diff options
Diffstat (limited to 'arch/x86/lguest/boot.c')
| -rw-r--r-- | arch/x86/lguest/boot.c | 129 |
1 files changed, 80 insertions, 49 deletions
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 73b1e1a1f48..aae94132bc2 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -7,8 +7,7 @@ * kernel and insert a module (lg.ko) which allows us to run other Linux * kernels the same way we'd run processes. We call the first kernel the Host, * and the others the Guests. The program which sets up and configures Guests - * (such as the example in Documentation/lguest/lguest.c) is called the - * Launcher. + * (such as the example in tools/lguest/lguest.c) is called the Launcher. * * Secondly, we only run specially modified Guests, not normal kernels: setting * CONFIG_LGUEST_GUEST to "y" compiles this file into the kernel so it knows @@ -56,6 +55,7 @@ #include <linux/lguest_launcher.h> #include <linux/virtio_console.h> #include <linux/pm.h> +#include <linux/export.h> #include <asm/apic.h> #include <asm/lguest.h> #include <asm/paravirt.h> @@ -70,8 +70,10 @@ #include <asm/i387.h> #include <asm/stackprotector.h> #include <asm/reboot.h> /* for struct machine_ops */ +#include <asm/kvm_para.h> -/*G:010 Welcome to the Guest! +/*G:010 + * Welcome to the Guest! * * The Guest in our tale is a simple creature: identical to the Host but * behaving in simplified but equivalent ways. In particular, the Guest is the @@ -190,15 +192,23 @@ static void lazy_hcall4(unsigned long call, #endif /*G:036 - * When lazy mode is turned off reset the per-cpu lazy mode variable and then - * issue the do-nothing hypercall to flush any stored calls. -:*/ + * When lazy mode is turned off, we issue the do-nothing hypercall to + * flush any stored calls, and call the generic helper to reset the + * per-cpu lazy mode variable. + */ static void lguest_leave_lazy_mmu_mode(void) { hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0); paravirt_leave_lazy_mmu(); } +/* + * We also catch the end of context switch; we enter lazy mode for much of + * that too, so again we need to flush here. + * + * (Technically, this is lazy CPU mode, and normally we're in lazy MMU + * mode, but unlike Xen, lguest doesn't care about the difference). + */ static void lguest_end_context_switch(struct task_struct *next) { hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0); @@ -223,13 +233,13 @@ static void lguest_end_context_switch(struct task_struct *next) * flags word contains all kind of stuff, but in practice Linux only cares * about the interrupt flag. Our "save_flags()" just returns that. */ -static unsigned long save_fl(void) +asmlinkage __visible unsigned long lguest_save_fl(void) { return lguest_data.irq_enabled; } /* Interrupts go off... */ -static void irq_disable(void) +asmlinkage __visible void lguest_irq_disable(void) { lguest_data.irq_enabled = 0; } @@ -243,8 +253,8 @@ static void irq_disable(void) * PV_CALLEE_SAVE_REGS_THUNK(), which pushes %eax onto the stack, calls the * C function, then restores it. */ -PV_CALLEE_SAVE_REGS_THUNK(save_fl); -PV_CALLEE_SAVE_REGS_THUNK(irq_disable); +PV_CALLEE_SAVE_REGS_THUNK(lguest_save_fl); +PV_CALLEE_SAVE_REGS_THUNK(lguest_irq_disable); /*:*/ /* These are in i386_head.S */ @@ -391,13 +401,13 @@ static void lguest_load_tr_desc(void) * giant ball of hair. Its entry in the current Intel manual runs to 28 pages. * * This instruction even it has its own Wikipedia entry. The Wikipedia entry - * has been translated into 5 languages. I am not making this up! + * has been translated into 6 languages. I am not making this up! * * We could get funky here and identify ourselves as "GenuineLguest", but * instead we just use the real "cpuid" instruction. Then I pretty much turned * off feature bits until the Guest booted. (Don't say that: you'll damage * lguest sales!) Shut up, inner voice! (Hey, just pointing out that this is - * hardly future proof.) Noone's listening! They don't like you anyway, + * hardly future proof.) No one's listening! They don't like you anyway, * parenthetic weirdo! * * Replacing the cpuid so we can turn features off is great for the kernel, but @@ -446,6 +456,15 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx, *ax &= 0xFFFFF0FF; *ax |= 0x00000500; break; + + /* + * This is used to detect if we're running under KVM. We might be, + * but that's a Host matter, not us. So say we're not. + */ + case KVM_CPUID_SIGNATURE: + *bx = *cx = *dx = 0; + break; + /* * 0x80000000 returns the highest Extended Function, so we futureproof * like we do above by limiting it to known fields. @@ -458,7 +477,7 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx, /* * PAE systems can mark pages as non-executable. Linux calls this the * NX bit. Intel calls it XD (eXecute Disable), AMD EVP (Enhanced - * Virus Protection). We just switch turn if off here, since we don't + * Virus Protection). We just switch it off here, since we don't * support it. */ case 0x80000001: @@ -520,23 +539,26 @@ static unsigned long lguest_read_cr2(void) /* See lguest_set_pte() below. */ static bool cr3_changed = false; +static unsigned long current_cr3; /* * cr3 is the current toplevel pagetable page: the principle is the same as - * cr0. Keep a local copy, and tell the Host when it changes. The only - * difference is that our local copy is in lguest_data because the Host needs - * to set it upon our initial hypercall. + * cr0. Keep a local copy, and tell the Host when it changes. */ static void lguest_write_cr3(unsigned long cr3) { - lguest_data.pgdir = cr3; lazy_hcall1(LHCALL_NEW_PGTABLE, cr3); - cr3_changed = true; + current_cr3 = cr3; + + /* These two page tables are simple, linear, and used during boot */ + if (cr3 != __pa_symbol(swapper_pg_dir) && + cr3 != __pa_symbol(initial_page_table)) + cr3_changed = true; } static unsigned long lguest_read_cr3(void) { - return lguest_data.pgdir; + return current_cr3; } /* cr4 is used to enable and disable PGE, but we don't care. */ @@ -638,7 +660,7 @@ static void lguest_write_cr4(unsigned long val) /* * The Guest calls this after it has set a second-level entry (pte), ie. to map - * a page into a process' address space. Wetell the Host the toplevel and + * a page into a process' address space. We tell the Host the toplevel and * address this corresponds to. The Guest uses one pagetable per process, so * we need to tell the Host which one we're changing (mm->pgd). */ @@ -703,9 +725,9 @@ static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval) * to forget all of them. Fortunately, this is very rare. * * ... except in early boot when the kernel sets up the initial pagetables, - * which makes booting astonishingly slow: 1.83 seconds! So we don't even tell - * the Host anything changed until we've done the first page table switch, - * which brings boot back to 0.25 seconds. + * which makes booting astonishingly slow: 48 seconds! So we don't even tell + * the Host anything changed until we've done the first real page table switch, + * which brings boot back to 4.3 seconds. */ static void lguest_set_pte(pte_t *ptep, pte_t pteval) { @@ -755,7 +777,7 @@ static void lguest_pmd_clear(pmd_t *pmdp) static void lguest_flush_tlb_single(unsigned long addr) { /* Simply set it to zero: if it was not, it will fault back in. */ - lazy_hcall3(LHCALL_SET_PTE, lguest_data.pgdir, addr, 0); + lazy_hcall3(LHCALL_SET_PTE, current_cr3, addr, 0); } /* @@ -821,7 +843,7 @@ static void __init lguest_init_IRQ(void) for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) { /* Some systems map "vectors" to interrupts weirdly. Not us! */ - __get_cpu_var(vector_irq)[i] = i - FIRST_EXTERNAL_VECTOR; + __this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR); if (i != SYSCALL_VECTOR) set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]); } @@ -834,18 +856,23 @@ static void __init lguest_init_IRQ(void) } /* - * With CONFIG_SPARSE_IRQ, interrupt descriptors are allocated as-needed, so - * rather than set them in lguest_init_IRQ we are called here every time an - * lguest device needs an interrupt. - * - * FIXME: irq_alloc_desc_at() can fail due to lack of memory, we should - * pass that up! + * Interrupt descriptors are allocated as-needed, but low-numbered ones are + * reserved by the generic x86 code. So we ignore irq_alloc_desc_at if it + * tells us the irq is already used: other errors (ie. ENOMEM) we take + * seriously. */ -void lguest_setup_irq(unsigned int irq) +int lguest_setup_irq(unsigned int irq) { - irq_alloc_desc_at(irq, 0); - set_irq_chip_and_handler_name(irq, &lguest_irq_controller, + int err; + + /* Returns -ve error or vector number. */ + err = irq_alloc_desc_at(irq, 0); + if (err < 0 && err != -EEXIST) + return err; + + irq_set_chip_and_handler_name(irq, &lguest_irq_controller, handle_level_irq, "level"); + return 0; } /* @@ -854,9 +881,9 @@ void lguest_setup_irq(unsigned int irq) * It would be far better for everyone if the Guest had its own clock, but * until then the Host gives us the time on every interrupt. */ -static unsigned long lguest_get_wallclock(void) +static void lguest_get_wallclock(struct timespec *now) { - return lguest_data.time.tv_sec; + *now = lguest_data.time; } /* @@ -910,8 +937,6 @@ static struct clocksource lguest_clock = { .rating = 200, .read = lguest_clock_read, .mask = CLOCKSOURCE_MASK(64), - .mult = 1 << 22, - .shift = 22, .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; @@ -992,9 +1017,10 @@ static void lguest_time_irq(unsigned int irq, struct irq_desc *desc) static void lguest_time_init(void) { /* Set up the timer interrupt (0) to go to our simple timer routine */ - set_irq_handler(0, lguest_time_irq); + lguest_setup_irq(0); + irq_set_handler(0, lguest_time_irq); - clocksource_register(&lguest_clock); + clocksource_register_hz(&lguest_clock, NSEC_PER_SEC); /* We can't set cpumask in the initializer: damn C limitations! Set it * here and register our timer device. */ @@ -1002,7 +1028,7 @@ static void lguest_time_init(void) clockevents_register_device(&lguest_clockevent); /* Finally, we unblock the timer interrupt. */ - enable_lguest_irq(0); + clear_bit(0, lguest_data.blocked_interrupts); } /* @@ -1030,6 +1056,12 @@ static void lguest_load_sp0(struct tss_struct *tss, } /* Let's just say, I wouldn't do debugging under a Guest. */ +static unsigned long lguest_get_debugreg(int regno) +{ + /* FIXME: Implement */ + return 0; +} + static void lguest_set_debugreg(int regno, unsigned long value) { /* FIXME: Implement */ @@ -1138,7 +1170,7 @@ static struct notifier_block paniced = { static __init char *lguest_memory_setup(void) { /* - *The Linux bootloader header contains an "e820" memory map: the + * The Linux bootloader header contains an "e820" memory map: the * Launcher populated the first entry with our memory limit. */ e820_add_region(boot_params.e820_map[0].addr, @@ -1259,9 +1291,9 @@ __init void lguest_init(void) */ /* Interrupt-related operations */ - pv_irq_ops.save_fl = PV_CALLEE_SAVE(save_fl); + pv_irq_ops.save_fl = PV_CALLEE_SAVE(lguest_save_fl); pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(lg_restore_fl); - pv_irq_ops.irq_disable = PV_CALLEE_SAVE(irq_disable); + pv_irq_ops.irq_disable = PV_CALLEE_SAVE(lguest_irq_disable); pv_irq_ops.irq_enable = __PV_IS_CALLEE_SAVE(lg_irq_enable); pv_irq_ops.safe_halt = lguest_safe_halt; @@ -1277,6 +1309,7 @@ __init void lguest_init(void) pv_cpu_ops.load_tr_desc = lguest_load_tr_desc; pv_cpu_ops.set_ldt = lguest_set_ldt; pv_cpu_ops.load_tls = lguest_load_tls; + pv_cpu_ops.get_debugreg = lguest_get_debugreg; pv_cpu_ops.set_debugreg = lguest_set_debugreg; pv_cpu_ops.clts = lguest_clts; pv_cpu_ops.read_cr0 = lguest_read_cr0; @@ -1307,6 +1340,7 @@ __init void lguest_init(void) pv_mmu_ops.read_cr3 = lguest_read_cr3; pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu; pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode; + pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu; pv_mmu_ops.pte_update = lguest_pte_update; pv_mmu_ops.pte_update_defer = lguest_pte_update; @@ -1349,9 +1383,6 @@ __init void lguest_init(void) */ switch_to_new_gdt(0); - /* We actually boot with all memory mapped, but let's say 128MB. */ - max_pfn_mapped = (128*1024*1024) >> PAGE_SHIFT; - /* * The Host<->Guest Switcher lives at the top of our address space, and * the Host told us how big it is when we made LGUEST_INIT hypercall: @@ -1385,11 +1416,11 @@ __init void lguest_init(void) new_cpu_data.x86_capability[0] = cpuid_edx(1); /* Math is always hard! */ - new_cpu_data.hard_math = 1; + set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU); /* We don't have features. We have puppies! Puppies! */ #ifdef CONFIG_X86_MCE - mce_disabled = 1; + mca_cfg.disabled = true; #endif #ifdef CONFIG_ACPI acpi_disabled = 1; |