All of lore.kernel.org
 help / color / mirror / Atom feed
From: Steven Rostedt <rostedt@goodmis.org>
To: virtualization@lists.osdl.org
Cc: Chris Wright <chrisw@sous-sol.org>,
	Glauber de Oliveira Costa <gcosta@redhat.com>
Subject: [RFC/PATCH PV_OPS X86_64 01/17] paravirt_ops - core changes
Date: Thu, 08 Mar 2007 01:01:52 -0500	[thread overview]
Message-ID: <1173333712.25848.2.camel@localhost.localdomain> (raw)
In-Reply-To: 20070308054422.820010000@redhat.com

plain text document attachment (xx-paravirt-core.patch)
Paravirt Ops core files.

Signed-off-by: Steven Rostedt srostedt@redhat.com
Signed-off-by: Glauber de Oliveira Costa <gcosta@redhat.com>



Index: clean-start/arch/x86_64/kernel/paravirt.c
===================================================================
--- /dev/null
+++ clean-start/arch/x86_64/kernel/paravirt.c
@@ -0,0 +1,504 @@
+/*  Paravirtualization interfaces
+    Copyright (C) 2007 Glauber de Oliveira Costa, Red Hat Inc.
+    Based on i386 work by Rusty Russell.
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+*/
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/efi.h>
+#include <linux/bcd.h>
+#include <linux/start_kernel.h>
+
+#include <asm/bug.h>
+#include <asm/paravirt.h>
+#include <asm/desc.h>
+#include <asm/setup.h>
+#include <asm/irq.h>
+#include <asm/delay.h>
+#include <asm/fixmap.h>
+#include <asm/apic.h>
+#include <asm/tlbflush.h>
+#include <asm/msr.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/proto.h>
+#include <asm/time.h>
+#include <asm/e820.h>
+
+/* nop stub */
+void native_nop(void)
+{
+}
+
+static void __init default_banner(void)
+{
+	printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
+	       paravirt_ops.name);
+}
+
+void memory_setup(void)
+{
+	paravirt_ops.memory_setup();
+}
+
+void syscall_init(void)
+{
+	paravirt_ops.syscall_init();
+}
+
+/* Simple instruction patching code. */
+#define DEF_NATIVE(name, code)					\
+	extern const char start_##name[], end_##name[];		\
+	asm("start_" #name ": " code "; end_" #name ":")
+DEF_NATIVE(cli, "cli");
+DEF_NATIVE(sti, "sti");
+/* We push rdi , and pop in rda. This is due to x86_64 calling conventions
+ * Recall that we are patching a function call */
+DEF_NATIVE(popfq, "pushq %rdi; popfq");
+DEF_NATIVE(pushfq, "pushfq; popq %rax");
+DEF_NATIVE(pushfq_cli, "pushfq; popq %rax; cli");
+DEF_NATIVE(iret, "iretq");
+DEF_NATIVE(sysretq, "sysretq");
+DEF_NATIVE(swapgs, "swapgs");
+
+static const struct native_insns
+{
+	const char *start, *end;
+} native_insns[] = {
+	[PARAVIRT_IRQ_DISABLE] = { start_cli, end_cli },
+	[PARAVIRT_IRQ_ENABLE] = { start_sti, end_sti },
+	[PARAVIRT_RESTORE_FLAGS] = { start_popfq, end_popfq },
+	[PARAVIRT_SAVE_FLAGS] = { start_pushfq, end_pushfq },
+	[PARAVIRT_SAVE_FLAGS_IRQ_DISABLE] = { start_pushfq_cli, end_pushfq_cli },
+	[PARAVIRT_INTERRUPT_RETURN] = { start_iret, end_iret },
+	[PARAVIRT_SYSRETQ] = { start_sysretq, end_sysretq },
+	[PARAVIRT_SWAPGS] = { start_swapgs, end_swapgs },
+};
+
+static unsigned native_patch(u8 type, u16 clobbers, void *insns, unsigned len)
+{
+	unsigned int insn_len;
+
+	/* Don't touch it if we don't have a replacement */
+	if (type >= ARRAY_SIZE(native_insns) || !native_insns[type].start)
+		return len;
+
+	insn_len = native_insns[type].end - native_insns[type].start;
+
+	/* Similarly if we can't fit replacement. */
+	if (len < insn_len)
+		return len;
+
+	memcpy(insns, native_insns[type].start, insn_len);
+	return insn_len;
+}
+
+static unsigned long native_get_debugreg(int regno)
+{
+	unsigned long val = 0; 	/* Damn you, gcc! */
+
+	switch (regno) {
+	case 0:
+		asm("movq %%db0, %0" :"=r" (val)); break;
+	case 1:
+		asm("movq %%db1, %0" :"=r" (val)); break;
+	case 2:
+		asm("movq %%db2, %0" :"=r" (val)); break;
+	case 3:
+		asm("movq %%db3, %0" :"=r" (val)); break;
+	case 6:
+		asm("movq %%db6, %0" :"=r" (val)); break;
+	case 7:
+		asm("movq %%db7, %0" :"=r" (val)); break;
+	default:
+		BUG();
+	}
+	return val;
+}
+
+static void native_set_debugreg(int regno, unsigned long value)
+{
+	switch (regno) {
+	case 0:
+		asm("movq %0,%%db0"	: /* no output */ :"r" (value));
+		break;
+	case 1:
+		asm("movq %0,%%db1"	: /* no output */ :"r" (value));
+		break;
+	case 2:
+		asm("movq %0,%%db2"	: /* no output */ :"r" (value));
+		break;
+	case 3:
+		asm("movq %0,%%db3"	: /* no output */ :"r" (value));
+		break;
+	case 6:
+		asm("movq %0,%%db6"	: /* no output */ :"r" (value));
+		break;
+	case 7:
+		asm("movq %0,%%db7"	: /* no output */ :"r" (value));
+		break;
+	default:
+		BUG();
+	}
+}
+
+void init_IRQ(void)
+{
+	paravirt_ops.init_IRQ();
+}
+
+static unsigned long native_save_fl(void)
+{
+	unsigned long f;
+	asm volatile("pushfq ; popq %0":"=g" (f): /* no input */);
+	return f;
+}
+
+static void native_restore_fl(unsigned long f)
+{
+	asm volatile("pushq %0 ; popfq": /* no output */
+			     :"g" (f)
+			     :"memory", "cc");
+}
+
+static void native_irq_disable(void)
+{
+	asm volatile("cli": : :"memory");
+}
+
+static void native_irq_enable(void)
+{
+	asm volatile("sti": : :"memory");
+}
+
+static void native_safe_halt(void)
+{
+	asm volatile("sti; hlt": : :"memory");
+}
+
+static void native_halt(void)
+{
+	asm volatile("hlt": : :"memory");
+}
+
+static u64 native_read_tsc(void)
+{
+	unsigned long a, b;
+	asm volatile("rdtsc" : "=a" (a), "=d" (b));
+	return a | (b << 32);
+}
+
+static u64 native_read_tscp(int *aux)
+{
+	u64 a, b;
+	asm volatile ("rdtscp" : "=a" (a), "=b" (b), "=c" (aux));
+	return a | (b << 32);
+}
+
+static u64 native_read_pmc(void)
+{
+	unsigned long a, b;
+	asm volatile("rdpmc" : "=a" (a), "=b" (b));
+	return a | (b << 32);
+}
+
+static void native_store_gdt(struct desc_ptr *dtr)
+{
+	asm ("sgdt %w0":"=m" (*dtr));
+}
+
+static void native_store_idt(struct desc_ptr *dtr)
+{
+	asm ("sidt %w0":"=m" (*dtr));
+}
+
+static unsigned long native_store_tr(void)
+{
+	unsigned long tr;
+	asm ("str %w0":"=r" (tr));
+	return tr;
+}
+
+static void native_load_tls(struct thread_struct *t, unsigned int cpu)
+{
+	u64 *gdt = (u64 *)(cpu_gdt(cpu) + GDT_ENTRY_TLS_MIN);
+	gdt[0] = t->tls_array[0];
+	gdt[1] = t->tls_array[1];
+	gdt[2] = t->tls_array[2];
+}
+
+static inline void native_write_dt_entry(void *dt, int entry, u32 entry_low, u32 entry_high)
+{
+	u32 *lp = (u32 *)((char *)dt + entry*8);
+	lp[0] = entry_low;
+	lp[1] = entry_high;
+}
+
+static void native_write_ldt_entry(void *dt, int entrynum, u32 low, u32 high)
+{
+	native_write_dt_entry(dt, entrynum, low, high);
+}
+
+static void native_write_gdt_entry(void *dt, int entrynum, u32 low, u32 high)
+{
+	native_write_dt_entry(dt, entrynum, low, high);
+}
+
+static void native_write_idt_entry(void *dt, int entrynum, u32 low, u32 high)
+{
+	native_write_dt_entry(dt, entrynum, low, high);
+}
+
+static void native_load_rsp0(struct tss_struct *tss,
+				      struct thread_struct *thread)
+{
+	tss->rsp0 = thread->rsp0;
+}
+
+static void native_io_delay(void)
+{
+	asm volatile("outb %al,$0x80");
+}
+
+void native_pagetable_setup_start(pgd_t *base)
+{
+	int i;
+
+	/*
+	 * Init entries of the first-level page table to the
+	 * zero page, if they haven't already been set up.
+	 *
+	 * In a normal native boot, we'll be running on a
+	 * pagetable rooted in swapper_pg_dir, but not in PAE
+	 * mode, so this will end up clobbering the mappings
+	 * for the lower 24Mbytes of the address space,
+	 * without affecting the kernel address space.
+	 */
+	for (i = 0; i < USER_PTRS_PER_PGD; i++)
+		set_pgd(&base[i],
+			__pgd(__pa(empty_zero_page) | _PAGE_PRESENT));
+	memset(&base[USER_PTRS_PER_PGD], 0, sizeof(pgd_t));
+}
+
+void native_pagetable_setup_done(pgd_t *base)
+{
+	/*
+	 * Add low memory identity-mappings - SMP needs it when
+	 * starting up on an AP from real-mode. In the non-PAE
+	 * case we already have these mappings through head.S.
+	 * All user-space mappings are explicitly cleared after
+	 * SMP startup.
+	 */
+	set_pgd(&base[0], base[USER_PTRS_PER_PGD]);
+}
+
+
+static void native_flush_tlb(void)
+{
+	__native_flush_tlb();
+}
+
+/*
+ * Global pages have to be flushed a bit differently. Not a real
+ * performance problem because this does not happen often.
+ */
+static void native_flush_tlb_all(void)
+{
+	__native_flush_tlb_all();
+}
+
+static void native_flush_tlb_one(u64 addr)
+{
+	__native_flush_tlb_one(addr);
+}
+
+pte_t native_make_pte(unsigned long pte)
+{
+	return (pte_t){ pte };
+}
+
+pud_t native_make_pud(unsigned long pud)
+{
+	return (pud_t){ pud };
+}
+
+pmd_t native_make_pmd(unsigned long pmd)
+{
+	return (pmd_t){ pmd };
+}
+
+pgd_t native_make_pgd(unsigned long pgd)
+{
+	return (pgd_t){ pgd };
+}
+
+pte_t native_ptep_get_and_clear(struct mm_struct *mm, u64 addr,
+					 pte_t *ptep)
+{
+	return __pte(xchg(&(ptep)->pte, 0));
+}
+
+void native_set_pte_at(struct mm_struct *mm, u64 addr, pte_t *ptep,
+				pte_t pteval)
+{
+	native_set_pte(ptep,pteval);
+}
+
+void native_pte_clear(struct mm_struct *mm, u64 addr, pte_t *ptep)
+{
+	native_set_pte_at(mm,addr,ptep,__pte(0));
+}
+
+void native_pmd_clear(pmd_t *pmd)
+{
+	native_set_pmd(pmd,__pmd(0));
+}
+
+void native_swapgs(unsigned long rip)
+{
+	asm volatile ("swapgs" :: :"memory" );
+}
+
+/* These are in entry.S */
+extern void native_iret(void);
+extern void native_sysret(void);
+
+static int __init print_banner(void)
+{
+	paravirt_ops.banner();
+	return 0;
+}
+core_initcall(print_banner);
+
+/* We simply declare start_kernel to be the paravirt probe of last resort. */
+paravirt_probe_failsafe(start_kernel);
+
+extern unsigned long __vsyscall_0;
+struct paravirt_ops paravirt_ops = {
+	.name = "bare hardware",
+	.mem_type = "BIOS-e820",
+	.paravirt_enabled = 0,
+	.pgd_alignment = sizeof(pgd_t) * PTRS_PER_PGD,
+
+	.vsyscall_page = &__vsyscall_0,
+ 	.patch = native_patch,
+	.banner = default_banner,
+	.arch_setup = native_nop,
+	.memory_setup = setup_memory_region,
+	.syscall_init = x86_64_syscall_init,
+	.get_wallclock = do_get_cmos_time,
+	.set_wallclock = do_set_rtc_mmss,
+	.time_init = time_init_hook,
+	.init_IRQ = native_init_IRQ,
+
+	.cpuid = native_cpuid,
+	.get_debugreg = native_get_debugreg,
+	.set_debugreg = native_set_debugreg,
+	.clts = native_clts,
+	.read_cr0 = native_read_cr0,
+	.write_cr0 = native_write_cr0,
+	.read_cr2 = native_read_cr2,
+	.write_cr2 = native_write_cr2,
+	.read_cr3 = native_read_cr3,
+	.write_cr3 = native_write_cr3,
+	.read_cr4 = native_read_cr4,
+	.write_cr4 = native_write_cr4,
+	.save_fl = native_save_fl,
+	.restore_fl = native_restore_fl,
+	.irq_disable = native_irq_disable,
+	.irq_enable = native_irq_enable,
+	.safe_halt = native_safe_halt,
+	.halt = native_halt,
+	.wbinvd = native_wbinvd,
+	.read_msr = native_read_msr_safe,
+	.write_msr = native_write_msr_safe,
+	.read_tsc = native_read_tsc,
+	.read_tscp = native_read_tscp,
+	.read_pmc = native_read_pmc,
+	.load_tr_desc = native_load_tr_desc,
+	.set_ldt = native_set_ldt,
+	.load_gdt = native_load_gdt,
+	.load_idt = native_load_idt,
+	.store_gdt = native_store_gdt,
+	.store_idt = native_store_idt,
+	.store_tr = native_store_tr,
+	.load_tls = native_load_tls,
+	.write_ldt_entry = native_write_ldt_entry,
+	.write_gdt_entry = native_write_gdt_entry,
+	.write_idt_entry = native_write_idt_entry,
+	.load_rsp0 = native_load_rsp0,
+
+	.io_delay = native_io_delay,
+	.const_udelay = __const_udelay,
+
+#ifdef CONFIG_X86_LOCAL_APIC
+	.apic_write = native_apic_write,
+	.apic_read = native_apic_read,
+#endif
+	.set_lazy_mode = (void *)native_nop,
+	.ebda_info = native_ebda_info,
+
+	.pagetable_setup_start = native_pagetable_setup_start,
+	.pagetable_setup_done = native_pagetable_setup_done,
+
+	.flush_tlb_user = native_flush_tlb,
+	.flush_tlb_kernel = native_flush_tlb_all,
+	.flush_tlb_single = native_flush_tlb_one,
+
+	.alloc_pt = (void *)native_nop,
+	.alloc_pd = (void *)native_nop,
+	.alloc_pd_clone = (void *)native_nop,
+	.release_pt = (void *)native_nop,
+	.release_pd = (void *)native_nop,
+
+	.set_pte = native_set_pte,
+	.set_pte_at = native_set_pte_at,
+	.set_pmd = native_set_pmd,
+	.set_pud = native_set_pud,
+	.set_pgd = native_set_pgd,
+
+	.pte_update = (void *)native_nop,
+	.pte_update_defer = (void *)native_nop,
+
+	.ptep_get_and_clear = native_ptep_get_and_clear,
+
+	.pte_clear = native_pte_clear,
+	.pmd_clear = native_pmd_clear,
+	.pud_clear = native_pud_clear,
+	.pgd_clear = native_pgd_clear,
+
+	.pte_val = native_pte_val,
+	.pud_val = native_pud_val,
+	.pmd_val = native_pmd_val,
+	.pgd_val = native_pgd_val,
+
+	.make_pte = native_make_pte,
+	.make_pmd = native_make_pmd,
+	.make_pud = native_make_pud,
+	.make_pgd = native_make_pgd,
+
+	.swapgs = native_swapgs,
+	.sysret = native_sysret,
+	.iret = native_iret,
+
+	.dup_mmap = (void *)native_nop,
+	.exit_mmap = (void *)native_nop,
+	.activate_mm = (void *)native_nop,
+
+	.startup_ipi_hook = (void *)native_nop,
+};
+
+EXPORT_SYMBOL(paravirt_ops);
Index: clean-start/include/asm-x86_64/paravirt.h
===================================================================
--- /dev/null
+++ clean-start/include/asm-x86_64/paravirt.h
@@ -0,0 +1,678 @@
+#ifndef __ASM_PARAVIRT_H
+#define __ASM_PARAVIRT_H
+/* Various instructions on x86 need to be replaced for
+ * para-virtualization: those hooks are defined here. */
+#include <linux/linkage.h>
+#include <linux/stringify.h>
+#include <asm/page.h>
+#include <asm/types.h>
+#include <asm/pda.h>
+
+#ifdef CONFIG_PARAVIRT
+/* These are the most performance critical ops, so we want to be able to patch
+ * callers */
+#define PARAVIRT_IRQ_DISABLE 0
+#define PARAVIRT_IRQ_ENABLE 1
+#define PARAVIRT_RESTORE_FLAGS 2
+#define PARAVIRT_SAVE_FLAGS 3
+#define PARAVIRT_SAVE_FLAGS_IRQ_DISABLE 4
+#define PARAVIRT_INTERRUPT_RETURN 5
+#define PARAVIRT_SYSRETQ 6
+#define PARAVIRT_SWAPGS	7
+
+/* Bitmask of what can be clobbered: usually at least rax. */
+#define CLBR_NONE 0x0
+#define CLBR_RAX 0x1
+#define CLBR_RCX 0x2
+#define CLBR_RDX 0x4
+#define CLBR_ANY 0xf
+
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+
+struct thread_struct;
+struct desc_struct;
+struct desc_ptr;
+struct tss_struct;
+struct mm_struct;
+
+struct paravirt_ops
+{
+	int paravirt_enabled;
+
+	int pgd_alignment;
+
+	const char *name;
+	char *mem_type;
+
+	unsigned long *vsyscall_page;
+
+	/*
+	 * Patch may replace one of the defined code sequences with arbitrary
+	 * code, subject to the same register constraints.  This generally
+	 * means the code is not free to clobber any registers other than RAX.
+	 * The patch function should return the number of bytes of code
+	 * generated, as we nop pad the rest in generic code.
+	 */
+	unsigned (*patch)(u8 type, u16 clobber, void *firstinsn, unsigned len);
+
+	void (*arch_setup)(void);
+	void (*memory_setup)(void);
+	void (*init_IRQ)(void);
+	/* entry point for our hypervisor syscall handler */
+	void (*syscall_init)(void);
+
+	void (*pagetable_setup_start)(pgd_t *pgd_base);
+	void (*pagetable_setup_done)(pgd_t *pgd_base);
+
+	void (*banner)(void);
+
+	unsigned long (*get_wallclock)(void);
+	void (*set_wallclock)(unsigned long);
+	void (*time_init)(void);
+
+	void (*cpuid)(unsigned int *eax, unsigned int *ebx,
+		      unsigned int *ecx, unsigned int *edx);
+
+	unsigned long (*get_debugreg)(int regno);
+	void (*set_debugreg)(int regno, unsigned long value);
+
+	void (*clts)(void);
+
+	unsigned long (*read_cr0)(void);
+	void (*write_cr0)(unsigned long);
+
+	unsigned long (*read_cr2)(void);
+	void (*write_cr2)(unsigned long);
+
+	unsigned long (*read_cr3)(void);
+	void (*write_cr3)(unsigned long);
+
+	unsigned long (*read_cr4)(void);
+	void (*write_cr4)(unsigned long);
+
+	unsigned long (*save_fl)(void);
+	void (*restore_fl)(unsigned long);
+	void (*irq_disable)(void);
+	void (*irq_enable)(void);
+
+	void (*safe_halt)(void);
+	void (*halt)(void);
+	void (*wbinvd)(void);
+
+	/* err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
+	unsigned long (*read_msr)(unsigned int msr, int *err);
+	int (*write_msr)(unsigned int msr, unsigned long val);
+
+	u64 (*read_tsc)(void);
+	u64 (*read_tscp)(int *aux);
+	u64 (*read_pmc)(void);
+
+	void (*load_tr_desc)(void);
+	void (*load_gdt)(const struct desc_ptr *);
+	void (*load_idt)(const struct desc_ptr *);
+	void (*store_gdt)(struct desc_ptr *);
+	void (*store_idt)(struct desc_ptr *);
+	void (*set_ldt)(const void *desc, unsigned entries);
+	unsigned long (*store_tr)(void);
+	void (*load_tls)(struct thread_struct *t, unsigned int cpu);
+	void (*write_ldt_entry)(void *dt, int entrynum,
+					 u32 low, u32 high);
+	void (*write_gdt_entry)(void *dt, int entrynum,
+					 u32 low, u32 high);
+	void (*write_idt_entry)(void *dt, int entrynum,
+					 u32 low, u32 high);
+	void (*load_rsp0)(struct tss_struct *tss,
+				   struct thread_struct *thread);
+
+	void (*io_delay)(void);
+	void (*const_udelay)(unsigned long loops);
+
+	void (*activate_mm)(struct mm_struct *prev,
+				     struct mm_struct *next);
+	void (*dup_mmap)(struct mm_struct *oldmm,
+				  struct mm_struct *mm);
+	void (*exit_mmap)(struct mm_struct *mm);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+	void (*apic_write)(unsigned long reg, unsigned int v);
+	unsigned int (*apic_read)(unsigned long reg);
+#endif
+
+	void (*flush_tlb_user)(void);
+	void (*flush_tlb_kernel)(void);
+	void (*flush_tlb_single)(u64 addr);
+
+	void (*alloc_pt)(u64 pfn);
+	void (*alloc_pd)(u64 pfn);
+	void (*alloc_pd_clone)(u64 pfn, u64 clonepfn, u64 start, u64 count);
+	void (*release_pt)(u64 pfn);
+	void (*release_pd)(u64 pfn);
+
+	void (*set_pte)(pte_t *ptep, pte_t pteval);
+	void (*set_pte_at)(struct mm_struct *mm, u64 addr, pte_t *ptep, pte_t pteval);
+	void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
+	void (*set_pud)(pud_t *pudp, pud_t pudval);
+	void (*set_pgd)(pgd_t *pgdp, pgd_t pgdval);
+
+	void (*pte_update)(struct mm_struct *mm, u64 addr, pte_t *ptep);
+	void (*pte_update_defer)(struct mm_struct *mm, u64 addr, pte_t *ptep);
+
+	pte_t (*ptep_get_and_clear)(struct mm_struct *mm, u64 addr, pte_t *ptep);
+
+	void (*pte_clear)(struct mm_struct *mm, u64 addr, pte_t *ptep);
+	void (*pmd_clear)(pmd_t *pmdp);
+	void (*pud_clear)(pud_t *pudp);
+	void (*pgd_clear)(pgd_t *pgdp);
+
+	unsigned long (*pte_val)(pte_t);
+	unsigned long (*pud_val)(pud_t);
+	unsigned long (*pmd_val)(pmd_t);
+	unsigned long (*pgd_val)(pgd_t);
+
+	pte_t (*make_pte)(unsigned long pte);
+	pud_t (*make_pud)(unsigned long pud);
+	pmd_t (*make_pmd)(unsigned long pmd);
+	pgd_t (*make_pgd)(unsigned long pgd);
+
+	void (*swapgs)(unsigned long rip);
+	void (*ebda_info)(unsigned *addr, unsigned *size);
+	void (*set_lazy_mode)(int mode);
+
+	/* These two are jmp to, not actually called. */
+	void (*sysret)(void);
+	void (*iret)(void);
+
+	void (*startup_ipi_hook)(int phys_apicid, unsigned long start_eip, unsigned long start_esp);
+};
+
+#define MAP_TYPE_STR paravirt_ops.mem_type
+
+/* Mark a paravirt probe function. */
+#define paravirt_probe(fn)						\
+ static asmlinkage void (*__paravirtprobe_##fn)(void) __attribute_used__ \
+		__attribute__((__section__(".paravirtprobe"))) = fn
+
+#define paravirt_probe_failsafe(fn)						\
+ static asmlinkage void (*__paravirtprobe_##fn)(void) __attribute_used__ \
+		__attribute__((__section__(".paravirtprobe_failsafe"))) = fn
+extern struct paravirt_ops paravirt_ops;
+
+void native_pagetable_setup_start(pgd_t *pgd);
+
+pte_t native_make_pte(unsigned long pte);
+pud_t native_make_pud(unsigned long pud);
+pmd_t native_make_pmd(unsigned long pmd);
+pgd_t native_make_pgd(unsigned long pgd);
+
+#define paravirt_enabled() (paravirt_ops.paravirt_enabled)
+
+static inline void load_rsp0(struct tss_struct *tss,
+			     struct thread_struct *thread)
+{
+	paravirt_ops.load_rsp0(tss, thread);
+}
+
+#define ARCH_SETUP			paravirt_ops.arch_setup();
+
+static inline unsigned long get_wallclock(void)
+{
+	return paravirt_ops.get_wallclock();
+}
+
+static inline void set_wallclock(unsigned long nowtime)
+{
+	paravirt_ops.set_wallclock(nowtime);
+}
+
+static inline void do_time_init(void)
+{
+	return paravirt_ops.time_init();
+}
+
+/* The paravirtualized CPUID instruction. */
+static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
+			   unsigned int *ecx, unsigned int *edx)
+{
+	paravirt_ops.cpuid(eax, ebx, ecx, edx);
+}
+
+/*
+ * These special macros can be used to get or set a debugging register
+ */
+#define get_debugreg(var, reg) var = paravirt_ops.get_debugreg(reg)
+#define set_debugreg(val, reg) paravirt_ops.set_debugreg(reg, val)
+
+#define clts() paravirt_ops.clts()
+
+#define read_cr0() paravirt_ops.read_cr0()
+#define write_cr0(x) paravirt_ops.write_cr0(x)
+
+#define read_cr2() paravirt_ops.read_cr2()
+#define write_cr2(x) paravirt_ops.write_cr2(x)
+
+#define read_cr3() paravirt_ops.read_cr3()
+#define write_cr3(x) paravirt_ops.write_cr3(x)
+
+#define read_cr4() paravirt_ops.read_cr4()
+#define write_cr4(x) paravirt_ops.write_cr4(x)
+
+
+#define ptep_get_and_clear(mm,addr,xp)	\
+			(paravirt_ops.ptep_get_and_clear(mm,addr,xp))
+
+static inline void raw_safe_halt(void)
+{
+	paravirt_ops.safe_halt();
+}
+
+static inline void halt(void)
+{
+	paravirt_ops.safe_halt();
+}
+#define wbinvd() paravirt_ops.wbinvd()
+
+
+#define rdmsr(msr,val1,val2) do {				\
+	int _err;						\
+	u64 _l = paravirt_ops.read_msr(msr,&_err);		\
+	val1 = (u32)_l;						\
+	val2 = _l >> 32;					\
+} while(0)
+
+/* rdmsr with exception handling */
+#define rdmsr_safe(msr,a,b) ({					\
+	int _err;						\
+	u64 _l = paravirt_ops.read_msr(msr,&_err);		\
+	(*a) = (u32)_l;						\
+	(*b) = _l >> 32;					\
+	_err; })
+
+#define wrmsr(msr,val1,val2) do {				\
+	u64 _l = ((u64)(val2) << 32) | (val1);			\
+	paravirt_ops.write_msr((msr), _l);			\
+} while(0)
+
+#define rdmsrl(msr,val) do {					\
+	int _err;						\
+	val = paravirt_ops.read_msr((msr),&_err);		\
+} while(0)
+
+#define checking_wrmsrl(msr,val) (paravirt_ops.write_msr((msr),(val)))
+
+#define wrmsrl(msr,val) (paravirt_ops.write_msr((msr),(val)))
+
+#define wrmsr_safe(msr,a,b) ({					\
+	u64 _l = ((u64)(b) << 32) | (a);			\
+	paravirt_ops.write_msr((msr),_l);			\
+})
+
+#define rdtsc(low,high) do {					\
+	u64 _l = paravirt_ops.read_tsc();			\
+	low = (u32)_l;						\
+	high = _l >> 32;					\
+} while(0)
+
+#define rdtscl(low) do {					\
+	u64 _l = paravirt_ops.read_tsc();			\
+	low = (int)_l;						\
+} while(0)
+
+#define rdtscll(val) (val = paravirt_ops.read_tsc())
+
+#define rdtscp(low,high,aux) do {				\
+	u64 _val = paravirt_ops.read_tscp(&aux);		\
+	low = (int)_val;					\
+	high = _val >> 32;					\
+} while (0)
+
+#define rdtscpll(val, aux) (val) = paravirt_ops.read_tscp(&aux)
+
+#define write_tsc(val1,val2) wrmsr(0x10, val1, val2)
+
+#define rdpmc(counter,low,high) do {				\
+	u64 _l = paravirt_ops.read_pmc();			\
+	low = (u32)_l;						\
+	high = _l >> 32;					\
+} while(0)
+
+#define load_TR_desc() (paravirt_ops.load_tr_desc())
+#define load_gdt(dtr) (paravirt_ops.load_gdt(dtr))
+#define load_idt(dtr) (paravirt_ops.load_idt(dtr))
+#define set_ldt(addr, entries) (paravirt_ops.set_ldt((addr), (entries)))
+#define store_gdt(dtr) (paravirt_ops.store_gdt(dtr))
+#define store_idt(dtr) (paravirt_ops.store_idt(dtr))
+#define store_tr(tr) ((tr) = paravirt_ops.store_tr())
+#define load_TLS(t,cpu) (paravirt_ops.load_tls((t),(cpu)))
+#define write_ldt_entry(dt, entry, low, high)				\
+	(paravirt_ops.write_ldt_entry((dt), (entry), (low), (high)))
+#define write_gdt_entry(dt, entry, low, high)				\
+	(paravirt_ops.write_gdt_entry((dt), (entry), (low), (high)))
+#define write_idt_entry(dt, entry, low, high)				\
+	(paravirt_ops.write_idt_entry((dt), (entry), (low), (high)))
+
+#define __pte(x)	paravirt_ops.make_pte(x)
+#define pte_val(x)	paravirt_ops.pte_val(x)
+
+#define __pgd(x)	paravirt_ops.make_pgd(x)
+#define pgd_val(x)	paravirt_ops.pgd_val(x)
+
+#define __pud(x)	paravirt_ops.make_pud(x)
+#define pud_val(x)	paravirt_ops.pud_val(x)
+
+#define __pmd(x)	paravirt_ops.make_pmd(x)
+#define pmd_val(x)	paravirt_ops.pmd_val(x)
+
+#define ebda_info(addr,size) paravirt_ops.ebda_info(addr,size)
+
+/* The paravirtualized I/O functions */
+static inline void slow_down_io(void) {
+	paravirt_ops.io_delay();
+#ifdef REALLY_SLOW_IO
+	paravirt_ops.io_delay();
+	paravirt_ops.io_delay();
+	paravirt_ops.io_delay();
+#endif
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+/*
+ * Basic functions accessing APICs.
+ */
+static inline void apic_write(unsigned long reg, unsigned long v)
+{
+	paravirt_ops.apic_write(reg,v);
+}
+
+static inline unsigned long apic_read(unsigned long reg)
+{
+	return paravirt_ops.apic_read(reg);
+}
+#endif
+
+static inline void paravirt_pagetable_setup_start(pgd_t *base)
+{
+	if (paravirt_ops.pagetable_setup_start)
+		(*paravirt_ops.pagetable_setup_start)(base);
+}
+
+static inline void paravirt_pagetable_setup_done(pgd_t *base)
+{
+	if (paravirt_ops.pagetable_setup_done)
+		(*paravirt_ops.pagetable_setup_done)(base);
+}
+
+void native_pte_clear(struct mm_struct *mm, u64 addr, pte_t *ptep);
+void native_pmd_clear(pmd_t *pmd);
+void native_nop(void);
+
+static inline void paravirt_activate_mm(struct mm_struct *prev,
+					struct mm_struct *next)
+{
+	paravirt_ops.activate_mm(prev, next);
+}
+
+static inline void paravirt_dup_mmap(struct mm_struct *oldmm,
+				     struct mm_struct *mm)
+{
+	paravirt_ops.dup_mmap(oldmm, mm);
+}
+
+static inline void paravirt_exit_mmap(struct mm_struct *mm)
+{
+	paravirt_ops.exit_mmap(mm);
+}
+
+#define __flush_tlb() paravirt_ops.flush_tlb_user()
+#define __flush_tlb_all() paravirt_ops.flush_tlb_kernel()
+#define __flush_tlb_one(addr) paravirt_ops.flush_tlb_single(addr)
+
+#define paravirt_alloc_pt(pfn) paravirt_ops.alloc_pt(pfn)
+#define paravirt_release_pt(pfn) paravirt_ops.release_pt(pfn)
+
+#define paravirt_alloc_pd(pfn) paravirt_ops.alloc_pd(pfn)
+#define paravirt_alloc_pd_clone(pfn, clonepfn, start, count) \
+	paravirt_ops.alloc_pd_clone(pfn, clonepfn, start, count)
+#define paravirt_release_pd(pfn) paravirt_ops.release_pd(pfn)
+
+static inline void set_pte(pte_t *ptep, pte_t pteval)
+{
+	paravirt_ops.set_pte(ptep, pteval);
+}
+
+static inline void set_pte_at(struct mm_struct *mm, u64 addr, pte_t *ptep, pte_t pteval)
+{
+	paravirt_ops.set_pte_at(mm, addr, ptep, pteval);
+}
+
+static inline void set_pmd(pmd_t *pmdp, pmd_t pmdval)
+{
+	paravirt_ops.set_pmd(pmdp, pmdval);
+}
+
+static inline void pte_update(struct mm_struct *mm, u32 addr, pte_t *ptep)
+{
+	paravirt_ops.pte_update(mm, addr, ptep);
+}
+
+static inline void pte_update_defer(struct mm_struct *mm, u32 addr, pte_t *ptep)
+{
+	paravirt_ops.pte_update_defer(mm, addr, ptep);
+}
+
+
+static inline void set_pgd(pgd_t *pgdp, pgd_t pgdval)
+{
+	paravirt_ops.set_pgd(pgdp, pgdval);
+}
+
+static inline void set_pud(pud_t *pudp, pud_t pudval)
+{
+	paravirt_ops.set_pud(pudp, pudval);
+}
+
+static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+	paravirt_ops.pte_clear(mm, addr, ptep);
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+	paravirt_ops.pmd_clear(pmdp);
+}
+
+static inline void pud_clear(pud_t *pudp)
+{
+	paravirt_ops.pud_clear(pudp);
+}
+
+static inline void pgd_clear(pgd_t *pgdp)
+{
+	paravirt_ops.pgd_clear(pgdp);
+}
+
+/* Lazy mode for batching updates / context switch */
+#define PARAVIRT_LAZY_NONE 0
+#define PARAVIRT_LAZY_MMU  1
+#define PARAVIRT_LAZY_CPU  2
+
+#define  __HAVE_ARCH_ENTER_LAZY_CPU_MODE
+#define arch_enter_lazy_cpu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_CPU)
+#define arch_leave_lazy_cpu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_NONE)
+
+#define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
+#define arch_enter_lazy_mmu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_MMU)
+#define arch_leave_lazy_mmu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_NONE)
+
+/* These all sit in the .parainstructions section to tell us what to patch. */
+struct paravirt_patch {
+	u8 *instr; 		/* original instructions */
+	u8 instrtype;		/* type of this instruction */
+	u8 len;			/* length of original instruction */
+	u16 clobbers;		/* what registers you may clobber */
+} __attribute__((aligned(8)));
+
+#define paravirt_alt(insn_string, typenum, clobber)	\
+	"771:\n\t" insn_string "\n" "772:\n"		\
+	".pushsection .parainstructions,\"a\"\n"	\
+	".align 8\n"					\
+	"  .quad 771b\n"				\
+	"  .byte " __stringify(typenum) "\n"		\
+	"  .byte 772b-771b\n"				\
+	"  .short " __stringify(clobber) "\n"		\
+	".popsection"
+
+/* These functions tends to be very simple. So, if they touch any register,
+ * the calle-saved ones may already fulfill their needs, and hopefully we
+ * have no need to save any. */
+static inline unsigned long __raw_local_save_flags(void)
+{
+	unsigned long f;
+
+	__asm__ __volatile__(paravirt_alt("call *%1;",
+					  PARAVIRT_SAVE_FLAGS, CLBR_NONE)
+			     : "=a"(f): "m"(paravirt_ops.save_fl)
+			     : "memory", "cc");
+	return f;
+}
+
+static inline void raw_local_irq_restore(unsigned long f)
+{
+	__asm__ __volatile__(paravirt_alt("call *%1;", PARAVIRT_RESTORE_FLAGS,
+					CLBR_NONE)
+			     : : "D" (f) , "m" (paravirt_ops.restore_fl)
+			     : "memory", "rax", "cc");
+}
+
+static inline void raw_local_irq_disable(void)
+{
+	__asm__ __volatile__(paravirt_alt("call *%0;",
+					  PARAVIRT_IRQ_DISABLE, CLBR_NONE)
+			     : : "m" (paravirt_ops.irq_disable)
+			     : "memory", "rax", "cc");
+}
+
+static inline void raw_local_irq_enable(void)
+{
+	__asm__ __volatile__(paravirt_alt("call *%0;",
+					  PARAVIRT_IRQ_ENABLE, CLBR_NONE)
+			     : : "m" (paravirt_ops.irq_enable)
+			     : "memory", "rax", "cc");
+}
+
+static inline unsigned long __raw_local_irq_save(void)
+{
+	unsigned long f;
+
+	__asm__ __volatile__(paravirt_alt( "call *%1;"
+					   "call *%2;",
+					  PARAVIRT_SAVE_FLAGS_IRQ_DISABLE,
+					  CLBR_NONE)
+			     : "=a"(f)
+			     : "m" (paravirt_ops.save_fl),
+			       "m" (paravirt_ops.irq_disable)
+			     : "memory", "cc");
+	return f;
+}
+
+#define CLI_STRING paravirt_alt("call *paravirt_ops+%c[irq_disable];",	\
+		     PARAVIRT_IRQ_DISABLE, CLBR_NONE)
+
+#define STI_STRING paravirt_alt("call *paravirt_ops+%c[irq_enable];",	\
+		     PARAVIRT_IRQ_ENABLE, CLBR_NONE)
+
+#define CLI_STI_CLOBBERS , "%rax"
+#define CLI_STI_INPUT_ARGS \
+	,								\
+	[irq_disable] "i" (offsetof(struct paravirt_ops, irq_disable)),	\
+	[irq_enable] "i" (offsetof(struct paravirt_ops, irq_enable))
+
+#else  /* __ASSEMBLY__ */
+
+#define PARA_PATCH(ptype, clobbers, ops)	\
+771:;						\
+	ops;					\
+772:;						\
+	.pushsection .parainstructions,"a";	\
+	.align 8;				\
+	 .quad 771b;				\
+	 .byte ptype;				\
+	 .byte 772b-771b;			\
+	 .short clobbers;			\
+	.popsection
+
+#define INTERRUPT_RETURN				\
+	PARA_PATCH(PARAVIRT_INTERRUPT_RETURN, CLBR_ANY,	\
+	jmp *%cs:paravirt_ops+PARAVIRT_iret)
+
+#define DISABLE_INTERRUPTS(clobbers)			\
+	PARA_PATCH(PARAVIRT_IRQ_DISABLE, clobbers,	\
+	call *paravirt_ops+PARAVIRT_irq_disable)
+
+#define ENABLE_INTERRUPTS(clobbers)			\
+	PARA_PATCH(PARAVIRT_IRQ_ENABLE, clobbers,	\
+	call *%cs:paravirt_ops+PARAVIRT_irq_enable)
+
+#define SYSRETQ						\
+	PARA_PATCH(PARAVIRT_SYSRETQ, CLBR_ANY,		\
+	jmp *%cs:paravirt_ops+PARAVIRT_sysret)
+
+#define SWAPGS						\
+	PARA_PATCH(PARAVIRT_SWAPGS, CLBR_NONE,		\
+	call *paravirt_ops+PARAVIRT_swapgs)		\
+
+/* this is needed in early_idt_handler */
+#define GET_CR2_INTO_RAX 				\
+	call *paravirt_ops+PARAVIRT_read_cr2
+
+#endif /* __ASSEMBLY__ */
+#else  /* !CONFIG_PARAVIRT */
+
+static inline void paravirt_pagetable_setup_start(pgd_t *base)
+{
+	int i;
+
+	/*
+	 * Init entries of the first-level page table to the
+	 * zero page, if they haven't already been set up.
+	 *
+	 * In a normal native boot, we'll be running on a
+	 * pagetable rooted in swapper_pg_dir, but not in PAE
+	 * mode, so this will end up clobbering the mappings
+	 * for the lower 24Mbytes of the address space,
+	 * without affecting the kernel address space.
+	 */
+	for (i = 0; i < USER_PTRS_PER_PGD; i++)
+		set_pgd(&base[i],
+			__pgd(__pa(empty_zero_page) | _PAGE_PRESENT));
+	memset(&base[USER_PTRS_PER_PGD], 0, sizeof(pgd_t));
+}
+
+static inline void paravirt_pagetable_setup_done(pgd_t *base)
+{
+	/*
+	 * Add low memory identity-mappings - SMP needs it when
+	 * starting up on an AP from real-mode. In the non-PAE
+	 * case we already have these mappings through head.S.
+	 * All user-space mappings are explicitly cleared after
+	 * SMP startup.
+	 */
+	set_pgd(&base[0], base[USER_PTRS_PER_PGD]);
+}
+
+static inline void paravirt_activate_mm(struct mm_struct *prev,
+					struct mm_struct *next)
+{
+}
+
+static inline void paravirt_dup_mmap(struct mm_struct *oldmm,
+				     struct mm_struct *mm)
+{
+}
+
+static inline void paravirt_exit_mmap(struct mm_struct *mm)
+{
+}
+
+#endif /* CONFIG_PARAVIRT */
+#endif	/* __ASM_PARAVIRT_H */
Index: clean-start/arch/x86_64/kernel/Makefile
===================================================================
--- clean-start.orig/arch/x86_64/kernel/Makefile
+++ clean-start/arch/x86_64/kernel/Makefile
@@ -41,6 +41,8 @@ obj-$(CONFIG_AUDIT)		+= audit.o
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_PCI)		+= early-quirks.o
 
+obj-$(CONFIG_PARAVIRT)		+= paravirt.o
+
 obj-y				+= topology.o
 obj-y				+= intel_cacheinfo.o
 

--

       reply	other threads:[~2007-03-08  6:01 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20070308054422.820010000@redhat.com>
2007-03-08  6:01 ` Steven Rostedt [this message]
2007-03-08  6:01 ` [RFC/PATCH PV_OPS X86_64 02/17] paravirt_ops - msr Steven Rostedt
2007-03-08  6:01 ` [RFC/PATCH PV_OPS X86_64 03/17] paravirt_ops - system routines Steven Rostedt
2007-03-08  6:02 ` [RFC/PATCH PV_OPS X86_64 04/17] pavarvirt_ops - apci header updates Steven Rostedt
2007-03-08  6:02 ` [RFC/PATCH PV_OPS X86_64 05/17] pravirt_ops - segments Steven Rostedt
2007-03-08  6:49   ` Chris Wright
2007-03-08 13:06     ` Steven Rostedt
2007-03-08  6:02 ` [RFC/PATCH PV_OPS X86_64 06/17] paravirt_op - miscellaneous updates Steven Rostedt
2007-03-08  6:02 ` [RFC/PATCH PV_OPS X86_64 07/17] paravirt_ops - descriptor changes Steven Rostedt
2007-03-08  6:02 ` [RFC/PATCH PV_OPS X86_64 08/17] paravirt_ops - memory managment Steven Rostedt
2007-03-08  6:02 ` [RFC/PATCH PV_OPS X86_64 09/17] paravirt_ops - bios changes Steven Rostedt
2007-03-08  6:02 ` [RFC/PATCH PV_OPS X86_64 10/17] paravirt_ops - boot changes Steven Rostedt
2007-03-08  6:02 ` [RFC/PATCH PV_OPS X86_64 11/17] paravirt_ops - asm-offset updates Steven Rostedt
2007-03-08  6:02 ` [RFC/PATCH PV_OPS X86_64 12/17] paravirt_ops - interrupt/exception changes Steven Rostedt
2007-03-08  6:02 ` [RFC/PATCH PV_OPS X86_64 13/17] paravirt_ops - time updates Steven Rostedt
2007-03-08  6:02 ` [RFC/PATCH PV_OPS X86_64 14/17] paravirt_ops - vsyscall Steven Rostedt
2007-03-08  6:02 ` [RFC/PATCH PV_OPS X86_64 15/17] paravirt_op - kconfig Steven Rostedt
2007-03-08  6:02 ` [RFC/PATCH PV_OPS X86_64 16/17] paravirt_ops - touch ups Steven Rostedt
2007-03-08  6:02 ` [RFC/PATCH PV_OPS X86_64 17/17] paravirt_ops - pda entry Steven Rostedt

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1173333712.25848.2.camel@localhost.localdomain \
    --to=rostedt@goodmis.org \
    --cc=chrisw@sous-sol.org \
    --cc=gcosta@redhat.com \
    --cc=virtualization@lists.osdl.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.