aboutsummaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/alpha/kernel/sys_sio.c35
-rw-r--r--arch/alpha/lib/ev6-memset.S12
-rw-r--r--arch/arm/boot/dts/da850-lcdk.dts4
-rw-r--r--arch/arm/boot/dts/kirkwood-openblocks_a7.dts10
-rw-r--r--arch/arm/boot/dts/sun4i-a10.dtsi2
-rw-r--r--arch/arm/boot/dts/sun7i-a20.dtsi2
-rw-r--r--arch/arm/configs/sunxi_defconfig2
-rw-r--r--arch/arm/net/bpf_jit_32.c225
-rw-r--r--arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi1
-rw-r--r--arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi13
-rw-r--r--arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi9
-rw-r--r--arch/arm64/kvm/handle_exit.c4
-rw-r--r--arch/arm64/net/bpf_jit_comp.c20
-rw-r--r--arch/ia64/include/asm/atomic.h37
-rw-r--r--arch/mips/Kconfig12
-rw-r--r--arch/mips/Kconfig.debug14
-rw-r--r--arch/mips/ar7/platform.c2
-rw-r--r--arch/mips/ath25/devices.c2
-rw-r--r--arch/mips/kernel/mips-cm.c1
-rw-r--r--arch/mips/lib/Makefile3
-rw-r--r--arch/mips/lib/libgcc.h17
-rw-r--r--arch/mips/lib/multi3.c54
-rw-r--r--arch/mips/mm/uasm-micromips.c2
-rw-r--r--arch/mips/ralink/timer.c4
-rw-r--r--arch/mips/rb532/Makefile4
-rw-r--r--arch/mips/rb532/devices.c4
-rw-r--r--arch/powerpc/Kconfig1
-rw-r--r--arch/powerpc/include/asm/hvcall.h1
-rw-r--r--arch/powerpc/include/uapi/asm/kvm.h25
-rw-r--r--arch/powerpc/kernel/setup-common.c11
-rw-r--r--arch/powerpc/kernel/setup_64.c38
-rw-r--r--arch/powerpc/kvm/powerpc.c131
-rw-r--r--arch/powerpc/xmon/xmon.c26
-rw-r--r--arch/s390/include/asm/kvm_host.h3
-rw-r--r--arch/s390/include/uapi/asm/kvm.h5
-rw-r--r--arch/s390/kvm/kvm-s390.c12
-rw-r--r--arch/s390/kvm/vsie.c10
-rw-r--r--arch/x86/kvm/x86.c4
-rw-r--r--arch/x86/mm/mem_encrypt.c2
39 files changed, 556 insertions, 208 deletions
diff --git a/arch/alpha/kernel/sys_sio.c b/arch/alpha/kernel/sys_sio.c
index 37bd6d9b8eb9..a6bdc1da47ad 100644
--- a/arch/alpha/kernel/sys_sio.c
+++ b/arch/alpha/kernel/sys_sio.c
@@ -102,6 +102,15 @@ sio_pci_route(void)
alpha_mv.sys.sio.route_tab);
}
+static bool sio_pci_dev_irq_needs_level(const struct pci_dev *dev)
+{
+ if ((dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) &&
+ (dev->class >> 8 != PCI_CLASS_BRIDGE_PCMCIA))
+ return false;
+
+ return true;
+}
+
static unsigned int __init
sio_collect_irq_levels(void)
{
@@ -110,8 +119,7 @@ sio_collect_irq_levels(void)
/* Iterate through the devices, collecting IRQ levels. */
for_each_pci_dev(dev) {
- if ((dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) &&
- (dev->class >> 8 != PCI_CLASS_BRIDGE_PCMCIA))
+ if (!sio_pci_dev_irq_needs_level(dev))
continue;
if (dev->irq)
@@ -120,8 +128,7 @@ sio_collect_irq_levels(void)
return level_bits;
}
-static void __init
-sio_fixup_irq_levels(unsigned int level_bits)
+static void __sio_fixup_irq_levels(unsigned int level_bits, bool reset)
{
unsigned int old_level_bits;
@@ -139,12 +146,21 @@ sio_fixup_irq_levels(unsigned int level_bits)
*/
old_level_bits = inb(0x4d0) | (inb(0x4d1) << 8);
- level_bits |= (old_level_bits & 0x71ff);
+ if (reset)
+ old_level_bits &= 0x71ff;
+
+ level_bits |= old_level_bits;
outb((level_bits >> 0) & 0xff, 0x4d0);
outb((level_bits >> 8) & 0xff, 0x4d1);
}
+static inline void
+sio_fixup_irq_levels(unsigned int level_bits)
+{
+ __sio_fixup_irq_levels(level_bits, true);
+}
+
static inline int
noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
@@ -181,7 +197,14 @@ noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
const long min_idsel = 6, max_idsel = 14, irqs_per_slot = 5;
int irq = COMMON_TABLE_LOOKUP, tmp;
tmp = __kernel_extbl(alpha_mv.sys.sio.route_tab, irq);
- return irq >= 0 ? tmp : -1;
+
+ irq = irq >= 0 ? tmp : -1;
+
+ /* Fixup IRQ level if an actual IRQ mapping is detected */
+ if (sio_pci_dev_irq_needs_level(dev) && irq >= 0)
+ __sio_fixup_irq_levels(1 << irq, false);
+
+ return irq;
}
static inline int
diff --git a/arch/alpha/lib/ev6-memset.S b/arch/alpha/lib/ev6-memset.S
index 316a99aa9efe..1cfcfbbea6f0 100644
--- a/arch/alpha/lib/ev6-memset.S
+++ b/arch/alpha/lib/ev6-memset.S
@@ -18,7 +18,7 @@
* The algorithm for the leading and trailing quadwords remains the same,
* however the loop has been unrolled to enable better memory throughput,
* and the code has been replicated for each of the entry points: __memset
- * and __memsetw to permit better scheduling to eliminate the stalling
+ * and __memset16 to permit better scheduling to eliminate the stalling
* encountered during the mask replication.
* A future enhancement might be to put in a byte store loop for really
* small (say < 32 bytes) memset()s. Whether or not that change would be
@@ -34,7 +34,7 @@
.globl memset
.globl __memset
.globl ___memset
- .globl __memsetw
+ .globl __memset16
.globl __constant_c_memset
.ent ___memset
@@ -415,9 +415,9 @@ end:
* to mask stalls. Note that entry point names also had to change
*/
.align 5
- .ent __memsetw
+ .ent __memset16
-__memsetw:
+__memset16:
.frame $30,0,$26,0
.prologue 0
@@ -596,8 +596,8 @@ end_w:
nop
ret $31,($26),1 # L0 :
- .end __memsetw
- EXPORT_SYMBOL(__memsetw)
+ .end __memset16
+ EXPORT_SYMBOL(__memset16)
memset = ___memset
__memset = ___memset
diff --git a/arch/arm/boot/dts/da850-lcdk.dts b/arch/arm/boot/dts/da850-lcdk.dts
index eed89e659143..a1f4d6d5a569 100644
--- a/arch/arm/boot/dts/da850-lcdk.dts
+++ b/arch/arm/boot/dts/da850-lcdk.dts
@@ -293,12 +293,12 @@
label = "u-boot env";
reg = <0 0x020000>;
};
- partition@0x020000 {
+ partition@20000 {
/* The LCDK defaults to booting from this partition */
label = "u-boot";
reg = <0x020000 0x080000>;
};
- partition@0x0a0000 {
+ partition@a0000 {
label = "free space";
reg = <0x0a0000 0>;
};
diff --git a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
index cf2f5240e176..27cc913ca0f5 100644
--- a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
+++ b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
@@ -53,7 +53,8 @@
};
pinctrl: pin-controller@10000 {
- pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header>;
+ pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header
+ &pmx_gpio_header_gpo>;
pinctrl-names = "default";
pmx_uart0: pmx-uart0 {
@@ -85,11 +86,16 @@
* ground.
*/
pmx_gpio_header: pmx-gpio-header {
- marvell,pins = "mpp17", "mpp7", "mpp29", "mpp28",
+ marvell,pins = "mpp17", "mpp29", "mpp28",
"mpp35", "mpp34", "mpp40";
marvell,function = "gpio";
};
+ pmx_gpio_header_gpo: pxm-gpio-header-gpo {
+ marvell,pins = "mpp7";
+ marvell,function = "gpo";
+ };
+
pmx_gpio_init: pmx-init {
marvell,pins = "mpp38";
marvell,function = "gpio";
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 5840f5c75c3b..4f2f2eea0755 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -1104,7 +1104,7 @@
be1_out_tcon0: endpoint@0 {
reg = <0>;
- remote-endpoint = <&tcon1_in_be0>;
+ remote-endpoint = <&tcon0_in_be1>;
};
be1_out_tcon1: endpoint@1 {
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 59655e42e4b0..bd0cd3204273 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -1354,7 +1354,7 @@
be1_out_tcon0: endpoint@0 {
reg = <0>;
- remote-endpoint = <&tcon1_in_be0>;
+ remote-endpoint = <&tcon0_in_be1>;
};
be1_out_tcon1: endpoint@1 {
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index 5caaf971fb50..df433abfcb02 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -10,6 +10,7 @@ CONFIG_SMP=y
CONFIG_NR_CPUS=8
CONFIG_AEABI=y
CONFIG_HIGHMEM=y
+CONFIG_CMA=y
CONFIG_ARM_APPENDED_DTB=y
CONFIG_ARM_ATAG_DTB_COMPAT=y
CONFIG_CPU_FREQ=y
@@ -33,6 +34,7 @@ CONFIG_CAN_SUN4I=y
# CONFIG_WIRELESS is not set
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_DMA_CMA=y
CONFIG_BLK_DEV_SD=y
CONFIG_ATA=y
CONFIG_AHCI_SUNXI=y
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index c199990e12b6..323a4df59a6c 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -27,14 +27,58 @@
int bpf_jit_enable __read_mostly;
+/*
+ * eBPF prog stack layout:
+ *
+ * high
+ * original ARM_SP => +-----+
+ * | | callee saved registers
+ * +-----+ <= (BPF_FP + SCRATCH_SIZE)
+ * | ... | eBPF JIT scratch space
+ * eBPF fp register => +-----+
+ * (BPF_FP) | ... | eBPF prog stack
+ * +-----+
+ * |RSVD | JIT scratchpad
+ * current ARM_SP => +-----+ <= (BPF_FP - STACK_SIZE + SCRATCH_SIZE)
+ * | |
+ * | ... | Function call stack
+ * | |
+ * +-----+
+ * low
+ *
+ * The callee saved registers depends on whether frame pointers are enabled.
+ * With frame pointers (to be compliant with the ABI):
+ *
+ * high
+ * original ARM_SP => +------------------+ \
+ * | pc | |
+ * current ARM_FP => +------------------+ } callee saved registers
+ * |r4-r8,r10,fp,ip,lr| |
+ * +------------------+ /
+ * low
+ *
+ * Without frame pointers:
+ *
+ * high
+ * original ARM_SP => +------------------+
+ * | r4-r8,r10,fp,lr | callee saved registers
+ * current ARM_FP => +------------------+
+ * low
+ *
+ * When popping registers off the stack at the end of a BPF function, we
+ * reference them via the current ARM_FP register.
+ */
+#define CALLEE_MASK (1 << ARM_R4 | 1 << ARM_R5 | 1 << ARM_R6 | \
+ 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R10 | \
+ 1 << ARM_FP)
+#define CALLEE_PUSH_MASK (CALLEE_MASK | 1 << ARM_LR)
+#define CALLEE_POP_MASK (CALLEE_MASK | 1 << ARM_PC)
+
#define STACK_OFFSET(k) (k)
#define TMP_REG_1 (MAX_BPF_JIT_REG + 0) /* TEMP Register 1 */
#define TMP_REG_2 (MAX_BPF_JIT_REG + 1) /* TEMP Register 2 */
#define TCALL_CNT (MAX_BPF_JIT_REG + 2) /* Tail Call Count */
-/* Flags used for JIT optimization */
-#define SEEN_CALL (1 << 0)
-
#define FLAG_IMM_OVERFLOW (1 << 0)
/*
@@ -95,7 +139,6 @@ static const u8 bpf2a32[][2] = {
* idx : index of current last JITed instruction.
* prologue_bytes : bytes used in prologue.
* epilogue_offset : offset of epilogue starting.
- * seen : bit mask used for JIT optimization.
* offsets : array of eBPF instruction offsets in
* JITed code.
* target : final JITed code.
@@ -110,7 +153,6 @@ struct jit_ctx {
unsigned int idx;
unsigned int prologue_bytes;
unsigned int epilogue_offset;
- u32 seen;
u32 flags;
u32 *offsets;
u32 *target;
@@ -179,8 +221,13 @@ static void jit_fill_hole(void *area, unsigned int size)
*ptr++ = __opcode_to_mem_arm(ARM_INST_UDF);
}
-/* Stack must be multiples of 16 Bytes */
-#define STACK_ALIGN(sz) (((sz) + 3) & ~3)
+#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5)
+/* EABI requires the stack to be aligned to 64-bit boundaries */
+#define STACK_ALIGNMENT 8
+#else
+/* Stack must be aligned to 32-bit boundaries */
+#define STACK_ALIGNMENT 4
+#endif
/* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4,
* BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9,
@@ -194,7 +241,7 @@ static void jit_fill_hole(void *area, unsigned int size)
+ SCRATCH_SIZE + \
+ 4 /* extra for skb_copy_bits buffer */)
-#define STACK_SIZE STACK_ALIGN(_STACK_SIZE)
+#define STACK_SIZE ALIGN(_STACK_SIZE, STACK_ALIGNMENT)
/* Get the offset of eBPF REGISTERs stored on scratch space. */
#define STACK_VAR(off) (STACK_SIZE-off-4)
@@ -285,16 +332,19 @@ static inline void emit_mov_i(const u8 rd, u32 val, struct jit_ctx *ctx)
emit_mov_i_no8m(rd, val, ctx);
}
-static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
+static void emit_bx_r(u8 tgt_reg, struct jit_ctx *ctx)
{
- ctx->seen |= SEEN_CALL;
-#if __LINUX_ARM_ARCH__ < 5
- emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx);
-
if (elf_hwcap & HWCAP_THUMB)
emit(ARM_BX(tgt_reg), ctx);
else
emit(ARM_MOV_R(ARM_PC, tgt_reg), ctx);
+}
+
+static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ < 5
+ emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx);
+ emit_bx_r(tgt_reg, ctx);
#else
emit(ARM_BLX_R(tgt_reg), ctx);
#endif
@@ -354,7 +404,6 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
}
/* Call appropriate function */
- ctx->seen |= SEEN_CALL;
emit_mov_i(ARM_IP, op == BPF_DIV ?
(u32)jit_udiv32 : (u32)jit_mod32, ctx);
emit_blx_r(ARM_IP, ctx);
@@ -620,8 +669,6 @@ static inline void emit_a32_lsh_r64(const u8 dst[], const u8 src[], bool dstk,
/* Do LSH operation */
emit(ARM_SUB_I(ARM_IP, rt, 32), ctx);
emit(ARM_RSB_I(tmp2[0], rt, 32), ctx);
- /* As we are using ARM_LR */
- ctx->seen |= SEEN_CALL;
emit(ARM_MOV_SR(ARM_LR, rm, SRTYPE_ASL, rt), ctx);
emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd, SRTYPE_ASL, ARM_IP), ctx);
emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd, SRTYPE_LSR, tmp2[0]), ctx);
@@ -656,8 +703,6 @@ static inline void emit_a32_arsh_r64(const u8 dst[], const u8 src[], bool dstk,
/* Do the ARSH operation */
emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
- /* As we are using ARM_LR */
- ctx->seen |= SEEN_CALL;
emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
_emit(ARM_COND_MI, ARM_B(0), ctx);
@@ -692,8 +737,6 @@ static inline void emit_a32_lsr_r64(const u8 dst[], const u8 src[], bool dstk,
/* Do LSH operation */
emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
- /* As we are using ARM_LR */
- ctx->seen |= SEEN_CALL;
emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_LSR, tmp2[0]), ctx);
@@ -828,8 +871,6 @@ static inline void emit_a32_mul_r64(const u8 dst[], const u8 src[], bool dstk,
/* Do Multiplication */
emit(ARM_MUL(ARM_IP, rd, rn), ctx);
emit(ARM_MUL(ARM_LR, rm, rt), ctx);
- /* As we are using ARM_LR */
- ctx->seen |= SEEN_CALL;
emit(ARM_ADD_R(ARM_LR, ARM_IP, ARM_LR), ctx);
emit(ARM_UMULL(ARM_IP, rm, rd, rt), ctx);
@@ -872,33 +913,53 @@ static inline void emit_str_r(const u8 dst, const u8 src, bool dstk,
}
/* dst = *(size*)(src + off) */
-static inline void emit_ldx_r(const u8 dst, const u8 src, bool dstk,
- const s32 off, struct jit_ctx *ctx, const u8 sz){
+static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk,
+ s32 off, struct jit_ctx *ctx, const u8 sz){
const u8 *tmp = bpf2a32[TMP_REG_1];
- u8 rd = dstk ? tmp[1] : dst;
+ const u8 *rd = dstk ? tmp : dst;
u8 rm = src;
+ s32 off_max;
- if (off) {
+ if (sz == BPF_H)
+ off_max = 0xff;
+ else
+ off_max = 0xfff;
+
+ if (off < 0 || off > off_max) {
emit_a32_mov_i(tmp[0], off, false, ctx);
emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx);
rm = tmp[0];
+ off = 0;
+ } else if (rd[1] == rm) {
+ emit(ARM_MOV_R(tmp[0], rm), ctx);
+ rm = tmp[0];
}
switch (sz) {
- case BPF_W:
- /* Load a Word */
- emit(ARM_LDR_I(rd, rm, 0), ctx);
+ case BPF_B:
+ /* Load a Byte */
+ emit(ARM_LDRB_I(rd[1], rm, off), ctx);
+ emit_a32_mov_i(dst[0], 0, dstk, ctx);
break;
case BPF_H:
/* Load a HalfWord */
- emit(ARM_LDRH_I(rd, rm, 0), ctx);
+ emit(ARM_LDRH_I(rd[1], rm, off), ctx);
+ emit_a32_mov_i(dst[0], 0, dstk, ctx);
break;
- case BPF_B:
- /* Load a Byte */
- emit(ARM_LDRB_I(rd, rm, 0), ctx);
+ case BPF_W:
+ /* Load a Word */
+ emit(ARM_LDR_I(rd[1], rm, off), ctx);
+ emit_a32_mov_i(dst[0], 0, dstk, ctx);
+ break;
+ case BPF_DW:
+ /* Load a Double Word */
+ emit(ARM_LDR_I(rd[1], rm, off), ctx);
+ emit(ARM_LDR_I(rd[0], rm, off + 4), ctx);
break;
}
if (dstk)
- emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+ emit(ARM_STR_I(rd[1], ARM_SP, STACK_VAR(dst[1])), ctx);
+ if (dstk && sz == BPF_DW)
+ emit(ARM_STR_I(rd[0], ARM_SP, STACK_VAR(dst[0])), ctx);
}
/* Arithmatic Operation */
@@ -906,7 +967,6 @@ static inline void emit_ar_r(const u8 rd, const u8 rt, const u8 rm,
const u8 rn, struct jit_ctx *ctx, u8 op) {
switch (op) {
case BPF_JSET:
- ctx->seen |= SEEN_CALL;
emit(ARM_AND_R(ARM_IP, rt, rn), ctx);
emit(ARM_AND_R(ARM_LR, rd, rm), ctx);
emit(ARM_ORRS_R(ARM_IP, ARM_LR, ARM_IP), ctx);
@@ -945,7 +1005,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
const u8 *tcc = bpf2a32[TCALL_CNT];
const int idx0 = ctx->idx;
#define cur_offset (ctx->idx - idx0)
-#define jmp_offset (out_offset - (cur_offset))
+#define jmp_offset (out_offset - (cur_offset) - 2)
u32 off, lo, hi;
/* if (index >= array->map.max_entries)
@@ -956,7 +1016,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
emit_a32_mov_i(tmp[1], off, false, ctx);
emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx);
emit(ARM_LDR_R(tmp[1], tmp2[1], tmp[1]), ctx);
- /* index (64 bit) */
+ /* index is 32-bit for arrays */
emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx);
/* index >= array->map.max_entries */
emit(ARM_CMP_R(tmp2[1], tmp[1]), ctx);
@@ -997,7 +1057,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
emit_a32_mov_i(tmp2[1], off, false, ctx);
emit(ARM_LDR_R(tmp[1], tmp[1], tmp2[1]), ctx);
emit(ARM_ADD_I(tmp[1], tmp[1], ctx->prologue_bytes), ctx);
- emit(ARM_BX(tmp[1]), ctx);
+ emit_bx_r(tmp[1], ctx);
/* out: */
if (out_offset == -1)
@@ -1070,54 +1130,22 @@ static void build_prologue(struct jit_ctx *ctx)
const u8 r2 = bpf2a32[BPF_REG_1][1];
const u8 r3 = bpf2a32[BPF_REG_1][0];
const u8 r4 = bpf2a32[BPF_REG_6][1];
- const u8 r5 = bpf2a32[BPF_REG_6][0];
- const u8 r6 = bpf2a32[TMP_REG_1][1];
- const u8 r7 = bpf2a32[TMP_REG_1][0];
- const u8 r8 = bpf2a32[TMP_REG_2][1];
- const u8 r10 = bpf2a32[TMP_REG_2][0];
const u8 fplo = bpf2a32[BPF_REG_FP][1];
const u8 fphi = bpf2a32[BPF_REG_FP][0];
- const u8 sp = ARM_SP;
const u8 *tcc = bpf2a32[TCALL_CNT];
- u16 reg_set = 0;
-
- /*
- * eBPF prog stack layout
- *
- * high
- * original ARM_SP => +-----+ eBPF prologue
- * |FP/LR|
- * current ARM_FP => +-----+
- * | ... | callee saved registers
- * eBPF fp register => +-----+ <= (BPF_FP)
- * | ... | eBPF JIT scratch space
- * | | eBPF prog stack
- * +-----+
- * |RSVD | JIT scratchpad
- * current A64_SP => +-----+ <= (BPF_FP - STACK_SIZE)
- * | |
- * | ... | Function call stack
- * | |
- * +-----+
- * low
- */
-
/* Save callee saved registers. */
- reg_set |= (1<<r4) | (1<<r5) | (1<<r6) | (1<<r7) | (1<<r8) | (1<<r10);
#ifdef CONFIG_FRAME_POINTER
- reg_set |= (1<<ARM_FP) | (1<<ARM_IP) | (1<<ARM_LR) | (1<<ARM_PC);
- emit(ARM_MOV_R(ARM_IP, sp), ctx);
+ u16 reg_set = CALLEE_PUSH_MASK | 1 << ARM_IP | 1 << ARM_PC;
+ emit(ARM_MOV_R(ARM_IP, ARM_SP), ctx);
emit(ARM_PUSH(reg_set), ctx);
emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx);
#else
- /* Check if call instruction exists in BPF body */
- if (ctx->seen & SEEN_CALL)
- reg_set |= (1<<ARM_LR);
- emit(ARM_PUSH(reg_set), ctx);
+ emit(ARM_PUSH(CALLEE_PUSH_MASK), ctx);
+ emit(ARM_MOV_R(ARM_FP, ARM_SP), ctx);
#endif
/* Save frame pointer for later */
- emit(ARM_SUB_I(ARM_IP, sp, SCRATCH_SIZE), ctx);
+ emit(ARM_SUB_I(ARM_IP, ARM_SP, SCRATCH_SIZE), ctx);
ctx->stack_size = imm8m(STACK_SIZE);
@@ -1140,33 +1168,19 @@ static void build_prologue(struct jit_ctx *ctx)
/* end of prologue */
}
+/* restore callee saved registers. */
static void build_epilogue(struct jit_ctx *ctx)
{
- const u8 r4 = bpf2a32[BPF_REG_6][1];
- const u8 r5 = bpf2a32[BPF_REG_6][0];
- const u8 r6 = bpf2a32[TMP_REG_1][1];
- const u8 r7 = bpf2a32[TMP_REG_1][0];
- const u8 r8 = bpf2a32[TMP_REG_2][1];
- const u8 r10 = bpf2a32[TMP_REG_2][0];
- u16 reg_set = 0;
-
- /* unwind function call stack */
- emit(ARM_ADD_I(ARM_SP, ARM_SP, ctx->stack_size), ctx);
-
- /* restore callee saved registers. */
- reg_set |= (1<<r4) | (1<<r5) | (1<<r6) | (1<<r7) | (1<<r8) | (1<<r10);
#ifdef CONFIG_FRAME_POINTER
- /* the first instruction of the prologue was: mov ip, sp */
- reg_set |= (1<<ARM_FP) | (1<<ARM_SP) | (1<<ARM_PC);
+ /* When using frame pointers, some additional registers need to
+ * be loaded. */
+ u16 reg_set = CALLEE_POP_MASK | 1 << ARM_SP;
+ emit(ARM_SUB_I(ARM_SP, ARM_FP, hweight16(reg_set) * 4), ctx);
emit(ARM_LDM(ARM_SP, reg_set), ctx);
#else
- if (ctx->seen & SEEN_CALL)
- reg_set |= (1<<ARM_PC);
/* Restore callee saved registers. */
- emit(ARM_POP(reg_set), ctx);
- /* Return back to the callee function */
- if (!(ctx->seen & SEEN_CALL))
- emit(ARM_BX(ARM_LR), ctx);
+ emit(ARM_MOV_R(ARM_SP, ARM_FP), ctx);
+ emit(ARM_POP(CALLEE_POP_MASK), ctx);
#endif
}
@@ -1394,8 +1408,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
emit_rev32(rt, rt, ctx);
goto emit_bswap_uxt;
case 64:
- /* Because of the usage of ARM_LR */
- ctx->seen |= SEEN_CALL;
emit_rev32(ARM_LR, rt, ctx);
emit_rev32(rt, rd, ctx);
emit(ARM_MOV_R(rd, ARM_LR), ctx);
@@ -1448,22 +1460,7 @@ exit:
rn = sstk ? tmp2[1] : src_lo;
if (sstk)
emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
- switch (BPF_SIZE(code)) {
- case BPF_W:
- /* Load a Word */
- case BPF_H:
- /* Load a Half-Word */
- case BPF_B:
- /* Load a Byte */
- emit_ldx_r(dst_lo, rn, dstk, off, ctx, BPF_SIZE(code));
- emit_a32_mov_i(dst_hi, 0, dstk, ctx);
- break;
- case BPF_DW:
- /* Load a double word */
- emit_ldx_r(dst_lo, rn, dstk, off, ctx, BPF_W);
- emit_ldx_r(dst_hi, rn, dstk, off+4, ctx, BPF_W);
- break;
- }
+ emit_ldx_r(dst, rn, dstk, off, ctx, BPF_SIZE(code));
break;
/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
case BPF_LD | BPF_ABS | BPF_W:
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index 7c9bdc7ab50b..9db19314c60c 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -66,6 +66,7 @@
<&cpu1>,
<&cpu2>,
<&cpu3>;
+ interrupt-parent = <&intc>;
};
psci {
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
index e3b64d03fbd8..9c7724e82aff 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
@@ -63,8 +63,10 @@
cpm_ethernet: ethernet@0 {
compatible = "marvell,armada-7k-pp22";
reg = <0x0 0x100000>, <0x129000 0xb000>;
- clocks = <&cpm_clk 1 3>, <&cpm_clk 1 9>, <&cpm_clk 1 5>;
- clock-names = "pp_clk", "gop_clk", "mg_clk";
+ clocks = <&cpm_clk 1 3>, <&cpm_clk 1 9>,
+ <&cpm_clk 1 5>, <&cpm_clk 1 18>;
+ clock-names = "pp_clk", "gop_clk",
+ "mg_clk","axi_clk";
marvell,system-controller = <&cpm_syscon0>;
status = "disabled";
dma-coherent;
@@ -155,7 +157,8 @@
#size-cells = <0>;
compatible = "marvell,orion-mdio";
reg = <0x12a200 0x10>;
- clocks = <&cpm_clk 1 9>, <&cpm_clk 1 5>;
+ clocks = <&cpm_clk 1 9>, <&cpm_clk 1 5>,
+ <&cpm_clk 1 6>, <&cpm_clk 1 18>;
status = "disabled";
};
@@ -338,8 +341,8 @@
compatible = "marvell,armada-cp110-sdhci";
reg = <0x780000 0x300>;
interrupts = <ICU_GRP_NSR 27 IRQ_TYPE_LEVEL_HIGH>;
- clock-names = "core";
- clocks = <&cpm_clk 1 4>;
+ clock-names = "core","axi";
+ clocks = <&cpm_clk 1 4>, <&cpm_clk 1 18>;
dma-coherent;
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
index 0d51096c69f8..87ac68b2cf37 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
@@ -63,8 +63,10 @@
cps_ethernet: ethernet@0 {
compatible = "marvell,armada-7k-pp22";
reg = <0x0 0x100000>, <0x129000 0xb000>;
- clocks = <&cps_clk 1 3>, <&cps_clk 1 9>, <&cps_clk 1 5>;
- clock-names = "pp_clk", "gop_clk", "mg_clk";
+ clocks = <&cps_clk 1 3>, <&cps_clk 1 9>,
+ <&cps_clk 1 5>, <&cps_clk 1 18>;
+ clock-names = "pp_clk", "gop_clk",
+ "mg_clk", "axi_clk";
marvell,system-controller = <&cps_syscon0>;
status = "disabled";
dma-coherent;
@@ -155,7 +157,8 @@
#size-cells = <0>;
compatible = "marvell,orion-mdio";
reg = <0x12a200 0x10>;
- clocks = <&cps_clk 1 9>, <&cps_clk 1 5>;
+ clocks = <&cps_clk 1 9>, <&cps_clk 1 5>,
+ <&cps_clk 1 6>, <&cps_clk 1 18>;
status = "disabled";
};
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 304203fa9e33..e60494f1eef9 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -45,7 +45,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
ret = kvm_psci_call(vcpu);
if (ret < 0) {
- kvm_inject_undefined(vcpu);
+ vcpu_set_reg(vcpu, 0, ~0UL);
return 1;
}
@@ -54,7 +54,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
- kvm_inject_undefined(vcpu);
+ vcpu_set_reg(vcpu, 0, ~0UL);
return 1;
}
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index ba38d403abb2..bb32f7f6dd0f 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -148,7 +148,8 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
/* Stack must be multiples of 16B */
#define STACK_ALIGN(sz) (((sz) + 15) & ~15)
-#define PROLOGUE_OFFSET 8
+/* Tail call offset to jump into */
+#define PROLOGUE_OFFSET 7
static int build_prologue(struct jit_ctx *ctx)
{
@@ -200,19 +201,19 @@ static int build_prologue(struct jit_ctx *ctx)
/* Initialize tail_call_cnt */
emit(A64_MOVZ(1, tcc, 0, 0), ctx);
- /* 4 byte extra for skb_copy_bits buffer */
- ctx->stack_size = prog->aux->stack_depth + 4;
- ctx->stack_size = STACK_ALIGN(ctx->stack_size);
-
- /* Set up function call stack */
- emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
-
cur_offset = ctx->idx - idx0;
if (cur_offset != PROLOGUE_OFFSET) {
pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
cur_offset, PROLOGUE_OFFSET);
return -1;
}
+
+ /* 4 byte extra for skb_copy_bits buffer */
+ ctx->stack_size = prog->aux->stack_depth + 4;
+ ctx->stack_size = STACK_ALIGN(ctx->stack_size);
+
+ /* Set up function call stack */
+ emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
return 0;
}
@@ -260,11 +261,12 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
emit(A64_LDR64(prg, tmp, prg), ctx);
emit(A64_CBZ(1, prg, jmp_offset), ctx);
- /* goto *(prog->bpf_func + prologue_size); */
+ /* goto *(prog->bpf_func + prologue_offset); */
off = offsetof(struct bpf_prog, bpf_func);
emit_a64_mov_i64(tmp, off, ctx);
emit(A64_LDR64(tmp, prg, tmp), ctx);
emit(A64_ADD_I(1, tmp, tmp, sizeof(u32) * PROLOGUE_OFFSET), ctx);
+ emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
emit(A64_BR(tmp), ctx);
/* out: */
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 28e02c99be6d..762eeb0fcc1d 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -65,29 +65,30 @@ ia64_atomic_fetch_##op (int i, atomic_t *v) \
ATOMIC_OPS(add, +)
ATOMIC_OPS(sub, -)
-#define atomic_add_return(i,v) \
+#ifdef __OPTIMIZE__
+#define __ia64_atomic_const(i) __builtin_constant_p(i) ? \
+ ((i) == 1 || (i) == 4 || (i) == 8 || (i) == 16 || \
+ (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0
+
+#define atomic_add_return(i, v) \
({ \
- int __ia64_aar_i = (i); \
- (__builtin_constant_p(i) \
- && ( (__ia64_aar_i == 1) || (__ia64_aar_i == 4) \
- || (__ia64_aar_i == 8) || (__ia64_aar_i == 16) \
- || (__ia64_aar_i == -1) || (__ia64_aar_i == -4) \
- || (__ia64_aar_i == -8) || (__ia64_aar_i == -16))) \
- ? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter) \
- : ia64_atomic_add(__ia64_aar_i, v); \
+ int __i = (i); \
+ static const int __ia64_atomic_p = __ia64_atomic_const(i); \
+ __ia64_atomic_p ? ia64_fetch_and_add(__i, &(v)->counter) : \
+ ia64_atomic_add(__i, v); \
})
-#define atomic_sub_return(i,v) \
+#define atomic_sub_return(i, v) \
({ \
- int __ia64_asr_i = (i); \
- (__builtin_constant_p(i) \
- && ( (__ia64_asr_i == 1) || (__ia64_asr_i == 4) \
- || (__ia64_asr_i == 8) || (__ia64_asr_i == 16) \
- || (__ia64_asr_i == -1) || (__ia64_asr_i == -4) \
- || (__ia64_asr_i == -8) || (__ia64_asr_i == -16))) \
- ? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter) \
- : ia64_atomic_sub(__ia64_asr_i, v); \
+ int __i = (i); \
+ static const int __ia64_atomic_p = __ia64_atomic_const(i); \
+ __ia64_atomic_p ? ia64_fetch_and_add(-__i, &(v)->counter) : \
+ ia64_atomic_sub(__i, v); \
})
+#else
+#define atomic_add_return(i, v) ia64_atomic_add(i, v)
+#define atomic_sub_return(i, v) ia64_atomic_sub(i, v)
+#endif
#define atomic_fetch_add(i,v) \
({ \
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 350a990fc719..8e0b3702f1c0 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -259,6 +259,7 @@ config BCM47XX
select LEDS_GPIO_REGISTER
select BCM47XX_NVRAM
select BCM47XX_SPROM
+ select BCM47XX_SSB if !BCM47XX_BCMA
help
Support for BCM47XX based boards
@@ -389,6 +390,7 @@ config LANTIQ
select SYS_SUPPORTS_32BIT_KERNEL
select SYS_SUPPORTS_MIPS16
select SYS_SUPPORTS_MULTITHREADING
+ select SYS_SUPPORTS_VPE_LOADER
select SYS_HAS_EARLY_PRINTK
select GPIOLIB
select SWAP_IO_SPACE
@@ -516,6 +518,7 @@ config MIPS_MALTA
select SYS_SUPPORTS_MIPS16
select SYS_SUPPORTS_MULTITHREADING
select SYS_SUPPORTS_SMARTMIPS
+ select SYS_SUPPORTS_VPE_LOADER
select SYS_SUPPORTS_ZBOOT
select SYS_SUPPORTS_RELOCATABLE
select USE_OF
@@ -2281,9 +2284,16 @@ config MIPSR2_TO_R6_EMULATOR
The only reason this is a build-time option is to save ~14K from the
final kernel image.
+config SYS_SUPPORTS_VPE_LOADER
+ bool
+ depends on SYS_SUPPORTS_MULTITHREADING
+ help
+ Indicates that the platform supports the VPE loader, and provides
+ physical_memsize.
+
config MIPS_VPE_LOADER
bool "VPE loader support."
- depends on SYS_SUPPORTS_MULTITHREADING && MODULES
+ depends on SYS_SUPPORTS_VPE_LOADER && MODULES
select CPU_MIPSR2_IRQ_VI
select CPU_MIPSR2_IRQ_EI
select MIPS_MT
diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug
index 464af5e025d6..0749c3724543 100644
--- a/arch/mips/Kconfig.debug
+++ b/arch/mips/Kconfig.debug
@@ -124,30 +124,36 @@ config SCACHE_DEBUGFS
If unsure, say N.
-menuconfig MIPS_CPS_NS16550
+menuconfig MIPS_CPS_NS16550_BOOL
bool "CPS SMP NS16550 UART output"
depends on MIPS_CPS
help
Output debug information via an ns16550 compatible UART if exceptions
occur early in the boot process of a secondary core.
-if MIPS_CPS_NS16550
+if MIPS_CPS_NS16550_BOOL
+
+config MIPS_CPS_NS16550
+ def_bool MIPS_CPS_NS16550_BASE != 0
config MIPS_CPS_NS16550_BASE
hex "UART Base Address"
default 0x1b0003f8 if MIPS_MALTA
+ default 0
help
The base address of the ns16550 compatible UART on which to output
debug information from the early stages of core startup.
+ This is only used if non-zero.
+
config MIPS_CPS_NS16550_SHIFT
int "UART Register Shift"
- default 0 if MIPS_MALTA
+ default 0
help
The number of bits to shift ns16550 register indices by in order to
form their addresses. That is, log base 2 of the span between
adjacent ns16550 registers in the system.
-endif # MIPS_CPS_NS16550
+endif # MIPS_CPS_NS16550_BOOL
endmenu
diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c
index 4674f1efbe7a..e1675c25d5d4 100644
--- a/arch/mips/ar7/platform.c
+++ b/arch/mips/ar7/platform.c
@@ -575,7 +575,7 @@ static int __init ar7_register_uarts(void)
uart_port.type = PORT_AR7;
uart_port.uartclk = clk_get_rate(bus_clk) / 2;
uart_port.iotype = UPIO_MEM32;
- uart_port.flags = UPF_FIXED_TYPE;
+ uart_port.flags = UPF_FIXED_TYPE | UPF_BOOT_AUTOCONF;
uart_port.regshift = 2;
uart_port.line = 0;
diff --git a/arch/mips/ath25/devices.c b/arch/mips/ath25/devices.c
index e1156347da53..301a9028273c 100644
--- a/arch/mips/ath25/devices.c
+++ b/arch/mips/ath25/devices.c
@@ -73,6 +73,7 @@ const char *get_system_type(void)
void __init ath25_serial_setup(u32 mapbase, int irq, unsigned int uartclk)
{
+#ifdef CONFIG_SERIAL_8250_CONSOLE
struct uart_port s;
memset(&s, 0, sizeof(s));
@@ -85,6 +86,7 @@ void __init ath25_serial_setup(u32 mapbase, int irq, unsigned int uartclk)
s.uartclk = uartclk;
early_serial_setup(&s);
+#endif /* CONFIG_SERIAL_8250_CONSOLE */
}
int __init ath25_add_wmac(int nr, u32 base, int irq)
diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c
index dd5567b1e305..8f5bd04f320a 100644
--- a/arch/mips/kernel/mips-cm.c
+++ b/arch/mips/kernel/mips-cm.c
@@ -292,7 +292,6 @@ void mips_cm_lock_other(unsigned int cluster, unsigned int core,
*this_cpu_ptr(&cm_core_lock_flags));
} else {
WARN_ON(cluster != 0);
- WARN_ON(vp != 0);
WARN_ON(block != CM_GCR_Cx_OTHER_BLOCK_LOCAL);
/*
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index 78c2affeabf8..e84e12655fa8 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -16,4 +16,5 @@ obj-$(CONFIG_CPU_R3000) += r3k_dump_tlb.o
obj-$(CONFIG_CPU_TX39XX) += r3k_dump_tlb.o
# libgcc-style stuff needed in the kernel
-obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o ucmpdi2.o
+obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o multi3.o \
+ ucmpdi2.o
diff --git a/arch/mips/lib/libgcc.h b/arch/mips/lib/libgcc.h
index 28002ed90c2c..199a7f96282f 100644
--- a/arch/mips/lib/libgcc.h
+++ b/arch/mips/lib/libgcc.h
@@ -10,10 +10,18 @@ typedef int word_type __attribute__ ((mode (__word__)));
struct DWstruct {
int high, low;
};
+
+struct TWstruct {
+ long long high, low;
+};
#elif defined(__LITTLE_ENDIAN)
struct DWstruct {
int low, high;
};
+
+struct TWstruct {
+ long long low, high;
+};
#else
#error I feel sick.
#endif
@@ -23,4 +31,13 @@ typedef union {
long long ll;
} DWunion;
+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6)
+typedef int ti_type __attribute__((mode(TI)));
+
+typedef union {
+ struct TWstruct s;
+ ti_type ti;
+} TWunion;
+#endif
+
#endif /* __ASM_LIBGCC_H */
diff --git a/arch/mips/lib/multi3.c b/arch/mips/lib/multi3.c
new file mode 100644
index 000000000000..111ad475aa0c
--- /dev/null
+++ b/arch/mips/lib/multi3.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+
+#include "libgcc.h"
+
+/*
+ * GCC 7 suboptimally generates __multi3 calls for mips64r6, so for that
+ * specific case only we'll implement it here.
+ *
+ * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82981
+ */
+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6) && (__GNUC__ == 7)
+
+/* multiply 64-bit values, low 64-bits returned */
+static inline long long notrace dmulu(long long a, long long b)
+{
+ long long res;
+
+ asm ("dmulu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b));
+ return res;
+}
+
+/* multiply 64-bit unsigned values, high 64-bits of 128-bit result returned */
+static inline long long notrace dmuhu(long long a, long long b)
+{
+ long long res;
+
+ asm ("dmuhu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b));
+ return res;
+}
+
+/* multiply 128-bit values, low 128-bits returned */
+ti_type notrace __multi3(ti_type a, ti_type b)
+{
+ TWunion res, aa, bb;
+
+ aa.ti = a;
+ bb.ti = b;
+
+ /*
+ * a * b = (a.lo * b.lo)
+ * + 2^64 * (a.hi * b.lo + a.lo * b.hi)
+ * [+ 2^128 * (a.hi * b.hi)]
+ */
+ res.s.low = dmulu(aa.s.low, bb.s.low);
+ res.s.high = dmuhu(aa.s.low, bb.s.low);
+ res.s.high += dmulu(aa.s.high, bb.s.low);
+ res.s.high += dmulu(aa.s.low, bb.s.high);
+
+ return res.ti;
+}
+EXPORT_SYMBOL(__multi3);
+
+#endif /* 64BIT && CPU_MIPSR6 && GCC7 */
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index cdb5a191b9d5..9bb6baa45da3 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -40,7 +40,7 @@
#include "uasm.c"
-static const struct insn const insn_table_MM[insn_invalid] = {
+static const struct insn insn_table_MM[insn_invalid] = {
[insn_addu] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_addu32_op), RT | RS | RD},
[insn_addiu] = {M(mm_addiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM},
[insn_and] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_and_op), RT | RS | RD},
diff --git a/arch/mips/ralink/timer.c b/arch/mips/ralink/timer.c
index d4469b20d176..4f46a4509f79 100644
--- a/arch/mips/ralink/timer.c
+++ b/arch/mips/ralink/timer.c
@@ -109,9 +109,9 @@ static int rt_timer_probe(struct platform_device *pdev)
}
rt->irq = platform_get_irq(pdev, 0);
- if (!rt->irq) {
+ if (rt->irq < 0) {
dev_err(&pdev->dev, "failed to load irq\n");
- return -ENOENT;
+ return rt->irq;
}
rt->membase = devm_ioremap_resource(&pdev->dev, res);
diff --git a/arch/mips/rb532/Makefile b/arch/mips/rb532/Makefile
index efdecdb6e3ea..8186afca2234 100644
--- a/arch/mips/rb532/Makefile
+++ b/arch/mips/rb532/Makefile
@@ -2,4 +2,6 @@
# Makefile for the RB532 board specific parts of the kernel
#
-obj-y += irq.o time.o setup.o serial.o prom.o gpio.o devices.o
+obj-$(CONFIG_SERIAL_8250_CONSOLE) += serial.o
+
+obj-y += irq.o time.o setup.o prom.o gpio.o devices.o
diff --git a/arch/mips/rb532/devices.c b/arch/mips/rb532/devices.c
index 32ea3e6731d6..354d258396ff 100644
--- a/arch/mips/rb532/devices.c
+++ b/arch/mips/rb532/devices.c
@@ -310,6 +310,8 @@ static int __init plat_setup_devices(void)
return platform_add_devices(rb532_devs, ARRAY_SIZE(rb532_devs));
}
+#ifdef CONFIG_NET
+
static int __init setup_kmac(char *s)
{
printk(KERN_INFO "korina mac = %s\n", s);
@@ -322,4 +324,6 @@ static int __init setup_kmac(char *s)
__setup("kmac=", setup_kmac);
+#endif /* CONFIG_NET */
+
arch_initcall(plat_setup_devices);
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c51e6ce42e7a..2ed525a44734 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -166,6 +166,7 @@ config PPC
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
select GENERIC_CMOS_UPDATE
select GENERIC_CPU_AUTOPROBE
+ select GENERIC_CPU_VULNERABILITIES if PPC_BOOK3S_64
select GENERIC_IRQ_SHOW
select GENERIC_IRQ_SHOW_LEVEL
select GENERIC_SMP_IDLE_THREAD
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index f0461618bf7b..eca3f9c68907 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -353,6 +353,7 @@
#define PROC_TABLE_GTSE 0x01
#ifndef __ASSEMBLY__
+#include <linux/types.h>
/**
* plpar_hcall_norets: - Make a pseries hypervisor call with no return arguments
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 61d6049f4c1e..637b7263cb86 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -443,6 +443,31 @@ struct kvm_ppc_rmmu_info {
__u32 ap_encodings[8];
};
+/* For KVM_PPC_GET_CPU_CHAR */
+struct kvm_ppc_cpu_char {
+ __u64 character; /* characteristics of the CPU */
+ __u64 behaviour; /* recommended software behaviour */
+ __u64 character_mask; /* valid bits in character */
+ __u64 behaviour_mask; /* valid bits in behaviour */
+};
+
+/*
+ * Values for character and character_mask.
+ * These are identical to the values used by H_GET_CPU_CHARACTERISTICS.
+ */
+#define KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 (1ULL << 63)
+#define KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED (1ULL << 62)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 (1ULL << 61)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 (1ULL << 60)
+#define KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV (1ULL << 59)
+#define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED (1ULL << 58)
+#define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF (1ULL << 57)
+#define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS (1ULL << 56)
+
+#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY (1ULL << 63)
+#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR (1ULL << 62)
+#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ULL << 61)
+
/* Per-vcpu XICS interrupt controller state */
#define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 9d213542a48b..8fd3a70047f1 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -242,14 +242,6 @@ static int show_cpuinfo(struct seq_file *m, void *v)
unsigned short maj;
unsigned short min;
- /* We only show online cpus: disable preempt (overzealous, I
- * knew) to prevent cpu going down. */
- preempt_disable();
- if (!cpu_online(cpu_id)) {
- preempt_enable();
- return 0;
- }
-
#ifdef CONFIG_SMP
pvr = per_cpu(cpu_pvr, cpu_id);
#else
@@ -358,9 +350,6 @@ static int show_cpuinfo(struct seq_file *m, void *v)
#ifdef CONFIG_SMP
seq_printf(m, "\n");
#endif
-
- preempt_enable();
-
/* If this is the last cpu, print the summary */
if (cpumask_next(cpu_id, cpu_online_mask) >= nr_cpu_ids)
show_cpuinfo_summary(m);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 491be4179ddd..e67413f4a8f0 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -38,6 +38,7 @@
#include <linux/memory.h>
#include <linux/nmi.h>
+#include <asm/debugfs.h>
#include <asm/io.h>
#include <asm/kdump.h>
#include <asm/prom.h>
@@ -901,4 +902,41 @@ void __init setup_rfi_flush(enum l1d_flush_type types, bool enable)
if (!no_rfi_flush)
rfi_flush_enable(enable);
}
+
+#ifdef CONFIG_DEBUG_FS
+static int rfi_flush_set(void *data, u64 val)
+{
+ if (val == 1)
+ rfi_flush_enable(true);
+ else if (val == 0)
+ rfi_flush_enable(false);
+ else
+ return -EINVAL;
+
+ return 0;
+}
+
+static int rfi_flush_get(void *data, u64 *val)
+{
+ *val = rfi_flush ? 1 : 0;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n");
+
+static __init int rfi_flush_debugfs_init(void)
+{
+ debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush);
+ return 0;
+}
+device_initcall(rfi_flush_debugfs_init);
+#endif
+
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ if (rfi_flush)
+ return sprintf(buf, "Mitigation: RFI Flush\n");
+
+ return sprintf(buf, "Vulnerable\n");
+}
#endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 1915e86cef6f..0a7c88786ec0 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -39,6 +39,10 @@
#include <asm/iommu.h>
#include <asm/switch_to.h>
#include <asm/xive.h>
+#ifdef CONFIG_PPC_PSERIES
+#include <asm/hvcall.h>
+#include <asm/plpar_wrappers.h>
+#endif
#include "timing.h"
#include "irq.h"
@@ -548,6 +552,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
#ifdef CONFIG_KVM_XICS
case KVM_CAP_IRQ_XICS:
#endif
+ case KVM_CAP_PPC_GET_CPU_CHAR:
r = 1;
break;
@@ -1759,6 +1764,124 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
return r;
}
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * These functions check whether the underlying hardware is safe
+ * against attacks based on observing the effects of speculatively
+ * executed instructions, and whether it supplies instructions for
+ * use in workarounds. The information comes from firmware, either
+ * via the device tree on powernv platforms or from an hcall on
+ * pseries platforms.
+ */
+#ifdef CONFIG_PPC_PSERIES
+static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+ struct h_cpu_char_result c;
+ unsigned long rc;
+
+ if (!machine_is(pseries))
+ return -ENOTTY;
+
+ rc = plpar_get_cpu_characteristics(&c);
+ if (rc == H_SUCCESS) {
+ cp->character = c.character;
+ cp->behaviour = c.behaviour;
+ cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
+ KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
+ KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
+ KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
+ KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV |
+ KVM_PPC_CPU_CHAR_BR_HINT_HONOURED |
+ KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF |
+ KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+ cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
+ KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
+ KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+ }
+ return 0;
+}
+#else
+static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+ return -ENOTTY;
+}
+#endif
+
+static inline bool have_fw_feat(struct device_node *fw_features,
+ const char *state, const char *name)
+{
+ struct device_node *np;
+ bool r = false;
+
+ np = of_get_child_by_name(fw_features, name);
+ if (np) {
+ r = of_property_read_bool(np, state);
+ of_node_put(np);
+ }
+ return r;
+}
+
+static int kvmppc_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+ struct device_node *np, *fw_features;
+ int r;
+
+ memset(cp, 0, sizeof(*cp));
+ r = pseries_get_cpu_char(cp);
+ if (r != -ENOTTY)
+ return r;
+
+ np = of_find_node_by_name(NULL, "ibm,opal");
+ if (np) {
+ fw_features = of_get_child_by_name(np, "fw-features");
+ of_node_put(np);
+ if (!fw_features)
+ return 0;
+ if (have_fw_feat(fw_features, "enabled",
+ "inst-spec-barrier-ori31,31,0"))
+ cp->character |= KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31;
+ if (have_fw_feat(fw_features, "enabled",
+ "fw-bcctrl-serialized"))
+ cp->character |= KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED;
+ if (have_fw_feat(fw_features, "enabled",
+ "inst-l1d-flush-ori30,30,0"))
+ cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30;
+ if (have_fw_feat(fw_features, "enabled",
+ "inst-l1d-flush-trig2"))
+ cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2;
+ if (have_fw_feat(fw_features, "enabled",
+ "fw-l1d-thread-split"))
+ cp->character |= KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV;
+ if (have_fw_feat(fw_features, "enabled",
+ "fw-count-cache-disabled"))
+ cp->character |= KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+ cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
+ KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
+ KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
+ KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
+ KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV |
+ KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+
+ if (have_fw_feat(fw_features, "enabled",
+ "speculation-policy-favor-security"))
+ cp->behaviour |= KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY;
+ if (!have_fw_feat(fw_features, "disabled",
+ "needs-l1d-flush-msr-pr-0-to-1"))
+ cp->behaviour |= KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR;
+ if (!have_fw_feat(fw_features, "disabled",
+ "needs-spec-barrier-for-bound-checks"))
+ cp->behaviour |= KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+ cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
+ KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
+ KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+
+ of_node_put(fw_features);
+ }
+
+ return 0;
+}
+#endif
+
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -1861,6 +1984,14 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = -EFAULT;
break;
}
+ case KVM_PPC_GET_CPU_CHAR: {
+ struct kvm_ppc_cpu_char cpuchar;
+
+ r = kvmppc_get_cpu_char(&cpuchar);
+ if (r >= 0 && copy_to_user(argp, &cpuchar, sizeof(cpuchar)))
+ r = -EFAULT;
+ break;
+ }
default: {
struct kvm *kvm = filp->private_data;
r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg);
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index cab24f549e7c..0ddc7ac6c5f1 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2344,10 +2344,10 @@ static void dump_one_paca(int cpu)
DUMP(p, kernel_toc, "lx");
DUMP(p, kernelbase, "lx");
DUMP(p, kernel_msr, "lx");
- DUMP(p, emergency_sp, "p");
+ DUMP(p, emergency_sp, "px");
#ifdef CONFIG_PPC_BOOK3S_64
- DUMP(p, nmi_emergency_sp, "p");
- DUMP(p, mc_emergency_sp, "p");
+ DUMP(p, nmi_emergency_sp, "px");
+ DUMP(p, mc_emergency_sp, "px");
DUMP(p, in_nmi, "x");
DUMP(p, in_mce, "x");
DUMP(p, hmi_event_available, "x");
@@ -2375,17 +2375,21 @@ static void dump_one_paca(int cpu)
DUMP(p, slb_cache_ptr, "x");
for (i = 0; i < SLB_CACHE_ENTRIES; i++)
printf(" slb_cache[%d]: = 0x%016lx\n", i, p->slb_cache[i]);
+
+ DUMP(p, rfi_flush_fallback_area, "px");
+ DUMP(p, l1d_flush_congruence, "llx");
+ DUMP(p, l1d_flush_sets, "llx");
#endif
DUMP(p, dscr_default, "llx");
#ifdef CONFIG_PPC_BOOK3E
- DUMP(p, pgd, "p");
- DUMP(p, kernel_pgd, "p");
- DUMP(p, tcd_ptr, "p");
- DUMP(p, mc_kstack, "p");
- DUMP(p, crit_kstack, "p");
- DUMP(p, dbg_kstack, "p");
+ DUMP(p, pgd, "px");
+ DUMP(p, kernel_pgd, "px");
+ DUMP(p, tcd_ptr, "px");
+ DUMP(p, mc_kstack, "px");
+ DUMP(p, crit_kstack, "px");
+ DUMP(p, dbg_kstack, "px");
#endif
- DUMP(p, __current, "p");
+ DUMP(p, __current, "px");
DUMP(p, kstack, "lx");
printf(" kstack_base = 0x%016lx\n", p->kstack & ~(THREAD_SIZE - 1));
DUMP(p, stab_rr, "lx");
@@ -2403,7 +2407,7 @@ static void dump_one_paca(int cpu)
#endif
#ifdef CONFIG_PPC_POWERNV
- DUMP(p, core_idle_state_ptr, "p");
+ DUMP(p, core_idle_state_ptr, "px");
DUMP(p, thread_idle_state, "x");
DUMP(p, thread_mask, "x");
DUMP(p, subcore_sibling_mask, "x");
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index e14f381757f6..c1b0a9ac1dc8 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -207,7 +207,8 @@ struct kvm_s390_sie_block {
__u16 ipa; /* 0x0056 */
__u32 ipb; /* 0x0058 */
__u32 scaoh; /* 0x005c */
- __u8 reserved60; /* 0x0060 */
+#define FPF_BPBC 0x20
+ __u8 fpf; /* 0x0060 */
#define ECB_GS 0x40
#define ECB_TE 0x10
#define ECB_SRSI 0x04
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index 38535a57fef8..4cdaa55fabfe 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -224,6 +224,7 @@ struct kvm_guest_debug_arch {
#define KVM_SYNC_RICCB (1UL << 7)
#define KVM_SYNC_FPRS (1UL << 8)
#define KVM_SYNC_GSCB (1UL << 9)
+#define KVM_SYNC_BPBC (1UL << 10)
/* length and alignment of the sdnx as a power of two */
#define SDNXC 8
#define SDNXL (1UL << SDNXC)
@@ -247,7 +248,9 @@ struct kvm_sync_regs {
};
__u8 reserved[512]; /* for future vector expansion */
__u32 fpc; /* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
- __u8 padding1[52]; /* riccb needs to be 64byte aligned */
+ __u8 bpbc : 1; /* bp mode */
+ __u8 reserved2 : 7;
+ __u8 padding1[51]; /* riccb needs to be 64byte aligned */
__u8 riccb[64]; /* runtime instrumentation controls block */
__u8 padding2[192]; /* sdnx needs to be 256byte aligned */
union {
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2c93cbbcd15e..2598cf243b86 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -421,6 +421,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_S390_GS:
r = test_facility(133);
break;
+ case KVM_CAP_S390_BPB:
+ r = test_facility(82);
+ break;
default:
r = 0;
}
@@ -2198,6 +2201,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
kvm_s390_set_prefix(vcpu, 0);
if (test_kvm_facility(vcpu->kvm, 64))
vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
+ if (test_kvm_facility(vcpu->kvm, 82))
+ vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC;
if (test_kvm_facility(vcpu->kvm, 133))
vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB;
/* fprs can be synchronized via vrs, even if the guest has no vx. With
@@ -2339,6 +2344,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
current->thread.fpu.fpc = 0;
vcpu->arch.sie_block->gbea = 1;
vcpu->arch.sie_block->pp = 0;
+ vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
kvm_clear_async_pf_completion_queue(vcpu);
if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
@@ -3298,6 +3304,11 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
vcpu->arch.sie_block->ecd |= ECD_HOSTREGMGMT;
vcpu->arch.gs_enabled = 1;
}
+ if ((kvm_run->kvm_dirty_regs & KVM_SYNC_BPBC) &&
+ test_kvm_facility(vcpu->kvm, 82)) {
+ vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
+ vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0;
+ }
save_access_regs(vcpu->arch.host_acrs);
restore_access_regs(vcpu->run->s.regs.acrs);
/* save host (userspace) fprs/vrs */
@@ -3344,6 +3355,7 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
kvm_run->s.regs.pft = vcpu->arch.pfault_token;
kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
+ kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
save_access_regs(vcpu->run->s.regs.acrs);
restore_access_regs(vcpu->arch.host_acrs);
/* Save guest register state */
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 5d6ae0326d9e..751348348477 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -223,6 +223,12 @@ static void unshadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
memcpy(scb_o->gcr, scb_s->gcr, 128);
scb_o->pp = scb_s->pp;
+ /* branch prediction */
+ if (test_kvm_facility(vcpu->kvm, 82)) {
+ scb_o->fpf &= ~FPF_BPBC;
+ scb_o->fpf |= scb_s->fpf & FPF_BPBC;
+ }
+
/* interrupt intercept */
switch (scb_s->icptcode) {
case ICPT_PROGI:
@@ -265,6 +271,7 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
scb_s->ecb3 = 0;
scb_s->ecd = 0;
scb_s->fac = 0;
+ scb_s->fpf = 0;
rc = prepare_cpuflags(vcpu, vsie_page);
if (rc)
@@ -324,6 +331,9 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
prefix_unmapped(vsie_page);
scb_s->ecb |= scb_o->ecb & ECB_TE;
}
+ /* branch prediction */
+ if (test_kvm_facility(vcpu->kvm, 82))
+ scb_s->fpf |= scb_o->fpf & FPF_BPBC;
/* SIMD */
if (test_kvm_facility(vcpu->kvm, 129)) {
scb_s->eca |= scb_o->eca & ECA_VX;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1cec2c62a0b0..c53298dfbf50 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7496,13 +7496,13 @@ EXPORT_SYMBOL_GPL(kvm_task_switch);
int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
- if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG_BIT)) {
+ if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
/*
* When EFER.LME and CR0.PG are set, the processor is in
* 64-bit mode (though maybe in a 32-bit code segment).
* CR4.PAE and EFER.LMA must be set.
*/
- if (!(sregs->cr4 & X86_CR4_PAE_BIT)
+ if (!(sregs->cr4 & X86_CR4_PAE)
|| !(sregs->efer & EFER_LMA))
return -EINVAL;
} else {
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 3ef362f598e3..e1d61e8500f9 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -738,7 +738,7 @@ static unsigned long __init sme_pgtable_calc(unsigned long len)
return total;
}
-void __init sme_encrypt_kernel(struct boot_params *bp)
+void __init __nostackprotector sme_encrypt_kernel(struct boot_params *bp)
{
unsigned long workarea_start, workarea_end, workarea_len;
unsigned long execute_start, execute_end, execute_len;