lguest: remove NOTIFY call and eventfd facility.

Disappointing, as this was kind of neat (especially getting to use RCU
to manage the address -> eventfd mapping).  But now the devices are PCI
handled in userspace, we get rid of both the NOTIFY hypercall and
the interface to connect an eventfd.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
This commit is contained in:
Rusty Russell 2015-02-11 15:28:01 +10:30
parent 00f8d54651
commit d9bab50aa4
6 changed files with 10 additions and 215 deletions

View File

@ -16,7 +16,6 @@
#define LHCALL_SET_PTE 14
#define LHCALL_SET_PGD 15
#define LHCALL_LOAD_TLS 16
#define LHCALL_NOTIFY 17
#define LHCALL_LOAD_GDT_ENTRY 18
#define LHCALL_SEND_INTERRUPTS 19

View File

@ -225,22 +225,12 @@ int run_guest(struct lg_cpu *cpu, unsigned long __user *user)
if (cpu->hcall)
do_hypercalls(cpu);
/*
* It's possible the Guest did a NOTIFY hypercall to the
* Launcher.
*/
/* Do we have to tell the Launcher about a trap? */
if (cpu->pending.trap) {
/*
* Does it just needs to write to a registered
* eventfd (ie. the appropriate virtqueue thread)?
*/
if (!send_notify_to_eventfd(cpu)) {
/* OK, we tell the main Launcher. */
if (copy_to_user(user, &cpu->pending,
sizeof(cpu->pending)))
return -EFAULT;
return sizeof(cpu->pending);
}
if (copy_to_user(user, &cpu->pending,
sizeof(cpu->pending)))
return -EFAULT;
return sizeof(cpu->pending);
}
/*

View File

@ -117,10 +117,6 @@ static void do_hcall(struct lg_cpu *cpu, struct hcall_args *args)
/* Similarly, this sets the halted flag for run_guest(). */
cpu->halted = 1;
break;
case LHCALL_NOTIFY:
cpu->pending.trap = LGUEST_TRAP_ENTRY;
cpu->pending.addr = args->arg1;
break;
default:
/* It should be an architecture-specific hypercall. */
if (lguest_arch_do_hcall(cpu, args))

View File

@ -81,16 +81,6 @@ struct lg_cpu {
struct lg_cpu_arch arch;
};
struct lg_eventfd {
unsigned long addr;
struct eventfd_ctx *event;
};
struct lg_eventfd_map {
unsigned int num;
struct lg_eventfd map[];
};
/* The private info the thread maintains about the guest. */
struct lguest {
struct lguest_data __user *lguest_data;
@ -117,8 +107,6 @@ struct lguest {
unsigned int stack_pages;
u32 tsc_khz;
struct lg_eventfd_map *eventfds;
/* Dead? */
const char *dead;
};

View File

@ -2,182 +2,20 @@
* launcher controls and communicates with the Guest. For example,
* the first write will tell us the Guest's memory layout and entry
* point. A read will run the Guest until something happens, such as
* a signal or the Guest doing a NOTIFY out to the Launcher. There is
* also a way for the Launcher to attach eventfds to particular NOTIFY
* values instead of returning from the read() call.
* a signal or the Guest accessing a device.
:*/
#include <linux/uaccess.h>
#include <linux/miscdevice.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/eventfd.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/export.h>
#include "lg.h"
/*L:056
* Before we move on, let's jump ahead and look at what the kernel does when
* it needs to look up the eventfds. That will complete our picture of how we
* use RCU.
*
* The notification value is in cpu->pending_notify: we return true if it went
* to an eventfd.
*/
bool send_notify_to_eventfd(struct lg_cpu *cpu)
{
unsigned int i;
struct lg_eventfd_map *map;
/* We only connect LHCALL_NOTIFY to event fds, not other traps. */
if (cpu->pending.trap != LGUEST_TRAP_ENTRY)
return false;
/*
* This "rcu_read_lock()" helps track when someone is still looking at
* the (RCU-using) eventfds array. It's not actually a lock at all;
* indeed it's a noop in many configurations. (You didn't expect me to
* explain all the RCU secrets here, did you?)
*/
rcu_read_lock();
/*
* rcu_dereference is the counter-side of rcu_assign_pointer(); it
* makes sure we don't access the memory pointed to by
* cpu->lg->eventfds before cpu->lg->eventfds is set. Sounds crazy,
* but Alpha allows this! Paul McKenney points out that a really
* aggressive compiler could have the same effect:
* http://lists.ozlabs.org/pipermail/lguest/2009-July/001560.html
*
* So play safe, use rcu_dereference to get the rcu-protected pointer:
*/
map = rcu_dereference(cpu->lg->eventfds);
/*
* Simple array search: even if they add an eventfd while we do this,
* we'll continue to use the old array and just won't see the new one.
*/
for (i = 0; i < map->num; i++) {
if (map->map[i].addr == cpu->pending.addr) {
eventfd_signal(map->map[i].event, 1);
cpu->pending.trap = 0;
break;
}
}
/* We're done with the rcu-protected variable cpu->lg->eventfds. */
rcu_read_unlock();
/* If we cleared the notification, it's because we found a match. */
return cpu->pending.trap == 0;
}
/*L:055
* One of the more tricksy tricks in the Linux Kernel is a technique called
* Read Copy Update. Since one point of lguest is to teach lguest journeyers
* about kernel coding, I use it here. (In case you're curious, other purposes
* include learning about virtualization and instilling a deep appreciation for
* simplicity and puppies).
*
* We keep a simple array which maps LHCALL_NOTIFY values to eventfds, but we
* add new eventfds without ever blocking readers from accessing the array.
* The current Launcher only does this during boot, so that never happens. But
* Read Copy Update is cool, and adding a lock risks damaging even more puppies
* than this code does.
*
* We allocate a brand new one-larger array, copy the old one and add our new
* element. Then we make the lg eventfd pointer point to the new array.
* That's the easy part: now we need to free the old one, but we need to make
* sure no slow CPU somewhere is still looking at it. That's what
* synchronize_rcu does for us: waits until every CPU has indicated that it has
* moved on to know it's no longer using the old one.
*
* If that's unclear, see http://en.wikipedia.org/wiki/Read-copy-update.
*/
static int add_eventfd(struct lguest *lg, unsigned long addr, int fd)
{
struct lg_eventfd_map *new, *old = lg->eventfds;
/*
* We don't allow notifications on value 0 anyway (pending_notify of
* 0 means "nothing pending").
*/
if (!addr)
return -EINVAL;
/*
* Replace the old array with the new one, carefully: others can
* be accessing it at the same time.
*/
new = kmalloc(sizeof(*new) + sizeof(new->map[0]) * (old->num + 1),
GFP_KERNEL);
if (!new)
return -ENOMEM;
/* First make identical copy. */
memcpy(new->map, old->map, sizeof(old->map[0]) * old->num);
new->num = old->num;
/* Now append new entry. */
new->map[new->num].addr = addr;
new->map[new->num].event = eventfd_ctx_fdget(fd);
if (IS_ERR(new->map[new->num].event)) {
int err = PTR_ERR(new->map[new->num].event);
kfree(new);
return err;
}
new->num++;
/*
* Now put new one in place: rcu_assign_pointer() is a fancy way of
* doing "lg->eventfds = new", but it uses memory barriers to make
* absolutely sure that the contents of "new" written above is nailed
* down before we actually do the assignment.
*
* We have to think about these kinds of things when we're operating on
* live data without locks.
*/
rcu_assign_pointer(lg->eventfds, new);
/*
* We're not in a big hurry. Wait until no one's looking at old
* version, then free it.
*/
synchronize_rcu();
kfree(old);
return 0;
}
/*L:052
* Receiving notifications from the Guest is usually done by attaching a
* particular LHCALL_NOTIFY value to an event filedescriptor. The eventfd will
* become readable when the Guest does an LHCALL_NOTIFY with that value.
*
* This is really convenient for processing each virtqueue in a separate
* thread.
*/
static int attach_eventfd(struct lguest *lg, const unsigned long __user *input)
{
unsigned long addr, fd;
int err;
if (get_user(addr, input) != 0)
return -EFAULT;
input++;
if (get_user(fd, input) != 0)
return -EFAULT;
/*
* Just make sure two callers don't add eventfds at once. We really
* only need to lock against callers adding to the same Guest, so using
* the Big Lguest Lock is overkill. But this is setup, not a fast path.
*/
mutex_lock(&lguest_lock);
err = add_eventfd(lg, addr, fd);
mutex_unlock(&lguest_lock);
return err;
}
/* The Launcher can get the registers, and also set some of them. */
The Launcher can get the registers, and also set some of them.
*/
static int getreg_setup(struct lg_cpu *cpu, const unsigned long __user *input)
{
unsigned long which;
@ -409,13 +247,6 @@ static int initialize(struct file *file, const unsigned long __user *input)
goto unlock;
}
lg->eventfds = kmalloc(sizeof(*lg->eventfds), GFP_KERNEL);
if (!lg->eventfds) {
err = -ENOMEM;
goto free_lg;
}
lg->eventfds->num = 0;
/* Populate the easy fields of our "struct lguest" */
lg->mem_base = (void __user *)args[0];
lg->pfn_limit = args[1];
@ -424,7 +255,7 @@ static int initialize(struct file *file, const unsigned long __user *input)
/* This is the first cpu (cpu 0) and it will start booting at args[2] */
err = lg_cpu_start(&lg->cpus[0], 0, args[2]);
if (err)
goto free_eventfds;
goto free_lg;
/*
* Initialize the Guest's shadow page tables. This allocates
@ -445,8 +276,6 @@ static int initialize(struct file *file, const unsigned long __user *input)
free_regs:
/* FIXME: This should be in free_vcpu */
free_page(lg->cpus[0].regs_page);
free_eventfds:
kfree(lg->eventfds);
free_lg:
kfree(lg);
unlock:
@ -499,8 +328,6 @@ static ssize_t write(struct file *file, const char __user *in,
return initialize(file, input);
case LHREQ_IRQ:
return user_send_irq(cpu, input);
case LHREQ_EVENTFD:
return attach_eventfd(lg, input);
case LHREQ_GETREG:
return getreg_setup(cpu, input);
case LHREQ_SETREG:
@ -551,11 +378,6 @@ static int close(struct inode *inode, struct file *file)
mmput(lg->cpus[i].mm);
}
/* Release any eventfds they registered. */
for (i = 0; i < lg->eventfds->num; i++)
eventfd_ctx_put(lg->eventfds->map[i].event);
kfree(lg->eventfds);
/*
* If lg->dead doesn't contain an error code it will be NULL or a
* kmalloc()ed string, either of which is ok to hand to kfree().

View File

@ -23,7 +23,7 @@ enum lguest_req
LHREQ_GETDMA, /* No longer used */
LHREQ_IRQ, /* + irq */
LHREQ_BREAK, /* No longer used */
LHREQ_EVENTFD, /* + address, fd. */
LHREQ_EVENTFD, /* No longer used. */
LHREQ_GETREG, /* + offset within struct pt_regs (then read value). */
LHREQ_SETREG, /* + offset within struct pt_regs, value. */
LHREQ_TRAP, /* + trap number to deliver to guest. */