summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/alpha/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/arc/boot/dts/hsdk.dts13
-rw-r--r--arch/arc/include/asm/syscall.h7
-rw-r--r--arch/arc/lib/memset-archs.S4
-rw-r--r--arch/arc/mm/cache.c31
-rw-r--r--arch/arm/Kconfig2
-rw-r--r--arch/arm/Kconfig.debug6
-rw-r--r--arch/arm/boot/compressed/head.S16
-rw-r--r--arch/arm/boot/dts/am335x-evm.dts26
-rw-r--r--arch/arm/boot/dts/am335x-evmsk.dts26
-rw-r--r--arch/arm/boot/dts/am33xx-l4.dtsi4
-rw-r--r--arch/arm/boot/dts/rk3288-tinker.dtsi3
-rw-r--r--arch/arm/boot/dts/rk3288-veyron.dtsi2
-rw-r--r--arch/arm/boot/dts/rk3288.dtsi20
-rw-r--r--arch/arm/boot/dts/sama5d2-pinfunc.h2
-rw-r--r--arch/arm/boot/dts/ste-nomadik-nhk15.dts9
-rw-r--r--arch/arm/include/asm/syscall.h47
-rw-r--r--arch/arm/kernel/head-nommu.S2
-rw-r--r--arch/arm/mach-at91/pm.c6
-rw-r--r--arch/arm/mach-iop13xx/setup.c8
-rw-r--r--arch/arm/mach-iop13xx/tpmi.c10
-rw-r--r--arch/arm/mach-milbeaut/platsmp.c4
-rw-r--r--arch/arm/mach-omap1/board-ams-delta.c2
-rw-r--r--arch/arm/mach-omap2/display.c4
-rw-r--r--arch/arm/plat-iop/adma.c6
-rw-r--r--arch/arm/plat-orion/common.c4
-rw-r--r--arch/arm/tools/syscall.tbl4
-rw-r--r--arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi3
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts4
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3328-rock64.dts3
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3328.dtsi58
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dts1
-rw-r--r--arch/arm64/include/asm/futex.h14
-rw-r--r--arch/arm64/include/asm/module.h5
-rw-r--r--arch/arm64/include/asm/syscall.h46
-rw-r--r--arch/arm64/include/asm/unistd.h2
-rw-r--r--arch/arm64/include/asm/unistd32.h8
-rw-r--r--arch/arm64/kernel/ftrace.c12
-rw-r--r--arch/arm64/kernel/sdei.c6
-rw-r--r--arch/arm64/kernel/traps.c15
-rw-r--r--arch/arm64/mm/init.c2
-rw-r--r--arch/c6x/include/asm/syscall.h79
-rw-r--r--arch/csky/include/asm/syscall.h26
-rw-r--r--arch/h8300/include/asm/syscall.h34
-rw-r--r--arch/hexagon/include/asm/syscall.h4
-rw-r--r--arch/ia64/include/asm/syscall.h13
-rw-r--r--arch/ia64/kernel/ptrace.c7
-rw-r--r--arch/ia64/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/m68k/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/microblaze/include/asm/syscall.h8
-rw-r--r--arch/microblaze/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/mips/ath79/setup.c6
-rw-r--r--arch/mips/configs/generic/board-ocelot.config8
-rw-r--r--arch/mips/include/asm/syscall.h3
-rw-r--r--arch/mips/kernel/kgdb.c3
-rw-r--r--arch/mips/kernel/ptrace.c2
-rw-r--r--arch/mips/kernel/scall64-o32.S2
-rw-r--r--arch/mips/kernel/syscalls/syscall_n32.tbl4
-rw-r--r--arch/mips/kernel/syscalls/syscall_n64.tbl4
-rw-r--r--arch/mips/kernel/syscalls/syscall_o32.tbl4
-rw-r--r--arch/mips/net/ebpf_jit.c5
-rw-r--r--arch/mips/sgi-ip27/ip27-irq.c3
-rw-r--r--arch/nds32/include/asm/syscall.h62
-rw-r--r--arch/nios2/include/asm/syscall.h84
-rw-r--r--arch/openrisc/include/asm/syscall.h12
-rw-r--r--arch/parisc/include/asm/ptrace.h5
-rw-r--r--arch/parisc/include/asm/syscall.h30
-rw-r--r--arch/parisc/kernel/process.c6
-rw-r--r--arch/parisc/kernel/setup.c3
-rw-r--r--arch/parisc/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/powerpc/configs/skiroot_defconfig1
-rw-r--r--arch/powerpc/include/asm/mmu.h2
-rw-r--r--arch/powerpc/include/asm/syscall.h15
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S12
-rw-r--r--arch/powerpc/kernel/head_32.S8
-rw-r--r--arch/powerpc/kernel/kvm.c7
-rw-r--r--arch/powerpc/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/powerpc/kernel/vdso32/gettimeofday.S2
-rw-r--r--arch/powerpc/kvm/book3s_64_vio.c6
-rw-r--r--arch/powerpc/kvm/book3s_hv.c4
-rw-r--r--arch/powerpc/mm/mmu_context_iommu.c97
-rw-r--r--arch/powerpc/mm/ppc_mmu_32.c18
-rw-r--r--arch/powerpc/platforms/Kconfig.cputype2
-rw-r--r--arch/riscv/configs/rv32_defconfig84
-rw-r--r--arch/riscv/include/asm/fixmap.h2
-rw-r--r--arch/riscv/include/asm/syscall.h24
-rw-r--r--arch/riscv/include/asm/uaccess.h2
-rw-r--r--arch/riscv/kernel/Makefile3
-rw-r--r--arch/riscv/kernel/module.c2
-rw-r--r--arch/riscv/kernel/setup.c8
-rw-r--r--arch/riscv/mm/Makefile6
-rw-r--r--arch/riscv/mm/init.c36
-rw-r--r--arch/s390/boot/mem_detect.c2
-rw-r--r--arch/s390/include/asm/syscall.h28
-rw-r--r--arch/s390/kernel/fpu.c2
-rw-r--r--arch/s390/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/s390/kernel/vtime.c8
-rw-r--r--arch/sh/boards/of-generic.c4
-rw-r--r--arch/sh/include/asm/syscall_32.h47
-rw-r--r--arch/sh/include/asm/syscall_64.h8
-rw-r--r--arch/sh/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/sparc/include/asm/syscall.h11
-rw-r--r--arch/sparc/kernel/pci_sun4v.c20
-rw-r--r--arch/sparc/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/um/include/asm/syscall-generic.h78
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/boot/compressed/misc.c2
-rw-r--r--arch/x86/crypto/poly1305-avx2-x86_64.S14
-rw-r--r--arch/x86/crypto/poly1305-sse2-x86_64.S22
-rw-r--r--arch/x86/entry/vdso/vclock_gettime.c4
-rw-r--r--arch/x86/events/amd/core.c286
-rw-r--r--arch/x86/events/core.c13
-rw-r--r--arch/x86/events/intel/core.c20
-rw-r--r--arch/x86/events/intel/cstate.c10
-rw-r--r--arch/x86/events/intel/pt.c3
-rw-r--r--arch/x86/events/perf_event.h38
-rw-r--r--arch/x86/include/asm/bitops.h41
-rw-r--r--arch/x86/include/asm/kvm_emulate.h4
-rw-r--r--arch/x86/include/asm/kvm_host.h18
-rw-r--r--arch/x86/include/asm/pgtable.h2
-rw-r--r--arch/x86/include/asm/syscall.h142
-rw-r--r--arch/x86/include/asm/xen/hypercall.h3
-rw-r--r--arch/x86/include/uapi/asm/kvm.h1
-rw-r--r--arch/x86/include/uapi/asm/vmx.h1
-rw-r--r--arch/x86/kernel/cpu/bugs.c6
-rw-r--r--arch/x86/kernel/cpu/intel.c4
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c9
-rw-r--r--arch/x86/kernel/kprobes/core.c48
-rw-r--r--arch/x86/kernel/process.c8
-rw-r--r--arch/x86/kernel/reboot.c21
-rw-r--r--arch/x86/kernel/vmlinux.lds.S2
-rw-r--r--arch/x86/kvm/emulate.c191
-rw-r--r--arch/x86/kvm/hyperv.c11
-rw-r--r--arch/x86/kvm/lapic.c77
-rw-r--r--arch/x86/kvm/lapic.h4
-rw-r--r--arch/x86/kvm/mmu.c16
-rw-r--r--arch/x86/kvm/mmu.h2
-rw-r--r--arch/x86/kvm/pmu.c4
-rw-r--r--arch/x86/kvm/svm.c79
-rw-r--r--arch/x86/kvm/trace.h4
-rw-r--r--arch/x86/kvm/vmx/nested.c125
-rw-r--r--arch/x86/kvm/vmx/vmenter.S12
-rw-r--r--arch/x86/kvm/vmx/vmx.c42
-rw-r--r--arch/x86/kvm/vmx/vmx.h2
-rw-r--r--arch/x86/kvm/x86.c100
-rw-r--r--arch/x86/kvm/x86.h4
-rw-r--r--arch/x86/lib/Makefile12
-rw-r--r--arch/x86/mm/dump_pagetables.c3
-rw-r--r--arch/x86/mm/init.c6
-rw-r--r--arch/x86/mm/ioremap.c2
-rw-r--r--arch/x86/mm/kaslr.c2
-rw-r--r--arch/x86/mm/tlb.c2
-rw-r--r--arch/xtensa/include/asm/processor.h21
-rw-r--r--arch/xtensa/include/asm/syscall.h33
-rw-r--r--arch/xtensa/kernel/entry.S6
-rw-r--r--arch/xtensa/kernel/stacktrace.c6
-rw-r--r--arch/xtensa/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/xtensa/mm/mmu.c2
158 files changed, 1667 insertions, 1278 deletions
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 63ed39cbd3bd..165f268beafc 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -463,3 +463,7 @@
532 common getppid sys_getppid
# all other architectures have common numbers for new syscall, alpha
# is the exception.
+534 common pidfd_send_signal sys_pidfd_send_signal
+535 common io_uring_setup sys_io_uring_setup
+536 common io_uring_enter sys_io_uring_enter
+537 common io_uring_register sys_io_uring_register
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 69bc1c9e8e50..7425bb0f2d1b 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -18,8 +18,8 @@
model = "snps,hsdk";
compatible = "snps,hsdk";
- #address-cells = <1>;
- #size-cells = <1>;
+ #address-cells = <2>;
+ #size-cells = <2>;
chosen {
bootargs = "earlycon=uart8250,mmio32,0xf0005000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1";
@@ -105,7 +105,7 @@
#size-cells = <1>;
interrupt-parent = <&idu_intc>;
- ranges = <0x00000000 0xf0000000 0x10000000>;
+ ranges = <0x00000000 0x0 0xf0000000 0x10000000>;
cgu_rst: reset-controller@8a0 {
compatible = "snps,hsdk-reset";
@@ -269,9 +269,10 @@
};
memory@80000000 {
- #address-cells = <1>;
- #size-cells = <1>;
+ #address-cells = <2>;
+ #size-cells = <2>;
device_type = "memory";
- reg = <0x80000000 0x40000000>; /* 1 GiB */
+ reg = <0x0 0x80000000 0x0 0x40000000>; /* 1 GB lowmem */
+ /* 0x1 0x00000000 0x0 0x40000000>; 1 GB highmem */
};
};
diff --git a/arch/arc/include/asm/syscall.h b/arch/arc/include/asm/syscall.h
index 29de09804306..c7a4201ed62b 100644
--- a/arch/arc/include/asm/syscall.h
+++ b/arch/arc/include/asm/syscall.h
@@ -55,12 +55,11 @@ syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
*/
static inline void
syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
unsigned long *inside_ptregs = &(regs->r0);
- inside_ptregs -= i;
-
- BUG_ON((i + n) > 6);
+ unsigned int n = 6;
+ unsigned int i = 0;
while (n--) {
args[i++] = (*inside_ptregs);
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
index f230bb7092fd..b3373f5c88e0 100644
--- a/arch/arc/lib/memset-archs.S
+++ b/arch/arc/lib/memset-archs.S
@@ -30,10 +30,10 @@
#else
-.macro PREALLOC_INSTR
+.macro PREALLOC_INSTR reg, off
.endm
-.macro PREFETCHW_INSTR
+.macro PREFETCHW_INSTR reg, off
.endm
#endif
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 4135abec3fb0..63e6e6504699 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -113,10 +113,24 @@ static void read_decode_cache_bcr_arcv2(int cpu)
}
READ_BCR(ARC_REG_CLUSTER_BCR, cbcr);
- if (cbcr.c)
+ if (cbcr.c) {
ioc_exists = 1;
- else
+
+ /*
+ * As for today we don't support both IOC and ZONE_HIGHMEM enabled
+ * simultaneously. This happens because as of today IOC aperture covers
+ * only ZONE_NORMAL (low mem) and any dma transactions outside this
+ * region won't be HW coherent.
+ * If we want to use both IOC and ZONE_HIGHMEM we can use
+ * bounce_buffer to handle dma transactions to HIGHMEM.
+ * Also it is possible to modify dma_direct cache ops or increase IOC
+ * aperture size if we are planning to use HIGHMEM without PAE.
+ */
+ if (IS_ENABLED(CONFIG_HIGHMEM) || is_pae40_enabled())
+ ioc_enable = 0;
+ } else {
ioc_enable = 0;
+ }
/* HS 2.0 didn't have AUX_VOL */
if (cpuinfo_arc700[cpu].core.family > 0x51) {
@@ -1158,19 +1172,6 @@ noinline void __init arc_ioc_setup(void)
if (!ioc_enable)
return;
- /*
- * As for today we don't support both IOC and ZONE_HIGHMEM enabled
- * simultaneously. This happens because as of today IOC aperture covers
- * only ZONE_NORMAL (low mem) and any dma transactions outside this
- * region won't be HW coherent.
- * If we want to use both IOC and ZONE_HIGHMEM we can use
- * bounce_buffer to handle dma transactions to HIGHMEM.
- * Also it is possible to modify dma_direct cache ops or increase IOC
- * aperture size if we are planning to use HIGHMEM without PAE.
- */
- if (IS_ENABLED(CONFIG_HIGHMEM))
- panic("IOC and HIGHMEM can't be used simultaneously");
-
/* Flush + invalidate + disable L1 dcache */
__dc_disable();
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 850b4805e2d1..9aed25a6019b 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -73,7 +73,7 @@ config ARM
select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU
select HAVE_EXIT_THREAD
select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
- select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL
+ select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
select HAVE_FUNCTION_TRACER if !XIP_KERNEL
select HAVE_GCC_PLUGINS
select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 6d6e0330930b..e388af4594a6 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -47,8 +47,8 @@ config DEBUG_WX
choice
prompt "Choose kernel unwinder"
- default UNWINDER_ARM if AEABI && !FUNCTION_GRAPH_TRACER
- default UNWINDER_FRAME_POINTER if !AEABI || FUNCTION_GRAPH_TRACER
+ default UNWINDER_ARM if AEABI
+ default UNWINDER_FRAME_POINTER if !AEABI
help
This determines which method will be used for unwinding kernel stack
traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack,
@@ -65,7 +65,7 @@ config UNWINDER_FRAME_POINTER
config UNWINDER_ARM
bool "ARM EABI stack unwinder"
- depends on AEABI
+ depends on AEABI && !FUNCTION_GRAPH_TRACER
select ARM_UNWIND
help
This option enables stack unwinding support in the kernel
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 6c7ccb428c07..7135820f76d4 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -1438,7 +1438,21 @@ ENTRY(efi_stub_entry)
@ Preserve return value of efi_entry() in r4
mov r4, r0
- bl cache_clean_flush
+
+ @ our cache maintenance code relies on CP15 barrier instructions
+ @ but since we arrived here with the MMU and caches configured
+ @ by UEFI, we must check that the CP15BEN bit is set in SCTLR.
+ @ Note that this bit is RAO/WI on v6 and earlier, so the ISB in
+ @ the enable path will be executed on v7+ only.
+ mrc p15, 0, r1, c1, c0, 0 @ read SCTLR
+ tst r1, #(1 << 5) @ CP15BEN bit set?
+ bne 0f
+ orr r1, r1, #(1 << 5) @ CP15 barrier instructions
+ mcr p15, 0, r1, c1, c0, 0 @ write SCTLR
+ ARM( .inst 0xf57ff06f @ v7+ isb )
+ THUMB( isb )
+
+0: bl cache_clean_flush
bl cache_off
@ Set parameters for booting zImage according to boot protocol
diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts
index dce5be5df97b..edcff79879e7 100644
--- a/arch/arm/boot/dts/am335x-evm.dts
+++ b/arch/arm/boot/dts/am335x-evm.dts
@@ -57,6 +57,24 @@
enable-active-high;
};
+ /* TPS79501 */
+ v1_8d_reg: fixedregulator-v1_8d {
+ compatible = "regulator-fixed";
+ regulator-name = "v1_8d";
+ vin-supply = <&vbat>;
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <1800000>;
+ };
+
+ /* TPS79501 */
+ v3_3d_reg: fixedregulator-v3_3d {
+ compatible = "regulator-fixed";
+ regulator-name = "v3_3d";
+ vin-supply = <&vbat>;
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+ };
+
matrix_keypad: matrix_keypad0 {
compatible = "gpio-matrix-keypad";
debounce-delay-ms = <5>;
@@ -499,10 +517,10 @@
status = "okay";
/* Regulators */
- AVDD-supply = <&vaux2_reg>;
- IOVDD-supply = <&vaux2_reg>;
- DRVDD-supply = <&vaux2_reg>;
- DVDD-supply = <&vbat>;
+ AVDD-supply = <&v3_3d_reg>;
+ IOVDD-supply = <&v3_3d_reg>;
+ DRVDD-supply = <&v3_3d_reg>;
+ DVDD-supply = <&v1_8d_reg>;
};
};
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index b128998097ce..2c2d8b5b8cf5 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -73,6 +73,24 @@
enable-active-high;
};
+ /* TPS79518 */
+ v1_8d_reg: fixedregulator-v1_8d {
+ compatible = "regulator-fixed";
+ regulator-name = "v1_8d";
+ vin-supply = <&vbat>;
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <1800000>;
+ };
+
+ /* TPS78633 */
+ v3_3d_reg: fixedregulator-v3_3d {
+ compatible = "regulator-fixed";
+ regulator-name = "v3_3d";
+ vin-supply = <&vbat>;
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+ };
+
leds {
pinctrl-names = "default";
pinctrl-0 = <&user_leds_s0>;
@@ -501,10 +519,10 @@
status = "okay";
/* Regulators */
- AVDD-supply = <&vaux2_reg>;
- IOVDD-supply = <&vaux2_reg>;
- DRVDD-supply = <&vaux2_reg>;
- DVDD-supply = <&vbat>;
+ AVDD-supply = <&v3_3d_reg>;
+ IOVDD-supply = <&v3_3d_reg>;
+ DRVDD-supply = <&v3_3d_reg>;
+ DVDD-supply = <&v1_8d_reg>;
};
};
diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi
index f459ec316a22..ca6d9f02a800 100644
--- a/arch/arm/boot/dts/am33xx-l4.dtsi
+++ b/arch/arm/boot/dts/am33xx-l4.dtsi
@@ -1762,7 +1762,7 @@
reg = <0xcc000 0x4>;
reg-names = "rev";
/* Domains (P, C): per_pwrdm, l4ls_clkdm */
- clocks = <&l4ls_clkctrl AM3_D_CAN0_CLKCTRL 0>;
+ clocks = <&l4ls_clkctrl AM3_L4LS_D_CAN0_CLKCTRL 0>;
clock-names = "fck";
#address-cells = <1>;
#size-cells = <1>;
@@ -1785,7 +1785,7 @@
reg = <0xd0000 0x4>;
reg-names = "rev";
/* Domains (P, C): per_pwrdm, l4ls_clkdm */
- clocks = <&l4ls_clkctrl AM3_D_CAN1_CLKCTRL 0>;
+ clocks = <&l4ls_clkctrl AM3_L4LS_D_CAN1_CLKCTRL 0>;
clock-names = "fck";
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arm/boot/dts/rk3288-tinker.dtsi b/arch/arm/boot/dts/rk3288-tinker.dtsi
index aa107ee41b8b..ef653c3209bc 100644
--- a/arch/arm/boot/dts/rk3288-tinker.dtsi
+++ b/arch/arm/boot/dts/rk3288-tinker.dtsi
@@ -254,6 +254,7 @@
};
vccio_sd: LDO_REG5 {
+ regulator-boot-on;
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <3300000>;
regulator-name = "vccio_sd";
@@ -430,7 +431,7 @@
bus-width = <4>;
cap-mmc-highspeed;
cap-sd-highspeed;
- card-detect-delay = <200>;
+ broken-cd;
disable-wp; /* wp not hooked up */
pinctrl-names = "default";
pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd &sdmmc_bus4>;
diff --git a/arch/arm/boot/dts/rk3288-veyron.dtsi b/arch/arm/boot/dts/rk3288-veyron.dtsi
index 0bc2409f6903..192dbc089ade 100644
--- a/arch/arm/boot/dts/rk3288-veyron.dtsi
+++ b/arch/arm/boot/dts/rk3288-veyron.dtsi
@@ -25,8 +25,6 @@
gpio_keys: gpio-keys {
compatible = "gpio-keys";
- #address-cells = <1>;
- #size-cells = <0>;
pinctrl-names = "default";
pinctrl-0 = <&pwr_key_l>;
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index ca7d52daa8fb..a024d1e7e74c 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -70,7 +70,7 @@
compatible = "arm,cortex-a12";
reg = <0x501>;
resets = <&cru SRST_CORE1>;
- operating-points = <&cpu_opp_table>;
+ operating-points-v2 = <&cpu_opp_table>;
#cooling-cells = <2>; /* min followed by max */
clock-latency = <40000>;
clocks = <&cru ARMCLK>;
@@ -80,7 +80,7 @@
compatible = "arm,cortex-a12";
reg = <0x502>;
resets = <&cru SRST_CORE2>;
- operating-points = <&cpu_opp_table>;
+ operating-points-v2 = <&cpu_opp_table>;
#cooling-cells = <2>; /* min followed by max */
clock-latency = <40000>;
clocks = <&cru ARMCLK>;
@@ -90,7 +90,7 @@
compatible = "arm,cortex-a12";
reg = <0x503>;
resets = <&cru SRST_CORE3>;
- operating-points = <&cpu_opp_table>;
+ operating-points-v2 = <&cpu_opp_table>;
#cooling-cells = <2>; /* min followed by max */
clock-latency = <40000>;
clocks = <&cru ARMCLK>;
@@ -1119,8 +1119,6 @@
clock-names = "ref", "pclk";
power-domains = <&power RK3288_PD_VIO>;
rockchip,grf = <&grf>;
- #address-cells = <1>;
- #size-cells = <0>;
status = "disabled";
ports {
@@ -1282,27 +1280,27 @@
gpu_opp_table: gpu-opp-table {
compatible = "operating-points-v2";
- opp@100000000 {
+ opp-100000000 {
opp-hz = /bits/ 64 <100000000>;
opp-microvolt = <950000>;
};
- opp@200000000 {
+ opp-200000000 {
opp-hz = /bits/ 64 <200000000>;
opp-microvolt = <950000>;
};
- opp@300000000 {
+ opp-300000000 {
opp-hz = /bits/ 64 <300000000>;
opp-microvolt = <1000000>;
};
- opp@400000000 {
+ opp-400000000 {
opp-hz = /bits/ 64 <400000000>;
opp-microvolt = <1100000>;
};
- opp@500000000 {
+ opp-500000000 {
opp-hz = /bits/ 64 <500000000>;
opp-microvolt = <1200000>;
};
- opp@600000000 {
+ opp-600000000 {
opp-hz = /bits/ 64 <600000000>;
opp-microvolt = <1250000>;
};
diff --git a/arch/arm/boot/dts/sama5d2-pinfunc.h b/arch/arm/boot/dts/sama5d2-pinfunc.h
index 1c01a6f843d8..28a2e45752fe 100644
--- a/arch/arm/boot/dts/sama5d2-pinfunc.h
+++ b/arch/arm/boot/dts/sama5d2-pinfunc.h
@@ -518,7 +518,7 @@
#define PIN_PC9__GPIO PINMUX_PIN(PIN_PC9, 0, 0)
#define PIN_PC9__FIQ PINMUX_PIN(PIN_PC9, 1, 3)
#define PIN_PC9__GTSUCOMP PINMUX_PIN(PIN_PC9, 2, 1)
-#define PIN_PC9__ISC_D0 PINMUX_PIN(PIN_PC9, 2, 1)
+#define PIN_PC9__ISC_D0 PINMUX_PIN(PIN_PC9, 3, 1)
#define PIN_PC9__TIOA4 PINMUX_PIN(PIN_PC9, 4, 2)
#define PIN_PC10 74
#define PIN_PC10__GPIO PINMUX_PIN(PIN_PC10, 0, 0)
diff --git a/arch/arm/boot/dts/ste-nomadik-nhk15.dts b/arch/arm/boot/dts/ste-nomadik-nhk15.dts
index f2f6558a00f1..04066f9cb8a3 100644
--- a/arch/arm/boot/dts/ste-nomadik-nhk15.dts
+++ b/arch/arm/boot/dts/ste-nomadik-nhk15.dts
@@ -213,13 +213,12 @@
gpio-sck = <&gpio0 5 GPIO_ACTIVE_HIGH>;
gpio-mosi = <&gpio0 4 GPIO_ACTIVE_HIGH>;
/*
- * This chipselect is active high. Just setting the flags
- * to GPIO_ACTIVE_HIGH is not enough for the SPI DT bindings,
- * it will be ignored, only the special "spi-cs-high" flag
- * really counts.
+ * It's not actually active high, but the frameworks assume
+ * the polarity of the passed-in GPIO is "normal" (active
+ * high) then actively drives the line low to select the
+ * chip.
*/
cs-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>;
- spi-cs-high;
num-chipselects = <1>;
/*
diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h
index 06dea6bce293..080ce70cab12 100644
--- a/arch/arm/include/asm/syscall.h
+++ b/arch/arm/include/asm/syscall.h
@@ -55,53 +55,22 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
- unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
- pr_warn("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- memset(args_bad, 0, n_bad * sizeof(args[0]));
- n = SYSCALL_MAX_ARGS - i;
- }
-
- if (i == 0) {
- args[0] = regs->ARM_ORIG_r0;
- args++;
- i++;
- n--;
- }
-
- memcpy(args, &regs->ARM_r0 + i, n * sizeof(args[0]));
+ args[0] = regs->ARM_ORIG_r0;
+ args++;
+
+ memcpy(args, &regs->ARM_r0 + 1, 5 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- pr_warn("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- n = SYSCALL_MAX_ARGS - i;
- }
-
- if (i == 0) {
- regs->ARM_ORIG_r0 = args[0];
- args++;
- i++;
- n--;
- }
-
- memcpy(&regs->ARM_r0 + i, args, n * sizeof(args[0]));
+ regs->ARM_ORIG_r0 = args[0];
+ args++;
+
+ memcpy(&regs->ARM_r0 + 1, args, 5 * sizeof(args[0]));
}
static inline int syscall_get_arch(void)
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index c08d2d890f7b..b38bbd011b35 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -133,9 +133,9 @@ __secondary_data:
*/
.text
__after_proc_init:
-#ifdef CONFIG_ARM_MPU
M_CLASS(movw r12, #:lower16:BASEADDR_V7M_SCB)
M_CLASS(movt r12, #:upper16:BASEADDR_V7M_SCB)
+#ifdef CONFIG_ARM_MPU
M_CLASS(ldr r3, [r12, 0x50])
AR_CLASS(mrc p15, 0, r3, c0, c1, 4) @ Read ID_MMFR0
and r3, r3, #(MMFR0_PMSA) @ PMSA field
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 51e808adb00c..2a757dcaa1a5 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -591,13 +591,13 @@ static int __init at91_pm_backup_init(void)
np = of_find_compatible_node(NULL, NULL, "atmel,sama5d2-securam");
if (!np)
- goto securam_fail;
+ goto securam_fail_no_ref_dev;
pdev = of_find_device_by_node(np);
of_node_put(np);
if (!pdev) {
pr_warn("%s: failed to find securam device!\n", __func__);
- goto securam_fail;
+ goto securam_fail_no_ref_dev;
}
sram_pool = gen_pool_get(&pdev->dev, NULL);
@@ -620,6 +620,8 @@ static int __init at91_pm_backup_init(void)
return 0;
securam_fail:
+ put_device(&pdev->dev);
+securam_fail_no_ref_dev:
iounmap(pm_data.sfrbu);
pm_data.sfrbu = NULL;
return ret;
diff --git a/arch/arm/mach-iop13xx/setup.c b/arch/arm/mach-iop13xx/setup.c
index 53c316f7301e..fe4932fda01d 100644
--- a/arch/arm/mach-iop13xx/setup.c
+++ b/arch/arm/mach-iop13xx/setup.c
@@ -300,7 +300,7 @@ static struct resource iop13xx_adma_2_resources[] = {
}
};
-static u64 iop13xx_adma_dmamask = DMA_BIT_MASK(64);
+static u64 iop13xx_adma_dmamask = DMA_BIT_MASK(32);
static struct iop_adma_platform_data iop13xx_adma_0_data = {
.hw_id = 0,
.pool_size = PAGE_SIZE,
@@ -324,7 +324,7 @@ static struct platform_device iop13xx_adma_0_channel = {
.resource = iop13xx_adma_0_resources,
.dev = {
.dma_mask = &iop13xx_adma_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = (void *) &iop13xx_adma_0_data,
},
};
@@ -336,7 +336,7 @@ static struct platform_device iop13xx_adma_1_channel = {
.resource = iop13xx_adma_1_resources,
.dev = {
.dma_mask = &iop13xx_adma_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = (void *) &iop13xx_adma_1_data,
},
};
@@ -348,7 +348,7 @@ static struct platform_device iop13xx_adma_2_channel = {
.resource = iop13xx_adma_2_resources,
.dev = {
.dma_mask = &iop13xx_adma_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = (void *) &iop13xx_adma_2_data,
},
};
diff --git a/arch/arm/mach-iop13xx/tpmi.c b/arch/arm/mach-iop13xx/tpmi.c
index db511ec2b1df..116feb6b261e 100644
--- a/arch/arm/mach-iop13xx/tpmi.c
+++ b/arch/arm/mach-iop13xx/tpmi.c
@@ -152,7 +152,7 @@ static struct resource iop13xx_tpmi_3_resources[] = {
}
};
-u64 iop13xx_tpmi_mask = DMA_BIT_MASK(64);
+u64 iop13xx_tpmi_mask = DMA_BIT_MASK(32);
static struct platform_device iop13xx_tpmi_0_device = {
.name = "iop-tpmi",
.id = 0,
@@ -160,7 +160,7 @@ static struct platform_device iop13xx_tpmi_0_device = {
.resource = iop13xx_tpmi_0_resources,
.dev = {
.dma_mask = &iop13xx_tpmi_mask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
@@ -171,7 +171,7 @@ static struct platform_device iop13xx_tpmi_1_device = {
.resource = iop13xx_tpmi_1_resources,
.dev = {
.dma_mask = &iop13xx_tpmi_mask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
@@ -182,7 +182,7 @@ static struct platform_device iop13xx_tpmi_2_device = {
.resource = iop13xx_tpmi_2_resources,
.dev = {
.dma_mask = &iop13xx_tpmi_mask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
@@ -193,7 +193,7 @@ static struct platform_device iop13xx_tpmi_3_device = {
.resource = iop13xx_tpmi_3_resources,
.dev = {
.dma_mask = &iop13xx_tpmi_mask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
diff --git a/arch/arm/mach-milbeaut/platsmp.c b/arch/arm/mach-milbeaut/platsmp.c
index 591543c81399..3ea880f5fcb7 100644
--- a/arch/arm/mach-milbeaut/platsmp.c
+++ b/arch/arm/mach-milbeaut/platsmp.c
@@ -65,6 +65,7 @@ static void m10v_smp_init(unsigned int max_cpus)
writel(KERNEL_UNBOOT_FLAG, m10v_smp_base + cpu * 4);
}
+#ifdef CONFIG_HOTPLUG_CPU
static void m10v_cpu_die(unsigned int l_cpu)
{
gic_cpu_if_down(0);
@@ -83,12 +84,15 @@ static int m10v_cpu_kill(unsigned int l_cpu)
return 1;
}
+#endif
static struct smp_operations m10v_smp_ops __initdata = {
.smp_prepare_cpus = m10v_smp_init,
.smp_boot_secondary = m10v_boot_secondary,
+#ifdef CONFIG_HOTPLUG_CPU
.cpu_die = m10v_cpu_die,
.cpu_kill = m10v_cpu_kill,
+#endif
};
CPU_METHOD_OF_DECLARE(m10v_smp, "socionext,milbeaut-m10v-smp", &m10v_smp_ops);
diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c
index be30c3c061b4..1b15d593837e 100644
--- a/arch/arm/mach-omap1/board-ams-delta.c
+++ b/arch/arm/mach-omap1/board-ams-delta.c
@@ -182,6 +182,7 @@ static struct resource latch1_resources[] = {
static struct bgpio_pdata latch1_pdata = {
.label = LATCH1_LABEL,
+ .base = -1,
.ngpio = LATCH1_NGPIO,
};
@@ -219,6 +220,7 @@ static struct resource latch2_resources[] = {
static struct bgpio_pdata latch2_pdata = {
.label = LATCH2_LABEL,
+ .base = -1,
.ngpio = LATCH2_NGPIO,
};
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 1444b4b4bd9f..439e143cad7b 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -250,8 +250,10 @@ static int __init omapdss_init_of(void)
if (!node)
return 0;
- if (!of_device_is_available(node))
+ if (!of_device_is_available(node)) {
+ of_node_put(node);
return 0;
+ }
pdev = of_find_device_by_node(node);
diff --git a/arch/arm/plat-iop/adma.c b/arch/arm/plat-iop/adma.c
index a4d1f8de3b5b..d9612221e484 100644
--- a/arch/arm/plat-iop/adma.c
+++ b/arch/arm/plat-iop/adma.c
@@ -143,7 +143,7 @@ struct platform_device iop3xx_dma_0_channel = {
.resource = iop3xx_dma_0_resources,
.dev = {
.dma_mask = &iop3xx_adma_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = (void *) &iop3xx_dma_0_data,
},
};
@@ -155,7 +155,7 @@ struct platform_device iop3xx_dma_1_channel = {
.resource = iop3xx_dma_1_resources,
.dev = {
.dma_mask = &iop3xx_adma_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = (void *) &iop3xx_dma_1_data,
},
};
@@ -167,7 +167,7 @@ struct platform_device iop3xx_aau_channel = {
.resource = iop3xx_aau_resources,
.dev = {
.dma_mask = &iop3xx_adma_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = (void *) &iop3xx_aau_data,
},
};
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index a6c81ce00f52..8647cb80a93b 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -622,7 +622,7 @@ static struct platform_device orion_xor0_shared = {
.resource = orion_xor0_shared_resources,
.dev = {
.dma_mask = &orion_xor_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = &orion_xor0_pdata,
},
};
@@ -683,7 +683,7 @@ static struct platform_device orion_xor1_shared = {
.resource = orion_xor1_shared_resources,
.dev = {
.dma_mask = &orion_xor_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(64),
+ .coherent_dma_mask = DMA_BIT_MASK(32),
.platform_data = &orion_xor1_pdata,
},
};
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 9016f4081bb9..0393917eaa57 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -437,3 +437,7 @@
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index 7c649f6b14cb..cd7c76e58b09 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -162,6 +162,7 @@
rx-fifo-depth = <16384>;
snps,multicast-filter-bins = <256>;
iommus = <&smmu 1>;
+ altr,sysmgr-syscon = <&sysmgr 0x44 0>;
status = "disabled";
};
@@ -179,6 +180,7 @@
rx-fifo-depth = <16384>;
snps,multicast-filter-bins = <256>;
iommus = <&smmu 2>;
+ altr,sysmgr-syscon = <&sysmgr 0x48 0>;
status = "disabled";
};
@@ -196,6 +198,7 @@
rx-fifo-depth = <16384>;
snps,multicast-filter-bins = <256>;
iommus = <&smmu 3>;
+ altr,sysmgr-syscon = <&sysmgr 0x4c 0>;
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts b/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts
index 33c44e857247..0e34354b2092 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts
@@ -108,8 +108,8 @@
snps,reset-gpio = <&gpio1 RK_PC2 GPIO_ACTIVE_LOW>;
snps,reset-active-low;
snps,reset-delays-us = <0 10000 50000>;
- tx_delay = <0x25>;
- rx_delay = <0x11>;
+ tx_delay = <0x24>;
+ rx_delay = <0x18>;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
index 2157a528276b..79b4d1d4b5d6 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
@@ -46,8 +46,7 @@
vcc_host1_5v: vcc_otg_5v: vcc-host1-5v-regulator {
compatible = "regulator-fixed";
- enable-active-high;
- gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_HIGH>;
+ gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_LOW>;
pinctrl-names = "default";
pinctrl-0 = <&usb20_host_drv>;
regulator-name = "vcc_host1_5v";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index 84f14b132e8f..dabef1a21649 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -1445,11 +1445,11 @@
sdmmc0 {
sdmmc0_clk: sdmmc0-clk {
- rockchip,pins = <1 RK_PA6 1 &pcfg_pull_none_4ma>;
+ rockchip,pins = <1 RK_PA6 1 &pcfg_pull_none_8ma>;
};
sdmmc0_cmd: sdmmc0-cmd {
- rockchip,pins = <1 RK_PA4 1 &pcfg_pull_up_4ma>;
+ rockchip,pins = <1 RK_PA4 1 &pcfg_pull_up_8ma>;
};
sdmmc0_dectn: sdmmc0-dectn {
@@ -1461,14 +1461,14 @@
};
sdmmc0_bus1: sdmmc0-bus1 {
- rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_4ma>;
+ rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_8ma>;
};
sdmmc0_bus4: sdmmc0-bus4 {
- rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_4ma>,
- <1 RK_PA1 1 &pcfg_pull_up_4ma>,
- <1 RK_PA2 1 &pcfg_pull_up_4ma>,
- <1 RK_PA3 1 &pcfg_pull_up_4ma>;
+ rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_8ma>,
+ <1 RK_PA1 1 &pcfg_pull_up_8ma>,
+ <1 RK_PA2 1 &pcfg_pull_up_8ma>,
+ <1 RK_PA3 1 &pcfg_pull_up_8ma>;
};
sdmmc0_gpio: sdmmc0-gpio {
@@ -1642,50 +1642,50 @@
rgmiim1_pins: rgmiim1-pins {
rockchip,pins =
/* mac_txclk */
- <1 RK_PB4 2 &pcfg_pull_none_12ma>,
+ <1 RK_PB4 2 &pcfg_pull_none_8ma>,
/* mac_rxclk */
- <1 RK_PB5 2 &pcfg_pull_none_2ma>,
+ <1 RK_PB5 2 &pcfg_pull_none_4ma>,
/* mac_mdio */
- <1 RK_PC3 2 &pcfg_pull_none_2ma>,
+ <1 RK_PC3 2 &pcfg_pull_none_4ma>,
/* mac_txen */
- <1 RK_PD1 2 &pcfg_pull_none_12ma>,
+ <1 RK_PD1 2 &pcfg_pull_none_8ma>,
/* mac_clk */
- <1 RK_PC5 2 &pcfg_pull_none_2ma>,
+ <1 RK_PC5 2 &pcfg_pull_none_4ma>,
/* mac_rxdv */
- <1 RK_PC6 2 &pcfg_pull_none_2ma>,
+ <1 RK_PC6 2 &pcfg_pull_none_4ma>,
/* mac_mdc */
- <1 RK_PC7 2 &pcfg_pull_none_2ma>,
+ <1 RK_PC7 2 &pcfg_pull_none_4ma>,
/* mac_rxd1 */
- <1 RK_PB2 2 &pcfg_pull_none_2ma>,
+ <1 RK_PB2 2 &pcfg_pull_none_4ma>,
/* mac_rxd0 */
- <1 RK_PB3 2 &pcfg_pull_none_2ma>,
+ <1 RK_PB3 2 &pcfg_pull_none_4ma>,
/* mac_txd1 */
- <1 RK_PB0 2 &pcfg_pull_none_12ma>,
+ <1 RK_PB0 2 &pcfg_pull_none_8ma>,
/* mac_txd0 */
- <1 RK_PB1 2 &pcfg_pull_none_12ma>,
+ <1 RK_PB1 2 &pcfg_pull_none_8ma>,
/* mac_rxd3 */
- <1 RK_PB6 2 &pcfg_pull_none_2ma>,
+ <1 RK_PB6 2 &pcfg_pull_none_4ma>,
/* mac_rxd2 */
- <1 RK_PB7 2 &pcfg_pull_none_2ma>,
+ <1 RK_PB7 2 &pcfg_pull_none_4ma>,
/* mac_txd3 */
- <1 RK_PC0 2 &pcfg_pull_none_12ma>,
+ <1 RK_PC0 2 &pcfg_pull_none_8ma>,
/* mac_txd2 */
- <1 RK_PC1 2 &pcfg_pull_none_12ma>,
+ <1 RK_PC1 2 &pcfg_pull_none_8ma>,
/* mac_txclk */
- <0 RK_PB0 1 &pcfg_pull_none>,
+ <0 RK_PB0 1 &pcfg_pull_none_8ma>,
/* mac_txen */
- <0 RK_PB4 1 &pcfg_pull_none>,
+ <0 RK_PB4 1 &pcfg_pull_none_8ma>,
/* mac_clk */
- <0 RK_PD0 1 &pcfg_pull_none>,
+ <0 RK_PD0 1 &pcfg_pull_none_4ma>,
/* mac_txd1 */
- <0 RK_PC0 1 &pcfg_pull_none>,
+ <0 RK_PC0 1 &pcfg_pull_none_8ma>,
/* mac_txd0 */
- <0 RK_PC1 1 &pcfg_pull_none>,
+ <0 RK_PC1 1 &pcfg_pull_none_8ma>,
/* mac_txd3 */
- <0 RK_PC7 1 &pcfg_pull_none>,
+ <0 RK_PC7 1 &pcfg_pull_none_8ma>,
/* mac_txd2 */
- <0 RK_PC6 1 &pcfg_pull_none>;
+ <0 RK_PC6 1 &pcfg_pull_none_8ma>;
};
rmiim1_pins: rmiim1-pins {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dts b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dts
index 4a543f2117d4..844eac939a97 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dts
@@ -158,6 +158,7 @@
};
&hdmi {
+ ddc-i2c-bus = <&i2c3>;
pinctrl-names = "default";
pinctrl-0 = <&hdmi_cec>;
status = "okay";
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index cccb83ad7fa8..c7e1a7837706 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -30,8 +30,8 @@ do { \
" prfm pstl1strm, %2\n" \
"1: ldxr %w1, %2\n" \
insn "\n" \
-"2: stlxr %w3, %w0, %2\n" \
-" cbnz %w3, 1b\n" \
+"2: stlxr %w0, %w3, %2\n" \
+" cbnz %w0, 1b\n" \
" dmb ish\n" \
"3:\n" \
" .pushsection .fixup,\"ax\"\n" \
@@ -57,23 +57,23 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
switch (op) {
case FUTEX_OP_SET:
- __futex_atomic_op("mov %w0, %w4",
+ __futex_atomic_op("mov %w3, %w4",
ret, oldval, uaddr, tmp, oparg);
break;
case FUTEX_OP_ADD:
- __futex_atomic_op("add %w0, %w1, %w4",
+ __futex_atomic_op("add %w3, %w1, %w4",
ret, oldval, uaddr, tmp, oparg);
break;
case FUTEX_OP_OR:
- __futex_atomic_op("orr %w0, %w1, %w4",
+ __futex_atomic_op("orr %w3, %w1, %w4",
ret, oldval, uaddr, tmp, oparg);
break;
case FUTEX_OP_ANDN:
- __futex_atomic_op("and %w0, %w1, %w4",
+ __futex_atomic_op("and %w3, %w1, %w4",
ret, oldval, uaddr, tmp, ~oparg);
break;
case FUTEX_OP_XOR:
- __futex_atomic_op("eor %w0, %w1, %w4",
+ __futex_atomic_op("eor %w3, %w1, %w4",
ret, oldval, uaddr, tmp, oparg);
break;
default:
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index 905e1bb0e7bd..cd9f4e9d04d3 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -73,4 +73,9 @@ static inline bool is_forbidden_offset_for_adrp(void *place)
struct plt_entry get_plt_entry(u64 dst, void *pc);
bool plt_entries_equal(const struct plt_entry *a, const struct plt_entry *b);
+static inline bool plt_entry_is_initialized(const struct plt_entry *e)
+{
+ return e->adrp || e->add || e->br;
+}
+
#endif /* __ASM_MODULE_H */
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index ad8be16a39c9..a179df3674a1 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -65,52 +65,22 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
- unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
- pr_warning("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- memset(args_bad, 0, n_bad * sizeof(args[0]));
- }
-
- if (i == 0) {
- args[0] = regs->orig_x0;
- args++;
- i++;
- n--;
- }
-
- memcpy(args, &regs->regs[i], n * sizeof(args[0]));
+ args[0] = regs->orig_x0;
+ args++;
+
+ memcpy(args, &regs->regs[1], 5 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- pr_warning("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- n = SYSCALL_MAX_ARGS - i;
- }
-
- if (i == 0) {
- regs->orig_x0 = args[0];
- args++;
- i++;
- n--;
- }
-
- memcpy(&regs->regs[i], args, n * sizeof(args[0]));
+ regs->orig_x0 = args[0];
+ args++;
+
+ memcpy(&regs->regs[1], args, 5 * sizeof(args[0]));
}
/*
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index d1dd93436e1e..f2a83ff6b73c 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -44,7 +44,7 @@
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 424
+#define __NR_compat_syscalls 428
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 5590f2623690..23f1a44acada 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -866,6 +866,14 @@ __SYSCALL(__NR_rt_sigtimedwait_time64, compat_sys_rt_sigtimedwait_time64)
__SYSCALL(__NR_futex_time64, sys_futex)
#define __NR_sched_rr_get_interval_time64 423
__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
+#define __NR_pidfd_send_signal 424
+__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
+#define __NR_io_uring_setup 425
+__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
+#define __NR_io_uring_enter 426
+__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
+#define __NR_io_uring_register 427
+__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
/*
* Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 8e4431a8821f..65a51331088e 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -103,12 +103,16 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
* to be revisited if support for multiple ftrace entry points
* is added in the future, but for now, the pr_err() below
* deals with a theoretical issue only.
+ *
+ * Note that PLTs are place relative, and plt_entries_equal()
+ * checks whether they point to the same target. Here, we need
+ * to check if the actual opcodes are in fact identical,
+ * regardless of the offset in memory so use memcmp() instead.
*/
trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline);
- if (!plt_entries_equal(mod->arch.ftrace_trampoline,
- &trampoline)) {
- if (!plt_entries_equal(mod->arch.ftrace_trampoline,
- &(struct plt_entry){})) {
+ if (memcmp(mod->arch.ftrace_trampoline, &trampoline,
+ sizeof(trampoline))) {
+ if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) {
pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
return -EINVAL;
}
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index 5ba4465e44f0..ea94cf8f9dc6 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -94,6 +94,9 @@ static bool on_sdei_normal_stack(unsigned long sp, struct stack_info *info)
unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
unsigned long high = low + SDEI_STACK_SIZE;
+ if (!low)
+ return false;
+
if (sp < low || sp >= high)
return false;
@@ -111,6 +114,9 @@ static bool on_sdei_critical_stack(unsigned long sp, struct stack_info *info)
unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr);
unsigned long high = low + SDEI_STACK_SIZE;
+ if (!low)
+ return false;
+
if (sp < low || sp >= high)
return false;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 8ad119c3f665..29755989f616 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -102,10 +102,16 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
{
struct stackframe frame;
- int skip;
+ int skip = 0;
pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
+ if (regs) {
+ if (user_mode(regs))
+ return;
+ skip = 1;
+ }
+
if (!tsk)
tsk = current;
@@ -126,7 +132,6 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
frame.graph = 0;
#endif
- skip = !!regs;
printk("Call trace:\n");
do {
/* skip until specified stack frame */
@@ -176,15 +181,13 @@ static int __die(const char *str, int err, struct pt_regs *regs)
return ret;
print_modules();
- __show_regs(regs);
pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n",
TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk),
end_of_stack(tsk));
+ show_regs(regs);
- if (!user_mode(regs)) {
- dump_backtrace(regs, tsk);
+ if (!user_mode(regs))
dump_instr(KERN_EMERG, regs);
- }
return ret;
}
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 6bc135042f5e..7cae155e81a5 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -363,7 +363,7 @@ void __init arm64_memblock_init(void)
* Otherwise, this is a no-op
*/
u64 base = phys_initrd_start & PAGE_MASK;
- u64 size = PAGE_ALIGN(phys_initrd_size);
+ u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base;
/*
* We can only add back the initrd memory if we don't end up
diff --git a/arch/c6x/include/asm/syscall.h b/arch/c6x/include/asm/syscall.h
index ae2be315ee9c..15ba8599858e 100644
--- a/arch/c6x/include/asm/syscall.h
+++ b/arch/c6x/include/asm/syscall.h
@@ -46,78 +46,27 @@ static inline void syscall_set_return_value(struct task_struct *task,
}
static inline void syscall_get_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i,
- unsigned int n, unsigned long *args)
+ struct pt_regs *regs,
+ unsigned long *args)
{
- switch (i) {
- case 0:
- if (!n--)
- break;
- *args++ = regs->a4;
- case 1:
- if (!n--)
- break;
- *args++ = regs->b4;
- case 2:
- if (!n--)
- break;
- *args++ = regs->a6;
- case 3:
- if (!n--)
- break;
- *args++ = regs->b6;
- case 4:
- if (!n--)
- break;
- *args++ = regs->a8;
- case 5:
- if (!n--)
- break;
- *args++ = regs->b8;
- case 6:
- if (!n--)
- break;
- default:
- BUG();
- }
+ *args++ = regs->a4;
+ *args++ = regs->b4;
+ *args++ = regs->a6;
+ *args++ = regs->b6;
+ *args++ = regs->a8;
+ *args = regs->b8;
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- switch (i) {
- case 0:
- if (!n--)
- break;
- regs->a4 = *args++;
- case 1:
- if (!n--)
- break;
- regs->b4 = *args++;
- case 2:
- if (!n--)
- break;
- regs->a6 = *args++;
- case 3:
- if (!n--)
- break;
- regs->b6 = *args++;
- case 4:
- if (!n--)
- break;
- regs->a8 = *args++;
- case 5:
- if (!n--)
- break;
- regs->a9 = *args++;
- case 6:
- if (!n)
- break;
- default:
- BUG();
- }
+ regs->a4 = *args++;
+ regs->b4 = *args++;
+ regs->a6 = *args++;
+ regs->b6 = *args++;
+ regs->a8 = *args++;
+ regs->a9 = *args;
}
#endif /* __ASM_C6X_SYSCALLS_H */
diff --git a/arch/csky/include/asm/syscall.h b/arch/csky/include/asm/syscall.h
index d637445737b7..bda0a446c63e 100644
--- a/arch/csky/include/asm/syscall.h
+++ b/arch/csky/include/asm/syscall.h
@@ -43,30 +43,20 @@ syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
static inline void
syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
- BUG_ON(i + n > 6);
- if (i == 0) {
- args[0] = regs->orig_a0;
- args++;
- i++;
- n--;
- }
- memcpy(args, &regs->a1 + i * sizeof(regs->a1), n * sizeof(args[0]));
+ args[0] = regs->orig_a0;
+ args++;
+ memcpy(args, &regs->a1, 5 * sizeof(args[0]));
}
static inline void
syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, const unsigned long *args)
+ const unsigned long *args)
{
- BUG_ON(i + n > 6);
- if (i == 0) {
- regs->orig_a0 = args[0];
- args++;
- i++;
- n--;
- }
- memcpy(&regs->a1 + i * sizeof(regs->a1), args, n * sizeof(regs->a0));
+ regs->orig_a0 = args[0];
+ args++;
+ memcpy(&regs->a1, args, 5 * sizeof(regs->a1));
}
static inline int
diff --git a/arch/h8300/include/asm/syscall.h b/arch/h8300/include/asm/syscall.h
index 924990401237..ddd483c6ca95 100644
--- a/arch/h8300/include/asm/syscall.h
+++ b/arch/h8300/include/asm/syscall.h
@@ -17,34 +17,14 @@ syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
static inline void
syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- while (n > 0) {
- switch (i) {
- case 0:
- *args++ = regs->er1;
- break;
- case 1:
- *args++ = regs->er2;
- break;
- case 2:
- *args++ = regs->er3;
- break;
- case 3:
- *args++ = regs->er4;
- break;
- case 4:
- *args++ = regs->er5;
- break;
- case 5:
- *args++ = regs->er6;
- break;
- }
- i++;
- n--;
- }
+ *args++ = regs->er1;
+ *args++ = regs->er2;
+ *args++ = regs->er3;
+ *args++ = regs->er4;
+ *args++ = regs->er5;
+ *args = regs->er6;
}
diff --git a/arch/hexagon/include/asm/syscall.h b/arch/hexagon/include/asm/syscall.h
index 4af9c7b6f13a..ae3a1e24fabd 100644
--- a/arch/hexagon/include/asm/syscall.h
+++ b/arch/hexagon/include/asm/syscall.h
@@ -37,10 +37,8 @@ static inline long syscall_get_nr(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(args, &(&regs->r00)[i], n * sizeof(args[0]));
+ memcpy(args, &(&regs->r00)[0], 6 * sizeof(args[0]));
}
#endif
diff --git a/arch/ia64/include/asm/syscall.h b/arch/ia64/include/asm/syscall.h
index 1d0b875fec44..0d9e7fab4a79 100644
--- a/arch/ia64/include/asm/syscall.h
+++ b/arch/ia64/include/asm/syscall.h
@@ -59,26 +59,19 @@ static inline void syscall_set_return_value(struct task_struct *task,
}
extern void ia64_syscall_get_set_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i, unsigned int n,
- unsigned long *args, int rw);
+ struct pt_regs *regs, unsigned long *args, int rw);
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- ia64_syscall_get_set_arguments(task, regs, i, n, args, 0);
+ ia64_syscall_get_set_arguments(task, regs, args, 0);
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- ia64_syscall_get_set_arguments(task, regs, i, n, args, 1);
+ ia64_syscall_get_set_arguments(task, regs, args, 1);
}
static inline int syscall_get_arch(void)
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index 6d50ede0ed69..bf9c24d9ce84 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -2179,12 +2179,11 @@ static void syscall_get_set_args_cb(struct unw_frame_info *info, void *data)
}
void ia64_syscall_get_set_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i, unsigned int n,
- unsigned long *args, int rw)
+ struct pt_regs *regs, unsigned long *args, int rw)
{
struct syscall_get_set_args data = {
- .i = i,
- .n = n,
+ .i = 0,
+ .n = 6,
.args = args,
.regs = regs,
.rw = rw,
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index ab9cda5f6136..56e3d0b685e1 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -344,3 +344,7 @@
332 common pkey_free sys_pkey_free
333 common rseq sys_rseq
# 334 through 423 are reserved to sync up with other architectures
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 125c14178979..df4ec3ec71d1 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -423,3 +423,7 @@
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/microblaze/include/asm/syscall.h b/arch/microblaze/include/asm/syscall.h
index 220decd605a4..833d3a53dab3 100644
--- a/arch/microblaze/include/asm/syscall.h
+++ b/arch/microblaze/include/asm/syscall.h
@@ -82,18 +82,22 @@ static inline void microblaze_set_syscall_arg(struct pt_regs *regs,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
+ unsigned int i = 0;
+ unsigned int n = 6;
+
while (n--)
*args++ = microblaze_get_syscall_arg(regs, i++);
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
+ unsigned int i = 0;
+ unsigned int n = 6;
+
while (n--)
microblaze_set_syscall_arg(regs, i++, *args++);
}
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 8ee3a8c18498..4964947732af 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -429,3 +429,7 @@
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index 4a70c5de8c92..25a57895a3a3 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -210,12 +210,6 @@ const char *get_system_type(void)
return ath79_sys_type;
}
-int get_c0_perfcount_int(void)
-{
- return ATH79_MISC_IRQ(5);
-}
-EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
-
unsigned int get_c0_compare_int(void)
{
return CP0_LEGACY_COMPARE_IRQ;
diff --git a/arch/mips/configs/generic/board-ocelot.config b/arch/mips/configs/generic/board-ocelot.config
index f607888d2483..184eb65a6ba7 100644
--- a/arch/mips/configs/generic/board-ocelot.config
+++ b/arch/mips/configs/generic/board-ocelot.config
@@ -1,6 +1,10 @@
# require CONFIG_CPU_MIPS32_R2=y
CONFIG_LEGACY_BOARD_OCELOT=y
+CONFIG_FIT_IMAGE_FDT_OCELOT=y
+
+CONFIG_BRIDGE=y
+CONFIG_GENERIC_PHY=y
CONFIG_MTD=y
CONFIG_MTD_CMDLINE_PARTS=y
@@ -19,6 +23,8 @@ CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_NETDEVICES=y
+CONFIG_NET_SWITCHDEV=y
+CONFIG_NET_DSA=y
CONFIG_MSCC_OCELOT_SWITCH=y
CONFIG_MSCC_OCELOT_SWITCH_OCELOT=y
CONFIG_MDIO_MSCC_MIIM=y
@@ -35,6 +41,8 @@ CONFIG_SPI_DESIGNWARE=y
CONFIG_SPI_DW_MMIO=y
CONFIG_SPI_SPIDEV=y
+CONFIG_PINCTRL_OCELOT=y
+
CONFIG_GPIO_SYSFS=y
CONFIG_POWER_RESET=y
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index 6cf8ffb5367e..a2b4748655df 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -116,9 +116,10 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
+ unsigned int i = 0;
+ unsigned int n = 6;
int ret;
/* O32 ABI syscall() */
diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c
index 6e574c02e4c3..ea781b29f7f1 100644
--- a/arch/mips/kernel/kgdb.c
+++ b/arch/mips/kernel/kgdb.c
@@ -33,6 +33,7 @@
#include <asm/processor.h>
#include <asm/sigcontext.h>
#include <linux/uaccess.h>
+#include <asm/irq_regs.h>
static struct hard_trap_info {
unsigned char tt; /* Trap type code for MIPS R3xxx and R4xxx */
@@ -214,7 +215,7 @@ void kgdb_call_nmi_hook(void *ignored)
old_fs = get_fs();
set_fs(KERNEL_DS);
- kgdb_nmicallback(raw_smp_processor_id(), NULL);
+ kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs());
set_fs(old_fs);
}
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 0057c910bc2f..3a62f80958e1 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -1419,7 +1419,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
sd.nr = syscall;
sd.arch = syscall_get_arch();
- syscall_get_arguments(current, regs, 0, 6, args);
+ syscall_get_arguments(current, regs, args);
for (i = 0; i < 6; i++)
sd.args[i] = args[i];
sd.instruction_pointer = KSTK_EIP(current);
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index f158c5894a9a..feb2653490df 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -125,7 +125,7 @@ trace_a_syscall:
subu t1, v0, __NR_O32_Linux
move a1, v0
bnez t1, 1f /* __NR_syscall at offset 0 */
- lw a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
+ ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
.set pop
1: jal syscall_trace_enter
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 15f4117900ee..9392dfe33f97 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -362,3 +362,7 @@
421 n32 rt_sigtimedwait_time64 compat_sys_rt_sigtimedwait_time64
422 n32 futex_time64 sys_futex
423 n32 sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 n32 pidfd_send_signal sys_pidfd_send_signal
+425 n32 io_uring_setup sys_io_uring_setup
+426 n32 io_uring_enter sys_io_uring_enter
+427 n32 io_uring_register sys_io_uring_register
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index c85502e67b44..cd0c8aa21fba 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -338,3 +338,7 @@
327 n64 rseq sys_rseq
328 n64 io_pgetevents sys_io_pgetevents
# 329 through 423 are reserved to sync up with other architectures
+424 n64 pidfd_send_signal sys_pidfd_send_signal
+425 n64 io_uring_setup sys_io_uring_setup
+426 n64 io_uring_enter sys_io_uring_enter
+427 n64 io_uring_register sys_io_uring_register
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 2e063d0f837e..e849e8ffe4a2 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -411,3 +411,7 @@
421 o32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
422 o32 futex_time64 sys_futex sys_futex
423 o32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
+424 o32 pidfd_send_signal sys_pidfd_send_signal
+425 o32 io_uring_setup sys_io_uring_setup
+426 o32 io_uring_enter sys_io_uring_enter
+427 o32 io_uring_register sys_io_uring_register
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 0effd3cba9a7..98bf0c222b5f 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -186,8 +186,9 @@ enum which_ebpf_reg {
* separate frame pointer, so BPF_REG_10 relative accesses are
* adjusted to be $sp relative.
*/
-int ebpf_to_mips_reg(struct jit_ctx *ctx, const struct bpf_insn *insn,
- enum which_ebpf_reg w)
+static int ebpf_to_mips_reg(struct jit_ctx *ctx,
+ const struct bpf_insn *insn,
+ enum which_ebpf_reg w)
{
int ebpf_reg = (w == src_reg || w == src_reg_no_fp) ?
insn->src_reg : insn->dst_reg;
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index 710a59764b01..a32f843cdbe0 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -118,7 +118,6 @@ static void shutdown_bridge_irq(struct irq_data *d)
{
struct hub_irq_data *hd = irq_data_get_irq_chip_data(d);
struct bridge_controller *bc;
- int pin = hd->pin;
if (!hd)
return;
@@ -126,7 +125,7 @@ static void shutdown_bridge_irq(struct irq_data *d)
disable_hub_irq(d);
bc = hd->bc;
- bridge_clr(bc, b_int_enable, (1 << pin));
+ bridge_clr(bc, b_int_enable, (1 << hd->pin));
bridge_read(bc, b_wid_tflush);
}
diff --git a/arch/nds32/include/asm/syscall.h b/arch/nds32/include/asm/syscall.h
index f7e5e86765fe..671ebd357496 100644
--- a/arch/nds32/include/asm/syscall.h
+++ b/arch/nds32/include/asm/syscall.h
@@ -108,81 +108,41 @@ void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
* syscall_get_arguments - extract system call parameter values
* @task: task of interest, must be blocked
* @regs: task_pt_regs() of @task
- * @i: argument index [0,5]
- * @n: number of arguments; n+i must be [1,6].
* @args: array filled with argument values
*
- * Fetches @n arguments to the system call starting with the @i'th argument
- * (from 0 through 5). Argument @i is stored in @args[0], and so on.
- * An arch inline version is probably optimal when @i and @n are constants.
+ * Fetches 6 arguments to the system call (from 0 through 5). The first
+ * argument is stored in @args[0], and so on.
*
* It's only valid to call this when @task is stopped for tracing on
* entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
- * It's invalid to call this with @i + @n > 6; we only support system calls
- * taking up to 6 arguments.
*/
#define SYSCALL_MAX_ARGS 6
void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
- if (n == 0)
- return;
- if (i + n > SYSCALL_MAX_ARGS) {
- unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
- unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
- pr_warning("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- memset(args_bad, 0, n_bad * sizeof(args[0]));
- memset(args_bad, 0, n_bad * sizeof(args[0]));
- }
-
- if (i == 0) {
- args[0] = regs->orig_r0;
- args++;
- i++;
- n--;
- }
-
- memcpy(args, &regs->uregs[0] + i, n * sizeof(args[0]));
+ args[0] = regs->orig_r0;
+ args++;
+ memcpy(args, &regs->uregs[0] + 1, 5 * sizeof(args[0]));
}
/**
* syscall_set_arguments - change system call parameter value
* @task: task of interest, must be in system call entry tracing
* @regs: task_pt_regs() of @task
- * @i: argument index [0,5]
- * @n: number of arguments; n+i must be [1,6].
* @args: array of argument values to store
*
- * Changes @n arguments to the system call starting with the @i'th argument.
- * Argument @i gets value @args[0], and so on.
- * An arch inline version is probably optimal when @i and @n are constants.
+ * Changes 6 arguments to the system call. The first argument gets value
+ * @args[0], and so on.
*
* It's only valid to call this when @task is stopped for tracing on
* entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
- * It's invalid to call this with @i + @n > 6; we only support system calls
- * taking up to 6 arguments.
*/
void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- pr_warn("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- n = SYSCALL_MAX_ARGS - i;
- }
-
- if (i == 0) {
- regs->orig_r0 = args[0];
- args++;
- i++;
- n--;
- }
+ regs->orig_r0 = args[0];
+ args++;
- memcpy(&regs->uregs[0] + i, args, n * sizeof(args[0]));
+ memcpy(&regs->uregs[0] + 1, args, 5 * sizeof(args[0]));
}
#endif /* _ASM_NDS32_SYSCALL_H */
diff --git a/arch/nios2/include/asm/syscall.h b/arch/nios2/include/asm/syscall.h
index 9de220854c4a..d7624ed06efb 100644
--- a/arch/nios2/include/asm/syscall.h
+++ b/arch/nios2/include/asm/syscall.h
@@ -58,81 +58,25 @@ static inline void syscall_set_return_value(struct task_struct *task,
}
static inline void syscall_get_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i, unsigned int n,
- unsigned long *args)
+ struct pt_regs *regs, unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- switch (i) {
- case 0:
- if (!n--)
- break;
- *args++ = regs->r4;
- case 1:
- if (!n--)
- break;
- *args++ = regs->r5;
- case 2:
- if (!n--)
- break;
- *args++ = regs->r6;
- case 3:
- if (!n--)
- break;
- *args++ = regs->r7;
- case 4:
- if (!n--)
- break;
- *args++ = regs->r8;
- case 5:
- if (!n--)
- break;
- *args++ = regs->r9;
- case 6:
- if (!n--)
- break;
- default:
- BUG();
- }
+ *args++ = regs->r4;
+ *args++ = regs->r5;
+ *args++ = regs->r6;
+ *args++ = regs->r7;
+ *args++ = regs->r8;
+ *args = regs->r9;
}
static inline void syscall_set_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i, unsigned int n,
- const unsigned long *args)
+ struct pt_regs *regs, const unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- switch (i) {
- case 0:
- if (!n--)
- break;
- regs->r4 = *args++;
- case 1:
- if (!n--)
- break;
- regs->r5 = *args++;
- case 2:
- if (!n--)
- break;
- regs->r6 = *args++;
- case 3:
- if (!n--)
- break;
- regs->r7 = *args++;
- case 4:
- if (!n--)
- break;
- regs->r8 = *args++;
- case 5:
- if (!n--)
- break;
- regs->r9 = *args++;
- case 6:
- if (!n)
- break;
- default:
- BUG();
- }
+ regs->r4 = *args++;
+ regs->r5 = *args++;
+ regs->r6 = *args++;
+ regs->r7 = *args++;
+ regs->r8 = *args++;
+ regs->r9 = *args;
}
#endif
diff --git a/arch/openrisc/include/asm/syscall.h b/arch/openrisc/include/asm/syscall.h
index 2db9f1cf0694..b4ff07c1baed 100644
--- a/arch/openrisc/include/asm/syscall.h
+++ b/arch/openrisc/include/asm/syscall.h
@@ -56,20 +56,16 @@ syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
static inline void
syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- memcpy(args, &regs->gpr[3 + i], n * sizeof(args[0]));
+ memcpy(args, &regs->gpr[3], 6 * sizeof(args[0]));
}
static inline void
syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, const unsigned long *args)
+ const unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- memcpy(&regs->gpr[3 + i], args, n * sizeof(args[0]));
+ memcpy(&regs->gpr[3], args, 6 * sizeof(args[0]));
}
static inline int syscall_get_arch(void)
diff --git a/arch/parisc/include/asm/ptrace.h b/arch/parisc/include/asm/ptrace.h
index 2a27b275ab09..9ff033d261ab 100644
--- a/arch/parisc/include/asm/ptrace.h
+++ b/arch/parisc/include/asm/ptrace.h
@@ -22,13 +22,14 @@ unsigned long profile_pc(struct pt_regs *);
static inline unsigned long regs_return_value(struct pt_regs *regs)
{
- return regs->gr[20];
+ return regs->gr[28];
}
static inline void instruction_pointer_set(struct pt_regs *regs,
unsigned long val)
{
- regs->iaoq[0] = val;
+ regs->iaoq[0] = val;
+ regs->iaoq[1] = val + 4;
}
/* Query offset/name of register from its name/offset */
diff --git a/arch/parisc/include/asm/syscall.h b/arch/parisc/include/asm/syscall.h
index 8bff1a58c97f..62a6d477fae0 100644
--- a/arch/parisc/include/asm/syscall.h
+++ b/arch/parisc/include/asm/syscall.h
@@ -18,29 +18,15 @@ static inline long syscall_get_nr(struct task_struct *tsk,
}
static inline void syscall_get_arguments(struct task_struct *tsk,
- struct pt_regs *regs, unsigned int i,
- unsigned int n, unsigned long *args)
+ struct pt_regs *regs,
+ unsigned long *args)
{
- BUG_ON(i);
-
- switch (n) {
- case 6:
- args[5] = regs->gr[21];
- case 5:
- args[4] = regs->gr[22];
- case 4:
- args[3] = regs->gr[23];
- case 3:
- args[2] = regs->gr[24];
- case 2:
- args[1] = regs->gr[25];
- case 1:
- args[0] = regs->gr[26];
- case 0:
- break;
- default:
- BUG();
- }
+ args[5] = regs->gr[21];
+ args[4] = regs->gr[22];
+ args[3] = regs->gr[23];
+ args[2] = regs->gr[24];
+ args[1] = regs->gr[25];
+ args[0] = regs->gr[26];
}
static inline long syscall_get_return_value(struct task_struct *task,
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index eb39e7e380d7..841db71958cd 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -210,12 +210,6 @@ void __cpuidle arch_cpu_idle(void)
static int __init parisc_idle_init(void)
{
- const char *marker;
-
- /* check QEMU/SeaBIOS marker in PAGE0 */
- marker = (char *) &PAGE0->pad0;
- running_on_qemu = (memcmp(marker, "SeaBIOS", 8) == 0);
-
if (!running_on_qemu)
cpu_idle_poll_ctrl(1);
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 15dd9e21be7e..d908058d05c1 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -397,6 +397,9 @@ void __init start_parisc(void)
int ret, cpunum;
struct pdc_coproc_cfg coproc_cfg;
+ /* check QEMU/SeaBIOS marker in PAGE0 */
+ running_on_qemu = (memcmp(&PAGE0->pad0, "SeaBIOS", 8) == 0);
+
cpunum = smp_processor_id();
init_cpu_topology();
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index b26766c6647d..fe8ca623add8 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -420,3 +420,7 @@
421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
422 32 futex_time64 sys_futex sys_futex
423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index 5ba131c30f6b..1bcd468ab422 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -266,6 +266,7 @@ CONFIG_UDF_FS=m
CONFIG_MSDOS_FS=m
CONFIG_VFAT_FS=m
CONFIG_PROC_KCORE=y
+CONFIG_HUGETLBFS=y
# CONFIG_MISC_FILESYSTEMS is not set
# CONFIG_NETWORK_FILESYSTEMS is not set
CONFIG_NLS=y
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 598cdcdd1355..8ddd4a91bdc1 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -352,7 +352,7 @@ static inline bool strict_kernel_rwx_enabled(void)
#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) && \
defined (CONFIG_PPC_64K_PAGES)
#define MAX_PHYSMEM_BITS 51
-#elif defined(CONFIG_SPARSEMEM)
+#elif defined(CONFIG_PPC64)
#define MAX_PHYSMEM_BITS 46
#endif
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index 1a0e7a8b1c81..1243045bad2d 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -65,22 +65,20 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
unsigned long val, mask = -1UL;
-
- BUG_ON(i + n > 6);
+ unsigned int n = 6;
#ifdef CONFIG_COMPAT
if (test_tsk_thread_flag(task, TIF_32BIT))
mask = 0xffffffff;
#endif
while (n--) {
- if (n == 0 && i == 0)
+ if (n == 0)
val = regs->orig_gpr3;
else
- val = regs->gpr[3 + i + n];
+ val = regs->gpr[3 + n];
args[n] = val & mask;
}
@@ -88,15 +86,12 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(&regs->gpr[3 + i], args, n * sizeof(args[0]));
+ memcpy(&regs->gpr[3], args, 6 * sizeof(args[0]));
/* Also copy the first argument into orig_gpr3 */
- if (i == 0 && n > 0)
- regs->orig_gpr3 = args[0];
+ regs->orig_gpr3 = args[0];
}
static inline int syscall_get_arch(void)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index a5b8fbae56a0..9481a117e242 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -656,11 +656,17 @@ EXC_COMMON_BEGIN(data_access_slb_common)
ld r4,PACA_EXSLB+EX_DAR(r13)
std r4,_DAR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
+BEGIN_MMU_FTR_SECTION
+ /* HPT case, do SLB fault */
bl do_slb_fault
cmpdi r3,0
bne- 1f
b fast_exception_return
1: /* Error case */
+MMU_FTR_SECTION_ELSE
+ /* Radix case, access is outside page table range */
+ li r3,-EFAULT
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
@@ -705,11 +711,17 @@ EXC_COMMON_BEGIN(instruction_access_slb_common)
EXCEPTION_PROLOG_COMMON(0x480, PACA_EXSLB)
ld r4,_NIP(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
+BEGIN_MMU_FTR_SECTION
+ /* HPT case, do SLB fault */
bl do_slb_fault
cmpdi r3,0
bne- 1f
b fast_exception_return
1: /* Error case */
+MMU_FTR_SECTION_ELSE
+ /* Radix case, access is outside page table range */
+ li r3,-EFAULT
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 48051c8977c5..e25b615e9f9e 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -851,10 +851,6 @@ __secondary_start:
tophys(r4,r2)
addi r4,r4,THREAD /* phys address of our thread_struct */
mtspr SPRN_SPRG_THREAD,r4
-#ifdef CONFIG_PPC_RTAS
- li r3,0
- stw r3, RTAS_SP(r4) /* 0 => not in RTAS */
-#endif
lis r4, (swapper_pg_dir - PAGE_OFFSET)@h
ori r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l
mtspr SPRN_SPRG_PGDIR, r4
@@ -941,10 +937,6 @@ start_here:
tophys(r4,r2)
addi r4,r4,THREAD /* init task's THREAD */
mtspr SPRN_SPRG_THREAD,r4
-#ifdef CONFIG_PPC_RTAS
- li r3,0
- stw r3, RTAS_SP(r4) /* 0 => not in RTAS */
-#endif
lis r4, (swapper_pg_dir - PAGE_OFFSET)@h
ori r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l
mtspr SPRN_SPRG_PGDIR, r4
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 683b5b3805bd..cd381e2291df 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -22,6 +22,7 @@
#include <linux/kvm_host.h>
#include <linux/init.h>
#include <linux/export.h>
+#include <linux/kmemleak.h>
#include <linux/kvm_para.h>
#include <linux/slab.h>
#include <linux/of.h>
@@ -712,6 +713,12 @@ static void kvm_use_magic_page(void)
static __init void kvm_free_tmp(void)
{
+ /*
+ * Inform kmemleak about the hole in the .bss section since the
+ * corresponding pages will be unmapped with DEBUG_PAGEALLOC=y.
+ */
+ kmemleak_free_part(&kvm_tmp[kvm_tmp_index],
+ ARRAY_SIZE(kvm_tmp) - kvm_tmp_index);
free_reserved_area(&kvm_tmp[kvm_tmp_index],
&kvm_tmp[ARRAY_SIZE(kvm_tmp)], -1, NULL);
}
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index b18abb0c3dae..00f5a63c8d9a 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -505,3 +505,7 @@
421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
422 32 futex_time64 sys_futex sys_futex
423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 1e0bc5955a40..afd516b572f8 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -98,7 +98,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
* can be used, r7 contains NSEC_PER_SEC.
*/
- lwz r5,WTOM_CLOCK_SEC(r9)
+ lwz r5,(WTOM_CLOCK_SEC+LOPART)(r9)
lwz r6,WTOM_CLOCK_NSEC(r9)
/* We now have our offset in r5,r6. We create a fake dependency
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index f02b04973710..f100e331e69b 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -543,14 +543,14 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
if (ret != H_SUCCESS)
return ret;
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
+
ret = kvmppc_tce_validate(stt, tce);
if (ret != H_SUCCESS)
- return ret;
+ goto unlock_exit;
dir = iommu_tce_direction(tce);
- idx = srcu_read_lock(&vcpu->kvm->srcu);
-
if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) {
ret = H_PARAMETER;
goto unlock_exit;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 06964350b97a..b2b29d4f9842 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3423,7 +3423,9 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2);
vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3);
- mtspr(SPRN_PSSCR, host_psscr);
+ /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */
+ mtspr(SPRN_PSSCR, host_psscr |
+ (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
mtspr(SPRN_HFSCR, host_hfscr);
mtspr(SPRN_CIABR, host_ciabr);
mtspr(SPRN_DAWR, host_dawr);
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index e7a9c4f6bfca..8330f135294f 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -95,28 +95,15 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
unsigned long entries, unsigned long dev_hpa,
struct mm_iommu_table_group_mem_t **pmem)
{
- struct mm_iommu_table_group_mem_t *mem;
- long i, ret, locked_entries = 0;
+ struct mm_iommu_table_group_mem_t *mem, *mem2;
+ long i, ret, locked_entries = 0, pinned = 0;
unsigned int pageshift;
-
- mutex_lock(&mem_list_mutex);
-
- list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list,
- next) {
- /* Overlap? */
- if ((mem->ua < (ua + (entries << PAGE_SHIFT))) &&
- (ua < (mem->ua +
- (mem->entries << PAGE_SHIFT)))) {
- ret = -EINVAL;
- goto unlock_exit;
- }
-
- }
+ unsigned long entry, chunk;
if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
ret = mm_iommu_adjust_locked_vm(mm, entries, true);
if (ret)
- goto unlock_exit;
+ return ret;
locked_entries = entries;
}
@@ -148,17 +135,27 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
}
down_read(&mm->mmap_sem);
- ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL);
+ chunk = (1UL << (PAGE_SHIFT + MAX_ORDER - 1)) /
+ sizeof(struct vm_area_struct *);
+ chunk = min(chunk, entries);
+ for (entry = 0; entry < entries; entry += chunk) {
+ unsigned long n = min(entries - entry, chunk);
+
+ ret = get_user_pages_longterm(ua + (entry << PAGE_SHIFT), n,
+ FOLL_WRITE, mem->hpages + entry, NULL);
+ if (ret == n) {
+ pinned += n;
+ continue;
+ }
+ if (ret > 0)
+ pinned += ret;
+ break;
+ }
up_read(&mm->mmap_sem);
- if (ret != entries) {
- /* free the reference taken */
- for (i = 0; i < ret; i++)
- put_page(mem->hpages[i]);
-
- vfree(mem->hpas);
- kfree(mem);
- ret = -EFAULT;
- goto unlock_exit;
+ if (pinned != entries) {
+ if (!ret)
+ ret = -EFAULT;
+ goto free_exit;
}
pageshift = PAGE_SHIFT;
@@ -183,21 +180,43 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
}
good_exit:
- ret = 0;
atomic64_set(&mem->mapped, 1);
mem->used = 1;
mem->ua = ua;
mem->entries = entries;
- *pmem = mem;
- list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
+ mutex_lock(&mem_list_mutex);
-unlock_exit:
- if (locked_entries && ret)
- mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+ list_for_each_entry_rcu(mem2, &mm->context.iommu_group_mem_list, next) {
+ /* Overlap? */
+ if ((mem2->ua < (ua + (entries << PAGE_SHIFT))) &&
+ (ua < (mem2->ua +
+ (mem2->entries << PAGE_SHIFT)))) {
+ ret = -EINVAL;
+ mutex_unlock(&mem_list_mutex);
+ goto free_exit;
+ }
+ }
+
+ list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
mutex_unlock(&mem_list_mutex);
+ *pmem = mem;
+
+ return 0;
+
+free_exit:
+ /* free the reference taken */
+ for (i = 0; i < pinned; i++)
+ put_page(mem->hpages[i]);
+
+ vfree(mem->hpas);
+ kfree(mem);
+
+unlock_exit:
+ mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+
return ret;
}
@@ -266,7 +285,7 @@ static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem)
long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
{
long ret = 0;
- unsigned long entries, dev_hpa;
+ unsigned long unlock_entries = 0;
mutex_lock(&mem_list_mutex);
@@ -287,17 +306,17 @@ long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
goto unlock_exit;
}
+ if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
+ unlock_entries = mem->entries;
+
/* @mapped became 0 so now mappings are disabled, release the region */
- entries = mem->entries;
- dev_hpa = mem->dev_hpa;
mm_iommu_release(mem);
- if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
- mm_iommu_adjust_locked_vm(mm, entries, false);
-
unlock_exit:
mutex_unlock(&mem_list_mutex);
+ mm_iommu_adjust_locked_vm(mm, unlock_entries, false);
+
return ret;
}
EXPORT_SYMBOL_GPL(mm_iommu_put);
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index f29d2f118b44..5d9c3ff728c9 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -98,10 +98,20 @@ static int find_free_bat(void)
return -1;
}
+/*
+ * This function calculates the size of the larger block usable to map the
+ * beginning of an area based on the start address and size of that area:
+ * - max block size is 8M on 601 and 256 on other 6xx.
+ * - base address must be aligned to the block size. So the maximum block size
+ * is identified by the lowest bit set to 1 in the base address (for instance
+ * if base is 0x16000000, max size is 0x02000000).
+ * - block size has to be a power of two. This is calculated by finding the
+ * highest bit set to 1.
+ */
static unsigned int block_size(unsigned long base, unsigned long top)
{
unsigned int max_size = (cpu_has_feature(CPU_FTR_601) ? 8 : 256) << 20;
- unsigned int base_shift = (fls(base) - 1) & 31;
+ unsigned int base_shift = (ffs(base) - 1) & 31;
unsigned int block_shift = (fls(top - base) - 1) & 31;
return min3(max_size, 1U << base_shift, 1U << block_shift);
@@ -157,7 +167,7 @@ static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long to
unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
{
- int done;
+ unsigned long done;
unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET;
if (__map_without_bats) {
@@ -169,10 +179,10 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
return __mmu_mapin_ram(base, top);
done = __mmu_mapin_ram(base, border);
- if (done != border - base)
+ if (done != border)
return done;
- return done + __mmu_mapin_ram(border, top);
+ return __mmu_mapin_ram(border, top);
}
void mmu_mark_initmem_nx(void)
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 842b2c7e156a..50cd09b4e05d 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -324,7 +324,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
config PPC_RADIX_MMU
bool "Radix MMU Support"
- depends on PPC_BOOK3S_64
+ depends on PPC_BOOK3S_64 && HUGETLB_PAGE
select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
default y
help
diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig
new file mode 100644
index 000000000000..1a911ed8e772
--- /dev/null
+++ b/arch/riscv/configs/rv32_defconfig
@@ -0,0 +1,84 @@
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CFS_BANDWIDTH=y
+CONFIG_CGROUP_BPF=y
+CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
+CONFIG_CHECKPOINT_RESTORE=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_ARCH_RV32I=y
+CONFIG_SMP=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NETLINK_DIAG=y
+CONFIG_PCI=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCIE_XILINX=y
+CONFIG_DEVTMPFS=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_NETDEVICES=y
+CONFIG_VIRTIO_NET=y
+CONFIG_MACB=y
+CONFIG_E1000E=y
+CONFIG_R8169=y
+CONFIG_MICROSEMI_PHY=y
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
+CONFIG_HVC_RISCV_SBI=y
+# CONFIG_PTP_1588_CLOCK is not set
+CONFIG_DRM=y
+CONFIG_DRM_RADEON=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_USB=y
+CONFIG_USB_XHCI_HCD=y
+CONFIG_USB_XHCI_PLATFORM=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_UAS=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_SIFIVE_PLIC=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_NFS_V4_2=y
+CONFIG_ROOT_NFS=y
+CONFIG_CRYPTO_USER_API_HASH=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
+CONFIG_PRINTK_TIME=y
+# CONFIG_RCU_TRACE is not set
diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h
index 57afe604b495..c207f6634b91 100644
--- a/arch/riscv/include/asm/fixmap.h
+++ b/arch/riscv/include/asm/fixmap.h
@@ -26,7 +26,7 @@ enum fixed_addresses {
};
#define FIXADDR_SIZE (__end_of_fixed_addresses * PAGE_SIZE)
-#define FIXADDR_TOP (PAGE_OFFSET)
+#define FIXADDR_TOP (VMALLOC_START)
#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE)
#define FIXMAP_PAGE_IO PAGE_KERNEL
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
index bba3da6ef157..a3d5273ded7c 100644
--- a/arch/riscv/include/asm/syscall.h
+++ b/arch/riscv/include/asm/syscall.h
@@ -72,32 +72,20 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
- if (i == 0) {
- args[0] = regs->orig_a0;
- args++;
- i++;
- n--;
- }
- memcpy(args, &regs->a1 + i * sizeof(regs->a1), n * sizeof(args[0]));
+ args[0] = regs->orig_a0;
+ args++;
+ memcpy(args, &regs->a1, 5 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- BUG_ON(i + n > 6);
- if (i == 0) {
- regs->orig_a0 = args[0];
- args++;
- i++;
- n--;
- }
- memcpy(&regs->a1 + i * sizeof(regs->a1), args, n * sizeof(regs->a0));
+ regs->orig_a0 = args[0];
+ args++;
+ memcpy(&regs->a1, args, 5 * sizeof(regs->a1));
}
static inline int syscall_get_arch(void)
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index a00168b980d2..fb53a8089e76 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -300,7 +300,7 @@ do { \
" .balign 4\n" \
"4:\n" \
" li %0, %6\n" \
- " jump 2b, %1\n" \
+ " jump 3b, %1\n" \
" .previous\n" \
" .section __ex_table,\"a\"\n" \
" .balign " RISCV_SZPTR "\n" \
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index f13f7f276639..598568168d35 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -4,7 +4,6 @@
ifdef CONFIG_FTRACE
CFLAGS_REMOVE_ftrace.o = -pg
-CFLAGS_REMOVE_setup.o = -pg
endif
extra-y += head.o
@@ -29,8 +28,6 @@ obj-y += vdso.o
obj-y += cacheinfo.o
obj-y += vdso/
-CFLAGS_setup.o := -mcmodel=medany
-
obj-$(CONFIG_FPU) += fpu.o
obj-$(CONFIG_SMP) += smpboot.o
obj-$(CONFIG_SMP) += smp.o
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 7dd308129b40..2872edce894d 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -141,7 +141,7 @@ static int apply_r_riscv_hi20_rela(struct module *me, u32 *location,
{
s32 hi20;
- if (IS_ENABLED(CMODEL_MEDLOW)) {
+ if (IS_ENABLED(CONFIG_CMODEL_MEDLOW)) {
pr_err(
"%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
me->name, (long long)v, location);
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index ecb654f6a79e..540a331d1376 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -48,14 +48,6 @@ struct screen_info screen_info = {
};
#endif
-unsigned long va_pa_offset;
-EXPORT_SYMBOL(va_pa_offset);
-unsigned long pfn_base;
-EXPORT_SYMBOL(pfn_base);
-
-unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
-EXPORT_SYMBOL(empty_zero_page);
-
/* The lucky hart to first increment this variable will boot the other cores */
atomic_t hart_lottery;
unsigned long boot_cpu_hartid;
diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index eb22ab49b3e0..b68aac701803 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -1,3 +1,9 @@
+
+CFLAGS_init.o := -mcmodel=medany
+ifdef CONFIG_FTRACE
+CFLAGS_REMOVE_init.o = -pg
+endif
+
obj-y += init.o
obj-y += fault.o
obj-y += extable.o
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index b379a75ac6a6..bc7b77e34d09 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -25,6 +25,10 @@
#include <asm/pgtable.h>
#include <asm/io.h>
+unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
+ __page_aligned_bss;
+EXPORT_SYMBOL(empty_zero_page);
+
static void __init zone_sizes_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };
@@ -117,6 +121,14 @@ void __init setup_bootmem(void)
*/
memblock_reserve(reg->base, vmlinux_end - reg->base);
mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET);
+
+ /*
+ * Remove memblock from the end of usable area to the
+ * end of region
+ */
+ if (reg->base + mem_size < end)
+ memblock_remove(reg->base + mem_size,
+ end - reg->base - mem_size);
}
}
BUG_ON(mem_size == 0);
@@ -143,6 +155,11 @@ void __init setup_bootmem(void)
}
}
+unsigned long va_pa_offset;
+EXPORT_SYMBOL(va_pa_offset);
+unsigned long pfn_base;
+EXPORT_SYMBOL(pfn_base);
+
pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
pgd_t trampoline_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
@@ -172,6 +189,25 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
}
}
+/*
+ * setup_vm() is called from head.S with MMU-off.
+ *
+ * Following requirements should be honoured for setup_vm() to work
+ * correctly:
+ * 1) It should use PC-relative addressing for accessing kernel symbols.
+ * To achieve this we always use GCC cmodel=medany.
+ * 2) The compiler instrumentation for FTRACE will not work for setup_vm()
+ * so disable compiler instrumentation when FTRACE is enabled.
+ *
+ * Currently, the above requirements are honoured by using custom CFLAGS
+ * for init.o in mm/Makefile.
+ */
+
+#ifndef __riscv_cmodel_medany
+#error "setup_vm() is called from head.S before relocate so it should "
+ "not use absolute addressing."
+#endif
+
asmlinkage void __init setup_vm(void)
{
extern char _start;
diff --git a/arch/s390/boot/mem_detect.c b/arch/s390/boot/mem_detect.c
index 4cb771ba13fa..5d316fe40480 100644
--- a/arch/s390/boot/mem_detect.c
+++ b/arch/s390/boot/mem_detect.c
@@ -25,7 +25,7 @@ static void *mem_detect_alloc_extended(void)
{
unsigned long offset = ALIGN(mem_safe_offset(), sizeof(u64));
- if (IS_ENABLED(BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE &&
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE &&
INITRD_START < offset + ENTRIES_EXTENDED_MAX)
offset = ALIGN(INITRD_START + INITRD_SIZE, sizeof(u64));
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 96f9a9151fde..59c3e91f2cdb 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -56,40 +56,32 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
unsigned long mask = -1UL;
+ unsigned int n = 6;
- /*
- * No arguments for this syscall, there's nothing to do.
- */
- if (!n)
- return;
-
- BUG_ON(i + n > 6);
#ifdef CONFIG_COMPAT
if (test_tsk_thread_flag(task, TIF_31BIT))
mask = 0xffffffff;
#endif
while (n-- > 0)
- if (i + n > 0)
- args[n] = regs->gprs[2 + i + n] & mask;
- if (i == 0)
- args[0] = regs->orig_gpr2 & mask;
+ if (n > 0)
+ args[n] = regs->gprs[2 + n] & mask;
+
+ args[0] = regs->orig_gpr2 & mask;
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- BUG_ON(i + n > 6);
+ unsigned int n = 6;
+
while (n-- > 0)
- if (i + n > 0)
- regs->gprs[2 + i + n] = args[n];
- if (i == 0)
- regs->orig_gpr2 = args[0];
+ if (n > 0)
+ regs->gprs[2 + n] = args[n];
+ regs->orig_gpr2 = args[0];
}
static inline int syscall_get_arch(void)
diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c
index 594464f2129d..0da378e2eb25 100644
--- a/arch/s390/kernel/fpu.c
+++ b/arch/s390/kernel/fpu.c
@@ -23,7 +23,7 @@ void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags)
if (flags & KERNEL_FPC)
/* Save floating point control */
- asm volatile("stfpc %0" : "=m" (state->fpc));
+ asm volatile("stfpc %0" : "=Q" (state->fpc));
if (!MACHINE_HAS_VX) {
if (flags & KERNEL_VXR_V0V7) {
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 02579f95f391..061418f787c3 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -426,3 +426,7 @@
421 32 rt_sigtimedwait_time64 - compat_sys_rt_sigtimedwait_time64
422 32 futex_time64 - sys_futex
423 32 sched_rr_get_interval_time64 - sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register sys_io_uring_register
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index a69a0911ed0e..c475ca49cfc6 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -37,7 +37,7 @@ static inline u64 get_vtimer(void)
{
u64 timer;
- asm volatile("stpt %0" : "=m" (timer));
+ asm volatile("stpt %0" : "=Q" (timer));
return timer;
}
@@ -48,7 +48,7 @@ static inline void set_vtimer(u64 expires)
asm volatile(
" stpt %0\n" /* Store current cpu timer value */
" spt %1" /* Set new value imm. afterwards */
- : "=m" (timer) : "m" (expires));
+ : "=Q" (timer) : "Q" (expires));
S390_lowcore.system_timer += S390_lowcore.last_update_timer - timer;
S390_lowcore.last_update_timer = expires;
}
@@ -135,8 +135,8 @@ static int do_account_vtime(struct task_struct *tsk)
#else
" stck %1" /* Store current tod clock value */
#endif
- : "=m" (S390_lowcore.last_update_timer),
- "=m" (S390_lowcore.last_update_clock));
+ : "=Q" (S390_lowcore.last_update_timer),
+ "=Q" (S390_lowcore.last_update_clock));
clock = S390_lowcore.last_update_clock - clock;
timer -= S390_lowcore.last_update_timer;
diff --git a/arch/sh/boards/of-generic.c b/arch/sh/boards/of-generic.c
index 958f46da3a79..d91065e81a4e 100644
--- a/arch/sh/boards/of-generic.c
+++ b/arch/sh/boards/of-generic.c
@@ -164,10 +164,10 @@ static struct sh_machine_vector __initmv sh_of_generic_mv = {
struct sh_clk_ops;
-void __init arch_init_clk_ops(struct sh_clk_ops **ops, int idx)
+void __init __weak arch_init_clk_ops(struct sh_clk_ops **ops, int idx)
{
}
-void __init plat_irq_setup(void)
+void __init __weak plat_irq_setup(void)
{
}
diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h
index 6e118799831c..8c9d7e5e5dcc 100644
--- a/arch/sh/include/asm/syscall_32.h
+++ b/arch/sh/include/asm/syscall_32.h
@@ -48,51 +48,28 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- /*
- * Do this simply for now. If we need to start supporting
- * fetching arguments from arbitrary indices, this will need some
- * extra logic. Presently there are no in-tree users that depend
- * on this behaviour.
- */
- BUG_ON(i);
/* Argument pattern is: R4, R5, R6, R7, R0, R1 */
- switch (n) {
- case 6: args[5] = regs->regs[1];
- case 5: args[4] = regs->regs[0];
- case 4: args[3] = regs->regs[7];
- case 3: args[2] = regs->regs[6];
- case 2: args[1] = regs->regs[5];
- case 1: args[0] = regs->regs[4];
- case 0:
- break;
- default:
- BUG();
- }
+ args[5] = regs->regs[1];
+ args[4] = regs->regs[0];
+ args[3] = regs->regs[7];
+ args[2] = regs->regs[6];
+ args[1] = regs->regs[5];
+ args[0] = regs->regs[4];
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- /* Same note as above applies */
- BUG_ON(i);
-
- switch (n) {
- case 6: regs->regs[1] = args[5];
- case 5: regs->regs[0] = args[4];
- case 4: regs->regs[7] = args[3];
- case 3: regs->regs[6] = args[2];
- case 2: regs->regs[5] = args[1];
- case 1: regs->regs[4] = args[0];
- break;
- default:
- BUG();
- }
+ regs->regs[1] = args[5];
+ regs->regs[0] = args[4];
+ regs->regs[7] = args[3];
+ regs->regs[6] = args[2];
+ regs->regs[5] = args[1];
+ regs->regs[4] = args[0];
}
static inline int syscall_get_arch(void)
diff --git a/arch/sh/include/asm/syscall_64.h b/arch/sh/include/asm/syscall_64.h
index 43882580c7f9..22fad97da066 100644
--- a/arch/sh/include/asm/syscall_64.h
+++ b/arch/sh/include/asm/syscall_64.h
@@ -47,20 +47,16 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(args, &regs->regs[2 + i], n * sizeof(args[0]));
+ memcpy(args, &regs->regs[2], 6 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(&regs->regs[2 + i], args, n * sizeof(args[0]));
+ memcpy(&regs->regs[2], args, 6 * sizeof(args[0]));
}
static inline int syscall_get_arch(void)
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index bfda678576e4..480b057556ee 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -426,3 +426,7 @@
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/sparc/include/asm/syscall.h b/arch/sparc/include/asm/syscall.h
index 053989e3f6a6..4d075434e816 100644
--- a/arch/sparc/include/asm/syscall.h
+++ b/arch/sparc/include/asm/syscall.h
@@ -96,11 +96,11 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
int zero_extend = 0;
unsigned int j;
+ unsigned int n = 6;
#ifdef CONFIG_SPARC64
if (test_tsk_thread_flag(task, TIF_32BIT))
@@ -108,7 +108,7 @@ static inline void syscall_get_arguments(struct task_struct *task,
#endif
for (j = 0; j < n; j++) {
- unsigned long val = regs->u_regs[UREG_I0 + i + j];
+ unsigned long val = regs->u_regs[UREG_I0 + j];
if (zero_extend)
args[j] = (u32) val;
@@ -119,13 +119,12 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- unsigned int j;
+ unsigned int i;
- for (j = 0; j < n; j++)
- regs->u_regs[UREG_I0 + i + j] = args[j];
+ for (i = 0; i < 6; i++)
+ regs->u_regs[UREG_I0 + i] = args[i];
}
static inline int syscall_get_arch(void)
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index a8af6023c126..14b93c5564e3 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -73,6 +73,11 @@ static inline void iommu_batch_start(struct device *dev, unsigned long prot, uns
p->npages = 0;
}
+static inline bool iommu_use_atu(struct iommu *iommu, u64 mask)
+{
+ return iommu->atu && mask > DMA_BIT_MASK(32);
+}
+
/* Interrupts must be disabled. */
static long iommu_batch_flush(struct iommu_batch *p, u64 mask)
{
@@ -92,7 +97,7 @@ static long iommu_batch_flush(struct iommu_batch *p, u64 mask)
prot &= (HV_PCI_MAP_ATTR_READ | HV_PCI_MAP_ATTR_WRITE);
while (npages != 0) {
- if (mask <= DMA_BIT_MASK(32) || !pbm->iommu->atu) {
+ if (!iommu_use_atu(pbm->iommu, mask)) {
num = pci_sun4v_iommu_map(devhandle,
HV_PCI_TSBID(0, entry),
npages,
@@ -179,7 +184,6 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
unsigned long flags, order, first_page, npages, n;
unsigned long prot = 0;
struct iommu *iommu;
- struct atu *atu;
struct iommu_map_table *tbl;
struct page *page;
void *ret;
@@ -205,13 +209,11 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
memset((char *)first_page, 0, PAGE_SIZE << order);
iommu = dev->archdata.iommu;
- atu = iommu->atu;
-
mask = dev->coherent_dma_mask;
- if (mask <= DMA_BIT_MASK(32) || !atu)
+ if (!iommu_use_atu(iommu, mask))
tbl = &iommu->tbl;
else
- tbl = &atu->tbl;
+ tbl = &iommu->atu->tbl;
entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL,
(unsigned long)(-1), 0);
@@ -333,7 +335,7 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu,
atu = iommu->atu;
devhandle = pbm->devhandle;
- if (dvma <= DMA_BIT_MASK(32)) {
+ if (!iommu_use_atu(iommu, dvma)) {
tbl = &iommu->tbl;
iotsb_num = 0; /* we don't care for legacy iommu */
} else {
@@ -374,7 +376,7 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
npages >>= IO_PAGE_SHIFT;
mask = *dev->dma_mask;
- if (mask <= DMA_BIT_MASK(32))
+ if (!iommu_use_atu(iommu, mask))
tbl = &iommu->tbl;
else
tbl = &atu->tbl;
@@ -510,7 +512,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
mask = *dev->dma_mask;
- if (mask <= DMA_BIT_MASK(32))
+ if (!iommu_use_atu(iommu, mask))
tbl = &iommu->tbl;
else
tbl = &atu->tbl;
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index b9a5a04b2d2c..a1dd24307b00 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -469,3 +469,7 @@
421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
422 32 futex_time64 sys_futex sys_futex
423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/um/include/asm/syscall-generic.h b/arch/um/include/asm/syscall-generic.h
index 9fb9cf8cd39a..98e50c50c12e 100644
--- a/arch/um/include/asm/syscall-generic.h
+++ b/arch/um/include/asm/syscall-generic.h
@@ -53,84 +53,30 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
const struct uml_pt_regs *r = &regs->regs;
- switch (i) {
- case 0:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG1(r);
- case 1:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG2(r);
- case 2:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG3(r);
- case 3:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG4(r);
- case 4:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG5(r);
- case 5:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG6(r);
- case 6:
- if (!n--)
- break;
- default:
- BUG();
- break;
- }
+ *args++ = UPT_SYSCALL_ARG1(r);
+ *args++ = UPT_SYSCALL_ARG2(r);
+ *args++ = UPT_SYSCALL_ARG3(r);
+ *args++ = UPT_SYSCALL_ARG4(r);
+ *args++ = UPT_SYSCALL_ARG5(r);
+ *args = UPT_SYSCALL_ARG6(r);
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
struct uml_pt_regs *r = &regs->regs;
- switch (i) {
- case 0:
- if (!n--)
- break;
- UPT_SYSCALL_ARG1(r) = *args++;
- case 1:
- if (!n--)
- break;
- UPT_SYSCALL_ARG2(r) = *args++;
- case 2:
- if (!n--)
- break;
- UPT_SYSCALL_ARG3(r) = *args++;
- case 3:
- if (!n--)
- break;
- UPT_SYSCALL_ARG4(r) = *args++;
- case 4:
- if (!n--)
- break;
- UPT_SYSCALL_ARG5(r) = *args++;
- case 5:
- if (!n--)
- break;
- UPT_SYSCALL_ARG6(r) = *args++;
- case 6:
- if (!n--)
- break;
- default:
- BUG();
- break;
- }
+ UPT_SYSCALL_ARG1(r) = *args++;
+ UPT_SYSCALL_ARG2(r) = *args++;
+ UPT_SYSCALL_ARG3(r) = *args++;
+ UPT_SYSCALL_ARG4(r) = *args++;
+ UPT_SYSCALL_ARG5(r) = *args++;
+ UPT_SYSCALL_ARG6(r) = *args;
}
/* See arch/x86/um/asm/syscall.h for syscall_get_arch() definition. */
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b0f30d86c23f..406a0cf30c57 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1498,7 +1498,7 @@ config X86_CPA_STATISTICS
depends on DEBUG_FS
---help---
Expose statistics about the Change Page Attribute mechanims, which
- helps to determine the effectivness of preserving large and huge
+ helps to determine the effectiveness of preserving large and huge
page mappings when mapping protections are changed.
config ARCH_HAS_MEM_ENCRYPT
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index c0d6c560df69..5a237e8dbf8d 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -352,7 +352,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
boot_params->hdr.loadflags &= ~KASLR_FLAG;
/* Save RSDP address for later use. */
- boot_params->acpi_rsdp_addr = get_rsdp_addr();
+ /* boot_params->acpi_rsdp_addr = get_rsdp_addr(); */
sanitize_boot_params(boot_params);
diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S
index 3b6e70d085da..8457cdd47f75 100644
--- a/arch/x86/crypto/poly1305-avx2-x86_64.S
+++ b/arch/x86/crypto/poly1305-avx2-x86_64.S
@@ -323,6 +323,12 @@ ENTRY(poly1305_4block_avx2)
vpaddq t2,t1,t1
vmovq t1x,d4
+ # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 ->
+ # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small
+ # amount. Careful: we must not assume the carry bits 'd0 >> 26',
+ # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit
+ # integers. It's true in a single-block implementation, but not here.
+
# d1 += d0 >> 26
mov d0,%rax
shr $26,%rax
@@ -361,16 +367,16 @@ ENTRY(poly1305_4block_avx2)
# h0 += (d4 >> 26) * 5
mov d4,%rax
shr $26,%rax
- lea (%eax,%eax,4),%eax
- add %eax,%ebx
+ lea (%rax,%rax,4),%rax
+ add %rax,%rbx
# h4 = d4 & 0x3ffffff
mov d4,%rax
and $0x3ffffff,%eax
mov %eax,h4
# h1 += h0 >> 26
- mov %ebx,%eax
- shr $26,%eax
+ mov %rbx,%rax
+ shr $26,%rax
add %eax,h1
# h0 = h0 & 0x3ffffff
andl $0x3ffffff,%ebx
diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S
index e6add74d78a5..6f0be7a86964 100644
--- a/arch/x86/crypto/poly1305-sse2-x86_64.S
+++ b/arch/x86/crypto/poly1305-sse2-x86_64.S
@@ -253,16 +253,16 @@ ENTRY(poly1305_block_sse2)
# h0 += (d4 >> 26) * 5
mov d4,%rax
shr $26,%rax
- lea (%eax,%eax,4),%eax
- add %eax,%ebx
+ lea (%rax,%rax,4),%rax
+ add %rax,%rbx
# h4 = d4 & 0x3ffffff
mov d4,%rax
and $0x3ffffff,%eax
mov %eax,h4
# h1 += h0 >> 26
- mov %ebx,%eax
- shr $26,%eax
+ mov %rbx,%rax
+ shr $26,%rax
add %eax,h1
# h0 = h0 & 0x3ffffff
andl $0x3ffffff,%ebx
@@ -524,6 +524,12 @@ ENTRY(poly1305_2block_sse2)
paddq t2,t1
movq t1,d4
+ # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 ->
+ # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small
+ # amount. Careful: we must not assume the carry bits 'd0 >> 26',
+ # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit
+ # integers. It's true in a single-block implementation, but not here.
+
# d1 += d0 >> 26
mov d0,%rax
shr $26,%rax
@@ -562,16 +568,16 @@ ENTRY(poly1305_2block_sse2)
# h0 += (d4 >> 26) * 5
mov d4,%rax
shr $26,%rax
- lea (%eax,%eax,4),%eax
- add %eax,%ebx
+ lea (%rax,%rax,4),%rax
+ add %rax,%rbx
# h4 = d4 & 0x3ffffff
mov d4,%rax
and $0x3ffffff,%eax
mov %eax,h4
# h1 += h0 >> 26
- mov %ebx,%eax
- shr $26,%eax
+ mov %rbx,%rax
+ shr $26,%rax
add %eax,h1
# h0 = h0 & 0x3ffffff
andl $0x3ffffff,%ebx
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 007b3fe9d727..98c7d12b945c 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -29,12 +29,12 @@ extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz);
extern time_t __vdso_time(time_t *t);
#ifdef CONFIG_PARAVIRT_CLOCK
-extern u8 pvclock_page
+extern u8 pvclock_page[PAGE_SIZE]
__attribute__((visibility("hidden")));
#endif
#ifdef CONFIG_HYPERV_TSCPAGE
-extern u8 hvclock_page
+extern u8 hvclock_page[PAGE_SIZE]
__attribute__((visibility("hidden")));
#endif
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 7d2d7c801dba..f15441b07dad 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -3,10 +3,14 @@
#include <linux/types.h>
#include <linux/init.h>
#include <linux/slab.h>
+#include <linux/delay.h>
#include <asm/apicdef.h>
+#include <asm/nmi.h>
#include "../perf_event.h"
+static DEFINE_PER_CPU(unsigned int, perf_nmi_counter);
+
static __initconst const u64 amd_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -112,23 +116,144 @@ static __initconst const u64 amd_hw_cache_event_ids
},
};
+static __initconst const u64 amd_hw_cache_event_ids_f17h
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+[C(L1D)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x0040, /* Data Cache Accesses */
+ [C(RESULT_MISS)] = 0xc860, /* L2$ access from DC Miss */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0xff5a, /* h/w prefetch DC Fills */
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x0080, /* Instruction cache fetches */
+ [C(RESULT_MISS)] = 0x0081, /* Instruction cache misses */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(DTLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0xff45, /* All L2 DTLB accesses */
+ [C(RESULT_MISS)] = 0xf045, /* L2 DTLB misses (PT walks) */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x0084, /* L1 ITLB misses, L2 ITLB hits */
+ [C(RESULT_MISS)] = 0xff85, /* L1 ITLB misses, L2 misses */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+},
+[C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x00c2, /* Retired Branch Instr. */
+ [C(RESULT_MISS)] = 0x00c3, /* Retired Mispredicted BI */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+},
+[C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+},
+};
+
/*
- * AMD Performance Monitor K7 and later.
+ * AMD Performance Monitor K7 and later, up to and including Family 16h:
*/
static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
{
- [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
- [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x077e,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
- [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
- [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */
- [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x077e,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */
+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */
+};
+
+/*
+ * AMD Performance Monitor Family 17h and later:
+ */
+static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
+{
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287,
+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187,
};
static u64 amd_pmu_event_map(int hw_event)
{
+ if (boot_cpu_data.x86 >= 0x17)
+ return amd_f17h_perfmon_event_map[hw_event];
+
return amd_perfmon_event_map[hw_event];
}
@@ -429,6 +554,132 @@ static void amd_pmu_cpu_dead(int cpu)
}
}
+/*
+ * When a PMC counter overflows, an NMI is used to process the event and
+ * reset the counter. NMI latency can result in the counter being updated
+ * before the NMI can run, which can result in what appear to be spurious
+ * NMIs. This function is intended to wait for the NMI to run and reset
+ * the counter to avoid possible unhandled NMI messages.
+ */
+#define OVERFLOW_WAIT_COUNT 50
+
+static void amd_pmu_wait_on_overflow(int idx)
+{
+ unsigned int i;
+ u64 counter;
+
+ /*
+ * Wait for the counter to be reset if it has overflowed. This loop
+ * should exit very, very quickly, but just in case, don't wait
+ * forever...
+ */
+ for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) {
+ rdmsrl(x86_pmu_event_addr(idx), counter);
+ if (counter & (1ULL << (x86_pmu.cntval_bits - 1)))
+ break;
+
+ /* Might be in IRQ context, so can't sleep */
+ udelay(1);
+ }
+}
+
+static void amd_pmu_disable_all(void)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int idx;
+
+ x86_pmu_disable_all();
+
+ /*
+ * This shouldn't be called from NMI context, but add a safeguard here
+ * to return, since if we're in NMI context we can't wait for an NMI
+ * to reset an overflowed counter value.
+ */
+ if (in_nmi())
+ return;
+
+ /*
+ * Check each counter for overflow and wait for it to be reset by the
+ * NMI if it has overflowed. This relies on the fact that all active
+ * counters are always enabled when this function is caled and
+ * ARCH_PERFMON_EVENTSEL_INT is always set.
+ */
+ for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+
+ amd_pmu_wait_on_overflow(idx);
+ }
+}
+
+static void amd_pmu_disable_event(struct perf_event *event)
+{
+ x86_pmu_disable_event(event);
+
+ /*
+ * This can be called from NMI context (via x86_pmu_stop). The counter
+ * may have overflowed, but either way, we'll never see it get reset
+ * by the NMI if we're already in the NMI. And the NMI latency support
+ * below will take care of any pending NMI that might have been
+ * generated by the overflow.
+ */
+ if (in_nmi())
+ return;
+
+ amd_pmu_wait_on_overflow(event->hw.idx);
+}
+
+/*
+ * Because of NMI latency, if multiple PMC counters are active or other sources
+ * of NMIs are received, the perf NMI handler can handle one or more overflowed
+ * PMC counters outside of the NMI associated with the PMC overflow. If the NMI
+ * doesn't arrive at the LAPIC in time to become a pending NMI, then the kernel
+ * back-to-back NMI support won't be active. This PMC handler needs to take into
+ * account that this can occur, otherwise this could result in unknown NMI
+ * messages being issued. Examples of this is PMC overflow while in the NMI
+ * handler when multiple PMCs are active or PMC overflow while handling some
+ * other source of an NMI.
+ *
+ * Attempt to mitigate this by using the number of active PMCs to determine
+ * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset
+ * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the
+ * number of active PMCs or 2. The value of 2 is used in case an NMI does not
+ * arrive at the LAPIC in time to be collapsed into an already pending NMI.
+ */
+static int amd_pmu_handle_irq(struct pt_regs *regs)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int active, handled;
+
+ /*
+ * Obtain the active count before calling x86_pmu_handle_irq() since
+ * it is possible that x86_pmu_handle_irq() may make a counter
+ * inactive (through x86_pmu_stop).
+ */
+ active = __bitmap_weight(cpuc->active_mask, X86_PMC_IDX_MAX);
+
+ /* Process any counter overflows */
+ handled = x86_pmu_handle_irq(regs);
+
+ /*
+ * If a counter was handled, record the number of possible remaining
+ * NMIs that can occur.
+ */
+ if (handled) {
+ this_cpu_write(perf_nmi_counter,
+ min_t(unsigned int, 2, active));
+
+ return handled;
+ }
+
+ if (!this_cpu_read(perf_nmi_counter))
+ return NMI_DONE;
+
+ this_cpu_dec(perf_nmi_counter);
+
+ return NMI_HANDLED;
+}
+
static struct event_constraint *
amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
@@ -621,11 +872,11 @@ static ssize_t amd_event_sysfs_show(char *page, u64 config)
static __initconst const struct x86_pmu amd_pmu = {
.name = "AMD",
- .handle_irq = x86_pmu_handle_irq,
- .disable_all = x86_pmu_disable_all,
+ .handle_irq = amd_pmu_handle_irq,
+ .disable_all = amd_pmu_disable_all,
.enable_all = x86_pmu_enable_all,
.enable = x86_pmu_enable_event,
- .disable = x86_pmu_disable_event,
+ .disable = amd_pmu_disable_event,
.hw_config = amd_pmu_hw_config,
.schedule_events = x86_schedule_events,
.eventsel = MSR_K7_EVNTSEL0,
@@ -718,9 +969,10 @@ __init int amd_pmu_init(void)
x86_pmu.amd_nb_constraints = 0;
}
- /* Events are common for all AMDs */
- memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
- sizeof(hw_cache_event_ids));
+ if (boot_cpu_data.x86 >= 0x17)
+ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids_f17h, sizeof(hw_cache_event_ids));
+ else
+ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids));
return 0;
}
@@ -732,7 +984,7 @@ void amd_pmu_enable_virt(void)
cpuc->perf_ctr_virt_mask = 0;
/* Reload all events */
- x86_pmu_disable_all();
+ amd_pmu_disable_all();
x86_pmu_enable_all(0);
}
EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
@@ -750,7 +1002,7 @@ void amd_pmu_disable_virt(void)
cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
/* Reload all events */
- x86_pmu_disable_all();
+ amd_pmu_disable_all();
x86_pmu_enable_all(0);
}
EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index e2b1447192a8..81911e11a15d 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1349,8 +1349,9 @@ void x86_pmu_stop(struct perf_event *event, int flags)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
- if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
+ if (test_bit(hwc->idx, cpuc->active_mask)) {
x86_pmu.disable(event);
+ __clear_bit(hwc->idx, cpuc->active_mask);
cpuc->events[hwc->idx] = NULL;
WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
hwc->state |= PERF_HES_STOPPED;
@@ -1447,16 +1448,8 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
apic_write(APIC_LVTPC, APIC_DM_NMI);
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
- if (!test_bit(idx, cpuc->active_mask)) {
- /*
- * Though we deactivated the counter some cpus
- * might still deliver spurious interrupts still
- * in flight. Catch them:
- */
- if (__test_and_clear_bit(idx, cpuc->running))
- handled++;
+ if (!test_bit(idx, cpuc->active_mask))
continue;
- }
event = cpuc->events[idx];
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 8baa441d8000..d35f4775d5f1 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2091,15 +2091,19 @@ static void intel_pmu_disable_event(struct perf_event *event)
cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
cpuc->intel_cp_status &= ~(1ull << hwc->idx);
- if (unlikely(event->attr.precise_ip))
- intel_pmu_pebs_disable(event);
-
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_disable_fixed(hwc);
return;
}
x86_pmu_disable_event(event);
+
+ /*
+ * Needs to be called after x86_pmu_disable_event,
+ * so we don't trigger the event without PEBS bit set.
+ */
+ if (unlikely(event->attr.precise_ip))
+ intel_pmu_pebs_disable(event);
}
static void intel_pmu_del_event(struct perf_event *event)
@@ -3131,7 +3135,7 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
flags &= ~PERF_SAMPLE_TIME;
if (!event->attr.exclude_kernel)
flags &= ~PERF_SAMPLE_REGS_USER;
- if (event->attr.sample_regs_user & ~PEBS_REGS)
+ if (event->attr.sample_regs_user & ~PEBS_GP_REGS)
flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR);
return flags;
}
@@ -3185,7 +3189,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
return ret;
if (event->attr.precise_ip) {
- if (!event->attr.freq) {
+ if (!(event->attr.freq || event->attr.wakeup_events)) {
event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
if (!(event->attr.sample_type &
~intel_pmu_large_pebs_flags(event)))
@@ -3575,6 +3579,12 @@ static void intel_pmu_cpu_starting(int cpu)
cpuc->lbr_sel = NULL;
+ if (x86_pmu.flags & PMU_FL_TFA) {
+ WARN_ON_ONCE(cpuc->tfa_shadow);
+ cpuc->tfa_shadow = ~0ULL;
+ intel_set_tfa(cpuc, false);
+ }
+
if (x86_pmu.version > 1)
flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 94a4b7fc75d0..d41de9af7a39 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -76,15 +76,15 @@
* Scope: Package (physical package)
* MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter.
* perf code: 0x04
- * Available model: HSW ULT,CNL
+ * Available model: HSW ULT,KBL,CNL
* Scope: Package (physical package)
* MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter.
* perf code: 0x05
- * Available model: HSW ULT,CNL
+ * Available model: HSW ULT,KBL,CNL
* Scope: Package (physical package)
* MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
* perf code: 0x06
- * Available model: HSW ULT,GLM,CNL
+ * Available model: HSW ULT,KBL,GLM,CNL
* Scope: Package (physical package)
*
*/
@@ -566,8 +566,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, hswult_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, hswult_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_MOBILE, cnl_cstates),
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index fb3a2f13fc70..339d7628080c 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1525,8 +1525,7 @@ static __init int pt_init(void)
}
if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
- pt_pmu.pmu.capabilities =
- PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF;
+ pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG;
pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE;
pt_pmu.pmu.attr_groups = pt_attr_groups;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index a75955741c50..1e98a42b560a 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -96,25 +96,25 @@ struct amd_nb {
PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
PERF_SAMPLE_PERIOD)
-#define PEBS_REGS \
- (PERF_REG_X86_AX | \
- PERF_REG_X86_BX | \
- PERF_REG_X86_CX | \
- PERF_REG_X86_DX | \
- PERF_REG_X86_DI | \
- PERF_REG_X86_SI | \
- PERF_REG_X86_SP | \
- PERF_REG_X86_BP | \
- PERF_REG_X86_IP | \
- PERF_REG_X86_FLAGS | \
- PERF_REG_X86_R8 | \
- PERF_REG_X86_R9 | \
- PERF_REG_X86_R10 | \
- PERF_REG_X86_R11 | \
- PERF_REG_X86_R12 | \
- PERF_REG_X86_R13 | \
- PERF_REG_X86_R14 | \
- PERF_REG_X86_R15)
+#define PEBS_GP_REGS \
+ ((1ULL << PERF_REG_X86_AX) | \
+ (1ULL << PERF_REG_X86_BX) | \
+ (1ULL << PERF_REG_X86_CX) | \
+ (1ULL << PERF_REG_X86_DX) | \
+ (1ULL << PERF_REG_X86_DI) | \
+ (1ULL << PERF_REG_X86_SI) | \
+ (1ULL << PERF_REG_X86_SP) | \
+ (1ULL << PERF_REG_X86_BP) | \
+ (1ULL << PERF_REG_X86_IP) | \
+ (1ULL << PERF_REG_X86_FLAGS) | \
+ (1ULL << PERF_REG_X86_R8) | \
+ (1ULL << PERF_REG_X86_R9) | \
+ (1ULL << PERF_REG_X86_R10) | \
+ (1ULL << PERF_REG_X86_R11) | \
+ (1ULL << PERF_REG_X86_R12) | \
+ (1ULL << PERF_REG_X86_R13) | \
+ (1ULL << PERF_REG_X86_R14) | \
+ (1ULL << PERF_REG_X86_R15))
/*
* Per register state.
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index d153d570bb04..8e790ec219a5 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -36,16 +36,17 @@
* bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
*/
-#define BITOP_ADDR(x) "+m" (*(volatile long *) (x))
+#define RLONG_ADDR(x) "m" (*(volatile long *) (x))
+#define WBYTE_ADDR(x) "+m" (*(volatile char *) (x))
-#define ADDR BITOP_ADDR(addr)
+#define ADDR RLONG_ADDR(addr)
/*
* We do the locked ops that don't return the old value as
* a mask operation on a byte.
*/
#define IS_IMMEDIATE(nr) (__builtin_constant_p(nr))
-#define CONST_MASK_ADDR(nr, addr) BITOP_ADDR((void *)(addr) + ((nr)>>3))
+#define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3))
#define CONST_MASK(nr) (1 << ((nr) & 7))
/**
@@ -73,7 +74,7 @@ set_bit(long nr, volatile unsigned long *addr)
: "memory");
} else {
asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
- : BITOP_ADDR(addr) : "Ir" (nr) : "memory");
+ : : RLONG_ADDR(addr), "Ir" (nr) : "memory");
}
}
@@ -88,7 +89,7 @@ set_bit(long nr, volatile unsigned long *addr)
*/
static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
{
- asm volatile(__ASM_SIZE(bts) " %1,%0" : ADDR : "Ir" (nr) : "memory");
+ asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
/**
@@ -110,8 +111,7 @@ clear_bit(long nr, volatile unsigned long *addr)
: "iq" ((u8)~CONST_MASK(nr)));
} else {
asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
- : BITOP_ADDR(addr)
- : "Ir" (nr));
+ : : RLONG_ADDR(addr), "Ir" (nr) : "memory");
}
}
@@ -131,7 +131,7 @@ static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *ad
static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
{
- asm volatile(__ASM_SIZE(btr) " %1,%0" : ADDR : "Ir" (nr));
+ asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
@@ -139,7 +139,7 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile
bool negative;
asm volatile(LOCK_PREFIX "andb %2,%1"
CC_SET(s)
- : CC_OUT(s) (negative), ADDR
+ : CC_OUT(s) (negative), WBYTE_ADDR(addr)
: "ir" ((char) ~(1 << nr)) : "memory");
return negative;
}
@@ -155,13 +155,9 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile
* __clear_bit() is non-atomic and implies release semantics before the memory
* operation. It can be used for an unlock if no other CPUs can concurrently
* modify other bits in the word.
- *
- * No memory barrier is required here, because x86 cannot reorder stores past
- * older loads. Same principle as spin_unlock.
*/
static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
{
- barrier();
__clear_bit(nr, addr);
}
@@ -176,7 +172,7 @@ static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *
*/
static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
{
- asm volatile(__ASM_SIZE(btc) " %1,%0" : ADDR : "Ir" (nr));
+ asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
/**
@@ -196,8 +192,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
: "iq" ((u8)CONST_MASK(nr)));
} else {
asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
- : BITOP_ADDR(addr)
- : "Ir" (nr));
+ : : RLONG_ADDR(addr), "Ir" (nr) : "memory");
}
}
@@ -242,8 +237,8 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
asm(__ASM_SIZE(bts) " %2,%1"
CC_SET(c)
- : CC_OUT(c) (oldbit), ADDR
- : "Ir" (nr));
+ : CC_OUT(c) (oldbit)
+ : ADDR, "Ir" (nr) : "memory");
return oldbit;
}
@@ -282,8 +277,8 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long
asm volatile(__ASM_SIZE(btr) " %2,%1"
CC_SET(c)
- : CC_OUT(c) (oldbit), ADDR
- : "Ir" (nr));
+ : CC_OUT(c) (oldbit)
+ : ADDR, "Ir" (nr) : "memory");
return oldbit;
}
@@ -294,8 +289,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
asm volatile(__ASM_SIZE(btc) " %2,%1"
CC_SET(c)
- : CC_OUT(c) (oldbit), ADDR
- : "Ir" (nr) : "memory");
+ : CC_OUT(c) (oldbit)
+ : ADDR, "Ir" (nr) : "memory");
return oldbit;
}
@@ -326,7 +321,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l
asm volatile(__ASM_SIZE(bt) " %2,%1"
CC_SET(c)
: CC_OUT(c) (oldbit)
- : "m" (*(unsigned long *)addr), "Ir" (nr));
+ : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory");
return oldbit;
}
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 93c4bf598fb0..feab24cac610 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -226,7 +226,9 @@ struct x86_emulate_ops {
unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags);
- int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, u64 smbase);
+ int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt,
+ const char *smstate);
+ void (*post_leave_smm)(struct x86_emulate_ctxt *ctxt);
};
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 159b5988292f..c79abe7ca093 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -126,7 +126,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
}
#define KVM_PERMILLE_MMU_PAGES 20
-#define KVM_MIN_ALLOC_MMU_PAGES 64
+#define KVM_MIN_ALLOC_MMU_PAGES 64UL
#define KVM_MMU_HASH_SHIFT 12
#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
#define KVM_MIN_FREE_MMU_PAGES 5
@@ -295,6 +295,7 @@ union kvm_mmu_extended_role {
unsigned int valid:1;
unsigned int execonly:1;
unsigned int cr0_pg:1;
+ unsigned int cr4_pae:1;
unsigned int cr4_pse:1;
unsigned int cr4_pke:1;
unsigned int cr4_smap:1;
@@ -844,9 +845,9 @@ enum kvm_irqchip_mode {
};
struct kvm_arch {
- unsigned int n_used_mmu_pages;
- unsigned int n_requested_mmu_pages;
- unsigned int n_max_mmu_pages;
+ unsigned long n_used_mmu_pages;
+ unsigned long n_requested_mmu_pages;
+ unsigned long n_max_mmu_pages;
unsigned int indirect_shadow_pages;
struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
/*
@@ -1182,7 +1183,7 @@ struct kvm_x86_ops {
int (*smi_allowed)(struct kvm_vcpu *vcpu);
int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
- int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase);
+ int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
int (*enable_smi_window)(struct kvm_vcpu *vcpu);
int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
@@ -1256,8 +1257,8 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
gfn_t gfn_offset, unsigned long mask);
void kvm_mmu_zap_all(struct kvm *kvm);
void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
-unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages);
int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
bool pdptrs_changed(struct kvm_vcpu *vcpu);
@@ -1592,4 +1593,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
#define put_smstate(type, buf, offset, val) \
*(type *)((buf) + (offset) - 0x7e00) = val
+#define GET_SMSTATE(type, buf, offset) \
+ (*(type *)((buf) + (offset) - 0x7e00))
+
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 2779ace16d23..50b3e2d963c9 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -46,7 +46,7 @@ void ptdump_walk_user_pgd_level_checkwx(void);
*/
extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
__visible;
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+#define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page))
extern spinlock_t pgd_lock;
extern struct list_head pgd_list;
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index d653139857af..4c305471ec33 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -91,11 +91,9 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(args, &regs->bx + i, n * sizeof(args[0]));
+ memcpy(args, &regs->bx, 6 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
@@ -116,124 +114,50 @@ static inline int syscall_get_arch(void)
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
# ifdef CONFIG_IA32_EMULATION
- if (task->thread_info.status & TS_COMPAT)
- switch (i) {
- case 0:
- if (!n--) break;
- *args++ = regs->bx;
- case 1:
- if (!n--) break;
- *args++ = regs->cx;
- case 2:
- if (!n--) break;
- *args++ = regs->dx;
- case 3:
- if (!n--) break;
- *args++ = regs->si;
- case 4:
- if (!n--) break;
- *args++ = regs->di;
- case 5:
- if (!n--) break;
- *args++ = regs->bp;
- case 6:
- if (!n--) break;
- default:
- BUG();
- break;
- }
- else
+ if (task->thread_info.status & TS_COMPAT) {
+ *args++ = regs->bx;
+ *args++ = regs->cx;
+ *args++ = regs->dx;
+ *args++ = regs->si;
+ *args++ = regs->di;
+ *args = regs->bp;
+ } else
# endif
- switch (i) {
- case 0:
- if (!n--) break;
- *args++ = regs->di;
- case 1:
- if (!n--) break;
- *args++ = regs->si;
- case 2:
- if (!n--) break;
- *args++ = regs->dx;
- case 3:
- if (!n--) break;
- *args++ = regs->r10;
- case 4:
- if (!n--) break;
- *args++ = regs->r8;
- case 5:
- if (!n--) break;
- *args++ = regs->r9;
- case 6:
- if (!n--) break;
- default:
- BUG();
- break;
- }
+ {
+ *args++ = regs->di;
+ *args++ = regs->si;
+ *args++ = regs->dx;
+ *args++ = regs->r10;
+ *args++ = regs->r8;
+ *args = regs->r9;
+ }
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
# ifdef CONFIG_IA32_EMULATION
- if (task->thread_info.status & TS_COMPAT)
- switch (i) {
- case 0:
- if (!n--) break;
- regs->bx = *args++;
- case 1:
- if (!n--) break;
- regs->cx = *args++;
- case 2:
- if (!n--) break;
- regs->dx = *args++;
- case 3:
- if (!n--) break;
- regs->si = *args++;
- case 4:
- if (!n--) break;
- regs->di = *args++;
- case 5:
- if (!n--) break;
- regs->bp = *args++;
- case 6:
- if (!n--) break;
- default:
- BUG();
- break;
- }
- else
+ if (task->thread_info.status & TS_COMPAT) {
+ regs->bx = *args++;
+ regs->cx = *args++;
+ regs->dx = *args++;
+ regs->si = *args++;
+ regs->di = *args++;
+ regs->bp = *args;
+ } else
# endif
- switch (i) {
- case 0:
- if (!n--) break;
- regs->di = *args++;
- case 1:
- if (!n--) break;
- regs->si = *args++;
- case 2:
- if (!n--) break;
- regs->dx = *args++;
- case 3:
- if (!n--) break;
- regs->r10 = *args++;
- case 4:
- if (!n--) break;
- regs->r8 = *args++;
- case 5:
- if (!n--) break;
- regs->r9 = *args++;
- case 6:
- if (!n--) break;
- default:
- BUG();
- break;
- }
+ {
+ regs->di = *args++;
+ regs->si = *args++;
+ regs->dx = *args++;
+ regs->r10 = *args++;
+ regs->r8 = *args++;
+ regs->r9 = *args;
+ }
}
static inline int syscall_get_arch(void)
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index de6f0d59a24f..2863c2026655 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -206,6 +206,9 @@ xen_single_call(unsigned int call,
__HYPERCALL_DECLS;
__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
+ if (call >= PAGE_SIZE / sizeof(hypercall_page[0]))
+ return -EINVAL;
+
asm volatile(CALL_NOSPEC
: __HYPERCALL_5PARAM
: [thunk_target] "a" (&hypercall_page[call])
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index dabfcf7c3941..7a0e64ccd6ff 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -381,6 +381,7 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1)
#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2)
+#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3)
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index f0b0c90dd398..d213ec5c3766 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -146,6 +146,7 @@
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
+#define VMX_ABORT_VMCS_CORRUPTED 3
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
#endif /* _UAPIVMX_H */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 2da82eff0eb4..b91b3bfa5cfb 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -275,7 +275,7 @@ static const struct {
const char *option;
enum spectre_v2_user_cmd cmd;
bool secure;
-} v2_user_options[] __initdata = {
+} v2_user_options[] __initconst = {
{ "auto", SPECTRE_V2_USER_CMD_AUTO, false },
{ "off", SPECTRE_V2_USER_CMD_NONE, false },
{ "on", SPECTRE_V2_USER_CMD_FORCE, true },
@@ -419,7 +419,7 @@ static const struct {
const char *option;
enum spectre_v2_mitigation_cmd cmd;
bool secure;
-} mitigation_options[] __initdata = {
+} mitigation_options[] __initconst = {
{ "off", SPECTRE_V2_CMD_NONE, false },
{ "on", SPECTRE_V2_CMD_FORCE, true },
{ "retpoline", SPECTRE_V2_CMD_RETPOLINE, false },
@@ -658,7 +658,7 @@ static const char * const ssb_strings[] = {
static const struct {
const char *option;
enum ssb_mitigation_cmd cmd;
-} ssb_mitigation_options[] __initdata = {
+} ssb_mitigation_options[] __initconst = {
{ "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */
{ "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */
{ "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fc3c07fe7df5..3142fd7a9b32 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -611,8 +611,8 @@ static void init_intel_energy_perf(struct cpuinfo_x86 *c)
if ((epb & 0xF) != ENERGY_PERF_BIAS_PERFORMANCE)
return;
- pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
- pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n");
+ pr_info_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
+ pr_info_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n");
epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL;
wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
}
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 399601eda8e4..85212a32b54d 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2039,14 +2039,14 @@ out:
enum rdt_param {
Opt_cdp,
Opt_cdpl2,
- Opt_mba_mpbs,
+ Opt_mba_mbps,
nr__rdt_params
};
static const struct fs_parameter_spec rdt_param_specs[] = {
fsparam_flag("cdp", Opt_cdp),
fsparam_flag("cdpl2", Opt_cdpl2),
- fsparam_flag("mba_mpbs", Opt_mba_mpbs),
+ fsparam_flag("mba_MBps", Opt_mba_mbps),
{}
};
@@ -2072,7 +2072,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
case Opt_cdpl2:
ctx->enable_cdpl2 = true;
return 0;
- case Opt_mba_mpbs:
+ case Opt_mba_mbps:
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return -EINVAL;
ctx->enable_mba_mbps = true;
@@ -2610,9 +2610,10 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
rdt_last_cmd_puts("Failed to initialize allocations\n");
return ret;
}
- rdtgrp->mode = RDT_MODE_SHAREABLE;
}
+ rdtgrp->mode = RDT_MODE_SHAREABLE;
+
return 0;
}
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index a034cb808e7e..fed46ddb1eef 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -569,6 +569,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
unsigned long *sara = stack_addr(regs);
ri->ret_addr = (kprobe_opcode_t *) *sara;
+ ri->fp = sara;
/* Replace the return addr with trampoline addr */
*sara = (unsigned long) &kretprobe_trampoline;
@@ -748,26 +749,48 @@ asm(
NOKPROBE_SYMBOL(kretprobe_trampoline);
STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
+static struct kprobe kretprobe_kprobe = {
+ .addr = (void *)kretprobe_trampoline,
+};
+
/*
* Called from kretprobe_trampoline
*/
static __used void *trampoline_handler(struct pt_regs *regs)
{
+ struct kprobe_ctlblk *kcb;
struct kretprobe_instance *ri = NULL;
struct hlist_head *head, empty_rp;
struct hlist_node *tmp;
unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
kprobe_opcode_t *correct_ret_addr = NULL;
+ void *frame_pointer;
+ bool skipped = false;
+
+ preempt_disable();
+
+ /*
+ * Set a dummy kprobe for avoiding kretprobe recursion.
+ * Since kretprobe never run in kprobe handler, kprobe must not
+ * be running at this point.
+ */
+ kcb = get_kprobe_ctlblk();
+ __this_cpu_write(current_kprobe, &kretprobe_kprobe);
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
INIT_HLIST_HEAD(&empty_rp);
kretprobe_hash_lock(current, &head, &flags);
/* fixup registers */
#ifdef CONFIG_X86_64
regs->cs = __KERNEL_CS;
+ /* On x86-64, we use pt_regs->sp for return address holder. */
+ frame_pointer = &regs->sp;
#else
regs->cs = __KERNEL_CS | get_kernel_rpl();
regs->gs = 0;
+ /* On x86-32, we use pt_regs->flags for return address holder. */
+ frame_pointer = &regs->flags;
#endif
regs->ip = trampoline_address;
regs->orig_ax = ~0UL;
@@ -789,8 +812,25 @@ static __used void *trampoline_handler(struct pt_regs *regs)
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
+ /*
+ * Return probes must be pushed on this hash list correct
+ * order (same as return order) so that it can be poped
+ * correctly. However, if we find it is pushed it incorrect
+ * order, this means we find a function which should not be
+ * probed, because the wrong order entry is pushed on the
+ * path of processing other kretprobe itself.
+ */
+ if (ri->fp != frame_pointer) {
+ if (!skipped)
+ pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
+ skipped = true;
+ continue;
+ }
orig_ret_address = (unsigned long)ri->ret_addr;
+ if (skipped)
+ pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
+ ri->rp->kp.addr);
if (orig_ret_address != trampoline_address)
/*
@@ -808,14 +848,15 @@ static __used void *trampoline_handler(struct pt_regs *regs)
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
+ if (ri->fp != frame_pointer)
+ continue;
orig_ret_address = (unsigned long)ri->ret_addr;
if (ri->rp && ri->rp->handler) {
__this_cpu_write(current_kprobe, &ri->rp->kp);
- get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
ri->ret_addr = correct_ret_addr;
ri->rp->handler(ri, regs);
- __this_cpu_write(current_kprobe, NULL);
+ __this_cpu_write(current_kprobe, &kretprobe_kprobe);
}
recycle_rp_inst(ri, &empty_rp);
@@ -831,6 +872,9 @@ static __used void *trampoline_handler(struct pt_regs *regs)
kretprobe_hash_unlock(current, &flags);
+ __this_cpu_write(current_kprobe, NULL);
+ preempt_enable();
+
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
kfree(ri);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 58ac7be52c7a..957eae13b370 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -426,6 +426,8 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp,
u64 msr = x86_spec_ctrl_base;
bool updmsr = false;
+ lockdep_assert_irqs_disabled();
+
/*
* If TIF_SSBD is different, select the proper mitigation
* method. Note that if SSBD mitigation is disabled or permanentely
@@ -477,10 +479,12 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk)
void speculation_ctrl_update(unsigned long tif)
{
+ unsigned long flags;
+
/* Forced update. Make sure all relevant TIF flags are different */
- preempt_disable();
+ local_irq_save(flags);
__speculation_ctrl_update(~tif, tif);
- preempt_enable();
+ local_irq_restore(flags);
}
/* Called from seccomp/prctl update */
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 725624b6c0c0..8fd3cedd9acc 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -81,6 +81,19 @@ static int __init set_bios_reboot(const struct dmi_system_id *d)
return 0;
}
+/*
+ * Some machines don't handle the default ACPI reboot method and
+ * require the EFI reboot method:
+ */
+static int __init set_efi_reboot(const struct dmi_system_id *d)
+{
+ if (reboot_type != BOOT_EFI && !efi_runtime_disabled()) {
+ reboot_type = BOOT_EFI;
+ pr_info("%s series board detected. Selecting EFI-method for reboot.\n", d->ident);
+ }
+ return 0;
+}
+
void __noreturn machine_real_restart(unsigned int type)
{
local_irq_disable();
@@ -166,6 +179,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = {
DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"),
},
},
+ { /* Handle reboot issue on Acer TravelMate X514-51T */
+ .callback = set_efi_reboot,
+ .ident = "Acer TravelMate X514-51T",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate X514-51T"),
+ },
+ },
/* Apple */
{ /* Handle problems with rebooting on Apple MacBook5 */
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index bad8c51fee6e..a5127b2c195f 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -362,7 +362,7 @@ SECTIONS
.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
__bss_start = .;
*(.bss..page_aligned)
- *(.bss)
+ *(BSS_MAIN)
BSS_DECRYPTED
. = ALIGN(PAGE_SIZE);
__bss_stop = .;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index c338984c850d..d0d5dd44b4f4 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2331,24 +2331,18 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt)
static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
{
+#ifdef CONFIG_X86_64
u32 eax, ebx, ecx, edx;
eax = 0x80000001;
ecx = 0;
ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
return edx & bit(X86_FEATURE_LM);
+#else
+ return false;
+#endif
}
-#define GET_SMSTATE(type, smbase, offset) \
- ({ \
- type __val; \
- int r = ctxt->ops->read_phys(ctxt, smbase + offset, &__val, \
- sizeof(__val)); \
- if (r != X86EMUL_CONTINUE) \
- return X86EMUL_UNHANDLEABLE; \
- __val; \
- })
-
static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
{
desc->g = (flags >> 23) & 1;
@@ -2361,27 +2355,30 @@ static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
desc->type = (flags >> 8) & 15;
}
-static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate,
+ int n)
{
struct desc_struct desc;
int offset;
u16 selector;
- selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4);
+ selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4);
if (n < 3)
offset = 0x7f84 + n * 12;
else
offset = 0x7f2c + (n - 3) * 12;
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
return X86EMUL_CONTINUE;
}
-static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+#ifdef CONFIG_X86_64
+static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate,
+ int n)
{
struct desc_struct desc;
int offset;
@@ -2390,15 +2387,16 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
offset = 0x7e00 + n * 16;
- selector = GET_SMSTATE(u16, smbase, offset);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8));
- base3 = GET_SMSTATE(u32, smbase, offset + 12);
+ selector = GET_SMSTATE(u16, smstate, offset);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
+ base3 = GET_SMSTATE(u32, smstate, offset + 12);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
return X86EMUL_CONTINUE;
}
+#endif
static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
u64 cr0, u64 cr3, u64 cr4)
@@ -2445,7 +2443,8 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
return X86EMUL_CONTINUE;
}
-static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
{
struct desc_struct desc;
struct desc_ptr dt;
@@ -2453,53 +2452,55 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
u32 val, cr0, cr3, cr4;
int i;
- cr0 = GET_SMSTATE(u32, smbase, 0x7ffc);
- cr3 = GET_SMSTATE(u32, smbase, 0x7ff8);
- ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
- ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0);
+ cr0 = GET_SMSTATE(u32, smstate, 0x7ffc);
+ cr3 = GET_SMSTATE(u32, smstate, 0x7ff8);
+ ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
+ ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0);
for (i = 0; i < 8; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4);
+ *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
- val = GET_SMSTATE(u32, smbase, 0x7fcc);
+ val = GET_SMSTATE(u32, smstate, 0x7fcc);
ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
- val = GET_SMSTATE(u32, smbase, 0x7fc8);
+ val = GET_SMSTATE(u32, smstate, 0x7fc8);
ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
- selector = GET_SMSTATE(u32, smbase, 0x7fc4);
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f64));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f60));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f5c));
+ selector = GET_SMSTATE(u32, smstate, 0x7fc4);
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f60));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f5c));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
- selector = GET_SMSTATE(u32, smbase, 0x7fc0);
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f80));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f7c));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f78));
+ selector = GET_SMSTATE(u32, smstate, 0x7fc0);
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f80));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f7c));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f78));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
- dt.address = GET_SMSTATE(u32, smbase, 0x7f74);
- dt.size = GET_SMSTATE(u32, smbase, 0x7f70);
+ dt.address = GET_SMSTATE(u32, smstate, 0x7f74);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7f70);
ctxt->ops->set_gdt(ctxt, &dt);
- dt.address = GET_SMSTATE(u32, smbase, 0x7f58);
- dt.size = GET_SMSTATE(u32, smbase, 0x7f54);
+ dt.address = GET_SMSTATE(u32, smstate, 0x7f58);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7f54);
ctxt->ops->set_idt(ctxt, &dt);
for (i = 0; i < 6; i++) {
- int r = rsm_load_seg_32(ctxt, smbase, i);
+ int r = rsm_load_seg_32(ctxt, smstate, i);
if (r != X86EMUL_CONTINUE)
return r;
}
- cr4 = GET_SMSTATE(u32, smbase, 0x7f14);
+ cr4 = GET_SMSTATE(u32, smstate, 0x7f14);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
+ ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8));
return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
}
-static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
+#ifdef CONFIG_X86_64
+static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
{
struct desc_struct desc;
struct desc_ptr dt;
@@ -2509,43 +2510,43 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
int i, r;
for (i = 0; i < 16; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8);
+ *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
- ctxt->_eip = GET_SMSTATE(u64, smbase, 0x7f78);
- ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED;
+ ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78);
+ ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
- val = GET_SMSTATE(u32, smbase, 0x7f68);
+ val = GET_SMSTATE(u32, smstate, 0x7f68);
ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
- val = GET_SMSTATE(u32, smbase, 0x7f60);
+ val = GET_SMSTATE(u32, smstate, 0x7f60);
ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
- cr0 = GET_SMSTATE(u64, smbase, 0x7f58);
- cr3 = GET_SMSTATE(u64, smbase, 0x7f50);
- cr4 = GET_SMSTATE(u64, smbase, 0x7f48);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
- val = GET_SMSTATE(u64, smbase, 0x7ed0);
+ cr0 = GET_SMSTATE(u64, smstate, 0x7f58);
+ cr3 = GET_SMSTATE(u64, smstate, 0x7f50);
+ cr4 = GET_SMSTATE(u64, smstate, 0x7f48);
+ ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
+ val = GET_SMSTATE(u64, smstate, 0x7ed0);
ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
- selector = GET_SMSTATE(u32, smbase, 0x7e90);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e92) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e94));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e98));
- base3 = GET_SMSTATE(u32, smbase, 0x7e9c);
+ selector = GET_SMSTATE(u32, smstate, 0x7e90);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e94));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e98));
+ base3 = GET_SMSTATE(u32, smstate, 0x7e9c);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
- dt.size = GET_SMSTATE(u32, smbase, 0x7e84);
- dt.address = GET_SMSTATE(u64, smbase, 0x7e88);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7e84);
+ dt.address = GET_SMSTATE(u64, smstate, 0x7e88);
ctxt->ops->set_idt(ctxt, &dt);
- selector = GET_SMSTATE(u32, smbase, 0x7e70);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e72) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e74));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e78));
- base3 = GET_SMSTATE(u32, smbase, 0x7e7c);
+ selector = GET_SMSTATE(u32, smstate, 0x7e70);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e72) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e74));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e78));
+ base3 = GET_SMSTATE(u32, smstate, 0x7e7c);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
- dt.size = GET_SMSTATE(u32, smbase, 0x7e64);
- dt.address = GET_SMSTATE(u64, smbase, 0x7e68);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7e64);
+ dt.address = GET_SMSTATE(u64, smstate, 0x7e68);
ctxt->ops->set_gdt(ctxt, &dt);
r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
@@ -2553,37 +2554,49 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
return r;
for (i = 0; i < 6; i++) {
- r = rsm_load_seg_64(ctxt, smbase, i);
+ r = rsm_load_seg_64(ctxt, smstate, i);
if (r != X86EMUL_CONTINUE)
return r;
}
return X86EMUL_CONTINUE;
}
+#endif
static int em_rsm(struct x86_emulate_ctxt *ctxt)
{
unsigned long cr0, cr4, efer;
+ char buf[512];
u64 smbase;
int ret;
if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
return emulate_ud(ctxt);
+ smbase = ctxt->ops->get_smbase(ctxt);
+
+ ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf));
+ if (ret != X86EMUL_CONTINUE)
+ return X86EMUL_UNHANDLEABLE;
+
+ if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+ ctxt->ops->set_nmi_mask(ctxt, false);
+
+ ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
+ ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
+
/*
* Get back to real mode, to prepare a safe state in which to load
* CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU
* supports long mode.
*/
- cr4 = ctxt->ops->get_cr(ctxt, 4);
if (emulator_has_longmode(ctxt)) {
struct desc_struct cs_desc;
/* Zero CR4.PCIDE before CR0.PG. */
- if (cr4 & X86_CR4_PCIDE) {
+ cr4 = ctxt->ops->get_cr(ctxt, 4);
+ if (cr4 & X86_CR4_PCIDE)
ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
- cr4 &= ~X86_CR4_PCIDE;
- }
/* A 32-bit code segment is required to clear EFER.LMA. */
memset(&cs_desc, 0, sizeof(cs_desc));
@@ -2597,39 +2610,39 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
if (cr0 & X86_CR0_PE)
ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
- /* Now clear CR4.PAE (which must be done before clearing EFER.LME). */
- if (cr4 & X86_CR4_PAE)
- ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
-
- /* And finally go back to 32-bit mode. */
- efer = 0;
- ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+ if (emulator_has_longmode(ctxt)) {
+ /* Clear CR4.PAE before clearing EFER.LME. */
+ cr4 = ctxt->ops->get_cr(ctxt, 4);
+ if (cr4 & X86_CR4_PAE)
+ ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
- smbase = ctxt->ops->get_smbase(ctxt);
+ /* And finally go back to 32-bit mode. */
+ efer = 0;
+ ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+ }
/*
* Give pre_leave_smm() a chance to make ISA-specific changes to the
* vCPU state (e.g. enter guest mode) before loading state from the SMM
* state-save area.
*/
- if (ctxt->ops->pre_leave_smm(ctxt, smbase))
+ if (ctxt->ops->pre_leave_smm(ctxt, buf))
return X86EMUL_UNHANDLEABLE;
+#ifdef CONFIG_X86_64
if (emulator_has_longmode(ctxt))
- ret = rsm_load_state_64(ctxt, smbase + 0x8000);
+ ret = rsm_load_state_64(ctxt, buf);
else
- ret = rsm_load_state_32(ctxt, smbase + 0x8000);
+#endif
+ ret = rsm_load_state_32(ctxt, buf);
if (ret != X86EMUL_CONTINUE) {
/* FIXME: should triple fault */
return X86EMUL_UNHANDLEABLE;
}
- if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
- ctxt->ops->set_nmi_mask(ctxt, false);
+ ctxt->ops->post_leave_smm(ctxt);
- ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
- ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
return X86EMUL_CONTINUE;
}
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 421899f6ad7b..cc24b3a32c44 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1371,7 +1371,16 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
valid_bank_mask = BIT_ULL(0);
sparse_banks[0] = flush.processor_mask;
- all_cpus = flush.flags & HV_FLUSH_ALL_PROCESSORS;
+
+ /*
+ * Work around possible WS2012 bug: it sends hypercalls
+ * with processor_mask = 0x0 and HV_FLUSH_ALL_PROCESSORS clear,
+ * while also expecting us to flush something and crashing if
+ * we don't. Let's treat processor_mask == 0 same as
+ * HV_FLUSH_ALL_PROCESSORS.
+ */
+ all_cpus = (flush.flags & HV_FLUSH_ALL_PROCESSORS) ||
+ flush.processor_mask == 0;
} else {
if (unlikely(kvm_read_guest(kvm, ingpa, &flush_ex,
sizeof(flush_ex))))
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 991fdf7fc17f..bd13fdddbdc4 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -70,7 +70,6 @@
#define APIC_BROADCAST 0xFF
#define X2APIC_BROADCAST 0xFFFFFFFFul
-static bool lapic_timer_advance_adjust_done = false;
#define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100
/* step-by-step approximation to mitigate fluctuation */
#define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
@@ -138,6 +137,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
if (offset <= max_apic_id) {
u8 cluster_size = min(max_apic_id - offset + 1, 16U);
+ offset = array_index_nospec(offset, map->max_apic_id + 1);
*cluster = &map->phys_map[offset];
*mask = dest_id & (0xffff >> (16 - cluster_size));
} else {
@@ -901,7 +901,8 @@ static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm,
if (irq->dest_id > map->max_apic_id) {
*bitmap = 0;
} else {
- *dst = &map->phys_map[irq->dest_id];
+ u32 dest_id = array_index_nospec(irq->dest_id, map->max_apic_id + 1);
+ *dst = &map->phys_map[dest_id];
*bitmap = 1;
}
return true;
@@ -1480,14 +1481,32 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu)
return false;
}
+static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles)
+{
+ u64 timer_advance_ns = vcpu->arch.apic->lapic_timer.timer_advance_ns;
+
+ /*
+ * If the guest TSC is running at a different ratio than the host, then
+ * convert the delay to nanoseconds to achieve an accurate delay. Note
+ * that __delay() uses delay_tsc whenever the hardware has TSC, thus
+ * always for VMX enabled hardware.
+ */
+ if (vcpu->arch.tsc_scaling_ratio == kvm_default_tsc_scaling_ratio) {
+ __delay(min(guest_cycles,
+ nsec_to_cycles(vcpu, timer_advance_ns)));
+ } else {
+ u64 delay_ns = guest_cycles * 1000000ULL;
+ do_div(delay_ns, vcpu->arch.virtual_tsc_khz);
+ ndelay(min_t(u32, delay_ns, timer_advance_ns));
+ }
+}
+
void wait_lapic_expire(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
+ u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns;
u64 guest_tsc, tsc_deadline, ns;
- if (!lapic_in_kernel(vcpu))
- return;
-
if (apic->lapic_timer.expired_tscdeadline == 0)
return;
@@ -1499,33 +1518,37 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);
- /* __delay is delay_tsc whenever the hardware has TSC, thus always. */
if (guest_tsc < tsc_deadline)
- __delay(min(tsc_deadline - guest_tsc,
- nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
+ __wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
- if (!lapic_timer_advance_adjust_done) {
+ if (!apic->lapic_timer.timer_advance_adjust_done) {
/* too early */
if (guest_tsc < tsc_deadline) {
ns = (tsc_deadline - guest_tsc) * 1000000ULL;
do_div(ns, vcpu->arch.virtual_tsc_khz);
- lapic_timer_advance_ns -= min((unsigned int)ns,
- lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+ timer_advance_ns -= min((u32)ns,
+ timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
} else {
/* too late */
ns = (guest_tsc - tsc_deadline) * 1000000ULL;
do_div(ns, vcpu->arch.virtual_tsc_khz);
- lapic_timer_advance_ns += min((unsigned int)ns,
- lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+ timer_advance_ns += min((u32)ns,
+ timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
}
if (abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE)
- lapic_timer_advance_adjust_done = true;
+ apic->lapic_timer.timer_advance_adjust_done = true;
+ if (unlikely(timer_advance_ns > 5000)) {
+ timer_advance_ns = 0;
+ apic->lapic_timer.timer_advance_adjust_done = true;
+ }
+ apic->lapic_timer.timer_advance_ns = timer_advance_ns;
}
}
static void start_sw_tscdeadline(struct kvm_lapic *apic)
{
- u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline;
+ struct kvm_timer *ktimer = &apic->lapic_timer;
+ u64 guest_tsc, tscdeadline = ktimer->tscdeadline;
u64 ns = 0;
ktime_t expire;
struct kvm_vcpu *vcpu = apic->vcpu;
@@ -1540,13 +1563,15 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
now = ktime_get();
guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
- if (likely(tscdeadline > guest_tsc)) {
- ns = (tscdeadline - guest_tsc) * 1000000ULL;
- do_div(ns, this_tsc_khz);
+
+ ns = (tscdeadline - guest_tsc) * 1000000ULL;
+ do_div(ns, this_tsc_khz);
+
+ if (likely(tscdeadline > guest_tsc) &&
+ likely(ns > apic->lapic_timer.timer_advance_ns)) {
expire = ktime_add_ns(now, ns);
- expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
- hrtimer_start(&apic->lapic_timer.timer,
- expire, HRTIMER_MODE_ABS_PINNED);
+ expire = ktime_sub_ns(expire, ktimer->timer_advance_ns);
+ hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_PINNED);
} else
apic_timer_expired(apic);
@@ -2253,7 +2278,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
return HRTIMER_NORESTART;
}
-int kvm_create_lapic(struct kvm_vcpu *vcpu)
+int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
{
struct kvm_lapic *apic;
@@ -2277,6 +2302,14 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
HRTIMER_MODE_ABS_PINNED);
apic->lapic_timer.timer.function = apic_timer_fn;
+ if (timer_advance_ns == -1) {
+ apic->lapic_timer.timer_advance_ns = 1000;
+ apic->lapic_timer.timer_advance_adjust_done = false;
+ } else {
+ apic->lapic_timer.timer_advance_ns = timer_advance_ns;
+ apic->lapic_timer.timer_advance_adjust_done = true;
+ }
+
/*
* APIC is created enabled. This will prevent kvm_lapic_set_base from
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index ff6ef9c3d760..d6d049ba3045 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -31,8 +31,10 @@ struct kvm_timer {
u32 timer_mode_mask;
u64 tscdeadline;
u64 expired_tscdeadline;
+ u32 timer_advance_ns;
atomic_t pending; /* accumulated triggered timers */
bool hv_timer_in_use;
+ bool timer_advance_adjust_done;
};
struct kvm_lapic {
@@ -62,7 +64,7 @@ struct kvm_lapic {
struct dest_map;
-int kvm_create_lapic(struct kvm_vcpu *vcpu);
+int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns);
void kvm_free_lapic(struct kvm_vcpu *vcpu);
int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index eee455a8a612..d9c7b45d231f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2007,7 +2007,7 @@ static int is_empty_shadow_page(u64 *spt)
* aggregate version in order to make the slab shrinker
* faster
*/
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
{
kvm->arch.n_used_mmu_pages += nr;
percpu_counter_add(&kvm_total_used_mmu_pages, nr);
@@ -2238,7 +2238,7 @@ static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm,
struct list_head *invalid_list,
bool remote_flush)
{
- if (!remote_flush && !list_empty(invalid_list))
+ if (!remote_flush && list_empty(invalid_list))
return false;
if (!list_empty(invalid_list))
@@ -2763,7 +2763,7 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm,
* Changing the number of mmu pages allocated to the vm
* Note: if goal_nr_mmu_pages is too small, you will get dead lock
*/
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages)
{
LIST_HEAD(invalid_list);
@@ -4781,6 +4781,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu)
union kvm_mmu_extended_role ext = {0};
ext.cr0_pg = !!is_paging(vcpu);
+ ext.cr4_pae = !!is_pae(vcpu);
ext.cr4_smep = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
ext.cr4_smap = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
ext.cr4_pse = !!is_pse(vcpu);
@@ -6031,10 +6032,10 @@ out:
/*
* Calculate mmu pages needed for kvm.
*/
-unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
{
- unsigned int nr_mmu_pages;
- unsigned int nr_pages = 0;
+ unsigned long nr_mmu_pages;
+ unsigned long nr_pages = 0;
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int i;
@@ -6047,8 +6048,7 @@ unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
}
nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
- nr_mmu_pages = max(nr_mmu_pages,
- (unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
+ nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES);
return nr_mmu_pages;
}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index bbdc60f2fae8..54c2a377795b 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -64,7 +64,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
u64 fault_address, char *insn, int insn_len);
-static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
+static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm)
{
if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages)
return kvm->arch.n_max_mmu_pages -
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 58ead7db71a3..e39741997893 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -281,9 +281,13 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
{
bool fast_mode = idx & (1u << 31);
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
struct kvm_pmc *pmc;
u64 ctr_val;
+ if (!pmu->version)
+ return 1;
+
if (is_vmware_backdoor_pmc(idx))
return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 426039285fd1..406b558abfef 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -262,6 +262,7 @@ struct amd_svm_iommu_ir {
};
#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF)
+#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31
#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31)
#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL)
@@ -2692,6 +2693,7 @@ static int npf_interception(struct vcpu_svm *svm)
static int db_interception(struct vcpu_svm *svm)
{
struct kvm_run *kvm_run = svm->vcpu.run;
+ struct kvm_vcpu *vcpu = &svm->vcpu;
if (!(svm->vcpu.guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
@@ -2702,6 +2704,8 @@ static int db_interception(struct vcpu_svm *svm)
if (svm->nmi_singlestep) {
disable_nmi_singlestep(svm);
+ /* Make sure we check for pending NMIs upon entry */
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
}
if (svm->vcpu.guest_debug &
@@ -4517,14 +4521,25 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
kvm_lapic_reg_write(apic, APIC_ICR, icrl);
break;
case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
+ int i;
+ struct kvm_vcpu *vcpu;
+ struct kvm *kvm = svm->vcpu.kvm;
struct kvm_lapic *apic = svm->vcpu.arch.apic;
/*
- * Update ICR high and low, then emulate sending IPI,
- * which is handled when writing APIC_ICR.
+ * At this point, we expect that the AVIC HW has already
+ * set the appropriate IRR bits on the valid target
+ * vcpus. So, we just need to kick the appropriate vcpu.
*/
- kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
- kvm_lapic_reg_write(apic, APIC_ICR, icrl);
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ bool m = kvm_apic_match_dest(vcpu, apic,
+ icrl & KVM_APIC_SHORT_MASK,
+ GET_APIC_DEST_FIELD(icrh),
+ icrl & KVM_APIC_DEST_MASK);
+
+ if (m && !avic_vcpu_is_running(vcpu))
+ kvm_vcpu_wake_up(vcpu);
+ }
break;
}
case AVIC_IPI_FAILURE_INVALID_TARGET:
@@ -4596,7 +4611,7 @@ static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu)
u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat);
if (entry)
- WRITE_ONCE(*entry, (u32) ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK);
+ clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry);
}
static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
@@ -5621,6 +5636,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
svm->vmcb->save.cr2 = vcpu->arch.cr2;
clgi();
+ kvm_load_guest_xcr0(vcpu);
/*
* If this vCPU has touched SPEC_CTRL, restore the guest's value if
@@ -5766,6 +5782,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
kvm_before_interrupt(&svm->vcpu);
+ kvm_put_guest_xcr0(vcpu);
stgi();
/* Any pending NMI will happen here */
@@ -6215,32 +6232,24 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *nested_vmcb;
struct page *page;
- struct {
- u64 guest;
- u64 vmcb;
- } svm_state_save;
- int ret;
+ u64 guest;
+ u64 vmcb;
- ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfed8, &svm_state_save,
- sizeof(svm_state_save));
- if (ret)
- return ret;
+ guest = GET_SMSTATE(u64, smstate, 0x7ed8);
+ vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
- if (svm_state_save.guest) {
- vcpu->arch.hflags &= ~HF_SMM_MASK;
- nested_vmcb = nested_svm_map(svm, svm_state_save.vmcb, &page);
- if (nested_vmcb)
- enter_svm_guest_mode(svm, svm_state_save.vmcb, nested_vmcb, page);
- else
- ret = 1;
- vcpu->arch.hflags |= HF_SMM_MASK;
+ if (guest) {
+ nested_vmcb = nested_svm_map(svm, vmcb, &page);
+ if (!nested_vmcb)
+ return 1;
+ enter_svm_guest_mode(svm, vmcb, nested_vmcb, page);
}
- return ret;
+ return 0;
}
static int enable_smi_window(struct kvm_vcpu *vcpu)
@@ -6422,11 +6431,11 @@ e_free:
return ret;
}
-static int get_num_contig_pages(int idx, struct page **inpages,
- unsigned long npages)
+static unsigned long get_num_contig_pages(unsigned long idx,
+ struct page **inpages, unsigned long npages)
{
unsigned long paddr, next_paddr;
- int i = idx + 1, pages = 1;
+ unsigned long i = idx + 1, pages = 1;
/* find the number of contiguous pages starting from idx */
paddr = __sme_page_pa(inpages[idx]);
@@ -6445,12 +6454,12 @@ static int get_num_contig_pages(int idx, struct page **inpages,
static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
- unsigned long vaddr, vaddr_end, next_vaddr, npages, size;
+ unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i;
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
struct kvm_sev_launch_update_data params;
struct sev_data_launch_update_data *data;
struct page **inpages;
- int i, ret, pages;
+ int ret;
if (!sev_guest(kvm))
return -ENOTTY;
@@ -6799,7 +6808,8 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
struct page **src_p, **dst_p;
struct kvm_sev_dbg debug;
unsigned long n;
- int ret, size;
+ unsigned int size;
+ int ret;
if (!sev_guest(kvm))
return -ENOTTY;
@@ -6807,6 +6817,11 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug)))
return -EFAULT;
+ if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr)
+ return -EINVAL;
+ if (!debug.dst_uaddr)
+ return -EINVAL;
+
vaddr = debug.src_uaddr;
size = debug.len;
vaddr_end = vaddr + size;
@@ -6857,8 +6872,8 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
dst_vaddr,
len, &argp->error);
- sev_unpin_memory(kvm, src_p, 1);
- sev_unpin_memory(kvm, dst_p, 1);
+ sev_unpin_memory(kvm, src_p, n);
+ sev_unpin_memory(kvm, dst_p, n);
if (ret)
goto err;
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 6432d08c7de7..4d47a2631d1f 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -438,13 +438,13 @@ TRACE_EVENT(kvm_apic_ipi,
);
TRACE_EVENT(kvm_apic_accept_irq,
- TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec),
+ TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec),
TP_ARGS(apicid, dm, tm, vec),
TP_STRUCT__entry(
__field( __u32, apicid )
__field( __u16, dm )
- __field( __u8, tm )
+ __field( __u16, tm )
__field( __u8, vec )
),
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 153e539c29c9..0c601d079cd2 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -500,6 +500,17 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1,
}
}
+static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) {
+ int msr;
+
+ for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+ unsigned word = msr / BITS_PER_LONG;
+
+ msr_bitmap[word] = ~0;
+ msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
+ }
+}
+
/*
* Merge L0's and L1's MSR bitmap, return false to indicate that
* we do not use the hardware.
@@ -541,39 +552,44 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
return false;
msr_bitmap_l1 = (unsigned long *)kmap(page);
- if (nested_cpu_has_apic_reg_virt(vmcs12)) {
- /*
- * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it
- * just lets the processor take the value from the virtual-APIC page;
- * take those 256 bits directly from the L1 bitmap.
- */
- for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
- unsigned word = msr / BITS_PER_LONG;
- msr_bitmap_l0[word] = msr_bitmap_l1[word];
- msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
- }
- } else {
- for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
- unsigned word = msr / BITS_PER_LONG;
- msr_bitmap_l0[word] = ~0;
- msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
- }
- }
- nested_vmx_disable_intercept_for_msr(
- msr_bitmap_l1, msr_bitmap_l0,
- X2APIC_MSR(APIC_TASKPRI),
- MSR_TYPE_W);
+ /*
+ * To keep the control flow simple, pay eight 8-byte writes (sixteen
+ * 4-byte writes on 32-bit systems) up front to enable intercepts for
+ * the x2APIC MSR range and selectively disable them below.
+ */
+ enable_x2apic_msr_intercepts(msr_bitmap_l0);
+
+ if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
+ if (nested_cpu_has_apic_reg_virt(vmcs12)) {
+ /*
+ * L0 need not intercept reads for MSRs between 0x800
+ * and 0x8ff, it just lets the processor take the value
+ * from the virtual-APIC page; take those 256 bits
+ * directly from the L1 bitmap.
+ */
+ for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+ unsigned word = msr / BITS_PER_LONG;
+
+ msr_bitmap_l0[word] = msr_bitmap_l1[word];
+ }
+ }
- if (nested_cpu_has_vid(vmcs12)) {
- nested_vmx_disable_intercept_for_msr(
- msr_bitmap_l1, msr_bitmap_l0,
- X2APIC_MSR(APIC_EOI),
- MSR_TYPE_W);
nested_vmx_disable_intercept_for_msr(
msr_bitmap_l1, msr_bitmap_l0,
- X2APIC_MSR(APIC_SELF_IPI),
- MSR_TYPE_W);
+ X2APIC_MSR(APIC_TASKPRI),
+ MSR_TYPE_R | MSR_TYPE_W);
+
+ if (nested_cpu_has_vid(vmcs12)) {
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ X2APIC_MSR(APIC_EOI),
+ MSR_TYPE_W);
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ X2APIC_MSR(APIC_SELF_IPI),
+ MSR_TYPE_W);
+ }
}
if (spec_ctrl)
@@ -2857,20 +2873,27 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
/*
* If translation failed, VM entry will fail because
* prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull.
- * Failing the vm entry is _not_ what the processor
- * does but it's basically the only possibility we
- * have. We could still enter the guest if CR8 load
- * exits are enabled, CR8 store exits are enabled, and
- * virtualize APIC access is disabled; in this case
- * the processor would never use the TPR shadow and we
- * could simply clear the bit from the execution
- * control. But such a configuration is useless, so
- * let's keep the code simple.
*/
if (!is_error_page(page)) {
vmx->nested.virtual_apic_page = page;
hpa = page_to_phys(vmx->nested.virtual_apic_page);
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa);
+ } else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) &&
+ nested_cpu_has(vmcs12, CPU_BASED_CR8_STORE_EXITING) &&
+ !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ /*
+ * The processor will never use the TPR shadow, simply
+ * clear the bit from the execution control. Such a
+ * configuration is useless, but it happens in tests.
+ * For any other configuration, failing the vm entry is
+ * _not_ what the processor does but it's basically the
+ * only possibility we have.
+ */
+ vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
+ CPU_BASED_TPR_SHADOW);
+ } else {
+ printk("bad virtual-APIC page address\n");
+ dump_vmcs();
}
}
@@ -3773,8 +3796,18 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW));
nested_ept_uninit_mmu_context(vcpu);
- vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
- __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+
+ /*
+ * This is only valid if EPT is in use, otherwise the vmcs01 GUEST_CR3
+ * points to shadow pages! Fortunately we only get here after a WARN_ON
+ * if EPT is disabled, so a VMabort is perfectly fine.
+ */
+ if (enable_ept) {
+ vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+ __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+ } else {
+ nested_vmx_abort(vcpu, VMX_ABORT_VMCS_CORRUPTED);
+ }
/*
* Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
@@ -5390,7 +5423,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
return ret;
/* Empty 'VMXON' state is permitted */
- if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12))
+ if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12))
return 0;
if (kvm_state->vmx.vmcs_pa != -1ull) {
@@ -5434,7 +5467,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
vmcs12->vmcs_link_pointer != -1ull) {
struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu);
- if (kvm_state->size < sizeof(kvm_state) + 2 * sizeof(*vmcs12))
+ if (kvm_state->size < sizeof(*kvm_state) + 2 * sizeof(*vmcs12))
return -EINVAL;
if (copy_from_user(shadow_vmcs12,
@@ -5722,6 +5755,14 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
{
int i;
+ /*
+ * Without EPT it is not possible to restore L1's CR3 and PDPTR on
+ * VMfail, because they are not available in vmcs01. Just always
+ * use hardware checks.
+ */
+ if (!enable_ept)
+ nested_early_check = 1;
+
if (!cpu_has_vmx_shadow_vmcs())
enable_shadow_vmcs = 0;
if (enable_shadow_vmcs) {
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 7b272738c576..d4cb1945b2e3 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -3,6 +3,7 @@
#include <asm/asm.h>
#include <asm/bitsperlong.h>
#include <asm/kvm_vcpu_regs.h>
+#include <asm/nospec-branch.h>
#define WORD_SIZE (BITS_PER_LONG / 8)
@@ -77,6 +78,17 @@ ENDPROC(vmx_vmenter)
* referred to by VMCS.HOST_RIP.
*/
ENTRY(vmx_vmexit)
+#ifdef CONFIG_RETPOLINE
+ ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE
+ /* Preserve guest's RAX, it's used to stuff the RSB. */
+ push %_ASM_AX
+
+ /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
+ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
+
+ pop %_ASM_AX
+.Lvmexit_skip_rsb:
+#endif
ret
ENDPROC(vmx_vmexit)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index ab432a930ae8..0c955bb286ff 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5603,7 +5603,7 @@ static void vmx_dump_dtsel(char *name, uint32_t limit)
vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
}
-static void dump_vmcs(void)
+void dump_vmcs(void)
{
u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
@@ -6410,6 +6410,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
vmx_set_interrupt_shadow(vcpu, 0);
+ kvm_load_guest_xcr0(vcpu);
+
if (static_cpu_has(X86_FEATURE_PKU) &&
kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
vcpu->arch.pkru != vmx->host_pkru)
@@ -6460,9 +6462,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
- /* Eliminate branch target predictions from guest mode */
- vmexit_fill_RSB();
-
/* All fields are clean at this point */
if (static_branch_unlikely(&enable_evmcs))
current_evmcs->hv_clean_fields |=
@@ -6506,6 +6505,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
__write_pkru(vmx->host_pkru);
}
+ kvm_put_guest_xcr0(vcpu);
+
vmx->nested.nested_run_pending = 0;
vmx->idt_vectoring_info = 0;
@@ -6852,6 +6853,30 @@ static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
}
}
+static bool guest_cpuid_has_pmu(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *entry;
+ union cpuid10_eax eax;
+
+ entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
+ if (!entry)
+ return false;
+
+ eax.full = entry->eax;
+ return (eax.split.version_id > 0);
+}
+
+static void nested_vmx_procbased_ctls_update(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ bool pmu_enabled = guest_cpuid_has_pmu(vcpu);
+
+ if (pmu_enabled)
+ vmx->nested.msrs.procbased_ctls_high |= CPU_BASED_RDPMC_EXITING;
+ else
+ vmx->nested.msrs.procbased_ctls_high &= ~CPU_BASED_RDPMC_EXITING;
+}
+
static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6940,6 +6965,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
if (nested_vmx_allowed(vcpu)) {
nested_vmx_cr_fixed1_bits_update(vcpu);
nested_vmx_entry_exit_ctls_update(vcpu);
+ nested_vmx_procbased_ctls_update(vcpu);
}
if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
@@ -7003,6 +7029,7 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
{
struct vcpu_vmx *vmx;
u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles;
+ struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer;
if (kvm_mwait_in_guest(vcpu->kvm))
return -EOPNOTSUPP;
@@ -7011,7 +7038,8 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
tscl = rdtsc();
guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
- lapic_timer_advance_cycles = nsec_to_cycles(vcpu, lapic_timer_advance_ns);
+ lapic_timer_advance_cycles = nsec_to_cycles(vcpu,
+ ktimer->timer_advance_ns);
if (delta_tsc > lapic_timer_advance_cycles)
delta_tsc -= lapic_timer_advance_cycles;
@@ -7369,7 +7397,7 @@ static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int ret;
@@ -7380,9 +7408,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
}
if (vmx->nested.smm.guest_mode) {
- vcpu->arch.hflags &= ~HF_SMM_MASK;
ret = nested_vmx_enter_non_root_mode(vcpu, false);
- vcpu->arch.hflags |= HF_SMM_MASK;
if (ret)
return ret;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index a1e00d0a2482..f879529906b4 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -517,4 +517,6 @@ static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx)
vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
}
+void dump_vmcs(void);
+
#endif /* __KVM_X86_VMX_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 099b851dabaf..b5edc8e3ce1d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -136,10 +136,14 @@ EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio);
static u32 __read_mostly tsc_tolerance_ppm = 250;
module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
-/* lapic timer advance (tscdeadline mode only) in nanoseconds */
-unsigned int __read_mostly lapic_timer_advance_ns = 1000;
+/*
+ * lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables
+ * adaptive tuning starting from default advancment of 1000ns. '0' disables
+ * advancement entirely. Any other value is used as-is and disables adaptive
+ * tuning, i.e. allows priveleged userspace to set an exact advancement time.
+ */
+static int __read_mostly lapic_timer_advance_ns = -1;
module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
-EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);
static bool __read_mostly vector_hashing = true;
module_param(vector_hashing, bool, S_IRUGO);
@@ -800,7 +804,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
}
EXPORT_SYMBOL_GPL(kvm_lmsw);
-static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
{
if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
!vcpu->guest_xcr0_loaded) {
@@ -810,8 +814,9 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
vcpu->guest_xcr0_loaded = 1;
}
}
+EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
-static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
{
if (vcpu->guest_xcr0_loaded) {
if (vcpu->arch.xcr0 != host_xcr0)
@@ -819,6 +824,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
vcpu->guest_xcr0_loaded = 0;
}
}
+EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0);
static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
{
@@ -3093,7 +3099,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
break;
case KVM_CAP_NESTED_STATE:
r = kvm_x86_ops->get_nested_state ?
- kvm_x86_ops->get_nested_state(NULL, 0, 0) : 0;
+ kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0;
break;
default:
break;
@@ -3528,7 +3534,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
memset(&events->reserved, 0, sizeof(events->reserved));
}
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+static void kvm_smm_changed(struct kvm_vcpu *vcpu);
static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
@@ -3588,12 +3594,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
vcpu->arch.apic->sipi_vector = events->sipi_vector;
if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
- u32 hflags = vcpu->arch.hflags;
- if (events->smi.smm)
- hflags |= HF_SMM_MASK;
- else
- hflags &= ~HF_SMM_MASK;
- kvm_set_hflags(vcpu, hflags);
+ if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
+ if (events->smi.smm)
+ vcpu->arch.hflags |= HF_SMM_MASK;
+ else
+ vcpu->arch.hflags &= ~HF_SMM_MASK;
+ kvm_smm_changed(vcpu);
+ }
vcpu->arch.smi_pending = events->smi.pending;
@@ -4270,7 +4277,7 @@ static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm,
}
static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
- u32 kvm_nr_mmu_pages)
+ unsigned long kvm_nr_mmu_pages)
{
if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
return -EINVAL;
@@ -4284,7 +4291,7 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
return 0;
}
-static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
+static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
{
return kvm->arch.n_max_mmu_pages;
}
@@ -5958,12 +5965,18 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
{
- kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags);
+ emul_to_vcpu(ctxt)->arch.hflags = emul_flags;
}
-static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
{
- return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smbase);
+ return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smstate);
+}
+
+static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt)
+{
+ kvm_smm_changed(emul_to_vcpu(ctxt));
}
static const struct x86_emulate_ops emulate_ops = {
@@ -6006,6 +6019,7 @@ static const struct x86_emulate_ops emulate_ops = {
.get_hflags = emulator_get_hflags,
.set_hflags = emulator_set_hflags,
.pre_leave_smm = emulator_pre_leave_smm,
+ .post_leave_smm = emulator_post_leave_smm,
};
static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
@@ -6247,16 +6261,6 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu)
kvm_mmu_reset_context(vcpu);
}
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags)
-{
- unsigned changed = vcpu->arch.hflags ^ emul_flags;
-
- vcpu->arch.hflags = emul_flags;
-
- if (changed & HF_SMM_MASK)
- kvm_smm_changed(vcpu);
-}
-
static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
unsigned long *db)
{
@@ -6535,6 +6539,12 @@ int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
}
EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer);
+static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.pio.count = 0;
+ return 1;
+}
+
static int complete_fast_pio_out(struct kvm_vcpu *vcpu)
{
vcpu->arch.pio.count = 0;
@@ -6551,12 +6561,23 @@ static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt,
size, port, &val, 1);
+ if (ret)
+ return ret;
- if (!ret) {
+ /*
+ * Workaround userspace that relies on old KVM behavior of %rip being
+ * incremented prior to exiting to userspace to handle "OUT 0x7e".
+ */
+ if (port == 0x7e &&
+ kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) {
+ vcpu->arch.complete_userspace_io =
+ complete_fast_pio_out_port_0x7e;
+ kvm_skip_emulated_instruction(vcpu);
+ } else {
vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
vcpu->arch.complete_userspace_io = complete_fast_pio_out;
}
- return ret;
+ return 0;
}
static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
@@ -7441,9 +7462,9 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
}
+#ifdef CONFIG_X86_64
static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
{
-#ifdef CONFIG_X86_64
struct desc_ptr dt;
struct kvm_segment seg;
unsigned long val;
@@ -7493,10 +7514,8 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
for (i = 0; i < 6; i++)
enter_smm_save_seg_64(vcpu, buf, i);
-#else
- WARN_ON_ONCE(1);
-#endif
}
+#endif
static void enter_smm(struct kvm_vcpu *vcpu)
{
@@ -7507,9 +7526,11 @@ static void enter_smm(struct kvm_vcpu *vcpu)
trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
memset(buf, 0, 512);
+#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
enter_smm_save_state_64(vcpu, buf);
else
+#endif
enter_smm_save_state_32(vcpu, buf);
/*
@@ -7567,8 +7588,10 @@ static void enter_smm(struct kvm_vcpu *vcpu)
kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
+#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
kvm_x86_ops->set_efer(vcpu, 0);
+#endif
kvm_update_cpuid(vcpu);
kvm_mmu_reset_context(vcpu);
@@ -7865,15 +7888,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
goto cancel_injection;
}
- kvm_load_guest_xcr0(vcpu);
-
if (req_immediate_exit) {
kvm_make_request(KVM_REQ_EVENT, vcpu);
kvm_x86_ops->request_immediate_exit(vcpu);
}
trace_kvm_entry(vcpu->vcpu_id);
- if (lapic_timer_advance_ns)
+ if (lapic_in_kernel(vcpu) &&
+ vcpu->arch.apic->lapic_timer.timer_advance_ns)
wait_lapic_expire(vcpu);
guest_enter_irqoff();
@@ -7919,8 +7941,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
vcpu->mode = OUTSIDE_GUEST_MODE;
smp_wmb();
- kvm_put_guest_xcr0(vcpu);
-
kvm_before_interrupt(vcpu);
kvm_x86_ops->handle_external_intr(vcpu);
kvm_after_interrupt(vcpu);
@@ -9063,7 +9083,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
if (irqchip_in_kernel(vcpu->kvm)) {
vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu);
- r = kvm_create_lapic(vcpu);
+ r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
if (r < 0)
goto fail_mmu_destroy;
} else
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 28406aa1136d..534d3f28bb01 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -294,8 +294,6 @@ extern u64 kvm_supported_xcr0(void);
extern unsigned int min_timer_period_us;
-extern unsigned int lapic_timer_advance_ns;
-
extern bool enable_vmware_backdoor;
extern struct static_key kvm_no_apic_vcpu;
@@ -347,4 +345,6 @@ static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu)
__this_cpu_write(current_vcpu, NULL);
}
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu);
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu);
#endif
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 140e61843a07..3cb3af51ec89 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -6,6 +6,18 @@
# Produces uninteresting flaky coverage.
KCOV_INSTRUMENT_delay.o := n
+# Early boot use of cmdline; don't instrument it
+ifdef CONFIG_AMD_MEM_ENCRYPT
+KCOV_INSTRUMENT_cmdline.o := n
+KASAN_SANITIZE_cmdline.o := n
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_cmdline.o = -pg
+endif
+
+CFLAGS_cmdline.o := $(call cc-option, -fno-stack-protector)
+endif
+
inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk
inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt
quiet_cmd_inat_tables = GEN $@
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index ee8f8ab46941..c0309ea9abee 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -259,7 +259,8 @@ static void note_wx(struct pg_state *st)
#endif
/* Account the WX pages */
st->wx_pages += npages;
- WARN_ONCE(1, "x86/mm: Found insecure W+X mapping at address %pS\n",
+ WARN_ONCE(__supported_pte_mask & _PAGE_NX,
+ "x86/mm: Found insecure W+X mapping at address %pS\n",
(void *)st->start_address);
}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index f905a2371080..8dacdb96899e 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -5,6 +5,7 @@
#include <linux/memblock.h>
#include <linux/swapfile.h>
#include <linux/swapops.h>
+#include <linux/kmemleak.h>
#include <asm/set_memory.h>
#include <asm/e820/api.h>
@@ -766,6 +767,11 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end)
if (debug_pagealloc_enabled()) {
pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n",
begin, end - 1);
+ /*
+ * Inform kmemleak about the hole in the memory since the
+ * corresponding pages will be unmapped.
+ */
+ kmemleak_free_part((void *)begin, end - begin);
set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
} else {
/*
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 0029604af8a4..dd73d5d74393 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -825,7 +825,7 @@ void __init __early_set_fixmap(enum fixed_addresses idx,
pte = early_ioremap_pte(addr);
/* Sanitize 'prot' against any unsupported bits: */
- pgprot_val(flags) &= __default_kernel_pte_mask;
+ pgprot_val(flags) &= __supported_pte_mask;
if (pgprot_val(flags))
set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 3f452ffed7e9..d669c5e797e0 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -94,7 +94,7 @@ void __init kernel_randomize_memory(void)
if (!kaslr_memory_enabled())
return;
- kaslr_regions[0].size_tb = 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT);
+ kaslr_regions[0].size_tb = 1 << (MAX_PHYSMEM_BITS - TB_SHIFT);
kaslr_regions[1].size_tb = VMALLOC_SIZE_TB;
/*
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index bc4bc7b2f075..487b8474c01c 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -728,7 +728,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
{
int cpu;
- struct flush_tlb_info info __aligned(SMP_CACHE_BYTES) = {
+ struct flush_tlb_info info = {
.mm = mm,
.stride_shift = stride_shift,
.freed_tables = freed_tables,
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index f7dd895b2353..0c14018d1c26 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -187,15 +187,18 @@ struct thread_struct {
/* Clearing a0 terminates the backtrace. */
#define start_thread(regs, new_pc, new_sp) \
- memset(regs, 0, sizeof(*regs)); \
- regs->pc = new_pc; \
- regs->ps = USER_PS_VALUE; \
- regs->areg[1] = new_sp; \
- regs->areg[0] = 0; \
- regs->wmask = 1; \
- regs->depc = 0; \
- regs->windowbase = 0; \
- regs->windowstart = 1;
+ do { \
+ memset((regs), 0, sizeof(*(regs))); \
+ (regs)->pc = (new_pc); \
+ (regs)->ps = USER_PS_VALUE; \
+ (regs)->areg[1] = (new_sp); \
+ (regs)->areg[0] = 0; \
+ (regs)->wmask = 1; \
+ (regs)->depc = 0; \
+ (regs)->windowbase = 0; \
+ (regs)->windowstart = 1; \
+ (regs)->syscall = NO_SYSCALL; \
+ } while (0)
/* Forward declaration */
struct task_struct;
diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h
index a168bf81c7f4..91dc06d58060 100644
--- a/arch/xtensa/include/asm/syscall.h
+++ b/arch/xtensa/include/asm/syscall.h
@@ -59,45 +59,24 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
static const unsigned int reg[] = XTENSA_SYSCALL_ARGUMENT_REGS;
- unsigned int j;
+ unsigned int i;
- if (n == 0)
- return;
-
- WARN_ON_ONCE(i + n > SYSCALL_MAX_ARGS);
-
- for (j = 0; j < n; ++j) {
- if (i + j < SYSCALL_MAX_ARGS)
- args[j] = regs->areg[reg[i + j]];
- else
- args[j] = 0;
- }
+ for (i = 0; i < 6; ++i)
+ args[i] = regs->areg[reg[i]];
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
static const unsigned int reg[] = XTENSA_SYSCALL_ARGUMENT_REGS;
- unsigned int j;
-
- if (n == 0)
- return;
-
- if (WARN_ON_ONCE(i + n > SYSCALL_MAX_ARGS)) {
- if (i < SYSCALL_MAX_ARGS)
- n = SYSCALL_MAX_ARGS - i;
- else
- return;
- }
+ unsigned int i;
- for (j = 0; j < n; ++j)
- regs->areg[reg[i + j]] = args[j];
+ for (i = 0; i < 6; ++i)
+ regs->areg[reg[i]] = args[i];
}
asmlinkage long xtensa_rt_sigreturn(struct pt_regs*);
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index e50f5124dc6f..e54af8b7e0f8 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1860,6 +1860,8 @@ ENTRY(system_call)
l32i a7, a2, PT_SYSCALL
1:
+ s32i a7, a1, 4
+
/* syscall = sys_call_table[syscall_nr] */
movi a4, sys_call_table
@@ -1893,8 +1895,12 @@ ENTRY(system_call)
retw
1:
+ l32i a4, a1, 4
+ l32i a3, a2, PT_SYSCALL
+ s32i a4, a2, PT_SYSCALL
mov a6, a2
call4 do_syscall_trace_leave
+ s32i a3, a2, PT_SYSCALL
retw
ENDPROC(system_call)
diff --git a/arch/xtensa/kernel/stacktrace.c b/arch/xtensa/kernel/stacktrace.c
index 174c11f13bba..b9f82510c650 100644
--- a/arch/xtensa/kernel/stacktrace.c
+++ b/arch/xtensa/kernel/stacktrace.c
@@ -253,10 +253,14 @@ static int return_address_cb(struct stackframe *frame, void *data)
return 1;
}
+/*
+ * level == 0 is for the return address from the caller of this function,
+ * not from this function itself.
+ */
unsigned long return_address(unsigned level)
{
struct return_addr_data r = {
- .skip = level + 1,
+ .skip = level,
};
walk_stackframe(stack_pointer(NULL), return_address_cb, &r);
return r.addr;
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 6af49929de85..30084eaf8422 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -394,3 +394,7 @@
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c
index 2fb7d1172228..03678c4afc39 100644
--- a/arch/xtensa/mm/mmu.c
+++ b/arch/xtensa/mm/mmu.c
@@ -33,7 +33,7 @@ static void * __init init_pmd(unsigned long vaddr, unsigned long n_pages)
pte = memblock_alloc_low(n_pages * sizeof(pte_t), PAGE_SIZE);
if (!pte)
- panic("%s: Failed to allocate %zu bytes align=%lx\n",
+ panic("%s: Failed to allocate %lu bytes align=%lx\n",
__func__, n_pages * sizeof(pte_t), PAGE_SIZE);
for (i = 0; i < n_pages; ++i)