summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt9
-rw-r--r--Documentation/x86/index.rst1
-rw-r--r--Documentation/x86/xstate.rst65
-rw-r--r--arch/Kconfig3
-rw-r--r--arch/x86/Kconfig17
-rw-r--r--arch/x86/events/perf_event.h1
-rw-r--r--arch/x86/ia32/ia32_signal.c15
-rw-r--r--arch/x86/include/asm/asm.h50
-rw-r--r--arch/x86/include/asm/cpufeatures.h2
-rw-r--r--arch/x86/include/asm/extable.h44
-rw-r--r--arch/x86/include/asm/extable_fixup_types.h22
-rw-r--r--arch/x86/include/asm/fpu/api.h58
-rw-r--r--arch/x86/include/asm/fpu/internal.h540
-rw-r--r--arch/x86/include/asm/fpu/sched.h68
-rw-r--r--arch/x86/include/asm/fpu/signal.h13
-rw-r--r--arch/x86/include/asm/fpu/types.h214
-rw-r--r--arch/x86/include/asm/fpu/xcr.h11
-rw-r--r--arch/x86/include/asm/fpu/xstate.h90
-rw-r--r--arch/x86/include/asm/kvm_host.h7
-rw-r--r--arch/x86/include/asm/msr-index.h2
-rw-r--r--arch/x86/include/asm/msr.h4
-rw-r--r--arch/x86/include/asm/pkru.h2
-rw-r--r--arch/x86/include/asm/processor.h9
-rw-r--r--arch/x86/include/asm/proto.h2
-rw-r--r--arch/x86/include/asm/segment.h2
-rw-r--r--arch/x86/include/asm/trace/fpu.h4
-rw-r--r--arch/x86/include/uapi/asm/prctl.h4
-rw-r--r--arch/x86/kernel/cpu/bugs.c2
-rw-r--r--arch/x86/kernel/cpu/common.c2
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c2
-rw-r--r--arch/x86/kernel/cpu/mce/core.c40
-rw-r--r--arch/x86/kernel/cpu/mce/internal.h14
-rw-r--r--arch/x86/kernel/cpu/mce/severity.c22
-rw-r--r--arch/x86/kernel/fpu/bugs.c2
-rw-r--r--arch/x86/kernel/fpu/context.h83
-rw-r--r--arch/x86/kernel/fpu/core.c392
-rw-r--r--arch/x86/kernel/fpu/init.c76
-rw-r--r--arch/x86/kernel/fpu/internal.h28
-rw-r--r--arch/x86/kernel/fpu/legacy.h115
-rw-r--r--arch/x86/kernel/fpu/regset.c36
-rw-r--r--arch/x86/kernel/fpu/signal.c285
-rw-r--r--arch/x86/kernel/fpu/xstate.c898
-rw-r--r--arch/x86/kernel/fpu/xstate.h278
-rw-r--r--arch/x86/kernel/process.c27
-rw-r--r--arch/x86/kernel/process_32.c5
-rw-r--r--arch/x86/kernel/process_64.c5
-rw-r--r--arch/x86/kernel/ptrace.c2
-rw-r--r--arch/x86/kernel/sev.c2
-rw-r--r--arch/x86/kernel/signal.c83
-rw-r--r--arch/x86/kernel/smpboot.c2
-rw-r--r--arch/x86/kernel/traps.c40
-rw-r--r--arch/x86/kvm/svm/sev.c2
-rw-r--r--arch/x86/kvm/svm/svm.c7
-rw-r--r--arch/x86/kvm/vmx/vmx.c2
-rw-r--r--arch/x86/kvm/x86.c258
-rw-r--r--arch/x86/lib/copy_mc_64.S8
-rw-r--r--arch/x86/math-emu/fpu_aux.c2
-rw-r--r--arch/x86/math-emu/fpu_entry.c6
-rw-r--r--arch/x86/math-emu/fpu_system.h2
-rw-r--r--arch/x86/mm/extable.c135
-rw-r--r--arch/x86/net/bpf_jit_comp.c11
-rw-r--r--arch/x86/power/cpu.c2
-rw-r--r--include/linux/signal.h6
-rw-r--r--kernel/signal.c35
-rw-r--r--scripts/sorttable.c4
-rw-r--r--tools/testing/selftests/x86/Makefile2
-rw-r--r--tools/testing/selftests/x86/amx.c851
67 files changed, 3458 insertions, 1575 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 43dc35fe5bc0..eb9a73ad91a0 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5497,6 +5497,15 @@
stifb= [HW]
Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]]
+ strict_sas_size=
+ [X86]
+ Format: <bool>
+ Enable or disable strict sigaltstack size checks
+ against the required signal frame size which
+ depends on the supported FPU features. This can
+ be used to filter out binaries which have
+ not yet been made aware of AT_MINSIGSTKSZ.
+
sunrpc.min_resvport=
sunrpc.max_resvport=
[NFS,SUNRPC]
diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst
index 383048396336..f498f1d36cd3 100644
--- a/Documentation/x86/index.rst
+++ b/Documentation/x86/index.rst
@@ -37,3 +37,4 @@ x86-specific Documentation
sgx
features
elf_auxvec
+ xstate
diff --git a/Documentation/x86/xstate.rst b/Documentation/x86/xstate.rst
new file mode 100644
index 000000000000..65de3f054ba5
--- /dev/null
+++ b/Documentation/x86/xstate.rst
@@ -0,0 +1,65 @@
+Using XSTATE features in user space applications
+================================================
+
+The x86 architecture supports floating-point extensions which are
+enumerated via CPUID. Applications consult CPUID and use XGETBV to
+evaluate which features have been enabled by the kernel XCR0.
+
+Up to AVX-512 and PKRU states, these features are automatically enabled by
+the kernel if available. Features like AMX TILE_DATA (XSTATE component 18)
+are enabled by XCR0 as well, but the first use of related instruction is
+trapped by the kernel because by default the required large XSTATE buffers
+are not allocated automatically.
+
+Using dynamically enabled XSTATE features in user space applications
+--------------------------------------------------------------------
+
+The kernel provides an arch_prctl(2) based mechanism for applications to
+request the usage of such features. The arch_prctl(2) options related to
+this are:
+
+-ARCH_GET_XCOMP_SUPP
+
+ arch_prctl(ARCH_GET_XCOMP_SUPP, &features);
+
+ ARCH_GET_XCOMP_SUPP stores the supported features in userspace storage of
+ type uint64_t. The second argument is a pointer to that storage.
+
+-ARCH_GET_XCOMP_PERM
+
+ arch_prctl(ARCH_GET_XCOMP_PERM, &features);
+
+ ARCH_GET_XCOMP_PERM stores the features for which the userspace process
+ has permission in userspace storage of type uint64_t. The second argument
+ is a pointer to that storage.
+
+-ARCH_REQ_XCOMP_PERM
+
+ arch_prctl(ARCH_REQ_XCOMP_PERM, feature_nr);
+
+ ARCH_REQ_XCOMP_PERM allows to request permission for a dynamically enabled
+ feature or a feature set. A feature set can be mapped to a facility, e.g.
+ AMX, and can require one or more XSTATE components to be enabled.
+
+ The feature argument is the number of the highest XSTATE component which
+ is required for a facility to work.
+
+When requesting permission for a feature, the kernel checks the
+availability. The kernel ensures that sigaltstacks in the process's tasks
+are large enough to accommodate the resulting large signal frame. It
+enforces this both during ARCH_REQ_XCOMP_SUPP and during any subsequent
+sigaltstack(2) calls. If an installed sigaltstack is smaller than the
+resulting sigframe size, ARCH_REQ_XCOMP_SUPP results in -ENOSUPP. Also,
+sigaltstack(2) results in -ENOMEM if the requested altstack is too small
+for the permitted features.
+
+Permission, when granted, is valid per process. Permissions are inherited
+on fork(2) and cleared on exec(3).
+
+The first use of an instruction related to a dynamically enabled feature is
+trapped by the kernel. The trap handler checks whether the process has
+permission to use the feature. If the process has no permission then the
+kernel sends SIGILL to the application. If the process has permission then
+the handler allocates a larger xstate buffer for the task so the large
+state can be context switched. In the unlikely cases that the allocation
+fails, the kernel sends SIGSEGV.
diff --git a/arch/Kconfig b/arch/Kconfig
index 8df1c7102643..af5cf3009b4f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1288,6 +1288,9 @@ config ARCH_HAS_ELFCORE_COMPAT
config ARCH_HAS_PARANOID_L1D_FLUSH
bool
+config DYNAMIC_SIGFRAME
+ bool
+
source "kernel/gcov/Kconfig"
source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cdaeccc9127d..244d3a429dbb 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -125,6 +125,7 @@ config X86
select CLOCKSOURCE_VALIDATE_LAST_CYCLE
select CLOCKSOURCE_WATCHDOG
select DCACHE_WORD_ACCESS
+ select DYNAMIC_SIGFRAME
select EDAC_ATOMIC_SCRUB
select EDAC_SUPPORT
select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
@@ -2399,6 +2400,22 @@ config MODIFY_LDT_SYSCALL
Saying 'N' here may make sense for embedded or server kernels.
+config STRICT_SIGALTSTACK_SIZE
+ bool "Enforce strict size checking for sigaltstack"
+ depends on DYNAMIC_SIGFRAME
+ help
+ For historical reasons MINSIGSTKSZ is a constant which became
+ already too small with AVX512 support. Add a mechanism to
+ enforce strict checking of the sigaltstack size against the
+ real size of the FPU frame. This option enables the check
+ by default. It can also be controlled via the kernel command
+ line option 'strict_sas_size' independent of this config
+ switch. Enabling it might break existing applications which
+ allocate a too small sigaltstack but 'work' because they
+ never get a signal delivered.
+
+ Say 'N' unless you want to really enforce this check.
+
source "kernel/livepatch/Kconfig"
endmenu
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 76436a55d9ba..7b5167db3e78 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -14,6 +14,7 @@
#include <linux/perf_event.h>
+#include <asm/fpu/xstate.h>
#include <asm/intel_ds.h>
#include <asm/cpu.h>
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 5e3d9b7fd5fb..c9c3859322fa 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -24,7 +24,6 @@
#include <linux/syscalls.h>
#include <asm/ucontext.h>
#include <linux/uaccess.h>
-#include <asm/fpu/internal.h>
#include <asm/fpu/signal.h>
#include <asm/ptrace.h>
#include <asm/ia32_unistd.h>
@@ -57,8 +56,8 @@ static inline void reload_segments(struct sigcontext_32 *sc)
/*
* Do a signal return; undo the signal stack.
*/
-static int ia32_restore_sigcontext(struct pt_regs *regs,
- struct sigcontext_32 __user *usc)
+static bool ia32_restore_sigcontext(struct pt_regs *regs,
+ struct sigcontext_32 __user *usc)
{
struct sigcontext_32 sc;
@@ -66,7 +65,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
current->restart_block.fn = do_no_restart_syscall;
if (unlikely(copy_from_user(&sc, usc, sizeof(sc))))
- return -EFAULT;
+ return false;
/* Get only the ia32 registers. */
regs->bx = sc.bx;
@@ -111,7 +110,7 @@ COMPAT_SYSCALL_DEFINE0(sigreturn)
set_current_blocked(&set);
- if (ia32_restore_sigcontext(regs, &frame->sc))
+ if (!ia32_restore_sigcontext(regs, &frame->sc))
goto badframe;
return regs->ax;
@@ -135,7 +134,7 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
set_current_blocked(&set);
- if (ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext))
+ if (!ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext))
goto badframe;
if (compat_restore_altstack(&frame->uc.uc_stack))
@@ -220,8 +219,8 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size);
*fpstate = (struct _fpstate_32 __user *) sp;
- if (copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned,
- math_size) < 0)
+ if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned,
+ math_size))
return (void __user *) -1L;
sp -= frame_size;
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 3ad3da9a7d97..6aadb9a620ee 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -122,28 +122,19 @@
#ifdef __KERNEL__
+# include <asm/extable_fixup_types.h>
+
/* Exception table entry */
#ifdef __ASSEMBLY__
-# define _ASM_EXTABLE_HANDLE(from, to, handler) \
+
+# define _ASM_EXTABLE_TYPE(from, to, type) \
.pushsection "__ex_table","a" ; \
.balign 4 ; \
.long (from) - . ; \
.long (to) - . ; \
- .long (handler) - . ; \
+ .long type ; \
.popsection
-# define _ASM_EXTABLE(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
-
-# define _ASM_EXTABLE_UA(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess)
-
-# define _ASM_EXTABLE_CPY(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_copy)
-
-# define _ASM_EXTABLE_FAULT(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
-
# ifdef CONFIG_KPROBES
# define _ASM_NOKPROBE(entry) \
.pushsection "_kprobe_blacklist","aw" ; \
@@ -155,27 +146,15 @@
# endif
#else /* ! __ASSEMBLY__ */
-# define _EXPAND_EXTABLE_HANDLE(x) #x
-# define _ASM_EXTABLE_HANDLE(from, to, handler) \
+
+# define _ASM_EXTABLE_TYPE(from, to, type) \
" .pushsection \"__ex_table\",\"a\"\n" \
" .balign 4\n" \
" .long (" #from ") - .\n" \
" .long (" #to ") - .\n" \
- " .long (" _EXPAND_EXTABLE_HANDLE(handler) ") - .\n" \
+ " .long " __stringify(type) " \n" \
" .popsection\n"
-# define _ASM_EXTABLE(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
-
-# define _ASM_EXTABLE_UA(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess)
-
-# define _ASM_EXTABLE_CPY(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_copy)
-
-# define _ASM_EXTABLE_FAULT(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
-
/* For C file, we already have NOKPROBE_SYMBOL macro */
/*
@@ -188,6 +167,17 @@ register unsigned long current_stack_pointer asm(_ASM_SP);
#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
+#define _ASM_EXTABLE(from, to) \
+ _ASM_EXTABLE_TYPE(from, to, EX_TYPE_DEFAULT)
+#define _ASM_EXTABLE_UA(from, to) \
+ _ASM_EXTABLE_TYPE(from, to, EX_TYPE_UACCESS)
+
+#define _ASM_EXTABLE_CPY(from, to) \
+ _ASM_EXTABLE_TYPE(from, to, EX_TYPE_COPY)
+
+#define _ASM_EXTABLE_FAULT(from, to) \
+ _ASM_EXTABLE_TYPE(from, to, EX_TYPE_FAULT)
+
+#endif /* __KERNEL__ */
#endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index d0ce5cfd3ac1..d5b5f2ab87a0 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -277,6 +277,7 @@
#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC instruction */
#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */
#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */
+#define X86_FEATURE_XFD (10*32+ 4) /* "" eXtended Feature Disabling */
/*
* Extended auxiliary flags: Linux defined - for features scattered in various
@@ -298,6 +299,7 @@
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */
#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
+#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h
index 1f0cbc52937c..93f400eb728f 100644
--- a/arch/x86/include/asm/extable.h
+++ b/arch/x86/include/asm/extable.h
@@ -1,12 +1,18 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_X86_EXTABLE_H
#define _ASM_X86_EXTABLE_H
+
+#include <asm/extable_fixup_types.h>
+
/*
- * The exception table consists of triples of addresses relative to the
- * exception table entry itself. The first address is of an instruction
- * that is allowed to fault, the second is the target at which the program
- * should continue. The third is a handler function to deal with the fault
- * caused by the instruction in the first field.
+ * The exception table consists of two addresses relative to the
+ * exception table entry itself and a type selector field.
+ *
+ * The first address is of an instruction that is allowed to fault, the
+ * second is the target at which the program should continue.
+ *
+ * The type entry is used by fixup_exception() to select the handler to
+ * deal with the fault caused by the instruction in the first field.
*
* All the routines below use bits of fixup code that are out of line
* with the main instruction path. This means when everything is well,
@@ -15,7 +21,7 @@
*/
struct exception_table_entry {
- int insn, fixup, handler;
+ int insn, fixup, type;
};
struct pt_regs;
@@ -25,21 +31,27 @@ struct pt_regs;
do { \
(a)->fixup = (b)->fixup + (delta); \
(b)->fixup = (tmp).fixup - (delta); \
- (a)->handler = (b)->handler + (delta); \
- (b)->handler = (tmp).handler - (delta); \
+ (a)->type = (b)->type; \
+ (b)->type = (tmp).type; \
} while (0)
-enum handler_type {
- EX_HANDLER_NONE,
- EX_HANDLER_FAULT,
- EX_HANDLER_UACCESS,
- EX_HANDLER_OTHER
-};
-
extern int fixup_exception(struct pt_regs *regs, int trapnr,
unsigned long error_code, unsigned long fault_addr);
extern int fixup_bug(struct pt_regs *regs, int trapnr);
-extern enum handler_type ex_get_fault_handler_type(unsigned long ip);
+extern int ex_get_fixup_type(unsigned long ip);
extern void early_fixup_exception(struct pt_regs *regs, int trapnr);
+#ifdef CONFIG_X86_MCE
+extern void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr);
+#else
+static inline void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr) { }
+#endif
+
+#if defined(CONFIG_BPF_JIT) && defined(CONFIG_X86_64)
+bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs);
+#else
+static inline bool ex_handler_bpf(const struct exception_table_entry *x,
+ struct pt_regs *regs) { return false; }
+#endif
+
#endif
diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h
new file mode 100644
index 000000000000..409524d5d2eb
--- /dev/null
+++ b/arch/x86/include/asm/extable_fixup_types.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_EXTABLE_FIXUP_TYPES_H
+#define _ASM_X86_EXTABLE_FIXUP_TYPES_H
+
+#define EX_TYPE_NONE 0
+#define EX_TYPE_DEFAULT 1
+#define EX_TYPE_FAULT 2
+#define EX_TYPE_UACCESS 3
+#define EX_TYPE_COPY 4
+#define EX_TYPE_CLEAR_FS 5
+#define EX_TYPE_FPU_RESTORE 6
+#define EX_TYPE_WRMSR 7
+#define EX_TYPE_RDMSR 8
+#define EX_TYPE_BPF 9
+
+#define EX_TYPE_WRMSR_IN_MCE 10
+#define EX_TYPE_RDMSR_IN_MCE 11
+
+#define EX_TYPE_DEFAULT_MCE_SAFE 12
+#define EX_TYPE_FAULT_MCE_SAFE 13
+
+#endif
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 23bef08a8388..b7267b9e452f 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -12,6 +12,8 @@
#define _ASM_X86_FPU_API_H
#include <linux/bottom_half.h>
+#include <asm/fpu/types.h>
+
/*
* Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It
* disables preemption so be careful if you intend to use it for long periods
@@ -48,9 +50,9 @@ static inline void kernel_fpu_begin(void)
}
/*
- * Use fpregs_lock() while editing CPU's FPU registers or fpu->state.
+ * Use fpregs_lock() while editing CPU's FPU registers or fpu->fpstate.
* A context switch will (and softirq might) save CPU's FPU registers to
- * fpu->state and set TIF_NEED_FPU_LOAD leaving CPU's FPU registers in
+ * fpu->fpstate.regs and set TIF_NEED_FPU_LOAD leaving CPU's FPU registers in
* a random state.
*
* local_bh_disable() protects against both preemption and soft interrupts
@@ -108,4 +110,56 @@ extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name);
static inline void update_pasid(void) { }
+/* Trap handling */
+extern int fpu__exception_code(struct fpu *fpu, int trap_nr);
+extern void fpu_sync_fpstate(struct fpu *fpu);
+extern void fpu_reset_from_exception_fixup(void);
+
+/* Boot, hotplug and resume */
+extern void fpu__init_cpu(void);
+extern void fpu__init_system(struct cpuinfo_x86 *c);
+extern void fpu__init_check_bugs(void);
+extern void fpu__resume_cpu(void);
+
+#ifdef CONFIG_MATH_EMULATION
+extern void fpstate_init_soft(struct swregs_state *soft);
+#else
+static inline void fpstate_init_soft(struct swregs_state *soft) {}
+#endif
+
+/* State tracking */
+DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+
+/* Process cleanup */
+#ifdef CONFIG_X86_64
+extern void fpstate_free(struct fpu *fpu);
+#else
+static inline void fpstate_free(struct fpu *fpu) { }
+#endif
+
+/* fpstate-related functions which are exported to KVM */
+extern void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature);
+
+/* KVM specific functions */
+extern bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu);
+extern void fpu_free_guest_fpstate(struct fpu_guest *gfpu);
+extern int fpu_swap_kvm_fpstate(struct fpu_guest *gfpu, bool enter_guest);
+
+extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u32 pkru);
+extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru);
+
+static inline void fpstate_set_confidential(struct fpu_guest *gfpu)
+{
+ gfpu->fpstate->is_confidential = true;
+}
+
+static inline bool fpstate_is_confidential(struct fpu_guest *gfpu)
+{
+ return gfpu->fpstate->is_confidential;
+}
+
+/* prctl */
+struct task_struct;
+extern long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2);
+
#endif /* _ASM_X86_FPU_API_H */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 5a18694a89b2..e69de29bb2d1 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -1,540 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- * Gareth Hughes <gareth@valinux.com>, May 2000
- * x86-64 work by Andi Kleen 2002
- */
-
-#ifndef _ASM_X86_FPU_INTERNAL_H
-#define _ASM_X86_FPU_INTERNAL_H
-
-#include <linux/compat.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/mm.h>
-
-#include <asm/user.h>
-#include <asm/fpu/api.h>
-#include <asm/fpu/xstate.h>
-#include <asm/fpu/xcr.h>
-#include <asm/cpufeature.h>
-#include <asm/trace/fpu.h>
-
-/*
- * High level FPU state handling functions:
- */
-extern int fpu__restore_sig(void __user *buf, int ia32_frame);
-extern void fpu__drop(struct fpu *fpu);
-extern void fpu__clear_user_states(struct fpu *fpu);
-extern int fpu__exception_code(struct fpu *fpu, int trap_nr);
-
-extern void fpu_sync_fpstate(struct fpu *fpu);
-
-/* Clone and exit operations */
-extern int fpu_clone(struct task_struct *dst);
-extern void fpu_flush_thread(void);
-
-/*
- * Boot time FPU initialization functions:
- */
-extern void fpu__init_cpu(void);
-extern void fpu__init_system_xstate(void);
-extern void fpu__init_cpu_xstate(void);
-extern void fpu__init_system(struct cpuinfo_x86 *c);
-extern void fpu__init_check_bugs(void);
-extern void fpu__resume_cpu(void);
-
-/*
- * Debugging facility:
- */
-#ifdef CONFIG_X86_DEBUG_FPU
-# define WARN_ON_FPU(x) WARN_ON_ONCE(x)
-#else
-# define WARN_ON_FPU(x) ({ (void)(x); 0; })
-#endif
-
-/*
- * FPU related CPU feature flag helper routines:
- */
-static __always_inline __pure bool use_xsaveopt(void)
-{
- return static_cpu_has(X86_FEATURE_XSAVEOPT);
-}
-
-static __always_inline __pure bool use_xsave(void)
-{
- return static_cpu_has(X86_FEATURE_XSAVE);
-}
-
-static __always_inline __pure bool use_fxsr(void)
-{
- return static_cpu_has(X86_FEATURE_FXSR);
-}
-
-/*
- * fpstate handling functions:
- */
-
-extern union fpregs_state init_fpstate;
-
-extern void fpstate_init(union fpregs_state *state);
-#ifdef CONFIG_MATH_EMULATION
-extern void fpstate_init_soft(struct swregs_state *soft);
-#else
-static inline void fpstate_init_soft(struct swregs_state *soft) {}
-#endif
-extern void save_fpregs_to_fpstate(struct fpu *fpu);
-
-/* Returns 0 or the negated trap number, which results in -EFAULT for #PF */
-#define user_insn(insn, output, input...) \
-({ \
- int err; \
- \
- might_fault(); \
- \
- asm volatile(ASM_STAC "\n" \
- "1: " #insn "\n" \
- "2: " ASM_CLAC "\n" \
- ".section .fixup,\"ax\"\n" \
- "3: negl %%eax\n" \
- " jmp 2b\n" \
- ".previous\n" \
- _ASM_EXTABLE_FAULT(1b, 3b) \
- : [err] "=a" (err), output \
- : "0"(0), input); \
- err; \
-})
-
-#define kernel_insn_err(insn, output, input...) \
-({ \
- int err; \
- asm volatile("1:" #insn "\n\t" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: movl $-1,%[err]\n" \
- " jmp 2b\n" \
- ".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
- : [err] "=r" (err), output \
- : "0"(0), input); \
- err; \
-})
-
-#define kernel_insn(insn, output, input...) \
- asm volatile("1:" #insn "\n\t" \
- "2:\n" \
- _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore) \
- : output : input)
-
-static inline int fnsave_to_user_sigframe(struct fregs_state __user *fx)
-{
- return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx));
-}
-
-static inline int fxsave_to_user_sigframe(struct fxregs_state __user *fx)
-{
- if (IS_ENABLED(CONFIG_X86_32))
- return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
- else
- return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
-
-}
-
-static inline void fxrstor(struct fxregs_state *fx)
-{
- if (IS_ENABLED(CONFIG_X86_32))
- kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
- else
- kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline int fxrstor_safe(struct fxregs_state *fx)
-{
- if (IS_ENABLED(CONFIG_X86_32))
- return kernel_insn_err(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
- else
- return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline int fxrstor_from_user_sigframe(struct fxregs_state __user *fx)
-{
- if (IS_ENABLED(CONFIG_X86_32))
- return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
- else
- return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline void frstor(struct fregs_state *fx)
-{
- kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline int frstor_safe(struct fregs_state *fx)
-{
- return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline int frstor_from_user_sigframe(struct fregs_state __user *fx)
-{
- return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline void fxsave(struct fxregs_state *fx)
-{
- if (IS_ENABLED(CONFIG_X86_32))
- asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx));
- else
- asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx));
-}
-
-/* These macros all use (%edi)/(%rdi) as the single memory argument. */
-#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27"
-#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37"
-#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f"
-#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f"
-#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f"
-
-/*
- * After this @err contains 0 on success or the negated trap number when
- * the operation raises an exception. For faults this results in -EFAULT.
- */
-#define XSTATE_OP(op, st, lmask, hmask, err) \
- asm volatile("1:" op "\n\t" \
- "xor %[err], %[err]\n" \
- "2:\n\t" \
- ".pushsection .fixup,\"ax\"\n\t" \
- "3: negl %%eax\n\t" \
- "jmp 2b\n\t" \
- ".popsection\n\t" \
- _ASM_EXTABLE_FAULT(1b, 3b) \
- : [err] "=a" (err) \
- : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
- : "memory")
-
-/*
- * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact
- * format and supervisor states in addition to modified optimization in
- * XSAVEOPT.
- *
- * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT
- * supports modified optimization which is not supported by XSAVE.
- *
- * We use XSAVE as a fallback.
- *
- * The 661 label is defined in the ALTERNATIVE* macros as the address of the
- * original instruction which gets replaced. We need to use it here as the
- * address of the instruction where we might get an exception at.
- */
-#define XSTATE_XSAVE(st, lmask, hmask, err) \
- asm volatile(ALTERNATIVE_2(XSAVE, \
- XSAVEOPT, X86_FEATURE_XSAVEOPT, \
- XSAVES, X86_FEATURE_XSAVES) \
- "\n" \
- "xor %[err], %[err]\n" \
- "3:\n" \
- ".pushsection .fixup,\"ax\"\n" \
- "4: movl $-2, %[err]\n" \
- "jmp 3b\n" \
- ".popsection\n" \
- _ASM_EXTABLE(661b, 4b) \
- : [err] "=r" (err) \
- : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
- : "memory")
-
-/*
- * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact
- * XSAVE area format.
- */
-#define XSTATE_XRESTORE(st, lmask, hmask) \
- asm volatile(ALTERNATIVE(XRSTOR, \
- XRSTORS, X86_FEATURE_XSAVES) \
- "\n" \
- "3:\n" \
- _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\
- : \
- : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
- : "memory")
-
-/*
- * This function is called only during boot time when x86 caps are not set
- * up and alternative can not be used yet.
- */
-static inline void os_xrstor_booting(struct xregs_state *xstate)
-{
- u64 mask = xfeatures_mask_fpstate();
- u32 lmask = mask;
- u32 hmask = mask >> 32;
- int err;
-
- WARN_ON(system_state != SYSTEM_BOOTING);
-
- if (boot_cpu_has(X86_FEATURE_XSAVES))
- XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
- else
- XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
-
- /*
- * We should never fault when copying from a kernel buffer, and the FPU
- * state we set at boot time should be valid.
- */
- WARN_ON_FPU(err);
-}
-
-/*
- * Save processor xstate to xsave area.
- *
- * Uses either XSAVE or XSAVEOPT or XSAVES depending on the CPU features
- * and command line options. The choice is permanent until the next reboot.
- */
-static inline void os_xsave(struct xregs_state *xstate)
-{
- u64 mask = xfeatures_mask_all;
- u32 lmask = mask;
- u32 hmask = mask >> 32;
- int err;
-
- WARN_ON_FPU(!alternatives_patched);
-
- XSTATE_XSAVE(xstate, lmask, hmask, err);
-
- /* We should never fault when copying to a kernel buffer: */
- WARN_ON_FPU(err);
-}
-
-/*
- * Restore processor xstate from xsave area.
- *
- * Uses XRSTORS when XSAVES is used, XRSTOR otherwise.
- */
-static inline void os_xrstor(struct xregs_state *xstate, u64 mask)
-{
- u32 lmask = mask;
- u32 hmask = mask >> 32;
-
- XSTATE_XRESTORE(xstate, lmask, hmask);
-}
-
-/*
- * Save xstate to user space xsave area.
- *
- * We don't use modified optimization because xrstor/xrstors might track
- * a different application.
- *
- * We don't use compacted format xsave area for
- * backward compatibility for old applications which don't understand
- * compacted format of xsave area.
- */
-static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
-{
- /*
- * Include the features which are not xsaved/rstored by the kernel
- * internally, e.g. PKRU. That's user space ABI and also required
- * to allow the signal handler to modify PKRU.
- */
- u64 mask = xfeatures_mask_uabi();
- u32 lmask = mask;
- u32 hmask = mask >> 32;
- int err;
-
- /*
- * Clear the xsave header first, so that reserved fields are
- * initialized to zero.
- */
- err = __clear_user(&buf->header, sizeof(buf->header));
- if (unlikely(err))
- return -EFAULT;
-
- stac();
- XSTATE_OP(XSAVE, buf, lmask, hmask, err);
- clac();
-
- return err;
-}
-
-/*
- * Restore xstate from user space xsave area.
- */
-static inline int xrstor_from_user_sigframe(struct xregs_state __user *buf, u64 mask)
-{
- struct xregs_state *xstate = ((__force struct xregs_state *)buf);
- u32 lmask = mask;
- u32 hmask = mask >> 32;
- int err;
-
- stac();
- XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
- clac();
-
- return err;
-}
-
-/*
- * Restore xstate from kernel space xsave area, return an error code instead of
- * an exception.
- */
-static inline int os_xrstor_safe(struct xregs_state *xstate, u64 mask)
-{
- u32 lmask = mask;
- u32 hmask = mask >> 32;
- int err;
-
- if (cpu_feature_enabled(X86_FEATURE_XSAVES))
- XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
- else
- XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
-
- return err;
-}
-
-extern void __restore_fpregs_from_fpstate(union fpregs_state *fpstate, u64 mask);
-
-static inline void restore_fpregs_from_fpstate(union fpregs_state *fpstate)
-{
- __restore_fpregs_from_fpstate(fpstate, xfeatures_mask_fpstate());
-}
-
-extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);
-
-/*
- * FPU context switch related helper methods:
- */
-
-DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
-
-/*
- * The in-register FPU state for an FPU context on a CPU is assumed to be
- * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx
- * matches the FPU.
- *
- * If the FPU register state is valid, the kernel can skip restoring the
- * FPU state from memory.
- *
- * Any code that clobbers the FPU registers or updates the in-memory
- * FPU state for a task MUST let the rest of the kernel know that the
- * FPU registers are no longer valid for this task.
- *
- * Either one of these invalidation functions is enough. Invalidate
- * a resource you control: CPU if using the CPU for something else
- * (with preemption disabled), FPU for the current task, or a task that
- * is prevented from running by the current task.
- */
-static inline void __cpu_invalidate_fpregs_state(void)
-{
- __this_cpu_write(fpu_fpregs_owner_ctx, NULL);
-}
-
-static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu)
-{
- fpu->last_cpu = -1;
-}
-
-static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu)
-{
- return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
-}
-
-/*
- * These generally need preemption protection to work,
- * do try to avoid using these on their own:
- */
-static inline void fpregs_deactivate(struct fpu *fpu)
-{
- this_cpu_write(fpu_fpregs_owner_ctx, NULL);
- trace_x86_fpu_regs_deactivated(fpu);
-}
-
-static inline void fpregs_activate(struct fpu *fpu)
-{
- this_cpu_write(fpu_fpregs_owner_ctx, fpu);
- trace_x86_fpu_regs_activated(fpu);
-}
-
-/* Internal helper for switch_fpu_return() and signal frame setup */
-static inline void fpregs_restore_userregs(void)
-{
- struct fpu *fpu = &current->thread.fpu;
- int cpu = smp_processor_id();
-
- if (WARN_ON_ONCE(current->flags & PF_KTHREAD))
- return;
-
- if (!fpregs_state_valid(fpu, cpu)) {
- u64 mask;
-
- /*
- * This restores _all_ xstate which has not been
- * established yet.
- *
- * If PKRU is enabled, then the PKRU value is already
- * correct because it was either set in switch_to() or in
- * flush_thread(). So it is excluded because it might be
- * not up to date in current->thread.fpu.xsave state.
- */
- mask = xfeatures_mask_restore_user() |
- xfeatures_mask_supervisor();
- __restore_fpregs_from_fpstate(&fpu->state, mask);
-
- fpregs_activate(fpu);
- fpu->last_cpu = cpu;
- }
- clear_thread_flag(TIF_NEED_FPU_LOAD);
-}
-
-/*
- * FPU state switching for scheduling.
- *
- * This is a two-stage process:
- *
- * - switch_fpu_prepare() saves the old state.
- * This is done within the context of the old process.
- *
- * - switch_fpu_finish() sets TIF_NEED_FPU_LOAD; the floating point state
- * will get loaded on return to userspace, or when the kernel needs it.
- *
- * If TIF_NEED_FPU_LOAD is cleared then the CPU's FPU registers
- * are saved in the current thread's FPU register state.
- *
- * If TIF_NEED_FPU_LOAD is set then CPU's FPU registers may not
- * hold current()'s FPU registers. It is required to load the
- * registers before returning to userland or using the content
- * otherwise.
- *
- * The FPU context is only stored/restored for a user task and
- * PF_KTHREAD is used to distinguish between kernel and user threads.
- */
-static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
-{
- if (static_cpu_has(X86_FEATURE_FPU) && !(current->flags & PF_KTHREAD)) {
- save_fpregs_to_fpstate(old_fpu);
- /*
- * The save operation preserved register state, so the
- * fpu_fpregs_owner_ctx is still @old_fpu. Store the
- * current CPU number in @old_fpu, so the next return
- * to user space can avoid the FPU register restore
- * when is returns on the same CPU and still owns the
- * context.
- */
- old_fpu->last_cpu = cpu;
-
- trace_x86_fpu_regs_deactivated(old_fpu);
- }
-}
-
-/*
- * Misc helper functions:
- */
-
-/*
- * Delay loading of the complete FPU state until the return to userland.
- * PKRU is handled separately.
- */
-static inline void switch_fpu_finish(struct fpu *new_fpu)
-{
- if (cpu_feature_enabled(X86_FEATURE_FPU))
- set_thread_flag(TIF_NEED_FPU_LOAD);
-}
-
-#endif /* _ASM_X86_FPU_INTERNAL_H */
diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h
new file mode 100644
index 000000000000..99a8820e8cc4
--- /dev/null
+++ b/arch/x86/include/asm/fpu/sched.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_FPU_SCHED_H
+#define _ASM_X86_FPU_SCHED_H
+
+#include <linux/sched.h>
+
+#include <asm/cpufeature.h>
+#include <asm/fpu/types.h>
+
+#include <asm/trace/fpu.h>
+
+extern void save_fpregs_to_fpstate(struct fpu *fpu);
+extern void fpu__drop(struct fpu *fpu);
+extern int fpu_clone(struct task_struct *dst, unsigned long clone_flags);
+extern void fpu_flush_thread(void);
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ * - switch_fpu_prepare() saves the old state.
+ * This is done within the context of the old process.
+ *
+ * - switch_fpu_finish() sets TIF_NEED_FPU_LOAD; the floating point state
+ * will get loaded on return to userspace, or when the kernel needs it.
+ *
+ * If TIF_NEED_FPU_LOAD is cleared then the CPU's FPU registers
+ * are saved in the current thread's FPU register state.
+ *
+ * If TIF_NEED_FPU_LOAD is set then CPU's FPU registers may not
+ * hold current()'s FPU registers. It is required to load the
+ * registers before returning to userland or using the content
+ * otherwise.
+ *
+ * The FPU context is only stored/restored for a user task and
+ * PF_KTHREAD is used to distinguish between kernel and user threads.
+ */
+static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
+{
+ if (cpu_feature_enabled(X86_FEATURE_FPU) &&
+ !(current->flags & PF_KTHREAD)) {
+ save_fpregs_to_fpstate(old_fpu);
+ /*
+ * The save operation preserved register state, so the
+ * fpu_fpregs_owner_ctx is still @old_fpu. Store the
+ * current CPU number in @old_fpu, so the next return
+ * to user space can avoid the FPU register restore
+ * when is returns on the same CPU and still owns the
+ * context.
+ */
+ old_fpu->last_cpu = cpu;
+
+ trace_x86_fpu_regs_deactivated(old_fpu);
+ }
+}
+
+/*
+ * Delay loading of the complete FPU state until the return to userland.
+ * PKRU is handled separately.
+ */
+static inline void switch_fpu_finish(void)
+{
+ if (cpu_feature_enabled(X86_FEATURE_FPU))
+ set_thread_flag(TIF_NEED_FPU_LOAD);
+}
+
+#endif /* _ASM_X86_FPU_SCHED_H */
diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h
index 8b6631dffefd..22b0273a8bf1 100644
--- a/arch/x86/include/asm/fpu/signal.h
+++ b/arch/x86/include/asm/fpu/signal.h
@@ -5,6 +5,11 @@
#ifndef _ASM_X86_FPU_SIGNAL_H
#define _ASM_X86_FPU_SIGNAL_H
+#include <linux/compat.h>
+#include <linux/user.h>
+
+#include <asm/fpu/types.h>
+
#ifdef CONFIG_X86_64
# include <uapi/asm/sigcontext.h>
# include <asm/user32.h>
@@ -31,6 +36,12 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
unsigned long fpu__get_fpstate_size(void);
-extern void fpu__init_prepare_fx_sw_frame(void);
+extern bool copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);
+extern void fpu__clear_user_states(struct fpu *fpu);
+extern bool fpu__restore_sig(void __user *buf, int ia32_frame);
+
+extern void restore_fpregs_from_fpstate(struct fpstate *fpstate, u64 mask);
+
+extern bool copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);
#endif /* _ASM_X86_FPU_SIGNAL_H */
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index f5a38a5f3ae1..3c06c82ab355 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -120,6 +120,9 @@ enum xfeature {
XFEATURE_RSRVD_COMP_13,
XFEATURE_RSRVD_COMP_14,
XFEATURE_LBR,
+ XFEATURE_RSRVD_COMP_16,
+ XFEATURE_XTILE_CFG,
+ XFEATURE_XTILE_DATA,
XFEATURE_MAX,
};
@@ -136,12 +139,21 @@ enum xfeature {
#define XFEATURE_MASK_PKRU (1 << XFEATURE_PKRU)
#define XFEATURE_MASK_PASID (1 << XFEATURE_PASID)
#define XFEATURE_MASK_LBR (1 << XFEATURE_LBR)
+#define XFEATURE_MASK_XTILE_CFG (1 << XFEATURE_XTILE_CFG)
+#define XFEATURE_MASK_XTILE_DATA (1 << XFEATURE_XTILE_DATA)
#define XFEATURE_MASK_FPSSE (XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
#define XFEATURE_MASK_AVX512 (XFEATURE_MASK_OPMASK \
| XFEATURE_MASK_ZMM_Hi256 \
| XFEATURE_MASK_Hi16_ZMM)
+#ifdef CONFIG_X86_64
+# define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILE_DATA \
+ | XFEATURE_MASK_XTILE_CFG)
+#else
+# define XFEATURE_MASK_XTILE (0)
+#endif
+
#define FIRST_EXTENDED_XFEATURE XFEATURE_YMM
struct reg_128_bit {
@@ -153,6 +165,9 @@ struct reg_256_bit {
struct reg_512_bit {
u8 regbytes[512/8];
};
+struct reg_1024_byte {
+ u8 regbytes[1024];
+};
/*
* State component 2:
@@ -255,6 +270,23 @@ struct arch_lbr_state {
u64 ler_to;
u64 ler_info;
struct lbr_entry entries[];
+};
+
+/*
+ * State component 17: 64-byte tile configuration register.
+ */
+struct xtile_cfg {
+ u64 tcfg[8];
+} __packed;
+
+/*
+ * State component 18: 1KB tile data register.
+ * Each register represents 16 64-byte rows of the matrix
+ * data. But the number of registers depends on the actual
+ * implementation.
+ */
+struct xtile_data {
+ struct reg_1024_byte tmm;
} __packed;
/*
@@ -309,6 +341,91 @@ union fpregs_state {
u8 __padding[PAGE_SIZE];
};
+struct fpstate {
+ /* @kernel_size: The size of the kernel register image */
+ unsigned int size;
+
+ /* @user_size: The size in non-compacted UABI format */
+ unsigned int user_size;
+
+ /* @xfeatures: xfeatures for which the storage is sized */
+ u64 xfeatures;
+
+ /* @user_xfeatures: xfeatures valid in UABI buffers */
+ u64 user_xfeatures;
+
+ /* @xfd: xfeatures disabled to trap userspace use. */
+ u64 xfd;
+
+ /* @is_valloc: Indicator for dynamically allocated state */
+ unsigned int is_valloc : 1;
+
+ /* @is_guest: Indicator for guest state (KVM) */
+ unsigned int is_guest : 1;
+
+ /*
+ * @is_confidential: Indicator for KVM confidential mode.
+ * The FPU registers are restored by the
+ * vmentry firmware from encrypted guest
+ * memory. On vmexit the FPU registers are
+ * saved by firmware to encrypted guest memory
+ * and the registers are scrubbed before
+ * returning to the host. So there is no
+ * content which is worth saving and restoring.
+ * The fpstate has to be there so that
+ * preemption and softirq FPU usage works
+ * without special casing.
+ */
+ unsigned int is_confidential : 1;
+
+ /* @in_use: State is in use */
+ unsigned int in_use : 1;
+
+ /* @regs: The register state union for all supported formats */
+ union fpregs_state regs;
+
+ /* @regs is dynamically sized! Don't add anything after @regs! */
+} __aligned(64);
+
+struct fpu_state_perm {
+ /*
+ * @__state_perm:
+ *
+ * This bitmap indicates the permission for state components, which
+ * are available to a thread group. The permission prctl() sets the
+ * enabled state bits in thread_group_leader()->thread.fpu.
+ *
+ * All run time operations use the per thread information in the
+ * currently active fpu.fpstate which contains the xfeature masks
+ * and sizes for kernel and user space.
+ *
+ * This master permission field is only to be used when
+ * task.fpu.fpstate based checks fail to validate whether the task
+ * is allowed to expand it's xfeatures set which requires to
+ * allocate a larger sized fpstate buffer.
+ *
+ * Do not access this field directly. Use the provided helper
+ * function. Unlocked access is possible for quick checks.
+ */
+ u64 __state_perm;
+
+ /*
+ * @__state_size:
+ *
+ * The size required for @__state_perm. Only valid to access
+ * with sighand locked.
+ */
+ unsigned int __state_size;
+
+ /*
+ * @__user_state_size:
+ *
+ * The size required for @__state_perm user part. Only valid to
+ * access with sighand locked.
+ */
+ unsigned int __user_state_size;
+};
+
/*
* Highest level per task FPU state data structure that
* contains the FPU register state plus various FPU
@@ -337,19 +454,100 @@ struct fpu {
unsigned long avx512_timestamp;
/*
- * @state:
+ * @fpstate:
+ *
+ * Pointer to the active struct fpstate. Initialized to
+ * point at @__fpstate below.
+ */
+ struct fpstate *fpstate;
+
+ /*
+ * @__task_fpstate:
+ *
+ * Pointer to an inactive struct fpstate. Initialized to NULL. Is
+ * used only for KVM support to swap out the regular task fpstate.
+ */
+ struct fpstate *__task_fpstate;
+
+ /*
+ * @perm:
+ *
+ * Permission related information
+ */
+ struct fpu_state_perm perm;
+
+ /*
+ * @__fpstate:
*
- * In-memory copy of all FPU registers that we save/restore
- * over context switches. If the task is using the FPU then
- * the registers in the FPU are more recent than this state
- * copy. If the task context-switches away then they get
- * saved here and represent the FPU state.
+ * Initial in-memory storage for FPU registers which are saved in
+ * context switch and when the kernel uses the FPU. The registers
+ * are restored from this storage on return to user space if they
+ * are not longer containing the tasks FPU register state.
*/
- union fpregs_state state;
+ struct fpstate __fpstate;
/*
- * WARNING: 'state' is dynamically-sized. Do not put
+ * WARNING: '__fpstate' is dynamically-sized. Do not put
* anything after it here.
*/
};
+/*
+ * Guest pseudo FPU container
+ */
+struct fpu_guest {
+ /*
+ * @fpstate: Pointer to the allocated guest fpstate
+ */
+ struct fpstate *fpstate;
+};
+
+/*
+ * FPU state configuration data. Initialized at boot time. Read only after init.
+ */
+struct fpu_state_config {
+ /*
+ * @max_size:
+ *
+ * The maximum size of the register state buffer. Includes all
+ * supported features except independent managed features.
+ */
+ unsigned int max_size;
+
+ /*
+ * @default_size:
+ *
+ * The default size of the register state buffer. Includes all
+ * supported features except independent managed features and
+ * features which have to be requested by user space before usage.
+ */
+ unsigned int default_size;
+
+ /*
+ * @max_features:
+ *
+ * The maximum supported features bitmap. Does not include
+ * independent managed features.
+ */
+ u64 max_features;
+
+ /*
+ * @default_features:
+ *
+ * The default supported features bitmap. Does not include
+ * independent managed features and features which have to
+ * be requested by user space before usage.
+ */
+ u64 default_features;
+ /*
+ * @legacy_features:
+ *
+ * Features which can be reported back to user space
+ * even without XSAVE support, i.e. legacy features FP + SSE
+ */
+ u64 legacy_features;
+};
+
+/* FPU state configuration information */
+extern struct fpu_state_config fpu_kernel_cfg, fpu_user_cfg;
+
#endif /* _ASM_X86_FPU_H */
diff --git a/arch/x86/include/asm/fpu/xcr.h b/arch/x86/include/asm/fpu/xcr.h
index 1c7ab8d95da5..79f95d3787e2 100644
--- a/arch/x86/include/asm/fpu/xcr.h
+++ b/arch/x86/include/asm/fpu/xcr.h
@@ -2,17 +2,6 @@
#ifndef _ASM_X86_FPU_XCR_H
#define _ASM_X86_FPU_XCR_H
-/*
- * MXCSR and XCR definitions:
- */
-
-static inline void ldmxcsr(u32 mxcsr)
-{
- asm volatile("ldmxcsr %0" :: "m" (mxcsr));
-}
-
-extern unsigned int mxcsr_feature_mask;
-
#define XCR_XFEATURE_ENABLED_MASK 0x00000000
static inline u64 xgetbv(u32 index)
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 109dfcc75299..0f8b90ab18c9 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -14,6 +14,8 @@
#define XSTATE_CPUID 0x0000000d
+#define TILE_CPUID 0x0000001d
+
#define FXSAVE_SIZE 512
#define XSAVE_HDR_SIZE 64
@@ -33,7 +35,8 @@
XFEATURE_MASK_Hi16_ZMM | \
XFEATURE_MASK_PKRU | \
XFEATURE_MASK_BNDREGS | \
- XFEATURE_MASK_BNDCSR)
+ XFEATURE_MASK_BNDCSR | \
+ XFEATURE_MASK_XTILE)
/*
* Features which are restored when returning to user space.
@@ -43,6 +46,9 @@
#define XFEATURE_MASK_USER_RESTORE \
(XFEATURE_MASK_USER_SUPPORTED & ~XFEATURE_MASK_PKRU)
+/* Features which are dynamically enabled for a process on request */
+#define XFEATURE_MASK_USER_DYNAMIC XFEATURE_MASK_XTILE_DATA
+
/* All currently supported supervisor features */
#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID)
@@ -78,78 +84,42 @@
XFEATURE_MASK_INDEPENDENT | \
XFEATURE_MASK_SUPERVISOR_UNSUPPORTED)
-#ifdef CONFIG_X86_64
-#define REX_PREFIX "0x48, "
-#else
-#define REX_PREFIX
-#endif
-
-extern u64 xfeatures_mask_all;
-
-static inline u64 xfeatures_mask_supervisor(void)
-{
- return xfeatures_mask_all & XFEATURE_MASK_SUPERVISOR_SUPPORTED;
-}
-
/*
- * The xfeatures which are enabled in XCR0 and expected to be in ptrace
- * buffers and signal frames.
+ * The feature mask required to restore FPU state:
+ * - All user states which are not eagerly switched in switch_to()/exec()
+ * - The suporvisor states
*/
-static inline u64 xfeatures_mask_uabi(void)
-{
- return xfeatures_mask_all & XFEATURE_MASK_USER_SUPPORTED;
-}
-
-/*
- * The xfeatures which are restored by the kernel when returning to user
- * mode. This is not necessarily the same as xfeatures_mask_uabi() as the
- * kernel does not manage all XCR0 enabled features via xsave/xrstor as
- * some of them have to be switched eagerly on context switch and exec().
- */
-static inline u64 xfeatures_mask_restore_user(void)
-{
- return xfeatures_mask_all & XFEATURE_MASK_USER_RESTORE;
-}
-
-/*
- * Like xfeatures_mask_restore_user() but additionally restors the
- * supported supervisor states.
- */
-static inline u64 xfeatures_mask_fpstate(void)
-{
- return xfeatures_mask_all & \
- (XFEATURE_MASK_USER_RESTORE | XFEATURE_MASK_SUPERVISOR_SUPPORTED);
-}
-
-static inline u64 xfeatures_mask_independent(void)
-{
- if (!boot_cpu_has(X86_FEATURE_ARCH_LBR))
- return XFEATURE_MASK_INDEPENDENT & ~XFEATURE_MASK_LBR;
-
- return XFEATURE_MASK_INDEPENDENT;
-}
+#define XFEATURE_MASK_FPSTATE (XFEATURE_MASK_USER_RESTORE | \
+ XFEATURE_MASK_SUPERVISOR_SUPPORTED)
extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
extern void __init update_regset_xstate_info(unsigned int size,
u64 xstate_mask);
-void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
int xfeature_size(int xfeature_nr);
-int copy_uabi_from_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf);
-int copy_sigframe_from_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf);
void xsaves(struct xregs_state *xsave, u64 mask);
void xrstors(struct xregs_state *xsave, u64 mask);
-enum xstate_copy_mode {
- XSTATE_COPY_FP,
- XSTATE_COPY_FX,
- XSTATE_COPY_XSAVE,
-};
+int xfd_enable_feature(u64 xfd_err);
+
+#ifdef CONFIG_X86_64
+DECLARE_STATIC_KEY_FALSE(__fpu_state_size_dynamic);
+#endif
+
+#ifdef CONFIG_X86_64
+DECLARE_STATIC_KEY_FALSE(__fpu_state_size_dynamic);
-struct membuf;
-void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
- enum xstate_copy_mode mode);
+static __always_inline __pure bool fpu_state_size_dynamic(void)
+{
+ return static_branch_unlikely(&__fpu_state_size_dynamic);
+}
+#else
+static __always_inline __pure bool fpu_state_size_dynamic(void)
+{
+ return false;
+}
+#endif
#endif
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 13f64654dfff..32f300dade5e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -691,11 +691,10 @@ struct kvm_vcpu_arch {
*
* Note that while the PKRU state lives inside the fpu registers,
* it is switched out separately at VMENTER and VMEXIT time. The
- * "guest_fpu" state here contains the guest FPU context, with the
+ * "guest_fpstate" state here contains the guest FPU context, with the
* host PRKU bits.
*/
- struct fpu *user_fpu;
- struct fpu *guest_fpu;
+ struct fpu_guest guest_fpu;
u64 xcr0;
u64 guest_supported_xcr0;
@@ -1686,8 +1685,6 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
int reason, bool has_error_code, u32 error_code);
-void kvm_free_guest_fpu(struct kvm_vcpu *vcpu);
-
void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0);
void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4);
int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index a7c413432b33..01e2650b9585 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -625,6 +625,8 @@
#define MSR_IA32_BNDCFGS_RSVD 0x00000ffc
+#define MSR_IA32_XFD 0x000001c4
+#define MSR_IA32_XFD_ERR 0x000001c5
#define MSR_IA32_XSS 0x00000da0
#define MSR_IA32_APICBASE 0x0000001b
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index a3f87f1015d3..6b52182e178a 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -92,7 +92,7 @@ static __always_inline unsigned long long __rdmsr(unsigned int msr)
asm volatile("1: rdmsr\n"
"2:\n"
- _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_unsafe)
+ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_RDMSR)
: EAX_EDX_RET(val, low, high) : "c" (msr));
return EAX_EDX_VAL(val, low, high);
@@ -102,7 +102,7 @@ static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high)
{
asm volatile("1: wrmsr\n"
"2:\n"
- _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
+ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR)
: : "c" (msr), "a"(low), "d" (high) : "memory");
}
diff --git a/arch/x86/include/asm/pkru.h b/arch/x86/include/asm/pkru.h
index ccc539faa5bb..4cd49afa0ca4 100644
--- a/arch/x86/include/asm/pkru.h
+++ b/arch/x86/include/asm/pkru.h
@@ -2,7 +2,7 @@
#ifndef _ASM_X86_PKRU_H
#define _ASM_X86_PKRU_H
-#include <asm/fpu/xstate.h>
+#include <asm/cpufeature.h>
#define PKRU_AD_BIT 0x1
#define PKRU_WD_BIT 0x2
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index e81177edc681..f97aa49a31ea 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -461,9 +461,6 @@ DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
#endif /* !X86_64 */
-extern unsigned int fpu_kernel_xstate_size;
-extern unsigned int fpu_user_xstate_size;
-
struct perf_event;
struct thread_struct {
@@ -537,12 +534,12 @@ struct thread_struct {
*/
};
-/* Whitelist the FPU state from the task_struct for hardened usercopy. */
+extern void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size);
+
static inline void arch_thread_struct_whitelist(unsigned long *offset,
unsigned long *size)
{
- *offset = offsetof(struct thread_struct, fpu.state);
- *size = fpu_kernel_xstate_size;
+ fpu_thread_struct_whitelist(offset, size);
}
static inline void
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 8c5d1910a848..feed36d44d04 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -40,6 +40,6 @@ void x86_report_nx(void);
extern int reboot_force;
long do_arch_prctl_common(struct task_struct *task, int option,
- unsigned long cpuid_enabled);
+ unsigned long arg2);
#endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 72044026eb3c..8dd8e8ec9fa5 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -339,7 +339,7 @@ static inline void __loadsegment_fs(unsigned short value)
"1: movw %0, %%fs \n"
"2: \n"
- _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_clear_fs)
+ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_CLEAR_FS)
: : "rm" (value) : "memory");
}
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
index 879b77792f94..4645a6334063 100644
--- a/arch/x86/include/asm/trace/fpu.h
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -22,8 +22,8 @@ DECLARE_EVENT_CLASS(x86_fpu,
__entry->fpu = fpu;
__entry->load_fpu = test_thread_flag(TIF_NEED_FPU_LOAD);
if (boot_cpu_has(X86_FEATURE_OSXSAVE)) {
- __entry->xfeatures = fpu->state.xsave.header.xfeatures;
- __entry->xcomp_bv = fpu->state.xsave.header.xcomp_bv;
+ __entry->xfeatures = fpu->fpstate->regs.xsave.header.xfeatures;
+ __entry->xcomp_bv = fpu->fpstate->regs.xsave.header.xcomp_bv;
}
),
TP_printk("x86/fpu: %p load: %d xfeatures: %llx xcomp_bv: %llx",
diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h
index 5a6aac9fa41f..754a07856817 100644
--- a/arch/x86/include/uapi/asm/prctl.h
+++ b/arch/x86/include/uapi/asm/prctl.h
@@ -10,6 +10,10 @@
#define ARCH_GET_CPUID 0x1011
#define ARCH_SET_CPUID 0x1012
+#define ARCH_GET_XCOMP_SUPP 0x1021
+#define ARCH_GET_XCOMP_PERM 0x1022
+#define ARCH_REQ_XCOMP_PERM 0x1023
+
#define ARCH_MAP_VDSO_X32 0x2001
#define ARCH_MAP_VDSO_32 0x2002
#define ARCH_MAP_VDSO_64 0x2003
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index ba43597f1027..31e2412b3f17 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -22,7 +22,7 @@
#include <asm/bugs.h>
#include <asm/processor.h>
#include <asm/processor-flags.h>
-#include <asm/fpu/internal.h>
+#include <asm/fpu/api.h>
#include <asm/msr.h>
#include <asm/vmx.h>
#include <asm/paravirt.h>
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8be4b08fd299..8ed18d00c211 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -42,7 +42,7 @@
#include <asm/setup.h>
#include <asm/apic.h>
#include <asm/desc.h>
-#include <asm/fpu/internal.h>
+#include <asm/fpu/api.h>
#include <asm/mtrr.h>
#include <asm/hwcap2.h>
#include <linux/numa.h>
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index defda61f372d..cb2fdd130aae 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -75,6 +75,8 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_SGX_LC, X86_FEATURE_SGX },
{ X86_FEATURE_SGX1, X86_FEATURE_SGX },
{ X86_FEATURE_SGX2, X86_FEATURE_SGX1 },
+ { X86_FEATURE_XFD, X86_FEATURE_XSAVES },
+ { X86_FEATURE_AMX_TILE, X86_FEATURE_XFD },
{}
};
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 193204aee880..2af4b420172e 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -373,13 +373,16 @@ static int msr_to_offset(u32 msr)
return -1;
}
-__visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr,
- unsigned long error_code,
- unsigned long fault_addr)
+void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr)
{
- pr_emerg("MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
- (unsigned int)regs->cx, regs->ip, (void *)regs->ip);
+ if (wrmsr) {
+ pr_emerg("MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
+ (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax,
+ regs->ip, (void *)regs->ip);
+ } else {
+ pr_emerg("MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
+ (unsigned int)regs->cx, regs->ip, (void *)regs->ip);
+ }
show_stack_regs(regs);
@@ -387,8 +390,6 @@ __visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup,
while (true)
cpu_relax();
-
- return true;
}
/* MSR access wrappers used for error injection */
@@ -420,32 +421,13 @@ static noinstr u64 mce_rdmsrl(u32 msr)
*/
asm volatile("1: rdmsr\n"
"2:\n"
- _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_fault)
+ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_RDMSR_IN_MCE)
: EAX_EDX_RET(val, low, high) : "c" (msr));
return EAX_EDX_VAL(val, low, high);
}
-__visible bool ex_handler_wrmsr_fault(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr,
- unsigned long error_code,
- unsigned long fault_addr)
-{
- pr_emerg("MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
- (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax,
- regs->ip, (void *)regs->ip);
-
- show_stack_regs(regs);
-
- panic("MCA architectural violation!\n");
-
- while (true)
- cpu_relax();
-
- return true;
-}
-
static noinstr void mce_wrmsrl(u32 msr, u64 v)
{
u32 low, high;
@@ -470,7 +452,7 @@ static noinstr void mce_wrmsrl(u32 msr, u64 v)
/* See comment in mce_rdmsrl() */
asm volatile("1: wrmsr\n"
"2:\n"
- _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_fault)
+ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR_IN_MCE)
: : "c" (msr), "a"(low), "d" (high) : "memory");
}
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 88dcc79cfb07..3463f8cedb32 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -61,7 +61,7 @@ static inline void cmci_disable_bank(int bank) { }
static inline void intel_init_cmci(void) { }
static inline void intel_init_lmce(void) { }
static inline void intel_clear_lmce(void) { }
-static inline bool intel_filter_mce(struct mce *m) { return false; };
+static inline bool intel_filter_mce(struct mce *m) { return false; }
#endif
void mce_timer_kick(unsigned long interval);
@@ -183,17 +183,7 @@ extern bool filter_mce(struct mce *m);
#ifdef CONFIG_X86_MCE_AMD
extern bool amd_filter_mce(struct mce *m);
#else
-static inline bool amd_filter_mce(struct mce *m) { return false; };
+static inline bool amd_filter_mce(struct mce *m) { return false; }
#endif
-__visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr,
- unsigned long error_code,
- unsigned long fault_addr);
-
-__visible bool ex_handler_wrmsr_fault(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr,
- unsigned long error_code,
- unsigned long fault_addr);
-
#endif /* __X86_MCE_INTERNAL_H__ */
diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c
index 17e631443116..f60bbaff9f65 100644
--- a/arch/x86/kernel/cpu/mce/severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -265,25 +265,25 @@ static bool is_copy_from_user(struct pt_regs *regs)
*/
static int error_context(struct mce *m, struct pt_regs *regs)
{
- enum handler_type t;
-
if ((m->cs & 3) == 3)
return IN_USER;
if (!mc_recoverable(m->mcgstatus))
return IN_KERNEL;
- t = ex_get_fault_handler_type(m->ip);
- if (t == EX_HANDLER_FAULT) {
- m->kflags |= MCE_IN_KERNEL_RECOV;
- return IN_KERNEL_RECOV;
- }
- if (t == EX_HANDLER_UACCESS && regs && is_copy_from_user(regs)) {
- m->kflags |= MCE_IN_KERNEL_RECOV;
+ switch (ex_get_fixup_type(m->ip)) {
+ case EX_TYPE_UACCESS:
+ case EX_TYPE_COPY:
+ if (!regs || !is_copy_from_user(regs))
+ return IN_KERNEL;
m->kflags |= MCE_IN_KERNEL_COPYIN;
+ fallthrough;
+ case EX_TYPE_FAULT_MCE_SAFE:
+ case EX_TYPE_DEFAULT_MCE_SAFE:
+ m->kflags |= MCE_IN_KERNEL_RECOV;
return IN_KERNEL_RECOV;
+ default:
+ return IN_KERNEL;
}
-
- return IN_KERNEL;
}
static int mce_severity_amd_smca(struct mce *m, enum context err_ctx)
diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c
index 2954fab15e51..794e70151203 100644
--- a/arch/x86/kernel/fpu/bugs.c
+++ b/arch/x86/kernel/fpu/bugs.c
@@ -2,7 +2,7 @@
/*
* x86 FPU bug checks:
*/
-#include <asm/fpu/internal.h>
+#include <asm/fpu/api.h>
/*
* Boot time CPU/FPU FDIV bug detection code:
diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h
new file mode 100644
index 000000000000..958accf2ccf0
--- /dev/null
+++ b/arch/x86/kernel/fpu/context.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __X86_KERNEL_FPU_CONTEXT_H
+#define __X86_KERNEL_FPU_CONTEXT_H
+
+#include <asm/fpu/xstate.h>
+#include <asm/trace/fpu.h>
+
+/* Functions related to FPU context tracking */
+
+/*
+ * The in-register FPU state for an FPU context on a CPU is assumed to be
+ * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx
+ * matches the FPU.
+ *
+ * If the FPU register state is valid, the kernel can skip restoring the
+ * FPU state from memory.
+ *
+ * Any code that clobbers the FPU registers or updates the in-memory
+ * FPU state for a task MUST let the rest of the kernel know that the
+ * FPU registers are no longer valid for this task.
+ *
+ * Either one of these invalidation functions is enough. Invalidate
+ * a resource you control: CPU if using the CPU for something else
+ * (with preemption disabled), FPU for the current task, or a task that
+ * is prevented from running by the current task.
+ */
+static inline void __cpu_invalidate_fpregs_state(void)
+{
+ __this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+}
+
+static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu)
+{
+ fpu->last_cpu = -1;
+}
+
+static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu)
+{
+ return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
+}
+
+static inline void fpregs_deactivate(struct fpu *fpu)
+{
+ __this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+ trace_x86_fpu_regs_deactivated(fpu);
+}
+
+static inline void fpregs_activate(struct fpu *fpu)
+{
+ __this_cpu_write(fpu_fpregs_owner_ctx, fpu);
+ trace_x86_fpu_regs_activated(fpu);
+}
+
+/* Internal helper for switch_fpu_return() and signal frame setup */
+static inline void fpregs_restore_userregs(void)
+{
+ struct fpu *fpu = &current->thread.fpu;
+ int cpu = smp_processor_id();
+
+ if (WARN_ON_ONCE(current->flags & PF_KTHREAD))
+ return;
+
+ if (!fpregs_state_valid(fpu, cpu)) {
+ /*
+ * This restores _all_ xstate which has not been
+ * established yet.
+ *
+ * If PKRU is enabled, then the PKRU value is already
+ * correct because it was either set in switch_to() or in
+ * flush_thread(). So it is excluded because it might be
+ * not up to date in current->thread.fpu.xsave state.
+ *
+ * XFD state is handled in restore_fpregs_from_fpstate().
+ */
+ restore_fpregs_from_fpstate(fpu->fpstate, XFEATURE_MASK_FPSTATE);
+
+ fpregs_activate(fpu);
+ fpu->last_cpu = cpu;
+ }
+ clear_thread_flag(TIF_NEED_FPU_LOAD);
+}
+
+#endif
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 7ada7bd03a32..8ea306b1bf8e 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -6,8 +6,9 @@
* General FPU state handling cleanups
* Gareth Hughes <gareth@valinux.com>, May 2000
*/
-#include <asm/fpu/internal.h>
+#include <asm/fpu/api.h>
#include <asm/fpu/regset.h>
+#include <asm/fpu/sched.h>
#include <asm/fpu/signal.h>
#include <asm/fpu/types.h>
#include <asm/traps.h>
@@ -15,15 +16,30 @@
#include <linux/hardirq.h>
#include <linux/pkeys.h>
+#include <linux/vmalloc.h>
+
+#include "context.h"
+#include "internal.h"
+#include "legacy.h"
+#include "xstate.h"
#define CREATE_TRACE_POINTS
#include <asm/trace/fpu.h>
+#ifdef CONFIG_X86_64
+DEFINE_STATIC_KEY_FALSE(__fpu_state_size_dynamic);
+DEFINE_PER_CPU(u64, xfd_state);
+#endif
+
+/* The FPU state configuration data for kernel and user space */
+struct fpu_state_config fpu_kernel_cfg __ro_after_init;
+struct fpu_state_config fpu_user_cfg __ro_after_init;
+
/*
* Represents the initial FPU state. It's mostly (but not completely) zeroes,
* depending on the FPU hardware format:
*/
-union fpregs_state init_fpstate __ro_after_init;
+struct fpstate init_fpstate __ro_after_init;
/*
* Track whether the kernel is using the FPU state
@@ -83,7 +99,7 @@ bool irq_fpu_usable(void)
EXPORT_SYMBOL(irq_fpu_usable);
/*
- * Save the FPU register state in fpu->state. The register state is
+ * Save the FPU register state in fpu->fpstate->regs. The register state is
* preserved.
*
* Must be called with fpregs_lock() held.
@@ -99,19 +115,19 @@ EXPORT_SYMBOL(irq_fpu_usable);
void save_fpregs_to_fpstate(struct fpu *fpu)
{
if (likely(use_xsave())) {
- os_xsave(&fpu->state.xsave);
+ os_xsave(fpu->fpstate);
/*
* AVX512 state is tracked here because its use is
* known to slow the max clock speed of the core.
*/
- if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512)
+ if (fpu->fpstate->regs.xsave.header.xfeatures & XFEATURE_MASK_AVX512)
fpu->avx512_timestamp = jiffies;
return;
}
if (likely(use_fxsr())) {
- fxsave(&fpu->state.fxsave);
+ fxsave(&fpu->fpstate->regs.fxsave);
return;
}
@@ -119,12 +135,11 @@ void save_fpregs_to_fpstate(struct fpu *fpu)
* Legacy FPU register saving, FNSAVE always clears FPU registers,
* so we have to reload them from the memory state.
*/
- asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave));
- frstor(&fpu->state.fsave);
+ asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->fpstate->regs.fsave));
+ frstor(&fpu->fpstate->regs.fsave);
}
-EXPORT_SYMBOL(save_fpregs_to_fpstate);
-void __restore_fpregs_from_fpstate(union fpregs_state *fpstate, u64 mask)
+void restore_fpregs_from_fpstate(struct fpstate *fpstate, u64 mask)
{
/*
* AMD K7/K8 and later CPUs up to Zen don't save/restore
@@ -141,15 +156,181 @@ void __restore_fpregs_from_fpstate(union fpregs_state *fpstate, u64 mask)
}
if (use_xsave()) {
- os_xrstor(&fpstate->xsave, mask);
+ /*
+ * Dynamically enabled features are enabled in XCR0, but
+ * usage requires also that the corresponding bits in XFD
+ * are cleared. If the bits are set then using a related
+ * instruction will raise #NM. This allows to do the
+ * allocation of the larger FPU buffer lazy from #NM or if
+ * the task has no permission to kill it which would happen
+ * via #UD if the feature is disabled in XCR0.
+ *
+ * XFD state is following the same life time rules as
+ * XSTATE and to restore state correctly XFD has to be
+ * updated before XRSTORS otherwise the component would
+ * stay in or go into init state even if the bits are set
+ * in fpstate::regs::xsave::xfeatures.
+ */
+ xfd_update_state(fpstate);
+
+ /*
+ * Restoring state always needs to modify all features
+ * which are in @mask even if the current task cannot use
+ * extended features.
+ *
+ * So fpstate->xfeatures cannot be used here, because then
+ * a feature for which the task has no permission but was
+ * used by the previous task would not go into init state.
+ */
+ mask = fpu_kernel_cfg.max_features & mask;
+
+ os_xrstor(fpstate, mask);
} else {
if (use_fxsr())
- fxrstor(&fpstate->fxsave);
+ fxrstor(&fpstate->regs.fxsave);
else
- frstor(&fpstate->fsave);
+ frstor(&fpstate->regs.fsave);
}
}
-EXPORT_SYMBOL_GPL(__restore_fpregs_from_fpstate);
+
+void fpu_reset_from_exception_fixup(void)
+{
+ restore_fpregs_from_fpstate(&init_fpstate, XFEATURE_MASK_FPSTATE);
+}
+
+#if IS_ENABLED(CONFIG_KVM)
+static void __fpstate_reset(struct fpstate *fpstate);
+
+bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
+{
+ struct fpstate *fpstate;
+ unsigned int size;
+
+ size = fpu_user_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
+ fpstate = vzalloc(size);
+ if (!fpstate)
+ return false;
+
+ __fpstate_reset(fpstate);
+ fpstate_init_user(fpstate);
+ fpstate->is_valloc = true;
+ fpstate->is_guest = true;
+
+ gfpu->fpstate = fpstate;
+ return true;
+}
+EXPORT_SYMBOL_GPL(fpu_alloc_guest_fpstate);
+
+void fpu_free_guest_fpstate(struct fpu_guest *gfpu)
+{
+ struct fpstate *fps = gfpu->fpstate;
+
+ if (!fps)
+ return;
+
+ if (WARN_ON_ONCE(!fps->is_valloc || !fps->is_guest || fps->in_use))
+ return;
+
+ gfpu->fpstate = NULL;
+ vfree(fps);
+}
+EXPORT_SYMBOL_GPL(fpu_free_guest_fpstate);
+
+int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
+{
+ struct fpstate *guest_fps = guest_fpu->fpstate;
+ struct fpu *fpu = &current->thread.fpu;
+ struct fpstate *cur_fps = fpu->fpstate;
+
+ fpregs_lock();
+ if (!cur_fps->is_confidential && !test_thread_flag(TIF_NEED_FPU_LOAD))
+ save_fpregs_to_fpstate(fpu);
+
+ /* Swap fpstate */
+ if (enter_guest) {
+ fpu->__task_fpstate = cur_fps;
+ fpu->fpstate = guest_fps;
+ guest_fps->in_use = true;
+ } else {
+ guest_fps->in_use = false;
+ fpu->fpstate = fpu->__task_fpstate;
+ fpu->__task_fpstate = NULL;
+ }
+
+ cur_fps = fpu->fpstate;
+
+ if (!cur_fps->is_confidential) {
+ /* Includes XFD update */
+ restore_fpregs_from_fpstate(cur_fps, XFEATURE_MASK_FPSTATE);
+ } else {
+ /*
+ * XSTATE is restored by firmware from encrypted
+ * memory. Make sure XFD state is correct while
+ * running with guest fpstate
+ */
+ xfd_update_state(cur_fps);
+ }
+
+ fpregs_mark_activate();
+ fpregs_unlock();
+ return 0;
+}
+EXPORT_SYMBOL_GPL(fpu_swap_kvm_fpstate);
+
+void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf,
+ unsigned int size, u32 pkru)
+{
+ struct fpstate *kstate = gfpu->fpstate;
+ union fpregs_state *ustate = buf;
+ struct membuf mb = { .p = buf, .left = size };
+
+ if (cpu_feature_enabled(X86_FEATURE_XSAVE)) {
+ __copy_xstate_to_uabi_buf(mb, kstate, pkru, XSTATE_COPY_XSAVE);
+ } else {
+ memcpy(&ustate->fxsave, &kstate->regs.fxsave,
+ sizeof(ustate->fxsave));
+ /* Make it restorable on a XSAVE enabled host */
+ ustate->xsave.header.xfeatures = XFEATURE_MASK_FPSSE;
+ }
+}
+EXPORT_SYMBOL_GPL(fpu_copy_guest_fpstate_to_uabi);
+
+int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf,
+ u64 xcr0, u32 *vpkru)
+{
+ struct fpstate *kstate = gfpu->fpstate;
+ const union fpregs_state *ustate = buf;
+ struct pkru_state *xpkru;
+ int ret;
+
+ if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) {
+ if (ustate->xsave.header.xfeatures & ~XFEATURE_MASK_FPSSE)
+ return -EINVAL;
+ if (ustate->fxsave.mxcsr & ~mxcsr_feature_mask)
+ return -EINVAL;
+ memcpy(&kstate->regs.fxsave, &ustate->fxsave, sizeof(ustate->fxsave));
+ return 0;
+ }
+
+ if (ustate->xsave.header.xfeatures & ~xcr0)
+ return -EINVAL;
+
+ ret = copy_uabi_from_kernel_to_xstate(kstate, ustate);
+ if (ret)
+ return ret;
+
+ /* Retrieve PKRU if not in init state */
+ if (kstate->regs.xsave.header.xfeatures & XFEATURE_MASK_PKRU) {
+ xpkru = get_xsave_addr(&kstate->regs.xsave, XFEATURE_PKRU);
+ *vpkru = xpkru->pkru;
+ }
+
+ /* Ensure that XCOMP_BV is set up for XSAVES */
+ xstate_init_xcomp_bv(&kstate->regs.xsave, kstate->xfeatures);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate);
+#endif /* CONFIG_KVM */
void kernel_fpu_begin_mask(unsigned int kfpu_mask)
{
@@ -203,52 +384,88 @@ void fpu_sync_fpstate(struct fpu *fpu)
fpregs_unlock();
}
-static inline void fpstate_init_xstate(struct xregs_state *xsave)
+static inline unsigned int init_fpstate_copy_size(void)
{
- /*
- * XRSTORS requires these bits set in xcomp_bv, or it will
- * trigger #GP:
- */
- xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all;
+ if (!use_xsave())
+ return fpu_kernel_cfg.default_size;
+
+ /* XSAVE(S) just needs the legacy and the xstate header part */
+ return sizeof(init_fpstate.regs.xsave);
}
-static inline void fpstate_init_fxstate(struct fxregs_state *fx)
+static inline void fpstate_init_fxstate(struct fpstate *fpstate)
{
- fx->cwd = 0x37f;
- fx->mxcsr = MXCSR_DEFAULT;
+ fpstate->regs.fxsave.cwd = 0x37f;
+ fpstate->regs.fxsave.mxcsr = MXCSR_DEFAULT;
}
/*
* Legacy x87 fpstate state init:
*/
-static inline void fpstate_init_fstate(struct fregs_state *fp)
+static inline void fpstate_init_fstate(struct fpstate *fpstate)
{
- fp->cwd = 0xffff037fu;
- fp->swd = 0xffff0000u;
- fp->twd = 0xffffffffu;
- fp->fos = 0xffff0000u;
+ fpstate->regs.fsave.cwd = 0xffff037fu;
+ fpstate->regs.fsave.swd = 0xffff0000u;
+ fpstate->regs.fsave.twd = 0xffffffffu;
+ fpstate->regs.fsave.fos = 0xffff0000u;
}
-void fpstate_init(union fpregs_state *state)
+/*
+ * Used in two places:
+ * 1) Early boot to setup init_fpstate for non XSAVE systems
+ * 2) fpu_init_fpstate_user() which is invoked from KVM
+ */
+void fpstate_init_user(struct fpstate *fpstate)
{
- if (!static_cpu_has(X86_FEATURE_FPU)) {
- fpstate_init_soft(&state->soft);
+ if (!cpu_feature_enabled(X86_FEATURE_FPU)) {
+ fpstate_init_soft(&fpstate->regs.soft);
return;
}
- memset(state, 0, fpu_kernel_xstate_size);
+ xstate_init_xcomp_bv(&fpstate->regs.xsave, fpstate->xfeatures);
- if (static_cpu_has(X86_FEATURE_XSAVES))
- fpstate_init_xstate(&state->xsave);
- if (static_cpu_has(X86_FEATURE_FXSR))
- fpstate_init_fxstate(&state->fxsave);
+ if (cpu_feature_enabled(X86_FEATURE_FXSR))
+ fpstate_init_fxstate(fpstate);
else
- fpstate_init_fstate(&state->fsave);
+ fpstate_init_fstate(fpstate);
+}
+
+static void __fpstate_reset(struct fpstate *fpstate)
+{
+ /* Initialize sizes and feature masks */
+ fpstate->size = fpu_kernel_cfg.default_size;
+ fpstate->user_size = fpu_user_cfg.default_size;
+ fpstate->xfeatures = fpu_kernel_cfg.default_features;
+ fpstate->user_xfeatures = fpu_user_cfg.default_features;
+ fpstate->xfd = init_fpstate.xfd;
+}
+
+void fpstate_reset(struct fpu *fpu)
+{
+ /* Set the fpstate pointer to the default fpstate */
+ fpu->fpstate = &fpu->__fpstate;
+ __fpstate_reset(fpu->fpstate);
+
+ /* Initialize the permission related info in fpu */
+ fpu->perm.__state_perm = fpu_kernel_cfg.default_features;
+ fpu->perm.__state_size = fpu_kernel_cfg.default_size;
+ fpu->perm.__user_state_size = fpu_user_cfg.default_size;
+}
+
+static inline void fpu_inherit_perms(struct fpu *dst_fpu)
+{
+ if (fpu_state_size_dynamic()) {
+ struct fpu *src_fpu = &current->group_leader->thread.fpu;
+
+ spin_lock_irq(&current->sighand->siglock);
+ /* Fork also inherits the permissions of the parent */
+ dst_fpu->perm = src_fpu->perm;
+ spin_unlock_irq(&current->sighand->siglock);
+ }
}
-EXPORT_SYMBOL_GPL(fpstate_init);
/* Clone current's FPU state on fork */
-int fpu_clone(struct task_struct *dst)
+int fpu_clone(struct task_struct *dst, unsigned long clone_flags)
{
struct fpu *src_fpu = &current->thread.fpu;
struct fpu *dst_fpu = &dst->thread.fpu;
@@ -256,30 +473,51 @@ int fpu_clone(struct task_struct *dst)
/* The new task's FPU state cannot be valid in the hardware. */
dst_fpu->last_cpu = -1;
+ fpstate_reset(dst_fpu);
+
if (!cpu_feature_enabled(X86_FEATURE_FPU))
return 0;
/*
- * Don't let 'init optimized' areas of the XSAVE area
- * leak into the child task:
+ * Enforce reload for user space tasks and prevent kernel threads
+ * from trying to save the FPU registers on context switch.
+ */
+ set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD);
+
+ /*
+ * No FPU state inheritance for kernel threads and IO
+ * worker threads.
+ */
+ if (dst->flags & (PF_KTHREAD | PF_IO_WORKER)) {
+ /* Clear out the minimal state */
+ memcpy(&dst_fpu->fpstate->regs, &init_fpstate.regs,
+ init_fpstate_copy_size());
+ return 0;
+ }
+
+ /*
+ * If a new feature is added, ensure all dynamic features are
+ * caller-saved from here!
*/
- memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size);
+ BUILD_BUG_ON(XFEATURE_MASK_USER_DYNAMIC != XFEATURE_MASK_XTILE_DATA);
/*
- * If the FPU registers are not owned by current just memcpy() the
- * state. Otherwise save the FPU registers directly into the
- * child's FPU context, without any memory-to-memory copying.
+ * Save the default portion of the current FPU state into the
+ * clone. Assume all dynamic features to be defined as caller-
+ * saved, which enables skipping both the expansion of fpstate
+ * and the copying of any dynamic state.
+ *
+ * Do not use memcpy() when TIF_NEED_FPU_LOAD is set because
+ * copying is not valid when current uses non-default states.
*/
fpregs_lock();
if (test_thread_flag(TIF_NEED_FPU_LOAD))
- memcpy(&dst_fpu->state, &src_fpu->state, fpu_kernel_xstate_size);
-
- else
- save_fpregs_to_fpstate(dst_fpu);
+ fpregs_restore_userregs();
+ save_fpregs_to_fpstate(dst_fpu);
+ if (!(clone_flags & CLONE_THREAD))
+ fpu_inherit_perms(dst_fpu);
fpregs_unlock();
- set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD);
-
trace_x86_fpu_copy_src(src_fpu);
trace_x86_fpu_copy_dst(dst_fpu);
@@ -287,6 +525,16 @@ int fpu_clone(struct task_struct *dst)
}
/*
+ * Whitelist the FPU register state embedded into task_struct for hardened
+ * usercopy.
+ */
+void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size)
+{
+ *offset = offsetof(struct thread_struct, fpu.__fpstate.regs);
+ *size = fpu_kernel_cfg.default_size;
+}
+
+/*
* Drops current FPU state: deactivates the fpregs and
* the fpstate. NOTE: it still leaves previous contents
* in the fpregs in the eager-FPU case.
@@ -319,28 +567,19 @@ void fpu__drop(struct fpu *fpu)
static inline void restore_fpregs_from_init_fpstate(u64 features_mask)
{
if (use_xsave())
- os_xrstor(&init_fpstate.xsave, features_mask);
+ os_xrstor(&init_fpstate, features_mask);
else if (use_fxsr())
- fxrstor(&init_fpstate.fxsave);
+ fxrstor(&init_fpstate.regs.fxsave);
else
- frstor(&init_fpstate.fsave);
+ frstor(&init_fpstate.regs.fsave);
pkru_write_default();
}
-static inline unsigned int init_fpstate_copy_size(void)
-{
- if (!use_xsave())
- return fpu_kernel_xstate_size;
-
- /* XSAVE(S) just needs the legacy and the xstate header part */
- return sizeof(init_fpstate.xsave);
-}
-
/*
* Reset current->fpu memory state to the init values.
*/
-static void fpu_reset_fpstate(void)
+static void fpu_reset_fpregs(void)
{
struct fpu *fpu = &current->thread.fpu;
@@ -359,7 +598,7 @@ static void fpu_reset_fpstate(void)
* user space as PKRU is eagerly written in switch_to() and
* flush_thread().
*/
- memcpy(&fpu->state, &init_fpstate, init_fpstate_copy_size());
+ memcpy(&fpu->fpstate->regs, &init_fpstate.regs, init_fpstate_copy_size());
set_thread_flag(TIF_NEED_FPU_LOAD);
fpregs_unlock();
}
@@ -375,7 +614,7 @@ void fpu__clear_user_states(struct fpu *fpu)
fpregs_lock();
if (!cpu_feature_enabled(X86_FEATURE_FPU)) {
- fpu_reset_fpstate();
+ fpu_reset_fpregs();
fpregs_unlock();
return;
}
@@ -385,12 +624,11 @@ void fpu__clear_user_states(struct fpu *fpu)
* corresponding registers.
*/
if (xfeatures_mask_supervisor() &&
- !fpregs_state_valid(fpu, smp_processor_id())) {
- os_xrstor(&fpu->state.xsave, xfeatures_mask_supervisor());
- }
+ !fpregs_state_valid(fpu, smp_processor_id()))
+ os_xrstor_supervisor(fpu->fpstate);
/* Reset user states in registers. */
- restore_fpregs_from_init_fpstate(xfeatures_mask_restore_user());
+ restore_fpregs_from_init_fpstate(XFEATURE_MASK_USER_RESTORE);
/*
* Now all FPU registers have their desired values. Inform the FPU
@@ -405,7 +643,8 @@ void fpu__clear_user_states(struct fpu *fpu)
void fpu_flush_thread(void)
{
- fpu_reset_fpstate();
+ fpstate_reset(&current->thread.fpu);
+ fpu_reset_fpregs();
}
/*
* Load FPU context before returning to userspace.
@@ -445,7 +684,6 @@ void fpregs_mark_activate(void)
fpu->last_cpu = smp_processor_id();
clear_thread_flag(TIF_NEED_FPU_LOAD);
}
-EXPORT_SYMBOL_GPL(fpregs_mark_activate);
/*
* x87 math exception handling:
@@ -468,11 +706,11 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
* fully reproduce the context of the exception.
*/
if (boot_cpu_has(X86_FEATURE_FXSR)) {
- cwd = fpu->state.fxsave.cwd;
- swd = fpu->state.fxsave.swd;
+ cwd = fpu->fpstate->regs.fxsave.cwd;
+ swd = fpu->fpstate->regs.fxsave.swd;
} else {
- cwd = (unsigned short)fpu->state.fsave.cwd;
- swd = (unsigned short)fpu->state.fsave.swd;
+ cwd = (unsigned short)fpu->fpstate->regs.fsave.cwd;
+ swd = (unsigned short)fpu->fpstate->regs.fsave.swd;
}
err = swd & ~cwd;
@@ -486,7 +724,7 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
unsigned short mxcsr = MXCSR_DEFAULT;
if (boot_cpu_has(X86_FEATURE_XMM))
- mxcsr = fpu->state.fxsave.mxcsr;
+ mxcsr = fpu->fpstate->regs.fxsave.mxcsr;
err = ~(mxcsr >> 7) & mxcsr;
}
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 64e29927cc32..621f4b6cac4a 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -2,7 +2,7 @@
/*
* x86 FPU boot time init code:
*/
-#include <asm/fpu/internal.h>
+#include <asm/fpu/api.h>
#include <asm/tlbflush.h>
#include <asm/setup.h>
@@ -10,6 +10,10 @@
#include <linux/sched/task.h>
#include <linux/init.h>
+#include "internal.h"
+#include "legacy.h"
+#include "xstate.h"
+
/*
* Initialize the registers found in all CPUs, CR0 and CR4:
*/
@@ -34,7 +38,7 @@ static void fpu__init_cpu_generic(void)
/* Flush out any pending x87 state: */
#ifdef CONFIG_MATH_EMULATION
if (!boot_cpu_has(X86_FEATURE_FPU))
- fpstate_init_soft(&current->thread.fpu.state.soft);
+ fpstate_init_soft(&current->thread.fpu.fpstate->regs.soft);
else
#endif
asm volatile ("fninit");
@@ -121,23 +125,14 @@ static void __init fpu__init_system_mxcsr(void)
static void __init fpu__init_system_generic(void)
{
/*
- * Set up the legacy init FPU context. (xstate init might overwrite this
- * with a more modern format, if the CPU supports it.)
+ * Set up the legacy init FPU context. Will be updated when the
+ * CPU supports XSAVE[S].
*/
- fpstate_init(&init_fpstate);
+ fpstate_init_user(&init_fpstate);
fpu__init_system_mxcsr();
}
-/*
- * Size of the FPU context state. All tasks in the system use the
- * same context size, regardless of what portion they use.
- * This is inherent to the XSAVE architecture which puts all state
- * components into a single, continuous memory block:
- */
-unsigned int fpu_kernel_xstate_size __ro_after_init;
-EXPORT_SYMBOL_GPL(fpu_kernel_xstate_size);
-
/* Get alignment of the TYPE. */
#define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test)
@@ -162,13 +157,13 @@ static void __init fpu__init_task_struct_size(void)
* Subtract off the static size of the register state.
* It potentially has a bunch of padding.
*/
- task_size -= sizeof(((struct task_struct *)0)->thread.fpu.state);
+ task_size -= sizeof(current->thread.fpu.__fpstate.regs);
/*
* Add back the dynamically-calculated register state
* size.
*/
- task_size += fpu_kernel_xstate_size;
+ task_size += fpu_kernel_cfg.default_size;
/*
* We dynamically size 'struct fpu', so we require that
@@ -177,7 +172,7 @@ static void __init fpu__init_task_struct_size(void)
* you hit a compile error here, check the structure to
* see if something got added to the end.
*/
- CHECK_MEMBER_AT_END_OF(struct fpu, state);
+ CHECK_MEMBER_AT_END_OF(struct fpu, __fpstate);
CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu);
CHECK_MEMBER_AT_END_OF(struct task_struct, thread);
@@ -192,37 +187,34 @@ static void __init fpu__init_task_struct_size(void)
*/
static void __init fpu__init_system_xstate_size_legacy(void)
{
- static int on_boot_cpu __initdata = 1;
-
- WARN_ON_FPU(!on_boot_cpu);
- on_boot_cpu = 0;
+ unsigned int size;
/*
- * Note that xstate sizes might be overwritten later during
- * fpu__init_system_xstate().
+ * Note that the size configuration might be overwritten later
+ * during fpu__init_system_xstate().
*/
-
- if (!boot_cpu_has(X86_FEATURE_FPU)) {
- fpu_kernel_xstate_size = sizeof(struct swregs_state);
+ if (!cpu_feature_enabled(X86_FEATURE_FPU)) {
+ size = sizeof(struct swregs_state);
+ } else if (cpu_feature_enabled(X86_FEATURE_FXSR)) {
+ size = sizeof(struct fxregs_state);
+ fpu_user_cfg.legacy_features = XFEATURE_MASK_FPSSE;
} else {
- if (boot_cpu_has(X86_FEATURE_FXSR))
- fpu_kernel_xstate_size =
- sizeof(struct fxregs_state);
- else
- fpu_kernel_xstate_size =
- sizeof(struct fregs_state);
+ size = sizeof(struct fregs_state);
+ fpu_user_cfg.legacy_features = XFEATURE_MASK_FP;
}
- fpu_user_xstate_size = fpu_kernel_xstate_size;
+ fpu_kernel_cfg.max_size = size;
+ fpu_kernel_cfg.default_size = size;
+ fpu_user_cfg.max_size = size;
+ fpu_user_cfg.default_size = size;
+ fpstate_reset(&current->thread.fpu);
}
-/* Legacy code to initialize eager fpu mode. */
-static void __init fpu__init_system_ctx_switch(void)
+static void __init fpu__init_init_fpstate(void)
{
- static bool on_boot_cpu __initdata = 1;
-
- WARN_ON_FPU(!on_boot_cpu);
- on_boot_cpu = 0;
+ /* Bring init_fpstate size and features up to date */
+ init_fpstate.size = fpu_kernel_cfg.max_size;
+ init_fpstate.xfeatures = fpu_kernel_cfg.max_features;
}
/*
@@ -231,6 +223,7 @@ static void __init fpu__init_system_ctx_switch(void)
*/
void __init fpu__init_system(struct cpuinfo_x86 *c)
{
+ fpstate_reset(&current->thread.fpu);
fpu__init_system_early_generic(c);
/*
@@ -241,8 +234,7 @@ void __init fpu__init_system(struct cpuinfo_x86 *c)
fpu__init_system_generic();
fpu__init_system_xstate_size_legacy();
- fpu__init_system_xstate();
+ fpu__init_system_xstate(fpu_kernel_cfg.max_size);
fpu__init_task_struct_size();
-
- fpu__init_system_ctx_switch();
+ fpu__init_init_fpstate();
}
diff --git a/arch/x86/kernel/fpu/internal.h b/arch/x86/kernel/fpu/internal.h
new file mode 100644
index 000000000000..dbdb31f55fc7
--- /dev/null
+++ b/arch/x86/kernel/fpu/internal.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __X86_KERNEL_FPU_INTERNAL_H
+#define __X86_KERNEL_FPU_INTERNAL_H
+
+extern struct fpstate init_fpstate;
+
+/* CPU feature check wrappers */
+static __always_inline __pure bool use_xsave(void)
+{
+ return cpu_feature_enabled(X86_FEATURE_XSAVE);
+}
+
+static __always_inline __pure bool use_fxsr(void)
+{
+ return cpu_feature_enabled(X86_FEATURE_FXSR);
+}
+
+#ifdef CONFIG_X86_DEBUG_FPU
+# define WARN_ON_FPU(x) WARN_ON_ONCE(x)
+#else
+# define WARN_ON_FPU(x) ({ (void)(x); 0; })
+#endif
+
+/* Used in init.c */
+extern void fpstate_init_user(struct fpstate *fpstate);
+extern void fpstate_reset(struct fpu *fpu);
+
+#endif
diff --git a/arch/x86/kernel/fpu/legacy.h b/arch/x86/kernel/fpu/legacy.h
new file mode 100644
index 000000000000..17c26b164c63
--- /dev/null
+++ b/arch/x86/kernel/fpu/legacy.h
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __X86_KERNEL_FPU_LEGACY_H
+#define __X86_KERNEL_FPU_LEGACY_H
+
+#include <asm/fpu/types.h>
+
+extern unsigned int mxcsr_feature_mask;
+
+static inline void ldmxcsr(u32 mxcsr)
+{
+ asm volatile("ldmxcsr %0" :: "m" (mxcsr));
+}
+
+/*
+ * Returns 0 on success or the trap number when the operation raises an
+ * exception.
+ */
+#define user_insn(insn, output, input...) \
+({ \
+ int err; \
+ \
+ might_fault(); \
+ \
+ asm volatile(ASM_STAC "\n" \
+ "1: " #insn "\n" \
+ "2: " ASM_CLAC "\n" \
+ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE) \
+ : [err] "=a" (err), output \
+ : "0"(0), input); \
+ err; \
+})
+
+#define kernel_insn_err(insn, output, input...) \
+({ \
+ int err; \
+ asm volatile("1:" #insn "\n\t" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl $-1,%[err]\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : [err] "=r" (err), output \
+ : "0"(0), input); \
+ err; \
+})
+
+#define kernel_insn(insn, output, input...) \
+ asm volatile("1:" #insn "\n\t" \
+ "2:\n" \
+ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FPU_RESTORE) \
+ : output : input)
+
+static inline int fnsave_to_user_sigframe(struct fregs_state __user *fx)
+{
+ return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx));
+}
+
+static inline int fxsave_to_user_sigframe(struct fxregs_state __user *fx)
+{
+ if (IS_ENABLED(CONFIG_X86_32))
+ return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
+ else
+ return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
+
+}
+
+static inline void fxrstor(struct fxregs_state *fx)
+{
+ if (IS_ENABLED(CONFIG_X86_32))
+ kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ else
+ kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline int fxrstor_safe(struct fxregs_state *fx)
+{
+ if (IS_ENABLED(CONFIG_X86_32))
+ return kernel_insn_err(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ else
+ return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline int fxrstor_from_user_sigframe(struct fxregs_state __user *fx)
+{
+ if (IS_ENABLED(CONFIG_X86_32))
+ return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ else
+ return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline void frstor(struct fregs_state *fx)
+{
+ kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline int frstor_safe(struct fregs_state *fx)
+{
+ return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline int frstor_from_user_sigframe(struct fregs_state __user *fx)
+{
+ return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline void fxsave(struct fxregs_state *fx)
+{
+ if (IS_ENABLED(CONFIG_X86_32))
+ asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx));
+ else
+ asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx));
+}
+
+#endif
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 66ed317ebc0d..437d7c930c0b 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -5,10 +5,14 @@
#include <linux/sched/task_stack.h>
#include <linux/vmalloc.h>
-#include <asm/fpu/internal.h>
+#include <asm/fpu/api.h>
#include <asm/fpu/signal.h>
#include <asm/fpu/regset.h>
-#include <asm/fpu/xstate.h>
+
+#include "context.h"
+#include "internal.h"
+#include "legacy.h"
+#include "xstate.h"
/*
* The xstateregs_active() routine is the same as the regset_fpregs_active() routine,
@@ -74,8 +78,8 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
sync_fpstate(fpu);
if (!use_xsave()) {
- return membuf_write(&to, &fpu->state.fxsave,
- sizeof(fpu->state.fxsave));
+ return membuf_write(&to, &fpu->fpstate->regs.fxsave,
+ sizeof(fpu->fpstate->regs.fxsave));
}
copy_xstate_to_uabi_buf(to, target, XSTATE_COPY_FX);
@@ -110,15 +114,15 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
fpu_force_restore(fpu);
/* Copy the state */
- memcpy(&fpu->state.fxsave, &newstate, sizeof(newstate));
+ memcpy(&fpu->fpstate->regs.fxsave, &newstate, sizeof(newstate));
/* Clear xmm8..15 */
- BUILD_BUG_ON(sizeof(fpu->state.fxsave.xmm_space) != 16 * 16);
- memset(&fpu->state.fxsave.xmm_space[8], 0, 8 * 16);
+ BUILD_BUG_ON(sizeof(fpu->__fpstate.regs.fxsave.xmm_space) != 16 * 16);
+ memset(&fpu->fpstate->regs.fxsave.xmm_space[8], 0, 8 * 16);
/* Mark FP and SSE as in use when XSAVE is enabled */
if (use_xsave())
- fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE;
+ fpu->fpstate->regs.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE;
return 0;
}
@@ -149,7 +153,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
/*
* A whole standard-format XSAVE buffer is needed:
*/
- if (pos != 0 || count != fpu_user_xstate_size)
+ if (pos != 0 || count != fpu_user_cfg.max_size)
return -EFAULT;
if (!kbuf) {
@@ -164,7 +168,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
}
fpu_force_restore(fpu);
- ret = copy_uabi_from_kernel_to_xstate(&fpu->state.xsave, kbuf ?: tmpbuf);
+ ret = copy_uabi_from_kernel_to_xstate(fpu->fpstate, kbuf ?: tmpbuf);
out:
vfree(tmpbuf);
@@ -283,7 +287,7 @@ static void __convert_from_fxsr(struct user_i387_ia32_struct *env,
void
convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
{
- __convert_from_fxsr(env, tsk, &tsk->thread.fpu.state.fxsave);
+ __convert_from_fxsr(env, tsk, &tsk->thread.fpu.fpstate->regs.fxsave);
}
void convert_to_fxsr(struct fxregs_state *fxsave,
@@ -326,7 +330,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset,
return fpregs_soft_get(target, regset, to);
if (!cpu_feature_enabled(X86_FEATURE_FXSR)) {
- return membuf_write(&to, &fpu->state.fsave,
+ return membuf_write(&to, &fpu->fpstate->regs.fsave,
sizeof(struct fregs_state));
}
@@ -337,7 +341,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset,
copy_xstate_to_uabi_buf(mb, target, XSTATE_COPY_FP);
fx = &fxsave;
} else {
- fx = &fpu->state.fxsave;
+ fx = &fpu->fpstate->regs.fxsave;
}
__convert_from_fxsr(&env, target, fx);
@@ -366,16 +370,16 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
fpu_force_restore(fpu);
if (cpu_feature_enabled(X86_FEATURE_FXSR))
- convert_to_fxsr(&fpu->state.fxsave, &env);
+ convert_to_fxsr(&fpu->fpstate->regs.fxsave, &env);
else
- memcpy(&fpu->state.fsave, &env, sizeof(env));
+ memcpy(&fpu->fpstate->regs.fsave, &env, sizeof(env));
/*
* Update the header bit in the xsave header, indicating the
* presence of FP.
*/
if (cpu_feature_enabled(X86_FEATURE_XSAVE))
- fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FP;
+ fpu->fpstate->regs.xsave.header.xfeatures |= XFEATURE_MASK_FP;
return 0;
}
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 831b25c5e705..cc977da6e128 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -7,23 +7,25 @@
#include <linux/cpu.h>
#include <linux/pagemap.h>
-#include <asm/fpu/internal.h>
#include <asm/fpu/signal.h>
#include <asm/fpu/regset.h>
#include <asm/fpu/xstate.h>
#include <asm/sigframe.h>
+#include <asm/trapnr.h>
#include <asm/trace/fpu.h>
-static struct _fpx_sw_bytes fx_sw_reserved __ro_after_init;
-static struct _fpx_sw_bytes fx_sw_reserved_ia32 __ro_after_init;
+#include "context.h"
+#include "internal.h"
+#include "legacy.h"
+#include "xstate.h"
/*
* Check for the presence of extended state information in the
* user fpstate pointer in the sigcontext.
*/
-static inline int check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
- struct _fpx_sw_bytes *fx_sw)
+static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
+ struct _fpx_sw_bytes *fx_sw)
{
int min_xstate_size = sizeof(struct fxregs_state) +
sizeof(struct xstate_header);
@@ -31,12 +33,12 @@ static inline int check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
unsigned int magic2;
if (__copy_from_user(fx_sw, &fxbuf->sw_reserved[0], sizeof(*fx_sw)))
- return -EFAULT;
+ return false;
/* Check for the first magic field and other error scenarios. */
if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
fx_sw->xstate_size < min_xstate_size ||
- fx_sw->xstate_size > fpu_user_xstate_size ||
+ fx_sw->xstate_size > current->thread.fpu.fpstate->user_size ||
fx_sw->xstate_size > fx_sw->extended_size)
goto setfx;
@@ -47,10 +49,10 @@ static inline int check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
* in the memory layout.
*/
if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)))
- return -EFAULT;
+ return false;
if (likely(magic2 == FP_XSTATE_MAGIC2))
- return 0;
+ return true;
setfx:
trace_x86_fpu_xstate_check_failed(&current->thread.fpu);
@@ -58,22 +60,22 @@ setfx:
fx_sw->magic1 = 0;
fx_sw->xstate_size = sizeof(struct fxregs_state);
fx_sw->xfeatures = XFEATURE_MASK_FPSSE;
- return 0;
+ return true;
}
/*
* Signal frame handlers.
*/
-static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
+static inline bool save_fsave_header(struct task_struct *tsk, void __user *buf)
{
if (use_fxsr()) {
- struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+ struct xregs_state *xsave = &tsk->thread.fpu.fpstate->regs.xsave;
struct user_i387_ia32_struct env;
struct _fpstate_32 __user *fp = buf;
fpregs_lock();
if (!test_thread_flag(TIF_NEED_FPU_LOAD))
- fxsave(&tsk->thread.fpu.state.fxsave);
+ fxsave(&tsk->thread.fpu.fpstate->regs.fxsave);
fpregs_unlock();
convert_from_fxsr(&env, tsk);
@@ -81,33 +83,54 @@ static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
if (__copy_to_user(buf, &env, sizeof(env)) ||
__put_user(xsave->i387.swd, &fp->status) ||
__put_user(X86_FXSR_MAGIC, &fp->magic))
- return -1;
+ return false;
} else {
struct fregs_state __user *fp = buf;
u32 swd;
+
if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
- return -1;
+ return false;
}
- return 0;
+ return true;
+}
+
+/*
+ * Prepare the SW reserved portion of the fxsave memory layout, indicating
+ * the presence of the extended state information in the memory layout
+ * pointed to by the fpstate pointer in the sigcontext.
+ * This is saved when ever the FP and extended state context is
+ * saved on the user stack during the signal handler delivery to the user.
+ */
+static inline void save_sw_bytes(struct _fpx_sw_bytes *sw_bytes, bool ia32_frame,
+ struct fpstate *fpstate)
+{
+ sw_bytes->magic1 = FP_XSTATE_MAGIC1;
+ sw_bytes->extended_size = fpstate->user_size + FP_XSTATE_MAGIC2_SIZE;
+ sw_bytes->xfeatures = fpstate->user_xfeatures;
+ sw_bytes->xstate_size = fpstate->user_size;
+
+ if (ia32_frame)
+ sw_bytes->extended_size += sizeof(struct fregs_state);
}
-static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
+static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
+ struct fpstate *fpstate)
{
struct xregs_state __user *x = buf;
- struct _fpx_sw_bytes *sw_bytes;
+ struct _fpx_sw_bytes sw_bytes;
u32 xfeatures;
int err;
/* Setup the bytes not touched by the [f]xsave and reserved for SW. */
- sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
- err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
+ save_sw_bytes(&sw_bytes, ia32_frame, fpstate);
+ err = __copy_to_user(&x->i387.sw_reserved, &sw_bytes, sizeof(sw_bytes));
if (!use_xsave())
- return err;
+ return !err;
err |= __put_user(FP_XSTATE_MAGIC2,
- (__u32 __user *)(buf + fpu_user_xstate_size));
+ (__u32 __user *)(buf + fpstate->user_size));
/*
* Read the xfeatures which we copied (directly from the cpu or
@@ -130,23 +153,17 @@ static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
err |= __put_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
- return err;
+ return !err;
}
static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
{
- int err;
-
if (use_xsave())
- err = xsave_to_user_sigframe(buf);
- else if (use_fxsr())
- err = fxsave_to_user_sigframe((struct fxregs_state __user *) buf);
+ return xsave_to_user_sigframe(buf);
+ if (use_fxsr())
+ return fxsave_to_user_sigframe((struct fxregs_state __user *) buf);
else
- err = fnsave_to_user_sigframe((struct fregs_state __user *) buf);
-
- if (unlikely(err) && __clear_user(buf, fpu_user_xstate_size))
- err = -EFAULT;
- return err;
+ return fnsave_to_user_sigframe((struct fregs_state __user *) buf);
}
/*
@@ -159,10 +176,8 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
* buf == buf_fx for 64-bit frames and 32-bit fsave frame.
* buf != buf_fx for 32-bit frames with fxstate.
*
- * Try to save it directly to the user frame with disabled page fault handler.
- * If this fails then do the slow path where the FPU state is first saved to
- * task's fpu->state and then copy it to the user frame pointed to by the
- * aligned pointer 'buf_fx'.
+ * Save it directly to the user frame with disabled page fault handler. If
+ * that faults, try to clear the frame which handles the page fault.
*
* If this is a 32-bit frame with fxstate, put a fsave header before
* the aligned state at 'buf_fx'.
@@ -170,10 +185,11 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
* For [f]xsave state, update the SW reserved fields in the [f]xsave frame
* indicating the absence/presence of the extended state to the user.
*/
-int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
+bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
{
struct task_struct *tsk = current;
- int ia32_fxstate = (buf != buf_fx);
+ struct fpstate *fpstate = tsk->thread.fpu.fpstate;
+ bool ia32_fxstate = (buf != buf_fx);
int ret;
ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) ||
@@ -181,13 +197,25 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
if (!static_cpu_has(X86_FEATURE_FPU)) {
struct user_i387_ia32_struct fp;
+
fpregs_soft_get(current, NULL, (struct membuf){.p = &fp,
.left = sizeof(fp)});
- return copy_to_user(buf, &fp, sizeof(fp)) ? -EFAULT : 0;
+ return !copy_to_user(buf, &fp, sizeof(fp));
}
if (!access_ok(buf, size))
- return -EACCES;
+ return false;
+
+ if (use_xsave()) {
+ struct xregs_state __user *xbuf = buf_fx;
+
+ /*
+ * Clear the xsave header first, so that reserved fields are
+ * initialized to zero.
+ */
+ if (__clear_user(&xbuf->header, sizeof(xbuf->header)))
+ return false;
+ }
retry:
/*
* Load the FPU registers if they are not valid for the current task.
@@ -205,26 +233,26 @@ retry:
fpregs_unlock();
if (ret) {
- if (!fault_in_pages_writeable(buf_fx, fpu_user_xstate_size))
+ if (!__clear_user(buf_fx, fpstate->user_size))
goto retry;
- return -EFAULT;
+ return false;
}
/* Save the fsave header for the 32-bit frames. */
- if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
- return -1;
+ if ((ia32_fxstate || !use_fxsr()) && !save_fsave_header(tsk, buf))
+ return false;
- if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
- return -1;
+ if (use_fxsr() && !save_xstate_epilog(buf_fx, ia32_fxstate, fpstate))
+ return false;
- return 0;
+ return true;
}
-static int __restore_fpregs_from_user(void __user *buf, u64 xrestore,
- bool fx_only)
+static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures,
+ u64 xrestore, bool fx_only)
{
if (use_xsave()) {
- u64 init_bv = xfeatures_mask_uabi() & ~xrestore;
+ u64 init_bv = ufeatures & ~xrestore;
int ret;
if (likely(!fx_only))
@@ -233,7 +261,7 @@ static int __restore_fpregs_from_user(void __user *buf, u64 xrestore,
ret = fxrstor_from_user_sigframe(buf);
if (!ret && unlikely(init_bv))
- os_xrstor(&init_fpstate.xsave, init_bv);
+ os_xrstor(&init_fpstate, init_bv);
return ret;
} else if (use_fxsr()) {
return fxrstor_from_user_sigframe(buf);
@@ -246,16 +274,19 @@ static int __restore_fpregs_from_user(void __user *buf, u64 xrestore,
* Attempt to restore the FPU registers directly from user memory.
* Pagefaults are handled and any errors returned are fatal.
*/
-static int restore_fpregs_from_user(void __user *buf, u64 xrestore,
- bool fx_only, unsigned int size)
+static bool restore_fpregs_from_user(void __user *buf, u64 xrestore,
+ bool fx_only, unsigned int size)
{
struct fpu *fpu = &current->thread.fpu;
int ret;
retry:
fpregs_lock();
+ /* Ensure that XFD is up to date */
+ xfd_update_state(fpu->fpstate);
pagefault_disable();
- ret = __restore_fpregs_from_user(buf, xrestore, fx_only);
+ ret = __restore_fpregs_from_user(buf, fpu->fpstate->user_xfeatures,
+ xrestore, fx_only);
pagefault_enable();
if (unlikely(ret)) {
@@ -275,13 +306,12 @@ retry:
fpregs_unlock();
/* Try to handle #PF, but anything else is fatal. */
- if (ret != -EFAULT)
- return -EINVAL;
+ if (ret != X86_TRAP_PF)
+ return false;
- ret = fault_in_pages_readable(buf, size);
- if (!ret)
+ if (!fault_in_pages_readable(buf, size))
goto retry;
- return ret;
+ return false;
}
/*
@@ -294,45 +324,40 @@ retry:
* been restored from a user buffer directly.
*/
if (test_thread_flag(TIF_NEED_FPU_LOAD) && xfeatures_mask_supervisor())
- os_xrstor(&fpu->state.xsave, xfeatures_mask_supervisor());
+ os_xrstor_supervisor(fpu->fpstate);
fpregs_mark_activate();
fpregs_unlock();
- return 0;
+ return true;
}
-static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
- bool ia32_fxstate)
+static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
+ bool ia32_fxstate)
{
- int state_size = fpu_kernel_xstate_size;
struct task_struct *tsk = current;
struct fpu *fpu = &tsk->thread.fpu;
struct user_i387_ia32_struct env;
+ bool success, fx_only = false;
+ union fpregs_state *fpregs;
+ unsigned int state_size;
u64 user_xfeatures = 0;
- bool fx_only = false;
- int ret;
if (use_xsave()) {
struct _fpx_sw_bytes fx_sw_user;
- ret = check_xstate_in_sigframe(buf_fx, &fx_sw_user);
- if (unlikely(ret))
- return ret;
+ if (!check_xstate_in_sigframe(buf_fx, &fx_sw_user))
+ return false;
fx_only = !fx_sw_user.magic1;
state_size = fx_sw_user.xstate_size;
user_xfeatures = fx_sw_user.xfeatures;
} else {
user_xfeatures = XFEATURE_MASK_FPSSE;
+ state_size = fpu->fpstate->user_size;
}
if (likely(!ia32_fxstate)) {
- /*
- * Attempt to restore the FPU registers directly from user
- * memory. For that to succeed, the user access cannot cause page
- * faults. If it does, fall back to the slow path below, going
- * through the kernel buffer with the enabled pagefault handler.
- */
+ /* Restore the FPU registers directly from user memory. */
return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only,
state_size);
}
@@ -342,9 +367,8 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
* to be ignored for histerical raisins. The legacy state is folded
* in once the larger state has been copied.
*/
- ret = __copy_from_user(&env, buf, sizeof(env));
- if (ret)
- return ret;
+ if (__copy_from_user(&env, buf, sizeof(env)))
+ return false;
/*
* By setting TIF_NEED_FPU_LOAD it is ensured that our xstate is
@@ -363,38 +387,38 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
* the right place in memory. It's ia32 mode. Shrug.
*/
if (xfeatures_mask_supervisor())
- os_xsave(&fpu->state.xsave);
+ os_xsave(fpu->fpstate);
set_thread_flag(TIF_NEED_FPU_LOAD);
}
__fpu_invalidate_fpregs_state(fpu);
__cpu_invalidate_fpregs_state();
fpregs_unlock();
+ fpregs = &fpu->fpstate->regs;
if (use_xsave() && !fx_only) {
- ret = copy_sigframe_from_user_to_xstate(&fpu->state.xsave, buf_fx);
- if (ret)
- return ret;
+ if (copy_sigframe_from_user_to_xstate(fpu->fpstate, buf_fx))
+ return false;
} else {
- if (__copy_from_user(&fpu->state.fxsave, buf_fx,
- sizeof(fpu->state.fxsave)))
- return -EFAULT;
+ if (__copy_from_user(&fpregs->fxsave, buf_fx,
+ sizeof(fpregs->fxsave)))
+ return false;
if (IS_ENABLED(CONFIG_X86_64)) {
/* Reject invalid MXCSR values. */
- if (fpu->state.fxsave.mxcsr & ~mxcsr_feature_mask)
- return -EINVAL;
+ if (fpregs->fxsave.mxcsr & ~mxcsr_feature_mask)
+ return false;
} else {
/* Mask invalid bits out for historical reasons (broken hardware). */
- fpu->state.fxsave.mxcsr &= mxcsr_feature_mask;
+ fpregs->fxsave.mxcsr &= mxcsr_feature_mask;
}
/* Enforce XFEATURE_MASK_FPSSE when XSAVE is enabled */
if (use_xsave())
- fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE;
+ fpregs->xsave.header.xfeatures |= XFEATURE_MASK_FPSSE;
}
/* Fold the legacy FP storage */
- convert_to_fxsr(&fpu->state.fxsave, &env);
+ convert_to_fxsr(&fpregs->fxsave, &env);
fpregs_lock();
if (use_xsave()) {
@@ -409,40 +433,45 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
*/
u64 mask = user_xfeatures | xfeatures_mask_supervisor();
- fpu->state.xsave.header.xfeatures &= mask;
- ret = os_xrstor_safe(&fpu->state.xsave, xfeatures_mask_all);
+ fpregs->xsave.header.xfeatures &= mask;
+ success = !os_xrstor_safe(fpu->fpstate,
+ fpu_kernel_cfg.max_features);
} else {
- ret = fxrstor_safe(&fpu->state.fxsave);
+ success = !fxrstor_safe(&fpregs->fxsave);
}
- if (likely(!ret))
+ if (likely(success))
fpregs_mark_activate();
fpregs_unlock();
- return ret;
+ return success;
}
-static inline int xstate_sigframe_size(void)
+
+static inline unsigned int xstate_sigframe_size(struct fpstate *fpstate)
{
- return use_xsave() ? fpu_user_xstate_size + FP_XSTATE_MAGIC2_SIZE :
- fpu_user_xstate_size;
+ unsigned int size = fpstate->user_size;
+
+ return use_xsave() ? size + FP_XSTATE_MAGIC2_SIZE : size;
}
/*
* Restore FPU state from a sigframe:
*/
-int fpu__restore_sig(void __user *buf, int ia32_frame)
+bool fpu__restore_sig(void __user *buf, int ia32_frame)
{
- unsigned int size = xstate_sigframe_size();
struct fpu *fpu = &current->thread.fpu;
void __user *buf_fx = buf;
bool ia32_fxstate = false;
- int ret;
+ bool success = false;
+ unsigned int size;
if (unlikely(!buf)) {
fpu__clear_user_states(fpu);
- return 0;
+ return true;
}
+ size = xstate_sigframe_size(fpu->fpstate);
+
ia32_frame &= (IS_ENABLED(CONFIG_X86_32) ||
IS_ENABLED(CONFIG_IA32_EMULATION));
@@ -456,30 +485,28 @@ int fpu__restore_sig(void __user *buf, int ia32_frame)
ia32_fxstate = true;
}
- if (!access_ok(buf, size)) {
- ret = -EACCES;
+ if (!access_ok(buf, size))
goto out;
- }
if (!IS_ENABLED(CONFIG_X86_64) && !cpu_feature_enabled(X86_FEATURE_FPU)) {
- ret = fpregs_soft_set(current, NULL, 0,
- sizeof(struct user_i387_ia32_struct),
- NULL, buf);
+ success = !fpregs_soft_set(current, NULL, 0,
+ sizeof(struct user_i387_ia32_struct),
+ NULL, buf);
} else {
- ret = __fpu_restore_sig(buf, buf_fx, ia32_fxstate);
+ success = __fpu_restore_sig(buf, buf_fx, ia32_fxstate);
}
out:
- if (unlikely(ret))
+ if (unlikely(!success))
fpu__clear_user_states(fpu);
- return ret;
+ return success;
}
unsigned long
fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
unsigned long *buf_fx, unsigned long *size)
{
- unsigned long frame_size = xstate_sigframe_size();
+ unsigned long frame_size = xstate_sigframe_size(current->thread.fpu.fpstate);
*buf_fx = sp = round_down(sp - frame_size, 64);
if (ia32_frame && use_fxsr()) {
@@ -492,9 +519,12 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
return sp;
}
-unsigned long fpu__get_fpstate_size(void)
+unsigned long __init fpu__get_fpstate_size(void)
{
- unsigned long ret = xstate_sigframe_size();
+ unsigned long ret = fpu_user_cfg.max_size;
+
+ if (use_xsave())
+ ret += FP_XSTATE_MAGIC2_SIZE;
/*
* This space is needed on (most) 32-bit kernels, or when a 32-bit
@@ -510,28 +540,3 @@ unsigned long fpu__get_fpstate_size(void)
return ret;
}
-/*
- * Prepare the SW reserved portion of the fxsave memory layout, indicating
- * the presence of the extended state information in the memory layout
- * pointed by the fpstate pointer in the sigcontext.
- * This will be saved when ever the FP and extended state context is
- * saved on the user stack during the signal handler delivery to the user.
- */
-void fpu__init_prepare_fx_sw_frame(void)
-{
- int size = fpu_user_xstate_size + FP_XSTATE_MAGIC2_SIZE;
-
- fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
- fx_sw_reserved.extended_size = size;
- fx_sw_reserved.xfeatures = xfeatures_mask_uabi();
- fx_sw_reserved.xstate_size = fpu_user_xstate_size;
-
- if (IS_ENABLED(CONFIG_IA32_EMULATION) ||
- IS_ENABLED(CONFIG_X86_32)) {
- int fsave_header_size = sizeof(struct fregs_state);
-
- fx_sw_reserved_ia32 = fx_sw_reserved;
- fx_sw_reserved_ia32.extended_size = size + fsave_header_size;
- }
-}
-
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index c8def1b7f8fb..d28829403ed0 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -4,21 +4,33 @@
*
* Author: Suresh Siddha <suresh.b.siddha@intel.com>
*/
+#include <linux/bitops.h>
#include <linux/compat.h>
#include <linux/cpu.h>
#include <linux/mman.h>
+#include <linux/nospec.h>
#include <linux/pkeys.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
+#include <linux/vmalloc.h>
#include <asm/fpu/api.h>
-#include <asm/fpu/internal.h>
-#include <asm/fpu/signal.h>
#include <asm/fpu/regset.h>
-#include <asm/fpu/xstate.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/xcr.h>
#include <asm/tlbflush.h>
-#include <asm/cpufeature.h>
+#include <asm/prctl.h>
+#include <asm/elf.h>
+
+#include "context.h"
+#include "internal.h"
+#include "legacy.h"
+#include "xstate.h"
+
+#define for_each_extended_xfeature(bit, mask) \
+ (bit) = FIRST_EXTENDED_XFEATURE; \
+ for_each_set_bit_from(bit, (unsigned long *)&(mask), 8 * sizeof(mask))
/*
* Although we spell it out in here, the Processor Trace
@@ -39,29 +51,32 @@ static const char *xfeature_names[] =
"Protection Keys User registers",
"PASID state",
"unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "AMX Tile config" ,
+ "AMX Tile data" ,
+ "unknown xstate feature" ,
};
-static short xsave_cpuid_features[] __initdata = {
- X86_FEATURE_FPU,
- X86_FEATURE_XMM,
- X86_FEATURE_AVX,
- X86_FEATURE_MPX,
- X86_FEATURE_MPX,
- X86_FEATURE_AVX512F,
- X86_FEATURE_AVX512F,
- X86_FEATURE_AVX512F,
- X86_FEATURE_INTEL_PT,
- X86_FEATURE_PKU,
- X86_FEATURE_ENQCMD,
+static unsigned short xsave_cpuid_features[] __initdata = {
+ [XFEATURE_FP] = X86_FEATURE_FPU,
+ [XFEATURE_SSE] = X86_FEATURE_XMM,
+ [XFEATURE_YMM] = X86_FEATURE_AVX,
+ [XFEATURE_BNDREGS] = X86_FEATURE_MPX,
+ [XFEATURE_BNDCSR] = X86_FEATURE_MPX,
+ [XFEATURE_OPMASK] = X86_FEATURE_AVX512F,
+ [XFEATURE_ZMM_Hi256] = X86_FEATURE_AVX512F,
+ [XFEATURE_Hi16_ZMM] = X86_FEATURE_AVX512F,
+ [XFEATURE_PT_UNIMPLEMENTED_SO_FAR] = X86_FEATURE_INTEL_PT,
+ [XFEATURE_PKRU] = X86_FEATURE_PKU,
+ [XFEATURE_PASID] = X86_FEATURE_ENQCMD,
+ [XFEATURE_XTILE_CFG] = X86_FEATURE_AMX_TILE,
+ [XFEATURE_XTILE_DATA] = X86_FEATURE_AMX_TILE,
};
-/*
- * This represents the full set of bits that should ever be set in a kernel
- * XSAVE buffer, both supervisor and user xstates.
- */
-u64 xfeatures_mask_all __ro_after_init;
-EXPORT_SYMBOL_GPL(xfeatures_mask_all);
-
static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init =
{ [ 0 ... XFEATURE_MAX - 1] = -1};
static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init =
@@ -72,20 +87,13 @@ static unsigned int xstate_supervisor_only_offsets[XFEATURE_MAX] __ro_after_init
{ [ 0 ... XFEATURE_MAX - 1] = -1};
/*
- * The XSAVE area of kernel can be in standard or compacted format;
- * it is always in standard format for user mode. This is the user
- * mode standard format size used for signal and ptrace frames.
- */
-unsigned int fpu_user_xstate_size __ro_after_init;
-
-/*
* Return whether the system supports a given xfeature.
*
* Also return the name of the (most advanced) feature that the caller requested:
*/
int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
{
- u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask_all;
+ u64 xfeatures_missing = xfeatures_needed & ~fpu_kernel_cfg.max_features;
if (unlikely(feature_name)) {
long xfeature_idx, max_idx;
@@ -135,17 +143,26 @@ static bool xfeature_is_supervisor(int xfeature_nr)
*/
void fpu__init_cpu_xstate(void)
{
- if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask_all)
+ if (!boot_cpu_has(X86_FEATURE_XSAVE) || !fpu_kernel_cfg.max_features)
return;
cr4_set_bits(X86_CR4_OSXSAVE);
/*
+ * Must happen after CR4 setup and before xsetbv() to allow KVM
+ * lazy passthrough. Write independent of the dynamic state static
+ * key as that does not work on the boot CPU. This also ensures
+ * that any stale state is wiped out from XFD.
+ */
+ if (cpu_feature_enabled(X86_FEATURE_XFD))
+ wrmsrl(MSR_IA32_XFD, init_fpstate.xfd);
+
+ /*
* XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features
* managed by XSAVE{C, OPT, S} and XRSTOR{S}. Only XSAVE user
* states can be set here.
*/
- xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_uabi());
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, fpu_user_cfg.max_features);
/*
* MSR_IA32_XSS sets supervisor states managed by XSAVES.
@@ -158,7 +175,7 @@ void fpu__init_cpu_xstate(void)
static bool xfeature_enabled(enum xfeature xfeature)
{
- return xfeatures_mask_all & BIT_ULL(xfeature);
+ return fpu_kernel_cfg.max_features & BIT_ULL(xfeature);
}
/*
@@ -184,10 +201,7 @@ static void __init setup_xstate_features(void)
xstate_sizes[XFEATURE_SSE] = sizeof_field(struct fxregs_state,
xmm_space);
- for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
- if (!xfeature_enabled(i))
- continue;
-
+ for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
xstate_sizes[i] = eax;
@@ -236,6 +250,8 @@ static void __init print_xstate_features(void)
print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
print_xstate_feature(XFEATURE_MASK_PKRU);
print_xstate_feature(XFEATURE_MASK_PASID);
+ print_xstate_feature(XFEATURE_MASK_XTILE_CFG);
+ print_xstate_feature(XFEATURE_MASK_XTILE_DATA);
}
/*
@@ -291,20 +307,15 @@ static void __init setup_xstate_comp_offsets(void)
xstate_comp_offsets[XFEATURE_SSE] = offsetof(struct fxregs_state,
xmm_space);
- if (!boot_cpu_has(X86_FEATURE_XSAVES)) {
- for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
- if (xfeature_enabled(i))
- xstate_comp_offsets[i] = xstate_offsets[i];
- }
+ if (!cpu_feature_enabled(X86_FEATURE_XSAVES)) {
+ for_each_extended_xfeature(i, fpu_kernel_cfg.max_features)
+ xstate_comp_offsets[i] = xstate_offsets[i];
return;
}
next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE;
- for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
- if (!xfeature_enabled(i))
- continue;
-
+ for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
if (xfeature_is_aligned(i))
next_offset = ALIGN(next_offset, 64);
@@ -328,8 +339,8 @@ static void __init setup_supervisor_only_offsets(void)
next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE;
- for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
- if (!xfeature_enabled(i) || !xfeature_is_supervisor(i))
+ for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
+ if (!xfeature_is_supervisor(i))
continue;
if (xfeature_is_aligned(i))
@@ -347,15 +358,36 @@ static void __init print_xstate_offset_size(void)
{
int i;
- for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
- if (!xfeature_enabled(i))
- continue;
+ for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
pr_info("x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d\n",
i, xstate_comp_offsets[i], i, xstate_sizes[i]);
}
}
/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static __init void os_xrstor_booting(struct xregs_state *xstate)
+{
+ u64 mask = fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSTATE;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err;
+
+ if (cpu_feature_enabled(X86_FEATURE_XSAVES))
+ XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
+ else
+ XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+
+ /*
+ * We should never fault when copying from a kernel buffer, and the FPU
+ * state we set at boot time should be valid.
+ */
+ WARN_ON_FPU(err);
+}
+
+/*
* All supported features have either init state all zeros or are
* handled in setup_init_fpu() individually. This is an explicit
* feature list and does not use XFEATURE_MASK*SUPPORTED to catch
@@ -372,36 +404,30 @@ static void __init print_xstate_offset_size(void)
XFEATURE_MASK_PKRU | \
XFEATURE_MASK_BNDREGS | \
XFEATURE_MASK_BNDCSR | \
- XFEATURE_MASK_PASID)
+ XFEATURE_MASK_PASID | \
+ XFEATURE_MASK_XTILE)
/*
* setup the xstate image representing the init state
*/
static void __init setup_init_fpu_buf(void)
{
- static int on_boot_cpu __initdata = 1;
-
BUILD_BUG_ON((XFEATURE_MASK_USER_SUPPORTED |
XFEATURE_MASK_SUPERVISOR_SUPPORTED) !=
XFEATURES_INIT_FPSTATE_HANDLED);
- WARN_ON_FPU(!on_boot_cpu);
- on_boot_cpu = 0;
-
if (!boot_cpu_has(X86_FEATURE_XSAVE))
return;
setup_xstate_features();
print_xstate_features();
- if (boot_cpu_has(X86_FEATURE_XSAVES))
- init_fpstate.xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT |
- xfeatures_mask_all;
+ xstate_init_xcomp_bv(&init_fpstate.regs.xsave, fpu_kernel_cfg.max_features);
/*
* Init all the features state with header.xfeatures being 0x0
*/
- os_xrstor_booting(&init_fpstate.xsave);
+ os_xrstor_booting(&init_fpstate.regs.xsave);
/*
* All components are now in init state. Read the state back so
@@ -419,7 +445,7 @@ static void __init setup_init_fpu_buf(void)
* state is all zeroes or if not to add the necessary handling
* here.
*/
- fxsave(&init_fpstate.fxsave);
+ fxsave(&init_fpstate.regs.fxsave);
}
static int xfeature_uncompacted_offset(int xfeature_nr)
@@ -451,10 +477,11 @@ int xfeature_size(int xfeature_nr)
}
/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
-static int validate_user_xstate_header(const struct xstate_header *hdr)
+static int validate_user_xstate_header(const struct xstate_header *hdr,
+ struct fpstate *fpstate)
{
/* No unknown or supervisor features may be set */
- if (hdr->xfeatures & ~xfeatures_mask_uabi())
+ if (hdr->xfeatures & ~fpstate->user_xfeatures)
return -EINVAL;
/* Userspace must use the uncompacted format */
@@ -474,7 +501,7 @@ static int validate_user_xstate_header(const struct xstate_header *hdr)
return 0;
}
-static void __xstate_dump_leaves(void)
+static void __init __xstate_dump_leaves(void)
{
int i;
u32 eax, ebx, ecx, edx;
@@ -509,12 +536,73 @@ static void __xstate_dump_leaves(void)
} \
} while (0)
+/**
+ * check_xtile_data_against_struct - Check tile data state size.
+ *
+ * Calculate the state size by multiplying the single tile size which is
+ * recorded in a C struct, and the number of tiles that the CPU informs.
+ * Compare the provided size with the calculation.
+ *
+ * @size: The tile data state size
+ *
+ * Returns: 0 on success, -EINVAL on mismatch.
+ */
+static int __init check_xtile_data_against_struct(int size)
+{
+ u32 max_palid, palid, state_size;
+ u32 eax, ebx, ecx, edx;
+ u16 max_tile;
+
+ /*
+ * Check the maximum palette id:
+ * eax: the highest numbered palette subleaf.
+ */
+ cpuid_count(TILE_CPUID, 0, &max_palid, &ebx, &ecx, &edx);
+
+ /*
+ * Cross-check each tile size and find the maximum number of
+ * supported tiles.
+ */
+ for (palid = 1, max_tile = 0; palid <= max_palid; palid++) {
+ u16 tile_size, max;
+
+ /*
+ * Check the tile size info:
+ * eax[31:16]: bytes per title
+ * ebx[31:16]: the max names (or max number of tiles)
+ */
+ cpuid_count(TILE_CPUID, palid, &eax, &ebx, &edx, &edx);
+ tile_size = eax >> 16;
+ max = ebx >> 16;
+
+ if (tile_size != sizeof(struct xtile_data)) {
+ pr_err("%s: struct is %zu bytes, cpu xtile %d bytes\n",
+ __stringify(XFEATURE_XTILE_DATA),
+ sizeof(struct xtile_data), tile_size);
+ __xstate_dump_leaves();
+ return -EINVAL;
+ }
+
+ if (max > max_tile)
+ max_tile = max;
+ }
+
+ state_size = sizeof(struct xtile_data) * max_tile;
+ if (size != state_size) {
+ pr_err("%s: calculated size is %u bytes, cpu state %d bytes\n",
+ __stringify(XFEATURE_XTILE_DATA), state_size, size);
+ __xstate_dump_leaves();
+ return -EINVAL;
+ }
+ return 0;
+}
+
/*
* We have a C struct for each 'xstate'. We need to ensure
* that our software representation matches what the CPU
* tells us about the state's size.
*/
-static void check_xstate_against_struct(int nr)
+static bool __init check_xstate_against_struct(int nr)
{
/*
* Ask the CPU for the size of the state.
@@ -532,6 +620,11 @@ static void check_xstate_against_struct(int nr)
XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state);
XCHECK_SZ(sz, nr, XFEATURE_PKRU, struct pkru_state);
XCHECK_SZ(sz, nr, XFEATURE_PASID, struct ia32_pasid_state);
+ XCHECK_SZ(sz, nr, XFEATURE_XTILE_CFG, struct xtile_cfg);
+
+ /* The tile data size varies between implementations. */
+ if (nr == XFEATURE_XTILE_DATA)
+ check_xtile_data_against_struct(sz);
/*
* Make *SURE* to add any feature numbers in below if
@@ -541,10 +634,39 @@ static void check_xstate_against_struct(int nr)
if ((nr < XFEATURE_YMM) ||
(nr >= XFEATURE_MAX) ||
(nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) ||
- ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_LBR))) {
+ ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_RSRVD_COMP_16))) {
WARN_ONCE(1, "no structure for xstate: %d\n", nr);
XSTATE_WARN_ON(1);
+ return false;
+ }
+ return true;
+}
+
+static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted)
+{
+ unsigned int size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+ int i;
+
+ for_each_extended_xfeature(i, xfeatures) {
+ /* Align from the end of the previous feature */
+ if (xfeature_is_aligned(i))
+ size = ALIGN(size, 64);
+ /*
+ * In compacted format the enabled features are packed,
+ * i.e. disabled features do not occupy space.
+ *
+ * In non-compacted format the offsets are fixed and
+ * disabled states still occupy space in the memory buffer.
+ */
+ if (!compacted)
+ size = xfeature_uncompacted_offset(i);
+ /*
+ * Add the feature size even for non-compacted format
+ * to make the end result correct
+ */
+ size += xfeature_size(i);
}
+ return size;
}
/*
@@ -556,44 +678,29 @@ static void check_xstate_against_struct(int nr)
* covered by these checks. Only the size of the buffer for task->fpu
* is checked here.
*/
-static void do_extra_xstate_size_checks(void)
+static bool __init paranoid_xstate_size_valid(unsigned int kernel_size)
{
- int paranoid_xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+ bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES);
+ unsigned int size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
int i;
- for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
- if (!xfeature_enabled(i))
- continue;
-
- check_xstate_against_struct(i);
+ for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
+ if (!check_xstate_against_struct(i))
+ return false;
/*
* Supervisor state components can be managed only by
* XSAVES.
*/
- if (!cpu_feature_enabled(X86_FEATURE_XSAVES))
- XSTATE_WARN_ON(xfeature_is_supervisor(i));
-
- /* Align from the end of the previous feature */
- if (xfeature_is_aligned(i))
- paranoid_xstate_size = ALIGN(paranoid_xstate_size, 64);
- /*
- * The offset of a given state in the non-compacted
- * format is given to us in a CPUID leaf. We check
- * them for being ordered (increasing offsets) in
- * setup_xstate_features(). XSAVES uses compacted format.
- */
- if (!cpu_feature_enabled(X86_FEATURE_XSAVES))
- paranoid_xstate_size = xfeature_uncompacted_offset(i);
- /*
- * The compacted-format offset always depends on where
- * the previous state ended.
- */
- paranoid_xstate_size += xfeature_size(i);
+ if (!compacted && xfeature_is_supervisor(i)) {
+ XSTATE_WARN_ON(1);
+ return false;
+ }
}
- XSTATE_WARN_ON(paranoid_xstate_size != fpu_kernel_xstate_size);
+ size = xstate_calculate_size(fpu_kernel_cfg.max_features, compacted);
+ XSTATE_WARN_ON(size != kernel_size);
+ return size == kernel_size;
}
-
/*
* Get total size of enabled xstates in XCR0 | IA32_XSS.
*
@@ -644,7 +751,7 @@ static unsigned int __init get_xsaves_size_no_independent(void)
return size;
}
-static unsigned int __init get_xsave_size(void)
+static unsigned int __init get_xsave_size_user(void)
{
unsigned int eax, ebx, ecx, edx;
/*
@@ -662,44 +769,54 @@ static unsigned int __init get_xsave_size(void)
* Will the runtime-enumerated 'xstate_size' fit in the init
* task's statically-allocated buffer?
*/
-static bool is_supported_xstate_size(unsigned int test_xstate_size)
+static bool __init is_supported_xstate_size(unsigned int test_xstate_size)
{
- if (test_xstate_size <= sizeof(union fpregs_state))
+ if (test_xstate_size <= sizeof(init_fpstate.regs))
return true;
pr_warn("x86/fpu: xstate buffer too small (%zu < %d), disabling xsave\n",
- sizeof(union fpregs_state), test_xstate_size);
+ sizeof(init_fpstate.regs), test_xstate_size);
return false;
}
static int __init init_xstate_size(void)
{
/* Recompute the context size for enabled features: */
- unsigned int possible_xstate_size;
- unsigned int xsave_size;
+ unsigned int user_size, kernel_size, kernel_default_size;
+ bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES);
- xsave_size = get_xsave_size();
+ /* Uncompacted user space size */
+ user_size = get_xsave_size_user();
- if (boot_cpu_has(X86_FEATURE_XSAVES))
- possible_xstate_size = get_xsaves_size_no_independent();
+ /*
+ * XSAVES kernel size includes supervisor states and
+ * uses compacted format when available.
+ *
+ * XSAVE does not support supervisor states so
+ * kernel and user size is identical.
+ */
+ if (compacted)
+ kernel_size = get_xsaves_size_no_independent();
else
- possible_xstate_size = xsave_size;
+ kernel_size = user_size;
+
+ kernel_default_size =
+ xstate_calculate_size(fpu_kernel_cfg.default_features, compacted);
- /* Ensure we have the space to store all enabled: */
- if (!is_supported_xstate_size(possible_xstate_size))
+ /* Ensure we have the space to store all default enabled features. */
+ if (!is_supported_xstate_size(kernel_default_size))
return -EINVAL;
- /*
- * The size is OK, we are definitely going to use xsave,
- * make it known to the world that we need more space.
- */
- fpu_kernel_xstate_size = possible_xstate_size;
- do_extra_xstate_size_checks();
+ if (!paranoid_xstate_size_valid(kernel_size))
+ return -EINVAL;
+
+ fpu_kernel_cfg.max_size = kernel_size;
+ fpu_user_cfg.max_size = user_size;
+
+ fpu_kernel_cfg.default_size = kernel_default_size;
+ fpu_user_cfg.default_size =
+ xstate_calculate_size(fpu_user_cfg.default_features, false);
- /*
- * User space is always in standard format.
- */
- fpu_user_xstate_size = xsave_size;
return 0;
}
@@ -707,28 +824,38 @@ static int __init init_xstate_size(void)
* We enabled the XSAVE hardware, but something went wrong and
* we can not use it. Disable it.
*/
-static void fpu__init_disable_system_xstate(void)
+static void __init fpu__init_disable_system_xstate(unsigned int legacy_size)
{
- xfeatures_mask_all = 0;
+ fpu_kernel_cfg.max_features = 0;
cr4_clear_bits(X86_CR4_OSXSAVE);
setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+
+ /* Restore the legacy size.*/
+ fpu_kernel_cfg.max_size = legacy_size;
+ fpu_kernel_cfg.default_size = legacy_size;
+ fpu_user_cfg.max_size = legacy_size;
+ fpu_user_cfg.default_size = legacy_size;
+
+ /*
+ * Prevent enabling the static branch which enables writes to the
+ * XFD MSR.
+ */
+ init_fpstate.xfd = 0;
+
+ fpstate_reset(&current->thread.fpu);
}
/*
* Enable and initialize the xsave feature.
* Called once per system bootup.
*/
-void __init fpu__init_system_xstate(void)
+void __init fpu__init_system_xstate(unsigned int legacy_size)
{
unsigned int eax, ebx, ecx, edx;
- static int on_boot_cpu __initdata = 1;
u64 xfeatures;
int err;
int i;
- WARN_ON_FPU(!on_boot_cpu);
- on_boot_cpu = 0;
-
if (!boot_cpu_has(X86_FEATURE_FPU)) {
pr_info("x86/fpu: No FPU detected\n");
return;
@@ -749,22 +876,22 @@ void __init fpu__init_system_xstate(void)
* Find user xstates supported by the processor.
*/
cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
- xfeatures_mask_all = eax + ((u64)edx << 32);
+ fpu_kernel_cfg.max_features = eax + ((u64)edx << 32);
/*
* Find supervisor xstates supported by the processor.
*/
cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx);
- xfeatures_mask_all |= ecx + ((u64)edx << 32);
+ fpu_kernel_cfg.max_features |= ecx + ((u64)edx << 32);
- if ((xfeatures_mask_uabi() & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
+ if ((fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
/*
* This indicates that something really unexpected happened
* with the enumeration. Disable XSAVE and try to continue
* booting without it. This is too early to BUG().
*/
pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n",
- xfeatures_mask_all);
+ fpu_kernel_cfg.max_features);
goto out_disable;
}
@@ -772,15 +899,39 @@ void __init fpu__init_system_xstate(void)
* Clear XSAVE features that are disabled in the normal CPUID.
*/
for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) {
- if (!boot_cpu_has(xsave_cpuid_features[i]))
- xfeatures_mask_all &= ~BIT_ULL(i);
+ unsigned short cid = xsave_cpuid_features[i];
+
+ /* Careful: X86_FEATURE_FPU is 0! */
+ if ((i != XFEATURE_FP && !cid) || !boot_cpu_has(cid))
+ fpu_kernel_cfg.max_features &= ~BIT_ULL(i);
}
- xfeatures_mask_all &= XFEATURE_MASK_USER_SUPPORTED |
+ if (!cpu_feature_enabled(X86_FEATURE_XFD))
+ fpu_kernel_cfg.max_features &= ~XFEATURE_MASK_USER_DYNAMIC;
+
+ fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED |
XFEATURE_MASK_SUPERVISOR_SUPPORTED;
+ fpu_user_cfg.max_features = fpu_kernel_cfg.max_features;
+ fpu_user_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED;
+
+ /* Clean out dynamic features from default */
+ fpu_kernel_cfg.default_features = fpu_kernel_cfg.max_features;
+ fpu_kernel_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC;
+
+ fpu_user_cfg.default_features = fpu_user_cfg.max_features;
+ fpu_user_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC;
+
/* Store it for paranoia check at the end */
- xfeatures = xfeatures_mask_all;
+ xfeatures = fpu_kernel_cfg.max_features;
+
+ /*
+ * Initialize the default XFD state in initfp_state and enable the
+ * dynamic sizing mechanism if dynamic states are available. The
+ * static key cannot be enabled here because this runs before
+ * jump_label_init(). This is delayed to an initcall.
+ */
+ init_fpstate.xfd = fpu_user_cfg.max_features & XFEATURE_MASK_USER_DYNAMIC;
/* Enable xstate instructions to be able to continue with initialization: */
fpu__init_cpu_xstate();
@@ -788,13 +939,16 @@ void __init fpu__init_system_xstate(void)
if (err)
goto out_disable;
+ /* Reset the state for the current task */
+ fpstate_reset(&current->thread.fpu);
+
/*
* Update info used for ptrace frames; use standard-format size and no
* supervisor xstates:
*/
- update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask_uabi());
+ update_regset_xstate_info(fpu_user_cfg.max_size,
+ fpu_user_cfg.max_features);
- fpu__init_prepare_fx_sw_frame();
setup_init_fpu_buf();
setup_xstate_comp_offsets();
setup_supervisor_only_offsets();
@@ -803,22 +957,22 @@ void __init fpu__init_system_xstate(void)
* Paranoia check whether something in the setup modified the
* xfeatures mask.
*/
- if (xfeatures != xfeatures_mask_all) {
+ if (xfeatures != fpu_kernel_cfg.max_features) {
pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init, disabling XSAVE\n",
- xfeatures, xfeatures_mask_all);
+ xfeatures, fpu_kernel_cfg.max_features);
goto out_disable;
}
print_xstate_offset_size();
pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
- xfeatures_mask_all,
- fpu_kernel_xstate_size,
+ fpu_kernel_cfg.max_features,
+ fpu_kernel_cfg.max_size,
boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard");
return;
out_disable:
/* something went wrong, try to boot without any XSAVE support */
- fpu__init_disable_system_xstate();
+ fpu__init_disable_system_xstate(legacy_size);
}
/*
@@ -830,7 +984,7 @@ void fpu__resume_cpu(void)
* Restore XCR0 on xsave capable CPUs:
*/
if (cpu_feature_enabled(X86_FEATURE_XSAVE))
- xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_uabi());
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, fpu_user_cfg.max_features);
/*
* Restore IA32_XSS. The same CPUID bit enumerates support
@@ -840,6 +994,9 @@ void fpu__resume_cpu(void)
wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
xfeatures_mask_independent());
}
+
+ if (fpu_state_size_dynamic())
+ wrmsrl(MSR_IA32_XFD, current->thread.fpu.fpstate->xfd);
}
/*
@@ -886,7 +1043,7 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
* We should not ever be requesting features that we
* have not enabled.
*/
- WARN_ONCE(!(xfeatures_mask_all & BIT_ULL(xfeature_nr)),
+ WARN_ONCE(!(fpu_kernel_cfg.max_features & BIT_ULL(xfeature_nr)),
"get of unsupported state");
/*
* This assumes the last 'xsave*' instruction to
@@ -904,7 +1061,6 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
return __raw_xsave_addr(xsave, xfeature_nr);
}
-EXPORT_SYMBOL_GPL(get_xsave_addr);
#ifdef CONFIG_ARCH_HAS_PKEYS
@@ -961,9 +1117,10 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
}
/**
- * copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer
+ * __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer
* @to: membuf descriptor
- * @tsk: The task from which to copy the saved xstate
+ * @fpstate: The fpstate buffer from which to copy
+ * @pkru_val: The PKRU value to store in the PKRU component
* @copy_mode: The requested copy mode
*
* Converts from kernel XSAVE or XSAVES compacted format to UABI conforming
@@ -972,14 +1129,15 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
*
* It supports partial copy but @to.pos always starts from zero.
*/
-void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
- enum xstate_copy_mode copy_mode)
+void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
+ u32 pkru_val, enum xstate_copy_mode copy_mode)
{
const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr);
- struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
- struct xregs_state *xinit = &init_fpstate.xsave;
+ struct xregs_state *xinit = &init_fpstate.regs.xsave;
+ struct xregs_state *xsave = &fpstate->regs.xsave;
struct xstate_header header;
unsigned int zerofrom;
+ u64 mask;
int i;
memset(&header, 0, sizeof(header));
@@ -996,7 +1154,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
break;
case XSTATE_COPY_XSAVE:
- header.xfeatures &= xfeatures_mask_uabi();
+ header.xfeatures &= fpstate->user_xfeatures;
break;
}
@@ -1033,17 +1191,15 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
zerofrom = offsetof(struct xregs_state, extended_state_area);
- for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
- /*
- * The ptrace buffer is in non-compacted XSAVE format.
- * In non-compacted format disabled features still occupy
- * state space, but there is no state to copy from in the
- * compacted init_fpstate. The gap tracking will zero this
- * later.
- */
- if (!(xfeatures_mask_uabi() & BIT_ULL(i)))
- continue;
+ /*
+ * The ptrace buffer is in non-compacted XSAVE format. In
+ * non-compacted format disabled features still occupy state space,
+ * but there is no state to copy from in the compacted
+ * init_fpstate. The gap tracking will zero these states.
+ */
+ mask = fpstate->user_xfeatures;
+ for_each_extended_xfeature(i, mask) {
/*
* If there was a feature or alignment gap, zero the space
* in the destination buffer.
@@ -1055,10 +1211,9 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
struct pkru_state pkru = {0};
/*
* PKRU is not necessarily up to date in the
- * thread's XSAVE buffer. Fill this part from the
- * per-thread storage.
+ * XSAVE buffer. Use the provided value.
*/
- pkru.pkru = tsk->thread.pkru;
+ pkru.pkru = pkru_val;
membuf_write(&to, &pkru, sizeof(pkru));
} else {
copy_feature(header.xfeatures & BIT_ULL(i), &to,
@@ -1078,6 +1233,25 @@ out:
membuf_zero(&to, to.left);
}
+/**
+ * copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer
+ * @to: membuf descriptor
+ * @tsk: The task from which to copy the saved xstate
+ * @copy_mode: The requested copy mode
+ *
+ * Converts from kernel XSAVE or XSAVES compacted format to UABI conforming
+ * format, i.e. from the kernel internal hardware dependent storage format
+ * to the requested @mode. UABI XSTATE is always uncompacted!
+ *
+ * It supports partial copy but @to.pos always starts from zero.
+ */
+void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
+ enum xstate_copy_mode copy_mode)
+{
+ __copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate,
+ tsk->thread.pkru, copy_mode);
+}
+
static int copy_from_buffer(void *dst, unsigned int offset, unsigned int size,
const void *kbuf, const void __user *ubuf)
{
@@ -1091,9 +1265,10 @@ static int copy_from_buffer(void *dst, unsigned int offset, unsigned int size,
}
-static int copy_uabi_to_xstate(struct xregs_state *xsave, const void *kbuf,
+static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf,
const void __user *ubuf)
{
+ struct xregs_state *xsave = &fpstate->regs.xsave;
unsigned int offset, size;
struct xstate_header hdr;
u64 mask;
@@ -1103,7 +1278,7 @@ static int copy_uabi_to_xstate(struct xregs_state *xsave, const void *kbuf,
if (copy_from_buffer(&hdr, offset, sizeof(hdr), kbuf, ubuf))
return -EFAULT;
- if (validate_user_xstate_header(&hdr))
+ if (validate_user_xstate_header(&hdr, fpstate))
return -EINVAL;
/* Validate MXCSR when any of the related features is in use */
@@ -1156,12 +1331,11 @@ static int copy_uabi_to_xstate(struct xregs_state *xsave, const void *kbuf,
/*
* Convert from a ptrace standard-format kernel buffer to kernel XSAVE[S]
- * format and copy to the target thread. This is called from
- * xstateregs_set().
+ * format and copy to the target thread. Used by ptrace and KVM.
*/
-int copy_uabi_from_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf)
+int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf)
{
- return copy_uabi_to_xstate(xsave, kbuf, NULL);
+ return copy_uabi_to_xstate(fpstate, kbuf, NULL);
}
/*
@@ -1169,26 +1343,20 @@ int copy_uabi_from_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf)
* XSAVE[S] format and copy to the target thread. This is called from the
* sigreturn() and rt_sigreturn() system calls.
*/
-int copy_sigframe_from_user_to_xstate(struct xregs_state *xsave,
+int copy_sigframe_from_user_to_xstate(struct fpstate *fpstate,
const void __user *ubuf)
{
- return copy_uabi_to_xstate(xsave, NULL, ubuf);
+ return copy_uabi_to_xstate(fpstate, NULL, ubuf);
}
-static bool validate_xsaves_xrstors(u64 mask)
+static bool validate_independent_components(u64 mask)
{
u64 xchk;
if (WARN_ON_FPU(!cpu_feature_enabled(X86_FEATURE_XSAVES)))
return false;
- /*
- * Validate that this is either a task->fpstate related component
- * subset or an independent one.
- */
- if (mask & xfeatures_mask_independent())
- xchk = ~xfeatures_mask_independent();
- else
- xchk = ~xfeatures_mask_all;
+
+ xchk = ~xfeatures_mask_independent();
if (WARN_ON_ONCE(!mask || mask & xchk))
return false;
@@ -1206,14 +1374,13 @@ static bool validate_xsaves_xrstors(u64 mask)
* buffer should be zeroed otherwise a consecutive XRSTORS from that buffer
* can #GP.
*
- * The feature mask must either be a subset of the independent features or
- * a subset of the task->fpstate related features.
+ * The feature mask must be a subset of the independent features.
*/
void xsaves(struct xregs_state *xstate, u64 mask)
{
int err;
- if (!validate_xsaves_xrstors(mask))
+ if (!validate_independent_components(mask))
return;
XSTATE_OP(XSAVES, xstate, (u32)mask, (u32)(mask >> 32), err);
@@ -1231,20 +1398,379 @@ void xsaves(struct xregs_state *xstate, u64 mask)
* Proper usage is to restore the state which was saved with
* xsaves() into @xstate.
*
- * The feature mask must either be a subset of the independent features or
- * a subset of the task->fpstate related features.
+ * The feature mask must be a subset of the independent features.
*/
void xrstors(struct xregs_state *xstate, u64 mask)
{
int err;
- if (!validate_xsaves_xrstors(mask))
+ if (!validate_independent_components(mask))
return;
XSTATE_OP(XRSTORS, xstate, (u32)mask, (u32)(mask >> 32), err);
WARN_ON_ONCE(err);
}
+#if IS_ENABLED(CONFIG_KVM)
+void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature)
+{
+ void *addr = get_xsave_addr(&fps->regs.xsave, xfeature);
+
+ if (addr)
+ memset(addr, 0, xstate_sizes[xfeature]);
+}
+EXPORT_SYMBOL_GPL(fpstate_clear_xstate_component);
+#endif
+
+#ifdef CONFIG_X86_64
+
+#ifdef CONFIG_X86_DEBUG_FPU
+/*
+ * Ensure that a subsequent XSAVE* or XRSTOR* instruction with RFBM=@mask
+ * can safely operate on the @fpstate buffer.
+ */
+static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor)
+{
+ u64 xfd = __this_cpu_read(xfd_state);
+
+ if (fpstate->xfd == xfd)
+ return true;
+
+ /*
+ * The XFD MSR does not match fpstate->xfd. That's invalid when
+ * the passed in fpstate is current's fpstate.
+ */
+ if (fpstate->xfd == current->thread.fpu.fpstate->xfd)
+ return false;
+
+ /*
+ * XRSTOR(S) from init_fpstate are always correct as it will just
+ * bring all components into init state and not read from the
+ * buffer. XSAVE(S) raises #PF after init.
+ */
+ if (fpstate == &init_fpstate)
+ return rstor;
+
+ /*
+ * XSAVE(S): clone(), fpu_swap_kvm_fpu()
+ * XRSTORS(S): fpu_swap_kvm_fpu()
+ */
+
+ /*
+ * No XSAVE/XRSTOR instructions (except XSAVE itself) touch
+ * the buffer area for XFD-disabled state components.
+ */
+ mask &= ~xfd;
+
+ /*
+ * Remove features which are valid in fpstate. They
+ * have space allocated in fpstate.
+ */
+ mask &= ~fpstate->xfeatures;
+
+ /*
+ * Any remaining state components in 'mask' might be written
+ * by XSAVE/XRSTOR. Fail validation it found.
+ */
+ return !mask;
+}
+
+void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor)
+{
+ WARN_ON_ONCE(!xstate_op_valid(fpstate, mask, rstor));
+}
+#endif /* CONFIG_X86_DEBUG_FPU */
+
+static int __init xfd_update_static_branch(void)
+{
+ /*
+ * If init_fpstate.xfd has bits set then dynamic features are
+ * available and the dynamic sizing must be enabled.
+ */
+ if (init_fpstate.xfd)
+ static_branch_enable(&__fpu_state_size_dynamic);
+ return 0;
+}
+arch_initcall(xfd_update_static_branch)
+
+void fpstate_free(struct fpu *fpu)
+{
+ if (fpu->fpstate && fpu->fpstate != &fpu->__fpstate)
+ vfree(fpu->fpstate);
+}
+
+/**
+ * fpu_install_fpstate - Update the active fpstate in the FPU
+ *
+ * @fpu: A struct fpu * pointer
+ * @newfps: A struct fpstate * pointer
+ *
+ * Returns: A null pointer if the last active fpstate is the embedded
+ * one or the new fpstate is already installed;
+ * otherwise, a pointer to the old fpstate which has to
+ * be freed by the caller.
+ */
+static struct fpstate *fpu_install_fpstate(struct fpu *fpu,
+ struct fpstate *newfps)
+{
+ struct fpstate *oldfps = fpu->fpstate;
+
+ if (fpu->fpstate == newfps)
+ return NULL;
+
+ fpu->fpstate = newfps;
+ return oldfps != &fpu->__fpstate ? oldfps : NULL;
+}
+
+/**
+ * fpstate_realloc - Reallocate struct fpstate for the requested new features
+ *
+ * @xfeatures: A bitmap of xstate features which extend the enabled features
+ * of that task
+ * @ksize: The required size for the kernel buffer
+ * @usize: The required size for user space buffers
+ *
+ * Note vs. vmalloc(): If the task with a vzalloc()-allocated buffer
+ * terminates quickly, vfree()-induced IPIs may be a concern, but tasks
+ * with large states are likely to live longer.
+ *
+ * Returns: 0 on success, -ENOMEM on allocation error.
+ */
+static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
+ unsigned int usize)
+{
+ struct fpu *fpu = &current->thread.fpu;
+ struct fpstate *curfps, *newfps = NULL;
+ unsigned int fpsize;
+
+ curfps = fpu->fpstate;
+ fpsize = ksize + ALIGN(offsetof(struct fpstate, regs), 64);
+
+ newfps = vzalloc(fpsize);
+ if (!newfps)
+ return -ENOMEM;
+ newfps->size = ksize;
+ newfps->user_size = usize;
+ newfps->is_valloc = true;
+
+ fpregs_lock();
+ /*
+ * Ensure that the current state is in the registers before
+ * swapping fpstate as that might invalidate it due to layout
+ * changes.
+ */
+ if (test_thread_flag(TIF_NEED_FPU_LOAD))
+ fpregs_restore_userregs();
+
+ newfps->xfeatures = curfps->xfeatures | xfeatures;
+ newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
+ newfps->xfd = curfps->xfd & ~xfeatures;
+
+ curfps = fpu_install_fpstate(fpu, newfps);
+
+ /* Do the final updates within the locked region */
+ xstate_init_xcomp_bv(&newfps->regs.xsave, newfps->xfeatures);
+ xfd_update_state(newfps);
+
+ fpregs_unlock();
+
+ vfree(curfps);
+ return 0;
+}
+
+static int validate_sigaltstack(unsigned int usize)
+{
+ struct task_struct *thread, *leader = current->group_leader;
+ unsigned long framesize = get_sigframe_size();
+
+ lockdep_assert_held(&current->sighand->siglock);
+
+ /* get_sigframe_size() is based on fpu_user_cfg.max_size */
+ framesize -= fpu_user_cfg.max_size;
+ framesize += usize;
+ for_each_thread(leader, thread) {
+ if (thread->sas_ss_size && thread->sas_ss_size < framesize)
+ return -ENOSPC;
+ }
+ return 0;
+}
+
+static int __xstate_request_perm(u64 permitted, u64 requested)
+{
+ /*
+ * This deliberately does not exclude !XSAVES as we still might
+ * decide to optionally context switch XCR0 or talk the silicon
+ * vendors into extending XFD for the pre AMX states, especially
+ * AVX512.
+ */
+ bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES);
+ struct fpu *fpu = &current->group_leader->thread.fpu;
+ unsigned int ksize, usize;
+ u64 mask;
+ int ret;
+
+ /* Check whether fully enabled */
+ if ((permitted & requested) == requested)
+ return 0;
+
+ /* Calculate the resulting kernel state size */
+ mask = permitted | requested;
+ ksize = xstate_calculate_size(mask, compacted);
+
+ /* Calculate the resulting user state size */
+ mask &= XFEATURE_MASK_USER_SUPPORTED;
+ usize = xstate_calculate_size(mask, false);
+
+ ret = validate_sigaltstack(usize);
+ if (ret)
+ return ret;
+
+ /* Pairs with the READ_ONCE() in xstate_get_group_perm() */
+ WRITE_ONCE(fpu->perm.__state_perm, requested);
+ /* Protected by sighand lock */
+ fpu->perm.__state_size = ksize;
+ fpu->perm.__user_state_size = usize;
+ return ret;
+}
+
+/*
+ * Permissions array to map facilities with more than one component
+ */
+static const u64 xstate_prctl_req[XFEATURE_MAX] = {
+ [XFEATURE_XTILE_DATA] = XFEATURE_MASK_XTILE_DATA,
+};
+
+static int xstate_request_perm(unsigned long idx)
+{
+ u64 permitted, requested;
+ int ret;
+
+ if (idx >= XFEATURE_MAX)
+ return -EINVAL;
+
+ /*
+ * Look up the facility mask which can require more than
+ * one xstate component.
+ */
+ idx = array_index_nospec(idx, ARRAY_SIZE(xstate_prctl_req));
+ requested = xstate_prctl_req[idx];
+ if (!requested)
+ return -EOPNOTSUPP;
+
+ if ((fpu_user_cfg.max_features & requested) != requested)
+ return -EOPNOTSUPP;
+
+ /* Lockless quick check */
+ permitted = xstate_get_host_group_perm();
+ if ((permitted & requested) == requested)
+ return 0;
+
+ /* Protect against concurrent modifications */
+ spin_lock_irq(&current->sighand->siglock);
+ permitted = xstate_get_host_group_perm();
+ ret = __xstate_request_perm(permitted, requested);
+ spin_unlock_irq(&current->sighand->siglock);
+ return ret;
+}
+
+int xfd_enable_feature(u64 xfd_err)
+{
+ u64 xfd_event = xfd_err & XFEATURE_MASK_USER_DYNAMIC;
+ unsigned int ksize, usize;
+ struct fpu *fpu;
+
+ if (!xfd_event) {
+ pr_err_once("XFD: Invalid xfd error: %016llx\n", xfd_err);
+ return 0;
+ }
+
+ /* Protect against concurrent modifications */
+ spin_lock_irq(&current->sighand->siglock);
+
+ /* If not permitted let it die */
+ if ((xstate_get_host_group_perm() & xfd_event) != xfd_event) {
+ spin_unlock_irq(&current->sighand->siglock);
+ return -EPERM;
+ }
+
+ fpu = &current->group_leader->thread.fpu;
+ ksize = fpu->perm.__state_size;
+ usize = fpu->perm.__user_state_size;
+ /*
+ * The feature is permitted. State size is sufficient. Dropping
+ * the lock is safe here even if more features are added from
+ * another task, the retrieved buffer sizes are valid for the
+ * currently requested feature(s).
+ */
+ spin_unlock_irq(&current->sighand->siglock);
+
+ /*
+ * Try to allocate a new fpstate. If that fails there is no way
+ * out.
+ */
+ if (fpstate_realloc(xfd_event, ksize, usize))
+ return -EFAULT;
+ return 0;
+}
+#else /* CONFIG_X86_64 */
+static inline int xstate_request_perm(unsigned long idx)
+{
+ return -EPERM;
+}
+#endif /* !CONFIG_X86_64 */
+
+/**
+ * fpu_xstate_prctl - xstate permission operations
+ * @tsk: Redundant pointer to current
+ * @option: A subfunction of arch_prctl()
+ * @arg2: option argument
+ * Return: 0 if successful; otherwise, an error code
+ *
+ * Option arguments:
+ *
+ * ARCH_GET_XCOMP_SUPP: Pointer to user space u64 to store the info
+ * ARCH_GET_XCOMP_PERM: Pointer to user space u64 to store the info
+ * ARCH_REQ_XCOMP_PERM: Facility number requested
+ *
+ * For facilities which require more than one XSTATE component, the request
+ * must be the highest state component number related to that facility,
+ * e.g. for AMX which requires XFEATURE_XTILE_CFG(17) and
+ * XFEATURE_XTILE_DATA(18) this would be XFEATURE_XTILE_DATA(18).
+ */
+long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2)
+{
+ u64 __user *uptr = (u64 __user *)arg2;
+ u64 permitted, supported;
+ unsigned long idx = arg2;
+
+ if (tsk != current)
+ return -EPERM;
+
+ switch (option) {
+ case ARCH_GET_XCOMP_SUPP:
+ supported = fpu_user_cfg.max_features | fpu_user_cfg.legacy_features;
+ return put_user(supported, uptr);
+
+ case ARCH_GET_XCOMP_PERM:
+ /*
+ * Lockless snapshot as it can also change right after the
+ * dropping the lock.
+ */
+ permitted = xstate_get_host_group_perm();
+ permitted &= XFEATURE_MASK_USER_SUPPORTED;
+ return put_user(permitted, uptr);
+
+ case ARCH_REQ_XCOMP_PERM:
+ if (!IS_ENABLED(CONFIG_X86_64))
+ return -EOPNOTSUPP;
+
+ return xstate_request_perm(idx);
+
+ default:
+ return -EINVAL;
+ }
+}
+
#ifdef CONFIG_PROC_PID_ARCH_STATUS
/*
* Report the amount of time elapsed in millisecond since last AVX512
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
new file mode 100644
index 000000000000..e18210dff88c
--- /dev/null
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -0,0 +1,278 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __X86_KERNEL_FPU_XSTATE_H
+#define __X86_KERNEL_FPU_XSTATE_H
+
+#include <asm/cpufeature.h>
+#include <asm/fpu/xstate.h>
+
+#ifdef CONFIG_X86_64
+DECLARE_PER_CPU(u64, xfd_state);
+#endif
+
+static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask)
+{
+ /*
+ * XRSTORS requires these bits set in xcomp_bv, or it will
+ * trigger #GP:
+ */
+ if (cpu_feature_enabled(X86_FEATURE_XSAVES))
+ xsave->header.xcomp_bv = mask | XCOMP_BV_COMPACTED_FORMAT;
+}
+
+static inline u64 xstate_get_host_group_perm(void)
+{
+ /* Pairs with WRITE_ONCE() in xstate_request_perm() */
+ return READ_ONCE(current->group_leader->thread.fpu.perm.__state_perm);
+}
+
+enum xstate_copy_mode {
+ XSTATE_COPY_FP,
+ XSTATE_COPY_FX,
+ XSTATE_COPY_XSAVE,
+};
+
+struct membuf;
+extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
+ u32 pkru_val, enum xstate_copy_mode copy_mode);
+extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
+ enum xstate_copy_mode mode);
+extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf);
+extern int copy_sigframe_from_user_to_xstate(struct fpstate *fpstate, const void __user *ubuf);
+
+
+extern void fpu__init_cpu_xstate(void);
+extern void fpu__init_system_xstate(unsigned int legacy_size);
+
+extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
+
+static inline u64 xfeatures_mask_supervisor(void)
+{
+ return fpu_kernel_cfg.max_features & XFEATURE_MASK_SUPERVISOR_SUPPORTED;
+}
+
+static inline u64 xfeatures_mask_independent(void)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR))
+ return XFEATURE_MASK_INDEPENDENT & ~XFEATURE_MASK_LBR;
+
+ return XFEATURE_MASK_INDEPENDENT;
+}
+
+/* XSAVE/XRSTOR wrapper functions */
+
+#ifdef CONFIG_X86_64
+#define REX_PREFIX "0x48, "
+#else
+#define REX_PREFIX
+#endif
+
+/* These macros all use (%edi)/(%rdi) as the single memory argument. */
+#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27"
+#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37"
+#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f"
+#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f"
+#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f"
+
+/*
+ * After this @err contains 0 on success or the trap number when the
+ * operation raises an exception.
+ */
+#define XSTATE_OP(op, st, lmask, hmask, err) \
+ asm volatile("1:" op "\n\t" \
+ "xor %[err], %[err]\n" \
+ "2:\n\t" \
+ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE) \
+ : [err] "=a" (err) \
+ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
+ : "memory")
+
+/*
+ * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact
+ * format and supervisor states in addition to modified optimization in
+ * XSAVEOPT.
+ *
+ * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT
+ * supports modified optimization which is not supported by XSAVE.
+ *
+ * We use XSAVE as a fallback.
+ *
+ * The 661 label is defined in the ALTERNATIVE* macros as the address of the
+ * original instruction which gets replaced. We need to use it here as the
+ * address of the instruction where we might get an exception at.
+ */
+#define XSTATE_XSAVE(st, lmask, hmask, err) \
+ asm volatile(ALTERNATIVE_2(XSAVE, \
+ XSAVEOPT, X86_FEATURE_XSAVEOPT, \
+ XSAVES, X86_FEATURE_XSAVES) \
+ "\n" \
+ "xor %[err], %[err]\n" \
+ "3:\n" \
+ ".pushsection .fixup,\"ax\"\n" \
+ "4: movl $-2, %[err]\n" \
+ "jmp 3b\n" \
+ ".popsection\n" \
+ _ASM_EXTABLE(661b, 4b) \
+ : [err] "=r" (err) \
+ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
+ : "memory")
+
+/*
+ * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact
+ * XSAVE area format.
+ */
+#define XSTATE_XRESTORE(st, lmask, hmask) \
+ asm volatile(ALTERNATIVE(XRSTOR, \
+ XRSTORS, X86_FEATURE_XSAVES) \
+ "\n" \
+ "3:\n" \
+ _ASM_EXTABLE_TYPE(661b, 3b, EX_TYPE_FPU_RESTORE) \
+ : \
+ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
+ : "memory")
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_X86_DEBUG_FPU)
+extern void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor);
+#else
+static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor) { }
+#endif
+
+#ifdef CONFIG_X86_64
+static inline void xfd_update_state(struct fpstate *fpstate)
+{
+ if (fpu_state_size_dynamic()) {
+ u64 xfd = fpstate->xfd;
+
+ if (__this_cpu_read(xfd_state) != xfd) {
+ wrmsrl(MSR_IA32_XFD, xfd);
+ __this_cpu_write(xfd_state, xfd);
+ }
+ }
+}
+#else
+static inline void xfd_update_state(struct fpstate *fpstate) { }
+#endif
+
+/*
+ * Save processor xstate to xsave area.
+ *
+ * Uses either XSAVE or XSAVEOPT or XSAVES depending on the CPU features
+ * and command line options. The choice is permanent until the next reboot.
+ */
+static inline void os_xsave(struct fpstate *fpstate)
+{
+ u64 mask = fpstate->xfeatures;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err;
+
+ WARN_ON_FPU(!alternatives_patched);
+ xfd_validate_state(fpstate, mask, false);
+
+ XSTATE_XSAVE(&fpstate->regs.xsave, lmask, hmask, err);
+
+ /* We should never fault when copying to a kernel buffer: */
+ WARN_ON_FPU(err);
+}
+
+/*
+ * Restore processor xstate from xsave area.
+ *
+ * Uses XRSTORS when XSAVES is used, XRSTOR otherwise.
+ */
+static inline void os_xrstor(struct fpstate *fpstate, u64 mask)
+{
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+
+ xfd_validate_state(fpstate, mask, true);
+ XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask);
+}
+
+/* Restore of supervisor state. Does not require XFD */
+static inline void os_xrstor_supervisor(struct fpstate *fpstate)
+{
+ u64 mask = xfeatures_mask_supervisor();
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+
+ XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask);
+}
+
+/*
+ * Save xstate to user space xsave area.
+ *
+ * We don't use modified optimization because xrstor/xrstors might track
+ * a different application.
+ *
+ * We don't use compacted format xsave area for backward compatibility for
+ * old applications which don't understand the compacted format of the
+ * xsave area.
+ *
+ * The caller has to zero buf::header before calling this because XSAVE*
+ * does not touch the reserved fields in the header.
+ */
+static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
+{
+ /*
+ * Include the features which are not xsaved/rstored by the kernel
+ * internally, e.g. PKRU. That's user space ABI and also required
+ * to allow the signal handler to modify PKRU.
+ */
+ struct fpstate *fpstate = current->thread.fpu.fpstate;
+ u64 mask = fpstate->user_xfeatures;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err;
+
+ xfd_validate_state(fpstate, mask, false);
+
+ stac();
+ XSTATE_OP(XSAVE, buf, lmask, hmask, err);
+ clac();
+
+ return err;
+}
+
+/*
+ * Restore xstate from user space xsave area.
+ */
+static inline int xrstor_from_user_sigframe(struct xregs_state __user *buf, u64 mask)
+{
+ struct xregs_state *xstate = ((__force struct xregs_state *)buf);
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err;
+
+ xfd_validate_state(current->thread.fpu.fpstate, mask, true);
+
+ stac();
+ XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+ clac();
+
+ return err;
+}
+
+/*
+ * Restore xstate from kernel space xsave area, return an error code instead of
+ * an exception.
+ */
+static inline int os_xrstor_safe(struct fpstate *fpstate, u64 mask)
+{
+ struct xregs_state *xstate = &fpstate->regs.xsave;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err;
+
+ /* Ensure that XFD is up to date */
+ xfd_update_state(fpstate);
+
+ if (cpu_feature_enabled(X86_FEATURE_XSAVES))
+ XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
+ else
+ XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+
+ return err;
+}
+
+
+#endif
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 8fb6bd4cbc50..eb470be0e5ae 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -30,7 +30,9 @@
#include <asm/apic.h>
#include <linux/uaccess.h>
#include <asm/mwait.h>
-#include <asm/fpu/internal.h>
+#include <asm/fpu/api.h>
+#include <asm/fpu/sched.h>
+#include <asm/fpu/xstate.h>
#include <asm/debugreg.h>
#include <asm/nmi.h>
#include <asm/tlbflush.h>
@@ -88,8 +90,19 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
#ifdef CONFIG_VM86
dst->thread.vm86 = NULL;
#endif
- return fpu_clone(dst);
+ /* Drop the copied pointer to current's fpstate */
+ dst->thread.fpu.fpstate = NULL;
+
+ return 0;
+}
+
+#ifdef CONFIG_X86_64
+void arch_release_task_struct(struct task_struct *tsk)
+{
+ if (fpu_state_size_dynamic())
+ fpstate_free(&tsk->thread.fpu);
}
+#endif
/*
* Free thread data structures etc..
@@ -155,6 +168,8 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
frame->flags = X86_EFLAGS_FIXED;
#endif
+ fpu_clone(p, clone_flags);
+
/* Kernel thread ? */
if (unlikely(p->flags & PF_KTHREAD)) {
p->thread.pkru = pkru_get_init_value();
@@ -962,13 +977,17 @@ unsigned long __get_wchan(struct task_struct *p)
}
long do_arch_prctl_common(struct task_struct *task, int option,
- unsigned long cpuid_enabled)
+ unsigned long arg2)
{
switch (option) {
case ARCH_GET_CPUID:
return get_cpuid_mode();
case ARCH_SET_CPUID:
- return set_cpuid_mode(task, cpuid_enabled);
+ return set_cpuid_mode(task, arg2);
+ case ARCH_GET_XCOMP_SUPP:
+ case ARCH_GET_XCOMP_PERM:
+ case ARCH_REQ_XCOMP_PERM:
+ return fpu_xstate_prctl(task, option, arg2);
}
return -EINVAL;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 4f2f54e1281c..26edb1cd07a4 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -41,7 +41,7 @@
#include <asm/ldt.h>
#include <asm/processor.h>
-#include <asm/fpu/internal.h>
+#include <asm/fpu/sched.h>
#include <asm/desc.h>
#include <linux/err.h>
@@ -160,7 +160,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
struct thread_struct *prev = &prev_p->thread,
*next = &next_p->thread;
struct fpu *prev_fpu = &prev->fpu;
- struct fpu *next_fpu = &next->fpu;
int cpu = smp_processor_id();
/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
@@ -213,7 +212,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
this_cpu_write(current_task, next_p);
- switch_fpu_finish(next_fpu);
+ switch_fpu_finish();
/* Load the Intel cache allocation PQR MSR. */
resctrl_sched_in();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ec0d836a13b1..3402edec236c 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -42,7 +42,7 @@
#include <asm/processor.h>
#include <asm/pkru.h>
-#include <asm/fpu/internal.h>
+#include <asm/fpu/sched.h>
#include <asm/mmu_context.h>
#include <asm/prctl.h>
#include <asm/desc.h>
@@ -559,7 +559,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
struct thread_struct *prev = &prev_p->thread;
struct thread_struct *next = &next_p->thread;
struct fpu *prev_fpu = &prev->fpu;
- struct fpu *next_fpu = &next->fpu;
int cpu = smp_processor_id();
WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
@@ -620,7 +619,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
this_cpu_write(current_task, next_p);
this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
- switch_fpu_finish(next_fpu);
+ switch_fpu_finish();
/* Reload sp0. */
update_task_stack(next_p);
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 4c208ea3bd9f..6d2244c94799 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -29,9 +29,9 @@
#include <linux/uaccess.h>
#include <asm/processor.h>
-#include <asm/fpu/internal.h>
#include <asm/fpu/signal.h>
#include <asm/fpu/regset.h>
+#include <asm/fpu/xstate.h>
#include <asm/debugreg.h>
#include <asm/ldt.h>
#include <asm/desc.h>
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index a6895e440bc3..50c773c3384c 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -23,7 +23,7 @@
#include <asm/stacktrace.h>
#include <asm/sev.h>
#include <asm/insn-eval.h>
-#include <asm/fpu/internal.h>
+#include <asm/fpu/xcr.h>
#include <asm/processor.h>
#include <asm/realmode.h>
#include <asm/traps.h>
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index f4d21e470083..ec71e06ae364 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -15,6 +15,7 @@
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/kernel.h>
+#include <linux/kstrtox.h>
#include <linux/errno.h>
#include <linux/wait.h>
#include <linux/tracehook.h>
@@ -30,8 +31,8 @@
#include <asm/processor.h>
#include <asm/ucontext.h>
-#include <asm/fpu/internal.h>
#include <asm/fpu/signal.h>
+#include <asm/fpu/xstate.h>
#include <asm/vdso.h>
#include <asm/mce.h>
#include <asm/sighandling.h>
@@ -41,6 +42,7 @@
#include <linux/compat.h>
#include <asm/proto.h>
#include <asm/ia32_unistd.h>
+#include <asm/fpu/xstate.h>
#endif /* CONFIG_X86_64 */
#include <asm/syscall.h>
@@ -79,9 +81,9 @@ static void force_valid_ss(struct pt_regs *regs)
# define CONTEXT_COPY_SIZE sizeof(struct sigcontext)
#endif
-static int restore_sigcontext(struct pt_regs *regs,
- struct sigcontext __user *usc,
- unsigned long uc_flags)
+static bool restore_sigcontext(struct pt_regs *regs,
+ struct sigcontext __user *usc,
+ unsigned long uc_flags)
{
struct sigcontext sc;
@@ -89,7 +91,7 @@ static int restore_sigcontext(struct pt_regs *regs,
current->restart_block.fn = do_no_restart_syscall;
if (copy_from_user(&sc, usc, CONTEXT_COPY_SIZE))
- return -EFAULT;
+ return false;
#ifdef CONFIG_X86_32
set_user_gs(regs, sc.gs);
@@ -244,7 +246,6 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
unsigned long math_size = 0;
unsigned long sp = regs->sp;
unsigned long buf_fx = 0;
- int ret;
/* redzone */
if (IS_ENABLED(CONFIG_X86_64))
@@ -292,8 +293,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
}
/* save i387 and extended state */
- ret = copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size);
- if (ret < 0)
+ if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size))
return (void __user *)-1L;
return (void __user *)sp;
@@ -643,7 +643,7 @@ SYSCALL_DEFINE0(sigreturn)
* x86_32 has no uc_flags bits relevant to restore_sigcontext.
* Save a few cycles by skipping the __get_user.
*/
- if (restore_sigcontext(regs, &frame->sc, 0))
+ if (!restore_sigcontext(regs, &frame->sc, 0))
goto badframe;
return regs->ax;
@@ -671,7 +671,7 @@ SYSCALL_DEFINE0(rt_sigreturn)
set_current_blocked(&set);
- if (restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
+ if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
goto badframe;
if (restore_altstack(&frame->uc.uc_stack))
@@ -721,12 +721,15 @@ badframe:
/* max_frame_size tells userspace the worst case signal stack size. */
static unsigned long __ro_after_init max_frame_size;
+static unsigned int __ro_after_init fpu_default_state_size;
void __init init_sigframe_size(void)
{
+ fpu_default_state_size = fpu__get_fpstate_size();
+
max_frame_size = MAX_FRAME_SIGINFO_UCTXT_SIZE + MAX_FRAME_PADDING;
- max_frame_size += fpu__get_fpstate_size() + MAX_XSAVE_PADDING;
+ max_frame_size += fpu_default_state_size + MAX_XSAVE_PADDING;
/* Userspace expects an aligned size. */
max_frame_size = round_up(max_frame_size, FRAME_ALIGNMENT);
@@ -910,6 +913,62 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
force_sig(SIGSEGV);
}
+#ifdef CONFIG_DYNAMIC_SIGFRAME
+#ifdef CONFIG_STRICT_SIGALTSTACK_SIZE
+static bool strict_sigaltstack_size __ro_after_init = true;
+#else
+static bool strict_sigaltstack_size __ro_after_init = false;
+#endif
+
+static int __init strict_sas_size(char *arg)
+{
+ return kstrtobool(arg, &strict_sigaltstack_size);
+}
+__setup("strict_sas_size", strict_sas_size);
+
+/*
+ * MINSIGSTKSZ is 2048 and can't be changed despite the fact that AVX512
+ * exceeds that size already. As such programs might never use the
+ * sigaltstack they just continued to work. While always checking against
+ * the real size would be correct, this might be considered a regression.
+ *
+ * Therefore avoid the sanity check, unless enforced by kernel
+ * configuration or command line option.
+ *
+ * When dynamic FPU features are supported, the check is also enforced when
+ * the task has permissions to use dynamic features. Tasks which have no
+ * permission are checked against the size of the non-dynamic feature set
+ * if strict checking is enabled. This avoids forcing all tasks on the
+ * system to allocate large sigaltstacks even if they are never going
+ * to use a dynamic feature. As this is serialized via sighand::siglock
+ * any permission request for a dynamic feature either happened already
+ * or will see the newly install sigaltstack size in the permission checks.
+ */
+bool sigaltstack_size_valid(size_t ss_size)
+{
+ unsigned long fsize = max_frame_size - fpu_default_state_size;
+ u64 mask;
+
+ lockdep_assert_held(&current->sighand->siglock);
+
+ if (!fpu_state_size_dynamic() && !strict_sigaltstack_size)
+ return true;
+
+ fsize += current->group_leader->thread.fpu.perm.__user_state_size;
+ if (likely(ss_size > fsize))
+ return true;
+
+ if (strict_sigaltstack_size)
+ return ss_size > fsize;
+
+ mask = current->group_leader->thread.fpu.perm.__state_perm;
+ if (mask & XFEATURE_MASK_USER_DYNAMIC)
+ return ss_size > fsize;
+
+ return true;
+}
+#endif /* CONFIG_DYNAMIC_SIGFRAME */
+
#ifdef CONFIG_X86_X32_ABI
COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn)
{
@@ -929,7 +988,7 @@ COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn)
set_current_blocked(&set);
- if (restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
+ if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
goto badframe;
if (compat_restore_altstack(&frame->uc.uc_stack))
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f80f4595ed41..959599ac25a6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -70,7 +70,7 @@
#include <asm/mwait.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
-#include <asm/fpu/internal.h>
+#include <asm/fpu/api.h>
#include <asm/setup.h>
#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index a58800973aed..6ca1454a65d4 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -48,7 +48,7 @@
#include <asm/ftrace.h>
#include <asm/traps.h>
#include <asm/desc.h>
-#include <asm/fpu/internal.h>
+#include <asm/fpu/api.h>
#include <asm/cpu.h>
#include <asm/cpu_entry_area.h>
#include <asm/mce.h>
@@ -1108,10 +1108,48 @@ DEFINE_IDTENTRY(exc_spurious_interrupt_bug)
*/
}
+static bool handle_xfd_event(struct pt_regs *regs)
+{
+ u64 xfd_err;
+ int err;
+
+ if (!IS_ENABLED(CONFIG_X86_64) || !cpu_feature_enabled(X86_FEATURE_XFD))
+ return false;
+
+ rdmsrl(MSR_IA32_XFD_ERR, xfd_err);
+ if (!xfd_err)
+ return false;
+
+ wrmsrl(MSR_IA32_XFD_ERR, 0);
+
+ /* Die if that happens in kernel space */
+ if (WARN_ON(!user_mode(regs)))
+ return false;
+
+ local_irq_enable();
+
+ err = xfd_enable_feature(xfd_err);
+
+ switch (err) {
+ case -EPERM:
+ force_sig_fault(SIGILL, ILL_ILLOPC, error_get_trap_addr(regs));
+ break;
+ case -EFAULT:
+ force_sig(SIGSEGV);
+ break;
+ }
+
+ local_irq_disable();
+ return true;
+}
+
DEFINE_IDTENTRY(exc_device_not_available)
{
unsigned long cr0 = read_cr0();
+ if (handle_xfd_event(regs))
+ return;
+
#ifdef CONFIG_MATH_EMULATION
if (!boot_cpu_has(X86_FEATURE_FPU) && (cr0 & X86_CR0_EM)) {
struct math_emu_info info = { };
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 7e34d7163ada..5847b05d29da 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -17,10 +17,10 @@
#include <linux/misc_cgroup.h>
#include <linux/processor.h>
#include <linux/trace_events.h>
-#include <asm/fpu/internal.h>
#include <asm/pkru.h>
#include <asm/trapnr.h>
+#include <asm/fpu/xcr.h>
#include "x86.h"
#include "svm.h"
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 989685098b3e..f39c87ddc2e5 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -36,6 +36,7 @@
#include <asm/spec-ctrl.h>
#include <asm/cpu_device_id.h>
#include <asm/traps.h>
+#include <asm/fpu/api.h>
#include <asm/virtext.h>
#include "trace.h"
@@ -1346,10 +1347,10 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
/*
* SEV-ES guests maintain an encrypted version of their FPU
* state which is restored and saved on VMRUN and VMEXIT.
- * Free the fpu structure to prevent KVM from attempting to
- * access the FPU state.
+ * Mark vcpu->arch.guest_fpu->fpstate as scratch so it won't
+ * do xsave/xrstor on it.
*/
- kvm_free_guest_fpu(vcpu);
+ fpstate_set_confidential(&vcpu->arch.guest_fpu);
}
err = avic_init_vcpu(svm);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 7d595effb66f..fb9e4ac3df22 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -35,7 +35,7 @@
#include <asm/cpu_device_id.h>
#include <asm/debugreg.h>
#include <asm/desc.h>
-#include <asm/fpu/internal.h>
+#include <asm/fpu/api.h>
#include <asm/idtentry.h>
#include <asm/io.h>
#include <asm/irq_remapping.h>
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bfe0de3008a6..2686f2edb47c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -68,7 +68,9 @@
#include <asm/mce.h>
#include <asm/pkru.h>
#include <linux/kernel_stat.h>
-#include <asm/fpu/internal.h> /* Ugh! */
+#include <asm/fpu/api.h>
+#include <asm/fpu/xcr.h>
+#include <asm/fpu/xstate.h>
#include <asm/pvclock.h>
#include <asm/div64.h>
#include <asm/irq_remapping.h>
@@ -293,8 +295,6 @@ u64 __read_mostly host_xcr0;
u64 __read_mostly supported_xcr0;
EXPORT_SYMBOL_GPL(supported_xcr0);
-static struct kmem_cache *x86_fpu_cache;
-
static struct kmem_cache *x86_emulator_cache;
/*
@@ -4700,144 +4700,27 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
return 0;
}
-#define XSTATE_COMPACTION_ENABLED (1ULL << 63)
-
-static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
-{
- struct xregs_state *xsave = &vcpu->arch.guest_fpu->state.xsave;
- u64 xstate_bv = xsave->header.xfeatures;
- u64 valid;
-
- /*
- * Copy legacy XSAVE area, to avoid complications with CPUID
- * leaves 0 and 1 in the loop below.
- */
- memcpy(dest, xsave, XSAVE_HDR_OFFSET);
-
- /* Set XSTATE_BV */
- xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE;
- *(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
-
- /*
- * Copy each region from the possibly compacted offset to the
- * non-compacted offset.
- */
- valid = xstate_bv & ~XFEATURE_MASK_FPSSE;
- while (valid) {
- u32 size, offset, ecx, edx;
- u64 xfeature_mask = valid & -valid;
- int xfeature_nr = fls64(xfeature_mask) - 1;
- void *src;
-
- cpuid_count(XSTATE_CPUID, xfeature_nr,
- &size, &offset, &ecx, &edx);
-
- if (xfeature_nr == XFEATURE_PKRU) {
- memcpy(dest + offset, &vcpu->arch.pkru,
- sizeof(vcpu->arch.pkru));
- } else {
- src = get_xsave_addr(xsave, xfeature_nr);
- if (src)
- memcpy(dest + offset, src, size);
- }
-
- valid -= xfeature_mask;
- }
-}
-
-static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
-{
- struct xregs_state *xsave = &vcpu->arch.guest_fpu->state.xsave;
- u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET);
- u64 valid;
-
- /*
- * Copy legacy XSAVE area, to avoid complications with CPUID
- * leaves 0 and 1 in the loop below.
- */
- memcpy(xsave, src, XSAVE_HDR_OFFSET);
-
- /* Set XSTATE_BV and possibly XCOMP_BV. */
- xsave->header.xfeatures = xstate_bv;
- if (boot_cpu_has(X86_FEATURE_XSAVES))
- xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
-
- /*
- * Copy each region from the non-compacted offset to the
- * possibly compacted offset.
- */
- valid = xstate_bv & ~XFEATURE_MASK_FPSSE;
- while (valid) {
- u32 size, offset, ecx, edx;
- u64 xfeature_mask = valid & -valid;
- int xfeature_nr = fls64(xfeature_mask) - 1;
-
- cpuid_count(XSTATE_CPUID, xfeature_nr,
- &size, &offset, &ecx, &edx);
-
- if (xfeature_nr == XFEATURE_PKRU) {
- memcpy(&vcpu->arch.pkru, src + offset,
- sizeof(vcpu->arch.pkru));
- } else {
- void *dest = get_xsave_addr(xsave, xfeature_nr);
-
- if (dest)
- memcpy(dest, src + offset, size);
- }
-
- valid -= xfeature_mask;
- }
-}
-
static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
struct kvm_xsave *guest_xsave)
{
- if (!vcpu->arch.guest_fpu)
+ if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
return;
- if (boot_cpu_has(X86_FEATURE_XSAVE)) {
- memset(guest_xsave, 0, sizeof(struct kvm_xsave));
- fill_xsave((u8 *) guest_xsave->region, vcpu);
- } else {
- memcpy(guest_xsave->region,
- &vcpu->arch.guest_fpu->state.fxsave,
- sizeof(struct fxregs_state));
- *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] =
- XFEATURE_MASK_FPSSE;
- }
+ fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu,
+ guest_xsave->region,
+ sizeof(guest_xsave->region),
+ vcpu->arch.pkru);
}
-#define XSAVE_MXCSR_OFFSET 24
-
static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
struct kvm_xsave *guest_xsave)
{
- u64 xstate_bv;
- u32 mxcsr;
-
- if (!vcpu->arch.guest_fpu)
+ if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
return 0;
- xstate_bv = *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
- mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
-
- if (boot_cpu_has(X86_FEATURE_XSAVE)) {
- /*
- * Here we allow setting states that are not present in
- * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility
- * with old userspace.
- */
- if (xstate_bv & ~supported_xcr0 || mxcsr & ~mxcsr_feature_mask)
- return -EINVAL;
- load_xsave(vcpu, (u8 *)guest_xsave->region);
- } else {
- if (xstate_bv & ~XFEATURE_MASK_FPSSE ||
- mxcsr & ~mxcsr_feature_mask)
- return -EINVAL;
- memcpy(&vcpu->arch.guest_fpu->state.fxsave,
- guest_xsave->region, sizeof(struct fxregs_state));
- }
- return 0;
+ return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu,
+ guest_xsave->region,
+ supported_xcr0, &vcpu->arch.pkru);
}
static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu,
@@ -8434,18 +8317,11 @@ int kvm_arch_init(void *opaque)
}
r = -ENOMEM;
- x86_fpu_cache = kmem_cache_create("x86_fpu", sizeof(struct fpu),
- __alignof__(struct fpu), SLAB_ACCOUNT,
- NULL);
- if (!x86_fpu_cache) {
- printk(KERN_ERR "kvm: failed to allocate cache for x86 fpu\n");
- goto out;
- }
x86_emulator_cache = kvm_alloc_emulator_cache();
if (!x86_emulator_cache) {
pr_err("kvm: failed to allocate cache for x86 emulator\n");
- goto out_free_x86_fpu_cache;
+ goto out;
}
user_return_msrs = alloc_percpu(struct kvm_user_return_msrs);
@@ -8483,8 +8359,6 @@ out_free_percpu:
free_percpu(user_return_msrs);
out_free_x86_emulator_cache:
kmem_cache_destroy(x86_emulator_cache);
-out_free_x86_fpu_cache:
- kmem_cache_destroy(x86_fpu_cache);
out:
return r;
}
@@ -8511,7 +8385,6 @@ void kvm_arch_exit(void)
kvm_mmu_module_exit();
free_percpu(user_return_msrs);
kmem_cache_destroy(x86_emulator_cache);
- kmem_cache_destroy(x86_fpu_cache);
#ifdef CONFIG_KVM_XEN
static_key_deferred_flush(&kvm_xen_enabled);
WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key));
@@ -9938,58 +9811,21 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
return 0;
}
-static void kvm_save_current_fpu(struct fpu *fpu)
-{
- /*
- * If the target FPU state is not resident in the CPU registers, just
- * memcpy() from current, else save CPU state directly to the target.
- */
- if (test_thread_flag(TIF_NEED_FPU_LOAD))
- memcpy(&fpu->state, &current->thread.fpu.state,
- fpu_kernel_xstate_size);
- else
- save_fpregs_to_fpstate(fpu);
-}
-
/* Swap (qemu) user FPU context for the guest FPU context. */
static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
{
- fpregs_lock();
-
- kvm_save_current_fpu(vcpu->arch.user_fpu);
-
/*
- * Guests with protected state can't have it set by the hypervisor,
- * so skip trying to set it.
+ * Exclude PKRU from restore as restored separately in
+ * kvm_x86_ops.run().
*/
- if (vcpu->arch.guest_fpu)
- /* PKRU is separately restored in kvm_x86_ops.run. */
- __restore_fpregs_from_fpstate(&vcpu->arch.guest_fpu->state,
- ~XFEATURE_MASK_PKRU);
-
- fpregs_mark_activate();
- fpregs_unlock();
-
+ fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, true);
trace_kvm_fpu(1);
}
/* When vcpu_run ends, restore user space FPU context. */
static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
{
- fpregs_lock();
-
- /*
- * Guests with protected state can't have it read by the hypervisor,
- * so skip trying to save it.
- */
- if (vcpu->arch.guest_fpu)
- kvm_save_current_fpu(vcpu->arch.guest_fpu);
-
- restore_fpregs_from_fpstate(&vcpu->arch.user_fpu->state);
-
- fpregs_mark_activate();
- fpregs_unlock();
-
+ fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, false);
++vcpu->stat.fpu_reload;
trace_kvm_fpu(0);
}
@@ -10570,12 +10406,12 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
struct fxregs_state *fxsave;
- if (!vcpu->arch.guest_fpu)
+ if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
return 0;
vcpu_load(vcpu);
- fxsave = &vcpu->arch.guest_fpu->state.fxsave;
+ fxsave = &vcpu->arch.guest_fpu.fpstate->regs.fxsave;
memcpy(fpu->fpr, fxsave->st_space, 128);
fpu->fcw = fxsave->cwd;
fpu->fsw = fxsave->swd;
@@ -10593,12 +10429,12 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
struct fxregs_state *fxsave;
- if (!vcpu->arch.guest_fpu)
+ if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
return 0;
vcpu_load(vcpu);
- fxsave = &vcpu->arch.guest_fpu->state.fxsave;
+ fxsave = &vcpu->arch.guest_fpu.fpstate->regs.fxsave;
memcpy(fxsave->st_space, fpu->fpr, 128);
fxsave->cwd = fpu->fcw;
@@ -10651,14 +10487,6 @@ static int sync_regs(struct kvm_vcpu *vcpu)
static void fx_init(struct kvm_vcpu *vcpu)
{
- if (!vcpu->arch.guest_fpu)
- return;
-
- fpstate_init(&vcpu->arch.guest_fpu->state);
- if (boot_cpu_has(X86_FEATURE_XSAVES))
- vcpu->arch.guest_fpu->state.xsave.header.xcomp_bv =
- host_xcr0 | XSTATE_COMPACTION_ENABLED;
-
/*
* Ensure guest xcr0 is valid for loading
*/
@@ -10667,15 +10495,6 @@ static void fx_init(struct kvm_vcpu *vcpu)
vcpu->arch.cr0 |= X86_CR0_ET;
}
-void kvm_free_guest_fpu(struct kvm_vcpu *vcpu)
-{
- if (vcpu->arch.guest_fpu) {
- kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu);
- vcpu->arch.guest_fpu = NULL;
- }
-}
-EXPORT_SYMBOL_GPL(kvm_free_guest_fpu);
-
int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
{
if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
@@ -10732,19 +10551,11 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
if (!alloc_emulate_ctxt(vcpu))
goto free_wbinvd_dirty_mask;
- vcpu->arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
- GFP_KERNEL_ACCOUNT);
- if (!vcpu->arch.user_fpu) {
- pr_err("kvm: failed to allocate userspace's fpu\n");
+ if (!fpu_alloc_guest_fpstate(&vcpu->arch.guest_fpu)) {
+ pr_err("kvm: failed to allocate vcpu's fpu\n");
goto free_emulate_ctxt;
}
- vcpu->arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
- GFP_KERNEL_ACCOUNT);
- if (!vcpu->arch.guest_fpu) {
- pr_err("kvm: failed to allocate vcpu's fpu\n");
- goto free_user_fpu;
- }
fx_init(vcpu);
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
@@ -10777,9 +10588,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
return 0;
free_guest_fpu:
- kvm_free_guest_fpu(vcpu);
-free_user_fpu:
- kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu);
+ fpu_free_guest_fpstate(&vcpu->arch.guest_fpu);
free_emulate_ctxt:
kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt);
free_wbinvd_dirty_mask:
@@ -10828,8 +10637,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt);
free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
- kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu);
- kvm_free_guest_fpu(vcpu);
+ fpu_free_guest_fpstate(&vcpu->arch.guest_fpu);
kvm_hv_vcpu_uninit(vcpu);
kvm_pmu_destroy(vcpu);
@@ -10881,8 +10689,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
kvm_async_pf_hash_reset(vcpu);
vcpu->arch.apf.halted = false;
- if (vcpu->arch.guest_fpu && kvm_mpx_supported()) {
- void *mpx_state_buffer;
+ if (vcpu->arch.guest_fpu.fpstate && kvm_mpx_supported()) {
+ struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate;
/*
* To avoid have the INIT path from kvm_apic_has_events() that be
@@ -10890,14 +10698,10 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
*/
if (init_event)
kvm_put_guest_fpu(vcpu);
- mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave,
- XFEATURE_BNDREGS);
- if (mpx_state_buffer)
- memset(mpx_state_buffer, 0, sizeof(struct mpx_bndreg_state));
- mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave,
- XFEATURE_BNDCSR);
- if (mpx_state_buffer)
- memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr));
+
+ fpstate_clear_xstate_component(fpstate, XFEATURE_BNDREGS);
+ fpstate_clear_xstate_component(fpstate, XFEATURE_BNDCSR);
+
if (init_event)
kvm_load_guest_fpu(vcpu);
}
diff --git a/arch/x86/lib/copy_mc_64.S b/arch/x86/lib/copy_mc_64.S
index e5f77e293034..7334055157ba 100644
--- a/arch/x86/lib/copy_mc_64.S
+++ b/arch/x86/lib/copy_mc_64.S
@@ -107,9 +107,9 @@ SYM_FUNC_END(copy_mc_fragile)
.previous
- _ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
- _ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
- _ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
+ _ASM_EXTABLE_TYPE(.L_read_leading_bytes, .E_leading_bytes, EX_TYPE_DEFAULT_MCE_SAFE)
+ _ASM_EXTABLE_TYPE(.L_read_words, .E_read_words, EX_TYPE_DEFAULT_MCE_SAFE)
+ _ASM_EXTABLE_TYPE(.L_read_trailing_bytes, .E_trailing_bytes, EX_TYPE_DEFAULT_MCE_SAFE)
_ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
_ASM_EXTABLE(.L_write_words, .E_write_words)
_ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
@@ -149,5 +149,5 @@ SYM_FUNC_END(copy_mc_enhanced_fast_string)
.previous
- _ASM_EXTABLE_FAULT(.L_copy, .E_copy)
+ _ASM_EXTABLE_TYPE(.L_copy, .E_copy, EX_TYPE_DEFAULT_MCE_SAFE)
#endif /* !CONFIG_UML */
diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c
index 034748459482..d62662bdd460 100644
--- a/arch/x86/math-emu/fpu_aux.c
+++ b/arch/x86/math-emu/fpu_aux.c
@@ -53,7 +53,7 @@ void fpstate_init_soft(struct swregs_state *soft)
void finit(void)
{
- fpstate_init_soft(&current->thread.fpu.state.soft);
+ fpstate_init_soft(&current->thread.fpu.fpstate->regs.soft);
}
/*
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index 8679a9d6c47f..7fe56c594aa6 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -31,7 +31,7 @@
#include <linux/uaccess.h>
#include <asm/traps.h>
#include <asm/user.h>
-#include <asm/fpu/internal.h>
+#include <asm/fpu/api.h>
#include "fpu_system.h"
#include "fpu_emu.h"
@@ -640,7 +640,7 @@ int fpregs_soft_set(struct task_struct *target,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- struct swregs_state *s387 = &target->thread.fpu.state.soft;
+ struct swregs_state *s387 = &target->thread.fpu.fpstate->regs.soft;
void *space = s387->st_space;
int ret;
int offset, other, i, tags, regnr, tag, newtop;
@@ -691,7 +691,7 @@ int fpregs_soft_get(struct task_struct *target,
const struct user_regset *regset,
struct membuf to)
{
- struct swregs_state *s387 = &target->thread.fpu.state.soft;
+ struct swregs_state *s387 = &target->thread.fpu.fpstate->regs.soft;
const void *space = s387->st_space;
int offset = (S387->ftop & 7) * 10, other = 80 - offset;
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index 9b41391867dc..eec3e4805c75 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -73,7 +73,7 @@ static inline bool seg_writable(struct desc_struct *d)
return (d->type & SEG_TYPE_EXECUTE_MASK) == SEG_TYPE_WRITABLE;
}
-#define I387 (&current->thread.fpu.state)
+#define I387 (&current->thread.fpu.fpstate->regs)
#define FPU_info (I387->soft.info)
#define FPU_CS (*(unsigned short *) &(FPU_info->regs->cs))
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index e1664e9f969c..5cd2a88930a9 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -4,46 +4,30 @@
#include <linux/sched/debug.h>
#include <xen/xen.h>
-#include <asm/fpu/internal.h>
+#include <asm/fpu/api.h>
#include <asm/sev.h>
#include <asm/traps.h>
#include <asm/kdebug.h>
-typedef bool (*ex_handler_t)(const struct exception_table_entry *,
- struct pt_regs *, int, unsigned long,
- unsigned long);
-
static inline unsigned long
ex_fixup_addr(const struct exception_table_entry *x)
{
return (unsigned long)&x->fixup + x->fixup;
}
-static inline ex_handler_t
-ex_fixup_handler(const struct exception_table_entry *x)
-{
- return (ex_handler_t)((unsigned long)&x->handler + x->handler);
-}
-__visible bool ex_handler_default(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr,
- unsigned long error_code,
- unsigned long fault_addr)
+static bool ex_handler_default(const struct exception_table_entry *fixup,
+ struct pt_regs *regs)
{
regs->ip = ex_fixup_addr(fixup);
return true;
}
-EXPORT_SYMBOL(ex_handler_default);
-__visible bool ex_handler_fault(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr,
- unsigned long error_code,
- unsigned long fault_addr)
+static bool ex_handler_fault(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr)
{
- regs->ip = ex_fixup_addr(fixup);
regs->ax = trapnr;
- return true;
+ return ex_handler_default(fixup, regs);
}
-EXPORT_SYMBOL_GPL(ex_handler_fault);
/*
* Handler for when we fail to restore a task's FPU state. We should never get
@@ -55,65 +39,47 @@ EXPORT_SYMBOL_GPL(ex_handler_fault);
* of vulnerability by restoring from the initial state (essentially, zeroing
* out all the FPU registers) if we can't restore from the task's FPU state.
*/
-__visible bool ex_handler_fprestore(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr,
- unsigned long error_code,
- unsigned long fault_addr)
+static bool ex_handler_fprestore(const struct exception_table_entry *fixup,
+ struct pt_regs *regs)
{
regs->ip = ex_fixup_addr(fixup);
WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.",
(void *)instruction_pointer(regs));
- __restore_fpregs_from_fpstate(&init_fpstate, xfeatures_mask_fpstate());
+ fpu_reset_from_exception_fixup();
return true;
}
-EXPORT_SYMBOL_GPL(ex_handler_fprestore);
-__visible bool ex_handler_uaccess(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr,
- unsigned long error_code,
- unsigned long fault_addr)
+static bool ex_handler_uaccess(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr)
{
WARN_ONCE(trapnr == X86_TRAP_GP, "General protection fault in user access. Non-canonical address?");
- regs->ip = ex_fixup_addr(fixup);
- return true;
+ return ex_handler_default(fixup, regs);
}
-EXPORT_SYMBOL(ex_handler_uaccess);
-__visible bool ex_handler_copy(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr,
- unsigned long error_code,
- unsigned long fault_addr)
+static bool ex_handler_copy(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr)
{
WARN_ONCE(trapnr == X86_TRAP_GP, "General protection fault in user access. Non-canonical address?");
- regs->ip = ex_fixup_addr(fixup);
- regs->ax = trapnr;
- return true;
+ return ex_handler_fault(fixup, regs, trapnr);
}
-EXPORT_SYMBOL(ex_handler_copy);
-__visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr,
- unsigned long error_code,
- unsigned long fault_addr)
+static bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
+ struct pt_regs *regs)
{
if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
(unsigned int)regs->cx, regs->ip, (void *)regs->ip))
show_stack_regs(regs);
/* Pretend that the read succeeded and returned 0. */
- regs->ip = ex_fixup_addr(fixup);
regs->ax = 0;
regs->dx = 0;
- return true;
+ return ex_handler_default(fixup, regs);
}
-EXPORT_SYMBOL(ex_handler_rdmsr_unsafe);
-__visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr,
- unsigned long error_code,
- unsigned long fault_addr)
+static bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
+ struct pt_regs *regs)
{
if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
(unsigned int)regs->cx, (unsigned int)regs->dx,
@@ -121,45 +87,29 @@ __visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup
show_stack_regs(regs);
/* Pretend that the write succeeded. */
- regs->ip = ex_fixup_addr(fixup);
- return true;
+ return ex_handler_default(fixup, regs);
}
-EXPORT_SYMBOL(ex_handler_wrmsr_unsafe);
-__visible bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr,
- unsigned long error_code,
- unsigned long fault_addr)
+static bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
+ struct pt_regs *regs)
{
if (static_cpu_has(X86_BUG_NULL_SEG))
asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS));
asm volatile ("mov %0, %%fs" : : "rm" (0));
- return ex_handler_default(fixup, regs, trapnr, error_code, fault_addr);
+ return ex_handler_default(fixup, regs);
}
-EXPORT_SYMBOL(ex_handler_clear_fs);
-enum handler_type ex_get_fault_handler_type(unsigned long ip)
+int ex_get_fixup_type(unsigned long ip)
{
- const struct exception_table_entry *e;
- ex_handler_t handler;
+ const struct exception_table_entry *e = search_exception_tables(ip);
- e = search_exception_tables(ip);
- if (!e)
- return EX_HANDLER_NONE;
- handler = ex_fixup_handler(e);
- if (handler == ex_handler_fault)
- return EX_HANDLER_FAULT;
- else if (handler == ex_handler_uaccess || handler == ex_handler_copy)
- return EX_HANDLER_UACCESS;
- else
- return EX_HANDLER_OTHER;
+ return e ? e->type : EX_TYPE_NONE;
}
int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
unsigned long fault_addr)
{
const struct exception_table_entry *e;
- ex_handler_t handler;
#ifdef CONFIG_PNPBIOS
if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) {
@@ -179,8 +129,35 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
if (!e)
return 0;
- handler = ex_fixup_handler(e);
- return handler(e, regs, trapnr, error_code, fault_addr);
+ switch (e->type) {
+ case EX_TYPE_DEFAULT:
+ case EX_TYPE_DEFAULT_MCE_SAFE:
+ return ex_handler_default(e, regs);
+ case EX_TYPE_FAULT:
+ case EX_TYPE_FAULT_MCE_SAFE:
+ return ex_handler_fault(e, regs, trapnr);
+ case EX_TYPE_UACCESS:
+ return ex_handler_uaccess(e, regs, trapnr);
+ case EX_TYPE_COPY:
+ return ex_handler_copy(e, regs, trapnr);
+ case EX_TYPE_CLEAR_FS:
+ return ex_handler_clear_fs(e, regs);
+ case EX_TYPE_FPU_RESTORE:
+ return ex_handler_fprestore(e, regs);
+ case EX_TYPE_RDMSR:
+ return ex_handler_rdmsr_unsafe(e, regs);
+ case EX_TYPE_WRMSR:
+ return ex_handler_wrmsr_unsafe(e, regs);
+ case EX_TYPE_BPF:
+ return ex_handler_bpf(e, regs);
+ case EX_TYPE_RDMSR_IN_MCE:
+ ex_handler_msr_mce(regs, false);
+ break;
+ case EX_TYPE_WRMSR_IN_MCE:
+ ex_handler_msr_mce(regs, true);
+ break;
+ }
+ BUG();
}
extern unsigned int early_recursion_flag;
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 39c802525fce..8796559f62a4 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -803,9 +803,7 @@ static int emit_atomic(u8 **pprog, u8 atomic_op,
return 0;
}
-static bool ex_handler_bpf(const struct exception_table_entry *x,
- struct pt_regs *regs, int trapnr,
- unsigned long error_code, unsigned long fault_addr)
+bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs)
{
u32 reg = x->fixup >> 8;
@@ -1288,12 +1286,7 @@ st: if (is_imm8(insn->off))
}
ex->insn = delta;
- delta = (u8 *)ex_handler_bpf - (u8 *)&ex->handler;
- if (!is_simm32(delta)) {
- pr_err("extable->handler doesn't fit into 32-bit\n");
- return -EFAULT;
- }
- ex->handler = delta;
+ ex->type = EX_TYPE_BPF;
if (dst_reg > BPF_REG_9) {
pr_err("verifier error\n");
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 6665f8802098..9f2b251e83c5 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -20,7 +20,7 @@
#include <asm/page.h>
#include <asm/mce.h>
#include <asm/suspend.h>
-#include <asm/fpu/internal.h>
+#include <asm/fpu/api.h>
#include <asm/debugreg.h>
#include <asm/cpu.h>
#include <asm/mmu_context.h>
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 3f96a6374e4f..7d34105e20c6 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -464,6 +464,12 @@ int __save_altstack(stack_t __user *, unsigned long);
unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \
} while (0);
+#ifdef CONFIG_DYNAMIC_SIGFRAME
+bool sigaltstack_size_valid(size_t ss_size);
+#else
+static inline bool sigaltstack_size_valid(size_t size) { return true; }
+#endif /* !CONFIG_DYNAMIC_SIGFRAME */
+
#ifdef CONFIG_PROC_FS
struct seq_file;
extern void render_sigset_t(struct seq_file *, const char *, sigset_t *);
diff --git a/kernel/signal.c b/kernel/signal.c
index 487bf4f5dadf..e99aff33ff14 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -4138,11 +4138,29 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
return 0;
}
+#ifdef CONFIG_DYNAMIC_SIGFRAME
+static inline void sigaltstack_lock(void)
+ __acquires(&current->sighand->siglock)
+{
+ spin_lock_irq(&current->sighand->siglock);
+}
+
+static inline void sigaltstack_unlock(void)
+ __releases(&current->sighand->siglock)
+{
+ spin_unlock_irq(&current->sighand->siglock);
+}
+#else
+static inline void sigaltstack_lock(void) { }
+static inline void sigaltstack_unlock(void) { }
+#endif
+
static int
do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp,
size_t min_ss_size)
{
struct task_struct *t = current;
+ int ret = 0;
if (oss) {
memset(oss, 0, sizeof(stack_t));
@@ -4166,19 +4184,24 @@ do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp,
ss_mode != 0))
return -EINVAL;
+ sigaltstack_lock();
if (ss_mode == SS_DISABLE) {
ss_size = 0;
ss_sp = NULL;
} else {
if (unlikely(ss_size < min_ss_size))
- return -ENOMEM;
+ ret = -ENOMEM;
+ if (!sigaltstack_size_valid(ss_size))
+ ret = -ENOMEM;
}
-
- t->sas_ss_sp = (unsigned long) ss_sp;
- t->sas_ss_size = ss_size;
- t->sas_ss_flags = ss_flags;
+ if (!ret) {
+ t->sas_ss_sp = (unsigned long) ss_sp;
+ t->sas_ss_size = ss_size;
+ t->sas_ss_flags = ss_flags;
+ }
+ sigaltstack_unlock();
}
- return 0;
+ return ret;
}
SYSCALL_DEFINE2(sigaltstack,const stack_t __user *,uss, stack_t __user *,uoss)
diff --git a/scripts/sorttable.c b/scripts/sorttable.c
index 6ee4fa882919..278bb53b325c 100644
--- a/scripts/sorttable.c
+++ b/scripts/sorttable.c
@@ -240,7 +240,7 @@ static void x86_sort_relative_table(char *extab_image, int image_size)
w(r(loc) + i, loc);
w(r(loc + 1) + i + 4, loc + 1);
- w(r(loc + 2) + i + 8, loc + 2);
+ /* Don't touch the fixup type */
i += sizeof(uint32_t) * 3;
}
@@ -253,7 +253,7 @@ static void x86_sort_relative_table(char *extab_image, int image_size)
w(r(loc) - i, loc);
w(r(loc + 1) - (i + 4), loc + 1);
- w(r(loc + 2) - (i + 8), loc + 2);
+ /* Don't touch the fixup type */
i += sizeof(uint32_t) * 3;
}
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index b4142cd1c5c2..8a1f62ab3c8e 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -18,7 +18,7 @@ TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \
test_FCMOV test_FCOMI test_FISTTP \
vdso_restorer
TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering \
- corrupt_xstate_header
+ corrupt_xstate_header amx
# Some selftests require 32bit support enabled also on 64bit systems
TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall
diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c
new file mode 100644
index 000000000000..3615ef4a48bb
--- /dev/null
+++ b/tools/testing/selftests/x86/amx.c
@@ -0,0 +1,851 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <err.h>
+#include <errno.h>
+#include <pthread.h>
+#include <setjmp.h>
+#include <stdio.h>
+#include <string.h>
+#include <stdbool.h>
+#include <unistd.h>
+#include <x86intrin.h>
+
+#include <sys/auxv.h>
+#include <sys/mman.h>
+#include <sys/shm.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+
+#ifndef __x86_64__
+# error This test is 64-bit only
+#endif
+
+#define XSAVE_HDR_OFFSET 512
+#define XSAVE_HDR_SIZE 64
+
+struct xsave_buffer {
+ union {
+ struct {
+ char legacy[XSAVE_HDR_OFFSET];
+ char header[XSAVE_HDR_SIZE];
+ char extended[0];
+ };
+ char bytes[0];
+ };
+};
+
+static inline uint64_t xgetbv(uint32_t index)
+{
+ uint32_t eax, edx;
+
+ asm volatile("xgetbv;"
+ : "=a" (eax), "=d" (edx)
+ : "c" (index));
+ return eax + ((uint64_t)edx << 32);
+}
+
+static inline void cpuid(uint32_t *eax, uint32_t *ebx, uint32_t *ecx, uint32_t *edx)
+{
+ asm volatile("cpuid;"
+ : "=a" (*eax), "=b" (*ebx), "=c" (*ecx), "=d" (*edx)
+ : "0" (*eax), "2" (*ecx));
+}
+
+static inline void xsave(struct xsave_buffer *xbuf, uint64_t rfbm)
+{
+ uint32_t rfbm_lo = rfbm;
+ uint32_t rfbm_hi = rfbm >> 32;
+
+ asm volatile("xsave (%%rdi)"
+ : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi)
+ : "memory");
+}
+
+static inline void xrstor(struct xsave_buffer *xbuf, uint64_t rfbm)
+{
+ uint32_t rfbm_lo = rfbm;
+ uint32_t rfbm_hi = rfbm >> 32;
+
+ asm volatile("xrstor (%%rdi)"
+ : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi));
+}
+
+/* err() exits and will not return */
+#define fatal_error(msg, ...) err(1, "[FAIL]\t" msg, ##__VA_ARGS__)
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+ int flags)
+{
+ struct sigaction sa;
+
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_sigaction = handler;
+ sa.sa_flags = SA_SIGINFO | flags;
+ sigemptyset(&sa.sa_mask);
+ if (sigaction(sig, &sa, 0))
+ fatal_error("sigaction");
+}
+
+static void clearhandler(int sig)
+{
+ struct sigaction sa;
+
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_handler = SIG_DFL;
+ sigemptyset(&sa.sa_mask);
+ if (sigaction(sig, &sa, 0))
+ fatal_error("sigaction");
+}
+
+#define XFEATURE_XTILECFG 17
+#define XFEATURE_XTILEDATA 18
+#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG)
+#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA)
+#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA)
+
+#define CPUID_LEAF1_ECX_XSAVE_MASK (1 << 26)
+#define CPUID_LEAF1_ECX_OSXSAVE_MASK (1 << 27)
+static inline void check_cpuid_xsave(void)
+{
+ uint32_t eax, ebx, ecx, edx;
+
+ /*
+ * CPUID.1:ECX.XSAVE[bit 26] enumerates general
+ * support for the XSAVE feature set, including
+ * XGETBV.
+ */
+ eax = 1;
+ ecx = 0;
+ cpuid(&eax, &ebx, &ecx, &edx);
+ if (!(ecx & CPUID_LEAF1_ECX_XSAVE_MASK))
+ fatal_error("cpuid: no CPU xsave support");
+ if (!(ecx & CPUID_LEAF1_ECX_OSXSAVE_MASK))
+ fatal_error("cpuid: no OS xsave support");
+}
+
+static uint32_t xbuf_size;
+
+static struct {
+ uint32_t xbuf_offset;
+ uint32_t size;
+} xtiledata;
+
+#define CPUID_LEAF_XSTATE 0xd
+#define CPUID_SUBLEAF_XSTATE_USER 0x0
+#define TILE_CPUID 0x1d
+#define TILE_PALETTE_ID 0x1
+
+static void check_cpuid_xtiledata(void)
+{
+ uint32_t eax, ebx, ecx, edx;
+
+ eax = CPUID_LEAF_XSTATE;
+ ecx = CPUID_SUBLEAF_XSTATE_USER;
+ cpuid(&eax, &ebx, &ecx, &edx);
+
+ /*
+ * EBX enumerates the size (in bytes) required by the XSAVE
+ * instruction for an XSAVE area containing all the user state
+ * components corresponding to bits currently set in XCR0.
+ *
+ * Stash that off so it can be used to allocate buffers later.
+ */
+ xbuf_size = ebx;
+
+ eax = CPUID_LEAF_XSTATE;
+ ecx = XFEATURE_XTILEDATA;
+
+ cpuid(&eax, &ebx, &ecx, &edx);
+ /*
+ * eax: XTILEDATA state component size
+ * ebx: XTILEDATA state component offset in user buffer
+ */
+ if (!eax || !ebx)
+ fatal_error("xstate cpuid: invalid tile data size/offset: %d/%d",
+ eax, ebx);
+
+ xtiledata.size = eax;
+ xtiledata.xbuf_offset = ebx;
+}
+
+/* The helpers for managing XSAVE buffer and tile states: */
+
+struct xsave_buffer *alloc_xbuf(void)
+{
+ struct xsave_buffer *xbuf;
+
+ /* XSAVE buffer should be 64B-aligned. */
+ xbuf = aligned_alloc(64, xbuf_size);
+ if (!xbuf)
+ fatal_error("aligned_alloc()");
+ return xbuf;
+}
+
+static inline void clear_xstate_header(struct xsave_buffer *buffer)
+{
+ memset(&buffer->header, 0, sizeof(buffer->header));
+}
+
+static inline uint64_t get_xstatebv(struct xsave_buffer *buffer)
+{
+ /* XSTATE_BV is at the beginning of the header: */
+ return *(uint64_t *)&buffer->header;
+}
+
+static inline void set_xstatebv(struct xsave_buffer *buffer, uint64_t bv)
+{
+ /* XSTATE_BV is at the beginning of the header: */
+ *(uint64_t *)(&buffer->header) = bv;
+}
+
+static void set_rand_tiledata(struct xsave_buffer *xbuf)
+{
+ int *ptr = (int *)&xbuf->bytes[xtiledata.xbuf_offset];
+ int data;
+ int i;
+
+ /*
+ * Ensure that 'data' is never 0. This ensures that
+ * the registers are never in their initial configuration
+ * and thus never tracked as being in the init state.
+ */
+ data = rand() | 1;
+
+ for (i = 0; i < xtiledata.size / sizeof(int); i++, ptr++)
+ *ptr = data;
+}
+
+struct xsave_buffer *stashed_xsave;
+
+static void init_stashed_xsave(void)
+{
+ stashed_xsave = alloc_xbuf();
+ if (!stashed_xsave)
+ fatal_error("failed to allocate stashed_xsave\n");
+ clear_xstate_header(stashed_xsave);
+}
+
+static void free_stashed_xsave(void)
+{
+ free(stashed_xsave);
+}
+
+/* See 'struct _fpx_sw_bytes' at sigcontext.h */
+#define SW_BYTES_OFFSET 464
+/* N.B. The struct's field name varies so read from the offset. */
+#define SW_BYTES_BV_OFFSET (SW_BYTES_OFFSET + 8)
+
+static inline struct _fpx_sw_bytes *get_fpx_sw_bytes(void *buffer)
+{
+ return (struct _fpx_sw_bytes *)(buffer + SW_BYTES_OFFSET);
+}
+
+static inline uint64_t get_fpx_sw_bytes_features(void *buffer)
+{
+ return *(uint64_t *)(buffer + SW_BYTES_BV_OFFSET);
+}
+
+/* Work around printf() being unsafe in signals: */
+#define SIGNAL_BUF_LEN 1000
+char signal_message_buffer[SIGNAL_BUF_LEN];
+void sig_print(char *msg)
+{
+ int left = SIGNAL_BUF_LEN - strlen(signal_message_buffer) - 1;
+
+ strncat(signal_message_buffer, msg, left);
+}
+
+static volatile bool noperm_signaled;
+static int noperm_errs;
+/*
+ * Signal handler for when AMX is used but
+ * permission has not been obtained.
+ */
+static void handle_noperm(int sig, siginfo_t *si, void *ctx_void)
+{
+ ucontext_t *ctx = (ucontext_t *)ctx_void;
+ void *xbuf = ctx->uc_mcontext.fpregs;
+ struct _fpx_sw_bytes *sw_bytes;
+ uint64_t features;
+
+ /* Reset the signal message buffer: */
+ signal_message_buffer[0] = '\0';
+ sig_print("\tAt SIGILL handler,\n");
+
+ if (si->si_code != ILL_ILLOPC) {
+ noperm_errs++;
+ sig_print("[FAIL]\tInvalid signal code.\n");
+ } else {
+ sig_print("[OK]\tValid signal code (ILL_ILLOPC).\n");
+ }
+
+ sw_bytes = get_fpx_sw_bytes(xbuf);
+ /*
+ * Without permission, the signal XSAVE buffer should not
+ * have room for AMX register state (aka. xtiledata).
+ * Check that the size does not overlap with where xtiledata
+ * will reside.
+ *
+ * This also implies that no state components *PAST*
+ * XTILEDATA (features >=19) can be present in the buffer.
+ */
+ if (sw_bytes->xstate_size <= xtiledata.xbuf_offset) {
+ sig_print("[OK]\tValid xstate size\n");
+ } else {
+ noperm_errs++;
+ sig_print("[FAIL]\tInvalid xstate size\n");
+ }
+
+ features = get_fpx_sw_bytes_features(xbuf);
+ /*
+ * Without permission, the XTILEDATA feature
+ * bit should not be set.
+ */
+ if ((features & XFEATURE_MASK_XTILEDATA) == 0) {
+ sig_print("[OK]\tValid xstate mask\n");
+ } else {
+ noperm_errs++;
+ sig_print("[FAIL]\tInvalid xstate mask\n");
+ }
+
+ noperm_signaled = true;
+ ctx->uc_mcontext.gregs[REG_RIP] += 3; /* Skip the faulting XRSTOR */
+}
+
+/* Return true if XRSTOR is successful; otherwise, false. */
+static inline bool xrstor_safe(struct xsave_buffer *xbuf, uint64_t mask)
+{
+ noperm_signaled = false;
+ xrstor(xbuf, mask);
+
+ /* Print any messages produced by the signal code: */
+ printf("%s", signal_message_buffer);
+ /*
+ * Reset the buffer to make sure any future printing
+ * only outputs new messages:
+ */
+ signal_message_buffer[0] = '\0';
+
+ if (noperm_errs)
+ fatal_error("saw %d errors in noperm signal handler\n", noperm_errs);
+
+ return !noperm_signaled;
+}
+
+/*
+ * Use XRSTOR to populate the XTILEDATA registers with
+ * random data.
+ *
+ * Return true if successful; otherwise, false.
+ */
+static inline bool load_rand_tiledata(struct xsave_buffer *xbuf)
+{
+ clear_xstate_header(xbuf);
+ set_xstatebv(xbuf, XFEATURE_MASK_XTILEDATA);
+ set_rand_tiledata(xbuf);
+ return xrstor_safe(xbuf, XFEATURE_MASK_XTILEDATA);
+}
+
+/* Return XTILEDATA to its initial configuration. */
+static inline void init_xtiledata(void)
+{
+ clear_xstate_header(stashed_xsave);
+ xrstor_safe(stashed_xsave, XFEATURE_MASK_XTILEDATA);
+}
+
+enum expected_result { FAIL_EXPECTED, SUCCESS_EXPECTED };
+
+/* arch_prctl() and sigaltstack() test */
+
+#define ARCH_GET_XCOMP_PERM 0x1022
+#define ARCH_REQ_XCOMP_PERM 0x1023
+
+static void req_xtiledata_perm(void)
+{
+ syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_PERM, XFEATURE_XTILEDATA);
+}
+
+static void validate_req_xcomp_perm(enum expected_result exp)
+{
+ unsigned long bitmask;
+ long rc;
+
+ rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_PERM, XFEATURE_XTILEDATA);
+ if (exp == FAIL_EXPECTED) {
+ if (rc) {
+ printf("[OK]\tARCH_REQ_XCOMP_PERM saw expected failure..\n");
+ return;
+ }
+
+ fatal_error("ARCH_REQ_XCOMP_PERM saw unexpected success.\n");
+ } else if (rc) {
+ fatal_error("ARCH_REQ_XCOMP_PERM saw unexpected failure.\n");
+ }
+
+ rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_PERM, &bitmask);
+ if (rc) {
+ fatal_error("prctl(ARCH_GET_XCOMP_PERM) error: %ld", rc);
+ } else if (bitmask & XFEATURE_MASK_XTILE) {
+ printf("\tARCH_REQ_XCOMP_PERM is successful.\n");
+ }
+}
+
+static void validate_xcomp_perm(enum expected_result exp)
+{
+ bool load_success = load_rand_tiledata(stashed_xsave);
+
+ if (exp == FAIL_EXPECTED) {
+ if (load_success) {
+ noperm_errs++;
+ printf("[FAIL]\tLoad tiledata succeeded.\n");
+ } else {
+ printf("[OK]\tLoad tiledata failed.\n");
+ }
+ } else if (exp == SUCCESS_EXPECTED) {
+ if (load_success) {
+ printf("[OK]\tLoad tiledata succeeded.\n");
+ } else {
+ noperm_errs++;
+ printf("[FAIL]\tLoad tiledata failed.\n");
+ }
+ }
+}
+
+#ifndef AT_MINSIGSTKSZ
+# define AT_MINSIGSTKSZ 51
+#endif
+
+static void *alloc_altstack(unsigned int size)
+{
+ void *altstack;
+
+ altstack = mmap(NULL, size, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0);
+
+ if (altstack == MAP_FAILED)
+ fatal_error("mmap() for altstack");
+
+ return altstack;
+}
+
+static void setup_altstack(void *addr, unsigned long size, enum expected_result exp)
+{
+ stack_t ss;
+ int rc;
+
+ memset(&ss, 0, sizeof(ss));
+ ss.ss_size = size;
+ ss.ss_sp = addr;
+
+ rc = sigaltstack(&ss, NULL);
+
+ if (exp == FAIL_EXPECTED) {
+ if (rc) {
+ printf("[OK]\tsigaltstack() failed.\n");
+ } else {
+ fatal_error("sigaltstack() succeeded unexpectedly.\n");
+ }
+ } else if (rc) {
+ fatal_error("sigaltstack()");
+ }
+}
+
+static void test_dynamic_sigaltstack(void)
+{
+ unsigned int small_size, enough_size;
+ unsigned long minsigstksz;
+ void *altstack;
+
+ minsigstksz = getauxval(AT_MINSIGSTKSZ);
+ printf("\tAT_MINSIGSTKSZ = %lu\n", minsigstksz);
+ /*
+ * getauxval() itself can return 0 for failure or
+ * success. But, in this case, AT_MINSIGSTKSZ
+ * will always return a >=0 value if implemented.
+ * Just check for 0.
+ */
+ if (minsigstksz == 0) {
+ printf("no support for AT_MINSIGSTKSZ, skipping sigaltstack tests\n");
+ return;
+ }
+
+ enough_size = minsigstksz * 2;
+
+ altstack = alloc_altstack(enough_size);
+ printf("\tAllocate memory for altstack (%u bytes).\n", enough_size);
+
+ /*
+ * Try setup_altstack() with a size which can not fit
+ * XTILEDATA. ARCH_REQ_XCOMP_PERM should fail.
+ */
+ small_size = minsigstksz - xtiledata.size;
+ printf("\tAfter sigaltstack() with small size (%u bytes).\n", small_size);
+ setup_altstack(altstack, small_size, SUCCESS_EXPECTED);
+ validate_req_xcomp_perm(FAIL_EXPECTED);
+
+ /*
+ * Try setup_altstack() with a size derived from
+ * AT_MINSIGSTKSZ. It should be more than large enough
+ * and thus ARCH_REQ_XCOMP_PERM should succeed.
+ */
+ printf("\tAfter sigaltstack() with enough size (%u bytes).\n", enough_size);
+ setup_altstack(altstack, enough_size, SUCCESS_EXPECTED);
+ validate_req_xcomp_perm(SUCCESS_EXPECTED);
+
+ /*
+ * Try to coerce setup_altstack() to again accept a
+ * too-small altstack. This ensures that big-enough
+ * sigaltstacks can not shrink to a too-small value
+ * once XTILEDATA permission is established.
+ */
+ printf("\tThen, sigaltstack() with small size (%u bytes).\n", small_size);
+ setup_altstack(altstack, small_size, FAIL_EXPECTED);
+}
+
+static void test_dynamic_state(void)
+{
+ pid_t parent, child, grandchild;
+
+ parent = fork();
+ if (parent < 0) {
+ /* fork() failed */
+ fatal_error("fork");
+ } else if (parent > 0) {
+ int status;
+ /* fork() succeeded. Now in the parent. */
+
+ wait(&status);
+ if (!WIFEXITED(status) || WEXITSTATUS(status))
+ fatal_error("arch_prctl test parent exit");
+ return;
+ }
+ /* fork() succeeded. Now in the child . */
+
+ printf("[RUN]\tCheck ARCH_REQ_XCOMP_PERM around process fork() and sigaltack() test.\n");
+
+ printf("\tFork a child.\n");
+ child = fork();
+ if (child < 0) {
+ fatal_error("fork");
+ } else if (child > 0) {
+ int status;
+
+ wait(&status);
+ if (!WIFEXITED(status) || WEXITSTATUS(status))
+ fatal_error("arch_prctl test child exit");
+ _exit(0);
+ }
+
+ /*
+ * The permission request should fail without an
+ * XTILEDATA-compatible signal stack
+ */
+ printf("\tTest XCOMP_PERM at child.\n");
+ validate_xcomp_perm(FAIL_EXPECTED);
+
+ /*
+ * Set up an XTILEDATA-compatible signal stack and
+ * also obtain permission to populate XTILEDATA.
+ */
+ printf("\tTest dynamic sigaltstack at child:\n");
+ test_dynamic_sigaltstack();
+
+ /* Ensure that XTILEDATA can be populated. */
+ printf("\tTest XCOMP_PERM again at child.\n");
+ validate_xcomp_perm(SUCCESS_EXPECTED);
+
+ printf("\tFork a grandchild.\n");
+ grandchild = fork();
+ if (grandchild < 0) {
+ /* fork() failed */
+ fatal_error("fork");
+ } else if (!grandchild) {
+ /* fork() succeeded. Now in the (grand)child. */
+ printf("\tTest XCOMP_PERM at grandchild.\n");
+
+ /*
+ * Ensure that the grandchild inherited
+ * permission and a compatible sigaltstack:
+ */
+ validate_xcomp_perm(SUCCESS_EXPECTED);
+ } else {
+ int status;
+ /* fork() succeeded. Now in the parent. */
+
+ wait(&status);
+ if (!WIFEXITED(status) || WEXITSTATUS(status))
+ fatal_error("fork test grandchild");
+ }
+
+ _exit(0);
+}
+
+/*
+ * Save current register state and compare it to @xbuf1.'
+ *
+ * Returns false if @xbuf1 matches the registers.
+ * Returns true if @xbuf1 differs from the registers.
+ */
+static inline bool __validate_tiledata_regs(struct xsave_buffer *xbuf1)
+{
+ struct xsave_buffer *xbuf2;
+ int ret;
+
+ xbuf2 = alloc_xbuf();
+ if (!xbuf2)
+ fatal_error("failed to allocate XSAVE buffer\n");
+
+ xsave(xbuf2, XFEATURE_MASK_XTILEDATA);
+ ret = memcmp(&xbuf1->bytes[xtiledata.xbuf_offset],
+ &xbuf2->bytes[xtiledata.xbuf_offset],
+ xtiledata.size);
+
+ free(xbuf2);
+
+ if (ret == 0)
+ return false;
+ return true;
+}
+
+static inline void validate_tiledata_regs_same(struct xsave_buffer *xbuf)
+{
+ int ret = __validate_tiledata_regs(xbuf);
+
+ if (ret != 0)
+ fatal_error("TILEDATA registers changed");
+}
+
+static inline void validate_tiledata_regs_changed(struct xsave_buffer *xbuf)
+{
+ int ret = __validate_tiledata_regs(xbuf);
+
+ if (ret == 0)
+ fatal_error("TILEDATA registers did not change");
+}
+
+/* tiledata inheritance test */
+
+static void test_fork(void)
+{
+ pid_t child, grandchild;
+
+ child = fork();
+ if (child < 0) {
+ /* fork() failed */
+ fatal_error("fork");
+ } else if (child > 0) {
+ /* fork() succeeded. Now in the parent. */
+ int status;
+
+ wait(&status);
+ if (!WIFEXITED(status) || WEXITSTATUS(status))
+ fatal_error("fork test child");
+ return;
+ }
+ /* fork() succeeded. Now in the child. */
+ printf("[RUN]\tCheck tile data inheritance.\n\tBefore fork(), load tiledata\n");
+
+ load_rand_tiledata(stashed_xsave);
+
+ grandchild = fork();
+ if (grandchild < 0) {
+ /* fork() failed */
+ fatal_error("fork");
+ } else if (grandchild > 0) {
+ /* fork() succeeded. Still in the first child. */
+ int status;
+
+ wait(&status);
+ if (!WIFEXITED(status) || WEXITSTATUS(status))
+ fatal_error("fork test grand child");
+ _exit(0);
+ }
+ /* fork() succeeded. Now in the (grand)child. */
+
+ /*
+ * TILEDATA registers are not preserved across fork().
+ * Ensure that their value has changed:
+ */
+ validate_tiledata_regs_changed(stashed_xsave);
+
+ _exit(0);
+}
+
+/* Context switching test */
+
+static struct _ctxtswtest_cfg {
+ unsigned int iterations;
+ unsigned int num_threads;
+} ctxtswtest_config;
+
+struct futex_info {
+ pthread_t thread;
+ int nr;
+ pthread_mutex_t mutex;
+ struct futex_info *next;
+};
+
+static void *check_tiledata(void *info)
+{
+ struct futex_info *finfo = (struct futex_info *)info;
+ struct xsave_buffer *xbuf;
+ int i;
+
+ xbuf = alloc_xbuf();
+ if (!xbuf)
+ fatal_error("unable to allocate XSAVE buffer");
+
+ /*
+ * Load random data into 'xbuf' and then restore
+ * it to the tile registers themselves.
+ */
+ load_rand_tiledata(xbuf);
+ for (i = 0; i < ctxtswtest_config.iterations; i++) {
+ pthread_mutex_lock(&finfo->mutex);
+
+ /*
+ * Ensure the register values have not
+ * diverged from those recorded in 'xbuf'.
+ */
+ validate_tiledata_regs_same(xbuf);
+
+ /* Load new, random values into xbuf and registers */
+ load_rand_tiledata(xbuf);
+
+ /*
+ * The last thread's last unlock will be for
+ * thread 0's mutex. However, thread 0 will
+ * have already exited the loop and the mutex
+ * will already be unlocked.
+ *
+ * Because this is not an ERRORCHECK mutex,
+ * that inconsistency will be silently ignored.
+ */
+ pthread_mutex_unlock(&finfo->next->mutex);
+ }
+
+ free(xbuf);
+ /*
+ * Return this thread's finfo, which is
+ * a unique value for this thread.
+ */
+ return finfo;
+}
+
+static int create_threads(int num, struct futex_info *finfo)
+{
+ int i;
+
+ for (i = 0; i < num; i++) {
+ int next_nr;
+
+ finfo[i].nr = i;
+ /*
+ * Thread 'i' will wait on this mutex to
+ * be unlocked. Lock it immediately after
+ * initialization:
+ */
+ pthread_mutex_init(&finfo[i].mutex, NULL);
+ pthread_mutex_lock(&finfo[i].mutex);
+
+ next_nr = (i + 1) % num;
+ finfo[i].next = &finfo[next_nr];
+
+ if (pthread_create(&finfo[i].thread, NULL, check_tiledata, &finfo[i]))
+ fatal_error("pthread_create()");
+ }
+ return 0;
+}
+
+static void affinitize_cpu0(void)
+{
+ cpu_set_t cpuset;
+
+ CPU_ZERO(&cpuset);
+ CPU_SET(0, &cpuset);
+
+ if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+ fatal_error("sched_setaffinity to CPU 0");
+}
+
+static void test_context_switch(void)
+{
+ struct futex_info *finfo;
+ int i;
+
+ /* Affinitize to one CPU to force context switches */
+ affinitize_cpu0();
+
+ req_xtiledata_perm();
+
+ printf("[RUN]\tCheck tiledata context switches, %d iterations, %d threads.\n",
+ ctxtswtest_config.iterations,
+ ctxtswtest_config.num_threads);
+
+
+ finfo = malloc(sizeof(*finfo) * ctxtswtest_config.num_threads);
+ if (!finfo)
+ fatal_error("malloc()");
+
+ create_threads(ctxtswtest_config.num_threads, finfo);
+
+ /*
+ * This thread wakes up thread 0
+ * Thread 0 will wake up 1
+ * Thread 1 will wake up 2
+ * ...
+ * the last thread will wake up 0
+ *
+ * ... this will repeat for the configured
+ * number of iterations.
+ */
+ pthread_mutex_unlock(&finfo[0].mutex);
+
+ /* Wait for all the threads to finish: */
+ for (i = 0; i < ctxtswtest_config.num_threads; i++) {
+ void *thread_retval;
+ int rc;
+
+ rc = pthread_join(finfo[i].thread, &thread_retval);
+
+ if (rc)
+ fatal_error("pthread_join() failed for thread %d err: %d\n",
+ i, rc);
+
+ if (thread_retval != &finfo[i])
+ fatal_error("unexpected thread retval for thread %d: %p\n",
+ i, thread_retval);
+
+ }
+
+ printf("[OK]\tNo incorrect case was found.\n");
+
+ free(finfo);
+}
+
+int main(void)
+{
+ /* Check hardware availability at first */
+ check_cpuid_xsave();
+ check_cpuid_xtiledata();
+
+ init_stashed_xsave();
+ sethandler(SIGILL, handle_noperm, 0);
+
+ test_dynamic_state();
+
+ /* Request permission for the following tests */
+ req_xtiledata_perm();
+
+ test_fork();
+
+ ctxtswtest_config.iterations = 10;
+ ctxtswtest_config.num_threads = 5;
+ test_context_switch();
+
+ clearhandler(SIGILL);
+ free_stashed_xsave();
+
+ return 0;
+}