lguest: improve interrupt handling, speed up stream networking
lguest never checked for pending interrupts when enabling interrupts, and things still worked. However, it makes a significant difference to TCP performance, so it's time we fixed it by introducing a pending_irq flag and checking it on irq_restore and irq_enable. These two routines are now too big to patch into the 8/10 bytes patch space, so we drop that code. Note: The high latency on interrupt delivery had a very curious effect: once everything else was optimized, networking without GSO was faster than networking with GSO, since more interrupts were sent and hence a greater chance of one getting through to the Guest! Note2: (Almost) Closing the same loophole for iret doesn't have any measurable effect, so I'm leaving that patch for the moment. Before: 1GB tcpblast Guest->Host: 30.7 seconds 1GB tcpblast Guest->Host (no GSO): 76.0 seconds After: 1GB tcpblast Guest->Host: 6.8 seconds 1GB tcpblast Guest->Host (no GSO): 27.8 seconds Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
This commit is contained in:
@@ -189,6 +189,7 @@ int run_guest(struct lg_cpu *cpu, unsigned long __user *user)
|
||||
/* We stop running once the Guest is dead. */
|
||||
while (!cpu->lg->dead) {
|
||||
unsigned int irq;
|
||||
bool more;
|
||||
|
||||
/* First we run any hypercalls the Guest wants done. */
|
||||
if (cpu->hcall)
|
||||
@@ -213,9 +214,9 @@ int run_guest(struct lg_cpu *cpu, unsigned long __user *user)
|
||||
/* Check if there are any interrupts which can be delivered now:
|
||||
* if so, this sets up the hander to be executed when we next
|
||||
* run the Guest. */
|
||||
irq = interrupt_pending(cpu);
|
||||
irq = interrupt_pending(cpu, &more);
|
||||
if (irq < LGUEST_IRQS)
|
||||
try_deliver_interrupt(cpu, irq);
|
||||
try_deliver_interrupt(cpu, irq, more);
|
||||
|
||||
/* All long-lived kernel loops need to check with this horrible
|
||||
* thing called the freezer. If the Host is trying to suspend,
|
||||
@@ -233,7 +234,7 @@ int run_guest(struct lg_cpu *cpu, unsigned long __user *user)
|
||||
set_current_state(TASK_INTERRUPTIBLE);
|
||||
/* Just before we sleep, make sure nothing snuck in
|
||||
* which we should be doing. */
|
||||
if (interrupt_pending(cpu) < LGUEST_IRQS
|
||||
if (interrupt_pending(cpu, &more) < LGUEST_IRQS
|
||||
|| cpu->break_out)
|
||||
set_current_state(TASK_RUNNING);
|
||||
else
|
||||
|
@@ -37,6 +37,10 @@ static void do_hcall(struct lg_cpu *cpu, struct hcall_args *args)
|
||||
/* This call does nothing, except by breaking out of the Guest
|
||||
* it makes us process all the asynchronous hypercalls. */
|
||||
break;
|
||||
case LHCALL_SEND_INTERRUPTS:
|
||||
/* This call does nothing too, but by breaking out of the Guest
|
||||
* it makes us process any pending interrupts. */
|
||||
break;
|
||||
case LHCALL_LGUEST_INIT:
|
||||
/* You can't get here unless you're already initialized. Don't
|
||||
* do that. */
|
||||
|
@@ -131,7 +131,7 @@ static void set_guest_interrupt(struct lg_cpu *cpu, u32 lo, u32 hi,
|
||||
* interrupt_pending() returns the first pending interrupt which isn't blocked
|
||||
* by the Guest. It is called before every entry to the Guest, and just before
|
||||
* we go to sleep when the Guest has halted itself. */
|
||||
unsigned int interrupt_pending(struct lg_cpu *cpu)
|
||||
unsigned int interrupt_pending(struct lg_cpu *cpu, bool *more)
|
||||
{
|
||||
unsigned int irq;
|
||||
DECLARE_BITMAP(blk, LGUEST_IRQS);
|
||||
@@ -149,13 +149,14 @@ unsigned int interrupt_pending(struct lg_cpu *cpu)
|
||||
|
||||
/* Find the first interrupt. */
|
||||
irq = find_first_bit(blk, LGUEST_IRQS);
|
||||
*more = find_next_bit(blk, LGUEST_IRQS, irq+1);
|
||||
|
||||
return irq;
|
||||
}
|
||||
|
||||
/* This actually diverts the Guest to running an interrupt handler, once an
|
||||
* interrupt has been identified by interrupt_pending(). */
|
||||
void try_deliver_interrupt(struct lg_cpu *cpu, unsigned int irq)
|
||||
void try_deliver_interrupt(struct lg_cpu *cpu, unsigned int irq, bool more)
|
||||
{
|
||||
struct desc_struct *idt;
|
||||
|
||||
@@ -178,8 +179,12 @@ void try_deliver_interrupt(struct lg_cpu *cpu, unsigned int irq)
|
||||
u32 irq_enabled;
|
||||
if (get_user(irq_enabled, &cpu->lg->lguest_data->irq_enabled))
|
||||
irq_enabled = 0;
|
||||
if (!irq_enabled)
|
||||
if (!irq_enabled) {
|
||||
/* Make sure they know an IRQ is pending. */
|
||||
put_user(X86_EFLAGS_IF,
|
||||
&cpu->lg->lguest_data->irq_pending);
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
/* Look at the IDT entry the Guest gave us for this interrupt. The
|
||||
@@ -202,6 +207,11 @@ void try_deliver_interrupt(struct lg_cpu *cpu, unsigned int irq)
|
||||
* here is a compromise which means at least it gets updated every
|
||||
* timer interrupt. */
|
||||
write_timestamp(cpu);
|
||||
|
||||
/* If there are no other interrupts we want to deliver, clear
|
||||
* the pending flag. */
|
||||
if (!more)
|
||||
put_user(0, &cpu->lg->lguest_data->irq_pending);
|
||||
}
|
||||
/*:*/
|
||||
|
||||
|
@@ -139,8 +139,8 @@ int run_guest(struct lg_cpu *cpu, unsigned long __user *user);
|
||||
#define pgd_pfn(x) (pgd_val(x) >> PAGE_SHIFT)
|
||||
|
||||
/* interrupts_and_traps.c: */
|
||||
unsigned int interrupt_pending(struct lg_cpu *cpu);
|
||||
void try_deliver_interrupt(struct lg_cpu *cpu, unsigned int irq);
|
||||
unsigned int interrupt_pending(struct lg_cpu *cpu, bool *more);
|
||||
void try_deliver_interrupt(struct lg_cpu *cpu, unsigned int irq, bool more);
|
||||
bool deliver_trap(struct lg_cpu *cpu, unsigned int num);
|
||||
void load_guest_idt_entry(struct lg_cpu *cpu, unsigned int i,
|
||||
u32 low, u32 hi);
|
||||
|
Reference in New Issue
Block a user