summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/Kconfig3
-rw-r--r--arch/arc/Kconfig2
-rw-r--r--arch/arc/include/asm/checksum.h2
-rw-r--r--arch/arc/include/asm/perf_event.h2
-rw-r--r--arch/arc/kernel/fpu.c9
-rw-r--r--arch/arc/kernel/mcip.c2
-rw-r--r--arch/arc/kernel/unwind.c10
-rw-r--r--arch/arc/kernel/vmlinux.lds.S2
-rw-r--r--arch/arm/common/sa1111.c12
-rw-r--r--arch/arm/configs/nhk8815_defconfig8
-rw-r--r--arch/arm/crypto/curve25519-glue.c8
-rw-r--r--arch/arm/include/asm/memory.h7
-rw-r--r--arch/arm/kernel/head.S17
-rw-r--r--arch/arm/mach-ixp4xx/include/mach/ixp4xx-regs.h48
-rw-r--r--arch/arm/mach-pxa/pxa_cplds_irqs.c6
-rw-r--r--arch/arm/mach-s3c/irq-s3c24xx.c5
-rw-r--r--arch/arm/mm/mmu.c9
-rw-r--r--arch/arm/mm/pv-fixup-asm.S2
-rw-r--r--arch/arm64/Kconfig1
-rw-r--r--arch/arm64/Makefile2
-rw-r--r--arch/arm64/boot/dts/qcom/msm8992-bullhead-rev-101.dts12
-rw-r--r--arch/arm64/boot/dts/qcom/msm8994-angler-rev-101.dts4
-rw-r--r--arch/arm64/boot/dts/qcom/sc7280.dtsi2
-rw-r--r--arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi4
-rw-r--r--arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts4
-rw-r--r--arch/arm64/crypto/Kconfig2
-rw-r--r--arch/arm64/crypto/sm4-ce-glue.c20
-rw-r--r--arch/arm64/include/asm/el2_setup.h3
-rw-r--r--arch/arm64/include/asm/page.h1
-rw-r--r--arch/arm64/kvm/arm.c12
-rw-r--r--arch/arm64/kvm/hyp/nvhe/mem_protect.c2
-rw-r--r--arch/arm64/mm/init.c37
-rw-r--r--arch/m68k/Kconfig.cpu8
-rw-r--r--arch/m68k/configs/amiga_defconfig6
-rw-r--r--arch/m68k/configs/apollo_defconfig4
-rw-r--r--arch/m68k/configs/atari_defconfig6
-rw-r--r--arch/m68k/configs/bvme6000_defconfig4
-rw-r--r--arch/m68k/configs/hp300_defconfig4
-rw-r--r--arch/m68k/configs/mac_defconfig6
-rw-r--r--arch/m68k/configs/multi_defconfig6
-rw-r--r--arch/m68k/configs/mvme147_defconfig4
-rw-r--r--arch/m68k/configs/mvme16x_defconfig4
-rw-r--r--arch/m68k/configs/q40_defconfig6
-rw-r--r--arch/m68k/configs/sun3_defconfig4
-rw-r--r--arch/m68k/configs/sun3x_defconfig4
-rw-r--r--arch/m68k/emu/nfeth.c4
-rw-r--r--arch/m68k/include/asm/atomic.h4
-rw-r--r--arch/mips/ath25/ar2315.c14
-rw-r--r--arch/mips/ath25/ar5312.c13
-rw-r--r--arch/mips/lantiq/irq.c2
-rw-r--r--arch/mips/pci/pci-ar2315.c8
-rw-r--r--arch/mips/pci/pci-rt3883.c5
-rw-r--r--arch/mips/ralink/irq.c2
-rw-r--r--arch/mips/sgi-ip27/ip27-irq.c16
-rw-r--r--arch/mips/sgi-ip30/ip30-irq.c8
-rw-r--r--arch/nios2/kernel/irq.c4
-rw-r--r--arch/parisc/include/asm/string.h15
-rw-r--r--arch/parisc/kernel/parisc_ksyms.c4
-rw-r--r--arch/parisc/lib/Makefile4
-rw-r--r--arch/parisc/lib/memset.c72
-rw-r--r--arch/parisc/lib/string.S136
-rw-r--r--arch/powerpc/include/asm/book3s/32/kup.h20
-rw-r--r--arch/powerpc/include/asm/interrupt.h3
-rw-r--r--arch/powerpc/include/asm/irq.h2
-rw-r--r--arch/powerpc/include/asm/ptrace.h16
-rw-r--r--arch/powerpc/kernel/asm-offsets.c31
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S7
-rw-r--r--arch/powerpc/kernel/head_book3s_32.S2
-rw-r--r--arch/powerpc/kernel/head_booke.h27
-rw-r--r--arch/powerpc/kernel/irq.c7
-rw-r--r--arch/powerpc/kernel/kprobes.c3
-rw-r--r--arch/powerpc/kernel/sysfs.c2
-rw-r--r--arch/powerpc/kernel/time.c2
-rw-r--r--arch/powerpc/kernel/traps.c9
-rw-r--r--arch/powerpc/mm/pageattr.c23
-rw-r--r--arch/powerpc/platforms/4xx/uic.c4
-rw-r--r--arch/powerpc/platforms/512x/mpc5121_ads_cpld.c23
-rw-r--r--arch/powerpc/platforms/52xx/media5200.c9
-rw-r--r--arch/powerpc/platforms/52xx/mpc52xx_gpt.c7
-rw-r--r--arch/powerpc/platforms/82xx/pq2ads-pci-pic.c6
-rw-r--r--arch/powerpc/platforms/Kconfig.cputype2
-rw-r--r--arch/powerpc/platforms/cell/interrupt.c8
-rw-r--r--arch/powerpc/platforms/cell/spider-pic.c11
-rw-r--r--arch/powerpc/platforms/embedded6xx/hlwd-pic.c15
-rw-r--r--arch/powerpc/platforms/powernv/opal-irqchip.c11
-rw-r--r--arch/powerpc/platforms/pseries/setup.c5
-rw-r--r--arch/powerpc/sysdev/fsl_mpic_err.c11
-rw-r--r--arch/powerpc/sysdev/fsl_msi.c12
-rw-r--r--arch/powerpc/sysdev/xive/common.c35
-rw-r--r--arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts4
-rw-r--r--arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi2
-rw-r--r--arch/riscv/kernel/Makefile2
-rw-r--r--arch/riscv/kernel/ptrace.c4
-rw-r--r--arch/riscv/kernel/setup.c4
-rw-r--r--arch/riscv/mm/init.c2
-rw-r--r--arch/s390/Kconfig2
-rw-r--r--arch/s390/Makefile3
-rw-r--r--arch/s390/boot/Makefile7
-rw-r--r--arch/s390/boot/boot.h14
-rw-r--r--arch/s390/boot/compressed/Makefile1
-rw-r--r--arch/s390/boot/compressed/decompressor.c5
-rw-r--r--arch/s390/boot/compressed/decompressor.h5
-rw-r--r--arch/s390/boot/compressed/vmlinux.lds.S35
-rw-r--r--arch/s390/boot/head.S56
-rw-r--r--arch/s390/boot/ipl_report.c6
-rw-r--r--arch/s390/boot/kaslr.c6
-rw-r--r--arch/s390/boot/mem_detect.c8
-rw-r--r--arch/s390/boot/pgm_check_info.c5
-rw-r--r--arch/s390/boot/sclp_early_core.c9
-rw-r--r--arch/s390/boot/startup.c78
-rw-r--r--arch/s390/boot/uv.c40
-rw-r--r--arch/s390/boot/uv.h19
-rw-r--r--arch/s390/configs/debug_defconfig3
-rw-r--r--arch/s390/configs/defconfig1
-rw-r--r--arch/s390/hypfs/hypfs_diag0c.c12
-rw-r--r--arch/s390/include/asm/cio.h1
-rw-r--r--arch/s390/include/asm/cpacf.h208
-rw-r--r--arch/s390/include/asm/cpufeature.h2
-rw-r--r--arch/s390/include/asm/ctl_reg.h17
-rw-r--r--arch/s390/include/asm/debug.h122
-rw-r--r--arch/s390/include/asm/diag.h15
-rw-r--r--arch/s390/include/asm/elf.h76
-rw-r--r--arch/s390/include/asm/extable.h4
-rw-r--r--arch/s390/include/asm/ftrace.h46
-rw-r--r--arch/s390/include/asm/ftrace.lds.h21
-rw-r--r--arch/s390/include/asm/ipl.h1
-rw-r--r--arch/s390/include/asm/kfence.h42
-rw-r--r--arch/s390/include/asm/kvm_para.h229
-rw-r--r--arch/s390/include/asm/linkage.h4
-rw-r--r--arch/s390/include/asm/lowcore.h3
-rw-r--r--arch/s390/include/asm/module.h14
-rw-r--r--arch/s390/include/asm/page.h3
-rw-r--r--arch/s390/include/asm/pci.h7
-rw-r--r--arch/s390/include/asm/pci_dma.h2
-rw-r--r--arch/s390/include/asm/pgtable.h10
-rw-r--r--arch/s390/include/asm/processor.h2
-rw-r--r--arch/s390/include/asm/qdio.h19
-rw-r--r--arch/s390/include/asm/sclp.h10
-rw-r--r--arch/s390/include/asm/sections.h4
-rw-r--r--arch/s390/include/asm/set_memory.h6
-rw-r--r--arch/s390/include/asm/setup.h46
-rw-r--r--arch/s390/include/asm/syscall.h59
-rw-r--r--arch/s390/include/asm/uv.h8
-rw-r--r--arch/s390/include/asm/vdso/gettimeofday.h22
-rw-r--r--arch/s390/kernel/Makefile2
-rw-r--r--arch/s390/kernel/asm-offsets.c8
-rw-r--r--arch/s390/kernel/crash_dump.c46
-rw-r--r--arch/s390/kernel/debug.c247
-rw-r--r--arch/s390/kernel/diag.c27
-rw-r--r--arch/s390/kernel/dis.c2
-rw-r--r--arch/s390/kernel/early.c4
-rw-r--r--arch/s390/kernel/entry.S11
-rw-r--r--arch/s390/kernel/entry.h11
-rw-r--r--arch/s390/kernel/ftrace.c222
-rw-r--r--arch/s390/kernel/ftrace.h26
-rw-r--r--arch/s390/kernel/head64.S17
-rw-r--r--arch/s390/kernel/ipl.c5
-rw-r--r--arch/s390/kernel/ipl_vmparm.c2
-rw-r--r--arch/s390/kernel/irq.c4
-rw-r--r--arch/s390/kernel/jump_label.c2
-rw-r--r--arch/s390/kernel/machine_kexec.c5
-rw-r--r--arch/s390/kernel/module.c45
-rw-r--r--arch/s390/kernel/os_info.c2
-rw-r--r--arch/s390/kernel/perf_cpum_cf.c4
-rw-r--r--arch/s390/kernel/processor.c177
-rw-r--r--arch/s390/kernel/setup.c286
-rw-r--r--arch/s390/kernel/signal.c6
-rw-r--r--arch/s390/kernel/smp.c64
-rw-r--r--arch/s390/kernel/text_amode31.S (renamed from arch/s390/boot/text_dma.S)60
-rw-r--r--arch/s390/kernel/topology.c4
-rw-r--r--arch/s390/kernel/traps.c2
-rw-r--r--arch/s390/kernel/uv.c15
-rw-r--r--arch/s390/kernel/vdso32/Makefile1
-rw-r--r--arch/s390/kernel/vdso64/Makefile1
-rw-r--r--arch/s390/kernel/vmlinux.lds.S35
-rw-r--r--arch/s390/lib/delay.c11
-rw-r--r--arch/s390/mm/dump_pagetables.c16
-rw-r--r--arch/s390/mm/fault.c13
-rw-r--r--arch/s390/mm/init.c3
-rw-r--r--arch/s390/mm/kasan_init.c43
-rw-r--r--arch/s390/mm/maccess.c4
-rw-r--r--arch/s390/mm/page-states.c43
-rw-r--r--arch/s390/mm/pageattr.c19
-rw-r--r--arch/s390/mm/vmem.c2
-rw-r--r--arch/s390/pci/pci.c79
-rw-r--r--arch/s390/pci/pci_bus.c8
-rw-r--r--arch/s390/pci/pci_bus.h5
-rw-r--r--arch/s390/pci/pci_clp.c186
-rw-r--r--arch/s390/pci/pci_dma.c25
-rw-r--r--arch/s390/pci/pci_event.c5
-rw-r--r--arch/s390/pci/pci_irq.c4
-rw-r--r--arch/s390/pci/pci_sysfs.c19
-rw-r--r--arch/s390/purgatory/Makefile1
-rw-r--r--arch/s390/tools/opcodes.txt18
-rw-r--r--arch/sh/boards/mach-se/7343/irq.c2
-rw-r--r--arch/sh/boards/mach-se/7722/irq.c2
-rw-r--r--arch/sh/boards/mach-x3proto/gpio.c2
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/Makefile53
-rw-r--r--arch/x86/boot/Makefile7
-rw-r--r--arch/x86/boot/compressed/efi_thunk_64.S30
-rw-r--r--arch/x86/boot/compressed/head_64.S3
-rw-r--r--arch/x86/boot/compressed/kaslr.c2
-rw-r--r--arch/x86/crypto/Makefile6
-rw-r--r--arch/x86/crypto/aesni-intel_glue.c5
-rw-r--r--arch/x86/crypto/sm4-aesni-avx-asm_64.S589
-rw-r--r--arch/x86/crypto/sm4-aesni-avx2-asm_64.S497
-rw-r--r--arch/x86/crypto/sm4-avx.h24
-rw-r--r--arch/x86/crypto/sm4_aesni_avx2_glue.c169
-rw-r--r--arch/x86/crypto/sm4_aesni_avx_glue.c487
-rw-r--r--arch/x86/events/Kconfig10
-rw-r--r--arch/x86/events/amd/Makefile5
-rw-r--r--arch/x86/events/amd/ibs.c32
-rw-r--r--arch/x86/events/amd/power.c1
-rw-r--r--arch/x86/events/amd/uncore.c40
-rw-r--r--arch/x86/events/core.c4
-rw-r--r--arch/x86/events/intel/core.c8
-rw-r--r--arch/x86/events/intel/pt.c6
-rw-r--r--arch/x86/events/intel/uncore.c45
-rw-r--r--arch/x86/events/intel/uncore.h4
-rw-r--r--arch/x86/events/intel/uncore_discovery.c42
-rw-r--r--arch/x86/events/intel/uncore_discovery.h21
-rw-r--r--arch/x86/events/intel/uncore_snbep.c585
-rw-r--r--arch/x86/include/asm/amd-ibs.h132
-rw-r--r--arch/x86/include/asm/kfence.h4
-rw-r--r--arch/x86/include/asm/kvm_host.h7
-rw-r--r--arch/x86/include/asm/mce.h1
-rw-r--r--arch/x86/include/asm/nospec-branch.h2
-rw-r--r--arch/x86/include/asm/processor.h4
-rw-r--r--arch/x86/include/asm/svm.h2
-rw-r--r--arch/x86/include/asm/thread_info.h6
-rw-r--r--arch/x86/include/asm/tlbflush.h2
-rw-r--r--arch/x86/kernel/apic/io_apic.c6
-rw-r--r--arch/x86/kernel/apic/msi.c11
-rw-r--r--arch/x86/kernel/cpu/amd.c2
-rw-r--r--arch/x86/kernel/cpu/bugs.c70
-rw-r--r--arch/x86/kernel/cpu/common.c6
-rw-r--r--arch/x86/kernel/cpu/mce/core.c11
-rw-r--r--arch/x86/kernel/cpu/mce/inject.c8
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c18
-rw-r--r--arch/x86/kernel/cpu/mtrr/mtrr.c8
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c276
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c163
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h231
-rw-r--r--arch/x86/kernel/cpu/resctrl/monitor.c71
-rw-r--r--arch/x86/kernel/cpu/resctrl/pseudo_lock.c12
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c461
-rw-r--r--arch/x86/kernel/hpet.c2
-rw-r--r--arch/x86/kernel/smpboot.c10
-rw-r--r--arch/x86/kvm/cpuid.c28
-rw-r--r--arch/x86/kvm/hyperv.c2
-rw-r--r--arch/x86/kvm/mmu/mmu.c28
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c35
-rw-r--r--arch/x86/kvm/svm/nested.c13
-rw-r--r--arch/x86/kvm/svm/svm.c9
-rw-r--r--arch/x86/kvm/vmx/nested.c56
-rw-r--r--arch/x86/kvm/vmx/vmx.h2
-rw-r--r--arch/x86/mm/mmio-mod.c4
-rw-r--r--arch/x86/mm/tlb.c107
-rw-r--r--arch/x86/power/cpu.c31
-rw-r--r--arch/x86/tools/chkobjdump.awk1
-rw-r--r--arch/x86/tools/relocs.c37
-rw-r--r--arch/x86/tools/relocs.h1
-rw-r--r--arch/xtensa/kernel/irq.c4
264 files changed, 6085 insertions, 2614 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index 129df498a8e1..98db63496bab 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1282,6 +1282,9 @@ config ARCH_SPLIT_ARG64
config ARCH_HAS_ELFCORE_COMPAT
bool
+config ARCH_HAS_PARANOID_L1D_FLUSH
+ bool
+
source "kernel/gcov/Kconfig"
source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index d8f51eb8963b..b5bf68e74732 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -409,7 +409,7 @@ choice
help
Depending on the configuration, CPU can contain DSP registers
(ACC0_GLO, ACC0_GHI, DSP_BFLY0, DSP_CTRL, DSP_FFT_CTRL).
- Bellow is options describing how to handle these registers in
+ Below are options describing how to handle these registers in
interrupt entry / exit and in context switch.
config ARC_DSP_NONE
diff --git a/arch/arc/include/asm/checksum.h b/arch/arc/include/asm/checksum.h
index 69debd77cd04..0b485800a392 100644
--- a/arch/arc/include/asm/checksum.h
+++ b/arch/arc/include/asm/checksum.h
@@ -24,7 +24,7 @@
*/
static inline __sum16 csum_fold(__wsum s)
{
- unsigned r = s << 16 | s >> 16; /* ror */
+ unsigned int r = s << 16 | s >> 16; /* ror */
s = ~s;
s -= r;
return s >> 16;
diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
index 30b9ae511ea9..e1971d34ef30 100644
--- a/arch/arc/include/asm/perf_event.h
+++ b/arch/arc/include/asm/perf_event.h
@@ -123,7 +123,7 @@ static const char * const arc_pmu_ev_hw_map[] = {
#define C(_x) PERF_COUNT_HW_CACHE_##_x
#define CACHE_OP_UNSUPPORTED 0xffff
-static const unsigned arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static const unsigned int arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = PERF_COUNT_ARC_LDC,
diff --git a/arch/arc/kernel/fpu.c b/arch/arc/kernel/fpu.c
index c67c0f0f5f77..ec640219d989 100644
--- a/arch/arc/kernel/fpu.c
+++ b/arch/arc/kernel/fpu.c
@@ -57,23 +57,26 @@ void fpu_save_restore(struct task_struct *prev, struct task_struct *next)
void fpu_init_task(struct pt_regs *regs)
{
+ const unsigned int fwe = 0x80000000;
+
/* default rounding mode */
write_aux_reg(ARC_REG_FPU_CTRL, 0x100);
- /* set "Write enable" to allow explicit write to exception flags */
- write_aux_reg(ARC_REG_FPU_STATUS, 0x80000000);
+ /* Initialize to zero: setting requires FWE be set */
+ write_aux_reg(ARC_REG_FPU_STATUS, fwe);
}
void fpu_save_restore(struct task_struct *prev, struct task_struct *next)
{
struct arc_fpu *save = &prev->thread.fpu;
struct arc_fpu *restore = &next->thread.fpu;
+ const unsigned int fwe = 0x80000000;
save->ctrl = read_aux_reg(ARC_REG_FPU_CTRL);
save->status = read_aux_reg(ARC_REG_FPU_STATUS);
write_aux_reg(ARC_REG_FPU_CTRL, restore->ctrl);
- write_aux_reg(ARC_REG_FPU_STATUS, restore->status);
+ write_aux_reg(ARC_REG_FPU_STATUS, (fwe | restore->status));
}
#endif
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index abf9398cc333..f9fdb557c263 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -352,7 +352,7 @@ static void idu_cascade_isr(struct irq_desc *desc)
irq_hw_number_t idu_hwirq = core_hwirq - FIRST_EXT_IRQ;
chained_irq_enter(core_chip, desc);
- generic_handle_irq(irq_find_mapping(idu_domain, idu_hwirq));
+ generic_handle_domain_irq(idu_domain, idu_hwirq);
chained_irq_exit(core_chip, desc);
}
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 47bab67f8649..9e28058cdba8 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -260,7 +260,7 @@ static void init_unwind_hdr(struct unwind_table *table,
{
const u8 *ptr;
unsigned long tableSize = table->size, hdrSize;
- unsigned n;
+ unsigned int n;
const u32 *fde;
struct {
u8 version;
@@ -462,7 +462,7 @@ static uleb128_t get_uleb128(const u8 **pcur, const u8 *end)
{
const u8 *cur = *pcur;
uleb128_t value;
- unsigned shift;
+ unsigned int shift;
for (shift = 0, value = 0; cur < end; shift += 7) {
if (shift + 7 > 8 * sizeof(value)
@@ -483,7 +483,7 @@ static sleb128_t get_sleb128(const u8 **pcur, const u8 *end)
{
const u8 *cur = *pcur;
sleb128_t value;
- unsigned shift;
+ unsigned int shift;
for (shift = 0, value = 0; cur < end; shift += 7) {
if (shift + 7 > 8 * sizeof(value)
@@ -609,7 +609,7 @@ static unsigned long read_pointer(const u8 **pLoc, const void *end,
static signed fde_pointer_type(const u32 *cie)
{
const u8 *ptr = (const u8 *)(cie + 2);
- unsigned version = *ptr;
+ unsigned int version = *ptr;
if (*++ptr) {
const char *aug;
@@ -904,7 +904,7 @@ int arc_unwind(struct unwind_frame_info *frame)
const u8 *ptr = NULL, *end = NULL;
unsigned long pc = UNW_PC(frame) - frame->call_frame;
unsigned long startLoc = 0, endLoc = 0, cfa;
- unsigned i;
+ unsigned int i;
signed ptrType = -1;
uleb128_t retAddrReg = 0;
const struct unwind_table *table;
diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S
index e2146a8da195..529ae50f9fe2 100644
--- a/arch/arc/kernel/vmlinux.lds.S
+++ b/arch/arc/kernel/vmlinux.lds.S
@@ -88,6 +88,8 @@ SECTIONS
CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
+ IRQENTRY_TEXT
+ SOFTIRQENTRY_TEXT
*(.fixup)
*(.gnu.warning)
}
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index ff5e0d04cb89..d17083c3fe2d 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -196,14 +196,6 @@ static int sa1111_map_irq(struct sa1111 *sachip, irq_hw_number_t hwirq)
return irq_create_mapping(sachip->irqdomain, hwirq);
}
-static void sa1111_handle_irqdomain(struct irq_domain *irqdomain, int irq)
-{
- struct irq_desc *d = irq_to_desc(irq_linear_revmap(irqdomain, irq));
-
- if (d)
- generic_handle_irq_desc(d);
-}
-
/*
* SA1111 interrupt support. Since clearing an IRQ while there are
* active IRQs causes the interrupt output to pulse, the upper levels
@@ -234,11 +226,11 @@ static void sa1111_irq_handler(struct irq_desc *desc)
for (i = 0; stat0; i++, stat0 >>= 1)
if (stat0 & 1)
- sa1111_handle_irqdomain(irqdomain, i);
+ generic_handle_domain_irq(irqdomain, i);
for (i = 32; stat1; i++, stat1 >>= 1)
if (stat1 & 1)
- sa1111_handle_irqdomain(irqdomain, i);
+ generic_handle_domain_irq(irqdomain, i);
/* For level-based interrupts */
desc->irq_data.chip->irq_unmask(&desc->irq_data);
diff --git a/arch/arm/configs/nhk8815_defconfig b/arch/arm/configs/nhk8815_defconfig
index 3f35761dc9ff..23595fc5a29a 100644
--- a/arch/arm/configs/nhk8815_defconfig
+++ b/arch/arm/configs/nhk8815_defconfig
@@ -15,8 +15,6 @@ CONFIG_SLAB=y
CONFIG_ARCH_NOMADIK=y
CONFIG_MACH_NOMADIK_8815NHK=y
CONFIG_AEABI=y
-CONFIG_ZBOOT_ROM_TEXT=0x0
-CONFIG_ZBOOT_ROM_BSS=0x0
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
# CONFIG_BLK_DEV_BSG is not set
@@ -52,9 +50,9 @@ CONFIG_MTD_BLOCK=y
CONFIG_MTD_ONENAND=y
CONFIG_MTD_ONENAND_VERIFY_WRITE=y
CONFIG_MTD_ONENAND_GENERIC=y
-CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC=y
CONFIG_MTD_RAW_NAND=y
CONFIG_MTD_NAND_FSMC=y
+CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC=y
CONFIG_BLK_DEV_LOOP=y
CONFIG_BLK_DEV_CRYPTOLOOP=y
CONFIG_BLK_DEV_RAM=y
@@ -97,6 +95,7 @@ CONFIG_REGULATOR=y
CONFIG_DRM=y
CONFIG_DRM_PANEL_TPO_TPG110=y
CONFIG_DRM_PL111=y
+CONFIG_FB=y
CONFIG_BACKLIGHT_CLASS_DEVICE=y
CONFIG_BACKLIGHT_PWM=y
CONFIG_FRAMEBUFFER_CONSOLE=y
@@ -136,9 +135,8 @@ CONFIG_NLS_ISO8859_15=y
CONFIG_CRYPTO_MD5=y
CONFIG_CRYPTO_SHA1=y
CONFIG_CRYPTO_DES=y
+# CONFIG_DEBUG_BUGVERBOSE is not set
CONFIG_DEBUG_INFO=y
-# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_DEBUG_FS=y
# CONFIG_SCHED_DEBUG is not set
# CONFIG_DEBUG_PREEMPT is not set
-# CONFIG_DEBUG_BUGVERBOSE is not set
diff --git a/arch/arm/crypto/curve25519-glue.c b/arch/arm/crypto/curve25519-glue.c
index 31eb75b6002f..9bdafd57888c 100644
--- a/arch/arm/crypto/curve25519-glue.c
+++ b/arch/arm/crypto/curve25519-glue.c
@@ -112,7 +112,7 @@ static struct kpp_alg curve25519_alg = {
.max_size = curve25519_max_size,
};
-static int __init mod_init(void)
+static int __init arm_curve25519_init(void)
{
if (elf_hwcap & HWCAP_NEON) {
static_branch_enable(&have_neon);
@@ -122,14 +122,14 @@ static int __init mod_init(void)
return 0;
}
-static void __exit mod_exit(void)
+static void __exit arm_curve25519_exit(void)
{
if (IS_REACHABLE(CONFIG_CRYPTO_KPP) && elf_hwcap & HWCAP_NEON)
crypto_unregister_kpp(&curve25519_alg);
}
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(arm_curve25519_init);
+module_exit(arm_curve25519_exit);
MODULE_ALIAS_CRYPTO("curve25519");
MODULE_ALIAS_CRYPTO("curve25519-neon");
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index cfc9dfd70aad..f673e13e0f94 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -160,10 +160,11 @@ extern unsigned long vectors_base;
/*
* Physical start and end address of the kernel sections. These addresses are
- * 2MB-aligned to match the section mappings placed over the kernel.
+ * 2MB-aligned to match the section mappings placed over the kernel. We use
+ * u64 so that LPAE mappings beyond the 32bit limit will work out as well.
*/
-extern u32 kernel_sec_start;
-extern u32 kernel_sec_end;
+extern u64 kernel_sec_start;
+extern u64 kernel_sec_end;
/*
* Physical vs virtual RAM address space conversion. These are
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 9eb0b4dbcc12..29070eb8df7d 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -49,7 +49,8 @@
/*
* This needs to be assigned at runtime when the linker symbols are
- * resolved.
+ * resolved. These are unsigned 64bit really, but in this assembly code
+ * We store them as 32bit.
*/
.pushsection .data
.align 2
@@ -57,8 +58,10 @@
.globl kernel_sec_end
kernel_sec_start:
.long 0
+ .long 0
kernel_sec_end:
.long 0
+ .long 0
.popsection
.macro pgtbl, rd, phys
@@ -250,7 +253,11 @@ __create_page_tables:
add r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ORDER)
ldr r6, =(_end - 1)
adr_l r5, kernel_sec_start @ _pa(kernel_sec_start)
- str r8, [r5] @ Save physical start of kernel
+#ifdef CONFIG_CPU_ENDIAN_BE8
+ str r8, [r5, #4] @ Save physical start of kernel (BE)
+#else
+ str r8, [r5] @ Save physical start of kernel (LE)
+#endif
orr r3, r8, r7 @ Add the MMU flags
add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
1: str r3, [r0], #1 << PMD_ORDER
@@ -259,7 +266,11 @@ __create_page_tables:
bls 1b
eor r3, r3, r7 @ Remove the MMU flags
adr_l r5, kernel_sec_end @ _pa(kernel_sec_end)
- str r3, [r5] @ Save physical end of kernel
+#ifdef CONFIG_CPU_ENDIAN_BE8
+ str r3, [r5, #4] @ Save physical end of kernel (BE)
+#else
+ str r3, [r5] @ Save physical end of kernel (LE)
+#endif
#ifdef CONFIG_XIP_KERNEL
/*
diff --git a/arch/arm/mach-ixp4xx/include/mach/ixp4xx-regs.h b/arch/arm/mach-ixp4xx/include/mach/ixp4xx-regs.h
index abb07f105515..74e63d4531aa 100644
--- a/arch/arm/mach-ixp4xx/include/mach/ixp4xx-regs.h
+++ b/arch/arm/mach-ixp4xx/include/mach/ixp4xx-regs.h
@@ -218,30 +218,30 @@
/*
* PCI Control/Status Registers
*/
-#define IXP4XX_PCI_CSR(x) ((volatile u32 *)(IXP4XX_PCI_CFG_BASE_VIRT+(x)))
-
-#define PCI_NP_AD IXP4XX_PCI_CSR(PCI_NP_AD_OFFSET)
-#define PCI_NP_CBE IXP4XX_PCI_CSR(PCI_NP_CBE_OFFSET)
-#define PCI_NP_WDATA IXP4XX_PCI_CSR(PCI_NP_WDATA_OFFSET)
-#define PCI_NP_RDATA IXP4XX_PCI_CSR(PCI_NP_RDATA_OFFSET)
-#define PCI_CRP_AD_CBE IXP4XX_PCI_CSR(PCI_CRP_AD_CBE_OFFSET)
-#define PCI_CRP_WDATA IXP4XX_PCI_CSR(PCI_CRP_WDATA_OFFSET)
-#define PCI_CRP_RDATA IXP4XX_PCI_CSR(PCI_CRP_RDATA_OFFSET)
-#define PCI_CSR IXP4XX_PCI_CSR(PCI_CSR_OFFSET)
-#define PCI_ISR IXP4XX_PCI_CSR(PCI_ISR_OFFSET)
-#define PCI_INTEN IXP4XX_PCI_CSR(PCI_INTEN_OFFSET)
-#define PCI_DMACTRL IXP4XX_PCI_CSR(PCI_DMACTRL_OFFSET)
-#define PCI_AHBMEMBASE IXP4XX_PCI_CSR(PCI_AHBMEMBASE_OFFSET)
-#define PCI_AHBIOBASE IXP4XX_PCI_CSR(PCI_AHBIOBASE_OFFSET)
-#define PCI_PCIMEMBASE IXP4XX_PCI_CSR(PCI_PCIMEMBASE_OFFSET)
-#define PCI_AHBDOORBELL IXP4XX_PCI_CSR(PCI_AHBDOORBELL_OFFSET)
-#define PCI_PCIDOORBELL IXP4XX_PCI_CSR(PCI_PCIDOORBELL_OFFSET)
-#define PCI_ATPDMA0_AHBADDR IXP4XX_PCI_CSR(PCI_ATPDMA0_AHBADDR_OFFSET)
-#define PCI_ATPDMA0_PCIADDR IXP4XX_PCI_CSR(PCI_ATPDMA0_PCIADDR_OFFSET)
-#define PCI_ATPDMA0_LENADDR IXP4XX_PCI_CSR(PCI_ATPDMA0_LENADDR_OFFSET)
-#define PCI_ATPDMA1_AHBADDR IXP4XX_PCI_CSR(PCI_ATPDMA1_AHBADDR_OFFSET)
-#define PCI_ATPDMA1_PCIADDR IXP4XX_PCI_CSR(PCI_ATPDMA1_PCIADDR_OFFSET)
-#define PCI_ATPDMA1_LENADDR IXP4XX_PCI_CSR(PCI_ATPDMA1_LENADDR_OFFSET)
+#define _IXP4XX_PCI_CSR(x) ((volatile u32 *)(IXP4XX_PCI_CFG_BASE_VIRT+(x)))
+
+#define PCI_NP_AD _IXP4XX_PCI_CSR(PCI_NP_AD_OFFSET)
+#define PCI_NP_CBE _IXP4XX_PCI_CSR(PCI_NP_CBE_OFFSET)
+#define PCI_NP_WDATA _IXP4XX_PCI_CSR(PCI_NP_WDATA_OFFSET)
+#define PCI_NP_RDATA _IXP4XX_PCI_CSR(PCI_NP_RDATA_OFFSET)
+#define PCI_CRP_AD_CBE _IXP4XX_PCI_CSR(PCI_CRP_AD_CBE_OFFSET)
+#define PCI_CRP_WDATA _IXP4XX_PCI_CSR(PCI_CRP_WDATA_OFFSET)
+#define PCI_CRP_RDATA _IXP4XX_PCI_CSR(PCI_CRP_RDATA_OFFSET)
+#define PCI_CSR _IXP4XX_PCI_CSR(PCI_CSR_OFFSET)
+#define PCI_ISR _IXP4XX_PCI_CSR(PCI_ISR_OFFSET)
+#define PCI_INTEN _IXP4XX_PCI_CSR(PCI_INTEN_OFFSET)
+#define PCI_DMACTRL _IXP4XX_PCI_CSR(PCI_DMACTRL_OFFSET)
+#define PCI_AHBMEMBASE _IXP4XX_PCI_CSR(PCI_AHBMEMBASE_OFFSET)
+#define PCI_AHBIOBASE _IXP4XX_PCI_CSR(PCI_AHBIOBASE_OFFSET)
+#define PCI_PCIMEMBASE _IXP4XX_PCI_CSR(PCI_PCIMEMBASE_OFFSET)
+#define PCI_AHBDOORBELL _IXP4XX_PCI_CSR(PCI_AHBDOORBELL_OFFSET)
+#define PCI_PCIDOORBELL _IXP4XX_PCI_CSR(PCI_PCIDOORBELL_OFFSET)
+#define PCI_ATPDMA0_AHBADDR _IXP4XX_PCI_CSR(PCI_ATPDMA0_AHBADDR_OFFSET)
+#define PCI_ATPDMA0_PCIADDR _IXP4XX_PCI_CSR(PCI_ATPDMA0_PCIADDR_OFFSET)
+#define PCI_ATPDMA0_LENADDR _IXP4XX_PCI_CSR(PCI_ATPDMA0_LENADDR_OFFSET)
+#define PCI_ATPDMA1_AHBADDR _IXP4XX_PCI_CSR(PCI_ATPDMA1_AHBADDR_OFFSET)
+#define PCI_ATPDMA1_PCIADDR _IXP4XX_PCI_CSR(PCI_ATPDMA1_PCIADDR_OFFSET)
+#define PCI_ATPDMA1_LENADDR _IXP4XX_PCI_CSR(PCI_ATPDMA1_LENADDR_OFFSET)
/*
* PCI register values and bit definitions
diff --git a/arch/arm/mach-pxa/pxa_cplds_irqs.c b/arch/arm/mach-pxa/pxa_cplds_irqs.c
index bddfc7cd5d40..eda5a47d7fbb 100644
--- a/arch/arm/mach-pxa/pxa_cplds_irqs.c
+++ b/arch/arm/mach-pxa/pxa_cplds_irqs.c
@@ -39,10 +39,8 @@ static irqreturn_t cplds_irq_handler(int in_irq, void *d)
do {
pending = readl(fpga->base + FPGA_IRQ_SET_CLR) & fpga->irq_mask;
- for_each_set_bit(bit, &pending, CPLDS_NB_IRQ) {
- generic_handle_irq(irq_find_mapping(fpga->irqdomain,
- bit));
- }
+ for_each_set_bit(bit, &pending, CPLDS_NB_IRQ)
+ generic_handle_domain_irq(fpga->irqdomain, bit);
} while (pending);
return IRQ_HANDLED;
diff --git a/arch/arm/mach-s3c/irq-s3c24xx.c b/arch/arm/mach-s3c/irq-s3c24xx.c
index 0c631c14a817..3edc5f614eef 100644
--- a/arch/arm/mach-s3c/irq-s3c24xx.c
+++ b/arch/arm/mach-s3c/irq-s3c24xx.c
@@ -298,7 +298,7 @@ static void s3c_irq_demux(struct irq_desc *desc)
struct s3c_irq_data *irq_data = irq_desc_get_chip_data(desc);
struct s3c_irq_intc *intc = irq_data->intc;
struct s3c_irq_intc *sub_intc = irq_data->sub_intc;
- unsigned int n, offset, irq;
+ unsigned int n, offset;
unsigned long src, msk;
/* we're using individual domains for the non-dt case
@@ -318,8 +318,7 @@ static void s3c_irq_demux(struct irq_desc *desc)
while (src) {
n = __ffs(src);
src &= ~(1 << n);
- irq = irq_find_mapping(sub_intc->domain, offset + n);
- generic_handle_irq(irq);
+ generic_handle_domain_irq(sub_intc->domain, offset + n);
}
chained_irq_exit(chip, desc);
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 7583bda5ea7d..a4e006005107 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1609,6 +1609,13 @@ static void __init early_paging_init(const struct machine_desc *mdesc)
return;
/*
+ * Offset the kernel section physical offsets so that the kernel
+ * mapping will work out later on.
+ */
+ kernel_sec_start += offset;
+ kernel_sec_end += offset;
+
+ /*
* Get the address of the remap function in the 1:1 identity
* mapping setup by the early page table assembly code. We
* must get this prior to the pv update. The following barrier
@@ -1716,7 +1723,7 @@ void __init paging_init(const struct machine_desc *mdesc)
{
void *zero_page;
- pr_debug("physical kernel sections: 0x%08x-0x%08x\n",
+ pr_debug("physical kernel sections: 0x%08llx-0x%08llx\n",
kernel_sec_start, kernel_sec_end);
prepare_page_table();
diff --git a/arch/arm/mm/pv-fixup-asm.S b/arch/arm/mm/pv-fixup-asm.S
index 5c5e1952000a..f8e11f7c7880 100644
--- a/arch/arm/mm/pv-fixup-asm.S
+++ b/arch/arm/mm/pv-fixup-asm.S
@@ -29,7 +29,7 @@ ENTRY(lpae_pgtables_remap_asm)
ldr r6, =(_end - 1)
add r7, r2, #0x1000
add r6, r7, r6, lsr #SECTION_SHIFT - L2_ORDER
- add r7, r7, #PAGE_OFFSET >> (SECTION_SHIFT - L2_ORDER)
+ add r7, r7, #KERNEL_OFFSET >> (SECTION_SHIFT - L2_ORDER)
1: ldrd r4, r5, [r7]
adds r4, r4, r0
adc r5, r5, r1
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index fdcd54d39c1e..62c3c1d2190f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -156,6 +156,7 @@ config ARM64
select HAVE_ARCH_KGDB
select HAVE_ARCH_MMAP_RND_BITS
select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
+ select HAVE_ARCH_PFN_VALID
select HAVE_ARCH_PREL32_RELOCATIONS
select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
select HAVE_ARCH_SECCOMP_FILTER
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 7b668db43261..1110d386f3b4 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -183,6 +183,8 @@ endif
# We use MRPROPER_FILES and CLEAN_FILES now
archclean:
$(Q)$(MAKE) $(clean)=$(boot)
+ $(Q)$(MAKE) $(clean)=arch/arm64/kernel/vdso
+ $(Q)$(MAKE) $(clean)=arch/arm64/kernel/vdso32
ifeq ($(KBUILD_EXTMOD),)
# We need to generate vdso-offsets.h before compiling certain files in kernel/.
diff --git a/arch/arm64/boot/dts/qcom/msm8992-bullhead-rev-101.dts b/arch/arm64/boot/dts/qcom/msm8992-bullhead-rev-101.dts
index 23cdcc9f7c72..1ccca83292ac 100644
--- a/arch/arm64/boot/dts/qcom/msm8992-bullhead-rev-101.dts
+++ b/arch/arm64/boot/dts/qcom/msm8992-bullhead-rev-101.dts
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2015, LGE Inc. All rights reserved.
* Copyright (c) 2016, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021, Petr Vorel <petr.vorel@gmail.com>
*/
/dts-v1/;
@@ -9,6 +10,9 @@
#include "pm8994.dtsi"
#include "pmi8994.dtsi"
+/* cont_splash_mem has different memory mapping */
+/delete-node/ &cont_splash_mem;
+
/ {
model = "LG Nexus 5X";
compatible = "lg,bullhead", "qcom,msm8992";
@@ -17,6 +21,9 @@
qcom,board-id = <0xb64 0>;
qcom,pmic-id = <0x10009 0x1000A 0x0 0x0>;
+ /* Bullhead firmware doesn't support PSCI */
+ /delete-node/ psci;
+
aliases {
serial0 = &blsp1_uart2;
};
@@ -38,6 +45,11 @@
ftrace-size = <0x10000>;
pmsg-size = <0x20000>;
};
+
+ cont_splash_mem: memory@3400000 {
+ reg = <0 0x03400000 0 0x1200000>;
+ no-map;
+ };
};
};
diff --git a/arch/arm64/boot/dts/qcom/msm8994-angler-rev-101.dts b/arch/arm64/boot/dts/qcom/msm8994-angler-rev-101.dts
index ffe1a9bd8f70..c096b7758aa0 100644
--- a/arch/arm64/boot/dts/qcom/msm8994-angler-rev-101.dts
+++ b/arch/arm64/boot/dts/qcom/msm8994-angler-rev-101.dts
@@ -1,12 +1,16 @@
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2015, Huawei Inc. All rights reserved.
* Copyright (c) 2016, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021, Petr Vorel <petr.vorel@gmail.com>
*/
/dts-v1/;
#include "msm8994.dtsi"
+/* Angler's firmware does not report where the memory is allocated */
+/delete-node/ &cont_splash_mem;
+
/ {
model = "Huawei Nexus 6P";
compatible = "huawei,angler", "qcom,msm8994";
diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi
index a8c274ad74c4..188c5768a55a 100644
--- a/arch/arm64/boot/dts/qcom/sc7280.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi
@@ -200,7 +200,7 @@
&BIG_CPU_SLEEP_1
&CLUSTER_SLEEP_0>;
next-level-cache = <&L2_700>;
- qcom,freq-domain = <&cpufreq_hw 1>;
+ qcom,freq-domain = <&cpufreq_hw 2>;
#cooling-cells = <2>;
L2_700: l2-cache {
compatible = "cache";
diff --git a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi
index 4d052e39b348..eb6b1d15293d 100644
--- a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi
@@ -69,7 +69,7 @@
};
rmtfs_upper_guard: memory@f5d01000 {
no-map;
- reg = <0 0xf5d01000 0 0x2000>;
+ reg = <0 0xf5d01000 0 0x1000>;
};
/*
@@ -78,7 +78,7 @@
*/
removed_region: memory@88f00000 {
no-map;
- reg = <0 0x88f00000 0 0x200000>;
+ reg = <0 0x88f00000 0 0x1c00000>;
};
ramoops: ramoops@ac300000 {
diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
index c2a709a384e9..d7591a4621a2 100644
--- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
+++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
@@ -700,7 +700,7 @@
left_spkr: wsa8810-left{
compatible = "sdw10217211000";
reg = <0 3>;
- powerdown-gpios = <&wcdgpio 2 GPIO_ACTIVE_HIGH>;
+ powerdown-gpios = <&wcdgpio 1 GPIO_ACTIVE_HIGH>;
#thermal-sensor-cells = <0>;
sound-name-prefix = "SpkrLeft";
#sound-dai-cells = <0>;
@@ -708,7 +708,7 @@
right_spkr: wsa8810-right{
compatible = "sdw10217211000";
- powerdown-gpios = <&wcdgpio 3 GPIO_ACTIVE_HIGH>;
+ powerdown-gpios = <&wcdgpio 2 GPIO_ACTIVE_HIGH>;
reg = <0 4>;
#thermal-sensor-cells = <0>;
sound-name-prefix = "SpkrRight";
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index b8eb0453123d..55f19450091b 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -51,7 +51,7 @@ config CRYPTO_SM4_ARM64_CE
tristate "SM4 symmetric cipher (ARMv8.2 Crypto Extensions)"
depends on KERNEL_MODE_NEON
select CRYPTO_ALGAPI
- select CRYPTO_SM4
+ select CRYPTO_LIB_SM4
config CRYPTO_GHASH_ARM64_CE
tristate "GHASH/AES-GCM using ARMv8 Crypto Extensions"
diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-glue.c
index 2754c875d39c..9c93cfc4841b 100644
--- a/arch/arm64/crypto/sm4-ce-glue.c
+++ b/arch/arm64/crypto/sm4-ce-glue.c
@@ -17,12 +17,20 @@ MODULE_LICENSE("GPL v2");
asmlinkage void sm4_ce_do_crypt(const u32 *rk, void *out, const void *in);
+static int sm4_ce_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int key_len)
+{
+ struct sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ return sm4_expandkey(ctx, key, key_len);
+}
+
static void sm4_ce_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
{
- const struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+ const struct sm4_ctx *ctx = crypto_tfm_ctx(tfm);
if (!crypto_simd_usable()) {
- crypto_sm4_encrypt(tfm, out, in);
+ sm4_crypt_block(ctx->rkey_enc, out, in);
} else {
kernel_neon_begin();
sm4_ce_do_crypt(ctx->rkey_enc, out, in);
@@ -32,10 +40,10 @@ static void sm4_ce_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
static void sm4_ce_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
{
- const struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+ const struct sm4_ctx *ctx = crypto_tfm_ctx(tfm);
if (!crypto_simd_usable()) {
- crypto_sm4_decrypt(tfm, out, in);
+ sm4_crypt_block(ctx->rkey_dec, out, in);
} else {
kernel_neon_begin();
sm4_ce_do_crypt(ctx->rkey_dec, out, in);
@@ -49,12 +57,12 @@ static struct crypto_alg sm4_ce_alg = {
.cra_priority = 200,
.cra_flags = CRYPTO_ALG_TYPE_CIPHER,
.cra_blocksize = SM4_BLOCK_SIZE,
- .cra_ctxsize = sizeof(struct crypto_sm4_ctx),
+ .cra_ctxsize = sizeof(struct sm4_ctx),
.cra_module = THIS_MODULE,
.cra_u.cipher = {
.cia_min_keysize = SM4_KEY_SIZE,
.cia_max_keysize = SM4_KEY_SIZE,
- .cia_setkey = crypto_sm4_set_key,
+ .cia_setkey = sm4_ce_setkey,
.cia_encrypt = sm4_ce_encrypt,
.cia_decrypt = sm4_ce_decrypt
}
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index 21fa330f498d..b83fb24954b7 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -33,8 +33,7 @@
* EL2.
*/
.macro __init_el2_timers
- mrs x0, cnthctl_el2
- orr x0, x0, #3 // Enable EL1 physical timers
+ mov x0, #3 // Enable EL1 physical timers
msr cnthctl_el2, x0
msr cntvoff_el2, xzr // Clear virtual offset
.endm
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 993a27ea6f54..f98c91bbd7c1 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -41,6 +41,7 @@ void tag_clear_highpage(struct page *to);
typedef struct page *pgtable_t;
+int pfn_valid(unsigned long pfn);
int pfn_is_map_memory(unsigned long pfn);
#include <asm/memory.h>
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index e9a2b8f27792..0ca72f5cda41 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -94,10 +94,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
kvm->arch.return_nisv_io_abort_to_user = true;
break;
case KVM_CAP_ARM_MTE:
- if (!system_supports_mte() || kvm->created_vcpus)
- return -EINVAL;
- r = 0;
- kvm->arch.mte_enabled = true;
+ mutex_lock(&kvm->lock);
+ if (!system_supports_mte() || kvm->created_vcpus) {
+ r = -EINVAL;
+ } else {
+ r = 0;
+ kvm->arch.mte_enabled = true;
+ }
+ mutex_unlock(&kvm->lock);
break;
default:
r = -EINVAL;
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index d938ce95d3bd..a6ce991b1467 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -193,7 +193,7 @@ static bool range_is_memory(u64 start, u64 end)
{
struct kvm_mem_range r1, r2;
- if (!find_mem_range(start, &r1) || !find_mem_range(end, &r2))
+ if (!find_mem_range(start, &r1) || !find_mem_range(end - 1, &r2))
return false;
if (r1.start != r2.start)
return false;
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 8490ed2917ff..1fdb7bb7c198 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -219,6 +219,43 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
free_area_init(max_zone_pfns);
}
+int pfn_valid(unsigned long pfn)
+{
+ phys_addr_t addr = PFN_PHYS(pfn);
+ struct mem_section *ms;
+
+ /*
+ * Ensure the upper PAGE_SHIFT bits are clear in the
+ * pfn. Else it might lead to false positives when
+ * some of the upper bits are set, but the lower bits
+ * match a valid pfn.
+ */
+ if (PHYS_PFN(addr) != pfn)
+ return 0;
+
+ if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
+ return 0;
+
+ ms = __pfn_to_section(pfn);
+ if (!valid_section(ms))
+ return 0;
+
+ /*
+ * ZONE_DEVICE memory does not have the memblock entries.
+ * memblock_is_map_memory() check for ZONE_DEVICE based
+ * addresses will always fail. Even the normal hotplugged
+ * memory will never have MEMBLOCK_NOMAP flag set in their
+ * memblock entries. Skip memblock search for all non early
+ * memory sections covering all of hotplug memory including
+ * both normal and ZONE_DEVICE based.
+ */
+ if (!early_section(ms))
+ return pfn_section_valid(ms, pfn);
+
+ return memblock_is_memory(addr);
+}
+EXPORT_SYMBOL(pfn_valid);
+
int pfn_is_map_memory(unsigned long pfn)
{
phys_addr_t addr = PFN_PHYS(pfn);
diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu
index 29e946394fdb..277d61a09463 100644
--- a/arch/m68k/Kconfig.cpu
+++ b/arch/m68k/Kconfig.cpu
@@ -26,6 +26,7 @@ config COLDFIRE
bool "Coldfire CPU family support"
select ARCH_HAVE_CUSTOM_GPIO_H
select CPU_HAS_NO_BITFIELDS
+ select CPU_HAS_NO_CAS
select CPU_HAS_NO_MULDIV64
select GENERIC_CSUM
select GPIOLIB
@@ -39,6 +40,7 @@ config M68000
bool
depends on !MMU
select CPU_HAS_NO_BITFIELDS
+ select CPU_HAS_NO_CAS
select CPU_HAS_NO_MULDIV64
select CPU_HAS_NO_UNALIGNED
select GENERIC_CSUM
@@ -54,6 +56,7 @@ config M68000
config MCPU32
bool
select CPU_HAS_NO_BITFIELDS
+ select CPU_HAS_NO_CAS
select CPU_HAS_NO_UNALIGNED
select CPU_NO_EFFICIENT_FFS
help
@@ -383,7 +386,7 @@ config ADVANCED
config RMW_INSNS
bool "Use read-modify-write instructions"
- depends on ADVANCED
+ depends on ADVANCED && !CPU_HAS_NO_CAS
help
This allows to use certain instructions that work with indivisible
read-modify-write bus cycles. While this is faster than the
@@ -450,6 +453,9 @@ config M68K_L2_CACHE
config CPU_HAS_NO_BITFIELDS
bool
+config CPU_HAS_NO_CAS
+ bool
+
config CPU_HAS_NO_MULDIV64
bool
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 0a2cacf7be08..5f536286f5fc 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -84,6 +84,7 @@ CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_ZONES=y
# CONFIG_NF_CONNTRACK_PROCFS is not set
@@ -323,7 +324,6 @@ CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
CONFIG_RAID_ATTRS=m
-CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
CONFIG_CHR_DEV_ST=m
CONFIG_BLK_DEV_SR=y
@@ -502,6 +502,7 @@ CONFIG_ROOT_NFS=y
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
CONFIG_CIFS=m
+# CONFIG_CIFS_STATS2 is not set
# CONFIG_CIFS_DEBUG is not set
CONFIG_CODA_FS=m
CONFIG_NLS_CODEPAGE_437=y
@@ -616,6 +617,7 @@ CONFIG_PRIME_NUMBERS=m
CONFIG_CRC32_SELFTEST=m
CONFIG_CRC64=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_GLOB_SELFTEST=m
CONFIG_STRING_SELFTEST=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
@@ -624,7 +626,6 @@ CONFIG_WW_MUTEX_SELFTEST=m
CONFIG_EARLY_PRINTK=y
CONFIG_KUNIT=m
CONFIG_KUNIT_ALL_TESTS=m
-CONFIG_TEST_LIST_SORT=m
CONFIG_TEST_MIN_HEAP=m
CONFIG_TEST_SORT=m
CONFIG_TEST_DIV64=m
@@ -636,6 +637,7 @@ CONFIG_TEST_STRING_HELPERS=m
CONFIG_TEST_STRSCPY=m
CONFIG_TEST_KSTRTOX=m
CONFIG_TEST_PRINTF=m
+CONFIG_TEST_SCANF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
CONFIG_TEST_XARRAY=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 4dc6dcfaf28a..d9568644051a 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -80,6 +80,7 @@ CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_ZONES=y
# CONFIG_NF_CONNTRACK_PROCFS is not set
@@ -458,6 +459,7 @@ CONFIG_ROOT_NFS=y
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
CONFIG_CIFS=m
+# CONFIG_CIFS_STATS2 is not set
# CONFIG_CIFS_DEBUG is not set
CONFIG_CODA_FS=m
CONFIG_NLS_CODEPAGE_437=y
@@ -580,7 +582,6 @@ CONFIG_WW_MUTEX_SELFTEST=m
CONFIG_EARLY_PRINTK=y
CONFIG_KUNIT=m
CONFIG_KUNIT_ALL_TESTS=m
-CONFIG_TEST_LIST_SORT=m
CONFIG_TEST_MIN_HEAP=m
CONFIG_TEST_SORT=m
CONFIG_TEST_DIV64=m
@@ -592,6 +593,7 @@ CONFIG_TEST_STRING_HELPERS=m
CONFIG_TEST_STRSCPY=m
CONFIG_TEST_KSTRTOX=m
CONFIG_TEST_PRINTF=m
+CONFIG_TEST_SCANF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
CONFIG_TEST_XARRAY=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 23d910a692ab..dbf1960c6669 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -87,6 +87,7 @@ CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_ZONES=y
# CONFIG_NF_CONNTRACK_PROCFS is not set
@@ -324,7 +325,6 @@ CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
CONFIG_RAID_ATTRS=m
-CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
CONFIG_CHR_DEV_ST=m
CONFIG_BLK_DEV_SR=y
@@ -480,6 +480,7 @@ CONFIG_ROOT_NFS=y
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
CONFIG_CIFS=m
+# CONFIG_CIFS_STATS2 is not set
# CONFIG_CIFS_DEBUG is not set
CONFIG_CODA_FS=m
CONFIG_NLS_CODEPAGE_437=y
@@ -594,6 +595,7 @@ CONFIG_PRIME_NUMBERS=m
CONFIG_CRC32_SELFTEST=m
CONFIG_CRC64=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_GLOB_SELFTEST=m
CONFIG_STRING_SELFTEST=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
@@ -602,7 +604,6 @@ CONFIG_WW_MUTEX_SELFTEST=m
CONFIG_EARLY_PRINTK=y
CONFIG_KUNIT=m
CONFIG_KUNIT_ALL_TESTS=m
-CONFIG_TEST_LIST_SORT=m
CONFIG_TEST_MIN_HEAP=m
CONFIG_TEST_SORT=m
CONFIG_TEST_DIV64=m
@@ -614,6 +615,7 @@ CONFIG_TEST_STRING_HELPERS=m
CONFIG_TEST_STRSCPY=m
CONFIG_TEST_KSTRTOX=m
CONFIG_TEST_PRINTF=m
+CONFIG_TEST_SCANF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
CONFIG_TEST_XARRAY=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 2c3f42833846..7620db3e33e7 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -77,6 +77,7 @@ CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_ZONES=y
# CONFIG_NF_CONNTRACK_PROCFS is not set
@@ -451,6 +452,7 @@ CONFIG_ROOT_NFS=y
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
CONFIG_CIFS=m
+# CONFIG_CIFS_STATS2 is not set
# CONFIG_CIFS_DEBUG is not set
CONFIG_CODA_FS=m
CONFIG_NLS_CODEPAGE_437=y
@@ -573,7 +575,6 @@ CONFIG_WW_MUTEX_SELFTEST=m
CONFIG_EARLY_PRINTK=y
CONFIG_KUNIT=m
CONFIG_KUNIT_ALL_TESTS=m
-CONFIG_TEST_LIST_SORT=m
CONFIG_TEST_MIN_HEAP=m
CONFIG_TEST_SORT=m
CONFIG_TEST_DIV64=m
@@ -585,6 +586,7 @@ CONFIG_TEST_STRING_HELPERS=m
CONFIG_TEST_STRSCPY=m
CONFIG_TEST_KSTRTOX=m
CONFIG_TEST_PRINTF=m
+CONFIG_TEST_SCANF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
CONFIG_TEST_XARRAY=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 5b1898d4b249..113a02d47ebb 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -79,6 +79,7 @@ CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_ZONES=y
# CONFIG_NF_CONNTRACK_PROCFS is not set
@@ -460,6 +461,7 @@ CONFIG_ROOT_NFS=y
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
CONFIG_CIFS=m
+# CONFIG_CIFS_STATS2 is not set
# CONFIG_CIFS_DEBUG is not set
CONFIG_CODA_FS=m
CONFIG_NLS_CODEPAGE_437=y
@@ -582,7 +584,6 @@ CONFIG_WW_MUTEX_SELFTEST=m
CONFIG_EARLY_PRINTK=y
CONFIG_KUNIT=m
CONFIG_KUNIT_ALL_TESTS=m
-CONFIG_TEST_LIST_SORT=m
CONFIG_TEST_MIN_HEAP=m
CONFIG_TEST_SORT=m
CONFIG_TEST_DIV64=m
@@ -594,6 +595,7 @@ CONFIG_TEST_STRING_HELPERS=m
CONFIG_TEST_STRSCPY=m
CONFIG_TEST_KSTRTOX=m
CONFIG_TEST_PRINTF=m
+CONFIG_TEST_SCANF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
CONFIG_TEST_XARRAY=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 9606ccd8dafa..a8e006e8da66 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -78,6 +78,7 @@ CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_ZONES=y
# CONFIG_NF_CONNTRACK_PROCFS is not set
@@ -315,7 +316,6 @@ CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
CONFIG_RAID_ATTRS=m
-CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
CONFIG_CHR_DEV_ST=m
CONFIG_BLK_DEV_SR=y
@@ -482,6 +482,7 @@ CONFIG_ROOT_NFS=y
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
CONFIG_CIFS=m
+# CONFIG_CIFS_STATS2 is not set
# CONFIG_CIFS_DEBUG is not set
CONFIG_CODA_FS=m
CONFIG_NLS_CODEPAGE_437=y
@@ -596,6 +597,7 @@ CONFIG_PRIME_NUMBERS=m
CONFIG_CRC32_SELFTEST=m
CONFIG_CRC64=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_GLOB_SELFTEST=m
CONFIG_STRING_SELFTEST=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
@@ -604,7 +606,6 @@ CONFIG_WW_MUTEX_SELFTEST=m
CONFIG_EARLY_PRINTK=y
CONFIG_KUNIT=m
CONFIG_KUNIT_ALL_TESTS=m
-CONFIG_TEST_LIST_SORT=m
CONFIG_TEST_MIN_HEAP=m
CONFIG_TEST_SORT=m
CONFIG_TEST_DIV64=m
@@ -616,6 +617,7 @@ CONFIG_TEST_STRING_HELPERS=m
CONFIG_TEST_STRSCPY=m
CONFIG_TEST_KSTRTOX=m
CONFIG_TEST_PRINTF=m
+CONFIG_TEST_SCANF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
CONFIG_TEST_XARRAY=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 3175ba5007e1..b6655907a1f3 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -98,6 +98,7 @@ CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_ZONES=y
# CONFIG_NF_CONNTRACK_PROCFS is not set
@@ -344,7 +345,6 @@ CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
CONFIG_RAID_ATTRS=m
-CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
CONFIG_CHR_DEV_ST=m
CONFIG_BLK_DEV_SR=y
@@ -567,6 +567,7 @@ CONFIG_ROOT_NFS=y
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
CONFIG_CIFS=m
+# CONFIG_CIFS_STATS2 is not set
# CONFIG_CIFS_DEBUG is not set
CONFIG_CODA_FS=m
CONFIG_NLS_CODEPAGE_437=y
@@ -681,6 +682,7 @@ CONFIG_PRIME_NUMBERS=m
CONFIG_CRC32_SELFTEST=m
CONFIG_CRC64=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_GLOB_SELFTEST=m
CONFIG_STRING_SELFTEST=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
@@ -689,7 +691,6 @@ CONFIG_WW_MUTEX_SELFTEST=m
CONFIG_EARLY_PRINTK=y
CONFIG_KUNIT=m
CONFIG_KUNIT_ALL_TESTS=m
-CONFIG_TEST_LIST_SORT=m
CONFIG_TEST_MIN_HEAP=m
CONFIG_TEST_SORT=m
CONFIG_TEST_DIV64=m
@@ -701,6 +702,7 @@ CONFIG_TEST_STRING_HELPERS=m
CONFIG_TEST_STRSCPY=m
CONFIG_TEST_KSTRTOX=m
CONFIG_TEST_PRINTF=m
+CONFIG_TEST_SCANF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
CONFIG_TEST_XARRAY=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 793085f00c99..563ba47db8c6 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -76,6 +76,7 @@ CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_ZONES=y
# CONFIG_NF_CONNTRACK_PROCFS is not set
@@ -450,6 +451,7 @@ CONFIG_ROOT_NFS=y
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
CONFIG_CIFS=m
+# CONFIG_CIFS_STATS2 is not set
# CONFIG_CIFS_DEBUG is not set
CONFIG_CODA_FS=m
CONFIG_NLS_CODEPAGE_437=y
@@ -572,7 +574,6 @@ CONFIG_WW_MUTEX_SELFTEST=m
CONFIG_EARLY_PRINTK=y
CONFIG_KUNIT=m
CONFIG_KUNIT_ALL_TESTS=m
-CONFIG_TEST_LIST_SORT=m
CONFIG_TEST_MIN_HEAP=m
CONFIG_TEST_SORT=m
CONFIG_TEST_DIV64=m
@@ -584,6 +585,7 @@ CONFIG_TEST_STRING_HELPERS=m
CONFIG_TEST_STRSCPY=m
CONFIG_TEST_KSTRTOX=m
CONFIG_TEST_PRINTF=m
+CONFIG_TEST_SCANF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
CONFIG_TEST_XARRAY=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 56fbac7943b2..9f1b44de4706 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -77,6 +77,7 @@ CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_ZONES=y
# CONFIG_NF_CONNTRACK_PROCFS is not set
@@ -451,6 +452,7 @@ CONFIG_ROOT_NFS=y
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
CONFIG_CIFS=m
+# CONFIG_CIFS_STATS2 is not set
# CONFIG_CIFS_DEBUG is not set
CONFIG_CODA_FS=m
CONFIG_NLS_CODEPAGE_437=y
@@ -573,7 +575,6 @@ CONFIG_WW_MUTEX_SELFTEST=m
CONFIG_EARLY_PRINTK=y
CONFIG_KUNIT=m
CONFIG_KUNIT_ALL_TESTS=m
-CONFIG_TEST_LIST_SORT=m
CONFIG_TEST_MIN_HEAP=m
CONFIG_TEST_SORT=m
CONFIG_TEST_DIV64=m
@@ -585,6 +586,7 @@ CONFIG_TEST_STRING_HELPERS=m
CONFIG_TEST_STRSCPY=m
CONFIG_TEST_KSTRTOX=m
CONFIG_TEST_PRINTF=m
+CONFIG_TEST_SCANF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
CONFIG_TEST_XARRAY=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 0e15431b65e2..1993433d0840 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -78,6 +78,7 @@ CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_ZONES=y
# CONFIG_NF_CONNTRACK_PROCFS is not set
@@ -314,7 +315,6 @@ CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_DUMMY_IRQ=m
CONFIG_RAID_ATTRS=m
-CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
CONFIG_CHR_DEV_ST=m
CONFIG_BLK_DEV_SR=y
@@ -469,6 +469,7 @@ CONFIG_ROOT_NFS=y
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
CONFIG_CIFS=m
+# CONFIG_CIFS_STATS2 is not set
# CONFIG_CIFS_DEBUG is not set
CONFIG_CODA_FS=m
CONFIG_NLS_CODEPAGE_437=y
@@ -583,6 +584,7 @@ CONFIG_PRIME_NUMBERS=m
CONFIG_CRC32_SELFTEST=m
CONFIG_CRC64=m
CONFIG_XZ_DEC_TEST=m
+CONFIG_GLOB_SELFTEST=m
CONFIG_STRING_SELFTEST=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
@@ -591,7 +593,6 @@ CONFIG_WW_MUTEX_SELFTEST=m
CONFIG_EARLY_PRINTK=y
CONFIG_KUNIT=m
CONFIG_KUNIT_ALL_TESTS=m
-CONFIG_TEST_LIST_SORT=m
CONFIG_TEST_MIN_HEAP=m
CONFIG_TEST_SORT=m
CONFIG_TEST_DIV64=m
@@ -603,6 +604,7 @@ CONFIG_TEST_STRING_HELPERS=m
CONFIG_TEST_STRSCPY=m
CONFIG_TEST_KSTRTOX=m
CONFIG_TEST_PRINTF=m
+CONFIG_TEST_SCANF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
CONFIG_TEST_XARRAY=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 3490a05f29b8..56dbc63cef5b 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -74,6 +74,7 @@ CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_ZONES=y
# CONFIG_NF_CONNTRACK_PROCFS is not set
@@ -453,6 +454,7 @@ CONFIG_ROOT_NFS=y
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
CONFIG_CIFS=m
+# CONFIG_CIFS_STATS2 is not set
# CONFIG_CIFS_DEBUG is not set
CONFIG_CODA_FS=m
CONFIG_NLS_CODEPAGE_437=y
@@ -574,7 +576,6 @@ CONFIG_TEST_LOCKUP=m
CONFIG_WW_MUTEX_SELFTEST=m
CONFIG_KUNIT=m
CONFIG_KUNIT_ALL_TESTS=m
-CONFIG_TEST_LIST_SORT=m
CONFIG_TEST_MIN_HEAP=m
CONFIG_TEST_SORT=m
CONFIG_TEST_DIV64=m
@@ -586,6 +587,7 @@ CONFIG_TEST_STRING_HELPERS=m
CONFIG_TEST_STRSCPY=m
CONFIG_TEST_KSTRTOX=m
CONFIG_TEST_PRINTF=m
+CONFIG_TEST_SCANF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
CONFIG_TEST_XARRAY=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 4e92c8c332fc..6bd1bba81ac3 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -74,6 +74,7 @@ CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_ZONES=y
# CONFIG_NF_CONNTRACK_PROCFS is not set
@@ -452,6 +453,7 @@ CONFIG_ROOT_NFS=y
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
CONFIG_CIFS=m
+# CONFIG_CIFS_STATS2 is not set
# CONFIG_CIFS_DEBUG is not set
CONFIG_CODA_FS=m
CONFIG_NLS_CODEPAGE_437=y
@@ -574,7 +576,6 @@ CONFIG_WW_MUTEX_SELFTEST=m
CONFIG_EARLY_PRINTK=y
CONFIG_KUNIT=m
CONFIG_KUNIT_ALL_TESTS=m
-CONFIG_TEST_LIST_SORT=m
CONFIG_TEST_MIN_HEAP=m
CONFIG_TEST_SORT=m
CONFIG_TEST_DIV64=m
@@ -586,6 +587,7 @@ CONFIG_TEST_STRING_HELPERS=m
CONFIG_TEST_STRSCPY=m
CONFIG_TEST_KSTRTOX=m
CONFIG_TEST_PRINTF=m
+CONFIG_TEST_SCANF=m
CONFIG_TEST_BITMAP=m
CONFIG_TEST_UUID=m
CONFIG_TEST_XARRAY=m
diff --git a/arch/m68k/emu/nfeth.c b/arch/m68k/emu/nfeth.c
index d2875e32abfc..79e55421cfb1 100644
--- a/arch/m68k/emu/nfeth.c
+++ b/arch/m68k/emu/nfeth.c
@@ -254,8 +254,8 @@ static void __exit nfeth_cleanup(void)
for (i = 0; i < MAX_UNIT; i++) {
if (nfeth_dev[i]) {
- unregister_netdev(nfeth_dev[0]);
- free_netdev(nfeth_dev[0]);
+ unregister_netdev(nfeth_dev[i]);
+ free_netdev(nfeth_dev[i]);
}
}
free_irq(nfEtherIRQ, nfeth_interrupt);
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index 8637bf8a2f65..cfba83d230fd 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -48,7 +48,7 @@ static inline int arch_atomic_##op##_return(int i, atomic_t *v) \
" casl %2,%1,%0\n" \
" jne 1b" \
: "+m" (*v), "=&d" (t), "=&d" (tmp) \
- : "g" (i), "2" (arch_atomic_read(v))); \
+ : "di" (i), "2" (arch_atomic_read(v))); \
return t; \
}
@@ -63,7 +63,7 @@ static inline int arch_atomic_fetch_##op(int i, atomic_t *v) \
" casl %2,%1,%0\n" \
" jne 1b" \
: "+m" (*v), "=&d" (t), "=&d" (tmp) \
- : "g" (i), "2" (arch_atomic_read(v))); \
+ : "di" (i), "2" (arch_atomic_read(v))); \
return tmp; \
}
diff --git a/arch/mips/ath25/ar2315.c b/arch/mips/ath25/ar2315.c
index 9dbed7b5ea76..76e43a73ba1b 100644
--- a/arch/mips/ath25/ar2315.c
+++ b/arch/mips/ath25/ar2315.c
@@ -69,24 +69,24 @@ static void ar2315_misc_irq_handler(struct irq_desc *desc)
{
u32 pending = ar2315_rst_reg_read(AR2315_ISR) &
ar2315_rst_reg_read(AR2315_IMR);
- unsigned nr, misc_irq = 0;
+ unsigned nr;
+ int ret = 0;
if (pending) {
struct irq_domain *domain = irq_desc_get_handler_data(desc);
nr = __ffs(pending);
- misc_irq = irq_find_mapping(domain, nr);
- }
- if (misc_irq) {
if (nr == AR2315_MISC_IRQ_GPIO)
ar2315_rst_reg_write(AR2315_ISR, AR2315_ISR_GPIO);
else if (nr == AR2315_MISC_IRQ_WATCHDOG)
ar2315_rst_reg_write(AR2315_ISR, AR2315_ISR_WD);
- generic_handle_irq(misc_irq);
- } else {
- spurious_interrupt();
+
+ ret = generic_handle_domain_irq(domain, nr);
}
+
+ if (!pending || ret)
+ spurious_interrupt();
}
static void ar2315_misc_irq_unmask(struct irq_data *d)
diff --git a/arch/mips/ath25/ar5312.c b/arch/mips/ath25/ar5312.c
index 23c879f4b734..822b639dbd1e 100644
--- a/arch/mips/ath25/ar5312.c
+++ b/arch/mips/ath25/ar5312.c
@@ -73,22 +73,21 @@ static void ar5312_misc_irq_handler(struct irq_desc *desc)
{
u32 pending = ar5312_rst_reg_read(AR5312_ISR) &
ar5312_rst_reg_read(AR5312_IMR);
- unsigned nr, misc_irq = 0;
+ unsigned nr;
+ int ret = 0;
if (pending) {
struct irq_domain *domain = irq_desc_get_handler_data(desc);
nr = __ffs(pending);
- misc_irq = irq_find_mapping(domain, nr);
- }
- if (misc_irq) {
- generic_handle_irq(misc_irq);
+ ret = generic_handle_domain_irq(domain, nr);
if (nr == AR5312_MISC_IRQ_TIMER)
ar5312_rst_reg_read(AR5312_TIMER);
- } else {
- spurious_interrupt();
}
+
+ if (!pending || ret)
+ spurious_interrupt();
}
/* Enable the specified AR5312_MISC_IRQ interrupt */
diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c
index acfbdc01b0ac..b732495f138a 100644
--- a/arch/mips/lantiq/irq.c
+++ b/arch/mips/lantiq/irq.c
@@ -300,7 +300,7 @@ static void ltq_hw_irq_handler(struct irq_desc *desc)
*/
irq = __fls(irq);
hwirq = irq + MIPS_CPU_IRQ_CASCADE + (INT_NUM_IM_OFFSET * module);
- generic_handle_irq(irq_linear_revmap(ltq_domain, hwirq));
+ generic_handle_domain_irq(ltq_domain, hwirq);
/* if this is a EBU irq, we need to ack it or get a deadlock */
if (irq == LTQ_ICU_EBU_IRQ && !module && LTQ_EBU_PCC_ISTAT != 0)
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index c1a655aee599..9a4bfb4e63e3 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -337,14 +337,12 @@ static void ar2315_pci_irq_handler(struct irq_desc *desc)
struct ar2315_pci_ctrl *apc = irq_desc_get_handler_data(desc);
u32 pending = ar2315_pci_reg_read(apc, AR2315_PCI_ISR) &
ar2315_pci_reg_read(apc, AR2315_PCI_IMR);
- unsigned pci_irq = 0;
+ int ret = 0;
if (pending)
- pci_irq = irq_find_mapping(apc->domain, __ffs(pending));
+ ret = generic_handle_domain_irq(apc->domain, __ffs(pending));
- if (pci_irq)
- generic_handle_irq(pci_irq);
- else
+ if (!pending || ret)
spurious_interrupt();
}
diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c
index c48e23cf5b5e..d3c947fa2969 100644
--- a/arch/mips/pci/pci-rt3883.c
+++ b/arch/mips/pci/pci-rt3883.c
@@ -140,10 +140,9 @@ static void rt3883_pci_irq_handler(struct irq_desc *desc)
}
while (pending) {
- unsigned irq, bit = __ffs(pending);
+ unsigned bit = __ffs(pending);
- irq = irq_find_mapping(rpc->irq_domain, bit);
- generic_handle_irq(irq);
+ generic_handle_domain_irq(rpc->irq_domain, bit);
pending &= ~BIT(bit);
}
diff --git a/arch/mips/ralink/irq.c b/arch/mips/ralink/irq.c
index 220ca0cd7945..fa353bc13947 100644
--- a/arch/mips/ralink/irq.c
+++ b/arch/mips/ralink/irq.c
@@ -100,7 +100,7 @@ static void ralink_intc_irq_handler(struct irq_desc *desc)
if (pending) {
struct irq_domain *domain = irq_desc_get_handler_data(desc);
- generic_handle_irq(irq_find_mapping(domain, __ffs(pending)));
+ generic_handle_domain_irq(domain, __ffs(pending));
} else {
spurious_interrupt();
}
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index 95c1bff1ab9f..a0dd3bd2b81b 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -190,7 +190,7 @@ static void ip27_do_irq_mask0(struct irq_desc *desc)
unsigned long *mask = per_cpu(irq_enable_mask, cpu);
struct irq_domain *domain;
u64 pend0;
- int irq;
+ int ret;
/* copied from Irix intpend0() */
pend0 = LOCAL_HUB_L(PI_INT_PEND0);
@@ -216,10 +216,8 @@ static void ip27_do_irq_mask0(struct irq_desc *desc)
#endif
{
domain = irq_desc_get_handler_data(desc);
- irq = irq_linear_revmap(domain, __ffs(pend0));
- if (irq)
- generic_handle_irq(irq);
- else
+ ret = generic_handle_domain_irq(domain, __ffs(pend0));
+ if (ret)
spurious_interrupt();
}
@@ -232,7 +230,7 @@ static void ip27_do_irq_mask1(struct irq_desc *desc)
unsigned long *mask = per_cpu(irq_enable_mask, cpu);
struct irq_domain *domain;
u64 pend1;
- int irq;
+ int ret;
/* copied from Irix intpend0() */
pend1 = LOCAL_HUB_L(PI_INT_PEND1);
@@ -242,10 +240,8 @@ static void ip27_do_irq_mask1(struct irq_desc *desc)
return;
domain = irq_desc_get_handler_data(desc);
- irq = irq_linear_revmap(domain, __ffs(pend1) + 64);
- if (irq)
- generic_handle_irq(irq);
- else
+ ret = generic_handle_domain_irq(domain, __ffs(pend1) + 64);
+ if (ret)
spurious_interrupt();
LOCAL_HUB_L(PI_INT_PEND1);
diff --git a/arch/mips/sgi-ip30/ip30-irq.c b/arch/mips/sgi-ip30/ip30-irq.c
index ba87704073c8..423c32cb66ed 100644
--- a/arch/mips/sgi-ip30/ip30-irq.c
+++ b/arch/mips/sgi-ip30/ip30-irq.c
@@ -99,7 +99,7 @@ static void ip30_normal_irq(struct irq_desc *desc)
int cpu = smp_processor_id();
struct irq_domain *domain;
u64 pend, mask;
- int irq;
+ int ret;
pend = heart_read(&heart_regs->isr);
mask = (heart_read(&heart_regs->imr[cpu]) &
@@ -130,10 +130,8 @@ static void ip30_normal_irq(struct irq_desc *desc)
#endif
{
domain = irq_desc_get_handler_data(desc);
- irq = irq_linear_revmap(domain, __ffs(pend));
- if (irq)
- generic_handle_irq(irq);
- else
+ ret = generic_handle_domain_irq(domain, __ffs(pend));
+ if (ret)
spurious_interrupt();
}
}
diff --git a/arch/nios2/kernel/irq.c b/arch/nios2/kernel/irq.c
index c6a1a9f6ac42..6b7890e5f7af 100644
--- a/arch/nios2/kernel/irq.c
+++ b/arch/nios2/kernel/irq.c
@@ -19,11 +19,9 @@ static u32 ienable;
asmlinkage void do_IRQ(int hwirq, struct pt_regs *regs)
{
struct pt_regs *oldregs = set_irq_regs(regs);
- int irq;
irq_enter();
- irq = irq_find_mapping(NULL, hwirq);
- generic_handle_irq(irq);
+ generic_handle_domain_irq(NULL, hwirq);
irq_exit();
set_irq_regs(oldregs);
diff --git a/arch/parisc/include/asm/string.h b/arch/parisc/include/asm/string.h
index 4a0c9dbd62fd..f6e1132f4e35 100644
--- a/arch/parisc/include/asm/string.h
+++ b/arch/parisc/include/asm/string.h
@@ -8,19 +8,4 @@ extern void * memset(void *, int, size_t);
#define __HAVE_ARCH_MEMCPY
void * memcpy(void * dest,const void *src,size_t count);
-#define __HAVE_ARCH_STRLEN
-extern size_t strlen(const char *s);
-
-#define __HAVE_ARCH_STRCPY
-extern char *strcpy(char *dest, const char *src);
-
-#define __HAVE_ARCH_STRNCPY
-extern char *strncpy(char *dest, const char *src, size_t count);
-
-#define __HAVE_ARCH_STRCAT
-extern char *strcat(char *dest, const char *src);
-
-#define __HAVE_ARCH_MEMSET
-extern void *memset(void *, int, size_t);
-
#endif
diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c
index 8ed409ecec93..e8a6a751dfd8 100644
--- a/arch/parisc/kernel/parisc_ksyms.c
+++ b/arch/parisc/kernel/parisc_ksyms.c
@@ -17,10 +17,6 @@
#include <linux/string.h>
EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(strlen);
-EXPORT_SYMBOL(strcpy);
-EXPORT_SYMBOL(strncpy);
-EXPORT_SYMBOL(strcat);
#include <linux/atomic.h>
EXPORT_SYMBOL(__xchg8);
diff --git a/arch/parisc/lib/Makefile b/arch/parisc/lib/Makefile
index 2d7a9974dbae..7b197667faf6 100644
--- a/arch/parisc/lib/Makefile
+++ b/arch/parisc/lib/Makefile
@@ -3,7 +3,7 @@
# Makefile for parisc-specific library files
#
-lib-y := lusercopy.o bitops.o checksum.o io.o memcpy.o \
- ucmpdi2.o delay.o string.o
+lib-y := lusercopy.o bitops.o checksum.o io.o memset.o memcpy.o \
+ ucmpdi2.o delay.o
obj-y := iomap.o
diff --git a/arch/parisc/lib/memset.c b/arch/parisc/lib/memset.c
new file mode 100644
index 000000000000..133e4809859a
--- /dev/null
+++ b/arch/parisc/lib/memset.c
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#include <linux/types.h>
+#include <asm/string.h>
+
+#define OPSIZ (BITS_PER_LONG/8)
+typedef unsigned long op_t;
+
+void *
+memset (void *dstpp, int sc, size_t len)
+{
+ unsigned int c = sc;
+ long int dstp = (long int) dstpp;
+
+ if (len >= 8)
+ {
+ size_t xlen;
+ op_t cccc;
+
+ cccc = (unsigned char) c;
+ cccc |= cccc << 8;
+ cccc |= cccc << 16;
+ if (OPSIZ > 4)
+ /* Do the shift in two steps to avoid warning if long has 32 bits. */
+ cccc |= (cccc << 16) << 16;
+
+ /* There are at least some bytes to set.
+ No need to test for LEN == 0 in this alignment loop. */
+ while (dstp % OPSIZ != 0)
+ {
+ ((unsigned char *) dstp)[0] = c;
+ dstp += 1;
+ len -= 1;
+ }
+
+ /* Write 8 `op_t' per iteration until less than 8 `op_t' remain. */
+ xlen = len / (OPSIZ * 8);
+ while (xlen > 0)
+ {
+ ((op_t *) dstp)[0] = cccc;
+ ((op_t *) dstp)[1] = cccc;
+ ((op_t *) dstp)[2] = cccc;
+ ((op_t *) dstp)[3] = cccc;
+ ((op_t *) dstp)[4] = cccc;
+ ((op_t *) dstp)[5] = cccc;
+ ((op_t *) dstp)[6] = cccc;
+ ((op_t *) dstp)[7] = cccc;
+ dstp += 8 * OPSIZ;
+ xlen -= 1;
+ }
+ len %= OPSIZ * 8;
+
+ /* Write 1 `op_t' per iteration until less than OPSIZ bytes remain. */
+ xlen = len / OPSIZ;
+ while (xlen > 0)
+ {
+ ((op_t *) dstp)[0] = cccc;
+ dstp += OPSIZ;
+ xlen -= 1;
+ }
+ len %= OPSIZ;
+ }
+
+ /* Write the last few bytes. */
+ while (len > 0)
+ {
+ ((unsigned char *) dstp)[0] = c;
+ dstp += 1;
+ len -= 1;
+ }
+
+ return dstpp;
+}
diff --git a/arch/parisc/lib/string.S b/arch/parisc/lib/string.S
deleted file mode 100644
index 4a64264427a6..000000000000
--- a/arch/parisc/lib/string.S
+++ /dev/null
@@ -1,136 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * PA-RISC assembly string functions
- *
- * Copyright (C) 2019 Helge Deller <deller@gmx.de>
- */
-
-#include <asm/assembly.h>
-#include <linux/linkage.h>
-
- .section .text.hot
- .level PA_ASM_LEVEL
-
- t0 = r20
- t1 = r21
- t2 = r22
-
-ENTRY_CFI(strlen, frame=0,no_calls)
- or,COND(<>) arg0,r0,ret0
- b,l,n .Lstrlen_null_ptr,r0
- depwi 0,31,2,ret0
- cmpb,COND(<>) arg0,ret0,.Lstrlen_not_aligned
- ldw,ma 4(ret0),t0
- cmpib,tr 0,r0,.Lstrlen_loop
- uxor,nbz r0,t0,r0
-.Lstrlen_not_aligned:
- uaddcm arg0,ret0,t1
- shladd t1,3,r0,t1
- mtsar t1
- depwi -1,%sar,32,t0
- uxor,nbz r0,t0,r0
-.Lstrlen_loop:
- b,l,n .Lstrlen_end_loop,r0
- ldw,ma 4(ret0),t0
- cmpib,tr 0,r0,.Lstrlen_loop
- uxor,nbz r0,t0,r0
-.Lstrlen_end_loop:
- extrw,u,<> t0,7,8,r0
- addib,tr,n -3,ret0,.Lstrlen_out
- extrw,u,<> t0,15,8,r0
- addib,tr,n -2,ret0,.Lstrlen_out
- extrw,u,<> t0,23,8,r0
- addi -1,ret0,ret0
-.Lstrlen_out:
- bv r0(rp)
- uaddcm ret0,arg0,ret0
-.Lstrlen_null_ptr:
- bv,n r0(rp)
-ENDPROC_CFI(strlen)
-
-
-ENTRY_CFI(strcpy, frame=0,no_calls)
- ldb 0(arg1),t0
- stb t0,0(arg0)
- ldo 0(arg0),ret0
- ldo 1(arg1),t1
- cmpb,= r0,t0,2f
- ldo 1(arg0),t2
-1: ldb 0(t1),arg1
- stb arg1,0(t2)
- ldo 1(t1),t1
- cmpb,<> r0,arg1,1b
- ldo 1(t2),t2
-2: bv,n r0(rp)
-ENDPROC_CFI(strcpy)
-
-
-ENTRY_CFI(strncpy, frame=0,no_calls)
- ldb 0(arg1),t0
- stb t0,0(arg0)
- ldo 1(arg1),t1
- ldo 0(arg0),ret0
- cmpb,= r0,t0,2f
- ldo 1(arg0),arg1
-1: ldo -1(arg2),arg2
- cmpb,COND(=),n r0,arg2,2f
- ldb 0(t1),arg0
- stb arg0,0(arg1)
- ldo 1(t1),t1
- cmpb,<> r0,arg0,1b
- ldo 1(arg1),arg1
-2: bv,n r0(rp)
-ENDPROC_CFI(strncpy)
-
-
-ENTRY_CFI(strcat, frame=0,no_calls)
- ldb 0(arg0),t0
- cmpb,= t0,r0,2f
- ldo 0(arg0),ret0
- ldo 1(arg0),arg0
-1: ldb 0(arg0),t1
- cmpb,<>,n r0,t1,1b
- ldo 1(arg0),arg0
-2: ldb 0(arg1),t2
- stb t2,0(arg0)
- ldo 1(arg0),arg0
- ldb 0(arg1),t0
- cmpb,<> r0,t0,2b
- ldo 1(arg1),arg1
- bv,n r0(rp)
-ENDPROC_CFI(strcat)
-
-
-ENTRY_CFI(memset, frame=0,no_calls)
- copy arg0,ret0
- cmpb,COND(=) r0,arg0,4f
- copy arg0,t2
- cmpb,COND(=) r0,arg2,4f
- ldo -1(arg2),arg3
- subi -1,arg3,t0
- subi 0,t0,t1
- cmpiclr,COND(>=) 0,t1,arg2
- ldo -1(t1),arg2
- extru arg2,31,2,arg0
-2: stb arg1,0(t2)
- ldo 1(t2),t2
- addib,>= -1,arg0,2b
- ldo -1(arg3),arg3
- cmpiclr,COND(<=) 4,arg2,r0
- b,l,n 4f,r0
-#ifdef CONFIG_64BIT
- depd,* r0,63,2,arg2
-#else
- depw r0,31,2,arg2
-#endif
- ldo 1(t2),t2
-3: stb arg1,-1(t2)
- stb arg1,0(t2)
- stb arg1,1(t2)
- stb arg1,2(t2)
- addib,COND(>) -4,arg2,3b
- ldo 4(t2),t2
-4: bv,n r0(rp)
-ENDPROC_CFI(memset)
-
- .end
diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h
index 64201125a287..d4b145b279f6 100644
--- a/arch/powerpc/include/asm/book3s/32/kup.h
+++ b/arch/powerpc/include/asm/book3s/32/kup.h
@@ -4,6 +4,8 @@
#include <asm/bug.h>
#include <asm/book3s/32/mmu-hash.h>
+#include <asm/mmu.h>
+#include <asm/synch.h>
#ifndef __ASSEMBLY__
@@ -28,6 +30,15 @@ static inline void kuep_lock(void)
return;
update_user_segments(mfsr(0) | SR_NX);
+ /*
+ * This isync() shouldn't be necessary as the kernel is not excepted to
+ * run any instruction in userspace soon after the update of segments,
+ * but hash based cores (at least G3) seem to exhibit a random
+ * behaviour when the 'isync' is not there. 603 cores don't have this
+ * behaviour so don't do the 'isync' as it saves several CPU cycles.
+ */
+ if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
+ isync(); /* Context sync required after mtsr() */
}
static inline void kuep_unlock(void)
@@ -36,6 +47,15 @@ static inline void kuep_unlock(void)
return;
update_user_segments(mfsr(0) & ~SR_NX);
+ /*
+ * This isync() shouldn't be necessary as a 'rfi' will soon be executed
+ * to return to userspace, but hash based cores (at least G3) seem to
+ * exhibit a random behaviour when the 'isync' is not there. 603 cores
+ * don't have this behaviour so don't do the 'isync' as it saves several
+ * CPU cycles.
+ */
+ if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
+ isync(); /* Context sync required after mtsr() */
}
#ifdef CONFIG_PPC_KUAP
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index d4bdf7d274ac..6b800d3e2681 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -583,6 +583,9 @@ DECLARE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode);
DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException);
+/* irq.c */
+DECLARE_INTERRUPT_HANDLER_ASYNC(do_IRQ);
+
void __noreturn unrecoverable_exception(struct pt_regs *regs);
void replay_system_reset(void);
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 4982f3711fc3..2b3278534bc1 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -52,7 +52,7 @@ extern void *mcheckirq_ctx[NR_CPUS];
extern void *hardirq_ctx[NR_CPUS];
extern void *softirq_ctx[NR_CPUS];
-extern void do_IRQ(struct pt_regs *regs);
+void __do_IRQ(struct pt_regs *regs);
extern void __init init_IRQ(void);
extern void __do_irq(struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 3e5d470a6155..14422e851494 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -70,6 +70,22 @@ struct pt_regs
unsigned long __pad[4]; /* Maintain 16 byte interrupt stack alignment */
};
#endif
+#if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE)
+ struct { /* Must be a multiple of 16 bytes */
+ unsigned long mas0;
+ unsigned long mas1;
+ unsigned long mas2;
+ unsigned long mas3;
+ unsigned long mas6;
+ unsigned long mas7;
+ unsigned long srr0;
+ unsigned long srr1;
+ unsigned long csrr0;
+ unsigned long csrr1;
+ unsigned long dsrr0;
+ unsigned long dsrr1;
+ };
+#endif
};
#endif
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index a47eefa09bcb..5bee245d832b 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -309,24 +309,21 @@ int main(void)
STACK_PT_REGS_OFFSET(STACK_REGS_IAMR, iamr);
#endif
-#if defined(CONFIG_PPC32)
-#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
- DEFINE(EXC_LVL_SIZE, STACK_EXC_LVL_FRAME_SIZE);
- DEFINE(MAS0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0));
+#if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE)
+ STACK_PT_REGS_OFFSET(MAS0, mas0);
/* we overload MMUCR for 44x on MAS0 since they are mutually exclusive */
- DEFINE(MMUCR, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0));
- DEFINE(MAS1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas1));
- DEFINE(MAS2, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas2));
- DEFINE(MAS3, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas3));
- DEFINE(MAS6, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas6));
- DEFINE(MAS7, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas7));
- DEFINE(_SRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, srr0));
- DEFINE(_SRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, srr1));
- DEFINE(_CSRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, csrr0));
- DEFINE(_CSRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, csrr1));
- DEFINE(_DSRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, dsrr0));
- DEFINE(_DSRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, dsrr1));
-#endif
+ STACK_PT_REGS_OFFSET(MMUCR, mas0);
+ STACK_PT_REGS_OFFSET(MAS1, mas1);
+ STACK_PT_REGS_OFFSET(MAS2, mas2);
+ STACK_PT_REGS_OFFSET(MAS3, mas3);
+ STACK_PT_REGS_OFFSET(MAS6, mas6);
+ STACK_PT_REGS_OFFSET(MAS7, mas7);
+ STACK_PT_REGS_OFFSET(_SRR0, srr0);
+ STACK_PT_REGS_OFFSET(_SRR1, srr1);
+ STACK_PT_REGS_OFFSET(_CSRR0, csrr0);
+ STACK_PT_REGS_OFFSET(_CSRR1, csrr1);
+ STACK_PT_REGS_OFFSET(_DSRR0, dsrr0);
+ STACK_PT_REGS_OFFSET(_DSRR1, dsrr1);
#endif
/* About the CPU features table */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 4aec59a77d4c..37859e62a8dc 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -812,7 +812,6 @@ __start_interrupts:
* syscall register convention is in Documentation/powerpc/syscall64-abi.rst
*/
EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000)
-1:
/* SCV 0 */
mr r9,r13
GET_PACA(r13)
@@ -842,10 +841,12 @@ EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000)
b system_call_vectored_sigill
#endif
.endr
-2:
EXC_VIRT_END(system_call_vectored, 0x3000, 0x1000)
-SOFT_MASK_TABLE(1b, 2b) // Treat scv vectors as soft-masked, see comment above.
+// Treat scv vectors as soft-masked, see comment above.
+// Use absolute values rather than labels here, so they don't get relocated,
+// because this code runs unrelocated.
+SOFT_MASK_TABLE(0xc000000000003000, 0xc000000000004000)
#ifdef CONFIG_RELOCATABLE
TRAMP_VIRT_BEGIN(system_call_vectored_tramp)
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 764edd860ed4..68e5c0a7e99d 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -300,7 +300,7 @@ ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE)
EXCEPTION_PROLOG_1
EXCEPTION_PROLOG_2 INTERRUPT_DATA_STORAGE DataAccess handle_dar_dsisr=1
prepare_transfer_to_handler
- lwz r5, _DSISR(r11)
+ lwz r5, _DSISR(r1)
andis. r0, r5, DSISR_DABRMATCH@h
bne- 1f
bl do_page_fault
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 87b806e8eded..e5503420b6c6 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -168,20 +168,18 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
/* only on e500mc */
#define DBG_STACK_BASE dbgirq_ctx
-#define EXC_LVL_FRAME_OVERHEAD (THREAD_SIZE - INT_FRAME_SIZE - EXC_LVL_SIZE)
-
#ifdef CONFIG_SMP
#define BOOKE_LOAD_EXC_LEVEL_STACK(level) \
mfspr r8,SPRN_PIR; \
slwi r8,r8,2; \
addis r8,r8,level##_STACK_BASE@ha; \
lwz r8,level##_STACK_BASE@l(r8); \
- addi r8,r8,EXC_LVL_FRAME_OVERHEAD;
+ addi r8,r8,THREAD_SIZE - INT_FRAME_SIZE;
#else
#define BOOKE_LOAD_EXC_LEVEL_STACK(level) \
lis r8,level##_STACK_BASE@ha; \
lwz r8,level##_STACK_BASE@l(r8); \
- addi r8,r8,EXC_LVL_FRAME_OVERHEAD;
+ addi r8,r8,THREAD_SIZE - INT_FRAME_SIZE;
#endif
/*
@@ -208,7 +206,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
mtmsr r11; \
mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\
lwz r11, TASK_STACK - THREAD(r11); /* this thread's kernel stack */\
- addi r11,r11,EXC_LVL_FRAME_OVERHEAD; /* allocate stack frame */\
+ addi r11,r11,THREAD_SIZE - INT_FRAME_SIZE; /* allocate stack frame */\
beq 1f; \
/* COMING FROM USER MODE */ \
stw r9,_CCR(r11); /* save CR */\
@@ -516,24 +514,5 @@ label:
bl kernel_fp_unavailable_exception; \
b interrupt_return
-#else /* __ASSEMBLY__ */
-struct exception_regs {
- unsigned long mas0;
- unsigned long mas1;
- unsigned long mas2;
- unsigned long mas3;
- unsigned long mas6;
- unsigned long mas7;
- unsigned long srr0;
- unsigned long srr1;
- unsigned long csrr0;
- unsigned long csrr1;
- unsigned long dsrr0;
- unsigned long dsrr1;
-};
-
-/* ensure this structure is always sized to a multiple of the stack alignment */
-#define STACK_EXC_LVL_FRAME_SIZE ALIGN(sizeof (struct exception_regs), 16)
-
#endif /* __ASSEMBLY__ */
#endif /* __HEAD_BOOKE_H__ */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 91e63eac4e8f..551b653228c4 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -750,7 +750,7 @@ void __do_irq(struct pt_regs *regs)
trace_irq_exit(regs);
}
-DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
+void __do_IRQ(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
void *cursp, *irqsp, *sirqsp;
@@ -774,6 +774,11 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
set_irq_regs(old_regs);
}
+DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
+{
+ __do_IRQ(regs);
+}
+
static void *__init alloc_vm_stack(void)
{
return __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, THREADINFO_GFP,
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index cbc28d1a2e1b..7a7cd6bda53e 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -292,7 +292,8 @@ int kprobe_handler(struct pt_regs *regs)
if (user_mode(regs))
return 0;
- if (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR))
+ if (!IS_ENABLED(CONFIG_BOOKE) &&
+ (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR)))
return 0;
/*
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 5ff0e55d0db1..defecb3b1b15 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -1167,7 +1167,7 @@ static int __init topology_init(void)
* CPU. For instance, the boot cpu might never be valid
* for hotplugging.
*/
- if (smp_ops->cpu_offline_self)
+ if (smp_ops && smp_ops->cpu_offline_self)
c->hotpluggable = 1;
#endif
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index e45ce427bffb..c487ba5a6e11 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -586,7 +586,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
if (atomic_read(&ppc_n_lost_interrupts) != 0)
- do_IRQ(regs);
+ __do_IRQ(regs);
#endif
old_regs = set_irq_regs(regs);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index dfbce527c98e..d56254f05e17 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1104,7 +1104,7 @@ DEFINE_INTERRUPT_HANDLER(RunModeException)
_exception(SIGTRAP, regs, TRAP_UNK, 0);
}
-DEFINE_INTERRUPT_HANDLER(single_step_exception)
+static void __single_step_exception(struct pt_regs *regs)
{
clear_single_step(regs);
clear_br_trace(regs);
@@ -1121,6 +1121,11 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception)
_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
}
+DEFINE_INTERRUPT_HANDLER(single_step_exception)
+{
+ __single_step_exception(regs);
+}
+
/*
* After we have successfully emulated an instruction, we have to
* check if the instruction was being single-stepped, and if so,
@@ -1130,7 +1135,7 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception)
static void emulate_single_step(struct pt_regs *regs)
{
if (single_stepping(regs))
- single_step_exception(regs);
+ __single_step_exception(regs);
}
static inline int __parse_fpscr(unsigned long fpscr)
diff --git a/arch/powerpc/mm/pageattr.c b/arch/powerpc/mm/pageattr.c
index 0876216ceee6..edea388e9d3f 100644
--- a/arch/powerpc/mm/pageattr.c
+++ b/arch/powerpc/mm/pageattr.c
@@ -18,16 +18,12 @@
/*
* Updates the attributes of a page in three steps:
*
- * 1. invalidate the page table entry
- * 2. flush the TLB
- * 3. install the new entry with the updated attributes
- *
- * Invalidating the pte means there are situations where this will not work
- * when in theory it should.
- * For example:
- * - removing write from page whilst it is being executed
- * - setting a page read-only whilst it is being read by another CPU
+ * 1. take the page_table_lock
+ * 2. install the new entry with the updated attributes
+ * 3. flush the TLB
*
+ * This sequence is safe against concurrent updates, and also allows updating the
+ * attributes of a page currently being executed or accessed.
*/
static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
{
@@ -36,9 +32,7 @@ static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
spin_lock(&init_mm.page_table_lock);
- /* invalidate the PTE so it's safe to modify */
- pte = ptep_get_and_clear(&init_mm, addr, ptep);
- flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+ pte = ptep_get(ptep);
/* modify the PTE bits as desired, then apply */
switch (action) {
@@ -59,11 +53,14 @@ static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
break;
}
- set_pte_at(&init_mm, addr, ptep, pte);
+ pte_update(&init_mm, addr, ptep, ~0UL, pte_val(pte), 0);
/* See ptesync comment in radix__set_pte_at() */
if (radix_enabled())
asm volatile("ptesync": : :"memory");
+
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
spin_unlock(&init_mm.page_table_lock);
return 0;
diff --git a/arch/powerpc/platforms/4xx/uic.c b/arch/powerpc/platforms/4xx/uic.c
index 36fb66ce54cf..89e2587b1a59 100644
--- a/arch/powerpc/platforms/4xx/uic.c
+++ b/arch/powerpc/platforms/4xx/uic.c
@@ -198,7 +198,6 @@ static void uic_irq_cascade(struct irq_desc *desc)
struct uic *uic = irq_desc_get_handler_data(desc);
u32 msr;
int src;
- int subvirq;
raw_spin_lock(&desc->lock);
if (irqd_is_level_type(idata))
@@ -213,8 +212,7 @@ static void uic_irq_cascade(struct irq_desc *desc)
src = 32 - ffs(msr);
- subvirq = irq_linear_revmap(uic->irqhost, src);
- generic_handle_irq(subvirq);
+ generic_handle_domain_irq(uic->irqhost, src);
uic_irq_ret:
raw_spin_lock(&desc->lock);
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
index b2981634f1f8..ea46870e5d6e 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
@@ -81,11 +81,10 @@ static struct irq_chip cpld_pic = {
.irq_unmask = cpld_unmask_irq,
};
-static int
+static unsigned int
cpld_pic_get_irq(int offset, u8 ignore, u8 __iomem *statusp,
u8 __iomem *maskp)
{
- int cpld_irq;
u8 status = in_8(statusp);
u8 mask = in_8(maskp);
@@ -93,28 +92,26 @@ cpld_pic_get_irq(int offset, u8 ignore, u8 __iomem *statusp,
status |= (ignore | mask);
if (status == 0xff)
- return 0;
-
- cpld_irq = ffz(status) + offset;
+ return ~0;
- return irq_linear_revmap(cpld_pic_host, cpld_irq);
+ return ffz(status) + offset;
}
static void cpld_pic_cascade(struct irq_desc *desc)
{
- unsigned int irq;
+ unsigned int hwirq;
- irq = cpld_pic_get_irq(0, PCI_IGNORE, &cpld_regs->pci_status,
+ hwirq = cpld_pic_get_irq(0, PCI_IGNORE, &cpld_regs->pci_status,
&cpld_regs->pci_mask);
- if (irq) {
- generic_handle_irq(irq);
+ if (hwirq != ~0) {
+ generic_handle_domain_irq(cpld_pic_host, hwirq);
return;
}
- irq = cpld_pic_get_irq(8, MISC_IGNORE, &cpld_regs->misc_status,
+ hwirq = cpld_pic_get_irq(8, MISC_IGNORE, &cpld_regs->misc_status,
&cpld_regs->misc_mask);
- if (irq) {
- generic_handle_irq(irq);
+ if (hwirq != ~0) {
+ generic_handle_domain_irq(cpld_pic_host, hwirq);
return;
}
}
diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c
index efb8bdecbcc7..110c444f4bc7 100644
--- a/arch/powerpc/platforms/52xx/media5200.c
+++ b/arch/powerpc/platforms/52xx/media5200.c
@@ -78,7 +78,7 @@ static struct irq_chip media5200_irq_chip = {
static void media5200_irq_cascade(struct irq_desc *desc)
{
struct irq_chip *chip = irq_desc_get_chip(desc);
- int sub_virq, val;
+ int val;
u32 status, enable;
/* Mask off the cascaded IRQ */
@@ -92,11 +92,10 @@ static void media5200_irq_cascade(struct irq_desc *desc)
enable = in_be32(media5200_irq.regs + MEDIA5200_IRQ_STATUS);
val = ffs((status & enable) >> MEDIA5200_IRQ_SHIFT);
if (val) {
- sub_virq = irq_linear_revmap(media5200_irq.irqhost, val - 1);
- /* pr_debug("%s: virq=%i s=%.8x e=%.8x hwirq=%i subvirq=%i\n",
- * __func__, virq, status, enable, val - 1, sub_virq);
+ generic_handle_domain_irq(media5200_irq.irqhost, val - 1);
+ /* pr_debug("%s: virq=%i s=%.8x e=%.8x hwirq=%i\n",
+ * __func__, virq, status, enable, val - 1);
*/
- generic_handle_irq(sub_virq);
}
/* Processing done; can reenable the cascade now */
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index 3823df235f25..f862b48b4824 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -190,14 +190,11 @@ static struct irq_chip mpc52xx_gpt_irq_chip = {
static void mpc52xx_gpt_irq_cascade(struct irq_desc *desc)
{
struct mpc52xx_gpt_priv *gpt = irq_desc_get_handler_data(desc);
- int sub_virq;
u32 status;
status = in_be32(&gpt->regs->status) & MPC52xx_GPT_STATUS_IRQMASK;
- if (status) {
- sub_virq = irq_linear_revmap(gpt->irqhost, 0);
- generic_handle_irq(sub_virq);
- }
+ if (status)
+ generic_handle_domain_irq(gpt->irqhost, 0);
}
static int mpc52xx_gpt_irq_map(struct irq_domain *h, unsigned int virq,
diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
index f82f75a6085c..285bfe19b798 100644
--- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
+++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
@@ -91,10 +91,8 @@ static void pq2ads_pci_irq_demux(struct irq_desc *desc)
break;
for (bit = 0; pend != 0; ++bit, pend <<= 1) {
- if (pend & 0x80000000) {
- int virq = irq_linear_revmap(priv->host, bit);
- generic_handle_irq(virq);
- }
+ if (pend & 0x80000000)
+ generic_handle_domain_irq(priv->host, bit);
}
}
}
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 6794145603de..a208997ade88 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -98,7 +98,7 @@ config PPC_BOOK3S_64
select PPC_HAVE_PMU_SUPPORT
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
- select ARCH_ENABLE_PMD_SPLIT_PTLOCK
+ select ARCH_ENABLE_SPLIT_PMD_PTLOCK
select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
select ARCH_SUPPORTS_HUGETLBFS
select ARCH_SUPPORTS_NUMA_BALANCING
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index c0ab62ba6f16..0873a7a20271 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -106,13 +106,9 @@ static void iic_ioexc_cascade(struct irq_desc *desc)
out_be64(&node_iic->iic_is, ack);
/* handle them */
for (cascade = 63; cascade >= 0; cascade--)
- if (bits & (0x8000000000000000UL >> cascade)) {
- unsigned int cirq =
- irq_linear_revmap(iic_host,
+ if (bits & (0x8000000000000000UL >> cascade))
+ generic_handle_domain_irq(iic_host,
base | cascade);
- if (cirq)
- generic_handle_irq(cirq);
- }
/* post-ack level interrupts */
ack = bits & ~IIC_ISR_EDGE_MASK;
if (ack)
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 210785f59271..8af75867cb42 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -190,16 +190,11 @@ static void spider_irq_cascade(struct irq_desc *desc)
{
struct irq_chip *chip = irq_desc_get_chip(desc);
struct spider_pic *pic = irq_desc_get_handler_data(desc);
- unsigned int cs, virq;
+ unsigned int cs;
cs = in_be32(pic->regs + TIR_CS) >> 24;
- if (cs == SPIDER_IRQ_INVALID)
- virq = 0;
- else
- virq = irq_linear_revmap(pic->host, cs);
-
- if (virq)
- generic_handle_irq(virq);
+ if (cs != SPIDER_IRQ_INVALID)
+ generic_handle_domain_irq(pic->host, cs);
chip->irq_eoi(&desc->irq_data);
}
diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
index a1b7f79a8a15..15396333a90b 100644
--- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
@@ -108,7 +108,6 @@ static const struct irq_domain_ops hlwd_irq_domain_ops = {
static unsigned int __hlwd_pic_get_irq(struct irq_domain *h)
{
void __iomem *io_base = h->host_data;
- int irq;
u32 irq_status;
irq_status = in_be32(io_base + HW_BROADWAY_ICR) &
@@ -116,23 +115,22 @@ static unsigned int __hlwd_pic_get_irq(struct irq_domain *h)
if (irq_status == 0)
return 0; /* no more IRQs pending */
- irq = __ffs(irq_status);
- return irq_linear_revmap(h, irq);
+ return __ffs(irq_status);
}
static void hlwd_pic_irq_cascade(struct irq_desc *desc)
{
struct irq_chip *chip = irq_desc_get_chip(desc);
struct irq_domain *irq_domain = irq_desc_get_handler_data(desc);
- unsigned int virq;
+ unsigned int hwirq;
raw_spin_lock(&desc->lock);
chip->irq_mask(&desc->irq_data); /* IRQ_LEVEL */
raw_spin_unlock(&desc->lock);
- virq = __hlwd_pic_get_irq(irq_domain);
- if (virq)
- generic_handle_irq(virq);
+ hwirq = __hlwd_pic_get_irq(irq_domain);
+ if (hwirq)
+ generic_handle_domain_irq(irq_domain, hwirq);
else
pr_err("spurious interrupt!\n");
@@ -190,7 +188,8 @@ static struct irq_domain *hlwd_pic_init(struct device_node *np)
unsigned int hlwd_pic_get_irq(void)
{
- return __hlwd_pic_get_irq(hlwd_irq_host);
+ unsigned int hwirq = __hlwd_pic_get_irq(hlwd_irq_host);
+ return hwirq ? irq_linear_revmap(hlwd_irq_host, hwirq) : 0;
}
/*
diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c
index c164419e254d..d55652b5f6fa 100644
--- a/arch/powerpc/platforms/powernv/opal-irqchip.c
+++ b/arch/powerpc/platforms/powernv/opal-irqchip.c
@@ -46,18 +46,15 @@ void opal_handle_events(void)
e = READ_ONCE(last_outstanding_events) & opal_event_irqchip.mask;
again:
while (e) {
- int virq, hwirq;
+ int hwirq;
hwirq = fls64(e) - 1;
e &= ~BIT_ULL(hwirq);
local_irq_disable();
- virq = irq_find_mapping(opal_event_irqchip.domain, hwirq);
- if (virq) {
- irq_enter();
- generic_handle_irq(virq);
- irq_exit();
- }
+ irq_enter();
+ generic_handle_domain_irq(opal_event_irqchip.domain, hwirq);
+ irq_exit();
local_irq_enable();
cond_resched();
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 6b0886668465..0dfaa6ab44cc 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -539,9 +539,10 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result)
* H_CPU_BEHAV_FAVOUR_SECURITY_H could be set only if
* H_CPU_BEHAV_FAVOUR_SECURITY is.
*/
- if (!(result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY))
+ if (!(result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY)) {
security_ftr_clear(SEC_FTR_FAVOUR_SECURITY);
- else if (result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY_H)
+ pseries_security_flavor = 0;
+ } else if (result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY_H)
pseries_security_flavor = 1;
else
pseries_security_flavor = 2;
diff --git a/arch/powerpc/sysdev/fsl_mpic_err.c b/arch/powerpc/sysdev/fsl_mpic_err.c
index 5fa5fa215541..9a98bb212922 100644
--- a/arch/powerpc/sysdev/fsl_mpic_err.c
+++ b/arch/powerpc/sysdev/fsl_mpic_err.c
@@ -99,7 +99,6 @@ static irqreturn_t fsl_error_int_handler(int irq, void *data)
struct mpic *mpic = (struct mpic *) data;
u32 eisr, eimr;
int errint;
- unsigned int cascade_irq;
eisr = mpic_fsl_err_read(mpic->err_regs, MPIC_ERR_INT_EISR);
eimr = mpic_fsl_err_read(mpic->err_regs, MPIC_ERR_INT_EIMR);
@@ -108,13 +107,11 @@ static irqreturn_t fsl_error_int_handler(int irq, void *data)
return IRQ_NONE;
while (eisr) {
+ int ret;
errint = __builtin_clz(eisr);
- cascade_irq = irq_linear_revmap(mpic->irqhost,
- mpic->err_int_vecs[errint]);
- WARN_ON(!cascade_irq);
- if (cascade_irq) {
- generic_handle_irq(cascade_irq);
- } else {
+ ret = generic_handle_domain_irq(mpic->irqhost,
+ mpic->err_int_vecs[errint]);
+ if (WARN_ON(ret)) {
eimr |= 1 << (31 - errint);
mpic_fsl_err_write(mpic->err_regs, eimr);
}
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 808e7118abfc..e6b06c3f8197 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -266,7 +266,6 @@ out_free:
static irqreturn_t fsl_msi_cascade(int irq, void *data)
{
- unsigned int cascade_irq;
struct fsl_msi *msi_data;
int msir_index = -1;
u32 msir_value = 0;
@@ -279,9 +278,6 @@ static irqreturn_t fsl_msi_cascade(int irq, void *data)
msir_index = cascade_data->index;
- if (msir_index >= NR_MSI_REG_MAX)
- cascade_irq = 0;
-
switch (msi_data->feature & FSL_PIC_IP_MASK) {
case FSL_PIC_IP_MPIC:
msir_value = fsl_msi_read(msi_data->msi_regs,
@@ -305,15 +301,15 @@ static irqreturn_t fsl_msi_cascade(int irq, void *data)
}
while (msir_value) {
+ int err;
intr_index = ffs(msir_value) - 1;
- cascade_irq = irq_linear_revmap(msi_data->irqhost,
+ err = generic_handle_domain_irq(msi_data->irqhost,
msi_hwirq(msi_data, msir_index,
intr_index + have_shift));
- if (cascade_irq) {
- generic_handle_irq(cascade_irq);
+ if (!err)
ret = IRQ_HANDLED;
- }
+
have_shift += intr_index + 1;
msir_value = msir_value >> (intr_index + 1);
}
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index dbdbbc2f1dc5..8183ca343675 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -67,6 +67,7 @@ static struct irq_domain *xive_irq_domain;
static struct xive_ipi_desc {
unsigned int irq;
char name[16];
+ atomic_t started;
} *xive_ipis;
/*
@@ -1120,7 +1121,7 @@ static const struct irq_domain_ops xive_ipi_irq_domain_ops = {
.alloc = xive_ipi_irq_domain_alloc,
};
-static int __init xive_request_ipi(void)
+static int __init xive_init_ipis(void)
{
struct fwnode_handle *fwnode;
struct irq_domain *ipi_domain;
@@ -1144,10 +1145,6 @@ static int __init xive_request_ipi(void)
struct xive_ipi_desc *xid = &xive_ipis[node];
struct xive_ipi_alloc_info info = { node };
- /* Skip nodes without CPUs */
- if (cpumask_empty(cpumask_of_node(node)))
- continue;
-
/*
* Map one IPI interrupt per node for all cpus of that node.
* Since the HW interrupt number doesn't have any meaning,
@@ -1159,11 +1156,6 @@ static int __init xive_request_ipi(void)
xid->irq = ret;
snprintf(xid->name, sizeof(xid->name), "IPI-%d", node);
-
- ret = request_irq(xid->irq, xive_muxed_ipi_action,
- IRQF_PERCPU | IRQF_NO_THREAD, xid->name, NULL);
-
- WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret);
}
return ret;
@@ -1178,6 +1170,22 @@ out:
return ret;
}
+static int xive_request_ipi(unsigned int cpu)
+{
+ struct xive_ipi_desc *xid = &xive_ipis[early_cpu_to_node(cpu)];
+ int ret;
+
+ if (atomic_inc_return(&xid->started) > 1)
+ return 0;
+
+ ret = request_irq(xid->irq, xive_muxed_ipi_action,
+ IRQF_PERCPU | IRQF_NO_THREAD,
+ xid->name, NULL);
+
+ WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret);
+ return ret;
+}
+
static int xive_setup_cpu_ipi(unsigned int cpu)
{
unsigned int xive_ipi_irq = xive_ipi_cpu_to_irq(cpu);
@@ -1192,6 +1200,9 @@ static int xive_setup_cpu_ipi(unsigned int cpu)
if (xc->hw_ipi != XIVE_BAD_IRQ)
return 0;
+ /* Register the IPI */
+ xive_request_ipi(cpu);
+
/* Grab an IPI from the backend, this will populate xc->hw_ipi */
if (xive_ops->get_ipi(cpu, xc))
return -EIO;
@@ -1231,6 +1242,8 @@ static void xive_cleanup_cpu_ipi(unsigned int cpu, struct xive_cpu *xc)
if (xc->hw_ipi == XIVE_BAD_IRQ)
return;
+ /* TODO: clear IPI mapping */
+
/* Mask the IPI */
xive_do_source_set_mask(&xc->ipi_data, true);
@@ -1253,7 +1266,7 @@ void __init xive_smp_probe(void)
smp_ops->cause_ipi = xive_cause_ipi;
/* Register the IPI */
- xive_request_ipi();
+ xive_init_ipis();
/* Allocate and setup IPI for the boot CPU */
xive_setup_cpu_ipi(smp_processor_id());
diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts
index ec79944065c9..baea7d204639 100644
--- a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts
+++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts
@@ -14,6 +14,10 @@
model = "Microchip PolarFire-SoC Icicle Kit";
compatible = "microchip,mpfs-icicle-kit";
+ aliases {
+ ethernet0 = &emac1;
+ };
+
chosen {
stdout-path = &serial0;
};
diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi
index b9819570a7d1..9d2fbbc1f777 100644
--- a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi
+++ b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi
@@ -317,7 +317,7 @@
reg = <0x0 0x20112000 0x0 0x2000>;
interrupt-parent = <&plic>;
interrupts = <70 71 72 73>;
- mac-address = [00 00 00 00 00 00];
+ local-mac-address = [00 00 00 00 00 00];
clocks = <&clkcfg 5>, <&clkcfg 2>;
status = "disabled";
clock-names = "pclk", "hclk";
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index d3081e4d9600..3397ddac1a30 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -11,7 +11,7 @@ endif
CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,)
ifdef CONFIG_KEXEC
-AFLAGS_kexec_relocate.o := -mcmodel=medany -mno-relax
+AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax)
endif
extra-y += head.o
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 1a85305720e8..9c0511119bad 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -10,6 +10,7 @@
#include <asm/ptrace.h>
#include <asm/syscall.h>
#include <asm/thread_info.h>
+#include <asm/switch_to.h>
#include <linux/audit.h>
#include <linux/ptrace.h>
#include <linux/elf.h>
@@ -56,6 +57,9 @@ static int riscv_fpr_get(struct task_struct *target,
{
struct __riscv_d_ext_state *fstate = &target->thread.fstate;
+ if (target == current)
+ fstate_save(current, task_pt_regs(current));
+
membuf_write(&to, fstate, offsetof(struct __riscv_d_ext_state, fcsr));
membuf_store(&to, fstate->fcsr);
return membuf_zero(&to, 4); // explicitly pad
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 18bd0e4bc36c..120b2f6f71bc 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -229,8 +229,8 @@ static void __init init_resources(void)
}
/* Clean-up any unused pre-allocated resources */
- mem_res_sz = (num_resources - res_idx + 1) * sizeof(*mem_res);
- memblock_free(__pa(mem_res), mem_res_sz);
+ if (res_idx >= 0)
+ memblock_free(__pa(mem_res), (res_idx + 1) * sizeof(*mem_res));
return;
error:
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 88134cc288d9..7cb4f391d106 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -197,7 +197,7 @@ static void __init setup_bootmem(void)
* if end of dram is equal to maximum addressable memory. For 64-bit
* kernel, this problem can't happen here as the end of the virtual
* address space is occupied by the kernel mapping then this check must
- * be done in create_kernel_page_table.
+ * be done as soon as the kernel mapping base address is determined.
*/
max_mapped_addr = __pa(~(ulong)0);
if (max_mapped_addr == (phys_ram_end - 1))
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index a0e2130f0100..92c0a1b4c528 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -138,6 +138,8 @@ config S390
select HAVE_ARCH_JUMP_LABEL_RELATIVE
select HAVE_ARCH_KASAN
select HAVE_ARCH_KASAN_VMALLOC
+ select HAVE_ARCH_KCSAN
+ select HAVE_ARCH_KFENCE
select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_SOFT_DIRTY
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 1e3172877982..17dc4f1ac4fa 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -142,7 +142,8 @@ all: bzImage
KBUILD_IMAGE := $(boot)/bzImage
install:
- $(Q)$(MAKE) $(build)=$(boot) $@
+ sh -x $(srctree)/$(boot)/install.sh $(KERNELRELEASE) $(KBUILD_IMAGE) \
+ System.map "$(INSTALL_PATH)"
bzImage: vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index 41a64b8dce25..0ba646899131 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -7,6 +7,7 @@ KCOV_INSTRUMENT := n
GCOV_PROFILE := n
UBSAN_SANITIZE := n
KASAN_SANITIZE := n
+KCSAN_SANITIZE := n
KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
@@ -36,7 +37,7 @@ CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
obj-y := head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o
obj-y += string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o
-obj-y += version.o pgm_check_info.o ctype.o text_dma.o
+obj-y += version.o pgm_check_info.o ctype.o
obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE)) += uv.o
obj-$(CONFIG_RELOCATABLE) += machine_kexec_reloc.o
obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
@@ -69,7 +70,3 @@ $(obj)/compressed/vmlinux: $(obj)/startup.a FORCE
$(obj)/startup.a: $(OBJECTS) FORCE
$(call if_changed,ar)
-
-install:
- sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \
- System.map "$(INSTALL_PATH)"
diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h
index ae04e1c93764..641ce0fc5c3e 100644
--- a/arch/s390/boot/boot.h
+++ b/arch/s390/boot/boot.h
@@ -2,14 +2,9 @@
#ifndef BOOT_BOOT_H
#define BOOT_BOOT_H
+#include <asm/extable.h>
#include <linux/types.h>
-#define BOOT_STACK_OFFSET 0x8000
-
-#ifndef __ASSEMBLY__
-
-#include <linux/compiler.h>
-
void startup_kernel(void);
unsigned long detect_memory(void);
bool is_ipl_block_dump(void);
@@ -18,17 +13,22 @@ void setup_boot_command_line(void);
void parse_boot_command_line(void);
void verify_facilities(void);
void print_missing_facilities(void);
+void sclp_early_setup_buffer(void);
void print_pgm_check_info(void);
unsigned long get_random_base(unsigned long safe_addr);
void __printf(1, 2) decompressor_printk(const char *fmt, ...);
+/* Symbols defined by linker scripts */
extern const char kernel_version[];
extern unsigned long memory_limit;
extern unsigned long vmalloc_size;
extern int vmalloc_size_set;
extern int kaslr_enabled;
+extern char __boot_data_start[], __boot_data_end[];
+extern char __boot_data_preserved_start[], __boot_data_preserved_end[];
+extern char _decompressor_syms_start[], _decompressor_syms_end[];
+extern char _stack_start[], _stack_end[];
unsigned long read_ipl_report(unsigned long safe_offset);
-#endif /* __ASSEMBLY__ */
#endif /* BOOT_BOOT_H */
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index e30d3fdbbc78..3b860061e84d 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -9,6 +9,7 @@ KCOV_INSTRUMENT := n
GCOV_PROFILE := n
UBSAN_SANITIZE := n
KASAN_SANITIZE := n
+KCSAN_SANITIZE := n
obj-y := $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) info.o
obj-$(CONFIG_KERNEL_ZSTD) += clz_ctz.o
diff --git a/arch/s390/boot/compressed/decompressor.c b/arch/s390/boot/compressed/decompressor.c
index 37a4a8d33c6c..e27c2140d620 100644
--- a/arch/s390/boot/compressed/decompressor.c
+++ b/arch/s390/boot/compressed/decompressor.c
@@ -23,11 +23,6 @@
#define memmove memmove
#define memzero(s, n) memset((s), 0, (n))
-/* Symbols defined by linker scripts */
-extern char _end[];
-extern unsigned char _compressed_start[];
-extern unsigned char _compressed_end[];
-
#ifdef CONFIG_KERNEL_BZIP2
#define BOOT_HEAP_SIZE 0x400000
#elif CONFIG_KERNEL_ZSTD
diff --git a/arch/s390/boot/compressed/decompressor.h b/arch/s390/boot/compressed/decompressor.h
index 41f0ad97a4db..a59f75c5b049 100644
--- a/arch/s390/boot/compressed/decompressor.h
+++ b/arch/s390/boot/compressed/decompressor.h
@@ -26,7 +26,12 @@ struct vmlinux_info {
unsigned long rela_dyn_end;
};
+/* Symbols defined by linker scripts */
+extern char _end[];
+extern unsigned char _compressed_start[];
+extern unsigned char _compressed_end[];
extern char _vmlinux_info[];
+
#define vmlinux (*(struct vmlinux_info *)_vmlinux_info)
#endif /* BOOT_COMPRESSED_DECOMPRESSOR_H */
diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S
index 27a09c1c78f6..918e05137d4c 100644
--- a/arch/s390/boot/compressed/vmlinux.lds.S
+++ b/arch/s390/boot/compressed/vmlinux.lds.S
@@ -1,6 +1,9 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <asm-generic/vmlinux.lds.h>
#include <asm/vmlinux.lds.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include <asm/sclp.h>
OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
OUTPUT_ARCH(s390:64-bit)
@@ -34,27 +37,6 @@ SECTIONS
*(.data.*)
_edata = . ;
}
- /*
- * .dma section for code, data, ex_table that need to stay below 2 GB,
- * even when the kernel is relocate: above 2 GB.
- */
- . = ALIGN(PAGE_SIZE);
- _sdma = .;
- .dma.text : {
- _stext_dma = .;
- *(.dma.text)
- . = ALIGN(PAGE_SIZE);
- _etext_dma = .;
- }
- . = ALIGN(16);
- .dma.ex_table : {
- _start_dma_ex_table = .;
- KEEP(*(.dma.ex_table))
- _stop_dma_ex_table = .;
- }
- .dma.data : { *(.dma.data) }
- . = ALIGN(PAGE_SIZE);
- _edma = .;
BOOT_DATA
BOOT_DATA_PRESERVED
@@ -69,6 +51,17 @@ SECTIONS
*(.bss)
*(.bss.*)
*(COMMON)
+ /*
+ * Stacks for the decompressor
+ */
+ . = ALIGN(PAGE_SIZE);
+ _dump_info_stack_start = .;
+ . += PAGE_SIZE;
+ _dump_info_stack_end = .;
+ . = ALIGN(PAGE_SIZE);
+ _stack_start = .;
+ . += BOOT_STACK_SIZE;
+ _stack_end = .;
_ebss = .;
}
diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S
index 51693cfb65c2..40f4cff538b8 100644
--- a/arch/s390/boot/head.S
+++ b/arch/s390/boot/head.S
@@ -25,13 +25,15 @@
#include <linux/init.h>
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
#include <asm/page.h>
#include <asm/ptrace.h>
-#include "boot.h"
+#include <asm/sclp.h>
#define ARCH_OFFSET 4
+#define EP_OFFSET 0x10008
+#define EP_STRING "S390EP"
+
__HEAD
#define IPL_BS 0x730
@@ -275,11 +277,11 @@ iplstart:
.Lcpuid:.fill 8,1,0
#
-# startup-code at 0x10000, running in absolute addressing mode
+# normal startup-code, running in absolute addressing mode
# this is called either by the ipl loader or directly by PSW restart
# or linload or SALIPL
#
- .org 0x10000
+ .org STARTUP_NORMAL_OFFSET
SYM_CODE_START(startup)
j startup_normal
.org EP_OFFSET
@@ -292,9 +294,9 @@ SYM_CODE_START(startup)
.ascii EP_STRING
.byte 0x00,0x01
#
-# kdump startup-code at 0x10010, running in 64 bit absolute addressing mode
+# kdump startup-code, running in 64 bit absolute addressing mode
#
- .org 0x10010
+ .org STARTUP_KDUMP_OFFSET
j startup_kdump
SYM_CODE_END(startup)
SYM_CODE_START_LOCAL(startup_normal)
@@ -315,18 +317,16 @@ SYM_CODE_START_LOCAL(startup_normal)
xc 0x300(256),0x300
xc 0xe00(256),0xe00
xc 0xf00(256),0xf00
- lctlg %c0,%c15,.Lctl-.LPG0(%r13) # load control registers
stcke __LC_BOOT_CLOCK
mvc __LC_LAST_UPDATE_CLOCK(8),__LC_BOOT_CLOCK+1
spt 6f-.LPG0(%r13)
mvc __LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13)
- l %r15,.Lstack-.LPG0(%r13)
+ larl %r15,_stack_end-STACK_FRAME_OVERHEAD
+ brasl %r14,sclp_early_setup_buffer
brasl %r14,verify_facilities
brasl %r14,startup_kernel
SYM_CODE_END(startup_normal)
-.Lstack:
- .long BOOT_STACK_OFFSET + BOOT_STACK_SIZE - STACK_FRAME_OVERHEAD
.align 8
6: .long 0x7fffffff,0xffffffff
.Lext_new_psw:
@@ -335,35 +335,6 @@ SYM_CODE_END(startup_normal)
.quad 0x0000000180000000,startup_pgm_check_handler
.Lio_new_psw:
.quad 0x0002000180000000,0x1f0 # disabled wait
-.Lctl: .quad 0x04040000 # cr0: AFP registers & secondary space
- .quad 0 # cr1: primary space segment table
- .quad .Lduct # cr2: dispatchable unit control table
- .quad 0 # cr3: instruction authorization
- .quad 0xffff # cr4: instruction authorization
- .quad .Lduct # cr5: primary-aste origin
- .quad 0 # cr6: I/O interrupts
- .quad 0 # cr7: secondary space segment table
- .quad 0x0000000000008000 # cr8: access registers translation
- .quad 0 # cr9: tracing off
- .quad 0 # cr10: tracing off
- .quad 0 # cr11: tracing off
- .quad 0 # cr12: tracing off
- .quad 0 # cr13: home space segment table
- .quad 0xc0000000 # cr14: machine check handling off
- .quad .Llinkage_stack # cr15: linkage stack operations
-
- .section .dma.data,"aw",@progbits
-.Lduct: .long 0,.Laste,.Laste,0,.Lduald,0,0,0
- .long 0,0,0,0,0,0,0,0
-.Llinkage_stack:
- .long 0,0,0x89000000,0,0,0,0x8a000000,0
- .align 64
-.Laste: .quad 0,0xffffffffffffffff,0,0,0,0,0,0
- .align 128
-.Lduald:.rept 8
- .long 0x80000000,0,0,0 # invalid access-list entries
- .endr
- .previous
#include "head_kdump.S"
@@ -386,15 +357,13 @@ SYM_CODE_START_LOCAL(startup_pgm_check_handler)
oi __LC_RETURN_PSW+1,0x2 # set wait state bit
larl %r9,.Lold_psw_disabled_wait
stg %r9,__LC_PGM_NEW_PSW+8
- l %r15,.Ldump_info_stack-.Lold_psw_disabled_wait(%r9)
+ larl %r15,_dump_info_stack_end-STACK_FRAME_OVERHEAD
brasl %r14,print_pgm_check_info
.Lold_psw_disabled_wait:
la %r8,4095
lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r8)
lpswe __LC_RETURN_PSW # disabled wait
SYM_CODE_END(startup_pgm_check_handler)
-.Ldump_info_stack:
- .long 0x5000 + PAGE_SIZE - STACK_FRAME_OVERHEAD
#
# params at 10400 (setup.h)
@@ -415,7 +384,4 @@ SYM_DATA_START(parmarea)
.org PARMAREA+__PARMAREA_SIZE
SYM_DATA_END(parmarea)
- .org EARLY_SCCB_OFFSET
- .fill 4096
-
.org HEAD_END
diff --git a/arch/s390/boot/ipl_report.c b/arch/s390/boot/ipl_report.c
index 0b4965573656..9b14045065b6 100644
--- a/arch/s390/boot/ipl_report.c
+++ b/arch/s390/boot/ipl_report.c
@@ -54,9 +54,9 @@ static unsigned long find_bootdata_space(struct ipl_rb_components *comps,
* not overlap with any component or any certificate.
*/
repeat:
- if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE &&
- intersects(INITRD_START, INITRD_SIZE, safe_addr, size))
- safe_addr = INITRD_START + INITRD_SIZE;
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && initrd_data.start && initrd_data.size &&
+ intersects(initrd_data.start, initrd_data.size, safe_addr, size))
+ safe_addr = initrd_data.start + initrd_data.size;
for_each_rb_entry(comp, comps)
if (intersects(safe_addr, size, comp->addr, comp->len)) {
safe_addr = comp->addr + comp->len;
diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c
index 0dd48fbdbaa4..d8984462071f 100644
--- a/arch/s390/boot/kaslr.c
+++ b/arch/s390/boot/kaslr.c
@@ -186,9 +186,9 @@ unsigned long get_random_base(unsigned long safe_addr)
*/
memory_limit -= kasan_estimate_memory_needs(memory_limit);
- if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE) {
- if (safe_addr < INITRD_START + INITRD_SIZE)
- safe_addr = INITRD_START + INITRD_SIZE;
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && initrd_data.start && initrd_data.size) {
+ if (safe_addr < initrd_data.start + initrd_data.size)
+ safe_addr = initrd_data.start + initrd_data.size;
}
safe_addr = ALIGN(safe_addr, THREAD_SIZE);
diff --git a/arch/s390/boot/mem_detect.c b/arch/s390/boot/mem_detect.c
index 4e17adbde495..2f949cd9076b 100644
--- a/arch/s390/boot/mem_detect.c
+++ b/arch/s390/boot/mem_detect.c
@@ -1,6 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/errno.h>
#include <linux/init.h>
+#include <asm/setup.h>
+#include <asm/processor.h>
#include <asm/sclp.h>
#include <asm/sections.h>
#include <asm/mem_detect.h>
@@ -24,9 +26,9 @@ static void *mem_detect_alloc_extended(void)
{
unsigned long offset = ALIGN(mem_safe_offset(), sizeof(u64));
- 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));
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && initrd_data.start && initrd_data.size &&
+ initrd_data.start < offset + ENTRIES_EXTENDED_MAX)
+ offset = ALIGN(initrd_data.start + initrd_data.size, sizeof(u64));
return (void *)offset;
}
diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c
index 3a46abed2549..209f6ae5a197 100644
--- a/arch/s390/boot/pgm_check_info.c
+++ b/arch/s390/boot/pgm_check_info.c
@@ -29,7 +29,6 @@ static char *symstart(char *p)
return p + 1;
}
-extern char _decompressor_syms_start[], _decompressor_syms_end[];
static noinline char *findsym(unsigned long ip, unsigned short *off, unsigned short *len)
{
/* symbol entries are in a form "10000 c4 startup\0" */
@@ -126,8 +125,8 @@ out:
static noinline void print_stacktrace(void)
{
- struct stack_info boot_stack = { STACK_TYPE_TASK, BOOT_STACK_OFFSET,
- BOOT_STACK_OFFSET + BOOT_STACK_SIZE };
+ struct stack_info boot_stack = { STACK_TYPE_TASK, (unsigned long)_stack_start,
+ (unsigned long)_stack_end };
unsigned long sp = S390_lowcore.gpregs_save_area[15];
bool first = true;
diff --git a/arch/s390/boot/sclp_early_core.c b/arch/s390/boot/sclp_early_core.c
index 5a19fd7020b5..6f30646afbd0 100644
--- a/arch/s390/boot/sclp_early_core.c
+++ b/arch/s390/boot/sclp_early_core.c
@@ -1,2 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
+#include "boot.h"
#include "../../../drivers/s390/char/sclp_early_core.c"
+
+/* SCLP early buffer must stay page-aligned and below 2GB */
+static char __sclp_early_sccb[EXT_SCCB_READ_SCP] __aligned(PAGE_SIZE);
+
+void sclp_early_setup_buffer(void)
+{
+ sclp_early_set_buffer(&__sclp_early_sccb);
+}
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index d0cf21641e3a..6dc8d0a53864 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -12,9 +12,8 @@
#include <asm/uv.h>
#include "compressed/decompressor.h"
#include "boot.h"
+#include "uv.h"
-extern char __boot_data_start[], __boot_data_end[];
-extern char __boot_data_preserved_start[], __boot_data_preserved_end[];
unsigned long __bootdata_preserved(__kaslr_offset);
unsigned long __bootdata_preserved(VMALLOC_START);
unsigned long __bootdata_preserved(VMALLOC_END);
@@ -24,44 +23,11 @@ unsigned long __bootdata_preserved(MODULES_VADDR);
unsigned long __bootdata_preserved(MODULES_END);
unsigned long __bootdata(ident_map_size);
int __bootdata(is_full_image) = 1;
+struct initrd_data __bootdata(initrd_data);
u64 __bootdata_preserved(stfle_fac_list[16]);
u64 __bootdata_preserved(alt_stfle_fac_list[16]);
-
-/*
- * Some code and data needs to stay below 2 GB, even when the kernel would be
- * relocated above 2 GB, because it has to use 31 bit addresses.
- * Such code and data is part of the .dma section, and its location is passed
- * over to the decompressed / relocated kernel via the .boot.preserved.data
- * section.
- */
-extern char _sdma[], _edma[];
-extern char _stext_dma[], _etext_dma[];
-extern struct exception_table_entry _start_dma_ex_table[];
-extern struct exception_table_entry _stop_dma_ex_table[];
-unsigned long __bootdata_preserved(__sdma) = __pa(&_sdma);
-unsigned long __bootdata_preserved(__edma) = __pa(&_edma);
-unsigned long __bootdata_preserved(__stext_dma) = __pa(&_stext_dma);
-unsigned long __bootdata_preserved(__etext_dma) = __pa(&_etext_dma);
-struct exception_table_entry *
- __bootdata_preserved(__start_dma_ex_table) = _start_dma_ex_table;
-struct exception_table_entry *
- __bootdata_preserved(__stop_dma_ex_table) = _stop_dma_ex_table;
-
-int _diag210_dma(struct diag210 *addr);
-int _diag26c_dma(void *req, void *resp, enum diag26c_sc subcode);
-int _diag14_dma(unsigned long rx, unsigned long ry1, unsigned long subcode);
-void _diag0c_dma(struct hypfs_diag0c_entry *entry);
-void _diag308_reset_dma(void);
-struct diag_ops __bootdata_preserved(diag_dma_ops) = {
- .diag210 = _diag210_dma,
- .diag26c = _diag26c_dma,
- .diag14 = _diag14_dma,
- .diag0c = _diag0c_dma,
- .diag308_reset = _diag308_reset_dma
-};
-static struct diag210 _diag210_tmp_dma __section(".dma.data");
-struct diag210 *__bootdata_preserved(__diag210_tmp_dma) = &_diag210_tmp_dma;
+struct oldmem_data __bootdata_preserved(oldmem_data);
void error(char *x)
{
@@ -91,12 +57,12 @@ static void rescue_initrd(unsigned long addr)
{
if (!IS_ENABLED(CONFIG_BLK_DEV_INITRD))
return;
- if (!INITRD_START || !INITRD_SIZE)
+ if (!initrd_data.start || !initrd_data.size)
return;
- if (addr <= INITRD_START)
+ if (addr <= initrd_data.start)
return;
- memmove((void *)addr, (void *)INITRD_START, INITRD_SIZE);
- INITRD_START = addr;
+ memmove((void *)addr, (void *)initrd_data.start, initrd_data.size);
+ initrd_data.start = addr;
}
static void copy_bootdata(void)
@@ -169,9 +135,9 @@ static void setup_ident_map_size(unsigned long max_physmem_end)
ident_map_size = min(ident_map_size, 1UL << MAX_PHYSMEM_BITS);
#ifdef CONFIG_CRASH_DUMP
- if (OLDMEM_BASE) {
+ if (oldmem_data.start) {
kaslr_enabled = 0;
- ident_map_size = min(ident_map_size, OLDMEM_SIZE);
+ ident_map_size = min(ident_map_size, oldmem_data.size);
} else if (ipl_block_valid && is_ipl_block_dump()) {
kaslr_enabled = 0;
if (!sclp_early_get_hsa_size(&hsa_size) && hsa_size)
@@ -282,12 +248,28 @@ static void setup_vmalloc_size(void)
vmalloc_size = max(size, vmalloc_size);
}
+static void offset_vmlinux_info(unsigned long offset)
+{
+ vmlinux.default_lma += offset;
+ *(unsigned long *)(&vmlinux.entry) += offset;
+ vmlinux.bootdata_off += offset;
+ vmlinux.bootdata_preserved_off += offset;
+ vmlinux.rela_dyn_start += offset;
+ vmlinux.rela_dyn_end += offset;
+ vmlinux.dynsym_start += offset;
+}
+
void startup_kernel(void)
{
unsigned long random_lma;
unsigned long safe_addr;
void *img;
+ initrd_data.start = parmarea.initrd_start;
+ initrd_data.size = parmarea.initrd_size;
+ oldmem_data.start = parmarea.oldmem_base;
+ oldmem_data.size = parmarea.oldmem_size;
+
setup_lpp();
store_ipl_parmblock();
safe_addr = mem_safe_offset();
@@ -297,23 +279,17 @@ void startup_kernel(void)
sclp_early_read_info();
setup_boot_command_line();
parse_boot_command_line();
+ sanitize_prot_virt_host();
setup_ident_map_size(detect_memory());
setup_vmalloc_size();
setup_kernel_memory_layout();
- random_lma = __kaslr_offset = 0;
if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_enabled) {
random_lma = get_random_base(safe_addr);
if (random_lma) {
__kaslr_offset = random_lma - vmlinux.default_lma;
img = (void *)vmlinux.default_lma;
- vmlinux.default_lma += __kaslr_offset;
- vmlinux.entry += __kaslr_offset;
- vmlinux.bootdata_off += __kaslr_offset;
- vmlinux.bootdata_preserved_off += __kaslr_offset;
- vmlinux.rela_dyn_start += __kaslr_offset;
- vmlinux.rela_dyn_end += __kaslr_offset;
- vmlinux.dynsym_start += __kaslr_offset;
+ offset_vmlinux_info(__kaslr_offset);
}
}
diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c
index f6b0c4f43c99..e6be155ab2e5 100644
--- a/arch/s390/boot/uv.c
+++ b/arch/s390/boot/uv.c
@@ -1,8 +1,12 @@
// SPDX-License-Identifier: GPL-2.0
#include <asm/uv.h>
+#include <asm/boot_data.h>
#include <asm/facility.h>
#include <asm/sections.h>
+#include "boot.h"
+#include "uv.h"
+
/* will be used in arch/s390/kernel/uv.c */
#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
int __bootdata_preserved(prot_virt_guest);
@@ -47,26 +51,34 @@ void uv_query_info(void)
}
#if IS_ENABLED(CONFIG_KVM)
-static bool has_uv_sec_stor_limit(void)
+void adjust_to_uv_max(unsigned long *vmax)
{
- /*
- * keep these conditions in line with setup_uv()
- */
- if (!is_prot_virt_host())
- return false;
+ if (is_prot_virt_host() && uv_info.max_sec_stor_addr)
+ *vmax = min_t(unsigned long, *vmax, uv_info.max_sec_stor_addr);
+}
+static int is_prot_virt_host_capable(void)
+{
+ /* disable if no prot_virt=1 given on command-line */
+ if (!is_prot_virt_host())
+ return 0;
+ /* disable if protected guest virtualization is enabled */
if (is_prot_virt_guest())
- return false;
-
+ return 0;
+ /* disable if no hardware support */
if (!test_facility(158))
- return false;
-
- return !!uv_info.max_sec_stor_addr;
+ return 0;
+ /* disable if kdump */
+ if (oldmem_data.start)
+ return 0;
+ /* disable if stand-alone dump */
+ if (ipl_block_valid && is_ipl_block_dump())
+ return 0;
+ return 1;
}
-void adjust_to_uv_max(unsigned long *vmax)
+void sanitize_prot_virt_host(void)
{
- if (has_uv_sec_stor_limit())
- *vmax = min_t(unsigned long, *vmax, uv_info.max_sec_stor_addr);
+ prot_virt_host = is_prot_virt_host_capable();
}
#endif
diff --git a/arch/s390/boot/uv.h b/arch/s390/boot/uv.h
new file mode 100644
index 000000000000..690ce019af5a
--- /dev/null
+++ b/arch/s390/boot/uv.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef BOOT_UV_H
+#define BOOT_UV_H
+
+#if IS_ENABLED(CONFIG_KVM)
+void adjust_to_uv_max(unsigned long *vmax);
+void sanitize_prot_virt_host(void);
+#else
+static inline void adjust_to_uv_max(unsigned long *vmax) {}
+static inline void sanitize_prot_virt_host(void) {}
+#endif
+
+#if defined(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) || IS_ENABLED(CONFIG_KVM)
+void uv_query_info(void);
+#else
+static inline void uv_query_info(void) {}
+#endif
+
+#endif /* BOOT_UV_H */
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index b88184019af9..11ffc7c37ada 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -10,7 +10,6 @@ CONFIG_BPF_JIT=y
CONFIG_BPF_JIT_ALWAYS_ON=y
CONFIG_BPF_LSM=y
CONFIG_PREEMPT=y
-CONFIG_SCHED_CORE=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
CONFIG_TASKSTATS=y
@@ -75,7 +74,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_MODVERSIONS=y
CONFIG_MODULE_SRCVERSION_ALL=y
CONFIG_MODULE_SIG_SHA256=y
-CONFIG_BLK_DEV_INTEGRITY=y
CONFIG_BLK_DEV_THROTTLING=y
CONFIG_BLK_WBT=y
CONFIG_BLK_CGROUP_IOLATENCY=y
@@ -466,6 +464,7 @@ CONFIG_DM_FLAKEY=m
CONFIG_DM_VERITY=m
CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
CONFIG_DM_SWITCH=m
+CONFIG_DM_INTEGRITY=m
CONFIG_NETDEVICES=y
CONFIG_BONDING=m
CONFIG_DUMMY=m
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 1667a3cdcf0a..e1642d2cba59 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -8,7 +8,6 @@ CONFIG_BPF_SYSCALL=y
CONFIG_BPF_JIT=y
CONFIG_BPF_JIT_ALWAYS_ON=y
CONFIG_BPF_LSM=y
-CONFIG_SCHED_CORE=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
CONFIG_TASKSTATS=y
diff --git a/arch/s390/hypfs/hypfs_diag0c.c b/arch/s390/hypfs/hypfs_diag0c.c
index 6c43d2ba2079..9a2786079e3a 100644
--- a/arch/s390/hypfs/hypfs_diag0c.c
+++ b/arch/s390/hypfs/hypfs_diag0c.c
@@ -21,7 +21,7 @@
static void diag0c_fn(void *data)
{
diag_stat_inc(DIAG_STAT_X00C);
- diag_dma_ops.diag0c(((void **) data)[smp_processor_id()]);
+ diag_amode31_ops.diag0c(((void **)data)[smp_processor_id()]);
}
/*
@@ -33,12 +33,12 @@ static void *diag0c_store(unsigned int *count)
unsigned int cpu_count, cpu, i;
void **cpu_vec;
- get_online_cpus();
+ cpus_read_lock();
cpu_count = num_online_cpus();
cpu_vec = kmalloc_array(num_possible_cpus(), sizeof(*cpu_vec),
GFP_KERNEL);
if (!cpu_vec)
- goto fail_put_online_cpus;
+ goto fail_unlock_cpus;
/* Note: Diag 0c needs 8 byte alignment and real storage */
diag0c_data = kzalloc(struct_size(diag0c_data, entry, cpu_count),
GFP_KERNEL | GFP_DMA);
@@ -54,13 +54,13 @@ static void *diag0c_store(unsigned int *count)
on_each_cpu(diag0c_fn, cpu_vec, 1);
*count = cpu_count;
kfree(cpu_vec);
- put_online_cpus();
+ cpus_read_unlock();
return diag0c_data;
fail_kfree_cpu_vec:
kfree(cpu_vec);
-fail_put_online_cpus:
- put_online_cpus();
+fail_unlock_cpus:
+ cpus_read_unlock();
return ERR_PTR(-ENOMEM);
}
diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h
index f58c92f28701..1effac6a0152 100644
--- a/arch/s390/include/asm/cio.h
+++ b/arch/s390/include/asm/cio.h
@@ -5,7 +5,6 @@
#ifndef _ASM_S390_CIO_H_
#define _ASM_S390_CIO_H_
-#include <linux/spinlock.h>
#include <linux/bitops.h>
#include <linux/genalloc.h>
#include <asm/types.h>
diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h
index c0f3bfeddcbe..646b12981f20 100644
--- a/arch/s390/include/asm/cpacf.h
+++ b/arch/s390/include/asm/cpacf.h
@@ -173,17 +173,16 @@ typedef struct { unsigned char bytes[16]; } cpacf_mask_t;
*/
static __always_inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask)
{
- register unsigned long r0 asm("0") = 0; /* query function */
- register unsigned long r1 asm("1") = (unsigned long) mask;
-
asm volatile(
- " spm 0\n" /* pckmo doesn't change the cc */
+ " lghi 0,0\n" /* query function */
+ " lgr 1,%[mask]\n"
+ " spm 0\n" /* pckmo doesn't change the cc */
/* Parameter regs are ignored, but must be nonzero and unique */
"0: .insn rrf,%[opc] << 16,2,4,6,0\n"
" brc 1,0b\n" /* handle partial completion */
: "=m" (*mask)
- : [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (opcode)
- : "cc");
+ : [mask] "d" ((unsigned long)mask), [opc] "i" (opcode)
+ : "cc", "0", "1");
}
static __always_inline int __cpacf_check_opcode(unsigned int opcode)
@@ -249,20 +248,22 @@ static __always_inline int cpacf_query_func(unsigned int opcode, unsigned int fu
static inline int cpacf_km(unsigned long func, void *param,
u8 *dest, const u8 *src, long src_len)
{
- register unsigned long r0 asm("0") = (unsigned long) func;
- register unsigned long r1 asm("1") = (unsigned long) param;
- register unsigned long r2 asm("2") = (unsigned long) src;
- register unsigned long r3 asm("3") = (unsigned long) src_len;
- register unsigned long r4 asm("4") = (unsigned long) dest;
+ union register_pair d, s;
+ d.even = (unsigned long)dest;
+ s.even = (unsigned long)src;
+ s.odd = (unsigned long)src_len;
asm volatile(
+ " lgr 0,%[fc]\n"
+ " lgr 1,%[pba]\n"
"0: .insn rre,%[opc] << 16,%[dst],%[src]\n"
" brc 1,0b\n" /* handle partial completion */
- : [src] "+a" (r2), [len] "+d" (r3), [dst] "+a" (r4)
- : [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (CPACF_KM)
- : "cc", "memory");
+ : [src] "+&d" (s.pair), [dst] "+&d" (d.pair)
+ : [fc] "d" (func), [pba] "d" ((unsigned long)param),
+ [opc] "i" (CPACF_KM)
+ : "cc", "memory", "0", "1");
- return src_len - r3;
+ return src_len - s.odd;
}
/**
@@ -279,20 +280,22 @@ static inline int cpacf_km(unsigned long func, void *param,
static inline int cpacf_kmc(unsigned long func, void *param,
u8 *dest, const u8 *src, long src_len)
{
- register unsigned long r0 asm("0") = (unsigned long) func;
- register unsigned long r1 asm("1") = (unsigned long) param;
- register unsigned long r2 asm("2") = (unsigned long) src;
- register unsigned long r3 asm("3") = (unsigned long) src_len;
- register unsigned long r4 asm("4") = (unsigned long) dest;
+ union register_pair d, s;
+ d.even = (unsigned long)dest;
+ s.even = (unsigned long)src;
+ s.odd = (unsigned long)src_len;
asm volatile(
+ " lgr 0,%[fc]\n"
+ " lgr 1,%[pba]\n"
"0: .insn rre,%[opc] << 16,%[dst],%[src]\n"
" brc 1,0b\n" /* handle partial completion */
- : [src] "+a" (r2), [len] "+d" (r3), [dst] "+a" (r4)
- : [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (CPACF_KMC)
- : "cc", "memory");
+ : [src] "+&d" (s.pair), [dst] "+&d" (d.pair)
+ : [fc] "d" (func), [pba] "d" ((unsigned long)param),
+ [opc] "i" (CPACF_KMC)
+ : "cc", "memory", "0", "1");
- return src_len - r3;
+ return src_len - s.odd;
}
/**
@@ -306,17 +309,19 @@ static inline int cpacf_kmc(unsigned long func, void *param,
static inline void cpacf_kimd(unsigned long func, void *param,
const u8 *src, long src_len)
{
- register unsigned long r0 asm("0") = (unsigned long) func;
- register unsigned long r1 asm("1") = (unsigned long) param;
- register unsigned long r2 asm("2") = (unsigned long) src;
- register unsigned long r3 asm("3") = (unsigned long) src_len;
+ union register_pair s;
+ s.even = (unsigned long)src;
+ s.odd = (unsigned long)src_len;
asm volatile(
+ " lgr 0,%[fc]\n"
+ " lgr 1,%[pba]\n"
"0: .insn rre,%[opc] << 16,0,%[src]\n"
" brc 1,0b\n" /* handle partial completion */
- : [src] "+a" (r2), [len] "+d" (r3)
- : [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (CPACF_KIMD)
- : "cc", "memory");
+ : [src] "+&d" (s.pair)
+ : [fc] "d" (func), [pba] "d" ((unsigned long)(param)),
+ [opc] "i" (CPACF_KIMD)
+ : "cc", "memory", "0", "1");
}
/**
@@ -329,17 +334,19 @@ static inline void cpacf_kimd(unsigned long func, void *param,
static inline void cpacf_klmd(unsigned long func, void *param,
const u8 *src, long src_len)
{
- register unsigned long r0 asm("0") = (unsigned long) func;
- register unsigned long r1 asm("1") = (unsigned long) param;
- register unsigned long r2 asm("2") = (unsigned long) src;
- register unsigned long r3 asm("3") = (unsigned long) src_len;
+ union register_pair s;
+ s.even = (unsigned long)src;
+ s.odd = (unsigned long)src_len;
asm volatile(
+ " lgr 0,%[fc]\n"
+ " lgr 1,%[pba]\n"
"0: .insn rre,%[opc] << 16,0,%[src]\n"
" brc 1,0b\n" /* handle partial completion */
- : [src] "+a" (r2), [len] "+d" (r3)
- : [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (CPACF_KLMD)
- : "cc", "memory");
+ : [src] "+&d" (s.pair)
+ : [fc] "d" (func), [pba] "d" ((unsigned long)param),
+ [opc] "i" (CPACF_KLMD)
+ : "cc", "memory", "0", "1");
}
/**
@@ -355,19 +362,21 @@ static inline void cpacf_klmd(unsigned long func, void *param,
static inline int cpacf_kmac(unsigned long func, void *param,
const u8 *src, long src_len)
{
- register unsigned long r0 asm("0") = (unsigned long) func;
- register unsigned long r1 asm("1") = (unsigned long) param;
- register unsigned long r2 asm("2") = (unsigned long) src;
- register unsigned long r3 asm("3") = (unsigned long) src_len;
+ union register_pair s;
+ s.even = (unsigned long)src;
+ s.odd = (unsigned long)src_len;
asm volatile(
+ " lgr 0,%[fc]\n"
+ " lgr 1,%[pba]\n"
"0: .insn rre,%[opc] << 16,0,%[src]\n"
" brc 1,0b\n" /* handle partial completion */
- : [src] "+a" (r2), [len] "+d" (r3)
- : [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (CPACF_KMAC)
- : "cc", "memory");
+ : [src] "+&d" (s.pair)
+ : [fc] "d" (func), [pba] "d" ((unsigned long)param),
+ [opc] "i" (CPACF_KMAC)
+ : "cc", "memory", "0", "1");
- return src_len - r3;
+ return src_len - s.odd;
}
/**
@@ -385,22 +394,24 @@ static inline int cpacf_kmac(unsigned long func, void *param,
static inline int cpacf_kmctr(unsigned long func, void *param, u8 *dest,
const u8 *src, long src_len, u8 *counter)
{
- register unsigned long r0 asm("0") = (unsigned long) func;
- register unsigned long r1 asm("1") = (unsigned long) param;
- register unsigned long r2 asm("2") = (unsigned long) src;
- register unsigned long r3 asm("3") = (unsigned long) src_len;
- register unsigned long r4 asm("4") = (unsigned long) dest;
- register unsigned long r6 asm("6") = (unsigned long) counter;
+ union register_pair d, s, c;
+ d.even = (unsigned long)dest;
+ s.even = (unsigned long)src;
+ s.odd = (unsigned long)src_len;
+ c.even = (unsigned long)counter;
asm volatile(
+ " lgr 0,%[fc]\n"
+ " lgr 1,%[pba]\n"
"0: .insn rrf,%[opc] << 16,%[dst],%[src],%[ctr],0\n"
" brc 1,0b\n" /* handle partial completion */
- : [src] "+a" (r2), [len] "+d" (r3),
- [dst] "+a" (r4), [ctr] "+a" (r6)
- : [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (CPACF_KMCTR)
- : "cc", "memory");
+ : [src] "+&d" (s.pair), [dst] "+&d" (d.pair),
+ [ctr] "+&d" (c.pair)
+ : [fc] "d" (func), [pba] "d" ((unsigned long)param),
+ [opc] "i" (CPACF_KMCTR)
+ : "cc", "memory", "0", "1");
- return src_len - r3;
+ return src_len - s.odd;
}
/**
@@ -417,20 +428,21 @@ static inline void cpacf_prno(unsigned long func, void *param,
u8 *dest, unsigned long dest_len,
const u8 *seed, unsigned long seed_len)
{
- register unsigned long r0 asm("0") = (unsigned long) func;
- register unsigned long r1 asm("1") = (unsigned long) param;
- register unsigned long r2 asm("2") = (unsigned long) dest;
- register unsigned long r3 asm("3") = (unsigned long) dest_len;
- register unsigned long r4 asm("4") = (unsigned long) seed;
- register unsigned long r5 asm("5") = (unsigned long) seed_len;
+ union register_pair d, s;
+ d.even = (unsigned long)dest;
+ d.odd = (unsigned long)dest_len;
+ s.even = (unsigned long)seed;
+ s.odd = (unsigned long)seed_len;
asm volatile (
+ " lgr 0,%[fc]\n"
+ " lgr 1,%[pba]\n"
"0: .insn rre,%[opc] << 16,%[dst],%[seed]\n"
" brc 1,0b\n" /* handle partial completion */
- : [dst] "+a" (r2), [dlen] "+d" (r3)
- : [fc] "d" (r0), [pba] "a" (r1),
- [seed] "a" (r4), [slen] "d" (r5), [opc] "i" (CPACF_PRNO)
- : "cc", "memory");
+ : [dst] "+&d" (d.pair)
+ : [fc] "d" (func), [pba] "d" ((unsigned long)param),
+ [seed] "d" (s.pair), [opc] "i" (CPACF_PRNO)
+ : "cc", "memory", "0", "1");
}
/**
@@ -443,19 +455,19 @@ static inline void cpacf_prno(unsigned long func, void *param,
static inline void cpacf_trng(u8 *ucbuf, unsigned long ucbuf_len,
u8 *cbuf, unsigned long cbuf_len)
{
- register unsigned long r0 asm("0") = (unsigned long) CPACF_PRNO_TRNG;
- register unsigned long r2 asm("2") = (unsigned long) ucbuf;
- register unsigned long r3 asm("3") = (unsigned long) ucbuf_len;
- register unsigned long r4 asm("4") = (unsigned long) cbuf;
- register unsigned long r5 asm("5") = (unsigned long) cbuf_len;
+ union register_pair u, c;
+ u.even = (unsigned long)ucbuf;
+ u.odd = (unsigned long)ucbuf_len;
+ c.even = (unsigned long)cbuf;
+ c.odd = (unsigned long)cbuf_len;
asm volatile (
+ " lghi 0,%[fc]\n"
"0: .insn rre,%[opc] << 16,%[ucbuf],%[cbuf]\n"
" brc 1,0b\n" /* handle partial completion */
- : [ucbuf] "+a" (r2), [ucbuflen] "+d" (r3),
- [cbuf] "+a" (r4), [cbuflen] "+d" (r5)
- : [fc] "d" (r0), [opc] "i" (CPACF_PRNO)
- : "cc", "memory");
+ : [ucbuf] "+&d" (u.pair), [cbuf] "+&d" (c.pair)
+ : [fc] "K" (CPACF_PRNO_TRNG), [opc] "i" (CPACF_PRNO)
+ : "cc", "memory", "0");
}
/**
@@ -466,15 +478,15 @@ static inline void cpacf_trng(u8 *ucbuf, unsigned long ucbuf_len,
*/
static inline void cpacf_pcc(unsigned long func, void *param)
{
- register unsigned long r0 asm("0") = (unsigned long) func;
- register unsigned long r1 asm("1") = (unsigned long) param;
-
asm volatile(
+ " lgr 0,%[fc]\n"
+ " lgr 1,%[pba]\n"
"0: .insn rre,%[opc] << 16,0,0\n" /* PCC opcode */
" brc 1,0b\n" /* handle partial completion */
:
- : [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (CPACF_PCC)
- : "cc", "memory");
+ : [fc] "d" (func), [pba] "d" ((unsigned long)param),
+ [opc] "i" (CPACF_PCC)
+ : "cc", "memory", "0", "1");
}
/**
@@ -487,14 +499,14 @@ static inline void cpacf_pcc(unsigned long func, void *param)
*/
static inline void cpacf_pckmo(long func, void *param)
{
- register unsigned long r0 asm("0") = (unsigned long) func;
- register unsigned long r1 asm("1") = (unsigned long) param;
-
asm volatile(
+ " lgr 0,%[fc]\n"
+ " lgr 1,%[pba]\n"
" .insn rre,%[opc] << 16,0,0\n" /* PCKMO opcode */
:
- : [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (CPACF_PCKMO)
- : "cc", "memory");
+ : [fc] "d" (func), [pba] "d" ((unsigned long)param),
+ [opc] "i" (CPACF_PCKMO)
+ : "cc", "memory", "0", "1");
}
/**
@@ -512,21 +524,23 @@ static inline void cpacf_kma(unsigned long func, void *param, u8 *dest,
const u8 *src, unsigned long src_len,
const u8 *aad, unsigned long aad_len)
{
- register unsigned long r0 asm("0") = (unsigned long) func;
- register unsigned long r1 asm("1") = (unsigned long) param;
- register unsigned long r2 asm("2") = (unsigned long) src;
- register unsigned long r3 asm("3") = (unsigned long) src_len;
- register unsigned long r4 asm("4") = (unsigned long) aad;
- register unsigned long r5 asm("5") = (unsigned long) aad_len;
- register unsigned long r6 asm("6") = (unsigned long) dest;
+ union register_pair d, s, a;
+ d.even = (unsigned long)dest;
+ s.even = (unsigned long)src;
+ s.odd = (unsigned long)src_len;
+ a.even = (unsigned long)aad;
+ a.odd = (unsigned long)aad_len;
asm volatile(
+ " lgr 0,%[fc]\n"
+ " lgr 1,%[pba]\n"
"0: .insn rrf,%[opc] << 16,%[dst],%[src],%[aad],0\n"
" brc 1,0b\n" /* handle partial completion */
- : [dst] "+a" (r6), [src] "+a" (r2), [slen] "+d" (r3),
- [aad] "+a" (r4), [alen] "+d" (r5)
- : [fc] "d" (r0), [pba] "a" (r1), [opc] "i" (CPACF_KMA)
- : "cc", "memory");
+ : [dst] "+&d" (d.pair), [src] "+&d" (s.pair),
+ [aad] "+&d" (a.pair)
+ : [fc] "d" (func), [pba] "d" ((unsigned long)param),
+ [opc] "i" (CPACF_KMA)
+ : "cc", "memory", "0", "1");
}
#endif /* _ASM_S390_CPACF_H */
diff --git a/arch/s390/include/asm/cpufeature.h b/arch/s390/include/asm/cpufeature.h
index 1d007c6ede95..14cfd48d598e 100644
--- a/arch/s390/include/asm/cpufeature.h
+++ b/arch/s390/include/asm/cpufeature.h
@@ -23,7 +23,7 @@
#define MAX_ELF_HWCAP_FEATURES (8 * sizeof(elf_hwcap))
#define MAX_CPU_FEATURES MAX_ELF_HWCAP_FEATURES
-#define cpu_feature(feat) ilog2(HWCAP_S390_ ## feat)
+#define cpu_feature(feat) ilog2(HWCAP_ ## feat)
int cpu_have_feature(unsigned int nr);
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index adc0179fa34e..04dc65f8901d 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -111,6 +111,23 @@ union ctlreg2 {
};
};
+union ctlreg5 {
+ unsigned long val;
+ struct {
+ unsigned long : 33;
+ unsigned long pasteo: 25;
+ unsigned long : 6;
+ };
+};
+
+union ctlreg15 {
+ unsigned long val;
+ struct {
+ unsigned long lsea : 61;
+ unsigned long : 3;
+ };
+};
+
#define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit)
#define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit)
diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h
index c1b82bcc017c..19a55e1e3a0c 100644
--- a/arch/s390/include/asm/debug.h
+++ b/arch/s390/include/asm/debug.h
@@ -13,6 +13,7 @@
#include <linux/time.h>
#include <linux/refcount.h>
#include <linux/fs.h>
+#include <linux/init.h>
#define DEBUG_MAX_LEVEL 6 /* debug levels range from 0 to 6 */
#define DEBUG_OFF_LEVEL -1 /* level where debug is switched off */
@@ -391,38 +392,99 @@ int debug_register_view(debug_info_t *id, struct debug_view *view);
int debug_unregister_view(debug_info_t *id, struct debug_view *view);
+#ifndef MODULE
+
+/*
+ * Note: Initial page and area numbers must be fixed to allow static
+ * initialization. This enables very early tracing. Changes to these values
+ * must be reflected in __DEFINE_STATIC_AREA.
+ */
+#define EARLY_PAGES 8
+#define EARLY_AREAS 1
+
+#define VNAME(var, suffix) __##var##_##suffix
+
/*
- define the debug levels:
- - 0 No debugging output to console or syslog
- - 1 Log internal errors to syslog, ignore check conditions
- - 2 Log internal errors and check conditions to syslog
- - 3 Log internal errors to console, log check conditions to syslog
- - 4 Log internal errors and check conditions to console
- - 5 panic on internal errors, log check conditions to console
- - 6 panic on both, internal errors and check conditions
+ * Define static areas for early trace data. During boot debug_register_static()
+ * will replace these with dynamically allocated areas to allow custom page and
+ * area sizes, and dynamic resizing.
*/
+#define __DEFINE_STATIC_AREA(var) \
+static char VNAME(var, data)[EARLY_PAGES][PAGE_SIZE] __initdata; \
+static debug_entry_t *VNAME(var, pages)[EARLY_PAGES] __initdata = { \
+ (debug_entry_t *)VNAME(var, data)[0], \
+ (debug_entry_t *)VNAME(var, data)[1], \
+ (debug_entry_t *)VNAME(var, data)[2], \
+ (debug_entry_t *)VNAME(var, data)[3], \
+ (debug_entry_t *)VNAME(var, data)[4], \
+ (debug_entry_t *)VNAME(var, data)[5], \
+ (debug_entry_t *)VNAME(var, data)[6], \
+ (debug_entry_t *)VNAME(var, data)[7], \
+}; \
+static debug_entry_t **VNAME(var, areas)[EARLY_AREAS] __initdata = { \
+ (debug_entry_t **)VNAME(var, pages), \
+}; \
+static int VNAME(var, active_pages)[EARLY_AREAS] __initdata; \
+static int VNAME(var, active_entries)[EARLY_AREAS] __initdata
+
+#define __DEBUG_INFO_INIT(var, _name, _buf_size) { \
+ .next = NULL, \
+ .prev = NULL, \
+ .ref_count = REFCOUNT_INIT(1), \
+ .lock = __SPIN_LOCK_UNLOCKED(var.lock), \
+ .level = DEBUG_DEFAULT_LEVEL, \
+ .nr_areas = EARLY_AREAS, \
+ .pages_per_area = EARLY_PAGES, \
+ .buf_size = (_buf_size), \
+ .entry_size = sizeof(debug_entry_t) + (_buf_size), \
+ .areas = VNAME(var, areas), \
+ .active_area = 0, \
+ .active_pages = VNAME(var, active_pages), \
+ .active_entries = VNAME(var, active_entries), \
+ .debugfs_root_entry = NULL, \
+ .debugfs_entries = { NULL }, \
+ .views = { NULL }, \
+ .name = (_name), \
+ .mode = 0600, \
+}
+
+#define __REGISTER_STATIC_DEBUG_INFO(var, name, pages, areas, view) \
+static int __init VNAME(var, reg)(void) \
+{ \
+ debug_register_static(&var, (pages), (areas)); \
+ debug_register_view(&var, (view)); \
+ return 0; \
+} \
+arch_initcall(VNAME(var, reg))
+
+/**
+ * DEFINE_STATIC_DEBUG_INFO - Define static debug_info_t
+ *
+ * @var: Name of debug_info_t variable
+ * @name: Name of debug log (e.g. used for debugfs entry)
+ * @pages_per_area: Number of pages per area
+ * @nr_areas: Number of debug areas
+ * @buf_size: Size of data area in each debug entry
+ * @view: Pointer to debug view struct
+ *
+ * Define a static debug_info_t for early tracing. The associated debugfs log
+ * is automatically registered with the specified debug view.
+ *
+ * Important: Users of this macro must not call any of the
+ * debug_register/_unregister() functions for this debug_info_t!
+ *
+ * Note: Tracing will start with a fixed number of initial pages and areas.
+ * The debug area will be changed to use the specified numbers during
+ * arch_initcall.
+ */
+#define DEFINE_STATIC_DEBUG_INFO(var, name, pages, nr_areas, buf_size, view) \
+__DEFINE_STATIC_AREA(var); \
+static debug_info_t __refdata var = \
+ __DEBUG_INFO_INIT(var, (name), (buf_size)); \
+__REGISTER_STATIC_DEBUG_INFO(var, name, pages, nr_areas, view)
+
+void debug_register_static(debug_info_t *id, int pages_per_area, int nr_areas);
-#ifndef DEBUG_LEVEL
-#define DEBUG_LEVEL 4
-#endif
-
-#define INTERNAL_ERRMSG(x,y...) "E" __FILE__ "%d: " x, __LINE__, y
-#define INTERNAL_WRNMSG(x,y...) "W" __FILE__ "%d: " x, __LINE__, y
-#define INTERNAL_INFMSG(x,y...) "I" __FILE__ "%d: " x, __LINE__, y
-#define INTERNAL_DEBMSG(x,y...) "D" __FILE__ "%d: " x, __LINE__, y
-
-#if DEBUG_LEVEL > 0
-#define PRINT_DEBUG(x...) printk(KERN_DEBUG PRINTK_HEADER x)
-#define PRINT_INFO(x...) printk(KERN_INFO PRINTK_HEADER x)
-#define PRINT_WARN(x...) printk(KERN_WARNING PRINTK_HEADER x)
-#define PRINT_ERR(x...) printk(KERN_ERR PRINTK_HEADER x)
-#define PRINT_FATAL(x...) panic(PRINTK_HEADER x)
-#else
-#define PRINT_DEBUG(x...) printk(KERN_DEBUG PRINTK_HEADER x)
-#define PRINT_INFO(x...) printk(KERN_DEBUG PRINTK_HEADER x)
-#define PRINT_WARN(x...) printk(KERN_DEBUG PRINTK_HEADER x)
-#define PRINT_ERR(x...) printk(KERN_DEBUG PRINTK_HEADER x)
-#define PRINT_FATAL(x...) printk(KERN_DEBUG PRINTK_HEADER x)
-#endif /* DASD_DEBUG */
+#endif /* MODULE */
#endif /* DEBUG_H */
diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h
index ca8f85b53a90..b3a8cb4daed6 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -309,6 +309,10 @@ int diag26c(void *req, void *resp, enum diag26c_sc subcode);
struct hypfs_diag0c_entry;
+/*
+ * This structure must contain only pointers/references into
+ * the AMODE31 text section.
+ */
struct diag_ops {
int (*diag210)(struct diag210 *addr);
int (*diag26c)(void *req, void *resp, enum diag26c_sc subcode);
@@ -317,6 +321,13 @@ struct diag_ops {
void (*diag308_reset)(void);
};
-extern struct diag_ops diag_dma_ops;
-extern struct diag210 *__diag210_tmp_dma;
+extern struct diag_ops diag_amode31_ops;
+extern struct diag210 *__diag210_tmp_amode31;
+
+int _diag210_amode31(struct diag210 *addr);
+int _diag26c_amode31(void *req, void *resp, enum diag26c_sc subcode);
+int _diag14_amode31(unsigned long rx, unsigned long ry1, unsigned long subcode);
+void _diag0c_amode31(struct hypfs_diag0c_entry *entry);
+void _diag308_reset_amode31(void);
+
#endif /* _ASM_S390_DIAG_H */
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index bd00c94620d3..70a30ae258b7 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -91,29 +91,57 @@
/* Keep this the last entry. */
#define R_390_NUM 61
-/* Bits present in AT_HWCAP. */
-#define HWCAP_S390_ESAN3 1
-#define HWCAP_S390_ZARCH 2
-#define HWCAP_S390_STFLE 4
-#define HWCAP_S390_MSA 8
-#define HWCAP_S390_LDISP 16
-#define HWCAP_S390_EIMM 32
-#define HWCAP_S390_DFP 64
-#define HWCAP_S390_HPAGE 128
-#define HWCAP_S390_ETF3EH 256
-#define HWCAP_S390_HIGH_GPRS 512
-#define HWCAP_S390_TE 1024
-#define HWCAP_S390_VXRS 2048
-#define HWCAP_S390_VXRS_BCD 4096
-#define HWCAP_S390_VXRS_EXT 8192
-#define HWCAP_S390_GS 16384
-#define HWCAP_S390_VXRS_EXT2 32768
-#define HWCAP_S390_VXRS_PDE 65536
-#define HWCAP_S390_SORT 131072
-#define HWCAP_S390_DFLT 262144
+enum {
+ HWCAP_NR_ESAN3 = 0,
+ HWCAP_NR_ZARCH = 1,
+ HWCAP_NR_STFLE = 2,
+ HWCAP_NR_MSA = 3,
+ HWCAP_NR_LDISP = 4,
+ HWCAP_NR_EIMM = 5,
+ HWCAP_NR_DFP = 6,
+ HWCAP_NR_HPAGE = 7,
+ HWCAP_NR_ETF3EH = 8,
+ HWCAP_NR_HIGH_GPRS = 9,
+ HWCAP_NR_TE = 10,
+ HWCAP_NR_VXRS = 11,
+ HWCAP_NR_VXRS_BCD = 12,
+ HWCAP_NR_VXRS_EXT = 13,
+ HWCAP_NR_GS = 14,
+ HWCAP_NR_VXRS_EXT2 = 15,
+ HWCAP_NR_VXRS_PDE = 16,
+ HWCAP_NR_SORT = 17,
+ HWCAP_NR_DFLT = 18,
+ HWCAP_NR_VXRS_PDE2 = 19,
+ HWCAP_NR_NNPA = 20,
+ HWCAP_NR_PCI_MIO = 21,
+ HWCAP_NR_SIE = 22,
+ HWCAP_NR_MAX
+};
-/* Internal bits, not exposed via elf */
-#define HWCAP_INT_SIE 1UL
+/* Bits present in AT_HWCAP. */
+#define HWCAP_ESAN3 BIT(HWCAP_NR_ESAN3)
+#define HWCAP_ZARCH BIT(HWCAP_NR_ZARCH)
+#define HWCAP_STFLE BIT(HWCAP_NR_STFLE)
+#define HWCAP_MSA BIT(HWCAP_NR_MSA)
+#define HWCAP_LDISP BIT(HWCAP_NR_LDISP)
+#define HWCAP_EIMM BIT(HWCAP_NR_EIMM)
+#define HWCAP_DFP BIT(HWCAP_NR_DFP)
+#define HWCAP_HPAGE BIT(HWCAP_NR_HPAGE)
+#define HWCAP_ETF3EH BIT(HWCAP_NR_ETF3EH)
+#define HWCAP_HIGH_GPRS BIT(HWCAP_NR_HIGH_GPRS)
+#define HWCAP_TE BIT(HWCAP_NR_TE)
+#define HWCAP_VXRS BIT(HWCAP_NR_VXRS)
+#define HWCAP_VXRS_BCD BIT(HWCAP_NR_VXRS_BCD)
+#define HWCAP_VXRS_EXT BIT(HWCAP_NR_VXRS_EXT)
+#define HWCAP_GS BIT(HWCAP_NR_GS)
+#define HWCAP_VXRS_EXT2 BIT(HWCAP_NR_VXRS_EXT2)
+#define HWCAP_VXRS_PDE BIT(HWCAP_NR_VXRS_PDE)
+#define HWCAP_SORT BIT(HWCAP_NR_SORT)
+#define HWCAP_DFLT BIT(HWCAP_NR_DFLT)
+#define HWCAP_VXRS_PDE2 BIT(HWCAP_NR_VXRS_PDE2)
+#define HWCAP_NNPA BIT(HWCAP_NR_NNPA)
+#define HWCAP_PCI_MIO BIT(HWCAP_NR_PCI_MIO)
+#define HWCAP_SIE BIT(HWCAP_NR_SIE)
/*
* These are used to set parameters in the core dumps.
@@ -209,10 +237,6 @@ struct arch_elf_state {
extern unsigned long elf_hwcap;
#define ELF_HWCAP (elf_hwcap)
-/* Internal hardware capabilities, not exposed via elf */
-
-extern unsigned long int_hwcap;
-
/* This yields a string that ld.so will use to load implementation
specific libraries for optimization. This is more specific in
intent than poking at uname or /proc/cpuinfo.
diff --git a/arch/s390/include/asm/extable.h b/arch/s390/include/asm/extable.h
index 3beb294fd553..16dc57dd90b3 100644
--- a/arch/s390/include/asm/extable.h
+++ b/arch/s390/include/asm/extable.h
@@ -28,8 +28,8 @@ struct exception_table_entry
long handler;
};
-extern struct exception_table_entry *__start_dma_ex_table;
-extern struct exception_table_entry *__stop_dma_ex_table;
+extern struct exception_table_entry *__start_amode31_ex_table;
+extern struct exception_table_entry *__stop_amode31_ex_table;
const struct exception_table_entry *s390_search_extables(unsigned long addr);
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 345cbe982a8b..e8b460f39c58 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -18,7 +18,6 @@
void ftrace_caller(void);
extern char ftrace_graph_caller_end;
-extern unsigned long ftrace_plt;
extern void *ftrace_func;
struct dyn_arch_ftrace { };
@@ -31,10 +30,11 @@ struct dyn_arch_ftrace { };
struct module;
struct dyn_ftrace;
-/*
- * Either -mhotpatch or -mnop-mcount is used - no explicit init is required
- */
-static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) { return 0; }
+
+bool ftrace_need_init_nop(void);
+#define ftrace_need_init_nop ftrace_need_init_nop
+
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
#define ftrace_init_nop ftrace_init_nop
static inline unsigned long ftrace_call_adjust(unsigned long addr)
@@ -42,42 +42,6 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
return addr;
}
-struct ftrace_insn {
- u16 opc;
- s32 disp;
-} __packed;
-
-static inline void ftrace_generate_nop_insn(struct ftrace_insn *insn)
-{
-#ifdef CONFIG_FUNCTION_TRACER
- /* brcl 0,0 */
- insn->opc = 0xc004;
- insn->disp = 0;
-#endif
-}
-
-static inline int is_ftrace_nop(struct ftrace_insn *insn)
-{
-#ifdef CONFIG_FUNCTION_TRACER
- if (insn->disp == 0)
- return 1;
-#endif
- return 0;
-}
-
-static inline void ftrace_generate_call_insn(struct ftrace_insn *insn,
- unsigned long ip)
-{
-#ifdef CONFIG_FUNCTION_TRACER
- unsigned long target;
-
- /* brasl r0,ftrace_caller */
- target = is_module_addr((void *) ip) ? ftrace_plt : FTRACE_ADDR;
- insn->opc = 0xc005;
- insn->disp = (target - ip) / 2;
-#endif
-}
-
/*
* Even though the system call numbers are identical for s390/s390x a
* different system call table is used for compat tasks. This may lead
diff --git a/arch/s390/include/asm/ftrace.lds.h b/arch/s390/include/asm/ftrace.lds.h
new file mode 100644
index 000000000000..968adfd41240
--- /dev/null
+++ b/arch/s390/include/asm/ftrace.lds.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef DIV_ROUND_UP
+#define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
+#endif
+
+#define SIZEOF_MCOUNT_LOC_ENTRY 8
+#define SIZEOF_FTRACE_HOTPATCH_TRAMPOLINE 24
+#define FTRACE_HOTPATCH_TRAMPOLINES_SIZE(n) \
+ DIV_ROUND_UP(SIZEOF_FTRACE_HOTPATCH_TRAMPOLINE * (n), \
+ SIZEOF_MCOUNT_LOC_ENTRY)
+
+#ifdef CONFIG_FUNCTION_TRACER
+#define FTRACE_HOTPATCH_TRAMPOLINES_TEXT \
+ . = ALIGN(8); \
+ __ftrace_hotpatch_trampolines_start = .; \
+ . = . + FTRACE_HOTPATCH_TRAMPOLINES_SIZE(__stop_mcount_loc - \
+ __start_mcount_loc); \
+ __ftrace_hotpatch_trampolines_end = .;
+#else
+#define FTRACE_HOTPATCH_TRAMPOLINES_TEXT
+#endif
diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h
index a9e2c7295b35..3f8ee257f9aa 100644
--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@@ -12,6 +12,7 @@
#include <asm/types.h>
#include <asm/cio.h>
#include <asm/setup.h>
+#include <asm/page.h>
#include <uapi/asm/ipl.h>
struct ipl_parameter_block {
diff --git a/arch/s390/include/asm/kfence.h b/arch/s390/include/asm/kfence.h
new file mode 100644
index 000000000000..d55ba878378b
--- /dev/null
+++ b/arch/s390/include/asm/kfence.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_S390_KFENCE_H
+#define _ASM_S390_KFENCE_H
+
+#include <linux/mm.h>
+#include <linux/kfence.h>
+#include <asm/set_memory.h>
+#include <asm/page.h>
+
+void __kernel_map_pages(struct page *page, int numpages, int enable);
+
+static __always_inline bool arch_kfence_init_pool(void)
+{
+ return true;
+}
+
+#define arch_kfence_test_address(addr) ((addr) & PAGE_MASK)
+
+/*
+ * Do not split kfence pool to 4k mapping with arch_kfence_init_pool(),
+ * but earlier where page table allocations still happen with memblock.
+ * Reason is that arch_kfence_init_pool() gets called when the system
+ * is still in a limbo state - disabling and enabling bottom halves is
+ * not yet allowed, but that is what our page_table_alloc() would do.
+ */
+static __always_inline void kfence_split_mapping(void)
+{
+#ifdef CONFIG_KFENCE
+ unsigned long pool_pages = KFENCE_POOL_SIZE >> PAGE_SHIFT;
+
+ set_memory_4k((unsigned long)__kfence_pool, pool_pages);
+#endif
+}
+
+static inline bool kfence_protect_page(unsigned long addr, bool protect)
+{
+ __kernel_map_pages(virt_to_page(addr), 1, !protect);
+ return true;
+}
+
+#endif /* _ASM_S390_KFENCE_H */
diff --git a/arch/s390/include/asm/kvm_para.h b/arch/s390/include/asm/kvm_para.h
index cbc7c3a68e4d..df73a052760c 100644
--- a/arch/s390/include/asm/kvm_para.h
+++ b/arch/s390/include/asm/kvm_para.h
@@ -24,162 +24,79 @@
#include <uapi/asm/kvm_para.h>
#include <asm/diag.h>
-static inline long __kvm_hypercall0(unsigned long nr)
-{
- register unsigned long __nr asm("1") = nr;
- register long __rc asm("2");
-
- asm volatile ("diag 2,4,0x500\n"
- : "=d" (__rc) : "d" (__nr): "memory", "cc");
- return __rc;
-}
-
-static inline long kvm_hypercall0(unsigned long nr)
-{
- diag_stat_inc(DIAG_STAT_X500);
- return __kvm_hypercall0(nr);
-}
-
-static inline long __kvm_hypercall1(unsigned long nr, unsigned long p1)
-{
- register unsigned long __nr asm("1") = nr;
- register unsigned long __p1 asm("2") = p1;
- register long __rc asm("2");
-
- asm volatile ("diag 2,4,0x500\n"
- : "=d" (__rc) : "d" (__nr), "0" (__p1) : "memory", "cc");
- return __rc;
-}
-
-static inline long kvm_hypercall1(unsigned long nr, unsigned long p1)
-{
- diag_stat_inc(DIAG_STAT_X500);
- return __kvm_hypercall1(nr, p1);
-}
-
-static inline long __kvm_hypercall2(unsigned long nr, unsigned long p1,
- unsigned long p2)
-{
- register unsigned long __nr asm("1") = nr;
- register unsigned long __p1 asm("2") = p1;
- register unsigned long __p2 asm("3") = p2;
- register long __rc asm("2");
-
- asm volatile ("diag 2,4,0x500\n"
- : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2)
- : "memory", "cc");
- return __rc;
-}
-
-static inline long kvm_hypercall2(unsigned long nr, unsigned long p1,
- unsigned long p2)
-{
- diag_stat_inc(DIAG_STAT_X500);
- return __kvm_hypercall2(nr, p1, p2);
-}
-
-static inline long __kvm_hypercall3(unsigned long nr, unsigned long p1,
- unsigned long p2, unsigned long p3)
-{
- register unsigned long __nr asm("1") = nr;
- register unsigned long __p1 asm("2") = p1;
- register unsigned long __p2 asm("3") = p2;
- register unsigned long __p3 asm("4") = p3;
- register long __rc asm("2");
-
- asm volatile ("diag 2,4,0x500\n"
- : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2),
- "d" (__p3) : "memory", "cc");
- return __rc;
-}
-
-static inline long kvm_hypercall3(unsigned long nr, unsigned long p1,
- unsigned long p2, unsigned long p3)
-{
- diag_stat_inc(DIAG_STAT_X500);
- return __kvm_hypercall3(nr, p1, p2, p3);
-}
-
-static inline long __kvm_hypercall4(unsigned long nr, unsigned long p1,
- unsigned long p2, unsigned long p3,
- unsigned long p4)
-{
- register unsigned long __nr asm("1") = nr;
- register unsigned long __p1 asm("2") = p1;
- register unsigned long __p2 asm("3") = p2;
- register unsigned long __p3 asm("4") = p3;
- register unsigned long __p4 asm("5") = p4;
- register long __rc asm("2");
-
- asm volatile ("diag 2,4,0x500\n"
- : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2),
- "d" (__p3), "d" (__p4) : "memory", "cc");
- return __rc;
-}
-
-static inline long kvm_hypercall4(unsigned long nr, unsigned long p1,
- unsigned long p2, unsigned long p3,
- unsigned long p4)
-{
- diag_stat_inc(DIAG_STAT_X500);
- return __kvm_hypercall4(nr, p1, p2, p3, p4);
-}
-
-static inline long __kvm_hypercall5(unsigned long nr, unsigned long p1,
- unsigned long p2, unsigned long p3,
- unsigned long p4, unsigned long p5)
-{
- register unsigned long __nr asm("1") = nr;
- register unsigned long __p1 asm("2") = p1;
- register unsigned long __p2 asm("3") = p2;
- register unsigned long __p3 asm("4") = p3;
- register unsigned long __p4 asm("5") = p4;
- register unsigned long __p5 asm("6") = p5;
- register long __rc asm("2");
-
- asm volatile ("diag 2,4,0x500\n"
- : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2),
- "d" (__p3), "d" (__p4), "d" (__p5) : "memory", "cc");
- return __rc;
-}
-
-static inline long kvm_hypercall5(unsigned long nr, unsigned long p1,
- unsigned long p2, unsigned long p3,
- unsigned long p4, unsigned long p5)
-{
- diag_stat_inc(DIAG_STAT_X500);
- return __kvm_hypercall5(nr, p1, p2, p3, p4, p5);
-}
-
-static inline long __kvm_hypercall6(unsigned long nr, unsigned long p1,
- unsigned long p2, unsigned long p3,
- unsigned long p4, unsigned long p5,
- unsigned long p6)
-{
- register unsigned long __nr asm("1") = nr;
- register unsigned long __p1 asm("2") = p1;
- register unsigned long __p2 asm("3") = p2;
- register unsigned long __p3 asm("4") = p3;
- register unsigned long __p4 asm("5") = p4;
- register unsigned long __p5 asm("6") = p5;
- register unsigned long __p6 asm("7") = p6;
- register long __rc asm("2");
-
- asm volatile ("diag 2,4,0x500\n"
- : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2),
- "d" (__p3), "d" (__p4), "d" (__p5), "d" (__p6)
- : "memory", "cc");
- return __rc;
-}
-
-static inline long kvm_hypercall6(unsigned long nr, unsigned long p1,
- unsigned long p2, unsigned long p3,
- unsigned long p4, unsigned long p5,
- unsigned long p6)
-{
- diag_stat_inc(DIAG_STAT_X500);
- return __kvm_hypercall6(nr, p1, p2, p3, p4, p5, p6);
-}
+#define HYPERCALL_FMT_0
+#define HYPERCALL_FMT_1 , "0" (r2)
+#define HYPERCALL_FMT_2 , "d" (r3) HYPERCALL_FMT_1
+#define HYPERCALL_FMT_3 , "d" (r4) HYPERCALL_FMT_2
+#define HYPERCALL_FMT_4 , "d" (r5) HYPERCALL_FMT_3
+#define HYPERCALL_FMT_5 , "d" (r6) HYPERCALL_FMT_4
+#define HYPERCALL_FMT_6 , "d" (r7) HYPERCALL_FMT_5
+
+#define HYPERCALL_PARM_0
+#define HYPERCALL_PARM_1 , unsigned long arg1
+#define HYPERCALL_PARM_2 HYPERCALL_PARM_1, unsigned long arg2
+#define HYPERCALL_PARM_3 HYPERCALL_PARM_2, unsigned long arg3
+#define HYPERCALL_PARM_4 HYPERCALL_PARM_3, unsigned long arg4
+#define HYPERCALL_PARM_5 HYPERCALL_PARM_4, unsigned long arg5
+#define HYPERCALL_PARM_6 HYPERCALL_PARM_5, unsigned long arg6
+
+#define HYPERCALL_REGS_0
+#define HYPERCALL_REGS_1 \
+ register unsigned long r2 asm("2") = arg1
+#define HYPERCALL_REGS_2 \
+ HYPERCALL_REGS_1; \
+ register unsigned long r3 asm("3") = arg2
+#define HYPERCALL_REGS_3 \
+ HYPERCALL_REGS_2; \
+ register unsigned long r4 asm("4") = arg3
+#define HYPERCALL_REGS_4 \
+ HYPERCALL_REGS_3; \
+ register unsigned long r5 asm("5") = arg4
+#define HYPERCALL_REGS_5 \
+ HYPERCALL_REGS_4; \
+ register unsigned long r6 asm("6") = arg5
+#define HYPERCALL_REGS_6 \
+ HYPERCALL_REGS_5; \
+ register unsigned long r7 asm("7") = arg6
+
+#define HYPERCALL_ARGS_0
+#define HYPERCALL_ARGS_1 , arg1
+#define HYPERCALL_ARGS_2 HYPERCALL_ARGS_1, arg2
+#define HYPERCALL_ARGS_3 HYPERCALL_ARGS_2, arg3
+#define HYPERCALL_ARGS_4 HYPERCALL_ARGS_3, arg4
+#define HYPERCALL_ARGS_5 HYPERCALL_ARGS_4, arg5
+#define HYPERCALL_ARGS_6 HYPERCALL_ARGS_5, arg6
+
+#define GENERATE_KVM_HYPERCALL_FUNC(args) \
+static inline \
+long __kvm_hypercall##args(unsigned long nr HYPERCALL_PARM_##args) \
+{ \
+ register unsigned long __nr asm("1") = nr; \
+ register long __rc asm("2"); \
+ HYPERCALL_REGS_##args; \
+ \
+ asm volatile ( \
+ " diag 2,4,0x500\n" \
+ : "=d" (__rc) \
+ : "d" (__nr) HYPERCALL_FMT_##args \
+ : "memory", "cc"); \
+ return __rc; \
+} \
+ \
+static inline \
+long kvm_hypercall##args(unsigned long nr HYPERCALL_PARM_##args) \
+{ \
+ diag_stat_inc(DIAG_STAT_X500); \
+ return __kvm_hypercall##args(nr HYPERCALL_ARGS_##args); \
+}
+
+GENERATE_KVM_HYPERCALL_FUNC(0)
+GENERATE_KVM_HYPERCALL_FUNC(1)
+GENERATE_KVM_HYPERCALL_FUNC(2)
+GENERATE_KVM_HYPERCALL_FUNC(3)
+GENERATE_KVM_HYPERCALL_FUNC(4)
+GENERATE_KVM_HYPERCALL_FUNC(5)
+GENERATE_KVM_HYPERCALL_FUNC(6)
/* kvm on s390 is always paravirtualization enabled */
static inline int kvm_para_available(void)
diff --git a/arch/s390/include/asm/linkage.h b/arch/s390/include/asm/linkage.h
index 24e8fed150cf..1ffea75b8ebc 100644
--- a/arch/s390/include/asm/linkage.h
+++ b/arch/s390/include/asm/linkage.h
@@ -22,7 +22,7 @@
#define EX_TABLE(_fault, _target) \
__EX_TABLE(__ex_table, _fault, _target)
-#define EX_TABLE_DMA(_fault, _target) \
- __EX_TABLE(.dma.ex_table, _fault, _target)
+#define EX_TABLE_AMODE31(_fault, _target) \
+ __EX_TABLE(.amode31.ex_table, _fault, _target)
#endif
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 47bde5a20a41..11213c8bfca5 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -124,7 +124,8 @@ struct lowcore {
/* Restart function and parameter. */
__u64 restart_fn; /* 0x0370 */
__u64 restart_data; /* 0x0378 */
- __u64 restart_source; /* 0x0380 */
+ __u32 restart_source; /* 0x0380 */
+ __u32 restart_flags; /* 0x0384 */
/* Address space pointer. */
__u64 kernel_asce; /* 0x0388 */
diff --git a/arch/s390/include/asm/module.h b/arch/s390/include/asm/module.h
index e0a6d29846e2..9f1eea15872c 100644
--- a/arch/s390/include/asm/module.h
+++ b/arch/s390/include/asm/module.h
@@ -8,16 +8,14 @@
* This file contains the s390 architecture specific module code.
*/
-struct mod_arch_syminfo
-{
+struct mod_arch_syminfo {
unsigned long got_offset;
unsigned long plt_offset;
int got_initialized;
int plt_initialized;
};
-struct mod_arch_specific
-{
+struct mod_arch_specific {
/* Starting offset of got in the module core memory. */
unsigned long got_offset;
/* Starting offset of plt in the module core memory. */
@@ -30,6 +28,14 @@ struct mod_arch_specific
int nsyms;
/* Additional symbol information (got and plt offsets). */
struct mod_arch_syminfo *syminfo;
+#ifdef CONFIG_FUNCTION_TRACER
+ /* Start of memory reserved for ftrace hotpatch trampolines. */
+ struct ftrace_hotpatch_trampoline *trampolines_start;
+ /* End of memory reserved for ftrace hotpatch trampolines. */
+ struct ftrace_hotpatch_trampoline *trampolines_end;
+ /* Next unused ftrace hotpatch trampoline slot. */
+ struct ftrace_hotpatch_trampoline *next_trampoline;
+#endif /* CONFIG_FUNCTION_TRACER */
};
#endif /* _ASM_S390_MODULE_H */
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 3ba945c6b9dc..d98d17a36c7b 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -144,9 +144,6 @@ struct page;
void arch_free_page(struct page *page, int order);
void arch_alloc_page(struct page *page, int order);
void arch_set_page_dat(struct page *page, int order);
-void arch_set_page_nodat(struct page *page, int order);
-int arch_test_page_nodat(struct page *page);
-void arch_set_page_states(int make_stable);
static inline int devmem_is_allowed(unsigned long pfn)
{
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 5509b224c2ec..e4803ec51110 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -216,9 +216,10 @@ void zpci_remove_reserved_devices(void);
int clp_setup_writeback_mio(void);
int clp_scan_pci_devices(void);
int clp_query_pci_fn(struct zpci_dev *zdev);
-int clp_enable_fh(struct zpci_dev *, u8);
-int clp_disable_fh(struct zpci_dev *);
+int clp_enable_fh(struct zpci_dev *zdev, u32 *fh, u8 nr_dma_as);
+int clp_disable_fh(struct zpci_dev *zdev, u32 *fh);
int clp_get_state(u32 fid, enum zpci_state *state);
+int clp_refresh_fh(u32 fid, u32 *fh);
/* UID */
void update_uid_checking(bool new);
@@ -271,6 +272,8 @@ struct zpci_dev *get_zdev_by_fid(u32);
/* DMA */
int zpci_dma_init(void);
void zpci_dma_exit(void);
+int zpci_dma_init_device(struct zpci_dev *zdev);
+int zpci_dma_exit_device(struct zpci_dev *zdev);
/* IRQ */
int __init zpci_irq_init(void);
diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h
index f62cd3ed2d44..3b8e89d4578a 100644
--- a/arch/s390/include/asm/pci_dma.h
+++ b/arch/s390/include/asm/pci_dma.h
@@ -182,8 +182,6 @@ static inline unsigned long *get_st_pto(unsigned long entry)
}
/* Prototypes */
-int zpci_dma_init_device(struct zpci_dev *);
-void zpci_dma_exit_device(struct zpci_dev *);
void dma_free_seg_table(unsigned long);
unsigned long *dma_alloc_cpu_table(void);
void dma_cleanup_tables(unsigned long *);
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index dcac7b2df72c..b61426c9ef17 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -67,15 +67,15 @@ extern unsigned long zero_page_mask;
/* TODO: s390 cannot support io_remap_pfn_range... */
#define pte_ERROR(e) \
- printk("%s:%d: bad pte %p.\n", __FILE__, __LINE__, (void *) pte_val(e))
+ pr_err("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e))
#define pmd_ERROR(e) \
- printk("%s:%d: bad pmd %p.\n", __FILE__, __LINE__, (void *) pmd_val(e))
+ pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
#define pud_ERROR(e) \
- printk("%s:%d: bad pud %p.\n", __FILE__, __LINE__, (void *) pud_val(e))
+ pr_err("%s:%d: bad pud %016lx.\n", __FILE__, __LINE__, pud_val(e))
#define p4d_ERROR(e) \
- printk("%s:%d: bad p4d %p.\n", __FILE__, __LINE__, (void *) p4d_val(e))
+ pr_err("%s:%d: bad p4d %016lx.\n", __FILE__, __LINE__, p4d_val(e))
#define pgd_ERROR(e) \
- printk("%s:%d: bad pgd %p.\n", __FILE__, __LINE__, (void *) pgd_val(e))
+ pr_err("%s:%d: bad pgd %016lx.\n", __FILE__, __LINE__, pgd_val(e))
/*
* The vmalloc and module area will always be on the topmost area of the
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index ddc7858bbce4..879b8e3f609c 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -26,6 +26,8 @@
#define _CIF_MCCK_GUEST BIT(CIF_MCCK_GUEST)
#define _CIF_DEDICATED_CPU BIT(CIF_DEDICATED_CPU)
+#define RESTART_FLAG_CTLREGS _AC(1 << 0, U)
+
#ifndef __ASSEMBLY__
#include <linux/cpumask.h>
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index cb4f73c7228d..25b5dc34db75 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -291,16 +291,15 @@ struct qdio_ssqd_desc {
typedef void qdio_handler_t(struct ccw_device *, unsigned int, int,
int, int, unsigned long);
-/* qdio errors reported to the upper-layer program */
+/* qdio errors reported through the queue handlers: */
#define QDIO_ERROR_ACTIVATE 0x0001
#define QDIO_ERROR_GET_BUF_STATE 0x0002
#define QDIO_ERROR_SET_BUF_STATE 0x0004
+
+/* extra info for completed SBALs: */
#define QDIO_ERROR_SLSB_STATE 0x0100
#define QDIO_ERROR_SLSB_PENDING 0x0200
-#define QDIO_ERROR_FATAL 0x00ff
-#define QDIO_ERROR_TEMPORARY 0xff00
-
/* for qdio_cleanup */
#define QDIO_FLAG_CLEANUP_USING_CLEAR 0x01
#define QDIO_FLAG_CLEANUP_USING_HALT 0x02
@@ -312,8 +311,6 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int,
* @qib_param_field_format: format for qib_parm_field
* @qib_param_field: pointer to 128 bytes or NULL, if no param field
* @qib_rflags: rflags to set
- * @input_slib_elements: pointer to no_input_qs * 128 words of data or NULL
- * @output_slib_elements: pointer to no_output_qs * 128 words of data or NULL
* @no_input_qs: number of input queues
* @no_output_qs: number of output queues
* @input_handler: handler to be called for input queues
@@ -330,27 +327,18 @@ struct qdio_initialize {
unsigned int qib_param_field_format;
unsigned char *qib_param_field;
unsigned char qib_rflags;
- unsigned long *input_slib_elements;
- unsigned long *output_slib_elements;
unsigned int no_input_qs;
unsigned int no_output_qs;
qdio_handler_t *input_handler;
qdio_handler_t *output_handler;
void (*irq_poll)(struct ccw_device *cdev, unsigned long data);
- unsigned int scan_threshold;
unsigned long int_parm;
struct qdio_buffer ***input_sbal_addr_array;
struct qdio_buffer ***output_sbal_addr_array;
};
-#define QDIO_STATE_INACTIVE 0x00000002 /* after qdio_cleanup */
-#define QDIO_STATE_ESTABLISHED 0x00000004 /* after qdio_establish */
-#define QDIO_STATE_ACTIVE 0x00000008 /* after qdio_activate */
-#define QDIO_STATE_STOPPED 0x00000010 /* after queues went down */
-
#define QDIO_FLAG_SYNC_INPUT 0x01
#define QDIO_FLAG_SYNC_OUTPUT 0x02
-#define QDIO_FLAG_PCI_OUT 0x10
int qdio_alloc_buffers(struct qdio_buffer **buf, unsigned int count);
void qdio_free_buffers(struct qdio_buffer **buf, unsigned int count);
@@ -367,7 +355,6 @@ extern int do_QDIO(struct ccw_device *cdev, unsigned int callflags, int q_nr,
unsigned int bufnr, unsigned int count, struct qaob *aob);
extern int qdio_start_irq(struct ccw_device *cdev);
extern int qdio_stop_irq(struct ccw_device *cdev);
-extern int qdio_get_next_buffers(struct ccw_device *, int, int *, int *);
extern int qdio_inspect_queue(struct ccw_device *cdev, unsigned int nr,
bool is_input, unsigned int *bufnr,
unsigned int *error);
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 5763769a39b6..e3ae937bef1c 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -8,8 +8,6 @@
#define _ASM_S390_SCLP_H
#include <linux/types.h>
-#include <asm/chpid.h>
-#include <asm/cpu.h>
#define SCLP_CHP_INFO_MASK_SIZE 32
#define EARLY_SCCB_SIZE PAGE_SIZE
@@ -19,6 +17,10 @@
/* 24 + 16 * SCLP_MAX_CORES */
#define EXT_SCCB_READ_CPU (3 * PAGE_SIZE)
+#ifndef __ASSEMBLY__
+#include <asm/chpid.h>
+#include <asm/cpu.h>
+
struct sclp_chp_info {
u8 recognized[SCLP_CHP_INFO_MASK_SIZE];
u8 standby[SCLP_CHP_INFO_MASK_SIZE];
@@ -113,6 +115,9 @@ struct zpci_report_error_header {
u8 data[0]; /* Subsequent Data passed verbatim to SCLP ET 24 */
} __packed;
+extern char *sclp_early_sccb;
+
+void sclp_early_set_buffer(void *sccb);
int sclp_early_read_info(void);
int sclp_early_read_storage_info(void);
int sclp_early_get_core_info(struct sclp_core_info *info);
@@ -147,4 +152,5 @@ static inline int sclp_get_core_info(struct sclp_core_info *info, int early)
return _sclp_get_core_info(info);
}
+#endif /* __ASSEMBLY__ */
#endif /* _ASM_S390_SCLP_H */
diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h
index 0c2151451ba5..85881dd48022 100644
--- a/arch/s390/include/asm/sections.h
+++ b/arch/s390/include/asm/sections.h
@@ -35,7 +35,7 @@ static inline int arch_is_kernel_initmem_freed(unsigned long addr)
*/
#define __bootdata_preserved(var) __section(".boot.preserved.data." #var) var
-extern unsigned long __sdma, __edma;
-extern unsigned long __stext_dma, __etext_dma;
+extern unsigned long __samode31, __eamode31;
+extern unsigned long __stext_amode31, __etext_amode31;
#endif
diff --git a/arch/s390/include/asm/set_memory.h b/arch/s390/include/asm/set_memory.h
index a22a5a81811c..950d87bd997a 100644
--- a/arch/s390/include/asm/set_memory.h
+++ b/arch/s390/include/asm/set_memory.h
@@ -10,6 +10,7 @@ extern struct mutex cpa_mutex;
#define SET_MEMORY_RW 2UL
#define SET_MEMORY_NX 4UL
#define SET_MEMORY_X 8UL
+#define SET_MEMORY_4K 16UL
int __set_memory(unsigned long addr, int numpages, unsigned long flags);
@@ -33,4 +34,9 @@ static inline int set_memory_x(unsigned long addr, int numpages)
return __set_memory(addr, numpages, SET_MEMORY_X);
}
+static inline int set_memory_4k(unsigned long addr, int numpages)
+{
+ return __set_memory(addr, numpages, SET_MEMORY_4K);
+}
+
#endif
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 3a77aa96d092..b6606ffd85d8 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -10,11 +10,8 @@
#include <uapi/asm/setup.h>
#include <linux/build_bug.h>
-#define EP_OFFSET 0x10008
-#define EP_STRING "S390EP"
#define PARMAREA 0x10400
-#define EARLY_SCCB_OFFSET 0x11000
-#define HEAD_END 0x12000
+#define HEAD_END 0x11000
/*
* Machine features detected in early.c
@@ -36,6 +33,7 @@
#define MACHINE_FLAG_NX BIT(15)
#define MACHINE_FLAG_GS BIT(16)
#define MACHINE_FLAG_SCC BIT(17)
+#define MACHINE_FLAG_PCI_MIO BIT(18)
#define LPP_MAGIC BIT(31)
#define LPP_PID_MASK _AC(0xffffffff, UL)
@@ -45,28 +43,11 @@
#define STARTUP_NORMAL_OFFSET 0x10000
#define STARTUP_KDUMP_OFFSET 0x10010
-/* Offsets to parameters in kernel/head.S */
-
-#define IPL_DEVICE_OFFSET 0x10400
-#define INITRD_START_OFFSET 0x10408
-#define INITRD_SIZE_OFFSET 0x10410
-#define OLDMEM_BASE_OFFSET 0x10418
-#define OLDMEM_SIZE_OFFSET 0x10420
-#define KERNEL_VERSION_OFFSET 0x10428
-#define COMMAND_LINE_OFFSET 0x10480
-
#ifndef __ASSEMBLY__
#include <asm/lowcore.h>
#include <asm/types.h>
-#define IPL_DEVICE (*(unsigned long *) (IPL_DEVICE_OFFSET))
-#define INITRD_START (*(unsigned long *) (INITRD_START_OFFSET))
-#define INITRD_SIZE (*(unsigned long *) (INITRD_SIZE_OFFSET))
-#define OLDMEM_BASE (*(unsigned long *) (OLDMEM_BASE_OFFSET))
-#define OLDMEM_SIZE (*(unsigned long *) (OLDMEM_SIZE_OFFSET))
-#define COMMAND_LINE ((char *) (COMMAND_LINE_OFFSET))
-
struct parmarea {
unsigned long ipl_device; /* 0x10400 */
unsigned long initrd_start; /* 0x10408 */
@@ -110,6 +91,7 @@ extern unsigned long mio_wb_bit_mask;
#define MACHINE_HAS_NX (S390_lowcore.machine_flags & MACHINE_FLAG_NX)
#define MACHINE_HAS_GS (S390_lowcore.machine_flags & MACHINE_FLAG_GS)
#define MACHINE_HAS_SCC (S390_lowcore.machine_flags & MACHINE_FLAG_SCC)
+#define MACHINE_HAS_PCI_MIO (S390_lowcore.machine_flags & MACHINE_FLAG_PCI_MIO)
/*
* Console mode. Override with conmode=
@@ -161,20 +143,22 @@ static inline unsigned long kaslr_offset(void)
extern int is_full_image;
+struct initrd_data {
+ unsigned long start;
+ unsigned long size;
+};
+extern struct initrd_data initrd_data;
+
+struct oldmem_data {
+ unsigned long start;
+ unsigned long size;
+};
+extern struct oldmem_data oldmem_data;
+
static inline u32 gen_lpswe(unsigned long addr)
{
BUILD_BUG_ON(addr > 0xfff);
return 0xb2b20000 | addr;
}
-
-#else /* __ASSEMBLY__ */
-
-#define IPL_DEVICE (IPL_DEVICE_OFFSET)
-#define INITRD_START (INITRD_START_OFFSET)
-#define INITRD_SIZE (INITRD_SIZE_OFFSET)
-#define OLDMEM_BASE (OLDMEM_BASE_OFFSET)
-#define OLDMEM_SIZE (OLDMEM_SIZE_OFFSET)
-#define COMMAND_LINE (COMMAND_LINE_OFFSET)
-
#endif /* __ASSEMBLY__ */
#endif /* _ASM_S390_SETUP_H */
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 9107e3dab68c..b3dd883699e7 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -104,4 +104,63 @@ static inline bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
return false;
}
+#define SYSCALL_FMT_0
+#define SYSCALL_FMT_1 , "0" (r2)
+#define SYSCALL_FMT_2 , "d" (r3) SYSCALL_FMT_1
+#define SYSCALL_FMT_3 , "d" (r4) SYSCALL_FMT_2
+#define SYSCALL_FMT_4 , "d" (r5) SYSCALL_FMT_3
+#define SYSCALL_FMT_5 , "d" (r6) SYSCALL_FMT_4
+#define SYSCALL_FMT_6 , "d" (r7) SYSCALL_FMT_5
+
+#define SYSCALL_PARM_0
+#define SYSCALL_PARM_1 , long arg1
+#define SYSCALL_PARM_2 SYSCALL_PARM_1, long arg2
+#define SYSCALL_PARM_3 SYSCALL_PARM_2, long arg3
+#define SYSCALL_PARM_4 SYSCALL_PARM_3, long arg4
+#define SYSCALL_PARM_5 SYSCALL_PARM_4, long arg5
+#define SYSCALL_PARM_6 SYSCALL_PARM_5, long arg6
+
+#define SYSCALL_REGS_0
+#define SYSCALL_REGS_1 \
+ register long r2 asm("2") = arg1
+#define SYSCALL_REGS_2 \
+ SYSCALL_REGS_1; \
+ register long r3 asm("3") = arg2
+#define SYSCALL_REGS_3 \
+ SYSCALL_REGS_2; \
+ register long r4 asm("4") = arg3
+#define SYSCALL_REGS_4 \
+ SYSCALL_REGS_3; \
+ register long r5 asm("5") = arg4
+#define SYSCALL_REGS_5 \
+ SYSCALL_REGS_4; \
+ register long r6 asm("6") = arg5
+#define SYSCALL_REGS_6 \
+ SYSCALL_REGS_5; \
+ register long r7 asm("7") = arg6
+
+#define GENERATE_SYSCALL_FUNC(nr) \
+static __always_inline \
+long syscall##nr(unsigned long syscall SYSCALL_PARM_##nr) \
+{ \
+ register unsigned long r1 asm ("1") = syscall; \
+ register long rc asm ("2"); \
+ SYSCALL_REGS_##nr; \
+ \
+ asm volatile ( \
+ " svc 0\n" \
+ : "=d" (rc) \
+ : "d" (r1) SYSCALL_FMT_##nr \
+ : "memory"); \
+ return rc; \
+}
+
+GENERATE_SYSCALL_FUNC(0)
+GENERATE_SYSCALL_FUNC(1)
+GENERATE_SYSCALL_FUNC(2)
+GENERATE_SYSCALL_FUNC(3)
+GENERATE_SYSCALL_FUNC(4)
+GENERATE_SYSCALL_FUNC(5)
+GENERATE_SYSCALL_FUNC(6)
+
#endif /* _ASM_SYSCALL_H */
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index 12c5f006c136..fe92a4caf5ec 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -356,11 +356,9 @@ int uv_convert_from_secure(unsigned long paddr);
int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr);
void setup_uv(void);
-void adjust_to_uv_max(unsigned long *vmax);
#else
#define is_prot_virt_host() 0
static inline void setup_uv(void) {}
-static inline void adjust_to_uv_max(unsigned long *vmax) {}
static inline int uv_destroy_page(unsigned long paddr)
{
@@ -373,10 +371,4 @@ static inline int uv_convert_from_secure(unsigned long paddr)
}
#endif
-#if defined(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) || IS_ENABLED(CONFIG_KVM)
-void uv_query_info(void);
-#else
-static inline void uv_query_info(void) {}
-#endif
-
#endif /* _ASM_S390_UV_H */
diff --git a/arch/s390/include/asm/vdso/gettimeofday.h b/arch/s390/include/asm/vdso/gettimeofday.h
index d6465b22ffe3..db84942eb78f 100644
--- a/arch/s390/include/asm/vdso/gettimeofday.h
+++ b/arch/s390/include/asm/vdso/gettimeofday.h
@@ -6,6 +6,7 @@
#define VDSO_HAS_CLOCK_GETRES 1
+#include <asm/syscall.h>
#include <asm/timex.h>
#include <asm/unistd.h>
#include <linux/compiler.h>
@@ -35,35 +36,20 @@ static inline u64 __arch_get_hw_counter(s32 clock_mode, const struct vdso_data *
static __always_inline
long clock_gettime_fallback(clockid_t clkid, struct __kernel_timespec *ts)
{
- register unsigned long r1 __asm__("r1") = __NR_clock_gettime;
- register unsigned long r2 __asm__("r2") = (unsigned long)clkid;
- register void *r3 __asm__("r3") = ts;
-
- asm ("svc 0\n" : "+d" (r2) : "d" (r1), "d" (r3) : "cc", "memory");
- return r2;
+ return syscall2(__NR_clock_gettime, (long)clkid, (long)ts);
}
static __always_inline
long gettimeofday_fallback(register struct __kernel_old_timeval *tv,
register struct timezone *tz)
{
- register unsigned long r1 __asm__("r1") = __NR_gettimeofday;
- register unsigned long r2 __asm__("r2") = (unsigned long)tv;
- register void *r3 __asm__("r3") = tz;
-
- asm ("svc 0\n" : "+d" (r2) : "d" (r1), "d" (r3) : "cc", "memory");
- return r2;
+ return syscall2(__NR_gettimeofday, (long)tv, (long)tz);
}
static __always_inline
long clock_getres_fallback(clockid_t clkid, struct __kernel_timespec *ts)
{
- register unsigned long r1 __asm__("r1") = __NR_clock_getres;
- register unsigned long r2 __asm__("r2") = (unsigned long)clkid;
- register void *r3 __asm__("r3") = ts;
-
- asm ("svc 0\n" : "+d" (r2) : "d" (r1), "d" (r3) : "cc", "memory");
- return r2;
+ return syscall2(__NR_clock_getres, (long)clkid, (long)ts);
}
#ifdef CONFIG_TIME_NS
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 4a44ba5a2d73..80f500ffb55c 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -40,7 +40,7 @@ obj-y += sysinfo.o lgr.o os_info.o machine_kexec.o
obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
obj-y += entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o
obj-y += nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o
-obj-y += smp.o
+obj-y += smp.o text_amode31.o
extra-y += head64.o vmlinux.lds
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 77ff2130cb04..b57da9338588 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -116,6 +116,7 @@ int main(void)
OFFSET(__LC_RESTART_FN, lowcore, restart_fn);
OFFSET(__LC_RESTART_DATA, lowcore, restart_data);
OFFSET(__LC_RESTART_SOURCE, lowcore, restart_source);
+ OFFSET(__LC_RESTART_FLAGS, lowcore, restart_flags);
OFFSET(__LC_KERNEL_ASCE, lowcore, kernel_asce);
OFFSET(__LC_USER_ASCE, lowcore, user_asce);
OFFSET(__LC_LPP, lowcore, lpp);
@@ -152,5 +153,12 @@ int main(void)
DEFINE(__KEXEC_SHA_REGION_SIZE, sizeof(struct kexec_sha_region));
/* sizeof kernel parameter area */
DEFINE(__PARMAREA_SIZE, sizeof(struct parmarea));
+ /* kernel parameter area offsets */
+ DEFINE(IPL_DEVICE, PARMAREA + offsetof(struct parmarea, ipl_device));
+ DEFINE(INITRD_START, PARMAREA + offsetof(struct parmarea, initrd_start));
+ DEFINE(INITRD_SIZE, PARMAREA + offsetof(struct parmarea, initrd_size));
+ DEFINE(OLDMEM_BASE, PARMAREA + offsetof(struct parmarea, oldmem_base));
+ DEFINE(OLDMEM_SIZE, PARMAREA + offsetof(struct parmarea, oldmem_size));
+ DEFINE(COMMAND_LINE, PARMAREA + offsetof(struct parmarea, command_line));
return 0;
}
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 0e36dfc9ccd6..d72a6df058d7 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -140,7 +140,7 @@ int copy_oldmem_kernel(void *dst, void *src, size_t count)
while (count) {
from = __pa(src);
- if (!OLDMEM_BASE && from < sclp.hsa_size) {
+ if (!oldmem_data.start && from < sclp.hsa_size) {
/* Copy from zfcp/nvme dump HSA area */
len = min(count, sclp.hsa_size - from);
rc = memcpy_hsa_kernel(dst, from, len);
@@ -148,12 +148,12 @@ int copy_oldmem_kernel(void *dst, void *src, size_t count)
return rc;
} else {
/* Check for swapped kdump oldmem areas */
- if (OLDMEM_BASE && from - OLDMEM_BASE < OLDMEM_SIZE) {
- from -= OLDMEM_BASE;
- len = min(count, OLDMEM_SIZE - from);
- } else if (OLDMEM_BASE && from < OLDMEM_SIZE) {
- len = min(count, OLDMEM_SIZE - from);
- from += OLDMEM_BASE;
+ if (oldmem_data.start && from - oldmem_data.start < oldmem_data.size) {
+ from -= oldmem_data.start;
+ len = min(count, oldmem_data.size - from);
+ } else if (oldmem_data.start && from < oldmem_data.size) {
+ len = min(count, oldmem_data.size - from);
+ from += oldmem_data.start;
} else {
len = count;
}
@@ -183,7 +183,7 @@ static int copy_oldmem_user(void __user *dst, void *src, size_t count)
while (count) {
from = __pa(src);
- if (!OLDMEM_BASE && from < sclp.hsa_size) {
+ if (!oldmem_data.start && from < sclp.hsa_size) {
/* Copy from zfcp/nvme dump HSA area */
len = min(count, sclp.hsa_size - from);
rc = memcpy_hsa_user(dst, from, len);
@@ -191,12 +191,12 @@ static int copy_oldmem_user(void __user *dst, void *src, size_t count)
return rc;
} else {
/* Check for swapped kdump oldmem areas */
- if (OLDMEM_BASE && from - OLDMEM_BASE < OLDMEM_SIZE) {
- from -= OLDMEM_BASE;
- len = min(count, OLDMEM_SIZE - from);
- } else if (OLDMEM_BASE && from < OLDMEM_SIZE) {
- len = min(count, OLDMEM_SIZE - from);
- from += OLDMEM_BASE;
+ if (oldmem_data.start && from - oldmem_data.size < oldmem_data.size) {
+ from -= oldmem_data.size;
+ len = min(count, oldmem_data.size - from);
+ } else if (oldmem_data.start && from < oldmem_data.size) {
+ len = min(count, oldmem_data.size - from);
+ from += oldmem_data.start;
} else {
len = count;
}
@@ -243,10 +243,10 @@ static int remap_oldmem_pfn_range_kdump(struct vm_area_struct *vma,
unsigned long size_old;
int rc;
- if (pfn < OLDMEM_SIZE >> PAGE_SHIFT) {
- size_old = min(size, OLDMEM_SIZE - (pfn << PAGE_SHIFT));
+ if (pfn < oldmem_data.size >> PAGE_SHIFT) {
+ size_old = min(size, oldmem_data.size - (pfn << PAGE_SHIFT));
rc = remap_pfn_range(vma, from,
- pfn + (OLDMEM_BASE >> PAGE_SHIFT),
+ pfn + (oldmem_data.start >> PAGE_SHIFT),
size_old, prot);
if (rc || size == size_old)
return rc;
@@ -288,7 +288,7 @@ static int remap_oldmem_pfn_range_zfcpdump(struct vm_area_struct *vma,
int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from,
unsigned long pfn, unsigned long size, pgprot_t prot)
{
- if (OLDMEM_BASE)
+ if (oldmem_data.start)
return remap_oldmem_pfn_range_kdump(vma, from, pfn, size, prot);
else
return remap_oldmem_pfn_range_zfcpdump(vma, from, pfn, size,
@@ -633,17 +633,17 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
u64 hdr_off;
/* If we are not in kdump or zfcp/nvme dump mode return */
- if (!OLDMEM_BASE && !is_ipl_type_dump())
+ if (!oldmem_data.start && !is_ipl_type_dump())
return 0;
/* If we cannot get HSA size for zfcp/nvme dump return error */
if (is_ipl_type_dump() && !sclp.hsa_size)
return -ENODEV;
/* For kdump, exclude previous crashkernel memory */
- if (OLDMEM_BASE) {
- oldmem_region.base = OLDMEM_BASE;
- oldmem_region.size = OLDMEM_SIZE;
- oldmem_type.total_size = OLDMEM_SIZE;
+ if (oldmem_data.start) {
+ oldmem_region.base = oldmem_data.start;
+ oldmem_region.size = oldmem_data.size;
+ oldmem_type.total_size = oldmem_data.size;
}
mem_chunk_cnt = get_mem_chunk_cnt();
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 09b6c6402f9b..4331c7e6e1c0 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -24,6 +24,7 @@
#include <linux/export.h>
#include <linux/init.h>
#include <linux/fs.h>
+#include <linux/minmax.h>
#include <linux/debugfs.h>
#include <asm/debug.h>
@@ -92,6 +93,8 @@ static int debug_hex_ascii_format_fn(debug_info_t *id, struct debug_view *view,
char *out_buf, const char *in_buf);
static int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view,
char *out_buf, debug_sprintf_entry_t *curr_event);
+static void debug_areas_swap(debug_info_t *a, debug_info_t *b);
+static void debug_events_append(debug_info_t *dest, debug_info_t *src);
/* globals */
@@ -311,24 +314,6 @@ static debug_info_t *debug_info_create(const char *name, int pages_per_area,
goto out;
rc->mode = mode & ~S_IFMT;
-
- /* create root directory */
- rc->debugfs_root_entry = debugfs_create_dir(rc->name,
- debug_debugfs_root_entry);
-
- /* append new element to linked list */
- if (!debug_area_first) {
- /* first element in list */
- debug_area_first = rc;
- rc->prev = NULL;
- } else {
- /* append element to end of list */
- debug_area_last->next = rc;
- rc->prev = debug_area_last;
- }
- debug_area_last = rc;
- rc->next = NULL;
-
refcount_set(&rc->ref_count, 1);
out:
return rc;
@@ -388,27 +373,10 @@ static void debug_info_get(debug_info_t *db_info)
*/
static void debug_info_put(debug_info_t *db_info)
{
- int i;
-
if (!db_info)
return;
- if (refcount_dec_and_test(&db_info->ref_count)) {
- for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
- if (!db_info->views[i])
- continue;
- debugfs_remove(db_info->debugfs_entries[i]);
- }
- debugfs_remove(db_info->debugfs_root_entry);
- if (db_info == debug_area_first)
- debug_area_first = db_info->next;
- if (db_info == debug_area_last)
- debug_area_last = db_info->prev;
- if (db_info->prev)
- db_info->prev->next = db_info->next;
- if (db_info->next)
- db_info->next->prev = db_info->prev;
+ if (refcount_dec_and_test(&db_info->ref_count))
debug_info_free(db_info);
- }
}
/*
@@ -632,6 +600,31 @@ static int debug_close(struct inode *inode, struct file *file)
return 0; /* success */
}
+/* Create debugfs entries and add to internal list. */
+static void _debug_register(debug_info_t *id)
+{
+ /* create root directory */
+ id->debugfs_root_entry = debugfs_create_dir(id->name,
+ debug_debugfs_root_entry);
+
+ /* append new element to linked list */
+ if (!debug_area_first) {
+ /* first element in list */
+ debug_area_first = id;
+ id->prev = NULL;
+ } else {
+ /* append element to end of list */
+ debug_area_last->next = id;
+ id->prev = debug_area_last;
+ }
+ debug_area_last = id;
+ id->next = NULL;
+
+ debug_register_view(id, &debug_level_view);
+ debug_register_view(id, &debug_flush_view);
+ debug_register_view(id, &debug_pages_view);
+}
+
/**
* debug_register_mode() - creates and initializes debug area.
*
@@ -661,19 +654,16 @@ debug_info_t *debug_register_mode(const char *name, int pages_per_area,
if ((uid != 0) || (gid != 0))
pr_warn("Root becomes the owner of all s390dbf files in sysfs\n");
BUG_ON(!initialized);
- mutex_lock(&debug_mutex);
/* create new debug_info */
rc = debug_info_create(name, pages_per_area, nr_areas, buf_size, mode);
- if (!rc)
- goto out;
- debug_register_view(rc, &debug_level_view);
- debug_register_view(rc, &debug_flush_view);
- debug_register_view(rc, &debug_pages_view);
-out:
- if (!rc)
+ if (rc) {
+ mutex_lock(&debug_mutex);
+ _debug_register(rc);
+ mutex_unlock(&debug_mutex);
+ } else {
pr_err("Registering debug feature %s failed\n", name);
- mutex_unlock(&debug_mutex);
+ }
return rc;
}
EXPORT_SYMBOL(debug_register_mode);
@@ -703,6 +693,82 @@ debug_info_t *debug_register(const char *name, int pages_per_area,
EXPORT_SYMBOL(debug_register);
/**
+ * debug_register_static() - registers a static debug area
+ *
+ * @id: Handle for static debug area
+ * @pages_per_area: Number of pages per area
+ * @nr_areas: Number of debug areas
+ *
+ * Register debug_info_t defined using DEFINE_STATIC_DEBUG_INFO.
+ *
+ * Note: This function is called automatically via an initcall generated by
+ * DEFINE_STATIC_DEBUG_INFO.
+ */
+void debug_register_static(debug_info_t *id, int pages_per_area, int nr_areas)
+{
+ unsigned long flags;
+ debug_info_t *copy;
+
+ if (!initialized) {
+ pr_err("Tried to register debug feature %s too early\n",
+ id->name);
+ return;
+ }
+
+ copy = debug_info_alloc("", pages_per_area, nr_areas, id->buf_size,
+ id->level, ALL_AREAS);
+ if (!copy) {
+ pr_err("Registering debug feature %s failed\n", id->name);
+
+ /* Clear pointers to prevent tracing into released initdata. */
+ spin_lock_irqsave(&id->lock, flags);
+ id->areas = NULL;
+ id->active_pages = NULL;
+ id->active_entries = NULL;
+ spin_unlock_irqrestore(&id->lock, flags);
+
+ return;
+ }
+
+ /* Replace static trace area with dynamic copy. */
+ spin_lock_irqsave(&id->lock, flags);
+ debug_events_append(copy, id);
+ debug_areas_swap(id, copy);
+ spin_unlock_irqrestore(&id->lock, flags);
+
+ /* Clear pointers to initdata and discard copy. */
+ copy->areas = NULL;
+ copy->active_pages = NULL;
+ copy->active_entries = NULL;
+ debug_info_free(copy);
+
+ mutex_lock(&debug_mutex);
+ _debug_register(id);
+ mutex_unlock(&debug_mutex);
+}
+
+/* Remove debugfs entries and remove from internal list. */
+static void _debug_unregister(debug_info_t *id)
+{
+ int i;
+
+ for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
+ if (!id->views[i])
+ continue;
+ debugfs_remove(id->debugfs_entries[i]);
+ }
+ debugfs_remove(id->debugfs_root_entry);
+ if (id == debug_area_first)
+ debug_area_first = id->next;
+ if (id == debug_area_last)
+ debug_area_last = id->prev;
+ if (id->prev)
+ id->prev->next = id->next;
+ if (id->next)
+ id->next->prev = id->prev;
+}
+
+/**
* debug_unregister() - give back debug area.
*
* @id: handle for debug log
@@ -715,8 +781,10 @@ void debug_unregister(debug_info_t *id)
if (!id)
return;
mutex_lock(&debug_mutex);
- debug_info_put(id);
+ _debug_unregister(id);
mutex_unlock(&debug_mutex);
+
+ debug_info_put(id);
}
EXPORT_SYMBOL(debug_unregister);
@@ -726,35 +794,28 @@ EXPORT_SYMBOL(debug_unregister);
*/
static int debug_set_size(debug_info_t *id, int nr_areas, int pages_per_area)
{
- debug_entry_t ***new_areas;
+ debug_info_t *new_id;
unsigned long flags;
- int rc = 0;
if (!id || (nr_areas <= 0) || (pages_per_area < 0))
return -EINVAL;
- if (pages_per_area > 0) {
- new_areas = debug_areas_alloc(pages_per_area, nr_areas);
- if (!new_areas) {
- pr_info("Allocating memory for %i pages failed\n",
- pages_per_area);
- rc = -ENOMEM;
- goto out;
- }
- } else {
- new_areas = NULL;
+
+ new_id = debug_info_alloc("", pages_per_area, nr_areas, id->buf_size,
+ id->level, ALL_AREAS);
+ if (!new_id) {
+ pr_info("Allocating memory for %i pages failed\n",
+ pages_per_area);
+ return -ENOMEM;
}
+
spin_lock_irqsave(&id->lock, flags);
- debug_areas_free(id);
- id->areas = new_areas;
- id->nr_areas = nr_areas;
- id->pages_per_area = pages_per_area;
- id->active_area = 0;
- memset(id->active_entries, 0, sizeof(int)*id->nr_areas);
- memset(id->active_pages, 0, sizeof(int)*id->nr_areas);
+ debug_events_append(new_id, id);
+ debug_areas_swap(new_id, id);
+ debug_info_free(new_id);
spin_unlock_irqrestore(&id->lock, flags);
pr_info("%s: set new size (%i pages)\n", id->name, pages_per_area);
-out:
- return rc;
+
+ return 0;
}
/**
@@ -772,16 +833,17 @@ void debug_set_level(debug_info_t *id, int new_level)
if (!id)
return;
- spin_lock_irqsave(&id->lock, flags);
+
if (new_level == DEBUG_OFF_LEVEL) {
- id->level = DEBUG_OFF_LEVEL;
pr_info("%s: switched off\n", id->name);
} else if ((new_level > DEBUG_MAX_LEVEL) || (new_level < 0)) {
pr_info("%s: level %i is out of range (%i - %i)\n",
id->name, new_level, 0, DEBUG_MAX_LEVEL);
- } else {
- id->level = new_level;
+ return;
}
+
+ spin_lock_irqsave(&id->lock, flags);
+ id->level = new_level;
spin_unlock_irqrestore(&id->lock, flags);
}
EXPORT_SYMBOL(debug_set_level);
@@ -821,6 +883,42 @@ static inline debug_entry_t *get_active_entry(debug_info_t *id)
id->active_entries[id->active_area]);
}
+/* Swap debug areas of a and b. */
+static void debug_areas_swap(debug_info_t *a, debug_info_t *b)
+{
+ swap(a->nr_areas, b->nr_areas);
+ swap(a->pages_per_area, b->pages_per_area);
+ swap(a->areas, b->areas);
+ swap(a->active_area, b->active_area);
+ swap(a->active_pages, b->active_pages);
+ swap(a->active_entries, b->active_entries);
+}
+
+/* Append all debug events in active area from source to destination log. */
+static void debug_events_append(debug_info_t *dest, debug_info_t *src)
+{
+ debug_entry_t *from, *to, *last;
+
+ if (!src->areas || !dest->areas)
+ return;
+
+ /* Loop over all entries in src, starting with oldest. */
+ from = get_active_entry(src);
+ last = from;
+ do {
+ if (from->clock != 0LL) {
+ to = get_active_entry(dest);
+ memset(to, 0, dest->entry_size);
+ memcpy(to, from, min(src->entry_size,
+ dest->entry_size));
+ proceed_active_entry(dest);
+ }
+
+ proceed_active_entry(src);
+ from = get_active_entry(src);
+ } while (from != last);
+}
+
/*
* debug_finish_entry:
* - set timestamp, caller address, cpu number etc.
@@ -1111,16 +1209,17 @@ int debug_register_view(debug_info_t *id, struct debug_view *view)
break;
}
if (i == DEBUG_MAX_VIEWS) {
- pr_err("Registering view %s/%s would exceed the maximum "
- "number of views %i\n", id->name, view->name, i);
rc = -1;
} else {
id->views[i] = view;
id->debugfs_entries[i] = pde;
}
spin_unlock_irqrestore(&id->lock, flags);
- if (rc)
+ if (rc) {
+ pr_err("Registering view %s/%s would exceed the maximum "
+ "number of views %i\n", id->name, view->name, i);
debugfs_remove(pde);
+ }
out:
return rc;
}
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
index a3f47464c3f1..76a656b2146f 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -14,6 +14,7 @@
#include <asm/diag.h>
#include <asm/trace/diag.h>
#include <asm/sections.h>
+#include "entry.h"
struct diag_stat {
unsigned int counter[NR_DIAG_STAT];
@@ -50,8 +51,16 @@ static const struct diag_desc diag_map[NR_DIAG_STAT] = {
[DIAG_STAT_X500] = { .code = 0x500, .name = "Virtio Service" },
};
-struct diag_ops __bootdata_preserved(diag_dma_ops);
-struct diag210 *__bootdata_preserved(__diag210_tmp_dma);
+struct diag_ops __amode31_ref diag_amode31_ops = {
+ .diag210 = _diag210_amode31,
+ .diag26c = _diag26c_amode31,
+ .diag14 = _diag14_amode31,
+ .diag0c = _diag0c_amode31,
+ .diag308_reset = _diag308_reset_amode31
+};
+
+static struct diag210 _diag210_tmp_amode31 __section(".amode31.data");
+struct diag210 __amode31_ref *__diag210_tmp_amode31 = &_diag210_tmp_amode31;
static int show_diag_stat(struct seq_file *m, void *v)
{
@@ -59,7 +68,7 @@ static int show_diag_stat(struct seq_file *m, void *v)
unsigned long n = (unsigned long) v - 1;
int cpu, prec, tmp;
- get_online_cpus();
+ cpus_read_lock();
if (n == 0) {
seq_puts(m, " ");
@@ -78,7 +87,7 @@ static int show_diag_stat(struct seq_file *m, void *v)
}
seq_printf(m, " %s\n", diag_map[n-1].name);
}
- put_online_cpus();
+ cpus_read_unlock();
return 0;
}
@@ -135,7 +144,7 @@ EXPORT_SYMBOL(diag_stat_inc_norecursion);
int diag14(unsigned long rx, unsigned long ry1, unsigned long subcode)
{
diag_stat_inc(DIAG_STAT_X014);
- return diag_dma_ops.diag14(rx, ry1, subcode);
+ return diag_amode31_ops.diag14(rx, ry1, subcode);
}
EXPORT_SYMBOL(diag14);
@@ -172,12 +181,12 @@ int diag210(struct diag210 *addr)
int ccode;
spin_lock_irqsave(&diag210_lock, flags);
- *__diag210_tmp_dma = *addr;
+ *__diag210_tmp_amode31 = *addr;
diag_stat_inc(DIAG_STAT_X210);
- ccode = diag_dma_ops.diag210(__diag210_tmp_dma);
+ ccode = diag_amode31_ops.diag210(__diag210_tmp_amode31);
- *addr = *__diag210_tmp_dma;
+ *addr = *__diag210_tmp_amode31;
spin_unlock_irqrestore(&diag210_lock, flags);
return ccode;
@@ -205,6 +214,6 @@ EXPORT_SYMBOL(diag224);
int diag26c(void *req, void *resp, enum diag26c_sc subcode)
{
diag_stat_inc(DIAG_STAT_X26C);
- return diag_dma_ops.diag26c(req, resp, subcode);
+ return diag_amode31_ops.diag26c(req, resp, subcode);
}
EXPORT_SYMBOL(diag26c);
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 5412efe328f8..ec5515423f17 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -312,10 +312,12 @@ static const unsigned char formats[][6] = {
[INSTR_VRR_VV] = { V_8, V_12, 0, 0, 0, 0 },
[INSTR_VRR_VV0U] = { V_8, V_12, U4_32, 0, 0, 0 },
[INSTR_VRR_VV0U0U] = { V_8, V_12, U4_32, U4_24, 0, 0 },
+ [INSTR_VRR_VV0U2] = { V_8, V_12, U4_24, 0, 0, 0 },
[INSTR_VRR_VV0UU2] = { V_8, V_12, U4_32, U4_28, 0, 0 },
[INSTR_VRR_VV0UUU] = { V_8, V_12, U4_32, U4_28, U4_24, 0 },
[INSTR_VRR_VVV] = { V_8, V_12, V_16, 0, 0, 0 },
[INSTR_VRR_VVV0U] = { V_8, V_12, V_16, U4_32, 0, 0 },
+ [INSTR_VRR_VVV0U0] = { V_8, V_12, V_16, U4_24, 0, 0 },
[INSTR_VRR_VVV0U0U] = { V_8, V_12, V_16, U4_32, U4_24, 0 },
[INSTR_VRR_VVV0UU] = { V_8, V_12, V_16, U4_32, U4_28, 0 },
[INSTR_VRR_VVV0UUU] = { V_8, V_12, V_16, U4_32, U4_28, U4_24 },
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index fb84e3fc1686..9857cb046726 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -236,6 +236,10 @@ static __init void detect_machine_facilities(void)
clock_comparator_max = -1ULL >> 1;
__ctl_set_bit(0, 53);
}
+ if (IS_ENABLED(CONFIG_PCI) && test_facility(153)) {
+ S390_lowcore.machine_flags |= MACHINE_FLAG_PCI_MIO;
+ /* the control bit is set during PCI initialization */
+ }
}
static inline void save_vector_registers(void)
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 5a2f70cbd3a9..b9716a7e326d 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -624,12 +624,15 @@ ENTRY(mcck_int_handler)
4: j 4b
ENDPROC(mcck_int_handler)
-#
-# PSW restart interrupt handler
-#
ENTRY(restart_int_handler)
ALTERNATIVE "", ".insn s,0xb2800000,_LPP_OFFSET", 40
stg %r15,__LC_SAVE_AREA_RESTART
+ TSTMSK __LC_RESTART_FLAGS,RESTART_FLAG_CTLREGS,4
+ jz 0f
+ la %r15,4095
+ lctlg %c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r15)
+0: larl %r15,.Lstosm_tmp
+ stosm 0(%r15),0x04 # turn dat on, keep irqs off
lg %r15,__LC_RESTART_STACK
xc STACK_FRAME_OVERHEAD(__PT_SIZE,%r15),STACK_FRAME_OVERHEAD(%r15)
stmg %r0,%r14,STACK_FRAME_OVERHEAD+__PT_R0(%r15)
@@ -638,7 +641,7 @@ ENTRY(restart_int_handler)
xc 0(STACK_FRAME_OVERHEAD,%r15),0(%r15)
lg %r1,__LC_RESTART_FN # load fn, parm & source cpu
lg %r2,__LC_RESTART_DATA
- lg %r3,__LC_RESTART_SOURCE
+ lgf %r3,__LC_RESTART_SOURCE
ltgr %r3,%r3 # test source cpu address
jm 1f # negative -> skip source stop
0: sigp %r4,%r3,SIGP_SENSE # sigp sense to source cpu
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 1ab33465382f..7f2696e8d511 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -28,10 +28,8 @@ void do_non_secure_storage_access(struct pt_regs *regs);
void do_secure_storage_violation(struct pt_regs *regs);
void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str);
void kernel_stack_overflow(struct pt_regs * regs);
-void do_signal(struct pt_regs *regs);
void handle_signal32(struct ksignal *ksig, sigset_t *oldset,
struct pt_regs *regs);
-void do_notify_resume(struct pt_regs *regs);
void __init init_IRQ(void);
void do_io_irq(struct pt_regs *regs);
@@ -64,4 +62,13 @@ void stack_free(unsigned long stack);
extern char kprobes_insn_page[];
+extern char _samode31[], _eamode31[];
+extern char _stext_amode31[], _etext_amode31[];
+extern struct exception_table_entry _start_amode31_ex_table[];
+extern struct exception_table_entry _stop_amode31_ex_table[];
+
+#define __amode31_data __section(".amode31.data")
+#define __amode31_ref __section(".amode31.refs")
+extern long _start_amode31_refs[], _end_amode31_refs[];
+
#endif /* _ENTRY_H */
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 2d8f595d9196..0a464d328467 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -18,8 +18,11 @@
#include <trace/syscall.h>
#include <asm/asm-offsets.h>
#include <asm/cacheflush.h>
+#include <asm/ftrace.lds.h>
+#include <asm/nospec-branch.h>
#include <asm/set_memory.h>
#include "entry.h"
+#include "ftrace.h"
/*
* To generate function prologue either gcc's hotpatch feature (since gcc 4.8)
@@ -41,7 +44,130 @@
*/
void *ftrace_func __read_mostly = ftrace_stub;
-unsigned long ftrace_plt;
+struct ftrace_insn {
+ u16 opc;
+ s32 disp;
+} __packed;
+
+asm(
+ " .align 16\n"
+ "ftrace_shared_hotpatch_trampoline_br:\n"
+ " lmg %r0,%r1,2(%r1)\n"
+ " br %r1\n"
+ "ftrace_shared_hotpatch_trampoline_br_end:\n"
+);
+
+#ifdef CONFIG_EXPOLINE
+asm(
+ " .align 16\n"
+ "ftrace_shared_hotpatch_trampoline_ex:\n"
+ " lmg %r0,%r1,2(%r1)\n"
+ " ex %r0," __stringify(__LC_BR_R1) "(%r0)\n"
+ " j .\n"
+ "ftrace_shared_hotpatch_trampoline_ex_end:\n"
+);
+
+asm(
+ " .align 16\n"
+ "ftrace_shared_hotpatch_trampoline_exrl:\n"
+ " lmg %r0,%r1,2(%r1)\n"
+ " .insn ril,0xc60000000000,%r0,0f\n" /* exrl */
+ " j .\n"
+ "0: br %r1\n"
+ "ftrace_shared_hotpatch_trampoline_exrl_end:\n"
+);
+#endif /* CONFIG_EXPOLINE */
+
+#ifdef CONFIG_MODULES
+static char *ftrace_plt;
+
+asm(
+ " .data\n"
+ "ftrace_plt_template:\n"
+ " basr %r1,%r0\n"
+ " lg %r1,0f-.(%r1)\n"
+ " br %r1\n"
+ "0: .quad ftrace_caller\n"
+ "ftrace_plt_template_end:\n"
+ " .previous\n"
+);
+#endif /* CONFIG_MODULES */
+
+static const char *ftrace_shared_hotpatch_trampoline(const char **end)
+{
+ const char *tstart, *tend;
+
+ tstart = ftrace_shared_hotpatch_trampoline_br;
+ tend = ftrace_shared_hotpatch_trampoline_br_end;
+#ifdef CONFIG_EXPOLINE
+ if (!nospec_disable) {
+ tstart = ftrace_shared_hotpatch_trampoline_ex;
+ tend = ftrace_shared_hotpatch_trampoline_ex_end;
+ if (test_facility(35)) { /* exrl */
+ tstart = ftrace_shared_hotpatch_trampoline_exrl;
+ tend = ftrace_shared_hotpatch_trampoline_exrl_end;
+ }
+ }
+#endif /* CONFIG_EXPOLINE */
+ if (end)
+ *end = tend;
+ return tstart;
+}
+
+bool ftrace_need_init_nop(void)
+{
+ return ftrace_shared_hotpatch_trampoline(NULL);
+}
+
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
+{
+ static struct ftrace_hotpatch_trampoline *next_vmlinux_trampoline =
+ __ftrace_hotpatch_trampolines_start;
+ static const char orig[6] = { 0xc0, 0x04, 0x00, 0x00, 0x00, 0x00 };
+ static struct ftrace_hotpatch_trampoline *trampoline;
+ struct ftrace_hotpatch_trampoline **next_trampoline;
+ struct ftrace_hotpatch_trampoline *trampolines_end;
+ struct ftrace_hotpatch_trampoline tmp;
+ struct ftrace_insn *insn;
+ const char *shared;
+ s32 disp;
+
+ BUILD_BUG_ON(sizeof(struct ftrace_hotpatch_trampoline) !=
+ SIZEOF_FTRACE_HOTPATCH_TRAMPOLINE);
+
+ next_trampoline = &next_vmlinux_trampoline;
+ trampolines_end = __ftrace_hotpatch_trampolines_end;
+ shared = ftrace_shared_hotpatch_trampoline(NULL);
+#ifdef CONFIG_MODULES
+ if (mod) {
+ next_trampoline = &mod->arch.next_trampoline;
+ trampolines_end = mod->arch.trampolines_end;
+ shared = ftrace_plt;
+ }
+#endif
+
+ if (WARN_ON_ONCE(*next_trampoline >= trampolines_end))
+ return -ENOMEM;
+ trampoline = (*next_trampoline)++;
+
+ /* Check for the compiler-generated fentry nop (brcl 0, .). */
+ if (WARN_ON_ONCE(memcmp((const void *)rec->ip, &orig, sizeof(orig))))
+ return -EINVAL;
+
+ /* Generate the trampoline. */
+ tmp.brasl_opc = 0xc015; /* brasl %r1, shared */
+ tmp.brasl_disp = (shared - (const char *)&trampoline->brasl_opc) / 2;
+ tmp.interceptor = FTRACE_ADDR;
+ tmp.rest_of_intercepted_function = rec->ip + sizeof(struct ftrace_insn);
+ s390_kernel_write(trampoline, &tmp, sizeof(tmp));
+
+ /* Generate a jump to the trampoline. */
+ disp = ((char *)trampoline - (char *)rec->ip) / 2;
+ insn = (struct ftrace_insn *)rec->ip;
+ s390_kernel_write(&insn->disp, &disp, sizeof(disp));
+
+ return 0;
+}
int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long addr)
@@ -49,11 +175,45 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
return 0;
}
+static void ftrace_generate_nop_insn(struct ftrace_insn *insn)
+{
+ /* brcl 0,0 */
+ insn->opc = 0xc004;
+ insn->disp = 0;
+}
+
+static void ftrace_generate_call_insn(struct ftrace_insn *insn,
+ unsigned long ip)
+{
+ unsigned long target;
+
+ /* brasl r0,ftrace_caller */
+ target = FTRACE_ADDR;
+#ifdef CONFIG_MODULES
+ if (is_module_addr((void *)ip))
+ target = (unsigned long)ftrace_plt;
+#endif /* CONFIG_MODULES */
+ insn->opc = 0xc005;
+ insn->disp = (target - ip) / 2;
+}
+
+static void brcl_disable(void *brcl)
+{
+ u8 op = 0x04; /* set mask field to zero */
+
+ s390_kernel_write((char *)brcl + 1, &op, sizeof(op));
+}
+
int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
unsigned long addr)
{
struct ftrace_insn orig, new, old;
+ if (ftrace_shared_hotpatch_trampoline(NULL)) {
+ brcl_disable((void *)rec->ip);
+ return 0;
+ }
+
if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old)))
return -EFAULT;
/* Replace ftrace call with a nop. */
@@ -67,10 +227,22 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
return 0;
}
+static void brcl_enable(void *brcl)
+{
+ u8 op = 0xf4; /* set mask field to all ones */
+
+ s390_kernel_write((char *)brcl + 1, &op, sizeof(op));
+}
+
int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
struct ftrace_insn orig, new, old;
+ if (ftrace_shared_hotpatch_trampoline(NULL)) {
+ brcl_enable((void *)rec->ip);
+ return 0;
+ }
+
if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old)))
return -EFAULT;
/* Replace nop with an ftrace call. */
@@ -95,22 +267,44 @@ int __init ftrace_dyn_arch_init(void)
return 0;
}
+void arch_ftrace_update_code(int command)
+{
+ if (ftrace_shared_hotpatch_trampoline(NULL))
+ ftrace_modify_all_code(command);
+ else
+ ftrace_run_stop_machine(command);
+}
+
+static void __ftrace_sync(void *dummy)
+{
+}
+
+int ftrace_arch_code_modify_post_process(void)
+{
+ if (ftrace_shared_hotpatch_trampoline(NULL)) {
+ /* Send SIGP to the other CPUs, so they see the new code. */
+ smp_call_function(__ftrace_sync, NULL, 1);
+ }
+ return 0;
+}
+
#ifdef CONFIG_MODULES
static int __init ftrace_plt_init(void)
{
- unsigned int *ip;
+ const char *start, *end;
- ftrace_plt = (unsigned long) module_alloc(PAGE_SIZE);
+ ftrace_plt = module_alloc(PAGE_SIZE);
if (!ftrace_plt)
panic("cannot allocate ftrace plt\n");
- ip = (unsigned int *) ftrace_plt;
- ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */
- ip[1] = 0x100a0004;
- ip[2] = 0x07f10000;
- ip[3] = FTRACE_ADDR >> 32;
- ip[4] = FTRACE_ADDR & 0xffffffff;
- set_memory_ro(ftrace_plt, 1);
+
+ start = ftrace_shared_hotpatch_trampoline(&end);
+ if (!start) {
+ start = ftrace_plt_template;
+ end = ftrace_plt_template_end;
+ }
+ memcpy(ftrace_plt, start, end - start);
+ set_memory_ro((unsigned long)ftrace_plt, 1);
return 0;
}
device_initcall(ftrace_plt_init);
@@ -147,17 +341,13 @@ NOKPROBE_SYMBOL(prepare_ftrace_return);
*/
int ftrace_enable_ftrace_graph_caller(void)
{
- u8 op = 0x04; /* set mask field to zero */
-
- s390_kernel_write(__va(ftrace_graph_caller)+1, &op, sizeof(op));
+ brcl_disable(__va(ftrace_graph_caller));
return 0;
}
int ftrace_disable_ftrace_graph_caller(void)
{
- u8 op = 0xf4; /* set mask field to all ones */
-
- s390_kernel_write(__va(ftrace_graph_caller)+1, &op, sizeof(op));
+ brcl_enable(__va(ftrace_graph_caller));
return 0;
}
diff --git a/arch/s390/kernel/ftrace.h b/arch/s390/kernel/ftrace.h
new file mode 100644
index 000000000000..69e416f4c6b0
--- /dev/null
+++ b/arch/s390/kernel/ftrace.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _FTRACE_H
+#define _FTRACE_H
+
+#include <asm/types.h>
+
+struct ftrace_hotpatch_trampoline {
+ u16 brasl_opc;
+ s32 brasl_disp;
+ s16: 16;
+ u64 rest_of_intercepted_function;
+ u64 interceptor;
+} __packed;
+
+extern struct ftrace_hotpatch_trampoline __ftrace_hotpatch_trampolines_start[];
+extern struct ftrace_hotpatch_trampoline __ftrace_hotpatch_trampolines_end[];
+extern const char ftrace_shared_hotpatch_trampoline_br[];
+extern const char ftrace_shared_hotpatch_trampoline_br_end[];
+extern const char ftrace_shared_hotpatch_trampoline_ex[];
+extern const char ftrace_shared_hotpatch_trampoline_ex_end[];
+extern const char ftrace_shared_hotpatch_trampoline_exrl[];
+extern const char ftrace_shared_hotpatch_trampoline_exrl_end[];
+extern const char ftrace_plt_template[];
+extern const char ftrace_plt_template_end[];
+
+#endif /* _FTRACE_H */
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 0c253886da78..114b5490ad8e 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -21,6 +21,7 @@ ENTRY(startup_continue)
larl %r1,tod_clock_base
mvc 0(16,%r1),__LC_BOOT_CLOCK
larl %r13,.LPG1 # get base
+ lctlg %c0,%c15,.Lctl-.LPG1(%r13) # load control registers
#
# Setup stack
#
@@ -41,3 +42,19 @@ ENTRY(startup_continue)
.align 16
.LPG1:
.Ldw: .quad 0x0002000180000000,0x0000000000000000
+.Lctl: .quad 0x04040000 # cr0: AFP registers & secondary space
+ .quad 0 # cr1: primary space segment table
+ .quad 0 # cr2: dispatchable unit control table
+ .quad 0 # cr3: instruction authorization
+ .quad 0xffff # cr4: instruction authorization
+ .quad 0 # cr5: primary-aste origin
+ .quad 0 # cr6: I/O interrupts
+ .quad 0 # cr7: secondary space segment table
+ .quad 0x0000000000008000 # cr8: access registers translation
+ .quad 0 # cr9: tracing off
+ .quad 0 # cr10: tracing off
+ .quad 0 # cr11: tracing off
+ .quad 0 # cr12: tracing off
+ .quad 0 # cr13: home space segment table
+ .quad 0xc0000000 # cr14: machine check handling off
+ .quad 0 # cr15: linkage stack operations
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 50e2c21e0ec9..e2cc35775b99 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -179,8 +179,6 @@ static inline int __diag308(unsigned long subcode, void *addr)
int diag308(unsigned long subcode, void *addr)
{
- if (IS_ENABLED(CONFIG_KASAN))
- __arch_local_irq_stosm(0x04); /* enable DAT */
diag_stat_inc(DIAG_STAT_X308);
return __diag308(subcode, addr);
}
@@ -1843,7 +1841,6 @@ static struct kobj_attribute on_restart_attr = __ATTR_RW(on_restart);
static void __do_restart(void *ignore)
{
- __arch_local_irq_stosm(0x04); /* enable DAT */
smp_send_stop();
#ifdef CONFIG_CRASH_DUMP
crash_kexec(NULL);
@@ -2082,7 +2079,7 @@ void s390_reset_system(void)
/* Disable lowcore protection */
__ctl_clear_bit(0, 28);
- diag_dma_ops.diag308_reset();
+ diag_amode31_ops.diag308_reset();
}
#ifdef CONFIG_KEXEC_FILE
diff --git a/arch/s390/kernel/ipl_vmparm.c b/arch/s390/kernel/ipl_vmparm.c
index af43535a976d..b5245fadcfb0 100644
--- a/arch/s390/kernel/ipl_vmparm.c
+++ b/arch/s390/kernel/ipl_vmparm.c
@@ -1,4 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
+#include <linux/minmax.h>
+#include <linux/string.h>
#include <asm/ebcdic.h>
#include <asm/ipl.h>
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 234d085257eb..3a3145c4a3ba 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -228,7 +228,7 @@ int show_interrupts(struct seq_file *p, void *v)
int index = *(loff_t *) v;
int cpu, irq;
- get_online_cpus();
+ cpus_read_lock();
if (index == 0) {
seq_puts(p, " ");
for_each_online_cpu(cpu)
@@ -258,7 +258,7 @@ int show_interrupts(struct seq_file *p, void *v)
seq_putc(p, '\n');
}
out:
- put_online_cpus();
+ cpus_read_unlock();
return 0;
}
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
index ab584e8e3527..9156653b56f6 100644
--- a/arch/s390/kernel/jump_label.c
+++ b/arch/s390/kernel/jump_label.c
@@ -36,7 +36,7 @@ static void jump_label_bug(struct jump_entry *entry, struct insn *expected,
unsigned char *ipe = (unsigned char *)expected;
unsigned char *ipn = (unsigned char *)new;
- pr_emerg("Jump label code mismatch at %pS [%p]\n", ipc, ipc);
+ pr_emerg("Jump label code mismatch at %pS [%px]\n", ipc, ipc);
pr_emerg("Found: %6ph\n", ipc);
pr_emerg("Expected: %6ph\n", ipe);
pr_emerg("New: %6ph\n", ipn);
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 1005a6935fbe..0505e55a6297 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -224,8 +224,8 @@ void arch_crash_save_vmcoreinfo(void)
VMCOREINFO_SYMBOL(lowcore_ptr);
VMCOREINFO_SYMBOL(high_memory);
VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
- vmcoreinfo_append_str("SDMA=%lx\n", __sdma);
- vmcoreinfo_append_str("EDMA=%lx\n", __edma);
+ vmcoreinfo_append_str("SAMODE31=%lx\n", __samode31);
+ vmcoreinfo_append_str("EAMODE31=%lx\n", __eamode31);
vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
}
@@ -263,7 +263,6 @@ static void __do_machine_kexec(void *data)
*/
static void __machine_kexec(void *data)
{
- __arch_local_irq_stosm(0x04); /* enable DAT */
pfault_fini();
tracing_off();
debug_locks_off();
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index 4055f1c49814..b01ba460b7ca 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -14,6 +14,7 @@
#include <linux/elf.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
+#include <linux/ftrace.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/kasan.h>
@@ -23,6 +24,8 @@
#include <asm/alternative.h>
#include <asm/nospec-branch.h>
#include <asm/facility.h>
+#include <asm/ftrace.lds.h>
+#include <asm/set_memory.h>
#if 0
#define DEBUGP printk
@@ -48,6 +51,13 @@ void *module_alloc(unsigned long size)
return p;
}
+#ifdef CONFIG_FUNCTION_TRACER
+void module_arch_cleanup(struct module *mod)
+{
+ module_memfree(mod->arch.trampolines_start);
+}
+#endif
+
void module_arch_freeing_init(struct module *mod)
{
if (is_livepatch_module(mod) &&
@@ -466,6 +476,30 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
write);
}
+#ifdef CONFIG_FUNCTION_TRACER
+static int module_alloc_ftrace_hotpatch_trampolines(struct module *me,
+ const Elf_Shdr *s)
+{
+ char *start, *end;
+ int numpages;
+ size_t size;
+
+ size = FTRACE_HOTPATCH_TRAMPOLINES_SIZE(s->sh_size);
+ numpages = DIV_ROUND_UP(size, PAGE_SIZE);
+ start = module_alloc(numpages * PAGE_SIZE);
+ if (!start)
+ return -ENOMEM;
+ set_memory_ro((unsigned long)start, numpages);
+ end = start + size;
+
+ me->arch.trampolines_start = (struct ftrace_hotpatch_trampoline *)start;
+ me->arch.trampolines_end = (struct ftrace_hotpatch_trampoline *)end;
+ me->arch.next_trampoline = me->arch.trampolines_start;
+
+ return 0;
+}
+#endif /* CONFIG_FUNCTION_TRACER */
+
int module_finalize(const Elf_Ehdr *hdr,
const Elf_Shdr *sechdrs,
struct module *me)
@@ -473,6 +507,9 @@ int module_finalize(const Elf_Ehdr *hdr,
const Elf_Shdr *s;
char *secstrings, *secname;
void *aseg;
+#ifdef CONFIG_FUNCTION_TRACER
+ int ret;
+#endif
if (IS_ENABLED(CONFIG_EXPOLINE) &&
!nospec_disable && me->arch.plt_size) {
@@ -507,6 +544,14 @@ int module_finalize(const Elf_Ehdr *hdr,
if (IS_ENABLED(CONFIG_EXPOLINE) &&
(str_has_prefix(secname, ".s390_return")))
nospec_revert(aseg, aseg + s->sh_size);
+
+#ifdef CONFIG_FUNCTION_TRACER
+ if (!strcmp(FTRACE_CALLSITE_SECTION, secname)) {
+ ret = module_alloc_ftrace_hotpatch_trampolines(me, s);
+ if (ret < 0)
+ return ret;
+ }
+#endif /* CONFIG_FUNCTION_TRACER */
}
jump_label_apply_nops(me);
diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c
index 5a7420b23aa8..4bef35b79b93 100644
--- a/arch/s390/kernel/os_info.c
+++ b/arch/s390/kernel/os_info.c
@@ -121,7 +121,7 @@ static void os_info_old_init(void)
if (os_info_init)
return;
- if (!OLDMEM_BASE)
+ if (!oldmem_data.start)
goto fail;
if (copy_oldmem_kernel(&addr, &S390_lowcore.os_info, sizeof(addr)))
goto fail;
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index d7dc36ec0a60..2e3bb633acf6 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -1138,7 +1138,7 @@ static long cfset_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
int ret;
- get_online_cpus();
+ cpus_read_lock();
mutex_lock(&cfset_ctrset_mutex);
switch (cmd) {
case S390_HWCTR_START:
@@ -1155,7 +1155,7 @@ static long cfset_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
break;
}
mutex_unlock(&cfset_ctrset_mutex);
- put_online_cpus();
+ cpus_read_unlock();
return ret;
}
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 82df39b17bb5..d9d4a806979e 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -11,6 +11,7 @@
#include <linux/cpufeature.h>
#include <linux/bitops.h>
#include <linux/kernel.h>
+#include <linux/random.h>
#include <linux/sched/mm.h>
#include <linux/init.h>
#include <linux/seq_file.h>
@@ -23,8 +24,12 @@
#include <asm/elf.h>
#include <asm/lowcore.h>
#include <asm/param.h>
+#include <asm/sclp.h>
#include <asm/smp.h>
+unsigned long __read_mostly elf_hwcap;
+char elf_platform[ELF_PLATFORM_SIZE];
+
struct cpu_info {
unsigned int cpu_mhz_dynamic;
unsigned int cpu_mhz_static;
@@ -113,15 +118,33 @@ static void show_facilities(struct seq_file *m)
static void show_cpu_summary(struct seq_file *m, void *v)
{
static const char *hwcap_str[] = {
- "esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
- "edat", "etf3eh", "highgprs", "te", "vx", "vxd", "vxe", "gs",
- "vxe2", "vxp", "sort", "dflt"
- };
- static const char * const int_hwcap_str[] = {
- "sie"
+ [HWCAP_NR_ESAN3] = "esan3",
+ [HWCAP_NR_ZARCH] = "zarch",
+ [HWCAP_NR_STFLE] = "stfle",
+ [HWCAP_NR_MSA] = "msa",
+ [HWCAP_NR_LDISP] = "ldisp",
+ [HWCAP_NR_EIMM] = "eimm",
+ [HWCAP_NR_DFP] = "dfp",
+ [HWCAP_NR_HPAGE] = "edat",
+ [HWCAP_NR_ETF3EH] = "etf3eh",
+ [HWCAP_NR_HIGH_GPRS] = "highgprs",
+ [HWCAP_NR_TE] = "te",
+ [HWCAP_NR_VXRS] = "vx",
+ [HWCAP_NR_VXRS_BCD] = "vxd",
+ [HWCAP_NR_VXRS_EXT] = "vxe",
+ [HWCAP_NR_GS] = "gs",
+ [HWCAP_NR_VXRS_EXT2] = "vxe2",
+ [HWCAP_NR_VXRS_PDE] = "vxp",
+ [HWCAP_NR_SORT] = "sort",
+ [HWCAP_NR_DFLT] = "dflt",
+ [HWCAP_NR_VXRS_PDE2] = "vxp2",
+ [HWCAP_NR_NNPA] = "nnpa",
+ [HWCAP_NR_PCI_MIO] = "pcimio",
+ [HWCAP_NR_SIE] = "sie",
};
int i, cpu;
+ BUILD_BUG_ON(ARRAY_SIZE(hwcap_str) != HWCAP_NR_MAX);
seq_printf(m, "vendor_id : IBM/S390\n"
"# processors : %i\n"
"bogomips per cpu: %lu.%02lu\n",
@@ -132,9 +155,6 @@ static void show_cpu_summary(struct seq_file *m, void *v)
for (i = 0; i < ARRAY_SIZE(hwcap_str); i++)
if (hwcap_str[i] && (elf_hwcap & (1UL << i)))
seq_printf(m, "%s ", hwcap_str[i]);
- for (i = 0; i < ARRAY_SIZE(int_hwcap_str); i++)
- if (int_hwcap_str[i] && (int_hwcap & (1UL << i)))
- seq_printf(m, "%s ", int_hwcap_str[i]);
seq_puts(m, "\n");
show_facilities(m);
show_cacheinfo(m);
@@ -149,6 +169,141 @@ static void show_cpu_summary(struct seq_file *m, void *v)
}
}
+static int __init setup_hwcaps(void)
+{
+ /* instructions named N3, "backported" to esa-mode */
+ if (test_facility(0))
+ elf_hwcap |= HWCAP_ESAN3;
+
+ /* z/Architecture mode active */
+ elf_hwcap |= HWCAP_ZARCH;
+
+ /* store-facility-list-extended */
+ if (test_facility(7))
+ elf_hwcap |= HWCAP_STFLE;
+
+ /* message-security assist */
+ if (test_facility(17))
+ elf_hwcap |= HWCAP_MSA;
+
+ /* long-displacement */
+ if (test_facility(19))
+ elf_hwcap |= HWCAP_LDISP;
+
+ /* extended-immediate */
+ if (test_facility(21))
+ elf_hwcap |= HWCAP_EIMM;
+
+ /* extended-translation facility 3 enhancement */
+ if (test_facility(22) && test_facility(30))
+ elf_hwcap |= HWCAP_ETF3EH;
+
+ /* decimal floating point & perform floating point operation */
+ if (test_facility(42) && test_facility(44))
+ elf_hwcap |= HWCAP_DFP;
+
+ /* huge page support */
+ if (MACHINE_HAS_EDAT1)
+ elf_hwcap |= HWCAP_HPAGE;
+
+ /* 64-bit register support for 31-bit processes */
+ elf_hwcap |= HWCAP_HIGH_GPRS;
+
+ /* transactional execution */
+ if (MACHINE_HAS_TE)
+ elf_hwcap |= HWCAP_TE;
+
+ /*
+ * Vector extension can be disabled with the "novx" parameter.
+ * Use MACHINE_HAS_VX instead of facility bit 129.
+ */
+ if (MACHINE_HAS_VX) {
+ elf_hwcap |= HWCAP_VXRS;
+ if (test_facility(134))
+ elf_hwcap |= HWCAP_VXRS_BCD;
+ if (test_facility(135))
+ elf_hwcap |= HWCAP_VXRS_EXT;
+ if (test_facility(148))
+ elf_hwcap |= HWCAP_VXRS_EXT2;
+ if (test_facility(152))
+ elf_hwcap |= HWCAP_VXRS_PDE;
+ if (test_facility(192))
+ elf_hwcap |= HWCAP_VXRS_PDE2;
+ }
+
+ if (test_facility(150))
+ elf_hwcap |= HWCAP_SORT;
+
+ if (test_facility(151))
+ elf_hwcap |= HWCAP_DFLT;
+
+ if (test_facility(165))
+ elf_hwcap |= HWCAP_NNPA;
+
+ /* guarded storage */
+ if (MACHINE_HAS_GS)
+ elf_hwcap |= HWCAP_GS;
+
+ if (MACHINE_HAS_PCI_MIO)
+ elf_hwcap |= HWCAP_PCI_MIO;
+
+ /* virtualization support */
+ if (sclp.has_sief2)
+ elf_hwcap |= HWCAP_SIE;
+
+ return 0;
+}
+arch_initcall(setup_hwcaps);
+
+static int __init setup_elf_platform(void)
+{
+ struct cpuid cpu_id;
+
+ get_cpu_id(&cpu_id);
+ add_device_randomness(&cpu_id, sizeof(cpu_id));
+ switch (cpu_id.machine) {
+ case 0x2064:
+ case 0x2066:
+ default: /* Use "z900" as default for 64 bit kernels. */
+ strcpy(elf_platform, "z900");
+ break;
+ case 0x2084:
+ case 0x2086:
+ strcpy(elf_platform, "z990");
+ break;
+ case 0x2094:
+ case 0x2096:
+ strcpy(elf_platform, "z9-109");
+ break;
+ case 0x2097:
+ case 0x2098:
+ strcpy(elf_platform, "z10");
+ break;
+ case 0x2817:
+ case 0x2818:
+ strcpy(elf_platform, "z196");
+ break;
+ case 0x2827:
+ case 0x2828:
+ strcpy(elf_platform, "zEC12");
+ break;
+ case 0x2964:
+ case 0x2965:
+ strcpy(elf_platform, "z13");
+ break;
+ case 0x3906:
+ case 0x3907:
+ strcpy(elf_platform, "z14");
+ break;
+ case 0x8561:
+ case 0x8562:
+ strcpy(elf_platform, "z15");
+ break;
+ }
+ return 0;
+}
+arch_initcall(setup_elf_platform);
+
static void show_cpu_topology(struct seq_file *m, unsigned long n)
{
#ifdef CONFIG_SCHED_TOPOLOGY
@@ -210,7 +365,7 @@ static inline void *c_update(loff_t *pos)
static void *c_start(struct seq_file *m, loff_t *pos)
{
- get_online_cpus();
+ cpus_read_lock();
return c_update(pos);
}
@@ -222,7 +377,7 @@ static void *c_next(struct seq_file *m, void *v, loff_t *pos)
static void c_stop(struct seq_file *m, void *v)
{
- put_online_cpus();
+ cpus_read_unlock();
}
const struct seq_operations cpuinfo_op = {
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index ff0f9e838916..fe14beb338e5 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -89,27 +89,71 @@ EXPORT_SYMBOL(console_devno);
unsigned int console_irq = -1;
EXPORT_SYMBOL(console_irq);
-unsigned long elf_hwcap __read_mostly = 0;
-char elf_platform[ELF_PLATFORM_SIZE];
+/*
+ * Some code and data needs to stay below 2 GB, even when the kernel would be
+ * relocated above 2 GB, because it has to use 31 bit addresses.
+ * Such code and data is part of the .amode31 section.
+ */
+unsigned long __amode31_ref __samode31 = __pa(&_samode31);
+unsigned long __amode31_ref __eamode31 = __pa(&_eamode31);
+unsigned long __amode31_ref __stext_amode31 = __pa(&_stext_amode31);
+unsigned long __amode31_ref __etext_amode31 = __pa(&_etext_amode31);
+struct exception_table_entry __amode31_ref *__start_amode31_ex_table = _start_amode31_ex_table;
+struct exception_table_entry __amode31_ref *__stop_amode31_ex_table = _stop_amode31_ex_table;
+
+/*
+ * Control registers CR2, CR5 and CR15 are initialized with addresses
+ * of tables that must be placed below 2G which is handled by the AMODE31
+ * sections.
+ * Because the AMODE31 sections are relocated below 2G at startup,
+ * the content of control registers CR2, CR5 and CR15 must be updated
+ * with new addresses after the relocation. The initial initialization of
+ * control registers occurs in head64.S and then gets updated again after AMODE31
+ * relocation. We must access the relevant AMODE31 tables indirectly via
+ * pointers placed in the .amode31.refs linker section. Those pointers get
+ * updated automatically during AMODE31 relocation and always contain a valid
+ * address within AMODE31 sections.
+ */
+
+static __amode31_data u32 __ctl_duct_amode31[16] __aligned(64);
+
+static __amode31_data u64 __ctl_aste_amode31[8] __aligned(64) = {
+ [1] = 0xffffffffffffffff
+};
+
+static __amode31_data u32 __ctl_duald_amode31[32] __aligned(128) = {
+ 0x80000000, 0, 0, 0,
+ 0x80000000, 0, 0, 0,
+ 0x80000000, 0, 0, 0,
+ 0x80000000, 0, 0, 0,
+ 0x80000000, 0, 0, 0,
+ 0x80000000, 0, 0, 0,
+ 0x80000000, 0, 0, 0,
+ 0x80000000, 0, 0, 0
+};
+
+static __amode31_data u32 __ctl_linkage_stack_amode31[8] __aligned(64) = {
+ 0, 0, 0x89000000, 0,
+ 0, 0, 0x8a000000, 0
+};
-unsigned long int_hwcap = 0;
+static u64 __amode31_ref *__ctl_aste = __ctl_aste_amode31;
+static u32 __amode31_ref *__ctl_duald = __ctl_duald_amode31;
+static u32 __amode31_ref *__ctl_linkage_stack = __ctl_linkage_stack_amode31;
+static u32 __amode31_ref *__ctl_duct = __ctl_duct_amode31;
int __bootdata(noexec_disabled);
unsigned long __bootdata(ident_map_size);
struct mem_detect_info __bootdata(mem_detect);
+struct initrd_data __bootdata(initrd_data);
-struct exception_table_entry *__bootdata_preserved(__start_dma_ex_table);
-struct exception_table_entry *__bootdata_preserved(__stop_dma_ex_table);
-unsigned long __bootdata_preserved(__stext_dma);
-unsigned long __bootdata_preserved(__etext_dma);
-unsigned long __bootdata_preserved(__sdma);
-unsigned long __bootdata_preserved(__edma);
unsigned long __bootdata_preserved(__kaslr_offset);
unsigned int __bootdata_preserved(zlib_dfltcc_support);
EXPORT_SYMBOL(zlib_dfltcc_support);
u64 __bootdata_preserved(stfle_fac_list[16]);
EXPORT_SYMBOL(stfle_fac_list);
u64 __bootdata_preserved(alt_stfle_fac_list[16]);
+struct oldmem_data __bootdata_preserved(oldmem_data);
unsigned long VMALLOC_START;
EXPORT_SYMBOL(VMALLOC_START);
@@ -254,7 +298,7 @@ static void __init setup_zfcpdump(void)
{
if (!is_ipl_type_dump())
return;
- if (OLDMEM_BASE)
+ if (oldmem_data.start)
return;
strcat(boot_command_line, " cio_ignore=all,!ipldev,!condev");
console_loglevel = 2;
@@ -421,7 +465,7 @@ static void __init setup_lowcore_dat_off(void)
lc->restart_stack = (unsigned long) restart_stack;
lc->restart_fn = (unsigned long) do_restart;
lc->restart_data = 0;
- lc->restart_source = -1UL;
+ lc->restart_source = -1U;
mcck_stack = (unsigned long)memblock_alloc(THREAD_SIZE, THREAD_SIZE);
if (!mcck_stack)
@@ -450,12 +494,19 @@ static void __init setup_lowcore_dat_off(void)
static void __init setup_lowcore_dat_on(void)
{
+ struct lowcore *lc = lowcore_ptr[0];
+
__ctl_clear_bit(0, 28);
S390_lowcore.external_new_psw.mask |= PSW_MASK_DAT;
S390_lowcore.svc_new_psw.mask |= PSW_MASK_DAT;
S390_lowcore.program_new_psw.mask |= PSW_MASK_DAT;
S390_lowcore.io_new_psw.mask |= PSW_MASK_DAT;
+ __ctl_store(S390_lowcore.cregs_save_area, 0, 15);
__ctl_set_bit(0, 28);
+ mem_assign_absolute(S390_lowcore.restart_flags, RESTART_FLAG_CTLREGS);
+ mem_assign_absolute(S390_lowcore.program_new_psw, lc->program_new_psw);
+ memcpy_absolute(&S390_lowcore.cregs_save_area, lc->cregs_save_area,
+ sizeof(S390_lowcore.cregs_save_area));
}
static struct resource code_resource = {
@@ -610,9 +661,9 @@ static void __init reserve_crashkernel(void)
return;
}
- low = crash_base ?: OLDMEM_BASE;
+ low = crash_base ?: oldmem_data.start;
high = low + crash_size;
- if (low >= OLDMEM_BASE && high <= OLDMEM_BASE + OLDMEM_SIZE) {
+ if (low >= oldmem_data.start && high <= oldmem_data.start + oldmem_data.size) {
/* The crashkernel fits into OLDMEM, reuse OLDMEM */
crash_base = low;
} else {
@@ -639,7 +690,7 @@ static void __init reserve_crashkernel(void)
if (register_memory_notifier(&kdump_mem_nb))
return;
- if (!OLDMEM_BASE && MACHINE_IS_VM)
+ if (!oldmem_data.start && MACHINE_IS_VM)
diag10_range(PFN_DOWN(crash_base), PFN_DOWN(crash_size));
crashk_res.start = crash_base;
crashk_res.end = crash_base + crash_size - 1;
@@ -658,11 +709,11 @@ static void __init reserve_crashkernel(void)
static void __init reserve_initrd(void)
{
#ifdef CONFIG_BLK_DEV_INITRD
- if (!INITRD_START || !INITRD_SIZE)
+ if (!initrd_data.start || !initrd_data.size)
return;
- initrd_start = INITRD_START;
- initrd_end = initrd_start + INITRD_SIZE;
- memblock_reserve(INITRD_START, INITRD_SIZE);
+ initrd_start = initrd_data.start;
+ initrd_end = initrd_start + initrd_data.size;
+ memblock_reserve(initrd_data.start, initrd_data.size);
#endif
}
@@ -732,10 +783,10 @@ static void __init memblock_add_mem_detect_info(void)
static void __init check_initrd(void)
{
#ifdef CONFIG_BLK_DEV_INITRD
- if (INITRD_START && INITRD_SIZE &&
- !memblock_is_region_memory(INITRD_START, INITRD_SIZE)) {
+ if (initrd_data.start && initrd_data.size &&
+ !memblock_is_region_memory(initrd_data.start, initrd_data.size)) {
pr_err("The initial RAM disk does not fit into the memory\n");
- memblock_free(INITRD_START, INITRD_SIZE);
+ memblock_free(initrd_data.start, initrd_data.size);
initrd_start = initrd_end = 0;
}
#endif
@@ -748,10 +799,10 @@ static void __init reserve_kernel(void)
{
unsigned long start_pfn = PFN_UP(__pa(_end));
- memblock_reserve(0, HEAD_END);
+ memblock_reserve(0, STARTUP_NORMAL_OFFSET);
+ memblock_reserve((unsigned long)sclp_early_sccb, EXT_SCCB_READ_SCP);
memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn)
- (unsigned long)_stext);
- memblock_reserve(__sdma, __edma - __sdma);
}
static void __init setup_memory(void)
@@ -771,152 +822,52 @@ static void __init setup_memory(void)
memblock_enforce_memory_limit(memblock_end_of_DRAM());
}
-/*
- * Setup hardware capabilities.
- */
-static int __init setup_hwcaps(void)
+static void __init relocate_amode31_section(void)
{
- static const int stfl_bits[6] = { 0, 2, 7, 17, 19, 21 };
- struct cpuid cpu_id;
- int i;
-
- /*
- * The store facility list bits numbers as found in the principles
- * of operation are numbered with bit 1UL<<31 as number 0 to
- * bit 1UL<<0 as number 31.
- * Bit 0: instructions named N3, "backported" to esa-mode
- * Bit 2: z/Architecture mode is active
- * Bit 7: the store-facility-list-extended facility is installed
- * Bit 17: the message-security assist is installed
- * Bit 19: the long-displacement facility is installed
- * Bit 21: the extended-immediate facility is installed
- * Bit 22: extended-translation facility 3 is installed
- * Bit 30: extended-translation facility 3 enhancement facility
- * These get translated to:
- * HWCAP_S390_ESAN3 bit 0, HWCAP_S390_ZARCH bit 1,
- * HWCAP_S390_STFLE bit 2, HWCAP_S390_MSA bit 3,
- * HWCAP_S390_LDISP bit 4, HWCAP_S390_EIMM bit 5 and
- * HWCAP_S390_ETF3EH bit 8 (22 && 30).
- */
- for (i = 0; i < 6; i++)
- if (test_facility(stfl_bits[i]))
- elf_hwcap |= 1UL << i;
-
- if (test_facility(22) && test_facility(30))
- elf_hwcap |= HWCAP_S390_ETF3EH;
-
- /*
- * Check for additional facilities with store-facility-list-extended.
- * stfle stores doublewords (8 byte) with bit 1ULL<<63 as bit 0
- * and 1ULL<<0 as bit 63. Bits 0-31 contain the same information
- * as stored by stfl, bits 32-xxx contain additional facilities.
- * How many facility words are stored depends on the number of
- * doublewords passed to the instruction. The additional facilities
- * are:
- * Bit 42: decimal floating point facility is installed
- * Bit 44: perform floating point operation facility is installed
- * translated to:
- * HWCAP_S390_DFP bit 6 (42 && 44).
- */
- if ((elf_hwcap & (1UL << 2)) && test_facility(42) && test_facility(44))
- elf_hwcap |= HWCAP_S390_DFP;
-
- /*
- * Huge page support HWCAP_S390_HPAGE is bit 7.
- */
- if (MACHINE_HAS_EDAT1)
- elf_hwcap |= HWCAP_S390_HPAGE;
-
- /*
- * 64-bit register support for 31-bit processes
- * HWCAP_S390_HIGH_GPRS is bit 9.
- */
- elf_hwcap |= HWCAP_S390_HIGH_GPRS;
-
- /*
- * Transactional execution support HWCAP_S390_TE is bit 10.
- */
- if (MACHINE_HAS_TE)
- elf_hwcap |= HWCAP_S390_TE;
-
- /*
- * Vector extension HWCAP_S390_VXRS is bit 11. The Vector extension
- * can be disabled with the "novx" parameter. Use MACHINE_HAS_VX
- * instead of facility bit 129.
- */
- if (MACHINE_HAS_VX) {
- elf_hwcap |= HWCAP_S390_VXRS;
- if (test_facility(134))
- elf_hwcap |= HWCAP_S390_VXRS_BCD;
- if (test_facility(135))
- elf_hwcap |= HWCAP_S390_VXRS_EXT;
- if (test_facility(148))
- elf_hwcap |= HWCAP_S390_VXRS_EXT2;
- if (test_facility(152))
- elf_hwcap |= HWCAP_S390_VXRS_PDE;
- }
- if (test_facility(150))
- elf_hwcap |= HWCAP_S390_SORT;
- if (test_facility(151))
- elf_hwcap |= HWCAP_S390_DFLT;
-
- /*
- * Guarded storage support HWCAP_S390_GS is bit 12.
- */
- if (MACHINE_HAS_GS)
- elf_hwcap |= HWCAP_S390_GS;
-
- get_cpu_id(&cpu_id);
- add_device_randomness(&cpu_id, sizeof(cpu_id));
- switch (cpu_id.machine) {
- case 0x2064:
- case 0x2066:
- default: /* Use "z900" as default for 64 bit kernels. */
- strcpy(elf_platform, "z900");
- break;
- case 0x2084:
- case 0x2086:
- strcpy(elf_platform, "z990");
- break;
- case 0x2094:
- case 0x2096:
- strcpy(elf_platform, "z9-109");
- break;
- case 0x2097:
- case 0x2098:
- strcpy(elf_platform, "z10");
- break;
- case 0x2817:
- case 0x2818:
- strcpy(elf_platform, "z196");
- break;
- case 0x2827:
- case 0x2828:
- strcpy(elf_platform, "zEC12");
- break;
- case 0x2964:
- case 0x2965:
- strcpy(elf_platform, "z13");
- break;
- case 0x3906:
- case 0x3907:
- strcpy(elf_platform, "z14");
- break;
- case 0x8561:
- case 0x8562:
- strcpy(elf_platform, "z15");
- break;
- }
-
- /*
- * Virtualization support HWCAP_INT_SIE is bit 0.
- */
- if (sclp.has_sief2)
- int_hwcap |= HWCAP_INT_SIE;
+ unsigned long amode31_addr, amode31_size;
+ long amode31_offset;
+ long *ptr;
+
+ /* Allocate a new AMODE31 capable memory region */
+ amode31_size = __eamode31 - __samode31;
+ pr_info("Relocating AMODE31 section of size 0x%08lx\n", amode31_size);
+ amode31_addr = (unsigned long)memblock_alloc_low(amode31_size, PAGE_SIZE);
+ if (!amode31_addr)
+ panic("Failed to allocate memory for AMODE31 section\n");
+ amode31_offset = amode31_addr - __samode31;
+
+ /* Move original AMODE31 section to the new one */
+ memmove((void *)amode31_addr, (void *)__samode31, amode31_size);
+ /* Zero out the old AMODE31 section to catch invalid accesses within it */
+ memset((void *)__samode31, 0, amode31_size);
+
+ /* Update all AMODE31 region references */
+ for (ptr = _start_amode31_refs; ptr != _end_amode31_refs; ptr++)
+ *ptr += amode31_offset;
+}
- return 0;
+/* This must be called after AMODE31 relocation */
+static void __init setup_cr(void)
+{
+ union ctlreg2 cr2;
+ union ctlreg5 cr5;
+ union ctlreg15 cr15;
+
+ __ctl_duct[1] = (unsigned long)__ctl_aste;
+ __ctl_duct[2] = (unsigned long)__ctl_aste;
+ __ctl_duct[4] = (unsigned long)__ctl_duald;
+
+ /* Update control registers CR2, CR5 and CR15 */
+ __ctl_store(cr2.val, 2, 2);
+ __ctl_store(cr5.val, 5, 5);
+ __ctl_store(cr15.val, 15, 15);
+ cr2.ducto = (unsigned long)__ctl_duct >> 6;
+ cr5.pasteo = (unsigned long)__ctl_duct >> 6;
+ cr15.lsea = (unsigned long)__ctl_linkage_stack >> 3;
+ __ctl_load(cr2.val, 2, 2);
+ __ctl_load(cr5.val, 5, 5);
+ __ctl_load(cr15.val, 15, 15);
}
-arch_initcall(setup_hwcaps);
/*
* Add system information as device randomness
@@ -1059,6 +1010,9 @@ void __init setup_arch(char **cmdline_p)
free_mem_detect_info();
+ relocate_amode31_section();
+ setup_cr();
+
setup_uv();
setup_memory_end();
setup_memory();
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 78ef53b29958..307f5d99514d 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -533,9 +533,3 @@ void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal)
*/
restore_saved_sigmask();
}
-
-void do_notify_resume(struct pt_regs *regs)
-{
- tracehook_notify_resume(regs);
- rseq_handle_notify_resume(NULL, regs);
-}
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 8984711f72ed..2a991e43ead3 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -252,6 +252,7 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
cpumask_set_cpu(cpu, &init_mm.context.cpu_attach_mask);
cpumask_set_cpu(cpu, mm_cpumask(&init_mm));
lc->cpu_nr = cpu;
+ lc->restart_flags = RESTART_FLAG_CTLREGS;
lc->spinlock_lockval = arch_spin_lockval(cpu);
lc->spinlock_index = 0;
lc->percpu_offset = __per_cpu_offset[cpu];
@@ -294,10 +295,10 @@ static void pcpu_start_fn(struct pcpu *pcpu, void (*func)(void *), void *data)
cpu = pcpu - pcpu_devices;
lc = lowcore_ptr[cpu];
- lc->restart_stack = lc->nodat_stack;
+ lc->restart_stack = lc->kernel_stack;
lc->restart_fn = (unsigned long) func;
lc->restart_data = (unsigned long) data;
- lc->restart_source = -1UL;
+ lc->restart_source = -1U;
pcpu_sigp_retry(pcpu, SIGP_RESTART, 0);
}
@@ -311,12 +312,12 @@ static void __pcpu_delegate(pcpu_delegate_fn *func, void *data)
func(data); /* should not return */
}
-static void __no_sanitize_address pcpu_delegate(struct pcpu *pcpu,
- pcpu_delegate_fn *func,
- void *data, unsigned long stack)
+static void pcpu_delegate(struct pcpu *pcpu,
+ pcpu_delegate_fn *func,
+ void *data, unsigned long stack)
{
struct lowcore *lc = lowcore_ptr[pcpu - pcpu_devices];
- unsigned long source_cpu = stap();
+ unsigned int source_cpu = stap();
__load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT);
if (pcpu->address == source_cpu) {
@@ -569,6 +570,9 @@ static void smp_ctl_bit_callback(void *info)
__ctl_load(cregs, 0, 15);
}
+static DEFINE_SPINLOCK(ctl_lock);
+static unsigned long ctlreg;
+
/*
* Set a bit in a control register of all cpus
*/
@@ -576,6 +580,11 @@ void smp_ctl_set_bit(int cr, int bit)
{
struct ec_creg_mask_parms parms = { 1UL << bit, -1UL, cr };
+ spin_lock(&ctl_lock);
+ memcpy_absolute(&ctlreg, &S390_lowcore.cregs_save_area[cr], sizeof(ctlreg));
+ __set_bit(bit, &ctlreg);
+ memcpy_absolute(&S390_lowcore.cregs_save_area[cr], &ctlreg, sizeof(ctlreg));
+ spin_unlock(&ctl_lock);
on_each_cpu(smp_ctl_bit_callback, &parms, 1);
}
EXPORT_SYMBOL(smp_ctl_set_bit);
@@ -587,6 +596,11 @@ void smp_ctl_clear_bit(int cr, int bit)
{
struct ec_creg_mask_parms parms = { 0, ~(1UL << bit), cr };
+ spin_lock(&ctl_lock);
+ memcpy_absolute(&ctlreg, &S390_lowcore.cregs_save_area[cr], sizeof(ctlreg));
+ __clear_bit(bit, &ctlreg);
+ memcpy_absolute(&S390_lowcore.cregs_save_area[cr], &ctlreg, sizeof(ctlreg));
+ spin_unlock(&ctl_lock);
on_each_cpu(smp_ctl_bit_callback, &parms, 1);
}
EXPORT_SYMBOL(smp_ctl_clear_bit);
@@ -673,7 +687,7 @@ void __init smp_save_dump_cpus(void)
unsigned long page;
bool is_boot_cpu;
- if (!(OLDMEM_BASE || is_ipl_type_dump()))
+ if (!(oldmem_data.start || is_ipl_type_dump()))
/* No previous system present, normal boot. */
return;
/* Allocate a page as dumping area for the store status sigps */
@@ -704,12 +718,12 @@ void __init smp_save_dump_cpus(void)
* these registers an SCLP request is required which is
* done by drivers/s390/char/zcore.c:init_cpu_info()
*/
- if (!is_boot_cpu || OLDMEM_BASE)
+ if (!is_boot_cpu || oldmem_data.start)
/* Get the CPU registers */
smp_save_cpu_regs(sa, addr, is_boot_cpu, page);
}
memblock_free(page, PAGE_SIZE);
- diag_dma_ops.diag308_reset();
+ diag_amode31_ops.diag308_reset();
pcpu_set_smt(0);
}
#endif /* CONFIG_CRASH_DUMP */
@@ -793,7 +807,7 @@ static int __smp_rescan_cpus(struct sclp_core_info *info, bool early)
u16 core_id;
int nr, i;
- get_online_cpus();
+ cpus_read_lock();
mutex_lock(&smp_cpu_state_mutex);
nr = 0;
cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
@@ -816,7 +830,7 @@ static int __smp_rescan_cpus(struct sclp_core_info *info, bool early)
nr += smp_add_core(&info->core[i], &avail, configured, early);
}
mutex_unlock(&smp_cpu_state_mutex);
- put_online_cpus();
+ cpus_read_unlock();
return nr;
}
@@ -868,11 +882,19 @@ void __init smp_detect_cpus(void)
memblock_free_early((unsigned long)info, sizeof(*info));
}
-static void smp_init_secondary(void)
+/*
+ * Activate a secondary processor.
+ */
+static void smp_start_secondary(void *cpuvoid)
{
int cpu = raw_smp_processor_id();
S390_lowcore.last_update_clock = get_tod_clock();
+ S390_lowcore.restart_stack = (unsigned long)restart_stack;
+ S390_lowcore.restart_fn = (unsigned long)do_restart;
+ S390_lowcore.restart_data = 0;
+ S390_lowcore.restart_source = -1U;
+ S390_lowcore.restart_flags = 0;
restore_access_regs(S390_lowcore.access_regs_save_area);
cpu_init();
rcu_cpu_starting(cpu);
@@ -892,20 +914,6 @@ static void smp_init_secondary(void)
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
-/*
- * Activate a secondary processor.
- */
-static void __no_sanitize_address smp_start_secondary(void *cpuvoid)
-{
- S390_lowcore.restart_stack = (unsigned long) restart_stack;
- S390_lowcore.restart_fn = (unsigned long) do_restart;
- S390_lowcore.restart_data = 0;
- S390_lowcore.restart_source = -1UL;
- __ctl_load(S390_lowcore.cregs_save_area, 0, 15);
- __load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT);
- call_on_stack_noreturn(smp_init_secondary, S390_lowcore.kernel_stack);
-}
-
/* Upping and downing of CPUs */
int __cpu_up(unsigned int cpu, struct task_struct *tidle)
{
@@ -1055,7 +1063,7 @@ static ssize_t cpu_configure_store(struct device *dev,
return -EINVAL;
if (val != 0 && val != 1)
return -EINVAL;
- get_online_cpus();
+ cpus_read_lock();
mutex_lock(&smp_cpu_state_mutex);
rc = -EBUSY;
/* disallow configuration changes of online cpus and cpu 0 */
@@ -1104,7 +1112,7 @@ static ssize_t cpu_configure_store(struct device *dev,
}
out:
mutex_unlock(&smp_cpu_state_mutex);
- put_online_cpus();
+ cpus_read_unlock();
return rc ? rc : count;
}
static DEVICE_ATTR(configure, 0644, cpu_configure_show, cpu_configure_store);
diff --git a/arch/s390/boot/text_dma.S b/arch/s390/kernel/text_amode31.S
index 5ff5fee02801..868e4a604110 100644
--- a/arch/s390/boot/text_dma.S
+++ b/arch/s390/kernel/text_amode31.S
@@ -9,14 +9,14 @@
#include <asm/errno.h>
#include <asm/sigp.h>
- .section .dma.text,"ax"
+ .section .amode31.text,"ax"
/*
* Simplified version of expoline thunk. The normal thunks can not be used here,
* because they might be more than 2 GB away, and not reachable by the relative
* branch. No comdat, exrl, etc. optimizations used here, because it only
* affects a few functions that are not performance-relevant.
*/
- .macro BR_EX_DMA_r14
+ .macro BR_EX_AMODE31_r14
larl %r1,0f
ex 0,0(%r1)
j .
@@ -24,9 +24,9 @@
.endm
/*
- * int _diag14_dma(unsigned long rx, unsigned long ry1, unsigned long subcode)
+ * int _diag14_amode31(unsigned long rx, unsigned long ry1, unsigned long subcode)
*/
-ENTRY(_diag14_dma)
+ENTRY(_diag14_amode31)
lgr %r1,%r2
lgr %r2,%r3
lgr %r3,%r4
@@ -39,14 +39,14 @@ ENTRY(_diag14_dma)
.Ldiag14_fault:
sam64
lgfr %r2,%r5
- BR_EX_DMA_r14
- EX_TABLE_DMA(.Ldiag14_ex, .Ldiag14_fault)
-ENDPROC(_diag14_dma)
+ BR_EX_AMODE31_r14
+ EX_TABLE_AMODE31(.Ldiag14_ex, .Ldiag14_fault)
+ENDPROC(_diag14_amode31)
/*
- * int _diag210_dma(struct diag210 *addr)
+ * int _diag210_amode31(struct diag210 *addr)
*/
-ENTRY(_diag210_dma)
+ENTRY(_diag210_amode31)
lgr %r1,%r2
lhi %r2,-1
sam31
@@ -57,40 +57,40 @@ ENTRY(_diag210_dma)
.Ldiag210_fault:
sam64
lgfr %r2,%r2
- BR_EX_DMA_r14
- EX_TABLE_DMA(.Ldiag210_ex, .Ldiag210_fault)
-ENDPROC(_diag210_dma)
+ BR_EX_AMODE31_r14
+ EX_TABLE_AMODE31(.Ldiag210_ex, .Ldiag210_fault)
+ENDPROC(_diag210_amode31)
/*
- * int _diag26c_dma(void *req, void *resp, enum diag26c_sc subcode)
+ * int _diag26c_amode31(void *req, void *resp, enum diag26c_sc subcode)
*/
-ENTRY(_diag26c_dma)
+ENTRY(_diag26c_amode31)
lghi %r5,-EOPNOTSUPP
sam31
diag %r2,%r4,0x26c
.Ldiag26c_ex:
sam64
lgfr %r2,%r5
- BR_EX_DMA_r14
- EX_TABLE_DMA(.Ldiag26c_ex, .Ldiag26c_ex)
-ENDPROC(_diag26c_dma)
+ BR_EX_AMODE31_r14
+ EX_TABLE_AMODE31(.Ldiag26c_ex, .Ldiag26c_ex)
+ENDPROC(_diag26c_amode31)
/*
- * void _diag0c_dma(struct hypfs_diag0c_entry *entry)
+ * void _diag0c_amode31(struct hypfs_diag0c_entry *entry)
*/
-ENTRY(_diag0c_dma)
+ENTRY(_diag0c_amode31)
sam31
diag %r2,%r2,0x0c
sam64
- BR_EX_DMA_r14
-ENDPROC(_diag0c_dma)
+ BR_EX_AMODE31_r14
+ENDPROC(_diag0c_amode31)
/*
- * void _diag308_reset_dma(void)
+ * void _diag308_reset_amode31(void)
*
* Calls diag 308 subcode 1 and continues execution
*/
-ENTRY(_diag308_reset_dma)
+ENTRY(_diag308_reset_amode31)
larl %r4,.Lctlregs # Save control registers
stctg %c0,%c15,0(%r4)
lg %r2,0(%r4) # Disable lowcore protection
@@ -107,7 +107,7 @@ ENTRY(_diag308_reset_dma)
larl %r4,.Lcontinue_psw # Save PSW flags
epsw %r2,%r3
stm %r2,%r3,0(%r4)
- larl %r4,restart_part2 # Setup restart PSW at absolute 0
+ larl %r4,.Lrestart_part2 # Setup restart PSW at absolute 0
larl %r3,.Lrestart_diag308_psw
og %r4,0(%r3) # Save PSW
lghi %r3,0
@@ -115,7 +115,7 @@ ENTRY(_diag308_reset_dma)
lghi %r1,1
lghi %r0,0
diag %r0,%r1,0x308
-restart_part2:
+.Lrestart_part2:
lhi %r0,0 # Load r0 with zero
lhi %r1,2 # Use mode 2 = ESAME (dump)
sigp %r1,%r0,SIGP_SET_ARCHITECTURE # Switch to ESAME mode
@@ -127,19 +127,21 @@ restart_part2:
larl %r4,.Lprefix # Restore prefix register
spx 0(%r4)
larl %r4,.Lcontinue_psw # Restore PSW flags
+ larl %r2,.Lcontinue
+ stg %r2,8(%r4)
lpswe 0(%r4)
.Lcontinue:
- BR_EX_DMA_r14
-ENDPROC(_diag308_reset_dma)
+ BR_EX_AMODE31_r14
+ENDPROC(_diag308_reset_amode31)
- .section .dma.data,"aw",@progbits
+ .section .amode31.data,"aw",@progbits
.align 8
.Lrestart_diag308_psw:
.long 0x00080000,0x80000000
.align 8
.Lcontinue_psw:
- .quad 0,.Lcontinue
+ .quad 0,0
.align 8
.Lctlreg0:
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 26aa2614ee35..d2458a29618f 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -406,7 +406,7 @@ static ssize_t dispatching_store(struct device *dev,
if (val != 0 && val != 1)
return -EINVAL;
rc = 0;
- get_online_cpus();
+ cpus_read_lock();
mutex_lock(&smp_cpu_state_mutex);
if (cpu_management == val)
goto out;
@@ -417,7 +417,7 @@ static ssize_t dispatching_store(struct device *dev,
topology_expect_change();
out:
mutex_unlock(&smp_cpu_state_mutex);
- put_online_cpus();
+ cpus_read_unlock();
return rc ? rc : count;
}
static DEVICE_ATTR_RW(dispatching);
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 76947275fe8b..bcefc2173de4 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -291,7 +291,7 @@ static void __init test_monitor_call(void)
void __init trap_init(void)
{
- sort_extable(__start_dma_ex_table, __stop_dma_ex_table);
+ sort_extable(__start_amode31_ex_table, __stop_amode31_ex_table);
local_mcck_enable();
test_monitor_call();
}
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index aeb0a15bcbb7..5a656c7b7a67 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -51,24 +51,9 @@ void __init setup_uv(void)
{
unsigned long uv_stor_base;
- /*
- * keep these conditions in line with has_uv_sec_stor_limit()
- */
if (!is_prot_virt_host())
return;
- if (is_prot_virt_guest()) {
- prot_virt_host = 0;
- pr_warn("Protected virtualization not available in protected guests.");
- return;
- }
-
- if (!test_facility(158)) {
- prot_virt_host = 0;
- pr_warn("Protected virtualization not supported by the hardware.");
- return;
- }
-
uv_stor_base = (unsigned long)memblock_alloc_try_nid(
uv_info.uv_base_stor_len, SZ_1M, SZ_2G,
MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE);
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index 3457dcf10396..e3e6ac5686df 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -36,6 +36,7 @@ CPPFLAGS_vdso32.lds += -P -C -U$(ARCH)
GCOV_PROFILE := n
UBSAN_SANITIZE := n
KASAN_SANITIZE := n
+KCSAN_SANITIZE := n
# Force dependency (incbin is bad)
$(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index 2a2092ce19f1..6568de236701 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -39,6 +39,7 @@ CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
GCOV_PROFILE := n
UBSAN_SANITIZE := n
KASAN_SANITIZE := n
+KCSAN_SANITIZE := n
# Force dependency (incbin is bad)
$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 4c0e19145cc6..63bdb9e1bfc1 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -5,6 +5,7 @@
#include <asm/thread_info.h>
#include <asm/page.h>
+#include <asm/ftrace.lds.h>
/*
* Put .bss..swapper_pg_dir as the first thing in .bss. This will
@@ -46,6 +47,7 @@ SECTIONS
KPROBES_TEXT
IRQENTRY_TEXT
SOFTIRQENTRY_TEXT
+ FTRACE_HOTPATCH_TRAMPOLINES_TEXT
*(.text.*_indirect_*)
*(.fixup)
*(.gnu.warning)
@@ -71,6 +73,13 @@ SECTIONS
RW_DATA(0x100, PAGE_SIZE, THREAD_SIZE)
BOOT_DATA_PRESERVED
+ . = ALIGN(8);
+ .amode31.refs : {
+ _start_amode31_refs = .;
+ *(.amode31.refs)
+ _end_amode31_refs = .;
+ }
+
_edata = .; /* End of data section */
/* will be freed after init */
@@ -136,6 +145,32 @@ SECTIONS
BOOT_DATA
+ /*
+ * .amode31 section for code, data, ex_table that need to stay
+ * below 2 GB, even when the kernel is relocated above 2 GB.
+ */
+ . = ALIGN(PAGE_SIZE);
+ _samode31 = .;
+ .amode31.text : {
+ _stext_amode31 = .;
+ *(.amode31.text)
+ *(.amode31.text.*_indirect_*)
+ . = ALIGN(PAGE_SIZE);
+ _etext_amode31 = .;
+ }
+ . = ALIGN(16);
+ .amode31.ex_table : {
+ _start_amode31_ex_table = .;
+ KEEP(*(.amode31.ex_table))
+ _stop_amode31_ex_table = .;
+ }
+ . = ALIGN(PAGE_SIZE);
+ .amode31.data : {
+ *(.amode31.data)
+ }
+ . = ALIGN(PAGE_SIZE);
+ _eamode31 = .;
+
/* early.c uses stsi, which requires page aligned data. */
. = ALIGN(PAGE_SIZE);
INIT_DATA_SECTION(0x100)
diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index f289afeb3f31..bccbf394ae7e 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -7,17 +7,10 @@
* Heiko Carstens <heiko.carstens@de.ibm.com>,
*/
-#include <linux/sched.h>
+#include <linux/processor.h>
#include <linux/delay.h>
-#include <linux/timex.h>
-#include <linux/export.h>
-#include <linux/irqflags.h>
-#include <linux/interrupt.h>
-#include <linux/jump_label.h>
-#include <linux/irq.h>
-#include <asm/vtimer.h>
#include <asm/div64.h>
-#include <asm/idle.h>
+#include <asm/timex.h>
void __delay(unsigned long loops)
{
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index e40a30647d99..0b0c8c284953 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -4,6 +4,7 @@
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/mm.h>
+#include <linux/kfence.h>
#include <linux/kasan.h>
#include <asm/ptdump.h>
#include <asm/kasan.h>
@@ -21,6 +22,10 @@ enum address_markers_idx {
IDENTITY_BEFORE_END_NR,
KERNEL_START_NR,
KERNEL_END_NR,
+#ifdef CONFIG_KFENCE
+ KFENCE_START_NR,
+ KFENCE_END_NR,
+#endif
IDENTITY_AFTER_NR,
IDENTITY_AFTER_END_NR,
#ifdef CONFIG_KASAN
@@ -40,6 +45,10 @@ static struct addr_marker address_markers[] = {
[IDENTITY_BEFORE_END_NR] = {(unsigned long)_stext, "Identity Mapping End"},
[KERNEL_START_NR] = {(unsigned long)_stext, "Kernel Image Start"},
[KERNEL_END_NR] = {(unsigned long)_end, "Kernel Image End"},
+#ifdef CONFIG_KFENCE
+ [KFENCE_START_NR] = {0, "KFence Pool Start"},
+ [KFENCE_END_NR] = {0, "KFence Pool End"},
+#endif
[IDENTITY_AFTER_NR] = {(unsigned long)_end, "Identity Mapping Start"},
[IDENTITY_AFTER_END_NR] = {0, "Identity Mapping End"},
#ifdef CONFIG_KASAN
@@ -248,6 +257,9 @@ static void sort_address_markers(void)
static int pt_dump_init(void)
{
+#ifdef CONFIG_KFENCE
+ unsigned long kfence_start = (unsigned long)__kfence_pool;
+#endif
/*
* Figure out the maximum virtual address being accessible with the
* kernel ASCE. We need this to keep the page table walker functions
@@ -262,6 +274,10 @@ static int pt_dump_init(void)
address_markers[VMEMMAP_END_NR].start_address = (unsigned long)vmemmap + vmemmap_size;
address_markers[VMALLOC_NR].start_address = VMALLOC_START;
address_markers[VMALLOC_END_NR].start_address = VMALLOC_END;
+#ifdef CONFIG_KFENCE
+ address_markers[KFENCE_START_NR].start_address = kfence_start;
+ address_markers[KFENCE_END_NR].start_address = kfence_start + KFENCE_POOL_SIZE;
+#endif
sort_address_markers();
#ifdef CONFIG_PTDUMP_DEBUGFS
debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index e33c43b38afe..212632d57db9 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -31,6 +31,7 @@
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/hugetlb.h>
+#include <linux/kfence.h>
#include <asm/asm-offsets.h>
#include <asm/diag.h>
#include <asm/gmap.h>
@@ -230,8 +231,8 @@ const struct exception_table_entry *s390_search_extables(unsigned long addr)
{
const struct exception_table_entry *fixup;
- fixup = search_extable(__start_dma_ex_table,
- __stop_dma_ex_table - __start_dma_ex_table,
+ fixup = search_extable(__start_amode31_ex_table,
+ __stop_amode31_ex_table - __start_amode31_ex_table,
addr);
if (!fixup)
fixup = search_exception_tables(addr);
@@ -356,6 +357,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
unsigned long address;
unsigned int flags;
vm_fault_t fault;
+ bool is_write;
tsk = current;
/*
@@ -369,6 +371,8 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
mm = tsk->mm;
trans_exc_code = regs->int_parm_long;
+ address = trans_exc_code & __FAIL_ADDR_MASK;
+ is_write = (trans_exc_code & store_indication) == 0x400;
/*
* Verify that the fault happened in user space, that
@@ -379,6 +383,8 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
type = get_fault_type(regs);
switch (type) {
case KERNEL_FAULT:
+ if (kfence_handle_page_fault(address, is_write, regs))
+ return 0;
goto out;
case USER_FAULT:
case GMAP_FAULT:
@@ -387,12 +393,11 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
break;
}
- address = trans_exc_code & __FAIL_ADDR_MASK;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
flags = FAULT_FLAG_DEFAULT;
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
- if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
+ if (access == VM_WRITE || is_write)
flags |= FAULT_FLAG_WRITE;
mmap_read_lock(mm);
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 8ac710de1ab1..f3db3caa8447 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -34,6 +34,7 @@
#include <asm/processor.h>
#include <linux/uaccess.h>
#include <asm/pgalloc.h>
+#include <asm/kfence.h>
#include <asm/ptdump.h>
#include <asm/dma.h>
#include <asm/lowcore.h>
@@ -200,7 +201,7 @@ void __init mem_init(void)
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
pv_init();
-
+ kfence_split_mapping();
/* Setup guest page hinting */
cmma_init();
diff --git a/arch/s390/mm/kasan_init.c b/arch/s390/mm/kasan_init.c
index a0fdc6dc5f9d..3e4735168019 100644
--- a/arch/s390/mm/kasan_init.c
+++ b/arch/s390/mm/kasan_init.c
@@ -107,6 +107,9 @@ static void __init kasan_early_pgtable_populate(unsigned long address,
sgt_prot &= ~_SEGMENT_ENTRY_NOEXEC;
}
+ /*
+ * The first 1MB of 1:1 mapping is mapped with 4KB pages
+ */
while (address < end) {
pg_dir = pgd_offset_k(address);
if (pgd_none(*pg_dir)) {
@@ -157,30 +160,26 @@ static void __init kasan_early_pgtable_populate(unsigned long address,
pm_dir = pmd_offset(pu_dir, address);
if (pmd_none(*pm_dir)) {
- if (mode == POPULATE_ZERO_SHADOW &&
- IS_ALIGNED(address, PMD_SIZE) &&
+ if (IS_ALIGNED(address, PMD_SIZE) &&
end - address >= PMD_SIZE) {
- pmd_populate(&init_mm, pm_dir,
- kasan_early_shadow_pte);
- address = (address + PMD_SIZE) & PMD_MASK;
- continue;
- }
- /* the first megabyte of 1:1 is mapped with 4k pages */
- if (has_edat && address && end - address >= PMD_SIZE &&
- mode != POPULATE_ZERO_SHADOW) {
- void *page;
-
- if (mode == POPULATE_ONE2ONE) {
- page = (void *)address;
- } else {
- page = kasan_early_alloc_segment();
- memset(page, 0, _SEGMENT_SIZE);
+ if (mode == POPULATE_ZERO_SHADOW) {
+ pmd_populate(&init_mm, pm_dir, kasan_early_shadow_pte);
+ address = (address + PMD_SIZE) & PMD_MASK;
+ continue;
+ } else if (has_edat && address) {
+ void *page;
+
+ if (mode == POPULATE_ONE2ONE) {
+ page = (void *)address;
+ } else {
+ page = kasan_early_alloc_segment();
+ memset(page, 0, _SEGMENT_SIZE);
+ }
+ pmd_val(*pm_dir) = __pa(page) | sgt_prot;
+ address = (address + PMD_SIZE) & PMD_MASK;
+ continue;
}
- pmd_val(*pm_dir) = __pa(page) | sgt_prot;
- address = (address + PMD_SIZE) & PMD_MASK;
- continue;
}
-
pt_dir = kasan_early_pte_alloc();
pmd_populate(&init_mm, pm_dir, pt_dir);
} else if (pmd_large(*pm_dir)) {
@@ -300,7 +299,7 @@ void __init kasan_early_init(void)
pgalloc_low = round_up((unsigned long)_end, _SEGMENT_SIZE);
if (IS_ENABLED(CONFIG_BLK_DEV_INITRD)) {
initrd_end =
- round_up(INITRD_START + INITRD_SIZE, _SEGMENT_SIZE);
+ round_up(initrd_data.start + initrd_data.size, _SEGMENT_SIZE);
pgalloc_low = max(pgalloc_low, initrd_end);
}
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index a0f54bd5e98a..9663ce3625bc 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -228,7 +228,7 @@ void *xlate_dev_mem_ptr(phys_addr_t addr)
void *bounce = (void *) addr;
unsigned long size;
- get_online_cpus();
+ cpus_read_lock();
preempt_disable();
if (is_swapped(addr)) {
size = PAGE_SIZE - (addr & ~PAGE_MASK);
@@ -237,7 +237,7 @@ void *xlate_dev_mem_ptr(phys_addr_t addr)
memcpy_absolute(bounce, (void *) addr, size);
}
preempt_enable();
- put_online_cpus();
+ cpus_read_unlock();
return bounce;
}
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index 68b153083a92..18a6381097a9 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -228,46 +228,3 @@ void arch_set_page_dat(struct page *page, int order)
return;
set_page_stable_dat(page, order);
}
-
-void arch_set_page_nodat(struct page *page, int order)
-{
- if (cmma_flag < 2)
- return;
- set_page_stable_nodat(page, order);
-}
-
-int arch_test_page_nodat(struct page *page)
-{
- unsigned char state;
-
- if (cmma_flag < 2)
- return 0;
- state = get_page_state(page);
- return !!(state & 0x20);
-}
-
-void arch_set_page_states(int make_stable)
-{
- unsigned long flags, order, t;
- struct list_head *l;
- struct page *page;
- struct zone *zone;
-
- if (!cmma_flag)
- return;
- if (make_stable)
- drain_local_pages(NULL);
- for_each_populated_zone(zone) {
- spin_lock_irqsave(&zone->lock, flags);
- for_each_migratetype_order(order, t) {
- list_for_each(l, &zone->free_area[order].free_list[t]) {
- page = list_entry(l, struct page, lru);
- if (make_stable)
- set_page_stable_dat(page, order);
- else
- set_page_unused(page, order);
- }
- }
- spin_unlock_irqrestore(&zone->lock, flags);
- }
-}
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index ed8e5b3575d5..fdc86c0e4e6c 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -8,6 +8,7 @@
#include <asm/cacheflush.h>
#include <asm/facility.h>
#include <asm/pgalloc.h>
+#include <asm/kfence.h>
#include <asm/page.h>
#include <asm/set_memory.h>
@@ -85,6 +86,8 @@ static int walk_pte_level(pmd_t *pmdp, unsigned long addr, unsigned long end,
{
pte_t *ptep, new;
+ if (flags == SET_MEMORY_4K)
+ return 0;
ptep = pte_offset_kernel(pmdp, addr);
do {
new = *ptep;
@@ -155,6 +158,7 @@ static int walk_pmd_level(pud_t *pudp, unsigned long addr, unsigned long end,
unsigned long flags)
{
unsigned long next;
+ int need_split;
pmd_t *pmdp;
int rc = 0;
@@ -164,7 +168,10 @@ static int walk_pmd_level(pud_t *pudp, unsigned long addr, unsigned long end,
return -EINVAL;
next = pmd_addr_end(addr, end);
if (pmd_large(*pmdp)) {
- if (addr & ~PMD_MASK || addr + PMD_SIZE > next) {
+ need_split = !!(flags & SET_MEMORY_4K);
+ need_split |= !!(addr & ~PMD_MASK);
+ need_split |= !!(addr + PMD_SIZE > next);
+ if (need_split) {
rc = split_pmd_page(pmdp, addr);
if (rc)
return rc;
@@ -232,6 +239,7 @@ static int walk_pud_level(p4d_t *p4d, unsigned long addr, unsigned long end,
unsigned long flags)
{
unsigned long next;
+ int need_split;
pud_t *pudp;
int rc = 0;
@@ -241,7 +249,10 @@ static int walk_pud_level(p4d_t *p4d, unsigned long addr, unsigned long end,
return -EINVAL;
next = pud_addr_end(addr, end);
if (pud_large(*pudp)) {
- if (addr & ~PUD_MASK || addr + PUD_SIZE > next) {
+ need_split = !!(flags & SET_MEMORY_4K);
+ need_split |= !!(addr & ~PUD_MASK);
+ need_split |= !!(addr + PUD_SIZE > next);
+ if (need_split) {
rc = split_pud_page(pudp, addr);
if (rc)
break;
@@ -316,7 +327,7 @@ int __set_memory(unsigned long addr, int numpages, unsigned long flags)
return change_page_attr(addr, addr + numpages * PAGE_SIZE, flags);
}
-#ifdef CONFIG_DEBUG_PAGEALLOC
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
static void ipte_range(pte_t *pte, unsigned long address, int nr)
{
@@ -340,7 +351,7 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
pte_t *pte;
for (i = 0; i < numpages;) {
- address = page_to_phys(page + i);
+ address = (unsigned long)page_to_virt(page + i);
pte = virt_to_kpte(address);
nr = (unsigned long)pte >> ilog2(sizeof(long));
nr = PTRS_PER_PTE - (nr & (PTRS_PER_PTE - 1));
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 96897fab89dc..2b1c6d916cf9 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -581,7 +581,7 @@ void __init vmem_map_init(void)
__set_memory((unsigned long)_sinittext,
(unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT,
SET_MEMORY_RO | SET_MEMORY_X);
- __set_memory(__stext_dma, (__etext_dma - __stext_dma) >> PAGE_SHIFT,
+ __set_memory(__stext_amode31, (__etext_amode31 - __stext_amode31) >> PAGE_SHIFT,
SET_MEMORY_RO | SET_MEMORY_X);
/* we need lowcore executable for our LPSWE instructions */
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index b0993e05affe..e7e6788d75a8 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -113,13 +113,16 @@ int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas,
{
u64 req = ZPCI_CREATE_REQ(zdev->fh, dmaas, ZPCI_MOD_FC_REG_IOAT);
struct zpci_fib fib = {0};
- u8 status;
+ u8 cc, status;
WARN_ON_ONCE(iota & 0x3fff);
fib.pba = base;
fib.pal = limit;
fib.iota = iota | ZPCI_IOTA_RTTO_FLAG;
- return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
+ cc = zpci_mod_fc(req, &fib, &status);
+ if (cc)
+ zpci_dbg(3, "reg ioat fid:%x, cc:%d, status:%d\n", zdev->fid, cc, status);
+ return cc;
}
/* Modify PCI: Unregister I/O address translation parameters */
@@ -130,9 +133,9 @@ int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas)
u8 cc, status;
cc = zpci_mod_fc(req, &fib, &status);
- if (cc == 3) /* Function already gone. */
- cc = 0;
- return cc ? -EIO : 0;
+ if (cc)
+ zpci_dbg(3, "unreg ioat fid:%x, cc:%d, status:%d\n", zdev->fid, cc, status);
+ return cc;
}
/* Modify PCI: Set PCI function measurement parameters */
@@ -560,9 +563,12 @@ static void zpci_cleanup_bus_resources(struct zpci_dev *zdev)
int pcibios_add_device(struct pci_dev *pdev)
{
+ struct zpci_dev *zdev = to_zpci(pdev);
struct resource *res;
int i;
+ /* The pdev has a reference to the zdev via its bus */
+ zpci_zdev_get(zdev);
if (pdev->is_physfn)
pdev->no_vf_scan = 1;
@@ -582,7 +588,10 @@ int pcibios_add_device(struct pci_dev *pdev)
void pcibios_release_device(struct pci_dev *pdev)
{
+ struct zpci_dev *zdev = to_zpci(pdev);
+
zpci_unmap_resources(pdev);
+ zpci_zdev_put(zdev);
}
int pcibios_enable_device(struct pci_dev *pdev, int mask)
@@ -653,32 +662,37 @@ void zpci_free_domain(int domain)
int zpci_enable_device(struct zpci_dev *zdev)
{
- int rc;
-
- rc = clp_enable_fh(zdev, ZPCI_NR_DMA_SPACES);
- if (rc)
- goto out;
-
- rc = zpci_dma_init_device(zdev);
- if (rc)
- goto out_dma;
+ u32 fh = zdev->fh;
+ int rc = 0;
- return 0;
-
-out_dma:
- clp_disable_fh(zdev);
-out:
+ if (clp_enable_fh(zdev, &fh, ZPCI_NR_DMA_SPACES))
+ rc = -EIO;
+ else
+ zdev->fh = fh;
return rc;
}
int zpci_disable_device(struct zpci_dev *zdev)
{
- zpci_dma_exit_device(zdev);
- /*
- * The zPCI function may already be disabled by the platform, this is
- * detected in clp_disable_fh() which becomes a no-op.
- */
- return clp_disable_fh(zdev);
+ u32 fh = zdev->fh;
+ int cc, rc = 0;
+
+ cc = clp_disable_fh(zdev, &fh);
+ if (!cc) {
+ zdev->fh = fh;
+ } else if (cc == CLP_RC_SETPCIFN_ALRDY) {
+ pr_info("Disabling PCI function %08x had no effect as it was already disabled\n",
+ zdev->fid);
+ /* Function is already disabled - update handle */
+ rc = clp_refresh_fh(zdev->fid, &fh);
+ if (!rc) {
+ zdev->fh = fh;
+ rc = -EINVAL;
+ }
+ } else {
+ rc = -EIO;
+ }
+ return rc;
}
/**
@@ -788,6 +802,11 @@ int zpci_deconfigure_device(struct zpci_dev *zdev)
if (zdev->zbus->bus)
zpci_bus_remove_device(zdev, false);
+ if (zdev->dma_table) {
+ rc = zpci_dma_exit_device(zdev);
+ if (rc)
+ return rc;
+ }
if (zdev_enabled(zdev)) {
rc = zpci_disable_device(zdev);
if (rc)
@@ -811,6 +830,8 @@ void zpci_release_device(struct kref *kref)
if (zdev->zbus->bus)
zpci_bus_remove_device(zdev, false);
+ if (zdev->dma_table)
+ zpci_dma_exit_device(zdev);
if (zdev_enabled(zdev))
zpci_disable_device(zdev);
@@ -822,7 +843,8 @@ void zpci_release_device(struct kref *kref)
case ZPCI_FN_STATE_STANDBY:
if (zdev->has_hp_slot)
zpci_exit_slot(zdev);
- zpci_cleanup_bus_resources(zdev);
+ if (zdev->has_resources)
+ zpci_cleanup_bus_resources(zdev);
zpci_bus_device_unregister(zdev);
zpci_destroy_iommu(zdev);
fallthrough;
@@ -886,7 +908,6 @@ static void zpci_mem_exit(void)
}
static unsigned int s390_pci_probe __initdata = 1;
-static unsigned int s390_pci_no_mio __initdata;
unsigned int s390_pci_force_floating __initdata;
static unsigned int s390_pci_initialized;
@@ -897,7 +918,7 @@ char * __init pcibios_setup(char *str)
return NULL;
}
if (!strcmp(str, "nomio")) {
- s390_pci_no_mio = 1;
+ S390_lowcore.machine_flags &= ~MACHINE_FLAG_PCI_MIO;
return NULL;
}
if (!strcmp(str, "force_floating")) {
@@ -928,7 +949,7 @@ static int __init pci_base_init(void)
return 0;
}
- if (test_facility(153) && !s390_pci_no_mio) {
+ if (MACHINE_HAS_PCI_MIO) {
static_branch_enable(&have_mio);
ctl_set_bit(2, 5);
}
diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c
index 9629f9779c79..5d77acbd1c87 100644
--- a/arch/s390/pci/pci_bus.c
+++ b/arch/s390/pci/pci_bus.c
@@ -49,6 +49,11 @@ static int zpci_bus_prepare_device(struct zpci_dev *zdev)
rc = zpci_enable_device(zdev);
if (rc)
return rc;
+ rc = zpci_dma_init_device(zdev);
+ if (rc) {
+ zpci_disable_device(zdev);
+ return rc;
+ }
}
if (!zdev->has_resources) {
@@ -343,11 +348,11 @@ static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev)
{
int rc = -EINVAL;
- zdev->zbus = zbus;
if (zbus->function[zdev->devfn]) {
pr_err("devfn %04x is already assigned\n", zdev->devfn);
return rc;
}
+ zdev->zbus = zbus;
zbus->function[zdev->devfn] = zdev;
zpci_nb_devices++;
@@ -367,6 +372,7 @@ static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev)
error:
zbus->function[zdev->devfn] = NULL;
+ zdev->zbus = NULL;
zpci_nb_devices--;
return rc;
}
diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h
index b877a97e6745..e359d2686178 100644
--- a/arch/s390/pci/pci_bus.h
+++ b/arch/s390/pci/pci_bus.h
@@ -22,6 +22,11 @@ static inline void zpci_zdev_put(struct zpci_dev *zdev)
kref_put(&zdev->kref, zpci_release_device);
}
+static inline void zpci_zdev_get(struct zpci_dev *zdev)
+{
+ kref_get(&zdev->kref);
+}
+
int zpci_alloc_domain(int domain);
void zpci_free_domain(int domain);
int zpci_setup_bus_resources(struct zpci_dev *zdev,
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index d3331596ddbe..51dc2215a2b7 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -212,17 +212,22 @@ out:
return rc;
}
-static int clp_refresh_fh(u32 fid);
-/*
- * Enable/Disable a given PCI function and update its function handle if
- * necessary
+/**
+ * clp_set_pci_fn() - Execute a command on a PCI function
+ * @zdev: Function that will be affected
+ * @fh: Out parameter for updated function handle
+ * @nr_dma_as: DMA address space number
+ * @command: The command code to execute
+ *
+ * Returns: 0 on success, < 0 for Linux errors (e.g. -ENOMEM), and
+ * > 0 for non-success platform responses
*/
-static int clp_set_pci_fn(struct zpci_dev *zdev, u8 nr_dma_as, u8 command)
+static int clp_set_pci_fn(struct zpci_dev *zdev, u32 *fh, u8 nr_dma_as, u8 command)
{
struct clp_req_rsp_set_pci *rrb;
int rc, retries = 100;
- u32 fid = zdev->fid;
+ *fh = 0;
rrb = clp_alloc_block(GFP_KERNEL);
if (!rrb)
return -ENOMEM;
@@ -245,17 +250,13 @@ static int clp_set_pci_fn(struct zpci_dev *zdev, u8 nr_dma_as, u8 command)
}
} while (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY);
- if (rc || rrb->response.hdr.rsp != CLP_RC_OK) {
+ if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) {
+ *fh = rrb->response.fh;
+ } else {
zpci_err("Set PCI FN:\n");
zpci_err_clp(rrb->response.hdr.rsp, rc);
- }
-
- if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) {
- zdev->fh = rrb->response.fh;
- } else if (!rc && rrb->response.hdr.rsp == CLP_RC_SETPCIFN_ALRDY &&
- rrb->response.fh == 0) {
- /* Function is already in desired state - update handle */
- rc = clp_refresh_fh(fid);
+ if (!rc)
+ rc = rrb->response.hdr.rsp;
}
clp_free_block(rrb);
return rc;
@@ -295,35 +296,62 @@ int clp_setup_writeback_mio(void)
return rc;
}
-int clp_enable_fh(struct zpci_dev *zdev, u8 nr_dma_as)
+int clp_enable_fh(struct zpci_dev *zdev, u32 *fh, u8 nr_dma_as)
{
int rc;
- rc = clp_set_pci_fn(zdev, nr_dma_as, CLP_SET_ENABLE_PCI_FN);
- zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
- if (rc)
- goto out;
-
- if (zpci_use_mio(zdev)) {
- rc = clp_set_pci_fn(zdev, nr_dma_as, CLP_SET_ENABLE_MIO);
+ rc = clp_set_pci_fn(zdev, fh, nr_dma_as, CLP_SET_ENABLE_PCI_FN);
+ zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, *fh, rc);
+ if (!rc && zpci_use_mio(zdev)) {
+ rc = clp_set_pci_fn(zdev, fh, nr_dma_as, CLP_SET_ENABLE_MIO);
zpci_dbg(3, "ena mio fid:%x, fh:%x, rc:%d\n",
- zdev->fid, zdev->fh, rc);
+ zdev->fid, *fh, rc);
if (rc)
- clp_disable_fh(zdev);
+ clp_disable_fh(zdev, fh);
}
-out:
return rc;
}
-int clp_disable_fh(struct zpci_dev *zdev)
+int clp_disable_fh(struct zpci_dev *zdev, u32 *fh)
{
int rc;
if (!zdev_enabled(zdev))
return 0;
- rc = clp_set_pci_fn(zdev, 0, CLP_SET_DISABLE_PCI_FN);
- zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
+ rc = clp_set_pci_fn(zdev, fh, 0, CLP_SET_DISABLE_PCI_FN);
+ zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, *fh, rc);
+ return rc;
+}
+
+static int clp_list_pci_req(struct clp_req_rsp_list_pci *rrb,
+ u64 *resume_token, int *nentries)
+{
+ int rc;
+
+ memset(rrb, 0, sizeof(*rrb));
+ rrb->request.hdr.len = sizeof(rrb->request);
+ rrb->request.hdr.cmd = CLP_LIST_PCI;
+ /* store as many entries as possible */
+ rrb->response.hdr.len = CLP_BLK_SIZE - LIST_PCI_HDR_LEN;
+ rrb->request.resume_token = *resume_token;
+
+ /* Get PCI function handle list */
+ rc = clp_req(rrb, CLP_LPS_PCI);
+ if (rc || rrb->response.hdr.rsp != CLP_RC_OK) {
+ zpci_err("List PCI FN:\n");
+ zpci_err_clp(rrb->response.hdr.rsp, rc);
+ return -EIO;
+ }
+
+ update_uid_checking(rrb->response.uid_checking);
+ WARN_ON_ONCE(rrb->response.entry_size !=
+ sizeof(struct clp_fh_list_entry));
+
+ *nentries = (rrb->response.hdr.len - LIST_PCI_HDR_LEN) /
+ rrb->response.entry_size;
+ *resume_token = rrb->response.resume_token;
+
return rc;
}
@@ -331,38 +359,40 @@ static int clp_list_pci(struct clp_req_rsp_list_pci *rrb, void *data,
void (*cb)(struct clp_fh_list_entry *, void *))
{
u64 resume_token = 0;
- int entries, i, rc;
+ int nentries, i, rc;
do {
- memset(rrb, 0, sizeof(*rrb));
- rrb->request.hdr.len = sizeof(rrb->request);
- rrb->request.hdr.cmd = CLP_LIST_PCI;
- /* store as many entries as possible */
- rrb->response.hdr.len = CLP_BLK_SIZE - LIST_PCI_HDR_LEN;
- rrb->request.resume_token = resume_token;
-
- /* Get PCI function handle list */
- rc = clp_req(rrb, CLP_LPS_PCI);
- if (rc || rrb->response.hdr.rsp != CLP_RC_OK) {
- zpci_err("List PCI FN:\n");
- zpci_err_clp(rrb->response.hdr.rsp, rc);
- rc = -EIO;
- goto out;
- }
+ rc = clp_list_pci_req(rrb, &resume_token, &nentries);
+ if (rc)
+ return rc;
+ for (i = 0; i < nentries; i++)
+ cb(&rrb->response.fh_list[i], data);
+ } while (resume_token);
- update_uid_checking(rrb->response.uid_checking);
- WARN_ON_ONCE(rrb->response.entry_size !=
- sizeof(struct clp_fh_list_entry));
+ return rc;
+}
- entries = (rrb->response.hdr.len - LIST_PCI_HDR_LEN) /
- rrb->response.entry_size;
+static int clp_find_pci(struct clp_req_rsp_list_pci *rrb, u32 fid,
+ struct clp_fh_list_entry *entry)
+{
+ struct clp_fh_list_entry *fh_list;
+ u64 resume_token = 0;
+ int nentries, i, rc;
- resume_token = rrb->response.resume_token;
- for (i = 0; i < entries; i++)
- cb(&rrb->response.fh_list[i], data);
+ do {
+ rc = clp_list_pci_req(rrb, &resume_token, &nentries);
+ if (rc)
+ return rc;
+ for (i = 0; i < nentries; i++) {
+ fh_list = rrb->response.fh_list;
+ if (fh_list[i].fid == fid) {
+ *entry = fh_list[i];
+ return 0;
+ }
+ }
} while (resume_token);
-out:
- return rc;
+
+ return -ENODEV;
}
static void __clp_add(struct clp_fh_list_entry *entry, void *data)
@@ -392,67 +422,41 @@ int clp_scan_pci_devices(void)
return rc;
}
-static void __clp_refresh_fh(struct clp_fh_list_entry *entry, void *data)
-{
- struct zpci_dev *zdev;
- u32 fid = *((u32 *)data);
-
- if (!entry->vendor_id || fid != entry->fid)
- return;
-
- zdev = get_zdev_by_fid(fid);
- if (!zdev)
- return;
-
- zdev->fh = entry->fh;
-}
-
/*
- * Refresh the function handle of the function matching @fid
+ * Get the current function handle of the function matching @fid
*/
-static int clp_refresh_fh(u32 fid)
+int clp_refresh_fh(u32 fid, u32 *fh)
{
struct clp_req_rsp_list_pci *rrb;
+ struct clp_fh_list_entry entry;
int rc;
rrb = clp_alloc_block(GFP_NOWAIT);
if (!rrb)
return -ENOMEM;
- rc = clp_list_pci(rrb, &fid, __clp_refresh_fh);
+ rc = clp_find_pci(rrb, fid, &entry);
+ if (!rc)
+ *fh = entry.fh;
clp_free_block(rrb);
return rc;
}
-struct clp_state_data {
- u32 fid;
- enum zpci_state state;
-};
-
-static void __clp_get_state(struct clp_fh_list_entry *entry, void *data)
-{
- struct clp_state_data *sd = data;
-
- if (entry->fid != sd->fid)
- return;
-
- sd->state = entry->config_state;
-}
-
int clp_get_state(u32 fid, enum zpci_state *state)
{
struct clp_req_rsp_list_pci *rrb;
- struct clp_state_data sd = {fid, ZPCI_FN_STATE_RESERVED};
+ struct clp_fh_list_entry entry;
int rc;
+ *state = ZPCI_FN_STATE_RESERVED;
rrb = clp_alloc_block(GFP_ATOMIC);
if (!rrb)
return -ENOMEM;
- rc = clp_list_pci(rrb, &sd, __clp_get_state);
+ rc = clp_find_pci(rrb, fid, &entry);
if (!rc)
- *state = sd.state;
+ *state = entry.config_state;
clp_free_block(rrb);
return rc;
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index ebc9a49523aa..58f2f7abea96 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -590,10 +590,11 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
}
}
- rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
- (u64) zdev->dma_table);
- if (rc)
+ if (zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
+ (u64)zdev->dma_table)) {
+ rc = -EIO;
goto free_bitmap;
+ }
return 0;
free_bitmap:
@@ -608,17 +609,25 @@ out:
return rc;
}
-void zpci_dma_exit_device(struct zpci_dev *zdev)
+int zpci_dma_exit_device(struct zpci_dev *zdev)
{
+ int cc = 0;
+
/*
* At this point, if the device is part of an IOMMU domain, this would
* be a strong hint towards a bug in the IOMMU API (common) code and/or
* simultaneous access via IOMMU and DMA API. So let's issue a warning.
*/
WARN_ON(zdev->s390_domain);
-
- if (zpci_unregister_ioat(zdev, 0))
- return;
+ if (zdev_enabled(zdev))
+ cc = zpci_unregister_ioat(zdev, 0);
+ /*
+ * cc == 3 indicates the function is gone already. This can happen
+ * if the function was deconfigured/disabled suddenly and we have not
+ * received a new handle yet.
+ */
+ if (cc && cc != 3)
+ return -EIO;
dma_cleanup_tables(zdev->dma_table);
zdev->dma_table = NULL;
@@ -626,8 +635,8 @@ void zpci_dma_exit_device(struct zpci_dev *zdev)
zdev->iommu_bitmap = NULL;
vfree(zdev->lazy_bitmap);
zdev->lazy_bitmap = NULL;
-
zdev->next_bit = 0;
+ return 0;
}
static int __init dma_alloc_cpu_table_caches(void)
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index cd447b96b4b1..c856f80cb21b 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -84,7 +84,10 @@ static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh)
/* Even though the device is already gone we still
* need to free zPCI resources as part of the disable.
*/
- zpci_disable_device(zdev);
+ if (zdev->dma_table)
+ zpci_dma_exit_device(zdev);
+ if (zdev_enabled(zdev))
+ zpci_disable_device(zdev);
zdev->state = ZPCI_FN_STATE_STANDBY;
}
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
index 9c7de9089939..3823e159bf74 100644
--- a/arch/s390/pci/pci_irq.c
+++ b/arch/s390/pci/pci_irq.c
@@ -365,10 +365,6 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev)
for_each_pci_msi_entry(msi, pdev) {
if (!msi->irq)
continue;
- if (msi->msi_attrib.is_msix)
- __pci_msix_desc_mask_irq(msi, 1);
- else
- __pci_msi_desc_mask_irq(msi, 1, 1);
irq_set_msi_desc(msi->irq, NULL);
irq_free_desc(msi->irq);
msi->msg.address_lo = 0;
diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c
index 6e2450c2b9c1..335c281811c7 100644
--- a/arch/s390/pci/pci_sysfs.c
+++ b/arch/s390/pci/pci_sysfs.c
@@ -82,13 +82,26 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
pci_lock_rescan_remove();
if (pci_dev_is_added(pdev)) {
pci_stop_and_remove_bus_device(pdev);
- ret = zpci_disable_device(zdev);
- if (ret)
- goto out;
+ if (zdev->dma_table) {
+ ret = zpci_dma_exit_device(zdev);
+ if (ret)
+ goto out;
+ }
+
+ if (zdev_enabled(zdev)) {
+ ret = zpci_disable_device(zdev);
+ if (ret)
+ goto out;
+ }
ret = zpci_enable_device(zdev);
if (ret)
goto out;
+ ret = zpci_dma_init_device(zdev);
+ if (ret) {
+ zpci_disable_device(zdev);
+ goto out;
+ }
pci_rescan_bus(zdev->zbus->bus);
}
out:
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index 21c4ebe29b9a..360ada80d20c 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -19,6 +19,7 @@ KCOV_INSTRUMENT := n
GCOV_PROFILE := n
UBSAN_SANITIZE := n
KASAN_SANITIZE := n
+KCSAN_SANITIZE := n
KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
diff --git a/arch/s390/tools/opcodes.txt b/arch/s390/tools/opcodes.txt
index 0e207c46e8da..6db9820d104a 100644
--- a/arch/s390/tools/opcodes.txt
+++ b/arch/s390/tools/opcodes.txt
@@ -189,6 +189,8 @@ ad stosm SI_URD
ae sigp RS_RRRD
af mc SI_URD
b1 lra RX_RRRD
+b200 lbear S_RD
+b201 stbear S_RD
b202 stidp S_RD
b204 sck S_RD
b205 stck S_RD
@@ -523,6 +525,7 @@ b931 clgfr RRE_RR
b938 sortl RRE_RR
b939 dfltcc RRF_R0RR2
b93a kdsa RRE_RR
+b93b nnpa RRE_00
b93c ppno RRE_RR
b93e kimd RRE_RR
b93f klmd RRE_RR
@@ -562,6 +565,7 @@ b987 dlgr RRE_RR
b988 alcgr RRE_RR
b989 slbgr RRE_RR
b98a cspg RRE_RR
+b98b rdp RRF_RURR2
b98d epsw RRE_RR
b98e idte RRF_RURR2
b98f crdte RRF_RURR2
@@ -876,19 +880,32 @@ e63d vstrl VSI_URDV
e63f vstrlr VRS_RRDV
e649 vlip VRI_V0UU2
e650 vcvb VRR_RV0UU
+e651 vclzdp VRR_VV0U2
e652 vcvbg VRR_RV0UU
+e654 vupkzh VRR_VV0U2
+e655 vcnf VRR_VV0UU2
+e656 vclfnh VRR_VV0UU2
e658 vcvd VRI_VR0UU
e659 vsrp VRI_VVUUU2
e65a vcvdg VRI_VR0UU
e65b vpsop VRI_VVUUU2
+e65c vupkzl VRR_VV0U2
+e65d vcfn VRR_VV0UU2
+e65e vclfnl VRR_VV0UU2
e65f vtp VRR_0V
+e670 vpkzr VRI_VVV0UU2
e671 vap VRI_VVV0UU2
+e672 vsrpr VRI_VVV0UU2
e673 vsp VRI_VVV0UU2
+e674 vschp VRR_VVV0U0U
+e675 vcrnf VRR_VVV0UU
e677 vcp VRR_0VV0U
e678 vmp VRI_VVV0UU2
e679 vmsp VRI_VVV0UU2
e67a vdp VRI_VVV0UU2
e67b vrp VRI_VVV0UU2
+e67c vscshp VRR_VVV
+e67d vcsph VRR_VVV0U0
e67e vsdp VRI_VVV0UU2
e700 vleb VRX_VRRDU
e701 vleh VRX_VRRDU
@@ -1081,6 +1098,7 @@ eb61 stric RSY_RDRU
eb62 mric RSY_RDRU
eb6a asi SIY_IRD
eb6e alsi SIY_IRD
+eb71 lpswey SIY_URD
eb7a agsi SIY_IRD
eb7e algsi SIY_IRD
eb80 icmh RSY_RURD
diff --git a/arch/sh/boards/mach-se/7343/irq.c b/arch/sh/boards/mach-se/7343/irq.c
index 1aedbfe32654..f9f3b14f70d5 100644
--- a/arch/sh/boards/mach-se/7343/irq.c
+++ b/arch/sh/boards/mach-se/7343/irq.c
@@ -38,7 +38,7 @@ static void se7343_irq_demux(struct irq_desc *desc)
mask = ioread16(se7343_irq_regs + PA_CPLD_ST_REG);
for_each_set_bit(bit, &mask, SE7343_FPGA_IRQ_NR)
- generic_handle_irq(irq_linear_revmap(se7343_irq_domain, bit));
+ generic_handle_domain_irq(se7343_irq_domain, bit);
chip->irq_unmask(data);
}
diff --git a/arch/sh/boards/mach-se/7722/irq.c b/arch/sh/boards/mach-se/7722/irq.c
index 6d34592767f8..efa96edd47dc 100644
--- a/arch/sh/boards/mach-se/7722/irq.c
+++ b/arch/sh/boards/mach-se/7722/irq.c
@@ -37,7 +37,7 @@ static void se7722_irq_demux(struct irq_desc *desc)
mask = ioread16(se7722_irq_regs + IRQ01_STS_REG);
for_each_set_bit(bit, &mask, SE7722_FPGA_IRQ_NR)
- generic_handle_irq(irq_linear_revmap(se7722_irq_domain, bit));
+ generic_handle_domain_irq(se7722_irq_domain, bit);
chip->irq_unmask(data);
}
diff --git a/arch/sh/boards/mach-x3proto/gpio.c b/arch/sh/boards/mach-x3proto/gpio.c
index efc992f641a6..f82d3a6a844a 100644
--- a/arch/sh/boards/mach-x3proto/gpio.c
+++ b/arch/sh/boards/mach-x3proto/gpio.c
@@ -68,7 +68,7 @@ static void x3proto_gpio_irq_handler(struct irq_desc *desc)
mask = __raw_readw(KEYDETR);
for_each_set_bit(pin, &mask, NR_BASEBOARD_GPIOS)
- generic_handle_irq(irq_linear_revmap(x3proto_irq_domain, pin));
+ generic_handle_domain_irq(x3proto_irq_domain, pin);
chip->irq_unmask(data);
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 88fb922c23a0..421fa9e38c60 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -119,6 +119,7 @@ config X86
select ARCH_WANT_HUGE_PMD_SHARE
select ARCH_WANT_LD_ORPHAN_WARN
select ARCH_WANTS_THP_SWAP if X86_64
+ select ARCH_HAS_PARANOID_L1D_FLUSH
select BUILDTIME_TABLE_SORT
select CLKEVT_I8253
select CLOCKSOURCE_VALIDATE_LAST_CYCLE
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 307fd0000a83..d82d01490dd3 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -31,8 +31,8 @@ REALMODE_CFLAGS := -m16 -g -Os -DDISABLE_BRANCH_PROFILING \
REALMODE_CFLAGS += -ffreestanding
REALMODE_CFLAGS += -fno-stack-protector
-REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -Wno-address-of-packed-member)
-REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4))
+REALMODE_CFLAGS += -Wno-address-of-packed-member
+REALMODE_CFLAGS += $(cc_stack_align4)
REALMODE_CFLAGS += $(CLANG_FLAGS)
export REALMODE_CFLAGS
@@ -48,8 +48,7 @@ export BITS
#
# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383
#
-KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow
-KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
+KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx
# Intel CET isn't enabled in the kernel
KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none)
@@ -59,9 +58,8 @@ ifeq ($(CONFIG_X86_32),y)
UTS_MACHINE := i386
CHECKFLAGS += -D__i386__
- biarch := $(call cc-option,-m32)
- KBUILD_AFLAGS += $(biarch)
- KBUILD_CFLAGS += $(biarch)
+ KBUILD_AFLAGS += -m32
+ KBUILD_CFLAGS += -m32
KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
@@ -72,7 +70,7 @@ ifeq ($(CONFIG_X86_32),y)
# Align the stack to the register width instead of using the default
# alignment of 16 bytes. This reduces stack usage and the number of
# alignment instructions.
- KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align4))
+ KBUILD_CFLAGS += $(cc_stack_align4)
# CPU-specific tuning. Anything which can be shared with UML should go here.
include arch/x86/Makefile_32.cpu
@@ -93,7 +91,6 @@ else
UTS_MACHINE := x86_64
CHECKFLAGS += -D__x86_64__
- biarch := -m64
KBUILD_AFLAGS += -m64
KBUILD_CFLAGS += -m64
@@ -104,7 +101,7 @@ else
KBUILD_CFLAGS += $(call cc-option,-falign-loops=1)
# Don't autogenerate traditional x87 instructions
- KBUILD_CFLAGS += $(call cc-option,-mno-80387)
+ KBUILD_CFLAGS += -mno-80387
KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
# By default gcc and clang use a stack alignment of 16 bytes for x86.
@@ -114,20 +111,17 @@ else
# default alignment which keep the stack *mis*aligned.
# Furthermore an alignment to the register width reduces stack usage
# and the number of alignment instructions.
- KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align8))
+ KBUILD_CFLAGS += $(cc_stack_align8)
# Use -mskip-rax-setup if supported.
KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
# FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
- cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
- cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
-
- cflags-$(CONFIG_MCORE2) += \
- $(call cc-option,-march=core2,$(call cc-option,-mtune=generic))
- cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom) \
- $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))
- cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic)
+ cflags-$(CONFIG_MK8) += -march=k8
+ cflags-$(CONFIG_MPSC) += -march=nocona
+ cflags-$(CONFIG_MCORE2) += -march=core2
+ cflags-$(CONFIG_MATOM) += -march=atom
+ cflags-$(CONFIG_GENERIC_CPU) += -mtune=generic
KBUILD_CFLAGS += $(cflags-y)
KBUILD_CFLAGS += -mno-red-zone
@@ -158,18 +152,6 @@ export CONFIG_X86_X32_ABI
ifdef CONFIG_FUNCTION_GRAPH_TRACER
ifndef CONFIG_HAVE_FENTRY
ACCUMULATE_OUTGOING_ARGS := 1
- else
- ifeq ($(call cc-option-yn, -mfentry), n)
- ACCUMULATE_OUTGOING_ARGS := 1
-
- # GCC ignores '-maccumulate-outgoing-args' when used with '-Os'.
- # If '-Os' is enabled, disable it and print a warning.
- ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
- undefine CONFIG_CC_OPTIMIZE_FOR_SIZE
- $(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE. Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.)
- endif
-
- endif
endif
endif
@@ -193,7 +175,7 @@ ifdef CONFIG_RETPOLINE
# only been fixed starting from gcc stable version 8.4.0 and
# onwards, but not for older ones. See gcc bug #86952.
ifndef CONFIG_CC_IS_CLANG
- KBUILD_CFLAGS += $(call cc-option,-fno-jump-tables)
+ KBUILD_CFLAGS += -fno-jump-tables
endif
endif
@@ -275,9 +257,10 @@ endif
$(BOOT_TARGETS): vmlinux
$(Q)$(MAKE) $(build)=$(boot) $@
-PHONY += install bzlilo
-install bzlilo:
- $(Q)$(MAKE) $(build)=$(boot) $@
+PHONY += install
+install:
+ $(CONFIG_SHELL) $(srctree)/$(boot)/install.sh $(KERNELRELEASE) \
+ $(KBUILD_IMAGE) System.map "$(INSTALL_PATH)"
PHONY += vdso_install
vdso_install:
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index dfbc26a8e924..b5aecb524a8a 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -133,7 +133,7 @@ quiet_cmd_genimage = GENIMAGE $3
cmd_genimage = $(BASH) $(srctree)/$(src)/genimage.sh $2 $3 $(obj)/bzImage \
$(obj)/mtools.conf '$(FDARGS)' $(FDINITRD)
-PHONY += bzdisk fdimage fdimage144 fdimage288 hdimage isoimage install
+PHONY += bzdisk fdimage fdimage144 fdimage288 hdimage isoimage
# This requires write access to /dev/fd0
# All images require syslinux to be installed; hdimage also requires
@@ -156,8 +156,3 @@ hdimage: $(imgdeps)
isoimage: $(imgdeps)
$(call cmd,genimage,isoimage,$(obj)/image.iso)
@$(kecho) 'Kernel: $(obj)/image.iso is ready'
-
-install:
- $(CONFIG_SHELL) $(srctree)/$(src)/install.sh \
- $(KERNELRELEASE) $(obj)/bzImage \
- System.map "$(INSTALL_PATH)"
diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S
index 95a223b3e56a..8bb92e9f4e97 100644
--- a/arch/x86/boot/compressed/efi_thunk_64.S
+++ b/arch/x86/boot/compressed/efi_thunk_64.S
@@ -5,9 +5,8 @@
* Early support for invoking 32-bit EFI services from a 64-bit kernel.
*
* Because this thunking occurs before ExitBootServices() we have to
- * restore the firmware's 32-bit GDT before we make EFI service calls,
- * since the firmware's 32-bit IDT is still currently installed and it
- * needs to be able to service interrupts.
+ * restore the firmware's 32-bit GDT and IDT before we make EFI service
+ * calls.
*
* On the plus side, we don't have to worry about mangling 64-bit
* addresses into 32-bits because we're executing with an identity
@@ -39,7 +38,7 @@ SYM_FUNC_START(__efi64_thunk)
/*
* Convert x86-64 ABI params to i386 ABI
*/
- subq $32, %rsp
+ subq $64, %rsp
movl %esi, 0x0(%rsp)
movl %edx, 0x4(%rsp)
movl %ecx, 0x8(%rsp)
@@ -49,14 +48,19 @@ SYM_FUNC_START(__efi64_thunk)
leaq 0x14(%rsp), %rbx
sgdt (%rbx)
+ addq $16, %rbx
+ sidt (%rbx)
+
/*
- * Switch to gdt with 32-bit segments. This is the firmware GDT
- * that was installed when the kernel started executing. This
- * pointer was saved at the EFI stub entry point in head_64.S.
+ * Switch to IDT and GDT with 32-bit segments. This is the firmware GDT
+ * and IDT that was installed when the kernel started executing. The
+ * pointers were saved at the EFI stub entry point in head_64.S.
*
* Pass the saved DS selector to the 32-bit code, and use far return to
* restore the saved CS selector.
*/
+ leaq efi32_boot_idt(%rip), %rax
+ lidt (%rax)
leaq efi32_boot_gdt(%rip), %rax
lgdt (%rax)
@@ -67,7 +71,7 @@ SYM_FUNC_START(__efi64_thunk)
pushq %rax
lretq
-1: addq $32, %rsp
+1: addq $64, %rsp
movq %rdi, %rax
pop %rbx
@@ -128,10 +132,13 @@ SYM_FUNC_START_LOCAL(efi_enter32)
/*
* Some firmware will return with interrupts enabled. Be sure to
- * disable them before we switch GDTs.
+ * disable them before we switch GDTs and IDTs.
*/
cli
+ lidtl (%ebx)
+ subl $16, %ebx
+
lgdtl (%ebx)
movl %cr4, %eax
@@ -166,6 +173,11 @@ SYM_DATA_START(efi32_boot_gdt)
.quad 0
SYM_DATA_END(efi32_boot_gdt)
+SYM_DATA_START(efi32_boot_idt)
+ .word 0
+ .quad 0
+SYM_DATA_END(efi32_boot_idt)
+
SYM_DATA_START(efi32_boot_cs)
.word 0
SYM_DATA_END(efi32_boot_cs)
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index a2347ded77ea..572c535cf45b 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -319,6 +319,9 @@ SYM_INNER_LABEL(efi32_pe_stub_entry, SYM_L_LOCAL)
movw %cs, rva(efi32_boot_cs)(%ebp)
movw %ds, rva(efi32_boot_ds)(%ebp)
+ /* Store firmware IDT descriptor */
+ sidtl rva(efi32_boot_idt)(%ebp)
+
/* Disable paging */
movl %cr0, %eax
btrl $X86_CR0_PG_BIT, %eax
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index e36690778497..67c3208b668a 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -668,7 +668,7 @@ static bool process_mem_region(struct mem_vector *region,
if (slot_area_index == MAX_SLOT_AREA) {
debug_putstr("Aborted e820/efi memmap scan when walking immovable regions(slot_areas full)!\n");
- return 1;
+ return true;
}
}
#endif
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index d0959e7b809f..f307c93fc90a 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -88,6 +88,12 @@ nhpoly1305-avx2-y := nh-avx2-x86_64.o nhpoly1305-avx2-glue.o
obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o
+obj-$(CONFIG_CRYPTO_SM4_AESNI_AVX_X86_64) += sm4-aesni-avx-x86_64.o
+sm4-aesni-avx-x86_64-y := sm4-aesni-avx-asm_64.o sm4_aesni_avx_glue.o
+
+obj-$(CONFIG_CRYPTO_SM4_AESNI_AVX2_X86_64) += sm4-aesni-avx2-x86_64.o
+sm4-aesni-avx2-x86_64-y := sm4-aesni-avx2-asm_64.o sm4_aesni_avx2_glue.o
+
quiet_cmd_perlasm = PERLASM $@
cmd_perlasm = $(PERL) $< > $@
$(obj)/%.S: $(src)/%.pl FORCE
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 2144e54a6c89..0fc961bef299 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -849,6 +849,8 @@ static int xts_crypt(struct skcipher_request *req, bool encrypt)
return -EINVAL;
err = skcipher_walk_virt(&walk, req, false);
+ if (!walk.nbytes)
+ return err;
if (unlikely(tail > 0 && walk.nbytes < walk.total)) {
int blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
@@ -862,7 +864,10 @@ static int xts_crypt(struct skcipher_request *req, bool encrypt)
skcipher_request_set_crypt(&subreq, req->src, req->dst,
blocks * AES_BLOCK_SIZE, req->iv);
req = &subreq;
+
err = skcipher_walk_virt(&walk, req, false);
+ if (err)
+ return err;
} else {
tail = 0;
}
diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
new file mode 100644
index 000000000000..fa2c3f50aecb
--- /dev/null
+++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
@@ -0,0 +1,589 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * SM4 Cipher Algorithm, AES-NI/AVX optimized.
+ * as specified in
+ * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html
+ *
+ * Copyright (C) 2018 Markku-Juhani O. Saarinen <mjos@iki.fi>
+ * Copyright (C) 2020 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
+ */
+
+/* Based on SM4 AES-NI work by libgcrypt and Markku-Juhani O. Saarinen at:
+ * https://github.com/mjosaarinen/sm4ni
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+
+#define rRIP (%rip)
+
+#define RX0 %xmm0
+#define RX1 %xmm1
+#define MASK_4BIT %xmm2
+#define RTMP0 %xmm3
+#define RTMP1 %xmm4
+#define RTMP2 %xmm5
+#define RTMP3 %xmm6
+#define RTMP4 %xmm7
+
+#define RA0 %xmm8
+#define RA1 %xmm9
+#define RA2 %xmm10
+#define RA3 %xmm11
+
+#define RB0 %xmm12
+#define RB1 %xmm13
+#define RB2 %xmm14
+#define RB3 %xmm15
+
+#define RNOT %xmm0
+#define RBSWAP %xmm1
+
+
+/* Transpose four 32-bit words between 128-bit vectors. */
+#define transpose_4x4(x0, x1, x2, x3, t1, t2) \
+ vpunpckhdq x1, x0, t2; \
+ vpunpckldq x1, x0, x0; \
+ \
+ vpunpckldq x3, x2, t1; \
+ vpunpckhdq x3, x2, x2; \
+ \
+ vpunpckhqdq t1, x0, x1; \
+ vpunpcklqdq t1, x0, x0; \
+ \
+ vpunpckhqdq x2, t2, x3; \
+ vpunpcklqdq x2, t2, x2;
+
+/* pre-SubByte transform. */
+#define transform_pre(x, lo_t, hi_t, mask4bit, tmp0) \
+ vpand x, mask4bit, tmp0; \
+ vpandn x, mask4bit, x; \
+ vpsrld $4, x, x; \
+ \
+ vpshufb tmp0, lo_t, tmp0; \
+ vpshufb x, hi_t, x; \
+ vpxor tmp0, x, x;
+
+/* post-SubByte transform. Note: x has been XOR'ed with mask4bit by
+ * 'vaeslastenc' instruction.
+ */
+#define transform_post(x, lo_t, hi_t, mask4bit, tmp0) \
+ vpandn mask4bit, x, tmp0; \
+ vpsrld $4, x, x; \
+ vpand x, mask4bit, x; \
+ \
+ vpshufb tmp0, lo_t, tmp0; \
+ vpshufb x, hi_t, x; \
+ vpxor tmp0, x, x;
+
+
+.section .rodata.cst164, "aM", @progbits, 164
+.align 16
+
+/*
+ * Following four affine transform look-up tables are from work by
+ * Markku-Juhani O. Saarinen, at https://github.com/mjosaarinen/sm4ni
+ *
+ * These allow exposing SM4 S-Box from AES SubByte.
+ */
+
+/* pre-SubByte affine transform, from SM4 field to AES field. */
+.Lpre_tf_lo_s:
+ .quad 0x9197E2E474720701, 0xC7C1B4B222245157
+.Lpre_tf_hi_s:
+ .quad 0xE240AB09EB49A200, 0xF052B91BF95BB012
+
+/* post-SubByte affine transform, from AES field to SM4 field. */
+.Lpost_tf_lo_s:
+ .quad 0x5B67F2CEA19D0834, 0xEDD14478172BBE82
+.Lpost_tf_hi_s:
+ .quad 0xAE7201DD73AFDC00, 0x11CDBE62CC1063BF
+
+/* For isolating SubBytes from AESENCLAST, inverse shift row */
+.Linv_shift_row:
+ .byte 0x00, 0x0d, 0x0a, 0x07, 0x04, 0x01, 0x0e, 0x0b
+ .byte 0x08, 0x05, 0x02, 0x0f, 0x0c, 0x09, 0x06, 0x03
+
+/* Inverse shift row + Rotate left by 8 bits on 32-bit words with vpshufb */
+.Linv_shift_row_rol_8:
+ .byte 0x07, 0x00, 0x0d, 0x0a, 0x0b, 0x04, 0x01, 0x0e
+ .byte 0x0f, 0x08, 0x05, 0x02, 0x03, 0x0c, 0x09, 0x06
+
+/* Inverse shift row + Rotate left by 16 bits on 32-bit words with vpshufb */
+.Linv_shift_row_rol_16:
+ .byte 0x0a, 0x07, 0x00, 0x0d, 0x0e, 0x0b, 0x04, 0x01
+ .byte 0x02, 0x0f, 0x08, 0x05, 0x06, 0x03, 0x0c, 0x09
+
+/* Inverse shift row + Rotate left by 24 bits on 32-bit words with vpshufb */
+.Linv_shift_row_rol_24:
+ .byte 0x0d, 0x0a, 0x07, 0x00, 0x01, 0x0e, 0x0b, 0x04
+ .byte 0x05, 0x02, 0x0f, 0x08, 0x09, 0x06, 0x03, 0x0c
+
+/* For CTR-mode IV byteswap */
+.Lbswap128_mask:
+ .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
+
+/* For input word byte-swap */
+.Lbswap32_mask:
+ .byte 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12
+
+.align 4
+/* 4-bit mask */
+.L0f0f0f0f:
+ .long 0x0f0f0f0f
+
+
+.text
+.align 16
+
+/*
+ * void sm4_aesni_avx_crypt4(const u32 *rk, u8 *dst,
+ * const u8 *src, int nblocks)
+ */
+.align 8
+SYM_FUNC_START(sm4_aesni_avx_crypt4)
+ /* input:
+ * %rdi: round key array, CTX
+ * %rsi: dst (1..4 blocks)
+ * %rdx: src (1..4 blocks)
+ * %rcx: num blocks (1..4)
+ */
+ FRAME_BEGIN
+
+ vmovdqu 0*16(%rdx), RA0;
+ vmovdqa RA0, RA1;
+ vmovdqa RA0, RA2;
+ vmovdqa RA0, RA3;
+ cmpq $2, %rcx;
+ jb .Lblk4_load_input_done;
+ vmovdqu 1*16(%rdx), RA1;
+ je .Lblk4_load_input_done;
+ vmovdqu 2*16(%rdx), RA2;
+ cmpq $3, %rcx;
+ je .Lblk4_load_input_done;
+ vmovdqu 3*16(%rdx), RA3;
+
+.Lblk4_load_input_done:
+
+ vmovdqa .Lbswap32_mask rRIP, RTMP2;
+ vpshufb RTMP2, RA0, RA0;
+ vpshufb RTMP2, RA1, RA1;
+ vpshufb RTMP2, RA2, RA2;
+ vpshufb RTMP2, RA3, RA3;
+
+ vbroadcastss .L0f0f0f0f rRIP, MASK_4BIT;
+ vmovdqa .Lpre_tf_lo_s rRIP, RTMP4;
+ vmovdqa .Lpre_tf_hi_s rRIP, RB0;
+ vmovdqa .Lpost_tf_lo_s rRIP, RB1;
+ vmovdqa .Lpost_tf_hi_s rRIP, RB2;
+ vmovdqa .Linv_shift_row rRIP, RB3;
+ vmovdqa .Linv_shift_row_rol_8 rRIP, RTMP2;
+ vmovdqa .Linv_shift_row_rol_16 rRIP, RTMP3;
+ transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1);
+
+#define ROUND(round, s0, s1, s2, s3) \
+ vbroadcastss (4*(round))(%rdi), RX0; \
+ vpxor s1, RX0, RX0; \
+ vpxor s2, RX0, RX0; \
+ vpxor s3, RX0, RX0; /* s1 ^ s2 ^ s3 ^ rk */ \
+ \
+ /* sbox, non-linear part */ \
+ transform_pre(RX0, RTMP4, RB0, MASK_4BIT, RTMP0); \
+ vaesenclast MASK_4BIT, RX0, RX0; \
+ transform_post(RX0, RB1, RB2, MASK_4BIT, RTMP0); \
+ \
+ /* linear part */ \
+ vpshufb RB3, RX0, RTMP0; \
+ vpxor RTMP0, s0, s0; /* s0 ^ x */ \
+ vpshufb RTMP2, RX0, RTMP1; \
+ vpxor RTMP1, RTMP0, RTMP0; /* x ^ rol(x,8) */ \
+ vpshufb RTMP3, RX0, RTMP1; \
+ vpxor RTMP1, RTMP0, RTMP0; /* x ^ rol(x,8) ^ rol(x,16) */ \
+ vpshufb .Linv_shift_row_rol_24 rRIP, RX0, RTMP1; \
+ vpxor RTMP1, s0, s0; /* s0 ^ x ^ rol(x,24) */ \
+ vpslld $2, RTMP0, RTMP1; \
+ vpsrld $30, RTMP0, RTMP0; \
+ vpxor RTMP0, s0, s0; \
+ /* s0 ^ x ^ rol(x,2) ^ rol(x,10) ^ rol(x,18) ^ rol(x,24) */ \
+ vpxor RTMP1, s0, s0;
+
+ leaq (32*4)(%rdi), %rax;
+.align 16
+.Lroundloop_blk4:
+ ROUND(0, RA0, RA1, RA2, RA3);
+ ROUND(1, RA1, RA2, RA3, RA0);
+ ROUND(2, RA2, RA3, RA0, RA1);
+ ROUND(3, RA3, RA0, RA1, RA2);
+ leaq (4*4)(%rdi), %rdi;
+ cmpq %rax, %rdi;
+ jne .Lroundloop_blk4;
+
+#undef ROUND
+
+ vmovdqa .Lbswap128_mask rRIP, RTMP2;
+
+ transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1);
+ vpshufb RTMP2, RA0, RA0;
+ vpshufb RTMP2, RA1, RA1;
+ vpshufb RTMP2, RA2, RA2;
+ vpshufb RTMP2, RA3, RA3;
+
+ vmovdqu RA0, 0*16(%rsi);
+ cmpq $2, %rcx;
+ jb .Lblk4_store_output_done;
+ vmovdqu RA1, 1*16(%rsi);
+ je .Lblk4_store_output_done;
+ vmovdqu RA2, 2*16(%rsi);
+ cmpq $3, %rcx;
+ je .Lblk4_store_output_done;
+ vmovdqu RA3, 3*16(%rsi);
+
+.Lblk4_store_output_done:
+ vzeroall;
+ FRAME_END
+ ret;
+SYM_FUNC_END(sm4_aesni_avx_crypt4)
+
+.align 8
+SYM_FUNC_START_LOCAL(__sm4_crypt_blk8)
+ /* input:
+ * %rdi: round key array, CTX
+ * RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3: eight parallel
+ * plaintext blocks
+ * output:
+ * RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3: eight parallel
+ * ciphertext blocks
+ */
+ FRAME_BEGIN
+
+ vmovdqa .Lbswap32_mask rRIP, RTMP2;
+ vpshufb RTMP2, RA0, RA0;
+ vpshufb RTMP2, RA1, RA1;
+ vpshufb RTMP2, RA2, RA2;
+ vpshufb RTMP2, RA3, RA3;
+ vpshufb RTMP2, RB0, RB0;
+ vpshufb RTMP2, RB1, RB1;
+ vpshufb RTMP2, RB2, RB2;
+ vpshufb RTMP2, RB3, RB3;
+
+ vbroadcastss .L0f0f0f0f rRIP, MASK_4BIT;
+ transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1);
+ transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1);
+
+#define ROUND(round, s0, s1, s2, s3, r0, r1, r2, r3) \
+ vbroadcastss (4*(round))(%rdi), RX0; \
+ vmovdqa .Lpre_tf_lo_s rRIP, RTMP4; \
+ vmovdqa .Lpre_tf_hi_s rRIP, RTMP1; \
+ vmovdqa RX0, RX1; \
+ vpxor s1, RX0, RX0; \
+ vpxor s2, RX0, RX0; \
+ vpxor s3, RX0, RX0; /* s1 ^ s2 ^ s3 ^ rk */ \
+ vmovdqa .Lpost_tf_lo_s rRIP, RTMP2; \
+ vmovdqa .Lpost_tf_hi_s rRIP, RTMP3; \
+ vpxor r1, RX1, RX1; \
+ vpxor r2, RX1, RX1; \
+ vpxor r3, RX1, RX1; /* r1 ^ r2 ^ r3 ^ rk */ \
+ \
+ /* sbox, non-linear part */ \
+ transform_pre(RX0, RTMP4, RTMP1, MASK_4BIT, RTMP0); \
+ transform_pre(RX1, RTMP4, RTMP1, MASK_4BIT, RTMP0); \
+ vmovdqa .Linv_shift_row rRIP, RTMP4; \
+ vaesenclast MASK_4BIT, RX0, RX0; \
+ vaesenclast MASK_4BIT, RX1, RX1; \
+ transform_post(RX0, RTMP2, RTMP3, MASK_4BIT, RTMP0); \
+ transform_post(RX1, RTMP2, RTMP3, MASK_4BIT, RTMP0); \
+ \
+ /* linear part */ \
+ vpshufb RTMP4, RX0, RTMP0; \
+ vpxor RTMP0, s0, s0; /* s0 ^ x */ \
+ vpshufb RTMP4, RX1, RTMP2; \
+ vmovdqa .Linv_shift_row_rol_8 rRIP, RTMP4; \
+ vpxor RTMP2, r0, r0; /* r0 ^ x */ \
+ vpshufb RTMP4, RX0, RTMP1; \
+ vpxor RTMP1, RTMP0, RTMP0; /* x ^ rol(x,8) */ \
+ vpshufb RTMP4, RX1, RTMP3; \
+ vmovdqa .Linv_shift_row_rol_16 rRIP, RTMP4; \
+ vpxor RTMP3, RTMP2, RTMP2; /* x ^ rol(x,8) */ \
+ vpshufb RTMP4, RX0, RTMP1; \
+ vpxor RTMP1, RTMP0, RTMP0; /* x ^ rol(x,8) ^ rol(x,16) */ \
+ vpshufb RTMP4, RX1, RTMP3; \
+ vmovdqa .Linv_shift_row_rol_24 rRIP, RTMP4; \
+ vpxor RTMP3, RTMP2, RTMP2; /* x ^ rol(x,8) ^ rol(x,16) */ \
+ vpshufb RTMP4, RX0, RTMP1; \
+ vpxor RTMP1, s0, s0; /* s0 ^ x ^ rol(x,24) */ \
+ /* s0 ^ x ^ rol(x,2) ^ rol(x,10) ^ rol(x,18) ^ rol(x,24) */ \
+ vpslld $2, RTMP0, RTMP1; \
+ vpsrld $30, RTMP0, RTMP0; \
+ vpxor RTMP0, s0, s0; \
+ vpxor RTMP1, s0, s0; \
+ vpshufb RTMP4, RX1, RTMP3; \
+ vpxor RTMP3, r0, r0; /* r0 ^ x ^ rol(x,24) */ \
+ /* r0 ^ x ^ rol(x,2) ^ rol(x,10) ^ rol(x,18) ^ rol(x,24) */ \
+ vpslld $2, RTMP2, RTMP3; \
+ vpsrld $30, RTMP2, RTMP2; \
+ vpxor RTMP2, r0, r0; \
+ vpxor RTMP3, r0, r0;
+
+ leaq (32*4)(%rdi), %rax;
+.align 16
+.Lroundloop_blk8:
+ ROUND(0, RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3);
+ ROUND(1, RA1, RA2, RA3, RA0, RB1, RB2, RB3, RB0);
+ ROUND(2, RA2, RA3, RA0, RA1, RB2, RB3, RB0, RB1);
+ ROUND(3, RA3, RA0, RA1, RA2, RB3, RB0, RB1, RB2);
+ leaq (4*4)(%rdi), %rdi;
+ cmpq %rax, %rdi;
+ jne .Lroundloop_blk8;
+
+#undef ROUND
+
+ vmovdqa .Lbswap128_mask rRIP, RTMP2;
+
+ transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1);
+ transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1);
+ vpshufb RTMP2, RA0, RA0;
+ vpshufb RTMP2, RA1, RA1;
+ vpshufb RTMP2, RA2, RA2;
+ vpshufb RTMP2, RA3, RA3;
+ vpshufb RTMP2, RB0, RB0;
+ vpshufb RTMP2, RB1, RB1;
+ vpshufb RTMP2, RB2, RB2;
+ vpshufb RTMP2, RB3, RB3;
+
+ FRAME_END
+ ret;
+SYM_FUNC_END(__sm4_crypt_blk8)
+
+/*
+ * void sm4_aesni_avx_crypt8(const u32 *rk, u8 *dst,
+ * const u8 *src, int nblocks)
+ */
+.align 8
+SYM_FUNC_START(sm4_aesni_avx_crypt8)
+ /* input:
+ * %rdi: round key array, CTX
+ * %rsi: dst (1..8 blocks)
+ * %rdx: src (1..8 blocks)
+ * %rcx: num blocks (1..8)
+ */
+ FRAME_BEGIN
+
+ cmpq $5, %rcx;
+ jb sm4_aesni_avx_crypt4;
+ vmovdqu (0 * 16)(%rdx), RA0;
+ vmovdqu (1 * 16)(%rdx), RA1;
+ vmovdqu (2 * 16)(%rdx), RA2;
+ vmovdqu (3 * 16)(%rdx), RA3;
+ vmovdqu (4 * 16)(%rdx), RB0;
+ vmovdqa RB0, RB1;
+ vmovdqa RB0, RB2;
+ vmovdqa RB0, RB3;
+ je .Lblk8_load_input_done;
+ vmovdqu (5 * 16)(%rdx), RB1;
+ cmpq $7, %rcx;
+ jb .Lblk8_load_input_done;
+ vmovdqu (6 * 16)(%rdx), RB2;
+ je .Lblk8_load_input_done;
+ vmovdqu (7 * 16)(%rdx), RB3;
+
+.Lblk8_load_input_done:
+ call __sm4_crypt_blk8;
+
+ cmpq $6, %rcx;
+ vmovdqu RA0, (0 * 16)(%rsi);
+ vmovdqu RA1, (1 * 16)(%rsi);
+ vmovdqu RA2, (2 * 16)(%rsi);
+ vmovdqu RA3, (3 * 16)(%rsi);
+ vmovdqu RB0, (4 * 16)(%rsi);
+ jb .Lblk8_store_output_done;
+ vmovdqu RB1, (5 * 16)(%rsi);
+ je .Lblk8_store_output_done;
+ vmovdqu RB2, (6 * 16)(%rsi);
+ cmpq $7, %rcx;
+ je .Lblk8_store_output_done;
+ vmovdqu RB3, (7 * 16)(%rsi);
+
+.Lblk8_store_output_done:
+ vzeroall;
+ FRAME_END
+ ret;
+SYM_FUNC_END(sm4_aesni_avx_crypt8)
+
+/*
+ * void sm4_aesni_avx_ctr_enc_blk8(const u32 *rk, u8 *dst,
+ * const u8 *src, u8 *iv)
+ */
+.align 8
+SYM_FUNC_START(sm4_aesni_avx_ctr_enc_blk8)
+ /* input:
+ * %rdi: round key array, CTX
+ * %rsi: dst (8 blocks)
+ * %rdx: src (8 blocks)
+ * %rcx: iv (big endian, 128bit)
+ */
+ FRAME_BEGIN
+
+ /* load IV and byteswap */
+ vmovdqu (%rcx), RA0;
+
+ vmovdqa .Lbswap128_mask rRIP, RBSWAP;
+ vpshufb RBSWAP, RA0, RTMP0; /* be => le */
+
+ vpcmpeqd RNOT, RNOT, RNOT;
+ vpsrldq $8, RNOT, RNOT; /* low: -1, high: 0 */
+
+#define inc_le128(x, minus_one, tmp) \
+ vpcmpeqq minus_one, x, tmp; \
+ vpsubq minus_one, x, x; \
+ vpslldq $8, tmp, tmp; \
+ vpsubq tmp, x, x;
+
+ /* construct IVs */
+ inc_le128(RTMP0, RNOT, RTMP2); /* +1 */
+ vpshufb RBSWAP, RTMP0, RA1;
+ inc_le128(RTMP0, RNOT, RTMP2); /* +2 */
+ vpshufb RBSWAP, RTMP0, RA2;
+ inc_le128(RTMP0, RNOT, RTMP2); /* +3 */
+ vpshufb RBSWAP, RTMP0, RA3;
+ inc_le128(RTMP0, RNOT, RTMP2); /* +4 */
+ vpshufb RBSWAP, RTMP0, RB0;
+ inc_le128(RTMP0, RNOT, RTMP2); /* +5 */
+ vpshufb RBSWAP, RTMP0, RB1;
+ inc_le128(RTMP0, RNOT, RTMP2); /* +6 */
+ vpshufb RBSWAP, RTMP0, RB2;
+ inc_le128(RTMP0, RNOT, RTMP2); /* +7 */
+ vpshufb RBSWAP, RTMP0, RB3;
+ inc_le128(RTMP0, RNOT, RTMP2); /* +8 */
+ vpshufb RBSWAP, RTMP0, RTMP1;
+
+ /* store new IV */
+ vmovdqu RTMP1, (%rcx);
+
+ call __sm4_crypt_blk8;
+
+ vpxor (0 * 16)(%rdx), RA0, RA0;
+ vpxor (1 * 16)(%rdx), RA1, RA1;
+ vpxor (2 * 16)(%rdx), RA2, RA2;
+ vpxor (3 * 16)(%rdx), RA3, RA3;
+ vpxor (4 * 16)(%rdx), RB0, RB0;
+ vpxor (5 * 16)(%rdx), RB1, RB1;
+ vpxor (6 * 16)(%rdx), RB2, RB2;
+ vpxor (7 * 16)(%rdx), RB3, RB3;
+
+ vmovdqu RA0, (0 * 16)(%rsi);
+ vmovdqu RA1, (1 * 16)(%rsi);
+ vmovdqu RA2, (2 * 16)(%rsi);
+ vmovdqu RA3, (3 * 16)(%rsi);
+ vmovdqu RB0, (4 * 16)(%rsi);
+ vmovdqu RB1, (5 * 16)(%rsi);
+ vmovdqu RB2, (6 * 16)(%rsi);
+ vmovdqu RB3, (7 * 16)(%rsi);
+
+ vzeroall;
+ FRAME_END
+ ret;
+SYM_FUNC_END(sm4_aesni_avx_ctr_enc_blk8)
+
+/*
+ * void sm4_aesni_avx_cbc_dec_blk8(const u32 *rk, u8 *dst,
+ * const u8 *src, u8 *iv)
+ */
+.align 8
+SYM_FUNC_START(sm4_aesni_avx_cbc_dec_blk8)
+ /* input:
+ * %rdi: round key array, CTX
+ * %rsi: dst (8 blocks)
+ * %rdx: src (8 blocks)
+ * %rcx: iv
+ */
+ FRAME_BEGIN
+
+ vmovdqu (0 * 16)(%rdx), RA0;
+ vmovdqu (1 * 16)(%rdx), RA1;
+ vmovdqu (2 * 16)(%rdx), RA2;
+ vmovdqu (3 * 16)(%rdx), RA3;
+ vmovdqu (4 * 16)(%rdx), RB0;
+ vmovdqu (5 * 16)(%rdx), RB1;
+ vmovdqu (6 * 16)(%rdx), RB2;
+ vmovdqu (7 * 16)(%rdx), RB3;
+
+ call __sm4_crypt_blk8;
+
+ vmovdqu (7 * 16)(%rdx), RNOT;
+ vpxor (%rcx), RA0, RA0;
+ vpxor (0 * 16)(%rdx), RA1, RA1;
+ vpxor (1 * 16)(%rdx), RA2, RA2;
+ vpxor (2 * 16)(%rdx), RA3, RA3;
+ vpxor (3 * 16)(%rdx), RB0, RB0;
+ vpxor (4 * 16)(%rdx), RB1, RB1;
+ vpxor (5 * 16)(%rdx), RB2, RB2;
+ vpxor (6 * 16)(%rdx), RB3, RB3;
+ vmovdqu RNOT, (%rcx); /* store new IV */
+
+ vmovdqu RA0, (0 * 16)(%rsi);
+ vmovdqu RA1, (1 * 16)(%rsi);
+ vmovdqu RA2, (2 * 16)(%rsi);
+ vmovdqu RA3, (3 * 16)(%rsi);
+ vmovdqu RB0, (4 * 16)(%rsi);
+ vmovdqu RB1, (5 * 16)(%rsi);
+ vmovdqu RB2, (6 * 16)(%rsi);
+ vmovdqu RB3, (7 * 16)(%rsi);
+
+ vzeroall;
+ FRAME_END
+ ret;
+SYM_FUNC_END(sm4_aesni_avx_cbc_dec_blk8)
+
+/*
+ * void sm4_aesni_avx_cfb_dec_blk8(const u32 *rk, u8 *dst,
+ * const u8 *src, u8 *iv)
+ */
+.align 8
+SYM_FUNC_START(sm4_aesni_avx_cfb_dec_blk8)
+ /* input:
+ * %rdi: round key array, CTX
+ * %rsi: dst (8 blocks)
+ * %rdx: src (8 blocks)
+ * %rcx: iv
+ */
+ FRAME_BEGIN
+
+ /* Load input */
+ vmovdqu (%rcx), RA0;
+ vmovdqu 0 * 16(%rdx), RA1;
+ vmovdqu 1 * 16(%rdx), RA2;
+ vmovdqu 2 * 16(%rdx), RA3;
+ vmovdqu 3 * 16(%rdx), RB0;
+ vmovdqu 4 * 16(%rdx), RB1;
+ vmovdqu 5 * 16(%rdx), RB2;
+ vmovdqu 6 * 16(%rdx), RB3;
+
+ /* Update IV */
+ vmovdqu 7 * 16(%rdx), RNOT;
+ vmovdqu RNOT, (%rcx);
+
+ call __sm4_crypt_blk8;
+
+ vpxor (0 * 16)(%rdx), RA0, RA0;
+ vpxor (1 * 16)(%rdx), RA1, RA1;
+ vpxor (2 * 16)(%rdx), RA2, RA2;
+ vpxor (3 * 16)(%rdx), RA3, RA3;
+ vpxor (4 * 16)(%rdx), RB0, RB0;
+ vpxor (5 * 16)(%rdx), RB1, RB1;
+ vpxor (6 * 16)(%rdx), RB2, RB2;
+ vpxor (7 * 16)(%rdx), RB3, RB3;
+
+ vmovdqu RA0, (0 * 16)(%rsi);
+ vmovdqu RA1, (1 * 16)(%rsi);
+ vmovdqu RA2, (2 * 16)(%rsi);
+ vmovdqu RA3, (3 * 16)(%rsi);
+ vmovdqu RB0, (4 * 16)(%rsi);
+ vmovdqu RB1, (5 * 16)(%rsi);
+ vmovdqu RB2, (6 * 16)(%rsi);
+ vmovdqu RB3, (7 * 16)(%rsi);
+
+ vzeroall;
+ FRAME_END
+ ret;
+SYM_FUNC_END(sm4_aesni_avx_cfb_dec_blk8)
diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
new file mode 100644
index 000000000000..d2ffd7f76ee2
--- /dev/null
+++ b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
@@ -0,0 +1,497 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SM4 Cipher Algorithm, AES-NI/AVX2 optimized.
+ * as specified in
+ * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html
+ *
+ * Copyright (C) 2018 Markku-Juhani O. Saarinen <mjos@iki.fi>
+ * Copyright (C) 2020 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
+ */
+
+/* Based on SM4 AES-NI work by libgcrypt and Markku-Juhani O. Saarinen at:
+ * https://github.com/mjosaarinen/sm4ni
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+
+#define rRIP (%rip)
+
+/* vector registers */
+#define RX0 %ymm0
+#define RX1 %ymm1
+#define MASK_4BIT %ymm2
+#define RTMP0 %ymm3
+#define RTMP1 %ymm4
+#define RTMP2 %ymm5
+#define RTMP3 %ymm6
+#define RTMP4 %ymm7
+
+#define RA0 %ymm8
+#define RA1 %ymm9
+#define RA2 %ymm10
+#define RA3 %ymm11
+
+#define RB0 %ymm12
+#define RB1 %ymm13
+#define RB2 %ymm14
+#define RB3 %ymm15
+
+#define RNOT %ymm0
+#define RBSWAP %ymm1
+
+#define RX0x %xmm0
+#define RX1x %xmm1
+#define MASK_4BITx %xmm2
+
+#define RNOTx %xmm0
+#define RBSWAPx %xmm1
+
+#define RTMP0x %xmm3
+#define RTMP1x %xmm4
+#define RTMP2x %xmm5
+#define RTMP3x %xmm6
+#define RTMP4x %xmm7
+
+
+/* helper macros */
+
+/* Transpose four 32-bit words between 128-bit vector lanes. */
+#define transpose_4x4(x0, x1, x2, x3, t1, t2) \
+ vpunpckhdq x1, x0, t2; \
+ vpunpckldq x1, x0, x0; \
+ \
+ vpunpckldq x3, x2, t1; \
+ vpunpckhdq x3, x2, x2; \
+ \
+ vpunpckhqdq t1, x0, x1; \
+ vpunpcklqdq t1, x0, x0; \
+ \
+ vpunpckhqdq x2, t2, x3; \
+ vpunpcklqdq x2, t2, x2;
+
+/* post-SubByte transform. */
+#define transform_pre(x, lo_t, hi_t, mask4bit, tmp0) \
+ vpand x, mask4bit, tmp0; \
+ vpandn x, mask4bit, x; \
+ vpsrld $4, x, x; \
+ \
+ vpshufb tmp0, lo_t, tmp0; \
+ vpshufb x, hi_t, x; \
+ vpxor tmp0, x, x;
+
+/* post-SubByte transform. Note: x has been XOR'ed with mask4bit by
+ * 'vaeslastenc' instruction. */
+#define transform_post(x, lo_t, hi_t, mask4bit, tmp0) \
+ vpandn mask4bit, x, tmp0; \
+ vpsrld $4, x, x; \
+ vpand x, mask4bit, x; \
+ \
+ vpshufb tmp0, lo_t, tmp0; \
+ vpshufb x, hi_t, x; \
+ vpxor tmp0, x, x;
+
+
+.section .rodata.cst164, "aM", @progbits, 164
+.align 16
+
+/*
+ * Following four affine transform look-up tables are from work by
+ * Markku-Juhani O. Saarinen, at https://github.com/mjosaarinen/sm4ni
+ *
+ * These allow exposing SM4 S-Box from AES SubByte.
+ */
+
+/* pre-SubByte affine transform, from SM4 field to AES field. */
+.Lpre_tf_lo_s:
+ .quad 0x9197E2E474720701, 0xC7C1B4B222245157
+.Lpre_tf_hi_s:
+ .quad 0xE240AB09EB49A200, 0xF052B91BF95BB012
+
+/* post-SubByte affine transform, from AES field to SM4 field. */
+.Lpost_tf_lo_s:
+ .quad 0x5B67F2CEA19D0834, 0xEDD14478172BBE82
+.Lpost_tf_hi_s:
+ .quad 0xAE7201DD73AFDC00, 0x11CDBE62CC1063BF
+
+/* For isolating SubBytes from AESENCLAST, inverse shift row */
+.Linv_shift_row:
+ .byte 0x00, 0x0d, 0x0a, 0x07, 0x04, 0x01, 0x0e, 0x0b
+ .byte 0x08, 0x05, 0x02, 0x0f, 0x0c, 0x09, 0x06, 0x03
+
+/* Inverse shift row + Rotate left by 8 bits on 32-bit words with vpshufb */
+.Linv_shift_row_rol_8:
+ .byte 0x07, 0x00, 0x0d, 0x0a, 0x0b, 0x04, 0x01, 0x0e
+ .byte 0x0f, 0x08, 0x05, 0x02, 0x03, 0x0c, 0x09, 0x06
+
+/* Inverse shift row + Rotate left by 16 bits on 32-bit words with vpshufb */
+.Linv_shift_row_rol_16:
+ .byte 0x0a, 0x07, 0x00, 0x0d, 0x0e, 0x0b, 0x04, 0x01
+ .byte 0x02, 0x0f, 0x08, 0x05, 0x06, 0x03, 0x0c, 0x09
+
+/* Inverse shift row + Rotate left by 24 bits on 32-bit words with vpshufb */
+.Linv_shift_row_rol_24:
+ .byte 0x0d, 0x0a, 0x07, 0x00, 0x01, 0x0e, 0x0b, 0x04
+ .byte 0x05, 0x02, 0x0f, 0x08, 0x09, 0x06, 0x03, 0x0c
+
+/* For CTR-mode IV byteswap */
+.Lbswap128_mask:
+ .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
+
+/* For input word byte-swap */
+.Lbswap32_mask:
+ .byte 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12
+
+.align 4
+/* 4-bit mask */
+.L0f0f0f0f:
+ .long 0x0f0f0f0f
+
+.text
+.align 16
+
+.align 8
+SYM_FUNC_START_LOCAL(__sm4_crypt_blk16)
+ /* input:
+ * %rdi: round key array, CTX
+ * RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3: sixteen parallel
+ * plaintext blocks
+ * output:
+ * RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3: sixteen parallel
+ * ciphertext blocks
+ */
+ FRAME_BEGIN
+
+ vbroadcasti128 .Lbswap32_mask rRIP, RTMP2;
+ vpshufb RTMP2, RA0, RA0;
+ vpshufb RTMP2, RA1, RA1;
+ vpshufb RTMP2, RA2, RA2;
+ vpshufb RTMP2, RA3, RA3;
+ vpshufb RTMP2, RB0, RB0;
+ vpshufb RTMP2, RB1, RB1;
+ vpshufb RTMP2, RB2, RB2;
+ vpshufb RTMP2, RB3, RB3;
+
+ vpbroadcastd .L0f0f0f0f rRIP, MASK_4BIT;
+ transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1);
+ transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1);
+
+#define ROUND(round, s0, s1, s2, s3, r0, r1, r2, r3) \
+ vpbroadcastd (4*(round))(%rdi), RX0; \
+ vbroadcasti128 .Lpre_tf_lo_s rRIP, RTMP4; \
+ vbroadcasti128 .Lpre_tf_hi_s rRIP, RTMP1; \
+ vmovdqa RX0, RX1; \
+ vpxor s1, RX0, RX0; \
+ vpxor s2, RX0, RX0; \
+ vpxor s3, RX0, RX0; /* s1 ^ s2 ^ s3 ^ rk */ \
+ vbroadcasti128 .Lpost_tf_lo_s rRIP, RTMP2; \
+ vbroadcasti128 .Lpost_tf_hi_s rRIP, RTMP3; \
+ vpxor r1, RX1, RX1; \
+ vpxor r2, RX1, RX1; \
+ vpxor r3, RX1, RX1; /* r1 ^ r2 ^ r3 ^ rk */ \
+ \
+ /* sbox, non-linear part */ \
+ transform_pre(RX0, RTMP4, RTMP1, MASK_4BIT, RTMP0); \
+ transform_pre(RX1, RTMP4, RTMP1, MASK_4BIT, RTMP0); \
+ vextracti128 $1, RX0, RTMP4x; \
+ vextracti128 $1, RX1, RTMP0x; \
+ vaesenclast MASK_4BITx, RX0x, RX0x; \
+ vaesenclast MASK_4BITx, RTMP4x, RTMP4x; \
+ vaesenclast MASK_4BITx, RX1x, RX1x; \
+ vaesenclast MASK_4BITx, RTMP0x, RTMP0x; \
+ vinserti128 $1, RTMP4x, RX0, RX0; \
+ vbroadcasti128 .Linv_shift_row rRIP, RTMP4; \
+ vinserti128 $1, RTMP0x, RX1, RX1; \
+ transform_post(RX0, RTMP2, RTMP3, MASK_4BIT, RTMP0); \
+ transform_post(RX1, RTMP2, RTMP3, MASK_4BIT, RTMP0); \
+ \
+ /* linear part */ \
+ vpshufb RTMP4, RX0, RTMP0; \
+ vpxor RTMP0, s0, s0; /* s0 ^ x */ \
+ vpshufb RTMP4, RX1, RTMP2; \
+ vbroadcasti128 .Linv_shift_row_rol_8 rRIP, RTMP4; \
+ vpxor RTMP2, r0, r0; /* r0 ^ x */ \
+ vpshufb RTMP4, RX0, RTMP1; \
+ vpxor RTMP1, RTMP0, RTMP0; /* x ^ rol(x,8) */ \
+ vpshufb RTMP4, RX1, RTMP3; \
+ vbroadcasti128 .Linv_shift_row_rol_16 rRIP, RTMP4; \
+ vpxor RTMP3, RTMP2, RTMP2; /* x ^ rol(x,8) */ \
+ vpshufb RTMP4, RX0, RTMP1; \
+ vpxor RTMP1, RTMP0, RTMP0; /* x ^ rol(x,8) ^ rol(x,16) */ \
+ vpshufb RTMP4, RX1, RTMP3; \
+ vbroadcasti128 .Linv_shift_row_rol_24 rRIP, RTMP4; \
+ vpxor RTMP3, RTMP2, RTMP2; /* x ^ rol(x,8) ^ rol(x,16) */ \
+ vpshufb RTMP4, RX0, RTMP1; \
+ vpxor RTMP1, s0, s0; /* s0 ^ x ^ rol(x,24) */ \
+ vpslld $2, RTMP0, RTMP1; \
+ vpsrld $30, RTMP0, RTMP0; \
+ vpxor RTMP0, s0, s0; \
+ /* s0 ^ x ^ rol(x,2) ^ rol(x,10) ^ rol(x,18) ^ rol(x,24) */ \
+ vpxor RTMP1, s0, s0; \
+ vpshufb RTMP4, RX1, RTMP3; \
+ vpxor RTMP3, r0, r0; /* r0 ^ x ^ rol(x,24) */ \
+ vpslld $2, RTMP2, RTMP3; \
+ vpsrld $30, RTMP2, RTMP2; \
+ vpxor RTMP2, r0, r0; \
+ /* r0 ^ x ^ rol(x,2) ^ rol(x,10) ^ rol(x,18) ^ rol(x,24) */ \
+ vpxor RTMP3, r0, r0;
+
+ leaq (32*4)(%rdi), %rax;
+.align 16
+.Lroundloop_blk8:
+ ROUND(0, RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3);
+ ROUND(1, RA1, RA2, RA3, RA0, RB1, RB2, RB3, RB0);
+ ROUND(2, RA2, RA3, RA0, RA1, RB2, RB3, RB0, RB1);
+ ROUND(3, RA3, RA0, RA1, RA2, RB3, RB0, RB1, RB2);
+ leaq (4*4)(%rdi), %rdi;
+ cmpq %rax, %rdi;
+ jne .Lroundloop_blk8;
+
+#undef ROUND
+
+ vbroadcasti128 .Lbswap128_mask rRIP, RTMP2;
+
+ transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1);
+ transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1);
+ vpshufb RTMP2, RA0, RA0;
+ vpshufb RTMP2, RA1, RA1;
+ vpshufb RTMP2, RA2, RA2;
+ vpshufb RTMP2, RA3, RA3;
+ vpshufb RTMP2, RB0, RB0;
+ vpshufb RTMP2, RB1, RB1;
+ vpshufb RTMP2, RB2, RB2;
+ vpshufb RTMP2, RB3, RB3;
+
+ FRAME_END
+ ret;
+SYM_FUNC_END(__sm4_crypt_blk16)
+
+#define inc_le128(x, minus_one, tmp) \
+ vpcmpeqq minus_one, x, tmp; \
+ vpsubq minus_one, x, x; \
+ vpslldq $8, tmp, tmp; \
+ vpsubq tmp, x, x;
+
+/*
+ * void sm4_aesni_avx2_ctr_enc_blk16(const u32 *rk, u8 *dst,
+ * const u8 *src, u8 *iv)
+ */
+.align 8
+SYM_FUNC_START(sm4_aesni_avx2_ctr_enc_blk16)
+ /* input:
+ * %rdi: round key array, CTX
+ * %rsi: dst (16 blocks)
+ * %rdx: src (16 blocks)
+ * %rcx: iv (big endian, 128bit)
+ */
+ FRAME_BEGIN
+
+ movq 8(%rcx), %rax;
+ bswapq %rax;
+
+ vzeroupper;
+
+ vbroadcasti128 .Lbswap128_mask rRIP, RTMP3;
+ vpcmpeqd RNOT, RNOT, RNOT;
+ vpsrldq $8, RNOT, RNOT; /* ab: -1:0 ; cd: -1:0 */
+ vpaddq RNOT, RNOT, RTMP2; /* ab: -2:0 ; cd: -2:0 */
+
+ /* load IV and byteswap */
+ vmovdqu (%rcx), RTMP4x;
+ vpshufb RTMP3x, RTMP4x, RTMP4x;
+ vmovdqa RTMP4x, RTMP0x;
+ inc_le128(RTMP4x, RNOTx, RTMP1x);
+ vinserti128 $1, RTMP4x, RTMP0, RTMP0;
+ vpshufb RTMP3, RTMP0, RA0; /* +1 ; +0 */
+
+ /* check need for handling 64-bit overflow and carry */
+ cmpq $(0xffffffffffffffff - 16), %rax;
+ ja .Lhandle_ctr_carry;
+
+ /* construct IVs */
+ vpsubq RTMP2, RTMP0, RTMP0; /* +3 ; +2 */
+ vpshufb RTMP3, RTMP0, RA1;
+ vpsubq RTMP2, RTMP0, RTMP0; /* +5 ; +4 */
+ vpshufb RTMP3, RTMP0, RA2;
+ vpsubq RTMP2, RTMP0, RTMP0; /* +7 ; +6 */
+ vpshufb RTMP3, RTMP0, RA3;
+ vpsubq RTMP2, RTMP0, RTMP0; /* +9 ; +8 */
+ vpshufb RTMP3, RTMP0, RB0;
+ vpsubq RTMP2, RTMP0, RTMP0; /* +11 ; +10 */
+ vpshufb RTMP3, RTMP0, RB1;
+ vpsubq RTMP2, RTMP0, RTMP0; /* +13 ; +12 */
+ vpshufb RTMP3, RTMP0, RB2;
+ vpsubq RTMP2, RTMP0, RTMP0; /* +15 ; +14 */
+ vpshufb RTMP3, RTMP0, RB3;
+ vpsubq RTMP2, RTMP0, RTMP0; /* +16 */
+ vpshufb RTMP3x, RTMP0x, RTMP0x;
+
+ jmp .Lctr_carry_done;
+
+.Lhandle_ctr_carry:
+ /* construct IVs */
+ inc_le128(RTMP0, RNOT, RTMP1);
+ inc_le128(RTMP0, RNOT, RTMP1);
+ vpshufb RTMP3, RTMP0, RA1; /* +3 ; +2 */
+ inc_le128(RTMP0, RNOT, RTMP1);
+ inc_le128(RTMP0, RNOT, RTMP1);
+ vpshufb RTMP3, RTMP0, RA2; /* +5 ; +4 */
+ inc_le128(RTMP0, RNOT, RTMP1);
+ inc_le128(RTMP0, RNOT, RTMP1);
+ vpshufb RTMP3, RTMP0, RA3; /* +7 ; +6 */
+ inc_le128(RTMP0, RNOT, RTMP1);
+ inc_le128(RTMP0, RNOT, RTMP1);
+ vpshufb RTMP3, RTMP0, RB0; /* +9 ; +8 */
+ inc_le128(RTMP0, RNOT, RTMP1);
+ inc_le128(RTMP0, RNOT, RTMP1);
+ vpshufb RTMP3, RTMP0, RB1; /* +11 ; +10 */
+ inc_le128(RTMP0, RNOT, RTMP1);
+ inc_le128(RTMP0, RNOT, RTMP1);
+ vpshufb RTMP3, RTMP0, RB2; /* +13 ; +12 */
+ inc_le128(RTMP0, RNOT, RTMP1);
+ inc_le128(RTMP0, RNOT, RTMP1);
+ vpshufb RTMP3, RTMP0, RB3; /* +15 ; +14 */
+ inc_le128(RTMP0, RNOT, RTMP1);
+ vextracti128 $1, RTMP0, RTMP0x;
+ vpshufb RTMP3x, RTMP0x, RTMP0x; /* +16 */
+
+.align 4
+.Lctr_carry_done:
+ /* store new IV */
+ vmovdqu RTMP0x, (%rcx);
+
+ call __sm4_crypt_blk16;
+
+ vpxor (0 * 32)(%rdx), RA0, RA0;
+ vpxor (1 * 32)(%rdx), RA1, RA1;
+ vpxor (2 * 32)(%rdx), RA2, RA2;
+ vpxor (3 * 32)(%rdx), RA3, RA3;
+ vpxor (4 * 32)(%rdx), RB0, RB0;
+ vpxor (5 * 32)(%rdx), RB1, RB1;
+ vpxor (6 * 32)(%rdx), RB2, RB2;
+ vpxor (7 * 32)(%rdx), RB3, RB3;
+
+ vmovdqu RA0, (0 * 32)(%rsi);
+ vmovdqu RA1, (1 * 32)(%rsi);
+ vmovdqu RA2, (2 * 32)(%rsi);
+ vmovdqu RA3, (3 * 32)(%rsi);
+ vmovdqu RB0, (4 * 32)(%rsi);
+ vmovdqu RB1, (5 * 32)(%rsi);
+ vmovdqu RB2, (6 * 32)(%rsi);
+ vmovdqu RB3, (7 * 32)(%rsi);
+
+ vzeroall;
+ FRAME_END
+ ret;
+SYM_FUNC_END(sm4_aesni_avx2_ctr_enc_blk16)
+
+/*
+ * void sm4_aesni_avx2_cbc_dec_blk16(const u32 *rk, u8 *dst,
+ * const u8 *src, u8 *iv)
+ */
+.align 8
+SYM_FUNC_START(sm4_aesni_avx2_cbc_dec_blk16)
+ /* input:
+ * %rdi: round key array, CTX
+ * %rsi: dst (16 blocks)
+ * %rdx: src (16 blocks)
+ * %rcx: iv
+ */
+ FRAME_BEGIN
+
+ vzeroupper;
+
+ vmovdqu (0 * 32)(%rdx), RA0;
+ vmovdqu (1 * 32)(%rdx), RA1;
+ vmovdqu (2 * 32)(%rdx), RA2;
+ vmovdqu (3 * 32)(%rdx), RA3;
+ vmovdqu (4 * 32)(%rdx), RB0;
+ vmovdqu (5 * 32)(%rdx), RB1;
+ vmovdqu (6 * 32)(%rdx), RB2;
+ vmovdqu (7 * 32)(%rdx), RB3;
+
+ call __sm4_crypt_blk16;
+
+ vmovdqu (%rcx), RNOTx;
+ vinserti128 $1, (%rdx), RNOT, RNOT;
+ vpxor RNOT, RA0, RA0;
+ vpxor (0 * 32 + 16)(%rdx), RA1, RA1;
+ vpxor (1 * 32 + 16)(%rdx), RA2, RA2;
+ vpxor (2 * 32 + 16)(%rdx), RA3, RA3;
+ vpxor (3 * 32 + 16)(%rdx), RB0, RB0;
+ vpxor (4 * 32 + 16)(%rdx), RB1, RB1;
+ vpxor (5 * 32 + 16)(%rdx), RB2, RB2;
+ vpxor (6 * 32 + 16)(%rdx), RB3, RB3;
+ vmovdqu (7 * 32 + 16)(%rdx), RNOTx;
+ vmovdqu RNOTx, (%rcx); /* store new IV */
+
+ vmovdqu RA0, (0 * 32)(%rsi);
+ vmovdqu RA1, (1 * 32)(%rsi);
+ vmovdqu RA2, (2 * 32)(%rsi);
+ vmovdqu RA3, (3 * 32)(%rsi);
+ vmovdqu RB0, (4 * 32)(%rsi);
+ vmovdqu RB1, (5 * 32)(%rsi);
+ vmovdqu RB2, (6 * 32)(%rsi);
+ vmovdqu RB3, (7 * 32)(%rsi);
+
+ vzeroall;
+ FRAME_END
+ ret;
+SYM_FUNC_END(sm4_aesni_avx2_cbc_dec_blk16)
+
+/*
+ * void sm4_aesni_avx2_cfb_dec_blk16(const u32 *rk, u8 *dst,
+ * const u8 *src, u8 *iv)
+ */
+.align 8
+SYM_FUNC_START(sm4_aesni_avx2_cfb_dec_blk16)
+ /* input:
+ * %rdi: round key array, CTX
+ * %rsi: dst (16 blocks)
+ * %rdx: src (16 blocks)
+ * %rcx: iv
+ */
+ FRAME_BEGIN
+
+ vzeroupper;
+
+ /* Load input */
+ vmovdqu (%rcx), RNOTx;
+ vinserti128 $1, (%rdx), RNOT, RA0;
+ vmovdqu (0 * 32 + 16)(%rdx), RA1;
+ vmovdqu (1 * 32 + 16)(%rdx), RA2;
+ vmovdqu (2 * 32 + 16)(%rdx), RA3;
+ vmovdqu (3 * 32 + 16)(%rdx), RB0;
+ vmovdqu (4 * 32 + 16)(%rdx), RB1;
+ vmovdqu (5 * 32 + 16)(%rdx), RB2;
+ vmovdqu (6 * 32 + 16)(%rdx), RB3;
+
+ /* Update IV */
+ vmovdqu (7 * 32 + 16)(%rdx), RNOTx;
+ vmovdqu RNOTx, (%rcx);
+
+ call __sm4_crypt_blk16;
+
+ vpxor (0 * 32)(%rdx), RA0, RA0;
+ vpxor (1 * 32)(%rdx), RA1, RA1;
+ vpxor (2 * 32)(%rdx), RA2, RA2;
+ vpxor (3 * 32)(%rdx), RA3, RA3;
+ vpxor (4 * 32)(%rdx), RB0, RB0;
+ vpxor (5 * 32)(%rdx), RB1, RB1;
+ vpxor (6 * 32)(%rdx), RB2, RB2;
+ vpxor (7 * 32)(%rdx), RB3, RB3;
+
+ vmovdqu RA0, (0 * 32)(%rsi);
+ vmovdqu RA1, (1 * 32)(%rsi);
+ vmovdqu RA2, (2 * 32)(%rsi);
+ vmovdqu RA3, (3 * 32)(%rsi);
+ vmovdqu RB0, (4 * 32)(%rsi);
+ vmovdqu RB1, (5 * 32)(%rsi);
+ vmovdqu RB2, (6 * 32)(%rsi);
+ vmovdqu RB3, (7 * 32)(%rsi);
+
+ vzeroall;
+ FRAME_END
+ ret;
+SYM_FUNC_END(sm4_aesni_avx2_cfb_dec_blk16)
diff --git a/arch/x86/crypto/sm4-avx.h b/arch/x86/crypto/sm4-avx.h
new file mode 100644
index 000000000000..1bceab7516aa
--- /dev/null
+++ b/arch/x86/crypto/sm4-avx.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef ASM_X86_SM4_AVX_H
+#define ASM_X86_SM4_AVX_H
+
+#include <linux/types.h>
+#include <crypto/sm4.h>
+
+typedef void (*sm4_crypt_func)(const u32 *rk, u8 *dst, const u8 *src, u8 *iv);
+
+int sm4_avx_ecb_encrypt(struct skcipher_request *req);
+int sm4_avx_ecb_decrypt(struct skcipher_request *req);
+
+int sm4_cbc_encrypt(struct skcipher_request *req);
+int sm4_avx_cbc_decrypt(struct skcipher_request *req,
+ unsigned int bsize, sm4_crypt_func func);
+
+int sm4_cfb_encrypt(struct skcipher_request *req);
+int sm4_avx_cfb_decrypt(struct skcipher_request *req,
+ unsigned int bsize, sm4_crypt_func func);
+
+int sm4_avx_ctr_crypt(struct skcipher_request *req,
+ unsigned int bsize, sm4_crypt_func func);
+
+#endif
diff --git a/arch/x86/crypto/sm4_aesni_avx2_glue.c b/arch/x86/crypto/sm4_aesni_avx2_glue.c
new file mode 100644
index 000000000000..84bc718f49a3
--- /dev/null
+++ b/arch/x86/crypto/sm4_aesni_avx2_glue.c
@@ -0,0 +1,169 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * SM4 Cipher Algorithm, AES-NI/AVX2 optimized.
+ * as specified in
+ * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html
+ *
+ * Copyright (c) 2021, Alibaba Group.
+ * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
+ */
+
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <asm/simd.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/sm4.h>
+#include "sm4-avx.h"
+
+#define SM4_CRYPT16_BLOCK_SIZE (SM4_BLOCK_SIZE * 16)
+
+asmlinkage void sm4_aesni_avx2_ctr_enc_blk16(const u32 *rk, u8 *dst,
+ const u8 *src, u8 *iv);
+asmlinkage void sm4_aesni_avx2_cbc_dec_blk16(const u32 *rk, u8 *dst,
+ const u8 *src, u8 *iv);
+asmlinkage void sm4_aesni_avx2_cfb_dec_blk16(const u32 *rk, u8 *dst,
+ const u8 *src, u8 *iv);
+
+static int sm4_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key,
+ unsigned int key_len)
+{
+ struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ return sm4_expandkey(ctx, key, key_len);
+}
+
+static int cbc_decrypt(struct skcipher_request *req)
+{
+ return sm4_avx_cbc_decrypt(req, SM4_CRYPT16_BLOCK_SIZE,
+ sm4_aesni_avx2_cbc_dec_blk16);
+}
+
+
+static int cfb_decrypt(struct skcipher_request *req)
+{
+ return sm4_avx_cfb_decrypt(req, SM4_CRYPT16_BLOCK_SIZE,
+ sm4_aesni_avx2_cfb_dec_blk16);
+}
+
+static int ctr_crypt(struct skcipher_request *req)
+{
+ return sm4_avx_ctr_crypt(req, SM4_CRYPT16_BLOCK_SIZE,
+ sm4_aesni_avx2_ctr_enc_blk16);
+}
+
+static struct skcipher_alg sm4_aesni_avx2_skciphers[] = {
+ {
+ .base = {
+ .cra_name = "__ecb(sm4)",
+ .cra_driver_name = "__ecb-sm4-aesni-avx2",
+ .cra_priority = 500,
+ .cra_flags = CRYPTO_ALG_INTERNAL,
+ .cra_blocksize = SM4_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct sm4_ctx),
+ .cra_module = THIS_MODULE,
+ },
+ .min_keysize = SM4_KEY_SIZE,
+ .max_keysize = SM4_KEY_SIZE,
+ .walksize = 16 * SM4_BLOCK_SIZE,
+ .setkey = sm4_skcipher_setkey,
+ .encrypt = sm4_avx_ecb_encrypt,
+ .decrypt = sm4_avx_ecb_decrypt,
+ }, {
+ .base = {
+ .cra_name = "__cbc(sm4)",
+ .cra_driver_name = "__cbc-sm4-aesni-avx2",
+ .cra_priority = 500,
+ .cra_flags = CRYPTO_ALG_INTERNAL,
+ .cra_blocksize = SM4_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct sm4_ctx),
+ .cra_module = THIS_MODULE,
+ },
+ .min_keysize = SM4_KEY_SIZE,
+ .max_keysize = SM4_KEY_SIZE,
+ .ivsize = SM4_BLOCK_SIZE,
+ .walksize = 16 * SM4_BLOCK_SIZE,
+ .setkey = sm4_skcipher_setkey,
+ .encrypt = sm4_cbc_encrypt,
+ .decrypt = cbc_decrypt,
+ }, {
+ .base = {
+ .cra_name = "__cfb(sm4)",
+ .cra_driver_name = "__cfb-sm4-aesni-avx2",
+ .cra_priority = 500,
+ .cra_flags = CRYPTO_ALG_INTERNAL,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct sm4_ctx),
+ .cra_module = THIS_MODULE,
+ },
+ .min_keysize = SM4_KEY_SIZE,
+ .max_keysize = SM4_KEY_SIZE,
+ .ivsize = SM4_BLOCK_SIZE,
+ .chunksize = SM4_BLOCK_SIZE,
+ .walksize = 16 * SM4_BLOCK_SIZE,
+ .setkey = sm4_skcipher_setkey,
+ .encrypt = sm4_cfb_encrypt,
+ .decrypt = cfb_decrypt,
+ }, {
+ .base = {
+ .cra_name = "__ctr(sm4)",
+ .cra_driver_name = "__ctr-sm4-aesni-avx2",
+ .cra_priority = 500,
+ .cra_flags = CRYPTO_ALG_INTERNAL,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct sm4_ctx),
+ .cra_module = THIS_MODULE,
+ },
+ .min_keysize = SM4_KEY_SIZE,
+ .max_keysize = SM4_KEY_SIZE,
+ .ivsize = SM4_BLOCK_SIZE,
+ .chunksize = SM4_BLOCK_SIZE,
+ .walksize = 16 * SM4_BLOCK_SIZE,
+ .setkey = sm4_skcipher_setkey,
+ .encrypt = ctr_crypt,
+ .decrypt = ctr_crypt,
+ }
+};
+
+static struct simd_skcipher_alg *
+simd_sm4_aesni_avx2_skciphers[ARRAY_SIZE(sm4_aesni_avx2_skciphers)];
+
+static int __init sm4_init(void)
+{
+ const char *feature_name;
+
+ if (!boot_cpu_has(X86_FEATURE_AVX) ||
+ !boot_cpu_has(X86_FEATURE_AVX2) ||
+ !boot_cpu_has(X86_FEATURE_AES) ||
+ !boot_cpu_has(X86_FEATURE_OSXSAVE)) {
+ pr_info("AVX2 or AES-NI instructions are not detected.\n");
+ return -ENODEV;
+ }
+
+ if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM,
+ &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
+ return -ENODEV;
+ }
+
+ return simd_register_skciphers_compat(sm4_aesni_avx2_skciphers,
+ ARRAY_SIZE(sm4_aesni_avx2_skciphers),
+ simd_sm4_aesni_avx2_skciphers);
+}
+
+static void __exit sm4_exit(void)
+{
+ simd_unregister_skciphers(sm4_aesni_avx2_skciphers,
+ ARRAY_SIZE(sm4_aesni_avx2_skciphers),
+ simd_sm4_aesni_avx2_skciphers);
+}
+
+module_init(sm4_init);
+module_exit(sm4_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Tianjia Zhang <tianjia.zhang@linux.alibaba.com>");
+MODULE_DESCRIPTION("SM4 Cipher Algorithm, AES-NI/AVX2 optimized");
+MODULE_ALIAS_CRYPTO("sm4");
+MODULE_ALIAS_CRYPTO("sm4-aesni-avx2");
diff --git a/arch/x86/crypto/sm4_aesni_avx_glue.c b/arch/x86/crypto/sm4_aesni_avx_glue.c
new file mode 100644
index 000000000000..7800f77d68ad
--- /dev/null
+++ b/arch/x86/crypto/sm4_aesni_avx_glue.c
@@ -0,0 +1,487 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * SM4 Cipher Algorithm, AES-NI/AVX optimized.
+ * as specified in
+ * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html
+ *
+ * Copyright (c) 2021, Alibaba Group.
+ * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
+ */
+
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <asm/simd.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/sm4.h>
+#include "sm4-avx.h"
+
+#define SM4_CRYPT8_BLOCK_SIZE (SM4_BLOCK_SIZE * 8)
+
+asmlinkage void sm4_aesni_avx_crypt4(const u32 *rk, u8 *dst,
+ const u8 *src, int nblocks);
+asmlinkage void sm4_aesni_avx_crypt8(const u32 *rk, u8 *dst,
+ const u8 *src, int nblocks);
+asmlinkage void sm4_aesni_avx_ctr_enc_blk8(const u32 *rk, u8 *dst,
+ const u8 *src, u8 *iv);
+asmlinkage void sm4_aesni_avx_cbc_dec_blk8(const u32 *rk, u8 *dst,
+ const u8 *src, u8 *iv);
+asmlinkage void sm4_aesni_avx_cfb_dec_blk8(const u32 *rk, u8 *dst,
+ const u8 *src, u8 *iv);
+
+static int sm4_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key,
+ unsigned int key_len)
+{
+ struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ return sm4_expandkey(ctx, key, key_len);
+}
+
+static int ecb_do_crypt(struct skcipher_request *req, const u32 *rkey)
+{
+ struct skcipher_walk walk;
+ unsigned int nbytes;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while ((nbytes = walk.nbytes) > 0) {
+ const u8 *src = walk.src.virt.addr;
+ u8 *dst = walk.dst.virt.addr;
+
+ kernel_fpu_begin();
+ while (nbytes >= SM4_CRYPT8_BLOCK_SIZE) {
+ sm4_aesni_avx_crypt8(rkey, dst, src, 8);
+ dst += SM4_CRYPT8_BLOCK_SIZE;
+ src += SM4_CRYPT8_BLOCK_SIZE;
+ nbytes -= SM4_CRYPT8_BLOCK_SIZE;
+ }
+ while (nbytes >= SM4_BLOCK_SIZE) {
+ unsigned int nblocks = min(nbytes >> 4, 4u);
+ sm4_aesni_avx_crypt4(rkey, dst, src, nblocks);
+ dst += nblocks * SM4_BLOCK_SIZE;
+ src += nblocks * SM4_BLOCK_SIZE;
+ nbytes -= nblocks * SM4_BLOCK_SIZE;
+ }
+ kernel_fpu_end();
+
+ err = skcipher_walk_done(&walk, nbytes);
+ }
+
+ return err;
+}
+
+int sm4_avx_ecb_encrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ return ecb_do_crypt(req, ctx->rkey_enc);
+}
+EXPORT_SYMBOL_GPL(sm4_avx_ecb_encrypt);
+
+int sm4_avx_ecb_decrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ return ecb_do_crypt(req, ctx->rkey_dec);
+}
+EXPORT_SYMBOL_GPL(sm4_avx_ecb_decrypt);
+
+int sm4_cbc_encrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ unsigned int nbytes;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while ((nbytes = walk.nbytes) > 0) {
+ const u8 *iv = walk.iv;
+ const u8 *src = walk.src.virt.addr;
+ u8 *dst = walk.dst.virt.addr;
+
+ while (nbytes >= SM4_BLOCK_SIZE) {
+ crypto_xor_cpy(dst, src, iv, SM4_BLOCK_SIZE);
+ sm4_crypt_block(ctx->rkey_enc, dst, dst);
+ iv = dst;
+ src += SM4_BLOCK_SIZE;
+ dst += SM4_BLOCK_SIZE;
+ nbytes -= SM4_BLOCK_SIZE;
+ }
+ if (iv != walk.iv)
+ memcpy(walk.iv, iv, SM4_BLOCK_SIZE);
+
+ err = skcipher_walk_done(&walk, nbytes);
+ }
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(sm4_cbc_encrypt);
+
+int sm4_avx_cbc_decrypt(struct skcipher_request *req,
+ unsigned int bsize, sm4_crypt_func func)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ unsigned int nbytes;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while ((nbytes = walk.nbytes) > 0) {
+ const u8 *src = walk.src.virt.addr;
+ u8 *dst = walk.dst.virt.addr;
+
+ kernel_fpu_begin();
+
+ while (nbytes >= bsize) {
+ func(ctx->rkey_dec, dst, src, walk.iv);
+ dst += bsize;
+ src += bsize;
+ nbytes -= bsize;
+ }
+
+ while (nbytes >= SM4_BLOCK_SIZE) {
+ u8 keystream[SM4_BLOCK_SIZE * 8];
+ u8 iv[SM4_BLOCK_SIZE];
+ unsigned int nblocks = min(nbytes >> 4, 8u);
+ int i;
+
+ sm4_aesni_avx_crypt8(ctx->rkey_dec, keystream,
+ src, nblocks);
+
+ src += ((int)nblocks - 2) * SM4_BLOCK_SIZE;
+ dst += (nblocks - 1) * SM4_BLOCK_SIZE;
+ memcpy(iv, src + SM4_BLOCK_SIZE, SM4_BLOCK_SIZE);
+
+ for (i = nblocks - 1; i > 0; i--) {
+ crypto_xor_cpy(dst, src,
+ &keystream[i * SM4_BLOCK_SIZE],
+ SM4_BLOCK_SIZE);
+ src -= SM4_BLOCK_SIZE;
+ dst -= SM4_BLOCK_SIZE;
+ }
+ crypto_xor_cpy(dst, walk.iv, keystream, SM4_BLOCK_SIZE);
+ memcpy(walk.iv, iv, SM4_BLOCK_SIZE);
+ dst += nblocks * SM4_BLOCK_SIZE;
+ src += (nblocks + 1) * SM4_BLOCK_SIZE;
+ nbytes -= nblocks * SM4_BLOCK_SIZE;
+ }
+
+ kernel_fpu_end();
+ err = skcipher_walk_done(&walk, nbytes);
+ }
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(sm4_avx_cbc_decrypt);
+
+static int cbc_decrypt(struct skcipher_request *req)
+{
+ return sm4_avx_cbc_decrypt(req, SM4_CRYPT8_BLOCK_SIZE,
+ sm4_aesni_avx_cbc_dec_blk8);
+}
+
+int sm4_cfb_encrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ unsigned int nbytes;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while ((nbytes = walk.nbytes) > 0) {
+ u8 keystream[SM4_BLOCK_SIZE];
+ const u8 *iv = walk.iv;
+ const u8 *src = walk.src.virt.addr;
+ u8 *dst = walk.dst.virt.addr;
+
+ while (nbytes >= SM4_BLOCK_SIZE) {
+ sm4_crypt_block(ctx->rkey_enc, keystream, iv);
+ crypto_xor_cpy(dst, src, keystream, SM4_BLOCK_SIZE);
+ iv = dst;
+ src += SM4_BLOCK_SIZE;
+ dst += SM4_BLOCK_SIZE;
+ nbytes -= SM4_BLOCK_SIZE;
+ }
+ if (iv != walk.iv)
+ memcpy(walk.iv, iv, SM4_BLOCK_SIZE);
+
+ /* tail */
+ if (walk.nbytes == walk.total && nbytes > 0) {
+ sm4_crypt_block(ctx->rkey_enc, keystream, walk.iv);
+ crypto_xor_cpy(dst, src, keystream, nbytes);
+ nbytes = 0;
+ }
+
+ err = skcipher_walk_done(&walk, nbytes);
+ }
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(sm4_cfb_encrypt);
+
+int sm4_avx_cfb_decrypt(struct skcipher_request *req,
+ unsigned int bsize, sm4_crypt_func func)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ unsigned int nbytes;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while ((nbytes = walk.nbytes) > 0) {
+ const u8 *src = walk.src.virt.addr;
+ u8 *dst = walk.dst.virt.addr;
+
+ kernel_fpu_begin();
+
+ while (nbytes >= bsize) {
+ func(ctx->rkey_enc, dst, src, walk.iv);
+ dst += bsize;
+ src += bsize;
+ nbytes -= bsize;
+ }
+
+ while (nbytes >= SM4_BLOCK_SIZE) {
+ u8 keystream[SM4_BLOCK_SIZE * 8];
+ unsigned int nblocks = min(nbytes >> 4, 8u);
+
+ memcpy(keystream, walk.iv, SM4_BLOCK_SIZE);
+ if (nblocks > 1)
+ memcpy(&keystream[SM4_BLOCK_SIZE], src,
+ (nblocks - 1) * SM4_BLOCK_SIZE);
+ memcpy(walk.iv, src + (nblocks - 1) * SM4_BLOCK_SIZE,
+ SM4_BLOCK_SIZE);
+
+ sm4_aesni_avx_crypt8(ctx->rkey_enc, keystream,
+ keystream, nblocks);
+
+ crypto_xor_cpy(dst, src, keystream,
+ nblocks * SM4_BLOCK_SIZE);
+ dst += nblocks * SM4_BLOCK_SIZE;
+ src += nblocks * SM4_BLOCK_SIZE;
+ nbytes -= nblocks * SM4_BLOCK_SIZE;
+ }
+
+ kernel_fpu_end();
+
+ /* tail */
+ if (walk.nbytes == walk.total && nbytes > 0) {
+ u8 keystream[SM4_BLOCK_SIZE];
+
+ sm4_crypt_block(ctx->rkey_enc, keystream, walk.iv);
+ crypto_xor_cpy(dst, src, keystream, nbytes);
+ nbytes = 0;
+ }
+
+ err = skcipher_walk_done(&walk, nbytes);
+ }
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(sm4_avx_cfb_decrypt);
+
+static int cfb_decrypt(struct skcipher_request *req)
+{
+ return sm4_avx_cfb_decrypt(req, SM4_CRYPT8_BLOCK_SIZE,
+ sm4_aesni_avx_cfb_dec_blk8);
+}
+
+int sm4_avx_ctr_crypt(struct skcipher_request *req,
+ unsigned int bsize, sm4_crypt_func func)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ unsigned int nbytes;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while ((nbytes = walk.nbytes) > 0) {
+ const u8 *src = walk.src.virt.addr;
+ u8 *dst = walk.dst.virt.addr;
+
+ kernel_fpu_begin();
+
+ while (nbytes >= bsize) {
+ func(ctx->rkey_enc, dst, src, walk.iv);
+ dst += bsize;
+ src += bsize;
+ nbytes -= bsize;
+ }
+
+ while (nbytes >= SM4_BLOCK_SIZE) {
+ u8 keystream[SM4_BLOCK_SIZE * 8];
+ unsigned int nblocks = min(nbytes >> 4, 8u);
+ int i;
+
+ for (i = 0; i < nblocks; i++) {
+ memcpy(&keystream[i * SM4_BLOCK_SIZE],
+ walk.iv, SM4_BLOCK_SIZE);
+ crypto_inc(walk.iv, SM4_BLOCK_SIZE);
+ }
+ sm4_aesni_avx_crypt8(ctx->rkey_enc, keystream,
+ keystream, nblocks);
+
+ crypto_xor_cpy(dst, src, keystream,
+ nblocks * SM4_BLOCK_SIZE);
+ dst += nblocks * SM4_BLOCK_SIZE;
+ src += nblocks * SM4_BLOCK_SIZE;
+ nbytes -= nblocks * SM4_BLOCK_SIZE;
+ }
+
+ kernel_fpu_end();
+
+ /* tail */
+ if (walk.nbytes == walk.total && nbytes > 0) {
+ u8 keystream[SM4_BLOCK_SIZE];
+
+ memcpy(keystream, walk.iv, SM4_BLOCK_SIZE);
+ crypto_inc(walk.iv, SM4_BLOCK_SIZE);
+
+ sm4_crypt_block(ctx->rkey_enc, keystream, keystream);
+
+ crypto_xor_cpy(dst, src, keystream, nbytes);
+ dst += nbytes;
+ src += nbytes;
+ nbytes = 0;
+ }
+
+ err = skcipher_walk_done(&walk, nbytes);
+ }
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(sm4_avx_ctr_crypt);
+
+static int ctr_crypt(struct skcipher_request *req)
+{
+ return sm4_avx_ctr_crypt(req, SM4_CRYPT8_BLOCK_SIZE,
+ sm4_aesni_avx_ctr_enc_blk8);
+}
+
+static struct skcipher_alg sm4_aesni_avx_skciphers[] = {
+ {
+ .base = {
+ .cra_name = "__ecb(sm4)",
+ .cra_driver_name = "__ecb-sm4-aesni-avx",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_INTERNAL,
+ .cra_blocksize = SM4_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct sm4_ctx),
+ .cra_module = THIS_MODULE,
+ },
+ .min_keysize = SM4_KEY_SIZE,
+ .max_keysize = SM4_KEY_SIZE,
+ .walksize = 8 * SM4_BLOCK_SIZE,
+ .setkey = sm4_skcipher_setkey,
+ .encrypt = sm4_avx_ecb_encrypt,
+ .decrypt = sm4_avx_ecb_decrypt,
+ }, {
+ .base = {
+ .cra_name = "__cbc(sm4)",
+ .cra_driver_name = "__cbc-sm4-aesni-avx",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_INTERNAL,
+ .cra_blocksize = SM4_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct sm4_ctx),
+ .cra_module = THIS_MODULE,
+ },
+ .min_keysize = SM4_KEY_SIZE,
+ .max_keysize = SM4_KEY_SIZE,
+ .ivsize = SM4_BLOCK_SIZE,
+ .walksize = 8 * SM4_BLOCK_SIZE,
+ .setkey = sm4_skcipher_setkey,
+ .encrypt = sm4_cbc_encrypt,
+ .decrypt = cbc_decrypt,
+ }, {
+ .base = {
+ .cra_name = "__cfb(sm4)",
+ .cra_driver_name = "__cfb-sm4-aesni-avx",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_INTERNAL,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct sm4_ctx),
+ .cra_module = THIS_MODULE,
+ },
+ .min_keysize = SM4_KEY_SIZE,
+ .max_keysize = SM4_KEY_SIZE,
+ .ivsize = SM4_BLOCK_SIZE,
+ .chunksize = SM4_BLOCK_SIZE,
+ .walksize = 8 * SM4_BLOCK_SIZE,
+ .setkey = sm4_skcipher_setkey,
+ .encrypt = sm4_cfb_encrypt,
+ .decrypt = cfb_decrypt,
+ }, {
+ .base = {
+ .cra_name = "__ctr(sm4)",
+ .cra_driver_name = "__ctr-sm4-aesni-avx",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_INTERNAL,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct sm4_ctx),
+ .cra_module = THIS_MODULE,
+ },
+ .min_keysize = SM4_KEY_SIZE,
+ .max_keysize = SM4_KEY_SIZE,
+ .ivsize = SM4_BLOCK_SIZE,
+ .chunksize = SM4_BLOCK_SIZE,
+ .walksize = 8 * SM4_BLOCK_SIZE,
+ .setkey = sm4_skcipher_setkey,
+ .encrypt = ctr_crypt,
+ .decrypt = ctr_crypt,
+ }
+};
+
+static struct simd_skcipher_alg *
+simd_sm4_aesni_avx_skciphers[ARRAY_SIZE(sm4_aesni_avx_skciphers)];
+
+static int __init sm4_init(void)
+{
+ const char *feature_name;
+
+ if (!boot_cpu_has(X86_FEATURE_AVX) ||
+ !boot_cpu_has(X86_FEATURE_AES) ||
+ !boot_cpu_has(X86_FEATURE_OSXSAVE)) {
+ pr_info("AVX or AES-NI instructions are not detected.\n");
+ return -ENODEV;
+ }
+
+ if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM,
+ &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
+ return -ENODEV;
+ }
+
+ return simd_register_skciphers_compat(sm4_aesni_avx_skciphers,
+ ARRAY_SIZE(sm4_aesni_avx_skciphers),
+ simd_sm4_aesni_avx_skciphers);
+}
+
+static void __exit sm4_exit(void)
+{
+ simd_unregister_skciphers(sm4_aesni_avx_skciphers,
+ ARRAY_SIZE(sm4_aesni_avx_skciphers),
+ simd_sm4_aesni_avx_skciphers);
+}
+
+module_init(sm4_init);
+module_exit(sm4_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Tianjia Zhang <tianjia.zhang@linux.alibaba.com>");
+MODULE_DESCRIPTION("SM4 Cipher Algorithm, AES-NI/AVX optimized");
+MODULE_ALIAS_CRYPTO("sm4");
+MODULE_ALIAS_CRYPTO("sm4-aesni-avx");
diff --git a/arch/x86/events/Kconfig b/arch/x86/events/Kconfig
index 39d9ded9e25a..d6cdfe631674 100644
--- a/arch/x86/events/Kconfig
+++ b/arch/x86/events/Kconfig
@@ -34,4 +34,14 @@ config PERF_EVENTS_AMD_POWER
(CPUID Fn8000_0007_EDX[12]) interface to calculate the
average power consumption on Family 15h processors.
+config PERF_EVENTS_AMD_UNCORE
+ tristate "AMD Uncore performance events"
+ depends on PERF_EVENTS && CPU_SUP_AMD
+ default y
+ help
+ Include support for AMD uncore performance events for use with
+ e.g., perf stat -e amd_l3/.../,amd_df/.../.
+
+ To compile this driver as a module, choose M here: the
+ module will be called 'amd-uncore'.
endmenu
diff --git a/arch/x86/events/amd/Makefile b/arch/x86/events/amd/Makefile
index fe8795a67385..6cbe38d5fd9d 100644
--- a/arch/x86/events/amd/Makefile
+++ b/arch/x86/events/amd/Makefile
@@ -1,8 +1,9 @@
# SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_CPU_SUP_AMD) += core.o uncore.o
+obj-$(CONFIG_CPU_SUP_AMD) += core.o
obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += power.o
obj-$(CONFIG_X86_LOCAL_APIC) += ibs.o
+obj-$(CONFIG_PERF_EVENTS_AMD_UNCORE) += amd-uncore.o
+amd-uncore-objs := uncore.o
ifdef CONFIG_AMD_IOMMU
obj-$(CONFIG_CPU_SUP_AMD) += iommu.o
endif
-
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 40669eac9d6d..9739019d4b67 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -26,6 +26,7 @@ static u32 ibs_caps;
#include <linux/hardirq.h>
#include <asm/nmi.h>
+#include <asm/amd-ibs.h>
#define IBS_FETCH_CONFIG_MASK (IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT)
#define IBS_OP_CONFIG_MASK IBS_OP_MAX_CNT
@@ -90,6 +91,7 @@ struct perf_ibs {
unsigned long offset_mask[1];
int offset_max;
unsigned int fetch_count_reset_broken : 1;
+ unsigned int fetch_ignore_if_zero_rip : 1;
struct cpu_perf_ibs __percpu *pcpu;
struct attribute **format_attrs;
@@ -99,15 +101,6 @@ struct perf_ibs {
u64 (*get_count)(u64 config);
};
-struct perf_ibs_data {
- u32 size;
- union {
- u32 data[0]; /* data buffer starts here */
- u32 caps;
- };
- u64 regs[MSR_AMD64_IBS_REG_COUNT_MAX];
-};
-
static int
perf_event_set_period(struct hw_perf_event *hwc, u64 min, u64 max, u64 *hw_period)
{
@@ -328,11 +321,14 @@ static int perf_ibs_set_period(struct perf_ibs *perf_ibs,
static u64 get_ibs_fetch_count(u64 config)
{
- return (config & IBS_FETCH_CNT) >> 12;
+ union ibs_fetch_ctl fetch_ctl = (union ibs_fetch_ctl)config;
+
+ return fetch_ctl.fetch_cnt << 4;
}
static u64 get_ibs_op_count(u64 config)
{
+ union ibs_op_ctl op_ctl = (union ibs_op_ctl)config;
u64 count = 0;
/*
@@ -340,12 +336,12 @@ static u64 get_ibs_op_count(u64 config)
* and the lower 7 bits of CurCnt are randomized.
* Otherwise CurCnt has the full 27-bit current counter value.
*/
- if (config & IBS_OP_VAL) {
- count = (config & IBS_OP_MAX_CNT) << 4;
+ if (op_ctl.op_val) {
+ count = op_ctl.opmaxcnt << 4;
if (ibs_caps & IBS_CAPS_OPCNTEXT)
- count += config & IBS_OP_MAX_CNT_EXT_MASK;
+ count += op_ctl.opmaxcnt_ext << 20;
} else if (ibs_caps & IBS_CAPS_RDWROPCNT) {
- count = (config & IBS_OP_CUR_CNT) >> 32;
+ count = op_ctl.opcurcnt;
}
return count;
@@ -570,6 +566,7 @@ static struct perf_ibs perf_ibs_op = {
.start = perf_ibs_start,
.stop = perf_ibs_stop,
.read = perf_ibs_read,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
},
.msr = MSR_AMD64_IBSOPCTL,
.config_mask = IBS_OP_CONFIG_MASK,
@@ -672,6 +669,10 @@ fail:
if (check_rip && (ibs_data.regs[2] & IBS_RIP_INVALID)) {
regs.flags &= ~PERF_EFLAGS_EXACT;
} else {
+ /* Workaround for erratum #1197 */
+ if (perf_ibs->fetch_ignore_if_zero_rip && !(ibs_data.regs[1]))
+ goto out;
+
set_linear_ip(&regs, ibs_data.regs[1]);
regs.flags |= PERF_EFLAGS_EXACT;
}
@@ -769,6 +770,9 @@ static __init void perf_event_ibs_init(void)
if (boot_cpu_data.x86 >= 0x16 && boot_cpu_data.x86 <= 0x18)
perf_ibs_fetch.fetch_count_reset_broken = 1;
+ if (boot_cpu_data.x86 == 0x19 && boot_cpu_data.x86_model < 0x10)
+ perf_ibs_fetch.fetch_ignore_if_zero_rip = 1;
+
perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch");
if (ibs_caps & IBS_CAPS_OPCNT) {
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index 16a2369c586e..37d5b380516e 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -213,6 +213,7 @@ static struct pmu pmu_class = {
.stop = pmu_event_stop,
.read = pmu_event_read,
.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
+ .module = THIS_MODULE,
};
static int power_cpu_exit(unsigned int cpu)
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 582c0ffb5e98..0d04414b97d2 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -12,11 +12,11 @@
#include <linux/init.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
+#include <linux/cpufeature.h>
+#include <linux/smp.h>
-#include <asm/cpufeature.h>
#include <asm/perf_event.h>
#include <asm/msr.h>
-#include <asm/smp.h>
#define NUM_COUNTERS_NB 4
#define NUM_COUNTERS_L2 4
@@ -347,6 +347,7 @@ static struct pmu amd_nb_pmu = {
.stop = amd_uncore_stop,
.read = amd_uncore_read,
.capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
+ .module = THIS_MODULE,
};
static struct pmu amd_llc_pmu = {
@@ -360,6 +361,7 @@ static struct pmu amd_llc_pmu = {
.stop = amd_uncore_stop,
.read = amd_uncore_read,
.capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
+ .module = THIS_MODULE,
};
static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)
@@ -452,7 +454,7 @@ static int amd_uncore_cpu_starting(unsigned int cpu)
if (amd_uncore_llc) {
uncore = *per_cpu_ptr(amd_uncore_llc, cpu);
- uncore->id = per_cpu(cpu_llc_id, cpu);
+ uncore->id = get_llc_id(cpu);
uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc);
*per_cpu_ptr(amd_uncore_llc, cpu) = uncore;
@@ -659,12 +661,34 @@ fail_prep:
fail_llc:
if (boot_cpu_has(X86_FEATURE_PERFCTR_NB))
perf_pmu_unregister(&amd_nb_pmu);
- if (amd_uncore_llc)
- free_percpu(amd_uncore_llc);
+ free_percpu(amd_uncore_llc);
fail_nb:
- if (amd_uncore_nb)
- free_percpu(amd_uncore_nb);
+ free_percpu(amd_uncore_nb);
return ret;
}
-device_initcall(amd_uncore_init);
+
+static void __exit amd_uncore_exit(void)
+{
+ cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE);
+ cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING);
+ cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP);
+
+ if (boot_cpu_has(X86_FEATURE_PERFCTR_LLC)) {
+ perf_pmu_unregister(&amd_llc_pmu);
+ free_percpu(amd_uncore_llc);
+ amd_uncore_llc = NULL;
+ }
+
+ if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) {
+ perf_pmu_unregister(&amd_nb_pmu);
+ free_percpu(amd_uncore_nb);
+ amd_uncore_nb = NULL;
+ }
+}
+
+module_init(amd_uncore_init);
+module_exit(amd_uncore_exit);
+
+MODULE_DESCRIPTION("AMD Uncore Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 3092fbf9dbe4..2a57dbed4894 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1087,10 +1087,8 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
* validate an event group (assign == NULL)
*/
if (!unsched && assign) {
- for (i = 0; i < n; i++) {
- e = cpuc->event_list[i];
+ for (i = 0; i < n; i++)
static_call_cond(x86_pmu_commit_scheduling)(cpuc, i, assign[i]);
- }
} else {
for (i = n0; i < n; i++) {
e = cpuc->event_list[i];
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index ac6fd2dabf6a..7011e87be6d0 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -5032,9 +5032,9 @@ static ssize_t freeze_on_smi_store(struct device *cdev,
x86_pmu.attr_freeze_on_smi = val;
- get_online_cpus();
+ cpus_read_lock();
on_each_cpu(flip_smm_bit, &val, 1);
- put_online_cpus();
+ cpus_read_unlock();
done:
mutex_unlock(&freeze_on_smi_mutex);
@@ -5077,9 +5077,9 @@ static ssize_t set_sysctl_tfa(struct device *cdev,
allow_tsx_force_abort = val;
- get_online_cpus();
+ cpus_read_lock();
on_each_cpu(update_tfa_sched, NULL, 1);
- put_online_cpus();
+ cpus_read_unlock();
return count;
}
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 915847655c06..7f406c14715f 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -62,7 +62,7 @@ static struct pt_cap_desc {
PT_CAP(single_range_output, 0, CPUID_ECX, BIT(2)),
PT_CAP(output_subsys, 0, CPUID_ECX, BIT(3)),
PT_CAP(payloads_lip, 0, CPUID_ECX, BIT(31)),
- PT_CAP(num_address_ranges, 1, CPUID_EAX, 0x3),
+ PT_CAP(num_address_ranges, 1, CPUID_EAX, 0x7),
PT_CAP(mtc_periods, 1, CPUID_EAX, 0xffff0000),
PT_CAP(cycle_thresholds, 1, CPUID_EBX, 0xffff),
PT_CAP(psb_periods, 1, CPUID_EBX, 0xffff0000),
@@ -1708,7 +1708,7 @@ static __init int pt_init(void)
if (!boot_cpu_has(X86_FEATURE_INTEL_PT))
return -ENODEV;
- get_online_cpus();
+ cpus_read_lock();
for_each_online_cpu(cpu) {
u64 ctl;
@@ -1716,7 +1716,7 @@ static __init int pt_init(void)
if (!ret && (ctl & RTIT_CTL_TRACEEN))
prior_warn++;
}
- put_online_cpus();
+ cpus_read_unlock();
if (prior_warn) {
x86_add_exclusive(x86_lbr_exclusive_pt);
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 9bf4dbbc26e2..c72e368dd164 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -842,6 +842,18 @@ static const struct attribute_group uncore_pmu_attr_group = {
.attrs = uncore_pmu_attrs,
};
+void uncore_get_alias_name(char *pmu_name, struct intel_uncore_pmu *pmu)
+{
+ struct intel_uncore_type *type = pmu->type;
+
+ if (type->num_boxes == 1)
+ sprintf(pmu_name, "uncore_type_%u", type->type_id);
+ else {
+ sprintf(pmu_name, "uncore_type_%u_%d",
+ type->type_id, type->box_ids[pmu->pmu_idx]);
+ }
+}
+
static void uncore_get_pmu_name(struct intel_uncore_pmu *pmu)
{
struct intel_uncore_type *type = pmu->type;
@@ -851,12 +863,7 @@ static void uncore_get_pmu_name(struct intel_uncore_pmu *pmu)
* Use uncore_type_&typeid_&boxid as name.
*/
if (!type->name) {
- if (type->num_boxes == 1)
- sprintf(pmu->name, "uncore_type_%u", type->type_id);
- else {
- sprintf(pmu->name, "uncore_type_%u_%d",
- type->type_id, type->box_ids[pmu->pmu_idx]);
- }
+ uncore_get_alias_name(pmu->name, pmu);
return;
}
@@ -865,9 +872,13 @@ static void uncore_get_pmu_name(struct intel_uncore_pmu *pmu)
sprintf(pmu->name, "uncore_%s", type->name);
else
sprintf(pmu->name, "uncore");
- } else
- sprintf(pmu->name, "uncore_%s_%d", type->name, pmu->pmu_idx);
-
+ } else {
+ /*
+ * Use the box ID from the discovery table if applicable.
+ */
+ sprintf(pmu->name, "uncore_%s_%d", type->name,
+ type->box_ids ? type->box_ids[pmu->pmu_idx] : pmu->pmu_idx);
+ }
}
static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
@@ -1663,6 +1674,7 @@ struct intel_uncore_init_fun {
void (*cpu_init)(void);
int (*pci_init)(void);
void (*mmio_init)(void);
+ bool use_discovery;
};
static const struct intel_uncore_init_fun nhm_uncore_init __initconst = {
@@ -1765,6 +1777,13 @@ static const struct intel_uncore_init_fun snr_uncore_init __initconst = {
.mmio_init = snr_uncore_mmio_init,
};
+static const struct intel_uncore_init_fun spr_uncore_init __initconst = {
+ .cpu_init = spr_uncore_cpu_init,
+ .pci_init = spr_uncore_pci_init,
+ .mmio_init = spr_uncore_mmio_init,
+ .use_discovery = true,
+};
+
static const struct intel_uncore_init_fun generic_uncore_init __initconst = {
.cpu_init = intel_uncore_generic_uncore_cpu_init,
.pci_init = intel_uncore_generic_uncore_pci_init,
@@ -1809,6 +1828,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rkl_uncore_init),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_uncore_init),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init),
X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init),
{},
};
@@ -1832,8 +1852,13 @@ static int __init intel_uncore_init(void)
uncore_init = (struct intel_uncore_init_fun *)&generic_uncore_init;
else
return -ENODEV;
- } else
+ } else {
uncore_init = (struct intel_uncore_init_fun *)id->driver_data;
+ if (uncore_no_discover && uncore_init->use_discovery)
+ return -ENODEV;
+ if (uncore_init->use_discovery && !intel_uncore_has_discovery_tables())
+ return -ENODEV;
+ }
if (uncore_init->pci_init) {
pret = uncore_init->pci_init();
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 187d7287039c..b9687980aab6 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -561,6 +561,7 @@ struct event_constraint *
uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event);
void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event);
u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx);
+void uncore_get_alias_name(char *pmu_name, struct intel_uncore_pmu *pmu);
extern struct intel_uncore_type *empty_uncore[];
extern struct intel_uncore_type **uncore_msr_uncores;
@@ -608,6 +609,9 @@ void snr_uncore_mmio_init(void);
int icx_uncore_pci_init(void);
void icx_uncore_cpu_init(void);
void icx_uncore_mmio_init(void);
+int spr_uncore_pci_init(void);
+void spr_uncore_cpu_init(void);
+void spr_uncore_mmio_init(void);
/* uncore_nhmex.c */
void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c
index aba9bff95413..3049c646fa20 100644
--- a/arch/x86/events/intel/uncore_discovery.c
+++ b/arch/x86/events/intel/uncore_discovery.c
@@ -337,17 +337,17 @@ static const struct attribute_group generic_uncore_format_group = {
.attrs = generic_uncore_formats_attr,
};
-static void intel_generic_uncore_msr_init_box(struct intel_uncore_box *box)
+void intel_generic_uncore_msr_init_box(struct intel_uncore_box *box)
{
wrmsrl(uncore_msr_box_ctl(box), GENERIC_PMON_BOX_CTL_INT);
}
-static void intel_generic_uncore_msr_disable_box(struct intel_uncore_box *box)
+void intel_generic_uncore_msr_disable_box(struct intel_uncore_box *box)
{
wrmsrl(uncore_msr_box_ctl(box), GENERIC_PMON_BOX_CTL_FRZ);
}
-static void intel_generic_uncore_msr_enable_box(struct intel_uncore_box *box)
+void intel_generic_uncore_msr_enable_box(struct intel_uncore_box *box)
{
wrmsrl(uncore_msr_box_ctl(box), 0);
}
@@ -377,7 +377,7 @@ static struct intel_uncore_ops generic_uncore_msr_ops = {
.read_counter = uncore_msr_read_counter,
};
-static void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box)
+void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box)
{
struct pci_dev *pdev = box->pci_dev;
int box_ctl = uncore_pci_box_ctl(box);
@@ -386,7 +386,7 @@ static void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box)
pci_write_config_dword(pdev, box_ctl, GENERIC_PMON_BOX_CTL_INT);
}
-static void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box)
+void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box)
{
struct pci_dev *pdev = box->pci_dev;
int box_ctl = uncore_pci_box_ctl(box);
@@ -394,7 +394,7 @@ static void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box)
pci_write_config_dword(pdev, box_ctl, GENERIC_PMON_BOX_CTL_FRZ);
}
-static void intel_generic_uncore_pci_enable_box(struct intel_uncore_box *box)
+void intel_generic_uncore_pci_enable_box(struct intel_uncore_box *box)
{
struct pci_dev *pdev = box->pci_dev;
int box_ctl = uncore_pci_box_ctl(box);
@@ -411,8 +411,8 @@ static void intel_generic_uncore_pci_enable_event(struct intel_uncore_box *box,
pci_write_config_dword(pdev, hwc->config_base, hwc->config);
}
-static void intel_generic_uncore_pci_disable_event(struct intel_uncore_box *box,
- struct perf_event *event)
+void intel_generic_uncore_pci_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
{
struct pci_dev *pdev = box->pci_dev;
struct hw_perf_event *hwc = &event->hw;
@@ -420,8 +420,8 @@ static void intel_generic_uncore_pci_disable_event(struct intel_uncore_box *box,
pci_write_config_dword(pdev, hwc->config_base, 0);
}
-static u64 intel_generic_uncore_pci_read_counter(struct intel_uncore_box *box,
- struct perf_event *event)
+u64 intel_generic_uncore_pci_read_counter(struct intel_uncore_box *box,
+ struct perf_event *event)
{
struct pci_dev *pdev = box->pci_dev;
struct hw_perf_event *hwc = &event->hw;
@@ -454,7 +454,7 @@ static unsigned int generic_uncore_mmio_box_ctl(struct intel_uncore_box *box)
return type->box_ctls[box->dieid] + type->mmio_offsets[box->pmu->pmu_idx];
}
-static void intel_generic_uncore_mmio_init_box(struct intel_uncore_box *box)
+void intel_generic_uncore_mmio_init_box(struct intel_uncore_box *box)
{
unsigned int box_ctl = generic_uncore_mmio_box_ctl(box);
struct intel_uncore_type *type = box->pmu->type;
@@ -478,7 +478,7 @@ static void intel_generic_uncore_mmio_init_box(struct intel_uncore_box *box)
writel(GENERIC_PMON_BOX_CTL_INT, box->io_addr);
}
-static void intel_generic_uncore_mmio_disable_box(struct intel_uncore_box *box)
+void intel_generic_uncore_mmio_disable_box(struct intel_uncore_box *box)
{
if (!box->io_addr)
return;
@@ -486,7 +486,7 @@ static void intel_generic_uncore_mmio_disable_box(struct intel_uncore_box *box)
writel(GENERIC_PMON_BOX_CTL_FRZ, box->io_addr);
}
-static void intel_generic_uncore_mmio_enable_box(struct intel_uncore_box *box)
+void intel_generic_uncore_mmio_enable_box(struct intel_uncore_box *box)
{
if (!box->io_addr)
return;
@@ -505,8 +505,8 @@ static void intel_generic_uncore_mmio_enable_event(struct intel_uncore_box *box,
writel(hwc->config, box->io_addr + hwc->config_base);
}
-static void intel_generic_uncore_mmio_disable_event(struct intel_uncore_box *box,
- struct perf_event *event)
+void intel_generic_uncore_mmio_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
@@ -568,8 +568,8 @@ static bool uncore_update_uncore_type(enum uncore_access_type type_id,
return true;
}
-static struct intel_uncore_type **
-intel_uncore_generic_init_uncores(enum uncore_access_type type_id)
+struct intel_uncore_type **
+intel_uncore_generic_init_uncores(enum uncore_access_type type_id, int num_extra)
{
struct intel_uncore_discovery_type *type;
struct intel_uncore_type **uncores;
@@ -577,7 +577,7 @@ intel_uncore_generic_init_uncores(enum uncore_access_type type_id)
struct rb_node *node;
int i = 0;
- uncores = kcalloc(num_discovered_types[type_id] + 1,
+ uncores = kcalloc(num_discovered_types[type_id] + num_extra + 1,
sizeof(struct intel_uncore_type *), GFP_KERNEL);
if (!uncores)
return empty_uncore;
@@ -606,17 +606,17 @@ intel_uncore_generic_init_uncores(enum uncore_access_type type_id)
void intel_uncore_generic_uncore_cpu_init(void)
{
- uncore_msr_uncores = intel_uncore_generic_init_uncores(UNCORE_ACCESS_MSR);
+ uncore_msr_uncores = intel_uncore_generic_init_uncores(UNCORE_ACCESS_MSR, 0);
}
int intel_uncore_generic_uncore_pci_init(void)
{
- uncore_pci_uncores = intel_uncore_generic_init_uncores(UNCORE_ACCESS_PCI);
+ uncore_pci_uncores = intel_uncore_generic_init_uncores(UNCORE_ACCESS_PCI, 0);
return 0;
}
void intel_uncore_generic_uncore_mmio_init(void)
{
- uncore_mmio_uncores = intel_uncore_generic_init_uncores(UNCORE_ACCESS_MMIO);
+ uncore_mmio_uncores = intel_uncore_generic_init_uncores(UNCORE_ACCESS_MMIO, 0);
}
diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h
index 1d652939a01c..7280c8a3c831 100644
--- a/arch/x86/events/intel/uncore_discovery.h
+++ b/arch/x86/events/intel/uncore_discovery.h
@@ -129,3 +129,24 @@ void intel_uncore_clear_discovery_tables(void);
void intel_uncore_generic_uncore_cpu_init(void);
int intel_uncore_generic_uncore_pci_init(void);
void intel_uncore_generic_uncore_mmio_init(void);
+
+void intel_generic_uncore_msr_init_box(struct intel_uncore_box *box);
+void intel_generic_uncore_msr_disable_box(struct intel_uncore_box *box);
+void intel_generic_uncore_msr_enable_box(struct intel_uncore_box *box);
+
+void intel_generic_uncore_mmio_init_box(struct intel_uncore_box *box);
+void intel_generic_uncore_mmio_disable_box(struct intel_uncore_box *box);
+void intel_generic_uncore_mmio_enable_box(struct intel_uncore_box *box);
+void intel_generic_uncore_mmio_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event);
+
+void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box);
+void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box);
+void intel_generic_uncore_pci_enable_box(struct intel_uncore_box *box);
+void intel_generic_uncore_pci_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event);
+u64 intel_generic_uncore_pci_read_counter(struct intel_uncore_box *box,
+ struct perf_event *event);
+
+struct intel_uncore_type **
+intel_uncore_generic_init_uncores(enum uncore_access_type type_id, int num_extra);
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 609c24aec71a..5ddc0f30db6f 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* SandyBridge-EP/IvyTown uncore support */
#include "uncore.h"
+#include "uncore_discovery.h"
/* SNB-EP pci bus to socket mapping */
#define SNBEP_CPUNODEID 0x40
@@ -454,6 +455,17 @@
#define ICX_NUMBER_IMC_CHN 2
#define ICX_IMC_MEM_STRIDE 0x4
+/* SPR */
+#define SPR_RAW_EVENT_MASK_EXT 0xffffff
+
+/* SPR CHA */
+#define SPR_CHA_PMON_CTL_TID_EN (1 << 16)
+#define SPR_CHA_PMON_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \
+ SPR_CHA_PMON_CTL_TID_EN)
+#define SPR_CHA_PMON_BOX_FILTER_TID 0x3ff
+
+#define SPR_C0_MSR_PMON_BOX_FILTER0 0x200e
+
DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6");
DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
@@ -466,6 +478,7 @@ DEFINE_UNCORE_FORMAT_ATTR(umask_ext4, umask, "config:8-15,32-55");
DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16");
DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
+DEFINE_UNCORE_FORMAT_ATTR(tid_en2, tid_en, "config:16");
DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
DEFINE_UNCORE_FORMAT_ATTR(thresh9, thresh, "config:24-35");
DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
@@ -3838,26 +3851,32 @@ clear_attr_update:
return ret;
}
-static int skx_iio_set_mapping(struct intel_uncore_type *type)
-{
- return pmu_iio_set_mapping(type, &skx_iio_mapping_group);
-}
-
-static void skx_iio_cleanup_mapping(struct intel_uncore_type *type)
+static void
+pmu_iio_cleanup_mapping(struct intel_uncore_type *type, struct attribute_group *ag)
{
- struct attribute **attr = skx_iio_mapping_group.attrs;
+ struct attribute **attr = ag->attrs;
if (!attr)
return;
for (; *attr; attr++)
kfree((*attr)->name);
- kfree(attr_to_ext_attr(*skx_iio_mapping_group.attrs));
- kfree(skx_iio_mapping_group.attrs);
- skx_iio_mapping_group.attrs = NULL;
+ kfree(attr_to_ext_attr(*ag->attrs));
+ kfree(ag->attrs);
+ ag->attrs = NULL;
kfree(type->topology);
}
+static int skx_iio_set_mapping(struct intel_uncore_type *type)
+{
+ return pmu_iio_set_mapping(type, &skx_iio_mapping_group);
+}
+
+static void skx_iio_cleanup_mapping(struct intel_uncore_type *type)
+{
+ pmu_iio_cleanup_mapping(type, &skx_iio_mapping_group);
+}
+
static struct intel_uncore_type skx_uncore_iio = {
.name = "iio",
.num_counters = 4,
@@ -4501,6 +4520,11 @@ static int snr_iio_set_mapping(struct intel_uncore_type *type)
return pmu_iio_set_mapping(type, &snr_iio_mapping_group);
}
+static void snr_iio_cleanup_mapping(struct intel_uncore_type *type)
+{
+ pmu_iio_cleanup_mapping(type, &snr_iio_mapping_group);
+}
+
static struct intel_uncore_type snr_uncore_iio = {
.name = "iio",
.num_counters = 4,
@@ -4517,7 +4541,7 @@ static struct intel_uncore_type snr_uncore_iio = {
.attr_update = snr_iio_attr_update,
.get_topology = snr_iio_get_topology,
.set_mapping = snr_iio_set_mapping,
- .cleanup_mapping = skx_iio_cleanup_mapping,
+ .cleanup_mapping = snr_iio_cleanup_mapping,
};
static struct intel_uncore_type snr_uncore_irp = {
@@ -4783,13 +4807,15 @@ int snr_uncore_pci_init(void)
return 0;
}
-static struct pci_dev *snr_uncore_get_mc_dev(int id)
+#define SNR_MC_DEVICE_ID 0x3451
+
+static struct pci_dev *snr_uncore_get_mc_dev(unsigned int device, int id)
{
struct pci_dev *mc_dev = NULL;
int pkg;
while (1) {
- mc_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3451, mc_dev);
+ mc_dev = pci_get_device(PCI_VENDOR_ID_INTEL, device, mc_dev);
if (!mc_dev)
break;
pkg = uncore_pcibus_to_dieid(mc_dev->bus);
@@ -4799,19 +4825,20 @@ static struct pci_dev *snr_uncore_get_mc_dev(int id)
return mc_dev;
}
-static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box,
- unsigned int box_ctl, int mem_offset)
+static int snr_uncore_mmio_map(struct intel_uncore_box *box,
+ unsigned int box_ctl, int mem_offset,
+ unsigned int device)
{
- struct pci_dev *pdev = snr_uncore_get_mc_dev(box->dieid);
+ struct pci_dev *pdev = snr_uncore_get_mc_dev(device, box->dieid);
struct intel_uncore_type *type = box->pmu->type;
resource_size_t addr;
u32 pci_dword;
if (!pdev)
- return;
+ return -ENODEV;
pci_read_config_dword(pdev, SNR_IMC_MMIO_BASE_OFFSET, &pci_dword);
- addr = (pci_dword & SNR_IMC_MMIO_BASE_MASK) << 23;
+ addr = ((resource_size_t)pci_dword & SNR_IMC_MMIO_BASE_MASK) << 23;
pci_read_config_dword(pdev, mem_offset, &pci_dword);
addr |= (pci_dword & SNR_IMC_MMIO_MEM0_MASK) << 12;
@@ -4821,16 +4848,25 @@ static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box,
box->io_addr = ioremap(addr, type->mmio_map_size);
if (!box->io_addr) {
pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name);
- return;
+ return -EINVAL;
}
- writel(IVBEP_PMON_BOX_CTL_INT, box->io_addr);
+ return 0;
+}
+
+static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box,
+ unsigned int box_ctl, int mem_offset,
+ unsigned int device)
+{
+ if (!snr_uncore_mmio_map(box, box_ctl, mem_offset, device))
+ writel(IVBEP_PMON_BOX_CTL_INT, box->io_addr);
}
static void snr_uncore_mmio_init_box(struct intel_uncore_box *box)
{
__snr_uncore_mmio_init_box(box, uncore_mmio_box_ctl(box),
- SNR_IMC_MMIO_MEM0_OFFSET);
+ SNR_IMC_MMIO_MEM0_OFFSET,
+ SNR_MC_DEVICE_ID);
}
static void snr_uncore_mmio_disable_box(struct intel_uncore_box *box)
@@ -5092,6 +5128,11 @@ static int icx_iio_set_mapping(struct intel_uncore_type *type)
return pmu_iio_set_mapping(type, &icx_iio_mapping_group);
}
+static void icx_iio_cleanup_mapping(struct intel_uncore_type *type)
+{
+ pmu_iio_cleanup_mapping(type, &icx_iio_mapping_group);
+}
+
static struct intel_uncore_type icx_uncore_iio = {
.name = "iio",
.num_counters = 4,
@@ -5109,7 +5150,7 @@ static struct intel_uncore_type icx_uncore_iio = {
.attr_update = icx_iio_attr_update,
.get_topology = icx_iio_get_topology,
.set_mapping = icx_iio_set_mapping,
- .cleanup_mapping = skx_iio_cleanup_mapping,
+ .cleanup_mapping = icx_iio_cleanup_mapping,
};
static struct intel_uncore_type icx_uncore_irp = {
@@ -5405,7 +5446,8 @@ static void icx_uncore_imc_init_box(struct intel_uncore_box *box)
int mem_offset = (box->pmu->pmu_idx / ICX_NUMBER_IMC_CHN) * ICX_IMC_MEM_STRIDE +
SNR_IMC_MMIO_MEM0_OFFSET;
- __snr_uncore_mmio_init_box(box, box_ctl, mem_offset);
+ __snr_uncore_mmio_init_box(box, box_ctl, mem_offset,
+ SNR_MC_DEVICE_ID);
}
static struct intel_uncore_ops icx_uncore_mmio_ops = {
@@ -5475,7 +5517,8 @@ static void icx_uncore_imc_freerunning_init_box(struct intel_uncore_box *box)
int mem_offset = box->pmu->pmu_idx * ICX_IMC_MEM_STRIDE +
SNR_IMC_MMIO_MEM0_OFFSET;
- __snr_uncore_mmio_init_box(box, uncore_mmio_box_ctl(box), mem_offset);
+ snr_uncore_mmio_map(box, uncore_mmio_box_ctl(box),
+ mem_offset, SNR_MC_DEVICE_ID);
}
static struct intel_uncore_ops icx_uncore_imc_freerunning_ops = {
@@ -5509,3 +5552,497 @@ void icx_uncore_mmio_init(void)
}
/* end of ICX uncore support */
+
+/* SPR uncore support */
+
+static void spr_uncore_msr_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE)
+ wrmsrl(reg1->reg, reg1->config);
+
+ wrmsrl(hwc->config_base, hwc->config);
+}
+
+static void spr_uncore_msr_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE)
+ wrmsrl(reg1->reg, 0);
+
+ wrmsrl(hwc->config_base, 0);
+}
+
+static int spr_cha_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ bool tie_en = !!(event->hw.config & SPR_CHA_PMON_CTL_TID_EN);
+ struct intel_uncore_type *type = box->pmu->type;
+
+ if (tie_en) {
+ reg1->reg = SPR_C0_MSR_PMON_BOX_FILTER0 +
+ HSWEP_CBO_MSR_OFFSET * type->box_ids[box->pmu->pmu_idx];
+ reg1->config = event->attr.config1 & SPR_CHA_PMON_BOX_FILTER_TID;
+ reg1->idx = 0;
+ }
+
+ return 0;
+}
+
+static struct intel_uncore_ops spr_uncore_chabox_ops = {
+ .init_box = intel_generic_uncore_msr_init_box,
+ .disable_box = intel_generic_uncore_msr_disable_box,
+ .enable_box = intel_generic_uncore_msr_enable_box,
+ .disable_event = spr_uncore_msr_disable_event,
+ .enable_event = spr_uncore_msr_enable_event,
+ .read_counter = uncore_msr_read_counter,
+ .hw_config = spr_cha_hw_config,
+ .get_constraint = uncore_get_constraint,
+ .put_constraint = uncore_put_constraint,
+};
+
+static struct attribute *spr_uncore_cha_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask_ext4.attr,
+ &format_attr_tid_en2.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ &format_attr_filter_tid5.attr,
+ NULL,
+};
+static const struct attribute_group spr_uncore_chabox_format_group = {
+ .name = "format",
+ .attrs = spr_uncore_cha_formats_attr,
+};
+
+static ssize_t alias_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct intel_uncore_pmu *pmu = dev_to_uncore_pmu(dev);
+ char pmu_name[UNCORE_PMU_NAME_LEN];
+
+ uncore_get_alias_name(pmu_name, pmu);
+ return sysfs_emit(buf, "%s\n", pmu_name);
+}
+
+static DEVICE_ATTR_RO(alias);
+
+static struct attribute *uncore_alias_attrs[] = {
+ &dev_attr_alias.attr,
+ NULL
+};
+
+ATTRIBUTE_GROUPS(uncore_alias);
+
+static struct intel_uncore_type spr_uncore_chabox = {
+ .name = "cha",
+ .event_mask = SPR_CHA_PMON_EVENT_MASK,
+ .event_mask_ext = SPR_RAW_EVENT_MASK_EXT,
+ .num_shared_regs = 1,
+ .ops = &spr_uncore_chabox_ops,
+ .format_group = &spr_uncore_chabox_format_group,
+ .attr_update = uncore_alias_groups,
+};
+
+static struct intel_uncore_type spr_uncore_iio = {
+ .name = "iio",
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .event_mask_ext = SNR_IIO_PMON_RAW_EVENT_MASK_EXT,
+ .format_group = &snr_uncore_iio_format_group,
+ .attr_update = uncore_alias_groups,
+};
+
+static struct attribute *spr_uncore_raw_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask_ext4.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ NULL,
+};
+
+static const struct attribute_group spr_uncore_raw_format_group = {
+ .name = "format",
+ .attrs = spr_uncore_raw_formats_attr,
+};
+
+#define SPR_UNCORE_COMMON_FORMAT() \
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK, \
+ .event_mask_ext = SPR_RAW_EVENT_MASK_EXT, \
+ .format_group = &spr_uncore_raw_format_group, \
+ .attr_update = uncore_alias_groups
+
+static struct intel_uncore_type spr_uncore_irp = {
+ SPR_UNCORE_COMMON_FORMAT(),
+ .name = "irp",
+
+};
+
+static struct intel_uncore_type spr_uncore_m2pcie = {
+ SPR_UNCORE_COMMON_FORMAT(),
+ .name = "m2pcie",
+};
+
+static struct intel_uncore_type spr_uncore_pcu = {
+ .name = "pcu",
+ .attr_update = uncore_alias_groups,
+};
+
+static void spr_uncore_mmio_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!box->io_addr)
+ return;
+
+ if (uncore_pmc_fixed(hwc->idx))
+ writel(SNBEP_PMON_CTL_EN, box->io_addr + hwc->config_base);
+ else
+ writel(hwc->config, box->io_addr + hwc->config_base);
+}
+
+static struct intel_uncore_ops spr_uncore_mmio_ops = {
+ .init_box = intel_generic_uncore_mmio_init_box,
+ .exit_box = uncore_mmio_exit_box,
+ .disable_box = intel_generic_uncore_mmio_disable_box,
+ .enable_box = intel_generic_uncore_mmio_enable_box,
+ .disable_event = intel_generic_uncore_mmio_disable_event,
+ .enable_event = spr_uncore_mmio_enable_event,
+ .read_counter = uncore_mmio_read_counter,
+};
+
+static struct intel_uncore_type spr_uncore_imc = {
+ SPR_UNCORE_COMMON_FORMAT(),
+ .name = "imc",
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR,
+ .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL,
+ .ops = &spr_uncore_mmio_ops,
+};
+
+static void spr_uncore_pci_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+
+ pci_write_config_dword(pdev, hwc->config_base + 4, (u32)(hwc->config >> 32));
+ pci_write_config_dword(pdev, hwc->config_base, (u32)hwc->config);
+}
+
+static struct intel_uncore_ops spr_uncore_pci_ops = {
+ .init_box = intel_generic_uncore_pci_init_box,
+ .disable_box = intel_generic_uncore_pci_disable_box,
+ .enable_box = intel_generic_uncore_pci_enable_box,
+ .disable_event = intel_generic_uncore_pci_disable_event,
+ .enable_event = spr_uncore_pci_enable_event,
+ .read_counter = intel_generic_uncore_pci_read_counter,
+};
+
+#define SPR_UNCORE_PCI_COMMON_FORMAT() \
+ SPR_UNCORE_COMMON_FORMAT(), \
+ .ops = &spr_uncore_pci_ops
+
+static struct intel_uncore_type spr_uncore_m2m = {
+ SPR_UNCORE_PCI_COMMON_FORMAT(),
+ .name = "m2m",
+};
+
+static struct intel_uncore_type spr_uncore_upi = {
+ SPR_UNCORE_PCI_COMMON_FORMAT(),
+ .name = "upi",
+};
+
+static struct intel_uncore_type spr_uncore_m3upi = {
+ SPR_UNCORE_PCI_COMMON_FORMAT(),
+ .name = "m3upi",
+};
+
+static struct intel_uncore_type spr_uncore_mdf = {
+ SPR_UNCORE_COMMON_FORMAT(),
+ .name = "mdf",
+};
+
+#define UNCORE_SPR_NUM_UNCORE_TYPES 12
+#define UNCORE_SPR_IIO 1
+#define UNCORE_SPR_IMC 6
+
+static struct intel_uncore_type *spr_uncores[UNCORE_SPR_NUM_UNCORE_TYPES] = {
+ &spr_uncore_chabox,
+ &spr_uncore_iio,
+ &spr_uncore_irp,
+ &spr_uncore_m2pcie,
+ &spr_uncore_pcu,
+ NULL,
+ &spr_uncore_imc,
+ &spr_uncore_m2m,
+ &spr_uncore_upi,
+ &spr_uncore_m3upi,
+ NULL,
+ &spr_uncore_mdf,
+};
+
+enum perf_uncore_spr_iio_freerunning_type_id {
+ SPR_IIO_MSR_IOCLK,
+ SPR_IIO_MSR_BW_IN,
+ SPR_IIO_MSR_BW_OUT,
+
+ SPR_IIO_FREERUNNING_TYPE_MAX,
+};
+
+static struct freerunning_counters spr_iio_freerunning[] = {
+ [SPR_IIO_MSR_IOCLK] = { 0x340e, 0x1, 0x10, 1, 48 },
+ [SPR_IIO_MSR_BW_IN] = { 0x3800, 0x1, 0x10, 8, 48 },
+ [SPR_IIO_MSR_BW_OUT] = { 0x3808, 0x1, 0x10, 8, 48 },
+};
+
+static struct uncore_event_desc spr_uncore_iio_freerunning_events[] = {
+ /* Free-Running IIO CLOCKS Counter */
+ INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"),
+ /* Free-Running IIO BANDWIDTH IN Counters */
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"),
+ /* Free-Running IIO BANDWIDTH OUT Counters */
+ INTEL_UNCORE_EVENT_DESC(bw_out_port0, "event=0xff,umask=0x30"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port0.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port0.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port1, "event=0xff,umask=0x31"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port1.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port1.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port2, "event=0xff,umask=0x32"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port2.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port2.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port3, "event=0xff,umask=0x33"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port3.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port3.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port4, "event=0xff,umask=0x34"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port4.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port4.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port5, "event=0xff,umask=0x35"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port5.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port5.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port6, "event=0xff,umask=0x36"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port6.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port6.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port7, "event=0xff,umask=0x37"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port7.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port7.unit, "MiB"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type spr_uncore_iio_free_running = {
+ .name = "iio_free_running",
+ .num_counters = 17,
+ .num_freerunning_types = SPR_IIO_FREERUNNING_TYPE_MAX,
+ .freerunning = spr_iio_freerunning,
+ .ops = &skx_uncore_iio_freerunning_ops,
+ .event_descs = spr_uncore_iio_freerunning_events,
+ .format_group = &skx_uncore_iio_freerunning_format_group,
+};
+
+enum perf_uncore_spr_imc_freerunning_type_id {
+ SPR_IMC_DCLK,
+ SPR_IMC_PQ_CYCLES,
+
+ SPR_IMC_FREERUNNING_TYPE_MAX,
+};
+
+static struct freerunning_counters spr_imc_freerunning[] = {
+ [SPR_IMC_DCLK] = { 0x22b0, 0x0, 0, 1, 48 },
+ [SPR_IMC_PQ_CYCLES] = { 0x2318, 0x8, 0, 2, 48 },
+};
+
+static struct uncore_event_desc spr_uncore_imc_freerunning_events[] = {
+ INTEL_UNCORE_EVENT_DESC(dclk, "event=0xff,umask=0x10"),
+
+ INTEL_UNCORE_EVENT_DESC(rpq_cycles, "event=0xff,umask=0x20"),
+ INTEL_UNCORE_EVENT_DESC(wpq_cycles, "event=0xff,umask=0x21"),
+ { /* end: all zeroes */ },
+};
+
+#define SPR_MC_DEVICE_ID 0x3251
+
+static void spr_uncore_imc_freerunning_init_box(struct intel_uncore_box *box)
+{
+ int mem_offset = box->pmu->pmu_idx * ICX_IMC_MEM_STRIDE + SNR_IMC_MMIO_MEM0_OFFSET;
+
+ snr_uncore_mmio_map(box, uncore_mmio_box_ctl(box),
+ mem_offset, SPR_MC_DEVICE_ID);
+}
+
+static struct intel_uncore_ops spr_uncore_imc_freerunning_ops = {
+ .init_box = spr_uncore_imc_freerunning_init_box,
+ .exit_box = uncore_mmio_exit_box,
+ .read_counter = uncore_mmio_read_counter,
+ .hw_config = uncore_freerunning_hw_config,
+};
+
+static struct intel_uncore_type spr_uncore_imc_free_running = {
+ .name = "imc_free_running",
+ .num_counters = 3,
+ .mmio_map_size = SNR_IMC_MMIO_SIZE,
+ .num_freerunning_types = SPR_IMC_FREERUNNING_TYPE_MAX,
+ .freerunning = spr_imc_freerunning,
+ .ops = &spr_uncore_imc_freerunning_ops,
+ .event_descs = spr_uncore_imc_freerunning_events,
+ .format_group = &skx_uncore_iio_freerunning_format_group,
+};
+
+#define UNCORE_SPR_MSR_EXTRA_UNCORES 1
+#define UNCORE_SPR_MMIO_EXTRA_UNCORES 1
+
+static struct intel_uncore_type *spr_msr_uncores[UNCORE_SPR_MSR_EXTRA_UNCORES] = {
+ &spr_uncore_iio_free_running,
+};
+
+static struct intel_uncore_type *spr_mmio_uncores[UNCORE_SPR_MMIO_EXTRA_UNCORES] = {
+ &spr_uncore_imc_free_running,
+};
+
+static void uncore_type_customized_copy(struct intel_uncore_type *to_type,
+ struct intel_uncore_type *from_type)
+{
+ if (!to_type || !from_type)
+ return;
+
+ if (from_type->name)
+ to_type->name = from_type->name;
+ if (from_type->fixed_ctr_bits)
+ to_type->fixed_ctr_bits = from_type->fixed_ctr_bits;
+ if (from_type->event_mask)
+ to_type->event_mask = from_type->event_mask;
+ if (from_type->event_mask_ext)
+ to_type->event_mask_ext = from_type->event_mask_ext;
+ if (from_type->fixed_ctr)
+ to_type->fixed_ctr = from_type->fixed_ctr;
+ if (from_type->fixed_ctl)
+ to_type->fixed_ctl = from_type->fixed_ctl;
+ if (from_type->fixed_ctr_bits)
+ to_type->fixed_ctr_bits = from_type->fixed_ctr_bits;
+ if (from_type->num_shared_regs)
+ to_type->num_shared_regs = from_type->num_shared_regs;
+ if (from_type->constraints)
+ to_type->constraints = from_type->constraints;
+ if (from_type->ops)
+ to_type->ops = from_type->ops;
+ if (from_type->event_descs)
+ to_type->event_descs = from_type->event_descs;
+ if (from_type->format_group)
+ to_type->format_group = from_type->format_group;
+ if (from_type->attr_update)
+ to_type->attr_update = from_type->attr_update;
+}
+
+static struct intel_uncore_type **
+uncore_get_uncores(enum uncore_access_type type_id, int num_extra,
+ struct intel_uncore_type **extra)
+{
+ struct intel_uncore_type **types, **start_types;
+ int i;
+
+ start_types = types = intel_uncore_generic_init_uncores(type_id, num_extra);
+
+ /* Only copy the customized features */
+ for (; *types; types++) {
+ if ((*types)->type_id >= UNCORE_SPR_NUM_UNCORE_TYPES)
+ continue;
+ uncore_type_customized_copy(*types, spr_uncores[(*types)->type_id]);
+ }
+
+ for (i = 0; i < num_extra; i++, types++)
+ *types = extra[i];
+
+ return start_types;
+}
+
+static struct intel_uncore_type *
+uncore_find_type_by_id(struct intel_uncore_type **types, int type_id)
+{
+ for (; *types; types++) {
+ if (type_id == (*types)->type_id)
+ return *types;
+ }
+
+ return NULL;
+}
+
+static int uncore_type_max_boxes(struct intel_uncore_type **types,
+ int type_id)
+{
+ struct intel_uncore_type *type;
+ int i, max = 0;
+
+ type = uncore_find_type_by_id(types, type_id);
+ if (!type)
+ return 0;
+
+ for (i = 0; i < type->num_boxes; i++) {
+ if (type->box_ids[i] > max)
+ max = type->box_ids[i];
+ }
+
+ return max + 1;
+}
+
+void spr_uncore_cpu_init(void)
+{
+ uncore_msr_uncores = uncore_get_uncores(UNCORE_ACCESS_MSR,
+ UNCORE_SPR_MSR_EXTRA_UNCORES,
+ spr_msr_uncores);
+
+ spr_uncore_iio_free_running.num_boxes = uncore_type_max_boxes(uncore_msr_uncores, UNCORE_SPR_IIO);
+}
+
+int spr_uncore_pci_init(void)
+{
+ uncore_pci_uncores = uncore_get_uncores(UNCORE_ACCESS_PCI, 0, NULL);
+ return 0;
+}
+
+void spr_uncore_mmio_init(void)
+{
+ int ret = snbep_pci2phy_map_init(0x3250, SKX_CPUNODEID, SKX_GIDNIDMAP, true);
+
+ if (ret)
+ uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO, 0, NULL);
+ else {
+ uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO,
+ UNCORE_SPR_MMIO_EXTRA_UNCORES,
+ spr_mmio_uncores);
+
+ spr_uncore_imc_free_running.num_boxes = uncore_type_max_boxes(uncore_mmio_uncores, UNCORE_SPR_IMC) / 2;
+ }
+}
+
+/* end of SPR uncore support */
diff --git a/arch/x86/include/asm/amd-ibs.h b/arch/x86/include/asm/amd-ibs.h
new file mode 100644
index 000000000000..46e1df45efc0
--- /dev/null
+++ b/arch/x86/include/asm/amd-ibs.h
@@ -0,0 +1,132 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * From PPR Vol 1 for AMD Family 19h Model 01h B1
+ * 55898 Rev 0.35 - Feb 5, 2021
+ */
+
+#include <asm/msr-index.h>
+
+/*
+ * IBS Hardware MSRs
+ */
+
+/* MSR 0xc0011030: IBS Fetch Control */
+union ibs_fetch_ctl {
+ __u64 val;
+ struct {
+ __u64 fetch_maxcnt:16,/* 0-15: instruction fetch max. count */
+ fetch_cnt:16, /* 16-31: instruction fetch count */
+ fetch_lat:16, /* 32-47: instruction fetch latency */
+ fetch_en:1, /* 48: instruction fetch enable */
+ fetch_val:1, /* 49: instruction fetch valid */
+ fetch_comp:1, /* 50: instruction fetch complete */
+ ic_miss:1, /* 51: i-cache miss */
+ phy_addr_valid:1,/* 52: physical address valid */
+ l1tlb_pgsz:2, /* 53-54: i-cache L1TLB page size
+ * (needs IbsPhyAddrValid) */
+ l1tlb_miss:1, /* 55: i-cache fetch missed in L1TLB */
+ l2tlb_miss:1, /* 56: i-cache fetch missed in L2TLB */
+ rand_en:1, /* 57: random tagging enable */
+ fetch_l2_miss:1,/* 58: L2 miss for sampled fetch
+ * (needs IbsFetchComp) */
+ reserved:5; /* 59-63: reserved */
+ };
+};
+
+/* MSR 0xc0011033: IBS Execution Control */
+union ibs_op_ctl {
+ __u64 val;
+ struct {
+ __u64 opmaxcnt:16, /* 0-15: periodic op max. count */
+ reserved0:1, /* 16: reserved */
+ op_en:1, /* 17: op sampling enable */
+ op_val:1, /* 18: op sample valid */
+ cnt_ctl:1, /* 19: periodic op counter control */
+ opmaxcnt_ext:7, /* 20-26: upper 7 bits of periodic op maximum count */
+ reserved1:5, /* 27-31: reserved */
+ opcurcnt:27, /* 32-58: periodic op counter current count */
+ reserved2:5; /* 59-63: reserved */
+ };
+};
+
+/* MSR 0xc0011035: IBS Op Data 2 */
+union ibs_op_data {
+ __u64 val;
+ struct {
+ __u64 comp_to_ret_ctr:16, /* 0-15: op completion to retire count */
+ tag_to_ret_ctr:16, /* 15-31: op tag to retire count */
+ reserved1:2, /* 32-33: reserved */
+ op_return:1, /* 34: return op */
+ op_brn_taken:1, /* 35: taken branch op */
+ op_brn_misp:1, /* 36: mispredicted branch op */
+ op_brn_ret:1, /* 37: branch op retired */
+ op_rip_invalid:1, /* 38: RIP is invalid */
+ op_brn_fuse:1, /* 39: fused branch op */
+ op_microcode:1, /* 40: microcode op */
+ reserved2:23; /* 41-63: reserved */
+ };
+};
+
+/* MSR 0xc0011036: IBS Op Data 2 */
+union ibs_op_data2 {
+ __u64 val;
+ struct {
+ __u64 data_src:3, /* 0-2: data source */
+ reserved0:1, /* 3: reserved */
+ rmt_node:1, /* 4: destination node */
+ cache_hit_st:1, /* 5: cache hit state */
+ reserved1:57; /* 5-63: reserved */
+ };
+};
+
+/* MSR 0xc0011037: IBS Op Data 3 */
+union ibs_op_data3 {
+ __u64 val;
+ struct {
+ __u64 ld_op:1, /* 0: load op */
+ st_op:1, /* 1: store op */
+ dc_l1tlb_miss:1, /* 2: data cache L1TLB miss */
+ dc_l2tlb_miss:1, /* 3: data cache L2TLB hit in 2M page */
+ dc_l1tlb_hit_2m:1, /* 4: data cache L1TLB hit in 2M page */
+ dc_l1tlb_hit_1g:1, /* 5: data cache L1TLB hit in 1G page */
+ dc_l2tlb_hit_2m:1, /* 6: data cache L2TLB hit in 2M page */
+ dc_miss:1, /* 7: data cache miss */
+ dc_mis_acc:1, /* 8: misaligned access */
+ reserved:4, /* 9-12: reserved */
+ dc_wc_mem_acc:1, /* 13: write combining memory access */
+ dc_uc_mem_acc:1, /* 14: uncacheable memory access */
+ dc_locked_op:1, /* 15: locked operation */
+ dc_miss_no_mab_alloc:1, /* 16: DC miss with no MAB allocated */
+ dc_lin_addr_valid:1, /* 17: data cache linear address valid */
+ dc_phy_addr_valid:1, /* 18: data cache physical address valid */
+ dc_l2_tlb_hit_1g:1, /* 19: data cache L2 hit in 1GB page */
+ l2_miss:1, /* 20: L2 cache miss */
+ sw_pf:1, /* 21: software prefetch */
+ op_mem_width:4, /* 22-25: load/store size in bytes */
+ op_dc_miss_open_mem_reqs:6, /* 26-31: outstanding mem reqs on DC fill */
+ dc_miss_lat:16, /* 32-47: data cache miss latency */
+ tlb_refill_lat:16; /* 48-63: L1 TLB refill latency */
+ };
+};
+
+/* MSR 0xc001103c: IBS Fetch Control Extended */
+union ic_ibs_extd_ctl {
+ __u64 val;
+ struct {
+ __u64 itlb_refill_lat:16, /* 0-15: ITLB Refill latency for sampled fetch */
+ reserved:48; /* 16-63: reserved */
+ };
+};
+
+/*
+ * IBS driver related
+ */
+
+struct perf_ibs_data {
+ u32 size;
+ union {
+ u32 data[0]; /* data buffer starts here */
+ u32 caps;
+ };
+ u64 regs[MSR_AMD64_IBS_REG_COUNT_MAX];
+};
diff --git a/arch/x86/include/asm/kfence.h b/arch/x86/include/asm/kfence.h
index 05b48b33baf0..ff5c7134a37a 100644
--- a/arch/x86/include/asm/kfence.h
+++ b/arch/x86/include/asm/kfence.h
@@ -8,6 +8,8 @@
#ifndef _ASM_X86_KFENCE_H
#define _ASM_X86_KFENCE_H
+#ifndef MODULE
+
#include <linux/bug.h>
#include <linux/kfence.h>
@@ -66,4 +68,6 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
return true;
}
+#endif /* !MODULE */
+
#endif /* _ASM_X86_KFENCE_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 974cbfb1eefe..af6ce8d4c86a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1038,6 +1038,13 @@ struct kvm_arch {
struct list_head lpage_disallowed_mmu_pages;
struct kvm_page_track_notifier_node mmu_sp_tracker;
struct kvm_page_track_notifier_head track_notifier_head;
+ /*
+ * Protects marking pages unsync during page faults, as TDP MMU page
+ * faults only take mmu_lock for read. For simplicity, the unsync
+ * pages lock is always taken when marking pages unsync regardless of
+ * whether mmu_lock is held for read or write.
+ */
+ spinlock_t mmu_unsync_pages_lock;
struct list_head assigned_dev_head;
struct iommu_domain *iommu_domain;
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 0607ec4f5091..da9321548f6f 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -265,6 +265,7 @@ enum mcp_flags {
MCP_TIMESTAMP = BIT(0), /* log time stamp */
MCP_UC = BIT(1), /* log uncorrected errors */
MCP_DONTLOG = BIT(2), /* only clear, don't log */
+ MCP_QUEUE_LOG = BIT(3), /* only queue to genpool */
};
bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 3ad8c6d3cbb3..ec2d5c8c6694 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -252,6 +252,8 @@ DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
DECLARE_STATIC_KEY_FALSE(mds_user_clear);
DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
+DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
+
#include <asm/segment.h>
/**
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index f3020c54e2cb..9ad2acaaae9b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -136,6 +136,8 @@ struct cpuinfo_x86 {
u16 logical_die_id;
/* Index into per_cpu list: */
u16 cpu_index;
+ /* Is SMT active on this core? */
+ bool smt_active;
u32 microcode;
/* Address space bits used by the cache internally */
u8 x86_cache_bits;
@@ -795,6 +797,8 @@ extern int set_tsc_mode(unsigned int val);
DECLARE_PER_CPU(u64, msr_misc_features_shadow);
+extern u16 get_llc_id(unsigned int cpu);
+
#ifdef CONFIG_CPU_SUP_AMD
extern u32 amd_get_nodes_per_socket(void);
extern u32 amd_get_highest_perf(void);
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index e322676039f4..b00dbc5fac2b 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -184,6 +184,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
#define V_IGN_TPR_SHIFT 20
#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT)
+#define V_IRQ_INJECTION_BITS_MASK (V_IRQ_MASK | V_INTR_PRIO_MASK | V_IGN_TPR_MASK)
+
#define V_INTR_MASKING_SHIFT 24
#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT)
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index de406d93b515..cf132663c219 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -81,7 +81,7 @@ struct thread_info {
#define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/
#define TIF_SSBD 5 /* Speculative store bypass disable */
#define TIF_SPEC_IB 9 /* Indirect branch speculation mitigation */
-#define TIF_SPEC_FORCE_UPDATE 10 /* Force speculation MSR update in context switch */
+#define TIF_SPEC_L1D_FLUSH 10 /* Flush L1D on mm switches (processes) */
#define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */
#define TIF_UPROBE 12 /* breakpointed or singlestepping */
#define TIF_PATCH_PENDING 13 /* pending live patching update */
@@ -93,6 +93,7 @@ struct thread_info {
#define TIF_MEMDIE 20 /* is terminating due to OOM killer */
#define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */
#define TIF_IO_BITMAP 22 /* uses I/O bitmap */
+#define TIF_SPEC_FORCE_UPDATE 23 /* Force speculation MSR update in context switch */
#define TIF_FORCED_TF 24 /* true if TF in eflags artificially */
#define TIF_BLOCKSTEP 25 /* set when we want DEBUGCTLMSR_BTF */
#define TIF_LAZY_MMU_UPDATES 27 /* task is updating the mmu lazily */
@@ -104,7 +105,7 @@ struct thread_info {
#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP)
#define _TIF_SSBD (1 << TIF_SSBD)
#define _TIF_SPEC_IB (1 << TIF_SPEC_IB)
-#define _TIF_SPEC_FORCE_UPDATE (1 << TIF_SPEC_FORCE_UPDATE)
+#define _TIF_SPEC_L1D_FLUSH (1 << TIF_SPEC_L1D_FLUSH)
#define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY)
#define _TIF_UPROBE (1 << TIF_UPROBE)
#define _TIF_PATCH_PENDING (1 << TIF_PATCH_PENDING)
@@ -115,6 +116,7 @@ struct thread_info {
#define _TIF_SLD (1 << TIF_SLD)
#define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG)
#define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP)
+#define _TIF_SPEC_FORCE_UPDATE (1 << TIF_SPEC_FORCE_UPDATE)
#define _TIF_FORCED_TF (1 << TIF_FORCED_TF)
#define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP)
#define _TIF_LAZY_MMU_UPDATES (1 << TIF_LAZY_MMU_UPDATES)
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index fa952eadbc2e..b587a9ee9cb2 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -83,7 +83,7 @@ struct tlb_state {
/* Last user mm for optimizing IBPB */
union {
struct mm_struct *last_user_mm;
- unsigned long last_user_mm_ibpb;
+ unsigned long last_user_mm_spec;
};
u16 loaded_mm_asid;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 7846499c54ec..c1bb384935b0 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1986,7 +1986,8 @@ static struct irq_chip ioapic_chip __read_mostly = {
.irq_set_affinity = ioapic_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_get_irqchip_state = ioapic_irq_get_chip_state,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
static struct irq_chip ioapic_ir_chip __read_mostly = {
@@ -1999,7 +2000,8 @@ static struct irq_chip ioapic_ir_chip __read_mostly = {
.irq_set_affinity = ioapic_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_get_irqchip_state = ioapic_irq_get_chip_state,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
static inline void init_IO_APIC_traps(void)
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 44ebe25e7703..dbacb9ec8843 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -58,11 +58,13 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force)
* The quirk bit is not set in this case.
* - The new vector is the same as the old vector
* - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up)
+ * - The interrupt is not yet started up
* - The new destination CPU is the same as the old destination CPU
*/
if (!irqd_msi_nomask_quirk(irqd) ||
cfg->vector == old_cfg.vector ||
old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR ||
+ !irqd_is_started(irqd) ||
cfg->dest_apicid == old_cfg.dest_apicid) {
irq_msi_update_msg(irqd, cfg);
return ret;
@@ -150,7 +152,8 @@ static struct irq_chip pci_msi_controller = {
.irq_ack = irq_chip_ack_parent,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_set_affinity = msi_set_affinity,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
@@ -219,7 +222,8 @@ static struct irq_chip pci_msi_ir_controller = {
.irq_mask = pci_msi_mask_irq,
.irq_ack = irq_chip_ack_parent,
.irq_retrigger = irq_chip_retrigger_hierarchy,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
static struct msi_domain_info pci_msi_ir_domain_info = {
@@ -273,7 +277,8 @@ static struct irq_chip dmar_msi_controller = {
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_compose_msi_msg = dmar_msi_compose_msg,
.irq_write_msi_msg = dmar_msi_write_msg,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
static int dmar_msi_init(struct irq_domain *domain,
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index b7c003013d41..2131af9f2fa2 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -438,7 +438,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
node = numa_cpu_node(cpu);
if (node == NUMA_NO_NODE)
- node = per_cpu(cpu_llc_id, cpu);
+ node = get_llc_id(cpu);
/*
* On multi-fabric platform (e.g. Numascale NumaChip) a
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d41b70fe4918..ecfca3bbcd96 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -43,6 +43,7 @@ static void __init mds_select_mitigation(void);
static void __init mds_print_mitigation(void);
static void __init taa_select_mitigation(void);
static void __init srbds_select_mitigation(void);
+static void __init l1d_flush_select_mitigation(void);
/* The base value of the SPEC_CTRL MSR that always has to be preserved. */
u64 x86_spec_ctrl_base;
@@ -76,6 +77,13 @@ EXPORT_SYMBOL_GPL(mds_user_clear);
DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
EXPORT_SYMBOL_GPL(mds_idle_clear);
+/*
+ * Controls whether l1d flush based mitigations are enabled,
+ * based on hw features and admin setting via boot parameter
+ * defaults to false
+ */
+DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
+
void __init check_bugs(void)
{
identify_boot_cpu();
@@ -111,6 +119,7 @@ void __init check_bugs(void)
mds_select_mitigation();
taa_select_mitigation();
srbds_select_mitigation();
+ l1d_flush_select_mitigation();
/*
* As MDS and TAA mitigations are inter-related, print MDS
@@ -492,6 +501,34 @@ static int __init srbds_parse_cmdline(char *str)
early_param("srbds", srbds_parse_cmdline);
#undef pr_fmt
+#define pr_fmt(fmt) "L1D Flush : " fmt
+
+enum l1d_flush_mitigations {
+ L1D_FLUSH_OFF = 0,
+ L1D_FLUSH_ON,
+};
+
+static enum l1d_flush_mitigations l1d_flush_mitigation __initdata = L1D_FLUSH_OFF;
+
+static void __init l1d_flush_select_mitigation(void)
+{
+ if (!l1d_flush_mitigation || !boot_cpu_has(X86_FEATURE_FLUSH_L1D))
+ return;
+
+ static_branch_enable(&switch_mm_cond_l1d_flush);
+ pr_info("Conditional flush on switch_mm() enabled\n");
+}
+
+static int __init l1d_flush_parse_cmdline(char *str)
+{
+ if (!strcmp(str, "on"))
+ l1d_flush_mitigation = L1D_FLUSH_ON;
+
+ return 0;
+}
+early_param("l1d_flush", l1d_flush_parse_cmdline);
+
+#undef pr_fmt
#define pr_fmt(fmt) "Spectre V1 : " fmt
enum spectre_v1_mitigation {
@@ -1215,6 +1252,24 @@ static void task_update_spec_tif(struct task_struct *tsk)
speculation_ctrl_update_current();
}
+static int l1d_flush_prctl_set(struct task_struct *task, unsigned long ctrl)
+{
+
+ if (!static_branch_unlikely(&switch_mm_cond_l1d_flush))
+ return -EPERM;
+
+ switch (ctrl) {
+ case PR_SPEC_ENABLE:
+ set_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH);
+ return 0;
+ case PR_SPEC_DISABLE:
+ clear_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH);
+ return 0;
+ default:
+ return -ERANGE;
+ }
+}
+
static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
{
if (ssb_mode != SPEC_STORE_BYPASS_PRCTL &&
@@ -1324,6 +1379,8 @@ int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
return ssb_prctl_set(task, ctrl);
case PR_SPEC_INDIRECT_BRANCH:
return ib_prctl_set(task, ctrl);
+ case PR_SPEC_L1D_FLUSH:
+ return l1d_flush_prctl_set(task, ctrl);
default:
return -ENODEV;
}
@@ -1340,6 +1397,17 @@ void arch_seccomp_spec_mitigate(struct task_struct *task)
}
#endif
+static int l1d_flush_prctl_get(struct task_struct *task)
+{
+ if (!static_branch_unlikely(&switch_mm_cond_l1d_flush))
+ return PR_SPEC_FORCE_DISABLE;
+
+ if (test_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH))
+ return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
+ else
+ return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
+}
+
static int ssb_prctl_get(struct task_struct *task)
{
switch (ssb_mode) {
@@ -1390,6 +1458,8 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
return ssb_prctl_get(task);
case PR_SPEC_INDIRECT_BRANCH:
return ib_prctl_get(task);
+ case PR_SPEC_L1D_FLUSH:
+ return l1d_flush_prctl_get(task);
default:
return -ENODEV;
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 64b805bd6a54..0f8885949e8c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -79,6 +79,12 @@ EXPORT_SYMBOL(smp_num_siblings);
/* Last level cache ID of each logical CPU */
DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
+u16 get_llc_id(unsigned int cpu)
+{
+ return per_cpu(cpu_llc_id, cpu);
+}
+EXPORT_SYMBOL_GPL(get_llc_id);
+
/* correctly size the local cpu masks */
void __init setup_cpu_local_masks(void)
{
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 22791aadc085..8cb7816d03b4 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -817,7 +817,10 @@ log_it:
if (mca_cfg.dont_log_ce && !mce_usable_address(&m))
goto clear_it;
- mce_log(&m);
+ if (flags & MCP_QUEUE_LOG)
+ mce_gen_pool_add(&m);
+ else
+ mce_log(&m);
clear_it:
/*
@@ -1639,10 +1642,12 @@ static void __mcheck_cpu_init_generic(void)
m_fl = MCP_DONTLOG;
/*
- * Log the machine checks left over from the previous reset.
+ * Log the machine checks left over from the previous reset. Log them
+ * only, do not start processing them. That will happen in mcheck_late_init()
+ * when all consumers have been registered on the notifier chain.
*/
bitmap_fill(all_banks, MAX_NR_BANKS);
- machine_check_poll(MCP_UC | m_fl, &all_banks);
+ machine_check_poll(MCP_UC | MCP_QUEUE_LOG | m_fl, &all_banks);
cr4_set_bits(X86_CR4_MCE);
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 4e86d97f9653..0bfc14041bbb 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -235,7 +235,7 @@ static void __maybe_unused raise_mce(struct mce *m)
unsigned long start;
int cpu;
- get_online_cpus();
+ cpus_read_lock();
cpumask_copy(mce_inject_cpumask, cpu_online_mask);
cpumask_clear_cpu(get_cpu(), mce_inject_cpumask);
for_each_online_cpu(cpu) {
@@ -269,7 +269,7 @@ static void __maybe_unused raise_mce(struct mce *m)
}
raise_local();
put_cpu();
- put_online_cpus();
+ cpus_read_unlock();
} else {
preempt_disable();
raise_local();
@@ -529,7 +529,7 @@ static void do_inject(void)
cpu = get_nbc_for_node(topology_die_id(cpu));
}
- get_online_cpus();
+ cpus_read_lock();
if (!cpu_online(cpu))
goto err;
@@ -553,7 +553,7 @@ static void do_inject(void)
}
err:
- put_online_cpus();
+ cpus_read_unlock();
}
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 6a6318e9590c..efb69be41ab1 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -55,7 +55,7 @@ LIST_HEAD(microcode_cache);
* All non cpu-hotplug-callback call sites use:
*
* - microcode_mutex to synchronize with each other;
- * - get/put_online_cpus() to synchronize with
+ * - cpus_read_lock/unlock() to synchronize with
* the cpu-hotplug-callback call sites.
*
* We guarantee that only a single cpu is being
@@ -431,7 +431,7 @@ static ssize_t microcode_write(struct file *file, const char __user *buf,
return ret;
}
- get_online_cpus();
+ cpus_read_lock();
mutex_lock(&microcode_mutex);
if (do_microcode_update(buf, len) == 0)
@@ -441,7 +441,7 @@ static ssize_t microcode_write(struct file *file, const char __user *buf,
perf_check_microcode();
mutex_unlock(&microcode_mutex);
- put_online_cpus();
+ cpus_read_unlock();
return ret;
}
@@ -629,7 +629,7 @@ static ssize_t reload_store(struct device *dev,
if (val != 1)
return size;
- get_online_cpus();
+ cpus_read_lock();
ret = check_online_cpus();
if (ret)
@@ -644,7 +644,7 @@ static ssize_t reload_store(struct device *dev,
mutex_unlock(&microcode_mutex);
put:
- put_online_cpus();
+ cpus_read_unlock();
if (ret == 0)
ret = size;
@@ -853,14 +853,14 @@ static int __init microcode_init(void)
if (IS_ERR(microcode_pdev))
return PTR_ERR(microcode_pdev);
- get_online_cpus();
+ cpus_read_lock();
mutex_lock(&microcode_mutex);
error = subsys_interface_register(&mc_cpu_interface);
if (!error)
perf_check_microcode();
mutex_unlock(&microcode_mutex);
- put_online_cpus();
+ cpus_read_unlock();
if (error)
goto out_pdev;
@@ -892,13 +892,13 @@ static int __init microcode_init(void)
&cpu_root_microcode_group);
out_driver:
- get_online_cpus();
+ cpus_read_lock();
mutex_lock(&microcode_mutex);
subsys_interface_unregister(&mc_cpu_interface);
mutex_unlock(&microcode_mutex);
- put_online_cpus();
+ cpus_read_unlock();
out_pdev:
platform_device_unregister(microcode_pdev);
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c
index a76694bffe86..2746cac9d8a9 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.c
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.c
@@ -336,7 +336,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
replace = -1;
/* No CPU hotplug when we change MTRR entries */
- get_online_cpus();
+ cpus_read_lock();
/* Search for existing MTRR */
mutex_lock(&mtrr_mutex);
@@ -398,7 +398,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
error = i;
out:
mutex_unlock(&mtrr_mutex);
- put_online_cpus();
+ cpus_read_unlock();
return error;
}
@@ -485,7 +485,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
max = num_var_ranges;
/* No CPU hotplug when we change MTRR entries */
- get_online_cpus();
+ cpus_read_lock();
mutex_lock(&mtrr_mutex);
if (reg < 0) {
/* Search for existing MTRR */
@@ -520,7 +520,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
error = reg;
out:
mutex_unlock(&mtrr_mutex);
- put_online_cpus();
+ cpus_read_unlock();
return error;
}
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 23001ae03e82..4b8813bafffd 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -57,128 +57,57 @@ static void
mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m,
struct rdt_resource *r);
-#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains)
+#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains)
-struct rdt_resource rdt_resources_all[] = {
+struct rdt_hw_resource rdt_resources_all[] = {
[RDT_RESOURCE_L3] =
{
- .rid = RDT_RESOURCE_L3,
- .name = "L3",
- .domains = domain_init(RDT_RESOURCE_L3),
- .msr_base = MSR_IA32_L3_CBM_BASE,
- .msr_update = cat_wrmsr,
- .cache_level = 3,
- .cache = {
- .min_cbm_bits = 1,
- .cbm_idx_mult = 1,
- .cbm_idx_offset = 0,
- },
- .parse_ctrlval = parse_cbm,
- .format_str = "%d=%0*x",
- .fflags = RFTYPE_RES_CACHE,
- },
- [RDT_RESOURCE_L3DATA] =
- {
- .rid = RDT_RESOURCE_L3DATA,
- .name = "L3DATA",
- .domains = domain_init(RDT_RESOURCE_L3DATA),
- .msr_base = MSR_IA32_L3_CBM_BASE,
- .msr_update = cat_wrmsr,
- .cache_level = 3,
- .cache = {
- .min_cbm_bits = 1,
- .cbm_idx_mult = 2,
- .cbm_idx_offset = 0,
+ .r_resctrl = {
+ .rid = RDT_RESOURCE_L3,
+ .name = "L3",
+ .cache_level = 3,
+ .cache = {
+ .min_cbm_bits = 1,
+ },
+ .domains = domain_init(RDT_RESOURCE_L3),
+ .parse_ctrlval = parse_cbm,
+ .format_str = "%d=%0*x",
+ .fflags = RFTYPE_RES_CACHE,
},
- .parse_ctrlval = parse_cbm,
- .format_str = "%d=%0*x",
- .fflags = RFTYPE_RES_CACHE,
- },
- [RDT_RESOURCE_L3CODE] =
- {
- .rid = RDT_RESOURCE_L3CODE,
- .name = "L3CODE",
- .domains = domain_init(RDT_RESOURCE_L3CODE),
.msr_base = MSR_IA32_L3_CBM_BASE,
.msr_update = cat_wrmsr,
- .cache_level = 3,
- .cache = {
- .min_cbm_bits = 1,
- .cbm_idx_mult = 2,
- .cbm_idx_offset = 1,
- },
- .parse_ctrlval = parse_cbm,
- .format_str = "%d=%0*x",
- .fflags = RFTYPE_RES_CACHE,
},
[RDT_RESOURCE_L2] =
{
- .rid = RDT_RESOURCE_L2,
- .name = "L2",
- .domains = domain_init(RDT_RESOURCE_L2),
- .msr_base = MSR_IA32_L2_CBM_BASE,
- .msr_update = cat_wrmsr,
- .cache_level = 2,
- .cache = {
- .min_cbm_bits = 1,
- .cbm_idx_mult = 1,
- .cbm_idx_offset = 0,
+ .r_resctrl = {
+ .rid = RDT_RESOURCE_L2,
+ .name = "L2",
+ .cache_level = 2,
+ .cache = {
+ .min_cbm_bits = 1,
+ },
+ .domains = domain_init(RDT_RESOURCE_L2),
+ .parse_ctrlval = parse_cbm,
+ .format_str = "%d=%0*x",
+ .fflags = RFTYPE_RES_CACHE,
},
- .parse_ctrlval = parse_cbm,
- .format_str = "%d=%0*x",
- .fflags = RFTYPE_RES_CACHE,
- },
- [RDT_RESOURCE_L2DATA] =
- {
- .rid = RDT_RESOURCE_L2DATA,
- .name = "L2DATA",
- .domains = domain_init(RDT_RESOURCE_L2DATA),
.msr_base = MSR_IA32_L2_CBM_BASE,
.msr_update = cat_wrmsr,
- .cache_level = 2,
- .cache = {
- .min_cbm_bits = 1,
- .cbm_idx_mult = 2,
- .cbm_idx_offset = 0,
- },
- .parse_ctrlval = parse_cbm,
- .format_str = "%d=%0*x",
- .fflags = RFTYPE_RES_CACHE,
- },
- [RDT_RESOURCE_L2CODE] =
- {
- .rid = RDT_RESOURCE_L2CODE,
- .name = "L2CODE",
- .domains = domain_init(RDT_RESOURCE_L2CODE),
- .msr_base = MSR_IA32_L2_CBM_BASE,
- .msr_update = cat_wrmsr,
- .cache_level = 2,
- .cache = {
- .min_cbm_bits = 1,
- .cbm_idx_mult = 2,
- .cbm_idx_offset = 1,
- },
- .parse_ctrlval = parse_cbm,
- .format_str = "%d=%0*x",
- .fflags = RFTYPE_RES_CACHE,
},
[RDT_RESOURCE_MBA] =
{
- .rid = RDT_RESOURCE_MBA,
- .name = "MB",
- .domains = domain_init(RDT_RESOURCE_MBA),
- .cache_level = 3,
- .parse_ctrlval = parse_bw,
- .format_str = "%d=%*u",
- .fflags = RFTYPE_RES_MB,
+ .r_resctrl = {
+ .rid = RDT_RESOURCE_MBA,
+ .name = "MB",
+ .cache_level = 3,
+ .domains = domain_init(RDT_RESOURCE_MBA),
+ .parse_ctrlval = parse_bw,
+ .format_str = "%d=%*u",
+ .fflags = RFTYPE_RES_MB,
+ },
},
};
-static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid)
-{
- return closid * r->cache.cbm_idx_mult + r->cache.cbm_idx_offset;
-}
-
/*
* cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
* as they do not have CPUID enumeration support for Cache allocation.
@@ -199,7 +128,8 @@ static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid)
*/
static inline void cache_alloc_hsw_probe(void)
{
- struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
+ struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_L3];
+ struct rdt_resource *r = &hw_res->r_resctrl;
u32 l, h, max_cbm = BIT_MASK(20) - 1;
if (wrmsr_safe(MSR_IA32_L3_CBM_BASE, max_cbm, 0))
@@ -211,7 +141,7 @@ static inline void cache_alloc_hsw_probe(void)
if (l != max_cbm)
return;
- r->num_closid = 4;
+ hw_res->num_closid = 4;
r->default_ctrl = max_cbm;
r->cache.cbm_len = 20;
r->cache.shareable_bits = 0xc0000;
@@ -225,7 +155,7 @@ static inline void cache_alloc_hsw_probe(void)
bool is_mba_sc(struct rdt_resource *r)
{
if (!r)
- return rdt_resources_all[RDT_RESOURCE_MBA].membw.mba_sc;
+ return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.mba_sc;
return r->membw.mba_sc;
}
@@ -253,12 +183,13 @@ static inline bool rdt_get_mb_table(struct rdt_resource *r)
static bool __get_mem_config_intel(struct rdt_resource *r)
{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
union cpuid_0x10_3_eax eax;
union cpuid_0x10_x_edx edx;
u32 ebx, ecx, max_delay;
cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full);
- r->num_closid = edx.split.cos_max + 1;
+ hw_res->num_closid = edx.split.cos_max + 1;
max_delay = eax.split.max_delay + 1;
r->default_ctrl = MAX_MBA_BW;
r->membw.arch_needs_linear = true;
@@ -287,12 +218,13 @@ static bool __get_mem_config_intel(struct rdt_resource *r)
static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
union cpuid_0x10_3_eax eax;
union cpuid_0x10_x_edx edx;
u32 ebx, ecx;
cpuid_count(0x80000020, 1, &eax.full, &ebx, &ecx, &edx.full);
- r->num_closid = edx.split.cos_max + 1;
+ hw_res->num_closid = edx.split.cos_max + 1;
r->default_ctrl = MAX_MBA_BW_AMD;
/* AMD does not use delay */
@@ -317,12 +249,13 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
union cpuid_0x10_1_eax eax;
union cpuid_0x10_x_edx edx;
u32 ebx, ecx;
cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full);
- r->num_closid = edx.split.cos_max + 1;
+ hw_res->num_closid = edx.split.cos_max + 1;
r->cache.cbm_len = eax.split.cbm_len + 1;
r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1;
r->cache.shareable_bits = ebx & r->default_ctrl;
@@ -331,43 +264,35 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
r->alloc_enabled = true;
}
-static void rdt_get_cdp_config(int level, int type)
+static void rdt_get_cdp_config(int level)
{
- struct rdt_resource *r_l = &rdt_resources_all[level];
- struct rdt_resource *r = &rdt_resources_all[type];
-
- r->num_closid = r_l->num_closid / 2;
- r->cache.cbm_len = r_l->cache.cbm_len;
- r->default_ctrl = r_l->default_ctrl;
- r->cache.shareable_bits = r_l->cache.shareable_bits;
- r->data_width = (r->cache.cbm_len + 3) / 4;
- r->alloc_capable = true;
/*
* By default, CDP is disabled. CDP can be enabled by mount parameter
* "cdp" during resctrl file system mount time.
*/
- r->alloc_enabled = false;
+ rdt_resources_all[level].cdp_enabled = false;
+ rdt_resources_all[level].r_resctrl.cdp_capable = true;
}
static void rdt_get_cdp_l3_config(void)
{
- rdt_get_cdp_config(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA);
- rdt_get_cdp_config(RDT_RESOURCE_L3, RDT_RESOURCE_L3CODE);
+ rdt_get_cdp_config(RDT_RESOURCE_L3);
}
static void rdt_get_cdp_l2_config(void)
{
- rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA);
- rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2CODE);
+ rdt_get_cdp_config(RDT_RESOURCE_L2);
}
static void
mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
{
unsigned int i;
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
for (i = m->low; i < m->high; i++)
- wrmsrl(r->msr_base + i, d->ctrl_val[i]);
+ wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
}
/*
@@ -389,19 +314,23 @@ mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
struct rdt_resource *r)
{
unsigned int i;
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
/* Write the delay values for mba. */
for (i = m->low; i < m->high; i++)
- wrmsrl(r->msr_base + i, delay_bw_map(d->ctrl_val[i], r));
+ wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], r));
}
static void
cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
{
unsigned int i;
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
for (i = m->low; i < m->high; i++)
- wrmsrl(r->msr_base + cbm_idx(r, i), d->ctrl_val[i]);
+ wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
}
struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
@@ -417,16 +346,22 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
return NULL;
}
+u32 resctrl_arch_get_num_closid(struct rdt_resource *r)
+{
+ return resctrl_to_arch_res(r)->num_closid;
+}
+
void rdt_ctrl_update(void *arg)
{
struct msr_param *m = arg;
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
struct rdt_resource *r = m->res;
int cpu = smp_processor_id();
struct rdt_domain *d;
d = get_domain_from_cpu(cpu, r);
if (d) {
- r->msr_update(d, m, r);
+ hw_res->msr_update(d, m, r);
return;
}
pr_warn_once("cpu %d not found in any domain for resource %s\n",
@@ -468,6 +403,7 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm)
{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
int i;
/*
@@ -476,7 +412,7 @@ void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm)
* For Memory Allocation: Set b/w requested to 100%
* and the bandwidth in MBps to U32_MAX
*/
- for (i = 0; i < r->num_closid; i++, dc++, dm++) {
+ for (i = 0; i < hw_res->num_closid; i++, dc++, dm++) {
*dc = r->default_ctrl;
*dm = MBA_MAX_MBPS;
}
@@ -484,26 +420,30 @@ void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm)
static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
struct msr_param m;
u32 *dc, *dm;
- dc = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL);
+ dc = kmalloc_array(hw_res->num_closid, sizeof(*hw_dom->ctrl_val),
+ GFP_KERNEL);
if (!dc)
return -ENOMEM;
- dm = kmalloc_array(r->num_closid, sizeof(*d->mbps_val), GFP_KERNEL);
+ dm = kmalloc_array(hw_res->num_closid, sizeof(*hw_dom->mbps_val),
+ GFP_KERNEL);
if (!dm) {
kfree(dc);
return -ENOMEM;
}
- d->ctrl_val = dc;
- d->mbps_val = dm;
+ hw_dom->ctrl_val = dc;
+ hw_dom->mbps_val = dm;
setup_default_ctrlval(r, dc, dm);
m.low = 0;
- m.high = r->num_closid;
- r->msr_update(d, &m, r);
+ m.high = hw_res->num_closid;
+ hw_res->msr_update(d, &m, r);
return 0;
}
@@ -560,6 +500,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
{
int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
struct list_head *add_pos = NULL;
+ struct rdt_hw_domain *hw_dom;
struct rdt_domain *d;
d = rdt_find_domain(r, id, &add_pos);
@@ -575,10 +516,11 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
return;
}
- d = kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu));
- if (!d)
+ hw_dom = kzalloc_node(sizeof(*hw_dom), GFP_KERNEL, cpu_to_node(cpu));
+ if (!hw_dom)
return;
+ d = &hw_dom->d_resctrl;
d->id = id;
cpumask_set_cpu(cpu, &d->cpu_mask);
@@ -607,6 +549,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
static void domain_remove_cpu(int cpu, struct rdt_resource *r)
{
int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
+ struct rdt_hw_domain *hw_dom;
struct rdt_domain *d;
d = rdt_find_domain(r, id, NULL);
@@ -614,6 +557,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
pr_warn("Couldn't find cache id for CPU %d\n", cpu);
return;
}
+ hw_dom = resctrl_to_arch_dom(d);
cpumask_clear_cpu(cpu, &d->cpu_mask);
if (cpumask_empty(&d->cpu_mask)) {
@@ -646,16 +590,16 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
if (d->plr)
d->plr->d = NULL;
- kfree(d->ctrl_val);
- kfree(d->mbps_val);
+ kfree(hw_dom->ctrl_val);
+ kfree(hw_dom->mbps_val);
bitmap_free(d->rmid_busy_llc);
kfree(d->mbm_total);
kfree(d->mbm_local);
- kfree(d);
+ kfree(hw_dom);
return;
}
- if (r == &rdt_resources_all[RDT_RESOURCE_L3]) {
+ if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) {
if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
cancel_delayed_work(&d->mbm_over);
mbm_setup_overflow_handler(d, 0);
@@ -732,13 +676,8 @@ static int resctrl_offline_cpu(unsigned int cpu)
static __init void rdt_init_padding(void)
{
struct rdt_resource *r;
- int cl;
for_each_alloc_capable_rdt_resource(r) {
- cl = strlen(r->name);
- if (cl > max_name_width)
- max_name_width = cl;
-
if (r->data_width > max_data_width)
max_data_width = r->data_width;
}
@@ -827,19 +766,22 @@ static bool __init rdt_cpu_has(int flag)
static __init bool get_mem_config(void)
{
+ struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_MBA];
+
if (!rdt_cpu_has(X86_FEATURE_MBA))
return false;
if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
- return __get_mem_config_intel(&rdt_resources_all[RDT_RESOURCE_MBA]);
+ return __get_mem_config_intel(&hw_res->r_resctrl);
else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
- return __rdt_get_mem_config_amd(&rdt_resources_all[RDT_RESOURCE_MBA]);
+ return __rdt_get_mem_config_amd(&hw_res->r_resctrl);
return false;
}
static __init bool get_rdt_alloc_resources(void)
{
+ struct rdt_resource *r;
bool ret = false;
if (rdt_alloc_capable)
@@ -849,14 +791,16 @@ static __init bool get_rdt_alloc_resources(void)
return false;
if (rdt_cpu_has(X86_FEATURE_CAT_L3)) {
- rdt_get_cache_alloc_cfg(1, &rdt_resources_all[RDT_RESOURCE_L3]);
+ r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+ rdt_get_cache_alloc_cfg(1, r);
if (rdt_cpu_has(X86_FEATURE_CDP_L3))
rdt_get_cdp_l3_config();
ret = true;
}
if (rdt_cpu_has(X86_FEATURE_CAT_L2)) {
/* CPUID 0x10.2 fields are same format at 0x10.1 */
- rdt_get_cache_alloc_cfg(2, &rdt_resources_all[RDT_RESOURCE_L2]);
+ r = &rdt_resources_all[RDT_RESOURCE_L2].r_resctrl;
+ rdt_get_cache_alloc_cfg(2, r);
if (rdt_cpu_has(X86_FEATURE_CDP_L2))
rdt_get_cdp_l2_config();
ret = true;
@@ -870,6 +814,8 @@ static __init bool get_rdt_alloc_resources(void)
static __init bool get_rdt_mon_resources(void)
{
+ struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+
if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC))
rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID);
if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL))
@@ -880,7 +826,7 @@ static __init bool get_rdt_mon_resources(void)
if (!rdt_mon_features)
return false;
- return !rdt_get_mon_l3_config(&rdt_resources_all[RDT_RESOURCE_L3]);
+ return !rdt_get_mon_l3_config(r);
}
static __init void __check_quirks_intel(void)
@@ -918,42 +864,40 @@ static __init bool get_rdt_resources(void)
static __init void rdt_init_res_defs_intel(void)
{
+ struct rdt_hw_resource *hw_res;
struct rdt_resource *r;
for_each_rdt_resource(r) {
+ hw_res = resctrl_to_arch_res(r);
+
if (r->rid == RDT_RESOURCE_L3 ||
- r->rid == RDT_RESOURCE_L3DATA ||
- r->rid == RDT_RESOURCE_L3CODE ||
- r->rid == RDT_RESOURCE_L2 ||
- r->rid == RDT_RESOURCE_L2DATA ||
- r->rid == RDT_RESOURCE_L2CODE) {
+ r->rid == RDT_RESOURCE_L2) {
r->cache.arch_has_sparse_bitmaps = false;
r->cache.arch_has_empty_bitmaps = false;
r->cache.arch_has_per_cpu_cfg = false;
} else if (r->rid == RDT_RESOURCE_MBA) {
- r->msr_base = MSR_IA32_MBA_THRTL_BASE;
- r->msr_update = mba_wrmsr_intel;
+ hw_res->msr_base = MSR_IA32_MBA_THRTL_BASE;
+ hw_res->msr_update = mba_wrmsr_intel;
}
}
}
static __init void rdt_init_res_defs_amd(void)
{
+ struct rdt_hw_resource *hw_res;
struct rdt_resource *r;
for_each_rdt_resource(r) {
+ hw_res = resctrl_to_arch_res(r);
+
if (r->rid == RDT_RESOURCE_L3 ||
- r->rid == RDT_RESOURCE_L3DATA ||
- r->rid == RDT_RESOURCE_L3CODE ||
- r->rid == RDT_RESOURCE_L2 ||
- r->rid == RDT_RESOURCE_L2DATA ||
- r->rid == RDT_RESOURCE_L2CODE) {
+ r->rid == RDT_RESOURCE_L2) {
r->cache.arch_has_sparse_bitmaps = true;
r->cache.arch_has_empty_bitmaps = true;
r->cache.arch_has_per_cpu_cfg = true;
} else if (r->rid == RDT_RESOURCE_MBA) {
- r->msr_base = MSR_IA32_MBA_BW_BASE;
- r->msr_update = mba_wrmsr_amd;
+ hw_res->msr_base = MSR_IA32_MBA_BW_BASE;
+ hw_res->msr_update = mba_wrmsr_amd;
}
}
}
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index c877642e8a14..87666275eed9 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -57,20 +57,23 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
return true;
}
-int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
struct rdt_domain *d)
{
+ struct resctrl_staged_config *cfg;
+ struct rdt_resource *r = s->res;
unsigned long bw_val;
- if (d->have_new_ctrl) {
+ cfg = &d->staged_config[s->conf_type];
+ if (cfg->have_new_ctrl) {
rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
return -EINVAL;
}
if (!bw_validate(data->buf, &bw_val, r))
return -EINVAL;
- d->new_ctrl = bw_val;
- d->have_new_ctrl = true;
+ cfg->new_ctrl = bw_val;
+ cfg->have_new_ctrl = true;
return 0;
}
@@ -125,13 +128,16 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
* Read one cache bit mask (hex). Check that it is valid for the current
* resource type.
*/
-int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
+int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
struct rdt_domain *d)
{
struct rdtgroup *rdtgrp = data->rdtgrp;
+ struct resctrl_staged_config *cfg;
+ struct rdt_resource *r = s->res;
u32 cbm_val;
- if (d->have_new_ctrl) {
+ cfg = &d->staged_config[s->conf_type];
+ if (cfg->have_new_ctrl) {
rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
return -EINVAL;
}
@@ -160,12 +166,12 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
* The CBM may not overlap with the CBM of another closid if
* either is exclusive.
*/
- if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, true)) {
+ if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, true)) {
rdt_last_cmd_puts("Overlaps with exclusive group\n");
return -EINVAL;
}
- if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) {
+ if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, false)) {
if (rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
rdt_last_cmd_puts("Overlaps with other group\n");
@@ -173,8 +179,8 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
}
}
- d->new_ctrl = cbm_val;
- d->have_new_ctrl = true;
+ cfg->new_ctrl = cbm_val;
+ cfg->have_new_ctrl = true;
return 0;
}
@@ -185,9 +191,12 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
* separated by ";". The "id" is in decimal, and must match one of
* the "id"s for this resource.
*/
-static int parse_line(char *line, struct rdt_resource *r,
+static int parse_line(char *line, struct resctrl_schema *s,
struct rdtgroup *rdtgrp)
{
+ enum resctrl_conf_type t = s->conf_type;
+ struct resctrl_staged_config *cfg;
+ struct rdt_resource *r = s->res;
struct rdt_parse_data data;
char *dom = NULL, *id;
struct rdt_domain *d;
@@ -213,9 +222,10 @@ next:
if (d->id == dom_id) {
data.buf = dom;
data.rdtgrp = rdtgrp;
- if (r->parse_ctrlval(&data, r, d))
+ if (r->parse_ctrlval(&data, s, d))
return -EINVAL;
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+ cfg = &d->staged_config[t];
/*
* In pseudo-locking setup mode and just
* parsed a valid CBM that should be
@@ -224,9 +234,9 @@ next:
* the required initialization for single
* region and return.
*/
- rdtgrp->plr->r = r;
+ rdtgrp->plr->s = s;
rdtgrp->plr->d = d;
- rdtgrp->plr->cbm = d->new_ctrl;
+ rdtgrp->plr->cbm = cfg->new_ctrl;
d->plr = rdtgrp->plr;
return 0;
}
@@ -236,28 +246,72 @@ next:
return -EINVAL;
}
-int update_domains(struct rdt_resource *r, int closid)
+static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
{
+ switch (type) {
+ default:
+ case CDP_NONE:
+ return closid;
+ case CDP_CODE:
+ return closid * 2 + 1;
+ case CDP_DATA:
+ return closid * 2;
+ }
+}
+
+static bool apply_config(struct rdt_hw_domain *hw_dom,
+ struct resctrl_staged_config *cfg, u32 idx,
+ cpumask_var_t cpu_mask, bool mba_sc)
+{
+ struct rdt_domain *dom = &hw_dom->d_resctrl;
+ u32 *dc = !mba_sc ? hw_dom->ctrl_val : hw_dom->mbps_val;
+
+ if (cfg->new_ctrl != dc[idx]) {
+ cpumask_set_cpu(cpumask_any(&dom->cpu_mask), cpu_mask);
+ dc[idx] = cfg->new_ctrl;
+
+ return true;
+ }
+
+ return false;
+}
+
+int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
+{
+ struct resctrl_staged_config *cfg;
+ struct rdt_hw_domain *hw_dom;
struct msr_param msr_param;
+ enum resctrl_conf_type t;
cpumask_var_t cpu_mask;
struct rdt_domain *d;
bool mba_sc;
- u32 *dc;
int cpu;
+ u32 idx;
if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
return -ENOMEM;
- msr_param.low = closid;
- msr_param.high = msr_param.low + 1;
- msr_param.res = r;
-
mba_sc = is_mba_sc(r);
+ msr_param.res = NULL;
list_for_each_entry(d, &r->domains, list) {
- dc = !mba_sc ? d->ctrl_val : d->mbps_val;
- if (d->have_new_ctrl && d->new_ctrl != dc[closid]) {
- cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
- dc[closid] = d->new_ctrl;
+ hw_dom = resctrl_to_arch_dom(d);
+ for (t = 0; t < CDP_NUM_TYPES; t++) {
+ cfg = &hw_dom->d_resctrl.staged_config[t];
+ if (!cfg->have_new_ctrl)
+ continue;
+
+ idx = get_config_index(closid, t);
+ if (!apply_config(hw_dom, cfg, idx, cpu_mask, mba_sc))
+ continue;
+
+ if (!msr_param.res) {
+ msr_param.low = idx;
+ msr_param.high = msr_param.low + 1;
+ msr_param.res = r;
+ } else {
+ msr_param.low = min(msr_param.low, idx);
+ msr_param.high = max(msr_param.high, idx + 1);
+ }
}
}
@@ -284,11 +338,11 @@ done:
static int rdtgroup_parse_resource(char *resname, char *tok,
struct rdtgroup *rdtgrp)
{
- struct rdt_resource *r;
+ struct resctrl_schema *s;
- for_each_alloc_enabled_rdt_resource(r) {
- if (!strcmp(resname, r->name) && rdtgrp->closid < r->num_closid)
- return parse_line(tok, r, rdtgrp);
+ list_for_each_entry(s, &resctrl_schema_all, list) {
+ if (!strcmp(resname, s->name) && rdtgrp->closid < s->num_closid)
+ return parse_line(tok, s, rdtgrp);
}
rdt_last_cmd_printf("Unknown or unsupported resource name '%s'\n", resname);
return -EINVAL;
@@ -297,6 +351,7 @@ static int rdtgroup_parse_resource(char *resname, char *tok,
ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
+ struct resctrl_schema *s;
struct rdtgroup *rdtgrp;
struct rdt_domain *dom;
struct rdt_resource *r;
@@ -327,9 +382,9 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
goto out;
}
- for_each_alloc_enabled_rdt_resource(r) {
- list_for_each_entry(dom, &r->domains, list)
- dom->have_new_ctrl = false;
+ list_for_each_entry(s, &resctrl_schema_all, list) {
+ list_for_each_entry(dom, &s->res->domains, list)
+ memset(dom->staged_config, 0, sizeof(dom->staged_config));
}
while ((tok = strsep(&buf, "\n")) != NULL) {
@@ -349,8 +404,9 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
goto out;
}
- for_each_alloc_enabled_rdt_resource(r) {
- ret = update_domains(r, rdtgrp->closid);
+ list_for_each_entry(s, &resctrl_schema_all, list) {
+ r = s->res;
+ ret = resctrl_arch_update_domains(r, rdtgrp->closid);
if (ret)
goto out;
}
@@ -371,19 +427,31 @@ out:
return ret ?: nbytes;
}
-static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid)
+u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
+ u32 closid, enum resctrl_conf_type type)
+{
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+ u32 idx = get_config_index(closid, type);
+
+ if (!is_mba_sc(r))
+ return hw_dom->ctrl_val[idx];
+ return hw_dom->mbps_val[idx];
+}
+
+static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid)
{
+ struct rdt_resource *r = schema->res;
struct rdt_domain *dom;
bool sep = false;
u32 ctrl_val;
- seq_printf(s, "%*s:", max_name_width, r->name);
+ seq_printf(s, "%*s:", max_name_width, schema->name);
list_for_each_entry(dom, &r->domains, list) {
if (sep)
seq_puts(s, ";");
- ctrl_val = (!is_mba_sc(r) ? dom->ctrl_val[closid] :
- dom->mbps_val[closid]);
+ ctrl_val = resctrl_arch_get_config(r, dom, closid,
+ schema->conf_type);
seq_printf(s, r->format_str, dom->id, max_data_width,
ctrl_val);
sep = true;
@@ -394,16 +462,17 @@ static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid)
int rdtgroup_schemata_show(struct kernfs_open_file *of,
struct seq_file *s, void *v)
{
+ struct resctrl_schema *schema;
struct rdtgroup *rdtgrp;
- struct rdt_resource *r;
int ret = 0;
u32 closid;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (rdtgrp) {
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
- for_each_alloc_enabled_rdt_resource(r)
- seq_printf(s, "%s:uninitialized\n", r->name);
+ list_for_each_entry(schema, &resctrl_schema_all, list) {
+ seq_printf(s, "%s:uninitialized\n", schema->name);
+ }
} else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
if (!rdtgrp->plr->d) {
rdt_last_cmd_clear();
@@ -411,15 +480,15 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
ret = -ENODEV;
} else {
seq_printf(s, "%s:%d=%x\n",
- rdtgrp->plr->r->name,
+ rdtgrp->plr->s->res->name,
rdtgrp->plr->d->id,
rdtgrp->plr->cbm);
}
} else {
closid = rdtgrp->closid;
- for_each_alloc_enabled_rdt_resource(r) {
- if (closid < r->num_closid)
- show_doms(s, r, closid);
+ list_for_each_entry(schema, &resctrl_schema_all, list) {
+ if (closid < schema->num_closid)
+ show_doms(s, schema, closid);
}
}
} else {
@@ -449,6 +518,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
int rdtgroup_mondata_show(struct seq_file *m, void *arg)
{
struct kernfs_open_file *of = m->private;
+ struct rdt_hw_resource *hw_res;
u32 resid, evtid, domid;
struct rdtgroup *rdtgrp;
struct rdt_resource *r;
@@ -468,7 +538,8 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
domid = md.u.domid;
evtid = md.u.evtid;
- r = &rdt_resources_all[resid];
+ hw_res = &rdt_resources_all[resid];
+ r = &hw_res->r_resctrl;
d = rdt_find_domain(r, domid, NULL);
if (IS_ERR_OR_NULL(d)) {
ret = -ENOENT;
@@ -482,7 +553,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
else if (rr.val & RMID_VAL_UNAVAIL)
seq_puts(m, "Unavailable\n");
else
- seq_printf(m, "%llu\n", rr.val * r->mon_scale);
+ seq_printf(m, "%llu\n", rr.val * hw_res->mon_scale);
out:
rdtgroup_kn_unlock(of->kn);
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 6a5f60a37219..1d647188a43b 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -2,6 +2,7 @@
#ifndef _ASM_X86_RESCTRL_INTERNAL_H
#define _ASM_X86_RESCTRL_INTERNAL_H
+#include <linux/resctrl.h>
#include <linux/sched.h>
#include <linux/kernfs.h>
#include <linux/fs_context.h>
@@ -109,6 +110,7 @@ extern unsigned int resctrl_cqm_threshold;
extern bool rdt_alloc_capable;
extern bool rdt_mon_capable;
extern unsigned int rdt_mon_features;
+extern struct list_head resctrl_schema_all;
enum rdt_group_type {
RDTCTRL_GROUP = 0,
@@ -161,8 +163,8 @@ struct mongroup {
/**
* struct pseudo_lock_region - pseudo-lock region information
- * @r: RDT resource to which this pseudo-locked region
- * belongs
+ * @s: Resctrl schema for the resource to which this
+ * pseudo-locked region belongs
* @d: RDT domain to which this pseudo-locked region
* belongs
* @cbm: bitmask of the pseudo-locked region
@@ -182,7 +184,7 @@ struct mongroup {
* @pm_reqs: Power management QoS requests related to this region
*/
struct pseudo_lock_region {
- struct rdt_resource *r;
+ struct resctrl_schema *s;
struct rdt_domain *d;
u32 cbm;
wait_queue_head_t lock_thread_wq;
@@ -303,44 +305,25 @@ struct mbm_state {
};
/**
- * struct rdt_domain - group of cpus sharing an RDT resource
- * @list: all instances of this resource
- * @id: unique id for this instance
- * @cpu_mask: which cpus share this resource
- * @rmid_busy_llc:
- * bitmap of which limbo RMIDs are above threshold
- * @mbm_total: saved state for MBM total bandwidth
- * @mbm_local: saved state for MBM local bandwidth
- * @mbm_over: worker to periodically read MBM h/w counters
- * @cqm_limbo: worker to periodically read CQM h/w counters
- * @mbm_work_cpu:
- * worker cpu for MBM h/w counters
- * @cqm_work_cpu:
- * worker cpu for CQM h/w counters
+ * struct rdt_hw_domain - Arch private attributes of a set of CPUs that share
+ * a resource
+ * @d_resctrl: Properties exposed to the resctrl file system
* @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID)
* @mbps_val: When mba_sc is enabled, this holds the bandwidth in MBps
- * @new_ctrl: new ctrl value to be loaded
- * @have_new_ctrl: did user provide new_ctrl for this domain
- * @plr: pseudo-locked region (if any) associated with domain
+ *
+ * Members of this structure are accessed via helpers that provide abstraction.
*/
-struct rdt_domain {
- struct list_head list;
- int id;
- struct cpumask cpu_mask;
- unsigned long *rmid_busy_llc;
- struct mbm_state *mbm_total;
- struct mbm_state *mbm_local;
- struct delayed_work mbm_over;
- struct delayed_work cqm_limbo;
- int mbm_work_cpu;
- int cqm_work_cpu;
+struct rdt_hw_domain {
+ struct rdt_domain d_resctrl;
u32 *ctrl_val;
u32 *mbps_val;
- u32 new_ctrl;
- bool have_new_ctrl;
- struct pseudo_lock_region *plr;
};
+static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r)
+{
+ return container_of(r, struct rdt_hw_domain, d_resctrl);
+}
+
/**
* struct msr_param - set a range of MSRs from a domain
* @res: The resource to use
@@ -349,69 +332,8 @@ struct rdt_domain {
*/
struct msr_param {
struct rdt_resource *res;
- int low;
- int high;
-};
-
-/**
- * struct rdt_cache - Cache allocation related data
- * @cbm_len: Length of the cache bit mask
- * @min_cbm_bits: Minimum number of consecutive bits to be set
- * @cbm_idx_mult: Multiplier of CBM index
- * @cbm_idx_offset: Offset of CBM index. CBM index is computed by:
- * closid * cbm_idx_multi + cbm_idx_offset
- * in a cache bit mask
- * @shareable_bits: Bitmask of shareable resource with other
- * executing entities
- * @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid.
- * @arch_has_empty_bitmaps: True if the '0' bitmap is valid.
- * @arch_has_per_cpu_cfg: True if QOS_CFG register for this cache
- * level has CPU scope.
- */
-struct rdt_cache {
- unsigned int cbm_len;
- unsigned int min_cbm_bits;
- unsigned int cbm_idx_mult;
- unsigned int cbm_idx_offset;
- unsigned int shareable_bits;
- bool arch_has_sparse_bitmaps;
- bool arch_has_empty_bitmaps;
- bool arch_has_per_cpu_cfg;
-};
-
-/**
- * enum membw_throttle_mode - System's memory bandwidth throttling mode
- * @THREAD_THROTTLE_UNDEFINED: Not relevant to the system
- * @THREAD_THROTTLE_MAX: Memory bandwidth is throttled at the core
- * always using smallest bandwidth percentage
- * assigned to threads, aka "max throttling"
- * @THREAD_THROTTLE_PER_THREAD: Memory bandwidth is throttled at the thread
- */
-enum membw_throttle_mode {
- THREAD_THROTTLE_UNDEFINED = 0,
- THREAD_THROTTLE_MAX,
- THREAD_THROTTLE_PER_THREAD,
-};
-
-/**
- * struct rdt_membw - Memory bandwidth allocation related data
- * @min_bw: Minimum memory bandwidth percentage user can request
- * @bw_gran: Granularity at which the memory bandwidth is allocated
- * @delay_linear: True if memory B/W delay is in linear scale
- * @arch_needs_linear: True if we can't configure non-linear resources
- * @throttle_mode: Bandwidth throttling mode when threads request
- * different memory bandwidths
- * @mba_sc: True if MBA software controller(mba_sc) is enabled
- * @mb_map: Mapping of memory B/W percentage to memory B/W delay
- */
-struct rdt_membw {
- u32 min_bw;
- u32 bw_gran;
- u32 delay_linear;
- bool arch_needs_linear;
- enum membw_throttle_mode throttle_mode;
- bool mba_sc;
- u32 *mb_map;
+ u32 low;
+ u32 high;
};
static inline bool is_llc_occupancy_enabled(void)
@@ -446,111 +368,103 @@ struct rdt_parse_data {
};
/**
- * struct rdt_resource - attributes of an RDT resource
- * @rid: The index of the resource
- * @alloc_enabled: Is allocation enabled on this machine
- * @mon_enabled: Is monitoring enabled for this feature
- * @alloc_capable: Is allocation available on this machine
- * @mon_capable: Is monitor feature available on this machine
- * @name: Name to use in "schemata" file
- * @num_closid: Number of CLOSIDs available
- * @cache_level: Which cache level defines scope of this resource
- * @default_ctrl: Specifies default cache cbm or memory B/W percent.
+ * struct rdt_hw_resource - arch private attributes of a resctrl resource
+ * @r_resctrl: Attributes of the resource used directly by resctrl.
+ * @num_closid: Maximum number of closid this hardware can support,
+ * regardless of CDP. This is exposed via
+ * resctrl_arch_get_num_closid() to avoid confusion
+ * with struct resctrl_schema's property of the same name,
+ * which has been corrected for features like CDP.
* @msr_base: Base MSR address for CBMs
* @msr_update: Function pointer to update QOS MSRs
- * @data_width: Character width of data when displaying
- * @domains: All domains for this resource
- * @cache: Cache allocation related data
- * @membw: If the component has bandwidth controls, their properties.
- * @format_str: Per resource format string to show domain value
- * @parse_ctrlval: Per resource function pointer to parse control values
- * @evt_list: List of monitoring events
- * @num_rmid: Number of RMIDs available
* @mon_scale: cqm counter * mon_scale = occupancy in bytes
* @mbm_width: Monitor width, to detect and correct for overflow.
- * @fflags: flags to choose base and info files
+ * @cdp_enabled: CDP state of this resource
+ *
+ * Members of this structure are either private to the architecture
+ * e.g. mbm_width, or accessed via helpers that provide abstraction. e.g.
+ * msr_update and msr_base.
*/
-struct rdt_resource {
- int rid;
- bool alloc_enabled;
- bool mon_enabled;
- bool alloc_capable;
- bool mon_capable;
- char *name;
- int num_closid;
- int cache_level;
- u32 default_ctrl;
+struct rdt_hw_resource {
+ struct rdt_resource r_resctrl;
+ u32 num_closid;
unsigned int msr_base;
void (*msr_update) (struct rdt_domain *d, struct msr_param *m,
struct rdt_resource *r);
- int data_width;
- struct list_head domains;
- struct rdt_cache cache;
- struct rdt_membw membw;
- const char *format_str;
- int (*parse_ctrlval)(struct rdt_parse_data *data,
- struct rdt_resource *r,
- struct rdt_domain *d);
- struct list_head evt_list;
- int num_rmid;
unsigned int mon_scale;
unsigned int mbm_width;
- unsigned long fflags;
+ bool cdp_enabled;
};
-int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
+static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r)
+{
+ return container_of(r, struct rdt_hw_resource, r_resctrl);
+}
+
+int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
struct rdt_domain *d);
-int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
struct rdt_domain *d);
extern struct mutex rdtgroup_mutex;
-extern struct rdt_resource rdt_resources_all[];
+extern struct rdt_hw_resource rdt_resources_all[];
extern struct rdtgroup rdtgroup_default;
DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
extern struct dentry *debugfs_resctrl;
-enum {
+enum resctrl_res_level {
RDT_RESOURCE_L3,
- RDT_RESOURCE_L3DATA,
- RDT_RESOURCE_L3CODE,
RDT_RESOURCE_L2,
- RDT_RESOURCE_L2DATA,
- RDT_RESOURCE_L2CODE,
RDT_RESOURCE_MBA,
/* Must be the last */
RDT_NUM_RESOURCES,
};
+static inline struct rdt_resource *resctrl_inc(struct rdt_resource *res)
+{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(res);
+
+ hw_res++;
+ return &hw_res->r_resctrl;
+}
+
+static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
+{
+ return rdt_resources_all[l].cdp_enabled;
+}
+
+int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable);
+
+/*
+ * To return the common struct rdt_resource, which is contained in struct
+ * rdt_hw_resource, walk the resctrl member of struct rdt_hw_resource.
+ */
#define for_each_rdt_resource(r) \
- for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
- r++)
+ for (r = &rdt_resources_all[0].r_resctrl; \
+ r <= &rdt_resources_all[RDT_NUM_RESOURCES - 1].r_resctrl; \
+ r = resctrl_inc(r))
#define for_each_capable_rdt_resource(r) \
- for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
- r++) \
+ for_each_rdt_resource(r) \
if (r->alloc_capable || r->mon_capable)
#define for_each_alloc_capable_rdt_resource(r) \
- for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
- r++) \
+ for_each_rdt_resource(r) \
if (r->alloc_capable)
#define for_each_mon_capable_rdt_resource(r) \
- for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
- r++) \
+ for_each_rdt_resource(r) \
if (r->mon_capable)
#define for_each_alloc_enabled_rdt_resource(r) \
- for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
- r++) \
+ for_each_rdt_resource(r) \
if (r->alloc_enabled)
#define for_each_mon_enabled_rdt_resource(r) \
- for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
- r++) \
+ for_each_rdt_resource(r) \
if (r->mon_enabled)
/* CPUID.(EAX=10H, ECX=ResID=1).EAX */
@@ -594,7 +508,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off);
int rdtgroup_schemata_show(struct kernfs_open_file *of,
struct seq_file *s, void *v);
-bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d,
unsigned long cbm, int closid, bool exclusive);
unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d,
unsigned long cbm);
@@ -609,7 +523,6 @@ void rdt_pseudo_lock_release(void);
int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
-int update_domains(struct rdt_resource *r, int closid);
int closids_supported(void);
void closid_free(int closid);
int alloc_rmid(void);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index f07c10b87a87..c9f0f3d63f75 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -174,7 +174,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
struct rdt_resource *r;
u32 crmid = 1, nrmid;
- r = &rdt_resources_all[RDT_RESOURCE_L3];
+ r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
/*
* Skip RMID 0 and start from RMID 1 and check all the RMIDs that
@@ -232,7 +232,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
int cpu;
u64 val;
- r = &rdt_resources_all[RDT_RESOURCE_L3];
+ r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
entry->busy = 0;
cpu = get_cpu();
@@ -285,15 +285,15 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
return chunks >>= shift;
}
-static int __mon_event_count(u32 rmid, struct rmid_read *rr)
+static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r);
struct mbm_state *m;
u64 chunks, tval;
tval = __rmid_read(rmid, rr->evtid);
if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) {
- rr->val = tval;
- return -EINVAL;
+ return tval;
}
switch (rr->evtid) {
case QOS_L3_OCCUP_EVENT_ID:
@@ -307,10 +307,10 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
break;
default:
/*
- * Code would never reach here because
- * an invalid event id would fail the __rmid_read.
+ * Code would never reach here because an invalid
+ * event id would fail the __rmid_read.
*/
- return -EINVAL;
+ return RMID_VAL_ERROR;
}
if (rr->first) {
@@ -319,7 +319,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
return 0;
}
- chunks = mbm_overflow_count(m->prev_msr, tval, rr->r->mbm_width);
+ chunks = mbm_overflow_count(m->prev_msr, tval, hw_res->mbm_width);
m->chunks += chunks;
m->prev_msr = tval;
@@ -334,7 +334,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
*/
static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
{
- struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r);
struct mbm_state *m = &rr->d->mbm_local[rmid];
u64 tval, cur_bw, chunks;
@@ -342,8 +342,8 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
return;
- chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width);
- cur_bw = (get_corrected_mbm_count(rmid, chunks) * r->mon_scale) >> 20;
+ chunks = mbm_overflow_count(m->prev_bw_msr, tval, hw_res->mbm_width);
+ cur_bw = (get_corrected_mbm_count(rmid, chunks) * hw_res->mon_scale) >> 20;
if (m->delta_comp)
m->delta_bw = abs(cur_bw - m->prev_bw);
@@ -361,23 +361,29 @@ void mon_event_count(void *info)
struct rdtgroup *rdtgrp, *entry;
struct rmid_read *rr = info;
struct list_head *head;
+ u64 ret_val;
rdtgrp = rr->rgrp;
- if (__mon_event_count(rdtgrp->mon.rmid, rr))
- return;
+ ret_val = __mon_event_count(rdtgrp->mon.rmid, rr);
/*
- * For Ctrl groups read data from child monitor groups.
+ * For Ctrl groups read data from child monitor groups and
+ * add them together. Count events which are read successfully.
+ * Discard the rmid_read's reporting errors.
*/
head = &rdtgrp->mon.crdtgrp_list;
if (rdtgrp->type == RDTCTRL_GROUP) {
list_for_each_entry(entry, head, mon.crdtgrp_list) {
- if (__mon_event_count(entry->mon.rmid, rr))
- return;
+ if (__mon_event_count(entry->mon.rmid, rr) == 0)
+ ret_val = 0;
}
}
+
+ /* Report error if none of rmid_reads are successful */
+ if (ret_val)
+ rr->val = ret_val;
}
/*
@@ -416,6 +422,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
{
u32 closid, rmid, cur_msr, cur_msr_val, new_msr_val;
struct mbm_state *pmbm_data, *cmbm_data;
+ struct rdt_hw_resource *hw_r_mba;
+ struct rdt_hw_domain *hw_dom_mba;
u32 cur_bw, delta_bw, user_bw;
struct rdt_resource *r_mba;
struct rdt_domain *dom_mba;
@@ -425,7 +433,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
if (!is_mbm_local_enabled())
return;
- r_mba = &rdt_resources_all[RDT_RESOURCE_MBA];
+ hw_r_mba = &rdt_resources_all[RDT_RESOURCE_MBA];
+ r_mba = &hw_r_mba->r_resctrl;
closid = rgrp->closid;
rmid = rgrp->mon.rmid;
pmbm_data = &dom_mbm->mbm_local[rmid];
@@ -435,11 +444,16 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
pr_warn_once("Failure to get domain for MBA update\n");
return;
}
+ hw_dom_mba = resctrl_to_arch_dom(dom_mba);
cur_bw = pmbm_data->prev_bw;
- user_bw = dom_mba->mbps_val[closid];
+ user_bw = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE);
delta_bw = pmbm_data->delta_bw;
- cur_msr_val = dom_mba->ctrl_val[closid];
+ /*
+ * resctrl_arch_get_config() chooses the mbps/ctrl value to return
+ * based on is_mba_sc(). For now, reach into the hw_dom.
+ */
+ cur_msr_val = hw_dom_mba->ctrl_val[closid];
/*
* For Ctrl groups read data from child monitor groups.
@@ -474,9 +488,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
return;
}
- cur_msr = r_mba->msr_base + closid;
+ cur_msr = hw_r_mba->msr_base + closid;
wrmsrl(cur_msr, delay_bw_map(new_msr_val, r_mba));
- dom_mba->ctrl_val[closid] = new_msr_val;
+ hw_dom_mba->ctrl_val[closid] = new_msr_val;
/*
* Delta values are updated dynamically package wise for each
@@ -538,7 +552,7 @@ void cqm_handle_limbo(struct work_struct *work)
mutex_lock(&rdtgroup_mutex);
- r = &rdt_resources_all[RDT_RESOURCE_L3];
+ r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
d = container_of(work, struct rdt_domain, cqm_limbo.work);
__check_limbo(d, false);
@@ -574,7 +588,7 @@ void mbm_handle_overflow(struct work_struct *work)
if (!static_branch_likely(&rdt_mon_enable_key))
goto out_unlock;
- r = &rdt_resources_all[RDT_RESOURCE_L3];
+ r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
d = container_of(work, struct rdt_domain, mbm_over.work);
list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
@@ -671,15 +685,16 @@ static void l3_mon_evt_init(struct rdt_resource *r)
int rdt_get_mon_l3_config(struct rdt_resource *r)
{
unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
unsigned int cl_size = boot_cpu_data.x86_cache_size;
int ret;
- r->mon_scale = boot_cpu_data.x86_cache_occ_scale;
+ hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale;
r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
- r->mbm_width = MBM_CNTR_WIDTH_BASE;
+ hw_res->mbm_width = MBM_CNTR_WIDTH_BASE;
if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
- r->mbm_width += mbm_offset;
+ hw_res->mbm_width += mbm_offset;
else if (mbm_offset > MBM_CNTR_WIDTH_OFFSET_MAX)
pr_warn("Ignoring impossible MBM counter offset\n");
@@ -693,7 +708,7 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)
resctrl_cqm_threshold = cl_size * 1024 / r->num_rmid;
/* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */
- resctrl_cqm_threshold /= r->mon_scale;
+ resctrl_cqm_threshold /= hw_res->mon_scale;
ret = dom_data_init(r);
if (ret)
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 2207916cae65..db813f819ad6 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -250,7 +250,7 @@ static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
plr->line_size = 0;
kfree(plr->kmem);
plr->kmem = NULL;
- plr->r = NULL;
+ plr->s = NULL;
if (plr->d)
plr->d->plr = NULL;
plr->d = NULL;
@@ -294,10 +294,10 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
ci = get_cpu_cacheinfo(plr->cpu);
- plr->size = rdtgroup_cbm_to_size(plr->r, plr->d, plr->cbm);
+ plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
for (i = 0; i < ci->num_leaves; i++) {
- if (ci->info_list[i].level == plr->r->cache_level) {
+ if (ci->info_list[i].level == plr->s->res->cache_level) {
plr->line_size = ci->info_list[i].coherency_line_size;
return 0;
}
@@ -688,8 +688,8 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
* resource, the portion of cache used by it should be made
* unavailable to all future allocations from both resources.
*/
- if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled ||
- rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) {
+ if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3) ||
+ resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) {
rdt_last_cmd_puts("CDP enabled\n");
return -EINVAL;
}
@@ -800,7 +800,7 @@ bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm
unsigned long cbm_b;
if (d->plr) {
- cbm_len = d->plr->r->cache.cbm_len;
+ cbm_len = d->plr->s->res->cache.cbm_len;
cbm_b = d->plr->cbm;
if (bitmap_intersects(&cbm, &cbm_b, cbm_len))
return true;
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 01fd30e7829d..b57b3db9a6a7 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -39,6 +39,9 @@ static struct kernfs_root *rdt_root;
struct rdtgroup rdtgroup_default;
LIST_HEAD(rdt_all_groups);
+/* list of entries for the schemata file */
+LIST_HEAD(resctrl_schema_all);
+
/* Kernel fs node for "info" directory under root */
static struct kernfs_node *kn_info;
@@ -100,12 +103,12 @@ int closids_supported(void)
static void closid_init(void)
{
- struct rdt_resource *r;
- int rdt_min_closid = 32;
+ struct resctrl_schema *s;
+ u32 rdt_min_closid = 32;
/* Compute rdt_min_closid across all resources */
- for_each_alloc_enabled_rdt_resource(r)
- rdt_min_closid = min(rdt_min_closid, r->num_closid);
+ list_for_each_entry(s, &resctrl_schema_all, list)
+ rdt_min_closid = min(rdt_min_closid, s->num_closid);
closid_free_map = BIT_MASK(rdt_min_closid) - 1;
@@ -842,16 +845,17 @@ static int rdt_last_cmd_status_show(struct kernfs_open_file *of,
static int rdt_num_closids_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
- struct rdt_resource *r = of->kn->parent->priv;
+ struct resctrl_schema *s = of->kn->parent->priv;
- seq_printf(seq, "%d\n", r->num_closid);
+ seq_printf(seq, "%u\n", s->num_closid);
return 0;
}
static int rdt_default_ctrl_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
- struct rdt_resource *r = of->kn->parent->priv;
+ struct resctrl_schema *s = of->kn->parent->priv;
+ struct rdt_resource *r = s->res;
seq_printf(seq, "%x\n", r->default_ctrl);
return 0;
@@ -860,7 +864,8 @@ static int rdt_default_ctrl_show(struct kernfs_open_file *of,
static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
- struct rdt_resource *r = of->kn->parent->priv;
+ struct resctrl_schema *s = of->kn->parent->priv;
+ struct rdt_resource *r = s->res;
seq_printf(seq, "%u\n", r->cache.min_cbm_bits);
return 0;
@@ -869,7 +874,8 @@ static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
static int rdt_shareable_bits_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
- struct rdt_resource *r = of->kn->parent->priv;
+ struct resctrl_schema *s = of->kn->parent->priv;
+ struct rdt_resource *r = s->res;
seq_printf(seq, "%x\n", r->cache.shareable_bits);
return 0;
@@ -892,38 +898,40 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of,
static int rdt_bit_usage_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
- struct rdt_resource *r = of->kn->parent->priv;
+ struct resctrl_schema *s = of->kn->parent->priv;
/*
* Use unsigned long even though only 32 bits are used to ensure
* test_bit() is used safely.
*/
unsigned long sw_shareable = 0, hw_shareable = 0;
unsigned long exclusive = 0, pseudo_locked = 0;
+ struct rdt_resource *r = s->res;
struct rdt_domain *dom;
int i, hwb, swb, excl, psl;
enum rdtgrp_mode mode;
bool sep = false;
- u32 *ctrl;
+ u32 ctrl_val;
mutex_lock(&rdtgroup_mutex);
hw_shareable = r->cache.shareable_bits;
list_for_each_entry(dom, &r->domains, list) {
if (sep)
seq_putc(seq, ';');
- ctrl = dom->ctrl_val;
sw_shareable = 0;
exclusive = 0;
seq_printf(seq, "%d=", dom->id);
- for (i = 0; i < closids_supported(); i++, ctrl++) {
+ for (i = 0; i < closids_supported(); i++) {
if (!closid_allocated(i))
continue;
+ ctrl_val = resctrl_arch_get_config(r, dom, i,
+ s->conf_type);
mode = rdtgroup_mode_by_closid(i);
switch (mode) {
case RDT_MODE_SHAREABLE:
- sw_shareable |= *ctrl;
+ sw_shareable |= ctrl_val;
break;
case RDT_MODE_EXCLUSIVE:
- exclusive |= *ctrl;
+ exclusive |= ctrl_val;
break;
case RDT_MODE_PSEUDO_LOCKSETUP:
/*
@@ -970,7 +978,8 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
static int rdt_min_bw_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
- struct rdt_resource *r = of->kn->parent->priv;
+ struct resctrl_schema *s = of->kn->parent->priv;
+ struct rdt_resource *r = s->res;
seq_printf(seq, "%u\n", r->membw.min_bw);
return 0;
@@ -1001,7 +1010,8 @@ static int rdt_mon_features_show(struct kernfs_open_file *of,
static int rdt_bw_gran_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
- struct rdt_resource *r = of->kn->parent->priv;
+ struct resctrl_schema *s = of->kn->parent->priv;
+ struct rdt_resource *r = s->res;
seq_printf(seq, "%u\n", r->membw.bw_gran);
return 0;
@@ -1010,7 +1020,8 @@ static int rdt_bw_gran_show(struct kernfs_open_file *of,
static int rdt_delay_linear_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
- struct rdt_resource *r = of->kn->parent->priv;
+ struct resctrl_schema *s = of->kn->parent->priv;
+ struct rdt_resource *r = s->res;
seq_printf(seq, "%u\n", r->membw.delay_linear);
return 0;
@@ -1020,8 +1031,9 @@ static int max_threshold_occ_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
struct rdt_resource *r = of->kn->parent->priv;
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
- seq_printf(seq, "%u\n", resctrl_cqm_threshold * r->mon_scale);
+ seq_printf(seq, "%u\n", resctrl_cqm_threshold * hw_res->mon_scale);
return 0;
}
@@ -1029,7 +1041,8 @@ static int max_threshold_occ_show(struct kernfs_open_file *of,
static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
- struct rdt_resource *r = of->kn->parent->priv;
+ struct resctrl_schema *s = of->kn->parent->priv;
+ struct rdt_resource *r = s->res;
if (r->membw.throttle_mode == THREAD_THROTTLE_PER_THREAD)
seq_puts(seq, "per-thread\n");
@@ -1042,7 +1055,7 @@ static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
- struct rdt_resource *r = of->kn->parent->priv;
+ struct rdt_hw_resource *hw_res;
unsigned int bytes;
int ret;
@@ -1053,7 +1066,8 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
if (bytes > (boot_cpu_data.x86_cache_size * 1024))
return -EINVAL;
- resctrl_cqm_threshold = bytes / r->mon_scale;
+ hw_res = resctrl_to_arch_res(of->kn->parent->priv);
+ resctrl_cqm_threshold = bytes / hw_res->mon_scale;
return nbytes;
}
@@ -1078,76 +1092,17 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of,
return 0;
}
-/**
- * rdt_cdp_peer_get - Retrieve CDP peer if it exists
- * @r: RDT resource to which RDT domain @d belongs
- * @d: Cache instance for which a CDP peer is requested
- * @r_cdp: RDT resource that shares hardware with @r (RDT resource peer)
- * Used to return the result.
- * @d_cdp: RDT domain that shares hardware with @d (RDT domain peer)
- * Used to return the result.
- *
- * RDT resources are managed independently and by extension the RDT domains
- * (RDT resource instances) are managed independently also. The Code and
- * Data Prioritization (CDP) RDT resources, while managed independently,
- * could refer to the same underlying hardware. For example,
- * RDT_RESOURCE_L2CODE and RDT_RESOURCE_L2DATA both refer to the L2 cache.
- *
- * When provided with an RDT resource @r and an instance of that RDT
- * resource @d rdt_cdp_peer_get() will return if there is a peer RDT
- * resource and the exact instance that shares the same hardware.
- *
- * Return: 0 if a CDP peer was found, <0 on error or if no CDP peer exists.
- * If a CDP peer was found, @r_cdp will point to the peer RDT resource
- * and @d_cdp will point to the peer RDT domain.
- */
-static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d,
- struct rdt_resource **r_cdp,
- struct rdt_domain **d_cdp)
+static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type)
{
- struct rdt_resource *_r_cdp = NULL;
- struct rdt_domain *_d_cdp = NULL;
- int ret = 0;
-
- switch (r->rid) {
- case RDT_RESOURCE_L3DATA:
- _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3CODE];
- break;
- case RDT_RESOURCE_L3CODE:
- _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3DATA];
- break;
- case RDT_RESOURCE_L2DATA:
- _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2CODE];
- break;
- case RDT_RESOURCE_L2CODE:
- _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2DATA];
- break;
+ switch (my_type) {
+ case CDP_CODE:
+ return CDP_DATA;
+ case CDP_DATA:
+ return CDP_CODE;
default:
- ret = -ENOENT;
- goto out;
- }
-
- /*
- * When a new CPU comes online and CDP is enabled then the new
- * RDT domains (if any) associated with both CDP RDT resources
- * are added in the same CPU online routine while the
- * rdtgroup_mutex is held. It should thus not happen for one
- * RDT domain to exist and be associated with its RDT CDP
- * resource but there is no RDT domain associated with the
- * peer RDT CDP resource. Hence the WARN.
- */
- _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL);
- if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) {
- _r_cdp = NULL;
- _d_cdp = NULL;
- ret = -EINVAL;
+ case CDP_NONE:
+ return CDP_NONE;
}
-
-out:
- *r_cdp = _r_cdp;
- *d_cdp = _d_cdp;
-
- return ret;
}
/**
@@ -1171,11 +1126,11 @@ out:
* Return: false if CBM does not overlap, true if it does.
*/
static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
- unsigned long cbm, int closid, bool exclusive)
+ unsigned long cbm, int closid,
+ enum resctrl_conf_type type, bool exclusive)
{
enum rdtgrp_mode mode;
unsigned long ctrl_b;
- u32 *ctrl;
int i;
/* Check for any overlap with regions used by hardware directly */
@@ -1186,9 +1141,8 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d
}
/* Check for overlap with other resource groups */
- ctrl = d->ctrl_val;
- for (i = 0; i < closids_supported(); i++, ctrl++) {
- ctrl_b = *ctrl;
+ for (i = 0; i < closids_supported(); i++) {
+ ctrl_b = resctrl_arch_get_config(r, d, i, type);
mode = rdtgroup_mode_by_closid(i);
if (closid_allocated(i) && i != closid &&
mode != RDT_MODE_PSEUDO_LOCKSETUP) {
@@ -1208,7 +1162,7 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d
/**
* rdtgroup_cbm_overlaps - Does CBM overlap with other use of hardware
- * @r: Resource to which domain instance @d belongs.
+ * @s: Schema for the resource to which domain instance @d belongs.
* @d: The domain instance for which @closid is being tested.
* @cbm: Capacity bitmask being tested.
* @closid: Intended closid for @cbm.
@@ -1226,19 +1180,19 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d
*
* Return: true if CBM overlap detected, false if there is no overlap
*/
-bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d,
unsigned long cbm, int closid, bool exclusive)
{
- struct rdt_resource *r_cdp;
- struct rdt_domain *d_cdp;
+ enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
+ struct rdt_resource *r = s->res;
- if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, exclusive))
+ if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, s->conf_type,
+ exclusive))
return true;
- if (rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp) < 0)
+ if (!resctrl_arch_get_cdp_enabled(r->rid))
return false;
-
- return __rdtgroup_cbm_overlaps(r_cdp, d_cdp, cbm, closid, exclusive);
+ return __rdtgroup_cbm_overlaps(r, d, cbm, closid, peer_type, exclusive);
}
/**
@@ -1256,17 +1210,21 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
{
int closid = rdtgrp->closid;
+ struct resctrl_schema *s;
struct rdt_resource *r;
bool has_cache = false;
struct rdt_domain *d;
+ u32 ctrl;
- for_each_alloc_enabled_rdt_resource(r) {
+ list_for_each_entry(s, &resctrl_schema_all, list) {
+ r = s->res;
if (r->rid == RDT_RESOURCE_MBA)
continue;
has_cache = true;
list_for_each_entry(d, &r->domains, list) {
- if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid],
- rdtgrp->closid, false)) {
+ ctrl = resctrl_arch_get_config(r, d, closid,
+ s->conf_type);
+ if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) {
rdt_last_cmd_puts("Schemata overlaps\n");
return false;
}
@@ -1397,6 +1355,7 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
static int rdtgroup_size_show(struct kernfs_open_file *of,
struct seq_file *s, void *v)
{
+ struct resctrl_schema *schema;
struct rdtgroup *rdtgrp;
struct rdt_resource *r;
struct rdt_domain *d;
@@ -1418,8 +1377,8 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
ret = -ENODEV;
} else {
seq_printf(s, "%*s:", max_name_width,
- rdtgrp->plr->r->name);
- size = rdtgroup_cbm_to_size(rdtgrp->plr->r,
+ rdtgrp->plr->s->name);
+ size = rdtgroup_cbm_to_size(rdtgrp->plr->s->res,
rdtgrp->plr->d,
rdtgrp->plr->cbm);
seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
@@ -1427,18 +1386,19 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
goto out;
}
- for_each_alloc_enabled_rdt_resource(r) {
+ list_for_each_entry(schema, &resctrl_schema_all, list) {
+ r = schema->res;
sep = false;
- seq_printf(s, "%*s:", max_name_width, r->name);
+ seq_printf(s, "%*s:", max_name_width, schema->name);
list_for_each_entry(d, &r->domains, list) {
if (sep)
seq_putc(s, ';');
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
size = 0;
} else {
- ctrl = (!is_mba_sc(r) ?
- d->ctrl_val[rdtgrp->closid] :
- d->mbps_val[rdtgrp->closid]);
+ ctrl = resctrl_arch_get_config(r, d,
+ rdtgrp->closid,
+ schema->conf_type);
if (r->rid == RDT_RESOURCE_MBA)
size = ctrl;
else
@@ -1757,14 +1717,14 @@ int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
return ret;
}
-static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name,
+static int rdtgroup_mkdir_info_resdir(void *priv, char *name,
unsigned long fflags)
{
struct kernfs_node *kn_subdir;
int ret;
kn_subdir = kernfs_create_dir(kn_info, name,
- kn_info->mode, r);
+ kn_info->mode, priv);
if (IS_ERR(kn_subdir))
return PTR_ERR(kn_subdir);
@@ -1781,6 +1741,7 @@ static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name,
static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
{
+ struct resctrl_schema *s;
struct rdt_resource *r;
unsigned long fflags;
char name[32];
@@ -1795,9 +1756,11 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
if (ret)
goto out_destroy;
- for_each_alloc_enabled_rdt_resource(r) {
+ /* loop over enabled controls, these are all alloc_enabled */
+ list_for_each_entry(s, &resctrl_schema_all, list) {
+ r = s->res;
fflags = r->fflags | RF_CTRL_INFO;
- ret = rdtgroup_mkdir_info_resdir(r, r->name, fflags);
+ ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags);
if (ret)
goto out_destroy;
}
@@ -1867,7 +1830,7 @@ static void l2_qos_cfg_update(void *arg)
static inline bool is_mba_linear(void)
{
- return rdt_resources_all[RDT_RESOURCE_MBA].membw.delay_linear;
+ return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.delay_linear;
}
static int set_cache_qos_cfg(int level, bool enable)
@@ -1888,7 +1851,7 @@ static int set_cache_qos_cfg(int level, bool enable)
if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
return -ENOMEM;
- r_l = &rdt_resources_all[level];
+ r_l = &rdt_resources_all[level].r_resctrl;
list_for_each_entry(d, &r_l->domains, list) {
if (r_l->cache.arch_has_per_cpu_cfg)
/* Pick all the CPUs in the domain instance */
@@ -1914,14 +1877,16 @@ static int set_cache_qos_cfg(int level, bool enable)
/* Restore the qos cfg state when a domain comes online */
void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
{
- if (!r->alloc_capable)
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+
+ if (!r->cdp_capable)
return;
- if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA])
- l2_qos_cfg_update(&r->alloc_enabled);
+ if (r->rid == RDT_RESOURCE_L2)
+ l2_qos_cfg_update(&hw_res->cdp_enabled);
- if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA])
- l3_qos_cfg_update(&r->alloc_enabled);
+ if (r->rid == RDT_RESOURCE_L3)
+ l3_qos_cfg_update(&hw_res->cdp_enabled);
}
/*
@@ -1932,7 +1897,8 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
*/
static int set_mba_sc(bool mba_sc)
{
- struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA];
+ struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
+ struct rdt_hw_domain *hw_dom;
struct rdt_domain *d;
if (!is_mbm_enabled() || !is_mba_linear() ||
@@ -1940,73 +1906,60 @@ static int set_mba_sc(bool mba_sc)
return -EINVAL;
r->membw.mba_sc = mba_sc;
- list_for_each_entry(d, &r->domains, list)
- setup_default_ctrlval(r, d->ctrl_val, d->mbps_val);
+ list_for_each_entry(d, &r->domains, list) {
+ hw_dom = resctrl_to_arch_dom(d);
+ setup_default_ctrlval(r, hw_dom->ctrl_val, hw_dom->mbps_val);
+ }
return 0;
}
-static int cdp_enable(int level, int data_type, int code_type)
+static int cdp_enable(int level)
{
- struct rdt_resource *r_ldata = &rdt_resources_all[data_type];
- struct rdt_resource *r_lcode = &rdt_resources_all[code_type];
- struct rdt_resource *r_l = &rdt_resources_all[level];
+ struct rdt_resource *r_l = &rdt_resources_all[level].r_resctrl;
int ret;
- if (!r_l->alloc_capable || !r_ldata->alloc_capable ||
- !r_lcode->alloc_capable)
+ if (!r_l->alloc_capable)
return -EINVAL;
ret = set_cache_qos_cfg(level, true);
- if (!ret) {
- r_l->alloc_enabled = false;
- r_ldata->alloc_enabled = true;
- r_lcode->alloc_enabled = true;
- }
+ if (!ret)
+ rdt_resources_all[level].cdp_enabled = true;
+
return ret;
}
-static int cdpl3_enable(void)
+static void cdp_disable(int level)
{
- return cdp_enable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA,
- RDT_RESOURCE_L3CODE);
-}
+ struct rdt_hw_resource *r_hw = &rdt_resources_all[level];
-static int cdpl2_enable(void)
-{
- return cdp_enable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA,
- RDT_RESOURCE_L2CODE);
+ if (r_hw->cdp_enabled) {
+ set_cache_qos_cfg(level, false);
+ r_hw->cdp_enabled = false;
+ }
}
-static void cdp_disable(int level, int data_type, int code_type)
+int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable)
{
- struct rdt_resource *r = &rdt_resources_all[level];
+ struct rdt_hw_resource *hw_res = &rdt_resources_all[l];
- r->alloc_enabled = r->alloc_capable;
+ if (!hw_res->r_resctrl.cdp_capable)
+ return -EINVAL;
- if (rdt_resources_all[data_type].alloc_enabled) {
- rdt_resources_all[data_type].alloc_enabled = false;
- rdt_resources_all[code_type].alloc_enabled = false;
- set_cache_qos_cfg(level, false);
- }
-}
+ if (enable)
+ return cdp_enable(l);
-static void cdpl3_disable(void)
-{
- cdp_disable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA, RDT_RESOURCE_L3CODE);
-}
+ cdp_disable(l);
-static void cdpl2_disable(void)
-{
- cdp_disable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA, RDT_RESOURCE_L2CODE);
+ return 0;
}
static void cdp_disable_all(void)
{
- if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled)
- cdpl3_disable();
- if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled)
- cdpl2_disable();
+ if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3))
+ resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
+ if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2))
+ resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
}
/*
@@ -2084,10 +2037,10 @@ static int rdt_enable_ctx(struct rdt_fs_context *ctx)
int ret = 0;
if (ctx->enable_cdpl2)
- ret = cdpl2_enable();
+ ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, true);
if (!ret && ctx->enable_cdpl3)
- ret = cdpl3_enable();
+ ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, true);
if (!ret && ctx->enable_mba_mbps)
ret = set_mba_sc(true);
@@ -2095,6 +2048,92 @@ static int rdt_enable_ctx(struct rdt_fs_context *ctx)
return ret;
}
+static int schemata_list_add(struct rdt_resource *r, enum resctrl_conf_type type)
+{
+ struct resctrl_schema *s;
+ const char *suffix = "";
+ int ret, cl;
+
+ s = kzalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+
+ s->res = r;
+ s->num_closid = resctrl_arch_get_num_closid(r);
+ if (resctrl_arch_get_cdp_enabled(r->rid))
+ s->num_closid /= 2;
+
+ s->conf_type = type;
+ switch (type) {
+ case CDP_CODE:
+ suffix = "CODE";
+ break;
+ case CDP_DATA:
+ suffix = "DATA";
+ break;
+ case CDP_NONE:
+ suffix = "";
+ break;
+ }
+
+ ret = snprintf(s->name, sizeof(s->name), "%s%s", r->name, suffix);
+ if (ret >= sizeof(s->name)) {
+ kfree(s);
+ return -EINVAL;
+ }
+
+ cl = strlen(s->name);
+
+ /*
+ * If CDP is supported by this resource, but not enabled,
+ * include the suffix. This ensures the tabular format of the
+ * schemata file does not change between mounts of the filesystem.
+ */
+ if (r->cdp_capable && !resctrl_arch_get_cdp_enabled(r->rid))
+ cl += 4;
+
+ if (cl > max_name_width)
+ max_name_width = cl;
+
+ INIT_LIST_HEAD(&s->list);
+ list_add(&s->list, &resctrl_schema_all);
+
+ return 0;
+}
+
+static int schemata_list_create(void)
+{
+ struct rdt_resource *r;
+ int ret = 0;
+
+ for_each_alloc_enabled_rdt_resource(r) {
+ if (resctrl_arch_get_cdp_enabled(r->rid)) {
+ ret = schemata_list_add(r, CDP_CODE);
+ if (ret)
+ break;
+
+ ret = schemata_list_add(r, CDP_DATA);
+ } else {
+ ret = schemata_list_add(r, CDP_NONE);
+ }
+
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+static void schemata_list_destroy(void)
+{
+ struct resctrl_schema *s, *tmp;
+
+ list_for_each_entry_safe(s, tmp, &resctrl_schema_all, list) {
+ list_del(&s->list);
+ kfree(s);
+ }
+}
+
static int rdt_get_tree(struct fs_context *fc)
{
struct rdt_fs_context *ctx = rdt_fc2context(fc);
@@ -2116,11 +2155,17 @@ static int rdt_get_tree(struct fs_context *fc)
if (ret < 0)
goto out_cdp;
+ ret = schemata_list_create();
+ if (ret) {
+ schemata_list_destroy();
+ goto out_mba;
+ }
+
closid_init();
ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
if (ret < 0)
- goto out_mba;
+ goto out_schemata_free;
if (rdt_mon_capable) {
ret = mongroup_create_dir(rdtgroup_default.kn,
@@ -2153,7 +2198,7 @@ static int rdt_get_tree(struct fs_context *fc)
static_branch_enable_cpuslocked(&rdt_enable_key);
if (is_mbm_enabled()) {
- r = &rdt_resources_all[RDT_RESOURCE_L3];
+ r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
list_for_each_entry(dom, &r->domains, list)
mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL);
}
@@ -2170,6 +2215,8 @@ out_mongrp:
kernfs_remove(kn_mongrp);
out_info:
kernfs_remove(kn_info);
+out_schemata_free:
+ schemata_list_destroy();
out_mba:
if (ctx->enable_mba_mbps)
set_mba_sc(false);
@@ -2257,6 +2304,8 @@ static int rdt_init_fs_context(struct fs_context *fc)
static int reset_all_ctrls(struct rdt_resource *r)
{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+ struct rdt_hw_domain *hw_dom;
struct msr_param msr_param;
cpumask_var_t cpu_mask;
struct rdt_domain *d;
@@ -2267,7 +2316,7 @@ static int reset_all_ctrls(struct rdt_resource *r)
msr_param.res = r;
msr_param.low = 0;
- msr_param.high = r->num_closid;
+ msr_param.high = hw_res->num_closid;
/*
* Disable resource control for this resource by setting all
@@ -2275,10 +2324,11 @@ static int reset_all_ctrls(struct rdt_resource *r)
* from each domain to update the MSRs below.
*/
list_for_each_entry(d, &r->domains, list) {
+ hw_dom = resctrl_to_arch_dom(d);
cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
- for (i = 0; i < r->num_closid; i++)
- d->ctrl_val[i] = r->default_ctrl;
+ for (i = 0; i < hw_res->num_closid; i++)
+ hw_dom->ctrl_val[i] = r->default_ctrl;
}
cpu = get_cpu();
/* Update CBM on this cpu if it's in cpu_mask. */
@@ -2408,6 +2458,7 @@ static void rdt_kill_sb(struct super_block *sb)
rmdir_all_sub();
rdt_pseudo_lock_release();
rdtgroup_default.mode = RDT_MODE_SHAREABLE;
+ schemata_list_destroy();
static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
static_branch_disable_cpuslocked(&rdt_mon_enable_key);
static_branch_disable_cpuslocked(&rdt_enable_key);
@@ -2642,23 +2693,24 @@ static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r)
* Set the RDT domain up to start off with all usable allocations. That is,
* all shareable and unused bits. All-zero CBM is invalid.
*/
-static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r,
+static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s,
u32 closid)
{
- struct rdt_resource *r_cdp = NULL;
- struct rdt_domain *d_cdp = NULL;
+ enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
+ enum resctrl_conf_type t = s->conf_type;
+ struct resctrl_staged_config *cfg;
+ struct rdt_resource *r = s->res;
u32 used_b = 0, unused_b = 0;
unsigned long tmp_cbm;
enum rdtgrp_mode mode;
- u32 peer_ctl, *ctrl;
+ u32 peer_ctl, ctrl_val;
int i;
- rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp);
- d->have_new_ctrl = false;
- d->new_ctrl = r->cache.shareable_bits;
+ cfg = &d->staged_config[t];
+ cfg->have_new_ctrl = false;
+ cfg->new_ctrl = r->cache.shareable_bits;
used_b = r->cache.shareable_bits;
- ctrl = d->ctrl_val;
- for (i = 0; i < closids_supported(); i++, ctrl++) {
+ for (i = 0; i < closids_supported(); i++) {
if (closid_allocated(i) && i != closid) {
mode = rdtgroup_mode_by_closid(i);
if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
@@ -2673,35 +2725,38 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r,
* usage to ensure there is no overlap
* with an exclusive group.
*/
- if (d_cdp)
- peer_ctl = d_cdp->ctrl_val[i];
+ if (resctrl_arch_get_cdp_enabled(r->rid))
+ peer_ctl = resctrl_arch_get_config(r, d, i,
+ peer_type);
else
peer_ctl = 0;
- used_b |= *ctrl | peer_ctl;
+ ctrl_val = resctrl_arch_get_config(r, d, i,
+ s->conf_type);
+ used_b |= ctrl_val | peer_ctl;
if (mode == RDT_MODE_SHAREABLE)
- d->new_ctrl |= *ctrl | peer_ctl;
+ cfg->new_ctrl |= ctrl_val | peer_ctl;
}
}
if (d->plr && d->plr->cbm > 0)
used_b |= d->plr->cbm;
unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
- d->new_ctrl |= unused_b;
+ cfg->new_ctrl |= unused_b;
/*
* Force the initial CBM to be valid, user can
* modify the CBM based on system availability.
*/
- d->new_ctrl = cbm_ensure_valid(d->new_ctrl, r);
+ cfg->new_ctrl = cbm_ensure_valid(cfg->new_ctrl, r);
/*
* Assign the u32 CBM to an unsigned long to ensure that
* bitmap_weight() does not access out-of-bound memory.
*/
- tmp_cbm = d->new_ctrl;
+ tmp_cbm = cfg->new_ctrl;
if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) {
- rdt_last_cmd_printf("No space on %s:%d\n", r->name, d->id);
+ rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->id);
return -ENOSPC;
}
- d->have_new_ctrl = true;
+ cfg->have_new_ctrl = true;
return 0;
}
@@ -2716,13 +2771,13 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r,
* If there are no more shareable bits available on any domain then
* the entire allocation will fail.
*/
-static int rdtgroup_init_cat(struct rdt_resource *r, u32 closid)
+static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
{
struct rdt_domain *d;
int ret;
- list_for_each_entry(d, &r->domains, list) {
- ret = __init_one_rdt_domain(d, r, closid);
+ list_for_each_entry(d, &s->res->domains, list) {
+ ret = __init_one_rdt_domain(d, s, closid);
if (ret < 0)
return ret;
}
@@ -2733,30 +2788,34 @@ static int rdtgroup_init_cat(struct rdt_resource *r, u32 closid)
/* Initialize MBA resource with default values. */
static void rdtgroup_init_mba(struct rdt_resource *r)
{
+ struct resctrl_staged_config *cfg;
struct rdt_domain *d;
list_for_each_entry(d, &r->domains, list) {
- d->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl;
- d->have_new_ctrl = true;
+ cfg = &d->staged_config[CDP_NONE];
+ cfg->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl;
+ cfg->have_new_ctrl = true;
}
}
/* Initialize the RDT group's allocations. */
static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
{
+ struct resctrl_schema *s;
struct rdt_resource *r;
int ret;
- for_each_alloc_enabled_rdt_resource(r) {
+ list_for_each_entry(s, &resctrl_schema_all, list) {
+ r = s->res;
if (r->rid == RDT_RESOURCE_MBA) {
rdtgroup_init_mba(r);
} else {
- ret = rdtgroup_init_cat(r, rdtgrp->closid);
+ ret = rdtgroup_init_cat(s, rdtgrp->closid);
if (ret < 0)
return ret;
}
- ret = update_domains(r, rdtgrp->closid);
+ ret = resctrl_arch_update_domains(r, rdtgrp->closid);
if (ret < 0) {
rdt_last_cmd_puts("Failed to initialize allocations\n");
return ret;
@@ -3124,13 +3183,13 @@ out:
static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
{
- if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled)
+ if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3))
seq_puts(seq, ",cdp");
- if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled)
+ if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2))
seq_puts(seq, ",cdpl2");
- if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA]))
+ if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl))
seq_puts(seq, ",mba_MBps");
return 0;
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 08651a4e6aa0..42fc41dd0e1f 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -508,7 +508,7 @@ static struct irq_chip hpet_msi_controller __ro_after_init = {
.irq_set_affinity = msi_domain_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_write_msi_msg = hpet_msi_write_msg,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_AFFINITY_PRE_STARTUP,
};
static int hpet_msi_init(struct irq_domain *domain,
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 9320285a5e29..85f6e242b6b4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -610,6 +610,9 @@ void set_cpu_sibling_map(int cpu)
if (threads > __max_smt_threads)
__max_smt_threads = threads;
+ for_each_cpu(i, topology_sibling_cpumask(cpu))
+ cpu_data(i).smt_active = threads > 1;
+
/*
* This needs a separate iteration over the cpus because we rely on all
* topology_sibling_cpumask links to be set-up.
@@ -1552,8 +1555,13 @@ static void remove_siblinginfo(int cpu)
for_each_cpu(sibling, topology_die_cpumask(cpu))
cpumask_clear_cpu(cpu, topology_die_cpumask(sibling));
- for_each_cpu(sibling, topology_sibling_cpumask(cpu))
+
+ for_each_cpu(sibling, topology_sibling_cpumask(cpu)) {
cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
+ if (cpumask_weight(topology_sibling_cpumask(sibling)) == 1)
+ cpu_data(sibling).smt_active = false;
+ }
+
for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
cpumask_clear(cpu_llc_shared_mask(cpu));
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 739be5da3bca..fe03bd978761 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -208,30 +208,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
kvm_mmu_after_set_cpuid(vcpu);
}
-static int is_efer_nx(void)
-{
- return host_efer & EFER_NX;
-}
-
-static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
-{
- int i;
- struct kvm_cpuid_entry2 *e, *entry;
-
- entry = NULL;
- for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
- e = &vcpu->arch.cpuid_entries[i];
- if (e->function == 0x80000001) {
- entry = e;
- break;
- }
- }
- if (entry && cpuid_entry_has(entry, X86_FEATURE_NX) && !is_efer_nx()) {
- cpuid_entry_clear(entry, X86_FEATURE_NX);
- printk(KERN_INFO "kvm: guest NX capability removed\n");
- }
-}
-
int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
@@ -302,7 +278,6 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
vcpu->arch.cpuid_entries = e2;
vcpu->arch.cpuid_nent = cpuid->nent;
- cpuid_fix_nx_cap(vcpu);
kvm_update_cpuid_runtime(vcpu);
kvm_vcpu_after_set_cpuid(vcpu);
@@ -401,7 +376,6 @@ static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask)
void kvm_set_cpu_caps(void)
{
- unsigned int f_nx = is_efer_nx() ? F(NX) : 0;
#ifdef CONFIG_X86_64
unsigned int f_gbpages = F(GBPAGES);
unsigned int f_lm = F(LM);
@@ -515,7 +489,7 @@ void kvm_set_cpu_caps(void)
F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) |
F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
F(PAT) | F(PSE36) | 0 /* Reserved */ |
- f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) |
+ F(NX) | 0 /* Reserved */ | F(MMXEXT) | F(MMX) |
F(FXSR) | F(FXSR_OPT) | f_gbpages | F(RDTSCP) |
0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW)
);
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 0b38f944c6b6..41d2a53c5dea 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1933,7 +1933,7 @@ ret_success:
void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *entry;
- struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ struct kvm_vcpu_hv *hv_vcpu;
entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE, 0);
if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) {
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index c4f4fa23320e..47b765270239 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2535,6 +2535,7 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync)
{
struct kvm_mmu_page *sp;
+ bool locked = false;
/*
* Force write-protection if the page is being tracked. Note, the page
@@ -2557,9 +2558,34 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync)
if (sp->unsync)
continue;
+ /*
+ * TDP MMU page faults require an additional spinlock as they
+ * run with mmu_lock held for read, not write, and the unsync
+ * logic is not thread safe. Take the spinklock regardless of
+ * the MMU type to avoid extra conditionals/parameters, there's
+ * no meaningful penalty if mmu_lock is held for write.
+ */
+ if (!locked) {
+ locked = true;
+ spin_lock(&vcpu->kvm->arch.mmu_unsync_pages_lock);
+
+ /*
+ * Recheck after taking the spinlock, a different vCPU
+ * may have since marked the page unsync. A false
+ * positive on the unprotected check above is not
+ * possible as clearing sp->unsync _must_ hold mmu_lock
+ * for write, i.e. unsync cannot transition from 0->1
+ * while this CPU holds mmu_lock for read (or write).
+ */
+ if (READ_ONCE(sp->unsync))
+ continue;
+ }
+
WARN_ON(sp->role.level != PG_LEVEL_4K);
kvm_unsync_page(vcpu, sp);
}
+ if (locked)
+ spin_unlock(&vcpu->kvm->arch.mmu_unsync_pages_lock);
/*
* We need to ensure that the marking of unsync pages is visible
@@ -5537,6 +5563,8 @@ void kvm_mmu_init_vm(struct kvm *kvm)
{
struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+ spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
+
if (!kvm_mmu_init_tdp_mmu(kvm))
/*
* No smp_load/store wrappers needed here as we are in
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 0853370bd811..d80cb122b5f3 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -43,6 +43,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
if (!kvm->arch.tdp_mmu_enabled)
return;
+ WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages));
WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
/*
@@ -81,8 +82,6 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
bool shared)
{
- gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
-
kvm_lockdep_assert_mmu_lock_held(kvm, shared);
if (!refcount_dec_and_test(&root->tdp_mmu_root_count))
@@ -94,7 +93,7 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
list_del_rcu(&root->link);
spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
- zap_gfn_range(kvm, root, 0, max_gfn, false, false, shared);
+ zap_gfn_range(kvm, root, 0, -1ull, false, false, shared);
call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback);
}
@@ -724,13 +723,29 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
gfn_t start, gfn_t end, bool can_yield, bool flush,
bool shared)
{
+ gfn_t max_gfn_host = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
+ bool zap_all = (start == 0 && end >= max_gfn_host);
struct tdp_iter iter;
+ /*
+ * No need to try to step down in the iterator when zapping all SPTEs,
+ * zapping the top-level non-leaf SPTEs will recurse on their children.
+ */
+ int min_level = zap_all ? root->role.level : PG_LEVEL_4K;
+
+ /*
+ * Bound the walk at host.MAXPHYADDR, guest accesses beyond that will
+ * hit a #PF(RSVD) and never get to an EPT Violation/Misconfig / #NPF,
+ * and so KVM will never install a SPTE for such addresses.
+ */
+ end = min(end, max_gfn_host);
+
kvm_lockdep_assert_mmu_lock_held(kvm, shared);
rcu_read_lock();
- tdp_root_for_each_pte(iter, root, start, end) {
+ for_each_tdp_pte_min_level(iter, root->spt, root->role.level,
+ min_level, start, end) {
retry:
if (can_yield &&
tdp_mmu_iter_cond_resched(kvm, &iter, flush, shared)) {
@@ -744,9 +759,10 @@ retry:
/*
* If this is a non-last-level SPTE that covers a larger range
* than should be zapped, continue, and zap the mappings at a
- * lower level.
+ * lower level, except when zapping all SPTEs.
*/
- if ((iter.gfn < start ||
+ if (!zap_all &&
+ (iter.gfn < start ||
iter.gfn + KVM_PAGES_PER_HPAGE(iter.level) > end) &&
!is_last_spte(iter.old_spte, iter.level))
continue;
@@ -794,12 +810,11 @@ bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start,
void kvm_tdp_mmu_zap_all(struct kvm *kvm)
{
- gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
bool flush = false;
int i;
for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
- flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, 0, max_gfn,
+ flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, 0, -1ull,
flush, false);
if (flush)
@@ -838,7 +853,6 @@ static struct kvm_mmu_page *next_invalidated_root(struct kvm *kvm,
*/
void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
{
- gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
struct kvm_mmu_page *next_root;
struct kvm_mmu_page *root;
bool flush = false;
@@ -854,8 +868,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
rcu_read_unlock();
- flush = zap_gfn_range(kvm, root, 0, max_gfn, true, flush,
- true);
+ flush = zap_gfn_range(kvm, root, 0, -1ull, true, flush, true);
/*
* Put the reference acquired in
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 61738ff8ef33..e5515477c30a 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -158,6 +158,9 @@ void recalc_intercepts(struct vcpu_svm *svm)
/* If SMI is not intercepted, ignore guest SMI intercept as well */
if (!intercept_smi)
vmcb_clr_intercept(c, INTERCEPT_SMI);
+
+ vmcb_set_intercept(c, INTERCEPT_VMLOAD);
+ vmcb_set_intercept(c, INTERCEPT_VMSAVE);
}
static void copy_vmcb_control_area(struct vmcb_control_area *dst,
@@ -503,7 +506,11 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12
static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
{
- const u32 mask = V_INTR_MASKING_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK;
+ const u32 int_ctl_vmcb01_bits =
+ V_INTR_MASKING_MASK | V_GIF_MASK | V_GIF_ENABLE_MASK;
+
+ const u32 int_ctl_vmcb12_bits = V_TPR_MASK | V_IRQ_INJECTION_BITS_MASK;
+
struct kvm_vcpu *vcpu = &svm->vcpu;
/*
@@ -535,8 +542,8 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
vcpu->arch.l1_tsc_offset + svm->nested.ctl.tsc_offset;
svm->vmcb->control.int_ctl =
- (svm->nested.ctl.int_ctl & ~mask) |
- (svm->vmcb01.ptr->control.int_ctl & mask);
+ (svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) |
+ (svm->vmcb01.ptr->control.int_ctl & int_ctl_vmcb01_bits);
svm->vmcb->control.virt_ext = svm->nested.ctl.virt_ext;
svm->vmcb->control.int_vector = svm->nested.ctl.int_vector;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index e8ccab50ebf6..69639f9624f5 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1589,17 +1589,18 @@ static void svm_set_vintr(struct vcpu_svm *svm)
static void svm_clear_vintr(struct vcpu_svm *svm)
{
- const u32 mask = V_TPR_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK | V_INTR_MASKING_MASK;
svm_clr_intercept(svm, INTERCEPT_VINTR);
/* Drop int_ctl fields related to VINTR injection. */
- svm->vmcb->control.int_ctl &= mask;
+ svm->vmcb->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK;
if (is_guest_mode(&svm->vcpu)) {
- svm->vmcb01.ptr->control.int_ctl &= mask;
+ svm->vmcb01.ptr->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK;
WARN_ON((svm->vmcb->control.int_ctl & V_TPR_MASK) !=
(svm->nested.ctl.int_ctl & V_TPR_MASK));
- svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl & ~mask;
+
+ svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl &
+ V_IRQ_INJECTION_BITS_MASK;
}
vmcb_mark_dirty(svm->vmcb, VMCB_INTR);
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 1a52134b0c42..b3f77d18eb5a 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -330,6 +330,31 @@ void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu)
vcpu_put(vcpu);
}
+#define EPTP_PA_MASK GENMASK_ULL(51, 12)
+
+static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp)
+{
+ return VALID_PAGE(root_hpa) &&
+ ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK));
+}
+
+static void nested_ept_invalidate_addr(struct kvm_vcpu *vcpu, gpa_t eptp,
+ gpa_t addr)
+{
+ uint i;
+ struct kvm_mmu_root_info *cached_root;
+
+ WARN_ON_ONCE(!mmu_is_nested(vcpu));
+
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
+ cached_root = &vcpu->arch.mmu->prev_roots[i];
+
+ if (nested_ept_root_matches(cached_root->hpa, cached_root->pgd,
+ eptp))
+ vcpu->arch.mmu->invlpg(vcpu, addr, cached_root->hpa);
+ }
+}
+
static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
struct x86_exception *fault)
{
@@ -342,10 +367,22 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
vm_exit_reason = EXIT_REASON_PML_FULL;
vmx->nested.pml_full = false;
exit_qualification &= INTR_INFO_UNBLOCK_NMI;
- } else if (fault->error_code & PFERR_RSVD_MASK)
- vm_exit_reason = EXIT_REASON_EPT_MISCONFIG;
- else
- vm_exit_reason = EXIT_REASON_EPT_VIOLATION;
+ } else {
+ if (fault->error_code & PFERR_RSVD_MASK)
+ vm_exit_reason = EXIT_REASON_EPT_MISCONFIG;
+ else
+ vm_exit_reason = EXIT_REASON_EPT_VIOLATION;
+
+ /*
+ * Although the caller (kvm_inject_emulated_page_fault) would
+ * have already synced the faulting address in the shadow EPT
+ * tables for the current EPTP12, we also need to sync it for
+ * any other cached EPTP02s based on the same EP4TA, since the
+ * TLB associates mappings to the EP4TA rather than the full EPTP.
+ */
+ nested_ept_invalidate_addr(vcpu, vmcs12->ept_pointer,
+ fault->address);
+ }
nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification);
vmcs12->guest_physical_address = fault->address;
@@ -5325,14 +5362,6 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
return nested_vmx_succeed(vcpu);
}
-#define EPTP_PA_MASK GENMASK_ULL(51, 12)
-
-static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp)
-{
- return VALID_PAGE(root_hpa) &&
- ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK));
-}
-
/* Emulate the INVEPT instruction */
static int handle_invept(struct kvm_vcpu *vcpu)
{
@@ -5826,7 +5855,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
if (is_nmi(intr_info))
return true;
else if (is_page_fault(intr_info))
- return vcpu->arch.apf.host_apf_flags || !enable_ept;
+ return vcpu->arch.apf.host_apf_flags ||
+ vmx_need_pf_intercept(vcpu);
else if (is_debug(intr_info) &&
vcpu->guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index db88ed4f2121..17a1cb4b059d 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -522,7 +522,7 @@ static inline struct vmcs *alloc_vmcs(bool shadow)
static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx)
{
- return vmx->secondary_exec_control &
+ return secondary_exec_controls_get(vmx) &
SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
}
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index cd768dafca9e..933a2ebad471 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -376,12 +376,12 @@ static void enter_uniprocessor(void)
goto out;
}
- get_online_cpus();
+ cpus_read_lock();
cpumask_copy(downed_cpus, cpu_online_mask);
cpumask_clear_cpu(cpumask_first(cpu_online_mask), downed_cpus);
if (num_online_cpus() > 1)
pr_notice("Disabling non-boot CPUs...\n");
- put_online_cpus();
+ cpus_read_unlock();
for_each_cpu(cpu, downed_cpus) {
err = remove_cpu(cpu);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index cfe6b1e85fa6..59ba2968af1b 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -8,11 +8,13 @@
#include <linux/export.h>
#include <linux/cpu.h>
#include <linux/debugfs.h>
+#include <linux/sched/smt.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/nospec-branch.h>
#include <asm/cache.h>
+#include <asm/cacheflush.h>
#include <asm/apic.h>
#include <asm/perf_event.h>
@@ -43,10 +45,15 @@
*/
/*
- * Use bit 0 to mangle the TIF_SPEC_IB state into the mm pointer which is
- * stored in cpu_tlb_state.last_user_mm_ibpb.
+ * Bits to mangle the TIF_SPEC_* state into the mm pointer which is
+ * stored in cpu_tlb_state.last_user_mm_spec.
*/
#define LAST_USER_MM_IBPB 0x1UL
+#define LAST_USER_MM_L1D_FLUSH 0x2UL
+#define LAST_USER_MM_SPEC_MASK (LAST_USER_MM_IBPB | LAST_USER_MM_L1D_FLUSH)
+
+/* Bits to set when tlbstate and flush is (re)initialized */
+#define LAST_USER_MM_INIT LAST_USER_MM_IBPB
/*
* The x86 feature is called PCID (Process Context IDentifier). It is similar
@@ -317,20 +324,70 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
local_irq_restore(flags);
}
-static unsigned long mm_mangle_tif_spec_ib(struct task_struct *next)
+/*
+ * Invoked from return to user/guest by a task that opted-in to L1D
+ * flushing but ended up running on an SMT enabled core due to wrong
+ * affinity settings or CPU hotplug. This is part of the paranoid L1D flush
+ * contract which this task requested.
+ */
+static void l1d_flush_force_sigbus(struct callback_head *ch)
+{
+ force_sig(SIGBUS);
+}
+
+static void l1d_flush_evaluate(unsigned long prev_mm, unsigned long next_mm,
+ struct task_struct *next)
+{
+ /* Flush L1D if the outgoing task requests it */
+ if (prev_mm & LAST_USER_MM_L1D_FLUSH)
+ wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+
+ /* Check whether the incoming task opted in for L1D flush */
+ if (likely(!(next_mm & LAST_USER_MM_L1D_FLUSH)))
+ return;
+
+ /*
+ * Validate that it is not running on an SMT sibling as this would
+ * make the excercise pointless because the siblings share L1D. If
+ * it runs on a SMT sibling, notify it with SIGBUS on return to
+ * user/guest
+ */
+ if (this_cpu_read(cpu_info.smt_active)) {
+ clear_ti_thread_flag(&next->thread_info, TIF_SPEC_L1D_FLUSH);
+ next->l1d_flush_kill.func = l1d_flush_force_sigbus;
+ task_work_add(next, &next->l1d_flush_kill, TWA_RESUME);
+ }
+}
+
+static unsigned long mm_mangle_tif_spec_bits(struct task_struct *next)
{
unsigned long next_tif = task_thread_info(next)->flags;
- unsigned long ibpb = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_IBPB;
+ unsigned long spec_bits = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_SPEC_MASK;
- return (unsigned long)next->mm | ibpb;
+ /*
+ * Ensure that the bit shift above works as expected and the two flags
+ * end up in bit 0 and 1.
+ */
+ BUILD_BUG_ON(TIF_SPEC_L1D_FLUSH != TIF_SPEC_IB + 1);
+
+ return (unsigned long)next->mm | spec_bits;
}
-static void cond_ibpb(struct task_struct *next)
+static void cond_mitigation(struct task_struct *next)
{
+ unsigned long prev_mm, next_mm;
+
if (!next || !next->mm)
return;
+ next_mm = mm_mangle_tif_spec_bits(next);
+ prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_spec);
+
/*
+ * Avoid user/user BTB poisoning by flushing the branch predictor
+ * when switching between processes. This stops one process from
+ * doing Spectre-v2 attacks on another.
+ *
* Both, the conditional and the always IBPB mode use the mm
* pointer to avoid the IBPB when switching between tasks of the
* same process. Using the mm pointer instead of mm->context.ctx_id
@@ -340,8 +397,6 @@ static void cond_ibpb(struct task_struct *next)
* exposed data is not really interesting.
*/
if (static_branch_likely(&switch_mm_cond_ibpb)) {
- unsigned long prev_mm, next_mm;
-
/*
* This is a bit more complex than the always mode because
* it has to handle two cases:
@@ -371,20 +426,14 @@ static void cond_ibpb(struct task_struct *next)
* Optimize this with reasonably small overhead for the
* above cases. Mangle the TIF_SPEC_IB bit into the mm
* pointer of the incoming task which is stored in
- * cpu_tlbstate.last_user_mm_ibpb for comparison.
- */
- next_mm = mm_mangle_tif_spec_ib(next);
- prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_ibpb);
-
- /*
+ * cpu_tlbstate.last_user_mm_spec for comparison.
+ *
* Issue IBPB only if the mm's are different and one or
* both have the IBPB bit set.
*/
if (next_mm != prev_mm &&
(next_mm | prev_mm) & LAST_USER_MM_IBPB)
indirect_branch_prediction_barrier();
-
- this_cpu_write(cpu_tlbstate.last_user_mm_ibpb, next_mm);
}
if (static_branch_unlikely(&switch_mm_always_ibpb)) {
@@ -393,11 +442,22 @@ static void cond_ibpb(struct task_struct *next)
* different context than the user space task which ran
* last on this CPU.
*/
- if (this_cpu_read(cpu_tlbstate.last_user_mm) != next->mm) {
+ if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) !=
+ (unsigned long)next->mm)
indirect_branch_prediction_barrier();
- this_cpu_write(cpu_tlbstate.last_user_mm, next->mm);
- }
}
+
+ if (static_branch_unlikely(&switch_mm_cond_l1d_flush)) {
+ /*
+ * Flush L1D when the outgoing task requested it and/or
+ * check whether the incoming task requested L1D flushing
+ * and ended up on an SMT sibling.
+ */
+ if (unlikely((prev_mm | next_mm) & LAST_USER_MM_L1D_FLUSH))
+ l1d_flush_evaluate(prev_mm, next_mm, next);
+ }
+
+ this_cpu_write(cpu_tlbstate.last_user_mm_spec, next_mm);
}
#ifdef CONFIG_PERF_EVENTS
@@ -531,11 +591,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
need_flush = true;
} else {
/*
- * Avoid user/user BTB poisoning by flushing the branch
- * predictor when switching between processes. This stops
- * one process from doing Spectre-v2 attacks on another.
+ * Apply process to process speculation vulnerability
+ * mitigations if applicable.
*/
- cond_ibpb(tsk);
+ cond_mitigation(tsk);
/*
* Stop remote flushes for the previous mm.
@@ -643,7 +702,7 @@ void initialize_tlbstate_and_flush(void)
write_cr3(build_cr3(mm->pgd, 0));
/* Reinitialize tlbstate. */
- this_cpu_write(cpu_tlbstate.last_user_mm_ibpb, LAST_USER_MM_IBPB);
+ this_cpu_write(cpu_tlbstate.last_user_mm_spec, LAST_USER_MM_INIT);
this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0);
this_cpu_write(cpu_tlbstate.next_asid, 1);
this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id);
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 3a070e7cdb8b..6665f8802098 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -58,19 +58,20 @@ static void msr_restore_context(struct saved_context *ctxt)
}
/**
- * __save_processor_state - save CPU registers before creating a
- * hibernation image and before restoring the memory state from it
- * @ctxt - structure to store the registers contents in
+ * __save_processor_state() - Save CPU registers before creating a
+ * hibernation image and before restoring
+ * the memory state from it
+ * @ctxt: Structure to store the registers contents in.
*
- * NOTE: If there is a CPU register the modification of which by the
- * boot kernel (ie. the kernel used for loading the hibernation image)
- * might affect the operations of the restored target kernel (ie. the one
- * saved in the hibernation image), then its contents must be saved by this
- * function. In other words, if kernel A is hibernated and different
- * kernel B is used for loading the hibernation image into memory, the
- * kernel A's __save_processor_state() function must save all registers
- * needed by kernel A, so that it can operate correctly after the resume
- * regardless of what kernel B does in the meantime.
+ * NOTE: If there is a CPU register the modification of which by the
+ * boot kernel (ie. the kernel used for loading the hibernation image)
+ * might affect the operations of the restored target kernel (ie. the one
+ * saved in the hibernation image), then its contents must be saved by this
+ * function. In other words, if kernel A is hibernated and different
+ * kernel B is used for loading the hibernation image into memory, the
+ * kernel A's __save_processor_state() function must save all registers
+ * needed by kernel A, so that it can operate correctly after the resume
+ * regardless of what kernel B does in the meantime.
*/
static void __save_processor_state(struct saved_context *ctxt)
{
@@ -181,9 +182,9 @@ static void fix_processor_context(void)
}
/**
- * __restore_processor_state - restore the contents of CPU registers saved
- * by __save_processor_state()
- * @ctxt - structure to load the registers contents from
+ * __restore_processor_state() - Restore the contents of CPU registers saved
+ * by __save_processor_state()
+ * @ctxt: Structure to load the registers contents from.
*
* The asm code that gets us here will have restored a usable GDT, although
* it will be pointing to the wrong alias.
diff --git a/arch/x86/tools/chkobjdump.awk b/arch/x86/tools/chkobjdump.awk
index fd1ab80be0de..a4cf678cf5c8 100644
--- a/arch/x86/tools/chkobjdump.awk
+++ b/arch/x86/tools/chkobjdump.awk
@@ -10,6 +10,7 @@ BEGIN {
/^GNU objdump/ {
verstr = ""
+ gsub(/\(.*\)/, "");
for (i = 3; i <= NF; i++)
if (match($(i), "^[0-9]")) {
verstr = $(i);
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 9ba700dc47de..27c82207d387 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -26,6 +26,9 @@ static struct relocs relocs32;
#if ELF_BITS == 64
static struct relocs relocs32neg;
static struct relocs relocs64;
+#define FMT PRIu64
+#else
+#define FMT PRIu32
#endif
struct section {
@@ -389,7 +392,7 @@ static void read_ehdr(FILE *fp)
Elf_Shdr shdr;
if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0)
- die("Seek to %d failed: %s\n", ehdr.e_shoff, strerror(errno));
+ die("Seek to %" FMT " failed: %s\n", ehdr.e_shoff, strerror(errno));
if (fread(&shdr, sizeof(shdr), 1, fp) != 1)
die("Cannot read initial ELF section header: %s\n", strerror(errno));
@@ -412,17 +415,17 @@ static void read_shdrs(FILE *fp)
secs = calloc(shnum, sizeof(struct section));
if (!secs) {
- die("Unable to allocate %d section headers\n",
+ die("Unable to allocate %ld section headers\n",
shnum);
}
if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0) {
- die("Seek to %d failed: %s\n",
- ehdr.e_shoff, strerror(errno));
+ die("Seek to %" FMT " failed: %s\n",
+ ehdr.e_shoff, strerror(errno));
}
for (i = 0; i < shnum; i++) {
struct section *sec = &secs[i];
if (fread(&shdr, sizeof(shdr), 1, fp) != 1)
- die("Cannot read ELF section headers %d/%d: %s\n",
+ die("Cannot read ELF section headers %d/%ld: %s\n",
i, shnum, strerror(errno));
sec->shdr.sh_name = elf_word_to_cpu(shdr.sh_name);
sec->shdr.sh_type = elf_word_to_cpu(shdr.sh_type);
@@ -450,12 +453,12 @@ static void read_strtabs(FILE *fp)
}
sec->strtab = malloc(sec->shdr.sh_size);
if (!sec->strtab) {
- die("malloc of %d bytes for strtab failed\n",
- sec->shdr.sh_size);
+ die("malloc of %" FMT " bytes for strtab failed\n",
+ sec->shdr.sh_size);
}
if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) {
- die("Seek to %d failed: %s\n",
- sec->shdr.sh_offset, strerror(errno));
+ die("Seek to %" FMT " failed: %s\n",
+ sec->shdr.sh_offset, strerror(errno));
}
if (fread(sec->strtab, 1, sec->shdr.sh_size, fp)
!= sec->shdr.sh_size) {
@@ -475,12 +478,12 @@ static void read_symtabs(FILE *fp)
}
sec->symtab = malloc(sec->shdr.sh_size);
if (!sec->symtab) {
- die("malloc of %d bytes for symtab failed\n",
- sec->shdr.sh_size);
+ die("malloc of %" FMT " bytes for symtab failed\n",
+ sec->shdr.sh_size);
}
if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) {
- die("Seek to %d failed: %s\n",
- sec->shdr.sh_offset, strerror(errno));
+ die("Seek to %" FMT " failed: %s\n",
+ sec->shdr.sh_offset, strerror(errno));
}
if (fread(sec->symtab, 1, sec->shdr.sh_size, fp)
!= sec->shdr.sh_size) {
@@ -508,12 +511,12 @@ static void read_relocs(FILE *fp)
}
sec->reltab = malloc(sec->shdr.sh_size);
if (!sec->reltab) {
- die("malloc of %d bytes for relocs failed\n",
- sec->shdr.sh_size);
+ die("malloc of %" FMT " bytes for relocs failed\n",
+ sec->shdr.sh_size);
}
if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) {
- die("Seek to %d failed: %s\n",
- sec->shdr.sh_offset, strerror(errno));
+ die("Seek to %" FMT " failed: %s\n",
+ sec->shdr.sh_offset, strerror(errno));
}
if (fread(sec->reltab, 1, sec->shdr.sh_size, fp)
!= sec->shdr.sh_size) {
diff --git a/arch/x86/tools/relocs.h b/arch/x86/tools/relocs.h
index 43c83c0fd22c..4c49c82446eb 100644
--- a/arch/x86/tools/relocs.h
+++ b/arch/x86/tools/relocs.h
@@ -17,6 +17,7 @@
#include <regex.h>
#include <tools/le_byteshift.h>
+__attribute__((__format__(printf, 1, 2)))
void die(char *fmt, ...) __attribute__((noreturn));
#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index a48bf2d10ac2..764b54bef701 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -33,8 +33,6 @@ DECLARE_PER_CPU(unsigned long, nmi_count);
asmlinkage void do_IRQ(int hwirq, struct pt_regs *regs)
{
- int irq = irq_find_mapping(NULL, hwirq);
-
#ifdef CONFIG_DEBUG_STACKOVERFLOW
/* Debugging check for stack overflow: is there less than 1KB free? */
{
@@ -48,7 +46,7 @@ asmlinkage void do_IRQ(int hwirq, struct pt_regs *regs)
sp - sizeof(struct thread_info));
}
#endif
- generic_handle_irq(irq);
+ generic_handle_domain_irq(NULL, hwirq);
}
int arch_show_interrupts(struct seq_file *p, int prec)