summaryrefslogtreecommitdiffstats
path: root/sys/amd64/include
diff options
context:
space:
mode:
authorgibbs <gibbs@FreeBSD.org>2013-08-29 19:52:18 +0000
committergibbs <gibbs@FreeBSD.org>2013-08-29 19:52:18 +0000
commitfcdbf70fd9ffe66a2cd744ca6626d7f87b39e593 (patch)
tree645c89eddfbfb23b9b30e45b882f5beb39a4a267 /sys/amd64/include
parentd60bb760ec3e7d8592b384e51bf1e6402f0e8700 (diff)
downloadFreeBSD-src-fcdbf70fd9ffe66a2cd744ca6626d7f87b39e593.zip
FreeBSD-src-fcdbf70fd9ffe66a2cd744ca6626d7f87b39e593.tar.gz
Implement vector callback for PVHVM and unify event channel implementations
Re-structure Xen HVM support so that: - Xen is detected and hypercalls can be performed very early in system startup. - Xen interrupt services are implemented using FreeBSD's native interrupt delivery infrastructure. - the Xen interrupt service implementation is shared between PV and HVM guests. - Xen interrupt handlers can optionally use a filter handler in order to avoid the overhead of dispatch to an interrupt thread. - interrupt load can be distributed among all available CPUs. - the overhead of accessing the emulated local and I/O apics on HVM is removed for event channel port events. - a similar optimization can eventually, and fairly easily, be used to optimize MSI. Early Xen detection, HVM refactoring, PVHVM interrupt infrastructure, and misc Xen cleanups: Sponsored by: Spectra Logic Corporation Unification of PV & HVM interrupt infrastructure, bug fixes, and misc Xen cleanups: Submitted by: Roger Pau Monné Sponsored by: Citrix Systems R&D sys/x86/x86/local_apic.c: sys/amd64/include/apicvar.h: sys/i386/include/apicvar.h: sys/amd64/amd64/apic_vector.S: sys/i386/i386/apic_vector.s: sys/amd64/amd64/machdep.c: sys/i386/i386/machdep.c: sys/i386/xen/exception.s: sys/x86/include/segments.h: Reserve IDT vector 0x93 for the Xen event channel upcall interrupt handler. On Hypervisors that support the direct vector callback feature, we can request that this vector be called directly by an injected HVM interrupt event, instead of a simulated PCI interrupt on the Xen platform PCI device. This avoids all of the overhead of dealing with the emulated I/O APIC and local APIC. It also means that the Hypervisor can inject these events on any CPU, allowing upcalls for different ports to be handled in parallel. sys/amd64/amd64/mp_machdep.c: sys/i386/i386/mp_machdep.c: Map Xen per-vcpu area during AP startup. sys/amd64/include/intr_machdep.h: sys/i386/include/intr_machdep.h: Increase the FreeBSD IRQ vector table to include space for event channel interrupt sources. sys/amd64/include/pcpu.h: sys/i386/include/pcpu.h: Remove Xen HVM per-cpu variable data. These fields are now allocated via the dynamic per-cpu scheme. See xen_intr.c for details. sys/amd64/include/xen/hypercall.h: sys/dev/xen/blkback/blkback.c: sys/i386/include/xen/xenvar.h: sys/i386/xen/clock.c: sys/i386/xen/xen_machdep.c: sys/xen/gnttab.c: Prefer FreeBSD primatives to Linux ones in Xen support code. sys/amd64/include/xen/xen-os.h: sys/i386/include/xen/xen-os.h: sys/xen/xen-os.h: sys/dev/xen/balloon/balloon.c: sys/dev/xen/blkback/blkback.c: sys/dev/xen/blkfront/blkfront.c: sys/dev/xen/console/xencons_ring.c: sys/dev/xen/control/control.c: sys/dev/xen/netback/netback.c: sys/dev/xen/netfront/netfront.c: sys/dev/xen/xenpci/xenpci.c: sys/i386/i386/machdep.c: sys/i386/include/pmap.h: sys/i386/include/xen/xenfunc.h: sys/i386/isa/npx.c: sys/i386/xen/clock.c: sys/i386/xen/mp_machdep.c: sys/i386/xen/mptable.c: sys/i386/xen/xen_clock_util.c: sys/i386/xen/xen_machdep.c: sys/i386/xen/xen_rtc.c: sys/xen/evtchn/evtchn_dev.c: sys/xen/features.c: sys/xen/gnttab.c: sys/xen/gnttab.h: sys/xen/hvm.h: sys/xen/xenbus/xenbus.c: sys/xen/xenbus/xenbus_if.m: sys/xen/xenbus/xenbusb_front.c: sys/xen/xenbus/xenbusvar.h: sys/xen/xenstore/xenstore.c: sys/xen/xenstore/xenstore_dev.c: sys/xen/xenstore/xenstorevar.h: Pull common Xen OS support functions/settings into xen/xen-os.h. sys/amd64/include/xen/xen-os.h: sys/i386/include/xen/xen-os.h: sys/xen/xen-os.h: Remove constants, macros, and functions unused in FreeBSD's Xen support. sys/xen/xen-os.h: sys/i386/xen/xen_machdep.c: sys/x86/xen/hvm.c: Introduce new functions xen_domain(), xen_pv_domain(), and xen_hvm_domain(). These are used in favor of #ifdefs so that FreeBSD can dynamically detect and adapt to the presence of a hypervisor. The goal is to have an HVM optimized GENERIC, but more is necessary before this is possible. sys/amd64/amd64/machdep.c: sys/dev/xen/xenpci/xenpcivar.h: sys/dev/xen/xenpci/xenpci.c: sys/x86/xen/hvm.c: sys/sys/kernel.h: Refactor magic ioport, Hypercall table and Hypervisor shared information page setup, and move it to a dedicated HVM support module. HVM mode initialization is now triggered during the SI_SUB_HYPERVISOR phase of system startup. This currently occurs just after the kernel VM is fully setup which is just enough infrastructure to allow the hypercall table and shared info page to be properly mapped. sys/xen/hvm.h: sys/x86/xen/hvm.c: Add definitions and a method for configuring Hypervisor event delievery via a direct vector callback. sys/amd64/include/xen/xen-os.h: sys/x86/xen/hvm.c: sys/conf/files: sys/conf/files.amd64: sys/conf/files.i386: Adjust kernel build to reflect the refactoring of early Xen startup code and Xen interrupt services. sys/dev/xen/blkback/blkback.c: sys/dev/xen/blkfront/blkfront.c: sys/dev/xen/blkfront/block.h: sys/dev/xen/control/control.c: sys/dev/xen/evtchn/evtchn_dev.c: sys/dev/xen/netback/netback.c: sys/dev/xen/netfront/netfront.c: sys/xen/xenstore/xenstore.c: sys/xen/evtchn/evtchn_dev.c: sys/dev/xen/console/console.c: sys/dev/xen/console/xencons_ring.c Adjust drivers to use new xen_intr_*() API. sys/dev/xen/blkback/blkback.c: Since blkback defers all event handling to a taskqueue, convert this task queue to a "fast" taskqueue, and schedule it via an interrupt filter. This avoids an unnecessary ithread context switch. sys/xen/xenstore/xenstore.c: The xenstore driver is MPSAFE. Indicate as much when registering its interrupt handler. sys/xen/xenbus/xenbus.c: sys/xen/xenbus/xenbusvar.h: Remove unused event channel APIs. sys/xen/evtchn.h: Remove all kernel Xen interrupt service API definitions from this file. It is now only used for structure and ioctl definitions related to the event channel userland device driver. Update the definitions in this file to match those from NetBSD. Implementing this interface will be necessary for Dom0 support. sys/xen/evtchn/evtchnvar.h: Add a header file for implemenation internal APIs related to managing event channels event delivery. This is used to allow, for example, the event channel userland device driver to access low-level routines that typical kernel consumers of event channel services should never access. sys/xen/interface/event_channel.h: sys/xen/xen_intr.h: Standardize on the evtchn_port_t type for referring to an event channel port id. In order to prevent low-level event channel APIs from leaking to kernel consumers who should not have access to this data, the type is defined twice: Once in the Xen provided event_channel.h, and again in xen/xen_intr.h. The double declaration is protected by __XEN_EVTCHN_PORT_DEFINED__ to ensure it is never declared twice within a given compilation unit. sys/xen/xen_intr.h: sys/xen/evtchn/evtchn.c: sys/x86/xen/xen_intr.c: sys/dev/xen/xenpci/evtchn.c: sys/dev/xen/xenpci/xenpcivar.h: New implementation of Xen interrupt services. This is similar in many respects to the i386 PV implementation with the exception that events for bound to event channel ports (i.e. not IPI, virtual IRQ, or physical IRQ) are further optimized to avoid mask/unmask operations that aren't necessary for these edge triggered events. Stubs exist for supporting physical IRQ binding, but will need additional work before this implementation can be fully shared between PV and HVM. sys/amd64/amd64/mp_machdep.c: sys/i386/i386/mp_machdep.c: sys/i386/xen/mp_machdep.c sys/x86/xen/hvm.c: Add support for placing vcpu_info into an arbritary memory page instead of using HYPERVISOR_shared_info->vcpu_info. This allows the creation of domains with more than 32 vcpus. sys/i386/i386/machdep.c: sys/i386/xen/clock.c: sys/i386/xen/xen_machdep.c: sys/i386/xen/exception.s: Add support for new event channle implementation.
Diffstat (limited to 'sys/amd64/include')
-rw-r--r--sys/amd64/include/apicvar.h1
-rw-r--r--sys/amd64/include/intr_machdep.h18
-rw-r--r--sys/amd64/include/pcpu.h12
-rw-r--r--sys/amd64/include/xen/hypercall.h8
-rw-r--r--sys/amd64/include/xen/xen-os.h219
5 files changed, 48 insertions, 210 deletions
diff --git a/sys/amd64/include/apicvar.h b/sys/amd64/include/apicvar.h
index ae2f5b9..9cd4c95 100644
--- a/sys/amd64/include/apicvar.h
+++ b/sys/amd64/include/apicvar.h
@@ -227,6 +227,7 @@ int lapic_set_lvt_triggermode(u_int apic_id, u_int lvt,
enum intr_trigger trigger);
void lapic_set_tpr(u_int vector);
void lapic_setup(int boot);
+void xen_intr_handle_upcall(struct trapframe *frame);
#endif /* !LOCORE */
#endif /* _MACHINE_APICVAR_H_ */
diff --git a/sys/amd64/include/intr_machdep.h b/sys/amd64/include/intr_machdep.h
index 8671605..c8b454d 100644
--- a/sys/amd64/include/intr_machdep.h
+++ b/sys/amd64/include/intr_machdep.h
@@ -44,12 +44,24 @@
* allocate IDT vectors.
*
* The first 255 IRQs (0 - 254) are reserved for ISA IRQs and PCI intline IRQs.
- * IRQ values beyond 256 are used by MSI. We leave 255 unused to avoid
- * confusion since 255 is used in PCI to indicate an invalid IRQ.
+ * IRQ values from 256 to 767 are used by MSI. When running under the Xen
+ * Hypervisor, IRQ values from 768 to 4863 are available for binding to
+ * event channel events. We leave 255 unused to avoid confusion since 255 is
+ * used in PCI to indicate an invalid IRQ.
*/
#define NUM_MSI_INTS 512
#define FIRST_MSI_INT 256
-#define NUM_IO_INTS (FIRST_MSI_INT + NUM_MSI_INTS)
+#ifdef XENHVM
+#include <xen/xen-os.h>
+#define NUM_EVTCHN_INTS NR_EVENT_CHANNELS
+#define FIRST_EVTCHN_INT \
+ (FIRST_MSI_INT + NUM_MSI_INTS)
+#define LAST_EVTCHN_INT \
+ (FIRST_EVTCHN_INT + NUM_EVTCHN_INTS - 1)
+#else
+#define NUM_EVTCHN_INTS 0
+#endif
+#define NUM_IO_INTS (FIRST_MSI_INT + NUM_MSI_INTS + NUM_EVTCHN_INTS)
/*
* Default base address for MSI messages on x86 platforms.
diff --git a/sys/amd64/include/pcpu.h b/sys/amd64/include/pcpu.h
index ba4c618..1c83c2a 100644
--- a/sys/amd64/include/pcpu.h
+++ b/sys/amd64/include/pcpu.h
@@ -42,15 +42,6 @@
#endif
#endif
-#ifdef XENHVM
-#define PCPU_XEN_FIELDS \
- ; \
- unsigned int pc_last_processed_l1i; \
- unsigned int pc_last_processed_l2i
-#else
-#define PCPU_XEN_FIELDS
-#endif
-
/*
* The SMP parts are setup in pmap.c and locore.s for the BSP, and
* mp_machdep.c sets up the data for the AP's to "see" when they awake.
@@ -76,8 +67,7 @@
struct system_segment_descriptor *pc_ldt; \
/* Pointer to the CPU TSS descriptor */ \
struct system_segment_descriptor *pc_tss; \
- u_int pc_cmci_mask /* MCx banks for CMCI */ \
- PCPU_XEN_FIELDS; \
+ u_int pc_cmci_mask; /* MCx banks for CMCI */ \
uint64_t pc_dbreg[16]; /* ddb debugging regs */ \
int pc_dbreg_cmd; /* ddb debugging reg cmd */ \
char __pad[161] /* be divisor of PAGE_SIZE \
diff --git a/sys/amd64/include/xen/hypercall.h b/sys/amd64/include/xen/hypercall.h
index 50fa376..a1b2a5c 100644
--- a/sys/amd64/include/xen/hypercall.h
+++ b/sys/amd64/include/xen/hypercall.h
@@ -1,7 +1,7 @@
/******************************************************************************
* hypercall.h
*
- * Linux-specific hypervisor handling.
+ * FreeBSD-specific hypervisor handling.
*
* Copyright (c) 2002-2004, K A Fraser
*
@@ -32,6 +32,8 @@
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
+ *
+ * $FreeBSD$
*/
#ifndef __MACHINE_XEN_HYPERCALL_H__
@@ -270,7 +272,7 @@ HYPERVISOR_event_channel_op(
int rc = _hypercall2(int, event_channel_op, cmd, arg);
#if CONFIG_XEN_COMPAT <= 0x030002
- if (unlikely(rc == -ENOXENSYS)) {
+ if (__predict_false(rc == -ENOXENSYS)) {
struct evtchn_op op;
op.cmd = cmd;
memcpy(&op.u, arg, sizeof(op.u));
@@ -303,7 +305,7 @@ HYPERVISOR_physdev_op(
int rc = _hypercall2(int, physdev_op, cmd, arg);
#if CONFIG_XEN_COMPAT <= 0x030002
- if (unlikely(rc == -ENOXENSYS)) {
+ if (__predict_false(rc == -ENOXENSYS)) {
struct physdev_op op;
op.cmd = cmd;
memcpy(&op.u, arg, sizeof(op.u));
diff --git a/sys/amd64/include/xen/xen-os.h b/sys/amd64/include/xen/xen-os.h
index 8974323..ee498b9 100644
--- a/sys/amd64/include/xen/xen-os.h
+++ b/sys/amd64/include/xen/xen-os.h
@@ -1,40 +1,42 @@
/******************************************************************************
- * os.h
+ * amd64/xen/xen-os.h
*
- * random collection of macros and definition
+ * Random collection of macros and definition
+ *
+ * Copyright (c) 2003, 2004 Keir Fraser (on behalf of the Xen team)
+ * All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
*
* $FreeBSD$
*/
-#ifndef _XEN_OS_H_
-#define _XEN_OS_H_
+#ifndef _MACHINE_XEN_XEN_OS_H_
+#define _MACHINE_XEN_XEN_OS_H_
#ifdef PAE
#define CONFIG_X86_PAE
#endif
-#ifdef LOCORE
-#define __ASSEMBLY__
-#endif
-
-#if !defined(__XEN_INTERFACE_VERSION__)
-#define __XEN_INTERFACE_VERSION__ 0x00030208
-#endif
-
-#define GRANT_REF_INVALID 0xffffffff
-
-#include <xen/interface/xen.h>
-
/* Everything below this point is not included by assembler (.S) files. */
#ifndef __ASSEMBLY__
-/* Force a proper event-channel callback from Xen. */
-void force_evtchn_callback(void);
-
-extern int gdtset;
-
-extern shared_info_t *HYPERVISOR_shared_info;
-
/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
static inline void rep_nop(void)
{
@@ -42,161 +44,12 @@ static inline void rep_nop(void)
}
#define cpu_relax() rep_nop()
-/* crude memory allocator for memory allocation early in
- * boot
- */
-void *bootmem_alloc(unsigned int size);
-void bootmem_free(void *ptr, unsigned int size);
-
-void printk(const char *fmt, ...);
-
-/* some function prototypes */
-void trap_init(void);
-
-#define likely(x) __builtin_expect((x),1)
-#define unlikely(x) __builtin_expect((x),0)
-
-#ifndef XENHVM
-
-/*
- * STI/CLI equivalents. These basically set and clear the virtual
- * event_enable flag in the shared_info structure. Note that when
- * the enable bit is set, there may be pending events to be handled.
- * We may therefore call into do_hypervisor_callback() directly.
- */
-
-#define __cli() \
-do { \
- vcpu_info_t *_vcpu; \
- _vcpu = &HYPERVISOR_shared_info->vcpu_info[PCPU_GET(cpuid)]; \
- _vcpu->evtchn_upcall_mask = 1; \
- barrier(); \
-} while (0)
-
-#define __sti() \
-do { \
- vcpu_info_t *_vcpu; \
- barrier(); \
- _vcpu = &HYPERVISOR_shared_info->vcpu_info[PCPU_GET(cpuid)]; \
- _vcpu->evtchn_upcall_mask = 0; \
- barrier(); /* unmask then check (avoid races) */ \
- if ( unlikely(_vcpu->evtchn_upcall_pending) ) \
- force_evtchn_callback(); \
-} while (0)
-
-#define __restore_flags(x) \
-do { \
- vcpu_info_t *_vcpu; \
- barrier(); \
- _vcpu = &HYPERVISOR_shared_info->vcpu_info[PCPU_GET(cpuid)]; \
- if ((_vcpu->evtchn_upcall_mask = (x)) == 0) { \
- barrier(); /* unmask then check (avoid races) */ \
- if ( unlikely(_vcpu->evtchn_upcall_pending) ) \
- force_evtchn_callback(); \
- } \
-} while (0)
-
-/*
- * Add critical_{enter, exit}?
- *
- */
-#define __save_and_cli(x) \
-do { \
- vcpu_info_t *_vcpu; \
- _vcpu = &HYPERVISOR_shared_info->vcpu_info[PCPU_GET(cpuid)]; \
- (x) = _vcpu->evtchn_upcall_mask; \
- _vcpu->evtchn_upcall_mask = 1; \
- barrier(); \
-} while (0)
-
-
-#define cli() __cli()
-#define sti() __sti()
-#define save_flags(x) __save_flags(x)
-#define restore_flags(x) __restore_flags(x)
-#define save_and_cli(x) __save_and_cli(x)
-
-#define local_irq_save(x) __save_and_cli(x)
-#define local_irq_restore(x) __restore_flags(x)
-#define local_irq_disable() __cli()
-#define local_irq_enable() __sti()
-
-#define mtx_lock_irqsave(lock, x) {local_irq_save((x)); mtx_lock_spin((lock));}
-#define mtx_unlock_irqrestore(lock, x) {mtx_unlock_spin((lock)); local_irq_restore((x)); }
-#define spin_lock_irqsave mtx_lock_irqsave
-#define spin_unlock_irqrestore mtx_unlock_irqrestore
-
-#else
-#endif
-
-#ifndef xen_mb
-#define xen_mb() mb()
-#endif
-#ifndef xen_rmb
-#define xen_rmb() rmb()
-#endif
-#ifndef xen_wmb
-#define xen_wmb() wmb()
-#endif
-#ifdef SMP
-#define smp_mb() mb()
-#define smp_rmb() rmb()
-#define smp_wmb() wmb()
-#define smp_read_barrier_depends() read_barrier_depends()
-#define set_mb(var, value) do { xchg(&var, value); } while (0)
-#else
-#define smp_mb() barrier()
-#define smp_rmb() barrier()
-#define smp_wmb() barrier()
-#define smp_read_barrier_depends() do { } while(0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
-
-
/* This is a barrier for the compiler only, NOT the processor! */
#define barrier() __asm__ __volatile__("": : :"memory")
#define LOCK_PREFIX ""
#define LOCK ""
#define ADDR (*(volatile long *) addr)
-/*
- * Make sure gcc doesn't try to be clever and move things around
- * on us. We need to use _exactly_ the address the user gave us,
- * not some alias that contains the same information.
- */
-typedef struct { volatile int counter; } atomic_t;
-
-
-
-#define xen_xchg(ptr,v) \
- ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr))))
-struct __xchg_dummy { unsigned long a[100]; };
-#define __xg(x) ((volatile struct __xchg_dummy *)(x))
-static __inline unsigned long __xchg(unsigned long x, volatile void * ptr,
- int size)
-{
- switch (size) {
- case 1:
- __asm__ __volatile__("xchgb %b0,%1"
- :"=q" (x)
- :"m" (*__xg(ptr)), "0" (x)
- :"memory");
- break;
- case 2:
- __asm__ __volatile__("xchgw %w0,%1"
- :"=r" (x)
- :"m" (*__xg(ptr)), "0" (x)
- :"memory");
- break;
- case 4:
- __asm__ __volatile__("xchgl %0,%1"
- :"=r" (x)
- :"m" (*__xg(ptr)), "0" (x)
- :"memory");
- break;
- }
- return x;
-}
/**
* test_and_clear_bit - Clear a bit and return its old value
@@ -238,7 +91,6 @@ static __inline int variable_test_bit(int nr, volatile void * addr)
constant_test_bit((nr),(addr)) : \
variable_test_bit((nr),(addr)))
-
/**
* set_bit - Atomically set a bit in memory
* @nr: the bit to set
@@ -275,25 +127,6 @@ static __inline__ void clear_bit(int nr, volatile void * addr)
:"Ir" (nr));
}
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1. Note that the guaranteed
- * useful range of an atomic_t is only 24 bits.
- */
-static __inline__ void atomic_inc(atomic_t *v)
-{
- __asm__ __volatile__(
- LOCK "incl %0"
- :"=m" (v->counter)
- :"m" (v->counter));
-}
-
-
-#define rdtscll(val) \
- __asm__ __volatile__("rdtsc" : "=A" (val))
-
#endif /* !__ASSEMBLY__ */
-#endif /* _OS_H_ */
+#endif /* _MACHINE_XEN_XEN_OS_H_ */
OpenPOWER on IntegriCloud