diff options
39 files changed, 1190 insertions, 342 deletions
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 74f0c5ea2a03..c98d54688180 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -403,6 +403,7 @@ struct pv_mmu_ops pv_mmu_ops = { #endif /* PAGETABLE_LEVELS >= 3 */ .pte_val = native_pte_val, + .pte_flags = native_pte_val, .pgd_val = native_pgd_val, .make_pte = native_make_pte, diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 2e641be2737e..d0f1c7c5dc3d 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -6,8 +6,18 @@ config XEN bool "Xen guest support" select PARAVIRT depends on X86_32 - depends on X86_CMPXCHG && X86_TSC && !(X86_VISWS || X86_VOYAGER) + depends on X86_CMPXCHG && X86_TSC && X86_PAE && !(X86_VISWS || X86_VOYAGER) help This is the Linux Xen port. Enabling this will allow the kernel to boot in a paravirtualized environment under the Xen hypervisor. + +config XEN_MAX_DOMAIN_MEMORY + int "Maximum allowed size of a domain in gigabytes" + default 8 + depends on XEN + help + The pseudo-physical to machine address array is sized + according to the maximum possible memory size of a Xen + domain. This array uses 1 page per gigabyte, so there's no + need to be too stingy here.
\ No newline at end of file diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 3d8df981d5fd..2ba2d1649131 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -1,4 +1,4 @@ obj-y := enlighten.o setup.o multicalls.o mmu.o \ - time.o manage.o xen-asm.o grant-table.o + time.o xen-asm.o grant-table.o suspend.o obj-$(CONFIG_SMP) += smp.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c8a56e457d61..8e6152e6ed88 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -75,13 +75,13 @@ DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */ struct start_info *xen_start_info; EXPORT_SYMBOL_GPL(xen_start_info); -static /* __initdata */ struct shared_info dummy_shared_info; +struct shared_info xen_dummy_shared_info; /* * Point at some empty memory to start with. We map the real shared_info * page as soon as fixmap is up and running. */ -struct shared_info *HYPERVISOR_shared_info = (void *)&dummy_shared_info; +struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; /* * Flag to determine whether vcpu info placement is available on all @@ -98,13 +98,13 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&dummy_shared_info; */ static int have_vcpu_info_placement = 1; -static void __init xen_vcpu_setup(int cpu) +static void xen_vcpu_setup(int cpu) { struct vcpu_register_vcpu_info info; int err; struct vcpu_info *vcpup; - BUG_ON(HYPERVISOR_shared_info == &dummy_shared_info); + BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; if (!have_vcpu_info_placement) @@ -136,6 +136,34 @@ static void __init xen_vcpu_setup(int cpu) } } +/* + * On restore, set the vcpu placement up again. + * If it fails, then we're in a bad state, since + * we can't back out from using it... + */ +void xen_vcpu_restore(void) +{ + if (have_vcpu_info_placement) { + int cpu; + + for_each_online_cpu(cpu) { + bool other_cpu = (cpu != smp_processor_id()); + + if (other_cpu && + HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL)) + BUG(); + + xen_vcpu_setup(cpu); + + if (other_cpu && + HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL)) + BUG(); + } + + BUG_ON(!have_vcpu_info_placement); + } +} + static void __init xen_banner(void) { printk(KERN_INFO "Booting paravirtualized kernel on %s\n", @@ -235,13 +263,13 @@ static void xen_irq_enable(void) { struct vcpu_info *vcpu; - /* There's a one instruction preempt window here. We need to - make sure we're don't switch CPUs between getting the vcpu - pointer and updating the mask. */ - preempt_disable(); + /* We don't need to worry about being preempted here, since + either a) interrupts are disabled, so no preemption, or b) + the caller is confused and is trying to re-enable interrupts + on an indeterminate processor. */ + vcpu = x86_read_percpu(xen_vcpu); vcpu->evtchn_upcall_mask = 0; - preempt_enable_no_resched(); /* Doesn't matter if we get preempted here, because any pending event will get dealt with anyway. */ @@ -254,7 +282,7 @@ static void xen_irq_enable(void) static void xen_safe_halt(void) { /* Blocking includes an implicit local_irq_enable(). */ - if (HYPERVISOR_sched_op(SCHEDOP_block, 0) != 0) + if (HYPERVISOR_sched_op(SCHEDOP_block, NULL) != 0) BUG(); } @@ -607,6 +635,30 @@ static void xen_flush_tlb_others(const cpumask_t *cpus, struct mm_struct *mm, xen_mc_issue(PARAVIRT_LAZY_MMU); } +static void xen_clts(void) +{ + struct multicall_space mcs; + + mcs = xen_mc_entry(0); + + MULTI_fpu_taskswitch(mcs.mc, 0); + + xen_mc_issue(PARAVIRT_LAZY_CPU); +} + +static void xen_write_cr0(unsigned long cr0) +{ + struct multicall_space mcs; + + /* Only pay attention to cr0.TS; everything else is + ignored. */ + mcs = xen_mc_entry(0); + + MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0); + + xen_mc_issue(PARAVIRT_LAZY_CPU); +} + static void xen_write_cr2(unsigned long cr2) { x86_read_percpu(xen_vcpu)->arch.cr2 = cr2; @@ -624,8 +676,10 @@ static unsigned long xen_read_cr2_direct(void) static void xen_write_cr4(unsigned long cr4) { - /* Just ignore cr4 changes; Xen doesn't allow us to do - anything anyway. */ + cr4 &= ~X86_CR4_PGE; + cr4 &= ~X86_CR4_PSE; + + native_write_cr4(cr4); } static unsigned long xen_read_cr3(void) @@ -785,38 +839,35 @@ static __init void xen_set_pte_init(pte_t *ptep, pte_t pte) static __init void xen_pagetable_setup_start(pgd_t *base) { pgd_t *xen_pgd = (pgd_t *)xen_start_info->pt_base; + int i; /* special set_pte for pagetable initialization */ pv_mmu_ops.set_pte = xen_set_pte_init; init_mm.pgd = base; /* - * copy top-level of Xen-supplied pagetable into place. For - * !PAE we can use this as-is, but for PAE it is a stand-in - * while we copy the pmd pages. + * copy top-level of Xen-supplied pagetable into place. This + * is a stand-in while we copy the pmd pages. */ memcpy(base, xen_pgd, PTRS_PER_PGD * sizeof(pgd_t)); - if (PTRS_PER_PMD > 1) { - int i; - /* - * For PAE, need to allocate new pmds, rather than - * share Xen's, since Xen doesn't like pmd's being - * shared between address spaces. - */ - for (i = 0; i < PTRS_PER_PGD; i++) { - if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) { - pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE); + /* + * For PAE, need to allocate new pmds, rather than + * share Xen's, since Xen doesn't like pmd's being + * shared between address spaces. + */ + for (i = 0; i < PTRS_PER_PGD; i++) { + if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) { + pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE); - memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]), - PAGE_SIZE); + memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]), + PAGE_SIZE); - make_lowmem_page_readonly(pmd); + make_lowmem_page_readonly(pmd); - set_pgd(&base[i], __pgd(1 + __pa(pmd))); - } else - pgd_clear(&base[i]); - } + set_pgd(&base[i], __pgd(1 + __pa(pmd))); + } else + pgd_clear(&base[i]); } /* make sure zero_page is mapped RO so we can use it in pagetables */ @@ -834,7 +885,7 @@ static __init void xen_pagetable_setup_start(pgd_t *base) PFN_DOWN(__pa(xen_start_info->pt_base))); } -static __init void setup_shared_info(void) +void xen_setup_shared_info(void) { if (!xen_feature(XENFEAT_auto_translated_physmap)) { unsigned long addr = fix_to_virt(FIX_PARAVIRT_BOOTMAP); @@ -857,6 +908,8 @@ static __init void setup_shared_info(void) /* In UP this is as good a place as any to set up shared info */ xen_setup_vcpu_info_placement(); #endif + + xen_setup_mfn_list_list(); } static __init void xen_pagetable_setup_done(pgd_t *base) @@ -869,25 +922,23 @@ static __init void xen_pagetable_setup_done(pgd_t *base) pv_mmu_ops.release_pmd = xen_release_pmd; pv_mmu_ops.set_pte = xen_set_pte; - setup_shared_info(); + xen_setup_shared_info(); /* Actually pin the pagetable down, but we can't set PG_pinned yet because the page structures don't exist yet. */ - { - unsigned level; + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(base))); +} -#ifdef CONFIG_X86_PAE - level = MMUEXT_PIN_L3_TABLE; -#else - level = MMUEXT_PIN_L2_TABLE; -#endif +static __init void xen_post_allocator_init(void) +{ + pv_mmu_ops.set_pmd = xen_set_pmd; + pv_mmu_ops.set_pud = xen_set_pud; - pin_pagetable_pfn(level, PFN_DOWN(__pa(base))); - } + xen_mark_init_mm_pinned(); } /* This is called once we have the cpu_possible_map */ -void __init xen_setup_vcpu_info_placement(void) +void xen_setup_vcpu_info_placement(void) { int cpu; @@ -973,7 +1024,7 @@ static const struct pv_init_ops xen_init_ops __initdata = { .banner = xen_banner, .memory_setup = xen_memory_setup, .arch_setup = xen_arch_setup, - .post_allocator_init = xen_mark_init_mm_pinned, + .post_allocator_init = xen_post_allocator_init, }; static const struct pv_time_ops xen_time_ops __initdata = { @@ -991,10 +1042,10 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = { .set_debugreg = xen_set_debugreg, .get_debugreg = xen_get_debugreg, - .clts = native_clts, + .clts = xen_clts, .read_cr0 = native_read_cr0, - .write_cr0 = native_write_cr0, + .write_cr0 = xen_write_cr0, .read_cr4 = native_read_cr4, .read_cr4_safe = native_read_cr4_safe, @@ -1085,24 +1136,23 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = { .set_pte = NULL, /* see xen_pagetable_setup_* */ .set_pte_at = xen_set_pte_at, - .set_pmd = xen_set_pmd, + .set_pmd = xen_set_pmd_hyper, .pte_val = xen_pte_val, + .pte_flags = native_pte_val, .pgd_val = xen_pgd_val, .make_pte = xen_make_pte, .make_pgd = xen_make_pgd, -#ifdef CONFIG_X86_PAE .set_pte_atomic = xen_set_pte_atomic, .set_pte_present = xen_set_pte_at, - .set_pud = xen_set_pud, + .set_pud = xen_set_pud_hyper, .pte_clear = xen_pte_clear, .pmd_clear = xen_pmd_clear, .make_pmd = xen_make_pmd, .pmd_val = xen_pmd_val, -#endif /* PAE */ .activate_mm = xen_activate_mm, .dup_mmap = xen_dup_mmap, @@ -1129,11 +1179,13 @@ static const struct smp_ops xen_smp_ops __initdata = { static void xen_reboot(int reason) { + struct sched_shutdown r = { .reason = reason }; + #ifdef CONFIG_SMP smp_send_stop(); #endif - if (HYPERVISOR_sched_op(SCHEDOP_shutdown, reason)) + if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r)) BUG(); } @@ -1207,7 +1259,7 @@ asmlinkage void __init xen_start_kernel(void) /* Get mfn list */ if (!xen_feature(XENFEAT_auto_translated_physmap)) - phys_to_machine_mapping = (unsigned long *)xen_start_info->mfn_list; + xen_build_dynamic_phys_to_machine(); pgd = (pgd_t *)xen_start_info->pt_base; @@ -1242,8 +1294,11 @@ asmlinkage void __init xen_start_kernel(void) ? __pa(xen_start_info->mod_start) : 0; boot_params.hdr.ramdisk_size = xen_start_info->mod_len; - if (!is_initial_xendomain()) + if (!is_initial_xendomain()) { + add_preferred_console("xenboot", 0, NULL); + add_preferred_console("tty", 0, NULL); add_preferred_console("hvc", 0, NULL); + } /* Start the world */ start_kernel(); diff --git a/arch/x86/xen/manage.c b/arch/x86/xen/manage.c deleted file mode 100644 index aa7af9e6abc0..000000000000 --- a/arch/x86/xen/manage.c +++ /dev/null @@ -1,143 +0,0 @@ -/* - * Handle extern requests for shutdown, reboot and sysrq - */ -#include <linux/kernel.h> -#include <linux/err.h> -#include <linux/reboot.h> -#include <linux/sysrq.h> - -#include <xen/xenbus.h> - -#define SHUTDOWN_INVALID -1 -#define SHUTDOWN_POWEROFF 0 -#define SHUTDOWN_SUSPEND 2 -/* Code 3 is SHUTDOWN_CRASH, which we don't use because the domain can only - * report a crash, not be instructed to crash! - * HALT is the same as POWEROFF, as far as we're concerned. The tools use - * the distinction when we return the reason code to them. - */ -#define SHUTDOWN_HALT 4 - -/* Ignore multiple shutdown requests. */ -static int shutting_down = SHUTDOWN_INVALID; - -static void shutdown_handler(struct xenbus_watch *watch, - const char **vec, unsigned int len) -{ - char *str; - struct xenbus_transaction xbt; - int err; - - if (shutting_down != SHUTDOWN_INVALID) - return; - - again: - err = xenbus_transaction_start(&xbt); - if (err) - return; - - str = (char *)xenbus_read(xbt, "control", "shutdown", NULL); - /* Ignore read errors and empty reads. */ - if (XENBUS_IS_ERR_READ(str)) { - xenbus_transaction_end(xbt, 1); - return; - } - - xenbus_write(xbt, "control", "shutdown", ""); - - err = xenbus_transaction_end(xbt, 0); - if (err == -EAGAIN) { - kfree(str); - goto again; - } - - if (strcmp(str, "poweroff") == 0 || - strcmp(str, "halt") == 0) - orderly_poweroff(false); - else if (strcmp(str, "reboot") == 0) - ctrl_alt_del(); - else { - printk(KERN_INFO "Ignoring shutdown request: %s\n", str); - shutting_down = SHUTDOWN_INVALID; - } - - kfree(str); -} - -static void sysrq_handler(struct xenbus_watch *watch, const char **vec, - unsigned int len) -{ - char sysrq_key = '\0'; - struct xenbus_transaction xbt; - int err; - - again: - err = xenbus_transaction_start(&xbt); - if (err) - return; - if (!xenbus_scanf(xbt, "control", "sysrq", "%c", &sysrq_key)) { - printk(KERN_ERR "Unable to read sysrq code in " - "control/sysrq\n"); - xenbus_transaction_end(xbt, 1); - return; - } - - if (sysrq_key != '\0') - xenbus_printf(xbt, "control", "sysrq", "%c", '\0'); - - err = xenbus_transaction_end(xbt, 0); - if (err == -EAGAIN) - goto again; - - if (sysrq_key != '\0') - handle_sysrq(sysrq_key, NULL); -} - -static struct xenbus_watch shutdown_watch = { - .node = "control/shutdown", - .callback = shutdown_handler -}; - -static struct xenbus_watch sysrq_watch = { - .node = "control/sysrq", - .callback = sysrq_handler -}; - -static int setup_shutdown_watcher(void) -{ - int err; - - err = register_xenbus_watch(&shutdown_watch); - if (err) { - printk(KERN_ERR "Failed to set shutdown watcher\n"); - return err; - } - - err = register_xenbus_watch(&sysrq_watch); - if (err) { - printk(KERN_ERR "Failed to set sysrq watcher\n"); - return err; - } - - return 0; -} - -static int shutdown_event(struct notifier_block *notifier, - unsigned long event, - void *data) -{ - setup_shutdown_watcher(); - return NOTIFY_DONE; -} - -static int __init setup_shutdown_event(void) -{ - static struct notifier_block xenstore_notifier = { - .notifier_call = shutdown_event - }; - register_xenstore_notifier(&xenstore_notifier); - - return 0; -} - -subsys_initcall(setup_shutdown_event); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 3525ef523a74..7c9935858f92 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -56,6 +56,131 @@ #include "multicalls.h" #include "mmu.h" +#define P2M_ENTRIES_PER_PAGE (PAGE_SIZE / sizeof(unsigned long)) +#define TOP_ENTRIES (MAX_DOMAIN_PAGES / P2M_ENTRIES_PER_PAGE) + +/* Placeholder for holes in the address space */ +static unsigned long p2m_missing[P2M_ENTRIES_PER_PAGE] + __attribute__((section(".data.page_aligned"))) = + { [ 0 ... P2M_ENTRIES_PER_PAGE-1 ] = ~0UL }; + + /* Array of pointers to pages containing p2m entries */ +static unsigned long *p2m_top[TOP_ENTRIES] + __attribute__((section(".data.page_aligned"))) = + { [ 0 ... TOP_ENTRIES - 1] = &p2m_missing[0] }; + +/* Arrays of p2m arrays expressed in mfns used for save/restore */ +static unsigned long p2m_top_mfn[TOP_ENTRIES] + __attribute__((section(".bss.page_aligned"))); + +static unsigned long p2m_top_mfn_list[ + PAGE_ALIGN(TOP_ENTRIES / P2M_ENTRIES_PER_PAGE)] + __attribute__((section(".bss.page_aligned"))); + +static inline unsigned p2m_top_index(unsigned long pfn) +{ + BUG_ON(pfn >= MAX_DOMAIN_PAGES); + return pfn / P2M_ENTRIES_PER_PAGE; +} + +static inline unsigned p2m_index(unsigned long pfn) +{ + return pfn % P2M_ENTRIES_PER_PAGE; +} + +/* Build the parallel p2m_top_mfn structures */ +void xen_setup_mfn_list_list(void) +{ + unsigned pfn, idx; + + for(pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_ENTRIES_PER_PAGE) { + unsigned topidx = p2m_top_index(pfn); + + p2m_top_mfn[topidx] = virt_to_mfn(p2m_top[topidx]); + } + + for(idx = 0; idx < ARRAY_SIZE(p2m_top_mfn_list); idx++) { + unsigned topidx = idx * P2M_ENTRIES_PER_PAGE; + p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]); + } + + BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); + + HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = + virt_to_mfn(p2m_top_mfn_list); + HYPERVISOR_shared_info->arch.max_pfn = xen_start_info->nr_pages; +} + +/* Set up p2m_top to point to the domain-builder provided p2m pages */ +void __init xen_build_dynamic_phys_to_machine(void) +{ + unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list; + unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages); + unsigned pfn; + + for(pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) { + unsigned topidx = p2m_top_index(pfn); + + p2m_top[topidx] = &mfn_list[pfn]; + } +} + +unsigned long get_phys_to_machine(unsigned long pfn) +{ + unsigned topidx, idx; + + if (unlikely(pfn >= MAX_DOMAIN_PAGES)) + return INVALID_P2M_ENTRY; + + topidx = p2m_top_index(pfn); + idx = p2m_index(pfn); + return p2m_top[topidx][idx]; +} +EXPORT_SYMBOL_GPL(get_phys_to_machine); + +static void alloc_p2m(unsigned long **pp, unsigned long *mfnp) +{ + unsigned long *p; + unsigned i; + + p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL); + BUG_ON(p == NULL); + + for(i = 0; i < P2M_ENTRIES_PER_PAGE; i++) + p[i] = INVALID_P2M_ENTRY; + + if (cmpxchg(pp, p2m_missing, p) != p2m_missing) + free_page((unsigned long)p); + else + *mfnp = virt_to_mfn(p); +} + +void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + unsigned topidx, idx; + + if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { + BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); + return; + } + + if (unlikely(pfn >= MAX_DOMAIN_PAGES)) { + BUG_ON(mfn != INVALID_P2M_ENTRY); + return; + } + + topidx = p2m_top_index(pfn); + if (p2m_top[topidx] == p2m_missing) { + /* no need to allocate a page to store an invalid entry */ + if (mfn == INVALID_P2M_ENTRY) + return; + alloc_p2m(&p2m_top[topidx], &p2m_top_mfn[topidx]); + } + + idx = p2m_index(pfn); + p2m_top[topidx][idx] = mfn; +} + xmaddr_t arbitrary_virt_to_machine(unsigned long address) { unsigned int level; @@ -98,7 +223,14 @@ void make_lowmem_page_readwrite(void *vaddr) } -void xen_set_pmd(pmd_t *ptr, pmd_t val) +static bool page_pinned(void *ptr) +{ + struct page *page = virt_to_page(ptr); + + return PagePinned(page); +} + +void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val) { struct multicall_space mcs; struct mmu_update *u; @@ -116,6 +248,18 @@ void xen_set_pmd(pmd_t *ptr, pmd_t val) preempt_enable(); } +void xen_set_pmd(pmd_t *ptr, pmd_t val) +{ + /* If page is not pinned, we can just update the entry + directly */ + if (!page_pinned(ptr)) { + *ptr = val; + return; + } + + xen_set_pmd_hyper(ptr, val); +} + /* * Associate a virtual page frame with a given physical page frame * and protection flags for that frame. @@ -222,8 +366,8 @@ pmdval_t xen_pmd_val(pmd_t pmd) ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT; return ret; } -#ifdef CONFIG_X86_PAE -void xen_set_pud(pud_t *ptr, pud_t val) + +void xen_set_pud_hyper(pud_t *ptr, pud_t val) { struct multicall_space mcs; struct mmu_update *u; @@ -241,6 +385,18 @@ void xen_set_pud(pud_t *ptr, pud_t val) preempt_enable(); } +void xen_set_pud(pud_t *ptr, pud_t val) +{ + /* If page is not pinned, we can just update the entry + directly */ + if (!page_pinned(ptr)) { + *ptr = val; + return; + } + + xen_set_pud_hyper(ptr, val); +} + void xen_set_pte(pte_t *ptep, pte_t pte) { ptep->pte_high = pte.pte_high; @@ -262,7 +418,7 @@ void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) void xen_pmd_clear(pmd_t *pmdp) { - xen_set_pmd(pmdp, __pmd(0)); + set_pmd(pmdp, __pmd(0)); } pmd_t xen_make_pmd(pmdval_t pmd) @@ -272,12 +428,6 @@ pmd_t xen_make_pmd(pmdval_t pmd) return native_make_pmd(pmd); } -#else /* !PAE */ -void xen_set_pte(pte_t *ptep, pte_t pte) -{ - *ptep = pte; -} -#endif /* CONFIG_X86_PAE */ /* (Yet another) pagetable walker. This one is intended for pinning a @@ -430,8 +580,6 @@ static int pin_page(struct page *page, enum pt_level level) read-only, and can be pinned. */ void xen_pgd_pin(pgd_t *pgd) { - unsigned level; - xen_mc_batch(); if (pgd_walk(pgd, pin_page, TASK_SIZE)) { @@ -441,15 +589,31 @@ void xen_pgd_pin(pgd_t *pgd) xen_mc_batch(); } -#ifdef CONFIG_X86_PAE - level = MMUEXT_PIN_L3_TABLE; -#else - level = MMUEXT_PIN_L2_TABLE; -#endif + xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd))); + xen_mc_issue(0); +} - xen_do_pin(level, PFN_DOWN(__pa(pgd))); +/* + * On save, we need to pin all pagetables to make sure they get their + * mfns turned into pfns. Search the list for any unpinned pgds and pin + * them (unpinned pgds are not currently in use, probably because the + * process is under construction or destruction). + */ +void xen_mm_pin_all(void) +{ + unsigned long flags; + struct page *page; - xen_mc_issue(0); + spin_lock_irqsave(&pgd_lock, flags); + + list_for_each_entry(page, &pgd_list, lru) { + if (!PagePinned(page)) { + xen_pgd_pin((pgd_t *)page_address(page)); + SetPageSavePinned(page); + } + } + + spin_unlock_irqrestore(&pgd_lock, flags); } /* The init_mm pagetable is really pinned as soon as its created, but @@ -509,6 +673,29 @@ static void xen_pgd_unpin(pgd_t *pgd) xen_mc_issue(0); } +/* + * On resume, undo any pinning done at save, so that the rest of the + * kernel doesn't see any unexpected pinned pagetables. + */ +void xen_mm_unpin_all(void) +{ + unsigned long flags; + struct page *page; + + spin_lock_irqsave(&pgd_lock, flags); + + list_for_each_entry(page, &pgd_list, lru) { + if (PageSavePinned(page)) { + BUG_ON(!PagePinned(page)); + printk("unpinning pinned %p\n", page_address(page)); + xen_pgd_unpin((pgd_t *)page_address(page)); + ClearPageSavePinned(page); + } + } + + spin_unlock_irqrestore(&pgd_lock, flags); +} + void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next) { spin_lock(&next->page_table_lock); @@ -602,7 +789,7 @@ void xen_exit_mmap(struct mm_struct *mm) spin_lock(&mm->page_table_lock); /* pgd may not be pinned in the error exit path of execve */ - if (PagePinned(virt_to_page(mm->pgd))) + if (page_pinned(mm->pgd)) xen_pgd_unpin(mm->pgd); spin_unlock(&mm->page_table_lock); diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index b5e189b1519d..e3dd09e25c63 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -25,10 +25,6 @@ enum pt_level { void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags); -void xen_set_pte(pte_t *ptep, pte_t pteval); -void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pteval); -void xen_set_pmd(pmd_t *pmdp, pmd_t pmdval); void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next); void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm); @@ -37,31 +33,23 @@ void xen_exit_mmap(struct mm_struct *mm); void xen_pgd_pin(pgd_t *pgd); //void xen_pgd_unpin(pgd_t *pgd); -#ifdef CONFIG_X86_PAE -unsigned long long xen_pte_val(pte_t); -unsigned long long xen_pmd_val(pmd_t); -unsigned long long xen_pgd_val(pgd_t); +pteval_t xen_pte_val(pte_t); +pmdval_t xen_pmd_val(pmd_t); +pgdval_t xen_pgd_val(pgd_t); -pte_t xen_make_pte(unsigned long long); -pmd_t xen_make_pmd(unsigned long long); -pgd_t xen_make_pgd(unsigned long long); +pte_t xen_make_pte(pteval_t); +pmd_t xen_make_pmd(pmdval_t); +pgd_t xen_make_pgd(pgdval_t); +void xen_set_pte(pte_t *ptep, pte_t pteval); void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pteval); void xen_set_pte_atomic(pte_t *ptep, pte_t pte); +void xen_set_pmd(pmd_t *pmdp, pmd_t pmdval); void xen_set_pud(pud_t *ptr, pud_t val); +void xen_set_pmd_hyper(pmd_t *pmdp, pmd_t pmdval); +void xen_set_pud_hyper(pud_t *ptr, pud_t val); void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); void xen_pmd_clear(pmd_t *pmdp); - -#else -unsigned long xen_pte_val(pte_t); -unsigned long xen_pmd_val(pmd_t); -unsigned long xen_pgd_val(pgd_t); - -pte_t xen_make_pte(unsigned long); -pmd_t xen_make_pmd(unsigned long); -pgd_t xen_make_pgd(unsigned long); -#endif - #endif /* _XEN_MMU_H */ diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 82517e4a752a..488447878a9d 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -16,6 +16,7 @@ #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> +#include <xen/page.h> #include <xen/interface/callback.h> #include <xen/interface/physdev.h> #include <xen/features.h> @@ -27,8 +28,6 @@ extern const char xen_hypervisor_callback[]; extern const char xen_failsafe_callback[]; -unsigned long *phys_to_machine_mapping; -EXPORT_SYMBOL(phys_to_machine_mapping); /** * machine_specific_memory_setup - Hook for machine specific memory setup. @@ -38,6 +37,8 @@ char * __init xen_memory_setup(void) { unsigned long max_pfn = xen_start_info->nr_pages; + max_pfn = min(MAX_DOMAIN_PAGES, max_pfn); + e820.nr_map = 0; add_memory_region(0, LOWMEMSIZE(), E820_RAM); add_memory_region(HIGH_MEMORY, PFN_PHYS(max_pfn)-HIGH_MEMORY, E820_RAM); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 94e69000f982..d2e3c20127d7 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -35,7 +35,7 @@ #include "xen-ops.h" #include "mmu.h" -static cpumask_t xen_cpu_initialized_map; +cpumask_t xen_cpu_initialized_map; static DEFINE_PER_CPU(int, resched_irq) = -1; static DEFINE_PER_CPU(int, callfunc_irq) = -1; static DEFINE_PER_CPU(int, debug_irq) = -1; @@ -65,6 +65,12 @@ static struct call_data_struct *call_data; */ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id) { +#ifdef CONFIG_X86_32 + __get_cpu_var(irq_stat).irq_resched_count++; +#else + add_pda(irq_resched_count, 1); +#endif + return IRQ_HANDLED; } diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c new file mode 100644 index 000000000000..251669a932d4 --- /dev/null +++ b/arch/x86/xen/suspend.c @@ -0,0 +1,45 @@ +#include <linux/types.h> + +#include <xen/interface/xen.h> +#include <xen/grant_table.h> +#include <xen/events.h> + +#include <asm/xen/hypercall.h> +#include <asm/xen/page.h> + +#include "xen-ops.h" +#include "mmu.h" + +void xen_pre_suspend(void) +{ + xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn); + xen_start_info->console.domU.mfn = + mfn_to_pfn(xen_start_info->console.domU.mfn); + + BUG_ON(!irqs_disabled()); + + HYPERVISOR_shared_info = &xen_dummy_shared_info; + if (HYPERVISOR_update_va_mapping(fix_to_virt(FIX_PARAVIRT_BOOTMAP), + __pte_ma(0), 0)) + BUG(); +} + +void xen_post_suspend(int suspend_cancelled) +{ + xen_setup_shared_info(); + + if (suspend_cancelled) { + xen_start_info->store_mfn = + pfn_to_mfn(xen_start_info->store_mfn); + xen_start_info->console.domU.mfn = + pfn_to_mfn(xen_start_info->console.domU.mfn); + } else { +#ifdef CONFIG_SMP + xen_cpu_initialized_map = cpu_online_map; +#endif + xen_vcpu_restore(); + xen_timer_resume(); + } + +} + diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 52b2e3856980..0da249dbdc49 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -565,6 +565,19 @@ void xen_setup_cpu_clockevents(void) clockevents_register_device(&__get_cpu_var(xen_clock_events)); } +void xen_timer_resume(void) +{ + int cpu; + + if (xen_clockevent != &xen_vcpuop_clockevent) + return; + + for_each_online_cpu(cpu) { + if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL)) + BUG(); + } +} + __init void xen_time_init(void) { int cpu = smp_processor_id(); diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 288d587ce73c..ef6c9e005f90 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -7,6 +7,7 @@ #include <linux/init.h> #include <asm/boot.h> #include <xen/interface/elfnote.h> +#include <asm/xen/interface.h> __INIT ENTRY(startup_xen) @@ -30,11 +31,11 @@ ENTRY(hypercall_page) ELFNOTE(Xen, XEN_ELFNOTE_ENTRY, .long startup_xen) ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .long hypercall_page) ELFNOTE(Xen, XEN_ELFNOTE_FEATURES, .asciz "!writable_page_tables|pae_pgdir_above_4gb") -#ifdef CONFIG_X86_PAE ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE, .asciz "yes") -#else - ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE, .asciz "no") -#endif ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic") + ELFNOTE(Xen, XEN_ELFNOTE_L1_MFN_VALID, + .quad _PAGE_PRESENT; .quad _PAGE_PRESENT) + ELFNOTE(Xen, XEN_ELFNOTE_SUSPEND_CANCEL, .long 1) + ELFNOTE(Xen, XEN_ELFNOTE_HV_START_LOW, .long __HYPERVISOR_VIRT_START) #endif /*CONFIG_XEN */ diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index f1063ae08037..9a055592a307 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -9,18 +9,26 @@ extern const char xen_hypervisor_callback[]; extern const char xen_failsafe_callback[]; +struct trap_info; void xen_copy_trap_info(struct trap_info *traps); DECLARE_PER_CPU(unsigned long, xen_cr3); DECLARE_PER_CPU(unsigned long, xen_current_cr3); extern struct start_info *xen_start_info; +extern struct shared_info xen_dummy_shared_info; extern struct shared_info *HYPERVISOR_shared_info; +void xen_setup_mfn_list_list(void); +void xen_setup_shared_info(void); + char * __init xen_memory_setup(void); void __init xen_arch_setup(void); void __init xen_init_IRQ(void); void xen_enable_sysenter(void); +void xen_vcpu_restore(void); + +void __init xen_build_dynamic_phys_to_machine(void); void xen_setup_timer(int cpu); void xen_setup_cpu_clockevents(void); @@ -29,6 +37,7 @@ void __init xen_time_init(void); unsigned long xen_get_wallclock(void); int xen_set_wallclock(unsigned long time); unsigned long long xen_sched_clock(void); +void xen_timer_resume(void); irqreturn_t xen_debug_interrupt(int irq, void *dev_id); @@ -54,6 +63,8 @@ int xen_smp_call_function_single(int cpu, void (*func) (void *info), void *info, int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info, int wait); +extern cpumask_t xen_cpu_initialized_map; + /* Declare an asm function, along with symbols needed to make it inlineable */ diff --git a/drivers/char/hvc_xen.c b/drivers/char/hvc_xen.c index dd68f8541c2d..db2ae4216279 100644 --- a/drivers/char/hvc_xen.c +++ b/drivers/char/hvc_xen.c @@ -39,9 +39,14 @@ static int xencons_irq; /* ------------------------------------------------------------------ */ +static unsigned long console_pfn = ~0ul; + static inline struct xencons_interface *xencons_interface(void) { - return mfn_to_virt(xen_start_info->console.domU.mfn); + if (console_pfn == ~0ul) + return mfn_to_virt(xen_start_info->console.domU.mfn); + else + return __va(console_pfn << PAGE_SHIFT); } static inline void notify_daemon(void) @@ -101,20 +106,32 @@ static int __init xen_init(void) { struct hvc_struct *hp; - if (!is_running_on_xen()) - return 0; + if (!is_running_on_xen() || + is_initial_xendomain() || + !xen_start_info->console.domU.evtchn) + return -ENODEV; xencons_irq = bind_evtchn_to_irq(xen_start_info->console.domU.evtchn); if (xencons_irq < 0) - xencons_irq = 0 /* NO_IRQ */; + xencons_irq = 0; /* NO_IRQ */ + hp = hvc_alloc(HVC_COOKIE, xencons_irq, &hvc_ops, 256); if (IS_ERR(hp)) return PTR_ERR(hp); hvc = hp; + + console_pfn = mfn_to_pfn(xen_start_info->console.domU.mfn); + return 0; } +void xen_console_resume(void) +{ + if (xencons_irq) + rebind_evtchn_irq(xen_start_info->console.domU.evtchn, xencons_irq); +} + static void __exit xen_fini(void) { if (hvc) @@ -134,12 +151,28 @@ module_init(xen_init); module_exit(xen_fini); console_initcall(xen_cons_init); +static void raw_console_write(const char *str, int len) +{ + while(len > 0) { + int rc = HYPERVISOR_console_io(CONSOLEIO_write, len, (char *)str); + if (rc <= 0) + break; + + str += rc; + len -= rc; + } +} + +#ifdef CONFIG_EARLY_PRINTK static void xenboot_write_console(struct console *console, const char *string, unsigned len) { unsigned int linelen, off = 0; const char *pos; + raw_console_write(string, len); + + write_console(0, "(early) ", 8); while (off < len && NULL != (pos = strchr(string+off, '\n'))) { linelen = pos-string+off; if (off + linelen > len) @@ -155,5 +188,23 @@ static void xenboot_write_console(struct console *console, const char *string, struct console xenboot_console = { .name = "xenboot", .write = xenboot_write_console, - .flags = CON_PRINTBUFFER | CON_BOOT, + .flags = CON_PRINTBUFFER | CON_BOOT | CON_ANYTIME, }; +#endif /* CONFIG_EARLY_PRINTK */ + +void xen_raw_console_write(const char *str) +{ + raw_console_write(str, strlen(str)); +} + +void xen_raw_printk(const char *fmt, ...) +{ + static char buf[512]; + va_list ap; + + va_start(ap, fmt); + vsnprintf(buf, sizeof(buf), fmt, ap); + va_end(ap); + + xen_raw_console_write(buf); +} diff --git a/drivers/input/xen-kbdfront.c b/drivers/input/xen-kbdfront.c index 0f47f4697cdf..9ce3b3baf3a2 100644 --- a/drivers/input/xen-kbdfront.c +++ b/drivers/input/xen-kbdfront.c @@ -66,6 +66,9 @@ static irqreturn_t input_handler(int rq, void *dev_id) case XENKBD_TYPE_MOTION: input_report_rel(dev, REL_X, event->motion.rel_x); input_report_rel(dev, REL_Y, event->motion.rel_y); + if (event->motion.rel_z) + input_report_rel(dev, REL_WHEEL, + -event->motion.rel_z); break; case XENKBD_TYPE_KEY: dev = NULL; @@ -84,6 +87,9 @@ static irqreturn_t input_handler(int rq, void *dev_id) case XENKBD_TYPE_POS: input_report_abs(dev, ABS_X, event->pos.abs_x); input_report_abs(dev, ABS_Y, event->pos.abs_y); + if (event->pos.rel_z) + input_report_rel(dev, REL_WHEEL, + -event->pos.rel_z); break; } if (dev) @@ -152,7 +158,7 @@ static int __devinit xenkbd_probe(struct xenbus_device *dev, ptr->evbit[0] = BIT(EV_KEY) | BIT(EV_REL) | BIT(EV_ABS); for (i = BTN_LEFT; i <= BTN_TASK; i++) set_bit(i, ptr->keybit); - ptr->relbit[0] = BIT(REL_X) | BIT(REL_Y); + ptr->relbit[0] = BIT(REL_X) | BIT(REL_Y) | BIT(REL_WHEEL); input_set_abs_params(ptr, ABS_X, 0, XENFB_WIDTH, 0, 0); input_set_abs_params(ptr, ABS_Y, 0, XENFB_HEIGHT, 0, 0); @@ -294,6 +300,16 @@ InitWait: */ if (dev->state != XenbusStateConnected) goto InitWait; /* no InitWait seen yet, fudge it */ + + /* Set input abs params to match backend screen res */ + if (xenbus_scanf(XBT_NIL, info->xbdev->otherend, + "width", "%d", &val) > 0) + input_set_abs_params(info->ptr, ABS_X, 0, val, 0, 0); + + if (xenbus_scanf(XBT_NIL, info->xbdev->otherend, + "height", "%d", &val) > 0) + input_set_abs_params(info->ptr, ABS_Y, 0, val, 0, 0); + break; case XenbusStateClosing: @@ -337,4 +353,6 @@ static void __exit xenkbd_cleanup(void) module_init(xenkbd_init); module_exit(xenkbd_cleanup); +MODULE_DESCRIPTION("Xen virtual keyboard/pointer device frontend"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("xen:vkbd"); diff --git a/drivers/lguest/lg.h b/drivers/lguest/lg.h index 005bd045d2eb..5faefeaf6790 100644 --- a/drivers/lguest/lg.h +++ b/drivers/lguest/lg.h @@ -136,7 +136,6 @@ int run_guest(struct lg_cpu *cpu, unsigned long __user *user); * first step in the migration to the kernel types. pte_pfn is already defined * in the kernel. */ #define pgd_flags(x) (pgd_val(x) & ~PAGE_MASK) -#define pte_flags(x) (pte_val(x) & ~PAGE_MASK) #define pgd_pfn(x) (pgd_val(x) >> PAGE_SHIFT) /* interrupts_and_traps.c: */ diff --git a/drivers/video/xen-fbfront.c b/drivers/video/xen-fbfront.c index 619a6f8d65a2..47ed39b52f9c 100644 --- a/drivers/video/xen-fbfront.c +++ b/drivers/video/xen-fbfront.c @@ -18,6 +18,7 @@ * frame buffer. */ +#include <linux/console.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/fb.h> @@ -42,37 +43,68 @@ struct xenfb_info { struct xenfb_page *page; unsigned long *mfns; int update_wanted; /* XENFB_TYPE_UPDATE wanted */ + int feature_resize; /* XENFB_TYPE_RESIZE ok */ + struct xenfb_resize resize; /* protected by resize_lock */ + int resize_dpy; /* ditto */ + spinlock_t resize_lock; struct xenbus_device *xbdev; }; -static u32 xenfb_mem_len = XENFB_WIDTH * XENFB_HEIGHT * XENFB_DEPTH / 8; +#define XENFB_DEFAULT_FB_LEN (XENFB_WIDTH * XENFB_HEIGHT * XENFB_DEPTH / 8) +enum { KPARAM_MEM, KPARAM_WIDTH, KPARAM_HEIGHT, KPARAM_CNT }; +static int video[KPARAM_CNT] = { 2, XENFB_WIDTH, XENFB_HEIGHT }; +module_param_array(video, int, NULL, 0); +MODULE_PARM_DESC(video, + "Video memory size in MB, width, height in pixels (default 2,800,600)"); + +static void xenfb_make_preferred_console(void); static int xenfb_remove(struct xenbus_device *); -static void xenfb_init_shared_page(struct xenfb_info *); +static void xenfb_init_shared_page(struct xenfb_info *, struct fb_info *); static int xenfb_connect_backend(struct xenbus_device *, struct xenfb_info *); static void xenfb_disconnect_backend(struct xenfb_info *); +static void xenfb_send_event(struct xenfb_info *info, + union xenfb_out_event *event) +{ + u32 prod; + + prod = info->page->out_prod; + /* caller ensures !xenfb_queue_full() */ + mb(); /* ensure ring space available */ + XENFB_OUT_RING_REF(info->page, prod) = *event; + wmb(); /* ensure ring contents visible */ + info->page->out_prod = prod + 1; + + notify_remote_via_irq(info->irq); +} + static void xenfb_do_update(struct xenfb_info *info, int x, int y, int w, int h) { union xenfb_out_event event; - u32 prod; + memset(&event, 0, sizeof(event)); event.type = XENFB_TYPE_UPDATE; event.update.x = x; event.update.y = y; event.update.width = w; event.update.height = h; - prod = info->page->out_prod; /* caller ensures !xenfb_queue_full() */ - mb(); /* ensure ring space available */ - XENFB_OUT_RING_REF(info->page, prod) = event; - wmb(); /* ensure ring contents visible */ - info->page->out_prod = prod + 1; + xenfb_send_event(info, &event); +} - notify_remote_via_irq(info->irq); +static void xenfb_do_resize(struct xenfb_info *info) +{ + union xenfb_out_event event; + + memset(&event, 0, sizeof(event)); + event.resize = info->resize; + + /* caller ensures !xenfb_queue_full() */ + xenfb_send_event(info, &event); } static int xenfb_queue_full(struct xenfb_info *info) @@ -84,12 +116,28 @@ static int xenfb_queue_full(struct xenfb_info *info) return prod - cons == XENFB_OUT_RING_LEN; } +static void xenfb_handle_resize_dpy(struct xenfb_info *info) +{ + unsigned long flags; + + spin_lock_irqsave(&info->resize_lock, flags); + if (info->resize_dpy) { + if (!xenfb_queue_full(info)) { + info->resize_dpy = 0; + xenfb_do_resize(info); + } + } + spin_unlock_irqrestore(&info->resize_lock, flags); +} + static void xenfb_refresh(struct xenfb_info *info, int x1, int y1, int w, int h) { unsigned long flags; - int y2 = y1 + h - 1; int x2 = x1 + w - 1; + int y2 = y1 + h - 1; + + xenfb_handle_resize_dpy(info); if (!info->update_wanted) return; @@ -222,6 +270,57 @@ static ssize_t xenfb_write(struct fb_info *p, const char __user *buf, return res; } +static int +xenfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) +{ + struct xenfb_info *xenfb_info; + int required_mem_len; + + xenfb_info = info->par; + + if (!xenfb_info->feature_resize) { + if (var->xres == video[KPARAM_WIDTH] && + var->yres == video[KPARAM_HEIGHT] && + var->bits_per_pixel == xenfb_info->page->depth) { + return 0; + } + return -EINVAL; + } + + /* Can't resize past initial width and height */ + if (var->xres > video[KPARAM_WIDTH] || var->yres > video[KPARAM_HEIGHT]) + return -EINVAL; + + required_mem_len = var->xres * var->yres * xenfb_info->page->depth / 8; + if (var->bits_per_pixel == xenfb_info->page->depth && + var->xres <= info->fix.line_length / (XENFB_DEPTH / 8) && + required_mem_len <= info->fix.smem_len) { + var->xres_virtual = var->xres; + var->yres_virtual = var->yres; + return 0; + } + return -EINVAL; +} + +static int xenfb_set_par(struct fb_info *info) +{ + struct xenfb_info *xenfb_info; + unsigned long flags; + + xenfb_info = info->par; + + spin_lock_irqsave(&xenfb_info->resize_lock, flags); + xenfb_info->resize.type = XENFB_TYPE_RESIZE; + xenfb_info->resize.width = info->var.xres; + xenfb_info->resize.height = info->var.yres; + xenfb_info->resize.stride = info->fix.line_length; + xenfb_info->resize.depth = info->var.bits_per_pixel; + xenfb_info->resize.offset = 0; + xenfb_info->resize_dpy = 1; + spin_unlock_irqrestore(&xenfb_info->resize_lock, flags); + return 0; +} + static struct fb_ops xenfb_fb_ops = { .owner = THIS_MODULE, .fb_read = fb_sys_read, @@ -230,6 +329,8 @@ static struct fb_ops xenfb_fb_ops = { .fb_fillrect = xenfb_fillrect, .fb_copyarea = xenfb_copyarea, .fb_imageblit = xenfb_imageblit, + .fb_check_var = xenfb_check_var, + .fb_set_par = xenfb_set_par, }; static irqreturn_t xenfb_event_handler(int rq, void *dev_id) @@ -258,6 +359,8 @@ static int __devinit xenfb_probe(struct xenbus_device *dev, { struct xenfb_info *info; struct fb_info *fb_info; + int fb_size; + int val; int ret; info = kzalloc(sizeof(*info), GFP_KERNEL); @@ -265,18 +368,35 @@ static int __devinit xenfb_probe(struct xenbus_device *dev, xenbus_dev_fatal(dev, -ENOMEM, "allocating info structure"); return -ENOMEM; } + + /* Limit kernel param videoram amount to what is in xenstore */ + if (xenbus_scanf(XBT_NIL, dev->otherend, "videoram", "%d", &val) == 1) { + if (val < video[KPARAM_MEM]) + video[KPARAM_MEM] = val; + } + + /* If requested res does not fit in available memory, use default */ + fb_size = video[KPARAM_MEM] * 1024 * 1024; + if (video[KPARAM_WIDTH] * video[KPARAM_HEIGHT] * XENFB_DEPTH / 8 + > fb_size) { + video[KPARAM_WIDTH] = XENFB_WIDTH; + video[KPARAM_HEIGHT] = XENFB_HEIGHT; + fb_size = XENFB_DEFAULT_FB_LEN; + } + dev->dev.driver_data = info; info->xbdev = dev; info->irq = -1; info->x1 = info->y1 = INT_MAX; spin_lock_init(&info->dirty_lock); + spin_lock_init(&info->resize_lock); - info->fb = vmalloc(xenfb_mem_len); + info->fb = vmalloc(fb_size); if (info->fb == NULL) goto error_nomem; - memset(info->fb, 0, xenfb_mem_len); + memset(info->fb, 0, fb_size); - info->nr_pages = (xenfb_mem_len + PAGE_SIZE - 1) >> PAGE_SHIFT; + info->nr_pages = (fb_size + PAGE_SIZE - 1) >> PAGE_SHIFT; info->mfns = vmalloc(sizeof(unsigned long) * info->nr_pages); if (!info->mfns) @@ -287,8 +407,6 @@ static int __devinit xenfb_probe(struct xenbus_device *dev, if (!info->page) goto error_nomem; - xenfb_init_shared_page(info); - /* abusing framebuffer_alloc() to allocate pseudo_palette */ fb_info = framebuffer_alloc(sizeof(u32) * 256, NULL); if (fb_info == NULL) @@ -301,9 +419,9 @@ static int __devinit xenfb_probe(struct xenbus_device *dev, fb_info->screen_base = info->fb; fb_info->fbops = &xenfb_fb_ops; - fb_info->var.xres_virtual = fb_info->var.xres = info->page->width; - fb_info->var.yres_virtual = fb_info->var.yres = info->page->height; - fb_info->var.bits_per_pixel = info->page->depth; + fb_info->var.xres_virtual = fb_info->var.xres = video[KPARAM_WIDTH]; + fb_info->var.yres_virtual = fb_info->var.yres = video[KPARAM_HEIGHT]; + fb_info->var.bits_per_pixel = XENFB_DEPTH; fb_info->var.red = (struct fb_bitfield){16, 8, 0}; fb_info->var.green = (struct fb_bitfield){8, 8, 0}; @@ -315,9 +433,9 @@ static int __devinit xenfb_probe(struct xenbus_device *dev, fb_info->var.vmode = FB_VMODE_NONINTERLACED; fb_info->fix.visual = FB_VISUAL_TRUECOLOR; - fb_info->fix.line_length = info->page->line_length; + fb_info->fix.line_length = fb_info->var.xres * XENFB_DEPTH / 8; fb_info->fix.smem_start = 0; - fb_info->fix.smem_len = xenfb_mem_len; + fb_info->fix.smem_len = fb_size; strcpy(fb_info->fix.id, "xen"); fb_info->fix.type = FB_TYPE_PACKED_PIXELS; fb_info->fix.accel = FB_ACCEL_NONE; @@ -334,6 +452,8 @@ static int __devinit xenfb_probe(struct xenbus_device *dev, fb_info->fbdefio = &xenfb_defio; fb_deferred_io_init(fb_info); + xenfb_init_shared_page(info, fb_info); + ret = register_framebuffer(fb_info); if (ret) { fb_deferred_io_cleanup(fb_info); @@ -348,6 +468,7 @@ static int __devinit xenfb_probe(struct xenbus_device *dev, if (ret < 0) goto error; + xenfb_make_preferred_console(); return 0; error_nomem: @@ -358,12 +479,34 @@ static int __devinit xenfb_probe(struct xenbus_device *dev, return ret; } +static __devinit void +xenfb_make_preferred_console(void) +{ + struct console *c; + + if (console_set_on_cmdline) + return; + + acquire_console_sem(); + for (c = console_drivers; c; c = c->next) { + if (!strcmp(c->name, "tty") && c->index == 0) + break; + } + release_console_sem(); + if (c) { + unregister_console(c); + c->flags |= CON_CONSDEV; + c->flags &= ~CON_PRINTBUFFER; /* don't print again */ + register_console(c); + } +} + static int xenfb_resume(struct xenbus_device *dev) { struct xenfb_info *info = dev->dev.driver_data; xenfb_disconnect_backend(info); - xenfb_init_shared_page(info); + xenfb_init_shared_page(info, info->fb_info); return xenfb_connect_backend(dev, info); } @@ -391,20 +534,23 @@ static unsigned long vmalloc_to_mfn(void *address) return pfn_to_mfn(vmalloc_to_pfn(address)); } -static void xenfb_init_shared_page(struct xenfb_info *info) +static void xenfb_init_shared_page(struct xenfb_info *info, + struct fb_info *fb_info) { int i; + int epd = PAGE_SIZE / sizeof(info->mfns[0]); for (i = 0; i < info->nr_pages; i++) info->mfns[i] = vmalloc_to_mfn(info->fb + i * PAGE_SIZE); - info->page->pd[0] = vmalloc_to_mfn(info->mfns); - info->page->pd[1] = 0; - info->page->width = XENFB_WIDTH; - info->page->height = XENFB_HEIGHT; - info->page->depth = XENFB_DEPTH; - info->page->line_length = (info->page->depth / 8) * info->page->width; - info->page->mem_length = xenfb_mem_len; + for (i = 0; i * epd < info->nr_pages; i++) + info->page->pd[i] = vmalloc_to_mfn(&info->mfns[i * epd]); + + info->page->width = fb_info->var.xres; + info->page->height = fb_info->var.yres; + info->page->depth = fb_info->var.bits_per_pixel; + info->page->line_length = fb_info->fix.line_length; + info->page->mem_length = fb_info->fix.smem_len; info->page->in_cons = info->page->in_prod = 0; info->page->out_cons = info->page->out_prod = 0; } @@ -504,6 +650,11 @@ InitWait: val = 0; if (val) info->update_wanted = 1; + + if (xenbus_scanf(XBT_NIL, dev->otherend, + "feature-resize", "%d", &val) < 0) + val = 0; + info->feature_resize = val; break; case XenbusStateClosing: @@ -547,4 +698,6 @@ static void __exit xenfb_cleanup(void) module_init(xenfb_init); module_exit(xenfb_cleanup); +MODULE_DESCRIPTION("Xen virtual framebuffer device frontend"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("xen:vfb"); diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 37af04f1ffd9..363286c54290 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -1,4 +1,4 @@ -obj-y += grant-table.o features.o events.o +obj-y += grant-table.o features.o events.o manage.o obj-y += xenbus/ obj-$(CONFIG_XEN_XENCOMM) += xencomm.o obj-$(CONFIG_XEN_BALLOON) += balloon.o diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index ab25ba6cbbb9..591bc29b55f5 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -225,7 +225,7 @@ static int increase_reservation(unsigned long nr_pages) page = balloon_next_page(page); } - reservation.extent_start = (unsigned long)frame_list; + set_xen_guest_handle(reservation.extent_start, frame_list); reservation.nr_extents = nr_pages; rc = HYPERVISOR_memory_op( XENMEM_populate_physmap, &reservation); @@ -321,7 +321,7 @@ static int decrease_reservation(unsigned long nr_pages) balloon_append(pfn_to_page(pfn)); } - reservation.extent_start = (unsigned long)frame_list; + set_xen_guest_handle(reservation.extent_start, frame_list); reservation.nr_extents = nr_pages; ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation); BUG_ON(ret != nr_pages); @@ -368,7 +368,7 @@ static void balloon_process(struct work_struct *work) } /* Resets the Xen limit, sets new target, and kicks off processing. */ -void balloon_set_new_target(unsigned long target) +static void balloon_set_new_target(unsigned long target) { /* No need for lock. Not read-modify-write updates. */ balloon_stats.hard_limit = ~0UL; @@ -483,7 +483,7 @@ static int dealloc_pte_fn( .extent_order = 0, .domid = DOMID_SELF }; - reservation.extent_start = (unsigned long)&mfn; + set_xen_guest_handle(reservation.extent_start, &mfn); set_pte_at(&init_mm, addr, pte, __pte_ma(0ull)); set_phys_to_machine(__pa(addr) >> PAGE_SHIFT, INVALID_P2M_ENTRY); ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation); @@ -519,7 +519,7 @@ static struct page **alloc_empty_pages_and_pagevec(int nr_pages) .extent_order = 0, .domid = DOMID_SELF }; - reservation.extent_start = (unsigned long)&gmfn; + set_xen_guest_handle(reservation.extent_start, &gmfn); ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation); if (ret == 1) diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 4f0f22b020ea..73d78dc9b875 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -355,7 +355,7 @@ static void unbind_from_irq(unsigned int irq) spin_lock(&irq_mapping_update_lock); - if (VALID_EVTCHN(evtchn) && (--irq_bindcount[irq] == 0)) { + if ((--irq_bindcount[irq] == 0) && VALID_EVTCHN(evtchn)) { close.port = evtchn; if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0) BUG(); @@ -375,7 +375,7 @@ static void unbind_from_irq(unsigned int irq) evtchn_to_irq[evtchn] = -1; irq_info[irq] = IRQ_UNBOUND; - dynamic_irq_init(irq); + dynamic_irq_cleanup(irq); } spin_unlock(&irq_mapping_update_lock); @@ -557,6 +557,33 @@ out: put_cpu(); } +/* Rebind a new event channel to an existing irq. */ +void rebind_evtchn_irq(int evtchn, int irq) +{ + /* Make sure the irq is masked, since the new event channel + will also be masked. */ + disable_irq(irq); + + spin_lock(&irq_mapping_update_lock); + + /* After resume the irq<->evtchn mappings are all cleared out */ + BUG_ON(evtchn_to_irq[evtchn] != -1); + /* Expect irq to have been bound before, + so the bindcount should be non-0 */ + BUG_ON(irq_bindcount[irq] == 0); + + evtchn_to_irq[evtchn] = irq; + irq_info[irq] = mk_irq_info(IRQT_EVTCHN, 0, evtchn); + + spin_unlock(&irq_mapping_update_lock); + + /* new event channels are always bound to cpu 0 */ + irq_set_affinity(irq, cpumask_of_cpu(0)); + + /* Unmask the event channel. */ + enable_irq(irq); +} + /* Rebind an evtchn so that it gets delivered to a specific cpu */ static void rebind_irq_to_cpu(unsigned irq, unsigned tcpu) { @@ -647,6 +674,89 @@ static int retrigger_dynirq(unsigned int irq) return ret; } +static void restore_cpu_virqs(unsigned int cpu) +{ + struct evtchn_bind_virq bind_virq; + int virq, irq, evtchn; + + for (virq = 0; virq < NR_VIRQS; virq++) { + if ((irq = per_cpu(virq_to_irq, cpu)[virq]) == -1) + continue; + + BUG_ON(irq_info[irq].type != IRQT_VIRQ); + BUG_ON(irq_info[irq].index != virq); + + /* Get a new binding from Xen. */ + bind_virq.virq = virq; + bind_virq.vcpu = cpu; + if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq, + &bind_virq) != 0) + BUG(); + evtchn = bind_virq.port; + + /* Record the new mapping. */ + evtchn_to_irq[evtchn] = irq; + irq_info[irq] = mk_irq_info(IRQT_VIRQ, virq, evtchn); + bind_evtchn_to_cpu(evtchn, cpu); + + /* Ready for use. */ + unmask_evtchn(evtchn); + } +} + +static void restore_cpu_ipis(unsigned int cpu) +{ + struct evtchn_bind_ipi bind_ipi; + int ipi, irq, evtchn; + + for (ipi = 0; ipi < XEN_NR_IPIS; ipi++) { + if ((irq = per_cpu(ipi_to_irq, cpu)[ipi]) == -1) + continue; + + BUG_ON(irq_info[irq].type != IRQT_IPI); + BUG_ON(irq_info[irq].index != ipi); + + /* Get a new binding from Xen. */ + bind_ipi.vcpu = cpu; + if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_ipi, + &bind_ipi) != 0) + BUG(); + evtchn = bind_ipi.port; + + /* Record the new mapping. */ + evtchn_to_irq[evtchn] = irq; + irq_info[irq] = mk_irq_info(IRQT_IPI, ipi, evtchn); + bind_evtchn_to_cpu(evtchn, cpu); + + /* Ready for use. */ + unmask_evtchn(evtchn); + + } +} + +void xen_irq_resume(void) +{ + unsigned int cpu, irq, evtchn; + + init_evtchn_cpu_bindings(); + + /* New event-channel space is not 'live' yet. */ + for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++) + mask_evtchn(evtchn); + + /* No IRQ <-> event-channel mappings. */ + for (irq = 0; irq < NR_IRQS; irq++) + irq_info[irq].evtchn = 0; /* zap event-channel binding */ + + for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++) + evtchn_to_irq[evtchn] = -1; + + for_each_possible_cpu(cpu) { + restore_cpu_virqs(cpu); + restore_cpu_ipis(cpu); + } +} + static struct irq_chip xen_dynamic_chip __read_mostly = { .name = "xen-dyn", .mask = disable_dynirq, diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 52b6b41b909d..e9e11168616a 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -471,14 +471,14 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx) return 0; } -static int gnttab_resume(void) +int gnttab_resume(void) { if (max_nr_grant_frames() < nr_grant_frames) return -ENOSYS; return gnttab_map(0, nr_grant_frames - 1); } -static int gnttab_suspend(void) +int gnttab_suspend(void) { arch_gnttab_unmap_shared(shared, nr_grant_frames); return 0; diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c new file mode 100644 index 000000000000..5b546e365f00 --- /dev/null +++ b/drivers/xen/manage.c @@ -0,0 +1,252 @@ +/* + * Handle extern requests for shutdown, reboot and sysrq + */ +#include <linux/kernel.h> +#include <linux/err.h> +#include <linux/reboot.h> +#include <linux/sysrq.h> +#include <linux/stop_machine.h> +#include <linux/freezer.h> + +#include <xen/xenbus.h> +#include <xen/grant_table.h> +#include <xen/events.h> +#include <xen/hvc-console.h> +#include <xen/xen-ops.h> + +#include <asm/xen/hypercall.h> +#include <asm/xen/page.h> + +enum shutdown_state { + SHUTDOWN_INVALID = -1, + SHUTDOWN_POWEROFF = 0, + SHUTDOWN_SUSPEND = 2, + /* Code 3 is SHUTDOWN_CRASH, which we don't use because the domain can only + report a crash, not be instructed to crash! + HALT is the same as POWEROFF, as far as we're concerned. The tools use + the distinction when we return the reason code to them. */ + SHUTDOWN_HALT = 4, +}; + +/* Ignore multiple shutdown requests. */ +static enum shutdown_state shutting_down = SHUTDOWN_INVALID; + +#ifdef CONFIG_PM_SLEEP +static int xen_suspend(void *data) +{ + int *cancelled = data; + int err; + + BUG_ON(!irqs_disabled()); + + load_cr3(swapper_pg_dir); + + err = device_power_down(PMSG_SUSPEND); + if (err) { + printk(KERN_ERR "xen_suspend: device_power_down failed: %d\n", + err); + return err; + } + + xen_mm_pin_all(); + gnttab_suspend(); + xen_pre_suspend(); + + /* + * This hypercall returns 1 if suspend was cancelled + * or the domain was merely checkpointed, and 0 if it + * is resuming in a new domain. + */ + *cancelled = HYPERVISOR_suspend(virt_to_mfn(xen_start_info)); + + xen_post_suspend(*cancelled); + gnttab_resume(); + xen_mm_unpin_all(); + + device_power_up(); + + if (!*cancelled) { + xen_irq_resume(); + xen_console_resume(); + } + + return 0; +} + +static void do_suspend(void) +{ + int err; + int cancelled = 1; + + shutting_down = SHUTDOWN_SUSPEND; + +#ifdef CONFIG_PREEMPT + /* If the kernel is preemptible, we need to freeze all the processes + to prevent them from being in the middle of a pagetable update + during suspend. */ + err = freeze_processes(); + if (err) { + printk(KERN_ERR "xen suspend: freeze failed %d\n", err); + return; + } +#endif + + err = device_suspend(PMSG_SUSPEND); + if (err) { + printk(KERN_ERR "xen suspend: device_suspend %d\n", err); + goto out; + } + + printk("suspending xenbus...\n"); + /* XXX use normal device tree? */ + xenbus_suspend(); + + err = stop_machine_run(xen_suspend, &cancelled, 0); + if (err) { + printk(KERN_ERR "failed to start xen_suspend: %d\n", err); + goto out; + } + + if (!cancelled) + xenbus_resume(); + else + xenbus_suspend_cancel(); + + device_resume(); + + /* Make sure timer events get retriggered on all CPUs */ + clock_was_set(); +out: +#ifdef CONFIG_PREEMPT + thaw_processes(); +#endif + shutting_down = SHUTDOWN_INVALID; +} +#endif /* CONFIG_PM_SLEEP */ + +static void shutdown_handler(struct xenbus_watch *watch, + const char **vec, unsigned int len) +{ + char *str; + struct xenbus_transaction xbt; + int err; + + if (shutting_down != SHUTDOWN_INVALID) + return; + + again: + err = xenbus_transaction_start(&xbt); + if (err) + return; + + str = (char *)xenbus_read(xbt, "control", "shutdown", NULL); + /* Ignore read errors and empty reads. */ + if (XENBUS_IS_ERR_READ(str)) { + xenbus_transaction_end(xbt, 1); + return; + } + + xenbus_write(xbt, "control", "shutdown", ""); + + err = xenbus_transaction_end(xbt, 0); + if (err == -EAGAIN) { + kfree(str); + goto again; + } + + if (strcmp(str, "poweroff") == 0 || + strcmp(str, "halt") == 0) { + shutting_down = SHUTDOWN_POWEROFF; + orderly_poweroff(false); + } else if (strcmp(str, "reboot") == 0) { + shutting_down = SHUTDOWN_POWEROFF; /* ? */ + ctrl_alt_del(); +#ifdef CONFIG_PM_SLEEP + } else if (strcmp(str, "suspend") == 0) { + do_suspend(); +#endif + } else { + printk(KERN_INFO "Ignoring shutdown request: %s\n", str); + shutting_down = SHUTDOWN_INVALID; + } + + kfree(str); +} + +static void sysrq_handler(struct xenbus_watch *watch, const char **vec, + unsigned int len) +{ + char sysrq_key = '\0'; + struct xenbus_transaction xbt; + int err; + + again: + err = xenbus_transaction_start(&xbt); + if (err) + return; + if (!xenbus_scanf(xbt, "control", "sysrq", "%c", &sysrq_key)) { + printk(KERN_ERR "Unable to read sysrq code in " + "control/sysrq\n"); + xenbus_transaction_end(xbt, 1); + return; + } + + if (sysrq_key != '\0') + xenbus_printf(xbt, "control", "sysrq", "%c", '\0'); + + err = xenbus_transaction_end(xbt, 0); + if (err == -EAGAIN) + goto again; + + if (sysrq_key != '\0') + handle_sysrq(sysrq_key, NULL); +} + +static struct xenbus_watch shutdown_watch = { + .node = "control/shutdown", + .callback = shutdown_handler +}; + +static struct xenbus_watch sysrq_watch = { + .node = "control/sysrq", + .callback = sysrq_handler +}; + +static int setup_shutdown_watcher(void) +{ + int err; + + err = register_xenbus_watch(&shutdown_watch); + if (err) { + printk(KERN_ERR "Failed to set shutdown watcher\n"); + return err; + } + + err = register_xenbus_watch(&sysrq_watch); + if (err) { + printk(KERN_ERR "Failed to set sysrq watcher\n"); + return err; + } + + return 0; +} + +static int shutdown_event(struct notifier_block *notifier, + unsigned long event, + void *data) +{ + setup_shutdown_watcher(); + return NOTIFY_DONE; +} + +static int __init setup_shutdown_event(void) +{ + static struct notifier_block xenstore_notifier = { + .notifier_call = shutdown_event + }; + register_xenstore_notifier(&xenstore_notifier); + + return 0; +} + +subsys_initcall(setup_shutdown_event); diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c index 6efbe3f29ca5..090c61ee8fd0 100644 --- a/drivers/xen/xenbus/xenbus_comms.c +++ b/drivers/xen/xenbus/xenbus_comms.c @@ -203,7 +203,6 @@ int xb_read(void *data, unsigned len) int xb_init_comms(void) { struct xenstore_domain_interface *intf = xen_store_interface; - int err; if (intf->req_prod != intf->req_cons) printk(KERN_ERR "XENBUS request ring is not quiescent " @@ -216,18 +215,20 @@ int xb_init_comms(void) intf->rsp_cons = intf->rsp_prod; } - if (xenbus_irq) - unbind_from_irqhandler(xenbus_irq, &xb_waitq); + if (xenbus_irq) { + /* Already have an irq; assume we're resuming */ + rebind_evtchn_irq(xen_store_evtchn, xenbus_irq); + } else { + int err; + err = bind_evtchn_to_irqhandler(xen_store_evtchn, wake_waiting, + 0, "xenbus", &xb_waitq); + if (err <= 0) { + printk(KERN_ERR "XENBUS request irq failed %i\n", err); + return err; + } - err = bind_evtchn_to_irqhandler( - xen_store_evtchn, wake_waiting, - 0, "xenbus", &xb_waitq); - if (err <= 0) { - printk(KERN_ERR "XENBUS request irq failed %i\n", err); - return err; + xenbus_irq = err; } - xenbus_irq = err; - return 0; } diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h index dc936dddf161..a1e2b9470f25 100644 --- a/include/asm-x86/page.h +++ b/include/asm-x86/page.h @@ -160,6 +160,7 @@ static inline pteval_t native_pte_val(pte_t pte) #endif #define pte_val(x) native_pte_val(x) +#define pte_flags(x) native_pte_val(x) #define __pte(x) native_make_pte(x) #endif /* CONFIG_PARAVIRT */ diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h index 0f13b945e240..5ea37a48eecb 100644 --- a/include/asm-x86/paravirt.h +++ b/include/asm-x86/paravirt.h @@ -239,6 +239,7 @@ struct pv_mmu_ops { unsigned long addr, pte_t *ptep); pteval_t (*pte_val)(pte_t); + pteval_t (*pte_flags)(pte_t); pte_t (*make_pte)(pteval_t pte); pgdval_t (*pgd_val)(pgd_t); @@ -996,6 +997,20 @@ static inline pteval_t pte_val(pte_t pte) return ret; } +static inline pteval_t pte_flags(pte_t pte) +{ + pteval_t ret; + + if (sizeof(pteval_t) > sizeof(long)) + ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_flags, + pte.pte, (u64)pte.pte >> 32); + else + ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_flags, + pte.pte); + + return ret; +} + static inline pgd_t __pgd(pgdval_t val) { pgdval_t ret; diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h index 97c271b2910b..47a852cb8c92 100644 --- a/include/asm-x86/pgtable.h +++ b/include/asm-x86/pgtable.h @@ -164,37 +164,37 @@ extern struct list_head pgd_list; */ static inline int pte_dirty(pte_t pte) { - return pte_val(pte) & _PAGE_DIRTY; + return pte_flags(pte) & _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { - return pte_val(pte) & _PAGE_ACCESSED; + return pte_flags(pte) & _PAGE_ACCESSED; } static inline int pte_write(pte_t pte) { - return pte_val(pte) & _PAGE_RW; + return pte_flags(pte) & _PAGE_RW; } static inline int pte_file(pte_t pte) { - return pte_val(pte) & _PAGE_FILE; + return pte_flags(pte) & _PAGE_FILE; } static inline int pte_huge(pte_t pte) { - return pte_val(pte) & _PAGE_PSE; + return pte_flags(pte) & _PAGE_PSE; } static inline int pte_global(pte_t pte) { - return pte_val(pte) & _PAGE_GLOBAL; + return pte_flags(pte) & _PAGE_GLOBAL; } static inline int pte_exec(pte_t pte) { - return !(pte_val(pte) & _PAGE_NX); + return !(pte_flags(pte) & _PAGE_NX); } static inline int pte_special(pte_t pte) @@ -305,7 +305,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) return __pgprot(preservebits | addbits); } -#define pte_pgprot(x) __pgprot(pte_val(x) & ~PTE_MASK) +#define pte_pgprot(x) __pgprot(pte_flags(x) & ~PTE_MASK) #define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask) diff --git a/include/asm-x86/xen/hypercall.h b/include/asm-x86/xen/hypercall.h index c2ccd997ed35..2a4f9b41d684 100644 --- a/include/asm-x86/xen/hypercall.h +++ b/include/asm-x86/xen/hypercall.h @@ -176,9 +176,9 @@ HYPERVISOR_fpu_taskswitch(int set) } static inline int -HYPERVISOR_sched_op(int cmd, unsigned long arg) +HYPERVISOR_sched_op(int cmd, void *arg) { - return _hypercall2(int, sched_op, cmd, arg); + return _hypercall2(int, sched_op_new, cmd, arg); } static inline long @@ -315,6 +315,13 @@ HYPERVISOR_nmi_op(unsigned long op, unsigned long arg) } static inline void +MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set) +{ + mcl->op = __HYPERVISOR_fpu_taskswitch; + mcl->args[0] = set; +} + +static inline void MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va, pte_t new_val, unsigned long flags) { diff --git a/include/asm-x86/xen/page.h b/include/asm-x86/xen/page.h index baf3a4dce28c..377c04591c15 100644 --- a/include/asm-x86/xen/page.h +++ b/include/asm-x86/xen/page.h @@ -26,15 +26,20 @@ typedef struct xpaddr { #define FOREIGN_FRAME_BIT (1UL<<31) #define FOREIGN_FRAME(m) ((m) | FOREIGN_FRAME_BIT) -extern unsigned long *phys_to_machine_mapping; +/* Maximum amount of memory we can handle in a domain in pages */ +#define MAX_DOMAIN_PAGES \ + ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE)) + + +extern unsigned long get_phys_to_machine(unsigned long pfn); +extern void set_phys_to_machine(unsigned long pfn, unsigned long mfn); static inline unsigned long pfn_to_mfn(unsigned long pfn) { if (xen_feature(XENFEAT_auto_translated_physmap)) return pfn; - return phys_to_machine_mapping[(unsigned int)(pfn)] & - ~FOREIGN_FRAME_BIT; + return get_phys_to_machine(pfn) & ~FOREIGN_FRAME_BIT; } static inline int phys_to_machine_mapping_valid(unsigned long pfn) @@ -42,7 +47,7 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn) if (xen_feature(XENFEAT_auto_translated_physmap)) return 1; - return (phys_to_machine_mapping[pfn] != INVALID_P2M_ENTRY); + return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY; } static inline unsigned long mfn_to_pfn(unsigned long mfn) @@ -106,20 +111,12 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn) unsigned long pfn = mfn_to_pfn(mfn); if ((pfn < max_mapnr) && !xen_feature(XENFEAT_auto_translated_physmap) - && (phys_to_machine_mapping[pfn] != mfn)) + && (get_phys_to_machine(pfn) != mfn)) return max_mapnr; /* force !pfn_valid() */ + /* XXX fixme; not true with sparsemem */ return pfn; } -static inline void set_phys_to_machine(unsigned long pfn, unsigned long mfn) -{ - if (xen_feature(XENFEAT_auto_translated_physmap)) { - BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); - return; - } - phys_to_machine_mapping[pfn] = mfn; -} - /* VIRT <-> MACHINE conversion */ #define virt_to_machine(v) (phys_to_machine(XPADDR(__pa(v)))) #define virt_to_mfn(v) (pfn_to_mfn(PFN_DOWN(__pa(v)))) @@ -150,13 +147,9 @@ static inline pte_t __pte_ma(pteval_t x) return (pte_t) { .pte = x }; } -#ifdef CONFIG_X86_PAE #define pmd_val_ma(v) ((v).pmd) #define pud_val_ma(v) ((v).pgd.pgd) #define __pmd_ma(x) ((pmd_t) { (x) } ) -#else /* !X86_PAE */ -#define pmd_val_ma(v) ((v).pud.pgd.pgd) -#endif /* CONFIG_X86_PAE */ #define pgd_val_ma(x) ((x).pgd) diff --git a/include/linux/console.h b/include/linux/console.h index a4f27fbdf549..248e6e3b9b73 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -108,6 +108,8 @@ struct console { struct console *next; }; +extern int console_set_on_cmdline; + extern int add_preferred_console(char *name, int idx, char *options); extern int update_console_cmdline(char *name, int idx, char *name_new, int idx_new, char *options); extern void register_console(struct console *); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f31debfac926..0d2a4e7012aa 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -157,6 +157,7 @@ PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active) __PAGEFLAG(Slab, slab) PAGEFLAG(Checked, owner_priv_1) /* Used by some filesystems */ PAGEFLAG(Pinned, owner_priv_1) TESTSCFLAG(Pinned, owner_priv_1) /* Xen */ +PAGEFLAG(SavePinned, dirty); /* Xen */ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private) __SETPAGEFLAG(Private, private) diff --git a/include/xen/events.h b/include/xen/events.h index acd8e062c85f..67c4436554a9 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -32,6 +32,7 @@ void unbind_from_irqhandler(unsigned int irq, void *dev_id); void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector); int resend_irq_on_evtchn(unsigned int irq); +void rebind_evtchn_irq(int evtchn, int irq); static inline void notify_remote_via_evtchn(int port) { @@ -40,4 +41,7 @@ static inline void notify_remote_via_evtchn(int port) } extern void notify_remote_via_irq(int irq); + +extern void xen_irq_resume(void); + #endif /* _XEN_EVENTS_H */ diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 466204846121..a40f1cd91be1 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -51,6 +51,9 @@ struct gnttab_free_callback { u16 count; }; +int gnttab_suspend(void); +int gnttab_resume(void); + int gnttab_grant_foreign_access(domid_t domid, unsigned long frame, int readonly); diff --git a/include/xen/hvc-console.h b/include/xen/hvc-console.h index 21c0ecfd786d..98b79bc404dd 100644 --- a/include/xen/hvc-console.h +++ b/include/xen/hvc-console.h @@ -3,4 +3,13 @@ extern struct console xenboot_console; +#ifdef CONFIG_HVC_XEN +void xen_console_resume(void); +#else +static inline void xen_console_resume(void) { } +#endif + +void xen_raw_console_write(const char *str); +void xen_raw_printk(const char *fmt, ...); + #endif /* XEN_HVC_CONSOLE_H */ diff --git a/include/xen/interface/elfnote.h b/include/xen/interface/elfnote.h index a64d3df5bd95..7a8262c375cc 100644 --- a/include/xen/interface/elfnote.h +++ b/include/xen/interface/elfnote.h @@ -120,6 +120,26 @@ */ #define XEN_ELFNOTE_BSD_SYMTAB 11 +/* + * The lowest address the hypervisor hole can begin at (numeric). + * + * This must not be set higher than HYPERVISOR_VIRT_START. Its presence + * also indicates to the hypervisor that the kernel can deal with the + * hole starting at a higher address. + */ +#define XEN_ELFNOTE_HV_START_LOW 12 + +/* + * List of maddr_t-sized mask/value pairs describing how to recognize + * (non-present) L1 page table entries carrying valid MFNs (numeric). + */ +#define XEN_ELFNOTE_L1_MFN_VALID 13 + +/* + * Whether or not the guest supports cooperative suspend cancellation. + */ +#define XEN_ELFNOTE_SUSPEND_CANCEL 14 + #endif /* __XEN_PUBLIC_ELFNOTE_H__ */ /* diff --git a/include/xen/interface/io/fbif.h b/include/xen/interface/io/fbif.h index 5a934dd7796d..974a51ed9165 100644 --- a/include/xen/interface/io/fbif.h +++ b/include/xen/interface/io/fbif.h @@ -49,11 +49,27 @@ struct xenfb_update { int32_t height; /* rect height */ }; +/* + * Framebuffer resize notification event + * Capable backend sets feature-resize in xenstore. + */ +#define XENFB_TYPE_RESIZE 3 + +struct xenfb_resize { + uint8_t type; /* XENFB_TYPE_RESIZE */ + int32_t width; /* width in pixels */ + int32_t height; /* height in pixels */ + int32_t stride; /* stride in bytes */ + int32_t depth; /* depth in bits */ + int32_t offset; /* start offset within framebuffer */ +}; + #define XENFB_OUT_EVENT_SIZE 40 union xenfb_out_event { uint8_t type; struct xenfb_update update; + struct xenfb_resize resize; char pad[XENFB_OUT_EVENT_SIZE]; }; @@ -105,15 +121,18 @@ struct xenfb_page { * Each directory page holds PAGE_SIZE / sizeof(*pd) * framebuffer pages, and can thus map up to PAGE_SIZE * * PAGE_SIZE / sizeof(*pd) bytes. With PAGE_SIZE == 4096 and - * sizeof(unsigned long) == 4, that's 4 Megs. Two directory - * pages should be enough for a while. + * sizeof(unsigned long) == 4/8, that's 4 Megs 32 bit and 2 + * Megs 64 bit. 256 directories give enough room for a 512 + * Meg framebuffer with a max resolution of 12,800x10,240. + * Should be enough for a while with room leftover for + * expansion. */ - unsigned long pd[2]; + unsigned long pd[256]; }; /* - * Wart: xenkbd needs to know resolution. Put it here until a better - * solution is found, but don't leak it to the backend. + * Wart: xenkbd needs to know default resolution. Put it here until a + * better solution is found, but don't leak it to the backend. */ #ifdef __KERNEL__ #define XENFB_WIDTH 800 diff --git a/include/xen/interface/io/kbdif.h b/include/xen/interface/io/kbdif.h index fb97f4284ffd..8066c7849fbe 100644 --- a/include/xen/interface/io/kbdif.h +++ b/include/xen/interface/io/kbdif.h @@ -49,6 +49,7 @@ struct xenkbd_motion { uint8_t type; /* XENKBD_TYPE_MOTION */ int32_t rel_x; /* relative X motion */ int32_t rel_y; /* relative Y motion */ + int32_t rel_z; /* relative Z motion (wheel) */ }; struct xenkbd_key { @@ -61,6 +62,7 @@ struct xenkbd_position { uint8_t type; /* XENKBD_TYPE_POS */ int32_t abs_x; /* absolute X position (in FB pixels) */ int32_t abs_y; /* absolute Y position (in FB pixels) */ + int32_t rel_z; /* relative Z motion (wheel) */ }; #define XENKBD_IN_EVENT_SIZE 40 diff --git a/include/xen/interface/memory.h b/include/xen/interface/memory.h index da768469aa92..af36ead16817 100644 --- a/include/xen/interface/memory.h +++ b/include/xen/interface/memory.h @@ -29,7 +29,7 @@ struct xen_memory_reservation { * OUT: GMFN bases of extents that were allocated * (NB. This command also updates the mach_to_phys translation table) */ - ulong extent_start; + GUEST_HANDLE(ulong) extent_start; /* Number of extents, and size/alignment of each (2^extent_order pages). */ unsigned long nr_extents; @@ -50,6 +50,7 @@ struct xen_memory_reservation { domid_t domid; }; +DEFINE_GUEST_HANDLE_STRUCT(xen_memory_reservation); /* * Returns the maximum machine frame number of mapped RAM in this system. @@ -85,7 +86,7 @@ struct xen_machphys_mfn_list { * any large discontiguities in the machine address space, 2MB gaps in * the machphys table will be represented by an MFN base of zero. */ - ulong extent_start; + GUEST_HANDLE(ulong) extent_start; /* * Number of extents written to the above array. This will be smaller @@ -93,6 +94,7 @@ struct xen_machphys_mfn_list { */ unsigned int nr_extents; }; +DEFINE_GUEST_HANDLE_STRUCT(xen_machphys_mfn_list); /* * Sets the GPFN at which a particular page appears in the specified guest's @@ -115,6 +117,7 @@ struct xen_add_to_physmap { /* GPFN where the source mapping page should appear. */ unsigned long gpfn; }; +DEFINE_GUEST_HANDLE_STRUCT(xen_add_to_physmap); /* * Translates a list of domain-specific GPFNs into MFNs. Returns a -ve error @@ -129,13 +132,14 @@ struct xen_translate_gpfn_list { unsigned long nr_gpfns; /* List of GPFNs to translate. */ - ulong gpfn_list; + GUEST_HANDLE(ulong) gpfn_list; /* * Output list to contain MFN translations. May be the same as the input * list (in which case each input GPFN is overwritten with the output MFN). */ - ulong mfn_list; + GUEST_HANDLE(ulong) mfn_list; }; +DEFINE_GUEST_HANDLE_STRUCT(xen_translate_gpfn_list); #endif /* __XEN_PUBLIC_MEMORY_H__ */ diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 10ddfe0142d0..a706d6a78960 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -5,4 +5,10 @@ DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu); +void xen_pre_suspend(void); +void xen_post_suspend(int suspend_cancelled); + +void xen_mm_pin_all(void); +void xen_mm_unpin_all(void); + #endif /* INCLUDE_XEN_OPS_H */ diff --git a/kernel/printk.c b/kernel/printk.c index 8fb01c32aa3b..028ed75d4864 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -121,6 +121,8 @@ struct console_cmdline static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES]; static int selected_console = -1; static int preferred_console = -1; +int console_set_on_cmdline; +EXPORT_SYMBOL(console_set_on_cmdline); /* Flag: console code may call schedule() */ static int console_may_schedule; @@ -890,6 +892,7 @@ static int __init console_setup(char *str) *s = 0; __add_preferred_console(buf, idx, options, brl_options); + console_set_on_cmdline = 1; return 1; } __setup("console=", console_setup); |