qboot changes for PVH boot

benchmark.h

@@ -9,5 +9,6 @@
 #define FW_START    1
 #define LINUX_START_FWCFG 2
 #define LINUX_START_BOOT  3
+#define LINUX_START_PVHBOOT  4
 
-#endif
+#endif /* BENCHMARK_H */

fw_cfg.c

@@ -6,8 +6,12 @@
 #include "fw_cfg.h"
 #include "bswap.h"
 #include "linuxboot.h"
+#include "memaccess.h"
 #include "multiboot.h"
 #include "benchmark.h"
+#include "start_info.h"
+
+extern struct hvm_start_info start_info;
 
 struct fw_cfg_file {
 	uint32_t size;
@@ -184,6 +188,72 @@ static void boot_multiboot_from_fw_cfg(void)
 	panic();
 }
 
+static void pvh_e820_setup()
+{
+	struct hvm_memmap_table_entry *pvh_e820p;
+	int i, pvh_e820_sz;
+
+	pvh_e820_sz = sizeof(struct hvm_memmap_table_entry) * e820->nr_map;
+
+	pvh_e820p = malloc(pvh_e820_sz);
+	memset(pvh_e820p, 0, pvh_e820_sz);
+
+	for (i = 0; i < e820->nr_map; i++) {
+		pvh_e820p[i].addr = e820->map[i].addr;
+		pvh_e820p[i].size = e820->map[i].size;
+		pvh_e820p[i].type = e820->map[i].type;
+	}
+	start_info.memmap_paddr = (uintptr_t)pvh_e820p;
+	start_info.memmap_entries = e820->nr_map;
+}
+
+static void boot_pvh_from_fw_cfg(void)
+{
+	void *kernel_entry;
+	uint32_t sz;
+	struct linuxboot_args args;
+	struct hvm_modlist_entry ramdisk_mod;
+
+	start_info.magic = XEN_HVM_START_MAGIC_VALUE;
+	start_info.version = 1;
+	start_info.flags = 0;
+	start_info.nr_modules = 1;
+	start_info.reserved = 0;
+
+	fw_cfg_select(FW_CFG_CMDLINE_SIZE);
+	args.cmdline_size = fw_cfg_readl_le();
+	args.cmdline_addr = malloc(args.cmdline_size);
+	fw_cfg_read_entry(FW_CFG_CMDLINE_DATA, args.cmdline_addr,
+			  args.cmdline_size);
+	start_info.cmdline_paddr = (uintptr_t)args.cmdline_addr;
+
+	/* Use this field for pvhboot. Not used by pvhboot otherwise */
+	fw_cfg_read_entry(FW_CFG_KERNEL_DATA, &ramdisk_mod,
+			  sizeof(ramdisk_mod));
+	ramdisk_mod.cmdline_paddr = (uintptr_t)&ramdisk_mod;
+	start_info.modlist_paddr = (uintptr_t)&ramdisk_mod;
+
+	pvh_e820_setup();
+
+	fw_cfg_select(FW_CFG_KERNEL_SIZE);
+	sz = fw_cfg_readl_le();
+	if (!sz)
+		panic();
+
+	fw_cfg_select(FW_CFG_KERNEL_ENTRY);
+	kernel_entry = (void *) fw_cfg_readl_le();
+
+#ifdef BENCHMARK_HACK
+	/* Exit just before jumping to vmlinux, so that it is easy
+	 * to time/profile the firmware.
+	 */
+	outb(LINUX_EXIT_PORT, LINUX_START_PVHBOOT);
+#endif
+	asm volatile("jmp *%2" : : "a" (0x2badb002),
+		     "b"(&start_info), "c"(kernel_entry));
+	panic();
+}
+
 void boot_from_fwcfg(void)
 {
 	struct linuxboot_args args;
@@ -208,8 +278,13 @@ void boot_from_fwcfg(void)
 	fw_cfg_select(FW_CFG_SETUP_DATA);
 	fw_cfg_read(args.header, sizeof(args.header));
 
-	if (!parse_bzimage(&args))
+	if (!parse_bzimage(&args)) {
+		uint8_t *header = args.header;
+
+		if (ldl_p(header) == 0x464c457f)  /* ELF magic */
+			boot_pvh_from_fw_cfg();
 		boot_multiboot_from_fw_cfg();
+	}
 
 	/* SETUP_DATA already selected */
 	if (args.setup_size > sizeof(args.header))

include/memaccess.h

@@ -0,0 +1,30 @@
+#ifndef MEMACCESS_H_
+#define MEMACCESS_H_
+
+#include "string.h"
+
+static inline uint16_t lduw_p(void *p)
+{
+	uint16_t val;
+	memcpy(&val, p, 2);
+	return val;
+}
+
+static inline uint32_t ldl_p(void *p)
+{
+	uint32_t val;
+	memcpy(&val, p, 4);
+	return val;
+}
+
+static inline void stw_p(void *p, uint16_t val)
+{
+	memcpy(p, &val, 2);
+}
+
+static inline void stl_p(void *p, uint32_t val)
+{
+	memcpy(p, &val, 4);
+}
+
+#endif /* MEMACCESS_H_ */

include/start_info.h

@@ -0,0 +1,146 @@
+/*
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Copyright (c) 2016, Citrix Systems, Inc.
+ */
+
+#ifndef __XEN_PUBLIC_ARCH_X86_HVM_START_INFO_H__
+#define __XEN_PUBLIC_ARCH_X86_HVM_START_INFO_H__
+
+/*
+ * Start of day structure passed to PVH guests and to HVM guests in %ebx.
+ *
+ * NOTE: nothing will be loaded at physical address 0, so a 0 value in any
+ * of the address fields should be treated as not present.
+ *
+ *  0 +----------------+
+ *    | magic          | Contains the magic value XEN_HVM_START_MAGIC_VALUE
+ *    |                | ("xEn3" with the 0x80 bit of the "E" set).
+ *  4 +----------------+
+ *    | version        | Version of this structure. Current version is 1. New
+ *    |                | versions are guaranteed to be backwards-compatible.
+ *  8 +----------------+
+ *    | flags          | SIF_xxx flags.
+ * 12 +----------------+
+ *    | nr_modules     | Number of modules passed to the kernel.
+ * 16 +----------------+
+ *    | modlist_paddr  | Physical address of an array of modules
+ *    |                | (layout of the structure below).
+ * 24 +----------------+
+ *    | cmdline_paddr  | Physical address of the command line,
+ *    |                | a zero-terminated ASCII string.
+ * 32 +----------------+
+ *    | rsdp_paddr     | Physical address of the RSDP ACPI data structure.
+ * 40 +----------------+
+ *    | memmap_paddr   | Physical address of the (optional) memory map. Only
+ *    |                | present in version 1 and newer of the structure.
+ * 48 +----------------+
+ *    | memmap_entries | Number of entries in the memory map table. Only
+ *    |                | present in version 1 and newer of the structure.
+ *    |                | Zero if there is no memory map being provided.
+ * 52 +----------------+
+ *    | reserved       | Version 1 and newer only.
+ * 56 +----------------+
+ *
+ * The layout of each entry in the module structure is the following:
+ *
+ *  0 +----------------+
+ *    | paddr          | Physical address of the module.
+ *  8 +----------------+
+ *    | size           | Size of the module in bytes.
+ * 16 +----------------+
+ *    | cmdline_paddr  | Physical address of the command line,
+ *    |                | a zero-terminated ASCII string.
+ * 24 +----------------+
+ *    | reserved       |
+ * 32 +----------------+
+ *
+ * The layout of each entry in the memory map table is as follows:
+ *
+ *  0 +----------------+
+ *    | addr           | Base address
+ *  8 +----------------+
+ *    | size           | Size of mapping in bytes
+ * 16 +----------------+
+ *    | type           | Type of mapping as defined between the hypervisor
+ *    |                | and guest it's starting. E820_TYPE_xxx, for example.
+ * 20 +----------------|
+ *    | reserved       |
+ * 24 +----------------+
+ *
+ * The address and sizes are always a 64bit little endian unsigned integer.
+ *
+ * NB: Xen on x86 will always try to place all the data below the 4GiB
+ * boundary.
+ *
+ * Version numbers of the hvm_start_info structure have evolved like this:
+ *
+ * Version 0:
+ *
+ * Version 1:   Added the memmap_paddr/memmap_entries fields (plus 4 bytes of
+ *              padding) to the end of the hvm_start_info struct. These new
+ *              fields can be used to pass a memory map to the guest. The
+ *              memory map is optional and so guests that understand version 1
+ *              of the structure must check that memmap_entries is non-zero
+ *              before trying to read the memory map.
+ */
+#define XEN_HVM_START_MAGIC_VALUE 0x336ec578
+
+/*
+ * C representation of the x86/HVM start info layout.
+ *
+ * The canonical definition of this layout is above, this is just a way to
+ * represent the layout described there using C types.
+ */
+struct hvm_start_info {
+    uint32_t magic;             /* Contains the magic value 0x336ec578       */
+                                /* ("xEn3" with the 0x80 bit of the "E" set).*/
+    uint32_t version;           /* Version of this structure.                */
+    uint32_t flags;             /* SIF_xxx flags.                            */
+    uint32_t nr_modules;        /* Number of modules passed to the kernel.   */
+    uint64_t modlist_paddr;     /* Physical address of an array of           */
+                                /* hvm_modlist_entry.                        */
+    uint64_t cmdline_paddr;     /* Physical address of the command line.     */
+    uint64_t rsdp_paddr;        /* Physical address of the RSDP ACPI data    */
+                                /* structure.                                */
+    uint64_t memmap_paddr;      /* Physical address of an array of           */
+                                /* hvm_memmap_table_entry. Only present in   */
+                                /* version 1 and newer of the structure      */
+    uint32_t memmap_entries;    /* Number of entries in the memmap table.    */
+                                /* Only present in version 1 and newer of    */
+                                /* the structure. Value will be zero if      */
+                                /* there is no memory map being provided.    */
+    uint32_t reserved;
+};
+
+struct hvm_modlist_entry {
+    uint64_t paddr;             /* Physical address of the module.           */
+    uint64_t size;              /* Size of the module in bytes.              */
+    uint64_t cmdline_paddr;     /* Physical address of the command line.     */
+    uint64_t reserved;
+};
+
+struct hvm_memmap_table_entry {
+    uint64_t addr;              /* Base address of the memory region         */
+    uint64_t size;              /* Size of the memory region in bytes        */
+    uint32_t type;              /* Mapping type                              */
+    uint32_t reserved;
+};
+
+#endif /* __XEN_PUBLIC_ARCH_X86_HVM_START_INFO_H__ */

linuxboot.c

@@ -1,33 +1,13 @@
 #include "bios.h"
 #include "linuxboot.h"
+#include "memaccess.h"
 #include "ioport.h"
+#include "start_info.h"
 #include "string.h"
 #include "stdio.h"
 #include "benchmark.h"
 
-static inline uint16_t lduw_p(void *p)
-{
-	uint16_t val;
-	memcpy(&val, p, 2);
-	return val;
-}
-
-static inline uint32_t ldl_p(void *p)
-{
-	uint32_t val;
-	memcpy(&val, p, 4);
-	return val;
-}
-
-static inline void stw_p(void *p, uint16_t val)
-{
-	memcpy(p, &val, 2);
-}
-
-static inline void stl_p(void *p, uint32_t val)
-{
-	memcpy(p, &val, 4);
-}
+struct hvm_start_info start_info = {0};
 
 bool parse_bzimage(struct linuxboot_args *args)
 {

tables.c

@@ -2,6 +2,9 @@
 #include "stdio.h"
 #include "fw_cfg.h"
 #include "string.h"
+#include "start_info.h"
+
+extern struct hvm_start_info start_info;
 
 struct loader_cmd {
 	uint32_t cmd;
@@ -67,6 +70,13 @@ static void do_alloc(char *file, uint32_t align, uint8_t zone)
 
 	set_file_addr(id, p);
 	fw_cfg_read_file(id, p, n);
+
+	/* For PVH boot, save the PA where the RSDP is stored */
+	if (zone == ALLOC_FSEG) {
+		if (!memcmp(p, "RSD PTR ", 8)) {
+			start_info.rsdp_paddr = (uintptr_t)id_to_addr(id);
+		}
+	}
 }
 
 static void do_ptr(char *dest, char *src, uint32_t offset, uint8_t size)