is not found.\n"); - close(fd); - show_line_range(&session.line_range); - return 0; - } -#endif - if (session.dellist) { - del_trace_kprobe_events(session.dellist); - strlist__delete(session.dellist); - if (session.nr_probe == 0) - return 0; + ret = show_line_range(¶ms.line_range); + if (ret < 0) + pr_err(" Error: Failed to show lines. (%d)\n", ret); + return ret; } +#endif - /* Add probes */ - init_vmlinux(); - - if (session.need_dwarf) -#ifdef NO_DWARF_SUPPORT - die("Debuginfo-analysis is not supported"); -#else /* !NO_DWARF_SUPPORT */ - pr_debug("Some probes require debuginfo.\n"); - - fd = open_vmlinux(); - if (fd < 0) { - if (session.need_dwarf) - die("Could not open debuginfo file."); - - pr_debug("Could not open vmlinux/module file." - " Try to use symbols.\n"); - goto end_dwarf; - } - - /* Searching probe points */ - for (i = 0; i < session.nr_probe; i++) { - pp = &session.probes[i]; - if (pp->found) - continue; - - lseek(fd, SEEK_SET, 0); - ret = find_probe_point(fd, pp); - if (ret > 0) - continue; - if (ret == 0) { /* No error but failed to find probe point. */ - synthesize_perf_probe_point(pp); - die("Probe point '%s' not found. - probe not added.", - pp->probes[0]); - } - /* Error path */ - if (session.need_dwarf) { - if (ret == -ENOENT) - pr_warning("No dwarf info found in the vmlinux - please rebuild with CONFIG_DEBUG_INFO=y.\n"); - die("Could not analyze debuginfo."); + if (params.dellist) { + ret = del_perf_probe_events(params.dellist); + strlist__delete(params.dellist); + if (ret < 0) { + pr_err(" Error: Failed to delete events. (%d)\n", ret); + return ret; } - pr_debug("An error occurred in debuginfo analysis." - " Try to use symbols.\n"); - break; } - close(fd); - -end_dwarf: -#endif /* !NO_DWARF_SUPPORT */ - /* Synthesize probes without dwarf */ - for (i = 0; i < session.nr_probe; i++) { - pp = &session.probes[i]; - if (pp->found) /* This probe is already found. */ - continue; - - evaluate_probe_point(pp); - ret = synthesize_trace_kprobe_event(pp); - if (ret == -E2BIG) - die("probe point definition becomes too long."); - else if (ret < 0) - die("Failed to synthesize a probe point."); + if (params.nevents) { + ret = add_perf_probe_events(params.events, params.nevents, + params.force_add); + if (ret < 0) { + pr_err(" Error: Failed to add events. (%d)\n", ret); + return ret; + } } - - /* Settng up probe points */ - add_trace_kprobe_events(session.probes, session.nr_probe, - session.force_add); return 0; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 3b8b6387c47c..27f992aca8b5 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -15,7 +15,6 @@ #include "util/util.h" #include "util/parse-options.h" #include "util/parse-events.h" -#include "util/string.h" #include "util/header.h" #include "util/event.h" @@ -27,31 +26,41 @@ #include <unistd.h> #include <sched.h> -static int fd[MAX_NR_CPUS][MAX_COUNTERS]; +enum write_mode_t { + WRITE_FORCE, + WRITE_APPEND +}; + +static int *fd[MAX_NR_CPUS][MAX_COUNTERS]; +static unsigned int user_interval = UINT_MAX; static long default_interval = 0; static int nr_cpus = 0; static unsigned int page_size; static unsigned int mmap_pages = 128; +static unsigned int user_freq = UINT_MAX; static int freq = 1000; static int output; +static int pipe_output = 0; static const char *output_name = "perf.data"; static int group = 0; static unsigned int realtime_prio = 0; -static int raw_samples = 0; -static int system_wide = 0; +static bool raw_samples = false; +static bool system_wide = false; static int profile_cpu = -1; static pid_t target_pid = -1; +static pid_t target_tid = -1; +static pid_t *all_tids = NULL; +static int thread_num = 0; static pid_t child_pid = -1; -static int inherit = 1; -static int force = 0; -static int append_file = 0; -static int call_graph = 0; -static int inherit_stat = 0; -static int no_samples = 0; -static int sample_address = 0; -static int multiplex = 0; +static bool inherit = true; +static enum write_mode_t write_mode = WRITE_FORCE; +static bool call_graph = false; +static bool inherit_stat = false; +static bool no_samples = false; +static bool sample_address = false; +static bool multiplex = false; static int multiplex_fd = -1; static long samples = 0; @@ -60,7 +69,7 @@ static struct timeval this_read; static u64 bytes_written = 0; -static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS]; +static struct pollfd *event_array; static int nr_poll = 0; static int nr_cpu = 0; @@ -77,7 +86,7 @@ struct mmap_data { unsigned int prev; }; -static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS]; +static struct mmap_data *mmap_array[MAX_NR_CPUS][MAX_COUNTERS]; static unsigned long mmap_read_head(struct mmap_data *md) { @@ -101,6 +110,11 @@ static void mmap_write_tail(struct mmap_data *md, unsigned long tail) pc->data_tail = tail; } +static void advance_output(size_t size) +{ + bytes_written += size; +} + static void write_output(void *buf, size_t size) { while (size) { @@ -225,12 +239,13 @@ static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int n return h_attr; } -static void create_counter(int counter, int cpu, pid_t pid) +static void create_counter(int counter, int cpu) { char *filter = filters[counter]; struct perf_event_attr *attr = attrs + counter; struct perf_header_attr *h_attr; int track = !counter; /* only the first counter needs these */ + int thread_index; int ret; struct { u64 count; @@ -248,10 +263,19 @@ static void create_counter(int counter, int cpu, pid_t pid) if (nr_counters > 1) attr->sample_type |= PERF_SAMPLE_ID; - if (freq) { - attr->sample_type |= PERF_SAMPLE_PERIOD; - attr->freq = 1; - attr->sample_freq = freq; + /* + * We default some events to a 1 default interval. But keep + * it a weak assumption overridable by the user. + */ + if (!attr->sample_period || (user_freq != UINT_MAX && + user_interval != UINT_MAX)) { + if (freq) { + attr->sample_type |= PERF_SAMPLE_PERIOD; + attr->freq = 1; + attr->sample_freq = freq; + } else { + attr->sample_period = default_interval; + } } if (no_samples) @@ -275,118 +299,129 @@ static void create_counter(int counter, int cpu, pid_t pid) attr->mmap = track; attr->comm = track; attr->inherit = inherit; - attr->disabled = 1; + if (target_pid == -1 && !system_wide) { + attr->disabled = 1; + attr->enable_on_exec = 1; + } + for (thread_index = 0; thread_index < thread_num; thread_index++) { try_again: - fd[nr_cpu][counter] = sys_perf_event_open(attr, pid, cpu, group_fd, 0); - - if (fd[nr_cpu][counter] < 0) { - int err = errno; - - if (err == EPERM || err == EACCES) - die("Permission error - are you root?\n"); - else if (err == ENODEV && profile_cpu != -1) - die("No such device - did you specify an out-of-range profile CPU?\n"); + fd[nr_cpu][counter][thread_index] = sys_perf_event_open(attr, + all_tids[thread_index], cpu, group_fd, 0); + + if (fd[nr_cpu][counter][thread_index] < 0) { + int err = errno; + + if (err == EPERM || err == EACCES) + die("Permission error - are you root?\n" + "\t Consider tweaking" + " /proc/sys/kernel/perf_event_paranoid.\n"); + else if (err == ENODEV && profile_cpu != -1) { + die("No such device - did you specify" + " an out-of-range profile CPU?\n"); + } - /* - * If it's cycles then fall back to hrtimer - * based cpu-clock-tick sw counter, which - * is always available even if no PMU support: - */ - if (attr->type == PERF_TYPE_HARDWARE - && attr->config == PERF_COUNT_HW_CPU_CYCLES) { - - if (verbose) - warning(" ... trying to fall back to cpu-clock-ticks\n"); - attr->type = PERF_TYPE_SOFTWARE; - attr->config = PERF_COUNT_SW_CPU_CLOCK; - goto try_again; - } - printf("\n"); - error("perfcounter syscall returned with %d (%s)\n", - fd[nr_cpu][counter], strerror(err)); + /* + * If it's cycles then fall back to hrtimer + * based cpu-clock-tick sw counter, which + * is always available even if no PMU support: + */ + if (attr->type == PERF_TYPE_HARDWARE + && attr->config == PERF_COUNT_HW_CPU_CYCLES) { + + if (verbose) + warning(" ... trying to fall back to cpu-clock-ticks\n"); + attr->type = PERF_TYPE_SOFTWARE; + attr->config = PERF_COUNT_SW_CPU_CLOCK; + goto try_again; + } + printf("\n"); + error("perfcounter syscall returned with %d (%s)\n", + fd[nr_cpu][counter][thread_index], strerror(err)); #if defined(__i386__) || defined(__x86_64__) - if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP) - die("No hardware sampling interrupt available. No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.\n"); + if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP) + die("No hardware sampling interrupt available." + " No APIC? If so then you can boot the kernel" + " with the \"lapic\" boot parameter to" + " force-enable it.\n"); #endif - die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); - exit(-1); - } + die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); + exit(-1); + } - h_attr = get_header_attr(attr, counter); - if (h_attr == NULL) - die("nomem\n"); + h_attr = get_header_attr(attr, counter); + if (h_attr == NULL) + die("nomem\n"); - if (!file_new) { - if (memcmp(&h_attr->attr, attr, sizeof(*attr))) { - fprintf(stderr, "incompatible append\n"); - exit(-1); + if (!file_new) { + if (memcmp(&h_attr->attr, attr, sizeof(*attr))) { + fprintf(stderr, "incompatible append\n"); + exit(-1); + } } - } - if (read(fd[nr_cpu][counter], &read_data, sizeof(read_data)) == -1) { - perror("Unable to read perf file descriptor\n"); - exit(-1); - } + if (read(fd[nr_cpu][counter][thread_index], &read_data, sizeof(read_data)) == -1) { + perror("Unable to read perf file descriptor\n"); + exit(-1); + } - if (perf_header_attr__add_id(h_attr, read_data.id) < 0) { - pr_warning("Not enough memory to add id\n"); - exit(-1); - } + if (perf_header_attr__add_id(h_attr, read_data.id) < 0) { + pr_warning("Not enough memory to add id\n"); + exit(-1); + } - assert(fd[nr_cpu][counter] >= 0); - fcntl(fd[nr_cpu][counter], F_SETFL, O_NONBLOCK); + assert(fd[nr_cpu][counter][thread_index] >= 0); + fcntl(fd[nr_cpu][counter][thread_index], F_SETFL, O_NONBLOCK); - /* - * First counter acts as the group leader: - */ - if (group && group_fd == -1) - group_fd = fd[nr_cpu][counter]; - if (multiplex && multiplex_fd == -1) - multiplex_fd = fd[nr_cpu][counter]; + /* + * First counter acts as the group leader: + */ + if (group && group_fd == -1) + group_fd = fd[nr_cpu][counter][thread_index]; + if (multiplex && multiplex_fd == -1) + multiplex_fd = fd[nr_cpu][counter][thread_index]; - if (multiplex && fd[nr_cpu][counter] != multiplex_fd) { + if (multiplex && fd[nr_cpu][counter][thread_index] != multiplex_fd) { - ret = ioctl(fd[nr_cpu][counter], PERF_EVENT_IOC_SET_OUTPUT, multiplex_fd); - assert(ret != -1); - } else { - event_array[nr_poll].fd = fd[nr_cpu][counter]; - event_array[nr_poll].events = POLLIN; - nr_poll++; - - mmap_array[nr_cpu][counter].counter = counter; - mmap_array[nr_cpu][counter].prev = 0; - mmap_array[nr_cpu][counter].mask = mmap_pages*page_size - 1; - mmap_array[nr_cpu][counter].base = mmap(NULL, (mmap_pages+1)*page_size, - PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter], 0); - if (mmap_array[nr_cpu][counter].base == MAP_FAILED) { - error("failed to mmap with %d (%s)\n", errno, strerror(errno)); - exit(-1); + ret = ioctl(fd[nr_cpu][counter][thread_index], PERF_EVENT_IOC_SET_OUTPUT, multiplex_fd); + assert(ret != -1); + } else { + event_array[nr_poll].fd = fd[nr_cpu][counter][thread_index]; + event_array[nr_poll].events = POLLIN; + nr_poll++; + + mmap_array[nr_cpu][counter][thread_index].counter = counter; + mmap_array[nr_cpu][counter][thread_index].prev = 0; + mmap_array[nr_cpu][counter][thread_index].mask = mmap_pages*page_size - 1; + mmap_array[nr_cpu][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size, + PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter][thread_index], 0); + if (mmap_array[nr_cpu][counter][thread_index].base == MAP_FAILED) { + error("failed to mmap with %d (%s)\n", errno, strerror(errno)); + exit(-1); + } } - } - if (filter != NULL) { - ret = ioctl(fd[nr_cpu][counter], - PERF_EVENT_IOC_SET_FILTER, filter); - if (ret) { - error("failed to set filter with %d (%s)\n", errno, - strerror(errno)); - exit(-1); + if (filter != NULL) { + ret = ioctl(fd[nr_cpu][counter][thread_index], + PERF_EVENT_IOC_SET_FILTER, filter); + if (ret) { + error("failed to set filter with %d (%s)\n", errno, + strerror(errno)); + exit(-1); + } } } - - ioctl(fd[nr_cpu][counter], PERF_EVENT_IOC_ENABLE); } -static void open_counters(int cpu, pid_t pid) +static void open_counters(int cpu) { int counter; group_fd = -1; for (counter = 0; counter < nr_counters; counter++) - create_counter(counter, cpu, pid); + create_counter(counter, cpu); nr_cpu++; } @@ -406,10 +441,65 @@ static int process_buildids(void) static void atexit_header(void) { - session->header.data_size += bytes_written; + if (!pipe_output) { + session->header.data_size += bytes_written; + + process_buildids(); + perf_header__write(&session->header, output, true); + } else { + int err; + + err = event__synthesize_build_ids(process_synthesized_event, + session); + if (err < 0) + pr_err("Couldn't synthesize build ids.\n"); + } +} + +static void event__synthesize_guest_os(struct kernel_info *kerninfo, + void *data __attribute__((unused))) +{ + int err; + char *guest_kallsyms; + char path[PATH_MAX]; + + if (is_host_kernel(kerninfo)) + return; + + /* + *As for guest kernel when processing subcommand record&report, + *we arrange module mmap prior to guest kernel mmap and trigger + *a preload dso because default guest module symbols are loaded + *from guest kallsyms instead of /lib/modules/XXX/XXX. This + *method is used to avoid symbol missing when the first addr is + *in module instead of in guest kernel. + */ + err = event__synthesize_modules(process_synthesized_event, + session, + kerninfo); + if (err < 0) + pr_err("Couldn't record guest kernel [%d]'s reference" + " relocation symbol.\n", kerninfo->pid); + + if (is_default_guest(kerninfo)) + guest_kallsyms = (char *) symbol_conf.default_guest_kallsyms; + else { + sprintf(path, "%s/proc/kallsyms", kerninfo->root_dir); + guest_kallsyms = path; + } - process_buildids(); - perf_header__write(&session->header, output, true); + /* + * We use _stext for guest kernel because guest kernel's /proc/kallsyms + * have no _text sometimes. + */ + err = event__synthesize_kernel_mmap(process_synthesized_event, + session, kerninfo, "_text"); + if (err < 0) + err = event__synthesize_kernel_mmap(process_synthesized_event, + session, kerninfo, "_stext"); + if (err < 0) + pr_err("Couldn't record guest kernel [%d]'s reference" + " relocation symbol.\n", kerninfo->pid); } static int __cmd_record(int argc, const char **argv) @@ -421,8 +511,9 @@ static int __cmd_record(int argc, const char **argv) int err; unsigned long waking = 0; int child_ready_pipe[2], go_pipe[2]; - const bool forks = target_pid == -1 && argc > 0; + const bool forks = argc > 0; char buf; + struct kernel_info *kerninfo; page_size = sysconf(_SC_PAGE_SIZE); @@ -435,45 +526,44 @@ static int __cmd_record(int argc, const char **argv) exit(-1); } - if (!stat(output_name, &st) && st.st_size) { - if (!force) { - if (!append_file) { - pr_err("Error, output file %s exists, use -A " - "to append or -f to overwrite.\n", - output_name); - exit(-1); - } - } else { + if (!strcmp(output_name, "-")) + pipe_output = 1; + else if (!stat(output_name, &st) && st.st_size) { + if (write_mode == WRITE_FORCE) { char oldname[PATH_MAX]; snprintf(oldname, sizeof(oldname), "%s.old", output_name); unlink(oldname); rename(output_name, oldname); } - } else { - append_file = 0; + } else if (write_mode == WRITE_APPEND) { + write_mode = WRITE_FORCE; } flags = O_CREAT|O_RDWR; - if (append_file) + if (write_mode == WRITE_APPEND) file_new = 0; else flags |= O_TRUNC; - output = open(output_name, flags, S_IRUSR|S_IWUSR); + if (pipe_output) + output = STDOUT_FILENO; + else + output = open(output_name, flags, S_IRUSR | S_IWUSR); if (output < 0) { perror("failed to create output file"); exit(-1); } - session = perf_session__new(output_name, O_WRONLY, force); + session = perf_session__new(output_name, O_WRONLY, + write_mode == WRITE_FORCE); if (session == NULL) { pr_err("Not enough memory for reading perf file header\n"); return -1; } if (!file_new) { - err = perf_header__read(&session->header, output); + err = perf_header__read(session, output); if (err < 0) return err; } @@ -492,13 +582,15 @@ static int __cmd_record(int argc, const char **argv) atexit(atexit_header); if (forks) { - pid = fork(); + child_pid = fork(); if (pid < 0) { perror("failed to fork"); exit(-1); } - if (!pid) { + if (!child_pid) { + if (pipe_output) + dup2(2, 1); close(child_ready_pipe[0]); close(go_pipe[1]); fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC); @@ -527,10 +619,8 @@ static int __cmd_record(int argc, const char **argv) exit(-1); } - child_pid = pid; - - if (!system_wide) - target_pid = pid; + if (!system_wide && target_tid == -1 && target_pid == -1) + all_tids[0] = child_pid; close(child_ready_pipe[1]); close(go_pipe[0]); @@ -544,16 +634,19 @@ static int __cmd_record(int argc, const char **argv) close(child_ready_pipe[0]); } - if ((!system_wide && !inherit) || profile_cpu != -1) { - open_counters(profile_cpu, target_pid); + open_counters(profile_cpu); } else { nr_cpus = read_cpu_map(); for (i = 0; i < nr_cpus; i++) - open_counters(cpumap[i], target_pid); + open_counters(cpumap[i]); } - if (file_new) { + if (pipe_output) { + err = perf_header__write_pipe(output); + if (err < 0) + return err; + } else if (file_new) { err = perf_header__write(&session->header, output, false); if (err < 0) return err; @@ -561,21 +654,62 @@ static int __cmd_record(int argc, const char **argv) post_processing_offset = lseek(output, 0, SEEK_CUR); + if (pipe_output) { + err = event__synthesize_attrs(&session->header, + process_synthesized_event, + session); + if (err < 0) { + pr_err("Couldn't synthesize attrs.\n"); + return err; + } + + err = event__synthesize_event_types(process_synthesized_event, + session); + if (err < 0) { + pr_err("Couldn't synthesize event_types.\n"); + return err; + } + + err = event__synthesize_tracing_data(output, attrs, + nr_counters, + process_synthesized_event, + session); + if (err <= 0) { + pr_err("Couldn't record tracing data.\n"); + return err; + } + + advance_output(err); + } + + kerninfo = kerninfo__findhost(&session->kerninfo_root); + if (!kerninfo) { + pr_err("Couldn't find native kernel information.\n"); + return -1; + } + err = event__synthesize_kernel_mmap(process_synthesized_event, - session, "_text"); + session, kerninfo, "_text"); + if (err < 0) + err = event__synthesize_kernel_mmap(process_synthesized_event, + session, kerninfo, "_stext"); if (err < 0) { pr_err("Couldn't record kernel reference relocation symbol.\n"); return err; } - err = event__synthesize_modules(process_synthesized_event, session); + err = event__synthesize_modules(process_synthesized_event, + session, kerninfo); if (err < 0) { pr_err("Couldn't record kernel reference relocation symbol.\n"); return err; } + if (perf_guest) + kerninfo__process_allkernels(&session->kerninfo_root, + event__synthesize_guest_os, session); if (!system_wide && profile_cpu == -1) - event__synthesize_thread(target_pid, process_synthesized_event, + event__synthesize_thread(target_tid, process_synthesized_event, session); else event__synthesize_threads(process_synthesized_event, session); @@ -598,11 +732,16 @@ static int __cmd_record(int argc, const char **argv) for (;;) { int hits = samples; + int thread; for (i = 0; i < nr_cpu; i++) { for (counter = 0; counter < nr_counters; counter++) { - if (mmap_array[i][counter].base) - mmap_read(&mmap_array[i][counter]); + for (thread = 0; + thread < thread_num; thread++) { + if (mmap_array[i][counter][thread].base) + mmap_read(&mmap_array[i][counter][thread]); + } + } } @@ -615,8 +754,15 @@ static int __cmd_record(int argc, const char **argv) if (done) { for (i = 0; i < nr_cpu; i++) { - for (counter = 0; counter < nr_counters; counter++) - ioctl(fd[i][counter], PERF_EVENT_IOC_DISABLE); + for (counter = 0; + counter < nr_counters; + counter++) { + for (thread = 0; + thread < thread_num; + thread++) + ioctl(fd[i][counter][thread], + PERF_EVENT_IOC_DISABLE); + } } } } @@ -641,6 +787,8 @@ static const char * const record_usage[] = { NULL }; +static bool force, append_file; + static const struct option options[] = { OPT_CALLBACK('e', "event", NULL, "event", "event selector. use 'perf list' to list available events", @@ -648,7 +796,9 @@ static const struct option options[] = { OPT_CALLBACK(0, "filter", NULL, "filter", "event filter", parse_filter), OPT_INTEGER('p', "pid", &target_pid, - "record events on existing pid"), + "record events on existing process id"), + OPT_INTEGER('t', "tid", &target_tid, + "record events on existing thread id"), OPT_INTEGER('r', "realtime", &realtime_prio, "collect data with this RT SCHED_FIFO priority"), OPT_BOOLEAN('R', "raw-samples", &raw_samples, @@ -660,20 +810,20 @@ static const struct option options[] = { OPT_INTEGER('C', "profile_cpu", &profile_cpu, "CPU to profile on"), OPT_BOOLEAN('f', "force", &force, - "overwrite existing data file"), - OPT_LONG('c', "count", &default_interval, + "overwrite existing data file (deprecated)"), + OPT_LONG('c', "count", &user_interval, "event period to sample"), OPT_STRING('o', "output", &output_name, "file", "output file name"), OPT_BOOLEAN('i', "inherit", &inherit, "child tasks inherit counters"), - OPT_INTEGER('F', "freq", &freq, + OPT_INTEGER('F', "freq", &user_freq, "profile at this frequency"), OPT_INTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"), OPT_BOOLEAN('g', "call-graph", &call_graph, "do call-graph (stack chain/backtrace) recording"), - OPT_BOOLEAN('v', "verbose", &verbose, + OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_BOOLEAN('s', "stat", &inherit_stat, "per thread counts"), @@ -688,13 +838,24 @@ static const struct option options[] = { int cmd_record(int argc, const char **argv, const char *prefix __used) { - int counter; + int i,j; argc = parse_options(argc, argv, options, record_usage, PARSE_OPT_STOP_AT_NON_OPTION); - if (!argc && target_pid == -1 && !system_wide && profile_cpu == -1) + if (!argc && target_pid == -1 && target_tid == -1 && + !system_wide && profile_cpu == -1) usage_with_options(record_usage, options); + if (force && append_file) { + fprintf(stderr, "Can't overwrite and append at the same time." + " You need to choose between -f and -A"); + usage_with_options(record_usage, options); + } else if (append_file) { + write_mode = WRITE_APPEND; + } else { + write_mode = WRITE_FORCE; + } + symbol__init(); if (!nr_counters) { @@ -703,6 +864,42 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) attrs[0].config = PERF_COUNT_HW_CPU_CYCLES; } + if (target_pid != -1) { + target_tid = target_pid; + thread_num = find_all_tid(target_pid, &all_tids); + if (thread_num <= 0) { + fprintf(stderr, "Can't find all threads of pid %d\n", + target_pid); + usage_with_options(record_usage, options); + } + } else { + all_tids=malloc(sizeof(pid_t)); + if (!all_tids) + return -ENOMEM; + + all_tids[0] = target_tid; + thread_num = 1; + } + + for (i = 0; i < MAX_NR_CPUS; i++) { + for (j = 0; j < MAX_COUNTERS; j++) { + fd[i][j] = malloc(sizeof(int)*thread_num); + mmap_array[i][j] = zalloc( + sizeof(struct mmap_data)*thread_num); + if (!fd[i][j] || !mmap_array[i][j]) + return -ENOMEM; + } + } + event_array = malloc( + sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num); + if (!event_array) + return -ENOMEM; + + if (user_interval != UINT_MAX) + default_interval = user_interval; + if (user_freq != UINT_MAX) + freq = user_freq; + /* * User specified count overrides default frequency. */ @@ -715,12 +912,5 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) exit(EXIT_FAILURE); } - for (counter = 0; counter < nr_counters; counter++) { - if (attrs[counter].sample_period) - continue; - - attrs[counter].sample_period = default_interval; - } - return __cmd_record(argc, argv); } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index f815de25d0fc..816edae7c5b2 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -14,7 +14,6 @@ #include "util/cache.h" #include <linux/rbtree.h> #include "util/symbol.h" -#include "util/string.h" #include "util/callchain.h" #include "util/strlist.h" #include "util/values.h" @@ -33,11 +32,11 @@ static char const *input_name = "perf.data"; -static int force; +static bool force; static bool hide_unresolved; static bool dont_use_callchains; -static int show_threads; +static bool show_threads; static struct perf_read_values show_threads_values; static char default_pretty_printing_style[] = "normal"; @@ -81,15 +80,20 @@ static int perf_session__add_hist_entry(struct perf_session *self, struct addr_location *al, struct sample_data *data) { - struct symbol **syms = NULL, *parent = NULL; + struct map_symbol *syms = NULL; + struct symbol *parent = NULL; bool hit; + int err; struct hist_entry *he; struct event_stat_id *stats; struct perf_event_attr *attr; - if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain) + if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain) { syms = perf_session__resolve_callchain(self, al->thread, data->callchain, &parent); + if (syms == NULL) + return -ENOMEM; + } attr = perf_header__find_attr(data->id, &self->header); if (attr) @@ -104,13 +108,16 @@ static int perf_session__add_hist_entry(struct perf_session *self, return -ENOMEM; if (hit) - he->count += data->period; + __perf_session__add_count(he, al, data->period); if (symbol_conf.use_callchain) { if (!hit) - callchain_init(&he->callchain); - append_chain(&he->callchain, data->callchain, syms); + callchain_init(he->callchain); + err = append_chain(he->callchain, data->callchain, syms); free(syms); + + if (err) + return err; } return 0; @@ -260,13 +267,27 @@ static struct perf_event_ops event_ops = { .fork = event__process_task, .lost = event__process_lost, .read = process_read_event, + .attr = event__process_attr, + .event_type = event__process_event_type, + .tracing_data = event__process_tracing_data, + .build_id = event__process_build_id, }; +extern volatile int session_done; + +static void sig_handler(int sig __attribute__((__unused__))) +{ + session_done = 1; +} + static int __cmd_report(void) { int ret = -EINVAL; struct perf_session *session; struct rb_node *next; + const char *help = "For a higher level overview, try: perf report --sort comm,dso"; + + signal(SIGINT, sig_handler); session = perf_session__new(input_name, O_RDONLY, force); if (session == NULL) @@ -292,39 +313,49 @@ static int __cmd_report(void) perf_session__fprintf(session, stdout); if (verbose > 2) - dsos__fprintf(stdout); + dsos__fprintf(&session->kerninfo_root, stdout); next = rb_first(&session->stats_by_id); while (next) { struct event_stat_id *stats; + u64 nr_hists; stats = rb_entry(next, struct event_stat_id, rb_node); perf_session__collapse_resort(&stats->hists); - perf_session__output_resort(&stats->hists, stats->stats.total); - if (rb_first(&session->stats_by_id) == - rb_last(&session->stats_by_id)) - fprintf(stdout, "# Samples: %Ld\n#\n", - stats->stats.total); - else - fprintf(stdout, "# Samples: %Ld %s\n#\n", - stats->stats.total, - __event_name(stats->type, stats->config)); - - perf_session__fprintf_hists(&stats->hists, NULL, false, stdout, + nr_hists = perf_session__output_resort(&stats->hists, + stats->stats.total); + if (use_browser) + perf_session__browse_hists(&stats->hists, nr_hists, + stats->stats.total, help, + input_name); + else { + if (rb_first(&session->stats_by_id) == + rb_last(&session->stats_by_id)) + fprintf(stdout, "# Samples: %Ld\n#\n", + stats->stats.total); + else + fprintf(stdout, "# Samples: %Ld %s\n#\n", + stats->stats.total, + __event_name(stats->type, stats->config)); + + perf_session__fprintf_hists(&stats->hists, NULL, false, stdout, stats->stats.total); - fprintf(stdout, "\n\n"); + fprintf(stdout, "\n\n"); + } + next = rb_next(&stats->rb_node); } - if (sort_order == default_sort_order && - parent_pattern == default_parent_pattern) - fprintf(stdout, "#\n# (For a higher level overview, try: perf report --sort comm,dso)\n#\n"); + if (!use_browser && sort_order == default_sort_order && + parent_pattern == default_parent_pattern) { + fprintf(stdout, "#\n# (%s)\n#\n", help); - if (show_threads) { - bool raw_printing_style = !strcmp(pretty_printing_style, "raw"); - perf_read_values_display(stdout, &show_threads_values, - raw_printing_style); - perf_read_values_destroy(&show_threads_values); + if (show_threads) { + bool style = !strcmp(pretty_printing_style, "raw"); + perf_read_values_display(stdout, &show_threads_values, + style); + perf_read_values_destroy(&show_threads_values); + } } out_delete: perf_session__delete(session); @@ -400,7 +431,7 @@ static const char * const report_usage[] = { static const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), - OPT_BOOLEAN('v', "verbose", &verbose, + OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), @@ -419,6 +450,8 @@ static const struct option options[] = { "sort by key(s): pid, comm, dso, symbol, parent"), OPT_BOOLEAN('P', "full-paths", &symbol_conf.full_paths, "Don't shorten the pathnames taking into account the cwd"), + OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, + "Show sample percentage for different cpu modes"), OPT_STRING('p', "parent", &parent_pattern, "regex", "regex filter to identify parent, see: '--sort parent'"), OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other, @@ -447,7 +480,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) { argc = parse_options(argc, argv, options, report_usage, 0); - setup_pager(); + if (strcmp(input_name, "-") != 0) + setup_browser(); if (symbol__init() < 0) return -1; @@ -455,7 +489,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) setup_sorting(report_usage, options); if (parent_pattern != default_parent_pattern) { - sort_dimension__add("parent"); + if (sort_dimension__add("parent") < 0) + return -1; sort_parent.elide = 1; } else symbol_conf.exclude_other = false; diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 4f5a03e43444..09ddc8e6d8e1 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -68,10 +68,10 @@ enum sched_event_type { struct sched_atom { enum sched_event_type type; + int specific_wait; u64 timestamp; u64 duration; unsigned long nr; - int specific_wait; sem_t *wait_sem; struct task_desc *wakee; }; @@ -1790,7 +1790,7 @@ static const char * const sched_usage[] = { static const struct option sched_options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), - OPT_BOOLEAN('v', "verbose", &verbose, + OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), @@ -1805,7 +1805,7 @@ static const char * const latency_usage[] = { static const struct option latency_options[] = { OPT_STRING('s', "sort", &sort_order, "key[,key2...]", "sort by key(s): runtime, switch, avg, max"), - OPT_BOOLEAN('v', "verbose", &verbose, + OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_INTEGER('C', "CPU", &profile_cpu, "CPU to profile on"), @@ -1822,7 +1822,7 @@ static const char * const replay_usage[] = { static const struct option replay_options[] = { OPT_INTEGER('r', "repeat", &replay_repeat, "repeat the workload replay N times (-1: infinite)"), - OPT_BOOLEAN('v', "verbose", &verbose, + OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 95db31cff6fd..e619ac89dff5 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -46,6 +46,7 @@ #include "util/debug.h" #include "util/header.h" #include "util/cpumap.h" +#include "util/thread.h" #include <sys/prctl.h> #include <math.h> @@ -66,18 +67,21 @@ static struct perf_event_attr default_attrs[] = { }; -static int system_wide = 0; +static bool system_wide = false; static unsigned int nr_cpus = 0; static int run_idx = 0; static int run_count = 1; -static int inherit = 1; -static int scale = 1; +static bool inherit = true; +static bool scale = true; static pid_t target_pid = -1; +static pid_t target_tid = -1; +static pid_t *all_tids = NULL; +static int thread_num = 0; static pid_t child_pid = -1; -static int null_run = 0; +static bool null_run = false; -static int fd[MAX_NR_CPUS][MAX_COUNTERS]; +static int *fd[MAX_NR_CPUS][MAX_COUNTERS]; static int event_scaled[MAX_COUNTERS]; @@ -140,9 +144,11 @@ struct stats runtime_branches_stats; #define ERR_PERF_OPEN \ "Error: counter %d, sys_perf_event_open() syscall returned with %d (%s)\n" -static void create_perf_stat_counter(int counter, int pid) +static int create_perf_stat_counter(int counter) { struct perf_event_attr *attr = attrs + counter; + int thread; + int ncreated = 0; if (scale) attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | @@ -152,21 +158,33 @@ static void create_perf_stat_counter(int counter, int pid) unsigned int cpu; for (cpu = 0; cpu < nr_cpus; cpu++) { - fd[cpu][counter] = sys_perf_event_open(attr, -1, cpumap[cpu], -1, 0); - if (fd[cpu][counter] < 0 && verbose) - fprintf(stderr, ERR_PERF_OPEN, counter, - fd[cpu][counter], strerror(errno)); + fd[cpu][counter][0] = sys_perf_event_open(attr, + -1, cpumap[cpu], -1, 0); + if (fd[cpu][counter][0] < 0) + pr_debug(ERR_PERF_OPEN, counter, + fd[cpu][counter][0], strerror(errno)); + else + ++ncreated; } } else { attr->inherit = inherit; - attr->disabled = 1; - attr->enable_on_exec = 1; - - fd[0][counter] = sys_perf_event_open(attr, pid, -1, -1, 0); - if (fd[0][counter] < 0 && verbose) - fprintf(stderr, ERR_PERF_OPEN, counter, - fd[0][counter], strerror(errno)); + if (target_pid == -1) { + attr->disabled = 1; + attr->enable_on_exec = 1; + } + for (thread = 0; thread < thread_num; thread++) { + fd[0][counter][thread] = sys_perf_event_open(attr, + all_tids[thread], -1, -1, 0); + if (fd[0][counter][thread] < 0) + pr_debug(ERR_PERF_OPEN, counter, + fd[0][counter][thread], + strerror(errno)); + else + ++ncreated; + } } + + return ncreated; } /* @@ -190,25 +208,28 @@ static void read_counter(int counter) unsigned int cpu; size_t res, nv; int scaled; - int i; + int i, thread; count[0] = count[1] = count[2] = 0; nv = scale ? 3 : 1; for (cpu = 0; cpu < nr_cpus; cpu++) { - if (fd[cpu][counter] < 0) - continue; - - res = read(fd[cpu][counter], single_count, nv * sizeof(u64)); - assert(res == nv * sizeof(u64)); - - close(fd[cpu][counter]); - fd[cpu][counter] = -1; - - count[0] += single_count[0]; - if (scale) { - count[1] += single_count[1]; - count[2] += single_count[2]; + for (thread = 0; thread < thread_num; thread++) { + if (fd[cpu][counter][thread] < 0) + continue; + + res = read(fd[cpu][counter][thread], + single_count, nv * sizeof(u64)); + assert(res == nv * sizeof(u64)); + + close(fd[cpu][counter][thread]); + fd[cpu][counter][thread] = -1; + + count[0] += single_count[0]; + if (scale) { + count[1] += single_count[1]; + count[2] += single_count[2]; + } } } @@ -250,10 +271,9 @@ static int run_perf_stat(int argc __used, const char **argv) { unsigned long long t0, t1; int status = 0; - int counter; - int pid = target_pid; + int counter, ncreated = 0; int child_ready_pipe[2], go_pipe[2]; - const bool forks = (target_pid == -1 && argc > 0); + const bool forks = (argc > 0); char buf; if (!system_wide) @@ -265,10 +285,10 @@ static int run_perf_stat(int argc __used, const char **argv) } if (forks) { - if ((pid = fork()) < 0) + if ((child_pid = fork()) < 0) perror("failed to fork"); - if (!pid) { + if (!child_pid) { close(child_ready_pipe[0]); close(go_pipe[1]); fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC); @@ -297,7 +317,8 @@ static int run_perf_stat(int argc __used, const char **argv) exit(-1); } - child_pid = pid; + if (target_tid == -1 && target_pid == -1 && !system_wide) + all_tids[0] = child_pid; /* * Wait for the child to be ready to exec. @@ -310,7 +331,16 @@ static int run_perf_stat(int argc __used, const char **argv) } for (counter = 0; counter < nr_counters; counter++) - create_perf_stat_counter(counter, pid); + ncreated += create_perf_stat_counter(counter); + + if (ncreated == 0) { + pr_err("No permission to collect %sstats.\n" + "Consider tweaking /proc/sys/kernel/perf_event_paranoid.\n", + system_wide ? "system-wide " : ""); + if (child_pid != -1) + kill(child_pid, SIGTERM); + return -1; + } /* * Enable counters and exec the command: @@ -321,7 +351,7 @@ static int run_perf_stat(int argc __used, const char **argv) close(go_pipe[1]); wait(&status); } else { - while(!done); + while(!done) sleep(1); } t1 = rdclock(); @@ -429,12 +459,14 @@ static void print_stat(int argc, const char **argv) fprintf(stderr, "\n"); fprintf(stderr, " Performance counter stats for "); - if(target_pid == -1) { + if(target_pid == -1 && target_tid == -1) { fprintf(stderr, "\'%s", argv[0]); for (i = 1; i < argc; i++) fprintf(stderr, " %s", argv[i]); - }else - fprintf(stderr, "task pid \'%d", target_pid); + } else if (target_pid != -1) + fprintf(stderr, "process id \'%d", target_pid); + else + fprintf(stderr, "thread id \'%d", target_tid); fprintf(stderr, "\'"); if (run_count > 1) @@ -459,7 +491,7 @@ static volatile int signr = -1; static void skip_signal(int signo) { - if(target_pid != -1) + if(child_pid == -1) done = 1; signr = signo; @@ -489,12 +521,14 @@ static const struct option options[] = { OPT_BOOLEAN('i', "inherit", &inherit, "child tasks inherit counters"), OPT_INTEGER('p', "pid", &target_pid, - "stat events on existing pid"), + "stat events on existing process id"), + OPT_INTEGER('t', "tid", &target_tid, + "stat events on existing thread id"), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_BOOLEAN('c', "scale", &scale, "scale/normalize counters"), - OPT_BOOLEAN('v', "verbose", &verbose, + OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_INTEGER('r', "repeat", &run_count, "repeat command and print average + stddev (max: 100)"), @@ -506,10 +540,11 @@ static const struct option options[] = { int cmd_stat(int argc, const char **argv, const char *prefix __used) { int status; + int i,j; argc = parse_options(argc, argv, options, stat_usage, PARSE_OPT_STOP_AT_NON_OPTION); - if (!argc && target_pid == -1) + if (!argc && target_pid == -1 && target_tid == -1) usage_with_options(stat_usage, options); if (run_count <= 0) usage_with_options(stat_usage, options); @@ -525,6 +560,31 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) else nr_cpus = 1; + if (target_pid != -1) { + target_tid = target_pid; + thread_num = find_all_tid(target_pid, &all_tids); + if (thread_num <= 0) { + fprintf(stderr, "Can't find all threads of pid %d\n", + target_pid); + usage_with_options(stat_usage, options); + } + } else { + all_tids=malloc(sizeof(pid_t)); + if (!all_tids) + return -ENOMEM; + + all_tids[0] = target_tid; + thread_num = 1; + } + + for (i = 0; i < MAX_NR_CPUS; i++) { + for (j = 0; j < MAX_COUNTERS; j++) { + fd[i][j] = malloc(sizeof(int)*thread_num); + if (!fd[i][j]) + return -ENOMEM; + } + } + /* * We dont want to block the signals - that would cause * child tasks to inherit that and Ctrl-C would not work. @@ -543,7 +603,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) status = run_perf_stat(argc, argv); } - print_stat(argc, argv); + if (status != -1) + print_stat(argc, argv); return status; } diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 0d4d8ff7914b..96f4a092df37 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -21,7 +21,6 @@ #include "util/cache.h" #include <linux/rbtree.h> #include "util/symbol.h" -#include "util/string.h" #include "util/callchain.h" #include "util/strlist.h" @@ -43,7 +42,7 @@ static u64 turbo_frequency; static u64 first_time, last_time; -static int power_only; +static bool power_only; struct per_pid; @@ -78,8 +77,6 @@ struct per_pid { struct per_pidcomm *all; struct per_pidcomm *current; - - int painted; }; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 1f529321607e..dfd7ea7dabdd 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -55,9 +55,9 @@ #include <linux/unistd.h> #include <linux/types.h> -static int fd[MAX_NR_CPUS][MAX_COUNTERS]; +static int *fd[MAX_NR_CPUS][MAX_COUNTERS]; -static int system_wide = 0; +static bool system_wide = false; static int default_interval = 0; @@ -65,18 +65,21 @@ static int count_filter = 5; static int print_entries; static int target_pid = -1; -static int inherit = 0; +static int target_tid = -1; +static pid_t *all_tids = NULL; +static int thread_num = 0; +static bool inherit = false; static int profile_cpu = -1; static int nr_cpus = 0; static unsigned int realtime_prio = 0; -static int group = 0; +static bool group = false; static unsigned int page_size; static unsigned int mmap_pages = 16; static int freq = 1000; /* 1 KHz */ static int delay_secs = 2; -static int zero = 0; -static int dump_symtab = 0; +static bool zero = false; +static bool dump_symtab = false; static bool hide_kernel_symbols = false; static bool hide_user_symbols = false; @@ -133,7 +136,7 @@ static inline struct symbol *sym_entry__symbol(struct sym_entry *self) return ((void *)self) + symbol_conf.priv_size; } -static void get_term_dimensions(struct winsize *ws) +void get_term_dimensions(struct winsize *ws) { char *s = getenv("LINES"); @@ -169,7 +172,7 @@ static void sig_winch_handler(int sig __used) update_print_entries(&winsize); } -static void parse_source(struct sym_entry *syme) +static int parse_source(struct sym_entry *syme) { struct symbol *sym; struct sym_entry_source *source; @@ -180,12 +183,21 @@ static void parse_source(struct sym_entry *syme) u64 len; if (!syme) - return; + return -1; + + sym = sym_entry__symbol(syme); + map = syme->map; + + /* + * We can't annotate with just /proc/kallsyms + */ + if (map->dso->origin == DSO__ORIG_KERNEL) + return -1; if (syme->src == NULL) { syme->src = zalloc(sizeof(*source)); if (syme->src == NULL) - return; + return -1; pthread_mutex_init(&syme->src->lock, NULL); } @@ -195,9 +207,6 @@ static void parse_source(struct sym_entry *syme) pthread_mutex_lock(&source->lock); goto out_assign; } - - sym = sym_entry__symbol(syme); - map = syme->map; path = map->dso->long_name; len = sym->end - sym->start; @@ -209,7 +218,7 @@ static void parse_source(struct sym_entry *syme) file = popen(command, "r"); if (!file) - return; + return -1; pthread_mutex_lock(&source->lock); source->lines_tail = &source->lines; @@ -245,6 +254,7 @@ static void parse_source(struct sym_entry *syme) out_assign: sym_filter_entry = syme; pthread_mutex_unlock(&source->lock); + return 0; } static void __zero_source_counters(struct sym_entry *syme) @@ -410,7 +420,9 @@ static double sym_weight(const struct sym_entry *sym) } static long samples; -static long userspace_samples; +static long kernel_samples, us_samples; +static long exact_samples; +static long guest_us_samples, guest_kernel_samples; static const char CONSOLE_CLEAR[] = "[H[2J"; static void __list_insert_active_sym(struct sym_entry *syme) @@ -450,7 +462,11 @@ static void print_sym_table(void) int printed = 0, j; int counter, snap = !display_weighted ? sym_counter : 0; float samples_per_sec = samples/delay_secs; - float ksamples_per_sec = (samples-userspace_samples)/delay_secs; + float ksamples_per_sec = kernel_samples/delay_secs; + float us_samples_per_sec = (us_samples)/delay_secs; + float guest_kernel_samples_per_sec = (guest_kernel_samples)/delay_secs; + float guest_us_samples_per_sec = (guest_us_samples)/delay_secs; + float esamples_percent = (100.0*exact_samples)/samples; float sum_ksamples = 0.0; struct sym_entry *syme, *n; struct rb_root tmp = RB_ROOT; @@ -458,7 +474,8 @@ static void print_sym_table(void) int sym_width = 0, dso_width = 0, dso_short_width = 0; const int win_width = winsize.ws_col - 1; - samples = userspace_samples = 0; + samples = us_samples = kernel_samples = exact_samples = 0; + guest_kernel_samples = guest_us_samples = 0; /* Sort the active symbols */ pthread_mutex_lock(&active_symbols_lock); @@ -489,9 +506,30 @@ static void print_sym_table(void) puts(CONSOLE_CLEAR); printf("%-*.*s\n", win_width, win_width, graph_dotted_line); - printf( " PerfTop:%8.0f irqs/sec kernel:%4.1f%% [", - samples_per_sec, - 100.0 - (100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec))); + if (!perf_guest) { + printf(" PerfTop:%8.0f irqs/sec kernel:%4.1f%%" + " exact: %4.1f%% [", + samples_per_sec, + 100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) / + samples_per_sec)), + esamples_percent); + } else { + printf(" PerfTop:%8.0f irqs/sec kernel:%4.1f%% us:%4.1f%%" + " guest kernel:%4.1f%% guest us:%4.1f%%" + " exact: %4.1f%% [", + samples_per_sec, + 100.0 - (100.0 * ((samples_per_sec-ksamples_per_sec) / + samples_per_sec)), + 100.0 - (100.0 * ((samples_per_sec-us_samples_per_sec) / + samples_per_sec)), + 100.0 - (100.0 * ((samples_per_sec - + guest_kernel_samples_per_sec) / + samples_per_sec)), + 100.0 - (100.0 * ((samples_per_sec - + guest_us_samples_per_sec) / + samples_per_sec)), + esamples_percent); + } if (nr_counters == 1 || !display_weighted) { printf("%Ld", (u64)attrs[0].sample_period); @@ -514,13 +552,15 @@ static void print_sym_table(void) if (target_pid != -1) printf(" (target_pid: %d", target_pid); + else if (target_tid != -1) + printf(" (target_tid: %d", target_tid); else printf(" (all"); if (profile_cpu != -1) printf(", cpu: %d)\n", profile_cpu); else { - if (target_pid != -1) + if (target_tid != -1) printf(")\n"); else printf(", %d CPUs)\n", nr_cpus); @@ -582,7 +622,6 @@ static void print_sym_table(void) syme = rb_entry(nd, struct sym_entry, rb_node); sym = sym_entry__symbol(syme); - if (++printed > print_entries || (int)syme->snap_count < count_filter) continue; @@ -746,7 +785,7 @@ static int key_mapped(int c) return 0; } -static void handle_keypress(int c) +static void handle_keypress(struct perf_session *session, int c) { if (!key_mapped(c)) { struct pollfd stdin_poll = { .fd = 0, .events = POLLIN }; @@ -815,7 +854,7 @@ static void handle_keypress(int c) case 'Q': printf("exiting.\n"); if (dump_symtab) - dsos__fprintf(stderr); + dsos__fprintf(&session->kerninfo_root, stderr); exit(0); case 's': prompt_symbol(&sym_filter_entry, "Enter details symbol"); @@ -839,7 +878,7 @@ static void handle_keypress(int c) display_weighted = ~display_weighted; break; case 'z': - zero = ~zero; + zero = !zero; break; default: break; @@ -851,6 +890,7 @@ static void *display_thread(void *arg __used) struct pollfd stdin_poll = { .fd = 0, .events = POLLIN }; struct termios tc, save; int delay_msecs, c; + struct perf_session *session = (struct perf_session *) arg; tcgetattr(0, &save); tc = save; @@ -871,7 +911,7 @@ repeat: c = getc(stdin); tcsetattr(0, TCSAFLUSH, &save); - handle_keypress(c); + handle_keypress(session, c); goto repeat; return NULL; @@ -942,24 +982,49 @@ static void event__process_sample(const event_t *self, u64 ip = self->ip.ip; struct sym_entry *syme; struct addr_location al; + struct kernel_info *kerninfo; u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; ++samples; switch (origin) { case PERF_RECORD_MISC_USER: - ++userspace_samples; + ++us_samples; if (hide_user_symbols) return; + kerninfo = kerninfo__findhost(&session->kerninfo_root); break; case PERF_RECORD_MISC_KERNEL: + ++kernel_samples; if (hide_kernel_symbols) return; + kerninfo = kerninfo__findhost(&session->kerninfo_root); + break; + case PERF_RECORD_MISC_GUEST_KERNEL: + ++guest_kernel_samples; + kerninfo = kerninfo__find(&session->kerninfo_root, + self->ip.pid); break; + case PERF_RECORD_MISC_GUEST_USER: + ++guest_us_samples; + /* + * TODO: we don't process guest user from host side + * except simple counting. + */ + return; default: return; } + if (!kerninfo && perf_guest) { + pr_err("Can't find guest [%d]'s kernel information\n", + self->ip.pid); + return; + } + + if (self->header.misc & PERF_RECORD_MISC_EXACT) + exact_samples++; + if (event__preprocess_sample(self, session, &al, symbol_filter) < 0 || al.filtered) return; @@ -976,7 +1041,7 @@ static void event__process_sample(const event_t *self, * --hide-kernel-symbols, even if the user specifies an * invalid --vmlinux ;-) */ - if (al.map == session->vmlinux_maps[MAP__FUNCTION] && + if (al.map == kerninfo->vmlinux_maps[MAP__FUNCTION] && RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) { pr_err("The %s file can't be used\n", symbol_conf.vmlinux_name); @@ -990,7 +1055,17 @@ static void event__process_sample(const event_t *self, if (sym_filter_entry_sched) { sym_filter_entry = sym_filter_entry_sched; sym_filter_entry_sched = NULL; - parse_source(sym_filter_entry); + if (parse_source(sym_filter_entry) < 0) { + struct symbol *sym = sym_entry__symbol(sym_filter_entry); + + pr_err("Can't annotate %s", sym->name); + if (sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) { + pr_err(": No vmlinux file was found in the path:\n"); + vmlinux_path__fprintf(stderr); + } else + pr_err(".\n"); + exit(1); + } } syme = symbol__priv(al.sym); @@ -1106,16 +1181,21 @@ static void perf_session__mmap_read_counter(struct perf_session *self, md->prev = old; } -static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS]; -static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS]; +static struct pollfd *event_array; +static struct mmap_data *mmap_array[MAX_NR_CPUS][MAX_COUNTERS]; static void perf_session__mmap_read(struct perf_session *self) { - int i, counter; + int i, counter, thread_index; for (i = 0; i < nr_cpus; i++) { for (counter = 0; counter < nr_counters; counter++) - perf_session__mmap_read_counter(self, &mmap_array[i][counter]); + for (thread_index = 0; + thread_index < thread_num; + thread_index++) { + perf_session__mmap_read_counter(self, + &mmap_array[i][counter][thread_index]); + } } } @@ -1126,9 +1206,10 @@ static void start_counter(int i, int counter) { struct perf_event_attr *attr; int cpu; + int thread_index; cpu = profile_cpu; - if (target_pid == -1 && profile_cpu == -1) + if (target_tid == -1 && profile_cpu == -1) cpu = cpumap[i]; attr = attrs + counter; @@ -1144,55 +1225,58 @@ static void start_counter(int i, int counter) attr->inherit = (cpu < 0) && inherit; attr->mmap = 1; + for (thread_index = 0; thread_index < thread_num; thread_index++) { try_again: - fd[i][counter] = sys_perf_event_open(attr, target_pid, cpu, group_fd, 0); - - if (fd[i][counter] < 0) { - int err = errno; + fd[i][counter][thread_index] = sys_perf_event_open(attr, + all_tids[thread_index], cpu, group_fd, 0); + + if (fd[i][counter][thread_index] < 0) { + int err = errno; + + if (err == EPERM || err == EACCES) + die("No permission - are you root?\n"); + /* + * If it's cycles then fall back to hrtimer + * based cpu-clock-tick sw counter, which + * is always available even if no PMU support: + */ + if (attr->type == PERF_TYPE_HARDWARE + && attr->config == PERF_COUNT_HW_CPU_CYCLES) { + + if (verbose) + warning(" ... trying to fall back to cpu-clock-ticks\n"); + + attr->type = PERF_TYPE_SOFTWARE; + attr->config = PERF_COUNT_SW_CPU_CLOCK; + goto try_again; + } + printf("\n"); + error("perfcounter syscall returned with %d (%s)\n", + fd[i][counter][thread_index], strerror(err)); + die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); + exit(-1); + } + assert(fd[i][counter][thread_index] >= 0); + fcntl(fd[i][counter][thread_index], F_SETFL, O_NONBLOCK); - if (err == EPERM || err == EACCES) - die("No permission - are you root?\n"); /* - * If it's cycles then fall back to hrtimer - * based cpu-clock-tick sw counter, which - * is always available even if no PMU support: + * First counter acts as the group leader: */ - if (attr->type == PERF_TYPE_HARDWARE - && attr->config == PERF_COUNT_HW_CPU_CYCLES) { - - if (verbose) - warning(" ... trying to fall back to cpu-clock-ticks\n"); - - attr->type = PERF_TYPE_SOFTWARE; - attr->config = PERF_COUNT_SW_CPU_CLOCK; - goto try_again; - } - printf("\n"); - error("perfcounter syscall returned with %d (%s)\n", - fd[i][counter], strerror(err)); - die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); - exit(-1); + if (group && group_fd == -1) + group_fd = fd[i][counter][thread_index]; + + event_array[nr_poll].fd = fd[i][counter][thread_index]; + event_array[nr_poll].events = POLLIN; + nr_poll++; + + mmap_array[i][counter][thread_index].counter = counter; + mmap_array[i][counter][thread_index].prev = 0; + mmap_array[i][counter][thread_index].mask = mmap_pages*page_size - 1; + mmap_array[i][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size, + PROT_READ, MAP_SHARED, fd[i][counter][thread_index], 0); + if (mmap_array[i][counter][thread_index].base == MAP_FAILED) + die("failed to mmap with %d (%s)\n", errno, strerror(errno)); } - assert(fd[i][counter] >= 0); - fcntl(fd[i][counter], F_SETFL, O_NONBLOCK); - - /* - * First counter acts as the group leader: - */ - if (group && group_fd == -1) - group_fd = fd[i][counter]; - - event_array[nr_poll].fd = fd[i][counter]; - event_array[nr_poll].events = POLLIN; - nr_poll++; - - mmap_array[i][counter].counter = counter; - mmap_array[i][counter].prev = 0; - mmap_array[i][counter].mask = mmap_pages*page_size - 1; - mmap_array[i][counter].base = mmap(NULL, (mmap_pages+1)*page_size, - PROT_READ, MAP_SHARED, fd[i][counter], 0); - if (mmap_array[i][counter].base == MAP_FAILED) - die("failed to mmap with %d (%s)\n", errno, strerror(errno)); } static int __cmd_top(void) @@ -1208,8 +1292,8 @@ static int __cmd_top(void) if (session == NULL) return -ENOMEM; - if (target_pid != -1) - event__synthesize_thread(target_pid, event__process, session); + if (target_tid != -1) + event__synthesize_thread(target_tid, event__process, session); else event__synthesize_threads(event__process, session); @@ -1220,11 +1304,11 @@ static int __cmd_top(void) } /* Wait for a minimal set of events before starting the snapshot */ - poll(event_array, nr_poll, 100); + poll(&event_array[0], nr_poll, 100); perf_session__mmap_read(session); - if (pthread_create(&thread, NULL, display_thread, NULL)) { + if (pthread_create(&thread, NULL, display_thread, session)) { printf("Could not create display thread.\n"); exit(-1); } @@ -1263,7 +1347,9 @@ static const struct option options[] = { OPT_INTEGER('c', "count", &default_interval, "event period to sample"), OPT_INTEGER('p', "pid", &target_pid, - "profile events on existing pid"), + "profile events on existing process id"), + OPT_INTEGER('t', "tid", &target_tid, + "profile events on existing thread id"), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_INTEGER('C', "CPU", &profile_cpu, @@ -1296,7 +1382,7 @@ static const struct option options[] = { "display this many functions"), OPT_BOOLEAN('U', "hide_user_symbols", &hide_user_symbols, "hide user symbols"), - OPT_BOOLEAN('v', "verbose", &verbose, + OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_END() }; @@ -1304,6 +1390,7 @@ static const struct option options[] = { int cmd_top(int argc, const char **argv, const char *prefix __used) { int counter; + int i,j; page_size = sysconf(_SC_PAGE_SIZE); @@ -1311,8 +1398,39 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) if (argc) usage_with_options(top_usage, options); + if (target_pid != -1) { + target_tid = target_pid; + thread_num = find_all_tid(target_pid, &all_tids); + if (thread_num <= 0) { + fprintf(stderr, "Can't find all threads of pid %d\n", + target_pid); + usage_with_options(top_usage, options); + } + } else { + all_tids=malloc(sizeof(pid_t)); + if (!all_tids) + return -ENOMEM; + + all_tids[0] = target_tid; + thread_num = 1; + } + + for (i = 0; i < MAX_NR_CPUS; i++) { + for (j = 0; j < MAX_COUNTERS; j++) { + fd[i][j] = malloc(sizeof(int)*thread_num); + mmap_array[i][j] = zalloc( + sizeof(struct mmap_data)*thread_num); + if (!fd[i][j] || !mmap_array[i][j]) + return -ENOMEM; + } + } + event_array = malloc( + sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num); + if (!event_array) + return -ENOMEM; + /* CPU and PID are mutually exclusive */ - if (target_pid != -1 && profile_cpu != -1) { + if (target_tid > 0 && profile_cpu != -1) { printf("WARNING: PID switch overriding CPU\n"); sleep(1); profile_cpu = -1; @@ -1353,7 +1471,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) attrs[counter].sample_period = default_interval; } - if (target_pid != -1 || profile_cpu != -1) + if (target_tid != -1 || profile_cpu != -1) nr_cpus = 1; else nr_cpus = read_cpu_map(); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 407041d20de0..2eefb33c9679 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -104,10 +104,23 @@ static int process_sample_event(event_t *event, struct perf_session *session) static struct perf_event_ops event_ops = { .sample = process_sample_event, .comm = event__process_comm, + .attr = event__process_attr, + .event_type = event__process_event_type, + .tracing_data = event__process_tracing_data, + .build_id = event__process_build_id, }; +extern volatile int session_done; + +static void sig_handler(int sig __unused) +{ + session_done = 1; +} + static int __cmd_trace(struct perf_session *session) { + signal(SIGINT, sig_handler); + return perf_session__process_events(session, &event_ops); } @@ -505,7 +518,7 @@ static const char * const trace_usage[] = { static const struct option options[] = { OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), - OPT_BOOLEAN('v', "verbose", &verbose, + OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('L', "Latency", &latency_format, "show latency attributes (irqs/preemption disabled, etc)"), @@ -548,6 +561,65 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used) suffix = REPORT_SUFFIX; } + if (!suffix && argc >= 2 && strncmp(argv[1], "-", strlen("-")) != 0) { + char *record_script_path, *report_script_path; + int live_pipe[2]; + pid_t pid; + + record_script_path = get_script_path(argv[1], RECORD_SUFFIX); + if (!record_script_path) { + fprintf(stderr, "record script not found\n"); + return -1; + } + + report_script_path = get_script_path(argv[1], REPORT_SUFFIX); + if (!report_script_path) { + fprintf(stderr, "report script not found\n"); + return -1; + } + + if (pipe(live_pipe) < 0) { + perror("failed to create pipe"); + exit(-1); + } + + pid = fork(); + if (pid < 0) { + perror("failed to fork"); + exit(-1); + } + + if (!pid) { + dup2(live_pipe[1], 1); + close(live_pipe[0]); + + __argv = malloc(5 * sizeof(const char *)); + __argv[0] = "/bin/sh"; + __argv[1] = record_script_path; + __argv[2] = "-o"; + __argv[3] = "-"; + __argv[4] = NULL; + + execvp("/bin/sh", (char **)__argv); + exit(-1); + } + + dup2(live_pipe[0], 0); + close(live_pipe[1]); + + __argv = malloc((argc + 3) * sizeof(const char *)); + __argv[0] = "/bin/sh"; + __argv[1] = report_script_path; + for (i = 2; i < argc; i++) + __argv[i] = argv[i]; + __argv[i++] = "-i"; + __argv[i++] = "-"; + __argv[i++] = NULL; + + execvp("/bin/sh", (char **)__argv); + exit(-1); + } + if (suffix) { script_path = get_script_path(argv[2], suffix); if (!script_path) { @@ -580,7 +652,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used) if (session == NULL) return -ENOMEM; - if (!perf_session__has_traces(session, "record -R")) + if (strcmp(input_name, "-") && + !perf_session__has_traces(session, "record -R")) return -EINVAL; if (generate_script_lang) { diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index 10fe49e7048a..ab28bca92e52 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -32,5 +32,6 @@ extern int cmd_version(int argc, const char **argv, const char *prefix); extern int cmd_probe(int argc, const char **argv, const char *prefix); extern int cmd_kmem(int argc, const char **argv, const char *prefix); extern int cmd_lock(int argc, const char **argv, const char *prefix); +extern int cmd_kvm(int argc, const char **argv, const char *prefix); #endif diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index db6ee94d4a8e..2a1162d413a8 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -19,3 +19,4 @@ perf-trace mainporcelain common perf-probe mainporcelain common perf-kmem mainporcelain common perf-lock mainporcelain common +perf-kvm mainporcelain common diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh index 910468e6e01c..2e7a4f417e20 100644 --- a/tools/perf/perf-archive.sh +++ b/tools/perf/perf-archive.sh @@ -30,4 +30,7 @@ done tar cfj $PERF_DATA.tar.bz2 -C $DEBUGDIR -T $MANIFEST rm -f $MANIFEST $BUILDIDS +echo -e "Now please run:\n" +echo -e "$ tar xvf $PERF_DATA.tar.bz2 -C ~/.debug\n" +echo "wherever you need to run 'perf report' on." exit 0 diff --git a/tools/perf/perf.c b/tools/perf/perf.c index cd32c200cdb3..985cdb4bd005 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -13,9 +13,10 @@ #include "util/quote.h" #include "util/run-command.h" #include "util/parse-events.h" -#include "util/string.h" #include "util/debugfs.h" +bool use_browser; + const char perf_usage_string[] = "perf [--version] [--help] COMMAND [ARGS]"; @@ -262,6 +263,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) set_debugfs_path(); status = p->fn(argc, argv, prefix); + exit_browser(status); + if (status) return status & 0xff; @@ -304,6 +307,7 @@ static void handle_internal_command(int argc, const char **argv) { "probe", cmd_probe, 0 }, { "kmem", cmd_kmem, 0 }, { "lock", cmd_lock, 0 }, + { "kvm", cmd_kvm, 0 }, }; unsigned int i; static const char ext[] = STRIP_EXTENSION; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 6fb379bc1d1f..02821febb704 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -1,6 +1,10 @@ #ifndef _PERF_PERF_H #define _PERF_PERF_H +struct winsize; + +void get_term_dimensions(struct winsize *ws); + #if defined(__i386__) #include "../../arch/x86/include/asm/unistd.h" #define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") @@ -102,8 +106,6 @@ static inline unsigned long long rdclock(void) #define __user #define asmlinkage -#define __used __attribute__((__unused__)) - #define unlikely(x) __builtin_expect(!!(x), 0) #define min(x, y) ({ \ typeof(x) _min1 = (x); \ @@ -129,4 +131,6 @@ struct ip_callchain { u64 ips[0]; }; +extern int perf_host, perf_guest; + #endif diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm index f869c48dc9b0..d94b40c8ac85 100644 --- a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm +++ b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm @@ -15,6 +15,7 @@ our @EXPORT_OK = ( @{ $EXPORT_TAGS{'all'} } ); our @EXPORT = qw( avg nsecs nsecs_secs nsecs_nsecs nsecs_usecs print_nsecs +clear_term ); our $VERSION = '0.01'; @@ -55,6 +56,11 @@ sub nsecs_str { return $str; } +sub clear_term +{ + print "\x1b[H\x1b[2J"; +} + 1; __END__ =head1 NAME diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-record b/tools/perf/scripts/perl/bin/failed-syscalls-record index f8885d389e6f..6ad9b8f5f009 100644 --- a/tools/perf/scripts/perl/bin/failed-syscalls-record +++ b/tools/perf/scripts/perl/bin/failed-syscalls-record @@ -1,2 +1,2 @@ #!/bin/bash -perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit +perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit $@ diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-report b/tools/perf/scripts/perl/bin/failed-syscalls-report index 8bfc660e5056..f6346082a8fc 100644 --- a/tools/perf/scripts/perl/bin/failed-syscalls-report +++ b/tools/perf/scripts/perl/bin/failed-syscalls-report @@ -1,4 +1,10 @@ #!/bin/bash # description: system-wide failed syscalls # args: [comm] -perf trace -s ~/libexec/perf-core/scripts/perl/failed-syscalls.pl $1 +if [ $# -gt 0 ] ; then + if ! expr match "$1" "-" ; then + comm=$1 + shift + fi +fi +perf trace $@ -s ~/libexec/perf-core/scripts/perl/failed-syscalls.pl $comm diff --git a/tools/perf/scripts/perl/bin/rw-by-file-record b/tools/perf/scripts/perl/bin/rw-by-file-record index b25056ebf963..a828679837a8 100644 --- a/tools/perf/scripts/perl/bin/rw-by-file-record +++ b/tools/perf/scripts/perl/bin/rw-by-file-record @@ -1,2 +1,3 @@ #!/bin/bash -perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_enter_write +perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@ + diff --git a/tools/perf/scripts/perl/bin/rw-by-file-report b/tools/perf/scripts/perl/bin/rw-by-file-report index eddb9ccce6a5..d83070b7eeb5 100644 --- a/tools/perf/scripts/perl/bin/rw-by-file-report +++ b/tools/perf/scripts/perl/bin/rw-by-file-report @@ -1,7 +1,13 @@ #!/bin/bash # description: r/w activity for a program, by file # args: <comm> -perf trace -s ~/libexec/perf-core/scripts/perl/rw-by-file.pl $1 +if [ $# -lt 1 ] ; then + echo "usage: rw-by-file <comm>" + exit +fi +comm=$1 +shift +perf trace $@ -s ~/libexec/perf-core/scripts/perl/rw-by-file.pl $comm diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-record b/tools/perf/scripts/perl/bin/rw-by-pid-record index 8903979c5b6c..63976bf11e8b 100644 --- a/tools/perf/scripts/perl/bin/rw-by-pid-record +++ b/tools/perf/scripts/perl/bin/rw-by-pid-record @@ -1,2 +1,2 @@ #!/bin/bash -perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write +perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@ diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-report b/tools/perf/scripts/perl/bin/rw-by-pid-report index 7f44c25cc857..7ef46983f62f 100644 --- a/tools/perf/scripts/perl/bin/rw-by-pid-report +++ b/tools/perf/scripts/perl/bin/rw-by-pid-report @@ -1,6 +1,6 @@ #!/bin/bash # description: system-wide r/w activity -perf trace -s ~/libexec/perf-core/scripts/perl/rw-by-pid.pl +perf trace $@ -s ~/libexec/perf-core/scripts/perl/rw-by-pid.pl diff --git a/tools/perf/scripts/perl/bin/rwtop-record b/tools/perf/scripts/perl/bin/rwtop-record new file mode 100644 index 000000000000..63976bf11e8b --- /dev/null +++ b/tools/perf/scripts/perl/bin/rwtop-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@ diff --git a/tools/perf/scripts/perl/bin/rwtop-report b/tools/perf/scripts/perl/bin/rwtop-report new file mode 100644 index 000000000000..93e698cd3f38 --- /dev/null +++ b/tools/perf/scripts/perl/bin/rwtop-report @@ -0,0 +1,23 @@ +#!/bin/bash +# description: system-wide r/w top +# args: [interval] +n_args=0 +for i in "$@" +do + if expr match "$i" "-" > /dev/null ; then + break + fi + n_args=$(( $n_args + 1 )) +done +if [ "$n_args" -gt 1 ] ; then + echo "usage: rwtop-report [interval]" + exit +fi +if [ "$n_args" -gt 0 ] ; then + interval=$1 + shift +fi +perf trace $@ -s ~/libexec/perf-core/scripts/perl/rwtop.pl $interval + + + diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-record b/tools/perf/scripts/perl/bin/wakeup-latency-record index 6abedda911a4..9c0cf588ff8c 100644 --- a/tools/perf/scripts/perl/bin/wakeup-latency-record +++ b/tools/perf/scripts/perl/bin/wakeup-latency-record @@ -1,5 +1,5 @@ #!/bin/bash -perf record -c 1 -f -a -M -R -e sched:sched_switch -e sched:sched_wakeup +perf record -c 1 -f -a -M -R -e sched:sched_switch -e sched:sched_wakeup $@ diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-report b/tools/perf/scripts/perl/bin/wakeup-latency-report index fce3adcb3249..a0d898f9ca1d 100644 --- a/tools/perf/scripts/perl/bin/wakeup-latency-report +++ b/tools/perf/scripts/perl/bin/wakeup-latency-report @@ -1,6 +1,6 @@ #!/bin/bash # description: system-wide min/max/avg wakeup latency -perf trace -s ~/libexec/perf-core/scripts/perl/wakeup-latency.pl +perf trace $@ -s ~/libexec/perf-core/scripts/perl/wakeup-latency.pl diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-record b/tools/perf/scripts/perl/bin/workqueue-stats-record index fce6637b19ba..c2a1a9421133 100644 --- a/tools/perf/scripts/perl/bin/workqueue-stats-record +++ b/tools/perf/scripts/perl/bin/workqueue-stats-record @@ -1,2 +1,2 @@ #!/bin/bash -perf record -c 1 -f -a -M -R -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion +perf record -c 1 -f -a -M -R -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@ diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-report b/tools/perf/scripts/perl/bin/workqueue-stats-report index 71cfbd182fb9..35081132ef97 100644 --- a/tools/perf/scripts/perl/bin/workqueue-stats-report +++ b/tools/perf/scripts/perl/bin/workqueue-stats-report @@ -1,6 +1,6 @@ #!/bin/bash # description: workqueue stats (ins/exe/create/destroy) -perf trace -s ~/libexec/perf-core/scripts/perl/workqueue-stats.pl +perf trace $@ -s ~/libexec/perf-core/scripts/perl/workqueue-stats.pl diff --git a/tools/perf/scripts/perl/rwtop.pl b/tools/perf/scripts/perl/rwtop.pl new file mode 100644 index 000000000000..ec2ab49a6f25 --- /dev/null +++ b/tools/perf/scripts/perl/rwtop.pl @@ -0,0 +1,177 @@ +#!/usr/bin/perl -w +# (c) 2010, Tom Zanussi <tzanussi@gmail.com> +# Licensed under the terms of the GNU GPL License version 2 + +# read/write top +# +# Periodically displays system-wide r/w call activity, broken down by +# pid. If an [interval] arg is specified, the display will be +# refreshed every [interval] seconds. The default interval is 3 +# seconds. + +use 5.010000; +use strict; +use warnings; + +use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib"; +use lib "./Perf-Trace-Util/lib"; +use Perf::Trace::Core; +use Perf::Trace::Util; + +my $default_interval = 3; +my $nlines = 20; +my $print_thread; + +my %reads; +my %writes; + +my $interval = shift; +if (!$interval) { + $interval = $default_interval; +} + +sub syscalls::sys_exit_read +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $nr, $ret) = @_; + + if ($ret > 0) { + $reads{$common_pid}{bytes_read} += $ret; + } else { + if (!defined ($reads{$common_pid}{bytes_read})) { + $reads{$common_pid}{bytes_read} = 0; + } + $reads{$common_pid}{errors}{$ret}++; + } +} + +sub syscalls::sys_enter_read +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $nr, $fd, $buf, $count) = @_; + + $reads{$common_pid}{bytes_requested} += $count; + $reads{$common_pid}{total_reads}++; + $reads{$common_pid}{comm} = $common_comm; +} + +sub syscalls::sys_exit_write +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $nr, $ret) = @_; + + if ($ret <= 0) { + $writes{$common_pid}{errors}{$ret}++; + } +} + +sub syscalls::sys_enter_write +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $nr, $fd, $buf, $count) = @_; + + $writes{$common_pid}{bytes_written} += $count; + $writes{$common_pid}{total_writes}++; + $writes{$common_pid}{comm} = $common_comm; +} + +sub trace_begin +{ + $SIG{ALRM} = \&print_totals; + alarm 1; +} + +sub trace_end +{ + print_unhandled(); + print_totals(); +} + +sub print_totals +{ + my $count; + + $count = 0; + + clear_term(); + + printf("\nread counts by pid:\n\n"); + + printf("%6s %20s %10s %10s %10s\n", "pid", "comm", + "# reads", "bytes_req", "bytes_read"); + printf("%6s %-20s %10s %10s %10s\n", "------", "--------------------", + "----------", "----------", "----------"); + + foreach my $pid (sort {$reads{$b}{bytes_read} <=> + $reads{$a}{bytes_read}} keys %reads) { + my $comm = $reads{$pid}{comm}; + my $total_reads = $reads{$pid}{total_reads}; + my $bytes_requested = $reads{$pid}{bytes_requested}; + my $bytes_read = $reads{$pid}{bytes_read}; + + printf("%6s %-20s %10s %10s %10s\n", $pid, $comm, + $total_reads, $bytes_requested, $bytes_read); + + if (++$count == $nlines) { + last; + } + } + + $count = 0; + + printf("\nwrite counts by pid:\n\n"); + + printf("%6s %20s %10s %13s\n", "pid", "comm", + "# writes", "bytes_written"); + printf("%6s %-20s %10s %13s\n", "------", "--------------------", + "----------", "-------------"); + + foreach my $pid (sort {$writes{$b}{bytes_written} <=> + $writes{$a}{bytes_written}} keys %writes) { + my $comm = $writes{$pid}{comm}; + my $total_writes = $writes{$pid}{total_writes}; + my $bytes_written = $writes{$pid}{bytes_written}; + + printf("%6s %-20s %10s %13s\n", $pid, $comm, + $total_writes, $bytes_written); + + if (++$count == $nlines) { + last; + } + } + + %reads = (); + %writes = (); + alarm $interval; +} + +my %unhandled; + +sub print_unhandled +{ + if ((scalar keys %unhandled) == 0) { + return; + } + + print "\nunhandled events:\n\n"; + + printf("%-40s %10s\n", "event", "count"); + printf("%-40s %10s\n", "----------------------------------------", + "-----------"); + + foreach my $event_name (keys %unhandled) { + printf("%-40s %10d\n", $event_name, $unhandled{$event_name}); + } +} + +sub trace_unhandled +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm) = @_; + + $unhandled{$event_name}++; +} diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py index 83e91435ed09..9689bc0acd9f 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py @@ -23,3 +23,6 @@ def nsecs_nsecs(nsecs): def nsecs_str(nsecs): str = "%5u.%09u" % (nsecs_secs(nsecs), nsecs_nsecs(nsecs)), return str + +def clear_term(): + print("\x1b[H\x1b[2J") diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record index f8885d389e6f..6ad9b8f5f009 100644 --- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record +++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record @@ -1,2 +1,2 @@ #!/bin/bash -perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit +perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit $@ diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report index 1e0c0a860c87..8c128eff9c0a 100644 --- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report +++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report @@ -1,4 +1,10 @@ #!/bin/bash # description: system-wide failed syscalls, by pid # args: [comm] -perf trace -s ~/libexec/perf-core/scripts/python/failed-syscalls-by-pid.py $1 +if [ $# -gt 0 ] ; then + if ! expr match "$1" "-" ; then + comm=$1 + shift + fi +fi +perf trace $@ -s ~/libexec/perf-core/scripts/python/failed-syscalls-by-pid.py $comm diff --git a/tools/perf/scripts/python/bin/sctop-record b/tools/perf/scripts/python/bin/sctop-record new file mode 100644 index 000000000000..27ccffa26ab4 --- /dev/null +++ b/tools/perf/scripts/python/bin/sctop-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter $@ diff --git a/tools/perf/scripts/python/bin/sctop-report b/tools/perf/scripts/python/bin/sctop-report new file mode 100644 index 000000000000..b01c842ae7b4 --- /dev/null +++ b/tools/perf/scripts/python/bin/sctop-report @@ -0,0 +1,24 @@ +#!/bin/bash +# description: syscall top +# args: [comm] [interval] +n_args=0 +for i in "$@" +do + if expr match "$i" "-" > /dev/null ; then + break + fi + n_args=$(( $n_args + 1 )) +done +if [ "$n_args" -gt 2 ] ; then + echo "usage: sctop-report [comm] [interval]" + exit +fi +if [ "$n_args" -gt 1 ] ; then + comm=$1 + interval=$2 + shift 2 +elif [ "$n_args" -gt 0 ] ; then + interval=$1 + shift +fi +perf trace $@ -s ~/libexec/perf-core/scripts/python/sctop.py $comm $interval diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record index 45a8c50359da..27ccffa26ab4 100644 --- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record +++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record @@ -1,2 +1,2 @@ #!/bin/bash -perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter +perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter $@ diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-report b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report index f8044d192271..c53362e48602 100644 --- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-report +++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report @@ -1,4 +1,10 @@ #!/bin/bash # description: system-wide syscall counts, by pid # args: [comm] -perf trace -s ~/libexec/perf-core/scripts/python/syscall-counts-by-pid.py $1 +if [ $# -gt 0 ] ; then + if ! expr match "$1" "-" ; then + comm=$1 + shift + fi +fi +perf trace $@ -s ~/libexec/perf-core/scripts/python/syscall-counts-by-pid.py $comm diff --git a/tools/perf/scripts/python/bin/syscall-counts-record b/tools/perf/scripts/python/bin/syscall-counts-record index 45a8c50359da..27ccffa26ab4 100644 --- a/tools/perf/scripts/python/bin/syscall-counts-record +++ b/tools/perf/scripts/python/bin/syscall-counts-record @@ -1,2 +1,2 @@ #!/bin/bash -perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter +perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter $@ diff --git a/tools/perf/scripts/python/bin/syscall-counts-report b/tools/perf/scripts/python/bin/syscall-counts-report index a366aa61612f..8c21552b3cdc 100644 --- a/tools/perf/scripts/python/bin/syscall-counts-report +++ b/tools/perf/scripts/python/bin/syscall-counts-report @@ -1,4 +1,10 @@ #!/bin/bash # description: system-wide syscall counts # args: [comm] -perf trace -s ~/libexec/perf-core/scripts/python/syscall-counts.py $1 +if [ $# -gt 0 ] ; then + if ! expr match "$1" "-" ; then + comm=$1 + shift + fi +fi +perf trace $@ -s ~/libexec/perf-core/scripts/python/syscall-counts.py $comm diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py new file mode 100644 index 000000000000..6cafad40c296 --- /dev/null +++ b/tools/perf/scripts/python/sctop.py @@ -0,0 +1,78 @@ +# system call top +# (c) 2010, Tom Zanussi <tzanussi@gmail.com> +# Licensed under the terms of the GNU GPL License version 2 +# +# Periodically displays system-wide system call totals, broken down by +# syscall. If a [comm] arg is specified, only syscalls called by +# [comm] are displayed. If an [interval] arg is specified, the display +# will be refreshed every [interval] seconds. The default interval is +# 3 seconds. + +import thread +import time +import os +import sys + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * +from Util import * + +usage = "perf trace -s syscall-counts.py [comm] [interval]\n"; + +for_comm = None +default_interval = 3 +interval = default_interval + +if len(sys.argv) > 3: + sys.exit(usage) + +if len(sys.argv) > 2: + for_comm = sys.argv[1] + interval = int(sys.argv[2]) +elif len(sys.argv) > 1: + try: + interval = int(sys.argv[1]) + except ValueError: + for_comm = sys.argv[1] + interval = default_interval + +syscalls = autodict() + +def trace_begin(): + thread.start_new_thread(print_syscall_totals, (interval,)) + pass + +def raw_syscalls__sys_enter(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + id, args): + if for_comm is not None: + if common_comm != for_comm: + return + try: + syscalls[id] += 1 + except TypeError: + syscalls[id] = 1 + +def print_syscall_totals(interval): + while 1: + clear_term() + if for_comm is not None: + print "\nsyscall events for %s:\n\n" % (for_comm), + else: + print "\nsyscall events:\n\n", + + print "%-40s %10s\n" % ("event", "count"), + print "%-40s %10s\n" % ("----------------------------------------", \ + "----------"), + + for id, val in sorted(syscalls.iteritems(), key = lambda(k, v): (v, k), \ + reverse = True): + try: + print "%-40d %10d\n" % (id, val), + except TypeError: + pass + syscalls.clear() + time.sleep(interval) diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN index 54552a00a117..49ece7921914 100755 --- a/tools/perf/util/PERF-VERSION-GEN +++ b/tools/perf/util/PERF-VERSION-GEN @@ -1,6 +1,10 @@ #!/bin/sh -GVF=PERF-VERSION-FILE +if [ $# -eq 1 ] ; then + OUTPUT=$1 +fi + +GVF=${OUTPUT}PERF-VERSION-FILE DEF_VER=v0.0.2.PERF LF=' diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 04904b35ba81..0f60a3906808 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -24,7 +24,7 @@ static int build_id__mark_dso_hit(event_t *event, struct perf_session *session) } thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION, - event->ip.ip, &al); + event->ip.pid, event->ip.ip, &al); if (al.map != NULL) al.map->dso->hit = 1; diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 918eb376abe3..4b9aab7f0405 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -1,6 +1,7 @@ #ifndef __PERF_CACHE_H #define __PERF_CACHE_H +#include <stdbool.h> #include "util.h" #include "strbuf.h" #include "../perf.h" @@ -69,6 +70,19 @@ extern const char *pager_program; extern int pager_in_use(void); extern int pager_use_color; +extern bool use_browser; + +#ifdef NO_NEWT_SUPPORT +static inline void setup_browser(void) +{ + setup_pager(); +} +static inline void exit_browser(bool wait_for_ok __used) {} +#else +void setup_browser(void); +void exit_browser(bool wait_for_ok); +#endif + extern const char *editor_program; extern const char *excludes_file; diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index b3b71258272a..db628af6d20d 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009, Frederic Weisbecker <fweisbec@gmail.com> + * Copyright (C) 2009-2010, Frederic Weisbecker <fweisbec@gmail.com> * * Handle the callchains from the stream in an ad-hoc radix tree and then * sort them in an rbtree. @@ -183,12 +183,23 @@ create_child(struct callchain_node *parent, bool inherit_children) return new; } + +struct resolved_ip { + u64 ip; + struct map_symbol ms; +}; + +struct resolved_chain { + u64 nr; + struct resolved_ip ips[0]; +}; + + /* * Fill the node with callchain values */ static void -fill_node(struct callchain_node *node, struct ip_callchain *chain, - int start, struct symbol **syms) +fill_node(struct callchain_node *node, struct resolved_chain *chain, int start) { unsigned int i; @@ -200,8 +211,8 @@ fill_node(struct callchain_node *node, struct ip_callchain *chain, perror("not enough memory for the code path tree"); return; } - call->ip = chain->ips[i]; - call->sym = syms[i]; + call->ip = chain->ips[i].ip; + call->ms = chain->ips[i].ms; list_add_tail(&call->list, &node->val); } node->val_nr = chain->nr - start; @@ -210,13 +221,13 @@ fill_node(struct callchain_node *node, struct ip_callchain *chain, } static void -add_child(struct callchain_node *parent, struct ip_callchain *chain, - int start, struct symbol **syms) +add_child(struct callchain_node *parent, struct resolved_chain *chain, + int start) { struct callchain_node *new; new = create_child(parent, false); - fill_node(new, chain, start, syms); + fill_node(new, chain, start); new->children_hit = 0; new->hit = 1; @@ -228,9 +239,8 @@ add_child(struct callchain_node *parent, struct ip_callchain *chain, * Then create another child to host the given callchain of new branch */ static void -split_add_child(struct callchain_node *parent, struct ip_callchain *chain, - struct callchain_list *to_split, int idx_parents, int idx_local, - struct symbol **syms) +split_add_child(struct callchain_node *parent, struct resolved_chain *chain, + struct callchain_list *to_split, int idx_parents, int idx_local) { struct callchain_node *new; struct list_head *old_tail; @@ -257,7 +267,7 @@ split_add_child(struct callchain_node *parent, struct ip_callchain *chain, /* create a new child for the new branch if any */ if (idx_total < chain->nr) { parent->hit = 0; - add_child(parent, chain, idx_total, syms); + add_child(parent, chain, idx_total); parent->children_hit++; } else { parent->hit = 1; @@ -265,32 +275,33 @@ split_add_child(struct callchain_node *parent, struct ip_callchain *chain, } static int -__append_chain(struct callchain_node *root, struct ip_callchain *chain, - unsigned int start, struct symbol **syms); +__append_chain(struct callchain_node *root, struct resolved_chain *chain, + unsigned int start); static void -__append_chain_children(struct callchain_node *root, struct ip_callchain *chain, - struct symbol **syms, unsigned int start) +__append_chain_children(struct callchain_node *root, + struct resolved_chain *chain, + unsigned int start) { struct callchain_node *rnode; /* lookup in childrens */ chain_for_each_child(rnode, root) { - unsigned int ret = __append_chain(rnode, chain, start, syms); + unsigned int ret = __append_chain(rnode, chain, start); if (!ret) goto inc_children_hit; } /* nothing in children, add to the current node */ - add_child(root, chain, start, syms); + add_child(root, chain, start); inc_children_hit: root->children_hit++; } static int -__append_chain(struct callchain_node *root, struct ip_callchain *chain, - unsigned int start, struct symbol **syms) +__append_chain(struct callchain_node *root, struct resolved_chain *chain, + unsigned int start) { struct callchain_list *cnode; unsigned int i = start; @@ -302,13 +313,19 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain, * anywhere inside a function. */ list_for_each_entry(cnode, &root->val, list) { + struct symbol *sym; + if (i == chain->nr) break; - if (cnode->sym && syms[i]) { - if (cnode->sym->start != syms[i]->start) + + sym = chain->ips[i].ms.sym; + + if (cnode->ms.sym && sym) { + if (cnode->ms.sym->start != sym->start) break; - } else if (cnode->ip != chain->ips[i]) + } else if (cnode->ip != chain->ips[i].ip) break; + if (!found) found = true; i++; @@ -320,7 +337,7 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain, /* we match only a part of the node. Split it and add the new chain */ if (i - start < root->val_nr) { - split_add_child(root, chain, cnode, start, i - start, syms); + split_add_child(root, chain, cnode, start, i - start); return 0; } @@ -331,15 +348,50 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain, } /* We match the node and still have a part remaining */ - __append_chain_children(root, chain, syms, i); + __append_chain_children(root, chain, i); return 0; } -void append_chain(struct callchain_node *root, struct ip_callchain *chain, - struct symbol **syms) +static void filter_context(struct ip_callchain *old, struct resolved_chain *new, + struct map_symbol *syms) +{ + int i, j = 0; + + for (i = 0; i < (int)old->nr; i++) { + if (old->ips[i] >= PERF_CONTEXT_MAX) + continue; + + new->ips[j].ip = old->ips[i]; + new->ips[j].ms = syms[i]; + j++; + } + + new->nr = j; +} + + +int append_chain(struct callchain_node *root, struct ip_callchain *chain, + struct map_symbol *syms) { + struct resolved_chain *filtered; + if (!chain->nr) - return; - __append_chain_children(root, chain, syms, 0); + return 0; + + filtered = malloc(sizeof(*filtered) + + chain->nr * sizeof(struct resolved_ip)); + if (!filtered) + return -ENOMEM; + + filter_context(chain, filtered, syms); + + if (!filtered->nr) + goto end; + + __append_chain_children(root, filtered, 0); +end: + free(filtered); + + return 0; } diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index ad4626de4c2b..8a7e8bbd0fda 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -39,7 +39,7 @@ struct callchain_param { struct callchain_list { u64 ip; - struct symbol *sym; + struct map_symbol ms; struct list_head list; }; @@ -56,6 +56,6 @@ static inline u64 cumul_hits(struct callchain_node *node) } int register_callchain_param(struct callchain_param *param); -void append_chain(struct callchain_node *root, struct ip_callchain *chain, - struct symbol **syms); +int append_chain(struct callchain_node *root, struct ip_callchain *chain, + struct map_symbol *syms); #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index e88bca55a599..e191eb9a667f 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -166,6 +166,31 @@ int perf_color_default_config(const char *var, const char *value, void *cb) return perf_default_config(var, value, cb); } +static int __color_vsnprintf(char *bf, size_t size, const char *color, + const char *fmt, va_list args, const char *trail) +{ + int r = 0; + + /* + * Auto-detect: + */ + if (perf_use_color_default < 0) { + if (isatty(1) || pager_in_use()) + perf_use_color_default = 1; + else + perf_use_color_default = 0; + } + + if (perf_use_color_default && *color) + r += snprintf(bf, size, "%s", color); + r += vsnprintf(bf + r, size - r, fmt, args); + if (perf_use_color_default && *color) + r += snprintf(bf + r, size - r, "%s", PERF_COLOR_RESET); + if (trail) + r += snprintf(bf + r, size - r, "%s", trail); + return r; +} + static int __color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args, const char *trail) { @@ -191,11 +216,28 @@ static int __color_vfprintf(FILE *fp, const char *color, const char *fmt, return r; } +int color_vsnprintf(char *bf, size_t size, const char *color, + const char *fmt, va_list args) +{ + return __color_vsnprintf(bf, size, color, fmt, args, NULL); +} + int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args) { return __color_vfprintf(fp, color, fmt, args, NULL); } +int color_snprintf(char *bf, size_t size, const char *color, + const char *fmt, ...) +{ + va_list args; + int r; + + va_start(args, fmt); + r = color_vsnprintf(bf, size, color, fmt, args); + va_end(args); + return r; +} int color_fprintf(FILE *fp, const char *color, const char *fmt, ...) { @@ -274,3 +316,9 @@ int percent_color_fprintf(FILE *fp, const char *fmt, double percent) return r; } + +int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent) +{ + const char *color = get_percent_color(percent); + return color_snprintf(bf, size, color, fmt, percent); +} diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index 24e8809210bb..dea082b79602 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -32,10 +32,14 @@ int perf_color_default_config(const char *var, const char *value, void *cb); int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty); void color_parse(const char *value, const char *var, char *dst); void color_parse_mem(const char *value, int len, const char *var, char *dst); +int color_vsnprintf(char *bf, size_t size, const char *color, + const char *fmt, va_list args); int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args); int color_fprintf(FILE *fp, const char *color, const char *fmt, ...); +int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...); int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...); int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf); +int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent); int percent_color_fprintf(FILE *fp, const char *fmt, double percent); const char *get_percent_color(double percent); diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 0905600c3851..dd824cf3b628 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -6,13 +6,14 @@ #include <stdarg.h> #include <stdio.h> +#include "cache.h" #include "color.h" #include "event.h" #include "debug.h" #include "util.h" int verbose = 0; -int dump_trace = 0; +bool dump_trace = false; int eprintf(int level, const char *fmt, ...) { @@ -21,7 +22,10 @@ int eprintf(int level, const char *fmt, ...) if (verbose >= level) { va_start(args, fmt); - ret = vfprintf(stderr, fmt, args); + if (use_browser) + ret = browser__show_help(fmt, args); + else + ret = vfprintf(stderr, fmt, args); va_end(args); } diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index c6c24c522dea..047ac3324ebe 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -2,14 +2,38 @@ #ifndef __PERF_DEBUG_H #define __PERF_DEBUG_H +#include <stdbool.h> #include "event.h" extern int verbose; -extern int dump_trace; +extern bool dump_trace; -int eprintf(int level, - const char *fmt, ...) __attribute__((format(printf, 2, 3))); int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); void trace_event(event_t *event); +struct ui_progress; + +#ifdef NO_NEWT_SUPPORT +static inline int browser__show_help(const char *format __used, va_list ap __used) +{ + return 0; +} + +static inline struct ui_progress *ui_progress__new(const char *title __used, + u64 total __used) +{ + return (struct ui_progress *)1; +} + +static inline void ui_progress__update(struct ui_progress *self __used, + u64 curr __used) {} + +static inline void ui_progress__delete(struct ui_progress *self __used) {} +#else +int browser__show_help(const char *format, va_list ap); +struct ui_progress *ui_progress__new(const char *title, u64 total); +void ui_progress__update(struct ui_progress *self, u64 curr); +void ui_progress__delete(struct ui_progress *self); +#endif + #endif /* __PERF_DEBUG_H */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 705ec63548b4..e3fa8d3d11b4 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -112,7 +112,11 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid, event_t ev = { .header = { .type = PERF_RECORD_MMAP, - .misc = 0, /* Just like the kernel, see kernel/perf_event.c __perf_event_mmap */ + /* + * Just like the kernel, see __perf_event_mmap + * in kernel/perf_event.c + */ + .misc = PERF_RECORD_MISC_USER, }, }; int n; @@ -130,6 +134,7 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid, continue; pbf += n + 3; if (*pbf == 'x') { /* vm_exec */ + u64 vm_pgoff; char *execname = strchr(bf, '/'); /* Catch VDSO */ @@ -139,6 +144,14 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid, if (execname == NULL) continue; + pbf += 3; + n = hex2u64(pbf, &vm_pgoff); + /* pgoff is in bytes, not pages */ + if (n >= 0) + ev.mmap.pgoff = vm_pgoff << getpagesize(); + else + ev.mmap.pgoff = 0; + size = strlen(execname); execname[size - 1] = '\0'; /* Remove \n */ memcpy(ev.mmap.filename, execname, size); @@ -158,11 +171,23 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid, } int event__synthesize_modules(event__handler_t process, - struct perf_session *session) + struct perf_session *session, + struct kernel_info *kerninfo) { struct rb_node *nd; + struct map_groups *kmaps = &kerninfo->kmaps; + u16 misc; + + /* + * kernel uses 0 for user space maps, see kernel/perf_event.c + * __perf_event_mmap + */ + if (is_host_kernel(kerninfo)) + misc = PERF_RECORD_MISC_KERNEL; + else + misc = PERF_RECORD_MISC_GUEST_KERNEL; - for (nd = rb_first(&session->kmaps.maps[MAP__FUNCTION]); + for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) { event_t ev; size_t size; @@ -173,12 +198,13 @@ int event__synthesize_modules(event__handler_t process, size = ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); memset(&ev, 0, sizeof(ev)); - ev.mmap.header.misc = 1; /* kernel uses 0 for user space maps, see kernel/perf_event.c __perf_event_mmap */ + ev.mmap.header.misc = misc; ev.mmap.header.type = PERF_RECORD_MMAP; ev.mmap.header.size = (sizeof(ev.mmap) - (sizeof(ev.mmap.filename) - size)); ev.mmap.start = pos->start; ev.mmap.len = pos->end - pos->start; + ev.mmap.pid = kerninfo->pid; memcpy(ev.mmap.filename, pos->dso->long_name, pos->dso->long_name_len + 1); @@ -241,13 +267,18 @@ static int find_symbol_cb(void *arg, const char *name, char type, u64 start) int event__synthesize_kernel_mmap(event__handler_t process, struct perf_session *session, + struct kernel_info *kerninfo, const char *symbol_name) { size_t size; + const char *filename, *mmap_name; + char path[PATH_MAX]; + char name_buff[PATH_MAX]; + struct map *map; + event_t ev = { .header = { .type = PERF_RECORD_MMAP, - .misc = 1, /* kernel uses 0 for user space maps, see kernel/perf_event.c __perf_event_mmap */ }, }; /* @@ -257,16 +288,37 @@ int event__synthesize_kernel_mmap(event__handler_t process, */ struct process_symbol_args args = { .name = symbol_name, }; - if (kallsyms__parse("/proc/kallsyms", &args, find_symbol_cb) <= 0) + mmap_name = kern_mmap_name(kerninfo, name_buff); + if (is_host_kernel(kerninfo)) { + /* + * kernel uses PERF_RECORD_MISC_USER for user space maps, + * see kernel/perf_event.c __perf_event_mmap + */ + ev.header.misc = PERF_RECORD_MISC_KERNEL; + filename = "/proc/kallsyms"; + } else { + ev.header.misc = PERF_RECORD_MISC_GUEST_KERNEL; + if (is_default_guest(kerninfo)) + filename = (char *) symbol_conf.default_guest_kallsyms; + else { + sprintf(path, "%s/proc/kallsyms", kerninfo->root_dir); + filename = path; + } + } + + if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) return -ENOENT; + map = kerninfo->vmlinux_maps[MAP__FUNCTION]; size = snprintf(ev.mmap.filename, sizeof(ev.mmap.filename), - "[kernel.kallsyms.%s]", symbol_name) + 1; + "%s%s", mmap_name, symbol_name) + 1; size = ALIGN(size, sizeof(u64)); - ev.mmap.header.size = (sizeof(ev.mmap) - (sizeof(ev.mmap.filename) - size)); + ev.mmap.header.size = (sizeof(ev.mmap) - + (sizeof(ev.mmap.filename) - size)); ev.mmap.pgoff = args.start; - ev.mmap.start = session->vmlinux_maps[MAP__FUNCTION]->start; - ev.mmap.len = session->vmlinux_maps[MAP__FUNCTION]->end - ev.mmap.start ; + ev.mmap.start = map->start; + ev.mmap.len = map->end - ev.mmap.start; + ev.mmap.pid = kerninfo->pid; return process(&ev, session); } @@ -320,22 +372,50 @@ int event__process_lost(event_t *self, struct perf_session *session) return 0; } -int event__process_mmap(event_t *self, struct perf_session *session) +static void event_set_kernel_mmap_len(struct map **maps, event_t *self) +{ + maps[MAP__FUNCTION]->start = self->mmap.start; + maps[MAP__FUNCTION]->end = self->mmap.start + self->mmap.len; + /* + * Be a bit paranoid here, some perf.data file came with + * a zero sized synthesized MMAP event for the kernel. + */ + if (maps[MAP__FUNCTION]->end == 0) + maps[MAP__FUNCTION]->end = ~0UL; +} + +static int event__process_kernel_mmap(event_t *self, + struct perf_session *session) { - struct thread *thread; struct map *map; + char kmmap_prefix[PATH_MAX]; + struct kernel_info *kerninfo; + enum dso_kernel_type kernel_type; + bool is_kernel_mmap; + + kerninfo = kerninfo__findnew(&session->kerninfo_root, self->mmap.pid); + if (!kerninfo) { + pr_err("Can't find id %d's kerninfo\n", self->mmap.pid); + goto out_problem; + } - dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n", - self->mmap.pid, self->mmap.tid, self->mmap.start, - self->mmap.len, self->mmap.pgoff, self->mmap.filename); + kern_mmap_name(kerninfo, kmmap_prefix); + if (is_host_kernel(kerninfo)) + kernel_type = DSO_TYPE_KERNEL; + else + kernel_type = DSO_TYPE_GUEST_KERNEL; - if (self->mmap.pid == 0) { - static const char kmmap_prefix[] = "[kernel.kallsyms."; + is_kernel_mmap = memcmp(self->mmap.filename, + kmmap_prefix, + strlen(kmmap_prefix)) == 0; + if (self->mmap.filename[0] == '/' || + (!is_kernel_mmap && self->mmap.filename[0] == '[')) { - if (self->mmap.filename[0] == '/') { - char short_module_name[1024]; - char *name = strrchr(self->mmap.filename, '/'), *dot; + char short_module_name[1024]; + char *name, *dot; + if (self->mmap.filename[0] == '/') { + name = strrchr(self->mmap.filename, '/'); if (name == NULL) goto out_problem; @@ -343,58 +423,86 @@ int event__process_mmap(event_t *self, struct perf_session *session) dot = strrchr(name, '.'); if (dot == NULL) goto out_problem; - snprintf(short_module_name, sizeof(short_module_name), - "[%.*s]", (int)(dot - name), name); + "[%.*s]", (int)(dot - name), name); strxfrchar(short_module_name, '-', '_'); - - map = perf_session__new_module_map(session, - self->mmap.start, - self->mmap.filename); - if (map == NULL) - goto out_problem; - - name = strdup(short_module_name); - if (name == NULL) - goto out_problem; - - map->dso->short_name = name; - map->end = map->start + self->mmap.len; - } else if (memcmp(self->mmap.filename, kmmap_prefix, - sizeof(kmmap_prefix) - 1) == 0) { - const char *symbol_name = (self->mmap.filename + - sizeof(kmmap_prefix) - 1); + } else + strcpy(short_module_name, self->mmap.filename); + + map = map_groups__new_module(&kerninfo->kmaps, + self->mmap.start, + self->mmap.filename, + kerninfo); + if (map == NULL) + goto out_problem; + + name = strdup(short_module_name); + if (name == NULL) + goto out_problem; + + map->dso->short_name = name; + map->end = map->start + self->mmap.len; + } else if (is_kernel_mmap) { + const char *symbol_name = (self->mmap.filename + + strlen(kmmap_prefix)); + /* + * Should be there already, from the build-id table in + * the header. + */ + struct dso *kernel = __dsos__findnew(&kerninfo->dsos__kernel, + kmmap_prefix); + if (kernel == NULL) + goto out_problem; + + kernel->kernel = kernel_type; + if (__map_groups__create_kernel_maps(&kerninfo->kmaps, + kerninfo->vmlinux_maps, kernel) < 0) + goto out_problem; + + event_set_kernel_mmap_len(kerninfo->vmlinux_maps, self); + perf_session__set_kallsyms_ref_reloc_sym(kerninfo->vmlinux_maps, + symbol_name, + self->mmap.pgoff); + if (is_default_guest(kerninfo)) { /* - * Should be there already, from the build-id table in - * the header. + * preload dso of guest kernel and modules */ - struct dso *kernel = __dsos__findnew(&dsos__kernel, - "[kernel.kallsyms]"); - if (kernel == NULL) - goto out_problem; - - kernel->kernel = 1; - if (__perf_session__create_kernel_maps(session, kernel) < 0) - goto out_problem; + dso__load(kernel, + kerninfo->vmlinux_maps[MAP__FUNCTION], + NULL); + } + } + return 0; +out_problem: + return -1; +} - session->vmlinux_maps[MAP__FUNCTION]->start = self->mmap.start; - session->vmlinux_maps[MAP__FUNCTION]->end = self->mmap.start + self->mmap.len; - /* - * Be a bit paranoid here, some perf.data file came with - * a zero sized synthesized MMAP event for the kernel. - */ - if (session->vmlinux_maps[MAP__FUNCTION]->end == 0) - session->vmlinux_maps[MAP__FUNCTION]->end = ~0UL; +int event__process_mmap(event_t *self, struct perf_session *session) +{ + struct kernel_info *kerninfo; + struct thread *thread; + struct map *map; + u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + int ret = 0; - perf_session__set_kallsyms_ref_reloc_sym(session, symbol_name, - self->mmap.pgoff); - } + dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n", + self->mmap.pid, self->mmap.tid, self->mmap.start, + self->mmap.len, self->mmap.pgoff, self->mmap.filename); + + if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL || + cpumode == PERF_RECORD_MISC_KERNEL) { + ret = event__process_kernel_mmap(self, session); + if (ret < 0) + goto out_problem; return 0; } thread = perf_session__findnew(session, self->mmap.pid); - map = map__new(&self->mmap, MAP__FUNCTION, - session->cwd, session->cwdlen); + kerninfo = kerninfo__findhost(&session->kerninfo_root); + map = map__new(&kerninfo->dsos__user, self->mmap.start, + self->mmap.len, self->mmap.pgoff, + self->mmap.pid, self->mmap.filename, + MAP__FUNCTION, session->cwd, session->cwdlen); if (thread == NULL || map == NULL) goto out_problem; @@ -434,22 +542,52 @@ int event__process_task(event_t *self, struct perf_session *session) void thread__find_addr_map(struct thread *self, struct perf_session *session, u8 cpumode, - enum map_type type, u64 addr, + enum map_type type, pid_t pid, u64 addr, struct addr_location *al) { struct map_groups *mg = &self->mg; + struct kernel_info *kerninfo = NULL; al->thread = self; al->addr = addr; + al->cpumode = cpumode; + al->filtered = false; - if (cpumode == PERF_RECORD_MISC_KERNEL) { + if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) { al->level = 'k'; - mg = &session->kmaps; - } else if (cpumode == PERF_RECORD_MISC_USER) + kerninfo = kerninfo__findhost(&session->kerninfo_root); + mg = &kerninfo->kmaps; + } else if (cpumode == PERF_RECORD_MISC_USER && perf_host) { al->level = '.'; - else { - al->level = 'H'; + kerninfo = kerninfo__findhost(&session->kerninfo_root); + } else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) { + al->level = 'g'; + kerninfo = kerninfo__find(&session->kerninfo_root, pid); + if (!kerninfo) { + al->map = NULL; + return; + } + mg = &kerninfo->kmaps; + } else { + /* + * 'u' means guest os user space. + * TODO: We don't support guest user space. Might support late. + */ + if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) + al->level = 'u'; + else + al->level = 'H'; al->map = NULL; + + if ((cpumode == PERF_RECORD_MISC_GUEST_USER || + cpumode == PERF_RECORD_MISC_GUEST_KERNEL) && + !perf_guest) + al->filtered = true; + if ((cpumode == PERF_RECORD_MISC_USER || + cpumode == PERF_RECORD_MISC_KERNEL) && + !perf_host) + al->filtered = true; + return; } try_again: @@ -464,8 +602,11 @@ try_again: * "[vdso]" dso, but for now lets use the old trick of looking * in the whole kernel symbol list. */ - if ((long long)al->addr < 0 && mg != &session->kmaps) { - mg = &session->kmaps; + if ((long long)al->addr < 0 && + cpumode == PERF_RECORD_MISC_KERNEL && + kerninfo && + mg != &kerninfo->kmaps) { + mg = &kerninfo->kmaps; goto try_again; } } else @@ -474,11 +615,11 @@ try_again: void thread__find_addr_location(struct thread *self, struct perf_session *session, u8 cpumode, - enum map_type type, u64 addr, + enum map_type type, pid_t pid, u64 addr, struct addr_location *al, symbol_filter_t filter) { - thread__find_addr_map(self, session, cpumode, type, addr, al); + thread__find_addr_map(self, session, cpumode, type, pid, addr, al); if (al->map != NULL) al->sym = map__find_symbol(al->map, al->addr, filter); else @@ -513,30 +654,37 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session, dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); - thread__find_addr_location(thread, session, cpumode, MAP__FUNCTION, - self->ip.ip, al, filter); + thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION, + self->ip.pid, self->ip.ip, al); dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : "<not found>"); - /* - * We have to do this here as we may have a dso with no symbol hit that - * has a name longer than the ones with symbols sampled. - */ - if (al->map && !sort_dso.elide && !al->map->dso->slen_calculated) - dso__calc_col_width(al->map->dso); - - if (symbol_conf.dso_list && - (!al->map || !al->map->dso || - !(strlist__has_entry(symbol_conf.dso_list, al->map->dso->short_name) || - (al->map->dso->short_name != al->map->dso->long_name && - strlist__has_entry(symbol_conf.dso_list, al->map->dso->long_name))))) - goto out_filtered; + al->sym = NULL; + + if (al->map) { + if (symbol_conf.dso_list && + (!al->map || !al->map->dso || + !(strlist__has_entry(symbol_conf.dso_list, + al->map->dso->short_name) || + (al->map->dso->short_name != al->map->dso->long_name && + strlist__has_entry(symbol_conf.dso_list, + al->map->dso->long_name))))) + goto out_filtered; + /* + * We have to do this here as we may have a dso with no symbol + * hit that has a name longer than the ones with symbols + * sampled. + */ + if (!sort_dso.elide && !al->map->dso->slen_calculated) + dso__calc_col_width(al->map->dso); + + al->sym = map__find_symbol(al->map, al->addr, filter); + } if (symbol_conf.sym_list && al->sym && !strlist__has_entry(symbol_conf.sym_list, al->sym->name)) goto out_filtered; - al->filtered = false; return 0; out_filtered: diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index a33b94952e34..4af2ed5d48ad 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -68,21 +68,53 @@ struct sample_data { u64 addr; u64 id; u64 stream_id; - u32 cpu; u64 period; - struct ip_callchain *callchain; + u32 cpu; u32 raw_size; void *raw_data; + struct ip_callchain *callchain; }; #define BUILD_ID_SIZE 20 struct build_id_event { struct perf_event_header header; + pid_t pid; u8 build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))]; char filename[]; }; +enum perf_header_event_type { /* above any possible kernel type */ + PERF_RECORD_HEADER_ATTR = 64, + PERF_RECORD_HEADER_EVENT_TYPE = 65, + PERF_RECORD_HEADER_TRACING_DATA = 66, + PERF_RECORD_HEADER_BUILD_ID = 67, + PERF_RECORD_HEADER_MAX +}; + +struct attr_event { + struct perf_event_header header; + struct perf_event_attr attr; + u64 id[]; +}; + +#define MAX_EVENT_NAME 64 + +struct perf_trace_event_type { + u64 event_id; + char name[MAX_EVENT_NAME]; +}; + +struct event_type_event { + struct perf_event_header header; + struct perf_trace_event_type event_type; +}; + +struct tracing_data_event { + struct perf_event_header header; + u32 size; +}; + typedef union event_union { struct perf_event_header header; struct ip_event ip; @@ -92,6 +124,10 @@ typedef union event_union { struct lost_event lost; struct read_event read; struct sample_event sample; + struct attr_event attr; + struct event_type_event event_type; + struct tracing_data_event tracing_data; + struct build_id_event build_id; } event_t; struct events_stats { @@ -119,10 +155,13 @@ int event__synthesize_thread(pid_t pid, event__handler_t process, void event__synthesize_threads(event__handler_t process, struct perf_session *session); int event__synthesize_kernel_mmap(event__handler_t process, - struct perf_session *session, - const char *symbol_name); + struct perf_session *session, + struct kernel_info *kerninfo, + const char *symbol_name); + int event__synthesize_modules(event__handler_t process, - struct perf_session *session); + struct perf_session *session, + struct kernel_info *kerninfo); int event__process_comm(event_t *self, struct perf_session *session); int event__process_lost(event_t *self, struct perf_session *session); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 6c9aa16ee51f..75d016768021 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -99,13 +99,6 @@ int perf_header__add_attr(struct perf_header *self, return 0; } -#define MAX_EVENT_NAME 64 - -struct perf_trace_event_type { - u64 event_id; - char name[MAX_EVENT_NAME]; -}; - static int event_count; static struct perf_trace_event_type *events; @@ -197,7 +190,8 @@ static int write_padded(int fd, const void *bf, size_t count, continue; \ else -static int __dsos__write_buildid_table(struct list_head *head, u16 misc, int fd) +static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, + u16 misc, int fd) { struct dso *pos; @@ -212,6 +206,7 @@ static int __dsos__write_buildid_table(struct list_head *head, u16 misc, int fd) len = ALIGN(len, NAME_ALIGN); memset(&b, 0, sizeof(b)); memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id)); + b.pid = pid; b.header.misc = misc; b.header.size = sizeof(b) + len; err = do_write(fd, &b, sizeof(b)); @@ -226,13 +221,33 @@ static int __dsos__write_buildid_table(struct list_head *head, u16 misc, int fd) return 0; } -static int dsos__write_buildid_table(int fd) +static int dsos__write_buildid_table(struct perf_header *header, int fd) { - int err = __dsos__write_buildid_table(&dsos__kernel, - PERF_RECORD_MISC_KERNEL, fd); - if (err == 0) - err = __dsos__write_buildid_table(&dsos__user, - PERF_RECORD_MISC_USER, fd); + struct perf_session *session = container_of(header, + struct perf_session, header); + struct rb_node *nd; + int err = 0; + u16 kmisc, umisc; + + for (nd = rb_first(&session->kerninfo_root); nd; nd = rb_next(nd)) { + struct kernel_info *pos = rb_entry(nd, struct kernel_info, + rb_node); + if (is_host_kernel(pos)) { + kmisc = PERF_RECORD_MISC_KERNEL; + umisc = PERF_RECORD_MISC_USER; + } else { + kmisc = PERF_RECORD_MISC_GUEST_KERNEL; + umisc = PERF_RECORD_MISC_GUEST_USER; + } + + err = __dsos__write_buildid_table(&pos->dsos__kernel, pos->pid, + kmisc, fd); + if (err == 0) + err = __dsos__write_buildid_table(&pos->dsos__user, + pos->pid, umisc, fd); + if (err) + break; + } return err; } @@ -349,9 +364,12 @@ static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) return err; } -static int dsos__cache_build_ids(void) +static int dsos__cache_build_ids(struct perf_header *self) { - int err_kernel, err_user; + struct perf_session *session = container_of(self, + struct perf_session, header); + struct rb_node *nd; + int ret = 0; char debugdir[PATH_MAX]; snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"), @@ -360,9 +378,30 @@ static int dsos__cache_build_ids(void) if (mkdir(debugdir, 0755) != 0 && errno != EEXIST) return -1; - err_kernel = __dsos__cache_build_ids(&dsos__kernel, debugdir); - err_user = __dsos__cache_build_ids(&dsos__user, debugdir); - return err_kernel || err_user ? -1 : 0; + for (nd = rb_first(&session->kerninfo_root); nd; nd = rb_next(nd)) { + struct kernel_info *pos = rb_entry(nd, struct kernel_info, + rb_node); + ret |= __dsos__cache_build_ids(&pos->dsos__kernel, debugdir); + ret |= __dsos__cache_build_ids(&pos->dsos__user, debugdir); + } + return ret ? -1 : 0; +} + +static bool dsos__read_build_ids(struct perf_header *self, bool with_hits) +{ + bool ret = false; + struct perf_session *session = container_of(self, + struct perf_session, header); + struct rb_node *nd; + + for (nd = rb_first(&session->kerninfo_root); nd; nd = rb_next(nd)) { + struct kernel_info *pos = rb_entry(nd, struct kernel_info, + rb_node); + ret |= __dsos__read_build_ids(&pos->dsos__kernel, with_hits); + ret |= __dsos__read_build_ids(&pos->dsos__user, with_hits); + } + + return ret; } static int perf_header__adds_write(struct perf_header *self, int fd) @@ -373,7 +412,7 @@ static int perf_header__adds_write(struct perf_header *self, int fd) u64 sec_start; int idx = 0, err; - if (dsos__read_build_ids(true)) + if (dsos__read_build_ids(self, true)) perf_header__set_feat(self, HEADER_BUILD_ID); nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS); @@ -408,14 +447,14 @@ static int perf_header__adds_write(struct perf_header *self, int fd) /* Write build-ids */ buildid_sec->offset = lseek(fd, 0, SEEK_CUR); - err = dsos__write_buildid_table(fd); + err = dsos__write_buildid_table(self, fd); if (err < 0) { pr_debug("failed to write buildid table\n"); goto out_free; } buildid_sec->size = lseek(fd, 0, SEEK_CUR) - buildid_sec->offset; - dsos__cache_build_ids(); + dsos__cache_build_ids(self); } lseek(fd, sec_start, SEEK_SET); @@ -427,6 +466,25 @@ out_free: return err; } +int perf_header__write_pipe(int fd) +{ + struct perf_pipe_file_header f_header; + int err; + + f_header = (struct perf_pipe_file_header){ + .magic = PERF_MAGIC, + .size = sizeof(f_header), + }; + + err = do_write(fd, &f_header, sizeof(f_header)); + if (err < 0) { + pr_debug("failed to write perf pipe header\n"); + return err; + } + + return 0; +} + int perf_header__write(struct perf_header *self, int fd, bool at_exit) { struct perf_file_header f_header; @@ -518,25 +576,10 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit) return 0; } -static int do_read(int fd, void *buf, size_t size) -{ - while (size) { - int ret = read(fd, buf, size); - - if (ret <= 0) - return -1; - - size -= ret; - buf += ret; - } - - return 0; -} - static int perf_header__getbuffer64(struct perf_header *self, int fd, void *buf, size_t size) { - if (do_read(fd, buf, size)) + if (do_read(fd, buf, size) <= 0) return -1; if (self->needs_swap) @@ -592,7 +635,7 @@ int perf_file_header__read(struct perf_file_header *self, { lseek(fd, 0, SEEK_SET); - if (do_read(fd, self, sizeof(*self)) || + if (do_read(fd, self, sizeof(*self)) <= 0 || memcmp(&self->magic, __perf_magic, sizeof(self->magic))) return -1; @@ -636,6 +679,85 @@ int perf_file_header__read(struct perf_file_header *self, return 0; } +static int __event_process_build_id(struct build_id_event *bev, + char *filename, + struct perf_session *session) +{ + int err = -1; + struct list_head *head; + struct kernel_info *kerninfo; + u16 misc; + struct dso *dso; + enum dso_kernel_type dso_type; + + kerninfo = kerninfo__findnew(&session->kerninfo_root, bev->pid); + if (!kerninfo) + goto out; + + misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + + switch (misc) { + case PERF_RECORD_MISC_KERNEL: + dso_type = DSO_TYPE_KERNEL; + head = &kerninfo->dsos__kernel; + break; + case PERF_RECORD_MISC_GUEST_KERNEL: + dso_type = DSO_TYPE_GUEST_KERNEL; + head = &kerninfo->dsos__kernel; + break; + case PERF_RECORD_MISC_USER: + case PERF_RECORD_MISC_GUEST_USER: + dso_type = DSO_TYPE_USER; + head = &kerninfo->dsos__user; + break; + default: + goto out; + } + + dso = __dsos__findnew(head, filename); + if (dso != NULL) { + dso__set_build_id(dso, &bev->build_id); + if (filename[0] == '[') + dso->kernel = dso_type; + } + + err = 0; +out: + return err; +} + +static int perf_header__read_build_ids(struct perf_header *self, + int input, u64 offset, u64 size) +{ + struct perf_session *session = container_of(self, + struct perf_session, header); + struct build_id_event bev; + char filename[PATH_MAX]; + u64 limit = offset + size; + int err = -1; + + while (offset < limit) { + ssize_t len; + + if (read(input, &bev, sizeof(bev)) != sizeof(bev)) + goto out; + + if (self->needs_swap) + perf_event_header__bswap(&bev.header); + + len = bev.header.size - sizeof(bev); + if (read(input, filename, len) != len) + goto out; + + __event_process_build_id(&bev, filename, session); + + offset += bev.header.size; + } + err = 0; +out: + return err; +} + static int perf_file_section__process(struct perf_file_section *self, struct perf_header *ph, int feat, int fd) @@ -662,13 +784,51 @@ static int perf_file_section__process(struct perf_file_section *self, return 0; } -int perf_header__read(struct perf_header *self, int fd) +static int perf_file_header__read_pipe(struct perf_pipe_file_header *self, + struct perf_header *ph, int fd) +{ + if (do_read(fd, self, sizeof(*self)) <= 0 || + memcmp(&self->magic, __perf_magic, sizeof(self->magic))) + return -1; + + if (self->size != sizeof(*self)) { + u64 size = bswap_64(self->size); + + if (size != sizeof(*self)) + return -1; + + ph->needs_swap = true; + } + + return 0; +} + +static int perf_header__read_pipe(struct perf_session *session, int fd) +{ + struct perf_header *self = &session->header; + struct perf_pipe_file_header f_header; + + if (perf_file_header__read_pipe(&f_header, self, fd) < 0) { + pr_debug("incompatible file format\n"); + return -EINVAL; + } + + session->fd = fd; + + return 0; +} + +int perf_header__read(struct perf_session *session, int fd) { + struct perf_header *self = &session->header; struct perf_file_header f_header; struct perf_file_attr f_attr; u64 f_id; int nr_attrs, nr_ids, i, j; + if (session->fd_pipe) + return perf_header__read_pipe(session, fd); + if (perf_file_header__read(&f_header, self, fd) < 0) { pr_debug("incompatible file format\n"); return -EINVAL; @@ -765,3 +925,287 @@ perf_header__find_attr(u64 id, struct perf_header *header) return NULL; } + +int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id, + event__handler_t process, + struct perf_session *session) +{ + event_t *ev; + size_t size; + int err; + + size = sizeof(struct perf_event_attr); + size = ALIGN(size, sizeof(u64)); + size += sizeof(struct perf_event_header); + size += ids * sizeof(u64); + + ev = malloc(size); + + ev->attr.attr = *attr; + memcpy(ev->attr.id, id, ids * sizeof(u64)); + + ev->attr.header.type = PERF_RECORD_HEADER_ATTR; + ev->attr.header.size = size; + + err = process(ev, session); + + free(ev); + + return err; +} + +int event__synthesize_attrs(struct perf_header *self, + event__handler_t process, + struct perf_session *session) +{ + struct perf_header_attr *attr; + int i, err = 0; + + for (i = 0; i < self->attrs; i++) { + attr = self->attr[i]; + + err = event__synthesize_attr(&attr->attr, attr->ids, attr->id, + process, session); + if (err) { + pr_debug("failed to create perf header attribute\n"); + return err; + } + } + + return err; +} + +int event__process_attr(event_t *self, struct perf_session *session) +{ + struct perf_header_attr *attr; + unsigned int i, ids, n_ids; + + attr = perf_header_attr__new(&self->attr.attr); + if (attr == NULL) + return -ENOMEM; + + ids = self->header.size; + ids -= (void *)&self->attr.id - (void *)self; + n_ids = ids / sizeof(u64); + + for (i = 0; i < n_ids; i++) { + if (perf_header_attr__add_id(attr, self->attr.id[i]) < 0) { + perf_header_attr__delete(attr); + return -ENOMEM; + } + } + + if (perf_header__add_attr(&session->header, attr) < 0) { + perf_header_attr__delete(attr); + return -ENOMEM; + } + + perf_session__update_sample_type(session); + + return 0; +} + +int event__synthesize_event_type(u64 event_id, char *name, + event__handler_t process, + struct perf_session *session) +{ + event_t ev; + size_t size = 0; + int err = 0; + + memset(&ev, 0, sizeof(ev)); + + ev.event_type.event_type.event_id = event_id; + memset(ev.event_type.event_type.name, 0, MAX_EVENT_NAME); + strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1); + + ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE; + size = strlen(name); + size = ALIGN(size, sizeof(u64)); + ev.event_type.header.size = sizeof(ev.event_type) - + (sizeof(ev.event_type.event_type.name) - size); + + err = process(&ev, session); + + return err; +} + +int event__synthesize_event_types(event__handler_t process, + struct perf_session *session) +{ + struct perf_trace_event_type *type; + int i, err = 0; + + for (i = 0; i < event_count; i++) { + type = &events[i]; + + err = event__synthesize_event_type(type->event_id, type->name, + process, session); + if (err) { + pr_debug("failed to create perf header event type\n"); + return err; + } + } + + return err; +} + +int event__process_event_type(event_t *self, + struct perf_session *session __unused) +{ + if (perf_header__push_event(self->event_type.event_type.event_id, + self->event_type.event_type.name) < 0) + return -ENOMEM; + + return 0; +} + +int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs, + int nb_events, + event__handler_t process, + struct perf_session *session __unused) +{ + event_t ev; + ssize_t size = 0, aligned_size = 0, padding; + int err = 0; + + memset(&ev, 0, sizeof(ev)); + + ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA; + size = read_tracing_data_size(fd, pattrs, nb_events); + if (size <= 0) + return size; + aligned_size = ALIGN(size, sizeof(u64)); + padding = aligned_size - size; + ev.tracing_data.header.size = sizeof(ev.tracing_data); + ev.tracing_data.size = aligned_size; + + process(&ev, session); + + err = read_tracing_data(fd, pattrs, nb_events); + write_padded(fd, NULL, 0, padding); + + return aligned_size; +} + +int event__process_tracing_data(event_t *self, + struct perf_session *session) +{ + ssize_t size_read, padding, size = self->tracing_data.size; + off_t offset = lseek(session->fd, 0, SEEK_CUR); + char buf[BUFSIZ]; + + /* setup for reading amidst mmap */ + lseek(session->fd, offset + sizeof(struct tracing_data_event), + SEEK_SET); + + size_read = trace_report(session->fd); + + padding = ALIGN(size_read, sizeof(u64)) - size_read; + + if (read(session->fd, buf, padding) < 0) + die("reading input file"); + + if (size_read + padding != size) + die("tracing data size mismatch"); + + return size_read + padding; +} + +int event__synthesize_build_id(struct dso *pos, u16 misc, + event__handler_t process, + struct kernel_info *kerninfo, + struct perf_session *session) +{ + event_t ev; + size_t len; + int err = 0; + + if (!pos->hit) + return err; + + memset(&ev, 0, sizeof(ev)); + + len = pos->long_name_len + 1; + len = ALIGN(len, NAME_ALIGN); + memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id)); + ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID; + ev.build_id.header.misc = misc; + ev.build_id.pid = kerninfo->pid; + ev.build_id.header.size = sizeof(ev.build_id) + len; + memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len); + + err = process(&ev, session); + + return err; +} + +static int __event_synthesize_build_ids(struct list_head *head, u16 misc, + event__handler_t process, + struct kernel_info *kerninfo, + struct perf_session *session) +{ + struct dso *pos; + + dsos__for_each_with_build_id(pos, head) { + int err; + if (!pos->hit) + continue; + + err = event__synthesize_build_id(pos, misc, process, + kerninfo, session); + if (err < 0) + return err; + } + + return 0; +} + +int event__synthesize_build_ids(event__handler_t process, + struct perf_session *session) +{ + int err = 0; + u16 kmisc, umisc; + struct kernel_info *pos; + struct rb_node *nd; + + if (!dsos__read_build_ids(&session->header, true)) + return 0; + + for (nd = rb_first(&session->kerninfo_root); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct kernel_info, rb_node); + if (is_host_kernel(pos)) { + kmisc = PERF_RECORD_MISC_KERNEL; + umisc = PERF_RECORD_MISC_USER; + } else { + kmisc = PERF_RECORD_MISC_GUEST_KERNEL; + umisc = PERF_RECORD_MISC_GUEST_USER; + } + + err = __event_synthesize_build_ids(&pos->dsos__kernel, + kmisc, process, pos, session); + if (err == 0) + err = __event_synthesize_build_ids(&pos->dsos__user, + umisc, process, pos, session); + if (err) + break; + } + + if (err < 0) { + pr_debug("failed to synthesize build ids\n"); + return err; + } + + dsos__cache_build_ids(&session->header); + + return 0; +} + +int event__process_build_id(event_t *self, + struct perf_session *session) +{ + __event_process_build_id(&self->build_id, + self->build_id.filename, + session); + return 0; +} diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 82a6af72d4cc..275915458148 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -39,6 +39,11 @@ struct perf_file_header { DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS); }; +struct perf_pipe_file_header { + u64 magic; + u64 size; +}; + struct perf_header; int perf_file_header__read(struct perf_file_header *self, @@ -47,21 +52,22 @@ int perf_file_header__read(struct perf_file_header *self, struct perf_header { int frozen; int attrs, size; + bool needs_swap; struct perf_header_attr **attr; s64 attr_offset; u64 data_offset; u64 data_size; u64 event_offset; u64 event_size; - bool needs_swap; DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS); }; int perf_header__init(struct perf_header *self); void perf_header__exit(struct perf_header *self); -int perf_header__read(struct perf_header *self, int fd); +int perf_header__read(struct perf_session *session, int fd); int perf_header__write(struct perf_header *self, int fd, bool at_exit); +int perf_header__write_pipe(int fd); int perf_header__add_attr(struct perf_header *self, struct perf_header_attr *attr); @@ -89,4 +95,35 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, const char *name, bool is_kallsyms); int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir); +int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id, + event__handler_t process, + struct perf_session *session); +int event__synthesize_attrs(struct perf_header *self, + event__handler_t process, + struct perf_session *session); +int event__process_attr(event_t *self, struct perf_session *session); + +int event__synthesize_event_type(u64 event_id, char *name, + event__handler_t process, + struct perf_session *session); +int event__synthesize_event_types(event__handler_t process, + struct perf_session *session); +int event__process_event_type(event_t *self, + struct perf_session *session); + +int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs, + int nb_events, + event__handler_t process, + struct perf_session *session); +int event__process_tracing_data(event_t *self, + struct perf_session *session); + +int event__synthesize_build_id(struct dso *pos, u16 misc, + event__handler_t process, + struct kernel_info *kerninfo, + struct perf_session *session); +int event__synthesize_build_ids(event__handler_t process, + struct perf_session *session); +int event__process_build_id(event_t *self, struct perf_session *session); + #endif /* __PERF_HEADER_H */ diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 2be33c7dbf03..ad6b22dde27f 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -8,6 +8,30 @@ struct callchain_param callchain_param = { .min_percent = 0.5 }; +void __perf_session__add_count(struct hist_entry *he, + struct addr_location *al, + u64 count) +{ + he->count += count; + + switch (al->cpumode) { + case PERF_RECORD_MISC_KERNEL: + he->count_sys += count; + break; + case PERF_RECORD_MISC_USER: + he->count_us += count; + break; + case PERF_RECORD_MISC_GUEST_KERNEL: + he->count_guest_sys += count; + break; + case PERF_RECORD_MISC_GUEST_USER: + he->count_guest_us += count; + break; + default: + break; + } +} + /* * histogram, sorted on item, collects counts */ @@ -22,8 +46,10 @@ struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists, struct hist_entry *he; struct hist_entry entry = { .thread = al->thread, - .map = al->map, - .sym = al->sym, + .ms = { + .map = al->map, + .sym = al->sym, + }, .ip = al->addr, .level = al->level, .count = count, @@ -48,7 +74,8 @@ struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists, p = &(*p)->rb_right; } - he = malloc(sizeof(*he)); + he = malloc(sizeof(*he) + (symbol_conf.use_callchain ? + sizeof(struct callchain_node) : 0)); if (!he) return NULL; *he = entry; @@ -65,7 +92,7 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) int64_t cmp = 0; list_for_each_entry(se, &hist_entry__sort_list, list) { - cmp = se->cmp(left, right); + cmp = se->se_cmp(left, right); if (cmp) break; } @@ -82,7 +109,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) list_for_each_entry(se, &hist_entry__sort_list, list) { int64_t (*f)(struct hist_entry *, struct hist_entry *); - f = se->collapse ?: se->cmp; + f = se->se_collapse ?: se->se_cmp; cmp = f(left, right); if (cmp) @@ -166,7 +193,7 @@ static void perf_session__insert_output_hist_entry(struct rb_root *root, struct hist_entry *iter; if (symbol_conf.use_callchain) - callchain_param.sort(&he->sorted_chain, &he->callchain, + callchain_param.sort(&he->sorted_chain, he->callchain, min_callchain_hits, &callchain_param); while (*p != NULL) { @@ -183,12 +210,13 @@ static void perf_session__insert_output_hist_entry(struct rb_root *root, rb_insert_color(&he->rb_node, root); } -void perf_session__output_resort(struct rb_root *hists, u64 total_samples) +u64 perf_session__output_resort(struct rb_root *hists, u64 total_samples) { struct rb_root tmp; struct rb_node *next; struct hist_entry *n; u64 min_callchain_hits; + u64 nr_hists = 0; min_callchain_hits = total_samples * (callchain_param.min_percent / 100); @@ -203,9 +231,11 @@ void perf_session__output_resort(struct rb_root *hists, u64 total_samples) rb_erase(&n->rb_node, hists); perf_session__insert_output_hist_entry(&tmp, n, min_callchain_hits); + ++nr_hists; } *hists = tmp; + return nr_hists; } static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin) @@ -258,8 +288,8 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, } else ret += fprintf(fp, "%s", " "); } - if (chain->sym) - ret += fprintf(fp, "%s\n", chain->sym->name); + if (chain->ms.sym) + ret += fprintf(fp, "%s\n", chain->ms.sym->name); else ret += fprintf(fp, "%p\n", (void *)(long)chain->ip); @@ -278,7 +308,7 @@ static void init_rem_hits(void) } strcpy(rem_sq_bracket->name, "[...]"); - rem_hits.sym = rem_sq_bracket; + rem_hits.ms.sym = rem_sq_bracket; } static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self, @@ -328,8 +358,6 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self, left_margin); i = 0; list_for_each_entry(chain, &child->val, list) { - if (chain->ip >= PERF_CONTEXT_MAX) - continue; ret += ipchain__fprintf_graph(fp, chain, depth, new_depth_mask, i++, new_total, @@ -368,9 +396,6 @@ static size_t callchain__fprintf_graph(FILE *fp, struct callchain_node *self, int ret = 0; list_for_each_entry(chain, &self->val, list) { - if (chain->ip >= PERF_CONTEXT_MAX) - continue; - if (!i++ && sort__first_dimension == SORT_SYM) continue; @@ -385,8 +410,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct callchain_node *self, } else ret += callchain__fprintf_left_margin(fp, left_margin); - if (chain->sym) - ret += fprintf(fp, " %s\n", chain->sym->name); + if (chain->ms.sym) + ret += fprintf(fp, " %s\n", chain->ms.sym->name); else ret += fprintf(fp, " %p\n", (void *)(long)chain->ip); } @@ -411,8 +436,8 @@ static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self, list_for_each_entry(chain, &self->val, list) { if (chain->ip >= PERF_CONTEXT_MAX) continue; - if (chain->sym) - ret += fprintf(fp, " %s\n", chain->sym->name); + if (chain->ms.sym) + ret += fprintf(fp, " %s\n", chain->ms.sym->name); else ret += fprintf(fp, " %p\n", (void *)(long)chain->ip); @@ -455,16 +480,17 @@ static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self, return ret; } -static size_t hist_entry__fprintf(struct hist_entry *self, - struct perf_session *pair_session, - bool show_displacement, - long displacement, FILE *fp, - u64 session_total) +int hist_entry__snprintf(struct hist_entry *self, + char *s, size_t size, + struct perf_session *pair_session, + bool show_displacement, + long displacement, bool color, + u64 session_total) { struct sort_entry *se; - u64 count, total; + u64 count, total, count_sys, count_us, count_guest_sys, count_guest_us; const char *sep = symbol_conf.field_sep; - size_t ret; + int ret; if (symbol_conf.exclude_other && !self->parent) return 0; @@ -472,22 +498,55 @@ static size_t hist_entry__fprintf(struct hist_entry *self, if (pair_session) { count = self->pair ? self->pair->count : 0; total = pair_session->events_stats.total; + count_sys = self->pair ? self->pair->count_sys : 0; + count_us = self->pair ? self->pair->count_us : 0; + count_guest_sys = self->pair ? self->pair->count_guest_sys : 0; + count_guest_us = self->pair ? self->pair->count_guest_us : 0; } else { count = self->count; total = session_total; + count_sys = self->count_sys; + count_us = self->count_us; + count_guest_sys = self->count_guest_sys; + count_guest_us = self->count_guest_us; } - if (total) - ret = percent_color_fprintf(fp, sep ? "%.2f" : " %6.2f%%", - (count * 100.0) / total); - else - ret = fprintf(fp, sep ? "%lld" : "%12lld ", count); + if (total) { + if (color) + ret = percent_color_snprintf(s, size, + sep ? "%.2f" : " %6.2f%%", + (count * 100.0) / total); + else + ret = snprintf(s, size, sep ? "%.2f" : " %6.2f%%", + (count * 100.0) / total); + if (symbol_conf.show_cpu_utilization) { + ret += percent_color_snprintf(s + ret, size - ret, + sep ? "%.2f" : " %6.2f%%", + (count_sys * 100.0) / total); + ret += percent_color_snprintf(s + ret, size - ret, + sep ? "%.2f" : " %6.2f%%", + (count_us * 100.0) / total); + if (perf_guest) { + ret += percent_color_snprintf(s + ret, + size - ret, + sep ? "%.2f" : " %6.2f%%", + (count_guest_sys * 100.0) / + total); + ret += percent_color_snprintf(s + ret, + size - ret, + sep ? "%.2f" : " %6.2f%%", + (count_guest_us * 100.0) / + total); + } + } + } else + ret = snprintf(s, size, sep ? "%lld" : "%12lld ", count); if (symbol_conf.show_nr_samples) { if (sep) - fprintf(fp, "%c%lld", *sep, count); + ret += snprintf(s + ret, size - ret, "%c%lld", *sep, count); else - fprintf(fp, "%11lld", count); + ret += snprintf(s + ret, size - ret, "%11lld", count); } if (pair_session) { @@ -507,9 +566,9 @@ static size_t hist_entry__fprintf(struct hist_entry *self, snprintf(bf, sizeof(bf), " "); if (sep) - ret += fprintf(fp, "%c%s", *sep, bf); + ret += snprintf(s + ret, size - ret, "%c%s", *sep, bf); else - ret += fprintf(fp, "%11.11s", bf); + ret += snprintf(s + ret, size - ret, "%11.11s", bf); if (show_displacement) { if (displacement) @@ -518,9 +577,9 @@ static size_t hist_entry__fprintf(struct hist_entry *self, snprintf(bf, sizeof(bf), " "); if (sep) - fprintf(fp, "%c%s", *sep, bf); + ret += snprintf(s + ret, size - ret, "%c%s", *sep, bf); else - fprintf(fp, "%6.6s", bf); + ret += snprintf(s + ret, size - ret, "%6.6s", bf); } } @@ -528,27 +587,41 @@ static size_t hist_entry__fprintf(struct hist_entry *self, if (se->elide) continue; - fprintf(fp, "%s", sep ?: " "); - ret += se->print(fp, self, se->width ? *se->width : 0); + ret += snprintf(s + ret, size - ret, "%s", sep ?: " "); + ret += se->se_snprintf(self, s + ret, size - ret, + se->se_width ? *se->se_width : 0); } - ret += fprintf(fp, "\n"); + return ret; +} - if (symbol_conf.use_callchain) { - int left_margin = 0; +int hist_entry__fprintf(struct hist_entry *self, + struct perf_session *pair_session, + bool show_displacement, + long displacement, FILE *fp, + u64 session_total) +{ + char bf[512]; + hist_entry__snprintf(self, bf, sizeof(bf), pair_session, + show_displacement, displacement, + true, session_total); + return fprintf(fp, "%s\n", bf); +} - if (sort__first_dimension == SORT_COMM) { - se = list_first_entry(&hist_entry__sort_list, typeof(*se), - list); - left_margin = se->width ? *se->width : 0; - left_margin -= thread__comm_len(self->thread); - } +static size_t hist_entry__fprintf_callchain(struct hist_entry *self, FILE *fp, + u64 session_total) +{ + int left_margin = 0; - hist_entry_callchain__fprintf(fp, self, session_total, - left_margin); + if (sort__first_dimension == SORT_COMM) { + struct sort_entry *se = list_first_entry(&hist_entry__sort_list, + typeof(*se), list); + left_margin = se->se_width ? *se->se_width : 0; + left_margin -= thread__comm_len(self->thread); } - return ret; + return hist_entry_callchain__fprintf(fp, self, session_total, + left_margin); } size_t perf_session__fprintf_hists(struct rb_root *hists, @@ -576,6 +649,24 @@ size_t perf_session__fprintf_hists(struct rb_root *hists, fputs(" Samples ", fp); } + if (symbol_conf.show_cpu_utilization) { + if (sep) { + ret += fprintf(fp, "%csys", *sep); + ret += fprintf(fp, "%cus", *sep); + if (perf_guest) { + ret += fprintf(fp, "%cguest sys", *sep); + ret += fprintf(fp, "%cguest us", *sep); + } + } else { + ret += fprintf(fp, " sys "); + ret += fprintf(fp, " us "); + if (perf_guest) { + ret += fprintf(fp, " guest sys "); + ret += fprintf(fp, " guest us "); + } + } + } + if (pair) { if (sep) ret += fprintf(fp, "%cDelta", *sep); @@ -594,22 +685,22 @@ size_t perf_session__fprintf_hists(struct rb_root *hists, if (se->elide) continue; if (sep) { - fprintf(fp, "%c%s", *sep, se->header); + fprintf(fp, "%c%s", *sep, se->se_header); continue; } - width = strlen(se->header); - if (se->width) { + width = strlen(se->se_header); + if (se->se_width) { if (symbol_conf.col_width_list_str) { if (col_width) { - *se->width = atoi(col_width); + *se->se_width = atoi(col_width); col_width = strchr(col_width, ','); if (col_width) ++col_width; } } - width = *se->width = max(*se->width, width); + width = *se->se_width = max(*se->se_width, width); } - fprintf(fp, " %*s", width, se->header); + fprintf(fp, " %*s", width, se->se_header); } fprintf(fp, "\n"); @@ -631,10 +722,10 @@ size_t perf_session__fprintf_hists(struct rb_root *hists, continue; fprintf(fp, " "); - if (se->width) - width = *se->width; + if (se->se_width) + width = *se->se_width; else - width = strlen(se->header); + width = strlen(se->se_header); for (i = 0; i < width; i++) fprintf(fp, "."); } @@ -655,9 +746,13 @@ print_entries: } ret += hist_entry__fprintf(h, pair, show_displacement, displacement, fp, session_total); - if (h->map == NULL && verbose > 1) { + + if (symbol_conf.use_callchain) + ret += hist_entry__fprintf_callchain(h, fp, session_total); + + if (h->ms.map == NULL && verbose > 1) { __map_groups__fprintf_maps(&h->thread->mg, - MAP__FUNCTION, fp); + MAP__FUNCTION, verbose, fp); fprintf(fp, "%.10s end\n", graph_dotted_line); } } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 16f360cce5bf..9df1c340ec92 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -12,15 +12,28 @@ struct addr_location; struct symbol; struct rb_root; +void __perf_session__add_count(struct hist_entry *he, + struct addr_location *al, + u64 count); struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists, struct addr_location *al, struct symbol *parent, u64 count, bool *hit); extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *); extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *); +int hist_entry__fprintf(struct hist_entry *self, + struct perf_session *pair_session, + bool show_displacement, + long displacement, FILE *fp, + u64 session_total); +int hist_entry__snprintf(struct hist_entry *self, + char *bf, size_t size, + struct perf_session *pair_session, + bool show_displacement, long displacement, + bool color, u64 session_total); void hist_entry__free(struct hist_entry *); -void perf_session__output_resort(struct rb_root *hists, u64 total_samples); +u64 perf_session__output_resort(struct rb_root *hists, u64 total_samples); void perf_session__collapse_resort(struct rb_root *hists); size_t perf_session__fprintf_hists(struct rb_root *hists, struct perf_session *pair, diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h index dfb0713ed47f..791f9dd27ebf 100644 --- a/tools/perf/util/include/linux/compiler.h +++ b/tools/perf/util/include/linux/compiler.h @@ -7,4 +7,6 @@ #define __user #define __attribute_const__ +#define __used __attribute__((__unused__)) + #endif diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h index f2611655ab51..388ab1bfd114 100644 --- a/tools/perf/util/include/linux/kernel.h +++ b/tools/perf/util/include/linux/kernel.h @@ -85,16 +85,19 @@ simple_strtoul(const char *nptr, char **endptr, int base) return strtoul(nptr, endptr, base); } +int eprintf(int level, + const char *fmt, ...) __attribute__((format(printf, 2, 3))); + #ifndef pr_fmt #define pr_fmt(fmt) fmt #endif #define pr_err(fmt, ...) \ - do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0) + eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) #define pr_warning(fmt, ...) \ - do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0) + eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) #define pr_info(fmt, ...) \ - do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0) + eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) #define pr_debug(fmt, ...) \ eprintf(1, pr_fmt(fmt), ##__VA_ARGS__) #define pr_debugN(n, fmt, ...) \ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index e509cd59c67d..7facd016ec97 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -1,9 +1,11 @@ -#include "event.h" #include "symbol.h" +#include <errno.h> +#include <limits.h> #include <stdlib.h> #include <string.h> #include <stdio.h> -#include "debug.h" +#include <unistd.h> +#include "map.h" const char *map_type__name[MAP__NR_TYPES] = { [MAP__FUNCTION] = "Functions", @@ -36,15 +38,16 @@ void map__init(struct map *self, enum map_type type, self->map_ip = map__map_ip; self->unmap_ip = map__unmap_ip; RB_CLEAR_NODE(&self->rb_node); + self->groups = NULL; } -struct map *map__new(struct mmap_event *event, enum map_type type, - char *cwd, int cwdlen) +struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, + u64 pgoff, u32 pid, char *filename, + enum map_type type, char *cwd, int cwdlen) { struct map *self = malloc(sizeof(*self)); if (self != NULL) { - const char *filename = event->filename; char newfilename[PATH_MAX]; struct dso *dso; int anon; @@ -62,16 +65,15 @@ struct map *map__new(struct mmap_event *event, enum map_type type, anon = is_anon_memory(filename); if (anon) { - snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", event->pid); + snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid); filename = newfilename; } - dso = dsos__findnew(filename); + dso = __dsos__findnew(dsos__list, filename); if (dso == NULL) goto out_delete; - map__init(self, type, event->start, event->start + event->len, - event->pgoff, dso); + map__init(self, type, start, start + len, pgoff, dso); if (anon) { set_identity: @@ -235,3 +237,409 @@ u64 map__objdump_2ip(struct map *map, u64 addr) map->unmap_ip(map, addr); /* RIP -> IP */ return ip; } + +void map_groups__init(struct map_groups *self) +{ + int i; + for (i = 0; i < MAP__NR_TYPES; ++i) { + self->maps[i] = RB_ROOT; + INIT_LIST_HEAD(&self->removed_maps[i]); + } + self->this_kerninfo = NULL; +} + +void map_groups__flush(struct map_groups *self) +{ + int type; + + for (type = 0; type < MAP__NR_TYPES; type++) { + struct rb_root *root = &self->maps[type]; + struct rb_node *next = rb_first(root); + + while (next) { + struct map *pos = rb_entry(next, struct map, rb_node); + next = rb_next(&pos->rb_node); + rb_erase(&pos->rb_node, root); + /* + * We may have references to this map, for + * instance in some hist_entry instances, so + * just move them to a separate list. + */ + list_add_tail(&pos->node, &self->removed_maps[pos->type]); + } + } +} + +struct symbol *map_groups__find_symbol(struct map_groups *self, + enum map_type type, u64 addr, + struct map **mapp, + symbol_filter_t filter) +{ + struct map *map = map_groups__find(self, type, addr); + + if (map != NULL) { + if (mapp != NULL) + *mapp = map; + return map__find_symbol(map, map->map_ip(map, addr), filter); + } + + return NULL; +} + +struct symbol *map_groups__find_symbol_by_name(struct map_groups *self, + enum map_type type, + const char *name, + struct map **mapp, + symbol_filter_t filter) +{ + struct rb_node *nd; + + for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) { + struct map *pos = rb_entry(nd, struct map, rb_node); + struct symbol *sym = map__find_symbol_by_name(pos, name, filter); + + if (sym == NULL) + continue; + if (mapp != NULL) + *mapp = pos; + return sym; + } + + return NULL; +} + +size_t __map_groups__fprintf_maps(struct map_groups *self, + enum map_type type, int verbose, FILE *fp) +{ + size_t printed = fprintf(fp, "%s:\n", map_type__name[type]); + struct rb_node *nd; + + for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) { + struct map *pos = rb_entry(nd, struct map, rb_node); + printed += fprintf(fp, "Map:"); + printed += map__fprintf(pos, fp); + if (verbose > 2) { + printed += dso__fprintf(pos->dso, type, fp); + printed += fprintf(fp, "--\n"); + } + } + + return printed; +} + +size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp) +{ + size_t printed = 0, i; + for (i = 0; i < MAP__NR_TYPES; ++i) + printed += __map_groups__fprintf_maps(self, i, verbose, fp); + return printed; +} + +static size_t __map_groups__fprintf_removed_maps(struct map_groups *self, + enum map_type type, + int verbose, FILE *fp) +{ + struct map *pos; + size_t printed = 0; + + list_for_each_entry(pos, &self->removed_maps[type], node) { + printed += fprintf(fp, "Map:"); + printed += map__fprintf(pos, fp); + if (verbose > 1) { + printed += dso__fprintf(pos->dso, type, fp); + printed += fprintf(fp, "--\n"); + } + } + return printed; +} + +static size_t map_groups__fprintf_removed_maps(struct map_groups *self, + int verbose, FILE *fp) +{ + size_t printed = 0, i; + for (i = 0; i < MAP__NR_TYPES; ++i) + printed += __map_groups__fprintf_removed_maps(self, i, verbose, fp); + return printed; +} + +size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp) +{ + size_t printed = map_groups__fprintf_maps(self, verbose, fp); + printed += fprintf(fp, "Removed maps:\n"); + return printed + map_groups__fprintf_removed_maps(self, verbose, fp); +} + +int map_groups__fixup_overlappings(struct map_groups *self, struct map *map, + int verbose, FILE *fp) +{ + struct rb_root *root = &self->maps[map->type]; + struct rb_node *next = rb_first(root); + + while (next) { + struct map *pos = rb_entry(next, struct map, rb_node); + next = rb_next(&pos->rb_node); + + if (!map__overlap(pos, map)) + continue; + + if (verbose >= 2) { + fputs("overlapping maps:\n", fp); + map__fprintf(map, fp); + map__fprintf(pos, fp); + } + + rb_erase(&pos->rb_node, root); + /* + * We may have references to this map, for instance in some + * hist_entry instances, so just move them to a separate + * list. + */ + list_add_tail(&pos->node, &self->removed_maps[map->type]); + /* + * Now check if we need to create new maps for areas not + * overlapped by the new map: + */ + if (map->start > pos->start) { + struct map *before = map__clone(pos); + + if (before == NULL) + return -ENOMEM; + + before->end = map->start - 1; + map_groups__insert(self, before); + if (verbose >= 2) + map__fprintf(before, fp); + } + + if (map->end < pos->end) { + struct map *after = map__clone(pos); + + if (after == NULL) + return -ENOMEM; + + after->start = map->end + 1; + map_groups__insert(self, after); + if (verbose >= 2) + map__fprintf(after, fp); + } + } + + return 0; +} + +/* + * XXX This should not really _copy_ te maps, but refcount them. + */ +int map_groups__clone(struct map_groups *self, + struct map_groups *parent, enum map_type type) +{ + struct rb_node *nd; + for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) { + struct map *map = rb_entry(nd, struct map, rb_node); + struct map *new = map__clone(map); + if (new == NULL) + return -ENOMEM; + map_groups__insert(self, new); + } + return 0; +} + +static u64 map__reloc_map_ip(struct map *map, u64 ip) +{ + return ip + (s64)map->pgoff; +} + +static u64 map__reloc_unmap_ip(struct map *map, u64 ip) +{ + return ip - (s64)map->pgoff; +} + +void map__reloc_vmlinux(struct map *self) +{ + struct kmap *kmap = map__kmap(self); + s64 reloc; + + if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr) + return; + + reloc = (kmap->ref_reloc_sym->unrelocated_addr - + kmap->ref_reloc_sym->addr); + + if (!reloc) + return; + + self->map_ip = map__reloc_map_ip; + self->unmap_ip = map__reloc_unmap_ip; + self->pgoff = reloc; +} + +void maps__insert(struct rb_root *maps, struct map *map) +{ + struct rb_node **p = &maps->rb_node; + struct rb_node *parent = NULL; + const u64 ip = map->start; + struct map *m; + + while (*p != NULL) { + parent = *p; + m = rb_entry(parent, struct map, rb_node); + if (ip < m->start) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&map->rb_node, parent, p); + rb_insert_color(&map->rb_node, maps); +} + +struct map *maps__find(struct rb_root *maps, u64 ip) +{ + struct rb_node **p = &maps->rb_node; + struct rb_node *parent = NULL; + struct map *m; + + while (*p != NULL) { + parent = *p; + m = rb_entry(parent, struct map, rb_node); + if (ip < m->start) + p = &(*p)->rb_left; + else if (ip > m->end) + p = &(*p)->rb_right; + else + return m; + } + + return NULL; +} + +struct kernel_info *add_new_kernel_info(struct rb_root *kerninfo_root, + pid_t pid, const char *root_dir) +{ + struct rb_node **p = &kerninfo_root->rb_node; + struct rb_node *parent = NULL; + struct kernel_info *kerninfo, *pos; + + kerninfo = malloc(sizeof(struct kernel_info)); + if (!kerninfo) + return NULL; + + kerninfo->pid = pid; + map_groups__init(&kerninfo->kmaps); + kerninfo->root_dir = strdup(root_dir); + RB_CLEAR_NODE(&kerninfo->rb_node); + INIT_LIST_HEAD(&kerninfo->dsos__user); + INIT_LIST_HEAD(&kerninfo->dsos__kernel); + kerninfo->kmaps.this_kerninfo = kerninfo; + + while (*p != NULL) { + parent = *p; + pos = rb_entry(parent, struct kernel_info, rb_node); + if (pid < pos->pid) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&kerninfo->rb_node, parent, p); + rb_insert_color(&kerninfo->rb_node, kerninfo_root); + + return kerninfo; +} + +struct kernel_info *kerninfo__find(struct rb_root *kerninfo_root, pid_t pid) +{ + struct rb_node **p = &kerninfo_root->rb_node; + struct rb_node *parent = NULL; + struct kernel_info *kerninfo; + struct kernel_info *default_kerninfo = NULL; + + while (*p != NULL) { + parent = *p; + kerninfo = rb_entry(parent, struct kernel_info, rb_node); + if (pid < kerninfo->pid) + p = &(*p)->rb_left; + else if (pid > kerninfo->pid) + p = &(*p)->rb_right; + else + return kerninfo; + if (!kerninfo->pid) + default_kerninfo = kerninfo; + } + + return default_kerninfo; +} + +struct kernel_info *kerninfo__findhost(struct rb_root *kerninfo_root) +{ + struct rb_node **p = &kerninfo_root->rb_node; + struct rb_node *parent = NULL; + struct kernel_info *kerninfo; + pid_t pid = HOST_KERNEL_ID; + + while (*p != NULL) { + parent = *p; + kerninfo = rb_entry(parent, struct kernel_info, rb_node); + if (pid < kerninfo->pid) + p = &(*p)->rb_left; + else if (pid > kerninfo->pid) + p = &(*p)->rb_right; + else + return kerninfo; + } + + return NULL; +} + +struct kernel_info *kerninfo__findnew(struct rb_root *kerninfo_root, pid_t pid) +{ + char path[PATH_MAX]; + const char *root_dir; + int ret; + struct kernel_info *kerninfo = kerninfo__find(kerninfo_root, pid); + + if (!kerninfo || kerninfo->pid != pid) { + if (pid == HOST_KERNEL_ID || pid == DEFAULT_GUEST_KERNEL_ID) + root_dir = ""; + else { + if (!symbol_conf.guestmount) + goto out; + sprintf(path, "%s/%d", symbol_conf.guestmount, pid); + ret = access(path, R_OK); + if (ret) { + pr_err("Can't access file %s\n", path); + goto out; + } + root_dir = path; + } + kerninfo = add_new_kernel_info(kerninfo_root, pid, root_dir); + } + +out: + return kerninfo; +} + +void kerninfo__process_allkernels(struct rb_root *kerninfo_root, + process_kernel_info process, + void *data) +{ + struct rb_node *nd; + + for (nd = rb_first(kerninfo_root); nd; nd = rb_next(nd)) { + struct kernel_info *pos = rb_entry(nd, struct kernel_info, + rb_node); + process(pos, data); + } +} + +char *kern_mmap_name(struct kernel_info *kerninfo, char *buff) +{ + if (is_host_kernel(kerninfo)) + sprintf(buff, "[%s]", "kernel.kallsyms"); + else if (is_default_guest(kerninfo)) + sprintf(buff, "[%s]", "guest.kernel.kallsyms"); + else + sprintf(buff, "[%s.%d]", "guest.kernel.kallsyms", kerninfo->pid); + + return buff; +} diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index b756368076c6..30d38d634e09 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -4,7 +4,8 @@ #include <linux/compiler.h> #include <linux/list.h> #include <linux/rbtree.h> -#include <linux/types.h> +#include <stdio.h> +#include "types.h" enum map_type { MAP__FUNCTION = 0, @@ -18,6 +19,7 @@ extern const char *map_type__name[MAP__NR_TYPES]; struct dso; struct ref_reloc_sym; struct map_groups; +struct kernel_info; struct map { union { @@ -35,6 +37,7 @@ struct map { u64 (*unmap_ip)(struct map *, u64); struct dso *dso; + struct map_groups *groups; }; struct kmap { @@ -42,6 +45,26 @@ struct kmap { struct map_groups *kmaps; }; +struct map_groups { + struct rb_root maps[MAP__NR_TYPES]; + struct list_head removed_maps[MAP__NR_TYPES]; + struct kernel_info *this_kerninfo; +}; + +/* Native host kernel uses -1 as pid index in kernel_info */ +#define HOST_KERNEL_ID (-1) +#define DEFAULT_GUEST_KERNEL_ID (0) + +struct kernel_info { + struct rb_node rb_node; + pid_t pid; + char *root_dir; + struct list_head dsos__user; + struct list_head dsos__kernel; + struct map_groups kmaps; + struct map *vmlinux_maps[MAP__NR_TYPES]; +}; + static inline struct kmap *map__kmap(struct map *self) { return (struct kmap *)(self + 1); @@ -68,14 +91,14 @@ u64 map__rip_2objdump(struct map *map, u64 rip); u64 map__objdump_2ip(struct map *map, u64 addr); struct symbol; -struct mmap_event; typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); void map__init(struct map *self, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); -struct map *map__new(struct mmap_event *event, enum map_type, - char *cwd, int cwdlen); +struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, + u64 pgoff, u32 pid, char *filename, + enum map_type type, char *cwd, int cwdlen); void map__delete(struct map *self); struct map *map__clone(struct map *self); int map__overlap(struct map *l, struct map *r); @@ -91,4 +114,94 @@ void map__fixup_end(struct map *self); void map__reloc_vmlinux(struct map *self); +size_t __map_groups__fprintf_maps(struct map_groups *self, + enum map_type type, int verbose, FILE *fp); +void maps__insert(struct rb_root *maps, struct map *map); +struct map *maps__find(struct rb_root *maps, u64 addr); +void map_groups__init(struct map_groups *self); +int map_groups__clone(struct map_groups *self, + struct map_groups *parent, enum map_type type); +size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp); +size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp); + +struct kernel_info *add_new_kernel_info(struct rb_root *kerninfo_root, + pid_t pid, const char *root_dir); +struct kernel_info *kerninfo__find(struct rb_root *kerninfo_root, pid_t pid); +struct kernel_info *kerninfo__findnew(struct rb_root *kerninfo_root, pid_t pid); +struct kernel_info *kerninfo__findhost(struct rb_root *kerninfo_root); +char *kern_mmap_name(struct kernel_info *kerninfo, char *buff); + +/* + * Default guest kernel is defined by parameter --guestkallsyms + * and --guestmodules + */ +static inline int is_default_guest(struct kernel_info *kerninfo) +{ + if (!kerninfo) + return 0; + return kerninfo->pid == DEFAULT_GUEST_KERNEL_ID; +} + +static inline int is_host_kernel(struct kernel_info *kerninfo) +{ + if (!kerninfo) + return 0; + return kerninfo->pid == HOST_KERNEL_ID; +} + +typedef void (*process_kernel_info)(struct kernel_info *kerninfo, void *data); +void kerninfo__process_allkernels(struct rb_root *kerninfo_root, + process_kernel_info process, + void *data); + +static inline void map_groups__insert(struct map_groups *self, struct map *map) +{ + maps__insert(&self->maps[map->type], map); + map->groups = self; +} + +static inline struct map *map_groups__find(struct map_groups *self, + enum map_type type, u64 addr) +{ + return maps__find(&self->maps[type], addr); +} + +struct symbol *map_groups__find_symbol(struct map_groups *self, + enum map_type type, u64 addr, + struct map **mapp, + symbol_filter_t filter); + +struct symbol *map_groups__find_symbol_by_name(struct map_groups *self, + enum map_type type, + const char *name, + struct map **mapp, + symbol_filter_t filter); + +static inline +struct symbol *map_groups__find_function(struct map_groups *self, u64 addr, + struct map **mapp, symbol_filter_t filter) +{ + return map_groups__find_symbol(self, MAP__FUNCTION, addr, mapp, filter); +} + +static inline +struct symbol *map_groups__find_function_by_name(struct map_groups *self, + const char *name, struct map **mapp, + symbol_filter_t filter) +{ + return map_groups__find_symbol_by_name(self, MAP__FUNCTION, name, mapp, filter); +} + +int map_groups__fixup_overlappings(struct map_groups *self, struct map *map, + int verbose, FILE *fp); + +struct map *map_groups__find_by_name(struct map_groups *self, + enum map_type type, const char *name); +struct map *map_groups__new_module(struct map_groups *self, + u64 start, + const char *filename, + struct kernel_info *kerninfo); + +void map_groups__flush(struct map_groups *self); + #endif /* __PERF_MAP_H */ diff --git a/tools/perf/util/newt.c b/tools/perf/util/newt.c new file mode 100644 index 000000000000..7a123a94e3fc --- /dev/null +++ b/tools/perf/util/newt.c @@ -0,0 +1,725 @@ +#define _GNU_SOURCE +#include <stdio.h> +#undef _GNU_SOURCE + +#include <stdlib.h> +#include <newt.h> +#include <sys/ttydefaults.h> + +#include "cache.h" +#include "hist.h" +#include "session.h" +#include "sort.h" +#include "symbol.h" + +struct ui_progress { + newtComponent form, scale; +}; + +struct ui_progress *ui_progress__new(const char *title, u64 total) +{ + struct ui_progress *self = malloc(sizeof(*self)); + + if (self != NULL) { + int cols; + newtGetScreenSize(&cols, NULL); + cols -= 4; + newtCenteredWindow(cols, 1, title); + self->form = newtForm(NULL, NULL, 0); + if (self->form == NULL) + goto out_free_self; + self->scale = newtScale(0, 0, cols, total); + if (self->scale == NULL) + goto out_free_form; + newtFormAddComponents(self->form, self->scale, NULL); + newtRefresh(); + } + + return self; + +out_free_form: + newtFormDestroy(self->form); +out_free_self: + free(self); + return NULL; +} + +void ui_progress__update(struct ui_progress *self, u64 curr) +{ + newtScaleSet(self->scale, curr); + newtRefresh(); +} + +void ui_progress__delete(struct ui_progress *self) +{ + newtFormDestroy(self->form); + newtPopWindow(); + free(self); +} + +static char browser__last_msg[1024]; + +int browser__show_help(const char *format, va_list ap) +{ + int ret; + static int backlog; + + ret = vsnprintf(browser__last_msg + backlog, + sizeof(browser__last_msg) - backlog, format, ap); + backlog += ret; + + if (browser__last_msg[backlog - 1] == '\n') { + newtPopHelpLine(); + newtPushHelpLine(browser__last_msg); + newtRefresh(); + backlog = 0; + } + + return ret; +} + +static void newt_form__set_exit_keys(newtComponent self) +{ + newtFormAddHotKey(self, NEWT_KEY_ESCAPE); + newtFormAddHotKey(self, 'Q'); + newtFormAddHotKey(self, 'q'); + newtFormAddHotKey(self, CTRL('c')); +} + +static newtComponent newt_form__new(void) +{ + newtComponent self = newtForm(NULL, NULL, 0); + if (self) + newt_form__set_exit_keys(self); + return self; +} + +static int popup_menu(int argc, char * const argv[]) +{ + struct newtExitStruct es; + int i, rc = -1, max_len = 5; + newtComponent listbox, form = newt_form__new(); + + if (form == NULL) + return -1; + + listbox = newtListbox(0, 0, argc, NEWT_FLAG_RETURNEXIT); + if (listbox == NULL) + goto out_destroy_form; + + newtFormAddComponents(form, listbox, NULL); + + for (i = 0; i < argc; ++i) { + int len = strlen(argv[i]); + if (len > max_len) + max_len = len; + if (newtListboxAddEntry(listbox, argv[i], (void *)(long)i)) + goto out_destroy_form; + } + + newtCenteredWindow(max_len, argc, NULL); + newtFormRun(form, &es); + rc = newtListboxGetCurrent(listbox) - NULL; + if (es.reason == NEWT_EXIT_HOTKEY) + rc = -1; + newtPopWindow(); +out_destroy_form: + newtFormDestroy(form); + return rc; +} + +static bool dialog_yesno(const char *msg) +{ + /* newtWinChoice should really be accepting const char pointers... */ + char yes[] = "Yes", no[] = "No"; + return newtWinChoice(NULL, yes, no, (char *)msg) == 1; +} + +/* + * When debugging newt problems it was useful to be able to "unroll" + * the calls to newtCheckBoxTreeAdd{Array,Item}, so that we can generate + * a source file with the sequence of calls to these methods, to then + * tweak the arrays to get the intended results, so I'm keeping this code + * here, may be useful again in the future. + */ +#undef NEWT_DEBUG + +static void newt_checkbox_tree__add(newtComponent tree, const char *str, + void *priv, int *indexes) +{ +#ifdef NEWT_DEBUG + /* Print the newtCheckboxTreeAddArray to tinker with its index arrays */ + int i = 0, len = 40 - strlen(str); + + fprintf(stderr, + "\tnewtCheckboxTreeAddItem(tree, %*.*s\"%s\", (void *)%p, 0, ", + len, len, " ", str, priv); + while (indexes[i] != NEWT_ARG_LAST) { + if (indexes[i] != NEWT_ARG_APPEND) + fprintf(stderr, " %d,", indexes[i]); + else + fprintf(stderr, " %s,", "NEWT_ARG_APPEND"); + ++i; + } + fprintf(stderr, " %s", " NEWT_ARG_LAST);\n"); + fflush(stderr); +#endif + newtCheckboxTreeAddArray(tree, str, priv, 0, indexes); +} + +static char *callchain_list__sym_name(struct callchain_list *self, + char *bf, size_t bfsize) +{ + if (self->ms.sym) + return self->ms.sym->name; + + snprintf(bf, bfsize, "%#Lx", self->ip); + return bf; +} + +static void __callchain__append_graph_browser(struct callchain_node *self, + newtComponent tree, u64 total, + int *indexes, int depth) +{ + struct rb_node *node; + u64 new_total, remaining; + int idx = 0; + + if (callchain_param.mode == CHAIN_GRAPH_REL) + new_total = self->children_hit; + else + new_total = total; + + remaining = new_total; + node = rb_first(&self->rb_root); + while (node) { + struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); + struct rb_node *next = rb_next(node); + u64 cumul = cumul_hits(child); + struct callchain_list *chain; + int first = true, printed = 0; + int chain_idx = -1; + remaining -= cumul; + + indexes[depth] = NEWT_ARG_APPEND; + indexes[depth + 1] = NEWT_ARG_LAST; + + list_for_each_entry(chain, &child->val, list) { + char ipstr[BITS_PER_LONG / 4 + 1], + *alloc_str = NULL; + const char *str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); + + if (first) { + double percent = cumul * 100.0 / new_total; + + first = false; + if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0) + str = "Not enough memory!"; + else + str = alloc_str; + } else { + indexes[depth] = idx; + indexes[depth + 1] = NEWT_ARG_APPEND; + indexes[depth + 2] = NEWT_ARG_LAST; + ++chain_idx; + } + newt_checkbox_tree__add(tree, str, &chain->ms, indexes); + free(alloc_str); + ++printed; + } + + indexes[depth] = idx; + if (chain_idx != -1) + indexes[depth + 1] = chain_idx; + if (printed != 0) + ++idx; + __callchain__append_graph_browser(child, tree, new_total, indexes, + depth + (chain_idx != -1 ? 2 : 1)); + node = next; + } +} + +static void callchain__append_graph_browser(struct callchain_node *self, + newtComponent tree, u64 total, + int *indexes, int parent_idx) +{ + struct callchain_list *chain; + int i = 0; + + indexes[1] = NEWT_ARG_APPEND; + indexes[2] = NEWT_ARG_LAST; + + list_for_each_entry(chain, &self->val, list) { + char ipstr[BITS_PER_LONG / 4 + 1], *str; + + if (chain->ip >= PERF_CONTEXT_MAX) + continue; + + if (!i++ && sort__first_dimension == SORT_SYM) + continue; + + str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); + newt_checkbox_tree__add(tree, str, &chain->ms, indexes); + } + + indexes[1] = parent_idx; + indexes[2] = NEWT_ARG_APPEND; + indexes[3] = NEWT_ARG_LAST; + __callchain__append_graph_browser(self, tree, total, indexes, 2); +} + +static void hist_entry__append_callchain_browser(struct hist_entry *self, + newtComponent tree, u64 total, int parent_idx) +{ + struct rb_node *rb_node; + int indexes[1024] = { [0] = parent_idx, }; + int idx = 0; + struct callchain_node *chain; + + rb_node = rb_first(&self->sorted_chain); + while (rb_node) { + chain = rb_entry(rb_node, struct callchain_node, rb_node); + switch (callchain_param.mode) { + case CHAIN_FLAT: + break; + case CHAIN_GRAPH_ABS: /* falldown */ + case CHAIN_GRAPH_REL: + callchain__append_graph_browser(chain, tree, total, indexes, idx++); + break; + case CHAIN_NONE: + default: + break; + } + rb_node = rb_next(rb_node); + } +} + +static size_t hist_entry__append_browser(struct hist_entry *self, + newtComponent tree, u64 total) +{ + char s[256]; + size_t ret; + + if (symbol_conf.exclude_other && !self->parent) + return 0; + + ret = hist_entry__snprintf(self, s, sizeof(s), NULL, + false, 0, false, total); + if (symbol_conf.use_callchain) { + int indexes[2]; + + indexes[0] = NEWT_ARG_APPEND; + indexes[1] = NEWT_ARG_LAST; + newt_checkbox_tree__add(tree, s, &self->ms, indexes); + } else + newtListboxAppendEntry(tree, s, &self->ms); + + return ret; +} + +static void map_symbol__annotate_browser(const struct map_symbol *self, + const char *input_name) +{ + FILE *fp; + int cols, rows; + newtComponent form, tree; + struct newtExitStruct es; + char *str; + size_t line_len, max_line_len = 0; + size_t max_usable_width; + char *line = NULL; + + if (self->sym == NULL) + return; + + if (asprintf(&str, "perf annotate -i \"%s\" -d \"%s\" %s 2>&1 | expand", + input_name, self->map->dso->name, self->sym->name) < 0) + return; + + fp = popen(str, "r"); + if (fp == NULL) + goto out_free_str; + + newtPushHelpLine("Press ESC to exit"); + newtGetScreenSize(&cols, &rows); + tree = newtListbox(0, 0, rows - 5, NEWT_FLAG_SCROLL); + + while (!feof(fp)) { + if (getline(&line, &line_len, fp) < 0 || !line_len) + break; + while (line_len != 0 && isspace(line[line_len - 1])) + line[--line_len] = '\0'; + + if (line_len > max_line_len) + max_line_len = line_len; + newtListboxAppendEntry(tree, line, NULL); + } + fclose(fp); + free(line); + + max_usable_width = cols - 22; + if (max_line_len > max_usable_width) + max_line_len = max_usable_width; + + newtListboxSetWidth(tree, max_line_len); + + newtCenteredWindow(max_line_len + 2, rows - 5, self->sym->name); + form = newt_form__new(); + newtFormAddComponents(form, tree, NULL); + + newtFormRun(form, &es); + newtFormDestroy(form); + newtPopWindow(); + newtPopHelpLine(); +out_free_str: + free(str); +} + +static const void *newt__symbol_tree_get_current(newtComponent self) +{ + if (symbol_conf.use_callchain) + return newtCheckboxTreeGetCurrent(self); + return newtListboxGetCurrent(self); +} + +static void hist_browser__selection(newtComponent self, void *data) +{ + const struct map_symbol **symbol_ptr = data; + *symbol_ptr = newt__symbol_tree_get_current(self); +} + +struct hist_browser { + newtComponent form, tree; + const struct map_symbol *selection; +}; + +static struct hist_browser *hist_browser__new(void) +{ + struct hist_browser *self = malloc(sizeof(*self)); + + if (self != NULL) + self->form = NULL; + + return self; +} + +static void hist_browser__delete(struct hist_browser *self) +{ + newtFormDestroy(self->form); + newtPopWindow(); + free(self); +} + +static int hist_browser__populate(struct hist_browser *self, struct rb_root *hists, + u64 nr_hists, u64 session_total, const char *title) +{ + int max_len = 0, idx, cols, rows; + struct ui_progress *progress; + struct rb_node *nd; + u64 curr_hist = 0; + char seq[] = "."; + char str[256]; + + if (self->form) { + newtFormDestroy(self->form); + newtPopWindow(); + } + + snprintf(str, sizeof(str), "Samples: %Ld ", + session_total); + newtDrawRootText(0, 0, str); + + newtGetScreenSize(NULL, &rows); + + if (symbol_conf.use_callchain) + self->tree = newtCheckboxTreeMulti(0, 0, rows - 5, seq, + NEWT_FLAG_SCROLL); + else + self->tree = newtListbox(0, 0, rows - 5, + (NEWT_FLAG_SCROLL | + NEWT_FLAG_RETURNEXIT)); + + newtComponentAddCallback(self->tree, hist_browser__selection, + &self->selection); + + progress = ui_progress__new("Adding entries to the browser...", nr_hists); + if (progress == NULL) + return -1; + + idx = 0; + for (nd = rb_first(hists); nd; nd = rb_next(nd)) { + struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + int len; + + if (h->filtered) + continue; + + len = hist_entry__append_browser(h, self->tree, session_total); + if (len > max_len) + max_len = len; + if (symbol_conf.use_callchain) + hist_entry__append_callchain_browser(h, self->tree, + session_total, idx++); + ++curr_hist; + if (curr_hist % 5) + ui_progress__update(progress, curr_hist); + } + + ui_progress__delete(progress); + + newtGetScreenSize(&cols, &rows); + + if (max_len > cols) + max_len = cols - 3; + + if (!symbol_conf.use_callchain) + newtListboxSetWidth(self->tree, max_len); + + newtCenteredWindow(max_len + (symbol_conf.use_callchain ? 5 : 0), + rows - 5, title); + self->form = newt_form__new(); + if (self->form == NULL) + return -1; + + newtFormAddHotKey(self->form, 'A'); + newtFormAddHotKey(self->form, 'a'); + newtFormAddHotKey(self->form, NEWT_KEY_RIGHT); + newtFormAddComponents(self->form, self->tree, NULL); + self->selection = newt__symbol_tree_get_current(self->tree); + + return 0; +} + +enum hist_filter { + HIST_FILTER__DSO, + HIST_FILTER__THREAD, +}; + +static u64 hists__filter_by_dso(struct rb_root *hists, const struct dso *dso, + u64 *session_total) +{ + struct rb_node *nd; + u64 nr_hists = 0; + + *session_total = 0; + + for (nd = rb_first(hists); nd; nd = rb_next(nd)) { + struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + + if (dso != NULL && (h->ms.map == NULL || h->ms.map->dso != dso)) { + h->filtered |= (1 << HIST_FILTER__DSO); + continue; + } + h->filtered &= ~(1 << HIST_FILTER__DSO); + ++nr_hists; + *session_total += h->count; + } + + return nr_hists; +} + +static u64 hists__filter_by_thread(struct rb_root *hists, const struct thread *thread, + u64 *session_total) +{ + struct rb_node *nd; + u64 nr_hists = 0; + + *session_total = 0; + + for (nd = rb_first(hists); nd; nd = rb_next(nd)) { + struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + + if (thread != NULL && h->thread != thread) { + h->filtered |= (1 << HIST_FILTER__THREAD); + continue; + } + h->filtered &= ~(1 << HIST_FILTER__THREAD); + ++nr_hists; + *session_total += h->count; + } + + return nr_hists; +} + +static struct thread *hist_browser__selected_thread(struct hist_browser *self) +{ + int *indexes; + + if (!symbol_conf.use_callchain) + goto out; + + indexes = newtCheckboxTreeFindItem(self->tree, (void *)self->selection); + if (indexes) { + bool is_hist_entry = indexes[1] == NEWT_ARG_LAST; + free(indexes); + if (is_hist_entry) + goto out; + } + return NULL; +out: + return *(struct thread **)(self->selection + 1); +} + +static int hist_browser__title(char *bf, size_t size, const char *input_name, + const struct dso *dso, const struct thread *thread) +{ + int printed = 0; + + if (thread) + printed += snprintf(bf + printed, size - printed, + "Thread: %s(%d)", + (thread->comm_set ? thread->comm : ""), + thread->pid); + if (dso) + printed += snprintf(bf + printed, size - printed, + "%sDSO: %s", thread ? " " : "", + dso->short_name); + return printed ?: snprintf(bf, size, "Report: %s", input_name); +} + +int perf_session__browse_hists(struct rb_root *hists, u64 nr_hists, + u64 session_total, const char *helpline, + const char *input_name) +{ + struct hist_browser *browser = hist_browser__new(); + const struct thread *thread_filter = NULL; + const struct dso *dso_filter = NULL; + struct newtExitStruct es; + char msg[160]; + int err = -1; + + if (browser == NULL) + return -1; + + newtPushHelpLine(helpline); + + hist_browser__title(msg, sizeof(msg), input_name, + dso_filter, thread_filter); + if (hist_browser__populate(browser, hists, nr_hists, session_total, msg) < 0) + goto out; + + while (1) { + const struct thread *thread; + const struct dso *dso; + char *options[16]; + int nr_options = 0, choice = 0, i, + annotate = -2, zoom_dso = -2, zoom_thread = -2; + + newtFormRun(browser->form, &es); + if (es.reason == NEWT_EXIT_HOTKEY) { + if (toupper(es.u.key) == 'A') + goto do_annotate; + if (es.u.key == NEWT_KEY_ESCAPE || + toupper(es.u.key) == 'Q' || + es.u.key == CTRL('c')) { + if (dialog_yesno("Do you really want to exit?")) + break; + else + continue; + } + } + + if (browser->selection->sym != NULL && + asprintf(&options[nr_options], "Annotate %s", + browser->selection->sym->name) > 0) + annotate = nr_options++; + + thread = hist_browser__selected_thread(browser); + if (thread != NULL && + asprintf(&options[nr_options], "Zoom %s %s(%d) thread", + (thread_filter ? "out of" : "into"), + (thread->comm_set ? thread->comm : ""), + thread->pid) > 0) + zoom_thread = nr_options++; + + dso = browser->selection->map ? browser->selection->map->dso : NULL; + if (dso != NULL && + asprintf(&options[nr_options], "Zoom %s %s DSO", + (dso_filter ? "out of" : "into"), + (dso->kernel ? "the Kernel" : dso->short_name)) > 0) + zoom_dso = nr_options++; + + options[nr_options++] = (char *)"Exit"; + + choice = popup_menu(nr_options, options); + + for (i = 0; i < nr_options - 1; ++i) + free(options[i]); + + if (choice == nr_options - 1) + break; + + if (choice == -1) + continue; +do_annotate: + if (choice == annotate) { + if (browser->selection->map->dso->origin == DSO__ORIG_KERNEL) { + newtPopHelpLine(); + newtPushHelpLine("No vmlinux file found, can't " + "annotate with just a " + "kallsyms file"); + continue; + } + map_symbol__annotate_browser(browser->selection, input_name); + } else if (choice == zoom_dso) { + if (dso_filter) { + newtPopHelpLine(); + dso_filter = NULL; + } else { + snprintf(msg, sizeof(msg), + "To zoom out press -> + \"Zoom out of %s DSO\"", + dso->kernel ? "the Kernel" : dso->short_name); + newtPushHelpLine(msg); + dso_filter = dso; + } + nr_hists = hists__filter_by_dso(hists, dso_filter, &session_total); + hist_browser__title(msg, sizeof(msg), input_name, + dso_filter, thread_filter); + if (hist_browser__populate(browser, hists, nr_hists, session_total, msg) < 0) + goto out; + } else if (choice == zoom_thread) { + if (thread_filter) { + newtPopHelpLine(); + thread_filter = NULL; + } else { + snprintf(msg, sizeof(msg), + "To zoom out press -> + \"Zoom out of %s(%d) thread\"", + (thread->comm_set ? thread->comm : ""), + thread->pid); + newtPushHelpLine(msg); + thread_filter = thread; + } + nr_hists = hists__filter_by_thread(hists, thread_filter, &session_total); + hist_browser__title(msg, sizeof(msg), input_name, + dso_filter, thread_filter); + if (hist_browser__populate(browser, hists, nr_hists, session_total, msg) < 0) + goto out; + } + } + err = 0; +out: + hist_browser__delete(browser); + return err; +} + +void setup_browser(void) +{ + if (!isatty(1)) + return; + + use_browser = true; + newtInit(); + newtCls(); + newtPushHelpLine(" "); +} + +void exit_browser(bool wait_for_ok) +{ + if (use_browser) { + if (wait_for_ok) { + char title[] = "Fatal Error", ok[] = "Ok"; + newtWinMessage(title, ok, browser__last_msg); + } + newtFinished(); + } +} diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 05d0c5c2030c..3b4ec6797565 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -5,6 +5,7 @@ #include "parse-events.h" #include "exec_cmd.h" #include "string.h" +#include "symbol.h" #include "cache.h" #include "header.h" #include "debugfs.h" @@ -409,7 +410,6 @@ static enum event_result parse_single_tracepoint_event(char *sys_name, const char *evt_name, unsigned int evt_length, - char *flags, struct perf_event_attr *attr, const char **strp) { @@ -418,13 +418,11 @@ parse_single_tracepoint_event(char *sys_name, u64 id; int fd; - if (flags) { - if (!strncmp(flags, "record", strlen(flags))) { - attr->sample_type |= PERF_SAMPLE_RAW; - attr->sample_type |= PERF_SAMPLE_TIME; - attr->sample_type |= PERF_SAMPLE_CPU; - } - } + attr->sample_type |= PERF_SAMPLE_RAW; + attr->sample_type |= PERF_SAMPLE_TIME; + attr->sample_type |= PERF_SAMPLE_CPU; + + attr->sample_period = 1; snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", debugfs_path, sys_name, evt_name); @@ -532,8 +530,7 @@ static enum event_result parse_tracepoint_event(const char **strp, flags); } else return parse_single_tracepoint_event(sys_name, evt_name, - evt_length, flags, - attr, strp); + evt_length, attr, strp); } static enum event_result @@ -656,6 +653,10 @@ parse_raw_event(const char **strp, struct perf_event_attr *attr) return EVT_FAILED; n = hex2u64(str + 1, &config); if (n > 0) { + if (str[n+1] == 'p') { + attr->precise = 1; + n++; + } *strp = str + n + 1; attr->type = PERF_TYPE_RAW; attr->config = config; diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index efebd5b476b3..ed887642460c 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -49,6 +49,7 @@ static int get_value(struct parse_opt_ctx_t *p, break; /* FALLTHROUGH */ case OPTION_BOOLEAN: + case OPTION_INCR: case OPTION_BIT: case OPTION_SET_INT: case OPTION_SET_PTR: @@ -73,6 +74,10 @@ static int get_value(struct parse_opt_ctx_t *p, return 0; case OPTION_BOOLEAN: + *(bool *)opt->value = unset ? false : true; + return 0; + + case OPTION_INCR: *(int *)opt->value = unset ? 0 : *(int *)opt->value + 1; return 0; @@ -478,6 +483,7 @@ int usage_with_options_internal(const char * const *usagestr, case OPTION_GROUP: case OPTION_BIT: case OPTION_BOOLEAN: + case OPTION_INCR: case OPTION_SET_INT: case OPTION_SET_PTR: case OPTION_LONG: @@ -500,6 +506,7 @@ int usage_with_options_internal(const char * const *usagestr, void usage_with_options(const char * const *usagestr, const struct option *opts) { + exit_browser(false); usage_with_options_internal(usagestr, opts, 0); exit(129); } diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index 948805af43c2..b2da725f102a 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -8,7 +8,8 @@ enum parse_opt_type { OPTION_GROUP, /* options with no arguments */ OPTION_BIT, - OPTION_BOOLEAN, /* _INCR would have been a better name */ + OPTION_BOOLEAN, + OPTION_INCR, OPTION_SET_INT, OPTION_SET_PTR, /* options with arguments (usually) */ @@ -95,6 +96,7 @@ struct option { #define OPT_GROUP(h) { .type = OPTION_GROUP, .help = (h) } #define OPT_BIT(s, l, v, h, b) { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (b) } #define OPT_BOOLEAN(s, l, v, h) { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = (v), .help = (h) } +#define OPT_INCR(s, l, v, h) { .type = OPTION_INCR, .short_name = (s), .long_name = (l), .value = (v), .help = (h) } #define OPT_SET_INT(s, l, v, h, i) { .type = OPTION_SET_INT, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (i) } #define OPT_SET_PTR(s, l, v, h, p) { .type = OPTION_SET_PTR, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (p) } #define OPT_INTEGER(s, l, v, h) { .type = OPTION_INTEGER, .short_name = (s), .long_name = (l), .value = (v), .help = (h) } diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 7c004b6ef24f..4fb480367c3e 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -33,20 +33,27 @@ #include <limits.h> #undef _GNU_SOURCE +#include "util.h" #include "event.h" #include "string.h" #include "strlist.h" #include "debug.h" #include "cache.h" #include "color.h" -#include "parse-events.h" /* For debugfs_path */ +#include "symbol.h" +#include "thread.h" +#include "debugfs.h" +#include "trace-event.h" /* For __unused */ #include "probe-event.h" +#include "probe-finder.h" #define MAX_CMDLEN 256 #define MAX_PROBE_ARGS 128 #define PERFPROBE_GROUP "probe" -#define semantic_error(msg ...) die("Semantic error :" msg) +bool probe_event_dry_run; /* Dry run flag */ + +#define semantic_error(msg ...) pr_err("Semantic error :" msg) /* If there is no space to write, returns -E2BIG. */ static int e_snprintf(char *str, size_t size, const char *format, ...) @@ -64,7 +71,270 @@ static int e_snprintf(char *str, size_t size, const char *format, ...) return ret; } -void parse_line_range_desc(const char *arg, struct line_range *lr) +static char *synthesize_perf_probe_point(struct perf_probe_point *pp); +static struct map_groups kmap_groups; +static struct map *kmaps[MAP__NR_TYPES]; + +/* Initialize symbol maps and path of vmlinux */ +static int init_vmlinux(void) +{ + struct dso *kernel; + int ret; + + symbol_conf.sort_by_name = true; + if (symbol_conf.vmlinux_name == NULL) + symbol_conf.try_vmlinux_path = true; + else + pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name); + ret = symbol__init(); + if (ret < 0) { + pr_debug("Failed to init symbol map.\n"); + goto out; + } + + kernel = dso__new_kernel(symbol_conf.vmlinux_name); + if (kernel == NULL) + die("Failed to create kernel dso."); + + map_groups__init(&kmap_groups); + ret = __map_groups__create_kernel_maps(&kmap_groups, kmaps, kernel); + if (ret < 0) + pr_debug("Failed to create kernel maps.\n"); + +out: + if (ret < 0) + pr_warning("Failed to init vmlinux path.\n"); + return ret; +} + +#ifdef DWARF_SUPPORT +static int open_vmlinux(void) +{ + if (map__load(kmaps[MAP__FUNCTION], NULL) < 0) { + pr_debug("Failed to load kernel map.\n"); + return -EINVAL; + } + pr_debug("Try to open %s\n", kmaps[MAP__FUNCTION]->dso->long_name); + return open(kmaps[MAP__FUNCTION]->dso->long_name, O_RDONLY); +} + +/* Convert trace point to probe point with debuginfo */ +static int convert_to_perf_probe_point(struct kprobe_trace_point *tp, + struct perf_probe_point *pp) +{ + struct symbol *sym; + int fd, ret = -ENOENT; + + sym = map__find_symbol_by_name(kmaps[MAP__FUNCTION], + tp->symbol, NULL); + if (sym) { + fd = open_vmlinux(); + if (fd >= 0) { + ret = find_perf_probe_point(fd, + sym->start + tp->offset, pp); + close(fd); + } + } + if (ret <= 0) { + pr_debug("Failed to find corresponding probes from " + "debuginfo. Use kprobe event information.\n"); + pp->function = strdup(tp->symbol); + if (pp->function == NULL) + return -ENOMEM; + pp->offset = tp->offset; + } + pp->retprobe = tp->retprobe; + + return 0; +} + +/* Try to find perf_probe_event with debuginfo */ +static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev, + struct kprobe_trace_event **tevs) +{ + bool need_dwarf = perf_probe_event_need_dwarf(pev); + int fd, ntevs; + + fd = open_vmlinux(); + if (fd < 0) { + if (need_dwarf) { + pr_warning("Failed to open debuginfo file.\n"); + return fd; + } + pr_debug("Could not open vmlinux. Try to use symbols.\n"); + return 0; + } + + /* Searching trace events corresponding to probe event */ + ntevs = find_kprobe_trace_events(fd, pev, tevs); + close(fd); + + if (ntevs > 0) { /* Succeeded to find trace events */ + pr_debug("find %d kprobe_trace_events.\n", ntevs); + return ntevs; + } + + if (ntevs == 0) { /* No error but failed to find probe point. */ + pr_warning("Probe point '%s' not found.\n", + synthesize_perf_probe_point(&pev->point)); + return -ENOENT; + } + /* Error path : ntevs < 0 */ + if (need_dwarf) { + if (ntevs == -EBADF) + pr_warning("No dwarf info found in the vmlinux - " + "please rebuild with CONFIG_DEBUG_INFO=y.\n"); + return ntevs; + } + pr_debug("An error occurred in debuginfo analysis." + " Try to use symbols.\n"); + return 0; +} + +#define LINEBUF_SIZE 256 +#define NR_ADDITIONAL_LINES 2 + +static int show_one_line(FILE *fp, int l, bool skip, bool show_num) +{ + char buf[LINEBUF_SIZE]; + const char *color = PERF_COLOR_BLUE; + + if (fgets(buf, LINEBUF_SIZE, fp) == NULL) + goto error; + if (!skip) { + if (show_num) + fprintf(stdout, "%7d %s", l, buf); + else + color_fprintf(stdout, color, " %s", buf); + } + + while (strlen(buf) == LINEBUF_SIZE - 1 && + buf[LINEBUF_SIZE - 2] != '\n') { + if (fgets(buf, LINEBUF_SIZE, fp) == NULL) + goto error; + if (!skip) { + if (show_num) + fprintf(stdout, "%s", buf); + else + color_fprintf(stdout, color, "%s", buf); + } + } + + return 0; +error: + if (feof(fp)) + pr_warning("Source file is shorter than expected.\n"); + else + pr_warning("File read error: %s\n", strerror(errno)); + + return -1; +} + +/* + * Show line-range always requires debuginfo to find source file and + * line number. + */ +int show_line_range(struct line_range *lr) +{ + int l = 1; + struct line_node *ln; + FILE *fp; + int fd, ret; + + /* Search a line range */ + ret = init_vmlinux(); + if (ret < 0) + return ret; + + fd = open_vmlinux(); + if (fd < 0) { + pr_warning("Failed to open debuginfo file.\n"); + return fd; + } + + ret = find_line_range(fd, lr); + close(fd); + if (ret == 0) { + pr_warning("Specified source line is not found.\n"); + return -ENOENT; + } else if (ret < 0) { + pr_warning("Debuginfo analysis failed. (%d)\n", ret); + return ret; + } + + setup_pager(); + + if (lr->function) + fprintf(stdout, "<%s:%d>\n", lr->function, + lr->start - lr->offset); + else + fprintf(stdout, "<%s:%d>\n", lr->file, lr->start); + + fp = fopen(lr->path, "r"); + if (fp == NULL) { + pr_warning("Failed to open %s: %s\n", lr->path, + strerror(errno)); + return -errno; + } + /* Skip to starting line number */ + while (l < lr->start && ret >= 0) + ret = show_one_line(fp, l++, true, false); + if (ret < 0) + goto end; + + list_for_each_entry(ln, &lr->line_list, list) { + while (ln->line > l && ret >= 0) + ret = show_one_line(fp, (l++) - lr->offset, + false, false); + if (ret >= 0) + ret = show_one_line(fp, (l++) - lr->offset, + false, true); + if (ret < 0) + goto end; + } + + if (lr->end == INT_MAX) + lr->end = l + NR_ADDITIONAL_LINES; + while (l <= lr->end && !feof(fp) && ret >= 0) + ret = show_one_line(fp, (l++) - lr->offset, false, false); +end: + fclose(fp); + return ret; +} + +#else /* !DWARF_SUPPORT */ + +static int convert_to_perf_probe_point(struct kprobe_trace_point *tp, + struct perf_probe_point *pp) +{ + pp->function = strdup(tp->symbol); + if (pp->function == NULL) + return -ENOMEM; + pp->offset = tp->offset; + pp->retprobe = tp->retprobe; + + return 0; +} + +static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev, + struct kprobe_trace_event **tevs __unused) +{ + if (perf_probe_event_need_dwarf(pev)) { + pr_warning("Debuginfo-analysis is not supported.\n"); + return -ENOSYS; + } + return 0; +} + +int show_line_range(struct line_range *lr __unused) +{ + pr_warning("Debuginfo-analysis is not supported.\n"); + return -ENOSYS; +} + +#endif + +int parse_line_range_desc(const char *arg, struct line_range *lr) { const char *ptr; char *tmp; @@ -75,29 +345,45 @@ void parse_line_range_desc(const char *arg, struct line_range *lr) */ ptr = strchr(arg, ':'); if (ptr) { - lr->start = (unsigned int)strtoul(ptr + 1, &tmp, 0); - if (*tmp == '+') - lr->end = lr->start + (unsigned int)strtoul(tmp + 1, - &tmp, 0); - else if (*tmp == '-') - lr->end = (unsigned int)strtoul(tmp + 1, &tmp, 0); + lr->start = (int)strtoul(ptr + 1, &tmp, 0); + if (*tmp == '+') { + lr->end = lr->start + (int)strtoul(tmp + 1, &tmp, 0); + lr->end--; /* + * Adjust the number of lines here. + * If the number of lines == 1, the + * the end of line should be equal to + * the start of line. + */ + } else if (*tmp == '-') + lr->end = (int)strtoul(tmp + 1, &tmp, 0); else - lr->end = 0; - pr_debug("Line range is %u to %u\n", lr->start, lr->end); - if (lr->end && lr->start > lr->end) + lr->end = INT_MAX; + pr_debug("Line range is %d to %d\n", lr->start, lr->end); + if (lr->start > lr->end) { semantic_error("Start line must be smaller" - " than end line."); - if (*tmp != '\0') - semantic_error("Tailing with invalid character '%d'.", + " than end line.\n"); + return -EINVAL; + } + if (*tmp != '\0') { + semantic_error("Tailing with invalid character '%d'.\n", *tmp); + return -EINVAL; + } tmp = strndup(arg, (ptr - arg)); - } else + } else { tmp = strdup(arg); + lr->end = INT_MAX; + } + + if (tmp == NULL) + return -ENOMEM; if (strchr(tmp, '.')) lr->file = tmp; else lr->function = tmp; + + return 0; } /* Check the name is good for event/group */ @@ -113,8 +399,9 @@ static bool check_event_name(const char *name) } /* Parse probepoint definition. */ -static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp) +static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) { + struct perf_probe_point *pp = &pev->point; char *ptr, *tmp; char c, nc = 0; /* @@ -129,13 +416,19 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp) if (ptr && *ptr == '=') { /* Event name */ *ptr = '\0'; tmp = ptr + 1; - ptr = strchr(arg, ':'); - if (ptr) /* Group name is not supported yet. */ - semantic_error("Group name is not supported yet."); - if (!check_event_name(arg)) + if (strchr(arg, ':')) { + semantic_error("Group name is not supported yet.\n"); + return -ENOTSUP; + } + if (!check_event_name(arg)) { semantic_error("%s is bad for event name -it must " - "follow C symbol-naming rule.", arg); - pp->event = strdup(arg); + "follow C symbol-naming rule.\n", arg); + return -EINVAL; + } + pev->event = strdup(arg); + if (pev->event == NULL) + return -ENOMEM; + pev->group = NULL; arg = tmp; } @@ -145,12 +438,15 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp) *ptr++ = '\0'; } + tmp = strdup(arg); + if (tmp == NULL) + return -ENOMEM; + /* Check arg is function or file and copy it */ - if (strchr(arg, '.')) /* File */ - pp->file = strdup(arg); + if (strchr(tmp, '.')) /* File */ + pp->file = tmp; else /* Function */ - pp->function = strdup(arg); - DIE_IF(pp->file == NULL && pp->function == NULL); + pp->function = tmp; /* Parse other options */ while (ptr) { @@ -158,6 +454,8 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp) c = nc; if (c == ';') { /* Lazy pattern must be the last part */ pp->lazy_line = strdup(arg); + if (pp->lazy_line == NULL) + return -ENOMEM; break; } ptr = strpbrk(arg, ";:+@%"); @@ -168,266 +466,658 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp) switch (c) { case ':': /* Line number */ pp->line = strtoul(arg, &tmp, 0); - if (*tmp != '\0') + if (*tmp != '\0') { semantic_error("There is non-digit char" - " in line number."); + " in line number.\n"); + return -EINVAL; + } break; case '+': /* Byte offset from a symbol */ pp->offset = strtoul(arg, &tmp, 0); - if (*tmp != '\0') + if (*tmp != '\0') { semantic_error("There is non-digit character" - " in offset."); + " in offset.\n"); + return -EINVAL; + } break; case '@': /* File name */ - if (pp->file) - semantic_error("SRC@SRC is not allowed."); + if (pp->file) { + semantic_error("SRC@SRC is not allowed.\n"); + return -EINVAL; + } pp->file = strdup(arg); - DIE_IF(pp->file == NULL); + if (pp->file == NULL) + return -ENOMEM; break; case '%': /* Probe places */ if (strcmp(arg, "return") == 0) { pp->retprobe = 1; - } else /* Others not supported yet */ - semantic_error("%%%s is not supported.", arg); + } else { /* Others not supported yet */ + semantic_error("%%%s is not supported.\n", arg); + return -ENOTSUP; + } break; - default: - DIE_IF("Program has a bug."); + default: /* Buggy case */ + pr_err("This program has a bug at %s:%d.\n", + __FILE__, __LINE__); + return -ENOTSUP; break; } } /* Exclusion check */ - if (pp->lazy_line && pp->line) + if (pp->lazy_line && pp->line) { semantic_error("Lazy pattern can't be used with line number."); + return -EINVAL; + } - if (pp->lazy_line && pp->offset) + if (pp->lazy_line && pp->offset) { semantic_error("Lazy pattern can't be used with offset."); + return -EINVAL; + } - if (pp->line && pp->offset) + if (pp->line && pp->offset) { semantic_error("Offset can't be used with line number."); + return -EINVAL; + } - if (!pp->line && !pp->lazy_line && pp->file && !pp->function) + if (!pp->line && !pp->lazy_line && pp->file && !pp->function) { semantic_error("File always requires line number or " "lazy pattern."); + return -EINVAL; + } - if (pp->offset && !pp->function) + if (pp->offset && !pp->function) { semantic_error("Offset requires an entry function."); + return -EINVAL; + } - if (pp->retprobe && !pp->function) + if (pp->retprobe && !pp->function) { semantic_error("Return probe requires an entry function."); + return -EINVAL; + } - if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) + if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) { semantic_error("Offset/Line/Lazy pattern can't be used with " "return probe."); + return -EINVAL; + } - pr_debug("symbol:%s file:%s line:%d offset:%d return:%d lazy:%s\n", + pr_debug("symbol:%s file:%s line:%d offset:%lu return:%d lazy:%s\n", pp->function, pp->file, pp->line, pp->offset, pp->retprobe, pp->lazy_line); + return 0; } -/* Parse perf-probe event definition */ -void parse_perf_probe_event(const char *str, struct probe_point *pp, - bool *need_dwarf) +/* Parse perf-probe event argument */ +static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg) { - char **argv; - int argc, i; + char *tmp; + struct perf_probe_arg_field **fieldp; + + pr_debug("parsing arg: %s into ", str); + + tmp = strchr(str, '='); + if (tmp) { + arg->name = strndup(str, tmp - str); + if (arg->name == NULL) + return -ENOMEM; + pr_debug("name:%s ", arg->name); + str = tmp + 1; + } - *need_dwarf = false; + tmp = strchr(str, ':'); + if (tmp) { /* Type setting */ + *tmp = '\0'; + arg->type = strdup(tmp + 1); + if (arg->type == NULL) + return -ENOMEM; + pr_debug("type:%s ", arg->type); + } - argv = argv_split(str, &argc); - if (!argv) - die("argv_split failed."); - if (argc > MAX_PROBE_ARGS + 1) - semantic_error("Too many arguments"); + tmp = strpbrk(str, "-."); + if (!is_c_varname(str) || !tmp) { + /* A variable, register, symbol or special value */ + arg->var = strdup(str); + if (arg->var == NULL) + return -ENOMEM; + pr_debug("%s\n", arg->var); + return 0; + } + /* Structure fields */ + arg->var = strndup(str, tmp - str); + if (arg->var == NULL) + return -ENOMEM; + pr_debug("%s, ", arg->var); + fieldp = &arg->field; + + do { + *fieldp = zalloc(sizeof(struct perf_probe_arg_field)); + if (*fieldp == NULL) + return -ENOMEM; + if (*tmp == '.') { + str = tmp + 1; + (*fieldp)->ref = false; + } else if (tmp[1] == '>') { + str = tmp + 2; + (*fieldp)->ref = true; + } else { + semantic_error("Argument parse error: %s\n", str); + return -EINVAL; + } + + tmp = strpbrk(str, "-."); + if (tmp) { + (*fieldp)->name = strndup(str, tmp - str); + if ((*fieldp)->name == NULL) + return -ENOMEM; + pr_debug("%s(%d), ", (*fieldp)->name, (*fieldp)->ref); + fieldp = &(*fieldp)->next; + } + } while (tmp); + (*fieldp)->name = strdup(str); + if ((*fieldp)->name == NULL) + return -ENOMEM; + pr_debug("%s(%d)\n", (*fieldp)->name, (*fieldp)->ref); + + /* If no name is specified, set the last field name */ + if (!arg->name) { + arg->name = strdup((*fieldp)->name); + if (arg->name == NULL) + return -ENOMEM; + } + return 0; +} + +/* Parse perf-probe event command */ +int parse_perf_probe_command(const char *cmd, struct perf_probe_event *pev) +{ + char **argv; + int argc, i, ret = 0; + + argv = argv_split(cmd, &argc); + if (!argv) { + pr_debug("Failed to split arguments.\n"); + return -ENOMEM; + } + if (argc - 1 > MAX_PROBE_ARGS) { + semantic_error("Too many probe arguments (%d).\n", argc - 1); + ret = -ERANGE; + goto out; + } /* Parse probe point */ - parse_perf_probe_probepoint(argv[0], pp); - if (pp->file || pp->line || pp->lazy_line) - *need_dwarf = true; + ret = parse_perf_probe_point(argv[0], pev); + if (ret < 0) + goto out; /* Copy arguments and ensure return probe has no C argument */ - pp->nr_args = argc - 1; - pp->args = zalloc(sizeof(char *) * pp->nr_args); - for (i = 0; i < pp->nr_args; i++) { - pp->args[i] = strdup(argv[i + 1]); - if (!pp->args[i]) - die("Failed to copy argument."); - if (is_c_varname(pp->args[i])) { - if (pp->retprobe) - semantic_error("You can't specify local" - " variable for kretprobe"); - *need_dwarf = true; + pev->nargs = argc - 1; + pev->args = zalloc(sizeof(struct perf_probe_arg) * pev->nargs); + if (pev->args == NULL) { + ret = -ENOMEM; + goto out; + } + for (i = 0; i < pev->nargs && ret >= 0; i++) { + ret = parse_perf_probe_arg(argv[i + 1], &pev->args[i]); + if (ret >= 0 && + is_c_varname(pev->args[i].var) && pev->point.retprobe) { + semantic_error("You can't specify local variable for" + " kretprobe.\n"); + ret = -EINVAL; } } - +out: argv_free(argv); + + return ret; +} + +/* Return true if this perf_probe_event requires debuginfo */ +bool perf_probe_event_need_dwarf(struct perf_probe_event *pev) +{ + int i; + + if (pev->point.file || pev->point.line || pev->point.lazy_line) + return true; + + for (i = 0; i < pev->nargs; i++) + if (is_c_varname(pev->args[i].var)) + return true; + + return false; } /* Parse kprobe_events event into struct probe_point */ -void parse_trace_kprobe_event(const char *str, struct probe_point *pp) +int parse_kprobe_trace_command(const char *cmd, struct kprobe_trace_event *tev) { + struct kprobe_trace_point *tp = &tev->point; char pr; char *p; int ret, i, argc; char **argv; - pr_debug("Parsing kprobe_events: %s\n", str); - argv = argv_split(str, &argc); - if (!argv) - die("argv_split failed."); - if (argc < 2) - semantic_error("Too less arguments."); + pr_debug("Parsing kprobe_events: %s\n", cmd); + argv = argv_split(cmd, &argc); + if (!argv) { + pr_debug("Failed to split arguments.\n"); + return -ENOMEM; + } + if (argc < 2) { + semantic_error("Too few probe arguments.\n"); + ret = -ERANGE; + goto out; + } /* Scan event and group name. */ ret = sscanf(argv[0], "%c:%a[^/ \t]/%a[^ \t]", - &pr, (float *)(void *)&pp->group, - (float *)(void *)&pp->event); - if (ret != 3) - semantic_error("Failed to parse event name: %s", argv[0]); - pr_debug("Group:%s Event:%s probe:%c\n", pp->group, pp->event, pr); + &pr, (float *)(void *)&tev->group, + (float *)(void *)&tev->event); + if (ret != 3) { + semantic_error("Failed to parse event name: %s\n", argv[0]); + ret = -EINVAL; + goto out; + } + pr_debug("Group:%s Event:%s probe:%c\n", tev->group, tev->event, pr); - pp->retprobe = (pr == 'r'); + tp->retprobe = (pr == 'r'); /* Scan function name and offset */ - ret = sscanf(argv[1], "%a[^+]+%d", (float *)(void *)&pp->function, - &pp->offset); + ret = sscanf(argv[1], "%a[^+]+%lu", (float *)(void *)&tp->symbol, + &tp->offset); if (ret == 1) - pp->offset = 0; - - /* kprobe_events doesn't have this information */ - pp->line = 0; - pp->file = NULL; + tp->offset = 0; - pp->nr_args = argc - 2; - pp->args = zalloc(sizeof(char *) * pp->nr_args); - for (i = 0; i < pp->nr_args; i++) { + tev->nargs = argc - 2; + tev->args = zalloc(sizeof(struct kprobe_trace_arg) * tev->nargs); + if (tev->args == NULL) { + ret = -ENOMEM; + goto out; + } + for (i = 0; i < tev->nargs; i++) { p = strchr(argv[i + 2], '='); if (p) /* We don't need which register is assigned. */ - *p = '\0'; - pp->args[i] = strdup(argv[i + 2]); - if (!pp->args[i]) - die("Failed to copy argument."); + *p++ = '\0'; + else + p = argv[i + 2]; + tev->args[i].name = strdup(argv[i + 2]); + /* TODO: parse regs and offset */ + tev->args[i].value = strdup(p); + if (tev->args[i].name == NULL || tev->args[i].value == NULL) { + ret = -ENOMEM; + goto out; + } } - + ret = 0; +out: argv_free(argv); + return ret; } -/* Synthesize only probe point (not argument) */ -int synthesize_perf_probe_point(struct probe_point *pp) +/* Compose only probe arg */ +int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len) { - char *buf; - char offs[64] = "", line[64] = ""; + struct perf_probe_arg_field *field = pa->field; int ret; + char *tmp = buf; - pp->probes[0] = buf = zalloc(MAX_CMDLEN); - pp->found = 1; - if (!buf) - die("Failed to allocate memory by zalloc."); + if (pa->name && pa->var) + ret = e_snprintf(tmp, len, "%s=%s", pa->name, pa->var); + else + ret = e_snprintf(tmp, len, "%s", pa->name ? pa->name : pa->var); + if (ret <= 0) + goto error; + tmp += ret; + len -= ret; + + while (field) { + ret = e_snprintf(tmp, len, "%s%s", field->ref ? "->" : ".", + field->name); + if (ret <= 0) + goto error; + tmp += ret; + len -= ret; + field = field->next; + } + + if (pa->type) { + ret = e_snprintf(tmp, len, ":%s", pa->type); + if (ret <= 0) + goto error; + tmp += ret; + len -= ret; + } + + return tmp - buf; +error: + pr_debug("Failed to synthesize perf probe argument: %s", + strerror(-ret)); + return ret; +} + +/* Compose only probe point (not argument) */ +static char *synthesize_perf_probe_point(struct perf_probe_point *pp) +{ + char *buf, *tmp; + char offs[32] = "", line[32] = "", file[32] = ""; + int ret, len; + + buf = zalloc(MAX_CMDLEN); + if (buf == NULL) { + ret = -ENOMEM; + goto error; + } if (pp->offset) { - ret = e_snprintf(offs, 64, "+%d", pp->offset); + ret = e_snprintf(offs, 32, "+%lu", pp->offset); if (ret <= 0) goto error; } if (pp->line) { - ret = e_snprintf(line, 64, ":%d", pp->line); + ret = e_snprintf(line, 32, ":%d", pp->line); + if (ret <= 0) + goto error; + } + if (pp->file) { + len = strlen(pp->file) - 31; + if (len < 0) + len = 0; + tmp = strchr(pp->file + len, '/'); + if (!tmp) + tmp = pp->file + len; + ret = e_snprintf(file, 32, "@%s", tmp + 1); if (ret <= 0) goto error; } if (pp->function) - ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s", pp->function, - offs, pp->retprobe ? "%return" : "", line); + ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s%s", pp->function, + offs, pp->retprobe ? "%return" : "", line, + file); else - ret = e_snprintf(buf, MAX_CMDLEN, "%s%s", pp->file, line); - if (ret <= 0) { + ret = e_snprintf(buf, MAX_CMDLEN, "%s%s", file, line); + if (ret <= 0) + goto error; + + return buf; error: - free(pp->probes[0]); - pp->probes[0] = NULL; - pp->found = 0; - } - return ret; + pr_debug("Failed to synthesize perf probe point: %s", + strerror(-ret)); + if (buf) + free(buf); + return NULL; } -int synthesize_perf_probe_event(struct probe_point *pp) +#if 0 +char *synthesize_perf_probe_command(struct perf_probe_event *pev) { char *buf; int i, len, ret; - len = synthesize_perf_probe_point(pp); - if (len < 0) - return 0; + buf = synthesize_perf_probe_point(&pev->point); + if (!buf) + return NULL; - buf = pp->probes[0]; - for (i = 0; i < pp->nr_args; i++) { + len = strlen(buf); + for (i = 0; i < pev->nargs; i++) { ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s", - pp->args[i]); - if (ret <= 0) - goto error; + pev->args[i].name); + if (ret <= 0) { + free(buf); + return NULL; + } len += ret; } - pp->found = 1; - return pp->found; -error: - free(pp->probes[0]); - pp->probes[0] = NULL; + return buf; +} +#endif + +static int __synthesize_kprobe_trace_arg_ref(struct kprobe_trace_arg_ref *ref, + char **buf, size_t *buflen, + int depth) +{ + int ret; + if (ref->next) { + depth = __synthesize_kprobe_trace_arg_ref(ref->next, buf, + buflen, depth + 1); + if (depth < 0) + goto out; + } + + ret = e_snprintf(*buf, *buflen, "%+ld(", ref->offset); + if (ret < 0) + depth = ret; + else { + *buf += ret; + *buflen -= ret; + } +out: + return depth; - return ret; } -int synthesize_trace_kprobe_event(struct probe_point *pp) +static int synthesize_kprobe_trace_arg(struct kprobe_trace_arg *arg, + char *buf, size_t buflen) { + int ret, depth = 0; + char *tmp = buf; + + /* Argument name or separator */ + if (arg->name) + ret = e_snprintf(buf, buflen, " %s=", arg->name); + else + ret = e_snprintf(buf, buflen, " "); + if (ret < 0) + return ret; + buf += ret; + buflen -= ret; + + /* Dereferencing arguments */ + if (arg->ref) { + depth = __synthesize_kprobe_trace_arg_ref(arg->ref, &buf, + &buflen, 1); + if (depth < 0) + return depth; + } + + /* Print argument value */ + ret = e_snprintf(buf, buflen, "%s", arg->value); + if (ret < 0) + return ret; + buf += ret; + buflen -= ret; + + /* Closing */ + while (depth--) { + ret = e_snprintf(buf, buflen, ")"); + if (ret < 0) + return ret; + buf += ret; + buflen -= ret; + } + /* Print argument type */ + if (arg->type) { + ret = e_snprintf(buf, buflen, ":%s", arg->type); + if (ret <= 0) + return ret; + buf += ret; + } + + return buf - tmp; +} + +char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev) +{ + struct kprobe_trace_point *tp = &tev->point; char *buf; int i, len, ret; - pp->probes[0] = buf = zalloc(MAX_CMDLEN); - if (!buf) - die("Failed to allocate memory by zalloc."); - ret = e_snprintf(buf, MAX_CMDLEN, "%s+%d", pp->function, pp->offset); - if (ret <= 0) + buf = zalloc(MAX_CMDLEN); + if (buf == NULL) + return NULL; + + len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s+%lu", + tp->retprobe ? 'r' : 'p', + tev->group, tev->event, + tp->symbol, tp->offset); + if (len <= 0) goto error; - len = ret; - for (i = 0; i < pp->nr_args; i++) { - ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s", - pp->args[i]); + for (i = 0; i < tev->nargs; i++) { + ret = synthesize_kprobe_trace_arg(&tev->args[i], buf + len, + MAX_CMDLEN - len); if (ret <= 0) goto error; len += ret; } - pp->found = 1; - return pp->found; + return buf; error: - free(pp->probes[0]); - pp->probes[0] = NULL; + free(buf); + return NULL; +} + +int convert_to_perf_probe_event(struct kprobe_trace_event *tev, + struct perf_probe_event *pev) +{ + char buf[64] = ""; + int i, ret; + + /* Convert event/group name */ + pev->event = strdup(tev->event); + pev->group = strdup(tev->group); + if (pev->event == NULL || pev->group == NULL) + return -ENOMEM; + + /* Convert trace_point to probe_point */ + ret = convert_to_perf_probe_point(&tev->point, &pev->point); + if (ret < 0) + return ret; + + /* Convert trace_arg to probe_arg */ + pev->nargs = tev->nargs; + pev->args = zalloc(sizeof(struct perf_probe_arg) * pev->nargs); + if (pev->args == NULL) + return -ENOMEM; + for (i = 0; i < tev->nargs && ret >= 0; i++) { + if (tev->args[i].name) + pev->args[i].name = strdup(tev->args[i].name); + else { + ret = synthesize_kprobe_trace_arg(&tev->args[i], + buf, 64); + pev->args[i].name = strdup(buf); + } + if (pev->args[i].name == NULL && ret >= 0) + ret = -ENOMEM; + } + + if (ret < 0) + clear_perf_probe_event(pev); return ret; } -static int open_kprobe_events(int flags, int mode) +void clear_perf_probe_event(struct perf_probe_event *pev) +{ + struct perf_probe_point *pp = &pev->point; + struct perf_probe_arg_field *field, *next; + int i; + + if (pev->event) + free(pev->event); + if (pev->group) + free(pev->group); + if (pp->file) + free(pp->file); + if (pp->function) + free(pp->function); + if (pp->lazy_line) + free(pp->lazy_line); + for (i = 0; i < pev->nargs; i++) { + if (pev->args[i].name) + free(pev->args[i].name); + if (pev->args[i].var) + free(pev->args[i].var); + if (pev->args[i].type) + free(pev->args[i].type); + field = pev->args[i].field; + while (field) { + next = field->next; + if (field->name) + free(field->name); + free(field); + field = next; + } + } + if (pev->args) + free(pev->args); + memset(pev, 0, sizeof(*pev)); +} + +void clear_kprobe_trace_event(struct kprobe_trace_event *tev) +{ + struct kprobe_trace_arg_ref *ref, *next; + int i; + + if (tev->event) + free(tev->event); + if (tev->group) + free(tev->group); + if (tev->point.symbol) + free(tev->point.symbol); + for (i = 0; i < tev->nargs; i++) { + if (tev->args[i].name) + free(tev->args[i].name); + if (tev->args[i].value) + free(tev->args[i].value); + if (tev->args[i].type) + free(tev->args[i].type); + ref = tev->args[i].ref; + while (ref) { + next = ref->next; + free(ref); + ref = next; + } + } + if (tev->args) + free(tev->args); + memset(tev, 0, sizeof(*tev)); +} + +static int open_kprobe_events(bool readwrite) { char buf[PATH_MAX]; + const char *__debugfs; int ret; - ret = e_snprintf(buf, PATH_MAX, "%s/../kprobe_events", debugfs_path); - if (ret < 0) - die("Failed to make kprobe_events path."); + __debugfs = debugfs_find_mountpoint(); + if (__debugfs == NULL) { + pr_warning("Debugfs is not mounted.\n"); + return -ENOENT; + } + + ret = e_snprintf(buf, PATH_MAX, "%stracing/kprobe_events", __debugfs); + if (ret >= 0) { + pr_debug("Opening %s write=%d\n", buf, readwrite); + if (readwrite && !probe_event_dry_run) + ret = open(buf, O_RDWR, O_APPEND); + else + ret = open(buf, O_RDONLY, 0); + } - ret = open(buf, flags, mode); if (ret < 0) { if (errno == ENOENT) - die("kprobe_events file does not exist -" - " please rebuild with CONFIG_KPROBE_EVENT."); + pr_warning("kprobe_events file does not exist - please" + " rebuild kernel with CONFIG_KPROBE_EVENT.\n"); else - die("Could not open kprobe_events file: %s", - strerror(errno)); + pr_warning("Failed to open kprobe_events file: %s\n", + strerror(errno)); } return ret; } /* Get raw string list of current kprobe_events */ -static struct strlist *get_trace_kprobe_event_rawlist(int fd) +static struct strlist *get_kprobe_trace_command_rawlist(int fd) { int ret, idx; FILE *fp; @@ -447,271 +1137,485 @@ static struct strlist *get_trace_kprobe_event_rawlist(int fd) if (p[idx] == '\n') p[idx] = '\0'; ret = strlist__add(sl, buf); - if (ret < 0) - die("strlist__add failed: %s", strerror(-ret)); + if (ret < 0) { + pr_debug("strlist__add failed: %s\n", strerror(-ret)); + strlist__delete(sl); + return NULL; + } } fclose(fp); return sl; } -/* Free and zero clear probe_point */ -static void clear_probe_point(struct probe_point *pp) -{ - int i; - - if (pp->event) - free(pp->event); - if (pp->group) - free(pp->group); - if (pp->function) - free(pp->function); - if (pp->file) - free(pp->file); - if (pp->lazy_line) - free(pp->lazy_line); - for (i = 0; i < pp->nr_args; i++) - free(pp->args[i]); - if (pp->args) - free(pp->args); - for (i = 0; i < pp->found; i++) - free(pp->probes[i]); - memset(pp, 0, sizeof(*pp)); -} - /* Show an event */ -static void show_perf_probe_event(const char *event, const char *place, - struct probe_point *pp) +static int show_perf_probe_event(struct perf_probe_event *pev) { int i, ret; char buf[128]; + char *place; + + /* Synthesize only event probe point */ + place = synthesize_perf_probe_point(&pev->point); + if (!place) + return -EINVAL; - ret = e_snprintf(buf, 128, "%s:%s", pp->group, event); + ret = e_snprintf(buf, 128, "%s:%s", pev->group, pev->event); if (ret < 0) - die("Failed to copy event: %s", strerror(-ret)); - printf(" %-40s (on %s", buf, place); + return ret; - if (pp->nr_args > 0) { + printf(" %-20s (on %s", buf, place); + + if (pev->nargs > 0) { printf(" with"); - for (i = 0; i < pp->nr_args; i++) - printf(" %s", pp->args[i]); + for (i = 0; i < pev->nargs; i++) { + ret = synthesize_perf_probe_arg(&pev->args[i], + buf, 128); + if (ret < 0) + break; + printf(" %s", buf); + } } printf(")\n"); + free(place); + return ret; } /* List up current perf-probe events */ -void show_perf_probe_events(void) +int show_perf_probe_events(void) { - int fd; - struct probe_point pp; + int fd, ret; + struct kprobe_trace_event tev; + struct perf_probe_event pev; struct strlist *rawlist; struct str_node *ent; setup_pager(); - memset(&pp, 0, sizeof(pp)); + ret = init_vmlinux(); + if (ret < 0) + return ret; + + memset(&tev, 0, sizeof(tev)); + memset(&pev, 0, sizeof(pev)); - fd = open_kprobe_events(O_RDONLY, 0); - rawlist = get_trace_kprobe_event_rawlist(fd); + fd = open_kprobe_events(false); + if (fd < 0) + return fd; + + rawlist = get_kprobe_trace_command_rawlist(fd); close(fd); + if (!rawlist) + return -ENOENT; strlist__for_each(ent, rawlist) { - parse_trace_kprobe_event(ent->s, &pp); - /* Synthesize only event probe point */ - synthesize_perf_probe_point(&pp); - /* Show an event */ - show_perf_probe_event(pp.event, pp.probes[0], &pp); - clear_probe_point(&pp); + ret = parse_kprobe_trace_command(ent->s, &tev); + if (ret >= 0) { + ret = convert_to_perf_probe_event(&tev, &pev); + if (ret >= 0) + ret = show_perf_probe_event(&pev); + } + clear_perf_probe_event(&pev); + clear_kprobe_trace_event(&tev); + if (ret < 0) + break; } - strlist__delete(rawlist); + + return ret; } /* Get current perf-probe event names */ -static struct strlist *get_perf_event_names(int fd, bool include_group) +static struct strlist *get_kprobe_trace_event_names(int fd, bool include_group) { char buf[128]; struct strlist *sl, *rawlist; struct str_node *ent; - struct probe_point pp; + struct kprobe_trace_event tev; + int ret = 0; - memset(&pp, 0, sizeof(pp)); - rawlist = get_trace_kprobe_event_rawlist(fd); + memset(&tev, 0, sizeof(tev)); + rawlist = get_kprobe_trace_command_rawlist(fd); sl = strlist__new(true, NULL); strlist__for_each(ent, rawlist) { - parse_trace_kprobe_event(ent->s, &pp); + ret = parse_kprobe_trace_command(ent->s, &tev); + if (ret < 0) + break; if (include_group) { - if (e_snprintf(buf, 128, "%s:%s", pp.group, - pp.event) < 0) - die("Failed to copy group:event name."); - strlist__add(sl, buf); + ret = e_snprintf(buf, 128, "%s:%s", tev.group, + tev.event); + if (ret >= 0) + ret = strlist__add(sl, buf); } else - strlist__add(sl, pp.event); - clear_probe_point(&pp); + ret = strlist__add(sl, tev.event); + clear_kprobe_trace_event(&tev); + if (ret < 0) + break; } - strlist__delete(rawlist); + if (ret < 0) { + strlist__delete(sl); + return NULL; + } return sl; } -static void write_trace_kprobe_event(int fd, const char *buf) +static int write_kprobe_trace_event(int fd, struct kprobe_trace_event *tev) { - int ret; + int ret = 0; + char *buf = synthesize_kprobe_trace_command(tev); + + if (!buf) { + pr_debug("Failed to synthesize kprobe trace event.\n"); + return -EINVAL; + } pr_debug("Writing event: %s\n", buf); - ret = write(fd, buf, strlen(buf)); - if (ret <= 0) - die("Failed to write event: %s", strerror(errno)); + if (!probe_event_dry_run) { + ret = write(fd, buf, strlen(buf)); + if (ret <= 0) + pr_warning("Failed to write event: %s\n", + strerror(errno)); + } + free(buf); + return ret; } -static void get_new_event_name(char *buf, size_t len, const char *base, - struct strlist *namelist, bool allow_suffix) +static int get_new_event_name(char *buf, size_t len, const char *base, + struct strlist *namelist, bool allow_suffix) { int i, ret; /* Try no suffix */ ret = e_snprintf(buf, len, "%s", base); - if (ret < 0) - die("snprintf() failed: %s", strerror(-ret)); + if (ret < 0) { + pr_debug("snprintf() failed: %s\n", strerror(-ret)); + return ret; + } if (!strlist__has_entry(namelist, buf)) - return; + return 0; if (!allow_suffix) { pr_warning("Error: event \"%s\" already exists. " "(Use -f to force duplicates.)\n", base); - die("Can't add new event."); + return -EEXIST; } /* Try to add suffix */ for (i = 1; i < MAX_EVENT_INDEX; i++) { ret = e_snprintf(buf, len, "%s_%d", base, i); - if (ret < 0) - die("snprintf() failed: %s", strerror(-ret)); + if (ret < 0) { + pr_debug("snprintf() failed: %s\n", strerror(-ret)); + return ret; + } if (!strlist__has_entry(namelist, buf)) break; } - if (i == MAX_EVENT_INDEX) - die("Too many events are on the same function."); + if (i == MAX_EVENT_INDEX) { + pr_warning("Too many events are on the same function.\n"); + ret = -ERANGE; + } + + return ret; } -void add_trace_kprobe_events(struct probe_point *probes, int nr_probes, - bool force_add) +static int __add_kprobe_trace_events(struct perf_probe_event *pev, + struct kprobe_trace_event *tevs, + int ntevs, bool allow_suffix) { - int i, j, fd; - struct probe_point *pp; - char buf[MAX_CMDLEN]; - char event[64]; + int i, fd, ret; + struct kprobe_trace_event *tev = NULL; + char buf[64]; + const char *event, *group; struct strlist *namelist; - bool allow_suffix; - fd = open_kprobe_events(O_RDWR, O_APPEND); + fd = open_kprobe_events(true); + if (fd < 0) + return fd; /* Get current event names */ - namelist = get_perf_event_names(fd, false); - - for (j = 0; j < nr_probes; j++) { - pp = probes + j; - if (!pp->event) - pp->event = strdup(pp->function); - if (!pp->group) - pp->group = strdup(PERFPROBE_GROUP); - DIE_IF(!pp->event || !pp->group); - /* If force_add is true, suffix search is allowed */ - allow_suffix = force_add; - for (i = 0; i < pp->found; i++) { - /* Get an unused new event name */ - get_new_event_name(event, 64, pp->event, namelist, - allow_suffix); - snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s\n", - pp->retprobe ? 'r' : 'p', - pp->group, event, - pp->probes[i]); - write_trace_kprobe_event(fd, buf); - printf("Added new event:\n"); - /* Get the first parameter (probe-point) */ - sscanf(pp->probes[i], "%s", buf); - show_perf_probe_event(event, buf, pp); - /* Add added event name to namelist */ - strlist__add(namelist, event); - /* - * Probes after the first probe which comes from same - * user input are always allowed to add suffix, because - * there might be several addresses corresponding to - * one code line. - */ - allow_suffix = true; + namelist = get_kprobe_trace_event_names(fd, false); + if (!namelist) { + pr_debug("Failed to get current event list.\n"); + return -EIO; + } + + ret = 0; + printf("Add new event%s\n", (ntevs > 1) ? "s:" : ":"); + for (i = 0; i < ntevs; i++) { + tev = &tevs[i]; + if (pev->event) + event = pev->event; + else + if (pev->point.function) + event = pev->point.function; + else + event = tev->point.symbol; + if (pev->group) + group = pev->group; + else + group = PERFPROBE_GROUP; + + /* Get an unused new event name */ + ret = get_new_event_name(buf, 64, event, + namelist, allow_suffix); + if (ret < 0) + break; + event = buf; + + tev->event = strdup(event); + tev->group = strdup(group); + if (tev->event == NULL || tev->group == NULL) { + ret = -ENOMEM; + break; } + ret = write_kprobe_trace_event(fd, tev); + if (ret < 0) + break; + /* Add added event name to namelist */ + strlist__add(namelist, event); + + /* Trick here - save current event/group */ + event = pev->event; + group = pev->group; + pev->event = tev->event; + pev->group = tev->group; + show_perf_probe_event(pev); + /* Trick here - restore current event/group */ + pev->event = (char *)event; + pev->group = (char *)group; + + /* + * Probes after the first probe which comes from same + * user input are always allowed to add suffix, because + * there might be several addresses corresponding to + * one code line. + */ + allow_suffix = true; + } + + if (ret >= 0) { + /* Show how to use the event. */ + printf("\nYou can now use it on all perf tools, such as:\n\n"); + printf("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group, + tev->event); } - /* Show how to use the event. */ - printf("\nYou can now use it on all perf tools, such as:\n\n"); - printf("\tperf record -e %s:%s -a sleep 1\n\n", PERFPROBE_GROUP, event); strlist__delete(namelist); close(fd); + return ret; } -static void __del_trace_kprobe_event(int fd, struct str_node *ent) +static int convert_to_kprobe_trace_events(struct perf_probe_event *pev, + struct kprobe_trace_event **tevs) +{ + struct symbol *sym; + int ret = 0, i; + struct kprobe_trace_event *tev; + + /* Convert perf_probe_event with debuginfo */ + ret = try_to_find_kprobe_trace_events(pev, tevs); + if (ret != 0) + return ret; + + /* Allocate trace event buffer */ + tev = *tevs = zalloc(sizeof(struct kprobe_trace_event)); + if (tev == NULL) + return -ENOMEM; + + /* Copy parameters */ + tev->point.symbol = strdup(pev->point.function); + if (tev->point.symbol == NULL) { + ret = -ENOMEM; + goto error; + } + tev->point.offset = pev->point.offset; + tev->nargs = pev->nargs; + if (tev->nargs) { + tev->args = zalloc(sizeof(struct kprobe_trace_arg) + * tev->nargs); + if (tev->args == NULL) { + ret = -ENOMEM; + goto error; + } + for (i = 0; i < tev->nargs; i++) { + if (pev->args[i].name) { + tev->args[i].name = strdup(pev->args[i].name); + if (tev->args[i].name == NULL) { + ret = -ENOMEM; + goto error; + } + } + tev->args[i].value = strdup(pev->args[i].var); + if (tev->args[i].value == NULL) { + ret = -ENOMEM; + goto error; + } + if (pev->args[i].type) { + tev->args[i].type = strdup(pev->args[i].type); + if (tev->args[i].type == NULL) { + ret = -ENOMEM; + goto error; + } + } + } + } + + /* Currently just checking function name from symbol map */ + sym = map__find_symbol_by_name(kmaps[MAP__FUNCTION], + tev->point.symbol, NULL); + if (!sym) { + pr_warning("Kernel symbol \'%s\' not found.\n", + tev->point.symbol); + ret = -ENOENT; + goto error; + } + + return 1; +error: + clear_kprobe_trace_event(tev); + free(tev); + *tevs = NULL; + return ret; +} + +struct __event_package { + struct perf_probe_event *pev; + struct kprobe_trace_event *tevs; + int ntevs; +}; + +int add_perf_probe_events(struct perf_probe_event *pevs, int npevs, + bool force_add) +{ + int i, j, ret; + struct __event_package *pkgs; + + pkgs = zalloc(sizeof(struct __event_package) * npevs); + if (pkgs == NULL) + return -ENOMEM; + + /* Init vmlinux path */ + ret = init_vmlinux(); + if (ret < 0) + return ret; + + /* Loop 1: convert all events */ + for (i = 0; i < npevs; i++) { + pkgs[i].pev = &pevs[i]; + /* Convert with or without debuginfo */ + ret = convert_to_kprobe_trace_events(pkgs[i].pev, + &pkgs[i].tevs); + if (ret < 0) + goto end; + pkgs[i].ntevs = ret; + } + + /* Loop 2: add all events */ + for (i = 0; i < npevs && ret >= 0; i++) + ret = __add_kprobe_trace_events(pkgs[i].pev, pkgs[i].tevs, + pkgs[i].ntevs, force_add); +end: + /* Loop 3: cleanup trace events */ + for (i = 0; i < npevs; i++) + for (j = 0; j < pkgs[i].ntevs; j++) + clear_kprobe_trace_event(&pkgs[i].tevs[j]); + + return ret; +} + +static int __del_trace_kprobe_event(int fd, struct str_node *ent) { char *p; char buf[128]; + int ret; /* Convert from perf-probe event to trace-kprobe event */ - if (e_snprintf(buf, 128, "-:%s", ent->s) < 0) - die("Failed to copy event."); + ret = e_snprintf(buf, 128, "-:%s", ent->s); + if (ret < 0) + goto error; + p = strchr(buf + 2, ':'); - if (!p) - die("Internal error: %s should have ':' but not.", ent->s); + if (!p) { + pr_debug("Internal error: %s should have ':' but not.\n", + ent->s); + ret = -ENOTSUP; + goto error; + } *p = '/'; - write_trace_kprobe_event(fd, buf); + pr_debug("Writing event: %s\n", buf); + ret = write(fd, buf, strlen(buf)); + if (ret < 0) + goto error; + printf("Remove event: %s\n", ent->s); + return 0; +error: + pr_warning("Failed to delete event: %s\n", strerror(-ret)); + return ret; } -static void del_trace_kprobe_event(int fd, const char *group, - const char *event, struct strlist *namelist) +static int del_trace_kprobe_event(int fd, const char *group, + const char *event, struct strlist *namelist) { char buf[128]; struct str_node *ent, *n; - int found = 0; + int found = 0, ret = 0; - if (e_snprintf(buf, 128, "%s:%s", group, event) < 0) - die("Failed to copy event."); + ret = e_snprintf(buf, 128, "%s:%s", group, event); + if (ret < 0) { + pr_err("Failed to copy event."); + return ret; + } if (strpbrk(buf, "*?")) { /* Glob-exp */ strlist__for_each_safe(ent, n, namelist) if (strglobmatch(ent->s, buf)) { found++; - __del_trace_kprobe_event(fd, ent); + ret = __del_trace_kprobe_event(fd, ent); + if (ret < 0) + break; strlist__remove(namelist, ent); } } else { ent = strlist__find(namelist, buf); if (ent) { found++; - __del_trace_kprobe_event(fd, ent); - strlist__remove(namelist, ent); + ret = __del_trace_kprobe_event(fd, ent); + if (ret >= 0) + strlist__remove(namelist, ent); } } - if (found == 0) - pr_info("Info: event \"%s\" does not exist, could not remove it.\n", buf); + if (found == 0 && ret >= 0) + pr_info("Info: Event \"%s\" does not exist.\n", buf); + + return ret; } -void del_trace_kprobe_events(struct strlist *dellist) +int del_perf_probe_events(struct strlist *dellist) { - int fd; + int fd, ret = 0; const char *group, *event; char *p, *str; struct str_node *ent; struct strlist *namelist; - fd = open_kprobe_events(O_RDWR, O_APPEND); + fd = open_kprobe_events(true); + if (fd < 0) + return fd; + /* Get current event names */ - namelist = get_perf_event_names(fd, true); + namelist = get_kprobe_trace_event_names(fd, true); + if (namelist == NULL) + return -EINVAL; strlist__for_each(ent, dellist) { str = strdup(ent->s); - if (!str) - die("Failed to copy event."); + if (str == NULL) { + ret = -ENOMEM; + break; + } pr_debug("Parsing: %s\n", str); p = strchr(str, ':'); if (p) { @@ -723,80 +1627,14 @@ void del_trace_kprobe_events(struct strlist *dellist) event = str; } pr_debug("Group: %s, Event: %s\n", group, event); - del_trace_kprobe_event(fd, group, event, namelist); + ret = del_trace_kprobe_event(fd, group, event, namelist); free(str); + if (ret < 0) + break; } strlist__delete(namelist); close(fd); -} -#define LINEBUF_SIZE 256 -#define NR_ADDITIONAL_LINES 2 - -static void show_one_line(FILE *fp, unsigned int l, bool skip, bool show_num) -{ - char buf[LINEBUF_SIZE]; - const char *color = PERF_COLOR_BLUE; - - if (fgets(buf, LINEBUF_SIZE, fp) == NULL) - goto error; - if (!skip) { - if (show_num) - fprintf(stdout, "%7u %s", l, buf); - else - color_fprintf(stdout, color, " %s", buf); - } - - while (strlen(buf) == LINEBUF_SIZE - 1 && - buf[LINEBUF_SIZE - 2] != '\n') { - if (fgets(buf, LINEBUF_SIZE, fp) == NULL) - goto error; - if (!skip) { - if (show_num) - fprintf(stdout, "%s", buf); - else - color_fprintf(stdout, color, "%s", buf); - } - } - return; -error: - if (feof(fp)) - die("Source file is shorter than expected."); - else - die("File read error: %s", strerror(errno)); + return ret; } -void show_line_range(struct line_range *lr) -{ - unsigned int l = 1; - struct line_node *ln; - FILE *fp; - - setup_pager(); - - if (lr->function) - fprintf(stdout, "<%s:%d>\n", lr->function, - lr->start - lr->offset); - else - fprintf(stdout, "<%s:%d>\n", lr->file, lr->start); - - fp = fopen(lr->path, "r"); - if (fp == NULL) - die("Failed to open %s: %s", lr->path, strerror(errno)); - /* Skip to starting line number */ - while (l < lr->start) - show_one_line(fp, l++, true, false); - - list_for_each_entry(ln, &lr->line_list, list) { - while (ln->line > l) - show_one_line(fp, (l++) - lr->offset, false, false); - show_one_line(fp, (l++) - lr->offset, false, true); - } - - if (lr->end == INT_MAX) - lr->end = l + NR_ADDITIONAL_LINES; - while (l < lr->end && !feof(fp)) - show_one_line(fp, (l++) - lr->offset, false, false); - - fclose(fp); -} diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 711287d4baea..e7ff0d02c0d4 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -2,21 +2,125 @@ #define _PROBE_EVENT_H #include <stdbool.h> -#include "probe-finder.h" #include "strlist.h" -extern void parse_line_range_desc(const char *arg, struct line_range *lr); -extern void parse_perf_probe_event(const char *str, struct probe_point *pp, - bool *need_dwarf); -extern int synthesize_perf_probe_point(struct probe_point *pp); -extern int synthesize_perf_probe_event(struct probe_point *pp); -extern void parse_trace_kprobe_event(const char *str, struct probe_point *pp); -extern int synthesize_trace_kprobe_event(struct probe_point *pp); -extern void add_trace_kprobe_events(struct probe_point *probes, int nr_probes, - bool force_add); -extern void del_trace_kprobe_events(struct strlist *dellist); -extern void show_perf_probe_events(void); -extern void show_line_range(struct line_range *lr); +extern bool probe_event_dry_run; + +/* kprobe-tracer tracing point */ +struct kprobe_trace_point { + char *symbol; /* Base symbol */ + unsigned long offset; /* Offset from symbol */ + bool retprobe; /* Return probe flag */ +}; + +/* kprobe-tracer tracing argument referencing offset */ +struct kprobe_trace_arg_ref { + struct kprobe_trace_arg_ref *next; /* Next reference */ + long offset; /* Offset value */ +}; + +/* kprobe-tracer tracing argument */ +struct kprobe_trace_arg { + char *name; /* Argument name */ + char *value; /* Base value */ + char *type; /* Type name */ + struct kprobe_trace_arg_ref *ref; /* Referencing offset */ +}; + +/* kprobe-tracer tracing event (point + arg) */ +struct kprobe_trace_event { + char *event; /* Event name */ + char *group; /* Group name */ + struct kprobe_trace_point point; /* Trace point */ + int nargs; /* Number of args */ + struct kprobe_trace_arg *args; /* Arguments */ +}; + +/* Perf probe probing point */ +struct perf_probe_point { + char *file; /* File path */ + char *function; /* Function name */ + int line; /* Line number */ + bool retprobe; /* Return probe flag */ + char *lazy_line; /* Lazy matching pattern */ + unsigned long offset; /* Offset from function entry */ +}; + +/* Perf probe probing argument field chain */ +struct perf_probe_arg_field { + struct perf_probe_arg_field *next; /* Next field */ + char *name; /* Name of the field */ + bool ref; /* Referencing flag */ +}; + +/* Perf probe probing argument */ +struct perf_probe_arg { + char *name; /* Argument name */ + char *var; /* Variable name */ + char *type; /* Type name */ + struct perf_probe_arg_field *field; /* Structure fields */ +}; + +/* Perf probe probing event (point + arg) */ +struct perf_probe_event { + char *event; /* Event name */ + char *group; /* Group name */ + struct perf_probe_point point; /* Probe point */ + int nargs; /* Number of arguments */ + struct perf_probe_arg *args; /* Arguments */ +}; + + +/* Line number container */ +struct line_node { + struct list_head list; + int line; +}; + +/* Line range */ +struct line_range { + char *file; /* File name */ + char *function; /* Function name */ + int start; /* Start line number */ + int end; /* End line number */ + int offset; /* Start line offset */ + char *path; /* Real path name */ + struct list_head line_list; /* Visible lines */ +}; + +/* Command string to events */ +extern int parse_perf_probe_command(const char *cmd, + struct perf_probe_event *pev); +extern int parse_kprobe_trace_command(const char *cmd, + struct kprobe_trace_event *tev); + +/* Events to command string */ +extern char *synthesize_perf_probe_command(struct perf_probe_event *pev); +extern char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev); +extern int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, + size_t len); + +/* Check the perf_probe_event needs debuginfo */ +extern bool perf_probe_event_need_dwarf(struct perf_probe_event *pev); + +/* Convert from kprobe_trace_event to perf_probe_event */ +extern int convert_to_perf_probe_event(struct kprobe_trace_event *tev, + struct perf_probe_event *pev); + +/* Release event contents */ +extern void clear_perf_probe_event(struct perf_probe_event *pev); +extern void clear_kprobe_trace_event(struct kprobe_trace_event *tev); + +/* Command string to line-range */ +extern int parse_line_range_desc(const char *cmd, struct line_range *lr); + + +extern int add_perf_probe_events(struct perf_probe_event *pevs, int ntevs, + bool force_add); +extern int del_perf_probe_events(struct strlist *dellist); +extern int show_perf_probe_events(void); +extern int show_line_range(struct line_range *lr); + /* Maximum index number of event-name postfix */ #define MAX_EVENT_INDEX 1024 diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index c171a243d05b..3e7977560be5 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -84,6 +84,9 @@ const char *x86_64_regs_table[X86_64_MAX_REGS] = { #define arch_regs_table x86_32_regs_table #endif +/* Kprobe tracer basic type is up to u64 */ +#define MAX_BASIC_TYPE_BITS 64 + /* Return architecture dependent register string (for kprobe-tracer) */ static const char *get_arch_regstr(unsigned int n) { @@ -108,7 +111,7 @@ static int strtailcmp(const char *s1, const char *s2) /* Line number list operations */ /* Add a line to line number list */ -static void line_list__add_line(struct list_head *head, unsigned int line) +static int line_list__add_line(struct list_head *head, int line) { struct line_node *ln; struct list_head *p; @@ -119,21 +122,23 @@ static void line_list__add_line(struct list_head *head, unsigned int line) p = &ln->list; goto found; } else if (ln->line == line) /* Already exist */ - return ; + return 1; } /* List is empty, or the smallest entry */ p = head; found: pr_debug("line list: add a line %u\n", line); ln = zalloc(sizeof(struct line_node)); - DIE_IF(ln == NULL); + if (ln == NULL) + return -ENOMEM; ln->line = line; INIT_LIST_HEAD(&ln->list); list_add(&ln->list, p); + return 0; } /* Check if the line in line number list */ -static int line_list__has_line(struct list_head *head, unsigned int line) +static int line_list__has_line(struct list_head *head, int line) { struct line_node *ln; @@ -184,9 +189,129 @@ static const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname) if (strtailcmp(src, fname) == 0) break; } + if (i == nfiles) + return NULL; return src; } +/* Compare diename and tname */ +static bool die_compare_name(Dwarf_Die *dw_die, const char *tname) +{ + const char *name; + name = dwarf_diename(dw_die); + return name ? strcmp(tname, name) : -1; +} + +/* Get type die, but skip qualifiers and typedef */ +static Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem) +{ + Dwarf_Attribute attr; + int tag; + + do { + if (dwarf_attr(vr_die, DW_AT_type, &attr) == NULL || + dwarf_formref_die(&attr, die_mem) == NULL) + return NULL; + + tag = dwarf_tag(die_mem); + vr_die = die_mem; + } while (tag == DW_TAG_const_type || + tag == DW_TAG_restrict_type || + tag == DW_TAG_volatile_type || + tag == DW_TAG_shared_type || + tag == DW_TAG_typedef); + + return die_mem; +} + +static bool die_is_signed_type(Dwarf_Die *tp_die) +{ + Dwarf_Attribute attr; + Dwarf_Word ret; + + if (dwarf_attr(tp_die, DW_AT_encoding, &attr) == NULL || + dwarf_formudata(&attr, &ret) != 0) + return false; + + return (ret == DW_ATE_signed_char || ret == DW_ATE_signed || + ret == DW_ATE_signed_fixed); +} + +static int die_get_byte_size(Dwarf_Die *tp_die) +{ + Dwarf_Attribute attr; + Dwarf_Word ret; + + if (dwarf_attr(tp_die, DW_AT_byte_size, &attr) == NULL || + dwarf_formudata(&attr, &ret) != 0) + return 0; + + return (int)ret; +} + +/* Get data_member_location offset */ +static int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs) +{ + Dwarf_Attribute attr; + Dwarf_Op *expr; + size_t nexpr; + int ret; + + if (dwarf_attr(mb_die, DW_AT_data_member_location, &attr) == NULL) + return -ENOENT; + + if (dwarf_formudata(&attr, offs) != 0) { + /* DW_AT_data_member_location should be DW_OP_plus_uconst */ + ret = dwarf_getlocation(&attr, &expr, &nexpr); + if (ret < 0 || nexpr == 0) + return -ENOENT; + + if (expr[0].atom != DW_OP_plus_uconst || nexpr != 1) { + pr_debug("Unable to get offset:Unexpected OP %x (%zd)\n", + expr[0].atom, nexpr); + return -ENOTSUP; + } + *offs = (Dwarf_Word)expr[0].number; + } + return 0; +} + +/* Return values for die_find callbacks */ +enum { + DIE_FIND_CB_FOUND = 0, /* End of Search */ + DIE_FIND_CB_CHILD = 1, /* Search only children */ + DIE_FIND_CB_SIBLING = 2, /* Search only siblings */ + DIE_FIND_CB_CONTINUE = 3, /* Search children and siblings */ +}; + +/* Search a child die */ +static Dwarf_Die *die_find_child(Dwarf_Die *rt_die, + int (*callback)(Dwarf_Die *, void *), + void *data, Dwarf_Die *die_mem) +{ + Dwarf_Die child_die; + int ret; + + ret = dwarf_child(rt_die, die_mem); + if (ret != 0) + return NULL; + + do { + ret = callback(die_mem, data); + if (ret == DIE_FIND_CB_FOUND) + return die_mem; + + if ((ret & DIE_FIND_CB_CHILD) && + die_find_child(die_mem, callback, data, &child_die)) { + memcpy(die_mem, &child_die, sizeof(Dwarf_Die)); + return die_mem; + } + } while ((ret & DIE_FIND_CB_SIBLING) && + dwarf_siblingof(die_mem, die_mem) == 0); + + return NULL; +} + struct __addr_die_search_param { Dwarf_Addr addr; Dwarf_Die *die_mem; @@ -205,8 +330,8 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data) } /* Search a real subprogram including this line, */ -static Dwarf_Die *die_get_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr, - Dwarf_Die *die_mem) +static Dwarf_Die *die_find_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr, + Dwarf_Die *die_mem) { struct __addr_die_search_param ad; ad.addr = addr; @@ -218,77 +343,64 @@ static Dwarf_Die *die_get_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr, return die_mem; } -/* Similar to dwarf_getfuncs, but returns inlined_subroutine if exists. */ -static Dwarf_Die *die_get_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, - Dwarf_Die *die_mem) +/* die_find callback for inline function search */ +static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data) { - Dwarf_Die child_die; - int ret; + Dwarf_Addr *addr = data; - ret = dwarf_child(sp_die, die_mem); - if (ret != 0) - return NULL; + if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine && + dwarf_haspc(die_mem, *addr)) + return DIE_FIND_CB_FOUND; - do { - if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine && - dwarf_haspc(die_mem, addr)) - return die_mem; - - if (die_get_inlinefunc(die_mem, addr, &child_die)) { - memcpy(die_mem, &child_die, sizeof(Dwarf_Die)); - return die_mem; - } - } while (dwarf_siblingof(die_mem, die_mem) == 0); - - return NULL; + return DIE_FIND_CB_CONTINUE; } -/* Compare diename and tname */ -static bool die_compare_name(Dwarf_Die *dw_die, const char *tname) +/* Similar to dwarf_getfuncs, but returns inlined_subroutine if exists. */ +static Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, + Dwarf_Die *die_mem) { - const char *name; - name = dwarf_diename(dw_die); - DIE_IF(name == NULL); - return strcmp(tname, name); + return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem); } -/* Get entry pc(or low pc, 1st entry of ranges) of the die */ -static Dwarf_Addr die_get_entrypc(Dwarf_Die *dw_die) +static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data) { - Dwarf_Addr epc; - int ret; + const char *name = data; + int tag; - ret = dwarf_entrypc(dw_die, &epc); - DIE_IF(ret == -1); - return epc; + tag = dwarf_tag(die_mem); + if ((tag == DW_TAG_formal_parameter || + tag == DW_TAG_variable) && + (die_compare_name(die_mem, name) == 0)) + return DIE_FIND_CB_FOUND; + + return DIE_FIND_CB_CONTINUE; } -/* Get a variable die */ +/* Find a variable called 'name' */ static Dwarf_Die *die_find_variable(Dwarf_Die *sp_die, const char *name, Dwarf_Die *die_mem) { - Dwarf_Die child_die; - int tag; - int ret; + return die_find_child(sp_die, __die_find_variable_cb, (void *)name, + die_mem); +} - ret = dwarf_child(sp_die, die_mem); - if (ret != 0) - return NULL; +static int __die_find_member_cb(Dwarf_Die *die_mem, void *data) +{ + const char *name = data; - do { - tag = dwarf_tag(die_mem); - if ((tag == DW_TAG_formal_parameter || - tag == DW_TAG_variable) && - (die_compare_name(die_mem, name) == 0)) - return die_mem; + if ((dwarf_tag(die_mem) == DW_TAG_member) && + (die_compare_name(die_mem, name) == 0)) + return DIE_FIND_CB_FOUND; - if (die_find_variable(die_mem, name, &child_die)) { - memcpy(die_mem, &child_die, sizeof(Dwarf_Die)); - return die_mem; - } - } while (dwarf_siblingof(die_mem, die_mem) == 0); + return DIE_FIND_CB_SIBLING; +} - return NULL; +/* Find a member called 'name' */ +static Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name, + Dwarf_Die *die_mem) +{ + return die_find_child(st_die, __die_find_member_cb, (void *)name, + die_mem); } /* @@ -296,19 +408,22 @@ static Dwarf_Die *die_find_variable(Dwarf_Die *sp_die, const char *name, */ /* Show a location */ -static void show_location(Dwarf_Op *op, struct probe_finder *pf) +static int convert_location(Dwarf_Op *op, struct probe_finder *pf) { unsigned int regn; Dwarf_Word offs = 0; - int deref = 0, ret; + bool ref = false; const char *regs; + struct kprobe_trace_arg *tvar = pf->tvar; - /* TODO: support CFA */ /* If this is based on frame buffer, set the offset */ if (op->atom == DW_OP_fbreg) { - if (pf->fb_ops == NULL) - die("The attribute of frame base is not supported.\n"); - deref = 1; + if (pf->fb_ops == NULL) { + pr_warning("The attribute of frame base is not " + "supported.\n"); + return -ENOTSUP; + } + ref = true; offs = op->number; op = &pf->fb_ops[0]; } @@ -316,35 +431,164 @@ static void show_location(Dwarf_Op *op, struct probe_finder *pf) if (op->atom >= DW_OP_breg0 && op->atom <= DW_OP_breg31) { regn = op->atom - DW_OP_breg0; offs += op->number; - deref = 1; + ref = true; } else if (op->atom >= DW_OP_reg0 && op->atom <= DW_OP_reg31) { regn = op->atom - DW_OP_reg0; } else if (op->atom == DW_OP_bregx) { regn = op->number; offs += op->number2; - deref = 1; + ref = true; } else if (op->atom == DW_OP_regx) { regn = op->number; - } else - die("DW_OP %d is not supported.", op->atom); + } else { + pr_warning("DW_OP %x is not supported.\n", op->atom); + return -ENOTSUP; + } regs = get_arch_regstr(regn); - if (!regs) - die("%u exceeds max register number.", regn); + if (!regs) { + pr_warning("%u exceeds max register number.\n", regn); + return -ERANGE; + } + + tvar->value = strdup(regs); + if (tvar->value == NULL) + return -ENOMEM; + + if (ref) { + tvar->ref = zalloc(sizeof(struct kprobe_trace_arg_ref)); + if (tvar->ref == NULL) + return -ENOMEM; + tvar->ref->offset = (long)offs; + } + return 0; +} + +static int convert_variable_type(Dwarf_Die *vr_die, + struct kprobe_trace_arg *targ) +{ + Dwarf_Die type; + char buf[16]; + int ret; + + if (die_get_real_type(vr_die, &type) == NULL) { + pr_warning("Failed to get a type information of %s.\n", + dwarf_diename(vr_die)); + return -ENOENT; + } + + ret = die_get_byte_size(&type) * 8; + if (ret) { + /* Check the bitwidth */ + if (ret > MAX_BASIC_TYPE_BITS) { + pr_info("%s exceeds max-bitwidth." + " Cut down to %d bits.\n", + dwarf_diename(&type), MAX_BASIC_TYPE_BITS); + ret = MAX_BASIC_TYPE_BITS; + } + + ret = snprintf(buf, 16, "%c%d", + die_is_signed_type(&type) ? 's' : 'u', ret); + if (ret < 0 || ret >= 16) { + if (ret >= 16) + ret = -E2BIG; + pr_warning("Failed to convert variable type: %s\n", + strerror(-ret)); + return ret; + } + targ->type = strdup(buf); + if (targ->type == NULL) + return -ENOMEM; + } + return 0; +} + +static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, + struct perf_probe_arg_field *field, + struct kprobe_trace_arg_ref **ref_ptr, + Dwarf_Die *die_mem) +{ + struct kprobe_trace_arg_ref *ref = *ref_ptr; + Dwarf_Die type; + Dwarf_Word offs; + int ret; + + pr_debug("converting %s in %s\n", field->name, varname); + if (die_get_real_type(vr_die, &type) == NULL) { + pr_warning("Failed to get the type of %s.\n", varname); + return -ENOENT; + } - if (deref) - ret = snprintf(pf->buf, pf->len, " %s=%+jd(%s)", - pf->var, (intmax_t)offs, regs); + /* Check the pointer and dereference */ + if (dwarf_tag(&type) == DW_TAG_pointer_type) { + if (!field->ref) { + pr_err("Semantic error: %s must be referred by '->'\n", + field->name); + return -EINVAL; + } + /* Get the type pointed by this pointer */ + if (die_get_real_type(&type, &type) == NULL) { + pr_warning("Failed to get the type of %s.\n", varname); + return -ENOENT; + } + /* Verify it is a data structure */ + if (dwarf_tag(&type) != DW_TAG_structure_type) { + pr_warning("%s is not a data structure.\n", varname); + return -EINVAL; + } + + ref = zalloc(sizeof(struct kprobe_trace_arg_ref)); + if (ref == NULL) + return -ENOMEM; + if (*ref_ptr) + (*ref_ptr)->next = ref; + else + *ref_ptr = ref; + } else { + /* Verify it is a data structure */ + if (dwarf_tag(&type) != DW_TAG_structure_type) { + pr_warning("%s is not a data structure.\n", varname); + return -EINVAL; + } + if (field->ref) { + pr_err("Semantic error: %s must be referred by '.'\n", + field->name); + return -EINVAL; + } + if (!ref) { + pr_warning("Structure on a register is not " + "supported yet.\n"); + return -ENOTSUP; + } + } + + if (die_find_member(&type, field->name, die_mem) == NULL) { + pr_warning("%s(tyep:%s) has no member %s.\n", varname, + dwarf_diename(&type), field->name); + return -EINVAL; + } + + /* Get the offset of the field */ + ret = die_get_data_member_location(die_mem, &offs); + if (ret < 0) { + pr_warning("Failed to get the offset of %s.\n", field->name); + return ret; + } + ref->offset += (long)offs; + + /* Converting next field */ + if (field->next) + return convert_variable_fields(die_mem, field->name, + field->next, &ref, die_mem); else - ret = snprintf(pf->buf, pf->len, " %s=%s", pf->var, regs); - DIE_IF(ret < 0); - DIE_IF(ret >= pf->len); + return 0; } /* Show a variables in kprobe event format */ -static void show_variable(Dwarf_Die *vr_die, struct probe_finder *pf) +static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) { Dwarf_Attribute attr; + Dwarf_Die die_mem; Dwarf_Op *expr; size_t nexpr; int ret; @@ -356,142 +600,190 @@ static void show_variable(Dwarf_Die *vr_die, struct probe_finder *pf) if (ret <= 0 || nexpr == 0) goto error; - show_location(expr, pf); + ret = convert_location(expr, pf); + if (ret == 0 && pf->pvar->field) { + ret = convert_variable_fields(vr_die, pf->pvar->var, + pf->pvar->field, &pf->tvar->ref, + &die_mem); + vr_die = &die_mem; + } + if (ret == 0) { + if (pf->pvar->type) { + pf->tvar->type = strdup(pf->pvar->type); + if (pf->tvar->type == NULL) + ret = -ENOMEM; + } else + ret = convert_variable_type(vr_die, pf->tvar); + } /* *expr will be cached in libdw. Don't free it. */ - return ; + return ret; error: /* TODO: Support const_value */ - die("Failed to find the location of %s at this address.\n" - " Perhaps, it has been optimized out.", pf->var); + pr_err("Failed to find the location of %s at this address.\n" + " Perhaps, it has been optimized out.\n", pf->pvar->var); + return -ENOENT; } /* Find a variable in a subprogram die */ -static void find_variable(Dwarf_Die *sp_die, struct probe_finder *pf) +static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf) { - int ret; Dwarf_Die vr_die; + char buf[32], *ptr; + int ret; - /* TODO: Support struct members and arrays */ - if (!is_c_varname(pf->var)) { - /* Output raw parameters */ - ret = snprintf(pf->buf, pf->len, " %s", pf->var); - DIE_IF(ret < 0); - DIE_IF(ret >= pf->len); - return ; + /* TODO: Support arrays */ + if (pf->pvar->name) + pf->tvar->name = strdup(pf->pvar->name); + else { + ret = synthesize_perf_probe_arg(pf->pvar, buf, 32); + if (ret < 0) + return ret; + ptr = strchr(buf, ':'); /* Change type separator to _ */ + if (ptr) + *ptr = '_'; + pf->tvar->name = strdup(buf); + } + if (pf->tvar->name == NULL) + return -ENOMEM; + + if (!is_c_varname(pf->pvar->var)) { + /* Copy raw parameters */ + pf->tvar->value = strdup(pf->pvar->var); + if (pf->tvar->value == NULL) + return -ENOMEM; + else + return 0; } - pr_debug("Searching '%s' variable in context.\n", pf->var); + pr_debug("Searching '%s' variable in context.\n", + pf->pvar->var); /* Search child die for local variables and parameters. */ - if (!die_find_variable(sp_die, pf->var, &vr_die)) - die("Failed to find '%s' in this function.", pf->var); - - show_variable(&vr_die, pf); + if (!die_find_variable(sp_die, pf->pvar->var, &vr_die)) { + pr_warning("Failed to find '%s' in this function.\n", + pf->pvar->var); + return -ENOENT; + } + return convert_variable(&vr_die, pf); } /* Show a probe point to output buffer */ -static void show_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf) +static int convert_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf) { - struct probe_point *pp = pf->pp; + struct kprobe_trace_event *tev; Dwarf_Addr eaddr; Dwarf_Die die_mem; const char *name; - char tmp[MAX_PROBE_BUFFER]; - int ret, i, len; + int ret, i; Dwarf_Attribute fb_attr; size_t nops; + if (pf->ntevs == MAX_PROBES) { + pr_warning("Too many( > %d) probe point found.\n", MAX_PROBES); + return -ERANGE; + } + tev = &pf->tevs[pf->ntevs++]; + /* If no real subprogram, find a real one */ if (!sp_die || dwarf_tag(sp_die) != DW_TAG_subprogram) { - sp_die = die_get_real_subprogram(&pf->cu_die, + sp_die = die_find_real_subprogram(&pf->cu_die, pf->addr, &die_mem); - if (!sp_die) - die("Probe point is not found in subprograms."); + if (!sp_die) { + pr_warning("Failed to find probe point in any " + "functions.\n"); + return -ENOENT; + } } - /* Output name of probe point */ + /* Copy the name of probe point */ name = dwarf_diename(sp_die); if (name) { - dwarf_entrypc(sp_die, &eaddr); - ret = snprintf(tmp, MAX_PROBE_BUFFER, "%s+%lu", name, - (unsigned long)(pf->addr - eaddr)); - /* Copy the function name if possible */ - if (!pp->function) { - pp->function = strdup(name); - pp->offset = (size_t)(pf->addr - eaddr); + if (dwarf_entrypc(sp_die, &eaddr) != 0) { + pr_warning("Failed to get entry pc of %s\n", + dwarf_diename(sp_die)); + return -ENOENT; } - } else { + tev->point.symbol = strdup(name); + if (tev->point.symbol == NULL) + return -ENOMEM; + tev->point.offset = (unsigned long)(pf->addr - eaddr); + } else /* This function has no name. */ - ret = snprintf(tmp, MAX_PROBE_BUFFER, "0x%jx", - (uintmax_t)pf->addr); - if (!pp->function) { - /* TODO: Use _stext */ - pp->function = strdup(""); - pp->offset = (size_t)pf->addr; - } - } - DIE_IF(ret < 0); - DIE_IF(ret >= MAX_PROBE_BUFFER); - len = ret; - pr_debug("Probe point found: %s\n", tmp); + tev->point.offset = (unsigned long)pf->addr; + + pr_debug("Probe point found: %s+%lu\n", tev->point.symbol, + tev->point.offset); /* Get the frame base attribute/ops */ dwarf_attr(sp_die, DW_AT_frame_base, &fb_attr); ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1); - if (ret <= 0 || nops == 0) + if (ret <= 0 || nops == 0) { pf->fb_ops = NULL; + } else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa && + pf->cfi != NULL) { + Dwarf_Frame *frame; + if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 || + dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) { + pr_warning("Failed to get CFA on 0x%jx\n", + (uintmax_t)pf->addr); + return -ENOENT; + } + } /* Find each argument */ - /* TODO: use dwarf_cfi_addrframe */ - for (i = 0; i < pp->nr_args; i++) { - pf->var = pp->args[i]; - pf->buf = &tmp[len]; - pf->len = MAX_PROBE_BUFFER - len; - find_variable(sp_die, pf); - len += strlen(pf->buf); + tev->nargs = pf->pev->nargs; + tev->args = zalloc(sizeof(struct kprobe_trace_arg) * tev->nargs); + if (tev->args == NULL) + return -ENOMEM; + for (i = 0; i < pf->pev->nargs; i++) { + pf->pvar = &pf->pev->args[i]; + pf->tvar = &tev->args[i]; + ret = find_variable(sp_die, pf); + if (ret != 0) + return ret; } /* *pf->fb_ops will be cached in libdw. Don't free it. */ pf->fb_ops = NULL; - - if (pp->found == MAX_PROBES) - die("Too many( > %d) probe point found.\n", MAX_PROBES); - - pp->probes[pp->found] = strdup(tmp); - pp->found++; + return 0; } /* Find probe point from its line number */ -static void find_probe_point_by_line(struct probe_finder *pf) +static int find_probe_point_by_line(struct probe_finder *pf) { Dwarf_Lines *lines; Dwarf_Line *line; size_t nlines, i; Dwarf_Addr addr; int lineno; - int ret; + int ret = 0; - ret = dwarf_getsrclines(&pf->cu_die, &lines, &nlines); - DIE_IF(ret != 0); + if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) { + pr_warning("No source lines found in this CU.\n"); + return -ENOENT; + } - for (i = 0; i < nlines; i++) { + for (i = 0; i < nlines && ret == 0; i++) { line = dwarf_onesrcline(lines, i); - dwarf_lineno(line, &lineno); - if (lineno != pf->lno) + if (dwarf_lineno(line, &lineno) != 0 || + lineno != pf->lno) continue; /* TODO: Get fileno from line, but how? */ if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0) continue; - ret = dwarf_lineaddr(line, &addr); - DIE_IF(ret != 0); + if (dwarf_lineaddr(line, &addr) != 0) { + pr_warning("Failed to get the address of the line.\n"); + return -ENOENT; + } pr_debug("Probe line found: line[%d]:%d addr:0x%jx\n", (int)i, lineno, (uintmax_t)addr); pf->addr = addr; - show_probe_point(NULL, pf); + ret = convert_probe_point(NULL, pf); /* Continuing, because target line might be inlined. */ } + return ret; } /* Find lines which match lazy pattern */ @@ -499,16 +791,27 @@ static int find_lazy_match_lines(struct list_head *head, const char *fname, const char *pat) { char *fbuf, *p1, *p2; - int fd, line, nlines = 0; + int fd, ret, line, nlines = 0; struct stat st; fd = open(fname, O_RDONLY); - if (fd < 0) - die("failed to open %s", fname); - DIE_IF(fstat(fd, &st) < 0); - fbuf = malloc(st.st_size + 2); - DIE_IF(fbuf == NULL); - DIE_IF(read(fd, fbuf, st.st_size) < 0); + if (fd < 0) { + pr_warning("Failed to open %s: %s\n", fname, strerror(-fd)); + return fd; + } + + ret = fstat(fd, &st); + if (ret < 0) { + pr_warning("Failed to get the size of %s: %s\n", + fname, strerror(errno)); + return ret; + } + fbuf = xmalloc(st.st_size + 2); + ret = read(fd, fbuf, st.st_size); + if (ret < 0) { + pr_warning("Failed to read %s: %s\n", fname, strerror(errno)); + return ret; + } close(fd); fbuf[st.st_size] = '\n'; /* Dummy line */ fbuf[st.st_size + 1] = '\0'; @@ -528,7 +831,7 @@ static int find_lazy_match_lines(struct list_head *head, } /* Find probe points from lazy pattern */ -static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) +static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) { Dwarf_Lines *lines; Dwarf_Line *line; @@ -536,37 +839,46 @@ static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) Dwarf_Addr addr; Dwarf_Die die_mem; int lineno; - int ret; + int ret = 0; if (list_empty(&pf->lcache)) { /* Matching lazy line pattern */ ret = find_lazy_match_lines(&pf->lcache, pf->fname, - pf->pp->lazy_line); - if (ret <= 0) - die("No matched lines found in %s.", pf->fname); + pf->pev->point.lazy_line); + if (ret == 0) { + pr_debug("No matched lines found in %s.\n", pf->fname); + return 0; + } else if (ret < 0) + return ret; } - ret = dwarf_getsrclines(&pf->cu_die, &lines, &nlines); - DIE_IF(ret != 0); - for (i = 0; i < nlines; i++) { + if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) { + pr_warning("No source lines found in this CU.\n"); + return -ENOENT; + } + + for (i = 0; i < nlines && ret >= 0; i++) { line = dwarf_onesrcline(lines, i); - dwarf_lineno(line, &lineno); - if (!line_list__has_line(&pf->lcache, lineno)) + if (dwarf_lineno(line, &lineno) != 0 || + !line_list__has_line(&pf->lcache, lineno)) continue; /* TODO: Get fileno from line, but how? */ if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0) continue; - ret = dwarf_lineaddr(line, &addr); - DIE_IF(ret != 0); + if (dwarf_lineaddr(line, &addr) != 0) { + pr_debug("Failed to get the address of line %d.\n", + lineno); + continue; + } if (sp_die) { /* Address filtering 1: does sp_die include addr? */ if (!dwarf_haspc(sp_die, addr)) continue; /* Address filtering 2: No child include addr? */ - if (die_get_inlinefunc(sp_die, addr, &die_mem)) + if (die_find_inlinefunc(sp_die, addr, &die_mem)) continue; } @@ -574,27 +886,42 @@ static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) (int)i, lineno, (unsigned long long)addr); pf->addr = addr; - show_probe_point(sp_die, pf); + ret = convert_probe_point(sp_die, pf); /* Continuing, because target line might be inlined. */ } /* TODO: deallocate lines, but how? */ + return ret; } +/* Callback parameter with return value */ +struct dwarf_callback_param { + void *data; + int retval; +}; + static int probe_point_inline_cb(Dwarf_Die *in_die, void *data) { - struct probe_finder *pf = (struct probe_finder *)data; - struct probe_point *pp = pf->pp; + struct dwarf_callback_param *param = data; + struct probe_finder *pf = param->data; + struct perf_probe_point *pp = &pf->pev->point; + Dwarf_Addr addr; if (pp->lazy_line) - find_probe_point_lazy(in_die, pf); + param->retval = find_probe_point_lazy(in_die, pf); else { /* Get probe address */ - pf->addr = die_get_entrypc(in_die); + if (dwarf_entrypc(in_die, &addr) != 0) { + pr_warning("Failed to get entry pc of %s.\n", + dwarf_diename(in_die)); + param->retval = -ENOENT; + return DWARF_CB_ABORT; + } + pf->addr = addr; pf->addr += pp->offset; pr_debug("found inline addr: 0x%jx\n", (uintmax_t)pf->addr); - show_probe_point(in_die, pf); + param->retval = convert_probe_point(in_die, pf); } return DWARF_CB_OK; @@ -603,59 +930,88 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data) /* Search function from function name */ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) { - struct probe_finder *pf = (struct probe_finder *)data; - struct probe_point *pp = pf->pp; + struct dwarf_callback_param *param = data; + struct probe_finder *pf = param->data; + struct perf_probe_point *pp = &pf->pev->point; /* Check tag and diename */ if (dwarf_tag(sp_die) != DW_TAG_subprogram || die_compare_name(sp_die, pp->function) != 0) - return 0; + return DWARF_CB_OK; pf->fname = dwarf_decl_file(sp_die); if (pp->line) { /* Function relative line */ dwarf_decl_line(sp_die, &pf->lno); pf->lno += pp->line; - find_probe_point_by_line(pf); + param->retval = find_probe_point_by_line(pf); } else if (!dwarf_func_inline(sp_die)) { /* Real function */ if (pp->lazy_line) - find_probe_point_lazy(sp_die, pf); + param->retval = find_probe_point_lazy(sp_die, pf); else { - pf->addr = die_get_entrypc(sp_die); + if (dwarf_entrypc(sp_die, &pf->addr) != 0) { + pr_warning("Failed to get entry pc of %s.\n", + dwarf_diename(sp_die)); + param->retval = -ENOENT; + return DWARF_CB_ABORT; + } pf->addr += pp->offset; /* TODO: Check the address in this function */ - show_probe_point(sp_die, pf); + param->retval = convert_probe_point(sp_die, pf); } - } else + } else { + struct dwarf_callback_param _param = {.data = (void *)pf, + .retval = 0}; /* Inlined function: search instances */ - dwarf_func_inline_instances(sp_die, probe_point_inline_cb, pf); + dwarf_func_inline_instances(sp_die, probe_point_inline_cb, + &_param); + param->retval = _param.retval; + } - return 1; /* Exit; no same symbol in this CU. */ + return DWARF_CB_ABORT; /* Exit; no same symbol in this CU. */ } -static void find_probe_point_by_func(struct probe_finder *pf) +static int find_probe_point_by_func(struct probe_finder *pf) { - dwarf_getfuncs(&pf->cu_die, probe_point_search_cb, pf, 0); + struct dwarf_callback_param _param = {.data = (void *)pf, + .retval = 0}; + dwarf_getfuncs(&pf->cu_die, probe_point_search_cb, &_param, 0); + return _param.retval; } -/* Find a probe point */ -int find_probe_point(int fd, struct probe_point *pp) +/* Find kprobe_trace_events specified by perf_probe_event from debuginfo */ +int find_kprobe_trace_events(int fd, struct perf_probe_event *pev, + struct kprobe_trace_event **tevs) { - struct probe_finder pf = {.pp = pp}; + struct probe_finder pf = {.pev = pev}; + struct perf_probe_point *pp = &pev->point; Dwarf_Off off, noff; size_t cuhl; Dwarf_Die *diep; Dwarf *dbg; + int ret = 0; + + pf.tevs = zalloc(sizeof(struct kprobe_trace_event) * MAX_PROBES); + if (pf.tevs == NULL) + return -ENOMEM; + *tevs = pf.tevs; + pf.ntevs = 0; dbg = dwarf_begin(fd, DWARF_C_READ); - if (!dbg) - return -ENOENT; + if (!dbg) { + pr_warning("No dwarf info found in the vmlinux - " + "please rebuild with CONFIG_DEBUG_INFO=y.\n"); + return -EBADF; + } + + /* Get the call frame information from this dwarf */ + pf.cfi = dwarf_getcfi(dbg); - pp->found = 0; off = 0; line_list__init(&pf.lcache); /* Loop on CUs (Compilation Unit) */ - while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL)) { + while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) && + ret >= 0) { /* Get the DIE(Debugging Information Entry) of this CU */ diep = dwarf_offdie(dbg, off + cuhl, &pf.cu_die); if (!diep) @@ -669,12 +1025,12 @@ int find_probe_point(int fd, struct probe_point *pp) if (!pp->file || pf.fname) { if (pp->function) - find_probe_point_by_func(&pf); + ret = find_probe_point_by_func(&pf); else if (pp->lazy_line) - find_probe_point_lazy(NULL, &pf); + ret = find_probe_point_lazy(NULL, &pf); else { pf.lno = pp->line; - find_probe_point_by_line(&pf); + ret = find_probe_point_by_line(&pf); } } off = noff; @@ -682,41 +1038,167 @@ int find_probe_point(int fd, struct probe_point *pp) line_list__free(&pf.lcache); dwarf_end(dbg); - return pp->found; + return (ret < 0) ? ret : pf.ntevs; +} + +/* Reverse search */ +int find_perf_probe_point(int fd, unsigned long addr, + struct perf_probe_point *ppt) +{ + Dwarf_Die cudie, spdie, indie; + Dwarf *dbg; + Dwarf_Line *line; + Dwarf_Addr laddr, eaddr; + const char *tmp; + int lineno, ret = 0; + bool found = false; + + dbg = dwarf_begin(fd, DWARF_C_READ); + if (!dbg) + return -EBADF; + + /* Find cu die */ + if (!dwarf_addrdie(dbg, (Dwarf_Addr)addr, &cudie)) { + ret = -EINVAL; + goto end; + } + + /* Find a corresponding line */ + line = dwarf_getsrc_die(&cudie, (Dwarf_Addr)addr); + if (line) { + if (dwarf_lineaddr(line, &laddr) == 0 && + (Dwarf_Addr)addr == laddr && + dwarf_lineno(line, &lineno) == 0) { + tmp = dwarf_linesrc(line, NULL, NULL); + if (tmp) { + ppt->line = lineno; + ppt->file = strdup(tmp); + if (ppt->file == NULL) { + ret = -ENOMEM; + goto end; + } + found = true; + } + } + } + + /* Find a corresponding function */ + if (die_find_real_subprogram(&cudie, (Dwarf_Addr)addr, &spdie)) { + tmp = dwarf_diename(&spdie); + if (!tmp || dwarf_entrypc(&spdie, &eaddr) != 0) + goto end; + + if (ppt->line) { + if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr, + &indie)) { + /* addr in an inline function */ + tmp = dwarf_diename(&indie); + if (!tmp) + goto end; + ret = dwarf_decl_line(&indie, &lineno); + } else { + if (eaddr == addr) { /* Function entry */ + lineno = ppt->line; + ret = 0; + } else + ret = dwarf_decl_line(&spdie, &lineno); + } + if (ret == 0) { + /* Make a relative line number */ + ppt->line -= lineno; + goto found; + } + } + /* We don't have a line number, let's use offset */ + ppt->offset = addr - (unsigned long)eaddr; +found: + ppt->function = strdup(tmp); + if (ppt->function == NULL) { + ret = -ENOMEM; + goto end; + } + found = true; + } + +end: + dwarf_end(dbg); + if (ret >= 0) + ret = found ? 1 : 0; + return ret; +} + +/* Add a line and store the src path */ +static int line_range_add_line(const char *src, unsigned int lineno, + struct line_range *lr) +{ + /* Copy real path */ + if (!lr->path) { + lr->path = strdup(src); + if (lr->path == NULL) + return -ENOMEM; + } + return line_list__add_line(&lr->line_list, lineno); +} + +/* Search function declaration lines */ +static int line_range_funcdecl_cb(Dwarf_Die *sp_die, void *data) +{ + struct dwarf_callback_param *param = data; + struct line_finder *lf = param->data; + const char *src; + int lineno; + + src = dwarf_decl_file(sp_die); + if (src && strtailcmp(src, lf->fname) != 0) + return DWARF_CB_OK; + + if (dwarf_decl_line(sp_die, &lineno) != 0 || + (lf->lno_s > lineno || lf->lno_e < lineno)) + return DWARF_CB_OK; + + param->retval = line_range_add_line(src, lineno, lf->lr); + return DWARF_CB_OK; +} + +static int find_line_range_func_decl_lines(struct line_finder *lf) +{ + struct dwarf_callback_param param = {.data = (void *)lf, .retval = 0}; + dwarf_getfuncs(&lf->cu_die, line_range_funcdecl_cb, ¶m, 0); + return param.retval; } /* Find line range from its line number */ -static void find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf) +static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf) { Dwarf_Lines *lines; Dwarf_Line *line; size_t nlines, i; Dwarf_Addr addr; - int lineno; - int ret; + int lineno, ret = 0; const char *src; Dwarf_Die die_mem; line_list__init(&lf->lr->line_list); - ret = dwarf_getsrclines(&lf->cu_die, &lines, &nlines); - DIE_IF(ret != 0); + if (dwarf_getsrclines(&lf->cu_die, &lines, &nlines) != 0) { + pr_warning("No source lines found in this CU.\n"); + return -ENOENT; + } + /* Search probable lines on lines list */ for (i = 0; i < nlines; i++) { line = dwarf_onesrcline(lines, i); - ret = dwarf_lineno(line, &lineno); - DIE_IF(ret != 0); - if (lf->lno_s > lineno || lf->lno_e < lineno) + if (dwarf_lineno(line, &lineno) != 0 || + (lf->lno_s > lineno || lf->lno_e < lineno)) continue; if (sp_die) { /* Address filtering 1: does sp_die include addr? */ - ret = dwarf_lineaddr(line, &addr); - DIE_IF(ret != 0); - if (!dwarf_haspc(sp_die, addr)) + if (dwarf_lineaddr(line, &addr) != 0 || + !dwarf_haspc(sp_die, addr)) continue; /* Address filtering 2: No child include addr? */ - if (die_get_inlinefunc(sp_die, addr, &die_mem)) + if (die_find_inlinefunc(sp_die, addr, &die_mem)) continue; } @@ -725,30 +1207,49 @@ static void find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf) if (strtailcmp(src, lf->fname) != 0) continue; - /* Copy real path */ - if (!lf->lr->path) - lf->lr->path = strdup(src); - line_list__add_line(&lf->lr->line_list, (unsigned int)lineno); + ret = line_range_add_line(src, lineno, lf->lr); + if (ret < 0) + return ret; } + + /* + * Dwarf lines doesn't include function declarations. We have to + * check functions list or given function. + */ + if (sp_die) { + src = dwarf_decl_file(sp_die); + if (src && dwarf_decl_line(sp_die, &lineno) == 0 && + (lf->lno_s <= lineno && lf->lno_e >= lineno)) + ret = line_range_add_line(src, lineno, lf->lr); + } else + ret = find_line_range_func_decl_lines(lf); + /* Update status */ - if (!list_empty(&lf->lr->line_list)) - lf->found = 1; + if (ret >= 0) + if (!list_empty(&lf->lr->line_list)) + ret = lf->found = 1; + else + ret = 0; /* Lines are not found */ else { free(lf->lr->path); lf->lr->path = NULL; } + return ret; } static int line_range_inline_cb(Dwarf_Die *in_die, void *data) { - find_line_range_by_line(in_die, (struct line_finder *)data); + struct dwarf_callback_param *param = data; + + param->retval = find_line_range_by_line(in_die, param->data); return DWARF_CB_ABORT; /* No need to find other instances */ } /* Search function from function name */ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) { - struct line_finder *lf = (struct line_finder *)data; + struct dwarf_callback_param *param = data; + struct line_finder *lf = param->data; struct line_range *lr = lf->lr; if (dwarf_tag(sp_die) == DW_TAG_subprogram && @@ -757,44 +1258,55 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) dwarf_decl_line(sp_die, &lr->offset); pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset); lf->lno_s = lr->offset + lr->start; - if (!lr->end) + if (lf->lno_s < 0) /* Overflow */ + lf->lno_s = INT_MAX; + lf->lno_e = lr->offset + lr->end; + if (lf->lno_e < 0) /* Overflow */ lf->lno_e = INT_MAX; - else - lf->lno_e = lr->offset + lr->end; + pr_debug("New line range: %d to %d\n", lf->lno_s, lf->lno_e); lr->start = lf->lno_s; lr->end = lf->lno_e; - if (dwarf_func_inline(sp_die)) + if (dwarf_func_inline(sp_die)) { + struct dwarf_callback_param _param; + _param.data = (void *)lf; + _param.retval = 0; dwarf_func_inline_instances(sp_die, - line_range_inline_cb, lf); - else - find_line_range_by_line(sp_die, lf); - return 1; + line_range_inline_cb, + &_param); + param->retval = _param.retval; + } else + param->retval = find_line_range_by_line(sp_die, lf); + return DWARF_CB_ABORT; } - return 0; + return DWARF_CB_OK; } -static void find_line_range_by_func(struct line_finder *lf) +static int find_line_range_by_func(struct line_finder *lf) { - dwarf_getfuncs(&lf->cu_die, line_range_search_cb, lf, 0); + struct dwarf_callback_param param = {.data = (void *)lf, .retval = 0}; + dwarf_getfuncs(&lf->cu_die, line_range_search_cb, ¶m, 0); + return param.retval; } int find_line_range(int fd, struct line_range *lr) { struct line_finder lf = {.lr = lr, .found = 0}; - int ret; + int ret = 0; Dwarf_Off off = 0, noff; size_t cuhl; Dwarf_Die *diep; Dwarf *dbg; dbg = dwarf_begin(fd, DWARF_C_READ); - if (!dbg) - return -ENOENT; + if (!dbg) { + pr_warning("No dwarf info found in the vmlinux - " + "please rebuild with CONFIG_DEBUG_INFO=y.\n"); + return -EBADF; + } /* Loop on CUs (Compilation Unit) */ - while (!lf.found) { - ret = dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL); - if (ret != 0) + while (!lf.found && ret >= 0) { + if (dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) != 0) break; /* Get the DIE(Debugging Information Entry) of this CU */ @@ -810,20 +1322,18 @@ int find_line_range(int fd, struct line_range *lr) if (!lr->file || lf.fname) { if (lr->function) - find_line_range_by_func(&lf); + ret = find_line_range_by_func(&lf); else { lf.lno_s = lr->start; - if (!lr->end) - lf.lno_e = INT_MAX; - else - lf.lno_e = lr->end; - find_line_range_by_line(NULL, &lf); + lf.lno_e = lr->end; + ret = find_line_range_by_line(NULL, &lf); } } off = noff; } pr_debug("path: %lx\n", (unsigned long)lr->path); dwarf_end(dbg); - return lf.found; + + return (ret < 0) ? ret : lf.found; } diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 21f7354397b4..310ce897229c 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -3,6 +3,7 @@ #include <stdbool.h> #include "util.h" +#include "probe-event.h" #define MAX_PATH_LEN 256 #define MAX_PROBE_BUFFER 1024 @@ -14,67 +15,37 @@ static inline int is_c_varname(const char *name) return isalpha(name[0]) || name[0] == '_'; } -struct probe_point { - char *event; /* Event name */ - char *group; /* Event group */ +#ifdef DWARF_SUPPORT +/* Find kprobe_trace_events specified by perf_probe_event from debuginfo */ +extern int find_kprobe_trace_events(int fd, struct perf_probe_event *pev, + struct kprobe_trace_event **tevs); - /* Inputs */ - char *file; /* File name */ - int line; /* Line number */ - char *lazy_line; /* Lazy line pattern */ +/* Find a perf_probe_point from debuginfo */ +extern int find_perf_probe_point(int fd, unsigned long addr, + struct perf_probe_point *ppt); - char *function; /* Function name */ - int offset; /* Offset bytes */ - - int nr_args; /* Number of arguments */ - char **args; /* Arguments */ - - int retprobe; /* Return probe */ - - /* Output */ - int found; /* Number of found probe points */ - char *probes[MAX_PROBES]; /* Output buffers (will be allocated)*/ -}; - -/* Line number container */ -struct line_node { - struct list_head list; - unsigned int line; -}; - -/* Line range */ -struct line_range { - char *file; /* File name */ - char *function; /* Function name */ - unsigned int start; /* Start line number */ - unsigned int end; /* End line number */ - int offset; /* Start line offset */ - char *path; /* Real path name */ - struct list_head line_list; /* Visible lines */ -}; - -#ifndef NO_DWARF_SUPPORT -extern int find_probe_point(int fd, struct probe_point *pp); extern int find_line_range(int fd, struct line_range *lr); #include <dwarf.h> #include <libdw.h> struct probe_finder { - struct probe_point *pp; /* Target probe point */ + struct perf_probe_event *pev; /* Target probe event */ + struct kprobe_trace_event *tevs; /* Result trace events */ + int ntevs; /* number of trace events */ /* For function searching */ - Dwarf_Addr addr; /* Address */ - const char *fname; /* File name */ int lno; /* Line number */ + Dwarf_Addr addr; /* Address */ + const char *fname; /* Real file name */ Dwarf_Die cu_die; /* Current CU */ + struct list_head lcache; /* Line cache for lazy match */ /* For variable searching */ + Dwarf_CFI *cfi; /* Call Frame Information */ Dwarf_Op *fb_ops; /* Frame base attribute */ - const char *var; /* Current variable name */ - char *buf; /* Current output buffer */ - int len; /* Length of output buffer */ - struct list_head lcache; /* Line cache for lazy match */ + struct perf_probe_arg *pvar; /* Current target variable */ + struct kprobe_trace_arg *tvar; /* Current result variable */ }; struct line_finder { @@ -87,6 +58,6 @@ struct line_finder { int found; }; -#endif /* NO_DWARF_SUPPORT */ +#endif /* DWARF_SUPPORT */ #endif /*_PROBE_FINDER_H */ diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index eed1cb889008..7d88ae5c270f 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -14,6 +14,16 @@ static int perf_session__open(struct perf_session *self, bool force) { struct stat input_stat; + if (!strcmp(self->filename, "-")) { + self->fd_pipe = true; + self->fd = STDIN_FILENO; + + if (perf_header__read(self, self->fd) < 0) + pr_err("incompatible file format"); + + return 0; + } + self->fd = open(self->filename, O_RDONLY); if (self->fd < 0) { pr_err("failed to open file: %s", self->filename); @@ -38,7 +48,7 @@ static int perf_session__open(struct perf_session *self, bool force) goto out_close; } - if (perf_header__read(&self->header, self->fd) < 0) { + if (perf_header__read(self, self->fd) < 0) { pr_err("incompatible file format"); goto out_close; } @@ -52,9 +62,20 @@ out_close: return -1; } -static inline int perf_session__create_kernel_maps(struct perf_session *self) +void perf_session__update_sample_type(struct perf_session *self) { - return map_groups__create_kernel_maps(&self->kmaps, self->vmlinux_maps); + self->sample_type = perf_header__sample_type(&self->header); +} + +int perf_session__create_kernel_maps(struct perf_session *self) +{ + int ret; + struct rb_root *root = &self->kerninfo_root; + + ret = map_groups__create_kernel_maps(root, HOST_KERNEL_ID); + if (ret >= 0) + ret = map_groups__create_guest_kernel_maps(root); + return ret; } struct perf_session *perf_session__new(const char *filename, int mode, bool force) @@ -76,7 +97,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc self->cwd = NULL; self->cwdlen = 0; self->unknown_events = 0; - map_groups__init(&self->kmaps); + self->kerninfo_root = RB_ROOT; if (mode == O_RDONLY) { if (perf_session__open(self, force) < 0) @@ -90,7 +111,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc goto out_delete; } - self->sample_type = perf_header__sample_type(&self->header); + perf_session__update_sample_type(self); out: return self; out_free: @@ -117,22 +138,17 @@ static bool symbol__match_parent_regex(struct symbol *sym) return 0; } -struct symbol **perf_session__resolve_callchain(struct perf_session *self, - struct thread *thread, - struct ip_callchain *chain, - struct symbol **parent) +struct map_symbol *perf_session__resolve_callchain(struct perf_session *self, + struct thread *thread, + struct ip_callchain *chain, + struct symbol **parent) { u8 cpumode = PERF_RECORD_MISC_USER; - struct symbol **syms = NULL; unsigned int i; + struct map_symbol *syms = calloc(chain->nr, sizeof(*syms)); - if (symbol_conf.use_callchain) { - syms = calloc(chain->nr, sizeof(*syms)); - if (!syms) { - fprintf(stderr, "Can't allocate memory for symbols\n"); - exit(-1); - } - } + if (!syms) + return NULL; for (i = 0; i < chain->nr; i++) { u64 ip = chain->ips[i]; @@ -152,15 +168,17 @@ struct symbol **perf_session__resolve_callchain(struct perf_session *self, continue; } + al.filtered = false; thread__find_addr_location(thread, self, cpumode, - MAP__FUNCTION, ip, &al, NULL); + MAP__FUNCTION, thread->pid, ip, &al, NULL); if (al.sym != NULL) { if (sort__has_parent && !*parent && symbol__match_parent_regex(al.sym)) *parent = al.sym; if (!symbol_conf.use_callchain) break; - syms[i] = al.sym; + syms[i].map = al.map; + syms[i].sym = al.sym; } } @@ -194,6 +212,14 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler) handler->throttle = process_event_stub; if (handler->unthrottle == NULL) handler->unthrottle = process_event_stub; + if (handler->attr == NULL) + handler->attr = process_event_stub; + if (handler->event_type == NULL) + handler->event_type = process_event_stub; + if (handler->tracing_data == NULL) + handler->tracing_data = process_event_stub; + if (handler->build_id == NULL) + handler->build_id = process_event_stub; } static const char *event__name[] = { @@ -207,16 +233,23 @@ static const char *event__name[] = { [PERF_RECORD_FORK] = "FORK", [PERF_RECORD_READ] = "READ", [PERF_RECORD_SAMPLE] = "SAMPLE", + [PERF_RECORD_HEADER_ATTR] = "ATTR", + [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", + [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA", + [PERF_RECORD_HEADER_BUILD_ID] = "BUILD_ID", }; -unsigned long event__total[PERF_RECORD_MAX]; +unsigned long event__total[PERF_RECORD_HEADER_MAX]; void event__print_totals(void) { int i; - for (i = 0; i < PERF_RECORD_MAX; ++i) + for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) { + if (!event__name[i]) + continue; pr_info("%10s events: %10ld\n", event__name[i], event__total[i]); + } } void mem_bswap_64(void *src, int byte_size) @@ -270,6 +303,37 @@ static void event__read_swap(event_t *self) self->read.id = bswap_64(self->read.id); } +static void event__attr_swap(event_t *self) +{ + size_t size; + + self->attr.attr.type = bswap_32(self->attr.attr.type); + self->attr.attr.size = bswap_32(self->attr.attr.size); + self->attr.attr.config = bswap_64(self->attr.attr.config); + self->attr.attr.sample_period = bswap_64(self->attr.attr.sample_period); + self->attr.attr.sample_type = bswap_64(self->attr.attr.sample_type); + self->attr.attr.read_format = bswap_64(self->attr.attr.read_format); + self->attr.attr.wakeup_events = bswap_32(self->attr.attr.wakeup_events); + self->attr.attr.bp_type = bswap_32(self->attr.attr.bp_type); + self->attr.attr.bp_addr = bswap_64(self->attr.attr.bp_addr); + self->attr.attr.bp_len = bswap_64(self->attr.attr.bp_len); + + size = self->header.size; + size -= (void *)&self->attr.id - (void *)self; + mem_bswap_64(self->attr.id, size); +} + +static void event__event_type_swap(event_t *self) +{ + self->event_type.event_type.event_id = + bswap_64(self->event_type.event_type.event_id); +} + +static void event__tracing_data_swap(event_t *self) +{ + self->tracing_data.size = bswap_32(self->tracing_data.size); +} + typedef void (*event__swap_op)(event_t *self); static event__swap_op event__swap_ops[] = { @@ -280,7 +344,11 @@ static event__swap_op event__swap_ops[] = { [PERF_RECORD_LOST] = event__all64_swap, [PERF_RECORD_READ] = event__read_swap, [PERF_RECORD_SAMPLE] = event__all64_swap, - [PERF_RECORD_MAX] = NULL, + [PERF_RECORD_HEADER_ATTR] = event__attr_swap, + [PERF_RECORD_HEADER_EVENT_TYPE] = event__event_type_swap, + [PERF_RECORD_HEADER_TRACING_DATA] = event__tracing_data_swap, + [PERF_RECORD_HEADER_BUILD_ID] = NULL, + [PERF_RECORD_HEADER_MAX] = NULL, }; static int perf_session__process_event(struct perf_session *self, @@ -290,7 +358,7 @@ static int perf_session__process_event(struct perf_session *self, { trace_event(event); - if (event->header.type < PERF_RECORD_MAX) { + if (event->header.type < PERF_RECORD_HEADER_MAX) { dump_printf("%#Lx [%#x]: PERF_RECORD_%s", offset + head, event->header.size, event__name[event->header.type]); @@ -320,6 +388,16 @@ static int perf_session__process_event(struct perf_session *self, return ops->throttle(event, self); case PERF_RECORD_UNTHROTTLE: return ops->unthrottle(event, self); + case PERF_RECORD_HEADER_ATTR: + return ops->attr(event, self); + case PERF_RECORD_HEADER_EVENT_TYPE: + return ops->event_type(event, self); + case PERF_RECORD_HEADER_TRACING_DATA: + /* setup for reading amidst mmap */ + lseek(self->fd, offset + head, SEEK_SET); + return ops->tracing_data(event, self); + case PERF_RECORD_HEADER_BUILD_ID: + return ops->build_id(event, self); default: self->unknown_events++; return -1; @@ -333,46 +411,6 @@ void perf_event_header__bswap(struct perf_event_header *self) self->size = bswap_16(self->size); } -int perf_header__read_build_ids(struct perf_header *self, - int input, u64 offset, u64 size) -{ - struct build_id_event bev; - char filename[PATH_MAX]; - u64 limit = offset + size; - int err = -1; - - while (offset < limit) { - struct dso *dso; - ssize_t len; - struct list_head *head = &dsos__user; - - if (read(input, &bev, sizeof(bev)) != sizeof(bev)) - goto out; - - if (self->needs_swap) - perf_event_header__bswap(&bev.header); - - len = bev.header.size - sizeof(bev); - if (read(input, filename, len) != len) - goto out; - - if (bev.header.misc & PERF_RECORD_MISC_KERNEL) - head = &dsos__kernel; - - dso = __dsos__findnew(head, filename); - if (dso != NULL) { - dso__set_build_id(dso, &bev.build_id); - if (head == &dsos__kernel && filename[0] == '[') - dso->kernel = 1; - } - - offset += bev.header.size; - } - err = 0; -out: - return err; -} - static struct thread *perf_session__register_idle_thread(struct perf_session *self) { struct thread *thread = perf_session__findnew(self, 0); @@ -385,6 +423,101 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se return thread; } +int do_read(int fd, void *buf, size_t size) +{ + void *buf_start = buf; + + while (size) { + int ret = read(fd, buf, size); + + if (ret <= 0) + return ret; + + size -= ret; + buf += ret; + } + + return buf - buf_start; +} + +#define session_done() (*(volatile int *)(&session_done)) +volatile int session_done; + +static int __perf_session__process_pipe_events(struct perf_session *self, + struct perf_event_ops *ops) +{ + event_t event; + uint32_t size; + int skip = 0; + u64 head; + int err; + void *p; + + perf_event_ops__fill_defaults(ops); + + head = 0; +more: + err = do_read(self->fd, &event, sizeof(struct perf_event_header)); + if (err <= 0) { + if (err == 0) + goto done; + + pr_err("failed to read event header\n"); + goto out_err; + } + + if (self->header.needs_swap) + perf_event_header__bswap(&event.header); + + size = event.header.size; + if (size == 0) + size = 8; + + p = &event; + p += sizeof(struct perf_event_header); + + err = do_read(self->fd, p, size - sizeof(struct perf_event_header)); + if (err <= 0) { + if (err == 0) { + pr_err("unexpected end of event stream\n"); + goto done; + } + + pr_err("failed to read event data\n"); + goto out_err; + } + + if (size == 0 || + (skip = perf_session__process_event(self, &event, ops, + 0, head)) < 0) { + dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n", + head, event.header.size, event.header.type); + /* + * assume we lost track of the stream, check alignment, and + * increment a single u64 in the hope to catch on again 'soon'. + */ + if (unlikely(head & 7)) + head &= ~7ULL; + + size = 8; + } + + head += size; + + dump_printf("\n%#Lx [%#x]: event: %d\n", + head, event.header.size, event.header.type); + + if (skip > 0) + head += skip; + + if (!session_done()) + goto more; +done: + err = 0; +out_err: + return err; +} + int __perf_session__process_events(struct perf_session *self, u64 data_offset, u64 data_size, u64 file_size, struct perf_event_ops *ops) @@ -396,6 +529,10 @@ int __perf_session__process_events(struct perf_session *self, event_t *event; uint32_t size; char *buf; + struct ui_progress *progress = ui_progress__new("Processing events...", + self->size); + if (progress == NULL) + return -1; perf_event_ops__fill_defaults(ops); @@ -424,6 +561,7 @@ remap: more: event = (event_t *)(buf + head); + ui_progress__update(progress, offset); if (self->header.needs_swap) perf_event_header__bswap(&event->header); @@ -474,6 +612,7 @@ more: done: err = 0; out_err: + ui_progress__delete(progress); return err; } @@ -502,9 +641,13 @@ out_getcwd_err: self->cwdlen = strlen(self->cwd); } - err = __perf_session__process_events(self, self->header.data_offset, - self->header.data_size, - self->size, ops); + if (!self->fd_pipe) + err = __perf_session__process_events(self, + self->header.data_offset, + self->header.data_size, + self->size, ops); + else + err = __perf_session__process_pipe_events(self, ops); out_err: return err; } @@ -519,56 +662,34 @@ bool perf_session__has_traces(struct perf_session *self, const char *msg) return true; } -int perf_session__set_kallsyms_ref_reloc_sym(struct perf_session *self, +int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, u64 addr) { char *bracket; enum map_type i; + struct ref_reloc_sym *ref; - self->ref_reloc_sym.name = strdup(symbol_name); - if (self->ref_reloc_sym.name == NULL) + ref = zalloc(sizeof(struct ref_reloc_sym)); + if (ref == NULL) return -ENOMEM; - bracket = strchr(self->ref_reloc_sym.name, ']'); + ref->name = strdup(symbol_name); + if (ref->name == NULL) { + free(ref); + return -ENOMEM; + } + + bracket = strchr(ref->name, ']'); if (bracket) *bracket = '\0'; - self->ref_reloc_sym.addr = addr; + ref->addr = addr; for (i = 0; i < MAP__NR_TYPES; ++i) { - struct kmap *kmap = map__kmap(self->vmlinux_maps[i]); - kmap->ref_reloc_sym = &self->ref_reloc_sym; + struct kmap *kmap = map__kmap(maps[i]); + kmap->ref_reloc_sym = ref; } return 0; } - -static u64 map__reloc_map_ip(struct map *map, u64 ip) -{ - return ip + (s64)map->pgoff; -} - -static u64 map__reloc_unmap_ip(struct map *map, u64 ip) -{ - return ip - (s64)map->pgoff; -} - -void map__reloc_vmlinux(struct map *self) -{ - struct kmap *kmap = map__kmap(self); - s64 reloc; - - if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr) - return; - - reloc = (kmap->ref_reloc_sym->unrelocated_addr - - kmap->ref_reloc_sym->addr); - - if (!reloc) - return; - - self->map_ip = map__reloc_map_ip; - self->unmap_ip = map__reloc_unmap_ip; - self->pgoff = reloc; -} diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 5c33417eebb3..5e47c87b9266 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -15,18 +15,17 @@ struct perf_session { struct perf_header header; unsigned long size; unsigned long mmap_window; - struct map_groups kmaps; struct rb_root threads; struct thread *last_match; - struct map *vmlinux_maps[MAP__NR_TYPES]; + struct rb_root kerninfo_root; struct events_stats events_stats; struct rb_root stats_by_id; unsigned long event_total[PERF_RECORD_MAX]; unsigned long unknown_events; struct rb_root hists; u64 sample_type; - struct ref_reloc_sym ref_reloc_sym; int fd; + bool fd_pipe; int cwdlen; char *cwd; char filename[0]; @@ -43,7 +42,11 @@ struct perf_event_ops { lost, read, throttle, - unthrottle; + unthrottle, + attr, + event_type, + tracing_data, + build_id; }; struct perf_session *perf_session__new(const char *filename, int mode, bool force); @@ -57,33 +60,36 @@ int __perf_session__process_events(struct perf_session *self, int perf_session__process_events(struct perf_session *self, struct perf_event_ops *event_ops); -struct symbol **perf_session__resolve_callchain(struct perf_session *self, - struct thread *thread, - struct ip_callchain *chain, - struct symbol **parent); +struct map_symbol *perf_session__resolve_callchain(struct perf_session *self, + struct thread *thread, + struct ip_callchain *chain, + struct symbol **parent); bool perf_session__has_traces(struct perf_session *self, const char *msg); -int perf_header__read_build_ids(struct perf_header *self, int input, - u64 offset, u64 file_size); - -int perf_session__set_kallsyms_ref_reloc_sym(struct perf_session *self, +int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, u64 addr); void mem_bswap_64(void *src, int byte_size); -static inline int __perf_session__create_kernel_maps(struct perf_session *self, - struct dso *kernel) -{ - return __map_groups__create_kernel_maps(&self->kmaps, - self->vmlinux_maps, kernel); -} +int perf_session__create_kernel_maps(struct perf_session *self); + +int do_read(int fd, void *buf, size_t size); +void perf_session__update_sample_type(struct perf_session *self); -static inline struct map * - perf_session__new_module_map(struct perf_session *self, - u64 start, const char *filename) +#ifdef NO_NEWT_SUPPORT +static inline int perf_session__browse_hists(struct rb_root *hists __used, + u64 nr_hists __used, + u64 session_total __used, + const char *helpline __used, + const char *input_name __used) { - return map_groups__new_module(&self->kmaps, start, filename); + return 0; } +#else +int perf_session__browse_hists(struct rb_root *hists, u64 nr_hists, + u64 session_total, const char *helpline, + const char *input_name); +#endif #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index cb0f327de9e8..da30b305fba0 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -18,39 +18,50 @@ char * field_sep; LIST_HEAD(hist_entry__sort_list); +static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width); +static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width); +static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width); +static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width); +static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width); + struct sort_entry sort_thread = { - .header = "Command: Pid", - .cmp = sort__thread_cmp, - .print = sort__thread_print, - .width = &threads__col_width, + .se_header = "Command: Pid", + .se_cmp = sort__thread_cmp, + .se_snprintf = hist_entry__thread_snprintf, + .se_width = &threads__col_width, }; struct sort_entry sort_comm = { - .header = "Command", - .cmp = sort__comm_cmp, - .collapse = sort__comm_collapse, - .print = sort__comm_print, - .width = &comms__col_width, + .se_header = "Command", + .se_cmp = sort__comm_cmp, + .se_collapse = sort__comm_collapse, + .se_snprintf = hist_entry__comm_snprintf, + .se_width = &comms__col_width, }; struct sort_entry sort_dso = { - .header = "Shared Object", - .cmp = sort__dso_cmp, - .print = sort__dso_print, - .width = &dsos__col_width, + .se_header = "Shared Object", + .se_cmp = sort__dso_cmp, + .se_snprintf = hist_entry__dso_snprintf, + .se_width = &dsos__col_width, }; struct sort_entry sort_sym = { - .header = "Symbol", - .cmp = sort__sym_cmp, - .print = sort__sym_print, + .se_header = "Symbol", + .se_cmp = sort__sym_cmp, + .se_snprintf = hist_entry__sym_snprintf, }; struct sort_entry sort_parent = { - .header = "Parent symbol", - .cmp = sort__parent_cmp, - .print = sort__parent_print, - .width = &parent_symbol__col_width, + .se_header = "Parent symbol", + .se_cmp = sort__parent_cmp, + .se_snprintf = hist_entry__parent_snprintf, + .se_width = &parent_symbol__col_width, }; struct sort_dimension { @@ -85,45 +96,38 @@ sort__thread_cmp(struct hist_entry *left, struct hist_entry *right) return right->thread->pid - left->thread->pid; } -int repsep_fprintf(FILE *fp, const char *fmt, ...) +static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...) { int n; va_list ap; va_start(ap, fmt); - if (!field_sep) - n = vfprintf(fp, fmt, ap); - else { - char *bf = NULL; - n = vasprintf(&bf, fmt, ap); - if (n > 0) { - char *sep = bf; - - while (1) { - sep = strchr(sep, *field_sep); - if (sep == NULL) - break; - *sep = '.'; - } + n = vsnprintf(bf, size, fmt, ap); + if (field_sep && n > 0) { + char *sep = bf; + + while (1) { + sep = strchr(sep, *field_sep); + if (sep == NULL) + break; + *sep = '.'; } - fputs(bf, fp); - free(bf); } va_end(ap); return n; } -size_t -sort__thread_print(FILE *fp, struct hist_entry *self, unsigned int width) +static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) { - return repsep_fprintf(fp, "%*s:%5d", width - 6, + return repsep_snprintf(bf, size, "%*s:%5d", width, self->thread->comm ?: "", self->thread->pid); } -size_t -sort__comm_print(FILE *fp, struct hist_entry *self, unsigned int width) +static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) { - return repsep_fprintf(fp, "%*s", width, self->thread->comm); + return repsep_snprintf(bf, size, "%*s", width, self->thread->comm); } /* --sort dso */ @@ -131,8 +135,8 @@ sort__comm_print(FILE *fp, struct hist_entry *self, unsigned int width) int64_t sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) { - struct dso *dso_l = left->map ? left->map->dso : NULL; - struct dso *dso_r = right->map ? right->map->dso : NULL; + struct dso *dso_l = left->ms.map ? left->ms.map->dso : NULL; + struct dso *dso_r = right->ms.map ? right->ms.map->dso : NULL; const char *dso_name_l, *dso_name_r; if (!dso_l || !dso_r) @@ -149,16 +153,16 @@ sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) return strcmp(dso_name_l, dso_name_r); } -size_t -sort__dso_print(FILE *fp, struct hist_entry *self, unsigned int width) +static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) { - if (self->map && self->map->dso) { - const char *dso_name = !verbose ? self->map->dso->short_name : - self->map->dso->long_name; - return repsep_fprintf(fp, "%-*s", width, dso_name); + if (self->ms.map && self->ms.map->dso) { + const char *dso_name = !verbose ? self->ms.map->dso->short_name : + self->ms.map->dso->long_name; + return repsep_snprintf(bf, size, "%-*s", width, dso_name); } - return repsep_fprintf(fp, "%*llx", width, (u64)self->ip); + return repsep_snprintf(bf, size, "%*Lx", width, self->ip); } /* --sort symbol */ @@ -168,31 +172,31 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) { u64 ip_l, ip_r; - if (left->sym == right->sym) + if (left->ms.sym == right->ms.sym) return 0; - ip_l = left->sym ? left->sym->start : left->ip; - ip_r = right->sym ? right->sym->start : right->ip; + ip_l = left->ms.sym ? left->ms.sym->start : left->ip; + ip_r = right->ms.sym ? right->ms.sym->start : right->ip; return (int64_t)(ip_r - ip_l); } - -size_t -sort__sym_print(FILE *fp, struct hist_entry *self, unsigned int width __used) +static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width __used) { size_t ret = 0; if (verbose) { - char o = self->map ? dso__symtab_origin(self->map->dso) : '!'; - ret += repsep_fprintf(fp, "%#018llx %c ", (u64)self->ip, o); + char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!'; + ret += repsep_snprintf(bf, size, "%#018llx %c ", self->ip, o); } - ret += repsep_fprintf(fp, "[%c] ", self->level); - if (self->sym) - ret += repsep_fprintf(fp, "%s", self->sym->name); + ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level); + if (self->ms.sym) + ret += repsep_snprintf(bf + ret, size - ret, "%s", + self->ms.sym->name); else - ret += repsep_fprintf(fp, "%#016llx", (u64)self->ip); + ret += repsep_snprintf(bf + ret, size - ret, "%#016llx", self->ip); return ret; } @@ -231,10 +235,10 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right) return strcmp(sym_l->name, sym_r->name); } -size_t -sort__parent_print(FILE *fp, struct hist_entry *self, unsigned int width) +static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) { - return repsep_fprintf(fp, "%-*s", width, + return repsep_snprintf(bf, size, "%-*s", width, self->parent ? self->parent->name : "[other]"); } @@ -251,7 +255,7 @@ int sort_dimension__add(const char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; - if (sd->entry->collapse) + if (sd->entry->se_collapse) sort__need_collapse = 1; if (sd->entry == &sort_parent) { @@ -260,9 +264,8 @@ int sort_dimension__add(const char *tok) char err[BUFSIZ]; regerror(ret, &parent_regex, err, sizeof(err)); - fprintf(stderr, "Invalid regex: %s\n%s", - parent_pattern, err); - exit(-1); + pr_err("Invalid regex: %s\n%s", parent_pattern, err); + return -EINVAL; } sort__has_parent = 1; } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 753f9ea99fb0..b7c54eeed9c9 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -44,18 +44,28 @@ extern enum sort_type sort__first_dimension; struct hist_entry { struct rb_node rb_node; u64 count; + u64 count_sys; + u64 count_us; + u64 count_guest_sys; + u64 count_guest_us; + + /* + * XXX WARNING! + * thread _has_ to come after ms, see + * hist_browser__selected_thread in util/newt.c + */ + struct map_symbol ms; struct thread *thread; - struct map *map; - struct symbol *sym; u64 ip; char level; - struct symbol *parent; - struct callchain_node callchain; + u8 filtered; + struct symbol *parent; union { unsigned long position; struct hist_entry *pair; struct rb_root sorted_chain; }; + struct callchain_node callchain[0]; }; enum sort_type { @@ -73,12 +83,13 @@ enum sort_type { struct sort_entry { struct list_head list; - const char *header; + const char *se_header; - int64_t (*cmp)(struct hist_entry *, struct hist_entry *); - int64_t (*collapse)(struct hist_entry *, struct hist_entry *); - size_t (*print)(FILE *fp, struct hist_entry *, unsigned int width); - unsigned int *width; + int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *); + int64_t (*se_collapse)(struct hist_entry *, struct hist_entry *); + int (*se_snprintf)(struct hist_entry *self, char *bf, size_t size, + unsigned int width); + unsigned int *se_width; bool elide; }; @@ -87,7 +98,6 @@ extern struct list_head hist_entry__sort_list; void setup_sorting(const char * const usagestr[], const struct option *opts); -extern int repsep_fprintf(FILE *fp, const char *fmt, ...); extern size_t sort__thread_print(FILE *, struct hist_entry *, unsigned int); extern size_t sort__comm_print(FILE *, struct hist_entry *, unsigned int); extern size_t sort__dso_print(FILE *, struct hist_entry *, unsigned int); diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index a175949ed216..0409fc7c0058 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -1,48 +1,5 @@ -#include "string.h" #include "util.h" - -static int hex(char ch) -{ - if ((ch >= '0') && (ch <= '9')) - return ch - '0'; - if ((ch >= 'a') && (ch <= 'f')) - return ch - 'a' + 10; - if ((ch >= 'A') && (ch <= 'F')) - return ch - 'A' + 10; - return -1; -} - -/* - * While we find nice hex chars, build a long_val. - * Return number of chars processed. - */ -int hex2u64(const char *ptr, u64 *long_val) -{ - const char *p = ptr; - *long_val = 0; - - while (*p) { - const int hex_val = hex(*p); - - if (hex_val < 0) - break; - - *long_val = (*long_val << 4) | hex_val; - p++; - } - - return p - ptr; -} - -char *strxfrchar(char *s, char from, char to) -{ - char *p = s; - - while ((p = strchr(p, from)) != NULL) - *p++ = to; - - return s; -} +#include "string.h" #define K 1024LL /* diff --git a/tools/perf/util/string.h b/tools/perf/util/string.h deleted file mode 100644 index 542e44de3719..000000000000 --- a/tools/perf/util/string.h +++ /dev/null @@ -1,18 +0,0 @@ -#ifndef __PERF_STRING_H_ -#define __PERF_STRING_H_ - -#include <stdbool.h> -#include "types.h" - -int hex2u64(const char *ptr, u64 *val); -char *strxfrchar(char *s, char from, char to); -s64 perf_atoll(const char *str); -char **argv_split(const char *str, int *argcp); -void argv_free(char **argv); -bool strglobmatch(const char *str, const char *pat); -bool strlazymatch(const char *str, const char *pat); - -#define _STR(x) #x -#define STR(x) _STR(x) - -#endif /* __PERF_STRING_H */ diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index c458c4a371d1..e782e7db16c5 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1,13 +1,19 @@ -#include "util.h" -#include "../perf.h" -#include "sort.h" -#include "string.h" +#define _GNU_SOURCE +#include <ctype.h> +#include <dirent.h> +#include <errno.h> +#include <libgen.h> +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/param.h> +#include <fcntl.h> +#include <unistd.h> #include "symbol.h" -#include "thread.h" +#include "strlist.h" -#include "debug.h" - -#include <asm/bug.h> #include <libelf.h> #include <gelf.h> #include <elf.h> @@ -18,22 +24,12 @@ #define NT_GNU_BUILD_ID 3 #endif -enum dso_origin { - DSO__ORIG_KERNEL = 0, - DSO__ORIG_JAVA_JIT, - DSO__ORIG_BUILD_ID_CACHE, - DSO__ORIG_FEDORA, - DSO__ORIG_UBUNTU, - DSO__ORIG_BUILDID, - DSO__ORIG_DSO, - DSO__ORIG_KMODULE, - DSO__ORIG_NOT_FOUND, -}; - static void dsos__add(struct list_head *head, struct dso *dso); static struct map *map__new2(u64 start, struct dso *dso, enum map_type type); static int dso__load_kernel_sym(struct dso *self, struct map *map, symbol_filter_t filter); +static int dso__load_guest_kernel_sym(struct dso *self, struct map *map, + symbol_filter_t filter); static int vmlinux_path__nr_entries; static char **vmlinux_path; @@ -126,8 +122,8 @@ static void map_groups__fixup_end(struct map_groups *self) static struct symbol *symbol__new(u64 start, u64 len, const char *name) { size_t namelen = strlen(name) + 1; - struct symbol *self = zalloc(symbol_conf.priv_size + - sizeof(*self) + namelen); + struct symbol *self = calloc(1, (symbol_conf.priv_size + + sizeof(*self) + namelen)); if (self == NULL) return NULL; @@ -178,7 +174,7 @@ static void dso__set_basename(struct dso *self) struct dso *dso__new(const char *name) { - struct dso *self = zalloc(sizeof(*self) + strlen(name) + 1); + struct dso *self = calloc(1, sizeof(*self) + strlen(name) + 1); if (self != NULL) { int i; @@ -192,6 +188,7 @@ struct dso *dso__new(const char *name) self->loaded = 0; self->sorted_by_name = 0; self->has_build_id = 0; + self->kernel = DSO_TYPE_USER; } return self; @@ -408,12 +405,9 @@ int kallsyms__parse(const char *filename, void *arg, char *symbol_name; line_len = getline(&line, &n, file); - if (line_len < 0) + if (line_len < 0 || !line) break; - if (!line) - goto out_failure; - line[--line_len] = '\0'; /* \n */ len = hex2u64(line, &start); @@ -465,6 +459,7 @@ static int map__process_kallsym_symbol(void *arg, const char *name, * map__split_kallsyms, when we have split the maps per module */ symbols__insert(root, sym); + return 0; } @@ -489,6 +484,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map, symbol_filter_t filter) { struct map_groups *kmaps = map__kmap(map)->kmaps; + struct kernel_info *kerninfo = kmaps->this_kerninfo; struct map *curr_map = map; struct symbol *pos; int count = 0; @@ -510,15 +506,33 @@ static int dso__split_kallsyms(struct dso *self, struct map *map, *module++ = '\0'; if (strcmp(curr_map->dso->short_name, module)) { - curr_map = map_groups__find_by_name(kmaps, map->type, module); + if (curr_map != map && + self->kernel == DSO_TYPE_GUEST_KERNEL && + is_default_guest(kerninfo)) { + /* + * We assume all symbols of a module are + * continuous in * kallsyms, so curr_map + * points to a module and all its + * symbols are in its kmap. Mark it as + * loaded. + */ + dso__set_loaded(curr_map->dso, + curr_map->type); + } + + curr_map = map_groups__find_by_name(kmaps, + map->type, module); if (curr_map == NULL) { - pr_debug("/proc/{kallsyms,modules} " + pr_err("%s/proc/{kallsyms,modules} " "inconsistency while looking " - "for \"%s\" module!\n", module); - return -1; + "for \"%s\" module!\n", + kerninfo->root_dir, module); + curr_map = map; + goto discard_symbol; } - if (curr_map->dso->loaded) + if (curr_map->dso->loaded && + !is_default_guest(kmaps->this_kerninfo)) goto discard_symbol; } /* @@ -531,13 +545,21 @@ static int dso__split_kallsyms(struct dso *self, struct map *map, char dso_name[PATH_MAX]; struct dso *dso; - snprintf(dso_name, sizeof(dso_name), "[kernel].%d", - kernel_range++); + if (self->kernel == DSO_TYPE_GUEST_KERNEL) + snprintf(dso_name, sizeof(dso_name), + "[guest.kernel].%d", + kernel_range++); + else + snprintf(dso_name, sizeof(dso_name), + "[kernel].%d", + kernel_range++); dso = dso__new(dso_name); if (dso == NULL) return -1; + dso->kernel = self->kernel; + curr_map = map__new2(pos->start, dso, map->type); if (curr_map == NULL) { dso__delete(dso); @@ -561,6 +583,12 @@ discard_symbol: rb_erase(&pos->rb_node, root); } } + if (curr_map != map && + self->kernel == DSO_TYPE_GUEST_KERNEL && + is_default_guest(kmaps->this_kerninfo)) { + dso__set_loaded(curr_map->dso, curr_map->type); + } + return count; } @@ -571,7 +599,10 @@ int dso__load_kallsyms(struct dso *self, const char *filename, return -1; symbols__fixup_end(&self->symbols[map->type]); - self->origin = DSO__ORIG_KERNEL; + if (self->kernel == DSO_TYPE_GUEST_KERNEL) + self->origin = DSO__ORIG_GUEST_KERNEL; + else + self->origin = DSO__ORIG_KERNEL; return dso__split_kallsyms(self, map, filter); } @@ -870,8 +901,8 @@ out_close: if (err == 0) return nr; out: - pr_warning("%s: problems reading %s PLT info.\n", - __func__, self->long_name); + pr_debug("%s: problems reading %s PLT info.\n", + __func__, self->long_name); return 0; } @@ -958,7 +989,7 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name, nr_syms = shdr.sh_size / shdr.sh_entsize; memset(&sym, 0, sizeof(sym)); - if (!self->kernel) { + if (self->kernel == DSO_TYPE_USER) { self->adjust_symbols = (ehdr.e_type == ET_EXEC || elf_section_by_name(elf, &ehdr, &shdr, ".gnu.prelink_undo", @@ -990,7 +1021,7 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name, section_name = elf_sec__name(&shdr, secstrs); - if (self->kernel || kmodule) { + if (self->kernel != DSO_TYPE_USER || kmodule) { char dso_name[PATH_MAX]; if (strcmp(section_name, @@ -1017,6 +1048,7 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name, curr_dso = dso__new(dso_name); if (curr_dso == NULL) goto out_elf_end; + curr_dso->kernel = self->kernel; curr_map = map__new2(start, curr_dso, map->type); if (curr_map == NULL) { @@ -1025,9 +1057,9 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name, } curr_map->map_ip = identity__map_ip; curr_map->unmap_ip = identity__map_ip; - curr_dso->origin = DSO__ORIG_KERNEL; + curr_dso->origin = self->origin; map_groups__insert(kmap->kmaps, curr_map); - dsos__add(&dsos__kernel, curr_dso); + dsos__add(&self->node, curr_dso); dso__set_loaded(curr_dso, map->type); } else curr_dso = curr_map->dso; @@ -1089,7 +1121,7 @@ static bool dso__build_id_equal(const struct dso *self, u8 *build_id) return memcmp(self->build_id, build_id, sizeof(self->build_id)) == 0; } -static bool __dsos__read_build_ids(struct list_head *head, bool with_hits) +bool __dsos__read_build_ids(struct list_head *head, bool with_hits) { bool have_build_id = false; struct dso *pos; @@ -1107,13 +1139,6 @@ static bool __dsos__read_build_ids(struct list_head *head, bool with_hits) return have_build_id; } -bool dsos__read_build_ids(bool with_hits) -{ - bool kbuildids = __dsos__read_build_ids(&dsos__kernel, with_hits), - ubuildids = __dsos__read_build_ids(&dsos__user, with_hits); - return kbuildids || ubuildids; -} - /* * Align offset to 4 bytes as needed for note name and descriptor data. */ @@ -1248,6 +1273,8 @@ char dso__symtab_origin(const struct dso *self) [DSO__ORIG_BUILDID] = 'b', [DSO__ORIG_DSO] = 'd', [DSO__ORIG_KMODULE] = 'K', + [DSO__ORIG_GUEST_KERNEL] = 'g', + [DSO__ORIG_GUEST_KMODULE] = 'G', }; if (self == NULL || self->origin == DSO__ORIG_NOT_FOUND) @@ -1263,11 +1290,20 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter) char build_id_hex[BUILD_ID_SIZE * 2 + 1]; int ret = -1; int fd; + struct kernel_info *kerninfo; + const char *root_dir; dso__set_loaded(self, map->type); - if (self->kernel) + if (self->kernel == DSO_TYPE_KERNEL) return dso__load_kernel_sym(self, map, filter); + else if (self->kernel == DSO_TYPE_GUEST_KERNEL) + return dso__load_guest_kernel_sym(self, map, filter); + + if (map->groups && map->groups->this_kerninfo) + kerninfo = map->groups->this_kerninfo; + else + kerninfo = NULL; name = malloc(size); if (!name) @@ -1321,6 +1357,13 @@ more: case DSO__ORIG_DSO: snprintf(name, size, "%s", self->long_name); break; + case DSO__ORIG_GUEST_KMODULE: + if (map->groups && map->groups->this_kerninfo) + root_dir = map->groups->this_kerninfo->root_dir; + else + root_dir = ""; + snprintf(name, size, "%s%s", root_dir, self->long_name); + break; default: goto out; @@ -1374,7 +1417,8 @@ struct map *map_groups__find_by_name(struct map_groups *self, return NULL; } -static int dso__kernel_module_get_build_id(struct dso *self) +static int dso__kernel_module_get_build_id(struct dso *self, + const char *root_dir) { char filename[PATH_MAX]; /* @@ -1384,8 +1428,8 @@ static int dso__kernel_module_get_build_id(struct dso *self) const char *name = self->short_name + 1; snprintf(filename, sizeof(filename), - "/sys/module/%.*s/notes/.note.gnu.build-id", - (int)strlen(name - 1), name); + "%s/sys/module/%.*s/notes/.note.gnu.build-id", + root_dir, (int)strlen(name) - 1, name); if (sysfs__read_build_id(filename, self->build_id, sizeof(self->build_id)) == 0) @@ -1394,26 +1438,33 @@ static int dso__kernel_module_get_build_id(struct dso *self) return 0; } -static int map_groups__set_modules_path_dir(struct map_groups *self, char *dirname) +static int map_groups__set_modules_path_dir(struct map_groups *self, + const char *dir_name) { struct dirent *dent; - DIR *dir = opendir(dirname); + DIR *dir = opendir(dir_name); if (!dir) { - pr_debug("%s: cannot open %s dir\n", __func__, dirname); + pr_debug("%s: cannot open %s dir\n", __func__, dir_name); return -1; } while ((dent = readdir(dir)) != NULL) { char path[PATH_MAX]; + struct stat st; - if (dent->d_type == DT_DIR) { + /*sshfs might return bad dent->d_type, so we have to stat*/ + sprintf(path, "%s/%s", dir_name, dent->d_name); + if (stat(path, &st)) + continue; + + if (S_ISDIR(st.st_mode)) { if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) continue; snprintf(path, sizeof(path), "%s/%s", - dirname, dent->d_name); + dir_name, dent->d_name); if (map_groups__set_modules_path_dir(self, path) < 0) goto failure; } else { @@ -1433,13 +1484,13 @@ static int map_groups__set_modules_path_dir(struct map_groups *self, char *dirna continue; snprintf(path, sizeof(path), "%s/%s", - dirname, dent->d_name); + dir_name, dent->d_name); long_name = strdup(path); if (long_name == NULL) goto failure; dso__set_long_name(map->dso, long_name); - dso__kernel_module_get_build_id(map->dso); + dso__kernel_module_get_build_id(map->dso, ""); } } @@ -1449,16 +1500,46 @@ failure: return -1; } -static int map_groups__set_modules_path(struct map_groups *self) +static char *get_kernel_version(const char *root_dir) { - struct utsname uts; + char version[PATH_MAX]; + FILE *file; + char *name, *tmp; + const char *prefix = "Linux version "; + + sprintf(version, "%s/proc/version", root_dir); + file = fopen(version, "r"); + if (!file) + return NULL; + + version[0] = '\0'; + tmp = fgets(version, sizeof(version), file); + fclose(file); + + name = strstr(version, prefix); + if (!name) + return NULL; + name += strlen(prefix); + tmp = strchr(name, ' '); + if (tmp) + *tmp = '\0'; + + return strdup(name); +} + +static int map_groups__set_modules_path(struct map_groups *self, + const char *root_dir) +{ + char *version; char modules_path[PATH_MAX]; - if (uname(&uts) < 0) + version = get_kernel_version(root_dir); + if (!version) return -1; - snprintf(modules_path, sizeof(modules_path), "/lib/modules/%s/kernel", - uts.release); + snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel", + root_dir, version); + free(version); return map_groups__set_modules_path_dir(self, modules_path); } @@ -1470,8 +1551,8 @@ static int map_groups__set_modules_path(struct map_groups *self) */ static struct map *map__new2(u64 start, struct dso *dso, enum map_type type) { - struct map *self = zalloc(sizeof(*self) + - (dso->kernel ? sizeof(struct kmap) : 0)); + struct map *self = calloc(1, (sizeof(*self) + + (dso->kernel ? sizeof(struct kmap) : 0))); if (self != NULL) { /* * ->end will be filled after we load all the symbols @@ -1483,11 +1564,13 @@ static struct map *map__new2(u64 start, struct dso *dso, enum map_type type) } struct map *map_groups__new_module(struct map_groups *self, u64 start, - const char *filename) + const char *filename, + struct kernel_info *kerninfo) { struct map *map; - struct dso *dso = __dsos__findnew(&dsos__kernel, filename); + struct dso *dso; + dso = __dsos__findnew(&kerninfo->dsos__kernel, filename); if (dso == NULL) return NULL; @@ -1495,21 +1578,37 @@ struct map *map_groups__new_module(struct map_groups *self, u64 start, if (map == NULL) return NULL; - dso->origin = DSO__ORIG_KMODULE; + if (is_host_kernel(kerninfo)) + dso->origin = DSO__ORIG_KMODULE; + else + dso->origin = DSO__ORIG_GUEST_KMODULE; map_groups__insert(self, map); return map; } -static int map_groups__create_modules(struct map_groups *self) +static int map_groups__create_modules(struct kernel_info *kerninfo) { char *line = NULL; size_t n; - FILE *file = fopen("/proc/modules", "r"); + FILE *file; struct map *map; + const char *root_dir; + const char *modules; + char path[PATH_MAX]; + + if (is_default_guest(kerninfo)) + modules = symbol_conf.default_guest_modules; + else { + sprintf(path, "%s/proc/modules", kerninfo->root_dir); + modules = path; + } + file = fopen(modules, "r"); if (file == NULL) return -1; + root_dir = kerninfo->root_dir; + while (!feof(file)) { char name[PATH_MAX]; u64 start; @@ -1538,16 +1637,17 @@ static int map_groups__create_modules(struct map_groups *self) *sep = '\0'; snprintf(name, sizeof(name), "[%s]", line); - map = map_groups__new_module(self, start, name); + map = map_groups__new_module(&kerninfo->kmaps, + start, name, kerninfo); if (map == NULL) goto out_delete_line; - dso__kernel_module_get_build_id(map->dso); + dso__kernel_module_get_build_id(map->dso, root_dir); } free(line); fclose(file); - return map_groups__set_modules_path(self); + return map_groups__set_modules_path(&kerninfo->kmaps, root_dir); out_delete_line: free(line); @@ -1714,8 +1814,57 @@ out_fixup: return err; } -LIST_HEAD(dsos__user); -LIST_HEAD(dsos__kernel); +static int dso__load_guest_kernel_sym(struct dso *self, struct map *map, + symbol_filter_t filter) +{ + int err; + const char *kallsyms_filename = NULL; + struct kernel_info *kerninfo; + char path[PATH_MAX]; + + if (!map->groups) { + pr_debug("Guest kernel map hasn't the point to groups\n"); + return -1; + } + kerninfo = map->groups->this_kerninfo; + + if (is_default_guest(kerninfo)) { + /* + * if the user specified a vmlinux filename, use it and only + * it, reporting errors to the user if it cannot be used. + * Or use file guest_kallsyms inputted by user on commandline + */ + if (symbol_conf.default_guest_vmlinux_name != NULL) { + err = dso__load_vmlinux(self, map, + symbol_conf.default_guest_vmlinux_name, filter); + goto out_try_fixup; + } + + kallsyms_filename = symbol_conf.default_guest_kallsyms; + if (!kallsyms_filename) + return -1; + } else { + sprintf(path, "%s/proc/kallsyms", kerninfo->root_dir); + kallsyms_filename = path; + } + + err = dso__load_kallsyms(self, kallsyms_filename, map, filter); + if (err > 0) + pr_debug("Using %s for symbols\n", kallsyms_filename); + +out_try_fixup: + if (err > 0) { + if (kallsyms_filename != NULL) { + kern_mmap_name(kerninfo, path); + dso__set_long_name(self, + strdup(path)); + } + map__fixup_start(map); + map__fixup_end(map); + } + + return err; +} static void dsos__add(struct list_head *head, struct dso *dso) { @@ -1758,10 +1907,16 @@ static void __dsos__fprintf(struct list_head *head, FILE *fp) } } -void dsos__fprintf(FILE *fp) +void dsos__fprintf(struct rb_root *kerninfo_root, FILE *fp) { - __dsos__fprintf(&dsos__kernel, fp); - __dsos__fprintf(&dsos__user, fp); + struct rb_node *nd; + + for (nd = rb_first(kerninfo_root); nd; nd = rb_next(nd)) { + struct kernel_info *pos = rb_entry(nd, struct kernel_info, + rb_node); + __dsos__fprintf(&pos->dsos__kernel, fp); + __dsos__fprintf(&pos->dsos__user, fp); + } } static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, @@ -1779,10 +1934,21 @@ static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, return ret; } -size_t dsos__fprintf_buildid(FILE *fp, bool with_hits) +size_t dsos__fprintf_buildid(struct rb_root *kerninfo_root, + FILE *fp, bool with_hits) { - return (__dsos__fprintf_buildid(&dsos__kernel, fp, with_hits) + - __dsos__fprintf_buildid(&dsos__user, fp, with_hits)); + struct rb_node *nd; + size_t ret = 0; + + for (nd = rb_first(kerninfo_root); nd; nd = rb_next(nd)) { + struct kernel_info *pos = rb_entry(nd, struct kernel_info, + rb_node); + ret += __dsos__fprintf_buildid(&pos->dsos__kernel, + fp, with_hits); + ret += __dsos__fprintf_buildid(&pos->dsos__user, + fp, with_hits); + } + return ret; } struct dso *dso__new_kernel(const char *name) @@ -1791,28 +1957,59 @@ struct dso *dso__new_kernel(const char *name) if (self != NULL) { dso__set_short_name(self, "[kernel]"); - self->kernel = 1; + self->kernel = DSO_TYPE_KERNEL; + } + + return self; +} + +static struct dso *dso__new_guest_kernel(struct kernel_info *kerninfo, + const char *name) +{ + char buff[PATH_MAX]; + struct dso *self; + + kern_mmap_name(kerninfo, buff); + self = dso__new(name ?: buff); + if (self != NULL) { + dso__set_short_name(self, "[guest.kernel]"); + self->kernel = DSO_TYPE_GUEST_KERNEL; } return self; } -void dso__read_running_kernel_build_id(struct dso *self) +void dso__read_running_kernel_build_id(struct dso *self, + struct kernel_info *kerninfo) { - if (sysfs__read_build_id("/sys/kernel/notes", self->build_id, + char path[PATH_MAX]; + + if (is_default_guest(kerninfo)) + return; + sprintf(path, "%s/sys/kernel/notes", kerninfo->root_dir); + if (sysfs__read_build_id(path, self->build_id, sizeof(self->build_id)) == 0) self->has_build_id = true; } -static struct dso *dsos__create_kernel(const char *vmlinux) +static struct dso *dsos__create_kernel(struct kernel_info *kerninfo) { - struct dso *kernel = dso__new_kernel(vmlinux); + const char *vmlinux_name = NULL; + struct dso *kernel; - if (kernel != NULL) { - dso__read_running_kernel_build_id(kernel); - dsos__add(&dsos__kernel, kernel); + if (is_host_kernel(kerninfo)) { + vmlinux_name = symbol_conf.vmlinux_name; + kernel = dso__new_kernel(vmlinux_name); + } else { + if (is_default_guest(kerninfo)) + vmlinux_name = symbol_conf.default_guest_vmlinux_name; + kernel = dso__new_guest_kernel(kerninfo, vmlinux_name); } + if (kernel != NULL) { + dso__read_running_kernel_build_id(kernel, kerninfo); + dsos__add(&kerninfo->dsos__kernel, kernel); + } return kernel; } @@ -1895,6 +2092,17 @@ out_fail: return -1; } +size_t vmlinux_path__fprintf(FILE *fp) +{ + int i; + size_t printed = 0; + + for (i = 0; i < vmlinux_path__nr_entries; ++i) + printed += fprintf(fp, "[%d] %s\n", i, vmlinux_path[i]); + + return printed; +} + static int setup_list(struct strlist **list, const char *list_str, const char *list_name) { @@ -1945,22 +2153,114 @@ out_free_comm_list: return -1; } -int map_groups__create_kernel_maps(struct map_groups *self, - struct map *vmlinux_maps[MAP__NR_TYPES]) +int map_groups__create_kernel_maps(struct rb_root *kerninfo_root, pid_t pid) { - struct dso *kernel = dsos__create_kernel(symbol_conf.vmlinux_name); + struct kernel_info *kerninfo; + struct dso *kernel; + kerninfo = kerninfo__findnew(kerninfo_root, pid); + if (kerninfo == NULL) + return -1; + kernel = dsos__create_kernel(kerninfo); if (kernel == NULL) return -1; - if (__map_groups__create_kernel_maps(self, vmlinux_maps, kernel) < 0) + if (__map_groups__create_kernel_maps(&kerninfo->kmaps, + kerninfo->vmlinux_maps, kernel) < 0) return -1; - if (symbol_conf.use_modules && map_groups__create_modules(self) < 0) + if (symbol_conf.use_modules && + map_groups__create_modules(kerninfo) < 0) pr_debug("Problems creating module maps, continuing anyway...\n"); /* * Now that we have all the maps created, just set the ->end of them: */ - map_groups__fixup_end(self); + map_groups__fixup_end(&kerninfo->kmaps); return 0; } + +static int hex(char ch) +{ + if ((ch >= '0') && (ch <= '9')) + return ch - '0'; + if ((ch >= 'a') && (ch <= 'f')) + return ch - 'a' + 10; + if ((ch >= 'A') && (ch <= 'F')) + return ch - 'A' + 10; + return -1; +} + +/* + * While we find nice hex chars, build a long_val. + * Return number of chars processed. + */ +int hex2u64(const char *ptr, u64 *long_val) +{ + const char *p = ptr; + *long_val = 0; + + while (*p) { + const int hex_val = hex(*p); + + if (hex_val < 0) + break; + + *long_val = (*long_val << 4) | hex_val; + p++; + } + + return p - ptr; +} + +char *strxfrchar(char *s, char from, char to) +{ + char *p = s; + + while ((p = strchr(p, from)) != NULL) + *p++ = to; + + return s; +} + +int map_groups__create_guest_kernel_maps(struct rb_root *kerninfo_root) +{ + int ret = 0; + struct dirent **namelist = NULL; + int i, items = 0; + char path[PATH_MAX]; + pid_t pid; + + if (symbol_conf.default_guest_vmlinux_name || + symbol_conf.default_guest_modules || + symbol_conf.default_guest_kallsyms) { + map_groups__create_kernel_maps(kerninfo_root, + DEFAULT_GUEST_KERNEL_ID); + } + + if (symbol_conf.guestmount) { + items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL); + if (items <= 0) + return -ENOENT; + for (i = 0; i < items; i++) { + if (!isdigit(namelist[i]->d_name[0])) { + /* Filter out . and .. */ + continue; + } + pid = atoi(namelist[i]->d_name); + sprintf(path, "%s/%s/proc/kallsyms", + symbol_conf.guestmount, + namelist[i]->d_name); + ret = access(path, R_OK); + if (ret) { + pr_debug("Can't access file %s\n", path); + goto failure; + } + map_groups__create_kernel_maps(kerninfo_root, + pid); + } +failure: + free(namelist); + } + + return ret; +} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index f30a37428919..478f5ab37787 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -3,10 +3,11 @@ #include <linux/types.h> #include <stdbool.h> -#include "types.h" +#include <stdint.h> +#include "map.h" #include <linux/list.h> #include <linux/rbtree.h> -#include "event.h" +#include <stdio.h> #define DEBUG_CACHE_DIR ".debug" @@ -29,6 +30,9 @@ static inline char *bfd_demangle(void __used *v, const char __used *c, #endif #endif +int hex2u64(const char *ptr, u64 *val); +char *strxfrchar(char *s, char from, char to); + /* * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP; * for newer versions we can use mmap to reduce memory usage: @@ -44,6 +48,8 @@ static inline char *bfd_demangle(void __used *v, const char __used *c, #define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ #endif +#define BUILD_ID_SIZE 20 + struct symbol { struct rb_node rb_node; u64 start; @@ -63,10 +69,15 @@ struct symbol_conf { show_nr_samples, use_callchain, exclude_other, - full_paths; + full_paths, + show_cpu_utilization; const char *vmlinux_name, *field_sep; - char *dso_list_str, + const char *default_guest_vmlinux_name, + *default_guest_kallsyms, + *default_guest_modules; + const char *guestmount; + char *dso_list_str, *comm_list_str, *sym_list_str, *col_width_list_str; @@ -88,6 +99,11 @@ struct ref_reloc_sym { u64 unrelocated_addr; }; +struct map_symbol { + struct map *map; + struct symbol *sym; +}; + struct addr_location { struct thread *thread; struct map *map; @@ -95,6 +111,13 @@ struct addr_location { u64 addr; char level; bool filtered; + unsigned int cpumode; +}; + +enum dso_kernel_type { + DSO_TYPE_USER = 0, + DSO_TYPE_KERNEL, + DSO_TYPE_GUEST_KERNEL }; struct dso { @@ -104,8 +127,9 @@ struct dso { u8 adjust_symbols:1; u8 slen_calculated:1; u8 has_build_id:1; - u8 kernel:1; + enum dso_kernel_type kernel; u8 hit:1; + u8 annotate_warned:1; unsigned char origin; u8 sorted_by_name; u8 loaded; @@ -131,42 +155,60 @@ static inline void dso__set_loaded(struct dso *self, enum map_type type) void dso__sort_by_name(struct dso *self, enum map_type type); -extern struct list_head dsos__user, dsos__kernel; - struct dso *__dsos__findnew(struct list_head *head, const char *name); -static inline struct dso *dsos__findnew(const char *name) -{ - return __dsos__findnew(&dsos__user, name); -} - int dso__load(struct dso *self, struct map *map, symbol_filter_t filter); int dso__load_vmlinux_path(struct dso *self, struct map *map, symbol_filter_t filter); int dso__load_kallsyms(struct dso *self, const char *filename, struct map *map, symbol_filter_t filter); -void dsos__fprintf(FILE *fp); -size_t dsos__fprintf_buildid(FILE *fp, bool with_hits); +void dsos__fprintf(struct rb_root *kerninfo_root, FILE *fp); +size_t dsos__fprintf_buildid(struct rb_root *kerninfo_root, + FILE *fp, bool with_hits); size_t dso__fprintf_buildid(struct dso *self, FILE *fp); size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp); + +enum dso_origin { + DSO__ORIG_KERNEL = 0, + DSO__ORIG_GUEST_KERNEL, + DSO__ORIG_JAVA_JIT, + DSO__ORIG_BUILD_ID_CACHE, + DSO__ORIG_FEDORA, + DSO__ORIG_UBUNTU, + DSO__ORIG_BUILDID, + DSO__ORIG_DSO, + DSO__ORIG_GUEST_KMODULE, + DSO__ORIG_KMODULE, + DSO__ORIG_NOT_FOUND, +}; + char dso__symtab_origin(const struct dso *self); void dso__set_long_name(struct dso *self, char *name); void dso__set_build_id(struct dso *self, void *build_id); -void dso__read_running_kernel_build_id(struct dso *self); +void dso__read_running_kernel_build_id(struct dso *self, + struct kernel_info *kerninfo); struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr); struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type, const char *name); int filename__read_build_id(const char *filename, void *bf, size_t size); int sysfs__read_build_id(const char *filename, void *bf, size_t size); -bool dsos__read_build_ids(bool with_hits); +bool __dsos__read_build_ids(struct list_head *head, bool with_hits); int build_id__sprintf(const u8 *self, int len, char *bf); int kallsyms__parse(const char *filename, void *arg, int (*process_symbol)(void *arg, const char *name, char type, u64 start)); +int __map_groups__create_kernel_maps(struct map_groups *self, + struct map *vmlinux_maps[MAP__NR_TYPES], + struct dso *kernel); +int map_groups__create_kernel_maps(struct rb_root *kerninfo_root, pid_t pid); +int map_groups__create_guest_kernel_maps(struct rb_root *kerninfo_root); + int symbol__init(void); bool symbol_type__is_a(char symbol_type, enum map_type map_type); +size_t vmlinux_path__fprintf(FILE *fp); + #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index fa968312ee7d..1f7ecd47f499 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -7,13 +7,35 @@ #include "util.h" #include "debug.h" -void map_groups__init(struct map_groups *self) +int find_all_tid(int pid, pid_t ** all_tid) { + char name[256]; + int items; + struct dirent **namelist = NULL; + int ret = 0; int i; - for (i = 0; i < MAP__NR_TYPES; ++i) { - self->maps[i] = RB_ROOT; - INIT_LIST_HEAD(&self->removed_maps[i]); + + sprintf(name, "/proc/%d/task", pid); + items = scandir(name, &namelist, NULL, NULL); + if (items <= 0) + return -ENOENT; + *all_tid = malloc(sizeof(pid_t) * items); + if (!*all_tid) { + ret = -ENOMEM; + goto failure; } + + for (i = 0; i < items; i++) + (*all_tid)[i] = atoi(namelist[i]->d_name); + + ret = items; + +failure: + for (i=0; i<items; i++) + free(namelist[i]); + free(namelist); + + return ret; } static struct thread *thread__new(pid_t pid) @@ -31,28 +53,6 @@ static struct thread *thread__new(pid_t pid) return self; } -static void map_groups__flush(struct map_groups *self) -{ - int type; - - for (type = 0; type < MAP__NR_TYPES; type++) { - struct rb_root *root = &self->maps[type]; - struct rb_node *next = rb_first(root); - - while (next) { - struct map *pos = rb_entry(next, struct map, rb_node); - next = rb_next(&pos->rb_node); - rb_erase(&pos->rb_node, root); - /* - * We may have references to this map, for - * instance in some hist_entry instances, so - * just move them to a separate list. - */ - list_add_tail(&pos->node, &self->removed_maps[pos->type]); - } - } -} - int thread__set_comm(struct thread *self, const char *comm) { int err; @@ -79,69 +79,10 @@ int thread__comm_len(struct thread *self) return self->comm_len; } -size_t __map_groups__fprintf_maps(struct map_groups *self, - enum map_type type, FILE *fp) -{ - size_t printed = fprintf(fp, "%s:\n", map_type__name[type]); - struct rb_node *nd; - - for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) { - struct map *pos = rb_entry(nd, struct map, rb_node); - printed += fprintf(fp, "Map:"); - printed += map__fprintf(pos, fp); - if (verbose > 2) { - printed += dso__fprintf(pos->dso, type, fp); - printed += fprintf(fp, "--\n"); - } - } - - return printed; -} - -size_t map_groups__fprintf_maps(struct map_groups *self, FILE *fp) -{ - size_t printed = 0, i; - for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __map_groups__fprintf_maps(self, i, fp); - return printed; -} - -static size_t __map_groups__fprintf_removed_maps(struct map_groups *self, - enum map_type type, FILE *fp) -{ - struct map *pos; - size_t printed = 0; - - list_for_each_entry(pos, &self->removed_maps[type], node) { - printed += fprintf(fp, "Map:"); - printed += map__fprintf(pos, fp); - if (verbose > 1) { - printed += dso__fprintf(pos->dso, type, fp); - printed += fprintf(fp, "--\n"); - } - } - return printed; -} - -static size_t map_groups__fprintf_removed_maps(struct map_groups *self, FILE *fp) -{ - size_t printed = 0, i; - for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __map_groups__fprintf_removed_maps(self, i, fp); - return printed; -} - -static size_t map_groups__fprintf(struct map_groups *self, FILE *fp) -{ - size_t printed = map_groups__fprintf_maps(self, fp); - printed += fprintf(fp, "Removed maps:\n"); - return printed + map_groups__fprintf_removed_maps(self, fp); -} - static size_t thread__fprintf(struct thread *self, FILE *fp) { return fprintf(fp, "Thread %d %s\n", self->pid, self->comm) + - map_groups__fprintf(&self->mg, fp); + map_groups__fprintf(&self->mg, verbose, fp); } struct thread *perf_session__findnew(struct perf_session *self, pid_t pid) @@ -183,127 +124,12 @@ struct thread *perf_session__findnew(struct perf_session *self, pid_t pid) return th; } -static int map_groups__fixup_overlappings(struct map_groups *self, - struct map *map) -{ - struct rb_root *root = &self->maps[map->type]; - struct rb_node *next = rb_first(root); - - while (next) { - struct map *pos = rb_entry(next, struct map, rb_node); - next = rb_next(&pos->rb_node); - - if (!map__overlap(pos, map)) - continue; - - if (verbose >= 2) { - fputs("overlapping maps:\n", stderr); - map__fprintf(map, stderr); - map__fprintf(pos, stderr); - } - - rb_erase(&pos->rb_node, root); - /* - * We may have references to this map, for instance in some - * hist_entry instances, so just move them to a separate - * list. - */ - list_add_tail(&pos->node, &self->removed_maps[map->type]); - /* - * Now check if we need to create new maps for areas not - * overlapped by the new map: - */ - if (map->start > pos->start) { - struct map *before = map__clone(pos); - - if (before == NULL) - return -ENOMEM; - - before->end = map->start - 1; - map_groups__insert(self, before); - if (verbose >= 2) - map__fprintf(before, stderr); - } - - if (map->end < pos->end) { - struct map *after = map__clone(pos); - - if (after == NULL) - return -ENOMEM; - - after->start = map->end + 1; - map_groups__insert(self, after); - if (verbose >= 2) - map__fprintf(after, stderr); - } - } - - return 0; -} - -void maps__insert(struct rb_root *maps, struct map *map) -{ - struct rb_node **p = &maps->rb_node; - struct rb_node *parent = NULL; - const u64 ip = map->start; - struct map *m; - - while (*p != NULL) { - parent = *p; - m = rb_entry(parent, struct map, rb_node); - if (ip < m->start) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - rb_link_node(&map->rb_node, parent, p); - rb_insert_color(&map->rb_node, maps); -} - -struct map *maps__find(struct rb_root *maps, u64 ip) -{ - struct rb_node **p = &maps->rb_node; - struct rb_node *parent = NULL; - struct map *m; - - while (*p != NULL) { - parent = *p; - m = rb_entry(parent, struct map, rb_node); - if (ip < m->start) - p = &(*p)->rb_left; - else if (ip > m->end) - p = &(*p)->rb_right; - else - return m; - } - - return NULL; -} - void thread__insert_map(struct thread *self, struct map *map) { - map_groups__fixup_overlappings(&self->mg, map); + map_groups__fixup_overlappings(&self->mg, map, verbose, stderr); map_groups__insert(&self->mg, map); } -/* - * XXX This should not really _copy_ te maps, but refcount them. - */ -static int map_groups__clone(struct map_groups *self, - struct map_groups *parent, enum map_type type) -{ - struct rb_node *nd; - for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) { - struct map *map = rb_entry(nd, struct map, rb_node); - struct map *new = map__clone(map); - if (new == NULL) - return -ENOMEM; - map_groups__insert(self, new); - } - return 0; -} - int thread__fork(struct thread *self, struct thread *parent) { int i; @@ -336,15 +162,3 @@ size_t perf_session__fprintf(struct perf_session *self, FILE *fp) return ret; } - -struct symbol *map_groups__find_symbol(struct map_groups *self, - enum map_type type, u64 addr, - symbol_filter_t filter) -{ - struct map *map = map_groups__find(self, type, addr); - - if (map != NULL) - return map__find_symbol(map, map->map_ip(map, addr), filter); - - return NULL; -} diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index dcf70303e58e..1dfd9ff8bdcd 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -5,14 +5,6 @@ #include <unistd.h> #include "symbol.h" -struct map_groups { - struct rb_root maps[MAP__NR_TYPES]; - struct list_head removed_maps[MAP__NR_TYPES]; -}; - -size_t __map_groups__fprintf_maps(struct map_groups *self, - enum map_type type, FILE *fp); - struct thread { struct rb_node rb_node; struct map_groups mg; @@ -23,29 +15,16 @@ struct thread { int comm_len; }; -void map_groups__init(struct map_groups *self); +struct perf_session; + +int find_all_tid(int pid, pid_t ** all_tid); int thread__set_comm(struct thread *self, const char *comm); int thread__comm_len(struct thread *self); struct thread *perf_session__findnew(struct perf_session *self, pid_t pid); void thread__insert_map(struct thread *self, struct map *map); int thread__fork(struct thread *self, struct thread *parent); -size_t map_groups__fprintf_maps(struct map_groups *self, FILE *fp); size_t perf_session__fprintf(struct perf_session *self, FILE *fp); -void maps__insert(struct rb_root *maps, struct map *map); -struct map *maps__find(struct rb_root *maps, u64 addr); - -static inline void map_groups__insert(struct map_groups *self, struct map *map) -{ - maps__insert(&self->maps[map->type], map); -} - -static inline struct map *map_groups__find(struct map_groups *self, - enum map_type type, u64 addr) -{ - return maps__find(&self->maps[type], addr); -} - static inline struct map *thread__find_map(struct thread *self, enum map_type type, u64 addr) { @@ -54,34 +33,12 @@ static inline struct map *thread__find_map(struct thread *self, void thread__find_addr_map(struct thread *self, struct perf_session *session, u8 cpumode, - enum map_type type, u64 addr, + enum map_type type, pid_t pid, u64 addr, struct addr_location *al); void thread__find_addr_location(struct thread *self, struct perf_session *session, u8 cpumode, - enum map_type type, u64 addr, + enum map_type type, pid_t pid, u64 addr, struct addr_location *al, symbol_filter_t filter); -struct symbol *map_groups__find_symbol(struct map_groups *self, - enum map_type type, u64 addr, - symbol_filter_t filter); - -static inline struct symbol *map_groups__find_function(struct map_groups *self, - u64 addr, - symbol_filter_t filter) -{ - return map_groups__find_symbol(self, MAP__FUNCTION, addr, filter); -} - -struct map *map_groups__find_by_name(struct map_groups *self, - enum map_type type, const char *name); - -int __map_groups__create_kernel_maps(struct map_groups *self, - struct map *vmlinux_maps[MAP__NR_TYPES], - struct dso *kernel); -int map_groups__create_kernel_maps(struct map_groups *self, - struct map *vmlinux_maps[MAP__NR_TYPES]); - -struct map *map_groups__new_module(struct map_groups *self, u64 start, - const char *filename); #endif /* __PERF_THREAD_H */ diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index 5ea8973ad331..30cd9b575953 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -154,10 +154,17 @@ static void put_tracing_file(char *file) free(file); } +static ssize_t calc_data_size; + static ssize_t write_or_die(const void *buf, size_t len) { int ret; + if (calc_data_size) { + calc_data_size += len; + return len; + } + ret = write(output_fd, buf, len); if (ret < 0) die("writing to '%s'", output_file); @@ -526,3 +533,20 @@ int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events) return 0; } + +ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs, + int nb_events) +{ + ssize_t size; + int err = 0; + + calc_data_size = 1; + err = read_tracing_data(fd, pattrs, nb_events); + size = calc_data_size - 1; + calc_data_size = 0; + + if (err < 0) + return err; + + return size; +} diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 9b3c20f42f98..d6ef414075a6 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -37,10 +37,12 @@ int header_page_ts_offset; int header_page_ts_size; int header_page_size_offset; int header_page_size_size; +int header_page_overwrite_offset; +int header_page_overwrite_size; int header_page_data_offset; int header_page_data_size; -int latency_format; +bool latency_format; static char *input_buf; static unsigned long long input_buf_ptr; @@ -628,23 +630,32 @@ static int test_type(enum event_type type, enum event_type expect) return 0; } -static int test_type_token(enum event_type type, char *token, - enum event_type expect, const char *expect_tok) +static int __test_type_token(enum event_type type, char *token, + enum event_type expect, const char *expect_tok, + bool warn) { if (type != expect) { - warning("Error: expected type %d but read %d", - expect, type); + if (warn) + warning("Error: expected type %d but read %d", + expect, type); return -1; } if (strcmp(token, expect_tok) != 0) { - warning("Error: expected '%s' but read '%s'", - expect_tok, token); + if (warn) + warning("Error: expected '%s' but read '%s'", + expect_tok, token); return -1; } return 0; } +static int test_type_token(enum event_type type, char *token, + enum event_type expect, const char *expect_tok) +{ + return __test_type_token(type, token, expect, expect_tok, true); +} + static int __read_expect_type(enum event_type expect, char **tok, int newline_ok) { enum event_type type; @@ -661,7 +672,8 @@ static int read_expect_type(enum event_type expect, char **tok) return __read_expect_type(expect, tok, 1); } -static int __read_expected(enum event_type expect, const char *str, int newline_ok) +static int __read_expected(enum event_type expect, const char *str, + int newline_ok, bool warn) { enum event_type type; char *token; @@ -672,21 +684,26 @@ static int __read_expected(enum event_type expect, const char *str, int newline_ else type = read_token_item(&token); - ret = test_type_token(type, token, expect, str); + ret = __test_type_token(type, token, expect, str, warn); free_token(token); return ret; } +static int read_expected_warn(enum event_type expect, const char *str, bool warn) +{ + return __read_expected(expect, str, 1, warn); +} + static int read_expected(enum event_type expect, const char *str) { - return __read_expected(expect, str, 1); + return __read_expected(expect, str, 1, true); } static int read_expected_item(enum event_type expect, const char *str) { - return __read_expected(expect, str, 0); + return __read_expected(expect, str, 0, true); } static char *event_read_name(void) @@ -744,7 +761,7 @@ static int field_is_string(struct format_field *field) static int field_is_dynamic(struct format_field *field) { - if (!strcmp(field->type, "__data_loc")) + if (!strncmp(field->type, "__data_loc", 10)) return 1; return 0; @@ -3088,7 +3105,7 @@ static void print_args(struct print_arg *args) } static void parse_header_field(const char *field, - int *offset, int *size) + int *offset, int *size, bool warn) { char *token; int type; @@ -3103,7 +3120,7 @@ static void parse_header_field(const char *field, goto fail; free_token(token); - if (read_expected(EVENT_ITEM, field) < 0) + if (read_expected_warn(EVENT_ITEM, field, warn) < 0) return; if (read_expected(EVENT_OP, ";") < 0) return; @@ -3160,11 +3177,13 @@ int parse_header_page(char *buf, unsigned long size) init_input_buf(buf, size); parse_header_field("timestamp", &header_page_ts_offset, - &header_page_ts_size); + &header_page_ts_size, true); parse_header_field("commit", &header_page_size_offset, - &header_page_size_size); + &header_page_size_size, true); + parse_header_field("overwrite", &header_page_overwrite_offset, + &header_page_overwrite_size, false); parse_header_field("data", &header_page_data_offset, - &header_page_data_size); + &header_page_data_size, true); return 0; } diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index 7cd1193918c7..44889c9b5630 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -50,14 +50,37 @@ static int long_size; static unsigned long page_size; +static ssize_t calc_data_size; + +static int do_read(int fd, void *buf, int size) +{ + int rsize = size; + + while (size) { + int ret = read(fd, buf, size); + + if (ret <= 0) + return -1; + + size -= ret; + buf += ret; + } + + return rsize; +} + static int read_or_die(void *data, int size) { int r; - r = read(input_fd, data, size); - if (r != size) + r = do_read(input_fd, data, size); + if (r <= 0) die("reading input file (size expected=%d received=%d)", size, r); + + if (calc_data_size) + calc_data_size += r; + return r; } @@ -82,56 +105,28 @@ static char *read_string(void) char buf[BUFSIZ]; char *str = NULL; int size = 0; - int i; off_t r; + char c; for (;;) { - r = read(input_fd, buf, BUFSIZ); + r = read(input_fd, &c, 1); if (r < 0) die("reading input file"); if (!r) die("no data"); - for (i = 0; i < r; i++) { - if (!buf[i]) - break; - } - if (i < r) - break; + buf[size++] = c; - if (str) { - size += BUFSIZ; - str = realloc(str, size); - if (!str) - die("malloc of size %d", size); - memcpy(str + (size - BUFSIZ), buf, BUFSIZ); - } else { - size = BUFSIZ; - str = malloc_or_die(size); - memcpy(str, buf, size); - } + if (!c) + break; } - /* trailing \0: */ - i++; - - /* move the file descriptor to the end of the string */ - r = lseek(input_fd, -(r - i), SEEK_CUR); - if (r == (off_t)-1) - die("lseek"); - - if (str) { - size += i; - str = realloc(str, size); - if (!str) - die("malloc of size %d", size); - memcpy(str + (size - i), buf, i); - } else { - size = i; - str = malloc_or_die(i); - memcpy(str, buf, i); - } + if (calc_data_size) + calc_data_size += size; + + str = malloc_or_die(size); + memcpy(str, buf, size); return str; } @@ -459,7 +454,7 @@ struct record *trace_read_data(int cpu) return data; } -void trace_report(int fd) +ssize_t trace_report(int fd) { char buf[BUFSIZ]; char test[] = { 23, 8, 68 }; @@ -467,6 +462,9 @@ void trace_report(int fd) int show_version = 0; int show_funcs = 0; int show_printk = 0; + ssize_t size; + + calc_data_size = 1; input_fd = fd; @@ -499,14 +497,17 @@ void trace_report(int fd) read_proc_kallsyms(); read_ftrace_printk(); + size = calc_data_size - 1; + calc_data_size = 0; + if (show_funcs) { print_funcs(); - return; + return size; } if (show_printk) { print_printk(); - return; + return size; } - return; + return size; } diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index c3269b937db4..1f45d468fd9a 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -1,6 +1,7 @@ #ifndef __PERF_TRACE_EVENTS_H #define __PERF_TRACE_EVENTS_H +#include <stdbool.h> #include "parse-events.h" #define __unused __attribute__((unused)) @@ -162,7 +163,7 @@ struct record *trace_read_data(int cpu); void parse_set_info(int nr_cpus, int long_sz); -void trace_report(int fd); +ssize_t trace_report(int fd); void *malloc_or_die(unsigned int size); @@ -241,7 +242,7 @@ extern int header_page_size_size; extern int header_page_data_offset; extern int header_page_data_size; -extern int latency_format; +extern bool latency_format; int parse_header_page(char *buf, unsigned long size); int trace_parse_common_type(void *data); @@ -258,6 +259,8 @@ void *raw_field_ptr(struct event *event, const char *name, void *data); unsigned long long eval_flag(const char *flag); int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events); +ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs, + int nb_events); /* taken from kernel/trace/trace.h */ enum trace_flag_type { diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 0f5b2a6f1080..fbf45d1b26f7 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -42,12 +42,14 @@ #define _ALL_SOURCE 1 #define _GNU_SOURCE 1 #define _BSD_SOURCE 1 +#define HAS_BOOL #include <unistd.h> #include <stdio.h> #include <sys/stat.h> #include <sys/statfs.h> #include <fcntl.h> +#include <stdbool.h> #include <stddef.h> #include <stdlib.h> #include <stdarg.h> @@ -78,6 +80,7 @@ #include <pwd.h> #include <inttypes.h> #include "../../../include/linux/magic.h" +#include "types.h" #ifndef NO_ICONV @@ -295,6 +298,13 @@ extern void *xmemdupz(const void *data, size_t len); extern char *xstrndup(const char *str, size_t len); extern void *xrealloc(void *ptr, size_t size) __attribute__((weak)); +static inline void *xzalloc(size_t size) +{ + void *buf = xmalloc(size); + + return memset(buf, 0, size); +} + static inline void *zalloc(size_t size) { return calloc(1, size); @@ -309,6 +319,7 @@ static inline int has_extension(const char *filename, const char *ext) { size_t len = strlen(filename); size_t extlen = strlen(ext); + return len > extlen && !memcmp(filename + len - extlen, ext, extlen); } @@ -322,6 +333,7 @@ static inline int has_extension(const char *filename, const char *ext) #undef isalnum #undef tolower #undef toupper + extern unsigned char sane_ctype[256]; #define GIT_SPACE 0x01 #define GIT_DIGIT 0x02 @@ -406,4 +418,13 @@ void git_qsort(void *base, size_t nmemb, size_t size, int mkdir_p(char *path, mode_t mode); int copyfile(const char *from, const char *to); +s64 perf_atoll(const char *str); +char **argv_split(const char *str, int *argcp); +void argv_free(char **argv); +bool strglobmatch(const char *str, const char *pat); +bool strlazymatch(const char *str, const char *pat); + +#define _STR(x) #x +#define STR(x) _STR(x) + #endif diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c index 02ff2b19dbe2..4d10b1e047f4 100644 --- a/virt/kvm/assigned-dev.c +++ b/virt/kvm/assigned-dev.c @@ -316,12 +316,16 @@ static int assigned_device_enable_host_msix(struct kvm *kvm, kvm_assigned_dev_intr, 0, "kvm_assigned_msix_device", (void *)dev); - /* FIXME: free requested_irq's on failure */ if (r) - return r; + goto err; } return 0; +err: + for (i -= 1; i >= 0; i--) + free_irq(dev->host_msix_entries[i].vector, (void *)dev); + pci_disable_msix(dev->dev); + return r; } #endif diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index 36e258029649..53850177163f 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -120,8 +120,10 @@ int kvm_coalesced_mmio_init(struct kvm *kvm) return ret; out_free_dev: + kvm->coalesced_mmio_dev = NULL; kfree(dev); out_free_page: + kvm->coalesced_mmio_ring = NULL; __free_page(page); out_err: return ret; @@ -139,7 +141,7 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, struct kvm_coalesced_mmio_dev *dev = kvm->coalesced_mmio_dev; if (dev == NULL) - return -EINVAL; + return -ENXIO; mutex_lock(&kvm->slots_lock); if (dev->nb_zones >= KVM_COALESCED_MMIO_ZONE_MAX) { @@ -162,7 +164,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, struct kvm_coalesced_mmio_zone *z; if (dev == NULL) - return -EINVAL; + return -ENXIO; mutex_lock(&kvm->slots_lock); diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index 80fd3ad3b2de..37ca71ebdba8 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -78,7 +78,7 @@ static int kvm_iommu_map_memslots(struct kvm *kvm) int i, r = 0; struct kvm_memslots *slots; - slots = rcu_dereference(kvm->memslots); + slots = kvm_memslots(kvm); for (i = 0; i < slots->nmemslots; i++) { r = kvm_iommu_map_pages(kvm, &slots->memslots[i]); @@ -217,7 +217,7 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm) int i; struct kvm_memslots *slots; - slots = rcu_dereference(kvm->memslots); + slots = kvm_memslots(kvm); for (i = 0; i < slots->nmemslots; i++) { kvm_iommu_put_pages(kvm, slots->memslots[i].base_gfn, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c82ae2492634..9ab1a77941ef 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -422,9 +422,6 @@ static struct kvm *kvm_create_vm(void) spin_lock(&kvm_lock); list_add(&kvm->vm_list, &vm_list); spin_unlock(&kvm_lock); -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET - kvm_coalesced_mmio_init(kvm); -#endif out: return kvm; @@ -560,6 +557,10 @@ int __kvm_set_memory_region(struct kvm *kvm, base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; npages = mem->memory_size >> PAGE_SHIFT; + r = -EINVAL; + if (npages > KVM_MEM_MAX_NR_PAGES) + goto out; + if (!npages) mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES; @@ -833,7 +834,7 @@ EXPORT_SYMBOL_GPL(kvm_is_error_hva); struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn) { int i; - struct kvm_memslots *slots = rcu_dereference(kvm->memslots); + struct kvm_memslots *slots = kvm_memslots(kvm); for (i = 0; i < slots->nmemslots; ++i) { struct kvm_memory_slot *memslot = &slots->memslots[i]; @@ -855,7 +856,7 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { int i; - struct kvm_memslots *slots = rcu_dereference(kvm->memslots); + struct kvm_memslots *slots = kvm_memslots(kvm); gfn = unalias_gfn_instantiation(kvm, gfn); for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { @@ -899,7 +900,7 @@ out: int memslot_id(struct kvm *kvm, gfn_t gfn) { int i; - struct kvm_memslots *slots = rcu_dereference(kvm->memslots); + struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *memslot = NULL; gfn = unalias_gfn(kvm, gfn); @@ -914,6 +915,11 @@ int memslot_id(struct kvm *kvm, gfn_t gfn) return memslot - slots->memslots; } +static unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +{ + return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE; +} + unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *slot; @@ -922,7 +928,7 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) slot = gfn_to_memslot_unaliased(kvm, gfn); if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return bad_hva(); - return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE); + return gfn_to_hva_memslot(slot, gfn); } EXPORT_SYMBOL_GPL(gfn_to_hva); @@ -972,11 +978,6 @@ pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_pfn); -static unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) -{ - return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE); -} - pfn_t gfn_to_pfn_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn) { @@ -1190,13 +1191,8 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn) memslot = gfn_to_memslot_unaliased(kvm, gfn); if (memslot && memslot->dirty_bitmap) { unsigned long rel_gfn = gfn - memslot->base_gfn; - unsigned long *p = memslot->dirty_bitmap + - rel_gfn / BITS_PER_LONG; - int offset = rel_gfn % BITS_PER_LONG; - /* avoid RMW */ - if (!generic_test_le_bit(offset, p)) - generic___set_le_bit(offset, p); + generic___set_le_bit(rel_gfn, memslot->dirty_bitmap); } } @@ -1609,7 +1605,6 @@ static long kvm_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&zone, argp, sizeof zone)) goto out; - r = -ENXIO; r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone); if (r) goto out; @@ -1621,7 +1616,6 @@ static long kvm_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&zone, argp, sizeof zone)) goto out; - r = -ENXIO; r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone); if (r) goto out; @@ -1755,12 +1749,19 @@ static struct file_operations kvm_vm_fops = { static int kvm_dev_ioctl_create_vm(void) { - int fd; + int fd, r; struct kvm *kvm; kvm = kvm_create_vm(); if (IS_ERR(kvm)) return PTR_ERR(kvm); +#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET + r = kvm_coalesced_mmio_init(kvm); + if (r < 0) { + kvm_put_kvm(kvm); + return r; + } +#endif fd = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR); if (fd < 0) kvm_put_kvm(kvm); @@ -1928,11 +1929,6 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, cpu); hardware_disable(NULL); break; - case CPU_UP_CANCELED: - printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n", - cpu); - smp_call_function_single(cpu, hardware_disable, NULL, 1); - break; case CPU_ONLINE: printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n", cpu); @@ -1991,7 +1987,9 @@ int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val) { int i; - struct kvm_io_bus *bus = rcu_dereference(kvm->buses[bus_idx]); + struct kvm_io_bus *bus; + + bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); for (i = 0; i < bus->dev_count; i++) if (!kvm_iodevice_write(bus->devs[i], addr, len, val)) return 0; @@ -2003,8 +2001,9 @@ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, void *val) { int i; - struct kvm_io_bus *bus = rcu_dereference(kvm->buses[bus_idx]); + struct kvm_io_bus *bus; + bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); for (i = 0; i < bus->dev_count; i++) if (!kvm_iodevice_read(bus->devs[i], addr, len, val)) return 0; @@ -2279,7 +2278,6 @@ EXPORT_SYMBOL_GPL(kvm_init); void kvm_exit(void) { - tracepoint_synchronize_unregister(); kvm_exit_debug(); misc_deregister(&kvm_dev); kmem_cache_destroy(kvm_vcpu_cache); |