summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/alpha/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/arm/Kconfig2
-rw-r--r--arch/arm/Kconfig.debug6
-rw-r--r--arch/arm/boot/compressed/head.S16
-rw-r--r--arch/arm/kernel/head-nommu.S2
-rw-r--r--arch/arm/tools/syscall.tbl4
-rw-r--r--arch/arm64/include/asm/futex.h2
-rw-r--r--arch/arm64/include/asm/unistd.h2
-rw-r--r--arch/arm64/include/asm/unistd32.h8
-rw-r--r--arch/arm64/kernel/ftrace.c9
-rw-r--r--arch/arm64/mm/init.c2
-rw-r--r--arch/ia64/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/m68k/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/microblaze/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/mips/ath79/setup.c6
-rw-r--r--arch/mips/kernel/scall64-o32.S2
-rw-r--r--arch/mips/kernel/syscalls/syscall_n32.tbl4
-rw-r--r--arch/mips/kernel/syscalls/syscall_n64.tbl4
-rw-r--r--arch/mips/kernel/syscalls/syscall_o32.tbl4
-rw-r--r--arch/parisc/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/powerpc/configs/skiroot_defconfig1
-rw-r--r--arch/powerpc/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/powerpc/mm/mmu_context_iommu.c97
-rw-r--r--arch/powerpc/platforms/Kconfig.cputype2
-rw-r--r--arch/riscv/configs/rv32_defconfig84
-rw-r--r--arch/riscv/mm/init.c8
-rw-r--r--arch/s390/boot/mem_detect.c2
-rw-r--r--arch/s390/kernel/fpu.c2
-rw-r--r--arch/s390/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/s390/kernel/vtime.c8
-rw-r--r--arch/sh/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/sparc/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/boot/compressed/misc.c2
-rw-r--r--arch/x86/crypto/poly1305-avx2-x86_64.S14
-rw-r--r--arch/x86/crypto/poly1305-sse2-x86_64.S22
-rw-r--r--arch/x86/events/amd/core.c35
-rw-r--r--arch/x86/events/intel/core.c2
-rw-r--r--arch/x86/events/intel/cstate.c10
-rw-r--r--arch/x86/events/perf_event.h38
-rw-r--r--arch/x86/include/asm/kvm_emulate.h4
-rw-r--r--arch/x86/include/asm/kvm_host.h17
-rw-r--r--arch/x86/include/uapi/asm/vmx.h1
-rw-r--r--arch/x86/kernel/cpu/Makefile2
-rw-r--r--arch/x86/kernel/cpu/bugs.c6
-rw-r--r--arch/x86/kernel/cpu/common.c17
-rw-r--r--arch/x86/kernel/cpu/cpu.h1
-rw-r--r--arch/x86/kernel/cpu/intel.c34
-rw-r--r--arch/x86/kernel/cpu/intel_epb.c216
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c3
-rw-r--r--arch/x86/kernel/kprobes/core.c48
-rw-r--r--arch/x86/kernel/process.c8
-rw-r--r--arch/x86/kernel/reboot.c21
-rw-r--r--arch/x86/kernel/tsc.c29
-rw-r--r--arch/x86/kernel/vmlinux.lds.S2
-rw-r--r--arch/x86/kvm/emulate.c191
-rw-r--r--arch/x86/kvm/lapic.c4
-rw-r--r--arch/x86/kvm/mmu.c15
-rw-r--r--arch/x86/kvm/mmu.h2
-rw-r--r--arch/x86/kvm/pmu.c4
-rw-r--r--arch/x86/kvm/svm.c57
-rw-r--r--arch/x86/kvm/trace.h4
-rw-r--r--arch/x86/kvm/vmx/nested.c47
-rw-r--r--arch/x86/kvm/vmx/vmx.c35
-rw-r--r--arch/x86/kvm/vmx/vmx.h2
-rw-r--r--arch/x86/kvm/x86.c64
-rw-r--r--arch/x86/kvm/x86.h2
-rw-r--r--arch/x86/mm/dump_pagetables.c3
-rw-r--r--arch/x86/mm/init.c6
-rw-r--r--arch/x86/mm/ioremap.c2
-rw-r--r--arch/x86/mm/kaslr.c2
-rw-r--r--arch/x86/mm/tlb.c2
-rw-r--r--arch/xtensa/kernel/syscalls/syscall.tbl4
73 files changed, 919 insertions, 374 deletions
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 63ed39cbd3bd..165f268beafc 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -463,3 +463,7 @@
532 common getppid sys_getppid
# all other architectures have common numbers for new syscall, alpha
# is the exception.
+534 common pidfd_send_signal sys_pidfd_send_signal
+535 common io_uring_setup sys_io_uring_setup
+536 common io_uring_enter sys_io_uring_enter
+537 common io_uring_register sys_io_uring_register
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 850b4805e2d1..9aed25a6019b 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -73,7 +73,7 @@ config ARM
select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU
select HAVE_EXIT_THREAD
select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
- select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL
+ select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
select HAVE_FUNCTION_TRACER if !XIP_KERNEL
select HAVE_GCC_PLUGINS
select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 6d6e0330930b..e388af4594a6 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -47,8 +47,8 @@ config DEBUG_WX
choice
prompt "Choose kernel unwinder"
- default UNWINDER_ARM if AEABI && !FUNCTION_GRAPH_TRACER
- default UNWINDER_FRAME_POINTER if !AEABI || FUNCTION_GRAPH_TRACER
+ default UNWINDER_ARM if AEABI
+ default UNWINDER_FRAME_POINTER if !AEABI
help
This determines which method will be used for unwinding kernel stack
traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack,
@@ -65,7 +65,7 @@ config UNWINDER_FRAME_POINTER
config UNWINDER_ARM
bool "ARM EABI stack unwinder"
- depends on AEABI
+ depends on AEABI && !FUNCTION_GRAPH_TRACER
select ARM_UNWIND
help
This option enables stack unwinding support in the kernel
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 6c7ccb428c07..7135820f76d4 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -1438,7 +1438,21 @@ ENTRY(efi_stub_entry)
@ Preserve return value of efi_entry() in r4
mov r4, r0
- bl cache_clean_flush
+
+ @ our cache maintenance code relies on CP15 barrier instructions
+ @ but since we arrived here with the MMU and caches configured
+ @ by UEFI, we must check that the CP15BEN bit is set in SCTLR.
+ @ Note that this bit is RAO/WI on v6 and earlier, so the ISB in
+ @ the enable path will be executed on v7+ only.
+ mrc p15, 0, r1, c1, c0, 0 @ read SCTLR
+ tst r1, #(1 << 5) @ CP15BEN bit set?
+ bne 0f
+ orr r1, r1, #(1 << 5) @ CP15 barrier instructions
+ mcr p15, 0, r1, c1, c0, 0 @ write SCTLR
+ ARM( .inst 0xf57ff06f @ v7+ isb )
+ THUMB( isb )
+
+0: bl cache_clean_flush
bl cache_off
@ Set parameters for booting zImage according to boot protocol
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index c08d2d890f7b..b38bbd011b35 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -133,9 +133,9 @@ __secondary_data:
*/
.text
__after_proc_init:
-#ifdef CONFIG_ARM_MPU
M_CLASS(movw r12, #:lower16:BASEADDR_V7M_SCB)
M_CLASS(movt r12, #:upper16:BASEADDR_V7M_SCB)
+#ifdef CONFIG_ARM_MPU
M_CLASS(ldr r3, [r12, 0x50])
AR_CLASS(mrc p15, 0, r3, c0, c1, 4) @ Read ID_MMFR0
and r3, r3, #(MMFR0_PMSA) @ PMSA field
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 9016f4081bb9..0393917eaa57 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -437,3 +437,7 @@
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index e1d95f08f8e1..c7e1a7837706 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -50,7 +50,7 @@ do { \
static inline int
arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
{
- int oldval, ret, tmp;
+ int oldval = 0, ret, tmp;
u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);
pagefault_disable();
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index d1dd93436e1e..f2a83ff6b73c 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -44,7 +44,7 @@
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 424
+#define __NR_compat_syscalls 428
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 5590f2623690..23f1a44acada 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -866,6 +866,14 @@ __SYSCALL(__NR_rt_sigtimedwait_time64, compat_sys_rt_sigtimedwait_time64)
__SYSCALL(__NR_futex_time64, sys_futex)
#define __NR_sched_rr_get_interval_time64 423
__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
+#define __NR_pidfd_send_signal 424
+__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
+#define __NR_io_uring_setup 425
+__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
+#define __NR_io_uring_enter 426
+__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
+#define __NR_io_uring_register 427
+__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
/*
* Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 07b298120182..65a51331088e 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -103,10 +103,15 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
* to be revisited if support for multiple ftrace entry points
* is added in the future, but for now, the pr_err() below
* deals with a theoretical issue only.
+ *
+ * Note that PLTs are place relative, and plt_entries_equal()
+ * checks whether they point to the same target. Here, we need
+ * to check if the actual opcodes are in fact identical,
+ * regardless of the offset in memory so use memcmp() instead.
*/
trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline);
- if (!plt_entries_equal(mod->arch.ftrace_trampoline,
- &trampoline)) {
+ if (memcmp(mod->arch.ftrace_trampoline, &trampoline,
+ sizeof(trampoline))) {
if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) {
pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
return -EINVAL;
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 6bc135042f5e..7cae155e81a5 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -363,7 +363,7 @@ void __init arm64_memblock_init(void)
* Otherwise, this is a no-op
*/
u64 base = phys_initrd_start & PAGE_MASK;
- u64 size = PAGE_ALIGN(phys_initrd_size);
+ u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base;
/*
* We can only add back the initrd memory if we don't end up
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index ab9cda5f6136..56e3d0b685e1 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -344,3 +344,7 @@
332 common pkey_free sys_pkey_free
333 common rseq sys_rseq
# 334 through 423 are reserved to sync up with other architectures
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 125c14178979..df4ec3ec71d1 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -423,3 +423,7 @@
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 8ee3a8c18498..4964947732af 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -429,3 +429,7 @@
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index 4a70c5de8c92..25a57895a3a3 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -210,12 +210,6 @@ const char *get_system_type(void)
return ath79_sys_type;
}
-int get_c0_perfcount_int(void)
-{
- return ATH79_MISC_IRQ(5);
-}
-EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
-
unsigned int get_c0_compare_int(void)
{
return CP0_LEGACY_COMPARE_IRQ;
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index f158c5894a9a..feb2653490df 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -125,7 +125,7 @@ trace_a_syscall:
subu t1, v0, __NR_O32_Linux
move a1, v0
bnez t1, 1f /* __NR_syscall at offset 0 */
- lw a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
+ ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
.set pop
1: jal syscall_trace_enter
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 15f4117900ee..9392dfe33f97 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -362,3 +362,7 @@
421 n32 rt_sigtimedwait_time64 compat_sys_rt_sigtimedwait_time64
422 n32 futex_time64 sys_futex
423 n32 sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 n32 pidfd_send_signal sys_pidfd_send_signal
+425 n32 io_uring_setup sys_io_uring_setup
+426 n32 io_uring_enter sys_io_uring_enter
+427 n32 io_uring_register sys_io_uring_register
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index c85502e67b44..cd0c8aa21fba 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -338,3 +338,7 @@
327 n64 rseq sys_rseq
328 n64 io_pgetevents sys_io_pgetevents
# 329 through 423 are reserved to sync up with other architectures
+424 n64 pidfd_send_signal sys_pidfd_send_signal
+425 n64 io_uring_setup sys_io_uring_setup
+426 n64 io_uring_enter sys_io_uring_enter
+427 n64 io_uring_register sys_io_uring_register
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 2e063d0f837e..e849e8ffe4a2 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -411,3 +411,7 @@
421 o32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
422 o32 futex_time64 sys_futex sys_futex
423 o32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
+424 o32 pidfd_send_signal sys_pidfd_send_signal
+425 o32 io_uring_setup sys_io_uring_setup
+426 o32 io_uring_enter sys_io_uring_enter
+427 o32 io_uring_register sys_io_uring_register
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index b26766c6647d..fe8ca623add8 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -420,3 +420,7 @@
421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
422 32 futex_time64 sys_futex sys_futex
423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index 5ba131c30f6b..1bcd468ab422 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -266,6 +266,7 @@ CONFIG_UDF_FS=m
CONFIG_MSDOS_FS=m
CONFIG_VFAT_FS=m
CONFIG_PROC_KCORE=y
+CONFIG_HUGETLBFS=y
# CONFIG_MISC_FILESYSTEMS is not set
# CONFIG_NETWORK_FILESYSTEMS is not set
CONFIG_NLS=y
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index b18abb0c3dae..00f5a63c8d9a 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -505,3 +505,7 @@
421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
422 32 futex_time64 sys_futex sys_futex
423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index e7a9c4f6bfca..8330f135294f 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -95,28 +95,15 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
unsigned long entries, unsigned long dev_hpa,
struct mm_iommu_table_group_mem_t **pmem)
{
- struct mm_iommu_table_group_mem_t *mem;
- long i, ret, locked_entries = 0;
+ struct mm_iommu_table_group_mem_t *mem, *mem2;
+ long i, ret, locked_entries = 0, pinned = 0;
unsigned int pageshift;
-
- mutex_lock(&mem_list_mutex);
-
- list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list,
- next) {
- /* Overlap? */
- if ((mem->ua < (ua + (entries << PAGE_SHIFT))) &&
- (ua < (mem->ua +
- (mem->entries << PAGE_SHIFT)))) {
- ret = -EINVAL;
- goto unlock_exit;
- }
-
- }
+ unsigned long entry, chunk;
if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
ret = mm_iommu_adjust_locked_vm(mm, entries, true);
if (ret)
- goto unlock_exit;
+ return ret;
locked_entries = entries;
}
@@ -148,17 +135,27 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
}
down_read(&mm->mmap_sem);
- ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL);
+ chunk = (1UL << (PAGE_SHIFT + MAX_ORDER - 1)) /
+ sizeof(struct vm_area_struct *);
+ chunk = min(chunk, entries);
+ for (entry = 0; entry < entries; entry += chunk) {
+ unsigned long n = min(entries - entry, chunk);
+
+ ret = get_user_pages_longterm(ua + (entry << PAGE_SHIFT), n,
+ FOLL_WRITE, mem->hpages + entry, NULL);
+ if (ret == n) {
+ pinned += n;
+ continue;
+ }
+ if (ret > 0)
+ pinned += ret;
+ break;
+ }
up_read(&mm->mmap_sem);
- if (ret != entries) {
- /* free the reference taken */
- for (i = 0; i < ret; i++)
- put_page(mem->hpages[i]);
-
- vfree(mem->hpas);
- kfree(mem);
- ret = -EFAULT;
- goto unlock_exit;
+ if (pinned != entries) {
+ if (!ret)
+ ret = -EFAULT;
+ goto free_exit;
}
pageshift = PAGE_SHIFT;
@@ -183,21 +180,43 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
}
good_exit:
- ret = 0;
atomic64_set(&mem->mapped, 1);
mem->used = 1;
mem->ua = ua;
mem->entries = entries;
- *pmem = mem;
- list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
+ mutex_lock(&mem_list_mutex);
-unlock_exit:
- if (locked_entries && ret)
- mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+ list_for_each_entry_rcu(mem2, &mm->context.iommu_group_mem_list, next) {
+ /* Overlap? */
+ if ((mem2->ua < (ua + (entries << PAGE_SHIFT))) &&
+ (ua < (mem2->ua +
+ (mem2->entries << PAGE_SHIFT)))) {
+ ret = -EINVAL;
+ mutex_unlock(&mem_list_mutex);
+ goto free_exit;
+ }
+ }
+
+ list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
mutex_unlock(&mem_list_mutex);
+ *pmem = mem;
+
+ return 0;
+
+free_exit:
+ /* free the reference taken */
+ for (i = 0; i < pinned; i++)
+ put_page(mem->hpages[i]);
+
+ vfree(mem->hpas);
+ kfree(mem);
+
+unlock_exit:
+ mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+
return ret;
}
@@ -266,7 +285,7 @@ static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem)
long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
{
long ret = 0;
- unsigned long entries, dev_hpa;
+ unsigned long unlock_entries = 0;
mutex_lock(&mem_list_mutex);
@@ -287,17 +306,17 @@ long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
goto unlock_exit;
}
+ if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
+ unlock_entries = mem->entries;
+
/* @mapped became 0 so now mappings are disabled, release the region */
- entries = mem->entries;
- dev_hpa = mem->dev_hpa;
mm_iommu_release(mem);
- if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
- mm_iommu_adjust_locked_vm(mm, entries, false);
-
unlock_exit:
mutex_unlock(&mem_list_mutex);
+ mm_iommu_adjust_locked_vm(mm, unlock_entries, false);
+
return ret;
}
EXPORT_SYMBOL_GPL(mm_iommu_put);
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 842b2c7e156a..50cd09b4e05d 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -324,7 +324,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
config PPC_RADIX_MMU
bool "Radix MMU Support"
- depends on PPC_BOOK3S_64
+ depends on PPC_BOOK3S_64 && HUGETLB_PAGE
select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
default y
help
diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig
new file mode 100644
index 000000000000..1a911ed8e772
--- /dev/null
+++ b/arch/riscv/configs/rv32_defconfig
@@ -0,0 +1,84 @@
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CFS_BANDWIDTH=y
+CONFIG_CGROUP_BPF=y
+CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
+CONFIG_CHECKPOINT_RESTORE=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_ARCH_RV32I=y
+CONFIG_SMP=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NETLINK_DIAG=y
+CONFIG_PCI=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCIE_XILINX=y
+CONFIG_DEVTMPFS=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_NETDEVICES=y
+CONFIG_VIRTIO_NET=y
+CONFIG_MACB=y
+CONFIG_E1000E=y
+CONFIG_R8169=y
+CONFIG_MICROSEMI_PHY=y
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
+CONFIG_HVC_RISCV_SBI=y
+# CONFIG_PTP_1588_CLOCK is not set
+CONFIG_DRM=y
+CONFIG_DRM_RADEON=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_USB=y
+CONFIG_USB_XHCI_HCD=y
+CONFIG_USB_XHCI_PLATFORM=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_UAS=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_SIFIVE_PLIC=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_NFS_V4_2=y
+CONFIG_ROOT_NFS=y
+CONFIG_CRYPTO_USER_API_HASH=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
+CONFIG_PRINTK_TIME=y
+# CONFIG_RCU_TRACE is not set
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 5fd8c922e1c2..bc7b77e34d09 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -121,6 +121,14 @@ void __init setup_bootmem(void)
*/
memblock_reserve(reg->base, vmlinux_end - reg->base);
mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET);
+
+ /*
+ * Remove memblock from the end of usable area to the
+ * end of region
+ */
+ if (reg->base + mem_size < end)
+ memblock_remove(reg->base + mem_size,
+ end - reg->base - mem_size);
}
}
BUG_ON(mem_size == 0);
diff --git a/arch/s390/boot/mem_detect.c b/arch/s390/boot/mem_detect.c
index 4cb771ba13fa..5d316fe40480 100644
--- a/arch/s390/boot/mem_detect.c
+++ b/arch/s390/boot/mem_detect.c
@@ -25,7 +25,7 @@ static void *mem_detect_alloc_extended(void)
{
unsigned long offset = ALIGN(mem_safe_offset(), sizeof(u64));
- if (IS_ENABLED(BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE &&
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE &&
INITRD_START < offset + ENTRIES_EXTENDED_MAX)
offset = ALIGN(INITRD_START + INITRD_SIZE, sizeof(u64));
diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c
index 594464f2129d..0da378e2eb25 100644
--- a/arch/s390/kernel/fpu.c
+++ b/arch/s390/kernel/fpu.c
@@ -23,7 +23,7 @@ void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags)
if (flags & KERNEL_FPC)
/* Save floating point control */
- asm volatile("stfpc %0" : "=m" (state->fpc));
+ asm volatile("stfpc %0" : "=Q" (state->fpc));
if (!MACHINE_HAS_VX) {
if (flags & KERNEL_VXR_V0V7) {
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 02579f95f391..061418f787c3 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -426,3 +426,7 @@
421 32 rt_sigtimedwait_time64 - compat_sys_rt_sigtimedwait_time64
422 32 futex_time64 - sys_futex
423 32 sched_rr_get_interval_time64 - sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register sys_io_uring_register
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index a69a0911ed0e..c475ca49cfc6 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -37,7 +37,7 @@ static inline u64 get_vtimer(void)
{
u64 timer;
- asm volatile("stpt %0" : "=m" (timer));
+ asm volatile("stpt %0" : "=Q" (timer));
return timer;
}
@@ -48,7 +48,7 @@ static inline void set_vtimer(u64 expires)
asm volatile(
" stpt %0\n" /* Store current cpu timer value */
" spt %1" /* Set new value imm. afterwards */
- : "=m" (timer) : "m" (expires));
+ : "=Q" (timer) : "Q" (expires));
S390_lowcore.system_timer += S390_lowcore.last_update_timer - timer;
S390_lowcore.last_update_timer = expires;
}
@@ -135,8 +135,8 @@ static int do_account_vtime(struct task_struct *tsk)
#else
" stck %1" /* Store current tod clock value */
#endif
- : "=m" (S390_lowcore.last_update_timer),
- "=m" (S390_lowcore.last_update_clock));
+ : "=Q" (S390_lowcore.last_update_timer),
+ "=Q" (S390_lowcore.last_update_clock));
clock = S390_lowcore.last_update_clock - clock;
timer -= S390_lowcore.last_update_timer;
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index bfda678576e4..480b057556ee 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -426,3 +426,7 @@
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index b9a5a04b2d2c..a1dd24307b00 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -469,3 +469,7 @@
421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
422 32 futex_time64 sys_futex sys_futex
423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5ad92419be19..62fc3fda1a05 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1499,7 +1499,7 @@ config X86_CPA_STATISTICS
depends on DEBUG_FS
---help---
Expose statistics about the Change Page Attribute mechanims, which
- helps to determine the effectivness of preserving large and huge
+ helps to determine the effectiveness of preserving large and huge
page mappings when mapping protections are changed.
config ARCH_HAS_MEM_ENCRYPT
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index c0d6c560df69..5a237e8dbf8d 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -352,7 +352,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
boot_params->hdr.loadflags &= ~KASLR_FLAG;
/* Save RSDP address for later use. */
- boot_params->acpi_rsdp_addr = get_rsdp_addr();
+ /* boot_params->acpi_rsdp_addr = get_rsdp_addr(); */
sanitize_boot_params(boot_params);
diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S
index 3b6e70d085da..8457cdd47f75 100644
--- a/arch/x86/crypto/poly1305-avx2-x86_64.S
+++ b/arch/x86/crypto/poly1305-avx2-x86_64.S
@@ -323,6 +323,12 @@ ENTRY(poly1305_4block_avx2)
vpaddq t2,t1,t1
vmovq t1x,d4
+ # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 ->
+ # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small
+ # amount. Careful: we must not assume the carry bits 'd0 >> 26',
+ # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit
+ # integers. It's true in a single-block implementation, but not here.
+
# d1 += d0 >> 26
mov d0,%rax
shr $26,%rax
@@ -361,16 +367,16 @@ ENTRY(poly1305_4block_avx2)
# h0 += (d4 >> 26) * 5
mov d4,%rax
shr $26,%rax
- lea (%eax,%eax,4),%eax
- add %eax,%ebx
+ lea (%rax,%rax,4),%rax
+ add %rax,%rbx
# h4 = d4 & 0x3ffffff
mov d4,%rax
and $0x3ffffff,%eax
mov %eax,h4
# h1 += h0 >> 26
- mov %ebx,%eax
- shr $26,%eax
+ mov %rbx,%rax
+ shr $26,%rax
add %eax,h1
# h0 = h0 & 0x3ffffff
andl $0x3ffffff,%ebx
diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S
index e6add74d78a5..6f0be7a86964 100644
--- a/arch/x86/crypto/poly1305-sse2-x86_64.S
+++ b/arch/x86/crypto/poly1305-sse2-x86_64.S
@@ -253,16 +253,16 @@ ENTRY(poly1305_block_sse2)
# h0 += (d4 >> 26) * 5
mov d4,%rax
shr $26,%rax
- lea (%eax,%eax,4),%eax
- add %eax,%ebx
+ lea (%rax,%rax,4),%rax
+ add %rax,%rbx
# h4 = d4 & 0x3ffffff
mov d4,%rax
and $0x3ffffff,%eax
mov %eax,h4
# h1 += h0 >> 26
- mov %ebx,%eax
- shr $26,%eax
+ mov %rbx,%rax
+ shr $26,%rax
add %eax,h1
# h0 = h0 & 0x3ffffff
andl $0x3ffffff,%ebx
@@ -524,6 +524,12 @@ ENTRY(poly1305_2block_sse2)
paddq t2,t1
movq t1,d4
+ # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 ->
+ # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small
+ # amount. Careful: we must not assume the carry bits 'd0 >> 26',
+ # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit
+ # integers. It's true in a single-block implementation, but not here.
+
# d1 += d0 >> 26
mov d0,%rax
shr $26,%rax
@@ -562,16 +568,16 @@ ENTRY(poly1305_2block_sse2)
# h0 += (d4 >> 26) * 5
mov d4,%rax
shr $26,%rax
- lea (%eax,%eax,4),%eax
- add %eax,%ebx
+ lea (%rax,%rax,4),%rax
+ add %rax,%rbx
# h4 = d4 & 0x3ffffff
mov d4,%rax
and $0x3ffffff,%eax
mov %eax,h4
# h1 += h0 >> 26
- mov %ebx,%eax
- shr $26,%eax
+ mov %rbx,%rax
+ shr $26,%rax
add %eax,h1
# h0 = h0 & 0x3ffffff
andl $0x3ffffff,%ebx
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 0ecfac84ba91..d45f3fbd232e 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -117,22 +117,39 @@ static __initconst const u64 amd_hw_cache_event_ids
};
/*
- * AMD Performance Monitor K7 and later.
+ * AMD Performance Monitor K7 and later, up to and including Family 16h:
*/
static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
{
- [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
- [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x077e,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
- [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
- [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */
- [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x077e,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */
+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */
+};
+
+/*
+ * AMD Performance Monitor Family 17h and later:
+ */
+static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
+{
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287,
+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187,
};
static u64 amd_pmu_event_map(int hw_event)
{
+ if (boot_cpu_data.x86 >= 0x17)
+ return amd_f17h_perfmon_event_map[hw_event];
+
return amd_perfmon_event_map[hw_event];
}
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index f61dcbef20ff..f9451566cd9b 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3131,7 +3131,7 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
flags &= ~PERF_SAMPLE_TIME;
if (!event->attr.exclude_kernel)
flags &= ~PERF_SAMPLE_REGS_USER;
- if (event->attr.sample_regs_user & ~PEBS_REGS)
+ if (event->attr.sample_regs_user & ~PEBS_GP_REGS)
flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR);
return flags;
}
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 94a4b7fc75d0..d41de9af7a39 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -76,15 +76,15 @@
* Scope: Package (physical package)
* MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter.
* perf code: 0x04
- * Available model: HSW ULT,CNL
+ * Available model: HSW ULT,KBL,CNL
* Scope: Package (physical package)
* MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter.
* perf code: 0x05
- * Available model: HSW ULT,CNL
+ * Available model: HSW ULT,KBL,CNL
* Scope: Package (physical package)
* MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
* perf code: 0x06
- * Available model: HSW ULT,GLM,CNL
+ * Available model: HSW ULT,KBL,GLM,CNL
* Scope: Package (physical package)
*
*/
@@ -566,8 +566,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, hswult_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, hswult_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_MOBILE, cnl_cstates),
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index a75955741c50..1e98a42b560a 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -96,25 +96,25 @@ struct amd_nb {
PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
PERF_SAMPLE_PERIOD)
-#define PEBS_REGS \
- (PERF_REG_X86_AX | \
- PERF_REG_X86_BX | \
- PERF_REG_X86_CX | \
- PERF_REG_X86_DX | \
- PERF_REG_X86_DI | \
- PERF_REG_X86_SI | \
- PERF_REG_X86_SP | \
- PERF_REG_X86_BP | \
- PERF_REG_X86_IP | \
- PERF_REG_X86_FLAGS | \
- PERF_REG_X86_R8 | \
- PERF_REG_X86_R9 | \
- PERF_REG_X86_R10 | \
- PERF_REG_X86_R11 | \
- PERF_REG_X86_R12 | \
- PERF_REG_X86_R13 | \
- PERF_REG_X86_R14 | \
- PERF_REG_X86_R15)
+#define PEBS_GP_REGS \
+ ((1ULL << PERF_REG_X86_AX) | \
+ (1ULL << PERF_REG_X86_BX) | \
+ (1ULL << PERF_REG_X86_CX) | \
+ (1ULL << PERF_REG_X86_DX) | \
+ (1ULL << PERF_REG_X86_DI) | \
+ (1ULL << PERF_REG_X86_SI) | \
+ (1ULL << PERF_REG_X86_SP) | \
+ (1ULL << PERF_REG_X86_BP) | \
+ (1ULL << PERF_REG_X86_IP) | \
+ (1ULL << PERF_REG_X86_FLAGS) | \
+ (1ULL << PERF_REG_X86_R8) | \
+ (1ULL << PERF_REG_X86_R9) | \
+ (1ULL << PERF_REG_X86_R10) | \
+ (1ULL << PERF_REG_X86_R11) | \
+ (1ULL << PERF_REG_X86_R12) | \
+ (1ULL << PERF_REG_X86_R13) | \
+ (1ULL << PERF_REG_X86_R14) | \
+ (1ULL << PERF_REG_X86_R15))
/*
* Per register state.
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 93c4bf598fb0..feab24cac610 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -226,7 +226,9 @@ struct x86_emulate_ops {
unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags);
- int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, u64 smbase);
+ int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt,
+ const char *smstate);
+ void (*post_leave_smm)(struct x86_emulate_ctxt *ctxt);
};
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 159b5988292f..a9d03af34030 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -126,7 +126,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
}
#define KVM_PERMILLE_MMU_PAGES 20
-#define KVM_MIN_ALLOC_MMU_PAGES 64
+#define KVM_MIN_ALLOC_MMU_PAGES 64UL
#define KVM_MMU_HASH_SHIFT 12
#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
#define KVM_MIN_FREE_MMU_PAGES 5
@@ -844,9 +844,9 @@ enum kvm_irqchip_mode {
};
struct kvm_arch {
- unsigned int n_used_mmu_pages;
- unsigned int n_requested_mmu_pages;
- unsigned int n_max_mmu_pages;
+ unsigned long n_used_mmu_pages;
+ unsigned long n_requested_mmu_pages;
+ unsigned long n_max_mmu_pages;
unsigned int indirect_shadow_pages;
struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
/*
@@ -1182,7 +1182,7 @@ struct kvm_x86_ops {
int (*smi_allowed)(struct kvm_vcpu *vcpu);
int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
- int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase);
+ int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
int (*enable_smi_window)(struct kvm_vcpu *vcpu);
int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
@@ -1256,8 +1256,8 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
gfn_t gfn_offset, unsigned long mask);
void kvm_mmu_zap_all(struct kvm *kvm);
void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
-unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages);
int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
bool pdptrs_changed(struct kvm_vcpu *vcpu);
@@ -1592,4 +1592,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
#define put_smstate(type, buf, offset, val) \
*(type *)((buf) + (offset) - 0x7e00) = val
+#define GET_SMSTATE(type, buf, offset) \
+ (*(type *)((buf) + (offset) - 0x7e00))
+
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index f0b0c90dd398..d213ec5c3766 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -146,6 +146,7 @@
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
+#define VMX_ABORT_VMCS_CORRUPTED 3
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
#endif /* _UAPIVMX_H */
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index cfd24f9f7614..1796d2bdcaaa 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 intel_pconfig.o
+obj-$(CONFIG_CPU_SUP_INTEL) += intel.o intel_pconfig.o intel_epb.o
obj-$(CONFIG_CPU_SUP_AMD) += amd.o
obj-$(CONFIG_CPU_SUP_HYGON) += hygon.o
obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 2da82eff0eb4..b91b3bfa5cfb 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -275,7 +275,7 @@ static const struct {
const char *option;
enum spectre_v2_user_cmd cmd;
bool secure;
-} v2_user_options[] __initdata = {
+} v2_user_options[] __initconst = {
{ "auto", SPECTRE_V2_USER_CMD_AUTO, false },
{ "off", SPECTRE_V2_USER_CMD_NONE, false },
{ "on", SPECTRE_V2_USER_CMD_FORCE, true },
@@ -419,7 +419,7 @@ static const struct {
const char *option;
enum spectre_v2_mitigation_cmd cmd;
bool secure;
-} mitigation_options[] __initdata = {
+} mitigation_options[] __initconst = {
{ "off", SPECTRE_V2_CMD_NONE, false },
{ "on", SPECTRE_V2_CMD_FORCE, true },
{ "retpoline", SPECTRE_V2_CMD_RETPOLINE, false },
@@ -658,7 +658,7 @@ static const char * const ssb_strings[] = {
static const struct {
const char *option;
enum ssb_mitigation_cmd cmd;
-} ssb_mitigation_options[] __initdata = {
+} ssb_mitigation_options[] __initconst = {
{ "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */
{ "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */
{ "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index cb28e98a0659..5e37dfa4d9df 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1864,23 +1864,6 @@ void cpu_init(void)
}
#endif
-static void bsp_resume(void)
-{
- if (this_cpu->c_bsp_resume)
- this_cpu->c_bsp_resume(&boot_cpu_data);
-}
-
-static struct syscore_ops cpu_syscore_ops = {
- .resume = bsp_resume,
-};
-
-static int __init init_cpu_syscore(void)
-{
- register_syscore_ops(&cpu_syscore_ops);
- return 0;
-}
-core_initcall(init_cpu_syscore);
-
/*
* The microcode loader calls this upon late microcode load to recheck features,
* only when microcode has been updated. Caller holds microcode_mutex and CPU
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 5eb946b9a9f3..c0e2407abdd6 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -14,7 +14,6 @@ struct cpu_dev {
void (*c_init)(struct cpuinfo_x86 *);
void (*c_identify)(struct cpuinfo_x86 *);
void (*c_detect_tlb)(struct cpuinfo_x86 *);
- void (*c_bsp_resume)(struct cpuinfo_x86 *);
int c_x86_vendor;
#ifdef CONFIG_X86_32
/* Optional vendor specific routine to obtain the cache size. */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fc3c07fe7df5..f17c1a714779 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -596,36 +596,6 @@ detect_keyid_bits:
c->x86_phys_bits -= keyid_bits;
}
-static void init_intel_energy_perf(struct cpuinfo_x86 *c)
-{
- u64 epb;
-
- /*
- * Initialize MSR_IA32_ENERGY_PERF_BIAS if not already initialized.
- * (x86_energy_perf_policy(8) is available to change it at run-time.)
- */
- if (!cpu_has(c, X86_FEATURE_EPB))
- return;
-
- rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
- if ((epb & 0xF) != ENERGY_PERF_BIAS_PERFORMANCE)
- return;
-
- pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
- pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n");
- epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL;
- wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
-}
-
-static void intel_bsp_resume(struct cpuinfo_x86 *c)
-{
- /*
- * MSR_IA32_ENERGY_PERF_BIAS is lost across suspend/resume,
- * so reinitialize it properly like during bootup:
- */
- init_intel_energy_perf(c);
-}
-
static void init_cpuid_fault(struct cpuinfo_x86 *c)
{
u64 msr;
@@ -763,8 +733,6 @@ static void init_intel(struct cpuinfo_x86 *c)
if (cpu_has(c, X86_FEATURE_TME))
detect_tme(c);
- init_intel_energy_perf(c);
-
init_intel_misc_features(c);
}
@@ -1023,9 +991,7 @@ static const struct cpu_dev intel_cpu_dev = {
.c_detect_tlb = intel_detect_tlb,
.c_early_init = early_init_intel,
.c_init = init_intel,
- .c_bsp_resume = intel_bsp_resume,
.c_x86_vendor = X86_VENDOR_INTEL,
};
cpu_dev_register(intel_cpu_dev);
-
diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
new file mode 100644
index 000000000000..f4dd73396f28
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Performance and Energy Bias Hint support.
+ *
+ * Copyright (C) 2019 Intel Corporation
+ *
+ * Author:
+ * Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ */
+
+#include <linux/cpuhotplug.h>
+#include <linux/cpu.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/syscore_ops.h>
+#include <linux/pm.h>
+
+#include <asm/cpufeature.h>
+#include <asm/msr.h>
+
+/**
+ * DOC: overview
+ *
+ * The Performance and Energy Bias Hint (EPB) allows software to specify its
+ * preference with respect to the power-performance tradeoffs present in the
+ * processor. Generally, the EPB is expected to be set by user space (directly
+ * via sysfs or with the help of the x86_energy_perf_policy tool), but there are
+ * two reasons for the kernel to update it.
+ *
+ * First, there are systems where the platform firmware resets the EPB during
+ * system-wide transitions from sleep states back into the working state
+ * effectively causing the previous EPB updates by user space to be lost.
+ * Thus the kernel needs to save the current EPB values for all CPUs during
+ * system-wide transitions to sleep states and restore them on the way back to
+ * the working state. That can be achieved by saving EPB for secondary CPUs
+ * when they are taken offline during transitions into system sleep states and
+ * for the boot CPU in a syscore suspend operation, so that it can be restored
+ * for the boot CPU in a syscore resume operation and for the other CPUs when
+ * they are brought back online. However, CPUs that are already offline when
+ * a system-wide PM transition is started are not taken offline again, but their
+ * EPB values may still be reset by the platform firmware during the transition,
+ * so in fact it is necessary to save the EPB of any CPU taken offline and to
+ * restore it when the given CPU goes back online at all times.
+ *
+ * Second, on many systems the initial EPB value coming from the platform
+ * firmware is 0 ('performance') and at least on some of them that is because
+ * the platform firmware does not initialize EPB at all with the assumption that
+ * the OS will do that anyway. That sometimes is problematic, as it may cause
+ * the system battery to drain too fast, for example, so it is better to adjust
+ * it on CPU bring-up and if the initial EPB value for a given CPU is 0, the
+ * kernel changes it to 6 ('normal').
+ */
+
+static DEFINE_PER_CPU(u8, saved_epb);
+
+#define EPB_MASK 0x0fULL
+#define EPB_SAVED 0x10ULL
+#define MAX_EPB EPB_MASK
+
+static int intel_epb_save(void)
+{
+ u64 epb;
+
+ rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+ /*
+ * Ensure that saved_epb will always be nonzero after this write even if
+ * the EPB value read from the MSR is 0.
+ */
+ this_cpu_write(saved_epb, (epb & EPB_MASK) | EPB_SAVED);
+
+ return 0;
+}
+
+static void intel_epb_restore(void)
+{
+ u64 val = this_cpu_read(saved_epb);
+ u64 epb;
+
+ rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+ if (val) {
+ val &= EPB_MASK;
+ } else {
+ /*
+ * Because intel_epb_save() has not run for the current CPU yet,
+ * it is going online for the first time, so if its EPB value is
+ * 0 ('performance') at this point, assume that it has not been
+ * initialized by the platform firmware and set it to 6
+ * ('normal').
+ */
+ val = epb & EPB_MASK;
+ if (val == ENERGY_PERF_BIAS_PERFORMANCE) {
+ val = ENERGY_PERF_BIAS_NORMAL;
+ pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
+ }
+ }
+ wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, (epb & ~EPB_MASK) | val);
+}
+
+static struct syscore_ops intel_epb_syscore_ops = {
+ .suspend = intel_epb_save,
+ .resume = intel_epb_restore,
+};
+
+static const char * const energy_perf_strings[] = {
+ "performance",
+ "balance-performance",
+ "normal",
+ "balance-power",
+ "power"
+};
+static const u8 energ_perf_values[] = {
+ ENERGY_PERF_BIAS_PERFORMANCE,
+ ENERGY_PERF_BIAS_BALANCE_PERFORMANCE,
+ ENERGY_PERF_BIAS_NORMAL,
+ ENERGY_PERF_BIAS_BALANCE_POWERSAVE,
+ ENERGY_PERF_BIAS_POWERSAVE
+};
+
+static ssize_t energy_perf_bias_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ unsigned int cpu = dev->id;
+ u64 epb;
+ int ret;
+
+ ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
+ if (ret < 0)
+ return ret;
+
+ return sprintf(buf, "%llu\n", epb);
+}
+
+static ssize_t energy_perf_bias_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ unsigned int cpu = dev->id;
+ u64 epb, val;
+ int ret;
+
+ ret = __sysfs_match_string(energy_perf_strings,
+ ARRAY_SIZE(energy_perf_strings), buf);
+ if (ret >= 0)
+ val = energ_perf_values[ret];
+ else if (kstrtou64(buf, 0, &val) || val > MAX_EPB)
+ return -EINVAL;
+
+ ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
+ if (ret < 0)
+ return ret;
+
+ ret = wrmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS,
+ (epb & ~EPB_MASK) | val);
+ if (ret < 0)
+ return ret;
+
+ return count;
+}
+
+static DEVICE_ATTR_RW(energy_perf_bias);
+
+static struct attribute *intel_epb_attrs[] = {
+ &dev_attr_energy_perf_bias.attr,
+ NULL
+};
+
+static const struct attribute_group intel_epb_attr_group = {
+ .name = power_group_name,
+ .attrs = intel_epb_attrs
+};
+
+static int intel_epb_online(unsigned int cpu)
+{
+ struct device *cpu_dev = get_cpu_device(cpu);
+
+ intel_epb_restore();
+ if (!cpuhp_tasks_frozen)
+ sysfs_merge_group(&cpu_dev->kobj, &intel_epb_attr_group);
+
+ return 0;
+}
+
+static int intel_epb_offline(unsigned int cpu)
+{
+ struct device *cpu_dev = get_cpu_device(cpu);
+
+ if (!cpuhp_tasks_frozen)
+ sysfs_unmerge_group(&cpu_dev->kobj, &intel_epb_attr_group);
+
+ intel_epb_save();
+ return 0;
+}
+
+static __init int intel_epb_init(void)
+{
+ int ret;
+
+ if (!boot_cpu_has(X86_FEATURE_EPB))
+ return -ENODEV;
+
+ ret = cpuhp_setup_state(CPUHP_AP_X86_INTEL_EPB_ONLINE,
+ "x86/intel/epb:online", intel_epb_online,
+ intel_epb_offline);
+ if (ret < 0)
+ goto err_out_online;
+
+ register_syscore_ops(&intel_epb_syscore_ops);
+ return 0;
+
+err_out_online:
+ cpuhp_remove_state(CPUHP_AP_X86_INTEL_EPB_ONLINE);
+ return ret;
+}
+subsys_initcall(intel_epb_init);
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 54b9eef3eea9..85212a32b54d 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2610,9 +2610,10 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
rdt_last_cmd_puts("Failed to initialize allocations\n");
return ret;
}
- rdtgrp->mode = RDT_MODE_SHAREABLE;
}
+ rdtgrp->mode = RDT_MODE_SHAREABLE;
+
return 0;
}
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index a034cb808e7e..fed46ddb1eef 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -569,6 +569,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
unsigned long *sara = stack_addr(regs);
ri->ret_addr = (kprobe_opcode_t *) *sara;
+ ri->fp = sara;
/* Replace the return addr with trampoline addr */
*sara = (unsigned long) &kretprobe_trampoline;
@@ -748,26 +749,48 @@ asm(
NOKPROBE_SYMBOL(kretprobe_trampoline);
STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
+static struct kprobe kretprobe_kprobe = {
+ .addr = (void *)kretprobe_trampoline,
+};
+
/*
* Called from kretprobe_trampoline
*/
static __used void *trampoline_handler(struct pt_regs *regs)
{
+ struct kprobe_ctlblk *kcb;
struct kretprobe_instance *ri = NULL;
struct hlist_head *head, empty_rp;
struct hlist_node *tmp;
unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
kprobe_opcode_t *correct_ret_addr = NULL;
+ void *frame_pointer;
+ bool skipped = false;
+
+ preempt_disable();
+
+ /*
+ * Set a dummy kprobe for avoiding kretprobe recursion.
+ * Since kretprobe never run in kprobe handler, kprobe must not
+ * be running at this point.
+ */
+ kcb = get_kprobe_ctlblk();
+ __this_cpu_write(current_kprobe, &kretprobe_kprobe);
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
INIT_HLIST_HEAD(&empty_rp);
kretprobe_hash_lock(current, &head, &flags);
/* fixup registers */
#ifdef CONFIG_X86_64
regs->cs = __KERNEL_CS;
+ /* On x86-64, we use pt_regs->sp for return address holder. */
+ frame_pointer = &regs->sp;
#else
regs->cs = __KERNEL_CS | get_kernel_rpl();
regs->gs = 0;
+ /* On x86-32, we use pt_regs->flags for return address holder. */
+ frame_pointer = &regs->flags;
#endif
regs->ip = trampoline_address;
regs->orig_ax = ~0UL;
@@ -789,8 +812,25 @@ static __used void *trampoline_handler(struct pt_regs *regs)
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
+ /*
+ * Return probes must be pushed on this hash list correct
+ * order (same as return order) so that it can be poped
+ * correctly. However, if we find it is pushed it incorrect
+ * order, this means we find a function which should not be
+ * probed, because the wrong order entry is pushed on the
+ * path of processing other kretprobe itself.
+ */
+ if (ri->fp != frame_pointer) {
+ if (!skipped)
+ pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
+ skipped = true;
+ continue;
+ }
orig_ret_address = (unsigned long)ri->ret_addr;
+ if (skipped)
+ pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
+ ri->rp->kp.addr);
if (orig_ret_address != trampoline_address)
/*
@@ -808,14 +848,15 @@ static __used void *trampoline_handler(struct pt_regs *regs)
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
+ if (ri->fp != frame_pointer)
+ continue;
orig_ret_address = (unsigned long)ri->ret_addr;
if (ri->rp && ri->rp->handler) {
__this_cpu_write(current_kprobe, &ri->rp->kp);
- get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
ri->ret_addr = correct_ret_addr;
ri->rp->handler(ri, regs);
- __this_cpu_write(current_kprobe, NULL);
+ __this_cpu_write(current_kprobe, &kretprobe_kprobe);
}
recycle_rp_inst(ri, &empty_rp);
@@ -831,6 +872,9 @@ static __used void *trampoline_handler(struct pt_regs *regs)
kretprobe_hash_unlock(current, &flags);
+ __this_cpu_write(current_kprobe, NULL);
+ preempt_enable();
+
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
kfree(ri);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 58ac7be52c7a..957eae13b370 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -426,6 +426,8 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp,
u64 msr = x86_spec_ctrl_base;
bool updmsr = false;
+ lockdep_assert_irqs_disabled();
+
/*
* If TIF_SSBD is different, select the proper mitigation
* method. Note that if SSBD mitigation is disabled or permanentely
@@ -477,10 +479,12 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk)
void speculation_ctrl_update(unsigned long tif)
{
+ unsigned long flags;
+
/* Forced update. Make sure all relevant TIF flags are different */
- preempt_disable();
+ local_irq_save(flags);
__speculation_ctrl_update(~tif, tif);
- preempt_enable();
+ local_irq_restore(flags);
}
/* Called from seccomp/prctl update */
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 725624b6c0c0..8fd3cedd9acc 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -81,6 +81,19 @@ static int __init set_bios_reboot(const struct dmi_system_id *d)
return 0;
}
+/*
+ * Some machines don't handle the default ACPI reboot method and
+ * require the EFI reboot method:
+ */
+static int __init set_efi_reboot(const struct dmi_system_id *d)
+{
+ if (reboot_type != BOOT_EFI && !efi_runtime_disabled()) {
+ reboot_type = BOOT_EFI;
+ pr_info("%s series board detected. Selecting EFI-method for reboot.\n", d->ident);
+ }
+ return 0;
+}
+
void __noreturn machine_real_restart(unsigned int type)
{
local_irq_disable();
@@ -166,6 +179,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = {
DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"),
},
},
+ { /* Handle reboot issue on Acer TravelMate X514-51T */
+ .callback = set_efi_reboot,
+ .ident = "Acer TravelMate X514-51T",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate X514-51T"),
+ },
+ },
/* Apple */
{ /* Handle problems with rebooting on Apple MacBook5 */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 3fae23834069..cc6df5c6d7b3 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -185,8 +185,7 @@ static void __init cyc2ns_init_boot_cpu(void)
/*
* Secondary CPUs do not run through tsc_init(), so set up
* all the scale factors for all CPUs, assuming the same
- * speed as the bootup CPU. (cpufreq notifiers will fix this
- * up if their speed diverges)
+ * speed as the bootup CPU.
*/
static void __init cyc2ns_init_secondary_cpus(void)
{
@@ -937,12 +936,12 @@ void tsc_restore_sched_clock_state(void)
}
#ifdef CONFIG_CPU_FREQ
-/* Frequency scaling support. Adjust the TSC based timer when the cpu frequency
+/*
+ * Frequency scaling support. Adjust the TSC based timer when the CPU frequency
* changes.
*
- * RED-PEN: On SMP we assume all CPUs run with the same frequency. It's
- * not that important because current Opteron setups do not support
- * scaling on SMP anyroads.
+ * NOTE: On SMP the situation is not fixable in general, so simply mark the TSC
+ * as unstable and give up in those cases.
*
* Should fix up last_tsc too. Currently gettimeofday in the
* first tick after the change will be slightly wrong.
@@ -956,22 +955,22 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
void *data)
{
struct cpufreq_freqs *freq = data;
- unsigned long *lpj;
- lpj = &boot_cpu_data.loops_per_jiffy;
-#ifdef CONFIG_SMP
- if (!(freq->flags & CPUFREQ_CONST_LOOPS))
- lpj = &cpu_data(freq->cpu).loops_per_jiffy;
-#endif
+ if (num_online_cpus() > 1) {
+ mark_tsc_unstable("cpufreq changes on SMP");
+ return 0;
+ }
if (!ref_freq) {
ref_freq = freq->old;
- loops_per_jiffy_ref = *lpj;
+ loops_per_jiffy_ref = boot_cpu_data.loops_per_jiffy;
tsc_khz_ref = tsc_khz;
}
+
if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) ||
- (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
- *lpj = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
+ (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
+ boot_cpu_data.loops_per_jiffy =
+ cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
if (!(freq->flags & CPUFREQ_CONST_LOOPS))
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index bad8c51fee6e..a5127b2c195f 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -362,7 +362,7 @@ SECTIONS
.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
__bss_start = .;
*(.bss..page_aligned)
- *(.bss)
+ *(BSS_MAIN)
BSS_DECRYPTED
. = ALIGN(PAGE_SIZE);
__bss_stop = .;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index c338984c850d..d0d5dd44b4f4 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2331,24 +2331,18 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt)
static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
{
+#ifdef CONFIG_X86_64
u32 eax, ebx, ecx, edx;
eax = 0x80000001;
ecx = 0;
ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
return edx & bit(X86_FEATURE_LM);
+#else
+ return false;
+#endif
}
-#define GET_SMSTATE(type, smbase, offset) \
- ({ \
- type __val; \
- int r = ctxt->ops->read_phys(ctxt, smbase + offset, &__val, \
- sizeof(__val)); \
- if (r != X86EMUL_CONTINUE) \
- return X86EMUL_UNHANDLEABLE; \
- __val; \
- })
-
static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
{
desc->g = (flags >> 23) & 1;
@@ -2361,27 +2355,30 @@ static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
desc->type = (flags >> 8) & 15;
}
-static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate,
+ int n)
{
struct desc_struct desc;
int offset;
u16 selector;
- selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4);
+ selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4);
if (n < 3)
offset = 0x7f84 + n * 12;
else
offset = 0x7f2c + (n - 3) * 12;
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
return X86EMUL_CONTINUE;
}
-static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+#ifdef CONFIG_X86_64
+static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate,
+ int n)
{
struct desc_struct desc;
int offset;
@@ -2390,15 +2387,16 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
offset = 0x7e00 + n * 16;
- selector = GET_SMSTATE(u16, smbase, offset);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8));
- base3 = GET_SMSTATE(u32, smbase, offset + 12);
+ selector = GET_SMSTATE(u16, smstate, offset);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
+ base3 = GET_SMSTATE(u32, smstate, offset + 12);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
return X86EMUL_CONTINUE;
}
+#endif
static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
u64 cr0, u64 cr3, u64 cr4)
@@ -2445,7 +2443,8 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
return X86EMUL_CONTINUE;
}
-static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
{
struct desc_struct desc;
struct desc_ptr dt;
@@ -2453,53 +2452,55 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
u32 val, cr0, cr3, cr4;
int i;
- cr0 = GET_SMSTATE(u32, smbase, 0x7ffc);
- cr3 = GET_SMSTATE(u32, smbase, 0x7ff8);
- ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
- ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0);
+ cr0 = GET_SMSTATE(u32, smstate, 0x7ffc);
+ cr3 = GET_SMSTATE(u32, smstate, 0x7ff8);
+ ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
+ ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0);
for (i = 0; i < 8; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4);
+ *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
- val = GET_SMSTATE(u32, smbase, 0x7fcc);
+ val = GET_SMSTATE(u32, smstate, 0x7fcc);
ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
- val = GET_SMSTATE(u32, smbase, 0x7fc8);
+ val = GET_SMSTATE(u32, smstate, 0x7fc8);
ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
- selector = GET_SMSTATE(u32, smbase, 0x7fc4);
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f64));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f60));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f5c));
+ selector = GET_SMSTATE(u32, smstate, 0x7fc4);
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f60));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f5c));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
- selector = GET_SMSTATE(u32, smbase, 0x7fc0);
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f80));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f7c));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f78));
+ selector = GET_SMSTATE(u32, smstate, 0x7fc0);
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f80));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f7c));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f78));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
- dt.address = GET_SMSTATE(u32, smbase, 0x7f74);
- dt.size = GET_SMSTATE(u32, smbase, 0x7f70);
+ dt.address = GET_SMSTATE(u32, smstate, 0x7f74);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7f70);
ctxt->ops->set_gdt(ctxt, &dt);
- dt.address = GET_SMSTATE(u32, smbase, 0x7f58);
- dt.size = GET_SMSTATE(u32, smbase, 0x7f54);
+ dt.address = GET_SMSTATE(u32, smstate, 0x7f58);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7f54);
ctxt->ops->set_idt(ctxt, &dt);
for (i = 0; i < 6; i++) {
- int r = rsm_load_seg_32(ctxt, smbase, i);
+ int r = rsm_load_seg_32(ctxt, smstate, i);
if (r != X86EMUL_CONTINUE)
return r;
}
- cr4 = GET_SMSTATE(u32, smbase, 0x7f14);
+ cr4 = GET_SMSTATE(u32, smstate, 0x7f14);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
+ ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8));
return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
}
-static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
+#ifdef CONFIG_X86_64
+static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
{
struct desc_struct desc;
struct desc_ptr dt;
@@ -2509,43 +2510,43 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
int i, r;
for (i = 0; i < 16; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8);
+ *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
- ctxt->_eip = GET_SMSTATE(u64, smbase, 0x7f78);
- ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED;
+ ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78);
+ ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
- val = GET_SMSTATE(u32, smbase, 0x7f68);
+ val = GET_SMSTATE(u32, smstate, 0x7f68);
ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
- val = GET_SMSTATE(u32, smbase, 0x7f60);
+ val = GET_SMSTATE(u32, smstate, 0x7f60);
ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
- cr0 = GET_SMSTATE(u64, smbase, 0x7f58);
- cr3 = GET_SMSTATE(u64, smbase, 0x7f50);
- cr4 = GET_SMSTATE(u64, smbase, 0x7f48);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
- val = GET_SMSTATE(u64, smbase, 0x7ed0);
+ cr0 = GET_SMSTATE(u64, smstate, 0x7f58);
+ cr3 = GET_SMSTATE(u64, smstate, 0x7f50);
+ cr4 = GET_SMSTATE(u64, smstate, 0x7f48);
+ ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
+ val = GET_SMSTATE(u64, smstate, 0x7ed0);
ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
- selector = GET_SMSTATE(u32, smbase, 0x7e90);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e92) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e94));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e98));
- base3 = GET_SMSTATE(u32, smbase, 0x7e9c);
+ selector = GET_SMSTATE(u32, smstate, 0x7e90);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e94));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e98));
+ base3 = GET_SMSTATE(u32, smstate, 0x7e9c);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
- dt.size = GET_SMSTATE(u32, smbase, 0x7e84);
- dt.address = GET_SMSTATE(u64, smbase, 0x7e88);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7e84);
+ dt.address = GET_SMSTATE(u64, smstate, 0x7e88);
ctxt->ops->set_idt(ctxt, &dt);
- selector = GET_SMSTATE(u32, smbase, 0x7e70);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e72) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e74));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e78));
- base3 = GET_SMSTATE(u32, smbase, 0x7e7c);
+ selector = GET_SMSTATE(u32, smstate, 0x7e70);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e72) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e74));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e78));
+ base3 = GET_SMSTATE(u32, smstate, 0x7e7c);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
- dt.size = GET_SMSTATE(u32, smbase, 0x7e64);
- dt.address = GET_SMSTATE(u64, smbase, 0x7e68);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7e64);
+ dt.address = GET_SMSTATE(u64, smstate, 0x7e68);
ctxt->ops->set_gdt(ctxt, &dt);
r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
@@ -2553,37 +2554,49 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
return r;
for (i = 0; i < 6; i++) {
- r = rsm_load_seg_64(ctxt, smbase, i);
+ r = rsm_load_seg_64(ctxt, smstate, i);
if (r != X86EMUL_CONTINUE)
return r;
}
return X86EMUL_CONTINUE;
}
+#endif
static int em_rsm(struct x86_emulate_ctxt *ctxt)
{
unsigned long cr0, cr4, efer;
+ char buf[512];
u64 smbase;
int ret;
if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
return emulate_ud(ctxt);
+ smbase = ctxt->ops->get_smbase(ctxt);
+
+ ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf));
+ if (ret != X86EMUL_CONTINUE)
+ return X86EMUL_UNHANDLEABLE;
+
+ if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+ ctxt->ops->set_nmi_mask(ctxt, false);
+
+ ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
+ ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
+
/*
* Get back to real mode, to prepare a safe state in which to load
* CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU
* supports long mode.
*/
- cr4 = ctxt->ops->get_cr(ctxt, 4);
if (emulator_has_longmode(ctxt)) {
struct desc_struct cs_desc;
/* Zero CR4.PCIDE before CR0.PG. */
- if (cr4 & X86_CR4_PCIDE) {
+ cr4 = ctxt->ops->get_cr(ctxt, 4);
+ if (cr4 & X86_CR4_PCIDE)
ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
- cr4 &= ~X86_CR4_PCIDE;
- }
/* A 32-bit code segment is required to clear EFER.LMA. */
memset(&cs_desc, 0, sizeof(cs_desc));
@@ -2597,39 +2610,39 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
if (cr0 & X86_CR0_PE)
ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
- /* Now clear CR4.PAE (which must be done before clearing EFER.LME). */
- if (cr4 & X86_CR4_PAE)
- ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
-
- /* And finally go back to 32-bit mode. */
- efer = 0;
- ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+ if (emulator_has_longmode(ctxt)) {
+ /* Clear CR4.PAE before clearing EFER.LME. */
+ cr4 = ctxt->ops->get_cr(ctxt, 4);
+ if (cr4 & X86_CR4_PAE)
+ ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
- smbase = ctxt->ops->get_smbase(ctxt);
+ /* And finally go back to 32-bit mode. */
+ efer = 0;
+ ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+ }
/*
* Give pre_leave_smm() a chance to make ISA-specific changes to the
* vCPU state (e.g. enter guest mode) before loading state from the SMM
* state-save area.
*/
- if (ctxt->ops->pre_leave_smm(ctxt, smbase))
+ if (ctxt->ops->pre_leave_smm(ctxt, buf))
return X86EMUL_UNHANDLEABLE;
+#ifdef CONFIG_X86_64
if (emulator_has_longmode(ctxt))
- ret = rsm_load_state_64(ctxt, smbase + 0x8000);
+ ret = rsm_load_state_64(ctxt, buf);
else
- ret = rsm_load_state_32(ctxt, smbase + 0x8000);
+#endif
+ ret = rsm_load_state_32(ctxt, buf);
if (ret != X86EMUL_CONTINUE) {
/* FIXME: should triple fault */
return X86EMUL_UNHANDLEABLE;
}
- if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
- ctxt->ops->set_nmi_mask(ctxt, false);
+ ctxt->ops->post_leave_smm(ctxt);
- ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
- ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
return X86EMUL_CONTINUE;
}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 991fdf7fc17f..9bf70cf84564 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -138,6 +138,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
if (offset <= max_apic_id) {
u8 cluster_size = min(max_apic_id - offset + 1, 16U);
+ offset = array_index_nospec(offset, map->max_apic_id + 1);
*cluster = &map->phys_map[offset];
*mask = dest_id & (0xffff >> (16 - cluster_size));
} else {
@@ -901,7 +902,8 @@ static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm,
if (irq->dest_id > map->max_apic_id) {
*bitmap = 0;
} else {
- *dst = &map->phys_map[irq->dest_id];
+ u32 dest_id = array_index_nospec(irq->dest_id, map->max_apic_id + 1);
+ *dst = &map->phys_map[dest_id];
*bitmap = 1;
}
return true;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index eee455a8a612..e10962dfc203 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2007,7 +2007,7 @@ static int is_empty_shadow_page(u64 *spt)
* aggregate version in order to make the slab shrinker
* faster
*/
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
{
kvm->arch.n_used_mmu_pages += nr;
percpu_counter_add(&kvm_total_used_mmu_pages, nr);
@@ -2238,7 +2238,7 @@ static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm,
struct list_head *invalid_list,
bool remote_flush)
{
- if (!remote_flush && !list_empty(invalid_list))
+ if (!remote_flush && list_empty(invalid_list))
return false;
if (!list_empty(invalid_list))
@@ -2763,7 +2763,7 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm,
* Changing the number of mmu pages allocated to the vm
* Note: if goal_nr_mmu_pages is too small, you will get dead lock
*/
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages)
{
LIST_HEAD(invalid_list);
@@ -6031,10 +6031,10 @@ out:
/*
* Calculate mmu pages needed for kvm.
*/
-unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
{
- unsigned int nr_mmu_pages;
- unsigned int nr_pages = 0;
+ unsigned long nr_mmu_pages;
+ unsigned long nr_pages = 0;
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int i;
@@ -6047,8 +6047,7 @@ unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
}
nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
- nr_mmu_pages = max(nr_mmu_pages,
- (unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
+ nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES);
return nr_mmu_pages;
}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index bbdc60f2fae8..54c2a377795b 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -64,7 +64,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
u64 fault_address, char *insn, int insn_len);
-static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
+static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm)
{
if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages)
return kvm->arch.n_max_mmu_pages -
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 58ead7db71a3..e39741997893 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -281,9 +281,13 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
{
bool fast_mode = idx & (1u << 31);
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
struct kvm_pmc *pmc;
u64 ctr_val;
+ if (!pmu->version)
+ return 1;
+
if (is_vmware_backdoor_pmc(idx))
return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e0a791c3d4fc..406b558abfef 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -262,6 +262,7 @@ struct amd_svm_iommu_ir {
};
#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF)
+#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31
#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31)
#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL)
@@ -2692,6 +2693,7 @@ static int npf_interception(struct vcpu_svm *svm)
static int db_interception(struct vcpu_svm *svm)
{
struct kvm_run *kvm_run = svm->vcpu.run;
+ struct kvm_vcpu *vcpu = &svm->vcpu;
if (!(svm->vcpu.guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
@@ -2702,6 +2704,8 @@ static int db_interception(struct vcpu_svm *svm)
if (svm->nmi_singlestep) {
disable_nmi_singlestep(svm);
+ /* Make sure we check for pending NMIs upon entry */
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
}
if (svm->vcpu.guest_debug &
@@ -4517,14 +4521,25 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
kvm_lapic_reg_write(apic, APIC_ICR, icrl);
break;
case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
+ int i;
+ struct kvm_vcpu *vcpu;
+ struct kvm *kvm = svm->vcpu.kvm;
struct kvm_lapic *apic = svm->vcpu.arch.apic;
/*
- * Update ICR high and low, then emulate sending IPI,
- * which is handled when writing APIC_ICR.
+ * At this point, we expect that the AVIC HW has already
+ * set the appropriate IRR bits on the valid target
+ * vcpus. So, we just need to kick the appropriate vcpu.
*/
- kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
- kvm_lapic_reg_write(apic, APIC_ICR, icrl);
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ bool m = kvm_apic_match_dest(vcpu, apic,
+ icrl & KVM_APIC_SHORT_MASK,
+ GET_APIC_DEST_FIELD(icrh),
+ icrl & KVM_APIC_DEST_MASK);
+
+ if (m && !avic_vcpu_is_running(vcpu))
+ kvm_vcpu_wake_up(vcpu);
+ }
break;
}
case AVIC_IPI_FAILURE_INVALID_TARGET:
@@ -4596,7 +4611,7 @@ static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu)
u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat);
if (entry)
- WRITE_ONCE(*entry, (u32) ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK);
+ clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry);
}
static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
@@ -5621,6 +5636,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
svm->vmcb->save.cr2 = vcpu->arch.cr2;
clgi();
+ kvm_load_guest_xcr0(vcpu);
/*
* If this vCPU has touched SPEC_CTRL, restore the guest's value if
@@ -5766,6 +5782,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
kvm_before_interrupt(&svm->vcpu);
+ kvm_put_guest_xcr0(vcpu);
stgi();
/* Any pending NMI will happen here */
@@ -6215,32 +6232,24 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *nested_vmcb;
struct page *page;
- struct {
- u64 guest;
- u64 vmcb;
- } svm_state_save;
- int ret;
+ u64 guest;
+ u64 vmcb;
- ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfed8, &svm_state_save,
- sizeof(svm_state_save));
- if (ret)
- return ret;
+ guest = GET_SMSTATE(u64, smstate, 0x7ed8);
+ vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
- if (svm_state_save.guest) {
- vcpu->arch.hflags &= ~HF_SMM_MASK;
- nested_vmcb = nested_svm_map(svm, svm_state_save.vmcb, &page);
- if (nested_vmcb)
- enter_svm_guest_mode(svm, svm_state_save.vmcb, nested_vmcb, page);
- else
- ret = 1;
- vcpu->arch.hflags |= HF_SMM_MASK;
+ if (guest) {
+ nested_vmcb = nested_svm_map(svm, vmcb, &page);
+ if (!nested_vmcb)
+ return 1;
+ enter_svm_guest_mode(svm, vmcb, nested_vmcb, page);
}
- return ret;
+ return 0;
}
static int enable_smi_window(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 6432d08c7de7..4d47a2631d1f 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -438,13 +438,13 @@ TRACE_EVENT(kvm_apic_ipi,
);
TRACE_EVENT(kvm_apic_accept_irq,
- TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec),
+ TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec),
TP_ARGS(apicid, dm, tm, vec),
TP_STRUCT__entry(
__field( __u32, apicid )
__field( __u16, dm )
- __field( __u8, tm )
+ __field( __u16, tm )
__field( __u8, vec )
),
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 7ec9bb1dd723..6401eb7ef19c 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2873,20 +2873,27 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
/*
* If translation failed, VM entry will fail because
* prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull.
- * Failing the vm entry is _not_ what the processor
- * does but it's basically the only possibility we
- * have. We could still enter the guest if CR8 load
- * exits are enabled, CR8 store exits are enabled, and
- * virtualize APIC access is disabled; in this case
- * the processor would never use the TPR shadow and we
- * could simply clear the bit from the execution
- * control. But such a configuration is useless, so
- * let's keep the code simple.
*/
if (!is_error_page(page)) {
vmx->nested.virtual_apic_page = page;
hpa = page_to_phys(vmx->nested.virtual_apic_page);
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa);
+ } else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) &&
+ nested_cpu_has(vmcs12, CPU_BASED_CR8_STORE_EXITING) &&
+ !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ /*
+ * The processor will never use the TPR shadow, simply
+ * clear the bit from the execution control. Such a
+ * configuration is useless, but it happens in tests.
+ * For any other configuration, failing the vm entry is
+ * _not_ what the processor does but it's basically the
+ * only possibility we have.
+ */
+ vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
+ CPU_BASED_TPR_SHADOW);
+ } else {
+ printk("bad virtual-APIC page address\n");
+ dump_vmcs();
}
}
@@ -3789,8 +3796,18 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW));
nested_ept_uninit_mmu_context(vcpu);
- vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
- __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+
+ /*
+ * This is only valid if EPT is in use, otherwise the vmcs01 GUEST_CR3
+ * points to shadow pages! Fortunately we only get here after a WARN_ON
+ * if EPT is disabled, so a VMabort is perfectly fine.
+ */
+ if (enable_ept) {
+ vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+ __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+ } else {
+ nested_vmx_abort(vcpu, VMX_ABORT_VMCS_CORRUPTED);
+ }
/*
* Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
@@ -5738,6 +5755,14 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
{
int i;
+ /*
+ * Without EPT it is not possible to restore L1's CR3 and PDPTR on
+ * VMfail, because they are not available in vmcs01. Just always
+ * use hardware checks.
+ */
+ if (!enable_ept)
+ nested_early_check = 1;
+
if (!cpu_has_vmx_shadow_vmcs())
enable_shadow_vmcs = 0;
if (enable_shadow_vmcs) {
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index ab432a930ae8..b4e7d645275a 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5603,7 +5603,7 @@ static void vmx_dump_dtsel(char *name, uint32_t limit)
vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
}
-static void dump_vmcs(void)
+void dump_vmcs(void)
{
u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
@@ -6410,6 +6410,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
vmx_set_interrupt_shadow(vcpu, 0);
+ kvm_load_guest_xcr0(vcpu);
+
if (static_cpu_has(X86_FEATURE_PKU) &&
kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
vcpu->arch.pkru != vmx->host_pkru)
@@ -6506,6 +6508,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
__write_pkru(vmx->host_pkru);
}
+ kvm_put_guest_xcr0(vcpu);
+
vmx->nested.nested_run_pending = 0;
vmx->idt_vectoring_info = 0;
@@ -6852,6 +6856,30 @@ static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
}
}
+static bool guest_cpuid_has_pmu(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *entry;
+ union cpuid10_eax eax;
+
+ entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
+ if (!entry)
+ return false;
+
+ eax.full = entry->eax;
+ return (eax.split.version_id > 0);
+}
+
+static void nested_vmx_procbased_ctls_update(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ bool pmu_enabled = guest_cpuid_has_pmu(vcpu);
+
+ if (pmu_enabled)
+ vmx->nested.msrs.procbased_ctls_high |= CPU_BASED_RDPMC_EXITING;
+ else
+ vmx->nested.msrs.procbased_ctls_high &= ~CPU_BASED_RDPMC_EXITING;
+}
+
static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6940,6 +6968,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
if (nested_vmx_allowed(vcpu)) {
nested_vmx_cr_fixed1_bits_update(vcpu);
nested_vmx_entry_exit_ctls_update(vcpu);
+ nested_vmx_procbased_ctls_update(vcpu);
}
if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
@@ -7369,7 +7398,7 @@ static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int ret;
@@ -7380,9 +7409,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
}
if (vmx->nested.smm.guest_mode) {
- vcpu->arch.hflags &= ~HF_SMM_MASK;
ret = nested_vmx_enter_non_root_mode(vcpu, false);
- vcpu->arch.hflags |= HF_SMM_MASK;
if (ret)
return ret;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index a1e00d0a2482..f879529906b4 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -517,4 +517,6 @@ static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx)
vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
}
+void dump_vmcs(void);
+
#endif /* __KVM_X86_VMX_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 099b851dabaf..a0d1fc80ac5a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -800,7 +800,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
}
EXPORT_SYMBOL_GPL(kvm_lmsw);
-static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
{
if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
!vcpu->guest_xcr0_loaded) {
@@ -810,8 +810,9 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
vcpu->guest_xcr0_loaded = 1;
}
}
+EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
-static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
{
if (vcpu->guest_xcr0_loaded) {
if (vcpu->arch.xcr0 != host_xcr0)
@@ -819,6 +820,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
vcpu->guest_xcr0_loaded = 0;
}
}
+EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0);
static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
{
@@ -3093,7 +3095,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
break;
case KVM_CAP_NESTED_STATE:
r = kvm_x86_ops->get_nested_state ?
- kvm_x86_ops->get_nested_state(NULL, 0, 0) : 0;
+ kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0;
break;
default:
break;
@@ -3528,7 +3530,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
memset(&events->reserved, 0, sizeof(events->reserved));
}
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+static void kvm_smm_changed(struct kvm_vcpu *vcpu);
static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
@@ -3588,12 +3590,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
vcpu->arch.apic->sipi_vector = events->sipi_vector;
if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
- u32 hflags = vcpu->arch.hflags;
- if (events->smi.smm)
- hflags |= HF_SMM_MASK;
- else
- hflags &= ~HF_SMM_MASK;
- kvm_set_hflags(vcpu, hflags);
+ if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
+ if (events->smi.smm)
+ vcpu->arch.hflags |= HF_SMM_MASK;
+ else
+ vcpu->arch.hflags &= ~HF_SMM_MASK;
+ kvm_smm_changed(vcpu);
+ }
vcpu->arch.smi_pending = events->smi.pending;
@@ -4270,7 +4273,7 @@ static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm,
}
static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
- u32 kvm_nr_mmu_pages)
+ unsigned long kvm_nr_mmu_pages)
{
if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
return -EINVAL;
@@ -4284,7 +4287,7 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
return 0;
}
-static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
+static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
{
return kvm->arch.n_max_mmu_pages;
}
@@ -5958,12 +5961,18 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
{
- kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags);
+ emul_to_vcpu(ctxt)->arch.hflags = emul_flags;
+}
+
+static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
+{
+ return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smstate);
}
-static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt)
{
- return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smbase);
+ kvm_smm_changed(emul_to_vcpu(ctxt));
}
static const struct x86_emulate_ops emulate_ops = {
@@ -6006,6 +6015,7 @@ static const struct x86_emulate_ops emulate_ops = {
.get_hflags = emulator_get_hflags,
.set_hflags = emulator_set_hflags,
.pre_leave_smm = emulator_pre_leave_smm,
+ .post_leave_smm = emulator_post_leave_smm,
};
static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
@@ -6247,16 +6257,6 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu)
kvm_mmu_reset_context(vcpu);
}
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags)
-{
- unsigned changed = vcpu->arch.hflags ^ emul_flags;
-
- vcpu->arch.hflags = emul_flags;
-
- if (changed & HF_SMM_MASK)
- kvm_smm_changed(vcpu);
-}
-
static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
unsigned long *db)
{
@@ -7441,9 +7441,9 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
}
+#ifdef CONFIG_X86_64
static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
{
-#ifdef CONFIG_X86_64
struct desc_ptr dt;
struct kvm_segment seg;
unsigned long val;
@@ -7493,10 +7493,8 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
for (i = 0; i < 6; i++)
enter_smm_save_seg_64(vcpu, buf, i);
-#else
- WARN_ON_ONCE(1);
-#endif
}
+#endif
static void enter_smm(struct kvm_vcpu *vcpu)
{
@@ -7507,9 +7505,11 @@ static void enter_smm(struct kvm_vcpu *vcpu)
trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
memset(buf, 0, 512);
+#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
enter_smm_save_state_64(vcpu, buf);
else
+#endif
enter_smm_save_state_32(vcpu, buf);
/*
@@ -7567,8 +7567,10 @@ static void enter_smm(struct kvm_vcpu *vcpu)
kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
+#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
kvm_x86_ops->set_efer(vcpu, 0);
+#endif
kvm_update_cpuid(vcpu);
kvm_mmu_reset_context(vcpu);
@@ -7865,8 +7867,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
goto cancel_injection;
}
- kvm_load_guest_xcr0(vcpu);
-
if (req_immediate_exit) {
kvm_make_request(KVM_REQ_EVENT, vcpu);
kvm_x86_ops->request_immediate_exit(vcpu);
@@ -7919,8 +7919,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
vcpu->mode = OUTSIDE_GUEST_MODE;
smp_wmb();
- kvm_put_guest_xcr0(vcpu);
-
kvm_before_interrupt(vcpu);
kvm_x86_ops->handle_external_intr(vcpu);
kvm_after_interrupt(vcpu);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 28406aa1136d..aedc5d0d4989 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -347,4 +347,6 @@ static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu)
__this_cpu_write(current_vcpu, NULL);
}
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu);
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu);
#endif
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index ee8f8ab46941..c0309ea9abee 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -259,7 +259,8 @@ static void note_wx(struct pg_state *st)
#endif
/* Account the WX pages */
st->wx_pages += npages;
- WARN_ONCE(1, "x86/mm: Found insecure W+X mapping at address %pS\n",
+ WARN_ONCE(__supported_pte_mask & _PAGE_NX,
+ "x86/mm: Found insecure W+X mapping at address %pS\n",
(void *)st->start_address);
}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index f905a2371080..8dacdb96899e 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -5,6 +5,7 @@
#include <linux/memblock.h>
#include <linux/swapfile.h>
#include <linux/swapops.h>
+#include <linux/kmemleak.h>
#include <asm/set_memory.h>
#include <asm/e820/api.h>
@@ -766,6 +767,11 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end)
if (debug_pagealloc_enabled()) {
pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n",
begin, end - 1);
+ /*
+ * Inform kmemleak about the hole in the memory since the
+ * corresponding pages will be unmapped.
+ */
+ kmemleak_free_part((void *)begin, end - begin);
set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
} else {
/*
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 0029604af8a4..dd73d5d74393 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -825,7 +825,7 @@ void __init __early_set_fixmap(enum fixed_addresses idx,
pte = early_ioremap_pte(addr);
/* Sanitize 'prot' against any unsupported bits: */
- pgprot_val(flags) &= __default_kernel_pte_mask;
+ pgprot_val(flags) &= __supported_pte_mask;
if (pgprot_val(flags))
set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 3f452ffed7e9..d669c5e797e0 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -94,7 +94,7 @@ void __init kernel_randomize_memory(void)
if (!kaslr_memory_enabled())
return;
- kaslr_regions[0].size_tb = 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT);
+ kaslr_regions[0].size_tb = 1 << (MAX_PHYSMEM_BITS - TB_SHIFT);
kaslr_regions[1].size_tb = VMALLOC_SIZE_TB;
/*
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index bc4bc7b2f075..487b8474c01c 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -728,7 +728,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
{
int cpu;
- struct flush_tlb_info info __aligned(SMP_CACHE_BYTES) = {
+ struct flush_tlb_info info = {
.mm = mm,
.stride_shift = stride_shift,
.freed_tables = freed_tables,
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 6af49929de85..30084eaf8422 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -394,3 +394,7 @@
421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait
422 common futex_time64 sys_futex
423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register