aboutsummaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorMark Brown <broonie@kernel.org>2014-11-14 17:56:33 +0000
committerMark Brown <broonie@kernel.org>2014-11-14 17:56:33 +0000
commit11a266d2e5e6b73bfba337fb3ef21c8fd4fa4150 (patch)
tree3c4ca0079cb67feeaa6a678212ca6f4313cf5a69 /arch
parent5bca889af9ee712d0dac3b61b1cec79e7c99ec58 (diff)
parent9c3da88145da7cd96bb898bc0304d3f783d4c8b2 (diff)
Merge tag 'v3.14.24' into linux-linaro-lsk-v3.14
This is the 3.14.24 stable release
Diffstat (limited to 'arch')
-rw-r--r--arch/arc/boot/dts/nsimosci.dts2
-rw-r--r--arch/arc/include/asm/cache.h27
-rw-r--r--arch/arc/include/asm/kgdb.h32
-rw-r--r--arch/arc/kernel/head.S45
-rw-r--r--arch/arc/mm/cache_arc700.c113
-rw-r--r--arch/mips/include/asm/ftrace.h4
-rw-r--r--arch/mips/mm/tlbex.c6
-rw-r--r--arch/powerpc/platforms/pseries/dlpar.c4
-rw-r--r--arch/sh/kernel/cpu/sh3/setup-sh770x.c6
-rw-r--r--arch/um/drivers/ubd_kern.c5
-rw-r--r--arch/x86/Kconfig7
-rw-r--r--arch/x86/ia32/ia32entry.S18
-rw-r--r--arch/x86/include/asm/elf.h5
-rw-r--r--arch/x86/include/asm/iosf_mbi.h55
-rw-r--r--arch/x86/include/asm/kvm_host.h16
-rw-r--r--arch/x86/include/uapi/asm/vmx.h2
-rw-r--r--arch/x86/kernel/apic/apic.c4
-rw-r--r--arch/x86/kernel/cpu/common.c2
-rw-r--r--arch/x86/kernel/cpu/intel.c17
-rw-r--r--arch/x86/kernel/iosf_mbi.c15
-rw-r--r--arch/x86/kernel/signal.c5
-rw-r--r--arch/x86/kernel/tsc.c5
-rw-r--r--arch/x86/kernel/xsave.c7
-rw-r--r--arch/x86/kvm/emulate.c99
-rw-r--r--arch/x86/kvm/i8254.c2
-rw-r--r--arch/x86/kvm/svm.c8
-rw-r--r--arch/x86/kvm/vmx.c24
-rw-r--r--arch/x86/kvm/x86.c38
-rw-r--r--arch/x86/mm/pageattr.c2
29 files changed, 401 insertions, 174 deletions
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index 4f31b2eb5cdf..398064cef746 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -20,7 +20,7 @@
/* this is for console on PGU */
/* bootargs = "console=tty0 consoleblank=0"; */
/* this is for console on serial */
- bootargs = "earlycon=uart8250,mmio32,0xc0000000,115200n8 console=ttyS0,115200n8 consoleblank=0 debug";
+ bootargs = "earlycon=uart8250,mmio32,0xc0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug";
};
aliases {
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 2fd3162ec4df..c1d3d2da1191 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -55,4 +55,31 @@ extern void read_decode_cache_bcr(void);
#endif /* !__ASSEMBLY__ */
+/* Instruction cache related Auxiliary registers */
+#define ARC_REG_IC_BCR 0x77 /* Build Config reg */
+#define ARC_REG_IC_IVIC 0x10
+#define ARC_REG_IC_CTRL 0x11
+#define ARC_REG_IC_IVIL 0x19
+#if defined(CONFIG_ARC_MMU_V3) || defined (CONFIG_ARC_MMU_V4)
+#define ARC_REG_IC_PTAG 0x1E
+#endif
+
+/* Bit val in IC_CTRL */
+#define IC_CTRL_CACHE_DISABLE 0x1
+
+/* Data cache related Auxiliary registers */
+#define ARC_REG_DC_BCR 0x72 /* Build Config reg */
+#define ARC_REG_DC_IVDC 0x47
+#define ARC_REG_DC_CTRL 0x48
+#define ARC_REG_DC_IVDL 0x4A
+#define ARC_REG_DC_FLSH 0x4B
+#define ARC_REG_DC_FLDL 0x4C
+#if defined(CONFIG_ARC_MMU_V3) || defined (CONFIG_ARC_MMU_V4)
+#define ARC_REG_DC_PTAG 0x5C
+#endif
+
+/* Bit val in DC_CTRL */
+#define DC_CTRL_INV_MODE_FLUSH 0x40
+#define DC_CTRL_FLUSH_STATUS 0x100
+
#endif /* _ASM_CACHE_H */
diff --git a/arch/arc/include/asm/kgdb.h b/arch/arc/include/asm/kgdb.h
index b65fca7ffeb5..fea931634136 100644
--- a/arch/arc/include/asm/kgdb.h
+++ b/arch/arc/include/asm/kgdb.h
@@ -19,7 +19,7 @@
* register API yet */
#undef DBG_MAX_REG_NUM
-#define GDB_MAX_REGS 39
+#define GDB_MAX_REGS 87
#define BREAK_INSTR_SIZE 2
#define CACHE_FLUSH_IS_SAFE 1
@@ -33,23 +33,27 @@ static inline void arch_kgdb_breakpoint(void)
extern void kgdb_trap(struct pt_regs *regs);
-enum arc700_linux_regnums {
+/* This is the numbering of registers according to the GDB. See GDB's
+ * arc-tdep.h for details.
+ *
+ * Registers are ordered for GDB 7.5. It is incompatible with GDB 6.8. */
+enum arc_linux_regnums {
_R0 = 0,
_R1, _R2, _R3, _R4, _R5, _R6, _R7, _R8, _R9, _R10, _R11, _R12, _R13,
_R14, _R15, _R16, _R17, _R18, _R19, _R20, _R21, _R22, _R23, _R24,
_R25, _R26,
- _BTA = 27,
- _LP_START = 28,
- _LP_END = 29,
- _LP_COUNT = 30,
- _STATUS32 = 31,
- _BLINK = 32,
- _FP = 33,
- __SP = 34,
- _EFA = 35,
- _RET = 36,
- _ORIG_R8 = 37,
- _STOP_PC = 38
+ _FP = 27,
+ __SP = 28,
+ _R30 = 30,
+ _BLINK = 31,
+ _LP_COUNT = 60,
+ _STOP_PC = 64,
+ _RET = 64,
+ _LP_START = 65,
+ _LP_END = 66,
+ _STATUS32 = 67,
+ _ECR = 76,
+ _BTA = 82,
};
#else
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 991997269d02..07a58f2d3077 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -12,10 +12,42 @@
* to skip certain things during boot on simulator
*/
+#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#include <asm/entry.h>
-#include <linux/linkage.h>
#include <asm/arcregs.h>
+#include <asm/cache.h>
+
+.macro CPU_EARLY_SETUP
+
+ ; Setting up Vectror Table (in case exception happens in early boot
+ sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+
+ ; Disable I-cache/D-cache if kernel so configured
+ lr r5, [ARC_REG_IC_BCR]
+ breq r5, 0, 1f ; I$ doesn't exist
+ lr r5, [ARC_REG_IC_CTRL]
+#ifdef CONFIG_ARC_HAS_ICACHE
+ bclr r5, r5, 0 ; 0 - Enable, 1 is Disable
+#else
+ bset r5, r5, 0 ; I$ exists, but is not used
+#endif
+ sr r5, [ARC_REG_IC_CTRL]
+
+1:
+ lr r5, [ARC_REG_DC_BCR]
+ breq r5, 0, 1f ; D$ doesn't exist
+ lr r5, [ARC_REG_DC_CTRL]
+ bclr r5, r5, 6 ; Invalidate (discard w/o wback)
+#ifdef CONFIG_ARC_HAS_DCACHE
+ bclr r5, r5, 0 ; Enable (+Inv)
+#else
+ bset r5, r5, 0 ; Disable (+Inv)
+#endif
+ sr r5, [ARC_REG_DC_CTRL]
+
+1:
+.endm
.cpu A7
@@ -24,13 +56,13 @@
.globl stext
stext:
;-------------------------------------------------------------------
- ; Don't clobber r0-r4 yet. It might have bootloader provided info
+ ; Don't clobber r0-r2 yet. It might have bootloader provided info
;-------------------------------------------------------------------
- sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+ CPU_EARLY_SETUP
#ifdef CONFIG_SMP
- ; Only Boot (Master) proceeds. Others wait in platform dependent way
+ ; Ensure Boot (Master) proceeds. Others wait in platform dependent way
; IDENTITY Reg [ 3 2 1 0 ]
; (cpu-id) ^^^ => Zero for UP ARC700
; => #Core-ID if SMP (Master 0)
@@ -39,7 +71,8 @@ stext:
; need to make sure only boot cpu takes this path.
GET_CPU_ID r5
cmp r5, 0
- jnz arc_platform_smp_wait_to_boot
+ mov.ne r0, r5
+ jne arc_platform_smp_wait_to_boot
#endif
; Clear BSS before updating any globals
; XXX: use ZOL here
@@ -89,7 +122,7 @@ stext:
first_lines_of_secondary:
- sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+ CPU_EARLY_SETUP
; setup per-cpu idle task as "current" on this CPU
ld r0, [@secondary_idle_tsk]
diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
index 400c663b21c2..1f676c4794e0 100644
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache_arc700.c
@@ -73,37 +73,9 @@
#include <asm/cachectl.h>
#include <asm/setup.h>
-/* Instruction cache related Auxiliary registers */
-#define ARC_REG_IC_BCR 0x77 /* Build Config reg */
-#define ARC_REG_IC_IVIC 0x10
-#define ARC_REG_IC_CTRL 0x11
-#define ARC_REG_IC_IVIL 0x19
-#if (CONFIG_ARC_MMU_VER > 2)
-#define ARC_REG_IC_PTAG 0x1E
-#endif
-
-/* Bit val in IC_CTRL */
-#define IC_CTRL_CACHE_DISABLE 0x1
-
-/* Data cache related Auxiliary registers */
-#define ARC_REG_DC_BCR 0x72 /* Build Config reg */
-#define ARC_REG_DC_IVDC 0x47
-#define ARC_REG_DC_CTRL 0x48
-#define ARC_REG_DC_IVDL 0x4A
-#define ARC_REG_DC_FLSH 0x4B
-#define ARC_REG_DC_FLDL 0x4C
-#if (CONFIG_ARC_MMU_VER > 2)
-#define ARC_REG_DC_PTAG 0x5C
-#endif
-
-/* Bit val in DC_CTRL */
-#define DC_CTRL_INV_MODE_FLUSH 0x40
-#define DC_CTRL_FLUSH_STATUS 0x100
-
-char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len)
+char *arc_cache_mumbojumbo(int c, char *buf, int len)
{
int n = 0;
- unsigned int c = smp_processor_id();
#define PR_CACHE(p, enb, str) \
{ \
@@ -169,72 +141,43 @@ void read_decode_cache_bcr(void)
*/
void arc_cache_init(void)
{
- unsigned int cpu = smp_processor_id();
- struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
- struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache;
- unsigned int dcache_does_alias, temp;
+ unsigned int __maybe_unused cpu = smp_processor_id();
+ struct cpuinfo_arc_cache __maybe_unused *ic, __maybe_unused *dc;
char str[256];
printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
- if (!ic->ver)
- goto chk_dc;
-
-#ifdef CONFIG_ARC_HAS_ICACHE
- /* 1. Confirm some of I-cache params which Linux assumes */
- if (ic->line_len != L1_CACHE_BYTES)
- panic("Cache H/W doesn't match kernel Config");
-
- if (ic->ver != CONFIG_ARC_MMU_VER)
- panic("Cache ver doesn't match MMU ver\n");
-#endif
-
- /* Enable/disable I-Cache */
- temp = read_aux_reg(ARC_REG_IC_CTRL);
-
#ifdef CONFIG_ARC_HAS_ICACHE
- temp &= ~IC_CTRL_CACHE_DISABLE;
-#else
- temp |= IC_CTRL_CACHE_DISABLE;
+ ic = &cpuinfo_arc700[cpu].icache;
+ if (ic->ver) {
+ if (ic->line_len != L1_CACHE_BYTES)
+ panic("ICache line [%d] != kernel Config [%d]",
+ ic->line_len, L1_CACHE_BYTES);
+
+ if (ic->ver != CONFIG_ARC_MMU_VER)
+ panic("Cache ver [%d] doesn't match MMU ver [%d]\n",
+ ic->ver, CONFIG_ARC_MMU_VER);
+ }
#endif
- write_aux_reg(ARC_REG_IC_CTRL, temp);
-
-chk_dc:
- if (!dc->ver)
- return;
-
#ifdef CONFIG_ARC_HAS_DCACHE
- if (dc->line_len != L1_CACHE_BYTES)
- panic("Cache H/W doesn't match kernel Config");
+ dc = &cpuinfo_arc700[cpu].dcache;
+ if (dc->ver) {
+ unsigned int dcache_does_alias;
- /* check for D-Cache aliasing */
- dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE;
+ if (dc->line_len != L1_CACHE_BYTES)
+ panic("DCache line [%d] != kernel Config [%d]",
+ dc->line_len, L1_CACHE_BYTES);
- if (dcache_does_alias && !cache_is_vipt_aliasing())
- panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
- else if (!dcache_does_alias && cache_is_vipt_aliasing())
- panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n");
-#endif
-
- /* Set the default Invalidate Mode to "simpy discard dirty lines"
- * as this is more frequent then flush before invalidate
- * Ofcourse we toggle this default behviour when desired
- */
- temp = read_aux_reg(ARC_REG_DC_CTRL);
- temp &= ~DC_CTRL_INV_MODE_FLUSH;
+ /* check for D-Cache aliasing */
+ dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE;
-#ifdef CONFIG_ARC_HAS_DCACHE
- /* Enable D-Cache: Clear Bit 0 */
- write_aux_reg(ARC_REG_DC_CTRL, temp & ~IC_CTRL_CACHE_DISABLE);
-#else
- /* Flush D cache */
- write_aux_reg(ARC_REG_DC_FLSH, 0x1);
- /* Disable D cache */
- write_aux_reg(ARC_REG_DC_CTRL, temp | IC_CTRL_CACHE_DISABLE);
+ if (dcache_does_alias && !cache_is_vipt_aliasing())
+ panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+ else if (!dcache_does_alias && cache_is_vipt_aliasing())
+ panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+ }
#endif
-
- return;
}
#define OP_INV 0x1
@@ -254,12 +197,16 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr,
if (cacheop == OP_INV_IC) {
aux_cmd = ARC_REG_IC_IVIL;
+#if (CONFIG_ARC_MMU_VER > 2)
aux_tag = ARC_REG_IC_PTAG;
+#endif
}
else {
/* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */
aux_cmd = cacheop & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL;
+#if (CONFIG_ARC_MMU_VER > 2)
aux_tag = ARC_REG_DC_PTAG;
+#endif
}
/* Ensure we properly floor/ceil the non-line aligned/sized requests
diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h
index 992aaba603b5..b463f2aa5a61 100644
--- a/arch/mips/include/asm/ftrace.h
+++ b/arch/mips/include/asm/ftrace.h
@@ -24,7 +24,7 @@ do { \
asm volatile ( \
"1: " load " %[tmp_dst], 0(%[tmp_src])\n" \
" li %[tmp_err], 0\n" \
- "2:\n" \
+ "2: .insn\n" \
\
".section .fixup, \"ax\"\n" \
"3: li %[tmp_err], 1\n" \
@@ -46,7 +46,7 @@ do { \
asm volatile ( \
"1: " store " %[tmp_src], 0(%[tmp_dst])\n"\
" li %[tmp_err], 0\n" \
- "2:\n" \
+ "2: .insn\n" \
\
".section .fixup, \"ax\"\n" \
"3: li %[tmp_err], 1\n" \
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 65d452aa1fda..dd012c599ad1 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -1057,6 +1057,7 @@ static void build_update_entries(u32 **p, unsigned int tmp, unsigned int ptep)
struct mips_huge_tlb_info {
int huge_pte;
int restore_scratch;
+ bool need_reload_pte;
};
static struct mips_huge_tlb_info
@@ -1071,6 +1072,7 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l,
rv.huge_pte = scratch;
rv.restore_scratch = 0;
+ rv.need_reload_pte = false;
if (check_for_high_segbits) {
UASM_i_MFC0(p, tmp, C0_BADVADDR);
@@ -1259,6 +1261,7 @@ static void build_r4000_tlb_refill_handler(void)
} else {
htlb_info.huge_pte = K0;
htlb_info.restore_scratch = 0;
+ htlb_info.need_reload_pte = true;
vmalloc_mode = refill_noscratch;
/*
* create the plain linear handler
@@ -1295,7 +1298,8 @@ static void build_r4000_tlb_refill_handler(void)
}
#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
uasm_l_tlb_huge_update(&l, p);
- UASM_i_LW(&p, K0, 0, K1);
+ if (htlb_info.need_reload_pte)
+ UASM_i_LW(&p, htlb_info.huge_pte, 0, K1);
build_huge_update_entries(&p, htlb_info.huge_pte, K1);
build_huge_tlb_write_entry(&p, &l, &r, K0, tlb_random,
htlb_info.restore_scratch);
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index a8fe5aa3d34f..3b46eed1dcf6 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -380,7 +380,7 @@ static int dlpar_online_cpu(struct device_node *dn)
BUG_ON(get_cpu_current_state(cpu)
!= CPU_STATE_OFFLINE);
cpu_maps_update_done();
- rc = cpu_up(cpu);
+ rc = device_online(get_cpu_device(cpu));
if (rc)
goto out;
cpu_maps_update_begin();
@@ -463,7 +463,7 @@ static int dlpar_offline_cpu(struct device_node *dn)
if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) {
set_preferred_offline_state(cpu, CPU_STATE_OFFLINE);
cpu_maps_update_done();
- rc = cpu_down(cpu);
+ rc = device_offline(get_cpu_device(cpu));
if (rc)
goto out;
cpu_maps_update_begin();
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh770x.c b/arch/sh/kernel/cpu/sh3/setup-sh770x.c
index ff1465c0519c..5acf89c1afc5 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c
@@ -118,7 +118,7 @@ static struct plat_sci_port scif0_platform_data = {
};
static struct resource scif0_resources[] = {
- DEFINE_RES_MEM(0xfffffe80, 0x100),
+ DEFINE_RES_MEM(0xfffffe80, 0x10),
DEFINE_RES_IRQ(evt2irq(0x4e0)),
};
@@ -143,7 +143,7 @@ static struct plat_sci_port scif1_platform_data = {
};
static struct resource scif1_resources[] = {
- DEFINE_RES_MEM(0xa4000150, 0x100),
+ DEFINE_RES_MEM(0xa4000150, 0x10),
DEFINE_RES_IRQ(evt2irq(0x900)),
};
@@ -169,7 +169,7 @@ static struct plat_sci_port scif2_platform_data = {
};
static struct resource scif2_resources[] = {
- DEFINE_RES_MEM(0xa4000140, 0x100),
+ DEFINE_RES_MEM(0xa4000140, 0x10),
DEFINE_RES_IRQ(evt2irq(0x880)),
};
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 3716e6952554..e8ab93c3e638 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -1277,7 +1277,7 @@ static void do_ubd_request(struct request_queue *q)
while(1){
struct ubd *dev = q->queuedata;
- if(dev->end_sg == 0){
+ if(dev->request == NULL){
struct request *req = blk_fetch_request(q);
if(req == NULL)
return;
@@ -1299,7 +1299,8 @@ static void do_ubd_request(struct request_queue *q)
return;
}
prepare_flush_request(req, io_req);
- submit_request(io_req, dev);
+ if (submit_request(io_req, dev) == false)
+ return;
}
while(dev->start_sg < dev->end_sg){
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e4098912fef2..98aa930230ec 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2436,12 +2436,9 @@ config X86_DMA_REMAP
depends on STA2X11
config IOSF_MBI
- bool
+ tristate
+ default m
depends on PCI
- ---help---
- To be selected by modules requiring access to the Intel OnChip System
- Fabric (IOSF) Sideband MailBox Interface (MBI). For MBI platforms
- enumerable by PCI.
source "net/Kconfig"
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 4299eb05023c..92a2e9333620 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -151,6 +151,16 @@ ENTRY(ia32_sysenter_target)
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-ARGOFFSET(%rsp)
+ jnz sysenter_fix_flags
+sysenter_flags_fixed:
+
orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
CFI_REMEMBER_STATE
@@ -184,6 +194,8 @@ sysexit_from_sys_call:
TRACE_IRQS_ON
ENABLE_INTERRUPTS_SYSEXIT32
+ CFI_RESTORE_STATE
+
#ifdef CONFIG_AUDITSYSCALL
.macro auditsys_entry_common
movl %esi,%r9d /* 6th arg: 4th syscall arg */
@@ -226,7 +238,6 @@ sysexit_from_sys_call:
.endm
sysenter_auditsys:
- CFI_RESTORE_STATE
auditsys_entry_common
movl %ebp,%r9d /* reload 6th syscall arg */
jmp sysenter_dispatch
@@ -235,6 +246,11 @@ 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),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 9c999c1674fa..01f15b227d7e 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -155,8 +155,9 @@ do { \
#define elf_check_arch(x) \
((x)->e_machine == EM_X86_64)
-#define compat_elf_check_arch(x) \
- (elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64)
+#define compat_elf_check_arch(x) \
+ (elf_check_arch_ia32(x) || \
+ (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64))
#if __USER32_DS != __USER_DS
# error "The following code assumes __USER32_DS == __USER_DS"
diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h
index 8e71c7941767..57995f0596a6 100644
--- a/arch/x86/include/asm/iosf_mbi.h
+++ b/arch/x86/include/asm/iosf_mbi.h
@@ -50,6 +50,32 @@
#define BT_MBI_PCIE_READ 0x00
#define BT_MBI_PCIE_WRITE 0x01
+/* Quark available units */
+#define QRK_MBI_UNIT_HBA 0x00
+#define QRK_MBI_UNIT_HB 0x03
+#define QRK_MBI_UNIT_RMU 0x04
+#define QRK_MBI_UNIT_MM 0x05
+#define QRK_MBI_UNIT_MMESRAM 0x05
+#define QRK_MBI_UNIT_SOC 0x31
+
+/* Quark read/write opcodes */
+#define QRK_MBI_HBA_READ 0x10
+#define QRK_MBI_HBA_WRITE 0x11
+#define QRK_MBI_HB_READ 0x10
+#define QRK_MBI_HB_WRITE 0x11
+#define QRK_MBI_RMU_READ 0x10
+#define QRK_MBI_RMU_WRITE 0x11
+#define QRK_MBI_MM_READ 0x10
+#define QRK_MBI_MM_WRITE 0x11
+#define QRK_MBI_MMESRAM_READ 0x12
+#define QRK_MBI_MMESRAM_WRITE 0x13
+#define QRK_MBI_SOC_READ 0x06
+#define QRK_MBI_SOC_WRITE 0x07
+
+#if IS_ENABLED(CONFIG_IOSF_MBI)
+
+bool iosf_mbi_available(void);
+
/**
* iosf_mbi_read() - MailBox Interface read command
* @port: port indicating subunit being accessed
@@ -87,4 +113,33 @@ int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr);
*/
int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask);
+#else /* CONFIG_IOSF_MBI is not enabled */
+static inline
+bool iosf_mbi_available(void)
+{
+ return false;
+}
+
+static inline
+int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr)
+{
+ WARN(1, "IOSF_MBI driver not available");
+ return -EPERM;
+}
+
+static inline
+int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr)
+{
+ WARN(1, "IOSF_MBI driver not available");
+ return -EPERM;
+}
+
+static inline
+int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask)
+{
+ WARN(1, "IOSF_MBI driver not available");
+ return -EPERM;
+}
+#endif /* CONFIG_IOSF_MBI */
+
#endif /* IOSF_MBI_SYMS_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a2b17f7ac842..829e3088b5a0 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -980,6 +980,20 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
}
+static inline u64 get_canonical(u64 la)
+{
+ return ((int64_t)la << 16) >> 16;
+}
+
+static inline bool is_noncanonical_address(u64 la)
+{
+#ifdef CONFIG_X86_64
+ return get_canonical(la) != la;
+#else
+ return false;
+#endif
+}
+
#define TSS_IOPB_BASE_OFFSET 0x66
#define TSS_BASE_SIZE 0x68
#define TSS_IOPB_SIZE (65536 / 8)
@@ -1038,7 +1052,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
void kvm_vcpu_reset(struct kvm_vcpu *vcpu);
void kvm_define_shared_msr(unsigned index, u32 msr);
-void kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
+int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 0e79420376eb..990a2fe1588d 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -67,6 +67,7 @@
#define EXIT_REASON_EPT_MISCONFIG 49
#define EXIT_REASON_INVEPT 50
#define EXIT_REASON_PREEMPTION_TIMER 52
+#define EXIT_REASON_INVVPID 53
#define EXIT_REASON_WBINVD 54
#define EXIT_REASON_XSETBV 55
#define EXIT_REASON_APIC_WRITE 56
@@ -114,6 +115,7 @@
{ EXIT_REASON_EOI_INDUCED, "EOI_INDUCED" }, \
{ EXIT_REASON_INVALID_STATE, "INVALID_STATE" }, \
{ EXIT_REASON_INVD, "INVD" }, \
+ { EXIT_REASON_INVVPID, "INVVPID" }, \
{ EXIT_REASON_INVPCID, "INVPCID" }
#endif /* _UAPIVMX_H */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 7f26c9a70a9e..523f147b2470 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1290,7 +1290,7 @@ void setup_local_APIC(void)
unsigned int value, queued;
int i, j, acked = 0;
unsigned long long tsc = 0, ntsc;
- long long max_loops = cpu_khz;
+ long long max_loops = cpu_khz ? cpu_khz : 1000000;
if (cpu_has_tsc)
rdtscll(tsc);
@@ -1387,7 +1387,7 @@ void setup_local_APIC(void)
break;
}
if (queued) {
- if (cpu_has_tsc) {
+ if (cpu_has_tsc && cpu_khz) {
rdtscll(ntsc);
max_loops = (cpu_khz << 10) - (ntsc - tsc);
} else
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8e28bf2fc3ef..3f27f5fd0847 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1141,7 +1141,7 @@ void syscall_init(void)
/* Flags to clear on syscall */
wrmsrl(MSR_SYSCALL_MASK,
X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|
- X86_EFLAGS_IOPL|X86_EFLAGS_AC);
+ X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT);
}
/*
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index c1a07d33e67e..66746a880dec 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -383,6 +383,13 @@ static void init_intel(struct cpuinfo_x86 *c)
detect_extended_topology(c);
l2 = init_intel_cacheinfo(c);
+
+ /* Detect legacy cache sizes if init_intel_cacheinfo did not */
+ if (l2 == 0) {
+ cpu_detect_cache_sizes(c);
+ l2 = c->x86_cache_size;
+ }
+
if (c->cpuid_level > 9) {
unsigned eax = cpuid_eax(10);
/* Check for version and the number of counters */
@@ -497,6 +504,13 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
*/
if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0))
size = 256;
+
+ /*
+ * Intel Quark SoC X1000 contains a 4-way set associative
+ * 16K cache with a 16 byte cache line and 256 lines per tag
+ */
+ if ((c->x86 == 5) && (c->x86_model == 9))
+ size = 16;
return size;
}
#endif
@@ -724,7 +738,8 @@ static const struct cpu_dev intel_cpu_dev = {
[3] = "OverDrive PODP5V83",
[4] = "Pentium MMX",
[7] = "Mobile Pentium 75 - 200",
- [8] = "Mobile Pentium MMX"
+ [8] = "Mobile Pentium MMX",
+ [9] = "Quark SoC X1000",
}
},
{ .family = 6, .model_names =
diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c
index c3aae6672843..2e97b3cfa6c7 100644
--- a/arch/x86/kernel/iosf_mbi.c
+++ b/arch/x86/kernel/iosf_mbi.c
@@ -25,6 +25,10 @@
#include <asm/iosf_mbi.h>
+#define PCI_DEVICE_ID_BAYTRAIL 0x0F00
+#define PCI_DEVICE_ID_BRASWELL 0x2280
+#define PCI_DEVICE_ID_QUARK_X1000 0x0958
+
static DEFINE_SPINLOCK(iosf_mbi_lock);
static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset)
@@ -177,6 +181,13 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask)
}
EXPORT_SYMBOL(iosf_mbi_modify);
+bool iosf_mbi_available(void)
+{
+ /* Mbi isn't hot-pluggable. No remove routine is provided */
+ return mbi_pdev;
+}
+EXPORT_SYMBOL(iosf_mbi_available);
+
static int iosf_mbi_probe(struct pci_dev *pdev,
const struct pci_device_id *unused)
{
@@ -193,7 +204,9 @@ static int iosf_mbi_probe(struct pci_dev *pdev,
}
static DEFINE_PCI_DEVICE_TABLE(iosf_mbi_pci_ids) = {
- { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0F00) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) },
{ 0, },
};
MODULE_DEVICE_TABLE(pci, iosf_mbi_pci_ids);
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 9e5de6813e1f..b88fc86309bc 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -673,6 +673,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
* handler too.
*/
regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF);
+ /*
+ * Ensure the signal handler starts with the new fpu state.
+ */
+ if (used_math())
+ drop_init_fpu(current);
}
signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP));
}
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index e0d1d7a8354e..de0290605903 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1173,14 +1173,17 @@ void __init tsc_init(void)
x86_init.timers.tsc_pre_init();
- if (!cpu_has_tsc)
+ if (!cpu_has_tsc) {
+ setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
return;
+ }
tsc_khz = x86_platform.calibrate_tsc();
cpu_khz = tsc_khz;
if (!tsc_khz) {
mark_tsc_unstable("could not calculate TSC khz");
+ setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
return;
}
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index a4b451c6addf..dd50e26c58f6 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -268,8 +268,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
return -1;
- drop_init_fpu(tsk); /* trigger finit */
-
return 0;
}
@@ -399,8 +397,11 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
set_used_math();
}
- if (use_eager_fpu())
+ if (use_eager_fpu()) {
+ preempt_disable();
math_state_restore();
+ preempt_enable();
+ }
return err;
} else {
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 7bff3e2a7a11..38d3751472e4 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -498,11 +498,6 @@ static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
masked_increment(reg_rmw(ctxt, VCPU_REGS_RSP), stack_mask(ctxt), inc);
}
-static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
-{
- register_address_increment(ctxt, &ctxt->_eip, rel);
-}
-
static u32 desc_limit_scaled(struct desc_struct *desc)
{
u32 limit = get_desc_limit(desc);
@@ -576,6 +571,38 @@ static int emulate_nm(struct x86_emulate_ctxt *ctxt)
return emulate_exception(ctxt, NM_VECTOR, 0, false);
}
+static inline int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst,
+ int cs_l)
+{
+ switch (ctxt->op_bytes) {
+ case 2:
+ ctxt->_eip = (u16)dst;
+ break;
+ case 4:
+ ctxt->_eip = (u32)dst;
+ break;
+ case 8:
+ if ((cs_l && is_noncanonical_address(dst)) ||
+ (!cs_l && (dst & ~(u32)-1)))
+ return emulate_gp(ctxt, 0);
+ ctxt->_eip = dst;
+ break;
+ default:
+ WARN(1, "unsupported eip assignment size\n");
+ }
+ return X86EMUL_CONTINUE;
+}
+
+static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst)
+{
+ return assign_eip_far(ctxt, dst, ctxt->mode == X86EMUL_MODE_PROT64);
+}
+
+static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
+{
+ return assign_eip_near(ctxt, ctxt->_eip + rel);
+}
+
static u16 get_segment_selector(struct x86_emulate_ctxt *ctxt, unsigned seg)
{
u16 selector;
@@ -1958,13 +1985,15 @@ static int em_grp45(struct x86_emulate_ctxt *ctxt)
case 2: /* call near abs */ {
long int old_eip;
old_eip = ctxt->_eip;
- ctxt->_eip = ctxt->src.val;
+ rc = assign_eip_near(ctxt, ctxt->src.val);
+ if (rc != X86EMUL_CONTINUE)
+ break;
ctxt->src.val = old_eip;
rc = em_push(ctxt);
break;
}
case 4: /* jmp abs */
- ctxt->_eip = ctxt->src.val;
+ rc = assign_eip_near(ctxt, ctxt->src.val);
break;
case 5: /* jmp far */
rc = em_jmp_far(ctxt);
@@ -1996,10 +2025,14 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt)
static int em_ret(struct x86_emulate_ctxt *ctxt)
{
- ctxt->dst.type = OP_REG;
- ctxt->dst.addr.reg = &ctxt->_eip;
- ctxt->dst.bytes = ctxt->op_bytes;
- return em_pop(ctxt);
+ int rc;
+ unsigned long eip;
+
+ rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
+ return assign_eip_near(ctxt, eip);
}
static int em_ret_far(struct x86_emulate_ctxt *ctxt)
@@ -2277,7 +2310,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
{
const struct x86_emulate_ops *ops = ctxt->ops;
struct desc_struct cs, ss;
- u64 msr_data;
+ u64 msr_data, rcx, rdx;
int usermode;
u16 cs_sel = 0, ss_sel = 0;
@@ -2293,6 +2326,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
else
usermode = X86EMUL_MODE_PROT32;
+ rcx = reg_read(ctxt, VCPU_REGS_RCX);
+ rdx = reg_read(ctxt, VCPU_REGS_RDX);
+
cs.dpl = 3;
ss.dpl = 3;
ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
@@ -2310,6 +2346,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
ss_sel = cs_sel + 8;
cs.d = 0;
cs.l = 1;
+ if (is_noncanonical_address(rcx) ||
+ is_noncanonical_address(rdx))
+ return emulate_gp(ctxt, 0);
break;
}
cs_sel |= SELECTOR_RPL_MASK;
@@ -2318,8 +2357,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS);
ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
- ctxt->_eip = reg_read(ctxt, VCPU_REGS_RDX);
- *reg_write(ctxt, VCPU_REGS_RSP) = reg_read(ctxt, VCPU_REGS_RCX);
+ ctxt->_eip = rdx;
+ *reg_write(ctxt, VCPU_REGS_RSP) = rcx;
return X86EMUL_CONTINUE;
}
@@ -2858,10 +2897,13 @@ static int em_aad(struct x86_emulate_ctxt *ctxt)
static int em_call(struct x86_emulate_ctxt *ctxt)
{
+ int rc;
long rel = ctxt->src.val;
ctxt->src.val = (unsigned long)ctxt->_eip;
- jmp_rel(ctxt, rel);
+ rc = jmp_rel(ctxt, rel);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
return em_push(ctxt);
}
@@ -2893,11 +2935,12 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt)
static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt)
{
int rc;
+ unsigned long eip;
- ctxt->dst.type = OP_REG;
- ctxt->dst.addr.reg = &ctxt->_eip;
- ctxt->dst.bytes = ctxt->op_bytes;
- rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes);
+ rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+ rc = assign_eip_near(ctxt, eip);
if (rc != X86EMUL_CONTINUE)
return rc;
rsp_increment(ctxt, ctxt->src.val);
@@ -3227,20 +3270,24 @@ static int em_lmsw(struct x86_emulate_ctxt *ctxt)
static int em_loop(struct x86_emulate_ctxt *ctxt)
{
+ int rc = X86EMUL_CONTINUE;
+
register_address_increment(ctxt, reg_rmw(ctxt, VCPU_REGS_RCX), -1);
if ((address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) != 0) &&
(ctxt->b == 0xe2 || test_cc(ctxt->b ^ 0x5, ctxt->eflags)))
- jmp_rel(ctxt, ctxt->src.val);
+ rc = jmp_rel(ctxt, ctxt->src.val);
- return X86EMUL_CONTINUE;
+ return rc;
}
static int em_jcxz(struct x86_emulate_ctxt *ctxt)
{
+ int rc = X86EMUL_CONTINUE;
+
if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0)
- jmp_rel(ctxt, ctxt->src.val);
+ rc = jmp_rel(ctxt, ctxt->src.val);
- return X86EMUL_CONTINUE;
+ return rc;
}
static int em_in(struct x86_emulate_ctxt *ctxt)
@@ -4637,7 +4684,7 @@ special_insn:
break;
case 0x70 ... 0x7f: /* jcc (short) */
if (test_cc(ctxt->b, ctxt->eflags))
- jmp_rel(ctxt, ctxt->src.val);
+ rc = jmp_rel(ctxt, ctxt->src.val);
break;
case 0x8d: /* lea r16/r32, m */
ctxt->dst.val = ctxt->src.addr.mem.ea;
@@ -4666,7 +4713,7 @@ special_insn:
break;
case 0xe9: /* jmp rel */
case 0xeb: /* jmp rel short */
- jmp_rel(ctxt, ctxt->src.val);
+ rc = jmp_rel(ctxt, ctxt->src.val);
ctxt->dst.type = OP_NONE; /* Disable writeback. */
break;
case 0xf4: /* hlt */
@@ -4786,7 +4833,7 @@ twobyte_insn:
break;
case 0x80 ... 0x8f: /* jnz rel, etc*/
if (test_cc(ctxt->b, ctxt->eflags))
- jmp_rel(ctxt, ctxt->src.val);
+ rc = jmp_rel(ctxt, ctxt->src.val);
break;
case 0x90 ... 0x9f: /* setcc r/m8 */
ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags);
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 518d86471b76..298781d4cfb4 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -262,8 +262,10 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
return;
timer = &pit->pit_state.timer;
+ mutex_lock(&pit->pit_state.lock);
if (hrtimer_cancel(timer))
hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+ mutex_unlock(&pit->pit_state.lock);
}
static void destroy_pit_timer(struct kvm_pit *pit)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 945b426c2550..78cfcb348f8a 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3213,7 +3213,7 @@ static int wrmsr_interception(struct vcpu_svm *svm)
msr.host_initiated = false;
svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
- if (svm_set_msr(&svm->vcpu, &msr)) {
+ if (kvm_set_msr(&svm->vcpu, &msr)) {
trace_kvm_msr_write_ex(ecx, data);
kvm_inject_gp(&svm->vcpu, 0);
} else {
@@ -3495,9 +3495,9 @@ static int handle_exit(struct kvm_vcpu *vcpu)
if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
|| !svm_exit_handlers[exit_code]) {
- kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
- kvm_run->hw.hardware_exit_reason = exit_code;
- return 0;
+ WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code);
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
}
return svm_exit_handlers[exit_code](svm);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 8123dc70b443..9ffaf739a86b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2582,12 +2582,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
default:
msr = find_msr_entry(vmx, msr_index);
if (msr) {
+ u64 old_msr_data = msr->data;
msr->data = data;
if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
preempt_disable();
- kvm_set_shared_msr(msr->index, msr->data,
- msr->mask);
+ ret = kvm_set_shared_msr(msr->index, msr->data,
+ msr->mask);
preempt_enable();
+ if (ret)
+ msr->data = old_msr_data;
}
break;
}
@@ -5169,7 +5172,7 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu)
msr.data = data;
msr.index = ecx;
msr.host_initiated = false;
- if (vmx_set_msr(vcpu, &msr) != 0) {
+ if (kvm_set_msr(vcpu, &msr) != 0) {
trace_kvm_msr_write_ex(ecx, data);
kvm_inject_gp(vcpu, 0);
return 1;
@@ -6441,6 +6444,12 @@ static int handle_invept(struct kvm_vcpu *vcpu)
return 1;
}
+static int handle_invvpid(struct kvm_vcpu *vcpu)
+{
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+}
+
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
@@ -6486,6 +6495,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[EXIT_REASON_MWAIT_INSTRUCTION] = handle_invalid_op,
[EXIT_REASON_MONITOR_INSTRUCTION] = handle_invalid_op,
[EXIT_REASON_INVEPT] = handle_invept,
+ [EXIT_REASON_INVVPID] = handle_invvpid,
};
static const int kvm_vmx_max_exit_handlers =
@@ -6719,7 +6729,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD:
case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE:
case EXIT_REASON_VMOFF: case EXIT_REASON_VMON:
- case EXIT_REASON_INVEPT:
+ case EXIT_REASON_INVEPT: case EXIT_REASON_INVVPID:
/*
* VMX instructions trap unconditionally. This allows L1 to
* emulate them for its L2 guest, i.e., allows 3-level nesting!
@@ -6884,10 +6894,10 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
&& kvm_vmx_exit_handlers[exit_reason])
return kvm_vmx_exit_handlers[exit_reason](vcpu);
else {
- vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
- vcpu->run->hw.hardware_exit_reason = exit_reason;
+ WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason);
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
}
- return 0;
}
static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fc39a0cdfd03..aa21c23e010e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -225,20 +225,25 @@ static void kvm_shared_msr_cpu_online(void)
shared_msr_update(i, shared_msrs_global.msrs[i]);
}
-void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
+int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
{
unsigned int cpu = smp_processor_id();
struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+ int err;
if (((value ^ smsr->values[slot].curr) & mask) == 0)
- return;
+ return 0;
smsr->values[slot].curr = value;
- wrmsrl(shared_msrs_global.msrs[slot], value);
+ err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
+ if (err)
+ return 1;
+
if (!smsr->registered) {
smsr->urn.on_user_return = kvm_on_user_return;
user_return_notifier_register(&smsr->urn);
smsr->registered = true;
}
+ return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
@@ -946,7 +951,6 @@ void kvm_enable_efer_bits(u64 mask)
}
EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
-
/*
* Writes msr value into into the appropriate "register".
* Returns 0 on success, non-0 otherwise.
@@ -954,8 +958,34 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
*/
int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
{
+ switch (msr->index) {
+ case MSR_FS_BASE:
+ case MSR_GS_BASE:
+ case MSR_KERNEL_GS_BASE:
+ case MSR_CSTAR:
+ case MSR_LSTAR:
+ if (is_noncanonical_address(msr->data))
+ return 1;
+ break;
+ case MSR_IA32_SYSENTER_EIP:
+ case MSR_IA32_SYSENTER_ESP:
+ /*
+ * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if
+ * non-canonical address is written on Intel but not on
+ * AMD (which ignores the top 32-bits, because it does
+ * not implement 64-bit SYSENTER).
+ *
+ * 64-bit code should hence be able to write a non-canonical
+ * value on AMD. Making the address canonical ensures that
+ * vmentry does not fail on Intel after writing a non-canonical
+ * value, and that something deterministic happens if the guest
+ * invokes 64-bit SYSENTER.
+ */
+ msr->data = get_canonical(msr->data);
+ }
return kvm_x86_ops->set_msr(vcpu, msr);
}
+EXPORT_SYMBOL_GPL(kvm_set_msr);
/*
* Adapt set_msr() to msr_io()'s calling convention
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a3488689e301..fed892de9baf 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -405,7 +405,7 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr)
psize = page_level_size(level);
pmask = page_level_mask(level);
offset = virt_addr & ~pmask;
- phys_addr = pte_pfn(*pte) << PAGE_SHIFT;
+ phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
return (phys_addr | offset);
}
EXPORT_SYMBOL_GPL(slow_virt_to_phys);