Resguardo inicial

linux-7.2.3/arch/x86/platform/pvh/Makefile

@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+OBJECT_FILES_NON_STANDARD_head.o := y
+KASAN_SANITIZE := n
+
+obj-$(CONFIG_PVH) += enlighten.o
+obj-$(CONFIG_PVH) += head.o

linux-7.2.3/arch/x86/platform/pvh/enlighten.c

@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/acpi.h>
+
+#include <xen/hvc-console.h>
+
+#include <asm/bootparam.h>
+#include <asm/io_apic.h>
+#include <asm/hypervisor.h>
+#include <asm/e820/api.h>
+#include <asm/x86_init.h>
+
+#include <asm/xen/interface.h>
+
+#include <xen/xen.h>
+#include <xen/interface/hvm/start_info.h>
+
+/*
+ * PVH variables.
+ *
+ * pvh_bootparams and pvh_start_info need to live in a data segment since
+ * they are used after startup_{32|64}, which clear .bss, are invoked.
+ */
+struct boot_params __initdata pvh_bootparams;
+struct hvm_start_info __initdata pvh_start_info;
+
+const unsigned int __initconst pvh_start_info_sz = sizeof(pvh_start_info);
+
+/*
+ * 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)
+{
+	xen_raw_printk("Error: Could not find memory map\n");
+	BUG();
+}
+
+static void __init init_pvh_bootparams(bool xen_guest)
+{
+	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 =
+			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/arch/x86/boot.rst.
+	 *
+	 * 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 = ((xen_guest ? 0x9 : 0xb) << 4) | 0;
+
+	pvh_bootparams.acpi_rsdp_addr = pvh_start_info.rsdp_paddr;
+}
+
+/*
+ * 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(struct boot_params *boot_params)
+{
+	xen_raw_printk("Error: Missing xen PVH initialization\n");
+	BUG();
+}
+
+static void __init hypervisor_specific_init(bool xen_guest)
+{
+	if (xen_guest)
+		xen_pvh_init(&pvh_bootparams);
+}
+
+/*
+ * 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 = 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();
+	}
+
+	/*
+	 * This must not compile to "call memset" because memset() may be
+	 * instrumented.
+	 */
+	__builtin_memset(&pvh_bootparams, 0, sizeof(pvh_bootparams));
+
+	hypervisor_specific_init(xen_guest);
+
+	init_pvh_bootparams(xen_guest);
+}

linux-7.2.3/arch/x86/platform/pvh/head.S

@@ -0,0 +1,313 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright C 2016, Oracle and/or its affiliates. All rights reserved.
+ */
+
+	.code32
+	.text
+#ifdef CONFIG_X86_32
+#define _pa(x)          ((x) - __START_KERNEL_map)
+#endif
+#define rva(x)          ((x) - pvh_start_xen)
+
+#include <linux/elfnote.h>
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/desc_defs.h>
+#include <asm/segment.h>
+#include <asm/asm.h>
+#include <asm/boot.h>
+#include <asm/pgtable.h>
+#include <asm/processor-flags.h>
+#include <asm/msr.h>
+#include <asm/nospec-branch.h>
+#include <xen/interface/elfnote.h>
+
+	__INIT
+
+/*
+ * 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 its own stack, GDT and IDT.
+ */
+
+#define PVH_GDT_ENTRY_CS	1
+#define PVH_GDT_ENTRY_DS	2
+#define PVH_CS_SEL		(PVH_GDT_ENTRY_CS * 8)
+#define PVH_DS_SEL		(PVH_GDT_ENTRY_DS * 8)
+
+SYM_CODE_START(pvh_start_xen)
+	UNWIND_HINT_END_OF_STACK
+	cld
+
+	/*
+	 * See the comment for startup_32 for more details.  We need to
+	 * execute a call to get the execution address to be position
+	 * independent, but we don't have a stack.  Save and restore the
+	 * magic field of start_info in ebx, and use that as the stack.
+	 */
+	mov  (%ebx), %eax
+	leal 4(%ebx), %esp
+	ANNOTATE_INTRA_FUNCTION_CALL
+	call 1f
+1:	popl %ebp
+	mov  %eax, (%ebx)
+	subl $rva(1b), %ebp
+	movl $0, %esp
+
+	leal rva(gdt)(%ebp), %eax
+	addl %eax, 2(%eax)
+	lgdt (%eax)
+
+	mov $PVH_DS_SEL,%eax
+	mov %eax,%ds
+	mov %eax,%es
+	mov %eax,%ss
+
+	/* Stash hvm_start_info. */
+	leal rva(pvh_start_info)(%ebp), %edi
+	mov %ebx, %esi
+	movl rva(pvh_start_info_sz)(%ebp), %ecx
+	shr $2,%ecx
+	rep movsl
+
+	leal rva(early_stack_end)(%ebp), %esp
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+	/* Enable PAE mode. */
+	mov %cr4, %eax
+	orl $X86_CR4_PAE, %eax
+	mov %eax, %cr4
+#endif
+
+#ifdef CONFIG_X86_64
+	/* Enable Long mode. */
+	mov $MSR_EFER, %ecx
+	rdmsr
+	btsl $_EFER_LME, %eax
+	wrmsr
+
+	/*
+	 * Reuse the non-relocatable symbol emitted for the ELF note to
+	 * subtract the build time physical address of pvh_start_xen() from
+	 * its actual runtime address, without relying on absolute 32-bit ELF
+	 * relocations, as these are not supported by the linker when running
+	 * in -pie mode, and should be avoided in .head.text in general.
+	 */
+	mov %ebp, %ebx
+	subl rva(xen_elfnote_phys32_entry)(%ebp), %ebx
+	jz .Lpagetable_done
+
+	/*
+	 * Store the resulting load offset in phys_base.  __pa() needs
+	 * phys_base set to calculate the hypercall page in xen_pvh_init().
+	 */
+	movl %ebx, rva(phys_base)(%ebp)
+
+	/* Fixup page-tables for relocation. */
+	leal rva(pvh_init_top_pgt)(%ebp), %edi
+	movl $PTRS_PER_PGD, %ecx
+2:
+	testl $_PAGE_PRESENT, 0x00(%edi)
+	jz 1f
+	addl %ebx, 0x00(%edi)
+1:
+	addl $8, %edi
+	decl %ecx
+	jnz 2b
+
+	/* L3 ident has a single entry. */
+	leal rva(pvh_level3_ident_pgt)(%ebp), %edi
+	addl %ebx, 0x00(%edi)
+
+	leal rva(pvh_level3_kernel_pgt)(%ebp), %edi
+	addl %ebx, (PAGE_SIZE - 16)(%edi)
+	addl %ebx, (PAGE_SIZE - 8)(%edi)
+
+	/* pvh_level2_ident_pgt is fine - large pages */
+
+	/* pvh_level2_kernel_pgt needs adjustment - large pages */
+	leal rva(pvh_level2_kernel_pgt)(%ebp), %edi
+	movl $PTRS_PER_PMD, %ecx
+2:
+	testl $_PAGE_PRESENT, 0x00(%edi)
+	jz 1f
+	addl %ebx, 0x00(%edi)
+1:
+	addl $8, %edi
+	decl %ecx
+	jnz 2b
+
+.Lpagetable_done:
+	/* Enable pre-constructed page tables. */
+	leal rva(pvh_init_top_pgt)(%ebp), %eax
+	mov %eax, %cr3
+	mov $(X86_CR0_PG | X86_CR0_PE), %eax
+	mov %eax, %cr0
+
+	/* Jump to 64-bit mode. */
+	pushl $PVH_CS_SEL
+	leal  rva(1f)(%ebp), %eax
+	pushl %eax
+	lretl
+
+	/* 64-bit entry point. */
+	.code64
+1:
+	UNWIND_HINT_END_OF_STACK
+
+	/*
+	 * Set up GSBASE.
+	 * Note that on SMP the boot CPU uses the init data section until
+	 * the per-CPU areas are set up.
+	 */
+	movl $MSR_GS_BASE,%ecx
+	xorl %eax, %eax
+	xorl %edx, %edx
+	wrmsr
+
+	/* Call xen_prepare_pvh() via the kernel virtual mapping */
+	leaq xen_prepare_pvh(%rip), %rax
+	subq phys_base(%rip), %rax
+	addq $__START_KERNEL_map, %rax
+	ANNOTATE_RETPOLINE_SAFE
+	call *%rax
+
+	/* startup_64 expects boot_params in %rsi. */
+	lea pvh_bootparams(%rip), %rsi
+	jmp startup_64
+
+#else /* CONFIG_X86_64 */
+
+	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
+SYM_CODE_END(pvh_start_xen)
+
+	.section ".init.data","aw"
+	.balign 8
+SYM_DATA_START_LOCAL(gdt)
+	.word gdt_end - gdt_start - 1
+	.long gdt_start - gdt
+	.word 0
+SYM_DATA_END(gdt)
+SYM_DATA_START_LOCAL(gdt_start)
+	.quad 0x0000000000000000            /* NULL descriptor */
+#ifdef CONFIG_X86_64
+	.quad GDT_ENTRY(DESC_CODE64, 0, 0xfffff) /* PVH_CS_SEL */
+#else
+	.quad GDT_ENTRY(DESC_CODE32, 0, 0xfffff) /* PVH_CS_SEL */
+#endif
+	.quad GDT_ENTRY(DESC_DATA32, 0, 0xfffff) /* PVH_DS_SEL */
+SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end)
+
+	.balign 16
+SYM_DATA_START_LOCAL(early_stack)
+	.fill BOOT_STACK_SIZE, 1, 0
+SYM_DATA_END_LABEL(early_stack, SYM_L_LOCAL, early_stack_end)
+
+#ifdef CONFIG_X86_64
+/*
+ * Xen PVH needs a set of identity mapped and kernel high mapping
+ * page tables.  pvh_start_xen starts running on the identity mapped
+ * page tables, but xen_prepare_pvh calls into the high mapping.
+ * These page tables need to be relocatable and are only used until
+ * startup_64 transitions to init_top_pgt.
+ */
+SYM_DATA_START_PAGE_ALIGNED(pvh_init_top_pgt)
+	.quad   pvh_level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
+	.org    pvh_init_top_pgt + L4_PAGE_OFFSET * 8, 0
+	.quad   pvh_level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
+	.org    pvh_init_top_pgt + L4_START_KERNEL * 8, 0
+	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
+	.quad   pvh_level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
+SYM_DATA_END(pvh_init_top_pgt)
+
+SYM_DATA_START_PAGE_ALIGNED(pvh_level3_ident_pgt)
+	.quad	pvh_level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
+	.fill	511, 8, 0
+SYM_DATA_END(pvh_level3_ident_pgt)
+SYM_DATA_START_PAGE_ALIGNED(pvh_level2_ident_pgt)
+	/*
+	 * Since I easily can, map the first 1G.
+	 * Don't set NX because code runs from these pages.
+	 *
+	 * Note: This sets _PAGE_GLOBAL despite whether
+	 * the CPU supports it or it is enabled.  But,
+	 * the CPU should ignore the bit.
+	 */
+	PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
+SYM_DATA_END(pvh_level2_ident_pgt)
+SYM_DATA_START_PAGE_ALIGNED(pvh_level3_kernel_pgt)
+	.fill	L3_START_KERNEL, 8, 0
+	/* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */
+	.quad	pvh_level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
+	.quad	0 /* no fixmap */
+SYM_DATA_END(pvh_level3_kernel_pgt)
+
+SYM_DATA_START_PAGE_ALIGNED(pvh_level2_kernel_pgt)
+	/*
+	 * Kernel high mapping.
+	 *
+	 * The kernel code+data+bss must be located below KERNEL_IMAGE_SIZE in
+	 * virtual address space, which is 1 GiB if RANDOMIZE_BASE is enabled,
+	 * 512 MiB otherwise.
+	 *
+	 * (NOTE: after that starts the module area, see MODULES_VADDR.)
+	 *
+	 * This table is eventually used by the kernel during normal runtime.
+	 * Care must be taken to clear out undesired bits later, like _PAGE_RW
+	 * or _PAGE_GLOBAL in some cases.
+	 */
+	PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE / PMD_SIZE)
+SYM_DATA_END(pvh_level2_kernel_pgt)
+
+	ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_RELOC,
+		     .long CONFIG_PHYSICAL_ALIGN;
+		     .long LOAD_PHYSICAL_ADDR;
+		     .long KERNEL_IMAGE_SIZE - 1)
+#endif
+
+	ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY, .global xen_elfnote_phys32_entry;
+		xen_elfnote_phys32_entry: _ASM_PTR xen_elfnote_phys32_entry_value - .)