Adding upstream version 5.10.209.upstream/5.10.209upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

3 files changed, 319 insertions, 0 deletions

diff --git a/arch/x86/platform/pvh/Makefile b/arch/x86/platform/pvh/Makefile
new file mode 100644
index 000000000..5dec5067c
--- /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-$(CONFIG_PVH) += enlighten.o
+obj-$(CONFIG_PVH) += head.o
diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c
new file mode 100644
index 000000000..9ac7457f5
--- /dev/null
+++ b/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/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 the data segment since
+ * they are used after startup_{32|64}, which clear .bss, are invoked.
+ */
+struct boot_params pvh_bootparams __section(".data");
+struct hvm_start_info pvh_start_info __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;
+}
+
+/*
+ * 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/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;
+
+	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(struct boot_params *boot_params)
+{
+	xen_raw_printk("Error: Missing xen PVH initialization\n");
+	BUG();
+}
+
+static void 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();
+	}
+
+	memset(&pvh_bootparams, 0, sizeof(pvh_bootparams));
+
+	hypervisor_specific_init(xen_guest);
+
+	init_pvh_bootparams(xen_guest);
+}
diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S
new file mode 100644
index 000000000..43b4d8648
--- /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 <linux/elfnote.h>
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/asm.h>
+#include <asm/boot.h>
+#include <asm/processor-flags.h>
+#include <asm/msr.h>
+#include <xen/interface/elfnote.h>
+
+	__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)
+
+SYM_CODE_START_LOCAL(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
+SYM_CODE_END(pvh_start_xen)
+
+	.section ".init.data","aw"
+	.balign 8
+SYM_DATA_START_LOCAL(gdt)
+	.word gdt_end - gdt_start
+	.long _pa(gdt_start)
+	.word 0
+SYM_DATA_END(gdt)
+SYM_DATA_START_LOCAL(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 */
+SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end)
+
+	.balign 16
+SYM_DATA_LOCAL(canary, .fill 48, 1, 0)
+
+SYM_DATA_START_LOCAL(early_stack)
+	.fill BOOT_STACK_SIZE, 1, 0
+SYM_DATA_END_LABEL(early_stack, SYM_L_LOCAL, early_stack_end)
+
+	ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY,
+	             _ASM_PTR (pvh_start_xen - __START_KERNEL_map))