We copy 7 bytes at eip for userspace's instruction decode; we have to
carefully handle the case where eip is at the end of a page. We can't
leave this to userspace since kernel has all the page table decode
logic.
The decode logic moves to userspace, basically unchanged.
Signed-off-by: Rusty Russell <ru...@rustcorp.com.au>
---
drivers/lguest/x86/core.c | 133 +++++++++++++----------------------------
tools/lguest/lguest.c | 149 ++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 192 insertions(+), 90 deletions(-)
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index f7a16b4ea456..42e87bf14113 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -314,95 +314,52 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
* usually attached to a PC.
*
* When the Guest uses one of these instructions, we get a trap (General
- * Protection Fault) and come here. We see if it's one of those troublesome
- * instructions and skip over it. We return true if we did.
+ * Protection Fault) and come here. We queue this to be sent out to the
+ * Launcher to handle.
*/
-static int emulate_insn(struct lg_cpu *cpu)
-{
- u8 insn;
- unsigned int insnlen = 0, in = 0, small_operand = 0;
- /*
- * The eip contains the *virtual* address of the Guest's instruction:
- * walk the Guest's page tables to find the "physical" address.
- */
- unsigned long physaddr = guest_pa(cpu, cpu->regs->eip);
-
- /*
- * This must be the Guest kernel trying to do something, not userspace!
- * The bottom two bits of the CS segment register are the privilege
- * level.
- */
- if ((cpu->regs->cs & 3) != GUEST_PL)
- return 0;
- /* Decoding x86 instructions is icky. */
- insn = lgread(cpu, physaddr, u8);
-
- /*
- * Around 2.6.33, the kernel started using an emulation for the
- * cmpxchg8b instruction in early boot on many configurations. This
- * code isn't paravirtualized, and it tries to disable interrupts.
- * Ignore it, which will Mostly Work.
- */
- if (insn == 0xfa) {
- /* "cli", or Clear Interrupt Enable instruction. Skip it. */
- cpu->regs->eip++;
- return 1;
+/*
+ * The eip contains the *virtual* address of the Guest's instruction:
+ * we copy the instruction here so the Launcher doesn't have to walk
+ * the page tables to decode it. We handle the case (eg. in a kernel
+ * module) where the instruction is over two pages, and the pages are
+ * virtually but not physically contiguous.
+ *
+ * The longest possible x86 instruction is 15 bytes, but we don't handle
+ * anything that strange.
+ */
+static void copy_from_guest(struct lg_cpu *cpu,
+ void *dst, unsigned long vaddr, size_t len)
+{
+ size_t to_page_end = PAGE_SIZE - (vaddr % PAGE_SIZE);
+ unsigned long paddr;
+
+ BUG_ON(len > PAGE_SIZE);
+
+ /* If it goes over a page, copy in two parts. */
+ if (len > to_page_end) {
+ /* But make sure the next page is mapped! */
+ if (__guest_pa(cpu, vaddr + to_page_end, &paddr))
+ copy_from_guest(cpu, dst + to_page_end,
+ vaddr + to_page_end,
+ len - to_page_end);
+ else
+ /* Otherwise fill with zeroes. */
+ memset(dst + to_page_end, 0, len - to_page_end);
+ len = to_page_end;
}
- /*
- * 0x66 is an "operand prefix". It means a 16, not 32 bit in/out.
- */
- if (insn == 0x66) {
- small_operand = 1;
- /* The instruction is 1 byte so far, read the next byte. */
- insnlen = 1;
- insn = lgread(cpu, physaddr + insnlen, u8);
- }
+ /* This will kill the guest if it isn't mapped, but that
+ * shouldn't happen. */
+ __lgread(cpu, dst, guest_pa(cpu, vaddr), len);
+}
- /*
- * We can ignore the lower bit for the moment and decode the 4 opcodes
- * we need to emulate.
- */
- switch (insn & 0xFE) {
- case 0xE4: /* in <next byte>,%al */
- insnlen += 2;
- in = 1;
- break;
- case 0xEC: /* in (%dx),%al */
- insnlen += 1;
- in = 1;
- break;
- case 0xE6: /* out %al,<next byte> */
- insnlen += 2;
- break;
- case 0xEE: /* out %al,(%dx) */
- insnlen += 1;
- break;
- default:
- /* OK, we don't know what this is, can't emulate. */
- return 0;
- }
- /*
- * If it was an "IN" instruction, they expect the result to be read
- * into %eax, so we change %eax. We always return all-ones, which
- * traditionally means "there's nothing there".
- */
- if (in) {
- /* 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;
- /* Success! */
- return 1;
+static void setup_emulate_insn(struct lg_cpu *cpu)
+{
+ cpu->pending.trap = 13;
+ copy_from_guest(cpu, cpu->pending.insn, cpu->regs->eip,
+ sizeof(cpu->pending.insn));
}
/*H:050 Once we've re-enabled interrupts, we look at why the Guest exited. */
@@ -410,14 +367,10 @@ void lguest_arch_handle_trap(struct lg_cpu *cpu)
{
switch (cpu->regs->trapnum) {
case 13: /* We've intercepted a General Protection Fault. */
- /*
- * Check if this was one of those annoying IN or OUT
- * instructions which we need to emulate. If so, we just go
- * back into the Guest after we've done it.
- */
+ /* Hand to Launcher to emulate those pesky IN and OUT insns */
if (cpu->regs->errcode == 0) {
- if (emulate_insn(cpu))
- return;
+ setup_emulate_insn(cpu);
+ return;
}
break;
case 14: /* We've intercepted a Page Fault. */
diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c
index 0e754d04876d..b2217657f62c 100644
--- a/tools/lguest/lguest.c
+++ b/tools/lguest/lguest.c
@@ -41,6 +41,7 @@
#include <signal.h>
#include <pwd.h>
#include <grp.h>
+#include <sys/user.h>
#ifndef VIRTIO_F_ANY_LAYOUT
#define VIRTIO_F_ANY_LAYOUT 27
@@ -1143,6 +1144,150 @@ static void handle_output(unsigned long addr)
strnlen(from_guest_phys(addr), guest_limit - addr));
}
+/*L:216
+ * This is where we emulate a handful of Guest instructions. It's ugly
+ * and we used to do it in the kernel but it grew over time.
+ */
+
+/*
+ * We use the ptrace syscall's pt_regs struct to talk about registers
+ * to lguest: these macros convert the names to the offsets.
+ */
+#define getreg(name) getreg_off(offsetof(struct user_regs_struct, name))
+#define setreg(name, val) \
+ setreg_off(offsetof(struct user_regs_struct, name), (val))
+
+static u32 getreg_off(size_t offset)
+{
+ u32 r;
+ unsigned long args[] = { LHREQ_GETREG, offset };
+
+ if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0)
+ err(1, "Getting register %u", offset);
+ if (pread(lguest_fd, &r, sizeof(r), cpu_id) != sizeof(r))
+ err(1, "Reading register %u", offset);
+
+ return r;
+}
+
+static void setreg_off(size_t offset, u32 val)
+{
+ unsigned long args[] = { LHREQ_SETREG, offset, val };
+
+ if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0)
+ err(1, "Setting register %u", offset);
+}
+
+static void emulate_insn(const u8 insn[])
+{
+ unsigned long args[] = { LHREQ_TRAP, 13 };
+ unsigned int insnlen = 0, in = 0, small_operand = 0, byte_access;
+ unsigned int eax, port, mask;
+ /*
+ * We always return all-ones on IO port reads, which traditionally
+ * means "there's nothing there".
+ */
+ u32 val = 0xFFFFFFFF;
+
+ /*
+ * This must be the Guest kernel trying to do something, not userspace!
+ * The bottom two bits of the CS segment register are the privilege
+ * level.
+ */
+ if ((getreg(xcs) & 3) != 0x1)
+ goto no_emulate;
+
+ /* Decoding x86 instructions is icky. */
+
+ /*
+ * Around 2.6.33, the kernel started using an emulation for the
+ * cmpxchg8b instruction in early boot on many configurations. This
+ * code isn't paravirtualized, and it tries to disable interrupts.
+ * Ignore it, which will Mostly Work.
+ */
+ if (insn[insnlen] == 0xfa) {
+ /* "cli", or Clear Interrupt Enable instruction. Skip it. */
+ insnlen = 1;
+ goto skip_insn;
+ }
+
+ /*
+ * 0x66 is an "operand prefix". It means a 16, not 32 bit in/out.
+ */
+ if (insn[insnlen] == 0x66) {
+ small_operand = 1;
+ /* The instruction is 1 byte so far, read the next byte. */
+ insnlen = 1;
+ }
+
+ /* If the lower bit isn't set, it's a single byte access */
+ byte_access = !(insn[insnlen] & 1);
+
+ /*
+ * Now we can ignore the lower bit and decode the 4 opcodes
+ * we need to emulate.
+ */
+ switch (insn[insnlen] & 0xFE) {
+ case 0xE4: /* in <next byte>,%al */
+ port = insn[insnlen+1];
+ insnlen += 2;
+ in = 1;
+ break;
+ case 0xEC: /* in (%dx),%al */
+ port = getreg(edx) & 0xFFFF;
+ insnlen += 1;
+ in = 1;
+ break;
+ case 0xE6: /* out %al,<next byte> */
+ port = insn[insnlen+1];
+ insnlen += 2;
+ break;
+ case 0xEE: /* out %al,(%dx) */
+ port = getreg(edx) & 0xFFFF;
+ insnlen += 1;
+ break;
+ default:
+ /* OK, we don't know what this is, can't emulate. */
+ goto no_emulate;
+ }
+
+ /* Set a mask of the 1, 2 or 4 bytes, depending on size of IO */
+ if (byte_access)
+ mask = 0xFF;
+ else if (small_operand)
+ mask = 0xFFFF;
+ else
+ mask = 0xFFFFFFFF;
+
+ /*
+ * If it was an "IN" instruction, they expect the result to be read
+ * into %eax, so we change %eax.
+ */
+ eax = getreg(eax);
+
+ if (in) {
+ /* Clear the bits we're about to read */
+ eax &= ~mask;
+ /* Copy bits in from val. */
+ eax |= val & mask;
+ /* Now update the register. */
+ setreg(eax, eax);
+ }
+
+ verbose("IO %s of %x to %u: %#08x\n",
+ in ? "IN" : "OUT", mask, port, eax);
+skip_insn:
+ /* Finally, we've "done" the instruction, so move past it. */
+ setreg(eip, getreg(eip) + insnlen);
+ return;
+
+no_emulate:
+ /* Inject trap into Guest. */
+ if (write(lguest_fd, args, sizeof(args)) < 0)
+ err(1, "Reinjecting trap 13 for fault at %#x", getreg(eip));
+}
+
+
/*L:190
* Device Setup
*
@@ -1832,6 +1977,10 @@ static void __attribute__((noreturn)) run_guest(void)
verbose("Notify on address %#08x\n",
notify.addr);
handle_output(notify.addr);
+ } else if (notify.trap == 13) {
+ verbose("Emulating instruction at %#x\n",
+ getreg(eip));
+ emulate_insn(notify.insn);
} else
errx(1, "Unknown trap %i addr %#08x\n",
notify.trap, notify.addr);
--
2.1.0
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
