linux-sg2042/drivers/lguest/x86/switcher_32.S

389 lines
13 KiB
ArmAsm
Raw Normal View History

/*P:900
* This is the Switcher: code which sits at 0xFFC00000 (or 0xFFE00000) astride
* both the Host and Guest to do the low-level Guest<->Host switch. It is as
* simple as it can be made, but it's naturally very specific to x86.
*
* You have now completed Preparation. If this has whet your appetite; if you
* are feeling invigorated and refreshed then the next, more challenging stage
* can be found in "make Guest".
:*/
/*M:012
* Lguest is meant to be simple: my rule of thumb is that 1% more LOC must
* gain at least 1% more performance. Since neither LOC nor performance can be
* measured beforehand, it generally means implementing a feature then deciding
* if it's worth it. And once it's implemented, who can say no?
*
* This is why I haven't implemented this idea myself. I want to, but I
* haven't. You could, though.
*
* The main place where lguest performance sucks is Guest page faulting. When
* a Guest userspace process hits an unmapped page we switch back to the Host,
* walk the page tables, find it's not mapped, switch back to the Guest page
* fault handler, which calls a hypercall to set the page table entry, then
* finally returns to userspace. That's two round-trips.
*
* If we had a small walker in the Switcher, we could quickly check the Guest
* page table and if the page isn't mapped, immediately reflect the fault back
* into the Guest. This means the Switcher would have to know the top of the
* Guest page table and the page fault handler address.
*
* For simplicity, the Guest should only handle the case where the privilege
* level of the fault is 3 and probably only not present or write faults. It
* should also detect recursive faults, and hand the original fault to the
* Host (which is actually really easy).
*
* Two questions remain. Would the performance gain outweigh the complexity?
* And who would write the verse documenting it?
:*/
/*M:011
* Lguest64 handles NMI. This gave me NMI envy (until I looked at their
* code). It's worth doing though, since it would let us use oprofile in the
* Host when a Guest is running.
:*/
/*S:100
* Welcome to the Switcher itself!
*
* This file contains the low-level code which changes the CPU to run the Guest
* code, and returns to the Host when something happens. Understand this, and
* you understand the heart of our journey.
*
* Because this is in assembler rather than C, our tale switches from prose to
* verse. First I tried limericks:
*
* There once was an eax reg,
* To which our pointer was fed,
* It needed an add,
* Which asm-offsets.h had
* But this limerick is hurting my head.
*
* Next I tried haikus, but fitting the required reference to the seasons in
* every stanza was quickly becoming tiresome:
*
* The %eax reg
* Holds "struct lguest_pages" now:
* Cherry blossoms fall.
*
* Then I started with Heroic Verse, but the rhyming requirement leeched away
* the content density and led to some uniquely awful oblique rhymes:
*
* These constants are coming from struct offsets
* For use within the asm switcher text.
*
* Finally, I settled for something between heroic hexameter, and normal prose
* with inappropriate linebreaks. Anyway, it aint no Shakespeare.
*/
// Not all kernel headers work from assembler
// But these ones are needed: the ENTRY() define
// And constants extracted from struct offsets
// To avoid magic numbers and breakage:
// Should they change the compiler can't save us
// Down here in the depths of assembler code.
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#include <asm/page.h>
#include <asm/segment.h>
#include <asm/lguest.h>
// We mark the start of the code to copy
// It's placed in .text tho it's never run here
// You'll see the trick macro at the end
// Which interleaves data and text to effect.
.text
ENTRY(start_switcher_text)
// When we reach switch_to_guest we have just left
// The safe and comforting shores of C code
// %eax has the "struct lguest_pages" to use
// Where we save state and still see it from the Guest
// And %ebx holds the Guest shadow pagetable:
// Once set we have truly left Host behind.
ENTRY(switch_to_guest)
// We told gcc all its regs could fade,
// Clobbered by our journey into the Guest
// We could have saved them, if we tried
// But time is our master and cycles count.
// Segment registers must be saved for the Host
// We push them on the Host stack for later
pushl %es
pushl %ds
pushl %gs
pushl %fs
// But the compiler is fickle, and heeds
// No warning of %ebp clobbers
// When frame pointers are used. That register
// Must be saved and restored or chaos strikes.
pushl %ebp
// The Host's stack is done, now save it away
// In our "struct lguest_pages" at offset
// Distilled into asm-offsets.h
movl %esp, LGUEST_PAGES_host_sp(%eax)
// All saved and there's now five steps before us:
// Stack, GDT, IDT, TSS
// Then last of all the page tables are flipped.
// Yet beware that our stack pointer must be
// Always valid lest an NMI hits
// %edx does the duty here as we juggle
// %eax is lguest_pages: our stack lies within.
movl %eax, %edx
addl $LGUEST_PAGES_regs, %edx
movl %edx, %esp
// The Guest's GDT we so carefully
// Placed in the "struct lguest_pages" before
lgdt LGUEST_PAGES_guest_gdt_desc(%eax)
// The Guest's IDT we did partially
// Copy to "struct lguest_pages" as well.
lidt LGUEST_PAGES_guest_idt_desc(%eax)
// The TSS entry which controls traps
// Must be loaded up with "ltr" now:
// The GDT entry that TSS uses
// Changes type when we load it: damn Intel!
// For after we switch over our page tables
// That entry will be read-only: we'd crash.
movl $(GDT_ENTRY_TSS*8), %edx
ltr %dx
// Look back now, before we take this last step!
// The Host's TSS entry was also marked used;
// Let's clear it again for our return.
// The GDT descriptor of the Host
// Points to the table after two "size" bytes
movl (LGUEST_PAGES_host_gdt_desc+2)(%eax), %edx
// Clear "used" from type field (byte 5, bit 2)
andb $0xFD, (GDT_ENTRY_TSS*8 + 5)(%edx)
// Once our page table's switched, the Guest is live!
// The Host fades as we run this final step.
// Our "struct lguest_pages" is now read-only.
movl %ebx, %cr3
// The page table change did one tricky thing:
// The Guest's register page has been mapped
// Writable under our %esp (stack) --
// We can simply pop off all Guest regs.
popl %eax
popl %ebx
popl %ecx
popl %edx
popl %esi
popl %edi
popl %ebp
popl %gs
popl %fs
popl %ds
popl %es
// Near the base of the stack lurk two strange fields
// Which we fill as we exit the Guest
// These are the trap number and its error
// We can simply step past them on our way.
addl $8, %esp
// The last five stack slots hold return address
// And everything needed to switch privilege
// From Switcher's level 0 to Guest's 1,
// And the stack where the Guest had last left it.
// Interrupts are turned back on: we are Guest.
iret
// We tread two paths to switch back to the Host
// Yet both must save Guest state and restore Host
// So we put the routine in a macro.
#define SWITCH_TO_HOST \
/* We save the Guest state: all registers first \
* Laid out just as "struct lguest_regs" defines */ \
pushl %es; \
pushl %ds; \
pushl %fs; \
pushl %gs; \
pushl %ebp; \
pushl %edi; \
pushl %esi; \
pushl %edx; \
pushl %ecx; \
pushl %ebx; \
pushl %eax; \
/* Our stack and our code are using segments \
* Set in the TSS and IDT \
* Yet if we were to touch data we'd use \
* Whatever data segment the Guest had. \
* Load the lguest ds segment for now. */ \
movl $(LGUEST_DS), %eax; \
movl %eax, %ds; \
/* So where are we? Which CPU, which struct? \
* The stack is our clue: our TSS starts \
* It at the end of "struct lguest_pages". \
* Or we may have stumbled while restoring \
* Our Guest segment regs while in switch_to_guest, \
* The fault pushed atop that part-unwound stack. \
* If we round the stack down to the page start \
* We're at the start of "struct lguest_pages". */ \
movl %esp, %eax; \
andl $(~(1 << PAGE_SHIFT - 1)), %eax; \
/* Save our trap number: the switch will obscure it \
* (In the Host the Guest regs are not mapped here) \
* %ebx holds it safe for deliver_to_host */ \
movl LGUEST_PAGES_regs_trapnum(%eax), %ebx; \
/* The Host GDT, IDT and stack! \
* All these lie safely hidden from the Guest: \
* We must return to the Host page tables \
* (Hence that was saved in struct lguest_pages) */ \
movl LGUEST_PAGES_host_cr3(%eax), %edx; \
movl %edx, %cr3; \
/* As before, when we looked back at the Host \
* As we left and marked TSS unused \
* So must we now for the Guest left behind. */ \
andb $0xFD, (LGUEST_PAGES_guest_gdt+GDT_ENTRY_TSS*8+5)(%eax); \
/* Switch to Host's GDT, IDT. */ \
lgdt LGUEST_PAGES_host_gdt_desc(%eax); \
lidt LGUEST_PAGES_host_idt_desc(%eax); \
/* Restore the Host's stack where its saved regs lie */ \
movl LGUEST_PAGES_host_sp(%eax), %esp; \
/* Last the TSS: our Host is returned */ \
movl $(GDT_ENTRY_TSS*8), %edx; \
ltr %dx; \
/* Restore now the regs saved right at the first. */ \
popl %ebp; \
popl %fs; \
popl %gs; \
popl %ds; \
popl %es
// The first path is trod when the Guest has trapped:
// (Which trap it was has been pushed on the stack).
// We need only switch back, and the Host will decode
// Why we came home, and what needs to be done.
return_to_host:
SWITCH_TO_HOST
iret
// We are lead to the second path like so:
// An interrupt, with some cause external
// Has ajerked us rudely from the Guest's code
// Again we must return home to the Host
deliver_to_host:
SWITCH_TO_HOST
// But now we must go home via that place
// Where that interrupt was supposed to go
// Had we not been ensconced, running the Guest.
// Here we see the trickness of run_guest_once():
// The Host stack is formed like an interrupt
// With EIP, CS and EFLAGS layered.
// Interrupt handlers end with "iret"
// And that will take us home at long long last.
// But first we must find the handler to call!
// The IDT descriptor for the Host
// Has two bytes for size, and four for address:
// %edx will hold it for us for now.
movl (LGUEST_PAGES_host_idt_desc+2)(%eax), %edx
// We now know the table address we need,
// And saved the trap's number inside %ebx.
// Yet the pointer to the handler is smeared
// Across the bits of the table entry.
// What oracle can tell us how to extract
// From such a convoluted encoding?
// I consulted gcc, and it gave
// These instructions, which I gladly credit:
leal (%edx,%ebx,8), %eax
movzwl (%eax),%edx
movl 4(%eax), %eax
xorw %ax, %ax
orl %eax, %edx
// Now the address of the handler's in %edx
// We call it now: its "iret" drops us home.
jmp *%edx
// Every interrupt can come to us here
// But we must truly tell each apart.
// They number two hundred and fifty six
// And each must land in a different spot,
// Push its number on stack, and join the stream.
// And worse, a mere six of the traps stand apart
// And push on their stack an addition:
// An error number, thirty two bits long
// So we punish the other two fifty
// And make them push a zero so they match.
// Yet two fifty six entries is long
// And all will look most the same as the last
// So we create a macro which can make
// As many entries as we need to fill.
// Note the change to .data then .text:
// We plant the address of each entry
// Into a (data) table for the Host
// To know where each Guest interrupt should go.
.macro IRQ_STUB N TARGET
.data; .long 1f; .text; 1:
// Trap eight, ten through fourteen and seventeen
// Supply an error number. Else zero.
.if (\N <> 8) && (\N < 10 || \N > 14) && (\N <> 17)
pushl $0
.endif
pushl $\N
jmp \TARGET
ALIGN
.endm
// This macro creates numerous entries
// Using GAS macros which out-power C's.
.macro IRQ_STUBS FIRST LAST TARGET
irq=\FIRST
.rept \LAST-\FIRST+1
IRQ_STUB irq \TARGET
irq=irq+1
.endr
.endm
// Here's the marker for our pointer table
// Laid in the data section just before
// Each macro places the address of code
// Forming an array: each one points to text
// Which handles interrupt in its turn.
.data
.global default_idt_entries
default_idt_entries:
.text
// The first two traps go straight back to the Host
IRQ_STUBS 0 1 return_to_host
// We'll say nothing, yet, about NMI
IRQ_STUB 2 handle_nmi
// Other traps also return to the Host
IRQ_STUBS 3 31 return_to_host
// All interrupts go via their handlers
IRQ_STUBS 32 127 deliver_to_host
// 'Cept system calls coming from userspace
// Are to go to the Guest, never the Host.
IRQ_STUB 128 return_to_host
IRQ_STUBS 129 255 deliver_to_host
// The NMI, what a fabulous beast
// Which swoops in and stops us no matter that
// We're suspended between heaven and hell,
// (Or more likely between the Host and Guest)
// When in it comes! We are dazed and confused
// So we do the simplest thing which one can.
// Though we've pushed the trap number and zero
// We discard them, return, and hope we live.
handle_nmi:
addl $8, %esp
iret
// We are done; all that's left is Mastery
// And "make Mastery" is a journey long
// Designed to make your fingers itch to code.
// Here ends the text, the file and poem.
ENTRY(end_switcher_text)