Subject: xen3 arch-x86_64 From: http://xenbits.xensource.com/linux-2.6.18-xen.hg (tip 728:832aac894efd) Patch-mainline: obsolete Acked-by: jbeulich@novell.com Index: head-2008-11-25/arch/x86/kernel/asm-offsets_64.c =================================================================== --- head-2008-11-25.orig/arch/x86/kernel/asm-offsets_64.c 2008-11-25 12:33:06.000000000 +0100 +++ head-2008-11-25/arch/x86/kernel/asm-offsets_64.c 2008-11-25 12:35:54.000000000 +0100 @@ -122,8 +122,10 @@ int main(void) ENTRY(cr8); BLANK(); #undef ENTRY +#ifndef CONFIG_X86_NO_TSS DEFINE(TSS_ist, offsetof(struct tss_struct, x86_tss.ist)); BLANK(); +#endif DEFINE(crypto_tfm_ctx_offset, offsetof(struct crypto_tfm, __crt_ctx)); BLANK(); DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); Index: head-2008-11-25/arch/x86/kernel/machine_kexec_64.c =================================================================== --- head-2008-11-25.orig/arch/x86/kernel/machine_kexec_64.c 2008-08-18 10:13:08.000000000 +0200 +++ head-2008-11-25/arch/x86/kernel/machine_kexec_64.c 2008-11-25 12:35:54.000000000 +0100 @@ -27,6 +27,119 @@ static u64 kexec_pud1[512] PAGE_ALIGNED; static u64 kexec_pmd1[512] PAGE_ALIGNED; static u64 kexec_pte1[512] PAGE_ALIGNED; +#ifdef CONFIG_XEN + +/* In the case of Xen, override hypervisor functions to be able to create + * a regular identity mapping page table... + */ + +#include +#include + +#define x__pmd(x) ((pmd_t) { (x) } ) +#define x__pud(x) ((pud_t) { (x) } ) +#define x__pgd(x) ((pgd_t) { (x) } ) + +#define x_pmd_val(x) ((x).pmd) +#define x_pud_val(x) ((x).pud) +#define x_pgd_val(x) ((x).pgd) + +static inline void x_set_pmd(pmd_t *dst, pmd_t val) +{ + x_pmd_val(*dst) = x_pmd_val(val); +} + +static inline void x_set_pud(pud_t *dst, pud_t val) +{ + x_pud_val(*dst) = phys_to_machine(x_pud_val(val)); +} + +static inline void x_pud_clear (pud_t *pud) +{ + x_pud_val(*pud) = 0; +} + +static inline void x_set_pgd(pgd_t *dst, pgd_t val) +{ + x_pgd_val(*dst) = phys_to_machine(x_pgd_val(val)); +} + +static inline void x_pgd_clear (pgd_t * pgd) +{ + x_pgd_val(*pgd) = 0; +} + +#define X__PAGE_KERNEL_LARGE_EXEC \ + _PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_PSE +#define X_KERNPG_TABLE _PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY + +#define __ma(x) (pfn_to_mfn(__pa((x)) >> PAGE_SHIFT) << PAGE_SHIFT) + +#if PAGES_NR > KEXEC_XEN_NO_PAGES +#error PAGES_NR is greater than KEXEC_XEN_NO_PAGES - Xen support will break +#endif + +#if PA_CONTROL_PAGE != 0 +#error PA_CONTROL_PAGE is non zero - Xen support will break +#endif + +void machine_kexec_setup_load_arg(xen_kexec_image_t *xki, struct kimage *image) +{ + void *control_page; + void *table_page; + + memset(xki->page_list, 0, sizeof(xki->page_list)); + + control_page = page_address(image->control_code_page) + PAGE_SIZE; + memcpy(control_page, relocate_kernel, PAGE_SIZE); + + table_page = page_address(image->control_code_page); + + xki->page_list[PA_CONTROL_PAGE] = __ma(control_page); + xki->page_list[PA_TABLE_PAGE] = __ma(table_page); + + xki->page_list[PA_PGD] = __ma(kexec_pgd); + xki->page_list[PA_PUD_0] = __ma(kexec_pud0); + xki->page_list[PA_PUD_1] = __ma(kexec_pud1); + xki->page_list[PA_PMD_0] = __ma(kexec_pmd0); + xki->page_list[PA_PMD_1] = __ma(kexec_pmd1); + xki->page_list[PA_PTE_0] = __ma(kexec_pte0); + xki->page_list[PA_PTE_1] = __ma(kexec_pte1); +} + +int __init machine_kexec_setup_resources(struct resource *hypervisor, + struct resource *phys_cpus, + int nr_phys_cpus) +{ + int k; + + /* The per-cpu crash note resources belong to the hypervisor resource */ + for (k = 0; k < nr_phys_cpus; k++) + request_resource(hypervisor, phys_cpus + k); + + return 0; +} + +void machine_kexec_register_resources(struct resource *res) { ; } + +#else /* CONFIG_XEN */ + +#define x__pmd(x) __pmd(x) +#define x__pud(x) __pud(x) +#define x__pgd(x) __pgd(x) + +#define x_set_pmd(x, y) set_pmd(x, y) +#define x_set_pud(x, y) set_pud(x, y) +#define x_set_pgd(x, y) set_pgd(x, y) + +#define x_pud_clear(x) pud_clear(x) +#define x_pgd_clear(x) pgd_clear(x) + +#define X__PAGE_KERNEL_LARGE_EXEC __PAGE_KERNEL_LARGE_EXEC +#define X_KERNPG_TABLE _KERNPG_TABLE + +#endif /* CONFIG_XEN */ + static void init_level2_page(pmd_t *level2p, unsigned long addr) { unsigned long end_addr; @@ -34,7 +147,7 @@ static void init_level2_page(pmd_t *leve addr &= PAGE_MASK; end_addr = addr + PUD_SIZE; while (addr < end_addr) { - set_pmd(level2p++, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC)); + x_set_pmd(level2p++, x__pmd(addr | X__PAGE_KERNEL_LARGE_EXEC)); addr += PMD_SIZE; } } @@ -59,12 +172,12 @@ static int init_level3_page(struct kimag } level2p = (pmd_t *)page_address(page); init_level2_page(level2p, addr); - set_pud(level3p++, __pud(__pa(level2p) | _KERNPG_TABLE)); + x_set_pud(level3p++, x__pud(__pa(level2p) | X_KERNPG_TABLE)); addr += PUD_SIZE; } /* clear the unused entries */ while (addr < end_addr) { - pud_clear(level3p++); + x_pud_clear(level3p++); addr += PUD_SIZE; } out: @@ -95,12 +208,12 @@ static int init_level4_page(struct kimag if (result) { goto out; } - set_pgd(level4p++, __pgd(__pa(level3p) | _KERNPG_TABLE)); + x_set_pgd(level4p++, x__pgd(__pa(level3p) | X_KERNPG_TABLE)); addr += PGDIR_SIZE; } /* clear the unused entries */ while (addr < end_addr) { - pgd_clear(level4p++); + x_pgd_clear(level4p++); addr += PGDIR_SIZE; } out: @@ -111,8 +224,14 @@ out: static int init_pgtable(struct kimage *image, unsigned long start_pgtable) { pgd_t *level4p; + unsigned long x_max_pfn = max_pfn; + +#ifdef CONFIG_XEN + x_max_pfn = HYPERVISOR_memory_op(XENMEM_maximum_ram_page, NULL); +#endif + level4p = (pgd_t *)__va(start_pgtable); - return init_level4_page(image, level4p, 0, max_pfn << PAGE_SHIFT); + return init_level4_page(image, level4p, 0, x_max_pfn << PAGE_SHIFT); } int machine_kexec_prepare(struct kimage *image) @@ -136,6 +255,7 @@ void machine_kexec_cleanup(struct kimage return; } +#ifndef CONFIG_XEN /* * Do not allocate memory (or fail in any way) in machine_kexec(). * We are past the point of no return, committed to rebooting now. @@ -176,6 +296,7 @@ void machine_kexec(struct kimage *image) relocate_kernel((unsigned long)image->head, (unsigned long)page_list, image->start); } +#endif void arch_crash_save_vmcoreinfo(void) { Index: head-2008-11-25/arch/x86/power/cpu_64.c =================================================================== --- head-2008-11-25.orig/arch/x86/power/cpu_64.c 2008-11-25 12:33:06.000000000 +0100 +++ head-2008-11-25/arch/x86/power/cpu_64.c 2008-11-25 12:35:54.000000000 +0100 @@ -135,6 +135,7 @@ void restore_processor_state(void) static void fix_processor_context(void) { +#ifndef CONFIG_X86_NO_TSS int cpu = smp_processor_id(); struct tss_struct *t = &per_cpu(init_tss, cpu); @@ -146,6 +147,7 @@ static void fix_processor_context(void) set_tss_desc(cpu, t); get_cpu_gdt_table(cpu)[GDT_ENTRY_TSS].type = 9; +#endif syscall_init(); /* This sets MSR_*STAR and related */ load_TR_desc(); /* This does ltr */ Index: head-2008-11-25/arch/x86/vdso/Makefile =================================================================== --- head-2008-11-25.orig/arch/x86/vdso/Makefile 2008-11-25 12:33:06.000000000 +0100 +++ head-2008-11-25/arch/x86/vdso/Makefile 2008-11-25 12:35:54.000000000 +0100 @@ -65,6 +65,8 @@ obj-$(VDSO32-y) += vdso32-syms.lds vdso32.so-$(VDSO32-y) += int80 vdso32.so-$(CONFIG_COMPAT) += syscall vdso32.so-$(VDSO32-y) += sysenter +xen-vdso32-$(subst 1,$(CONFIG_COMPAT),$(shell expr $(CONFIG_XEN_COMPAT)0 '<' 0x0302000)) += int80 +vdso32.so-$(CONFIG_XEN) += $(xen-vdso32-y) vdso32-images = $(vdso32.so-y:%=vdso32-%.so)