summaryrefslogtreecommitdiffstats
path: root/drivers/lguest/x86/core.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/lguest/x86/core.c')
-rw-r--r--drivers/lguest/x86/core.c107
1 files changed, 15 insertions, 92 deletions
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index 9f1659c3d1f3..65af42f2d593 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -269,10 +269,10 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
static int emulate_insn(struct lg_cpu *cpu)
{
u8 insn;
- unsigned int insnlen = 0, in = 0, shift = 0;
+ unsigned int insnlen = 0, in = 0, small_operand = 0;
/*
* The eip contains the *virtual* address of the Guest's instruction:
- * guest_pa just subtracts the Guest's page_offset.
+ * walk the Guest's page tables to find the "physical" address.
*/
unsigned long physaddr = guest_pa(cpu, cpu->regs->eip);
@@ -300,11 +300,10 @@ static int emulate_insn(struct lg_cpu *cpu)
}
/*
- * 0x66 is an "operand prefix". It means it's using the upper 16 bits
- * of the eax register.
+ * 0x66 is an "operand prefix". It means a 16, not 32 bit in/out.
*/
if (insn == 0x66) {
- shift = 16;
+ small_operand = 1;
/* The instruction is 1 byte so far, read the next byte. */
insnlen = 1;
insn = lgread(cpu, physaddr + insnlen, u8);
@@ -340,11 +339,14 @@ static int emulate_insn(struct lg_cpu *cpu)
* traditionally means "there's nothing there".
*/
if (in) {
- /* Lower bit tells is whether it's a 16 or 32 bit access */
- if (insn & 0x1)
- cpu->regs->eax = 0xFFFFFFFF;
- else
- cpu->regs->eax |= (0xFFFF << shift);
+ /* Lower bit tells means it's a 32/16 bit access */
+ if (insn & 0x1) {
+ if (small_operand)
+ cpu->regs->eax |= 0xFFFF;
+ else
+ cpu->regs->eax = 0xFFFFFFFF;
+ } else
+ cpu->regs->eax |= 0xFF;
}
/* Finally, we've "done" the instruction, so move past it. */
cpu->regs->eip += insnlen;
@@ -352,69 +354,6 @@ static int emulate_insn(struct lg_cpu *cpu)
return 1;
}
-/*
- * Our hypercalls mechanism used to be based on direct software interrupts.
- * After Anthony's "Refactor hypercall infrastructure" kvm patch, we decided to
- * change over to using kvm hypercalls.
- *
- * KVM_HYPERCALL is actually a "vmcall" instruction, which generates an invalid
- * opcode fault (fault 6) on non-VT cpus, so the easiest solution seemed to be
- * an *emulation approach*: if the fault was really produced by an hypercall
- * (is_hypercall() does exactly this check), we can just call the corresponding
- * hypercall host implementation function.
- *
- * But these invalid opcode faults are notably slower than software interrupts.
- * So we implemented the *patching (or rewriting) approach*: every time we hit
- * the KVM_HYPERCALL opcode in Guest code, we patch it to the old "int 0x1f"
- * opcode, so next time the Guest calls this hypercall it will use the
- * faster trap mechanism.
- *
- * Matias even benchmarked it to convince you: this shows the average cycle
- * cost of a hypercall. For each alternative solution mentioned above we've
- * made 5 runs of the benchmark:
- *
- * 1) direct software interrupt: 2915, 2789, 2764, 2721, 2898
- * 2) emulation technique: 3410, 3681, 3466, 3392, 3780
- * 3) patching (rewrite) technique: 2977, 2975, 2891, 2637, 2884
- *
- * One two-line function is worth a 20% hypercall speed boost!
- */
-static void rewrite_hypercall(struct lg_cpu *cpu)
-{
- /*
- * This are the opcodes we use to patch the Guest. The opcode for "int
- * $0x1f" is "0xcd 0x1f" but vmcall instruction is 3 bytes long, so we
- * complete the sequence with a NOP (0x90).
- */
- u8 insn[3] = {0xcd, 0x1f, 0x90};
-
- __lgwrite(cpu, guest_pa(cpu, cpu->regs->eip), insn, sizeof(insn));
- /*
- * The above write might have caused a copy of that page to be made
- * (if it was read-only). We need to make sure the Guest has
- * up-to-date pagetables. As this doesn't happen often, we can just
- * drop them all.
- */
- guest_pagetable_clear_all(cpu);
-}
-
-static bool is_hypercall(struct lg_cpu *cpu)
-{
- u8 insn[3];
-
- /*
- * This must be the Guest kernel trying to do something.
- * The bottom two bits of the CS segment register are the privilege
- * level.
- */
- if ((cpu->regs->cs & 3) != GUEST_PL)
- return false;
-
- /* Is it a vmcall? */
- __lgread(cpu, insn, guest_pa(cpu, cpu->regs->eip), sizeof(insn));
- return insn[0] == 0x0f && insn[1] == 0x01 && insn[2] == 0xc1;
-}
-
/*H:050 Once we've re-enabled interrupts, we look at why the Guest exited. */
void lguest_arch_handle_trap(struct lg_cpu *cpu)
{
@@ -429,20 +368,6 @@ void lguest_arch_handle_trap(struct lg_cpu *cpu)
if (emulate_insn(cpu))
return;
}
- /*
- * If KVM is active, the vmcall instruction triggers a General
- * Protection Fault. Normally it triggers an invalid opcode
- * fault (6):
- */
- case 6:
- /*
- * We need to check if ring == GUEST_PL and faulting
- * instruction == vmcall.
- */
- if (is_hypercall(cpu)) {
- rewrite_hypercall(cpu);
- return;
- }
break;
case 14: /* We've intercepted a Page Fault. */
/*
@@ -486,7 +411,7 @@ void lguest_arch_handle_trap(struct lg_cpu *cpu)
* These values mean a real interrupt occurred, in which case
* the Host handler has already been run. We just do a
* friendly check if another process should now be run, then
- * return to run the Guest again
+ * return to run the Guest again.
*/
cond_resched();
return;
@@ -536,7 +461,7 @@ void __init lguest_arch_host_init(void)
int i;
/*
- * Most of the i386/switcher.S doesn't care that it's been moved; on
+ * Most of the x86/switcher_32.S doesn't care that it's been moved; on
* Intel, jumps are relative, and it doesn't access any references to
* external code or data.
*
@@ -664,7 +589,7 @@ void __init lguest_arch_host_init(void)
clear_cpu_cap(&boot_cpu_data, X86_FEATURE_PGE);
}
put_online_cpus();
-};
+}
/*:*/
void __exit lguest_arch_host_fini(void)
@@ -747,8 +672,6 @@ int lguest_arch_init_hypercalls(struct lg_cpu *cpu)
/*:*/
/*L:030
- * lguest_arch_setup_regs()
- *
* Most of the Guest's registers are left alone: we used get_zeroed_page() to
* allocate the structure, so they will be 0.
*/