Basic infrastructure patches for a paravirtualized kernel

diff -r 521d1bcdaa86 -r 79a98a10911f include/linux/mm.h
@@ -1026,6 +1026,11 @@ struct page *follow_page(struct vm_area_
 #define FOLL_GET	0x04	/* do get_page on page */
 #define FOLL_ANON	0x08	/* give ZERO_PAGE if no pgtable */
 
+typedef int (*pte_fn_t)(pte_t *pte, struct page *pmd_page, unsigned long addr,
+			void *data);
+extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
+			       unsigned long size, pte_fn_t fn, void *data);
+
 #ifdef CONFIG_PROC_FS
 void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
 #else

100 lines not on this page · raw message

diff -r 79a98a10911f -r ffccb62e9244 arch/i386/kernel/reboot.c
@@ -145,14 +145,10 @@ real_mode_gdt_entries [3] =
 	0x000092000100ffffULL	/* 16-bit real-mode 64k data at 0x00000100 */
 };
 
-static struct
-{
-	unsigned short       size __attribute__ ((packed));
-	unsigned long long * base __attribute__ ((packed));
-}
-real_mode_gdt = { sizeof (real_mode_gdt_entries) - 1, real_mode_gdt_entries },
-real_mode_idt = { 0x3ff, NULL },
-no_idt = { 0, NULL };
+static struct Xgt_desc_struct
+real_mode_gdt = { sizeof (real_mode_gdt_entries) - 1, (long)real_mode_gdt_entries },
+real_mode_idt = { 0x3ff, 0 },
+no_idt = { 0, 0 };
 
 
 /* This is 16-bit protected mode code to disable paging and the cache,

diff -r ffccb62e9244 -r 85e7eadfaea1 include/asm-i386/system.h
@@ -261,6 +261,9 @@ static inline unsigned long __xchg(unsig
 #define cmpxchg(ptr,o,n)\
 	((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
 					(unsigned long)(n),sizeof(*(ptr))))
+#define sync_cmpxchg(ptr,o,n)\
+	((__typeof__(*(ptr)))__sync_cmpxchg((ptr),(unsigned long)(o),\
+					(unsigned long)(n),sizeof(*(ptr))))
 #endif
 
 static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,

@@ -282,6 +285,39 @@ static inline unsigned long __cmpxchg(vo
 		return prev;
 	case 4:
 		__asm__ __volatile__(LOCK_PREFIX "cmpxchgl %1,%2"
+				     : "=a"(prev)
+				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	}
+	return old;
+}
+
+/*
+ * Always use locked operations when touching memory shared with a
+ * hypervisor, since the system may be SMP even if the guest kernel
+ * isn't.
+ */
+static inline unsigned long __sync_cmpxchg(volatile void *ptr,
+					    unsigned long old,
+					    unsigned long new, int size)
+{
+	unsigned long prev;
+	switch (size) {
+	case 1:
+		__asm__ __volatile__("lock; cmpxchgb %b1,%2"
+				     : "=a"(prev)
+				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 2:
+		__asm__ __volatile__("lock; cmpxchgw %w1,%2"
+				     : "=a"(prev)
+				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 4:
+		__asm__ __volatile__("lock; cmpxchgl %1,%2"
 				     : "=a"(prev)
 				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
 				     : "memory");

156 lines not on this page · raw message

diff -r 85e7eadfaea1 -r cf6767d9babb arch/i386/kernel/process.c
@@ -346,7 +346,7 @@ int kernel_thread(int (*fn)(void *), voi
 	regs.xes = __USER_DS;
 	regs.orig_eax = -1;
 	regs.eip = (unsigned long) kernel_thread_helper;
-	regs.xcs = __KERNEL_CS;
+	regs.xcs = __KERNEL_CS | get_kernel_rpl();
 	regs.eflags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2;
 
 	/* Ok, create the new process.. */

diff -r 85e7eadfaea1 -r cf6767d9babb arch/i386/mm/extable.c
@@ -11,7 +11,7 @@ int fixup_exception(struct pt_regs *regs
 	const struct exception_table_entry *fixup;
 
 #ifdef CONFIG_PNPBIOS
-	if (unlikely((regs->xcs & ~15) == (GDT_ENTRY_PNPBIOS_BASE << 3)))
+	if (unlikely(SEGMENT_IS_PNP_CODE(regs->xcs)))
 	{
 		extern u32 pnp_bios_fault_eip, pnp_bios_fault_esp;
 		extern u32 pnp_bios_is_utter_crap;

diff -r 85e7eadfaea1 -r cf6767d9babb arch/i386/mm/fault.c
@@ -27,6 +27,7 @@
 #include <asm/uaccess.h>
 #include <asm/desc.h>
 #include <asm/kdebug.h>
+#include <asm/segment.h>
 
 extern void die(const char *,struct pt_regs *,long);
 

@@ -119,10 +120,10 @@ static inline unsigned long get_segment_
 	}
 
 	/* The standard kernel/user address space limit. */
-	*eip_limit = (seg & 3) ? USER_DS.seg : KERNEL_DS.seg;
+	*eip_limit = user_mode(regs) ? USER_DS.seg : KERNEL_DS.seg;
 	
 	/* By far the most common cases. */
-	if (likely(seg == __USER_CS || seg == __KERNEL_CS))
+	if (likely(SEGMENT_IS_FLAT_CODE(seg)))
 		return eip;
 
 	/* Check the segment exists, is within the current LDT/GDT size,

@@ -436,11 +437,7 @@ good_area:
 	write = 0;
 	switch (error_code & 3) {
 		default:	/* 3: write, present */
-#ifdef TEST_VERIFY_AREA
-			if (regs->cs == KERNEL_CS)
-				printk("WP fault at %08lx\n", regs->eip);
-#endif
-			/* fall through */
+				/* fall through */
 		case 2:		/* write, not present */
 			if (!(vma->vm_flags & VM_WRITE))
 				goto bad_area;

diff -r 85e7eadfaea1 -r cf6767d9babb include/asm-i386/ptrace.h
@@ -60,6 +60,7 @@ struct pt_regs {
 #ifdef __KERNEL__
 
 #include <asm/vm86.h>
+#include <asm/segment.h>
 
 struct task_struct;
 extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code);

@@ -73,11 +74,11 @@ extern void send_sigtrap(struct task_str
  */
 static inline int user_mode(struct pt_regs *regs)
 {
-	return (regs->xcs & 3) != 0;
+	return (regs->xcs & SEGMENT_RPL_MASK) == 3;
 }
 static inline int user_mode_vm(struct pt_regs *regs)
 {
-	return ((regs->xcs & 3) | (regs->eflags & VM_MASK)) != 0;
+	return (((regs->xcs & SEGMENT_RPL_MASK) | (regs->eflags & VM_MASK)) >= 3);
 }
 #define instruction_pointer(regs) ((regs)->eip)
 #if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER)

diff -r 85e7eadfaea1 -r cf6767d9babb include/asm-i386/segment.h
@@ -83,6 +83,12 @@
 
 #define GDT_SIZE (GDT_ENTRIES * 8)
 
+/*
+ * Some tricky tests to match code segments after a fault
+ */
+#define SEGMENT_IS_FLAT_CODE(x)  (((x) & 0xec) == GDT_ENTRY_KERNEL_CS * 8)
+#define SEGMENT_IS_PNP_CODE(x)   (((x) & 0xf4) == GDT_ENTRY_PNPBIOS_BASE * 8)
+
 /* Simple and small GDT entries for booting only */
 
 #define GDT_ENTRY_BOOT_CS		2

@@ -112,4 +118,8 @@
  */
 #define IDT_ENTRIES 256
 
+/* Bottom three bits of xcs give the ring privilege level */
+#define SEGMENT_RPL_MASK 0x3
+
+#define get_kernel_rpl()  0
 #endif

diff -r cf6767d9babb -r 09b35e6bc0ca include/asm-i386/spinlock.h
@@ -16,6 +16,9 @@
  *
  * (the type definitions are in asm/spinlock_types.h)
  */
+
+#define CLI_STRING	"cli"
+#define STI_STRING	"sti"
 
 #define __raw_spin_is_locked(x) \
 		(*(volatile signed char *)(&(x)->slock) <= 0)

@@ -43,12 +46,12 @@
 	"2:\t" \
 	"testl $0x200, %1\n\t" \
 	"jz 4f\n\t" \
-	"sti\n" \
+	STI_STRING "\n" \
 	"3:\t" \
 	"rep;nop\n\t" \
 	"cmpb $0, %0\n\t" \
 	"jle 3b\n\t" \
-	"cli\n\t" \
+	CLI_STRING "\n\t" \
 	"jmp 1b\n" \
 	"4:\t" \
 	"rep;nop\n\t" \

diff -r 09b35e6bc0ca -r 730b4fe6bc1e include/asm-i386/processor.h
@@ -143,31 +143,37 @@ static inline void detect_ht(struct cpui
 #define X86_EFLAGS_VIP	0x00100000 /* Virtual Interrupt Pending */
 #define X86_EFLAGS_ID	0x00200000 /* CPUID detection flag */
 
-/*
- * Generic CPUID function
- * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx
- * resulting in stale register contents being returned.
- */
-static inline void cpuid(unsigned int op, unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx)
-{
+static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
+			   unsigned int *ecx, unsigned int *edx)
+{
+	/* ecx is often an input as well as an output. */
 	__asm__("cpuid"
 		: "=a" (*eax),
 		  "=b" (*ebx),
 		  "=c" (*ecx),
 		  "=d" (*edx)
-		: "0" (op), "c"(0));
+		: "0" (*eax), "2" (*ecx));
+}
+
+/*
+ * Generic CPUID function
+ * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx
+ * resulting in stale register contents being returned.
+ */
+static inline void cpuid(unsigned int op, unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx)
+{
+	*eax = op;
+	*ecx = 0;
+	__cpuid(eax, ebx, ecx, edx);
 }
 
 /* Some CPUID calls want 'count' to be placed in ecx */
 static inline void cpuid_count(int op, int count, int *eax, int *ebx, int *ecx,
-	       	int *edx)
-{
-	__asm__("cpuid"
-		: "=a" (*eax),
-		  "=b" (*ebx),
-		  "=c" (*ecx),
-		  "=d" (*edx)
-		: "0" (op), "c" (count));
+			       int *edx)
+{
+	*eax = op;
+	*ecx = count;
+	__cpuid(eax, ebx, ecx, edx);
 }
 
 /*

@@ -175,42 +181,30 @@ static inline void cpuid_count(int op, i
  */
 static inline unsigned int cpuid_eax(unsigned int op)
 {
-	unsigned int eax;
-
-	__asm__("cpuid"
-		: "=a" (eax)
-		: "0" (op)
-		: "bx", "cx", "dx");
+	unsigned int eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
 	return eax;
 }
 static inline unsigned int cpuid_ebx(unsigned int op)
 {
-	unsigned int eax, ebx;
-
-	__asm__("cpuid"
-		: "=a" (eax), "=b" (ebx)
-		: "0" (op)
-		: "cx", "dx" );
+	unsigned int eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
 	return ebx;
 }
 static inline unsigned int cpuid_ecx(unsigned int op)
 {
-	unsigned int eax, ecx;
-
-	__asm__("cpuid"
-		: "=a" (eax), "=c" (ecx)
-		: "0" (op)
-		: "bx", "dx" );
+	unsigned int eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
 	return ecx;
 }
 static inline unsigned int cpuid_edx(unsigned int op)
 {
-	unsigned int eax, edx;
-
-	__asm__("cpuid"
-		: "=a" (eax), "=d" (edx)
-		: "0" (op)
-		: "bx", "cx");
+	unsigned int eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
 	return edx;
 }

48 lines not on this page · raw message

diff -r 730b4fe6bc1e -r b6c100bb5ca5 arch/i386/mm/pgtable.c
@@ -12,6 +12,7 @@
 #include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/spinlock.h>
+#include <linux/module.h>
 
 #include <asm/system.h>
 #include <asm/pgtable.h>

@@ -137,6 +138,12 @@ void set_pmd_pfn(unsigned long vaddr, un
 	__flush_tlb_one(vaddr);
 }
 
+static int fixmaps = 0;
+#ifndef CONFIG_COMPAT_VDSO
+unsigned long __FIXADDR_TOP = 0xfffff000;
+EXPORT_SYMBOL(__FIXADDR_TOP);
+#endif
+
 void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t flags)
 {
 	unsigned long address = __fix_to_virt(idx);

@@ -146,6 +153,17 @@ void __set_fixmap (enum fixed_addresses 
 		return;
 	}
 	set_pte_pfn(address, phys >> PAGE_SHIFT, flags);
+	fixmaps++;
+}
+
+void set_fixaddr_top(unsigned long top)
+{
+	BUG_ON(fixmaps > 0);
+#ifdef CONFIG_COMPAT_VDSO
+	BUG_ON(top - PAGE_SIZE != __FIXADDR_TOP);
+#else
+	__FIXADDR_TOP = top - PAGE_SIZE;
+#endif
 }
 
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)

diff -r 730b4fe6bc1e -r b6c100bb5ca5 include/asm-i386/fixmap.h
@@ -19,7 +19,11 @@
  * Leave one empty page between vmalloc'ed areas and
  * the start of the fixmap.
  */
-#define __FIXADDR_TOP	0xfffff000
+#ifndef CONFIG_COMPAT_VDSO
+extern unsigned long __FIXADDR_TOP;
+#else
+#define __FIXADDR_TOP  0xfffff000
+#endif
 
 #ifndef __ASSEMBLY__
 #include <linux/kernel.h>

@@ -93,6 +97,7 @@ enum fixed_addresses {
 
 extern void __set_fixmap (enum fixed_addresses idx,
 					unsigned long phys, pgprot_t flags);
+extern void set_fixaddr_top(unsigned long top);
 
 #define set_fixmap(idx, phys) \
 		__set_fixmap(idx, phys, PAGE_KERNEL)

diff -r 730b4fe6bc1e -r b6c100bb5ca5 include/asm-i386/page.h
@@ -122,7 +122,7 @@ extern int page_is_ram(unsigned long pag
 
 #define PAGE_OFFSET		((unsigned long)__PAGE_OFFSET)
 #define VMALLOC_RESERVE		((unsigned long)__VMALLOC_RESERVE)
-#define MAXMEM			(-__PAGE_OFFSET-__VMALLOC_RESERVE)
+#define MAXMEM			(__FIXADDR_TOP-__PAGE_OFFSET-__VMALLOC_RESERVE)
 #define __pa(x)			((unsigned long)(x)-PAGE_OFFSET)
 #define __va(x)			((void *)((unsigned long)(x)+PAGE_OFFSET))
 #define pfn_to_kaddr(pfn)      __va((pfn) << PAGE_SHIFT)

diff -r b6c100bb5ca5 -r 0adfc39039c7 arch/i386/kernel/setup.c
@@ -917,6 +917,19 @@ static void __init parse_cmdline_early (
 		else if (!memcmp(from, "vmalloc=", 8))
 			__VMALLOC_RESERVE = memparse(from+8, &from);
 
+		/*
+		 * reservedtop=size reserves a hole at the top of the kernel
+		 * address space which a hypervisor can load into later.
+		 * Needed for dynamically loaded hypervisors, so relocating
+		 * the fixmap can be done before paging initialization.
+		 * This hole must be a multiple of 4M.
+		 */
+		else if (!memcmp(from, "reservedtop=", 12)) {
+			unsigned long reserved = memparse(from+12, &from);
+			reserved &= ~0x3fffff;
+			set_fixaddr_top(-reserved);
+		}
+
 	next_char:
 		c = *(from++);
 		if (!c)

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/arch/i386/kernel/machine_kexec.c working-2.6.18-rc2-mm1-i386-parse_early_param/arch/i386/kernel/machine_kexec.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/kexec.h>
 #include <linux/delay.h>
+#include <linux/init.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>

@@ -209,3 +210,25 @@ NORET_TYPE void machine_kexec(struct kim
 	rnk = (relocate_new_kernel_t) reboot_code_buffer;
 	(*rnk)(page_list, reboot_code_buffer, image->start, cpu_has_pae);
 }
+
+/* crashkernel=size@addr specifies the location to reserve for
+ * a crash kernel.  By reserving this memory we guarantee
+ * that linux never sets it up as a DMA target.
+ * Useful for holding code to do something appropriate
+ * after a kernel panic.
+ */
+static int __init parse_crashkernel(char *arg)
+{
+	unsigned long size, base;
+	size = memparse(arg, &arg);
+	if (*arg == '@') {
+		base = memparse(arg+1, &arg);
+		/* FIXME: Do I want a sanity check
+		 * to validate the memory range?
+		 */
+		crashk_res.start = base;
+		crashk_res.end   = base + size - 1;
+	}
+	return 0;
+}
+early_param("crashkernel", parse_crashkernel);

464 lines not on this page · raw message

78 lines not on this page · raw message

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/arch/i386/mm/init.c working-2.6.18-rc2-mm1-i386-parse_early_param/arch/i386/mm/init.c
@@ -435,7 +435,7 @@ u64 __supported_pte_mask __read_mostly =
  * on      Enable
  * off     Disable
  */
-void __init noexec_setup(const char *str)
+static int __init noexec_setup(char *str)
 {
 	if (!strncmp(str, "on",2) && cpu_has_nx) {
 		__supported_pte_mask |= _PAGE_NX;

@@ -444,7 +444,9 @@ void __init noexec_setup(const char *str
 		disable_nx = 1;
 		__supported_pte_mask &= ~_PAGE_NX;
 	}
+	return 0;
 }
+early_param("noexec", noexec_setup);
 
 int nx_enabled = 0;
 #ifdef CONFIG_X86_PAE

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/include/asm-i386/apic.h working-2.6.18-rc2-mm1-i386-parse_early_param/include/asm-i386/apic.h
@@ -42,6 +42,8 @@ static inline void lapic_enable(void)
 	} while (0)
 
 
+extern void generic_apic_probe(void);
+
 #ifdef CONFIG_X86_LOCAL_APIC
 
 /*

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/include/asm-i386/pgtable.h working-2.6.18-rc2-mm1-i386-parse_early_param/include/asm-i386/pgtable.h
@@ -391,8 +391,6 @@ extern pte_t *lookup_address(unsigned lo
  static inline int set_kernel_exec(unsigned long vaddr, int enable) { return 0;}
 #endif
 
-extern void noexec_setup(const char *str);
-
 #if defined(CONFIG_HIGHPTE)
 #define pte_offset_map(dir, address) \
 	((pte_t *)kmap_atomic(pmd_page(*(dir)),KM_PTE0) + pte_index(address))

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/init/main.c working-2.6.18-rc2-mm1-i386-parse_early_param/init/main.c
@@ -182,16 +182,19 @@ extern struct obs_kernel_param __setup_s
 static int __init obsolete_checksetup(char *line)
 {
 	struct obs_kernel_param *p;
+	int had_early_param = 0;
 
 	p = __setup_start;
 	do {
 		int n = strlen(p->str);
 		if (!strncmp(line, p->str, n)) {
 			if (p->early) {
-				/* Already done in parse_early_param?  (Needs
-				 * exact match on param part) */
+				/* Already done in parse_early_param?
+				 * (Needs exact match on param part).
+				 * Keep iterating, as we can have early
+				 * params and __setups of same names 8( */
 				if (line[n] == '\0' || line[n] == '=')
-					return 1;
+					had_early_param = 1;
 			} else if (!p->setup_func) {
 				printk(KERN_WARNING "Parameter %s is obsolete,"
 				       " ignored\n", p->str);

@@ -201,7 +204,8 @@ static int __init obsolete_checksetup(ch
 		}
 		p++;
 	} while (p < __setup_end);
-	return 0;
+
+	return had_early_param;
 }
 
 /*

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/arch/i386/kernel/acpi/boot.c working-2.6.18-rc2-mm1-i386-parse_early_param/arch/i386/kernel/acpi/boot.c
@@ -1216,3 +1216,57 @@ int __init acpi_boot_init(void)
 
 	return 0;
 }
+
+static int __init parse_acpi(char *arg)
+{
+	if (!arg)
+		return -EINVAL;
+
+	/* "acpi=off" disables both ACPI table parsing and interpreter */
+	if (strcmp(arg, "off") == 0) {
+		disable_acpi();
+	} 
+	/* acpi=force to over-ride black-list */
+	else if (strcmp(arg, "force") == 0) {
+		acpi_force = 1;
+		acpi_ht = 1;
+		acpi_disabled = 0;
+	}
+	/* acpi=strict disables out-of-spec workarounds */
+	else if (strcmp(arg, "strict") == 0) {
+		acpi_strict = 1;
+	}
+	/* Limit ACPI just to boot-time to enable HT */
+	else if (strcmp(arg, "ht") == 0) {
+		if (!acpi_force)
+			disable_acpi();
+		acpi_ht = 1;
+	}
+	/* "acpi=noirq" disables ACPI interrupt routing */
+	else if (strcmp(arg, "noirq") == 0) {
+		acpi_noirq_set();
+	} else {
+		/* Core will printk when we return error. */
+		return -EINVAL;
+	}
+	return 0;
+}
+early_param("acpi", parse_acpi);
+
+/* FIXME: Using pci= for an ACPI parameter is a travesty. */
+static int __init parse_pci(char *arg)
+{
+	if (arg && strcmp(arg, "noacpi") == 0)
+		acpi_disable_pci();
+	return 0;
+}
+early_param("pci", parse_pci);
+
+#ifdef CONFIG_X86_IO_APIC
+static int __init parse_acpi_skip_timer_override(char *arg)
+{
+	acpi_skip_timer_override = 1;
+	return 0;
+}
+early_param("acpi_skip_timer_override", parse_acpi_skip_timer_override);
+#endif /* CONFIG_X86_IO_APIC */

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/arch/i386/kernel/apic.c working-2.6.18-rc2-mm1-i386-parse_early_param/arch/i386/kernel/apic.c
@@ -1372,3 +1372,18 @@ int __init APIC_init_uniprocessor (void)
 
 	return 0;
 }
+
+static int __init parse_lapic(char *arg)
+{
+	lapic_enable();
+	return 0;
+}
+early_param("lapic", parse_lapic);
+
+static int __init parse_nolapic(char *arg)
+{
+	lapic_disable();
+	return 0;
+}
+early_param("nolapic", parse_nolapic);
+

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/arch/i386/kernel/io_apic.c working-2.6.18-rc2-mm1-i386-parse_early_param/arch/i386/kernel/io_apic.c
@@ -69,7 +69,7 @@ int sis_apic_bug = -1;
  */
 int nr_ioapic_registers[MAX_IO_APICS];
 
-int disable_timer_pin_1 __initdata;
+static int disable_timer_pin_1 __initdata;
 
 /*
  * Rough estimation of how many shared IRQs there are, can

@@ -2767,3 +2767,25 @@ int io_apic_set_pci_routing (int ioapic,
 }
 
 #endif /* CONFIG_ACPI */
+
+static int __init parse_disable_timer_pin_1(char *arg)
+{
+	disable_timer_pin_1 = 1;
+	return 0;
+}
+early_param("disable_timer_pin_1", parse_disable_timer_pin_1);
+
+static int __init parse_enable_timer_pin_1(char *arg)
+{
+	disable_timer_pin_1 = -1;
+	return 0;
+}
+early_param("enable_timer_pin_1", parse_enable_timer_pin_1);
+
+static int __init parse_noapic(char *arg)
+{
+	/* disable IO-APIC */
+	disable_ioapic_setup();
+	return 0;
+}
+early_param("noapic", parse_noapic);

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/arch/i386/kernel/machine_kexec.c working-2.6.18-rc2-mm1-i386-parse_early_param/arch/i386/kernel/machine_kexec.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/kexec.h>
 #include <linux/delay.h>
+#include <linux/init.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>

@@ -209,3 +210,25 @@ NORET_TYPE void machine_kexec(struct kim
 	rnk = (relocate_new_kernel_t) reboot_code_buffer;
 	(*rnk)(page_list, reboot_code_buffer, image->start, cpu_has_pae);
 }
+
+/* crashkernel=size@addr specifies the location to reserve for
+ * a crash kernel.  By reserving this memory we guarantee
+ * that linux never sets it up as a DMA target.
+ * Useful for holding code to do something appropriate
+ * after a kernel panic.
+ */
+static int __init parse_crashkernel(char *arg)
+{
+	unsigned long size, base;
+	size = memparse(arg, &arg);
+	if (*arg == '@') {
+		base = memparse(arg+1, &arg);
+		/* FIXME: Do I want a sanity check
+		 * to validate the memory range?
+		 */
+		crashk_res.start = base;
+		crashk_res.end   = base + size - 1;
+	}
+	return 0;
+}
+early_param("crashkernel", parse_crashkernel);

387 lines not on this page · raw message

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/arch/i386/kernel/smpboot.c working-2.6.18-rc2-mm1-i386-parse_early_param/arch/i386/kernel/smpboot.c
@@ -1490,3 +1490,16 @@ void __init smp_intr_init(void)
 	/* IPI for generic function call */
 	set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
 }
+
+/*
+ * If the BIOS enumerates physical processors before logical,
+ * maxcpus=N at enumeration-time can be used to disable HT.
+ */
+static int __init parse_maxcpus(char *arg)
+{
+	extern unsigned int maxcpus;
+
+	maxcpus = simple_strtoul(arg, NULL, 0);
+	return 0;
+}
+early_param("maxcpus", parse_maxcpus);

81 lines not on this page · raw message

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/arch/i386/mm/init.c working-2.6.18-rc2-mm1-i386-parse_early_param/arch/i386/mm/init.c
@@ -435,16 +435,22 @@ u64 __supported_pte_mask __read_mostly =
  * on      Enable
  * off     Disable
  */
-void __init noexec_setup(const char *str)
+static int __init noexec_setup(char *str)
 {
-	if (!strncmp(str, "on",2) && cpu_has_nx) {
-		__supported_pte_mask |= _PAGE_NX;
-		disable_nx = 0;
-	} else if (!strncmp(str,"off",3)) {
+	if (!str || !strcmp(str, "on")) {
+		if (cpu_has_nx) {
+			__supported_pte_mask |= _PAGE_NX;
+			disable_nx = 0;
+		}
+	} else if (!strcmp(str,"off")) {
 		disable_nx = 1;
 		__supported_pte_mask &= ~_PAGE_NX;
-	}
+	} else
+		return -EINVAL;
+
+	return 0;
 }
+early_param("noexec", noexec_setup);
 
 int nx_enabled = 0;
 #ifdef CONFIG_X86_PAE

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/include/asm-i386/acpi.h working-2.6.18-rc2-mm1-i386-parse_early_param/include/asm-i386/acpi.h
@@ -131,21 +131,7 @@ static inline void disable_acpi(void) 
 extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
 
 #ifdef CONFIG_X86_IO_APIC
-extern int skip_ioapic_setup;
 extern int acpi_skip_timer_override;
-
-static inline void disable_ioapic_setup(void)
-{
-	skip_ioapic_setup = 1;
-}
-
-static inline int ioapic_setup_disabled(void)
-{
-	return skip_ioapic_setup;
-}
-
-#else
-static inline void disable_ioapic_setup(void) { }
 #endif
 
 static inline void acpi_noirq_set(void) { acpi_noirq = 1; }

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/include/asm-i386/apic.h working-2.6.18-rc2-mm1-i386-parse_early_param/include/asm-i386/apic.h
@@ -42,6 +42,8 @@ static inline void lapic_enable(void)
 	} while (0)
 
 
+extern void generic_apic_probe(void);
+
 #ifdef CONFIG_X86_LOCAL_APIC
 
 /*

@@ -117,8 +119,6 @@ extern void enable_APIC_timer(void);
 
 extern void enable_NMI_through_LVT0 (void * dummy);
 
-extern int disable_timer_pin_1;
-
 void smp_send_timer_broadcast_ipi(struct pt_regs *regs);
 void switch_APIC_timer_to_ipi(void *cpumask);
 void switch_ipi_to_APIC_timer(void *cpumask);

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/include/asm-i386/io_apic.h working-2.6.18-rc2-mm1-i386-parse_early_param/include/asm-i386/io_apic.h
@@ -148,6 +148,16 @@ static inline void io_apic_modify(unsign
 /* 1 if "noapic" boot option passed */
 extern int skip_ioapic_setup;
 
+static inline void disable_ioapic_setup(void)
+{
+	skip_ioapic_setup = 1;
+}
+
+static inline int ioapic_setup_disabled(void)
+{
+	return skip_ioapic_setup;
+}
+
 /*
  * If we use the IO-APIC for IRQ routing, disable automatic
  * assignment of PCI IRQ's.

@@ -166,6 +176,7 @@ extern int (*ioapic_renumber_irq)(int io
 
 #else  /* !CONFIG_X86_IO_APIC */
 #define io_apic_assign_pci_irqs 0
+static inline void disable_ioapic_setup(void) { }
 #endif
 
 #endif

diff -urpN --exclude TAGS -X /home/rusty/devel/kernel/kernel-patches/current-dontdiff --minimal linux-2.6.18-rc2-mm1/include/asm-i386/pgtable.h working-2.6.18-rc2-mm1-i386-parse_early_param/include/asm-i386/pgtable.h
@@ -391,8 +391,6 @@ extern pte_t *lookup_address(unsigned lo
  static inline int set_kernel_exec(unsigned long vaddr, int enable) { return 0;}
 #endif
 
-extern void noexec_setup(const char *str);
-
 #if defined(CONFIG_HIGHPTE)
 #define pte_offset_map(dir, address) \
 	((pte_t *)kmap_atomic(pmd_page(*(dir)),KM_PTE0) + pte_index(address))

diff -r 0adfc39039c7 -r 20f9c0c451af mm/memory.c
@@ -466,7 +466,7 @@ copy_one_pte(struct mm_struct *dst_mm, s
 	 */
 	if (is_cow_mapping(vm_flags)) {
 		ptep_set_wrprotect(src_mm, addr, src_pte);
-		pte = *src_pte;
+		pte = pte_wrprotect(pte);
 	}
 
 	/*

diff -r 20f9c0c451af -r 553154516a1b include/asm-generic/pgtable.h
@@ -110,8 +110,8 @@ do {				  					  \
 })
 #endif
 
-#ifndef __HAVE_ARCH_PTE_CLEAR_FULL
-#define pte_clear_full(__mm, __address, __ptep, __full)			\
+#ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL
+#define pte_clear_not_present_full(__mm, __address, __ptep, __full)	\
 do {									\
 	pte_clear((__mm), (__address), (__ptep));			\
 } while (0)

diff -r 20f9c0c451af -r 553154516a1b mm/fremap.c
@@ -39,7 +39,7 @@ static int zap_pte(struct mm_struct *mm,
 	} else {
 		if (!pte_file(pte))
 			free_swap_and_cache(pte_to_swp_entry(pte));
-		pte_clear(mm, addr, ptep);
+		pte_clear_not_present_full(mm, addr, ptep, 0);
 	}
 	return !!page;
 }

diff -r 20f9c0c451af -r 553154516a1b mm/memory.c
@@ -689,7 +689,7 @@ static unsigned long zap_pte_range(struc
 			continue;
 		if (!pte_file(ptent))
 			free_swap_and_cache(pte_to_swp_entry(ptent));
-		pte_clear_full(mm, addr, pte, tlb->fullmm);
+		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
 	} while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0));
 
 	add_mm_rss(mm, file_rss, anon_rss);

diff -r 553154516a1b -r 398f8fd6b334 include/asm-generic/pgtable.h
@@ -164,6 +164,26 @@ static inline void ptep_set_wrprotect(st
 #endif
 
 /*
+ * A facility to provide lazy MMU batching.  This allows PTE updates and
+ * page invalidations to be delayed until a call to leave lazy MMU mode
+ * is issued.  Some architectures may benefit from doing this, and it is
+ * beneficial for both shadow and direct mode hypervisors, which may batch
+ * the PTE updates which happen during this window.  Note that using this
+ * interface requires that read hazards be removed from the code.  A read
+ * hazard could result in the direct mode hypervisor case, since the actual
+ * write to the page tables may not yet have taken place, so reads though
+ * a raw PTE pointer after it has been modified are not guaranteed to be
+ * up to date.  This mode can only be entered and left under the protection of
+ * the page table locks for all page tables which may be modified.  In the UP
+ * case, this is required so that preemption is disabled, and in the SMP case,
+ * it must synchronize the delayed page table writes properly on other CPUs.
+ */
+#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE
+#define arch_enter_lazy_mmu_mode()	do {} while (0)
+#define arch_leave_lazy_mmu_mode()	do {} while (0)
+#endif
+
+/*
  * When walking page tables, get the address of the next boundary,
  * or the end address of the range if that comes earlier.  Although no
  * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout.

diff -r 553154516a1b -r 398f8fd6b334 mm/memory.c
@@ -505,6 +505,7 @@ again:
 	src_pte = pte_offset_map_nested(src_pmd, addr);
 	src_ptl = pte_lockptr(src_mm, src_pmd);
 	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
+	arch_enter_lazy_mmu_mode();
 
 	do {
 		/*

@@ -526,6 +527,7 @@ again:
 		progress += 8;
 	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
 
+	arch_leave_lazy_mmu_mode();
 	spin_unlock(src_ptl);
 	pte_unmap_nested(src_pte - 1);
 	add_mm_rss(dst_mm, rss[0], rss[1]);

@@ -627,6 +629,7 @@ static unsigned long zap_pte_range(struc
 	int anon_rss = 0;
 
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	arch_enter_lazy_mmu_mode();
 	do {
 		pte_t ptent = *pte;
 		if (pte_none(ptent)) {

@@ -693,6 +696,7 @@ static unsigned long zap_pte_range(struc
 	} while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0));
 
 	add_mm_rss(mm, file_rss, anon_rss);
+	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
 
 	return addr;

@@ -1108,6 +1112,7 @@ static int zeromap_pte_range(struct mm_s
 	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (!pte)
 		return -ENOMEM;
+	arch_enter_lazy_mmu_mode();
 	do {
 		struct page *page = ZERO_PAGE(addr);
 		pte_t zero_pte = pte_wrprotect(mk_pte(page, prot));

@@ -1117,6 +1122,7 @@ static int zeromap_pte_range(struct mm_s
 		BUG_ON(!pte_none(*pte));
 		set_pte_at(mm, addr, pte, zero_pte);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
+	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
 	return 0;
 }

@@ -1269,11 +1275,13 @@ static int remap_pte_range(struct mm_str
 	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (!pte)
 		return -ENOMEM;
+	arch_enter_lazy_mmu_mode();
 	do {
 		BUG_ON(!pte_none(*pte));
 		set_pte_at(mm, addr, pte, pfn_pte(pfn, prot));
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
+	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
 	return 0;
 }

diff -r 553154516a1b -r 398f8fd6b334 mm/mprotect.c
@@ -33,6 +33,7 @@ static void change_pte_range(struct mm_s
 	spinlock_t *ptl;
 
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	arch_enter_lazy_mmu_mode();
 	do {
 		oldpte = *pte;
 		if (pte_present(oldpte)) {

@@ -62,6 +63,7 @@ static void change_pte_range(struct mm_s
 		}
 
 	} while (pte++, addr += PAGE_SIZE, addr != end);
+	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
 }
 

diff -r 553154516a1b -r 398f8fd6b334 mm/mremap.c
@@ -98,6 +98,7 @@ static void move_ptes(struct vm_area_str
 	new_ptl = pte_lockptr(mm, new_pmd);
 	if (new_ptl != old_ptl)
 		spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
+	arch_enter_lazy_mmu_mode();
 
 	for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE,
 				   new_pte++, new_addr += PAGE_SIZE) {

@@ -109,6 +110,7 @@ static void move_ptes(struct vm_area_str
 		set_pte_at(mm, new_addr, new_pte, pte);
 	}
 
+	arch_leave_lazy_mmu_mode();
 	if (new_ptl != old_ptl)
 		spin_unlock(new_ptl);
 	pte_unmap_nested(new_pte - 1);

diff -r 553154516a1b -r 398f8fd6b334 mm/msync.c
@@ -30,6 +30,7 @@ static unsigned long msync_pte_range(str
 
 again:
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	arch_enter_lazy_mmu_mode();
 	do {
 		struct page *page;
 

@@ -51,6 +52,7 @@ again:
 			ret += set_page_dirty(page);
 		progress += 3;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
+	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
 	cond_resched();
 	if (addr != end)

diff -r 398f8fd6b334 -r 8235caea9d68 arch/i386/mm/pgtable.c
@@ -275,9 +275,10 @@ out_oom:
 	return NULL;
 }
 
-void pgd_free(pgd_t *pgd)
+void pgd_free(struct mm_struct *mm)
 {
 	int i;
+	pgd_t *pgd = mm->pgd;
 
 	/* in the PAE case user pgd entries are overwritten before usage */
 	if (PTRS_PER_PMD > 1)

diff -r 398f8fd6b334 -r 8235caea9d68 include/asm-i386/pgalloc.h
@@ -3,7 +3,6 @@
 
 #include <asm/fixmap.h>
 #include <linux/threads.h>
-#include <linux/mm.h>		/* for struct page */
 
 #define pmd_populate_kernel(mm, pmd, pte) \
 		set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte)))

@@ -16,7 +15,8 @@
  * Allocate and free page tables.
  */
 extern pgd_t *pgd_alloc(struct mm_struct *);
-extern void pgd_free(pgd_t *pgd);
+extern void pgd_free(struct mm_struct *);
+#define pgd_free_mm(mm) pgd_free(mm)
 
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
 extern struct page *pte_alloc_one(struct mm_struct *, unsigned long);

diff -r 398f8fd6b334 -r 8235caea9d68 include/asm-i386/pgtable.h
@@ -393,6 +393,7 @@ extern pte_t *lookup_address(unsigned lo
 
 extern void noexec_setup(const char *str);
 
+#include <asm/pgalloc.h>
 #if defined(CONFIG_HIGHPTE)
 #define pte_offset_map(dir, address) \
 	((pte_t *)kmap_atomic(pmd_page(*(dir)),KM_PTE0) + pte_index(address))

diff -r 398f8fd6b334 -r 8235caea9d68 include/linux/mm.h
@@ -1077,5 +1077,9 @@ extern int randomize_va_space;
 
 const char *arch_vma_name(struct vm_area_struct *vma);
 
+#ifndef pgd_free_mm
+#define pgd_free_mm(mm) pgd_free((mm)->pgd)
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */

diff -r 398f8fd6b334 -r 8235caea9d68 kernel/fork.c
@@ -299,7 +299,7 @@ static inline int mm_alloc_pgd(struct mm
 
 static inline void mm_free_pgd(struct mm_struct * mm)
 {
-	pgd_free(mm->pgd);
+	pgd_free_mm(mm);
 }
 #else
 #define dup_mmap(mm, oldmm)	(0)

diff -r 8235caea9d68 -r 2bf2abf6e970 include/asm-generic/vmlinux.lds.h
@@ -194,3 +194,6 @@
 		.stab.index 0 : { *(.stab.index) }			\
 		.stab.indexstr 0 : { *(.stab.indexstr) }		\
 		.comment 0 : { *(.comment) }
+
+#define NOTES								\
+		.notes : { *(.note.*) } :note

88 lines not on this page · raw message