1 files changed, 192 insertions, 125 deletions

diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index cfa99e8f054b..3823e52aef52 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -6,19 +6,21 @@
  */
 
 #include <linux/init.h>
+#include <linux/iscsi_ibft.h>
 #include <linux/sched.h>
+#include <linux/kstrtox.h>
 #include <linux/mm.h>
 #include <linux/pm.h>
 #include <linux/memblock.h>
 #include <linux/cpuidle.h>
 #include <linux/cpufreq.h>
 #include <linux/memory_hotplug.h>
+#include <linux/acpi.h>
 
 #include <asm/elf.h>
 #include <asm/vdso.h>
 #include <asm/e820/api.h>
 #include <asm/setup.h>
-#include <asm/acpi.h>
 #include <asm/numa.h>
 #include <asm/idtentry.h>
 #include <asm/xen/hypervisor.h>
@@ -32,19 +34,18 @@
 #include <xen/features.h>
 #include <xen/hvc-console.h>
 #include "xen-ops.h"
-#include "mmu.h"
 
 #define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024)
 
-/* Amount of extra memory space we add to the e820 ranges */
-struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
-
-/* Number of pages released from the initial allocation. */
-unsigned long xen_released_pages;
+/* Memory map would allow PCI passthrough. */
+bool xen_pv_pci_possible;
 
 /* E820 map used during setting up memory. */
 static struct e820_table xen_e820_table __initdata;
 
+/* Number of initially usable memory pages. */
+static unsigned long ini_nr_pages __initdata;
+
 /*
  * Buffer used to remap identity mapped pages. We only need the virtual space.
  * The physical page behind this address is remapped as needed to different
@@ -59,18 +60,6 @@ static struct {
 } xen_remap_buf __initdata __aligned(PAGE_SIZE);
 static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY;
 
-/*
- * The maximum amount of extra memory compared to the base size.  The
- * main scaling factor is the size of struct page.  At extreme ratios
- * of base:extra, all the base memory can be filled with page
- * structures for the extra memory, leaving no space for anything
- * else.
- *
- * 10x seems like a reasonable balance between scaling flexibility and
- * leaving a practically usable system.
- */
-#define EXTRA_MEM_RATIO		(10)
-
 static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB);
 
 static void __init xen_parse_512gb(void)
@@ -85,41 +74,12 @@ static void __init xen_parse_512gb(void)
 	arg = strstr(xen_start_info->cmd_line, "xen_512gb_limit=");
 	if (!arg)
 		val = true;
-	else if (strtobool(arg + strlen("xen_512gb_limit="), &val))
+	else if (kstrtobool(arg + strlen("xen_512gb_limit="), &val))
 		return;
 
 	xen_512gb_limit = val;
 }
 
-static void __init xen_add_extra_mem(unsigned long start_pfn,
-				     unsigned long n_pfns)
-{
-	int i;
-
-	/*
-	 * No need to check for zero size, should happen rarely and will only
-	 * write a new entry regarded to be unused due to zero size.
-	 */
-	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
-		/* Add new region. */
-		if (xen_extra_mem[i].n_pfns == 0) {
-			xen_extra_mem[i].start_pfn = start_pfn;
-			xen_extra_mem[i].n_pfns = n_pfns;
-			break;
-		}
-		/* Append to existing region. */
-		if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns ==
-		    start_pfn) {
-			xen_extra_mem[i].n_pfns += n_pfns;
-			break;
-		}
-	}
-	if (i == XEN_EXTRA_MEM_MAX_REGIONS)
-		printk(KERN_WARNING "Warning: not enough extra memory regions\n");
-
-	memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));
-}
-
 static void __init xen_del_extra_mem(unsigned long start_pfn,
 				     unsigned long n_pfns)
 {
@@ -252,7 +212,7 @@ static int __init xen_free_mfn(unsigned long mfn)
  * as a fallback if the remapping fails.
  */
 static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
-			unsigned long end_pfn, unsigned long nr_pages)
+						      unsigned long end_pfn)
 {
 	unsigned long pfn, end;
 	int ret;
@@ -260,7 +220,7 @@ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
 	WARN_ON(start_pfn > end_pfn);
 
 	/* Release pages first. */
-	end = min(end_pfn, nr_pages);
+	end = min(end_pfn, ini_nr_pages);
 	for (pfn = start_pfn; pfn < end; pfn++) {
 		unsigned long mfn = pfn_to_mfn(pfn);
 
@@ -338,7 +298,7 @@ static void __init xen_do_set_identity_and_remap_chunk(
 
 	WARN_ON(size == 0);
 
-	mfn_save = virt_to_mfn(buf);
+	mfn_save = virt_to_mfn((void *)buf);
 
 	for (ident_pfn_iter = start_pfn, remap_pfn_iter = remap_pfn;
 	     ident_pfn_iter < ident_end_pfn;
@@ -381,15 +341,14 @@ static void __init xen_do_set_identity_and_remap_chunk(
  * to Xen and not remapped.
  */
 static unsigned long __init xen_set_identity_and_remap_chunk(
-	unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
-	unsigned long remap_pfn)
+	unsigned long start_pfn, unsigned long end_pfn, unsigned long remap_pfn)
 {
 	unsigned long pfn;
 	unsigned long i = 0;
 	unsigned long n = end_pfn - start_pfn;
 
 	if (remap_pfn == 0)
-		remap_pfn = nr_pages;
+		remap_pfn = ini_nr_pages;
 
 	while (i < n) {
 		unsigned long cur_pfn = start_pfn + i;
@@ -398,19 +357,19 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 		unsigned long remap_range_size;
 
 		/* Do not remap pages beyond the current allocation */
-		if (cur_pfn >= nr_pages) {
+		if (cur_pfn >= ini_nr_pages) {
 			/* Identity map remaining pages */
 			set_phys_range_identity(cur_pfn, cur_pfn + size);
 			break;
 		}
-		if (cur_pfn + size > nr_pages)
-			size = nr_pages - cur_pfn;
+		if (cur_pfn + size > ini_nr_pages)
+			size = ini_nr_pages - cur_pfn;
 
 		remap_range_size = xen_find_pfn_range(&remap_pfn);
 		if (!remap_range_size) {
 			pr_warn("Unable to find available pfn range, not remapping identity pages\n");
 			xen_set_identity_and_release_chunk(cur_pfn,
-						cur_pfn + left, nr_pages);
+							   cur_pfn + left);
 			break;
 		}
 		/* Adjust size to fit in current e820 RAM region */
@@ -437,18 +396,18 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 }
 
 static unsigned long __init xen_count_remap_pages(
-	unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
+	unsigned long start_pfn, unsigned long end_pfn,
 	unsigned long remap_pages)
 {
-	if (start_pfn >= nr_pages)
+	if (start_pfn >= ini_nr_pages)
 		return remap_pages;
 
-	return remap_pages + min(end_pfn, nr_pages) - start_pfn;
+	return remap_pages + min(end_pfn, ini_nr_pages) - start_pfn;
 }
 
-static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages,
+static unsigned long __init xen_foreach_remap_area(
 	unsigned long (*func)(unsigned long start_pfn, unsigned long end_pfn,
-			      unsigned long nr_pages, unsigned long last_val))
+			      unsigned long last_val))
 {
 	phys_addr_t start = 0;
 	unsigned long ret_val = 0;
@@ -476,8 +435,7 @@ static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages,
 				end_pfn = PFN_UP(entry->addr);
 
 			if (start_pfn < end_pfn)
-				ret_val = func(start_pfn, end_pfn, nr_pages,
-					       ret_val);
+				ret_val = func(start_pfn, end_pfn, ret_val);
 			start = end;
 		}
 	}
@@ -501,7 +459,7 @@ void __init xen_remap_memory(void)
 	unsigned long pfn_s = ~0UL;
 	unsigned long len = 0;
 
-	mfn_save = virt_to_mfn(buf);
+	mfn_save = virt_to_mfn((void *)buf);
 
 	while (xen_remap_mfn != INVALID_P2M_ENTRY) {
 		/* Map the remap information */
@@ -534,6 +492,8 @@ void __init xen_remap_memory(void)
 	set_pte_mfn(buf, mfn_save, PAGE_KERNEL);
 
 	pr_info("Remapped %ld page(s)\n", remapped);
+
+	xen_do_remap_nonram();
 }
 
 static unsigned long __init xen_get_pages_limit(void)
@@ -607,7 +567,7 @@ static void __init xen_ignore_unusable(void)
 	}
 }
 
-bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size)
+static bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size)
 {
 	struct e820_entry *entry;
 	unsigned mapcnt;
@@ -665,6 +625,111 @@ phys_addr_t __init xen_find_free_area(phys_addr_t size)
 }
 
 /*
+ * Swap a non-RAM E820 map entry with RAM above ini_nr_pages.
+ * Note that the E820 map is modified accordingly, but the P2M map isn't yet.
+ * The adaption of the P2M must be deferred until page allocation is possible.
+ */
+static void __init xen_e820_swap_entry_with_ram(struct e820_entry *swap_entry)
+{
+	struct e820_entry *entry;
+	unsigned int mapcnt;
+	phys_addr_t mem_end = PFN_PHYS(ini_nr_pages);
+	phys_addr_t swap_addr, swap_size, entry_end;
+
+	swap_addr = PAGE_ALIGN_DOWN(swap_entry->addr);
+	swap_size = PAGE_ALIGN(swap_entry->addr - swap_addr + swap_entry->size);
+	entry = xen_e820_table.entries;
+
+	for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++) {
+		entry_end = entry->addr + entry->size;
+		if (entry->type == E820_TYPE_RAM && entry->size >= swap_size &&
+		    entry_end - swap_size >= mem_end) {
+			/* Reduce RAM entry by needed space (whole pages). */
+			entry->size -= swap_size;
+
+			/* Add new entry at the end of E820 map. */
+			entry = xen_e820_table.entries +
+				xen_e820_table.nr_entries;
+			xen_e820_table.nr_entries++;
+
+			/* Fill new entry (keep size and page offset). */
+			entry->type = swap_entry->type;
+			entry->addr = entry_end - swap_size +
+				      swap_addr - swap_entry->addr;
+			entry->size = swap_entry->size;
+
+			/* Convert old entry to RAM, align to pages. */
+			swap_entry->type = E820_TYPE_RAM;
+			swap_entry->addr = swap_addr;
+			swap_entry->size = swap_size;
+
+			/* Remember PFN<->MFN relation for P2M update. */
+			xen_add_remap_nonram(swap_addr, entry_end - swap_size,
+					     swap_size);
+
+			/* Order E820 table and merge entries. */
+			e820__update_table(&xen_e820_table);
+
+			return;
+		}
+
+		entry++;
+	}
+
+	xen_raw_console_write("No suitable area found for required E820 entry remapping action\n");
+	BUG();
+}
+
+/*
+ * Look for non-RAM memory types in a specific guest physical area and move
+ * those away if possible (ACPI NVS only for now).
+ */
+static void __init xen_e820_resolve_conflicts(phys_addr_t start,
+					      phys_addr_t size)
+{
+	struct e820_entry *entry;
+	unsigned int mapcnt;
+	phys_addr_t end;
+
+	if (!size)
+		return;
+
+	end = start + size;
+	entry = xen_e820_table.entries;
+
+	for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++) {
+		if (entry->addr >= end)
+			return;
+
+		if (entry->addr + entry->size > start &&
+		    entry->type == E820_TYPE_NVS)
+			xen_e820_swap_entry_with_ram(entry);
+
+		entry++;
+	}
+}
+
+/*
+ * Check for an area in physical memory to be usable for non-movable purposes.
+ * An area is considered to usable if the used E820 map lists it to be RAM or
+ * some other type which can be moved to higher PFNs while keeping the MFNs.
+ * In case the area is not usable, crash the system with an error message.
+ */
+void __init xen_chk_is_e820_usable(phys_addr_t start, phys_addr_t size,
+				   const char *component)
+{
+	xen_e820_resolve_conflicts(start, size);
+
+	if (!xen_is_e820_reserved(start, size))
+		return;
+
+	xen_raw_console_write("Xen hypervisor allocated ");
+	xen_raw_console_write(component);
+	xen_raw_console_write(" memory conflicts with E820 map\n");
+	BUG();
+}
+
+/*
  * Like memcpy, but with physical addresses for dest and src.
  */
 static void __init xen_phys_memcpy(phys_addr_t dest, phys_addr_t src,
@@ -723,20 +788,20 @@ static void __init xen_reserve_xen_mfnlist(void)
  **/
 char * __init xen_memory_setup(void)
 {
-	unsigned long max_pfn, pfn_s, n_pfns;
+	unsigned long pfn_s, n_pfns;
 	phys_addr_t mem_end, addr, size, chunk_size;
 	u32 type;
 	int rc;
 	struct xen_memory_map memmap;
 	unsigned long max_pages;
 	unsigned long extra_pages = 0;
+	unsigned long maxmem_pages;
 	int i;
 	int op;
 
 	xen_parse_512gb();
-	max_pfn = xen_get_pages_limit();
-	max_pfn = min(max_pfn, xen_start_info->nr_pages);
-	mem_end = PFN_PHYS(max_pfn);
+	ini_nr_pages = min(xen_get_pages_limit(), xen_start_info->nr_pages);
+	mem_end = PFN_PHYS(ini_nr_pages);
 
 	memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries);
 	set_xen_guest_handle(memmap.buffer, xen_e820_table.entries);
@@ -763,27 +828,58 @@ char * __init xen_memory_setup(void)
 	BUG_ON(memmap.nr_entries == 0);
 	xen_e820_table.nr_entries = memmap.nr_entries;
 
-	/*
-	 * Xen won't allow a 1:1 mapping to be created to UNUSABLE
-	 * regions, so if we're using the machine memory map leave the
-	 * region as RAM as it is in the pseudo-physical map.
-	 *
-	 * UNUSABLE regions in domUs are not handled and will need
-	 * a patch in the future.
-	 */
-	if (xen_initial_domain())
+	if (xen_initial_domain()) {
+		/*
+		 * Xen won't allow a 1:1 mapping to be created to UNUSABLE
+		 * regions, so if we're using the machine memory map leave the
+		 * region as RAM as it is in the pseudo-physical map.
+		 *
+		 * UNUSABLE regions in domUs are not handled and will need
+		 * a patch in the future.
+		 */
 		xen_ignore_unusable();
 
+#ifdef CONFIG_ISCSI_IBFT_FIND
+		/* Reserve 0.5 MiB to 1 MiB region so iBFT can be found */
+		xen_e820_table.entries[xen_e820_table.nr_entries].addr = IBFT_START;
+		xen_e820_table.entries[xen_e820_table.nr_entries].size = IBFT_END - IBFT_START;
+		xen_e820_table.entries[xen_e820_table.nr_entries].type = E820_TYPE_RESERVED;
+		xen_e820_table.nr_entries++;
+#endif
+	}
+
 	/* Make sure the Xen-supplied memory map is well-ordered. */
 	e820__update_table(&xen_e820_table);
 
+	/*
+	 * Check whether the kernel itself conflicts with the target E820 map.
+	 * Failing now is better than running into weird problems later due
+	 * to relocating (and even reusing) pages with kernel text or data.
+	 */
+	xen_chk_is_e820_usable(__pa_symbol(_text),
+			       __pa_symbol(_end) - __pa_symbol(_text),
+			       "kernel");
+
+	/*
+	 * Check for a conflict of the xen_start_info memory with the target
+	 * E820 map.
+	 */
+	xen_chk_is_e820_usable(__pa(xen_start_info), sizeof(*xen_start_info),
+			       "xen_start_info");
+
+	/*
+	 * Check for a conflict of the hypervisor supplied page tables with
+	 * the target E820 map.
+	 */
+	xen_pt_check_e820();
+
 	max_pages = xen_get_max_pages();
 
 	/* How many extra pages do we need due to remapping? */
-	max_pages += xen_foreach_remap_area(max_pfn, xen_count_remap_pages);
+	max_pages += xen_foreach_remap_area(xen_count_remap_pages);
 
-	if (max_pages > max_pfn)
-		extra_pages += max_pages - max_pfn;
+	if (max_pages > ini_nr_pages)
+		extra_pages += max_pages - ini_nr_pages;
 
 	/*
 	 * Clamp the amount of extra memory to a EXTRA_MEM_RATIO
@@ -792,8 +888,8 @@ char * __init xen_memory_setup(void)
 	 * Make sure we have no memory above max_pages, as this area
 	 * isn't handled by the p2m management.
 	 */
-	extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
-			   extra_pages, max_pages - max_pfn);
+	maxmem_pages = EXTRA_MEM_RATIO * min(ini_nr_pages, PFN_DOWN(MAXMEM));
+	extra_pages = min3(maxmem_pages, extra_pages, max_pages - ini_nr_pages);
 	i = 0;
 	addr = xen_e820_table.entries[0].addr;
 	size = xen_e820_table.entries[0].size;
@@ -803,6 +899,9 @@ char * __init xen_memory_setup(void)
 		chunk_size = size;
 		type = xen_e820_table.entries[i].type;
 
+		if (type == E820_TYPE_RESERVED)
+			xen_pv_pci_possible = true;
+
 		if (type == E820_TYPE_RAM) {
 			if (addr < mem_end) {
 				chunk_size = min(size, mem_end - addr);
@@ -846,23 +945,6 @@ char * __init xen_memory_setup(void)
 
 	e820__update_table(e820_table);
 
-	/*
-	 * Check whether the kernel itself conflicts with the target E820 map.
-	 * Failing now is better than running into weird problems later due
-	 * to relocating (and even reusing) pages with kernel text or data.
-	 */
-	if (xen_is_e820_reserved(__pa_symbol(_text),
-			__pa_symbol(__bss_stop) - __pa_symbol(_text))) {
-		xen_raw_console_write("Xen hypervisor allocated kernel memory conflicts with E820 map\n");
-		BUG();
-	}
-
-	/*
-	 * Check for a conflict of the hypervisor supplied page tables with
-	 * the target E820 map.
-	 */
-	xen_pt_check_e820();
-
 	xen_reserve_xen_mfnlist();
 
 	/* Check for a conflict of the initrd with the target E820 map. */
@@ -890,7 +972,7 @@ char * __init xen_memory_setup(void)
 	 * Set identity map on non-RAM pages and prepare remapping the
 	 * underlying RAM.
 	 */
-	xen_foreach_remap_area(max_pfn, xen_set_identity_and_remap_chunk);
+	xen_foreach_remap_area(xen_set_identity_and_remap_chunk);
 
 	pr_info("Released %ld page(s)\n", xen_released_pages);
 
@@ -910,17 +992,9 @@ static int register_callback(unsigned type, const void *func)
 
 void xen_enable_sysenter(void)
 {
-	int ret;
-	unsigned sysenter_feature;
-
-	sysenter_feature = X86_FEATURE_SYSENTER32;
-
-	if (!boot_cpu_has(sysenter_feature))
-		return;
-
-	ret = register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat);
-	if(ret != 0)
-		setup_clear_cpu_cap(sysenter_feature);
+	if (cpu_feature_enabled(X86_FEATURE_SYSENTER32) &&
+	    register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat))
+		setup_clear_cpu_cap(X86_FEATURE_SYSENTER32);
 }
 
 void xen_enable_syscall(void)
@@ -934,22 +1008,15 @@ void xen_enable_syscall(void)
 		   mechanism for syscalls. */
 	}
 
-	if (boot_cpu_has(X86_FEATURE_SYSCALL32)) {
-		ret = register_callback(CALLBACKTYPE_syscall32,
-					xen_entry_SYSCALL_compat);
-		if (ret != 0)
-			setup_clear_cpu_cap(X86_FEATURE_SYSCALL32);
-	}
+	if (cpu_feature_enabled(X86_FEATURE_SYSCALL32) &&
+	    register_callback(CALLBACKTYPE_syscall32, xen_entry_SYSCALL_compat))
+		setup_clear_cpu_cap(X86_FEATURE_SYSCALL32);
 }
 
 static void __init xen_pvmmu_arch_setup(void)
 {
-	HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments);
 	HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_writable_pagetables);
 
-	HYPERVISOR_vm_assist(VMASST_CMD_enable,
-			     VMASST_TYPE_pae_extended_cr3);
-
 	if (register_callback(CALLBACKTYPE_event,
 			      xen_asm_exc_xen_hypervisor_callback) ||
 	    register_callback(CALLBACKTYPE_failsafe, xen_failsafe_callback))