aboutsummaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig43
-rw-r--r--arch/x86/Kconfig.cpu13
-rw-r--r--arch/x86/Makefile16
-rw-r--r--arch/x86/boot/compressed/Makefile4
-rw-r--r--arch/x86/boot/compressed/eboot.c3
-rw-r--r--arch/x86/boot/compressed/head_64.S168
-rw-r--r--arch/x86/boot/compressed/kaslr.c14
-rw-r--r--arch/x86/boot/compressed/kaslr_64.c (renamed from arch/x86/boot/compressed/pagetable.c)14
-rw-r--r--arch/x86/boot/compressed/mem_encrypt.S17
-rw-r--r--arch/x86/boot/compressed/misc.c26
-rw-r--r--arch/x86/boot/compressed/misc.h7
-rw-r--r--arch/x86/boot/compressed/pgtable.h20
-rw-r--r--arch/x86/boot/compressed/pgtable_64.c148
-rw-r--r--arch/x86/entry/entry_64.S7
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl4
-rw-r--r--arch/x86/entry/vdso/vdso32/vclock_gettime.c2
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_64.c2
-rw-r--r--arch/x86/events/core.c28
-rw-r--r--arch/x86/events/intel/core.c35
-rw-r--r--arch/x86/events/intel/cstate.c44
-rw-r--r--arch/x86/events/intel/ds.c132
-rw-r--r--arch/x86/events/intel/pt.c13
-rw-r--r--arch/x86/events/intel/rapl.c2
-rw-r--r--arch/x86/events/intel/uncore.c2
-rw-r--r--arch/x86/events/intel/uncore_snbep.c32
-rw-r--r--arch/x86/events/msr.c3
-rw-r--r--arch/x86/events/perf_event.h11
-rw-r--r--arch/x86/ia32/ia32_signal.c1
-rw-r--r--arch/x86/ia32/sys_ia32.c50
-rw-r--r--arch/x86/include/asm/acpi.h11
-rw-r--r--arch/x86/include/asm/alternative.h4
-rw-r--r--arch/x86/include/asm/apic.h18
-rw-r--r--arch/x86/include/asm/atomic.h106
-rw-r--r--arch/x86/include/asm/atomic64_32.h106
-rw-r--r--arch/x86/include/asm/atomic64_64.h108
-rw-r--r--arch/x86/include/asm/barrier.h30
-rw-r--r--arch/x86/include/asm/cmpxchg.h12
-rw-r--r--arch/x86/include/asm/cmpxchg_32.h8
-rw-r--r--arch/x86/include/asm/cmpxchg_64.h4
-rw-r--r--arch/x86/include/asm/cpufeature.h8
-rw-r--r--arch/x86/include/asm/cpufeatures.h2
-rw-r--r--arch/x86/include/asm/device.h3
-rw-r--r--arch/x86/include/asm/dma-direct.h25
-rw-r--r--arch/x86/include/asm/dma-mapping.h33
-rw-r--r--arch/x86/include/asm/efi.h26
-rw-r--r--arch/x86/include/asm/hw_irq.h1
-rw-r--r--arch/x86/include/asm/intel_pconfig.h65
-rw-r--r--arch/x86/include/asm/io.h15
-rw-r--r--arch/x86/include/asm/io_apic.h10
-rw-r--r--arch/x86/include/asm/iommu.h3
-rw-r--r--arch/x86/include/asm/jailhouse_para.h2
-rw-r--r--arch/x86/include/asm/kaslr.h4
-rw-r--r--arch/x86/include/asm/mce.h53
-rw-r--r--arch/x86/include/asm/mem_encrypt.h3
-rw-r--r--arch/x86/include/asm/microcode.h15
-rw-r--r--arch/x86/include/asm/mmu_context.h5
-rw-r--r--arch/x86/include/asm/msr.h17
-rw-r--r--arch/x86/include/asm/nospec-branch.h5
-rw-r--r--arch/x86/include/asm/page_64.h6
-rw-r--r--arch/x86/include/asm/page_64_types.h20
-rw-r--r--arch/x86/include/asm/paravirt.h21
-rw-r--r--arch/x86/include/asm/pci_x86.h2
-rw-r--r--arch/x86/include/asm/pgalloc.h5
-rw-r--r--arch/x86/include/asm/pgtable-3level_types.h1
-rw-r--r--arch/x86/include/asm/pgtable.h11
-rw-r--r--arch/x86/include/asm/pgtable_32.h2
-rw-r--r--arch/x86/include/asm/pgtable_32_types.h2
-rw-r--r--arch/x86/include/asm/pgtable_64.h23
-rw-r--r--arch/x86/include/asm/pgtable_64_types.h70
-rw-r--r--arch/x86/include/asm/required-features.h8
-rw-r--r--arch/x86/include/asm/smp.h10
-rw-r--r--arch/x86/include/asm/sparsemem.h9
-rw-r--r--arch/x86/include/asm/stacktrace.h2
-rw-r--r--arch/x86/include/asm/swiotlb.h8
-rw-r--r--arch/x86/include/asm/sys_ia32.h67
-rw-r--r--arch/x86/include/asm/syscalls.h3
-rw-r--r--arch/x86/include/asm/tsc.h1
-rw-r--r--arch/x86/include/asm/uv/uv_mmrs.h2
-rw-r--r--arch/x86/include/asm/vmx.h1
-rw-r--r--arch/x86/include/asm/x86_init.h19
-rw-r--r--arch/x86/include/uapi/asm/mce.h52
-rw-r--r--arch/x86/kernel/Makefile4
-rw-r--r--arch/x86/kernel/acpi/boot.c22
-rw-r--r--arch/x86/kernel/amd_gart_64.c41
-rw-r--r--arch/x86/kernel/apic/apic.c111
-rw-r--r--arch/x86/kernel/apic/io_apic.c16
-rw-r--r--arch/x86/kernel/apic/x2apic_phys.c2
-rw-r--r--arch/x86/kernel/cpu/Makefile2
-rw-r--r--arch/x86/kernel/cpu/amd.c2
-rw-r--r--arch/x86/kernel/cpu/intel.c90
-rw-r--r--arch/x86/kernel/cpu/intel_pconfig.c82
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-inject.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-internal.h59
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c38
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c78
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c34
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c76
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c4
-rw-r--r--arch/x86/kernel/cpuid.c34
-rw-r--r--arch/x86/kernel/crash.c3
-rw-r--r--arch/x86/kernel/devicetree.c68
-rw-r--r--arch/x86/kernel/dumpstack.c49
-rw-r--r--arch/x86/kernel/dumpstack_32.c42
-rw-r--r--arch/x86/kernel/dumpstack_64.c42
-rw-r--r--arch/x86/kernel/e820.c18
-rw-r--r--arch/x86/kernel/head64.c81
-rw-r--r--arch/x86/kernel/head_64.S22
-rw-r--r--arch/x86/kernel/idt.c5
-rw-r--r--arch/x86/kernel/ioport.c7
-rw-r--r--arch/x86/kernel/irqinit.c9
-rw-r--r--arch/x86/kernel/jailhouse.c8
-rw-r--r--arch/x86/kernel/kvm.c4
-rw-r--r--arch/x86/kernel/machine_kexec_32.c8
-rw-r--r--arch/x86/kernel/machine_kexec_64.c9
-rw-r--r--arch/x86/kernel/pci-calgary_64.c5
-rw-r--r--arch/x86/kernel/pci-dma.c70
-rw-r--r--arch/x86/kernel/pci-nommu.c19
-rw-r--r--arch/x86/kernel/pci-swiotlb.c48
-rw-r--r--arch/x86/kernel/reboot.c3
-rw-r--r--arch/x86/kernel/rtc.c6
-rw-r--r--arch/x86/kernel/setup.c5
-rw-r--r--arch/x86/kernel/signal.c5
-rw-r--r--arch/x86/kernel/sys_x86_64.c2
-rw-r--r--arch/x86/kernel/traps.c15
-rw-r--r--arch/x86/kernel/tsc.c39
-rw-r--r--arch/x86/kernel/vm86_32.c3
-rw-r--r--arch/x86/kernel/vmlinux.lds.S7
-rw-r--r--arch/x86/kernel/x86_init.c21
-rw-r--r--arch/x86/kvm/mmu.c4
-rw-r--r--arch/x86/kvm/svm.c1
-rw-r--r--arch/x86/kvm/vmx.c20
-rw-r--r--arch/x86/lib/clear_page_64.S2
-rw-r--r--arch/x86/lib/msr-smp.c43
-rw-r--r--arch/x86/mm/Makefile15
-rw-r--r--arch/x86/mm/debug_pagetables.c32
-rw-r--r--arch/x86/mm/dump_pagetables.c125
-rw-r--r--arch/x86/mm/fault.c67
-rw-r--r--arch/x86/mm/ident_map.c2
-rw-r--r--arch/x86/mm/init_64.c92
-rw-r--r--arch/x86/mm/kasan_init_64.c20
-rw-r--r--arch/x86/mm/kaslr.c29
-rw-r--r--arch/x86/mm/mem_encrypt.c668
-rw-r--r--arch/x86/mm/mem_encrypt_identity.c564
-rw-r--r--arch/x86/mm/numa_32.c11
-rw-r--r--arch/x86/mm/pgtable.c48
-rw-r--r--arch/x86/mm/tlb.c4
-rw-r--r--arch/x86/net/bpf_jit_comp.c237
-rw-r--r--arch/x86/pci/acpi.c8
-rw-r--r--arch/x86/pci/direct.c5
-rw-r--r--arch/x86/pci/legacy.c4
-rw-r--r--arch/x86/pci/mmconfig-shared.c13
-rw-r--r--arch/x86/pci/sta2x11-fixup.c52
-rw-r--r--arch/x86/platform/atom/punit_atom_debug.c17
-rw-r--r--arch/x86/platform/efi/efi_64.c68
-rw-r--r--arch/x86/platform/efi/efi_thunk_64.S2
-rw-r--r--arch/x86/platform/efi/quirks.c10
-rw-r--r--arch/x86/platform/intel-mid/intel-mid.c6
-rw-r--r--arch/x86/platform/intel-quark/imr.c24
-rw-r--r--arch/x86/platform/uv/tlb_uv.c2
-rw-r--r--arch/x86/power/hibernate_64.c6
-rw-r--r--arch/x86/purgatory/Makefile2
-rw-r--r--arch/x86/um/asm/barrier.h4
-rw-r--r--arch/x86/xen/Kconfig5
-rw-r--r--arch/x86/xen/apic.c2
-rw-r--r--arch/x86/xen/enlighten_pvh.c14
-rw-r--r--arch/x86/xen/mmu_pv.c21
166 files changed, 2999 insertions, 2478 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0fa71a78ec99..27fede438959 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -54,7 +54,6 @@ config X86
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAS_KCOV if X86_64
- select ARCH_HAS_PHYS_TO_DMA
select ARCH_HAS_MEMBARRIER_SYNC_CORE
select ARCH_HAS_PMEM_API if X86_64
select ARCH_HAS_REFCOUNT
@@ -83,6 +82,7 @@ config X86
select CLOCKSOURCE_VALIDATE_LAST_CYCLE
select CLOCKSOURCE_WATCHDOG
select DCACHE_WORD_ACCESS
+ select DMA_DIRECT_OPS
select EDAC_ATOMIC_SCRUB
select EDAC_SUPPORT
select GENERIC_CLOCKEVENTS
@@ -393,17 +393,6 @@ config X86_FEATURE_NAMES
If in doubt, say Y.
-config X86_FAST_FEATURE_TESTS
- bool "Fast CPU feature tests" if EMBEDDED
- default y
- ---help---
- Some fast-paths in the kernel depend on the capabilities of the CPU.
- Say Y here for the kernel to patch in the appropriate code at runtime
- based on the capabilities of the CPU. The infrastructure for patching
- code at runtime takes up some additional space; space-constrained
- embedded systems may wish to say N here to produce smaller, slightly
- slower code.
-
config X86_X2APIC
bool "Support x2apic"
depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST)
@@ -691,6 +680,7 @@ config X86_SUPPORTS_MEMORY_FAILURE
config STA2X11
bool "STA2X11 Companion Chip Support"
depends on X86_32_NON_STANDARD && PCI
+ select ARCH_HAS_PHYS_TO_DMA
select X86_DEV_DMA_OPS
select X86_DMA_REMAP
select SWIOTLB
@@ -1472,6 +1462,8 @@ config X86_PAE
config X86_5LEVEL
bool "Enable 5-level page tables support"
+ select DYNAMIC_MEMORY_LAYOUT
+ select SPARSEMEM_VMEMMAP
depends on X86_64
---help---
5-level paging enables access to larger address space:
@@ -1480,8 +1472,8 @@ config X86_5LEVEL
It will be supported by future Intel CPUs.
- Note: a kernel with this option enabled can only be booted
- on machines that support the feature.
+ A kernel with the option enabled can be booted on machines that
+ support 4- or 5-level paging.
See Documentation/x86/x86_64/5level-paging.txt for more
information.
@@ -1606,10 +1598,6 @@ config ARCH_HAVE_MEMORY_PRESENT
def_bool y
depends on X86_32 && DISCONTIGMEM
-config NEED_NODE_MEMMAP_SIZE
- def_bool y
- depends on X86_32 && (DISCONTIGMEM || SPARSEMEM)
-
config ARCH_FLATMEM_ENABLE
def_bool y
depends on X86_32 && !NUMA
@@ -2185,10 +2173,17 @@ config PHYSICAL_ALIGN
Don't change this unless you know what you are doing.
+config DYNAMIC_MEMORY_LAYOUT
+ bool
+ ---help---
+ This option makes base addresses of vmalloc and vmemmap as well as
+ __PAGE_OFFSET movable during boot.
+
config RANDOMIZE_MEMORY
bool "Randomize the kernel memory sections"
depends on X86_64
depends on RANDOMIZE_BASE
+ select DYNAMIC_MEMORY_LAYOUT
default RANDOMIZE_BASE
---help---
Randomizes the base virtual address of kernel memory sections
@@ -2632,8 +2627,10 @@ config PCI_DIRECT
depends on PCI && (X86_64 || (PCI_GODIRECT || PCI_GOANY || PCI_GOOLPC || PCI_GOMMCONFIG))
config PCI_MMCONFIG
- def_bool y
- depends on X86_32 && PCI && (ACPI || SFI) && (PCI_GOMMCONFIG || PCI_GOANY)
+ bool "Support mmconfig PCI config space access" if X86_64
+ default y
+ depends on PCI && (ACPI || SFI || JAILHOUSE_GUEST)
+ depends on X86_64 || (PCI_GOANY || PCI_GOMMCONFIG)
config PCI_OLPC
def_bool y
@@ -2648,9 +2645,9 @@ config PCI_DOMAINS
def_bool y
depends on PCI
-config PCI_MMCONFIG
- bool "Support mmconfig PCI config space access"
- depends on X86_64 && PCI && ACPI
+config MMCONF_FAM10H
+ def_bool y
+ depends on X86_64 && PCI_MMCONFIG && ACPI
config PCI_CNB20LE_QUIRK
bool "Read CNB20LE Host Bridge Windows" if EXPERT
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 8b8d2297d486..638411f22267 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -315,19 +315,6 @@ config X86_L1_CACHE_SHIFT
default "4" if MELAN || M486 || MGEODEGX1
default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
-config X86_PPRO_FENCE
- bool "PentiumPro memory ordering errata workaround"
- depends on M686 || M586MMX || M586TSC || M586 || M486 || MGEODEGX1
- ---help---
- Old PentiumPro multiprocessor systems had errata that could cause
- memory operations to violate the x86 ordering standard in rare cases.
- Enabling this option will attempt to work around some (but not all)
- occurrences of this problem, at the cost of much heavier spinlock and
- memory barrier operations.
-
- If unsure, say n here. Even distro kernels should think twice before
- enabling this: there are few systems, and an unlikely bug.
-
config X86_F00F_BUG
def_bool y
depends on M586MMX || M586TSC || M586 || M486
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 498c1b812300..60135cbd905c 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -31,8 +31,7 @@ endif
CODE16GCC_CFLAGS := -m32 -Wa,$(srctree)/arch/x86/boot/code16gcc.h
M16_CFLAGS := $(call cc-option, -m16, $(CODE16GCC_CFLAGS))
-REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -D__KERNEL__ \
- -DDISABLE_BRANCH_PROFILING \
+REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -DDISABLE_BRANCH_PROFILING \
-Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
-fno-strict-aliasing -fomit-frame-pointer -fno-pic \
-mno-mmx -mno-sse
@@ -181,6 +180,10 @@ ifdef CONFIG_FUNCTION_GRAPH_TRACER
endif
endif
+ifndef CC_HAVE_ASM_GOTO
+ $(error Compiler lacks asm-goto support.)
+endif
+
#
# Jump labels need '-maccumulate-outgoing-args' for gcc < 4.5.2 to prevent a
# GCC bug (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46226). There's no way
@@ -223,6 +226,15 @@ KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr)
LDFLAGS := -m elf_$(UTS_MACHINE)
+#
+# The 64-bit kernel must be aligned to 2MB. Pass -z max-page-size=0x200000 to
+# the linker to force 2MB page size regardless of the default page size used
+# by the linker.
+#
+ifdef CONFIG_X86_64
+LDFLAGS += $(call ld-option, -z max-page-size=0x200000)
+endif
+
# Speed up the build
KBUILD_CFLAGS += -pipe
# Workaround for a gcc prelease that unfortunately was shipped in a suse release
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index f25e1530e064..fa42f895fdde 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -26,7 +26,7 @@ KCOV_INSTRUMENT := n
targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4
-KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ -O2
+KBUILD_CFLAGS := -m$(BITS) -O2
KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC)
KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
cflags-$(CONFIG_X86_32) := -march=i386
@@ -78,7 +78,7 @@ vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o
vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o
ifdef CONFIG_X86_64
- vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/pagetable.o
+ vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr_64.o
vmlinux-objs-y += $(obj)/mem_encrypt.o
vmlinux-objs-y += $(obj)/pgtable_64.o
endif
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 886a9115af62..47d3efff6805 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -421,9 +421,10 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
}
}
+static const efi_char16_t apple[] = L"Apple";
+
static void setup_quirks(struct boot_params *boot_params)
{
- efi_char16_t const apple[] = { 'A', 'p', 'p', 'l', 'e', 0 };
efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long)
efi_table_attr(efi_system_table, fw_vendor, sys_table);
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index fc313e29fe2c..fca012baba19 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -33,6 +33,7 @@
#include <asm/processor-flags.h>
#include <asm/asm-offsets.h>
#include <asm/bootparam.h>
+#include "pgtable.h"
/*
* Locally defined symbols should be marked hidden:
@@ -304,55 +305,77 @@ ENTRY(startup_64)
/* Set up the stack */
leaq boot_stack_end(%rbx), %rsp
-#ifdef CONFIG_X86_5LEVEL
/*
- * Check if we need to enable 5-level paging.
- * RSI holds real mode data and need to be preserved across
- * a function call.
+ * At this point we are in long mode with 4-level paging enabled,
+ * but we might want to enable 5-level paging or vice versa.
+ *
+ * The problem is that we cannot do it directly. Setting or clearing
+ * CR4.LA57 in long mode would trigger #GP. So we need to switch off
+ * long mode and paging first.
+ *
+ * We also need a trampoline in lower memory to switch over from
+ * 4- to 5-level paging for cases when the bootloader puts the kernel
+ * above 4G, but didn't enable 5-level paging for us.
+ *
+ * The same trampoline can be used to switch from 5- to 4-level paging
+ * mode, like when starting 4-level paging kernel via kexec() when
+ * original kernel worked in 5-level paging mode.
+ *
+ * For the trampoline, we need the top page table to reside in lower
+ * memory as we don't have a way to load 64-bit values into CR3 in
+ * 32-bit mode.
+ *
+ * We go though the trampoline even if we don't have to: if we're
+ * already in a desired paging mode. This way the trampoline code gets
+ * tested on every boot.
*/
- pushq %rsi
- call l5_paging_required
- popq %rsi
- /* If l5_paging_required() returned zero, we're done here. */
- cmpq $0, %rax
- je lvl5
+ /* Make sure we have GDT with 32-bit code segment */
+ leaq gdt(%rip), %rax
+ movq %rax, gdt64+2(%rip)
+ lgdt gdt64(%rip)
/*
- * At this point we are in long mode with 4-level paging enabled,
- * but we want to enable 5-level paging.
+ * paging_prepare() sets up the trampoline and checks if we need to
+ * enable 5-level paging.
*
- * The problem is that we cannot do it directly. Setting LA57 in
- * long mode would trigger #GP. So we need to switch off long mode
- * first.
+ * Address of the trampoline is returned in RAX.
+ * Non zero RDX on return means we need to enable 5-level paging.
*
- * NOTE: This is not going to work if bootloader put us above 4G
- * limit.
- *
- * The first step is go into compatibility mode.
+ * RSI holds real mode data and needs to be preserved across
+ * this function call.
*/
+ pushq %rsi
+ call paging_prepare
+ popq %rsi
- /* Clear additional page table */
- leaq lvl5_pgtable(%rbx), %rdi
- xorq %rax, %rax
- movq $(PAGE_SIZE/8), %rcx
- rep stosq
+ /* Save the trampoline address in RCX */
+ movq %rax, %rcx
/*
- * Setup current CR3 as the first and only entry in a new top level
- * page table.
+ * Load the address of trampoline_return() into RDI.
+ * It will be used by the trampoline to return to the main code.
*/
- movq %cr3, %rdi
- leaq 0x7 (%rdi), %rax
- movq %rax, lvl5_pgtable(%rbx)
+ leaq trampoline_return(%rip), %rdi
/* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */
pushq $__KERNEL32_CS
- leaq compatible_mode(%rip), %rax
+ leaq TRAMPOLINE_32BIT_CODE_OFFSET(%rax), %rax
pushq %rax
lretq
-lvl5:
-#endif
+trampoline_return:
+ /* Restore the stack, the 32-bit trampoline uses its own stack */
+ leaq boot_stack_end(%rbx), %rsp
+
+ /*
+ * cleanup_trampoline() would restore trampoline memory.
+ *
+ * RSI holds real mode data and needs to be preserved across
+ * this function call.
+ */
+ pushq %rsi
+ call cleanup_trampoline
+ popq %rsi
/* Zero EFLAGS */
pushq $0
@@ -490,46 +513,82 @@ relocated:
jmp *%rax
.code32
-#ifdef CONFIG_X86_5LEVEL
-compatible_mode:
- /* Setup data and stack segments */
+/*
+ * This is the 32-bit trampoline that will be copied over to low memory.
+ *
+ * RDI contains the return address (might be above 4G).
+ * ECX contains the base address of the trampoline memory.
+ * Non zero RDX on return means we need to enable 5-level paging.
+ */
+ENTRY(trampoline_32bit_src)
+ /* Set up data and stack segments */
movl $__KERNEL_DS, %eax
movl %eax, %ds
movl %eax, %ss
+ /* Set up new stack */
+ leal TRAMPOLINE_32BIT_STACK_END(%ecx), %esp
+
/* Disable paging */
movl %cr0, %eax
btrl $X86_CR0_PG_BIT, %eax
movl %eax, %cr0
- /* Point CR3 to 5-level paging */
- leal lvl5_pgtable(%ebx), %eax
- movl %eax, %cr3
+ /* Check what paging mode we want to be in after the trampoline */
+ cmpl $0, %edx
+ jz 1f
- /* Enable PAE and LA57 mode */
+ /* We want 5-level paging: don't touch CR3 if it already points to 5-level page tables */
+ movl %cr4, %eax
+ testl $X86_CR4_LA57, %eax
+ jnz 3f
+ jmp 2f
+1:
+ /* We want 4-level paging: don't touch CR3 if it already points to 4-level page tables */
movl %cr4, %eax
- orl $(X86_CR4_PAE | X86_CR4_LA57), %eax
+ testl $X86_CR4_LA57, %eax
+ jz 3f
+2:
+ /* Point CR3 to the trampoline's new top level page table */
+ leal TRAMPOLINE_32BIT_PGTABLE_OFFSET(%ecx), %eax
+ movl %eax, %cr3
+3:
+ /* Enable PAE and LA57 (if required) paging modes */
+ movl $X86_CR4_PAE, %eax
+ cmpl $0, %edx
+ jz 1f
+ orl $X86_CR4_LA57, %eax
+1:
movl %eax, %cr4
- /* Calculate address we are running at */
- call 1f
-1: popl %edi
- subl $1b, %edi
+ /* Calculate address of paging_enabled() once we are executing in the trampoline */
+ leal paging_enabled - trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_OFFSET(%ecx), %eax
- /* Prepare stack for far return to Long Mode */
+ /* Prepare the stack for far return to Long Mode */
pushl $__KERNEL_CS
- leal lvl5(%edi), %eax
- push %eax
+ pushl %eax
- /* Enable paging back */
+ /* Enable paging again */
movl $(X86_CR0_PG | X86_CR0_PE), %eax
movl %eax, %cr0
lret
-#endif
+ .code64
+paging_enabled:
+ /* Return from the trampoline */
+ jmp *%rdi
+
+ /*
+ * The trampoline code has a size limit.
+ * Make sure we fail to compile if the trampoline code grows
+ * beyond TRAMPOLINE_32BIT_CODE_SIZE bytes.
+ */
+ .org trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE
+
+ .code32
no_longmode:
- /* This isn't an x86-64 CPU so hang */
+ /* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */
1:
hlt
jmp 1b
@@ -537,6 +596,11 @@ no_longmode:
#include "../../kernel/verify_cpu.S"
.data
+gdt64:
+ .word gdt_end - gdt
+ .long 0
+ .word 0
+ .quad 0
gdt:
.word gdt_end - gdt
.long gdt
@@ -585,7 +649,3 @@ boot_stack_end:
.balign 4096
pgtable:
.fill BOOT_PGT_SIZE, 1, 0
-#ifdef CONFIG_X86_5LEVEL
-lvl5_pgtable:
- .fill PAGE_SIZE, 1, 0
-#endif
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index 8199a6187251..66e42a098d70 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -46,6 +46,12 @@
#define STATIC
#include <linux/decompress/mm.h>
+#ifdef CONFIG_X86_5LEVEL
+unsigned int pgtable_l5_enabled __ro_after_init;
+unsigned int pgdir_shift __ro_after_init = 39;
+unsigned int ptrs_per_p4d __ro_after_init = 1;
+#endif
+
extern unsigned long get_cmd_line_ptr(void);
/* Simplified build-specific string for starting entropy. */
@@ -723,6 +729,14 @@ void choose_random_location(unsigned long input,
return;
}
+#ifdef CONFIG_X86_5LEVEL
+ if (__read_cr4() & X86_CR4_LA57) {
+ pgtable_l5_enabled = 1;
+ pgdir_shift = 48;
+ ptrs_per_p4d = 512;
+ }
+#endif
+
boot_params->hdr.loadflags |= KASLR_FLAG;
/* Prepare to add new identity pagetables on demand. */
diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/kaslr_64.c
index b5e5e02f8cde..522d11431433 100644
--- a/arch/x86/boot/compressed/pagetable.c
+++ b/arch/x86/boot/compressed/kaslr_64.c
@@ -16,13 +16,6 @@
#define __pa(x) ((unsigned long)(x))
#define __va(x) ((void *)((unsigned long)(x)))
-/*
- * The pgtable.h and mm/ident_map.c includes make use of the SME related
- * information which is not used in the compressed image support. Un-define
- * the SME support to avoid any compile and link errors.
- */
-#undef CONFIG_AMD_MEM_ENCRYPT
-
/* No PAGE_TABLE_ISOLATION support needed either: */
#undef CONFIG_PAGE_TABLE_ISOLATION
@@ -85,13 +78,14 @@ static struct x86_mapping_info mapping_info;
/* Locates and clears a region for a new top level page table. */
void initialize_identity_maps(void)
{
- unsigned long sev_me_mask = get_sev_encryption_mask();
+ /* If running as an SEV guest, the encryption mask is required. */
+ set_sev_encryption_mask();
/* Init mapping_info with run-time function/buffer pointers. */
mapping_info.alloc_pgt_page = alloc_pgt_page;
mapping_info.context = &pgt_data;
- mapping_info.page_flag = __PAGE_KERNEL_LARGE_EXEC | sev_me_mask;
- mapping_info.kernpg_flag = _KERNPG_TABLE | sev_me_mask;
+ mapping_info.page_flag = __PAGE_KERNEL_LARGE_EXEC | sme_me_mask;
+ mapping_info.kernpg_flag = _KERNPG_TABLE;
/*
* It should be impossible for this not to already be true,
diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S
index 54f5f6625a73..eaa843a52907 100644
--- a/arch/x86/boot/compressed/mem_encrypt.S
+++ b/arch/x86/boot/compressed/mem_encrypt.S
@@ -88,9 +88,7 @@ ENTRY(get_sev_encryption_bit)
ENDPROC(get_sev_encryption_bit)
.code64
-ENTRY(get_sev_encryption_mask)
- xor %rax, %rax
-
+ENTRY(set_sev_encryption_mask)
#ifdef CONFIG_AMD_MEM_ENCRYPT
push %rbp
push %rdx
@@ -101,9 +99,7 @@ ENTRY(get_sev_encryption_mask)
testl %eax, %eax
jz .Lno_sev_mask
- xor %rdx, %rdx
- bts %rax, %rdx /* Create the encryption mask */
- mov %rdx, %rax /* ... and return it */
+ bts %rax, sme_me_mask(%rip) /* Create the encryption mask */
.Lno_sev_mask:
movq %rbp, %rsp /* Restore original stack pointer */
@@ -112,9 +108,16 @@ ENTRY(get_sev_encryption_mask)
pop %rbp
#endif
+ xor %rax, %rax
ret
-ENDPROC(get_sev_encryption_mask)
+ENDPROC(set_sev_encryption_mask)
.data
enc_bit:
.int 0xffffffff
+
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+ .balign 8
+GLOBAL(sme_me_mask)
+ .quad 0
+#endif
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 98761a1576ce..8dd1d5ccae58 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -14,6 +14,7 @@
#include "misc.h"
#include "error.h"
+#include "pgtable.h"
#include "../string.h"
#include "../voffset.h"
@@ -169,16 +170,6 @@ void __puthex(unsigned long value)
}
}
-static bool l5_supported(void)
-{
- /* Check if leaf 7 is supported. */
- if (native_cpuid_eax(0) < 7)
- return 0;
-
- /* Check if la57 is supported. */
- return native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31));
-}
-
#if CONFIG_X86_NEED_RELOCS
static void handle_relocations(void *output, unsigned long output_len,
unsigned long virt_addr)
@@ -309,6 +300,10 @@ static void parse_elf(void *output)
switch (phdr->p_type) {
case PT_LOAD:
+#ifdef CONFIG_X86_64
+ if ((phdr->p_align % 0x200000) != 0)
+ error("Alignment of LOAD segment isn't multiple of 2MB");
+#endif
#ifdef CONFIG_RELOCATABLE
dest = output;
dest += (phdr->p_paddr - LOAD_PHYSICAL_ADDR);
@@ -372,12 +367,6 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
console_init();
debug_putstr("early console in extract_kernel\n");
- if (IS_ENABLED(CONFIG_X86_5LEVEL) && !l5_supported()) {
- error("This linux kernel as configured requires 5-level paging\n"
- "This CPU does not support the required 'cr4.la57' feature\n"
- "Unable to boot - please use a kernel appropriate for your CPU\n");
- }
-
free_mem_ptr = heap; /* Heap */
free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
@@ -388,6 +377,11 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
debug_putaddr(output_len);
debug_putaddr(kernel_total_size);
+#ifdef CONFIG_X86_64
+ /* Report address of 32-bit trampoline */
+ debug_putaddr(trampoline_32bit);
+#endif
+
/*
* The memory hole needed for the kernel is the larger of either
* the entire decompressed kernel plus relocation table, or the
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 9d323dc6b159..9e11be4cae19 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -12,6 +12,11 @@
#undef CONFIG_PARAVIRT_SPINLOCKS
#undef CONFIG_KASAN
+#ifdef CONFIG_X86_5LEVEL
+/* cpu_feature_enabled() cannot be used that early */
+#define pgtable_l5_enabled __pgtable_l5_enabled
+#endif
+
#include <linux/linkage.h>
#include <linux/screen_info.h>
#include <linux/elf.h>
@@ -109,6 +114,6 @@ static inline void console_init(void)
{ }
#endif
-unsigned long get_sev_encryption_mask(void);
+void set_sev_encryption_mask(void);
#endif
diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h
new file mode 100644
index 000000000000..91f75638f6e6
--- /dev/null
+++ b/arch/x86/boot/compressed/pgtable.h
@@ -0,0 +1,20 @@
+#ifndef BOOT_COMPRESSED_PAGETABLE_H
+#define BOOT_COMPRESSED_PAGETABLE_H
+
+#define TRAMPOLINE_32BIT_SIZE (2 * PAGE_SIZE)
+
+#define TRAMPOLINE_32BIT_PGTABLE_OFFSET 0
+
+#define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE
+#define TRAMPOLINE_32BIT_CODE_SIZE 0x60
+
+#define TRAMPOLINE_32BIT_STACK_END TRAMPOLINE_32BIT_SIZE
+
+#ifndef __ASSEMBLER__
+
+extern unsigned long *trampoline_32bit;
+
+extern void trampoline_32bit_src(void *return_ptr);
+
+#endif /* __ASSEMBLER__ */
+#endif /* BOOT_COMPRESSED_PAGETABLE_H */
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index b4469a37e9a1..32af1cbcd903 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -1,4 +1,6 @@
#include <asm/processor.h>
+#include "pgtable.h"
+#include "../string.h"
/*
* __force_order is used by special_insns.h asm code to force instruction
@@ -9,20 +11,144 @@
*/
unsigned long __force_order;
-int l5_paging_required(void)
+#define BIOS_START_MIN 0x20000U /* 128K, less than this is insane */
+#define BIOS_START_MAX 0x9f000U /* 640K, absolute maximum */
+
+struct paging_config {
+ unsigned long trampoline_start;
+ unsigned long l5_required;
+};
+
+/* Buffer to preserve trampoline memory */
+static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
+
+/*
+ * The page table is going to be used instead of page table in the trampoline
+ * memory.
+ *
+ * It must not be in BSS as BSS is cleared after cleanup_trampoline().
+ */
+static char top_pgtable[PAGE_SIZE] __aligned(PAGE_SIZE) __section(.data);
+
+/*
+ * Trampoline address will be printed by extract_kernel() for debugging
+ * purposes.
+ *
+ * Avoid putting the pointer into .bss as it will be cleared between
+ * paging_prepare() and extract_kernel().
+ */
+unsigned long *trampoline_32bit __section(.data);
+
+struct paging_config paging_prepare(void)
{
- /* Check if leaf 7 is supported. */
+ struct paging_config paging_config = {};
+ unsigned long bios_start, ebda_start;
+
+ /*
+ * Check if LA57 is desired and supported.
+ *
+ * There are two parts to the check:
+ * - if the kernel supports 5-level paging: CONFIG_X86_5LEVEL=y
+ * - if the machine supports 5-level paging:
+ * + CPUID leaf 7 is supported
+ * + the leaf has the feature bit set
+ *
+ * That's substitute for boot_cpu_has() in early boot code.
+ */
+ if (IS_ENABLED(CONFIG_X86_5LEVEL) &&
+ native_cpuid_eax(0) >= 7 &&
+ (native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) {
+ paging_config.l5_required = 1;
+ }
+
+ /*
+ * Find a suitable spot for the trampoline.
+ * This code is based on reserve_bios_regions().
+ */
+
+ ebda_start = *(unsigned short *)0x40e << 4;
+ bios_start = *(unsigned short *)0x413 << 10;
- if (native_cpuid_eax(0) < 7)
- return 0;
+ if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX)
+ bios_start = BIOS_START_MAX;
+
+ if (ebda_start > BIOS_START_MIN && ebda_start < bios_start)
+ bios_start = ebda_start;
+
+ /* Place the trampoline just below the end of low memory, aligned to 4k */
+ paging_config.trampoline_start = bios_start - TRAMPOLINE_32BIT_SIZE;
+ paging_config.trampoline_start = round_down(paging_config.trampoline_start, PAGE_SIZE);
+
+ trampoline_32bit = (unsigned long *)paging_config.trampoline_start;
+
+ /* Preserve trampoline memory */
+ memcpy(trampoline_save, trampoline_32bit, TRAMPOLINE_32BIT_SIZE);
+
+ /* Clear trampoline memory first */
+ memset(trampoline_32bit, 0, TRAMPOLINE_32BIT_SIZE);
+
+ /* Copy trampoline code in place */
+ memcpy(trampoline_32bit + TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long),
+ &trampoline_32bit_src, TRAMPOLINE_32BIT_CODE_SIZE);
+
+ /*
+ * The code below prepares page table in trampoline memory.
+ *
+ * The new page table will be used by trampoline code for switching
+ * from 4- to 5-level paging or vice versa.
+ *
+ * If switching is not required, the page table is unused: trampoline
+ * code wouldn't touch CR3.
+ */
+
+ /*
+ * We are not going to use the page table in trampoline memory if we
+ * are already in the desired paging mode.
+ */
+ if (paging_config.l5_required == !!(native_read_cr4() & X86_CR4_LA57))
+ goto out;
+
+ if (paging_config.l5_required) {
+ /*
+ * For 4- to 5-level paging transition, set up current CR3 as
+ * the first and the only entry in a new top-level page table.
+ */
+ trampoline_32bit[TRAMPOLINE_32BIT_PGTABLE_OFFSET] = __native_read_cr3() | _PAGE_TABLE_NOENC;
+ } else {
+ unsigned long src;
+
+ /*
+ * For 5- to 4-level paging transition, copy page table pointed
+ * by first entry in the current top-level page table as our
+ * new top-level page table.
+ *
+ * We cannot just point to the page table from trampoline as it
+ * may be above 4G.
+ */
+ src = *(unsigned long *)__native_read_cr3() & PAGE_MASK;
+ memcpy(trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long),
+ (void *)src, PAGE_SIZE);
+ }
+
+out:
+ return paging_config;
+}
+
+void cleanup_trampoline(void)
+{
+ void *trampoline_pgtable;
- /* Check if la57 is supported. */
- if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31))))
- return 0;
+ trampoline_pgtable = trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET;
- /* Check if 5-level paging has already been enabled. */
- if (native_read_cr4() & X86_CR4_LA57)
- return 0;
+ /*
+ * Move the top level page table out of trampoline memory,
+ * if it's there.
+ */
+ if ((void *)__native_read_cr3() == trampoline_pgtable) {
+ memcpy(top_pgtable, trampoline_pgtable, PAGE_SIZE);
+ native_write_cr3((unsigned long)top_pgtable);
+ }
- return 1;
+ /* Restore trampoline memory */
+ memcpy(trampoline_32bit, trampoline_save, TRAMPOLINE_32BIT_SIZE);
}
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 805f52703ee3..936e19642eab 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -260,8 +260,13 @@ GLOBAL(entry_SYSCALL_64_after_hwframe)
* Change top bits to match most significant bit (47th or 56th bit
* depending on paging mode) in the address.
*/
+#ifdef CONFIG_X86_5LEVEL
+ ALTERNATIVE "shl $(64 - 48), %rcx; sar $(64 - 48), %rcx", \
+ "shl $(64 - 57), %rcx; sar $(64 - 57), %rcx", X86_FEATURE_LA57
+#else
shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
+#endif
/* If this changed %rcx, it was not canonical */
cmpq %rcx, %r11
@@ -1138,7 +1143,7 @@ apicinterrupt3 HYPERV_REENLIGHTENMENT_VECTOR \
#endif /* CONFIG_HYPERV */
idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
+idtentry int3 do_int3 has_error_code=0
idtentry stack_segment do_stack_segment has_error_code=1
#ifdef CONFIG_XEN
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 2a5e99cff859..c58f75b088c5 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -13,7 +13,7 @@
4 i386 write sys_write
5 i386 open sys_open compat_sys_open
6 i386 close sys_close
-7 i386 waitpid sys_waitpid compat_sys_x86_waitpid
+7 i386 waitpid sys_waitpid
8 i386 creat sys_creat
9 i386 link sys_link
10 i386 unlink sys_unlink
@@ -137,7 +137,7 @@
128 i386 init_module sys_init_module
129 i386 delete_module sys_delete_module
130 i386 get_kernel_syms
-131 i386 quotactl sys_quotactl sys32_quotactl
+131 i386 quotactl sys_quotactl compat_sys_quotactl32
132 i386 getpgid sys_getpgid
133 i386 fchdir sys_fchdir
134 i386 bdflush sys_bdflush
diff --git a/arch/x86/entry/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
index 7780bbfb06ef..9242b28418d5 100644
--- a/arch/x86/entry/vdso/vdso32/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
@@ -5,8 +5,6 @@
#undef CONFIG_OPTIMIZE_INLINING
#endif
-#undef CONFIG_X86_PPRO_FENCE
-
#ifdef CONFIG_X86_64
/*
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 8560ef68a9d6..317be365bce3 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -347,7 +347,7 @@ void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
p4d = p4d_offset(pgd, VSYSCALL_ADDR);
#if CONFIG_PGTABLE_LEVELS >= 5
- p4d->p4d |= _PAGE_USER;
+ set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER));
#endif
pud = pud_offset(p4d, VSYSCALL_ADDR);
set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 140d33288e78..a6006e7bb729 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -48,7 +48,7 @@ DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
.enabled = 1,
};
-struct static_key rdpmc_always_available = STATIC_KEY_INIT_FALSE;
+DEFINE_STATIC_KEY_FALSE(rdpmc_always_available_key);
u64 __read_mostly hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
@@ -990,7 +990,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
if (!dogrp)
return n;
- list_for_each_entry(event, &leader->sibling_list, group_entry) {
+ for_each_sibling_event(event, leader) {
if (!is_x86_event(event) ||
event->state <= PERF_EVENT_STATE_OFF)
continue;
@@ -1156,16 +1156,13 @@ int x86_perf_event_set_period(struct perf_event *event)
per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
- if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) ||
- local64_read(&hwc->prev_count) != (u64)-left) {
- /*
- * The hw event starts counting from this event offset,
- * mark it to be able to extra future deltas:
- */
- local64_set(&hwc->prev_count, (u64)-left);
+ /*
+ * The hw event starts counting from this event offset,
+ * mark it to be able to extra future deltas:
+ */
+ local64_set(&hwc->prev_count, (u64)-left);
- wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
- }
+ wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
/*
* Due to erratum on certan cpu we need
@@ -1884,6 +1881,8 @@ early_initcall(init_hw_perf_events);
static inline void x86_pmu_read(struct perf_event *event)
{
+ if (x86_pmu.read)
+ return x86_pmu.read(event);
x86_perf_event_update(event);
}
@@ -2118,7 +2117,8 @@ static int x86_pmu_event_init(struct perf_event *event)
event->destroy(event);
}
- if (READ_ONCE(x86_pmu.attr_rdpmc))
+ if (READ_ONCE(x86_pmu.attr_rdpmc) &&
+ !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS))
event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED;
return err;
@@ -2206,9 +2206,9 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
* but only root can trigger it, so it's okay.
*/
if (val == 2)
- static_key_slow_inc(&rdpmc_always_available);
+ static_branch_inc(&rdpmc_always_available_key);
else
- static_key_slow_dec(&rdpmc_always_available);
+ static_branch_dec(&rdpmc_always_available_key);
on_each_cpu(refresh_pce, NULL, 1);
}
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 56457cb73448..607bf565a90c 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2060,6 +2060,14 @@ static void intel_pmu_del_event(struct perf_event *event)
intel_pmu_pebs_del(event);
}
+static void intel_pmu_read_event(struct perf_event *event)
+{
+ if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
+ intel_pmu_auto_reload_read(event);
+ else
+ x86_perf_event_update(event);
+}
+
static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
{
int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
@@ -2201,16 +2209,23 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
int bit, loops;
u64 status;
int handled;
+ int pmu_enabled;
cpuc = this_cpu_ptr(&cpu_hw_events);
/*
+ * Save the PMU state.
+ * It needs to be restored when leaving the handler.
+ */
+ pmu_enabled = cpuc->enabled;
+ /*
* No known reason to not always do late ACK,
* but just in case do it opt-in.
*/
if (!x86_pmu.late_ack)
apic_write(APIC_LVTPC, APIC_DM_NMI);
intel_bts_disable_local();
+ cpuc->enabled = 0;
__intel_pmu_disable_all();
handled = intel_pmu_drain_bts_buffer();
handled += intel_bts_interrupt();
@@ -2320,7 +2335,8 @@ again:
done:
/* Only restore PMU state when it's active. See x86_pmu_disable(). */
- if (cpuc->enabled)
+ cpuc->enabled = pmu_enabled;
+ if (pmu_enabled)
__intel_pmu_enable_all(0, true);
intel_bts_enable_local();
@@ -2952,9 +2968,9 @@ static void intel_pebs_aliases_skl(struct perf_event *event)
return intel_pebs_aliases_precdist(event);
}
-static unsigned long intel_pmu_free_running_flags(struct perf_event *event)
+static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
{
- unsigned long flags = x86_pmu.free_running_flags;
+ unsigned long flags = x86_pmu.large_pebs_flags;
if (event->attr.use_clockid)
flags &= ~PERF_SAMPLE_TIME;
@@ -2976,8 +2992,8 @@ static int intel_pmu_hw_config(struct perf_event *event)
if (!event->attr.freq) {
event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
if (!(event->attr.sample_type &
- ~intel_pmu_free_running_flags(event)))
- event->hw.flags |= PERF_X86_EVENT_FREERUNNING;
+ ~intel_pmu_large_pebs_flags(event)))
+ event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS;
}
if (x86_pmu.pebs_aliases)
x86_pmu.pebs_aliases(event);
@@ -3188,13 +3204,13 @@ glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
* Therefore the effective (average) period matches the requested period,
* despite coarser hardware granularity.
*/
-static unsigned bdw_limit_period(struct perf_event *event, unsigned left)
+static u64 bdw_limit_period(struct perf_event *event, u64 left)
{
if ((event->hw.config & INTEL_ARCH_EVENT_MASK) ==
X86_CONFIG(.event=0xc0, .umask=0x01)) {
if (left < 128)
left = 128;
- left &= ~0x3fu;
+ left &= ~0x3fULL;
}
return left;
}
@@ -3460,7 +3476,7 @@ static __initconst const struct x86_pmu core_pmu = {
.event_map = intel_pmu_event_map,
.max_events = ARRAY_SIZE(intel_perfmon_event_map),
.apic = 1,
- .free_running_flags = PEBS_FREERUNNING_FLAGS,
+ .large_pebs_flags = LARGE_PEBS_FLAGS,
/*
* Intel PMCs cannot be accessed sanely above 32-bit width,
@@ -3495,6 +3511,7 @@ static __initconst const struct x86_pmu intel_pmu = {
.disable = intel_pmu_disable_event,
.add = intel_pmu_add_event,
.del = intel_pmu_del_event,
+ .read = intel_pmu_read_event,
.hw_config = intel_pmu_hw_config,
.schedule_events = x86_schedule_events,
.eventsel = MSR_ARCH_PERFMON_EVENTSEL0,
@@ -3502,7 +3519,7 @@ static __initconst const struct x86_pmu intel_pmu = {
.event_map = intel_pmu_event_map,
.max_events = ARRAY_SIZE(intel_perfmon_event_map),
.apic = 1,
- .free_running_flags = PEBS_FREERUNNING_FLAGS,
+ .large_pebs_flags = LARGE_PEBS_FLAGS,
/*
* Intel PMCs cannot be accessed sanely above 32 bit width,
* so we install an artificial 1<<31 period regardless of
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 72db0664a53d..9aca448bb8e6 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -40,50 +40,51 @@
* Model specific counters:
* MSR_CORE_C1_RES: CORE C1 Residency Counter
* perf code: 0x00
- * Available model: SLM,AMT,GLM
+ * Available model: SLM,AMT,GLM,CNL
* Scope: Core (each processor core has a MSR)
* MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
* perf code: 0x01
- * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM
+ * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM,
+ CNL
* Scope: Core
* MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
* perf code: 0x02
- * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- * SKL,KNL,GLM
+ * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
+ * SKL,KNL,GLM,CNL
* Scope: Core
* MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
* perf code: 0x03
- * Available model: SNB,IVB,HSW,BDW,SKL
+ * Available model: SNB,IVB,HSW,BDW,SKL,CNL
* Scope: Core
* MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter.
* perf code: 0x00
- * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM
+ * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL
* Scope: Package (physical package)
* MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter.
* perf code: 0x01
- * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL
- * GLM
+ * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
+ * GLM,CNL
* Scope: Package (physical package)
* MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter.
* perf code: 0x02
* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- * SKL,KNL,GLM
+ * SKL,KNL,GLM,CNL
* Scope: Package (physical package)
* MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter.
* perf code: 0x03
- * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL
* Scope: Package (physical package)
* MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter.
* perf code: 0x04
- * Available model: HSW ULT only
+ * Available model: HSW ULT,CNL
* Scope: Package (physical package)
* MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter.
* perf code: 0x05
- * Available model: HSW ULT only
+ * Available model: HSW ULT,CNL
* Scope: Package (physical package)
* MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
* perf code: 0x06
- * Available model: HSW ULT, GLM
+ * Available model: HSW ULT,GLM,CNL
* Scope: Package (physical package)
*
*/
@@ -486,6 +487,21 @@ static const struct cstate_model hswult_cstates __initconst = {
BIT(PERF_CSTATE_PKG_C10_RES),
};
+static const struct cstate_model cnl_cstates __initconst = {
+ .core_events = BIT(PERF_CSTATE_CORE_C1_RES) |
+ BIT(PERF_CSTATE_CORE_C3_RES) |
+ BIT(PERF_CSTATE_CORE_C6_RES) |
+ BIT(PERF_CSTATE_CORE_C7_RES),
+
+ .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) |
+ BIT(PERF_CSTATE_PKG_C3_RES) |
+ BIT(PERF_CSTATE_PKG_C6_RES) |
+ BIT(PERF_CSTATE_PKG_C7_RES) |
+ BIT(PERF_CSTATE_PKG_C8_RES) |
+ BIT(PERF_CSTATE_PKG_C9_RES) |
+ BIT(PERF_CSTATE_PKG_C10_RES),
+};
+
static const struct cstate_model slm_cstates __initconst = {
.core_events = BIT(PERF_CSTATE_CORE_C1_RES) |
BIT(PERF_CSTATE_CORE_C6_RES),
@@ -557,6 +573,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_MOBILE, cnl_cstates),
+
X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 18c25ab28557..da6780122786 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -935,7 +935,7 @@ void intel_pmu_pebs_add(struct perf_event *event)
bool needed_cb = pebs_needs_sched_cb(cpuc);
cpuc->n_pebs++;
- if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+ if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
cpuc->n_large_pebs++;
pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
@@ -975,7 +975,7 @@ void intel_pmu_pebs_del(struct perf_event *event)
bool needed_cb = pebs_needs_sched_cb(cpuc);
cpuc->n_pebs--;
- if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+ if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
cpuc->n_large_pebs--;
pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
@@ -1153,6 +1153,7 @@ static void setup_pebs_sample_data(struct perf_event *event,
if (pebs == NULL)
return;
+ regs->flags &= ~PERF_EFLAGS_EXACT;
sample_type = event->attr.sample_type;
dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
@@ -1197,7 +1198,6 @@ static void setup_pebs_sample_data(struct perf_event *event,
*/
*regs = *iregs;
regs->flags = pebs->flags;
- set_linear_ip(regs, pebs->ip);
if (sample_type & PERF_SAMPLE_REGS_INTR) {
regs->ax = pebs->ax;
@@ -1233,13 +1233,22 @@ static void setup_pebs_sample_data(struct perf_event *event,
#endif
}
- if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
- regs->ip = pebs->real_ip;
- regs->flags |= PERF_EFLAGS_EXACT;
- } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs))
- regs->flags |= PERF_EFLAGS_EXACT;
- else
- regs->flags &= ~PERF_EFLAGS_EXACT;
+ if (event->attr.precise_ip > 1) {
+ /* Haswell and later have the eventing IP, so use it: */
+ if (x86_pmu.intel_cap.pebs_format >= 2) {
+ set_linear_ip(regs, pebs->real_ip);
+ regs->flags |= PERF_EFLAGS_EXACT;
+ } else {
+ /* Otherwise use PEBS off-by-1 IP: */
+ set_linear_ip(regs, pebs->ip);
+
+ /* ... and try to fix it up using the LBR entries: */
+ if (intel_pmu_pebs_fixup_ip(regs))
+ regs->flags |= PERF_EFLAGS_EXACT;
+ }
+ } else
+ set_linear_ip(regs, pebs->ip);
+
if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) &&
x86_pmu.intel_cap.pebs_format >= 1)
@@ -1306,17 +1315,93 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
return NULL;
}
+void intel_pmu_auto_reload_read(struct perf_event *event)
+{
+ WARN_ON(!(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD));
+
+ perf_pmu_disable(event->pmu);
+ intel_pmu_drain_pebs_buffer();
+ perf_pmu_enable(event->pmu);
+}
+
+/*
+ * Special variant of intel_pmu_save_and_restart() for auto-reload.
+ */
+static int
+intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ int shift = 64 - x86_pmu.cntval_bits;
+ u64 period = hwc->sample_period;
+ u64 prev_raw_count, new_raw_count;
+ s64 new, old;
+
+ WARN_ON(!period);
+
+ /*
+ * drain_pebs() only happens when the PMU is disabled.
+ */
+ WARN_ON(this_cpu_read(cpu_hw_events.enabled));
+
+ prev_raw_count = local64_read(&hwc->prev_count);
+ rdpmcl(hwc->event_base_rdpmc, new_raw_count);
+ local64_set(&hwc->prev_count, new_raw_count);
+
+ /*
+ * Since the counter increments a negative counter value and
+ * overflows on the sign switch, giving the interval:
+ *
+ * [-period, 0]
+ *
+ * the difference between two consequtive reads is:
+ *
+ * A) value2 - value1;
+ * when no overflows have happened in between,
+ *
+ * B) (0 - value1) + (value2 - (-period));
+ * when one overflow happened in between,
+ *
+ * C) (0 - value1) + (n - 1) * (period) + (value2 - (-period));
+ * when @n overflows happened in between.
+ *
+ * Here A) is the obvious difference, B) is the extension to the
+ * discrete interval, where the first term is to the top of the
+ * interval and the second term is from the bottom of the next
+ * interval and C) the extension to multiple intervals, where the
+ * middle term is the whole intervals covered.
+ *
+ * An equivalent of C, by reduction, is:
+ *
+ * value2 - value1 + n * period
+ */
+ new = ((s64)(new_raw_count << shift) >> shift);
+ old = ((s64)(prev_raw_count << shift) >> shift);
+ local64_add(new - old + count * period, &event->count);
+
+ perf_event_update_userpage(event);
+
+ return 0;
+}
+
static void __intel_pmu_pebs_event(struct perf_event *event,
struct pt_regs *iregs,
void *base, void *top,
int bit, int count)
{
+ struct hw_perf_event *hwc = &event->hw;
struct perf_sample_data data;
struct pt_regs regs;
void *at = get_next_pebs_record_by_bit(base, top, bit);
- if (!intel_pmu_save_and_restart(event) &&
- !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD))
+ if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
+ /*
+ * Now, auto-reload is only enabled in fixed period mode.
+ * The reload value is always hwc->sample_period.
+ * May need to change it, if auto-reload is enabled in
+ * freq mode later.
+ */
+ intel_pmu_save_and_restart_reload(event, count);
+ } else if (!intel_pmu_save_and_restart(event))
return;
while (count > 1) {
@@ -1368,8 +1453,11 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
return;
n = top - at;
- if (n <= 0)
+ if (n <= 0) {
+ if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
+ intel_pmu_save_and_restart_reload(event, 0);
return;
+ }
__intel_pmu_pebs_event(event, iregs, at, top, 0, n);
}
@@ -1392,8 +1480,22 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
ds->pebs_index = ds->pebs_buffer_base;
- if (unlikely(base >= top))
+ if (unlikely(base >= top)) {
+ /*
+ * The drain_pebs() could be called twice in a short period
+ * for auto-reload event in pmu::read(). There are no
+ * overflows have happened in between.
+ * It needs to call intel_pmu_save_and_restart_reload() to
+ * update the event->count for this case.
+ */
+ for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
+ x86_pmu.max_pebs_events) {
+ event = cpuc->events[bit];
+ if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
+ intel_pmu_save_and_restart_reload(event, 0);
+ }
return;
+ }
for (at = base; at < top; at += x86_pmu.pebs_record_size) {
struct pebs_record_nhm *p = at;
@@ -1530,7 +1632,7 @@ void __init intel_ds_init(void)
x86_pmu.pebs_record_size =
sizeof(struct pebs_record_skl);
x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
- x86_pmu.free_running_flags |= PERF_SAMPLE_TIME;
+ x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
break;
default:
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 81fd41d5a0d9..3b993942a0e4 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1186,8 +1186,12 @@ static int pt_event_addr_filters_validate(struct list_head *filters)
int range = 0;
list_for_each_entry(filter, filters, entry) {
- /* PT doesn't support single address triggers */
- if (!filter->range || !filter->size)
+ /*
+ * PT doesn't support single address triggers and
+ * 'start' filters.
+ */
+ if (!filter->size ||
+ filter->action == PERF_ADDR_FILTER_ACTION_START)
return -EOPNOTSUPP;
if (!filter->inode) {
@@ -1227,7 +1231,10 @@ static void pt_event_addr_filters_sync(struct perf_event *event)
filters->filter[range].msr_a = msr_a;
filters->filter[range].msr_b = msr_b;
- filters->filter[range].config = filter->filter ? 1 : 2;
+ if (filter->action == PERF_ADDR_FILTER_ACTION_FILTER)
+ filters->filter[range].config = 1;
+ else
+ filters->filter[range].config = 2;
range++;
}
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index a2efb490f743..32f3e9423e99 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -774,6 +774,8 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_MOBILE, skl_rapl_init),
+
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init),
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 7874c980d569..a7956fc7ca1d 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -354,7 +354,7 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader,
if (!dogrp)
return n;
- list_for_each_entry(event, &leader->sibling_list, group_entry) {
+ for_each_sibling_event(event, leader) {
if (!is_box_event(box, event) ||
event->state <= PERF_EVENT_STATE_OFF)
continue;
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 22ec65bc033a..c98b943e58b4 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3343,6 +3343,7 @@ static struct extra_reg skx_uncore_cha_extra_regs[] = {
SNBEP_CBO_EVENT_EXTRA_REG(0x9134, 0xffff, 0x4),
SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x8),
SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x38, 0xff, 0x3),
EVENT_EXTRA_END
};
@@ -3562,24 +3563,27 @@ static struct intel_uncore_type *skx_msr_uncores[] = {
NULL,
};
+/*
+ * To determine the number of CHAs, it should read bits 27:0 in the CAPID6
+ * register which located at Device 30, Function 3, Offset 0x9C. PCI ID 0x2083.
+ */
+#define SKX_CAPID6 0x9c
+#define SKX_CHA_BIT_MASK GENMASK(27, 0)
+
static int skx_count_chabox(void)
{
- struct pci_dev *chabox_dev = NULL;
- int bus, count = 0;
+ struct pci_dev *dev = NULL;
+ u32 val = 0;
- while (1) {
- chabox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x208d, chabox_dev);
- if (!chabox_dev)
- break;
- if (count == 0)
- bus = chabox_dev->bus->number;
- if (bus != chabox_dev->bus->number)
- break;
- count++;
- }
+ dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2083, dev);
+ if (!dev)
+ goto out;
- pci_dev_put(chabox_dev);
- return count;
+ pci_read_config_dword(dev, SKX_CAPID6, &val);
+ val &= SKX_CHA_BIT_MASK;
+out:
+ pci_dev_put(dev);
+ return hweight32(val);
}
void skx_uncore_cpu_init(void)
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 18e2628e2d8f..e7edf19e64c2 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -188,10 +188,11 @@ static inline u64 msr_read_counter(struct perf_event *event)
if (event->hw.event_base)
rdmsrl(event->hw.event_base, now);
else
- rdtscll(now);
+ now = rdtsc_ordered();
return now;
}
+
static void msr_event_update(struct perf_event *event)
{
u64 prev, now;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 78f91ec1056e..9f3711470ec1 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -69,7 +69,7 @@ struct event_constraint {
#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */
#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */
#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */
-#define PERF_X86_EVENT_FREERUNNING 0x0800 /* use freerunning PEBS */
+#define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */
struct amd_nb {
@@ -88,7 +88,7 @@ struct amd_nb {
* REGS_USER can be handled for events limited to ring 3.
*
*/
-#define PEBS_FREERUNNING_FLAGS \
+#define LARGE_PEBS_FLAGS \
(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
@@ -520,6 +520,7 @@ struct x86_pmu {
void (*disable)(struct perf_event *);
void (*add)(struct perf_event *);
void (*del)(struct perf_event *);
+ void (*read)(struct perf_event *event);
int (*hw_config)(struct perf_event *event);
int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
unsigned eventsel;
@@ -557,7 +558,7 @@ struct x86_pmu {
struct x86_pmu_quirk *quirks;
int perfctr_second_write;
bool late_ack;
- unsigned (*limit_period)(struct perf_event *event, unsigned l);
+ u64 (*limit_period)(struct perf_event *event, u64 l);
/*
* sysfs attrs
@@ -608,7 +609,7 @@ struct x86_pmu {
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
int max_pebs_events;
- unsigned long free_running_flags;
+ unsigned long large_pebs_flags;
/*
* Intel LBR
@@ -923,6 +924,8 @@ void intel_pmu_pebs_disable_all(void);
void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
+void intel_pmu_auto_reload_read(struct perf_event *event);
+
void intel_ds_init(void);
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 41c671854642..86b1341cba9a 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -33,7 +33,6 @@
#include <asm/vdso.h>
#include <asm/sigframe.h>
#include <asm/sighandling.h>
-#include <asm/sys_ia32.h>
#include <asm/smap.h>
/*
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 6512498bbef6..11ef7b7c9cc8 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -41,12 +41,13 @@
#include <linux/highuid.h>
#include <linux/sysctl.h>
#include <linux/slab.h>
+#include <linux/sched/task.h>
#include <asm/mman.h>
#include <asm/types.h>
#include <linux/uaccess.h>
#include <linux/atomic.h>
#include <asm/vgtod.h>
-#include <asm/sys_ia32.h>
+#include <asm/ia32.h>
#define AA(__x) ((unsigned long)(__x))
@@ -54,13 +55,14 @@
COMPAT_SYSCALL_DEFINE3(x86_truncate64, const char __user *, filename,
unsigned long, offset_low, unsigned long, offset_high)
{
- return sys_truncate(filename, ((loff_t) offset_high << 32) | offset_low);
+ return ksys_truncate(filename,
+ ((loff_t) offset_high << 32) | offset_low);
}
COMPAT_SYSCALL_DEFINE3(x86_ftruncate64, unsigned int, fd,
unsigned long, offset_low, unsigned long, offset_high)
{
- return sys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low);
+ return ksys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low);
}
/*
@@ -164,29 +166,23 @@ COMPAT_SYSCALL_DEFINE1(x86_mmap, struct mmap_arg_struct32 __user *, arg)
if (a.offset & ~PAGE_MASK)
return -EINVAL;
- return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
+ return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
a.offset>>PAGE_SHIFT);
}
-COMPAT_SYSCALL_DEFINE3(x86_waitpid, compat_pid_t, pid, unsigned int __user *,
- stat_addr, int, options)
-{
- return compat_sys_wait4(pid, stat_addr, options, NULL);
-}
-
/* warning: next two assume little endian */
COMPAT_SYSCALL_DEFINE5(x86_pread, unsigned int, fd, char __user *, ubuf,
u32, count, u32, poslo, u32, poshi)
{
- return sys_pread64(fd, ubuf, count,
- ((loff_t)AA(poshi) << 32) | AA(poslo));
+ return ksys_pread64(fd, ubuf, count,
+ ((loff_t)AA(poshi) << 32) | AA(poslo));
}
COMPAT_SYSCALL_DEFINE5(x86_pwrite, unsigned int, fd, const char __user *, ubuf,
u32, count, u32, poslo, u32, poshi)
{
- return sys_pwrite64(fd, ubuf, count,
- ((loff_t)AA(poshi) << 32) | AA(poslo));
+ return ksys_pwrite64(fd, ubuf, count,
+ ((loff_t)AA(poshi) << 32) | AA(poslo));
}
@@ -198,40 +194,40 @@ COMPAT_SYSCALL_DEFINE6(x86_fadvise64_64, int, fd, __u32, offset_low,
__u32, offset_high, __u32, len_low, __u32, len_high,
int, advice)
{
- return sys_fadvise64_64(fd,
- (((u64)offset_high)<<32) | offset_low,
- (((u64)len_high)<<32) | len_low,
- advice);
+ return ksys_fadvise64_64(fd,
+ (((u64)offset_high)<<32) | offset_low,
+ (((u64)len_high)<<32) | len_low,
+ advice);
}
COMPAT_SYSCALL_DEFINE4(x86_readahead, int, fd, unsigned int, off_lo,
unsigned int, off_hi, size_t, count)
{
- return sys_readahead(fd, ((u64)off_hi << 32) | off_lo, count);
+ return ksys_readahead(fd, ((u64)off_hi << 32) | off_lo, count);
}
COMPAT_SYSCALL_DEFINE6(x86_sync_file_range, int, fd, unsigned int, off_low,
unsigned int, off_hi, unsigned int, n_low,
unsigned int, n_hi, int, flags)
{
- return sys_sync_file_range(fd,
- ((u64)off_hi << 32) | off_low,
- ((u64)n_hi << 32) | n_low, flags);
+ return ksys_sync_file_range(fd,
+ ((u64)off_hi << 32) | off_low,
+ ((u64)n_hi << 32) | n_low, flags);
}
COMPAT_SYSCALL_DEFINE5(x86_fadvise64, int, fd, unsigned int, offset_lo,
unsigned int, offset_hi, size_t, len, int, advice)
{
- return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo,
- len, advice);
+ return ksys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo,
+ len, advice);
}
COMPAT_SYSCALL_DEFINE6(x86_fallocate, int, fd, int, mode,
unsigned int, offset_lo, unsigned int, offset_hi,
unsigned int, len_lo, unsigned int, len_hi)
{
- return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo,
- ((u64)len_hi << 32) | len_lo);
+ return ksys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo,
+ ((u64)len_hi << 32) | len_lo);
}
/*
@@ -241,6 +237,6 @@ COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags,
unsigned long, newsp, int __user *, parent_tidptr,
unsigned long, tls_val, int __user *, child_tidptr)
{
- return sys_clone(clone_flags, newsp, parent_tidptr, child_tidptr,
+ return _do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr,
tls_val);
}
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 11881726ed37..a303d7b7d763 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -31,6 +31,7 @@
#include <asm/mmu.h>
#include <asm/mpspec.h>
#include <asm/realmode.h>
+#include <asm/x86_init.h>
#ifdef CONFIG_ACPI_APEI
# include <asm/pgtable_types.h>
@@ -133,6 +134,14 @@ static inline bool acpi_has_cpu_in_madt(void)
return !!acpi_lapic;
}
+#define ACPI_HAVE_ARCH_GET_ROOT_POINTER
+static inline u64 acpi_arch_get_root_pointer(void)
+{
+ return x86_init.acpi.get_root_pointer();
+}
+
+void acpi_generic_reduced_hw_init(void);
+
#else /* !CONFIG_ACPI */
#define acpi_lapic 0
@@ -142,6 +151,8 @@ static inline void acpi_noirq_set(void) { }
static inline void acpi_disable_pci(void) { }
static inline void disable_acpi(void) { }
+static inline void acpi_generic_reduced_hw_init(void) { }
+
#endif /* !CONFIG_ACPI */
#define ARCH_HAS_POWER_INIT 1
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index cf5961ca8677..4cd6a3b71824 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -218,13 +218,11 @@ static inline int alternatives_text_reserved(void *start, void *end)
*/
#define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \
output, input...) \
-{ \
asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\
"call %P[new2]", feature2) \
: output, ASM_CALL_CONSTRAINT \
: [old] "i" (oldfunc), [new1] "i" (newfunc1), \
- [new2] "i" (newfunc2), ## input); \
-}
+ [new2] "i" (newfunc2), ## input)
/*
* use this macro(s) if you need more than one output parameter
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 98722773391d..40a3d3642f3a 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -138,7 +138,6 @@ extern void lapic_shutdown(void);
extern void sync_Arb_IDs(void);
extern void init_bsp_APIC(void);
extern void apic_intr_mode_init(void);
-extern void setup_local_APIC(void);
extern void init_apic_mappings(void);
void register_lapic_address(unsigned long address);
extern void setup_boot_APIC_clock(void);
@@ -183,6 +182,7 @@ static inline void disable_local_APIC(void) { }
# define setup_boot_APIC_clock x86_init_noop
# define setup_secondary_APIC_clock x86_init_noop
static inline void lapic_update_tsc_freq(void) { }
+static inline void init_bsp_APIC(void) { }
static inline void apic_intr_mode_init(void) { }
static inline void lapic_assign_system_vectors(void) { }
static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { }
@@ -304,12 +304,6 @@ struct apic {
u32 irq_delivery_mode;
u32 irq_dest_mode;
- /* Functions and data related to vector allocation */
- void (*vector_allocation_domain)(int cpu, struct cpumask *retmask,
- const struct cpumask *mask);
- int (*cpu_mask_to_apicid)(const struct cpumask *cpumask,
- struct irq_data *irqdata,
- unsigned int *apicid);
u32 (*calc_dest_apicid)(unsigned int cpu);
/* ICR related functions */
@@ -499,17 +493,7 @@ extern void default_setup_apic_routing(void);
extern u32 apic_default_calc_apicid(unsigned int cpu);
extern u32 apic_flat_calc_apicid(unsigned int cpu);
-extern int flat_cpu_mask_to_apicid(const struct cpumask *cpumask,
- struct irq_data *irqdata,
- unsigned int *apicid);
-extern int default_cpu_mask_to_apicid(const struct cpumask *cpumask,
- struct irq_data *irqdata,
- unsigned int *apicid);
extern bool default_check_apicid_used(physid_mask_t *map, int apicid);
-extern void flat_vector_allocation_domain(int cpu, struct cpumask *retmask,
- const struct cpumask *mask);
-extern void default_vector_allocation_domain(int cpu, struct cpumask *retmask,
- const struct cpumask *mask);
extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap);
extern int default_cpu_present_to_apicid(int mps_cpu);
extern int default_check_phys_apicid_present(int phys_apicid);
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 72759f131cc5..0db6bec95489 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -17,36 +17,40 @@
#define ATOMIC_INIT(i) { (i) }
/**
- * atomic_read - read atomic variable
+ * arch_atomic_read - read atomic variable
* @v: pointer of type atomic_t
*
* Atomically reads the value of @v.
*/
-static __always_inline int atomic_read(const atomic_t *v)
+static __always_inline int arch_atomic_read(const atomic_t *v)
{
+ /*
+ * Note for KASAN: we deliberately don't use READ_ONCE_NOCHECK() here,
+ * it's non-inlined function that increases binary size and stack usage.
+ */
return READ_ONCE((v)->counter);
}
/**
- * atomic_set - set atomic variable
+ * arch_atomic_set - set atomic variable
* @v: pointer of type atomic_t
* @i: required value
*
* Atomically sets the value of @v to @i.
*/
-static __always_inline void atomic_set(atomic_t *v, int i)
+static __always_inline void arch_atomic_set(atomic_t *v, int i)
{
WRITE_ONCE(v->counter, i);
}
/**
- * atomic_add - add integer to atomic variable
+ * arch_atomic_add - add integer to atomic variable
* @i: integer value to add
* @v: pointer of type atomic_t
*
* Atomically adds @i to @v.
*/
-static __always_inline void atomic_add(int i, atomic_t *v)
+static __always_inline void arch_atomic_add(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "addl %1,%0"
: "+m" (v->counter)
@@ -54,13 +58,13 @@ static __always_inline void atomic_add(int i, atomic_t *v)
}
/**
- * atomic_sub - subtract integer from atomic variable
+ * arch_atomic_sub - subtract integer from atomic variable
* @i: integer value to subtract
* @v: pointer of type atomic_t
*
* Atomically subtracts @i from @v.
*/
-static __always_inline void atomic_sub(int i, atomic_t *v)
+static __always_inline void arch_atomic_sub(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "subl %1,%0"
: "+m" (v->counter)
@@ -68,7 +72,7 @@ static __always_inline void atomic_sub(int i, atomic_t *v)
}
/**
- * atomic_sub_and_test - subtract value from variable and test result
+ * arch_atomic_sub_and_test - subtract value from variable and test result
* @i: integer value to subtract
* @v: pointer of type atomic_t
*
@@ -76,63 +80,63 @@ static __always_inline void atomic_sub(int i, atomic_t *v)
* true if the result is zero, or false for all
* other cases.
*/
-static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
+static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
}
/**
- * atomic_inc - increment atomic variable
+ * arch_atomic_inc - increment atomic variable
* @v: pointer of type atomic_t
*
* Atomically increments @v by 1.
*/
-static __always_inline void atomic_inc(atomic_t *v)
+static __always_inline void arch_atomic_inc(atomic_t *v)
{
asm volatile(LOCK_PREFIX "incl %0"
: "+m" (v->counter));
}
/**
- * atomic_dec - decrement atomic variable
+ * arch_atomic_dec - decrement atomic variable
* @v: pointer of type atomic_t
*
* Atomically decrements @v by 1.
*/
-static __always_inline void atomic_dec(atomic_t *v)
+static __always_inline void arch_atomic_dec(atomic_t *v)
{
asm volatile(LOCK_PREFIX "decl %0"
: "+m" (v->counter));
}
/**
- * atomic_dec_and_test - decrement and test
+ * arch_atomic_dec_and_test - decrement and test
* @v: pointer of type atomic_t
*
* Atomically decrements @v by 1 and
* returns true if the result is 0, or false for all other
* cases.
*/
-static __always_inline bool atomic_dec_and_test(atomic_t *v)
+static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
}
/**
- * atomic_inc_and_test - increment and test
+ * arch_atomic_inc_and_test - increment and test
* @v: pointer of type atomic_t
*
* Atomically increments @v by 1
* and returns true if the result is zero, or false for all
* other cases.
*/
-static __always_inline bool atomic_inc_and_test(atomic_t *v)
+static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
}
/**
- * atomic_add_negative - add and test if negative
+ * arch_atomic_add_negative - add and test if negative
* @i: integer value to add
* @v: pointer of type atomic_t
*
@@ -140,65 +144,65 @@ static __always_inline bool atomic_inc_and_test(atomic_t *v)
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
-static __always_inline bool atomic_add_negative(int i, atomic_t *v)
+static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
}
/**
- * atomic_add_return - add integer and return
+ * arch_atomic_add_return - add integer and return
* @i: integer value to add
* @v: pointer of type atomic_t
*
* Atomically adds @i to @v and returns @i + @v
*/
-static __always_inline int atomic_add_return(int i, atomic_t *v)
+static __always_inline int arch_atomic_add_return(int i, atomic_t *v)
{
return i + xadd(&v->counter, i);
}
/**
- * atomic_sub_return - subtract integer and return
+ * arch_atomic_sub_return - subtract integer and return
* @v: pointer of type atomic_t
* @i: integer value to subtract
*
* Atomically subtracts @i from @v and returns @v - @i
*/
-static __always_inline int atomic_sub_return(int i, atomic_t *v)
+static __always_inline int arch_atomic_sub_return(int i, atomic_t *v)
{
- return atomic_add_return(-i, v);
+ return arch_atomic_add_return(-i, v);
}
-#define atomic_inc_return(v) (atomic_add_return(1, v))
-#define atomic_dec_return(v) (atomic_sub_return(1, v))
+#define arch_atomic_inc_return(v) (arch_atomic_add_return(1, v))
+#define arch_atomic_dec_return(v) (arch_atomic_sub_return(1, v))
-static __always_inline int atomic_fetch_add(int i, atomic_t *v)
+static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
{
return xadd(&v->counter, i);
}
-static __always_inline int atomic_fetch_sub(int i, atomic_t *v)
+static __always_inline int arch_atomic_fetch_sub(int i, atomic_t *v)
{
return xadd(&v->counter, -i);
}
-static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
{
- return cmpxchg(&v->counter, old, new);
+ return arch_cmpxchg(&v->counter, old, new);
}
-#define atomic_try_cmpxchg atomic_try_cmpxchg
-static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new)
+#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg
+static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new)
{
return try_cmpxchg(&v->counter, old, new);
}
-static inline int atomic_xchg(atomic_t *v, int new)
+static inline int arch_atomic_xchg(atomic_t *v, int new)
{
return xchg(&v->counter, new);
}
-static inline void atomic_and(int i, atomic_t *v)
+static inline void arch_atomic_and(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "andl %1,%0"
: "+m" (v->counter)
@@ -206,16 +210,16 @@ static inline void atomic_and(int i, atomic_t *v)
: "memory");
}
-static inline int atomic_fetch_and(int i, atomic_t *v)
+static inline int arch_atomic_fetch_and(int i, atomic_t *v)
{
- int val = atomic_read(v);
+ int val = arch_atomic_read(v);
- do { } while (!atomic_try_cmpxchg(v, &val, val & i));
+ do { } while (!arch_atomic_try_cmpxchg(v, &val, val & i));
return val;
}
-static inline void atomic_or(int i, atomic_t *v)
+static inline void arch_atomic_or(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "orl %1,%0"
: "+m" (v->counter)
@@ -223,16 +227,16 @@ static inline void atomic_or(int i, atomic_t *v)
: "memory");
}
-static inline int atomic_fetch_or(int i, atomic_t *v)
+static inline int arch_atomic_fetch_or(int i, atomic_t *v)
{
- int val = atomic_read(v);
+ int val = arch_atomic_read(v);
- do { } while (!atomic_try_cmpxchg(v, &val, val | i));
+ do { } while (!arch_atomic_try_cmpxchg(v, &val, val | i));
return val;
}
-static inline void atomic_xor(int i, atomic_t *v)
+static inline void arch_atomic_xor(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "xorl %1,%0"
: "+m" (v->counter)
@@ -240,17 +244,17 @@ static inline void atomic_xor(int i, atomic_t *v)
: "memory");
}
-static inline int atomic_fetch_xor(int i, atomic_t *v)
+static inline int arch_atomic_fetch_xor(int i, atomic_t *v)
{
- int val = atomic_read(v);
+ int val = arch_atomic_read(v);
- do { } while (!atomic_try_cmpxchg(v, &val, val ^ i));
+ do { } while (!arch_atomic_try_cmpxchg(v, &val, val ^ i));
return val;
}
/**
- * __atomic_add_unless - add unless the number is already a given value
+ * __arch_atomic_add_unless - add unless the number is already a given value
* @v: pointer of type atomic_t
* @a: the amount to add to v...
* @u: ...unless v is equal to u.
@@ -258,14 +262,14 @@ static inline int atomic_fetch_xor(int i, atomic_t *v)
* Atomically adds @a to @v, so long as @v was not already @u.
* Returns the old value of @v.
*/
-static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int __arch_atomic_add_unless(atomic_t *v, int a, int u)
{
- int c = atomic_read(v);
+ int c = arch_atomic_read(v);
do {
if (unlikely(c == u))
break;
- } while (!atomic_try_cmpxchg(v, &c, c + a));
+ } while (!arch_atomic_try_cmpxchg(v, &c, c + a));
return c;
}
@@ -276,4 +280,6 @@ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
# include <asm/atomic64_64.h>
#endif
+#include <asm-generic/atomic-instrumented.h>
+
#endif /* _ASM_X86_ATOMIC_H */
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 97c46b8169b7..46e1ef17d92d 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -62,7 +62,7 @@ ATOMIC64_DECL(add_unless);
#undef ATOMIC64_EXPORT
/**
- * atomic64_cmpxchg - cmpxchg atomic64 variable
+ * arch_atomic64_cmpxchg - cmpxchg atomic64 variable
* @v: pointer to type atomic64_t
* @o: expected value
* @n: new value
@@ -71,20 +71,21 @@ ATOMIC64_DECL(add_unless);
* the old value.
*/
-static inline long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n)
+static inline long long arch_atomic64_cmpxchg(atomic64_t *v, long long o,
+ long long n)
{
- return cmpxchg64(&v->counter, o, n);
+ return arch_cmpxchg64(&v->counter, o, n);
}
/**
- * atomic64_xchg - xchg atomic64 variable
+ * arch_atomic64_xchg - xchg atomic64 variable
* @v: pointer to type atomic64_t
* @n: value to assign
*
* Atomically xchgs the value of @v to @n and returns
* the old value.
*/
-static inline long long atomic64_xchg(atomic64_t *v, long long n)
+static inline long long arch_atomic64_xchg(atomic64_t *v, long long n)
{
long long o;
unsigned high = (unsigned)(n >> 32);
@@ -96,13 +97,13 @@ static inline long long atomic64_xchg(atomic64_t *v, long long n)
}
/**
- * atomic64_set - set atomic64 variable
+ * arch_atomic64_set - set atomic64 variable
* @v: pointer to type atomic64_t
* @i: value to assign
*
* Atomically sets the value of @v to @n.
*/
-static inline void atomic64_set(atomic64_t *v, long long i)
+static inline void arch_atomic64_set(atomic64_t *v, long long i)
{
unsigned high = (unsigned)(i >> 32);
unsigned low = (unsigned)i;
@@ -112,12 +113,12 @@ static inline void atomic64_set(atomic64_t *v, long long i)
}
/**
- * atomic64_read - read atomic64 variable
+ * arch_atomic64_read - read atomic64 variable
* @v: pointer to type atomic64_t
*
* Atomically reads the value of @v and returns it.
*/
-static inline long long atomic64_read(const atomic64_t *v)
+static inline long long arch_atomic64_read(const atomic64_t *v)
{
long long r;
alternative_atomic64(read, "=&A" (r), "c" (v) : "memory");
@@ -125,13 +126,13 @@ static inline long long atomic64_read(const atomic64_t *v)
}
/**
- * atomic64_add_return - add and return
+ * arch_atomic64_add_return - add and return
* @i: integer value to add
* @v: pointer to type atomic64_t
*
* Atomically adds @i to @v and returns @i + *@v
*/
-static inline long long atomic64_add_return(long long i, atomic64_t *v)
+static inline long long arch_atomic64_add_return(long long i, atomic64_t *v)
{
alternative_atomic64(add_return,
ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -142,7 +143,7 @@ static inline long long atomic64_add_return(long long i, atomic64_t *v)
/*
* Other variants with different arithmetic operators:
*/
-static inline long long atomic64_sub_return(long long i, atomic64_t *v)
+static inline long long arch_atomic64_sub_return(long long i, atomic64_t *v)
{
alternative_atomic64(sub_return,
ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -150,7 +151,7 @@ static inline long long atomic64_sub_return(long long i, atomic64_t *v)
return i;
}
-static inline long long atomic64_inc_return(atomic64_t *v)
+static inline long long arch_atomic64_inc_return(atomic64_t *v)
{
long long a;
alternative_atomic64(inc_return, "=&A" (a),
@@ -158,7 +159,7 @@ static inline long long atomic64_inc_return(atomic64_t *v)
return a;
}
-static inline long long atomic64_dec_return(atomic64_t *v)
+static inline long long arch_atomic64_dec_return(atomic64_t *v)
{
long long a;
alternative_atomic64(dec_return, "=&A" (a),
@@ -167,13 +168,13 @@ static inline long long atomic64_dec_return(atomic64_t *v)
}
/**
- * atomic64_add - add integer to atomic64 variable
+ * arch_atomic64_add - add integer to atomic64 variable
* @i: integer value to add
* @v: pointer to type atomic64_t
*
* Atomically adds @i to @v.
*/
-static inline long long atomic64_add(long long i, atomic64_t *v)
+static inline long long arch_atomic64_add(long long i, atomic64_t *v)
{
__alternative_atomic64(add, add_return,
ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -182,13 +183,13 @@ static inline long long atomic64_add(long long i, atomic64_t *v)
}
/**
- * atomic64_sub - subtract the atomic64 variable
+ * arch_atomic64_sub - subtract the atomic64 variable
* @i: integer value to subtract
* @v: pointer to type atomic64_t
*
* Atomically subtracts @i from @v.
*/
-static inline long long atomic64_sub(long long i, atomic64_t *v)
+static inline long long arch_atomic64_sub(long long i, atomic64_t *v)
{
__alternative_atomic64(sub, sub_return,
ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -197,7 +198,7 @@ static inline long long atomic64_sub(long long i, atomic64_t *v)
}
/**
- * atomic64_sub_and_test - subtract value from variable and test result
+ * arch_atomic64_sub_and_test - subtract value from variable and test result
* @i: integer value to subtract
* @v: pointer to type atomic64_t
*
@@ -205,46 +206,46 @@ static inline long long atomic64_sub(long long i, atomic64_t *v)
* true if the result is zero, or false for all
* other cases.
*/
-static inline int atomic64_sub_and_test(long long i, atomic64_t *v)
+static inline int arch_atomic64_sub_and_test(long long i, atomic64_t *v)
{
- return atomic64_sub_return(i, v) == 0;
+ return arch_atomic64_sub_return(i, v) == 0;
}
/**
- * atomic64_inc - increment atomic64 variable
+ * arch_atomic64_inc - increment atomic64 variable
* @v: pointer to type atomic64_t
*
* Atomically increments @v by 1.
*/
-static inline void atomic64_inc(atomic64_t *v)
+static inline void arch_atomic64_inc(atomic64_t *v)
{
__alternative_atomic64(inc, inc_return, /* no output */,
"S" (v) : "memory", "eax", "ecx", "edx");
}
/**
- * atomic64_dec - decrement atomic64 variable
+ * arch_atomic64_dec - decrement atomic64 variable
* @v: pointer to type atomic64_t
*
* Atomically decrements @v by 1.
*/
-static inline void atomic64_dec(atomic64_t *v)
+static inline void arch_atomic64_dec(atomic64_t *v)
{
__alternative_atomic64(dec, dec_return, /* no output */,
"S" (v) : "memory", "eax", "ecx", "edx");
}
/**
- * atomic64_dec_and_test - decrement and test
+ * arch_atomic64_dec_and_test - decrement and test
* @v: pointer to type atomic64_t
*
* Atomically decrements @v by 1 and
* returns true if the result is 0, or false for all other
* cases.
*/
-static inline int atomic64_dec_and_test(atomic64_t *v)
+static inline int arch_atomic64_dec_and_test(atomic64_t *v)
{
- return atomic64_dec_return(v) == 0;
+ return arch_atomic64_dec_return(v) == 0;
}
/**
@@ -255,13 +256,13 @@ static inline int atomic64_dec_and_test(atomic64_t *v)
* and returns true if the result is zero, or false for all
* other cases.
*/
-static inline int atomic64_inc_and_test(atomic64_t *v)
+static inline int arch_atomic64_inc_and_test(atomic64_t *v)
{
- return atomic64_inc_return(v) == 0;
+ return arch_atomic64_inc_return(v) == 0;
}
/**
- * atomic64_add_negative - add and test if negative
+ * arch_atomic64_add_negative - add and test if negative
* @i: integer value to add
* @v: pointer to type atomic64_t
*
@@ -269,13 +270,13 @@ static inline int atomic64_inc_and_test(atomic64_t *v)
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
-static inline int atomic64_add_negative(long long i, atomic64_t *v)
+static inline int arch_atomic64_add_negative(long long i, atomic64_t *v)
{
- return atomic64_add_return(i, v) < 0;
+ return arch_atomic64_add_return(i, v) < 0;
}
/**
- * atomic64_add_unless - add unless the number is a given value
+ * arch_atomic64_add_unless - add unless the number is a given value
* @v: pointer of type atomic64_t
* @a: the amount to add to v...
* @u: ...unless v is equal to u.
@@ -283,7 +284,8 @@ static inline int atomic64_add_negative(long long i, atomic64_t *v)
* Atomically adds @a to @v, so long as it was not @u.
* Returns non-zero if the add was done, zero otherwise.
*/
-static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+static inline int arch_atomic64_add_unless(atomic64_t *v, long long a,
+ long long u)
{
unsigned low = (unsigned)u;
unsigned high = (unsigned)(u >> 32);
@@ -294,7 +296,7 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
}
-static inline int atomic64_inc_not_zero(atomic64_t *v)
+static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
{
int r;
alternative_atomic64(inc_not_zero, "=&a" (r),
@@ -302,7 +304,7 @@ static inline int atomic64_inc_not_zero(atomic64_t *v)
return r;
}
-static inline long long atomic64_dec_if_positive(atomic64_t *v)
+static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
{
long long r;
alternative_atomic64(dec_if_positive, "=&A" (r),
@@ -313,70 +315,70 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
#undef alternative_atomic64
#undef __alternative_atomic64
-static inline void atomic64_and(long long i, atomic64_t *v)
+static inline void arch_atomic64_and(long long i, atomic64_t *v)
{
long long old, c = 0;
- while ((old = atomic64_cmpxchg(v, c, c & i)) != c)
+ while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
c = old;
}
-static inline long long atomic64_fetch_and(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_and(long long i, atomic64_t *v)
{
long long old, c = 0;
- while ((old = atomic64_cmpxchg(v, c, c & i)) != c)
+ while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
c = old;
return old;
}
-static inline void atomic64_or(long long i, atomic64_t *v)
+static inline void arch_atomic64_or(long long i, atomic64_t *v)
{
long long old, c = 0;
- while ((old = atomic64_cmpxchg(v, c, c | i)) != c)
+ while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
c = old;
}
-static inline long long atomic64_fetch_or(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_or(long long i, atomic64_t *v)
{
long long old, c = 0;
- while ((old = atomic64_cmpxchg(v, c, c | i)) != c)
+ while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
c = old;
return old;
}
-static inline void atomic64_xor(long long i, atomic64_t *v)
+static inline void arch_atomic64_xor(long long i, atomic64_t *v)
{
long long old, c = 0;
- while ((old = atomic64_cmpxchg(v, c, c ^ i)) != c)
+ while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
c = old;
}
-static inline long long atomic64_fetch_xor(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_xor(long long i, atomic64_t *v)
{
long long old, c = 0;
- while ((old = atomic64_cmpxchg(v, c, c ^ i)) != c)
+ while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
c = old;
return old;
}
-static inline long long atomic64_fetch_add(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_add(long long i, atomic64_t *v)
{
long long old, c = 0;
- while ((old = atomic64_cmpxchg(v, c, c + i)) != c)
+ while ((old = arch_atomic64_cmpxchg(v, c, c + i)) != c)
c = old;
return old;
}
-#define atomic64_fetch_sub(i, v) atomic64_fetch_add(-(i), (v))
+#define arch_atomic64_fetch_sub(i, v) arch_atomic64_fetch_add(-(i), (v))
#endif /* _ASM_X86_ATOMIC64_32_H */
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 738495caf05f..6106b59d3260 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -11,37 +11,37 @@
#define ATOMIC64_INIT(i) { (i) }
/**
- * atomic64_read - read atomic64 variable
+ * arch_atomic64_read - read atomic64 variable
* @v: pointer of type atomic64_t
*
* Atomically reads the value of @v.
* Doesn't imply a read memory barrier.
*/
-static inline long atomic64_read(const atomic64_t *v)
+static inline long arch_atomic64_read(const atomic64_t *v)
{
return READ_ONCE((v)->counter);
}
/**
- * atomic64_set - set atomic64 variable
+ * arch_atomic64_set - set atomic64 variable
* @v: pointer to type atomic64_t
* @i: required value
*
* Atomically sets the value of @v to @i.
*/
-static inline void atomic64_set(atomic64_t *v, long i)
+static inline void arch_atomic64_set(atomic64_t *v, long i)
{
WRITE_ONCE(v->counter, i);
}
/**
- * atomic64_add - add integer to atomic64 variable
+ * arch_atomic64_add - add integer to atomic64 variable
* @i: integer value to add
* @v: pointer to type atomic64_t
*
* Atomically adds @i to @v.
*/
-static __always_inline void atomic64_add(long i, atomic64_t *v)
+static __always_inline void arch_atomic64_add(long i, atomic64_t *v)
{
asm volatile(LOCK_PREFIX "addq %1,%0"
: "=m" (v->counter)
@@ -49,13 +49,13 @@ static __always_inline void atomic64_add(long i, atomic64_t *v)
}
/**
- * atomic64_sub - subtract the atomic64 variable
+ * arch_atomic64_sub - subtract the atomic64 variable
* @i: integer value to subtract
* @v: pointer to type atomic64_t
*
* Atomically subtracts @i from @v.
*/
-static inline void atomic64_sub(long i, atomic64_t *v)
+static inline void arch_atomic64_sub(long i, atomic64_t *v)
{
asm volatile(LOCK_PREFIX "subq %1,%0"
: "=m" (v->counter)
@@ -63,7 +63,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
}
/**
- * atomic64_sub_and_test - subtract value from variable and test result
+ * arch_atomic64_sub_and_test - subtract value from variable and test result
* @i: integer value to subtract
* @v: pointer to type atomic64_t
*
@@ -71,18 +71,18 @@ static inline void atomic64_sub(long i, atomic64_t *v)
* true if the result is zero, or false for all
* other cases.
*/
-static inline bool atomic64_sub_and_test(long i, atomic64_t *v)
+static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
}
/**
- * atomic64_inc - increment atomic64 variable
+ * arch_atomic64_inc - increment atomic64 variable
* @v: pointer to type atomic64_t
*
* Atomically increments @v by 1.
*/
-static __always_inline void atomic64_inc(atomic64_t *v)
+static __always_inline void arch_atomic64_inc(atomic64_t *v)
{
asm volatile(LOCK_PREFIX "incq %0"
: "=m" (v->counter)
@@ -90,12 +90,12 @@ static __always_inline void atomic64_inc(atomic64_t *v)
}
/**
- * atomic64_dec - decrement atomic64 variable
+ * arch_atomic64_dec - decrement atomic64 variable
* @v: pointer to type atomic64_t
*
* Atomically decrements @v by 1.
*/
-static __always_inline void atomic64_dec(atomic64_t *v)
+static __always_inline void arch_atomic64_dec(atomic64_t *v)
{
asm volatile(LOCK_PREFIX "decq %0"
: "=m" (v->counter)
@@ -103,33 +103,33 @@ static __always_inline void atomic64_dec(atomic64_t *v)
}
/**
- * atomic64_dec_and_test - decrement and test
+ * arch_atomic64_dec_and_test - decrement and test
* @v: pointer to type atomic64_t
*
* Atomically decrements @v by 1 and
* returns true if the result is 0, or false for all other
* cases.
*/
-static inline bool atomic64_dec_and_test(atomic64_t *v)
+static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
}
/**
- * atomic64_inc_and_test - increment and test
+ * arch_atomic64_inc_and_test - increment and test
* @v: pointer to type atomic64_t
*
* Atomically increments @v by 1
* and returns true if the result is zero, or false for all
* other cases.
*/
-static inline bool atomic64_inc_and_test(atomic64_t *v)
+static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
}
/**
- * atomic64_add_negative - add and test if negative
+ * arch_atomic64_add_negative - add and test if negative
* @i: integer value to add
* @v: pointer to type atomic64_t
*
@@ -137,59 +137,59 @@ static inline bool atomic64_inc_and_test(atomic64_t *v)
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
-static inline bool atomic64_add_negative(long i, atomic64_t *v)
+static inline bool arch_atomic64_add_negative(long i, atomic64_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
}
/**
- * atomic64_add_return - add and return
+ * arch_atomic64_add_return - add and return
* @i: integer value to add
* @v: pointer to type atomic64_t
*
* Atomically adds @i to @v and returns @i + @v
*/
-static __always_inline long atomic64_add_return(long i, atomic64_t *v)
+static __always_inline long arch_atomic64_add_return(long i, atomic64_t *v)
{
return i + xadd(&v->counter, i);
}
-static inline long atomic64_sub_return(long i, atomic64_t *v)
+static inline long arch_atomic64_sub_return(long i, atomic64_t *v)
{
- return atomic64_add_return(-i, v);
+ return arch_atomic64_add_return(-i, v);
}
-static inline long atomic64_fetch_add(long i, atomic64_t *v)
+static inline long arch_atomic64_fetch_add(long i, atomic64_t *v)
{
return xadd(&v->counter, i);
}
-static inline long atomic64_fetch_sub(long i, atomic64_t *v)
+static inline long arch_atomic64_fetch_sub(long i, atomic64_t *v)
{
return xadd(&v->counter, -i);
}
-#define atomic64_inc_return(v) (atomic64_add_return(1, (v)))
-#define atomic64_dec_return(v) (atomic64_sub_return(1, (v)))
+#define arch_atomic64_inc_return(v) (arch_atomic64_add_return(1, (v)))
+#define arch_atomic64_dec_return(v) (arch_atomic64_sub_return(1, (v)))
-static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
+static inline long arch_atomic64_cmpxchg(atomic64_t *v, long old, long new)
{
- return cmpxchg(&v->counter, old, new);
+ return arch_cmpxchg(&v->counter, old, new);
}
-#define atomic64_try_cmpxchg atomic64_try_cmpxchg
-static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, long new)
+#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
+static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, long new)
{
return try_cmpxchg(&v->counter, old, new);
}
-static inline long atomic64_xchg(atomic64_t *v, long new)
+static inline long arch_atomic64_xchg(atomic64_t *v, long new)
{
return xchg(&v->counter, new);
}
/**
- * atomic64_add_unless - add unless the number is a given value
+ * arch_atomic64_add_unless - add unless the number is a given value
* @v: pointer of type atomic64_t
* @a: the amount to add to v...
* @u: ...unless v is equal to u.
@@ -197,37 +197,37 @@ static inline long atomic64_xchg(atomic64_t *v, long new)
* Atomically adds @a to @v, so long as it was not @u.
* Returns the old value of @v.
*/
-static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
+static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u)
{
- s64 c = atomic64_read(v);
+ s64 c = arch_atomic64_read(v);
do {
if (unlikely(c == u))
return false;
- } while (!atomic64_try_cmpxchg(v, &c, c + a));
+ } while (!arch_atomic64_try_cmpxchg(v, &c, c + a));
return true;
}
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
+#define arch_atomic64_inc_not_zero(v) arch_atomic64_add_unless((v), 1, 0)
/*
- * atomic64_dec_if_positive - decrement by 1 if old value positive
+ * arch_atomic64_dec_if_positive - decrement by 1 if old value positive
* @v: pointer of type atomic_t
*
* The function returns the old value of *v minus 1, even if
* the atomic variable, v, was not decremented.
*/
-static inline long atomic64_dec_if_positive(atomic64_t *v)
+static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
{
- s64 dec, c = atomic64_read(v);
+ s64 dec, c = arch_atomic64_read(v);
do {
dec = c - 1;
if (unlikely(dec < 0))
break;
- } while (!atomic64_try_cmpxchg(v, &c, dec));
+ } while (!arch_atomic64_try_cmpxchg(v, &c, dec));
return dec;
}
-static inline void atomic64_and(long i, atomic64_t *v)
+static inline void arch_atomic64_and(long i, atomic64_t *v)
{
asm volatile(LOCK_PREFIX "andq %1,%0"
: "+m" (v->counter)
@@ -235,16 +235,16 @@ static inline void atomic64_and(long i, atomic64_t *v)
: "memory");
}
-static inline long atomic64_fetch_and(long i, atomic64_t *v)
+static inline long arch_atomic64_fetch_and(long i, atomic64_t *v)
{
- s64 val = atomic64_read(v);
+ s64 val = arch_atomic64_read(v);
do {
- } while (!atomic64_try_cmpxchg(v, &val, val & i));
+ } while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
return val;
}
-static inline void atomic64_or(long i, atomic64_t *v)
+static inline void arch_atomic64_or(long i, atomic64_t *v)
{
asm volatile(LOCK_PREFIX "orq %1,%0"
: "+m" (v->counter)
@@ -252,16 +252,16 @@ static inline void atomic64_or(long i, atomic64_t *v)
: "memory");
}
-static inline long atomic64_fetch_or(long i, atomic64_t *v)
+static inline long arch_atomic64_fetch_or(long i, atomic64_t *v)
{
- s64 val = atomic64_read(v);
+ s64 val = arch_atomic64_read(v);
do {
- } while (!atomic64_try_cmpxchg(v, &val, val | i));
+ } while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
return val;
}
-static inline void atomic64_xor(long i, atomic64_t *v)
+static inline void arch_atomic64_xor(long i, atomic64_t *v)
{
asm volatile(LOCK_PREFIX "xorq %1,%0"
: "+m" (v->counter)
@@ -269,12 +269,12 @@ static inline void atomic64_xor(long i, atomic64_t *v)
: "memory");
}
-static inline long atomic64_fetch_xor(long i, atomic64_t *v)
+static inline long arch_atomic64_fetch_xor(long i, atomic64_t *v)
{
- s64 val = atomic64_read(v);
+ s64 val = arch_atomic64_read(v);
do {
- } while (!atomic64_try_cmpxchg(v, &val, val ^ i));
+ } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
return val;
}
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index e1259f043ae9..042b5e892ed1 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -52,11 +52,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
#define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \
"lfence", X86_FEATURE_LFENCE_RDTSC)
-#ifdef CONFIG_X86_PPRO_FENCE
-#define dma_rmb() rmb()
-#else
#define dma_rmb() barrier()
-#endif
#define dma_wmb() barrier()
#ifdef CONFIG_X86_32
@@ -68,30 +64,6 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
#define __smp_wmb() barrier()
#define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#if defined(CONFIG_X86_PPRO_FENCE)
-
-/*
- * For this option x86 doesn't have a strong TSO memory
- * model and we should fall back to full barriers.
- */
-
-#define __smp_store_release(p, v) \
-do { \
- compiletime_assert_atomic_type(*p); \
- __smp_mb(); \
- WRITE_ONCE(*p, v); \
-} while (0)
-
-#define __smp_load_acquire(p) \
-({ \
- typeof(*p) ___p1 = READ_ONCE(*p); \
- compiletime_assert_atomic_type(*p); \
- __smp_mb(); \
- ___p1; \
-})
-
-#else /* regular x86 TSO memory ordering */
-
#define __smp_store_release(p, v) \
do { \
compiletime_assert_atomic_type(*p); \
@@ -107,8 +79,6 @@ do { \
___p1; \
})
-#endif
-
/* Atomic operations are already serializing on x86 */
#define __smp_mb__before_atomic() barrier()
#define __smp_mb__after_atomic() barrier()
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 56bd436ed01b..e3efd8a06066 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -145,13 +145,13 @@ extern void __add_wrong_size(void)
# include <asm/cmpxchg_64.h>
#endif
-#define cmpxchg(ptr, old, new) \
+#define arch_cmpxchg(ptr, old, new) \
__cmpxchg(ptr, old, new, sizeof(*(ptr)))
-#define sync_cmpxchg(ptr, old, new) \
+#define arch_sync_cmpxchg(ptr, old, new) \
__sync_cmpxchg(ptr, old, new, sizeof(*(ptr)))
-#define cmpxchg_local(ptr, old, new) \
+#define arch_cmpxchg_local(ptr, old, new) \
__cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
@@ -221,7 +221,7 @@ extern void __add_wrong_size(void)
#define __try_cmpxchg(ptr, pold, new, size) \
__raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
-#define try_cmpxchg(ptr, pold, new) \
+#define try_cmpxchg(ptr, pold, new) \
__try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr)))
/*
@@ -250,10 +250,10 @@ extern void __add_wrong_size(void)
__ret; \
})
-#define cmpxchg_double(p1, p2, o1, o2, n1, n2) \
+#define arch_cmpxchg_double(p1, p2, o1, o2, n1, n2) \
__cmpxchg_double(LOCK_PREFIX, p1, p2, o1, o2, n1, n2)
-#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \
+#define arch_cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \
__cmpxchg_double(, p1, p2, o1, o2, n1, n2)
#endif /* ASM_X86_CMPXCHG_H */
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index 1732704f0445..1a2eafca7038 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -36,10 +36,10 @@ static inline void set_64bit(volatile u64 *ptr, u64 value)
}
#ifdef CONFIG_X86_CMPXCHG64
-#define cmpxchg64(ptr, o, n) \
+#define arch_cmpxchg64(ptr, o, n) \
((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
(unsigned long long)(n)))
-#define cmpxchg64_local(ptr, o, n) \
+#define arch_cmpxchg64_local(ptr, o, n) \
((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o), \
(unsigned long long)(n)))
#endif
@@ -76,7 +76,7 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
* to simulate the cmpxchg8b on the 80386 and 80486 CPU.
*/
-#define cmpxchg64(ptr, o, n) \
+#define arch_cmpxchg64(ptr, o, n) \
({ \
__typeof__(*(ptr)) __ret; \
__typeof__(*(ptr)) __old = (o); \
@@ -93,7 +93,7 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
__ret; })
-#define cmpxchg64_local(ptr, o, n) \
+#define arch_cmpxchg64_local(ptr, o, n) \
({ \
__typeof__(*(ptr)) __ret; \
__typeof__(*(ptr)) __old = (o); \
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 03cad196a301..bfca3b346c74 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -7,13 +7,13 @@ static inline void set_64bit(volatile u64 *ptr, u64 val)
*ptr = val;
}
-#define cmpxchg64(ptr, o, n) \
+#define arch_cmpxchg64(ptr, o, n) \
({ \
BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
cmpxchg((ptr), (o), (n)); \
})
-#define cmpxchg64_local(ptr, o, n) \
+#define arch_cmpxchg64_local(ptr, o, n) \
({ \
BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
cmpxchg_local((ptr), (o), (n)); \
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 736771c9822e..b27da9602a6d 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -140,7 +140,6 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
-#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
/*
* Static testing of CPU features. Used the same as boot_cpu_has().
* These will statically patch the target code for additional
@@ -196,13 +195,6 @@ t_no:
boot_cpu_has(bit) : \
_static_cpu_has(bit) \
)
-#else
-/*
- * Fall back to dynamic for gcc versions which don't support asm goto. Should be
- * a minority now anyway.
- */
-#define static_cpu_has(bit) boot_cpu_has(bit)
-#endif
#define cpu_has_bug(c, bit) cpu_has(c, (bit))
#define set_cpu_bug(c, bit) set_cpu_cap(c, (bit))
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index f41079da38c5..d554c11e01ff 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -316,6 +316,7 @@
#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* Carry-Less Multiplication Double Quadword */
#define X86_FEATURE_AVX512_VNNI (16*32+11) /* Vector Neural Network Instructions */
#define X86_FEATURE_AVX512_BITALG (16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */
+#define X86_FEATURE_TME (16*32+13) /* Intel Total Memory Encryption */
#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */
#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */
@@ -328,6 +329,7 @@
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 5e12c63b47aa..a8f6c809d9b1 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -6,6 +6,9 @@ struct dev_archdata {
#if defined(CONFIG_INTEL_IOMMU) || defined(CONFIG_AMD_IOMMU)
void *iommu; /* hook for IOMMU specific extension */
#endif
+#ifdef CONFIG_STA2X11
+ bool is_sta2x11;
+#endif
};
#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
diff --git a/arch/x86/include/asm/dma-direct.h b/arch/x86/include/asm/dma-direct.h
index 1295bc622ebe..1a19251eaac9 100644
--- a/arch/x86/include/asm/dma-direct.h
+++ b/arch/x86/include/asm/dma-direct.h
@@ -2,29 +2,8 @@
#ifndef ASM_X86_DMA_DIRECT_H
#define ASM_X86_DMA_DIRECT_H 1
-#include <linux/mem_encrypt.h>
-
-#ifdef CONFIG_X86_DMA_REMAP /* Platform code defines bridge-specific code */
bool dma_capable(struct device *dev, dma_addr_t addr, size_t size);
-dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
-phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
-#else
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
- if (!dev->dma_mask)
- return 0;
-
- return addr + size - 1 <= *dev->dma_mask;
-}
-
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
- return __sme_set(paddr);
-}
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
- return __sme_clr(daddr);
-}
-#endif /* CONFIG_X86_DMA_REMAP */
#endif /* ASM_X86_DMA_DIRECT_H */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 6277c83c0eb1..89ce4bfd241f 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -36,37 +36,4 @@ int arch_dma_supported(struct device *dev, u64 mask);
bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp);
#define arch_dma_alloc_attrs arch_dma_alloc_attrs
-extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_addr, gfp_t flag,
- unsigned long attrs);
-
-extern void dma_generic_free_coherent(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_addr,
- unsigned long attrs);
-
-static inline unsigned long dma_alloc_coherent_mask(struct device *dev,
- gfp_t gfp)
-{
- unsigned long dma_mask = 0;
-
- dma_mask = dev->coherent_dma_mask;
- if (!dma_mask)
- dma_mask = (gfp & GFP_DMA) ? DMA_BIT_MASK(24) : DMA_BIT_MASK(32);
-
- return dma_mask;
-}
-
-static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
-{
- unsigned long dma_mask = dma_alloc_coherent_mask(dev, gfp);
-
- if (dma_mask <= DMA_BIT_MASK(24))
- gfp |= GFP_DMA;
-#ifdef CONFIG_X86_64
- if (dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA))
- gfp |= GFP_DMA32;
-#endif
- return gfp;
-}
-
#endif
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index a399c1ebf6f0..cec5fae23eb3 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -7,6 +7,7 @@
#include <asm/processor-flags.h>
#include <asm/tlb.h>
#include <asm/nospec-branch.h>
+#include <asm/mmu_context.h>
/*
* We map the EFI regions needed for runtime services non-contiguously,
@@ -69,14 +70,13 @@ extern asmlinkage u64 efi_call(void *fp, ...);
#define efi_call_phys(f, args...) efi_call((f), args)
/*
- * Scratch space used for switching the pagetable in the EFI stub
+ * struct efi_scratch - Scratch space used while switching to/from efi_mm
+ * @phys_stack: stack used during EFI Mixed Mode
+ * @prev_mm: store/restore stolen mm_struct while switching to/from efi_mm
*/
struct efi_scratch {
- u64 r15;
- u64 prev_cr3;
- pgd_t *efi_pgt;
- bool use_pgd;
- u64 phys_stack;
+ u64 phys_stack;
+ struct mm_struct *prev_mm;
} __packed;
#define arch_efi_call_virt_setup() \
@@ -86,11 +86,8 @@ struct efi_scratch {
__kernel_fpu_begin(); \
firmware_restrict_branch_speculation_start(); \
\
- if (efi_scratch.use_pgd) { \
- efi_scratch.prev_cr3 = __read_cr3(); \
- write_cr3((unsigned long)efi_scratch.efi_pgt); \
- __flush_tlb_all(); \
- } \
+ if (!efi_enabled(EFI_OLD_MEMMAP)) \
+ efi_switch_mm(&efi_mm); \
})
#define arch_efi_call_virt(p, f, args...) \
@@ -98,10 +95,8 @@ struct efi_scratch {
#define arch_efi_call_virt_teardown() \
({ \
- if (efi_scratch.use_pgd) { \
- write_cr3(efi_scratch.prev_cr3); \
- __flush_tlb_all(); \
- } \
+ if (!efi_enabled(EFI_OLD_MEMMAP)) \
+ efi_switch_mm(efi_scratch.prev_mm); \
\
firmware_restrict_branch_speculation_end(); \
__kernel_fpu_end(); \
@@ -144,6 +139,7 @@ extern void __init efi_dump_pagetable(void);
extern void __init efi_apply_memmap_quirks(void);
extern int __init efi_reuse_config(u64 tables, int nr_tables);
extern void efi_delete_dummy_variable(void);
+extern void efi_switch_mm(struct mm_struct *mm);
struct efi_setup_data {
u64 fw_vendor;
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 2851077b6051..32e666e1231e 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -36,6 +36,7 @@ extern asmlinkage void kvm_posted_intr_wakeup_ipi(void);
extern asmlinkage void kvm_posted_intr_nested_ipi(void);
extern asmlinkage void error_interrupt(void);
extern asmlinkage void irq_work_interrupt(void);
+extern asmlinkage void uv_bau_message_intr1(void);
extern asmlinkage void spurious_interrupt(void);
extern asmlinkage void thermal_interrupt(void);
diff --git a/arch/x86/include/asm/intel_pconfig.h b/arch/x86/include/asm/intel_pconfig.h
new file mode 100644
index 000000000000..3cb002b1d0f9
--- /dev/null
+++ b/arch/x86/include/asm/intel_pconfig.h
@@ -0,0 +1,65 @@
+#ifndef _ASM_X86_INTEL_PCONFIG_H
+#define _ASM_X86_INTEL_PCONFIG_H
+
+#include <asm/asm.h>
+#include <asm/processor.h>
+
+enum pconfig_target {
+ INVALID_TARGET = 0,
+ MKTME_TARGET = 1,
+ PCONFIG_TARGET_NR
+};
+
+int pconfig_target_supported(enum pconfig_target target);
+
+enum pconfig_leaf {
+ MKTME_KEY_PROGRAM = 0,
+ PCONFIG_LEAF_INVALID,
+};
+
+#define PCONFIG ".byte 0x0f, 0x01, 0xc5"
+
+/* Defines and structure for MKTME_KEY_PROGRAM of PCONFIG instruction */
+
+/* mktme_key_program::keyid_ctrl COMMAND, bits [7:0] */
+#define MKTME_KEYID_SET_KEY_DIRECT 0
+#define MKTME_KEYID_SET_KEY_RANDOM 1
+#define MKTME_KEYID_CLEAR_KEY 2
+#define MKTME_KEYID_NO_ENCRYPT 3
+
+/* mktme_key_program::keyid_ctrl ENC_ALG, bits [23:8] */
+#define MKTME_AES_XTS_128 (1 << 8)
+
+/* Return codes from the PCONFIG MKTME_KEY_PROGRAM */
+#define MKTME_PROG_SUCCESS 0
+#define MKTME_INVALID_PROG_CMD 1
+#define MKTME_ENTROPY_ERROR 2
+#define MKTME_INVALID_KEYID 3
+#define MKTME_INVALID_ENC_ALG 4
+#define MKTME_DEVICE_BUSY 5
+
+/* Hardware requires the structure to be 256 byte alinged. Otherwise #GP(0). */
+struct mktme_key_program {
+ u16 keyid;
+ u32 keyid_ctrl;
+ u8 __rsvd[58];
+ u8 key_field_1[64];
+ u8 key_field_2[64];
+} __packed __aligned(256);
+
+static inline int mktme_key_program(struct mktme_key_program *key_program)
+{
+ unsigned long rax = MKTME_KEY_PROGRAM;
+
+ if (!pconfig_target_supported(MKTME_TARGET))
+ return -ENXIO;
+
+ asm volatile(PCONFIG
+ : "=a" (rax), "=b" (key_program)
+ : "0" (rax), "1" (key_program)
+ : "memory", "cc");
+
+ return rax;
+}
+
+#endif /* _ASM_X86_INTEL_PCONFIG_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 95e948627fd0..f6e5b9375d8c 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -232,21 +232,6 @@ extern void set_iounmap_nonlazy(void);
*/
#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
-/*
- * Cache management
- *
- * This needed for two cases
- * 1. Out of order aware processors
- * 2. Accidentally out of order processors (PPro errata #51)
- */
-
-static inline void flush_write_buffers(void)
-{
-#if defined(CONFIG_X86_PPRO_FENCE)
- asm volatile("lock; addl $0,0(%%esp)": : :"memory");
-#endif
-}
-
#endif /* __KERNEL__ */
extern void native_io_delay(void);
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index a8834dd546cd..fd20a2334885 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -183,16 +183,17 @@ extern void disable_ioapic_support(void);
extern void __init io_apic_init_mappings(void);
extern unsigned int native_io_apic_read(unsigned int apic, unsigned int reg);
-extern void native_disable_io_apic(void);
+extern void native_restore_boot_irq_mode(void);
static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
{
- return x86_io_apic_ops.read(apic, reg);
+ return x86_apic_ops.io_apic_read(apic, reg);
}
extern void setup_IO_APIC(void);
extern void enable_IO_APIC(void);
-extern void disable_IO_APIC(void);
+extern void clear_IO_APIC(void);
+extern void restore_boot_irq_mode(void);
extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin);
extern void print_IO_APICs(void);
#else /* !CONFIG_X86_IO_APIC */
@@ -228,10 +229,11 @@ static inline void mp_save_irq(struct mpc_intsrc *m) { }
static inline void disable_ioapic_support(void) { }
static inline void io_apic_init_mappings(void) { }
#define native_io_apic_read NULL
-#define native_disable_io_apic NULL
+#define native_restore_boot_irq_mode NULL
static inline void setup_IO_APIC(void) { }
static inline void enable_IO_APIC(void) { }
+static inline void restore_boot_irq_mode(void) { }
#endif
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index 1e5d5d92eb40..baedab8ac538 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -2,13 +2,10 @@
#ifndef _ASM_X86_IOMMU_H
#define _ASM_X86_IOMMU_H
-extern const struct dma_map_ops nommu_dma_ops;
extern int force_iommu, no_iommu;
extern int iommu_detected;
extern int iommu_pass_through;
-int x86_dma_supported(struct device *dev, u64 mask);
-
/* 10 seconds */
#define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
diff --git a/arch/x86/include/asm/jailhouse_para.h b/arch/x86/include/asm/jailhouse_para.h
index 875b54376689..b885a961a150 100644
--- a/arch/x86/include/asm/jailhouse_para.h
+++ b/arch/x86/include/asm/jailhouse_para.h
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL2.0 */
/*
- * Jailhouse paravirt_ops implementation
+ * Jailhouse paravirt detection
*
* Copyright (c) Siemens AG, 2015-2017
*
diff --git a/arch/x86/include/asm/kaslr.h b/arch/x86/include/asm/kaslr.h
index 460991e3b529..db7ba2feb947 100644
--- a/arch/x86/include/asm/kaslr.h
+++ b/arch/x86/include/asm/kaslr.h
@@ -5,10 +5,6 @@
unsigned long kaslr_get_random_long(const char *purpose);
#ifdef CONFIG_RANDOMIZE_MEMORY
-extern unsigned long page_offset_base;
-extern unsigned long vmalloc_base;
-extern unsigned long vmemmap_base;
-
void kernel_randomize_memory(void);
#else
static inline void kernel_randomize_memory(void) { }
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 96ea4b5ba658..8c7b3e5a2d01 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -138,58 +138,6 @@ struct mce_log_buffer {
struct mce entry[MCE_LOG_LEN];
};
-struct mca_config {
- bool dont_log_ce;
- bool cmci_disabled;
- bool lmce_disabled;
- bool ignore_ce;
- bool disabled;
- bool ser;
- bool recovery;
- bool bios_cmci_threshold;
- u8 banks;
- s8 bootlog;
- int tolerant;
- int monarch_timeout;
- int panic_timeout;
- u32 rip_msr;
-};
-
-struct mce_vendor_flags {
- /*
- * Indicates that overflow conditions are not fatal, when set.
- */
- __u64 overflow_recov : 1,
-
- /*
- * (AMD) SUCCOR stands for S/W UnCorrectable error COntainment and
- * Recovery. It indicates support for data poisoning in HW and deferred
- * error interrupts.
- */
- succor : 1,
-
- /*
- * (AMD) SMCA: This bit indicates support for Scalable MCA which expands
- * the register space for each MCA bank and also increases number of
- * banks. Also, to accommodate the new banks and registers, the MCA
- * register space is moved to a new MSR range.
- */
- smca : 1,
-
- __reserved_0 : 61;
-};
-
-struct mca_msr_regs {
- u32 (*ctl) (int bank);
- u32 (*status) (int bank);
- u32 (*addr) (int bank);
- u32 (*misc) (int bank);
-};
-
-extern struct mce_vendor_flags mce_flags;
-
-extern struct mca_msr_regs msr_ops;
-
enum mce_notifier_prios {
MCE_PRIO_FIRST = INT_MAX,
MCE_PRIO_SRAO = INT_MAX - 1,
@@ -346,6 +294,7 @@ enum smca_bank_types {
SMCA_IF, /* Instruction Fetch */
SMCA_L2_CACHE, /* L2 Cache */
SMCA_DE, /* Decoder Unit */
+ SMCA_RESERVED, /* Reserved */
SMCA_EX, /* Execution Unit */
SMCA_FP, /* Floating Point */
SMCA_L3_CACHE, /* L3 Cache */
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 22c5f3e6f820..c0643831706e 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -22,6 +22,7 @@
#ifdef CONFIG_AMD_MEM_ENCRYPT
extern u64 sme_me_mask;
+extern bool sev_enabled;
void sme_encrypt_execute(unsigned long encrypted_kernel_vaddr,
unsigned long decrypted_kernel_vaddr,
@@ -48,8 +49,6 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size);
/* Architecture __weak replacement functions */
void __init mem_encrypt_init(void);
-void swiotlb_set_mem_attributes(void *vaddr, unsigned long size);
-
bool sme_active(void);
bool sev_active(void);
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 7fb1047d61c7..2b7cc5397f80 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -6,20 +6,6 @@
#include <linux/earlycpio.h>
#include <linux/initrd.h>
-#define native_rdmsr(msr, val1, val2) \
-do { \
- u64 __val = __rdmsr((msr)); \
- (void)((val1) = (u32)__val); \
- (void)((val2) = (u32)(__val >> 32)); \
-} while (0)
-
-#define native_wrmsr(msr, low, high) \
- __wrmsr(msr, low, high)
-
-#define native_wrmsrl(msr, val) \
- __wrmsr((msr), (u32)((u64)(val)), \
- (u32)((u64)(val) >> 32))
-
struct ucode_patch {
struct list_head plist;
void *data; /* Intel uses only this one */
@@ -39,6 +25,7 @@ struct device;
enum ucode_state {
UCODE_OK = 0,
+ UCODE_NEW,
UCODE_UPDATED,
UCODE_NFOUND,
UCODE_ERROR,
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 1de72ce514cd..57e3785d0d26 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -24,11 +24,12 @@ static inline void paravirt_activate_mm(struct mm_struct *prev,
#endif /* !CONFIG_PARAVIRT */
#ifdef CONFIG_PERF_EVENTS
-extern struct static_key rdpmc_always_available;
+
+DECLARE_STATIC_KEY_FALSE(rdpmc_always_available_key);
static inline void load_mm_cr4(struct mm_struct *mm)
{
- if (static_key_false(&rdpmc_always_available) ||
+ if (static_branch_unlikely(&rdpmc_always_available_key) ||
atomic_read(&mm->context.perf_rdpmc_allowed))
cr4_set_bits(X86_CR4_PCE);
else
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 30df295f6d94..04addd6e0a4a 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -108,6 +108,20 @@ static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high)
: : "c" (msr), "a"(low), "d" (high) : "memory");
}
+#define native_rdmsr(msr, val1, val2) \
+do { \
+ u64 __val = __rdmsr((msr)); \
+ (void)((val1) = (u32)__val); \
+ (void)((val2) = (u32)(__val >> 32)); \
+} while (0)
+
+#define native_wrmsr(msr, low, high) \
+ __wrmsr(msr, low, high)
+
+#define native_wrmsrl(msr, val) \
+ __wrmsr((msr), (u32)((u64)(val)), \
+ (u32)((u64)(val) >> 32))
+
static inline unsigned long long native_read_msr(unsigned int msr)
{
unsigned long long val;
@@ -218,9 +232,6 @@ static __always_inline unsigned long long rdtsc_ordered(void)
return rdtsc();
}
-/* Deprecated, keep it for a cycle for easier merging: */
-#define rdtscll(now) do { (now) = rdtsc_ordered(); } while (0)
-
static inline unsigned long long native_read_pmc(int counter)
{
DECLARE_ARGS(val, low, high);
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index d0dabeae0505..f928ad9b143f 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -183,7 +183,10 @@
* otherwise we'll run out of registers. We don't care about CET
* here, anyway.
*/
-# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n", \
+# define CALL_NOSPEC \
+ ALTERNATIVE( \
+ ANNOTATE_RETPOLINE_SAFE \
+ "call *%[thunk_target]\n", \
" jmp 904f;\n" \
" .align 16\n" \
"901: call 903f;\n" \
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index d652a3808065..939b1cff4a7b 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -11,6 +11,10 @@
extern unsigned long max_pfn;
extern unsigned long phys_base;
+extern unsigned long page_offset_base;
+extern unsigned long vmalloc_base;
+extern unsigned long vmemmap_base;
+
static inline unsigned long __phys_addr_nodebug(unsigned long x)
{
unsigned long y = x - __START_KERNEL_map;
@@ -47,7 +51,7 @@ static inline void clear_page(void *page)
clear_page_erms, X86_FEATURE_ERMS,
"=D" (page),
"0" (page)
- : "memory", "rax", "rcx");
+ : "cc", "memory", "rax", "rcx");
}
void copy_page(void *to, void *from);
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index e1407312c412..2c5a966dc222 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -37,26 +37,24 @@
* hypervisor to fit. Choosing 16 slots here is arbitrary, but it's
* what Xen requires.
*/
-#ifdef CONFIG_X86_5LEVEL
-#define __PAGE_OFFSET_BASE _AC(0xff10000000000000, UL)
-#else
-#define __PAGE_OFFSET_BASE _AC(0xffff880000000000, UL)
-#endif
+#define __PAGE_OFFSET_BASE_L5 _AC(0xff10000000000000, UL)
+#define __PAGE_OFFSET_BASE_L4 _AC(0xffff880000000000, UL)
-#ifdef CONFIG_RANDOMIZE_MEMORY
+#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
#define __PAGE_OFFSET page_offset_base
#else
-#define __PAGE_OFFSET __PAGE_OFFSET_BASE
-#endif /* CONFIG_RANDOMIZE_MEMORY */
+#define __PAGE_OFFSET __PAGE_OFFSET_BASE_L4
+#endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */
#define __START_KERNEL_map _AC(0xffffffff80000000, UL)
/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
-#ifdef CONFIG_X86_5LEVEL
+
#define __PHYSICAL_MASK_SHIFT 52
-#define __VIRTUAL_MASK_SHIFT 56
+
+#ifdef CONFIG_X86_5LEVEL
+#define __VIRTUAL_MASK_SHIFT (pgtable_l5_enabled ? 56 : 47)
#else
-#define __PHYSICAL_MASK_SHIFT 46
#define __VIRTUAL_MASK_SHIFT 47
#endif
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index c83a2f418cea..9be2bf13825b 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -568,17 +568,22 @@ static inline p4dval_t p4d_val(p4d_t p4d)
return PVOP_CALLEE1(p4dval_t, pv_mmu_ops.p4d_val, p4d.p4d);
}
-static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
+static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
{
- pgdval_t val = native_pgd_val(pgd);
-
- PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, val);
+ PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, native_pgd_val(pgd));
}
-static inline void pgd_clear(pgd_t *pgdp)
-{
- set_pgd(pgdp, __pgd(0));
-}
+#define set_pgd(pgdp, pgdval) do { \
+ if (pgtable_l5_enabled) \
+ __set_pgd(pgdp, pgdval); \
+ else \
+ set_p4d((p4d_t *)(pgdp), (p4d_t) { (pgdval).pgd }); \
+} while (0)
+
+#define pgd_clear(pgdp) do { \
+ if (pgtable_l5_enabled) \
+ set_pgd(pgdp, __pgd(0)); \
+} while (0)
#endif /* CONFIG_PGTABLE_LEVELS == 5 */
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index eb66fa9cd0fc..959d618dbb17 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -151,6 +151,8 @@ extern int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
phys_addr_t addr);
extern int pci_mmconfig_delete(u16 seg, u8 start, u8 end);
extern struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus);
+extern struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start,
+ int end, u64 addr);
extern struct list_head pci_mmcfg_list;
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index aff42e1da6ee..263c142a6a6c 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -167,6 +167,8 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
#if CONFIG_PGTABLE_LEVELS > 4
static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d)
{
+ if (!pgtable_l5_enabled)
+ return;
paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT);
set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d)));
}
@@ -191,7 +193,8 @@ extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d);
static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
unsigned long address)
{
- ___p4d_free_tlb(tlb, p4d);
+ if (pgtable_l5_enabled)
+ ___p4d_free_tlb(tlb, p4d);
}
#endif /* CONFIG_PGTABLE_LEVELS > 4 */
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index 876b4c77d983..6a59a6d0cc50 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -44,5 +44,6 @@ typedef union {
*/
#define PTRS_PER_PTE 512
+#define MAX_POSSIBLE_PHYSMEM_BITS 36
#endif /* _ASM_X86_PGTABLE_3LEVEL_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index b444d83cfc95..89d5c8886c85 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -65,7 +65,7 @@ extern pmdval_t early_pmd_flags;
#ifndef __PAGETABLE_P4D_FOLDED
#define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd)
-#define pgd_clear(pgd) native_pgd_clear(pgd)
+#define pgd_clear(pgd) (pgtable_l5_enabled ? native_pgd_clear(pgd) : 0)
#endif
#ifndef set_p4d
@@ -859,6 +859,8 @@ static inline unsigned long p4d_index(unsigned long address)
#if CONFIG_PGTABLE_LEVELS > 4
static inline int pgd_present(pgd_t pgd)
{
+ if (!pgtable_l5_enabled)
+ return 1;
return pgd_flags(pgd) & _PAGE_PRESENT;
}
@@ -876,6 +878,8 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd)
/* to find an entry in a page-table-directory. */
static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
{
+ if (!pgtable_l5_enabled)
+ return (p4d_t *)pgd;
return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address);
}
@@ -883,6 +887,9 @@ static inline int pgd_bad(pgd_t pgd)
{
unsigned long ignore_flags = _PAGE_USER;
+ if (!pgtable_l5_enabled)
+ return 0;
+
if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
ignore_flags |= _PAGE_NX;
@@ -891,6 +898,8 @@ static inline int pgd_bad(pgd_t pgd)
static inline int pgd_none(pgd_t pgd)
{
+ if (!pgtable_l5_enabled)
+ return 0;
/*
* There is no need to do a workaround for the KNL stray
* A/D bit erratum here. PGDs only point to page tables
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index b3ec519e3982..88a056b01db4 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -34,6 +34,8 @@ static inline void check_pgt_cache(void) { }
void paging_init(void);
void sync_initial_page_table(void);
+static inline int pgd_large(pgd_t pgd) { return 0; }
+
/*
* Define this if things work differently on an i386 and an i486:
* it will (on an i486) warn about kernel memory accesses that are
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index 0777e18a1d23..e3225e83db7d 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -15,6 +15,8 @@
# include <asm/pgtable-2level_types.h>
#endif
+#define pgtable_l5_enabled 0
+
#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE - 1))
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 1149d2112b2e..877bc27718ae 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -218,29 +218,26 @@ static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
{
-#if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL)
- p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd);
-#else
- *p4dp = p4d;
-#endif
+ pgd_t pgd;
+
+ if (pgtable_l5_enabled || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) {
+ *p4dp = p4d;
+ return;
+ }
+
+ pgd = native_make_pgd(native_p4d_val(p4d));
+ pgd = pti_set_user_pgd((pgd_t *)p4dp, pgd);
+ *p4dp = native_make_p4d(native_pgd_val(pgd));
}
static inline void native_p4d_clear(p4d_t *p4d)
{
-#ifdef CONFIG_X86_5LEVEL
native_set_p4d(p4d, native_make_p4d(0));
-#else
- native_set_p4d(p4d, (p4d_t) { .pgd = native_make_pgd(0)});
-#endif
}
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
*pgdp = pti_set_user_pgd(pgdp, pgd);
-#else
- *pgdp = pgd;
-#endif
}
static inline void native_pgd_clear(pgd_t *pgd)
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 6b8f73dcbc2c..d5c21a382475 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -20,6 +20,18 @@ typedef unsigned long pgprotval_t;
typedef struct { pteval_t pte; } pte_t;
+#ifdef CONFIG_X86_5LEVEL
+extern unsigned int __pgtable_l5_enabled;
+#ifndef pgtable_l5_enabled
+#define pgtable_l5_enabled cpu_feature_enabled(X86_FEATURE_LA57)
+#endif
+#else
+#define pgtable_l5_enabled 0
+#endif
+
+extern unsigned int pgdir_shift;
+extern unsigned int ptrs_per_p4d;
+
#endif /* !__ASSEMBLY__ */
#define SHARED_KERNEL_PMD 0
@@ -29,24 +41,28 @@ typedef struct { pteval_t pte; } pte_t;
/*
* PGDIR_SHIFT determines what a top-level page table entry can map
*/
-#define PGDIR_SHIFT 48
+#define PGDIR_SHIFT pgdir_shift
#define PTRS_PER_PGD 512
/*
* 4th level page in 5-level paging case
*/
-#define P4D_SHIFT 39
-#define PTRS_PER_P4D 512
-#define P4D_SIZE (_AC(1, UL) << P4D_SHIFT)
-#define P4D_MASK (~(P4D_SIZE - 1))
+#define P4D_SHIFT 39
+#define MAX_PTRS_PER_P4D 512
+#define PTRS_PER_P4D ptrs_per_p4d
+#define P4D_SIZE (_AC(1, UL) << P4D_SHIFT)
+#define P4D_MASK (~(P4D_SIZE - 1))
+
+#define MAX_POSSIBLE_PHYSMEM_BITS 52
#else /* CONFIG_X86_5LEVEL */
/*
* PGDIR_SHIFT determines what a top-level page table entry can map
*/
-#define PGDIR_SHIFT 39
-#define PTRS_PER_PGD 512
+#define PGDIR_SHIFT 39
+#define PTRS_PER_PGD 512
+#define MAX_PTRS_PER_P4D 1
#endif /* CONFIG_X86_5LEVEL */
@@ -82,31 +98,33 @@ typedef struct { pteval_t pte; } pte_t;
* range must not overlap with anything except the KASAN shadow area, which
* is correct as KASAN disables KASLR.
*/
-#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+#define MAXMEM (1UL << MAX_PHYSMEM_BITS)
-#ifdef CONFIG_X86_5LEVEL
-# define VMALLOC_SIZE_TB _AC(12800, UL)
-# define __VMALLOC_BASE _AC(0xffa0000000000000, UL)
-# define __VMEMMAP_BASE _AC(0xffd4000000000000, UL)
-# define LDT_PGD_ENTRY _AC(-112, UL)
-# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
-#else
-# define VMALLOC_SIZE_TB _AC(32, UL)
-# define __VMALLOC_BASE _AC(0xffffc90000000000, UL)
-# define __VMEMMAP_BASE _AC(0xffffea0000000000, UL)
-# define LDT_PGD_ENTRY _AC(-3, UL)
-# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
-#endif
+#define LDT_PGD_ENTRY_L4 -3UL
+#define LDT_PGD_ENTRY_L5 -112UL
+#define LDT_PGD_ENTRY (pgtable_l5_enabled ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
+#define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
+
+#define __VMALLOC_BASE_L4 0xffffc90000000000
+#define __VMALLOC_BASE_L5 0xffa0000000000000
+
+#define VMALLOC_SIZE_TB_L4 32UL
+#define VMALLOC_SIZE_TB_L5 12800UL
+
+#define __VMEMMAP_BASE_L4 0xffffea0000000000
+#define __VMEMMAP_BASE_L5 0xffd4000000000000
-#ifdef CONFIG_RANDOMIZE_MEMORY
+#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
# define VMALLOC_START vmalloc_base
+# define VMALLOC_SIZE_TB (pgtable_l5_enabled ? VMALLOC_SIZE_TB_L5 : VMALLOC_SIZE_TB_L4)
# define VMEMMAP_START vmemmap_base
#else
-# define VMALLOC_START __VMALLOC_BASE
-# define VMEMMAP_START __VMEMMAP_BASE
-#endif /* CONFIG_RANDOMIZE_MEMORY */
+# define VMALLOC_START __VMALLOC_BASE_L4
+# define VMALLOC_SIZE_TB VMALLOC_SIZE_TB_L4
+# define VMEMMAP_START __VMEMMAP_BASE_L4
+#endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */
-#define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
+#define VMALLOC_END (VMALLOC_START + (VMALLOC_SIZE_TB << 40) - 1)
#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
/* The module sections ends with the start of the fixmap */
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index fb3a6de7440b..6847d85400a8 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -53,12 +53,6 @@
# define NEED_MOVBE 0
#endif
-#ifdef CONFIG_X86_5LEVEL
-# define NEED_LA57 (1<<(X86_FEATURE_LA57 & 31))
-#else
-# define NEED_LA57 0
-#endif
-
#ifdef CONFIG_X86_64
#ifdef CONFIG_PARAVIRT
/* Paravirtualized systems may not have PSE or PGE available */
@@ -104,7 +98,7 @@
#define REQUIRED_MASK13 0
#define REQUIRED_MASK14 0
#define REQUIRED_MASK15 0
-#define REQUIRED_MASK16 (NEED_LA57)
+#define REQUIRED_MASK16 0
#define REQUIRED_MASK17 0
#define REQUIRED_MASK18 0
#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index a4189762b266..f75bff8f9d82 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -177,16 +177,6 @@ static inline int wbinvd_on_all_cpus(void)
extern unsigned disabled_cpus;
#ifdef CONFIG_X86_LOCAL_APIC
-
-#ifndef CONFIG_X86_64
-static inline int logical_smp_processor_id(void)
-{
- /* we don't want to mark this access volatile - bad code generation */
- return GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
-}
-
-#endif
-
extern int hard_smp_processor_id(void);
#else /* CONFIG_X86_LOCAL_APIC */
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 4fc1e9d3c43e..4617a2bf123c 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -27,13 +27,8 @@
# endif
#else /* CONFIG_X86_32 */
# define SECTION_SIZE_BITS 27 /* matt - 128 is convenient right now */
-# ifdef CONFIG_X86_5LEVEL
-# define MAX_PHYSADDR_BITS 52
-# define MAX_PHYSMEM_BITS 52
-# else
-# define MAX_PHYSADDR_BITS 44
-# define MAX_PHYSMEM_BITS 46
-# endif
+# define MAX_PHYSADDR_BITS (pgtable_l5_enabled ? 52 : 44)
+# define MAX_PHYSMEM_BITS (pgtable_l5_enabled ? 52 : 46)
#endif
#endif /* CONFIG_SPARSEMEM */
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index f73706878772..133d9425fced 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -87,8 +87,6 @@ get_stack_pointer(struct task_struct *task, struct pt_regs *regs)
void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack, char *log_lvl);
-extern unsigned int code_bytes;
-
/* The form of the top of the frame on the stack */
struct stack_frame {
struct stack_frame *next_frame;
diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h
index 1c6a6cb230ff..ff6c92eff035 100644
--- a/arch/x86/include/asm/swiotlb.h
+++ b/arch/x86/include/asm/swiotlb.h
@@ -27,12 +27,4 @@ static inline void pci_swiotlb_late_init(void)
{
}
#endif
-
-extern void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
- dma_addr_t *dma_handle, gfp_t flags,
- unsigned long attrs);
-extern void x86_swiotlb_free_coherent(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_addr,
- unsigned long attrs);
-
#endif /* _ASM_X86_SWIOTLB_H */
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
deleted file mode 100644
index 906794aa034e..000000000000
--- a/arch/x86/include/asm/sys_ia32.h
+++ /dev/null
@@ -1,67 +0,0 @@
-/*
- * sys_ia32.h - Linux ia32 syscall interfaces
- *
- * Copyright (c) 2008 Jaswinder Singh Rajput
- *
- * This file is released under the GPLv2.
- * See the file COPYING for more details.
- */
-
-#ifndef _ASM_X86_SYS_IA32_H
-#define _ASM_X86_SYS_IA32_H
-
-#ifdef CONFIG_COMPAT
-
-#include <linux/compiler.h>
-#include <linux/linkage.h>
-#include <linux/types.h>
-#include <linux/signal.h>
-#include <asm/compat.h>
-#include <asm/ia32.h>
-
-/* ia32/sys_ia32.c */
-asmlinkage long compat_sys_x86_truncate64(const char __user *, unsigned long,
- unsigned long);
-asmlinkage long compat_sys_x86_ftruncate64(unsigned int, unsigned long,
- unsigned long);
-
-asmlinkage long compat_sys_x86_stat64(const char __user *,
- struct stat64 __user *);
-asmlinkage long compat_sys_x86_lstat64(const char __user *,
- struct stat64 __user *);
-asmlinkage long compat_sys_x86_fstat64(unsigned int, struct stat64 __user *);
-asmlinkage long compat_sys_x86_fstatat(unsigned int, const char __user *,
- struct stat64 __user *, int);
-struct mmap_arg_struct32;
-asmlinkage long compat_sys_x86_mmap(struct mmap_arg_struct32 __user *);
-
-asmlinkage long compat_sys_x86_waitpid(compat_pid_t, unsigned int __user *,
- int);
-
-asmlinkage long compat_sys_x86_pread(unsigned int, char __user *, u32, u32,
- u32);
-asmlinkage long compat_sys_x86_pwrite(unsigned int, const char __user *, u32,
- u32, u32);
-
-asmlinkage long compat_sys_x86_fadvise64_64(int, __u32, __u32, __u32, __u32,
- int);
-
-asmlinkage ssize_t compat_sys_x86_readahead(int, unsigned int, unsigned int,
- size_t);
-asmlinkage long compat_sys_x86_sync_file_range(int, unsigned int, unsigned int,
- unsigned int, unsigned int,
- int);
-asmlinkage long compat_sys_x86_fadvise64(int, unsigned int, unsigned int,
- size_t, int);
-asmlinkage long compat_sys_x86_fallocate(int, int, unsigned int, unsigned int,
- unsigned int, unsigned int);
-asmlinkage long compat_sys_x86_clone(unsigned long, unsigned long, int __user *,
- unsigned long, int __user *);
-
-/* ia32/ia32_signal.c */
-asmlinkage long sys32_sigreturn(void);
-asmlinkage long sys32_rt_sigreturn(void);
-
-#endif /* CONFIG_COMPAT */
-
-#endif /* _ASM_X86_SYS_IA32_H */
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index bad25bb80679..ae6e05fdc24b 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -17,6 +17,7 @@
/* Common in X86_32 and X86_64 */
/* kernel/ioport.c */
+long ksys_ioperm(unsigned long from, unsigned long num, int turn_on);
asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
asmlinkage long sys_iopl(unsigned int);
@@ -34,7 +35,7 @@ asmlinkage long sys_get_thread_area(struct user_desc __user *);
#ifdef CONFIG_X86_32
/* kernel/signal.c */
-asmlinkage unsigned long sys_sigreturn(void);
+asmlinkage long sys_sigreturn(void);
/* kernel/vm86_32.c */
struct vm86_struct;
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index cf5d53c3f9ea..2701d221583a 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -31,6 +31,7 @@ static inline cycles_t get_cycles(void)
}
extern struct system_counterval_t convert_art_to_tsc(u64 art);
+extern struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns);
extern void tsc_early_delay_calibrate(void);
extern void tsc_init(void);
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index ecb9ddef128f..62c79e26a59a 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -3833,7 +3833,7 @@ union uvh_rh_gam_mmioh_overlay_config0_mmr_u {
#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR uv_undefined("UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR")
#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR uv_undefined("UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR")
#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR 0x1603000UL
-#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR 0x483000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR 0x484000UL
#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR ( \
is_uv1_hub() ? UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR : \
is_uv2_hub() ? UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR : \
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 8b6780751132..5db8b0b10766 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -352,6 +352,7 @@ enum vmcs_field {
#define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */
#define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */
#define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */
+#define INTR_TYPE_PRIV_SW_EXCEPTION (5 << 8) /* ICE breakpoint - undocumented */
#define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */
/* GUEST_INTERRUPTIBILITY_INFO flags. */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index fc2f082ac635..199e15bd3ec5 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -131,6 +131,16 @@ struct x86_hyper_init {
};
/**
+ * struct x86_init_acpi - x86 ACPI init functions
+ * @get_root_pointer: get RSDP address
+ * @reduced_hw_early_init: hardware reduced platform early init
+ */
+struct x86_init_acpi {
+ u64 (*get_root_pointer)(void);
+ void (*reduced_hw_early_init)(void);
+};
+
+/**
* struct x86_init_ops - functions for platform specific setup
*
*/
@@ -144,6 +154,7 @@ struct x86_init_ops {
struct x86_init_iommu iommu;
struct x86_init_pci pci;
struct x86_hyper_init hyper;
+ struct x86_init_acpi acpi;
};
/**
@@ -274,16 +285,16 @@ struct x86_msi_ops {
void (*restore_msi_irqs)(struct pci_dev *dev);
};
-struct x86_io_apic_ops {
- unsigned int (*read) (unsigned int apic, unsigned int reg);
- void (*disable)(void);
+struct x86_apic_ops {
+ unsigned int (*io_apic_read) (unsigned int apic, unsigned int reg);
+ void (*restore)(void);
};
extern struct x86_init_ops x86_init;
extern struct x86_cpuinit_ops x86_cpuinit;
extern struct x86_platform_ops x86_platform;
extern struct x86_msi_ops x86_msi;
-extern struct x86_io_apic_ops x86_io_apic_ops;
+extern struct x86_apic_ops x86_apic_ops;
extern void x86_early_init_platform_quirks(void);
extern void x86_init_noop(void);
diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h
index 435db58a7bad..955c2a2e1cf9 100644
--- a/arch/x86/include/uapi/asm/mce.h
+++ b/arch/x86/include/uapi/asm/mce.h
@@ -5,32 +5,36 @@
#include <linux/types.h>
#include <linux/ioctl.h>
-/* Fields are zero when not available */
+/*
+ * Fields are zero when not available. Also, this struct is shared with
+ * userspace mcelog and thus must keep existing fields at current offsets.
+ * Only add new fields to the end of the structure
+ */
struct mce {
- __u64 status;
- __u64 misc;
- __u64 addr;
- __u64 mcgstatus;
- __u64 ip;
- __u64 tsc; /* cpu time stamp counter */
- __u64 time; /* wall time_t when error was detected */
- __u8 cpuvendor; /* cpu vendor as encoded in system.h */
- __u8 inject_flags; /* software inject flags */
- __u8 severity;
+ __u64 status; /* Bank's MCi_STATUS MSR */
+ __u64 misc; /* Bank's MCi_MISC MSR */
+ __u64 addr; /* Bank's MCi_ADDR MSR */
+ __u64 mcgstatus; /* Machine Check Global Status MSR */
+ __u64 ip; /* Instruction Pointer when the error happened */
+ __u64 tsc; /* CPU time stamp counter */
+ __u64 time; /* Wall time_t when error was detected */
+ __u8 cpuvendor; /* Kernel's X86_VENDOR enum */
+ __u8 inject_flags; /* Software inject flags */
+ __u8 severity; /* Error severity */
__u8 pad;
- __u32 cpuid; /* CPUID 1 EAX */
- __u8 cs; /* code segment */
- __u8 bank; /* machine check bank */
- __u8 cpu; /* cpu number; obsolete; use extcpu now */
- __u8 finished; /* entry is valid */
- __u32 extcpu; /* linux cpu number that detected the error */
- __u32 socketid; /* CPU socket ID */
- __u32 apicid; /* CPU initial apic ID */
- __u64 mcgcap; /* MCGCAP MSR: machine check capabilities of CPU */
- __u64 synd; /* MCA_SYND MSR: only valid on SMCA systems */
- __u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */
- __u64 ppin; /* Protected Processor Inventory Number */
- __u32 microcode;/* Microcode revision */
+ __u32 cpuid; /* CPUID 1 EAX */
+ __u8 cs; /* Code segment */
+ __u8 bank; /* Machine check bank reporting the error */
+ __u8 cpu; /* CPU number; obsoleted by extcpu */
+ __u8 finished; /* Entry is valid */
+ __u32 extcpu; /* Linux CPU number that detected the error */
+ __u32 socketid; /* CPU socket ID */
+ __u32 apicid; /* CPU initial APIC ID */
+ __u64 mcgcap; /* MCGCAP MSR: machine check capabilities of CPU */
+ __u64 synd; /* MCA_SYND MSR: only valid on SMCA systems */
+ __u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */
+ __u64 ppin; /* Protected Processor Inventory Number */
+ __u32 microcode; /* Microcode revision */
};
#define MCE_GET_RECORD_LEN _IOR('M', 1, int)
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 29786c87e864..02d6f5cf4e70 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -57,7 +57,7 @@ obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o
obj-$(CONFIG_SYSFS) += ksysfs.o
obj-y += bootflag.o e820.o
obj-y += pci-dma.o quirks.o topology.o kdebugfs.o
-obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o
+obj-y += alternative.o i8253.o hw_breakpoint.o
obj-y += tsc.o tsc_msr.o io_delay.o rtc.o
obj-y += pci-iommu_table.o
obj-y += resource.o
@@ -146,6 +146,6 @@ ifeq ($(CONFIG_X86_64),y)
obj-$(CONFIG_GART_IOMMU) += amd_gart_64.o aperture_64.o
obj-$(CONFIG_CALGARY_IOMMU) += pci-calgary_64.o tce_64.o
- obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o
+ obj-$(CONFIG_MMCONF_FAM10H) += mmconf-fam10h_64.o
obj-y += vsmp_64.o
endif
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 2aa92094b59d..7a37d9357bc4 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1376,17 +1376,21 @@ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d)
*
* We initialize the Hardware-reduced ACPI model here:
*/
+void __init acpi_generic_reduced_hw_init(void)
+{
+ /*
+ * Override x86_init functions and bypass legacy PIC in
+ * hardware reduced ACPI mode.
+ */
+ x86_init.timers.timer_init = x86_init_noop;
+ x86_init.irqs.pre_vector_init = x86_init_noop;
+ legacy_pic = &null_legacy_pic;
+}
+
static void __init acpi_reduced_hw_init(void)
{
- if (acpi_gbl_reduced_hardware) {
- /*
- * Override x86_init functions and bypass legacy pic
- * in Hardware-reduced ACPI mode
- */
- x86_init.timers.timer_init = x86_init_noop;
- x86_init.irqs.pre_vector_init = x86_init_noop;
- legacy_pic = &null_legacy_pic;
- }
+ if (acpi_gbl_reduced_hardware)
+ x86_init.acpi.reduced_hw_early_init();
}
/*
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index ecd486cb06ab..f299d8a479bb 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -480,30 +480,21 @@ static void *
gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
gfp_t flag, unsigned long attrs)
{
- dma_addr_t paddr;
- unsigned long align_mask;
- struct page *page;
-
- if (force_iommu && !(flag & GFP_DMA)) {
- flag &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
- page = alloc_pages(flag | __GFP_ZERO, get_order(size));
- if (!page)
- return NULL;
-
- align_mask = (1UL << get_order(size)) - 1;
- paddr = dma_map_area(dev, page_to_phys(page), size,
- DMA_BIDIRECTIONAL, align_mask);
-
- flush_gart();
- if (paddr != bad_dma_addr) {
- *dma_addr = paddr;
- return page_address(page);
- }
- __free_pages(page, get_order(size));
- } else
- return dma_generic_alloc_coherent(dev, size, dma_addr, flag,
- attrs);
+ void *vaddr;
+
+ vaddr = dma_direct_alloc(dev, size, dma_addr, flag, attrs);
+ if (!vaddr ||
+ !force_iommu || dev->coherent_dma_mask <= DMA_BIT_MASK(24))
+ return vaddr;
+ *dma_addr = dma_map_area(dev, virt_to_phys(vaddr), size,
+ DMA_BIDIRECTIONAL, (1UL << get_order(size)) - 1);
+ flush_gart();
+ if (unlikely(*dma_addr == bad_dma_addr))
+ goto out_free;
+ return vaddr;
+out_free:
+ dma_direct_free(dev, size, vaddr, *dma_addr, attrs);
return NULL;
}
@@ -513,7 +504,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_addr, unsigned long attrs)
{
gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, 0);
- dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs);
+ dma_direct_free(dev, size, vaddr, dma_addr, attrs);
}
static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr)
@@ -705,7 +696,7 @@ static const struct dma_map_ops gart_dma_ops = {
.alloc = gart_alloc_coherent,
.free = gart_free_coherent,
.mapping_error = gart_mapping_error,
- .dma_supported = x86_dma_supported,
+ .dma_supported = dma_direct_supported,
};
static void gart_iommu_shutdown(void)
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b203af0855b5..2aabd4cb0e3f 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1408,22 +1408,69 @@ static void lapic_setup_esr(void)
oldvalue, value);
}
+static void apic_pending_intr_clear(void)
+{
+ long long max_loops = cpu_khz ? cpu_khz : 1000000;
+ unsigned long long tsc = 0, ntsc;
+ unsigned int queued;
+ unsigned long value;
+ int i, j, acked = 0;
+
+ if (boot_cpu_has(X86_FEATURE_TSC))
+ tsc = rdtsc();
+ /*
+ * After a crash, we no longer service the interrupts and a pending
+ * interrupt from previous kernel might still have ISR bit set.
+ *
+ * Most probably by now CPU has serviced that pending interrupt and
+ * it might not have done the ack_APIC_irq() because it thought,
+ * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it
+ * does not clear the ISR bit and cpu thinks it has already serivced
+ * the interrupt. Hence a vector might get locked. It was noticed
+ * for timer irq (vector 0x31). Issue an extra EOI to clear ISR.
+ */
+ do {
+ queued = 0;
+ for (i = APIC_ISR_NR - 1; i >= 0; i--)
+ queued |= apic_read(APIC_IRR + i*0x10);
+
+ for (i = APIC_ISR_NR - 1; i >= 0; i--) {
+ value = apic_read(APIC_ISR + i*0x10);
+ for_each_set_bit(j, &value, 32) {
+ ack_APIC_irq();
+ acked++;
+ }
+ }
+ if (acked > 256) {
+ pr_err("LAPIC pending interrupts after %d EOI\n", acked);
+ break;
+ }
+ if (queued) {
+ if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) {
+ ntsc = rdtsc();
+ max_loops = (cpu_khz << 10) - (ntsc - tsc);
+ } else {
+ max_loops--;
+ }
+ }
+ } while (queued && max_loops > 0);
+ WARN_ON(max_loops <= 0);
+}
+
/**
* setup_local_APIC - setup the local APIC
*
* Used to setup local APIC while initializing BSP or bringing up APs.
* Always called with preemption disabled.
*/
-void setup_local_APIC(void)
+static void setup_local_APIC(void)
{
int cpu = smp_processor_id();
- unsigned int value, queued;
- int i, j, acked = 0;
- unsigned long long tsc = 0, ntsc;
- long long max_loops = cpu_khz ? cpu_khz : 1000000;
+ unsigned int value;
+#ifdef CONFIG_X86_32
+ int logical_apicid, ldr_apicid;
+#endif
- if (boot_cpu_has(X86_FEATURE_TSC))
- tsc = rdtsc();
if (disable_apic) {
disable_ioapic_support();
@@ -1460,11 +1507,11 @@ void setup_local_APIC(void)
* initialized during get_smp_config(), make sure it matches the
* actual value.
*/
- i = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
- WARN_ON(i != BAD_APICID && i != logical_smp_processor_id());
+ logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+ ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
+ WARN_ON(logical_apicid != BAD_APICID && logical_apicid != ldr_apicid);
/* always use the value from LDR */
- early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
- logical_smp_processor_id();
+ early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid;
#endif
/*
@@ -1475,45 +1522,7 @@ void setup_local_APIC(void)
value &= ~APIC_TPRI_MASK;
apic_write(APIC_TASKPRI, value);
- /*
- * After a crash, we no longer service the interrupts and a pending
- * interrupt from previous kernel might still have ISR bit set.
- *
- * Most probably by now CPU has serviced that pending interrupt and
- * it might not have done the ack_APIC_irq() because it thought,
- * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it
- * does not clear the ISR bit and cpu thinks it has already serivced
- * the interrupt. Hence a vector might get locked. It was noticed
- * for timer irq (vector 0x31). Issue an extra EOI to clear ISR.
- */
- do {
- queued = 0;
- for (i = APIC_ISR_NR - 1; i >= 0; i--)
- queued |= apic_read(APIC_IRR + i*0x10);
-
- for (i = APIC_ISR_NR - 1; i >= 0; i--) {
- value = apic_read(APIC_ISR + i*0x10);
- for (j = 31; j >= 0; j--) {
- if (value & (1<<j)) {
- ack_APIC_irq();
- acked++;
- }
- }
- }
- if (acked > 256) {
- printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n",
- acked);
- break;
- }
- if (queued) {
- if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) {
- ntsc = rdtsc();
- max_loops = (cpu_khz << 10) - (ntsc - tsc);
- } else
- max_loops--;
- }
- } while (queued && max_loops > 0);
- WARN_ON(max_loops <= 0);
+ apic_pending_intr_clear();
/*
* Now that we are all set up, enable the APIC
@@ -1570,7 +1579,7 @@ void setup_local_APIC(void)
* TODO: set up through-local-APIC from through-I/O-APIC? --macro
*/
value = apic_read(APIC_LVT0) & APIC_LVT_MASKED;
- if (!cpu && (pic_mode || !value)) {
+ if (!cpu && (pic_mode || !value || skip_ioapic_setup)) {
value = APIC_DM_EXTINT;
apic_printk(APIC_VERBOSE, "enabled ExtINT on CPU#%d\n", cpu);
} else {
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 7c5538769f7e..7553819c74c3 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -587,7 +587,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
mpc_ioapic_id(apic), pin);
}
-static void clear_IO_APIC (void)
+void clear_IO_APIC (void)
{
int apic, pin;
@@ -1410,7 +1410,7 @@ void __init enable_IO_APIC(void)
clear_IO_APIC();
}
-void native_disable_io_apic(void)
+void native_restore_boot_irq_mode(void)
{
/*
* If the i8259 is routed through an IOAPIC
@@ -1438,20 +1438,12 @@ void native_disable_io_apic(void)
disconnect_bsp_APIC(ioapic_i8259.pin != -1);
}
-/*
- * Not an __init, needed by the reboot code
- */
-void disable_IO_APIC(void)
+void restore_boot_irq_mode(void)
{
- /*
- * Clear the IO-APIC before rebooting:
- */
- clear_IO_APIC();
-
if (!nr_legacy_irqs())
return;
- x86_io_apic_ops.disable();
+ x86_apic_ops.restore();
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index f8d9d69994e6..e2829bf40e4a 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -14,7 +14,7 @@ int x2apic_phys;
static struct apic apic_x2apic_phys;
-static int set_x2apic_phys_mode(char *arg)
+static int __init set_x2apic_phys_mode(char *arg)
{
x2apic_phys = 1;
return 0;
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 570e8bb1f386..a66229f51b12 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -28,7 +28,7 @@ obj-y += cpuid-deps.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
-obj-$(CONFIG_CPU_SUP_INTEL) += intel.o
+obj-$(CONFIG_CPU_SUP_INTEL) += intel.o intel_pconfig.o
obj-$(CONFIG_CPU_SUP_AMD) += amd.o
obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o
obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f0e6456ca7d3..12bc0a1139da 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -716,7 +716,7 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
static void init_amd_gh(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_MMCONF_FAM10H
/* do this for boot cpu */
if (c == &boot_cpu_data)
check_enable_amd_mmconf_dmi();
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 4aa9fd379390..b9693b80fc21 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -105,7 +105,7 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c)
/*
* Early microcode releases for the Spectre v2 mitigation were broken.
* Information taken from;
- * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-update-guidance.pdf
+ * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/03/microcode-update-guidance.pdf
* - https://kb.vmware.com/s/article/52345
* - Microcode revisions observed in the wild
* - Release note from 20180108 microcode release
@@ -123,7 +123,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = {
{ INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x80 },
{ INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e },
{ INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c },
- { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 },
{ INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 },
{ INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b },
{ INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 },
@@ -510,6 +509,90 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c)
}
}
+#define MSR_IA32_TME_ACTIVATE 0x982
+
+/* Helpers to access TME_ACTIVATE MSR */
+#define TME_ACTIVATE_LOCKED(x) (x & 0x1)
+#define TME_ACTIVATE_ENABLED(x) (x & 0x2)
+
+#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */
+#define TME_ACTIVATE_POLICY_AES_XTS_128 0
+
+#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */
+
+#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */
+#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1
+
+/* Values for mktme_status (SW only construct) */
+#define MKTME_ENABLED 0
+#define MKTME_DISABLED 1
+#define MKTME_UNINITIALIZED 2
+static int mktme_status = MKTME_UNINITIALIZED;
+
+static void detect_tme(struct cpuinfo_x86 *c)
+{
+ u64 tme_activate, tme_policy, tme_crypto_algs;
+ int keyid_bits = 0, nr_keyids = 0;
+ static u64 tme_activate_cpu0 = 0;
+
+ rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
+
+ if (mktme_status != MKTME_UNINITIALIZED) {
+ if (tme_activate != tme_activate_cpu0) {
+ /* Broken BIOS? */
+ pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
+ pr_err_once("x86/tme: MKTME is not usable\n");
+ mktme_status = MKTME_DISABLED;
+
+ /* Proceed. We may need to exclude bits from x86_phys_bits. */
+ }
+ } else {
+ tme_activate_cpu0 = tme_activate;
+ }
+
+ if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
+ pr_info_once("x86/tme: not enabled by BIOS\n");
+ mktme_status = MKTME_DISABLED;
+ return;
+ }
+
+ if (mktme_status != MKTME_UNINITIALIZED)
+ goto detect_keyid_bits;
+
+ pr_info("x86/tme: enabled by BIOS\n");
+
+ tme_policy = TME_ACTIVATE_POLICY(tme_activate);
+ if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
+ pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
+
+ tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
+ if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
+ pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
+ tme_crypto_algs);
+ mktme_status = MKTME_DISABLED;
+ }
+detect_keyid_bits:
+ keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
+ nr_keyids = (1UL << keyid_bits) - 1;
+ if (nr_keyids) {
+ pr_info_once("x86/mktme: enabled by BIOS\n");
+ pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
+ } else {
+ pr_info_once("x86/mktme: disabled by BIOS\n");
+ }
+
+ if (mktme_status == MKTME_UNINITIALIZED) {
+ /* MKTME is usable */
+ mktme_status = MKTME_ENABLED;
+ }
+
+ /*
+ * KeyID bits effectively lower the number of physical address
+ * bits. Update cpuinfo_x86::x86_phys_bits accordingly.
+ */
+ c->x86_phys_bits -= keyid_bits;
+}
+
static void init_intel_energy_perf(struct cpuinfo_x86 *c)
{
u64 epb;
@@ -680,6 +763,9 @@ static void init_intel(struct cpuinfo_x86 *c)
if (cpu_has(c, X86_FEATURE_VMX))
detect_vmx_virtcap(c);
+ if (cpu_has(c, X86_FEATURE_TME))
+ detect_tme(c);
+
init_intel_energy_perf(c);
init_intel_misc_features(c);
diff --git a/arch/x86/kernel/cpu/intel_pconfig.c b/arch/x86/kernel/cpu/intel_pconfig.c
new file mode 100644
index 000000000000..0771a905b286
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_pconfig.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel PCONFIG instruction support.
+ *
+ * Copyright (C) 2017 Intel Corporation
+ *
+ * Author:
+ * Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
+ */
+
+#include <asm/cpufeature.h>
+#include <asm/intel_pconfig.h>
+
+#define PCONFIG_CPUID 0x1b
+
+#define PCONFIG_CPUID_SUBLEAF_MASK ((1 << 12) - 1)
+
+/* Subleaf type (EAX) for PCONFIG CPUID leaf (0x1B) */
+enum {
+ PCONFIG_CPUID_SUBLEAF_INVALID = 0,
+ PCONFIG_CPUID_SUBLEAF_TARGETID = 1,
+};
+
+/* Bitmask of supported targets */
+static u64 targets_supported __read_mostly;
+
+int pconfig_target_supported(enum pconfig_target target)
+{
+ /*
+ * We would need to re-think the implementation once we get > 64
+ * PCONFIG targets. Spec allows up to 2^32 targets.
+ */
+ BUILD_BUG_ON(PCONFIG_TARGET_NR >= 64);
+
+ if (WARN_ON_ONCE(target >= 64))
+ return 0;
+ return targets_supported & (1ULL << target);
+}
+
+static int __init intel_pconfig_init(void)
+{
+ int subleaf;
+
+ if (!boot_cpu_has(X86_FEATURE_PCONFIG))
+ return 0;
+
+ /*
+ * Scan subleafs of PCONFIG CPUID leaf.
+ *
+ * Subleafs of the same type need not to be consecutive.
+ *
+ * Stop on the first invalid subleaf type. All subleafs after the first
+ * invalid are invalid too.
+ */
+ for (subleaf = 0; subleaf < INT_MAX; subleaf++) {
+ struct cpuid_regs regs;
+
+ cpuid_count(PCONFIG_CPUID, subleaf,
+ &regs.eax, &regs.ebx, &regs.ecx, &regs.edx);
+
+ switch (regs.eax & PCONFIG_CPUID_SUBLEAF_MASK) {
+ case PCONFIG_CPUID_SUBLEAF_INVALID:
+ /* Stop on the first invalid subleaf */
+ goto out;
+ case PCONFIG_CPUID_SUBLEAF_TARGETID:
+ /* Mark supported PCONFIG targets */
+ if (regs.ebx < 64)
+ targets_supported |= (1ULL << regs.ebx);
+ if (regs.ecx < 64)
+ targets_supported |= (1ULL << regs.ecx);
+ if (regs.edx < 64)
+ targets_supported |= (1ULL << regs.edx);
+ break;
+ default:
+ /* Unknown CPUID.PCONFIG subleaf: ignore */
+ break;
+ }
+ }
+out:
+ return 0;
+}
+arch_initcall(intel_pconfig_init);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 231ad23b24a9..475cb4f5f14f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -491,7 +491,7 @@ static void do_inject(void)
unsigned int cpu = i_mce.extcpu;
u8 b = i_mce.bank;
- rdtscll(i_mce.tsc);
+ i_mce.tsc = rdtsc_ordered();
if (i_mce.misc)
i_mce.status |= MCI_STATUS_MISCV;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index e956eb267061..374d1aa66952 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -113,8 +113,6 @@ static inline void mce_register_injector_chain(struct notifier_block *nb) { }
static inline void mce_unregister_injector_chain(struct notifier_block *nb) { }
#endif
-extern struct mca_config mca_cfg;
-
#ifndef CONFIG_X86_64
/*
* On 32-bit systems it would be difficult to safely unmap a poison page
@@ -130,4 +128,61 @@ static inline void mce_unmap_kpfn(unsigned long pfn) {}
#define mce_unmap_kpfn mce_unmap_kpfn
#endif
+struct mca_config {
+ bool dont_log_ce;
+ bool cmci_disabled;
+ bool ignore_ce;
+
+ __u64 lmce_disabled : 1,
+ disabled : 1,
+ ser : 1,
+ recovery : 1,
+ bios_cmci_threshold : 1,
+ __reserved : 59;
+
+ u8 banks;
+ s8 bootlog;
+ int tolerant;
+ int monarch_timeout;
+ int panic_timeout;
+ u32 rip_msr;
+};
+
+extern struct mca_config mca_cfg;
+
+struct mce_vendor_flags {
+ /*
+ * Indicates that overflow conditions are not fatal, when set.
+ */
+ __u64 overflow_recov : 1,
+
+ /*
+ * (AMD) SUCCOR stands for S/W UnCorrectable error COntainment and
+ * Recovery. It indicates support for data poisoning in HW and deferred
+ * error interrupts.
+ */
+ succor : 1,
+
+ /*
+ * (AMD) SMCA: This bit indicates support for Scalable MCA which expands
+ * the register space for each MCA bank and also increases number of
+ * banks. Also, to accommodate the new banks and registers, the MCA
+ * register space is moved to a new MSR range.
+ */
+ smca : 1,
+
+ __reserved_0 : 61;
+};
+
+extern struct mce_vendor_flags mce_flags;
+
+struct mca_msr_regs {
+ u32 (*ctl) (int bank);
+ u32 (*status) (int bank);
+ u32 (*addr) (int bank);
+ u32 (*misc) (int bank);
+};
+
+extern struct mca_msr_regs msr_ops;
+
#endif /* __X86_MCE_INTERNAL_H__ */
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 466f47301334..42cf2880d0ed 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -273,7 +273,9 @@ static void __print_mce(struct mce *m)
static void print_mce(struct mce *m)
{
__print_mce(m);
- pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
+
+ if (m->cpuvendor != X86_VENDOR_AMD)
+ pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
}
#define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -1093,19 +1095,7 @@ static void mce_unmap_kpfn(unsigned long pfn)
* a legal address.
*/
-/*
- * Build time check to see if we have a spare virtual bit. Don't want
- * to leave this until run time because most developers don't have a
- * system that can exercise this code path. This will only become a
- * problem if/when we move beyond 5-level page tables.
- *
- * Hard code "9" here because cpp doesn't grok ilog2(PTRS_PER_PGD)
- */
-#if PGDIR_SHIFT + 9 < 63
decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
-#else
-#error "no unused virtual bit available"
-#endif
if (set_memory_np(decoy_addr, 1))
pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
@@ -1516,7 +1506,7 @@ static int __mcheck_cpu_cap_init(void)
mca_cfg.rip_msr = MSR_IA32_MCG_EIP;
if (cap & MCG_SER_P)
- mca_cfg.ser = true;
+ mca_cfg.ser = 1;
return 0;
}
@@ -1824,12 +1814,12 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
return;
if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) {
- mca_cfg.disabled = true;
+ mca_cfg.disabled = 1;
return;
}
if (mce_gen_pool_init()) {
- mca_cfg.disabled = true;
+ mca_cfg.disabled = 1;
pr_emerg("Couldn't allocate MCE records pool!\n");
return;
}
@@ -1907,11 +1897,11 @@ static int __init mcheck_enable(char *str)
if (*str == '=')
str++;
if (!strcmp(str, "off"))
- cfg->disabled = true;
+ cfg->disabled = 1;
else if (!strcmp(str, "no_cmci"))
cfg->cmci_disabled = true;
else if (!strcmp(str, "no_lmce"))
- cfg->lmce_disabled = true;
+ cfg->lmce_disabled = 1;
else if (!strcmp(str, "dont_log_ce"))
cfg->dont_log_ce = true;
else if (!strcmp(str, "ignore_ce"))
@@ -1919,9 +1909,9 @@ static int __init mcheck_enable(char *str)
else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog"))
cfg->bootlog = (str[0] == 'b');
else if (!strcmp(str, "bios_cmci_threshold"))
- cfg->bios_cmci_threshold = true;
+ cfg->bios_cmci_threshold = 1;
else if (!strcmp(str, "recovery"))
- cfg->recovery = true;
+ cfg->recovery = 1;
else if (isdigit(str[0])) {
if (get_option(&str, &cfg->tolerant) == 2)
get_option(&str, &(cfg->monarch_timeout));
@@ -2355,6 +2345,12 @@ static __init int mcheck_init_device(void)
{
int err;
+ /*
+ * Check if we have a spare virtual bit. This will only become
+ * a problem if/when we move beyond 5-level page tables.
+ */
+ MAYBE_BUILD_BUG_ON(__VIRTUAL_MASK_SHIFT >= 63);
+
if (!mce_available(&boot_cpu_data)) {
err = -EIO;
goto err_out;
@@ -2403,7 +2399,7 @@ device_initcall_sync(mcheck_init_device);
*/
static int __init mcheck_disable(char *str)
{
- mca_cfg.disabled = true;
+ mca_cfg.disabled = 1;
return 1;
}
__setup("nomce", mcheck_disable);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 0f32ad242324..f7666eef4a87 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -82,6 +82,7 @@ static struct smca_bank_name smca_names[] = {
[SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" },
[SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" },
[SMCA_DE] = { "decode_unit", "Decode Unit" },
+ [SMCA_RESERVED] = { "reserved", "Reserved" },
[SMCA_EX] = { "execution_unit", "Execution Unit" },
[SMCA_FP] = { "floating_point", "Floating Point Unit" },
[SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" },
@@ -110,14 +111,14 @@ const char *smca_get_long_name(enum smca_bank_types t)
}
EXPORT_SYMBOL_GPL(smca_get_long_name);
-static enum smca_bank_types smca_get_bank_type(struct mce *m)
+static enum smca_bank_types smca_get_bank_type(unsigned int bank)
{
struct smca_bank *b;
- if (m->bank >= N_SMCA_BANK_TYPES)
+ if (bank >= MAX_NR_BANKS)
return N_SMCA_BANK_TYPES;
- b = &smca_banks[m->bank];
+ b = &smca_banks[bank];
if (!b->hwid)
return N_SMCA_BANK_TYPES;
@@ -127,6 +128,9 @@ static enum smca_bank_types smca_get_bank_type(struct mce *m)
static struct smca_hwid smca_hwid_mcatypes[] = {
/* { bank_type, hwid_mcatype, xec_bitmap } */
+ /* Reserved type */
+ { SMCA_RESERVED, HWID_MCATYPE(0x00, 0x0), 0x0 },
+
/* ZN Core (HWID=0xB0) MCA types */
{ SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFEF },
{ SMCA_IF, HWID_MCATYPE(0xB0, 0x1), 0x3FFF },
@@ -427,35 +431,58 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
wrmsr(MSR_CU_DEF_ERR, low, high);
}
+static u32 smca_get_block_address(unsigned int cpu, unsigned int bank,
+ unsigned int block)
+{
+ u32 low, high;
+ u32 addr = 0;
+
+ if (smca_get_bank_type(bank) == SMCA_RESERVED)
+ return addr;
+
+ if (!block)
+ return MSR_AMD64_SMCA_MCx_MISC(bank);
+
+ /*
+ * For SMCA enabled processors, BLKPTR field of the first MISC register
+ * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4).
+ */
+ if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
+ return addr;
+
+ if (!(low & MCI_CONFIG_MCAX))
+ return addr;
+
+ if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
+ (low & MASK_BLKPTR_LO))
+ return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+
+ return addr;
+}
+
static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 high,
unsigned int bank, unsigned int block)
{
u32 addr = 0, offset = 0;
- if (mce_flags.smca) {
- if (!block) {
- addr = MSR_AMD64_SMCA_MCx_MISC(bank);
- } else {
- /*
- * For SMCA enabled processors, BLKPTR field of the
- * first MISC register (MCx_MISC0) indicates presence of
- * additional MISC register set (MISC1-4).
- */
- u32 low, high;
+ if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
+ return addr;
- if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
- return addr;
+ /* Get address from already initialized block. */
+ if (per_cpu(threshold_banks, cpu)) {
+ struct threshold_bank *bankp = per_cpu(threshold_banks, cpu)[bank];
- if (!(low & MCI_CONFIG_MCAX))
- return addr;
+ if (bankp && bankp->blocks) {
+ struct threshold_block *blockp = &bankp->blocks[block];
- if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
- (low & MASK_BLKPTR_LO))
- addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+ if (blockp)
+ return blockp->address;
}
- return addr;
}
+ if (mce_flags.smca)
+ return smca_get_block_address(cpu, bank, block);
+
/* Fall back to method we used for older processors: */
switch (block) {
case 0:
@@ -760,7 +787,7 @@ bool amd_mce_is_memory_error(struct mce *m)
u8 xec = (m->status >> 16) & 0x1f;
if (mce_flags.smca)
- return smca_get_bank_type(m) == SMCA_UMC && xec == 0x0;
+ return smca_get_bank_type(m->bank) == SMCA_UMC && xec == 0x0;
return m->bank == 4 && xec == 0x8;
}
@@ -1063,7 +1090,7 @@ static struct kobj_type threshold_ktype = {
static const char *get_name(unsigned int bank, struct threshold_block *b)
{
- unsigned int bank_type;
+ enum smca_bank_types bank_type;
if (!mce_flags.smca) {
if (b && bank == 4)
@@ -1072,11 +1099,10 @@ static const char *get_name(unsigned int bank, struct threshold_block *b)
return th_names[bank];
}
- if (!smca_banks[bank].hwid)
+ bank_type = smca_get_bank_type(bank);
+ if (bank_type >= N_SMCA_BANK_TYPES)
return NULL;
- bank_type = smca_banks[bank].hwid->bank_type;
-
if (b && bank_type == SMCA_UMC) {
if (b->block < ARRAY_SIZE(smca_umc_block_names))
return smca_umc_block_names[b->block];
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index a998e1a7d46f..48179928ff38 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -339,7 +339,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
return -EINVAL;
ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size);
- if (ret != UCODE_OK)
+ if (ret > UCODE_UPDATED)
return -EINVAL;
return 0;
@@ -683,27 +683,35 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
static enum ucode_state
load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
{
+ struct ucode_patch *p;
enum ucode_state ret;
/* free old equiv table */
free_equiv_cpu_table();
ret = __load_microcode_amd(family, data, size);
-
- if (ret != UCODE_OK)
+ if (ret != UCODE_OK) {
cleanup();
+ return ret;
+ }
-#ifdef CONFIG_X86_32
- /* save BSP's matching patch for early load */
- if (save) {
- struct ucode_patch *p = find_patch(0);
- if (p) {
- memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
- memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
- PATCH_MAX_SIZE));
- }
+ p = find_patch(0);
+ if (!p) {
+ return ret;
+ } else {
+ if (boot_cpu_data.microcode == p->patch_id)
+ return ret;
+
+ ret = UCODE_NEW;
}
-#endif
+
+ /* save BSP's matching patch for early load */
+ if (!save)
+ return ret;
+
+ memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
+ memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), PATCH_MAX_SIZE));
+
return ret;
}
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 70ecbc8099c9..10c4fc2c91f8 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -517,7 +517,29 @@ static int check_online_cpus(void)
return -EINVAL;
}
-static atomic_t late_cpus;
+static atomic_t late_cpus_in;
+static atomic_t late_cpus_out;
+
+static int __wait_for_cpus(atomic_t *t, long long timeout)
+{
+ int all_cpus = num_online_cpus();
+
+ atomic_inc(t);
+
+ while (atomic_read(t) < all_cpus) {
+ if (timeout < SPINUNIT) {
+ pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n",
+ all_cpus - atomic_read(t));
+ return 1;
+ }
+
+ ndelay(SPINUNIT);
+ timeout -= SPINUNIT;
+
+ touch_nmi_watchdog();
+ }
+ return 0;
+}
/*
* Returns:
@@ -527,30 +549,16 @@ static atomic_t late_cpus;
*/
static int __reload_late(void *info)
{
- unsigned int timeout = NSEC_PER_SEC;
- int all_cpus = num_online_cpus();
int cpu = smp_processor_id();
enum ucode_state err;
int ret = 0;
- atomic_dec(&late_cpus);
-
/*
* Wait for all CPUs to arrive. A load will not be attempted unless all
* CPUs show up.
* */
- while (atomic_read(&late_cpus)) {
- if (timeout < SPINUNIT) {
- pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n",
- atomic_read(&late_cpus));
- return -1;
- }
-
- ndelay(SPINUNIT);
- timeout -= SPINUNIT;
-
- touch_nmi_watchdog();
- }
+ if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC))
+ return -1;
spin_lock(&update_lock);
apply_microcode_local(&err);
@@ -558,15 +566,22 @@ static int __reload_late(void *info)
if (err > UCODE_NFOUND) {
pr_warn("Error reloading microcode on CPU %d\n", cpu);
- ret = -1;
- } else if (err == UCODE_UPDATED) {
+ return -1;
+ /* siblings return UCODE_OK because their engine got updated already */
+ } else if (err == UCODE_UPDATED || err == UCODE_OK) {
ret = 1;
+ } else {
+ return ret;
}
- atomic_inc(&late_cpus);
-
- while (atomic_read(&late_cpus) != all_cpus)
- cpu_relax();
+ /*
+ * Increase the wait timeout to a safe value here since we're
+ * serializing the microcode update and that could take a while on a
+ * large number of CPUs. And that is fine as the *actual* timeout will
+ * be determined by the last CPU finished updating and thus cut short.
+ */
+ if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC * num_online_cpus()))
+ panic("Timeout during microcode update!\n");
return ret;
}
@@ -579,12 +594,11 @@ static int microcode_reload_late(void)
{
int ret;
- atomic_set(&late_cpus, num_online_cpus());
+ atomic_set(&late_cpus_in, 0);
+ atomic_set(&late_cpus_out, 0);
ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
- if (ret < 0)
- return ret;
- else if (ret > 0)
+ if (ret > 0)
microcode_check();
return ret;
@@ -607,7 +621,7 @@ static ssize_t reload_store(struct device *dev,
return size;
tmp_ret = microcode_ops->request_microcode_fw(bsp, &microcode_pdev->dev, true);
- if (tmp_ret != UCODE_OK)
+ if (tmp_ret != UCODE_NEW)
return size;
get_online_cpus();
@@ -691,10 +705,8 @@ static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw)
if (system_state != SYSTEM_RUNNING)
return UCODE_NFOUND;
- ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev,
- refresh_fw);
-
- if (ustate == UCODE_OK) {
+ ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, refresh_fw);
+ if (ustate == UCODE_NEW) {
pr_debug("CPU%d updated upon init\n", cpu);
apply_microcode_on_target(cpu);
}
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 2aded9db1d42..32b8e5724f96 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -862,6 +862,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
unsigned int leftover = size;
unsigned int curr_mc_size = 0, new_mc_size = 0;
unsigned int csig, cpf;
+ enum ucode_state ret = UCODE_OK;
while (leftover) {
struct microcode_header_intel mc_header;
@@ -903,6 +904,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
new_mc = mc;
new_mc_size = mc_size;
mc = NULL; /* trigger new vmalloc */
+ ret = UCODE_NEW;
}
ucode_ptr += mc_size;
@@ -932,7 +934,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
cpu, new_rev, uci->cpu_sig.rev);
- return UCODE_OK;
+ return ret;
}
static int get_ucode_fw(void *to, const void *from, size_t n)
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 0931a105ffe1..1d300f96df4b 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -40,6 +40,7 @@
#include <linux/notifier.h>
#include <linux/uaccess.h>
#include <linux/gfp.h>
+#include <linux/completion.h>
#include <asm/processor.h>
#include <asm/msr.h>
@@ -47,19 +48,27 @@
static struct class *cpuid_class;
static enum cpuhp_state cpuhp_cpuid_state;
+struct cpuid_regs_done {
+ struct cpuid_regs regs;
+ struct completion done;
+};
+
static void cpuid_smp_cpuid(void *cmd_block)
{
- struct cpuid_regs *cmd = (struct cpuid_regs *)cmd_block;
+ struct cpuid_regs_done *cmd = cmd_block;
+
+ cpuid_count(cmd->regs.eax, cmd->regs.ecx,
+ &cmd->regs.eax, &cmd->regs.ebx,
+ &cmd->regs.ecx, &cmd->regs.edx);
- cpuid_count(cmd->eax, cmd->ecx,
- &cmd->eax, &cmd->ebx, &cmd->ecx, &cmd->edx);
+ complete(&cmd->done);
}
static ssize_t cpuid_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
char __user *tmp = buf;
- struct cpuid_regs cmd;
+ struct cpuid_regs_done cmd;
int cpu = iminor(file_inode(file));
u64 pos = *ppos;
ssize_t bytes = 0;
@@ -68,19 +77,28 @@ static ssize_t cpuid_read(struct file *file, char __user *buf,
if (count % 16)
return -EINVAL; /* Invalid chunk size */
+ init_completion(&cmd.done);
for (; count; count -= 16) {
- cmd.eax = pos;
- cmd.ecx = pos >> 32;
- err = smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1);
+ call_single_data_t csd = {
+ .func = cpuid_smp_cpuid,
+ .info = &cmd,
+ };
+
+ cmd.regs.eax = pos;
+ cmd.regs.ecx = pos >> 32;
+
+ err = smp_call_function_single_async(cpu, &csd);
if (err)
break;
- if (copy_to_user(tmp, &cmd, 16)) {
+ wait_for_completion(&cmd.done);
+ if (copy_to_user(tmp, &cmd.regs, 16)) {
err = -EFAULT;
break;
}
tmp += 16;
bytes += 16;
*ppos = ++pos;
+ reinit_completion(&cmd.done);
}
return bytes ? bytes : err;
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 10e74d4778a1..1f6680427ff0 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -199,9 +199,10 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
#ifdef CONFIG_X86_IO_APIC
/* Prevent crash_kexec() from deadlocking on ioapic_lock. */
ioapic_zap_locks();
- disable_IO_APIC();
+ clear_IO_APIC();
#endif
lapic_shutdown();
+ restore_boot_irq_mode();
#ifdef CONFIG_HPET_TIMER
hpet_disable();
#endif
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 25de5f6ca997..f39f3a06c26f 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -11,6 +11,7 @@
#include <linux/of_address.h>
#include <linux/of_platform.h>
#include <linux/of_irq.h>
+#include <linux/libfdt.h>
#include <linux/slab.h>
#include <linux/pci.h>
#include <linux/of_pci.h>
@@ -130,34 +131,52 @@ static void __init dtb_setup_hpet(void)
#endif
}
+#ifdef CONFIG_X86_LOCAL_APIC
+
+static void __init dtb_cpu_setup(void)
+{
+ struct device_node *dn;
+ u32 apic_id, version;
+ int ret;
+
+ version = GET_APIC_VERSION(apic_read(APIC_LVR));
+ for_each_node_by_type(dn, "cpu") {
+ ret = of_property_read_u32(dn, "reg", &apic_id);
+ if (ret < 0) {
+ pr_warn("%pOF: missing local APIC ID\n", dn);
+ continue;
+ }
+ generic_processor_info(apic_id, version);
+ }
+}
+
static void __init dtb_lapic_setup(void)
{
-#ifdef CONFIG_X86_LOCAL_APIC
struct device_node *dn;
struct resource r;
+ unsigned long lapic_addr = APIC_DEFAULT_PHYS_BASE;
int ret;
dn = of_find_compatible_node(NULL, NULL, "intel,ce4100-lapic");
- if (!dn)
- return;
-
- ret = of_address_to_resource(dn, 0, &r);
- if (WARN_ON(ret))
- return;
+ if (dn) {
+ ret = of_address_to_resource(dn, 0, &r);
+ if (WARN_ON(ret))
+ return;
+ lapic_addr = r.start;
+ }
/* Did the boot loader setup the local APIC ? */
if (!boot_cpu_has(X86_FEATURE_APIC)) {
- if (apic_force_enable(r.start))
+ if (apic_force_enable(lapic_addr))
return;
}
smp_found_config = 1;
pic_mode = 1;
- register_lapic_address(r.start);
- generic_processor_info(boot_cpu_physical_apicid,
- GET_APIC_VERSION(apic_read(APIC_LVR)));
-#endif
+ register_lapic_address(lapic_addr);
}
+#endif /* CONFIG_X86_LOCAL_APIC */
+
#ifdef CONFIG_X86_IO_APIC
static unsigned int ioapic_id;
@@ -194,19 +213,22 @@ static struct of_ioapic_type of_ioapic_type[] =
static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs, void *arg)
{
- struct of_phandle_args *irq_data = (void *)arg;
+ struct irq_fwspec *fwspec = (struct irq_fwspec *)arg;
struct of_ioapic_type *it;
struct irq_alloc_info tmp;
+ int type_index;
- if (WARN_ON(irq_data->args_count < 2))
+ if (WARN_ON(fwspec->param_count < 2))
return -EINVAL;
- if (irq_data->args[1] >= ARRAY_SIZE(of_ioapic_type))
+
+ type_index = fwspec->param[1];
+ if (type_index >= ARRAY_SIZE(of_ioapic_type))
return -EINVAL;
- it = &of_ioapic_type[irq_data->args[1]];
+ it = &of_ioapic_type[type_index];
ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity);
tmp.ioapic_id = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain));
- tmp.ioapic_pin = irq_data->args[0];
+ tmp.ioapic_pin = fwspec->param[0];
return mp_irqdomain_alloc(domain, virq, nr_irqs, &tmp);
}
@@ -255,11 +277,14 @@ static void __init dtb_ioapic_setup(void) {}
static void __init dtb_apic_setup(void)
{
+#ifdef CONFIG_X86_LOCAL_APIC
dtb_lapic_setup();
+ dtb_cpu_setup();
+#endif
dtb_ioapic_setup();
}
-#ifdef CONFIG_OF_FLATTREE
+#ifdef CONFIG_OF_EARLY_FLATTREE
static void __init x86_flattree_get_config(void)
{
u32 size, map_len;
@@ -270,14 +295,15 @@ static void __init x86_flattree_get_config(void)
map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128);
- initial_boot_params = dt = early_memremap(initial_dtb, map_len);
- size = of_get_flat_dt_size();
+ dt = early_memremap(initial_dtb, map_len);
+ size = fdt_totalsize(dt);
if (map_len < size) {
early_memunmap(dt, map_len);
- initial_boot_params = dt = early_memremap(initial_dtb, size);
+ dt = early_memremap(initial_dtb, size);
map_len = size;
}
+ early_init_dt_verify(dt);
unflatten_and_copy_device_tree();
early_memunmap(dt, map_len);
}
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index a2d8a3908670..18fa9d74c182 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -24,7 +24,7 @@
int panic_on_unrecovered_nmi;
int panic_on_io_nmi;
-unsigned int code_bytes = 64;
+static unsigned int code_bytes = 64;
static int die_counter;
bool in_task_stack(unsigned long *stack, struct task_struct *task,
@@ -375,3 +375,50 @@ static int __init code_bytes_setup(char *s)
return 1;
}
__setup("code_bytes=", code_bytes_setup);
+
+void show_regs(struct pt_regs *regs)
+{
+ bool all = true;
+ int i;
+
+ show_regs_print_info(KERN_DEFAULT);
+
+ if (IS_ENABLED(CONFIG_X86_32))
+ all = !user_mode(regs);
+
+ __show_regs(regs, all);
+
+ /*
+ * When in-kernel, we also print out the stack and code at the
+ * time of the fault..
+ */
+ if (!user_mode(regs)) {
+ unsigned int code_prologue = code_bytes * 43 / 64;
+ unsigned int code_len = code_bytes;
+ unsigned char c;
+ u8 *ip;
+
+ show_trace_log_lvl(current, regs, NULL, KERN_DEFAULT);
+
+ printk(KERN_DEFAULT "Code: ");
+
+ ip = (u8 *)regs->ip - code_prologue;
+ if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
+ /* try starting at IP */
+ ip = (u8 *)regs->ip;
+ code_len = code_len - code_prologue + 1;
+ }
+ for (i = 0; i < code_len; i++, ip++) {
+ if (ip < (u8 *)PAGE_OFFSET ||
+ probe_kernel_address(ip, c)) {
+ pr_cont(" Bad RIP value.");
+ break;
+ }
+ if (ip == (u8 *)regs->ip)
+ pr_cont("<%02x> ", c);
+ else
+ pr_cont("%02x ", c);
+ }
+ }
+ pr_cont("\n");
+}
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 04170f63e3a1..cd53f3030e40 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -127,45 +127,3 @@ unknown:
info->type = STACK_TYPE_UNKNOWN;
return -EINVAL;
}
-
-void show_regs(struct pt_regs *regs)
-{
- int i;
-
- show_regs_print_info(KERN_EMERG);
- __show_regs(regs, !user_mode(regs));
-
- /*
- * When in-kernel, we also print out the stack and code at the
- * time of the fault..
- */
- if (!user_mode(regs)) {
- unsigned int code_prologue = code_bytes * 43 / 64;
- unsigned int code_len = code_bytes;
- unsigned char c;
- u8 *ip;
-
- show_trace_log_lvl(current, regs, NULL, KERN_EMERG);
-
- pr_emerg("Code:");
-
- ip = (u8 *)regs->ip - code_prologue;
- if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
- /* try starting at IP */
- ip = (u8 *)regs->ip;
- code_len = code_len - code_prologue + 1;
- }
- for (i = 0; i < code_len; i++, ip++) {
- if (ip < (u8 *)PAGE_OFFSET ||
- probe_kernel_address(ip, c)) {
- pr_cont(" Bad EIP value.");
- break;
- }
- if (ip == (u8 *)regs->ip)
- pr_cont(" <%02x>", c);
- else
- pr_cont(" %02x", c);
- }
- }
- pr_cont("\n");
-}
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 563e28d14f2c..5cdb9e84da57 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -149,45 +149,3 @@ unknown:
info->type = STACK_TYPE_UNKNOWN;
return -EINVAL;
}
-
-void show_regs(struct pt_regs *regs)
-{
- int i;
-
- show_regs_print_info(KERN_DEFAULT);
- __show_regs(regs, 1);
-
- /*
- * When in-kernel, we also print out the stack and code at the
- * time of the fault..
- */
- if (!user_mode(regs)) {
- unsigned int code_prologue = code_bytes * 43 / 64;
- unsigned int code_len = code_bytes;
- unsigned char c;
- u8 *ip;
-
- show_trace_log_lvl(current, regs, NULL, KERN_DEFAULT);
-
- printk(KERN_DEFAULT "Code: ");
-
- ip = (u8 *)regs->ip - code_prologue;
- if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
- /* try starting at IP */
- ip = (u8 *)regs->ip;
- code_len = code_len - code_prologue + 1;
- }
- for (i = 0; i < code_len; i++, ip++) {
- if (ip < (u8 *)PAGE_OFFSET ||
- probe_kernel_address(ip, c)) {
- pr_cont(" Bad RIP value.");
- break;
- }
- if (ip == (u8 *)regs->ip)
- pr_cont("<%02x> ", c);
- else
- pr_cont("%02x ", c);
- }
- }
- pr_cont("\n");
-}
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 71c11ad5643e..6a2cb1442e05 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -924,6 +924,24 @@ static int __init parse_memmap_one(char *p)
} else if (*p == '!') {
start_at = memparse(p+1, &p);
e820__range_add(start_at, mem_size, E820_TYPE_PRAM);
+ } else if (*p == '%') {
+ enum e820_type from = 0, to = 0;
+
+ start_at = memparse(p + 1, &p);
+ if (*p == '-')
+ from = simple_strtoull(p + 1, &p, 0);
+ if (*p == '+')
+ to = simple_strtoull(p + 1, &p, 0);
+ if (*p != '\0')
+ return -EINVAL;
+ if (from && to)
+ e820__range_update(start_at, mem_size, from, to);
+ else if (to)
+ e820__range_add(start_at, mem_size, to);
+ else if (from)
+ e820__range_remove(start_at, mem_size, from, 1);
+ else
+ e820__range_remove(start_at, mem_size, 0, 0);
} else {
e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1);
}
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 7ba5d819ebe3..0c855deee165 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -32,6 +32,11 @@
#include <asm/microcode.h>
#include <asm/kasan.h>
+#ifdef CONFIG_X86_5LEVEL
+#undef pgtable_l5_enabled
+#define pgtable_l5_enabled __pgtable_l5_enabled
+#endif
+
/*
* Manage page tables very early on.
*/
@@ -39,6 +44,24 @@ extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
static unsigned int __initdata next_early_pgt;
pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
+#ifdef CONFIG_X86_5LEVEL
+unsigned int __pgtable_l5_enabled __ro_after_init;
+EXPORT_SYMBOL(__pgtable_l5_enabled);
+unsigned int pgdir_shift __ro_after_init = 39;
+EXPORT_SYMBOL(pgdir_shift);
+unsigned int ptrs_per_p4d __ro_after_init = 1;
+EXPORT_SYMBOL(ptrs_per_p4d);
+#endif
+
+#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
+unsigned long page_offset_base __ro_after_init = __PAGE_OFFSET_BASE_L4;
+EXPORT_SYMBOL(page_offset_base);
+unsigned long vmalloc_base __ro_after_init = __VMALLOC_BASE_L4;
+EXPORT_SYMBOL(vmalloc_base);
+unsigned long vmemmap_base __ro_after_init = __VMEMMAP_BASE_L4;
+EXPORT_SYMBOL(vmemmap_base);
+#endif
+
#define __head __section(.head.text)
static void __head *fixup_pointer(void *ptr, unsigned long physaddr)
@@ -46,6 +69,41 @@ static void __head *fixup_pointer(void *ptr, unsigned long physaddr)
return ptr - (void *)_text + (void *)physaddr;
}
+static unsigned long __head *fixup_long(void *ptr, unsigned long physaddr)
+{
+ return fixup_pointer(ptr, physaddr);
+}
+
+#ifdef CONFIG_X86_5LEVEL
+static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr)
+{
+ return fixup_pointer(ptr, physaddr);
+}
+
+static bool __head check_la57_support(unsigned long physaddr)
+{
+ if (native_cpuid_eax(0) < 7)
+ return false;
+
+ if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31))))
+ return false;
+
+ *fixup_int(&pgtable_l5_enabled, physaddr) = 1;
+ *fixup_int(&pgdir_shift, physaddr) = 48;
+ *fixup_int(&ptrs_per_p4d, physaddr) = 512;
+ *fixup_long(&page_offset_base, physaddr) = __PAGE_OFFSET_BASE_L5;
+ *fixup_long(&vmalloc_base, physaddr) = __VMALLOC_BASE_L5;
+ *fixup_long(&vmemmap_base, physaddr) = __VMEMMAP_BASE_L5;
+
+ return true;
+}
+#else
+static bool __head check_la57_support(unsigned long physaddr)
+{
+ return false;
+}
+#endif
+
unsigned long __head __startup_64(unsigned long physaddr,
struct boot_params *bp)
{
@@ -55,9 +113,12 @@ unsigned long __head __startup_64(unsigned long physaddr,
p4dval_t *p4d;
pudval_t *pud;
pmdval_t *pmd, pmd_entry;
+ bool la57;
int i;
unsigned int *next_pgt_ptr;
+ la57 = check_la57_support(physaddr);
+
/* Is the address too large? */
if (physaddr >> MAX_PHYSMEM_BITS)
for (;;);
@@ -81,9 +142,14 @@ unsigned long __head __startup_64(unsigned long physaddr,
/* Fixup the physical addresses in the page table */
pgd = fixup_pointer(&early_top_pgt, physaddr);
- pgd[pgd_index(__START_KERNEL_map)] += load_delta;
-
- if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+ p = pgd + pgd_index(__START_KERNEL_map);
+ if (la57)
+ *p = (unsigned long)level4_kernel_pgt;
+ else
+ *p = (unsigned long)level3_kernel_pgt;
+ *p += _PAGE_TABLE_NOENC - __START_KERNEL_map + load_delta;
+
+ if (la57) {
p4d = fixup_pointer(&level4_kernel_pgt, physaddr);
p4d[511] += load_delta;
}
@@ -108,7 +174,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask();
- if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+ if (la57) {
p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
@@ -154,8 +220,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
* Fixup phys_base - remove the memory encryption mask to obtain
* the true physical address.
*/
- p = fixup_pointer(&phys_base, physaddr);
- *p += load_delta - sme_get_me_mask();
+ *fixup_long(&phys_base, physaddr) += load_delta - sme_get_me_mask();
/* Encrypt the kernel and related (if SME is active) */
sme_encrypt_kernel(bp);
@@ -206,7 +271,7 @@ again:
* critical -- __PAGE_OFFSET would point us back into the dynamic
* range and we might end up looping forever...
*/
- if (!IS_ENABLED(CONFIG_X86_5LEVEL))
+ if (!pgtable_l5_enabled)
p4d_p = pgd_p;
else if (pgd)
p4d_p = (p4dval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base);
@@ -322,7 +387,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
BUILD_BUG_ON((__START_KERNEL_map & ~PMD_MASK) != 0);
BUILD_BUG_ON((MODULES_VADDR & ~PMD_MASK) != 0);
BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL));
- BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) ==
+ MAYBE_BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) ==
(__START_KERNEL & PGDIR_MASK)));
BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END);
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 0f545b3cf926..48385c1074a5 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -39,12 +39,12 @@
*
*/
+#define l4_index(x) (((x) >> 39) & 511)
#define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
-#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH)
-PGD_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE)
-PGD_START_KERNEL = pgd_index(__START_KERNEL_map)
-#endif
+L4_PAGE_OFFSET = l4_index(__PAGE_OFFSET_BASE_L4)
+L4_START_KERNEL = l4_index(__START_KERNEL_map)
+
L3_START_KERNEL = pud_index(__START_KERNEL_map)
.text
@@ -125,7 +125,10 @@ ENTRY(secondary_startup_64)
/* Enable PAE mode, PGE and LA57 */
movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx
#ifdef CONFIG_X86_5LEVEL
+ testl $1, __pgtable_l5_enabled(%rip)
+ jz 1f
orl $X86_CR4_LA57, %ecx
+1:
#endif
movq %rcx, %cr4
@@ -374,12 +377,7 @@ GLOBAL(name)
__INITDATA
NEXT_PGD_PAGE(early_top_pgt)
- .fill 511,8,0
-#ifdef CONFIG_X86_5LEVEL
- .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
-#else
- .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
-#endif
+ .fill 512,8,0
.fill PTI_USER_PGD_FILL,8,0
NEXT_PAGE(early_dynamic_pgts)
@@ -390,9 +388,9 @@ NEXT_PAGE(early_dynamic_pgts)
#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH)
NEXT_PGD_PAGE(init_top_pgt)
.quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
- .org init_top_pgt + PGD_PAGE_OFFSET*8, 0
+ .org init_top_pgt + L4_PAGE_OFFSET*8, 0
.quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
- .org init_top_pgt + PGD_START_KERNEL*8, 0
+ .org init_top_pgt + L4_START_KERNEL*8, 0
/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
.quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
.fill PTI_USER_PGD_FILL,8,0
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 56d99be3706a..2c3a1b4294eb 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -140,6 +140,9 @@ static const __initconst struct idt_data apic_idts[] = {
# ifdef CONFIG_IRQ_WORK
INTG(IRQ_WORK_VECTOR, irq_work_interrupt),
# endif
+#ifdef CONFIG_X86_UV
+ INTG(UV_BAU_MESSAGE, uv_bau_message_intr1),
+#endif
INTG(SPURIOUS_APIC_VECTOR, spurious_interrupt),
INTG(ERROR_APIC_VECTOR, error_interrupt),
#endif
@@ -160,7 +163,6 @@ static const __initconst struct idt_data early_pf_idts[] = {
*/
static const __initconst struct idt_data dbg_idts[] = {
INTG(X86_TRAP_DB, debug),
- INTG(X86_TRAP_BP, int3),
};
#endif
@@ -183,7 +185,6 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss;
static const __initconst struct idt_data ist_idts[] = {
ISTG(X86_TRAP_DB, debug, DEBUG_STACK),
ISTG(X86_TRAP_NMI, nmi, NMI_STACK),
- SISTG(X86_TRAP_BP, int3, DEBUG_STACK),
ISTG(X86_TRAP_DF, double_fault, DOUBLEFAULT_STACK),
#ifdef CONFIG_X86_MCE
ISTG(X86_TRAP_MC, &machine_check, MCE_STACK),
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 38deafebb21b..0fe1c8782208 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -23,7 +23,7 @@
/*
* this changes the io permissions bitmap in the current task.
*/
-SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on)
+long ksys_ioperm(unsigned long from, unsigned long num, int turn_on)
{
struct thread_struct *t = &current->thread;
struct tss_struct *tss;
@@ -96,6 +96,11 @@ SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on)
return 0;
}
+SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on)
+{
+ return ksys_ioperm(from, num, turn_on);
+}
+
/*
* sys_iopl has to be used when you want to access the IO ports
* beyond the 0x3ff range: to get the full 65536 ports bitmapped
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index a539410c4ea9..772196c1b8c4 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -61,9 +61,14 @@ void __init init_ISA_irqs(void)
struct irq_chip *chip = legacy_pic->chip;
int i;
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
+ /*
+ * Try to set up the through-local-APIC virtual wire mode earlier.
+ *
+ * On some 32-bit UP machines, whose APIC has been disabled by BIOS
+ * and then got re-enabled by "lapic", it hangs at boot time without this.
+ */
init_bsp_APIC();
-#endif
+
legacy_pic->init(0);
for (i = 0; i < nr_legacy_irqs(); i++)
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index b68fd895235a..fa183a131edc 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -124,6 +124,14 @@ static int __init jailhouse_pci_arch_init(void)
if (pcibios_last_bus < 0)
pcibios_last_bus = 0xff;
+#ifdef CONFIG_PCI_MMCONFIG
+ if (setup_data.pci_mmconfig_base) {
+ pci_mmconfig_add(0, 0, pcibios_last_bus,
+ setup_data.pci_mmconfig_base);
+ pci_mmcfg_arch_init();
+ }
+#endif
+
return 0;
}
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index bc1a27280c4b..fae86e36e399 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -546,7 +546,7 @@ static void __init kvm_guest_init(void)
}
if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
- !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
+ kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -635,7 +635,7 @@ static __init int kvm_setup_pv_tlb_flush(void)
int cpu;
if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
- !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+ kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
for_each_possible_cpu(cpu) {
zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
GFP_KERNEL, cpu_to_node(cpu));
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index edfede768688..60cdec6628b0 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -195,11 +195,11 @@ void machine_kexec(struct kimage *image)
/*
* We need to put APICs in legacy mode so that we can
* get timer interrupts in second kernel. kexec/kdump
- * paths already have calls to disable_IO_APIC() in
- * one form or other. kexec jump path also need
- * one.
+ * paths already have calls to restore_boot_irq_mode()
+ * in one form or other. kexec jump path also need one.
*/
- disable_IO_APIC();
+ clear_IO_APIC();
+ restore_boot_irq_mode();
#endif
}
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 3b7427aa7d85..93bd4fb603d1 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -293,11 +293,11 @@ void machine_kexec(struct kimage *image)
/*
* We need to put APICs in legacy mode so that we can
* get timer interrupts in second kernel. kexec/kdump
- * paths already have calls to disable_IO_APIC() in
- * one form or other. kexec jump path also need
- * one.
+ * paths already have calls to restore_boot_irq_mode()
+ * in one form or other. kexec jump path also need one.
*/
- disable_IO_APIC();
+ clear_IO_APIC();
+ restore_boot_irq_mode();
#endif
}
@@ -350,6 +350,7 @@ void arch_crash_save_vmcoreinfo(void)
{
VMCOREINFO_NUMBER(phys_base);
VMCOREINFO_SYMBOL(init_top_pgt);
+ VMCOREINFO_NUMBER(pgtable_l5_enabled);
#ifdef CONFIG_NUMA
VMCOREINFO_SYMBOL(node_data);
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 35c461f21815..bbfc8b1e9104 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -33,6 +33,7 @@
#include <linux/string.h>
#include <linux/crash_dump.h>
#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
#include <linux/bitmap.h>
#include <linux/pci_ids.h>
#include <linux/pci.h>
@@ -445,8 +446,6 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size,
npages = size >> PAGE_SHIFT;
order = get_order(size);
- flag &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
-
/* alloc enough pages (and possibly more) */
ret = (void *)__get_free_pages(flag, order);
if (!ret)
@@ -493,7 +492,7 @@ static const struct dma_map_ops calgary_dma_ops = {
.map_page = calgary_map_page,
.unmap_page = calgary_unmap_page,
.mapping_error = calgary_mapping_error,
- .dma_supported = x86_dma_supported,
+ .dma_supported = dma_direct_supported,
};
static inline void __iomem * busno_to_bbar(unsigned char num)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index df7ab02f959f..14437116ffea 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -18,7 +18,7 @@
static int forbid_dac __read_mostly;
-const struct dma_map_ops *dma_ops = &nommu_dma_ops;
+const struct dma_map_ops *dma_ops = &dma_direct_ops;
EXPORT_SYMBOL(dma_ops);
static int iommu_sac_force __read_mostly;
@@ -76,70 +76,12 @@ void __init pci_iommu_alloc(void)
}
}
}
-void *dma_generic_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_addr, gfp_t flag,
- unsigned long attrs)
-{
- unsigned long dma_mask;
- struct page *page;
- unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
- dma_addr_t addr;
-
- dma_mask = dma_alloc_coherent_mask(dev, flag);
-
-again:
- page = NULL;
- /* CMA can be used only in the context which permits sleeping */
- if (gfpflags_allow_blocking(flag)) {
- page = dma_alloc_from_contiguous(dev, count, get_order(size),
- flag);
- if (page) {
- addr = phys_to_dma(dev, page_to_phys(page));
- if (addr + size > dma_mask) {
- dma_release_from_contiguous(dev, page, count);
- page = NULL;
- }
- }
- }
- /* fallback */
- if (!page)
- page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
- if (!page)
- return NULL;
-
- addr = phys_to_dma(dev, page_to_phys(page));
- if (addr + size > dma_mask) {
- __free_pages(page, get_order(size));
-
- if (dma_mask < DMA_BIT_MASK(32) && !(flag & GFP_DMA)) {
- flag = (flag & ~GFP_DMA32) | GFP_DMA;
- goto again;
- }
-
- return NULL;
- }
- memset(page_address(page), 0, size);
- *dma_addr = addr;
- return page_address(page);
-}
-
-void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_addr, unsigned long attrs)
-{
- unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
- struct page *page = virt_to_page(vaddr);
-
- if (!dma_release_from_contiguous(dev, page, count))
- free_pages((unsigned long)vaddr, get_order(size));
-}
bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp)
{
if (!*dev)
*dev = &x86_dma_fallback_dev;
- *gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp);
-
if (!is_device_dma_capable(*dev))
return false;
return true;
@@ -245,16 +187,6 @@ int arch_dma_supported(struct device *dev, u64 mask)
}
EXPORT_SYMBOL(arch_dma_supported);
-int x86_dma_supported(struct device *dev, u64 mask)
-{
- /* Copied from i386. Doesn't make much sense, because it will
- only work for pci_alloc_coherent.
- The caller just has to use GFP_DMA in this case. */
- if (mask < DMA_BIT_MASK(24))
- return 0;
- return 1;
-}
-
static int __init pci_iommu_init(void)
{
struct iommu_table_entry *p;
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 618285e475c6..ac7ea3a8242f 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -37,7 +37,6 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
WARN_ON(size == 0);
if (!check_addr("map_single", dev, bus, size))
return NOMMU_MAPPING_ERROR;
- flush_write_buffers();
return bus;
}
@@ -72,25 +71,9 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
return 0;
s->dma_length = s->length;
}
- flush_write_buffers();
return nents;
}
-static void nommu_sync_single_for_device(struct device *dev,
- dma_addr_t addr, size_t size,
- enum dma_data_direction dir)
-{
- flush_write_buffers();
-}
-
-
-static void nommu_sync_sg_for_device(struct device *dev,
- struct scatterlist *sg, int nelems,
- enum dma_data_direction dir)
-{
- flush_write_buffers();
-}
-
static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
return dma_addr == NOMMU_MAPPING_ERROR;
@@ -101,8 +84,6 @@ const struct dma_map_ops nommu_dma_ops = {
.free = dma_generic_free_coherent,
.map_sg = nommu_map_sg,
.map_page = nommu_map_page,
- .sync_single_for_device = nommu_sync_single_for_device,
- .sync_sg_for_device = nommu_sync_sg_for_device,
.is_phys = 1,
.mapping_error = nommu_mapping_error,
.dma_supported = x86_dma_supported,
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 0ee0f8f34251..661583662430 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -17,52 +17,6 @@
int swiotlb __read_mostly;
-void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
- dma_addr_t *dma_handle, gfp_t flags,
- unsigned long attrs)
-{
- void *vaddr;
-
- /*
- * Don't print a warning when the first allocation attempt fails.
- * swiotlb_alloc_coherent() will print a warning when the DMA
- * memory allocation ultimately failed.
- */
- flags |= __GFP_NOWARN;
-
- vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags,
- attrs);
- if (vaddr)
- return vaddr;
-
- return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags);
-}
-
-void x86_swiotlb_free_coherent(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_addr,
- unsigned long attrs)
-{
- if (is_swiotlb_buffer(dma_to_phys(dev, dma_addr)))
- swiotlb_free_coherent(dev, size, vaddr, dma_addr);
- else
- dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs);
-}
-
-static const struct dma_map_ops x86_swiotlb_dma_ops = {
- .mapping_error = swiotlb_dma_mapping_error,
- .alloc = x86_swiotlb_alloc_coherent,
- .free = x86_swiotlb_free_coherent,
- .sync_single_for_cpu = swiotlb_sync_single_for_cpu,
- .sync_single_for_device = swiotlb_sync_single_for_device,
- .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
- .sync_sg_for_device = swiotlb_sync_sg_for_device,
- .map_sg = swiotlb_map_sg_attrs,
- .unmap_sg = swiotlb_unmap_sg_attrs,
- .map_page = swiotlb_map_page,
- .unmap_page = swiotlb_unmap_page,
- .dma_supported = NULL,
-};
-
/*
* pci_swiotlb_detect_override - set swiotlb to 1 if necessary
*
@@ -112,7 +66,7 @@ void __init pci_swiotlb_init(void)
{
if (swiotlb) {
swiotlb_init(0);
- dma_ops = &x86_swiotlb_dma_ops;
+ dma_ops = &swiotlb_dma_ops;
}
}
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 2126b9d27c34..725624b6c0c0 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -666,7 +666,7 @@ void native_machine_shutdown(void)
* Even without the erratum, it still makes sense to quiet IO APIC
* before disabling Local APIC.
*/
- disable_IO_APIC();
+ clear_IO_APIC();
#endif
#ifdef CONFIG_SMP
@@ -680,6 +680,7 @@ void native_machine_shutdown(void)
#endif
lapic_shutdown();
+ restore_boot_irq_mode();
#ifdef CONFIG_HPET_TIMER
hpet_disable();
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 69ac9cb9cac6..f7b82ed7b5b5 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -41,11 +41,11 @@ EXPORT_SYMBOL(rtc_lock);
*/
int mach_set_rtc_mmss(const struct timespec *now)
{
- unsigned long nowtime = now->tv_sec;
+ unsigned long long nowtime = now->tv_sec;
struct rtc_time tm;
int retval = 0;
- rtc_time_to_tm(nowtime, &tm);
+ rtc_time64_to_tm(nowtime, &tm);
if (!rtc_valid_tm(&tm)) {
retval = mc146818_set_time(&tm);
if (retval)
@@ -53,7 +53,7 @@ int mach_set_rtc_mmss(const struct timespec *now)
__func__, retval);
} else {
printk(KERN_ERR
- "%s: Invalid RTC value: write of %lx to RTC failed\n",
+ "%s: Invalid RTC value: write of %llx to RTC failed\n",
__func__, nowtime);
retval = -EINVAL;
}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 4c616be28506..6285697b6e56 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -189,9 +189,7 @@ struct ist_info ist_info;
#endif
#else
-struct cpuinfo_x86 boot_cpu_data __read_mostly = {
- .x86_phys_bits = MAX_PHYSMEM_BITS,
-};
+struct cpuinfo_x86 boot_cpu_data __read_mostly;
EXPORT_SYMBOL(boot_cpu_data);
#endif
@@ -851,6 +849,7 @@ void __init setup_arch(char **cmdline_p)
__flush_tlb_all();
#else
printk(KERN_INFO "Command line: %s\n", boot_command_line);
+ boot_cpu_data.x86_phys_bits = MAX_PHYSMEM_BITS;
#endif
/*
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 4cdc0b27ec82..da270b95fe4d 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -25,6 +25,7 @@
#include <linux/user-return-notifier.h>
#include <linux/uprobes.h>
#include <linux/context_tracking.h>
+#include <linux/syscalls.h>
#include <asm/processor.h>
#include <asm/ucontext.h>
@@ -601,7 +602,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
* Do a signal return; undo the signal stack.
*/
#ifdef CONFIG_X86_32
-asmlinkage unsigned long sys_sigreturn(void)
+SYSCALL_DEFINE0(sigreturn)
{
struct pt_regs *regs = current_pt_regs();
struct sigframe __user *frame;
@@ -633,7 +634,7 @@ badframe:
}
#endif /* CONFIG_X86_32 */
-asmlinkage long sys_rt_sigreturn(void)
+SYSCALL_DEFINE0(rt_sigreturn)
{
struct pt_regs *regs = current_pt_regs();
struct rt_sigframe __user *frame;
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index 676774b9bb8d..a3f15ed545b5 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -97,7 +97,7 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
if (off & ~PAGE_MASK)
goto out;
- error = sys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT);
+ error = ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT);
out:
return error;
}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 3d9b2308e7fa..03f3d7695dac 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -577,7 +577,6 @@ do_general_protection(struct pt_regs *regs, long error_code)
}
NOKPROBE_SYMBOL(do_general_protection);
-/* May run on IST stack. */
dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
{
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -592,6 +591,13 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
if (poke_int3_handler(regs))
return;
+ /*
+ * Use ist_enter despite the fact that we don't use an IST stack.
+ * We can be called from a kprobe in non-CONTEXT_KERNEL kernel
+ * mode or even during context tracking state changes.
+ *
+ * This means that we can't schedule. That's okay.
+ */
ist_enter(regs);
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
@@ -609,15 +615,10 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
SIGTRAP) == NOTIFY_STOP)
goto exit;
- /*
- * Let others (NMI) know that the debug stack is in use
- * as we may switch to the interrupt stack.
- */
- debug_stack_usage_inc();
cond_local_irq_enable(regs);
do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
cond_local_irq_disable(regs);
- debug_stack_usage_dec();
+
exit:
ist_exit(regs);
}
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index fb4302738410..ef32297ff17e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1179,6 +1179,45 @@ struct system_counterval_t convert_art_to_tsc(u64 art)
}
EXPORT_SYMBOL(convert_art_to_tsc);
+/**
+ * convert_art_ns_to_tsc() - Convert ART in nanoseconds to TSC.
+ * @art_ns: ART (Always Running Timer) in unit of nanoseconds
+ *
+ * PTM requires all timestamps to be in units of nanoseconds. When user
+ * software requests a cross-timestamp, this function converts system timestamp
+ * to TSC.
+ *
+ * This is valid when CPU feature flag X86_FEATURE_TSC_KNOWN_FREQ is set
+ * indicating the tsc_khz is derived from CPUID[15H]. Drivers should check
+ * that this flag is set before conversion to TSC is attempted.
+ *
+ * Return:
+ * struct system_counterval_t - system counter value with the pointer to the
+ * corresponding clocksource
+ * @cycles: System counter value
+ * @cs: Clocksource corresponding to system counter value. Used
+ * by timekeeping code to verify comparibility of two cycle
+ * values.
+ */
+
+struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns)
+{
+ u64 tmp, res, rem;
+
+ rem = do_div(art_ns, USEC_PER_SEC);
+
+ res = art_ns * tsc_khz;
+ tmp = rem * tsc_khz;
+
+ do_div(tmp, USEC_PER_SEC);
+ res += tmp;
+
+ return (struct system_counterval_t) { .cs = art_related_clocksource,
+ .cycles = res};
+}
+EXPORT_SYMBOL(convert_art_ns_to_tsc);
+
+
static void tsc_refine_calibration_work(struct work_struct *work);
static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
/**
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 5edb27f1a2c4..9d0b5af7db91 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -727,7 +727,8 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code)
return;
check_vip:
- if (VEFLAGS & X86_EFLAGS_VIP) {
+ if ((VEFLAGS & (X86_EFLAGS_VIP | X86_EFLAGS_VIF)) ==
+ (X86_EFLAGS_VIP | X86_EFLAGS_VIF)) {
save_v86_state(regs, VM86_STI);
return;
}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index b854ebf5851b..795f3a80e576 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -102,7 +102,6 @@ SECTIONS
_stext = .;
/* bootstrapping code */
HEAD_TEXT
- . = ALIGN(8);
TEXT_TEXT
SCHED_TEXT
CPUIDLE_TEXT
@@ -200,7 +199,7 @@ SECTIONS
. = __vvar_beginning_hack + PAGE_SIZE;
} :data
- . = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE);
+ . = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE);
/* Init code and data - will be freed after init */
. = ALIGN(PAGE_SIZE);
@@ -368,8 +367,8 @@ SECTIONS
. = ALIGN(PAGE_SIZE); /* keep VO_INIT_SIZE page aligned */
_end = .;
- STABS_DEBUG
- DWARF_DEBUG
+ STABS_DEBUG
+ DWARF_DEBUG
/* Sections to be discarded */
DISCARDS
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 1151ccd72ce9..ebda84a91510 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -8,6 +8,7 @@
#include <linux/export.h>
#include <linux/pci.h>
+#include <asm/acpi.h>
#include <asm/bios_ebda.h>
#include <asm/paravirt.h>
#include <asm/pci_x86.h>
@@ -26,10 +27,11 @@
void x86_init_noop(void) { }
void __init x86_init_uint_noop(unsigned int unused) { }
-int __init iommu_init_noop(void) { return 0; }
-void iommu_shutdown_noop(void) { }
-bool __init bool_x86_init_noop(void) { return false; }
-void x86_op_int_noop(int cpu) { }
+static int __init iommu_init_noop(void) { return 0; }
+static void iommu_shutdown_noop(void) { }
+static bool __init bool_x86_init_noop(void) { return false; }
+static void x86_op_int_noop(int cpu) { }
+static u64 u64_x86_init_noop(void) { return 0; }
/*
* The platform setup functions are preset with the default functions
@@ -91,6 +93,11 @@ struct x86_init_ops x86_init __initdata = {
.x2apic_available = bool_x86_init_noop,
.init_mem_mapping = x86_init_noop,
},
+
+ .acpi = {
+ .get_root_pointer = u64_x86_init_noop,
+ .reduced_hw_early_init = acpi_generic_reduced_hw_init,
+ },
};
struct x86_cpuinit_ops x86_cpuinit = {
@@ -146,7 +153,7 @@ void arch_restore_msi_irqs(struct pci_dev *dev)
}
#endif
-struct x86_io_apic_ops x86_io_apic_ops __ro_after_init = {
- .read = native_io_apic_read,
- .disable = native_disable_io_apic,
+struct x86_apic_ops x86_apic_ops __ro_after_init = {
+ .io_apic_read = native_io_apic_read,
+ .restore = native_restore_boot_irq_mode,
};
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index f551962ac294..763bb3bade63 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2770,8 +2770,10 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
else
pte_access &= ~ACC_WRITE_MASK;
+ if (!kvm_is_mmio_pfn(pfn))
+ spte |= shadow_me_mask;
+
spte |= (u64)pfn << PAGE_SHIFT;
- spte |= shadow_me_mask;
if (pte_access & ACC_WRITE_MASK) {
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index be9c839e2c89..9d2043f94e29 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -49,7 +49,6 @@
#include <asm/debugreg.h>
#include <asm/kvm_para.h>
#include <asm/irq_remapping.h>
-#include <asm/microcode.h>
#include <asm/nospec-branch.h>
#include <asm/virtext.h>
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 051dab74e4e9..92496b9b5f2b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -51,7 +51,6 @@
#include <asm/apic.h>
#include <asm/irq_remapping.h>
#include <asm/mmu_context.h>
-#include <asm/microcode.h>
#include <asm/nospec-branch.h>
#include "trace.h"
@@ -1045,6 +1044,13 @@ static inline bool is_machine_check(u32 intr_info)
(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
}
+/* Undocumented: icebp/int1 */
+static inline bool is_icebp(u32 intr_info)
+{
+ return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
+ == (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK);
+}
+
static inline bool cpu_has_vmx_msr_bitmap(void)
{
return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
@@ -6179,7 +6185,7 @@ static int handle_exception(struct kvm_vcpu *vcpu)
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
vcpu->arch.dr6 &= ~15;
vcpu->arch.dr6 |= dr6 | DR6_RTM;
- if (!(dr6 & ~DR6_RESERVED)) /* icebp */
+ if (is_icebp(intr_info))
skip_emulated_instruction(vcpu);
kvm_queue_exception(vcpu, DB_VECTOR);
@@ -10704,6 +10710,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 exec_control, vmcs12_exec_ctrl;
+ if (vmx->nested.dirty_vmcs12) {
+ prepare_vmcs02_full(vcpu, vmcs12, from_vmentry);
+ vmx->nested.dirty_vmcs12 = false;
+ }
+
/*
* First, the fields that are shadowed. This must be kept in sync
* with vmx_shadow_fields.h.
@@ -10941,11 +10952,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
/* Note: modifies VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
vmx_set_efer(vcpu, vcpu->arch.efer);
- if (vmx->nested.dirty_vmcs12) {
- prepare_vmcs02_full(vcpu, vmcs12, from_vmentry);
- vmx->nested.dirty_vmcs12 = false;
- }
-
/* Shadow page tables on either EPT or shadow page tables. */
if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
entry_failure_code))
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index 81b1635d67de..88acd349911b 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,6 +1,4 @@
#include <linux/linkage.h>
-#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
#include <asm/export.h>
/*
diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c
index 693cce0be82d..fee8b9c0520c 100644
--- a/arch/x86/lib/msr-smp.c
+++ b/arch/x86/lib/msr-smp.c
@@ -2,6 +2,7 @@
#include <linux/export.h>
#include <linux/preempt.h>
#include <linux/smp.h>
+#include <linux/completion.h>
#include <asm/msr.h>
static void __rdmsr_on_cpu(void *info)
@@ -143,13 +144,19 @@ void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
}
EXPORT_SYMBOL(wrmsr_on_cpus);
+struct msr_info_completion {
+ struct msr_info msr;
+ struct completion done;
+};
+
/* These "safe" variants are slower and should be used when the target MSR
may not actually exist. */
static void __rdmsr_safe_on_cpu(void *info)
{
- struct msr_info *rv = info;
+ struct msr_info_completion *rv = info;
- rv->err = rdmsr_safe(rv->msr_no, &rv->reg.l, &rv->reg.h);
+ rv->msr.err = rdmsr_safe(rv->msr.msr_no, &rv->msr.reg.l, &rv->msr.reg.h);
+ complete(&rv->done);
}
static void __wrmsr_safe_on_cpu(void *info)
@@ -161,17 +168,26 @@ static void __wrmsr_safe_on_cpu(void *info)
int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
{
+ struct msr_info_completion rv;
+ call_single_data_t csd = {
+ .func = __rdmsr_safe_on_cpu,
+ .info = &rv,
+ };
int err;
- struct msr_info rv;
memset(&rv, 0, sizeof(rv));
+ init_completion(&rv.done);
+ rv.msr.msr_no = msr_no;
- rv.msr_no = msr_no;
- err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1);
- *l = rv.reg.l;
- *h = rv.reg.h;
+ err = smp_call_function_single_async(cpu, &csd);
+ if (!err) {
+ wait_for_completion(&rv.done);
+ err = rv.msr.err;
+ }
+ *l = rv.msr.reg.l;
+ *h = rv.msr.reg.h;
- return err ? err : rv.err;
+ return err;
}
EXPORT_SYMBOL(rdmsr_safe_on_cpu);
@@ -209,16 +225,13 @@ EXPORT_SYMBOL(wrmsrl_safe_on_cpu);
int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
{
+ u32 low, high;
int err;
- struct msr_info rv;
- memset(&rv, 0, sizeof(rv));
+ err = rdmsr_safe_on_cpu(cpu, msr_no, &low, &high);
+ *q = (u64)high << 32 | low;
- rv.msr_no = msr_no;
- err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1);
- *q = rv.reg.q;
-
- return err ? err : rv.err;
+ return err;
}
EXPORT_SYMBOL(rdmsrl_safe_on_cpu);
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 27e9e90a8d35..4b101dd6e52f 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,12 +1,15 @@
# SPDX-License-Identifier: GPL-2.0
-# Kernel does not boot with instrumentation of tlb.c and mem_encrypt.c
-KCOV_INSTRUMENT_tlb.o := n
-KCOV_INSTRUMENT_mem_encrypt.o := n
+# Kernel does not boot with instrumentation of tlb.c and mem_encrypt*.c
+KCOV_INSTRUMENT_tlb.o := n
+KCOV_INSTRUMENT_mem_encrypt.o := n
+KCOV_INSTRUMENT_mem_encrypt_identity.o := n
-KASAN_SANITIZE_mem_encrypt.o := n
+KASAN_SANITIZE_mem_encrypt.o := n
+KASAN_SANITIZE_mem_encrypt_identity.o := n
ifdef CONFIG_FUNCTION_TRACER
-CFLAGS_REMOVE_mem_encrypt.o = -pg
+CFLAGS_REMOVE_mem_encrypt.o = -pg
+CFLAGS_REMOVE_mem_encrypt_identity.o = -pg
endif
obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
@@ -16,6 +19,7 @@ obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_physaddr.o := $(nostackp)
CFLAGS_setup_nx.o := $(nostackp)
+CFLAGS_mem_encrypt_identity.o := $(nostackp)
CFLAGS_fault.o := -I$(src)/../include/asm/trace
@@ -47,4 +51,5 @@ obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o
obj-$(CONFIG_PAGE_TABLE_ISOLATION) += pti.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt.o
+obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_identity.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_boot.o
diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c
index 421f2664ffa0..225fe2f0bfec 100644
--- a/arch/x86/mm/debug_pagetables.c
+++ b/arch/x86/mm/debug_pagetables.c
@@ -1,4 +1,5 @@
#include <linux/debugfs.h>
+#include <linux/efi.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <asm/pgtable.h>
@@ -72,6 +73,30 @@ static const struct file_operations ptdump_curusr_fops = {
};
#endif
+#if defined(CONFIG_EFI) && defined(CONFIG_X86_64)
+static struct dentry *pe_efi;
+
+static int ptdump_show_efi(struct seq_file *m, void *v)
+{
+ if (efi_mm.pgd)
+ ptdump_walk_pgd_level_debugfs(m, efi_mm.pgd, false);
+ return 0;
+}
+
+static int ptdump_open_efi(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, ptdump_show_efi, NULL);
+}
+
+static const struct file_operations ptdump_efi_fops = {
+ .owner = THIS_MODULE,
+ .open = ptdump_open_efi,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+#endif
+
static struct dentry *dir, *pe_knl, *pe_curknl;
static int __init pt_dump_debug_init(void)
@@ -96,6 +121,13 @@ static int __init pt_dump_debug_init(void)
if (!pe_curusr)
goto err;
#endif
+
+#if defined(CONFIG_EFI) && defined(CONFIG_X86_64)
+ pe_efi = debugfs_create_file("efi", 0400, dir, NULL, &ptdump_efi_fops);
+ if (!pe_efi)
+ goto err;
+#endif
+
return 0;
err:
debugfs_remove_recursive(dir);
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 2a4849e92831..62a7e9f65dec 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -29,6 +29,7 @@
struct pg_state {
int level;
pgprot_t current_prot;
+ pgprotval_t effective_prot;
unsigned long start_address;
unsigned long current_address;
const struct addr_marker *marker;
@@ -85,11 +86,15 @@ static struct addr_marker address_markers[] = {
[VMALLOC_START_NR] = { 0UL, "vmalloc() Area" },
[VMEMMAP_START_NR] = { 0UL, "Vmemmap" },
#ifdef CONFIG_KASAN
- [KASAN_SHADOW_START_NR] = { KASAN_SHADOW_START, "KASAN shadow" },
- [KASAN_SHADOW_END_NR] = { KASAN_SHADOW_END, "KASAN shadow end" },
+ /*
+ * These fields get initialized with the (dynamic)
+ * KASAN_SHADOW_{START,END} values in pt_dump_init().
+ */
+ [KASAN_SHADOW_START_NR] = { 0UL, "KASAN shadow" },
+ [KASAN_SHADOW_END_NR] = { 0UL, "KASAN shadow end" },
#endif
#ifdef CONFIG_MODIFY_LDT_SYSCALL
- [LDT_NR] = { LDT_BASE_ADDR, "LDT remap" },
+ [LDT_NR] = { 0UL, "LDT remap" },
#endif
[CPU_ENTRY_AREA_NR] = { CPU_ENTRY_AREA_BASE,"CPU entry Area" },
#ifdef CONFIG_X86_ESPFIX64
@@ -231,9 +236,9 @@ static unsigned long normalize_addr(unsigned long u)
* print what we collected so far.
*/
static void note_page(struct seq_file *m, struct pg_state *st,
- pgprot_t new_prot, int level)
+ pgprot_t new_prot, pgprotval_t new_eff, int level)
{
- pgprotval_t prot, cur;
+ pgprotval_t prot, cur, eff;
static const char units[] = "BKMGTPE";
/*
@@ -243,23 +248,24 @@ static void note_page(struct seq_file *m, struct pg_state *st,
*/
prot = pgprot_val(new_prot);
cur = pgprot_val(st->current_prot);
+ eff = st->effective_prot;
if (!st->level) {
/* First entry */
st->current_prot = new_prot;
+ st->effective_prot = new_eff;
st->level = level;
st->marker = address_markers;
st->lines = 0;
pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n",
st->marker->name);
- } else if (prot != cur || level != st->level ||
+ } else if (prot != cur || new_eff != eff || level != st->level ||
st->current_address >= st->marker[1].start_address) {
const char *unit = units;
unsigned long delta;
int width = sizeof(unsigned long) * 2;
- pgprotval_t pr = pgprot_val(st->current_prot);
- if (st->check_wx && (pr & _PAGE_RW) && !(pr & _PAGE_NX)) {
+ if (st->check_wx && (eff & _PAGE_RW) && !(eff & _PAGE_NX)) {
WARN_ONCE(1,
"x86/mm: Found insecure W+X mapping at address %p/%pS\n",
(void *)st->start_address,
@@ -313,21 +319,30 @@ static void note_page(struct seq_file *m, struct pg_state *st,
st->start_address = st->current_address;
st->current_prot = new_prot;
+ st->effective_prot = new_eff;
st->level = level;
}
}
-static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, unsigned long P)
+static inline pgprotval_t effective_prot(pgprotval_t prot1, pgprotval_t prot2)
+{
+ return (prot1 & prot2 & (_PAGE_USER | _PAGE_RW)) |
+ ((prot1 | prot2) & _PAGE_NX);
+}
+
+static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr,
+ pgprotval_t eff_in, unsigned long P)
{
int i;
pte_t *start;
- pgprotval_t prot;
+ pgprotval_t prot, eff;
start = (pte_t *)pmd_page_vaddr(addr);
for (i = 0; i < PTRS_PER_PTE; i++) {
prot = pte_flags(*start);
+ eff = effective_prot(eff_in, prot);
st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT);
- note_page(m, st, __pgprot(prot), 5);
+ note_page(m, st, __pgprot(prot), eff, 5);
start++;
}
}
@@ -344,12 +359,10 @@ static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st,
void *pt)
{
if (__pa(pt) == __pa(kasan_zero_pmd) ||
-#ifdef CONFIG_X86_5LEVEL
- __pa(pt) == __pa(kasan_zero_p4d) ||
-#endif
+ (pgtable_l5_enabled && __pa(pt) == __pa(kasan_zero_p4d)) ||
__pa(pt) == __pa(kasan_zero_pud)) {
pgprotval_t prot = pte_flags(kasan_zero_pte[0]);
- note_page(m, st, __pgprot(prot), 5);
+ note_page(m, st, __pgprot(prot), 0, 5);
return true;
}
return false;
@@ -364,42 +377,45 @@ static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st,
#if PTRS_PER_PMD > 1
-static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, unsigned long P)
+static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr,
+ pgprotval_t eff_in, unsigned long P)
{
int i;
pmd_t *start, *pmd_start;
- pgprotval_t prot;
+ pgprotval_t prot, eff;
pmd_start = start = (pmd_t *)pud_page_vaddr(addr);
for (i = 0; i < PTRS_PER_PMD; i++) {
st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT);
if (!pmd_none(*start)) {
+ prot = pmd_flags(*start);
+ eff = effective_prot(eff_in, prot);
if (pmd_large(*start) || !pmd_present(*start)) {
- prot = pmd_flags(*start);
- note_page(m, st, __pgprot(prot), 4);
+ note_page(m, st, __pgprot(prot), eff, 4);
} else if (!kasan_page_table(m, st, pmd_start)) {
- walk_pte_level(m, st, *start,
+ walk_pte_level(m, st, *start, eff,
P + i * PMD_LEVEL_MULT);
}
} else
- note_page(m, st, __pgprot(0), 4);
+ note_page(m, st, __pgprot(0), 0, 4);
start++;
}
}
#else
-#define walk_pmd_level(m,s,a,p) walk_pte_level(m,s,__pmd(pud_val(a)),p)
+#define walk_pmd_level(m,s,a,e,p) walk_pte_level(m,s,__pmd(pud_val(a)),e,p)
#define pud_large(a) pmd_large(__pmd(pud_val(a)))
#define pud_none(a) pmd_none(__pmd(pud_val(a)))
#endif
#if PTRS_PER_PUD > 1
-static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, unsigned long P)
+static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr,
+ pgprotval_t eff_in, unsigned long P)
{
int i;
pud_t *start, *pud_start;
- pgprotval_t prot;
+ pgprotval_t prot, eff;
pud_t *prev_pud = NULL;
pud_start = start = (pud_t *)p4d_page_vaddr(addr);
@@ -407,15 +423,16 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr,
for (i = 0; i < PTRS_PER_PUD; i++) {
st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT);
if (!pud_none(*start)) {
+ prot = pud_flags(*start);
+ eff = effective_prot(eff_in, prot);
if (pud_large(*start) || !pud_present(*start)) {
- prot = pud_flags(*start);
- note_page(m, st, __pgprot(prot), 3);
+ note_page(m, st, __pgprot(prot), eff, 3);
} else if (!kasan_page_table(m, st, pud_start)) {
- walk_pmd_level(m, st, *start,
+ walk_pmd_level(m, st, *start, eff,
P + i * PUD_LEVEL_MULT);
}
} else
- note_page(m, st, __pgprot(0), 3);
+ note_page(m, st, __pgprot(0), 0, 3);
prev_pud = start;
start++;
@@ -423,43 +440,43 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr,
}
#else
-#define walk_pud_level(m,s,a,p) walk_pmd_level(m,s,__pud(p4d_val(a)),p)
+#define walk_pud_level(m,s,a,e,p) walk_pmd_level(m,s,__pud(p4d_val(a)),e,p)
#define p4d_large(a) pud_large(__pud(p4d_val(a)))
#define p4d_none(a) pud_none(__pud(p4d_val(a)))
#endif
-#if PTRS_PER_P4D > 1
-
-static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr, unsigned long P)
+static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
+ pgprotval_t eff_in, unsigned long P)
{
int i;
p4d_t *start, *p4d_start;
- pgprotval_t prot;
+ pgprotval_t prot, eff;
+
+ if (PTRS_PER_P4D == 1)
+ return walk_pud_level(m, st, __p4d(pgd_val(addr)), eff_in, P);
p4d_start = start = (p4d_t *)pgd_page_vaddr(addr);
for (i = 0; i < PTRS_PER_P4D; i++) {
st->current_address = normalize_addr(P + i * P4D_LEVEL_MULT);
if (!p4d_none(*start)) {
+ prot = p4d_flags(*start);
+ eff = effective_prot(eff_in, prot);
if (p4d_large(*start) || !p4d_present(*start)) {
- prot = p4d_flags(*start);
- note_page(m, st, __pgprot(prot), 2);
+ note_page(m, st, __pgprot(prot), eff, 2);
} else if (!kasan_page_table(m, st, p4d_start)) {
- walk_pud_level(m, st, *start,
+ walk_pud_level(m, st, *start, eff,
P + i * P4D_LEVEL_MULT);
}
} else
- note_page(m, st, __pgprot(0), 2);
+ note_page(m, st, __pgprot(0), 0, 2);
start++;
}
}
-#else
-#define walk_p4d_level(m,s,a,p) walk_pud_level(m,s,__p4d(pgd_val(a)),p)
-#define pgd_large(a) p4d_large(__p4d(pgd_val(a)))
-#define pgd_none(a) p4d_none(__p4d(pgd_val(a)))
-#endif
+#define pgd_large(a) (pgtable_l5_enabled ? pgd_large(a) : p4d_large(__p4d(pgd_val(a))))
+#define pgd_none(a) (pgtable_l5_enabled ? pgd_none(a) : p4d_none(__p4d(pgd_val(a))))
static inline bool is_hypervisor_range(int idx)
{
@@ -483,7 +500,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
#else
pgd_t *start = swapper_pg_dir;
#endif
- pgprotval_t prot;
+ pgprotval_t prot, eff;
int i;
struct pg_state st = {};
@@ -499,15 +516,20 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
for (i = 0; i < PTRS_PER_PGD; i++) {
st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
if (!pgd_none(*start) && !is_hypervisor_range(i)) {
+ prot = pgd_flags(*start);
+#ifdef CONFIG_X86_PAE
+ eff = _PAGE_USER | _PAGE_RW;
+#else
+ eff = prot;
+#endif
if (pgd_large(*start) || !pgd_present(*start)) {
- prot = pgd_flags(*start);
- note_page(m, &st, __pgprot(prot), 1);
+ note_page(m, &st, __pgprot(prot), eff, 1);
} else {
- walk_p4d_level(m, &st, *start,
+ walk_p4d_level(m, &st, *start, eff,
i * PGD_LEVEL_MULT);
}
} else
- note_page(m, &st, __pgprot(0), 1);
+ note_page(m, &st, __pgprot(0), 0, 1);
cond_resched();
start++;
@@ -515,7 +537,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
/* Flush out the last page */
st.current_address = normalize_addr(PTRS_PER_PGD*PGD_LEVEL_MULT);
- note_page(m, &st, __pgprot(0), 0);
+ note_page(m, &st, __pgprot(0), 0, 0);
if (!checkwx)
return;
if (st.wx_pages)
@@ -570,6 +592,13 @@ static int __init pt_dump_init(void)
address_markers[LOW_KERNEL_NR].start_address = PAGE_OFFSET;
address_markers[VMALLOC_START_NR].start_address = VMALLOC_START;
address_markers[VMEMMAP_START_NR].start_address = VMEMMAP_START;
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ address_markers[LDT_NR].start_address = LDT_BASE_ADDR;
+#endif
+#ifdef CONFIG_KASAN
+ address_markers[KASAN_SHADOW_START_NR].start_address = KASAN_SHADOW_START;
+ address_markers[KASAN_SHADOW_END_NR].start_address = KASAN_SHADOW_END;
+#endif
#endif
#ifdef CONFIG_X86_32
address_markers[VMALLOC_START_NR].start_address = VMALLOC_START;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index c88573d90f3e..73bd8c95ac71 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -330,7 +330,7 @@ static noinline int vmalloc_fault(unsigned long address)
if (!pmd_k)
return -1;
- if (pmd_huge(*pmd_k))
+ if (pmd_large(*pmd_k))
return 0;
pte_k = pte_offset_kernel(pmd_k, address);
@@ -417,11 +417,11 @@ void vmalloc_sync_all(void)
*/
static noinline int vmalloc_fault(unsigned long address)
{
- pgd_t *pgd, *pgd_ref;
- p4d_t *p4d, *p4d_ref;
- pud_t *pud, *pud_ref;
- pmd_t *pmd, *pmd_ref;
- pte_t *pte, *pte_ref;
+ pgd_t *pgd, *pgd_k;
+ p4d_t *p4d, *p4d_k;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
/* Make sure we are in vmalloc area: */
if (!(address >= VMALLOC_START && address < VMALLOC_END))
@@ -435,73 +435,51 @@ static noinline int vmalloc_fault(unsigned long address)
* case just flush:
*/
pgd = (pgd_t *)__va(read_cr3_pa()) + pgd_index(address);
- pgd_ref = pgd_offset_k(address);
- if (pgd_none(*pgd_ref))
+ pgd_k = pgd_offset_k(address);
+ if (pgd_none(*pgd_k))
return -1;
- if (CONFIG_PGTABLE_LEVELS > 4) {
+ if (pgtable_l5_enabled) {
if (pgd_none(*pgd)) {
- set_pgd(pgd, *pgd_ref);
+ set_pgd(pgd, *pgd_k);
arch_flush_lazy_mmu_mode();
} else {
- BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+ BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_k));
}
}
/* With 4-level paging, copying happens on the p4d level. */
p4d = p4d_offset(pgd, address);
- p4d_ref = p4d_offset(pgd_ref, address);
- if (p4d_none(*p4d_ref))
+ p4d_k = p4d_offset(pgd_k, address);
+ if (p4d_none(*p4d_k))
return -1;
- if (p4d_none(*p4d) && CONFIG_PGTABLE_LEVELS == 4) {
- set_p4d(p4d, *p4d_ref);
+ if (p4d_none(*p4d) && !pgtable_l5_enabled) {
+ set_p4d(p4d, *p4d_k);
arch_flush_lazy_mmu_mode();
} else {
- BUG_ON(p4d_pfn(*p4d) != p4d_pfn(*p4d_ref));
+ BUG_ON(p4d_pfn(*p4d) != p4d_pfn(*p4d_k));
}
- /*
- * Below here mismatches are bugs because these lower tables
- * are shared:
- */
BUILD_BUG_ON(CONFIG_PGTABLE_LEVELS < 4);
pud = pud_offset(p4d, address);
- pud_ref = pud_offset(p4d_ref, address);
- if (pud_none(*pud_ref))
+ if (pud_none(*pud))
return -1;
- if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref))
- BUG();
-
- if (pud_huge(*pud))
+ if (pud_large(*pud))
return 0;
pmd = pmd_offset(pud, address);
- pmd_ref = pmd_offset(pud_ref, address);
- if (pmd_none(*pmd_ref))
+ if (pmd_none(*pmd))
return -1;
- if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref))
- BUG();
-
- if (pmd_huge(*pmd))
+ if (pmd_large(*pmd))
return 0;
- pte_ref = pte_offset_kernel(pmd_ref, address);
- if (!pte_present(*pte_ref))
- return -1;
-
pte = pte_offset_kernel(pmd, address);
-
- /*
- * Don't use pte_page here, because the mappings can point
- * outside mem_map, and the NUMA hash lookup cannot handle
- * that:
- */
- if (!pte_present(*pte) || pte_pfn(*pte) != pte_pfn(*pte_ref))
- BUG();
+ if (!pte_present(*pte))
+ return -1;
return 0;
}
@@ -699,7 +677,6 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code,
printk(KERN_CONT "paging request");
printk(KERN_CONT " at %px\n", (void *) address);
- printk(KERN_ALERT "IP: %pS\n", (void *)regs->ip);
dump_pagetable(address);
}
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index ab33a32df2a8..9aa22be8331e 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -120,7 +120,7 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
result = ident_p4d_init(info, p4d, addr, next);
if (result)
return result;
- if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+ if (pgtable_l5_enabled) {
set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag));
} else {
/*
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 8b72923f1d35..45241de66785 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -88,12 +88,7 @@ static int __init nonx32_setup(char *str)
}
__setup("noexec32=", nonx32_setup);
-/*
- * When memory was added make sure all the processes MM have
- * suitable PGD entries in the local PGD level page.
- */
-#ifdef CONFIG_X86_5LEVEL
-void sync_global_pgds(unsigned long start, unsigned long end)
+static void sync_global_pgds_l5(unsigned long start, unsigned long end)
{
unsigned long addr;
@@ -129,8 +124,8 @@ void sync_global_pgds(unsigned long start, unsigned long end)
spin_unlock(&pgd_lock);
}
}
-#else
-void sync_global_pgds(unsigned long start, unsigned long end)
+
+static void sync_global_pgds_l4(unsigned long start, unsigned long end)
{
unsigned long addr;
@@ -143,7 +138,7 @@ void sync_global_pgds(unsigned long start, unsigned long end)
* With folded p4d, pgd_none() is always false, we need to
* handle synchonization on p4d level.
*/
- BUILD_BUG_ON(pgd_none(*pgd_ref));
+ MAYBE_BUILD_BUG_ON(pgd_none(*pgd_ref));
p4d_ref = p4d_offset(pgd_ref, addr);
if (p4d_none(*p4d_ref))
@@ -173,7 +168,18 @@ void sync_global_pgds(unsigned long start, unsigned long end)
spin_unlock(&pgd_lock);
}
}
-#endif
+
+/*
+ * When memory was added make sure all the processes MM have
+ * suitable PGD entries in the local PGD level page.
+ */
+void sync_global_pgds(unsigned long start, unsigned long end)
+{
+ if (pgtable_l5_enabled)
+ sync_global_pgds_l5(start, end);
+ else
+ sync_global_pgds_l4(start, end);
+}
/*
* NOTE: This function is marked __ref because it calls __init function
@@ -632,7 +638,7 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
unsigned long vaddr = (unsigned long)__va(paddr);
int i = p4d_index(vaddr);
- if (!IS_ENABLED(CONFIG_X86_5LEVEL))
+ if (!pgtable_l5_enabled)
return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end, page_size_mask);
for (; i < PTRS_PER_P4D; i++, paddr = paddr_next) {
@@ -712,7 +718,7 @@ kernel_physical_mapping_init(unsigned long paddr_start,
page_size_mask);
spin_lock(&init_mm.page_table_lock);
- if (IS_ENABLED(CONFIG_X86_5LEVEL))
+ if (pgtable_l5_enabled)
pgd_populate(&init_mm, pgd, p4d);
else
p4d_populate(&init_mm, p4d_offset(pgd, vaddr), (pud_t *) p4d);
@@ -800,17 +806,11 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
#define PAGE_INUSE 0xFD
-static void __meminit free_pagetable(struct page *page, int order,
- struct vmem_altmap *altmap)
+static void __meminit free_pagetable(struct page *page, int order)
{
unsigned long magic;
unsigned int nr_pages = 1 << order;
- if (altmap) {
- vmem_altmap_free(altmap, nr_pages);
- return;
- }
-
/* bootmem page has reserved flag */
if (PageReserved(page)) {
__ClearPageReserved(page);
@@ -826,9 +826,17 @@ static void __meminit free_pagetable(struct page *page, int order,
free_pages((unsigned long)page_address(page), order);
}
-static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd,
+static void __meminit free_hugepage_table(struct page *page,
struct vmem_altmap *altmap)
{
+ if (altmap)
+ vmem_altmap_free(altmap, PMD_SIZE / PAGE_SIZE);
+ else
+ free_pagetable(page, get_order(PMD_SIZE));
+}
+
+static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
+{
pte_t *pte;
int i;
@@ -839,14 +847,13 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd,
}
/* free a pte talbe */
- free_pagetable(pmd_page(*pmd), 0, altmap);
+ free_pagetable(pmd_page(*pmd), 0);
spin_lock(&init_mm.page_table_lock);
pmd_clear(pmd);
spin_unlock(&init_mm.page_table_lock);
}
-static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud,
- struct vmem_altmap *altmap)
+static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
{
pmd_t *pmd;
int i;
@@ -858,14 +865,13 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud,
}
/* free a pmd talbe */
- free_pagetable(pud_page(*pud), 0, altmap);
+ free_pagetable(pud_page(*pud), 0);
spin_lock(&init_mm.page_table_lock);
pud_clear(pud);
spin_unlock(&init_mm.page_table_lock);
}
-static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d,
- struct vmem_altmap *altmap)
+static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d)
{
pud_t *pud;
int i;
@@ -877,7 +883,7 @@ static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d,
}
/* free a pud talbe */
- free_pagetable(p4d_page(*p4d), 0, altmap);
+ free_pagetable(p4d_page(*p4d), 0);
spin_lock(&init_mm.page_table_lock);
p4d_clear(p4d);
spin_unlock(&init_mm.page_table_lock);
@@ -885,7 +891,7 @@ static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d,
static void __meminit
remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
- struct vmem_altmap *altmap, bool direct)
+ bool direct)
{
unsigned long next, pages = 0;
pte_t *pte;
@@ -916,7 +922,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
* freed when offlining, or simplely not in use.
*/
if (!direct)
- free_pagetable(pte_page(*pte), 0, altmap);
+ free_pagetable(pte_page(*pte), 0);
spin_lock(&init_mm.page_table_lock);
pte_clear(&init_mm, addr, pte);
@@ -939,7 +945,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
page_addr = page_address(pte_page(*pte));
if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) {
- free_pagetable(pte_page(*pte), 0, altmap);
+ free_pagetable(pte_page(*pte), 0);
spin_lock(&init_mm.page_table_lock);
pte_clear(&init_mm, addr, pte);
@@ -974,9 +980,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
if (IS_ALIGNED(addr, PMD_SIZE) &&
IS_ALIGNED(next, PMD_SIZE)) {
if (!direct)
- free_pagetable(pmd_page(*pmd),
- get_order(PMD_SIZE),
- altmap);
+ free_hugepage_table(pmd_page(*pmd),
+ altmap);
spin_lock(&init_mm.page_table_lock);
pmd_clear(pmd);
@@ -989,9 +994,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
page_addr = page_address(pmd_page(*pmd));
if (!memchr_inv(page_addr, PAGE_INUSE,
PMD_SIZE)) {
- free_pagetable(pmd_page(*pmd),
- get_order(PMD_SIZE),
- altmap);
+ free_hugepage_table(pmd_page(*pmd),
+ altmap);
spin_lock(&init_mm.page_table_lock);
pmd_clear(pmd);
@@ -1003,8 +1007,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
}
pte_base = (pte_t *)pmd_page_vaddr(*pmd);
- remove_pte_table(pte_base, addr, next, altmap, direct);
- free_pte_table(pte_base, pmd, altmap);
+ remove_pte_table(pte_base, addr, next, direct);
+ free_pte_table(pte_base, pmd);
}
/* Call free_pmd_table() in remove_pud_table(). */
@@ -1033,8 +1037,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
IS_ALIGNED(next, PUD_SIZE)) {
if (!direct)
free_pagetable(pud_page(*pud),
- get_order(PUD_SIZE),
- altmap);
+ get_order(PUD_SIZE));
spin_lock(&init_mm.page_table_lock);
pud_clear(pud);
@@ -1048,8 +1051,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
if (!memchr_inv(page_addr, PAGE_INUSE,
PUD_SIZE)) {
free_pagetable(pud_page(*pud),
- get_order(PUD_SIZE),
- altmap);
+ get_order(PUD_SIZE));
spin_lock(&init_mm.page_table_lock);
pud_clear(pud);
@@ -1062,7 +1064,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
pmd_base = pmd_offset(pud, 0);
remove_pmd_table(pmd_base, addr, next, direct, altmap);
- free_pmd_table(pmd_base, pud, altmap);
+ free_pmd_table(pmd_base, pud);
}
if (direct)
@@ -1093,8 +1095,8 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end,
* 5-level case we should free them. This code will have to change
* to adapt for boot-time switching between 4 and 5 level page tables.
*/
- if (CONFIG_PGTABLE_LEVELS == 5)
- free_pud_table(pud_base, p4d, altmap);
+ if (pgtable_l5_enabled)
+ free_pud_table(pud_base, p4d);
}
if (direct)
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index af6f2f9c6a26..d8ff013ea9d0 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,6 +1,12 @@
// SPDX-License-Identifier: GPL-2.0
#define DISABLE_BRANCH_PROFILING
#define pr_fmt(fmt) "kasan: " fmt
+
+#ifdef CONFIG_X86_5LEVEL
+/* Too early to use cpu_feature_enabled() */
+#define pgtable_l5_enabled __pgtable_l5_enabled
+#endif
+
#include <linux/bootmem.h>
#include <linux/kasan.h>
#include <linux/kdebug.h>
@@ -19,7 +25,7 @@
extern struct range pfn_mapped[E820_MAX_ENTRIES];
-static p4d_t tmp_p4d_table[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE);
+static p4d_t tmp_p4d_table[MAX_PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE);
static __init void *early_alloc(size_t size, int nid, bool panic)
{
@@ -176,10 +182,10 @@ static void __init clear_pgds(unsigned long start,
* With folded p4d, pgd_clear() is nop, use p4d_clear()
* instead.
*/
- if (CONFIG_PGTABLE_LEVELS < 5)
- p4d_clear(p4d_offset(pgd, start));
- else
+ if (pgtable_l5_enabled)
pgd_clear(pgd);
+ else
+ p4d_clear(p4d_offset(pgd, start));
}
pgd = pgd_offset_k(start);
@@ -191,7 +197,7 @@ static inline p4d_t *early_p4d_offset(pgd_t *pgd, unsigned long addr)
{
unsigned long p4d;
- if (!IS_ENABLED(CONFIG_X86_5LEVEL))
+ if (!pgtable_l5_enabled)
return (p4d_t *)pgd;
p4d = __pa_nodebug(pgd_val(*pgd)) & PTE_PFN_MASK;
@@ -272,7 +278,7 @@ void __init kasan_early_init(void)
for (i = 0; i < PTRS_PER_PUD; i++)
kasan_zero_pud[i] = __pud(pud_val);
- for (i = 0; IS_ENABLED(CONFIG_X86_5LEVEL) && i < PTRS_PER_P4D; i++)
+ for (i = 0; pgtable_l5_enabled && i < PTRS_PER_P4D; i++)
kasan_zero_p4d[i] = __p4d(p4d_val);
kasan_map_early_shadow(early_top_pgt);
@@ -303,7 +309,7 @@ void __init kasan_init(void)
* bunch of things like kernel code, modules, EFI mapping, etc.
* We need to take extra steps to not overwrite them.
*/
- if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+ if (pgtable_l5_enabled) {
void *ptr;
ptr = (void *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END));
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index aedebd2ebf1e..615cc03ced84 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -34,23 +34,12 @@
#define TB_SHIFT 40
/*
- * Virtual address start and end range for randomization.
- *
* The end address could depend on more configuration options to make the
* highest amount of space for randomization available, but that's too hard
* to keep straight and caused issues already.
*/
-static const unsigned long vaddr_start = __PAGE_OFFSET_BASE;
static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE;
-/* Default values */
-unsigned long page_offset_base = __PAGE_OFFSET_BASE;
-EXPORT_SYMBOL(page_offset_base);
-unsigned long vmalloc_base = __VMALLOC_BASE;
-EXPORT_SYMBOL(vmalloc_base);
-unsigned long vmemmap_base = __VMEMMAP_BASE;
-EXPORT_SYMBOL(vmemmap_base);
-
/*
* Memory regions randomized by KASLR (except modules that use a separate logic
* earlier during boot). The list is ordered based on virtual addresses. This
@@ -60,8 +49,8 @@ static __initdata struct kaslr_memory_region {
unsigned long *base;
unsigned long size_tb;
} kaslr_regions[] = {
- { &page_offset_base, 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT) /* Maximum */ },
- { &vmalloc_base, VMALLOC_SIZE_TB },
+ { &page_offset_base, 0 },
+ { &vmalloc_base, 0 },
{ &vmemmap_base, 1 },
};
@@ -84,11 +73,14 @@ static inline bool kaslr_memory_enabled(void)
void __init kernel_randomize_memory(void)
{
size_t i;
- unsigned long vaddr = vaddr_start;
+ unsigned long vaddr_start, vaddr;
unsigned long rand, memory_tb;
struct rnd_state rand_state;
unsigned long remain_entropy;
+ vaddr_start = pgtable_l5_enabled ? __PAGE_OFFSET_BASE_L5 : __PAGE_OFFSET_BASE_L4;
+ vaddr = vaddr_start;
+
/*
* These BUILD_BUG_ON checks ensure the memory layout is consistent
* with the vaddr_start/vaddr_end variables. These checks are very
@@ -101,6 +93,9 @@ void __init kernel_randomize_memory(void)
if (!kaslr_memory_enabled())
return;
+ kaslr_regions[0].size_tb = 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT);
+ kaslr_regions[1].size_tb = VMALLOC_SIZE_TB;
+
/*
* Update Physical memory mapping to available and
* add padding if needed (especially for memory hotplug support).
@@ -129,7 +124,7 @@ void __init kernel_randomize_memory(void)
*/
entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i);
prandom_bytes_state(&rand_state, &rand, sizeof(rand));
- if (IS_ENABLED(CONFIG_X86_5LEVEL))
+ if (pgtable_l5_enabled)
entropy = (rand % (entropy + 1)) & P4D_MASK;
else
entropy = (rand % (entropy + 1)) & PUD_MASK;
@@ -141,7 +136,7 @@ void __init kernel_randomize_memory(void)
* randomization alignment.
*/
vaddr += get_padding(&kaslr_regions[i]);
- if (IS_ENABLED(CONFIG_X86_5LEVEL))
+ if (pgtable_l5_enabled)
vaddr = round_up(vaddr + 1, P4D_SIZE);
else
vaddr = round_up(vaddr + 1, PUD_SIZE);
@@ -217,7 +212,7 @@ void __meminit init_trampoline(void)
return;
}
- if (IS_ENABLED(CONFIG_X86_5LEVEL))
+ if (pgtable_l5_enabled)
init_trampoline_p4d();
else
init_trampoline_pud();
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 1a53071e2e17..b2de398d1fd3 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -25,17 +25,12 @@
#include <asm/bootparam.h>
#include <asm/set_memory.h>
#include <asm/cacheflush.h>
-#include <asm/sections.h>
#include <asm/processor-flags.h>
#include <asm/msr.h>
#include <asm/cmdline.h>
#include "mm_internal.h"
-static char sme_cmdline_arg[] __initdata = "mem_encrypt";
-static char sme_cmdline_on[] __initdata = "on";
-static char sme_cmdline_off[] __initdata = "off";
-
/*
* Since SME related variables are set early in the boot process they must
* reside in the .data section so as not to be zeroed out when the .bss
@@ -46,7 +41,7 @@ EXPORT_SYMBOL(sme_me_mask);
DEFINE_STATIC_KEY_FALSE(sev_enable_key);
EXPORT_SYMBOL_GPL(sev_enable_key);
-static bool sev_enabled __section(.data);
+bool sev_enabled __section(.data);
/* Buffer used for early in-place encryption by BSP, no locking needed */
static char sme_early_buffer[PAGE_SIZE] __aligned(PAGE_SIZE);
@@ -200,67 +195,6 @@ void __init sme_early_init(void)
swiotlb_force = SWIOTLB_FORCE;
}
-static void *sev_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
- gfp_t gfp, unsigned long attrs)
-{
- unsigned long dma_mask;
- unsigned int order;
- struct page *page;
- void *vaddr = NULL;
-
- dma_mask = dma_alloc_coherent_mask(dev, gfp);
- order = get_order(size);
-
- /*
- * Memory will be memset to zero after marking decrypted, so don't
- * bother clearing it before.
- */
- gfp &= ~__GFP_ZERO;
-
- page = alloc_pages_node(dev_to_node(dev), gfp, order);
- if (page) {
- dma_addr_t addr;
-
- /*
- * Since we will be clearing the encryption bit, check the
- * mask with it already cleared.
- */
- addr = __sme_clr(phys_to_dma(dev, page_to_phys(page)));
- if ((addr + size) > dma_mask) {
- __free_pages(page, get_order(size));
- } else {
- vaddr = page_address(page);
- *dma_handle = addr;
- }
- }
-
- if (!vaddr)
- vaddr = swiotlb_alloc_coherent(dev, size, dma_handle, gfp);
-
- if (!vaddr)
- return NULL;
-
- /* Clear the SME encryption bit for DMA use if not swiotlb area */
- if (!is_swiotlb_buffer(dma_to_phys(dev, *dma_handle))) {
- set_memory_decrypted((unsigned long)vaddr, 1 << order);
- memset(vaddr, 0, PAGE_SIZE << order);
- *dma_handle = __sme_clr(*dma_handle);
- }
-
- return vaddr;
-}
-
-static void sev_free(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_handle, unsigned long attrs)
-{
- /* Set the SME encryption bit for re-use if not swiotlb area */
- if (!is_swiotlb_buffer(dma_to_phys(dev, dma_handle)))
- set_memory_encrypted((unsigned long)vaddr,
- 1 << get_order(size));
-
- swiotlb_free_coherent(dev, size, vaddr, dma_handle);
-}
-
static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
{
pgprot_t old_prot, new_prot;
@@ -413,20 +347,6 @@ bool sev_active(void)
}
EXPORT_SYMBOL(sev_active);
-static const struct dma_map_ops sev_dma_ops = {
- .alloc = sev_alloc,
- .free = sev_free,
- .map_page = swiotlb_map_page,
- .unmap_page = swiotlb_unmap_page,
- .map_sg = swiotlb_map_sg_attrs,
- .unmap_sg = swiotlb_unmap_sg_attrs,
- .sync_single_for_cpu = swiotlb_sync_single_for_cpu,
- .sync_single_for_device = swiotlb_sync_single_for_device,
- .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
- .sync_sg_for_device = swiotlb_sync_sg_for_device,
- .mapping_error = swiotlb_dma_mapping_error,
-};
-
/* Architecture __weak replacement functions */
void __init mem_encrypt_init(void)
{
@@ -437,12 +357,11 @@ void __init mem_encrypt_init(void)
swiotlb_update_mem_attributes();
/*
- * With SEV, DMA operations cannot use encryption. New DMA ops
- * are required in order to mark the DMA areas as decrypted or
- * to use bounce buffers.
+ * With SEV, DMA operations cannot use encryption, we need to use
+ * SWIOTLB to bounce buffer DMA operation.
*/
if (sev_active())
- dma_ops = &sev_dma_ops;
+ dma_ops = &swiotlb_dma_ops;
/*
* With SEV, we need to unroll the rep string I/O instructions.
@@ -455,582 +374,3 @@ void __init mem_encrypt_init(void)
: "Secure Memory Encryption (SME)");
}
-void swiotlb_set_mem_attributes(void *vaddr, unsigned long size)
-{
- WARN(PAGE_ALIGN(size) != size,
- "size is not page-aligned (%#lx)\n", size);
-
- /* Make the SWIOTLB buffer area decrypted */
- set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT);
-}
-
-struct sme_populate_pgd_data {
- void *pgtable_area;
- pgd_t *pgd;
-
- pmdval_t pmd_flags;
- pteval_t pte_flags;
- unsigned long paddr;
-
- unsigned long vaddr;
- unsigned long vaddr_end;
-};
-
-static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
-{
- unsigned long pgd_start, pgd_end, pgd_size;
- pgd_t *pgd_p;
-
- pgd_start = ppd->vaddr & PGDIR_MASK;
- pgd_end = ppd->vaddr_end & PGDIR_MASK;
-
- pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1) * sizeof(pgd_t);
-
- pgd_p = ppd->pgd + pgd_index(ppd->vaddr);
-
- memset(pgd_p, 0, pgd_size);
-}
-
-#define PGD_FLAGS _KERNPG_TABLE_NOENC
-#define P4D_FLAGS _KERNPG_TABLE_NOENC
-#define PUD_FLAGS _KERNPG_TABLE_NOENC
-#define PMD_FLAGS _KERNPG_TABLE_NOENC
-
-#define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL)
-
-#define PMD_FLAGS_DEC PMD_FLAGS_LARGE
-#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
- (_PAGE_PAT | _PAGE_PWT))
-
-#define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC)
-
-#define PTE_FLAGS (__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL)
-
-#define PTE_FLAGS_DEC PTE_FLAGS
-#define PTE_FLAGS_DEC_WP ((PTE_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
- (_PAGE_PAT | _PAGE_PWT))
-
-#define PTE_FLAGS_ENC (PTE_FLAGS | _PAGE_ENC)
-
-static pmd_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
-{
- pgd_t *pgd_p;
- p4d_t *p4d_p;
- pud_t *pud_p;
- pmd_t *pmd_p;
-
- pgd_p = ppd->pgd + pgd_index(ppd->vaddr);
- if (native_pgd_val(*pgd_p)) {
- if (IS_ENABLED(CONFIG_X86_5LEVEL))
- p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK);
- else
- pud_p = (pud_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK);
- } else {
- pgd_t pgd;
-
- if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
- p4d_p = ppd->pgtable_area;
- memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D);
- ppd->pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D;
-
- pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS);
- } else {
- pud_p = ppd->pgtable_area;
- memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
- ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
-
- pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS);
- }
- native_set_pgd(pgd_p, pgd);
- }
-
- if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
- p4d_p += p4d_index(ppd->vaddr);
- if (native_p4d_val(*p4d_p)) {
- pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK);
- } else {
- p4d_t p4d;
-
- pud_p = ppd->pgtable_area;
- memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
- ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
-
- p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS);
- native_set_p4d(p4d_p, p4d);
- }
- }
-
- pud_p += pud_index(ppd->vaddr);
- if (native_pud_val(*pud_p)) {
- if (native_pud_val(*pud_p) & _PAGE_PSE)
- return NULL;
-
- pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK);
- } else {
- pud_t pud;
-
- pmd_p = ppd->pgtable_area;
- memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD);
- ppd->pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD;
-
- pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS);
- native_set_pud(pud_p, pud);
- }
-
- return pmd_p;
-}
-
-static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
-{
- pmd_t *pmd_p;
-
- pmd_p = sme_prepare_pgd(ppd);
- if (!pmd_p)
- return;
-
- pmd_p += pmd_index(ppd->vaddr);
- if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE))
- native_set_pmd(pmd_p, native_make_pmd(ppd->paddr | ppd->pmd_flags));
-}
-
-static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
-{
- pmd_t *pmd_p;
- pte_t *pte_p;
-
- pmd_p = sme_prepare_pgd(ppd);
- if (!pmd_p)
- return;
-
- pmd_p += pmd_index(ppd->vaddr);
- if (native_pmd_val(*pmd_p)) {
- if (native_pmd_val(*pmd_p) & _PAGE_PSE)
- return;
-
- pte_p = (pte_t *)(native_pmd_val(*pmd_p) & ~PTE_FLAGS_MASK);
- } else {
- pmd_t pmd;
-
- pte_p = ppd->pgtable_area;
- memset(pte_p, 0, sizeof(*pte_p) * PTRS_PER_PTE);
- ppd->pgtable_area += sizeof(*pte_p) * PTRS_PER_PTE;
-
- pmd = native_make_pmd((pteval_t)pte_p + PMD_FLAGS);
- native_set_pmd(pmd_p, pmd);
- }
-
- pte_p += pte_index(ppd->vaddr);
- if (!native_pte_val(*pte_p))
- native_set_pte(pte_p, native_make_pte(ppd->paddr | ppd->pte_flags));
-}
-
-static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
-{
- while (ppd->vaddr < ppd->vaddr_end) {
- sme_populate_pgd_large(ppd);
-
- ppd->vaddr += PMD_PAGE_SIZE;
- ppd->paddr += PMD_PAGE_SIZE;
- }
-}
-
-static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
-{
- while (ppd->vaddr < ppd->vaddr_end) {
- sme_populate_pgd(ppd);
-
- ppd->vaddr += PAGE_SIZE;
- ppd->paddr += PAGE_SIZE;
- }
-}
-
-static void __init __sme_map_range(struct sme_populate_pgd_data *ppd,
- pmdval_t pmd_flags, pteval_t pte_flags)
-{
- unsigned long vaddr_end;
-
- ppd->pmd_flags = pmd_flags;
- ppd->pte_flags = pte_flags;
-
- /* Save original end value since we modify the struct value */
- vaddr_end = ppd->vaddr_end;
-
- /* If start is not 2MB aligned, create PTE entries */
- ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE);
- __sme_map_range_pte(ppd);
-
- /* Create PMD entries */
- ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK;
- __sme_map_range_pmd(ppd);
-
- /* If end is not 2MB aligned, create PTE entries */
- ppd->vaddr_end = vaddr_end;
- __sme_map_range_pte(ppd);
-}
-
-static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd)
-{
- __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC);
-}
-
-static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd)
-{
- __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC);
-}
-
-static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd)
-{
- __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP);
-}
-
-static unsigned long __init sme_pgtable_calc(unsigned long len)
-{
- unsigned long p4d_size, pud_size, pmd_size, pte_size;
- unsigned long total;
-
- /*
- * Perform a relatively simplistic calculation of the pagetable
- * entries that are needed. Those mappings will be covered mostly
- * by 2MB PMD entries so we can conservatively calculate the required
- * number of P4D, PUD and PMD structures needed to perform the
- * mappings. For mappings that are not 2MB aligned, PTE mappings
- * would be needed for the start and end portion of the address range
- * that fall outside of the 2MB alignment. This results in, at most,
- * two extra pages to hold PTE entries for each range that is mapped.
- * Incrementing the count for each covers the case where the addresses
- * cross entries.
- */
- if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
- p4d_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1;
- p4d_size *= sizeof(p4d_t) * PTRS_PER_P4D;
- pud_size = (ALIGN(len, P4D_SIZE) / P4D_SIZE) + 1;
- pud_size *= sizeof(pud_t) * PTRS_PER_PUD;
- } else {
- p4d_size = 0;
- pud_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1;
- pud_size *= sizeof(pud_t) * PTRS_PER_PUD;
- }
- pmd_size = (ALIGN(len, PUD_SIZE) / PUD_SIZE) + 1;
- pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD;
- pte_size = 2 * sizeof(pte_t) * PTRS_PER_PTE;
-
- total = p4d_size + pud_size + pmd_size + pte_size;
-
- /*
- * Now calculate the added pagetable structures needed to populate
- * the new pagetables.
- */
- if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
- p4d_size = ALIGN(total, PGDIR_SIZE) / PGDIR_SIZE;
- p4d_size *= sizeof(p4d_t) * PTRS_PER_P4D;
- pud_size = ALIGN(total, P4D_SIZE) / P4D_SIZE;
- pud_size *= sizeof(pud_t) * PTRS_PER_PUD;
- } else {
- p4d_size = 0;
- pud_size = ALIGN(total, PGDIR_SIZE) / PGDIR_SIZE;
- pud_size *= sizeof(pud_t) * PTRS_PER_PUD;
- }
- pmd_size = ALIGN(total, PUD_SIZE) / PUD_SIZE;
- pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD;
-
- total += p4d_size + pud_size + pmd_size;
-
- return total;
-}
-
-void __init __nostackprotector sme_encrypt_kernel(struct boot_params *bp)
-{
- unsigned long workarea_start, workarea_end, workarea_len;
- unsigned long execute_start, execute_end, execute_len;
- unsigned long kernel_start, kernel_end, kernel_len;
- unsigned long initrd_start, initrd_end, initrd_len;
- struct sme_populate_pgd_data ppd;
- unsigned long pgtable_area_len;
- unsigned long decrypted_base;
-
- if (!sme_active())
- return;
-
- /*
- * Prepare for encrypting the kernel and initrd by building new
- * pagetables with the necessary attributes needed to encrypt the
- * kernel in place.
- *
- * One range of virtual addresses will map the memory occupied
- * by the kernel and initrd as encrypted.
- *
- * Another range of virtual addresses will map the memory occupied
- * by the kernel and initrd as decrypted and write-protected.
- *
- * The use of write-protect attribute will prevent any of the
- * memory from being cached.
- */
-
- /* Physical addresses gives us the identity mapped virtual addresses */
- kernel_start = __pa_symbol(_text);
- kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE);
- kernel_len = kernel_end - kernel_start;
-
- initrd_start = 0;
- initrd_end = 0;
- initrd_len = 0;
-#ifdef CONFIG_BLK_DEV_INITRD
- initrd_len = (unsigned long)bp->hdr.ramdisk_size |
- ((unsigned long)bp->ext_ramdisk_size << 32);
- if (initrd_len) {
- initrd_start = (unsigned long)bp->hdr.ramdisk_image |
- ((unsigned long)bp->ext_ramdisk_image << 32);
- initrd_end = PAGE_ALIGN(initrd_start + initrd_len);
- initrd_len = initrd_end - initrd_start;
- }
-#endif
-
- /* Set the encryption workarea to be immediately after the kernel */
- workarea_start = kernel_end;
-
- /*
- * Calculate required number of workarea bytes needed:
- * executable encryption area size:
- * stack page (PAGE_SIZE)
- * encryption routine page (PAGE_SIZE)
- * intermediate copy buffer (PMD_PAGE_SIZE)
- * pagetable structures for the encryption of the kernel
- * pagetable structures for workarea (in case not currently mapped)
- */
- execute_start = workarea_start;
- execute_end = execute_start + (PAGE_SIZE * 2) + PMD_PAGE_SIZE;
- execute_len = execute_end - execute_start;
-
- /*
- * One PGD for both encrypted and decrypted mappings and a set of
- * PUDs and PMDs for each of the encrypted and decrypted mappings.
- */
- pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD;
- pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2;
- if (initrd_len)
- pgtable_area_len += sme_pgtable_calc(initrd_len) * 2;
-
- /* PUDs and PMDs needed in the current pagetables for the workarea */
- pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len);
-
- /*
- * The total workarea includes the executable encryption area and
- * the pagetable area. The start of the workarea is already 2MB
- * aligned, align the end of the workarea on a 2MB boundary so that
- * we don't try to create/allocate PTE entries from the workarea
- * before it is mapped.
- */
- workarea_len = execute_len + pgtable_area_len;
- workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE);
-
- /*
- * Set the address to the start of where newly created pagetable
- * structures (PGDs, PUDs and PMDs) will be allocated. New pagetable
- * structures are created when the workarea is added to the current
- * pagetables and when the new encrypted and decrypted kernel
- * mappings are populated.
- */
- ppd.pgtable_area = (void *)execute_end;
-
- /*
- * Make sure the current pagetable structure has entries for
- * addressing the workarea.
- */
- ppd.pgd = (pgd_t *)native_read_cr3_pa();
- ppd.paddr = workarea_start;
- ppd.vaddr = workarea_start;
- ppd.vaddr_end = workarea_end;
- sme_map_range_decrypted(&ppd);
-
- /* Flush the TLB - no globals so cr3 is enough */
- native_write_cr3(__native_read_cr3());
-
- /*
- * A new pagetable structure is being built to allow for the kernel
- * and initrd to be encrypted. It starts with an empty PGD that will
- * then be populated with new PUDs and PMDs as the encrypted and
- * decrypted kernel mappings are created.
- */
- ppd.pgd = ppd.pgtable_area;
- memset(ppd.pgd, 0, sizeof(pgd_t) * PTRS_PER_PGD);
- ppd.pgtable_area += sizeof(pgd_t) * PTRS_PER_PGD;
-
- /*
- * A different PGD index/entry must be used to get different
- * pagetable entries for the decrypted mapping. Choose the next
- * PGD index and convert it to a virtual address to be used as
- * the base of the mapping.
- */
- decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1);
- if (initrd_len) {
- unsigned long check_base;
-
- check_base = (pgd_index(initrd_end) + 1) & (PTRS_PER_PGD - 1);
- decrypted_base = max(decrypted_base, check_base);
- }
- decrypted_base <<= PGDIR_SHIFT;
-
- /* Add encrypted kernel (identity) mappings */
- ppd.paddr = kernel_start;
- ppd.vaddr = kernel_start;
- ppd.vaddr_end = kernel_end;
- sme_map_range_encrypted(&ppd);
-
- /* Add decrypted, write-protected kernel (non-identity) mappings */
- ppd.paddr = kernel_start;
- ppd.vaddr = kernel_start + decrypted_base;
- ppd.vaddr_end = kernel_end + decrypted_base;
- sme_map_range_decrypted_wp(&ppd);
-
- if (initrd_len) {
- /* Add encrypted initrd (identity) mappings */
- ppd.paddr = initrd_start;
- ppd.vaddr = initrd_start;
- ppd.vaddr_end = initrd_end;
- sme_map_range_encrypted(&ppd);
- /*
- * Add decrypted, write-protected initrd (non-identity) mappings
- */
- ppd.paddr = initrd_start;
- ppd.vaddr = initrd_start + decrypted_base;
- ppd.vaddr_end = initrd_end + decrypted_base;
- sme_map_range_decrypted_wp(&ppd);
- }
-
- /* Add decrypted workarea mappings to both kernel mappings */
- ppd.paddr = workarea_start;
- ppd.vaddr = workarea_start;
- ppd.vaddr_end = workarea_end;
- sme_map_range_decrypted(&ppd);
-
- ppd.paddr = workarea_start;
- ppd.vaddr = workarea_start + decrypted_base;
- ppd.vaddr_end = workarea_end + decrypted_base;
- sme_map_range_decrypted(&ppd);
-
- /* Perform the encryption */
- sme_encrypt_execute(kernel_start, kernel_start + decrypted_base,
- kernel_len, workarea_start, (unsigned long)ppd.pgd);
-
- if (initrd_len)
- sme_encrypt_execute(initrd_start, initrd_start + decrypted_base,
- initrd_len, workarea_start,
- (unsigned long)ppd.pgd);
-
- /*
- * At this point we are running encrypted. Remove the mappings for
- * the decrypted areas - all that is needed for this is to remove
- * the PGD entry/entries.
- */
- ppd.vaddr = kernel_start + decrypted_base;
- ppd.vaddr_end = kernel_end + decrypted_base;
- sme_clear_pgd(&ppd);
-
- if (initrd_len) {
- ppd.vaddr = initrd_start + decrypted_base;
- ppd.vaddr_end = initrd_end + decrypted_base;
- sme_clear_pgd(&ppd);
- }
-
- ppd.vaddr = workarea_start + decrypted_base;
- ppd.vaddr_end = workarea_end + decrypted_base;
- sme_clear_pgd(&ppd);
-
- /* Flush the TLB - no globals so cr3 is enough */
- native_write_cr3(__native_read_cr3());
-}
-
-void __init __nostackprotector sme_enable(struct boot_params *bp)
-{
- const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off;
- unsigned int eax, ebx, ecx, edx;
- unsigned long feature_mask;
- bool active_by_default;
- unsigned long me_mask;
- char buffer[16];
- u64 msr;
-
- /* Check for the SME/SEV support leaf */
- eax = 0x80000000;
- ecx = 0;
- native_cpuid(&eax, &ebx, &ecx, &edx);
- if (eax < 0x8000001f)
- return;
-
-#define AMD_SME_BIT BIT(0)
-#define AMD_SEV_BIT BIT(1)
- /*
- * Set the feature mask (SME or SEV) based on whether we are
- * running under a hypervisor.
- */
- eax = 1;
- ecx = 0;
- native_cpuid(&eax, &ebx, &ecx, &edx);
- feature_mask = (ecx & BIT(31)) ? AMD_SEV_BIT : AMD_SME_BIT;
-
- /*
- * Check for the SME/SEV feature:
- * CPUID Fn8000_001F[EAX]
- * - Bit 0 - Secure Memory Encryption support
- * - Bit 1 - Secure Encrypted Virtualization support
- * CPUID Fn8000_001F[EBX]
- * - Bits 5:0 - Pagetable bit position used to indicate encryption
- */
- eax = 0x8000001f;
- ecx = 0;
- native_cpuid(&eax, &ebx, &ecx, &edx);
- if (!(eax & feature_mask))
- return;
-
- me_mask = 1UL << (ebx & 0x3f);
-
- /* Check if memory encryption is enabled */
- if (feature_mask == AMD_SME_BIT) {
- /* For SME, check the SYSCFG MSR */
- msr = __rdmsr(MSR_K8_SYSCFG);
- if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
- return;
- } else {
- /* For SEV, check the SEV MSR */
- msr = __rdmsr(MSR_AMD64_SEV);
- if (!(msr & MSR_AMD64_SEV_ENABLED))
- return;
-
- /* SEV state cannot be controlled by a command line option */
- sme_me_mask = me_mask;
- sev_enabled = true;
- return;
- }
-
- /*
- * Fixups have not been applied to phys_base yet and we're running
- * identity mapped, so we must obtain the address to the SME command
- * line argument data using rip-relative addressing.
- */
- asm ("lea sme_cmdline_arg(%%rip), %0"
- : "=r" (cmdline_arg)
- : "p" (sme_cmdline_arg));
- asm ("lea sme_cmdline_on(%%rip), %0"
- : "=r" (cmdline_on)
- : "p" (sme_cmdline_on));
- asm ("lea sme_cmdline_off(%%rip), %0"
- : "=r" (cmdline_off)
- : "p" (sme_cmdline_off));
-
- if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT))
- active_by_default = true;
- else
- active_by_default = false;
-
- cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr |
- ((u64)bp->ext_cmd_line_ptr << 32));
-
- cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer));
-
- if (!strncmp(buffer, cmdline_on, sizeof(buffer)))
- sme_me_mask = me_mask;
- else if (!strncmp(buffer, cmdline_off, sizeof(buffer)))
- sme_me_mask = 0;
- else
- sme_me_mask = active_by_default ? me_mask : 0;
-}
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
new file mode 100644
index 000000000000..1b2197d13832
--- /dev/null
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -0,0 +1,564 @@
+/*
+ * AMD Memory Encryption Support
+ *
+ * Copyright (C) 2016 Advanced Micro Devices, Inc.
+ *
+ * Author: Tom Lendacky <thomas.lendacky@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define DISABLE_BRANCH_PROFILING
+
+/*
+ * Since we're dealing with identity mappings, physical and virtual
+ * addresses are the same, so override these defines which are ultimately
+ * used by the headers in misc.h.
+ */
+#define __pa(x) ((unsigned long)(x))
+#define __va(x) ((void *)((unsigned long)(x)))
+
+/*
+ * Special hack: we have to be careful, because no indirections are
+ * allowed here, and paravirt_ops is a kind of one. As it will only run in
+ * baremetal anyway, we just keep it from happening. (This list needs to
+ * be extended when new paravirt and debugging variants are added.)
+ */
+#undef CONFIG_PARAVIRT
+#undef CONFIG_PARAVIRT_SPINLOCKS
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/mem_encrypt.h>
+
+#include <asm/setup.h>
+#include <asm/sections.h>
+#include <asm/cmdline.h>
+
+#include "mm_internal.h"
+
+#define PGD_FLAGS _KERNPG_TABLE_NOENC
+#define P4D_FLAGS _KERNPG_TABLE_NOENC
+#define PUD_FLAGS _KERNPG_TABLE_NOENC
+#define PMD_FLAGS _KERNPG_TABLE_NOENC
+
+#define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL)
+
+#define PMD_FLAGS_DEC PMD_FLAGS_LARGE
+#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
+ (_PAGE_PAT | _PAGE_PWT))
+
+#define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC)
+
+#define PTE_FLAGS (__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL)
+
+#define PTE_FLAGS_DEC PTE_FLAGS
+#define PTE_FLAGS_DEC_WP ((PTE_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
+ (_PAGE_PAT | _PAGE_PWT))
+
+#define PTE_FLAGS_ENC (PTE_FLAGS | _PAGE_ENC)
+
+struct sme_populate_pgd_data {
+ void *pgtable_area;
+ pgd_t *pgd;
+
+ pmdval_t pmd_flags;
+ pteval_t pte_flags;
+ unsigned long paddr;
+
+ unsigned long vaddr;
+ unsigned long vaddr_end;
+};
+
+static char sme_cmdline_arg[] __initdata = "mem_encrypt";
+static char sme_cmdline_on[] __initdata = "on";
+static char sme_cmdline_off[] __initdata = "off";
+
+static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
+{
+ unsigned long pgd_start, pgd_end, pgd_size;
+ pgd_t *pgd_p;
+
+ pgd_start = ppd->vaddr & PGDIR_MASK;
+ pgd_end = ppd->vaddr_end & PGDIR_MASK;
+
+ pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1) * sizeof(pgd_t);
+
+ pgd_p = ppd->pgd + pgd_index(ppd->vaddr);
+
+ memset(pgd_p, 0, pgd_size);
+}
+
+static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
+{
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ pgd = ppd->pgd + pgd_index(ppd->vaddr);
+ if (pgd_none(*pgd)) {
+ p4d = ppd->pgtable_area;
+ memset(p4d, 0, sizeof(*p4d) * PTRS_PER_P4D);
+ ppd->pgtable_area += sizeof(*p4d) * PTRS_PER_P4D;
+ set_pgd(pgd, __pgd(PGD_FLAGS | __pa(p4d)));
+ }
+
+ p4d = p4d_offset(pgd, ppd->vaddr);
+ if (p4d_none(*p4d)) {
+ pud = ppd->pgtable_area;
+ memset(pud, 0, sizeof(*pud) * PTRS_PER_PUD);
+ ppd->pgtable_area += sizeof(*pud) * PTRS_PER_PUD;
+ set_p4d(p4d, __p4d(P4D_FLAGS | __pa(pud)));
+ }
+
+ pud = pud_offset(p4d, ppd->vaddr);
+ if (pud_none(*pud)) {
+ pmd = ppd->pgtable_area;
+ memset(pmd, 0, sizeof(*pmd) * PTRS_PER_PMD);
+ ppd->pgtable_area += sizeof(*pmd) * PTRS_PER_PMD;
+ set_pud(pud, __pud(PUD_FLAGS | __pa(pmd)));
+ }
+
+ if (pud_large(*pud))
+ return NULL;
+
+ return pud;
+}
+
+static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
+{
+ pud_t *pud;
+ pmd_t *pmd;
+
+ pud = sme_prepare_pgd(ppd);
+ if (!pud)
+ return;
+
+ pmd = pmd_offset(pud, ppd->vaddr);
+ if (pmd_large(*pmd))
+ return;
+
+ set_pmd(pmd, __pmd(ppd->paddr | ppd->pmd_flags));
+}
+
+static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
+{
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pud = sme_prepare_pgd(ppd);
+ if (!pud)
+ return;
+
+ pmd = pmd_offset(pud, ppd->vaddr);
+ if (pmd_none(*pmd)) {
+ pte = ppd->pgtable_area;
+ memset(pte, 0, sizeof(pte) * PTRS_PER_PTE);
+ ppd->pgtable_area += sizeof(pte) * PTRS_PER_PTE;
+ set_pmd(pmd, __pmd(PMD_FLAGS | __pa(pte)));
+ }
+
+ if (pmd_large(*pmd))
+ return;
+
+ pte = pte_offset_map(pmd, ppd->vaddr);
+ if (pte_none(*pte))
+ set_pte(pte, __pte(ppd->paddr | ppd->pte_flags));
+}
+
+static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
+{
+ while (ppd->vaddr < ppd->vaddr_end) {
+ sme_populate_pgd_large(ppd);
+
+ ppd->vaddr += PMD_PAGE_SIZE;
+ ppd->paddr += PMD_PAGE_SIZE;
+ }
+}
+
+static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
+{
+ while (ppd->vaddr < ppd->vaddr_end) {
+ sme_populate_pgd(ppd);
+
+ ppd->vaddr += PAGE_SIZE;
+ ppd->paddr += PAGE_SIZE;
+ }
+}
+
+static void __init __sme_map_range(struct sme_populate_pgd_data *ppd,
+ pmdval_t pmd_flags, pteval_t pte_flags)
+{
+ unsigned long vaddr_end;
+
+ ppd->pmd_flags = pmd_flags;
+ ppd->pte_flags = pte_flags;
+
+ /* Save original end value since we modify the struct value */
+ vaddr_end = ppd->vaddr_end;
+
+ /* If start is not 2MB aligned, create PTE entries */
+ ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE);
+ __sme_map_range_pte(ppd);
+
+ /* Create PMD entries */
+ ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK;
+ __sme_map_range_pmd(ppd);
+
+ /* If end is not 2MB aligned, create PTE entries */
+ ppd->vaddr_end = vaddr_end;
+ __sme_map_range_pte(ppd);
+}
+
+static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd)
+{
+ __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC);
+}
+
+static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd)
+{
+ __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC);
+}
+
+static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd)
+{
+ __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP);
+}
+
+static unsigned long __init sme_pgtable_calc(unsigned long len)
+{
+ unsigned long entries = 0, tables = 0;
+
+ /*
+ * Perform a relatively simplistic calculation of the pagetable
+ * entries that are needed. Those mappings will be covered mostly
+ * by 2MB PMD entries so we can conservatively calculate the required
+ * number of P4D, PUD and PMD structures needed to perform the
+ * mappings. For mappings that are not 2MB aligned, PTE mappings
+ * would be needed for the start and end portion of the address range
+ * that fall outside of the 2MB alignment. This results in, at most,
+ * two extra pages to hold PTE entries for each range that is mapped.
+ * Incrementing the count for each covers the case where the addresses
+ * cross entries.
+ */
+
+ /* PGDIR_SIZE is equal to P4D_SIZE on 4-level machine. */
+ if (PTRS_PER_P4D > 1)
+ entries += (DIV_ROUND_UP(len, PGDIR_SIZE) + 1) * sizeof(p4d_t) * PTRS_PER_P4D;
+ entries += (DIV_ROUND_UP(len, P4D_SIZE) + 1) * sizeof(pud_t) * PTRS_PER_PUD;
+ entries += (DIV_ROUND_UP(len, PUD_SIZE) + 1) * sizeof(pmd_t) * PTRS_PER_PMD;
+ entries += 2 * sizeof(pte_t) * PTRS_PER_PTE;
+
+ /*
+ * Now calculate the added pagetable structures needed to populate
+ * the new pagetables.
+ */
+
+ if (PTRS_PER_P4D > 1)
+ tables += DIV_ROUND_UP(entries, PGDIR_SIZE) * sizeof(p4d_t) * PTRS_PER_P4D;
+ tables += DIV_ROUND_UP(entries, P4D_SIZE) * sizeof(pud_t) * PTRS_PER_PUD;
+ tables += DIV_ROUND_UP(entries, PUD_SIZE) * sizeof(pmd_t) * PTRS_PER_PMD;
+
+ return entries + tables;
+}
+
+void __init sme_encrypt_kernel(struct boot_params *bp)
+{
+ unsigned long workarea_start, workarea_end, workarea_len;
+ unsigned long execute_start, execute_end, execute_len;
+ unsigned long kernel_start, kernel_end, kernel_len;
+ unsigned long initrd_start, initrd_end, initrd_len;
+ struct sme_populate_pgd_data ppd;
+ unsigned long pgtable_area_len;
+ unsigned long decrypted_base;
+
+ if (!sme_active())
+ return;
+
+ /*
+ * Prepare for encrypting the kernel and initrd by building new
+ * pagetables with the necessary attributes needed to encrypt the
+ * kernel in place.
+ *
+ * One range of virtual addresses will map the memory occupied
+ * by the kernel and initrd as encrypted.
+ *
+ * Another range of virtual addresses will map the memory occupied
+ * by the kernel and initrd as decrypted and write-protected.
+ *
+ * The use of write-protect attribute will prevent any of the
+ * memory from being cached.
+ */
+
+ /* Physical addresses gives us the identity mapped virtual addresses */
+ kernel_start = __pa_symbol(_text);
+ kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE);
+ kernel_len = kernel_end - kernel_start;
+
+ initrd_start = 0;
+ initrd_end = 0;
+ initrd_len = 0;
+#ifdef CONFIG_BLK_DEV_INITRD
+ initrd_len = (unsigned long)bp->hdr.ramdisk_size |
+ ((unsigned long)bp->ext_ramdisk_size << 32);
+ if (initrd_len) {
+ initrd_start = (unsigned long)bp->hdr.ramdisk_image |
+ ((unsigned long)bp->ext_ramdisk_image << 32);
+ initrd_end = PAGE_ALIGN(initrd_start + initrd_len);
+ initrd_len = initrd_end - initrd_start;
+ }
+#endif
+
+ /* Set the encryption workarea to be immediately after the kernel */
+ workarea_start = kernel_end;
+
+ /*
+ * Calculate required number of workarea bytes needed:
+ * executable encryption area size:
+ * stack page (PAGE_SIZE)
+ * encryption routine page (PAGE_SIZE)
+ * intermediate copy buffer (PMD_PAGE_SIZE)
+ * pagetable structures for the encryption of the kernel
+ * pagetable structures for workarea (in case not currently mapped)
+ */
+ execute_start = workarea_start;
+ execute_end = execute_start + (PAGE_SIZE * 2) + PMD_PAGE_SIZE;
+ execute_len = execute_end - execute_start;
+
+ /*
+ * One PGD for both encrypted and decrypted mappings and a set of
+ * PUDs and PMDs for each of the encrypted and decrypted mappings.
+ */
+ pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD;
+ pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2;
+ if (initrd_len)
+ pgtable_area_len += sme_pgtable_calc(initrd_len) * 2;
+
+ /* PUDs and PMDs needed in the current pagetables for the workarea */
+ pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len);
+
+ /*
+ * The total workarea includes the executable encryption area and
+ * the pagetable area. The start of the workarea is already 2MB
+ * aligned, align the end of the workarea on a 2MB boundary so that
+ * we don't try to create/allocate PTE entries from the workarea
+ * before it is mapped.
+ */
+ workarea_len = execute_len + pgtable_area_len;
+ workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE);
+
+ /*
+ * Set the address to the start of where newly created pagetable
+ * structures (PGDs, PUDs and PMDs) will be allocated. New pagetable
+ * structures are created when the workarea is added to the current
+ * pagetables and when the new encrypted and decrypted kernel
+ * mappings are populated.
+ */
+ ppd.pgtable_area = (void *)execute_end;
+
+ /*
+ * Make sure the current pagetable structure has entries for
+ * addressing the workarea.
+ */
+ ppd.pgd = (pgd_t *)native_read_cr3_pa();
+ ppd.paddr = workarea_start;
+ ppd.vaddr = workarea_start;
+ ppd.vaddr_end = workarea_end;
+ sme_map_range_decrypted(&ppd);
+
+ /* Flush the TLB - no globals so cr3 is enough */
+ native_write_cr3(__native_read_cr3());
+
+ /*
+ * A new pagetable structure is being built to allow for the kernel
+ * and initrd to be encrypted. It starts with an empty PGD that will
+ * then be populated with new PUDs and PMDs as the encrypted and
+ * decrypted kernel mappings are created.
+ */
+ ppd.pgd = ppd.pgtable_area;
+ memset(ppd.pgd, 0, sizeof(pgd_t) * PTRS_PER_PGD);
+ ppd.pgtable_area += sizeof(pgd_t) * PTRS_PER_PGD;
+
+ /*
+ * A different PGD index/entry must be used to get different
+ * pagetable entries for the decrypted mapping. Choose the next
+ * PGD index and convert it to a virtual address to be used as
+ * the base of the mapping.
+ */
+ decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1);
+ if (initrd_len) {
+ unsigned long check_base;
+
+ check_base = (pgd_index(initrd_end) + 1) & (PTRS_PER_PGD - 1);
+ decrypted_base = max(decrypted_base, check_base);
+ }
+ decrypted_base <<= PGDIR_SHIFT;
+
+ /* Add encrypted kernel (identity) mappings */
+ ppd.paddr = kernel_start;
+ ppd.vaddr = kernel_start;
+ ppd.vaddr_end = kernel_end;
+ sme_map_range_encrypted(&ppd);
+
+ /* Add decrypted, write-protected kernel (non-identity) mappings */
+ ppd.paddr = kernel_start;
+ ppd.vaddr = kernel_start + decrypted_base;
+ ppd.vaddr_end = kernel_end + decrypted_base;
+ sme_map_range_decrypted_wp(&ppd);
+
+ if (initrd_len) {
+ /* Add encrypted initrd (identity) mappings */
+ ppd.paddr = initrd_start;
+ ppd.vaddr = initrd_start;
+ ppd.vaddr_end = initrd_end;
+ sme_map_range_encrypted(&ppd);
+ /*
+ * Add decrypted, write-protected initrd (non-identity) mappings
+ */
+ ppd.paddr = initrd_start;
+ ppd.vaddr = initrd_start + decrypted_base;
+ ppd.vaddr_end = initrd_end + decrypted_base;
+ sme_map_range_decrypted_wp(&ppd);
+ }
+
+ /* Add decrypted workarea mappings to both kernel mappings */
+ ppd.paddr = workarea_start;
+ ppd.vaddr = workarea_start;
+ ppd.vaddr_end = workarea_end;
+ sme_map_range_decrypted(&ppd);
+
+ ppd.paddr = workarea_start;
+ ppd.vaddr = workarea_start + decrypted_base;
+ ppd.vaddr_end = workarea_end + decrypted_base;
+ sme_map_range_decrypted(&ppd);
+
+ /* Perform the encryption */
+ sme_encrypt_execute(kernel_start, kernel_start + decrypted_base,
+ kernel_len, workarea_start, (unsigned long)ppd.pgd);
+
+ if (initrd_len)
+ sme_encrypt_execute(initrd_start, initrd_start + decrypted_base,
+ initrd_len, workarea_start,
+ (unsigned long)ppd.pgd);
+
+ /*
+ * At this point we are running encrypted. Remove the mappings for
+ * the decrypted areas - all that is needed for this is to remove
+ * the PGD entry/entries.
+ */
+ ppd.vaddr = kernel_start + decrypted_base;
+ ppd.vaddr_end = kernel_end + decrypted_base;
+ sme_clear_pgd(&ppd);
+
+ if (initrd_len) {
+ ppd.vaddr = initrd_start + decrypted_base;
+ ppd.vaddr_end = initrd_end + decrypted_base;
+ sme_clear_pgd(&ppd);
+ }
+
+ ppd.vaddr = workarea_start + decrypted_base;
+ ppd.vaddr_end = workarea_end + decrypted_base;
+ sme_clear_pgd(&ppd);
+
+ /* Flush the TLB - no globals so cr3 is enough */
+ native_write_cr3(__native_read_cr3());
+}
+
+void __init sme_enable(struct boot_params *bp)
+{
+ const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off;
+ unsigned int eax, ebx, ecx, edx;
+ unsigned long feature_mask;
+ bool active_by_default;
+ unsigned long me_mask;
+ char buffer[16];
+ u64 msr;
+
+ /* Check for the SME/SEV support leaf */
+ eax = 0x80000000;
+ ecx = 0;
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+ if (eax < 0x8000001f)
+ return;
+
+#define AMD_SME_BIT BIT(0)
+#define AMD_SEV_BIT BIT(1)
+ /*
+ * Set the feature mask (SME or SEV) based on whether we are
+ * running under a hypervisor.
+ */
+ eax = 1;
+ ecx = 0;
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+ feature_mask = (ecx & BIT(31)) ? AMD_SEV_BIT : AMD_SME_BIT;
+
+ /*
+ * Check for the SME/SEV feature:
+ * CPUID Fn8000_001F[EAX]
+ * - Bit 0 - Secure Memory Encryption support
+ * - Bit 1 - Secure Encrypted Virtualization support
+ * CPUID Fn8000_001F[EBX]
+ * - Bits 5:0 - Pagetable bit position used to indicate encryption
+ */
+ eax = 0x8000001f;
+ ecx = 0;
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+ if (!(eax & feature_mask))
+ return;
+
+ me_mask = 1UL << (ebx & 0x3f);
+
+ /* Check if memory encryption is enabled */
+ if (feature_mask == AMD_SME_BIT) {
+ /* For SME, check the SYSCFG MSR */
+ msr = __rdmsr(MSR_K8_SYSCFG);
+ if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
+ return;
+ } else {
+ /* For SEV, check the SEV MSR */
+ msr = __rdmsr(MSR_AMD64_SEV);
+ if (!(msr & MSR_AMD64_SEV_ENABLED))
+ return;
+
+ /* SEV state cannot be controlled by a command line option */
+ sme_me_mask = me_mask;
+ sev_enabled = true;
+ return;
+ }
+
+ /*
+ * Fixups have not been applied to phys_base yet and we're running
+ * identity mapped, so we must obtain the address to the SME command
+ * line argument data using rip-relative addressing.
+ */
+ asm ("lea sme_cmdline_arg(%%rip), %0"
+ : "=r" (cmdline_arg)
+ : "p" (sme_cmdline_arg));
+ asm ("lea sme_cmdline_on(%%rip), %0"
+ : "=r" (cmdline_on)
+ : "p" (sme_cmdline_on));
+ asm ("lea sme_cmdline_off(%%rip), %0"
+ : "=r" (cmdline_off)
+ : "p" (sme_cmdline_off));
+
+ if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT))
+ active_by_default = true;
+ else
+ active_by_default = false;
+
+ cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr |
+ ((u64)bp->ext_cmd_line_ptr << 32));
+
+ cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer));
+
+ if (!strncmp(buffer, cmdline_on, sizeof(buffer)))
+ sme_me_mask = me_mask;
+ else if (!strncmp(buffer, cmdline_off, sizeof(buffer)))
+ sme_me_mask = 0;
+ else
+ sme_me_mask = active_by_default ? me_mask : 0;
+}
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index aca6295350f3..e8a4a09e20f1 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -60,17 +60,6 @@ void memory_present(int nid, unsigned long start, unsigned long end)
}
printk(KERN_CONT "\n");
}
-
-unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn,
- unsigned long end_pfn)
-{
- unsigned long nr_pages = end_pfn - start_pfn;
-
- if (!nr_pages)
- return 0;
-
- return (nr_pages + 1) * sizeof(struct page);
-}
#endif
extern unsigned long highend_pfn, highstart_pfn;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 004abf9ebf12..34cda7e0551b 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -702,4 +702,52 @@ int pmd_clear_huge(pmd_t *pmd)
return 0;
}
+
+/**
+ * pud_free_pmd_page - Clear pud entry and free pmd page.
+ * @pud: Pointer to a PUD.
+ *
+ * Context: The pud range has been unmaped and TLB purged.
+ * Return: 1 if clearing the entry succeeded. 0 otherwise.
+ */
+int pud_free_pmd_page(pud_t *pud)
+{
+ pmd_t *pmd;
+ int i;
+
+ if (pud_none(*pud))
+ return 1;
+
+ pmd = (pmd_t *)pud_page_vaddr(*pud);
+
+ for (i = 0; i < PTRS_PER_PMD; i++)
+ if (!pmd_free_pte_page(&pmd[i]))
+ return 0;
+
+ pud_clear(pud);
+ free_page((unsigned long)pmd);
+
+ return 1;
+}
+
+/**
+ * pmd_free_pte_page - Clear pmd entry and free pte page.
+ * @pmd: Pointer to a PMD.
+ *
+ * Context: The pmd range has been unmaped and TLB purged.
+ * Return: 1 if clearing the entry succeeded. 0 otherwise.
+ */
+int pmd_free_pte_page(pmd_t *pmd)
+{
+ pte_t *pte;
+
+ if (pmd_none(*pmd))
+ return 1;
+
+ pte = (pte_t *)pmd_page_vaddr(*pmd);
+ pmd_clear(pmd);
+ free_page((unsigned long)pte);
+
+ return 1;
+}
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 7f1a51399674..e055d1a06699 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -157,7 +157,7 @@ static void sync_current_stack_to_mm(struct mm_struct *mm)
unsigned long sp = current_stack_pointer;
pgd_t *pgd = pgd_offset(mm, sp);
- if (CONFIG_PGTABLE_LEVELS > 4) {
+ if (pgtable_l5_enabled) {
if (unlikely(pgd_none(*pgd))) {
pgd_t *pgd_ref = pgd_offset_k(sp);
@@ -613,7 +613,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
{
int cpu;
- struct flush_tlb_info info = {
+ struct flush_tlb_info info __aligned(SMP_CACHE_BYTES) = {
.mm = mm,
};
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 45e4eb5bcbb2..b725154182cc 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -11,10 +11,10 @@
#include <linux/netdevice.h>
#include <linux/filter.h>
#include <linux/if_vlan.h>
-#include <asm/cacheflush.h>
+#include <linux/bpf.h>
+
#include <asm/set_memory.h>
#include <asm/nospec-branch.h>
-#include <linux/bpf.h>
/*
* assembly code in arch/x86/net/bpf_jit.S
@@ -61,7 +61,12 @@ static bool is_imm8(int value)
static bool is_simm32(s64 value)
{
- return value == (s64) (s32) value;
+ return value == (s64)(s32)value;
+}
+
+static bool is_uimm32(u64 value)
+{
+ return value == (u64)(u32)value;
}
/* mov dst, src */
@@ -98,16 +103,6 @@ static int bpf_size_to_x86_bytes(int bpf_size)
#define X86_JLE 0x7E
#define X86_JG 0x7F
-static void bpf_flush_icache(void *start, void *end)
-{
- mm_segment_t old_fs = get_fs();
-
- set_fs(KERNEL_DS);
- smp_wmb();
- flush_icache_range((unsigned long)start, (unsigned long)end);
- set_fs(old_fs);
-}
-
#define CHOOSE_LOAD_FUNC(K, func) \
((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
@@ -212,7 +207,7 @@ struct jit_context {
/* emit x64 prologue code for BPF program and check it's size.
* bpf_tail_call helper will skip it while jumping into another program
*/
-static void emit_prologue(u8 **pprog, u32 stack_depth)
+static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
{
u8 *prog = *pprog;
int cnt = 0;
@@ -247,18 +242,21 @@ static void emit_prologue(u8 **pprog, u32 stack_depth)
/* mov qword ptr [rbp+24],r15 */
EMIT4(0x4C, 0x89, 0x7D, 24);
- /* Clear the tail call counter (tail_call_cnt): for eBPF tail calls
- * we need to reset the counter to 0. It's done in two instructions,
- * resetting rax register to 0 (xor on eax gets 0 extended), and
- * moving it to the counter location.
- */
+ if (!ebpf_from_cbpf) {
+ /* Clear the tail call counter (tail_call_cnt): for eBPF tail
+ * calls we need to reset the counter to 0. It's done in two
+ * instructions, resetting rax register to 0, and moving it
+ * to the counter location.
+ */
- /* xor eax, eax */
- EMIT2(0x31, 0xc0);
- /* mov qword ptr [rbp+32], rax */
- EMIT4(0x48, 0x89, 0x45, 32);
+ /* xor eax, eax */
+ EMIT2(0x31, 0xc0);
+ /* mov qword ptr [rbp+32], rax */
+ EMIT4(0x48, 0x89, 0x45, 32);
+
+ BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
+ }
- BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
*pprog = prog;
}
@@ -356,6 +354,86 @@ static void emit_load_skb_data_hlen(u8 **pprog)
*pprog = prog;
}
+static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
+ u32 dst_reg, const u32 imm32)
+{
+ u8 *prog = *pprog;
+ u8 b1, b2, b3;
+ int cnt = 0;
+
+ /* optimization: if imm32 is positive, use 'mov %eax, imm32'
+ * (which zero-extends imm32) to save 2 bytes.
+ */
+ if (sign_propagate && (s32)imm32 < 0) {
+ /* 'mov %rax, imm32' sign extends imm32 */
+ b1 = add_1mod(0x48, dst_reg);
+ b2 = 0xC7;
+ b3 = 0xC0;
+ EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32);
+ goto done;
+ }
+
+ /* optimization: if imm32 is zero, use 'xor %eax, %eax'
+ * to save 3 bytes.
+ */
+ if (imm32 == 0) {
+ if (is_ereg(dst_reg))
+ EMIT1(add_2mod(0x40, dst_reg, dst_reg));
+ b2 = 0x31; /* xor */
+ b3 = 0xC0;
+ EMIT2(b2, add_2reg(b3, dst_reg, dst_reg));
+ goto done;
+ }
+
+ /* mov %eax, imm32 */
+ if (is_ereg(dst_reg))
+ EMIT1(add_1mod(0x40, dst_reg));
+ EMIT1_off32(add_1reg(0xB8, dst_reg), imm32);
+done:
+ *pprog = prog;
+}
+
+static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
+ const u32 imm32_hi, const u32 imm32_lo)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+
+ if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) {
+ /* For emitting plain u32, where sign bit must not be
+ * propagated LLVM tends to load imm64 over mov32
+ * directly, so save couple of bytes by just doing
+ * 'mov %eax, imm32' instead.
+ */
+ emit_mov_imm32(&prog, false, dst_reg, imm32_lo);
+ } else {
+ /* movabsq %rax, imm64 */
+ EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));
+ EMIT(imm32_lo, 4);
+ EMIT(imm32_hi, 4);
+ }
+
+ *pprog = prog;
+}
+
+static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+
+ if (is64) {
+ /* mov dst, src */
+ EMIT_mov(dst_reg, src_reg);
+ } else {
+ /* mov32 dst, src */
+ if (is_ereg(dst_reg) || is_ereg(src_reg))
+ EMIT1(add_2mod(0x40, dst_reg, src_reg));
+ EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg));
+ }
+
+ *pprog = prog;
+}
+
static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
int oldproglen, struct jit_context *ctx)
{
@@ -369,7 +447,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
int proglen = 0;
u8 *prog = temp;
- emit_prologue(&prog, bpf_prog->aux->stack_depth);
+ emit_prologue(&prog, bpf_prog->aux->stack_depth,
+ bpf_prog_was_classic(bpf_prog));
if (seen_ld_abs)
emit_load_skb_data_hlen(&prog);
@@ -378,7 +457,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
const s32 imm32 = insn->imm;
u32 dst_reg = insn->dst_reg;
u32 src_reg = insn->src_reg;
- u8 b1 = 0, b2 = 0, b3 = 0;
+ u8 b2 = 0, b3 = 0;
s64 jmp_offset;
u8 jmp_cond;
bool reload_skb_data;
@@ -414,16 +493,11 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg));
break;
- /* mov dst, src */
case BPF_ALU64 | BPF_MOV | BPF_X:
- EMIT_mov(dst_reg, src_reg);
- break;
-
- /* mov32 dst, src */
case BPF_ALU | BPF_MOV | BPF_X:
- if (is_ereg(dst_reg) || is_ereg(src_reg))
- EMIT1(add_2mod(0x40, dst_reg, src_reg));
- EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg));
+ emit_mov_reg(&prog,
+ BPF_CLASS(insn->code) == BPF_ALU64,
+ dst_reg, src_reg);
break;
/* neg dst */
@@ -486,58 +560,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
break;
case BPF_ALU64 | BPF_MOV | BPF_K:
- /* optimization: if imm32 is positive,
- * use 'mov eax, imm32' (which zero-extends imm32)
- * to save 2 bytes
- */
- if (imm32 < 0) {
- /* 'mov rax, imm32' sign extends imm32 */
- b1 = add_1mod(0x48, dst_reg);
- b2 = 0xC7;
- b3 = 0xC0;
- EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32);
- break;
- }
-
case BPF_ALU | BPF_MOV | BPF_K:
- /* optimization: if imm32 is zero, use 'xor <dst>,<dst>'
- * to save 3 bytes.
- */
- if (imm32 == 0) {
- if (is_ereg(dst_reg))
- EMIT1(add_2mod(0x40, dst_reg, dst_reg));
- b2 = 0x31; /* xor */
- b3 = 0xC0;
- EMIT2(b2, add_2reg(b3, dst_reg, dst_reg));
- break;
- }
-
- /* mov %eax, imm32 */
- if (is_ereg(dst_reg))
- EMIT1(add_1mod(0x40, dst_reg));
- EMIT1_off32(add_1reg(0xB8, dst_reg), imm32);
+ emit_mov_imm32(&prog, BPF_CLASS(insn->code) == BPF_ALU64,
+ dst_reg, imm32);
break;
case BPF_LD | BPF_IMM | BPF_DW:
- /* optimization: if imm64 is zero, use 'xor <dst>,<dst>'
- * to save 7 bytes.
- */
- if (insn[0].imm == 0 && insn[1].imm == 0) {
- b1 = add_2mod(0x48, dst_reg, dst_reg);
- b2 = 0x31; /* xor */
- b3 = 0xC0;
- EMIT3(b1, b2, add_2reg(b3, dst_reg, dst_reg));
-
- insn++;
- i++;
- break;
- }
-
- /* movabsq %rax, imm64 */
- EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));
- EMIT(insn[0].imm, 4);
- EMIT(insn[1].imm, 4);
-
+ emit_mov_imm64(&prog, dst_reg, insn[1].imm, insn[0].imm);
insn++;
i++;
break;
@@ -594,36 +623,38 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
case BPF_ALU | BPF_MUL | BPF_X:
case BPF_ALU64 | BPF_MUL | BPF_K:
case BPF_ALU64 | BPF_MUL | BPF_X:
- EMIT1(0x50); /* push rax */
- EMIT1(0x52); /* push rdx */
+ {
+ bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
+
+ if (dst_reg != BPF_REG_0)
+ EMIT1(0x50); /* push rax */
+ if (dst_reg != BPF_REG_3)
+ EMIT1(0x52); /* push rdx */
/* mov r11, dst_reg */
EMIT_mov(AUX_REG, dst_reg);
if (BPF_SRC(insn->code) == BPF_X)
- /* mov rax, src_reg */
- EMIT_mov(BPF_REG_0, src_reg);
+ emit_mov_reg(&prog, is64, BPF_REG_0, src_reg);
else
- /* mov rax, imm32 */
- EMIT3_off32(0x48, 0xC7, 0xC0, imm32);
+ emit_mov_imm32(&prog, is64, BPF_REG_0, imm32);
- if (BPF_CLASS(insn->code) == BPF_ALU64)
+ if (is64)
EMIT1(add_1mod(0x48, AUX_REG));
else if (is_ereg(AUX_REG))
EMIT1(add_1mod(0x40, AUX_REG));
/* mul(q) r11 */
EMIT2(0xF7, add_1reg(0xE0, AUX_REG));
- /* mov r11, rax */
- EMIT_mov(AUX_REG, BPF_REG_0);
-
- EMIT1(0x5A); /* pop rdx */
- EMIT1(0x58); /* pop rax */
-
- /* mov dst_reg, r11 */
- EMIT_mov(dst_reg, AUX_REG);
+ if (dst_reg != BPF_REG_3)
+ EMIT1(0x5A); /* pop rdx */
+ if (dst_reg != BPF_REG_0) {
+ /* mov dst_reg, rax */
+ EMIT_mov(dst_reg, BPF_REG_0);
+ EMIT1(0x58); /* pop rax */
+ }
break;
-
+ }
/* shifts */
case BPF_ALU | BPF_LSH | BPF_K:
case BPF_ALU | BPF_RSH | BPF_K:
@@ -641,7 +672,11 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
case BPF_RSH: b3 = 0xE8; break;
case BPF_ARSH: b3 = 0xF8; break;
}
- EMIT3(0xC1, add_1reg(b3, dst_reg), imm32);
+
+ if (imm32 == 1)
+ EMIT2(0xD1, add_1reg(b3, dst_reg));
+ else
+ EMIT3(0xC1, add_1reg(b3, dst_reg), imm32);
break;
case BPF_ALU | BPF_LSH | BPF_X:
@@ -1188,7 +1223,7 @@ skip_init_addrs:
* may converge on the last pass. In such case do one more
* pass to emit the final image
*/
- for (pass = 0; pass < 10 || image; pass++) {
+ for (pass = 0; pass < 20 || image; pass++) {
proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
if (proglen <= 0) {
image = NULL;
@@ -1215,13 +1250,13 @@ skip_init_addrs:
}
}
oldproglen = proglen;
+ cond_resched();
}
if (bpf_jit_enable > 1)
bpf_jit_dump(prog->len, proglen, pass + 1, image);
if (image) {
- bpf_flush_icache(header, image + proglen);
if (!prog->is_func || extra_pass) {
bpf_jit_binary_lock_ro(header);
} else {
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 7df49c40665e..5559dcaddd5e 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -140,12 +140,10 @@ static const struct dmi_system_id pci_crs_quirks[] __initconst = {
void __init pci_acpi_crs_quirks(void)
{
- int year;
+ int year = dmi_get_bios_year();
- if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008) {
- if (iomem_resource.end <= 0xffffffff)
- pci_use_crs = false;
- }
+ if (year >= 0 && year < 2008 && iomem_resource.end <= 0xffffffff)
+ pci_use_crs = false;
dmi_check_system(pci_crs_quirks);
diff --git a/arch/x86/pci/direct.c b/arch/x86/pci/direct.c
index 2d9503323d10..a51074c55982 100644
--- a/arch/x86/pci/direct.c
+++ b/arch/x86/pci/direct.c
@@ -195,14 +195,13 @@ static const struct pci_raw_ops pci_direct_conf2 = {
static int __init pci_sanity_check(const struct pci_raw_ops *o)
{
u32 x = 0;
- int year, devfn;
+ int devfn;
if (pci_probe & PCI_NO_CHECKS)
return 1;
/* Assume Type 1 works for newer systems.
This handles machines that don't have anything on PCI Bus 0. */
- dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL);
- if (year >= 2001)
+ if (dmi_get_bios_year() >= 2001)
return 1;
for (devfn = 0; devfn < 0x100; devfn++) {
diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c
index 1cb01abcb1be..dfbe6ac38830 100644
--- a/arch/x86/pci/legacy.c
+++ b/arch/x86/pci/legacy.c
@@ -4,6 +4,7 @@
#include <linux/init.h>
#include <linux/export.h>
#include <linux/pci.h>
+#include <asm/jailhouse_para.h>
#include <asm/pci_x86.h>
/*
@@ -34,13 +35,14 @@ int __init pci_legacy_init(void)
void pcibios_scan_specific_bus(int busn)
{
+ int stride = jailhouse_paravirt() ? 1 : 8;
int devfn;
u32 l;
if (pci_find_bus(0, busn))
return;
- for (devfn = 0; devfn < 256; devfn += 8) {
+ for (devfn = 0; devfn < 256; devfn += stride) {
if (!raw_pci_read(0, busn, devfn, PCI_VENDOR_ID, 2, &l) &&
l != 0x0000 && l != 0xffff) {
DBG("Found device at %02x:%02x [%04x]\n", busn, devfn, l);
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 96684d0adcf9..7389db538c30 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -94,8 +94,8 @@ static struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, int start,
return new;
}
-static struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start,
- int end, u64 addr)
+struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start,
+ int end, u64 addr)
{
struct pci_mmcfg_region *new;
@@ -547,19 +547,14 @@ static void __init pci_mmcfg_reject_broken(int early)
static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg,
struct acpi_mcfg_allocation *cfg)
{
- int year;
-
if (cfg->address < 0xFFFFFFFF)
return 0;
if (!strncmp(mcfg->header.oem_id, "SGI", 3))
return 0;
- if (mcfg->header.revision >= 1) {
- if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) &&
- year >= 2010)
- return 0;
- }
+ if ((mcfg->header.revision >= 1) && (dmi_get_bios_year() >= 2010))
+ return 0;
pr_err(PREFIX "MCFG region for %04x [bus %02x-%02x] at %#llx "
"is above 4GB, ignored\n", cfg->pci_segment,
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index 75577c1490c4..7a5bafb76d77 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -159,43 +159,6 @@ static dma_addr_t a2p(dma_addr_t a, struct pci_dev *pdev)
return p;
}
-/**
- * sta2x11_swiotlb_alloc_coherent - Allocate swiotlb bounce buffers
- * returns virtual address. This is the only "special" function here.
- * @dev: PCI device
- * @size: Size of the buffer
- * @dma_handle: DMA address
- * @flags: memory flags
- */
-static void *sta2x11_swiotlb_alloc_coherent(struct device *dev,
- size_t size,
- dma_addr_t *dma_handle,
- gfp_t flags,
- unsigned long attrs)
-{
- void *vaddr;
-
- vaddr = x86_swiotlb_alloc_coherent(dev, size, dma_handle, flags, attrs);
- *dma_handle = p2a(*dma_handle, to_pci_dev(dev));
- return vaddr;
-}
-
-/* We have our own dma_ops: the same as swiotlb but from alloc (above) */
-static const struct dma_map_ops sta2x11_dma_ops = {
- .alloc = sta2x11_swiotlb_alloc_coherent,
- .free = x86_swiotlb_free_coherent,
- .map_page = swiotlb_map_page,
- .unmap_page = swiotlb_unmap_page,
- .map_sg = swiotlb_map_sg_attrs,
- .unmap_sg = swiotlb_unmap_sg_attrs,
- .sync_single_for_cpu = swiotlb_sync_single_for_cpu,
- .sync_single_for_device = swiotlb_sync_single_for_device,
- .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
- .sync_sg_for_device = swiotlb_sync_sg_for_device,
- .mapping_error = swiotlb_dma_mapping_error,
- .dma_supported = x86_dma_supported,
-};
-
/* At setup time, we use our own ops if the device is a ConneXt one */
static void sta2x11_setup_pdev(struct pci_dev *pdev)
{
@@ -205,7 +168,8 @@ static void sta2x11_setup_pdev(struct pci_dev *pdev)
return;
pci_set_consistent_dma_mask(pdev, STA2X11_AMBA_SIZE - 1);
pci_set_dma_mask(pdev, STA2X11_AMBA_SIZE - 1);
- pdev->dev.dma_ops = &sta2x11_dma_ops;
+ pdev->dev.dma_ops = &swiotlb_dma_ops;
+ pdev->dev.archdata.is_sta2x11 = true;
/* We must enable all devices as master, for audio DMA to work */
pci_set_master(pdev);
@@ -225,7 +189,7 @@ bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
{
struct sta2x11_mapping *map;
- if (dev->dma_ops != &sta2x11_dma_ops) {
+ if (!dev->archdata.is_sta2x11) {
if (!dev->dma_mask)
return false;
return addr + size - 1 <= *dev->dma_mask;
@@ -243,13 +207,13 @@ bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
}
/**
- * phys_to_dma - Return the DMA AMBA address used for this STA2x11 device
+ * __phys_to_dma - Return the DMA AMBA address used for this STA2x11 device
* @dev: device for a PCI device
* @paddr: Physical address
*/
-dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
{
- if (dev->dma_ops != &sta2x11_dma_ops)
+ if (!dev->archdata.is_sta2x11)
return paddr;
return p2a(paddr, to_pci_dev(dev));
}
@@ -259,9 +223,9 @@ dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
* @dev: device for a PCI device
* @daddr: STA2x11 AMBA DMA address
*/
-phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
{
- if (dev->dma_ops != &sta2x11_dma_ops)
+ if (!dev->archdata.is_sta2x11)
return daddr;
return a2p(daddr, to_pci_dev(dev));
}
diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c
index d49d3be81953..034813d4ab1e 100644
--- a/arch/x86/platform/atom/punit_atom_debug.c
+++ b/arch/x86/platform/atom/punit_atom_debug.c
@@ -109,18 +109,7 @@ static int punit_dev_state_show(struct seq_file *seq_file, void *unused)
return 0;
}
-
-static int punit_dev_state_open(struct inode *inode, struct file *file)
-{
- return single_open(file, punit_dev_state_show, inode->i_private);
-}
-
-static const struct file_operations punit_dev_state_ops = {
- .open = punit_dev_state_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(punit_dev_state);
static struct dentry *punit_dbg_file;
@@ -132,9 +121,9 @@ static int punit_dbgfs_register(struct punit_device *punit_device)
if (!punit_dbg_file)
return -ENXIO;
- dev_state = debugfs_create_file("dev_power_state", S_IFREG | S_IRUGO,
+ dev_state = debugfs_create_file("dev_power_state", 0444,
punit_dbg_file, punit_device,
- &punit_dev_state_ops);
+ &punit_dev_state_fops);
if (!dev_state) {
pr_err("punit_dev_state register failed\n");
debugfs_remove(punit_dbg_file);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index c310a8284358..bed7e7f4e44c 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -27,12 +27,14 @@
#include <linux/ioport.h>
#include <linux/mc146818rtc.h>
#include <linux/efi.h>
+#include <linux/export.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/reboot.h>
#include <linux/slab.h>
#include <linux/ucs2_string.h>
#include <linux/mem_encrypt.h>
+#include <linux/sched/task.h>
#include <asm/setup.h>
#include <asm/page.h>
@@ -81,9 +83,8 @@ pgd_t * __init efi_call_phys_prolog(void)
int n_pgds, i, j;
if (!efi_enabled(EFI_OLD_MEMMAP)) {
- save_pgd = (pgd_t *)__read_cr3();
- write_cr3((unsigned long)efi_scratch.efi_pgt);
- goto out;
+ efi_switch_mm(&efi_mm);
+ return NULL;
}
early_code_mapping_set_exec(1);
@@ -155,8 +156,7 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
pud_t *pud;
if (!efi_enabled(EFI_OLD_MEMMAP)) {
- write_cr3((unsigned long)save_pgd);
- __flush_tlb_all();
+ efi_switch_mm(efi_scratch.prev_mm);
return;
}
@@ -190,7 +190,7 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
early_code_mapping_set_exec(0);
}
-static pgd_t *efi_pgd;
+EXPORT_SYMBOL_GPL(efi_mm);
/*
* We need our own copy of the higher levels of the page tables
@@ -203,7 +203,7 @@ static pgd_t *efi_pgd;
*/
int __init efi_alloc_page_tables(void)
{
- pgd_t *pgd;
+ pgd_t *pgd, *efi_pgd;
p4d_t *p4d;
pud_t *pud;
gfp_t gfp_mask;
@@ -225,12 +225,16 @@ int __init efi_alloc_page_tables(void)
pud = pud_alloc(&init_mm, p4d, EFI_VA_END);
if (!pud) {
- if (CONFIG_PGTABLE_LEVELS > 4)
+ if (pgtable_l5_enabled)
free_page((unsigned long) pgd_page_vaddr(*pgd));
- free_page((unsigned long)efi_pgd);
+ free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
return -ENOMEM;
}
+ efi_mm.pgd = efi_pgd;
+ mm_init_cpumask(&efi_mm);
+ init_new_context(NULL, &efi_mm);
+
return 0;
}
@@ -243,6 +247,7 @@ void efi_sync_low_kernel_mappings(void)
pgd_t *pgd_k, *pgd_efi;
p4d_t *p4d_k, *p4d_efi;
pud_t *pud_k, *pud_efi;
+ pgd_t *efi_pgd = efi_mm.pgd;
if (efi_enabled(EFI_OLD_MEMMAP))
return;
@@ -255,8 +260,8 @@ void efi_sync_low_kernel_mappings(void)
* only span a single PGD entry and that the entry also maps
* other important kernel regions.
*/
- BUILD_BUG_ON(pgd_index(EFI_VA_END) != pgd_index(MODULES_END));
- BUILD_BUG_ON((EFI_VA_START & PGDIR_MASK) !=
+ MAYBE_BUILD_BUG_ON(pgd_index(EFI_VA_END) != pgd_index(MODULES_END));
+ MAYBE_BUILD_BUG_ON((EFI_VA_START & PGDIR_MASK) !=
(EFI_VA_END & PGDIR_MASK));
pgd_efi = efi_pgd + pgd_index(PAGE_OFFSET);
@@ -336,20 +341,12 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
unsigned long pfn, text, pf;
struct page *page;
unsigned npages;
- pgd_t *pgd;
+ pgd_t *pgd = efi_mm.pgd;
if (efi_enabled(EFI_OLD_MEMMAP))
return 0;
/*
- * Since the PGD is encrypted, set the encryption mask so that when
- * this value is loaded into cr3 the PGD will be decrypted during
- * the pagetable walk.
- */
- efi_scratch.efi_pgt = (pgd_t *)__sme_pa(efi_pgd);
- pgd = efi_pgd;
-
- /*
* It can happen that the physical address of new_memmap lands in memory
* which is not mapped in the EFI page table. Therefore we need to go
* and ident-map those pages containing the map before calling
@@ -362,8 +359,6 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
return 1;
}
- efi_scratch.use_pgd = true;
-
/*
* Certain firmware versions are way too sentimential and still believe
* they are exclusive and unquestionable owners of the first physical page,
@@ -417,7 +412,7 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va)
{
unsigned long flags = _PAGE_RW;
unsigned long pfn;
- pgd_t *pgd = efi_pgd;
+ pgd_t *pgd = efi_mm.pgd;
if (!(md->attribute & EFI_MEMORY_WB))
flags |= _PAGE_PCD;
@@ -521,7 +516,7 @@ void __init parse_efi_setup(u64 phys_addr, u32 data_len)
static int __init efi_update_mappings(efi_memory_desc_t *md, unsigned long pf)
{
unsigned long pfn;
- pgd_t *pgd = efi_pgd;
+ pgd_t *pgd = efi_mm.pgd;
int err1, err2;
/* Update the 1:1 mapping */
@@ -618,10 +613,26 @@ void __init efi_dump_pagetable(void)
if (efi_enabled(EFI_OLD_MEMMAP))
ptdump_walk_pgd_level(NULL, swapper_pg_dir);
else
- ptdump_walk_pgd_level(NULL, efi_pgd);
+ ptdump_walk_pgd_level(NULL, efi_mm.pgd);
#endif
}
+/*
+ * Makes the calling thread switch to/from efi_mm context. Can be used
+ * for SetVirtualAddressMap() i.e. current->active_mm == init_mm as well
+ * as during efi runtime calls i.e current->active_mm == current_mm.
+ * We are not mm_dropping()/mm_grabbing() any mm, because we are not
+ * losing/creating any references.
+ */
+void efi_switch_mm(struct mm_struct *mm)
+{
+ task_lock(current);
+ efi_scratch.prev_mm = current->active_mm;
+ current->active_mm = mm;
+ switch_mm(efi_scratch.prev_mm, mm, NULL);
+ task_unlock(current);
+}
+
#ifdef CONFIG_EFI_MIXED
extern efi_status_t efi64_thunk(u32, ...);
@@ -675,16 +686,13 @@ efi_status_t efi_thunk_set_virtual_address_map(
efi_sync_low_kernel_mappings();
local_irq_save(flags);
- efi_scratch.prev_cr3 = __read_cr3();
- write_cr3((unsigned long)efi_scratch.efi_pgt);
- __flush_tlb_all();
+ efi_switch_mm(&efi_mm);
func = (u32)(unsigned long)phys_set_virtual_address_map;
status = efi64_thunk(func, memory_map_size, descriptor_size,
descriptor_version, virtual_map);
- write_cr3(efi_scratch.prev_cr3);
- __flush_tlb_all();
+ efi_switch_mm(efi_scratch.prev_mm);
local_irq_restore(flags);
return status;
diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S
index 189b218da87c..46c58b08739c 100644
--- a/arch/x86/platform/efi/efi_thunk_64.S
+++ b/arch/x86/platform/efi/efi_thunk_64.S
@@ -33,7 +33,7 @@ ENTRY(efi64_thunk)
* Switch to 1:1 mapped 32-bit stack pointer.
*/
movq %rsp, efi_saved_sp(%rip)
- movq efi_scratch+25(%rip), %rsp
+ movq efi_scratch(%rip), %rsp
/*
* Calculate the physical address of the kernel text.
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 5b513ccffde4..36c1f8b9f7e0 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -75,7 +75,7 @@ struct quark_security_header {
u32 rsvd[2];
};
-static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
+static const efi_char16_t efi_dummy_name[] = L"DUMMY";
static bool efi_no_storage_paranoia;
@@ -105,7 +105,8 @@ early_param("efi_no_storage_paranoia", setup_storage_paranoia);
*/
void efi_delete_dummy_variable(void)
{
- efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+ efi.set_variable((efi_char16_t *)efi_dummy_name,
+ &EFI_DUMMY_GUID,
EFI_VARIABLE_NON_VOLATILE |
EFI_VARIABLE_BOOTSERVICE_ACCESS |
EFI_VARIABLE_RUNTIME_ACCESS,
@@ -177,12 +178,13 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size,
* that by attempting to use more space than is available.
*/
unsigned long dummy_size = remaining_size + 1024;
- void *dummy = kzalloc(dummy_size, GFP_ATOMIC);
+ void *dummy = kzalloc(dummy_size, GFP_KERNEL);
if (!dummy)
return EFI_OUT_OF_RESOURCES;
- status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+ status = efi.set_variable((efi_char16_t *)efi_dummy_name,
+ &EFI_DUMMY_GUID,
EFI_VARIABLE_NON_VOLATILE |
EFI_VARIABLE_BOOTSERVICE_ACCESS |
EFI_VARIABLE_RUNTIME_ACCESS,
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index fb1df9488e98..2ebdf31d9996 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -199,6 +199,12 @@ void __init x86_intel_mid_early_setup(void)
legacy_pic = &null_legacy_pic;
+ /*
+ * Do nothing for now as everything needed done in
+ * x86_intel_mid_early_setup() below.
+ */
+ x86_init.acpi.reduced_hw_early_init = x86_init_noop;
+
pm_power_off = intel_mid_power_off;
machine_ops.emergency_restart = intel_mid_reboot;
diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c
index 17d6d2296e4d..49828c2707ac 100644
--- a/arch/x86/platform/intel-quark/imr.c
+++ b/arch/x86/platform/intel-quark/imr.c
@@ -224,25 +224,7 @@ static int imr_dbgfs_state_show(struct seq_file *s, void *unused)
mutex_unlock(&idev->lock);
return ret;
}
-
-/**
- * imr_state_open - debugfs open callback.
- *
- * @inode: pointer to struct inode.
- * @file: pointer to struct file.
- * @return: result of single open.
- */
-static int imr_state_open(struct inode *inode, struct file *file)
-{
- return single_open(file, imr_dbgfs_state_show, inode->i_private);
-}
-
-static const struct file_operations imr_state_ops = {
- .open = imr_state_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(imr_dbgfs_state);
/**
* imr_debugfs_register - register debugfs hooks.
@@ -252,8 +234,8 @@ static const struct file_operations imr_state_ops = {
*/
static int imr_debugfs_register(struct imr_device *idev)
{
- idev->file = debugfs_create_file("imr_state", S_IFREG | S_IRUGO, NULL,
- idev, &imr_state_ops);
+ idev->file = debugfs_create_file("imr_state", 0444, NULL, idev,
+ &imr_dbgfs_state_fops);
return PTR_ERR_OR_ZERO(idev->file);
}
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index db77e087adaf..b36caae0fb2f 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -2255,8 +2255,6 @@ static int __init uv_bau_init(void)
init_uvhub(uvhub, vector, uv_base_pnode);
}
- alloc_intr_gate(vector, uv_bau_message_intr1);
-
for_each_possible_blade(uvhub) {
if (uv_blade_nr_possible_cpus(uvhub)) {
unsigned long val;
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 0ef5e5204968..74a532989308 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -50,7 +50,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd)
{
pmd_t *pmd;
pud_t *pud;
- p4d_t *p4d;
+ p4d_t *p4d = NULL;
/*
* The new mapping only has to cover the page containing the image
@@ -66,7 +66,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd)
* tables used by the image kernel.
*/
- if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+ if (pgtable_l5_enabled) {
p4d = (p4d_t *)get_safe_page(GFP_ATOMIC);
if (!p4d)
return -ENOMEM;
@@ -84,7 +84,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd)
__pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC));
set_pud(pud + pud_index(restore_jump_address),
__pud(__pa(pmd) | _KERNPG_TABLE));
- if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+ if (p4d) {
set_p4d(p4d + p4d_index(restore_jump_address), __p4d(__pa(pud) | _KERNPG_TABLE));
set_pgd(pgd + pgd_index(restore_jump_address), __pgd(__pa(p4d) | _KERNPG_TABLE));
} else {
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 2f15a2ac4209..d70c15de417b 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -16,7 +16,7 @@ KCOV_INSTRUMENT := n
# in turn leaves some undefined symbols like __fentry__ in purgatory and not
# sure how to relocate those. Like kexec-tools, use custom flags.
-KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -MD -Os -mcmodel=large
+KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -Os -mcmodel=large
KBUILD_CFLAGS += -m$(BITS)
KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index b7d73400ea29..f31e5d903161 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -30,11 +30,7 @@
#endif /* CONFIG_X86_32 */
-#ifdef CONFIG_X86_PPRO_FENCE
-#define dma_rmb() rmb()
-#else /* CONFIG_X86_PPRO_FENCE */
#define dma_rmb() barrier()
-#endif /* CONFIG_X86_PPRO_FENCE */
#define dma_wmb() barrier()
#include <asm-generic/barrier.h>
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index f605825a04ab..c1f98f32c45f 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -18,9 +18,6 @@ config XEN_PV
bool "Xen PV guest support"
default y
depends on XEN
- # XEN_PV is not ready to work with 5-level paging.
- # Changes to hypervisor are also required.
- depends on !X86_5LEVEL
select XEN_HAVE_PVMMU
select XEN_HAVE_VPMU
help
@@ -79,6 +76,4 @@ config XEN_DEBUG_FS
config XEN_PVH
bool "Support for running as a PVH guest"
depends on XEN && XEN_PVHVM && ACPI
- # Pre-built page tables are not ready to handle 5-level paging.
- depends on !X86_5LEVEL
def_bool n
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index de58533d3664..2163888497d3 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -215,7 +215,7 @@ static void __init xen_apic_check(void)
}
void __init xen_init_apic(void)
{
- x86_io_apic_ops.read = xen_io_apic_read;
+ x86_apic_ops.io_apic_read = xen_io_apic_read;
/* On PV guests the APIC CPUID bit is disabled so none of the
* routines end up executing. */
if (!xen_initial_domain())
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index 436c4f003e17..aa1c6a6831a9 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -6,6 +6,7 @@
#include <asm/io_apic.h>
#include <asm/hypervisor.h>
#include <asm/e820/api.h>
+#include <asm/x86_init.h>
#include <asm/xen/interface.h>
#include <asm/xen/hypercall.h>
@@ -16,15 +17,20 @@
/*
* PVH variables.
*
- * xen_pvh and pvh_bootparams need to live in data segment since they
- * are used after startup_{32|64}, which clear .bss, are invoked.
+ * xen_pvh pvh_bootparams and pvh_start_info need to live in data segment
+ * since they are used after startup_{32|64}, which clear .bss, are invoked.
*/
bool xen_pvh __attribute__((section(".data"))) = 0;
struct boot_params pvh_bootparams __attribute__((section(".data")));
+struct hvm_start_info pvh_start_info __attribute__((section(".data")));
-struct hvm_start_info pvh_start_info;
unsigned int pvh_start_info_sz = sizeof(pvh_start_info);
+static u64 pvh_get_root_pointer(void)
+{
+ return pvh_start_info.rsdp_paddr;
+}
+
static void __init init_pvh_bootparams(void)
{
struct xen_memory_map memmap;
@@ -71,6 +77,8 @@ static void __init init_pvh_bootparams(void)
*/
pvh_bootparams.hdr.version = 0x212;
pvh_bootparams.hdr.type_of_loader = (9 << 4) | 0; /* Xen loader */
+
+ x86_init.acpi.get_root_pointer = pvh_get_root_pointer;
}
/*
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index aae88fec9941..d20763472920 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -538,6 +538,22 @@ static void xen_set_p4d(p4d_t *ptr, p4d_t val)
xen_mc_issue(PARAVIRT_LAZY_MMU);
}
+
+#if CONFIG_PGTABLE_LEVELS >= 5
+__visible p4dval_t xen_p4d_val(p4d_t p4d)
+{
+ return pte_mfn_to_pfn(p4d.p4d);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_p4d_val);
+
+__visible p4d_t xen_make_p4d(p4dval_t p4d)
+{
+ p4d = pte_pfn_to_mfn(p4d);
+
+ return native_make_p4d(p4d);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_p4d);
+#endif /* CONFIG_PGTABLE_LEVELS >= 5 */
#endif /* CONFIG_X86_64 */
static int xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd,
@@ -2411,6 +2427,11 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
.alloc_pud = xen_alloc_pmd_init,
.release_pud = xen_release_pmd_init,
+
+#if CONFIG_PGTABLE_LEVELS >= 5
+ .p4d_val = PV_CALLEE_SAVE(xen_p4d_val),
+ .make_p4d = PV_CALLEE_SAVE(xen_make_p4d),
+#endif
#endif /* CONFIG_X86_64 */
.activate_mm = xen_activate_mm,