From 7733607fb3aa72e3df47e6165156feb92ced8f5f Mon Sep 17 00:00:00 2001 From: Maran Wilson Date: Mon, 10 Dec 2018 11:07:28 -0800 Subject: xen/pvh: Split CONFIG_XEN_PVH into CONFIG_PVH and CONFIG_XEN_PVH In order to pave the way for hypervisors other than Xen to use the PVH entry point for VMs, we need to factor the PVH entry code into Xen specific and hypervisor agnostic components. The first step in doing that, is to create a new config option for PVH entry that can be enabled independently from CONFIG_XEN. Signed-off-by: Maran Wilson Reviewed-by: Juergen Gross Acked-by: Borislav Petkov Signed-off-by: Boris Ostrovsky --- arch/x86/Kconfig | 6 ++++++ arch/x86/kernel/head_64.S | 2 +- arch/x86/xen/Kconfig | 3 ++- 3 files changed, 9 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8689e794a43c..c2a22a74abee 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -796,6 +796,12 @@ config KVM_GUEST underlying device model, the host provides the guest with timing infrastructure such as time of day, and system time +config PVH + bool "Support for running PVH guests" + ---help--- + This option enables the PVH entry point for guest virtual machines + as specified in the x86/HVM direct boot ABI. + config KVM_DEBUG_FS bool "Enable debug information for KVM Guests in debugfs" depends on KVM_GUEST && DEBUG_FS diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 747c758f67b7..d1dbe8e4eb82 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -386,7 +386,7 @@ NEXT_PAGE(early_dynamic_pgts) .data -#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH) +#if defined(CONFIG_XEN_PV) || defined(CONFIG_PVH) NEXT_PGD_PAGE(init_top_pgt) .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .org init_top_pgt + L4_PAGE_OFFSET*8, 0 diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 1ef391aa184d..e07abefd3d26 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -74,6 +74,7 @@ config XEN_DEBUG_FS Enabling this option may incur a significant performance overhead. config XEN_PVH - bool "Support for running as a PVH guest" + bool "Support for running as a Xen PVH guest" depends on XEN && XEN_PVHVM && ACPI + select PVH def_bool n -- cgit v1.2.3 From fcd4747698150bc3a9596481d3eb2b3ae71d82f1 Mon Sep 17 00:00:00 2001 From: Maran Wilson Date: Mon, 10 Dec 2018 11:07:55 -0800 Subject: xen/pvh: Move PVH entry code out of Xen specific tree Once hypervisors other than Xen start using the PVH entry point for starting VMs, we would like the option of being able to compile PVH entry capable kernels without enabling CONFIG_XEN and all the code that comes along with that. To allow that, we are moving the PVH code out of Xen and into files sitting at a higher level in the tree. This patch is not introducing any code or functional changes, just moving files from one location to another. Signed-off-by: Maran Wilson Reviewed-by: Konrad Rzeszutek Wilk Reviewed-by: Juergen Gross Signed-off-by: Boris Ostrovsky --- arch/x86/Kbuild | 2 + arch/x86/platform/pvh/Makefile | 5 ++ arch/x86/platform/pvh/enlighten.c | 108 +++++++++++++++++++++++ arch/x86/platform/pvh/head.S | 177 ++++++++++++++++++++++++++++++++++++++ arch/x86/xen/Makefile | 4 - arch/x86/xen/enlighten_pvh.c | 108 ----------------------- arch/x86/xen/xen-pvh.S | 177 -------------------------------------- 7 files changed, 292 insertions(+), 289 deletions(-) create mode 100644 arch/x86/platform/pvh/Makefile create mode 100644 arch/x86/platform/pvh/enlighten.c create mode 100644 arch/x86/platform/pvh/head.S delete mode 100644 arch/x86/xen/enlighten_pvh.c delete mode 100644 arch/x86/xen/xen-pvh.S (limited to 'arch/x86') diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild index 0038a2d10a7a..2089e4414300 100644 --- a/arch/x86/Kbuild +++ b/arch/x86/Kbuild @@ -7,6 +7,8 @@ obj-$(CONFIG_KVM) += kvm/ # Xen paravirtualization support obj-$(CONFIG_XEN) += xen/ +obj-$(CONFIG_XEN_PVH) += platform/pvh/ + # Hyper-V paravirtualization support obj-$(subst m,y,$(CONFIG_HYPERV)) += hyperv/ diff --git a/arch/x86/platform/pvh/Makefile b/arch/x86/platform/pvh/Makefile new file mode 100644 index 000000000000..9fd25efcd2a3 --- /dev/null +++ b/arch/x86/platform/pvh/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 +OBJECT_FILES_NON_STANDARD_head.o := y + +obj-$(CONFIG_XEN_PVH) += enlighten.o +obj-$(CONFIG_XEN_PVH) += head.o diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c new file mode 100644 index 000000000000..02e3ab7ff242 --- /dev/null +++ b/arch/x86/platform/pvh/enlighten.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 +#include + +#include + +#include +#include +#include +#include + +#include +#include + +#include +#include +#include + +/* + * PVH variables. + * + * xen_pvh pvh_bootparams and pvh_start_info need to live in data segment + * since they are used after startup_{32|64}, which clear .bss, are invoked. + */ +bool xen_pvh __attribute__((section(".data"))) = 0; +struct boot_params pvh_bootparams __attribute__((section(".data"))); +struct hvm_start_info pvh_start_info __attribute__((section(".data"))); + +unsigned int pvh_start_info_sz = sizeof(pvh_start_info); + +static u64 pvh_get_root_pointer(void) +{ + return pvh_start_info.rsdp_paddr; +} + +static void __init init_pvh_bootparams(void) +{ + struct xen_memory_map memmap; + int rc; + + memset(&pvh_bootparams, 0, sizeof(pvh_bootparams)); + + memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_table); + set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_table); + rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap); + if (rc) { + xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc); + BUG(); + } + pvh_bootparams.e820_entries = memmap.nr_entries; + + if (pvh_bootparams.e820_entries < E820_MAX_ENTRIES_ZEROPAGE - 1) { + pvh_bootparams.e820_table[pvh_bootparams.e820_entries].addr = + ISA_START_ADDRESS; + pvh_bootparams.e820_table[pvh_bootparams.e820_entries].size = + ISA_END_ADDRESS - ISA_START_ADDRESS; + pvh_bootparams.e820_table[pvh_bootparams.e820_entries].type = + E820_TYPE_RESERVED; + pvh_bootparams.e820_entries++; + } else + xen_raw_printk("Warning: Can fit ISA range into e820\n"); + + pvh_bootparams.hdr.cmd_line_ptr = + pvh_start_info.cmdline_paddr; + + /* The first module is always ramdisk. */ + if (pvh_start_info.nr_modules) { + struct hvm_modlist_entry *modaddr = + __va(pvh_start_info.modlist_paddr); + pvh_bootparams.hdr.ramdisk_image = modaddr->paddr; + pvh_bootparams.hdr.ramdisk_size = modaddr->size; + } + + /* + * See Documentation/x86/boot.txt. + * + * Version 2.12 supports Xen entry point but we will use default x86/PC + * environment (i.e. hardware_subarch 0). + */ + pvh_bootparams.hdr.version = (2 << 8) | 12; + pvh_bootparams.hdr.type_of_loader = (9 << 4) | 0; /* Xen loader */ + + x86_init.acpi.get_root_pointer = pvh_get_root_pointer; +} + +/* + * This routine (and those that it might call) should not use + * anything that lives in .bss since that segment will be cleared later. + */ +void __init xen_prepare_pvh(void) +{ + u32 msr; + u64 pfn; + + if (pvh_start_info.magic != XEN_HVM_START_MAGIC_VALUE) { + xen_raw_printk("Error: Unexpected magic value (0x%08x)\n", + pvh_start_info.magic); + BUG(); + } + + xen_pvh = 1; + xen_start_flags = pvh_start_info.flags; + + msr = cpuid_ebx(xen_cpuid_base() + 2); + pfn = __pa(hypercall_page); + wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + + init_pvh_bootparams(); +} diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S new file mode 100644 index 000000000000..1f8825bbaffb --- /dev/null +++ b/arch/x86/platform/pvh/head.S @@ -0,0 +1,177 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright C 2016, Oracle and/or its affiliates. All rights reserved. + */ + + .code32 + .text +#define _pa(x) ((x) - __START_KERNEL_map) + +#include +#include +#include +#include +#include +#include +#include +#include +#include + + __HEAD + +/* + * Entry point for PVH guests. + * + * Xen ABI specifies the following register state when we come here: + * + * - `ebx`: contains the physical memory address where the loader has placed + * the boot start info structure. + * - `cr0`: bit 0 (PE) must be set. All the other writeable bits are cleared. + * - `cr4`: all bits are cleared. + * - `cs `: must be a 32-bit read/execute code segment with a base of ‘0’ + * and a limit of ‘0xFFFFFFFF’. The selector value is unspecified. + * - `ds`, `es`: must be a 32-bit read/write data segment with a base of + * ‘0’ and a limit of ‘0xFFFFFFFF’. The selector values are all + * unspecified. + * - `tr`: must be a 32-bit TSS (active) with a base of '0' and a limit + * of '0x67'. + * - `eflags`: bit 17 (VM) must be cleared. Bit 9 (IF) must be cleared. + * Bit 8 (TF) must be cleared. Other bits are all unspecified. + * + * All other processor registers and flag bits are unspecified. The OS is in + * charge of setting up it's own stack, GDT and IDT. + */ + +#define PVH_GDT_ENTRY_CS 1 +#define PVH_GDT_ENTRY_DS 2 +#define PVH_GDT_ENTRY_CANARY 3 +#define PVH_CS_SEL (PVH_GDT_ENTRY_CS * 8) +#define PVH_DS_SEL (PVH_GDT_ENTRY_DS * 8) +#define PVH_CANARY_SEL (PVH_GDT_ENTRY_CANARY * 8) + +ENTRY(pvh_start_xen) + cld + + lgdt (_pa(gdt)) + + mov $PVH_DS_SEL,%eax + mov %eax,%ds + mov %eax,%es + mov %eax,%ss + + /* Stash hvm_start_info. */ + mov $_pa(pvh_start_info), %edi + mov %ebx, %esi + mov _pa(pvh_start_info_sz), %ecx + shr $2,%ecx + rep + movsl + + mov $_pa(early_stack_end), %esp + + /* Enable PAE mode. */ + mov %cr4, %eax + orl $X86_CR4_PAE, %eax + mov %eax, %cr4 + +#ifdef CONFIG_X86_64 + /* Enable Long mode. */ + mov $MSR_EFER, %ecx + rdmsr + btsl $_EFER_LME, %eax + wrmsr + + /* Enable pre-constructed page tables. */ + mov $_pa(init_top_pgt), %eax + mov %eax, %cr3 + mov $(X86_CR0_PG | X86_CR0_PE), %eax + mov %eax, %cr0 + + /* Jump to 64-bit mode. */ + ljmp $PVH_CS_SEL, $_pa(1f) + + /* 64-bit entry point. */ + .code64 +1: + /* Set base address in stack canary descriptor. */ + mov $MSR_GS_BASE,%ecx + mov $_pa(canary), %eax + xor %edx, %edx + wrmsr + + call xen_prepare_pvh + + /* startup_64 expects boot_params in %rsi. */ + mov $_pa(pvh_bootparams), %rsi + mov $_pa(startup_64), %rax + jmp *%rax + +#else /* CONFIG_X86_64 */ + + /* Set base address in stack canary descriptor. */ + movl $_pa(gdt_start),%eax + movl $_pa(canary),%ecx + movw %cx, (PVH_GDT_ENTRY_CANARY * 8) + 2(%eax) + shrl $16, %ecx + movb %cl, (PVH_GDT_ENTRY_CANARY * 8) + 4(%eax) + movb %ch, (PVH_GDT_ENTRY_CANARY * 8) + 7(%eax) + + mov $PVH_CANARY_SEL,%eax + mov %eax,%gs + + call mk_early_pgtbl_32 + + mov $_pa(initial_page_table), %eax + mov %eax, %cr3 + + mov %cr0, %eax + or $(X86_CR0_PG | X86_CR0_PE), %eax + mov %eax, %cr0 + + ljmp $PVH_CS_SEL, $1f +1: + call xen_prepare_pvh + mov $_pa(pvh_bootparams), %esi + + /* startup_32 doesn't expect paging and PAE to be on. */ + ljmp $PVH_CS_SEL, $_pa(2f) +2: + mov %cr0, %eax + and $~X86_CR0_PG, %eax + mov %eax, %cr0 + mov %cr4, %eax + and $~X86_CR4_PAE, %eax + mov %eax, %cr4 + + ljmp $PVH_CS_SEL, $_pa(startup_32) +#endif +END(pvh_start_xen) + + .section ".init.data","aw" + .balign 8 +gdt: + .word gdt_end - gdt_start + .long _pa(gdt_start) + .word 0 +gdt_start: + .quad 0x0000000000000000 /* NULL descriptor */ +#ifdef CONFIG_X86_64 + .quad GDT_ENTRY(0xa09a, 0, 0xfffff) /* PVH_CS_SEL */ +#else + .quad GDT_ENTRY(0xc09a, 0, 0xfffff) /* PVH_CS_SEL */ +#endif + .quad GDT_ENTRY(0xc092, 0, 0xfffff) /* PVH_DS_SEL */ + .quad GDT_ENTRY(0x4090, 0, 0x18) /* PVH_CANARY_SEL */ +gdt_end: + + .balign 16 +canary: + .fill 48, 1, 0 + +early_stack: + .fill BOOT_STACK_SIZE, 1, 0 +early_stack_end: + + ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY, + _ASM_PTR (pvh_start_xen - __START_KERNEL_map)) diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index dd2550d33b38..b239922f6c6c 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 OBJECT_FILES_NON_STANDARD_xen-asm_$(BITS).o := y -OBJECT_FILES_NON_STANDARD_xen-pvh.o := y ifdef CONFIG_FUNCTION_TRACER # Do not profile debug and lowlevel utilities @@ -37,9 +36,6 @@ obj-$(CONFIG_XEN_PV) += multicalls.o obj-$(CONFIG_XEN_PV) += xen-asm.o obj-$(CONFIG_XEN_PV) += xen-asm_$(BITS).o -obj-$(CONFIG_XEN_PVH) += enlighten_pvh.o -obj-$(CONFIG_XEN_PVH) += xen-pvh.o - obj-$(CONFIG_EVENT_TRACING) += trace.o obj-$(CONFIG_SMP) += smp.o diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c deleted file mode 100644 index 02e3ab7ff242..000000000000 --- a/arch/x86/xen/enlighten_pvh.c +++ /dev/null @@ -1,108 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -#include - -#include -#include -#include -#include - -#include -#include - -#include -#include -#include - -/* - * PVH variables. - * - * xen_pvh pvh_bootparams and pvh_start_info need to live in data segment - * since they are used after startup_{32|64}, which clear .bss, are invoked. - */ -bool xen_pvh __attribute__((section(".data"))) = 0; -struct boot_params pvh_bootparams __attribute__((section(".data"))); -struct hvm_start_info pvh_start_info __attribute__((section(".data"))); - -unsigned int pvh_start_info_sz = sizeof(pvh_start_info); - -static u64 pvh_get_root_pointer(void) -{ - return pvh_start_info.rsdp_paddr; -} - -static void __init init_pvh_bootparams(void) -{ - struct xen_memory_map memmap; - int rc; - - memset(&pvh_bootparams, 0, sizeof(pvh_bootparams)); - - memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_table); - set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_table); - rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap); - if (rc) { - xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc); - BUG(); - } - pvh_bootparams.e820_entries = memmap.nr_entries; - - if (pvh_bootparams.e820_entries < E820_MAX_ENTRIES_ZEROPAGE - 1) { - pvh_bootparams.e820_table[pvh_bootparams.e820_entries].addr = - ISA_START_ADDRESS; - pvh_bootparams.e820_table[pvh_bootparams.e820_entries].size = - ISA_END_ADDRESS - ISA_START_ADDRESS; - pvh_bootparams.e820_table[pvh_bootparams.e820_entries].type = - E820_TYPE_RESERVED; - pvh_bootparams.e820_entries++; - } else - xen_raw_printk("Warning: Can fit ISA range into e820\n"); - - pvh_bootparams.hdr.cmd_line_ptr = - pvh_start_info.cmdline_paddr; - - /* The first module is always ramdisk. */ - if (pvh_start_info.nr_modules) { - struct hvm_modlist_entry *modaddr = - __va(pvh_start_info.modlist_paddr); - pvh_bootparams.hdr.ramdisk_image = modaddr->paddr; - pvh_bootparams.hdr.ramdisk_size = modaddr->size; - } - - /* - * See Documentation/x86/boot.txt. - * - * Version 2.12 supports Xen entry point but we will use default x86/PC - * environment (i.e. hardware_subarch 0). - */ - pvh_bootparams.hdr.version = (2 << 8) | 12; - pvh_bootparams.hdr.type_of_loader = (9 << 4) | 0; /* Xen loader */ - - x86_init.acpi.get_root_pointer = pvh_get_root_pointer; -} - -/* - * This routine (and those that it might call) should not use - * anything that lives in .bss since that segment will be cleared later. - */ -void __init xen_prepare_pvh(void) -{ - u32 msr; - u64 pfn; - - if (pvh_start_info.magic != XEN_HVM_START_MAGIC_VALUE) { - xen_raw_printk("Error: Unexpected magic value (0x%08x)\n", - pvh_start_info.magic); - BUG(); - } - - xen_pvh = 1; - xen_start_flags = pvh_start_info.flags; - - msr = cpuid_ebx(xen_cpuid_base() + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - - init_pvh_bootparams(); -} diff --git a/arch/x86/xen/xen-pvh.S b/arch/x86/xen/xen-pvh.S deleted file mode 100644 index 1f8825bbaffb..000000000000 --- a/arch/x86/xen/xen-pvh.S +++ /dev/null @@ -1,177 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* - * Copyright C 2016, Oracle and/or its affiliates. All rights reserved. - */ - - .code32 - .text -#define _pa(x) ((x) - __START_KERNEL_map) - -#include -#include -#include -#include -#include -#include -#include -#include -#include - - __HEAD - -/* - * Entry point for PVH guests. - * - * Xen ABI specifies the following register state when we come here: - * - * - `ebx`: contains the physical memory address where the loader has placed - * the boot start info structure. - * - `cr0`: bit 0 (PE) must be set. All the other writeable bits are cleared. - * - `cr4`: all bits are cleared. - * - `cs `: must be a 32-bit read/execute code segment with a base of ‘0’ - * and a limit of ‘0xFFFFFFFF’. The selector value is unspecified. - * - `ds`, `es`: must be a 32-bit read/write data segment with a base of - * ‘0’ and a limit of ‘0xFFFFFFFF’. The selector values are all - * unspecified. - * - `tr`: must be a 32-bit TSS (active) with a base of '0' and a limit - * of '0x67'. - * - `eflags`: bit 17 (VM) must be cleared. Bit 9 (IF) must be cleared. - * Bit 8 (TF) must be cleared. Other bits are all unspecified. - * - * All other processor registers and flag bits are unspecified. The OS is in - * charge of setting up it's own stack, GDT and IDT. - */ - -#define PVH_GDT_ENTRY_CS 1 -#define PVH_GDT_ENTRY_DS 2 -#define PVH_GDT_ENTRY_CANARY 3 -#define PVH_CS_SEL (PVH_GDT_ENTRY_CS * 8) -#define PVH_DS_SEL (PVH_GDT_ENTRY_DS * 8) -#define PVH_CANARY_SEL (PVH_GDT_ENTRY_CANARY * 8) - -ENTRY(pvh_start_xen) - cld - - lgdt (_pa(gdt)) - - mov $PVH_DS_SEL,%eax - mov %eax,%ds - mov %eax,%es - mov %eax,%ss - - /* Stash hvm_start_info. */ - mov $_pa(pvh_start_info), %edi - mov %ebx, %esi - mov _pa(pvh_start_info_sz), %ecx - shr $2,%ecx - rep - movsl - - mov $_pa(early_stack_end), %esp - - /* Enable PAE mode. */ - mov %cr4, %eax - orl $X86_CR4_PAE, %eax - mov %eax, %cr4 - -#ifdef CONFIG_X86_64 - /* Enable Long mode. */ - mov $MSR_EFER, %ecx - rdmsr - btsl $_EFER_LME, %eax - wrmsr - - /* Enable pre-constructed page tables. */ - mov $_pa(init_top_pgt), %eax - mov %eax, %cr3 - mov $(X86_CR0_PG | X86_CR0_PE), %eax - mov %eax, %cr0 - - /* Jump to 64-bit mode. */ - ljmp $PVH_CS_SEL, $_pa(1f) - - /* 64-bit entry point. */ - .code64 -1: - /* Set base address in stack canary descriptor. */ - mov $MSR_GS_BASE,%ecx - mov $_pa(canary), %eax - xor %edx, %edx - wrmsr - - call xen_prepare_pvh - - /* startup_64 expects boot_params in %rsi. */ - mov $_pa(pvh_bootparams), %rsi - mov $_pa(startup_64), %rax - jmp *%rax - -#else /* CONFIG_X86_64 */ - - /* Set base address in stack canary descriptor. */ - movl $_pa(gdt_start),%eax - movl $_pa(canary),%ecx - movw %cx, (PVH_GDT_ENTRY_CANARY * 8) + 2(%eax) - shrl $16, %ecx - movb %cl, (PVH_GDT_ENTRY_CANARY * 8) + 4(%eax) - movb %ch, (PVH_GDT_ENTRY_CANARY * 8) + 7(%eax) - - mov $PVH_CANARY_SEL,%eax - mov %eax,%gs - - call mk_early_pgtbl_32 - - mov $_pa(initial_page_table), %eax - mov %eax, %cr3 - - mov %cr0, %eax - or $(X86_CR0_PG | X86_CR0_PE), %eax - mov %eax, %cr0 - - ljmp $PVH_CS_SEL, $1f -1: - call xen_prepare_pvh - mov $_pa(pvh_bootparams), %esi - - /* startup_32 doesn't expect paging and PAE to be on. */ - ljmp $PVH_CS_SEL, $_pa(2f) -2: - mov %cr0, %eax - and $~X86_CR0_PG, %eax - mov %eax, %cr0 - mov %cr4, %eax - and $~X86_CR4_PAE, %eax - mov %eax, %cr4 - - ljmp $PVH_CS_SEL, $_pa(startup_32) -#endif -END(pvh_start_xen) - - .section ".init.data","aw" - .balign 8 -gdt: - .word gdt_end - gdt_start - .long _pa(gdt_start) - .word 0 -gdt_start: - .quad 0x0000000000000000 /* NULL descriptor */ -#ifdef CONFIG_X86_64 - .quad GDT_ENTRY(0xa09a, 0, 0xfffff) /* PVH_CS_SEL */ -#else - .quad GDT_ENTRY(0xc09a, 0, 0xfffff) /* PVH_CS_SEL */ -#endif - .quad GDT_ENTRY(0xc092, 0, 0xfffff) /* PVH_DS_SEL */ - .quad GDT_ENTRY(0x4090, 0, 0x18) /* PVH_CANARY_SEL */ -gdt_end: - - .balign 16 -canary: - .fill 48, 1, 0 - -early_stack: - .fill BOOT_STACK_SIZE, 1, 0 -early_stack_end: - - ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY, - _ASM_PTR (pvh_start_xen - __START_KERNEL_map)) -- cgit v1.2.3 From 4df7363e52105bf7a8589efb2959c907872644fb Mon Sep 17 00:00:00 2001 From: Maran Wilson Date: Mon, 10 Dec 2018 11:08:44 -0800 Subject: xen/pvh: Create a new file for Xen specific PVH code We need to refactor PVH entry code so that support for other hypervisors like Qemu/KVM can be added more easily. The first step in that direction is to create a new file that will eventually hold the Xen specific routines. Signed-off-by: Maran Wilson Reviewed-by: Juergen Gross Signed-off-by: Boris Ostrovsky --- arch/x86/platform/pvh/enlighten.c | 5 ++--- arch/x86/xen/Makefile | 2 ++ arch/x86/xen/enlighten_pvh.c | 10 ++++++++++ 3 files changed, 14 insertions(+), 3 deletions(-) create mode 100644 arch/x86/xen/enlighten_pvh.c (limited to 'arch/x86') diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 02e3ab7ff242..491932991202 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -18,10 +18,9 @@ /* * PVH variables. * - * xen_pvh pvh_bootparams and pvh_start_info need to live in data segment - * since they are used after startup_{32|64}, which clear .bss, are invoked. + * pvh_bootparams and pvh_start_info need to live in the data segment since + * they are used after startup_{32|64}, which clear .bss, are invoked. */ -bool xen_pvh __attribute__((section(".data"))) = 0; struct boot_params pvh_bootparams __attribute__((section(".data"))); struct hvm_start_info pvh_start_info __attribute__((section(".data"))); diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index b239922f6c6c..084de77a109e 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -36,6 +36,8 @@ obj-$(CONFIG_XEN_PV) += multicalls.o obj-$(CONFIG_XEN_PV) += xen-asm.o obj-$(CONFIG_XEN_PV) += xen-asm_$(BITS).o +obj-$(CONFIG_XEN_PVH) += enlighten_pvh.o + obj-$(CONFIG_EVENT_TRACING) += trace.o obj-$(CONFIG_SMP) += smp.o diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c new file mode 100644 index 000000000000..6be7bc719b38 --- /dev/null +++ b/arch/x86/xen/enlighten_pvh.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 +#include + +/* + * PVH variables. + * + * The variable xen_pvh needs to live in the data segment since it is used + * after startup_{32|64} is invoked, which will clear the .bss segment. + */ +bool xen_pvh __attribute__((section(".data"))) = 0; -- cgit v1.2.3 From 8cee3974b35bfb235d4637e10de5c5b364a9057e Mon Sep 17 00:00:00 2001 From: Maran Wilson Date: Mon, 10 Dec 2018 11:08:45 -0800 Subject: xen/pvh: Move Xen specific PVH VM initialization out of common file We need to refactor PVH entry code so that support for other hypervisors like Qemu/KVM can be added more easily. This patch moves the small block of code used for initializing Xen PVH virtual machines into the Xen specific file. This initialization is not going to be needed for Qemu/KVM guests. Moving it out of the common file is going to allow us to compile kernels in the future without CONFIG_XEN that are still capable of being booted as a Qemu/KVM guest via the PVH entry point. Signed-off-by: Maran Wilson Reviewed-by: Konrad Rzeszutek Wilk Reviewed-by: Juergen Gross Signed-off-by: Boris Ostrovsky --- arch/x86/platform/pvh/enlighten.c | 29 ++++++++++++++++++++--------- arch/x86/xen/enlighten_pvh.c | 22 +++++++++++++++++++++- 2 files changed, 41 insertions(+), 10 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 491932991202..637bd74ba32d 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -81,27 +81,38 @@ static void __init init_pvh_bootparams(void) x86_init.acpi.get_root_pointer = pvh_get_root_pointer; } +/* + * If we are trying to boot a Xen PVH guest, it is expected that the kernel + * will have been configured to provide the required override for this routine. + */ +void __init __weak xen_pvh_init(void) +{ + xen_raw_printk("Error: Missing xen PVH initialization\n"); + BUG(); +} + +/* + * When we add support for other hypervisors like Qemu/KVM, this routine can + * selectively invoke the appropriate initialization based on guest type. + */ +static void hypervisor_specific_init(void) +{ + xen_pvh_init(); +} + /* * This routine (and those that it might call) should not use * anything that lives in .bss since that segment will be cleared later. */ void __init xen_prepare_pvh(void) { - u32 msr; - u64 pfn; - if (pvh_start_info.magic != XEN_HVM_START_MAGIC_VALUE) { xen_raw_printk("Error: Unexpected magic value (0x%08x)\n", pvh_start_info.magic); BUG(); } - xen_pvh = 1; - xen_start_flags = pvh_start_info.flags; - - msr = cpuid_ebx(xen_cpuid_base() + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + hypervisor_specific_init(); init_pvh_bootparams(); } diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index 6be7bc719b38..41a7d6ad74e0 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -1,5 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 -#include +#include + +#include +#include + +#include +#include +#include /* * PVH variables. @@ -8,3 +15,16 @@ * after startup_{32|64} is invoked, which will clear the .bss segment. */ bool xen_pvh __attribute__((section(".data"))) = 0; + +void __init xen_pvh_init(void) +{ + u32 msr; + u64 pfn; + + xen_pvh = 1; + xen_start_flags = pvh_start_info.flags; + + msr = cpuid_ebx(xen_cpuid_base() + 2); + pfn = __pa(hypercall_page); + wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); +} -- cgit v1.2.3 From a43fb7da53007e67ad593e179f01a1925b04f586 Mon Sep 17 00:00:00 2001 From: Maran Wilson Date: Mon, 10 Dec 2018 11:08:46 -0800 Subject: xen/pvh: Move Xen code for getting mem map via hcall out of common file We need to refactor PVH entry code so that support for other hypervisors like Qemu/KVM can be added more easily. The original design for PVH entry in Xen guests relies on being able to obtain the memory map from the hypervisor using a hypercall. When we extend the PVH entry ABI to support other hypervisors like Qemu/KVM, a new mechanism will be added that allows the guest to get the memory map without needing to use hypercalls. For Xen guests, the hypercall approach will still be supported. In preparation for adding support for other hypervisors, we can move the code that uses hypercalls into the Xen specific file. This will allow us to compile kernels in the future without CONFIG_XEN that are still capable of being booted as a Qemu/KVM guest via the PVH entry point. Signed-off-by: Maran Wilson Reviewed-by: Juergen Gross Signed-off-by: Boris Ostrovsky --- arch/x86/platform/pvh/enlighten.c | 29 ++++++++++++++--------------- arch/x86/xen/enlighten_pvh.c | 20 ++++++++++++++++++++ 2 files changed, 34 insertions(+), 15 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 637bd74ba32d..8040b3fbf545 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -8,11 +8,7 @@ #include #include -#include -#include - #include -#include #include /* @@ -31,21 +27,24 @@ static u64 pvh_get_root_pointer(void) return pvh_start_info.rsdp_paddr; } -static void __init init_pvh_bootparams(void) +/* + * Xen guests are able to obtain the memory map from the hypervisor via the + * HYPERVISOR_memory_op hypercall. + * If we are trying to boot a Xen PVH guest, it is expected that the kernel + * will have been configured to provide an override for this routine to do + * just that. + */ +void __init __weak mem_map_via_hcall(struct boot_params *ptr __maybe_unused) { - struct xen_memory_map memmap; - int rc; + xen_raw_printk("Error: Could not find memory map\n"); + BUG(); +} +static void __init init_pvh_bootparams(void) +{ memset(&pvh_bootparams, 0, sizeof(pvh_bootparams)); - memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_table); - set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_table); - rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap); - if (rc) { - xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc); - BUG(); - } - pvh_bootparams.e820_entries = memmap.nr_entries; + mem_map_via_hcall(&pvh_bootparams); if (pvh_bootparams.e820_entries < E820_MAX_ENTRIES_ZEROPAGE - 1) { pvh_bootparams.e820_table[pvh_bootparams.e820_entries].addr = diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index 41a7d6ad74e0..35b7599d2d0b 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -1,13 +1,18 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include + #include #include +#include #include #include #include +#include + /* * PVH variables. * @@ -28,3 +33,18 @@ void __init xen_pvh_init(void) pfn = __pa(hypercall_page); wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); } + +void __init mem_map_via_hcall(struct boot_params *boot_params_p) +{ + struct xen_memory_map memmap; + int rc; + + memmap.nr_entries = ARRAY_SIZE(boot_params_p->e820_table); + set_xen_guest_handle(memmap.buffer, boot_params_p->e820_table); + rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap); + if (rc) { + xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc); + BUG(); + } + boot_params_p->e820_entries = memmap.nr_entries; +} -- cgit v1.2.3 From 716ff017a39e552f47de7667ba934d0547ba7535 Mon Sep 17 00:00:00 2001 From: Maran Wilson Date: Mon, 10 Dec 2018 11:09:35 -0800 Subject: KVM: x86: Allow Qemu/KVM to use PVH entry point For certain applications it is desirable to rapidly boot a KVM virtual machine. In cases where legacy hardware and software support within the guest is not needed, Qemu should be able to boot directly into the uncompressed Linux kernel binary without the need to run firmware. There already exists an ABI to allow this for Xen PVH guests and the ABI is supported by Linux and FreeBSD: https://xenbits.xen.org/docs/unstable/misc/pvh.html This patch enables Qemu to use that same entry point for booting KVM guests. Signed-off-by: Maran Wilson Suggested-by: Konrad Rzeszutek Wilk Suggested-by: Boris Ostrovsky Tested-by: Boris Ostrovsky Reviewed-by: Juergen Gross Signed-off-by: Boris Ostrovsky --- arch/x86/Kbuild | 2 +- arch/x86/platform/pvh/Makefile | 4 ++-- arch/x86/platform/pvh/enlighten.c | 42 +++++++++++++++++++++++++++++---------- 3 files changed, 34 insertions(+), 14 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild index 2089e4414300..c625f57472f7 100644 --- a/arch/x86/Kbuild +++ b/arch/x86/Kbuild @@ -7,7 +7,7 @@ obj-$(CONFIG_KVM) += kvm/ # Xen paravirtualization support obj-$(CONFIG_XEN) += xen/ -obj-$(CONFIG_XEN_PVH) += platform/pvh/ +obj-$(CONFIG_PVH) += platform/pvh/ # Hyper-V paravirtualization support obj-$(subst m,y,$(CONFIG_HYPERV)) += hyperv/ diff --git a/arch/x86/platform/pvh/Makefile b/arch/x86/platform/pvh/Makefile index 9fd25efcd2a3..5dec5067c9fb 100644 --- a/arch/x86/platform/pvh/Makefile +++ b/arch/x86/platform/pvh/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 OBJECT_FILES_NON_STANDARD_head.o := y -obj-$(CONFIG_XEN_PVH) += enlighten.o -obj-$(CONFIG_XEN_PVH) += head.o +obj-$(CONFIG_PVH) += enlighten.o +obj-$(CONFIG_PVH) += head.o diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 8040b3fbf545..62f5c7045944 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -8,6 +8,8 @@ #include #include +#include + #include #include @@ -40,11 +42,28 @@ void __init __weak mem_map_via_hcall(struct boot_params *ptr __maybe_unused) BUG(); } -static void __init init_pvh_bootparams(void) +static void __init init_pvh_bootparams(bool xen_guest) { memset(&pvh_bootparams, 0, sizeof(pvh_bootparams)); - mem_map_via_hcall(&pvh_bootparams); + if ((pvh_start_info.version > 0) && (pvh_start_info.memmap_entries)) { + struct hvm_memmap_table_entry *ep; + int i; + + ep = __va(pvh_start_info.memmap_paddr); + pvh_bootparams.e820_entries = pvh_start_info.memmap_entries; + + for (i = 0; i < pvh_bootparams.e820_entries ; i++, ep++) { + pvh_bootparams.e820_table[i].addr = ep->addr; + pvh_bootparams.e820_table[i].size = ep->size; + pvh_bootparams.e820_table[i].type = ep->type; + } + } else if (xen_guest) { + mem_map_via_hcall(&pvh_bootparams); + } else { + /* Non-xen guests are not supported by version 0 */ + BUG(); + } if (pvh_bootparams.e820_entries < E820_MAX_ENTRIES_ZEROPAGE - 1) { pvh_bootparams.e820_table[pvh_bootparams.e820_entries].addr = @@ -75,7 +94,7 @@ static void __init init_pvh_bootparams(void) * environment (i.e. hardware_subarch 0). */ pvh_bootparams.hdr.version = (2 << 8) | 12; - pvh_bootparams.hdr.type_of_loader = (9 << 4) | 0; /* Xen loader */ + pvh_bootparams.hdr.type_of_loader = ((xen_guest ? 0x9 : 0xb) << 4) | 0; x86_init.acpi.get_root_pointer = pvh_get_root_pointer; } @@ -90,13 +109,10 @@ void __init __weak xen_pvh_init(void) BUG(); } -/* - * When we add support for other hypervisors like Qemu/KVM, this routine can - * selectively invoke the appropriate initialization based on guest type. - */ -static void hypervisor_specific_init(void) +static void hypervisor_specific_init(bool xen_guest) { - xen_pvh_init(); + if (xen_guest) + xen_pvh_init(); } /* @@ -105,13 +121,17 @@ static void hypervisor_specific_init(void) */ void __init xen_prepare_pvh(void) { + + u32 msr = xen_cpuid_base(); + bool xen_guest = !!msr; + if (pvh_start_info.magic != XEN_HVM_START_MAGIC_VALUE) { xen_raw_printk("Error: Unexpected magic value (0x%08x)\n", pvh_start_info.magic); BUG(); } - hypervisor_specific_init(); + hypervisor_specific_init(xen_guest); - init_pvh_bootparams(); + init_pvh_bootparams(xen_guest); } -- cgit v1.2.3 From bf9445a33ae6ac2f0822d2f1ce1365408387d568 Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Mon, 10 Dec 2018 16:12:57 +0100 Subject: kprobes/x86/xen: blacklist non-attachable xen interrupt functions Blacklist symbols in Xen probe-prohibited areas, so that user can see these prohibited symbols in debugfs. See also: a50480cb6d61. Signed-off-by: Andrea Righi Acked-by: Masami Hiramatsu Signed-off-by: Boris Ostrovsky --- arch/x86/xen/xen-asm_64.S | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index bb1c2da0381d..1e9ef0ba30a5 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -12,6 +12,7 @@ #include #include #include +#include #include @@ -24,6 +25,7 @@ ENTRY(xen_\name) pop %r11 jmp \name END(xen_\name) +_ASM_NOKPROBE(xen_\name) .endm xen_pv_trap divide_error -- cgit v1.2.3