Merge branches 'x86/apic', 'x86/asm', 'x86/mm' and 'x86/platform' into x86/core, to merge last updates
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 99983e6..da95513 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -162,7 +162,7 @@
What: /sys/devices/system/cpu/cpu*/cache/index3/cache_disable_{0,1}
Date: August 2008
KernelVersion: 2.6.27
-Contact: discuss@x86-64.org
+Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
Description: Disable L3 cache indices
These files exist in every CPU's cache/index3 directory. Each
diff --git a/Documentation/hwmon/tmp401 b/Documentation/hwmon/tmp401
index 8eb88e9..711f75e 100644
--- a/Documentation/hwmon/tmp401
+++ b/Documentation/hwmon/tmp401
@@ -20,7 +20,7 @@
Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp432.html
* Texas Instruments TMP435
Prefix: 'tmp435'
- Addresses scanned: I2C 0x37, 0x48 - 0x4f
+ Addresses scanned: I2C 0x48 - 0x4f
Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp435.html
Authors:
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 61ab162..a320a41 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -746,6 +746,12 @@
cpuidle.off=1 [CPU_IDLE]
disable the cpuidle sub-system
+ cpu_init_udelay=N
+ [X86] Delay for N microsec between assert and de-assert
+ of APIC INIT to start processors. This delay occurs
+ on every CPU online, such as boot, and resume from suspend.
+ Default: 10000
+
cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver
Format:
<first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index f957461..fe4020e 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1662,7 +1662,7 @@
There are some more advanced barrier functions:
- (*) set_mb(var, value)
+ (*) smp_store_mb(var, value)
This assigns the value to the variable and then inserts a full memory
barrier after it, depending on the function. It isn't guaranteed to
@@ -1975,7 +1975,7 @@
CPU 1
===============================
set_current_state();
- set_mb();
+ smp_store_mb();
STORE current->state
<general barrier>
LOAD event_indicated
@@ -2016,7 +2016,7 @@
CPU 1 CPU 2
=============================== ===============================
set_current_state(); STORE event_indicated
- set_mb(); wake_up();
+ smp_store_mb(); wake_up();
STORE current->state <write barrier>
<general barrier> STORE current->state
LOAD event_indicated
diff --git a/Documentation/target/tcmu-design.txt b/Documentation/target/tcmu-design.txt
index 43e94ea..263b907 100644
--- a/Documentation/target/tcmu-design.txt
+++ b/Documentation/target/tcmu-design.txt
@@ -15,8 +15,7 @@
a) Discovering and configuring TCMU uio devices
b) Waiting for events on the device(s)
c) Managing the command ring
-3) Command filtering and pass_level
-4) A final note
+3) A final note
TCM Userspace Design
@@ -324,7 +323,7 @@
/* Process events from cmd ring until we catch up with cmd_head */
while (ent != (void *)mb + mb->cmdr_off + mb->cmd_head) {
- if (tcmu_hdr_get_op(&ent->hdr) == TCMU_OP_CMD) {
+ if (tcmu_hdr_get_op(ent->hdr.len_op) == TCMU_OP_CMD) {
uint8_t *cdb = (void *)mb + ent->req.cdb_off;
bool success = true;
@@ -339,8 +338,12 @@
ent->rsp.scsi_status = SCSI_CHECK_CONDITION;
}
}
+ else if (tcmu_hdr_get_op(ent->hdr.len_op) != TCMU_OP_PAD) {
+ /* Tell the kernel we didn't handle unknown opcodes */
+ ent->hdr.uflags |= TCMU_UFLAG_UNKNOWN_OP;
+ }
else {
- /* Do nothing for PAD entries */
+ /* Do nothing for PAD entries except update cmd_tail */
}
/* update cmd_tail */
@@ -360,28 +363,6 @@
}
-Command filtering and pass_level
---------------------------------
-
-TCMU supports a "pass_level" option with valid values of 0 or 1. When
-the value is 0 (the default), nearly all SCSI commands received for
-the device are passed through to the handler. This allows maximum
-flexibility but increases the amount of code required by the handler,
-to support all mandatory SCSI commands. If pass_level is set to 1,
-then only IO-related commands are presented, and the rest are handled
-by LIO's in-kernel command emulation. The commands presented at level
-1 include all versions of:
-
-READ
-WRITE
-WRITE_VERIFY
-XDWRITEREAD
-WRITE_SAME
-COMPARE_AND_WRITE
-SYNCHRONIZE_CACHE
-UNMAP
-
-
A final note
------------
diff --git a/Documentation/x86/entry_64.txt b/Documentation/x86/entry_64.txt
index 9132b86..33884d1 100644
--- a/Documentation/x86/entry_64.txt
+++ b/Documentation/x86/entry_64.txt
@@ -18,10 +18,10 @@
- system_call: syscall instruction from 64-bit code.
- - ia32_syscall: int 0x80 from 32-bit or 64-bit code; compat syscall
+ - entry_INT80_compat: int 0x80 from 32-bit or 64-bit code; compat syscall
either way.
- - ia32_syscall, ia32_sysenter: syscall and sysenter from 32-bit
+ - entry_INT80_compat, ia32_sysenter: syscall and sysenter from 32-bit
code
- interrupt: An array of entries. Every IDT vector that doesn't
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 5223479..68ed311 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -31,6 +31,9 @@
(e.g. BIOS or hardware monitoring applications), conflicting
with OS's error handling, and you cannot deactivate the agent,
then this option will be a help.
+ mce=no_lmce
+ Do not opt-in to Local MCE delivery. Use legacy method
+ to broadcast MCEs.
mce=bootlog
Enable logging of machine checks left over from booting.
Disabled by default on AMD because some BIOS leave bogus ones.
diff --git a/MAINTAINERS b/MAINTAINERS
index 474bcb6..2987968 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2427,7 +2427,6 @@
S: Supported
F: include/linux/capability.h
F: include/uapi/linux/capability.h
-F: security/capability.c
F: security/commoncap.c
F: kernel/capability.c
@@ -10588,8 +10587,7 @@
F: include/uapi/linux/virtio_input.h
VIA RHINE NETWORK DRIVER
-M: Roger Luethi <rl@hellgate.ch>
-S: Maintained
+S: Orphan
F: drivers/net/ethernet/via/via-rhine.c
VIA SD/MMC CARD CONTROLLER DRIVER
@@ -10895,7 +10893,7 @@
L: linux-kernel@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/vdso
S: Maintained
-F: arch/x86/vdso/
+F: arch/x86/entry/vdso/
XC2028/3028 TUNER DRIVER
M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
diff --git a/Makefile b/Makefile
index 92a7078..aee7e5c 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 4
PATCHLEVEL = 1
SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
NAME = Hurr durr I'ma sheep
# *DOCUMENTATION*
diff --git a/arch/alpha/boot/Makefile b/arch/alpha/boot/Makefile
index cd14388..8399bd0 100644
--- a/arch/alpha/boot/Makefile
+++ b/arch/alpha/boot/Makefile
@@ -14,6 +14,9 @@
tools/bootpzh bootloader bootpheader bootpzheader
OBJSTRIP := $(obj)/tools/objstrip
+HOSTCFLAGS := -Wall -I$(objtree)/usr/include
+BOOTCFLAGS += -I$(obj) -I$(srctree)/$(obj)
+
# SRM bootable image. Copy to offset 512 of a partition.
$(obj)/bootimage: $(addprefix $(obj)/tools/,mkbb lxboot bootlx) $(obj)/vmlinux.nh
( cat $(obj)/tools/lxboot $(obj)/tools/bootlx $(obj)/vmlinux.nh ) > $@
@@ -96,13 +99,14 @@
$(obj)/tools/bootpzh: $(obj)/bootpzheader $(OBJSTRIP) FORCE
$(call if_changed,objstrip)
-LDFLAGS_bootloader := -static -uvsprintf -T #-N -relax
-LDFLAGS_bootpheader := -static -uvsprintf -T #-N -relax
-LDFLAGS_bootpzheader := -static -uvsprintf -T #-N -relax
+LDFLAGS_bootloader := -static -T # -N -relax
+LDFLAGS_bootloader := -static -T # -N -relax
+LDFLAGS_bootpheader := -static -T # -N -relax
+LDFLAGS_bootpzheader := -static -T # -N -relax
-OBJ_bootlx := $(obj)/head.o $(obj)/main.o
-OBJ_bootph := $(obj)/head.o $(obj)/bootp.o
-OBJ_bootpzh := $(obj)/head.o $(obj)/bootpz.o $(obj)/misc.o
+OBJ_bootlx := $(obj)/head.o $(obj)/stdio.o $(obj)/main.o
+OBJ_bootph := $(obj)/head.o $(obj)/stdio.o $(obj)/bootp.o
+OBJ_bootpzh := $(obj)/head.o $(obj)/stdio.o $(obj)/bootpz.o $(obj)/misc.o
$(obj)/bootloader: $(obj)/bootloader.lds $(OBJ_bootlx) $(LIBS_Y) FORCE
$(call if_changed,ld)
diff --git a/arch/alpha/boot/main.c b/arch/alpha/boot/main.c
index 3baf2d1..dd6eb4a 100644
--- a/arch/alpha/boot/main.c
+++ b/arch/alpha/boot/main.c
@@ -19,7 +19,6 @@
#include "ksize.h"
-extern int vsprintf(char *, const char *, va_list);
extern unsigned long switch_to_osf_pal(unsigned long nr,
struct pcb_struct * pcb_va, struct pcb_struct * pcb_pa,
unsigned long *vptb);
diff --git a/arch/alpha/boot/stdio.c b/arch/alpha/boot/stdio.c
new file mode 100644
index 0000000..f844dae
--- /dev/null
+++ b/arch/alpha/boot/stdio.c
@@ -0,0 +1,306 @@
+/*
+ * Copyright (C) Paul Mackerras 1997.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <stdarg.h>
+#include <stddef.h>
+
+size_t strnlen(const char * s, size_t count)
+{
+ const char *sc;
+
+ for (sc = s; count-- && *sc != '\0'; ++sc)
+ /* nothing */;
+ return sc - s;
+}
+
+# define do_div(n, base) ({ \
+ unsigned int __base = (base); \
+ unsigned int __rem; \
+ __rem = ((unsigned long long)(n)) % __base; \
+ (n) = ((unsigned long long)(n)) / __base; \
+ __rem; \
+})
+
+
+static int skip_atoi(const char **s)
+{
+ int i, c;
+
+ for (i = 0; '0' <= (c = **s) && c <= '9'; ++*s)
+ i = i*10 + c - '0';
+ return i;
+}
+
+#define ZEROPAD 1 /* pad with zero */
+#define SIGN 2 /* unsigned/signed long */
+#define PLUS 4 /* show plus */
+#define SPACE 8 /* space if plus */
+#define LEFT 16 /* left justified */
+#define SPECIAL 32 /* 0x */
+#define LARGE 64 /* use 'ABCDEF' instead of 'abcdef' */
+
+static char * number(char * str, unsigned long long num, int base, int size, int precision, int type)
+{
+ char c,sign,tmp[66];
+ const char *digits="0123456789abcdefghijklmnopqrstuvwxyz";
+ int i;
+
+ if (type & LARGE)
+ digits = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
+ if (type & LEFT)
+ type &= ~ZEROPAD;
+ if (base < 2 || base > 36)
+ return 0;
+ c = (type & ZEROPAD) ? '0' : ' ';
+ sign = 0;
+ if (type & SIGN) {
+ if ((signed long long)num < 0) {
+ sign = '-';
+ num = - (signed long long)num;
+ size--;
+ } else if (type & PLUS) {
+ sign = '+';
+ size--;
+ } else if (type & SPACE) {
+ sign = ' ';
+ size--;
+ }
+ }
+ if (type & SPECIAL) {
+ if (base == 16)
+ size -= 2;
+ else if (base == 8)
+ size--;
+ }
+ i = 0;
+ if (num == 0)
+ tmp[i++]='0';
+ else while (num != 0) {
+ tmp[i++] = digits[do_div(num, base)];
+ }
+ if (i > precision)
+ precision = i;
+ size -= precision;
+ if (!(type&(ZEROPAD+LEFT)))
+ while(size-->0)
+ *str++ = ' ';
+ if (sign)
+ *str++ = sign;
+ if (type & SPECIAL) {
+ if (base==8)
+ *str++ = '0';
+ else if (base==16) {
+ *str++ = '0';
+ *str++ = digits[33];
+ }
+ }
+ if (!(type & LEFT))
+ while (size-- > 0)
+ *str++ = c;
+ while (i < precision--)
+ *str++ = '0';
+ while (i-- > 0)
+ *str++ = tmp[i];
+ while (size-- > 0)
+ *str++ = ' ';
+ return str;
+}
+
+int vsprintf(char *buf, const char *fmt, va_list args)
+{
+ int len;
+ unsigned long long num;
+ int i, base;
+ char * str;
+ const char *s;
+
+ int flags; /* flags to number() */
+
+ int field_width; /* width of output field */
+ int precision; /* min. # of digits for integers; max
+ number of chars for from string */
+ int qualifier; /* 'h', 'l', or 'L' for integer fields */
+ /* 'z' support added 23/7/1999 S.H. */
+ /* 'z' changed to 'Z' --davidm 1/25/99 */
+
+
+ for (str=buf ; *fmt ; ++fmt) {
+ if (*fmt != '%') {
+ *str++ = *fmt;
+ continue;
+ }
+
+ /* process flags */
+ flags = 0;
+ repeat:
+ ++fmt; /* this also skips first '%' */
+ switch (*fmt) {
+ case '-': flags |= LEFT; goto repeat;
+ case '+': flags |= PLUS; goto repeat;
+ case ' ': flags |= SPACE; goto repeat;
+ case '#': flags |= SPECIAL; goto repeat;
+ case '0': flags |= ZEROPAD; goto repeat;
+ }
+
+ /* get field width */
+ field_width = -1;
+ if ('0' <= *fmt && *fmt <= '9')
+ field_width = skip_atoi(&fmt);
+ else if (*fmt == '*') {
+ ++fmt;
+ /* it's the next argument */
+ field_width = va_arg(args, int);
+ if (field_width < 0) {
+ field_width = -field_width;
+ flags |= LEFT;
+ }
+ }
+
+ /* get the precision */
+ precision = -1;
+ if (*fmt == '.') {
+ ++fmt;
+ if ('0' <= *fmt && *fmt <= '9')
+ precision = skip_atoi(&fmt);
+ else if (*fmt == '*') {
+ ++fmt;
+ /* it's the next argument */
+ precision = va_arg(args, int);
+ }
+ if (precision < 0)
+ precision = 0;
+ }
+
+ /* get the conversion qualifier */
+ qualifier = -1;
+ if (*fmt == 'l' && *(fmt + 1) == 'l') {
+ qualifier = 'q';
+ fmt += 2;
+ } else if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L'
+ || *fmt == 'Z') {
+ qualifier = *fmt;
+ ++fmt;
+ }
+
+ /* default base */
+ base = 10;
+
+ switch (*fmt) {
+ case 'c':
+ if (!(flags & LEFT))
+ while (--field_width > 0)
+ *str++ = ' ';
+ *str++ = (unsigned char) va_arg(args, int);
+ while (--field_width > 0)
+ *str++ = ' ';
+ continue;
+
+ case 's':
+ s = va_arg(args, char *);
+ if (!s)
+ s = "<NULL>";
+
+ len = strnlen(s, precision);
+
+ if (!(flags & LEFT))
+ while (len < field_width--)
+ *str++ = ' ';
+ for (i = 0; i < len; ++i)
+ *str++ = *s++;
+ while (len < field_width--)
+ *str++ = ' ';
+ continue;
+
+ case 'p':
+ if (field_width == -1) {
+ field_width = 2*sizeof(void *);
+ flags |= ZEROPAD;
+ }
+ str = number(str,
+ (unsigned long) va_arg(args, void *), 16,
+ field_width, precision, flags);
+ continue;
+
+
+ case 'n':
+ if (qualifier == 'l') {
+ long * ip = va_arg(args, long *);
+ *ip = (str - buf);
+ } else if (qualifier == 'Z') {
+ size_t * ip = va_arg(args, size_t *);
+ *ip = (str - buf);
+ } else {
+ int * ip = va_arg(args, int *);
+ *ip = (str - buf);
+ }
+ continue;
+
+ case '%':
+ *str++ = '%';
+ continue;
+
+ /* integer number formats - set up the flags and "break" */
+ case 'o':
+ base = 8;
+ break;
+
+ case 'X':
+ flags |= LARGE;
+ case 'x':
+ base = 16;
+ break;
+
+ case 'd':
+ case 'i':
+ flags |= SIGN;
+ case 'u':
+ break;
+
+ default:
+ *str++ = '%';
+ if (*fmt)
+ *str++ = *fmt;
+ else
+ --fmt;
+ continue;
+ }
+ if (qualifier == 'l') {
+ num = va_arg(args, unsigned long);
+ if (flags & SIGN)
+ num = (signed long) num;
+ } else if (qualifier == 'q') {
+ num = va_arg(args, unsigned long long);
+ if (flags & SIGN)
+ num = (signed long long) num;
+ } else if (qualifier == 'Z') {
+ num = va_arg(args, size_t);
+ } else if (qualifier == 'h') {
+ num = (unsigned short) va_arg(args, int);
+ if (flags & SIGN)
+ num = (signed short) num;
+ } else {
+ num = va_arg(args, unsigned int);
+ if (flags & SIGN)
+ num = (signed int) num;
+ }
+ str = number(str, num, base, field_width, precision, flags);
+ }
+ *str = '\0';
+ return str-buf;
+}
+
+int sprintf(char * buf, const char *fmt, ...)
+{
+ va_list args;
+ int i;
+
+ va_start(args, fmt);
+ i=vsprintf(buf,fmt,args);
+ va_end(args);
+ return i;
+}
diff --git a/arch/alpha/boot/tools/objstrip.c b/arch/alpha/boot/tools/objstrip.c
index 367d53d..dee8269 100644
--- a/arch/alpha/boot/tools/objstrip.c
+++ b/arch/alpha/boot/tools/objstrip.c
@@ -27,6 +27,9 @@
#include <linux/param.h>
#ifdef __ELF__
# include <linux/elf.h>
+# define elfhdr elf64_hdr
+# define elf_phdr elf64_phdr
+# define elf_check_arch(x) ((x)->e_machine == EM_ALPHA)
#endif
/* bootfile size must be multiple of BLOCK_SIZE: */
diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h
index 429e8cd..e511776 100644
--- a/arch/alpha/include/asm/cmpxchg.h
+++ b/arch/alpha/include/asm/cmpxchg.h
@@ -66,6 +66,4 @@
#undef __ASM__MB
#undef ____cmpxchg
-#define __HAVE_ARCH_CMPXCHG 1
-
#endif /* _ALPHA_CMPXCHG_H */
diff --git a/arch/alpha/include/asm/types.h b/arch/alpha/include/asm/types.h
index f61e1a5..4cb4b6d 100644
--- a/arch/alpha/include/asm/types.h
+++ b/arch/alpha/include/asm/types.h
@@ -2,6 +2,5 @@
#define _ALPHA_TYPES_H
#include <asm-generic/int-ll64.h>
-#include <uapi/asm/types.h>
#endif /* _ALPHA_TYPES_H */
diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h
index c509d30..a56e608 100644
--- a/arch/alpha/include/asm/unistd.h
+++ b/arch/alpha/include/asm/unistd.h
@@ -3,7 +3,7 @@
#include <uapi/asm/unistd.h>
-#define NR_SYSCALLS 511
+#define NR_SYSCALLS 514
#define __ARCH_WANT_OLD_READDIR
#define __ARCH_WANT_STAT64
diff --git a/arch/alpha/include/uapi/asm/unistd.h b/arch/alpha/include/uapi/asm/unistd.h
index d214a035..aa33bf5 100644
--- a/arch/alpha/include/uapi/asm/unistd.h
+++ b/arch/alpha/include/uapi/asm/unistd.h
@@ -472,5 +472,8 @@
#define __NR_sched_setattr 508
#define __NR_sched_getattr 509
#define __NR_renameat2 510
+#define __NR_getrandom 511
+#define __NR_memfd_create 512
+#define __NR_execveat 513
#endif /* _UAPI_ALPHA_UNISTD_H */
diff --git a/arch/alpha/kernel/err_ev6.c b/arch/alpha/kernel/err_ev6.c
index 253cf1a..51267ac 100644
--- a/arch/alpha/kernel/err_ev6.c
+++ b/arch/alpha/kernel/err_ev6.c
@@ -6,7 +6,6 @@
* Error handling code supporting Alpha systems
*/
-#include <linux/init.h>
#include <linux/sched.h>
#include <asm/io.h>
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index 7b2be25..51f2c86 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -19,7 +19,6 @@
#include <linux/ptrace.h>
#include <linux/interrupt.h>
#include <linux/random.h>
-#include <linux/init.h>
#include <linux/irq.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index e51f578..36dc91a 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1019,14 +1019,13 @@
if (tv) {
if (get_tv32((struct timeval *)&kts, tv))
return -EFAULT;
+ kts.tv_nsec *= 1000;
}
if (tz) {
if (copy_from_user(&ktz, tz, sizeof(*tz)))
return -EFAULT;
}
- kts.tv_nsec *= 1000;
-
return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
}
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 1941a07..84d1326 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -236,12 +236,11 @@
}
/*
- * Copy an alpha thread..
+ * Copy architecture-specific thread state
*/
-
int
copy_thread(unsigned long clone_flags, unsigned long usp,
- unsigned long arg,
+ unsigned long kthread_arg,
struct task_struct *p)
{
extern void ret_from_fork(void);
@@ -262,7 +261,7 @@
sizeof(struct switch_stack) + sizeof(struct pt_regs));
childstack->r26 = (unsigned long) ret_from_kernel_thread;
childstack->r9 = usp; /* function */
- childstack->r10 = arg;
+ childstack->r10 = kthread_arg;
childregs->hae = alpha_mv.hae_cache,
childti->pcb.usp = 0;
return 0;
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 99ac36d..2f24447f 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -63,7 +63,6 @@
enum ipi_message_type {
IPI_RESCHEDULE,
IPI_CALL_FUNC,
- IPI_CALL_FUNC_SINGLE,
IPI_CPU_STOP,
};
@@ -506,7 +505,6 @@
return -EINVAL;
}
-
static void
send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
{
@@ -552,10 +550,6 @@
generic_smp_call_function_interrupt();
break;
- case IPI_CALL_FUNC_SINGLE:
- generic_smp_call_function_single_interrupt();
- break;
-
case IPI_CPU_STOP:
halt();
@@ -606,7 +600,7 @@
void arch_send_call_function_single_ipi(int cpu)
{
- send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
+ send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC);
}
static void
diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c
index 6f01d9a..72b5951 100644
--- a/arch/alpha/kernel/srmcons.c
+++ b/arch/alpha/kernel/srmcons.c
@@ -237,8 +237,7 @@
return -ENODEV;
}
-
-module_init(srmcons_init);
+device_initcall(srmcons_init);
/*
diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c
index f21d61f..24e41bd 100644
--- a/arch/alpha/kernel/sys_marvel.c
+++ b/arch/alpha/kernel/sys_marvel.c
@@ -331,7 +331,7 @@
pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &intline);
irq = intline;
- msi_loc = pci_find_capability(dev, PCI_CAP_ID_MSI);
+ msi_loc = dev->msi_cap;
msg_ctl = 0;
if (msi_loc)
pci_read_config_word(dev, msi_loc + PCI_MSI_FLAGS, &msg_ctl);
diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S
index 24789713..9b62e3f 100644
--- a/arch/alpha/kernel/systbls.S
+++ b/arch/alpha/kernel/systbls.S
@@ -529,6 +529,9 @@
.quad sys_sched_setattr
.quad sys_sched_getattr
.quad sys_renameat2 /* 510 */
+ .quad sys_getrandom
+ .quad sys_memfd_create
+ .quad sys_execveat
.size sys_call_table, . - sys_call_table
.type sys_call_table, @object
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index 9c4c189..74aceea 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -14,7 +14,6 @@
#include <linux/tty.h>
#include <linux/delay.h>
#include <linux/module.h>
-#include <linux/init.h>
#include <linux/kallsyms.h>
#include <linux/ratelimit.h>
diff --git a/arch/alpha/oprofile/op_model_ev4.c b/arch/alpha/oprofile/op_model_ev4.c
index 18aa9b4..086a0d5 100644
--- a/arch/alpha/oprofile/op_model_ev4.c
+++ b/arch/alpha/oprofile/op_model_ev4.c
@@ -8,7 +8,6 @@
*/
#include <linux/oprofile.h>
-#include <linux/init.h>
#include <linux/smp.h>
#include <asm/ptrace.h>
diff --git a/arch/alpha/oprofile/op_model_ev5.c b/arch/alpha/oprofile/op_model_ev5.c
index c32f8a0..c300f5e 100644
--- a/arch/alpha/oprofile/op_model_ev5.c
+++ b/arch/alpha/oprofile/op_model_ev5.c
@@ -8,7 +8,6 @@
*/
#include <linux/oprofile.h>
-#include <linux/init.h>
#include <linux/smp.h>
#include <asm/ptrace.h>
diff --git a/arch/alpha/oprofile/op_model_ev6.c b/arch/alpha/oprofile/op_model_ev6.c
index 1c84cc2..02edf59 100644
--- a/arch/alpha/oprofile/op_model_ev6.c
+++ b/arch/alpha/oprofile/op_model_ev6.c
@@ -8,7 +8,6 @@
*/
#include <linux/oprofile.h>
-#include <linux/init.h>
#include <linux/smp.h>
#include <asm/ptrace.h>
diff --git a/arch/alpha/oprofile/op_model_ev67.c b/arch/alpha/oprofile/op_model_ev67.c
index 34a57a1..adb1744 100644
--- a/arch/alpha/oprofile/op_model_ev67.c
+++ b/arch/alpha/oprofile/op_model_ev67.c
@@ -9,7 +9,6 @@
*/
#include <linux/oprofile.h>
-#include <linux/init.h>
#include <linux/smp.h>
#include <asm/ptrace.h>
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 86217db..992736b 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -223,7 +223,7 @@
imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dtb \
imx25-karo-tx25.dtb \
imx25-pdk.dtb
-dtb-$(CONFIG_SOC_IMX31) += \
+dtb-$(CONFIG_SOC_IMX27) += \
imx27-apf27.dtb \
imx27-apf27dev.dtb \
imx27-eukrea-mbimxsd27-baseboard.dtb \
diff --git a/arch/arm/boot/dts/am335x-boneblack.dts b/arch/arm/boot/dts/am335x-boneblack.dts
index 5c42d25..901739f 100644
--- a/arch/arm/boot/dts/am335x-boneblack.dts
+++ b/arch/arm/boot/dts/am335x-boneblack.dts
@@ -80,7 +80,3 @@
status = "okay";
};
};
-
-&rtc {
- system-power-controller;
-};
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 87fc7a3..156d05e 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -654,7 +654,7 @@
wlcore: wlcore@2 {
compatible = "ti,wl1271";
reg = <2>;
- interrupt-parent = <&gpio1>;
+ interrupt-parent = <&gpio0>;
interrupts = <31 IRQ_TYPE_LEVEL_HIGH>; /* gpio 31 */
ref-clock-frequency = <38400000>;
};
diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts
index 173ffa4..792394d 100644
--- a/arch/arm/boot/dts/exynos4412-trats2.dts
+++ b/arch/arm/boot/dts/exynos4412-trats2.dts
@@ -736,7 +736,7 @@
display-timings {
timing-0 {
- clock-frequency = <0>;
+ clock-frequency = <57153600>;
hactive = <720>;
vactive = <1280>;
hfront-porch = <5>;
diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi
index 6951b66..bc215e4 100644
--- a/arch/arm/boot/dts/imx27.dtsi
+++ b/arch/arm/boot/dts/imx27.dtsi
@@ -533,7 +533,7 @@
fec: ethernet@1002b000 {
compatible = "fsl,imx27-fec";
- reg = <0x1002b000 0x4000>;
+ reg = <0x1002b000 0x1000>;
interrupts = <50>;
clocks = <&clks IMX27_CLK_FEC_IPG_GATE>,
<&clks IMX27_CLK_FEC_AHB_GATE>;
diff --git a/arch/arm/boot/dts/omap3-devkit8000.dts b/arch/arm/boot/dts/omap3-devkit8000.dts
index 134d3f2..921de66 100644
--- a/arch/arm/boot/dts/omap3-devkit8000.dts
+++ b/arch/arm/boot/dts/omap3-devkit8000.dts
@@ -110,6 +110,8 @@
nand@0,0 {
reg = <0 0 4>; /* CS0, offset 0, IO size 4 */
nand-bus-width = <16>;
+ gpmc,device-width = <2>;
+ ti,nand-ecc-opt = "sw";
gpmc,sync-clk-ps = <0>;
gpmc,cs-on-ns = <0>;
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 0ca4a3e..fbbb191 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -429,7 +429,7 @@
CONFIG_USB_EHCI_TEGRA=y
CONFIG_USB_EHCI_HCD_STI=y
CONFIG_USB_EHCI_HCD_PLATFORM=y
-CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_ISP1760=y
CONFIG_USB_OHCI_HCD=y
CONFIG_USB_OHCI_HCD_STI=y
CONFIG_USB_OHCI_HCD_PLATFORM=y
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index d2f81e6..6c2327e 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -81,7 +81,7 @@
#define read_barrier_depends() do { } while(0)
#define smp_read_barrier_depends() do { } while(0)
-#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
#define smp_mb__before_atomic() smp_mb()
#define smp_mb__after_atomic() smp_mb()
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index f8ccc21..4e7f40c 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -33,7 +33,9 @@
UNWIND(.fnstart )
UNWIND(.cantunwind )
disable_irq @ disable interrupts
- ldr r1, [tsk, #TI_FLAGS]
+ ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
+ tst r1, #_TIF_SYSCALL_WORK
+ bne __sys_trace_return
tst r1, #_TIF_WORK_MASK
bne fast_work_pending
asm_trace_hardirqs_on
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 213919b..3b8c283 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -304,16 +304,17 @@
static int of_pmu_irq_cfg(struct platform_device *pdev)
{
int i, irq;
- int *irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
-
- if (!irqs)
- return -ENOMEM;
+ int *irqs;
/* Don't bother with PPIs; they're already affine */
irq = platform_get_irq(pdev, 0);
if (irq >= 0 && irq_is_percpu(irq))
return 0;
+ irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
+ if (!irqs)
+ return -ENOMEM;
+
for (i = 0; i < pdev->num_resources; ++i) {
struct device_node *dn;
int cpu;
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 4d60005..6d0893a 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -280,9 +280,15 @@
struct device_node *np;
np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpc");
- if (WARN_ON(!np ||
- !of_find_property(np, "interrupt-controller", NULL)))
- pr_warn("Outdated DT detected, system is about to crash!!!\n");
+ if (WARN_ON(!np))
+ return;
+
+ if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) {
+ pr_warn("Outdated DT detected, suspend/resume will NOT work\n");
+
+ /* map GPC, so that at least CPUidle and WARs keep working */
+ gpc_base = of_iomap(np, 0);
+ }
}
#ifdef CONFIG_PM_GENERIC_DOMAINS
@@ -443,6 +449,10 @@
struct regulator *pu_reg;
int ret;
+ /* bail out if DT too old and doesn't provide the necessary info */
+ if (!of_property_read_bool(pdev->dev.of_node, "#power-domain-cells"))
+ return 0;
+
pu_reg = devm_regulator_get_optional(&pdev->dev, "pu");
if (PTR_ERR(pu_reg) == -ENODEV)
pu_reg = NULL;
diff --git a/arch/arm/mach-pxa/pxa_cplds_irqs.c b/arch/arm/mach-pxa/pxa_cplds_irqs.c
index f1aeb54..2385052 100644
--- a/arch/arm/mach-pxa/pxa_cplds_irqs.c
+++ b/arch/arm/mach-pxa/pxa_cplds_irqs.c
@@ -107,7 +107,7 @@
struct resource *res;
struct cplds *fpga;
int ret;
- unsigned int base_irq = 0;
+ int base_irq;
unsigned long irqflags = 0;
fpga = devm_kzalloc(&pdev->dev, sizeof(*fpga), GFP_KERNEL);
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4e6ef89..7186382 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1112,22 +1112,22 @@
}
/*
- * Find the first non-section-aligned page, and point
+ * Find the first non-pmd-aligned page, and point
* memblock_limit at it. This relies on rounding the
- * limit down to be section-aligned, which happens at
- * the end of this function.
+ * limit down to be pmd-aligned, which happens at the
+ * end of this function.
*
* With this algorithm, the start or end of almost any
- * bank can be non-section-aligned. The only exception
- * is that the start of the bank 0 must be section-
+ * bank can be non-pmd-aligned. The only exception is
+ * that the start of the bank 0 must be section-
* aligned, since otherwise memory would need to be
* allocated when mapping the start of bank 0, which
* occurs before any free memory is mapped.
*/
if (!memblock_limit) {
- if (!IS_ALIGNED(block_start, SECTION_SIZE))
+ if (!IS_ALIGNED(block_start, PMD_SIZE))
memblock_limit = block_start;
- else if (!IS_ALIGNED(block_end, SECTION_SIZE))
+ else if (!IS_ALIGNED(block_end, PMD_SIZE))
memblock_limit = arm_lowmem_limit;
}
@@ -1137,12 +1137,12 @@
high_memory = __va(arm_lowmem_limit - 1) + 1;
/*
- * Round the memblock limit down to a section size. This
+ * Round the memblock limit down to a pmd size. This
* helps to ensure that we will allocate memory from the
- * last full section, which should be mapped.
+ * last full pmd, which should be mapped.
*/
if (memblock_limit)
- memblock_limit = round_down(memblock_limit, SECTION_SIZE);
+ memblock_limit = round_down(memblock_limit, PMD_SIZE);
if (!memblock_limit)
memblock_limit = arm_lowmem_limit;
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 71f19c4..0fa47c4 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -114,7 +114,7 @@
#define read_barrier_depends() do { } while(0)
#define smp_read_barrier_depends() do { } while(0)
-#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
#define nop() asm volatile("nop");
#define smp_mb__before_atomic() smp_mb()
diff --git a/arch/avr32/include/asm/cmpxchg.h b/arch/avr32/include/asm/cmpxchg.h
index 962a6ae..366bbea 100644
--- a/arch/avr32/include/asm/cmpxchg.h
+++ b/arch/avr32/include/asm/cmpxchg.h
@@ -70,8 +70,6 @@
if something tries to do an invalid cmpxchg(). */
extern void __cmpxchg_called_with_bad_pointer(void);
-#define __HAVE_ARCH_CMPXCHG 1
-
static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
unsigned long new, int size)
{
diff --git a/arch/hexagon/include/asm/cmpxchg.h b/arch/hexagon/include/asm/cmpxchg.h
index 9e78029..a6e34e2 100644
--- a/arch/hexagon/include/asm/cmpxchg.h
+++ b/arch/hexagon/include/asm/cmpxchg.h
@@ -64,7 +64,6 @@
* looks just like atomic_cmpxchg on our arch currently with a bunch of
* variable casting.
*/
-#define __HAVE_ARCH_CMPXCHG 1
#define cmpxchg(ptr, old, new) \
({ \
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
index f6769eb..843ba43 100644
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -77,12 +77,7 @@
___p1; \
})
-/*
- * XXX check on this ---I suspect what Linus really wants here is
- * acquire vs release semantics but we can't discuss this stuff with
- * Linus just yet. Grrr...
- */
-#define set_mb(var, value) do { (var) = (value); mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0)
/*
* The group barrier in front of the rsm & ssm are necessary to ensure
diff --git a/arch/ia64/include/asm/irq_remapping.h b/arch/ia64/include/asm/irq_remapping.h
index e3b3556..a8687b1 100644
--- a/arch/ia64/include/asm/irq_remapping.h
+++ b/arch/ia64/include/asm/irq_remapping.h
@@ -1,6 +1,4 @@
#ifndef __IA64_INTR_REMAPPING_H
#define __IA64_INTR_REMAPPING_H
#define irq_remapping_enabled 0
-#define dmar_alloc_hwirq create_irq
-#define dmar_free_hwirq destroy_irq
#endif
diff --git a/arch/ia64/include/uapi/asm/cmpxchg.h b/arch/ia64/include/uapi/asm/cmpxchg.h
index f35109b..a0e3620 100644
--- a/arch/ia64/include/uapi/asm/cmpxchg.h
+++ b/arch/ia64/include/uapi/asm/cmpxchg.h
@@ -61,8 +61,6 @@
* indicated by comparing RETURN with OLD.
*/
-#define __HAVE_ARCH_CMPXCHG 1
-
/*
* This function doesn't exist, so you'll get a linker error
* if something tries to do an invalid cmpxchg().
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 9dd7464..d70bf15 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -165,7 +165,7 @@
.irq_retrigger = ia64_msi_retrigger_irq,
};
-static int
+static void
msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
{
struct irq_cfg *cfg = irq_cfg + irq;
@@ -186,21 +186,29 @@
MSI_DATA_LEVEL_ASSERT |
MSI_DATA_DELIVERY_FIXED |
MSI_DATA_VECTOR(cfg->vector);
- return 0;
}
-int arch_setup_dmar_msi(unsigned int irq)
+int dmar_alloc_hwirq(int id, int node, void *arg)
{
- int ret;
+ int irq;
struct msi_msg msg;
- ret = msi_compose_msg(NULL, irq, &msg);
- if (ret < 0)
- return ret;
- dmar_msi_write(irq, &msg);
- irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
- "edge");
- return 0;
+ irq = create_irq();
+ if (irq > 0) {
+ irq_set_handler_data(irq, arg);
+ irq_set_chip_and_handler_name(irq, &dmar_msi_type,
+ handle_edge_irq, "edge");
+ msi_compose_msg(NULL, irq, &msg);
+ dmar_msi_write(irq, &msg);
+ }
+
+ return irq;
+}
+
+void dmar_free_hwirq(int irq)
+{
+ irq_set_handler_data(irq, NULL);
+ destroy_irq(irq);
}
#endif /* CONFIG_INTEL_IOMMU */
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index d4e162d..7cc3be9 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -478,9 +478,16 @@
int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
{
- struct pci_controller *controller = bridge->bus->sysdata;
-
- ACPI_COMPANION_SET(&bridge->dev, controller->companion);
+ /*
+ * We pass NULL as parent to pci_create_root_bus(), so if it is not NULL
+ * here, pci_create_root_bus() has been called by someone else and
+ * sysdata is likely to be different from what we expect. Let it go in
+ * that case.
+ */
+ if (!bridge->dev.parent) {
+ struct pci_controller *controller = bridge->bus->sysdata;
+ ACPI_COMPANION_SET(&bridge->dev, controller->companion);
+ }
return 0;
}
diff --git a/arch/m32r/include/asm/cmpxchg.h b/arch/m32r/include/asm/cmpxchg.h
index de651db..14bf9b7 100644
--- a/arch/m32r/include/asm/cmpxchg.h
+++ b/arch/m32r/include/asm/cmpxchg.h
@@ -107,8 +107,6 @@
((__typeof__(*(ptr)))__xchg_local((unsigned long)(x), (ptr), \
sizeof(*(ptr))))
-#define __HAVE_ARCH_CMPXCHG 1
-
static inline unsigned long
__cmpxchg_u32(volatile unsigned int *p, unsigned int old, unsigned int new)
{
diff --git a/arch/m68k/include/asm/cmpxchg.h b/arch/m68k/include/asm/cmpxchg.h
index bc755bc..83b1df8 100644
--- a/arch/m68k/include/asm/cmpxchg.h
+++ b/arch/m68k/include/asm/cmpxchg.h
@@ -90,7 +90,6 @@
* indicated by comparing RETURN with OLD.
*/
#ifdef CONFIG_RMW_INSNS
-#define __HAVE_ARCH_CMPXCHG 1
static inline unsigned long __cmpxchg(volatile void *p, unsigned long old,
unsigned long new, int size)
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index d703d8e..5a696e5 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -84,7 +84,7 @@
#define read_barrier_depends() do { } while (0)
#define smp_read_barrier_depends() do { } while (0)
-#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
#define smp_store_release(p, v) \
do { \
diff --git a/arch/metag/include/asm/cmpxchg.h b/arch/metag/include/asm/cmpxchg.h
index b1bc1be..be29e3e 100644
--- a/arch/metag/include/asm/cmpxchg.h
+++ b/arch/metag/include/asm/cmpxchg.h
@@ -51,8 +51,6 @@
return old;
}
-#define __HAVE_ARCH_CMPXCHG 1
-
#define cmpxchg(ptr, o, n) \
({ \
__typeof__(*(ptr)) _o_ = (o); \
diff --git a/arch/mips/ath79/prom.c b/arch/mips/ath79/prom.c
index e1fe630..597899a 100644
--- a/arch/mips/ath79/prom.c
+++ b/arch/mips/ath79/prom.c
@@ -1,6 +1,7 @@
/*
* Atheros AR71XX/AR724X/AR913X specific prom routines
*
+ * Copyright (C) 2015 Laurent Fasnacht <l@libres.ch>
* Copyright (C) 2008-2010 Gabor Juhos <juhosg@openwrt.org>
* Copyright (C) 2008 Imre Kaloz <kaloz@openwrt.org>
*
@@ -25,12 +26,14 @@
{
fw_init_cmdline();
+#ifdef CONFIG_BLK_DEV_INITRD
/* Read the initrd address from the firmware environment */
initrd_start = fw_getenvl("initrd_start");
if (initrd_start) {
initrd_start = KSEG0ADDR(initrd_start);
initrd_end = initrd_start + fw_getenvl("initrd_size");
}
+#endif
}
void __init prom_free_prom_memory(void)
diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig
index 0026806..b2a577e 100644
--- a/arch/mips/configs/fuloong2e_defconfig
+++ b/arch/mips/configs/fuloong2e_defconfig
@@ -194,7 +194,7 @@
CONFIG_USB_C67X00_HCD=m
CONFIG_USB_EHCI_HCD=y
CONFIG_USB_EHCI_ROOT_HUB_TT=y
-CONFIG_USB_ISP1760_HCD=m
+CONFIG_USB_ISP1760=m
CONFIG_USB_OHCI_HCD=y
CONFIG_USB_UHCI_HCD=m
CONFIG_USB_R8A66597_HCD=m
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index 2b8bbbc..7ecba84 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -112,8 +112,8 @@
#define __WEAK_LLSC_MB " \n"
#endif
-#define set_mb(var, value) \
- do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) \
+ do { WRITE_ONCE(var, value); smp_mb(); } while (0)
#define smp_llsc_mb() __asm__ __volatile__(__WEAK_LLSC_MB : : :"memory")
diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index 412f945..b71ab4a 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -138,8 +138,6 @@
__xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))); \
})
-#define __HAVE_ARCH_CMPXCHG 1
-
#define __cmpxchg_asm(ld, st, m, old, new) \
({ \
__typeof(*(m)) __ret; \
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index d2bfbc2..51f57d8 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -29,7 +29,7 @@
int kgdb_early_setup;
#endif
-static unsigned long irq_map[NR_IRQS / BITS_PER_LONG];
+static DECLARE_BITMAP(irq_map, NR_IRQS);
int allocate_irqno(void)
{
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index fd528d7..336708a 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -444,7 +444,7 @@
static void bmips_wr_vec(unsigned long dst, char *start, char *end)
{
memcpy((void *)dst, start, end - start);
- dma_cache_wback((unsigned long)start, end - start);
+ dma_cache_wback(dst, end - start);
local_flush_icache_range(dst, dst + (end - start));
instruction_hazard();
}
diff --git a/arch/mips/lib/strnlen_user.S b/arch/mips/lib/strnlen_user.S
index 7d12c0d..77e6494 100644
--- a/arch/mips/lib/strnlen_user.S
+++ b/arch/mips/lib/strnlen_user.S
@@ -34,7 +34,12 @@
FEXPORT(__strnlen_\func\()_nocheck_asm)
move v0, a0
PTR_ADDU a1, a0 # stop pointer
-1: beq v0, a1, 1f # limit reached?
+1:
+#ifdef CONFIG_CPU_DADDI_WORKAROUNDS
+ .set noat
+ li AT, 1
+#endif
+ beq v0, a1, 1f # limit reached?
.ifeqs "\func", "kernel"
EX(lb, t0, (v0), .Lfault\@)
.else
@@ -42,7 +47,13 @@
.endif
.set noreorder
bnez t0, 1b
-1: PTR_ADDIU v0, 1
+1:
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
+ PTR_ADDIU v0, 1
+#else
+ PTR_ADDU v0, AT
+ .set at
+#endif
.set reorder
PTR_SUBU v0, a0
jr ra
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index dbd1335..0a90b96 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -46,8 +46,6 @@
#define xchg(ptr, x) \
((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
-#define __HAVE_ARCH_CMPXCHG 1
-
/* bug catcher for when unsupported size is used - won't link */
extern void __cmpxchg_called_with_bad_pointer(void);
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index a3bf5be..39505d6 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -34,7 +34,7 @@
#define rmb() __asm__ __volatile__ ("sync" : : : "memory")
#define wmb() __asm__ __volatile__ ("sync" : : : "memory")
-#define set_mb(var, value) do { var = value; mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0)
#ifdef __SUBARCH_HAS_LWSYNC
# define SMPWMB LWSYNC
diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h
index d463c68..ad6263c 100644
--- a/arch/powerpc/include/asm/cmpxchg.h
+++ b/arch/powerpc/include/asm/cmpxchg.h
@@ -144,7 +144,6 @@
* Compare and exchange - if *p == old, set it to new,
* and return the old value of *p.
*/
-#define __HAVE_ARCH_CMPXCHG 1
static __always_inline unsigned long
__cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 8d72471..e6f8615 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -36,7 +36,7 @@
#define smp_mb__before_atomic() smp_mb()
#define smp_mb__after_atomic() smp_mb()
-#define set_mb(var, value) do { var = value; mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0)
#define smp_store_release(p, v) \
do { \
diff --git a/arch/s390/include/asm/cmpxchg.h b/arch/s390/include/asm/cmpxchg.h
index 4eadec4..411464f 100644
--- a/arch/s390/include/asm/cmpxchg.h
+++ b/arch/s390/include/asm/cmpxchg.h
@@ -32,8 +32,6 @@
__old; \
})
-#define __HAVE_ARCH_CMPXCHG
-
#define __cmpxchg_double_op(p1, p2, o1, o2, n1, n2, insn) \
({ \
register __typeof__(*(p1)) __old1 asm("2") = (o1); \
diff --git a/arch/score/include/asm/cmpxchg.h b/arch/score/include/asm/cmpxchg.h
index f384839..cc3f642 100644
--- a/arch/score/include/asm/cmpxchg.h
+++ b/arch/score/include/asm/cmpxchg.h
@@ -42,8 +42,6 @@
(unsigned long)(o), \
(unsigned long)(n)))
-#define __HAVE_ARCH_CMPXCHG 1
-
#include <asm-generic/cmpxchg-local.h>
#endif /* _ASM_SCORE_CMPXCHG_H */
diff --git a/arch/sh/include/asm/barrier.h b/arch/sh/include/asm/barrier.h
index 4371530..bf91037 100644
--- a/arch/sh/include/asm/barrier.h
+++ b/arch/sh/include/asm/barrier.h
@@ -32,7 +32,7 @@
#define ctrl_barrier() __asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop")
#endif
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
#include <asm-generic/barrier.h>
diff --git a/arch/sh/include/asm/cmpxchg.h b/arch/sh/include/asm/cmpxchg.h
index f6bd140..85c97b18 100644
--- a/arch/sh/include/asm/cmpxchg.h
+++ b/arch/sh/include/asm/cmpxchg.h
@@ -46,8 +46,6 @@
* if something tries to do an invalid cmpxchg(). */
extern void __cmpxchg_called_with_bad_pointer(void);
-#define __HAVE_ARCH_CMPXCHG 1
-
static inline unsigned long __cmpxchg(volatile void * ptr, unsigned long old,
unsigned long new, int size)
{
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
index 7664894..809941e 100644
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -40,8 +40,8 @@
#define dma_rmb() rmb()
#define dma_wmb() wmb()
-#define set_mb(__var, __value) \
- do { __var = __value; membar_safe("#StoreLoad"); } while(0)
+#define smp_store_mb(__var, __value) \
+ do { WRITE_ONCE(__var, __value); membar_safe("#StoreLoad"); } while(0)
#ifdef CONFIG_SMP
#define smp_mb() mb()
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
index d38b52d..83ffb83 100644
--- a/arch/sparc/include/asm/cmpxchg_32.h
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -34,7 +34,6 @@
*
* Cribbed from <asm-parisc/atomic.h>
*/
-#define __HAVE_ARCH_CMPXCHG 1
/* bug catcher for when unsupported size is used - won't link */
void __cmpxchg_called_with_bad_pointer(void);
diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h
index 0e1ed6c..faa2f61 100644
--- a/arch/sparc/include/asm/cmpxchg_64.h
+++ b/arch/sparc/include/asm/cmpxchg_64.h
@@ -65,8 +65,6 @@
#include <asm-generic/cmpxchg-local.h>
-#define __HAVE_ARCH_CMPXCHG 1
-
static inline unsigned long
__cmpxchg_u32(volatile int *m, int old, int new)
{
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index a6e424d..a6cfdab 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -24,7 +24,8 @@
unsigned int icache_line_size;
unsigned int ecache_size;
unsigned int ecache_line_size;
- int core_id;
+ unsigned short sock_id;
+ unsigned short core_id;
int proc_id;
} cpuinfo_sparc;
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index dc165eb..2a52c91 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -308,12 +308,26 @@
" sllx %1, 32, %1\n"
" or %0, %1, %0\n"
" .previous\n"
+ " .section .sun_m7_2insn_patch, \"ax\"\n"
+ " .word 661b\n"
+ " sethi %%uhi(%4), %1\n"
+ " sethi %%hi(%4), %0\n"
+ " .word 662b\n"
+ " or %1, %%ulo(%4), %1\n"
+ " or %0, %%lo(%4), %0\n"
+ " .word 663b\n"
+ " sllx %1, 32, %1\n"
+ " or %0, %1, %0\n"
+ " .previous\n"
: "=r" (mask), "=r" (tmp)
: "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U |
_PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U |
_PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4U),
"i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
_PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V |
+ _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V),
+ "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
+ _PAGE_CP_4V | _PAGE_E_4V |
_PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V));
return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask));
@@ -342,9 +356,15 @@
" andn %0, %4, %0\n"
" or %0, %5, %0\n"
" .previous\n"
+ " .section .sun_m7_2insn_patch, \"ax\"\n"
+ " .word 661b\n"
+ " andn %0, %6, %0\n"
+ " or %0, %5, %0\n"
+ " .previous\n"
: "=r" (val)
: "0" (val), "i" (_PAGE_CP_4U | _PAGE_CV_4U), "i" (_PAGE_E_4U),
- "i" (_PAGE_CP_4V | _PAGE_CV_4V), "i" (_PAGE_E_4V));
+ "i" (_PAGE_CP_4V | _PAGE_CV_4V), "i" (_PAGE_E_4V),
+ "i" (_PAGE_CP_4V));
return __pgprot(val);
}
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index ed8f071..d1761df 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -40,11 +40,12 @@
#ifdef CONFIG_SMP
#define topology_physical_package_id(cpu) (cpu_data(cpu).proc_id)
#define topology_core_id(cpu) (cpu_data(cpu).core_id)
-#define topology_core_cpumask(cpu) (&cpu_core_map[cpu])
+#define topology_core_cpumask(cpu) (&cpu_core_sib_map[cpu])
#define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu))
#endif /* CONFIG_SMP */
extern cpumask_t cpu_core_map[NR_CPUS];
+extern cpumask_t cpu_core_sib_map[NR_CPUS];
static inline const struct cpumask *cpu_coregroup_mask(int cpu)
{
return &cpu_core_map[cpu];
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index 6fd4436..ec9c04d 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -79,6 +79,8 @@
};
extern struct sun4v_2insn_patch_entry __sun4v_2insn_patch,
__sun4v_2insn_patch_end;
+extern struct sun4v_2insn_patch_entry __sun_m7_2insn_patch,
+ __sun_m7_2insn_patch_end;
#endif /* !(__ASSEMBLY__) */
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index 07cc49e5..0f67942 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -69,6 +69,8 @@
struct sun4v_1insn_patch_entry *);
void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
struct sun4v_2insn_patch_entry *);
+void sun_m7_patch_2insn_range(struct sun4v_2insn_patch_entry *,
+ struct sun4v_2insn_patch_entry *);
extern unsigned int dcache_parity_tl1_occurred;
extern unsigned int icache_parity_tl1_occurred;
diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c
index 94e392b..814fb17 100644
--- a/arch/sparc/kernel/leon_pci_grpci2.c
+++ b/arch/sparc/kernel/leon_pci_grpci2.c
@@ -723,7 +723,6 @@
err = -ENOMEM;
goto err1;
}
- memset(grpci2priv, 0, sizeof(*grpci2priv));
priv->regs = regs;
priv->irq = ofdev->archdata.irqs[0]; /* BASE IRQ */
priv->irq_mode = (capability & STS_IRQMODE) >> STS_IRQMODE_BIT;
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index 26c80e1..6f80936 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -614,45 +614,68 @@
}
}
-static void mark_core_ids(struct mdesc_handle *hp, u64 mp, int core_id)
+static void find_back_node_value(struct mdesc_handle *hp, u64 node,
+ char *srch_val,
+ void (*func)(struct mdesc_handle *, u64, int),
+ u64 val, int depth)
{
- u64 a;
+ u64 arc;
- mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_BACK) {
- u64 t = mdesc_arc_target(hp, a);
- const char *name;
- const u64 *id;
+ /* Since we have an estimate of recursion depth, do a sanity check. */
+ if (depth == 0)
+ return;
- name = mdesc_node_name(hp, t);
- if (!strcmp(name, "cpu")) {
- id = mdesc_get_property(hp, t, "id", NULL);
- if (*id < NR_CPUS)
- cpu_data(*id).core_id = core_id;
- } else {
- u64 j;
+ mdesc_for_each_arc(arc, hp, node, MDESC_ARC_TYPE_BACK) {
+ u64 n = mdesc_arc_target(hp, arc);
+ const char *name = mdesc_node_name(hp, n);
- mdesc_for_each_arc(j, hp, t, MDESC_ARC_TYPE_BACK) {
- u64 n = mdesc_arc_target(hp, j);
- const char *n_name;
+ if (!strcmp(srch_val, name))
+ (*func)(hp, n, val);
- n_name = mdesc_node_name(hp, n);
- if (strcmp(n_name, "cpu"))
- continue;
-
- id = mdesc_get_property(hp, n, "id", NULL);
- if (*id < NR_CPUS)
- cpu_data(*id).core_id = core_id;
- }
- }
+ find_back_node_value(hp, n, srch_val, func, val, depth-1);
}
}
+static void __mark_core_id(struct mdesc_handle *hp, u64 node,
+ int core_id)
+{
+ const u64 *id = mdesc_get_property(hp, node, "id", NULL);
+
+ if (*id < num_possible_cpus())
+ cpu_data(*id).core_id = core_id;
+}
+
+static void __mark_sock_id(struct mdesc_handle *hp, u64 node,
+ int sock_id)
+{
+ const u64 *id = mdesc_get_property(hp, node, "id", NULL);
+
+ if (*id < num_possible_cpus())
+ cpu_data(*id).sock_id = sock_id;
+}
+
+static void mark_core_ids(struct mdesc_handle *hp, u64 mp,
+ int core_id)
+{
+ find_back_node_value(hp, mp, "cpu", __mark_core_id, core_id, 10);
+}
+
+static void mark_sock_ids(struct mdesc_handle *hp, u64 mp,
+ int sock_id)
+{
+ find_back_node_value(hp, mp, "cpu", __mark_sock_id, sock_id, 10);
+}
+
static void set_core_ids(struct mdesc_handle *hp)
{
int idx;
u64 mp;
idx = 1;
+
+ /* Identify unique cores by looking for cpus backpointed to by
+ * level 1 instruction caches.
+ */
mdesc_for_each_node_by_name(hp, mp, "cache") {
const u64 *level;
const char *type;
@@ -667,11 +690,72 @@
continue;
mark_core_ids(hp, mp, idx);
-
idx++;
}
}
+static int set_sock_ids_by_cache(struct mdesc_handle *hp, int level)
+{
+ u64 mp;
+ int idx = 1;
+ int fnd = 0;
+
+ /* Identify unique sockets by looking for cpus backpointed to by
+ * shared level n caches.
+ */
+ mdesc_for_each_node_by_name(hp, mp, "cache") {
+ const u64 *cur_lvl;
+
+ cur_lvl = mdesc_get_property(hp, mp, "level", NULL);
+ if (*cur_lvl != level)
+ continue;
+
+ mark_sock_ids(hp, mp, idx);
+ idx++;
+ fnd = 1;
+ }
+ return fnd;
+}
+
+static void set_sock_ids_by_socket(struct mdesc_handle *hp, u64 mp)
+{
+ int idx = 1;
+
+ mdesc_for_each_node_by_name(hp, mp, "socket") {
+ u64 a;
+
+ mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_FWD) {
+ u64 t = mdesc_arc_target(hp, a);
+ const char *name;
+ const u64 *id;
+
+ name = mdesc_node_name(hp, t);
+ if (strcmp(name, "cpu"))
+ continue;
+
+ id = mdesc_get_property(hp, t, "id", NULL);
+ if (*id < num_possible_cpus())
+ cpu_data(*id).sock_id = idx;
+ }
+ idx++;
+ }
+}
+
+static void set_sock_ids(struct mdesc_handle *hp)
+{
+ u64 mp;
+
+ /* If machine description exposes sockets data use it.
+ * Otherwise fallback to use shared L3 or L2 caches.
+ */
+ mp = mdesc_node_by_name(hp, MDESC_NODE_NULL, "sockets");
+ if (mp != MDESC_NODE_NULL)
+ return set_sock_ids_by_socket(hp, mp);
+
+ if (!set_sock_ids_by_cache(hp, 3))
+ set_sock_ids_by_cache(hp, 2);
+}
+
static void mark_proc_ids(struct mdesc_handle *hp, u64 mp, int proc_id)
{
u64 a;
@@ -707,7 +791,6 @@
continue;
mark_proc_ids(hp, mp, idx);
-
idx++;
}
}
@@ -900,6 +983,7 @@
set_core_ids(hp);
set_proc_ids(hp);
+ set_sock_ids(hp);
mdesc_release(hp);
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 6f7251f..c928bc6 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -1002,6 +1002,38 @@
subsys_initcall(pcibios_init);
#ifdef CONFIG_SYSFS
+
+#define SLOT_NAME_SIZE 11 /* Max decimal digits + null in u32 */
+
+static void pcie_bus_slot_names(struct pci_bus *pbus)
+{
+ struct pci_dev *pdev;
+ struct pci_bus *bus;
+
+ list_for_each_entry(pdev, &pbus->devices, bus_list) {
+ char name[SLOT_NAME_SIZE];
+ struct pci_slot *pci_slot;
+ const u32 *slot_num;
+ int len;
+
+ slot_num = of_get_property(pdev->dev.of_node,
+ "physical-slot#", &len);
+
+ if (slot_num == NULL || len != 4)
+ continue;
+
+ snprintf(name, sizeof(name), "%u", slot_num[0]);
+ pci_slot = pci_create_slot(pbus, slot_num[0], name, NULL);
+
+ if (IS_ERR(pci_slot))
+ pr_err("PCI: pci_create_slot returned %ld.\n",
+ PTR_ERR(pci_slot));
+ }
+
+ list_for_each_entry(bus, &pbus->children, node)
+ pcie_bus_slot_names(bus);
+}
+
static void pci_bus_slot_names(struct device_node *node, struct pci_bus *bus)
{
const struct pci_slot_names {
@@ -1053,18 +1085,29 @@
while ((pbus = pci_find_next_bus(pbus)) != NULL) {
struct device_node *node;
+ struct pci_dev *pdev;
- if (pbus->self) {
- /* PCI->PCI bridge */
- node = pbus->self->dev.of_node;
+ pdev = list_first_entry(&pbus->devices, struct pci_dev,
+ bus_list);
+
+ if (pdev && pci_is_pcie(pdev)) {
+ pcie_bus_slot_names(pbus);
} else {
- struct pci_pbm_info *pbm = pbus->sysdata;
- /* Host PCI controller */
- node = pbm->op->dev.of_node;
+ if (pbus->self) {
+
+ /* PCI->PCI bridge */
+ node = pbus->self->dev.of_node;
+
+ } else {
+ struct pci_pbm_info *pbm = pbus->sysdata;
+
+ /* Host PCI controller */
+ node = pbm->op->dev.of_node;
+ }
+
+ pci_bus_slot_names(node, pbus);
}
-
- pci_bus_slot_names(node, pbus);
}
return 0;
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index c38d19f..f7b2617 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -255,6 +255,24 @@
}
}
+void sun_m7_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
+ struct sun4v_2insn_patch_entry *end)
+{
+ while (start < end) {
+ unsigned long addr = start->addr;
+
+ *(unsigned int *) (addr + 0) = start->insns[0];
+ wmb();
+ __asm__ __volatile__("flush %0" : : "r" (addr + 0));
+
+ *(unsigned int *) (addr + 4) = start->insns[1];
+ wmb();
+ __asm__ __volatile__("flush %0" : : "r" (addr + 4));
+
+ start++;
+ }
+}
+
static void __init sun4v_patch(void)
{
extern void sun4v_hvapi_init(void);
@@ -267,6 +285,9 @@
sun4v_patch_2insn_range(&__sun4v_2insn_patch,
&__sun4v_2insn_patch_end);
+ if (sun4v_chip_type == SUN4V_CHIP_SPARC_M7)
+ sun_m7_patch_2insn_range(&__sun_m7_2insn_patch,
+ &__sun_m7_2insn_patch_end);
sun4v_hvapi_init();
}
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 61139d9..19cd08d 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -60,8 +60,12 @@
cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
{ [0 ... NR_CPUS-1] = CPU_MASK_NONE };
+cpumask_t cpu_core_sib_map[NR_CPUS] __read_mostly = {
+ [0 ... NR_CPUS-1] = CPU_MASK_NONE };
+
EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
EXPORT_SYMBOL(cpu_core_map);
+EXPORT_SYMBOL(cpu_core_sib_map);
static cpumask_t smp_commenced_mask;
@@ -1243,6 +1247,15 @@
}
}
+ for_each_present_cpu(i) {
+ unsigned int j;
+
+ for_each_present_cpu(j) {
+ if (cpu_data(i).sock_id == cpu_data(j).sock_id)
+ cpumask_set_cpu(j, &cpu_core_sib_map[i]);
+ }
+ }
+
for_each_present_cpu(i) {
unsigned int j;
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 0924305..f1a2f68 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -138,6 +138,11 @@
*(.pause_3insn_patch)
__pause_3insn_patch_end = .;
}
+ .sun_m7_2insn_patch : {
+ __sun_m7_2insn_patch = .;
+ *(.sun_m7_2insn_patch)
+ __sun_m7_2insn_patch_end = .;
+ }
PERCPU_SECTION(SMP_CACHE_BYTES)
. = ALIGN(PAGE_SIZE);
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 4ca0d6b..559cb74 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -54,6 +54,7 @@
#include "init_64.h"
unsigned long kern_linear_pte_xor[4] __read_mostly;
+static unsigned long page_cache4v_flag;
/* A bitmap, two bits for every 256MB of physical memory. These two
* bits determine what page size we use for kernel linear
@@ -1909,11 +1910,24 @@
static void __init sun4v_linear_pte_xor_finalize(void)
{
+ unsigned long pagecv_flag;
+
+ /* Bit 9 of TTE is no longer CV bit on M7 processor and it instead
+ * enables MCD error. Do not set bit 9 on M7 processor.
+ */
+ switch (sun4v_chip_type) {
+ case SUN4V_CHIP_SPARC_M7:
+ pagecv_flag = 0x00;
+ break;
+ default:
+ pagecv_flag = _PAGE_CV_4V;
+ break;
+ }
#ifndef CONFIG_DEBUG_PAGEALLOC
if (cpu_pgsz_mask & HV_PGSZ_MASK_256MB) {
kern_linear_pte_xor[1] = (_PAGE_VALID | _PAGE_SZ256MB_4V) ^
PAGE_OFFSET;
- kern_linear_pte_xor[1] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+ kern_linear_pte_xor[1] |= (_PAGE_CP_4V | pagecv_flag |
_PAGE_P_4V | _PAGE_W_4V);
} else {
kern_linear_pte_xor[1] = kern_linear_pte_xor[0];
@@ -1922,7 +1936,7 @@
if (cpu_pgsz_mask & HV_PGSZ_MASK_2GB) {
kern_linear_pte_xor[2] = (_PAGE_VALID | _PAGE_SZ2GB_4V) ^
PAGE_OFFSET;
- kern_linear_pte_xor[2] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+ kern_linear_pte_xor[2] |= (_PAGE_CP_4V | pagecv_flag |
_PAGE_P_4V | _PAGE_W_4V);
} else {
kern_linear_pte_xor[2] = kern_linear_pte_xor[1];
@@ -1931,7 +1945,7 @@
if (cpu_pgsz_mask & HV_PGSZ_MASK_16GB) {
kern_linear_pte_xor[3] = (_PAGE_VALID | _PAGE_SZ16GB_4V) ^
PAGE_OFFSET;
- kern_linear_pte_xor[3] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+ kern_linear_pte_xor[3] |= (_PAGE_CP_4V | pagecv_flag |
_PAGE_P_4V | _PAGE_W_4V);
} else {
kern_linear_pte_xor[3] = kern_linear_pte_xor[2];
@@ -1958,6 +1972,13 @@
return available;
}
+#define _PAGE_CACHE_4U (_PAGE_CP_4U | _PAGE_CV_4U)
+#define _PAGE_CACHE_4V (_PAGE_CP_4V | _PAGE_CV_4V)
+#define __DIRTY_BITS_4U (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U)
+#define __DIRTY_BITS_4V (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V)
+#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R)
+#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R)
+
/* We need to exclude reserved regions. This exclusion will include
* vmlinux and initrd. To be more precise the initrd size could be used to
* compute a new lower limit because it is freed later during initialization.
@@ -2034,6 +2055,25 @@
memset(swapper_4m_tsb, 0x40, sizeof(swapper_4m_tsb));
#endif
+ /* TTE.cv bit on sparc v9 occupies the same position as TTE.mcde
+ * bit on M7 processor. This is a conflicting usage of the same
+ * bit. Enabling TTE.cv on M7 would turn on Memory Corruption
+ * Detection error on all pages and this will lead to problems
+ * later. Kernel does not run with MCD enabled and hence rest
+ * of the required steps to fully configure memory corruption
+ * detection are not taken. We need to ensure TTE.mcde is not
+ * set on M7 processor. Compute the value of cacheability
+ * flag for use later taking this into consideration.
+ */
+ switch (sun4v_chip_type) {
+ case SUN4V_CHIP_SPARC_M7:
+ page_cache4v_flag = _PAGE_CP_4V;
+ break;
+ default:
+ page_cache4v_flag = _PAGE_CACHE_4V;
+ break;
+ }
+
if (tlb_type == hypervisor)
sun4v_pgprot_init();
else
@@ -2274,13 +2314,6 @@
}
#endif
-#define _PAGE_CACHE_4U (_PAGE_CP_4U | _PAGE_CV_4U)
-#define _PAGE_CACHE_4V (_PAGE_CP_4V | _PAGE_CV_4V)
-#define __DIRTY_BITS_4U (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U)
-#define __DIRTY_BITS_4V (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V)
-#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R)
-#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R)
-
pgprot_t PAGE_KERNEL __read_mostly;
EXPORT_SYMBOL(PAGE_KERNEL);
@@ -2312,8 +2345,7 @@
_PAGE_P_4U | _PAGE_W_4U);
if (tlb_type == hypervisor)
pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4V |
- _PAGE_CP_4V | _PAGE_CV_4V |
- _PAGE_P_4V | _PAGE_W_4V);
+ page_cache4v_flag | _PAGE_P_4V | _PAGE_W_4V);
pte_base |= _PAGE_PMD_HUGE;
@@ -2450,14 +2482,14 @@
int i;
PAGE_KERNEL = __pgprot (_PAGE_PRESENT_4V | _PAGE_VALID |
- _PAGE_CACHE_4V | _PAGE_P_4V |
+ page_cache4v_flag | _PAGE_P_4V |
__ACCESS_BITS_4V | __DIRTY_BITS_4V |
_PAGE_EXEC_4V);
PAGE_KERNEL_LOCKED = PAGE_KERNEL;
_PAGE_IE = _PAGE_IE_4V;
_PAGE_E = _PAGE_E_4V;
- _PAGE_CACHE = _PAGE_CACHE_4V;
+ _PAGE_CACHE = page_cache4v_flag;
#ifdef CONFIG_DEBUG_PAGEALLOC
kern_linear_pte_xor[0] = _PAGE_VALID ^ PAGE_OFFSET;
@@ -2465,8 +2497,8 @@
kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4V) ^
PAGE_OFFSET;
#endif
- kern_linear_pte_xor[0] |= (_PAGE_CP_4V | _PAGE_CV_4V |
- _PAGE_P_4V | _PAGE_W_4V);
+ kern_linear_pte_xor[0] |= (page_cache4v_flag | _PAGE_P_4V |
+ _PAGE_W_4V);
for (i = 1; i < 4; i++)
kern_linear_pte_xor[i] = kern_linear_pte_xor[0];
@@ -2479,12 +2511,12 @@
_PAGE_SZ4MB_4V | _PAGE_SZ512K_4V |
_PAGE_SZ64K_4V | _PAGE_SZ8K_4V);
- page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | _PAGE_CACHE_4V;
- page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+ page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | page_cache4v_flag;
+ page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
__ACCESS_BITS_4V | _PAGE_WRITE_4V | _PAGE_EXEC_4V);
- page_copy = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+ page_copy = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
__ACCESS_BITS_4V | _PAGE_EXEC_4V);
- page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+ page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
__ACCESS_BITS_4V | _PAGE_EXEC_4V);
page_exec_bit = _PAGE_EXEC_4V;
@@ -2542,7 +2574,7 @@
_PAGE_EXEC_4U | _PAGE_L_4U | _PAGE_W_4U);
if (tlb_type == hypervisor)
val = (_PAGE_VALID | _PAGE_SZ4MB_4V |
- _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V |
+ page_cache4v_flag | _PAGE_P_4V |
_PAGE_EXEC_4V | _PAGE_W_4V);
return val | paddr;
diff --git a/arch/tile/include/asm/atomic_64.h b/arch/tile/include/asm/atomic_64.h
index 7b11c5f..0496970 100644
--- a/arch/tile/include/asm/atomic_64.h
+++ b/arch/tile/include/asm/atomic_64.h
@@ -105,9 +105,6 @@
#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-/* Define this to indicate that cmpxchg is an efficient operation. */
-#define __HAVE_ARCH_CMPXCHG
-
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_TILE_ATOMIC_64_H */
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
index 3942f74..1538562 100644
--- a/arch/x86/Kbuild
+++ b/arch/x86/Kbuild
@@ -1,3 +1,6 @@
+
+obj-y += entry/
+
obj-$(CONFIG_KVM) += kvm/
# Xen paravirtualization support
@@ -11,7 +14,7 @@
obj-y += mm/
obj-y += crypto/
-obj-y += vdso/
+
obj-$(CONFIG_IA32_EMULATION) += ia32/
obj-y += platform/
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4eb0b0f..7e39f9b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -9,140 +9,141 @@
config X86_32
def_bool y
depends on !64BIT
- select CLKSRC_I8253
- select HAVE_UID16
config X86_64
def_bool y
depends on 64BIT
- select X86_DEV_DMA_OPS
- select ARCH_USE_CMPXCHG_LOCKREF
- select HAVE_LIVEPATCH
### Arch settings
config X86
def_bool y
- select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
- select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
+ select ACPI_LEGACY_TABLES_LOOKUP if ACPI
+ select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
+ select ANON_INODES
+ select ARCH_CLOCKSOURCE_DATA
+ select ARCH_DISCARD_MEMBLOCK
+ select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+ select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FAST_MULTIPLIER
select ARCH_HAS_GCOV_PROFILE_ALL
+ select ARCH_HAS_SG_CHAIN
+ select ARCH_HAVE_NMI_SAFE_CMPXCHG
+ select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
select ARCH_MIGHT_HAVE_PC_PARPORT
select ARCH_MIGHT_HAVE_PC_SERIO
- select HAVE_AOUT if X86_32
- select HAVE_UNSTABLE_SCHED_CLOCK
- select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
- select ARCH_SUPPORTS_INT128 if X86_64
- select HAVE_IDE
- select HAVE_OPROFILE
- select HAVE_PCSPKR_PLATFORM
- select HAVE_PERF_EVENTS
- select HAVE_IOREMAP_PROT
- select HAVE_KPROBES
- select HAVE_MEMBLOCK
- select HAVE_MEMBLOCK_NODE_MAP
- select ARCH_DISCARD_MEMBLOCK
- select ARCH_WANT_OPTIONAL_GPIOLIB
+ select ARCH_SUPPORTS_ATOMIC_RMW
+ select ARCH_SUPPORTS_INT128 if X86_64
+ select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
+ select ARCH_USE_BUILTIN_BSWAP
+ select ARCH_USE_CMPXCHG_LOCKREF if X86_64
+ select ARCH_USE_QUEUED_RWLOCKS
+ select ARCH_USE_QUEUED_SPINLOCKS
select ARCH_WANT_FRAME_POINTERS
+ select ARCH_WANT_IPC_PARSE_VERSION if X86_32
+ select ARCH_WANT_OPTIONAL_GPIOLIB
+ select BUILDTIME_EXTABLE_SORT
+ select CLKEVT_I8253
+ select CLKSRC_I8253 if X86_32
+ select CLOCKSOURCE_VALIDATE_LAST_CYCLE
+ select CLOCKSOURCE_WATCHDOG
+ select CLONE_BACKWARDS if X86_32
+ select COMPAT_OLD_SIGACTION if IA32_EMULATION
+ select DCACHE_WORD_ACCESS
+ select GENERIC_CLOCKEVENTS
+ select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
+ select GENERIC_CLOCKEVENTS_MIN_ADJUST
+ select GENERIC_CMOS_UPDATE
+ select GENERIC_CPU_AUTOPROBE
+ select GENERIC_EARLY_IOREMAP
+ select GENERIC_FIND_FIRST_BIT
+ select GENERIC_IOMAP
+ select GENERIC_IRQ_PROBE
+ select GENERIC_IRQ_SHOW
+ select GENERIC_PENDING_IRQ if SMP
+ select GENERIC_SMP_IDLE_THREAD
+ select GENERIC_STRNCPY_FROM_USER
+ select GENERIC_STRNLEN_USER
+ select GENERIC_TIME_VSYSCALL
+ select HAVE_ACPI_APEI if ACPI
+ select HAVE_ACPI_APEI_NMI if ACPI
+ select HAVE_ALIGNED_STRUCT_PAGE if SLUB
+ select HAVE_AOUT if X86_32
+ select HAVE_ARCH_AUDITSYSCALL
+ select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE
+ select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP
+ select HAVE_ARCH_KGDB
+ select HAVE_ARCH_KMEMCHECK
+ select HAVE_ARCH_SECCOMP_FILTER
+ select HAVE_ARCH_SOFT_DIRTY if X86_64
+ select HAVE_ARCH_TRACEHOOK
+ select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ select HAVE_BPF_JIT if X86_64
+ select HAVE_CC_STACKPROTECTOR
+ select HAVE_CMPXCHG_DOUBLE
+ select HAVE_CMPXCHG_LOCAL
+ select HAVE_CONTEXT_TRACKING if X86_64
+ select HAVE_C_RECORDMCOUNT
+ select HAVE_DEBUG_KMEMLEAK
+ select HAVE_DEBUG_STACKOVERFLOW
+ select HAVE_DMA_API_DEBUG
select HAVE_DMA_ATTRS
select HAVE_DMA_CONTIGUOUS
- select HAVE_KRETPROBES
- select GENERIC_EARLY_IOREMAP
- select HAVE_OPTPROBES
- select HAVE_KPROBES_ON_FTRACE
- select HAVE_FTRACE_MCOUNT_RECORD
- select HAVE_FENTRY if X86_64
- select HAVE_C_RECORDMCOUNT
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_REGS
- select HAVE_FUNCTION_TRACER
- select HAVE_FUNCTION_GRAPH_TRACER
- select HAVE_FUNCTION_GRAPH_FP_TEST
- select HAVE_SYSCALL_TRACEPOINTS
- select SYSCTL_EXCEPTION_TRACE
- select HAVE_KVM
- select HAVE_ARCH_KGDB
- select HAVE_ARCH_TRACEHOOK
- select HAVE_GENERIC_DMA_COHERENT if X86_32
select HAVE_EFFICIENT_UNALIGNED_ACCESS
- select USER_STACKTRACE_SUPPORT
- select HAVE_REGS_AND_STACK_ACCESS_API
- select HAVE_DMA_API_DEBUG
- select HAVE_KERNEL_GZIP
- select HAVE_KERNEL_BZIP2
- select HAVE_KERNEL_LZMA
- select HAVE_KERNEL_XZ
- select HAVE_KERNEL_LZO
- select HAVE_KERNEL_LZ4
+ select HAVE_FENTRY if X86_64
+ select HAVE_FTRACE_MCOUNT_RECORD
+ select HAVE_FUNCTION_GRAPH_FP_TEST
+ select HAVE_FUNCTION_GRAPH_TRACER
+ select HAVE_FUNCTION_TRACER
+ select HAVE_GENERIC_DMA_COHERENT if X86_32
select HAVE_HW_BREAKPOINT
+ select HAVE_IDE
+ select HAVE_IOREMAP_PROT
+ select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
+ select HAVE_IRQ_TIME_ACCOUNTING
+ select HAVE_KERNEL_BZIP2
+ select HAVE_KERNEL_GZIP
+ select HAVE_KERNEL_LZ4
+ select HAVE_KERNEL_LZMA
+ select HAVE_KERNEL_LZO
+ select HAVE_KERNEL_XZ
+ select HAVE_KPROBES
+ select HAVE_KPROBES_ON_FTRACE
+ select HAVE_KRETPROBES
+ select HAVE_KVM
+ select HAVE_LIVEPATCH if X86_64
+ select HAVE_MEMBLOCK
+ select HAVE_MEMBLOCK_NODE_MAP
select HAVE_MIXED_BREAKPOINTS_REGS
- select PERF_EVENTS
+ select HAVE_OPROFILE
+ select HAVE_OPTPROBES
+ select HAVE_PCSPKR_PLATFORM
+ select HAVE_PERF_EVENTS
select HAVE_PERF_EVENTS_NMI
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
- select HAVE_DEBUG_KMEMLEAK
- select ANON_INODES
- select HAVE_ALIGNED_STRUCT_PAGE if SLUB
- select HAVE_CMPXCHG_LOCAL
- select HAVE_CMPXCHG_DOUBLE
- select HAVE_ARCH_KMEMCHECK
- select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP
+ select HAVE_REGS_AND_STACK_ACCESS_API
+ select HAVE_SYSCALL_TRACEPOINTS
+ select HAVE_UID16 if X86_32
+ select HAVE_UNSTABLE_SCHED_CLOCK
select HAVE_USER_RETURN_NOTIFIER
- select ARCH_HAS_ELF_RANDOMIZE
- select HAVE_ARCH_JUMP_LABEL
- select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
- select SPARSE_IRQ
- select GENERIC_FIND_FIRST_BIT
- select GENERIC_IRQ_PROBE
- select GENERIC_PENDING_IRQ if SMP
- select GENERIC_IRQ_SHOW
- select GENERIC_CLOCKEVENTS_MIN_ADJUST
select IRQ_FORCED_THREADING
- select HAVE_BPF_JIT if X86_64
- select HAVE_ARCH_TRANSPARENT_HUGEPAGE
- select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE
- select ARCH_HAS_SG_CHAIN
- select CLKEVT_I8253
- select ARCH_HAVE_NMI_SAFE_CMPXCHG
- select GENERIC_IOMAP
- select DCACHE_WORD_ACCESS
- select GENERIC_SMP_IDLE_THREAD
- select ARCH_WANT_IPC_PARSE_VERSION if X86_32
- select HAVE_ARCH_SECCOMP_FILTER
- select BUILDTIME_EXTABLE_SORT
- select GENERIC_CMOS_UPDATE
- select HAVE_ARCH_SOFT_DIRTY if X86_64
- select CLOCKSOURCE_WATCHDOG
- select GENERIC_CLOCKEVENTS
- select ARCH_CLOCKSOURCE_DATA
- select CLOCKSOURCE_VALIDATE_LAST_CYCLE
- select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
- select GENERIC_TIME_VSYSCALL
- select GENERIC_STRNCPY_FROM_USER
- select GENERIC_STRNLEN_USER
- select HAVE_CONTEXT_TRACKING if X86_64
- select HAVE_IRQ_TIME_ACCOUNTING
- select VIRT_TO_BUS
- select MODULES_USE_ELF_REL if X86_32
- select MODULES_USE_ELF_RELA if X86_64
- select CLONE_BACKWARDS if X86_32
- select ARCH_USE_BUILTIN_BSWAP
- select ARCH_USE_QUEUE_RWLOCK
- select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION
- select OLD_SIGACTION if X86_32
- select COMPAT_OLD_SIGACTION if IA32_EMULATION
+ select MODULES_USE_ELF_RELA if X86_64
+ select MODULES_USE_ELF_REL if X86_32
+ select OLD_SIGACTION if X86_32
+ select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION
+ select PERF_EVENTS
select RTC_LIB
- select HAVE_DEBUG_STACKOVERFLOW
- select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
- select HAVE_CC_STACKPROTECTOR
- select GENERIC_CPU_AUTOPROBE
- select HAVE_ARCH_AUDITSYSCALL
- select ARCH_SUPPORTS_ATOMIC_RMW
- select HAVE_ACPI_APEI if ACPI
- select HAVE_ACPI_APEI_NMI if ACPI
- select ACPI_LEGACY_TABLES_LOOKUP if ACPI
- select X86_FEATURE_NAMES if PROC_FS
+ select SPARSE_IRQ
select SRCU
+ select SYSCTL_EXCEPTION_TRACE
+ select USER_STACKTRACE_SUPPORT
+ select VIRT_TO_BUS
+ select X86_DEV_DMA_OPS if X86_64
+ select X86_FEATURE_NAMES if PROC_FS
config INSTRUCTION_DECODER
def_bool y
@@ -260,10 +261,6 @@
def_bool y
depends on X86_64 && SMP
-config X86_HT
- def_bool y
- depends on SMP
-
config X86_32_LAZY_GS
def_bool y
depends on X86_32 && !CC_STACKPROTECTOR
@@ -341,7 +338,7 @@
config X86_X2APIC
bool "Support x2apic"
- depends on X86_LOCAL_APIC && X86_64 && IRQ_REMAP
+ depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST)
---help---
This enables x2apic support on CPUs that have this feature.
@@ -441,6 +438,7 @@
depends on X86_EXTENDED_PLATFORM
depends on NUMA
depends on X86_X2APIC
+ depends on PCI
---help---
This option is needed in order to support SGI Ultraviolet systems.
If you don't have one of these, you should say N here.
@@ -466,7 +464,6 @@
select X86_REBOOTFIXUPS
select OF
select OF_EARLY_FLATTREE
- select IRQ_DOMAIN
---help---
Select for the Intel CE media processor (CE4100) SOC.
This option compiles in support for the CE4100 SOC for settop
@@ -666,7 +663,7 @@
config PARAVIRT_SPINLOCKS
bool "Paravirtualization layer for spinlocks"
depends on PARAVIRT && SMP
- select UNINLINE_SPIN_UNLOCK
+ select UNINLINE_SPIN_UNLOCK if !QUEUED_SPINLOCKS
---help---
Paravirtualized spinlocks allow a pvops backend to replace the
spinlock implementation with something virtualization-friendly
@@ -851,11 +848,12 @@
default "1" if !SMP
default "8192" if MAXSMP
default "32" if SMP && X86_BIGSMP
- default "8" if SMP
+ default "8" if SMP && X86_32
+ default "64" if SMP
---help---
This allows you to specify the maximum number of CPUs which this
kernel will support. If CPUMASK_OFFSTACK is enabled, the maximum
- supported value is 4096, otherwise the maximum value is 512. The
+ supported value is 8192, otherwise the maximum value is 512. The
minimum value which makes sense is 2.
This is purely to save memory - each supported CPU adds
@@ -863,7 +861,7 @@
config SCHED_SMT
bool "SMT (Hyperthreading) scheduler support"
- depends on X86_HT
+ depends on SMP
---help---
SMT scheduler support improves the CPU scheduler's decision making
when dealing with Intel Pentium 4 chips with HyperThreading at a
@@ -873,7 +871,7 @@
config SCHED_MC
def_bool y
prompt "Multi-core scheduler support"
- depends on X86_HT
+ depends on SMP
---help---
Multi-core scheduler support improves the CPU scheduler's decision
making when dealing with multi-core CPU chips at a cost of slightly
@@ -914,12 +912,12 @@
config X86_LOCAL_APIC
def_bool y
depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
- select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
+ select IRQ_DOMAIN_HIERARCHY
+ select PCI_MSI_IRQ_DOMAIN if PCI_MSI
config X86_IO_APIC
def_bool y
depends on X86_LOCAL_APIC || X86_UP_IOAPIC
- select IRQ_DOMAIN
config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
bool "Reroute for broken boot IRQs"
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 72484a6..a5973f8 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -332,4 +332,15 @@
If unsure, say N.
+config PUNIT_ATOM_DEBUG
+ tristate "ATOM Punit debug driver"
+ select DEBUG_FS
+ select IOSF_MBI
+ ---help---
+ This is a debug driver, which gets the power states
+ of all Punit North Complex devices. The power states of
+ each device is exposed as part of the debugfs interface.
+ The current power state can be read from
+ /sys/kernel/debug/punit_atom/dev_power_state
+
endmenu
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2fda005..118e6de 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -77,6 +77,12 @@
KBUILD_AFLAGS += -m64
KBUILD_CFLAGS += -m64
+ # Align jump targets to 1 byte, not the default 16 bytes:
+ KBUILD_CFLAGS += -falign-jumps=1
+
+ # Pack loops tightly as well:
+ KBUILD_CFLAGS += -falign-loops=1
+
# Don't autogenerate traditional x87 instructions
KBUILD_CFLAGS += $(call cc-option,-mno-80387)
KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
@@ -84,6 +90,9 @@
# Use -mpreferred-stack-boundary=3 if supported.
KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
+ # Use -mskip-rax-setup if supported.
+ KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
+
# FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
@@ -140,12 +149,6 @@
sp-$(CONFIG_X86_32) := esp
sp-$(CONFIG_X86_64) := rsp
-# do binutils support CFI?
-cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_endproc,-DCONFIG_AS_CFI=1)
-# is .cfi_signal_frame supported too?
-cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1)
-cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1)
-
# does binutils support specific instructions?
asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1)
@@ -153,8 +156,8 @@
avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
-KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
-KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
+KBUILD_AFLAGS += $(asinstr) $(avx_instr) $(avx2_instr)
+KBUILD_CFLAGS += $(asinstr) $(avx_instr) $(avx2_instr)
LDFLAGS := -m elf_$(UTS_MACHINE)
@@ -178,7 +181,7 @@
# Syscall table generation
archheaders:
- $(Q)$(MAKE) $(build)=arch/x86/syscalls all
+ $(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
archprepare:
ifeq ($(CONFIG_KEXEC_FILE),y)
@@ -241,7 +244,7 @@
PHONY += vdso_install
vdso_install:
- $(Q)$(MAKE) $(build)=arch/x86/vdso $@
+ $(Q)$(MAKE) $(build)=arch/x86/entry/vdso $@
archclean:
$(Q)rm -rf $(objtree)/arch/i386
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
new file mode 100644
index 0000000..7a14497
--- /dev/null
+++ b/arch/x86/entry/Makefile
@@ -0,0 +1,10 @@
+#
+# Makefile for the x86 low level entry code
+#
+obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
+
+obj-y += vdso/
+obj-y += vsyscall/
+
+obj-$(CONFIG_IA32_EMULATION) += entry_64_compat.o syscall_32.o
+
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/entry/calling.h
similarity index 80%
rename from arch/x86/include/asm/calling.h
rename to arch/x86/entry/calling.h
index 1c8b50e..f4e6308 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/entry/calling.h
@@ -46,8 +46,6 @@
*/
-#include <asm/dwarf2.h>
-
#ifdef CONFIG_X86_64
/*
@@ -91,28 +89,27 @@
#define SIZEOF_PTREGS 21*8
.macro ALLOC_PT_GPREGS_ON_STACK addskip=0
- subq $15*8+\addskip, %rsp
- CFI_ADJUST_CFA_OFFSET 15*8+\addskip
+ addq $-(15*8+\addskip), %rsp
.endm
.macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1
.if \r11
- movq_cfi r11, 6*8+\offset
+ movq %r11, 6*8+\offset(%rsp)
.endif
.if \r8910
- movq_cfi r10, 7*8+\offset
- movq_cfi r9, 8*8+\offset
- movq_cfi r8, 9*8+\offset
+ movq %r10, 7*8+\offset(%rsp)
+ movq %r9, 8*8+\offset(%rsp)
+ movq %r8, 9*8+\offset(%rsp)
.endif
.if \rax
- movq_cfi rax, 10*8+\offset
+ movq %rax, 10*8+\offset(%rsp)
.endif
.if \rcx
- movq_cfi rcx, 11*8+\offset
+ movq %rcx, 11*8+\offset(%rsp)
.endif
- movq_cfi rdx, 12*8+\offset
- movq_cfi rsi, 13*8+\offset
- movq_cfi rdi, 14*8+\offset
+ movq %rdx, 12*8+\offset(%rsp)
+ movq %rsi, 13*8+\offset(%rsp)
+ movq %rdi, 14*8+\offset(%rsp)
.endm
.macro SAVE_C_REGS offset=0
SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1
@@ -131,24 +128,24 @@
.endm
.macro SAVE_EXTRA_REGS offset=0
- movq_cfi r15, 0*8+\offset
- movq_cfi r14, 1*8+\offset
- movq_cfi r13, 2*8+\offset
- movq_cfi r12, 3*8+\offset
- movq_cfi rbp, 4*8+\offset
- movq_cfi rbx, 5*8+\offset
+ movq %r15, 0*8+\offset(%rsp)
+ movq %r14, 1*8+\offset(%rsp)
+ movq %r13, 2*8+\offset(%rsp)
+ movq %r12, 3*8+\offset(%rsp)
+ movq %rbp, 4*8+\offset(%rsp)
+ movq %rbx, 5*8+\offset(%rsp)
.endm
.macro SAVE_EXTRA_REGS_RBP offset=0
- movq_cfi rbp, 4*8+\offset
+ movq %rbp, 4*8+\offset(%rsp)
.endm
.macro RESTORE_EXTRA_REGS offset=0
- movq_cfi_restore 0*8+\offset, r15
- movq_cfi_restore 1*8+\offset, r14
- movq_cfi_restore 2*8+\offset, r13
- movq_cfi_restore 3*8+\offset, r12
- movq_cfi_restore 4*8+\offset, rbp
- movq_cfi_restore 5*8+\offset, rbx
+ movq 0*8+\offset(%rsp), %r15
+ movq 1*8+\offset(%rsp), %r14
+ movq 2*8+\offset(%rsp), %r13
+ movq 3*8+\offset(%rsp), %r12
+ movq 4*8+\offset(%rsp), %rbp
+ movq 5*8+\offset(%rsp), %rbx
.endm
.macro ZERO_EXTRA_REGS
@@ -162,24 +159,24 @@
.macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1
.if \rstor_r11
- movq_cfi_restore 6*8, r11
+ movq 6*8(%rsp), %r11
.endif
.if \rstor_r8910
- movq_cfi_restore 7*8, r10
- movq_cfi_restore 8*8, r9
- movq_cfi_restore 9*8, r8
+ movq 7*8(%rsp), %r10
+ movq 8*8(%rsp), %r9
+ movq 9*8(%rsp), %r8
.endif
.if \rstor_rax
- movq_cfi_restore 10*8, rax
+ movq 10*8(%rsp), %rax
.endif
.if \rstor_rcx
- movq_cfi_restore 11*8, rcx
+ movq 11*8(%rsp), %rcx
.endif
.if \rstor_rdx
- movq_cfi_restore 12*8, rdx
+ movq 12*8(%rsp), %rdx
.endif
- movq_cfi_restore 13*8, rsi
- movq_cfi_restore 14*8, rdi
+ movq 13*8(%rsp), %rsi
+ movq 14*8(%rsp), %rdi
.endm
.macro RESTORE_C_REGS
RESTORE_C_REGS_HELPER 1,1,1,1,1
@@ -204,8 +201,7 @@
.endm
.macro REMOVE_PT_GPREGS_FROM_STACK addskip=0
- addq $15*8+\addskip, %rsp
- CFI_ADJUST_CFA_OFFSET -(15*8+\addskip)
+ subq $-(15*8+\addskip), %rsp
.endm
.macro icebp
@@ -224,23 +220,23 @@
*/
.macro SAVE_ALL
- pushl_cfi_reg eax
- pushl_cfi_reg ebp
- pushl_cfi_reg edi
- pushl_cfi_reg esi
- pushl_cfi_reg edx
- pushl_cfi_reg ecx
- pushl_cfi_reg ebx
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
.endm
.macro RESTORE_ALL
- popl_cfi_reg ebx
- popl_cfi_reg ecx
- popl_cfi_reg edx
- popl_cfi_reg esi
- popl_cfi_reg edi
- popl_cfi_reg ebp
- popl_cfi_reg eax
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esi
+ popl %edi
+ popl %ebp
+ popl %eax
.endm
#endif /* CONFIG_X86_64 */
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
new file mode 100644
index 0000000..21dc60a
--- /dev/null
+++ b/arch/x86/entry/entry_32.S
@@ -0,0 +1,1248 @@
+/*
+ * Copyright (C) 1991,1992 Linus Torvalds
+ *
+ * entry_32.S contains the system-call and low-level fault and trap handling routines.
+ *
+ * Stack layout in 'syscall_exit':
+ * ptrace needs to have all registers on the stack.
+ * If the order here is changed, it needs to be
+ * updated in fork.c:copy_process(), signal.c:do_signal(),
+ * ptrace.c and ptrace.h
+ *
+ * 0(%esp) - %ebx
+ * 4(%esp) - %ecx
+ * 8(%esp) - %edx
+ * C(%esp) - %esi
+ * 10(%esp) - %edi
+ * 14(%esp) - %ebp
+ * 18(%esp) - %eax
+ * 1C(%esp) - %ds
+ * 20(%esp) - %es
+ * 24(%esp) - %fs
+ * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS
+ * 2C(%esp) - orig_eax
+ * 30(%esp) - %eip
+ * 34(%esp) - %cs
+ * 38(%esp) - %eflags
+ * 3C(%esp) - %oldesp
+ * 40(%esp) - %oldss
+ */
+
+#include <linux/linkage.h>
+#include <linux/err.h>
+#include <asm/thread_info.h>
+#include <asm/irqflags.h>
+#include <asm/errno.h>
+#include <asm/segment.h>
+#include <asm/smp.h>
+#include <asm/page_types.h>
+#include <asm/percpu.h>
+#include <asm/processor-flags.h>
+#include <asm/ftrace.h>
+#include <asm/irq_vectors.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+
+/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
+#include <linux/elf-em.h>
+#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_LE 0x40000000
+
+#ifndef CONFIG_AUDITSYSCALL
+# define sysenter_audit syscall_trace_entry
+# define sysexit_audit syscall_exit_work
+#endif
+
+ .section .entry.text, "ax"
+
+/*
+ * We use macros for low-level operations which need to be overridden
+ * for paravirtualization. The following will never clobber any registers:
+ * INTERRUPT_RETURN (aka. "iret")
+ * GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
+ * ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
+ *
+ * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
+ * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
+ * Allowing a register to be clobbered can shrink the paravirt replacement
+ * enough to patch inline, increasing performance.
+ */
+
+#ifdef CONFIG_PREEMPT
+# define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
+#else
+# define preempt_stop(clobbers)
+# define resume_kernel restore_all
+#endif
+
+.macro TRACE_IRQS_IRET
+#ifdef CONFIG_TRACE_IRQFLAGS
+ testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off?
+ jz 1f
+ TRACE_IRQS_ON
+1:
+#endif
+.endm
+
+/*
+ * User gs save/restore
+ *
+ * %gs is used for userland TLS and kernel only uses it for stack
+ * canary which is required to be at %gs:20 by gcc. Read the comment
+ * at the top of stackprotector.h for more info.
+ *
+ * Local labels 98 and 99 are used.
+ */
+#ifdef CONFIG_X86_32_LAZY_GS
+
+ /* unfortunately push/pop can't be no-op */
+.macro PUSH_GS
+ pushl $0
+.endm
+.macro POP_GS pop=0
+ addl $(4 + \pop), %esp
+.endm
+.macro POP_GS_EX
+.endm
+
+ /* all the rest are no-op */
+.macro PTGS_TO_GS
+.endm
+.macro PTGS_TO_GS_EX
+.endm
+.macro GS_TO_REG reg
+.endm
+.macro REG_TO_PTGS reg
+.endm
+.macro SET_KERNEL_GS reg
+.endm
+
+#else /* CONFIG_X86_32_LAZY_GS */
+
+.macro PUSH_GS
+ pushl %gs
+.endm
+
+.macro POP_GS pop=0
+98: popl %gs
+ .if \pop <> 0
+ add $\pop, %esp
+ .endif
+.endm
+.macro POP_GS_EX
+.pushsection .fixup, "ax"
+99: movl $0, (%esp)
+ jmp 98b
+.popsection
+ _ASM_EXTABLE(98b, 99b)
+.endm
+
+.macro PTGS_TO_GS
+98: mov PT_GS(%esp), %gs
+.endm
+.macro PTGS_TO_GS_EX
+.pushsection .fixup, "ax"
+99: movl $0, PT_GS(%esp)
+ jmp 98b
+.popsection
+ _ASM_EXTABLE(98b, 99b)
+.endm
+
+.macro GS_TO_REG reg
+ movl %gs, \reg
+.endm
+.macro REG_TO_PTGS reg
+ movl \reg, PT_GS(%esp)
+.endm
+.macro SET_KERNEL_GS reg
+ movl $(__KERNEL_STACK_CANARY), \reg
+ movl \reg, %gs
+.endm
+
+#endif /* CONFIG_X86_32_LAZY_GS */
+
+.macro SAVE_ALL
+ cld
+ PUSH_GS
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+ movl $(__USER_DS), %edx
+ movl %edx, %ds
+ movl %edx, %es
+ movl $(__KERNEL_PERCPU), %edx
+ movl %edx, %fs
+ SET_KERNEL_GS %edx
+.endm
+
+.macro RESTORE_INT_REGS
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esi
+ popl %edi
+ popl %ebp
+ popl %eax
+.endm
+
+.macro RESTORE_REGS pop=0
+ RESTORE_INT_REGS
+1: popl %ds
+2: popl %es
+3: popl %fs
+ POP_GS \pop
+.pushsection .fixup, "ax"
+4: movl $0, (%esp)
+ jmp 1b
+5: movl $0, (%esp)
+ jmp 2b
+6: movl $0, (%esp)
+ jmp 3b
+.popsection
+ _ASM_EXTABLE(1b, 4b)
+ _ASM_EXTABLE(2b, 5b)
+ _ASM_EXTABLE(3b, 6b)
+ POP_GS_EX
+.endm
+
+ENTRY(ret_from_fork)
+ pushl %eax
+ call schedule_tail
+ GET_THREAD_INFO(%ebp)
+ popl %eax
+ pushl $0x0202 # Reset kernel eflags
+ popfl
+ jmp syscall_exit
+END(ret_from_fork)
+
+ENTRY(ret_from_kernel_thread)
+ pushl %eax
+ call schedule_tail
+ GET_THREAD_INFO(%ebp)
+ popl %eax
+ pushl $0x0202 # Reset kernel eflags
+ popfl
+ movl PT_EBP(%esp), %eax
+ call *PT_EBX(%esp)
+ movl $0, PT_EAX(%esp)
+ jmp syscall_exit
+ENDPROC(ret_from_kernel_thread)
+
+/*
+ * Return to user mode is not as complex as all this looks,
+ * but we want the default path for a system call return to
+ * go as quickly as possible which is why some of this is
+ * less clear than it otherwise should be.
+ */
+
+ # userspace resumption stub bypassing syscall exit tracing
+ ALIGN
+ret_from_exception:
+ preempt_stop(CLBR_ANY)
+ret_from_intr:
+ GET_THREAD_INFO(%ebp)
+#ifdef CONFIG_VM86
+ movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS
+ movb PT_CS(%esp), %al
+ andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
+#else
+ /*
+ * We can be coming here from child spawned by kernel_thread().
+ */
+ movl PT_CS(%esp), %eax
+ andl $SEGMENT_RPL_MASK, %eax
+#endif
+ cmpl $USER_RPL, %eax
+ jb resume_kernel # not returning to v8086 or userspace
+
+ENTRY(resume_userspace)
+ LOCKDEP_SYS_EXIT
+ DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
+ # setting need_resched or sigpending
+ # between sampling and the iret
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ andl $_TIF_WORK_MASK, %ecx # is there any work to be done on
+ # int/exception return?
+ jne work_pending
+ jmp restore_all
+END(ret_from_exception)
+
+#ifdef CONFIG_PREEMPT
+ENTRY(resume_kernel)
+ DISABLE_INTERRUPTS(CLBR_ANY)
+need_resched:
+ cmpl $0, PER_CPU_VAR(__preempt_count)
+ jnz restore_all
+ testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ?
+ jz restore_all
+ call preempt_schedule_irq
+ jmp need_resched
+END(resume_kernel)
+#endif
+
+/*
+ * SYSENTER_RETURN points to after the SYSENTER instruction
+ * in the vsyscall page. See vsyscall-sysentry.S, which defines
+ * the symbol.
+ */
+
+ # SYSENTER call handler stub
+ENTRY(entry_SYSENTER_32)
+ movl TSS_sysenter_sp0(%esp), %esp
+sysenter_past_esp:
+ /*
+ * Interrupts are disabled here, but we can't trace it until
+ * enough kernel state to call TRACE_IRQS_OFF can be called - but
+ * we immediately enable interrupts at that point anyway.
+ */
+ pushl $__USER_DS
+ pushl %ebp
+ pushfl
+ orl $X86_EFLAGS_IF, (%esp)
+ pushl $__USER_CS
+ /*
+ * Push current_thread_info()->sysenter_return to the stack.
+ * A tiny bit of offset fixup is necessary: TI_sysenter_return
+ * is relative to thread_info, which is at the bottom of the
+ * kernel stack page. 4*4 means the 4 words pushed above;
+ * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
+ * and THREAD_SIZE takes us to the bottom.
+ */
+ pushl ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)
+
+ pushl %eax
+ SAVE_ALL
+ ENABLE_INTERRUPTS(CLBR_NONE)
+
+/*
+ * Load the potential sixth argument from user stack.
+ * Careful about security.
+ */
+ cmpl $__PAGE_OFFSET-3, %ebp
+ jae syscall_fault
+ ASM_STAC
+1: movl (%ebp), %ebp
+ ASM_CLAC
+ movl %ebp, PT_EBP(%esp)
+ _ASM_EXTABLE(1b, syscall_fault)
+
+ GET_THREAD_INFO(%ebp)
+
+ testl $_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
+ jnz sysenter_audit
+sysenter_do_call:
+ cmpl $(NR_syscalls), %eax
+ jae sysenter_badsys
+ call *sys_call_table(, %eax, 4)
+sysenter_after_call:
+ movl %eax, PT_EAX(%esp)
+ LOCKDEP_SYS_EXIT
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ testl $_TIF_ALLWORK_MASK, %ecx
+ jnz sysexit_audit
+sysenter_exit:
+/* if something modifies registers it must also disable sysexit */
+ movl PT_EIP(%esp), %edx
+ movl PT_OLDESP(%esp), %ecx
+ xorl %ebp, %ebp
+ TRACE_IRQS_ON
+1: mov PT_FS(%esp), %fs
+ PTGS_TO_GS
+ ENABLE_INTERRUPTS_SYSEXIT
+
+#ifdef CONFIG_AUDITSYSCALL
+sysenter_audit:
+ testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), TI_flags(%ebp)
+ jnz syscall_trace_entry
+ /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */
+ movl PT_EBX(%esp), %edx /* ebx/a0: 2nd arg to audit */
+ /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */
+ pushl PT_ESI(%esp) /* a3: 5th arg */
+ pushl PT_EDX+4(%esp) /* a2: 4th arg */
+ call __audit_syscall_entry
+ popl %ecx /* get that remapped edx off the stack */
+ popl %ecx /* get that remapped esi off the stack */
+ movl PT_EAX(%esp), %eax /* reload syscall number */
+ jmp sysenter_do_call
+
+sysexit_audit:
+ testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
+ jnz syscall_exit_work
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_ANY)
+ movl %eax, %edx /* second arg, syscall return value */
+ cmpl $-MAX_ERRNO, %eax /* is it an error ? */
+ setbe %al /* 1 if so, 0 if not */
+ movzbl %al, %eax /* zero-extend that */
+ call __audit_syscall_exit
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
+ jnz syscall_exit_work
+ movl PT_EAX(%esp), %eax /* reload syscall return value */
+ jmp sysenter_exit
+#endif
+
+.pushsection .fixup, "ax"
+2: movl $0, PT_FS(%esp)
+ jmp 1b
+.popsection
+ _ASM_EXTABLE(1b, 2b)
+ PTGS_TO_GS_EX
+ENDPROC(entry_SYSENTER_32)
+
+ # system call handler stub
+ENTRY(entry_INT80_32)
+ ASM_CLAC
+ pushl %eax # save orig_eax
+ SAVE_ALL
+ GET_THREAD_INFO(%ebp)
+ # system call tracing in operation / emulation
+ testl $_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
+ jnz syscall_trace_entry
+ cmpl $(NR_syscalls), %eax
+ jae syscall_badsys
+syscall_call:
+ call *sys_call_table(, %eax, 4)
+syscall_after_call:
+ movl %eax, PT_EAX(%esp) # store the return value
+syscall_exit:
+ LOCKDEP_SYS_EXIT
+ DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
+ # setting need_resched or sigpending
+ # between sampling and the iret
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ testl $_TIF_ALLWORK_MASK, %ecx # current->work
+ jnz syscall_exit_work
+
+restore_all:
+ TRACE_IRQS_IRET
+restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
+ movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
+ /*
+ * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
+ * are returning to the kernel.
+ * See comments in process.c:copy_thread() for details.
+ */
+ movb PT_OLDSS(%esp), %ah
+ movb PT_CS(%esp), %al
+ andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
+ cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
+ je ldt_ss # returning to user-space with LDT SS
+#endif
+restore_nocheck:
+ RESTORE_REGS 4 # skip orig_eax/error_code
+irq_return:
+ INTERRUPT_RETURN
+.section .fixup, "ax"
+ENTRY(iret_exc )
+ pushl $0 # no error code
+ pushl $do_iret_error
+ jmp error_code
+.previous
+ _ASM_EXTABLE(irq_return, iret_exc)
+
+#ifdef CONFIG_X86_ESPFIX32
+ldt_ss:
+#ifdef CONFIG_PARAVIRT
+ /*
+ * The kernel can't run on a non-flat stack if paravirt mode
+ * is active. Rather than try to fixup the high bits of
+ * ESP, bypass this code entirely. This may break DOSemu
+ * and/or Wine support in a paravirt VM, although the option
+ * is still available to implement the setting of the high
+ * 16-bits in the INTERRUPT_RETURN paravirt-op.
+ */
+ cmpl $0, pv_info+PARAVIRT_enabled
+ jne restore_nocheck
+#endif
+
+/*
+ * Setup and switch to ESPFIX stack
+ *
+ * We're returning to userspace with a 16 bit stack. The CPU will not
+ * restore the high word of ESP for us on executing iret... This is an
+ * "official" bug of all the x86-compatible CPUs, which we can work
+ * around to make dosemu and wine happy. We do this by preloading the
+ * high word of ESP with the high word of the userspace ESP while
+ * compensating for the offset by changing to the ESPFIX segment with
+ * a base address that matches for the difference.
+ */
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
+ mov %esp, %edx /* load kernel esp */
+ mov PT_OLDESP(%esp), %eax /* load userspace esp */
+ mov %dx, %ax /* eax: new kernel esp */
+ sub %eax, %edx /* offset (low word is 0) */
+ shr $16, %edx
+ mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
+ mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
+ pushl $__ESPFIX_SS
+ pushl %eax /* new kernel esp */
+ /*
+ * Disable interrupts, but do not irqtrace this section: we
+ * will soon execute iret and the tracer was already set to
+ * the irqstate after the IRET:
+ */
+ DISABLE_INTERRUPTS(CLBR_EAX)
+ lss (%esp), %esp /* switch to espfix segment */
+ jmp restore_nocheck
+#endif
+ENDPROC(entry_INT80_32)
+
+ # perform work that needs to be done immediately before resumption
+ ALIGN
+work_pending:
+ testb $_TIF_NEED_RESCHED, %cl
+ jz work_notifysig
+work_resched:
+ call schedule
+ LOCKDEP_SYS_EXIT
+ DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
+ # setting need_resched or sigpending
+ # between sampling and the iret
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ andl $_TIF_WORK_MASK, %ecx # is there any work to be done other
+ # than syscall tracing?
+ jz restore_all
+ testb $_TIF_NEED_RESCHED, %cl
+ jnz work_resched
+
+work_notifysig: # deal with pending signals and
+ # notify-resume requests
+#ifdef CONFIG_VM86
+ testl $X86_EFLAGS_VM, PT_EFLAGS(%esp)
+ movl %esp, %eax
+ jnz work_notifysig_v86 # returning to kernel-space or
+ # vm86-space
+1:
+#else
+ movl %esp, %eax
+#endif
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ movb PT_CS(%esp), %bl
+ andb $SEGMENT_RPL_MASK, %bl
+ cmpb $USER_RPL, %bl
+ jb resume_kernel
+ xorl %edx, %edx
+ call do_notify_resume
+ jmp resume_userspace
+
+#ifdef CONFIG_VM86
+ ALIGN
+work_notifysig_v86:
+ pushl %ecx # save ti_flags for do_notify_resume
+ call save_v86_state # %eax contains pt_regs pointer
+ popl %ecx
+ movl %eax, %esp
+ jmp 1b
+#endif
+END(work_pending)
+
+ # perform syscall exit tracing
+ ALIGN
+syscall_trace_entry:
+ movl $-ENOSYS, PT_EAX(%esp)
+ movl %esp, %eax
+ call syscall_trace_enter
+ /* What it returned is what we'll actually use. */
+ cmpl $(NR_syscalls), %eax
+ jnae syscall_call
+ jmp syscall_exit
+END(syscall_trace_entry)
+
+ # perform syscall exit tracing
+ ALIGN
+syscall_exit_work:
+ testl $_TIF_WORK_SYSCALL_EXIT, %ecx
+ jz work_pending
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call
+ # schedule() instead
+ movl %esp, %eax
+ call syscall_trace_leave
+ jmp resume_userspace
+END(syscall_exit_work)
+
+syscall_fault:
+ ASM_CLAC
+ GET_THREAD_INFO(%ebp)
+ movl $-EFAULT, PT_EAX(%esp)
+ jmp resume_userspace
+END(syscall_fault)
+
+syscall_badsys:
+ movl $-ENOSYS, %eax
+ jmp syscall_after_call
+END(syscall_badsys)
+
+sysenter_badsys:
+ movl $-ENOSYS, %eax
+ jmp sysenter_after_call
+END(sysenter_badsys)
+
+.macro FIXUP_ESPFIX_STACK
+/*
+ * Switch back for ESPFIX stack to the normal zerobased stack
+ *
+ * We can't call C functions using the ESPFIX stack. This code reads
+ * the high word of the segment base from the GDT and swiches to the
+ * normal stack and adjusts ESP with the matching offset.
+ */
+#ifdef CONFIG_X86_ESPFIX32
+ /* fixup the stack */
+ mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
+ mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
+ shl $16, %eax
+ addl %esp, %eax /* the adjusted stack pointer */
+ pushl $__KERNEL_DS
+ pushl %eax
+ lss (%esp), %esp /* switch to the normal stack segment */
+#endif
+.endm
+.macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
+ movl %ss, %eax
+ /* see if on espfix stack */
+ cmpw $__ESPFIX_SS, %ax
+ jne 27f
+ movl $__KERNEL_DS, %eax
+ movl %eax, %ds
+ movl %eax, %es
+ /* switch to normal stack */
+ FIXUP_ESPFIX_STACK
+27:
+#endif
+.endm
+
+/*
+ * Build the entry stubs with some assembler magic.
+ * We pack 1 stub into every 8-byte block.
+ */
+ .align 8
+ENTRY(irq_entries_start)
+ vector=FIRST_EXTERNAL_VECTOR
+ .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
+ pushl $(~vector+0x80) /* Note: always in signed byte range */
+ vector=vector+1
+ jmp common_interrupt
+ .align 8
+ .endr
+END(irq_entries_start)
+
+/*
+ * the CPU automatically disables interrupts when executing an IRQ vector,
+ * so IRQ-flags tracing has to follow that:
+ */
+ .p2align CONFIG_X86_L1_CACHE_SHIFT
+common_interrupt:
+ ASM_CLAC
+ addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */
+ SAVE_ALL
+ TRACE_IRQS_OFF
+ movl %esp, %eax
+ call do_IRQ
+ jmp ret_from_intr
+ENDPROC(common_interrupt)
+
+#define BUILD_INTERRUPT3(name, nr, fn) \
+ENTRY(name) \
+ ASM_CLAC; \
+ pushl $~(nr); \
+ SAVE_ALL; \
+ TRACE_IRQS_OFF \
+ movl %esp, %eax; \
+ call fn; \
+ jmp ret_from_intr; \
+ENDPROC(name)
+
+
+#ifdef CONFIG_TRACING
+# define TRACE_BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name)
+#else
+# define TRACE_BUILD_INTERRUPT(name, nr)
+#endif
+
+#define BUILD_INTERRUPT(name, nr) \
+ BUILD_INTERRUPT3(name, nr, smp_##name); \
+ TRACE_BUILD_INTERRUPT(name, nr)
+
+/* The include is where all of the SMP etc. interrupts come from */
+#include <asm/entry_arch.h>
+
+ENTRY(coprocessor_error)
+ ASM_CLAC
+ pushl $0
+ pushl $do_coprocessor_error
+ jmp error_code
+END(coprocessor_error)
+
+ENTRY(simd_coprocessor_error)
+ ASM_CLAC
+ pushl $0
+#ifdef CONFIG_X86_INVD_BUG
+ /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
+ ALTERNATIVE "pushl $do_general_protection", \
+ "pushl $do_simd_coprocessor_error", \
+ X86_FEATURE_XMM
+#else
+ pushl $do_simd_coprocessor_error
+#endif
+ jmp error_code
+END(simd_coprocessor_error)
+
+ENTRY(device_not_available)
+ ASM_CLAC
+ pushl $-1 # mark this as an int
+ pushl $do_device_not_available
+ jmp error_code
+END(device_not_available)
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_iret)
+ iret
+ _ASM_EXTABLE(native_iret, iret_exc)
+END(native_iret)
+
+ENTRY(native_irq_enable_sysexit)
+ sti
+ sysexit
+END(native_irq_enable_sysexit)
+#endif
+
+ENTRY(overflow)
+ ASM_CLAC
+ pushl $0
+ pushl $do_overflow
+ jmp error_code
+END(overflow)
+
+ENTRY(bounds)
+ ASM_CLAC
+ pushl $0
+ pushl $do_bounds
+ jmp error_code
+END(bounds)
+
+ENTRY(invalid_op)
+ ASM_CLAC
+ pushl $0
+ pushl $do_invalid_op
+ jmp error_code
+END(invalid_op)
+
+ENTRY(coprocessor_segment_overrun)
+ ASM_CLAC
+ pushl $0
+ pushl $do_coprocessor_segment_overrun
+ jmp error_code
+END(coprocessor_segment_overrun)
+
+ENTRY(invalid_TSS)
+ ASM_CLAC
+ pushl $do_invalid_TSS
+ jmp error_code
+END(invalid_TSS)
+
+ENTRY(segment_not_present)
+ ASM_CLAC
+ pushl $do_segment_not_present
+ jmp error_code
+END(segment_not_present)
+
+ENTRY(stack_segment)
+ ASM_CLAC
+ pushl $do_stack_segment
+ jmp error_code
+END(stack_segment)
+
+ENTRY(alignment_check)
+ ASM_CLAC
+ pushl $do_alignment_check
+ jmp error_code
+END(alignment_check)
+
+ENTRY(divide_error)
+ ASM_CLAC
+ pushl $0 # no error code
+ pushl $do_divide_error
+ jmp error_code
+END(divide_error)
+
+#ifdef CONFIG_X86_MCE
+ENTRY(machine_check)
+ ASM_CLAC
+ pushl $0
+ pushl machine_check_vector
+ jmp error_code
+END(machine_check)
+#endif
+
+ENTRY(spurious_interrupt_bug)
+ ASM_CLAC
+ pushl $0
+ pushl $do_spurious_interrupt_bug
+ jmp error_code
+END(spurious_interrupt_bug)
+
+#ifdef CONFIG_XEN
+/*
+ * Xen doesn't set %esp to be precisely what the normal SYSENTER
+ * entry point expects, so fix it up before using the normal path.
+ */
+ENTRY(xen_sysenter_target)
+ addl $5*4, %esp /* remove xen-provided frame */
+ jmp sysenter_past_esp
+
+ENTRY(xen_hypervisor_callback)
+ pushl $-1 /* orig_ax = -1 => not a system call */
+ SAVE_ALL
+ TRACE_IRQS_OFF
+
+ /*
+ * Check to see if we got the event in the critical
+ * region in xen_iret_direct, after we've reenabled
+ * events and checked for pending events. This simulates
+ * iret instruction's behaviour where it delivers a
+ * pending interrupt when enabling interrupts:
+ */
+ movl PT_EIP(%esp), %eax
+ cmpl $xen_iret_start_crit, %eax
+ jb 1f
+ cmpl $xen_iret_end_crit, %eax
+ jae 1f
+
+ jmp xen_iret_crit_fixup
+
+ENTRY(xen_do_upcall)
+1: mov %esp, %eax
+ call xen_evtchn_do_upcall
+#ifndef CONFIG_PREEMPT
+ call xen_maybe_preempt_hcall
+#endif
+ jmp ret_from_intr
+ENDPROC(xen_hypervisor_callback)
+
+/*
+ * Hypervisor uses this for application faults while it executes.
+ * We get here for two reasons:
+ * 1. Fault while reloading DS, ES, FS or GS
+ * 2. Fault while executing IRET
+ * Category 1 we fix up by reattempting the load, and zeroing the segment
+ * register if the load fails.
+ * Category 2 we fix up by jumping to do_iret_error. We cannot use the
+ * normal Linux return path in this case because if we use the IRET hypercall
+ * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
+ * We distinguish between categories by maintaining a status value in EAX.
+ */
+ENTRY(xen_failsafe_callback)
+ pushl %eax
+ movl $1, %eax
+1: mov 4(%esp), %ds
+2: mov 8(%esp), %es
+3: mov 12(%esp), %fs
+4: mov 16(%esp), %gs
+ /* EAX == 0 => Category 1 (Bad segment)
+ EAX != 0 => Category 2 (Bad IRET) */
+ testl %eax, %eax
+ popl %eax
+ lea 16(%esp), %esp
+ jz 5f
+ jmp iret_exc
+5: pushl $-1 /* orig_ax = -1 => not a system call */
+ SAVE_ALL
+ jmp ret_from_exception
+
+.section .fixup, "ax"
+6: xorl %eax, %eax
+ movl %eax, 4(%esp)
+ jmp 1b
+7: xorl %eax, %eax
+ movl %eax, 8(%esp)
+ jmp 2b
+8: xorl %eax, %eax
+ movl %eax, 12(%esp)
+ jmp 3b
+9: xorl %eax, %eax
+ movl %eax, 16(%esp)
+ jmp 4b
+.previous
+ _ASM_EXTABLE(1b, 6b)
+ _ASM_EXTABLE(2b, 7b)
+ _ASM_EXTABLE(3b, 8b)
+ _ASM_EXTABLE(4b, 9b)
+ENDPROC(xen_failsafe_callback)
+
+BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
+ xen_evtchn_do_upcall)
+
+#endif /* CONFIG_XEN */
+
+#if IS_ENABLED(CONFIG_HYPERV)
+
+BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
+ hyperv_vector_handler)
+
+#endif /* CONFIG_HYPERV */
+
+#ifdef CONFIG_FUNCTION_TRACER
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+ENTRY(mcount)
+ ret
+END(mcount)
+
+ENTRY(ftrace_caller)
+ pushl %eax
+ pushl %ecx
+ pushl %edx
+ pushl $0 /* Pass NULL as regs pointer */
+ movl 4*4(%esp), %eax
+ movl 0x4(%ebp), %edx
+ movl function_trace_op, %ecx
+ subl $MCOUNT_INSN_SIZE, %eax
+
+.globl ftrace_call
+ftrace_call:
+ call ftrace_stub
+
+ addl $4, %esp /* skip NULL pointer */
+ popl %edx
+ popl %ecx
+ popl %eax
+ftrace_ret:
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+ jmp ftrace_stub
+#endif
+
+.globl ftrace_stub
+ftrace_stub:
+ ret
+END(ftrace_caller)
+
+ENTRY(ftrace_regs_caller)
+ pushf /* push flags before compare (in cs location) */
+
+ /*
+ * i386 does not save SS and ESP when coming from kernel.
+ * Instead, to get sp, ®s->sp is used (see ptrace.h).
+ * Unfortunately, that means eflags must be at the same location
+ * as the current return ip is. We move the return ip into the
+ * ip location, and move flags into the return ip location.
+ */
+ pushl 4(%esp) /* save return ip into ip slot */
+
+ pushl $0 /* Load 0 into orig_ax */
+ pushl %gs
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+
+ movl 13*4(%esp), %eax /* Get the saved flags */
+ movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */
+ /* clobbering return ip */
+ movl $__KERNEL_CS, 13*4(%esp)
+
+ movl 12*4(%esp), %eax /* Load ip (1st parameter) */
+ subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */
+ movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */
+ movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
+ pushl %esp /* Save pt_regs as 4th parameter */
+
+GLOBAL(ftrace_regs_call)
+ call ftrace_stub
+
+ addl $4, %esp /* Skip pt_regs */
+ movl 14*4(%esp), %eax /* Move flags back into cs */
+ movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */
+ movl 12*4(%esp), %eax /* Get return ip from regs->ip */
+ movl %eax, 14*4(%esp) /* Put return ip back for ret */
+
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esi
+ popl %edi
+ popl %ebp
+ popl %eax
+ popl %ds
+ popl %es
+ popl %fs
+ popl %gs
+ addl $8, %esp /* Skip orig_ax and ip */
+ popf /* Pop flags at end (no addl to corrupt flags) */
+ jmp ftrace_ret
+
+ popf
+ jmp ftrace_stub
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(mcount)
+ cmpl $__PAGE_OFFSET, %esp
+ jb ftrace_stub /* Paging not enabled yet? */
+
+ cmpl $ftrace_stub, ftrace_trace_function
+ jnz trace
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ cmpl $ftrace_stub, ftrace_graph_return
+ jnz ftrace_graph_caller
+
+ cmpl $ftrace_graph_entry_stub, ftrace_graph_entry
+ jnz ftrace_graph_caller
+#endif
+.globl ftrace_stub
+ftrace_stub:
+ ret
+
+ /* taken from glibc */
+trace:
+ pushl %eax
+ pushl %ecx
+ pushl %edx
+ movl 0xc(%esp), %eax
+ movl 0x4(%ebp), %edx
+ subl $MCOUNT_INSN_SIZE, %eax
+
+ call *ftrace_trace_function
+
+ popl %edx
+ popl %ecx
+ popl %eax
+ jmp ftrace_stub
+END(mcount)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+ pushl %eax
+ pushl %ecx
+ pushl %edx
+ movl 0xc(%esp), %eax
+ lea 0x4(%ebp), %edx
+ movl (%ebp), %ecx
+ subl $MCOUNT_INSN_SIZE, %eax
+ call prepare_ftrace_return
+ popl %edx
+ popl %ecx
+ popl %eax
+ ret
+END(ftrace_graph_caller)
+
+.globl return_to_handler
+return_to_handler:
+ pushl %eax
+ pushl %edx
+ movl %ebp, %eax
+ call ftrace_return_to_handler
+ movl %eax, %ecx
+ popl %edx
+ popl %eax
+ jmp *%ecx
+#endif
+
+#ifdef CONFIG_TRACING
+ENTRY(trace_page_fault)
+ ASM_CLAC
+ pushl $trace_do_page_fault
+ jmp error_code
+END(trace_page_fault)
+#endif
+
+ENTRY(page_fault)
+ ASM_CLAC
+ pushl $do_page_fault
+ ALIGN
+error_code:
+ /* the function address is in %gs's slot on the stack */
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+ cld
+ movl $(__KERNEL_PERCPU), %ecx
+ movl %ecx, %fs
+ UNWIND_ESPFIX_STACK
+ GS_TO_REG %ecx
+ movl PT_GS(%esp), %edi # get the function address
+ movl PT_ORIG_EAX(%esp), %edx # get the error code
+ movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart
+ REG_TO_PTGS %ecx
+ SET_KERNEL_GS %ecx
+ movl $(__USER_DS), %ecx
+ movl %ecx, %ds
+ movl %ecx, %es
+ TRACE_IRQS_OFF
+ movl %esp, %eax # pt_regs pointer
+ call *%edi
+ jmp ret_from_exception
+END(page_fault)
+
+/*
+ * Debug traps and NMI can happen at the one SYSENTER instruction
+ * that sets up the real kernel stack. Check here, since we can't
+ * allow the wrong stack to be used.
+ *
+ * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
+ * already pushed 3 words if it hits on the sysenter instruction:
+ * eflags, cs and eip.
+ *
+ * We just load the right stack, and push the three (known) values
+ * by hand onto the new stack - while updating the return eip past
+ * the instruction that would have done it for sysenter.
+ */
+.macro FIX_STACK offset ok label
+ cmpw $__KERNEL_CS, 4(%esp)
+ jne \ok
+\label:
+ movl TSS_sysenter_sp0 + \offset(%esp), %esp
+ pushfl
+ pushl $__KERNEL_CS
+ pushl $sysenter_past_esp
+.endm
+
+ENTRY(debug)
+ ASM_CLAC
+ cmpl $entry_SYSENTER_32, (%esp)
+ jne debug_stack_correct
+ FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
+debug_stack_correct:
+ pushl $-1 # mark this as an int
+ SAVE_ALL
+ TRACE_IRQS_OFF
+ xorl %edx, %edx # error code 0
+ movl %esp, %eax # pt_regs pointer
+ call do_debug
+ jmp ret_from_exception
+END(debug)
+
+/*
+ * NMI is doubly nasty. It can happen _while_ we're handling
+ * a debug fault, and the debug fault hasn't yet been able to
+ * clear up the stack. So we first check whether we got an
+ * NMI on the sysenter entry path, but after that we need to
+ * check whether we got an NMI on the debug path where the debug
+ * fault happened on the sysenter path.
+ */
+ENTRY(nmi)
+ ASM_CLAC
+#ifdef CONFIG_X86_ESPFIX32
+ pushl %eax
+ movl %ss, %eax
+ cmpw $__ESPFIX_SS, %ax
+ popl %eax
+ je nmi_espfix_stack
+#endif
+ cmpl $entry_SYSENTER_32, (%esp)
+ je nmi_stack_fixup
+ pushl %eax
+ movl %esp, %eax
+ /*
+ * Do not access memory above the end of our stack page,
+ * it might not exist.
+ */
+ andl $(THREAD_SIZE-1), %eax
+ cmpl $(THREAD_SIZE-20), %eax
+ popl %eax
+ jae nmi_stack_correct
+ cmpl $entry_SYSENTER_32, 12(%esp)
+ je nmi_debug_stack_check
+nmi_stack_correct:
+ pushl %eax
+ SAVE_ALL
+ xorl %edx, %edx # zero error code
+ movl %esp, %eax # pt_regs pointer
+ call do_nmi
+ jmp restore_all_notrace
+
+nmi_stack_fixup:
+ FIX_STACK 12, nmi_stack_correct, 1
+ jmp nmi_stack_correct
+
+nmi_debug_stack_check:
+ cmpw $__KERNEL_CS, 16(%esp)
+ jne nmi_stack_correct
+ cmpl $debug, (%esp)
+ jb nmi_stack_correct
+ cmpl $debug_esp_fix_insn, (%esp)
+ ja nmi_stack_correct
+ FIX_STACK 24, nmi_stack_correct, 1
+ jmp nmi_stack_correct
+
+#ifdef CONFIG_X86_ESPFIX32
+nmi_espfix_stack:
+ /*
+ * create the pointer to lss back
+ */
+ pushl %ss
+ pushl %esp
+ addl $4, (%esp)
+ /* copy the iret frame of 12 bytes */
+ .rept 3
+ pushl 16(%esp)
+ .endr
+ pushl %eax
+ SAVE_ALL
+ FIXUP_ESPFIX_STACK # %eax == %esp
+ xorl %edx, %edx # zero error code
+ call do_nmi
+ RESTORE_REGS
+ lss 12+4(%esp), %esp # back to espfix stack
+ jmp irq_return
+#endif
+END(nmi)
+
+ENTRY(int3)
+ ASM_CLAC
+ pushl $-1 # mark this as an int
+ SAVE_ALL
+ TRACE_IRQS_OFF
+ xorl %edx, %edx # zero error code
+ movl %esp, %eax # pt_regs pointer
+ call do_int3
+ jmp ret_from_exception
+END(int3)
+
+ENTRY(general_protection)
+ pushl $do_general_protection
+ jmp error_code
+END(general_protection)
+
+#ifdef CONFIG_KVM_GUEST
+ENTRY(async_page_fault)
+ ASM_CLAC
+ pushl $do_async_page_fault
+ jmp error_code
+END(async_page_fault)
+#endif
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
new file mode 100644
index 0000000..3bb2c43
--- /dev/null
+++ b/arch/x86/entry/entry_64.S
@@ -0,0 +1,1458 @@
+/*
+ * linux/arch/x86_64/entry.S
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs
+ * Copyright (C) 2000 Pavel Machek <pavel@suse.cz>
+ *
+ * entry.S contains the system-call and fault low-level handling routines.
+ *
+ * Some of this is documented in Documentation/x86/entry_64.txt
+ *
+ * A note on terminology:
+ * - iret frame: Architecture defined interrupt frame from SS to RIP
+ * at the top of the kernel process stack.
+ *
+ * Some macro usage:
+ * - ENTRY/END: Define functions in the symbol table.
+ * - TRACE_IRQ_*: Trace hardirq state for lock debugging.
+ * - idtentry: Define exception entry points.
+ */
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/cache.h>
+#include <asm/errno.h>
+#include "calling.h"
+#include <asm/asm-offsets.h>
+#include <asm/msr.h>
+#include <asm/unistd.h>
+#include <asm/thread_info.h>
+#include <asm/hw_irq.h>
+#include <asm/page_types.h>
+#include <asm/irqflags.h>
+#include <asm/paravirt.h>
+#include <asm/percpu.h>
+#include <asm/asm.h>
+#include <asm/context_tracking.h>
+#include <asm/smap.h>
+#include <asm/pgtable_types.h>
+#include <linux/err.h>
+
+/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
+#include <linux/elf-em.h>
+#define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_64BIT 0x80000000
+#define __AUDIT_ARCH_LE 0x40000000
+
+.code64
+.section .entry.text, "ax"
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_usergs_sysret64)
+ swapgs
+ sysretq
+ENDPROC(native_usergs_sysret64)
+#endif /* CONFIG_PARAVIRT */
+
+.macro TRACE_IRQS_IRETQ
+#ifdef CONFIG_TRACE_IRQFLAGS
+ bt $9, EFLAGS(%rsp) /* interrupts off? */
+ jnc 1f
+ TRACE_IRQS_ON
+1:
+#endif
+.endm
+
+/*
+ * When dynamic function tracer is enabled it will add a breakpoint
+ * to all locations that it is about to modify, sync CPUs, update
+ * all the code, sync CPUs, then remove the breakpoints. In this time
+ * if lockdep is enabled, it might jump back into the debug handler
+ * outside the updating of the IST protection. (TRACE_IRQS_ON/OFF).
+ *
+ * We need to change the IDT table before calling TRACE_IRQS_ON/OFF to
+ * make sure the stack pointer does not get reset back to the top
+ * of the debug stack, and instead just reuses the current stack.
+ */
+#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS)
+
+.macro TRACE_IRQS_OFF_DEBUG
+ call debug_stack_set_zero
+ TRACE_IRQS_OFF
+ call debug_stack_reset
+.endm
+
+.macro TRACE_IRQS_ON_DEBUG
+ call debug_stack_set_zero
+ TRACE_IRQS_ON
+ call debug_stack_reset
+.endm
+
+.macro TRACE_IRQS_IRETQ_DEBUG
+ bt $9, EFLAGS(%rsp) /* interrupts off? */
+ jnc 1f
+ TRACE_IRQS_ON_DEBUG
+1:
+.endm
+
+#else
+# define TRACE_IRQS_OFF_DEBUG TRACE_IRQS_OFF
+# define TRACE_IRQS_ON_DEBUG TRACE_IRQS_ON
+# define TRACE_IRQS_IRETQ_DEBUG TRACE_IRQS_IRETQ
+#endif
+
+/*
+ * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers.
+ *
+ * 64-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
+ * then loads new ss, cs, and rip from previously programmed MSRs.
+ * rflags gets masked by a value from another MSR (so CLD and CLAC
+ * are not needed). SYSCALL does not save anything on the stack
+ * and does not change rsp.
+ *
+ * Registers on entry:
+ * rax system call number
+ * rcx return address
+ * r11 saved rflags (note: r11 is callee-clobbered register in C ABI)
+ * rdi arg0
+ * rsi arg1
+ * rdx arg2
+ * r10 arg3 (needs to be moved to rcx to conform to C ABI)
+ * r8 arg4
+ * r9 arg5
+ * (note: r12-r15, rbp, rbx are callee-preserved in C ABI)
+ *
+ * Only called from user space.
+ *
+ * When user can change pt_regs->foo always force IRET. That is because
+ * it deals with uncanonical addresses better. SYSRET has trouble
+ * with them due to bugs in both AMD and Intel CPUs.
+ */
+
+ENTRY(entry_SYSCALL_64)
+ /*
+ * Interrupts are off on entry.
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
+ SWAPGS_UNSAFE_STACK
+ /*
+ * A hypervisor implementation might want to use a label
+ * after the swapgs, so that it can do the swapgs
+ * for the guest and jump here on syscall.
+ */
+GLOBAL(entry_SYSCALL_64_after_swapgs)
+
+ movq %rsp, PER_CPU_VAR(rsp_scratch)
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+ /* Construct struct pt_regs on stack */
+ pushq $__USER_DS /* pt_regs->ss */
+ pushq PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */
+ /*
+ * Re-enable interrupts.
+ * We use 'rsp_scratch' as a scratch space, hence irq-off block above
+ * must execute atomically in the face of possible interrupt-driven
+ * task preemption. We must enable interrupts only after we're done
+ * with using rsp_scratch:
+ */
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ pushq %r11 /* pt_regs->flags */
+ pushq $__USER_CS /* pt_regs->cs */
+ pushq %rcx /* pt_regs->ip */
+ pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ pushq %rdx /* pt_regs->dx */
+ pushq %rcx /* pt_regs->cx */
+ pushq $-ENOSYS /* pt_regs->ax */
+ pushq %r8 /* pt_regs->r8 */
+ pushq %r9 /* pt_regs->r9 */
+ pushq %r10 /* pt_regs->r10 */
+ pushq %r11 /* pt_regs->r11 */
+ sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */
+
+ testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz tracesys
+entry_SYSCALL_64_fastpath:
+#if __SYSCALL_MASK == ~0
+ cmpq $__NR_syscall_max, %rax
+#else
+ andl $__SYSCALL_MASK, %eax
+ cmpl $__NR_syscall_max, %eax
+#endif
+ ja 1f /* return -ENOSYS (already in pt_regs->ax) */
+ movq %r10, %rcx
+ call *sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
+1:
+/*
+ * Syscall return path ending with SYSRET (fast path).
+ * Has incompletely filled pt_regs.
+ */
+ LOCKDEP_SYS_EXIT
+ /*
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
+ DISABLE_INTERRUPTS(CLBR_NONE)
+
+ /*
+ * We must check ti flags with interrupts (or at least preemption)
+ * off because we must *never* return to userspace without
+ * processing exit work that is enqueued if we're preempted here.
+ * In particular, returning to userspace with any of the one-shot
+ * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
+ * very bad.
+ */
+ testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */
+
+ RESTORE_C_REGS_EXCEPT_RCX_R11
+ movq RIP(%rsp), %rcx
+ movq EFLAGS(%rsp), %r11
+ movq RSP(%rsp), %rsp
+ /*
+ * 64-bit SYSRET restores rip from rcx,
+ * rflags from r11 (but RF and VM bits are forced to 0),
+ * cs and ss are loaded from MSRs.
+ * Restoration of rflags re-enables interrupts.
+ *
+ * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
+ * descriptor is not reinitialized. This means that we should
+ * avoid SYSRET with SS == NULL, which could happen if we schedule,
+ * exit the kernel, and re-enter using an interrupt vector. (All
+ * interrupt entries on x86_64 set SS to NULL.) We prevent that
+ * from happening by reloading SS in __switch_to. (Actually
+ * detecting the failure in 64-bit userspace is tricky but can be
+ * done.)
+ */
+ USERGS_SYSRET64
+
+ /* Do syscall entry tracing */
+tracesys:
+ movq %rsp, %rdi
+ movl $AUDIT_ARCH_X86_64, %esi
+ call syscall_trace_enter_phase1
+ test %rax, %rax
+ jnz tracesys_phase2 /* if needed, run the slow path */
+ RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */
+ movq ORIG_RAX(%rsp), %rax
+ jmp entry_SYSCALL_64_fastpath /* and return to the fast path */
+
+tracesys_phase2:
+ SAVE_EXTRA_REGS
+ movq %rsp, %rdi
+ movl $AUDIT_ARCH_X86_64, %esi
+ movq %rax, %rdx
+ call syscall_trace_enter_phase2
+
+ /*
+ * Reload registers from stack in case ptrace changed them.
+ * We don't reload %rax because syscall_trace_entry_phase2() returned
+ * the value it wants us to use in the table lookup.
+ */
+ RESTORE_C_REGS_EXCEPT_RAX
+ RESTORE_EXTRA_REGS
+#if __SYSCALL_MASK == ~0
+ cmpq $__NR_syscall_max, %rax
+#else
+ andl $__SYSCALL_MASK, %eax
+ cmpl $__NR_syscall_max, %eax
+#endif
+ ja 1f /* return -ENOSYS (already in pt_regs->ax) */
+ movq %r10, %rcx /* fixup for C */
+ call *sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
+1:
+ /* Use IRET because user could have changed pt_regs->foo */
+
+/*
+ * Syscall return path ending with IRET.
+ * Has correct iret frame.
+ */
+GLOBAL(int_ret_from_sys_call)
+ DISABLE_INTERRUPTS(CLBR_NONE)
+int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */
+ TRACE_IRQS_OFF
+ movl $_TIF_ALLWORK_MASK, %edi
+ /* edi: mask to check */
+GLOBAL(int_with_check)
+ LOCKDEP_SYS_EXIT_IRQ
+ GET_THREAD_INFO(%rcx)
+ movl TI_flags(%rcx), %edx
+ andl %edi, %edx
+ jnz int_careful
+ andl $~TS_COMPAT, TI_status(%rcx)
+ jmp syscall_return
+
+ /*
+ * Either reschedule or signal or syscall exit tracking needed.
+ * First do a reschedule test.
+ * edx: work, edi: workmask
+ */
+int_careful:
+ bt $TIF_NEED_RESCHED, %edx
+ jnc int_very_careful
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ pushq %rdi
+ SCHEDULE_USER
+ popq %rdi
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ jmp int_with_check
+
+ /* handle signals and tracing -- both require a full pt_regs */
+int_very_careful:
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ SAVE_EXTRA_REGS
+ /* Check for syscall exit trace */
+ testl $_TIF_WORK_SYSCALL_EXIT, %edx
+ jz int_signal
+ pushq %rdi
+ leaq 8(%rsp), %rdi /* &ptregs -> arg1 */
+ call syscall_trace_leave
+ popq %rdi
+ andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU), %edi
+ jmp int_restore_rest
+
+int_signal:
+ testl $_TIF_DO_NOTIFY_MASK, %edx
+ jz 1f
+ movq %rsp, %rdi /* &ptregs -> arg1 */
+ xorl %esi, %esi /* oldset -> arg2 */
+ call do_notify_resume
+1: movl $_TIF_WORK_MASK, %edi
+int_restore_rest:
+ RESTORE_EXTRA_REGS
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ jmp int_with_check
+
+syscall_return:
+ /* The IRETQ could re-enable interrupts: */
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_IRETQ
+
+ /*
+ * Try to use SYSRET instead of IRET if we're returning to
+ * a completely clean 64-bit userspace context.
+ */
+ movq RCX(%rsp), %rcx
+ movq RIP(%rsp), %r11
+ cmpq %rcx, %r11 /* RCX == RIP */
+ jne opportunistic_sysret_failed
+
+ /*
+ * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
+ * in kernel space. This essentially lets the user take over
+ * the kernel, since userspace controls RSP.
+ *
+ * If width of "canonical tail" ever becomes variable, this will need
+ * to be updated to remain correct on both old and new CPUs.
+ */
+ .ifne __VIRTUAL_MASK_SHIFT - 47
+ .error "virtual address width changed -- SYSRET checks need update"
+ .endif
+
+ /* Change top 16 bits to be the sign-extension of 47th bit */
+ shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
+ sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
+
+ /* If this changed %rcx, it was not canonical */
+ cmpq %rcx, %r11
+ jne opportunistic_sysret_failed
+
+ cmpq $__USER_CS, CS(%rsp) /* CS must match SYSRET */
+ jne opportunistic_sysret_failed
+
+ movq R11(%rsp), %r11
+ cmpq %r11, EFLAGS(%rsp) /* R11 == RFLAGS */
+ jne opportunistic_sysret_failed
+
+ /*
+ * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET,
+ * restoring TF results in a trap from userspace immediately after
+ * SYSRET. This would cause an infinite loop whenever #DB happens
+ * with register state that satisfies the opportunistic SYSRET
+ * conditions. For example, single-stepping this user code:
+ *
+ * movq $stuck_here, %rcx
+ * pushfq
+ * popq %r11
+ * stuck_here:
+ *
+ * would never get past 'stuck_here'.
+ */
+ testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
+ jnz opportunistic_sysret_failed
+
+ /* nothing to check for RSP */
+
+ cmpq $__USER_DS, SS(%rsp) /* SS must match SYSRET */
+ jne opportunistic_sysret_failed
+
+ /*
+ * We win! This label is here just for ease of understanding
+ * perf profiles. Nothing jumps here.
+ */
+syscall_return_via_sysret:
+ /* rcx and r11 are already restored (see code above) */
+ RESTORE_C_REGS_EXCEPT_RCX_R11
+ movq RSP(%rsp), %rsp
+ USERGS_SYSRET64
+
+opportunistic_sysret_failed:
+ SWAPGS
+ jmp restore_c_regs_and_iret
+END(entry_SYSCALL_64)
+
+
+ .macro FORK_LIKE func
+ENTRY(stub_\func)
+ SAVE_EXTRA_REGS 8
+ jmp sys_\func
+END(stub_\func)
+ .endm
+
+ FORK_LIKE clone
+ FORK_LIKE fork
+ FORK_LIKE vfork
+
+ENTRY(stub_execve)
+ call sys_execve
+return_from_execve:
+ testl %eax, %eax
+ jz 1f
+ /* exec failed, can use fast SYSRET code path in this case */
+ ret
+1:
+ /* must use IRET code path (pt_regs->cs may have changed) */
+ addq $8, %rsp
+ ZERO_EXTRA_REGS
+ movq %rax, RAX(%rsp)
+ jmp int_ret_from_sys_call
+END(stub_execve)
+/*
+ * Remaining execve stubs are only 7 bytes long.
+ * ENTRY() often aligns to 16 bytes, which in this case has no benefits.
+ */
+ .align 8
+GLOBAL(stub_execveat)
+ call sys_execveat
+ jmp return_from_execve
+END(stub_execveat)
+
+#if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION)
+ .align 8
+GLOBAL(stub_x32_execve)
+GLOBAL(stub32_execve)
+ call compat_sys_execve
+ jmp return_from_execve
+END(stub32_execve)
+END(stub_x32_execve)
+ .align 8
+GLOBAL(stub_x32_execveat)
+GLOBAL(stub32_execveat)
+ call compat_sys_execveat
+ jmp return_from_execve
+END(stub32_execveat)
+END(stub_x32_execveat)
+#endif
+
+/*
+ * sigreturn is special because it needs to restore all registers on return.
+ * This cannot be done with SYSRET, so use the IRET return path instead.
+ */
+ENTRY(stub_rt_sigreturn)
+ /*
+ * SAVE_EXTRA_REGS result is not normally needed:
+ * sigreturn overwrites all pt_regs->GPREGS.
+ * But sigreturn can fail (!), and there is no easy way to detect that.
+ * To make sure RESTORE_EXTRA_REGS doesn't restore garbage on error,
+ * we SAVE_EXTRA_REGS here.
+ */
+ SAVE_EXTRA_REGS 8
+ call sys_rt_sigreturn
+return_from_stub:
+ addq $8, %rsp
+ RESTORE_EXTRA_REGS
+ movq %rax, RAX(%rsp)
+ jmp int_ret_from_sys_call
+END(stub_rt_sigreturn)
+
+#ifdef CONFIG_X86_X32_ABI
+ENTRY(stub_x32_rt_sigreturn)
+ SAVE_EXTRA_REGS 8
+ call sys32_x32_rt_sigreturn
+ jmp return_from_stub
+END(stub_x32_rt_sigreturn)
+#endif
+
+/*
+ * A newly forked process directly context switches into this address.
+ *
+ * rdi: prev task we switched from
+ */
+ENTRY(ret_from_fork)
+
+ LOCK ; btr $TIF_FORK, TI_flags(%r8)
+
+ pushq $0x0002
+ popfq /* reset kernel eflags */
+
+ call schedule_tail /* rdi: 'prev' task parameter */
+
+ RESTORE_EXTRA_REGS
+
+ testb $3, CS(%rsp) /* from kernel_thread? */
+
+ /*
+ * By the time we get here, we have no idea whether our pt_regs,
+ * ti flags, and ti status came from the 64-bit SYSCALL fast path,
+ * the slow path, or one of the 32-bit compat paths.
+ * Use IRET code path to return, since it can safely handle
+ * all of the above.
+ */
+ jnz int_ret_from_sys_call
+
+ /*
+ * We came from kernel_thread
+ * nb: we depend on RESTORE_EXTRA_REGS above
+ */
+ movq %rbp, %rdi
+ call *%rbx
+ movl $0, RAX(%rsp)
+ RESTORE_EXTRA_REGS
+ jmp int_ret_from_sys_call
+END(ret_from_fork)
+
+/*
+ * Build the entry stubs with some assembler magic.
+ * We pack 1 stub into every 8-byte block.
+ */
+ .align 8
+ENTRY(irq_entries_start)
+ vector=FIRST_EXTERNAL_VECTOR
+ .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
+ pushq $(~vector+0x80) /* Note: always in signed byte range */
+ vector=vector+1
+ jmp common_interrupt
+ .align 8
+ .endr
+END(irq_entries_start)
+
+/*
+ * Interrupt entry/exit.
+ *
+ * Interrupt entry points save only callee clobbered registers in fast path.
+ *
+ * Entry runs with interrupts off.
+ */
+
+/* 0(%rsp): ~(interrupt number) */
+ .macro interrupt func
+ cld
+ /*
+ * Since nothing in interrupt handling code touches r12...r15 members
+ * of "struct pt_regs", and since interrupts can nest, we can save
+ * four stack slots and simultaneously provide
+ * an unwind-friendly stack layout by saving "truncated" pt_regs
+ * exactly up to rbp slot, without these members.
+ */
+ ALLOC_PT_GPREGS_ON_STACK -RBP
+ SAVE_C_REGS -RBP
+ /* this goes to 0(%rsp) for unwinder, not for saving the value: */
+ SAVE_EXTRA_REGS_RBP -RBP
+
+ leaq -RBP(%rsp), %rdi /* arg1 for \func (pointer to pt_regs) */
+
+ testb $3, CS-RBP(%rsp)
+ jz 1f
+ SWAPGS
+1:
+ /*
+ * Save previous stack pointer, optionally switch to interrupt stack.
+ * irq_count is used to check if a CPU is already on an interrupt stack
+ * or not. While this is essentially redundant with preempt_count it is
+ * a little cheaper to use a separate counter in the PDA (short of
+ * moving irq_enter into assembly, which would be too much work)
+ */
+ movq %rsp, %rsi
+ incl PER_CPU_VAR(irq_count)
+ cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp
+ pushq %rsi
+ /* We entered an interrupt context - irqs are off: */
+ TRACE_IRQS_OFF
+
+ call \func
+ .endm
+
+ /*
+ * The interrupt stubs push (~vector+0x80) onto the stack and
+ * then jump to common_interrupt.
+ */
+ .p2align CONFIG_X86_L1_CACHE_SHIFT
+common_interrupt:
+ ASM_CLAC
+ addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */
+ interrupt do_IRQ
+ /* 0(%rsp): old RSP */
+ret_from_intr:
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ decl PER_CPU_VAR(irq_count)
+
+ /* Restore saved previous stack */
+ popq %rsi
+ /* return code expects complete pt_regs - adjust rsp accordingly: */
+ leaq -RBP(%rsi), %rsp
+
+ testb $3, CS(%rsp)
+ jz retint_kernel
+ /* Interrupt came from user space */
+retint_user:
+ GET_THREAD_INFO(%rcx)
+
+ /* %rcx: thread info. Interrupts are off. */
+retint_with_reschedule:
+ movl $_TIF_WORK_MASK, %edi
+retint_check:
+ LOCKDEP_SYS_EXIT_IRQ
+ movl TI_flags(%rcx), %edx
+ andl %edi, %edx
+ jnz retint_careful
+
+retint_swapgs: /* return to user-space */
+ /*
+ * The iretq could re-enable interrupts:
+ */
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_IRETQ
+
+ SWAPGS
+ jmp restore_c_regs_and_iret
+
+/* Returning to kernel space */
+retint_kernel:
+#ifdef CONFIG_PREEMPT
+ /* Interrupts are off */
+ /* Check if we need preemption */
+ bt $9, EFLAGS(%rsp) /* were interrupts off? */
+ jnc 1f
+0: cmpl $0, PER_CPU_VAR(__preempt_count)
+ jnz 1f
+ call preempt_schedule_irq
+ jmp 0b
+1:
+#endif
+ /*
+ * The iretq could re-enable interrupts:
+ */
+ TRACE_IRQS_IRETQ
+
+/*
+ * At this label, code paths which return to kernel and to user,
+ * which come from interrupts/exception and from syscalls, merge.
+ */
+restore_c_regs_and_iret:
+ RESTORE_C_REGS
+ REMOVE_PT_GPREGS_FROM_STACK 8
+ INTERRUPT_RETURN
+
+ENTRY(native_iret)
+ /*
+ * Are we returning to a stack segment from the LDT? Note: in
+ * 64-bit mode SS:RSP on the exception stack is always valid.
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ testb $4, (SS-RIP)(%rsp)
+ jnz native_irq_return_ldt
+#endif
+
+.global native_irq_return_iret
+native_irq_return_iret:
+ /*
+ * This may fault. Non-paranoid faults on return to userspace are
+ * handled by fixup_bad_iret. These include #SS, #GP, and #NP.
+ * Double-faults due to espfix64 are handled in do_double_fault.
+ * Other faults here are fatal.
+ */
+ iretq
+
+#ifdef CONFIG_X86_ESPFIX64
+native_irq_return_ldt:
+ pushq %rax
+ pushq %rdi
+ SWAPGS
+ movq PER_CPU_VAR(espfix_waddr), %rdi
+ movq %rax, (0*8)(%rdi) /* RAX */
+ movq (2*8)(%rsp), %rax /* RIP */
+ movq %rax, (1*8)(%rdi)
+ movq (3*8)(%rsp), %rax /* CS */
+ movq %rax, (2*8)(%rdi)
+ movq (4*8)(%rsp), %rax /* RFLAGS */
+ movq %rax, (3*8)(%rdi)
+ movq (6*8)(%rsp), %rax /* SS */
+ movq %rax, (5*8)(%rdi)
+ movq (5*8)(%rsp), %rax /* RSP */
+ movq %rax, (4*8)(%rdi)
+ andl $0xffff0000, %eax
+ popq %rdi
+ orq PER_CPU_VAR(espfix_stack), %rax
+ SWAPGS
+ movq %rax, %rsp
+ popq %rax
+ jmp native_irq_return_iret
+#endif
+
+ /* edi: workmask, edx: work */
+retint_careful:
+ bt $TIF_NEED_RESCHED, %edx
+ jnc retint_signal
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ pushq %rdi
+ SCHEDULE_USER
+ popq %rdi
+ GET_THREAD_INFO(%rcx)
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ jmp retint_check
+
+retint_signal:
+ testl $_TIF_DO_NOTIFY_MASK, %edx
+ jz retint_swapgs
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ SAVE_EXTRA_REGS
+ movq $-1, ORIG_RAX(%rsp)
+ xorl %esi, %esi /* oldset */
+ movq %rsp, %rdi /* &pt_regs */
+ call do_notify_resume
+ RESTORE_EXTRA_REGS
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ GET_THREAD_INFO(%rcx)
+ jmp retint_with_reschedule
+
+END(common_interrupt)
+
+/*
+ * APIC interrupts.
+ */
+.macro apicinterrupt3 num sym do_sym
+ENTRY(\sym)
+ ASM_CLAC
+ pushq $~(\num)
+.Lcommon_\sym:
+ interrupt \do_sym
+ jmp ret_from_intr
+END(\sym)
+.endm
+
+#ifdef CONFIG_TRACING
+#define trace(sym) trace_##sym
+#define smp_trace(sym) smp_trace_##sym
+
+.macro trace_apicinterrupt num sym
+apicinterrupt3 \num trace(\sym) smp_trace(\sym)
+.endm
+#else
+.macro trace_apicinterrupt num sym do_sym
+.endm
+#endif
+
+.macro apicinterrupt num sym do_sym
+apicinterrupt3 \num \sym \do_sym
+trace_apicinterrupt \num \sym
+.endm
+
+#ifdef CONFIG_SMP
+apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
+apicinterrupt3 REBOOT_VECTOR reboot_interrupt smp_reboot_interrupt
+#endif
+
+#ifdef CONFIG_X86_UV
+apicinterrupt3 UV_BAU_MESSAGE uv_bau_message_intr1 uv_bau_message_interrupt
+#endif
+
+apicinterrupt LOCAL_TIMER_VECTOR apic_timer_interrupt smp_apic_timer_interrupt
+apicinterrupt X86_PLATFORM_IPI_VECTOR x86_platform_ipi smp_x86_platform_ipi
+
+#ifdef CONFIG_HAVE_KVM
+apicinterrupt3 POSTED_INTR_VECTOR kvm_posted_intr_ipi smp_kvm_posted_intr_ipi
+apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR kvm_posted_intr_wakeup_ipi smp_kvm_posted_intr_wakeup_ipi
+#endif
+
+#ifdef CONFIG_X86_MCE_THRESHOLD
+apicinterrupt THRESHOLD_APIC_VECTOR threshold_interrupt smp_threshold_interrupt
+#endif
+
+#ifdef CONFIG_X86_MCE_AMD
+apicinterrupt DEFERRED_ERROR_VECTOR deferred_error_interrupt smp_deferred_error_interrupt
+#endif
+
+#ifdef CONFIG_X86_THERMAL_VECTOR
+apicinterrupt THERMAL_APIC_VECTOR thermal_interrupt smp_thermal_interrupt
+#endif
+
+#ifdef CONFIG_SMP
+apicinterrupt CALL_FUNCTION_SINGLE_VECTOR call_function_single_interrupt smp_call_function_single_interrupt
+apicinterrupt CALL_FUNCTION_VECTOR call_function_interrupt smp_call_function_interrupt
+apicinterrupt RESCHEDULE_VECTOR reschedule_interrupt smp_reschedule_interrupt
+#endif
+
+apicinterrupt ERROR_APIC_VECTOR error_interrupt smp_error_interrupt
+apicinterrupt SPURIOUS_APIC_VECTOR spurious_interrupt smp_spurious_interrupt
+
+#ifdef CONFIG_IRQ_WORK
+apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt
+#endif
+
+/*
+ * Exception entry points.
+ */
+#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8)
+
+.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
+ENTRY(\sym)
+ /* Sanity check */
+ .if \shift_ist != -1 && \paranoid == 0
+ .error "using shift_ist requires paranoid=1"
+ .endif
+
+ ASM_CLAC
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
+
+ .ifeq \has_error_code
+ pushq $-1 /* ORIG_RAX: no syscall to restart */
+ .endif
+
+ ALLOC_PT_GPREGS_ON_STACK
+
+ .if \paranoid
+ .if \paranoid == 1
+ testb $3, CS(%rsp) /* If coming from userspace, switch stacks */
+ jnz 1f
+ .endif
+ call paranoid_entry
+ .else
+ call error_entry
+ .endif
+ /* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
+
+ .if \paranoid
+ .if \shift_ist != -1
+ TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */
+ .else
+ TRACE_IRQS_OFF
+ .endif
+ .endif
+
+ movq %rsp, %rdi /* pt_regs pointer */
+
+ .if \has_error_code
+ movq ORIG_RAX(%rsp), %rsi /* get error code */
+ movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */
+ .else
+ xorl %esi, %esi /* no error code */
+ .endif
+
+ .if \shift_ist != -1
+ subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+ .endif
+
+ call \do_sym
+
+ .if \shift_ist != -1
+ addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+ .endif
+
+ /* these procedures expect "no swapgs" flag in ebx */
+ .if \paranoid
+ jmp paranoid_exit
+ .else
+ jmp error_exit
+ .endif
+
+ .if \paranoid == 1
+ /*
+ * Paranoid entry from userspace. Switch stacks and treat it
+ * as a normal entry. This means that paranoid handlers
+ * run in real process context if user_mode(regs).
+ */
+1:
+ call error_entry
+
+
+ movq %rsp, %rdi /* pt_regs pointer */
+ call sync_regs
+ movq %rax, %rsp /* switch stack */
+
+ movq %rsp, %rdi /* pt_regs pointer */
+
+ .if \has_error_code
+ movq ORIG_RAX(%rsp), %rsi /* get error code */
+ movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */
+ .else
+ xorl %esi, %esi /* no error code */
+ .endif
+
+ call \do_sym
+
+ jmp error_exit /* %ebx: no swapgs flag */
+ .endif
+END(\sym)
+.endm
+
+#ifdef CONFIG_TRACING
+.macro trace_idtentry sym do_sym has_error_code:req
+idtentry trace(\sym) trace(\do_sym) has_error_code=\has_error_code
+idtentry \sym \do_sym has_error_code=\has_error_code
+.endm
+#else
+.macro trace_idtentry sym do_sym has_error_code:req
+idtentry \sym \do_sym has_error_code=\has_error_code
+.endm
+#endif
+
+idtentry divide_error do_divide_error has_error_code=0
+idtentry overflow do_overflow has_error_code=0
+idtentry bounds do_bounds has_error_code=0
+idtentry invalid_op do_invalid_op has_error_code=0
+idtentry device_not_available do_device_not_available has_error_code=0
+idtentry double_fault do_double_fault has_error_code=1 paranoid=2
+idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
+idtentry invalid_TSS do_invalid_TSS has_error_code=1
+idtentry segment_not_present do_segment_not_present has_error_code=1
+idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0
+idtentry coprocessor_error do_coprocessor_error has_error_code=0
+idtentry alignment_check do_alignment_check has_error_code=1
+idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0
+
+
+ /*
+ * Reload gs selector with exception handling
+ * edi: new selector
+ */
+ENTRY(native_load_gs_index)
+ pushfq
+ DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
+ SWAPGS
+gs_change:
+ movl %edi, %gs
+2: mfence /* workaround */
+ SWAPGS
+ popfq
+ ret
+END(native_load_gs_index)
+
+ _ASM_EXTABLE(gs_change, bad_gs)
+ .section .fixup, "ax"
+ /* running with kernelgs */
+bad_gs:
+ SWAPGS /* switch back to user gs */
+ xorl %eax, %eax
+ movl %eax, %gs
+ jmp 2b
+ .previous
+
+/* Call softirq on interrupt stack. Interrupts are off. */
+ENTRY(do_softirq_own_stack)
+ pushq %rbp
+ mov %rsp, %rbp
+ incl PER_CPU_VAR(irq_count)
+ cmove PER_CPU_VAR(irq_stack_ptr), %rsp
+ push %rbp /* frame pointer backlink */
+ call __do_softirq
+ leaveq
+ decl PER_CPU_VAR(irq_count)
+ ret
+END(do_softirq_own_stack)
+
+#ifdef CONFIG_XEN
+idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0
+
+/*
+ * A note on the "critical region" in our callback handler.
+ * We want to avoid stacking callback handlers due to events occurring
+ * during handling of the last event. To do this, we keep events disabled
+ * until we've done all processing. HOWEVER, we must enable events before
+ * popping the stack frame (can't be done atomically) and so it would still
+ * be possible to get enough handler activations to overflow the stack.
+ * Although unlikely, bugs of that kind are hard to track down, so we'd
+ * like to avoid the possibility.
+ * So, on entry to the handler we detect whether we interrupted an
+ * existing activation in its critical region -- if so, we pop the current
+ * activation and restart the handler using the previous one.
+ */
+ENTRY(xen_do_hypervisor_callback) /* do_hypervisor_callback(struct *pt_regs) */
+
+/*
+ * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
+ * see the correct pointer to the pt_regs
+ */
+ movq %rdi, %rsp /* we don't return, adjust the stack frame */
+11: incl PER_CPU_VAR(irq_count)
+ movq %rsp, %rbp
+ cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp
+ pushq %rbp /* frame pointer backlink */
+ call xen_evtchn_do_upcall
+ popq %rsp
+ decl PER_CPU_VAR(irq_count)
+#ifndef CONFIG_PREEMPT
+ call xen_maybe_preempt_hcall
+#endif
+ jmp error_exit
+END(xen_do_hypervisor_callback)
+
+/*
+ * Hypervisor uses this for application faults while it executes.
+ * We get here for two reasons:
+ * 1. Fault while reloading DS, ES, FS or GS
+ * 2. Fault while executing IRET
+ * Category 1 we do not need to fix up as Xen has already reloaded all segment
+ * registers that could be reloaded and zeroed the others.
+ * Category 2 we fix up by killing the current process. We cannot use the
+ * normal Linux return path in this case because if we use the IRET hypercall
+ * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
+ * We distinguish between categories by comparing each saved segment register
+ * with its current contents: any discrepancy means we in category 1.
+ */
+ENTRY(xen_failsafe_callback)
+ movl %ds, %ecx
+ cmpw %cx, 0x10(%rsp)
+ jne 1f
+ movl %es, %ecx
+ cmpw %cx, 0x18(%rsp)
+ jne 1f
+ movl %fs, %ecx
+ cmpw %cx, 0x20(%rsp)
+ jne 1f
+ movl %gs, %ecx
+ cmpw %cx, 0x28(%rsp)
+ jne 1f
+ /* All segments match their saved values => Category 2 (Bad IRET). */
+ movq (%rsp), %rcx
+ movq 8(%rsp), %r11
+ addq $0x30, %rsp
+ pushq $0 /* RIP */
+ pushq %r11
+ pushq %rcx
+ jmp general_protection
+1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
+ movq (%rsp), %rcx
+ movq 8(%rsp), %r11
+ addq $0x30, %rsp
+ pushq $-1 /* orig_ax = -1 => not a system call */
+ ALLOC_PT_GPREGS_ON_STACK
+ SAVE_C_REGS
+ SAVE_EXTRA_REGS
+ jmp error_exit
+END(xen_failsafe_callback)
+
+apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
+ xen_hvm_callback_vector xen_evtchn_do_upcall
+
+#endif /* CONFIG_XEN */
+
+#if IS_ENABLED(CONFIG_HYPERV)
+apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
+ hyperv_callback_vector hyperv_vector_handler
+#endif /* CONFIG_HYPERV */
+
+idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
+idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
+idtentry stack_segment do_stack_segment has_error_code=1
+
+#ifdef CONFIG_XEN
+idtentry xen_debug do_debug has_error_code=0
+idtentry xen_int3 do_int3 has_error_code=0
+idtentry xen_stack_segment do_stack_segment has_error_code=1
+#endif
+
+idtentry general_protection do_general_protection has_error_code=1
+trace_idtentry page_fault do_page_fault has_error_code=1
+
+#ifdef CONFIG_KVM_GUEST
+idtentry async_page_fault do_async_page_fault has_error_code=1
+#endif
+
+#ifdef CONFIG_X86_MCE
+idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip)
+#endif
+
+/*
+ * Save all registers in pt_regs, and switch gs if needed.
+ * Use slow, but surefire "are we in kernel?" check.
+ * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
+ */
+ENTRY(paranoid_entry)
+ cld
+ SAVE_C_REGS 8
+ SAVE_EXTRA_REGS 8
+ movl $1, %ebx
+ movl $MSR_GS_BASE, %ecx
+ rdmsr
+ testl %edx, %edx
+ js 1f /* negative -> in kernel */
+ SWAPGS
+ xorl %ebx, %ebx
+1: ret
+END(paranoid_entry)
+
+/*
+ * "Paranoid" exit path from exception stack. This is invoked
+ * only on return from non-NMI IST interrupts that came
+ * from kernel space.
+ *
+ * We may be returning to very strange contexts (e.g. very early
+ * in syscall entry), so checking for preemption here would
+ * be complicated. Fortunately, we there's no good reason
+ * to try to handle preemption here.
+ *
+ * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
+ */
+ENTRY(paranoid_exit)
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF_DEBUG
+ testl %ebx, %ebx /* swapgs needed? */
+ jnz paranoid_exit_no_swapgs
+ TRACE_IRQS_IRETQ
+ SWAPGS_UNSAFE_STACK
+ jmp paranoid_exit_restore
+paranoid_exit_no_swapgs:
+ TRACE_IRQS_IRETQ_DEBUG
+paranoid_exit_restore:
+ RESTORE_EXTRA_REGS
+ RESTORE_C_REGS
+ REMOVE_PT_GPREGS_FROM_STACK 8
+ INTERRUPT_RETURN
+END(paranoid_exit)
+
+/*
+ * Save all registers in pt_regs, and switch gs if needed.
+ * Return: EBX=0: came from user mode; EBX=1: otherwise
+ */
+ENTRY(error_entry)
+ cld
+ SAVE_C_REGS 8
+ SAVE_EXTRA_REGS 8
+ xorl %ebx, %ebx
+ testb $3, CS+8(%rsp)
+ jz error_kernelspace
+
+ /* We entered from user mode */
+ SWAPGS
+
+error_entry_done:
+ TRACE_IRQS_OFF
+ ret
+
+ /*
+ * There are two places in the kernel that can potentially fault with
+ * usergs. Handle them here. B stepping K8s sometimes report a
+ * truncated RIP for IRET exceptions returning to compat mode. Check
+ * for these here too.
+ */
+error_kernelspace:
+ incl %ebx
+ leaq native_irq_return_iret(%rip), %rcx
+ cmpq %rcx, RIP+8(%rsp)
+ je error_bad_iret
+ movl %ecx, %eax /* zero extend */
+ cmpq %rax, RIP+8(%rsp)
+ je bstep_iret
+ cmpq $gs_change, RIP+8(%rsp)
+ jne error_entry_done
+
+ /*
+ * hack: gs_change can fail with user gsbase. If this happens, fix up
+ * gsbase and proceed. We'll fix up the exception and land in
+ * gs_change's error handler with kernel gsbase.
+ */
+ SWAPGS
+ jmp error_entry_done
+
+bstep_iret:
+ /* Fix truncated RIP */
+ movq %rcx, RIP+8(%rsp)
+ /* fall through */
+
+error_bad_iret:
+ /*
+ * We came from an IRET to user mode, so we have user gsbase.
+ * Switch to kernel gsbase:
+ */
+ SWAPGS
+
+ /*
+ * Pretend that the exception came from user mode: set up pt_regs
+ * as if we faulted immediately after IRET and clear EBX so that
+ * error_exit knows that we will be returning to user mode.
+ */
+ mov %rsp, %rdi
+ call fixup_bad_iret
+ mov %rax, %rsp
+ decl %ebx
+ jmp error_entry_done
+END(error_entry)
+
+
+/*
+ * On entry, EBS is a "return to kernel mode" flag:
+ * 1: already in kernel mode, don't need SWAPGS
+ * 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode
+ */
+ENTRY(error_exit)
+ movl %ebx, %eax
+ RESTORE_EXTRA_REGS
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ testl %eax, %eax
+ jnz retint_kernel
+ jmp retint_user
+END(error_exit)
+
+/* Runs on exception stack */
+ENTRY(nmi)
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
+ /*
+ * We allow breakpoints in NMIs. If a breakpoint occurs, then
+ * the iretq it performs will take us out of NMI context.
+ * This means that we can have nested NMIs where the next
+ * NMI is using the top of the stack of the previous NMI. We
+ * can't let it execute because the nested NMI will corrupt the
+ * stack of the previous NMI. NMI handlers are not re-entrant
+ * anyway.
+ *
+ * To handle this case we do the following:
+ * Check the a special location on the stack that contains
+ * a variable that is set when NMIs are executing.
+ * The interrupted task's stack is also checked to see if it
+ * is an NMI stack.
+ * If the variable is not set and the stack is not the NMI
+ * stack then:
+ * o Set the special variable on the stack
+ * o Copy the interrupt frame into a "saved" location on the stack
+ * o Copy the interrupt frame into a "copy" location on the stack
+ * o Continue processing the NMI
+ * If the variable is set or the previous stack is the NMI stack:
+ * o Modify the "copy" location to jump to the repeate_nmi
+ * o return back to the first NMI
+ *
+ * Now on exit of the first NMI, we first clear the stack variable
+ * The NMI stack will tell any nested NMIs at that point that it is
+ * nested. Then we pop the stack normally with iret, and if there was
+ * a nested NMI that updated the copy interrupt stack frame, a
+ * jump will be made to the repeat_nmi code that will handle the second
+ * NMI.
+ */
+
+ /* Use %rdx as our temp variable throughout */
+ pushq %rdx
+
+ /*
+ * If %cs was not the kernel segment, then the NMI triggered in user
+ * space, which means it is definitely not nested.
+ */
+ cmpl $__KERNEL_CS, 16(%rsp)
+ jne first_nmi
+
+ /*
+ * Check the special variable on the stack to see if NMIs are
+ * executing.
+ */
+ cmpl $1, -8(%rsp)
+ je nested_nmi
+
+ /*
+ * Now test if the previous stack was an NMI stack.
+ * We need the double check. We check the NMI stack to satisfy the
+ * race when the first NMI clears the variable before returning.
+ * We check the variable because the first NMI could be in a
+ * breakpoint routine using a breakpoint stack.
+ */
+ lea 6*8(%rsp), %rdx
+ /* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */
+ cmpq %rdx, 4*8(%rsp)
+ /* If the stack pointer is above the NMI stack, this is a normal NMI */
+ ja first_nmi
+
+ subq $EXCEPTION_STKSZ, %rdx
+ cmpq %rdx, 4*8(%rsp)
+ /* If it is below the NMI stack, it is a normal NMI */
+ jb first_nmi
+ /* Ah, it is within the NMI stack, treat it as nested */
+
+nested_nmi:
+ /*
+ * Do nothing if we interrupted the fixup in repeat_nmi.
+ * It's about to repeat the NMI handler, so we are fine
+ * with ignoring this one.
+ */
+ movq $repeat_nmi, %rdx
+ cmpq 8(%rsp), %rdx
+ ja 1f
+ movq $end_repeat_nmi, %rdx
+ cmpq 8(%rsp), %rdx
+ ja nested_nmi_out
+
+1:
+ /* Set up the interrupted NMIs stack to jump to repeat_nmi */
+ leaq -1*8(%rsp), %rdx
+ movq %rdx, %rsp
+ leaq -10*8(%rsp), %rdx
+ pushq $__KERNEL_DS
+ pushq %rdx
+ pushfq
+ pushq $__KERNEL_CS
+ pushq $repeat_nmi
+
+ /* Put stack back */
+ addq $(6*8), %rsp
+
+nested_nmi_out:
+ popq %rdx
+
+ /* No need to check faults here */
+ INTERRUPT_RETURN
+
+first_nmi:
+ /*
+ * Because nested NMIs will use the pushed location that we
+ * stored in rdx, we must keep that space available.
+ * Here's what our stack frame will look like:
+ * +-------------------------+
+ * | original SS |
+ * | original Return RSP |
+ * | original RFLAGS |
+ * | original CS |
+ * | original RIP |
+ * +-------------------------+
+ * | temp storage for rdx |
+ * +-------------------------+
+ * | NMI executing variable |
+ * +-------------------------+
+ * | copied SS |
+ * | copied Return RSP |
+ * | copied RFLAGS |
+ * | copied CS |
+ * | copied RIP |
+ * +-------------------------+
+ * | Saved SS |
+ * | Saved Return RSP |
+ * | Saved RFLAGS |
+ * | Saved CS |
+ * | Saved RIP |
+ * +-------------------------+
+ * | pt_regs |
+ * +-------------------------+
+ *
+ * The saved stack frame is used to fix up the copied stack frame
+ * that a nested NMI may change to make the interrupted NMI iret jump
+ * to the repeat_nmi. The original stack frame and the temp storage
+ * is also used by nested NMIs and can not be trusted on exit.
+ */
+ /* Do not pop rdx, nested NMIs will corrupt that part of the stack */
+ movq (%rsp), %rdx
+
+ /* Set the NMI executing variable on the stack. */
+ pushq $1
+
+ /* Leave room for the "copied" frame */
+ subq $(5*8), %rsp
+
+ /* Copy the stack frame to the Saved frame */
+ .rept 5
+ pushq 11*8(%rsp)
+ .endr
+
+ /* Everything up to here is safe from nested NMIs */
+
+ /*
+ * If there was a nested NMI, the first NMI's iret will return
+ * here. But NMIs are still enabled and we can take another
+ * nested NMI. The nested NMI checks the interrupted RIP to see
+ * if it is between repeat_nmi and end_repeat_nmi, and if so
+ * it will just return, as we are about to repeat an NMI anyway.
+ * This makes it safe to copy to the stack frame that a nested
+ * NMI will update.
+ */
+repeat_nmi:
+ /*
+ * Update the stack variable to say we are still in NMI (the update
+ * is benign for the non-repeat case, where 1 was pushed just above
+ * to this very stack slot).
+ */
+ movq $1, 10*8(%rsp)
+
+ /* Make another copy, this one may be modified by nested NMIs */
+ addq $(10*8), %rsp
+ .rept 5
+ pushq -6*8(%rsp)
+ .endr
+ subq $(5*8), %rsp
+end_repeat_nmi:
+
+ /*
+ * Everything below this point can be preempted by a nested
+ * NMI if the first NMI took an exception and reset our iret stack
+ * so that we repeat another NMI.
+ */
+ pushq $-1 /* ORIG_RAX: no syscall to restart */
+ ALLOC_PT_GPREGS_ON_STACK
+
+ /*
+ * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
+ * as we should not be calling schedule in NMI context.
+ * Even with normal interrupts enabled. An NMI should not be
+ * setting NEED_RESCHED or anything that normal interrupts and
+ * exceptions might do.
+ */
+ call paranoid_entry
+
+ /*
+ * Save off the CR2 register. If we take a page fault in the NMI then
+ * it could corrupt the CR2 value. If the NMI preempts a page fault
+ * handler before it was able to read the CR2 register, and then the
+ * NMI itself takes a page fault, the page fault that was preempted
+ * will read the information from the NMI page fault and not the
+ * origin fault. Save it off and restore it if it changes.
+ * Use the r12 callee-saved register.
+ */
+ movq %cr2, %r12
+
+ /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
+ movq %rsp, %rdi
+ movq $-1, %rsi
+ call do_nmi
+
+ /* Did the NMI take a page fault? Restore cr2 if it did */
+ movq %cr2, %rcx
+ cmpq %rcx, %r12
+ je 1f
+ movq %r12, %cr2
+1:
+ testl %ebx, %ebx /* swapgs needed? */
+ jnz nmi_restore
+nmi_swapgs:
+ SWAPGS_UNSAFE_STACK
+nmi_restore:
+ RESTORE_EXTRA_REGS
+ RESTORE_C_REGS
+ /* Pop the extra iret frame at once */
+ REMOVE_PT_GPREGS_FROM_STACK 6*8
+
+ /* Clear the NMI executing stack variable */
+ movq $0, 5*8(%rsp)
+ INTERRUPT_RETURN
+END(nmi)
+
+ENTRY(ignore_sysret)
+ mov $-ENOSYS, %eax
+ sysret
+END(ignore_sysret)
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
new file mode 100644
index 0000000..bb187a6
--- /dev/null
+++ b/arch/x86/entry/entry_64_compat.S
@@ -0,0 +1,556 @@
+/*
+ * Compatibility mode system call entry point for x86-64.
+ *
+ * Copyright 2000-2002 Andi Kleen, SuSE Labs.
+ */
+#include "calling.h"
+#include <asm/asm-offsets.h>
+#include <asm/current.h>
+#include <asm/errno.h>
+#include <asm/ia32_unistd.h>
+#include <asm/thread_info.h>
+#include <asm/segment.h>
+#include <asm/irqflags.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+#include <linux/linkage.h>
+#include <linux/err.h>
+
+/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
+#include <linux/elf-em.h>
+#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_LE 0x40000000
+
+#ifndef CONFIG_AUDITSYSCALL
+# define sysexit_audit ia32_ret_from_sys_call
+# define sysretl_audit ia32_ret_from_sys_call
+#endif
+
+ .section .entry.text, "ax"
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_usergs_sysret32)
+ swapgs
+ sysretl
+ENDPROC(native_usergs_sysret32)
+#endif
+
+/*
+ * 32-bit SYSENTER instruction entry.
+ *
+ * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs.
+ * IF and VM in rflags are cleared (IOW: interrupts are off).
+ * SYSENTER does not save anything on the stack,
+ * and does not save old rip (!!!) and rflags.
+ *
+ * Arguments:
+ * eax system call number
+ * ebx arg1
+ * ecx arg2
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * ebp user stack
+ * 0(%ebp) arg6
+ *
+ * This is purely a fast path. For anything complicated we use the int 0x80
+ * path below. We set up a complete hardware stack frame to share code
+ * with the int 0x80 path.
+ */
+ENTRY(entry_SYSENTER_compat)
+ /*
+ * Interrupts are off on entry.
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
+ SWAPGS_UNSAFE_STACK
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+ ENABLE_INTERRUPTS(CLBR_NONE)
+
+ /* Zero-extending 32-bit regs, do not remove */
+ movl %ebp, %ebp
+ movl %eax, %eax
+
+ movl ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d
+
+ /* Construct struct pt_regs on stack */
+ pushq $__USER32_DS /* pt_regs->ss */
+ pushq %rbp /* pt_regs->sp */
+ pushfq /* pt_regs->flags */
+ pushq $__USER32_CS /* pt_regs->cs */
+ pushq %r10 /* pt_regs->ip = thread_info->sysenter_return */
+ pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ pushq %rdx /* pt_regs->dx */
+ pushq %rcx /* pt_regs->cx */
+ pushq $-ENOSYS /* pt_regs->ax */
+ cld
+ sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */
+
+ /*
+ * no need to do an access_ok check here because rbp has been
+ * 32-bit zero extended
+ */
+ ASM_STAC
+1: movl (%rbp), %ebp
+ _ASM_EXTABLE(1b, ia32_badarg)
+ ASM_CLAC
+
+ /*
+ * Sysenter doesn't filter flags, so we need to clear NT
+ * ourselves. To save a few cycles, we can check whether
+ * NT was set instead of doing an unconditional popfq.
+ */
+ testl $X86_EFLAGS_NT, EFLAGS(%rsp)
+ jnz sysenter_fix_flags
+sysenter_flags_fixed:
+
+ orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz sysenter_tracesys
+
+sysenter_do_call:
+ /* 32-bit syscall -> 64-bit C ABI argument conversion */
+ movl %edi, %r8d /* arg5 */
+ movl %ebp, %r9d /* arg6 */
+ xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
+ movl %ebx, %edi /* arg1 */
+ movl %edx, %edx /* arg3 (zero extension) */
+sysenter_dispatch:
+ cmpq $(IA32_NR_syscalls-1), %rax
+ ja 1f
+ call *ia32_sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
+1:
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz sysexit_audit
+sysexit_from_sys_call:
+ /*
+ * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an
+ * NMI between STI and SYSEXIT has poorly specified behavior,
+ * and and NMI followed by an IRQ with usergs is fatal. So
+ * we just pretend we're using SYSEXIT but we really use
+ * SYSRETL instead.
+ *
+ * This code path is still called 'sysexit' because it pairs
+ * with 'sysenter' and it uses the SYSENTER calling convention.
+ */
+ andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ movl RIP(%rsp), %ecx /* User %eip */
+ RESTORE_RSI_RDI
+ xorl %edx, %edx /* Do not leak kernel information */
+ xorq %r8, %r8
+ xorq %r9, %r9
+ xorq %r10, %r10
+ movl EFLAGS(%rsp), %r11d /* User eflags */
+ TRACE_IRQS_ON
+
+ /*
+ * SYSRETL works even on Intel CPUs. Use it in preference to SYSEXIT,
+ * since it avoids a dicey window with interrupts enabled.
+ */
+ movl RSP(%rsp), %esp
+
+ /*
+ * USERGS_SYSRET32 does:
+ * gsbase = user's gs base
+ * eip = ecx
+ * rflags = r11
+ * cs = __USER32_CS
+ * ss = __USER_DS
+ *
+ * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does:
+ *
+ * pop %ebp
+ * pop %edx
+ * pop %ecx
+ *
+ * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to
+ * avoid info leaks. R11 ends up with VDSO32_SYSENTER_RETURN's
+ * address (already known to user code), and R12-R15 are
+ * callee-saved and therefore don't contain any interesting
+ * kernel data.
+ */
+ USERGS_SYSRET32
+
+#ifdef CONFIG_AUDITSYSCALL
+ .macro auditsys_entry_common
+ /*
+ * At this point, registers hold syscall args in the 32-bit syscall ABI:
+ * EAX is syscall number, the 6 args are in EBX,ECX,EDX,ESI,EDI,EBP.
+ *
+ * We want to pass them to __audit_syscall_entry(), which is a 64-bit
+ * C function with 5 parameters, so shuffle them to match what
+ * the function expects: RDI,RSI,RDX,RCX,R8.
+ */
+ movl %esi, %r8d /* arg5 (R8 ) <= 4th syscall arg (ESI) */
+ xchg %ecx, %edx /* arg4 (RCX) <= 3rd syscall arg (EDX) */
+ /* arg3 (RDX) <= 2nd syscall arg (ECX) */
+ movl %ebx, %esi /* arg2 (RSI) <= 1st syscall arg (EBX) */
+ movl %eax, %edi /* arg1 (RDI) <= syscall number (EAX) */
+ call __audit_syscall_entry
+
+ /*
+ * We are going to jump back to the syscall dispatch code.
+ * Prepare syscall args as required by the 64-bit C ABI.
+ * Registers clobbered by __audit_syscall_entry() are
+ * loaded from pt_regs on stack:
+ */
+ movl ORIG_RAX(%rsp), %eax /* syscall number */
+ movl %ebx, %edi /* arg1 */
+ movl RCX(%rsp), %esi /* arg2 */
+ movl RDX(%rsp), %edx /* arg3 */
+ movl RSI(%rsp), %ecx /* arg4 */
+ movl RDI(%rsp), %r8d /* arg5 */
+ movl %ebp, %r9d /* arg6 */
+ .endm
+
+ .macro auditsys_exit exit
+ testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz ia32_ret_from_sys_call
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ movl %eax, %esi /* second arg, syscall return value */
+ cmpl $-MAX_ERRNO, %eax /* is it an error ? */
+ jbe 1f
+ movslq %eax, %rsi /* if error sign extend to 64 bits */
+1: setbe %al /* 1 if error, 0 if not */
+ movzbl %al, %edi /* zero-extend that into %edi */
+ call __audit_syscall_exit
+ movq RAX(%rsp), %rax /* reload syscall return value */
+ movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ testl %edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jz \exit
+ xorl %eax, %eax /* Do not leak kernel information */
+ movq %rax, R11(%rsp)
+ movq %rax, R10(%rsp)
+ movq %rax, R9(%rsp)
+ movq %rax, R8(%rsp)
+ jmp int_with_check
+ .endm
+
+sysenter_auditsys:
+ auditsys_entry_common
+ jmp sysenter_dispatch
+
+sysexit_audit:
+ auditsys_exit sysexit_from_sys_call
+#endif
+
+sysenter_fix_flags:
+ pushq $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
+ popfq
+ jmp sysenter_flags_fixed
+
+sysenter_tracesys:
+#ifdef CONFIG_AUDITSYSCALL
+ testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jz sysenter_auditsys
+#endif
+ SAVE_EXTRA_REGS
+ xorl %eax, %eax /* Do not leak kernel information */
+ movq %rax, R11(%rsp)
+ movq %rax, R10(%rsp)
+ movq %rax, R9(%rsp)
+ movq %rax, R8(%rsp)
+ movq %rsp, %rdi /* &pt_regs -> arg1 */
+ call syscall_trace_enter
+
+ /* Reload arg registers from stack. (see sysenter_tracesys) */
+ movl RCX(%rsp), %ecx
+ movl RDX(%rsp), %edx
+ movl RSI(%rsp), %esi
+ movl RDI(%rsp), %edi
+ movl %eax, %eax /* zero extension */
+
+ RESTORE_EXTRA_REGS
+ jmp sysenter_do_call
+ENDPROC(entry_SYSENTER_compat)
+
+/*
+ * 32-bit SYSCALL instruction entry.
+ *
+ * 32-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
+ * then loads new ss, cs, and rip from previously programmed MSRs.
+ * rflags gets masked by a value from another MSR (so CLD and CLAC
+ * are not needed). SYSCALL does not save anything on the stack
+ * and does not change rsp.
+ *
+ * Note: rflags saving+masking-with-MSR happens only in Long mode
+ * (in legacy 32-bit mode, IF, RF and VM bits are cleared and that's it).
+ * Don't get confused: rflags saving+masking depends on Long Mode Active bit
+ * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
+ * or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
+ *
+ * Arguments:
+ * eax system call number
+ * ecx return address
+ * ebx arg1
+ * ebp arg2 (note: not saved in the stack frame, should not be touched)
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * esp user stack
+ * 0(%esp) arg6
+ *
+ * This is purely a fast path. For anything complicated we use the int 0x80
+ * path below. We set up a complete hardware stack frame to share code
+ * with the int 0x80 path.
+ */
+ENTRY(entry_SYSCALL_compat)
+ /*
+ * Interrupts are off on entry.
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
+ SWAPGS_UNSAFE_STACK
+ movl %esp, %r8d
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+ ENABLE_INTERRUPTS(CLBR_NONE)
+
+ /* Zero-extending 32-bit regs, do not remove */
+ movl %eax, %eax
+
+ /* Construct struct pt_regs on stack */
+ pushq $__USER32_DS /* pt_regs->ss */
+ pushq %r8 /* pt_regs->sp */
+ pushq %r11 /* pt_regs->flags */
+ pushq $__USER32_CS /* pt_regs->cs */
+ pushq %rcx /* pt_regs->ip */
+ pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ pushq %rdx /* pt_regs->dx */
+ pushq %rbp /* pt_regs->cx */
+ movl %ebp, %ecx
+ pushq $-ENOSYS /* pt_regs->ax */
+ sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */
+
+ /*
+ * No need to do an access_ok check here because r8 has been
+ * 32-bit zero extended:
+ */
+ ASM_STAC
+1: movl (%r8), %ebp
+ _ASM_EXTABLE(1b, ia32_badarg)
+ ASM_CLAC
+ orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz cstar_tracesys
+
+cstar_do_call:
+ /* 32-bit syscall -> 64-bit C ABI argument conversion */
+ movl %edi, %r8d /* arg5 */
+ movl %ebp, %r9d /* arg6 */
+ xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
+ movl %ebx, %edi /* arg1 */
+ movl %edx, %edx /* arg3 (zero extension) */
+
+cstar_dispatch:
+ cmpq $(IA32_NR_syscalls-1), %rax
+ ja 1f
+
+ call *ia32_sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
+1:
+ movl RCX(%rsp), %ebp
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz sysretl_audit
+
+sysretl_from_sys_call:
+ andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ RESTORE_RSI_RDI_RDX
+ movl RIP(%rsp), %ecx
+ movl EFLAGS(%rsp), %r11d
+ xorq %r10, %r10
+ xorq %r9, %r9
+ xorq %r8, %r8
+ TRACE_IRQS_ON
+ movl RSP(%rsp), %esp
+ /*
+ * 64-bit->32-bit SYSRET restores eip from ecx,
+ * eflags from r11 (but RF and VM bits are forced to 0),
+ * cs and ss are loaded from MSRs.
+ * (Note: 32-bit->32-bit SYSRET is different: since r11
+ * does not exist, it merely sets eflags.IF=1).
+ *
+ * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
+ * descriptor is not reinitialized. This means that we must
+ * avoid SYSRET with SS == NULL, which could happen if we schedule,
+ * exit the kernel, and re-enter using an interrupt vector. (All
+ * interrupt entries on x86_64 set SS to NULL.) We prevent that
+ * from happening by reloading SS in __switch_to.
+ */
+ USERGS_SYSRET32
+
+#ifdef CONFIG_AUDITSYSCALL
+cstar_auditsys:
+ auditsys_entry_common
+ jmp cstar_dispatch
+
+sysretl_audit:
+ auditsys_exit sysretl_from_sys_call
+#endif
+
+cstar_tracesys:
+#ifdef CONFIG_AUDITSYSCALL
+ testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jz cstar_auditsys
+#endif
+ SAVE_EXTRA_REGS
+ xorl %eax, %eax /* Do not leak kernel information */
+ movq %rax, R11(%rsp)
+ movq %rax, R10(%rsp)
+ movq %rax, R9(%rsp)
+ movq %rax, R8(%rsp)
+ movq %rsp, %rdi /* &pt_regs -> arg1 */
+ call syscall_trace_enter
+
+ /* Reload arg registers from stack. (see sysenter_tracesys) */
+ movl RCX(%rsp), %ecx
+ movl RDX(%rsp), %edx
+ movl RSI(%rsp), %esi
+ movl RDI(%rsp), %edi
+ movl %eax, %eax /* zero extension */
+
+ RESTORE_EXTRA_REGS
+ jmp cstar_do_call
+END(entry_SYSCALL_compat)
+
+ia32_badarg:
+ ASM_CLAC
+ movq $-EFAULT, RAX(%rsp)
+ia32_ret_from_sys_call:
+ xorl %eax, %eax /* Do not leak kernel information */
+ movq %rax, R11(%rsp)
+ movq %rax, R10(%rsp)
+ movq %rax, R9(%rsp)
+ movq %rax, R8(%rsp)
+ jmp int_ret_from_sys_call
+
+/*
+ * Emulated IA32 system calls via int 0x80.
+ *
+ * Arguments:
+ * eax system call number
+ * ebx arg1
+ * ecx arg2
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * ebp arg6 (note: not saved in the stack frame, should not be touched)
+ *
+ * Notes:
+ * Uses the same stack frame as the x86-64 version.
+ * All registers except eax must be saved (but ptrace may violate that).
+ * Arguments are zero extended. For system calls that want sign extension and
+ * take long arguments a wrapper is needed. Most calls can just be called
+ * directly.
+ * Assumes it is only called from user space and entered with interrupts off.
+ */
+
+ENTRY(entry_INT80_compat)
+ /*
+ * Interrupts are off on entry.
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
+ SWAPGS
+ ENABLE_INTERRUPTS(CLBR_NONE)
+
+ /* Zero-extending 32-bit regs, do not remove */
+ movl %eax, %eax
+
+ /* Construct struct pt_regs on stack (iret frame is already on stack) */
+ pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ pushq %rdx /* pt_regs->dx */
+ pushq %rcx /* pt_regs->cx */
+ pushq $-ENOSYS /* pt_regs->ax */
+ pushq $0 /* pt_regs->r8 */
+ pushq $0 /* pt_regs->r9 */
+ pushq $0 /* pt_regs->r10 */
+ pushq $0 /* pt_regs->r11 */
+ cld
+ sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */
+
+ orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz ia32_tracesys
+
+ia32_do_call:
+ /* 32-bit syscall -> 64-bit C ABI argument conversion */
+ movl %edi, %r8d /* arg5 */
+ movl %ebp, %r9d /* arg6 */
+ xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
+ movl %ebx, %edi /* arg1 */
+ movl %edx, %edx /* arg3 (zero extension) */
+ cmpq $(IA32_NR_syscalls-1), %rax
+ ja 1f
+
+ call *ia32_sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
+1:
+ jmp int_ret_from_sys_call
+
+ia32_tracesys:
+ SAVE_EXTRA_REGS
+ movq %rsp, %rdi /* &pt_regs -> arg1 */
+ call syscall_trace_enter
+ /*
+ * Reload arg registers from stack in case ptrace changed them.
+ * Don't reload %eax because syscall_trace_enter() returned
+ * the %rax value we should see. But do truncate it to 32 bits.
+ * If it's -1 to make us punt the syscall, then (u32)-1 is still
+ * an appropriately invalid value.
+ */
+ movl RCX(%rsp), %ecx
+ movl RDX(%rsp), %edx
+ movl RSI(%rsp), %esi
+ movl RDI(%rsp), %edi
+ movl %eax, %eax /* zero extension */
+ RESTORE_EXTRA_REGS
+ jmp ia32_do_call
+END(entry_INT80_compat)
+
+ .macro PTREGSCALL label, func
+ ALIGN
+GLOBAL(\label)
+ leaq \func(%rip), %rax
+ jmp ia32_ptregs_common
+ .endm
+
+ PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn
+ PTREGSCALL stub32_sigreturn, sys32_sigreturn
+ PTREGSCALL stub32_fork, sys_fork
+ PTREGSCALL stub32_vfork, sys_vfork
+
+ ALIGN
+GLOBAL(stub32_clone)
+ leaq sys_clone(%rip), %rax
+ /*
+ * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr).
+ * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val).
+ *
+ * The native 64-bit kernel's sys_clone() implements the latter,
+ * so we need to swap arguments here before calling it:
+ */
+ xchg %r8, %rcx
+ jmp ia32_ptregs_common
+
+ ALIGN
+ia32_ptregs_common:
+ SAVE_EXTRA_REGS 8
+ call *%rax
+ RESTORE_EXTRA_REGS 8
+ ret
+END(ia32_ptregs_common)
diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/entry/syscall_32.c
similarity index 79%
rename from arch/x86/kernel/syscall_32.c
rename to arch/x86/entry/syscall_32.c
index 3777189..8ea34f9 100644
--- a/arch/x86/kernel/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -10,7 +10,7 @@
#else
#define SYM(sym, compat) sym
#define ia32_sys_call_table sys_call_table
-#define __NR_ia32_syscall_max __NR_syscall_max
+#define __NR_syscall_compat_max __NR_syscall_max
#endif
#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void SYM(sym, compat)(void) ;
@@ -23,11 +23,11 @@
extern asmlinkage void sys_ni_syscall(void);
-__visible const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = {
+__visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = {
/*
* Smells like a compiler bug -- it doesn't work
* when the & below is removed.
*/
- [0 ... __NR_ia32_syscall_max] = &sys_ni_syscall,
+ [0 ... __NR_syscall_compat_max] = &sys_ni_syscall,
#include <asm/syscalls_32.h>
};
diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/entry/syscall_64.c
similarity index 100%
rename from arch/x86/kernel/syscall_64.c
rename to arch/x86/entry/syscall_64.c
diff --git a/arch/x86/syscalls/Makefile b/arch/x86/entry/syscalls/Makefile
similarity index 95%
rename from arch/x86/syscalls/Makefile
rename to arch/x86/entry/syscalls/Makefile
index a55abb9..57aa59f 100644
--- a/arch/x86/syscalls/Makefile
+++ b/arch/x86/entry/syscalls/Makefile
@@ -1,5 +1,5 @@
-out := $(obj)/../include/generated/asm
-uapi := $(obj)/../include/generated/uapi/asm
+out := $(obj)/../../include/generated/asm
+uapi := $(obj)/../../include/generated/uapi/asm
# Create output directory if not already present
_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
similarity index 100%
rename from arch/x86/syscalls/syscall_32.tbl
rename to arch/x86/entry/syscalls/syscall_32.tbl
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
similarity index 100%
rename from arch/x86/syscalls/syscall_64.tbl
rename to arch/x86/entry/syscalls/syscall_64.tbl
diff --git a/arch/x86/syscalls/syscallhdr.sh b/arch/x86/entry/syscalls/syscallhdr.sh
similarity index 100%
rename from arch/x86/syscalls/syscallhdr.sh
rename to arch/x86/entry/syscalls/syscallhdr.sh
diff --git a/arch/x86/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh
similarity index 100%
rename from arch/x86/syscalls/syscalltbl.sh
rename to arch/x86/entry/syscalls/syscalltbl.sh
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/entry/thunk_32.S
similarity index 83%
rename from arch/x86/lib/thunk_32.S
rename to arch/x86/entry/thunk_32.S
index 5eb7150..e9acf5f 100644
--- a/arch/x86/lib/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -6,16 +6,14 @@
*/
#include <linux/linkage.h>
#include <asm/asm.h>
- #include <asm/dwarf2.h>
/* put return address in eax (arg1) */
.macro THUNK name, func, put_ret_addr_in_eax=0
.globl \name
\name:
- CFI_STARTPROC
- pushl_cfi_reg eax
- pushl_cfi_reg ecx
- pushl_cfi_reg edx
+ pushl %eax
+ pushl %ecx
+ pushl %edx
.if \put_ret_addr_in_eax
/* Place EIP in the arg1 */
@@ -23,11 +21,10 @@
.endif
call \func
- popl_cfi_reg edx
- popl_cfi_reg ecx
- popl_cfi_reg eax
+ popl %edx
+ popl %ecx
+ popl %eax
ret
- CFI_ENDPROC
_ASM_NOKPROBE(\name)
.endm
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/entry/thunk_64.S
similarity index 72%
rename from arch/x86/lib/thunk_64.S
rename to arch/x86/entry/thunk_64.S
index f89ba4e9..3e95681 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -6,35 +6,32 @@
* Subject to the GNU public license, v.2. No warranty of any kind.
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
+#include "calling.h"
#include <asm/asm.h>
/* rdi: arg1 ... normal C conventions. rax is saved/restored. */
.macro THUNK name, func, put_ret_addr_in_rdi=0
.globl \name
\name:
- CFI_STARTPROC
/* this one pushes 9 elems, the next one would be %rIP */
- pushq_cfi_reg rdi
- pushq_cfi_reg rsi
- pushq_cfi_reg rdx
- pushq_cfi_reg rcx
- pushq_cfi_reg rax
- pushq_cfi_reg r8
- pushq_cfi_reg r9
- pushq_cfi_reg r10
- pushq_cfi_reg r11
+ pushq %rdi
+ pushq %rsi
+ pushq %rdx
+ pushq %rcx
+ pushq %rax
+ pushq %r8
+ pushq %r9
+ pushq %r10
+ pushq %r11
.if \put_ret_addr_in_rdi
/* 9*8(%rsp) is return addr on stack */
- movq_cfi_restore 9*8, rdi
+ movq 9*8(%rsp), %rdi
.endif
call \func
jmp restore
- CFI_ENDPROC
_ASM_NOKPROBE(\name)
.endm
@@ -57,19 +54,16 @@
#if defined(CONFIG_TRACE_IRQFLAGS) \
|| defined(CONFIG_DEBUG_LOCK_ALLOC) \
|| defined(CONFIG_PREEMPT)
- CFI_STARTPROC
- CFI_ADJUST_CFA_OFFSET 9*8
restore:
- popq_cfi_reg r11
- popq_cfi_reg r10
- popq_cfi_reg r9
- popq_cfi_reg r8
- popq_cfi_reg rax
- popq_cfi_reg rcx
- popq_cfi_reg rdx
- popq_cfi_reg rsi
- popq_cfi_reg rdi
+ popq %r11
+ popq %r10
+ popq %r9
+ popq %r8
+ popq %rax
+ popq %rcx
+ popq %rdx
+ popq %rsi
+ popq %rdi
ret
- CFI_ENDPROC
_ASM_NOKPROBE(restore)
#endif
diff --git a/arch/x86/vdso/.gitignore b/arch/x86/entry/vdso/.gitignore
similarity index 100%
rename from arch/x86/vdso/.gitignore
rename to arch/x86/entry/vdso/.gitignore
diff --git a/arch/x86/vdso/Makefile b/arch/x86/entry/vdso/Makefile
similarity index 100%
rename from arch/x86/vdso/Makefile
rename to arch/x86/entry/vdso/Makefile
diff --git a/arch/x86/vdso/checkundef.sh b/arch/x86/entry/vdso/checkundef.sh
similarity index 100%
rename from arch/x86/vdso/checkundef.sh
rename to arch/x86/entry/vdso/checkundef.sh
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
similarity index 100%
rename from arch/x86/vdso/vclock_gettime.c
rename to arch/x86/entry/vdso/vclock_gettime.c
diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
similarity index 100%
rename from arch/x86/vdso/vdso-layout.lds.S
rename to arch/x86/entry/vdso/vdso-layout.lds.S
diff --git a/arch/x86/vdso/vdso-note.S b/arch/x86/entry/vdso/vdso-note.S
similarity index 100%
rename from arch/x86/vdso/vdso-note.S
rename to arch/x86/entry/vdso/vdso-note.S
diff --git a/arch/x86/vdso/vdso.lds.S b/arch/x86/entry/vdso/vdso.lds.S
similarity index 100%
rename from arch/x86/vdso/vdso.lds.S
rename to arch/x86/entry/vdso/vdso.lds.S
diff --git a/arch/x86/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
similarity index 100%
rename from arch/x86/vdso/vdso2c.c
rename to arch/x86/entry/vdso/vdso2c.c
diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
similarity index 100%
rename from arch/x86/vdso/vdso2c.h
rename to arch/x86/entry/vdso/vdso2c.h
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
similarity index 100%
rename from arch/x86/vdso/vdso32-setup.c
rename to arch/x86/entry/vdso/vdso32-setup.c
diff --git a/arch/x86/vdso/vdso32/.gitignore b/arch/x86/entry/vdso/vdso32/.gitignore
similarity index 100%
rename from arch/x86/vdso/vdso32/.gitignore
rename to arch/x86/entry/vdso/vdso32/.gitignore
diff --git a/arch/x86/vdso/vdso32/int80.S b/arch/x86/entry/vdso/vdso32/int80.S
similarity index 100%
rename from arch/x86/vdso/vdso32/int80.S
rename to arch/x86/entry/vdso/vdso32/int80.S
diff --git a/arch/x86/vdso/vdso32/note.S b/arch/x86/entry/vdso/vdso32/note.S
similarity index 100%
rename from arch/x86/vdso/vdso32/note.S
rename to arch/x86/entry/vdso/vdso32/note.S
diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/entry/vdso/vdso32/sigreturn.S
similarity index 100%
rename from arch/x86/vdso/vdso32/sigreturn.S
rename to arch/x86/entry/vdso/vdso32/sigreturn.S
diff --git a/arch/x86/vdso/vdso32/syscall.S b/arch/x86/entry/vdso/vdso32/syscall.S
similarity index 100%
rename from arch/x86/vdso/vdso32/syscall.S
rename to arch/x86/entry/vdso/vdso32/syscall.S
diff --git a/arch/x86/vdso/vdso32/sysenter.S b/arch/x86/entry/vdso/vdso32/sysenter.S
similarity index 100%
rename from arch/x86/vdso/vdso32/sysenter.S
rename to arch/x86/entry/vdso/vdso32/sysenter.S
diff --git a/arch/x86/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
similarity index 100%
rename from arch/x86/vdso/vdso32/vclock_gettime.c
rename to arch/x86/entry/vdso/vdso32/vclock_gettime.c
diff --git a/arch/x86/vdso/vdso32/vdso-fakesections.c b/arch/x86/entry/vdso/vdso32/vdso-fakesections.c
similarity index 100%
rename from arch/x86/vdso/vdso32/vdso-fakesections.c
rename to arch/x86/entry/vdso/vdso32/vdso-fakesections.c
diff --git a/arch/x86/vdso/vdso32/vdso32.lds.S b/arch/x86/entry/vdso/vdso32/vdso32.lds.S
similarity index 100%
rename from arch/x86/vdso/vdso32/vdso32.lds.S
rename to arch/x86/entry/vdso/vdso32/vdso32.lds.S
diff --git a/arch/x86/vdso/vdsox32.lds.S b/arch/x86/entry/vdso/vdsox32.lds.S
similarity index 100%
rename from arch/x86/vdso/vdsox32.lds.S
rename to arch/x86/entry/vdso/vdsox32.lds.S
diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/entry/vdso/vgetcpu.c
similarity index 100%
rename from arch/x86/vdso/vgetcpu.c
rename to arch/x86/entry/vdso/vgetcpu.c
diff --git a/arch/x86/vdso/vma.c b/arch/x86/entry/vdso/vma.c
similarity index 100%
rename from arch/x86/vdso/vma.c
rename to arch/x86/entry/vdso/vma.c
diff --git a/arch/x86/entry/vsyscall/Makefile b/arch/x86/entry/vsyscall/Makefile
new file mode 100644
index 0000000..a9f4856
--- /dev/null
+++ b/arch/x86/entry/vsyscall/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the x86 low level vsyscall code
+#
+obj-y := vsyscall_gtod.o
+
+obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o
+
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
similarity index 100%
rename from arch/x86/kernel/vsyscall_64.c
rename to arch/x86/entry/vsyscall/vsyscall_64.c
diff --git a/arch/x86/kernel/vsyscall_emu_64.S b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
similarity index 100%
rename from arch/x86/kernel/vsyscall_emu_64.S
rename to arch/x86/entry/vsyscall/vsyscall_emu_64.S
diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c
similarity index 100%
rename from arch/x86/kernel/vsyscall_gtod.c
rename to arch/x86/entry/vsyscall/vsyscall_gtod.c
diff --git a/arch/x86/kernel/vsyscall_trace.h b/arch/x86/entry/vsyscall/vsyscall_trace.h
similarity index 89%
rename from arch/x86/kernel/vsyscall_trace.h
rename to arch/x86/entry/vsyscall/vsyscall_trace.h
index a8b2ede..9dd7359 100644
--- a/arch/x86/kernel/vsyscall_trace.h
+++ b/arch/x86/entry/vsyscall/vsyscall_trace.h
@@ -24,6 +24,6 @@
#endif
#undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH ../../arch/x86/kernel
+#define TRACE_INCLUDE_PATH ../../arch/x86/entry/vsyscall/
#define TRACE_INCLUDE_FILE vsyscall_trace
#include <trace/define_trace.h>
diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile
index bb635c6..cd4339b 100644
--- a/arch/x86/ia32/Makefile
+++ b/arch/x86/ia32/Makefile
@@ -2,7 +2,7 @@
# Makefile for the ia32 kernel emulation subsystem.
#
-obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o
+obj-$(CONFIG_IA32_EMULATION) := sys_ia32.o ia32_signal.o
obj-$(CONFIG_IA32_AOUT) += ia32_aout.o
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
deleted file mode 100644
index 72bf268..0000000
--- a/arch/x86/ia32/ia32entry.S
+++ /dev/null
@@ -1,611 +0,0 @@
-/*
- * Compatibility mode system call entry point for x86-64.
- *
- * Copyright 2000-2002 Andi Kleen, SuSE Labs.
- */
-
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
-#include <asm/asm-offsets.h>
-#include <asm/current.h>
-#include <asm/errno.h>
-#include <asm/ia32_unistd.h>
-#include <asm/thread_info.h>
-#include <asm/segment.h>
-#include <asm/irqflags.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-#include <linux/linkage.h>
-#include <linux/err.h>
-
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_LE 0x40000000
-
-#ifndef CONFIG_AUDITSYSCALL
-#define sysexit_audit ia32_ret_from_sys_call
-#define sysretl_audit ia32_ret_from_sys_call
-#endif
-
- .section .entry.text, "ax"
-
- /* clobbers %rax */
- .macro CLEAR_RREGS _r9=rax
- xorl %eax,%eax
- movq %rax,R11(%rsp)
- movq %rax,R10(%rsp)
- movq %\_r9,R9(%rsp)
- movq %rax,R8(%rsp)
- .endm
-
- /*
- * Reload arg registers from stack in case ptrace changed them.
- * We don't reload %eax because syscall_trace_enter() returned
- * the %rax value we should see. Instead, we just truncate that
- * value to 32 bits again as we did on entry from user mode.
- * If it's a new value set by user_regset during entry tracing,
- * this matches the normal truncation of the user-mode value.
- * If it's -1 to make us punt the syscall, then (u32)-1 is still
- * an appropriately invalid value.
- */
- .macro LOAD_ARGS32 _r9=0
- .if \_r9
- movl R9(%rsp),%r9d
- .endif
- movl RCX(%rsp),%ecx
- movl RDX(%rsp),%edx
- movl RSI(%rsp),%esi
- movl RDI(%rsp),%edi
- movl %eax,%eax /* zero extension */
- .endm
-
- .macro CFI_STARTPROC32 simple
- CFI_STARTPROC \simple
- CFI_UNDEFINED r8
- CFI_UNDEFINED r9
- CFI_UNDEFINED r10
- CFI_UNDEFINED r11
- CFI_UNDEFINED r12
- CFI_UNDEFINED r13
- CFI_UNDEFINED r14
- CFI_UNDEFINED r15
- .endm
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_usergs_sysret32)
- swapgs
- sysretl
-ENDPROC(native_usergs_sysret32)
-
-ENTRY(native_irq_enable_sysexit)
- swapgs
- sti
- sysexit
-ENDPROC(native_irq_enable_sysexit)
-#endif
-
-/*
- * 32bit SYSENTER instruction entry.
- *
- * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs.
- * IF and VM in rflags are cleared (IOW: interrupts are off).
- * SYSENTER does not save anything on the stack,
- * and does not save old rip (!!!) and rflags.
- *
- * Arguments:
- * eax system call number
- * ebx arg1
- * ecx arg2
- * edx arg3
- * esi arg4
- * edi arg5
- * ebp user stack
- * 0(%ebp) arg6
- *
- * This is purely a fast path. For anything complicated we use the int 0x80
- * path below. We set up a complete hardware stack frame to share code
- * with the int 0x80 path.
- */
-ENTRY(ia32_sysenter_target)
- CFI_STARTPROC32 simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,0
- CFI_REGISTER rsp,rbp
-
- /*
- * Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
- SWAPGS_UNSAFE_STACK
- movq PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp
- ENABLE_INTERRUPTS(CLBR_NONE)
-
- /* Zero-extending 32-bit regs, do not remove */
- movl %ebp, %ebp
- movl %eax, %eax
-
- movl ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d
- CFI_REGISTER rip,r10
-
- /* Construct struct pt_regs on stack */
- pushq_cfi $__USER32_DS /* pt_regs->ss */
- pushq_cfi %rbp /* pt_regs->sp */
- CFI_REL_OFFSET rsp,0
- pushfq_cfi /* pt_regs->flags */
- pushq_cfi $__USER32_CS /* pt_regs->cs */
- pushq_cfi %r10 /* pt_regs->ip = thread_info->sysenter_return */
- CFI_REL_OFFSET rip,0
- pushq_cfi_reg rax /* pt_regs->orig_ax */
- pushq_cfi_reg rdi /* pt_regs->di */
- pushq_cfi_reg rsi /* pt_regs->si */
- pushq_cfi_reg rdx /* pt_regs->dx */
- pushq_cfi_reg rcx /* pt_regs->cx */
- pushq_cfi_reg rax /* pt_regs->ax */
- cld
- sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
- CFI_ADJUST_CFA_OFFSET 10*8
-
- /*
- * no need to do an access_ok check here because rbp has been
- * 32bit zero extended
- */
- ASM_STAC
-1: movl (%rbp),%ebp
- _ASM_EXTABLE(1b,ia32_badarg)
- ASM_CLAC
-
- /*
- * Sysenter doesn't filter flags, so we need to clear NT
- * ourselves. To save a few cycles, we can check whether
- * NT was set instead of doing an unconditional popfq.
- */
- testl $X86_EFLAGS_NT,EFLAGS(%rsp)
- jnz sysenter_fix_flags
-sysenter_flags_fixed:
-
- orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- CFI_REMEMBER_STATE
- jnz sysenter_tracesys
- cmpq $(IA32_NR_syscalls-1),%rax
- ja ia32_badsys
-sysenter_do_call:
- /* 32bit syscall -> 64bit C ABI argument conversion */
- movl %edi,%r8d /* arg5 */
- movl %ebp,%r9d /* arg6 */
- xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */
- movl %ebx,%edi /* arg1 */
- movl %edx,%edx /* arg3 (zero extension) */
-sysenter_dispatch:
- call *ia32_sys_call_table(,%rax,8)
- movq %rax,RAX(%rsp)
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz sysexit_audit
-sysexit_from_sys_call:
- /*
- * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an
- * NMI between STI and SYSEXIT has poorly specified behavior,
- * and and NMI followed by an IRQ with usergs is fatal. So
- * we just pretend we're using SYSEXIT but we really use
- * SYSRETL instead.
- *
- * This code path is still called 'sysexit' because it pairs
- * with 'sysenter' and it uses the SYSENTER calling convention.
- */
- andl $~TS_COMPAT,ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- movl RIP(%rsp),%ecx /* User %eip */
- CFI_REGISTER rip,rcx
- RESTORE_RSI_RDI
- xorl %edx,%edx /* avoid info leaks */
- xorq %r8,%r8
- xorq %r9,%r9
- xorq %r10,%r10
- movl EFLAGS(%rsp),%r11d /* User eflags */
- /*CFI_RESTORE rflags*/
- TRACE_IRQS_ON
-
- /*
- * SYSRETL works even on Intel CPUs. Use it in preference to SYSEXIT,
- * since it avoids a dicey window with interrupts enabled.
- */
- movl RSP(%rsp),%esp
-
- /*
- * USERGS_SYSRET32 does:
- * gsbase = user's gs base
- * eip = ecx
- * rflags = r11
- * cs = __USER32_CS
- * ss = __USER_DS
- *
- * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does:
- *
- * pop %ebp
- * pop %edx
- * pop %ecx
- *
- * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to
- * avoid info leaks. R11 ends up with VDSO32_SYSENTER_RETURN's
- * address (already known to user code), and R12-R15 are
- * callee-saved and therefore don't contain any interesting
- * kernel data.
- */
- USERGS_SYSRET32
-
- CFI_RESTORE_STATE
-
-#ifdef CONFIG_AUDITSYSCALL
- .macro auditsys_entry_common
- movl %esi,%r8d /* 5th arg: 4th syscall arg */
- movl %ecx,%r9d /*swap with edx*/
- movl %edx,%ecx /* 4th arg: 3rd syscall arg */
- movl %r9d,%edx /* 3rd arg: 2nd syscall arg */
- movl %ebx,%esi /* 2nd arg: 1st syscall arg */
- movl %eax,%edi /* 1st arg: syscall number */
- call __audit_syscall_entry
- movl RAX(%rsp),%eax /* reload syscall number */
- cmpq $(IA32_NR_syscalls-1),%rax
- ja ia32_badsys
- movl %ebx,%edi /* reload 1st syscall arg */
- movl RCX(%rsp),%esi /* reload 2nd syscall arg */
- movl RDX(%rsp),%edx /* reload 3rd syscall arg */
- movl RSI(%rsp),%ecx /* reload 4th syscall arg */
- movl RDI(%rsp),%r8d /* reload 5th syscall arg */
- .endm
-
- .macro auditsys_exit exit
- testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz ia32_ret_from_sys_call
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- movl %eax,%esi /* second arg, syscall return value */
- cmpl $-MAX_ERRNO,%eax /* is it an error ? */
- jbe 1f
- movslq %eax, %rsi /* if error sign extend to 64 bits */
-1: setbe %al /* 1 if error, 0 if not */
- movzbl %al,%edi /* zero-extend that into %edi */
- call __audit_syscall_exit
- movq RAX(%rsp),%rax /* reload syscall return value */
- movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- testl %edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jz \exit
- CLEAR_RREGS
- jmp int_with_check
- .endm
-
-sysenter_auditsys:
- auditsys_entry_common
- movl %ebp,%r9d /* reload 6th syscall arg */
- jmp sysenter_dispatch
-
-sysexit_audit:
- auditsys_exit sysexit_from_sys_call
-#endif
-
-sysenter_fix_flags:
- pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
- popfq_cfi
- jmp sysenter_flags_fixed
-
-sysenter_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jz sysenter_auditsys
-#endif
- SAVE_EXTRA_REGS
- CLEAR_RREGS
- movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */
- movq %rsp,%rdi /* &pt_regs -> arg1 */
- call syscall_trace_enter
- LOAD_ARGS32 /* reload args from stack in case ptrace changed it */
- RESTORE_EXTRA_REGS
- cmpq $(IA32_NR_syscalls-1),%rax
- ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
- jmp sysenter_do_call
- CFI_ENDPROC
-ENDPROC(ia32_sysenter_target)
-
-/*
- * 32bit SYSCALL instruction entry.
- *
- * 32bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
- * then loads new ss, cs, and rip from previously programmed MSRs.
- * rflags gets masked by a value from another MSR (so CLD and CLAC
- * are not needed). SYSCALL does not save anything on the stack
- * and does not change rsp.
- *
- * Note: rflags saving+masking-with-MSR happens only in Long mode
- * (in legacy 32bit mode, IF, RF and VM bits are cleared and that's it).
- * Don't get confused: rflags saving+masking depends on Long Mode Active bit
- * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
- * or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
- *
- * Arguments:
- * eax system call number
- * ecx return address
- * ebx arg1
- * ebp arg2 (note: not saved in the stack frame, should not be touched)
- * edx arg3
- * esi arg4
- * edi arg5
- * esp user stack
- * 0(%esp) arg6
- *
- * This is purely a fast path. For anything complicated we use the int 0x80
- * path below. We set up a complete hardware stack frame to share code
- * with the int 0x80 path.
- */
-ENTRY(ia32_cstar_target)
- CFI_STARTPROC32 simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,0
- CFI_REGISTER rip,rcx
- /*CFI_REGISTER rflags,r11*/
-
- /*
- * Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
- SWAPGS_UNSAFE_STACK
- movl %esp,%r8d
- CFI_REGISTER rsp,r8
- movq PER_CPU_VAR(kernel_stack),%rsp
- ENABLE_INTERRUPTS(CLBR_NONE)
-
- /* Zero-extending 32-bit regs, do not remove */
- movl %eax,%eax
-
- /* Construct struct pt_regs on stack */
- pushq_cfi $__USER32_DS /* pt_regs->ss */
- pushq_cfi %r8 /* pt_regs->sp */
- CFI_REL_OFFSET rsp,0
- pushq_cfi %r11 /* pt_regs->flags */
- pushq_cfi $__USER32_CS /* pt_regs->cs */
- pushq_cfi %rcx /* pt_regs->ip */
- CFI_REL_OFFSET rip,0
- pushq_cfi_reg rax /* pt_regs->orig_ax */
- pushq_cfi_reg rdi /* pt_regs->di */
- pushq_cfi_reg rsi /* pt_regs->si */
- pushq_cfi_reg rdx /* pt_regs->dx */
- pushq_cfi_reg rbp /* pt_regs->cx */
- movl %ebp,%ecx
- pushq_cfi_reg rax /* pt_regs->ax */
- sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
- CFI_ADJUST_CFA_OFFSET 10*8
-
- /*
- * no need to do an access_ok check here because r8 has been
- * 32bit zero extended
- */
- ASM_STAC
-1: movl (%r8),%r9d
- _ASM_EXTABLE(1b,ia32_badarg)
- ASM_CLAC
- orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- CFI_REMEMBER_STATE
- jnz cstar_tracesys
- cmpq $IA32_NR_syscalls-1,%rax
- ja ia32_badsys
-cstar_do_call:
- /* 32bit syscall -> 64bit C ABI argument conversion */
- movl %edi,%r8d /* arg5 */
- /* r9 already loaded */ /* arg6 */
- xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */
- movl %ebx,%edi /* arg1 */
- movl %edx,%edx /* arg3 (zero extension) */
-cstar_dispatch:
- call *ia32_sys_call_table(,%rax,8)
- movq %rax,RAX(%rsp)
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz sysretl_audit
-sysretl_from_sys_call:
- andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- RESTORE_RSI_RDI_RDX
- movl RIP(%rsp),%ecx
- CFI_REGISTER rip,rcx
- movl EFLAGS(%rsp),%r11d
- /*CFI_REGISTER rflags,r11*/
- xorq %r10,%r10
- xorq %r9,%r9
- xorq %r8,%r8
- TRACE_IRQS_ON
- movl RSP(%rsp),%esp
- CFI_RESTORE rsp
- /*
- * 64bit->32bit SYSRET restores eip from ecx,
- * eflags from r11 (but RF and VM bits are forced to 0),
- * cs and ss are loaded from MSRs.
- * (Note: 32bit->32bit SYSRET is different: since r11
- * does not exist, it merely sets eflags.IF=1).
- *
- * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
- * descriptor is not reinitialized. This means that we must
- * avoid SYSRET with SS == NULL, which could happen if we schedule,
- * exit the kernel, and re-enter using an interrupt vector. (All
- * interrupt entries on x86_64 set SS to NULL.) We prevent that
- * from happening by reloading SS in __switch_to.
- */
- USERGS_SYSRET32
-
-#ifdef CONFIG_AUDITSYSCALL
-cstar_auditsys:
- CFI_RESTORE_STATE
- movl %r9d,R9(%rsp) /* register to be clobbered by call */
- auditsys_entry_common
- movl R9(%rsp),%r9d /* reload 6th syscall arg */
- jmp cstar_dispatch
-
-sysretl_audit:
- auditsys_exit sysretl_from_sys_call
-#endif
-
-cstar_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jz cstar_auditsys
-#endif
- xchgl %r9d,%ebp
- SAVE_EXTRA_REGS
- CLEAR_RREGS r9
- movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
- movq %rsp,%rdi /* &pt_regs -> arg1 */
- call syscall_trace_enter
- LOAD_ARGS32 1 /* reload args from stack in case ptrace changed it */
- RESTORE_EXTRA_REGS
- xchgl %ebp,%r9d
- cmpq $(IA32_NR_syscalls-1),%rax
- ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */
- jmp cstar_do_call
-END(ia32_cstar_target)
-
-ia32_badarg:
- ASM_CLAC
- movq $-EFAULT,%rax
- jmp ia32_sysret
- CFI_ENDPROC
-
-/*
- * Emulated IA32 system calls via int 0x80.
- *
- * Arguments:
- * eax system call number
- * ebx arg1
- * ecx arg2
- * edx arg3
- * esi arg4
- * edi arg5
- * ebp arg6 (note: not saved in the stack frame, should not be touched)
- *
- * Notes:
- * Uses the same stack frame as the x86-64 version.
- * All registers except eax must be saved (but ptrace may violate that).
- * Arguments are zero extended. For system calls that want sign extension and
- * take long arguments a wrapper is needed. Most calls can just be called
- * directly.
- * Assumes it is only called from user space and entered with interrupts off.
- */
-
-ENTRY(ia32_syscall)
- CFI_STARTPROC32 simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,5*8
- /*CFI_REL_OFFSET ss,4*8 */
- CFI_REL_OFFSET rsp,3*8
- /*CFI_REL_OFFSET rflags,2*8 */
- /*CFI_REL_OFFSET cs,1*8 */
- CFI_REL_OFFSET rip,0*8
-
- /*
- * Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
- PARAVIRT_ADJUST_EXCEPTION_FRAME
- SWAPGS
- ENABLE_INTERRUPTS(CLBR_NONE)
-
- /* Zero-extending 32-bit regs, do not remove */
- movl %eax,%eax
-
- /* Construct struct pt_regs on stack (iret frame is already on stack) */
- pushq_cfi_reg rax /* pt_regs->orig_ax */
- pushq_cfi_reg rdi /* pt_regs->di */
- pushq_cfi_reg rsi /* pt_regs->si */
- pushq_cfi_reg rdx /* pt_regs->dx */
- pushq_cfi_reg rcx /* pt_regs->cx */
- pushq_cfi_reg rax /* pt_regs->ax */
- cld
- sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
- CFI_ADJUST_CFA_OFFSET 10*8
-
- orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz ia32_tracesys
- cmpq $(IA32_NR_syscalls-1),%rax
- ja ia32_badsys
-ia32_do_call:
- /* 32bit syscall -> 64bit C ABI argument conversion */
- movl %edi,%r8d /* arg5 */
- movl %ebp,%r9d /* arg6 */
- xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */
- movl %ebx,%edi /* arg1 */
- movl %edx,%edx /* arg3 (zero extension) */
- call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
-ia32_sysret:
- movq %rax,RAX(%rsp)
-ia32_ret_from_sys_call:
- CLEAR_RREGS
- jmp int_ret_from_sys_call
-
-ia32_tracesys:
- SAVE_EXTRA_REGS
- CLEAR_RREGS
- movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
- movq %rsp,%rdi /* &pt_regs -> arg1 */
- call syscall_trace_enter
- LOAD_ARGS32 /* reload args from stack in case ptrace changed it */
- RESTORE_EXTRA_REGS
- cmpq $(IA32_NR_syscalls-1),%rax
- ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */
- jmp ia32_do_call
-END(ia32_syscall)
-
-ia32_badsys:
- movq $0,ORIG_RAX(%rsp)
- movq $-ENOSYS,%rax
- jmp ia32_sysret
-
- CFI_ENDPROC
-
- .macro PTREGSCALL label, func
- ALIGN
-GLOBAL(\label)
- leaq \func(%rip),%rax
- jmp ia32_ptregs_common
- .endm
-
- CFI_STARTPROC32
-
- PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn
- PTREGSCALL stub32_sigreturn, sys32_sigreturn
- PTREGSCALL stub32_fork, sys_fork
- PTREGSCALL stub32_vfork, sys_vfork
-
- ALIGN
-GLOBAL(stub32_clone)
- leaq sys_clone(%rip),%rax
- mov %r8, %rcx
- jmp ia32_ptregs_common
-
- ALIGN
-ia32_ptregs_common:
- CFI_ENDPROC
- CFI_STARTPROC32 simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,SIZEOF_PTREGS
- CFI_REL_OFFSET rax,RAX
- CFI_REL_OFFSET rcx,RCX
- CFI_REL_OFFSET rdx,RDX
- CFI_REL_OFFSET rsi,RSI
- CFI_REL_OFFSET rdi,RDI
- CFI_REL_OFFSET rip,RIP
-/* CFI_REL_OFFSET cs,CS*/
-/* CFI_REL_OFFSET rflags,EFLAGS*/
- CFI_REL_OFFSET rsp,RSP
-/* CFI_REL_OFFSET ss,SS*/
- SAVE_EXTRA_REGS 8
- call *%rax
- RESTORE_EXTRA_REGS 8
- ret
- CFI_ENDPROC
-END(ia32_ptregs_common)
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index bdf02ee..e7636ba 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -18,6 +18,12 @@
.endm
#endif
+/*
+ * Issue one struct alt_instr descriptor entry (need to put it into
+ * the section .altinstructions, see below). This entry contains
+ * enough information for the alternatives patching code to patch an
+ * instruction. See apply_alternatives().
+ */
.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
.long \orig - .
.long \alt - .
@@ -27,6 +33,12 @@
.byte \pad_len
.endm
+/*
+ * Define an alternative between two instructions. If @feature is
+ * present, early code in apply_alternatives() replaces @oldinstr with
+ * @newinstr. ".skip" directive takes care of proper instruction padding
+ * in case @newinstr is longer than @oldinstr.
+ */
.macro ALTERNATIVE oldinstr, newinstr, feature
140:
\oldinstr
@@ -55,6 +67,12 @@
*/
#define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
+
+/*
+ * Same as ALTERNATIVE macro above but for two alternatives. If CPU
+ * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
+ * @feature2, it replaces @oldinstr with @feature2.
+ */
.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
140:
\oldinstr
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 976b86a..c839363 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -644,6 +644,12 @@
entering_irq();
}
+static inline void ipi_entering_ack_irq(void)
+{
+ ack_APIC_irq();
+ irq_enter();
+}
+
static inline void exiting_irq(void)
{
irq_exit();
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 7730c1c..189679a 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -63,6 +63,31 @@
_ASM_ALIGN ; \
_ASM_PTR (entry); \
.popsection
+
+.macro ALIGN_DESTINATION
+ /* check for bad alignment of destination */
+ movl %edi,%ecx
+ andl $7,%ecx
+ jz 102f /* already aligned */
+ subl $8,%ecx
+ negl %ecx
+ subl %ecx,%edx
+100: movb (%rsi),%al
+101: movb %al,(%rdi)
+ incq %rsi
+ incq %rdi
+ decl %ecx
+ jnz 100b
+102:
+ .section .fixup,"ax"
+103: addl %ecx,%edx /* ecx is zerorest also */
+ jmp copy_user_handle_tail
+ .previous
+
+ _ASM_EXTABLE(100b,103b)
+ _ASM_EXTABLE(101b,103b)
+ .endm
+
#else
# define _ASM_EXTABLE(from,to) \
" .pushsection \"__ex_table\",\"a\"\n" \
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 5e5cd12..e916895 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -22,7 +22,7 @@
*
* Atomically reads the value of @v.
*/
-static inline int atomic_read(const atomic_t *v)
+static __always_inline int atomic_read(const atomic_t *v)
{
return ACCESS_ONCE((v)->counter);
}
@@ -34,7 +34,7 @@
*
* Atomically sets the value of @v to @i.
*/
-static inline void atomic_set(atomic_t *v, int i)
+static __always_inline void atomic_set(atomic_t *v, int i)
{
v->counter = i;
}
@@ -46,7 +46,7 @@
*
* Atomically adds @i to @v.
*/
-static inline void atomic_add(int i, atomic_t *v)
+static __always_inline void atomic_add(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "addl %1,%0"
: "+m" (v->counter)
@@ -60,7 +60,7 @@
*
* Atomically subtracts @i from @v.
*/
-static inline void atomic_sub(int i, atomic_t *v)
+static __always_inline void atomic_sub(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "subl %1,%0"
: "+m" (v->counter)
@@ -76,7 +76,7 @@
* true if the result is zero, or false for all
* other cases.
*/
-static inline int atomic_sub_and_test(int i, atomic_t *v)
+static __always_inline int atomic_sub_and_test(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e");
}
@@ -87,7 +87,7 @@
*
* Atomically increments @v by 1.
*/
-static inline void atomic_inc(atomic_t *v)
+static __always_inline void atomic_inc(atomic_t *v)
{
asm volatile(LOCK_PREFIX "incl %0"
: "+m" (v->counter));
@@ -99,7 +99,7 @@
*
* Atomically decrements @v by 1.
*/
-static inline void atomic_dec(atomic_t *v)
+static __always_inline void atomic_dec(atomic_t *v)
{
asm volatile(LOCK_PREFIX "decl %0"
: "+m" (v->counter));
@@ -113,7 +113,7 @@
* returns true if the result is 0, or false for all other
* cases.
*/
-static inline int atomic_dec_and_test(atomic_t *v)
+static __always_inline int atomic_dec_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
}
@@ -126,7 +126,7 @@
* and returns true if the result is zero, or false for all
* other cases.
*/
-static inline int atomic_inc_and_test(atomic_t *v)
+static __always_inline int atomic_inc_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
}
@@ -140,7 +140,7 @@
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
-static inline int atomic_add_negative(int i, atomic_t *v)
+static __always_inline int atomic_add_negative(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s");
}
@@ -152,7 +152,7 @@
*
* Atomically adds @i to @v and returns @i + @v
*/
-static inline int atomic_add_return(int i, atomic_t *v)
+static __always_inline int atomic_add_return(int i, atomic_t *v)
{
return i + xadd(&v->counter, i);
}
@@ -164,7 +164,7 @@
*
* Atomically subtracts @i from @v and returns @v - @i
*/
-static inline int atomic_sub_return(int i, atomic_t *v)
+static __always_inline int atomic_sub_return(int i, atomic_t *v)
{
return atomic_add_return(-i, v);
}
@@ -172,7 +172,7 @@
#define atomic_inc_return(v) (atomic_add_return(1, v))
#define atomic_dec_return(v) (atomic_sub_return(1, v))
-static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
{
return cmpxchg(&v->counter, old, new);
}
@@ -191,7 +191,7 @@
* Atomically adds @a to @v, so long as @v was not already @u.
* Returns the old value of @v.
*/
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
{
int c, old;
c = atomic_read(v);
@@ -213,7 +213,7 @@
* Atomically adds 1 to @v
* Returns the new value of @u
*/
-static inline short int atomic_inc_short(short int *v)
+static __always_inline short int atomic_inc_short(short int *v)
{
asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
return *v;
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index f8d273e..b965f9e 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -40,7 +40,7 @@
*
* Atomically adds @i to @v.
*/
-static inline void atomic64_add(long i, atomic64_t *v)
+static __always_inline void atomic64_add(long i, atomic64_t *v)
{
asm volatile(LOCK_PREFIX "addq %1,%0"
: "=m" (v->counter)
@@ -81,7 +81,7 @@
*
* Atomically increments @v by 1.
*/
-static inline void atomic64_inc(atomic64_t *v)
+static __always_inline void atomic64_inc(atomic64_t *v)
{
asm volatile(LOCK_PREFIX "incq %0"
: "=m" (v->counter)
@@ -94,7 +94,7 @@
*
* Atomically decrements @v by 1.
*/
-static inline void atomic64_dec(atomic64_t *v)
+static __always_inline void atomic64_dec(atomic64_t *v)
{
asm volatile(LOCK_PREFIX "decq %0"
: "=m" (v->counter)
@@ -148,7 +148,7 @@
*
* Atomically adds @i to @v and returns @i + @v
*/
-static inline long atomic64_add_return(long i, atomic64_t *v)
+static __always_inline long atomic64_add_return(long i, atomic64_t *v)
{
return i + xadd(&v->counter, i);
}
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 959e45b..e51a8f8 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -35,12 +35,12 @@
#define smp_mb() mb()
#define smp_rmb() dma_rmb()
#define smp_wmb() barrier()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
#else /* !SMP */
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0)
#endif /* SMP */
#define read_barrier_depends() do { } while (0)
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 99c105d7..ad19841 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -4,8 +4,6 @@
#include <linux/compiler.h>
#include <asm/alternative.h> /* Provides LOCK_PREFIX */
-#define __HAVE_ARCH_CMPXCHG 1
-
/*
* Non-existant functions to indicate usage errors at link time
* (or compile-time if the compiler implements __compiletime_error().
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
deleted file mode 100644
index de1cdaf..0000000
--- a/arch/x86/include/asm/dwarf2.h
+++ /dev/null
@@ -1,170 +0,0 @@
-#ifndef _ASM_X86_DWARF2_H
-#define _ASM_X86_DWARF2_H
-
-#ifndef __ASSEMBLY__
-#warning "asm/dwarf2.h should be only included in pure assembly files"
-#endif
-
-/*
- * Macros for dwarf2 CFI unwind table entries.
- * See "as.info" for details on these pseudo ops. Unfortunately
- * they are only supported in very new binutils, so define them
- * away for older version.
- */
-
-#ifdef CONFIG_AS_CFI
-
-#define CFI_STARTPROC .cfi_startproc
-#define CFI_ENDPROC .cfi_endproc
-#define CFI_DEF_CFA .cfi_def_cfa
-#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
-#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
-#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
-#define CFI_OFFSET .cfi_offset
-#define CFI_REL_OFFSET .cfi_rel_offset
-#define CFI_REGISTER .cfi_register
-#define CFI_RESTORE .cfi_restore
-#define CFI_REMEMBER_STATE .cfi_remember_state
-#define CFI_RESTORE_STATE .cfi_restore_state
-#define CFI_UNDEFINED .cfi_undefined
-#define CFI_ESCAPE .cfi_escape
-
-#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME .cfi_signal_frame
-#else
-#define CFI_SIGNAL_FRAME
-#endif
-
-#if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__)
- /*
- * Emit CFI data in .debug_frame sections, not .eh_frame sections.
- * The latter we currently just discard since we don't do DWARF
- * unwinding at runtime. So only the offline DWARF information is
- * useful to anyone. Note we should not use this directive if this
- * file is used in the vDSO assembly, or if vmlinux.lds.S gets
- * changed so it doesn't discard .eh_frame.
- */
- .cfi_sections .debug_frame
-#endif
-
-#else
-
-/*
- * Due to the structure of pre-exisiting code, don't use assembler line
- * comment character # to ignore the arguments. Instead, use a dummy macro.
- */
-.macro cfi_ignore a=0, b=0, c=0, d=0
-.endm
-
-#define CFI_STARTPROC cfi_ignore
-#define CFI_ENDPROC cfi_ignore
-#define CFI_DEF_CFA cfi_ignore
-#define CFI_DEF_CFA_REGISTER cfi_ignore
-#define CFI_DEF_CFA_OFFSET cfi_ignore
-#define CFI_ADJUST_CFA_OFFSET cfi_ignore
-#define CFI_OFFSET cfi_ignore
-#define CFI_REL_OFFSET cfi_ignore
-#define CFI_REGISTER cfi_ignore
-#define CFI_RESTORE cfi_ignore
-#define CFI_REMEMBER_STATE cfi_ignore
-#define CFI_RESTORE_STATE cfi_ignore
-#define CFI_UNDEFINED cfi_ignore
-#define CFI_ESCAPE cfi_ignore
-#define CFI_SIGNAL_FRAME cfi_ignore
-
-#endif
-
-/*
- * An attempt to make CFI annotations more or less
- * correct and shorter. It is implied that you know
- * what you're doing if you use them.
- */
-#ifdef __ASSEMBLY__
-#ifdef CONFIG_X86_64
- .macro pushq_cfi reg
- pushq \reg
- CFI_ADJUST_CFA_OFFSET 8
- .endm
-
- .macro pushq_cfi_reg reg
- pushq %\reg
- CFI_ADJUST_CFA_OFFSET 8
- CFI_REL_OFFSET \reg, 0
- .endm
-
- .macro popq_cfi reg
- popq \reg
- CFI_ADJUST_CFA_OFFSET -8
- .endm
-
- .macro popq_cfi_reg reg
- popq %\reg
- CFI_ADJUST_CFA_OFFSET -8
- CFI_RESTORE \reg
- .endm
-
- .macro pushfq_cfi
- pushfq
- CFI_ADJUST_CFA_OFFSET 8
- .endm
-
- .macro popfq_cfi
- popfq
- CFI_ADJUST_CFA_OFFSET -8
- .endm
-
- .macro movq_cfi reg offset=0
- movq %\reg, \offset(%rsp)
- CFI_REL_OFFSET \reg, \offset
- .endm
-
- .macro movq_cfi_restore offset reg
- movq \offset(%rsp), %\reg
- CFI_RESTORE \reg
- .endm
-#else /*!CONFIG_X86_64*/
- .macro pushl_cfi reg
- pushl \reg
- CFI_ADJUST_CFA_OFFSET 4
- .endm
-
- .macro pushl_cfi_reg reg
- pushl %\reg
- CFI_ADJUST_CFA_OFFSET 4
- CFI_REL_OFFSET \reg, 0
- .endm
-
- .macro popl_cfi reg
- popl \reg
- CFI_ADJUST_CFA_OFFSET -4
- .endm
-
- .macro popl_cfi_reg reg
- popl %\reg
- CFI_ADJUST_CFA_OFFSET -4
- CFI_RESTORE \reg
- .endm
-
- .macro pushfl_cfi
- pushfl
- CFI_ADJUST_CFA_OFFSET 4
- .endm
-
- .macro popfl_cfi
- popfl
- CFI_ADJUST_CFA_OFFSET -4
- .endm
-
- .macro movl_cfi reg offset=0
- movl %\reg, \offset(%esp)
- CFI_REL_OFFSET \reg, \offset
- .endm
-
- .macro movl_cfi_restore offset reg
- movl \offset(%esp), %\reg
- CFI_RESTORE \reg
- .endm
-#endif /*!CONFIG_X86_64*/
-#endif /*__ASSEMBLY__*/
-
-#endif /* _ASM_X86_DWARF2_H */
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index dc5fa66..df00299 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -23,6 +23,8 @@
#ifdef CONFIG_HAVE_KVM
BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR,
smp_kvm_posted_intr_ipi)
+BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR,
+ smp_kvm_posted_intr_wakeup_ipi)
#endif
/*
@@ -50,4 +52,7 @@
BUILD_INTERRUPT(threshold_interrupt,THRESHOLD_APIC_VECTOR)
#endif
+#ifdef CONFIG_X86_MCE_AMD
+BUILD_INTERRUPT(deferred_error_interrupt, DEFERRED_ERROR_VECTOR)
+#endif
#endif
diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h
index 3b629f4..793179c 100644
--- a/arch/x86/include/asm/frame.h
+++ b/arch/x86/include/asm/frame.h
@@ -1,20 +1,17 @@
#ifdef __ASSEMBLY__
#include <asm/asm.h>
-#include <asm/dwarf2.h>
/* The annotation hides the frame from the unwinder and makes it look
like a ordinary ebp save/restore. This avoids some special cases for
frame pointer later */
#ifdef CONFIG_FRAME_POINTER
.macro FRAME
- __ASM_SIZE(push,_cfi) %__ASM_REG(bp)
- CFI_REL_OFFSET __ASM_REG(bp), 0
+ __ASM_SIZE(push,) %__ASM_REG(bp)
__ASM_SIZE(mov) %__ASM_REG(sp), %__ASM_REG(bp)
.endm
.macro ENDFRAME
- __ASM_SIZE(pop,_cfi) %__ASM_REG(bp)
- CFI_RESTORE __ASM_REG(bp)
+ __ASM_SIZE(pop,) %__ASM_REG(bp)
.endm
#else
.macro FRAME
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 0f5fb6b..7178043 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -14,6 +14,7 @@
#endif
#ifdef CONFIG_HAVE_KVM
unsigned int kvm_posted_intr_ipis;
+ unsigned int kvm_posted_intr_wakeup_ipis;
#endif
unsigned int x86_platform_ipis; /* arch dependent */
unsigned int apic_perf_irqs;
@@ -33,6 +34,9 @@
#ifdef CONFIG_X86_MCE_THRESHOLD
unsigned int irq_threshold_count;
#endif
+#ifdef CONFIG_X86_MCE_AMD
+ unsigned int irq_deferred_error_count;
+#endif
#if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
unsigned int irq_hv_callback_count;
#endif
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 36f7125..5fa9fb0 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -74,20 +74,16 @@
extern void force_hpet_resume(void);
struct irq_data;
+struct hpet_dev;
+struct irq_domain;
+
extern void hpet_msi_unmask(struct irq_data *data);
extern void hpet_msi_mask(struct irq_data *data);
-struct hpet_dev;
extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg);
extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg);
-
-#ifdef CONFIG_PCI_MSI
-extern int default_setup_hpet_msi(unsigned int irq, unsigned int id);
-#else
-static inline int default_setup_hpet_msi(unsigned int irq, unsigned int id)
-{
- return -EINVAL;
-}
-#endif
+extern struct irq_domain *hpet_create_irq_domain(int hpet_id);
+extern int hpet_assign_irq(struct irq_domain *domain,
+ struct hpet_dev *dev, int dev_num);
#ifdef CONFIG_HPET_EMULATE_RTC
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index e9571dd..6615032 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -29,6 +29,7 @@
extern asmlinkage void apic_timer_interrupt(void);
extern asmlinkage void x86_platform_ipi(void);
extern asmlinkage void kvm_posted_intr_ipi(void);
+extern asmlinkage void kvm_posted_intr_wakeup_ipi(void);
extern asmlinkage void error_interrupt(void);
extern asmlinkage void irq_work_interrupt(void);
@@ -36,43 +37,10 @@
extern asmlinkage void thermal_interrupt(void);
extern asmlinkage void reschedule_interrupt(void);
-extern asmlinkage void invalidate_interrupt(void);
-extern asmlinkage void invalidate_interrupt0(void);
-extern asmlinkage void invalidate_interrupt1(void);
-extern asmlinkage void invalidate_interrupt2(void);
-extern asmlinkage void invalidate_interrupt3(void);
-extern asmlinkage void invalidate_interrupt4(void);
-extern asmlinkage void invalidate_interrupt5(void);
-extern asmlinkage void invalidate_interrupt6(void);
-extern asmlinkage void invalidate_interrupt7(void);
-extern asmlinkage void invalidate_interrupt8(void);
-extern asmlinkage void invalidate_interrupt9(void);
-extern asmlinkage void invalidate_interrupt10(void);
-extern asmlinkage void invalidate_interrupt11(void);
-extern asmlinkage void invalidate_interrupt12(void);
-extern asmlinkage void invalidate_interrupt13(void);
-extern asmlinkage void invalidate_interrupt14(void);
-extern asmlinkage void invalidate_interrupt15(void);
-extern asmlinkage void invalidate_interrupt16(void);
-extern asmlinkage void invalidate_interrupt17(void);
-extern asmlinkage void invalidate_interrupt18(void);
-extern asmlinkage void invalidate_interrupt19(void);
-extern asmlinkage void invalidate_interrupt20(void);
-extern asmlinkage void invalidate_interrupt21(void);
-extern asmlinkage void invalidate_interrupt22(void);
-extern asmlinkage void invalidate_interrupt23(void);
-extern asmlinkage void invalidate_interrupt24(void);
-extern asmlinkage void invalidate_interrupt25(void);
-extern asmlinkage void invalidate_interrupt26(void);
-extern asmlinkage void invalidate_interrupt27(void);
-extern asmlinkage void invalidate_interrupt28(void);
-extern asmlinkage void invalidate_interrupt29(void);
-extern asmlinkage void invalidate_interrupt30(void);
-extern asmlinkage void invalidate_interrupt31(void);
-
extern asmlinkage void irq_move_cleanup_interrupt(void);
extern asmlinkage void reboot_interrupt(void);
extern asmlinkage void threshold_interrupt(void);
+extern asmlinkage void deferred_error_interrupt(void);
extern asmlinkage void call_function_interrupt(void);
extern asmlinkage void call_function_single_interrupt(void);
@@ -87,60 +55,93 @@
extern void trace_thermal_interrupt(void);
extern void trace_reschedule_interrupt(void);
extern void trace_threshold_interrupt(void);
+extern void trace_deferred_error_interrupt(void);
extern void trace_call_function_interrupt(void);
extern void trace_call_function_single_interrupt(void);
#define trace_irq_move_cleanup_interrupt irq_move_cleanup_interrupt
#define trace_reboot_interrupt reboot_interrupt
#define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi
+#define trace_kvm_posted_intr_wakeup_ipi kvm_posted_intr_wakeup_ipi
#endif /* CONFIG_TRACING */
-#ifdef CONFIG_IRQ_REMAP
-/* Intel specific interrupt remapping information */
-struct irq_2_iommu {
- struct intel_iommu *iommu;
- u16 irte_index;
- u16 sub_handle;
- u8 irte_mask;
-};
-
-/* AMD specific interrupt remapping information */
-struct irq_2_irte {
- u16 devid; /* Device ID for IRTE table */
- u16 index; /* Index into IRTE table*/
-};
-#endif /* CONFIG_IRQ_REMAP */
-
#ifdef CONFIG_X86_LOCAL_APIC
struct irq_data;
+struct pci_dev;
+struct msi_desc;
-struct irq_cfg {
- cpumask_var_t domain;
- cpumask_var_t old_domain;
- u8 vector;
- u8 move_in_progress : 1;
-#ifdef CONFIG_IRQ_REMAP
- u8 remapped : 1;
+enum irq_alloc_type {
+ X86_IRQ_ALLOC_TYPE_IOAPIC = 1,
+ X86_IRQ_ALLOC_TYPE_HPET,
+ X86_IRQ_ALLOC_TYPE_MSI,
+ X86_IRQ_ALLOC_TYPE_MSIX,
+ X86_IRQ_ALLOC_TYPE_DMAR,
+ X86_IRQ_ALLOC_TYPE_UV,
+};
+
+struct irq_alloc_info {
+ enum irq_alloc_type type;
+ u32 flags;
+ const struct cpumask *mask; /* CPU mask for vector allocation */
union {
- struct irq_2_iommu irq_2_iommu;
- struct irq_2_irte irq_2_irte;
- };
-#endif
- union {
-#ifdef CONFIG_X86_IO_APIC
+ int unused;
+#ifdef CONFIG_HPET_TIMER
struct {
- struct list_head irq_2_pin;
+ int hpet_id;
+ int hpet_index;
+ void *hpet_data;
+ };
+#endif
+#ifdef CONFIG_PCI_MSI
+ struct {
+ struct pci_dev *msi_dev;
+ irq_hw_number_t msi_hwirq;
+ };
+#endif
+#ifdef CONFIG_X86_IO_APIC
+ struct {
+ int ioapic_id;
+ int ioapic_pin;
+ int ioapic_node;
+ u32 ioapic_trigger : 1;
+ u32 ioapic_polarity : 1;
+ u32 ioapic_valid : 1;
+ struct IO_APIC_route_entry *ioapic_entry;
+ };
+#endif
+#ifdef CONFIG_DMAR_TABLE
+ struct {
+ int dmar_id;
+ void *dmar_data;
+ };
+#endif
+#ifdef CONFIG_HT_IRQ
+ struct {
+ int ht_pos;
+ int ht_idx;
+ struct pci_dev *ht_dev;
+ void *ht_update;
+ };
+#endif
+#ifdef CONFIG_X86_UV
+ struct {
+ int uv_limit;
+ int uv_blade;
+ unsigned long uv_offset;
+ char *uv_name;
};
#endif
};
};
+struct irq_cfg {
+ unsigned int dest_apicid;
+ u8 vector;
+};
+
extern struct irq_cfg *irq_cfg(unsigned int irq);
extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data);
-extern struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node);
extern void lock_vector_lock(void);
extern void unlock_vector_lock(void);
-extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
-extern void clear_irq_vector(int irq, struct irq_cfg *cfg);
extern void setup_vector_irq(int cpu);
#ifdef CONFIG_SMP
extern void send_cleanup_vector(struct irq_cfg *);
@@ -150,10 +151,7 @@
static inline void irq_complete_move(struct irq_cfg *c) { }
#endif
-extern int apic_retrigger_irq(struct irq_data *data);
extern void apic_ack_edge(struct irq_data *data);
-extern int apic_set_affinity(struct irq_data *data, const struct cpumask *mask,
- unsigned int *dest_id);
#else /* CONFIG_X86_LOCAL_APIC */
static inline void lock_vector_lock(void) {}
static inline void unlock_vector_lock(void) {}
@@ -163,8 +161,7 @@
extern atomic_t irq_err_count;
extern atomic_t irq_mis_count;
-/* EISA */
-extern void eisa_set_level_irq(unsigned int irq);
+extern void elcr_set_level_irq(unsigned int irq);
/* SMP */
extern __visible void smp_apic_timer_interrupt(struct pt_regs *);
@@ -178,7 +175,6 @@
extern __visible void smp_reschedule_interrupt(struct pt_regs *);
extern __visible void smp_call_function_interrupt(struct pt_regs *);
extern __visible void smp_call_function_single_interrupt(struct pt_regs *);
-extern __visible void smp_invalidate_interrupt(struct pt_regs *);
#endif
extern char irq_entries_start[];
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 2f91685..6cbf2cf 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -95,9 +95,22 @@
index : 15;
} __attribute__ ((packed));
-#define IOAPIC_AUTO -1
-#define IOAPIC_EDGE 0
-#define IOAPIC_LEVEL 1
+struct irq_alloc_info;
+struct ioapic_domain_cfg;
+
+#define IOAPIC_AUTO -1
+#define IOAPIC_EDGE 0
+#define IOAPIC_LEVEL 1
+
+#define IOAPIC_MASKED 1
+#define IOAPIC_UNMASKED 0
+
+#define IOAPIC_POL_HIGH 0
+#define IOAPIC_POL_LOW 1
+
+#define IOAPIC_DEST_MODE_PHYSICAL 0
+#define IOAPIC_DEST_MODE_LOGICAL 1
+
#define IOAPIC_MAP_ALLOC 0x1
#define IOAPIC_MAP_CHECK 0x2
@@ -110,9 +123,6 @@
extern int mpc_ioapic_id(int ioapic);
extern unsigned int mpc_ioapic_addr(int ioapic);
-extern struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic);
-
-#define MP_MAX_IOAPIC_PIN 127
/* # of MP IRQ source entries */
extern int mp_irq_entries;
@@ -120,9 +130,6 @@
/* MP IRQ source entries */
extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
-/* Older SiS APIC requires we rewrite the index register */
-extern int sis_apic_bug;
-
/* 1 if "noapic" boot option passed */
extern int skip_ioapic_setup;
@@ -132,6 +139,8 @@
/* -1 if "noapic" boot option passed */
extern int noioapicreroute;
+extern u32 gsi_top;
+
extern unsigned long io_apic_irqs;
#define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1 << (x)) & io_apic_irqs))
@@ -147,13 +156,6 @@
extern void ioapic_insert_resources(void);
extern int arch_early_ioapic_init(void);
-extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *,
- unsigned int, int,
- struct io_apic_irq_attr *);
-extern void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg);
-
-extern void native_eoi_ioapic_pin(int apic, int pin, int vector);
-
extern int save_ioapic_entries(void);
extern void mask_ioapic_entries(void);
extern int restore_ioapic_entries(void);
@@ -161,82 +163,32 @@
extern void setup_ioapic_ids_from_mpc(void);
extern void setup_ioapic_ids_from_mpc_nocheck(void);
-struct io_apic_irq_attr {
- int ioapic;
- int ioapic_pin;
- int trigger;
- int polarity;
-};
-
-enum ioapic_domain_type {
- IOAPIC_DOMAIN_INVALID,
- IOAPIC_DOMAIN_LEGACY,
- IOAPIC_DOMAIN_STRICT,
- IOAPIC_DOMAIN_DYNAMIC,
-};
-
-struct device_node;
-struct irq_domain;
-struct irq_domain_ops;
-
-struct ioapic_domain_cfg {
- enum ioapic_domain_type type;
- const struct irq_domain_ops *ops;
- struct device_node *dev;
-};
-
-struct mp_ioapic_gsi{
- u32 gsi_base;
- u32 gsi_end;
-};
-extern u32 gsi_top;
-
extern int mp_find_ioapic(u32 gsi);
extern int mp_find_ioapic_pin(int ioapic, u32 gsi);
-extern u32 mp_pin_to_gsi(int ioapic, int pin);
-extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags);
+extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags,
+ struct irq_alloc_info *info);
extern void mp_unmap_irq(int irq);
extern int mp_register_ioapic(int id, u32 address, u32 gsi_base,
struct ioapic_domain_cfg *cfg);
extern int mp_unregister_ioapic(u32 gsi_base);
extern int mp_ioapic_registered(u32 gsi_base);
-extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
- irq_hw_number_t hwirq);
-extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq);
-extern int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node);
-extern void __init pre_init_apic_IRQ0(void);
+
+extern void ioapic_set_alloc_attr(struct irq_alloc_info *info,
+ int node, int trigger, int polarity);
extern void mp_save_irq(struct mpc_intsrc *m);
extern void disable_ioapic_support(void);
-extern void __init native_io_apic_init_mappings(void);
+extern void __init io_apic_init_mappings(void);
extern unsigned int native_io_apic_read(unsigned int apic, unsigned int reg);
-extern void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int val);
-extern void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int val);
extern void native_disable_io_apic(void);
-extern void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries);
-extern void intel_ir_io_apic_print_entries(unsigned int apic, unsigned int nr_entries);
-extern int native_ioapic_set_affinity(struct irq_data *,
- const struct cpumask *,
- bool);
static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
{
return x86_io_apic_ops.read(apic, reg);
}
-static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
-{
- x86_io_apic_ops.write(apic, reg, value);
-}
-static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
-{
- x86_io_apic_ops.modify(apic, reg, value);
-}
-
-extern void io_apic_eoi(unsigned int apic, unsigned int vector);
-
extern void setup_IO_APIC(void);
extern void enable_IO_APIC(void);
extern void disable_IO_APIC(void);
@@ -253,8 +205,12 @@
static inline void print_IO_APICs(void) {}
#define gsi_top (NR_IRQS_LEGACY)
static inline int mp_find_ioapic(u32 gsi) { return 0; }
-static inline u32 mp_pin_to_gsi(int ioapic, int pin) { return UINT_MAX; }
-static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) { return gsi; }
+static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags,
+ struct irq_alloc_info *info)
+{
+ return gsi;
+}
+
static inline void mp_unmap_irq(int irq) { }
static inline int save_ioapic_entries(void)
@@ -268,17 +224,11 @@
return -ENOMEM;
}
-static inline void mp_save_irq(struct mpc_intsrc *m) { };
+static inline void mp_save_irq(struct mpc_intsrc *m) { }
static inline void disable_ioapic_support(void) { }
-#define native_io_apic_init_mappings NULL
+static inline void io_apic_init_mappings(void) { }
#define native_io_apic_read NULL
-#define native_io_apic_write NULL
-#define native_io_apic_modify NULL
#define native_disable_io_apic NULL
-#define native_io_apic_print_entries NULL
-#define native_ioapic_set_affinity NULL
-#define native_setup_ioapic_entry NULL
-#define native_eoi_ioapic_pin NULL
static inline void setup_IO_APIC(void) { }
static inline void enable_IO_APIC(void) { }
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index a80cbb8..8008d06 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -30,6 +30,10 @@
extern void irq_force_complete_move(int);
#endif
+#ifdef CONFIG_HAVE_KVM
+extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void));
+#endif
+
extern void (*x86_platform_ipi_callback)(void);
extern void native_init_IRQ(void);
extern bool handle_irq(unsigned irq, struct pt_regs *regs);
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 6224d31..046c7fb 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -22,84 +22,72 @@
#ifndef __X86_IRQ_REMAPPING_H
#define __X86_IRQ_REMAPPING_H
+#include <asm/irqdomain.h>
+#include <asm/hw_irq.h>
#include <asm/io_apic.h>
-struct IO_APIC_route_entry;
-struct io_apic_irq_attr;
-struct irq_chip;
struct msi_msg;
-struct pci_dev;
-struct irq_cfg;
+struct irq_alloc_info;
+
+enum irq_remap_cap {
+ IRQ_POSTING_CAP = 0,
+};
#ifdef CONFIG_IRQ_REMAP
+extern bool irq_remapping_cap(enum irq_remap_cap cap);
extern void set_irq_remapping_broken(void);
extern int irq_remapping_prepare(void);
extern int irq_remapping_enable(void);
extern void irq_remapping_disable(void);
extern int irq_remapping_reenable(int);
extern int irq_remap_enable_fault_handling(void);
-extern int setup_ioapic_remapped_entry(int irq,
- struct IO_APIC_route_entry *entry,
- unsigned int destination,
- int vector,
- struct io_apic_irq_attr *attr);
-extern void free_remapped_irq(int irq);
-extern void compose_remapped_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id);
-extern int setup_hpet_msi_remapped(unsigned int irq, unsigned int id);
extern void panic_if_irq_remap(const char *msg);
-extern bool setup_remapped_irq(int irq,
- struct irq_cfg *cfg,
- struct irq_chip *chip);
-void irq_remap_modify_chip_defaults(struct irq_chip *chip);
+extern struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info);
+extern struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info);
+
+/* Create PCI MSI/MSIx irqdomain, use @parent as the parent irqdomain. */
+extern struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent);
+
+/* Get parent irqdomain for interrupt remapping irqdomain */
+static inline struct irq_domain *arch_get_ir_parent_domain(void)
+{
+ return x86_vector_domain;
+}
+
+struct vcpu_data {
+ u64 pi_desc_addr; /* Physical address of PI Descriptor */
+ u32 vector; /* Guest vector of the interrupt */
+};
#else /* CONFIG_IRQ_REMAP */
+static inline bool irq_remapping_cap(enum irq_remap_cap cap) { return 0; }
static inline void set_irq_remapping_broken(void) { }
static inline int irq_remapping_prepare(void) { return -ENODEV; }
static inline int irq_remapping_enable(void) { return -ENODEV; }
static inline void irq_remapping_disable(void) { }
static inline int irq_remapping_reenable(int eim) { return -ENODEV; }
static inline int irq_remap_enable_fault_handling(void) { return -ENODEV; }
-static inline int setup_ioapic_remapped_entry(int irq,
- struct IO_APIC_route_entry *entry,
- unsigned int destination,
- int vector,
- struct io_apic_irq_attr *attr)
-{
- return -ENODEV;
-}
-static inline void free_remapped_irq(int irq) { }
-static inline void compose_remapped_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id)
-{
-}
-static inline int setup_hpet_msi_remapped(unsigned int irq, unsigned int id)
-{
- return -ENODEV;
-}
static inline void panic_if_irq_remap(const char *msg)
{
}
-static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+static inline struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info)
{
+ return NULL;
}
-static inline bool setup_remapped_irq(int irq,
- struct irq_cfg *cfg,
- struct irq_chip *chip)
+static inline struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info)
{
- return false;
+ return NULL;
}
+
#endif /* CONFIG_IRQ_REMAP */
-
-#define dmar_alloc_hwirq() irq_alloc_hwirq(-1)
-#define dmar_free_hwirq irq_free_hwirq
-
#endif /* __X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 666c89e..4c2d2eb 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -47,31 +47,12 @@
#define IRQ_MOVE_CLEANUP_VECTOR FIRST_EXTERNAL_VECTOR
#define IA32_SYSCALL_VECTOR 0x80
-#ifdef CONFIG_X86_32
-# define SYSCALL_VECTOR 0x80
-#endif
/*
* Vectors 0x30-0x3f are used for ISA interrupts.
* round up to the next 16-vector boundary
*/
-#define IRQ0_VECTOR ((FIRST_EXTERNAL_VECTOR + 16) & ~15)
-
-#define IRQ1_VECTOR (IRQ0_VECTOR + 1)
-#define IRQ2_VECTOR (IRQ0_VECTOR + 2)
-#define IRQ3_VECTOR (IRQ0_VECTOR + 3)
-#define IRQ4_VECTOR (IRQ0_VECTOR + 4)
-#define IRQ5_VECTOR (IRQ0_VECTOR + 5)
-#define IRQ6_VECTOR (IRQ0_VECTOR + 6)
-#define IRQ7_VECTOR (IRQ0_VECTOR + 7)
-#define IRQ8_VECTOR (IRQ0_VECTOR + 8)
-#define IRQ9_VECTOR (IRQ0_VECTOR + 9)
-#define IRQ10_VECTOR (IRQ0_VECTOR + 10)
-#define IRQ11_VECTOR (IRQ0_VECTOR + 11)
-#define IRQ12_VECTOR (IRQ0_VECTOR + 12)
-#define IRQ13_VECTOR (IRQ0_VECTOR + 13)
-#define IRQ14_VECTOR (IRQ0_VECTOR + 14)
-#define IRQ15_VECTOR (IRQ0_VECTOR + 15)
+#define ISA_IRQ_VECTOR(irq) (((FIRST_EXTERNAL_VECTOR + 16) & ~15) + irq)
/*
* Special IRQ vectors used by the SMP architecture, 0xf0-0xff
@@ -102,21 +83,23 @@
*/
#define X86_PLATFORM_IPI_VECTOR 0xf7
-/* Vector for KVM to deliver posted interrupt IPI */
-#ifdef CONFIG_HAVE_KVM
-#define POSTED_INTR_VECTOR 0xf2
-#endif
-
+#define POSTED_INTR_WAKEUP_VECTOR 0xf1
/*
* IRQ work vector:
*/
#define IRQ_WORK_VECTOR 0xf6
#define UV_BAU_MESSAGE 0xf5
+#define DEFERRED_ERROR_VECTOR 0xf4
/* Vector on which hypervisor callbacks will be delivered */
#define HYPERVISOR_CALLBACK_VECTOR 0xf3
+/* Vector for KVM to deliver posted interrupt IPI */
+#ifdef CONFIG_HAVE_KVM
+#define POSTED_INTR_VECTOR 0xf2
+#endif
+
/*
* Local APIC timer IRQ vector is on a different priority level,
* to work around the 'lost local interrupt if more than 2 IRQ
@@ -155,18 +138,22 @@
* static arrays.
*/
-#define NR_IRQS_LEGACY 16
+#define NR_IRQS_LEGACY 16
-#define IO_APIC_VECTOR_LIMIT ( 32 * MAX_IO_APICS )
+#define CPU_VECTOR_LIMIT (64 * NR_CPUS)
+#define IO_APIC_VECTOR_LIMIT (32 * MAX_IO_APICS)
-#ifdef CONFIG_X86_IO_APIC
-# define CPU_VECTOR_LIMIT (64 * NR_CPUS)
-# define NR_IRQS \
+#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_PCI_MSI)
+#define NR_IRQS \
(CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ? \
(NR_VECTORS + CPU_VECTOR_LIMIT) : \
(NR_VECTORS + IO_APIC_VECTOR_LIMIT))
-#else /* !CONFIG_X86_IO_APIC: */
-# define NR_IRQS NR_IRQS_LEGACY
+#elif defined(CONFIG_X86_IO_APIC)
+#define NR_IRQS (NR_VECTORS + IO_APIC_VECTOR_LIMIT)
+#elif defined(CONFIG_PCI_MSI)
+#define NR_IRQS (NR_VECTORS + CPU_VECTOR_LIMIT)
+#else
+#define NR_IRQS NR_IRQS_LEGACY
#endif
#endif /* _ASM_X86_IRQ_VECTORS_H */
diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h
new file mode 100644
index 0000000..d26075b
--- /dev/null
+++ b/arch/x86/include/asm/irqdomain.h
@@ -0,0 +1,63 @@
+#ifndef _ASM_IRQDOMAIN_H
+#define _ASM_IRQDOMAIN_H
+
+#include <linux/irqdomain.h>
+#include <asm/hw_irq.h>
+
+#ifdef CONFIG_X86_LOCAL_APIC
+enum {
+ /* Allocate contiguous CPU vectors */
+ X86_IRQ_ALLOC_CONTIGUOUS_VECTORS = 0x1,
+};
+
+extern struct irq_domain *x86_vector_domain;
+
+extern void init_irq_alloc_info(struct irq_alloc_info *info,
+ const struct cpumask *mask);
+extern void copy_irq_alloc_info(struct irq_alloc_info *dst,
+ struct irq_alloc_info *src);
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+#ifdef CONFIG_X86_IO_APIC
+struct device_node;
+struct irq_data;
+
+enum ioapic_domain_type {
+ IOAPIC_DOMAIN_INVALID,
+ IOAPIC_DOMAIN_LEGACY,
+ IOAPIC_DOMAIN_STRICT,
+ IOAPIC_DOMAIN_DYNAMIC,
+};
+
+struct ioapic_domain_cfg {
+ enum ioapic_domain_type type;
+ const struct irq_domain_ops *ops;
+ struct device_node *dev;
+};
+
+extern const struct irq_domain_ops mp_ioapic_irqdomain_ops;
+
+extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg);
+extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs);
+extern void mp_irqdomain_activate(struct irq_domain *domain,
+ struct irq_data *irq_data);
+extern void mp_irqdomain_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data);
+extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain);
+#endif /* CONFIG_X86_IO_APIC */
+
+#ifdef CONFIG_PCI_MSI
+extern void arch_init_msi_domain(struct irq_domain *domain);
+#else
+static inline void arch_init_msi_domain(struct irq_domain *domain) { }
+#endif
+
+#ifdef CONFIG_HT_IRQ
+extern void arch_init_htirq_domain(struct irq_domain *domain);
+#else
+static inline void arch_init_htirq_domain(struct irq_domain *domain) { }
+#endif
+
+#endif
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 1f5a86d..982dfc3 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -17,11 +17,16 @@
#define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
#define MCG_SER_P (1ULL<<24) /* MCA recovery/new status bits */
#define MCG_ELOG_P (1ULL<<26) /* Extended error log supported */
+#define MCG_LMCE_P (1ULL<<27) /* Local machine check supported */
/* MCG_STATUS register defines */
#define MCG_STATUS_RIPV (1ULL<<0) /* restart ip valid */
#define MCG_STATUS_EIPV (1ULL<<1) /* ip points to correct instruction */
#define MCG_STATUS_MCIP (1ULL<<2) /* machine check in progress */
+#define MCG_STATUS_LMCES (1ULL<<3) /* LMCE signaled */
+
+/* MCG_EXT_CTL register defines */
+#define MCG_EXT_CTL_LMCE_EN (1ULL<<0) /* Enable LMCE */
/* MCi_STATUS register defines */
#define MCI_STATUS_VAL (1ULL<<63) /* valid error */
@@ -104,6 +109,7 @@
struct mca_config {
bool dont_log_ce;
bool cmci_disabled;
+ bool lmce_disabled;
bool ignore_ce;
bool disabled;
bool ser;
@@ -117,8 +123,19 @@
};
struct mce_vendor_flags {
- __u64 overflow_recov : 1, /* cpuid_ebx(80000007) */
- __reserved_0 : 63;
+ /*
+ * overflow recovery cpuid bit indicates that overflow
+ * conditions are not fatal
+ */
+ __u64 overflow_recov : 1,
+
+ /*
+ * SUCCOR stands for S/W UnCorrectable error COntainment
+ * and Recovery. It indicates support for data poisoning
+ * in HW and deferred error interrupts.
+ */
+ succor : 1,
+ __reserved_0 : 62;
};
extern struct mce_vendor_flags mce_flags;
@@ -168,12 +185,16 @@
void cmci_reenable(void);
void cmci_rediscover(void);
void cmci_recheck(void);
+void lmce_clear(void);
+void lmce_enable(void);
#else
static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
static inline void cmci_clear(void) {}
static inline void cmci_reenable(void) {}
static inline void cmci_rediscover(void) {}
static inline void cmci_recheck(void) {}
+static inline void lmce_clear(void) {}
+static inline void lmce_enable(void) {}
#endif
#ifdef CONFIG_X86_MCE_AMD
@@ -223,6 +244,9 @@
extern void (*mce_threshold_vector)(void);
extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
+/* Deferred error interrupt handler */
+extern void (*deferred_error_int_vector)(void);
+
/*
* Thermal handler
*/
diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h
new file mode 100644
index 0000000..93724cc
--- /dev/null
+++ b/arch/x86/include/asm/msi.h
@@ -0,0 +1,7 @@
+#ifndef _ASM_X86_MSI_H
+#define _ASM_X86_MSI_H
+#include <asm/hw_irq.h>
+
+typedef struct irq_alloc_info msi_alloc_info_t;
+
+#endif /* _ASM_X86_MSI_H */
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
similarity index 99%
rename from arch/x86/include/uapi/asm/msr-index.h
rename to arch/x86/include/asm/msr-index.h
index c469490..9ebc3d0 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -56,6 +56,7 @@
#define MSR_IA32_MCG_CAP 0x00000179
#define MSR_IA32_MCG_STATUS 0x0000017a
#define MSR_IA32_MCG_CTL 0x0000017b
+#define MSR_IA32_MCG_EXT_CTL 0x000004d0
#define MSR_OFFCORE_RSP_0 0x000001a6
#define MSR_OFFCORE_RSP_1 0x000001a7
@@ -140,6 +141,7 @@
#define MSR_CORE_C3_RESIDENCY 0x000003fc
#define MSR_CORE_C6_RESIDENCY 0x000003fd
#define MSR_CORE_C7_RESIDENCY 0x000003fe
+#define MSR_KNL_CORE_C6_RESIDENCY 0x000003ff
#define MSR_PKG_C2_RESIDENCY 0x0000060d
#define MSR_PKG_C8_RESIDENCY 0x00000630
#define MSR_PKG_C9_RESIDENCY 0x00000631
@@ -379,6 +381,7 @@
#define FEATURE_CONTROL_LOCKED (1<<0)
#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1<<1)
#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX (1<<2)
+#define FEATURE_CONTROL_LMCE (1<<20)
#define MSR_IA32_APICBASE 0x0000001b
#define MSR_IA32_APICBASE_BSP (1<<8)
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index de36f22..e6a707e 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -1,13 +1,14 @@
#ifndef _ASM_X86_MSR_H
#define _ASM_X86_MSR_H
-#include <uapi/asm/msr.h>
+#include "msr-index.h"
#ifndef __ASSEMBLY__
#include <asm/asm.h>
#include <asm/errno.h>
#include <asm/cpumask.h>
+#include <uapi/asm/msr.h>
struct msr {
union {
@@ -205,8 +206,13 @@
#endif /* !CONFIG_PARAVIRT */
-#define wrmsrl_safe(msr, val) wrmsr_safe((msr), (u32)(val), \
- (u32)((val) >> 32))
+/*
+ * 64-bit version of wrmsr_safe():
+ */
+static inline int wrmsrl_safe(u32 msr, u64 val)
+{
+ return wrmsr_safe(msr, (u32)val, (u32)(val >> 32));
+}
#define write_tsc(low, high) wrmsr(MSR_IA32_TSC, (low), (high))
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 8957810..d143bfa 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -712,6 +712,31 @@
#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock,
+ u32 val)
+{
+ PVOP_VCALL2(pv_lock_ops.queued_spin_lock_slowpath, lock, val);
+}
+
+static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
+{
+ PVOP_VCALLEE1(pv_lock_ops.queued_spin_unlock, lock);
+}
+
+static __always_inline void pv_wait(u8 *ptr, u8 val)
+{
+ PVOP_VCALL2(pv_lock_ops.wait, ptr, val);
+}
+
+static __always_inline void pv_kick(int cpu)
+{
+ PVOP_VCALL1(pv_lock_ops.kick, cpu);
+}
+
+#else /* !CONFIG_QUEUED_SPINLOCKS */
+
static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock,
__ticket_t ticket)
{
@@ -724,7 +749,9 @@
PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket);
}
-#endif
+#endif /* CONFIG_QUEUED_SPINLOCKS */
+
+#endif /* SMP && PARAVIRT_SPINLOCKS */
#ifdef CONFIG_X86_32
#define PV_SAVE_REGS "pushl %ecx; pushl %edx;"
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index f7b0b5c..a6b8f9f 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -160,13 +160,14 @@
u64 (*read_pmc)(int counter);
unsigned long long (*read_tscp)(unsigned int *aux);
+#ifdef CONFIG_X86_32
/*
* Atomically enable interrupts and return to userspace. This
- * is only ever used to return to 32-bit processes; in a
- * 64-bit kernel, it's used for 32-on-64 compat processes, but
- * never native 64-bit processes. (Jump, not call.)
+ * is only used in 32-bit kernels. 64-bit kernels use
+ * usergs_sysret32 instead.
*/
void (*irq_enable_sysexit)(void);
+#endif
/*
* Switch to usermode gs and return to 64-bit usermode using
@@ -333,9 +334,19 @@
typedef u16 __ticket_t;
#endif
+struct qspinlock;
+
struct pv_lock_ops {
+#ifdef CONFIG_QUEUED_SPINLOCKS
+ void (*queued_spin_lock_slowpath)(struct qspinlock *lock, u32 val);
+ struct paravirt_callee_save queued_spin_unlock;
+
+ void (*wait)(u8 *ptr, u8 val);
+ void (*kick)(int cpu);
+#else /* !CONFIG_QUEUED_SPINLOCKS */
struct paravirt_callee_save lock_spinning;
void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket);
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
};
/* This contains all the paravirt structures: we get a convenient
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 4e370a5..d8c80ff 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -96,15 +96,10 @@
#ifdef CONFIG_PCI_MSI
/* implemented in arch/x86/kernel/apic/io_apic. */
struct msi_desc;
-void native_compose_msi_msg(struct pci_dev *pdev, unsigned int irq,
- unsigned int dest, struct msi_msg *msg, u8 hpet_id);
int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
void native_teardown_msi_irq(unsigned int irq);
void native_restore_msi_irqs(struct pci_dev *dev);
-int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
- unsigned int irq_base, unsigned int irq_offset);
#else
-#define native_compose_msi_msg NULL
#define native_setup_msi_irqs NULL
#define native_teardown_msi_irq NULL
#endif
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index a90f897..a4a7728 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -5,12 +5,14 @@
/* misc architecture specific prototypes */
-void system_call(void);
void syscall_init(void);
-void ia32_syscall(void);
-void ia32_cstar_target(void);
-void ia32_sysenter_target(void);
+void entry_SYSCALL_64(void);
+void entry_SYSCALL_compat(void);
+void entry_INT80_32(void);
+void entry_INT80_compat(void);
+void entry_SYSENTER_32(void);
+void entry_SYSENTER_compat(void);
void x86_configure_nx(void);
void x86_report_nx(void);
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
new file mode 100644
index 0000000..9d51fae
--- /dev/null
+++ b/arch/x86/include/asm/qspinlock.h
@@ -0,0 +1,57 @@
+#ifndef _ASM_X86_QSPINLOCK_H
+#define _ASM_X86_QSPINLOCK_H
+
+#include <asm/cpufeature.h>
+#include <asm-generic/qspinlock_types.h>
+#include <asm/paravirt.h>
+
+#define queued_spin_unlock queued_spin_unlock
+/**
+ * queued_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * A smp_store_release() on the least-significant byte.
+ */
+static inline void native_queued_spin_unlock(struct qspinlock *lock)
+{
+ smp_store_release((u8 *)lock, 0);
+}
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __pv_init_lock_hash(void);
+extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
+
+static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+ pv_queued_spin_lock_slowpath(lock, val);
+}
+
+static inline void queued_spin_unlock(struct qspinlock *lock)
+{
+ pv_queued_spin_unlock(lock);
+}
+#else
+static inline void queued_spin_unlock(struct qspinlock *lock)
+{
+ native_queued_spin_unlock(lock);
+}
+#endif
+
+#define virt_queued_spin_lock virt_queued_spin_lock
+
+static inline bool virt_queued_spin_lock(struct qspinlock *lock)
+{
+ if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+ return false;
+
+ while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0)
+ cpu_relax();
+
+ return true;
+}
+
+#include <asm-generic/qspinlock.h>
+
+#endif /* _ASM_X86_QSPINLOCK_H */
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
new file mode 100644
index 0000000..b002e71
--- /dev/null
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_QSPINLOCK_PARAVIRT_H
+#define __ASM_QSPINLOCK_PARAVIRT_H
+
+PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock);
+
+#endif
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 5a9856e..7d5a192 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -231,11 +231,21 @@
#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES* 8)
#ifdef __KERNEL__
+
+/*
+ * early_idt_handler_array is an array of entry points referenced in the
+ * early IDT. For simplicity, it's a real array with one entry point
+ * every nine bytes. That leaves room for an optional 'push $0' if the
+ * vector has no error code (two bytes), a 'push $vector_number' (two
+ * bytes), and a jump to the common entry code (up to five bytes).
+ */
+#define EARLY_IDT_HANDLER_SIZE 9
+
#ifndef __ASSEMBLY__
-extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5];
+extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
#ifdef CONFIG_TRACING
-# define trace_early_idt_handlers early_idt_handlers
+# define trace_early_idt_handler_array early_idt_handler_array
#endif
/*
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 64b6117..be0a059 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -42,6 +42,10 @@
extern struct static_key paravirt_ticketlocks_enabled;
static __always_inline bool static_key_false(struct static_key *key);
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#include <asm/qspinlock.h>
+#else
+
#ifdef CONFIG_PARAVIRT_SPINLOCKS
static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
@@ -196,6 +200,7 @@
cpu_relax();
}
}
+#endif /* CONFIG_QUEUED_SPINLOCKS */
/*
* Read-write spinlocks, allowing multiple readers
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 5f9d757..65c3e37 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -23,6 +23,9 @@
#define TICKET_SHIFT (sizeof(__ticket_t) * 8)
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#include <asm-generic/qspinlock_types.h>
+#else
typedef struct arch_spinlock {
union {
__ticketpair_t head_tail;
@@ -33,6 +36,7 @@
} arch_spinlock_t;
#define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } }
+#endif /* CONFIG_QUEUED_SPINLOCKS */
#include <asm-generic/qrwlock_types.h>
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index b4bdec3..225ee54 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -177,8 +177,6 @@
*/
#ifndef __ASSEMBLY__
-DECLARE_PER_CPU(unsigned long, kernel_stack);
-
static inline struct thread_info *current_thread_info(void)
{
return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE);
@@ -197,9 +195,13 @@
#else /* !__ASSEMBLY__ */
+#ifdef CONFIG_X86_64
+# define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
+#endif
+
/* Load thread_info address into "reg" */
#define GET_THREAD_INFO(reg) \
- _ASM_MOV PER_CPU_VAR(kernel_stack),reg ; \
+ _ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \
_ASM_SUB $(THREAD_SIZE),reg ;
/*
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 0e8f04f..8d717fa 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -26,7 +26,7 @@
#define _ASM_X86_TOPOLOGY_H
#ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_HT
+# ifdef CONFIG_SMP
# define ENABLE_TOPO_DEFINES
# endif
#else
diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h
index 4cab890..38a09a1 100644
--- a/arch/x86/include/asm/trace/irq_vectors.h
+++ b/arch/x86/include/asm/trace/irq_vectors.h
@@ -101,6 +101,12 @@
DEFINE_IRQ_VECTOR_EVENT(threshold_apic);
/*
+ * deferred_error_apic - called when entering/exiting a deferred apic interrupt
+ * vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(deferred_error_apic);
+
+/*
* thermal_apic - called when entering/exiting a thermal apic interrupt
* vector handler
*/
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 4e49d7d..c5380be 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -108,7 +108,8 @@
void math_emulate(struct math_emu_info *);
#ifndef CONFIG_X86_32
asmlinkage void smp_thermal_interrupt(void);
-asmlinkage void mce_threshold_interrupt(void);
+asmlinkage void smp_threshold_interrupt(void);
+asmlinkage void smp_deferred_error_interrupt(void);
#endif
extern enum ctx_state ist_enter(struct pt_regs *regs);
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 3c03a5d..0ed5504 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -59,6 +59,10 @@
__put_user_size(*(u32 *)from, (u32 __user *)to,
4, ret, 4);
return ret;
+ case 8:
+ __put_user_size(*(u64 *)from, (u64 __user *)to,
+ 8, ret, 8);
+ return ret;
}
}
return __copy_to_user_ll(to, from, n);
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index f58a9c7..48d34d2 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -171,38 +171,17 @@
};
struct pci_dev;
-struct msi_msg;
struct x86_msi_ops {
int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
- void (*compose_msi_msg)(struct pci_dev *dev, unsigned int irq,
- unsigned int dest, struct msi_msg *msg,
- u8 hpet_id);
void (*teardown_msi_irq)(unsigned int irq);
void (*teardown_msi_irqs)(struct pci_dev *dev);
void (*restore_msi_irqs)(struct pci_dev *dev);
- int (*setup_hpet_msi)(unsigned int irq, unsigned int id);
};
-struct IO_APIC_route_entry;
-struct io_apic_irq_attr;
-struct irq_data;
-struct cpumask;
-
struct x86_io_apic_ops {
- void (*init) (void);
unsigned int (*read) (unsigned int apic, unsigned int reg);
- void (*write) (unsigned int apic, unsigned int reg, unsigned int value);
- void (*modify) (unsigned int apic, unsigned int reg, unsigned int value);
void (*disable)(void);
- void (*print_entries)(unsigned int apic, unsigned int nr_entries);
- int (*set_affinity)(struct irq_data *data,
- const struct cpumask *mask,
- bool force);
- int (*setup_entry)(int irq, struct IO_APIC_route_entry *entry,
- unsigned int destination, int vector,
- struct io_apic_irq_attr *attr);
- void (*eoi_ioapic_pin)(int apic, int pin, int vector);
};
extern struct x86_init_ops x86_init;
diff --git a/arch/x86/include/uapi/asm/msr.h b/arch/x86/include/uapi/asm/msr.h
index 155e510..c41f4fe 100644
--- a/arch/x86/include/uapi/asm/msr.h
+++ b/arch/x86/include/uapi/asm/msr.h
@@ -1,8 +1,6 @@
#ifndef _UAPI_ASM_X86_MSR_H
#define _UAPI_ASM_X86_MSR_H
-#include <asm/msr-index.h>
-
#ifndef __ASSEMBLY__
#include <linux/types.h>
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9bcd0b5..01663ee 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -22,7 +22,7 @@
CFLAGS_irq.o := -I$(src)/../include/asm/trace
-obj-y := process_$(BITS).o signal.o entry_$(BITS).o
+obj-y := process_$(BITS).o signal.o
obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
obj-y += time.o ioport.o ldt.o dumpstack.o nmi.o
obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o
@@ -31,9 +31,6 @@
obj-$(CONFIG_X86_32) += i386_ksyms_32.o
obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
obj-$(CONFIG_X86_64) += mcount_64.o
-obj-y += syscall_$(BITS).o vsyscall_gtod.o
-obj-$(CONFIG_IA32_EMULATION) += syscall_32.o
-obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o
obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o
obj-$(CONFIG_SYSFS) += ksysfs.o
obj-y += bootflag.o e820.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index dbe76a1..e49ee24 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -31,12 +31,12 @@
#include <linux/module.h>
#include <linux/dmi.h>
#include <linux/irq.h>
-#include <linux/irqdomain.h>
#include <linux/slab.h>
#include <linux/bootmem.h>
#include <linux/ioport.h>
#include <linux/pci.h>
+#include <asm/irqdomain.h>
#include <asm/pci_x86.h>
#include <asm/pgtable.h>
#include <asm/io_apic.h>
@@ -400,57 +400,13 @@
return 0;
}
-static int mp_register_gsi(struct device *dev, u32 gsi, int trigger,
- int polarity)
-{
- int irq, node;
-
- if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
- return gsi;
-
- trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1;
- polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1;
- node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
- if (mp_set_gsi_attr(gsi, trigger, polarity, node)) {
- pr_warn("Failed to set pin attr for GSI%d\n", gsi);
- return -1;
- }
-
- irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC);
- if (irq < 0)
- return irq;
-
- /* Don't set up the ACPI SCI because it's already set up */
- if (enable_update_mptable && acpi_gbl_FADT.sci_interrupt != gsi)
- mp_config_acpi_gsi(dev, gsi, trigger, polarity);
-
- return irq;
-}
-
-static void mp_unregister_gsi(u32 gsi)
-{
- int irq;
-
- if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
- return;
-
- irq = mp_map_gsi_to_irq(gsi, 0);
- if (irq > 0)
- mp_unmap_irq(irq);
-}
-
-static struct irq_domain_ops acpi_irqdomain_ops = {
- .map = mp_irqdomain_map,
- .unmap = mp_irqdomain_unmap,
-};
-
static int __init
acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
{
struct acpi_madt_io_apic *ioapic = NULL;
struct ioapic_domain_cfg cfg = {
.type = IOAPIC_DOMAIN_DYNAMIC,
- .ops = &acpi_irqdomain_ops,
+ .ops = &mp_ioapic_irqdomain_ops,
};
ioapic = (struct acpi_madt_io_apic *)header;
@@ -652,7 +608,7 @@
* Make sure all (legacy) PCI IRQs are set as level-triggered.
*/
if (trigger == ACPI_LEVEL_SENSITIVE)
- eisa_set_level_irq(gsi);
+ elcr_set_level_irq(gsi);
#endif
return gsi;
@@ -663,10 +619,21 @@
int trigger, int polarity)
{
int irq = gsi;
-
#ifdef CONFIG_X86_IO_APIC
+ int node;
+ struct irq_alloc_info info;
+
+ node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
+ trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1;
+ polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1;
+ ioapic_set_alloc_attr(&info, node, trigger, polarity);
+
mutex_lock(&acpi_ioapic_lock);
- irq = mp_register_gsi(dev, gsi, trigger, polarity);
+ irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info);
+ /* Don't set up the ACPI SCI because it's already set up */
+ if (irq >= 0 && enable_update_mptable &&
+ acpi_gbl_FADT.sci_interrupt != gsi)
+ mp_config_acpi_gsi(dev, gsi, trigger, polarity);
mutex_unlock(&acpi_ioapic_lock);
#endif
@@ -676,8 +643,12 @@
static void acpi_unregister_gsi_ioapic(u32 gsi)
{
#ifdef CONFIG_X86_IO_APIC
+ int irq;
+
mutex_lock(&acpi_ioapic_lock);
- mp_unregister_gsi(gsi);
+ irq = mp_map_gsi_to_irq(gsi, 0, NULL);
+ if (irq > 0)
+ mp_unmap_irq(irq);
mutex_unlock(&acpi_ioapic_lock);
#endif
}
@@ -786,7 +757,7 @@
u64 addr;
struct ioapic_domain_cfg cfg = {
.type = IOAPIC_DOMAIN_DYNAMIC,
- .ops = &acpi_irqdomain_ops,
+ .ops = &mp_ioapic_irqdomain_ops,
};
ioapic_id = acpi_get_ioapic_id(handle, gsi_base, &addr);
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index ae693b5..8c35df4 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -62,7 +62,7 @@
pushfq
popq pt_regs_flags(%rax)
- movq $resume_point, saved_rip(%rip)
+ movq $.Lresume_point, saved_rip(%rip)
movq %rsp, saved_rsp
movq %rbp, saved_rbp
@@ -75,10 +75,10 @@
xorl %eax, %eax
call x86_acpi_enter_sleep_state
/* in case something went wrong, restore the machine status and go on */
- jmp resume_point
+ jmp .Lresume_point
.align 4
-resume_point:
+.Lresume_point:
/* We don't restore %rax, it must be 0 anyway */
movq $saved_context, %rax
movq saved_context_cr4(%rax), %rbx
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index aef6531..b0932c4 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -227,6 +227,15 @@
#endif
}
break;
+
+ case X86_VENDOR_AMD:
+ if (boot_cpu_data.x86 > 0xf) {
+ ideal_nops = p6_nops;
+ return;
+ }
+
+ /* fall through */
+
default:
#ifdef CONFIG_X86_64
ideal_nops = k8_nops;
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 6a7c23f..ede92c3 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -171,10 +171,6 @@
static void apbt_setup_irq(struct apbt_dev *adev)
{
- /* timer0 irq has been setup early */
- if (adev->irq == 0)
- return;
-
irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
}
diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c
index 816f36e..ae50d34 100644
--- a/arch/x86/kernel/apic/htirq.c
+++ b/arch/x86/kernel/apic/htirq.c
@@ -3,6 +3,8 @@
*
* Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
* Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ * Add support of hierarchical irqdomain
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -14,78 +16,112 @@
#include <linux/device.h>
#include <linux/pci.h>
#include <linux/htirq.h>
+#include <asm/irqdomain.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
#include <asm/hypertransport.h>
+static struct irq_domain *htirq_domain;
+
/*
* Hypertransport interrupt support
*/
-static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
-{
- struct ht_irq_msg msg;
-
- fetch_ht_irq_msg(irq, &msg);
-
- msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK);
- msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
-
- msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest);
- msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest);
-
- write_ht_irq_msg(irq, &msg);
-}
-
static int
ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- unsigned int dest;
+ struct irq_data *parent = data->parent_data;
int ret;
- ret = apic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
+ ret = parent->chip->irq_set_affinity(parent, mask, force);
+ if (ret >= 0) {
+ struct ht_irq_msg msg;
+ struct irq_cfg *cfg = irqd_cfg(data);
- target_ht_irq(data->irq, dest, cfg->vector);
- return IRQ_SET_MASK_OK_NOCOPY;
+ fetch_ht_irq_msg(data->irq, &msg);
+ msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK |
+ HT_IRQ_LOW_DEST_ID_MASK);
+ msg.address_lo |= HT_IRQ_LOW_VECTOR(cfg->vector) |
+ HT_IRQ_LOW_DEST_ID(cfg->dest_apicid);
+ msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
+ msg.address_hi |= HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
+ write_ht_irq_msg(data->irq, &msg);
+ }
+
+ return ret;
}
static struct irq_chip ht_irq_chip = {
.name = "PCI-HT",
.irq_mask = mask_ht_irq,
.irq_unmask = unmask_ht_irq,
- .irq_ack = apic_ack_edge,
+ .irq_ack = irq_chip_ack_parent,
.irq_set_affinity = ht_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
-int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
+static int htirq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
{
- struct irq_cfg *cfg;
+ struct ht_irq_cfg *ht_cfg;
+ struct irq_alloc_info *info = arg;
+ struct pci_dev *dev;
+ irq_hw_number_t hwirq;
+ int ret;
+
+ if (nr_irqs > 1 || !info)
+ return -EINVAL;
+
+ dev = info->ht_dev;
+ hwirq = (info->ht_idx & 0xFF) |
+ PCI_DEVID(dev->bus->number, dev->devfn) << 8 |
+ (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 24;
+ if (irq_find_mapping(domain, hwirq) > 0)
+ return -EEXIST;
+
+ ht_cfg = kmalloc(sizeof(*ht_cfg), GFP_KERNEL);
+ if (!ht_cfg)
+ return -ENOMEM;
+
+ ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
+ if (ret < 0) {
+ kfree(ht_cfg);
+ return ret;
+ }
+
+ /* Initialize msg to a value that will never match the first write. */
+ ht_cfg->msg.address_lo = 0xffffffff;
+ ht_cfg->msg.address_hi = 0xffffffff;
+ ht_cfg->dev = info->ht_dev;
+ ht_cfg->update = info->ht_update;
+ ht_cfg->pos = info->ht_pos;
+ ht_cfg->idx = 0x10 + (info->ht_idx * 2);
+ irq_domain_set_info(domain, virq, hwirq, &ht_irq_chip, ht_cfg,
+ handle_edge_irq, ht_cfg, "edge");
+
+ return 0;
+}
+
+static void htirq_domain_free(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs)
+{
+ struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+
+ BUG_ON(nr_irqs != 1);
+ kfree(irq_data->chip_data);
+ irq_domain_free_irqs_top(domain, virq, nr_irqs);
+}
+
+static void htirq_domain_activate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
struct ht_irq_msg msg;
- unsigned dest;
- int err;
+ struct irq_cfg *cfg = irqd_cfg(irq_data);
- if (disable_apic)
- return -ENXIO;
-
- cfg = irq_cfg(irq);
- err = assign_irq_vector(irq, cfg, apic->target_cpus());
- if (err)
- return err;
-
- err = apic->cpu_mask_to_apicid_and(cfg->domain,
- apic->target_cpus(), &dest);
- if (err)
- return err;
-
- msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest);
-
+ msg.address_hi = HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
msg.address_lo =
HT_IRQ_LOW_BASE |
- HT_IRQ_LOW_DEST_ID(dest) |
+ HT_IRQ_LOW_DEST_ID(cfg->dest_apicid) |
HT_IRQ_LOW_VECTOR(cfg->vector) |
((apic->irq_dest_mode == 0) ?
HT_IRQ_LOW_DM_PHYSICAL :
@@ -95,13 +131,56 @@
HT_IRQ_LOW_MT_FIXED :
HT_IRQ_LOW_MT_ARBITRATED) |
HT_IRQ_LOW_IRQ_MASKED;
+ write_ht_irq_msg(irq_data->irq, &msg);
+}
- write_ht_irq_msg(irq, &msg);
+static void htirq_domain_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ struct ht_irq_msg msg;
- irq_set_chip_and_handler_name(irq, &ht_irq_chip,
- handle_edge_irq, "edge");
+ memset(&msg, 0, sizeof(msg));
+ write_ht_irq_msg(irq_data->irq, &msg);
+}
- dev_dbg(&dev->dev, "irq %d for HT\n", irq);
+static const struct irq_domain_ops htirq_domain_ops = {
+ .alloc = htirq_domain_alloc,
+ .free = htirq_domain_free,
+ .activate = htirq_domain_activate,
+ .deactivate = htirq_domain_deactivate,
+};
- return 0;
+void arch_init_htirq_domain(struct irq_domain *parent)
+{
+ if (disable_apic)
+ return;
+
+ htirq_domain = irq_domain_add_tree(NULL, &htirq_domain_ops, NULL);
+ if (!htirq_domain)
+ pr_warn("failed to initialize irqdomain for HTIRQ.\n");
+ else
+ htirq_domain->parent = parent;
+}
+
+int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev,
+ ht_irq_update_t *update)
+{
+ struct irq_alloc_info info;
+
+ if (!htirq_domain)
+ return -ENOSYS;
+
+ init_irq_alloc_info(&info, NULL);
+ info.ht_idx = idx;
+ info.ht_pos = pos;
+ info.ht_dev = dev;
+ info.ht_update = update;
+
+ return irq_domain_alloc_irqs(htirq_domain, 1, dev_to_node(&dev->dev),
+ &info);
+}
+
+void arch_teardown_ht_irq(unsigned int irq)
+{
+ irq_domain_free_irqs(irq, 1);
}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index f4dc246..845dc0d 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -18,6 +18,16 @@
* and Rolf G. Tews
* for testing these extensively
* Paul Diefenbaugh : Added full ACPI support
+ *
+ * Historical information which is worth to be preserved:
+ *
+ * - SiS APIC rmw bug:
+ *
+ * We used to have a workaround for a bug in SiS chips which
+ * required to rewrite the index register for a read-modify-write
+ * operation as the chip lost the index information which was
+ * setup for the read already. We cache the data now, so that
+ * workaround has been removed.
*/
#include <linux/mm.h>
@@ -31,13 +41,13 @@
#include <linux/acpi.h>
#include <linux/module.h>
#include <linux/syscore_ops.h>
-#include <linux/irqdomain.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/jiffies.h> /* time_after() */
#include <linux/slab.h>
#include <linux/bootmem.h>
+#include <asm/irqdomain.h>
#include <asm/idle.h>
#include <asm/io.h>
#include <asm/smp.h>
@@ -63,27 +73,31 @@
#define for_each_ioapic_pin(idx, pin) \
for_each_ioapic((idx)) \
for_each_pin((idx), (pin))
-
#define for_each_irq_pin(entry, head) \
list_for_each_entry(entry, &head, list)
-/*
- * Is the SiS APIC rmw bug present ?
- * -1 = don't know, 0 = no, 1 = yes
- */
-int sis_apic_bug = -1;
-
static DEFINE_RAW_SPINLOCK(ioapic_lock);
static DEFINE_MUTEX(ioapic_mutex);
static unsigned int ioapic_dynirq_base;
static int ioapic_initialized;
-struct mp_pin_info {
+struct irq_pin_list {
+ struct list_head list;
+ int apic, pin;
+};
+
+struct mp_chip_data {
+ struct list_head irq_2_pin;
+ struct IO_APIC_route_entry entry;
int trigger;
int polarity;
- int node;
- int set;
u32 count;
+ bool isa_irq;
+};
+
+struct mp_ioapic_gsi {
+ u32 gsi_base;
+ u32 gsi_end;
};
static struct ioapic {
@@ -101,7 +115,6 @@
struct mp_ioapic_gsi gsi_config;
struct ioapic_domain_cfg irqdomain_cfg;
struct irq_domain *irqdomain;
- struct mp_pin_info *pin_info;
struct resource *iomem_res;
} ioapics[MAX_IO_APICS];
@@ -117,7 +130,7 @@
return ioapics[ioapic_idx].mp_config.apicaddr;
}
-struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx)
+static inline struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx)
{
return &ioapics[ioapic_idx].gsi_config;
}
@@ -129,11 +142,16 @@
return gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1;
}
-u32 mp_pin_to_gsi(int ioapic, int pin)
+static inline u32 mp_pin_to_gsi(int ioapic, int pin)
{
return mp_ioapic_gsi_routing(ioapic)->gsi_base + pin;
}
+static inline bool mp_is_legacy_irq(int irq)
+{
+ return irq >= 0 && irq < nr_legacy_irqs();
+}
+
/*
* Initialize all legacy IRQs and all pins on the first IOAPIC
* if we have legacy interrupt controller. Kernel boot option "pirq="
@@ -144,12 +162,7 @@
if (!nr_legacy_irqs())
return 0;
- return ioapic == 0 || (irq >= 0 && irq < nr_legacy_irqs());
-}
-
-static inline struct mp_pin_info *mp_pin_info(int ioapic_idx, int pin)
-{
- return ioapics[ioapic_idx].pin_info + pin;
+ return ioapic == 0 || mp_is_legacy_irq(irq);
}
static inline struct irq_domain *mp_ioapic_irqdomain(int ioapic)
@@ -216,16 +229,6 @@
panic("Max # of irq sources exceeded!!\n");
}
-struct irq_pin_list {
- struct list_head list;
- int apic, pin;
-};
-
-static struct irq_pin_list *alloc_irq_pin_list(int node)
-{
- return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node);
-}
-
static void alloc_ioapic_saved_registers(int idx)
{
size_t size;
@@ -247,8 +250,7 @@
int __init arch_early_ioapic_init(void)
{
- struct irq_cfg *cfg;
- int i, node = cpu_to_node(0);
+ int i;
if (!nr_legacy_irqs())
io_apic_irqs = ~0UL;
@@ -256,16 +258,6 @@
for_each_ioapic(i)
alloc_ioapic_saved_registers(i);
- /*
- * For legacy IRQ's, start with assigning irq0 to irq15 to
- * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's.
- */
- for (i = 0; i < nr_legacy_irqs(); i++) {
- cfg = alloc_irq_and_cfg_at(i, node);
- cfg->vector = IRQ0_VECTOR + i;
- cpumask_setall(cfg->domain);
- }
-
return 0;
}
@@ -283,7 +275,7 @@
+ (mpc_ioapic_addr(idx) & ~PAGE_MASK);
}
-void io_apic_eoi(unsigned int apic, unsigned int vector)
+static inline void io_apic_eoi(unsigned int apic, unsigned int vector)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
writel(vector, &io_apic->eoi);
@@ -296,7 +288,8 @@
return readl(&io_apic->data);
}
-void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+static void io_apic_write(unsigned int apic, unsigned int reg,
+ unsigned int value)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
@@ -304,21 +297,6 @@
writel(value, &io_apic->data);
}
-/*
- * Re-write a value: to be used for read-modify-write
- * cycles where the read already set up the index register.
- *
- * Older SiS APIC requires we rewrite the index register
- */
-void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
-{
- struct io_apic __iomem *io_apic = io_apic_base(apic);
-
- if (sis_apic_bug)
- writel(reg, &io_apic->index);
- writel(value, &io_apic->data);
-}
-
union entry_union {
struct { u32 w1, w2; };
struct IO_APIC_route_entry entry;
@@ -378,7 +356,7 @@
static void ioapic_mask_entry(int apic, int pin)
{
unsigned long flags;
- union entry_union eu = { .entry.mask = 1 };
+ union entry_union eu = { .entry.mask = IOAPIC_MASKED };
raw_spin_lock_irqsave(&ioapic_lock, flags);
io_apic_write(apic, 0x10 + 2*pin, eu.w1);
@@ -391,16 +369,17 @@
* shared ISA-space IRQs, so we have to support them. We are super
* fast in the common case, and fast for shared ISA-space IRQs.
*/
-static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
+static int __add_pin_to_irq_node(struct mp_chip_data *data,
+ int node, int apic, int pin)
{
struct irq_pin_list *entry;
/* don't allow duplicates */
- for_each_irq_pin(entry, cfg->irq_2_pin)
+ for_each_irq_pin(entry, data->irq_2_pin)
if (entry->apic == apic && entry->pin == pin)
return 0;
- entry = alloc_irq_pin_list(node);
+ entry = kzalloc_node(sizeof(struct irq_pin_list), GFP_ATOMIC, node);
if (!entry) {
pr_err("can not alloc irq_pin_list (%d,%d,%d)\n",
node, apic, pin);
@@ -408,16 +387,16 @@
}
entry->apic = apic;
entry->pin = pin;
+ list_add_tail(&entry->list, &data->irq_2_pin);
- list_add_tail(&entry->list, &cfg->irq_2_pin);
return 0;
}
-static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin)
+static void __remove_pin_from_irq(struct mp_chip_data *data, int apic, int pin)
{
struct irq_pin_list *tmp, *entry;
- list_for_each_entry_safe(entry, tmp, &cfg->irq_2_pin, list)
+ list_for_each_entry_safe(entry, tmp, &data->irq_2_pin, list)
if (entry->apic == apic && entry->pin == pin) {
list_del(&entry->list);
kfree(entry);
@@ -425,22 +404,23 @@
}
}
-static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
+static void add_pin_to_irq_node(struct mp_chip_data *data,
+ int node, int apic, int pin)
{
- if (__add_pin_to_irq_node(cfg, node, apic, pin))
+ if (__add_pin_to_irq_node(data, node, apic, pin))
panic("IO-APIC: failed to add irq-pin. Can not proceed\n");
}
/*
* Reroute an IRQ to a different pin.
*/
-static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node,
+static void __init replace_pin_at_irq_node(struct mp_chip_data *data, int node,
int oldapic, int oldpin,
int newapic, int newpin)
{
struct irq_pin_list *entry;
- for_each_irq_pin(entry, cfg->irq_2_pin) {
+ for_each_irq_pin(entry, data->irq_2_pin) {
if (entry->apic == oldapic && entry->pin == oldpin) {
entry->apic = newapic;
entry->pin = newpin;
@@ -450,32 +430,26 @@
}
/* old apic/pin didn't exist, so just add new ones */
- add_pin_to_irq_node(cfg, node, newapic, newpin);
+ add_pin_to_irq_node(data, node, newapic, newpin);
}
-static void __io_apic_modify_irq(struct irq_pin_list *entry,
- int mask_and, int mask_or,
- void (*final)(struct irq_pin_list *entry))
-{
- unsigned int reg, pin;
-
- pin = entry->pin;
- reg = io_apic_read(entry->apic, 0x10 + pin * 2);
- reg &= mask_and;
- reg |= mask_or;
- io_apic_modify(entry->apic, 0x10 + pin * 2, reg);
- if (final)
- final(entry);
-}
-
-static void io_apic_modify_irq(struct irq_cfg *cfg,
+static void io_apic_modify_irq(struct mp_chip_data *data,
int mask_and, int mask_or,
void (*final)(struct irq_pin_list *entry))
{
+ union entry_union eu;
struct irq_pin_list *entry;
- for_each_irq_pin(entry, cfg->irq_2_pin)
- __io_apic_modify_irq(entry, mask_and, mask_or, final);
+ eu.entry = data->entry;
+ eu.w1 &= mask_and;
+ eu.w1 |= mask_or;
+ data->entry = eu.entry;
+
+ for_each_irq_pin(entry, data->irq_2_pin) {
+ io_apic_write(entry->apic, 0x10 + 2 * entry->pin, eu.w1);
+ if (final)
+ final(entry);
+ }
}
static void io_apic_sync(struct irq_pin_list *entry)
@@ -490,39 +464,31 @@
readl(&io_apic->data);
}
-static void mask_ioapic(struct irq_cfg *cfg)
+static void mask_ioapic_irq(struct irq_data *irq_data)
{
+ struct mp_chip_data *data = irq_data->chip_data;
unsigned long flags;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
+ io_apic_modify_irq(data, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
-static void mask_ioapic_irq(struct irq_data *data)
+static void __unmask_ioapic(struct mp_chip_data *data)
{
- mask_ioapic(irqd_cfg(data));
+ io_apic_modify_irq(data, ~IO_APIC_REDIR_MASKED, 0, NULL);
}
-static void __unmask_ioapic(struct irq_cfg *cfg)
+static void unmask_ioapic_irq(struct irq_data *irq_data)
{
- io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
-}
-
-static void unmask_ioapic(struct irq_cfg *cfg)
-{
+ struct mp_chip_data *data = irq_data->chip_data;
unsigned long flags;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- __unmask_ioapic(cfg);
+ __unmask_ioapic(data);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
-static void unmask_ioapic_irq(struct irq_data *data)
-{
- unmask_ioapic(irqd_cfg(data));
-}
-
/*
* IO-APIC versions below 0x20 don't support EOI register.
* For the record, here is the information about various versions:
@@ -539,7 +505,7 @@
* Otherwise, we simulate the EOI message manually by changing the trigger
* mode to edge and then back to level, with RTE being masked during this.
*/
-void native_eoi_ioapic_pin(int apic, int pin, int vector)
+static void __eoi_ioapic_pin(int apic, int pin, int vector)
{
if (mpc_ioapic_ver(apic) >= 0x20) {
io_apic_eoi(apic, vector);
@@ -551,7 +517,7 @@
/*
* Mask the entry and change the trigger mode to edge.
*/
- entry1.mask = 1;
+ entry1.mask = IOAPIC_MASKED;
entry1.trigger = IOAPIC_EDGE;
__ioapic_write_entry(apic, pin, entry1);
@@ -563,15 +529,14 @@
}
}
-void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+void eoi_ioapic_pin(int vector, struct mp_chip_data *data)
{
- struct irq_pin_list *entry;
unsigned long flags;
+ struct irq_pin_list *entry;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- for_each_irq_pin(entry, cfg->irq_2_pin)
- x86_io_apic_ops.eoi_ioapic_pin(entry->apic, entry->pin,
- cfg->vector);
+ for_each_irq_pin(entry, data->irq_2_pin)
+ __eoi_ioapic_pin(entry->apic, entry->pin, vector);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
@@ -588,8 +553,8 @@
* Make sure the entry is masked and re-read the contents to check
* if it is a level triggered pin and if the remote-IRR is set.
*/
- if (!entry.mask) {
- entry.mask = 1;
+ if (entry.mask == IOAPIC_UNMASKED) {
+ entry.mask = IOAPIC_MASKED;
ioapic_write_entry(apic, pin, entry);
entry = ioapic_read_entry(apic, pin);
}
@@ -602,13 +567,12 @@
* doesn't clear the remote-IRR if the trigger mode is not
* set to level.
*/
- if (!entry.trigger) {
+ if (entry.trigger == IOAPIC_EDGE) {
entry.trigger = IOAPIC_LEVEL;
ioapic_write_entry(apic, pin, entry);
}
-
raw_spin_lock_irqsave(&ioapic_lock, flags);
- x86_io_apic_ops.eoi_ioapic_pin(apic, pin, entry.vector);
+ __eoi_ioapic_pin(apic, pin, entry.vector);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
@@ -706,8 +670,8 @@
struct IO_APIC_route_entry entry;
entry = ioapics[apic].saved_registers[pin];
- if (!entry.mask) {
- entry.mask = 1;
+ if (entry.mask == IOAPIC_UNMASKED) {
+ entry.mask = IOAPIC_MASKED;
ioapic_write_entry(apic, pin, entry);
}
}
@@ -809,11 +773,11 @@
#endif
-/* ISA interrupts are always polarity zero edge triggered,
+/* ISA interrupts are always active high edge triggered,
* when listed as conforming in the MP table. */
-#define default_ISA_trigger(idx) (0)
-#define default_ISA_polarity(idx) (0)
+#define default_ISA_trigger(idx) (IOAPIC_EDGE)
+#define default_ISA_polarity(idx) (IOAPIC_POL_HIGH)
/* EISA interrupts are always polarity zero and can be edge or level
* trigger depending on the ELCR value. If an interrupt is listed as
@@ -823,54 +787,56 @@
#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].srcbusirq))
#define default_EISA_polarity(idx) default_ISA_polarity(idx)
-/* PCI interrupts are always polarity one level triggered,
+/* PCI interrupts are always active low level triggered,
* when listed as conforming in the MP table. */
-#define default_PCI_trigger(idx) (1)
-#define default_PCI_polarity(idx) (1)
+#define default_PCI_trigger(idx) (IOAPIC_LEVEL)
+#define default_PCI_polarity(idx) (IOAPIC_POL_LOW)
static int irq_polarity(int idx)
{
int bus = mp_irqs[idx].srcbus;
- int polarity;
/*
* Determine IRQ line polarity (high active or low active):
*/
- switch (mp_irqs[idx].irqflag & 3)
- {
- case 0: /* conforms, ie. bus-type dependent polarity */
- if (test_bit(bus, mp_bus_not_pci))
- polarity = default_ISA_polarity(idx);
- else
- polarity = default_PCI_polarity(idx);
- break;
- case 1: /* high active */
- {
- polarity = 0;
- break;
- }
- case 2: /* reserved */
- {
- pr_warn("broken BIOS!!\n");
- polarity = 1;
- break;
- }
- case 3: /* low active */
- {
- polarity = 1;
- break;
- }
- default: /* invalid */
- {
- pr_warn("broken BIOS!!\n");
- polarity = 1;
- break;
- }
+ switch (mp_irqs[idx].irqflag & 0x03) {
+ case 0:
+ /* conforms to spec, ie. bus-type dependent polarity */
+ if (test_bit(bus, mp_bus_not_pci))
+ return default_ISA_polarity(idx);
+ else
+ return default_PCI_polarity(idx);
+ case 1:
+ return IOAPIC_POL_HIGH;
+ case 2:
+ pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n");
+ case 3:
+ default: /* Pointless default required due to do gcc stupidity */
+ return IOAPIC_POL_LOW;
}
- return polarity;
}
+#ifdef CONFIG_EISA
+static int eisa_irq_trigger(int idx, int bus, int trigger)
+{
+ switch (mp_bus_id_to_type[bus]) {
+ case MP_BUS_PCI:
+ case MP_BUS_ISA:
+ return trigger;
+ case MP_BUS_EISA:
+ return default_EISA_trigger(idx);
+ }
+ pr_warn("IOAPIC: Invalid srcbus: %d defaulting to level\n", bus);
+ return IOAPIC_LEVEL;
+}
+#else
+static inline int eisa_irq_trigger(int idx, int bus, int trigger)
+{
+ return trigger;
+}
+#endif
+
static int irq_trigger(int idx)
{
int bus = mp_irqs[idx].srcbus;
@@ -879,153 +845,227 @@
/*
* Determine IRQ trigger mode (edge or level sensitive):
*/
- switch ((mp_irqs[idx].irqflag>>2) & 3)
- {
- case 0: /* conforms, ie. bus-type dependent */
- if (test_bit(bus, mp_bus_not_pci))
- trigger = default_ISA_trigger(idx);
- else
- trigger = default_PCI_trigger(idx);
-#ifdef CONFIG_EISA
- switch (mp_bus_id_to_type[bus]) {
- case MP_BUS_ISA: /* ISA pin */
- {
- /* set before the switch */
- break;
- }
- case MP_BUS_EISA: /* EISA pin */
- {
- trigger = default_EISA_trigger(idx);
- break;
- }
- case MP_BUS_PCI: /* PCI pin */
- {
- /* set before the switch */
- break;
- }
- default:
- {
- pr_warn("broken BIOS!!\n");
- trigger = 1;
- break;
- }
- }
-#endif
- break;
- case 1: /* edge */
- {
- trigger = 0;
- break;
- }
- case 2: /* reserved */
- {
- pr_warn("broken BIOS!!\n");
- trigger = 1;
- break;
- }
- case 3: /* level */
- {
- trigger = 1;
- break;
- }
- default: /* invalid */
- {
- pr_warn("broken BIOS!!\n");
- trigger = 0;
- break;
- }
+ switch ((mp_irqs[idx].irqflag >> 2) & 0x03) {
+ case 0:
+ /* conforms to spec, ie. bus-type dependent trigger mode */
+ if (test_bit(bus, mp_bus_not_pci))
+ trigger = default_ISA_trigger(idx);
+ else
+ trigger = default_PCI_trigger(idx);
+ /* Take EISA into account */
+ return eisa_irq_trigger(idx, bus, trigger);
+ case 1:
+ return IOAPIC_EDGE;
+ case 2:
+ pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n");
+ case 3:
+ default: /* Pointless default required due to do gcc stupidity */
+ return IOAPIC_LEVEL;
}
- return trigger;
}
-static int alloc_irq_from_domain(struct irq_domain *domain, u32 gsi, int pin)
+void ioapic_set_alloc_attr(struct irq_alloc_info *info, int node,
+ int trigger, int polarity)
{
+ init_irq_alloc_info(info, NULL);
+ info->type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+ info->ioapic_node = node;
+ info->ioapic_trigger = trigger;
+ info->ioapic_polarity = polarity;
+ info->ioapic_valid = 1;
+}
+
+#ifndef CONFIG_ACPI
+int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity);
+#endif
+
+static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst,
+ struct irq_alloc_info *src,
+ u32 gsi, int ioapic_idx, int pin)
+{
+ int trigger, polarity;
+
+ copy_irq_alloc_info(dst, src);
+ dst->type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+ dst->ioapic_id = mpc_ioapic_id(ioapic_idx);
+ dst->ioapic_pin = pin;
+ dst->ioapic_valid = 1;
+ if (src && src->ioapic_valid) {
+ dst->ioapic_node = src->ioapic_node;
+ dst->ioapic_trigger = src->ioapic_trigger;
+ dst->ioapic_polarity = src->ioapic_polarity;
+ } else {
+ dst->ioapic_node = NUMA_NO_NODE;
+ if (acpi_get_override_irq(gsi, &trigger, &polarity) >= 0) {
+ dst->ioapic_trigger = trigger;
+ dst->ioapic_polarity = polarity;
+ } else {
+ /*
+ * PCI interrupts are always active low level
+ * triggered.
+ */
+ dst->ioapic_trigger = IOAPIC_LEVEL;
+ dst->ioapic_polarity = IOAPIC_POL_LOW;
+ }
+ }
+}
+
+static int ioapic_alloc_attr_node(struct irq_alloc_info *info)
+{
+ return (info && info->ioapic_valid) ? info->ioapic_node : NUMA_NO_NODE;
+}
+
+static void mp_register_handler(unsigned int irq, unsigned long trigger)
+{
+ irq_flow_handler_t hdl;
+ bool fasteoi;
+
+ if (trigger) {
+ irq_set_status_flags(irq, IRQ_LEVEL);
+ fasteoi = true;
+ } else {
+ irq_clear_status_flags(irq, IRQ_LEVEL);
+ fasteoi = false;
+ }
+
+ hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq;
+ __irq_set_handler(irq, hdl, 0, fasteoi ? "fasteoi" : "edge");
+}
+
+static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info)
+{
+ struct mp_chip_data *data = irq_get_chip_data(irq);
+
+ /*
+ * setup_IO_APIC_irqs() programs all legacy IRQs with default trigger
+ * and polarity attirbutes. So allow the first user to reprogram the
+ * pin with real trigger and polarity attributes.
+ */
+ if (irq < nr_legacy_irqs() && data->count == 1) {
+ if (info->ioapic_trigger != data->trigger)
+ mp_register_handler(irq, data->trigger);
+ data->entry.trigger = data->trigger = info->ioapic_trigger;
+ data->entry.polarity = data->polarity = info->ioapic_polarity;
+ }
+
+ return data->trigger == info->ioapic_trigger &&
+ data->polarity == info->ioapic_polarity;
+}
+
+static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi,
+ struct irq_alloc_info *info)
+{
+ bool legacy = false;
int irq = -1;
- int ioapic = (int)(long)domain->host_data;
int type = ioapics[ioapic].irqdomain_cfg.type;
switch (type) {
case IOAPIC_DOMAIN_LEGACY:
/*
- * Dynamically allocate IRQ number for non-ISA IRQs in the first 16
- * GSIs on some weird platforms.
+ * Dynamically allocate IRQ number for non-ISA IRQs in the first
+ * 16 GSIs on some weird platforms.
*/
- if (gsi < nr_legacy_irqs())
- irq = irq_create_mapping(domain, pin);
- else if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0)
+ if (!ioapic_initialized || gsi >= nr_legacy_irqs())
irq = gsi;
+ legacy = mp_is_legacy_irq(irq);
break;
case IOAPIC_DOMAIN_STRICT:
- if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0)
- irq = gsi;
+ irq = gsi;
break;
case IOAPIC_DOMAIN_DYNAMIC:
- irq = irq_create_mapping(domain, pin);
break;
default:
WARN(1, "ioapic: unknown irqdomain type %d\n", type);
- break;
+ return -1;
}
- return irq > 0 ? irq : -1;
+ return __irq_domain_alloc_irqs(domain, irq, 1,
+ ioapic_alloc_attr_node(info),
+ info, legacy);
+}
+
+/*
+ * Need special handling for ISA IRQs because there may be multiple IOAPIC pins
+ * sharing the same ISA IRQ number and irqdomain only supports 1:1 mapping
+ * between IOAPIC pin and IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are
+ * used for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H).
+ * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are available, and
+ * some BIOSes may use MP Interrupt Source records to override IRQ numbers for
+ * PIRQs instead of reprogramming the interrupt routing logic. Thus there may be
+ * multiple pins sharing the same legacy IRQ number when ACPI is disabled.
+ */
+static int alloc_isa_irq_from_domain(struct irq_domain *domain,
+ int irq, int ioapic, int pin,
+ struct irq_alloc_info *info)
+{
+ struct mp_chip_data *data;
+ struct irq_data *irq_data = irq_get_irq_data(irq);
+ int node = ioapic_alloc_attr_node(info);
+
+ /*
+ * Legacy ISA IRQ has already been allocated, just add pin to
+ * the pin list assoicated with this IRQ and program the IOAPIC
+ * entry. The IOAPIC entry
+ */
+ if (irq_data && irq_data->parent_data) {
+ if (!mp_check_pin_attr(irq, info))
+ return -EBUSY;
+ if (__add_pin_to_irq_node(irq_data->chip_data, node, ioapic,
+ info->ioapic_pin))
+ return -ENOMEM;
+ } else {
+ irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true);
+ if (irq >= 0) {
+ irq_data = irq_domain_get_irq_data(domain, irq);
+ data = irq_data->chip_data;
+ data->isa_irq = true;
+ }
+ }
+
+ return irq;
}
static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin,
- unsigned int flags)
+ unsigned int flags, struct irq_alloc_info *info)
{
int irq;
+ bool legacy = false;
+ struct irq_alloc_info tmp;
+ struct mp_chip_data *data;
struct irq_domain *domain = mp_ioapic_irqdomain(ioapic);
- struct mp_pin_info *info = mp_pin_info(ioapic, pin);
if (!domain)
- return -1;
+ return -ENOSYS;
- mutex_lock(&ioapic_mutex);
-
- /*
- * Don't use irqdomain to manage ISA IRQs because there may be
- * multiple IOAPIC pins sharing the same ISA IRQ number and
- * irqdomain only supports 1:1 mapping between IOAPIC pin and
- * IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are used
- * for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H).
- * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are
- * available, and some BIOSes may use MP Interrupt Source records
- * to override IRQ numbers for PIRQs instead of reprogramming
- * the interrupt routing logic. Thus there may be multiple pins
- * sharing the same legacy IRQ number when ACPI is disabled.
- */
if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) {
irq = mp_irqs[idx].srcbusirq;
- if (flags & IOAPIC_MAP_ALLOC) {
- if (info->count == 0 &&
- mp_irqdomain_map(domain, irq, pin) != 0)
- irq = -1;
+ legacy = mp_is_legacy_irq(irq);
+ }
- /* special handling for timer IRQ0 */
+ mutex_lock(&ioapic_mutex);
+ if (!(flags & IOAPIC_MAP_ALLOC)) {
+ if (!legacy) {
+ irq = irq_find_mapping(domain, pin);
if (irq == 0)
- info->count++;
+ irq = -ENOENT;
}
} else {
- irq = irq_find_mapping(domain, pin);
- if (irq <= 0 && (flags & IOAPIC_MAP_ALLOC))
- irq = alloc_irq_from_domain(domain, gsi, pin);
+ ioapic_copy_alloc_attr(&tmp, info, gsi, ioapic, pin);
+ if (legacy)
+ irq = alloc_isa_irq_from_domain(domain, irq,
+ ioapic, pin, &tmp);
+ else if ((irq = irq_find_mapping(domain, pin)) == 0)
+ irq = alloc_irq_from_domain(domain, ioapic, gsi, &tmp);
+ else if (!mp_check_pin_attr(irq, &tmp))
+ irq = -EBUSY;
+ if (irq >= 0) {
+ data = irq_get_chip_data(irq);
+ data->count++;
+ }
}
-
- if (flags & IOAPIC_MAP_ALLOC) {
- /* special handling for legacy IRQs */
- if (irq < nr_legacy_irqs() && info->count == 1 &&
- mp_irqdomain_map(domain, irq, pin) != 0)
- irq = -1;
-
- if (irq > 0)
- info->count++;
- else if (info->count == 0)
- info->set = 0;
- }
-
mutex_unlock(&ioapic_mutex);
- return irq > 0 ? irq : -1;
+ return irq;
}
static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags)
@@ -1058,10 +1098,10 @@
}
#endif
- return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags);
+ return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, NULL);
}
-int mp_map_gsi_to_irq(u32 gsi, unsigned int flags)
+int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, struct irq_alloc_info *info)
{
int ioapic, pin, idx;
@@ -1074,31 +1114,24 @@
if ((flags & IOAPIC_MAP_CHECK) && idx < 0)
return -1;
- return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags);
+ return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, info);
}
void mp_unmap_irq(int irq)
{
- struct irq_data *data = irq_get_irq_data(irq);
- struct mp_pin_info *info;
- int ioapic, pin;
+ struct irq_data *irq_data = irq_get_irq_data(irq);
+ struct mp_chip_data *data;
- if (!data || !data->domain)
+ if (!irq_data || !irq_data->domain)
return;
- ioapic = (int)(long)data->domain->host_data;
- pin = (int)data->hwirq;
- info = mp_pin_info(ioapic, pin);
+ data = irq_data->chip_data;
+ if (!data || data->isa_irq)
+ return;
mutex_lock(&ioapic_mutex);
- if (--info->count == 0) {
- info->set = 0;
- if (irq < nr_legacy_irqs() &&
- ioapics[ioapic].irqdomain_cfg.type == IOAPIC_DOMAIN_LEGACY)
- mp_irqdomain_unmap(data->domain, irq);
- else
- irq_dispose_mapping(irq);
- }
+ if (--data->count == 0)
+ irq_domain_free_irqs(irq, 1);
mutex_unlock(&ioapic_mutex);
}
@@ -1165,7 +1198,7 @@
}
EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
-static struct irq_chip ioapic_chip;
+static struct irq_chip ioapic_chip, ioapic_ir_chip;
#ifdef CONFIG_X86_32
static inline int IO_APIC_irq_trigger(int irq)
@@ -1189,96 +1222,6 @@
}
#endif
-static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg,
- unsigned long trigger)
-{
- struct irq_chip *chip = &ioapic_chip;
- irq_flow_handler_t hdl;
- bool fasteoi;
-
- if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
- trigger == IOAPIC_LEVEL) {
- irq_set_status_flags(irq, IRQ_LEVEL);
- fasteoi = true;
- } else {
- irq_clear_status_flags(irq, IRQ_LEVEL);
- fasteoi = false;
- }
-
- if (setup_remapped_irq(irq, cfg, chip))
- fasteoi = trigger != 0;
-
- hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq;
- irq_set_chip_and_handler_name(irq, chip, hdl,
- fasteoi ? "fasteoi" : "edge");
-}
-
-int native_setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
- unsigned int destination, int vector,
- struct io_apic_irq_attr *attr)
-{
- memset(entry, 0, sizeof(*entry));
-
- entry->delivery_mode = apic->irq_delivery_mode;
- entry->dest_mode = apic->irq_dest_mode;
- entry->dest = destination;
- entry->vector = vector;
- entry->mask = 0; /* enable IRQ */
- entry->trigger = attr->trigger;
- entry->polarity = attr->polarity;
-
- /*
- * Mask level triggered irqs.
- * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
- */
- if (attr->trigger)
- entry->mask = 1;
-
- return 0;
-}
-
-static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg,
- struct io_apic_irq_attr *attr)
-{
- struct IO_APIC_route_entry entry;
- unsigned int dest;
-
- if (!IO_APIC_IRQ(irq))
- return;
-
- if (assign_irq_vector(irq, cfg, apic->target_cpus()))
- return;
-
- if (apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus(),
- &dest)) {
- pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n",
- mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
- clear_irq_vector(irq, cfg);
-
- return;
- }
-
- apic_printk(APIC_VERBOSE,KERN_DEBUG
- "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> "
- "IRQ %d Mode:%i Active:%i Dest:%d)\n",
- attr->ioapic, mpc_ioapic_id(attr->ioapic), attr->ioapic_pin,
- cfg->vector, irq, attr->trigger, attr->polarity, dest);
-
- if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) {
- pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n",
- mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
- clear_irq_vector(irq, cfg);
-
- return;
- }
-
- ioapic_register_intr(irq, cfg, attr->trigger);
- if (irq < nr_legacy_irqs())
- legacy_pic->mask(irq);
-
- ioapic_write_entry(attr->ioapic, attr->ioapic_pin, entry);
-}
-
static void __init setup_IO_APIC_irqs(void)
{
unsigned int ioapic, pin;
@@ -1298,106 +1241,41 @@
}
}
-/*
- * Set up the timer pin, possibly with the 8259A-master behind.
- */
-static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx,
- unsigned int pin, int vector)
-{
- struct IO_APIC_route_entry entry;
- unsigned int dest;
-
- memset(&entry, 0, sizeof(entry));
-
- /*
- * We use logical delivery to get the timer IRQ
- * to the first CPU.
- */
- if (unlikely(apic->cpu_mask_to_apicid_and(apic->target_cpus(),
- apic->target_cpus(), &dest)))
- dest = BAD_APICID;
-
- entry.dest_mode = apic->irq_dest_mode;
- entry.mask = 0; /* don't mask IRQ for edge */
- entry.dest = dest;
- entry.delivery_mode = apic->irq_delivery_mode;
- entry.polarity = 0;
- entry.trigger = 0;
- entry.vector = vector;
-
- /*
- * The timer IRQ doesn't have to know that behind the
- * scene we may have a 8259A-master in AEOI mode ...
- */
- irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
- "edge");
-
- /*
- * Add it to the IO-APIC irq-routing table:
- */
- ioapic_write_entry(ioapic_idx, pin, entry);
-}
-
-void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries)
-{
- int i;
-
- pr_debug(" NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect:\n");
-
- for (i = 0; i <= nr_entries; i++) {
- struct IO_APIC_route_entry entry;
-
- entry = ioapic_read_entry(apic, i);
-
- pr_debug(" %02x %02X ", i, entry.dest);
- pr_cont("%1d %1d %1d %1d %1d "
- "%1d %1d %02X\n",
- entry.mask,
- entry.trigger,
- entry.irr,
- entry.polarity,
- entry.delivery_status,
- entry.dest_mode,
- entry.delivery_mode,
- entry.vector);
- }
-}
-
-void intel_ir_io_apic_print_entries(unsigned int apic,
- unsigned int nr_entries)
-{
- int i;
-
- pr_debug(" NR Indx Fmt Mask Trig IRR Pol Stat Indx2 Zero Vect:\n");
-
- for (i = 0; i <= nr_entries; i++) {
- struct IR_IO_APIC_route_entry *ir_entry;
- struct IO_APIC_route_entry entry;
-
- entry = ioapic_read_entry(apic, i);
-
- ir_entry = (struct IR_IO_APIC_route_entry *)&entry;
-
- pr_debug(" %02x %04X ", i, ir_entry->index);
- pr_cont("%1d %1d %1d %1d %1d "
- "%1d %1d %X %02X\n",
- ir_entry->format,
- ir_entry->mask,
- ir_entry->trigger,
- ir_entry->irr,
- ir_entry->polarity,
- ir_entry->delivery_status,
- ir_entry->index2,
- ir_entry->zero,
- ir_entry->vector);
- }
-}
-
void ioapic_zap_locks(void)
{
raw_spin_lock_init(&ioapic_lock);
}
+static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries)
+{
+ int i;
+ char buf[256];
+ struct IO_APIC_route_entry entry;
+ struct IR_IO_APIC_route_entry *ir_entry = (void *)&entry;
+
+ printk(KERN_DEBUG "IOAPIC %d:\n", apic);
+ for (i = 0; i <= nr_entries; i++) {
+ entry = ioapic_read_entry(apic, i);
+ snprintf(buf, sizeof(buf),
+ " pin%02x, %s, %s, %s, V(%02X), IRR(%1d), S(%1d)",
+ i,
+ entry.mask == IOAPIC_MASKED ? "disabled" : "enabled ",
+ entry.trigger == IOAPIC_LEVEL ? "level" : "edge ",
+ entry.polarity == IOAPIC_POL_LOW ? "low " : "high",
+ entry.vector, entry.irr, entry.delivery_status);
+ if (ir_entry->format)
+ printk(KERN_DEBUG "%s, remapped, I(%04X), Z(%X)\n",
+ buf, (ir_entry->index << 15) | ir_entry->index,
+ ir_entry->zero);
+ else
+ printk(KERN_DEBUG "%s, %s, D(%02X), M(%1d)\n",
+ buf,
+ entry.dest_mode == IOAPIC_DEST_MODE_LOGICAL ?
+ "logical " : "physical",
+ entry.dest, entry.delivery_mode);
+ }
+}
+
static void __init print_IO_APIC(int ioapic_idx)
{
union IO_APIC_reg_00 reg_00;
@@ -1451,16 +1329,13 @@
}
printk(KERN_DEBUG ".... IRQ redirection table:\n");
-
- x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries);
+ io_apic_print_entries(ioapic_idx, reg_01.bits.entries);
}
void __init print_IO_APICs(void)
{
int ioapic_idx;
- struct irq_cfg *cfg;
unsigned int irq;
- struct irq_chip *chip;
printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
for_each_ioapic(ioapic_idx)
@@ -1480,18 +1355,20 @@
printk(KERN_DEBUG "IRQ to pin mappings:\n");
for_each_active_irq(irq) {
struct irq_pin_list *entry;
+ struct irq_chip *chip;
+ struct mp_chip_data *data;
chip = irq_get_chip(irq);
- if (chip != &ioapic_chip)
+ if (chip != &ioapic_chip && chip != &ioapic_ir_chip)
+ continue;
+ data = irq_get_chip_data(irq);
+ if (!data)
+ continue;
+ if (list_empty(&data->irq_2_pin))
continue;
- cfg = irq_cfg(irq);
- if (!cfg)
- continue;
- if (list_empty(&cfg->irq_2_pin))
- continue;
printk(KERN_DEBUG "IRQ%d ", irq);
- for_each_irq_pin(entry, cfg->irq_2_pin)
+ for_each_irq_pin(entry, data->irq_2_pin)
pr_cont("-> %d:%d", entry->apic, entry->pin);
pr_cont("\n");
}
@@ -1564,15 +1441,12 @@
struct IO_APIC_route_entry entry;
memset(&entry, 0, sizeof(entry));
- entry.mask = 0; /* Enabled */
- entry.trigger = 0; /* Edge */
- entry.irr = 0;
- entry.polarity = 0; /* High */
- entry.delivery_status = 0;
- entry.dest_mode = 0; /* Physical */
- entry.delivery_mode = dest_ExtINT; /* ExtInt */
- entry.vector = 0;
- entry.dest = read_apic_id();
+ entry.mask = IOAPIC_UNMASKED;
+ entry.trigger = IOAPIC_EDGE;
+ entry.polarity = IOAPIC_POL_HIGH;
+ entry.dest_mode = IOAPIC_DEST_MODE_PHYSICAL;
+ entry.delivery_mode = dest_ExtINT;
+ entry.dest = read_apic_id();
/*
* Add it to the IO-APIC irq-routing table:
@@ -1582,7 +1456,6 @@
if (cpu_has_apic || apic_from_smp_config())
disconnect_bsp_APIC(ioapic_i8259.pin != -1);
-
}
/*
@@ -1792,7 +1665,6 @@
* This is not complete - we should be able to fake
* an edge even if it isn't on the 8259A...
*/
-
static unsigned int startup_ioapic_irq(struct irq_data *data)
{
int was_pending = 0, irq = data->irq;
@@ -1804,74 +1676,22 @@
if (legacy_pic->irq_pending(irq))
was_pending = 1;
}
- __unmask_ioapic(irqd_cfg(data));
+ __unmask_ioapic(data->chip_data);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
return was_pending;
}
-/*
- * Level and edge triggered IO-APIC interrupts need different handling,
- * so we use two separate IRQ descriptors. Edge triggered IRQs can be
- * handled with the level-triggered descriptor, but that one has slightly
- * more overhead. Level-triggered interrupts cannot be handled with the
- * edge-triggered handler, without risking IRQ storms and other ugly
- * races.
- */
-
-static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
-{
- int apic, pin;
- struct irq_pin_list *entry;
- u8 vector = cfg->vector;
-
- for_each_irq_pin(entry, cfg->irq_2_pin) {
- unsigned int reg;
-
- apic = entry->apic;
- pin = entry->pin;
-
- io_apic_write(apic, 0x11 + pin*2, dest);
- reg = io_apic_read(apic, 0x10 + pin*2);
- reg &= ~IO_APIC_REDIR_VECTOR_MASK;
- reg |= vector;
- io_apic_modify(apic, 0x10 + pin*2, reg);
- }
-}
-
-int native_ioapic_set_affinity(struct irq_data *data,
- const struct cpumask *mask,
- bool force)
-{
- unsigned int dest, irq = data->irq;
- unsigned long flags;
- int ret;
-
- if (!config_enabled(CONFIG_SMP))
- return -EPERM;
-
- raw_spin_lock_irqsave(&ioapic_lock, flags);
- ret = apic_set_affinity(data, mask, &dest);
- if (!ret) {
- /* Only the high 8 bits are valid. */
- dest = SET_APIC_LOGICAL_ID(dest);
- __target_IO_APIC_irq(irq, dest, irqd_cfg(data));
- ret = IRQ_SET_MASK_OK_NOCOPY;
- }
- raw_spin_unlock_irqrestore(&ioapic_lock, flags);
- return ret;
-}
-
atomic_t irq_mis_count;
#ifdef CONFIG_GENERIC_PENDING_IRQ
-static bool io_apic_level_ack_pending(struct irq_cfg *cfg)
+static bool io_apic_level_ack_pending(struct mp_chip_data *data)
{
struct irq_pin_list *entry;
unsigned long flags;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- for_each_irq_pin(entry, cfg->irq_2_pin) {
+ for_each_irq_pin(entry, data->irq_2_pin) {
unsigned int reg;
int pin;
@@ -1888,18 +1708,17 @@
return false;
}
-static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+static inline bool ioapic_irqd_mask(struct irq_data *data)
{
/* If we are moving the irq we need to mask it */
if (unlikely(irqd_is_setaffinity_pending(data))) {
- mask_ioapic(cfg);
+ mask_ioapic_irq(data);
return true;
}
return false;
}
-static inline void ioapic_irqd_unmask(struct irq_data *data,
- struct irq_cfg *cfg, bool masked)
+static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
{
if (unlikely(masked)) {
/* Only migrate the irq if the ack has been received.
@@ -1928,31 +1747,30 @@
* accurate and is causing problems then it is a hardware bug
* and you can go talk to the chipset vendor about it.
*/
- if (!io_apic_level_ack_pending(cfg))
+ if (!io_apic_level_ack_pending(data->chip_data))
irq_move_masked_irq(data);
- unmask_ioapic(cfg);
+ unmask_ioapic_irq(data);
}
}
#else
-static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+static inline bool ioapic_irqd_mask(struct irq_data *data)
{
return false;
}
-static inline void ioapic_irqd_unmask(struct irq_data *data,
- struct irq_cfg *cfg, bool masked)
+static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
{
}
#endif
-static void ack_ioapic_level(struct irq_data *data)
+static void ioapic_ack_level(struct irq_data *irq_data)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- int i, irq = data->irq;
+ struct irq_cfg *cfg = irqd_cfg(irq_data);
unsigned long v;
bool masked;
+ int i;
irq_complete_move(cfg);
- masked = ioapic_irqd_mask(data, cfg);
+ masked = ioapic_irqd_mask(irq_data);
/*
* It appears there is an erratum which affects at least version 0x11
@@ -2004,11 +1822,49 @@
*/
if (!(v & (1 << (i & 0x1f)))) {
atomic_inc(&irq_mis_count);
-
- eoi_ioapic_irq(irq, cfg);
+ eoi_ioapic_pin(cfg->vector, irq_data->chip_data);
}
- ioapic_irqd_unmask(data, cfg, masked);
+ ioapic_irqd_unmask(irq_data, masked);
+}
+
+static void ioapic_ir_ack_level(struct irq_data *irq_data)
+{
+ struct mp_chip_data *data = irq_data->chip_data;
+
+ /*
+ * Intr-remapping uses pin number as the virtual vector
+ * in the RTE. Actual vector is programmed in
+ * intr-remapping table entry. Hence for the io-apic
+ * EOI we use the pin number.
+ */
+ ack_APIC_irq();
+ eoi_ioapic_pin(data->entry.vector, data);
+}
+
+static int ioapic_set_affinity(struct irq_data *irq_data,
+ const struct cpumask *mask, bool force)
+{
+ struct irq_data *parent = irq_data->parent_data;
+ struct mp_chip_data *data = irq_data->chip_data;
+ struct irq_pin_list *entry;
+ struct irq_cfg *cfg;
+ unsigned long flags;
+ int ret;
+
+ ret = parent->chip->irq_set_affinity(parent, mask, force);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
+ if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) {
+ cfg = irqd_cfg(irq_data);
+ data->entry.dest = cfg->dest_apicid;
+ data->entry.vector = cfg->vector;
+ for_each_irq_pin(entry, data->irq_2_pin)
+ __ioapic_write_entry(entry->apic, entry->pin,
+ data->entry);
+ }
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+
+ return ret;
}
static struct irq_chip ioapic_chip __read_mostly = {
@@ -2016,10 +1872,20 @@
.irq_startup = startup_ioapic_irq,
.irq_mask = mask_ioapic_irq,
.irq_unmask = unmask_ioapic_irq,
- .irq_ack = apic_ack_edge,
- .irq_eoi = ack_ioapic_level,
- .irq_set_affinity = native_ioapic_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_eoi = ioapic_ack_level,
+ .irq_set_affinity = ioapic_set_affinity,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
+};
+
+static struct irq_chip ioapic_ir_chip __read_mostly = {
+ .name = "IR-IO-APIC",
+ .irq_startup = startup_ioapic_irq,
+ .irq_mask = mask_ioapic_irq,
+ .irq_unmask = unmask_ioapic_irq,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_eoi = ioapic_ir_ack_level,
+ .irq_set_affinity = ioapic_set_affinity,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
@@ -2113,12 +1979,12 @@
memset(&entry1, 0, sizeof(entry1));
- entry1.dest_mode = 0; /* physical delivery */
- entry1.mask = 0; /* unmask IRQ now */
+ entry1.dest_mode = IOAPIC_DEST_MODE_PHYSICAL;
+ entry1.mask = IOAPIC_UNMASKED;
entry1.dest = hard_smp_processor_id();
entry1.delivery_mode = dest_ExtINT;
entry1.polarity = entry0.polarity;
- entry1.trigger = 0;
+ entry1.trigger = IOAPIC_EDGE;
entry1.vector = 0;
ioapic_write_entry(apic, pin, entry1);
@@ -2152,6 +2018,25 @@
}
early_param("disable_timer_pin_1", disable_timer_pin_setup);
+static int mp_alloc_timer_irq(int ioapic, int pin)
+{
+ int irq = -1;
+ struct irq_domain *domain = mp_ioapic_irqdomain(ioapic);
+
+ if (domain) {
+ struct irq_alloc_info info;
+
+ ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 0, 0);
+ info.ioapic_id = mpc_ioapic_id(ioapic);
+ info.ioapic_pin = pin;
+ mutex_lock(&ioapic_mutex);
+ irq = alloc_isa_irq_from_domain(domain, 0, ioapic, pin, &info);
+ mutex_unlock(&ioapic_mutex);
+ }
+
+ return irq;
+}
+
/*
* This code may look a bit paranoid, but it's supposed to cooperate with
* a wide range of boards and BIOS bugs. Fortunately only the timer IRQ
@@ -2162,7 +2047,9 @@
*/
static inline void __init check_timer(void)
{
- struct irq_cfg *cfg = irq_cfg(0);
+ struct irq_data *irq_data = irq_get_irq_data(0);
+ struct mp_chip_data *data = irq_data->chip_data;
+ struct irq_cfg *cfg = irqd_cfg(irq_data);
int node = cpu_to_node(0);
int apic1, pin1, apic2, pin2;
unsigned long flags;
@@ -2174,7 +2061,6 @@
* get/set the timer IRQ vector:
*/
legacy_pic->mask(0);
- assign_irq_vector(0, cfg, apic->target_cpus());
/*
* As IRQ0 is to be enabled in the 8259A, the virtual
@@ -2215,23 +2101,21 @@
}
if (pin1 != -1) {
- /*
- * Ok, does IRQ0 through the IOAPIC work?
- */
+ /* Ok, does IRQ0 through the IOAPIC work? */
if (no_pin1) {
- add_pin_to_irq_node(cfg, node, apic1, pin1);
- setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
+ mp_alloc_timer_irq(apic1, pin1);
} else {
- /* for edge trigger, setup_ioapic_irq already
- * leave it unmasked.
+ /*
+ * for edge trigger, it's already unmasked,
* so only need to unmask if it is level-trigger
* do we really have level trigger timer?
*/
int idx;
idx = find_irq_entry(apic1, pin1, mp_INT);
if (idx != -1 && irq_trigger(idx))
- unmask_ioapic(cfg);
+ unmask_ioapic_irq(irq_get_chip_data(0));
}
+ irq_domain_activate_irq(irq_data);
if (timer_irq_works()) {
if (disable_timer_pin_1 > 0)
clear_IO_APIC_pin(0, pin1);
@@ -2251,8 +2135,8 @@
/*
* legacy devices should be connected to IO APIC #0
*/
- replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
- setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
+ replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2);
+ irq_domain_activate_irq(irq_data);
legacy_pic->unmask(0);
if (timer_irq_works()) {
apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
@@ -2329,36 +2213,35 @@
static int mp_irqdomain_create(int ioapic)
{
- size_t size;
+ struct irq_alloc_info info;
+ struct irq_domain *parent;
int hwirqs = mp_ioapic_pin_count(ioapic);
struct ioapic *ip = &ioapics[ioapic];
struct ioapic_domain_cfg *cfg = &ip->irqdomain_cfg;
struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic);
- size = sizeof(struct mp_pin_info) * mp_ioapic_pin_count(ioapic);
- ip->pin_info = kzalloc(size, GFP_KERNEL);
- if (!ip->pin_info)
- return -ENOMEM;
-
if (cfg->type == IOAPIC_DOMAIN_INVALID)
return 0;
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+ info.ioapic_id = mpc_ioapic_id(ioapic);
+ parent = irq_remapping_get_ir_irq_domain(&info);
+ if (!parent)
+ parent = x86_vector_domain;
+
ip->irqdomain = irq_domain_add_linear(cfg->dev, hwirqs, cfg->ops,
(void *)(long)ioapic);
- if(!ip->irqdomain) {
- kfree(ip->pin_info);
- ip->pin_info = NULL;
+ if (!ip->irqdomain)
return -ENOMEM;
- }
+
+ ip->irqdomain->parent = parent;
if (cfg->type == IOAPIC_DOMAIN_LEGACY ||
cfg->type == IOAPIC_DOMAIN_STRICT)
ioapic_dynirq_base = max(ioapic_dynirq_base,
gsi_cfg->gsi_end + 1);
- if (gsi_cfg->gsi_base == 0)
- irq_set_default_host(ip->irqdomain);
-
return 0;
}
@@ -2368,8 +2251,6 @@
irq_domain_remove(ioapics[idx].irqdomain);
ioapics[idx].irqdomain = NULL;
}
- kfree(ioapics[idx].pin_info);
- ioapics[idx].pin_info = NULL;
}
void __init setup_IO_APIC(void)
@@ -2399,20 +2280,6 @@
ioapic_initialized = 1;
}
-/*
- * Called after all the initialization is done. If we didn't find any
- * APIC bugs then we can allow the modify fast path
- */
-
-static int __init io_apic_bug_finalize(void)
-{
- if (sis_apic_bug == -1)
- sis_apic_bug = 0;
- return 0;
-}
-
-late_initcall(io_apic_bug_finalize);
-
static void resume_ioapic_id(int ioapic_idx)
{
unsigned long flags;
@@ -2451,20 +2318,6 @@
device_initcall(ioapic_init_ops);
-static int
-io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
-{
- struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node);
- int ret;
-
- if (!cfg)
- return -EINVAL;
- ret = __add_pin_to_irq_node(cfg, node, attr->ioapic, attr->ioapic_pin);
- if (!ret)
- setup_ioapic_irq(irq, cfg, attr);
- return ret;
-}
-
static int io_apic_get_redir_entries(int ioapic)
{
union IO_APIC_reg_01 reg_01;
@@ -2692,7 +2545,7 @@
else
mask = apic->target_cpus();
- x86_io_apic_ops.set_affinity(idata, mask, false);
+ irq_set_affinity(irq, mask);
}
}
@@ -2737,7 +2590,7 @@
return res;
}
-void __init native_io_apic_init_mappings(void)
+void __init io_apic_init_mappings(void)
{
unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
struct resource *ioapic_res;
@@ -2962,7 +2815,6 @@
{
int ioapic, pin;
int found = 0;
- struct mp_pin_info *pin_info;
for_each_ioapic(ioapic)
if (ioapics[ioapic].gsi_config.gsi_base == gsi_base) {
@@ -2975,11 +2827,17 @@
}
for_each_pin(ioapic, pin) {
- pin_info = mp_pin_info(ioapic, pin);
- if (pin_info->count) {
- pr_warn("pin%d on IOAPIC%d is still in use.\n",
- pin, ioapic);
- return -EBUSY;
+ u32 gsi = mp_pin_to_gsi(ioapic, pin);
+ int irq = mp_map_gsi_to_irq(gsi, 0, NULL);
+ struct mp_chip_data *data;
+
+ if (irq >= 0) {
+ data = irq_get_chip_data(irq);
+ if (data && data->count) {
+ pr_warn("pin%d on IOAPIC%d is still in use.\n",
+ pin, ioapic);
+ return -EBUSY;
+ }
}
}
@@ -3006,108 +2864,141 @@
return 0;
}
-static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
- int ioapic, int ioapic_pin,
- int trigger, int polarity)
+static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data,
+ struct irq_alloc_info *info)
{
- irq_attr->ioapic = ioapic;
- irq_attr->ioapic_pin = ioapic_pin;
- irq_attr->trigger = trigger;
- irq_attr->polarity = polarity;
-}
-
-int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
- irq_hw_number_t hwirq)
-{
- int ioapic = (int)(long)domain->host_data;
- struct mp_pin_info *info = mp_pin_info(ioapic, hwirq);
- struct io_apic_irq_attr attr;
-
- /* Get default attribute if not set by caller yet */
- if (!info->set) {
- u32 gsi = mp_pin_to_gsi(ioapic, hwirq);
-
- if (acpi_get_override_irq(gsi, &info->trigger,
- &info->polarity) < 0) {
- /*
- * PCI interrupts are always polarity one level
- * triggered.
- */
- info->trigger = 1;
- info->polarity = 1;
- }
- info->node = NUMA_NO_NODE;
-
- /*
- * setup_IO_APIC_irqs() programs all legacy IRQs with default
- * trigger and polarity attributes. Don't set the flag for that
- * case so the first legacy IRQ user could reprogram the pin
- * with real trigger and polarity attributes.
- */
- if (virq >= nr_legacy_irqs() || info->count)
- info->set = 1;
+ if (info && info->ioapic_valid) {
+ data->trigger = info->ioapic_trigger;
+ data->polarity = info->ioapic_polarity;
+ } else if (acpi_get_override_irq(gsi, &data->trigger,
+ &data->polarity) < 0) {
+ /* PCI interrupts are always active low level triggered. */
+ data->trigger = IOAPIC_LEVEL;
+ data->polarity = IOAPIC_POL_LOW;
}
- set_io_apic_irq_attr(&attr, ioapic, hwirq, info->trigger,
- info->polarity);
-
- return io_apic_setup_irq_pin(virq, info->node, &attr);
}
-void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq)
+static void mp_setup_entry(struct irq_cfg *cfg, struct mp_chip_data *data,
+ struct IO_APIC_route_entry *entry)
{
- struct irq_data *data = irq_get_irq_data(virq);
- struct irq_cfg *cfg = irq_cfg(virq);
- int ioapic = (int)(long)domain->host_data;
- int pin = (int)data->hwirq;
-
- ioapic_mask_entry(ioapic, pin);
- __remove_pin_from_irq(cfg, ioapic, pin);
- WARN_ON(!list_empty(&cfg->irq_2_pin));
- arch_teardown_hwirq(virq);
+ memset(entry, 0, sizeof(*entry));
+ entry->delivery_mode = apic->irq_delivery_mode;
+ entry->dest_mode = apic->irq_dest_mode;
+ entry->dest = cfg->dest_apicid;
+ entry->vector = cfg->vector;
+ entry->trigger = data->trigger;
+ entry->polarity = data->polarity;
+ /*
+ * Mask level triggered irqs. Edge triggered irqs are masked
+ * by the irq core code in case they fire.
+ */
+ if (data->trigger == IOAPIC_LEVEL)
+ entry->mask = IOAPIC_MASKED;
+ else
+ entry->mask = IOAPIC_UNMASKED;
}
-int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node)
+int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
{
- int ret = 0;
- int ioapic, pin;
- struct mp_pin_info *info;
+ int ret, ioapic, pin;
+ struct irq_cfg *cfg;
+ struct irq_data *irq_data;
+ struct mp_chip_data *data;
+ struct irq_alloc_info *info = arg;
- ioapic = mp_find_ioapic(gsi);
- if (ioapic < 0)
- return -ENODEV;
+ if (!info || nr_irqs > 1)
+ return -EINVAL;
+ irq_data = irq_domain_get_irq_data(domain, virq);
+ if (!irq_data)
+ return -EINVAL;
- pin = mp_find_ioapic_pin(ioapic, gsi);
- info = mp_pin_info(ioapic, pin);
- trigger = trigger ? 1 : 0;
- polarity = polarity ? 1 : 0;
+ ioapic = mp_irqdomain_ioapic_idx(domain);
+ pin = info->ioapic_pin;
+ if (irq_find_mapping(domain, (irq_hw_number_t)pin) > 0)
+ return -EEXIST;
- mutex_lock(&ioapic_mutex);
- if (!info->set) {
- info->trigger = trigger;
- info->polarity = polarity;
- info->node = node;
- info->set = 1;
- } else if (info->trigger != trigger || info->polarity != polarity) {
- ret = -EBUSY;
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ info->ioapic_entry = &data->entry;
+ ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
+ if (ret < 0) {
+ kfree(data);
+ return ret;
}
- mutex_unlock(&ioapic_mutex);
- return ret;
+ INIT_LIST_HEAD(&data->irq_2_pin);
+ irq_data->hwirq = info->ioapic_pin;
+ irq_data->chip = (domain->parent == x86_vector_domain) ?
+ &ioapic_chip : &ioapic_ir_chip;
+ irq_data->chip_data = data;
+ mp_irqdomain_get_attr(mp_pin_to_gsi(ioapic, pin), data, info);
+
+ cfg = irqd_cfg(irq_data);
+ add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin);
+ if (info->ioapic_entry)
+ mp_setup_entry(cfg, data, info->ioapic_entry);
+ mp_register_handler(virq, data->trigger);
+ if (virq < nr_legacy_irqs())
+ legacy_pic->mask(virq);
+
+ apic_printk(APIC_VERBOSE, KERN_DEBUG
+ "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n",
+ ioapic, mpc_ioapic_id(ioapic), pin, cfg->vector,
+ virq, data->trigger, data->polarity, cfg->dest_apicid);
+
+ return 0;
}
-/* Enable IOAPIC early just for system timer */
-void __init pre_init_apic_IRQ0(void)
+void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs)
{
- struct io_apic_irq_attr attr = { 0, 0, 0, 0 };
+ struct irq_data *irq_data;
+ struct mp_chip_data *data;
- printk(KERN_INFO "Early APIC setup for system timer0\n");
-#ifndef CONFIG_SMP
- physid_set_mask_of_physid(boot_cpu_physical_apicid,
- &phys_cpu_present_map);
-#endif
- setup_local_APIC();
-
- io_apic_setup_irq_pin(0, 0, &attr);
- irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
- "edge");
+ BUG_ON(nr_irqs != 1);
+ irq_data = irq_domain_get_irq_data(domain, virq);
+ if (irq_data && irq_data->chip_data) {
+ data = irq_data->chip_data;
+ __remove_pin_from_irq(data, mp_irqdomain_ioapic_idx(domain),
+ (int)irq_data->hwirq);
+ WARN_ON(!list_empty(&data->irq_2_pin));
+ kfree(irq_data->chip_data);
+ }
+ irq_domain_free_irqs_top(domain, virq, nr_irqs);
}
+
+void mp_irqdomain_activate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ unsigned long flags;
+ struct irq_pin_list *entry;
+ struct mp_chip_data *data = irq_data->chip_data;
+
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
+ for_each_irq_pin(entry, data->irq_2_pin)
+ __ioapic_write_entry(entry->apic, entry->pin, data->entry);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+void mp_irqdomain_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ /* It won't be called for IRQ with multiple IOAPIC pins associated */
+ ioapic_mask_entry(mp_irqdomain_ioapic_idx(domain),
+ (int)irq_data->hwirq);
+}
+
+int mp_irqdomain_ioapic_idx(struct irq_domain *domain)
+{
+ return (int)(long)domain->host_data;
+}
+
+const struct irq_domain_ops mp_ioapic_irqdomain_ops = {
+ .alloc = mp_irqdomain_alloc,
+ .free = mp_irqdomain_free,
+ .activate = mp_irqdomain_activate,
+ .deactivate = mp_irqdomain_deactivate,
+};
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index d6ba2d6..1a9d735 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -3,6 +3,8 @@
*
* Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
* Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ * Convert to hierarchical irqdomain
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -14,22 +16,23 @@
#include <linux/dmar.h>
#include <linux/hpet.h>
#include <linux/msi.h>
+#include <asm/irqdomain.h>
#include <asm/msidef.h>
#include <asm/hpet.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
#include <asm/irq_remapping.h>
-void native_compose_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id)
+static struct irq_domain *msi_default_domain;
+
+static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
{
- struct irq_cfg *cfg = irq_cfg(irq);
+ struct irq_cfg *cfg = irqd_cfg(data);
msg->address_hi = MSI_ADDR_BASE_HI;
if (x2apic_enabled())
- msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest);
+ msg->address_hi |= MSI_ADDR_EXT_DEST_ID(cfg->dest_apicid);
msg->address_lo =
MSI_ADDR_BASE_LO |
@@ -39,7 +42,7 @@
((apic->irq_delivery_mode != dest_LowestPrio) ?
MSI_ADDR_REDIRECTION_CPU :
MSI_ADDR_REDIRECTION_LOWPRI) |
- MSI_ADDR_DEST_ID(dest);
+ MSI_ADDR_DEST_ID(cfg->dest_apicid);
msg->data =
MSI_DATA_TRIGGER_EDGE |
@@ -50,237 +53,305 @@
MSI_DATA_VECTOR(cfg->vector);
}
-static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
- struct msi_msg *msg, u8 hpet_id)
-{
- struct irq_cfg *cfg;
- int err;
- unsigned dest;
-
- if (disable_apic)
- return -ENXIO;
-
- cfg = irq_cfg(irq);
- err = assign_irq_vector(irq, cfg, apic->target_cpus());
- if (err)
- return err;
-
- err = apic->cpu_mask_to_apicid_and(cfg->domain,
- apic->target_cpus(), &dest);
- if (err)
- return err;
-
- x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id);
-
- return 0;
-}
-
-static int
-msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
-{
- struct irq_cfg *cfg = irqd_cfg(data);
- struct msi_msg msg;
- unsigned int dest;
- int ret;
-
- ret = apic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
-
- __get_cached_msi_msg(data->msi_desc, &msg);
-
- msg.data &= ~MSI_DATA_VECTOR_MASK;
- msg.data |= MSI_DATA_VECTOR(cfg->vector);
- msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
- msg.address_lo |= MSI_ADDR_DEST_ID(dest);
-
- __pci_write_msi_msg(data->msi_desc, &msg);
-
- return IRQ_SET_MASK_OK_NOCOPY;
-}
-
/*
* IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
* which implement the MSI or MSI-X Capability Structure.
*/
-static struct irq_chip msi_chip = {
+static struct irq_chip pci_msi_controller = {
.name = "PCI-MSI",
.irq_unmask = pci_msi_unmask_irq,
.irq_mask = pci_msi_mask_irq,
- .irq_ack = apic_ack_edge,
- .irq_set_affinity = msi_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_compose_msi_msg = irq_msi_compose_msg,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
-int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
- unsigned int irq_base, unsigned int irq_offset)
-{
- struct irq_chip *chip = &msi_chip;
- struct msi_msg msg;
- unsigned int irq = irq_base + irq_offset;
- int ret;
-
- ret = msi_compose_msg(dev, irq, &msg, -1);
- if (ret < 0)
- return ret;
-
- irq_set_msi_desc_off(irq_base, irq_offset, msidesc);
-
- /*
- * MSI-X message is written per-IRQ, the offset is always 0.
- * MSI message denotes a contiguous group of IRQs, written for 0th IRQ.
- */
- if (!irq_offset)
- pci_write_msi_msg(irq, &msg);
-
- setup_remapped_irq(irq, irq_cfg(irq), chip);
-
- irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
-
- dev_dbg(&dev->dev, "irq %d for MSI/MSI-X\n", irq);
-
- return 0;
-}
-
int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
- struct msi_desc *msidesc;
- unsigned int irq;
- int node, ret;
+ struct irq_domain *domain;
+ struct irq_alloc_info info;
- /* Multiple MSI vectors only supported with interrupt remapping */
- if (type == PCI_CAP_ID_MSI && nvec > 1)
- return 1;
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_MSI;
+ info.msi_dev = dev;
- node = dev_to_node(&dev->dev);
+ domain = irq_remapping_get_irq_domain(&info);
+ if (domain == NULL)
+ domain = msi_default_domain;
+ if (domain == NULL)
+ return -ENOSYS;
- list_for_each_entry(msidesc, &dev->msi_list, list) {
- irq = irq_alloc_hwirq(node);
- if (!irq)
- return -ENOSPC;
-
- ret = setup_msi_irq(dev, msidesc, irq, 0);
- if (ret < 0) {
- irq_free_hwirq(irq);
- return ret;
- }
-
- }
- return 0;
+ return pci_msi_domain_alloc_irqs(domain, dev, nvec, type);
}
void native_teardown_msi_irq(unsigned int irq)
{
- irq_free_hwirq(irq);
+ irq_domain_free_irqs(irq, 1);
}
-#ifdef CONFIG_DMAR_TABLE
-static int
-dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
+static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info,
+ msi_alloc_info_t *arg)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- unsigned int dest, irq = data->irq;
- struct msi_msg msg;
- int ret;
-
- ret = apic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
-
- dmar_msi_read(irq, &msg);
-
- msg.data &= ~MSI_DATA_VECTOR_MASK;
- msg.data |= MSI_DATA_VECTOR(cfg->vector);
- msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
- msg.address_lo |= MSI_ADDR_DEST_ID(dest);
- msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest);
-
- dmar_msi_write(irq, &msg);
-
- return IRQ_SET_MASK_OK_NOCOPY;
+ return arg->msi_hwirq;
}
-static struct irq_chip dmar_msi_type = {
- .name = "DMAR_MSI",
- .irq_unmask = dmar_msi_unmask,
- .irq_mask = dmar_msi_mask,
- .irq_ack = apic_ack_edge,
- .irq_set_affinity = dmar_msi_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
+static int pci_msi_prepare(struct irq_domain *domain, struct device *dev,
+ int nvec, msi_alloc_info_t *arg)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct msi_desc *desc = first_pci_msi_entry(pdev);
+
+ init_irq_alloc_info(arg, NULL);
+ arg->msi_dev = pdev;
+ if (desc->msi_attrib.is_msix) {
+ arg->type = X86_IRQ_ALLOC_TYPE_MSIX;
+ } else {
+ arg->type = X86_IRQ_ALLOC_TYPE_MSI;
+ arg->flags |= X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+ }
+
+ return 0;
+}
+
+static void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
+{
+ arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc);
+}
+
+static struct msi_domain_ops pci_msi_domain_ops = {
+ .get_hwirq = pci_msi_get_hwirq,
+ .msi_prepare = pci_msi_prepare,
+ .set_desc = pci_msi_set_desc,
+};
+
+static struct msi_domain_info pci_msi_domain_info = {
+ .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+ MSI_FLAG_PCI_MSIX,
+ .ops = &pci_msi_domain_ops,
+ .chip = &pci_msi_controller,
+ .handler = handle_edge_irq,
+ .handler_name = "edge",
+};
+
+void arch_init_msi_domain(struct irq_domain *parent)
+{
+ if (disable_apic)
+ return;
+
+ msi_default_domain = pci_msi_create_irq_domain(NULL,
+ &pci_msi_domain_info, parent);
+ if (!msi_default_domain)
+ pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n");
+}
+
+#ifdef CONFIG_IRQ_REMAP
+static struct irq_chip pci_msi_ir_controller = {
+ .name = "IR-PCI-MSI",
+ .irq_unmask = pci_msi_unmask_irq,
+ .irq_mask = pci_msi_mask_irq,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_set_vcpu_affinity = irq_chip_set_vcpu_affinity_parent,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
-int arch_setup_dmar_msi(unsigned int irq)
-{
- int ret;
- struct msi_msg msg;
+static struct msi_domain_info pci_msi_ir_domain_info = {
+ .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+ MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX,
+ .ops = &pci_msi_domain_ops,
+ .chip = &pci_msi_ir_controller,
+ .handler = handle_edge_irq,
+ .handler_name = "edge",
+};
- ret = msi_compose_msg(NULL, irq, &msg, -1);
- if (ret < 0)
- return ret;
- dmar_msi_write(irq, &msg);
- irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
- "edge");
+struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent)
+{
+ return pci_msi_create_irq_domain(NULL, &pci_msi_ir_domain_info, parent);
+}
+#endif
+
+#ifdef CONFIG_DMAR_TABLE
+static void dmar_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
+{
+ dmar_msi_write(data->irq, msg);
+}
+
+static struct irq_chip dmar_msi_controller = {
+ .name = "DMAR-MSI",
+ .irq_unmask = dmar_msi_unmask,
+ .irq_mask = dmar_msi_mask,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_set_affinity = msi_domain_set_affinity,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_compose_msi_msg = irq_msi_compose_msg,
+ .irq_write_msi_msg = dmar_msi_write_msg,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
+};
+
+static irq_hw_number_t dmar_msi_get_hwirq(struct msi_domain_info *info,
+ msi_alloc_info_t *arg)
+{
+ return arg->dmar_id;
+}
+
+static int dmar_msi_init(struct irq_domain *domain,
+ struct msi_domain_info *info, unsigned int virq,
+ irq_hw_number_t hwirq, msi_alloc_info_t *arg)
+{
+ irq_domain_set_info(domain, virq, arg->dmar_id, info->chip, NULL,
+ handle_edge_irq, arg->dmar_data, "edge");
+
return 0;
}
+
+static struct msi_domain_ops dmar_msi_domain_ops = {
+ .get_hwirq = dmar_msi_get_hwirq,
+ .msi_init = dmar_msi_init,
+};
+
+static struct msi_domain_info dmar_msi_domain_info = {
+ .ops = &dmar_msi_domain_ops,
+ .chip = &dmar_msi_controller,
+};
+
+static struct irq_domain *dmar_get_irq_domain(void)
+{
+ static struct irq_domain *dmar_domain;
+ static DEFINE_MUTEX(dmar_lock);
+
+ mutex_lock(&dmar_lock);
+ if (dmar_domain == NULL)
+ dmar_domain = msi_create_irq_domain(NULL, &dmar_msi_domain_info,
+ x86_vector_domain);
+ mutex_unlock(&dmar_lock);
+
+ return dmar_domain;
+}
+
+int dmar_alloc_hwirq(int id, int node, void *arg)
+{
+ struct irq_domain *domain = dmar_get_irq_domain();
+ struct irq_alloc_info info;
+
+ if (!domain)
+ return -1;
+
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_DMAR;
+ info.dmar_id = id;
+ info.dmar_data = arg;
+
+ return irq_domain_alloc_irqs(domain, 1, node, &info);
+}
+
+void dmar_free_hwirq(int irq)
+{
+ irq_domain_free_irqs(irq, 1);
+}
#endif
/*
* MSI message composition
*/
#ifdef CONFIG_HPET_TIMER
-
-static int hpet_msi_set_affinity(struct irq_data *data,
- const struct cpumask *mask, bool force)
+static inline int hpet_dev_id(struct irq_domain *domain)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- struct msi_msg msg;
- unsigned int dest;
- int ret;
+ struct msi_domain_info *info = msi_get_domain_info(domain);
- ret = apic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
-
- hpet_msi_read(data->handler_data, &msg);
-
- msg.data &= ~MSI_DATA_VECTOR_MASK;
- msg.data |= MSI_DATA_VECTOR(cfg->vector);
- msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
- msg.address_lo |= MSI_ADDR_DEST_ID(dest);
-
- hpet_msi_write(data->handler_data, &msg);
-
- return IRQ_SET_MASK_OK_NOCOPY;
+ return (int)(long)info->data;
}
-static struct irq_chip hpet_msi_type = {
- .name = "HPET_MSI",
+static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
+{
+ hpet_msi_write(data->handler_data, msg);
+}
+
+static struct irq_chip hpet_msi_controller = {
+ .name = "HPET-MSI",
.irq_unmask = hpet_msi_unmask,
.irq_mask = hpet_msi_mask,
- .irq_ack = apic_ack_edge,
- .irq_set_affinity = hpet_msi_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_set_affinity = msi_domain_set_affinity,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_compose_msi_msg = irq_msi_compose_msg,
+ .irq_write_msi_msg = hpet_msi_write_msg,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
-int default_setup_hpet_msi(unsigned int irq, unsigned int id)
+static irq_hw_number_t hpet_msi_get_hwirq(struct msi_domain_info *info,
+ msi_alloc_info_t *arg)
{
- struct irq_chip *chip = &hpet_msi_type;
- struct msi_msg msg;
- int ret;
+ return arg->hpet_index;
+}
- ret = msi_compose_msg(NULL, irq, &msg, id);
- if (ret < 0)
- return ret;
+static int hpet_msi_init(struct irq_domain *domain,
+ struct msi_domain_info *info, unsigned int virq,
+ irq_hw_number_t hwirq, msi_alloc_info_t *arg)
+{
+ irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
+ irq_domain_set_info(domain, virq, arg->hpet_index, info->chip, NULL,
+ handle_edge_irq, arg->hpet_data, "edge");
- hpet_msi_write(irq_get_handler_data(irq), &msg);
- irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- setup_remapped_irq(irq, irq_cfg(irq), chip);
-
- irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
return 0;
}
+
+static void hpet_msi_free(struct irq_domain *domain,
+ struct msi_domain_info *info, unsigned int virq)
+{
+ irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT);
+}
+
+static struct msi_domain_ops hpet_msi_domain_ops = {
+ .get_hwirq = hpet_msi_get_hwirq,
+ .msi_init = hpet_msi_init,
+ .msi_free = hpet_msi_free,
+};
+
+static struct msi_domain_info hpet_msi_domain_info = {
+ .ops = &hpet_msi_domain_ops,
+ .chip = &hpet_msi_controller,
+};
+
+struct irq_domain *hpet_create_irq_domain(int hpet_id)
+{
+ struct irq_domain *parent;
+ struct irq_alloc_info info;
+ struct msi_domain_info *domain_info;
+
+ if (x86_vector_domain == NULL)
+ return NULL;
+
+ domain_info = kzalloc(sizeof(*domain_info), GFP_KERNEL);
+ if (!domain_info)
+ return NULL;
+
+ *domain_info = hpet_msi_domain_info;
+ domain_info->data = (void *)(long)hpet_id;
+
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_HPET;
+ info.hpet_id = hpet_id;
+ parent = irq_remapping_get_ir_irq_domain(&info);
+ if (parent == NULL)
+ parent = x86_vector_domain;
+ else
+ hpet_msi_controller.name = "IR-HPET-MSI";
+
+ return msi_create_irq_domain(NULL, domain_info, parent);
+}
+
+int hpet_assign_irq(struct irq_domain *domain, struct hpet_dev *dev,
+ int dev_num)
+{
+ struct irq_alloc_info info;
+
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_HPET;
+ info.hpet_data = dev;
+ info.hpet_id = hpet_dev_id(domain);
+ info.hpet_index = dev_num;
+
+ return irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info);
+}
#endif
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 6cedd79..28eba2d 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -3,6 +3,8 @@
*
* Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
* Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ * Enable support of hierarchical irqdomains
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -11,15 +13,28 @@
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/compiler.h>
-#include <linux/irqdomain.h>
#include <linux/slab.h>
+#include <asm/irqdomain.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
#include <asm/i8259.h>
#include <asm/desc.h>
#include <asm/irq_remapping.h>
+struct apic_chip_data {
+ struct irq_cfg cfg;
+ cpumask_var_t domain;
+ cpumask_var_t old_domain;
+ u8 move_in_progress : 1;
+};
+
+struct irq_domain *x86_vector_domain;
static DEFINE_RAW_SPINLOCK(vector_lock);
+static cpumask_var_t vector_cpumask;
+static struct irq_chip lapic_controller;
+#ifdef CONFIG_X86_IO_APIC
+static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY];
+#endif
void lock_vector_lock(void)
{
@@ -34,71 +49,59 @@
raw_spin_unlock(&vector_lock);
}
-struct irq_cfg *irq_cfg(unsigned int irq)
+static struct apic_chip_data *apic_chip_data(struct irq_data *irq_data)
{
- return irq_get_chip_data(irq);
+ if (!irq_data)
+ return NULL;
+
+ while (irq_data->parent_data)
+ irq_data = irq_data->parent_data;
+
+ return irq_data->chip_data;
}
struct irq_cfg *irqd_cfg(struct irq_data *irq_data)
{
- return irq_data->chip_data;
+ struct apic_chip_data *data = apic_chip_data(irq_data);
+
+ return data ? &data->cfg : NULL;
}
-static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
+struct irq_cfg *irq_cfg(unsigned int irq)
{
- struct irq_cfg *cfg;
+ return irqd_cfg(irq_get_irq_data(irq));
+}
- cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node);
- if (!cfg)
+static struct apic_chip_data *alloc_apic_chip_data(int node)
+{
+ struct apic_chip_data *data;
+
+ data = kzalloc_node(sizeof(*data), GFP_KERNEL, node);
+ if (!data)
return NULL;
- if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node))
- goto out_cfg;
- if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node))
+ if (!zalloc_cpumask_var_node(&data->domain, GFP_KERNEL, node))
+ goto out_data;
+ if (!zalloc_cpumask_var_node(&data->old_domain, GFP_KERNEL, node))
goto out_domain;
-#ifdef CONFIG_X86_IO_APIC
- INIT_LIST_HEAD(&cfg->irq_2_pin);
-#endif
- return cfg;
+ return data;
out_domain:
- free_cpumask_var(cfg->domain);
-out_cfg:
- kfree(cfg);
+ free_cpumask_var(data->domain);
+out_data:
+ kfree(data);
return NULL;
}
-struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
+static void free_apic_chip_data(struct apic_chip_data *data)
{
- int res = irq_alloc_desc_at(at, node);
- struct irq_cfg *cfg;
-
- if (res < 0) {
- if (res != -EEXIST)
- return NULL;
- cfg = irq_cfg(at);
- if (cfg)
- return cfg;
+ if (data) {
+ free_cpumask_var(data->domain);
+ free_cpumask_var(data->old_domain);
+ kfree(data);
}
-
- cfg = alloc_irq_cfg(at, node);
- if (cfg)
- irq_set_chip_data(at, cfg);
- else
- irq_free_desc(at);
- return cfg;
}
-static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
-{
- if (!cfg)
- return;
- irq_set_chip_data(at, NULL);
- free_cpumask_var(cfg->domain);
- free_cpumask_var(cfg->old_domain);
- kfree(cfg);
-}
-
-static int
-__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+static int __assign_irq_vector(int irq, struct apic_chip_data *d,
+ const struct cpumask *mask)
{
/*
* NOTE! The local APIC isn't very good at handling
@@ -114,36 +117,33 @@
static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
static int current_offset = VECTOR_OFFSET_START % 16;
int cpu, err;
- cpumask_var_t tmp_mask;
- if (cfg->move_in_progress)
+ if (d->move_in_progress)
return -EBUSY;
- if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC))
- return -ENOMEM;
-
/* Only try and allocate irqs on cpus that are present */
err = -ENOSPC;
- cpumask_clear(cfg->old_domain);
+ cpumask_clear(d->old_domain);
cpu = cpumask_first_and(mask, cpu_online_mask);
while (cpu < nr_cpu_ids) {
int new_cpu, vector, offset;
- apic->vector_allocation_domain(cpu, tmp_mask, mask);
+ apic->vector_allocation_domain(cpu, vector_cpumask, mask);
- if (cpumask_subset(tmp_mask, cfg->domain)) {
+ if (cpumask_subset(vector_cpumask, d->domain)) {
err = 0;
- if (cpumask_equal(tmp_mask, cfg->domain))
+ if (cpumask_equal(vector_cpumask, d->domain))
break;
/*
* New cpumask using the vector is a proper subset of
* the current in use mask. So cleanup the vector
* allocation for the members that are not used anymore.
*/
- cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask);
- cfg->move_in_progress =
- cpumask_intersects(cfg->old_domain, cpu_online_mask);
- cpumask_and(cfg->domain, cfg->domain, tmp_mask);
+ cpumask_andnot(d->old_domain, d->domain,
+ vector_cpumask);
+ d->move_in_progress =
+ cpumask_intersects(d->old_domain, cpu_online_mask);
+ cpumask_and(d->domain, d->domain, vector_cpumask);
break;
}
@@ -157,16 +157,18 @@
}
if (unlikely(current_vector == vector)) {
- cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask);
- cpumask_andnot(tmp_mask, mask, cfg->old_domain);
- cpu = cpumask_first_and(tmp_mask, cpu_online_mask);
+ cpumask_or(d->old_domain, d->old_domain,
+ vector_cpumask);
+ cpumask_andnot(vector_cpumask, mask, d->old_domain);
+ cpu = cpumask_first_and(vector_cpumask,
+ cpu_online_mask);
continue;
}
if (test_bit(vector, used_vectors))
goto next;
- for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) {
+ for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) {
if (per_cpu(vector_irq, new_cpu)[vector] >
VECTOR_UNDEFINED)
goto next;
@@ -174,55 +176,73 @@
/* Found one! */
current_vector = vector;
current_offset = offset;
- if (cfg->vector) {
- cpumask_copy(cfg->old_domain, cfg->domain);
- cfg->move_in_progress =
- cpumask_intersects(cfg->old_domain, cpu_online_mask);
+ if (d->cfg.vector) {
+ cpumask_copy(d->old_domain, d->domain);
+ d->move_in_progress =
+ cpumask_intersects(d->old_domain, cpu_online_mask);
}
- for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask)
+ for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask)
per_cpu(vector_irq, new_cpu)[vector] = irq;
- cfg->vector = vector;
- cpumask_copy(cfg->domain, tmp_mask);
+ d->cfg.vector = vector;
+ cpumask_copy(d->domain, vector_cpumask);
err = 0;
break;
}
- free_cpumask_var(tmp_mask);
+
+ if (!err) {
+ /* cache destination APIC IDs into cfg->dest_apicid */
+ err = apic->cpu_mask_to_apicid_and(mask, d->domain,
+ &d->cfg.dest_apicid);
+ }
return err;
}
-int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+static int assign_irq_vector(int irq, struct apic_chip_data *data,
+ const struct cpumask *mask)
{
int err;
unsigned long flags;
raw_spin_lock_irqsave(&vector_lock, flags);
- err = __assign_irq_vector(irq, cfg, mask);
+ err = __assign_irq_vector(irq, data, mask);
raw_spin_unlock_irqrestore(&vector_lock, flags);
return err;
}
-void clear_irq_vector(int irq, struct irq_cfg *cfg)
+static int assign_irq_vector_policy(int irq, int node,
+ struct apic_chip_data *data,
+ struct irq_alloc_info *info)
+{
+ if (info && info->mask)
+ return assign_irq_vector(irq, data, info->mask);
+ if (node != NUMA_NO_NODE &&
+ assign_irq_vector(irq, data, cpumask_of_node(node)) == 0)
+ return 0;
+ return assign_irq_vector(irq, data, apic->target_cpus());
+}
+
+static void clear_irq_vector(int irq, struct apic_chip_data *data)
{
int cpu, vector;
unsigned long flags;
raw_spin_lock_irqsave(&vector_lock, flags);
- BUG_ON(!cfg->vector);
+ BUG_ON(!data->cfg.vector);
- vector = cfg->vector;
- for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+ vector = data->cfg.vector;
+ for_each_cpu_and(cpu, data->domain, cpu_online_mask)
per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
- cfg->vector = 0;
- cpumask_clear(cfg->domain);
+ data->cfg.vector = 0;
+ cpumask_clear(data->domain);
- if (likely(!cfg->move_in_progress)) {
+ if (likely(!data->move_in_progress)) {
raw_spin_unlock_irqrestore(&vector_lock, flags);
return;
}
- for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+ for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) {
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
vector++) {
if (per_cpu(vector_irq, cpu)[vector] != irq)
@@ -231,10 +251,95 @@
break;
}
}
- cfg->move_in_progress = 0;
+ data->move_in_progress = 0;
raw_spin_unlock_irqrestore(&vector_lock, flags);
}
+void init_irq_alloc_info(struct irq_alloc_info *info,
+ const struct cpumask *mask)
+{
+ memset(info, 0, sizeof(*info));
+ info->mask = mask;
+}
+
+void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src)
+{
+ if (src)
+ *dst = *src;
+ else
+ memset(dst, 0, sizeof(*dst));
+}
+
+static void x86_vector_free_irqs(struct irq_domain *domain,
+ unsigned int virq, unsigned int nr_irqs)
+{
+ struct irq_data *irq_data;
+ int i;
+
+ for (i = 0; i < nr_irqs; i++) {
+ irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i);
+ if (irq_data && irq_data->chip_data) {
+ clear_irq_vector(virq + i, irq_data->chip_data);
+ free_apic_chip_data(irq_data->chip_data);
+#ifdef CONFIG_X86_IO_APIC
+ if (virq + i < nr_legacy_irqs())
+ legacy_irq_data[virq + i] = NULL;
+#endif
+ irq_domain_reset_irq_data(irq_data);
+ }
+ }
+}
+
+static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
+{
+ struct irq_alloc_info *info = arg;
+ struct apic_chip_data *data;
+ struct irq_data *irq_data;
+ int i, err;
+
+ if (disable_apic)
+ return -ENXIO;
+
+ /* Currently vector allocator can't guarantee contiguous allocations */
+ if ((info->flags & X86_IRQ_ALLOC_CONTIGUOUS_VECTORS) && nr_irqs > 1)
+ return -ENOSYS;
+
+ for (i = 0; i < nr_irqs; i++) {
+ irq_data = irq_domain_get_irq_data(domain, virq + i);
+ BUG_ON(!irq_data);
+#ifdef CONFIG_X86_IO_APIC
+ if (virq + i < nr_legacy_irqs() && legacy_irq_data[virq + i])
+ data = legacy_irq_data[virq + i];
+ else
+#endif
+ data = alloc_apic_chip_data(irq_data->node);
+ if (!data) {
+ err = -ENOMEM;
+ goto error;
+ }
+
+ irq_data->chip = &lapic_controller;
+ irq_data->chip_data = data;
+ irq_data->hwirq = virq + i;
+ err = assign_irq_vector_policy(virq, irq_data->node, data,
+ info);
+ if (err)
+ goto error;
+ }
+
+ return 0;
+
+error:
+ x86_vector_free_irqs(domain, virq, i + 1);
+ return err;
+}
+
+static const struct irq_domain_ops x86_vector_domain_ops = {
+ .alloc = x86_vector_alloc_irqs,
+ .free = x86_vector_free_irqs,
+};
+
int __init arch_probe_nr_irqs(void)
{
int nr;
@@ -258,8 +363,43 @@
return nr_legacy_irqs();
}
+#ifdef CONFIG_X86_IO_APIC
+static void init_legacy_irqs(void)
+{
+ int i, node = cpu_to_node(0);
+ struct apic_chip_data *data;
+
+ /*
+ * For legacy IRQ's, start with assigning irq0 to irq15 to
+ * ISA_IRQ_VECTOR(i) for all cpu's.
+ */
+ for (i = 0; i < nr_legacy_irqs(); i++) {
+ data = legacy_irq_data[i] = alloc_apic_chip_data(node);
+ BUG_ON(!data);
+
+ data->cfg.vector = ISA_IRQ_VECTOR(i);
+ cpumask_setall(data->domain);
+ irq_set_chip_data(i, data);
+ }
+}
+#else
+static void init_legacy_irqs(void) { }
+#endif
+
int __init arch_early_irq_init(void)
{
+ init_legacy_irqs();
+
+ x86_vector_domain = irq_domain_add_tree(NULL, &x86_vector_domain_ops,
+ NULL);
+ BUG_ON(x86_vector_domain == NULL);
+ irq_set_default_host(x86_vector_domain);
+
+ arch_init_msi_domain(x86_vector_domain);
+ arch_init_htirq_domain(x86_vector_domain);
+
+ BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL));
+
return arch_early_ioapic_init();
}
@@ -267,7 +407,7 @@
{
/* Initialize vector_irq on a new cpu */
int irq, vector;
- struct irq_cfg *cfg;
+ struct apic_chip_data *data;
/*
* vector_lock will make sure that we don't run into irq vector
@@ -277,13 +417,13 @@
raw_spin_lock(&vector_lock);
/* Mark the inuse vectors */
for_each_active_irq(irq) {
- cfg = irq_cfg(irq);
- if (!cfg)
+ data = apic_chip_data(irq_get_irq_data(irq));
+ if (!data)
continue;
- if (!cpumask_test_cpu(cpu, cfg->domain))
+ if (!cpumask_test_cpu(cpu, data->domain))
continue;
- vector = cfg->vector;
+ vector = data->cfg.vector;
per_cpu(vector_irq, cpu)[vector] = irq;
}
/* Mark the free vectors */
@@ -292,8 +432,8 @@
if (irq <= VECTOR_UNDEFINED)
continue;
- cfg = irq_cfg(irq);
- if (!cpumask_test_cpu(cpu, cfg->domain))
+ data = apic_chip_data(irq_get_irq_data(irq));
+ if (!cpumask_test_cpu(cpu, data->domain))
per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
}
raw_spin_unlock(&vector_lock);
@@ -314,20 +454,20 @@
* legacy vector to irq mapping:
*/
for (irq = 0; irq < nr_legacy_irqs(); irq++)
- per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq;
+ per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq;
__setup_vector_irq(cpu);
}
-int apic_retrigger_irq(struct irq_data *data)
+static int apic_retrigger_irq(struct irq_data *irq_data)
{
- struct irq_cfg *cfg = irqd_cfg(data);
+ struct apic_chip_data *data = apic_chip_data(irq_data);
unsigned long flags;
int cpu;
raw_spin_lock_irqsave(&vector_lock, flags);
- cpu = cpumask_first_and(cfg->domain, cpu_online_mask);
- apic->send_IPI_mask(cpumask_of(cpu), cfg->vector);
+ cpu = cpumask_first_and(data->domain, cpu_online_mask);
+ apic->send_IPI_mask(cpumask_of(cpu), data->cfg.vector);
raw_spin_unlock_irqrestore(&vector_lock, flags);
return 1;
@@ -340,73 +480,76 @@
ack_APIC_irq();
}
-/*
- * Either sets data->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
- * leaves data->affinity untouched.
- */
-int apic_set_affinity(struct irq_data *data, const struct cpumask *mask,
- unsigned int *dest_id)
+static int apic_set_affinity(struct irq_data *irq_data,
+ const struct cpumask *dest, bool force)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- unsigned int irq = data->irq;
- int err;
+ struct apic_chip_data *data = irq_data->chip_data;
+ int err, irq = irq_data->irq;
if (!config_enabled(CONFIG_SMP))
return -EPERM;
- if (!cpumask_intersects(mask, cpu_online_mask))
+ if (!cpumask_intersects(dest, cpu_online_mask))
return -EINVAL;
- err = assign_irq_vector(irq, cfg, mask);
- if (err)
- return err;
-
- err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id);
+ err = assign_irq_vector(irq, data, dest);
if (err) {
- if (assign_irq_vector(irq, cfg, data->affinity))
+ struct irq_data *top = irq_get_irq_data(irq);
+
+ if (assign_irq_vector(irq, data, top->affinity))
pr_err("Failed to recover vector for irq %d\n", irq);
return err;
}
- cpumask_copy(data->affinity, mask);
-
- return 0;
+ return IRQ_SET_MASK_OK;
}
+static struct irq_chip lapic_controller = {
+ .irq_ack = apic_ack_edge,
+ .irq_set_affinity = apic_set_affinity,
+ .irq_retrigger = apic_retrigger_irq,
+};
+
#ifdef CONFIG_SMP
-void send_cleanup_vector(struct irq_cfg *cfg)
+static void __send_cleanup_vector(struct apic_chip_data *data)
{
cpumask_var_t cleanup_mask;
if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
unsigned int i;
- for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+ for_each_cpu_and(i, data->old_domain, cpu_online_mask)
apic->send_IPI_mask(cpumask_of(i),
IRQ_MOVE_CLEANUP_VECTOR);
} else {
- cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
+ cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask);
apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
free_cpumask_var(cleanup_mask);
}
- cfg->move_in_progress = 0;
+ data->move_in_progress = 0;
+}
+
+void send_cleanup_vector(struct irq_cfg *cfg)
+{
+ struct apic_chip_data *data;
+
+ data = container_of(cfg, struct apic_chip_data, cfg);
+ if (data->move_in_progress)
+ __send_cleanup_vector(data);
}
asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
{
unsigned vector, me;
- ack_APIC_irq();
- irq_enter();
- exit_idle();
+ entering_ack_irq();
me = smp_processor_id();
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
int irq;
unsigned int irr;
struct irq_desc *desc;
- struct irq_cfg *cfg;
+ struct apic_chip_data *data;
irq = __this_cpu_read(vector_irq[vector]);
@@ -417,8 +560,8 @@
if (!desc)
continue;
- cfg = irq_cfg(irq);
- if (!cfg)
+ data = apic_chip_data(&desc->irq_data);
+ if (!data)
continue;
raw_spin_lock(&desc->lock);
@@ -427,10 +570,11 @@
* Check if the irq migration is in progress. If so, we
* haven't received the cleanup request yet for this irq.
*/
- if (cfg->move_in_progress)
+ if (data->move_in_progress)
goto unlock;
- if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
+ if (vector == data->cfg.vector &&
+ cpumask_test_cpu(me, data->domain))
goto unlock;
irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
@@ -450,20 +594,21 @@
raw_spin_unlock(&desc->lock);
}
- irq_exit();
+ exiting_irq();
}
static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
{
unsigned me;
+ struct apic_chip_data *data;
- if (likely(!cfg->move_in_progress))
+ data = container_of(cfg, struct apic_chip_data, cfg);
+ if (likely(!data->move_in_progress))
return;
me = smp_processor_id();
-
- if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
- send_cleanup_vector(cfg);
+ if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain))
+ __send_cleanup_vector(data);
}
void irq_complete_move(struct irq_cfg *cfg)
@@ -475,46 +620,11 @@
{
struct irq_cfg *cfg = irq_cfg(irq);
- if (!cfg)
- return;
-
- __irq_complete_move(cfg, cfg->vector);
+ if (cfg)
+ __irq_complete_move(cfg, cfg->vector);
}
#endif
-/*
- * Dynamic irq allocate and deallocation. Should be replaced by irq domains!
- */
-int arch_setup_hwirq(unsigned int irq, int node)
-{
- struct irq_cfg *cfg;
- unsigned long flags;
- int ret;
-
- cfg = alloc_irq_cfg(irq, node);
- if (!cfg)
- return -ENOMEM;
-
- raw_spin_lock_irqsave(&vector_lock, flags);
- ret = __assign_irq_vector(irq, cfg, apic->target_cpus());
- raw_spin_unlock_irqrestore(&vector_lock, flags);
-
- if (!ret)
- irq_set_chip_data(irq, cfg);
- else
- free_irq_cfg(irq, cfg);
- return ret;
-}
-
-void arch_teardown_hwirq(unsigned int irq)
-{
- struct irq_cfg *cfg = irq_cfg(irq);
-
- free_remapped_irq(irq);
- clear_irq_vector(irq, cfg);
- free_irq_cfg(irq, cfg);
-}
-
static void __init print_APIC_field(int base)
{
int i;
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 6fae733..3ffd925 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -21,11 +21,13 @@
static bool x2apic_fadt_phys(void)
{
+#ifdef CONFIG_ACPI
if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
printk(KERN_DEBUG "System requires x2apic physical mode\n");
return true;
}
+#endif
return false;
}
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 9f6b934..8e3d22a1 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -41,6 +41,25 @@
OFFSET(pbe_orig_address, pbe, orig_address);
OFFSET(pbe_next, pbe, next);
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+ BLANK();
+ OFFSET(IA32_SIGCONTEXT_ax, sigcontext_ia32, ax);
+ OFFSET(IA32_SIGCONTEXT_bx, sigcontext_ia32, bx);
+ OFFSET(IA32_SIGCONTEXT_cx, sigcontext_ia32, cx);
+ OFFSET(IA32_SIGCONTEXT_dx, sigcontext_ia32, dx);
+ OFFSET(IA32_SIGCONTEXT_si, sigcontext_ia32, si);
+ OFFSET(IA32_SIGCONTEXT_di, sigcontext_ia32, di);
+ OFFSET(IA32_SIGCONTEXT_bp, sigcontext_ia32, bp);
+ OFFSET(IA32_SIGCONTEXT_sp, sigcontext_ia32, sp);
+ OFFSET(IA32_SIGCONTEXT_ip, sigcontext_ia32, ip);
+
+ BLANK();
+ OFFSET(TI_sysenter_return, thread_info, sysenter_return);
+
+ BLANK();
+ OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
+#endif
+
#ifdef CONFIG_PARAVIRT
BLANK();
OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
@@ -49,7 +68,9 @@
OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
+#ifdef CONFIG_X86_32
OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
+#endif
OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
#endif
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 47703ae..6ce3902 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -17,17 +17,6 @@
void foo(void)
{
- OFFSET(IA32_SIGCONTEXT_ax, sigcontext, ax);
- OFFSET(IA32_SIGCONTEXT_bx, sigcontext, bx);
- OFFSET(IA32_SIGCONTEXT_cx, sigcontext, cx);
- OFFSET(IA32_SIGCONTEXT_dx, sigcontext, dx);
- OFFSET(IA32_SIGCONTEXT_si, sigcontext, si);
- OFFSET(IA32_SIGCONTEXT_di, sigcontext, di);
- OFFSET(IA32_SIGCONTEXT_bp, sigcontext, bp);
- OFFSET(IA32_SIGCONTEXT_sp, sigcontext, sp);
- OFFSET(IA32_SIGCONTEXT_ip, sigcontext, ip);
- BLANK();
-
OFFSET(CPUINFO_x86, cpuinfo_x86, x86);
OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor);
OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model);
@@ -37,10 +26,6 @@
OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
BLANK();
- OFFSET(TI_sysenter_return, thread_info, sysenter_return);
- OFFSET(TI_cpu, thread_info, cpu);
- BLANK();
-
OFFSET(PT_EBX, pt_regs, bx);
OFFSET(PT_ECX, pt_regs, cx);
OFFSET(PT_EDX, pt_regs, dx);
@@ -60,9 +45,6 @@
OFFSET(PT_OLDSS, pt_regs, ss);
BLANK();
- OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext);
- BLANK();
-
OFFSET(saved_context_gdt_desc, saved_context, gdt_desc);
BLANK();
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 5ce6f2d..d8f42f9 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -29,27 +29,6 @@
BLANK();
#endif
-#ifdef CONFIG_IA32_EMULATION
- OFFSET(TI_sysenter_return, thread_info, sysenter_return);
- BLANK();
-
-#define ENTRY(entry) OFFSET(IA32_SIGCONTEXT_ ## entry, sigcontext_ia32, entry)
- ENTRY(ax);
- ENTRY(bx);
- ENTRY(cx);
- ENTRY(dx);
- ENTRY(si);
- ENTRY(di);
- ENTRY(bp);
- ENTRY(sp);
- ENTRY(ip);
- BLANK();
-#undef ENTRY
-
- OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
- BLANK();
-#endif
-
#define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry)
ENTRY(bx);
ENTRY(cx);
@@ -87,7 +66,7 @@
DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1);
DEFINE(NR_syscalls, sizeof(syscalls_64));
- DEFINE(__NR_ia32_syscall_max, sizeof(syscalls_ia32) - 1);
+ DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1);
DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32));
return 0;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e4cf633..eb4f012 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -288,7 +288,7 @@
* Assumption: Number of cores in each internal node is the same.
* (2) AMD processors supporting compute units
*/
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
static void amd_get_topology(struct cpuinfo_x86 *c)
{
u32 nodes, cores_per_cu = 1;
@@ -341,7 +341,7 @@
*/
static void amd_detect_cmp(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
unsigned bits;
int cpu = smp_processor_id();
@@ -420,7 +420,7 @@
static void early_init_amd_mc(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
unsigned bits, ecx;
/* Multi core CPU? */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a62cf04..cc7f753 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -508,7 +508,7 @@
void detect_ht(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
u32 eax, ebx, ecx, edx;
int index_msb, core_bits;
static bool printed;
@@ -844,7 +844,7 @@
if (c->cpuid_level >= 0x00000001) {
c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
#ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_HT
+# ifdef CONFIG_SMP
c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
# else
c->apicid = c->initial_apicid;
@@ -1026,7 +1026,7 @@
(unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
0);
- wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)ia32_sysenter_target, 0);
+ wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
out:
put_cpu();
@@ -1155,10 +1155,6 @@
}
__setup("clearcpuid=", setup_disablecpuid);
-DEFINE_PER_CPU(unsigned long, kernel_stack) =
- (unsigned long)&init_thread_union + THREAD_SIZE;
-EXPORT_PER_CPU_SYMBOL(kernel_stack);
-
#ifdef CONFIG_X86_64
struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
@@ -1208,10 +1204,10 @@
* set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
*/
wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32);
- wrmsrl(MSR_LSTAR, system_call);
+ wrmsrl(MSR_LSTAR, entry_SYSCALL_64);
#ifdef CONFIG_IA32_EMULATION
- wrmsrl(MSR_CSTAR, ia32_cstar_target);
+ wrmsrl(MSR_CSTAR, entry_SYSCALL_compat);
/*
* This only works on Intel CPUs.
* On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
@@ -1220,7 +1216,7 @@
*/
wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
- wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+ wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
#else
wrmsrl(MSR_CSTAR, ignore_sysret);
wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index edcb0e2..be4febc 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -654,7 +654,7 @@
unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
unsigned int cpu = c->cpu_index;
#endif
@@ -773,19 +773,19 @@
if (new_l2) {
l2 = new_l2;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
per_cpu(cpu_llc_id, cpu) = l2_id;
#endif
}
if (new_l3) {
l3 = new_l3;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
per_cpu(cpu_llc_id, cpu) = l3_id;
#endif
}
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
/*
* If cpu_llc_id is not yet set, this means cpuid_level < 4 which in
* turns means that the only possibility is SMT (as indicated in
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index e535533..5b974c9 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -708,6 +708,7 @@
struct pt_regs *regs)
{
int i, ret = 0;
+ char *tmp;
for (i = 0; i < mca_cfg.banks; i++) {
m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
@@ -716,9 +717,11 @@
if (quirk_no_way_out)
quirk_no_way_out(i, m, regs);
}
- if (mce_severity(m, mca_cfg.tolerant, msg, true) >=
- MCE_PANIC_SEVERITY)
+
+ if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+ *msg = tmp;
ret = 1;
+ }
}
return ret;
}
@@ -1047,6 +1050,7 @@
char *msg = "Unknown";
u64 recover_paddr = ~0ull;
int flags = MF_ACTION_REQUIRED;
+ int lmce = 0;
prev_state = ist_enter(regs);
@@ -1074,11 +1078,20 @@
kill_it = 1;
/*
- * Go through all the banks in exclusion of the other CPUs.
- * This way we don't report duplicated events on shared banks
- * because the first one to see it will clear it.
+ * Check if this MCE is signaled to only this logical processor
*/
- order = mce_start(&no_way_out);
+ if (m.mcgstatus & MCG_STATUS_LMCES)
+ lmce = 1;
+ else {
+ /*
+ * Go through all the banks in exclusion of the other CPUs.
+ * This way we don't report duplicated events on shared banks
+ * because the first one to see it will clear it.
+ * If this is a Local MCE, then no need to perform rendezvous.
+ */
+ order = mce_start(&no_way_out);
+ }
+
for (i = 0; i < cfg->banks; i++) {
__clear_bit(i, toclear);
if (!test_bit(i, valid_banks))
@@ -1155,8 +1168,18 @@
* Do most of the synchronization with other CPUs.
* When there's any problem use only local no_way_out state.
*/
- if (mce_end(order) < 0)
- no_way_out = worst >= MCE_PANIC_SEVERITY;
+ if (!lmce) {
+ if (mce_end(order) < 0)
+ no_way_out = worst >= MCE_PANIC_SEVERITY;
+ } else {
+ /*
+ * Local MCE skipped calling mce_reign()
+ * If we found a fatal error, we need to panic here.
+ */
+ if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
+ mce_panic("Machine check from unknown source",
+ NULL, NULL);
+ }
/*
* At insane "tolerant" levels we take no action. Otherwise
@@ -1637,10 +1660,16 @@
mce_intel_feature_init(c);
mce_adjust_timer = cmci_intel_adjust_timer;
break;
- case X86_VENDOR_AMD:
+
+ case X86_VENDOR_AMD: {
+ u32 ebx = cpuid_ebx(0x80000007);
+
mce_amd_feature_init(c);
- mce_flags.overflow_recov = cpuid_ebx(0x80000007) & 0x1;
+ mce_flags.overflow_recov = !!(ebx & BIT(0));
+ mce_flags.succor = !!(ebx & BIT(1));
break;
+ }
+
default:
break;
}
@@ -1976,6 +2005,7 @@
/*
* mce=off Disables machine check
* mce=no_cmci Disables CMCI
+ * mce=no_lmce Disables LMCE
* mce=dont_log_ce Clears corrected events silently, no log created for CEs.
* mce=ignore_ce Disables polling and CMCI, corrected events are not cleared.
* mce=TOLERANCELEVEL[,monarchtimeout] (number, see above)
@@ -1999,6 +2029,8 @@
cfg->disabled = true;
else if (!strcmp(str, "no_cmci"))
cfg->cmci_disabled = true;
+ else if (!strcmp(str, "no_lmce"))
+ cfg->lmce_disabled = true;
else if (!strcmp(str, "dont_log_ce"))
cfg->dont_log_ce = true;
else if (!strcmp(str, "ignore_ce"))
@@ -2008,11 +2040,8 @@
else if (!strcmp(str, "bios_cmci_threshold"))
cfg->bios_cmci_threshold = true;
else if (isdigit(str[0])) {
- get_option(&str, &(cfg->tolerant));
- if (*str == ',') {
- ++str;
+ if (get_option(&str, &cfg->tolerant) == 2)
get_option(&str, &(cfg->monarch_timeout));
- }
} else {
pr_info("mce argument %s ignored. Please use /sys\n", str);
return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 55ad9b3..e99b150 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -1,19 +1,13 @@
/*
- * (c) 2005-2012 Advanced Micro Devices, Inc.
+ * (c) 2005-2015 Advanced Micro Devices, Inc.
* Your use of this code is subject to the terms and conditions of the
* GNU general public license version 2. See "COPYING" or
* http://www.gnu.org/licenses/gpl.html
*
* Written by Jacob Shin - AMD, Inc.
- *
* Maintained by: Borislav Petkov <bp@alien8.de>
*
- * April 2006
- * - added support for AMD Family 0x10 processors
- * May 2012
- * - major scrubbing
- *
- * All MC4_MISCi registers are shared between multi-cores
+ * All MC4_MISCi registers are shared between cores on a node.
*/
#include <linux/interrupt.h>
#include <linux/notifier.h>
@@ -32,6 +26,7 @@
#include <asm/idle.h>
#include <asm/mce.h>
#include <asm/msr.h>
+#include <asm/trace/irq_vectors.h>
#define NR_BLOCKS 9
#define THRESHOLD_MAX 0xFFF
@@ -47,6 +42,13 @@
#define MASK_BLKPTR_LO 0xFF000000
#define MCG_XBLK_ADDR 0xC0000400
+/* Deferred error settings */
+#define MSR_CU_DEF_ERR 0xC0000410
+#define MASK_DEF_LVTOFF 0x000000F0
+#define MASK_DEF_INT_TYPE 0x00000006
+#define DEF_LVT_OFF 0x2
+#define DEF_INT_TYPE_APIC 0x2
+
static const char * const th_names[] = {
"load_store",
"insn_fetch",
@@ -60,6 +62,13 @@
static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */
static void amd_threshold_interrupt(void);
+static void amd_deferred_error_interrupt(void);
+
+static void default_deferred_error_interrupt(void)
+{
+ pr_err("Unexpected deferred interrupt at vector %x\n", DEFERRED_ERROR_VECTOR);
+}
+void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;
/*
* CPU Initialization
@@ -196,7 +205,7 @@
threshold_restart_bank(&tr);
};
-static int setup_APIC_mce(int reserved, int new)
+static int setup_APIC_mce_threshold(int reserved, int new)
{
if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR,
APIC_EILVT_MSG_FIX, 0))
@@ -205,6 +214,39 @@
return reserved;
}
+static int setup_APIC_deferred_error(int reserved, int new)
+{
+ if (reserved < 0 && !setup_APIC_eilvt(new, DEFERRED_ERROR_VECTOR,
+ APIC_EILVT_MSG_FIX, 0))
+ return new;
+
+ return reserved;
+}
+
+static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
+{
+ u32 low = 0, high = 0;
+ int def_offset = -1, def_new;
+
+ if (rdmsr_safe(MSR_CU_DEF_ERR, &low, &high))
+ return;
+
+ def_new = (low & MASK_DEF_LVTOFF) >> 4;
+ if (!(low & MASK_DEF_LVTOFF)) {
+ pr_err(FW_BUG "Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly.\n");
+ def_new = DEF_LVT_OFF;
+ low = (low & ~MASK_DEF_LVTOFF) | (DEF_LVT_OFF << 4);
+ }
+
+ def_offset = setup_APIC_deferred_error(def_offset, def_new);
+ if ((def_offset == def_new) &&
+ (deferred_error_int_vector != amd_deferred_error_interrupt))
+ deferred_error_int_vector = amd_deferred_error_interrupt;
+
+ low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
+ wrmsr(MSR_CU_DEF_ERR, low, high);
+}
+
/* cpu init entry point, called from mce.c with preempt off */
void mce_amd_feature_init(struct cpuinfo_x86 *c)
{
@@ -252,7 +294,7 @@
b.interrupt_enable = 1;
new = (high & MASK_LVTOFF_HI) >> 20;
- offset = setup_APIC_mce(offset, new);
+ offset = setup_APIC_mce_threshold(offset, new);
if ((offset == new) &&
(mce_threshold_vector != amd_threshold_interrupt))
@@ -262,6 +304,73 @@
mce_threshold_block_init(&b, offset);
}
}
+
+ if (mce_flags.succor)
+ deferred_error_interrupt_enable(c);
+}
+
+static void __log_error(unsigned int bank, bool threshold_err, u64 misc)
+{
+ struct mce m;
+ u64 status;
+
+ rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+ if (!(status & MCI_STATUS_VAL))
+ return;
+
+ mce_setup(&m);
+
+ m.status = status;
+ m.bank = bank;
+
+ if (threshold_err)
+ m.misc = misc;
+
+ if (m.status & MCI_STATUS_ADDRV)
+ rdmsrl(MSR_IA32_MCx_ADDR(bank), m.addr);
+
+ mce_log(&m);
+ wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
+}
+
+static inline void __smp_deferred_error_interrupt(void)
+{
+ inc_irq_stat(irq_deferred_error_count);
+ deferred_error_int_vector();
+}
+
+asmlinkage __visible void smp_deferred_error_interrupt(void)
+{
+ entering_irq();
+ __smp_deferred_error_interrupt();
+ exiting_ack_irq();
+}
+
+asmlinkage __visible void smp_trace_deferred_error_interrupt(void)
+{
+ entering_irq();
+ trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR);
+ __smp_deferred_error_interrupt();
+ trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR);
+ exiting_ack_irq();
+}
+
+/* APIC interrupt handler for deferred errors */
+static void amd_deferred_error_interrupt(void)
+{
+ u64 status;
+ unsigned int bank;
+
+ for (bank = 0; bank < mca_cfg.banks; ++bank) {
+ rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+
+ if (!(status & MCI_STATUS_VAL) ||
+ !(status & MCI_STATUS_DEFERRED))
+ continue;
+
+ __log_error(bank, false, 0);
+ break;
+ }
}
/*
@@ -273,12 +382,12 @@
* the interrupt goes off when error_count reaches threshold_limit.
* the handler will simply log mcelog w/ software defined bank number.
*/
+
static void amd_threshold_interrupt(void)
{
u32 low = 0, high = 0, address = 0;
int cpu = smp_processor_id();
unsigned int bank, block;
- struct mce m;
/* assume first bank caused it */
for (bank = 0; bank < mca_cfg.banks; ++bank) {
@@ -321,15 +430,7 @@
return;
log:
- mce_setup(&m);
- rdmsrl(MSR_IA32_MCx_STATUS(bank), m.status);
- if (!(m.status & MCI_STATUS_VAL))
- return;
- m.misc = ((u64)high << 32) | low;
- m.bank = bank;
- mce_log(&m);
-
- wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
+ __log_error(bank, true, ((u64)high << 32) | low);
}
/*
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index b4a41cf..844f56c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -91,6 +91,36 @@
return !!(cap & MCG_CMCI_P);
}
+static bool lmce_supported(void)
+{
+ u64 tmp;
+
+ if (mca_cfg.lmce_disabled)
+ return false;
+
+ rdmsrl(MSR_IA32_MCG_CAP, tmp);
+
+ /*
+ * LMCE depends on recovery support in the processor. Hence both
+ * MCG_SER_P and MCG_LMCE_P should be present in MCG_CAP.
+ */
+ if ((tmp & (MCG_SER_P | MCG_LMCE_P)) !=
+ (MCG_SER_P | MCG_LMCE_P))
+ return false;
+
+ /*
+ * BIOS should indicate support for LMCE by setting bit 20 in
+ * IA32_FEATURE_CONTROL without which touching MCG_EXT_CTL will
+ * generate a #GP fault.
+ */
+ rdmsrl(MSR_IA32_FEATURE_CONTROL, tmp);
+ if ((tmp & (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) ==
+ (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE))
+ return true;
+
+ return false;
+}
+
bool mce_intel_cmci_poll(void)
{
if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
@@ -405,8 +435,22 @@
cmci_recheck();
}
+void intel_init_lmce(void)
+{
+ u64 val;
+
+ if (!lmce_supported())
+ return;
+
+ rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+
+ if (!(val & MCG_EXT_CTL_LMCE_EN))
+ wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
+}
+
void mce_intel_feature_init(struct cpuinfo_x86 *c)
{
intel_init_thermal(c);
intel_init_cmci();
+ intel_init_lmce();
}
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 939155f..aad4bd8 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -39,14 +39,12 @@
{
struct pt_regs *old_regs = set_irq_regs(regs);
- irq_enter();
- exit_idle();
-
+ entering_irq();
inc_irq_stat(irq_hv_callback_count);
if (vmbus_handler)
vmbus_handler();
- irq_exit();
+ exiting_irq();
set_irq_regs(old_regs);
}
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 6367a78..5ee7718 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -4,7 +4,6 @@
#include <linux/bootmem.h>
#include <linux/export.h>
#include <linux/io.h>
-#include <linux/irqdomain.h>
#include <linux/interrupt.h>
#include <linux/list.h>
#include <linux/of.h>
@@ -17,6 +16,7 @@
#include <linux/of_pci.h>
#include <linux/initrd.h>
+#include <asm/irqdomain.h>
#include <asm/hpet.h>
#include <asm/apic.h>
#include <asm/pci_x86.h>
@@ -196,38 +196,31 @@
},
};
-static int ioapic_xlate(struct irq_domain *domain,
- struct device_node *controller,
- const u32 *intspec, u32 intsize,
- irq_hw_number_t *out_hwirq, u32 *out_type)
+static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
{
+ struct of_phandle_args *irq_data = (void *)arg;
struct of_ioapic_type *it;
- u32 line, idx, gsi;
+ struct irq_alloc_info tmp;
- if (WARN_ON(intsize < 2))
+ if (WARN_ON(irq_data->args_count < 2))
+ return -EINVAL;
+ if (irq_data->args[1] >= ARRAY_SIZE(of_ioapic_type))
return -EINVAL;
- line = intspec[0];
+ it = &of_ioapic_type[irq_data->args[1]];
+ ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity);
+ tmp.ioapic_id = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain));
+ tmp.ioapic_pin = irq_data->args[0];
- if (intspec[1] >= ARRAY_SIZE(of_ioapic_type))
- return -EINVAL;
-
- it = &of_ioapic_type[intspec[1]];
-
- idx = (u32)(long)domain->host_data;
- gsi = mp_pin_to_gsi(idx, line);
- if (mp_set_gsi_attr(gsi, it->trigger, it->polarity, cpu_to_node(0)))
- return -EBUSY;
-
- *out_hwirq = line;
- *out_type = it->out_type;
- return 0;
+ return mp_irqdomain_alloc(domain, virq, nr_irqs, &tmp);
}
-const struct irq_domain_ops ioapic_irq_domain_ops = {
- .map = mp_irqdomain_map,
- .unmap = mp_irqdomain_unmap,
- .xlate = ioapic_xlate,
+static const struct irq_domain_ops ioapic_irq_domain_ops = {
+ .alloc = dt_irqdomain_alloc,
+ .free = mp_irqdomain_free,
+ .activate = mp_irqdomain_activate,
+ .deactivate = mp_irqdomain_deactivate,
};
static void __init dtb_add_ioapic(struct device_node *dn)
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index fe9f0b7..5cb9a4d 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -627,8 +627,12 @@
{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID,
QFLAG_APPLY_ONCE, intel_graphics_stolen },
/*
- * HPET on current version of Baytrail platform has accuracy
- * problems, disable it for now:
+ * HPET on the current version of the Baytrail platform has accuracy
+ * problems: it will halt in deep idle state - so we disable it.
+ *
+ * More details can be found in section 18.10.1.3 of the datasheet:
+ *
+ * http://www.intel.com/content/dam/www/public/us/en/documents/datasheets/atom-z8000-datasheet-vol-1.pdf
*/
{ PCI_VENDOR_ID_INTEL, 0x0f00,
PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
deleted file mode 100644
index 1c30976..0000000
--- a/arch/x86/kernel/entry_32.S
+++ /dev/null
@@ -1,1401 +0,0 @@
-/*
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- */
-
-/*
- * entry.S contains the system-call and fault low-level handling routines.
- * This also contains the timer-interrupt handler, as well as all interrupts
- * and faults that can result in a task-switch.
- *
- * NOTE: This code handles signal-recognition, which happens every time
- * after a timer-interrupt and after each system call.
- *
- * I changed all the .align's to 4 (16 byte alignment), as that's faster
- * on a 486.
- *
- * Stack layout in 'syscall_exit':
- * ptrace needs to have all regs on the stack.
- * if the order here is changed, it needs to be
- * updated in fork.c:copy_process, signal.c:do_signal,
- * ptrace.c and ptrace.h
- *
- * 0(%esp) - %ebx
- * 4(%esp) - %ecx
- * 8(%esp) - %edx
- * C(%esp) - %esi
- * 10(%esp) - %edi
- * 14(%esp) - %ebp
- * 18(%esp) - %eax
- * 1C(%esp) - %ds
- * 20(%esp) - %es
- * 24(%esp) - %fs
- * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS
- * 2C(%esp) - orig_eax
- * 30(%esp) - %eip
- * 34(%esp) - %cs
- * 38(%esp) - %eflags
- * 3C(%esp) - %oldesp
- * 40(%esp) - %oldss
- *
- * "current" is in register %ebx during any slow entries.
- */
-
-#include <linux/linkage.h>
-#include <linux/err.h>
-#include <asm/thread_info.h>
-#include <asm/irqflags.h>
-#include <asm/errno.h>
-#include <asm/segment.h>
-#include <asm/smp.h>
-#include <asm/page_types.h>
-#include <asm/percpu.h>
-#include <asm/dwarf2.h>
-#include <asm/processor-flags.h>
-#include <asm/ftrace.h>
-#include <asm/irq_vectors.h>
-#include <asm/cpufeature.h>
-#include <asm/alternative-asm.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_LE 0x40000000
-
-#ifndef CONFIG_AUDITSYSCALL
-#define sysenter_audit syscall_trace_entry
-#define sysexit_audit syscall_exit_work
-#endif
-
- .section .entry.text, "ax"
-
-/*
- * We use macros for low-level operations which need to be overridden
- * for paravirtualization. The following will never clobber any registers:
- * INTERRUPT_RETURN (aka. "iret")
- * GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
- * ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
- *
- * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
- * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
- * Allowing a register to be clobbered can shrink the paravirt replacement
- * enough to patch inline, increasing performance.
- */
-
-#ifdef CONFIG_PREEMPT
-#define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
-#else
-#define preempt_stop(clobbers)
-#define resume_kernel restore_all
-#endif
-
-.macro TRACE_IRQS_IRET
-#ifdef CONFIG_TRACE_IRQFLAGS
- testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off?
- jz 1f
- TRACE_IRQS_ON
-1:
-#endif
-.endm
-
-/*
- * User gs save/restore
- *
- * %gs is used for userland TLS and kernel only uses it for stack
- * canary which is required to be at %gs:20 by gcc. Read the comment
- * at the top of stackprotector.h for more info.
- *
- * Local labels 98 and 99 are used.
- */
-#ifdef CONFIG_X86_32_LAZY_GS
-
- /* unfortunately push/pop can't be no-op */
-.macro PUSH_GS
- pushl_cfi $0
-.endm
-.macro POP_GS pop=0
- addl $(4 + \pop), %esp
- CFI_ADJUST_CFA_OFFSET -(4 + \pop)
-.endm
-.macro POP_GS_EX
-.endm
-
- /* all the rest are no-op */
-.macro PTGS_TO_GS
-.endm
-.macro PTGS_TO_GS_EX
-.endm
-.macro GS_TO_REG reg
-.endm
-.macro REG_TO_PTGS reg
-.endm
-.macro SET_KERNEL_GS reg
-.endm
-
-#else /* CONFIG_X86_32_LAZY_GS */
-
-.macro PUSH_GS
- pushl_cfi %gs
- /*CFI_REL_OFFSET gs, 0*/
-.endm
-
-.macro POP_GS pop=0
-98: popl_cfi %gs
- /*CFI_RESTORE gs*/
- .if \pop <> 0
- add $\pop, %esp
- CFI_ADJUST_CFA_OFFSET -\pop
- .endif
-.endm
-.macro POP_GS_EX
-.pushsection .fixup, "ax"
-99: movl $0, (%esp)
- jmp 98b
-.popsection
- _ASM_EXTABLE(98b,99b)
-.endm
-
-.macro PTGS_TO_GS
-98: mov PT_GS(%esp), %gs
-.endm
-.macro PTGS_TO_GS_EX
-.pushsection .fixup, "ax"
-99: movl $0, PT_GS(%esp)
- jmp 98b
-.popsection
- _ASM_EXTABLE(98b,99b)
-.endm
-
-.macro GS_TO_REG reg
- movl %gs, \reg
- /*CFI_REGISTER gs, \reg*/
-.endm
-.macro REG_TO_PTGS reg
- movl \reg, PT_GS(%esp)
- /*CFI_REL_OFFSET gs, PT_GS*/
-.endm
-.macro SET_KERNEL_GS reg
- movl $(__KERNEL_STACK_CANARY), \reg
- movl \reg, %gs
-.endm
-
-#endif /* CONFIG_X86_32_LAZY_GS */
-
-.macro SAVE_ALL
- cld
- PUSH_GS
- pushl_cfi %fs
- /*CFI_REL_OFFSET fs, 0;*/
- pushl_cfi %es
- /*CFI_REL_OFFSET es, 0;*/
- pushl_cfi %ds
- /*CFI_REL_OFFSET ds, 0;*/
- pushl_cfi %eax
- CFI_REL_OFFSET eax, 0
- pushl_cfi %ebp
- CFI_REL_OFFSET ebp, 0
- pushl_cfi %edi
- CFI_REL_OFFSET edi, 0
- pushl_cfi %esi
- CFI_REL_OFFSET esi, 0
- pushl_cfi %edx
- CFI_REL_OFFSET edx, 0
- pushl_cfi %ecx
- CFI_REL_OFFSET ecx, 0
- pushl_cfi %ebx
- CFI_REL_OFFSET ebx, 0
- movl $(__USER_DS), %edx
- movl %edx, %ds
- movl %edx, %es
- movl $(__KERNEL_PERCPU), %edx
- movl %edx, %fs
- SET_KERNEL_GS %edx
-.endm
-
-.macro RESTORE_INT_REGS
- popl_cfi %ebx
- CFI_RESTORE ebx
- popl_cfi %ecx
- CFI_RESTORE ecx
- popl_cfi %edx
- CFI_RESTORE edx
- popl_cfi %esi
- CFI_RESTORE esi
- popl_cfi %edi
- CFI_RESTORE edi
- popl_cfi %ebp
- CFI_RESTORE ebp
- popl_cfi %eax
- CFI_RESTORE eax
-.endm
-
-.macro RESTORE_REGS pop=0
- RESTORE_INT_REGS
-1: popl_cfi %ds
- /*CFI_RESTORE ds;*/
-2: popl_cfi %es
- /*CFI_RESTORE es;*/
-3: popl_cfi %fs
- /*CFI_RESTORE fs;*/
- POP_GS \pop
-.pushsection .fixup, "ax"
-4: movl $0, (%esp)
- jmp 1b
-5: movl $0, (%esp)
- jmp 2b
-6: movl $0, (%esp)
- jmp 3b
-.popsection
- _ASM_EXTABLE(1b,4b)
- _ASM_EXTABLE(2b,5b)
- _ASM_EXTABLE(3b,6b)
- POP_GS_EX
-.endm
-
-.macro RING0_INT_FRAME
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA esp, 3*4
- /*CFI_OFFSET cs, -2*4;*/
- CFI_OFFSET eip, -3*4
-.endm
-
-.macro RING0_EC_FRAME
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA esp, 4*4
- /*CFI_OFFSET cs, -2*4;*/
- CFI_OFFSET eip, -3*4
-.endm
-
-.macro RING0_PTREGS_FRAME
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA esp, PT_OLDESP-PT_EBX
- /*CFI_OFFSET cs, PT_CS-PT_OLDESP;*/
- CFI_OFFSET eip, PT_EIP-PT_OLDESP
- /*CFI_OFFSET es, PT_ES-PT_OLDESP;*/
- /*CFI_OFFSET ds, PT_DS-PT_OLDESP;*/
- CFI_OFFSET eax, PT_EAX-PT_OLDESP
- CFI_OFFSET ebp, PT_EBP-PT_OLDESP
- CFI_OFFSET edi, PT_EDI-PT_OLDESP
- CFI_OFFSET esi, PT_ESI-PT_OLDESP
- CFI_OFFSET edx, PT_EDX-PT_OLDESP
- CFI_OFFSET ecx, PT_ECX-PT_OLDESP
- CFI_OFFSET ebx, PT_EBX-PT_OLDESP
-.endm
-
-ENTRY(ret_from_fork)
- CFI_STARTPROC
- pushl_cfi %eax
- call schedule_tail
- GET_THREAD_INFO(%ebp)
- popl_cfi %eax
- pushl_cfi $0x0202 # Reset kernel eflags
- popfl_cfi
- jmp syscall_exit
- CFI_ENDPROC
-END(ret_from_fork)
-
-ENTRY(ret_from_kernel_thread)
- CFI_STARTPROC
- pushl_cfi %eax
- call schedule_tail
- GET_THREAD_INFO(%ebp)
- popl_cfi %eax
- pushl_cfi $0x0202 # Reset kernel eflags
- popfl_cfi
- movl PT_EBP(%esp),%eax
- call *PT_EBX(%esp)
- movl $0,PT_EAX(%esp)
- jmp syscall_exit
- CFI_ENDPROC
-ENDPROC(ret_from_kernel_thread)
-
-/*
- * Return to user mode is not as complex as all this looks,
- * but we want the default path for a system call return to
- * go as quickly as possible which is why some of this is
- * less clear than it otherwise should be.
- */
-
- # userspace resumption stub bypassing syscall exit tracing
- ALIGN
- RING0_PTREGS_FRAME
-ret_from_exception:
- preempt_stop(CLBR_ANY)
-ret_from_intr:
- GET_THREAD_INFO(%ebp)
-#ifdef CONFIG_VM86
- movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS
- movb PT_CS(%esp), %al
- andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
-#else
- /*
- * We can be coming here from child spawned by kernel_thread().
- */
- movl PT_CS(%esp), %eax
- andl $SEGMENT_RPL_MASK, %eax
-#endif
- cmpl $USER_RPL, %eax
- jb resume_kernel # not returning to v8086 or userspace
-
-ENTRY(resume_userspace)
- LOCKDEP_SYS_EXIT
- DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
- # setting need_resched or sigpending
- # between sampling and the iret
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- andl $_TIF_WORK_MASK, %ecx # is there any work to be done on
- # int/exception return?
- jne work_pending
- jmp restore_all
-END(ret_from_exception)
-
-#ifdef CONFIG_PREEMPT
-ENTRY(resume_kernel)
- DISABLE_INTERRUPTS(CLBR_ANY)
-need_resched:
- cmpl $0,PER_CPU_VAR(__preempt_count)
- jnz restore_all
- testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ?
- jz restore_all
- call preempt_schedule_irq
- jmp need_resched
-END(resume_kernel)
-#endif
- CFI_ENDPROC
-
-/* SYSENTER_RETURN points to after the "sysenter" instruction in
- the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */
-
- # sysenter call handler stub
-ENTRY(ia32_sysenter_target)
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA esp, 0
- CFI_REGISTER esp, ebp
- movl TSS_sysenter_sp0(%esp),%esp
-sysenter_past_esp:
- /*
- * Interrupts are disabled here, but we can't trace it until
- * enough kernel state to call TRACE_IRQS_OFF can be called - but
- * we immediately enable interrupts at that point anyway.
- */
- pushl_cfi $__USER_DS
- /*CFI_REL_OFFSET ss, 0*/
- pushl_cfi %ebp
- CFI_REL_OFFSET esp, 0
- pushfl_cfi
- orl $X86_EFLAGS_IF, (%esp)
- pushl_cfi $__USER_CS
- /*CFI_REL_OFFSET cs, 0*/
- /*
- * Push current_thread_info()->sysenter_return to the stack.
- * A tiny bit of offset fixup is necessary: TI_sysenter_return
- * is relative to thread_info, which is at the bottom of the
- * kernel stack page. 4*4 means the 4 words pushed above;
- * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
- * and THREAD_SIZE takes us to the bottom.
- */
- pushl_cfi ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)
- CFI_REL_OFFSET eip, 0
-
- pushl_cfi %eax
- SAVE_ALL
- ENABLE_INTERRUPTS(CLBR_NONE)
-
-/*
- * Load the potential sixth argument from user stack.
- * Careful about security.
- */
- cmpl $__PAGE_OFFSET-3,%ebp
- jae syscall_fault
- ASM_STAC
-1: movl (%ebp),%ebp
- ASM_CLAC
- movl %ebp,PT_EBP(%esp)
- _ASM_EXTABLE(1b,syscall_fault)
-
- GET_THREAD_INFO(%ebp)
-
- testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
- jnz sysenter_audit
-sysenter_do_call:
- cmpl $(NR_syscalls), %eax
- jae sysenter_badsys
- call *sys_call_table(,%eax,4)
-sysenter_after_call:
- movl %eax,PT_EAX(%esp)
- LOCKDEP_SYS_EXIT
- DISABLE_INTERRUPTS(CLBR_ANY)
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- testl $_TIF_ALLWORK_MASK, %ecx
- jnz sysexit_audit
-sysenter_exit:
-/* if something modifies registers it must also disable sysexit */
- movl PT_EIP(%esp), %edx
- movl PT_OLDESP(%esp), %ecx
- xorl %ebp,%ebp
- TRACE_IRQS_ON
-1: mov PT_FS(%esp), %fs
- PTGS_TO_GS
- ENABLE_INTERRUPTS_SYSEXIT
-
-#ifdef CONFIG_AUDITSYSCALL
-sysenter_audit:
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
- jnz syscall_trace_entry
- /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */
- movl PT_EBX(%esp), %edx /* ebx/a0: 2nd arg to audit */
- /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */
- pushl_cfi PT_ESI(%esp) /* a3: 5th arg */
- pushl_cfi PT_EDX+4(%esp) /* a2: 4th arg */
- call __audit_syscall_entry
- popl_cfi %ecx /* get that remapped edx off the stack */
- popl_cfi %ecx /* get that remapped esi off the stack */
- movl PT_EAX(%esp),%eax /* reload syscall number */
- jmp sysenter_do_call
-
-sysexit_audit:
- testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
- jnz syscall_exit_work
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_ANY)
- movl %eax,%edx /* second arg, syscall return value */
- cmpl $-MAX_ERRNO,%eax /* is it an error ? */
- setbe %al /* 1 if so, 0 if not */
- movzbl %al,%eax /* zero-extend that */
- call __audit_syscall_exit
- DISABLE_INTERRUPTS(CLBR_ANY)
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
- jnz syscall_exit_work
- movl PT_EAX(%esp),%eax /* reload syscall return value */
- jmp sysenter_exit
-#endif
-
- CFI_ENDPROC
-.pushsection .fixup,"ax"
-2: movl $0,PT_FS(%esp)
- jmp 1b
-.popsection
- _ASM_EXTABLE(1b,2b)
- PTGS_TO_GS_EX
-ENDPROC(ia32_sysenter_target)
-
- # system call handler stub
-ENTRY(system_call)
- RING0_INT_FRAME # can't unwind into user space anyway
- ASM_CLAC
- pushl_cfi %eax # save orig_eax
- SAVE_ALL
- GET_THREAD_INFO(%ebp)
- # system call tracing in operation / emulation
- testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
- jnz syscall_trace_entry
- cmpl $(NR_syscalls), %eax
- jae syscall_badsys
-syscall_call:
- call *sys_call_table(,%eax,4)
-syscall_after_call:
- movl %eax,PT_EAX(%esp) # store the return value
-syscall_exit:
- LOCKDEP_SYS_EXIT
- DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
- # setting need_resched or sigpending
- # between sampling and the iret
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- testl $_TIF_ALLWORK_MASK, %ecx # current->work
- jnz syscall_exit_work
-
-restore_all:
- TRACE_IRQS_IRET
-restore_all_notrace:
-#ifdef CONFIG_X86_ESPFIX32
- movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
- # Warning: PT_OLDSS(%esp) contains the wrong/random values if we
- # are returning to the kernel.
- # See comments in process.c:copy_thread() for details.
- movb PT_OLDSS(%esp), %ah
- movb PT_CS(%esp), %al
- andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
- cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
- CFI_REMEMBER_STATE
- je ldt_ss # returning to user-space with LDT SS
-#endif
-restore_nocheck:
- RESTORE_REGS 4 # skip orig_eax/error_code
-irq_return:
- INTERRUPT_RETURN
-.section .fixup,"ax"
-ENTRY(iret_exc)
- pushl $0 # no error code
- pushl $do_iret_error
- jmp error_code
-.previous
- _ASM_EXTABLE(irq_return,iret_exc)
-
-#ifdef CONFIG_X86_ESPFIX32
- CFI_RESTORE_STATE
-ldt_ss:
-#ifdef CONFIG_PARAVIRT
- /*
- * The kernel can't run on a non-flat stack if paravirt mode
- * is active. Rather than try to fixup the high bits of
- * ESP, bypass this code entirely. This may break DOSemu
- * and/or Wine support in a paravirt VM, although the option
- * is still available to implement the setting of the high
- * 16-bits in the INTERRUPT_RETURN paravirt-op.
- */
- cmpl $0, pv_info+PARAVIRT_enabled
- jne restore_nocheck
-#endif
-
-/*
- * Setup and switch to ESPFIX stack
- *
- * We're returning to userspace with a 16 bit stack. The CPU will not
- * restore the high word of ESP for us on executing iret... This is an
- * "official" bug of all the x86-compatible CPUs, which we can work
- * around to make dosemu and wine happy. We do this by preloading the
- * high word of ESP with the high word of the userspace ESP while
- * compensating for the offset by changing to the ESPFIX segment with
- * a base address that matches for the difference.
- */
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
- mov %esp, %edx /* load kernel esp */
- mov PT_OLDESP(%esp), %eax /* load userspace esp */
- mov %dx, %ax /* eax: new kernel esp */
- sub %eax, %edx /* offset (low word is 0) */
- shr $16, %edx
- mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
- mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
- pushl_cfi $__ESPFIX_SS
- pushl_cfi %eax /* new kernel esp */
- /* Disable interrupts, but do not irqtrace this section: we
- * will soon execute iret and the tracer was already set to
- * the irqstate after the iret */
- DISABLE_INTERRUPTS(CLBR_EAX)
- lss (%esp), %esp /* switch to espfix segment */
- CFI_ADJUST_CFA_OFFSET -8
- jmp restore_nocheck
-#endif
- CFI_ENDPROC
-ENDPROC(system_call)
-
- # perform work that needs to be done immediately before resumption
- ALIGN
- RING0_PTREGS_FRAME # can't unwind into user space anyway
-work_pending:
- testb $_TIF_NEED_RESCHED, %cl
- jz work_notifysig
-work_resched:
- call schedule
- LOCKDEP_SYS_EXIT
- DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
- # setting need_resched or sigpending
- # between sampling and the iret
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- andl $_TIF_WORK_MASK, %ecx # is there any work to be done other
- # than syscall tracing?
- jz restore_all
- testb $_TIF_NEED_RESCHED, %cl
- jnz work_resched
-
-work_notifysig: # deal with pending signals and
- # notify-resume requests
-#ifdef CONFIG_VM86
- testl $X86_EFLAGS_VM, PT_EFLAGS(%esp)
- movl %esp, %eax
- jnz work_notifysig_v86 # returning to kernel-space or
- # vm86-space
-1:
-#else
- movl %esp, %eax
-#endif
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- movb PT_CS(%esp), %bl
- andb $SEGMENT_RPL_MASK, %bl
- cmpb $USER_RPL, %bl
- jb resume_kernel
- xorl %edx, %edx
- call do_notify_resume
- jmp resume_userspace
-
-#ifdef CONFIG_VM86
- ALIGN
-work_notifysig_v86:
- pushl_cfi %ecx # save ti_flags for do_notify_resume
- call save_v86_state # %eax contains pt_regs pointer
- popl_cfi %ecx
- movl %eax, %esp
- jmp 1b
-#endif
-END(work_pending)
-
- # perform syscall exit tracing
- ALIGN
-syscall_trace_entry:
- movl $-ENOSYS,PT_EAX(%esp)
- movl %esp, %eax
- call syscall_trace_enter
- /* What it returned is what we'll actually use. */
- cmpl $(NR_syscalls), %eax
- jnae syscall_call
- jmp syscall_exit
-END(syscall_trace_entry)
-
- # perform syscall exit tracing
- ALIGN
-syscall_exit_work:
- testl $_TIF_WORK_SYSCALL_EXIT, %ecx
- jz work_pending
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call
- # schedule() instead
- movl %esp, %eax
- call syscall_trace_leave
- jmp resume_userspace
-END(syscall_exit_work)
- CFI_ENDPROC
-
- RING0_INT_FRAME # can't unwind into user space anyway
-syscall_fault:
- ASM_CLAC
- GET_THREAD_INFO(%ebp)
- movl $-EFAULT,PT_EAX(%esp)
- jmp resume_userspace
-END(syscall_fault)
-
-syscall_badsys:
- movl $-ENOSYS,%eax
- jmp syscall_after_call
-END(syscall_badsys)
-
-sysenter_badsys:
- movl $-ENOSYS,%eax
- jmp sysenter_after_call
-END(sysenter_badsys)
- CFI_ENDPROC
-
-.macro FIXUP_ESPFIX_STACK
-/*
- * Switch back for ESPFIX stack to the normal zerobased stack
- *
- * We can't call C functions using the ESPFIX stack. This code reads
- * the high word of the segment base from the GDT and swiches to the
- * normal stack and adjusts ESP with the matching offset.
- */
-#ifdef CONFIG_X86_ESPFIX32
- /* fixup the stack */
- mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
- mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
- shl $16, %eax
- addl %esp, %eax /* the adjusted stack pointer */
- pushl_cfi $__KERNEL_DS
- pushl_cfi %eax
- lss (%esp), %esp /* switch to the normal stack segment */
- CFI_ADJUST_CFA_OFFSET -8
-#endif
-.endm
-.macro UNWIND_ESPFIX_STACK
-#ifdef CONFIG_X86_ESPFIX32
- movl %ss, %eax
- /* see if on espfix stack */
- cmpw $__ESPFIX_SS, %ax
- jne 27f
- movl $__KERNEL_DS, %eax
- movl %eax, %ds
- movl %eax, %es
- /* switch to normal stack */
- FIXUP_ESPFIX_STACK
-27:
-#endif
-.endm
-
-/*
- * Build the entry stubs with some assembler magic.
- * We pack 1 stub into every 8-byte block.
- */
- .align 8
-ENTRY(irq_entries_start)
- RING0_INT_FRAME
- vector=FIRST_EXTERNAL_VECTOR
- .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
- pushl_cfi $(~vector+0x80) /* Note: always in signed byte range */
- vector=vector+1
- jmp common_interrupt
- CFI_ADJUST_CFA_OFFSET -4
- .align 8
- .endr
-END(irq_entries_start)
-
-/*
- * the CPU automatically disables interrupts when executing an IRQ vector,
- * so IRQ-flags tracing has to follow that:
- */
- .p2align CONFIG_X86_L1_CACHE_SHIFT
-common_interrupt:
- ASM_CLAC
- addl $-0x80,(%esp) /* Adjust vector into the [-256,-1] range */
- SAVE_ALL
- TRACE_IRQS_OFF
- movl %esp,%eax
- call do_IRQ
- jmp ret_from_intr
-ENDPROC(common_interrupt)
- CFI_ENDPROC
-
-#define BUILD_INTERRUPT3(name, nr, fn) \
-ENTRY(name) \
- RING0_INT_FRAME; \
- ASM_CLAC; \
- pushl_cfi $~(nr); \
- SAVE_ALL; \
- TRACE_IRQS_OFF \
- movl %esp,%eax; \
- call fn; \
- jmp ret_from_intr; \
- CFI_ENDPROC; \
-ENDPROC(name)
-
-
-#ifdef CONFIG_TRACING
-#define TRACE_BUILD_INTERRUPT(name, nr) \
- BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name)
-#else
-#define TRACE_BUILD_INTERRUPT(name, nr)
-#endif
-
-#define BUILD_INTERRUPT(name, nr) \
- BUILD_INTERRUPT3(name, nr, smp_##name); \
- TRACE_BUILD_INTERRUPT(name, nr)
-
-/* The include is where all of the SMP etc. interrupts come from */
-#include <asm/entry_arch.h>
-
-ENTRY(coprocessor_error)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_coprocessor_error
- jmp error_code
- CFI_ENDPROC
-END(coprocessor_error)
-
-ENTRY(simd_coprocessor_error)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
-#ifdef CONFIG_X86_INVD_BUG
- /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
- ALTERNATIVE "pushl_cfi $do_general_protection", \
- "pushl $do_simd_coprocessor_error", \
- X86_FEATURE_XMM
-#else
- pushl_cfi $do_simd_coprocessor_error
-#endif
- jmp error_code
- CFI_ENDPROC
-END(simd_coprocessor_error)
-
-ENTRY(device_not_available)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $-1 # mark this as an int
- pushl_cfi $do_device_not_available
- jmp error_code
- CFI_ENDPROC
-END(device_not_available)
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_iret)
- iret
- _ASM_EXTABLE(native_iret, iret_exc)
-END(native_iret)
-
-ENTRY(native_irq_enable_sysexit)
- sti
- sysexit
-END(native_irq_enable_sysexit)
-#endif
-
-ENTRY(overflow)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_overflow
- jmp error_code
- CFI_ENDPROC
-END(overflow)
-
-ENTRY(bounds)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_bounds
- jmp error_code
- CFI_ENDPROC
-END(bounds)
-
-ENTRY(invalid_op)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_invalid_op
- jmp error_code
- CFI_ENDPROC
-END(invalid_op)
-
-ENTRY(coprocessor_segment_overrun)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_coprocessor_segment_overrun
- jmp error_code
- CFI_ENDPROC
-END(coprocessor_segment_overrun)
-
-ENTRY(invalid_TSS)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_invalid_TSS
- jmp error_code
- CFI_ENDPROC
-END(invalid_TSS)
-
-ENTRY(segment_not_present)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_segment_not_present
- jmp error_code
- CFI_ENDPROC
-END(segment_not_present)
-
-ENTRY(stack_segment)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_stack_segment
- jmp error_code
- CFI_ENDPROC
-END(stack_segment)
-
-ENTRY(alignment_check)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_alignment_check
- jmp error_code
- CFI_ENDPROC
-END(alignment_check)
-
-ENTRY(divide_error)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0 # no error code
- pushl_cfi $do_divide_error
- jmp error_code
- CFI_ENDPROC
-END(divide_error)
-
-#ifdef CONFIG_X86_MCE
-ENTRY(machine_check)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi machine_check_vector
- jmp error_code
- CFI_ENDPROC
-END(machine_check)
-#endif
-
-ENTRY(spurious_interrupt_bug)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_spurious_interrupt_bug
- jmp error_code
- CFI_ENDPROC
-END(spurious_interrupt_bug)
-
-#ifdef CONFIG_XEN
-/* Xen doesn't set %esp to be precisely what the normal sysenter
- entrypoint expects, so fix it up before using the normal path. */
-ENTRY(xen_sysenter_target)
- RING0_INT_FRAME
- addl $5*4, %esp /* remove xen-provided frame */
- CFI_ADJUST_CFA_OFFSET -5*4
- jmp sysenter_past_esp
- CFI_ENDPROC
-
-ENTRY(xen_hypervisor_callback)
- CFI_STARTPROC
- pushl_cfi $-1 /* orig_ax = -1 => not a system call */
- SAVE_ALL
- TRACE_IRQS_OFF
-
- /* Check to see if we got the event in the critical
- region in xen_iret_direct, after we've reenabled
- events and checked for pending events. This simulates
- iret instruction's behaviour where it delivers a
- pending interrupt when enabling interrupts. */
- movl PT_EIP(%esp),%eax
- cmpl $xen_iret_start_crit,%eax
- jb 1f
- cmpl $xen_iret_end_crit,%eax
- jae 1f
-
- jmp xen_iret_crit_fixup
-
-ENTRY(xen_do_upcall)
-1: mov %esp, %eax
- call xen_evtchn_do_upcall
-#ifndef CONFIG_PREEMPT
- call xen_maybe_preempt_hcall
-#endif
- jmp ret_from_intr
- CFI_ENDPROC
-ENDPROC(xen_hypervisor_callback)
-
-# Hypervisor uses this for application faults while it executes.
-# We get here for two reasons:
-# 1. Fault while reloading DS, ES, FS or GS
-# 2. Fault while executing IRET
-# Category 1 we fix up by reattempting the load, and zeroing the segment
-# register if the load fails.
-# Category 2 we fix up by jumping to do_iret_error. We cannot use the
-# normal Linux return path in this case because if we use the IRET hypercall
-# to pop the stack frame we end up in an infinite loop of failsafe callbacks.
-# We distinguish between categories by maintaining a status value in EAX.
-ENTRY(xen_failsafe_callback)
- CFI_STARTPROC
- pushl_cfi %eax
- movl $1,%eax
-1: mov 4(%esp),%ds
-2: mov 8(%esp),%es
-3: mov 12(%esp),%fs
-4: mov 16(%esp),%gs
- /* EAX == 0 => Category 1 (Bad segment)
- EAX != 0 => Category 2 (Bad IRET) */
- testl %eax,%eax
- popl_cfi %eax
- lea 16(%esp),%esp
- CFI_ADJUST_CFA_OFFSET -16
- jz 5f
- jmp iret_exc
-5: pushl_cfi $-1 /* orig_ax = -1 => not a system call */
- SAVE_ALL
- jmp ret_from_exception
- CFI_ENDPROC
-
-.section .fixup,"ax"
-6: xorl %eax,%eax
- movl %eax,4(%esp)
- jmp 1b
-7: xorl %eax,%eax
- movl %eax,8(%esp)
- jmp 2b
-8: xorl %eax,%eax
- movl %eax,12(%esp)
- jmp 3b
-9: xorl %eax,%eax
- movl %eax,16(%esp)
- jmp 4b
-.previous
- _ASM_EXTABLE(1b,6b)
- _ASM_EXTABLE(2b,7b)
- _ASM_EXTABLE(3b,8b)
- _ASM_EXTABLE(4b,9b)
-ENDPROC(xen_failsafe_callback)
-
-BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
- xen_evtchn_do_upcall)
-
-#endif /* CONFIG_XEN */
-
-#if IS_ENABLED(CONFIG_HYPERV)
-
-BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
- hyperv_vector_handler)
-
-#endif /* CONFIG_HYPERV */
-
-#ifdef CONFIG_FUNCTION_TRACER
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-ENTRY(mcount)
- ret
-END(mcount)
-
-ENTRY(ftrace_caller)
- pushl %eax
- pushl %ecx
- pushl %edx
- pushl $0 /* Pass NULL as regs pointer */
- movl 4*4(%esp), %eax
- movl 0x4(%ebp), %edx
- movl function_trace_op, %ecx
- subl $MCOUNT_INSN_SIZE, %eax
-
-.globl ftrace_call
-ftrace_call:
- call ftrace_stub
-
- addl $4,%esp /* skip NULL pointer */
- popl %edx
- popl %ecx
- popl %eax
-ftrace_ret:
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-.globl ftrace_graph_call
-ftrace_graph_call:
- jmp ftrace_stub
-#endif
-
-.globl ftrace_stub
-ftrace_stub:
- ret
-END(ftrace_caller)
-
-ENTRY(ftrace_regs_caller)
- pushf /* push flags before compare (in cs location) */
-
- /*
- * i386 does not save SS and ESP when coming from kernel.
- * Instead, to get sp, ®s->sp is used (see ptrace.h).
- * Unfortunately, that means eflags must be at the same location
- * as the current return ip is. We move the return ip into the
- * ip location, and move flags into the return ip location.
- */
- pushl 4(%esp) /* save return ip into ip slot */
-
- pushl $0 /* Load 0 into orig_ax */
- pushl %gs
- pushl %fs
- pushl %es
- pushl %ds
- pushl %eax
- pushl %ebp
- pushl %edi
- pushl %esi
- pushl %edx
- pushl %ecx
- pushl %ebx
-
- movl 13*4(%esp), %eax /* Get the saved flags */
- movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */
- /* clobbering return ip */
- movl $__KERNEL_CS,13*4(%esp)
-
- movl 12*4(%esp), %eax /* Load ip (1st parameter) */
- subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */
- movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */
- movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
- pushl %esp /* Save pt_regs as 4th parameter */
-
-GLOBAL(ftrace_regs_call)
- call ftrace_stub
-
- addl $4, %esp /* Skip pt_regs */
- movl 14*4(%esp), %eax /* Move flags back into cs */
- movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */
- movl 12*4(%esp), %eax /* Get return ip from regs->ip */
- movl %eax, 14*4(%esp) /* Put return ip back for ret */
-
- popl %ebx
- popl %ecx
- popl %edx
- popl %esi
- popl %edi
- popl %ebp
- popl %eax
- popl %ds
- popl %es
- popl %fs
- popl %gs
- addl $8, %esp /* Skip orig_ax and ip */
- popf /* Pop flags at end (no addl to corrupt flags) */
- jmp ftrace_ret
-
- popf
- jmp ftrace_stub
-#else /* ! CONFIG_DYNAMIC_FTRACE */
-
-ENTRY(mcount)
- cmpl $__PAGE_OFFSET, %esp
- jb ftrace_stub /* Paging not enabled yet? */
-
- cmpl $ftrace_stub, ftrace_trace_function
- jnz trace
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- cmpl $ftrace_stub, ftrace_graph_return
- jnz ftrace_graph_caller
-
- cmpl $ftrace_graph_entry_stub, ftrace_graph_entry
- jnz ftrace_graph_caller
-#endif
-.globl ftrace_stub
-ftrace_stub:
- ret
-
- /* taken from glibc */
-trace:
- pushl %eax
- pushl %ecx
- pushl %edx
- movl 0xc(%esp), %eax
- movl 0x4(%ebp), %edx
- subl $MCOUNT_INSN_SIZE, %eax
-
- call *ftrace_trace_function
-
- popl %edx
- popl %ecx
- popl %eax
- jmp ftrace_stub
-END(mcount)
-#endif /* CONFIG_DYNAMIC_FTRACE */
-#endif /* CONFIG_FUNCTION_TRACER */
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
- pushl %eax
- pushl %ecx
- pushl %edx
- movl 0xc(%esp), %eax
- lea 0x4(%ebp), %edx
- movl (%ebp), %ecx
- subl $MCOUNT_INSN_SIZE, %eax
- call prepare_ftrace_return
- popl %edx
- popl %ecx
- popl %eax
- ret
-END(ftrace_graph_caller)
-
-.globl return_to_handler
-return_to_handler:
- pushl %eax
- pushl %edx
- movl %ebp, %eax
- call ftrace_return_to_handler
- movl %eax, %ecx
- popl %edx
- popl %eax
- jmp *%ecx
-#endif
-
-#ifdef CONFIG_TRACING
-ENTRY(trace_page_fault)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $trace_do_page_fault
- jmp error_code
- CFI_ENDPROC
-END(trace_page_fault)
-#endif
-
-ENTRY(page_fault)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_page_fault
- ALIGN
-error_code:
- /* the function address is in %gs's slot on the stack */
- pushl_cfi %fs
- /*CFI_REL_OFFSET fs, 0*/
- pushl_cfi %es
- /*CFI_REL_OFFSET es, 0*/
- pushl_cfi %ds
- /*CFI_REL_OFFSET ds, 0*/
- pushl_cfi_reg eax
- pushl_cfi_reg ebp
- pushl_cfi_reg edi
- pushl_cfi_reg esi
- pushl_cfi_reg edx
- pushl_cfi_reg ecx
- pushl_cfi_reg ebx
- cld
- movl $(__KERNEL_PERCPU), %ecx
- movl %ecx, %fs
- UNWIND_ESPFIX_STACK
- GS_TO_REG %ecx
- movl PT_GS(%esp), %edi # get the function address
- movl PT_ORIG_EAX(%esp), %edx # get the error code
- movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart
- REG_TO_PTGS %ecx
- SET_KERNEL_GS %ecx
- movl $(__USER_DS), %ecx
- movl %ecx, %ds
- movl %ecx, %es
- TRACE_IRQS_OFF
- movl %esp,%eax # pt_regs pointer
- call *%edi
- jmp ret_from_exception
- CFI_ENDPROC
-END(page_fault)
-
-/*
- * Debug traps and NMI can happen at the one SYSENTER instruction
- * that sets up the real kernel stack. Check here, since we can't
- * allow the wrong stack to be used.
- *
- * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
- * already pushed 3 words if it hits on the sysenter instruction:
- * eflags, cs and eip.
- *
- * We just load the right stack, and push the three (known) values
- * by hand onto the new stack - while updating the return eip past
- * the instruction that would have done it for sysenter.
- */
-.macro FIX_STACK offset ok label
- cmpw $__KERNEL_CS, 4(%esp)
- jne \ok
-\label:
- movl TSS_sysenter_sp0 + \offset(%esp), %esp
- CFI_DEF_CFA esp, 0
- CFI_UNDEFINED eip
- pushfl_cfi
- pushl_cfi $__KERNEL_CS
- pushl_cfi $sysenter_past_esp
- CFI_REL_OFFSET eip, 0
-.endm
-
-ENTRY(debug)
- RING0_INT_FRAME
- ASM_CLAC
- cmpl $ia32_sysenter_target,(%esp)
- jne debug_stack_correct
- FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
-debug_stack_correct:
- pushl_cfi $-1 # mark this as an int
- SAVE_ALL
- TRACE_IRQS_OFF
- xorl %edx,%edx # error code 0
- movl %esp,%eax # pt_regs pointer
- call do_debug
- jmp ret_from_exception
- CFI_ENDPROC
-END(debug)
-
-/*
- * NMI is doubly nasty. It can happen _while_ we're handling
- * a debug fault, and the debug fault hasn't yet been able to
- * clear up the stack. So we first check whether we got an
- * NMI on the sysenter entry path, but after that we need to
- * check whether we got an NMI on the debug path where the debug
- * fault happened on the sysenter path.
- */
-ENTRY(nmi)
- RING0_INT_FRAME
- ASM_CLAC
-#ifdef CONFIG_X86_ESPFIX32
- pushl_cfi %eax
- movl %ss, %eax
- cmpw $__ESPFIX_SS, %ax
- popl_cfi %eax
- je nmi_espfix_stack
-#endif
- cmpl $ia32_sysenter_target,(%esp)
- je nmi_stack_fixup
- pushl_cfi %eax
- movl %esp,%eax
- /* Do not access memory above the end of our stack page,
- * it might not exist.
- */
- andl $(THREAD_SIZE-1),%eax
- cmpl $(THREAD_SIZE-20),%eax
- popl_cfi %eax
- jae nmi_stack_correct
- cmpl $ia32_sysenter_target,12(%esp)
- je nmi_debug_stack_check
-nmi_stack_correct:
- /* We have a RING0_INT_FRAME here */
- pushl_cfi %eax
- SAVE_ALL
- xorl %edx,%edx # zero error code
- movl %esp,%eax # pt_regs pointer
- call do_nmi
- jmp restore_all_notrace
- CFI_ENDPROC
-
-nmi_stack_fixup:
- RING0_INT_FRAME
- FIX_STACK 12, nmi_stack_correct, 1
- jmp nmi_stack_correct
-
-nmi_debug_stack_check:
- /* We have a RING0_INT_FRAME here */
- cmpw $__KERNEL_CS,16(%esp)
- jne nmi_stack_correct
- cmpl $debug,(%esp)
- jb nmi_stack_correct
- cmpl $debug_esp_fix_insn,(%esp)
- ja nmi_stack_correct
- FIX_STACK 24, nmi_stack_correct, 1
- jmp nmi_stack_correct
-
-#ifdef CONFIG_X86_ESPFIX32
-nmi_espfix_stack:
- /* We have a RING0_INT_FRAME here.
- *
- * create the pointer to lss back
- */
- pushl_cfi %ss
- pushl_cfi %esp
- addl $4, (%esp)
- /* copy the iret frame of 12 bytes */
- .rept 3
- pushl_cfi 16(%esp)
- .endr
- pushl_cfi %eax
- SAVE_ALL
- FIXUP_ESPFIX_STACK # %eax == %esp
- xorl %edx,%edx # zero error code
- call do_nmi
- RESTORE_REGS
- lss 12+4(%esp), %esp # back to espfix stack
- CFI_ADJUST_CFA_OFFSET -24
- jmp irq_return
-#endif
- CFI_ENDPROC
-END(nmi)
-
-ENTRY(int3)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $-1 # mark this as an int
- SAVE_ALL
- TRACE_IRQS_OFF
- xorl %edx,%edx # zero error code
- movl %esp,%eax # pt_regs pointer
- call do_int3
- jmp ret_from_exception
- CFI_ENDPROC
-END(int3)
-
-ENTRY(general_protection)
- RING0_EC_FRAME
- pushl_cfi $do_general_protection
- jmp error_code
- CFI_ENDPROC
-END(general_protection)
-
-#ifdef CONFIG_KVM_GUEST
-ENTRY(async_page_fault)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_async_page_fault
- jmp error_code
- CFI_ENDPROC
-END(async_page_fault)
-#endif
-
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
deleted file mode 100644
index 02c2eff..0000000
--- a/arch/x86/kernel/entry_64.S
+++ /dev/null
@@ -1,1653 +0,0 @@
-/*
- * linux/arch/x86_64/entry.S
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs
- * Copyright (C) 2000 Pavel Machek <pavel@suse.cz>
- */
-
-/*
- * entry.S contains the system-call and fault low-level handling routines.
- *
- * Some of this is documented in Documentation/x86/entry_64.txt
- *
- * NOTE: This code handles signal-recognition, which happens every time
- * after an interrupt and after each system call.
- *
- * A note on terminology:
- * - iret frame: Architecture defined interrupt frame from SS to RIP
- * at the top of the kernel process stack.
- *
- * Some macro usage:
- * - CFI macros are used to generate dwarf2 unwind information for better
- * backtraces. They don't change any code.
- * - ENTRY/END Define functions in the symbol table.
- * - TRACE_IRQ_* - Trace hard interrupt state for lock debugging.
- * - idtentry - Define exception entry points.
- */
-
-#include <linux/linkage.h>
-#include <asm/segment.h>
-#include <asm/cache.h>
-#include <asm/errno.h>
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
-#include <asm/asm-offsets.h>
-#include <asm/msr.h>
-#include <asm/unistd.h>
-#include <asm/thread_info.h>
-#include <asm/hw_irq.h>
-#include <asm/page_types.h>
-#include <asm/irqflags.h>
-#include <asm/paravirt.h>
-#include <asm/percpu.h>
-#include <asm/asm.h>
-#include <asm/context_tracking.h>
-#include <asm/smap.h>
-#include <asm/pgtable_types.h>
-#include <linux/err.h>
-
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_64BIT 0x80000000
-#define __AUDIT_ARCH_LE 0x40000000
-
- .code64
- .section .entry.text, "ax"
-
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_usergs_sysret64)
- swapgs
- sysretq
-ENDPROC(native_usergs_sysret64)
-#endif /* CONFIG_PARAVIRT */
-
-
-.macro TRACE_IRQS_IRETQ
-#ifdef CONFIG_TRACE_IRQFLAGS
- bt $9,EFLAGS(%rsp) /* interrupts off? */
- jnc 1f
- TRACE_IRQS_ON
-1:
-#endif
-.endm
-
-/*
- * When dynamic function tracer is enabled it will add a breakpoint
- * to all locations that it is about to modify, sync CPUs, update
- * all the code, sync CPUs, then remove the breakpoints. In this time
- * if lockdep is enabled, it might jump back into the debug handler
- * outside the updating of the IST protection. (TRACE_IRQS_ON/OFF).
- *
- * We need to change the IDT table before calling TRACE_IRQS_ON/OFF to
- * make sure the stack pointer does not get reset back to the top
- * of the debug stack, and instead just reuses the current stack.
- */
-#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS)
-
-.macro TRACE_IRQS_OFF_DEBUG
- call debug_stack_set_zero
- TRACE_IRQS_OFF
- call debug_stack_reset
-.endm
-
-.macro TRACE_IRQS_ON_DEBUG
- call debug_stack_set_zero
- TRACE_IRQS_ON
- call debug_stack_reset
-.endm
-
-.macro TRACE_IRQS_IRETQ_DEBUG
- bt $9,EFLAGS(%rsp) /* interrupts off? */
- jnc 1f
- TRACE_IRQS_ON_DEBUG
-1:
-.endm
-
-#else
-# define TRACE_IRQS_OFF_DEBUG TRACE_IRQS_OFF
-# define TRACE_IRQS_ON_DEBUG TRACE_IRQS_ON
-# define TRACE_IRQS_IRETQ_DEBUG TRACE_IRQS_IRETQ
-#endif
-
-/*
- * empty frame
- */
- .macro EMPTY_FRAME start=1 offset=0
- .if \start
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,8+\offset
- .else
- CFI_DEF_CFA_OFFSET 8+\offset
- .endif
- .endm
-
-/*
- * initial frame state for interrupts (and exceptions without error code)
- */
- .macro INTR_FRAME start=1 offset=0
- EMPTY_FRAME \start, 5*8+\offset
- /*CFI_REL_OFFSET ss, 4*8+\offset*/
- CFI_REL_OFFSET rsp, 3*8+\offset
- /*CFI_REL_OFFSET rflags, 2*8+\offset*/
- /*CFI_REL_OFFSET cs, 1*8+\offset*/
- CFI_REL_OFFSET rip, 0*8+\offset
- .endm
-
-/*
- * initial frame state for exceptions with error code (and interrupts
- * with vector already pushed)
- */
- .macro XCPT_FRAME start=1 offset=0
- INTR_FRAME \start, 1*8+\offset
- .endm
-
-/*
- * frame that enables passing a complete pt_regs to a C function.
- */
- .macro DEFAULT_FRAME start=1 offset=0
- XCPT_FRAME \start, ORIG_RAX+\offset
- CFI_REL_OFFSET rdi, RDI+\offset
- CFI_REL_OFFSET rsi, RSI+\offset
- CFI_REL_OFFSET rdx, RDX+\offset
- CFI_REL_OFFSET rcx, RCX+\offset
- CFI_REL_OFFSET rax, RAX+\offset
- CFI_REL_OFFSET r8, R8+\offset
- CFI_REL_OFFSET r9, R9+\offset
- CFI_REL_OFFSET r10, R10+\offset
- CFI_REL_OFFSET r11, R11+\offset
- CFI_REL_OFFSET rbx, RBX+\offset
- CFI_REL_OFFSET rbp, RBP+\offset
- CFI_REL_OFFSET r12, R12+\offset
- CFI_REL_OFFSET r13, R13+\offset
- CFI_REL_OFFSET r14, R14+\offset
- CFI_REL_OFFSET r15, R15+\offset
- .endm
-
-/*
- * 64bit SYSCALL instruction entry. Up to 6 arguments in registers.
- *
- * 64bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
- * then loads new ss, cs, and rip from previously programmed MSRs.
- * rflags gets masked by a value from another MSR (so CLD and CLAC
- * are not needed). SYSCALL does not save anything on the stack
- * and does not change rsp.
- *
- * Registers on entry:
- * rax system call number
- * rcx return address
- * r11 saved rflags (note: r11 is callee-clobbered register in C ABI)
- * rdi arg0
- * rsi arg1
- * rdx arg2
- * r10 arg3 (needs to be moved to rcx to conform to C ABI)
- * r8 arg4
- * r9 arg5
- * (note: r12-r15,rbp,rbx are callee-preserved in C ABI)
- *
- * Only called from user space.
- *
- * When user can change pt_regs->foo always force IRET. That is because
- * it deals with uncanonical addresses better. SYSRET has trouble
- * with them due to bugs in both AMD and Intel CPUs.
- */
-
-ENTRY(system_call)
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,0
- CFI_REGISTER rip,rcx
- /*CFI_REGISTER rflags,r11*/
-
- /*
- * Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
- SWAPGS_UNSAFE_STACK
- /*
- * A hypervisor implementation might want to use a label
- * after the swapgs, so that it can do the swapgs
- * for the guest and jump here on syscall.
- */
-GLOBAL(system_call_after_swapgs)
-
- movq %rsp,PER_CPU_VAR(rsp_scratch)
- movq PER_CPU_VAR(kernel_stack),%rsp
-
- /* Construct struct pt_regs on stack */
- pushq_cfi $__USER_DS /* pt_regs->ss */
- pushq_cfi PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */
- /*
- * Re-enable interrupts.
- * We use 'rsp_scratch' as a scratch space, hence irq-off block above
- * must execute atomically in the face of possible interrupt-driven
- * task preemption. We must enable interrupts only after we're done
- * with using rsp_scratch:
- */
- ENABLE_INTERRUPTS(CLBR_NONE)
- pushq_cfi %r11 /* pt_regs->flags */
- pushq_cfi $__USER_CS /* pt_regs->cs */
- pushq_cfi %rcx /* pt_regs->ip */
- CFI_REL_OFFSET rip,0
- pushq_cfi_reg rax /* pt_regs->orig_ax */
- pushq_cfi_reg rdi /* pt_regs->di */
- pushq_cfi_reg rsi /* pt_regs->si */
- pushq_cfi_reg rdx /* pt_regs->dx */
- pushq_cfi_reg rcx /* pt_regs->cx */
- pushq_cfi $-ENOSYS /* pt_regs->ax */
- pushq_cfi_reg r8 /* pt_regs->r8 */
- pushq_cfi_reg r9 /* pt_regs->r9 */
- pushq_cfi_reg r10 /* pt_regs->r10 */
- pushq_cfi_reg r11 /* pt_regs->r11 */
- sub $(6*8),%rsp /* pt_regs->bp,bx,r12-15 not saved */
- CFI_ADJUST_CFA_OFFSET 6*8
-
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz tracesys
-system_call_fastpath:
-#if __SYSCALL_MASK == ~0
- cmpq $__NR_syscall_max,%rax
-#else
- andl $__SYSCALL_MASK,%eax
- cmpl $__NR_syscall_max,%eax
-#endif
- ja 1f /* return -ENOSYS (already in pt_regs->ax) */
- movq %r10,%rcx
- call *sys_call_table(,%rax,8)
- movq %rax,RAX(%rsp)
-1:
-/*
- * Syscall return path ending with SYSRET (fast path).
- * Has incompletely filled pt_regs.
- */
- LOCKDEP_SYS_EXIT
- /*
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
- DISABLE_INTERRUPTS(CLBR_NONE)
-
- /*
- * We must check ti flags with interrupts (or at least preemption)
- * off because we must *never* return to userspace without
- * processing exit work that is enqueued if we're preempted here.
- * In particular, returning to userspace with any of the one-shot
- * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
- * very bad.
- */
- testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */
-
- CFI_REMEMBER_STATE
-
- RESTORE_C_REGS_EXCEPT_RCX_R11
- movq RIP(%rsp),%rcx
- CFI_REGISTER rip,rcx
- movq EFLAGS(%rsp),%r11
- /*CFI_REGISTER rflags,r11*/
- movq RSP(%rsp),%rsp
- /*
- * 64bit SYSRET restores rip from rcx,
- * rflags from r11 (but RF and VM bits are forced to 0),
- * cs and ss are loaded from MSRs.
- * Restoration of rflags re-enables interrupts.
- *
- * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
- * descriptor is not reinitialized. This means that we should
- * avoid SYSRET with SS == NULL, which could happen if we schedule,
- * exit the kernel, and re-enter using an interrupt vector. (All
- * interrupt entries on x86_64 set SS to NULL.) We prevent that
- * from happening by reloading SS in __switch_to. (Actually
- * detecting the failure in 64-bit userspace is tricky but can be
- * done.)
- */
- USERGS_SYSRET64
-
- CFI_RESTORE_STATE
-
- /* Do syscall entry tracing */
-tracesys:
- movq %rsp, %rdi
- movl $AUDIT_ARCH_X86_64, %esi
- call syscall_trace_enter_phase1
- test %rax, %rax
- jnz tracesys_phase2 /* if needed, run the slow path */
- RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */
- movq ORIG_RAX(%rsp), %rax
- jmp system_call_fastpath /* and return to the fast path */
-
-tracesys_phase2:
- SAVE_EXTRA_REGS
- movq %rsp, %rdi
- movl $AUDIT_ARCH_X86_64, %esi
- movq %rax,%rdx
- call syscall_trace_enter_phase2
-
- /*
- * Reload registers from stack in case ptrace changed them.
- * We don't reload %rax because syscall_trace_entry_phase2() returned
- * the value it wants us to use in the table lookup.
- */
- RESTORE_C_REGS_EXCEPT_RAX
- RESTORE_EXTRA_REGS
-#if __SYSCALL_MASK == ~0
- cmpq $__NR_syscall_max,%rax
-#else
- andl $__SYSCALL_MASK,%eax
- cmpl $__NR_syscall_max,%eax
-#endif
- ja 1f /* return -ENOSYS (already in pt_regs->ax) */
- movq %r10,%rcx /* fixup for C */
- call *sys_call_table(,%rax,8)
- movq %rax,RAX(%rsp)
-1:
- /* Use IRET because user could have changed pt_regs->foo */
-
-/*
- * Syscall return path ending with IRET.
- * Has correct iret frame.
- */
-GLOBAL(int_ret_from_sys_call)
- DISABLE_INTERRUPTS(CLBR_NONE)
-int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */
- TRACE_IRQS_OFF
- movl $_TIF_ALLWORK_MASK,%edi
- /* edi: mask to check */
-GLOBAL(int_with_check)
- LOCKDEP_SYS_EXIT_IRQ
- GET_THREAD_INFO(%rcx)
- movl TI_flags(%rcx),%edx
- andl %edi,%edx
- jnz int_careful
- andl $~TS_COMPAT,TI_status(%rcx)
- jmp syscall_return
-
- /* Either reschedule or signal or syscall exit tracking needed. */
- /* First do a reschedule test. */
- /* edx: work, edi: workmask */
-int_careful:
- bt $TIF_NEED_RESCHED,%edx
- jnc int_very_careful
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- pushq_cfi %rdi
- SCHEDULE_USER
- popq_cfi %rdi
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- jmp int_with_check
-
- /* handle signals and tracing -- both require a full pt_regs */
-int_very_careful:
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- SAVE_EXTRA_REGS
- /* Check for syscall exit trace */
- testl $_TIF_WORK_SYSCALL_EXIT,%edx
- jz int_signal
- pushq_cfi %rdi
- leaq 8(%rsp),%rdi # &ptregs -> arg1
- call syscall_trace_leave
- popq_cfi %rdi
- andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
- jmp int_restore_rest
-
-int_signal:
- testl $_TIF_DO_NOTIFY_MASK,%edx
- jz 1f
- movq %rsp,%rdi # &ptregs -> arg1
- xorl %esi,%esi # oldset -> arg2
- call do_notify_resume
-1: movl $_TIF_WORK_MASK,%edi
-int_restore_rest:
- RESTORE_EXTRA_REGS
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- jmp int_with_check
-
-syscall_return:
- /* The IRETQ could re-enable interrupts: */
- DISABLE_INTERRUPTS(CLBR_ANY)
- TRACE_IRQS_IRETQ
-
- /*
- * Try to use SYSRET instead of IRET if we're returning to
- * a completely clean 64-bit userspace context.
- */
- movq RCX(%rsp),%rcx
- cmpq %rcx,RIP(%rsp) /* RCX == RIP */
- jne opportunistic_sysret_failed
-
- /*
- * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
- * in kernel space. This essentially lets the user take over
- * the kernel, since userspace controls RSP. It's not worth
- * testing for canonicalness exactly -- this check detects any
- * of the 17 high bits set, which is true for non-canonical
- * or kernel addresses. (This will pessimize vsyscall=native.
- * Big deal.)
- *
- * If virtual addresses ever become wider, this will need
- * to be updated to remain correct on both old and new CPUs.
- */
- .ifne __VIRTUAL_MASK_SHIFT - 47
- .error "virtual address width changed -- SYSRET checks need update"
- .endif
- shr $__VIRTUAL_MASK_SHIFT, %rcx
- jnz opportunistic_sysret_failed
-
- cmpq $__USER_CS,CS(%rsp) /* CS must match SYSRET */
- jne opportunistic_sysret_failed
-
- movq R11(%rsp),%r11
- cmpq %r11,EFLAGS(%rsp) /* R11 == RFLAGS */
- jne opportunistic_sysret_failed
-
- /*
- * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET,
- * restoring TF results in a trap from userspace immediately after
- * SYSRET. This would cause an infinite loop whenever #DB happens
- * with register state that satisfies the opportunistic SYSRET
- * conditions. For example, single-stepping this user code:
- *
- * movq $stuck_here,%rcx
- * pushfq
- * popq %r11
- * stuck_here:
- *
- * would never get past 'stuck_here'.
- */
- testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
- jnz opportunistic_sysret_failed
-
- /* nothing to check for RSP */
-
- cmpq $__USER_DS,SS(%rsp) /* SS must match SYSRET */
- jne opportunistic_sysret_failed
-
- /*
- * We win! This label is here just for ease of understanding
- * perf profiles. Nothing jumps here.
- */
-syscall_return_via_sysret:
- CFI_REMEMBER_STATE
- /* r11 is already restored (see code above) */
- RESTORE_C_REGS_EXCEPT_R11
- movq RSP(%rsp),%rsp
- USERGS_SYSRET64
- CFI_RESTORE_STATE
-
-opportunistic_sysret_failed:
- SWAPGS
- jmp restore_c_regs_and_iret
- CFI_ENDPROC
-END(system_call)
-
-
- .macro FORK_LIKE func
-ENTRY(stub_\func)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8 /* offset 8: return address */
- SAVE_EXTRA_REGS 8
- jmp sys_\func
- CFI_ENDPROC
-END(stub_\func)
- .endm
-
- FORK_LIKE clone
- FORK_LIKE fork
- FORK_LIKE vfork
-
-ENTRY(stub_execve)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- call sys_execve
-return_from_execve:
- testl %eax, %eax
- jz 1f
- /* exec failed, can use fast SYSRET code path in this case */
- ret
-1:
- /* must use IRET code path (pt_regs->cs may have changed) */
- addq $8, %rsp
- CFI_ADJUST_CFA_OFFSET -8
- ZERO_EXTRA_REGS
- movq %rax,RAX(%rsp)
- jmp int_ret_from_sys_call
- CFI_ENDPROC
-END(stub_execve)
-/*
- * Remaining execve stubs are only 7 bytes long.
- * ENTRY() often aligns to 16 bytes, which in this case has no benefits.
- */
- .align 8
-GLOBAL(stub_execveat)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- call sys_execveat
- jmp return_from_execve
- CFI_ENDPROC
-END(stub_execveat)
-
-#ifdef CONFIG_X86_X32_ABI
- .align 8
-GLOBAL(stub_x32_execve)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- call compat_sys_execve
- jmp return_from_execve
- CFI_ENDPROC
-END(stub_x32_execve)
- .align 8
-GLOBAL(stub_x32_execveat)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- call compat_sys_execveat
- jmp return_from_execve
- CFI_ENDPROC
-END(stub_x32_execveat)
-#endif
-
-#ifdef CONFIG_IA32_EMULATION
- .align 8
-GLOBAL(stub32_execve)
- CFI_STARTPROC
- call compat_sys_execve
- jmp return_from_execve
- CFI_ENDPROC
-END(stub32_execve)
- .align 8
-GLOBAL(stub32_execveat)
- CFI_STARTPROC
- call compat_sys_execveat
- jmp return_from_execve
- CFI_ENDPROC
-END(stub32_execveat)
-#endif
-
-/*
- * sigreturn is special because it needs to restore all registers on return.
- * This cannot be done with SYSRET, so use the IRET return path instead.
- */
-ENTRY(stub_rt_sigreturn)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- /*
- * SAVE_EXTRA_REGS result is not normally needed:
- * sigreturn overwrites all pt_regs->GPREGS.
- * But sigreturn can fail (!), and there is no easy way to detect that.
- * To make sure RESTORE_EXTRA_REGS doesn't restore garbage on error,
- * we SAVE_EXTRA_REGS here.
- */
- SAVE_EXTRA_REGS 8
- call sys_rt_sigreturn
-return_from_stub:
- addq $8, %rsp
- CFI_ADJUST_CFA_OFFSET -8
- RESTORE_EXTRA_REGS
- movq %rax,RAX(%rsp)
- jmp int_ret_from_sys_call
- CFI_ENDPROC
-END(stub_rt_sigreturn)
-
-#ifdef CONFIG_X86_X32_ABI
-ENTRY(stub_x32_rt_sigreturn)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- SAVE_EXTRA_REGS 8
- call sys32_x32_rt_sigreturn
- jmp return_from_stub
- CFI_ENDPROC
-END(stub_x32_rt_sigreturn)
-#endif
-
-/*
- * A newly forked process directly context switches into this address.
- *
- * rdi: prev task we switched from
- */
-ENTRY(ret_from_fork)
- DEFAULT_FRAME
-
- LOCK ; btr $TIF_FORK,TI_flags(%r8)
-
- pushq_cfi $0x0002
- popfq_cfi # reset kernel eflags
-
- call schedule_tail # rdi: 'prev' task parameter
-
- RESTORE_EXTRA_REGS
-
- testl $3,CS(%rsp) # from kernel_thread?
-
- /*
- * By the time we get here, we have no idea whether our pt_regs,
- * ti flags, and ti status came from the 64-bit SYSCALL fast path,
- * the slow path, or one of the ia32entry paths.
- * Use IRET code path to return, since it can safely handle
- * all of the above.
- */
- jnz int_ret_from_sys_call
-
- /* We came from kernel_thread */
- /* nb: we depend on RESTORE_EXTRA_REGS above */
- movq %rbp, %rdi
- call *%rbx
- movl $0, RAX(%rsp)
- RESTORE_EXTRA_REGS
- jmp int_ret_from_sys_call
- CFI_ENDPROC
-END(ret_from_fork)
-
-/*
- * Build the entry stubs with some assembler magic.
- * We pack 1 stub into every 8-byte block.
- */
- .align 8
-ENTRY(irq_entries_start)
- INTR_FRAME
- vector=FIRST_EXTERNAL_VECTOR
- .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
- pushq_cfi $(~vector+0x80) /* Note: always in signed byte range */
- vector=vector+1
- jmp common_interrupt
- CFI_ADJUST_CFA_OFFSET -8
- .align 8
- .endr
- CFI_ENDPROC
-END(irq_entries_start)
-
-/*
- * Interrupt entry/exit.
- *
- * Interrupt entry points save only callee clobbered registers in fast path.
- *
- * Entry runs with interrupts off.
- */
-
-/* 0(%rsp): ~(interrupt number) */
- .macro interrupt func
- cld
- /*
- * Since nothing in interrupt handling code touches r12...r15 members
- * of "struct pt_regs", and since interrupts can nest, we can save
- * four stack slots and simultaneously provide
- * an unwind-friendly stack layout by saving "truncated" pt_regs
- * exactly up to rbp slot, without these members.
- */
- ALLOC_PT_GPREGS_ON_STACK -RBP
- SAVE_C_REGS -RBP
- /* this goes to 0(%rsp) for unwinder, not for saving the value: */
- SAVE_EXTRA_REGS_RBP -RBP
-
- leaq -RBP(%rsp),%rdi /* arg1 for \func (pointer to pt_regs) */
-
- testl $3, CS-RBP(%rsp)
- je 1f
- SWAPGS
-1:
- /*
- * Save previous stack pointer, optionally switch to interrupt stack.
- * irq_count is used to check if a CPU is already on an interrupt stack
- * or not. While this is essentially redundant with preempt_count it is
- * a little cheaper to use a separate counter in the PDA (short of
- * moving irq_enter into assembly, which would be too much work)
- */
- movq %rsp, %rsi
- incl PER_CPU_VAR(irq_count)
- cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
- CFI_DEF_CFA_REGISTER rsi
- pushq %rsi
- /*
- * For debugger:
- * "CFA (Current Frame Address) is the value on stack + offset"
- */
- CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \
- 0x77 /* DW_OP_breg7 (rsp) */, 0, \
- 0x06 /* DW_OP_deref */, \
- 0x08 /* DW_OP_const1u */, SIZEOF_PTREGS-RBP, \
- 0x22 /* DW_OP_plus */
- /* We entered an interrupt context - irqs are off: */
- TRACE_IRQS_OFF
-
- call \func
- .endm
-
- /*
- * The interrupt stubs push (~vector+0x80) onto the stack and
- * then jump to common_interrupt.
- */
- .p2align CONFIG_X86_L1_CACHE_SHIFT
-common_interrupt:
- XCPT_FRAME
- ASM_CLAC
- addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */
- interrupt do_IRQ
- /* 0(%rsp): old RSP */
-ret_from_intr:
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- decl PER_CPU_VAR(irq_count)
-
- /* Restore saved previous stack */
- popq %rsi
- CFI_DEF_CFA rsi,SIZEOF_PTREGS-RBP /* reg/off reset after def_cfa_expr */
- /* return code expects complete pt_regs - adjust rsp accordingly: */
- leaq -RBP(%rsi),%rsp
- CFI_DEF_CFA_REGISTER rsp
- CFI_ADJUST_CFA_OFFSET RBP
-
- testl $3,CS(%rsp)
- je retint_kernel
- /* Interrupt came from user space */
-
- GET_THREAD_INFO(%rcx)
- /*
- * %rcx: thread info. Interrupts off.
- */
-retint_with_reschedule:
- movl $_TIF_WORK_MASK,%edi
-retint_check:
- LOCKDEP_SYS_EXIT_IRQ
- movl TI_flags(%rcx),%edx
- andl %edi,%edx
- CFI_REMEMBER_STATE
- jnz retint_careful
-
-retint_swapgs: /* return to user-space */
- /*
- * The iretq could re-enable interrupts:
- */
- DISABLE_INTERRUPTS(CLBR_ANY)
- TRACE_IRQS_IRETQ
-
- SWAPGS
- jmp restore_c_regs_and_iret
-
-/* Returning to kernel space */
-retint_kernel:
-#ifdef CONFIG_PREEMPT
- /* Interrupts are off */
- /* Check if we need preemption */
- bt $9,EFLAGS(%rsp) /* interrupts were off? */
- jnc 1f
-0: cmpl $0,PER_CPU_VAR(__preempt_count)
- jnz 1f
- call preempt_schedule_irq
- jmp 0b
-1:
-#endif
- /*
- * The iretq could re-enable interrupts:
- */
- TRACE_IRQS_IRETQ
-
-/*
- * At this label, code paths which return to kernel and to user,
- * which come from interrupts/exception and from syscalls, merge.
- */
-restore_c_regs_and_iret:
- RESTORE_C_REGS
- REMOVE_PT_GPREGS_FROM_STACK 8
-
-irq_return:
- INTERRUPT_RETURN
-
-ENTRY(native_iret)
- /*
- * Are we returning to a stack segment from the LDT? Note: in
- * 64-bit mode SS:RSP on the exception stack is always valid.
- */
-#ifdef CONFIG_X86_ESPFIX64
- testb $4,(SS-RIP)(%rsp)
- jnz native_irq_return_ldt
-#endif
-
-.global native_irq_return_iret
-native_irq_return_iret:
- /*
- * This may fault. Non-paranoid faults on return to userspace are
- * handled by fixup_bad_iret. These include #SS, #GP, and #NP.
- * Double-faults due to espfix64 are handled in do_double_fault.
- * Other faults here are fatal.
- */
- iretq
-
-#ifdef CONFIG_X86_ESPFIX64
-native_irq_return_ldt:
- pushq_cfi %rax
- pushq_cfi %rdi
- SWAPGS
- movq PER_CPU_VAR(espfix_waddr),%rdi
- movq %rax,(0*8)(%rdi) /* RAX */
- movq (2*8)(%rsp),%rax /* RIP */
- movq %rax,(1*8)(%rdi)
- movq (3*8)(%rsp),%rax /* CS */
- movq %rax,(2*8)(%rdi)
- movq (4*8)(%rsp),%rax /* RFLAGS */
- movq %rax,(3*8)(%rdi)
- movq (6*8)(%rsp),%rax /* SS */
- movq %rax,(5*8)(%rdi)
- movq (5*8)(%rsp),%rax /* RSP */
- movq %rax,(4*8)(%rdi)
- andl $0xffff0000,%eax
- popq_cfi %rdi
- orq PER_CPU_VAR(espfix_stack),%rax
- SWAPGS
- movq %rax,%rsp
- popq_cfi %rax
- jmp native_irq_return_iret
-#endif
-
- /* edi: workmask, edx: work */
-retint_careful:
- CFI_RESTORE_STATE
- bt $TIF_NEED_RESCHED,%edx
- jnc retint_signal
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- pushq_cfi %rdi
- SCHEDULE_USER
- popq_cfi %rdi
- GET_THREAD_INFO(%rcx)
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- jmp retint_check
-
-retint_signal:
- testl $_TIF_DO_NOTIFY_MASK,%edx
- jz retint_swapgs
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- SAVE_EXTRA_REGS
- movq $-1,ORIG_RAX(%rsp)
- xorl %esi,%esi # oldset
- movq %rsp,%rdi # &pt_regs
- call do_notify_resume
- RESTORE_EXTRA_REGS
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- GET_THREAD_INFO(%rcx)
- jmp retint_with_reschedule
-
- CFI_ENDPROC
-END(common_interrupt)
-
-/*
- * APIC interrupts.
- */
-.macro apicinterrupt3 num sym do_sym
-ENTRY(\sym)
- INTR_FRAME
- ASM_CLAC
- pushq_cfi $~(\num)
-.Lcommon_\sym:
- interrupt \do_sym
- jmp ret_from_intr
- CFI_ENDPROC
-END(\sym)
-.endm
-
-#ifdef CONFIG_TRACING
-#define trace(sym) trace_##sym
-#define smp_trace(sym) smp_trace_##sym
-
-.macro trace_apicinterrupt num sym
-apicinterrupt3 \num trace(\sym) smp_trace(\sym)
-.endm
-#else
-.macro trace_apicinterrupt num sym do_sym
-.endm
-#endif
-
-.macro apicinterrupt num sym do_sym
-apicinterrupt3 \num \sym \do_sym
-trace_apicinterrupt \num \sym
-.endm
-
-#ifdef CONFIG_SMP
-apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR \
- irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
-apicinterrupt3 REBOOT_VECTOR \
- reboot_interrupt smp_reboot_interrupt
-#endif
-
-#ifdef CONFIG_X86_UV
-apicinterrupt3 UV_BAU_MESSAGE \
- uv_bau_message_intr1 uv_bau_message_interrupt
-#endif
-apicinterrupt LOCAL_TIMER_VECTOR \
- apic_timer_interrupt smp_apic_timer_interrupt
-apicinterrupt X86_PLATFORM_IPI_VECTOR \
- x86_platform_ipi smp_x86_platform_ipi
-
-#ifdef CONFIG_HAVE_KVM
-apicinterrupt3 POSTED_INTR_VECTOR \
- kvm_posted_intr_ipi smp_kvm_posted_intr_ipi
-#endif
-
-#ifdef CONFIG_X86_MCE_THRESHOLD
-apicinterrupt THRESHOLD_APIC_VECTOR \
- threshold_interrupt smp_threshold_interrupt
-#endif
-
-#ifdef CONFIG_X86_THERMAL_VECTOR
-apicinterrupt THERMAL_APIC_VECTOR \
- thermal_interrupt smp_thermal_interrupt
-#endif
-
-#ifdef CONFIG_SMP
-apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \
- call_function_single_interrupt smp_call_function_single_interrupt
-apicinterrupt CALL_FUNCTION_VECTOR \
- call_function_interrupt smp_call_function_interrupt
-apicinterrupt RESCHEDULE_VECTOR \
- reschedule_interrupt smp_reschedule_interrupt
-#endif
-
-apicinterrupt ERROR_APIC_VECTOR \
- error_interrupt smp_error_interrupt
-apicinterrupt SPURIOUS_APIC_VECTOR \
- spurious_interrupt smp_spurious_interrupt
-
-#ifdef CONFIG_IRQ_WORK
-apicinterrupt IRQ_WORK_VECTOR \
- irq_work_interrupt smp_irq_work_interrupt
-#endif
-
-/*
- * Exception entry points.
- */
-#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8)
-
-.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
-ENTRY(\sym)
- /* Sanity check */
- .if \shift_ist != -1 && \paranoid == 0
- .error "using shift_ist requires paranoid=1"
- .endif
-
- .if \has_error_code
- XCPT_FRAME
- .else
- INTR_FRAME
- .endif
-
- ASM_CLAC
- PARAVIRT_ADJUST_EXCEPTION_FRAME
-
- .ifeq \has_error_code
- pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
- .endif
-
- ALLOC_PT_GPREGS_ON_STACK
-
- .if \paranoid
- .if \paranoid == 1
- CFI_REMEMBER_STATE
- testl $3, CS(%rsp) /* If coming from userspace, switch */
- jnz 1f /* stacks. */
- .endif
- call paranoid_entry
- .else
- call error_entry
- .endif
- /* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
-
- DEFAULT_FRAME 0
-
- .if \paranoid
- .if \shift_ist != -1
- TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */
- .else
- TRACE_IRQS_OFF
- .endif
- .endif
-
- movq %rsp,%rdi /* pt_regs pointer */
-
- .if \has_error_code
- movq ORIG_RAX(%rsp),%rsi /* get error code */
- movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */
- .else
- xorl %esi,%esi /* no error code */
- .endif
-
- .if \shift_ist != -1
- subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
- .endif
-
- call \do_sym
-
- .if \shift_ist != -1
- addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
- .endif
-
- /* these procedures expect "no swapgs" flag in ebx */
- .if \paranoid
- jmp paranoid_exit
- .else
- jmp error_exit
- .endif
-
- .if \paranoid == 1
- CFI_RESTORE_STATE
- /*
- * Paranoid entry from userspace. Switch stacks and treat it
- * as a normal entry. This means that paranoid handlers
- * run in real process context if user_mode(regs).
- */
-1:
- call error_entry
-
- DEFAULT_FRAME 0
-
- movq %rsp,%rdi /* pt_regs pointer */
- call sync_regs
- movq %rax,%rsp /* switch stack */
-
- movq %rsp,%rdi /* pt_regs pointer */
-
- .if \has_error_code
- movq ORIG_RAX(%rsp),%rsi /* get error code */
- movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */
- .else
- xorl %esi,%esi /* no error code */
- .endif
-
- call \do_sym
-
- jmp error_exit /* %ebx: no swapgs flag */
- .endif
-
- CFI_ENDPROC
-END(\sym)
-.endm
-
-#ifdef CONFIG_TRACING
-.macro trace_idtentry sym do_sym has_error_code:req
-idtentry trace(\sym) trace(\do_sym) has_error_code=\has_error_code
-idtentry \sym \do_sym has_error_code=\has_error_code
-.endm
-#else
-.macro trace_idtentry sym do_sym has_error_code:req
-idtentry \sym \do_sym has_error_code=\has_error_code
-.endm
-#endif
-
-idtentry divide_error do_divide_error has_error_code=0
-idtentry overflow do_overflow has_error_code=0
-idtentry bounds do_bounds has_error_code=0
-idtentry invalid_op do_invalid_op has_error_code=0
-idtentry device_not_available do_device_not_available has_error_code=0
-idtentry double_fault do_double_fault has_error_code=1 paranoid=2
-idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
-idtentry invalid_TSS do_invalid_TSS has_error_code=1
-idtentry segment_not_present do_segment_not_present has_error_code=1
-idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0
-idtentry coprocessor_error do_coprocessor_error has_error_code=0
-idtentry alignment_check do_alignment_check has_error_code=1
-idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0
-
-
- /* Reload gs selector with exception handling */
- /* edi: new selector */
-ENTRY(native_load_gs_index)
- CFI_STARTPROC
- pushfq_cfi
- DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
- SWAPGS
-gs_change:
- movl %edi,%gs
-2: mfence /* workaround */
- SWAPGS
- popfq_cfi
- ret
- CFI_ENDPROC
-END(native_load_gs_index)
-
- _ASM_EXTABLE(gs_change,bad_gs)
- .section .fixup,"ax"
- /* running with kernelgs */
-bad_gs:
- SWAPGS /* switch back to user gs */
- xorl %eax,%eax
- movl %eax,%gs
- jmp 2b
- .previous
-
-/* Call softirq on interrupt stack. Interrupts are off. */
-ENTRY(do_softirq_own_stack)
- CFI_STARTPROC
- pushq_cfi %rbp
- CFI_REL_OFFSET rbp,0
- mov %rsp,%rbp
- CFI_DEF_CFA_REGISTER rbp
- incl PER_CPU_VAR(irq_count)
- cmove PER_CPU_VAR(irq_stack_ptr),%rsp
- push %rbp # backlink for old unwinder
- call __do_softirq
- leaveq
- CFI_RESTORE rbp
- CFI_DEF_CFA_REGISTER rsp
- CFI_ADJUST_CFA_OFFSET -8
- decl PER_CPU_VAR(irq_count)
- ret
- CFI_ENDPROC
-END(do_softirq_own_stack)
-
-#ifdef CONFIG_XEN
-idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0
-
-/*
- * A note on the "critical region" in our callback handler.
- * We want to avoid stacking callback handlers due to events occurring
- * during handling of the last event. To do this, we keep events disabled
- * until we've done all processing. HOWEVER, we must enable events before
- * popping the stack frame (can't be done atomically) and so it would still
- * be possible to get enough handler activations to overflow the stack.
- * Although unlikely, bugs of that kind are hard to track down, so we'd
- * like to avoid the possibility.
- * So, on entry to the handler we detect whether we interrupted an
- * existing activation in its critical region -- if so, we pop the current
- * activation and restart the handler using the previous one.
- */
-ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs)
- CFI_STARTPROC
-/*
- * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
- * see the correct pointer to the pt_regs
- */
- movq %rdi, %rsp # we don't return, adjust the stack frame
- CFI_ENDPROC
- DEFAULT_FRAME
-11: incl PER_CPU_VAR(irq_count)
- movq %rsp,%rbp
- CFI_DEF_CFA_REGISTER rbp
- cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
- pushq %rbp # backlink for old unwinder
- call xen_evtchn_do_upcall
- popq %rsp
- CFI_DEF_CFA_REGISTER rsp
- decl PER_CPU_VAR(irq_count)
-#ifndef CONFIG_PREEMPT
- call xen_maybe_preempt_hcall
-#endif
- jmp error_exit
- CFI_ENDPROC
-END(xen_do_hypervisor_callback)
-
-/*
- * Hypervisor uses this for application faults while it executes.
- * We get here for two reasons:
- * 1. Fault while reloading DS, ES, FS or GS
- * 2. Fault while executing IRET
- * Category 1 we do not need to fix up as Xen has already reloaded all segment
- * registers that could be reloaded and zeroed the others.
- * Category 2 we fix up by killing the current process. We cannot use the
- * normal Linux return path in this case because if we use the IRET hypercall
- * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
- * We distinguish between categories by comparing each saved segment register
- * with its current contents: any discrepancy means we in category 1.
- */
-ENTRY(xen_failsafe_callback)
- INTR_FRAME 1 (6*8)
- /*CFI_REL_OFFSET gs,GS*/
- /*CFI_REL_OFFSET fs,FS*/
- /*CFI_REL_OFFSET es,ES*/
- /*CFI_REL_OFFSET ds,DS*/
- CFI_REL_OFFSET r11,8
- CFI_REL_OFFSET rcx,0
- movw %ds,%cx
- cmpw %cx,0x10(%rsp)
- CFI_REMEMBER_STATE
- jne 1f
- movw %es,%cx
- cmpw %cx,0x18(%rsp)
- jne 1f
- movw %fs,%cx
- cmpw %cx,0x20(%rsp)
- jne 1f
- movw %gs,%cx
- cmpw %cx,0x28(%rsp)
- jne 1f
- /* All segments match their saved values => Category 2 (Bad IRET). */
- movq (%rsp),%rcx
- CFI_RESTORE rcx
- movq 8(%rsp),%r11
- CFI_RESTORE r11
- addq $0x30,%rsp
- CFI_ADJUST_CFA_OFFSET -0x30
- pushq_cfi $0 /* RIP */
- pushq_cfi %r11
- pushq_cfi %rcx
- jmp general_protection
- CFI_RESTORE_STATE
-1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
- movq (%rsp),%rcx
- CFI_RESTORE rcx
- movq 8(%rsp),%r11
- CFI_RESTORE r11
- addq $0x30,%rsp
- CFI_ADJUST_CFA_OFFSET -0x30
- pushq_cfi $-1 /* orig_ax = -1 => not a system call */
- ALLOC_PT_GPREGS_ON_STACK
- SAVE_C_REGS
- SAVE_EXTRA_REGS
- jmp error_exit
- CFI_ENDPROC
-END(xen_failsafe_callback)
-
-apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
- xen_hvm_callback_vector xen_evtchn_do_upcall
-
-#endif /* CONFIG_XEN */
-
-#if IS_ENABLED(CONFIG_HYPERV)
-apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
- hyperv_callback_vector hyperv_vector_handler
-#endif /* CONFIG_HYPERV */
-
-idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry stack_segment do_stack_segment has_error_code=1
-#ifdef CONFIG_XEN
-idtentry xen_debug do_debug has_error_code=0
-idtentry xen_int3 do_int3 has_error_code=0
-idtentry xen_stack_segment do_stack_segment has_error_code=1
-#endif
-idtentry general_protection do_general_protection has_error_code=1
-trace_idtentry page_fault do_page_fault has_error_code=1
-#ifdef CONFIG_KVM_GUEST
-idtentry async_page_fault do_async_page_fault has_error_code=1
-#endif
-#ifdef CONFIG_X86_MCE
-idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip)
-#endif
-
-/*
- * Save all registers in pt_regs, and switch gs if needed.
- * Use slow, but surefire "are we in kernel?" check.
- * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
- */
-ENTRY(paranoid_entry)
- XCPT_FRAME 1 15*8
- cld
- SAVE_C_REGS 8
- SAVE_EXTRA_REGS 8
- movl $1,%ebx
- movl $MSR_GS_BASE,%ecx
- rdmsr
- testl %edx,%edx
- js 1f /* negative -> in kernel */
- SWAPGS
- xorl %ebx,%ebx
-1: ret
- CFI_ENDPROC
-END(paranoid_entry)
-
-/*
- * "Paranoid" exit path from exception stack. This is invoked
- * only on return from non-NMI IST interrupts that came
- * from kernel space.
- *
- * We may be returning to very strange contexts (e.g. very early
- * in syscall entry), so checking for preemption here would
- * be complicated. Fortunately, we there's no good reason
- * to try to handle preemption here.
- */
-/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */
-ENTRY(paranoid_exit)
- DEFAULT_FRAME
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF_DEBUG
- testl %ebx,%ebx /* swapgs needed? */
- jnz paranoid_exit_no_swapgs
- TRACE_IRQS_IRETQ
- SWAPGS_UNSAFE_STACK
- jmp paranoid_exit_restore
-paranoid_exit_no_swapgs:
- TRACE_IRQS_IRETQ_DEBUG
-paranoid_exit_restore:
- RESTORE_EXTRA_REGS
- RESTORE_C_REGS
- REMOVE_PT_GPREGS_FROM_STACK 8
- INTERRUPT_RETURN
- CFI_ENDPROC
-END(paranoid_exit)
-
-/*
- * Save all registers in pt_regs, and switch gs if needed.
- * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
- */
-ENTRY(error_entry)
- XCPT_FRAME 1 15*8
- cld
- SAVE_C_REGS 8
- SAVE_EXTRA_REGS 8
- xorl %ebx,%ebx
- testl $3,CS+8(%rsp)
- je error_kernelspace
-error_swapgs:
- SWAPGS
-error_sti:
- TRACE_IRQS_OFF
- ret
-
- /*
- * There are two places in the kernel that can potentially fault with
- * usergs. Handle them here. B stepping K8s sometimes report a
- * truncated RIP for IRET exceptions returning to compat mode. Check
- * for these here too.
- */
-error_kernelspace:
- CFI_REL_OFFSET rcx, RCX+8
- incl %ebx
- leaq native_irq_return_iret(%rip),%rcx
- cmpq %rcx,RIP+8(%rsp)
- je error_bad_iret
- movl %ecx,%eax /* zero extend */
- cmpq %rax,RIP+8(%rsp)
- je bstep_iret
- cmpq $gs_change,RIP+8(%rsp)
- je error_swapgs
- jmp error_sti
-
-bstep_iret:
- /* Fix truncated RIP */
- movq %rcx,RIP+8(%rsp)
- /* fall through */
-
-error_bad_iret:
- SWAPGS
- mov %rsp,%rdi
- call fixup_bad_iret
- mov %rax,%rsp
- decl %ebx /* Return to usergs */
- jmp error_sti
- CFI_ENDPROC
-END(error_entry)
-
-
-/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */
-ENTRY(error_exit)
- DEFAULT_FRAME
- movl %ebx,%eax
- RESTORE_EXTRA_REGS
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- GET_THREAD_INFO(%rcx)
- testl %eax,%eax
- jne retint_kernel
- LOCKDEP_SYS_EXIT_IRQ
- movl TI_flags(%rcx),%edx
- movl $_TIF_WORK_MASK,%edi
- andl %edi,%edx
- jnz retint_careful
- jmp retint_swapgs
- CFI_ENDPROC
-END(error_exit)
-
-/* Runs on exception stack */
-ENTRY(nmi)
- INTR_FRAME
- PARAVIRT_ADJUST_EXCEPTION_FRAME
- /*
- * We allow breakpoints in NMIs. If a breakpoint occurs, then
- * the iretq it performs will take us out of NMI context.
- * This means that we can have nested NMIs where the next
- * NMI is using the top of the stack of the previous NMI. We
- * can't let it execute because the nested NMI will corrupt the
- * stack of the previous NMI. NMI handlers are not re-entrant
- * anyway.
- *
- * To handle this case we do the following:
- * Check the a special location on the stack that contains
- * a variable that is set when NMIs are executing.
- * The interrupted task's stack is also checked to see if it
- * is an NMI stack.
- * If the variable is not set and the stack is not the NMI
- * stack then:
- * o Set the special variable on the stack
- * o Copy the interrupt frame into a "saved" location on the stack
- * o Copy the interrupt frame into a "copy" location on the stack
- * o Continue processing the NMI
- * If the variable is set or the previous stack is the NMI stack:
- * o Modify the "copy" location to jump to the repeate_nmi
- * o return back to the first NMI
- *
- * Now on exit of the first NMI, we first clear the stack variable
- * The NMI stack will tell any nested NMIs at that point that it is
- * nested. Then we pop the stack normally with iret, and if there was
- * a nested NMI that updated the copy interrupt stack frame, a
- * jump will be made to the repeat_nmi code that will handle the second
- * NMI.
- */
-
- /* Use %rdx as our temp variable throughout */
- pushq_cfi %rdx
- CFI_REL_OFFSET rdx, 0
-
- /*
- * If %cs was not the kernel segment, then the NMI triggered in user
- * space, which means it is definitely not nested.
- */
- cmpl $__KERNEL_CS, 16(%rsp)
- jne first_nmi
-
- /*
- * Check the special variable on the stack to see if NMIs are
- * executing.
- */
- cmpl $1, -8(%rsp)
- je nested_nmi
-
- /*
- * Now test if the previous stack was an NMI stack.
- * We need the double check. We check the NMI stack to satisfy the
- * race when the first NMI clears the variable before returning.
- * We check the variable because the first NMI could be in a
- * breakpoint routine using a breakpoint stack.
- */
- lea 6*8(%rsp), %rdx
- /* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */
- cmpq %rdx, 4*8(%rsp)
- /* If the stack pointer is above the NMI stack, this is a normal NMI */
- ja first_nmi
- subq $EXCEPTION_STKSZ, %rdx
- cmpq %rdx, 4*8(%rsp)
- /* If it is below the NMI stack, it is a normal NMI */
- jb first_nmi
- /* Ah, it is within the NMI stack, treat it as nested */
-
- CFI_REMEMBER_STATE
-
-nested_nmi:
- /*
- * Do nothing if we interrupted the fixup in repeat_nmi.
- * It's about to repeat the NMI handler, so we are fine
- * with ignoring this one.
- */
- movq $repeat_nmi, %rdx
- cmpq 8(%rsp), %rdx
- ja 1f
- movq $end_repeat_nmi, %rdx
- cmpq 8(%rsp), %rdx
- ja nested_nmi_out
-
-1:
- /* Set up the interrupted NMIs stack to jump to repeat_nmi */
- leaq -1*8(%rsp), %rdx
- movq %rdx, %rsp
- CFI_ADJUST_CFA_OFFSET 1*8
- leaq -10*8(%rsp), %rdx
- pushq_cfi $__KERNEL_DS
- pushq_cfi %rdx
- pushfq_cfi
- pushq_cfi $__KERNEL_CS
- pushq_cfi $repeat_nmi
-
- /* Put stack back */
- addq $(6*8), %rsp
- CFI_ADJUST_CFA_OFFSET -6*8
-
-nested_nmi_out:
- popq_cfi %rdx
- CFI_RESTORE rdx
-
- /* No need to check faults here */
- INTERRUPT_RETURN
-
- CFI_RESTORE_STATE
-first_nmi:
- /*
- * Because nested NMIs will use the pushed location that we
- * stored in rdx, we must keep that space available.
- * Here's what our stack frame will look like:
- * +-------------------------+
- * | original SS |
- * | original Return RSP |
- * | original RFLAGS |
- * | original CS |
- * | original RIP |
- * +-------------------------+
- * | temp storage for rdx |
- * +-------------------------+
- * | NMI executing variable |
- * +-------------------------+
- * | copied SS |
- * | copied Return RSP |
- * | copied RFLAGS |
- * | copied CS |
- * | copied RIP |
- * +-------------------------+
- * | Saved SS |
- * | Saved Return RSP |
- * | Saved RFLAGS |
- * | Saved CS |
- * | Saved RIP |
- * +-------------------------+
- * | pt_regs |
- * +-------------------------+
- *
- * The saved stack frame is used to fix up the copied stack frame
- * that a nested NMI may change to make the interrupted NMI iret jump
- * to the repeat_nmi. The original stack frame and the temp storage
- * is also used by nested NMIs and can not be trusted on exit.
- */
- /* Do not pop rdx, nested NMIs will corrupt that part of the stack */
- movq (%rsp), %rdx
- CFI_RESTORE rdx
-
- /* Set the NMI executing variable on the stack. */
- pushq_cfi $1
-
- /*
- * Leave room for the "copied" frame
- */
- subq $(5*8), %rsp
- CFI_ADJUST_CFA_OFFSET 5*8
-
- /* Copy the stack frame to the Saved frame */
- .rept 5
- pushq_cfi 11*8(%rsp)
- .endr
- CFI_DEF_CFA_OFFSET 5*8
-
- /* Everything up to here is safe from nested NMIs */
-
- /*
- * If there was a nested NMI, the first NMI's iret will return
- * here. But NMIs are still enabled and we can take another
- * nested NMI. The nested NMI checks the interrupted RIP to see
- * if it is between repeat_nmi and end_repeat_nmi, and if so
- * it will just return, as we are about to repeat an NMI anyway.
- * This makes it safe to copy to the stack frame that a nested
- * NMI will update.
- */
-repeat_nmi:
- /*
- * Update the stack variable to say we are still in NMI (the update
- * is benign for the non-repeat case, where 1 was pushed just above
- * to this very stack slot).
- */
- movq $1, 10*8(%rsp)
-
- /* Make another copy, this one may be modified by nested NMIs */
- addq $(10*8), %rsp
- CFI_ADJUST_CFA_OFFSET -10*8
- .rept 5
- pushq_cfi -6*8(%rsp)
- .endr
- subq $(5*8), %rsp
- CFI_DEF_CFA_OFFSET 5*8
-end_repeat_nmi:
-
- /*
- * Everything below this point can be preempted by a nested
- * NMI if the first NMI took an exception and reset our iret stack
- * so that we repeat another NMI.
- */
- pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
- ALLOC_PT_GPREGS_ON_STACK
-
- /*
- * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
- * as we should not be calling schedule in NMI context.
- * Even with normal interrupts enabled. An NMI should not be
- * setting NEED_RESCHED or anything that normal interrupts and
- * exceptions might do.
- */
- call paranoid_entry
- DEFAULT_FRAME 0
-
- /*
- * Save off the CR2 register. If we take a page fault in the NMI then
- * it could corrupt the CR2 value. If the NMI preempts a page fault
- * handler before it was able to read the CR2 register, and then the
- * NMI itself takes a page fault, the page fault that was preempted
- * will read the information from the NMI page fault and not the
- * origin fault. Save it off and restore it if it changes.
- * Use the r12 callee-saved register.
- */
- movq %cr2, %r12
-
- /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
- movq %rsp,%rdi
- movq $-1,%rsi
- call do_nmi
-
- /* Did the NMI take a page fault? Restore cr2 if it did */
- movq %cr2, %rcx
- cmpq %rcx, %r12
- je 1f
- movq %r12, %cr2
-1:
-
- testl %ebx,%ebx /* swapgs needed? */
- jnz nmi_restore
-nmi_swapgs:
- SWAPGS_UNSAFE_STACK
-nmi_restore:
- RESTORE_EXTRA_REGS
- RESTORE_C_REGS
- /* Pop the extra iret frame at once */
- REMOVE_PT_GPREGS_FROM_STACK 6*8
-
- /* Clear the NMI executing stack variable */
- movq $0, 5*8(%rsp)
- jmp irq_return
- CFI_ENDPROC
-END(nmi)
-
-ENTRY(ignore_sysret)
- CFI_STARTPROC
- mov $-ENOSYS,%eax
- sysret
- CFI_ENDPROC
-END(ignore_sysret)
-
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 2b55ee6..5a46681 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -167,7 +167,7 @@
clear_bss();
for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
- set_intr_gate(i, early_idt_handlers[i]);
+ set_intr_gate(i, early_idt_handler_array[i]);
load_idt((const struct desc_ptr *)&idt_descr);
copy_bootdata(__va(real_mode_data));
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index d031bad..544dec4 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -478,21 +478,22 @@
__INIT
setup_once:
/*
- * Set up a idt with 256 entries pointing to ignore_int,
- * interrupt gates. It doesn't actually load idt - that needs
- * to be done on each CPU. Interrupts are enabled elsewhere,
- * when we can be relatively sure everything is ok.
+ * Set up a idt with 256 interrupt gates that push zero if there
+ * is no error code and then jump to early_idt_handler_common.
+ * It doesn't actually load the idt - that needs to be done on
+ * each CPU. Interrupts are enabled elsewhere, when we can be
+ * relatively sure everything is ok.
*/
movl $idt_table,%edi
- movl $early_idt_handlers,%eax
+ movl $early_idt_handler_array,%eax
movl $NUM_EXCEPTION_VECTORS,%ecx
1:
movl %eax,(%edi)
movl %eax,4(%edi)
/* interrupt gate, dpl=0, present */
movl $(0x8E000000 + __KERNEL_CS),2(%edi)
- addl $9,%eax
+ addl $EARLY_IDT_HANDLER_SIZE,%eax
addl $8,%edi
loop 1b
@@ -524,30 +525,32 @@
andl $0,setup_once_ref /* Once is enough, thanks */
ret
-ENTRY(early_idt_handlers)
+ENTRY(early_idt_handler_array)
# 36(%esp) %eflags
# 32(%esp) %cs
# 28(%esp) %eip
# 24(%rsp) error code
i = 0
.rept NUM_EXCEPTION_VECTORS
- .if (EXCEPTION_ERRCODE_MASK >> i) & 1
- ASM_NOP2
- .else
+ .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1
pushl $0 # Dummy error code, to make stack frame uniform
.endif
pushl $i # 20(%esp) Vector number
- jmp early_idt_handler
+ jmp early_idt_handler_common
i = i + 1
+ .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
.endr
-ENDPROC(early_idt_handlers)
+ENDPROC(early_idt_handler_array)
- /* This is global to keep gas from relaxing the jumps */
-ENTRY(early_idt_handler)
+early_idt_handler_common:
+ /*
+ * The stack is the hardware frame, an error code or zero, and the
+ * vector number.
+ */
cld
cmpl $2,(%esp) # X86_TRAP_NMI
- je is_nmi # Ignore NMI
+ je .Lis_nmi # Ignore NMI
cmpl $2,%ss:early_recursion_flag
je hlt_loop
@@ -600,10 +603,10 @@
pop %ecx
pop %eax
decl %ss:early_recursion_flag
-is_nmi:
+.Lis_nmi:
addl $8,%esp /* drop vector number and error code */
iret
-ENDPROC(early_idt_handler)
+ENDPROC(early_idt_handler_common)
/* This is the default interrupt "handler" :-) */
ALIGN
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index ae6588b..e5c27f7 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -321,30 +321,32 @@
jmp bad_address
__INIT
- .globl early_idt_handlers
-early_idt_handlers:
+ENTRY(early_idt_handler_array)
# 104(%rsp) %rflags
# 96(%rsp) %cs
# 88(%rsp) %rip
# 80(%rsp) error code
i = 0
.rept NUM_EXCEPTION_VECTORS
- .if (EXCEPTION_ERRCODE_MASK >> i) & 1
- ASM_NOP2
- .else
+ .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1
pushq $0 # Dummy error code, to make stack frame uniform
.endif
pushq $i # 72(%rsp) Vector number
- jmp early_idt_handler
+ jmp early_idt_handler_common
i = i + 1
+ .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
.endr
+ENDPROC(early_idt_handler_array)
-/* This is global to keep gas from relaxing the jumps */
-ENTRY(early_idt_handler)
+early_idt_handler_common:
+ /*
+ * The stack is the hardware frame, an error code or zero, and the
+ * vector number.
+ */
cld
cmpl $2,(%rsp) # X86_TRAP_NMI
- je is_nmi # Ignore NMI
+ je .Lis_nmi # Ignore NMI
cmpl $2,early_recursion_flag(%rip)
jz 1f
@@ -409,10 +411,10 @@
popq %rcx
popq %rax
decl early_recursion_flag(%rip)
-is_nmi:
+.Lis_nmi:
addq $16,%rsp # drop vector number and error code
INTERRUPT_RETURN
-ENDPROC(early_idt_handler)
+ENDPROC(early_idt_handler_common)
__INITDATA
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 3acbff4..10757d0 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -12,6 +12,7 @@
#include <linux/pm.h>
#include <linux/io.h>
+#include <asm/irqdomain.h>
#include <asm/fixmap.h>
#include <asm/hpet.h>
#include <asm/time.h>
@@ -305,8 +306,6 @@
printk(KERN_DEBUG "hpet clockevent registered\n");
}
-static int hpet_setup_msi_irq(unsigned int irq);
-
static void hpet_set_mode(enum clock_event_mode mode,
struct clock_event_device *evt, int timer)
{
@@ -357,7 +356,7 @@
hpet_enable_legacy_int();
} else {
struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
- hpet_setup_msi_irq(hdev->irq);
+ irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
disable_irq(hdev->irq);
irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
enable_irq(hdev->irq);
@@ -423,6 +422,7 @@
static DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev);
static struct hpet_dev *hpet_devs;
+static struct irq_domain *hpet_domain;
void hpet_msi_unmask(struct irq_data *data)
{
@@ -473,31 +473,6 @@
return hpet_next_event(delta, evt, hdev->num);
}
-static int hpet_setup_msi_irq(unsigned int irq)
-{
- if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) {
- irq_free_hwirq(irq);
- return -EINVAL;
- }
- return 0;
-}
-
-static int hpet_assign_irq(struct hpet_dev *dev)
-{
- unsigned int irq = irq_alloc_hwirq(-1);
-
- if (!irq)
- return -EINVAL;
-
- irq_set_handler_data(irq, dev);
-
- if (hpet_setup_msi_irq(irq))
- return -EINVAL;
-
- dev->irq = irq;
- return 0;
-}
-
static irqreturn_t hpet_interrupt_handler(int irq, void *data)
{
struct hpet_dev *dev = (struct hpet_dev *)data;
@@ -540,9 +515,6 @@
if (!(hdev->flags & HPET_DEV_VALID))
return;
- if (hpet_setup_msi_irq(hdev->irq))
- return;
-
hdev->cpu = cpu;
per_cpu(cpu_hpet_dev, cpu) = hdev;
evt->name = hdev->name;
@@ -574,7 +546,7 @@
unsigned int id;
unsigned int num_timers;
unsigned int num_timers_used = 0;
- int i;
+ int i, irq;
if (hpet_msi_disable)
return;
@@ -587,6 +559,10 @@
num_timers++; /* Value read out starts from 0 */
hpet_print_config();
+ hpet_domain = hpet_create_irq_domain(hpet_blockid);
+ if (!hpet_domain)
+ return;
+
hpet_devs = kzalloc(sizeof(struct hpet_dev) * num_timers, GFP_KERNEL);
if (!hpet_devs)
return;
@@ -604,12 +580,14 @@
hdev->flags = 0;
if (cfg & HPET_TN_PERIODIC_CAP)
hdev->flags |= HPET_DEV_PERI_CAP;
+ sprintf(hdev->name, "hpet%d", i);
hdev->num = i;
- sprintf(hdev->name, "hpet%d", i);
- if (hpet_assign_irq(hdev))
+ irq = hpet_assign_irq(hpet_domain, hdev, hdev->num);
+ if (irq <= 0)
continue;
+ hdev->irq = irq;
hdev->flags |= HPET_DEV_FSB_CAP;
hdev->flags |= HPET_DEV_VALID;
num_timers_used++;
@@ -709,10 +687,6 @@
}
#else
-static int hpet_setup_msi_irq(unsigned int irq)
-{
- return 0;
-}
static void hpet_msi_capability_lookup(unsigned int start_timer)
{
return;
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 00918327..6185d31 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -173,6 +173,21 @@
xstate_size = sizeof(struct i387_fxsave_struct);
else
xstate_size = sizeof(struct i387_fsave_struct);
+
+ /*
+ * Quirk: we don't yet handle the XSAVES* instructions
+ * correctly, as we don't correctly convert between
+ * standard and compacted format when interfacing
+ * with user-space - so disable it for now.
+ *
+ * The difference is small: with recent CPUs the
+ * compacted format is only marginally smaller than
+ * the standard FPU state format.
+ *
+ * ( This is easy to backport while we are fixing
+ * XSAVES* support. )
+ */
+ setup_clear_cpu_cap(X86_FEATURE_XSAVES);
}
/*
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index e7cc537..16cb827 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -329,8 +329,8 @@
*/
outb_pic(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */
- /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */
- outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR);
+ /* ICW2: 8259A-1 IR0-7 mapped to ISA_IRQ_VECTOR(0) */
+ outb_pic(ISA_IRQ_VECTOR(0), PIC_MASTER_IMR);
/* 8259A-1 (the master) has a slave on IR2 */
outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR);
@@ -342,8 +342,8 @@
outb_pic(0x11, PIC_SLAVE_CMD); /* ICW1: select 8259A-2 init */
- /* ICW2: 8259A-2 IR0-7 mapped to IRQ8_VECTOR */
- outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR);
+ /* ICW2: 8259A-2 IR0-7 mapped to ISA_IRQ_VECTOR(8) */
+ outb_pic(ISA_IRQ_VECTOR(8), PIC_SLAVE_IMR);
/* 8259A-2 is a slave on master's IR2 */
outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);
/* (slave's support for AEOI in flat mode is to be investigated) */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index e5952c2..88b36648 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -22,6 +22,12 @@
#define CREATE_TRACE_POINTS
#include <asm/trace/irq_vectors.h>
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
+
+DEFINE_PER_CPU(struct pt_regs *, irq_regs);
+EXPORT_PER_CPU_SYMBOL(irq_regs);
+
atomic_t irq_err_count;
/* Function pointer for generic interrupt vector handling */
@@ -116,6 +122,12 @@
seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count);
seq_puts(p, " Threshold APIC interrupts\n");
#endif
+#ifdef CONFIG_X86_MCE_AMD
+ seq_printf(p, "%*s: ", prec, "DFR");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", irq_stats(j)->irq_deferred_error_count);
+ seq_puts(p, " Deferred Error APIC interrupts\n");
+#endif
#ifdef CONFIG_X86_MCE
seq_printf(p, "%*s: ", prec, "MCE");
for_each_online_cpu(j)
@@ -136,6 +148,18 @@
#if defined(CONFIG_X86_IO_APIC)
seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
#endif
+#ifdef CONFIG_HAVE_KVM
+ seq_printf(p, "%*s: ", prec, "PIN");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis);
+ seq_puts(p, " Posted-interrupt notification event\n");
+
+ seq_printf(p, "%*s: ", prec, "PIW");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ",
+ irq_stats(j)->kvm_posted_intr_wakeup_ipis);
+ seq_puts(p, " Posted-interrupt wakeup event\n");
+#endif
return 0;
}
@@ -192,8 +216,7 @@
unsigned vector = ~regs->orig_ax;
unsigned irq;
- irq_enter();
- exit_idle();
+ entering_irq();
irq = __this_cpu_read(vector_irq[vector]);
@@ -209,7 +232,7 @@
}
}
- irq_exit();
+ exiting_irq();
set_irq_regs(old_regs);
return 1;
@@ -237,6 +260,18 @@
}
#ifdef CONFIG_HAVE_KVM
+static void dummy_handler(void) {}
+static void (*kvm_posted_intr_wakeup_handler)(void) = dummy_handler;
+
+void kvm_set_posted_intr_wakeup_handler(void (*handler)(void))
+{
+ if (handler)
+ kvm_posted_intr_wakeup_handler = handler;
+ else
+ kvm_posted_intr_wakeup_handler = dummy_handler;
+}
+EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler);
+
/*
* Handler for POSTED_INTERRUPT_VECTOR.
*/
@@ -244,16 +279,23 @@
{
struct pt_regs *old_regs = set_irq_regs(regs);
- ack_APIC_irq();
-
- irq_enter();
-
- exit_idle();
-
+ entering_ack_irq();
inc_irq_stat(kvm_posted_intr_ipis);
+ exiting_irq();
+ set_irq_regs(old_regs);
+}
- irq_exit();
+/*
+ * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
+ */
+__visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+ entering_ack_irq();
+ inc_irq_stat(kvm_posted_intr_wakeup_ipis);
+ kvm_posted_intr_wakeup_handler();
+ exiting_irq();
set_irq_regs(old_regs);
}
#endif
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index f9fd86a..cd74f59 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -21,12 +21,6 @@
#include <asm/apic.h>
-DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
-EXPORT_PER_CPU_SYMBOL(irq_stat);
-
-DEFINE_PER_CPU(struct pt_regs *, irq_regs);
-EXPORT_PER_CPU_SYMBOL(irq_regs);
-
#ifdef CONFIG_DEBUG_STACKOVERFLOW
int sysctl_panic_on_stackoverflow __read_mostly;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 394e643..bc4604e 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -20,12 +20,6 @@
#include <asm/idle.h>
#include <asm/apic.h>
-DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
-EXPORT_PER_CPU_SYMBOL(irq_stat);
-
-DEFINE_PER_CPU(struct pt_regs *, irq_regs);
-EXPORT_PER_CPU_SYMBOL(irq_regs);
-
int sysctl_panic_on_stackoverflow;
/*
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index 15d741d..dc5fa6a 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -10,12 +10,6 @@
#include <asm/apic.h>
#include <asm/trace/irq_vectors.h>
-static inline void irq_work_entering_irq(void)
-{
- irq_enter();
- ack_APIC_irq();
-}
-
static inline void __smp_irq_work_interrupt(void)
{
inc_irq_stat(apic_irq_work_irqs);
@@ -24,14 +18,14 @@
__visible void smp_irq_work_interrupt(struct pt_regs *regs)
{
- irq_work_entering_irq();
+ ipi_entering_ack_irq();
__smp_irq_work_interrupt();
exiting_irq();
}
__visible void smp_trace_irq_work_interrupt(struct pt_regs *regs)
{
- irq_work_entering_irq();
+ ipi_entering_ack_irq();
trace_irq_work_entry(IRQ_WORK_VECTOR);
__smp_irq_work_interrupt();
trace_irq_work_exit(IRQ_WORK_VECTOR);
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index cd10a64..a3a5e15 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -86,7 +86,7 @@
int i;
/*
- * On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15.
+ * On cpu 0, Assign ISA_IRQ_VECTOR(irq) to IRQ 0..15.
* If these IRQ's are handled by legacy interrupt-controllers like PIC,
* then this configuration will likely be static after the boot. If
* these IRQ's are handled by more mordern controllers like IO-APIC,
@@ -94,7 +94,7 @@
* irq's migrate etc.
*/
for (i = 0; i < nr_legacy_irqs(); i++)
- per_cpu(vector_irq, 0)[IRQ0_VECTOR + i] = i;
+ per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = i;
x86_init.irqs.intr_init();
}
@@ -135,6 +135,10 @@
alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
#endif
+#ifdef CONFIG_X86_MCE_AMD
+ alloc_intr_gate(DEFERRED_ERROR_VECTOR, deferred_error_interrupt);
+#endif
+
#ifdef CONFIG_X86_LOCAL_APIC
/* self generated IPI for local APIC timer */
alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
@@ -144,6 +148,8 @@
#ifdef CONFIG_HAVE_KVM
/* IPI for KVM to deliver posted interrupt */
alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi);
+ /* IPI for KVM to deliver interrupt to wake up tasks */
+ alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi);
#endif
/* IPI vectors for APIC spurious and error interrupts */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 9435620..1681504 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -584,6 +584,39 @@
kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
}
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+#include <asm/qspinlock.h>
+
+static void kvm_wait(u8 *ptr, u8 val)
+{
+ unsigned long flags;
+
+ if (in_nmi())
+ return;
+
+ local_irq_save(flags);
+
+ if (READ_ONCE(*ptr) != val)
+ goto out;
+
+ /*
+ * halt until it's our turn and kicked. Note that we do safe halt
+ * for irq enabled case to avoid hang when lock info is overwritten
+ * in irq spinlock slowpath and no spurious interrupt occur to save us.
+ */
+ if (arch_irqs_disabled_flags(flags))
+ halt();
+ else
+ safe_halt();
+
+out:
+ local_irq_restore(flags);
+}
+
+#else /* !CONFIG_QUEUED_SPINLOCKS */
+
enum kvm_contention_stat {
TAKEN_SLOW,
TAKEN_SLOW_PICKUP,
@@ -817,6 +850,8 @@
}
}
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
+
/*
* Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
*/
@@ -828,8 +863,16 @@
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return;
+#ifdef CONFIG_QUEUED_SPINLOCKS
+ __pv_init_lock_hash();
+ pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+ pv_lock_ops.wait = kvm_wait;
+ pv_lock_ops.kick = kvm_kick_cpu;
+#else /* !CONFIG_QUEUED_SPINLOCKS */
pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
pv_lock_ops.unlock_kick = kvm_unlock_kick;
+#endif
}
static __init int kvm_spinlock_init_jump(void)
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 2d2a237..30ca760 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -19,8 +19,8 @@
#include <linux/module.h>
#include <linux/smp.h>
#include <linux/pci.h>
-#include <linux/irqdomain.h>
+#include <asm/irqdomain.h>
#include <asm/mtrr.h>
#include <asm/mpspec.h>
#include <asm/pgalloc.h>
@@ -113,11 +113,6 @@
pr_warn("Unknown bustype %s - ignoring\n", str);
}
-static struct irq_domain_ops mp_ioapic_irqdomain_ops = {
- .map = mp_irqdomain_map,
- .unmap = mp_irqdomain_unmap,
-};
-
static void __init MP_ioapic_info(struct mpc_ioapic *m)
{
struct ioapic_domain_cfg cfg = {
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index bbb6c73..33ee3e0 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -8,11 +8,33 @@
#include <asm/paravirt.h>
+#ifdef CONFIG_QUEUED_SPINLOCKS
+__visible void __native_queued_spin_unlock(struct qspinlock *lock)
+{
+ native_queued_spin_unlock(lock);
+}
+
+PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock);
+
+bool pv_is_native_spin_unlock(void)
+{
+ return pv_lock_ops.queued_spin_unlock.func ==
+ __raw_callee_save___native_queued_spin_unlock;
+}
+#endif
+
struct pv_lock_ops pv_lock_ops = {
#ifdef CONFIG_SMP
+#ifdef CONFIG_QUEUED_SPINLOCKS
+ .queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
+ .queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
+ .wait = paravirt_nop,
+ .kick = paravirt_nop,
+#else /* !CONFIG_QUEUED_SPINLOCKS */
.lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop),
.unlock_kick = paravirt_nop,
-#endif
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
+#endif /* SMP */
};
EXPORT_SYMBOL(pv_lock_ops);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c614dd4..58bcfb6 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -154,7 +154,9 @@
ret = paravirt_patch_ident_64(insnbuf, len);
else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
+#ifdef CONFIG_X86_32
type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) ||
+#endif
type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) ||
type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64))
/* If operation requires a jmp, then jmp */
@@ -371,7 +373,7 @@
.load_sp0 = native_load_sp0,
-#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+#if defined(CONFIG_X86_32)
.irq_enable_sysexit = native_irq_enable_sysexit,
#endif
#ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index d9f32e6..e1b0136 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -12,6 +12,10 @@
DEF_NATIVE(pv_cpu_ops, clts, "clts");
DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc");
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)");
+#endif
+
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
{
/* arg in %eax, return in %eax */
@@ -24,6 +28,8 @@
return 0;
}
+extern bool pv_is_native_spin_unlock(void);
+
unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
unsigned long addr, unsigned len)
{
@@ -47,14 +53,22 @@
PATCH_SITE(pv_mmu_ops, write_cr3);
PATCH_SITE(pv_cpu_ops, clts);
PATCH_SITE(pv_cpu_ops, read_tsc);
-
- patch_site:
- ret = paravirt_patch_insns(ibuf, len, start, end);
- break;
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+ case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
+ if (pv_is_native_spin_unlock()) {
+ start = start_pv_lock_ops_queued_spin_unlock;
+ end = end_pv_lock_ops_queued_spin_unlock;
+ goto patch_site;
+ }
+#endif
default:
ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
break;
+
+patch_site:
+ ret = paravirt_patch_insns(ibuf, len, start, end);
+ break;
}
#undef PATCH_SITE
return ret;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index a1da673..8aa0558 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -21,6 +21,10 @@
DEF_NATIVE(, mov32, "mov %edi, %eax");
DEF_NATIVE(, mov64, "mov %rdi, %rax");
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
+#endif
+
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
{
return paravirt_patch_insns(insnbuf, len,
@@ -33,6 +37,8 @@
start__mov64, end__mov64);
}
+extern bool pv_is_native_spin_unlock(void);
+
unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
unsigned long addr, unsigned len)
{
@@ -49,7 +55,6 @@
PATCH_SITE(pv_irq_ops, save_fl);
PATCH_SITE(pv_irq_ops, irq_enable);
PATCH_SITE(pv_irq_ops, irq_disable);
- PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
PATCH_SITE(pv_cpu_ops, usergs_sysret32);
PATCH_SITE(pv_cpu_ops, usergs_sysret64);
PATCH_SITE(pv_cpu_ops, swapgs);
@@ -59,14 +64,22 @@
PATCH_SITE(pv_cpu_ops, clts);
PATCH_SITE(pv_mmu_ops, flush_tlb_single);
PATCH_SITE(pv_cpu_ops, wbinvd);
-
- patch_site:
- ret = paravirt_patch_insns(ibuf, len, start, end);
- break;
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+ case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
+ if (pv_is_native_spin_unlock()) {
+ start = start_pv_lock_ops_queued_spin_unlock;
+ end = end_pv_lock_ops_queued_spin_unlock;
+ goto patch_site;
+ }
+#endif
default:
ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
break;
+
+patch_site:
+ ret = paravirt_patch_insns(ibuf, len, start, end);
+ break;
}
#undef PATCH_SITE
return ret;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 8ed2106..a99900c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -302,13 +302,10 @@
arch_end_context_switch(next_p);
/*
- * Reload esp0, kernel_stack, and current_top_of_stack. This changes
+ * Reload esp0 and cpu_current_top_of_stack. This changes
* current_thread_info().
*/
load_sp0(tss, next);
- this_cpu_write(kernel_stack,
- (unsigned long)task_stack_page(next_p) +
- THREAD_SIZE);
this_cpu_write(cpu_current_top_of_stack,
(unsigned long)task_stack_page(next_p) +
THREAD_SIZE);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ddfdbf7..8213450 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -409,9 +409,6 @@
/* Reload esp0 and ss1. This changes current_thread_info(). */
load_sp0(tss, next);
- this_cpu_write(kernel_stack,
- (unsigned long)task_stack_page(next_p) + THREAD_SIZE);
-
/*
* Now maybe reload the debug registers and handle I/O bitmaps
*/
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d74ac33..8d04a75 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1222,8 +1222,7 @@
init_cpu_to_node();
init_apic_mappings();
- if (x86_io_apic_ops.init)
- x86_io_apic_ops.init();
+ io_apic_init_mappings();
kvm_guest_init();
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index be8e1bd..15aaa69 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -170,8 +170,7 @@
asmlinkage __visible void smp_reboot_interrupt(void)
{
- ack_APIC_irq();
- irq_enter();
+ ipi_entering_ack_irq();
stop_this_cpu(NULL);
irq_exit();
}
@@ -265,12 +264,6 @@
*/
}
-static inline void smp_entering_irq(void)
-{
- ack_APIC_irq();
- irq_enter();
-}
-
__visible void smp_trace_reschedule_interrupt(struct pt_regs *regs)
{
/*
@@ -279,7 +272,7 @@
* scheduler_ipi(). This is OK, since those functions are allowed
* to nest.
*/
- smp_entering_irq();
+ ipi_entering_ack_irq();
trace_reschedule_entry(RESCHEDULE_VECTOR);
__smp_reschedule_interrupt();
trace_reschedule_exit(RESCHEDULE_VECTOR);
@@ -297,14 +290,14 @@
__visible void smp_call_function_interrupt(struct pt_regs *regs)
{
- smp_entering_irq();
+ ipi_entering_ack_irq();
__smp_call_function_interrupt();
exiting_irq();
}
__visible void smp_trace_call_function_interrupt(struct pt_regs *regs)
{
- smp_entering_irq();
+ ipi_entering_ack_irq();
trace_call_function_entry(CALL_FUNCTION_VECTOR);
__smp_call_function_interrupt();
trace_call_function_exit(CALL_FUNCTION_VECTOR);
@@ -319,14 +312,14 @@
__visible void smp_call_function_single_interrupt(struct pt_regs *regs)
{
- smp_entering_irq();
+ ipi_entering_ack_irq();
__smp_call_function_single_interrupt();
exiting_irq();
}
__visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs)
{
- smp_entering_irq();
+ ipi_entering_ack_irq();
trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);
__smp_call_function_single_interrupt();
trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 50e547e..fd6291c 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -514,6 +514,40 @@
}
/*
+ * The Multiprocessor Specification 1.4 (1997) example code suggests
+ * that there should be a 10ms delay between the BSP asserting INIT
+ * and de-asserting INIT, when starting a remote processor.
+ * But that slows boot and resume on modern processors, which include
+ * many cores and don't require that delay.
+ *
+ * Cmdline "init_cpu_udelay=" is available to over-ride this delay.
+ * Modern processor families are quirked to remove the delay entirely.
+ */
+#define UDELAY_10MS_DEFAULT 10000
+
+static unsigned int init_udelay = UDELAY_10MS_DEFAULT;
+
+static int __init cpu_init_udelay(char *str)
+{
+ get_option(&str, &init_udelay);
+
+ return 0;
+}
+early_param("cpu_init_udelay", cpu_init_udelay);
+
+static void __init smp_quirk_init_udelay(void)
+{
+ /* if cmdline changed it from default, leave it alone */
+ if (init_udelay != UDELAY_10MS_DEFAULT)
+ return;
+
+ /* if modern processor, use no delay */
+ if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
+ ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF)))
+ init_udelay = 0;
+}
+
+/*
* Poke the other CPU in the eye via NMI to wake it up. Remember that the normal
* INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
* won't ... remember to clear down the APIC, etc later.
@@ -555,7 +589,7 @@
static int
wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
{
- unsigned long send_status, accept_status = 0;
+ unsigned long send_status = 0, accept_status = 0;
int maxlvt, num_starts, j;
maxlvt = lapic_get_maxlvt();
@@ -583,7 +617,7 @@
pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
- mdelay(10);
+ udelay(init_udelay);
pr_debug("Deasserting INIT\n");
@@ -651,6 +685,7 @@
* Give the other CPU some time to accept the IPI.
*/
udelay(200);
+
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
accept_status = (apic_read(APIC_ESR) & 0xEF);
@@ -792,8 +827,6 @@
clear_tsk_thread_flag(idle, TIF_FORK);
initial_gs = per_cpu_offset(cpu);
#endif
- per_cpu(kernel_stack, cpu) =
- (unsigned long)task_stack_page(idle) + THREAD_SIZE;
}
/*
@@ -1176,6 +1209,8 @@
uv_system_init();
set_mtrr_aps_delayed_init();
+
+ smp_quirk_init_udelay();
}
void arch_enable_nonboot_cpus_begin(void)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 324ab52..de37936 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -72,8 +72,7 @@
#else
#include <asm/processor-flags.h>
#include <asm/setup.h>
-
-asmlinkage int system_call(void);
+#include <asm/proto.h>
#endif
/* Must be page-aligned because the real IDT is used in a fixmap. */
@@ -813,18 +812,6 @@
do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
{
conditional_sti(regs);
-#if 0
- /* No need to warn about this any longer. */
- pr_info("Ignoring P6 Local APIC Spurious Interrupt Bug...\n");
-#endif
-}
-
-asmlinkage __visible void __attribute__((weak)) smp_thermal_interrupt(void)
-{
-}
-
-asmlinkage __visible void __attribute__((weak)) smp_threshold_interrupt(void)
-{
}
/*
@@ -992,13 +979,13 @@
set_bit(i, used_vectors);
#ifdef CONFIG_IA32_EMULATION
- set_system_intr_gate(IA32_SYSCALL_VECTOR, ia32_syscall);
+ set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_compat);
set_bit(IA32_SYSCALL_VECTOR, used_vectors);
#endif
#ifdef CONFIG_X86_32
- set_system_trap_gate(SYSCALL_VECTOR, &system_call);
- set_bit(SYSCALL_VECTOR, used_vectors);
+ set_system_trap_gate(IA32_SYSCALL_VECTOR, entry_INT80_32);
+ set_bit(IA32_SYSCALL_VECTOR, used_vectors);
#endif
/*
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 234b072..3cee10a 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -111,11 +111,9 @@
#if defined(CONFIG_PCI_MSI)
struct x86_msi_ops x86_msi = {
.setup_msi_irqs = native_setup_msi_irqs,
- .compose_msi_msg = native_compose_msi_msg,
.teardown_msi_irq = native_teardown_msi_irq,
.teardown_msi_irqs = default_teardown_msi_irqs,
.restore_msi_irqs = default_restore_msi_irqs,
- .setup_hpet_msi = default_setup_hpet_msi,
};
/* MSI arch specific hooks */
@@ -141,13 +139,6 @@
#endif
struct x86_io_apic_ops x86_io_apic_ops = {
- .init = native_io_apic_init_mappings,
.read = native_io_apic_read,
- .write = native_io_apic_write,
- .modify = native_io_apic_modify,
.disable = native_disable_io_apic,
- .print_entries = native_io_apic_print_entries,
- .set_affinity = native_ioapic_set_affinity,
- .setup_entry = native_setup_ioapic_entry,
- .eoi_ioapic_pin = native_eoi_ioapic_pin,
};
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 8f9a133..cab9aaa 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -90,7 +90,7 @@
.noirq_iret = (u32)lguest_noirq_iret,
.kernel_address = PAGE_OFFSET,
.blocked_interrupts = { 1 }, /* Block timer interrupts */
- .syscall_vec = SYSCALL_VECTOR,
+ .syscall_vec = IA32_SYSCALL_VECTOR,
};
/*G:037
@@ -866,7 +866,7 @@
for (i = FIRST_EXTERNAL_VECTOR; i < FIRST_SYSTEM_VECTOR; i++) {
/* Some systems map "vectors" to interrupts weirdly. Not us! */
__this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR);
- if (i != SYSCALL_VECTOR)
+ if (i != IA32_SYSCALL_VECTOR)
set_intr_gate(i, irq_entries_start +
8 * (i - FIRST_EXTERNAL_VECTOR));
}
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 1530afb..f258788 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -17,7 +17,6 @@
obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
lib-y := delay.o misc.o cmdline.o
-lib-y += thunk_$(BITS).o
lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
lib-y += memcpy_$(BITS).o
lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
@@ -40,6 +39,6 @@
lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
lib-y += clear_page_64.o copy_page_64.o
lib-y += memmove_64.o memset_64.o
- lib-y += copy_user_64.o copy_user_nocache_64.o
+ lib-y += copy_user_64.o
lib-y += cmpxchg16b_emu.o
endif
diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S
index 00933d5..9b0ca8f 100644
--- a/arch/x86/lib/atomic64_386_32.S
+++ b/arch/x86/lib/atomic64_386_32.S
@@ -11,26 +11,23 @@
#include <linux/linkage.h>
#include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
/* if you want SMP support, implement these with real spinlocks */
.macro LOCK reg
- pushfl_cfi
+ pushfl
cli
.endm
.macro UNLOCK reg
- popfl_cfi
+ popfl
.endm
#define BEGIN(op) \
.macro endp; \
- CFI_ENDPROC; \
ENDPROC(atomic64_##op##_386); \
.purgem endp; \
.endm; \
ENTRY(atomic64_##op##_386); \
- CFI_STARTPROC; \
LOCK v;
#define ENDP endp
diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S
index 082a851..db3ae854 100644
--- a/arch/x86/lib/atomic64_cx8_32.S
+++ b/arch/x86/lib/atomic64_cx8_32.S
@@ -11,7 +11,6 @@
#include <linux/linkage.h>
#include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
.macro read64 reg
movl %ebx, %eax
@@ -22,16 +21,11 @@
.endm
ENTRY(atomic64_read_cx8)
- CFI_STARTPROC
-
read64 %ecx
ret
- CFI_ENDPROC
ENDPROC(atomic64_read_cx8)
ENTRY(atomic64_set_cx8)
- CFI_STARTPROC
-
1:
/* we don't need LOCK_PREFIX since aligned 64-bit writes
* are atomic on 586 and newer */
@@ -39,28 +33,23 @@
jne 1b
ret
- CFI_ENDPROC
ENDPROC(atomic64_set_cx8)
ENTRY(atomic64_xchg_cx8)
- CFI_STARTPROC
-
1:
LOCK_PREFIX
cmpxchg8b (%esi)
jne 1b
ret
- CFI_ENDPROC
ENDPROC(atomic64_xchg_cx8)
.macro addsub_return func ins insc
ENTRY(atomic64_\func\()_return_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebp
- pushl_cfi_reg ebx
- pushl_cfi_reg esi
- pushl_cfi_reg edi
+ pushl %ebp
+ pushl %ebx
+ pushl %esi
+ pushl %edi
movl %eax, %esi
movl %edx, %edi
@@ -79,12 +68,11 @@
10:
movl %ebx, %eax
movl %ecx, %edx
- popl_cfi_reg edi
- popl_cfi_reg esi
- popl_cfi_reg ebx
- popl_cfi_reg ebp
+ popl %edi
+ popl %esi
+ popl %ebx
+ popl %ebp
ret
- CFI_ENDPROC
ENDPROC(atomic64_\func\()_return_cx8)
.endm
@@ -93,8 +81,7 @@
.macro incdec_return func ins insc
ENTRY(atomic64_\func\()_return_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebx
+ pushl %ebx
read64 %esi
1:
@@ -109,9 +96,8 @@
10:
movl %ebx, %eax
movl %ecx, %edx
- popl_cfi_reg ebx
+ popl %ebx
ret
- CFI_ENDPROC
ENDPROC(atomic64_\func\()_return_cx8)
.endm
@@ -119,8 +105,7 @@
incdec_return dec sub sbb
ENTRY(atomic64_dec_if_positive_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebx
+ pushl %ebx
read64 %esi
1:
@@ -136,18 +121,16 @@
2:
movl %ebx, %eax
movl %ecx, %edx
- popl_cfi_reg ebx
+ popl %ebx
ret
- CFI_ENDPROC
ENDPROC(atomic64_dec_if_positive_cx8)
ENTRY(atomic64_add_unless_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebp
- pushl_cfi_reg ebx
+ pushl %ebp
+ pushl %ebx
/* these just push these two parameters on the stack */
- pushl_cfi_reg edi
- pushl_cfi_reg ecx
+ pushl %edi
+ pushl %ecx
movl %eax, %ebp
movl %edx, %edi
@@ -168,21 +151,18 @@
movl $1, %eax
3:
addl $8, %esp
- CFI_ADJUST_CFA_OFFSET -8
- popl_cfi_reg ebx
- popl_cfi_reg ebp
+ popl %ebx
+ popl %ebp
ret
4:
cmpl %edx, 4(%esp)
jne 2b
xorl %eax, %eax
jmp 3b
- CFI_ENDPROC
ENDPROC(atomic64_add_unless_cx8)
ENTRY(atomic64_inc_not_zero_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebx
+ pushl %ebx
read64 %esi
1:
@@ -199,7 +179,6 @@
movl $1, %eax
3:
- popl_cfi_reg ebx
+ popl %ebx
ret
- CFI_ENDPROC
ENDPROC(atomic64_inc_not_zero_cx8)
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 9bc944a..c1e6232 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -26,7 +26,6 @@
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/errno.h>
#include <asm/asm.h>
@@ -50,9 +49,8 @@
* alignment for the unrolled loop.
*/
ENTRY(csum_partial)
- CFI_STARTPROC
- pushl_cfi_reg esi
- pushl_cfi_reg ebx
+ pushl %esi
+ pushl %ebx
movl 20(%esp),%eax # Function arg: unsigned int sum
movl 16(%esp),%ecx # Function arg: int len
movl 12(%esp),%esi # Function arg: unsigned char *buff
@@ -129,10 +127,9 @@
jz 8f
roll $8, %eax
8:
- popl_cfi_reg ebx
- popl_cfi_reg esi
+ popl %ebx
+ popl %esi
ret
- CFI_ENDPROC
ENDPROC(csum_partial)
#else
@@ -140,9 +137,8 @@
/* Version for PentiumII/PPro */
ENTRY(csum_partial)
- CFI_STARTPROC
- pushl_cfi_reg esi
- pushl_cfi_reg ebx
+ pushl %esi
+ pushl %ebx
movl 20(%esp),%eax # Function arg: unsigned int sum
movl 16(%esp),%ecx # Function arg: int len
movl 12(%esp),%esi # Function arg: const unsigned char *buf
@@ -249,10 +245,9 @@
jz 90f
roll $8, %eax
90:
- popl_cfi_reg ebx
- popl_cfi_reg esi
+ popl %ebx
+ popl %esi
ret
- CFI_ENDPROC
ENDPROC(csum_partial)
#endif
@@ -287,12 +282,10 @@
#define FP 12
ENTRY(csum_partial_copy_generic)
- CFI_STARTPROC
subl $4,%esp
- CFI_ADJUST_CFA_OFFSET 4
- pushl_cfi_reg edi
- pushl_cfi_reg esi
- pushl_cfi_reg ebx
+ pushl %edi
+ pushl %esi
+ pushl %ebx
movl ARGBASE+16(%esp),%eax # sum
movl ARGBASE+12(%esp),%ecx # len
movl ARGBASE+4(%esp),%esi # src
@@ -401,12 +394,11 @@
.previous
- popl_cfi_reg ebx
- popl_cfi_reg esi
- popl_cfi_reg edi
- popl_cfi %ecx # equivalent to addl $4,%esp
+ popl %ebx
+ popl %esi
+ popl %edi
+ popl %ecx # equivalent to addl $4,%esp
ret
- CFI_ENDPROC
ENDPROC(csum_partial_copy_generic)
#else
@@ -426,10 +418,9 @@
#define ARGBASE 12
ENTRY(csum_partial_copy_generic)
- CFI_STARTPROC
- pushl_cfi_reg ebx
- pushl_cfi_reg edi
- pushl_cfi_reg esi
+ pushl %ebx
+ pushl %edi
+ pushl %esi
movl ARGBASE+4(%esp),%esi #src
movl ARGBASE+8(%esp),%edi #dst
movl ARGBASE+12(%esp),%ecx #len
@@ -489,11 +480,10 @@
jmp 7b
.previous
- popl_cfi_reg esi
- popl_cfi_reg edi
- popl_cfi_reg ebx
+ popl %esi
+ popl %edi
+ popl %ebx
ret
- CFI_ENDPROC
ENDPROC(csum_partial_copy_generic)
#undef ROUND
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index e67e579..a2fe51b 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,5 +1,4 @@
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
@@ -15,7 +14,6 @@
* %rdi - page
*/
ENTRY(clear_page)
- CFI_STARTPROC
ALTERNATIVE_2 "jmp clear_page_orig", "", X86_FEATURE_REP_GOOD, \
"jmp clear_page_c_e", X86_FEATURE_ERMS
@@ -24,11 +22,9 @@
xorl %eax,%eax
rep stosq
ret
- CFI_ENDPROC
ENDPROC(clear_page)
ENTRY(clear_page_orig)
- CFI_STARTPROC
xorl %eax,%eax
movl $4096/64,%ecx
@@ -48,14 +44,11 @@
jnz .Lloop
nop
ret
- CFI_ENDPROC
ENDPROC(clear_page_orig)
ENTRY(clear_page_c_e)
- CFI_STARTPROC
movl $4096,%ecx
xorl %eax,%eax
rep stosb
ret
- CFI_ENDPROC
ENDPROC(clear_page_c_e)
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index 40a1725..9b33024 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -6,7 +6,6 @@
*
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/percpu.h>
.text
@@ -21,7 +20,6 @@
* %al : Operation successful
*/
ENTRY(this_cpu_cmpxchg16b_emu)
-CFI_STARTPROC
#
# Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not
@@ -32,7 +30,7 @@
# *atomic* on a single cpu (as provided by the this_cpu_xx class of
# macros).
#
- pushfq_cfi
+ pushfq
cli
cmpq PER_CPU_VAR((%rsi)), %rax
@@ -43,17 +41,13 @@
movq %rbx, PER_CPU_VAR((%rsi))
movq %rcx, PER_CPU_VAR(8(%rsi))
- CFI_REMEMBER_STATE
- popfq_cfi
+ popfq
mov $1, %al
ret
- CFI_RESTORE_STATE
.Lnot_same:
- popfq_cfi
+ popfq
xor %al,%al
ret
-CFI_ENDPROC
-
ENDPROC(this_cpu_cmpxchg16b_emu)
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index b4807fce..ad53497 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -7,7 +7,6 @@
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
.text
@@ -20,14 +19,13 @@
* %ecx : high 32 bits of new value
*/
ENTRY(cmpxchg8b_emu)
-CFI_STARTPROC
#
# Emulate 'cmpxchg8b (%esi)' on UP except we don't
# set the whole ZF thing (caller will just compare
# eax:edx with the expected value)
#
- pushfl_cfi
+ pushfl
cli
cmpl (%esi), %eax
@@ -38,18 +36,15 @@
movl %ebx, (%esi)
movl %ecx, 4(%esi)
- CFI_REMEMBER_STATE
- popfl_cfi
+ popfl
ret
- CFI_RESTORE_STATE
.Lnot_same:
movl (%esi), %eax
.Lhalf_same:
movl 4(%esi), %edx
- popfl_cfi
+ popfl
ret
-CFI_ENDPROC
ENDPROC(cmpxchg8b_emu)
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 8239dbc..009f982 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -1,7 +1,6 @@
/* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
@@ -13,22 +12,16 @@
*/
ALIGN
ENTRY(copy_page)
- CFI_STARTPROC
ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
movl $4096/8, %ecx
rep movsq
ret
- CFI_ENDPROC
ENDPROC(copy_page)
ENTRY(copy_page_regs)
- CFI_STARTPROC
subq $2*8, %rsp
- CFI_ADJUST_CFA_OFFSET 2*8
movq %rbx, (%rsp)
- CFI_REL_OFFSET rbx, 0
movq %r12, 1*8(%rsp)
- CFI_REL_OFFSET r12, 1*8
movl $(4096/64)-5, %ecx
.p2align 4
@@ -87,11 +80,7 @@
jnz .Loop2
movq (%rsp), %rbx
- CFI_RESTORE rbx
movq 1*8(%rsp), %r12
- CFI_RESTORE r12
addq $2*8, %rsp
- CFI_ADJUST_CFA_OFFSET -2*8
ret
- CFI_ENDPROC
ENDPROC(copy_page_regs)
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index fa997df..982ce34 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -7,7 +7,6 @@
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/current.h>
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
@@ -16,33 +15,8 @@
#include <asm/asm.h>
#include <asm/smap.h>
- .macro ALIGN_DESTINATION
- /* check for bad alignment of destination */
- movl %edi,%ecx
- andl $7,%ecx
- jz 102f /* already aligned */
- subl $8,%ecx
- negl %ecx
- subl %ecx,%edx
-100: movb (%rsi),%al
-101: movb %al,(%rdi)
- incq %rsi
- incq %rdi
- decl %ecx
- jnz 100b
-102:
- .section .fixup,"ax"
-103: addl %ecx,%edx /* ecx is zerorest also */
- jmp copy_user_handle_tail
- .previous
-
- _ASM_EXTABLE(100b,103b)
- _ASM_EXTABLE(101b,103b)
- .endm
-
/* Standard copy_to_user with segment limit checking */
ENTRY(_copy_to_user)
- CFI_STARTPROC
GET_THREAD_INFO(%rax)
movq %rdi,%rcx
addq %rdx,%rcx
@@ -54,12 +28,10 @@
X86_FEATURE_REP_GOOD, \
"jmp copy_user_enhanced_fast_string", \
X86_FEATURE_ERMS
- CFI_ENDPROC
ENDPROC(_copy_to_user)
/* Standard copy_from_user with segment limit checking */
ENTRY(_copy_from_user)
- CFI_STARTPROC
GET_THREAD_INFO(%rax)
movq %rsi,%rcx
addq %rdx,%rcx
@@ -71,14 +43,12 @@
X86_FEATURE_REP_GOOD, \
"jmp copy_user_enhanced_fast_string", \
X86_FEATURE_ERMS
- CFI_ENDPROC
ENDPROC(_copy_from_user)
.section .fixup,"ax"
/* must zero dest */
ENTRY(bad_from_user)
bad_from_user:
- CFI_STARTPROC
movl %edx,%ecx
xorl %eax,%eax
rep
@@ -86,7 +56,6 @@
bad_to_user:
movl %edx,%eax
ret
- CFI_ENDPROC
ENDPROC(bad_from_user)
.previous
@@ -104,7 +73,6 @@
* eax uncopied bytes or 0 if successful.
*/
ENTRY(copy_user_generic_unrolled)
- CFI_STARTPROC
ASM_STAC
cmpl $8,%edx
jb 20f /* less then 8 bytes, go to byte copy loop */
@@ -186,7 +154,6 @@
_ASM_EXTABLE(19b,40b)
_ASM_EXTABLE(21b,50b)
_ASM_EXTABLE(22b,50b)
- CFI_ENDPROC
ENDPROC(copy_user_generic_unrolled)
/* Some CPUs run faster using the string copy instructions.
@@ -208,7 +175,6 @@
* eax uncopied bytes or 0 if successful.
*/
ENTRY(copy_user_generic_string)
- CFI_STARTPROC
ASM_STAC
cmpl $8,%edx
jb 2f /* less than 8 bytes, go to byte copy loop */
@@ -233,7 +199,6 @@
_ASM_EXTABLE(1b,11b)
_ASM_EXTABLE(3b,12b)
- CFI_ENDPROC
ENDPROC(copy_user_generic_string)
/*
@@ -249,7 +214,6 @@
* eax uncopied bytes or 0 if successful.
*/
ENTRY(copy_user_enhanced_fast_string)
- CFI_STARTPROC
ASM_STAC
movl %edx,%ecx
1: rep
@@ -264,5 +228,94 @@
.previous
_ASM_EXTABLE(1b,12b)
- CFI_ENDPROC
ENDPROC(copy_user_enhanced_fast_string)
+
+/*
+ * copy_user_nocache - Uncached memory copy with exception handling
+ * This will force destination/source out of cache for more performance.
+ */
+ENTRY(__copy_user_nocache)
+ ASM_STAC
+ cmpl $8,%edx
+ jb 20f /* less then 8 bytes, go to byte copy loop */
+ ALIGN_DESTINATION
+ movl %edx,%ecx
+ andl $63,%edx
+ shrl $6,%ecx
+ jz 17f
+1: movq (%rsi),%r8
+2: movq 1*8(%rsi),%r9
+3: movq 2*8(%rsi),%r10
+4: movq 3*8(%rsi),%r11
+5: movnti %r8,(%rdi)
+6: movnti %r9,1*8(%rdi)
+7: movnti %r10,2*8(%rdi)
+8: movnti %r11,3*8(%rdi)
+9: movq 4*8(%rsi),%r8
+10: movq 5*8(%rsi),%r9
+11: movq 6*8(%rsi),%r10
+12: movq 7*8(%rsi),%r11
+13: movnti %r8,4*8(%rdi)
+14: movnti %r9,5*8(%rdi)
+15: movnti %r10,6*8(%rdi)
+16: movnti %r11,7*8(%rdi)
+ leaq 64(%rsi),%rsi
+ leaq 64(%rdi),%rdi
+ decl %ecx
+ jnz 1b
+17: movl %edx,%ecx
+ andl $7,%edx
+ shrl $3,%ecx
+ jz 20f
+18: movq (%rsi),%r8
+19: movnti %r8,(%rdi)
+ leaq 8(%rsi),%rsi
+ leaq 8(%rdi),%rdi
+ decl %ecx
+ jnz 18b
+20: andl %edx,%edx
+ jz 23f
+ movl %edx,%ecx
+21: movb (%rsi),%al
+22: movb %al,(%rdi)
+ incq %rsi
+ incq %rdi
+ decl %ecx
+ jnz 21b
+23: xorl %eax,%eax
+ ASM_CLAC
+ sfence
+ ret
+
+ .section .fixup,"ax"
+30: shll $6,%ecx
+ addl %ecx,%edx
+ jmp 60f
+40: lea (%rdx,%rcx,8),%rdx
+ jmp 60f
+50: movl %ecx,%edx
+60: sfence
+ jmp copy_user_handle_tail
+ .previous
+
+ _ASM_EXTABLE(1b,30b)
+ _ASM_EXTABLE(2b,30b)
+ _ASM_EXTABLE(3b,30b)
+ _ASM_EXTABLE(4b,30b)
+ _ASM_EXTABLE(5b,30b)
+ _ASM_EXTABLE(6b,30b)
+ _ASM_EXTABLE(7b,30b)
+ _ASM_EXTABLE(8b,30b)
+ _ASM_EXTABLE(9b,30b)
+ _ASM_EXTABLE(10b,30b)
+ _ASM_EXTABLE(11b,30b)
+ _ASM_EXTABLE(12b,30b)
+ _ASM_EXTABLE(13b,30b)
+ _ASM_EXTABLE(14b,30b)
+ _ASM_EXTABLE(15b,30b)
+ _ASM_EXTABLE(16b,30b)
+ _ASM_EXTABLE(18b,40b)
+ _ASM_EXTABLE(19b,40b)
+ _ASM_EXTABLE(21b,50b)
+ _ASM_EXTABLE(22b,50b)
+ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S
deleted file mode 100644
index 6a4f43c..0000000
--- a/arch/x86/lib/copy_user_nocache_64.S
+++ /dev/null
@@ -1,136 +0,0 @@
-/*
- * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com>
- * Copyright 2002 Andi Kleen, SuSE Labs.
- * Subject to the GNU Public License v2.
- *
- * Functions to copy from and to user space.
- */
-
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-
-#define FIX_ALIGNMENT 1
-
-#include <asm/current.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-
- .macro ALIGN_DESTINATION
-#ifdef FIX_ALIGNMENT
- /* check for bad alignment of destination */
- movl %edi,%ecx
- andl $7,%ecx
- jz 102f /* already aligned */
- subl $8,%ecx
- negl %ecx
- subl %ecx,%edx
-100: movb (%rsi),%al
-101: movb %al,(%rdi)
- incq %rsi
- incq %rdi
- decl %ecx
- jnz 100b
-102:
- .section .fixup,"ax"
-103: addl %ecx,%edx /* ecx is zerorest also */
- jmp copy_user_handle_tail
- .previous
-
- _ASM_EXTABLE(100b,103b)
- _ASM_EXTABLE(101b,103b)
-#endif
- .endm
-
-/*
- * copy_user_nocache - Uncached memory copy with exception handling
- * This will force destination/source out of cache for more performance.
- */
-ENTRY(__copy_user_nocache)
- CFI_STARTPROC
- ASM_STAC
- cmpl $8,%edx
- jb 20f /* less then 8 bytes, go to byte copy loop */
- ALIGN_DESTINATION
- movl %edx,%ecx
- andl $63,%edx
- shrl $6,%ecx
- jz 17f
-1: movq (%rsi),%r8
-2: movq 1*8(%rsi),%r9
-3: movq 2*8(%rsi),%r10
-4: movq 3*8(%rsi),%r11
-5: movnti %r8,(%rdi)
-6: movnti %r9,1*8(%rdi)
-7: movnti %r10,2*8(%rdi)
-8: movnti %r11,3*8(%rdi)
-9: movq 4*8(%rsi),%r8
-10: movq 5*8(%rsi),%r9
-11: movq 6*8(%rsi),%r10
-12: movq 7*8(%rsi),%r11
-13: movnti %r8,4*8(%rdi)
-14: movnti %r9,5*8(%rdi)
-15: movnti %r10,6*8(%rdi)
-16: movnti %r11,7*8(%rdi)
- leaq 64(%rsi),%rsi
- leaq 64(%rdi),%rdi
- decl %ecx
- jnz 1b
-17: movl %edx,%ecx
- andl $7,%edx
- shrl $3,%ecx
- jz 20f
-18: movq (%rsi),%r8
-19: movnti %r8,(%rdi)
- leaq 8(%rsi),%rsi
- leaq 8(%rdi),%rdi
- decl %ecx
- jnz 18b
-20: andl %edx,%edx
- jz 23f
- movl %edx,%ecx
-21: movb (%rsi),%al
-22: movb %al,(%rdi)
- incq %rsi
- incq %rdi
- decl %ecx
- jnz 21b
-23: xorl %eax,%eax
- ASM_CLAC
- sfence
- ret
-
- .section .fixup,"ax"
-30: shll $6,%ecx
- addl %ecx,%edx
- jmp 60f
-40: lea (%rdx,%rcx,8),%rdx
- jmp 60f
-50: movl %ecx,%edx
-60: sfence
- jmp copy_user_handle_tail
- .previous
-
- _ASM_EXTABLE(1b,30b)
- _ASM_EXTABLE(2b,30b)
- _ASM_EXTABLE(3b,30b)
- _ASM_EXTABLE(4b,30b)
- _ASM_EXTABLE(5b,30b)
- _ASM_EXTABLE(6b,30b)
- _ASM_EXTABLE(7b,30b)
- _ASM_EXTABLE(8b,30b)
- _ASM_EXTABLE(9b,30b)
- _ASM_EXTABLE(10b,30b)
- _ASM_EXTABLE(11b,30b)
- _ASM_EXTABLE(12b,30b)
- _ASM_EXTABLE(13b,30b)
- _ASM_EXTABLE(14b,30b)
- _ASM_EXTABLE(15b,30b)
- _ASM_EXTABLE(16b,30b)
- _ASM_EXTABLE(18b,40b)
- _ASM_EXTABLE(19b,40b)
- _ASM_EXTABLE(21b,50b)
- _ASM_EXTABLE(22b,50b)
- CFI_ENDPROC
-ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index 9734182..7e48807 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -6,7 +6,6 @@
* for more details. No warranty for anything given at all.
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/errno.h>
#include <asm/asm.h>
@@ -47,23 +46,16 @@
ENTRY(csum_partial_copy_generic)
- CFI_STARTPROC
cmpl $3*64, %edx
jle .Lignore
.Lignore:
subq $7*8, %rsp
- CFI_ADJUST_CFA_OFFSET 7*8
movq %rbx, 2*8(%rsp)
- CFI_REL_OFFSET rbx, 2*8
movq %r12, 3*8(%rsp)
- CFI_REL_OFFSET r12, 3*8
movq %r14, 4*8(%rsp)
- CFI_REL_OFFSET r14, 4*8
movq %r13, 5*8(%rsp)
- CFI_REL_OFFSET r13, 5*8
movq %rbp, 6*8(%rsp)
- CFI_REL_OFFSET rbp, 6*8
movq %r8, (%rsp)
movq %r9, 1*8(%rsp)
@@ -206,22 +198,14 @@
addl %ebx, %eax
adcl %r9d, %eax /* carry */
- CFI_REMEMBER_STATE
.Lende:
movq 2*8(%rsp), %rbx
- CFI_RESTORE rbx
movq 3*8(%rsp), %r12
- CFI_RESTORE r12
movq 4*8(%rsp), %r14
- CFI_RESTORE r14
movq 5*8(%rsp), %r13
- CFI_RESTORE r13
movq 6*8(%rsp), %rbp
- CFI_RESTORE rbp
addq $7*8, %rsp
- CFI_ADJUST_CFA_OFFSET -7*8
ret
- CFI_RESTORE_STATE
/* Exception handlers. Very simple, zeroing is done in the wrappers */
.Lbad_source:
@@ -237,5 +221,4 @@
jz .Lende
movl $-EFAULT, (%rax)
jmp .Lende
- CFI_ENDPROC
ENDPROC(csum_partial_copy_generic)
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index a451235..46668cd 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -26,7 +26,6 @@
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/page_types.h>
#include <asm/errno.h>
#include <asm/asm-offsets.h>
@@ -36,7 +35,6 @@
.text
ENTRY(__get_user_1)
- CFI_STARTPROC
GET_THREAD_INFO(%_ASM_DX)
cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
jae bad_get_user
@@ -45,11 +43,9 @@
xor %eax,%eax
ASM_CLAC
ret
- CFI_ENDPROC
ENDPROC(__get_user_1)
ENTRY(__get_user_2)
- CFI_STARTPROC
add $1,%_ASM_AX
jc bad_get_user
GET_THREAD_INFO(%_ASM_DX)
@@ -60,11 +56,9 @@
xor %eax,%eax
ASM_CLAC
ret
- CFI_ENDPROC
ENDPROC(__get_user_2)
ENTRY(__get_user_4)
- CFI_STARTPROC
add $3,%_ASM_AX
jc bad_get_user
GET_THREAD_INFO(%_ASM_DX)
@@ -75,11 +69,9 @@
xor %eax,%eax
ASM_CLAC
ret
- CFI_ENDPROC
ENDPROC(__get_user_4)
ENTRY(__get_user_8)
- CFI_STARTPROC
#ifdef CONFIG_X86_64
add $7,%_ASM_AX
jc bad_get_user
@@ -104,28 +96,23 @@
ASM_CLAC
ret
#endif
- CFI_ENDPROC
ENDPROC(__get_user_8)
bad_get_user:
- CFI_STARTPROC
xor %edx,%edx
mov $(-EFAULT),%_ASM_AX
ASM_CLAC
ret
- CFI_ENDPROC
END(bad_get_user)
#ifdef CONFIG_X86_32
bad_get_user_8:
- CFI_STARTPROC
xor %edx,%edx
xor %ecx,%ecx
mov $(-EFAULT),%_ASM_AX
ASM_CLAC
ret
- CFI_ENDPROC
END(bad_get_user_8)
#endif
diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S
index 05a95e7..33147fe 100644
--- a/arch/x86/lib/iomap_copy_64.S
+++ b/arch/x86/lib/iomap_copy_64.S
@@ -16,15 +16,12 @@
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
/*
* override generic version in lib/iomap_copy.c
*/
ENTRY(__iowrite32_copy)
- CFI_STARTPROC
movl %edx,%ecx
rep movsd
ret
- CFI_ENDPROC
ENDPROC(__iowrite32_copy)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index b046664..16698bb 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -2,7 +2,6 @@
#include <linux/linkage.h>
#include <asm/cpufeature.h>
-#include <asm/dwarf2.h>
#include <asm/alternative-asm.h>
/*
@@ -53,7 +52,6 @@
ENDPROC(memcpy_erms)
ENTRY(memcpy_orig)
- CFI_STARTPROC
movq %rdi, %rax
cmpq $0x20, %rdx
@@ -178,5 +176,4 @@
.Lend:
retq
- CFI_ENDPROC
ENDPROC(memcpy_orig)
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 0f8a0d0..ca2afdd 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -6,7 +6,6 @@
* - Copyright 2011 Fenghua Yu <fenghua.yu@intel.com>
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
@@ -27,7 +26,6 @@
ENTRY(memmove)
ENTRY(__memmove)
- CFI_STARTPROC
/* Handle more 32 bytes in loop */
mov %rdi, %rax
@@ -207,6 +205,5 @@
movb %r11b, (%rdi)
13:
retq
- CFI_ENDPROC
ENDPROC(__memmove)
ENDPROC(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 93118fb..2661fad 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -1,7 +1,6 @@
/* Copyright 2002 Andi Kleen, SuSE Labs */
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
@@ -66,7 +65,6 @@
ENDPROC(memset_erms)
ENTRY(memset_orig)
- CFI_STARTPROC
movq %rdi,%r10
/* expand byte value */
@@ -78,7 +76,6 @@
movl %edi,%r9d
andl $7,%r9d
jnz .Lbad_alignment
- CFI_REMEMBER_STATE
.Lafter_bad_alignment:
movq %rdx,%rcx
@@ -128,7 +125,6 @@
movq %r10,%rax
ret
- CFI_RESTORE_STATE
.Lbad_alignment:
cmpq $7,%rdx
jbe .Lhandle_7
@@ -139,5 +135,4 @@
subq %r8,%rdx
jmp .Lafter_bad_alignment
.Lfinal:
- CFI_ENDPROC
ENDPROC(memset_orig)
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index 3ca5218..c815564 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -1,6 +1,5 @@
#include <linux/linkage.h>
#include <linux/errno.h>
-#include <asm/dwarf2.h>
#include <asm/asm.h>
#include <asm/msr.h>
@@ -13,9 +12,8 @@
*/
.macro op_safe_regs op
ENTRY(\op\()_safe_regs)
- CFI_STARTPROC
- pushq_cfi_reg rbx
- pushq_cfi_reg rbp
+ pushq %rbx
+ pushq %rbp
movq %rdi, %r10 /* Save pointer */
xorl %r11d, %r11d /* Return value */
movl (%rdi), %eax
@@ -25,7 +23,6 @@
movl 20(%rdi), %ebp
movl 24(%rdi), %esi
movl 28(%rdi), %edi
- CFI_REMEMBER_STATE
1: \op
2: movl %eax, (%r10)
movl %r11d, %eax /* Return value */
@@ -35,16 +32,14 @@
movl %ebp, 20(%r10)
movl %esi, 24(%r10)
movl %edi, 28(%r10)
- popq_cfi_reg rbp
- popq_cfi_reg rbx
+ popq %rbp
+ popq %rbx
ret
3:
- CFI_RESTORE_STATE
movl $-EIO, %r11d
jmp 2b
_ASM_EXTABLE(1b, 3b)
- CFI_ENDPROC
ENDPROC(\op\()_safe_regs)
.endm
@@ -52,13 +47,12 @@
.macro op_safe_regs op
ENTRY(\op\()_safe_regs)
- CFI_STARTPROC
- pushl_cfi_reg ebx
- pushl_cfi_reg ebp
- pushl_cfi_reg esi
- pushl_cfi_reg edi
- pushl_cfi $0 /* Return value */
- pushl_cfi %eax
+ pushl %ebx
+ pushl %ebp
+ pushl %esi
+ pushl %edi
+ pushl $0 /* Return value */
+ pushl %eax
movl 4(%eax), %ecx
movl 8(%eax), %edx
movl 12(%eax), %ebx
@@ -66,32 +60,28 @@
movl 24(%eax), %esi
movl 28(%eax), %edi
movl (%eax), %eax
- CFI_REMEMBER_STATE
1: \op
-2: pushl_cfi %eax
+2: pushl %eax
movl 4(%esp), %eax
- popl_cfi (%eax)
+ popl (%eax)
addl $4, %esp
- CFI_ADJUST_CFA_OFFSET -4
movl %ecx, 4(%eax)
movl %edx, 8(%eax)
movl %ebx, 12(%eax)
movl %ebp, 20(%eax)
movl %esi, 24(%eax)
movl %edi, 28(%eax)
- popl_cfi %eax
- popl_cfi_reg edi
- popl_cfi_reg esi
- popl_cfi_reg ebp
- popl_cfi_reg ebx
+ popl %eax
+ popl %edi
+ popl %esi
+ popl %ebp
+ popl %ebx
ret
3:
- CFI_RESTORE_STATE
movl $-EIO, 4(%esp)
jmp 2b
_ASM_EXTABLE(1b, 3b)
- CFI_ENDPROC
ENDPROC(\op\()_safe_regs)
.endm
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index fc6ba17..e0817a1 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -11,7 +11,6 @@
* return value.
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/thread_info.h>
#include <asm/errno.h>
#include <asm/asm.h>
@@ -30,11 +29,9 @@
* as they get called from within inline assembly.
*/
-#define ENTER CFI_STARTPROC ; \
- GET_THREAD_INFO(%_ASM_BX)
+#define ENTER GET_THREAD_INFO(%_ASM_BX)
#define EXIT ASM_CLAC ; \
- ret ; \
- CFI_ENDPROC
+ ret
.text
ENTRY(__put_user_1)
@@ -87,7 +84,6 @@
ENDPROC(__put_user_8)
bad_put_user:
- CFI_STARTPROC
movl $-EFAULT,%eax
EXIT
END(bad_put_user)
diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S
index 2322abe..40027db 100644
--- a/arch/x86/lib/rwsem.S
+++ b/arch/x86/lib/rwsem.S
@@ -15,7 +15,6 @@
#include <linux/linkage.h>
#include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
#define __ASM_HALF_REG(reg) __ASM_SEL(reg, e##reg)
#define __ASM_HALF_SIZE(inst) __ASM_SEL(inst##w, inst##l)
@@ -34,10 +33,10 @@
*/
#define save_common_regs \
- pushl_cfi_reg ecx
+ pushl %ecx
#define restore_common_regs \
- popl_cfi_reg ecx
+ popl %ecx
/* Avoid uglifying the argument copying x86-64 needs to do. */
.macro movq src, dst
@@ -64,50 +63,45 @@
*/
#define save_common_regs \
- pushq_cfi_reg rdi; \
- pushq_cfi_reg rsi; \
- pushq_cfi_reg rcx; \
- pushq_cfi_reg r8; \
- pushq_cfi_reg r9; \
- pushq_cfi_reg r10; \
- pushq_cfi_reg r11
+ pushq %rdi; \
+ pushq %rsi; \
+ pushq %rcx; \
+ pushq %r8; \
+ pushq %r9; \
+ pushq %r10; \
+ pushq %r11
#define restore_common_regs \
- popq_cfi_reg r11; \
- popq_cfi_reg r10; \
- popq_cfi_reg r9; \
- popq_cfi_reg r8; \
- popq_cfi_reg rcx; \
- popq_cfi_reg rsi; \
- popq_cfi_reg rdi
+ popq %r11; \
+ popq %r10; \
+ popq %r9; \
+ popq %r8; \
+ popq %rcx; \
+ popq %rsi; \
+ popq %rdi
#endif
/* Fix up special calling conventions */
ENTRY(call_rwsem_down_read_failed)
- CFI_STARTPROC
save_common_regs
- __ASM_SIZE(push,_cfi_reg) __ASM_REG(dx)
+ __ASM_SIZE(push,) %__ASM_REG(dx)
movq %rax,%rdi
call rwsem_down_read_failed
- __ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx)
+ __ASM_SIZE(pop,) %__ASM_REG(dx)
restore_common_regs
ret
- CFI_ENDPROC
ENDPROC(call_rwsem_down_read_failed)
ENTRY(call_rwsem_down_write_failed)
- CFI_STARTPROC
save_common_regs
movq %rax,%rdi
call rwsem_down_write_failed
restore_common_regs
ret
- CFI_ENDPROC
ENDPROC(call_rwsem_down_write_failed)
ENTRY(call_rwsem_wake)
- CFI_STARTPROC
/* do nothing if still outstanding active readers */
__ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx)
jnz 1f
@@ -116,17 +110,14 @@
call rwsem_wake
restore_common_regs
1: ret
- CFI_ENDPROC
ENDPROC(call_rwsem_wake)
ENTRY(call_rwsem_downgrade_wake)
- CFI_STARTPROC
save_common_regs
- __ASM_SIZE(push,_cfi_reg) __ASM_REG(dx)
+ __ASM_SIZE(push,) %__ASM_REG(dx)
movq %rax,%rdi
call rwsem_downgrade_wake
- __ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx)
+ __ASM_SIZE(pop,) %__ASM_REG(dx)
restore_common_regs
ret
- CFI_ENDPROC
ENDPROC(call_rwsem_downgrade_wake)
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 6440221..4093216 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -8,7 +8,6 @@
* of the License.
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
/*
* Calling convention :
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 99f7610..ddeff48 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -966,7 +966,12 @@
}
ctx.cleanup_addr = proglen;
- for (pass = 0; pass < 10; pass++) {
+ /* JITed image shrinks with every pass and the loop iterates
+ * until the image stops shrinking. Very large bpf programs
+ * may converge on the last pass. In such case do one more
+ * pass to emit the final image
+ */
+ for (pass = 0; pass < 10 || image; pass++) {
proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
if (proglen <= 0) {
image = NULL;
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index d939633..14a63ed 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -482,9 +482,16 @@
int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
{
- struct pci_sysdata *sd = bridge->bus->sysdata;
-
- ACPI_COMPANION_SET(&bridge->dev, sd->companion);
+ /*
+ * We pass NULL as parent to pci_create_root_bus(), so if it is not NULL
+ * here, pci_create_root_bus() has been called by someone else and
+ * sysdata is likely to be different from what we expect. Let it go in
+ * that case.
+ */
+ if (!bridge->dev.parent) {
+ struct pci_sysdata *sd = bridge->bus->sysdata;
+ ACPI_COMPANION_SET(&bridge->dev, sd->companion);
+ }
return 0;
}
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 852aa4c..2706230 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -208,6 +208,7 @@
static int intel_mid_pci_irq_enable(struct pci_dev *dev)
{
+ struct irq_alloc_info info;
int polarity;
if (dev->irq_managed && dev->irq > 0)
@@ -217,14 +218,13 @@
polarity = 0; /* active high */
else
polarity = 1; /* active low */
+ ioapic_set_alloc_attr(&info, dev_to_node(&dev->dev), 1, polarity);
/*
* MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
* IOAPIC RTE entries, so we just enable RTE for the device.
*/
- if (mp_set_gsi_attr(dev->irq, 1, polarity, dev_to_node(&dev->dev)))
- return -EBUSY;
- if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC) < 0)
+ if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC, &info) < 0)
return -EBUSY;
dev->irq_managed = 1;
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 5dc6ca5..9bd1154 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -146,19 +146,20 @@
/*
* Code for querying and setting of IRQ routes on various interrupt routers.
+ * PIC Edge/Level Control Registers (ELCR) 0x4d0 & 0x4d1.
*/
-void eisa_set_level_irq(unsigned int irq)
+void elcr_set_level_irq(unsigned int irq)
{
unsigned char mask = 1 << (irq & 7);
unsigned int port = 0x4d0 + (irq >> 3);
unsigned char val;
- static u16 eisa_irq_mask;
+ static u16 elcr_irq_mask;
- if (irq >= 16 || (1 << irq) & eisa_irq_mask)
+ if (irq >= 16 || (1 << irq) & elcr_irq_mask)
return;
- eisa_irq_mask |= (1 << irq);
+ elcr_irq_mask |= (1 << irq);
printk(KERN_DEBUG "PCI: setting IRQ %u as level-triggered\n", irq);
val = inb(port);
if (!(val & mask)) {
@@ -965,11 +966,11 @@
} else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \
((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) {
msg = "found";
- eisa_set_level_irq(irq);
+ elcr_set_level_irq(irq);
} else if (newirq && r->set &&
(dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) {
if (r->set(pirq_router_dev, dev, pirq, newirq)) {
- eisa_set_level_irq(newirq);
+ elcr_set_level_irq(newirq);
msg = "assigned";
irq = newirq;
}
diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile
index a62e0be..f1a6c8e 100644
--- a/arch/x86/platform/Makefile
+++ b/arch/x86/platform/Makefile
@@ -1,4 +1,5 @@
# Platform specific code goes here
+obj-y += atom/
obj-y += ce4100/
obj-y += efi/
obj-y += geode/
diff --git a/arch/x86/platform/atom/Makefile b/arch/x86/platform/atom/Makefile
new file mode 100644
index 0000000..0a3a40c
--- /dev/null
+++ b/arch/x86/platform/atom/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_PUNIT_ATOM_DEBUG) += punit_atom_debug.o
diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c
new file mode 100644
index 0000000..5ca8ead
--- /dev/null
+++ b/arch/x86/platform/atom/punit_atom_debug.c
@@ -0,0 +1,183 @@
+/*
+ * Intel SOC Punit device state debug driver
+ * Punit controls power management for North Complex devices (Graphics
+ * blocks, Image Signal Processing, video processing, display, DSP etc.)
+ *
+ * Copyright (c) 2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/io.h>
+#include <asm/cpu_device_id.h>
+#include <asm/iosf_mbi.h>
+
+/* Side band Interface port */
+#define PUNIT_PORT 0x04
+/* Power gate status reg */
+#define PWRGT_STATUS 0x61
+/* Subsystem config/status Video processor */
+#define VED_SS_PM0 0x32
+/* Subsystem config/status ISP (Image Signal Processor) */
+#define ISP_SS_PM0 0x39
+/* Subsystem config/status Input/output controller */
+#define MIO_SS_PM 0x3B
+/* Shift bits for getting status for video, isp and i/o */
+#define SSS_SHIFT 24
+/* Shift bits for getting status for graphics rendering */
+#define RENDER_POS 0
+/* Shift bits for getting status for media control */
+#define MEDIA_POS 2
+/* Shift bits for getting status for Valley View/Baytrail display */
+#define VLV_DISPLAY_POS 6
+/* Subsystem config/status display for Cherry Trail SOC */
+#define CHT_DSP_SSS 0x36
+/* Shift bits for getting status for display */
+#define CHT_DSP_SSS_POS 16
+
+struct punit_device {
+ char *name;
+ int reg;
+ int sss_pos;
+};
+
+static const struct punit_device punit_device_byt[] = {
+ { "GFX RENDER", PWRGT_STATUS, RENDER_POS },
+ { "GFX MEDIA", PWRGT_STATUS, MEDIA_POS },
+ { "DISPLAY", PWRGT_STATUS, VLV_DISPLAY_POS },
+ { "VED", VED_SS_PM0, SSS_SHIFT },
+ { "ISP", ISP_SS_PM0, SSS_SHIFT },
+ { "MIO", MIO_SS_PM, SSS_SHIFT },
+ { NULL }
+};
+
+static const struct punit_device punit_device_cht[] = {
+ { "GFX RENDER", PWRGT_STATUS, RENDER_POS },
+ { "GFX MEDIA", PWRGT_STATUS, MEDIA_POS },
+ { "DISPLAY", CHT_DSP_SSS, CHT_DSP_SSS_POS },
+ { "VED", VED_SS_PM0, SSS_SHIFT },
+ { "ISP", ISP_SS_PM0, SSS_SHIFT },
+ { "MIO", MIO_SS_PM, SSS_SHIFT },
+ { NULL }
+};
+
+static const char * const dstates[] = {"D0", "D0i1", "D0i2", "D0i3"};
+
+static int punit_dev_state_show(struct seq_file *seq_file, void *unused)
+{
+ u32 punit_pwr_status;
+ struct punit_device *punit_devp = seq_file->private;
+ int index;
+ int status;
+
+ seq_puts(seq_file, "\n\nPUNIT NORTH COMPLEX DEVICES :\n");
+ while (punit_devp->name) {
+ status = iosf_mbi_read(PUNIT_PORT, BT_MBI_PMC_READ,
+ punit_devp->reg,
+ &punit_pwr_status);
+ if (status) {
+ seq_printf(seq_file, "%9s : Read Failed\n",
+ punit_devp->name);
+ } else {
+ index = (punit_pwr_status >> punit_devp->sss_pos) & 3;
+ seq_printf(seq_file, "%9s : %s\n", punit_devp->name,
+ dstates[index]);
+ }
+ punit_devp++;
+ }
+
+ return 0;
+}
+
+static int punit_dev_state_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, punit_dev_state_show, inode->i_private);
+}
+
+static const struct file_operations punit_dev_state_ops = {
+ .open = punit_dev_state_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static struct dentry *punit_dbg_file;
+
+static int punit_dbgfs_register(struct punit_device *punit_device)
+{
+ static struct dentry *dev_state;
+
+ punit_dbg_file = debugfs_create_dir("punit_atom", NULL);
+ if (!punit_dbg_file)
+ return -ENXIO;
+
+ dev_state = debugfs_create_file("dev_power_state", S_IFREG | S_IRUGO,
+ punit_dbg_file, punit_device,
+ &punit_dev_state_ops);
+ if (!dev_state) {
+ pr_err("punit_dev_state register failed\n");
+ debugfs_remove(punit_dbg_file);
+ return -ENXIO;
+ }
+
+ return 0;
+}
+
+static void punit_dbgfs_unregister(void)
+{
+ debugfs_remove_recursive(punit_dbg_file);
+}
+
+#define ICPU(model, drv_data) \
+ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT,\
+ (kernel_ulong_t)&drv_data }
+
+static const struct x86_cpu_id intel_punit_cpu_ids[] = {
+ ICPU(55, punit_device_byt), /* Valleyview, Bay Trail */
+ ICPU(76, punit_device_cht), /* Braswell, Cherry Trail */
+ {}
+};
+
+MODULE_DEVICE_TABLE(x86cpu, intel_punit_cpu_ids);
+
+static int __init punit_atom_debug_init(void)
+{
+ const struct x86_cpu_id *id;
+ int ret;
+
+ id = x86_match_cpu(intel_punit_cpu_ids);
+ if (!id)
+ return -ENODEV;
+
+ ret = punit_dbgfs_register((struct punit_device *)id->driver_data);
+ if (ret < 0)
+ return ret;
+
+ return 0;
+}
+
+static void __exit punit_atom_debug_exit(void)
+{
+ punit_dbgfs_unregister();
+}
+
+module_init(punit_atom_debug_init);
+module_exit(punit_atom_debug_exit);
+
+MODULE_AUTHOR("Kumar P, Mahesh <mahesh.kumar.p@intel.com>");
+MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
+MODULE_DESCRIPTION("Driver for Punit devices states debugging");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
index 0b283d4..de73413 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
@@ -27,6 +27,7 @@
static int tangier_probe(struct platform_device *pdev)
{
int gsi;
+ struct irq_alloc_info info;
struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data;
if (!pdata)
@@ -34,8 +35,8 @@
/* IOAPIC builds identity mapping between GSI and IRQ on MID */
gsi = pdata->irq;
- if (mp_set_gsi_attr(gsi, 1, 0, cpu_to_node(0)) ||
- mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC) <= 0) {
+ ioapic_set_alloc_attr(&info, cpu_to_node(0), 1, 0);
+ if (mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info) <= 0) {
dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n",
gsi);
return -EINVAL;
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 3005f0c..01d54ea 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -81,26 +81,34 @@
return 0;
}
+static void __init intel_mid_setup_bp_timer(void)
+{
+ apbt_time_init();
+ setup_boot_APIC_clock();
+}
+
static void __init intel_mid_time_init(void)
{
sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
+
switch (intel_mid_timer_options) {
case INTEL_MID_TIMER_APBT_ONLY:
break;
case INTEL_MID_TIMER_LAPIC_APBT:
- x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
+ /* Use apbt and local apic */
+ x86_init.timers.setup_percpu_clockev = intel_mid_setup_bp_timer;
x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
- break;
+ return;
default:
if (!boot_cpu_has(X86_FEATURE_ARAT))
break;
+ /* Lapic only, no apbt */
x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
return;
}
- /* we need at least one APB timer */
- pre_init_apic_IRQ0();
- apbt_time_init();
+
+ x86_init.timers.setup_percpu_clockev = apbt_time_init;
}
static void intel_mid_arch_setup(void)
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index c14ad34..ce992e8 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -95,18 +95,16 @@
pr_debug("timer[%d]: paddr = 0x%08x, freq = %dHz, irq = %d\n",
totallen, (u32)pentry->phys_addr,
pentry->freq_hz, pentry->irq);
- if (!pentry->irq)
- continue;
- mp_irq.type = MP_INTSRC;
- mp_irq.irqtype = mp_INT;
-/* triggering mode edge bit 2-3, active high polarity bit 0-1 */
- mp_irq.irqflag = 5;
- mp_irq.srcbus = MP_BUS_ISA;
- mp_irq.srcbusirq = pentry->irq; /* IRQ */
- mp_irq.dstapic = MP_APIC_ALL;
- mp_irq.dstirq = pentry->irq;
- mp_save_irq(&mp_irq);
- mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC);
+ mp_irq.type = MP_INTSRC;
+ mp_irq.irqtype = mp_INT;
+ /* triggering mode edge bit 2-3, active high polarity bit 0-1 */
+ mp_irq.irqflag = 5;
+ mp_irq.srcbus = MP_BUS_ISA;
+ mp_irq.srcbusirq = pentry->irq; /* IRQ */
+ mp_irq.dstapic = MP_APIC_ALL;
+ mp_irq.dstirq = pentry->irq;
+ mp_save_irq(&mp_irq);
+ mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL);
}
return 0;
@@ -177,7 +175,7 @@
mp_irq.dstapic = MP_APIC_ALL;
mp_irq.dstirq = pentry->irq;
mp_save_irq(&mp_irq);
- mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC);
+ mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL);
}
return 0;
}
@@ -436,6 +434,7 @@
struct devs_id *dev = NULL;
int num, i, ret;
int polarity;
+ struct irq_alloc_info info;
sb = (struct sfi_table_simple *)table;
num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry);
@@ -469,9 +468,8 @@
polarity = 1;
}
- ret = mp_set_gsi_attr(irq, 1, polarity, NUMA_NO_NODE);
- if (ret == 0)
- ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC);
+ ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 1, polarity);
+ ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC, &info);
WARN_ON(ret < 0);
}
diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c
index 2a8a74f..6c7111b 100644
--- a/arch/x86/platform/sfi/sfi.c
+++ b/arch/x86/platform/sfi/sfi.c
@@ -25,8 +25,8 @@
#include <linux/init.h>
#include <linux/sfi.h>
#include <linux/io.h>
-#include <linux/irqdomain.h>
+#include <asm/irqdomain.h>
#include <asm/io_apic.h>
#include <asm/mpspec.h>
#include <asm/setup.h>
@@ -71,9 +71,6 @@
#endif /* CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_IO_APIC
-static struct irq_domain_ops sfi_ioapic_irqdomain_ops = {
- .map = mp_irqdomain_map,
-};
static int __init sfi_parse_ioapic(struct sfi_table_header *table)
{
@@ -82,7 +79,7 @@
int i, num;
struct ioapic_domain_cfg cfg = {
.type = IOAPIC_DOMAIN_STRICT,
- .ops = &sfi_ioapic_irqdomain_ops,
+ .ops = &mp_ioapic_irqdomain_ops,
};
sb = (struct sfi_table_simple *)table;
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index 0ce6736..8570abe 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -13,22 +13,37 @@
#include <linux/slab.h>
#include <linux/irq.h>
+#include <asm/irqdomain.h>
#include <asm/apic.h>
#include <asm/uv/uv_irq.h>
#include <asm/uv/uv_hub.h>
/* MMR offset and pnode of hub sourcing interrupts for a given irq */
-struct uv_irq_2_mmr_pnode{
- struct rb_node list;
+struct uv_irq_2_mmr_pnode {
unsigned long offset;
int pnode;
- int irq;
};
-static DEFINE_SPINLOCK(uv_irq_lock);
-static struct rb_root uv_irq_root;
+static void uv_program_mmr(struct irq_cfg *cfg, struct uv_irq_2_mmr_pnode *info)
+{
+ unsigned long mmr_value;
+ struct uv_IO_APIC_route_entry *entry;
-static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool);
+ BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
+ sizeof(unsigned long));
+
+ mmr_value = 0;
+ entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
+ entry->vector = cfg->vector;
+ entry->delivery_mode = apic->irq_delivery_mode;
+ entry->dest_mode = apic->irq_dest_mode;
+ entry->polarity = 0;
+ entry->trigger = 0;
+ entry->mask = 0;
+ entry->dest = cfg->dest_apicid;
+
+ uv_write_global_mmr64(info->pnode, info->offset, mmr_value);
+}
static void uv_noop(struct irq_data *data) { }
@@ -37,6 +52,23 @@
ack_APIC_irq();
}
+static int
+uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
+ bool force)
+{
+ struct irq_data *parent = data->parent_data;
+ struct irq_cfg *cfg = irqd_cfg(data);
+ int ret;
+
+ ret = parent->chip->irq_set_affinity(parent, mask, force);
+ if (ret >= 0) {
+ uv_program_mmr(cfg, data->chip_data);
+ send_cleanup_vector(cfg);
+ }
+
+ return ret;
+}
+
static struct irq_chip uv_irq_chip = {
.name = "UV-CORE",
.irq_mask = uv_noop,
@@ -45,189 +77,99 @@
.irq_set_affinity = uv_set_irq_affinity,
};
-/*
- * Add offset and pnode information of the hub sourcing interrupts to the
- * rb tree for a specific irq.
- */
-static int uv_set_irq_2_mmr_info(int irq, unsigned long offset, unsigned blade)
+static int uv_domain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
{
- struct rb_node **link = &uv_irq_root.rb_node;
- struct rb_node *parent = NULL;
- struct uv_irq_2_mmr_pnode *n;
- struct uv_irq_2_mmr_pnode *e;
- unsigned long irqflags;
+ struct uv_irq_2_mmr_pnode *chip_data;
+ struct irq_alloc_info *info = arg;
+ struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+ int ret;
- n = kmalloc_node(sizeof(struct uv_irq_2_mmr_pnode), GFP_KERNEL,
- uv_blade_to_memory_nid(blade));
- if (!n)
+ if (nr_irqs > 1 || !info || info->type != X86_IRQ_ALLOC_TYPE_UV)
+ return -EINVAL;
+
+ chip_data = kmalloc_node(sizeof(*chip_data), GFP_KERNEL,
+ irq_data->node);
+ if (!chip_data)
return -ENOMEM;
- n->irq = irq;
- n->offset = offset;
- n->pnode = uv_blade_to_pnode(blade);
- spin_lock_irqsave(&uv_irq_lock, irqflags);
- /* Find the right place in the rbtree: */
- while (*link) {
- parent = *link;
- e = rb_entry(parent, struct uv_irq_2_mmr_pnode, list);
-
- if (unlikely(irq == e->irq)) {
- /* irq entry exists */
- e->pnode = uv_blade_to_pnode(blade);
- e->offset = offset;
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- kfree(n);
- return 0;
- }
-
- if (irq < e->irq)
- link = &(*link)->rb_left;
+ ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+ if (ret >= 0) {
+ if (info->uv_limit == UV_AFFINITY_CPU)
+ irq_set_status_flags(virq, IRQ_NO_BALANCING);
else
- link = &(*link)->rb_right;
+ irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
+
+ chip_data->pnode = uv_blade_to_pnode(info->uv_blade);
+ chip_data->offset = info->uv_offset;
+ irq_domain_set_info(domain, virq, virq, &uv_irq_chip, chip_data,
+ handle_percpu_irq, NULL, info->uv_name);
+ } else {
+ kfree(chip_data);
}
- /* Insert the node into the rbtree. */
- rb_link_node(&n->list, parent, link);
- rb_insert_color(&n->list, &uv_irq_root);
-
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- return 0;
+ return ret;
}
-/* Retrieve offset and pnode information from the rb tree for a specific irq */
-int uv_irq_2_mmr_info(int irq, unsigned long *offset, int *pnode)
+static void uv_domain_free(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs)
{
- struct uv_irq_2_mmr_pnode *e;
- struct rb_node *n;
- unsigned long irqflags;
+ struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
- spin_lock_irqsave(&uv_irq_lock, irqflags);
- n = uv_irq_root.rb_node;
- while (n) {
- e = rb_entry(n, struct uv_irq_2_mmr_pnode, list);
-
- if (e->irq == irq) {
- *offset = e->offset;
- *pnode = e->pnode;
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- return 0;
- }
-
- if (irq < e->irq)
- n = n->rb_left;
- else
- n = n->rb_right;
- }
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- return -1;
+ BUG_ON(nr_irqs != 1);
+ kfree(irq_data->chip_data);
+ irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT);
+ irq_clear_status_flags(virq, IRQ_NO_BALANCING);
+ irq_domain_free_irqs_top(domain, virq, nr_irqs);
}
/*
* Re-target the irq to the specified CPU and enable the specified MMR located
* on the specified blade to allow the sending of MSIs to the specified CPU.
*/
-static int
-arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
- unsigned long mmr_offset, int limit)
+static void uv_domain_activate(struct irq_domain *domain,
+ struct irq_data *irq_data)
{
- const struct cpumask *eligible_cpu = cpumask_of(cpu);
- struct irq_cfg *cfg = irq_cfg(irq);
- unsigned long mmr_value;
- struct uv_IO_APIC_route_entry *entry;
- int mmr_pnode, err;
- unsigned int dest;
-
- BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
- sizeof(unsigned long));
-
- err = assign_irq_vector(irq, cfg, eligible_cpu);
- if (err != 0)
- return err;
-
- err = apic->cpu_mask_to_apicid_and(eligible_cpu, eligible_cpu, &dest);
- if (err != 0)
- return err;
-
- if (limit == UV_AFFINITY_CPU)
- irq_set_status_flags(irq, IRQ_NO_BALANCING);
- else
- irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-
- irq_set_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
- irq_name);
-
- mmr_value = 0;
- entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
- entry->vector = cfg->vector;
- entry->delivery_mode = apic->irq_delivery_mode;
- entry->dest_mode = apic->irq_dest_mode;
- entry->polarity = 0;
- entry->trigger = 0;
- entry->mask = 0;
- entry->dest = dest;
-
- mmr_pnode = uv_blade_to_pnode(mmr_blade);
- uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
-
- if (cfg->move_in_progress)
- send_cleanup_vector(cfg);
-
- return irq;
+ uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data);
}
/*
* Disable the specified MMR located on the specified blade so that MSIs are
* longer allowed to be sent.
*/
-static void arch_disable_uv_irq(int mmr_pnode, unsigned long mmr_offset)
+static void uv_domain_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data)
{
unsigned long mmr_value;
struct uv_IO_APIC_route_entry *entry;
- BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
- sizeof(unsigned long));
-
mmr_value = 0;
entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
entry->mask = 1;
-
- uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
+ uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data);
}
-static int
-uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
+static const struct irq_domain_ops uv_domain_ops = {
+ .alloc = uv_domain_alloc,
+ .free = uv_domain_free,
+ .activate = uv_domain_activate,
+ .deactivate = uv_domain_deactivate,
+};
+
+static struct irq_domain *uv_get_irq_domain(void)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- unsigned int dest;
- unsigned long mmr_value, mmr_offset;
- struct uv_IO_APIC_route_entry *entry;
- int mmr_pnode;
+ static struct irq_domain *uv_domain;
+ static DEFINE_MUTEX(uv_lock);
- if (apic_set_affinity(data, mask, &dest))
- return -1;
+ mutex_lock(&uv_lock);
+ if (uv_domain == NULL) {
+ uv_domain = irq_domain_add_tree(NULL, &uv_domain_ops, NULL);
+ if (uv_domain)
+ uv_domain->parent = x86_vector_domain;
+ }
+ mutex_unlock(&uv_lock);
- mmr_value = 0;
- entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
-
- entry->vector = cfg->vector;
- entry->delivery_mode = apic->irq_delivery_mode;
- entry->dest_mode = apic->irq_dest_mode;
- entry->polarity = 0;
- entry->trigger = 0;
- entry->mask = 0;
- entry->dest = dest;
-
- /* Get previously stored MMR and pnode of hub sourcing interrupts */
- if (uv_irq_2_mmr_info(data->irq, &mmr_offset, &mmr_pnode))
- return -1;
-
- uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
-
- if (cfg->move_in_progress)
- send_cleanup_vector(cfg);
-
- return IRQ_SET_MASK_OK_NOCOPY;
+ return uv_domain;
}
/*
@@ -238,19 +180,21 @@
int uv_setup_irq(char *irq_name, int cpu, int mmr_blade,
unsigned long mmr_offset, int limit)
{
- int ret, irq = irq_alloc_hwirq(uv_blade_to_memory_nid(mmr_blade));
+ struct irq_alloc_info info;
+ struct irq_domain *domain = uv_get_irq_domain();
- if (!irq)
- return -EBUSY;
+ if (!domain)
+ return -ENOMEM;
- ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset,
- limit);
- if (ret == irq)
- uv_set_irq_2_mmr_info(irq, mmr_offset, mmr_blade);
- else
- irq_free_hwirq(irq);
+ init_irq_alloc_info(&info, cpumask_of(cpu));
+ info.type = X86_IRQ_ALLOC_TYPE_UV;
+ info.uv_limit = limit;
+ info.uv_blade = mmr_blade;
+ info.uv_offset = mmr_offset;
+ info.uv_name = irq_name;
- return ret;
+ return irq_domain_alloc_irqs(domain, 1,
+ uv_blade_to_memory_nid(mmr_blade), &info);
}
EXPORT_SYMBOL_GPL(uv_setup_irq);
@@ -263,26 +207,6 @@
*/
void uv_teardown_irq(unsigned int irq)
{
- struct uv_irq_2_mmr_pnode *e;
- struct rb_node *n;
- unsigned long irqflags;
-
- spin_lock_irqsave(&uv_irq_lock, irqflags);
- n = uv_irq_root.rb_node;
- while (n) {
- e = rb_entry(n, struct uv_irq_2_mmr_pnode, list);
- if (e->irq == irq) {
- arch_disable_uv_irq(e->pnode, e->offset);
- rb_erase(n, &uv_irq_root);
- kfree(e);
- break;
- }
- if (irq < e->irq)
- n = n->rb_left;
- else
- n = n->rb_right;
- }
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- irq_free_hwirq(irq);
+ irq_domain_free_irqs(irq, 1);
}
EXPORT_SYMBOL_GPL(uv_teardown_irq);
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 3c4469a..e2386cb 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -78,9 +78,9 @@
/* code below has been relocated to a safe page */
ENTRY(core_restore_code)
-loop:
+.Lloop:
testq %rdx, %rdx
- jz done
+ jz .Ldone
/* get addresses from the pbe and copy the page */
movq pbe_address(%rdx), %rsi
@@ -91,8 +91,8 @@
/* progress to the next pbe */
movq pbe_next(%rdx), %rdx
- jmp loop
-done:
+ jmp .Lloop
+.Ldone:
/* jump to the restore_registers address from the image header */
jmpq *%rax
/*
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
index acb384d..a8fecc2 100644
--- a/arch/x86/um/Makefile
+++ b/arch/x86/um/Makefile
@@ -26,7 +26,7 @@
obj-y += syscalls_64.o vdso/
-subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../lib/thunk_64.o \
+subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o \
../lib/rwsem.o
endif
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index 7e8a1a6..b9531d3 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -39,7 +39,8 @@
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
+
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0)
#define read_barrier_depends() do { } while (0)
#define smp_read_barrier_depends() do { } while (0)
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 53233a9..a8f57a9 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1181,10 +1181,11 @@
.read_tscp = native_read_tscp,
.iret = xen_iret,
- .irq_enable_sysexit = xen_sysexit,
#ifdef CONFIG_X86_64
.usergs_sysret32 = xen_sysret32,
.usergs_sysret64 = xen_sysret64,
+#else
+ .irq_enable_sysexit = xen_sysexit,
#endif
.load_tr_desc = paravirt_nop,
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 956374c..9e2ba5c 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -17,6 +17,56 @@
#include "xen-ops.h"
#include "debugfs.h"
+static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
+static DEFINE_PER_CPU(char *, irq_name);
+static bool xen_pvspin = true;
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+#include <asm/qspinlock.h>
+
+static void xen_qlock_kick(int cpu)
+{
+ xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
+}
+
+/*
+ * Halt the current CPU & release it back to the host
+ */
+static void xen_qlock_wait(u8 *byte, u8 val)
+{
+ int irq = __this_cpu_read(lock_kicker_irq);
+
+ /* If kicker interrupts not initialized yet, just spin */
+ if (irq == -1)
+ return;
+
+ /* clear pending */
+ xen_clear_irq_pending(irq);
+ barrier();
+
+ /*
+ * We check the byte value after clearing pending IRQ to make sure
+ * that we won't miss a wakeup event because of the clearing.
+ *
+ * The sync_clear_bit() call in xen_clear_irq_pending() is atomic.
+ * So it is effectively a memory barrier for x86.
+ */
+ if (READ_ONCE(*byte) != val)
+ return;
+
+ /*
+ * If an interrupt happens here, it will leave the wakeup irq
+ * pending, which will cause xen_poll_irq() to return
+ * immediately.
+ */
+
+ /* Block until irq becomes pending (or perhaps a spurious wakeup) */
+ xen_poll_irq(irq);
+}
+
+#else /* CONFIG_QUEUED_SPINLOCKS */
+
enum xen_contention_stat {
TAKEN_SLOW,
TAKEN_SLOW_PICKUP,
@@ -100,12 +150,9 @@
__ticket_t want;
};
-static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
-static DEFINE_PER_CPU(char *, irq_name);
static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting);
static cpumask_t waiting_cpus;
-static bool xen_pvspin = true;
__visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
{
int irq = __this_cpu_read(lock_kicker_irq);
@@ -217,6 +264,7 @@
}
}
}
+#endif /* CONFIG_QUEUED_SPINLOCKS */
static irqreturn_t dummy_handler(int irq, void *dev_id)
{
@@ -280,8 +328,16 @@
return;
}
printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
+#ifdef CONFIG_QUEUED_SPINLOCKS
+ __pv_init_lock_hash();
+ pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+ pv_lock_ops.wait = xen_qlock_wait;
+ pv_lock_ops.kick = xen_qlock_kick;
+#else
pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
pv_lock_ops.unlock_kick = xen_unlock_kick;
+#endif
}
/*
@@ -310,7 +366,7 @@
}
early_param("xen_nopvspin", xen_parse_nopvspin);
-#ifdef CONFIG_XEN_DEBUG_FS
+#if defined(CONFIG_XEN_DEBUG_FS) && !defined(CONFIG_QUEUED_SPINLOCKS)
static struct dentry *d_spin_debug;
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 985fc3e..f22667a 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -15,6 +15,8 @@
#include <asm/percpu.h>
#include <asm/processor-flags.h>
#include <asm/segment.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
#include <xen/interface/xen.h>
@@ -47,29 +49,13 @@
ENDPATCH(xen_iret)
RELOC(xen_iret, 1b+1)
-/*
- * sysexit is not used for 64-bit processes, so it's only ever used to
- * return to 32-bit compat userspace.
- */
-ENTRY(xen_sysexit)
- pushq $__USER32_DS
- pushq %rcx
- pushq $X86_EFLAGS_IF
- pushq $__USER32_CS
- pushq %rdx
-
- pushq $0
-1: jmp hypercall_iret
-ENDPATCH(xen_sysexit)
-RELOC(xen_sysexit, 1b+1)
-
ENTRY(xen_sysret64)
/*
* We're already on the usermode stack at this point, but
* still with the kernel gs, so we can easily switch back
*/
movq %rsp, PER_CPU_VAR(rsp_scratch)
- movq PER_CPU_VAR(kernel_stack), %rsp
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
pushq $__USER_DS
pushq PER_CPU_VAR(rsp_scratch)
@@ -88,7 +74,7 @@
* still with the kernel gs, so we can easily switch back
*/
movq %rsp, PER_CPU_VAR(rsp_scratch)
- movq PER_CPU_VAR(kernel_stack), %rsp
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
pushq $__USER32_DS
pushq PER_CPU_VAR(rsp_scratch)
@@ -128,7 +114,7 @@
/* Normal 64-bit system call target */
ENTRY(xen_syscall_target)
undo_xen_syscall
- jmp system_call_after_swapgs
+ jmp entry_SYSCALL_64_after_swapgs
ENDPROC(xen_syscall_target)
#ifdef CONFIG_IA32_EMULATION
@@ -136,13 +122,13 @@
/* 32-bit compat syscall target */
ENTRY(xen_syscall32_target)
undo_xen_syscall
- jmp ia32_cstar_target
+ jmp entry_SYSCALL_compat
ENDPROC(xen_syscall32_target)
/* 32-bit compat sysenter target */
ENTRY(xen_sysenter_target)
undo_xen_syscall
- jmp ia32_sysenter_target
+ jmp entry_SYSENTER_compat
ENDPROC(xen_sysenter_target)
#else /* !CONFIG_IA32_EMULATION */
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 9e195c6..c20fe29 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -134,7 +134,9 @@
/* These are not functions, and cannot be called normally */
__visible void xen_iret(void);
+#ifdef CONFIG_X86_32
__visible void xen_sysexit(void);
+#endif
__visible void xen_sysret32(void);
__visible void xen_sysret64(void);
__visible void xen_adjust_exception_frame(void);
diff --git a/arch/xtensa/include/asm/dma-mapping.h b/arch/xtensa/include/asm/dma-mapping.h
index 172a02a..ba78ccf 100644
--- a/arch/xtensa/include/asm/dma-mapping.h
+++ b/arch/xtensa/include/asm/dma-mapping.h
@@ -185,4 +185,17 @@
return -EINVAL;
}
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flag,
+ struct dma_attrs *attrs)
+{
+ return NULL;
+}
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
+{
+}
+
#endif /* _XTENSA_DMA_MAPPING_H */
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 8aaf298..362905e 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1512,15 +1512,6 @@
This option enables the user-spaces interface for random
number generator algorithms.
-config CRYPTO_USER_API_AEAD
- tristate "User-space interface for AEAD cipher algorithms"
- depends on NET
- select CRYPTO_AEAD
- select CRYPTO_USER_API
- help
- This option enables the user-spaces interface for AEAD
- cipher algorithms.
-
config CRYPTO_HASH_INFO
bool
diff --git a/drivers/bus/mips_cdmm.c b/drivers/bus/mips_cdmm.c
index 5bd792c..ab3bde1 100644
--- a/drivers/bus/mips_cdmm.c
+++ b/drivers/bus/mips_cdmm.c
@@ -453,7 +453,7 @@
/* Look for a specific device type */
for (; drb < bus->drbs; drb += size + 1) {
- acsr = readl(cdmm + drb * CDMM_DRB_SIZE);
+ acsr = __raw_readl(cdmm + drb * CDMM_DRB_SIZE);
type = (acsr & CDMM_ACSR_DEVTYPE) >> CDMM_ACSR_DEVTYPE_SHIFT;
if (type == dev_type)
return cdmm + drb * CDMM_DRB_SIZE;
@@ -500,7 +500,7 @@
bus->discovered = true;
pr_info("cdmm%u discovery (%u blocks)\n", cpu, bus->drbs);
for (; drb < bus->drbs; drb += size + 1) {
- acsr = readl(cdmm + drb * CDMM_DRB_SIZE);
+ acsr = __raw_readl(cdmm + drb * CDMM_DRB_SIZE);
type = (acsr & CDMM_ACSR_DEVTYPE) >> CDMM_ACSR_DEVTYPE_SHIFT;
size = (acsr & CDMM_ACSR_DEVSIZE) >> CDMM_ACSR_DEVSIZE_SHIFT;
rev = (acsr & CDMM_ACSR_DEVREV) >> CDMM_ACSR_DEVREV_SHIFT;
diff --git a/drivers/gpio/gpio-kempld.c b/drivers/gpio/gpio-kempld.c
index 6b8115f..83f281d 100644
--- a/drivers/gpio/gpio-kempld.c
+++ b/drivers/gpio/gpio-kempld.c
@@ -117,7 +117,7 @@
= container_of(chip, struct kempld_gpio_data, chip);
struct kempld_device_data *pld = gpio->pld;
- return kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset);
+ return !kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset);
}
static int kempld_gpio_pincount(struct kempld_device_data *pld)
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 59eaa23..6bc612b 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -53,6 +53,11 @@
static LIST_HEAD(gpio_lookup_list);
LIST_HEAD(gpio_chips);
+
+static void gpiochip_free_hogs(struct gpio_chip *chip);
+static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip);
+
+
static inline void desc_set_label(struct gpio_desc *d, const char *label)
{
d->label = label;
@@ -297,6 +302,7 @@
err_remove_chip:
acpi_gpiochip_remove(chip);
+ gpiochip_free_hogs(chip);
of_gpiochip_remove(chip);
spin_lock_irqsave(&gpio_lock, flags);
list_del(&chip->list);
@@ -313,10 +319,6 @@
}
EXPORT_SYMBOL_GPL(gpiochip_add);
-/* Forward-declaration */
-static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip);
-static void gpiochip_free_hogs(struct gpio_chip *chip);
-
/**
* gpiochip_remove() - unregister a gpio_chip
* @chip: the chip to unregister
diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c
index 40c1db9..2f0ed11 100644
--- a/drivers/gpu/drm/drm_plane_helper.c
+++ b/drivers/gpu/drm/drm_plane_helper.c
@@ -465,6 +465,9 @@
if (!crtc[i])
continue;
+ if (crtc[i]->cursor == plane)
+ continue;
+
/* There's no other way to figure out whether the crtc is running. */
ret = drm_crtc_vblank_get(crtc[i]);
if (ret == 0) {
diff --git a/drivers/gpu/drm/nouveau/include/nvif/class.h b/drivers/gpu/drm/nouveau/include/nvif/class.h
index 0b5af0f..64f8b2f 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/class.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/class.h
@@ -14,7 +14,7 @@
#define FERMI_TWOD_A 0x0000902d
-#define FERMI_MEMORY_TO_MEMORY_FORMAT_A 0x0000903d
+#define FERMI_MEMORY_TO_MEMORY_FORMAT_A 0x00009039
#define KEPLER_INLINE_TO_MEMORY_A 0x0000a040
#define KEPLER_INLINE_TO_MEMORY_B 0x0000a140
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c
index 2f5eadd..fdb1dcf 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c
@@ -329,7 +329,6 @@
nv_mask(priv, 0x419cc0, 0x00000008, 0x00000008);
for (gpc = 0; gpc < priv->gpc_nr; gpc++) {
- printk(KERN_ERR "ppc %d %d\n", gpc, priv->ppc_nr[gpc]);
for (ppc = 0; ppc < priv->ppc_nr[gpc]; ppc++)
nv_wr32(priv, PPC_UNIT(gpc, ppc, 0x038), 0xc0000000);
nv_wr32(priv, GPC_UNIT(gpc, 0x0420), 0xc0000000);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c
index e8778c6..c61102f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c
@@ -90,12 +90,14 @@
return disable;
}
-static int
+int
gf100_devinit_ctor(struct nvkm_object *parent, struct nvkm_object *engine,
struct nvkm_oclass *oclass, void *data, u32 size,
struct nvkm_object **pobject)
{
+ struct nvkm_devinit_impl *impl = (void *)oclass;
struct nv50_devinit_priv *priv;
+ u64 disable;
int ret;
ret = nvkm_devinit_create(parent, engine, oclass, &priv);
@@ -103,7 +105,8 @@
if (ret)
return ret;
- if (nv_rd32(priv, 0x022500) & 0x00000001)
+ disable = impl->disable(&priv->base);
+ if (disable & (1ULL << NVDEV_ENGINE_DISP))
priv->base.post = true;
return 0;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
index b345a53..87ca0ec 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
@@ -48,7 +48,7 @@
gm107_devinit_oclass = &(struct nvkm_devinit_impl) {
.base.handle = NV_SUBDEV(DEVINIT, 0x07),
.base.ofuncs = &(struct nvkm_ofuncs) {
- .ctor = nv50_devinit_ctor,
+ .ctor = gf100_devinit_ctor,
.dtor = _nvkm_devinit_dtor,
.init = nv50_devinit_init,
.fini = _nvkm_devinit_fini,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c
index 535172c..1076fcf 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c
@@ -161,7 +161,7 @@
gm204_devinit_oclass = &(struct nvkm_devinit_impl) {
.base.handle = NV_SUBDEV(DEVINIT, 0x07),
.base.ofuncs = &(struct nvkm_ofuncs) {
- .ctor = nv50_devinit_ctor,
+ .ctor = gf100_devinit_ctor,
.dtor = _nvkm_devinit_dtor,
.init = nv50_devinit_init,
.fini = _nvkm_devinit_fini,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h
index b882b65..9243521c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h
@@ -15,6 +15,9 @@
int gt215_devinit_pll_set(struct nvkm_devinit *, u32, u32);
+int gf100_devinit_ctor(struct nvkm_object *, struct nvkm_object *,
+ struct nvkm_oclass *, void *, u32,
+ struct nvkm_object **);
int gf100_devinit_pll_set(struct nvkm_devinit *, u32, u32);
u64 gm107_devinit_disable(struct nvkm_devinit *);
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 42b2ea3..e597ffc 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1798,7 +1798,9 @@
if ((crtc->mode.clock == test_crtc->mode.clock) &&
(adjusted_clock == test_adjusted_clock) &&
(radeon_crtc->ss_enabled == test_radeon_crtc->ss_enabled) &&
- (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID))
+ (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID) &&
+ (drm_detect_monitor_audio(radeon_connector_edid(test_radeon_crtc->connector)) ==
+ drm_detect_monitor_audio(radeon_connector_edid(radeon_crtc->connector))))
return test_radeon_crtc->pll_id;
}
}
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index a0c35bb..ba50f3c 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -5822,7 +5822,7 @@
L2_CACHE_BIGK_FRAGMENT_SIZE(4));
/* setup context0 */
WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
- WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1);
+ WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12);
WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12);
WREG32(VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
(u32)(rdev->dummy_page.addr >> 12));
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 05e6d6e..f848acf 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2485,7 +2485,7 @@
WREG32(MC_VM_MB_L1_TLB2_CNTL, tmp);
WREG32(MC_VM_MB_L1_TLB3_CNTL, tmp);
WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
- WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1);
+ WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12);
WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12);
WREG32(VM_CONTEXT0_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(0) |
RANGE_PROTECTION_FAULT_ENABLE_DEFAULT);
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index 0926739..9953356 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -400,7 +400,7 @@
if (enable) {
struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
- if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+ if (connector && drm_detect_monitor_audio(radeon_connector_edid(connector))) {
WREG32(HDMI_INFOFRAME_CONTROL0 + dig->afmt->offset,
HDMI_AVI_INFO_SEND | /* enable AVI info frames */
HDMI_AVI_INFO_CONT | /* required for audio info values to be updated */
@@ -438,7 +438,8 @@
if (!dig || !dig->afmt)
return;
- if (enable && drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+ if (enable && connector &&
+ drm_detect_monitor_audio(radeon_connector_edid(connector))) {
struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
struct radeon_connector *radeon_connector = to_radeon_connector(connector);
struct radeon_connector_atom_dig *dig_connector;
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index aba2f42..64d3a77 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1282,7 +1282,7 @@
L2_CACHE_BIGK_FRAGMENT_SIZE(6));
/* setup context0 */
WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
- WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1);
+ WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12);
WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12);
WREG32(VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
(u32)(rdev->dummy_page.addr >> 12));
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 25b4ac9..8f6d862 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1112,7 +1112,7 @@
WREG32(MC_VM_L1_TLB_MCB_RD_SEM_CNTL, tmp | ENABLE_SEMAPHORE_MODE);
WREG32(MC_VM_L1_TLB_MCB_WR_SEM_CNTL, tmp | ENABLE_SEMAPHORE_MODE);
WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
- WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1);
+ WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12);
WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12);
WREG32(VM_CONTEXT0_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(0) |
RANGE_PROTECTION_FAULT_ENABLE_DEFAULT);
diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c
index dcb7796..25191f1 100644
--- a/drivers/gpu/drm/radeon/radeon_audio.c
+++ b/drivers/gpu/drm/radeon/radeon_audio.c
@@ -460,9 +460,6 @@
if (!connector || !connector->encoder)
return;
- if (!radeon_encoder_is_digital(connector->encoder))
- return;
-
rdev = connector->encoder->dev->dev_private;
if (!radeon_audio_chipset_supported(rdev))
@@ -471,26 +468,26 @@
radeon_encoder = to_radeon_encoder(connector->encoder);
dig = radeon_encoder->enc_priv;
- if (!dig->afmt)
- return;
-
if (status == connector_status_connected) {
- struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+ struct radeon_connector *radeon_connector;
+ int sink_type;
+
+ if (!drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+ radeon_encoder->audio = NULL;
+ return;
+ }
+
+ radeon_connector = to_radeon_connector(connector);
+ sink_type = radeon_dp_getsinktype(radeon_connector);
if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort &&
- radeon_dp_getsinktype(radeon_connector) ==
- CONNECTOR_OBJECT_ID_DISPLAYPORT)
+ sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT)
radeon_encoder->audio = rdev->audio.dp_funcs;
else
radeon_encoder->audio = rdev->audio.hdmi_funcs;
dig->afmt->pin = radeon_audio_get_pin(connector->encoder);
- if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
- radeon_audio_enable(rdev, dig->afmt->pin, 0xf);
- } else {
- radeon_audio_enable(rdev, dig->afmt->pin, 0);
- dig->afmt->pin = NULL;
- }
+ radeon_audio_enable(rdev, dig->afmt->pin, 0xf);
} else {
radeon_audio_enable(rdev, dig->afmt->pin, 0);
dig->afmt->pin = NULL;
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index d17d251..cebb65e 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1379,10 +1379,8 @@
/* updated in get modes as well since we need to know if it's analog or digital */
radeon_connector_update_scratch_regs(connector, ret);
- if (radeon_audio != 0) {
- radeon_connector_get_edid(connector);
+ if (radeon_audio != 0)
radeon_audio_detect(connector, ret);
- }
exit:
pm_runtime_mark_last_busy(connector->dev->dev);
@@ -1719,10 +1717,8 @@
radeon_connector_update_scratch_regs(connector, ret);
- if (radeon_audio != 0) {
- radeon_connector_get_edid(connector);
+ if (radeon_audio != 0)
radeon_audio_detect(connector, ret);
- }
out:
pm_runtime_mark_last_busy(connector->dev->dev);
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index c54d631..01ee96a 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -921,7 +921,7 @@
WREG32(MC_VM_MB_L1_TLB2_CNTL, tmp);
WREG32(MC_VM_MB_L1_TLB3_CNTL, tmp);
WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
- WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1);
+ WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12);
WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12);
WREG32(VM_CONTEXT0_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(0) |
RANGE_PROTECTION_FAULT_ENABLE_DEFAULT);
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 5326f75..4c679b8 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -4303,7 +4303,7 @@
L2_CACHE_BIGK_FRAGMENT_SIZE(4));
/* setup context0 */
WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
- WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1);
+ WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12);
WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12);
WREG32(VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
(u32)(rdev->dummy_page.addr >> 12));
diff --git a/drivers/gpu/drm/vgem/Makefile b/drivers/gpu/drm/vgem/Makefile
index 1055cb7..3f4c7b8 100644
--- a/drivers/gpu/drm/vgem/Makefile
+++ b/drivers/gpu/drm/vgem/Makefile
@@ -1,4 +1,4 @@
ccflags-y := -Iinclude/drm
-vgem-y := vgem_drv.o vgem_dma_buf.o
+vgem-y := vgem_drv.o
obj-$(CONFIG_DRM_VGEM) += vgem.o
diff --git a/drivers/gpu/drm/vgem/vgem_dma_buf.c b/drivers/gpu/drm/vgem/vgem_dma_buf.c
deleted file mode 100644
index 0254438..0000000
--- a/drivers/gpu/drm/vgem/vgem_dma_buf.c
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * Copyright © 2012 Intel Corporation
- * Copyright © 2014 The Chromium OS Authors
- *
- * 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 (including the next
- * paragraph) 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.
- *
- * Authors:
- * Ben Widawsky <ben@bwidawsk.net>
- *
- */
-
-#include <linux/dma-buf.h>
-#include "vgem_drv.h"
-
-struct sg_table *vgem_gem_prime_get_sg_table(struct drm_gem_object *gobj)
-{
- struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
- BUG_ON(obj->pages == NULL);
-
- return drm_prime_pages_to_sg(obj->pages, obj->base.size / PAGE_SIZE);
-}
-
-int vgem_gem_prime_pin(struct drm_gem_object *gobj)
-{
- struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
- return vgem_gem_get_pages(obj);
-}
-
-void vgem_gem_prime_unpin(struct drm_gem_object *gobj)
-{
- struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
- vgem_gem_put_pages(obj);
-}
-
-void *vgem_gem_prime_vmap(struct drm_gem_object *gobj)
-{
- struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
- BUG_ON(obj->pages == NULL);
-
- return vmap(obj->pages, obj->base.size / PAGE_SIZE, 0, PAGE_KERNEL);
-}
-
-void vgem_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
-{
- vunmap(vaddr);
-}
-
-struct drm_gem_object *vgem_gem_prime_import(struct drm_device *dev,
- struct dma_buf *dma_buf)
-{
- struct drm_vgem_gem_object *obj = NULL;
- int ret;
-
- obj = kzalloc(sizeof(*obj), GFP_KERNEL);
- if (obj == NULL) {
- ret = -ENOMEM;
- goto fail;
- }
-
- ret = drm_gem_object_init(dev, &obj->base, dma_buf->size);
- if (ret) {
- ret = -ENOMEM;
- goto fail_free;
- }
-
- get_dma_buf(dma_buf);
-
- obj->base.dma_buf = dma_buf;
- obj->use_dma_buf = true;
-
- return &obj->base;
-
-fail_free:
- kfree(obj);
-fail:
- return ERR_PTR(ret);
-}
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index cb3b435..7a207ca 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -302,22 +302,13 @@
};
static struct drm_driver vgem_driver = {
- .driver_features = DRIVER_GEM | DRIVER_PRIME,
+ .driver_features = DRIVER_GEM,
.gem_free_object = vgem_gem_free_object,
.gem_vm_ops = &vgem_gem_vm_ops,
.ioctls = vgem_ioctls,
.fops = &vgem_driver_fops,
.dumb_create = vgem_gem_dumb_create,
.dumb_map_offset = vgem_gem_dumb_map,
- .prime_handle_to_fd = drm_gem_prime_handle_to_fd,
- .prime_fd_to_handle = drm_gem_prime_fd_to_handle,
- .gem_prime_export = drm_gem_prime_export,
- .gem_prime_import = vgem_gem_prime_import,
- .gem_prime_pin = vgem_gem_prime_pin,
- .gem_prime_unpin = vgem_gem_prime_unpin,
- .gem_prime_get_sg_table = vgem_gem_prime_get_sg_table,
- .gem_prime_vmap = vgem_gem_prime_vmap,
- .gem_prime_vunmap = vgem_gem_prime_vunmap,
.name = DRIVER_NAME,
.desc = DRIVER_DESC,
.date = DRIVER_DATE,
diff --git a/drivers/gpu/drm/vgem/vgem_drv.h b/drivers/gpu/drm/vgem/vgem_drv.h
index 57ab4d8..e9f92f7 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.h
+++ b/drivers/gpu/drm/vgem/vgem_drv.h
@@ -43,15 +43,4 @@
extern void vgem_gem_put_pages(struct drm_vgem_gem_object *obj);
extern int vgem_gem_get_pages(struct drm_vgem_gem_object *obj);
-/* vgem_dma_buf.c */
-extern struct sg_table *vgem_gem_prime_get_sg_table(
- struct drm_gem_object *gobj);
-extern int vgem_gem_prime_pin(struct drm_gem_object *gobj);
-extern void vgem_gem_prime_unpin(struct drm_gem_object *gobj);
-extern void *vgem_gem_prime_vmap(struct drm_gem_object *gobj);
-extern void vgem_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
-extern struct drm_gem_object *vgem_gem_prime_import(struct drm_device *dev,
- struct dma_buf *dma_buf);
-
-
#endif
diff --git a/drivers/hwmon/nct6683.c b/drivers/hwmon/nct6683.c
index f3830db..37f0170 100644
--- a/drivers/hwmon/nct6683.c
+++ b/drivers/hwmon/nct6683.c
@@ -439,6 +439,7 @@
(*t)->dev_attr.attr.name, tg->base + i);
if ((*t)->s2) {
a2 = &su->u.a2;
+ sysfs_attr_init(&a2->dev_attr.attr);
a2->dev_attr.attr.name = su->name;
a2->nr = (*t)->u.s.nr + i;
a2->index = (*t)->u.s.index;
@@ -449,6 +450,7 @@
*attrs = &a2->dev_attr.attr;
} else {
a = &su->u.a1;
+ sysfs_attr_init(&a->dev_attr.attr);
a->dev_attr.attr.name = su->name;
a->index = (*t)->u.index + i;
a->dev_attr.attr.mode =
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index 4fcb481..bd1c99d 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -995,6 +995,7 @@
(*t)->dev_attr.attr.name, tg->base + i);
if ((*t)->s2) {
a2 = &su->u.a2;
+ sysfs_attr_init(&a2->dev_attr.attr);
a2->dev_attr.attr.name = su->name;
a2->nr = (*t)->u.s.nr + i;
a2->index = (*t)->u.s.index;
@@ -1005,6 +1006,7 @@
*attrs = &a2->dev_attr.attr;
} else {
a = &su->u.a1;
+ sysfs_attr_init(&a->dev_attr.attr);
a->dev_attr.attr.name = su->name;
a->index = (*t)->u.index + i;
a->dev_attr.attr.mode =
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index 112e4d4..68800115 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -239,8 +239,10 @@
ntc_thermistor_parse_dt(struct platform_device *pdev)
{
struct iio_channel *chan;
+ enum iio_chan_type type;
struct device_node *np = pdev->dev.of_node;
struct ntc_thermistor_platform_data *pdata;
+ int ret;
if (!np)
return NULL;
@@ -253,6 +255,13 @@
if (IS_ERR(chan))
return ERR_CAST(chan);
+ ret = iio_get_channel_type(chan, &type);
+ if (ret < 0)
+ return ERR_PTR(ret);
+
+ if (type != IIO_VOLTAGE)
+ return ERR_PTR(-EINVAL);
+
if (of_property_read_u32(np, "pullup-uv", &pdata->pullup_uv))
return ERR_PTR(-ENODEV);
if (of_property_read_u32(np, "pullup-ohm", &pdata->pullup_ohm))
diff --git a/drivers/hwmon/tmp401.c b/drivers/hwmon/tmp401.c
index 99664eb..ccf4cff 100644
--- a/drivers/hwmon/tmp401.c
+++ b/drivers/hwmon/tmp401.c
@@ -44,7 +44,7 @@
#include <linux/sysfs.h>
/* Addresses to scan */
-static const unsigned short normal_i2c[] = { 0x37, 0x48, 0x49, 0x4a, 0x4c, 0x4d,
+static const unsigned short normal_i2c[] = { 0x48, 0x49, 0x4a, 0x4c, 0x4d,
0x4e, 0x4f, I2C_CLIENT_END };
enum chips { tmp401, tmp411, tmp431, tmp432, tmp435 };
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 327529e..3f40319 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -547,11 +547,11 @@
return 0;
err_prot_mr:
- ib_dereg_mr(desc->pi_ctx->prot_mr);
+ ib_dereg_mr(pi_ctx->prot_mr);
err_prot_frpl:
- ib_free_fast_reg_page_list(desc->pi_ctx->prot_frpl);
+ ib_free_fast_reg_page_list(pi_ctx->prot_frpl);
err_pi_ctx:
- kfree(desc->pi_ctx);
+ kfree(pi_ctx);
return ret;
}
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index e43d489..cbe8c1f 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -34,6 +34,7 @@
#include <linux/irq.h>
#include <linux/msi.h>
#include <linux/dma-contiguous.h>
+#include <linux/irqdomain.h>
#include <asm/irq_remapping.h>
#include <asm/io_apic.h>
#include <asm/apic.h>
@@ -3851,6 +3852,21 @@
} fields;
};
+struct irq_2_irte {
+ u16 devid; /* Device ID for IRTE table */
+ u16 index; /* Index into IRTE table*/
+};
+
+struct amd_ir_data {
+ struct irq_2_irte irq_2_irte;
+ union irte irte_entry;
+ union {
+ struct msi_msg msi_entry;
+ };
+};
+
+static struct irq_chip amd_ir_chip;
+
#define DTE_IRQ_PHYS_ADDR_MASK (((1ULL << 45)-1) << 6)
#define DTE_IRQ_REMAP_INTCTL (2ULL << 60)
#define DTE_IRQ_TABLE_LEN (8ULL << 1)
@@ -3944,7 +3960,7 @@
return table;
}
-static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count)
+static int alloc_irq_index(u16 devid, int count)
{
struct irq_remap_table *table;
unsigned long flags;
@@ -3966,18 +3982,10 @@
c = 0;
if (c == count) {
- struct irq_2_irte *irte_info;
-
for (; c != 0; --c)
table->table[index - c + 1] = IRTE_ALLOCATED;
index -= count - 1;
-
- cfg->remapped = 1;
- irte_info = &cfg->irq_2_irte;
- irte_info->devid = devid;
- irte_info->index = index;
-
goto out;
}
}
@@ -3990,22 +3998,6 @@
return index;
}
-static int get_irte(u16 devid, int index, union irte *irte)
-{
- struct irq_remap_table *table;
- unsigned long flags;
-
- table = get_irq_table(devid, false);
- if (!table)
- return -ENOMEM;
-
- spin_lock_irqsave(&table->lock, flags);
- irte->val = table->table[index];
- spin_unlock_irqrestore(&table->lock, flags);
-
- return 0;
-}
-
static int modify_irte(u16 devid, int index, union irte irte)
{
struct irq_remap_table *table;
@@ -4052,229 +4044,70 @@
iommu_completion_wait(iommu);
}
-static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
- unsigned int destination, int vector,
- struct io_apic_irq_attr *attr)
+static int get_devid(struct irq_alloc_info *info)
{
- struct irq_remap_table *table;
- struct irq_2_irte *irte_info;
- struct irq_cfg *cfg;
- union irte irte;
- int ioapic_id;
- int index;
- int devid;
- int ret;
+ int devid = -1;
- cfg = irq_cfg(irq);
- if (!cfg)
- return -EINVAL;
-
- irte_info = &cfg->irq_2_irte;
- ioapic_id = mpc_ioapic_id(attr->ioapic);
- devid = get_ioapic_devid(ioapic_id);
-
- if (devid < 0)
- return devid;
-
- table = get_irq_table(devid, true);
- if (table == NULL)
- return -ENOMEM;
-
- index = attr->ioapic_pin;
-
- /* Setup IRQ remapping info */
- cfg->remapped = 1;
- irte_info->devid = devid;
- irte_info->index = index;
-
- /* Setup IRTE for IOMMU */
- irte.val = 0;
- irte.fields.vector = vector;
- irte.fields.int_type = apic->irq_delivery_mode;
- irte.fields.destination = destination;
- irte.fields.dm = apic->irq_dest_mode;
- irte.fields.valid = 1;
-
- ret = modify_irte(devid, index, irte);
- if (ret)
- return ret;
-
- /* Setup IOAPIC entry */
- memset(entry, 0, sizeof(*entry));
-
- entry->vector = index;
- entry->mask = 0;
- entry->trigger = attr->trigger;
- entry->polarity = attr->polarity;
-
- /*
- * Mask level triggered irqs.
- */
- if (attr->trigger)
- entry->mask = 1;
-
- return 0;
-}
-
-static int set_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
-{
- struct irq_2_irte *irte_info;
- unsigned int dest, irq;
- struct irq_cfg *cfg;
- union irte irte;
- int err;
-
- if (!config_enabled(CONFIG_SMP))
- return -1;
-
- cfg = irqd_cfg(data);
- irq = data->irq;
- irte_info = &cfg->irq_2_irte;
-
- if (!cpumask_intersects(mask, cpu_online_mask))
- return -EINVAL;
-
- if (get_irte(irte_info->devid, irte_info->index, &irte))
- return -EBUSY;
-
- if (assign_irq_vector(irq, cfg, mask))
- return -EBUSY;
-
- err = apic->cpu_mask_to_apicid_and(cfg->domain, mask, &dest);
- if (err) {
- if (assign_irq_vector(irq, cfg, data->affinity))
- pr_err("AMD-Vi: Failed to recover vector for irq %d\n", irq);
- return err;
+ switch (info->type) {
+ case X86_IRQ_ALLOC_TYPE_IOAPIC:
+ devid = get_ioapic_devid(info->ioapic_id);
+ break;
+ case X86_IRQ_ALLOC_TYPE_HPET:
+ devid = get_hpet_devid(info->hpet_id);
+ break;
+ case X86_IRQ_ALLOC_TYPE_MSI:
+ case X86_IRQ_ALLOC_TYPE_MSIX:
+ devid = get_device_id(&info->msi_dev->dev);
+ break;
+ default:
+ BUG_ON(1);
+ break;
}
- irte.fields.vector = cfg->vector;
- irte.fields.destination = dest;
-
- modify_irte(irte_info->devid, irte_info->index, irte);
-
- if (cfg->move_in_progress)
- send_cleanup_vector(cfg);
-
- cpumask_copy(data->affinity, mask);
-
- return 0;
+ return devid;
}
-static int free_irq(int irq)
+static struct irq_domain *get_ir_irq_domain(struct irq_alloc_info *info)
{
- struct irq_2_irte *irte_info;
- struct irq_cfg *cfg;
+ struct amd_iommu *iommu;
+ int devid;
- cfg = irq_cfg(irq);
- if (!cfg)
- return -EINVAL;
+ if (!info)
+ return NULL;
- irte_info = &cfg->irq_2_irte;
+ devid = get_devid(info);
+ if (devid >= 0) {
+ iommu = amd_iommu_rlookup_table[devid];
+ if (iommu)
+ return iommu->ir_domain;
+ }
- free_irte(irte_info->devid, irte_info->index);
-
- return 0;
+ return NULL;
}
-static void compose_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id)
+static struct irq_domain *get_irq_domain(struct irq_alloc_info *info)
{
- struct irq_2_irte *irte_info;
- struct irq_cfg *cfg;
- union irte irte;
+ struct amd_iommu *iommu;
+ int devid;
- cfg = irq_cfg(irq);
- if (!cfg)
- return;
+ if (!info)
+ return NULL;
- irte_info = &cfg->irq_2_irte;
+ switch (info->type) {
+ case X86_IRQ_ALLOC_TYPE_MSI:
+ case X86_IRQ_ALLOC_TYPE_MSIX:
+ devid = get_device_id(&info->msi_dev->dev);
+ if (devid >= 0) {
+ iommu = amd_iommu_rlookup_table[devid];
+ if (iommu)
+ return iommu->msi_domain;
+ }
+ break;
+ default:
+ break;
+ }
- irte.val = 0;
- irte.fields.vector = cfg->vector;
- irte.fields.int_type = apic->irq_delivery_mode;
- irte.fields.destination = dest;
- irte.fields.dm = apic->irq_dest_mode;
- irte.fields.valid = 1;
-
- modify_irte(irte_info->devid, irte_info->index, irte);
-
- msg->address_hi = MSI_ADDR_BASE_HI;
- msg->address_lo = MSI_ADDR_BASE_LO;
- msg->data = irte_info->index;
-}
-
-static int msi_alloc_irq(struct pci_dev *pdev, int irq, int nvec)
-{
- struct irq_cfg *cfg;
- int index;
- u16 devid;
-
- if (!pdev)
- return -EINVAL;
-
- cfg = irq_cfg(irq);
- if (!cfg)
- return -EINVAL;
-
- devid = get_device_id(&pdev->dev);
- index = alloc_irq_index(cfg, devid, nvec);
-
- return index < 0 ? MAX_IRQS_PER_TABLE : index;
-}
-
-static int msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
- int index, int offset)
-{
- struct irq_2_irte *irte_info;
- struct irq_cfg *cfg;
- u16 devid;
-
- if (!pdev)
- return -EINVAL;
-
- cfg = irq_cfg(irq);
- if (!cfg)
- return -EINVAL;
-
- if (index >= MAX_IRQS_PER_TABLE)
- return 0;
-
- devid = get_device_id(&pdev->dev);
- irte_info = &cfg->irq_2_irte;
-
- cfg->remapped = 1;
- irte_info->devid = devid;
- irte_info->index = index + offset;
-
- return 0;
-}
-
-static int alloc_hpet_msi(unsigned int irq, unsigned int id)
-{
- struct irq_2_irte *irte_info;
- struct irq_cfg *cfg;
- int index, devid;
-
- cfg = irq_cfg(irq);
- if (!cfg)
- return -EINVAL;
-
- irte_info = &cfg->irq_2_irte;
- devid = get_hpet_devid(id);
- if (devid < 0)
- return devid;
-
- index = alloc_irq_index(cfg, devid, 1);
- if (index < 0)
- return index;
-
- cfg->remapped = 1;
- irte_info->devid = devid;
- irte_info->index = index;
-
- return 0;
+ return NULL;
}
struct irq_remap_ops amd_iommu_irq_ops = {
@@ -4283,12 +4116,244 @@
.disable = amd_iommu_disable,
.reenable = amd_iommu_reenable,
.enable_faulting = amd_iommu_enable_faulting,
- .setup_ioapic_entry = setup_ioapic_entry,
- .set_affinity = set_affinity,
- .free_irq = free_irq,
- .compose_msi_msg = compose_msi_msg,
- .msi_alloc_irq = msi_alloc_irq,
- .msi_setup_irq = msi_setup_irq,
- .alloc_hpet_msi = alloc_hpet_msi,
+ .get_ir_irq_domain = get_ir_irq_domain,
+ .get_irq_domain = get_irq_domain,
};
+
+static void irq_remapping_prepare_irte(struct amd_ir_data *data,
+ struct irq_cfg *irq_cfg,
+ struct irq_alloc_info *info,
+ int devid, int index, int sub_handle)
+{
+ struct irq_2_irte *irte_info = &data->irq_2_irte;
+ struct msi_msg *msg = &data->msi_entry;
+ union irte *irte = &data->irte_entry;
+ struct IO_APIC_route_entry *entry;
+
+ data->irq_2_irte.devid = devid;
+ data->irq_2_irte.index = index + sub_handle;
+
+ /* Setup IRTE for IOMMU */
+ irte->val = 0;
+ irte->fields.vector = irq_cfg->vector;
+ irte->fields.int_type = apic->irq_delivery_mode;
+ irte->fields.destination = irq_cfg->dest_apicid;
+ irte->fields.dm = apic->irq_dest_mode;
+ irte->fields.valid = 1;
+
+ switch (info->type) {
+ case X86_IRQ_ALLOC_TYPE_IOAPIC:
+ /* Setup IOAPIC entry */
+ entry = info->ioapic_entry;
+ info->ioapic_entry = NULL;
+ memset(entry, 0, sizeof(*entry));
+ entry->vector = index;
+ entry->mask = 0;
+ entry->trigger = info->ioapic_trigger;
+ entry->polarity = info->ioapic_polarity;
+ /* Mask level triggered irqs. */
+ if (info->ioapic_trigger)
+ entry->mask = 1;
+ break;
+
+ case X86_IRQ_ALLOC_TYPE_HPET:
+ case X86_IRQ_ALLOC_TYPE_MSI:
+ case X86_IRQ_ALLOC_TYPE_MSIX:
+ msg->address_hi = MSI_ADDR_BASE_HI;
+ msg->address_lo = MSI_ADDR_BASE_LO;
+ msg->data = irte_info->index;
+ break;
+
+ default:
+ BUG_ON(1);
+ break;
+ }
+}
+
+static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
+{
+ struct irq_alloc_info *info = arg;
+ struct irq_data *irq_data;
+ struct amd_ir_data *data;
+ struct irq_cfg *cfg;
+ int i, ret, devid;
+ int index = -1;
+
+ if (!info)
+ return -EINVAL;
+ if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_MSI &&
+ info->type != X86_IRQ_ALLOC_TYPE_MSIX)
+ return -EINVAL;
+
+ /*
+ * With IRQ remapping enabled, don't need contiguous CPU vectors
+ * to support multiple MSI interrupts.
+ */
+ if (info->type == X86_IRQ_ALLOC_TYPE_MSI)
+ info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+
+ devid = get_devid(info);
+ if (devid < 0)
+ return -EINVAL;
+
+ ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+ if (ret < 0)
+ return ret;
+
+ ret = -ENOMEM;
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ goto out_free_parent;
+
+ if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) {
+ if (get_irq_table(devid, true))
+ index = info->ioapic_pin;
+ else
+ ret = -ENOMEM;
+ } else {
+ index = alloc_irq_index(devid, nr_irqs);
+ }
+ if (index < 0) {
+ pr_warn("Failed to allocate IRTE\n");
+ kfree(data);
+ goto out_free_parent;
+ }
+
+ for (i = 0; i < nr_irqs; i++) {
+ irq_data = irq_domain_get_irq_data(domain, virq + i);
+ cfg = irqd_cfg(irq_data);
+ if (!irq_data || !cfg) {
+ ret = -EINVAL;
+ goto out_free_data;
+ }
+
+ if (i > 0) {
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ goto out_free_data;
+ }
+ irq_data->hwirq = (devid << 16) + i;
+ irq_data->chip_data = data;
+ irq_data->chip = &amd_ir_chip;
+ irq_remapping_prepare_irte(data, cfg, info, devid, index, i);
+ irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
+ }
+ return 0;
+
+out_free_data:
+ for (i--; i >= 0; i--) {
+ irq_data = irq_domain_get_irq_data(domain, virq + i);
+ if (irq_data)
+ kfree(irq_data->chip_data);
+ }
+ for (i = 0; i < nr_irqs; i++)
+ free_irte(devid, index + i);
+out_free_parent:
+ irq_domain_free_irqs_common(domain, virq, nr_irqs);
+ return ret;
+}
+
+static void irq_remapping_free(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs)
+{
+ struct irq_2_irte *irte_info;
+ struct irq_data *irq_data;
+ struct amd_ir_data *data;
+ int i;
+
+ for (i = 0; i < nr_irqs; i++) {
+ irq_data = irq_domain_get_irq_data(domain, virq + i);
+ if (irq_data && irq_data->chip_data) {
+ data = irq_data->chip_data;
+ irte_info = &data->irq_2_irte;
+ free_irte(irte_info->devid, irte_info->index);
+ kfree(data);
+ }
+ }
+ irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
+
+static void irq_remapping_activate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ struct amd_ir_data *data = irq_data->chip_data;
+ struct irq_2_irte *irte_info = &data->irq_2_irte;
+
+ modify_irte(irte_info->devid, irte_info->index, data->irte_entry);
+}
+
+static void irq_remapping_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ struct amd_ir_data *data = irq_data->chip_data;
+ struct irq_2_irte *irte_info = &data->irq_2_irte;
+ union irte entry;
+
+ entry.val = 0;
+ modify_irte(irte_info->devid, irte_info->index, data->irte_entry);
+}
+
+static struct irq_domain_ops amd_ir_domain_ops = {
+ .alloc = irq_remapping_alloc,
+ .free = irq_remapping_free,
+ .activate = irq_remapping_activate,
+ .deactivate = irq_remapping_deactivate,
+};
+
+static int amd_ir_set_affinity(struct irq_data *data,
+ const struct cpumask *mask, bool force)
+{
+ struct amd_ir_data *ir_data = data->chip_data;
+ struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
+ struct irq_cfg *cfg = irqd_cfg(data);
+ struct irq_data *parent = data->parent_data;
+ int ret;
+
+ ret = parent->chip->irq_set_affinity(parent, mask, force);
+ if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+ return ret;
+
+ /*
+ * Atomically updates the IRTE with the new destination, vector
+ * and flushes the interrupt entry cache.
+ */
+ ir_data->irte_entry.fields.vector = cfg->vector;
+ ir_data->irte_entry.fields.destination = cfg->dest_apicid;
+ modify_irte(irte_info->devid, irte_info->index, ir_data->irte_entry);
+
+ /*
+ * After this point, all the interrupts will start arriving
+ * at the new destination. So, time to cleanup the previous
+ * vector allocation.
+ */
+ send_cleanup_vector(cfg);
+
+ return IRQ_SET_MASK_OK_DONE;
+}
+
+static void ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg)
+{
+ struct amd_ir_data *ir_data = irq_data->chip_data;
+
+ *msg = ir_data->msi_entry;
+}
+
+static struct irq_chip amd_ir_chip = {
+ .irq_ack = ir_ack_apic_edge,
+ .irq_set_affinity = amd_ir_set_affinity,
+ .irq_compose_msi_msg = ir_compose_msi_msg,
+};
+
+int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
+{
+ iommu->ir_domain = irq_domain_add_tree(NULL, &amd_ir_domain_ops, iommu);
+ if (!iommu->ir_domain)
+ return -ENOMEM;
+
+ iommu->ir_domain->parent = arch_get_ir_parent_domain();
+ iommu->msi_domain = arch_create_msi_irq_domain(iommu->ir_domain);
+
+ return 0;
+}
#endif
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 450ef50..c17df04 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1124,6 +1124,10 @@
if (ret)
return ret;
+ ret = amd_iommu_create_irq_domain(iommu);
+ if (ret)
+ return ret;
+
/*
* Make sure IOMMU is not considered to translate itself. The IVRS
* table tells us so, but this is a lie!
diff --git a/drivers/iommu/amd_iommu_proto.h b/drivers/iommu/amd_iommu_proto.h
index 72b0fd4..0a21142 100644
--- a/drivers/iommu/amd_iommu_proto.h
+++ b/drivers/iommu/amd_iommu_proto.h
@@ -62,6 +62,15 @@
extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
u64 *value, bool is_write);
+#ifdef CONFIG_IRQ_REMAP
+extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu);
+#else
+static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
+{
+ return 0;
+}
+#endif
+
#define PPR_SUCCESS 0x0
#define PPR_INVALID 0x1
#define PPR_FAILURE 0xf
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 05030e5..6533e87 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -398,6 +398,7 @@
struct iommu_domain;
+struct irq_domain;
/*
* This structure contains generic data for IOMMU protection domains
@@ -579,6 +580,10 @@
/* The maximum PC banks and counters/bank (PCSup=1) */
u8 max_banks;
u8 max_counters;
+#ifdef CONFIG_IRQ_REMAP
+ struct irq_domain *ir_domain;
+ struct irq_domain *msi_domain;
+#endif
};
struct devid_map {
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 9847613..536f2d8 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1087,8 +1087,8 @@
if (iommu->irq) {
free_irq(iommu->irq, iommu);
- irq_set_handler_data(iommu->irq, NULL);
dmar_free_hwirq(iommu->irq);
+ iommu->irq = 0;
}
if (iommu->qi) {
@@ -1642,23 +1642,14 @@
if (iommu->irq)
return 0;
- irq = dmar_alloc_hwirq();
- if (irq <= 0) {
+ irq = dmar_alloc_hwirq(iommu->seq_id, iommu->node, iommu);
+ if (irq > 0) {
+ iommu->irq = irq;
+ } else {
pr_err("IOMMU: no free vectors\n");
return -EINVAL;
}
- irq_set_handler_data(irq, iommu);
- iommu->irq = irq;
-
- ret = arch_setup_dmar_msi(irq);
- if (ret) {
- irq_set_handler_data(irq, NULL);
- iommu->irq = 0;
- dmar_free_hwirq(irq);
- return ret;
- }
-
ret = request_irq(irq, dmar_fault, IRQF_NO_THREAD, iommu->name, iommu);
if (ret)
pr_err("IOMMU: can't request irq\n");
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 5709ae9..80f1d14 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -8,6 +8,7 @@
#include <linux/irq.h>
#include <linux/intel-iommu.h>
#include <linux/acpi.h>
+#include <linux/irqdomain.h>
#include <asm/io_apic.h>
#include <asm/smp.h>
#include <asm/cpu.h>
@@ -17,6 +18,11 @@
#include "irq_remapping.h"
+enum irq_mode {
+ IRQ_REMAPPING,
+ IRQ_POSTING,
+};
+
struct ioapic_scope {
struct intel_iommu *iommu;
unsigned int id;
@@ -31,6 +37,22 @@
unsigned int devfn;
};
+struct irq_2_iommu {
+ struct intel_iommu *iommu;
+ u16 irte_index;
+ u16 sub_handle;
+ u8 irte_mask;
+ enum irq_mode mode;
+};
+
+struct intel_ir_data {
+ struct irq_2_iommu irq_2_iommu;
+ struct irte irte_entry;
+ union {
+ struct msi_msg msi_entry;
+ };
+};
+
#define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0)
#define IRTE_DEST(dest) ((eim_mode) ? dest : dest << 8)
@@ -50,43 +72,14 @@
* the dmar_global_lock.
*/
static DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
+static struct irq_domain_ops intel_ir_domain_ops;
static int __init parse_ioapics_under_ir(void);
-static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
-{
- struct irq_cfg *cfg = irq_cfg(irq);
- return cfg ? &cfg->irq_2_iommu : NULL;
-}
-
-static int get_irte(int irq, struct irte *entry)
-{
- struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
- unsigned long flags;
- int index;
-
- if (!entry || !irq_iommu)
- return -1;
-
- raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-
- if (unlikely(!irq_iommu->iommu)) {
- raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
- return -1;
- }
-
- index = irq_iommu->irte_index + irq_iommu->sub_handle;
- *entry = *(irq_iommu->iommu->ir_table->base + index);
-
- raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
- return 0;
-}
-
-static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
+static int alloc_irte(struct intel_iommu *iommu, int irq,
+ struct irq_2_iommu *irq_iommu, u16 count)
{
struct ir_table *table = iommu->ir_table;
- struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
- struct irq_cfg *cfg = irq_cfg(irq);
unsigned int mask = 0;
unsigned long flags;
int index;
@@ -113,11 +106,11 @@
if (index < 0) {
pr_warn("IR%d: can't allocate an IRTE\n", iommu->seq_id);
} else {
- cfg->remapped = 1;
irq_iommu->iommu = iommu;
irq_iommu->irte_index = index;
irq_iommu->sub_handle = 0;
irq_iommu->irte_mask = mask;
+ irq_iommu->mode = IRQ_REMAPPING;
}
raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
@@ -135,47 +128,9 @@
return qi_submit_sync(&desc, iommu);
}
-static int map_irq_to_irte_handle(int irq, u16 *sub_handle)
+static int modify_irte(struct irq_2_iommu *irq_iommu,
+ struct irte *irte_modified)
{
- struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
- unsigned long flags;
- int index;
-
- if (!irq_iommu)
- return -1;
-
- raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
- *sub_handle = irq_iommu->sub_handle;
- index = irq_iommu->irte_index;
- raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
- return index;
-}
-
-static int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
-{
- struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
- struct irq_cfg *cfg = irq_cfg(irq);
- unsigned long flags;
-
- if (!irq_iommu)
- return -1;
-
- raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-
- cfg->remapped = 1;
- irq_iommu->iommu = iommu;
- irq_iommu->irte_index = index;
- irq_iommu->sub_handle = subhandle;
- irq_iommu->irte_mask = 0;
-
- raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
- return 0;
-}
-
-static int modify_irte(int irq, struct irte *irte_modified)
-{
- struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
struct intel_iommu *iommu;
unsigned long flags;
struct irte *irte;
@@ -196,6 +151,9 @@
__iommu_flush_cache(iommu, irte, sizeof(*irte));
rc = qi_flush_iec(iommu, index, 0);
+
+ /* Update iommu mode according to the IRTE mode */
+ irq_iommu->mode = irte->pst ? IRQ_POSTING : IRQ_REMAPPING;
raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return rc;
@@ -242,7 +200,7 @@
return 0;
iommu = irq_iommu->iommu;
- index = irq_iommu->irte_index + irq_iommu->sub_handle;
+ index = irq_iommu->irte_index;
start = iommu->ir_table->base + index;
end = start + (1 << irq_iommu->irte_mask);
@@ -257,29 +215,6 @@
return qi_flush_iec(iommu, index, irq_iommu->irte_mask);
}
-static int free_irte(int irq)
-{
- struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
- unsigned long flags;
- int rc;
-
- if (!irq_iommu)
- return -1;
-
- raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-
- rc = clear_entries(irq_iommu);
-
- irq_iommu->iommu = NULL;
- irq_iommu->irte_index = 0;
- irq_iommu->sub_handle = 0;
- irq_iommu->irte_mask = 0;
-
- raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
- return rc;
-}
-
/*
* source validation type
*/
@@ -488,7 +423,6 @@
pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO,
INTR_REMAP_PAGE_ORDER);
-
if (!pages) {
pr_err("IR%d: failed to allocate pages of order %d\n",
iommu->seq_id, INTR_REMAP_PAGE_ORDER);
@@ -502,11 +436,23 @@
goto out_free_pages;
}
+ iommu->ir_domain = irq_domain_add_hierarchy(arch_get_ir_parent_domain(),
+ 0, INTR_REMAP_TABLE_ENTRIES,
+ NULL, &intel_ir_domain_ops,
+ iommu);
+ if (!iommu->ir_domain) {
+ pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id);
+ goto out_free_bitmap;
+ }
+ iommu->ir_msi_domain = arch_create_msi_irq_domain(iommu->ir_domain);
+
ir_table->base = page_address(pages);
ir_table->bitmap = bitmap;
iommu->ir_table = ir_table;
return 0;
+out_free_bitmap:
+ kfree(bitmap);
out_free_pages:
__free_pages(pages, INTR_REMAP_PAGE_ORDER);
out_free_table:
@@ -517,6 +463,14 @@
static void intel_teardown_irq_remapping(struct intel_iommu *iommu)
{
if (iommu && iommu->ir_table) {
+ if (iommu->ir_msi_domain) {
+ irq_domain_remove(iommu->ir_msi_domain);
+ iommu->ir_msi_domain = NULL;
+ }
+ if (iommu->ir_domain) {
+ irq_domain_remove(iommu->ir_domain);
+ iommu->ir_domain = NULL;
+ }
free_pages((unsigned long)iommu->ir_table->base,
INTR_REMAP_PAGE_ORDER);
kfree(iommu->ir_table->bitmap);
@@ -627,6 +581,26 @@
return -ENODEV;
}
+/*
+ * Set Posted-Interrupts capability.
+ */
+static inline void set_irq_posting_cap(void)
+{
+ struct dmar_drhd_unit *drhd;
+ struct intel_iommu *iommu;
+
+ if (!disable_irq_post) {
+ intel_irq_remap_ops.capability |= 1 << IRQ_POSTING_CAP;
+
+ for_each_iommu(iommu, drhd)
+ if (!cap_pi_support(iommu->cap)) {
+ intel_irq_remap_ops.capability &=
+ ~(1 << IRQ_POSTING_CAP);
+ break;
+ }
+ }
+}
+
static int __init intel_enable_irq_remapping(void)
{
struct dmar_drhd_unit *drhd;
@@ -702,12 +676,7 @@
irq_remapping_enabled = 1;
- /*
- * VT-d has a different layout for IO-APIC entries when
- * interrupt remapping is enabled. So it needs a special routine
- * to print IO-APIC entries for debugging purposes too.
- */
- x86_io_apic_ops.print_entries = intel_ir_io_apic_print_entries;
+ set_irq_posting_cap();
pr_info("Enabled IRQ remapping in %s mode\n", eim ? "x2apic" : "xapic");
@@ -909,6 +878,12 @@
iommu_disable_irq_remapping(iommu);
}
+
+ /*
+ * Clear Posted-Interrupts capability.
+ */
+ if (!disable_irq_post)
+ intel_irq_remap_ops.capability &= ~(1 << IRQ_POSTING_CAP);
}
static int reenable_irq_remapping(int eim)
@@ -936,6 +911,8 @@
if (!setup)
goto error;
+ set_irq_posting_cap();
+
return 0;
error:
@@ -945,8 +922,7 @@
return -1;
}
-static void prepare_irte(struct irte *irte, int vector,
- unsigned int dest)
+static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
{
memset(irte, 0, sizeof(*irte));
@@ -966,76 +942,63 @@
irte->redir_hint = 1;
}
-static int intel_setup_ioapic_entry(int irq,
- struct IO_APIC_route_entry *route_entry,
- unsigned int destination, int vector,
- struct io_apic_irq_attr *attr)
+static struct irq_domain *intel_get_ir_irq_domain(struct irq_alloc_info *info)
{
- int ioapic_id = mpc_ioapic_id(attr->ioapic);
- struct intel_iommu *iommu;
- struct IR_IO_APIC_route_entry *entry;
- struct irte irte;
- int index;
+ struct intel_iommu *iommu = NULL;
- down_read(&dmar_global_lock);
- iommu = map_ioapic_to_ir(ioapic_id);
- if (!iommu) {
- pr_warn("No mapping iommu for ioapic %d\n", ioapic_id);
- index = -ENODEV;
- } else {
- index = alloc_irte(iommu, irq, 1);
- if (index < 0) {
- pr_warn("Failed to allocate IRTE for ioapic %d\n",
- ioapic_id);
- index = -ENOMEM;
- }
+ if (!info)
+ return NULL;
+
+ switch (info->type) {
+ case X86_IRQ_ALLOC_TYPE_IOAPIC:
+ iommu = map_ioapic_to_ir(info->ioapic_id);
+ break;
+ case X86_IRQ_ALLOC_TYPE_HPET:
+ iommu = map_hpet_to_ir(info->hpet_id);
+ break;
+ case X86_IRQ_ALLOC_TYPE_MSI:
+ case X86_IRQ_ALLOC_TYPE_MSIX:
+ iommu = map_dev_to_ir(info->msi_dev);
+ break;
+ default:
+ BUG_ON(1);
+ break;
}
- up_read(&dmar_global_lock);
- if (index < 0)
- return index;
- prepare_irte(&irte, vector, destination);
-
- /* Set source-id of interrupt request */
- set_ioapic_sid(&irte, ioapic_id);
-
- modify_irte(irq, &irte);
-
- apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: "
- "Set IRTE entry (P:%d FPD:%d Dst_Mode:%d "
- "Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X "
- "Avail:%X Vector:%02X Dest:%08X "
- "SID:%04X SQ:%X SVT:%X)\n",
- attr->ioapic, irte.present, irte.fpd, irte.dst_mode,
- irte.redir_hint, irte.trigger_mode, irte.dlvry_mode,
- irte.avail, irte.vector, irte.dest_id,
- irte.sid, irte.sq, irte.svt);
-
- entry = (struct IR_IO_APIC_route_entry *)route_entry;
- memset(entry, 0, sizeof(*entry));
-
- entry->index2 = (index >> 15) & 0x1;
- entry->zero = 0;
- entry->format = 1;
- entry->index = (index & 0x7fff);
- /*
- * IO-APIC RTE will be configured with virtual vector.
- * irq handler will do the explicit EOI to the io-apic.
- */
- entry->vector = attr->ioapic_pin;
- entry->mask = 0; /* enable IRQ */
- entry->trigger = attr->trigger;
- entry->polarity = attr->polarity;
-
- /* Mask level triggered irqs.
- * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
- */
- if (attr->trigger)
- entry->mask = 1;
-
- return 0;
+ return iommu ? iommu->ir_domain : NULL;
}
+static struct irq_domain *intel_get_irq_domain(struct irq_alloc_info *info)
+{
+ struct intel_iommu *iommu;
+
+ if (!info)
+ return NULL;
+
+ switch (info->type) {
+ case X86_IRQ_ALLOC_TYPE_MSI:
+ case X86_IRQ_ALLOC_TYPE_MSIX:
+ iommu = map_dev_to_ir(info->msi_dev);
+ if (iommu)
+ return iommu->ir_msi_domain;
+ break;
+ default:
+ break;
+ }
+
+ return NULL;
+}
+
+struct irq_remap_ops intel_irq_remap_ops = {
+ .prepare = intel_prepare_irq_remapping,
+ .enable = intel_enable_irq_remapping,
+ .disable = disable_irq_remapping,
+ .reenable = reenable_irq_remapping,
+ .enable_faulting = enable_drhd_fault_handling,
+ .get_ir_irq_domain = intel_get_ir_irq_domain,
+ .get_irq_domain = intel_get_irq_domain,
+};
+
/*
* Migrate the IO-APIC irq in the presence of intr-remapping.
*
@@ -1051,170 +1014,282 @@
* is used to migrate MSI irq's in the presence of interrupt-remapping.
*/
static int
-intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
+intel_ir_set_affinity(struct irq_data *data, const struct cpumask *mask,
+ bool force)
{
+ struct intel_ir_data *ir_data = data->chip_data;
+ struct irte *irte = &ir_data->irte_entry;
struct irq_cfg *cfg = irqd_cfg(data);
- unsigned int dest, irq = data->irq;
- struct irte irte;
- int err;
+ struct irq_data *parent = data->parent_data;
+ int ret;
- if (!config_enabled(CONFIG_SMP))
- return -EINVAL;
-
- if (!cpumask_intersects(mask, cpu_online_mask))
- return -EINVAL;
-
- if (get_irte(irq, &irte))
- return -EBUSY;
-
- err = assign_irq_vector(irq, cfg, mask);
- if (err)
- return err;
-
- err = apic->cpu_mask_to_apicid_and(cfg->domain, mask, &dest);
- if (err) {
- if (assign_irq_vector(irq, cfg, data->affinity))
- pr_err("Failed to recover vector for irq %d\n", irq);
- return err;
- }
-
- irte.vector = cfg->vector;
- irte.dest_id = IRTE_DEST(dest);
+ ret = parent->chip->irq_set_affinity(parent, mask, force);
+ if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+ return ret;
/*
* Atomically updates the IRTE with the new destination, vector
* and flushes the interrupt entry cache.
*/
- modify_irte(irq, &irte);
+ irte->vector = cfg->vector;
+ irte->dest_id = IRTE_DEST(cfg->dest_apicid);
+
+ /* Update the hardware only if the interrupt is in remapped mode. */
+ if (ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
+ modify_irte(&ir_data->irq_2_iommu, irte);
/*
* After this point, all the interrupts will start arriving
* at the new destination. So, time to cleanup the previous
* vector allocation.
*/
- if (cfg->move_in_progress)
- send_cleanup_vector(cfg);
+ send_cleanup_vector(cfg);
- cpumask_copy(data->affinity, mask);
+ return IRQ_SET_MASK_OK_DONE;
+}
+
+static void intel_ir_compose_msi_msg(struct irq_data *irq_data,
+ struct msi_msg *msg)
+{
+ struct intel_ir_data *ir_data = irq_data->chip_data;
+
+ *msg = ir_data->msi_entry;
+}
+
+static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info)
+{
+ struct intel_ir_data *ir_data = data->chip_data;
+ struct vcpu_data *vcpu_pi_info = info;
+
+ /* stop posting interrupts, back to remapping mode */
+ if (!vcpu_pi_info) {
+ modify_irte(&ir_data->irq_2_iommu, &ir_data->irte_entry);
+ } else {
+ struct irte irte_pi;
+
+ /*
+ * We are not caching the posted interrupt entry. We
+ * copy the data from the remapped entry and modify
+ * the fields which are relevant for posted mode. The
+ * cached remapped entry is used for switching back to
+ * remapped mode.
+ */
+ memset(&irte_pi, 0, sizeof(irte_pi));
+ dmar_copy_shared_irte(&irte_pi, &ir_data->irte_entry);
+
+ /* Update the posted mode fields */
+ irte_pi.p_pst = 1;
+ irte_pi.p_urgent = 0;
+ irte_pi.p_vector = vcpu_pi_info->vector;
+ irte_pi.pda_l = (vcpu_pi_info->pi_desc_addr >>
+ (32 - PDA_LOW_BIT)) & ~(-1UL << PDA_LOW_BIT);
+ irte_pi.pda_h = (vcpu_pi_info->pi_desc_addr >> 32) &
+ ~(-1UL << PDA_HIGH_BIT);
+
+ modify_irte(&ir_data->irq_2_iommu, &irte_pi);
+ }
+
return 0;
}
-static void intel_compose_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id)
+static struct irq_chip intel_ir_chip = {
+ .irq_ack = ir_ack_apic_edge,
+ .irq_set_affinity = intel_ir_set_affinity,
+ .irq_compose_msi_msg = intel_ir_compose_msi_msg,
+ .irq_set_vcpu_affinity = intel_ir_set_vcpu_affinity,
+};
+
+static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data,
+ struct irq_cfg *irq_cfg,
+ struct irq_alloc_info *info,
+ int index, int sub_handle)
{
- struct irq_cfg *cfg;
- struct irte irte;
- u16 sub_handle = 0;
- int ir_index;
+ struct IR_IO_APIC_route_entry *entry;
+ struct irte *irte = &data->irte_entry;
+ struct msi_msg *msg = &data->msi_entry;
- cfg = irq_cfg(irq);
+ prepare_irte(irte, irq_cfg->vector, irq_cfg->dest_apicid);
+ switch (info->type) {
+ case X86_IRQ_ALLOC_TYPE_IOAPIC:
+ /* Set source-id of interrupt request */
+ set_ioapic_sid(irte, info->ioapic_id);
+ apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: Set IRTE entry (P:%d FPD:%d Dst_Mode:%d Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X Avail:%X Vector:%02X Dest:%08X SID:%04X SQ:%X SVT:%X)\n",
+ info->ioapic_id, irte->present, irte->fpd,
+ irte->dst_mode, irte->redir_hint,
+ irte->trigger_mode, irte->dlvry_mode,
+ irte->avail, irte->vector, irte->dest_id,
+ irte->sid, irte->sq, irte->svt);
- ir_index = map_irq_to_irte_handle(irq, &sub_handle);
- BUG_ON(ir_index == -1);
+ entry = (struct IR_IO_APIC_route_entry *)info->ioapic_entry;
+ info->ioapic_entry = NULL;
+ memset(entry, 0, sizeof(*entry));
+ entry->index2 = (index >> 15) & 0x1;
+ entry->zero = 0;
+ entry->format = 1;
+ entry->index = (index & 0x7fff);
+ /*
+ * IO-APIC RTE will be configured with virtual vector.
+ * irq handler will do the explicit EOI to the io-apic.
+ */
+ entry->vector = info->ioapic_pin;
+ entry->mask = 0; /* enable IRQ */
+ entry->trigger = info->ioapic_trigger;
+ entry->polarity = info->ioapic_polarity;
+ if (info->ioapic_trigger)
+ entry->mask = 1; /* Mask level triggered irqs. */
+ break;
- prepare_irte(&irte, cfg->vector, dest);
+ case X86_IRQ_ALLOC_TYPE_HPET:
+ case X86_IRQ_ALLOC_TYPE_MSI:
+ case X86_IRQ_ALLOC_TYPE_MSIX:
+ if (info->type == X86_IRQ_ALLOC_TYPE_HPET)
+ set_hpet_sid(irte, info->hpet_id);
+ else
+ set_msi_sid(irte, info->msi_dev);
- /* Set source-id of interrupt request */
- if (pdev)
- set_msi_sid(&irte, pdev);
- else
- set_hpet_sid(&irte, hpet_id);
+ msg->address_hi = MSI_ADDR_BASE_HI;
+ msg->data = sub_handle;
+ msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
+ MSI_ADDR_IR_SHV |
+ MSI_ADDR_IR_INDEX1(index) |
+ MSI_ADDR_IR_INDEX2(index);
+ break;
- modify_irte(irq, &irte);
-
- msg->address_hi = MSI_ADDR_BASE_HI;
- msg->data = sub_handle;
- msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
- MSI_ADDR_IR_SHV |
- MSI_ADDR_IR_INDEX1(ir_index) |
- MSI_ADDR_IR_INDEX2(ir_index);
+ default:
+ BUG_ON(1);
+ break;
+ }
}
-/*
- * Map the PCI dev to the corresponding remapping hardware unit
- * and allocate 'nvec' consecutive interrupt-remapping table entries
- * in it.
- */
-static int intel_msi_alloc_irq(struct pci_dev *dev, int irq, int nvec)
+static void intel_free_irq_resources(struct irq_domain *domain,
+ unsigned int virq, unsigned int nr_irqs)
{
- struct intel_iommu *iommu;
- int index;
+ struct irq_data *irq_data;
+ struct intel_ir_data *data;
+ struct irq_2_iommu *irq_iommu;
+ unsigned long flags;
+ int i;
- down_read(&dmar_global_lock);
- iommu = map_dev_to_ir(dev);
- if (!iommu) {
- printk(KERN_ERR
- "Unable to map PCI %s to iommu\n", pci_name(dev));
- index = -ENOENT;
- } else {
- index = alloc_irte(iommu, irq, nvec);
- if (index < 0) {
- printk(KERN_ERR
- "Unable to allocate %d IRTE for PCI %s\n",
- nvec, pci_name(dev));
- index = -ENOSPC;
+ for (i = 0; i < nr_irqs; i++) {
+ irq_data = irq_domain_get_irq_data(domain, virq + i);
+ if (irq_data && irq_data->chip_data) {
+ data = irq_data->chip_data;
+ irq_iommu = &data->irq_2_iommu;
+ raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+ clear_entries(irq_iommu);
+ raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+ irq_domain_reset_irq_data(irq_data);
+ kfree(data);
}
}
- up_read(&dmar_global_lock);
-
- return index;
}
-static int intel_msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
- int index, int sub_handle)
+static int intel_irq_remapping_alloc(struct irq_domain *domain,
+ unsigned int virq, unsigned int nr_irqs,
+ void *arg)
{
- struct intel_iommu *iommu;
- int ret = -ENOENT;
+ struct intel_iommu *iommu = domain->host_data;
+ struct irq_alloc_info *info = arg;
+ struct intel_ir_data *data, *ird;
+ struct irq_data *irq_data;
+ struct irq_cfg *irq_cfg;
+ int i, ret, index;
+
+ if (!info || !iommu)
+ return -EINVAL;
+ if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_MSI &&
+ info->type != X86_IRQ_ALLOC_TYPE_MSIX)
+ return -EINVAL;
+
+ /*
+ * With IRQ remapping enabled, don't need contiguous CPU vectors
+ * to support multiple MSI interrupts.
+ */
+ if (info->type == X86_IRQ_ALLOC_TYPE_MSI)
+ info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+
+ ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+ if (ret < 0)
+ return ret;
+
+ ret = -ENOMEM;
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ goto out_free_parent;
down_read(&dmar_global_lock);
- iommu = map_dev_to_ir(pdev);
- if (iommu) {
- /*
- * setup the mapping between the irq and the IRTE
- * base index, the sub_handle pointing to the
- * appropriate interrupt remap table entry.
- */
- set_irte_irq(irq, iommu, index, sub_handle);
- ret = 0;
- }
+ index = alloc_irte(iommu, virq, &data->irq_2_iommu, nr_irqs);
up_read(&dmar_global_lock);
+ if (index < 0) {
+ pr_warn("Failed to allocate IRTE\n");
+ kfree(data);
+ goto out_free_parent;
+ }
+ for (i = 0; i < nr_irqs; i++) {
+ irq_data = irq_domain_get_irq_data(domain, virq + i);
+ irq_cfg = irqd_cfg(irq_data);
+ if (!irq_data || !irq_cfg) {
+ ret = -EINVAL;
+ goto out_free_data;
+ }
+
+ if (i > 0) {
+ ird = kzalloc(sizeof(*ird), GFP_KERNEL);
+ if (!ird)
+ goto out_free_data;
+ /* Initialize the common data */
+ ird->irq_2_iommu = data->irq_2_iommu;
+ ird->irq_2_iommu.sub_handle = i;
+ } else {
+ ird = data;
+ }
+
+ irq_data->hwirq = (index << 16) + i;
+ irq_data->chip_data = ird;
+ irq_data->chip = &intel_ir_chip;
+ intel_irq_remapping_prepare_irte(ird, irq_cfg, info, index, i);
+ irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
+ }
+ return 0;
+
+out_free_data:
+ intel_free_irq_resources(domain, virq, i);
+out_free_parent:
+ irq_domain_free_irqs_common(domain, virq, nr_irqs);
return ret;
}
-static int intel_alloc_hpet_msi(unsigned int irq, unsigned int id)
+static void intel_irq_remapping_free(struct irq_domain *domain,
+ unsigned int virq, unsigned int nr_irqs)
{
- int ret = -1;
- struct intel_iommu *iommu;
- int index;
-
- down_read(&dmar_global_lock);
- iommu = map_hpet_to_ir(id);
- if (iommu) {
- index = alloc_irte(iommu, irq, 1);
- if (index >= 0)
- ret = 0;
- }
- up_read(&dmar_global_lock);
-
- return ret;
+ intel_free_irq_resources(domain, virq, nr_irqs);
+ irq_domain_free_irqs_common(domain, virq, nr_irqs);
}
-struct irq_remap_ops intel_irq_remap_ops = {
- .prepare = intel_prepare_irq_remapping,
- .enable = intel_enable_irq_remapping,
- .disable = disable_irq_remapping,
- .reenable = reenable_irq_remapping,
- .enable_faulting = enable_drhd_fault_handling,
- .setup_ioapic_entry = intel_setup_ioapic_entry,
- .set_affinity = intel_ioapic_set_affinity,
- .free_irq = free_irte,
- .compose_msi_msg = intel_compose_msi_msg,
- .msi_alloc_irq = intel_msi_alloc_irq,
- .msi_setup_irq = intel_msi_setup_irq,
- .alloc_hpet_msi = intel_alloc_hpet_msi,
+static void intel_irq_remapping_activate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ struct intel_ir_data *data = irq_data->chip_data;
+
+ modify_irte(&data->irq_2_iommu, &data->irte_entry);
+}
+
+static void intel_irq_remapping_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ struct intel_ir_data *data = irq_data->chip_data;
+ struct irte entry;
+
+ memset(&entry, 0, sizeof(entry));
+ modify_irte(&data->irq_2_iommu, &entry);
+}
+
+static struct irq_domain_ops intel_ir_domain_ops = {
+ .alloc = intel_irq_remapping_alloc,
+ .free = intel_irq_remapping_free,
+ .activate = intel_irq_remapping_activate,
+ .deactivate = intel_irq_remapping_deactivate,
};
/*
@@ -1280,6 +1355,9 @@
return -EINVAL;
if (!ecap_ir_support(iommu->ecap))
return 0;
+ if (irq_remapping_cap(IRQ_POSTING_CAP) &&
+ !cap_pi_support(iommu->cap))
+ return -EBUSY;
if (insert) {
if (!iommu->ir_table)
diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c
index 390079e..2d99930 100644
--- a/drivers/iommu/irq_remapping.c
+++ b/drivers/iommu/irq_remapping.c
@@ -6,6 +6,7 @@
#include <linux/msi.h>
#include <linux/irq.h>
#include <linux/pci.h>
+#include <linux/irqdomain.h>
#include <asm/hw_irq.h>
#include <asm/irq_remapping.h>
@@ -21,21 +22,11 @@
int disable_sourceid_checking;
int no_x2apic_optout;
+int disable_irq_post = 1;
+
static int disable_irq_remap;
static struct irq_remap_ops *remap_ops;
-static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec);
-static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq,
- int index, int sub_handle);
-static int set_remapped_irq_affinity(struct irq_data *data,
- const struct cpumask *mask,
- bool force);
-
-static bool irq_remapped(struct irq_cfg *cfg)
-{
- return (cfg->remapped == 1);
-}
-
static void irq_remapping_disable_io_apic(void)
{
/*
@@ -49,117 +40,9 @@
disconnect_bsp_APIC(0);
}
-static int do_setup_msi_irqs(struct pci_dev *dev, int nvec)
-{
- int ret, sub_handle, nvec_pow2, index = 0;
- unsigned int irq;
- struct msi_desc *msidesc;
-
- msidesc = list_entry(dev->msi_list.next, struct msi_desc, list);
-
- irq = irq_alloc_hwirqs(nvec, dev_to_node(&dev->dev));
- if (irq == 0)
- return -ENOSPC;
-
- nvec_pow2 = __roundup_pow_of_two(nvec);
- for (sub_handle = 0; sub_handle < nvec; sub_handle++) {
- if (!sub_handle) {
- index = msi_alloc_remapped_irq(dev, irq, nvec_pow2);
- if (index < 0) {
- ret = index;
- goto error;
- }
- } else {
- ret = msi_setup_remapped_irq(dev, irq + sub_handle,
- index, sub_handle);
- if (ret < 0)
- goto error;
- }
- ret = setup_msi_irq(dev, msidesc, irq, sub_handle);
- if (ret < 0)
- goto error;
- }
- return 0;
-
-error:
- irq_free_hwirqs(irq, nvec);
-
- /*
- * Restore altered MSI descriptor fields and prevent just destroyed
- * IRQs from tearing down again in default_teardown_msi_irqs()
- */
- msidesc->irq = 0;
-
- return ret;
-}
-
-static int do_setup_msix_irqs(struct pci_dev *dev, int nvec)
-{
- int node, ret, sub_handle, index = 0;
- struct msi_desc *msidesc;
- unsigned int irq;
-
- node = dev_to_node(&dev->dev);
- sub_handle = 0;
-
- list_for_each_entry(msidesc, &dev->msi_list, list) {
-
- irq = irq_alloc_hwirq(node);
- if (irq == 0)
- return -1;
-
- if (sub_handle == 0)
- ret = index = msi_alloc_remapped_irq(dev, irq, nvec);
- else
- ret = msi_setup_remapped_irq(dev, irq, index, sub_handle);
-
- if (ret < 0)
- goto error;
-
- ret = setup_msi_irq(dev, msidesc, irq, 0);
- if (ret < 0)
- goto error;
-
- sub_handle += 1;
- irq += 1;
- }
-
- return 0;
-
-error:
- irq_free_hwirq(irq);
- return ret;
-}
-
-static int irq_remapping_setup_msi_irqs(struct pci_dev *dev,
- int nvec, int type)
-{
- if (type == PCI_CAP_ID_MSI)
- return do_setup_msi_irqs(dev, nvec);
- else
- return do_setup_msix_irqs(dev, nvec);
-}
-
-static void eoi_ioapic_pin_remapped(int apic, int pin, int vector)
-{
- /*
- * Intr-remapping uses pin number as the virtual vector
- * in the RTE. Actual vector is programmed in
- * intr-remapping table entry. Hence for the io-apic
- * EOI we use the pin number.
- */
- io_apic_eoi(apic, pin);
-}
-
static void __init irq_remapping_modify_x86_ops(void)
{
x86_io_apic_ops.disable = irq_remapping_disable_io_apic;
- x86_io_apic_ops.set_affinity = set_remapped_irq_affinity;
- x86_io_apic_ops.setup_entry = setup_ioapic_remapped_entry;
- x86_io_apic_ops.eoi_ioapic_pin = eoi_ioapic_pin_remapped;
- x86_msi.setup_msi_irqs = irq_remapping_setup_msi_irqs;
- x86_msi.setup_hpet_msi = setup_hpet_msi_remapped;
- x86_msi.compose_msi_msg = compose_remapped_msi_msg;
}
static __init int setup_nointremap(char *str)
@@ -198,6 +81,15 @@
irq_remap_broken = 1;
}
+bool irq_remapping_cap(enum irq_remap_cap cap)
+{
+ if (!remap_ops || disable_irq_post)
+ return 0;
+
+ return (remap_ops->capability & (1 << cap));
+}
+EXPORT_SYMBOL_GPL(irq_remapping_cap);
+
int __init irq_remapping_prepare(void)
{
if (disable_irq_remap)
@@ -254,113 +146,48 @@
return remap_ops->enable_faulting();
}
-int setup_ioapic_remapped_entry(int irq,
- struct IO_APIC_route_entry *entry,
- unsigned int destination, int vector,
- struct io_apic_irq_attr *attr)
-{
- if (!remap_ops->setup_ioapic_entry)
- return -ENODEV;
-
- return remap_ops->setup_ioapic_entry(irq, entry, destination,
- vector, attr);
-}
-
-static int set_remapped_irq_affinity(struct irq_data *data,
- const struct cpumask *mask, bool force)
-{
- if (!config_enabled(CONFIG_SMP) || !remap_ops->set_affinity)
- return 0;
-
- return remap_ops->set_affinity(data, mask, force);
-}
-
-void free_remapped_irq(int irq)
-{
- struct irq_cfg *cfg = irq_cfg(irq);
-
- if (irq_remapped(cfg) && remap_ops->free_irq)
- remap_ops->free_irq(irq);
-}
-
-void compose_remapped_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id)
-{
- struct irq_cfg *cfg = irq_cfg(irq);
-
- if (!irq_remapped(cfg))
- native_compose_msi_msg(pdev, irq, dest, msg, hpet_id);
- else if (remap_ops->compose_msi_msg)
- remap_ops->compose_msi_msg(pdev, irq, dest, msg, hpet_id);
-}
-
-static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec)
-{
- if (!remap_ops->msi_alloc_irq)
- return -ENODEV;
-
- return remap_ops->msi_alloc_irq(pdev, irq, nvec);
-}
-
-static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq,
- int index, int sub_handle)
-{
- if (!remap_ops->msi_setup_irq)
- return -ENODEV;
-
- return remap_ops->msi_setup_irq(pdev, irq, index, sub_handle);
-}
-
-int setup_hpet_msi_remapped(unsigned int irq, unsigned int id)
-{
- int ret;
-
- if (!remap_ops->alloc_hpet_msi)
- return -ENODEV;
-
- ret = remap_ops->alloc_hpet_msi(irq, id);
- if (ret)
- return -EINVAL;
-
- return default_setup_hpet_msi(irq, id);
-}
-
void panic_if_irq_remap(const char *msg)
{
if (irq_remapping_enabled)
panic(msg);
}
-static void ir_ack_apic_edge(struct irq_data *data)
+void ir_ack_apic_edge(struct irq_data *data)
{
ack_APIC_irq();
}
-static void ir_ack_apic_level(struct irq_data *data)
+/**
+ * irq_remapping_get_ir_irq_domain - Get the irqdomain associated with the IOMMU
+ * device serving request @info
+ * @info: interrupt allocation information, used to identify the IOMMU device
+ *
+ * It's used to get parent irqdomain for HPET and IOAPIC irqdomains.
+ * Returns pointer to IRQ domain, or NULL on failure.
+ */
+struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info)
{
- ack_APIC_irq();
- eoi_ioapic_irq(data->irq, irqd_cfg(data));
+ if (!remap_ops || !remap_ops->get_ir_irq_domain)
+ return NULL;
+
+ return remap_ops->get_ir_irq_domain(info);
}
-static void ir_print_prefix(struct irq_data *data, struct seq_file *p)
+/**
+ * irq_remapping_get_irq_domain - Get the irqdomain serving the request @info
+ * @info: interrupt allocation information, used to identify the IOMMU device
+ *
+ * There will be one PCI MSI/MSIX irqdomain associated with each interrupt
+ * remapping device, so this interface is used to retrieve the PCI MSI/MSIX
+ * irqdomain serving request @info.
+ * Returns pointer to IRQ domain, or NULL on failure.
+ */
+struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info)
{
- seq_printf(p, " IR-%s", data->chip->name);
-}
+ if (!remap_ops || !remap_ops->get_irq_domain)
+ return NULL;
-void irq_remap_modify_chip_defaults(struct irq_chip *chip)
-{
- chip->irq_print_chip = ir_print_prefix;
- chip->irq_ack = ir_ack_apic_edge;
- chip->irq_eoi = ir_ack_apic_level;
- chip->irq_set_affinity = x86_io_apic_ops.set_affinity;
-}
-
-bool setup_remapped_irq(int irq, struct irq_cfg *cfg, struct irq_chip *chip)
-{
- if (!irq_remapped(cfg))
- return false;
- irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- irq_remap_modify_chip_defaults(chip);
- return true;
+ return remap_ops->get_irq_domain(info);
}
diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h
index 7c70cc2..039c7af 100644
--- a/drivers/iommu/irq_remapping.h
+++ b/drivers/iommu/irq_remapping.h
@@ -24,19 +24,22 @@
#ifdef CONFIG_IRQ_REMAP
-struct IO_APIC_route_entry;
-struct io_apic_irq_attr;
struct irq_data;
-struct cpumask;
-struct pci_dev;
struct msi_msg;
+struct irq_domain;
+struct irq_alloc_info;
extern int irq_remap_broken;
extern int disable_sourceid_checking;
extern int no_x2apic_optout;
extern int irq_remapping_enabled;
+extern int disable_irq_post;
+
struct irq_remap_ops {
+ /* The supported capabilities */
+ int capability;
+
/* Initializes hardware and makes it ready for remapping interrupts */
int (*prepare)(void);
@@ -52,40 +55,23 @@
/* Enable fault handling */
int (*enable_faulting)(void);
- /* IO-APIC setup routine */
- int (*setup_ioapic_entry)(int irq, struct IO_APIC_route_entry *,
- unsigned int, int,
- struct io_apic_irq_attr *);
+ /* Get the irqdomain associated the IOMMU device */
+ struct irq_domain *(*get_ir_irq_domain)(struct irq_alloc_info *);
- /* Set the CPU affinity of a remapped interrupt */
- int (*set_affinity)(struct irq_data *data, const struct cpumask *mask,
- bool force);
-
- /* Free an IRQ */
- int (*free_irq)(int);
-
- /* Create MSI msg to use for interrupt remapping */
- void (*compose_msi_msg)(struct pci_dev *,
- unsigned int, unsigned int,
- struct msi_msg *, u8);
-
- /* Allocate remapping resources for MSI */
- int (*msi_alloc_irq)(struct pci_dev *, int, int);
-
- /* Setup the remapped MSI irq */
- int (*msi_setup_irq)(struct pci_dev *, unsigned int, int, int);
-
- /* Setup interrupt remapping for an HPET MSI */
- int (*alloc_hpet_msi)(unsigned int, unsigned int);
+ /* Get the MSI irqdomain associated with the IOMMU device */
+ struct irq_domain *(*get_irq_domain)(struct irq_alloc_info *);
};
extern struct irq_remap_ops intel_irq_remap_ops;
extern struct irq_remap_ops amd_iommu_irq_ops;
+extern void ir_ack_apic_edge(struct irq_data *data);
+
#else /* CONFIG_IRQ_REMAP */
#define irq_remapping_enabled 0
#define irq_remap_broken 0
+#define disable_irq_post 1
#endif /* CONFIG_IRQ_REMAP */
diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c
index 7dc93aa..312ffd3 100644
--- a/drivers/lguest/core.c
+++ b/drivers/lguest/core.c
@@ -173,7 +173,7 @@
bool lguest_address_ok(const struct lguest *lg,
unsigned long addr, unsigned long len)
{
- return (addr+len) / PAGE_SIZE < lg->pfn_limit && (addr+len >= addr);
+ return addr+len <= lg->pfn_limit * PAGE_SIZE && (addr+len >= addr);
}
/*
diff --git a/drivers/lguest/interrupts_and_traps.c b/drivers/lguest/interrupts_and_traps.c
index 5e7559b..eb934b0 100644
--- a/drivers/lguest/interrupts_and_traps.c
+++ b/drivers/lguest/interrupts_and_traps.c
@@ -20,7 +20,7 @@
#include "lg.h"
/* Allow Guests to use a non-128 (ie. non-Linux) syscall trap. */
-static unsigned int syscall_vector = SYSCALL_VECTOR;
+static unsigned int syscall_vector = IA32_SYSCALL_VECTOR;
module_param(syscall_vector, uint, 0444);
/* The address of the interrupt handler is split into two bits: */
@@ -333,8 +333,8 @@
*/
static bool could_be_syscall(unsigned int num)
{
- /* Normal Linux SYSCALL_VECTOR or reserved vector? */
- return num == SYSCALL_VECTOR || num == syscall_vector;
+ /* Normal Linux IA32_SYSCALL_VECTOR or reserved vector? */
+ return num == IA32_SYSCALL_VECTOR || num == syscall_vector;
}
/* The syscall vector it wants must be unused by Host. */
@@ -351,7 +351,7 @@
int init_interrupts(void)
{
/* If they want some strange system call vector, reserve it now */
- if (syscall_vector != SYSCALL_VECTOR) {
+ if (syscall_vector != IA32_SYSCALL_VECTOR) {
if (test_bit(syscall_vector, used_vectors) ||
vector_used_by_percpu_irq(syscall_vector)) {
printk(KERN_ERR "lg: couldn't reserve syscall %u\n",
@@ -366,7 +366,7 @@
void free_interrupts(void)
{
- if (syscall_vector != SYSCALL_VECTOR)
+ if (syscall_vector != IA32_SYSCALL_VECTOR)
clear_bit(syscall_vector, used_vectors);
}
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 6395347..eff7bdd 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -429,9 +429,11 @@
/* blk-mq request-based interface */
*__clone = blk_get_request(bdev_get_queue(bdev),
rq_data_dir(rq), GFP_ATOMIC);
- if (IS_ERR(*__clone))
+ if (IS_ERR(*__clone)) {
/* ENOMEM, requeue */
+ clear_mapinfo(m, map_context);
return r;
+ }
(*__clone)->bio = (*__clone)->biotail = NULL;
(*__clone)->rq_disk = bdev->bd_disk;
(*__clone)->cmd_flags |= REQ_FAILFAST_TRANSPORT;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index d9b00b8..16ba55a 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -820,6 +820,12 @@
}
EXPORT_SYMBOL(dm_consume_args);
+static bool __table_type_request_based(unsigned table_type)
+{
+ return (table_type == DM_TYPE_REQUEST_BASED ||
+ table_type == DM_TYPE_MQ_REQUEST_BASED);
+}
+
static int dm_table_set_type(struct dm_table *t)
{
unsigned i;
@@ -852,8 +858,7 @@
* Determine the type from the live device.
* Default to bio-based if device is new.
*/
- if (live_md_type == DM_TYPE_REQUEST_BASED ||
- live_md_type == DM_TYPE_MQ_REQUEST_BASED)
+ if (__table_type_request_based(live_md_type))
request_based = 1;
else
bio_based = 1;
@@ -903,7 +908,7 @@
}
t->type = DM_TYPE_MQ_REQUEST_BASED;
- } else if (hybrid && list_empty(devices) && live_md_type != DM_TYPE_NONE) {
+ } else if (list_empty(devices) && __table_type_request_based(live_md_type)) {
/* inherit live MD type */
t->type = live_md_type;
@@ -925,10 +930,7 @@
bool dm_table_request_based(struct dm_table *t)
{
- unsigned table_type = dm_table_get_type(t);
-
- return (table_type == DM_TYPE_REQUEST_BASED ||
- table_type == DM_TYPE_MQ_REQUEST_BASED);
+ return __table_type_request_based(dm_table_get_type(t));
}
bool dm_table_mq_request_based(struct dm_table *t)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index a930b72..2caf492 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1082,13 +1082,11 @@
dm_put(md);
}
-static void free_rq_clone(struct request *clone, bool must_be_mapped)
+static void free_rq_clone(struct request *clone)
{
struct dm_rq_target_io *tio = clone->end_io_data;
struct mapped_device *md = tio->md;
- WARN_ON_ONCE(must_be_mapped && !clone->q);
-
blk_rq_unprep_clone(clone);
if (md->type == DM_TYPE_MQ_REQUEST_BASED)
@@ -1132,7 +1130,7 @@
rq->sense_len = clone->sense_len;
}
- free_rq_clone(clone, true);
+ free_rq_clone(clone);
if (!rq->q->mq_ops)
blk_end_request_all(rq, error);
else
@@ -1151,7 +1149,7 @@
}
if (clone)
- free_rq_clone(clone, false);
+ free_rq_clone(clone);
}
/*
@@ -1164,6 +1162,7 @@
spin_lock_irqsave(q->queue_lock, flags);
blk_requeue_request(q, rq);
+ blk_run_queue_async(q);
spin_unlock_irqrestore(q->queue_lock, flags);
}
@@ -1724,8 +1723,7 @@
struct mapped_device *md = q->queuedata;
struct dm_table *map = dm_get_live_table_fast(md);
struct dm_target *ti;
- sector_t max_sectors;
- int max_size = 0;
+ sector_t max_sectors, max_size = 0;
if (unlikely(!map))
goto out;
@@ -1740,8 +1738,16 @@
max_sectors = min(max_io_len(bvm->bi_sector, ti),
(sector_t) queue_max_sectors(q));
max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size;
- if (unlikely(max_size < 0)) /* this shouldn't _ever_ happen */
- max_size = 0;
+
+ /*
+ * FIXME: this stop-gap fix _must_ be cleaned up (by passing a sector_t
+ * to the targets' merge function since it holds sectors not bytes).
+ * Just doing this as an interim fix for stable@ because the more
+ * comprehensive cleanup of switching to sector_t will impact every
+ * DM target that implements a ->merge hook.
+ */
+ if (max_size > INT_MAX)
+ max_size = INT_MAX;
/*
* merge_bvec_fn() returns number of bytes
@@ -1749,7 +1755,7 @@
* max is precomputed maximal io size
*/
if (max_size && ti->type->merge)
- max_size = ti->type->merge(ti, bvm, biovec, max_size);
+ max_size = ti->type->merge(ti, bvm, biovec, (int) max_size);
/*
* If the target doesn't support merge method and some of the devices
* provided their merge_bvec method (we know this by looking for the
@@ -1971,8 +1977,8 @@
dm_kill_unmapped_request(rq, r);
return r;
}
- if (IS_ERR(clone))
- return DM_MAPIO_REQUEUE;
+ if (r != DM_MAPIO_REMAPPED)
+ return r;
if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
/* -ENOMEM */
ti->type->release_clone_rq(clone);
@@ -2753,13 +2759,15 @@
if (dm_table_get_type(map) == DM_TYPE_REQUEST_BASED) {
/* clone request is allocated at the end of the pdu */
tio->clone = (void *)blk_mq_rq_to_pdu(rq) + sizeof(struct dm_rq_target_io);
- if (!clone_rq(rq, md, tio, GFP_ATOMIC))
- return BLK_MQ_RQ_QUEUE_BUSY;
+ (void) clone_rq(rq, md, tio, GFP_ATOMIC);
queue_kthread_work(&md->kworker, &tio->work);
} else {
/* Direct call is fine since .queue_rq allows allocations */
- if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE)
- dm_requeue_unmapped_original_request(md, rq);
+ if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
+ /* Undo dm_start_request() before requeuing */
+ rq_completed(md, rq_data_dir(rq), false);
+ return BLK_MQ_RQ_QUEUE_BUSY;
+ }
}
return BLK_MQ_RQ_QUEUE_OK;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 593a024..2750630 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4211,12 +4211,12 @@
if (!mddev->pers || !mddev->pers->sync_request)
return -EINVAL;
- if (cmd_match(page, "frozen"))
- set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
- else
- clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
if (cmd_match(page, "idle") || cmd_match(page, "frozen")) {
+ if (cmd_match(page, "frozen"))
+ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ else
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
flush_workqueue(md_misc_wq);
if (mddev->sync_thread) {
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
@@ -4229,16 +4229,17 @@
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
return -EBUSY;
else if (cmd_match(page, "resync"))
- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
else if (cmd_match(page, "recover")) {
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
} else if (cmd_match(page, "reshape")) {
int err;
if (mddev->pers->start_reshape == NULL)
return -EINVAL;
err = mddev_lock(mddev);
if (!err) {
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
err = mddev->pers->start_reshape(mddev);
mddev_unlock(mddev);
}
@@ -4250,6 +4251,7 @@
set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
else if (!cmd_match(page, "repair"))
return -EINVAL;
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index b9f2b9c..553d54b 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -749,6 +749,7 @@
static bool stripe_can_batch(struct stripe_head *sh)
{
return test_bit(STRIPE_BATCH_READY, &sh->state) &&
+ !test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
is_full_stripe_write(sh);
}
@@ -837,6 +838,15 @@
< IO_THRESHOLD)
md_wakeup_thread(conf->mddev->thread);
+ if (test_and_clear_bit(STRIPE_BIT_DELAY, &sh->state)) {
+ int seq = sh->bm_seq;
+ if (test_bit(STRIPE_BIT_DELAY, &sh->batch_head->state) &&
+ sh->batch_head->bm_seq > seq)
+ seq = sh->batch_head->bm_seq;
+ set_bit(STRIPE_BIT_DELAY, &sh->batch_head->state);
+ sh->batch_head->bm_seq = seq;
+ }
+
atomic_inc(&sh->count);
unlock_out:
unlock_two_stripes(head, sh);
@@ -2987,14 +2997,32 @@
pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
(unsigned long long)(*bip)->bi_iter.bi_sector,
(unsigned long long)sh->sector, dd_idx);
- spin_unlock_irq(&sh->stripe_lock);
if (conf->mddev->bitmap && firstwrite) {
+ /* Cannot hold spinlock over bitmap_startwrite,
+ * but must ensure this isn't added to a batch until
+ * we have added to the bitmap and set bm_seq.
+ * So set STRIPE_BITMAP_PENDING to prevent
+ * batching.
+ * If multiple add_stripe_bio() calls race here they
+ * much all set STRIPE_BITMAP_PENDING. So only the first one
+ * to complete "bitmap_startwrite" gets to set
+ * STRIPE_BIT_DELAY. This is important as once a stripe
+ * is added to a batch, STRIPE_BIT_DELAY cannot be changed
+ * any more.
+ */
+ set_bit(STRIPE_BITMAP_PENDING, &sh->state);
+ spin_unlock_irq(&sh->stripe_lock);
bitmap_startwrite(conf->mddev->bitmap, sh->sector,
STRIPE_SECTORS, 0);
- sh->bm_seq = conf->seq_flush+1;
- set_bit(STRIPE_BIT_DELAY, &sh->state);
+ spin_lock_irq(&sh->stripe_lock);
+ clear_bit(STRIPE_BITMAP_PENDING, &sh->state);
+ if (!sh->batch_head) {
+ sh->bm_seq = conf->seq_flush+1;
+ set_bit(STRIPE_BIT_DELAY, &sh->state);
+ }
}
+ spin_unlock_irq(&sh->stripe_lock);
if (stripe_can_batch(sh))
stripe_add_to_batch_list(conf, sh);
@@ -3392,6 +3420,8 @@
set_bit(STRIPE_HANDLE, &sh->state);
}
+static void break_stripe_batch_list(struct stripe_head *head_sh,
+ unsigned long handle_flags);
/* handle_stripe_clean_event
* any written block on an uptodate or failed drive can be returned.
* Note that if we 'wrote' to a failed drive, it will be UPTODATE, but
@@ -3405,7 +3435,6 @@
int discard_pending = 0;
struct stripe_head *head_sh = sh;
bool do_endio = false;
- int wakeup_nr = 0;
for (i = disks; i--; )
if (sh->dev[i].written) {
@@ -3494,44 +3523,8 @@
if (atomic_dec_and_test(&conf->pending_full_writes))
md_wakeup_thread(conf->mddev->thread);
- if (!head_sh->batch_head || !do_endio)
- return;
- for (i = 0; i < head_sh->disks; i++) {
- if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags))
- wakeup_nr++;
- }
- while (!list_empty(&head_sh->batch_list)) {
- int i;
- sh = list_first_entry(&head_sh->batch_list,
- struct stripe_head, batch_list);
- list_del_init(&sh->batch_list);
-
- set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG,
- head_sh->state & ~((1 << STRIPE_ACTIVE) |
- (1 << STRIPE_PREREAD_ACTIVE) |
- STRIPE_EXPAND_SYNC_FLAG));
- sh->check_state = head_sh->check_state;
- sh->reconstruct_state = head_sh->reconstruct_state;
- for (i = 0; i < sh->disks; i++) {
- if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
- wakeup_nr++;
- sh->dev[i].flags = head_sh->dev[i].flags;
- }
-
- spin_lock_irq(&sh->stripe_lock);
- sh->batch_head = NULL;
- spin_unlock_irq(&sh->stripe_lock);
- if (sh->state & STRIPE_EXPAND_SYNC_FLAG)
- set_bit(STRIPE_HANDLE, &sh->state);
- release_stripe(sh);
- }
-
- spin_lock_irq(&head_sh->stripe_lock);
- head_sh->batch_head = NULL;
- spin_unlock_irq(&head_sh->stripe_lock);
- wake_up_nr(&conf->wait_for_overlap, wakeup_nr);
- if (head_sh->state & STRIPE_EXPAND_SYNC_FLAG)
- set_bit(STRIPE_HANDLE, &head_sh->state);
+ if (head_sh->batch_head && do_endio)
+ break_stripe_batch_list(head_sh, STRIPE_EXPAND_SYNC_FLAGS);
}
static void handle_stripe_dirtying(struct r5conf *conf,
@@ -4172,9 +4165,13 @@
static int clear_batch_ready(struct stripe_head *sh)
{
+ /* Return '1' if this is a member of batch, or
+ * '0' if it is a lone stripe or a head which can now be
+ * handled.
+ */
struct stripe_head *tmp;
if (!test_and_clear_bit(STRIPE_BATCH_READY, &sh->state))
- return 0;
+ return (sh->batch_head && sh->batch_head != sh);
spin_lock(&sh->stripe_lock);
if (!sh->batch_head) {
spin_unlock(&sh->stripe_lock);
@@ -4202,38 +4199,65 @@
return 0;
}
-static void check_break_stripe_batch_list(struct stripe_head *sh)
+static void break_stripe_batch_list(struct stripe_head *head_sh,
+ unsigned long handle_flags)
{
- struct stripe_head *head_sh, *next;
+ struct stripe_head *sh, *next;
int i;
-
- if (!test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state))
- return;
-
- head_sh = sh;
+ int do_wakeup = 0;
list_for_each_entry_safe(sh, next, &head_sh->batch_list, batch_list) {
list_del_init(&sh->batch_list);
- set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG,
- head_sh->state & ~((1 << STRIPE_ACTIVE) |
- (1 << STRIPE_PREREAD_ACTIVE) |
- (1 << STRIPE_DEGRADED) |
- STRIPE_EXPAND_SYNC_FLAG));
+ WARN_ON_ONCE(sh->state & ((1 << STRIPE_ACTIVE) |
+ (1 << STRIPE_SYNCING) |
+ (1 << STRIPE_REPLACED) |
+ (1 << STRIPE_PREREAD_ACTIVE) |
+ (1 << STRIPE_DELAYED) |
+ (1 << STRIPE_BIT_DELAY) |
+ (1 << STRIPE_FULL_WRITE) |
+ (1 << STRIPE_BIOFILL_RUN) |
+ (1 << STRIPE_COMPUTE_RUN) |
+ (1 << STRIPE_OPS_REQ_PENDING) |
+ (1 << STRIPE_DISCARD) |
+ (1 << STRIPE_BATCH_READY) |
+ (1 << STRIPE_BATCH_ERR) |
+ (1 << STRIPE_BITMAP_PENDING)));
+ WARN_ON_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) |
+ (1 << STRIPE_REPLACED)));
+
+ set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
+ (1 << STRIPE_DEGRADED)),
+ head_sh->state & (1 << STRIPE_INSYNC));
+
sh->check_state = head_sh->check_state;
sh->reconstruct_state = head_sh->reconstruct_state;
- for (i = 0; i < sh->disks; i++)
+ for (i = 0; i < sh->disks; i++) {
+ if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
+ do_wakeup = 1;
sh->dev[i].flags = head_sh->dev[i].flags &
(~((1 << R5_WriteError) | (1 << R5_Overlap)));
-
+ }
spin_lock_irq(&sh->stripe_lock);
sh->batch_head = NULL;
spin_unlock_irq(&sh->stripe_lock);
-
- set_bit(STRIPE_HANDLE, &sh->state);
+ if (handle_flags == 0 ||
+ sh->state & handle_flags)
+ set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
+ spin_lock_irq(&head_sh->stripe_lock);
+ head_sh->batch_head = NULL;
+ spin_unlock_irq(&head_sh->stripe_lock);
+ for (i = 0; i < head_sh->disks; i++)
+ if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags))
+ do_wakeup = 1;
+ if (head_sh->state & handle_flags)
+ set_bit(STRIPE_HANDLE, &head_sh->state);
+
+ if (do_wakeup)
+ wake_up(&head_sh->raid_conf->wait_for_overlap);
}
static void handle_stripe(struct stripe_head *sh)
@@ -4258,7 +4282,8 @@
return;
}
- check_break_stripe_batch_list(sh);
+ if (test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state))
+ break_stripe_batch_list(sh, 0);
if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) {
spin_lock(&sh->stripe_lock);
@@ -4312,6 +4337,7 @@
if (s.failed > conf->max_degraded) {
sh->check_state = 0;
sh->reconstruct_state = 0;
+ break_stripe_batch_list(sh, 0);
if (s.to_read+s.to_write+s.written)
handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
if (s.syncing + s.replacing)
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 7dc0dd8..896d603 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -337,9 +337,12 @@
STRIPE_ON_RELEASE_LIST,
STRIPE_BATCH_READY,
STRIPE_BATCH_ERR,
+ STRIPE_BITMAP_PENDING, /* Being added to bitmap, don't add
+ * to batch yet.
+ */
};
-#define STRIPE_EXPAND_SYNC_FLAG \
+#define STRIPE_EXPAND_SYNC_FLAGS \
((1 << STRIPE_EXPAND_SOURCE) |\
(1 << STRIPE_EXPAND_READY) |\
(1 << STRIPE_EXPANDING) |\
diff --git a/drivers/mfd/da9052-core.c b/drivers/mfd/da9052-core.c
index ae498b5..46e3840 100644
--- a/drivers/mfd/da9052-core.c
+++ b/drivers/mfd/da9052-core.c
@@ -433,6 +433,10 @@
static const struct mfd_cell da9052_subdev_info[] = {
{
.name = "da9052-regulator",
+ .id = 0,
+ },
+ {
+ .name = "da9052-regulator",
.id = 1,
},
{
@@ -484,10 +488,6 @@
.id = 13,
},
{
- .name = "da9052-regulator",
- .id = 14,
- },
- {
.name = "da9052-onkey",
},
{
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index a3b0f7a..1f82a04 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -1774,7 +1774,7 @@
int stats_state;
/* used for synchronization of concurrent threads statistics handling */
- struct mutex stats_lock;
+ struct semaphore stats_lock;
/* used by dmae command loader */
struct dmae_command stats_dmae;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index fd52ce9..33501bc 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -12054,7 +12054,7 @@
mutex_init(&bp->port.phy_mutex);
mutex_init(&bp->fw_mb_mutex);
mutex_init(&bp->drv_info_mutex);
- mutex_init(&bp->stats_lock);
+ sema_init(&bp->stats_lock, 1);
bp->drv_info_mng_owner = false;
INIT_DELAYED_WORK(&bp->sp_task, bnx2x_sp_task);
@@ -13690,9 +13690,10 @@
cancel_delayed_work_sync(&bp->sp_task);
cancel_delayed_work_sync(&bp->period_task);
- mutex_lock(&bp->stats_lock);
- bp->stats_state = STATS_STATE_DISABLED;
- mutex_unlock(&bp->stats_lock);
+ if (!down_timeout(&bp->stats_lock, HZ / 10)) {
+ bp->stats_state = STATS_STATE_DISABLED;
+ up(&bp->stats_lock);
+ }
bnx2x_save_statistics(bp);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
index 266b055..69d699f0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
@@ -1372,19 +1372,23 @@
* that context in case someone is in the middle of a transition.
* For other events, wait a bit until lock is taken.
*/
- if (!mutex_trylock(&bp->stats_lock)) {
+ if (down_trylock(&bp->stats_lock)) {
if (event == STATS_EVENT_UPDATE)
return;
DP(BNX2X_MSG_STATS,
"Unlikely stats' lock contention [event %d]\n", event);
- mutex_lock(&bp->stats_lock);
+ if (unlikely(down_timeout(&bp->stats_lock, HZ / 10))) {
+ BNX2X_ERR("Failed to take stats lock [event %d]\n",
+ event);
+ return;
+ }
}
bnx2x_stats_stm[state][event].action(bp);
bp->stats_state = bnx2x_stats_stm[state][event].next_state;
- mutex_unlock(&bp->stats_lock);
+ up(&bp->stats_lock);
if ((event != STATS_EVENT_UPDATE) || netif_msg_timer(bp))
DP(BNX2X_MSG_STATS, "state %d -> event %d -> state %d\n",
@@ -1970,7 +1974,11 @@
/* Wait for statistics to end [while blocking further requests],
* then run supplied function 'safely'.
*/
- mutex_lock(&bp->stats_lock);
+ rc = down_timeout(&bp->stats_lock, HZ / 10);
+ if (unlikely(rc)) {
+ BNX2X_ERR("Failed to take statistics lock for safe execution\n");
+ goto out_no_lock;
+ }
bnx2x_stats_comp(bp);
while (bp->stats_pending && cnt--)
@@ -1988,7 +1996,7 @@
/* No need to restart statistics - if they're enabled, the timer
* will restart the statistics.
*/
- mutex_unlock(&bp->stats_lock);
-
+ up(&bp->stats_lock);
+out_no_lock:
return rc;
}
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index 594a2ab..68f3c13 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -2414,7 +2414,7 @@
if (status == BFA_STATUS_OK)
bfa_ioc_lpu_start(ioc);
else
- bfa_nw_iocpf_timeout(ioc);
+ bfa_fsm_send_event(&ioc->iocpf, IOCPF_E_TIMEOUT);
return status;
}
@@ -3029,7 +3029,7 @@
}
if (ioc->iocpf.poll_time >= BFA_IOC_TOV) {
- bfa_nw_iocpf_timeout(ioc);
+ bfa_fsm_send_event(&ioc->iocpf, IOCPF_E_TIMEOUT);
} else {
ioc->iocpf.poll_time += BFA_IOC_POLL_TOV;
mod_timer(&ioc->iocpf_timer, jiffies +
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 37072a8..caae6cb 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -3701,10 +3701,6 @@
setup_timer(&bnad->bna.ioceth.ioc.sem_timer, bnad_iocpf_sem_timeout,
((unsigned long)bnad));
- /* Now start the timer before calling IOC */
- mod_timer(&bnad->bna.ioceth.ioc.iocpf_timer,
- jiffies + msecs_to_jiffies(BNA_IOC_TIMER_FREQ));
-
/*
* Start the chip
* If the call back comes with error, we bail out.
diff --git a/drivers/net/ethernet/brocade/bna/cna_fwimg.c b/drivers/net/ethernet/brocade/bna/cna_fwimg.c
index ebf462d..badea36 100644
--- a/drivers/net/ethernet/brocade/bna/cna_fwimg.c
+++ b/drivers/net/ethernet/brocade/bna/cna_fwimg.c
@@ -30,6 +30,7 @@
u32 *bfi_image_size, char *fw_name)
{
const struct firmware *fw;
+ u32 n;
if (request_firmware(&fw, fw_name, &pdev->dev)) {
pr_alert("Can't locate firmware %s\n", fw_name);
@@ -40,6 +41,12 @@
*bfi_image_size = fw->size/sizeof(u32);
bfi_fw = fw;
+ /* Convert loaded firmware to host order as it is stored in file
+ * as sequence of LE32 integers.
+ */
+ for (n = 0; n < *bfi_image_size; n++)
+ le32_to_cpus(*bfi_image + n);
+
return *bfi_image;
error:
return NULL;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index a6dcbf8..6f9ffb9 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -2358,11 +2358,11 @@
adapter->cfg_num_qs);
for_all_evt_queues(adapter, eqo, i) {
+ int numa_node = dev_to_node(&adapter->pdev->dev);
if (!zalloc_cpumask_var(&eqo->affinity_mask, GFP_KERNEL))
return -ENOMEM;
- cpumask_set_cpu_local_first(i, dev_to_node(&adapter->pdev->dev),
- eqo->affinity_mask);
-
+ cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+ eqo->affinity_mask);
netif_napi_add(adapter->netdev, &eqo->napi, be_poll,
BE_NAPI_WEIGHT);
napi_hash_add(&eqo->napi);
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index de79193..b9df0cb 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -2084,12 +2084,8 @@
static int emac_get_regs_len(struct emac_instance *dev)
{
- if (emac_has_feature(dev, EMAC_FTR_EMAC4))
return sizeof(struct emac_ethtool_regs_subhdr) +
- EMAC4_ETHTOOL_REGS_SIZE(dev);
- else
- return sizeof(struct emac_ethtool_regs_subhdr) +
- EMAC_ETHTOOL_REGS_SIZE(dev);
+ sizeof(struct emac_regs);
}
static int emac_ethtool_get_regs_len(struct net_device *ndev)
@@ -2114,15 +2110,15 @@
struct emac_ethtool_regs_subhdr *hdr = buf;
hdr->index = dev->cell_index;
- if (emac_has_feature(dev, EMAC_FTR_EMAC4)) {
+ if (emac_has_feature(dev, EMAC_FTR_EMAC4SYNC)) {
+ hdr->version = EMAC4SYNC_ETHTOOL_REGS_VER;
+ } else if (emac_has_feature(dev, EMAC_FTR_EMAC4)) {
hdr->version = EMAC4_ETHTOOL_REGS_VER;
- memcpy_fromio(hdr + 1, dev->emacp, EMAC4_ETHTOOL_REGS_SIZE(dev));
- return (void *)(hdr + 1) + EMAC4_ETHTOOL_REGS_SIZE(dev);
} else {
hdr->version = EMAC_ETHTOOL_REGS_VER;
- memcpy_fromio(hdr + 1, dev->emacp, EMAC_ETHTOOL_REGS_SIZE(dev));
- return (void *)(hdr + 1) + EMAC_ETHTOOL_REGS_SIZE(dev);
}
+ memcpy_fromio(hdr + 1, dev->emacp, sizeof(struct emac_regs));
+ return (void *)(hdr + 1) + sizeof(struct emac_regs);
}
static void emac_ethtool_get_regs(struct net_device *ndev,
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 67f342a..28df374 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -461,10 +461,7 @@
};
#define EMAC_ETHTOOL_REGS_VER 0
-#define EMAC_ETHTOOL_REGS_SIZE(dev) ((dev)->rsrc_regs.end - \
- (dev)->rsrc_regs.start + 1)
-#define EMAC4_ETHTOOL_REGS_VER 1
-#define EMAC4_ETHTOOL_REGS_SIZE(dev) ((dev)->rsrc_regs.end - \
- (dev)->rsrc_regs.start + 1)
+#define EMAC4_ETHTOOL_REGS_VER 1
+#define EMAC4SYNC_ETHTOOL_REGS_VER 2
#endif /* __IBM_NEWEMAC_CORE_H */
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 4f7dc04..529ef05 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -714,8 +714,13 @@
msecs_to_jiffies(timeout))) {
mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n",
op);
- err = -EIO;
- goto out_reset;
+ if (op == MLX4_CMD_NOP) {
+ err = -EBUSY;
+ goto out;
+ } else {
+ err = -EIO;
+ goto out_reset;
+ }
}
err = context->result;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 32f5ec7..cf467a9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1501,17 +1501,13 @@
{
struct mlx4_en_rx_ring *ring = priv->rx_ring[ring_idx];
int numa_node = priv->mdev->dev->numa_node;
- int ret = 0;
if (!zalloc_cpumask_var(&ring->affinity_mask, GFP_KERNEL))
return -ENOMEM;
- ret = cpumask_set_cpu_local_first(ring_idx, numa_node,
- ring->affinity_mask);
- if (ret)
- free_cpumask_var(ring->affinity_mask);
-
- return ret;
+ cpumask_set_cpu(cpumask_local_spread(ring_idx, numa_node),
+ ring->affinity_mask);
+ return 0;
}
static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index f7bf312..7bed3a8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -144,9 +144,9 @@
ring->queue_index = queue_index;
if (queue_index < priv->num_tx_rings_p_up)
- cpumask_set_cpu_local_first(queue_index,
- priv->mdev->dev->numa_node,
- &ring->affinity_mask);
+ cpumask_set_cpu(cpumask_local_spread(queue_index,
+ priv->mdev->dev->numa_node),
+ &ring->affinity_mask);
*pring = ring;
return 0;
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index e0c31e3..6409a06 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -3025,9 +3025,9 @@
u8 dw, rows, cols, banks, ranks;
u32 val;
- if (size != sizeof(struct netxen_dimm_cfg)) {
+ if (size < attr->size) {
netdev_err(netdev, "Invalid size\n");
- return -1;
+ return -EINVAL;
}
memset(&dimm, 0, sizeof(struct netxen_dimm_cfg));
@@ -3137,7 +3137,7 @@
static struct bin_attribute bin_attr_dimm = {
.attr = { .name = "dimm", .mode = (S_IRUGO | S_IWUSR) },
- .size = 0,
+ .size = sizeof(struct netxen_dimm_cfg),
.read = netxen_sysfs_read_dimm,
};
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index c0ad95d..809ea461 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -224,12 +224,17 @@
}
}
-static void efx_free_rx_buffer(struct efx_rx_buffer *rx_buf)
+static void efx_free_rx_buffers(struct efx_rx_queue *rx_queue,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int num_bufs)
{
- if (rx_buf->page) {
- put_page(rx_buf->page);
- rx_buf->page = NULL;
- }
+ do {
+ if (rx_buf->page) {
+ put_page(rx_buf->page);
+ rx_buf->page = NULL;
+ }
+ rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
+ } while (--num_bufs);
}
/* Attempt to recycle the page if there is an RX recycle ring; the page can
@@ -278,7 +283,7 @@
/* If this is the last buffer in a page, unmap and free it. */
if (rx_buf->flags & EFX_RX_BUF_LAST_IN_PAGE) {
efx_unmap_rx_buffer(rx_queue->efx, rx_buf);
- efx_free_rx_buffer(rx_buf);
+ efx_free_rx_buffers(rx_queue, rx_buf, 1);
}
rx_buf->page = NULL;
}
@@ -304,10 +309,7 @@
efx_recycle_rx_pages(channel, rx_buf, n_frags);
- do {
- efx_free_rx_buffer(rx_buf);
- rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
- } while (--n_frags);
+ efx_free_rx_buffers(rx_queue, rx_buf, n_frags);
}
/**
@@ -431,11 +433,10 @@
skb = napi_get_frags(napi);
if (unlikely(!skb)) {
- while (n_frags--) {
- put_page(rx_buf->page);
- rx_buf->page = NULL;
- rx_buf = efx_rx_buf_next(&channel->rx_queue, rx_buf);
- }
+ struct efx_rx_queue *rx_queue;
+
+ rx_queue = efx_channel_get_rx_queue(channel);
+ efx_free_rx_buffers(rx_queue, rx_buf, n_frags);
return;
}
@@ -622,7 +623,10 @@
skb = efx_rx_mk_skb(channel, rx_buf, n_frags, eh, hdr_len);
if (unlikely(skb == NULL)) {
- efx_free_rx_buffer(rx_buf);
+ struct efx_rx_queue *rx_queue;
+
+ rx_queue = efx_channel_get_rx_queue(channel);
+ efx_free_rx_buffers(rx_queue, rx_buf, n_frags);
return;
}
skb_record_rx_queue(skb, channel->rx_queue.core_index);
@@ -661,8 +665,12 @@
* loopback layer, and free the rx_buf here
*/
if (unlikely(efx->loopback_selftest)) {
+ struct efx_rx_queue *rx_queue;
+
efx_loopback_rx_packet(efx, eh, rx_buf->len);
- efx_free_rx_buffer(rx_buf);
+ rx_queue = efx_channel_get_rx_queue(channel);
+ efx_free_rx_buffers(rx_queue, rx_buf,
+ channel->rx_pkt_n_frags);
goto out;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 2ac9552..73bab98 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -117,6 +117,12 @@
int use_riwt;
int irq_wake;
spinlock_t ptp_lock;
+
+#ifdef CONFIG_DEBUG_FS
+ struct dentry *dbgfs_dir;
+ struct dentry *dbgfs_rings_status;
+ struct dentry *dbgfs_dma_cap;
+#endif
};
int stmmac_mdio_unregister(struct net_device *ndev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 05c146f..2c5ce2b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -118,7 +118,7 @@
#ifdef CONFIG_DEBUG_FS
static int stmmac_init_fs(struct net_device *dev);
-static void stmmac_exit_fs(void);
+static void stmmac_exit_fs(struct net_device *dev);
#endif
#define STMMAC_COAL_TIMER(x) (jiffies + usecs_to_jiffies(x))
@@ -1916,7 +1916,7 @@
netif_carrier_off(dev);
#ifdef CONFIG_DEBUG_FS
- stmmac_exit_fs();
+ stmmac_exit_fs(dev);
#endif
stmmac_release_ptp(priv);
@@ -2508,8 +2508,6 @@
#ifdef CONFIG_DEBUG_FS
static struct dentry *stmmac_fs_dir;
-static struct dentry *stmmac_rings_status;
-static struct dentry *stmmac_dma_cap;
static void sysfs_display_ring(void *head, int size, int extend_desc,
struct seq_file *seq)
@@ -2648,36 +2646,39 @@
static int stmmac_init_fs(struct net_device *dev)
{
- /* Create debugfs entries */
- stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL);
+ struct stmmac_priv *priv = netdev_priv(dev);
- if (!stmmac_fs_dir || IS_ERR(stmmac_fs_dir)) {
- pr_err("ERROR %s, debugfs create directory failed\n",
- STMMAC_RESOURCE_NAME);
+ /* Create per netdev entries */
+ priv->dbgfs_dir = debugfs_create_dir(dev->name, stmmac_fs_dir);
+
+ if (!priv->dbgfs_dir || IS_ERR(priv->dbgfs_dir)) {
+ pr_err("ERROR %s/%s, debugfs create directory failed\n",
+ STMMAC_RESOURCE_NAME, dev->name);
return -ENOMEM;
}
/* Entry to report DMA RX/TX rings */
- stmmac_rings_status = debugfs_create_file("descriptors_status",
- S_IRUGO, stmmac_fs_dir, dev,
- &stmmac_rings_status_fops);
+ priv->dbgfs_rings_status =
+ debugfs_create_file("descriptors_status", S_IRUGO,
+ priv->dbgfs_dir, dev,
+ &stmmac_rings_status_fops);
- if (!stmmac_rings_status || IS_ERR(stmmac_rings_status)) {
+ if (!priv->dbgfs_rings_status || IS_ERR(priv->dbgfs_rings_status)) {
pr_info("ERROR creating stmmac ring debugfs file\n");
- debugfs_remove(stmmac_fs_dir);
+ debugfs_remove_recursive(priv->dbgfs_dir);
return -ENOMEM;
}
/* Entry to report the DMA HW features */
- stmmac_dma_cap = debugfs_create_file("dma_cap", S_IRUGO, stmmac_fs_dir,
- dev, &stmmac_dma_cap_fops);
+ priv->dbgfs_dma_cap = debugfs_create_file("dma_cap", S_IRUGO,
+ priv->dbgfs_dir,
+ dev, &stmmac_dma_cap_fops);
- if (!stmmac_dma_cap || IS_ERR(stmmac_dma_cap)) {
+ if (!priv->dbgfs_dma_cap || IS_ERR(priv->dbgfs_dma_cap)) {
pr_info("ERROR creating stmmac MMC debugfs file\n");
- debugfs_remove(stmmac_rings_status);
- debugfs_remove(stmmac_fs_dir);
+ debugfs_remove_recursive(priv->dbgfs_dir);
return -ENOMEM;
}
@@ -2685,11 +2686,11 @@
return 0;
}
-static void stmmac_exit_fs(void)
+static void stmmac_exit_fs(struct net_device *dev)
{
- debugfs_remove(stmmac_rings_status);
- debugfs_remove(stmmac_dma_cap);
- debugfs_remove(stmmac_fs_dir);
+ struct stmmac_priv *priv = netdev_priv(dev);
+
+ debugfs_remove_recursive(priv->dbgfs_dir);
}
#endif /* CONFIG_DEBUG_FS */
@@ -3149,6 +3150,35 @@
__setup("stmmaceth=", stmmac_cmdline_opt);
#endif /* MODULE */
+static int __init stmmac_init(void)
+{
+#ifdef CONFIG_DEBUG_FS
+ /* Create debugfs main directory if it doesn't exist yet */
+ if (!stmmac_fs_dir) {
+ stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL);
+
+ if (!stmmac_fs_dir || IS_ERR(stmmac_fs_dir)) {
+ pr_err("ERROR %s, debugfs create directory failed\n",
+ STMMAC_RESOURCE_NAME);
+
+ return -ENOMEM;
+ }
+ }
+#endif
+
+ return 0;
+}
+
+static void __exit stmmac_exit(void)
+{
+#ifdef CONFIG_DEBUG_FS
+ debugfs_remove_recursive(stmmac_fs_dir);
+#endif
+}
+
+module_init(stmmac_init)
+module_exit(stmmac_exit)
+
MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet device driver");
MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/amd-xgbe-phy.c b/drivers/net/phy/amd-xgbe-phy.c
index fb276f6..34a75cb 100644
--- a/drivers/net/phy/amd-xgbe-phy.c
+++ b/drivers/net/phy/amd-xgbe-phy.c
@@ -755,6 +755,45 @@
return ret;
}
+static bool amd_xgbe_phy_use_xgmii_mode(struct phy_device *phydev)
+{
+ if (phydev->autoneg == AUTONEG_ENABLE) {
+ if (phydev->advertising & ADVERTISED_10000baseKR_Full)
+ return true;
+ } else {
+ if (phydev->speed == SPEED_10000)
+ return true;
+ }
+
+ return false;
+}
+
+static bool amd_xgbe_phy_use_gmii_2500_mode(struct phy_device *phydev)
+{
+ if (phydev->autoneg == AUTONEG_ENABLE) {
+ if (phydev->advertising & ADVERTISED_2500baseX_Full)
+ return true;
+ } else {
+ if (phydev->speed == SPEED_2500)
+ return true;
+ }
+
+ return false;
+}
+
+static bool amd_xgbe_phy_use_gmii_mode(struct phy_device *phydev)
+{
+ if (phydev->autoneg == AUTONEG_ENABLE) {
+ if (phydev->advertising & ADVERTISED_1000baseKX_Full)
+ return true;
+ } else {
+ if (phydev->speed == SPEED_1000)
+ return true;
+ }
+
+ return false;
+}
+
static int amd_xgbe_phy_set_an(struct phy_device *phydev, bool enable,
bool restart)
{
@@ -1235,11 +1274,11 @@
/* Set initial mode - call the mode setting routines
* directly to insure we are properly configured
*/
- if (phydev->advertising & SUPPORTED_10000baseKR_Full)
+ if (amd_xgbe_phy_use_xgmii_mode(phydev))
ret = amd_xgbe_phy_xgmii_mode(phydev);
- else if (phydev->advertising & SUPPORTED_1000baseKX_Full)
+ else if (amd_xgbe_phy_use_gmii_mode(phydev))
ret = amd_xgbe_phy_gmii_mode(phydev);
- else if (phydev->advertising & SUPPORTED_2500baseX_Full)
+ else if (amd_xgbe_phy_use_gmii_2500_mode(phydev))
ret = amd_xgbe_phy_gmii_2500_mode(phydev);
else
ret = -EINVAL;
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 64c74c6..b5dc59d 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -404,7 +404,7 @@
.name = "Broadcom BCM7425",
.features = PHY_GBIT_FEATURES |
SUPPORTED_Pause | SUPPORTED_Asym_Pause,
- .flags = 0,
+ .flags = PHY_IS_INTERNAL,
.config_init = bcm7xxx_config_init,
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 496e02f..00cb41e 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -47,7 +47,7 @@
#define PSF_TX 0x1000
#define EXT_EVENT 1
#define CAL_EVENT 7
-#define CAL_TRIGGER 7
+#define CAL_TRIGGER 1
#define DP83640_N_PINS 12
#define MII_DP83640_MICR 0x11
@@ -496,7 +496,9 @@
else
evnt |= EVNT_RISE;
}
+ mutex_lock(&clock->extreg_lock);
ext_write(0, phydev, PAGE5, PTP_EVNT, evnt);
+ mutex_unlock(&clock->extreg_lock);
return 0;
case PTP_CLK_REQ_PEROUT:
@@ -532,6 +534,8 @@
static void enable_status_frames(struct phy_device *phydev, bool on)
{
+ struct dp83640_private *dp83640 = phydev->priv;
+ struct dp83640_clock *clock = dp83640->clock;
u16 cfg0 = 0, ver;
if (on)
@@ -539,9 +543,13 @@
ver = (PSF_PTPVER & VERSIONPTP_MASK) << VERSIONPTP_SHIFT;
+ mutex_lock(&clock->extreg_lock);
+
ext_write(0, phydev, PAGE5, PSF_CFG0, cfg0);
ext_write(0, phydev, PAGE6, PSF_CFG1, ver);
+ mutex_unlock(&clock->extreg_lock);
+
if (!phydev->attached_dev) {
pr_warn("expected to find an attached netdevice\n");
return;
@@ -838,7 +846,7 @@
list_del_init(&rxts->list);
phy2rxts(phy_rxts, rxts);
- spin_lock_irqsave(&dp83640->rx_queue.lock, flags);
+ spin_lock(&dp83640->rx_queue.lock);
skb_queue_walk(&dp83640->rx_queue, skb) {
struct dp83640_skb_info *skb_info;
@@ -853,7 +861,7 @@
break;
}
}
- spin_unlock_irqrestore(&dp83640->rx_queue.lock, flags);
+ spin_unlock(&dp83640->rx_queue.lock);
if (!shhwtstamps)
list_add_tail(&rxts->list, &dp83640->rxts);
@@ -1173,11 +1181,18 @@
if (clock->chosen && !list_empty(&clock->phylist))
recalibrate(clock);
- else
+ else {
+ mutex_lock(&clock->extreg_lock);
enable_broadcast(phydev, clock->page, 1);
+ mutex_unlock(&clock->extreg_lock);
+ }
enable_status_frames(phydev, true);
+
+ mutex_lock(&clock->extreg_lock);
ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE);
+ mutex_unlock(&clock->extreg_lock);
+
return 0;
}
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c b/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c
index 4ec9811..65efb14 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c
@@ -511,11 +511,9 @@
msgbuf->rx_pktids,
msgbuf->ioctl_resp_pktid);
if (msgbuf->ioctl_resp_ret_len != 0) {
- if (!skb) {
- brcmf_err("Invalid packet id idx recv'd %d\n",
- msgbuf->ioctl_resp_pktid);
+ if (!skb)
return -EBADF;
- }
+
memcpy(buf, skb->data, (len < msgbuf->ioctl_resp_ret_len) ?
len : msgbuf->ioctl_resp_ret_len);
}
@@ -874,10 +872,8 @@
flowid -= BRCMF_NROF_H2D_COMMON_MSGRINGS;
skb = brcmf_msgbuf_get_pktid(msgbuf->drvr->bus_if->dev,
msgbuf->tx_pktids, idx);
- if (!skb) {
- brcmf_err("Invalid packet id idx recv'd %d\n", idx);
+ if (!skb)
return;
- }
set_bit(flowid, msgbuf->txstatus_done_map);
commonring = msgbuf->flowrings[flowid];
@@ -1156,6 +1152,8 @@
skb = brcmf_msgbuf_get_pktid(msgbuf->drvr->bus_if->dev,
msgbuf->rx_pktids, idx);
+ if (!skb)
+ return;
if (data_offset)
skb_pull(skb, data_offset);
diff --git a/drivers/net/wireless/iwlwifi/Kconfig b/drivers/net/wireless/iwlwifi/Kconfig
index ab019b4..f89f446 100644
--- a/drivers/net/wireless/iwlwifi/Kconfig
+++ b/drivers/net/wireless/iwlwifi/Kconfig
@@ -21,6 +21,7 @@
Intel 7260 Wi-Fi Adapter
Intel 3160 Wi-Fi Adapter
Intel 7265 Wi-Fi Adapter
+ Intel 3165 Wi-Fi Adapter
This driver uses the kernel's mac80211 subsystem.
diff --git a/drivers/net/wireless/iwlwifi/iwl-7000.c b/drivers/net/wireless/iwlwifi/iwl-7000.c
index 36e786f..74ad278 100644
--- a/drivers/net/wireless/iwlwifi/iwl-7000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-7000.c
@@ -70,15 +70,14 @@
/* Highest firmware API version supported */
#define IWL7260_UCODE_API_MAX 13
-#define IWL3160_UCODE_API_MAX 13
/* Oldest version we won't warn about */
#define IWL7260_UCODE_API_OK 12
-#define IWL3160_UCODE_API_OK 12
+#define IWL3165_UCODE_API_OK 13
/* Lowest firmware API version supported */
#define IWL7260_UCODE_API_MIN 10
-#define IWL3160_UCODE_API_MIN 10
+#define IWL3165_UCODE_API_MIN 13
/* NVM versions */
#define IWL7260_NVM_VERSION 0x0a1d
@@ -104,9 +103,6 @@
#define IWL3160_FW_PRE "iwlwifi-3160-"
#define IWL3160_MODULE_FIRMWARE(api) IWL3160_FW_PRE __stringify(api) ".ucode"
-#define IWL3165_FW_PRE "iwlwifi-3165-"
-#define IWL3165_MODULE_FIRMWARE(api) IWL3165_FW_PRE __stringify(api) ".ucode"
-
#define IWL7265_FW_PRE "iwlwifi-7265-"
#define IWL7265_MODULE_FIRMWARE(api) IWL7265_FW_PRE __stringify(api) ".ucode"
@@ -248,8 +244,13 @@
const struct iwl_cfg iwl3165_2ac_cfg = {
.name = "Intel(R) Dual Band Wireless AC 3165",
- .fw_name_pre = IWL3165_FW_PRE,
+ .fw_name_pre = IWL7265D_FW_PRE,
IWL_DEVICE_7000,
+ /* sparse doens't like the re-assignment but it is safe */
+#ifndef __CHECKER__
+ .ucode_api_ok = IWL3165_UCODE_API_OK,
+ .ucode_api_min = IWL3165_UCODE_API_MIN,
+#endif
.ht_params = &iwl7000_ht_params,
.nvm_ver = IWL3165_NVM_VERSION,
.nvm_calib_ver = IWL3165_TX_POWER_VERSION,
@@ -325,6 +326,5 @@
MODULE_FIRMWARE(IWL7260_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
MODULE_FIRMWARE(IWL3160_MODULE_FIRMWARE(IWL3160_UCODE_API_OK));
-MODULE_FIRMWARE(IWL3165_MODULE_FIRMWARE(IWL3160_UCODE_API_OK));
MODULE_FIRMWARE(IWL7265_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
MODULE_FIRMWARE(IWL7265D_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
diff --git a/drivers/net/wireless/iwlwifi/iwl-eeprom-parse.c b/drivers/net/wireless/iwlwifi/iwl-eeprom-parse.c
index 41ff85d..21302b6 100644
--- a/drivers/net/wireless/iwlwifi/iwl-eeprom-parse.c
+++ b/drivers/net/wireless/iwlwifi/iwl-eeprom-parse.c
@@ -6,6 +6,7 @@
* GPL LICENSE SUMMARY
*
* Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2015 Intel Mobile Communications GmbH
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
@@ -31,6 +32,7 @@
* BSD LICENSE
*
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2015 Intel Mobile Communications GmbH
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -748,6 +750,9 @@
return;
}
+ if (data->sku_cap_mimo_disabled)
+ rx_chains = 1;
+
ht_info->ht_supported = true;
ht_info->cap = IEEE80211_HT_CAP_DSSSCCK40;
diff --git a/drivers/net/wireless/iwlwifi/iwl-eeprom-parse.h b/drivers/net/wireless/iwlwifi/iwl-eeprom-parse.h
index 5234a0b..750c8c9 100644
--- a/drivers/net/wireless/iwlwifi/iwl-eeprom-parse.h
+++ b/drivers/net/wireless/iwlwifi/iwl-eeprom-parse.h
@@ -6,6 +6,7 @@
* GPL LICENSE SUMMARY
*
* Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2015 Intel Mobile Communications GmbH
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
@@ -31,6 +32,7 @@
* BSD LICENSE
*
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2015 Intel Mobile Communications GmbH
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -84,6 +86,7 @@
bool sku_cap_11ac_enable;
bool sku_cap_amt_enable;
bool sku_cap_ipan_enable;
+ bool sku_cap_mimo_disabled;
u16 radio_cfg_type;
u8 radio_cfg_step;
diff --git a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
index 83903a5..8e604a3 100644
--- a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
@@ -6,7 +6,7 @@
* GPL LICENSE SUMMARY
*
* Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
@@ -32,7 +32,7 @@
* BSD LICENSE
*
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -116,10 +116,11 @@
/* SKU Capabilities (actual values from NVM definition) */
enum nvm_sku_bits {
- NVM_SKU_CAP_BAND_24GHZ = BIT(0),
- NVM_SKU_CAP_BAND_52GHZ = BIT(1),
- NVM_SKU_CAP_11N_ENABLE = BIT(2),
- NVM_SKU_CAP_11AC_ENABLE = BIT(3),
+ NVM_SKU_CAP_BAND_24GHZ = BIT(0),
+ NVM_SKU_CAP_BAND_52GHZ = BIT(1),
+ NVM_SKU_CAP_11N_ENABLE = BIT(2),
+ NVM_SKU_CAP_11AC_ENABLE = BIT(3),
+ NVM_SKU_CAP_MIMO_DISABLE = BIT(5),
};
/*
@@ -368,6 +369,11 @@
if (cfg->ht_params->ldpc)
vht_cap->cap |= IEEE80211_VHT_CAP_RXLDPC;
+ if (data->sku_cap_mimo_disabled) {
+ num_rx_ants = 1;
+ num_tx_ants = 1;
+ }
+
if (num_tx_ants > 1)
vht_cap->cap |= IEEE80211_VHT_CAP_TXSTBC;
else
@@ -465,7 +471,7 @@
if (cfg->device_family != IWL_DEVICE_FAMILY_8000)
return le16_to_cpup(nvm_sw + RADIO_CFG);
- return le32_to_cpup((__le32 *)(nvm_sw + RADIO_CFG_FAMILY_8000));
+ return le32_to_cpup((__le32 *)(phy_sku + RADIO_CFG_FAMILY_8000));
}
@@ -527,6 +533,10 @@
const u8 *hw_addr;
if (mac_override) {
+ static const u8 reserved_mac[] = {
+ 0x02, 0xcc, 0xaa, 0xff, 0xee, 0x00
+ };
+
hw_addr = (const u8 *)(mac_override +
MAC_ADDRESS_OVERRIDE_FAMILY_8000);
@@ -538,7 +548,12 @@
data->hw_addr[4] = hw_addr[5];
data->hw_addr[5] = hw_addr[4];
- if (is_valid_ether_addr(data->hw_addr))
+ /*
+ * Force the use of the OTP MAC address in case of reserved MAC
+ * address in the NVM, or if address is given but invalid.
+ */
+ if (is_valid_ether_addr(data->hw_addr) &&
+ memcmp(reserved_mac, hw_addr, ETH_ALEN) != 0)
return;
IWL_ERR_DEV(dev,
@@ -610,6 +625,7 @@
data->sku_cap_11n_enable = false;
data->sku_cap_11ac_enable = data->sku_cap_11n_enable &&
(sku & NVM_SKU_CAP_11AC_ENABLE);
+ data->sku_cap_mimo_disabled = sku & NVM_SKU_CAP_MIMO_DISABLE;
data->n_hw_addrs = iwl_get_n_hw_addrs(cfg, nvm_sw);
diff --git a/drivers/net/wireless/iwlwifi/mvm/coex_legacy.c b/drivers/net/wireless/iwlwifi/mvm/coex_legacy.c
index d954591..6ac6de2 100644
--- a/drivers/net/wireless/iwlwifi/mvm/coex_legacy.c
+++ b/drivers/net/wireless/iwlwifi/mvm/coex_legacy.c
@@ -776,7 +776,7 @@
struct iwl_host_cmd cmd = {
.id = BT_CONFIG,
.len = { sizeof(*bt_cmd), },
- .dataflags = { IWL_HCMD_DFL_NOCOPY, },
+ .dataflags = { IWL_HCMD_DFL_DUP, },
.flags = CMD_ASYNC,
};
struct iwl_mvm_sta *mvmsta;
diff --git a/drivers/net/wireless/iwlwifi/mvm/d3.c b/drivers/net/wireless/iwlwifi/mvm/d3.c
index 1b1b2bf..4310cf1 100644
--- a/drivers/net/wireless/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/iwlwifi/mvm/d3.c
@@ -1750,8 +1750,10 @@
int i, j, n_matches, ret;
fw_status = iwl_mvm_get_wakeup_status(mvm, vif);
- if (!IS_ERR_OR_NULL(fw_status))
+ if (!IS_ERR_OR_NULL(fw_status)) {
reasons = le32_to_cpu(fw_status->wakeup_reasons);
+ kfree(fw_status);
+ }
if (reasons & IWL_WOWLAN_WAKEUP_BY_RFKILL_DEASSERTED)
wakeup.rfkill_release = true;
@@ -1868,15 +1870,15 @@
/* get the BSS vif pointer again */
vif = iwl_mvm_get_bss_vif(mvm);
if (IS_ERR_OR_NULL(vif))
- goto out_unlock;
+ goto err;
ret = iwl_trans_d3_resume(mvm->trans, &d3_status, test);
if (ret)
- goto out_unlock;
+ goto err;
if (d3_status != IWL_D3_STATUS_ALIVE) {
IWL_INFO(mvm, "Device was reset during suspend\n");
- goto out_unlock;
+ goto err;
}
/* query SRAM first in case we want event logging */
@@ -1902,7 +1904,8 @@
goto out_iterate;
}
- out_unlock:
+err:
+ iwl_mvm_free_nd(mvm);
mutex_unlock(&mvm->mutex);
out_iterate:
@@ -1915,6 +1918,14 @@
/* return 1 to reconfigure the device */
set_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status);
set_bit(IWL_MVM_STATUS_D3_RECONFIG, &mvm->status);
+
+ /* We always return 1, which causes mac80211 to do a reconfig
+ * with IEEE80211_RECONFIG_TYPE_RESTART. This type of
+ * reconfig calls iwl_mvm_restart_complete(), where we unref
+ * the IWL_MVM_REF_UCODE_DOWN, so we need to take the
+ * reference here.
+ */
+ iwl_mvm_ref(mvm, IWL_MVM_REF_UCODE_DOWN);
return 1;
}
@@ -2021,7 +2032,6 @@
__iwl_mvm_resume(mvm, true);
rtnl_unlock();
iwl_abort_notification_waits(&mvm->notif_wait);
- iwl_mvm_ref(mvm, IWL_MVM_REF_UCODE_DOWN);
ieee80211_restart_hw(mvm->hw);
/* wait for restart and disconnect all interfaces */
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index 40265b9..dda9f7b 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -3995,9 +3995,6 @@
if (!iwl_fw_dbg_trigger_enabled(mvm->fw, FW_DBG_TRIGGER_MLME))
return;
- if (event->u.mlme.status == MLME_SUCCESS)
- return;
-
trig = iwl_fw_dbg_get_trigger(mvm->fw, FW_DBG_TRIGGER_MLME);
trig_mlme = (void *)trig->data;
if (!iwl_fw_dbg_trigger_check_stop(mvm, vif, trig))
diff --git a/drivers/net/wireless/iwlwifi/mvm/ops.c b/drivers/net/wireless/iwlwifi/mvm/ops.c
index 1c66297..2ea0123 100644
--- a/drivers/net/wireless/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/iwlwifi/mvm/ops.c
@@ -1263,11 +1263,13 @@
ieee80211_iterate_active_interfaces(
mvm->hw, IEEE80211_IFACE_ITER_NORMAL,
iwl_mvm_d0i3_disconnect_iter, mvm);
-
- iwl_free_resp(&get_status_cmd);
out:
iwl_mvm_d0i3_enable_tx(mvm, qos_seq);
+ /* qos_seq might point inside resp_pkt, so free it only now */
+ if (get_status_cmd.resp_pkt)
+ iwl_free_resp(&get_status_cmd);
+
/* the FW might have updated the regdomain */
iwl_mvm_update_changed_regdom(mvm);
diff --git a/drivers/net/wireless/iwlwifi/mvm/rs.c b/drivers/net/wireless/iwlwifi/mvm/rs.c
index f9928f2..33cd68a 100644
--- a/drivers/net/wireless/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/iwlwifi/mvm/rs.c
@@ -180,6 +180,9 @@
if (iwl_mvm_vif_low_latency(mvmvif) && mvmsta->vif->p2p)
return false;
+ if (mvm->nvm_data->sku_cap_mimo_disabled)
+ return false;
+
return true;
}
diff --git a/drivers/net/wireless/iwlwifi/pcie/internal.h b/drivers/net/wireless/iwlwifi/pcie/internal.h
index 01996c9..376b84e 100644
--- a/drivers/net/wireless/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/iwlwifi/pcie/internal.h
@@ -1,7 +1,7 @@
/******************************************************************************
*
- * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2003 - 2015 Intel Corporation. All rights reserved.
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
*
* Portions of this file are derived from the ipw3945 project, as well
* as portions of the ieee80211 subsystem header files.
@@ -320,7 +320,7 @@
/*protect hw register */
spinlock_t reg_lock;
- bool cmd_in_flight;
+ bool cmd_hold_nic_awake;
bool ref_cmd_in_flight;
/* protect ref counter */
diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c
index 47bbf57..dc17909 100644
--- a/drivers/net/wireless/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c
@@ -1049,9 +1049,11 @@
iwl_pcie_rx_stop(trans);
/* Power-down device's busmaster DMA clocks */
- iwl_write_prph(trans, APMG_CLK_DIS_REG,
- APMG_CLK_VAL_DMA_CLK_RQT);
- udelay(5);
+ if (trans->cfg->device_family != IWL_DEVICE_FAMILY_8000) {
+ iwl_write_prph(trans, APMG_CLK_DIS_REG,
+ APMG_CLK_VAL_DMA_CLK_RQT);
+ udelay(5);
+ }
}
/* Make sure (redundant) we've released our request to stay awake */
@@ -1370,7 +1372,7 @@
spin_lock_irqsave(&trans_pcie->reg_lock, *flags);
- if (trans_pcie->cmd_in_flight)
+ if (trans_pcie->cmd_hold_nic_awake)
goto out;
/* this bit wakes up the NIC */
@@ -1436,7 +1438,7 @@
*/
__acquire(&trans_pcie->reg_lock);
- if (trans_pcie->cmd_in_flight)
+ if (trans_pcie->cmd_hold_nic_awake)
goto out;
__iwl_trans_pcie_clear_bit(trans, CSR_GP_CNTRL,
diff --git a/drivers/net/wireless/iwlwifi/pcie/tx.c b/drivers/net/wireless/iwlwifi/pcie/tx.c
index 06952aa..5ef8044 100644
--- a/drivers/net/wireless/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/tx.c
@@ -1039,18 +1039,14 @@
iwl_trans_pcie_ref(trans);
}
- if (trans_pcie->cmd_in_flight)
- return 0;
-
- trans_pcie->cmd_in_flight = true;
-
/*
* wake up the NIC to make sure that the firmware will see the host
* command - we will let the NIC sleep once all the host commands
* returned. This needs to be done only on NICs that have
* apmg_wake_up_wa set.
*/
- if (trans->cfg->base_params->apmg_wake_up_wa) {
+ if (trans->cfg->base_params->apmg_wake_up_wa &&
+ !trans_pcie->cmd_hold_nic_awake) {
__iwl_trans_pcie_set_bit(trans, CSR_GP_CNTRL,
CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000)
@@ -1064,10 +1060,10 @@
if (ret < 0) {
__iwl_trans_pcie_clear_bit(trans, CSR_GP_CNTRL,
CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
- trans_pcie->cmd_in_flight = false;
IWL_ERR(trans, "Failed to wake NIC for hcmd\n");
return -EIO;
}
+ trans_pcie->cmd_hold_nic_awake = true;
}
return 0;
@@ -1085,15 +1081,14 @@
iwl_trans_pcie_unref(trans);
}
- if (WARN_ON(!trans_pcie->cmd_in_flight))
- return 0;
+ if (trans->cfg->base_params->apmg_wake_up_wa) {
+ if (WARN_ON(!trans_pcie->cmd_hold_nic_awake))
+ return 0;
- trans_pcie->cmd_in_flight = false;
-
- if (trans->cfg->base_params->apmg_wake_up_wa)
+ trans_pcie->cmd_hold_nic_awake = false;
__iwl_trans_pcie_clear_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
-
+ CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+ }
return 0;
}
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 4de46aa..0d25943 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1250,7 +1250,7 @@
netdev_err(queue->vif->dev,
"txreq.offset: %x, size: %u, end: %lu\n",
txreq.offset, txreq.size,
- (txreq.offset&~PAGE_MASK) + txreq.size);
+ (unsigned long)(txreq.offset&~PAGE_MASK) + txreq.size);
xenvif_fatal_tx_err(queue->vif);
break;
}
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 3d8dbf5..968787a 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -34,6 +34,8 @@
enum xenbus_state frontend_state;
struct xenbus_watch hotplug_status_watch;
u8 have_hotplug_status_watch:1;
+
+ const char *hotplug_script;
};
static int connect_rings(struct backend_info *be, struct xenvif_queue *queue);
@@ -238,6 +240,7 @@
xenvif_free(be->vif);
be->vif = NULL;
}
+ kfree(be->hotplug_script);
kfree(be);
dev_set_drvdata(&dev->dev, NULL);
return 0;
@@ -255,6 +258,7 @@
struct xenbus_transaction xbt;
int err;
int sg;
+ const char *script;
struct backend_info *be = kzalloc(sizeof(struct backend_info),
GFP_KERNEL);
if (!be) {
@@ -347,6 +351,15 @@
if (err)
pr_debug("Error writing multi-queue-max-queues\n");
+ script = xenbus_read(XBT_NIL, dev->nodename, "script", NULL);
+ if (IS_ERR(script)) {
+ err = PTR_ERR(script);
+ xenbus_dev_fatal(dev, err, "reading script");
+ goto fail;
+ }
+
+ be->hotplug_script = script;
+
err = xenbus_switch_state(dev, XenbusStateInitWait);
if (err)
goto fail;
@@ -379,22 +392,14 @@
struct kobj_uevent_env *env)
{
struct backend_info *be = dev_get_drvdata(&xdev->dev);
- char *val;
- val = xenbus_read(XBT_NIL, xdev->nodename, "script", NULL);
- if (IS_ERR(val)) {
- int err = PTR_ERR(val);
- xenbus_dev_fatal(xdev, err, "reading script");
- return err;
- } else {
- if (add_uevent_var(env, "script=%s", val)) {
- kfree(val);
- return -ENOMEM;
- }
- kfree(val);
- }
+ if (!be)
+ return 0;
- if (!be || !be->vif)
+ if (add_uevent_var(env, "script=%s", be->hotplug_script))
+ return -ENOMEM;
+
+ if (!be->vif)
return 0;
return add_uevent_var(env, "vif=%s", be->vif->dev->name);
@@ -793,6 +798,7 @@
goto err;
}
+ queue->credit_bytes = credit_bytes;
queue->remaining_credit = credit_bytes;
queue->credit_usec = credit_usec;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 3f45afd4..e031c94 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1698,6 +1698,7 @@
if (netif_running(info->netdev))
napi_disable(&queue->napi);
+ del_timer_sync(&queue->rx_refill_timer);
netif_napi_del(&queue->napi);
}
@@ -2102,9 +2103,6 @@
static int xennet_remove(struct xenbus_device *dev)
{
struct netfront_info *info = dev_get_drvdata(&dev->dev);
- unsigned int num_queues = info->netdev->real_num_tx_queues;
- struct netfront_queue *queue = NULL;
- unsigned int i = 0;
dev_dbg(&dev->dev, "%s\n", dev->nodename);
@@ -2112,16 +2110,7 @@
unregister_netdev(info->netdev);
- for (i = 0; i < num_queues; ++i) {
- queue = &info->queues[i];
- del_timer_sync(&queue->rx_refill_timer);
- }
-
- if (num_queues) {
- kfree(info->queues);
- info->queues = NULL;
- }
-
+ xennet_destroy_queues(info);
xennet_free_netdev(info->netdev);
return 0;
diff --git a/drivers/pci/htirq.c b/drivers/pci/htirq.c
index a94dd2c..7eb4109 100644
--- a/drivers/pci/htirq.c
+++ b/drivers/pci/htirq.c
@@ -23,20 +23,11 @@
*/
static DEFINE_SPINLOCK(ht_irq_lock);
-struct ht_irq_cfg {
- struct pci_dev *dev;
- /* Update callback used to cope with buggy hardware */
- ht_irq_update_t *update;
- unsigned pos;
- unsigned idx;
- struct ht_irq_msg msg;
-};
-
-
void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg)
{
struct ht_irq_cfg *cfg = irq_get_handler_data(irq);
unsigned long flags;
+
spin_lock_irqsave(&ht_irq_lock, flags);
if (cfg->msg.address_lo != msg->address_lo) {
pci_write_config_byte(cfg->dev, cfg->pos + 2, cfg->idx);
@@ -55,6 +46,7 @@
void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg)
{
struct ht_irq_cfg *cfg = irq_get_handler_data(irq);
+
*msg = cfg->msg;
}
@@ -86,7 +78,6 @@
*/
int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
{
- struct ht_irq_cfg *cfg;
int max_irq, pos, irq;
unsigned long flags;
u32 data;
@@ -105,29 +96,9 @@
if (idx > max_irq)
return -EINVAL;
- cfg = kmalloc(sizeof(*cfg), GFP_KERNEL);
- if (!cfg)
- return -ENOMEM;
-
- cfg->dev = dev;
- cfg->update = update;
- cfg->pos = pos;
- cfg->idx = 0x10 + (idx * 2);
- /* Initialize msg to a value that will never match the first write. */
- cfg->msg.address_lo = 0xffffffff;
- cfg->msg.address_hi = 0xffffffff;
-
- irq = irq_alloc_hwirq(dev_to_node(&dev->dev));
- if (!irq) {
- kfree(cfg);
- return -EBUSY;
- }
- irq_set_handler_data(irq, cfg);
-
- if (arch_setup_ht_irq(irq, dev) < 0) {
- ht_destroy_irq(irq);
- return -EBUSY;
- }
+ irq = arch_setup_ht_irq(idx, pos, dev, update);
+ if (irq > 0)
+ dev_dbg(&dev->dev, "irq %d for HT\n", irq);
return irq;
}
@@ -158,13 +129,6 @@
*/
void ht_destroy_irq(unsigned int irq)
{
- struct ht_irq_cfg *cfg;
-
- cfg = irq_get_handler_data(irq);
- irq_set_chip(irq, NULL);
- irq_set_handler_data(irq, NULL);
- irq_free_hwirq(irq);
-
- kfree(cfg);
+ arch_teardown_ht_irq(irq);
}
EXPORT_SYMBOL(ht_destroy_irq);
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index c6dc1df..2890ad7 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -819,13 +819,6 @@
}
}
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_VIPER_7410, quirk_amd_ioapic);
-
-static void quirk_ioapic_rmw(struct pci_dev *dev)
-{
- if (dev->devfn == 0 && dev->bus->number == 0)
- sis_apic_bug = 1;
-}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SI, PCI_ANY_ID, quirk_ioapic_rmw);
#endif /* CONFIG_X86_IO_APIC */
/*
diff --git a/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c b/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c
index 4ad5c1a..e406e3d 100644
--- a/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c
+++ b/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c
@@ -643,7 +643,9 @@
CYGNUS_PINRANGE(87, 104, 12),
CYGNUS_PINRANGE(99, 102, 2),
CYGNUS_PINRANGE(101, 90, 4),
- CYGNUS_PINRANGE(105, 116, 10),
+ CYGNUS_PINRANGE(105, 116, 6),
+ CYGNUS_PINRANGE(111, 100, 2),
+ CYGNUS_PINRANGE(113, 122, 4),
CYGNUS_PINRANGE(123, 11, 1),
CYGNUS_PINRANGE(124, 38, 4),
CYGNUS_PINRANGE(128, 43, 1),
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index 82f691e..732ff75 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1292,6 +1292,49 @@
chv_gpio_irq_mask_unmask(d, false);
}
+static unsigned chv_gpio_irq_startup(struct irq_data *d)
+{
+ /*
+ * Check if the interrupt has been requested with 0 as triggering
+ * type. In that case it is assumed that the current values
+ * programmed to the hardware are used (e.g BIOS configured
+ * defaults).
+ *
+ * In that case ->irq_set_type() will never be called so we need to
+ * read back the values from hardware now, set correct flow handler
+ * and update mappings before the interrupt is being used.
+ */
+ if (irqd_get_trigger_type(d) == IRQ_TYPE_NONE) {
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct chv_pinctrl *pctrl = gpiochip_to_pinctrl(gc);
+ unsigned offset = irqd_to_hwirq(d);
+ int pin = chv_gpio_offset_to_pin(pctrl, offset);
+ irq_flow_handler_t handler;
+ unsigned long flags;
+ u32 intsel, value;
+
+ intsel = readl(chv_padreg(pctrl, pin, CHV_PADCTRL0));
+ intsel &= CHV_PADCTRL0_INTSEL_MASK;
+ intsel >>= CHV_PADCTRL0_INTSEL_SHIFT;
+
+ value = readl(chv_padreg(pctrl, pin, CHV_PADCTRL1));
+ if (value & CHV_PADCTRL1_INTWAKECFG_LEVEL)
+ handler = handle_level_irq;
+ else
+ handler = handle_edge_irq;
+
+ spin_lock_irqsave(&pctrl->lock, flags);
+ if (!pctrl->intr_lines[intsel]) {
+ __irq_set_handler_locked(d->irq, handler);
+ pctrl->intr_lines[intsel] = offset;
+ }
+ spin_unlock_irqrestore(&pctrl->lock, flags);
+ }
+
+ chv_gpio_irq_unmask(d);
+ return 0;
+}
+
static int chv_gpio_irq_type(struct irq_data *d, unsigned type)
{
struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
@@ -1357,6 +1400,7 @@
static struct irq_chip chv_gpio_irqchip = {
.name = "chv-gpio",
+ .irq_startup = chv_gpio_irq_startup,
.irq_ack = chv_gpio_irq_ack,
.irq_mask = chv_gpio_irq_mask,
.irq_unmask = chv_gpio_irq_unmask,
diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c
index edcd140..a70a5fe 100644
--- a/drivers/pinctrl/meson/pinctrl-meson.c
+++ b/drivers/pinctrl/meson/pinctrl-meson.c
@@ -569,7 +569,7 @@
domain->chip.direction_output = meson_gpio_direction_output;
domain->chip.get = meson_gpio_get;
domain->chip.set = meson_gpio_set;
- domain->chip.base = -1;
+ domain->chip.base = domain->data->pin_base;
domain->chip.ngpio = domain->data->num_pins;
domain->chip.can_sleep = false;
domain->chip.of_node = domain->of_node;
diff --git a/drivers/pinctrl/meson/pinctrl-meson8b.c b/drivers/pinctrl/meson/pinctrl-meson8b.c
index 2f7ea62..9677807 100644
--- a/drivers/pinctrl/meson/pinctrl-meson8b.c
+++ b/drivers/pinctrl/meson/pinctrl-meson8b.c
@@ -876,13 +876,13 @@
.banks = meson8b_banks,
.num_banks = ARRAY_SIZE(meson8b_banks),
.pin_base = 0,
- .num_pins = 83,
+ .num_pins = 130,
},
{
.name = "ao-bank",
.banks = meson8b_ao_banks,
.num_banks = ARRAY_SIZE(meson8b_ao_banks),
- .pin_base = 83,
+ .pin_base = 130,
.num_pins = 16,
},
};
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 9bb9ad6..28f3281 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -2897,7 +2897,7 @@
return snprintf(buf, PAGE_SIZE, "%d\n", hotkey_wakeup_reason);
}
-static DEVICE_ATTR_RO(hotkey_wakeup_reason);
+static DEVICE_ATTR(wakeup_reason, S_IRUGO, hotkey_wakeup_reason_show, NULL);
static void hotkey_wakeup_reason_notify_change(void)
{
@@ -2913,7 +2913,8 @@
return snprintf(buf, PAGE_SIZE, "%d\n", hotkey_autosleep_ack);
}
-static DEVICE_ATTR_RO(hotkey_wakeup_hotunplug_complete);
+static DEVICE_ATTR(wakeup_hotunplug_complete, S_IRUGO,
+ hotkey_wakeup_hotunplug_complete_show, NULL);
static void hotkey_wakeup_hotunplug_complete_notify_change(void)
{
@@ -2978,8 +2979,8 @@
&dev_attr_hotkey_enable.attr,
&dev_attr_hotkey_bios_enabled.attr,
&dev_attr_hotkey_bios_mask.attr,
- &dev_attr_hotkey_wakeup_reason.attr,
- &dev_attr_hotkey_wakeup_hotunplug_complete.attr,
+ &dev_attr_wakeup_reason.attr,
+ &dev_attr_wakeup_hotunplug_complete.attr,
&dev_attr_hotkey_mask.attr,
&dev_attr_hotkey_all_mask.attr,
&dev_attr_hotkey_recommended_mask.attr,
@@ -4393,12 +4394,13 @@
attr, buf, count);
}
-static DEVICE_ATTR_RW(wan_enable);
+static DEVICE_ATTR(wwan_enable, S_IWUSR | S_IRUGO,
+ wan_enable_show, wan_enable_store);
/* --------------------------------------------------------------------- */
static struct attribute *wan_attributes[] = {
- &dev_attr_wan_enable.attr,
+ &dev_attr_wwan_enable.attr,
NULL
};
@@ -8138,7 +8140,8 @@
return count;
}
-static DEVICE_ATTR_RW(fan_pwm1_enable);
+static DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO,
+ fan_pwm1_enable_show, fan_pwm1_enable_store);
/* sysfs fan pwm1 ------------------------------------------------------ */
static ssize_t fan_pwm1_show(struct device *dev,
@@ -8198,7 +8201,7 @@
return (rc) ? rc : count;
}
-static DEVICE_ATTR_RW(fan_pwm1);
+static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, fan_pwm1_show, fan_pwm1_store);
/* sysfs fan fan1_input ------------------------------------------------ */
static ssize_t fan_fan1_input_show(struct device *dev,
@@ -8215,7 +8218,7 @@
return snprintf(buf, PAGE_SIZE, "%u\n", speed);
}
-static DEVICE_ATTR_RO(fan_fan1_input);
+static DEVICE_ATTR(fan1_input, S_IRUGO, fan_fan1_input_show, NULL);
/* sysfs fan fan2_input ------------------------------------------------ */
static ssize_t fan_fan2_input_show(struct device *dev,
@@ -8232,7 +8235,7 @@
return snprintf(buf, PAGE_SIZE, "%u\n", speed);
}
-static DEVICE_ATTR_RO(fan_fan2_input);
+static DEVICE_ATTR(fan2_input, S_IRUGO, fan_fan2_input_show, NULL);
/* sysfs fan fan_watchdog (hwmon driver) ------------------------------- */
static ssize_t fan_fan_watchdog_show(struct device_driver *drv,
@@ -8265,8 +8268,8 @@
/* --------------------------------------------------------------------- */
static struct attribute *fan_attributes[] = {
- &dev_attr_fan_pwm1_enable.attr, &dev_attr_fan_pwm1.attr,
- &dev_attr_fan_fan1_input.attr,
+ &dev_attr_pwm1_enable.attr, &dev_attr_pwm1.attr,
+ &dev_attr_fan1_input.attr,
NULL, /* for fan2_input */
NULL
};
@@ -8400,7 +8403,7 @@
if (tp_features.second_fan) {
/* attach second fan tachometer */
fan_attributes[ARRAY_SIZE(fan_attributes)-2] =
- &dev_attr_fan_fan2_input.attr;
+ &dev_attr_fan2_input.attr;
}
rc = sysfs_create_group(&tpacpi_sensors_pdev->dev.kobj,
&fan_attr_group);
@@ -8848,7 +8851,7 @@
return snprintf(buf, PAGE_SIZE, "%s\n", TPACPI_NAME);
}
-static DEVICE_ATTR_RO(thinkpad_acpi_pdev_name);
+static DEVICE_ATTR(name, S_IRUGO, thinkpad_acpi_pdev_name_show, NULL);
/* --------------------------------------------------------------------- */
@@ -9390,8 +9393,7 @@
hwmon_device_unregister(tpacpi_hwmon);
if (tp_features.sensors_pdev_attrs_registered)
- device_remove_file(&tpacpi_sensors_pdev->dev,
- &dev_attr_thinkpad_acpi_pdev_name);
+ device_remove_file(&tpacpi_sensors_pdev->dev, &dev_attr_name);
if (tpacpi_sensors_pdev)
platform_device_unregister(tpacpi_sensors_pdev);
if (tpacpi_pdev)
@@ -9512,8 +9514,7 @@
thinkpad_acpi_module_exit();
return ret;
}
- ret = device_create_file(&tpacpi_sensors_pdev->dev,
- &dev_attr_thinkpad_acpi_pdev_name);
+ ret = device_create_file(&tpacpi_sensors_pdev->dev, &dev_attr_name);
if (ret) {
pr_err("unable to create sysfs hwmon device attributes\n");
thinkpad_acpi_module_exit();
diff --git a/drivers/regulator/da9052-regulator.c b/drivers/regulator/da9052-regulator.c
index 8a4df7a..e628d4c 100644
--- a/drivers/regulator/da9052-regulator.c
+++ b/drivers/regulator/da9052-regulator.c
@@ -394,6 +394,7 @@
static int da9052_regulator_probe(struct platform_device *pdev)
{
+ const struct mfd_cell *cell = mfd_get_cell(pdev);
struct regulator_config config = { };
struct da9052_regulator *regulator;
struct da9052 *da9052;
@@ -409,7 +410,7 @@
regulator->da9052 = da9052;
regulator->info = find_regulator_info(regulator->da9052->chip_id,
- pdev->id);
+ cell->id);
if (regulator->info == NULL) {
dev_err(&pdev->dev, "invalid regulator ID specified\n");
return -EINVAL;
@@ -419,7 +420,7 @@
config.driver_data = regulator;
config.regmap = da9052->regmap;
if (pdata && pdata->regulators) {
- config.init_data = pdata->regulators[pdev->id];
+ config.init_data = pdata->regulators[cell->id];
} else {
#ifdef CONFIG_OF
struct device_node *nproot = da9052->dev->of_node;
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 68c2002..5c9e680 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1020,8 +1020,7 @@
struct se_portal_group *se_tpg = &base_tpg->se_tpg;
struct scsi_qla_host *base_vha = base_tpg->lport->qla_vha;
- if (!configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys,
- &se_tpg->tpg_group.cg_item)) {
+ if (!target_depend_item(&se_tpg->tpg_group.cg_item)) {
atomic_set(&base_tpg->lport_tpg_enabled, 1);
qlt_enable_vha(base_vha);
}
@@ -1037,8 +1036,7 @@
if (!qlt_stop_phase1(base_vha->vha_tgt.qla_tgt)) {
atomic_set(&base_tpg->lport_tpg_enabled, 0);
- configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys,
- &se_tpg->tpg_group.cg_item);
+ target_undepend_item(&se_tpg->tpg_group.cg_item);
}
complete(&base_tpg->tpg_base_comp);
}
diff --git a/drivers/ssb/driver_pcicore.c b/drivers/ssb/driver_pcicore.c
index 15a7ee3..5fe1c22 100644
--- a/drivers/ssb/driver_pcicore.c
+++ b/drivers/ssb/driver_pcicore.c
@@ -359,12 +359,13 @@
/*
* Accessing PCI config without a proper delay after devices reset (not
- * GPIO reset) was causing reboots on WRT300N v1.0.
+ * GPIO reset) was causing reboots on WRT300N v1.0 (BCM4704).
* Tested delay 850 us lowered reboot chance to 50-80%, 1000 us fixed it
* completely. Flushing all writes was also tested but with no luck.
+ * The same problem was reported for WRT350N v1 (BCM4705), so we just
+ * sleep here unconditionally.
*/
- if (pc->dev->bus->chip_id == 0x4704)
- usleep_range(1000, 2000);
+ usleep_range(1000, 2000);
/* Enable PCI bridge BAR0 prefetch and burst */
val = PCI_COMMAND_MASTER | PCI_COMMAND_MEMORY;
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 34871a6..74e6114f 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -230,7 +230,7 @@
* Here we serialize access across the TIQN+TPG Tuple.
*/
ret = down_interruptible(&tpg->np_login_sem);
- if ((ret != 0) || signal_pending(current))
+ if (ret != 0)
return -1;
spin_lock_bh(&tpg->tpg_state_lock);
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 8ce94ff..70d799d 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -346,6 +346,7 @@
if (IS_ERR(sess->se_sess)) {
iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
ISCSI_LOGIN_STATUS_NO_RESOURCES);
+ kfree(sess->sess_ops);
kfree(sess);
return -ENOMEM;
}
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index e8a2408..5e3295f 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -161,10 +161,7 @@
int iscsit_get_tpg(
struct iscsi_portal_group *tpg)
{
- int ret;
-
- ret = mutex_lock_interruptible(&tpg->tpg_access_lock);
- return ((ret != 0) || signal_pending(current)) ? -1 : 0;
+ return mutex_lock_interruptible(&tpg->tpg_access_lock);
}
void iscsit_put_tpg(struct iscsi_portal_group *tpg)
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index 75cbde1..4f8d4d4 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -704,7 +704,7 @@
if (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)
return 0;
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return 0;
if (!port)
@@ -2377,7 +2377,7 @@
int core_setup_alua(struct se_device *dev)
{
- if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV &&
+ if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) &&
!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) {
struct t10_alua_lu_gp_member *lu_gp_mem;
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index ddaf76a..e7b0430 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -212,10 +212,6 @@
pr_debug("Target_Core_ConfigFS: REGISTER -> Allocated Fabric:"
" %s\n", tf->tf_group.cg_item.ci_name);
- /*
- * Setup tf_ops.tf_subsys pointer for usage with configfs_depend_item()
- */
- tf->tf_ops.tf_subsys = tf->tf_subsys;
tf->tf_fabric = &tf->tf_group.cg_item;
pr_debug("Target_Core_ConfigFS: REGISTER -> Set tf->tf_fabric"
" for %s\n", name);
@@ -291,10 +287,17 @@
},
};
-struct configfs_subsystem *target_core_subsystem[] = {
- &target_core_fabrics,
- NULL,
-};
+int target_depend_item(struct config_item *item)
+{
+ return configfs_depend_item(&target_core_fabrics, item);
+}
+EXPORT_SYMBOL(target_depend_item);
+
+void target_undepend_item(struct config_item *item)
+{
+ return configfs_undepend_item(&target_core_fabrics, item);
+}
+EXPORT_SYMBOL(target_undepend_item);
/*##############################################################################
// Start functions called by external Target Fabrics Modules
@@ -467,7 +470,6 @@
* struct target_fabric_configfs->tf_cit_tmpl
*/
tf->tf_module = fo->module;
- tf->tf_subsys = target_core_subsystem[0];
snprintf(tf->tf_name, TARGET_FABRIC_NAME_SIZE, "%s", fo->name);
tf->tf_ops = *fo;
@@ -809,7 +811,7 @@
{
int ret;
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return sprintf(page, "Passthrough\n");
spin_lock(&dev->dev_reservation_lock);
@@ -960,7 +962,7 @@
static ssize_t target_core_dev_pr_show_attr_res_type(
struct se_device *dev, char *page)
{
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return sprintf(page, "SPC_PASSTHROUGH\n");
else if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
return sprintf(page, "SPC2_RESERVATIONS\n");
@@ -973,7 +975,7 @@
static ssize_t target_core_dev_pr_show_attr_res_aptpl_active(
struct se_device *dev, char *page)
{
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return 0;
return sprintf(page, "APTPL Bit Status: %s\n",
@@ -988,7 +990,7 @@
static ssize_t target_core_dev_pr_show_attr_res_aptpl_metadata(
struct se_device *dev, char *page)
{
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return 0;
return sprintf(page, "Ready to process PR APTPL metadata..\n");
@@ -1035,7 +1037,7 @@
u16 port_rpti = 0, tpgt = 0;
u8 type = 0, scope;
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return 0;
if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
return 0;
@@ -2870,7 +2872,7 @@
{
struct config_group *target_cg, *hba_cg = NULL, *alua_cg = NULL;
struct config_group *lu_gp_cg = NULL;
- struct configfs_subsystem *subsys;
+ struct configfs_subsystem *subsys = &target_core_fabrics;
struct t10_alua_lu_gp *lu_gp;
int ret;
@@ -2878,7 +2880,6 @@
" Engine: %s on %s/%s on "UTS_RELEASE"\n",
TARGET_CORE_VERSION, utsname()->sysname, utsname()->machine);
- subsys = target_core_subsystem[0];
config_group_init(&subsys->su_group);
mutex_init(&subsys->su_mutex);
@@ -3008,13 +3009,10 @@
static void __exit target_core_exit_configfs(void)
{
- struct configfs_subsystem *subsys;
struct config_group *hba_cg, *alua_cg, *lu_gp_cg;
struct config_item *item;
int i;
- subsys = target_core_subsystem[0];
-
lu_gp_cg = &alua_lu_gps_group;
for (i = 0; lu_gp_cg->default_groups[i]; i++) {
item = &lu_gp_cg->default_groups[i]->cg_item;
@@ -3045,8 +3043,8 @@
* We expect subsys->su_group.default_groups to be released
* by configfs subsystem provider logic..
*/
- configfs_unregister_subsystem(subsys);
- kfree(subsys->su_group.default_groups);
+ configfs_unregister_subsystem(&target_core_fabrics);
+ kfree(target_core_fabrics.su_group.default_groups);
core_alua_free_lu_gp(default_lu_gp);
default_lu_gp = NULL;
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 7faa6ae..ce5f768 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -33,6 +33,7 @@
#include <linux/kthread.h>
#include <linux/in.h>
#include <linux/export.h>
+#include <asm/unaligned.h>
#include <net/sock.h>
#include <net/tcp.h>
#include <scsi/scsi.h>
@@ -527,7 +528,7 @@
list_add_tail(&port->sep_list, &dev->dev_sep_list);
spin_unlock(&dev->se_port_lock);
- if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV &&
+ if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) &&
!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) {
tg_pt_gp_mem = core_alua_allocate_tg_pt_gp_mem(port);
if (IS_ERR(tg_pt_gp_mem) || !tg_pt_gp_mem) {
@@ -1603,7 +1604,7 @@
* anything virtual (IBLOCK, FILEIO, RAMDISK), but not for TCM/pSCSI
* passthrough because this is being provided by the backend LLD.
*/
- if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV) {
+ if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)) {
strncpy(&dev->t10_wwn.vendor[0], "LIO-ORG", 8);
strncpy(&dev->t10_wwn.model[0],
dev->transport->inquiry_prod, 16);
@@ -1707,3 +1708,76 @@
target_free_device(g_lun0_dev);
core_delete_hba(hba);
}
+
+/*
+ * Common CDB parsing for kernel and user passthrough.
+ */
+sense_reason_t
+passthrough_parse_cdb(struct se_cmd *cmd,
+ sense_reason_t (*exec_cmd)(struct se_cmd *cmd))
+{
+ unsigned char *cdb = cmd->t_task_cdb;
+
+ /*
+ * Clear a lun set in the cdb if the initiator talking to use spoke
+ * and old standards version, as we can't assume the underlying device
+ * won't choke up on it.
+ */
+ switch (cdb[0]) {
+ case READ_10: /* SBC - RDProtect */
+ case READ_12: /* SBC - RDProtect */
+ case READ_16: /* SBC - RDProtect */
+ case SEND_DIAGNOSTIC: /* SPC - SELF-TEST Code */
+ case VERIFY: /* SBC - VRProtect */
+ case VERIFY_16: /* SBC - VRProtect */
+ case WRITE_VERIFY: /* SBC - VRProtect */
+ case WRITE_VERIFY_12: /* SBC - VRProtect */
+ case MAINTENANCE_IN: /* SPC - Parameter Data Format for SA RTPG */
+ break;
+ default:
+ cdb[1] &= 0x1f; /* clear logical unit number */
+ break;
+ }
+
+ /*
+ * For REPORT LUNS we always need to emulate the response, for everything
+ * else, pass it up.
+ */
+ if (cdb[0] == REPORT_LUNS) {
+ cmd->execute_cmd = spc_emulate_report_luns;
+ return TCM_NO_SENSE;
+ }
+
+ /* Set DATA_CDB flag for ops that should have it */
+ switch (cdb[0]) {
+ case READ_6:
+ case READ_10:
+ case READ_12:
+ case READ_16:
+ case WRITE_6:
+ case WRITE_10:
+ case WRITE_12:
+ case WRITE_16:
+ case WRITE_VERIFY:
+ case WRITE_VERIFY_12:
+ case 0x8e: /* WRITE_VERIFY_16 */
+ case COMPARE_AND_WRITE:
+ case XDWRITEREAD_10:
+ cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
+ break;
+ case VARIABLE_LENGTH_CMD:
+ switch (get_unaligned_be16(&cdb[8])) {
+ case READ_32:
+ case WRITE_32:
+ case 0x0c: /* WRITE_VERIFY_32 */
+ case XDWRITEREAD_32:
+ cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
+ break;
+ }
+ }
+
+ cmd->execute_cmd = exec_cmd;
+
+ return TCM_NO_SENSE;
+}
+EXPORT_SYMBOL(passthrough_parse_cdb);
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index f7e6e51..3f27bfd 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -958,7 +958,6 @@
.inquiry_prod = "FILEIO",
.inquiry_rev = FD_VERSION,
.owner = THIS_MODULE,
- .transport_type = TRANSPORT_PLUGIN_VHBA_PDEV,
.attach_hba = fd_attach_hba,
.detach_hba = fd_detach_hba,
.alloc_device = fd_alloc_device,
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 1b7947c..8c96568 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -904,7 +904,6 @@
.inquiry_prod = "IBLOCK",
.inquiry_rev = IBLOCK_VERSION,
.owner = THIS_MODULE,
- .transport_type = TRANSPORT_PLUGIN_VHBA_PDEV,
.attach_hba = iblock_attach_hba,
.detach_hba = iblock_detach_hba,
.alloc_device = iblock_alloc_device,
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index 874a9bc..68bd7f5 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -4,9 +4,6 @@
/* target_core_alua.c */
extern struct t10_alua_lu_gp *default_lu_gp;
-/* target_core_configfs.c */
-extern struct configfs_subsystem *target_core_subsystem[];
-
/* target_core_device.c */
extern struct mutex g_device_mutex;
extern struct list_head g_device_list;
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index c1aa965..a15411c 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -1367,41 +1367,26 @@
static int core_scsi3_tpg_depend_item(struct se_portal_group *tpg)
{
- return configfs_depend_item(tpg->se_tpg_tfo->tf_subsys,
- &tpg->tpg_group.cg_item);
+ return target_depend_item(&tpg->tpg_group.cg_item);
}
static void core_scsi3_tpg_undepend_item(struct se_portal_group *tpg)
{
- configfs_undepend_item(tpg->se_tpg_tfo->tf_subsys,
- &tpg->tpg_group.cg_item);
-
+ target_undepend_item(&tpg->tpg_group.cg_item);
atomic_dec_mb(&tpg->tpg_pr_ref_count);
}
static int core_scsi3_nodeacl_depend_item(struct se_node_acl *nacl)
{
- struct se_portal_group *tpg = nacl->se_tpg;
-
if (nacl->dynamic_node_acl)
return 0;
-
- return configfs_depend_item(tpg->se_tpg_tfo->tf_subsys,
- &nacl->acl_group.cg_item);
+ return target_depend_item(&nacl->acl_group.cg_item);
}
static void core_scsi3_nodeacl_undepend_item(struct se_node_acl *nacl)
{
- struct se_portal_group *tpg = nacl->se_tpg;
-
- if (nacl->dynamic_node_acl) {
- atomic_dec_mb(&nacl->acl_pr_ref_count);
- return;
- }
-
- configfs_undepend_item(tpg->se_tpg_tfo->tf_subsys,
- &nacl->acl_group.cg_item);
-
+ if (!nacl->dynamic_node_acl)
+ target_undepend_item(&nacl->acl_group.cg_item);
atomic_dec_mb(&nacl->acl_pr_ref_count);
}
@@ -1419,8 +1404,7 @@
nacl = lun_acl->se_lun_nacl;
tpg = nacl->se_tpg;
- return configfs_depend_item(tpg->se_tpg_tfo->tf_subsys,
- &lun_acl->se_lun_group.cg_item);
+ return target_depend_item(&lun_acl->se_lun_group.cg_item);
}
static void core_scsi3_lunacl_undepend_item(struct se_dev_entry *se_deve)
@@ -1438,9 +1422,7 @@
nacl = lun_acl->se_lun_nacl;
tpg = nacl->se_tpg;
- configfs_undepend_item(tpg->se_tpg_tfo->tf_subsys,
- &lun_acl->se_lun_group.cg_item);
-
+ target_undepend_item(&lun_acl->se_lun_group.cg_item);
atomic_dec_mb(&se_deve->pr_ref_count);
}
@@ -4111,7 +4093,7 @@
return 0;
if (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)
return 0;
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return 0;
spin_lock(&dev->dev_reservation_lock);
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index f6c954c..ecc5eae 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -521,6 +521,7 @@
" pdv_host_id: %d\n", pdv->pdv_host_id);
return -EINVAL;
}
+ pdv->pdv_lld_host = sh;
}
} else {
if (phv->phv_mode == PHV_VIRTUAL_HOST_ID) {
@@ -603,6 +604,8 @@
if ((phv->phv_mode == PHV_LLD_SCSI_HOST_NO) &&
(phv->phv_lld_host != NULL))
scsi_host_put(phv->phv_lld_host);
+ else if (pdv->pdv_lld_host)
+ scsi_host_put(pdv->pdv_lld_host);
if ((sd->type == TYPE_DISK) || (sd->type == TYPE_ROM))
scsi_device_put(sd);
@@ -970,64 +973,13 @@
return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
}
-/*
- * Clear a lun set in the cdb if the initiator talking to use spoke
- * and old standards version, as we can't assume the underlying device
- * won't choke up on it.
- */
-static inline void pscsi_clear_cdb_lun(unsigned char *cdb)
-{
- switch (cdb[0]) {
- case READ_10: /* SBC - RDProtect */
- case READ_12: /* SBC - RDProtect */
- case READ_16: /* SBC - RDProtect */
- case SEND_DIAGNOSTIC: /* SPC - SELF-TEST Code */
- case VERIFY: /* SBC - VRProtect */
- case VERIFY_16: /* SBC - VRProtect */
- case WRITE_VERIFY: /* SBC - VRProtect */
- case WRITE_VERIFY_12: /* SBC - VRProtect */
- case MAINTENANCE_IN: /* SPC - Parameter Data Format for SA RTPG */
- break;
- default:
- cdb[1] &= 0x1f; /* clear logical unit number */
- break;
- }
-}
-
static sense_reason_t
pscsi_parse_cdb(struct se_cmd *cmd)
{
- unsigned char *cdb = cmd->t_task_cdb;
-
if (cmd->se_cmd_flags & SCF_BIDI)
return TCM_UNSUPPORTED_SCSI_OPCODE;
- pscsi_clear_cdb_lun(cdb);
-
- /*
- * For REPORT LUNS we always need to emulate the response, for everything
- * else the default for pSCSI is to pass the command to the underlying
- * LLD / physical hardware.
- */
- switch (cdb[0]) {
- case REPORT_LUNS:
- cmd->execute_cmd = spc_emulate_report_luns;
- return 0;
- case READ_6:
- case READ_10:
- case READ_12:
- case READ_16:
- case WRITE_6:
- case WRITE_10:
- case WRITE_12:
- case WRITE_16:
- case WRITE_VERIFY:
- cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
- /* FALLTHROUGH*/
- default:
- cmd->execute_cmd = pscsi_execute_cmd;
- return 0;
- }
+ return passthrough_parse_cdb(cmd, pscsi_execute_cmd);
}
static sense_reason_t
@@ -1189,7 +1141,7 @@
static struct se_subsystem_api pscsi_template = {
.name = "pscsi",
.owner = THIS_MODULE,
- .transport_type = TRANSPORT_PLUGIN_PHBA_PDEV,
+ .transport_flags = TRANSPORT_FLAG_PASSTHROUGH,
.attach_hba = pscsi_attach_hba,
.detach_hba = pscsi_detach_hba,
.pmode_enable_hba = pscsi_pmode_enable_hba,
diff --git a/drivers/target/target_core_pscsi.h b/drivers/target/target_core_pscsi.h
index 1bd757d..820d305 100644
--- a/drivers/target/target_core_pscsi.h
+++ b/drivers/target/target_core_pscsi.h
@@ -45,6 +45,7 @@
int pdv_lun_id;
struct block_device *pdv_bd;
struct scsi_device *pdv_sd;
+ struct Scsi_Host *pdv_lld_host;
} ____cacheline_aligned;
typedef enum phv_modes {
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index a263bf5..d16489b 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -733,7 +733,6 @@
.name = "rd_mcp",
.inquiry_prod = "RAMDISK-MCP",
.inquiry_rev = RD_MCP_VERSION,
- .transport_type = TRANSPORT_PLUGIN_VHBA_VDEV,
.attach_hba = rd_attach_hba,
.detach_hba = rd_detach_hba,
.alloc_device = rd_alloc_device,
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 8855781..733824e 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -568,7 +568,7 @@
* comparision using SGLs at cmd->t_bidi_data_sg..
*/
rc = down_interruptible(&dev->caw_sem);
- if ((rc != 0) || signal_pending(current)) {
+ if (rc != 0) {
cmd->transport_complete_callback = NULL;
return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
}
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 3fe5cb2..675f2d9 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1196,7 +1196,7 @@
* Check if SAM Task Attribute emulation is enabled for this
* struct se_device storage object
*/
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return 0;
if (cmd->sam_task_attr == TCM_ACA_TAG) {
@@ -1770,7 +1770,7 @@
sectors, 0, NULL, 0);
if (unlikely(cmd->pi_err)) {
spin_lock_irq(&cmd->t_state_lock);
- cmd->transport_state &= ~CMD_T_BUSY|CMD_T_SENT;
+ cmd->transport_state &= ~(CMD_T_BUSY|CMD_T_SENT);
spin_unlock_irq(&cmd->t_state_lock);
transport_generic_request_failure(cmd, cmd->pi_err);
return -1;
@@ -1787,7 +1787,7 @@
{
struct se_device *dev = cmd->se_dev;
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return false;
/*
@@ -1868,7 +1868,7 @@
if (target_handle_task_attr(cmd)) {
spin_lock_irq(&cmd->t_state_lock);
- cmd->transport_state &= ~CMD_T_BUSY|CMD_T_SENT;
+ cmd->transport_state &= ~(CMD_T_BUSY | CMD_T_SENT);
spin_unlock_irq(&cmd->t_state_lock);
return;
}
@@ -1912,7 +1912,7 @@
{
struct se_device *dev = cmd->se_dev;
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return;
if (cmd->sam_task_attr == TCM_SIMPLE_TAG) {
@@ -1957,8 +1957,7 @@
case DMA_TO_DEVICE:
if (cmd->se_cmd_flags & SCF_BIDI) {
ret = cmd->se_tfo->queue_data_in(cmd);
- if (ret < 0)
- break;
+ break;
}
/* Fall through for DMA_TO_DEVICE */
case DMA_NONE:
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index dbc872a..07d2996 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -71,13 +71,6 @@
u32 host_id;
};
-/* User wants all cmds or just some */
-enum passthru_level {
- TCMU_PASS_ALL = 0,
- TCMU_PASS_IO,
- TCMU_PASS_INVALID,
-};
-
#define TCMU_CONFIG_LEN 256
struct tcmu_dev {
@@ -89,7 +82,6 @@
#define TCMU_DEV_BIT_OPEN 0
#define TCMU_DEV_BIT_BROKEN 1
unsigned long flags;
- enum passthru_level pass_level;
struct uio_info uio_info;
@@ -683,8 +675,6 @@
setup_timer(&udev->timeout, tcmu_device_timedout,
(unsigned long)udev);
- udev->pass_level = TCMU_PASS_ALL;
-
return &udev->se_dev;
}
@@ -948,13 +938,13 @@
}
enum {
- Opt_dev_config, Opt_dev_size, Opt_err, Opt_pass_level,
+ Opt_dev_config, Opt_dev_size, Opt_hw_block_size, Opt_err,
};
static match_table_t tokens = {
{Opt_dev_config, "dev_config=%s"},
{Opt_dev_size, "dev_size=%u"},
- {Opt_pass_level, "pass_level=%u"},
+ {Opt_hw_block_size, "hw_block_size=%u"},
{Opt_err, NULL}
};
@@ -965,7 +955,7 @@
char *orig, *ptr, *opts, *arg_p;
substring_t args[MAX_OPT_ARGS];
int ret = 0, token;
- int arg;
+ unsigned long tmp_ul;
opts = kstrdup(page, GFP_KERNEL);
if (!opts)
@@ -998,15 +988,23 @@
if (ret < 0)
pr_err("kstrtoul() failed for dev_size=\n");
break;
- case Opt_pass_level:
- match_int(args, &arg);
- if (arg >= TCMU_PASS_INVALID) {
- pr_warn("TCMU: Invalid pass_level: %d\n", arg);
+ case Opt_hw_block_size:
+ arg_p = match_strdup(&args[0]);
+ if (!arg_p) {
+ ret = -ENOMEM;
break;
}
-
- pr_debug("TCMU: Setting pass_level to %d\n", arg);
- udev->pass_level = arg;
+ ret = kstrtoul(arg_p, 0, &tmp_ul);
+ kfree(arg_p);
+ if (ret < 0) {
+ pr_err("kstrtoul() failed for hw_block_size=\n");
+ break;
+ }
+ if (!tmp_ul) {
+ pr_err("hw_block_size must be nonzero\n");
+ break;
+ }
+ dev->dev_attrib.hw_block_size = tmp_ul;
break;
default:
break;
@@ -1024,8 +1022,7 @@
bl = sprintf(b + bl, "Config: %s ",
udev->dev_config[0] ? udev->dev_config : "NULL");
- bl += sprintf(b + bl, "Size: %zu PassLevel: %u\n",
- udev->dev_size, udev->pass_level);
+ bl += sprintf(b + bl, "Size: %zu\n", udev->dev_size);
return bl;
}
@@ -1039,20 +1036,6 @@
}
static sense_reason_t
-tcmu_execute_rw(struct se_cmd *se_cmd, struct scatterlist *sgl, u32 sgl_nents,
- enum dma_data_direction data_direction)
-{
- int ret;
-
- ret = tcmu_queue_cmd(se_cmd);
-
- if (ret != 0)
- return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
- else
- return TCM_NO_SENSE;
-}
-
-static sense_reason_t
tcmu_pass_op(struct se_cmd *se_cmd)
{
int ret = tcmu_queue_cmd(se_cmd);
@@ -1063,91 +1046,29 @@
return TCM_NO_SENSE;
}
-static struct sbc_ops tcmu_sbc_ops = {
- .execute_rw = tcmu_execute_rw,
- .execute_sync_cache = tcmu_pass_op,
- .execute_write_same = tcmu_pass_op,
- .execute_write_same_unmap = tcmu_pass_op,
- .execute_unmap = tcmu_pass_op,
-};
-
static sense_reason_t
tcmu_parse_cdb(struct se_cmd *cmd)
{
- unsigned char *cdb = cmd->t_task_cdb;
- struct tcmu_dev *udev = TCMU_DEV(cmd->se_dev);
- sense_reason_t ret;
-
- switch (udev->pass_level) {
- case TCMU_PASS_ALL:
- /* We're just like pscsi, then */
- /*
- * For REPORT LUNS we always need to emulate the response, for everything
- * else, pass it up.
- */
- switch (cdb[0]) {
- case REPORT_LUNS:
- cmd->execute_cmd = spc_emulate_report_luns;
- break;
- case READ_6:
- case READ_10:
- case READ_12:
- case READ_16:
- case WRITE_6:
- case WRITE_10:
- case WRITE_12:
- case WRITE_16:
- case WRITE_VERIFY:
- cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
- /* FALLTHROUGH */
- default:
- cmd->execute_cmd = tcmu_pass_op;
- }
- ret = TCM_NO_SENSE;
- break;
- case TCMU_PASS_IO:
- ret = sbc_parse_cdb(cmd, &tcmu_sbc_ops);
- break;
- default:
- pr_err("Unknown tcm-user pass level %d\n", udev->pass_level);
- ret = TCM_CHECK_CONDITION_ABORT_CMD;
- }
-
- return ret;
+ return passthrough_parse_cdb(cmd, tcmu_pass_op);
}
-DEF_TB_DEFAULT_ATTRIBS(tcmu);
+DEF_TB_DEV_ATTRIB_RO(tcmu, hw_pi_prot_type);
+TB_DEV_ATTR_RO(tcmu, hw_pi_prot_type);
+
+DEF_TB_DEV_ATTRIB_RO(tcmu, hw_block_size);
+TB_DEV_ATTR_RO(tcmu, hw_block_size);
+
+DEF_TB_DEV_ATTRIB_RO(tcmu, hw_max_sectors);
+TB_DEV_ATTR_RO(tcmu, hw_max_sectors);
+
+DEF_TB_DEV_ATTRIB_RO(tcmu, hw_queue_depth);
+TB_DEV_ATTR_RO(tcmu, hw_queue_depth);
static struct configfs_attribute *tcmu_backend_dev_attrs[] = {
- &tcmu_dev_attrib_emulate_model_alias.attr,
- &tcmu_dev_attrib_emulate_dpo.attr,
- &tcmu_dev_attrib_emulate_fua_write.attr,
- &tcmu_dev_attrib_emulate_fua_read.attr,
- &tcmu_dev_attrib_emulate_write_cache.attr,
- &tcmu_dev_attrib_emulate_ua_intlck_ctrl.attr,
- &tcmu_dev_attrib_emulate_tas.attr,
- &tcmu_dev_attrib_emulate_tpu.attr,
- &tcmu_dev_attrib_emulate_tpws.attr,
- &tcmu_dev_attrib_emulate_caw.attr,
- &tcmu_dev_attrib_emulate_3pc.attr,
- &tcmu_dev_attrib_pi_prot_type.attr,
&tcmu_dev_attrib_hw_pi_prot_type.attr,
- &tcmu_dev_attrib_pi_prot_format.attr,
- &tcmu_dev_attrib_enforce_pr_isids.attr,
- &tcmu_dev_attrib_is_nonrot.attr,
- &tcmu_dev_attrib_emulate_rest_reord.attr,
- &tcmu_dev_attrib_force_pr_aptpl.attr,
&tcmu_dev_attrib_hw_block_size.attr,
- &tcmu_dev_attrib_block_size.attr,
&tcmu_dev_attrib_hw_max_sectors.attr,
- &tcmu_dev_attrib_optimal_sectors.attr,
&tcmu_dev_attrib_hw_queue_depth.attr,
- &tcmu_dev_attrib_queue_depth.attr,
- &tcmu_dev_attrib_max_unmap_lba_count.attr,
- &tcmu_dev_attrib_max_unmap_block_desc_count.attr,
- &tcmu_dev_attrib_unmap_granularity.attr,
- &tcmu_dev_attrib_unmap_granularity_alignment.attr,
- &tcmu_dev_attrib_max_write_same_len.attr,
NULL,
};
@@ -1156,7 +1077,7 @@
.inquiry_prod = "USER",
.inquiry_rev = TCMU_VERSION,
.owner = THIS_MODULE,
- .transport_type = TRANSPORT_PLUGIN_VHBA_PDEV,
+ .transport_flags = TRANSPORT_FLAG_PASSTHROUGH,
.attach_hba = tcmu_attach_hba,
.detach_hba = tcmu_detach_hba,
.alloc_device = tcmu_alloc_device,
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index a600ff1..8fd680a 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -58,7 +58,6 @@
bool src)
{
struct se_device *se_dev;
- struct configfs_subsystem *subsys = target_core_subsystem[0];
unsigned char tmp_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN], *dev_wwn;
int rc;
@@ -90,8 +89,7 @@
" se_dev\n", xop->src_dev);
}
- rc = configfs_depend_item(subsys,
- &se_dev->dev_group.cg_item);
+ rc = target_depend_item(&se_dev->dev_group.cg_item);
if (rc != 0) {
pr_err("configfs_depend_item attempt failed:"
" %d for se_dev: %p\n", rc, se_dev);
@@ -99,8 +97,8 @@
return rc;
}
- pr_debug("Called configfs_depend_item for subsys: %p se_dev: %p"
- " se_dev->se_dev_group: %p\n", subsys, se_dev,
+ pr_debug("Called configfs_depend_item for se_dev: %p"
+ " se_dev->se_dev_group: %p\n", se_dev,
&se_dev->dev_group);
mutex_unlock(&g_device_mutex);
@@ -373,7 +371,6 @@
static void xcopy_pt_undepend_remotedev(struct xcopy_op *xop)
{
- struct configfs_subsystem *subsys = target_core_subsystem[0];
struct se_device *remote_dev;
if (xop->op_origin == XCOL_SOURCE_RECV_OP)
@@ -381,11 +378,11 @@
else
remote_dev = xop->src_dev;
- pr_debug("Calling configfs_undepend_item for subsys: %p"
+ pr_debug("Calling configfs_undepend_item for"
" remote_dev: %p remote_dev->dev_group: %p\n",
- subsys, remote_dev, &remote_dev->dev_group.cg_item);
+ remote_dev, &remote_dev->dev_group.cg_item);
- configfs_undepend_item(subsys, &remote_dev->dev_group.cg_item);
+ target_undepend_item(&remote_dev->dev_group.cg_item);
}
static void xcopy_pt_release_cmd(struct se_cmd *se_cmd)
diff --git a/drivers/tty/mips_ejtag_fdc.c b/drivers/tty/mips_ejtag_fdc.c
index 04d9e23..358323c 100644
--- a/drivers/tty/mips_ejtag_fdc.c
+++ b/drivers/tty/mips_ejtag_fdc.c
@@ -174,13 +174,13 @@
static inline void mips_ejtag_fdc_write(struct mips_ejtag_fdc_tty *priv,
unsigned int offs, unsigned int data)
{
- iowrite32(data, priv->reg + offs);
+ __raw_writel(data, priv->reg + offs);
}
static inline unsigned int mips_ejtag_fdc_read(struct mips_ejtag_fdc_tty *priv,
unsigned int offs)
{
- return ioread32(priv->reg + offs);
+ return __raw_readl(priv->reg + offs);
}
/* Encoding of byte stream in FDC words */
@@ -347,9 +347,9 @@
s += inc[word.bytes - 1];
/* Busy wait until there's space in fifo */
- while (ioread32(regs + REG_FDSTAT) & REG_FDSTAT_TXF)
+ while (__raw_readl(regs + REG_FDSTAT) & REG_FDSTAT_TXF)
;
- iowrite32(word.word, regs + REG_FDTX(c->index));
+ __raw_writel(word.word, regs + REG_FDTX(c->index));
}
out:
local_irq_restore(flags);
@@ -1227,7 +1227,7 @@
/* Read next word from KGDB channel */
do {
- stat = ioread32(regs + REG_FDSTAT);
+ stat = __raw_readl(regs + REG_FDSTAT);
/* No data waiting? */
if (stat & REG_FDSTAT_RXE)
@@ -1236,7 +1236,7 @@
/* Read next word */
channel = (stat & REG_FDSTAT_RXCHAN) >>
REG_FDSTAT_RXCHAN_SHIFT;
- data = ioread32(regs + REG_FDRX);
+ data = __raw_readl(regs + REG_FDRX);
} while (channel != CONFIG_MIPS_EJTAG_FDC_KGDB_CHAN);
/* Decode into rbuf */
@@ -1266,9 +1266,10 @@
return;
/* Busy wait until there's space in fifo */
- while (ioread32(regs + REG_FDSTAT) & REG_FDSTAT_TXF)
+ while (__raw_readl(regs + REG_FDSTAT) & REG_FDSTAT_TXF)
;
- iowrite32(word.word, regs + REG_FDTX(CONFIG_MIPS_EJTAG_FDC_KGDB_CHAN));
+ __raw_writel(word.word,
+ regs + REG_FDTX(CONFIG_MIPS_EJTAG_FDC_KGDB_CHAN));
}
/* flush the whole write buffer to the TX FIFO */
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 5e19bb5..ea32b38 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1409,8 +1409,7 @@
* dependency now.
*/
se_tpg = &tpg->se_tpg;
- ret = configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys,
- &se_tpg->tpg_group.cg_item);
+ ret = target_depend_item(&se_tpg->tpg_group.cg_item);
if (ret) {
pr_warn("configfs_depend_item() failed: %d\n", ret);
kfree(vs_tpg);
@@ -1513,8 +1512,7 @@
* to allow vhost-scsi WWPN se_tpg->tpg_group shutdown to occur.
*/
se_tpg = &tpg->se_tpg;
- configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys,
- &se_tpg->tpg_group.cg_item);
+ target_undepend_item(&se_tpg->tpg_group.cg_item);
}
if (match) {
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c
index 3a145a6..6897f1c 100644
--- a/drivers/video/backlight/pwm_bl.c
+++ b/drivers/video/backlight/pwm_bl.c
@@ -274,6 +274,10 @@
pb->pwm = devm_pwm_get(&pdev->dev, NULL);
if (IS_ERR(pb->pwm)) {
+ ret = PTR_ERR(pb->pwm);
+ if (ret == -EPROBE_DEFER)
+ goto err_alloc;
+
dev_err(&pdev->dev, "unable to request PWM, trying legacy API\n");
pb->legacy = true;
pb->pwm = pwm_request(data->pwm_id, "pwm-backlight");
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 241ef68..cd46e41 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -918,7 +918,7 @@
total_size = total_mapping_size(elf_phdata,
loc->elf_ex.e_phnum);
if (!total_size) {
- error = -EINVAL;
+ retval = -EINVAL;
goto out_free_dentry;
}
}
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 430e034..7dc886c 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -24,6 +24,7 @@
#include "cifsfs.h"
#include "dns_resolve.h"
#include "cifs_debug.h"
+#include "cifs_unicode.h"
static LIST_HEAD(cifs_dfs_automount_list);
@@ -312,7 +313,7 @@
xid = get_xid();
rc = get_dfs_path(xid, ses, full_path + 1, cifs_sb->local_nls,
&num_referrals, &referrals,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ cifs_remap(cifs_sb));
free_xid(xid);
cifs_put_tlink(tlink);
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 0303c67..5a53ac6 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -27,41 +27,6 @@
#include "cifsglob.h"
#include "cifs_debug.h"
-/*
- * cifs_utf16_bytes - how long will a string be after conversion?
- * @utf16 - pointer to input string
- * @maxbytes - don't go past this many bytes of input string
- * @codepage - destination codepage
- *
- * Walk a utf16le string and return the number of bytes that the string will
- * be after being converted to the given charset, not including any null
- * termination required. Don't walk past maxbytes in the source buffer.
- */
-int
-cifs_utf16_bytes(const __le16 *from, int maxbytes,
- const struct nls_table *codepage)
-{
- int i;
- int charlen, outlen = 0;
- int maxwords = maxbytes / 2;
- char tmp[NLS_MAX_CHARSET_SIZE];
- __u16 ftmp;
-
- for (i = 0; i < maxwords; i++) {
- ftmp = get_unaligned_le16(&from[i]);
- if (ftmp == 0)
- break;
-
- charlen = codepage->uni2char(ftmp, tmp, NLS_MAX_CHARSET_SIZE);
- if (charlen > 0)
- outlen += charlen;
- else
- outlen++;
- }
-
- return outlen;
-}
-
int cifs_remap(struct cifs_sb_info *cifs_sb)
{
int map_type;
@@ -155,10 +120,13 @@
* enough to hold the result of the conversion (at least NLS_MAX_CHARSET_SIZE).
*/
static int
-cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp,
+cifs_mapchar(char *target, const __u16 *from, const struct nls_table *cp,
int maptype)
{
int len = 1;
+ __u16 src_char;
+
+ src_char = *from;
if ((maptype == SFM_MAP_UNI_RSVD) && convert_sfm_char(src_char, target))
return len;
@@ -168,10 +136,23 @@
/* if character not one of seven in special remap set */
len = cp->uni2char(src_char, target, NLS_MAX_CHARSET_SIZE);
- if (len <= 0) {
- *target = '?';
- len = 1;
- }
+ if (len <= 0)
+ goto surrogate_pair;
+
+ return len;
+
+surrogate_pair:
+ /* convert SURROGATE_PAIR and IVS */
+ if (strcmp(cp->charset, "utf8"))
+ goto unknown;
+ len = utf16s_to_utf8s(from, 3, UTF16_LITTLE_ENDIAN, target, 6);
+ if (len <= 0)
+ goto unknown;
+ return len;
+
+unknown:
+ *target = '?';
+ len = 1;
return len;
}
@@ -206,7 +187,7 @@
int nullsize = nls_nullsize(codepage);
int fromwords = fromlen / 2;
char tmp[NLS_MAX_CHARSET_SIZE];
- __u16 ftmp;
+ __u16 ftmp[3]; /* ftmp[3] = 3array x 2bytes = 6bytes UTF-16 */
/*
* because the chars can be of varying widths, we need to take care
@@ -217,9 +198,17 @@
safelen = tolen - (NLS_MAX_CHARSET_SIZE + nullsize);
for (i = 0; i < fromwords; i++) {
- ftmp = get_unaligned_le16(&from[i]);
- if (ftmp == 0)
+ ftmp[0] = get_unaligned_le16(&from[i]);
+ if (ftmp[0] == 0)
break;
+ if (i + 1 < fromwords)
+ ftmp[1] = get_unaligned_le16(&from[i + 1]);
+ else
+ ftmp[1] = 0;
+ if (i + 2 < fromwords)
+ ftmp[2] = get_unaligned_le16(&from[i + 2]);
+ else
+ ftmp[2] = 0;
/*
* check to see if converting this character might make the
@@ -234,6 +223,17 @@
/* put converted char into 'to' buffer */
charlen = cifs_mapchar(&to[outlen], ftmp, codepage, map_type);
outlen += charlen;
+
+ /* charlen (=bytes of UTF-8 for 1 character)
+ * 4bytes UTF-8(surrogate pair) is charlen=4
+ * (4bytes UTF-16 code)
+ * 7-8bytes UTF-8(IVS) is charlen=3+4 or 4+4
+ * (2 UTF-8 pairs divided to 2 UTF-16 pairs) */
+ if (charlen == 4)
+ i++;
+ else if (charlen >= 5)
+ /* 5-6bytes UTF-8 */
+ i += 2;
}
/* properly null-terminate string */
@@ -296,6 +296,46 @@
}
/*
+ * cifs_utf16_bytes - how long will a string be after conversion?
+ * @utf16 - pointer to input string
+ * @maxbytes - don't go past this many bytes of input string
+ * @codepage - destination codepage
+ *
+ * Walk a utf16le string and return the number of bytes that the string will
+ * be after being converted to the given charset, not including any null
+ * termination required. Don't walk past maxbytes in the source buffer.
+ */
+int
+cifs_utf16_bytes(const __le16 *from, int maxbytes,
+ const struct nls_table *codepage)
+{
+ int i;
+ int charlen, outlen = 0;
+ int maxwords = maxbytes / 2;
+ char tmp[NLS_MAX_CHARSET_SIZE];
+ __u16 ftmp[3];
+
+ for (i = 0; i < maxwords; i++) {
+ ftmp[0] = get_unaligned_le16(&from[i]);
+ if (ftmp[0] == 0)
+ break;
+ if (i + 1 < maxwords)
+ ftmp[1] = get_unaligned_le16(&from[i + 1]);
+ else
+ ftmp[1] = 0;
+ if (i + 2 < maxwords)
+ ftmp[2] = get_unaligned_le16(&from[i + 2]);
+ else
+ ftmp[2] = 0;
+
+ charlen = cifs_mapchar(tmp, ftmp, codepage, NO_MAP_UNI_RSVD);
+ outlen += charlen;
+ }
+
+ return outlen;
+}
+
+/*
* cifs_strndup_from_utf16 - copy a string from wire format to the local
* codepage
* @src - source string
@@ -409,10 +449,15 @@
char src_char;
__le16 dst_char;
wchar_t tmp;
+ wchar_t *wchar_to; /* UTF-16 */
+ int ret;
+ unicode_t u;
if (map_chars == NO_MAP_UNI_RSVD)
return cifs_strtoUTF16(target, source, PATH_MAX, cp);
+ wchar_to = kzalloc(6, GFP_KERNEL);
+
for (i = 0; i < srclen; j++) {
src_char = source[i];
charlen = 1;
@@ -441,11 +486,55 @@
* if no match, use question mark, which at least in
* some cases serves as wild card
*/
- if (charlen < 1) {
- dst_char = cpu_to_le16(0x003f);
- charlen = 1;
+ if (charlen > 0)
+ goto ctoUTF16;
+
+ /* convert SURROGATE_PAIR */
+ if (strcmp(cp->charset, "utf8") || !wchar_to)
+ goto unknown;
+ if (*(source + i) & 0x80) {
+ charlen = utf8_to_utf32(source + i, 6, &u);
+ if (charlen < 0)
+ goto unknown;
+ } else
+ goto unknown;
+ ret = utf8s_to_utf16s(source + i, charlen,
+ UTF16_LITTLE_ENDIAN,
+ wchar_to, 6);
+ if (ret < 0)
+ goto unknown;
+
+ i += charlen;
+ dst_char = cpu_to_le16(*wchar_to);
+ if (charlen <= 3)
+ /* 1-3bytes UTF-8 to 2bytes UTF-16 */
+ put_unaligned(dst_char, &target[j]);
+ else if (charlen == 4) {
+ /* 4bytes UTF-8(surrogate pair) to 4bytes UTF-16
+ * 7-8bytes UTF-8(IVS) divided to 2 UTF-16
+ * (charlen=3+4 or 4+4) */
+ put_unaligned(dst_char, &target[j]);
+ dst_char = cpu_to_le16(*(wchar_to + 1));
+ j++;
+ put_unaligned(dst_char, &target[j]);
+ } else if (charlen >= 5) {
+ /* 5-6bytes UTF-8 to 6bytes UTF-16 */
+ put_unaligned(dst_char, &target[j]);
+ dst_char = cpu_to_le16(*(wchar_to + 1));
+ j++;
+ put_unaligned(dst_char, &target[j]);
+ dst_char = cpu_to_le16(*(wchar_to + 2));
+ j++;
+ put_unaligned(dst_char, &target[j]);
}
+ continue;
+
+unknown:
+ dst_char = cpu_to_le16(0x003f);
+ charlen = 1;
}
+
+ctoUTF16:
/*
* character may take more than one byte in the source string,
* but will take exactly two bytes in the target string
@@ -456,6 +545,7 @@
ctoUTF16_out:
put_unaligned(0, &target[j]); /* Null terminate target unicode string */
+ kfree(wchar_to);
return j;
}
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index f5089bd..0a9fb6b 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -469,6 +469,8 @@
seq_puts(s, ",nouser_xattr");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
seq_puts(s, ",mapchars");
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR)
+ seq_puts(s, ",mapposix");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)
seq_puts(s, ",sfu");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index c31ce98..c63fd1d 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -361,11 +361,11 @@
extern int CIFSUnixCreateSymLink(const unsigned int xid,
struct cifs_tcon *tcon,
const char *fromName, const char *toName,
- const struct nls_table *nls_codepage);
+ const struct nls_table *nls_codepage, int remap);
extern int CIFSSMBUnixQuerySymLink(const unsigned int xid,
struct cifs_tcon *tcon,
const unsigned char *searchName, char **syminfo,
- const struct nls_table *nls_codepage);
+ const struct nls_table *nls_codepage, int remap);
extern int CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon,
__u16 fid, char **symlinkinfo,
const struct nls_table *nls_codepage);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 84650a5..f26ffbf 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -2784,7 +2784,7 @@
int
CIFSUnixCreateSymLink(const unsigned int xid, struct cifs_tcon *tcon,
const char *fromName, const char *toName,
- const struct nls_table *nls_codepage)
+ const struct nls_table *nls_codepage, int remap)
{
TRANSACTION2_SPI_REQ *pSMB = NULL;
TRANSACTION2_SPI_RSP *pSMBr = NULL;
@@ -2804,9 +2804,9 @@
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifs_strtoUTF16((__le16 *) pSMB->FileName, fromName,
- /* find define for this maxpathcomponent */
- PATH_MAX, nls_codepage);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName, fromName,
+ /* find define for this maxpathcomponent */
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
@@ -2828,9 +2828,9 @@
data_offset = (char *) (&pSMB->hdr.Protocol) + offset;
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len_target =
- cifs_strtoUTF16((__le16 *) data_offset, toName, PATH_MAX
- /* find define for this maxpathcomponent */
- , nls_codepage);
+ cifsConvertToUTF16((__le16 *) data_offset, toName,
+ /* find define for this maxpathcomponent */
+ PATH_MAX, nls_codepage, remap);
name_len_target++; /* trailing null */
name_len_target *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -3034,7 +3034,7 @@
int
CIFSSMBUnixQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon,
const unsigned char *searchName, char **symlinkinfo,
- const struct nls_table *nls_codepage)
+ const struct nls_table *nls_codepage, int remap)
{
/* SMB_QUERY_FILE_UNIX_LINK */
TRANSACTION2_QPI_REQ *pSMB = NULL;
@@ -3055,8 +3055,9 @@
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifs_strtoUTF16((__le16 *) pSMB->FileName, searchName,
- PATH_MAX, nls_codepage);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName,
+ searchName, PATH_MAX, nls_codepage,
+ remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
@@ -4917,7 +4918,7 @@
strncpy(pSMB->RequestFileName, search_name, name_len);
}
- if (ses->server && ses->server->sign)
+ if (ses->server->sign)
pSMB->hdr.Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
pSMB->hdr.Uid = ses->Suid;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index f3bfe08..8383d5e 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -386,6 +386,7 @@
rc = generic_ip_connect(server);
if (rc) {
cifs_dbg(FYI, "reconnect error %d\n", rc);
+ mutex_unlock(&server->srv_mutex);
msleep(3000);
} else {
atomic_inc(&tcpSesReconnectCount);
@@ -393,8 +394,8 @@
if (server->tcpStatus != CifsExiting)
server->tcpStatus = CifsNeedNegotiate;
spin_unlock(&GlobalMid_Lock);
+ mutex_unlock(&server->srv_mutex);
}
- mutex_unlock(&server->srv_mutex);
} while (server->tcpStatus == CifsNeedReconnect);
return rc;
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 338d569..c3eb998 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -620,8 +620,7 @@
}
rc = CIFSSMBUnixSetPathInfo(xid, tcon, full_path, &args,
cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ cifs_remap(cifs_sb));
if (rc)
goto mknod_out;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index cafbf10..3f50cee 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -140,8 +140,7 @@
posix_flags = cifs_posix_convert_flags(f_flags);
rc = CIFSPOSIXCreate(xid, tcon, posix_flags, mode, pnetfid, presp_data,
poplock, full_path, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ cifs_remap(cifs_sb));
cifs_put_tlink(tlink);
if (rc)
@@ -1553,8 +1552,8 @@
rc = server->ops->mand_unlock_range(cfile, flock, xid);
out:
- if (flock->fl_flags & FL_POSIX)
- posix_lock_file_wait(file, flock);
+ if (flock->fl_flags & FL_POSIX && !rc)
+ rc = posix_lock_file_wait(file, flock);
return rc;
}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 55b5811..f621b44 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -373,8 +373,7 @@
/* could have done a find first instead but this returns more info */
rc = CIFSSMBUnixQPathInfo(xid, tcon, full_path, &find_data,
- cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ cifs_sb->local_nls, cifs_remap(cifs_sb));
cifs_put_tlink(tlink);
if (!rc) {
@@ -402,9 +401,25 @@
rc = -ENOMEM;
} else {
/* we already have inode, update it */
+
+ /* if uniqueid is different, return error */
+ if (unlikely(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM &&
+ CIFS_I(*pinode)->uniqueid != fattr.cf_uniqueid)) {
+ rc = -ESTALE;
+ goto cgiiu_exit;
+ }
+
+ /* if filetype is different, return error */
+ if (unlikely(((*pinode)->i_mode & S_IFMT) !=
+ (fattr.cf_mode & S_IFMT))) {
+ rc = -ESTALE;
+ goto cgiiu_exit;
+ }
+
cifs_fattr_to_inode(*pinode, &fattr);
}
+cgiiu_exit:
return rc;
}
@@ -839,6 +854,15 @@
if (!*inode)
rc = -ENOMEM;
} else {
+ /* we already have inode, update it */
+
+ /* if filetype is different, return error */
+ if (unlikely(((*inode)->i_mode & S_IFMT) !=
+ (fattr.cf_mode & S_IFMT))) {
+ rc = -ESTALE;
+ goto cgii_exit;
+ }
+
cifs_fattr_to_inode(*inode, &fattr);
}
@@ -2215,8 +2239,7 @@
pTcon = tlink_tcon(tlink);
rc = CIFSSMBUnixSetPathInfo(xid, pTcon, full_path, args,
cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ cifs_remap(cifs_sb));
cifs_put_tlink(tlink);
}
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 252e672..e6c707c 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -717,7 +717,8 @@
rc = create_mf_symlink(xid, pTcon, cifs_sb, full_path, symname);
else if (pTcon->unix_ext)
rc = CIFSUnixCreateSymLink(xid, pTcon, full_path, symname,
- cifs_sb->local_nls);
+ cifs_sb->local_nls,
+ cifs_remap(cifs_sb));
/* else
rc = CIFSCreateReparseSymLink(xid, pTcon, fromName, toName,
cifs_sb_target->local_nls); */
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index b4a4723..b1eede3 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -90,6 +90,8 @@
if (dentry) {
inode = d_inode(dentry);
if (inode) {
+ if (d_mountpoint(dentry))
+ goto out;
/*
* If we're generating inode numbers, then we don't
* want to clobber the existing one with the one that
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 7bfdd60..fc537c2 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -960,7 +960,8 @@
/* Check for unix extensions */
if (cap_unix(tcon->ses)) {
rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, target_path,
- cifs_sb->local_nls);
+ cifs_sb->local_nls,
+ cifs_remap(cifs_sb));
if (rc == -EREMOTE)
rc = cifs_unix_dfs_readlink(xid, tcon, full_path,
target_path,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 65cd7a8..54cbe19 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -110,7 +110,7 @@
/* GLOBAL_CAP_LARGE_MTU will only be set if dialect > SMB2.02 */
/* See sections 2.2.4 and 3.2.4.1.5 of MS-SMB2 */
- if ((tcon->ses) &&
+ if ((tcon->ses) && (tcon->ses->server) &&
(tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU))
hdr->CreditCharge = cpu_to_le16(1);
/* else CreditCharge MBZ */
diff --git a/fs/dcache.c b/fs/dcache.c
index 656ce52..37b5afd 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1239,13 +1239,13 @@
/* might go back up the wrong parent if we have had a rename. */
if (need_seqretry(&rename_lock, seq))
goto rename_retry;
- next = child->d_child.next;
- while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) {
+ /* go into the first sibling still alive */
+ do {
+ next = child->d_child.next;
if (next == &this_parent->d_subdirs)
goto ascend;
child = list_entry(next, struct dentry, d_child);
- next = next->next;
- }
+ } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
rcu_read_unlock();
goto resume;
}
diff --git a/fs/omfs/bitmap.c b/fs/omfs/bitmap.c
index 0822345..83f4e76 100644
--- a/fs/omfs/bitmap.c
+++ b/fs/omfs/bitmap.c
@@ -159,7 +159,7 @@
goto out;
found:
- *return_block = i * bits_per_entry + bit;
+ *return_block = (u64) i * bits_per_entry + bit;
*return_size = run;
ret = set_run(sb, i, bits_per_entry, bit, run, 1);
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index 138321b..3d935c8 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -306,7 +306,8 @@
*/
static int omfs_get_imap(struct super_block *sb)
{
- unsigned int bitmap_size, count, array_size;
+ unsigned int bitmap_size, array_size;
+ int count;
struct omfs_sb_info *sbi = OMFS_SB(sb);
struct buffer_head *bh;
unsigned long **ptr;
@@ -359,7 +360,7 @@
}
enum {
- Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask
+ Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, Opt_err
};
static const match_table_t tokens = {
@@ -368,6 +369,7 @@
{Opt_umask, "umask=%o"},
{Opt_dmask, "dmask=%o"},
{Opt_fmask, "fmask=%o"},
+ {Opt_err, NULL},
};
static int parse_options(char *options, struct omfs_sb_info *sbi)
@@ -548,8 +550,10 @@
}
sb->s_root = d_make_root(root);
- if (!sb->s_root)
+ if (!sb->s_root) {
+ ret = -ENOMEM;
goto out_brelse_bh2;
+ }
printk(KERN_DEBUG "omfs: Mounted volume %s\n", omfs_rb->r_name);
ret = 0;
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 24f6404..84d693d 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -299,6 +299,9 @@
struct cred *override_cred;
char *link = NULL;
+ if (WARN_ON(!workdir))
+ return -EROFS;
+
ovl_path_upper(parent, &parentpath);
upperdir = parentpath.dentry;
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index d139405..692ceda 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -222,6 +222,9 @@
struct kstat stat;
int err;
+ if (WARN_ON(!workdir))
+ return ERR_PTR(-EROFS);
+
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out;
@@ -322,6 +325,9 @@
struct dentry *newdentry;
int err;
+ if (WARN_ON(!workdir))
+ return -EROFS;
+
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out;
@@ -506,11 +512,28 @@
struct dentry *opaquedir = NULL;
int err;
- if (is_dir && OVL_TYPE_MERGE_OR_LOWER(ovl_path_type(dentry))) {
- opaquedir = ovl_check_empty_and_clear(dentry);
- err = PTR_ERR(opaquedir);
- if (IS_ERR(opaquedir))
- goto out;
+ if (WARN_ON(!workdir))
+ return -EROFS;
+
+ if (is_dir) {
+ if (OVL_TYPE_MERGE_OR_LOWER(ovl_path_type(dentry))) {
+ opaquedir = ovl_check_empty_and_clear(dentry);
+ err = PTR_ERR(opaquedir);
+ if (IS_ERR(opaquedir))
+ goto out;
+ } else {
+ LIST_HEAD(list);
+
+ /*
+ * When removing an empty opaque directory, then it
+ * makes no sense to replace it with an exact replica of
+ * itself. But emptiness still needs to be checked.
+ */
+ err = ovl_check_empty_dir(dentry, &list);
+ ovl_cache_free(&list);
+ if (err)
+ goto out;
+ }
}
err = ovl_lock_rename_workdir(workdir, upperdir);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 5f0d199..bf8537c 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -529,7 +529,7 @@
{
struct ovl_fs *ufs = sb->s_fs_info;
- if (!(*flags & MS_RDONLY) && !ufs->upper_mnt)
+ if (!(*flags & MS_RDONLY) && (!ufs->upper_mnt || !ufs->workdir))
return -EROFS;
return 0;
@@ -925,9 +925,10 @@
ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry);
err = PTR_ERR(ufs->workdir);
if (IS_ERR(ufs->workdir)) {
- pr_err("overlayfs: failed to create directory %s/%s\n",
- ufs->config.workdir, OVL_WORKDIR_NAME);
- goto out_put_upper_mnt;
+ pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n",
+ ufs->config.workdir, OVL_WORKDIR_NAME, -err);
+ sb->s_flags |= MS_RDONLY;
+ ufs->workdir = NULL;
}
}
@@ -997,7 +998,6 @@
kfree(ufs->lower_mnt);
out_put_workdir:
dput(ufs->workdir);
-out_put_upper_mnt:
mntput(ufs->upper_mnt);
out_put_lowerpath:
for (i = 0; i < numlower; i++)
diff --git a/fs/select.c b/fs/select.c
index f684c75..0155473 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -189,7 +189,7 @@
* doesn't imply write barrier and the users expect write
* barrier semantics on wakeup functions. The following
* smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
- * and is paired with set_mb() in poll_schedule_timeout.
+ * and is paired with smp_store_mb() in poll_schedule_timeout.
*/
smp_wmb();
pwq->triggered = 1;
@@ -244,7 +244,7 @@
/*
* Prepare for the next iteration.
*
- * The following set_mb() serves two purposes. First, it's
+ * The following smp_store_mb() serves two purposes. First, it's
* the counterpart rmb of the wmb in pollwake() such that data
* written before wake up is always visible after wake up.
* Second, the full barrier guarantees that triggered clearing
@@ -252,7 +252,7 @@
* this problem doesn't exist for the first iteration as
* add_wait_queue() has full barrier semantics.
*/
- set_mb(pwq->triggered, 0);
+ smp_store_mb(pwq->triggered, 0);
return rc;
}
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 04e79d5..e9d401c 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -574,8 +574,8 @@
* After the last attribute is removed revert to original inode format,
* making all literal area available to the data fork once more.
*/
-STATIC void
-xfs_attr_fork_reset(
+void
+xfs_attr_fork_remove(
struct xfs_inode *ip,
struct xfs_trans *tp)
{
@@ -641,7 +641,7 @@
(mp->m_flags & XFS_MOUNT_ATTR2) &&
(dp->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
!(args->op_flags & XFS_DA_OP_ADDNAME)) {
- xfs_attr_fork_reset(dp, args->trans);
+ xfs_attr_fork_remove(dp, args->trans);
} else {
xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
@@ -905,7 +905,7 @@
if (forkoff == -1) {
ASSERT(dp->i_mount->m_flags & XFS_MOUNT_ATTR2);
ASSERT(dp->i_d.di_format != XFS_DINODE_FMT_BTREE);
- xfs_attr_fork_reset(dp, args->trans);
+ xfs_attr_fork_remove(dp, args->trans);
goto out;
}
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index 025c4b8..882c8d3 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -53,7 +53,7 @@
int xfs_attr_shortform_list(struct xfs_attr_list_context *context);
int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
int xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes);
-
+void xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp);
/*
* Internal routines when attribute fork size == XFS_LBSIZE(mp).
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index aeffeaa..f1026e8 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3224,12 +3224,24 @@
align_alen += temp;
align_off -= temp;
}
- /*
- * Same adjustment for the end of the requested area.
- */
- if ((temp = (align_alen % extsz))) {
+
+ /* Same adjustment for the end of the requested area. */
+ temp = (align_alen % extsz);
+ if (temp)
align_alen += extsz - temp;
- }
+
+ /*
+ * For large extent hint sizes, the aligned extent might be larger than
+ * MAXEXTLEN. In that case, reduce the size by an extsz so that it pulls
+ * the length back under MAXEXTLEN. The outer allocation loops handle
+ * short allocation just fine, so it is safe to do this. We only want to
+ * do it when we are forced to, though, because it means more allocation
+ * operations are required.
+ */
+ while (align_alen > MAXEXTLEN)
+ align_alen -= extsz;
+ ASSERT(align_alen <= MAXEXTLEN);
+
/*
* If the previous block overlaps with this proposed allocation
* then move the start forward without adjusting the length.
@@ -3318,7 +3330,9 @@
return -EINVAL;
} else {
ASSERT(orig_off >= align_off);
- ASSERT(orig_end <= align_off + align_alen);
+ /* see MAXEXTLEN handling above */
+ ASSERT(orig_end <= align_off + align_alen ||
+ align_alen + extsz > MAXEXTLEN);
}
#ifdef DEBUG
@@ -4099,13 +4113,6 @@
/* Figure out the extent size, adjust alen */
extsz = xfs_get_extsz_hint(ip);
if (extsz) {
- /*
- * Make sure we don't exceed a single extent length when we
- * align the extent by reducing length we are going to
- * allocate by the maximum amount extent size aligment may
- * require.
- */
- alen = XFS_FILBLKS_MIN(len, MAXEXTLEN - (2 * extsz - 1));
error = xfs_bmap_extsize_align(mp, got, prev, extsz, rt, eof,
1, 0, &aoff, &alen);
ASSERT(!error);
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 07349a1..1c9e755 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -376,7 +376,7 @@
*/
newlen = args.mp->m_ialloc_inos;
if (args.mp->m_maxicount &&
- percpu_counter_read(&args.mp->m_icount) + newlen >
+ percpu_counter_read_positive(&args.mp->m_icount) + newlen >
args.mp->m_maxicount)
return -ENOSPC;
args.minlen = args.maxlen = args.mp->m_ialloc_blks;
@@ -1339,10 +1339,13 @@
* If we have already hit the ceiling of inode blocks then clear
* okalloc so we scan all available agi structures for a free
* inode.
+ *
+ * Read rough value of mp->m_icount by percpu_counter_read_positive,
+ * which will sacrifice the preciseness but improve the performance.
*/
if (mp->m_maxicount &&
- percpu_counter_read(&mp->m_icount) + mp->m_ialloc_inos >
- mp->m_maxicount) {
+ percpu_counter_read_positive(&mp->m_icount) + mp->m_ialloc_inos
+ > mp->m_maxicount) {
noroom = 1;
okalloc = 0;
}
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index f9c1c64..3fbf167 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -380,23 +380,31 @@
return error;
}
+/*
+ * xfs_attr_inactive kills all traces of an attribute fork on an inode. It
+ * removes both the on-disk and in-memory inode fork. Note that this also has to
+ * handle the condition of inodes without attributes but with an attribute fork
+ * configured, so we can't use xfs_inode_hasattr() here.
+ *
+ * The in-memory attribute fork is removed even on error.
+ */
int
-xfs_attr_inactive(xfs_inode_t *dp)
+xfs_attr_inactive(
+ struct xfs_inode *dp)
{
- xfs_trans_t *trans;
- xfs_mount_t *mp;
- int error;
+ struct xfs_trans *trans;
+ struct xfs_mount *mp;
+ int cancel_flags = 0;
+ int lock_mode = XFS_ILOCK_SHARED;
+ int error = 0;
mp = dp->i_mount;
ASSERT(! XFS_NOT_DQATTACHED(mp, dp));
- xfs_ilock(dp, XFS_ILOCK_SHARED);
- if (!xfs_inode_hasattr(dp) ||
- dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
- xfs_iunlock(dp, XFS_ILOCK_SHARED);
- return 0;
- }
- xfs_iunlock(dp, XFS_ILOCK_SHARED);
+ xfs_ilock(dp, lock_mode);
+ if (!XFS_IFORK_Q(dp))
+ goto out_destroy_fork;
+ xfs_iunlock(dp, lock_mode);
/*
* Start our first transaction of the day.
@@ -408,13 +416,18 @@
* the inode in every transaction to let it float upward through
* the log.
*/
+ lock_mode = 0;
trans = xfs_trans_alloc(mp, XFS_TRANS_ATTRINVAL);
error = xfs_trans_reserve(trans, &M_RES(mp)->tr_attrinval, 0, 0);
- if (error) {
- xfs_trans_cancel(trans, 0);
- return error;
- }
- xfs_ilock(dp, XFS_ILOCK_EXCL);
+ if (error)
+ goto out_cancel;
+
+ lock_mode = XFS_ILOCK_EXCL;
+ cancel_flags = XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT;
+ xfs_ilock(dp, lock_mode);
+
+ if (!XFS_IFORK_Q(dp))
+ goto out_cancel;
/*
* No need to make quota reservations here. We expect to release some
@@ -422,29 +435,31 @@
*/
xfs_trans_ijoin(trans, dp, 0);
- /*
- * Decide on what work routines to call based on the inode size.
- */
- if (!xfs_inode_hasattr(dp) ||
- dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
- error = 0;
- goto out;
- }
- error = xfs_attr3_root_inactive(&trans, dp);
- if (error)
- goto out;
+ /* invalidate and truncate the attribute fork extents */
+ if (dp->i_d.di_aformat != XFS_DINODE_FMT_LOCAL) {
+ error = xfs_attr3_root_inactive(&trans, dp);
+ if (error)
+ goto out_cancel;
- error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
- if (error)
- goto out;
+ error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
+ if (error)
+ goto out_cancel;
+ }
+
+ /* Reset the attribute fork - this also destroys the in-core fork */
+ xfs_attr_fork_remove(dp, trans);
error = xfs_trans_commit(trans, XFS_TRANS_RELEASE_LOG_RES);
- xfs_iunlock(dp, XFS_ILOCK_EXCL);
-
+ xfs_iunlock(dp, lock_mode);
return error;
-out:
- xfs_trans_cancel(trans, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
- xfs_iunlock(dp, XFS_ILOCK_EXCL);
+out_cancel:
+ xfs_trans_cancel(trans, cancel_flags);
+out_destroy_fork:
+ /* kill the in-core attr fork before we drop the inode lock */
+ if (dp->i_afp)
+ xfs_idestroy_fork(dp, XFS_ATTR_FORK);
+ if (lock_mode)
+ xfs_iunlock(dp, lock_mode);
return error;
}
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 8121e75..3b75912 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -124,7 +124,7 @@
status = 0;
} while (count);
- return (-status);
+ return status;
}
int
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index d6ebc85..539a85f 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1946,21 +1946,17 @@
/*
* If there are attributes associated with the file then blow them away
* now. The code calls a routine that recursively deconstructs the
- * attribute fork. We need to just commit the current transaction
- * because we can't use it for xfs_attr_inactive().
+ * attribute fork. If also blows away the in-core attribute fork.
*/
- if (ip->i_d.di_anextents > 0) {
- ASSERT(ip->i_d.di_forkoff != 0);
-
+ if (XFS_IFORK_Q(ip)) {
error = xfs_attr_inactive(ip);
if (error)
return;
}
- if (ip->i_afp)
- xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-
+ ASSERT(!ip->i_afp);
ASSERT(ip->i_d.di_anextents == 0);
+ ASSERT(ip->i_d.di_forkoff == 0);
/*
* Free the inode.
@@ -2883,7 +2879,13 @@
if (error)
return error;
- /* Satisfy xfs_bumplink that this is a real tmpfile */
+ /*
+ * Prepare the tmpfile inode as if it were created through the VFS.
+ * Otherwise, the link increment paths will complain about nlink 0->1.
+ * Drop the link count as done by d_tmpfile(), complete the inode setup
+ * and flag it as linkable.
+ */
+ drop_nlink(VFS_I(tmpfile));
xfs_finish_inode_setup(tmpfile);
VFS_I(tmpfile)->i_state |= I_LINKABLE;
@@ -3151,7 +3153,7 @@
* intermediate state on disk.
*/
if (wip) {
- ASSERT(wip->i_d.di_nlink == 0);
+ ASSERT(VFS_I(wip)->i_nlink == 0 && wip->i_d.di_nlink == 0);
error = xfs_bumplink(tp, wip);
if (error)
goto out_trans_abort;
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 2ce7ee3..6f23fbd 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1084,14 +1084,18 @@
return xfs_sync_sb(mp, true);
}
+/*
+ * Deltas for the inode count are +/-64, hence we use a large batch size
+ * of 128 so we don't need to take the counter lock on every update.
+ */
+#define XFS_ICOUNT_BATCH 128
int
xfs_mod_icount(
struct xfs_mount *mp,
int64_t delta)
{
- /* deltas are +/-64, hence the large batch size of 128. */
- __percpu_counter_add(&mp->m_icount, delta, 128);
- if (percpu_counter_compare(&mp->m_icount, 0) < 0) {
+ __percpu_counter_add(&mp->m_icount, delta, XFS_ICOUNT_BATCH);
+ if (__percpu_counter_compare(&mp->m_icount, 0, XFS_ICOUNT_BATCH) < 0) {
ASSERT(0);
percpu_counter_add(&mp->m_icount, -delta);
return -EINVAL;
@@ -1113,6 +1117,14 @@
return 0;
}
+/*
+ * Deltas for the block count can vary from 1 to very large, but lock contention
+ * only occurs on frequent small block count updates such as in the delayed
+ * allocation path for buffered writes (page a time updates). Hence we set
+ * a large batch count (1024) to minimise global counter updates except when
+ * we get near to ENOSPC and we have to be very accurate with our updates.
+ */
+#define XFS_FDBLOCKS_BATCH 1024
int
xfs_mod_fdblocks(
struct xfs_mount *mp,
@@ -1151,25 +1163,19 @@
* Taking blocks away, need to be more accurate the closer we
* are to zero.
*
- * batch size is set to a maximum of 1024 blocks - if we are
- * allocating of freeing extents larger than this then we aren't
- * going to be hammering the counter lock so a lock per update
- * is not a problem.
- *
* If the counter has a value of less than 2 * max batch size,
* then make everything serialise as we are real close to
* ENOSPC.
*/
-#define __BATCH 1024
- if (percpu_counter_compare(&mp->m_fdblocks, 2 * __BATCH) < 0)
+ if (__percpu_counter_compare(&mp->m_fdblocks, 2 * XFS_FDBLOCKS_BATCH,
+ XFS_FDBLOCKS_BATCH) < 0)
batch = 1;
else
- batch = __BATCH;
-#undef __BATCH
+ batch = XFS_FDBLOCKS_BATCH;
__percpu_counter_add(&mp->m_fdblocks, delta, batch);
- if (percpu_counter_compare(&mp->m_fdblocks,
- XFS_ALLOC_SET_ASIDE(mp)) >= 0) {
+ if (__percpu_counter_compare(&mp->m_fdblocks, XFS_ALLOC_SET_ASIDE(mp),
+ XFS_FDBLOCKS_BATCH) >= 0) {
/* we had space! */
return 0;
}
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index f5c40b0f..e6a83d7 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -66,8 +66,8 @@
#define smp_read_barrier_depends() do { } while (0)
#endif
-#ifndef set_mb
-#define set_mb(var, value) do { (var) = (value); mb(); } while (0)
+#ifndef smp_store_mb
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0)
#endif
#ifndef smp_mb__before_atomic
diff --git a/include/asm-generic/cmpxchg.h b/include/asm-generic/cmpxchg.h
index 811fb1e..3766ab3 100644
--- a/include/asm-generic/cmpxchg.h
+++ b/include/asm-generic/cmpxchg.h
@@ -86,9 +86,6 @@
/*
* Atomic compare and exchange.
- *
- * Do not define __HAVE_ARCH_CMPXCHG because we want to use it to check whether
- * a cmpxchg primitive faster than repeated local irq save/restore exists.
*/
#include <asm-generic/cmpxchg-local.h>
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
new file mode 100644
index 0000000..83bfb87
--- /dev/null
+++ b/include/asm-generic/qspinlock.h
@@ -0,0 +1,139 @@
+/*
+ * Queued spinlock
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ */
+#ifndef __ASM_GENERIC_QSPINLOCK_H
+#define __ASM_GENERIC_QSPINLOCK_H
+
+#include <asm-generic/qspinlock_types.h>
+
+/**
+ * queued_spin_is_locked - is the spinlock locked?
+ * @lock: Pointer to queued spinlock structure
+ * Return: 1 if it is locked, 0 otherwise
+ */
+static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
+{
+ return atomic_read(&lock->val);
+}
+
+/**
+ * queued_spin_value_unlocked - is the spinlock structure unlocked?
+ * @lock: queued spinlock structure
+ * Return: 1 if it is unlocked, 0 otherwise
+ *
+ * N.B. Whenever there are tasks waiting for the lock, it is considered
+ * locked wrt the lockref code to avoid lock stealing by the lockref
+ * code and change things underneath the lock. This also allows some
+ * optimizations to be applied without conflict with lockref.
+ */
+static __always_inline int queued_spin_value_unlocked(struct qspinlock lock)
+{
+ return !atomic_read(&lock.val);
+}
+
+/**
+ * queued_spin_is_contended - check if the lock is contended
+ * @lock : Pointer to queued spinlock structure
+ * Return: 1 if lock contended, 0 otherwise
+ */
+static __always_inline int queued_spin_is_contended(struct qspinlock *lock)
+{
+ return atomic_read(&lock->val) & ~_Q_LOCKED_MASK;
+}
+/**
+ * queued_spin_trylock - try to acquire the queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ * Return: 1 if lock acquired, 0 if failed
+ */
+static __always_inline int queued_spin_trylock(struct qspinlock *lock)
+{
+ if (!atomic_read(&lock->val) &&
+ (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) == 0))
+ return 1;
+ return 0;
+}
+
+extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+
+/**
+ * queued_spin_lock - acquire a queued spinlock
+ * @lock: Pointer to queued spinlock structure
+ */
+static __always_inline void queued_spin_lock(struct qspinlock *lock)
+{
+ u32 val;
+
+ val = atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL);
+ if (likely(val == 0))
+ return;
+ queued_spin_lock_slowpath(lock, val);
+}
+
+#ifndef queued_spin_unlock
+/**
+ * queued_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ */
+static __always_inline void queued_spin_unlock(struct qspinlock *lock)
+{
+ /*
+ * smp_mb__before_atomic() in order to guarantee release semantics
+ */
+ smp_mb__before_atomic_dec();
+ atomic_sub(_Q_LOCKED_VAL, &lock->val);
+}
+#endif
+
+/**
+ * queued_spin_unlock_wait - wait until current lock holder releases the lock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * There is a very slight possibility of live-lock if the lockers keep coming
+ * and the waiter is just unfortunate enough to not see any unlock state.
+ */
+static inline void queued_spin_unlock_wait(struct qspinlock *lock)
+{
+ while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
+ cpu_relax();
+}
+
+#ifndef virt_queued_spin_lock
+static __always_inline bool virt_queued_spin_lock(struct qspinlock *lock)
+{
+ return false;
+}
+#endif
+
+/*
+ * Initializier
+ */
+#define __ARCH_SPIN_LOCK_UNLOCKED { ATOMIC_INIT(0) }
+
+/*
+ * Remapping spinlock architecture specific functions to the corresponding
+ * queued spinlock functions.
+ */
+#define arch_spin_is_locked(l) queued_spin_is_locked(l)
+#define arch_spin_is_contended(l) queued_spin_is_contended(l)
+#define arch_spin_value_unlocked(l) queued_spin_value_unlocked(l)
+#define arch_spin_lock(l) queued_spin_lock(l)
+#define arch_spin_trylock(l) queued_spin_trylock(l)
+#define arch_spin_unlock(l) queued_spin_unlock(l)
+#define arch_spin_lock_flags(l, f) queued_spin_lock(l)
+#define arch_spin_unlock_wait(l) queued_spin_unlock_wait(l)
+
+#endif /* __ASM_GENERIC_QSPINLOCK_H */
diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h
new file mode 100644
index 0000000..85f888e
--- /dev/null
+++ b/include/asm-generic/qspinlock_types.h
@@ -0,0 +1,79 @@
+/*
+ * Queued spinlock
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ */
+#ifndef __ASM_GENERIC_QSPINLOCK_TYPES_H
+#define __ASM_GENERIC_QSPINLOCK_TYPES_H
+
+/*
+ * Including atomic.h with PARAVIRT on will cause compilation errors because
+ * of recursive header file incluson via paravirt_types.h. So don't include
+ * it if PARAVIRT is on.
+ */
+#ifndef CONFIG_PARAVIRT
+#include <linux/types.h>
+#include <linux/atomic.h>
+#endif
+
+typedef struct qspinlock {
+ atomic_t val;
+} arch_spinlock_t;
+
+/*
+ * Bitfields in the atomic value:
+ *
+ * When NR_CPUS < 16K
+ * 0- 7: locked byte
+ * 8: pending
+ * 9-15: not used
+ * 16-17: tail index
+ * 18-31: tail cpu (+1)
+ *
+ * When NR_CPUS >= 16K
+ * 0- 7: locked byte
+ * 8: pending
+ * 9-10: tail index
+ * 11-31: tail cpu (+1)
+ */
+#define _Q_SET_MASK(type) (((1U << _Q_ ## type ## _BITS) - 1)\
+ << _Q_ ## type ## _OFFSET)
+#define _Q_LOCKED_OFFSET 0
+#define _Q_LOCKED_BITS 8
+#define _Q_LOCKED_MASK _Q_SET_MASK(LOCKED)
+
+#define _Q_PENDING_OFFSET (_Q_LOCKED_OFFSET + _Q_LOCKED_BITS)
+#if CONFIG_NR_CPUS < (1U << 14)
+#define _Q_PENDING_BITS 8
+#else
+#define _Q_PENDING_BITS 1
+#endif
+#define _Q_PENDING_MASK _Q_SET_MASK(PENDING)
+
+#define _Q_TAIL_IDX_OFFSET (_Q_PENDING_OFFSET + _Q_PENDING_BITS)
+#define _Q_TAIL_IDX_BITS 2
+#define _Q_TAIL_IDX_MASK _Q_SET_MASK(TAIL_IDX)
+
+#define _Q_TAIL_CPU_OFFSET (_Q_TAIL_IDX_OFFSET + _Q_TAIL_IDX_BITS)
+#define _Q_TAIL_CPU_BITS (32 - _Q_TAIL_CPU_OFFSET)
+#define _Q_TAIL_CPU_MASK _Q_SET_MASK(TAIL_CPU)
+
+#define _Q_TAIL_OFFSET _Q_TAIL_IDX_OFFSET
+#define _Q_TAIL_MASK (_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK)
+
+#define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET)
+#define _Q_PENDING_VAL (1U << _Q_PENDING_OFFSET)
+
+#endif /* __ASM_GENERIC_QSPINLOCK_TYPES_H */
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index ae2982c..656da2a 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -17,7 +17,7 @@
#define PHY_ID_BCM7250 0xae025280
#define PHY_ID_BCM7364 0xae025260
#define PHY_ID_BCM7366 0x600d8490
-#define PHY_ID_BCM7425 0x03625e60
+#define PHY_ID_BCM7425 0x600d86b0
#define PHY_ID_BCM7429 0x600d8730
#define PHY_ID_BCM7439 0x600d8480
#define PHY_ID_BCM7439_2 0xae025080
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 8677225..03e227b 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -250,7 +250,7 @@
({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
#define WRITE_ONCE(x, val) \
- ({ typeof(x) __val = (val); __write_once_size(&(x), &__val, sizeof(__val)); __val; })
+ ({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
#endif /* __KERNEL__ */
@@ -450,7 +450,7 @@
* with an explicit memory barrier or atomic instruction that provides the
* required ordering.
*
- * If possible use READ_ONCE/ASSIGN_ONCE instead.
+ * If possible use READ_ONCE()/WRITE_ONCE() instead.
*/
#define __ACCESS_ONCE(x) ({ \
__maybe_unused typeof(x) __var = (__force typeof(x)) 0; \
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 27e285b..59915ea 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -151,10 +151,8 @@
return 1;
}
-static inline int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp)
+static inline unsigned int cpumask_local_spread(unsigned int i, int node)
{
- set_bit(0, cpumask_bits(dstp));
-
return 0;
}
@@ -208,7 +206,7 @@
int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *);
int cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
-int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp);
+unsigned int cpumask_local_spread(unsigned int i, int node);
/**
* for_each_cpu - iterate over every cpu in a mask
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 3062495..e9bc929 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -185,33 +185,85 @@
struct irte {
union {
+ /* Shared between remapped and posted mode*/
struct {
- __u64 present : 1,
- fpd : 1,
- dst_mode : 1,
- redir_hint : 1,
- trigger_mode : 1,
- dlvry_mode : 3,
- avail : 4,
- __reserved_1 : 4,
- vector : 8,
- __reserved_2 : 8,
- dest_id : 32;
+ __u64 present : 1, /* 0 */
+ fpd : 1, /* 1 */
+ __res0 : 6, /* 2 - 6 */
+ avail : 4, /* 8 - 11 */
+ __res1 : 3, /* 12 - 14 */
+ pst : 1, /* 15 */
+ vector : 8, /* 16 - 23 */
+ __res2 : 40; /* 24 - 63 */
+ };
+
+ /* Remapped mode */
+ struct {
+ __u64 r_present : 1, /* 0 */
+ r_fpd : 1, /* 1 */
+ dst_mode : 1, /* 2 */
+ redir_hint : 1, /* 3 */
+ trigger_mode : 1, /* 4 */
+ dlvry_mode : 3, /* 5 - 7 */
+ r_avail : 4, /* 8 - 11 */
+ r_res0 : 4, /* 12 - 15 */
+ r_vector : 8, /* 16 - 23 */
+ r_res1 : 8, /* 24 - 31 */
+ dest_id : 32; /* 32 - 63 */
+ };
+
+ /* Posted mode */
+ struct {
+ __u64 p_present : 1, /* 0 */
+ p_fpd : 1, /* 1 */
+ p_res0 : 6, /* 2 - 7 */
+ p_avail : 4, /* 8 - 11 */
+ p_res1 : 2, /* 12 - 13 */
+ p_urgent : 1, /* 14 */
+ p_pst : 1, /* 15 */
+ p_vector : 8, /* 16 - 23 */
+ p_res2 : 14, /* 24 - 37 */
+ pda_l : 26; /* 38 - 63 */
};
__u64 low;
};
union {
+ /* Shared between remapped and posted mode*/
struct {
- __u64 sid : 16,
- sq : 2,
- svt : 2,
- __reserved_3 : 44;
+ __u64 sid : 16, /* 64 - 79 */
+ sq : 2, /* 80 - 81 */
+ svt : 2, /* 82 - 83 */
+ __res3 : 44; /* 84 - 127 */
+ };
+
+ /* Posted mode*/
+ struct {
+ __u64 p_sid : 16, /* 64 - 79 */
+ p_sq : 2, /* 80 - 81 */
+ p_svt : 2, /* 82 - 83 */
+ p_res3 : 12, /* 84 - 95 */
+ pda_h : 32; /* 96 - 127 */
};
__u64 high;
};
};
+static inline void dmar_copy_shared_irte(struct irte *dst, struct irte *src)
+{
+ dst->present = src->present;
+ dst->fpd = src->fpd;
+ dst->avail = src->avail;
+ dst->pst = src->pst;
+ dst->vector = src->vector;
+ dst->sid = src->sid;
+ dst->sq = src->sq;
+ dst->svt = src->svt;
+}
+
+#define PDA_LOW_BIT 26
+#define PDA_HIGH_BIT 32
+
enum {
IRQ_REMAP_XAPIC_MODE,
IRQ_REMAP_X2APIC_MODE,
@@ -227,6 +279,7 @@
extern void dmar_msi_write(int irq, struct msi_msg *msg);
extern int dmar_set_interrupt(struct intel_iommu *iommu);
extern irqreturn_t dmar_fault(int irq, void *dev_id);
-extern int arch_setup_dmar_msi(unsigned int irq);
+extern int dmar_alloc_hwirq(int id, int node, void *arg);
+extern void dmar_free_hwirq(int irq);
#endif /* __DMAR_H__ */
diff --git a/include/linux/htirq.h b/include/linux/htirq.h
index 70a1dbb..d4a527e 100644
--- a/include/linux/htirq.h
+++ b/include/linux/htirq.h
@@ -1,24 +1,38 @@
#ifndef LINUX_HTIRQ_H
#define LINUX_HTIRQ_H
+struct pci_dev;
+struct irq_data;
+
struct ht_irq_msg {
u32 address_lo; /* low 32 bits of the ht irq message */
u32 address_hi; /* high 32 bits of the it irq message */
};
+typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq,
+ struct ht_irq_msg *msg);
+
+struct ht_irq_cfg {
+ struct pci_dev *dev;
+ /* Update callback used to cope with buggy hardware */
+ ht_irq_update_t *update;
+ unsigned pos;
+ unsigned idx;
+ struct ht_irq_msg msg;
+};
+
/* Helper functions.. */
void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
-struct irq_data;
void mask_ht_irq(struct irq_data *data);
void unmask_ht_irq(struct irq_data *data);
/* The arch hook for getting things started */
-int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev);
+int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev,
+ ht_irq_update_t *update);
+void arch_teardown_ht_irq(unsigned int irq);
/* For drivers of buggy hardware */
-typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq,
- struct ht_irq_msg *msg);
int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update);
#endif /* LINUX_HTIRQ_H */
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 796ef96..0c251be 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -87,6 +87,7 @@
/*
* Decoding Capability Register
*/
+#define cap_pi_support(c) (((c) >> 59) & 1)
#define cap_read_drain(c) (((c) >> 55) & 1)
#define cap_write_drain(c) (((c) >> 54) & 1)
#define cap_max_amask_val(c) (((c) >> 48) & 0x3f)
@@ -298,6 +299,8 @@
#define INTR_REMAP_TABLE_ENTRIES 65536
+struct irq_domain;
+
struct ir_table {
struct irte *base;
unsigned long *bitmap;
@@ -347,6 +350,8 @@
#ifdef CONFIG_IRQ_REMAP
struct ir_table *ir_table; /* Interrupt remapping info */
+ struct irq_domain *ir_domain;
+ struct irq_domain *ir_msi_domain;
#endif
struct device *iommu_dev; /* IOMMU-sysfs device */
int node;
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 62c6901..48cb7d1 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -327,6 +327,7 @@
* @irq_write_msi_msg: optional to write message content for MSI
* @irq_get_irqchip_state: return the internal state of an interrupt
* @irq_set_irqchip_state: set the internal state of a interrupt
+ * @irq_set_vcpu_affinity: optional to target a vCPU in a virtual machine
* @flags: chip specific flags
*/
struct irq_chip {
@@ -369,6 +370,8 @@
int (*irq_get_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool *state);
int (*irq_set_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool state);
+ int (*irq_set_vcpu_affinity)(struct irq_data *data, void *vcpu_info);
+
unsigned long flags;
};
@@ -422,6 +425,7 @@
extern void irq_cpu_offline(void);
extern int irq_set_affinity_locked(struct irq_data *data,
const struct cpumask *cpumask, bool force);
+extern int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info);
#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
void irq_move_irq(struct irq_data *data);
@@ -467,6 +471,8 @@
const struct cpumask *dest,
bool force);
extern int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on);
+extern int irq_chip_set_vcpu_affinity_parent(struct irq_data *data,
+ void *vcpu_info);
#endif
/* Handling of unhandled and spurious interrupts: */
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index dd1109f..a113a8d 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -93,6 +93,15 @@
extern struct irq_desc irq_desc[NR_IRQS];
#endif
+static inline struct irq_desc *irq_data_to_desc(struct irq_data *data)
+{
+#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
+ return irq_to_desc(data->irq);
+#else
+ return container_of(data, struct irq_desc, irq_data);
+#endif
+}
+
static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc)
{
return &desc->irq_data;
diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h
index 3a6490e..703ea5c 100644
--- a/include/linux/osq_lock.h
+++ b/include/linux/osq_lock.h
@@ -32,4 +32,9 @@
extern bool osq_lock(struct optimistic_spin_queue *lock);
extern void osq_unlock(struct optimistic_spin_queue *lock);
+static inline bool osq_is_locked(struct optimistic_spin_queue *lock)
+{
+ return atomic_read(&lock->tail) != OSQ_UNLOCKED_VAL;
+}
+
#endif
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 50e5009..84a1094 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -41,7 +41,12 @@
void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
s64 __percpu_counter_sum(struct percpu_counter *fbc);
-int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs);
+int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch);
+
+static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
+{
+ return __percpu_counter_compare(fbc, rhs, percpu_counter_batch);
+}
static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
{
@@ -116,6 +121,12 @@
return 0;
}
+static inline int
+__percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
+{
+ return percpu_counter_compare(fbc, rhs);
+}
+
static inline void
percpu_counter_add(struct percpu_counter *fbc, s64 amount)
{
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 26a2e61..18f1972 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -252,7 +252,7 @@
#define set_task_state(tsk, state_value) \
do { \
(tsk)->task_state_change = _THIS_IP_; \
- set_mb((tsk)->state, (state_value)); \
+ smp_store_mb((tsk)->state, (state_value)); \
} while (0)
/*
@@ -274,7 +274,7 @@
#define set_current_state(state_value) \
do { \
current->task_state_change = _THIS_IP_; \
- set_mb(current->state, (state_value)); \
+ smp_store_mb(current->state, (state_value)); \
} while (0)
#else
@@ -282,7 +282,7 @@
#define __set_task_state(tsk, state_value) \
do { (tsk)->state = (state_value); } while (0)
#define set_task_state(tsk, state_value) \
- set_mb((tsk)->state, (state_value))
+ smp_store_mb((tsk)->state, (state_value))
/*
* set_current_state() includes a barrier so that the write of current->state
@@ -298,7 +298,7 @@
#define __set_current_state(state_value) \
do { current->state = (state_value); } while (0)
#define set_current_state(state_value) \
- set_mb(current->state, (state_value))
+ smp_store_mb(current->state, (state_value))
#endif
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 497bc14..0320bbb 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -98,7 +98,8 @@
const struct tcp_congestion_ops *icsk_ca_ops;
const struct inet_connection_sock_af_ops *icsk_af_ops;
unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
- __u8 icsk_ca_state:7,
+ __u8 icsk_ca_state:6,
+ icsk_ca_setsockopt:1,
icsk_ca_dst_locked:1;
__u8 icsk_retransmits;
__u8 icsk_pending;
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 8e3668b..fc57f6b 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -354,7 +354,7 @@
};
/**
- * enum ieee80211_rssi_event - data attached to an %RSSI_EVENT
+ * struct ieee80211_rssi_event - data attached to an %RSSI_EVENT
* @data: See &enum ieee80211_rssi_event_data
*/
struct ieee80211_rssi_event {
@@ -388,7 +388,7 @@
};
/**
- * enum ieee80211_mlme_event - data attached to an %MLME_EVENT
+ * struct ieee80211_mlme_event - data attached to an %MLME_EVENT
* @data: See &enum ieee80211_mlme_event_data
* @status: See &enum ieee80211_mlme_event_status
* @reason: the reason code if applicable
@@ -401,9 +401,10 @@
/**
* struct ieee80211_event - event to be sent to the driver
- * @type The event itself. See &enum ieee80211_event_type.
+ * @type: The event itself. See &enum ieee80211_event_type.
* @rssi: relevant if &type is %RSSI_EVENT
* @mlme: relevant if &type is %AUTH_EVENT
+ * @u: union holding the above two fields
*/
struct ieee80211_event {
enum ieee80211_event_type type;
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index c56a438..ce13cf2 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -574,11 +574,14 @@
/* Map v4 address to v4-mapped v6 address */
static inline void sctp_v4_map_v6(union sctp_addr *addr)
{
+ __be16 port;
+
+ port = addr->v4.sin_port;
+ addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
+ addr->v6.sin6_port = port;
addr->v6.sin6_family = AF_INET6;
addr->v6.sin6_flowinfo = 0;
addr->v6.sin6_scope_id = 0;
- addr->v6.sin6_port = addr->v4.sin_port;
- addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
addr->v6.sin6_addr.s6_addr32[0] = 0;
addr->v6.sin6_addr.s6_addr32[1] = 0;
addr->v6.sin6_addr.s6_addr32[2] = htonl(0x0000ffff);
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index d61be72..5f12257 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -1,9 +1,7 @@
#ifndef TARGET_CORE_BACKEND_H
#define TARGET_CORE_BACKEND_H
-#define TRANSPORT_PLUGIN_PHBA_PDEV 1
-#define TRANSPORT_PLUGIN_VHBA_PDEV 2
-#define TRANSPORT_PLUGIN_VHBA_VDEV 3
+#define TRANSPORT_FLAG_PASSTHROUGH 1
struct target_backend_cits {
struct config_item_type tb_dev_cit;
@@ -22,7 +20,7 @@
char inquiry_rev[4];
struct module *owner;
- u8 transport_type;
+ u8 transport_flags;
int (*attach_hba)(struct se_hba *, u32);
void (*detach_hba)(struct se_hba *);
@@ -138,5 +136,7 @@
int se_dev_set_max_sectors(struct se_device *, u32);
int se_dev_set_optimal_sectors(struct se_device *, u32);
int se_dev_set_block_size(struct se_device *, u32);
+sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd,
+ sense_reason_t (*exec_cmd)(struct se_cmd *cmd));
#endif /* TARGET_CORE_BACKEND_H */
diff --git a/include/target/target_core_configfs.h b/include/target/target_core_configfs.h
index 25bb04c..b99c011 100644
--- a/include/target/target_core_configfs.h
+++ b/include/target/target_core_configfs.h
@@ -40,8 +40,6 @@
struct config_item *tf_fabric;
/* Passed from fabric modules */
struct config_item_type *tf_fabric_cit;
- /* Pointer to target core subsystem */
- struct configfs_subsystem *tf_subsys;
/* Pointer to fabric's struct module */
struct module *tf_module;
struct target_core_fabric_ops tf_ops;
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 17c7f5ac..0f4dc37 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -4,7 +4,6 @@
struct target_core_fabric_ops {
struct module *module;
const char *name;
- struct configfs_subsystem *tf_subsys;
char *(*get_fabric_name)(void);
u8 (*get_fabric_proto_ident)(struct se_portal_group *);
char *(*tpg_get_wwn)(struct se_portal_group *);
@@ -109,6 +108,9 @@
int target_register_template(const struct target_core_fabric_ops *fo);
void target_unregister_template(const struct target_core_fabric_ops *fo);
+int target_depend_item(struct config_item *item);
+void target_undepend_item(struct config_item *item);
+
struct se_session *transport_init_session(enum target_prot_op);
int transport_alloc_session_tags(struct se_session *, unsigned int,
unsigned int);
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 81ea598..f7554fd 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -140,19 +140,42 @@
TP_ARGS(call_site, ptr)
);
-DEFINE_EVENT(kmem_free, kmem_cache_free,
+DEFINE_EVENT_CONDITION(kmem_free, kmem_cache_free,
TP_PROTO(unsigned long call_site, const void *ptr),
- TP_ARGS(call_site, ptr)
+ TP_ARGS(call_site, ptr),
+
+ /*
+ * This trace can be potentially called from an offlined cpu.
+ * Since trace points use RCU and RCU should not be used from
+ * offline cpus, filter such calls out.
+ * While this trace can be called from a preemptable section,
+ * it has no impact on the condition since tasks can migrate
+ * only from online cpus to other online cpus. Thus its safe
+ * to use raw_smp_processor_id.
+ */
+ TP_CONDITION(cpu_online(raw_smp_processor_id()))
);
-TRACE_EVENT(mm_page_free,
+TRACE_EVENT_CONDITION(mm_page_free,
TP_PROTO(struct page *page, unsigned int order),
TP_ARGS(page, order),
+
+ /*
+ * This trace can be potentially called from an offlined cpu.
+ * Since trace points use RCU and RCU should not be used from
+ * offline cpus, filter such calls out.
+ * While this trace can be called from a preemptable section,
+ * it has no impact on the condition since tasks can migrate
+ * only from online cpus to other online cpus. Thus its safe
+ * to use raw_smp_processor_id.
+ */
+ TP_CONDITION(cpu_online(raw_smp_processor_id())),
+
TP_STRUCT__entry(
__field( unsigned long, pfn )
__field( unsigned int, order )
@@ -253,12 +276,35 @@
TP_ARGS(page, order, migratetype)
);
-DEFINE_EVENT_PRINT(mm_page, mm_page_pcpu_drain,
+TRACE_EVENT_CONDITION(mm_page_pcpu_drain,
TP_PROTO(struct page *page, unsigned int order, int migratetype),
TP_ARGS(page, order, migratetype),
+ /*
+ * This trace can be potentially called from an offlined cpu.
+ * Since trace points use RCU and RCU should not be used from
+ * offline cpus, filter such calls out.
+ * While this trace can be called from a preemptable section,
+ * it has no impact on the condition since tasks can migrate
+ * only from online cpus to other online cpus. Thus its safe
+ * to use raw_smp_processor_id.
+ */
+ TP_CONDITION(cpu_online(raw_smp_processor_id())),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, pfn )
+ __field( unsigned int, order )
+ __field( int, migratetype )
+ ),
+
+ TP_fast_assign(
+ __entry->pfn = page ? page_to_pfn(page) : -1UL;
+ __entry->order = order;
+ __entry->migratetype = migratetype;
+ ),
+
TP_printk("page=%p pfn=%lu order=%d migratetype=%d",
pfn_to_page(__entry->pfn), __entry->pfn,
__entry->order, __entry->migratetype)
diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h
index 984169a..d7f1cbc 100644
--- a/include/uapi/linux/virtio_balloon.h
+++ b/include/uapi/linux/virtio_balloon.h
@@ -26,6 +26,7 @@
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE. */
#include <linux/types.h>
+#include <linux/virtio_types.h>
#include <linux/virtio_ids.h>
#include <linux/virtio_config.h>
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 08561f1..ebdb004 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -235,9 +235,16 @@
def_bool y
depends on MUTEX_SPIN_ON_OWNER || RWSEM_SPIN_ON_OWNER
-config ARCH_USE_QUEUE_RWLOCK
+config ARCH_USE_QUEUED_SPINLOCKS
bool
-config QUEUE_RWLOCK
- def_bool y if ARCH_USE_QUEUE_RWLOCK
+config QUEUED_SPINLOCKS
+ def_bool y if ARCH_USE_QUEUED_SPINLOCKS
+ depends on SMP
+
+config ARCH_USE_QUEUED_RWLOCKS
+ bool
+
+config QUEUED_RWLOCKS
+ def_bool y if ARCH_USE_QUEUED_RWLOCKS
depends on SMP
diff --git a/kernel/futex.c b/kernel/futex.c
index 2579e40..55ca63ad9 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2055,7 +2055,7 @@
{
/*
* The task state is guaranteed to be set before another task can
- * wake it. set_current_state() is implemented using set_mb() and
+ * wake it. set_current_state() is implemented using smp_store_mb() and
* queue_me() calls spin_unlock() upon completion, both serializing
* access to the hash list and forcing another memory barrier.
*/
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index eb9a4ea..55016b2 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -950,6 +950,20 @@
}
/**
+ * irq_chip_set_vcpu_affinity_parent - Set vcpu affinity on the parent interrupt
+ * @data: Pointer to interrupt specific data
+ * @dest: The vcpu affinity information
+ */
+int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info)
+{
+ data = data->parent_data;
+ if (data->chip->irq_set_vcpu_affinity)
+ return data->chip->irq_set_vcpu_affinity(data, vcpu_info);
+
+ return -ENOSYS;
+}
+
+/**
* irq_chip_set_wake_parent - Set/reset wake-up on the parent interrupt
* @data: Pointer to interrupt specific data
* @on: Whether to set or reset the wake-up capability of this irq
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index df553b0..b93d434 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -59,8 +59,6 @@
#include "debug.h"
#include "settings.h"
-#define irq_data_to_desc(data) container_of(data, struct irq_desc, irq_data)
-
extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
unsigned long flags);
extern void __disable_irq(struct irq_desc *desc, unsigned int irq);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index e68932b..b1c7e8f 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -256,6 +256,37 @@
}
EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
+/**
+ * irq_set_vcpu_affinity - Set vcpu affinity for the interrupt
+ * @irq: interrupt number to set affinity
+ * @vcpu_info: vCPU specific data
+ *
+ * This function uses the vCPU specific data to set the vCPU
+ * affinity for an irq. The vCPU specific data is passed from
+ * outside, such as KVM. One example code path is as below:
+ * KVM -> IOMMU -> irq_set_vcpu_affinity().
+ */
+int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info)
+{
+ unsigned long flags;
+ struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
+ struct irq_data *data;
+ struct irq_chip *chip;
+ int ret = -ENOSYS;
+
+ if (!desc)
+ return -EINVAL;
+
+ data = irq_desc_get_irq_data(desc);
+ chip = irq_data_get_irq_chip(data);
+ if (chip && chip->irq_set_vcpu_affinity)
+ ret = chip->irq_set_vcpu_affinity(data, vcpu_info);
+ irq_put_desc_unlock(desc, flags);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity);
+
static void irq_affinity_notify(struct work_struct *work)
{
struct irq_affinity_notify *notify =
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index ca3f4aa..dd203e2 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -7,7 +7,7 @@
void irq_move_masked_irq(struct irq_data *idata)
{
struct irq_desc *desc = irq_data_to_desc(idata);
- struct irq_chip *chip = idata->chip;
+ struct irq_chip *chip = desc->irq_data.chip;
if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
return;
@@ -52,6 +52,13 @@
{
bool masked;
+ /*
+ * Get top level irq_data when CONFIG_IRQ_DOMAIN_HIERARCHY is enabled,
+ * and it should be optimized away when CONFIG_IRQ_DOMAIN_HIERARCHY is
+ * disabled. So we avoid an "#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY" here.
+ */
+ idata = irq_desc_get_irq_data(irq_data_to_desc(idata));
+
if (likely(!irqd_is_setaffinity_pending(idata)))
return;
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index de7a416..7dd5c99 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -17,6 +17,7 @@
obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o
obj-$(CONFIG_SMP) += lglock.o
obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
+obj-$(CONFIG_QUEUED_SPINLOCKS) += qspinlock.o
obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
@@ -25,5 +26,5 @@
obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o
-obj-$(CONFIG_QUEUE_RWLOCK) += qrwlock.o
+obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index a0831e1..a61bb1d3 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4066,8 +4066,7 @@
#ifdef CONFIG_DEBUG_LOCKDEP
if (lockdep_init_error) {
- printk("WARNING: lockdep init error! lock-%s was acquired"
- "before lockdep_init\n", lock_init_error);
+ printk("WARNING: lockdep init error: lock '%s' was acquired before lockdep_init().\n", lock_init_error);
printk("Call stack leading to lockdep invocation was:\n");
print_stack_trace(&lockdep_init_trace, 0);
}
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index 75e114b..fd91aaa 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -17,6 +17,7 @@
struct mcs_spinlock {
struct mcs_spinlock *next;
int locked; /* 1 if lock acquired */
+ int count; /* nesting count, see qspinlock.c */
};
#ifndef arch_mcs_spin_lock_contended
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index f956ede..00c12bb 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -1,5 +1,5 @@
/*
- * Queue read/write lock
+ * Queued read/write locks
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
new file mode 100644
index 0000000..38c4920
--- /dev/null
+++ b/kernel/locking/qspinlock.c
@@ -0,0 +1,473 @@
+/*
+ * Queued spinlock
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ * (C) Copyright 2013-2014 Red Hat, Inc.
+ * (C) Copyright 2015 Intel Corp.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ * Peter Zijlstra <peterz@infradead.org>
+ */
+
+#ifndef _GEN_PV_LOCK_SLOWPATH
+
+#include <linux/smp.h>
+#include <linux/bug.h>
+#include <linux/cpumask.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <linux/mutex.h>
+#include <asm/byteorder.h>
+#include <asm/qspinlock.h>
+
+/*
+ * The basic principle of a queue-based spinlock can best be understood
+ * by studying a classic queue-based spinlock implementation called the
+ * MCS lock. The paper below provides a good description for this kind
+ * of lock.
+ *
+ * http://www.cise.ufl.edu/tr/DOC/REP-1992-71.pdf
+ *
+ * This queued spinlock implementation is based on the MCS lock, however to make
+ * it fit the 4 bytes we assume spinlock_t to be, and preserve its existing
+ * API, we must modify it somehow.
+ *
+ * In particular; where the traditional MCS lock consists of a tail pointer
+ * (8 bytes) and needs the next pointer (another 8 bytes) of its own node to
+ * unlock the next pending (next->locked), we compress both these: {tail,
+ * next->locked} into a single u32 value.
+ *
+ * Since a spinlock disables recursion of its own context and there is a limit
+ * to the contexts that can nest; namely: task, softirq, hardirq, nmi. As there
+ * are at most 4 nesting levels, it can be encoded by a 2-bit number. Now
+ * we can encode the tail by combining the 2-bit nesting level with the cpu
+ * number. With one byte for the lock value and 3 bytes for the tail, only a
+ * 32-bit word is now needed. Even though we only need 1 bit for the lock,
+ * we extend it to a full byte to achieve better performance for architectures
+ * that support atomic byte write.
+ *
+ * We also change the first spinner to spin on the lock bit instead of its
+ * node; whereby avoiding the need to carry a node from lock to unlock, and
+ * preserving existing lock API. This also makes the unlock code simpler and
+ * faster.
+ *
+ * N.B. The current implementation only supports architectures that allow
+ * atomic operations on smaller 8-bit and 16-bit data types.
+ *
+ */
+
+#include "mcs_spinlock.h"
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#define MAX_NODES 8
+#else
+#define MAX_NODES 4
+#endif
+
+/*
+ * Per-CPU queue node structures; we can never have more than 4 nested
+ * contexts: task, softirq, hardirq, nmi.
+ *
+ * Exactly fits one 64-byte cacheline on a 64-bit architecture.
+ *
+ * PV doubles the storage and uses the second cacheline for PV state.
+ */
+static DEFINE_PER_CPU_ALIGNED(struct mcs_spinlock, mcs_nodes[MAX_NODES]);
+
+/*
+ * We must be able to distinguish between no-tail and the tail at 0:0,
+ * therefore increment the cpu number by one.
+ */
+
+static inline u32 encode_tail(int cpu, int idx)
+{
+ u32 tail;
+
+#ifdef CONFIG_DEBUG_SPINLOCK
+ BUG_ON(idx > 3);
+#endif
+ tail = (cpu + 1) << _Q_TAIL_CPU_OFFSET;
+ tail |= idx << _Q_TAIL_IDX_OFFSET; /* assume < 4 */
+
+ return tail;
+}
+
+static inline struct mcs_spinlock *decode_tail(u32 tail)
+{
+ int cpu = (tail >> _Q_TAIL_CPU_OFFSET) - 1;
+ int idx = (tail & _Q_TAIL_IDX_MASK) >> _Q_TAIL_IDX_OFFSET;
+
+ return per_cpu_ptr(&mcs_nodes[idx], cpu);
+}
+
+#define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
+
+/*
+ * By using the whole 2nd least significant byte for the pending bit, we
+ * can allow better optimization of the lock acquisition for the pending
+ * bit holder.
+ *
+ * This internal structure is also used by the set_locked function which
+ * is not restricted to _Q_PENDING_BITS == 8.
+ */
+struct __qspinlock {
+ union {
+ atomic_t val;
+#ifdef __LITTLE_ENDIAN
+ struct {
+ u8 locked;
+ u8 pending;
+ };
+ struct {
+ u16 locked_pending;
+ u16 tail;
+ };
+#else
+ struct {
+ u16 tail;
+ u16 locked_pending;
+ };
+ struct {
+ u8 reserved[2];
+ u8 pending;
+ u8 locked;
+ };
+#endif
+ };
+};
+
+#if _Q_PENDING_BITS == 8
+/**
+ * clear_pending_set_locked - take ownership and clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,0 -> *,0,1
+ *
+ * Lock stealing is not allowed if this function is used.
+ */
+static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
+{
+ struct __qspinlock *l = (void *)lock;
+
+ WRITE_ONCE(l->locked_pending, _Q_LOCKED_VAL);
+}
+
+/*
+ * xchg_tail - Put in the new queue tail code word & retrieve previous one
+ * @lock : Pointer to queued spinlock structure
+ * @tail : The new queue tail code word
+ * Return: The previous queue tail code word
+ *
+ * xchg(lock, tail)
+ *
+ * p,*,* -> n,*,* ; prev = xchg(lock, node)
+ */
+static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
+{
+ struct __qspinlock *l = (void *)lock;
+
+ return (u32)xchg(&l->tail, tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
+}
+
+#else /* _Q_PENDING_BITS == 8 */
+
+/**
+ * clear_pending_set_locked - take ownership and clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,0 -> *,0,1
+ */
+static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
+{
+ atomic_add(-_Q_PENDING_VAL + _Q_LOCKED_VAL, &lock->val);
+}
+
+/**
+ * xchg_tail - Put in the new queue tail code word & retrieve previous one
+ * @lock : Pointer to queued spinlock structure
+ * @tail : The new queue tail code word
+ * Return: The previous queue tail code word
+ *
+ * xchg(lock, tail)
+ *
+ * p,*,* -> n,*,* ; prev = xchg(lock, node)
+ */
+static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
+{
+ u32 old, new, val = atomic_read(&lock->val);
+
+ for (;;) {
+ new = (val & _Q_LOCKED_PENDING_MASK) | tail;
+ old = atomic_cmpxchg(&lock->val, val, new);
+ if (old == val)
+ break;
+
+ val = old;
+ }
+ return old;
+}
+#endif /* _Q_PENDING_BITS == 8 */
+
+/**
+ * set_locked - Set the lock bit and own the lock
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,*,0 -> *,0,1
+ */
+static __always_inline void set_locked(struct qspinlock *lock)
+{
+ struct __qspinlock *l = (void *)lock;
+
+ WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
+}
+
+
+/*
+ * Generate the native code for queued_spin_unlock_slowpath(); provide NOPs for
+ * all the PV callbacks.
+ */
+
+static __always_inline void __pv_init_node(struct mcs_spinlock *node) { }
+static __always_inline void __pv_wait_node(struct mcs_spinlock *node) { }
+static __always_inline void __pv_kick_node(struct mcs_spinlock *node) { }
+
+static __always_inline void __pv_wait_head(struct qspinlock *lock,
+ struct mcs_spinlock *node) { }
+
+#define pv_enabled() false
+
+#define pv_init_node __pv_init_node
+#define pv_wait_node __pv_wait_node
+#define pv_kick_node __pv_kick_node
+#define pv_wait_head __pv_wait_head
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#define queued_spin_lock_slowpath native_queued_spin_lock_slowpath
+#endif
+
+#endif /* _GEN_PV_LOCK_SLOWPATH */
+
+/**
+ * queued_spin_lock_slowpath - acquire the queued spinlock
+ * @lock: Pointer to queued spinlock structure
+ * @val: Current value of the queued spinlock 32-bit word
+ *
+ * (queue tail, pending bit, lock value)
+ *
+ * fast : slow : unlock
+ * : :
+ * uncontended (0,0,0) -:--> (0,0,1) ------------------------------:--> (*,*,0)
+ * : | ^--------.------. / :
+ * : v \ \ | :
+ * pending : (0,1,1) +--> (0,1,0) \ | :
+ * : | ^--' | | :
+ * : v | | :
+ * uncontended : (n,x,y) +--> (n,0,0) --' | :
+ * queue : | ^--' | :
+ * : v | :
+ * contended : (*,x,y) +--> (*,0,0) ---> (*,0,1) -' :
+ * queue : ^--' :
+ */
+void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+ struct mcs_spinlock *prev, *next, *node;
+ u32 new, old, tail;
+ int idx;
+
+ BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
+
+ if (pv_enabled())
+ goto queue;
+
+ if (virt_queued_spin_lock(lock))
+ return;
+
+ /*
+ * wait for in-progress pending->locked hand-overs
+ *
+ * 0,1,0 -> 0,0,1
+ */
+ if (val == _Q_PENDING_VAL) {
+ while ((val = atomic_read(&lock->val)) == _Q_PENDING_VAL)
+ cpu_relax();
+ }
+
+ /*
+ * trylock || pending
+ *
+ * 0,0,0 -> 0,0,1 ; trylock
+ * 0,0,1 -> 0,1,1 ; pending
+ */
+ for (;;) {
+ /*
+ * If we observe any contention; queue.
+ */
+ if (val & ~_Q_LOCKED_MASK)
+ goto queue;
+
+ new = _Q_LOCKED_VAL;
+ if (val == new)
+ new |= _Q_PENDING_VAL;
+
+ old = atomic_cmpxchg(&lock->val, val, new);
+ if (old == val)
+ break;
+
+ val = old;
+ }
+
+ /*
+ * we won the trylock
+ */
+ if (new == _Q_LOCKED_VAL)
+ return;
+
+ /*
+ * we're pending, wait for the owner to go away.
+ *
+ * *,1,1 -> *,1,0
+ *
+ * this wait loop must be a load-acquire such that we match the
+ * store-release that clears the locked bit and create lock
+ * sequentiality; this is because not all clear_pending_set_locked()
+ * implementations imply full barriers.
+ */
+ while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_MASK)
+ cpu_relax();
+
+ /*
+ * take ownership and clear the pending bit.
+ *
+ * *,1,0 -> *,0,1
+ */
+ clear_pending_set_locked(lock);
+ return;
+
+ /*
+ * End of pending bit optimistic spinning and beginning of MCS
+ * queuing.
+ */
+queue:
+ node = this_cpu_ptr(&mcs_nodes[0]);
+ idx = node->count++;
+ tail = encode_tail(smp_processor_id(), idx);
+
+ node += idx;
+ node->locked = 0;
+ node->next = NULL;
+ pv_init_node(node);
+
+ /*
+ * We touched a (possibly) cold cacheline in the per-cpu queue node;
+ * attempt the trylock once more in the hope someone let go while we
+ * weren't watching.
+ */
+ if (queued_spin_trylock(lock))
+ goto release;
+
+ /*
+ * We have already touched the queueing cacheline; don't bother with
+ * pending stuff.
+ *
+ * p,*,* -> n,*,*
+ */
+ old = xchg_tail(lock, tail);
+
+ /*
+ * if there was a previous node; link it and wait until reaching the
+ * head of the waitqueue.
+ */
+ if (old & _Q_TAIL_MASK) {
+ prev = decode_tail(old);
+ WRITE_ONCE(prev->next, node);
+
+ pv_wait_node(node);
+ arch_mcs_spin_lock_contended(&node->locked);
+ }
+
+ /*
+ * we're at the head of the waitqueue, wait for the owner & pending to
+ * go away.
+ *
+ * *,x,y -> *,0,0
+ *
+ * this wait loop must use a load-acquire such that we match the
+ * store-release that clears the locked bit and create lock
+ * sequentiality; this is because the set_locked() function below
+ * does not imply a full barrier.
+ *
+ */
+ pv_wait_head(lock, node);
+ while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_PENDING_MASK)
+ cpu_relax();
+
+ /*
+ * claim the lock:
+ *
+ * n,0,0 -> 0,0,1 : lock, uncontended
+ * *,0,0 -> *,0,1 : lock, contended
+ *
+ * If the queue head is the only one in the queue (lock value == tail),
+ * clear the tail code and grab the lock. Otherwise, we only need
+ * to grab the lock.
+ */
+ for (;;) {
+ if (val != tail) {
+ set_locked(lock);
+ break;
+ }
+ old = atomic_cmpxchg(&lock->val, val, _Q_LOCKED_VAL);
+ if (old == val)
+ goto release; /* No contention */
+
+ val = old;
+ }
+
+ /*
+ * contended path; wait for next, release.
+ */
+ while (!(next = READ_ONCE(node->next)))
+ cpu_relax();
+
+ arch_mcs_spin_unlock_contended(&next->locked);
+ pv_kick_node(next);
+
+release:
+ /*
+ * release the node
+ */
+ this_cpu_dec(mcs_nodes[0].count);
+}
+EXPORT_SYMBOL(queued_spin_lock_slowpath);
+
+/*
+ * Generate the paravirt code for queued_spin_unlock_slowpath().
+ */
+#if !defined(_GEN_PV_LOCK_SLOWPATH) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+#define _GEN_PV_LOCK_SLOWPATH
+
+#undef pv_enabled
+#define pv_enabled() true
+
+#undef pv_init_node
+#undef pv_wait_node
+#undef pv_kick_node
+#undef pv_wait_head
+
+#undef queued_spin_lock_slowpath
+#define queued_spin_lock_slowpath __pv_queued_spin_lock_slowpath
+
+#include "qspinlock_paravirt.h"
+#include "qspinlock.c"
+
+#endif
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
new file mode 100644
index 0000000..04ab181
--- /dev/null
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -0,0 +1,325 @@
+#ifndef _GEN_PV_LOCK_SLOWPATH
+#error "do not include this file"
+#endif
+
+#include <linux/hash.h>
+#include <linux/bootmem.h>
+
+/*
+ * Implement paravirt qspinlocks; the general idea is to halt the vcpus instead
+ * of spinning them.
+ *
+ * This relies on the architecture to provide two paravirt hypercalls:
+ *
+ * pv_wait(u8 *ptr, u8 val) -- suspends the vcpu if *ptr == val
+ * pv_kick(cpu) -- wakes a suspended vcpu
+ *
+ * Using these we implement __pv_queued_spin_lock_slowpath() and
+ * __pv_queued_spin_unlock() to replace native_queued_spin_lock_slowpath() and
+ * native_queued_spin_unlock().
+ */
+
+#define _Q_SLOW_VAL (3U << _Q_LOCKED_OFFSET)
+
+enum vcpu_state {
+ vcpu_running = 0,
+ vcpu_halted,
+};
+
+struct pv_node {
+ struct mcs_spinlock mcs;
+ struct mcs_spinlock __res[3];
+
+ int cpu;
+ u8 state;
+};
+
+/*
+ * Lock and MCS node addresses hash table for fast lookup
+ *
+ * Hashing is done on a per-cacheline basis to minimize the need to access
+ * more than one cacheline.
+ *
+ * Dynamically allocate a hash table big enough to hold at least 4X the
+ * number of possible cpus in the system. Allocation is done on page
+ * granularity. So the minimum number of hash buckets should be at least
+ * 256 (64-bit) or 512 (32-bit) to fully utilize a 4k page.
+ *
+ * Since we should not be holding locks from NMI context (very rare indeed) the
+ * max load factor is 0.75, which is around the point where open addressing
+ * breaks down.
+ *
+ */
+struct pv_hash_entry {
+ struct qspinlock *lock;
+ struct pv_node *node;
+};
+
+#define PV_HE_PER_LINE (SMP_CACHE_BYTES / sizeof(struct pv_hash_entry))
+#define PV_HE_MIN (PAGE_SIZE / sizeof(struct pv_hash_entry))
+
+static struct pv_hash_entry *pv_lock_hash;
+static unsigned int pv_lock_hash_bits __read_mostly;
+
+/*
+ * Allocate memory for the PV qspinlock hash buckets
+ *
+ * This function should be called from the paravirt spinlock initialization
+ * routine.
+ */
+void __init __pv_init_lock_hash(void)
+{
+ int pv_hash_size = ALIGN(4 * num_possible_cpus(), PV_HE_PER_LINE);
+
+ if (pv_hash_size < PV_HE_MIN)
+ pv_hash_size = PV_HE_MIN;
+
+ /*
+ * Allocate space from bootmem which should be page-size aligned
+ * and hence cacheline aligned.
+ */
+ pv_lock_hash = alloc_large_system_hash("PV qspinlock",
+ sizeof(struct pv_hash_entry),
+ pv_hash_size, 0, HASH_EARLY,
+ &pv_lock_hash_bits, NULL,
+ pv_hash_size, pv_hash_size);
+}
+
+#define for_each_hash_entry(he, offset, hash) \
+ for (hash &= ~(PV_HE_PER_LINE - 1), he = &pv_lock_hash[hash], offset = 0; \
+ offset < (1 << pv_lock_hash_bits); \
+ offset++, he = &pv_lock_hash[(hash + offset) & ((1 << pv_lock_hash_bits) - 1)])
+
+static struct qspinlock **pv_hash(struct qspinlock *lock, struct pv_node *node)
+{
+ unsigned long offset, hash = hash_ptr(lock, pv_lock_hash_bits);
+ struct pv_hash_entry *he;
+
+ for_each_hash_entry(he, offset, hash) {
+ if (!cmpxchg(&he->lock, NULL, lock)) {
+ WRITE_ONCE(he->node, node);
+ return &he->lock;
+ }
+ }
+ /*
+ * Hard assume there is a free entry for us.
+ *
+ * This is guaranteed by ensuring every blocked lock only ever consumes
+ * a single entry, and since we only have 4 nesting levels per CPU
+ * and allocated 4*nr_possible_cpus(), this must be so.
+ *
+ * The single entry is guaranteed by having the lock owner unhash
+ * before it releases.
+ */
+ BUG();
+}
+
+static struct pv_node *pv_unhash(struct qspinlock *lock)
+{
+ unsigned long offset, hash = hash_ptr(lock, pv_lock_hash_bits);
+ struct pv_hash_entry *he;
+ struct pv_node *node;
+
+ for_each_hash_entry(he, offset, hash) {
+ if (READ_ONCE(he->lock) == lock) {
+ node = READ_ONCE(he->node);
+ WRITE_ONCE(he->lock, NULL);
+ return node;
+ }
+ }
+ /*
+ * Hard assume we'll find an entry.
+ *
+ * This guarantees a limited lookup time and is itself guaranteed by
+ * having the lock owner do the unhash -- IFF the unlock sees the
+ * SLOW flag, there MUST be a hash entry.
+ */
+ BUG();
+}
+
+/*
+ * Initialize the PV part of the mcs_spinlock node.
+ */
+static void pv_init_node(struct mcs_spinlock *node)
+{
+ struct pv_node *pn = (struct pv_node *)node;
+
+ BUILD_BUG_ON(sizeof(struct pv_node) > 5*sizeof(struct mcs_spinlock));
+
+ pn->cpu = smp_processor_id();
+ pn->state = vcpu_running;
+}
+
+/*
+ * Wait for node->locked to become true, halt the vcpu after a short spin.
+ * pv_kick_node() is used to wake the vcpu again.
+ */
+static void pv_wait_node(struct mcs_spinlock *node)
+{
+ struct pv_node *pn = (struct pv_node *)node;
+ int loop;
+
+ for (;;) {
+ for (loop = SPIN_THRESHOLD; loop; loop--) {
+ if (READ_ONCE(node->locked))
+ return;
+ cpu_relax();
+ }
+
+ /*
+ * Order pn->state vs pn->locked thusly:
+ *
+ * [S] pn->state = vcpu_halted [S] next->locked = 1
+ * MB MB
+ * [L] pn->locked [RmW] pn->state = vcpu_running
+ *
+ * Matches the xchg() from pv_kick_node().
+ */
+ smp_store_mb(pn->state, vcpu_halted);
+
+ if (!READ_ONCE(node->locked))
+ pv_wait(&pn->state, vcpu_halted);
+
+ /*
+ * Reset the vCPU state to avoid unncessary CPU kicking
+ */
+ WRITE_ONCE(pn->state, vcpu_running);
+
+ /*
+ * If the locked flag is still not set after wakeup, it is a
+ * spurious wakeup and the vCPU should wait again. However,
+ * there is a pretty high overhead for CPU halting and kicking.
+ * So it is better to spin for a while in the hope that the
+ * MCS lock will be released soon.
+ */
+ }
+ /*
+ * By now our node->locked should be 1 and our caller will not actually
+ * spin-wait for it. We do however rely on our caller to do a
+ * load-acquire for us.
+ */
+}
+
+/*
+ * Called after setting next->locked = 1, used to wake those stuck in
+ * pv_wait_node().
+ */
+static void pv_kick_node(struct mcs_spinlock *node)
+{
+ struct pv_node *pn = (struct pv_node *)node;
+
+ /*
+ * Note that because node->locked is already set, this actual
+ * mcs_spinlock entry could be re-used already.
+ *
+ * This should be fine however, kicking people for no reason is
+ * harmless.
+ *
+ * See the comment in pv_wait_node().
+ */
+ if (xchg(&pn->state, vcpu_running) == vcpu_halted)
+ pv_kick(pn->cpu);
+}
+
+/*
+ * Wait for l->locked to become clear; halt the vcpu after a short spin.
+ * __pv_queued_spin_unlock() will wake us.
+ */
+static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node)
+{
+ struct pv_node *pn = (struct pv_node *)node;
+ struct __qspinlock *l = (void *)lock;
+ struct qspinlock **lp = NULL;
+ int loop;
+
+ for (;;) {
+ for (loop = SPIN_THRESHOLD; loop; loop--) {
+ if (!READ_ONCE(l->locked))
+ return;
+ cpu_relax();
+ }
+
+ WRITE_ONCE(pn->state, vcpu_halted);
+ if (!lp) { /* ONCE */
+ lp = pv_hash(lock, pn);
+ /*
+ * lp must be set before setting _Q_SLOW_VAL
+ *
+ * [S] lp = lock [RmW] l = l->locked = 0
+ * MB MB
+ * [S] l->locked = _Q_SLOW_VAL [L] lp
+ *
+ * Matches the cmpxchg() in __pv_queued_spin_unlock().
+ */
+ if (!cmpxchg(&l->locked, _Q_LOCKED_VAL, _Q_SLOW_VAL)) {
+ /*
+ * The lock is free and _Q_SLOW_VAL has never
+ * been set. Therefore we need to unhash before
+ * getting the lock.
+ */
+ WRITE_ONCE(*lp, NULL);
+ return;
+ }
+ }
+ pv_wait(&l->locked, _Q_SLOW_VAL);
+
+ /*
+ * The unlocker should have freed the lock before kicking the
+ * CPU. So if the lock is still not free, it is a spurious
+ * wakeup and so the vCPU should wait again after spinning for
+ * a while.
+ */
+ }
+
+ /*
+ * Lock is unlocked now; the caller will acquire it without waiting.
+ * As with pv_wait_node() we rely on the caller to do a load-acquire
+ * for us.
+ */
+}
+
+/*
+ * PV version of the unlock function to be used in stead of
+ * queued_spin_unlock().
+ */
+__visible void __pv_queued_spin_unlock(struct qspinlock *lock)
+{
+ struct __qspinlock *l = (void *)lock;
+ struct pv_node *node;
+
+ /*
+ * We must not unlock if SLOW, because in that case we must first
+ * unhash. Otherwise it would be possible to have multiple @lock
+ * entries, which would be BAD.
+ */
+ if (likely(cmpxchg(&l->locked, _Q_LOCKED_VAL, 0) == _Q_LOCKED_VAL))
+ return;
+
+ /*
+ * Since the above failed to release, this must be the SLOW path.
+ * Therefore start by looking up the blocked node and unhashing it.
+ */
+ node = pv_unhash(lock);
+
+ /*
+ * Now that we have a reference to the (likely) blocked pv_node,
+ * release the lock.
+ */
+ smp_store_release(&l->locked, 0);
+
+ /*
+ * At this point the memory pointed at by lock can be freed/reused,
+ * however we can still use the pv_node to kick the CPU.
+ */
+ if (READ_ONCE(node->state) == vcpu_halted)
+ pv_kick(node->cpu);
+}
+/*
+ * Include the architecture specific callee-save thunk of the
+ * __pv_queued_spin_unlock(). This thunk is put together with
+ * __pv_queued_spin_unlock() near the top of the file to make sure
+ * that the callee-save thunk and the real unlock function are close
+ * to each other sharing consecutive instruction cachelines.
+ */
+#include <asm/qspinlock_paravirt.h>
+
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index b025295..30ec5b4 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -70,10 +70,10 @@
}
/*
- * We can speed up the acquire/release, if the architecture
- * supports cmpxchg and if there's no debugging state to be set up
+ * We can speed up the acquire/release, if there's no debugging state to be
+ * set up.
*/
-#if defined(__HAVE_ARCH_CMPXCHG) && !defined(CONFIG_DEBUG_RT_MUTEXES)
+#ifndef CONFIG_DEBUG_RT_MUTEXES
# define rt_mutex_cmpxchg(l,c,n) (cmpxchg(&l->owner, c, n) == c)
static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
{
@@ -1443,10 +1443,17 @@
*
* @lock: the rt_mutex to be locked
*
+ * This function can only be called in thread context. It's safe to
+ * call it from atomic regions, but not from hard interrupt or soft
+ * interrupt context.
+ *
* Returns 1 on success and 0 on contention
*/
int __sched rt_mutex_trylock(struct rt_mutex *lock)
{
+ if (WARN_ON(in_irq() || in_nmi() || in_serving_softirq()))
+ return 0;
+
return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock);
}
EXPORT_SYMBOL_GPL(rt_mutex_trylock);
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 3417d01..0f18971 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -409,11 +409,24 @@
return taken;
}
+/*
+ * Return true if the rwsem has active spinner
+ */
+static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
+{
+ return osq_is_locked(&sem->osq);
+}
+
#else
static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
{
return false;
}
+
+static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
+{
+ return false;
+}
#endif
/*
@@ -496,7 +509,38 @@
{
unsigned long flags;
+ /*
+ * If a spinner is present, it is not necessary to do the wakeup.
+ * Try to do wakeup only if the trylock succeeds to minimize
+ * spinlock contention which may introduce too much delay in the
+ * unlock operation.
+ *
+ * spinning writer up_write/up_read caller
+ * --------------- -----------------------
+ * [S] osq_unlock() [L] osq
+ * MB RMB
+ * [RmW] rwsem_try_write_lock() [RmW] spin_trylock(wait_lock)
+ *
+ * Here, it is important to make sure that there won't be a missed
+ * wakeup while the rwsem is free and the only spinning writer goes
+ * to sleep without taking the rwsem. Even when the spinning writer
+ * is just going to break out of the waiting loop, it will still do
+ * a trylock in rwsem_down_write_failed() before sleeping. IOW, if
+ * rwsem_has_spinner() is true, it will guarantee at least one
+ * trylock attempt on the rwsem later on.
+ */
+ if (rwsem_has_spinner(sem)) {
+ /*
+ * The smp_rmb() here is to make sure that the spinner
+ * state is consulted before reading the wait_lock.
+ */
+ smp_rmb();
+ if (!raw_spin_trylock_irqsave(&sem->wait_lock, flags))
+ return sem;
+ goto locked;
+ }
raw_spin_lock_irqsave(&sem->wait_lock, flags);
+locked:
/* do nothing if list empty */
if (!list_empty(&sem->wait_list))
diff --git a/kernel/module.c b/kernel/module.c
index 42a1d2a..cfc9e84 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3370,6 +3370,9 @@
module_bug_cleanup(mod);
mutex_unlock(&module_mutex);
+ blocking_notifier_call_chain(&module_notify_list,
+ MODULE_STATE_GOING, mod);
+
/* we can't deallocate the module until we clear memory protection */
unset_module_init_ro_nx(mod);
unset_module_core_ro_nx(mod);
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 852143a..9bc8232 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -341,7 +341,7 @@
* condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
* an event.
*/
- set_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */
+ smp_store_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */
return timeout;
}
@@ -354,7 +354,7 @@
* doesn't imply write barrier and the users expects write
* barrier semantics on wakeup functions. The following
* smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
- * and is paired with set_mb() in wait_woken().
+ * and is paired with smp_store_mb() in wait_woken().
*/
smp_wmb(); /* C */
wait->flags |= WQ_FLAG_WOKEN;
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 830dd5d..5f62708 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -139,64 +139,42 @@
#endif
/**
- * cpumask_set_cpu_local_first - set i'th cpu with local numa cpu's first
- *
+ * cpumask_local_spread - select the i'th cpu with local numa cpu's first
* @i: index number
- * @numa_node: local numa_node
- * @dstp: cpumask with the relevant cpu bit set according to the policy
+ * @node: local numa_node
*
- * This function sets the cpumask according to a numa aware policy.
- * cpumask could be used as an affinity hint for the IRQ related to a
- * queue. When the policy is to spread queues across cores - local cores
- * first.
+ * This function selects an online CPU according to a numa aware policy;
+ * local cpus are returned first, followed by non-local ones, then it
+ * wraps around.
*
- * Returns 0 on success, -ENOMEM for no memory, and -EAGAIN when failed to set
- * the cpu bit and need to re-call the function.
+ * It's not very efficient, but useful for setup.
*/
-int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp)
+unsigned int cpumask_local_spread(unsigned int i, int node)
{
- cpumask_var_t mask;
int cpu;
- int ret = 0;
- if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
- return -ENOMEM;
-
+ /* Wrap: we always want a cpu. */
i %= num_online_cpus();
- if (numa_node == -1 || !cpumask_of_node(numa_node)) {
- /* Use all online cpu's for non numa aware system */
- cpumask_copy(mask, cpu_online_mask);
+ if (node == -1) {
+ for_each_cpu(cpu, cpu_online_mask)
+ if (i-- == 0)
+ return cpu;
} else {
- int n;
+ /* NUMA first. */
+ for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask)
+ if (i-- == 0)
+ return cpu;
- cpumask_and(mask,
- cpumask_of_node(numa_node), cpu_online_mask);
+ for_each_cpu(cpu, cpu_online_mask) {
+ /* Skip NUMA nodes, done above. */
+ if (cpumask_test_cpu(cpu, cpumask_of_node(node)))
+ continue;
- n = cpumask_weight(mask);
- if (i >= n) {
- i -= n;
-
- /* If index > number of local cpu's, mask out local
- * cpu's
- */
- cpumask_andnot(mask, cpu_online_mask, mask);
+ if (i-- == 0)
+ return cpu;
}
}
-
- for_each_cpu(cpu, mask) {
- if (--i < 0)
- goto out;
- }
-
- ret = -EAGAIN;
-
-out:
- free_cpumask_var(mask);
-
- if (!ret)
- cpumask_set_cpu(cpu, dstp);
-
- return ret;
+ BUG();
}
-EXPORT_SYMBOL(cpumask_set_cpu_local_first);
+EXPORT_SYMBOL(cpumask_local_spread);
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 48144cd..f051d69 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -197,13 +197,13 @@
* Compare counter against given value.
* Return 1 if greater, 0 if equal and -1 if less
*/
-int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
+int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
{
s64 count;
count = percpu_counter_read(fbc);
/* Check to see if rough count will be sufficient for comparison */
- if (abs(count - rhs) > (percpu_counter_batch*num_online_cpus())) {
+ if (abs(count - rhs) > (batch * num_online_cpus())) {
if (count > rhs)
return 1;
else
@@ -218,7 +218,7 @@
else
return 0;
}
-EXPORT_SYMBOL(percpu_counter_compare);
+EXPORT_SYMBOL(__percpu_counter_compare);
static int __init percpu_counter_startup(void)
{
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index a3abe6e..22fd041 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1822,7 +1822,7 @@
if (query->startup_sent < br->multicast_startup_query_count)
query->startup_sent++;
- RCU_INIT_POINTER(querier, NULL);
+ RCU_INIT_POINTER(querier->port, NULL);
br_multicast_send_query(br, NULL, query);
spin_unlock(&br->multicast_lock);
}
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 24c7c96..91180a7 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1117,8 +1117,6 @@
return -ENOMEM;
if (tmp.num_counters >= INT_MAX / sizeof(struct ebt_counter))
return -ENOMEM;
- if (tmp.num_counters == 0)
- return -EINVAL;
tmp.name[sizeof(tmp.name) - 1] = 0;
@@ -2161,8 +2159,6 @@
return -ENOMEM;
if (tmp.num_counters >= INT_MAX / sizeof(struct ebt_counter))
return -ENOMEM;
- if (tmp.num_counters == 0)
- return -EINVAL;
memcpy(repl, &tmp, offsetof(struct ebt_replace, hook_entry));
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 4ec0c80..112ad78 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -330,6 +330,10 @@
release_sock(sk);
timeo = schedule_timeout(timeo);
lock_sock(sk);
+
+ if (sock_flag(sk, SOCK_DEAD))
+ break;
+
clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
}
@@ -373,6 +377,10 @@
struct sk_buff *skb;
lock_sock(sk);
+ if (sock_flag(sk, SOCK_DEAD)) {
+ err = -ECONNRESET;
+ goto unlock;
+ }
skb = skb_dequeue(&sk->sk_receive_queue);
caif_check_flow_release(sk);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 1347e11..1d00b89 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -359,15 +359,7 @@
int err;
struct ethtool_cmd cmd;
- if (!dev->ethtool_ops->get_settings)
- return -EOPNOTSUPP;
-
- if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
- return -EFAULT;
-
- cmd.cmd = ETHTOOL_GSET;
-
- err = dev->ethtool_ops->get_settings(dev, &cmd);
+ err = __ethtool_get_settings(dev, &cmd);
if (err < 0)
return err;
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index e6f6cc3..392e29a 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -359,7 +359,7 @@
*/
ds = kzalloc(sizeof(*ds) + drv->priv_size, GFP_KERNEL);
if (ds == NULL)
- return NULL;
+ return ERR_PTR(-ENOMEM);
ds->dst = dst;
ds->index = index;
@@ -370,7 +370,7 @@
ret = dsa_switch_setup_one(ds, parent);
if (ret)
- return NULL;
+ return ERR_PTR(ret);
return ds;
}
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 421a80b..30b544f 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -256,7 +256,8 @@
aead_givcrypt_set_crypt(req, sg, sg, clen, iv);
aead_givcrypt_set_assoc(req, asg, assoclen);
aead_givcrypt_set_giv(req, esph->enc_data,
- XFRM_SKB_CB(skb)->seq.output.low);
+ XFRM_SKB_CB(skb)->seq.output.low +
+ ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
ESP_SKB_CB(skb)->tmp = tmp;
err = crypto_aead_givencrypt(req);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 9f7269f..0c15208 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -65,7 +65,6 @@
goto drop;
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
- skb->mark = be32_to_cpu(tunnel->parms.i_key);
return xfrm_input(skb, nexthdr, spi, encap_type);
}
@@ -91,6 +90,8 @@
struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
+ u32 orig_mark = skb->mark;
+ int ret;
if (!tunnel)
return 1;
@@ -107,7 +108,11 @@
x = xfrm_input_state(skb);
family = x->inner_mode->afinfo->family;
- if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+ skb->mark = be32_to_cpu(tunnel->parms.i_key);
+ ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
+ skb->mark = orig_mark;
+
+ if (!ret)
return -EPERM;
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
@@ -216,8 +221,6 @@
memset(&fl, 0, sizeof(fl));
- skb->mark = be32_to_cpu(tunnel->parms.o_key);
-
switch (skb->protocol) {
case htons(ETH_P_IP):
xfrm_decode_session(skb, &fl, AF_INET);
@@ -233,6 +236,9 @@
return NETDEV_TX_OK;
}
+ /* override mark with tunnel output key */
+ fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key);
+
return vti_xmit(skb, dev, &fl);
}
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 7a5ae50..84be008 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -187,6 +187,7 @@
tcp_cleanup_congestion_control(sk);
icsk->icsk_ca_ops = ca;
+ icsk->icsk_ca_setsockopt = 1;
if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
icsk->icsk_ca_ops->init(sk);
@@ -335,8 +336,10 @@
rcu_read_lock();
ca = __tcp_ca_find_autoload(name);
/* No change asking for existing value */
- if (ca == icsk->icsk_ca_ops)
+ if (ca == icsk->icsk_ca_ops) {
+ icsk->icsk_ca_setsockopt = 1;
goto out;
+ }
if (!ca)
err = -ENOENT;
else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index b5732a5..17e7339 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -420,7 +420,10 @@
rcu_read_unlock();
}
- if (!ca_got_dst && !try_module_get(icsk->icsk_ca_ops->owner))
+ /* If no valid choice made yet, assign current system default ca. */
+ if (!ca_got_dst &&
+ (!icsk->icsk_ca_setsockopt ||
+ !try_module_get(icsk->icsk_ca_ops->owner)))
tcp_assign_congestion_control(sk);
tcp_set_ca_state(sk, TCP_CA_Open);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d10b7e0..1c92ea6 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1345,10 +1345,8 @@
}
unlock_sock_fast(sk, slow);
- if (noblock)
- return -EAGAIN;
-
- /* starting over for a new packet */
+ /* starting over for a new packet, but check if we need to yield */
+ cond_resched();
msg->msg_flags &= ~MSG_TRUNC;
goto try_again;
}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 31f1b5d..7c07ce3 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -248,7 +248,8 @@
aead_givcrypt_set_crypt(req, sg, sg, clen, iv);
aead_givcrypt_set_assoc(req, asg, assoclen);
aead_givcrypt_set_giv(req, esph->enc_data,
- XFRM_SKB_CB(skb)->seq.output.low);
+ XFRM_SKB_CB(skb)->seq.output.low +
+ ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
ESP_SKB_CB(skb)->tmp = tmp;
err = crypto_aead_givencrypt(req);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index ed9d681..0224c03 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -322,7 +322,6 @@
}
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t;
- skb->mark = be32_to_cpu(t->parms.i_key);
rcu_read_unlock();
@@ -342,6 +341,8 @@
struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6;
+ u32 orig_mark = skb->mark;
+ int ret;
if (!t)
return 1;
@@ -358,7 +359,11 @@
x = xfrm_input_state(skb);
family = x->inner_mode->afinfo->family;
- if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+ skb->mark = be32_to_cpu(t->parms.i_key);
+ ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
+ skb->mark = orig_mark;
+
+ if (!ret)
return -EPERM;
skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev)));
@@ -430,6 +435,7 @@
struct net_device *tdev;
struct xfrm_state *x;
int err = -1;
+ int mtu;
if (!dst)
goto tx_err_link_failure;
@@ -463,6 +469,19 @@
skb_dst_set(skb, dst);
skb->dev = skb_dst(skb)->dev;
+ mtu = dst_mtu(dst);
+ if (!skb->ignore_df && skb->len > mtu) {
+ skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu);
+
+ if (skb->protocol == htons(ETH_P_IPV6))
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ else
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(mtu));
+
+ return -EMSGSIZE;
+ }
+
err = dst_output(skb);
if (net_xmit_eval(err) == 0) {
struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
@@ -495,7 +514,6 @@
int ret;
memset(&fl, 0, sizeof(fl));
- skb->mark = be32_to_cpu(t->parms.o_key);
switch (skb->protocol) {
case htons(ETH_P_IPV6):
@@ -516,6 +534,9 @@
goto tx_err;
}
+ /* override mark with tunnel output key */
+ fl.flowi_mark = be32_to_cpu(t->parms.o_key);
+
ret = vti6_xmit(skb, dev, &fl);
if (ret < 0)
goto tx_err;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index c2ec416..e51fc3e 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -525,10 +525,8 @@
}
unlock_sock_fast(sk, slow);
- if (noblock)
- return -EAGAIN;
-
- /* starting over for a new packet */
+ /* starting over for a new packet, but check if we need to yield */
+ cond_resched();
msg->msg_flags &= ~MSG_TRUNC;
goto try_again;
}
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 265e427..ff347a0 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2495,51 +2495,22 @@
struct ieee80211_roc_work *new_roc,
struct ieee80211_roc_work *cur_roc)
{
- unsigned long j = jiffies;
- unsigned long cur_roc_end = cur_roc->hw_start_time +
- msecs_to_jiffies(cur_roc->duration);
- struct ieee80211_roc_work *next_roc;
- int new_dur;
+ unsigned long now = jiffies;
+ unsigned long remaining = cur_roc->hw_start_time +
+ msecs_to_jiffies(cur_roc->duration) -
+ now;
if (WARN_ON(!cur_roc->started || !cur_roc->hw_begun))
return false;
- if (time_after(j + IEEE80211_ROC_MIN_LEFT, cur_roc_end))
+ /* if it doesn't fit entirely, schedule a new one */
+ if (new_roc->duration > jiffies_to_msecs(remaining))
return false;
ieee80211_handle_roc_started(new_roc);
- new_dur = new_roc->duration - jiffies_to_msecs(cur_roc_end - j);
-
- /* cur_roc is long enough - add new_roc to the dependents list. */
- if (new_dur <= 0) {
- list_add_tail(&new_roc->list, &cur_roc->dependents);
- return true;
- }
-
- new_roc->duration = new_dur;
-
- /*
- * if cur_roc was already coalesced before, we might
- * want to extend the next roc instead of adding
- * a new one.
- */
- next_roc = list_entry(cur_roc->list.next,
- struct ieee80211_roc_work, list);
- if (&next_roc->list != &local->roc_list &&
- next_roc->chan == new_roc->chan &&
- next_roc->sdata == new_roc->sdata &&
- !WARN_ON(next_roc->started)) {
- list_add_tail(&new_roc->list, &next_roc->dependents);
- next_roc->duration = max(next_roc->duration,
- new_roc->duration);
- next_roc->type = max(next_roc->type, new_roc->type);
- return true;
- }
-
- /* add right after cur_roc */
- list_add(&new_roc->list, &cur_roc->list);
-
+ /* add to dependents so we send the expired event properly */
+ list_add_tail(&new_roc->list, &cur_roc->dependents);
return true;
}
@@ -2652,17 +2623,9 @@
* In the offloaded ROC case, if it hasn't begun, add
* this new one to the dependent list to be handled
* when the master one begins. If it has begun,
- * check that there's still a minimum time left and
- * if so, start this one, transmitting the frame, but
- * add it to the list directly after this one with
- * a reduced time so we'll ask the driver to execute
- * it right after finishing the previous one, in the
- * hope that it'll also be executed right afterwards,
- * effectively extending the old one.
- * If there's no minimum time left, just add it to the
- * normal list.
- * TODO: the ROC type is ignored here, assuming that it
- * is better to immediately use the current ROC.
+ * check if it fits entirely within the existing one,
+ * in which case it will just be dependent as well.
+ * Otherwise, schedule it by itself.
*/
if (!tmp->hw_begun) {
list_add_tail(&roc->list, &tmp->dependents);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index ab46ab4..c0a9187 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -205,6 +205,8 @@
* @IEEE80211_RX_CMNTR: received on cooked monitor already
* @IEEE80211_RX_BEACON_REPORTED: This frame was already reported
* to cfg80211_report_obss_beacon().
+ * @IEEE80211_RX_REORDER_TIMER: this frame is released by the
+ * reorder buffer timeout timer, not the normal RX path
*
* These flags are used across handling multiple interfaces
* for a single frame.
@@ -212,6 +214,7 @@
enum ieee80211_rx_flags {
IEEE80211_RX_CMNTR = BIT(0),
IEEE80211_RX_BEACON_REPORTED = BIT(1),
+ IEEE80211_RX_REORDER_TIMER = BIT(2),
};
struct ieee80211_rx_data {
@@ -325,12 +328,6 @@
u8 flags;
};
-#if HZ/100 == 0
-#define IEEE80211_ROC_MIN_LEFT 1
-#else
-#define IEEE80211_ROC_MIN_LEFT (HZ/100)
-#endif
-
struct ieee80211_roc_work {
struct list_head list;
struct list_head dependents;
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index bab5c63..84cef60 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -522,6 +522,12 @@
memcpy(sdata->vif.hw_queue, master->vif.hw_queue,
sizeof(sdata->vif.hw_queue));
sdata->vif.bss_conf.chandef = master->vif.bss_conf.chandef;
+
+ mutex_lock(&local->key_mtx);
+ sdata->crypto_tx_tailroom_needed_cnt +=
+ master->crypto_tx_tailroom_needed_cnt;
+ mutex_unlock(&local->key_mtx);
+
break;
}
case NL80211_IFTYPE_AP:
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 2291cd7..a907f2d 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -58,6 +58,22 @@
lockdep_assert_held(&local->key_mtx);
}
+static void
+update_vlan_tailroom_need_count(struct ieee80211_sub_if_data *sdata, int delta)
+{
+ struct ieee80211_sub_if_data *vlan;
+
+ if (sdata->vif.type != NL80211_IFTYPE_AP)
+ return;
+
+ mutex_lock(&sdata->local->mtx);
+
+ list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+ vlan->crypto_tx_tailroom_needed_cnt += delta;
+
+ mutex_unlock(&sdata->local->mtx);
+}
+
static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata)
{
/*
@@ -79,6 +95,8 @@
* http://mid.gmane.org/1308590980.4322.19.camel@jlt3.sipsolutions.net
*/
+ update_vlan_tailroom_need_count(sdata, 1);
+
if (!sdata->crypto_tx_tailroom_needed_cnt++) {
/*
* Flush all XMIT packets currently using HW encryption or no
@@ -88,6 +106,15 @@
}
}
+static void decrease_tailroom_need_count(struct ieee80211_sub_if_data *sdata,
+ int delta)
+{
+ WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt < delta);
+
+ update_vlan_tailroom_need_count(sdata, -delta);
+ sdata->crypto_tx_tailroom_needed_cnt -= delta;
+}
+
static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
{
struct ieee80211_sub_if_data *sdata;
@@ -144,7 +171,7 @@
if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
(key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM)))
- sdata->crypto_tx_tailroom_needed_cnt--;
+ decrease_tailroom_need_count(sdata, 1);
WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) &&
(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV));
@@ -541,7 +568,7 @@
schedule_delayed_work(&sdata->dec_tailroom_needed_wk,
HZ/2);
} else {
- sdata->crypto_tx_tailroom_needed_cnt--;
+ decrease_tailroom_need_count(sdata, 1);
}
}
@@ -631,6 +658,7 @@
void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_key *key;
+ struct ieee80211_sub_if_data *vlan;
ASSERT_RTNL();
@@ -639,7 +667,14 @@
mutex_lock(&sdata->local->key_mtx);
- sdata->crypto_tx_tailroom_needed_cnt = 0;
+ WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt ||
+ sdata->crypto_tx_tailroom_pending_dec);
+
+ if (sdata->vif.type == NL80211_IFTYPE_AP) {
+ list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+ WARN_ON_ONCE(vlan->crypto_tx_tailroom_needed_cnt ||
+ vlan->crypto_tx_tailroom_pending_dec);
+ }
list_for_each_entry(key, &sdata->key_list, list) {
increment_tailroom_need_count(sdata);
@@ -649,6 +684,22 @@
mutex_unlock(&sdata->local->key_mtx);
}
+void ieee80211_reset_crypto_tx_tailroom(struct ieee80211_sub_if_data *sdata)
+{
+ struct ieee80211_sub_if_data *vlan;
+
+ mutex_lock(&sdata->local->key_mtx);
+
+ sdata->crypto_tx_tailroom_needed_cnt = 0;
+
+ if (sdata->vif.type == NL80211_IFTYPE_AP) {
+ list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+ vlan->crypto_tx_tailroom_needed_cnt = 0;
+ }
+
+ mutex_unlock(&sdata->local->key_mtx);
+}
+
void ieee80211_iter_keys(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
void (*iter)(struct ieee80211_hw *hw,
@@ -688,8 +739,8 @@
{
struct ieee80211_key *key, *tmp;
- sdata->crypto_tx_tailroom_needed_cnt -=
- sdata->crypto_tx_tailroom_pending_dec;
+ decrease_tailroom_need_count(sdata,
+ sdata->crypto_tx_tailroom_pending_dec);
sdata->crypto_tx_tailroom_pending_dec = 0;
ieee80211_debugfs_key_remove_mgmt_default(sdata);
@@ -709,6 +760,7 @@
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_sub_if_data *vlan;
+ struct ieee80211_sub_if_data *master;
struct ieee80211_key *key, *tmp;
LIST_HEAD(keys);
@@ -728,8 +780,20 @@
list_for_each_entry_safe(key, tmp, &keys, list)
__ieee80211_key_destroy(key, false);
- WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt ||
- sdata->crypto_tx_tailroom_pending_dec);
+ if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
+ if (sdata->bss) {
+ master = container_of(sdata->bss,
+ struct ieee80211_sub_if_data,
+ u.ap);
+
+ WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt !=
+ master->crypto_tx_tailroom_needed_cnt);
+ }
+ } else {
+ WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt ||
+ sdata->crypto_tx_tailroom_pending_dec);
+ }
+
if (sdata->vif.type == NL80211_IFTYPE_AP) {
list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
WARN_ON_ONCE(vlan->crypto_tx_tailroom_needed_cnt ||
@@ -793,8 +857,8 @@
*/
mutex_lock(&sdata->local->key_mtx);
- sdata->crypto_tx_tailroom_needed_cnt -=
- sdata->crypto_tx_tailroom_pending_dec;
+ decrease_tailroom_need_count(sdata,
+ sdata->crypto_tx_tailroom_pending_dec);
sdata->crypto_tx_tailroom_pending_dec = 0;
mutex_unlock(&sdata->local->key_mtx);
}
diff --git a/net/mac80211/key.h b/net/mac80211/key.h
index c5a3183..96557dd 100644
--- a/net/mac80211/key.h
+++ b/net/mac80211/key.h
@@ -161,6 +161,7 @@
void ieee80211_free_sta_keys(struct ieee80211_local *local,
struct sta_info *sta);
void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata);
+void ieee80211_reset_crypto_tx_tailroom(struct ieee80211_sub_if_data *sdata);
#define key_mtx_dereference(local, ref) \
rcu_dereference_protected(ref, lockdep_is_held(&((local)->key_mtx)))
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 260eed45..5793f75 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2121,7 +2121,8 @@
/* deliver to local stack */
skb->protocol = eth_type_trans(skb, dev);
memset(skb->cb, 0, sizeof(skb->cb));
- if (rx->local->napi)
+ if (!(rx->flags & IEEE80211_RX_REORDER_TIMER) &&
+ rx->local->napi)
napi_gro_receive(rx->local->napi, skb);
else
netif_receive_skb(skb);
@@ -3231,7 +3232,7 @@
/* This is OK -- must be QoS data frame */
.security_idx = tid,
.seqno_idx = tid,
- .flags = 0,
+ .flags = IEEE80211_RX_REORDER_TIMER,
};
struct tid_ampdu_rx *tid_agg_rx;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 79412f1..b864ebc 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2023,6 +2023,9 @@
/* add back keys */
list_for_each_entry(sdata, &local->interfaces, list)
+ ieee80211_reset_crypto_tx_tailroom(sdata);
+
+ list_for_each_entry(sdata, &local->interfaces, list)
if (ieee80211_sdata_running(sdata))
ieee80211_enable_keys(sdata);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index ad9eed7..1e1c89e 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -815,10 +815,8 @@
if (dev->flags & IFF_UP)
dev_deactivate(dev);
- if (new && new->ops->attach) {
- new->ops->attach(new);
- num_q = 0;
- }
+ if (new && new->ops->attach)
+ goto skip;
for (i = 0; i < num_q; i++) {
struct netdev_queue *dev_queue = dev_ingress_queue(dev);
@@ -834,12 +832,16 @@
qdisc_destroy(old);
}
+skip:
if (!ingress) {
notify_and_destroy(net, skb, n, classid,
dev->qdisc, new);
if (new && !new->ops->attach)
atomic_inc(&new->refcnt);
dev->qdisc = new ? : &noop_qdisc;
+
+ if (new && new->ops->attach)
+ new->ops->attach(new);
} else {
notify_and_destroy(net, skb, n, classid, old, new);
}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5266ea7..0643059 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1880,6 +1880,10 @@
unix_state_unlock(sk);
timeo = freezable_schedule_timeout(timeo);
unix_state_lock(sk);
+
+ if (sock_flag(sk, SOCK_DEAD))
+ break;
+
clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
}
@@ -1939,6 +1943,10 @@
struct sk_buff *skb, *last;
unix_state_lock(sk);
+ if (sock_flag(sk, SOCK_DEAD)) {
+ err = -ECONNRESET;
+ goto unlock;
+ }
last = skb = skb_peek(&sk->sk_receive_queue);
again:
if (skb == NULL) {
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 526c4fe..b58286e 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -13,6 +13,8 @@
#include <net/dst.h>
#include <net/ip.h>
#include <net/xfrm.h>
+#include <net/ip_tunnels.h>
+#include <net/ip6_tunnel.h>
static struct kmem_cache *secpath_cachep __read_mostly;
@@ -186,6 +188,7 @@
struct xfrm_state *x = NULL;
xfrm_address_t *daddr;
struct xfrm_mode *inner_mode;
+ u32 mark = skb->mark;
unsigned int family;
int decaps = 0;
int async = 0;
@@ -203,6 +206,18 @@
XFRM_SPI_SKB_CB(skb)->daddroff);
family = XFRM_SPI_SKB_CB(skb)->family;
+ /* if tunnel is present override skb->mark value with tunnel i_key */
+ if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) {
+ switch (family) {
+ case AF_INET:
+ mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key);
+ break;
+ case AF_INET6:
+ mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key);
+ break;
+ }
+ }
+
/* Allocate new secpath or COW existing one. */
if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) {
struct sec_path *sp;
@@ -229,7 +244,7 @@
goto drop;
}
- x = xfrm_state_lookup(net, skb->mark, daddr, spi, nexthdr, family);
+ x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family);
if (x == NULL) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES);
xfrm_audit_state_notfound(skb, family, spi, seq);
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
index dab57da..4fd725a 100644
--- a/net/xfrm/xfrm_replay.c
+++ b/net/xfrm/xfrm_replay.c
@@ -99,6 +99,7 @@
if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
XFRM_SKB_CB(skb)->seq.output.low = ++x->replay.oseq;
+ XFRM_SKB_CB(skb)->seq.output.hi = 0;
if (unlikely(x->replay.oseq == 0)) {
x->replay.oseq--;
xfrm_audit_state_replay_overflow(x, skb);
@@ -177,6 +178,7 @@
if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
XFRM_SKB_CB(skb)->seq.output.low = ++replay_esn->oseq;
+ XFRM_SKB_CB(skb)->seq.output.hi = 0;
if (unlikely(replay_esn->oseq == 0)) {
replay_esn->oseq--;
xfrm_audit_state_replay_overflow(x, skb);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index f5e39e3..96688cd 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -927,8 +927,8 @@
x->id.spi != spi)
continue;
- spin_unlock_bh(&net->xfrm.xfrm_state_lock);
xfrm_state_hold(x);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
diff --git a/scripts/checksyscalls.sh b/scripts/checksyscalls.sh
index 5b3add3..2c9082b 100755
--- a/scripts/checksyscalls.sh
+++ b/scripts/checksyscalls.sh
@@ -212,5 +212,5 @@
)
}
-(ignore_list && syscall_list $(dirname $0)/../arch/x86/syscalls/syscall_32.tbl) | \
+(ignore_list && syscall_list $(dirname $0)/../arch/x86/entry/syscalls/syscall_32.tbl) | \
$* -E -x c - > /dev/null
diff --git a/scripts/gdb/linux/modules.py b/scripts/gdb/linux/modules.py
index a1504c4..25db8cf 100644
--- a/scripts/gdb/linux/modules.py
+++ b/scripts/gdb/linux/modules.py
@@ -73,18 +73,11 @@
" " if utils.get_long_type().sizeof == 8 else ""))
for module in module_list():
- ref = 0
- module_refptr = module['refptr']
- for cpu in cpus.cpu_list("cpu_possible_mask"):
- refptr = cpus.per_cpu(module_refptr, cpu)
- ref += refptr['incs']
- ref -= refptr['decs']
-
gdb.write("{address} {name:<19} {size:>8} {ref}".format(
address=str(module['module_core']).split()[0],
name=module['name'].string(),
size=str(module['core_size']),
- ref=str(ref)))
+ ref=str(module['refcnt']['counter'])))
source_list = module['source_list']
t = self._module_use_type.get_type().pointer()
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 1c86787..ac0db16 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -4926,9 +4926,12 @@
dig_only:
parse_digital(codec);
- if (spec->power_down_unused || codec->power_save_node)
+ if (spec->power_down_unused || codec->power_save_node) {
if (!codec->power_filter)
codec->power_filter = snd_hda_gen_path_power_filter;
+ if (!codec->patch_ops.stream_pm)
+ codec->patch_ops.stream_pm = snd_hda_gen_stream_pm;
+ }
if (!spec->no_analog && spec->beep_nid) {
err = snd_hda_attach_beep_device(codec, spec->beep_nid);
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 34040d2..fea198c 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2089,6 +2089,8 @@
.driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
{ PCI_DEVICE(0x1002, 0xaab0),
.driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+ { PCI_DEVICE(0x1002, 0xaac8),
+ .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
/* VIA VT8251/VT8237A */
{ PCI_DEVICE(0x1106, 0x3288),
.driver_data = AZX_DRIVER_VIA | AZX_DCAPS_POSFIX_VIA },
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 31f8f13..4641684 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -884,6 +884,7 @@
{ 0x10ec0275, 0x1028, 0, "ALC3260" },
{ 0x10ec0899, 0x1028, 0, "ALC3861" },
{ 0x10ec0298, 0x1028, 0, "ALC3266" },
+ { 0x10ec0256, 0x1028, 0, "ALC3246" },
{ 0x10ec0670, 0x1025, 0, "ALC669X" },
{ 0x10ec0676, 0x1025, 0, "ALC679X" },
{ 0x10ec0282, 0x1043, 0, "ALC3229" },
@@ -4227,6 +4228,11 @@
if (action == HDA_FIXUP_ACT_PRE_PROBE) {
spec->parse_flags |= HDA_PINCFG_HEADSET_MIC;
spec->gen.hp_mic = 1; /* Mic-in is same pin as headphone */
+
+ /* Disable boost for mic-in permanently. (This code is only called
+ from quirks that guarantee that the headphone is at NID 0x1b.) */
+ snd_hda_codec_write(codec, 0x1b, 0, AC_VERB_SET_AMP_GAIN_MUTE, 0x7000);
+ snd_hda_override_wcaps(codec, 0x1b, get_wcaps(codec, 0x1b) & ~AC_WCAP_IN_AMP);
} else
alc_fixup_headset_mode(codec, fix, action);
}
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 43c99ce..6833c74 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -4403,7 +4403,6 @@
#ifdef CONFIG_PM
.suspend = stac_suspend,
#endif
- .stream_pm = snd_hda_gen_stream_pm,
.reboot_notify = stac_shutup,
};
@@ -4697,7 +4696,8 @@
return err;
spec = codec->spec;
- codec->power_save_node = 1;
+ /* disabled power_save_node since it causes noises on a Dell machine */
+ /* codec->power_save_node = 1; */
spec->linear_tone_beep = 0;
spec->gen.own_eapd_ctl = 1;
spec->gen.power_down_unused = 1;
diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c
index d51703e..0a4ad5f 100644
--- a/sound/pci/hda/thinkpad_helper.c
+++ b/sound/pci/hda/thinkpad_helper.c
@@ -72,7 +72,6 @@
if (led_set_func(TPACPI_LED_MUTE, false) >= 0) {
old_vmaster_hook = spec->vmaster_mute.hook;
spec->vmaster_mute.hook = update_tpacpi_mute_led;
- spec->vmaster_mute_enum = 1;
removefunc = false;
}
if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0) {
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 46facfc..2917534 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1118,6 +1118,7 @@
case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema */
case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */
case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */
+ case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */
case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */
return true;
}
diff --git a/tools/net/bpf_jit_disasm.c b/tools/net/bpf_jit_disasm.c
index c5baf9c..618c2bc 100644
--- a/tools/net/bpf_jit_disasm.c
+++ b/tools/net/bpf_jit_disasm.c
@@ -123,6 +123,8 @@
assert(ret == 0);
ptr = haystack;
+ memset(pmatch, 0, sizeof(pmatch));
+
while (1) {
ret = regexec(®ex, ptr, 1, pmatch, 0);
if (ret == 0) {
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index 4039854..e367b1a 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -9,7 +9,7 @@
turbostat : turbostat.c
CFLAGS += -Wall
-CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/uapi/asm/msr-index.h"'
+CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
%: %.c
@mkdir -p $(BUILD_OUTPUT)
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index bac98ca..323b65e 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -52,6 +52,7 @@
unsigned int skip_c1;
unsigned int do_nhm_cstates;
unsigned int do_snb_cstates;
+unsigned int do_knl_cstates;
unsigned int do_pc2;
unsigned int do_pc3;
unsigned int do_pc6;
@@ -91,6 +92,7 @@
unsigned int do_ring_perf_limit_reasons;
unsigned int crystal_hz;
unsigned long long tsc_hz;
+int base_cpu;
#define RAPL_PKG (1 << 0)
/* 0x610 MSR_PKG_POWER_LIMIT */
@@ -316,7 +318,7 @@
if (do_nhm_cstates)
outp += sprintf(outp, " CPU%%c1");
- if (do_nhm_cstates && !do_slm_cstates)
+ if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
outp += sprintf(outp, " CPU%%c3");
if (do_nhm_cstates)
outp += sprintf(outp, " CPU%%c6");
@@ -546,7 +548,7 @@
if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
goto done;
- if (do_nhm_cstates && !do_slm_cstates)
+ if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
outp += sprintf(outp, "%8.2f", 100.0 * c->c3/t->tsc);
if (do_nhm_cstates)
outp += sprintf(outp, "%8.2f", 100.0 * c->c6/t->tsc);
@@ -1018,14 +1020,17 @@
if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
return 0;
- if (do_nhm_cstates && !do_slm_cstates) {
+ if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) {
if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
return -6;
}
- if (do_nhm_cstates) {
+ if (do_nhm_cstates && !do_knl_cstates) {
if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6))
return -7;
+ } else if (do_knl_cstates) {
+ if (get_msr(cpu, MSR_KNL_CORE_C6_RESIDENCY, &c->c6))
+ return -7;
}
if (do_snb_cstates)
@@ -1150,7 +1155,7 @@
unsigned long long msr;
unsigned int ratio;
- get_msr(0, MSR_NHM_PLATFORM_INFO, &msr);
+ get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr);
fprintf(stderr, "cpu0: MSR_NHM_PLATFORM_INFO: 0x%08llx\n", msr);
@@ -1162,7 +1167,7 @@
fprintf(stderr, "%d * %.0f = %.0f MHz base frequency\n",
ratio, bclk, ratio * bclk);
- get_msr(0, MSR_IA32_POWER_CTL, &msr);
+ get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr);
fprintf(stderr, "cpu0: MSR_IA32_POWER_CTL: 0x%08llx (C1E auto-promotion: %sabled)\n",
msr, msr & 0x2 ? "EN" : "DIS");
@@ -1175,7 +1180,7 @@
unsigned long long msr;
unsigned int ratio;
- get_msr(0, MSR_TURBO_RATIO_LIMIT2, &msr);
+ get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT2, &msr);
fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT2: 0x%08llx\n", msr);
@@ -1197,7 +1202,7 @@
unsigned long long msr;
unsigned int ratio;
- get_msr(0, MSR_TURBO_RATIO_LIMIT1, &msr);
+ get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &msr);
fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", msr);
@@ -1249,7 +1254,7 @@
unsigned long long msr;
unsigned int ratio;
- get_msr(0, MSR_TURBO_RATIO_LIMIT, &msr);
+ get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT, &msr);
fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", msr);
@@ -1296,11 +1301,72 @@
}
static void
+dump_knl_turbo_ratio_limits(void)
+{
+ int cores;
+ unsigned int ratio;
+ unsigned long long msr;
+ int delta_cores;
+ int delta_ratio;
+ int i;
+
+ get_msr(base_cpu, MSR_NHM_TURBO_RATIO_LIMIT, &msr);
+
+ fprintf(stderr, "cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x%08llx\n",
+ msr);
+
+ /**
+ * Turbo encoding in KNL is as follows:
+ * [7:0] -- Base value of number of active cores of bucket 1.
+ * [15:8] -- Base value of freq ratio of bucket 1.
+ * [20:16] -- +ve delta of number of active cores of bucket 2.
+ * i.e. active cores of bucket 2 =
+ * active cores of bucket 1 + delta
+ * [23:21] -- Negative delta of freq ratio of bucket 2.
+ * i.e. freq ratio of bucket 2 =
+ * freq ratio of bucket 1 - delta
+ * [28:24]-- +ve delta of number of active cores of bucket 3.
+ * [31:29]-- -ve delta of freq ratio of bucket 3.
+ * [36:32]-- +ve delta of number of active cores of bucket 4.
+ * [39:37]-- -ve delta of freq ratio of bucket 4.
+ * [44:40]-- +ve delta of number of active cores of bucket 5.
+ * [47:45]-- -ve delta of freq ratio of bucket 5.
+ * [52:48]-- +ve delta of number of active cores of bucket 6.
+ * [55:53]-- -ve delta of freq ratio of bucket 6.
+ * [60:56]-- +ve delta of number of active cores of bucket 7.
+ * [63:61]-- -ve delta of freq ratio of bucket 7.
+ */
+ cores = msr & 0xFF;
+ ratio = (msr >> 8) && 0xFF;
+ if (ratio > 0)
+ fprintf(stderr,
+ "%d * %.0f = %.0f MHz max turbo %d active cores\n",
+ ratio, bclk, ratio * bclk, cores);
+
+ for (i = 16; i < 64; i = i + 8) {
+ delta_cores = (msr >> i) & 0x1F;
+ delta_ratio = (msr >> (i + 5)) && 0x7;
+ if (!delta_cores || !delta_ratio)
+ return;
+ cores = cores + delta_cores;
+ ratio = ratio - delta_ratio;
+
+ /** -ve ratios will make successive ratio calculations
+ * negative. Hence return instead of carrying on.
+ */
+ if (ratio > 0)
+ fprintf(stderr,
+ "%d * %.0f = %.0f MHz max turbo %d active cores\n",
+ ratio, bclk, ratio * bclk, cores);
+ }
+}
+
+static void
dump_nhm_cst_cfg(void)
{
unsigned long long msr;
- get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
+ get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
#define SNB_C1_AUTO_UNDEMOTE (1UL << 27)
#define SNB_C3_AUTO_UNDEMOTE (1UL << 28)
@@ -1381,12 +1447,41 @@
}
/*
- * cpu_is_first_sibling_in_core(cpu)
- * return 1 if given CPU is 1st HT sibling in the core
+ * get_cpu_position_in_core(cpu)
+ * return the position of the CPU among its HT siblings in the core
+ * return -1 if the sibling is not in list
*/
-int cpu_is_first_sibling_in_core(int cpu)
+int get_cpu_position_in_core(int cpu)
{
- return cpu == parse_int_file("/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
+ char path[64];
+ FILE *filep;
+ int this_cpu;
+ char character;
+ int i;
+
+ sprintf(path,
+ "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list",
+ cpu);
+ filep = fopen(path, "r");
+ if (filep == NULL) {
+ perror(path);
+ exit(1);
+ }
+
+ for (i = 0; i < topo.num_threads_per_core; i++) {
+ fscanf(filep, "%d", &this_cpu);
+ if (this_cpu == cpu) {
+ fclose(filep);
+ return i;
+ }
+
+ /* Account for no separator after last thread*/
+ if (i != (topo.num_threads_per_core - 1))
+ fscanf(filep, "%c", &character);
+ }
+
+ fclose(filep);
+ return -1;
}
/*
@@ -1412,25 +1507,31 @@
{
char path[80];
FILE *filep;
- int sib1, sib2;
- int matches;
+ int sib1;
+ int matches = 0;
char character;
+ char str[100];
+ char *ch;
sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
filep = fopen_or_die(path, "r");
+
/*
* file format:
- * if a pair of number with a character between: 2 siblings (eg. 1-2, or 1,4)
- * otherwinse 1 sibling (self).
+ * A ',' separated or '-' separated set of numbers
+ * (eg 1-2 or 1,3,4,5)
*/
- matches = fscanf(filep, "%d%c%d\n", &sib1, &character, &sib2);
+ fscanf(filep, "%d%c\n", &sib1, &character);
+ fseek(filep, 0, SEEK_SET);
+ fgets(str, 100, filep);
+ ch = strchr(str, character);
+ while (ch != NULL) {
+ matches++;
+ ch = strchr(ch+1, character);
+ }
fclose(filep);
-
- if (matches == 3)
- return 2;
- else
- return 1;
+ return matches+1;
}
/*
@@ -1594,8 +1695,10 @@
void check_dev_msr()
{
struct stat sb;
+ char pathname[32];
- if (stat("/dev/cpu/0/msr", &sb))
+ sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
+ if (stat(pathname, &sb))
if (system("/sbin/modprobe msr > /dev/null 2>&1"))
err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" ");
}
@@ -1608,6 +1711,7 @@
cap_user_data_t cap_data = &cap_data_data;
extern int capget(cap_user_header_t hdrp, cap_user_data_t datap);
int do_exit = 0;
+ char pathname[32];
/* check for CAP_SYS_RAWIO */
cap_header->pid = getpid();
@@ -1622,7 +1726,8 @@
}
/* test file permissions */
- if (euidaccess("/dev/cpu/0/msr", R_OK)) {
+ sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
+ if (euidaccess(pathname, R_OK)) {
do_exit++;
warn("/dev/cpu/0/msr open failed, try chown or chmod +r /dev/cpu/*/msr");
}
@@ -1704,7 +1809,7 @@
default:
return 0;
}
- get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
+ get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
pkg_cstate_limit = pkg_cstate_limits[msr & 0xF];
@@ -1753,6 +1858,21 @@
}
}
+int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model)
+{
+ if (!genuine_intel)
+ return 0;
+
+ if (family != 6)
+ return 0;
+
+ switch (model) {
+ case 0x57: /* Knights Landing */
+ return 1;
+ default:
+ return 0;
+ }
+}
static void
dump_cstate_pstate_config_info(family, model)
{
@@ -1770,6 +1890,9 @@
if (has_nhm_turbo_ratio_limit(family, model))
dump_nhm_turbo_ratio_limits();
+ if (has_knl_turbo_ratio_limit(family, model))
+ dump_knl_turbo_ratio_limits();
+
dump_nhm_cst_cfg();
}
@@ -1801,7 +1924,7 @@
if (get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr))
return 0;
- switch (msr & 0x7) {
+ switch (msr & 0xF) {
case ENERGY_PERF_BIAS_PERFORMANCE:
epb_string = "performance";
break;
@@ -1925,7 +2048,7 @@
unsigned long long msr;
if (do_rapl & RAPL_PKG_POWER_INFO)
- if (!get_msr(0, MSR_PKG_POWER_INFO, &msr))
+ if (!get_msr(base_cpu, MSR_PKG_POWER_INFO, &msr))
return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units;
switch (model) {
@@ -1950,6 +2073,7 @@
case 0x3F: /* HSX */
case 0x4F: /* BDX */
case 0x56: /* BDX-DE */
+ case 0x57: /* KNL */
return (rapl_dram_energy_units = 15.3 / 1000000);
default:
return (rapl_energy_units);
@@ -1991,6 +2115,7 @@
case 0x3F: /* HSX */
case 0x4F: /* BDX */
case 0x56: /* BDX-DE */
+ case 0x57: /* KNL */
do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
break;
case 0x2D:
@@ -2006,7 +2131,7 @@
}
/* units on package 0, verify later other packages match */
- if (get_msr(0, MSR_RAPL_POWER_UNIT, &msr))
+ if (get_msr(base_cpu, MSR_RAPL_POWER_UNIT, &msr))
return;
rapl_power_units = 1.0 / (1 << (msr & 0xF));
@@ -2331,6 +2456,17 @@
return 0;
}
+int is_knl(unsigned int family, unsigned int model)
+{
+ if (!genuine_intel)
+ return 0;
+ switch (model) {
+ case 0x57: /* KNL */
+ return 1;
+ }
+ return 0;
+}
+
#define SLM_BCLK_FREQS 5
double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0};
@@ -2340,7 +2476,7 @@
unsigned int i;
double freq;
- if (get_msr(0, MSR_FSB_FREQ, &msr))
+ if (get_msr(base_cpu, MSR_FSB_FREQ, &msr))
fprintf(stderr, "SLM BCLK: unknown\n");
i = msr & 0xf;
@@ -2408,7 +2544,7 @@
if (!do_nhm_platform_info)
goto guess;
- if (get_msr(0, MSR_IA32_TEMPERATURE_TARGET, &msr))
+ if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr))
goto guess;
target_c_local = (msr >> 16) & 0xFF;
@@ -2541,6 +2677,7 @@
do_c8_c9_c10 = has_hsw_msrs(family, model);
do_skl_residency = has_skl_msrs(family, model);
do_slm_cstates = is_slm(family, model);
+ do_knl_cstates = is_knl(family, model);
bclk = discover_bclk(family, model);
rapl_probe(family, model);
@@ -2755,13 +2892,9 @@
my_package_id = get_physical_package_id(cpu_id);
my_core_id = get_core_id(cpu_id);
-
- if (cpu_is_first_sibling_in_core(cpu_id)) {
- my_thread_id = 0;
+ my_thread_id = get_cpu_position_in_core(cpu_id);
+ if (!my_thread_id)
topo.num_cores++;
- } else {
- my_thread_id = 1;
- }
init_counter(EVEN_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id);
init_counter(ODD_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id);
@@ -2785,13 +2918,24 @@
for_all_proc_cpus(initialize_counters);
}
+void set_base_cpu(void)
+{
+ base_cpu = sched_getcpu();
+ if (base_cpu < 0)
+ err(-ENODEV, "No valid cpus found");
+
+ if (debug > 1)
+ fprintf(stderr, "base_cpu = %d\n", base_cpu);
+}
+
void turbostat_init()
{
+ setup_all_buffers();
+ set_base_cpu();
check_dev_msr();
check_permissions();
process_cpuid();
- setup_all_buffers();
if (debug)
for_all_cpus(print_epb, ODD_COUNTERS);
@@ -2870,7 +3014,7 @@
}
void print_version() {
- fprintf(stderr, "turbostat version 4.5 2 Apr, 2015"
+ fprintf(stderr, "turbostat version 4.7 27-May, 2015"
" - Len Brown <lenb@kernel.org>\n");
}
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 5bdb781..59d364a 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -4,7 +4,7 @@
.PHONY: all all_32 all_64 warn_32bit_failure clean
-TARGETS_C_BOTHBITS := sigreturn single_step_syscall
+TARGETS_C_BOTHBITS := sigreturn single_step_syscall sysret_ss_attrs
BINARIES_32 := $(TARGETS_C_BOTHBITS:%=%_32)
BINARIES_64 := $(TARGETS_C_BOTHBITS:%=%_64)
@@ -55,3 +55,6 @@
echo " yum install glibc-devel.*i686"; \
exit 0;
endif
+
+# Some tests have additional dependencies.
+sysret_ss_attrs_64: thunks.S
diff --git a/tools/testing/selftests/x86/sysret_ss_attrs.c b/tools/testing/selftests/x86/sysret_ss_attrs.c
new file mode 100644
index 0000000..ce42d5a
--- /dev/null
+++ b/tools/testing/selftests/x86/sysret_ss_attrs.c
@@ -0,0 +1,112 @@
+/*
+ * sysret_ss_attrs.c - test that syscalls return valid hidden SS attributes
+ * Copyright (c) 2015 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * On AMD CPUs, SYSRET can return with a valid SS descriptor with with
+ * the hidden attributes set to an unusable state. Make sure the kernel
+ * doesn't let this happen.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <err.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <pthread.h>
+
+static void *threadproc(void *ctx)
+{
+ /*
+ * Do our best to cause sleeps on this CPU to exit the kernel and
+ * re-enter with SS = 0.
+ */
+ while (true)
+ ;
+
+ return NULL;
+}
+
+#ifdef __x86_64__
+extern unsigned long call32_from_64(void *stack, void (*function)(void));
+
+asm (".pushsection .text\n\t"
+ ".code32\n\t"
+ "test_ss:\n\t"
+ "pushl $0\n\t"
+ "popl %eax\n\t"
+ "ret\n\t"
+ ".code64");
+extern void test_ss(void);
+#endif
+
+int main()
+{
+ /*
+ * Start a busy-looping thread on the same CPU we're on.
+ * For simplicity, just stick everything to CPU 0. This will
+ * fail in some containers, but that's probably okay.
+ */
+ cpu_set_t cpuset;
+ CPU_ZERO(&cpuset);
+ CPU_SET(0, &cpuset);
+ if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+ printf("[WARN]\tsched_setaffinity failed\n");
+
+ pthread_t thread;
+ if (pthread_create(&thread, 0, threadproc, 0) != 0)
+ err(1, "pthread_create");
+
+#ifdef __x86_64__
+ unsigned char *stack32 = mmap(NULL, 4096, PROT_READ | PROT_WRITE,
+ MAP_32BIT | MAP_ANONYMOUS | MAP_PRIVATE,
+ -1, 0);
+ if (stack32 == MAP_FAILED)
+ err(1, "mmap");
+#endif
+
+ printf("[RUN]\tSyscalls followed by SS validation\n");
+
+ for (int i = 0; i < 1000; i++) {
+ /*
+ * Go to sleep and return using sysret (if we're 64-bit
+ * or we're 32-bit on AMD on a 64-bit kernel). On AMD CPUs,
+ * SYSRET doesn't fix up the cached SS descriptor, so the
+ * kernel needs some kind of workaround to make sure that we
+ * end the system call with a valid stack segment. This
+ * can be a confusing failure because the SS *selector*
+ * is the same regardless.
+ */
+ usleep(2);
+
+#ifdef __x86_64__
+ /*
+ * On 32-bit, just doing a syscall through glibc is enough
+ * to cause a crash if our cached SS descriptor is invalid.
+ * On 64-bit, it's not, so try extra hard.
+ */
+ call32_from_64(stack32 + 4088, test_ss);
+#endif
+ }
+
+ printf("[OK]\tWe survived\n");
+
+#ifdef __x86_64__
+ munmap(stack32, 4096);
+#endif
+
+ return 0;
+}
diff --git a/tools/testing/selftests/x86/thunks.S b/tools/testing/selftests/x86/thunks.S
new file mode 100644
index 0000000..ce8a995
--- /dev/null
+++ b/tools/testing/selftests/x86/thunks.S
@@ -0,0 +1,67 @@
+/*
+ * thunks.S - assembly helpers for mixed-bitness code
+ * Copyright (c) 2015 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * These are little helpers that make it easier to switch bitness on
+ * the fly.
+ */
+
+ .text
+
+ .global call32_from_64
+ .type call32_from_64, @function
+call32_from_64:
+ // rdi: stack to use
+ // esi: function to call
+
+ // Save registers
+ pushq %rbx
+ pushq %rbp
+ pushq %r12
+ pushq %r13
+ pushq %r14
+ pushq %r15
+ pushfq
+
+ // Switch stacks
+ mov %rsp,(%rdi)
+ mov %rdi,%rsp
+
+ // Switch to compatibility mode
+ pushq $0x23 /* USER32_CS */
+ pushq $1f
+ lretq
+
+1:
+ .code32
+ // Call the function
+ call *%esi
+ // Switch back to long mode
+ jmp $0x33,$1f
+ .code64
+
+1:
+ // Restore the stack
+ mov (%rsp),%rsp
+
+ // Restore registers
+ popfq
+ popq %r15
+ popq %r14
+ popq %r13
+ popq %r12
+ popq %rbp
+ popq %rbx
+
+ ret
+
+.size call32_from_64, .-call32_from_64