Justin T. Gibbs e44af46e4c Implement PV IPIs for PVHVM guests and further converge PV and HVM
IPI implmementations.

Submitted by: Roger Pau Monné
Sponsored by: Citrix Systems R&D
Submitted by: gibbs (misc cleanup, table driven config)
Reviewed by:  gibbs
MFC after: 2 weeks

sys/amd64/include/cpufunc.h:
sys/amd64/amd64/pmap.c:
	Move invltlb_globpcid() into cpufunc.h so that it can be
	used by the Xen HVM version of tlb shootdown IPI handlers.

sys/x86/xen/xen_intr.c:
sys/xen/xen_intr.h:
	Rename xen_intr_bind_ipi() to xen_intr_alloc_and_bind_ipi(),
	and remove the ipi vector parameter.  This api allocates
	an event channel port that can be used for ipi services,
	but knows nothing of the actual ipi for which that port
	will be used.  Removing the unused argument and cleaning
	up the comments surrounding its declaration helps clarify
	its actual role.

sys/amd64/amd64/mp_machdep.c:
sys/amd64/include/cpu.h:
sys/i386/i386/mp_machdep.c:
sys/i386/include/cpu.h:
	Implement a generic framework for amd64 and i386 that allows
	the implementation of certain CPU management functions to
	be selected at runtime.  Currently this is only used for
	the ipi send function, which we optimize for Xen when running
	on a Xen hypervisor, but can easily be expanded to support
	more operations.

sys/x86/xen/hvm.c:
	Implement Xen PV IPI handlers and operations, replacing native
	send IPI.

sys/amd64/include/pcpu.h:
sys/i386/include/pcpu.h:
sys/i386/include/smp.h:
	Remove NR_VIRQS and NR_IPIS from FreeBSD headers.  NR_VIRQS
	is defined already for us in the xen interface files.
	NR_IPIS is only needed in one file per Xen platform and is
	easily inferred by the IPI vector table that is defined in
	those files.

sys/i386/xen/mp_machdep.c:
	Restructure to more closely match the HVM implementation by
	performing table driven IPI setup.
2013-09-06 22:17:02 +00:00

249 lines
8.0 KiB
C

/*-
* Copyright (c) Peter Wemm <peter@netplex.com.au>
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* $FreeBSD$
*/
#ifndef _MACHINE_PCPU_H_
#define _MACHINE_PCPU_H_
#ifndef _SYS_CDEFS_H_
#error "sys/cdefs.h is a prerequisite for this file"
#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.
* The reason for doing it via a struct is so that an array of pointers
* to each CPU's data can be set up for things like "check curproc on all
* other processors"
*/
#define PCPU_MD_FIELDS \
char pc_monitorbuf[128] __aligned(128); /* cache line */ \
struct pcpu *pc_prvspace; /* Self-reference */ \
struct pmap *pc_curpmap; \
struct amd64tss *pc_tssp; /* TSS segment active on CPU */ \
struct amd64tss *pc_commontssp;/* Common TSS for the CPU */ \
register_t pc_rsp0; \
register_t pc_scratch_rsp; /* User %rsp in syscall */ \
u_int pc_apic_id; \
u_int pc_acpi_id; /* ACPI CPU id */ \
/* Pointer to the CPU %fs descriptor */ \
struct user_segment_descriptor *pc_fs32p; \
/* Pointer to the CPU %gs descriptor */ \
struct user_segment_descriptor *pc_gs32p; \
/* Pointer to the CPU LDT descriptor */ \
struct system_segment_descriptor *pc_ldt; \
/* Pointer to the CPU TSS descriptor */ \
struct system_segment_descriptor *pc_tss; \
uint64_t pc_pm_save_cnt; \
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 \
after cache alignment */
#define PC_DBREG_CMD_NONE 0
#define PC_DBREG_CMD_LOAD 1
#ifdef _KERNEL
#ifdef lint
extern struct pcpu *pcpup;
#define PCPU_GET(member) (pcpup->pc_ ## member)
#define PCPU_ADD(member, val) (pcpup->pc_ ## member += (val))
#define PCPU_INC(member) PCPU_ADD(member, 1)
#define PCPU_PTR(member) (&pcpup->pc_ ## member)
#define PCPU_SET(member, val) (pcpup->pc_ ## member = (val))
#elif defined(__GNUCLIKE_ASM) && defined(__GNUCLIKE___TYPEOF)
/*
* Evaluates to the byte offset of the per-cpu variable name.
*/
#define __pcpu_offset(name) \
__offsetof(struct pcpu, name)
/*
* Evaluates to the type of the per-cpu variable name.
*/
#define __pcpu_type(name) \
__typeof(((struct pcpu *)0)->name)
/*
* Evaluates to the address of the per-cpu variable name.
*/
#define __PCPU_PTR(name) __extension__ ({ \
__pcpu_type(name) *__p; \
\
__asm __volatile("movq %%gs:%1,%0; addq %2,%0" \
: "=r" (__p) \
: "m" (*(struct pcpu *)(__pcpu_offset(pc_prvspace))), \
"i" (__pcpu_offset(name))); \
\
__p; \
})
/*
* Evaluates to the value of the per-cpu variable name.
*/
#define __PCPU_GET(name) __extension__ ({ \
__pcpu_type(name) __res; \
struct __s { \
u_char __b[MIN(sizeof(__pcpu_type(name)), 8)]; \
} __s; \
\
if (sizeof(__res) == 1 || sizeof(__res) == 2 || \
sizeof(__res) == 4 || sizeof(__res) == 8) { \
__asm __volatile("mov %%gs:%1,%0" \
: "=r" (__s) \
: "m" (*(struct __s *)(__pcpu_offset(name)))); \
*(struct __s *)(void *)&__res = __s; \
} else { \
__res = *__PCPU_PTR(name); \
} \
__res; \
})
/*
* Adds the value to the per-cpu counter name. The implementation
* must be atomic with respect to interrupts.
*/
#define __PCPU_ADD(name, val) do { \
__pcpu_type(name) __val; \
struct __s { \
u_char __b[MIN(sizeof(__pcpu_type(name)), 8)]; \
} __s; \
\
__val = (val); \
if (sizeof(__val) == 1 || sizeof(__val) == 2 || \
sizeof(__val) == 4 || sizeof(__val) == 8) { \
__s = *(struct __s *)(void *)&__val; \
__asm __volatile("add %1,%%gs:%0" \
: "=m" (*(struct __s *)(__pcpu_offset(name))) \
: "r" (__s)); \
} else \
*__PCPU_PTR(name) += __val; \
} while (0)
/*
* Increments the value of the per-cpu counter name. The implementation
* must be atomic with respect to interrupts.
*/
#define __PCPU_INC(name) do { \
CTASSERT(sizeof(__pcpu_type(name)) == 1 || \
sizeof(__pcpu_type(name)) == 2 || \
sizeof(__pcpu_type(name)) == 4 || \
sizeof(__pcpu_type(name)) == 8); \
if (sizeof(__pcpu_type(name)) == 1) { \
__asm __volatile("incb %%gs:%0" \
: "=m" (*(__pcpu_type(name) *)(__pcpu_offset(name)))\
: "m" (*(__pcpu_type(name) *)(__pcpu_offset(name))));\
} else if (sizeof(__pcpu_type(name)) == 2) { \
__asm __volatile("incw %%gs:%0" \
: "=m" (*(__pcpu_type(name) *)(__pcpu_offset(name)))\
: "m" (*(__pcpu_type(name) *)(__pcpu_offset(name))));\
} else if (sizeof(__pcpu_type(name)) == 4) { \
__asm __volatile("incl %%gs:%0" \
: "=m" (*(__pcpu_type(name) *)(__pcpu_offset(name)))\
: "m" (*(__pcpu_type(name) *)(__pcpu_offset(name))));\
} else if (sizeof(__pcpu_type(name)) == 8) { \
__asm __volatile("incq %%gs:%0" \
: "=m" (*(__pcpu_type(name) *)(__pcpu_offset(name)))\
: "m" (*(__pcpu_type(name) *)(__pcpu_offset(name))));\
} \
} while (0)
/*
* Sets the value of the per-cpu variable name to value val.
*/
#define __PCPU_SET(name, val) { \
__pcpu_type(name) __val; \
struct __s { \
u_char __b[MIN(sizeof(__pcpu_type(name)), 8)]; \
} __s; \
\
__val = (val); \
if (sizeof(__val) == 1 || sizeof(__val) == 2 || \
sizeof(__val) == 4 || sizeof(__val) == 8) { \
__s = *(struct __s *)(void *)&__val; \
__asm __volatile("mov %1,%%gs:%0" \
: "=m" (*(struct __s *)(__pcpu_offset(name))) \
: "r" (__s)); \
} else { \
*__PCPU_PTR(name) = __val; \
} \
}
#define PCPU_GET(member) __PCPU_GET(pc_ ## member)
#define PCPU_ADD(member, val) __PCPU_ADD(pc_ ## member, val)
#define PCPU_INC(member) __PCPU_INC(pc_ ## member)
#define PCPU_PTR(member) __PCPU_PTR(pc_ ## member)
#define PCPU_SET(member, val) __PCPU_SET(pc_ ## member, val)
#define OFFSETOF_CURTHREAD 0
#ifdef __clang__
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wnull-dereference"
#endif
static __inline __pure2 struct thread *
__curthread(void)
{
struct thread *td;
__asm("movq %%gs:%1,%0" : "=r" (td)
: "m" (*(char *)OFFSETOF_CURTHREAD));
return (td);
}
#ifdef __clang__
#pragma clang diagnostic pop
#endif
#define curthread (__curthread())
#define OFFSETOF_CURPCB 32
static __inline __pure2 struct pcb *
__curpcb(void)
{
struct pcb *pcb;
__asm("movq %%gs:%1,%0" : "=r" (pcb) : "m" (*(char *)OFFSETOF_CURPCB));
return (pcb);
}
#define curpcb (__curpcb())
#define IS_BSP() (PCPU_GET(cpuid) == 0)
#else /* !lint || defined(__GNUCLIKE_ASM) && defined(__GNUCLIKE___TYPEOF) */
#error "this file needs to be ported to your compiler"
#endif /* lint, etc. */
#endif /* _KERNEL */
#endif /* !_MACHINE_PCPU_H_ */