From 7cd60e43a6def40ecb75deb8decc677995970d0b Mon Sep 17 00:00:00 2001 From: "Chang S. Bae" Date: Tue, 18 May 2021 13:03:15 -0700 Subject: [PATCH 01/74] uapi/auxvec: Define the aux vector AT_MINSIGSTKSZ Define AT_MINSIGSTKSZ in the generic uapi header. It is already used as generic ABI in glibc's generic elf.h, and this define will prevent future namespace conflicts. In particular, x86 is also using this generic definition. Signed-off-by: Chang S. Bae Signed-off-by: Borislav Petkov Reviewed-by: Len Brown Acked-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20210518200320.17239-2-chang.seok.bae@intel.com --- include/uapi/linux/auxvec.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/include/uapi/linux/auxvec.h b/include/uapi/linux/auxvec.h index abe5f2b6581be7..c7e502bf5a6fad 100644 --- a/include/uapi/linux/auxvec.h +++ b/include/uapi/linux/auxvec.h @@ -33,5 +33,8 @@ #define AT_EXECFN 31 /* filename of program */ +#ifndef AT_MINSIGSTKSZ +#define AT_MINSIGSTKSZ 51 /* minimal stack size for signal delivery */ +#endif #endif /* _UAPI_LINUX_AUXVEC_H */ From 939ef713297df2cc910592305aa26af0e87f28ac Mon Sep 17 00:00:00 2001 From: "Chang S. Bae" Date: Tue, 18 May 2021 13:03:16 -0700 Subject: [PATCH 02/74] x86/signal: Introduce helpers to get the maximum signal frame size Signal frames do not have a fixed format and can vary in size when a number of things change: supported XSAVE features, 32 vs. 64-bit apps, etc. Add support for a runtime method for userspace to dynamically discover how large a signal stack needs to be. Introduce a new variable, max_frame_size, and helper functions for the calculation to be used in a new user interface. Set max_frame_size to a system-wide worst-case value, instead of storing multiple app-specific values. Signed-off-by: Chang S. Bae Signed-off-by: Borislav Petkov Reviewed-by: Len Brown Acked-by: Thomas Gleixner Acked-by: H.J. Lu Link: https://lkml.kernel.org/r/20210518200320.17239-3-chang.seok.bae@intel.com --- arch/x86/include/asm/fpu/signal.h | 2 ++ arch/x86/include/asm/sigframe.h | 2 ++ arch/x86/kernel/cpu/common.c | 3 ++ arch/x86/kernel/fpu/signal.c | 19 ++++++++++ arch/x86/kernel/signal.c | 59 +++++++++++++++++++++++++++++-- 5 files changed, 83 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h index 7fb516b6893a8f..8b6631dffefdf2 100644 --- a/arch/x86/include/asm/fpu/signal.h +++ b/arch/x86/include/asm/fpu/signal.h @@ -29,6 +29,8 @@ unsigned long fpu__alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx, unsigned long *size); +unsigned long fpu__get_fpstate_size(void); + extern void fpu__init_prepare_fx_sw_frame(void); #endif /* _ASM_X86_FPU_SIGNAL_H */ diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h index 84eab272487542..5b1ed650b12489 100644 --- a/arch/x86/include/asm/sigframe.h +++ b/arch/x86/include/asm/sigframe.h @@ -85,4 +85,6 @@ struct rt_sigframe_x32 { #endif /* CONFIG_X86_64 */ +void __init init_sigframe_size(void); + #endif /* _ASM_X86_SIGFRAME_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a1b756c49a93a1..9173dd47581875 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -58,6 +58,7 @@ #include #include #include +#include #include "cpu.h" @@ -1332,6 +1333,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) fpu__init_system(c); + init_sigframe_size(); + #ifdef CONFIG_X86_32 /* * Regardless of whether PCID is enumerated, the SDM says diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index a4ec65317a7fa4..dbb304e48f1673 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -507,6 +507,25 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame, return sp; } + +unsigned long fpu__get_fpstate_size(void) +{ + unsigned long ret = xstate_sigframe_size(); + + /* + * This space is needed on (most) 32-bit kernels, or when a 32-bit + * app is running on a 64-bit kernel. To keep things simple, just + * assume the worst case and always include space for 'freg_state', + * even for 64-bit apps on 64-bit kernels. This wastes a bit of + * space, but keeps the code simple. + */ + if ((IS_ENABLED(CONFIG_IA32_EMULATION) || + IS_ENABLED(CONFIG_X86_32)) && use_fxsr()) + ret += sizeof(struct fregs_state); + + return ret; +} + /* * Prepare the SW reserved portion of the fxsave memory layout, indicating * the presence of the extended state information in the memory layout diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index a06cb107c0e88e..689a4b6dd18fc4 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -212,6 +212,11 @@ do { \ * Set up a signal frame. */ +/* x86 ABI requires 16-byte alignment */ +#define FRAME_ALIGNMENT 16UL + +#define MAX_FRAME_PADDING (FRAME_ALIGNMENT - 1) + /* * Determine which stack to use.. */ @@ -222,9 +227,9 @@ static unsigned long align_sigframe(unsigned long sp) * Align the stack pointer according to the i386 ABI, * i.e. so that on function entry ((sp + 4) & 15) == 0. */ - sp = ((sp + 4) & -16ul) - 4; + sp = ((sp + 4) & -FRAME_ALIGNMENT) - 4; #else /* !CONFIG_X86_32 */ - sp = round_down(sp, 16) - 8; + sp = round_down(sp, FRAME_ALIGNMENT) - 8; #endif return sp; } @@ -663,6 +668,56 @@ SYSCALL_DEFINE0(rt_sigreturn) return 0; } +/* + * There are four different struct types for signal frame: sigframe_ia32, + * rt_sigframe_ia32, rt_sigframe_x32, and rt_sigframe. Use the worst case + * -- the largest size. It means the size for 64-bit apps is a bit more + * than needed, but this keeps the code simple. + */ +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) +# define MAX_FRAME_SIGINFO_UCTXT_SIZE sizeof(struct sigframe_ia32) +#else +# define MAX_FRAME_SIGINFO_UCTXT_SIZE sizeof(struct rt_sigframe) +#endif + +/* + * The FP state frame contains an XSAVE buffer which must be 64-byte aligned. + * If a signal frame starts at an unaligned address, extra space is required. + * This is the max alignment padding, conservatively. + */ +#define MAX_XSAVE_PADDING 63UL + +/* + * The frame data is composed of the following areas and laid out as: + * + * ------------------------- + * | alignment padding | + * ------------------------- + * | (f)xsave frame | + * ------------------------- + * | fsave header | + * ------------------------- + * | alignment padding | + * ------------------------- + * | siginfo + ucontext | + * ------------------------- + */ + +/* max_frame_size tells userspace the worst case signal stack size. */ +static unsigned long __ro_after_init max_frame_size; + +void __init init_sigframe_size(void) +{ + max_frame_size = MAX_FRAME_SIGINFO_UCTXT_SIZE + MAX_FRAME_PADDING; + + max_frame_size += fpu__get_fpstate_size() + MAX_XSAVE_PADDING; + + /* Userspace expects an aligned size. */ + max_frame_size = round_up(max_frame_size, FRAME_ALIGNMENT); + + pr_info("max sigframe size: %lu\n", max_frame_size); +} + static inline int is_ia32_compat_frame(struct ksignal *ksig) { return IS_ENABLED(CONFIG_IA32_EMULATION) && From 1c33bb0507508af24fd754dd7123bd8e997fab2f Mon Sep 17 00:00:00 2001 From: "Chang S. Bae" Date: Tue, 18 May 2021 13:03:17 -0700 Subject: [PATCH 03/74] x86/elf: Support a new ELF aux vector AT_MINSIGSTKSZ Historically, signal.h defines MINSIGSTKSZ (2KB) and SIGSTKSZ (8KB), for use by all architectures with sigaltstack(2). Over time, the hardware state size grew, but these constants did not evolve. Today, literal use of these constants on several architectures may result in signal stack overflow, and thus user data corruption. A few years ago, the ARM team addressed this issue by establishing getauxval(AT_MINSIGSTKSZ). This enables the kernel to supply a value at runtime that is an appropriate replacement on current and future hardware. Add getauxval(AT_MINSIGSTKSZ) support to x86, analogous to the support added for ARM in 94b07c1f8c39 ("arm64: signal: Report signal frame size to userspace via auxv"). Also, include a documentation to describe x86-specific auxiliary vectors. Signed-off-by: Chang S. Bae Signed-off-by: Borislav Petkov Reviewed-by: Len Brown Acked-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20210518200320.17239-4-chang.seok.bae@intel.com --- Documentation/x86/elf_auxvec.rst | 53 ++++++++++++++++++++++++++++++ Documentation/x86/index.rst | 1 + arch/x86/include/asm/elf.h | 4 +++ arch/x86/include/uapi/asm/auxvec.h | 4 +-- arch/x86/kernel/signal.c | 5 +++ 5 files changed, 65 insertions(+), 2 deletions(-) create mode 100644 Documentation/x86/elf_auxvec.rst diff --git a/Documentation/x86/elf_auxvec.rst b/Documentation/x86/elf_auxvec.rst new file mode 100644 index 00000000000000..18e4744717f9e0 --- /dev/null +++ b/Documentation/x86/elf_auxvec.rst @@ -0,0 +1,53 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================== +x86-specific ELF Auxiliary Vectors +================================== + +This document describes the semantics of the x86 auxiliary vectors. + +Introduction +============ + +ELF Auxiliary vectors enable the kernel to efficiently provide +configuration-specific parameters to userspace. In this example, a program +allocates an alternate stack based on the kernel-provided size:: + + #include + #include + #include + #include + #include + #include + + #ifndef AT_MINSIGSTKSZ + #define AT_MINSIGSTKSZ 51 + #endif + + .... + stack_t ss; + + ss.ss_sp = malloc(ss.ss_size); + assert(ss.ss_sp); + + ss.ss_size = getauxval(AT_MINSIGSTKSZ) + SIGSTKSZ; + ss.ss_flags = 0; + + if (sigaltstack(&ss, NULL)) + err(1, "sigaltstack"); + + +The exposed auxiliary vectors +============================= + +AT_SYSINFO is used for locating the vsyscall entry point. It is not +exported on 64-bit mode. + +AT_SYSINFO_EHDR is the start address of the page containing the vDSO. + +AT_MINSIGSTKSZ denotes the minimum stack size required by the kernel to +deliver a signal to user-space. AT_MINSIGSTKSZ comprehends the space +consumed by the kernel to accommodate the user context for the current +hardware configuration. It does not comprehend subsequent user-space stack +consumption, which must be added by the user. (e.g. Above, user-space adds +SIGSTKSZ to AT_MINSIGSTKSZ.) diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst index 4693e192b447cc..d58614d5cde6b8 100644 --- a/Documentation/x86/index.rst +++ b/Documentation/x86/index.rst @@ -35,3 +35,4 @@ x86-specific Documentation sva sgx features + elf_auxvec diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 7d7500806af8a9..29fea180a6658e 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -312,6 +312,7 @@ do { \ NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \ NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \ } \ + NEW_AUX_ENT(AT_MINSIGSTKSZ, get_sigframe_size()); \ } while (0) /* @@ -328,6 +329,7 @@ extern unsigned long task_size_32bit(void); extern unsigned long task_size_64bit(int full_addr_space); extern unsigned long get_mmap_base(int is_legacy); extern bool mmap_address_hint_valid(unsigned long addr, unsigned long len); +extern unsigned long get_sigframe_size(void); #ifdef CONFIG_X86_32 @@ -349,6 +351,7 @@ do { \ if (vdso64_enabled) \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ (unsigned long __force)current->mm->context.vdso); \ + NEW_AUX_ENT(AT_MINSIGSTKSZ, get_sigframe_size()); \ } while (0) /* As a historical oddity, the x32 and x86_64 vDSOs are controlled together. */ @@ -357,6 +360,7 @@ do { \ if (vdso64_enabled) \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ (unsigned long __force)current->mm->context.vdso); \ + NEW_AUX_ENT(AT_MINSIGSTKSZ, get_sigframe_size()); \ } while (0) #define AT_SYSINFO 32 diff --git a/arch/x86/include/uapi/asm/auxvec.h b/arch/x86/include/uapi/asm/auxvec.h index 580e3c56704670..6beb55bbefa40b 100644 --- a/arch/x86/include/uapi/asm/auxvec.h +++ b/arch/x86/include/uapi/asm/auxvec.h @@ -12,9 +12,9 @@ /* entries in ARCH_DLINFO: */ #if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64) -# define AT_VECTOR_SIZE_ARCH 2 +# define AT_VECTOR_SIZE_ARCH 3 #else /* else it's non-compat x86-64 */ -# define AT_VECTOR_SIZE_ARCH 1 +# define AT_VECTOR_SIZE_ARCH 2 #endif #endif /* _ASM_X86_AUXVEC_H */ diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 689a4b6dd18fc4..86e53868159ad6 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -718,6 +718,11 @@ void __init init_sigframe_size(void) pr_info("max sigframe size: %lu\n", max_frame_size); } +unsigned long get_sigframe_size(void) +{ + return max_frame_size; +} + static inline int is_ia32_compat_frame(struct ksignal *ksig) { return IS_ENABLED(CONFIG_IA32_EMULATION) && From bdf6c8b84a4fa726c382ef6d3518f3ae123a7ebd Mon Sep 17 00:00:00 2001 From: "Chang S. Bae" Date: Tue, 18 May 2021 13:03:18 -0700 Subject: [PATCH 04/74] selftest/sigaltstack: Use the AT_MINSIGSTKSZ aux vector if available The SIGSTKSZ constant may not represent enough stack size in some architectures as the hardware state size grows. Use getauxval(AT_MINSIGSTKSZ) to increase the stack size. Signed-off-by: Chang S. Bae Signed-off-by: Borislav Petkov Reviewed-by: Len Brown Acked-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20210518200320.17239-5-chang.seok.bae@intel.com --- tools/testing/selftests/sigaltstack/sas.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c index 8934a3766d2076..c53b070755b65e 100644 --- a/tools/testing/selftests/sigaltstack/sas.c +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "../kselftest.h" @@ -24,6 +25,11 @@ #define SS_AUTODISARM (1U << 31) #endif +#ifndef AT_MINSIGSTKSZ +#define AT_MINSIGSTKSZ 51 +#endif + +static unsigned int stack_size; static void *sstack, *ustack; static ucontext_t uc, sc; static const char *msg = "[OK]\tStack preserved"; @@ -47,7 +53,7 @@ void my_usr1(int sig, siginfo_t *si, void *u) #endif if (sp < (unsigned long)sstack || - sp >= (unsigned long)sstack + SIGSTKSZ) { + sp >= (unsigned long)sstack + stack_size) { ksft_exit_fail_msg("SP is not on sigaltstack\n"); } /* put some data on stack. other sighandler will try to overwrite it */ @@ -108,6 +114,10 @@ int main(void) stack_t stk; int err; + /* Make sure more than the required minimum. */ + stack_size = getauxval(AT_MINSIGSTKSZ) + SIGSTKSZ; + ksft_print_msg("[NOTE]\tthe stack size is %lu\n", stack_size); + ksft_print_header(); ksft_set_plan(3); @@ -117,7 +127,7 @@ int main(void) sigaction(SIGUSR1, &act, NULL); act.sa_sigaction = my_usr2; sigaction(SIGUSR2, &act, NULL); - sstack = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE, + sstack = mmap(NULL, stack_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); if (sstack == MAP_FAILED) { ksft_exit_fail_msg("mmap() - %s\n", strerror(errno)); @@ -139,7 +149,7 @@ int main(void) } stk.ss_sp = sstack; - stk.ss_size = SIGSTKSZ; + stk.ss_size = stack_size; stk.ss_flags = SS_ONSTACK | SS_AUTODISARM; err = sigaltstack(&stk, NULL); if (err) { @@ -161,7 +171,7 @@ int main(void) } } - ustack = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE, + ustack = mmap(NULL, stack_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); if (ustack == MAP_FAILED) { ksft_exit_fail_msg("mmap() - %s\n", strerror(errno)); @@ -170,7 +180,7 @@ int main(void) getcontext(&uc); uc.uc_link = NULL; uc.uc_stack.ss_sp = ustack; - uc.uc_stack.ss_size = SIGSTKSZ; + uc.uc_stack.ss_size = stack_size; makecontext(&uc, switch_fn, 0); raise(SIGUSR1); From 2beb4a53fc3f1081cedc1c1a198c7f56cc4fc60c Mon Sep 17 00:00:00 2001 From: "Chang S. Bae" Date: Tue, 18 May 2021 13:03:19 -0700 Subject: [PATCH 05/74] x86/signal: Detect and prevent an alternate signal stack overflow The kernel pushes context on to the userspace stack to prepare for the user's signal handler. When the user has supplied an alternate signal stack, via sigaltstack(2), it is easy for the kernel to verify that the stack size is sufficient for the current hardware context. Check if writing the hardware context to the alternate stack will exceed it's size. If yes, then instead of corrupting user-data and proceeding with the original signal handler, an immediate SIGSEGV signal is delivered. Refactor the stack pointer check code from on_sig_stack() and use the new helper. While the kernel allows new source code to discover and use a sufficient alternate signal stack size, this check is still necessary to protect binaries with insufficient alternate signal stack size from data corruption. Fixes: c2bc11f10a39 ("x86, AVX-512: Enable AVX-512 States Context Switch") Reported-by: Florian Weimer Suggested-by: Jann Horn Suggested-by: Andy Lutomirski Signed-off-by: Chang S. Bae Signed-off-by: Borislav Petkov Reviewed-by: Len Brown Acked-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20210518200320.17239-6-chang.seok.bae@intel.com Link: https://bugzilla.kernel.org/show_bug.cgi?id=153531 --- arch/x86/kernel/signal.c | 24 ++++++++++++++++++++---- include/linux/sched/signal.h | 19 ++++++++++++------- 2 files changed, 32 insertions(+), 11 deletions(-) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 86e53868159ad6..2ddcf2165bcb87 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -239,10 +239,11 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, void __user **fpstate) { /* Default to using normal stack */ + bool nested_altstack = on_sig_stack(regs->sp); + bool entering_altstack = false; unsigned long math_size = 0; unsigned long sp = regs->sp; unsigned long buf_fx = 0; - int onsigstack = on_sig_stack(sp); int ret; /* redzone */ @@ -251,15 +252,23 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa.sa_flags & SA_ONSTACK) { - if (sas_ss_flags(sp) == 0) + /* + * This checks nested_altstack via sas_ss_flags(). Sensible + * programs use SS_AUTODISARM, which disables that check, and + * programs that don't use SS_AUTODISARM get compatible. + */ + if (sas_ss_flags(sp) == 0) { sp = current->sas_ss_sp + current->sas_ss_size; + entering_altstack = true; + } } else if (IS_ENABLED(CONFIG_X86_32) && - !onsigstack && + !nested_altstack && regs->ss != __USER_DS && !(ka->sa.sa_flags & SA_RESTORER) && ka->sa.sa_restorer) { /* This is the legacy signal stack switching. */ sp = (unsigned long) ka->sa.sa_restorer; + entering_altstack = true; } sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32), @@ -272,8 +281,15 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, * If we are on the alternate signal stack and would overflow it, don't. * Return an always-bogus address instead so we will die with SIGSEGV. */ - if (onsigstack && !likely(on_sig_stack(sp))) + if (unlikely((nested_altstack || entering_altstack) && + !__on_sig_stack(sp))) { + + if (show_unhandled_signals && printk_ratelimit()) + pr_info("%s[%d] overflowed sigaltstack\n", + current->comm, task_pid_nr(current)); + return (void __user *)-1L; + } /* save i387 and extended state */ ret = copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size); diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3f6a0fcaa10cf4..ae60f838ebb92a 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -537,6 +537,17 @@ static inline int kill_cad_pid(int sig, int priv) #define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0) #define SEND_SIG_PRIV ((struct kernel_siginfo *) 1) +static inline int __on_sig_stack(unsigned long sp) +{ +#ifdef CONFIG_STACK_GROWSUP + return sp >= current->sas_ss_sp && + sp - current->sas_ss_sp < current->sas_ss_size; +#else + return sp > current->sas_ss_sp && + sp - current->sas_ss_sp <= current->sas_ss_size; +#endif +} + /* * True if we are on the alternate signal stack. */ @@ -554,13 +565,7 @@ static inline int on_sig_stack(unsigned long sp) if (current->sas_ss_flags & SS_AUTODISARM) return 0; -#ifdef CONFIG_STACK_GROWSUP - return sp >= current->sas_ss_sp && - sp - current->sas_ss_sp < current->sas_ss_size; -#else - return sp > current->sas_ss_sp && - sp - current->sas_ss_sp <= current->sas_ss_size; -#endif + return __on_sig_stack(sp); } static inline int sas_ss_flags(unsigned long sp) From 8919f07276991c7bf0d0802f0356331c5c62f7a2 Mon Sep 17 00:00:00 2001 From: "Chang S. Bae" Date: Tue, 18 May 2021 13:03:20 -0700 Subject: [PATCH 06/74] selftest/x86/signal: Include test cases for validating sigaltstack The test measures the kernel's signal delivery with different (enough vs. insufficient) stack sizes. Signed-off-by: Chang S. Bae Signed-off-by: Borislav Petkov Reviewed-by: Len Brown Acked-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20210518200320.17239-7-chang.seok.bae@intel.com --- tools/testing/selftests/x86/Makefile | 2 +- tools/testing/selftests/x86/sigaltstack.c | 128 ++++++++++++++++++++++ 2 files changed, 129 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/x86/sigaltstack.c diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 333980375bc782..65bba2ae86eee5 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -13,7 +13,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie) TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ check_initial_reg_state sigreturn iopl ioperm \ test_vsyscall mov_ss_trap \ - syscall_arg_fault fsgsbase_restore + syscall_arg_fault fsgsbase_restore sigaltstack TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer diff --git a/tools/testing/selftests/x86/sigaltstack.c b/tools/testing/selftests/x86/sigaltstack.c new file mode 100644 index 00000000000000..f689af75e979ea --- /dev/null +++ b/tools/testing/selftests/x86/sigaltstack.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* sigaltstack()-enforced minimum stack */ +#define ENFORCED_MINSIGSTKSZ 2048 + +#ifndef AT_MINSIGSTKSZ +# define AT_MINSIGSTKSZ 51 +#endif + +static int nerrs; + +static bool sigalrm_expected; + +static unsigned long at_minstack_size; + +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)) + err(1, "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)) + err(1, "sigaction"); +} + +static int setup_altstack(void *start, unsigned long size) +{ + stack_t ss; + + memset(&ss, 0, sizeof(ss)); + ss.ss_size = size; + ss.ss_sp = start; + + return sigaltstack(&ss, NULL); +} + +static jmp_buf jmpbuf; + +static void sigsegv(int sig, siginfo_t *info, void *ctx_void) +{ + if (sigalrm_expected) { + printf("[FAIL]\tWrong signal delivered: SIGSEGV (expected SIGALRM)."); + nerrs++; + } else { + printf("[OK]\tSIGSEGV signal delivered.\n"); + } + + siglongjmp(jmpbuf, 1); +} + +static void sigalrm(int sig, siginfo_t *info, void *ctx_void) +{ + if (!sigalrm_expected) { + printf("[FAIL]\tWrong signal delivered: SIGALRM (expected SIGSEGV)."); + nerrs++; + } else { + printf("[OK]\tSIGALRM signal delivered.\n"); + } +} + +static void test_sigaltstack(void *altstack, unsigned long size) +{ + if (setup_altstack(altstack, size)) + err(1, "sigaltstack()"); + + sigalrm_expected = (size > at_minstack_size) ? true : false; + + sethandler(SIGSEGV, sigsegv, 0); + sethandler(SIGALRM, sigalrm, SA_ONSTACK); + + if (!sigsetjmp(jmpbuf, 1)) { + printf("[RUN]\tTest an alternate signal stack of %ssufficient size.\n", + sigalrm_expected ? "" : "in"); + printf("\tRaise SIGALRM. %s is expected to be delivered.\n", + sigalrm_expected ? "It" : "SIGSEGV"); + raise(SIGALRM); + } + + clearhandler(SIGALRM); + clearhandler(SIGSEGV); +} + +int main(void) +{ + void *altstack; + + at_minstack_size = getauxval(AT_MINSIGSTKSZ); + + altstack = mmap(NULL, at_minstack_size + SIGSTKSZ, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + if (altstack == MAP_FAILED) + err(1, "mmap()"); + + if ((ENFORCED_MINSIGSTKSZ + 1) < at_minstack_size) + test_sigaltstack(altstack, ENFORCED_MINSIGSTKSZ + 1); + + test_sigaltstack(altstack, at_minstack_size + SIGSTKSZ); + + return nerrs == 0 ? 0 : 1; +} From f72a249b0ba85564c6bfa94d609a70567485a061 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 8 Jun 2021 16:36:22 +0200 Subject: [PATCH 07/74] x86/fpu: Add address range checks to copy_user_to_xstate() copy_user_to_xstate() uses __copy_from_user(), which provides a negligible speedup. Fortunately, both call sites are at least almost correct. __fpu__restore_sig() checks access_ok() with xstate_sigframe_size() length and ptrace regset access uses fpu_user_xstate_size. These should be valid upper bounds on the length, so, at worst, this would cause spurious failures and not accesses to kernel memory. Nonetheless, this is far more fragile than necessary and none of these callers are in a hotpath. Use copy_from_user() instead. Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Acked-by: Dave Hansen Acked-by: Rik van Riel Link: https://lkml.kernel.org/r/20210608144346.140254130@linutronix.de --- arch/x86/kernel/fpu/xstate.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index a85c6400021896..8ac0f67b861aef 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1190,7 +1190,7 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) offset = offsetof(struct xregs_state, header); size = sizeof(hdr); - if (__copy_from_user(&hdr, ubuf + offset, size)) + if (copy_from_user(&hdr, ubuf + offset, size)) return -EFAULT; if (validate_user_xstate_header(&hdr)) @@ -1205,7 +1205,7 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) offset = xstate_offsets[i]; size = xstate_sizes[i]; - if (__copy_from_user(dst, ubuf + offset, size)) + if (copy_from_user(dst, ubuf + offset, size)) return -EFAULT; } } @@ -1213,7 +1213,7 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { offset = offsetof(struct fxregs_state, mxcsr); size = MXCSR_AND_FLAGS_SIZE; - if (__copy_from_user(&xsave->i387.mxcsr, ubuf + offset, size)) + if (copy_from_user(&xsave->i387.mxcsr, ubuf + offset, size)) return -EFAULT; } From b7c11876d24bdd7ae3feeaa771b8f903f6cf05eb Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 8 Jun 2021 16:36:23 +0200 Subject: [PATCH 08/74] selftests/x86: Test signal frame XSTATE header corruption handling This is very heavily based on some code from Thomas Gleixner. On a system without XSAVES, it triggers the WARN_ON(): Bad FPU state detected at copy_kernel_to_fpregs+0x2f/0x40, reinitializing FPU registers. [ bp: Massage in nitpicks. ] Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Acked-by: Dave Hansen Acked-by: Rik van Riel Link: https://lkml.kernel.org/r/20210608144346.234764986@linutronix.de --- tools/testing/selftests/x86/Makefile | 3 +- .../selftests/x86/corrupt_xstate_header.c | 114 ++++++++++++++++++ 2 files changed, 116 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/x86/corrupt_xstate_header.c diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 65bba2ae86eee5..b4142cd1c5c23b 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -17,7 +17,8 @@ TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap 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 +TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering \ + corrupt_xstate_header # 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/corrupt_xstate_header.c b/tools/testing/selftests/x86/corrupt_xstate_header.c new file mode 100644 index 00000000000000..ab8599c10ce5d8 --- /dev/null +++ b/tools/testing/selftests/x86/corrupt_xstate_header.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Corrupt the XSTATE header in a signal frame + * + * Based on analysis and a test case from Thomas Gleixner. + */ + +#define _GNU_SOURCE + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static inline void __cpuid(unsigned int *eax, unsigned int *ebx, + unsigned int *ecx, unsigned int *edx) +{ + asm volatile( + "cpuid;" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +static inline int xsave_enabled(void) +{ + unsigned int eax, ebx, ecx, edx; + + eax = 0x1; + ecx = 0x0; + __cpuid(&eax, &ebx, &ecx, &edx); + + /* Is CR4.OSXSAVE enabled ? */ + return ecx & (1U << 27); +} + +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)) + err(1, "sigaction"); +} + +static void sigusr1(int sig, siginfo_t *info, void *uc_void) +{ + ucontext_t *uc = uc_void; + uint8_t *fpstate = (uint8_t *)uc->uc_mcontext.fpregs; + uint64_t *xfeatures = (uint64_t *)(fpstate + 512); + + printf("\tWreck XSTATE header\n"); + /* Wreck the first reserved bytes in the header */ + *(xfeatures + 2) = 0xfffffff; +} + +static void sigsegv(int sig, siginfo_t *info, void *uc_void) +{ + printf("\tGot SIGSEGV\n"); +} + +int main(void) +{ + cpu_set_t set; + + sethandler(SIGUSR1, sigusr1, 0); + sethandler(SIGSEGV, sigsegv, 0); + + if (!xsave_enabled()) { + printf("[SKIP] CR4.OSXSAVE disabled.\n"); + return 0; + } + + CPU_ZERO(&set); + CPU_SET(0, &set); + + /* + * Enforce that the child runs on the same CPU + * which in turn forces a schedule. + */ + sched_setaffinity(getpid(), sizeof(set), &set); + + printf("[RUN]\tSend ourselves a signal\n"); + raise(SIGUSR1); + + printf("[OK]\tBack from the signal. Now schedule.\n"); + pid_t child = fork(); + if (child < 0) + err(1, "fork"); + if (child == 0) + return 0; + if (child) + waitpid(child, NULL, 0); + printf("[OK]\tBack in the main thread.\n"); + + /* + * We could try to confirm that extended state is still preserved + * when we schedule. For now, the only indication of failure is + * a warning in the kernel logs. + */ + + return 0; +} From 9625895011d130033d1bc7aac0d77a9bf68ff8a6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:28 +0200 Subject: [PATCH 09/74] x86/fpu: Fix copy_xstate_to_kernel() gap handling The gap handling in copy_xstate_to_kernel() is wrong when XSAVES is in use. Using init_fpstate for copying the init state of features which are not set in the xstate header is only correct for the legacy area, but not for the extended features area because when XSAVES is in use then init_fpstate is in compacted form which means the xstate offsets which are used to copy from init_fpstate are not valid. Fortunately, this is not a real problem today because all extended features in use have an all-zeros init state, but it is wrong nevertheless and with a potentially dynamically sized init_fpstate this would result in an access outside of the init_fpstate. Fix this by keeping track of the last copied state in the target buffer and explicitly zero it when there is a feature or alignment gap. Use the compacted offset when accessing the extended feature space in init_fpstate. As this is not a functional issue on older kernels this is intentionally not tagged for stable. Fixes: b8be15d58806 ("x86/fpu/xstate: Re-enable XSAVES") Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121451.294282032@linutronix.de --- arch/x86/kernel/fpu/xstate.c | 105 ++++++++++++++++++++--------------- 1 file changed, 61 insertions(+), 44 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index f0f64d42204d30..d822ce76f0a187 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1084,20 +1084,10 @@ static inline bool xfeatures_mxcsr_quirk(u64 xfeatures) return true; } -static void fill_gap(struct membuf *to, unsigned *last, unsigned offset) +static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, + void *init_xstate, unsigned int size) { - if (*last >= offset) - return; - membuf_write(to, (void *)&init_fpstate.xsave + *last, offset - *last); - *last = offset; -} - -static void copy_part(struct membuf *to, unsigned *last, unsigned offset, - unsigned size, void *from) -{ - fill_gap(to, last, offset); - membuf_write(to, from, size); - *last = offset + size; + membuf_write(to, from_xstate ? xstate : init_xstate, size); } /* @@ -1109,10 +1099,10 @@ static void copy_part(struct membuf *to, unsigned *last, unsigned offset, */ void copy_xstate_to_kernel(struct membuf to, struct xregs_state *xsave) { + const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr); + struct xregs_state *xinit = &init_fpstate.xsave; struct xstate_header header; - const unsigned off_mxcsr = offsetof(struct fxregs_state, mxcsr); - unsigned size = to.left; - unsigned last = 0; + unsigned int zerofrom; int i; /* @@ -1122,41 +1112,68 @@ void copy_xstate_to_kernel(struct membuf to, struct xregs_state *xsave) header.xfeatures = xsave->header.xfeatures; header.xfeatures &= xfeatures_mask_user(); - if (header.xfeatures & XFEATURE_MASK_FP) - copy_part(&to, &last, 0, off_mxcsr, &xsave->i387); - if (header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM)) - copy_part(&to, &last, off_mxcsr, - MXCSR_AND_FLAGS_SIZE, &xsave->i387.mxcsr); - if (header.xfeatures & XFEATURE_MASK_FP) - copy_part(&to, &last, offsetof(struct fxregs_state, st_space), - 128, &xsave->i387.st_space); - if (header.xfeatures & XFEATURE_MASK_SSE) - copy_part(&to, &last, xstate_offsets[XFEATURE_SSE], - 256, &xsave->i387.xmm_space); - /* - * Fill xsave->i387.sw_reserved value for ptrace frame: - */ - copy_part(&to, &last, offsetof(struct fxregs_state, sw_reserved), - 48, xstate_fx_sw_bytes); - /* - * Copy xregs_state->header: - */ - copy_part(&to, &last, offsetof(struct xregs_state, header), - sizeof(header), &header); + /* Copy FP state up to MXCSR */ + copy_feature(header.xfeatures & XFEATURE_MASK_FP, &to, &xsave->i387, + &xinit->i387, off_mxcsr); + + /* Copy MXCSR when SSE or YMM are set in the feature mask */ + copy_feature(header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM), + &to, &xsave->i387.mxcsr, &xinit->i387.mxcsr, + MXCSR_AND_FLAGS_SIZE); + + /* Copy the remaining FP state */ + copy_feature(header.xfeatures & XFEATURE_MASK_FP, + &to, &xsave->i387.st_space, &xinit->i387.st_space, + sizeof(xsave->i387.st_space)); + + /* Copy the SSE state - shared with YMM, but independently managed */ + copy_feature(header.xfeatures & XFEATURE_MASK_SSE, + &to, &xsave->i387.xmm_space, &xinit->i387.xmm_space, + sizeof(xsave->i387.xmm_space)); + + /* Zero the padding area */ + membuf_zero(&to, sizeof(xsave->i387.padding)); + + /* Copy xsave->i387.sw_reserved */ + membuf_write(&to, xstate_fx_sw_bytes, sizeof(xsave->i387.sw_reserved)); + + /* Copy the user space relevant state of @xsave->header */ + membuf_write(&to, &header, sizeof(header)); + + zerofrom = offsetof(struct xregs_state, extended_state_area); for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { /* - * Copy only in-use xstates: + * 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 ((header.xfeatures >> i) & 1) { - void *src = __raw_xsave_addr(xsave, i); + if (!(xfeatures_mask_user() & BIT_ULL(i))) + continue; - copy_part(&to, &last, xstate_offsets[i], - xstate_sizes[i], src); - } + /* + * If there was a feature or alignment gap, zero the space + * in the destination buffer. + */ + if (zerofrom < xstate_offsets[i]) + membuf_zero(&to, xstate_offsets[i] - zerofrom); + + copy_feature(header.xfeatures & BIT_ULL(i), &to, + __raw_xsave_addr(xsave, i), + __raw_xsave_addr(xinit, i), + xstate_sizes[i]); + /* + * Keep track of the last copied state in the non-compacted + * target buffer for gap zeroing. + */ + zerofrom = xstate_offsets[i] + xstate_sizes[i]; } - fill_gap(&to, &last, size); + + if (to.left) + membuf_zero(&to, to.left); } /* From b3607269ff57fd3c9690cb25962c5e4b91a0fd3b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:29 +0200 Subject: [PATCH 10/74] x86/pkeys: Revert a5eff7259790 ("x86/pkeys: Add PKRU value to init_fpstate") This cannot work and it's unclear how that ever made a difference. init_fpstate.xsave.header.xfeatures is always 0 so get_xsave_addr() will always return a NULL pointer, which will prevent storing the default PKRU value in init_fpstate. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121451.451391598@linutronix.de --- arch/x86/kernel/cpu/common.c | 5 ----- arch/x86/mm/pkeys.c | 6 ------ 2 files changed, 11 deletions(-) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9173dd47581875..dcbb11fda5d258 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -466,8 +466,6 @@ static bool pku_disabled; static __always_inline void setup_pku(struct cpuinfo_x86 *c) { - struct pkru_state *pk; - /* check the boot processor, plus compile options for PKU: */ if (!cpu_feature_enabled(X86_FEATURE_PKU)) return; @@ -478,9 +476,6 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c) return; cr4_set_bits(X86_CR4_PKE); - pk = get_xsave_addr(&init_fpstate.xsave, XFEATURE_PKRU); - if (pk) - pk->pkru = init_pkru_value; /* * Setting X86_CR4_PKE will cause the X86_FEATURE_OSPKE * cpuid bit to be set. We need to ensure that we diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index a2332eef66e9f8..a840ac78b6de46 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -10,7 +10,6 @@ #include /* boot_cpu_has, ... */ #include /* vma_pkey() */ -#include /* init_fpstate */ int __execute_only_pkey(struct mm_struct *mm) { @@ -154,7 +153,6 @@ static ssize_t init_pkru_read_file(struct file *file, char __user *user_buf, static ssize_t init_pkru_write_file(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { - struct pkru_state *pk; char buf[32]; ssize_t len; u32 new_init_pkru; @@ -177,10 +175,6 @@ static ssize_t init_pkru_write_file(struct file *file, return -EINVAL; WRITE_ONCE(init_pkru_value, new_init_pkru); - pk = get_xsave_addr(&init_fpstate.xsave, XFEATURE_PKRU); - if (!pk) - return -EINVAL; - pk->pkru = new_init_pkru; return count; } From ce578f16348b003675c928a1992498b33b515f18 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:30 +0200 Subject: [PATCH 11/74] x86/fpu: Mark various FPU state variables __ro_after_init Nothing modifies these after booting. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Reviewed-by: Andy Lutomirski Link: https://lkml.kernel.org/r/20210623121451.611751529@linutronix.de --- arch/x86/kernel/fpu/init.c | 4 ++-- arch/x86/kernel/fpu/xstate.c | 14 +++++++++----- 2 files changed, 11 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 701f196d7c6866..95aa1090ea7296 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -89,7 +89,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) /* * Boot time FPU feature detection code: */ -unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; +unsigned int mxcsr_feature_mask __ro_after_init = 0xffffffffu; EXPORT_SYMBOL_GPL(mxcsr_feature_mask); static void __init fpu__init_system_mxcsr(void) @@ -135,7 +135,7 @@ static void __init fpu__init_system_generic(void) * This is inherent to the XSAVE architecture which puts all state * components into a single, continuous memory block: */ -unsigned int fpu_kernel_xstate_size; +unsigned int fpu_kernel_xstate_size __ro_after_init; EXPORT_SYMBOL_GPL(fpu_kernel_xstate_size); /* Get alignment of the TYPE. */ diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index d822ce76f0a187..bcb9f5648cfd2b 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -61,17 +61,21 @@ static short xsave_cpuid_features[] __initdata = { */ u64 xfeatures_mask_all __read_mostly; -static unsigned int xstate_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1}; -static unsigned int xstate_sizes[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1}; -static unsigned int xstate_comp_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1}; -static unsigned int xstate_supervisor_only_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1}; +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 = + { [ 0 ... XFEATURE_MAX - 1] = -1}; +static unsigned int xstate_comp_offsets[XFEATURE_MAX] __ro_after_init = + { [ 0 ... XFEATURE_MAX - 1] = -1}; +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; +unsigned int fpu_user_xstate_size __ro_after_init; /* * Return whether the system supports a given xfeature. From 4e8e4313cf81add679e1c57677d689c02e382a67 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:31 +0200 Subject: [PATCH 12/74] x86/fpu: Make xfeatures_mask_all __ro_after_init Nothing has to modify this after init. But of course there is code which unconditionally masks xfeatures_mask_all on CPU hotplug. This goes unnoticed during boot hotplug because at that point the variable is still RW mapped. This is broken in several ways: 1) Masking this in post init CPU hotplug means that any modification of this state goes unnoticed until actual hotplug happens. 2) If that ever happens then these bogus feature bits are already populated all over the place and the system is in inconsistent state vs. the compacted XSTATE offsets. If at all then this has to panic the machine because the inconsistency cannot be undone anymore. Make this a one-time paranoia check in xstate init code and disable xsave when this happens. Reported-by: Kan Liang Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121451.712803952@linutronix.de --- arch/x86/kernel/fpu/xstate.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index bcb9f5648cfd2b..a64f61ae8540fb 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -59,7 +59,7 @@ static short xsave_cpuid_features[] __initdata = { * 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 __read_mostly; +u64 xfeatures_mask_all __ro_after_init; static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init = { [ 0 ... XFEATURE_MAX - 1] = -1}; @@ -213,19 +213,8 @@ void fpstate_sanitize_xstate(struct fpu *fpu) */ void fpu__init_cpu_xstate(void) { - u64 unsup_bits; - if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask_all) return; - /* - * Unsupported supervisor xstates should not be found in - * the xfeatures mask. - */ - unsup_bits = xfeatures_mask_all & XFEATURE_MASK_SUPERVISOR_UNSUPPORTED; - WARN_ONCE(unsup_bits, "x86/fpu: Found unsupported supervisor xstates: 0x%llx\n", - unsup_bits); - - xfeatures_mask_all &= ~XFEATURE_MASK_SUPERVISOR_UNSUPPORTED; cr4_set_bits(X86_CR4_OSXSAVE); @@ -825,6 +814,7 @@ void __init fpu__init_system_xstate(void) { unsigned int eax, ebx, ecx, edx; static int on_boot_cpu __initdata = 1; + u64 xfeatures; int err; int i; @@ -879,6 +869,8 @@ void __init fpu__init_system_xstate(void) } xfeatures_mask_all &= fpu__get_supported_xfeatures_mask(); + /* Store it for paranoia check at the end */ + xfeatures = xfeatures_mask_all; /* Enable xstate instructions to be able to continue with initialization: */ fpu__init_cpu_xstate(); @@ -896,8 +888,18 @@ void __init fpu__init_system_xstate(void) setup_init_fpu_buf(); setup_xstate_comp_offsets(); setup_supervisor_only_offsets(); - print_xstate_offset_size(); + /* + * Paranoia check whether something in the setup modified the + * xfeatures mask. + */ + if (xfeatures != xfeatures_mask_all) { + pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init, disabling XSAVE\n", + xfeatures, xfeatures_mask_all); + 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, From ce38f038ede735fd425ebda10d1758420a669a87 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:32 +0200 Subject: [PATCH 13/74] x86/fpu: Get rid of fpu__get_supported_xfeatures_mask() This function is really not doing what the comment advertises: "Find supported xfeatures based on cpu features and command-line input. This must be called after fpu__init_parse_early_param() is called and xfeatures_mask is enumerated." fpu__init_parse_early_param() does not exist anymore and the function just returns a constant. Remove it and fix the caller and get rid of further references to fpu__init_parse_early_param(). Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121451.816404717@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 1 - arch/x86/kernel/cpu/common.c | 5 ++--- arch/x86/kernel/fpu/init.c | 11 ----------- arch/x86/kernel/fpu/xstate.c | 4 +++- 4 files changed, 5 insertions(+), 16 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 16bf4d4a8159e2..58f20821662f89 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -45,7 +45,6 @@ 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); -extern u64 fpu__get_supported_xfeatures_mask(void); /* * Debugging facility: diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index dcbb11fda5d258..f875dea49d7e55 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1715,9 +1715,8 @@ void print_cpu_info(struct cpuinfo_x86 *c) } /* - * clearcpuid= was already parsed in fpu__init_parse_early_param. - * But we need to keep a dummy __setup around otherwise it would - * show up as an environment variable for init. + * clearcpuid= was already parsed in cpu_parse_early_param(). This dummy + * function prevents it from becoming an environment variable for init. */ static __init int setup_clearcpuid(char *arg) { diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 95aa1090ea7296..64e29927cc32fa 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -216,17 +216,6 @@ static void __init fpu__init_system_xstate_size_legacy(void) fpu_user_xstate_size = fpu_kernel_xstate_size; } -/* - * Find supported xfeatures based on cpu features and command-line input. - * This must be called after fpu__init_parse_early_param() is called and - * xfeatures_mask is enumerated. - */ -u64 __init fpu__get_supported_xfeatures_mask(void) -{ - return XFEATURE_MASK_USER_SUPPORTED | - XFEATURE_MASK_SUPERVISOR_SUPPORTED; -} - /* Legacy code to initialize eager fpu mode. */ static void __init fpu__init_system_ctx_switch(void) { diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index a64f61ae8540fb..5e825ff0bfdc83 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -868,7 +868,9 @@ void __init fpu__init_system_xstate(void) xfeatures_mask_all &= ~BIT_ULL(i); } - xfeatures_mask_all &= fpu__get_supported_xfeatures_mask(); + xfeatures_mask_all &= XFEATURE_MASK_USER_SUPPORTED | + XFEATURE_MASK_SUPERVISOR_SUPPORTED; + /* Store it for paranoia check at the end */ xfeatures = xfeatures_mask_all; From 4098b3eef37be19572d270f9b761c3e8ffcf37ac Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:33 +0200 Subject: [PATCH 14/74] x86/fpu: Remove unused get_xsave_field_ptr() Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Andy Lutomirski Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121451.915614415@linutronix.de --- arch/x86/include/asm/fpu/xstate.h | 1 - arch/x86/kernel/fpu/xstate.c | 30 ------------------------------ 2 files changed, 31 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 47a92232d59531..d22e973845c6b0 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -101,7 +101,6 @@ extern void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask); void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); -const void *get_xsave_field_ptr(int xfeature_nr); int using_compacted_format(void); int xfeature_size(int xfeature_nr); struct membuf; diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 5e825ff0bfdc83..b82879cd9151b8 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -998,36 +998,6 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) } EXPORT_SYMBOL_GPL(get_xsave_addr); -/* - * This wraps up the common operations that need to occur when retrieving - * data from xsave state. It first ensures that the current task was - * using the FPU and retrieves the data in to a buffer. It then calculates - * the offset of the requested field in the buffer. - * - * This function is safe to call whether the FPU is in use or not. - * - * Note that this only works on the current task. - * - * Inputs: - * @xfeature_nr: state which is defined in xsave.h (e.g. XFEATURE_FP, - * XFEATURE_SSE, etc...) - * Output: - * address of the state in the xsave area or NULL if the state - * is not present or is in its 'init state'. - */ -const void *get_xsave_field_ptr(int xfeature_nr) -{ - struct fpu *fpu = ¤t->thread.fpu; - - /* - * fpu__save() takes the CPU's xstate registers - * and saves them off to the 'fpu memory buffer. - */ - fpu__save(fpu); - - return get_xsave_addr(&fpu->state.xsave, xfeature_nr); -} - #ifdef CONFIG_ARCH_HAS_PKEYS /* From e68524456c855e500f0a636adb1aa977e1e0b4d8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:34 +0200 Subject: [PATCH 15/74] x86/fpu: Move inlines where they belong They are only used in fpstate_init() and there is no point to have them in a header just to make reading the code harder. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121452.023118522@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 14 -------------- arch/x86/kernel/fpu/core.c | 15 +++++++++++++++ 2 files changed, 15 insertions(+), 14 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 58f20821662f89..9ed98460959516 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -86,20 +86,6 @@ extern void fpstate_init_soft(struct swregs_state *soft); static inline void fpstate_init_soft(struct swregs_state *soft) {} #endif -static inline void fpstate_init_xstate(struct xregs_state *xsave) -{ - /* - * XRSTORS requires these bits set in xcomp_bv, or it will - * trigger #GP: - */ - xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all; -} - -static inline void fpstate_init_fxstate(struct fxregs_state *fx) -{ - fx->cwd = 0x37f; - fx->mxcsr = MXCSR_DEFAULT; -} extern void fpstate_sanitize_xstate(struct fpu *fpu); #define user_insn(insn, output, input...) \ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 571220ac8beaa7..9ff467bb4894c4 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -181,6 +181,21 @@ void fpu__save(struct fpu *fpu) fpregs_unlock(); } +static inline void fpstate_init_xstate(struct xregs_state *xsave) +{ + /* + * XRSTORS requires these bits set in xcomp_bv, or it will + * trigger #GP: + */ + xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all; +} + +static inline void fpstate_init_fxstate(struct fxregs_state *fx) +{ + fx->cwd = 0x37f; + fx->mxcsr = MXCSR_DEFAULT; +} + /* * Legacy x87 fpstate state init: */ From 07d6688b22e09be465652cf2da0da6bf86154df6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:35 +0200 Subject: [PATCH 16/74] x86/fpu: Limit xstate copy size in xstateregs_set() If the count argument is larger than the xstate size, this will happily copy beyond the end of xstate. Fixes: 91c3dba7dbc1 ("x86/fpu/xstate: Fix PTRACE frames for XSAVES") Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Andy Lutomirski Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121452.120741557@linutronix.de --- arch/x86/kernel/fpu/regset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index c413756ba89fa0..6bb874441de8b2 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -117,7 +117,7 @@ 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_xstate_size) return -EFAULT; xsave = &fpu->state.xsave; From 43be46e89698a41dbf4fff81a322f4c2ae21b5e2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:36 +0200 Subject: [PATCH 17/74] x86/fpu: Sanitize xstateregs_set() xstateregs_set() operates on a stopped task and tries to copy the provided buffer into the task's fpu.state.xsave buffer. Any error while copying or invalid state detected after copying results in wiping the target task's FPU state completely including supervisor states. That's just wrong. The caller supplied invalid data or has a problem with unmapped memory, so there is absolutely no justification to corrupt the target state. Fix this with the following modifications: 1) If data has to be copied from userspace, allocate a buffer and copy from user first. 2) Use copy_kernel_to_xstate() unconditionally so that header checking works correctly. 3) Return on error without corrupting the target state. This prevents corrupting states and lets the caller deal with the problem it caused in the first place. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121452.214903673@linutronix.de --- arch/x86/include/asm/fpu/xstate.h | 4 --- arch/x86/kernel/fpu/regset.c | 42 +++++++++++++------------------ arch/x86/kernel/fpu/xstate.c | 14 ++++++----- 3 files changed, 25 insertions(+), 35 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index d22e973845c6b0..1bb2d16f485b29 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -111,8 +111,4 @@ void copy_supervisor_to_kernel(struct xregs_state *xsave); void copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask); void copy_kernel_to_dynamic_supervisor(struct xregs_state *xstate, u64 mask); - -/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ -int validate_user_xstate_header(const struct xstate_header *hdr); - #endif diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 6bb874441de8b2..a50c0a93549985 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -2,11 +2,13 @@ /* * FPU register's regset abstraction, for ptrace, core dumps, etc. */ +#include +#include + #include #include #include #include -#include /* * The xstateregs_active() routine is the same as the regset_fpregs_active() routine, @@ -108,10 +110,10 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, const void *kbuf, const void __user *ubuf) { struct fpu *fpu = &target->thread.fpu; - struct xregs_state *xsave; + struct xregs_state *tmpbuf = NULL; int ret; - if (!boot_cpu_has(X86_FEATURE_XSAVE)) + if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) return -ENODEV; /* @@ -120,32 +122,22 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, if (pos != 0 || count != fpu_user_xstate_size) return -EFAULT; - xsave = &fpu->state.xsave; - - fpu__prepare_write(fpu); + if (!kbuf) { + tmpbuf = vmalloc(count); + if (!tmpbuf) + return -ENOMEM; - if (using_compacted_format()) { - if (kbuf) - ret = copy_kernel_to_xstate(xsave, kbuf); - else - ret = copy_user_to_xstate(xsave, ubuf); - } else { - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - if (!ret) - ret = validate_user_xstate_header(&xsave->header); + if (copy_from_user(tmpbuf, ubuf, count)) { + ret = -EFAULT; + goto out; + } } - /* - * mxcsr reserved bits must be masked to zero for security reasons. - */ - xsave->i387.mxcsr &= mxcsr_feature_mask; - - /* - * In case of failure, mark all states as init: - */ - if (ret) - fpstate_init(&fpu->state); + fpu__prepare_write(fpu); + ret = copy_kernel_to_xstate(&fpu->state.xsave, kbuf ?: tmpbuf); +out: + vfree(tmpbuf); return ret; } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index b82879cd9151b8..2b7b579f06b66e 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -543,7 +543,7 @@ int using_compacted_format(void) } /* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ -int validate_user_xstate_header(const struct xstate_header *hdr) +static int validate_user_xstate_header(const struct xstate_header *hdr) { /* No unknown or supervisor features may be set */ if (hdr->xfeatures & ~xfeatures_mask_user()) @@ -1155,7 +1155,7 @@ void copy_xstate_to_kernel(struct membuf to, struct xregs_state *xsave) } /* - * Convert from a ptrace standard-format kernel buffer to kernel XSAVES format + * 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(). */ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) @@ -1202,14 +1202,16 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) */ xsave->header.xfeatures |= hdr.xfeatures; + /* mxcsr reserved bits must be masked to zero for historical reasons. */ + xsave->i387.mxcsr &= mxcsr_feature_mask; + return 0; } /* - * Convert from a ptrace or sigreturn standard-format user-space buffer to - * kernel XSAVES format and copy to the target thread. This is called from - * xstateregs_set(), as well as potentially from the sigreturn() and - * rt_sigreturn() system calls. + * Convert from a sigreturn standard-format user-space buffer to kernel + * XSAVE[S] format and copy to the target thread. This is called from the + * sigreturn() and rt_sigreturn() system calls. */ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) { From 947f4947cf00ea1e6d319eb182c64ea51ba4de8d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:37 +0200 Subject: [PATCH 18/74] x86/fpu: Reject invalid MXCSR values in copy_kernel_to_xstate() Instead of masking out reserved bits, check them and reject the provided state as invalid if not zero. Suggested-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121452.308388343@linutronix.de --- arch/x86/kernel/fpu/xstate.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 2b7b579f06b66e..9cf84c5d1d37e0 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1154,6 +1154,19 @@ void copy_xstate_to_kernel(struct membuf to, struct xregs_state *xsave) membuf_zero(&to, to.left); } +static inline bool mxcsr_valid(struct xstate_header *hdr, const u32 *mxcsr) +{ + u64 mask = XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM; + + /* Only check if it is in use */ + if (hdr->xfeatures & mask) { + /* Reserved bits in MXCSR must be zero. */ + if (*mxcsr & ~mxcsr_feature_mask) + return false; + } + return true; +} + /* * 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(). @@ -1172,6 +1185,9 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) if (validate_user_xstate_header(&hdr)) return -EINVAL; + if (!mxcsr_valid(&hdr, kbuf + offsetof(struct fxregs_state, mxcsr))) + return -EINVAL; + for (i = 0; i < XFEATURE_MAX; i++) { u64 mask = ((u64)1 << i); @@ -1202,9 +1218,6 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) */ xsave->header.xfeatures |= hdr.xfeatures; - /* mxcsr reserved bits must be masked to zero for historical reasons. */ - xsave->i387.mxcsr &= mxcsr_feature_mask; - return 0; } From 3a3351126ee8f1f1c86c4c79c60a650c1da89733 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Wed, 23 Jun 2021 14:01:38 +0200 Subject: [PATCH 19/74] x86/fpu: Simplify PTRACE_GETREGS code ptrace() has interfaces that let a ptracer inspect a ptracee's register state. This includes XSAVE state. The ptrace() ABI includes a hardware-format XSAVE buffer for both the SETREGS and GETREGS interfaces. In the old days, the kernel buffer and the ptrace() ABI buffer were the same boring non-compacted format. But, since the advent of supervisor states and the compacted format, the kernel buffer has diverged from the format presented in the ABI. This leads to two paths in the kernel: 1. Effectively a verbatim copy_to_user() which just copies the kernel buffer out to userspace. This is used when the kernel buffer is kept in the non-compacted form which means that it shares a format with the ptrace ABI. 2. A one-state-at-a-time path: copy_xstate_to_kernel(). This is theoretically slower since it does a bunch of piecemeal copies. Remove the verbatim copy case. Speed probably does not matter in this path, and the vast majority of new hardware will use the one-state-at-a-time path anyway. This ensures greater testing for the "slow" path. This also makes enabling PKRU in this interface easier since a single path can be patched instead of two. Signed-off-by: Dave Hansen Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Andy Lutomirski Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121452.408457100@linutronix.de --- arch/x86/kernel/fpu/regset.c | 24 +++--------------------- arch/x86/kernel/fpu/xstate.c | 6 +++--- 2 files changed, 6 insertions(+), 24 deletions(-) diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index a50c0a93549985..d60e77d3922210 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -77,32 +77,14 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct fpu *fpu = &target->thread.fpu; - struct xregs_state *xsave; - if (!boot_cpu_has(X86_FEATURE_XSAVE)) + if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) return -ENODEV; - xsave = &fpu->state.xsave; - fpu__prepare_read(fpu); - if (using_compacted_format()) { - copy_xstate_to_kernel(to, xsave); - return 0; - } else { - fpstate_sanitize_xstate(fpu); - /* - * Copy the 48 bytes defined by the software into the xsave - * area in the thread struct, so that we can copy the whole - * area to user using one user_regset_copyout(). - */ - memcpy(&xsave->i387.sw_reserved, xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes)); - - /* - * Copy the xstate memory layout. - */ - return membuf_write(&to, xsave, fpu_user_xstate_size); - } + copy_xstate_to_kernel(to, &fpu->state.xsave); + return 0; } int xstateregs_set(struct task_struct *target, const struct user_regset *regset, diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 9cf84c5d1d37e0..42032471c95731 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1069,11 +1069,11 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, } /* - * Convert from kernel XSAVES compacted format to standard format and copy - * to a kernel-space ptrace buffer. + * Convert from kernel XSAVE or XSAVES compacted format to UABI + * non-compacted format and copy to a kernel-space ptrace buffer. * * It supports partial copy but pos always starts from zero. This is called - * from xstateregs_get() and there we check the CPU has XSAVES. + * from xstateregs_get() and there we check the CPU has XSAVE. */ void copy_xstate_to_kernel(struct membuf to, struct xregs_state *xsave) { From 6164331d15f7d912fb9369245368e9564ea49813 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 23 Jun 2021 14:01:39 +0200 Subject: [PATCH 20/74] x86/fpu: Rewrite xfpregs_set() xfpregs_set() was incomprehensible. Almost all of the complexity was due to trying to support nonsensically sized writes or -EFAULT errors that would have partially or completely overwritten the destination before failing. Nonsensically sized input would only have been possible using PTRACE_SETREGSET on REGSET_XFP. Fortunately, it appears (based on Debian code search results) that no one uses that API at all, let alone with the wrong sized buffer. Failed user access can be handled more cleanly by first copying to kernel memory. Just rewrite it to require sensible input. Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121452.504234607@linutronix.de --- arch/x86/kernel/fpu/regset.c | 37 ++++++++++++++++++++++-------------- 1 file changed, 23 insertions(+), 14 deletions(-) diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index d60e77d3922210..f24ce873bfc200 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -47,30 +47,39 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, const void *kbuf, const void __user *ubuf) { struct fpu *fpu = &target->thread.fpu; + struct user32_fxsr_struct newstate; int ret; - if (!boot_cpu_has(X86_FEATURE_FXSR)) + BUILD_BUG_ON(sizeof(newstate) != sizeof(struct fxregs_state)); + + if (!cpu_feature_enabled(X86_FEATURE_FXSR)) return -ENODEV; + /* No funny business with partial or oversized writes is permitted. */ + if (pos != 0 || count != sizeof(newstate)) + return -EINVAL; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, 0, -1); + if (ret) + return ret; + + /* Mask invalid MXCSR bits (for historical reasons). */ + newstate.mxcsr &= mxcsr_feature_mask; + fpu__prepare_write(fpu); - fpstate_sanitize_xstate(fpu); - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &fpu->state.fxsave, 0, -1); + /* Copy the state */ + memcpy(&fpu->state.fxsave, &newstate, sizeof(newstate)); - /* - * mxcsr reserved bits must be masked to zero for security reasons. - */ - fpu->state.fxsave.mxcsr &= mxcsr_feature_mask; + /* Clear xmm8..15 */ + BUILD_BUG_ON(sizeof(fpu->state.fxsave.xmm_space) != 16 * 16); + memset(&fpu->state.fxsave.xmm_space[8], 0, 8 * 16); - /* - * update the header bits in the xsave header, indicating the - * presence of FP and SSE state. - */ - if (boot_cpu_has(X86_FEATURE_XSAVE)) + /* Mark FP and SSE as in use when XSAVE is enabled */ + if (use_xsave()) fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE; - return ret; + return 0; } int xstateregs_get(struct task_struct *target, const struct user_regset *regset, From 145e9e0d8c6fada4a40f9fc65b34658077874d9c Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 23 Jun 2021 14:01:40 +0200 Subject: [PATCH 21/74] x86/fpu: Fail ptrace() requests that try to set invalid MXCSR values There is no benefit from accepting and silently changing an invalid MXCSR value supplied via ptrace(). Instead, return -EINVAL on invalid input. Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121452.613614842@linutronix.de --- arch/x86/kernel/fpu/regset.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index f24ce873bfc200..5610f77cacadf8 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -63,8 +63,9 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; - /* Mask invalid MXCSR bits (for historical reasons). */ - newstate.mxcsr &= mxcsr_feature_mask; + /* Do not allow an invalid MXCSR value. */ + if (newstate.mxcsr & ~mxcsr_feature_mask) + return -EINVAL; fpu__prepare_write(fpu); From da53f60bb86e60830932926cf1093953a811912c Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 23 Jun 2021 14:01:41 +0200 Subject: [PATCH 22/74] x86/fpu: Clean up fpregs_set() fpregs_set() has unnecessary complexity to support short or nonzero-offset writes and to handle the case in which a copy from userspace overwrites some of the target buffer and then fails. Support for partial writes is useless -- just require that the write has offset 0 and the correct size, and copy into a temporary kernel buffer to avoid clobbering the state if the user access fails. Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121452.710467587@linutronix.de --- arch/x86/kernel/fpu/regset.c | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 5610f77cacadf8..7041b140de604e 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -304,31 +304,32 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - fpu__prepare_write(fpu); - fpstate_sanitize_xstate(fpu); + /* No funny business with partial or oversized writes is permitted. */ + if (pos != 0 || count != sizeof(struct user_i387_ia32_struct)) + return -EINVAL; - if (!boot_cpu_has(X86_FEATURE_FPU)) + if (!cpu_feature_enabled(X86_FEATURE_FPU)) return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - if (!boot_cpu_has(X86_FEATURE_FXSR)) - return user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &fpu->state.fsave, 0, - -1); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1); + if (ret) + return ret; - if (pos > 0 || count < sizeof(env)) - convert_from_fxsr(&env, target); + fpu__prepare_write(fpu); - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1); - if (!ret) - convert_to_fxsr(&target->thread.fpu.state.fxsave, &env); + if (cpu_feature_enabled(X86_FEATURE_FXSR)) + convert_to_fxsr(&fpu->state.fxsave, &env); + else + memcpy(&fpu->state.fsave, &env, sizeof(env)); /* - * update the header bit in the xsave header, indicating the + * Update the header bit in the xsave header, indicating the * presence of FP. */ - if (boot_cpu_has(X86_FEATURE_XSAVE)) + if (cpu_feature_enabled(X86_FEATURE_XSAVE)) fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FP; - return ret; + + return 0; } #endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ From eb6f51723f03c9a1c098ed196a31a03e626b9fb6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:42 +0200 Subject: [PATCH 23/74] x86/fpu: Make copy_xstate_to_kernel() usable for [x]fpregs_get() When xsave with init state optimization is used then a component's state in the task's xsave buffer can be stale when the corresponding feature bit is not set. fpregs_get() and xfpregs_get() invoke fpstate_sanitize_xstate() to update the task's xsave buffer before retrieving the FX or FP state. That's just duplicated code as copy_xstate_to_kernel() already handles this correctly. Add a copy mode argument to the function which allows to restrict the state copy to the FP and SSE features. Also rename the function to copy_xstate_to_uabi_buf() so the name reflects what it is doing. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121452.805327286@linutronix.de --- arch/x86/include/asm/fpu/xstate.h | 12 +++++++-- arch/x86/kernel/fpu/regset.c | 2 +- arch/x86/kernel/fpu/xstate.c | 42 +++++++++++++++++++++++-------- 3 files changed, 42 insertions(+), 14 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 1bb2d16f485b29..732ae793c2ab3c 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -103,12 +103,20 @@ extern void __init update_regset_xstate_info(unsigned int size, void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); int using_compacted_format(void); int xfeature_size(int xfeature_nr); -struct membuf; -void copy_xstate_to_kernel(struct membuf to, struct xregs_state *xsave); int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf); int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf); void copy_supervisor_to_kernel(struct xregs_state *xsave); void copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask); void copy_kernel_to_dynamic_supervisor(struct xregs_state *xstate, u64 mask); +enum xstate_copy_mode { + XSTATE_COPY_FP, + XSTATE_COPY_FX, + XSTATE_COPY_XSAVE, +}; + +struct membuf; +void copy_xstate_to_uabi_buf(struct membuf to, struct xregs_state *xsave, + enum xstate_copy_mode mode); + #endif diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 7041b140de604e..783f84dfcd466c 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -93,7 +93,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, fpu__prepare_read(fpu); - copy_xstate_to_kernel(to, &fpu->state.xsave); + copy_xstate_to_uabi_buf(to, &fpu->state.xsave, XSTATE_COPY_XSAVE); return 0; } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 42032471c95731..8d023a26ae222e 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1068,14 +1068,20 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, membuf_write(to, from_xstate ? xstate : init_xstate, size); } -/* - * Convert from kernel XSAVE or XSAVES compacted format to UABI - * non-compacted format and copy to a kernel-space ptrace buffer. +/** + * copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer + * @to: membuf descriptor + * @xsave: The kernel xstate buffer to copy from + * @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 pos always starts from zero. This is called - * from xstateregs_get() and there we check the CPU has XSAVE. + * It supports partial copy but @to.pos always starts from zero. */ -void copy_xstate_to_kernel(struct membuf to, struct xregs_state *xsave) +void copy_xstate_to_uabi_buf(struct membuf to, struct xregs_state *xsave, + enum xstate_copy_mode copy_mode) { const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr); struct xregs_state *xinit = &init_fpstate.xsave; @@ -1083,12 +1089,22 @@ void copy_xstate_to_kernel(struct membuf to, struct xregs_state *xsave) unsigned int zerofrom; int i; - /* - * The destination is a ptrace buffer; we put in only user xstates: - */ - memset(&header, 0, sizeof(header)); header.xfeatures = xsave->header.xfeatures; - header.xfeatures &= xfeatures_mask_user(); + + /* Mask out the feature bits depending on copy mode */ + switch (copy_mode) { + case XSTATE_COPY_FP: + header.xfeatures &= XFEATURE_MASK_FP; + break; + + case XSTATE_COPY_FX: + header.xfeatures &= XFEATURE_MASK_FP | XFEATURE_MASK_SSE; + break; + + case XSTATE_COPY_XSAVE: + header.xfeatures &= xfeatures_mask_user(); + break; + } /* Copy FP state up to MXCSR */ copy_feature(header.xfeatures & XFEATURE_MASK_FP, &to, &xsave->i387, @@ -1109,6 +1125,9 @@ void copy_xstate_to_kernel(struct membuf to, struct xregs_state *xsave) &to, &xsave->i387.xmm_space, &xinit->i387.xmm_space, sizeof(xsave->i387.xmm_space)); + if (copy_mode != XSTATE_COPY_XSAVE) + goto out; + /* Zero the padding area */ membuf_zero(&to, sizeof(xsave->i387.padding)); @@ -1150,6 +1169,7 @@ void copy_xstate_to_kernel(struct membuf to, struct xregs_state *xsave) zerofrom = xstate_offsets[i] + xstate_sizes[i]; } +out: if (to.left) membuf_zero(&to, to.left); } From adc997b3d66d1cfa8c15a7dbafdaef239a51b5db Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:43 +0200 Subject: [PATCH 24/74] x86/fpu: Use copy_xstate_to_uabi_buf() in xfpregs_get() Use the new functionality of copy_xstate_to_uabi_buf() to retrieve the FX state when XSAVE* is in use. This avoids overwriting the FPU state buffer with fpstate_sanitize_xstate() which is error prone and duplicated code. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121452.901736860@linutronix.de --- arch/x86/kernel/fpu/regset.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 783f84dfcd466c..ccbe25f6627d4c 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -33,13 +33,18 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, { struct fpu *fpu = &target->thread.fpu; - if (!boot_cpu_has(X86_FEATURE_FXSR)) + if (!cpu_feature_enabled(X86_FEATURE_FXSR)) return -ENODEV; fpu__prepare_read(fpu); - fpstate_sanitize_xstate(fpu); - return membuf_write(&to, &fpu->state.fxsave, sizeof(struct fxregs_state)); + if (!use_xsave()) { + return membuf_write(&to, &fpu->state.fxsave, + sizeof(fpu->state.fxsave)); + } + + copy_xstate_to_uabi_buf(to, &fpu->state.xsave, XSTATE_COPY_FX); + return 0; } int xfpregs_set(struct task_struct *target, const struct user_regset *regset, From 3f7f75634ccefefcc929696f346db7a748e78f79 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:44 +0200 Subject: [PATCH 25/74] x86/fpu: Use copy_xstate_to_uabi_buf() in fpregs_get() Use the new functionality of copy_xstate_to_uabi_buf() to retrieve the FX state when XSAVE* is in use. This avoids to overwrite the FPU state buffer with fpstate_sanitize_xstate() which is error prone and duplicated code. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121453.014441775@linutronix.de --- arch/x86/kernel/fpu/regset.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index ccbe25f6627d4c..4b799e42ebc798 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -210,10 +210,10 @@ static inline u32 twd_fxsr_to_i387(struct fxregs_state *fxsave) * FXSR floating point environment conversions. */ -void -convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) +static void __convert_from_fxsr(struct user_i387_ia32_struct *env, + struct task_struct *tsk, + struct fxregs_state *fxsave) { - struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave; struct _fpreg *to = (struct _fpreg *) &env->st_space[0]; struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0]; int i; @@ -247,6 +247,12 @@ convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) memcpy(&to[i], &from[i], sizeof(to[0])); } +void +convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) +{ + __convert_from_fxsr(env, tsk, &tsk->thread.fpu.state.fxsave); +} + void convert_to_fxsr(struct fxregs_state *fxsave, const struct user_i387_ia32_struct *env) @@ -279,25 +285,29 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, { struct fpu *fpu = &target->thread.fpu; struct user_i387_ia32_struct env; + struct fxregs_state fxsave, *fx; fpu__prepare_read(fpu); - if (!boot_cpu_has(X86_FEATURE_FPU)) + if (!cpu_feature_enabled(X86_FEATURE_FPU)) return fpregs_soft_get(target, regset, to); - if (!boot_cpu_has(X86_FEATURE_FXSR)) { + if (!cpu_feature_enabled(X86_FEATURE_FXSR)) { return membuf_write(&to, &fpu->state.fsave, sizeof(struct fregs_state)); } - fpstate_sanitize_xstate(fpu); + if (use_xsave()) { + struct membuf mb = { .p = &fxsave, .left = sizeof(fxsave) }; - if (to.left == sizeof(env)) { - convert_from_fxsr(to.p, target); - return 0; + /* Handle init state optimized xstate correctly */ + copy_xstate_to_uabi_buf(mb, &fpu->state.xsave, XSTATE_COPY_FP); + fx = &fxsave; + } else { + fx = &fpu->state.fxsave; } - convert_from_fxsr(&env, target); + __convert_from_fxsr(&env, target, fx); return membuf_write(&to, &env, sizeof(env)); } From afac9e894364418731d1d7e66c1118b31fd130e8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:45 +0200 Subject: [PATCH 26/74] x86/fpu: Remove fpstate_sanitize_xstate() No more users. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121453.124819167@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 2 - arch/x86/kernel/fpu/xstate.c | 79 ----------------------------- 2 files changed, 81 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 9ed98460959516..0148791acc4926 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -86,8 +86,6 @@ extern void fpstate_init_soft(struct swregs_state *soft); static inline void fpstate_init_soft(struct swregs_state *soft) {} #endif -extern void fpstate_sanitize_xstate(struct fpu *fpu); - #define user_insn(insn, output, input...) \ ({ \ int err; \ diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 8d023a26ae222e..e17fde9b1ca3d8 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -128,85 +128,6 @@ static bool xfeature_is_supervisor(int xfeature_nr) return ecx & 1; } -/* - * When executing XSAVEOPT (or other optimized XSAVE instructions), if - * a processor implementation detects that an FPU state component is still - * (or is again) in its initialized state, it may clear the corresponding - * bit in the header.xfeatures field, and can skip the writeout of registers - * to the corresponding memory layout. - * - * This means that when the bit is zero, the state component might still contain - * some previous - non-initialized register state. - * - * Before writing xstate information to user-space we sanitize those components, - * to always ensure that the memory layout of a feature will be in the init state - * if the corresponding header bit is zero. This is to ensure that user-space doesn't - * see some stale state in the memory layout during signal handling, debugging etc. - */ -void fpstate_sanitize_xstate(struct fpu *fpu) -{ - struct fxregs_state *fx = &fpu->state.fxsave; - int feature_bit; - u64 xfeatures; - - if (!use_xsaveopt()) - return; - - xfeatures = fpu->state.xsave.header.xfeatures; - - /* - * None of the feature bits are in init state. So nothing else - * to do for us, as the memory layout is up to date. - */ - if ((xfeatures & xfeatures_mask_all) == xfeatures_mask_all) - return; - - /* - * FP is in init state - */ - if (!(xfeatures & XFEATURE_MASK_FP)) { - fx->cwd = 0x37f; - fx->swd = 0; - fx->twd = 0; - fx->fop = 0; - fx->rip = 0; - fx->rdp = 0; - memset(fx->st_space, 0, sizeof(fx->st_space)); - } - - /* - * SSE is in init state - */ - if (!(xfeatures & XFEATURE_MASK_SSE)) - memset(fx->xmm_space, 0, sizeof(fx->xmm_space)); - - /* - * First two features are FPU and SSE, which above we handled - * in a special way already: - */ - feature_bit = 0x2; - xfeatures = (xfeatures_mask_user() & ~xfeatures) >> 2; - - /* - * Update all the remaining memory layouts according to their - * standard xstate layout, if their header bit is in the init - * state: - */ - while (xfeatures) { - if (xfeatures & 0x1) { - int offset = xstate_comp_offsets[feature_bit]; - int size = xstate_sizes[feature_bit]; - - memcpy((void *)fx + offset, - (void *)&init_fpstate.xsave + offset, - size); - } - - xfeatures >>= 1; - feature_bit++; - } -} - /* * Enable the extended processor state save/restore feature. * Called once per CPU onlining. From 5a32fac8dbe8adc08c10e2c8770c95aebfc627cd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:46 +0200 Subject: [PATCH 27/74] x86/fpu/regset: Move fpu__read_begin() into regset The function can only be used from the regset get() callbacks safely. So there is no reason to have it globally exposed. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121453.234942936@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 1 - arch/x86/kernel/fpu/core.c | 20 -------------------- arch/x86/kernel/fpu/regset.c | 22 +++++++++++++++++++--- 3 files changed, 19 insertions(+), 24 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 0148791acc4926..4c669f3b54b4fc 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -26,7 +26,6 @@ /* * High level FPU state handling functions: */ -extern void fpu__prepare_read(struct fpu *fpu); extern void fpu__prepare_write(struct fpu *fpu); extern void fpu__save(struct fpu *fpu); extern int fpu__restore_sig(void __user *buf, int ia32_frame); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 9ff467bb4894c4..d390644e5fa192 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -281,26 +281,6 @@ static void fpu__initialize(struct fpu *fpu) trace_x86_fpu_init_state(fpu); } -/* - * This function must be called before we read a task's fpstate. - * - * There's two cases where this gets called: - * - * - for the current task (when coredumping), in which case we have - * to save the latest FPU registers into the fpstate, - * - * - or it's called for stopped tasks (ptrace), in which case the - * registers were already saved by the context-switch code when - * the task scheduled out. - * - * If the task has used the FPU before then save it. - */ -void fpu__prepare_read(struct fpu *fpu) -{ - if (fpu == ¤t->thread.fpu) - fpu__save(fpu); -} - /* * This function must be called before we write a task's fpstate. * diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 4b799e42ebc798..937adf702b3709 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -28,6 +28,22 @@ int regset_xregset_fpregs_active(struct task_struct *target, const struct user_r return 0; } +/* + * The regset get() functions are invoked from: + * + * - coredump to dump the current task's fpstate. If the current task + * owns the FPU then the memory state has to be synchronized and the + * FPU register state preserved. Otherwise fpstate is already in sync. + * + * - ptrace to dump fpstate of a stopped task, in which case the registers + * have already been saved to fpstate on context switch. + */ +static void sync_fpstate(struct fpu *fpu) +{ + if (fpu == ¤t->thread.fpu) + fpu__save(fpu); +} + int xfpregs_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { @@ -36,7 +52,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, if (!cpu_feature_enabled(X86_FEATURE_FXSR)) return -ENODEV; - fpu__prepare_read(fpu); + sync_fpstate(fpu); if (!use_xsave()) { return membuf_write(&to, &fpu->state.fxsave, @@ -96,7 +112,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) return -ENODEV; - fpu__prepare_read(fpu); + sync_fpstate(fpu); copy_xstate_to_uabi_buf(to, &fpu->state.xsave, XSTATE_COPY_XSAVE); return 0; @@ -287,7 +303,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; struct fxregs_state fxsave, *fx; - fpu__prepare_read(fpu); + sync_fpstate(fpu); if (!cpu_feature_enabled(X86_FEATURE_FPU)) return fpregs_soft_get(target, regset, to); From dbb60ac764581e62f2116c5a6b8926ba3a872dd4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:47 +0200 Subject: [PATCH 28/74] x86/fpu: Move fpu__write_begin() to regset The only usecase for fpu__write_begin is the set() callback of regset, so the function is pointlessly global. Move it to the regset code and rename it to fpu_force_restore() which is exactly decribing what the function does. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121453.328652975@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 1 - arch/x86/kernel/fpu/core.c | 24 ------------------------ arch/x86/kernel/fpu/regset.c | 25 ++++++++++++++++++++++--- 3 files changed, 22 insertions(+), 28 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 4c669f3b54b4fc..854bfb03645e60 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -26,7 +26,6 @@ /* * High level FPU state handling functions: */ -extern void fpu__prepare_write(struct fpu *fpu); extern void fpu__save(struct fpu *fpu); extern int fpu__restore_sig(void __user *buf, int ia32_frame); extern void fpu__drop(struct fpu *fpu); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index d390644e5fa192..22437011f4f088 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -281,30 +281,6 @@ static void fpu__initialize(struct fpu *fpu) trace_x86_fpu_init_state(fpu); } -/* - * This function must be called before we write a task's fpstate. - * - * Invalidate any cached FPU registers. - * - * After this function call, after registers in the fpstate are - * modified and the child task has woken up, the child task will - * restore the modified FPU state from the modified context. If we - * didn't clear its cached status here then the cached in-registers - * state pending on its former CPU could be restored, corrupting - * the modifications. - */ -void fpu__prepare_write(struct fpu *fpu) -{ - /* - * Only stopped child tasks can be used to modify the FPU - * state in the fpstate buffer: - */ - WARN_ON_FPU(fpu == ¤t->thread.fpu); - - /* Invalidate any cached state: */ - __fpu_invalidate_fpregs_state(fpu); -} - /* * Drops current FPU state: deactivates the fpregs and * the fpstate. NOTE: it still leaves previous contents diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 937adf702b3709..ddc290d9bf8e15 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -44,6 +44,25 @@ static void sync_fpstate(struct fpu *fpu) fpu__save(fpu); } +/* + * Invalidate cached FPU registers before modifying the stopped target + * task's fpstate. + * + * This forces the target task on resume to restore the FPU registers from + * modified fpstate. Otherwise the task might skip the restore and operate + * with the cached FPU registers which discards the modifications. + */ +static void fpu_force_restore(struct fpu *fpu) +{ + /* + * Only stopped child tasks can be used to modify the FPU + * state in the fpstate buffer: + */ + WARN_ON_FPU(fpu == ¤t->thread.fpu); + + __fpu_invalidate_fpregs_state(fpu); +} + int xfpregs_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { @@ -88,7 +107,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, if (newstate.mxcsr & ~mxcsr_feature_mask) return -EINVAL; - fpu__prepare_write(fpu); + fpu_force_restore(fpu); /* Copy the state */ memcpy(&fpu->state.fxsave, &newstate, sizeof(newstate)); @@ -146,7 +165,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, } } - fpu__prepare_write(fpu); + fpu_force_restore(fpu); ret = copy_kernel_to_xstate(&fpu->state.xsave, kbuf ?: tmpbuf); out: @@ -346,7 +365,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; - fpu__prepare_write(fpu); + fpu_force_restore(fpu); if (cpu_feature_enabled(X86_FEATURE_FXSR)) convert_to_fxsr(&fpu->state.fxsave, &env); From 02b93c0b00df222b9ccf7a1fbd0eb59353d0a58c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:48 +0200 Subject: [PATCH 29/74] x86/fpu: Get rid of using_compacted_format() This function is pointlessly global and a complete misnomer because it's usage is related to both supervisor state checks and compacted format checks. Remove it and just make the conditions check the XSAVES feature. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121453.425493349@linutronix.de --- arch/x86/include/asm/fpu/xstate.h | 1 - arch/x86/kernel/fpu/xstate.c | 22 ++++------------------ 2 files changed, 4 insertions(+), 19 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 732ae793c2ab3c..6e5ba42ffd424a 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -101,7 +101,6 @@ 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 using_compacted_format(void); int xfeature_size(int xfeature_nr); int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf); int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index e17fde9b1ca3d8..185cc5d1aa332a 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -449,20 +449,6 @@ int xfeature_size(int xfeature_nr) return eax; } -/* - * 'XSAVES' implies two different things: - * 1. saving of supervisor/system state - * 2. using the compacted format - * - * Use this function when dealing with the compacted format so - * that it is obvious which aspect of 'XSAVES' is being handled - * by the calling code. - */ -int using_compacted_format(void) -{ - return boot_cpu_has(X86_FEATURE_XSAVES); -} - /* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ static int validate_user_xstate_header(const struct xstate_header *hdr) { @@ -581,9 +567,9 @@ static void do_extra_xstate_size_checks(void) check_xstate_against_struct(i); /* * Supervisor state components can be managed only by - * XSAVES, which is compacted-format only. + * XSAVES. */ - if (!using_compacted_format()) + if (!cpu_feature_enabled(X86_FEATURE_XSAVES)) XSTATE_WARN_ON(xfeature_is_supervisor(i)); /* Align from the end of the previous feature */ @@ -593,9 +579,9 @@ static void do_extra_xstate_size_checks(void) * 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(). + * setup_xstate_features(). XSAVES uses compacted format. */ - if (!using_compacted_format()) + if (!cpu_feature_enabled(X86_FEATURE_XSAVES)) paranoid_xstate_size = xfeature_uncompacted_offset(i); /* * The compacted-format offset always depends on where From 71ef453355a9197fcfd8ff22391a4ad7861d79e6 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Wed, 23 Jun 2021 14:01:49 +0200 Subject: [PATCH 30/74] x86/kvm: Avoid looking up PKRU in XSAVE buffer PKRU is being removed from the kernel XSAVE/FPU buffers. This removal will probably include warnings for code that look up PKRU in those buffers. KVM currently looks up the location of PKRU but doesn't even use the pointer that it gets back. Rework the code to avoid calling get_xsave_addr() except in cases where its result is actually used. This makes the code more clear and also avoids the inevitable PKRU warnings. This is probably a good cleanup and could go upstream idependently of any PKRU rework. Signed-off-by: Dave Hansen Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121453.541037562@linutronix.de --- arch/x86/kvm/x86.c | 45 ++++++++++++++++++++++++--------------------- 1 file changed, 24 insertions(+), 21 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e0f4a46649d750..c25bf240eb269c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4604,20 +4604,21 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) */ 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 = get_xsave_addr(xsave, xfeature_nr); - - if (src) { - u32 size, offset, ecx, edx; - 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 - memcpy(dest + offset, src, size); + 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; @@ -4647,18 +4648,20 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) */ 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 *dest = get_xsave_addr(xsave, xfeature_nr); - - if (dest) { - u32 size, offset, ecx, edx; - 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 + + 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); } From 9fe8a6f5eed8fff6b2d7dbc99b911334e311732d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:50 +0200 Subject: [PATCH 31/74] x86/fpu: Cleanup arch_set_user_pkey_access() The function does a sanity check with a WARN_ON_ONCE() but happily proceeds when the pkey argument is out of range. Clean it up. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121453.635764326@linutronix.de --- arch/x86/kernel/fpu/xstate.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 185cc5d1aa332a..579e343e665404 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -912,11 +912,10 @@ EXPORT_SYMBOL_GPL(get_xsave_addr); * rights for @pkey to @init_val. */ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, - unsigned long init_val) + unsigned long init_val) { - u32 old_pkru; - int pkey_shift = (pkey * PKRU_BITS_PER_PKEY); - u32 new_pkru_bits = 0; + u32 old_pkru, new_pkru_bits = 0; + int pkey_shift; /* * This check implies XSAVE support. OSPKE only gets @@ -930,7 +929,8 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, * values originating from in-kernel users. Complain * if a bad value is observed. */ - WARN_ON_ONCE(pkey >= arch_max_pkey()); + if (WARN_ON_ONCE(pkey >= arch_max_pkey())) + return -EINVAL; /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) @@ -939,6 +939,7 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, new_pkru_bits |= PKRU_WD_BIT; /* Shift the bits in to the correct place in PKRU for pkey: */ + pkey_shift = pkey * PKRU_BITS_PER_PKEY; new_pkru_bits <<= pkey_shift; /* Get old PKRU and mask off any old bits in place: */ From 1f3171252dc586745bb548d48f3bcedfea34b58d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:51 +0200 Subject: [PATCH 32/74] x86/fpu: Get rid of copy_supervisor_to_kernel() If the fast path of restoring the FPU state on sigreturn fails or is not taken and the current task's FPU is active then the FPU has to be deactivated for the slow path to allow a safe update of the tasks FPU memory state. With supervisor states enabled, this requires to save the supervisor state in the memory state first. Supervisor states require XSAVES so saving only the supervisor state requires to reshuffle the memory buffer because XSAVES uses the compacted format and therefore stores the supervisor states at the beginning of the memory state. That's just an overengineered optimization. Get rid of it and save the full state for this case. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Andy Lutomirski Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121453.734561971@linutronix.de --- arch/x86/include/asm/fpu/xstate.h | 1 - arch/x86/kernel/fpu/signal.c | 13 +++++--- arch/x86/kernel/fpu/xstate.c | 55 ------------------------------- 3 files changed, 8 insertions(+), 61 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 6e5ba42ffd424a..6611e069e8347e 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -104,7 +104,6 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); int xfeature_size(int xfeature_nr); int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf); int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf); -void copy_supervisor_to_kernel(struct xregs_state *xsave); void copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask); void copy_kernel_to_dynamic_supervisor(struct xregs_state *xstate, u64 mask); diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 888c8e0d2ff111..501059579066b2 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -401,15 +401,18 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) * the optimisation). */ fpregs_lock(); - if (!test_thread_flag(TIF_NEED_FPU_LOAD)) { - /* - * Supervisor states are not modified by user space input. Save - * current supervisor states first and invalidate the FPU regs. + * If supervisor states are available then save the + * hardware state in current's fpstate so that the + * supervisor state is preserved. Save the full state for + * simplicity. There is no point in optimizing this by only + * saving the supervisor states and then shuffle them to + * the right place in memory. This is the slow path and the + * above XRSTOR failed or ia32_fxstate is true. Shrug. */ if (xfeatures_mask_supervisor()) - copy_supervisor_to_kernel(&fpu->state.xsave); + copy_xregs_to_kernel(&fpu->state.xsave); set_thread_flag(TIF_NEED_FPU_LOAD); } __fpu_invalidate_fpregs_state(fpu); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 579e343e665404..427977b52c6c2f 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1204,61 +1204,6 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) return 0; } -/* - * Save only supervisor states to the kernel buffer. This blows away all - * old states, and is intended to be used only in __fpu__restore_sig(), where - * user states are restored from the user buffer. - */ -void copy_supervisor_to_kernel(struct xregs_state *xstate) -{ - struct xstate_header *header; - u64 max_bit, min_bit; - u32 lmask, hmask; - int err, i; - - if (WARN_ON(!boot_cpu_has(X86_FEATURE_XSAVES))) - return; - - if (!xfeatures_mask_supervisor()) - return; - - max_bit = __fls(xfeatures_mask_supervisor()); - min_bit = __ffs(xfeatures_mask_supervisor()); - - lmask = xfeatures_mask_supervisor(); - hmask = xfeatures_mask_supervisor() >> 32; - XSTATE_OP(XSAVES, xstate, lmask, hmask, err); - - /* We should never fault when copying to a kernel buffer: */ - if (WARN_ON_FPU(err)) - return; - - /* - * At this point, the buffer has only supervisor states and must be - * converted back to normal kernel format. - */ - header = &xstate->header; - header->xcomp_bv |= xfeatures_mask_all; - - /* - * This only moves states up in the buffer. Start with - * the last state and move backwards so that states are - * not overwritten until after they are moved. Note: - * memmove() allows overlapping src/dst buffers. - */ - for (i = max_bit; i >= min_bit; i--) { - u8 *xbuf = (u8 *)xstate; - - if (!((header->xfeatures >> i) & 1)) - continue; - - /* Move xfeature 'i' into its normal location */ - memmove(xbuf + xstate_comp_offsets[i], - xbuf + xstate_supervisor_only_offsets[i], - xstate_sizes[i]); - } -} - /** * copy_dynamic_supervisor_to_kernel() - Save dynamic supervisor states to * an xsave area From b16313f71c1050ad5c92548925e0e9cec26989ab Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:52 +0200 Subject: [PATCH 33/74] x86/fpu: Rename copy_xregs_to_kernel() and copy_kernel_to_xregs() The function names for xsave[s]/xrstor[s] operations are horribly named and a permanent source of confusion. Rename: copy_xregs_to_kernel() to os_xsave() copy_kernel_to_xregs() to os_xrstor() These are truly low level wrappers around the actual instructions XSAVE[OPT]/XRSTOR and XSAVES/XRSTORS with the twist that the selection based on the available CPU features happens with an alternative to avoid conditionals all over the place and to provide the best performance for hot paths. The os_ prefix tells that this is the OS selected mechanism. No functional change. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121453.830239347@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 17 +++++++++++------ arch/x86/kernel/fpu/core.c | 7 +++---- arch/x86/kernel/fpu/signal.c | 21 +++++++++++---------- arch/x86/kernel/fpu/xstate.c | 2 +- 4 files changed, 26 insertions(+), 21 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 854bfb03645e60..dae15455914d6a 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -261,7 +261,7 @@ static inline void fxsave(struct fxregs_state *fx) * 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 copy_kernel_to_xregs_booting(struct xregs_state *xstate) +static inline void os_xrstor_booting(struct xregs_state *xstate) { u64 mask = -1; u32 lmask = mask; @@ -284,8 +284,11 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) /* * 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 copy_xregs_to_kernel(struct xregs_state *xstate) +static inline void os_xsave(struct xregs_state *xstate) { u64 mask = xfeatures_mask_all; u32 lmask = mask; @@ -302,8 +305,10 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) /* * Restore processor xstate from xsave area. + * + * Uses XRSTORS when XSAVES is used, XRSTOR otherwise. */ -static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) +static inline void os_xrstor(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; @@ -364,13 +369,13 @@ static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask) * Restore xstate from kernel space xsave area, return an error code instead of * an exception. */ -static inline int copy_kernel_to_xregs_err(struct xregs_state *xstate, u64 mask) +static inline int os_xrstor_safe(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; int err; - if (static_cpu_has(X86_FEATURE_XSAVES)) + if (cpu_feature_enabled(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); @@ -383,7 +388,7 @@ extern int copy_fpregs_to_fpstate(struct fpu *fpu); static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask) { if (use_xsave()) { - copy_kernel_to_xregs(&fpstate->xsave, mask); + os_xrstor(&fpstate->xsave, mask); } else { if (use_fxsr()) copy_kernel_to_fxregs(&fpstate->fxsave); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 22437011f4f088..bfdcf7fd63e3f7 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -95,7 +95,7 @@ EXPORT_SYMBOL(irq_fpu_usable); int copy_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { - copy_xregs_to_kernel(&fpu->state.xsave); + os_xsave(&fpu->state.xsave); /* * AVX512 state is tracked here because its use is @@ -314,7 +314,7 @@ void fpu__drop(struct fpu *fpu) static inline void copy_init_fpstate_to_fpregs(u64 features_mask) { if (use_xsave()) - copy_kernel_to_xregs(&init_fpstate.xsave, features_mask); + os_xrstor(&init_fpstate.xsave, features_mask); else if (static_cpu_has(X86_FEATURE_FXSR)) copy_kernel_to_fxregs(&init_fpstate.fxsave); else @@ -345,8 +345,7 @@ static void fpu__clear(struct fpu *fpu, bool user_only) if (user_only) { if (!fpregs_state_valid(fpu, smp_processor_id()) && xfeatures_mask_supervisor()) - copy_kernel_to_xregs(&fpu->state.xsave, - xfeatures_mask_supervisor()); + os_xrstor(&fpu->state.xsave, xfeatures_mask_supervisor()); copy_init_fpstate_to_fpregs(xfeatures_mask_user()); } else { copy_init_fpstate_to_fpregs(xfeatures_mask_all); diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 501059579066b2..33675b3dad0e10 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -261,14 +261,14 @@ static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only) r = copy_user_to_fxregs(buf); if (!r) - copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); + os_xrstor(&init_fpstate.xsave, init_bv); return r; } else { init_bv = xfeatures_mask_user() & ~xbv; r = copy_user_to_xregs(buf, xbv); if (!r && unlikely(init_bv)) - copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); + os_xrstor(&init_fpstate.xsave, init_bv); return r; } } else if (use_fxsr()) { @@ -356,9 +356,10 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) * has been copied to the kernel one. */ if (test_thread_flag(TIF_NEED_FPU_LOAD) && - xfeatures_mask_supervisor()) - copy_kernel_to_xregs(&fpu->state.xsave, - xfeatures_mask_supervisor()); + xfeatures_mask_supervisor()) { + os_xrstor(&fpu->state.xsave, + xfeatures_mask_supervisor()); + } fpregs_mark_activate(); fpregs_unlock(); return 0; @@ -412,7 +413,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) * above XRSTOR failed or ia32_fxstate is true. Shrug. */ if (xfeatures_mask_supervisor()) - copy_xregs_to_kernel(&fpu->state.xsave); + os_xsave(&fpu->state.xsave); set_thread_flag(TIF_NEED_FPU_LOAD); } __fpu_invalidate_fpregs_state(fpu); @@ -430,14 +431,14 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) fpregs_lock(); if (unlikely(init_bv)) - copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); + os_xrstor(&init_fpstate.xsave, init_bv); /* * Restore previously saved supervisor xstates along with * copied-in user xstates. */ - ret = copy_kernel_to_xregs_err(&fpu->state.xsave, - user_xfeatures | xfeatures_mask_supervisor()); + ret = os_xrstor_safe(&fpu->state.xsave, + user_xfeatures | xfeatures_mask_supervisor()); } else if (use_fxsr()) { ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size); @@ -454,7 +455,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) u64 init_bv; init_bv = xfeatures_mask_user() & ~XFEATURE_MASK_FPSSE; - copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); + os_xrstor(&init_fpstate.xsave, init_bv); } ret = copy_kernel_to_fxregs_err(&fpu->state.fxsave); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 427977b52c6c2f..4fca8a8edff8e4 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -400,7 +400,7 @@ static void __init setup_init_fpu_buf(void) /* * Init all the features state with header.xfeatures being 0x0 */ - copy_kernel_to_xregs_booting(&init_fpstate.xsave); + os_xrstor_booting(&init_fpstate.xsave); /* * All components are now in init state. Read the state back so From 6b862ba1821441e6083cf061404694d33a841526 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:53 +0200 Subject: [PATCH 34/74] x86/fpu: Rename copy_user_to_xregs() and copy_xregs_to_user() The function names for xsave[s]/xrstor[s] operations are horribly named and a permanent source of confusion. Rename: copy_xregs_to_user() to xsave_to_user_sigframe() copy_user_to_xregs() to xrstor_from_user_sigframe() so it's entirely clear what this is about. This is also a clear indicator of the potentially different storage format because this is user ABI and cannot use compacted format. No functional change. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121453.924266705@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 4 ++-- arch/x86/kernel/fpu/signal.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index dae15455914d6a..a2ab74478d1d28 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -326,7 +326,7 @@ static inline void os_xrstor(struct xregs_state *xstate, u64 mask) * backward compatibility for old applications which don't understand * compacted format of xsave area. */ -static inline int copy_xregs_to_user(struct xregs_state __user *buf) +static inline int xsave_to_user_sigframe(struct xregs_state __user *buf) { u64 mask = xfeatures_mask_user(); u32 lmask = mask; @@ -351,7 +351,7 @@ static inline int copy_xregs_to_user(struct xregs_state __user *buf) /* * Restore xstate from user space xsave area. */ -static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask) +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; diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 33675b3dad0e10..4fe632f56697a3 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -129,7 +129,7 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) int err; if (use_xsave()) - err = copy_xregs_to_user(buf); + err = xsave_to_user_sigframe(buf); else if (use_fxsr()) err = copy_fxregs_to_user((struct fxregs_state __user *) buf); else @@ -266,7 +266,7 @@ static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only) } else { init_bv = xfeatures_mask_user() & ~xbv; - r = copy_user_to_xregs(buf, xbv); + r = xrstor_from_user_sigframe(buf, xbv); if (!r && unlikely(init_bv)) os_xrstor(&init_fpstate.xsave, init_bv); return r; From 16dcf4385933a02bb21d0af86a04439d151ad42a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:54 +0200 Subject: [PATCH 35/74] x86/fpu: Rename fxregs-related copy functions The function names for fxsave/fxrstor operations are horribly named and a permanent source of confusion. Rename: copy_fxregs_to_kernel() to fxsave() copy_kernel_to_fxregs() to fxrstor() copy_fxregs_to_user() to fxsave_to_user_sigframe() copy_user_to_fxregs() to fxrstor_from_user_sigframe() so it's clear what these are doing. All these functions are really low level wrappers around the equally named instructions, so mapping to the documentation is just natural. While at it, replace the static_cpu_has(X86_FEATURE_FXSR) with use_fxsr() to be consistent with the rest of the code. No functional change. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121454.017863494@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 18 +++++------------- arch/x86/kernel/fpu/core.c | 6 +++--- arch/x86/kernel/fpu/signal.c | 10 +++++----- 3 files changed, 13 insertions(+), 21 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index a2ab74478d1d28..7806f39de3cbc7 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -129,7 +129,7 @@ static inline int copy_fregs_to_user(struct fregs_state __user *fx) return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); } -static inline int copy_fxregs_to_user(struct fxregs_state __user *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)); @@ -138,7 +138,7 @@ static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) } -static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) +static inline void fxrstor(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); @@ -146,7 +146,7 @@ static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } -static inline int copy_kernel_to_fxregs_err(struct fxregs_state *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)); @@ -154,7 +154,7 @@ static inline int copy_kernel_to_fxregs_err(struct fxregs_state *fx) return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } -static inline int copy_user_to_fxregs(struct fxregs_state __user *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)); @@ -177,14 +177,6 @@ static inline int copy_user_to_fregs(struct fregs_state __user *fx) return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } -static inline void copy_fxregs_to_kernel(struct fpu *fpu) -{ - if (IS_ENABLED(CONFIG_X86_32)) - asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave)); - else - asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave)); -} - static inline void fxsave(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) @@ -391,7 +383,7 @@ static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask os_xrstor(&fpstate->xsave, mask); } else { if (use_fxsr()) - copy_kernel_to_fxregs(&fpstate->fxsave); + fxrstor(&fpstate->fxsave); else copy_kernel_to_fregs(&fpstate->fsave); } diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index bfdcf7fd63e3f7..035487dcb29e75 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -107,7 +107,7 @@ int copy_fpregs_to_fpstate(struct fpu *fpu) } if (likely(use_fxsr())) { - copy_fxregs_to_kernel(fpu); + fxsave(&fpu->state.fxsave); return 1; } @@ -315,8 +315,8 @@ static inline void copy_init_fpstate_to_fpregs(u64 features_mask) { if (use_xsave()) os_xrstor(&init_fpstate.xsave, features_mask); - else if (static_cpu_has(X86_FEATURE_FXSR)) - copy_kernel_to_fxregs(&init_fpstate.fxsave); + else if (use_fxsr()) + fxrstor(&init_fpstate.fxsave); else copy_kernel_to_fregs(&init_fpstate.fsave); diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 4fe632f56697a3..05f8445eb676a6 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -64,7 +64,7 @@ static inline int save_fsave_header(struct task_struct *tsk, void __user *buf) fpregs_lock(); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) - copy_fxregs_to_kernel(&tsk->thread.fpu); + fxsave(&tsk->thread.fpu.state.fxsave); fpregs_unlock(); convert_from_fxsr(&env, tsk); @@ -131,7 +131,7 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) if (use_xsave()) err = xsave_to_user_sigframe(buf); else if (use_fxsr()) - err = copy_fxregs_to_user((struct fxregs_state __user *) buf); + err = fxsave_to_user_sigframe((struct fxregs_state __user *) buf); else err = copy_fregs_to_user((struct fregs_state __user *) buf); @@ -259,7 +259,7 @@ static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only) if (fx_only) { init_bv = xfeatures_mask_user() & ~XFEATURE_MASK_FPSSE; - r = copy_user_to_fxregs(buf); + r = fxrstor_from_user_sigframe(buf); if (!r) os_xrstor(&init_fpstate.xsave, init_bv); return r; @@ -272,7 +272,7 @@ static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only) return r; } } else if (use_fxsr()) { - return copy_user_to_fxregs(buf); + return fxrstor_from_user_sigframe(buf); } else return copy_user_to_fregs(buf); } @@ -458,7 +458,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) os_xrstor(&init_fpstate.xsave, init_bv); } - ret = copy_kernel_to_fxregs_err(&fpu->state.fxsave); + ret = fxrstor_safe(&fpu->state.fxsave); } else { ret = __copy_from_user(&fpu->state.fsave, buf_fx, state_size); if (ret) From 872c65dbf669b3b471b3d8656391a6b4f736d22b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:55 +0200 Subject: [PATCH 36/74] x86/math-emu: Rename frstor() This is in the way of renaming the low level hardware accessors to match the instruction name. Prepend it with FPU_ which is consistent vs. the rest of the emulation code. No functional change. [ bp: Correct the Reported-by: ] Reported-by: kernel test robot Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121454.111665161@linutronix.de --- arch/x86/math-emu/fpu_proto.h | 2 +- arch/x86/math-emu/load_store.c | 2 +- arch/x86/math-emu/reg_ld_str.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/math-emu/fpu_proto.h b/arch/x86/math-emu/fpu_proto.h index 70d35c20094517..94c4023092f3a6 100644 --- a/arch/x86/math-emu/fpu_proto.h +++ b/arch/x86/math-emu/fpu_proto.h @@ -144,7 +144,7 @@ extern int FPU_store_int16(FPU_REG *st0_ptr, u_char st0_tag, short __user *d); extern int FPU_store_bcd(FPU_REG *st0_ptr, u_char st0_tag, u_char __user *d); extern int FPU_round_to_int(FPU_REG *r, u_char tag); extern u_char __user *fldenv(fpu_addr_modes addr_modes, u_char __user *s); -extern void frstor(fpu_addr_modes addr_modes, u_char __user *data_address); +extern void FPU_frstor(fpu_addr_modes addr_modes, u_char __user *data_address); extern u_char __user *fstenv(fpu_addr_modes addr_modes, u_char __user *d); extern void fsave(fpu_addr_modes addr_modes, u_char __user *data_address); extern int FPU_tagof(FPU_REG *ptr); diff --git a/arch/x86/math-emu/load_store.c b/arch/x86/math-emu/load_store.c index f15263e158e8e6..4092df79de4f50 100644 --- a/arch/x86/math-emu/load_store.c +++ b/arch/x86/math-emu/load_store.c @@ -240,7 +240,7 @@ int FPU_load_store(u_char type, fpu_addr_modes addr_modes, fix-up operations. */ return 1; case 022: /* frstor m94/108byte */ - frstor(addr_modes, (u_char __user *) data_address); + FPU_frstor(addr_modes, (u_char __user *) data_address); /* Ensure that the values just loaded are not changed by fix-up operations. */ return 1; diff --git a/arch/x86/math-emu/reg_ld_str.c b/arch/x86/math-emu/reg_ld_str.c index 7ca6417c0c8d17..7e4521fbe7da0d 100644 --- a/arch/x86/math-emu/reg_ld_str.c +++ b/arch/x86/math-emu/reg_ld_str.c @@ -1117,7 +1117,7 @@ u_char __user *fldenv(fpu_addr_modes addr_modes, u_char __user *s) return s; } -void frstor(fpu_addr_modes addr_modes, u_char __user *data_address) +void FPU_frstor(fpu_addr_modes addr_modes, u_char __user *data_address) { int i, regnr; u_char __user *s = fldenv(addr_modes, data_address); From 6fdc908cb56123591baa4259400cfb0787582b11 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:56 +0200 Subject: [PATCH 37/74] x86/fpu: Rename fregs-related copy functions The function names for fnsave/fnrstor operations are horribly named and a permanent source of confusion. Rename: copy_kernel_to_fregs() to frstor() copy_fregs_to_user() to fnsave_to_user_sigframe() copy_user_to_fregs() to frstor_from_user_sigframe() so it's clear what these are doing. All these functions are really low level wrappers around the equally named instructions, so mapping to the documentation is just natural. No functional change. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121454.223594101@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 10 +++++----- arch/x86/kernel/fpu/core.c | 2 +- arch/x86/kernel/fpu/signal.c | 6 +++--- 3 files changed, 9 insertions(+), 9 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 7806f39de3cbc7..cd88233f10574a 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -124,7 +124,7 @@ static inline void fpstate_init_soft(struct swregs_state *soft) {} _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore) \ : output : input) -static inline int copy_fregs_to_user(struct fregs_state __user *fx) +static inline int fnsave_to_user_sigframe(struct fregs_state __user *fx) { return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); } @@ -162,17 +162,17 @@ static inline int fxrstor_from_user_sigframe(struct fxregs_state __user *fx) return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } -static inline void copy_kernel_to_fregs(struct fregs_state *fx) +static inline void frstor(struct fregs_state *fx) { kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } -static inline int copy_kernel_to_fregs_err(struct fregs_state *fx) +static inline int frstor_safe(struct fregs_state *fx) { return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } -static inline int copy_user_to_fregs(struct fregs_state __user *fx) +static inline int frstor_from_user_sigframe(struct fregs_state __user *fx) { return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } @@ -385,7 +385,7 @@ static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask if (use_fxsr()) fxrstor(&fpstate->fxsave); else - copy_kernel_to_fregs(&fpstate->fsave); + frstor(&fpstate->fsave); } } diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 035487dcb29e75..1d2587607a7f8c 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -318,7 +318,7 @@ static inline void copy_init_fpstate_to_fpregs(u64 features_mask) else if (use_fxsr()) fxrstor(&init_fpstate.fxsave); else - copy_kernel_to_fregs(&init_fpstate.fsave); + frstor(&init_fpstate.fsave); if (boot_cpu_has(X86_FEATURE_OSPKE)) copy_init_pkru_to_fpregs(); diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 05f8445eb676a6..430c66dc221862 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -133,7 +133,7 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) else if (use_fxsr()) err = fxsave_to_user_sigframe((struct fxregs_state __user *) buf); else - err = copy_fregs_to_user((struct fregs_state __user *) buf); + err = fnsave_to_user_sigframe((struct fregs_state __user *) buf); if (unlikely(err) && __clear_user(buf, fpu_user_xstate_size)) err = -EFAULT; @@ -274,7 +274,7 @@ static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only) } else if (use_fxsr()) { return fxrstor_from_user_sigframe(buf); } else - return copy_user_to_fregs(buf); + return frstor_from_user_sigframe(buf); } static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) @@ -465,7 +465,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) goto out; fpregs_lock(); - ret = copy_kernel_to_fregs_err(&fpu->state.fsave); + ret = frstor_safe(&fpu->state.fsave); } if (!ret) fpregs_mark_activate(); From 1cc34413ff3f18c30e5df89fefd95cc0f3b3292e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:57 +0200 Subject: [PATCH 38/74] x86/fpu: Rename xstate copy functions which are related to UABI Rename them to reflect that these functions deal with user space format XSAVE buffers. copy_kernel_to_xstate() -> copy_uabi_from_kernel_to_xstate() copy_user_to_xstate() -> copy_sigframe_from_user_to_xstate() Again a clear statement that these functions deal with user space ABI. Suggested-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121454.318485015@linutronix.de --- arch/x86/include/asm/fpu/xstate.h | 4 ++-- arch/x86/kernel/fpu/regset.c | 2 +- arch/x86/kernel/fpu/signal.c | 2 +- arch/x86/kernel/fpu/xstate.c | 5 +++-- 4 files changed, 7 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 6611e069e8347e..00e1a2ac52395b 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -102,8 +102,8 @@ extern void __init update_regset_xstate_info(unsigned int size, void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); int xfeature_size(int xfeature_nr); -int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf); -int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf); +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 copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask); void copy_kernel_to_dynamic_supervisor(struct xregs_state *xstate, u64 mask); diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index ddc290d9bf8e15..892aec1dd82232 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -166,7 +166,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, } fpu_force_restore(fpu); - ret = copy_kernel_to_xstate(&fpu->state.xsave, kbuf ?: tmpbuf); + ret = copy_uabi_from_kernel_to_xstate(&fpu->state.xsave, kbuf ?: tmpbuf); out: vfree(tmpbuf); diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 430c66dc221862..fd4b58d7b72ee6 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -422,7 +422,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) if (use_xsave() && !fx_only) { u64 init_bv = xfeatures_mask_user() & ~user_xfeatures; - ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx); + ret = copy_sigframe_from_user_to_xstate(&fpu->state.xsave, buf_fx); if (ret) goto out; diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 4fca8a8edff8e4..57674f8c234236 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1099,7 +1099,7 @@ static inline bool mxcsr_valid(struct xstate_header *hdr, const u32 *mxcsr) * 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(). */ -int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) +int copy_uabi_from_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) { unsigned int offset, size; int i; @@ -1154,7 +1154,8 @@ int copy_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_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) +int copy_sigframe_from_user_to_xstate(struct xregs_state *xsave, + const void __user *ubuf) { unsigned int offset, size; int i; From 522e92743b35351bda1b6a9136560f833a9c2490 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:58 +0200 Subject: [PATCH 39/74] x86/fpu: Deduplicate copy_uabi_from_user/kernel_to_xstate() copy_uabi_from_user_to_xstate() and copy_uabi_from_kernel_to_xstate() are almost identical except for the copy function. Unify them. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Acked-by: Andy Lutomirski Link: https://lkml.kernel.org/r/20210623121454.414215896@linutronix.de --- arch/x86/kernel/fpu/xstate.c | 137 ++++++++++++----------------------- 1 file changed, 47 insertions(+), 90 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 57674f8c234236..0eb42a1b11e1fa 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -953,23 +953,6 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, } #endif /* ! CONFIG_ARCH_HAS_PKEYS */ -/* - * Weird legacy quirk: SSE and YMM states store information in the - * MXCSR and MXCSR_FLAGS fields of the FP area. That means if the FP - * area is marked as unused in the xfeatures header, we need to copy - * MXCSR and MXCSR_FLAGS if either SSE or YMM are in use. - */ -static inline bool xfeatures_mxcsr_quirk(u64 xfeatures) -{ - if (!(xfeatures & (XFEATURE_MASK_SSE|XFEATURE_MASK_YMM))) - return false; - - if (xfeatures & XFEATURE_MASK_FP) - return false; - - return true; -} - static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, void *init_xstate, unsigned int size) { @@ -1082,39 +1065,53 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct xregs_state *xsave, membuf_zero(&to, to.left); } -static inline bool mxcsr_valid(struct xstate_header *hdr, const u32 *mxcsr) +static int copy_from_buffer(void *dst, unsigned int offset, unsigned int size, + const void *kbuf, const void __user *ubuf) { - u64 mask = XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM; - - /* Only check if it is in use */ - if (hdr->xfeatures & mask) { - /* Reserved bits in MXCSR must be zero. */ - if (*mxcsr & ~mxcsr_feature_mask) - return false; + if (kbuf) { + memcpy(dst, kbuf + offset, size); + } else { + if (copy_from_user(dst, ubuf + offset, size)) + return -EFAULT; } - return true; + return 0; } -/* - * 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(). - */ -int copy_uabi_from_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) + +static int copy_uabi_to_xstate(struct xregs_state *xsave, const void *kbuf, + const void __user *ubuf) { unsigned int offset, size; - int i; struct xstate_header hdr; + u64 mask; + int i; offset = offsetof(struct xregs_state, header); - size = sizeof(hdr); - - memcpy(&hdr, kbuf + offset, size); + if (copy_from_buffer(&hdr, offset, sizeof(hdr), kbuf, ubuf)) + return -EFAULT; if (validate_user_xstate_header(&hdr)) return -EINVAL; - if (!mxcsr_valid(&hdr, kbuf + offsetof(struct fxregs_state, mxcsr))) - return -EINVAL; + /* Validate MXCSR when any of the related features is in use */ + mask = XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM; + if (hdr.xfeatures & mask) { + u32 mxcsr[2]; + + offset = offsetof(struct fxregs_state, mxcsr); + if (copy_from_buffer(mxcsr, offset, sizeof(mxcsr), kbuf, ubuf)) + return -EFAULT; + + /* Reserved bits in MXCSR must be zero. */ + if (mxcsr[0] & ~mxcsr_feature_mask) + return -EINVAL; + + /* SSE and YMM require MXCSR even when FP is not in use. */ + if (!(hdr.xfeatures & XFEATURE_MASK_FP)) { + xsave->i387.mxcsr = mxcsr[0]; + xsave->i387.mxcsr_mask = mxcsr[1]; + } + } for (i = 0; i < XFEATURE_MAX; i++) { u64 mask = ((u64)1 << i); @@ -1125,16 +1122,11 @@ int copy_uabi_from_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) offset = xstate_offsets[i]; size = xstate_sizes[i]; - memcpy(dst, kbuf + offset, size); + if (copy_from_buffer(dst, offset, size, kbuf, ubuf)) + return -EFAULT; } } - if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { - offset = offsetof(struct fxregs_state, mxcsr); - size = MXCSR_AND_FLAGS_SIZE; - memcpy(&xsave->i387.mxcsr, kbuf + offset, size); - } - /* * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures': @@ -1149,6 +1141,16 @@ int copy_uabi_from_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) return 0; } +/* + * 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(). + */ +int copy_uabi_from_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) +{ + return copy_uabi_to_xstate(xsave, kbuf, NULL); +} + /* * Convert from a sigreturn standard-format user-space buffer to kernel * XSAVE[S] format and copy to the target thread. This is called from the @@ -1157,52 +1159,7 @@ 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) { - unsigned int offset, size; - int i; - struct xstate_header hdr; - - offset = offsetof(struct xregs_state, header); - size = sizeof(hdr); - - if (copy_from_user(&hdr, ubuf + offset, size)) - return -EFAULT; - - if (validate_user_xstate_header(&hdr)) - return -EINVAL; - - for (i = 0; i < XFEATURE_MAX; i++) { - u64 mask = ((u64)1 << i); - - if (hdr.xfeatures & mask) { - void *dst = __raw_xsave_addr(xsave, i); - - offset = xstate_offsets[i]; - size = xstate_sizes[i]; - - if (copy_from_user(dst, ubuf + offset, size)) - return -EFAULT; - } - } - - if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { - offset = offsetof(struct fxregs_state, mxcsr); - size = MXCSR_AND_FLAGS_SIZE; - if (copy_from_user(&xsave->i387.mxcsr, ubuf + offset, size)) - return -EFAULT; - } - - /* - * The state that came in from userspace was user-state only. - * Mask all the user states out of 'xfeatures': - */ - xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR_ALL; - - /* - * Add back in the features that came in from userspace: - */ - xsave->header.xfeatures |= hdr.xfeatures; - - return 0; + return copy_uabi_to_xstate(xsave, NULL, ubuf); } /** From ebe7234b08a42d69bae94c4062a84777ea26ef99 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:01:59 +0200 Subject: [PATCH 40/74] x86/fpu: Rename copy_fpregs_to_fpstate() to save_fpregs_to_fpstate() A copy is guaranteed to leave the source intact, which is not the case when FNSAVE is used as that reinitilizes the registers. Save does not make such guarantees and it matches what this is about, i.e. to save the state for a later restore. Rename it to save_fpregs_to_fpstate(). Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121454.508853062@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 4 ++-- arch/x86/kernel/fpu/core.c | 10 +++++----- arch/x86/kvm/x86.c | 2 +- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index cd88233f10574a..559dd3018fd420 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -375,7 +375,7 @@ static inline int os_xrstor_safe(struct xregs_state *xstate, u64 mask) return err; } -extern int copy_fpregs_to_fpstate(struct fpu *fpu); +extern int save_fpregs_to_fpstate(struct fpu *fpu); static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask) { @@ -507,7 +507,7 @@ static inline void __fpregs_load_activate(void) static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { if (static_cpu_has(X86_FEATURE_FPU) && !(current->flags & PF_KTHREAD)) { - if (!copy_fpregs_to_fpstate(old_fpu)) + if (!save_fpregs_to_fpstate(old_fpu)) old_fpu->last_cpu = -1; else old_fpu->last_cpu = cpu; diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 1d2587607a7f8c..dcf4d6b581809e 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -92,7 +92,7 @@ EXPORT_SYMBOL(irq_fpu_usable); * Modern FPU state can be kept in registers, if there are * no pending FP exceptions. */ -int copy_fpregs_to_fpstate(struct fpu *fpu) +int save_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { os_xsave(&fpu->state.xsave); @@ -119,7 +119,7 @@ int copy_fpregs_to_fpstate(struct fpu *fpu) return 0; } -EXPORT_SYMBOL(copy_fpregs_to_fpstate); +EXPORT_SYMBOL(save_fpregs_to_fpstate); void kernel_fpu_begin_mask(unsigned int kfpu_mask) { @@ -137,7 +137,7 @@ void kernel_fpu_begin_mask(unsigned int kfpu_mask) * Ignore return value -- we don't care if reg state * is clobbered. */ - copy_fpregs_to_fpstate(¤t->thread.fpu); + save_fpregs_to_fpstate(¤t->thread.fpu); } __cpu_invalidate_fpregs_state(); @@ -172,7 +172,7 @@ void fpu__save(struct fpu *fpu) trace_x86_fpu_before_save(fpu); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) { - if (!copy_fpregs_to_fpstate(fpu)) { + if (!save_fpregs_to_fpstate(fpu)) { copy_kernel_to_fpregs(&fpu->state); } } @@ -255,7 +255,7 @@ int fpu__copy(struct task_struct *dst, struct task_struct *src) if (test_thread_flag(TIF_NEED_FPU_LOAD)) memcpy(&dst_fpu->state, &src_fpu->state, fpu_kernel_xstate_size); - else if (!copy_fpregs_to_fpstate(dst_fpu)) + else if (!save_fpregs_to_fpstate(dst_fpu)) copy_kernel_to_fpregs(&dst_fpu->state); fpregs_unlock(); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c25bf240eb269c..71bacb73c115fe 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9637,7 +9637,7 @@ static void kvm_save_current_fpu(struct fpu *fpu) memcpy(&fpu->state, ¤t->thread.fpu.state, fpu_kernel_xstate_size); else - copy_fpregs_to_fpstate(fpu); + save_fpregs_to_fpstate(fpu); } /* Swap (qemu) user FPU context for the guest FPU context. */ From 08ded2cd18a09749e67a14426aa7fd1b04ab1dc0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:00 +0200 Subject: [PATCH 41/74] x86/fpu: Get rid of the FNSAVE optimization The FNSAVE support requires conditionals in quite some call paths because FNSAVE reinitializes the FPU hardware. If the save has to preserve the FPU register state then the caller has to conditionally restore it from memory when FNSAVE is in use. This also requires a conditional in context switch because the restore avoidance optimization cannot work with FNSAVE. As this only affects 20+ years old CPUs there is really no reason to keep this optimization effective for FNSAVE. It's about time to not optimize for antiques anymore. Just unconditionally FRSTOR the save content to the registers and clean up the conditionals all over the place. Suggested-by: Dave Hansen Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121454.617369268@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 18 ++++++---- arch/x86/kernel/fpu/core.c | 54 ++++++++++++----------------- 2 files changed, 34 insertions(+), 38 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 559dd3018fd420..3e0eedaacdac82 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -83,6 +83,7 @@ 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); #define user_insn(insn, output, input...) \ ({ \ @@ -375,8 +376,6 @@ static inline int os_xrstor_safe(struct xregs_state *xstate, u64 mask) return err; } -extern int save_fpregs_to_fpstate(struct fpu *fpu); - static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask) { if (use_xsave()) { @@ -507,12 +506,17 @@ static inline void __fpregs_load_activate(void) static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { if (static_cpu_has(X86_FEATURE_FPU) && !(current->flags & PF_KTHREAD)) { - if (!save_fpregs_to_fpstate(old_fpu)) - old_fpu->last_cpu = -1; - else - old_fpu->last_cpu = cpu; + 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; - /* But leave fpu_fpregs_owner_ctx! */ trace_x86_fpu_regs_deactivated(old_fpu); } } diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index dcf4d6b581809e..c290ba27ffef2e 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -83,16 +83,20 @@ bool irq_fpu_usable(void) EXPORT_SYMBOL(irq_fpu_usable); /* - * These must be called with preempt disabled. Returns - * 'true' if the FPU state is still intact and we can - * keep registers active. + * Save the FPU register state in fpu->state. The register state is + * preserved. * - * The legacy FNSAVE instruction cleared all FPU state - * unconditionally, so registers are essentially destroyed. - * Modern FPU state can be kept in registers, if there are - * no pending FP exceptions. + * Must be called with fpregs_lock() held. + * + * The legacy FNSAVE instruction clears all FPU state unconditionally, so + * register state has to be reloaded. That might be a pointless exercise + * when the FPU is going to be used by another task right after that. But + * this only affects 20+ years old 32bit systems and avoids conditionals all + * over the place. + * + * FXSAVE and all XSAVE variants preserve the FPU register state. */ -int save_fpregs_to_fpstate(struct fpu *fpu) +void save_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { os_xsave(&fpu->state.xsave); @@ -103,21 +107,20 @@ int save_fpregs_to_fpstate(struct fpu *fpu) */ if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512) fpu->avx512_timestamp = jiffies; - return 1; + return; } if (likely(use_fxsr())) { fxsave(&fpu->state.fxsave); - return 1; + return; } /* * Legacy FPU register saving, FNSAVE always clears FPU registers, - * so we have to mark them inactive: + * so we have to reload them from the memory state. */ asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave)); - - return 0; + frstor(&fpu->state.fsave); } EXPORT_SYMBOL(save_fpregs_to_fpstate); @@ -133,10 +136,6 @@ void kernel_fpu_begin_mask(unsigned int kfpu_mask) if (!(current->flags & PF_KTHREAD) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); - /* - * Ignore return value -- we don't care if reg state - * is clobbered. - */ save_fpregs_to_fpstate(¤t->thread.fpu); } __cpu_invalidate_fpregs_state(); @@ -171,11 +170,8 @@ void fpu__save(struct fpu *fpu) fpregs_lock(); trace_x86_fpu_before_save(fpu); - if (!test_thread_flag(TIF_NEED_FPU_LOAD)) { - if (!save_fpregs_to_fpstate(fpu)) { - copy_kernel_to_fpregs(&fpu->state); - } - } + if (!test_thread_flag(TIF_NEED_FPU_LOAD)) + save_fpregs_to_fpstate(fpu); trace_x86_fpu_after_save(fpu); fpregs_unlock(); @@ -244,20 +240,16 @@ int fpu__copy(struct task_struct *dst, struct task_struct *src) memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size); /* - * If the FPU registers are not current just memcpy() the state. - * Otherwise save current FPU registers directly into the child's FPU - * context, without any memory-to-memory copying. - * - * ( The function 'fails' in the FNSAVE case, which destroys - * register contents so we have to load them back. ) + * 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. */ fpregs_lock(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) memcpy(&dst_fpu->state, &src_fpu->state, fpu_kernel_xstate_size); - else if (!save_fpregs_to_fpstate(dst_fpu)) - copy_kernel_to_fpregs(&dst_fpu->state); - + else + save_fpregs_to_fpstate(dst_fpu); fpregs_unlock(); set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD); From 1c61fada304c125c3f8a2b8eb1896406e4098a05 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:01 +0200 Subject: [PATCH 42/74] x86/fpu: Rename copy_kernel_to_fpregs() to restore_fpregs_from_fpstate() This is not a copy functionality. It restores the register state from the supplied kernel buffer. No functional changes. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121454.716058365@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 8 ++++---- arch/x86/kvm/x86.c | 4 ++-- arch/x86/mm/extable.c | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 3e0eedaacdac82..3558cd05c62f64 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -376,7 +376,7 @@ static inline int os_xrstor_safe(struct xregs_state *xstate, u64 mask) return err; } -static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask) +static inline void __restore_fpregs_from_fpstate(union fpregs_state *fpstate, u64 mask) { if (use_xsave()) { os_xrstor(&fpstate->xsave, mask); @@ -388,7 +388,7 @@ static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask } } -static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate) +static inline void restore_fpregs_from_fpstate(union fpregs_state *fpstate) { /* * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is @@ -403,7 +403,7 @@ static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate) : : [addr] "m" (fpstate)); } - __copy_kernel_to_fpregs(fpstate, -1); + __restore_fpregs_from_fpstate(fpstate, -1); } extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); @@ -474,7 +474,7 @@ static inline void __fpregs_load_activate(void) return; if (!fpregs_state_valid(fpu, cpu)) { - copy_kernel_to_fpregs(&fpu->state); + restore_fpregs_from_fpstate(&fpu->state); fpregs_activate(fpu); fpu->last_cpu = cpu; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 71bacb73c115fe..6f651b9d774c79 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9653,7 +9653,7 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) */ if (vcpu->arch.guest_fpu) /* PKRU is separately restored in kvm_x86_ops.run. */ - __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state, + __restore_fpregs_from_fpstate(&vcpu->arch.guest_fpu->state, ~XFEATURE_MASK_PKRU); fpregs_mark_activate(); @@ -9674,7 +9674,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) if (vcpu->arch.guest_fpu) kvm_save_current_fpu(vcpu->arch.guest_fpu); - copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state); + restore_fpregs_from_fpstate(&vcpu->arch.user_fpu->state); fpregs_mark_activate(); fpregs_unlock(); diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 121921b2927cb8..2c5cccd77b8b97 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -65,7 +65,7 @@ __visible bool ex_handler_fprestore(const struct exception_table_entry *fixup, WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", (void *)instruction_pointer(regs)); - __copy_kernel_to_fpregs(&init_fpstate, -1); + __restore_fpregs_from_fpstate(&init_fpstate, -1); return true; } EXPORT_SYMBOL_GPL(ex_handler_fprestore); From b76411b1b568311bfd89d03acc587ffc1548c26f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:02 +0200 Subject: [PATCH 43/74] x86/fpu: Rename initstate copy functions Again this not a copy. It's restoring register state from kernel memory. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121454.816581630@linutronix.de --- arch/x86/kernel/fpu/core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index c290ba27ffef2e..4a59e0fbcfd851 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -303,7 +303,7 @@ void fpu__drop(struct fpu *fpu) * Clear FPU registers by setting them up from the init fpstate. * Caller must do fpregs_[un]lock() around it. */ -static inline void copy_init_fpstate_to_fpregs(u64 features_mask) +static inline void restore_fpregs_from_init_fpstate(u64 features_mask) { if (use_xsave()) os_xrstor(&init_fpstate.xsave, features_mask); @@ -338,9 +338,9 @@ static void fpu__clear(struct fpu *fpu, bool user_only) if (!fpregs_state_valid(fpu, smp_processor_id()) && xfeatures_mask_supervisor()) os_xrstor(&fpu->state.xsave, xfeatures_mask_supervisor()); - copy_init_fpstate_to_fpregs(xfeatures_mask_user()); + restore_fpregs_from_init_fpstate(xfeatures_mask_user()); } else { - copy_init_fpstate_to_fpregs(xfeatures_mask_all); + restore_fpregs_from_init_fpstate(xfeatures_mask_all); } fpregs_mark_activate(); From 01707b66535872f7a0d87f66078fd018d1814be0 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 23 Jun 2021 14:02:03 +0200 Subject: [PATCH 44/74] x86/fpu: Rename "dynamic" XSTATEs to "independent" The salient feature of "dynamic" XSTATEs is that they are not part of the main task XSTATE buffer. The fact that they are dynamically allocated is irrelevant and will become quite confusing when user math XSTATEs start being dynamically allocated. Rename them to "independent" because they are independent of the main XSTATE code. This is just a search-and-replace with some whitespace updates to keep things aligned. Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/1eecb0e4f3e07828ebe5d737ec77dc3b708fad2d.1623388344.git.luto@kernel.org Link: https://lkml.kernel.org/r/20210623121454.911450390@linutronix.de --- arch/x86/events/intel/lbr.c | 6 +-- arch/x86/include/asm/fpu/xstate.h | 22 +++++------ arch/x86/kernel/fpu/xstate.c | 62 +++++++++++++++---------------- 3 files changed, 45 insertions(+), 45 deletions(-) diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 4409d2cccfda57..2fa2df3d4e9bdd 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -491,7 +491,7 @@ static void intel_pmu_arch_lbr_xrstors(void *ctx) { struct x86_perf_task_context_arch_lbr_xsave *task_ctx = ctx; - copy_kernel_to_dynamic_supervisor(&task_ctx->xsave, XFEATURE_MASK_LBR); + copy_kernel_to_independent_supervisor(&task_ctx->xsave, XFEATURE_MASK_LBR); } static __always_inline bool lbr_is_reset_in_cstate(void *ctx) @@ -576,7 +576,7 @@ static void intel_pmu_arch_lbr_xsaves(void *ctx) { struct x86_perf_task_context_arch_lbr_xsave *task_ctx = ctx; - copy_dynamic_supervisor_to_kernel(&task_ctx->xsave, XFEATURE_MASK_LBR); + copy_independent_supervisor_to_kernel(&task_ctx->xsave, XFEATURE_MASK_LBR); } static void __intel_pmu_lbr_save(void *ctx) @@ -992,7 +992,7 @@ static void intel_pmu_arch_lbr_read_xsave(struct cpu_hw_events *cpuc) intel_pmu_store_lbr(cpuc, NULL); return; } - copy_dynamic_supervisor_to_kernel(&xsave->xsave, XFEATURE_MASK_LBR); + copy_independent_supervisor_to_kernel(&xsave->xsave, XFEATURE_MASK_LBR); intel_pmu_store_lbr(cpuc, xsave->lbr.entries); } diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 00e1a2ac52395b..a55bd5cabb5900 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -42,21 +42,21 @@ * and its size may be huge. Saving/restoring such supervisor state components * at each context switch can cause high CPU and space overhead, which should * be avoided. Such supervisor state components should only be saved/restored - * on demand. The on-demand dynamic supervisor features are set in this mask. + * on demand. The on-demand supervisor features are set in this mask. * - * Unlike the existing supported supervisor features, a dynamic supervisor + * Unlike the existing supported supervisor features, an independent supervisor * feature does not allocate a buffer in task->fpu, and the corresponding * supervisor state component cannot be saved/restored at each context switch. * - * To support a dynamic supervisor feature, a developer should follow the + * To support an independent supervisor feature, a developer should follow the * dos and don'ts as below: * - Do dynamically allocate a buffer for the supervisor state component. * - Do manually invoke the XSAVES/XRSTORS instruction to save/restore the * state component to/from the buffer. - * - Don't set the bit corresponding to the dynamic supervisor feature in + * - Don't set the bit corresponding to the independent supervisor feature in * IA32_XSS at run time, since it has been set at boot time. */ -#define XFEATURE_MASK_DYNAMIC (XFEATURE_MASK_LBR) +#define XFEATURE_MASK_INDEPENDENT (XFEATURE_MASK_LBR) /* * Unsupported supervisor features. When a supervisor feature in this mask is @@ -66,7 +66,7 @@ /* All supervisor states including supported and unsupported states. */ #define XFEATURE_MASK_SUPERVISOR_ALL (XFEATURE_MASK_SUPERVISOR_SUPPORTED | \ - XFEATURE_MASK_DYNAMIC | \ + XFEATURE_MASK_INDEPENDENT | \ XFEATURE_MASK_SUPERVISOR_UNSUPPORTED) #ifdef CONFIG_X86_64 @@ -87,12 +87,12 @@ static inline u64 xfeatures_mask_user(void) return xfeatures_mask_all & XFEATURE_MASK_USER_SUPPORTED; } -static inline u64 xfeatures_mask_dynamic(void) +static inline u64 xfeatures_mask_independent(void) { if (!boot_cpu_has(X86_FEATURE_ARCH_LBR)) - return XFEATURE_MASK_DYNAMIC & ~XFEATURE_MASK_LBR; + return XFEATURE_MASK_INDEPENDENT & ~XFEATURE_MASK_LBR; - return XFEATURE_MASK_DYNAMIC; + return XFEATURE_MASK_INDEPENDENT; } extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; @@ -104,8 +104,8 @@ 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 copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask); -void copy_kernel_to_dynamic_supervisor(struct xregs_state *xstate, u64 mask); +void copy_independent_supervisor_to_kernel(struct xregs_state *xstate, u64 mask); +void copy_kernel_to_independent_supervisor(struct xregs_state *xstate, u64 mask); enum xstate_copy_mode { XSTATE_COPY_FP, diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 0eb42a1b11e1fa..27246a83ecb999 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -151,7 +151,7 @@ void fpu__init_cpu_xstate(void) */ if (boot_cpu_has(X86_FEATURE_XSAVES)) { wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | - xfeatures_mask_dynamic()); + xfeatures_mask_independent()); } } @@ -551,7 +551,7 @@ static void check_xstate_against_struct(int nr) * how large the XSAVE buffer needs to be. We are recalculating * it to be safe. * - * Dynamic XSAVE features allocate their own buffers and are not + * Independent XSAVE features allocate their own buffers and are not * covered by these checks. Only the size of the buffer for task->fpu * is checked here. */ @@ -617,18 +617,18 @@ static unsigned int __init get_xsaves_size(void) } /* - * Get the total size of the enabled xstates without the dynamic supervisor + * Get the total size of the enabled xstates without the independent supervisor * features. */ -static unsigned int __init get_xsaves_size_no_dynamic(void) +static unsigned int __init get_xsaves_size_no_independent(void) { - u64 mask = xfeatures_mask_dynamic(); + u64 mask = xfeatures_mask_independent(); unsigned int size; if (!mask) return get_xsaves_size(); - /* Disable dynamic features. */ + /* Disable independent features. */ wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()); /* @@ -637,7 +637,7 @@ static unsigned int __init get_xsaves_size_no_dynamic(void) */ size = get_xsaves_size(); - /* Re-enable dynamic features so XSAVES will work on them again. */ + /* Re-enable independent features so XSAVES will work on them again. */ wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask); return size; @@ -680,7 +680,7 @@ static int __init init_xstate_size(void) xsave_size = get_xsave_size(); if (boot_cpu_has(X86_FEATURE_XSAVES)) - possible_xstate_size = get_xsaves_size_no_dynamic(); + possible_xstate_size = get_xsaves_size_no_independent(); else possible_xstate_size = xsave_size; @@ -837,7 +837,7 @@ void fpu__resume_cpu(void) */ if (boot_cpu_has(X86_FEATURE_XSAVES)) { wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | - xfeatures_mask_dynamic()); + xfeatures_mask_independent()); } } @@ -1163,34 +1163,34 @@ int copy_sigframe_from_user_to_xstate(struct xregs_state *xsave, } /** - * copy_dynamic_supervisor_to_kernel() - Save dynamic supervisor states to - * an xsave area + * copy_independent_supervisor_to_kernel() - Save independent supervisor states to + * an xsave area * @xstate: A pointer to an xsave area - * @mask: Represent the dynamic supervisor features saved into the xsave area + * @mask: Represent the independent supervisor features saved into the xsave area * - * Only the dynamic supervisor states sets in the mask are saved into the xsave - * area (See the comment in XFEATURE_MASK_DYNAMIC for the details of dynamic - * supervisor feature). Besides the dynamic supervisor states, the legacy + * Only the independent supervisor states sets in the mask are saved into the xsave + * area (See the comment in XFEATURE_MASK_INDEPENDENT for the details of independent + * supervisor feature). Besides the independent supervisor states, the legacy * region and XSAVE header are also saved into the xsave area. The supervisor * features in the XFEATURE_MASK_SUPERVISOR_SUPPORTED and * XFEATURE_MASK_SUPERVISOR_UNSUPPORTED are not saved. * * The xsave area must be 64-bytes aligned. */ -void copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask) +void copy_independent_supervisor_to_kernel(struct xregs_state *xstate, u64 mask) { - u64 dynamic_mask = xfeatures_mask_dynamic() & mask; + u64 independent_mask = xfeatures_mask_independent() & mask; u32 lmask, hmask; int err; if (WARN_ON_FPU(!boot_cpu_has(X86_FEATURE_XSAVES))) return; - if (WARN_ON_FPU(!dynamic_mask)) + if (WARN_ON_FPU(!independent_mask)) return; - lmask = dynamic_mask; - hmask = dynamic_mask >> 32; + lmask = independent_mask; + hmask = independent_mask >> 32; XSTATE_OP(XSAVES, xstate, lmask, hmask, err); @@ -1199,34 +1199,34 @@ void copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask) } /** - * copy_kernel_to_dynamic_supervisor() - Restore dynamic supervisor states from - * an xsave area + * copy_kernel_to_independent_supervisor() - Restore independent supervisor states from + * an xsave area * @xstate: A pointer to an xsave area - * @mask: Represent the dynamic supervisor features restored from the xsave area + * @mask: Represent the independent supervisor features restored from the xsave area * - * Only the dynamic supervisor states sets in the mask are restored from the - * xsave area (See the comment in XFEATURE_MASK_DYNAMIC for the details of - * dynamic supervisor feature). Besides the dynamic supervisor states, the + * Only the independent supervisor states sets in the mask are restored from the + * xsave area (See the comment in XFEATURE_MASK_INDEPENDENT for the details of + * independent supervisor feature). Besides the independent supervisor states, the * legacy region and XSAVE header are also restored from the xsave area. The * supervisor features in the XFEATURE_MASK_SUPERVISOR_SUPPORTED and * XFEATURE_MASK_SUPERVISOR_UNSUPPORTED are not restored. * * The xsave area must be 64-bytes aligned. */ -void copy_kernel_to_dynamic_supervisor(struct xregs_state *xstate, u64 mask) +void copy_kernel_to_independent_supervisor(struct xregs_state *xstate, u64 mask) { - u64 dynamic_mask = xfeatures_mask_dynamic() & mask; + u64 independent_mask = xfeatures_mask_independent() & mask; u32 lmask, hmask; int err; if (WARN_ON_FPU(!boot_cpu_has(X86_FEATURE_XSAVES))) return; - if (WARN_ON_FPU(!dynamic_mask)) + if (WARN_ON_FPU(!independent_mask)) return; - lmask = dynamic_mask; - hmask = dynamic_mask >> 32; + lmask = independent_mask; + hmask = independent_mask >> 32; XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); From a75c52896b6d42d6600db4d4dd9f7e4bde9218db Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:04 +0200 Subject: [PATCH 45/74] x86/fpu/xstate: Sanitize handling of independent features The copy functions for the independent features are horribly named and the supervisor and independent part is just overengineered. The point is that the supplied mask has either to be a subset of the independent features or a subset of the task->fpu.xstate managed features. Rewrite it so it checks for invalid overlaps of these areas in the caller supplied feature mask. Rename it so it follows the new naming convention for these operations. Mop up the function documentation. This allows to use that function for other purposes as well. Suggested-by: Peter Zijlstra Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Tested-by: Kan Liang Link: https://lkml.kernel.org/r/20210623121455.004880675@linutronix.de --- arch/x86/events/intel/lbr.c | 6 +- arch/x86/include/asm/fpu/xstate.h | 5 +- arch/x86/kernel/fpu/xstate.c | 98 +++++++++++++++---------------- 3 files changed, 54 insertions(+), 55 deletions(-) diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 2fa2df3d4e9bdd..f338645071c895 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -491,7 +491,7 @@ static void intel_pmu_arch_lbr_xrstors(void *ctx) { struct x86_perf_task_context_arch_lbr_xsave *task_ctx = ctx; - copy_kernel_to_independent_supervisor(&task_ctx->xsave, XFEATURE_MASK_LBR); + xrstors(&task_ctx->xsave, XFEATURE_MASK_LBR); } static __always_inline bool lbr_is_reset_in_cstate(void *ctx) @@ -576,7 +576,7 @@ static void intel_pmu_arch_lbr_xsaves(void *ctx) { struct x86_perf_task_context_arch_lbr_xsave *task_ctx = ctx; - copy_independent_supervisor_to_kernel(&task_ctx->xsave, XFEATURE_MASK_LBR); + xsaves(&task_ctx->xsave, XFEATURE_MASK_LBR); } static void __intel_pmu_lbr_save(void *ctx) @@ -992,7 +992,7 @@ static void intel_pmu_arch_lbr_read_xsave(struct cpu_hw_events *cpuc) intel_pmu_store_lbr(cpuc, NULL); return; } - copy_independent_supervisor_to_kernel(&xsave->xsave, XFEATURE_MASK_LBR); + xsaves(&xsave->xsave, XFEATURE_MASK_LBR); intel_pmu_store_lbr(cpuc, xsave->lbr.entries); } diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index a55bd5cabb5900..7de2384628e2a9 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -104,8 +104,9 @@ 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 copy_independent_supervisor_to_kernel(struct xregs_state *xstate, u64 mask); -void copy_kernel_to_independent_supervisor(struct xregs_state *xstate, u64 mask); + +void xsaves(struct xregs_state *xsave, u64 mask); +void xrstors(struct xregs_state *xsave, u64 mask); enum xstate_copy_mode { XSTATE_COPY_FP, diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 27246a83ecb999..735d44c3efb6f4 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1162,76 +1162,74 @@ int copy_sigframe_from_user_to_xstate(struct xregs_state *xsave, return copy_uabi_to_xstate(xsave, NULL, ubuf); } +static bool validate_xsaves_xrstors(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; + + if (WARN_ON_ONCE(!mask || mask & xchk)) + return false; + + return true; +} + /** - * copy_independent_supervisor_to_kernel() - Save independent supervisor states to - * an xsave area - * @xstate: A pointer to an xsave area - * @mask: Represent the independent supervisor features saved into the xsave area + * xsaves - Save selected components to a kernel xstate buffer + * @xstate: Pointer to the buffer + * @mask: Feature mask to select the components to save * - * Only the independent supervisor states sets in the mask are saved into the xsave - * area (See the comment in XFEATURE_MASK_INDEPENDENT for the details of independent - * supervisor feature). Besides the independent supervisor states, the legacy - * region and XSAVE header are also saved into the xsave area. The supervisor - * features in the XFEATURE_MASK_SUPERVISOR_SUPPORTED and - * XFEATURE_MASK_SUPERVISOR_UNSUPPORTED are not saved. + * The @xstate buffer must be 64 byte aligned and correctly initialized as + * XSAVES does not write the full xstate header. Before first use the + * buffer should be zeroed otherwise a consecutive XRSTORS from that buffer + * can #GP. * - * The xsave area must be 64-bytes aligned. + * The feature mask must either be a subset of the independent features or + * a subset of the task->fpstate related features. */ -void copy_independent_supervisor_to_kernel(struct xregs_state *xstate, u64 mask) +void xsaves(struct xregs_state *xstate, u64 mask) { - u64 independent_mask = xfeatures_mask_independent() & mask; - u32 lmask, hmask; int err; - if (WARN_ON_FPU(!boot_cpu_has(X86_FEATURE_XSAVES))) + if (!validate_xsaves_xrstors(mask)) return; - if (WARN_ON_FPU(!independent_mask)) - return; - - lmask = independent_mask; - hmask = independent_mask >> 32; - - XSTATE_OP(XSAVES, xstate, lmask, hmask, err); - - /* Should never fault when copying to a kernel buffer */ - WARN_ON_FPU(err); + XSTATE_OP(XSAVES, xstate, (u32)mask, (u32)(mask >> 32), err); + WARN_ON_ONCE(err); } /** - * copy_kernel_to_independent_supervisor() - Restore independent supervisor states from - * an xsave area - * @xstate: A pointer to an xsave area - * @mask: Represent the independent supervisor features restored from the xsave area + * xrstors - Restore selected components from a kernel xstate buffer + * @xstate: Pointer to the buffer + * @mask: Feature mask to select the components to restore + * + * The @xstate buffer must be 64 byte aligned and correctly initialized + * otherwise XRSTORS from that buffer can #GP. * - * Only the independent supervisor states sets in the mask are restored from the - * xsave area (See the comment in XFEATURE_MASK_INDEPENDENT for the details of - * independent supervisor feature). Besides the independent supervisor states, the - * legacy region and XSAVE header are also restored from the xsave area. The - * supervisor features in the XFEATURE_MASK_SUPERVISOR_SUPPORTED and - * XFEATURE_MASK_SUPERVISOR_UNSUPPORTED are not restored. + * Proper usage is to restore the state which was saved with + * xsaves() into @xstate. * - * The xsave area must be 64-bytes aligned. + * The feature mask must either be a subset of the independent features or + * a subset of the task->fpstate related features. */ -void copy_kernel_to_independent_supervisor(struct xregs_state *xstate, u64 mask) +void xrstors(struct xregs_state *xstate, u64 mask) { - u64 independent_mask = xfeatures_mask_independent() & mask; - u32 lmask, hmask; int err; - if (WARN_ON_FPU(!boot_cpu_has(X86_FEATURE_XSAVES))) + if (!validate_xsaves_xrstors(mask)) return; - if (WARN_ON_FPU(!independent_mask)) - return; - - lmask = independent_mask; - hmask = independent_mask >> 32; - - XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); - - /* Should never fault when copying from a kernel buffer */ - WARN_ON_FPU(err); + XSTATE_OP(XRSTORS, xstate, (u32)mask, (u32)(mask >> 32), err); + WARN_ON_ONCE(err); } #ifdef CONFIG_PROC_PID_ARCH_STATUS From 784a46618f634973a17535b7d3d03cd4ebc0ccbd Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Wed, 23 Jun 2021 14:02:05 +0200 Subject: [PATCH 46/74] x86/pkeys: Move read_pkru() and write_pkru() write_pkru() was originally used just to write to the PKRU register. It was mercifully short and sweet and was not out of place in pgtable.h with some other pkey-related code. But, later work included a requirement to also modify the task XSAVE buffer when updating the register. This really is more related to the XSAVE architecture than to paging. Move the read/write_pkru() to asm/pkru.h. pgtable.h won't miss them. Signed-off-by: Dave Hansen Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121455.102647114@linutronix.de --- arch/x86/include/asm/fpu/xstate.h | 1 + arch/x86/include/asm/pgtable.h | 57 +---------------------------- arch/x86/include/asm/pkru.h | 61 +++++++++++++++++++++++++++++++ arch/x86/kernel/process_64.c | 1 + arch/x86/kvm/svm/sev.c | 1 + arch/x86/kvm/x86.c | 1 + arch/x86/mm/pkeys.c | 1 + 7 files changed, 67 insertions(+), 56 deletions(-) create mode 100644 arch/x86/include/asm/pkru.h diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 7de2384628e2a9..5764cbe390148a 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -6,6 +6,7 @@ #include #include +#include #include /* Bit 63 of XCR0 is reserved for future expansion */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index b1099f2d9800c7..ec0d8e106646b0 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -23,7 +23,7 @@ #ifndef __ASSEMBLY__ #include -#include +#include #include #include @@ -126,35 +126,6 @@ static inline int pte_dirty(pte_t pte) return pte_flags(pte) & _PAGE_DIRTY; } - -static inline u32 read_pkru(void) -{ - if (boot_cpu_has(X86_FEATURE_OSPKE)) - return rdpkru(); - return 0; -} - -static inline void write_pkru(u32 pkru) -{ - struct pkru_state *pk; - - if (!boot_cpu_has(X86_FEATURE_OSPKE)) - return; - - pk = get_xsave_addr(¤t->thread.fpu.state.xsave, XFEATURE_PKRU); - - /* - * The PKRU value in xstate needs to be in sync with the value that is - * written to the CPU. The FPU restore on return to userland would - * otherwise load the previous value again. - */ - fpregs_lock(); - if (pk) - pk->pkru = pkru; - __write_pkru(pkru); - fpregs_unlock(); -} - static inline int pte_young(pte_t pte) { return pte_flags(pte) & _PAGE_ACCESSED; @@ -1360,32 +1331,6 @@ static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd) } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ -#define PKRU_AD_BIT 0x1 -#define PKRU_WD_BIT 0x2 -#define PKRU_BITS_PER_PKEY 2 - -#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS -extern u32 init_pkru_value; -#else -#define init_pkru_value 0 -#endif - -static inline bool __pkru_allows_read(u32 pkru, u16 pkey) -{ - int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; - return !(pkru & (PKRU_AD_BIT << pkru_pkey_bits)); -} - -static inline bool __pkru_allows_write(u32 pkru, u16 pkey) -{ - int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; - /* - * Access-disable disables writes too so we need to check - * both bits here. - */ - return !(pkru & ((PKRU_AD_BIT|PKRU_WD_BIT) << pkru_pkey_bits)); -} - static inline u16 pte_flags_pkey(unsigned long pte_flags) { #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS diff --git a/arch/x86/include/asm/pkru.h b/arch/x86/include/asm/pkru.h new file mode 100644 index 00000000000000..35ffcfd6e4037f --- /dev/null +++ b/arch/x86/include/asm/pkru.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PKRU_H +#define _ASM_X86_PKRU_H + +#include + +#define PKRU_AD_BIT 0x1 +#define PKRU_WD_BIT 0x2 +#define PKRU_BITS_PER_PKEY 2 + +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS +extern u32 init_pkru_value; +#else +#define init_pkru_value 0 +#endif + +static inline bool __pkru_allows_read(u32 pkru, u16 pkey) +{ + int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; + return !(pkru & (PKRU_AD_BIT << pkru_pkey_bits)); +} + +static inline bool __pkru_allows_write(u32 pkru, u16 pkey) +{ + int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; + /* + * Access-disable disables writes too so we need to check + * both bits here. + */ + return !(pkru & ((PKRU_AD_BIT|PKRU_WD_BIT) << pkru_pkey_bits)); +} + +static inline u32 read_pkru(void) +{ + if (boot_cpu_has(X86_FEATURE_OSPKE)) + return rdpkru(); + return 0; +} + +static inline void write_pkru(u32 pkru) +{ + struct pkru_state *pk; + + if (!boot_cpu_has(X86_FEATURE_OSPKE)) + return; + + pk = get_xsave_addr(¤t->thread.fpu.state.xsave, XFEATURE_PKRU); + + /* + * The PKRU value in xstate needs to be in sync with the value that is + * written to the CPU. The FPU restore on return to userland would + * otherwise load the previous value again. + */ + fpregs_lock(); + if (pk) + pk->pkru = pkru; + __write_pkru(pkru); + fpregs_unlock(); +} + +#endif diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index d08307df69ad5a..4651ab08e6e15a 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -41,6 +41,7 @@ #include #include +#include #include #include #include diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 8d36f0c7307187..62926f1a5f7ba4 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -19,6 +19,7 @@ #include #include +#include #include #include "x86.h" diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6f651b9d774c79..07f788872ddf21 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -65,6 +65,7 @@ #include #include #include +#include #include #include /* Ugh! */ #include diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index a840ac78b6de46..a02cfcf02d0d80 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -10,6 +10,7 @@ #include /* boot_cpu_has, ... */ #include /* vma_pkey() */ +#include /* read/write_pkru() */ int __execute_only_pkey(struct mm_struct *mm) { From b2681e791dbcee6acb1dca7a5076a0285109ac4c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:06 +0200 Subject: [PATCH 47/74] x86/fpu: Rename and sanitize fpu__save/copy() Both function names are a misnomer. fpu__save() is actually about synchronizing the hardware register state into the task's memory state so that either coredump or a math exception handler can inspect the state at the time where the problem happens. The function guarantees to preserve the register state, while "save" is a common terminology for saving the current state so it can be modified and restored later. This is clearly not the case here. Rename it to fpu_sync_fpstate(). fpu__copy() is used to clone the current task's FPU state when duplicating task_struct. While the register state is a copy the rest of the FPU state is not. Name it accordingly and remove the really pointless @src argument along with the warning which comes along with it. Nothing can ever copy the FPU state of a non-current task. It's clearly just a consequence of arch_dup_task_struct(), but it makes no sense to proliferate that further. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121455.196727450@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 6 ++++-- arch/x86/kernel/fpu/core.c | 17 ++++++++--------- arch/x86/kernel/fpu/regset.c | 2 +- arch/x86/kernel/process.c | 3 +-- arch/x86/kernel/traps.c | 5 +++-- 5 files changed, 17 insertions(+), 16 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 3558cd05c62f64..f5da2e9b87da6b 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -26,14 +26,16 @@ /* * High level FPU state handling functions: */ -extern void fpu__save(struct fpu *fpu); extern int fpu__restore_sig(void __user *buf, int ia32_frame); extern void fpu__drop(struct fpu *fpu); -extern int fpu__copy(struct task_struct *dst, struct task_struct *src); extern void fpu__clear_user_states(struct fpu *fpu); extern void fpu__clear_all(struct fpu *fpu); extern int fpu__exception_code(struct fpu *fpu, int trap_nr); +extern void fpu_sync_fpstate(struct fpu *fpu); + +extern int fpu_clone(struct task_struct *dst); + /* * Boot time FPU initialization functions: */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 4a59e0fbcfd851..8762b1a8966a5e 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -159,11 +159,10 @@ void kernel_fpu_end(void) EXPORT_SYMBOL_GPL(kernel_fpu_end); /* - * Save the FPU state (mark it for reload if necessary): - * - * This only ever gets called for the current task. + * Sync the FPU register state to current's memory register state when the + * current task owns the FPU. The hardware register state is preserved. */ -void fpu__save(struct fpu *fpu) +void fpu_sync_fpstate(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); @@ -221,18 +220,18 @@ void fpstate_init(union fpregs_state *state) } EXPORT_SYMBOL_GPL(fpstate_init); -int fpu__copy(struct task_struct *dst, struct task_struct *src) +/* Clone current's FPU state on fork */ +int fpu_clone(struct task_struct *dst) { + struct fpu *src_fpu = ¤t->thread.fpu; struct fpu *dst_fpu = &dst->thread.fpu; - struct fpu *src_fpu = &src->thread.fpu; + /* The new task's FPU state cannot be valid in the hardware. */ dst_fpu->last_cpu = -1; - if (!static_cpu_has(X86_FEATURE_FPU)) + if (!cpu_feature_enabled(X86_FEATURE_FPU)) return 0; - WARN_ON_FPU(src_fpu != ¤t->thread.fpu); - /* * Don't let 'init optimized' areas of the XSAVE area * leak into the child task: diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 892aec1dd82232..4575796d547baa 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -41,7 +41,7 @@ int regset_xregset_fpregs_active(struct task_struct *target, const struct user_r static void sync_fpstate(struct fpu *fpu) { if (fpu == ¤t->thread.fpu) - fpu__save(fpu); + fpu_sync_fpstate(fpu); } /* diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 5e1f38179f4957..af3db530983baa 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -87,8 +87,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) #ifdef CONFIG_VM86 dst->thread.vm86 = NULL; #endif - - return fpu__copy(dst, src); + return fpu_clone(dst); } /* diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 853ea7a8080611..4c9c4aa8321681 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -1046,9 +1046,10 @@ static void math_error(struct pt_regs *regs, int trapnr) } /* - * Save the info for the exception handler and clear the error. + * Synchronize the FPU register state to the memory register state + * if necessary. This allows the exception handler to inspect it. */ - fpu__save(fpu); + fpu_sync_fpstate(fpu); task->thread.trap_nr = trapnr; task->thread.error_code = 0; From 8a1dc55a3f3ef0a723c3c117a567e7b5dd2c1793 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:07 +0200 Subject: [PATCH 48/74] x86/cpu: Sanitize X86_FEATURE_OSPKE X86_FEATURE_OSPKE is enabled first on the boot CPU and the feature flag is set. Secondary CPUs have to enable CR4.PKE as well and set their per CPU feature flag. That's ineffective because all call sites have checks for boot_cpu_data. Make it smarter and force the feature flag when PKU is enabled on the boot cpu which allows then to use cpu_feature_enabled(X86_FEATURE_OSPKE) all over the place. That either compiles the code out when PKEY support is disabled in Kconfig or uses a static_cpu_has() for the feature check which makes a significant difference in hotpaths, e.g. context switch. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121455.305113644@linutronix.de --- arch/x86/include/asm/pkeys.h | 8 ++++---- arch/x86/include/asm/pkru.h | 4 ++-- arch/x86/kernel/cpu/common.c | 24 +++++++++++------------- arch/x86/kernel/fpu/core.c | 2 +- arch/x86/kernel/fpu/xstate.c | 2 +- arch/x86/kernel/process_64.c | 2 +- arch/x86/mm/fault.c | 2 +- 7 files changed, 21 insertions(+), 23 deletions(-) diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 2ff9b98812b763..4128f647c7552c 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -9,14 +9,14 @@ * will be necessary to ensure that the types that store key * numbers and masks have sufficient capacity. */ -#define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1) +#define arch_max_pkey() (cpu_feature_enabled(X86_FEATURE_OSPKE) ? 16 : 1) extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); static inline bool arch_pkeys_enabled(void) { - return boot_cpu_has(X86_FEATURE_OSPKE); + return cpu_feature_enabled(X86_FEATURE_OSPKE); } /* @@ -26,7 +26,7 @@ static inline bool arch_pkeys_enabled(void) extern int __execute_only_pkey(struct mm_struct *mm); static inline int execute_only_pkey(struct mm_struct *mm) { - if (!boot_cpu_has(X86_FEATURE_OSPKE)) + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return ARCH_DEFAULT_PKEY; return __execute_only_pkey(mm); @@ -37,7 +37,7 @@ extern int __arch_override_mprotect_pkey(struct vm_area_struct *vma, static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey) { - if (!boot_cpu_has(X86_FEATURE_OSPKE)) + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return 0; return __arch_override_mprotect_pkey(vma, prot, pkey); diff --git a/arch/x86/include/asm/pkru.h b/arch/x86/include/asm/pkru.h index 35ffcfd6e4037f..ec8dd2878dc997 100644 --- a/arch/x86/include/asm/pkru.h +++ b/arch/x86/include/asm/pkru.h @@ -32,7 +32,7 @@ static inline bool __pkru_allows_write(u32 pkru, u16 pkey) static inline u32 read_pkru(void) { - if (boot_cpu_has(X86_FEATURE_OSPKE)) + if (cpu_feature_enabled(X86_FEATURE_OSPKE)) return rdpkru(); return 0; } @@ -41,7 +41,7 @@ static inline void write_pkru(u32 pkru) { struct pkru_state *pk; - if (!boot_cpu_has(X86_FEATURE_OSPKE)) + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; pk = get_xsave_addr(¤t->thread.fpu.state.xsave, XFEATURE_PKRU); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f875dea49d7e55..dbfb335ffac4e0 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -466,22 +466,20 @@ static bool pku_disabled; static __always_inline void setup_pku(struct cpuinfo_x86 *c) { - /* check the boot processor, plus compile options for PKU: */ - if (!cpu_feature_enabled(X86_FEATURE_PKU)) - return; - /* checks the actual processor's cpuid bits: */ - if (!cpu_has(c, X86_FEATURE_PKU)) - return; - if (pku_disabled) + if (c == &boot_cpu_data) { + if (pku_disabled || !cpu_feature_enabled(X86_FEATURE_PKU)) + return; + /* + * Setting CR4.PKE will cause the X86_FEATURE_OSPKE cpuid + * bit to be set. Enforce it. + */ + setup_force_cpu_cap(X86_FEATURE_OSPKE); + + } else if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) { return; + } cr4_set_bits(X86_CR4_PKE); - /* - * Setting X86_CR4_PKE will cause the X86_FEATURE_OSPKE - * cpuid bit to be set. We need to ensure that we - * update that bit in this CPU's "cpu_info". - */ - set_cpu_cap(c, X86_FEATURE_OSPKE); } #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 8762b1a8966a5e..3866954354a45d 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -311,7 +311,7 @@ static inline void restore_fpregs_from_init_fpstate(u64 features_mask) else frstor(&init_fpstate.fsave); - if (boot_cpu_has(X86_FEATURE_OSPKE)) + if (cpu_feature_enabled(X86_FEATURE_OSPKE)) copy_init_pkru_to_fpregs(); } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 735d44c3efb6f4..bc71609ba65a3b 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -921,7 +921,7 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, * This check implies XSAVE support. OSPKE only gets * set if we enable XSAVE and we enable PKU in XCR0. */ - if (!boot_cpu_has(X86_FEATURE_OSPKE)) + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return -EINVAL; /* diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 4651ab08e6e15a..40a963809203d1 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -137,7 +137,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, log_lvl, d3, d6, d7); } - if (boot_cpu_has(X86_FEATURE_OSPKE)) + if (cpu_feature_enabled(X86_FEATURE_OSPKE)) printk("%sPKRU: %08x\n", log_lvl, read_pkru()); } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 6bda7f67d737e9..f33a61a432ce4f 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -875,7 +875,7 @@ static inline bool bad_area_access_from_pkeys(unsigned long error_code, /* This code is always called on the current mm */ bool foreign = false; - if (!boot_cpu_has(X86_FEATURE_OSPKE)) + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return false; if (error_code & X86_PF_PK) return true; From 739e2eec0f4849eb411567407d61491f923db405 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:08 +0200 Subject: [PATCH 49/74] x86/pkru: Provide pkru_get_init_value() When CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS is disabled then the following code fails to compile: if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { u32 pkru = READ_ONCE(init_pkru_value); .. } because init_pkru_value is defined as '0' which makes READ_ONCE() upset. Provide an accessor macro to avoid #ifdeffery all over the place. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121455.404880646@linutronix.de --- arch/x86/include/asm/pkru.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/include/asm/pkru.h b/arch/x86/include/asm/pkru.h index ec8dd2878dc997..19d3d7b9846582 100644 --- a/arch/x86/include/asm/pkru.h +++ b/arch/x86/include/asm/pkru.h @@ -10,8 +10,10 @@ #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS extern u32 init_pkru_value; +#define pkru_get_init_value() READ_ONCE(init_pkru_value) #else #define init_pkru_value 0 +#define pkru_get_init_value() 0 #endif static inline bool __pkru_allows_read(u32 pkru, u16 pkey) From ff7ebff47c595e747aa1bb10d8a30b2acb7d425b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:09 +0200 Subject: [PATCH 50/74] x86/pkru: Provide pkru_write_default() Provide a simple and trivial helper which just writes the PKRU default value without trying to fiddle with the task's xsave buffer. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121455.513729794@linutronix.de --- arch/x86/include/asm/pkru.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/include/asm/pkru.h b/arch/x86/include/asm/pkru.h index 19d3d7b9846582..7e4550911c5134 100644 --- a/arch/x86/include/asm/pkru.h +++ b/arch/x86/include/asm/pkru.h @@ -60,4 +60,12 @@ static inline void write_pkru(u32 pkru) fpregs_unlock(); } +static inline void pkru_write_default(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) + return; + + wrpkru(pkru_get_init_value()); +} + #endif From fa8c84b77a54bf3cf351c8b4b26a5aca27a14013 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:10 +0200 Subject: [PATCH 51/74] x86/cpu: Write the default PKRU value when enabling PKE In preparation of making the PKRU management more independent from XSTATES, write the default PKRU value into the hardware right after enabling PKRU in CR4. This ensures that switch_to() and copy_thread() have the correct setting for init task and the per CPU idle threads right away. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121455.622983906@linutronix.de --- arch/x86/kernel/cpu/common.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index dbfb335ffac4e0..ca668efa4c81e2 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -480,6 +480,8 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c) } cr4_set_bits(X86_CR4_PKE); + /* Load the default PKRU value */ + pkru_write_default(); } #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS From 371071131cd1032c1e9172c51234a2a324841cab Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:11 +0200 Subject: [PATCH 52/74] x86/fpu: Use pkru_write_default() in copy_init_fpstate_to_fpregs() There is no point in using copy_init_pkru_to_fpregs() which in turn calls write_pkru(). write_pkru() tries to fiddle with the task's xstate buffer for nothing because the XRSTOR[S](init_fpstate) just cleared the xfeature flag in the xstate header which makes get_xsave_addr() fail. It's a useless exercise anyway because the reinitialization activates the FPU so before the task's xstate buffer can be used again a XRSTOR[S] must happen which in turn dumps the PKRU value. Get rid of the now unused copy_init_pkru_to_fpregs(). Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121455.732508792@linutronix.de --- arch/x86/include/asm/pkeys.h | 1 - arch/x86/kernel/fpu/core.c | 3 +-- arch/x86/mm/pkeys.c | 17 ----------------- include/linux/pkeys.h | 4 ---- 4 files changed, 1 insertion(+), 24 deletions(-) diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 4128f647c7552c..5c7bcaa7962323 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -124,7 +124,6 @@ extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); -extern void copy_init_pkru_to_fpregs(void); static inline int vma_pkey(struct vm_area_struct *vma) { diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 3866954354a45d..fedadcb04ba2f5 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -311,8 +311,7 @@ static inline void restore_fpregs_from_init_fpstate(u64 features_mask) else frstor(&init_fpstate.fsave); - if (cpu_feature_enabled(X86_FEATURE_OSPKE)) - copy_init_pkru_to_fpregs(); + pkru_write_default(); } /* diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index a02cfcf02d0d80..fb171a5d7f339d 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -10,7 +10,6 @@ #include /* boot_cpu_has, ... */ #include /* vma_pkey() */ -#include /* read/write_pkru() */ int __execute_only_pkey(struct mm_struct *mm) { @@ -125,22 +124,6 @@ u32 init_pkru_value = PKRU_AD_KEY( 1) | PKRU_AD_KEY( 2) | PKRU_AD_KEY( 3) | PKRU_AD_KEY(10) | PKRU_AD_KEY(11) | PKRU_AD_KEY(12) | PKRU_AD_KEY(13) | PKRU_AD_KEY(14) | PKRU_AD_KEY(15); -/* - * Called from the FPU code when creating a fresh set of FPU - * registers. This is called from a very specific context where - * we know the FPU registers are safe for use and we can use PKRU - * directly. - */ -void copy_init_pkru_to_fpregs(void) -{ - u32 init_pkru_value_snapshot = READ_ONCE(init_pkru_value); - /* - * Override the PKRU state that came from 'init_fpstate' - * with the baseline from the process. - */ - write_pkru(init_pkru_value_snapshot); -} - static ssize_t init_pkru_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index 2955ba97604892..6beb26b7151d21 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -44,10 +44,6 @@ static inline bool arch_pkeys_enabled(void) return false; } -static inline void copy_init_pkru_to_fpregs(void) -{ -} - #endif /* ! CONFIG_ARCH_HAS_PKEYS */ #endif /* _LINUX_PKEYS_H */ From e7ecad17c84d0f6bef635c20d02bbe4096eea700 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:12 +0200 Subject: [PATCH 53/74] x86/fpu: Rename fpu__clear_all() to fpu_flush_thread() Make it clear what the function is about. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121455.827979263@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 3 ++- arch/x86/kernel/fpu/core.c | 4 ++-- arch/x86/kernel/process.c | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index f5da2e9b87da6b..dabbb700c0ebd8 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -29,12 +29,13 @@ 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 void fpu__clear_all(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: diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index fedadcb04ba2f5..4b69be9bea5535 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -350,9 +350,9 @@ void fpu__clear_user_states(struct fpu *fpu) fpu__clear(fpu, true); } -void fpu__clear_all(struct fpu *fpu) +void fpu_flush_thread(void) { - fpu__clear(fpu, false); + fpu__clear(¤t->thread.fpu, false); } /* diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index af3db530983baa..19d05d39a81d8c 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -205,7 +205,7 @@ void flush_thread(void) flush_ptrace_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - fpu__clear_all(&tsk->thread.fpu); + fpu_flush_thread(); } void disable_TSC(void) From 33344368cb08f8d6bf55a32aa052318d3a69ea84 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 23 Jun 2021 14:02:13 +0200 Subject: [PATCH 54/74] x86/fpu: Clean up the fpu__clear() variants fpu__clear() currently resets both register state and kernel XSAVE buffer state. It has two modes: one for all state (supervisor and user) and another for user state only. fpu__clear_all() uses the "all state" (user_only=0) mode, while a number of signal paths use the user_only=1 mode. Make fpu__clear() work only for user state (user_only=1) and remove the "all state" (user_only=0) code. Rename it to match so it can be used by the signal paths. Replace the "all state" (user_only=0) fpu__clear() functionality. Use the TIF_NEED_FPU_LOAD functionality instead of making any actual hardware registers changes in this path. Instead of invoking fpu__initialize() just memcpy() init_fpstate into the task's FPU state because that has already the correct format and in case of PKRU also contains the default PKRU value. Move the actual PKRU write out into flush_thread() where it belongs and where it will end up anyway when PKRU and XSTATE have been untangled. For bisectability a workaround is required which stores the PKRU value in the xstate memory until PKRU is untangled from XSTATE for context switching and return to user. [ Dave Hansen: Polished changelog ] [ tglx: Fixed the PKRU fallout ] Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121455.922729522@linutronix.de --- arch/x86/kernel/fpu/core.c | 113 +++++++++++++++++++++++++------------ arch/x86/kernel/process.c | 10 ++++ 2 files changed, 86 insertions(+), 37 deletions(-) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 4b69be9bea5535..aa7e808b9d1e15 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -259,19 +259,6 @@ int fpu_clone(struct task_struct *dst) return 0; } -/* - * Activate the current task's in-memory FPU context, - * if it has not been used before: - */ -static void fpu__initialize(struct fpu *fpu) -{ - WARN_ON_FPU(fpu != ¤t->thread.fpu); - - set_thread_flag(TIF_NEED_FPU_LOAD); - fpstate_init(&fpu->state); - trace_x86_fpu_init_state(fpu); -} - /* * Drops current FPU state: deactivates the fpregs and * the fpstate. NOTE: it still leaves previous contents @@ -314,47 +301,99 @@ static inline void restore_fpregs_from_init_fpstate(u64 features_mask) 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); +} + +/* Temporary workaround. Will be removed once PKRU and XSTATE are untangled. */ +static inline void pkru_set_default_in_xstate(struct xregs_state *xsave) +{ + struct pkru_state *pk; + + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) + return; + /* + * Force XFEATURE_PKRU to be set in the header otherwise + * get_xsave_addr() does not work and it also needs to be set to + * make XRSTOR(S) load it. + */ + xsave->header.xfeatures |= XFEATURE_MASK_PKRU; + pk = get_xsave_addr(xsave, XFEATURE_PKRU); + pk->pkru = pkru_get_init_value(); +} + /* - * Clear the FPU state back to init state. - * - * Called by sys_execve(), by the signal handler code and by various - * error paths. + * Reset current->fpu memory state to the init values. + */ +static void fpu_reset_fpstate(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + + fpregs_lock(); + fpu__drop(fpu); + /* + * This does not change the actual hardware registers. It just + * resets the memory image and sets TIF_NEED_FPU_LOAD so a + * subsequent return to usermode will reload the registers from the + * task's memory image. + * + * Do not use fpstate_init() here. Just copy init_fpstate which has + * the correct content already except for PKRU. + */ + memcpy(&fpu->state, &init_fpstate, init_fpstate_copy_size()); + pkru_set_default_in_xstate(&fpu->state.xsave); + set_thread_flag(TIF_NEED_FPU_LOAD); + fpregs_unlock(); +} + +/* + * Reset current's user FPU states to the init states. current's + * supervisor states, if any, are not modified by this function. The + * caller guarantees that the XSTATE header in memory is intact. */ -static void fpu__clear(struct fpu *fpu, bool user_only) +void fpu__clear_user_states(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); - if (!static_cpu_has(X86_FEATURE_FPU)) { - fpu__drop(fpu); - fpu__initialize(fpu); + fpregs_lock(); + if (!cpu_feature_enabled(X86_FEATURE_FPU)) { + fpu_reset_fpstate(); + fpregs_unlock(); return; } - fpregs_lock(); - - if (user_only) { - if (!fpregs_state_valid(fpu, smp_processor_id()) && - xfeatures_mask_supervisor()) - os_xrstor(&fpu->state.xsave, xfeatures_mask_supervisor()); - restore_fpregs_from_init_fpstate(xfeatures_mask_user()); - } else { - restore_fpregs_from_init_fpstate(xfeatures_mask_all); + /* + * Ensure that current's supervisor states are loaded into their + * corresponding registers. + */ + if (xfeatures_mask_supervisor() && + !fpregs_state_valid(fpu, smp_processor_id())) { + os_xrstor(&fpu->state.xsave, xfeatures_mask_supervisor()); } + /* Reset user states in registers. */ + restore_fpregs_from_init_fpstate(xfeatures_mask_user()); + + /* + * Now all FPU registers have their desired values. Inform the FPU + * state machine that current's FPU registers are in the hardware + * registers. The memory image does not need to be updated because + * any operation relying on it has to save the registers first when + * current's FPU is marked active. + */ fpregs_mark_activate(); fpregs_unlock(); } -void fpu__clear_user_states(struct fpu *fpu) -{ - fpu__clear(fpu, true); -} - void fpu_flush_thread(void) { - fpu__clear(¤t->thread.fpu, false); + fpu_reset_fpstate(); } - /* * Load FPU context before returning to userspace. */ diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 19d05d39a81d8c..de942b0388155f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -198,6 +198,15 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, return ret; } +static void pkru_flush_thread(void) +{ + /* + * If PKRU is enabled the default PKRU value has to be loaded into + * the hardware right here (similar to context switch). + */ + pkru_write_default(); +} + void flush_thread(void) { struct task_struct *tsk = current; @@ -206,6 +215,7 @@ void flush_thread(void) memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); fpu_flush_thread(); + pkru_flush_thread(); } void disable_TSC(void) From 727d01100e15b18c67f05fb697779ad2a6c99b63 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:14 +0200 Subject: [PATCH 55/74] x86/fpu: Rename __fpregs_load_activate() to fpregs_restore_userregs() Rename it so that it becomes entirely clear what this function is about. It's purpose is to restore the FPU registers to the state which was saved in the task's FPU memory state either at context switch or by an in kernel FPU user. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121456.018867925@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 6 ++---- arch/x86/kernel/fpu/core.c | 2 +- arch/x86/kernel/fpu/signal.c | 2 +- 3 files changed, 4 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index dabbb700c0ebd8..f7688f6e86bcee 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -465,10 +465,8 @@ static inline void fpregs_activate(struct fpu *fpu) trace_x86_fpu_regs_activated(fpu); } -/* - * Internal helper, do not use directly. Use switch_fpu_return() instead. - */ -static inline void __fpregs_load_activate(void) +/* Internal helper for switch_fpu_return() and signal frame setup */ +static inline void fpregs_restore_userregs(void) { struct fpu *fpu = ¤t->thread.fpu; int cpu = smp_processor_id(); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index aa7e808b9d1e15..6babf187638982 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -402,7 +402,7 @@ void switch_fpu_return(void) if (!static_cpu_has(X86_FEATURE_FPU)) return; - __fpregs_load_activate(); + fpregs_restore_userregs(); } EXPORT_SYMBOL_GPL(switch_fpu_return); diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index fd4b58d7b72ee6..b12665c38a3026 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -188,7 +188,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) */ fpregs_lock(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) - __fpregs_load_activate(); + fpregs_restore_userregs(); pagefault_disable(); ret = copy_fpregs_to_sigframe(buf_fx); From 1d9bffab116fadfe1594f5fea2b50ab280d81d30 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:15 +0200 Subject: [PATCH 56/74] x86/fpu: Move FXSAVE_LEAK quirk info __copy_kernel_to_fpregs() copy_kernel_to_fpregs() restores all xfeatures but it is also the place where the AMD FXSAVE_LEAK bug is handled. That prevents fpregs_restore_userregs() to limit the restored features, which is required to untangle PKRU and XSTATE handling and also for the upcoming supervisor state management. Move the FXSAVE_LEAK quirk into __copy_kernel_to_fpregs() and deinline that function which has become rather fat. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121456.114271278@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 25 +------------------------ arch/x86/kernel/fpu/core.c | 27 +++++++++++++++++++++++++++ 2 files changed, 28 insertions(+), 24 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index f7688f6e86bcee..63d979656437c9 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -379,33 +379,10 @@ static inline int os_xrstor_safe(struct xregs_state *xstate, u64 mask) return err; } -static inline void __restore_fpregs_from_fpstate(union fpregs_state *fpstate, u64 mask) -{ - if (use_xsave()) { - os_xrstor(&fpstate->xsave, mask); - } else { - if (use_fxsr()) - fxrstor(&fpstate->fxsave); - else - frstor(&fpstate->fsave); - } -} +extern void __restore_fpregs_from_fpstate(union fpregs_state *fpstate, u64 mask); static inline void restore_fpregs_from_fpstate(union fpregs_state *fpstate) { - /* - * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is - * pending. Clear the x87 state here by setting it to fixed values. - * "m" is a random variable that should be in L1. - */ - if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) { - asm volatile( - "fnclex\n\t" - "emms\n\t" - "fildl %P[addr]" /* set F?P to defined value */ - : : [addr] "m" (fpstate)); - } - __restore_fpregs_from_fpstate(fpstate, -1); } diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 6babf187638982..afd0deee8cfdd0 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -124,6 +124,33 @@ void save_fpregs_to_fpstate(struct fpu *fpu) } EXPORT_SYMBOL(save_fpregs_to_fpstate); +void __restore_fpregs_from_fpstate(union fpregs_state *fpstate, u64 mask) +{ + /* + * AMD K7/K8 and later CPUs up to Zen don't save/restore + * FDP/FIP/FOP unless an exception is pending. Clear the x87 state + * here by setting it to fixed values. "m" is a random variable + * that should be in L1. + */ + if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) { + asm volatile( + "fnclex\n\t" + "emms\n\t" + "fildl %P[addr]" /* set F?P to defined value */ + : : [addr] "m" (fpstate)); + } + + if (use_xsave()) { + os_xrstor(&fpstate->xsave, mask); + } else { + if (use_fxsr()) + fxrstor(&fpstate->fxsave); + else + frstor(&fpstate->fsave); + } +} +EXPORT_SYMBOL_GPL(__restore_fpregs_from_fpstate); + void kernel_fpu_begin_mask(unsigned int kfpu_mask) { preempt_disable(); From 65e952102122bf89f0e4f1bebf8664e32587aaed Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:16 +0200 Subject: [PATCH 57/74] x86/fpu: Rename xfeatures_mask_user() to xfeatures_mask_uabi() Rename it so it's clear that this is about user ABI features which can differ from the feature set which the kernel saves and restores because the kernel handles e.g. PKRU differently. But the user ABI (ptrace, signal frame) expects it to be there. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121456.211585137@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 7 ++++++- arch/x86/include/asm/fpu/xstate.h | 6 +++++- arch/x86/kernel/fpu/core.c | 2 +- arch/x86/kernel/fpu/signal.c | 10 +++++----- arch/x86/kernel/fpu/xstate.c | 18 +++++++++--------- 5 files changed, 26 insertions(+), 17 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 63d979656437c9..bcfb6365a76bd9 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -324,7 +324,12 @@ static inline void os_xrstor(struct xregs_state *xstate, u64 mask) */ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf) { - u64 mask = xfeatures_mask_user(); + /* + * 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; diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 5764cbe390148a..af9ea134bf5e6a 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -83,7 +83,11 @@ static inline u64 xfeatures_mask_supervisor(void) return xfeatures_mask_all & XFEATURE_MASK_SUPERVISOR_SUPPORTED; } -static inline u64 xfeatures_mask_user(void) +/* + * The xfeatures which are enabled in XCR0 and expected to be in ptrace + * buffers and signal frames. + */ +static inline u64 xfeatures_mask_uabi(void) { return xfeatures_mask_all & XFEATURE_MASK_USER_SUPPORTED; } diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index afd0deee8cfdd0..12437383ff79fb 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -404,7 +404,7 @@ void fpu__clear_user_states(struct fpu *fpu) } /* Reset user states in registers. */ - restore_fpregs_from_init_fpstate(xfeatures_mask_user()); + restore_fpregs_from_init_fpstate(xfeatures_mask_uabi()); /* * Now all FPU registers have their desired values. Inform the FPU diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index b12665c38a3026..a42bc9d0b1cc57 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -257,14 +257,14 @@ static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only) if (use_xsave()) { if (fx_only) { - init_bv = xfeatures_mask_user() & ~XFEATURE_MASK_FPSSE; + init_bv = xfeatures_mask_uabi() & ~XFEATURE_MASK_FPSSE; r = fxrstor_from_user_sigframe(buf); if (!r) os_xrstor(&init_fpstate.xsave, init_bv); return r; } else { - init_bv = xfeatures_mask_user() & ~xbv; + init_bv = xfeatures_mask_uabi() & ~xbv; r = xrstor_from_user_sigframe(buf, xbv); if (!r && unlikely(init_bv)) @@ -420,7 +420,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) fpregs_unlock(); if (use_xsave() && !fx_only) { - u64 init_bv = xfeatures_mask_user() & ~user_xfeatures; + u64 init_bv = xfeatures_mask_uabi() & ~user_xfeatures; ret = copy_sigframe_from_user_to_xstate(&fpu->state.xsave, buf_fx); if (ret) @@ -454,7 +454,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) if (use_xsave()) { u64 init_bv; - init_bv = xfeatures_mask_user() & ~XFEATURE_MASK_FPSSE; + init_bv = xfeatures_mask_uabi() & ~XFEATURE_MASK_FPSSE; os_xrstor(&init_fpstate.xsave, init_bv); } @@ -549,7 +549,7 @@ void fpu__init_prepare_fx_sw_frame(void) fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; fx_sw_reserved.extended_size = size; - fx_sw_reserved.xfeatures = xfeatures_mask_user(); + fx_sw_reserved.xfeatures = xfeatures_mask_uabi(); fx_sw_reserved.xstate_size = fpu_user_xstate_size; if (IS_ENABLED(CONFIG_IA32_EMULATION) || diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index bc71609ba65a3b..c513596f8ec912 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -144,7 +144,7 @@ void fpu__init_cpu_xstate(void) * managed by XSAVE{C, OPT, S} and XRSTOR{S}. Only XSAVE user * states can be set here. */ - xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user()); + xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_uabi()); /* * MSR_IA32_XSS sets supervisor states managed by XSAVES. @@ -453,7 +453,7 @@ int xfeature_size(int xfeature_nr) static int validate_user_xstate_header(const struct xstate_header *hdr) { /* No unknown or supervisor features may be set */ - if (hdr->xfeatures & ~xfeatures_mask_user()) + if (hdr->xfeatures & ~xfeatures_mask_uabi()) return -EINVAL; /* Userspace must use the uncompacted format */ @@ -756,7 +756,7 @@ void __init fpu__init_system_xstate(void) cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); xfeatures_mask_all |= ecx + ((u64)edx << 32); - if ((xfeatures_mask_user() & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { + if ((xfeatures_mask_uabi() & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { /* * This indicates that something really unexpected happened * with the enumeration. Disable XSAVE and try to continue @@ -791,7 +791,7 @@ void __init fpu__init_system_xstate(void) * Update info used for ptrace frames; use standard-format size and no * supervisor xstates: */ - update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask_user()); + update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask_uabi()); fpu__init_prepare_fx_sw_frame(); setup_init_fpu_buf(); @@ -828,14 +828,14 @@ void fpu__resume_cpu(void) /* * Restore XCR0 on xsave capable CPUs: */ - if (boot_cpu_has(X86_FEATURE_XSAVE)) - xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user()); + if (cpu_feature_enabled(X86_FEATURE_XSAVE)) + xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_uabi()); /* * Restore IA32_XSS. The same CPUID bit enumerates support * of XSAVES and MSR_IA32_XSS. */ - if (boot_cpu_has(X86_FEATURE_XSAVES)) { + if (cpu_feature_enabled(X86_FEATURE_XSAVES)) { wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | xfeatures_mask_independent()); } @@ -993,7 +993,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct xregs_state *xsave, break; case XSTATE_COPY_XSAVE: - header.xfeatures &= xfeatures_mask_user(); + header.xfeatures &= xfeatures_mask_uabi(); break; } @@ -1038,7 +1038,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct xregs_state *xsave, * compacted init_fpstate. The gap tracking will zero this * later. */ - if (!(xfeatures_mask_user() & BIT_ULL(i))) + if (!(xfeatures_mask_uabi() & BIT_ULL(i))) continue; /* From 2ebe81c6d800576e1213f9d7cf0068017ae610c1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:17 +0200 Subject: [PATCH 58/74] x86/fpu: Dont restore PKRU in fpregs_restore_userspace() switch_to() and flush_thread() write the task's PKRU value eagerly so the PKRU value of current is always valid in the hardware. That means there is no point in restoring PKRU on exit to user or when reactivating the task's FPU registers in the signal frame setup path. This allows to remove all the xstate buffer updates with PKRU values once the PKRU state is stored in thread struct while a task is scheduled out. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121456.303919033@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 16 +++++++++++++++- arch/x86/include/asm/fpu/xstate.h | 19 +++++++++++++++++++ arch/x86/kernel/fpu/core.c | 2 +- 3 files changed, 35 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index bcfb6365a76bd9..521774320e6aa3 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -457,7 +457,21 @@ static inline void fpregs_restore_userregs(void) return; if (!fpregs_state_valid(fpu, cpu)) { - restore_fpregs_from_fpstate(&fpu->state); + 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; } diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index af9ea134bf5e6a..6a0aaafb93eca1 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -35,6 +35,14 @@ XFEATURE_MASK_BNDREGS | \ XFEATURE_MASK_BNDCSR) +/* + * Features which are restored when returning to user space. + * PKRU is not restored on return to user space because PKRU + * is switched eagerly in switch_to() and flush_thread() + */ +#define XFEATURE_MASK_USER_RESTORE \ + (XFEATURE_MASK_USER_SUPPORTED & ~XFEATURE_MASK_PKRU) + /* All currently supported supervisor features */ #define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID) @@ -92,6 +100,17 @@ 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; +} + static inline u64 xfeatures_mask_independent(void) { if (!boot_cpu_has(X86_FEATURE_ARCH_LBR)) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 12437383ff79fb..470576ced90799 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -404,7 +404,7 @@ void fpu__clear_user_states(struct fpu *fpu) } /* Reset user states in registers. */ - restore_fpregs_from_init_fpstate(xfeatures_mask_uabi()); + restore_fpregs_from_init_fpstate(xfeatures_mask_restore_user()); /* * Now all FPU registers have their desired values. Inform the FPU From 9782a712eb971ce483442076e79eb1d8d608646e Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Wed, 23 Jun 2021 14:02:18 +0200 Subject: [PATCH 59/74] x86/fpu: Add PKRU storage outside of task XSAVE buffer PKRU is currently partly XSAVE-managed and partly not. It has space in the task XSAVE buffer and is context-switched by XSAVE/XRSTOR. However, it is switched more eagerly than FPU because there may be a need for PKRU to be up-to-date for things like copy_to/from_user() since PKRU affects user-permission memory accesses, not just accesses from userspace itself. This leaves PKRU in a very odd position. XSAVE brings very little value to the table for how Linux uses PKRU except for signal related XSTATE handling. Prepare to move PKRU away from being XSAVE-managed. Allocate space in the thread_struct for it and save/restore it in the context-switch path separately from the XSAVE-managed features. task->thread_struct.pkru is only valid when the task is scheduled out. For the current task the authoritative source is the hardware, i.e. it has to be retrieved via rdpkru(). Leave the XSAVE code in place for now to ensure bisectability. Signed-off-by: Dave Hansen Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121456.399107624@linutronix.de --- arch/x86/include/asm/processor.h | 9 +++++++++ arch/x86/kernel/process.c | 7 +++++++ arch/x86/kernel/process_64.c | 25 +++++++++++++++++++++++++ 3 files changed, 41 insertions(+) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 556b2b17c3e2f7..91946fc3c006ec 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -518,6 +518,15 @@ struct thread_struct { unsigned int sig_on_uaccess_err:1; + /* + * Protection Keys Register for Userspace. Loaded immediately on + * context switch. Store it in thread_struct to avoid a lookup in + * the tasks's FPU xstate buffer. This value is only valid when a + * task is scheduled out. For 'current' the authoritative source of + * PKRU is the hardware itself. + */ + u32 pkru; + /* Floating point and extended processor state */ struct fpu fpu; /* diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index de942b0388155f..fa6c8fa0f77884 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -156,11 +156,18 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, /* Kernel thread ? */ if (unlikely(p->flags & PF_KTHREAD)) { + p->thread.pkru = pkru_get_init_value(); memset(childregs, 0, sizeof(struct pt_regs)); kthread_frame_init(frame, sp, arg); return 0; } + /* + * Clone current's PKRU value from hardware. tsk->thread.pkru + * is only valid when scheduled out. + */ + p->thread.pkru = read_pkru(); + frame->bx = 0; *childregs = *current_pt_regs(); childregs->ax = 0; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 40a963809203d1..ec0d836a13b12f 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -340,6 +340,29 @@ static __always_inline void load_seg_legacy(unsigned short prev_index, } } +/* + * Store prev's PKRU value and load next's PKRU value if they differ. PKRU + * is not XSTATE managed on context switch because that would require a + * lookup in the task's FPU xsave buffer and require to keep that updated + * in various places. + */ +static __always_inline void x86_pkru_load(struct thread_struct *prev, + struct thread_struct *next) +{ + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) + return; + + /* Stash the prev task's value: */ + prev->pkru = rdpkru(); + + /* + * PKRU writes are slightly expensive. Avoid them when not + * strictly necessary: + */ + if (prev->pkru != next->pkru) + wrpkru(next->pkru); +} + static __always_inline void x86_fsgsbase_load(struct thread_struct *prev, struct thread_struct *next) { @@ -589,6 +612,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) x86_fsgsbase_load(prev, next); + x86_pkru_load(prev, next); + /* * Switch the PDA and FPU contexts. */ From e84ba47e313dbc097bf859bb6e4f9219883d5f78 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Wed, 23 Jun 2021 14:02:19 +0200 Subject: [PATCH 60/74] x86/fpu: Hook up PKRU into ptrace() One nice thing about having PKRU be XSAVE-managed is that it gets naturally exposed into the XSAVE-using ABIs. Now that XSAVE will not be used to manage PKRU, these ABIs need to be manually enabled to deal with PKRU. ptrace() uses copy_uabi_xstate_to_kernel() to collect the tracee's XSTATE. As PKRU is not in the task's XSTATE buffer, use task->thread.pkru for filling in up the ptrace buffer. Signed-off-by: Dave Hansen Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121456.508770763@linutronix.de --- arch/x86/include/asm/fpu/xstate.h | 2 +- arch/x86/kernel/fpu/regset.c | 10 ++++------ arch/x86/kernel/fpu/xstate.c | 25 ++++++++++++++++++------- 3 files changed, 23 insertions(+), 14 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 6a0aaafb93eca1..4ff4a0093a4818 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -139,7 +139,7 @@ enum xstate_copy_mode { }; struct membuf; -void copy_xstate_to_uabi_buf(struct membuf to, struct xregs_state *xsave, +void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode mode); #endif diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 4575796d547baa..66ed317ebc0d34 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -78,7 +78,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, sizeof(fpu->state.fxsave)); } - copy_xstate_to_uabi_buf(to, &fpu->state.xsave, XSTATE_COPY_FX); + copy_xstate_to_uabi_buf(to, target, XSTATE_COPY_FX); return 0; } @@ -126,14 +126,12 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, int xstateregs_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { - struct fpu *fpu = &target->thread.fpu; - if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) return -ENODEV; - sync_fpstate(fpu); + sync_fpstate(&target->thread.fpu); - copy_xstate_to_uabi_buf(to, &fpu->state.xsave, XSTATE_COPY_XSAVE); + copy_xstate_to_uabi_buf(to, target, XSTATE_COPY_XSAVE); return 0; } @@ -336,7 +334,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, struct membuf mb = { .p = &fxsave, .left = sizeof(fxsave) }; /* Handle init state optimized xstate correctly */ - copy_xstate_to_uabi_buf(mb, &fpu->state.xsave, XSTATE_COPY_FP); + copy_xstate_to_uabi_buf(mb, target, XSTATE_COPY_FP); fx = &fxsave; } else { fx = &fpu->state.fxsave; diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index c513596f8ec912..9fd124a001b06f 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -962,7 +962,7 @@ 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 * @to: membuf descriptor - * @xsave: The kernel xstate buffer to copy from + * @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 @@ -971,10 +971,11 @@ 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 xregs_state *xsave, +void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, 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 xstate_header header; unsigned int zerofrom; @@ -1048,11 +1049,21 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct xregs_state *xsave, if (zerofrom < xstate_offsets[i]) membuf_zero(&to, xstate_offsets[i] - zerofrom); - copy_feature(header.xfeatures & BIT_ULL(i), &to, - __raw_xsave_addr(xsave, i), - __raw_xsave_addr(xinit, i), - xstate_sizes[i]); - + if (i == XFEATURE_PKRU) { + 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. + */ + pkru.pkru = tsk->thread.pkru; + membuf_write(&to, &pkru, sizeof(pkru)); + } else { + copy_feature(header.xfeatures & BIT_ULL(i), &to, + __raw_xsave_addr(xsave, i), + __raw_xsave_addr(xinit, i), + xstate_sizes[i]); + } /* * Keep track of the last copied state in the non-compacted * target buffer for gap zeroing. From 30a304a138738d71a09c730ca8044e9662de0dbf Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:20 +0200 Subject: [PATCH 61/74] x86/fpu: Mask PKRU from kernel XRSTOR[S] operations As the PKRU state is managed separately restoring it from the xstate buffer would be counterproductive as it might either restore a stale value or reinit the PKRU state to 0. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121456.606745195@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 4 ++-- arch/x86/include/asm/fpu/xstate.h | 10 ++++++++++ arch/x86/kernel/fpu/xstate.c | 1 + arch/x86/mm/extable.c | 2 +- 4 files changed, 14 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 521774320e6aa3..2a484f5f2413a7 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -259,7 +259,7 @@ static inline void fxsave(struct fxregs_state *fx) */ static inline void os_xrstor_booting(struct xregs_state *xstate) { - u64 mask = -1; + u64 mask = xfeatures_mask_fpstate(); u32 lmask = mask; u32 hmask = mask >> 32; int err; @@ -388,7 +388,7 @@ 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, -1); + __restore_fpregs_from_fpstate(fpstate, xfeatures_mask_fpstate()); } extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 4ff4a0093a4818..109dfcc75299d9 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -111,6 +111,16 @@ 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)) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 9fd124a001b06f..21a10a66c4e450 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -60,6 +60,7 @@ static short xsave_cpuid_features[] __initdata = { * 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}; diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 2c5cccd77b8b97..e1664e9f969c30 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -65,7 +65,7 @@ __visible bool ex_handler_fprestore(const struct exception_table_entry *fixup, WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", (void *)instruction_pointer(regs)); - __restore_fpregs_from_fpstate(&init_fpstate, -1); + __restore_fpregs_from_fpstate(&init_fpstate, xfeatures_mask_fpstate()); return true; } EXPORT_SYMBOL_GPL(ex_handler_fprestore); From 954436989cc550dd91aab98363240c9c0a4b7e23 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:21 +0200 Subject: [PATCH 62/74] x86/fpu: Remove PKRU handling from switch_fpu_finish() PKRU is already updated and the xstate is not longer the proper source of information. [ bp: Use cpu_feature_enabled() ] Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121456.708180184@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 34 ++++------------------------- 1 file changed, 4 insertions(+), 30 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 2a484f5f2413a7..528a86826f953c 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -523,39 +523,13 @@ static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) */ /* - * Load PKRU from the FPU context if available. Delay loading of the - * complete FPU state until the return to userland. + * 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) { - u32 pkru_val = init_pkru_value; - struct pkru_state *pk; - - if (!static_cpu_has(X86_FEATURE_FPU)) - return; - - set_thread_flag(TIF_NEED_FPU_LOAD); - - if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) - return; - - /* - * PKRU state is switched eagerly because it needs to be valid before we - * return to userland e.g. for a copy_to_user() operation. - */ - if (!(current->flags & PF_KTHREAD)) { - /* - * If the PKRU bit in xsave.header.xfeatures is not set, - * then the PKRU component was in init state, which means - * XRSTOR will set PKRU to 0. If the bit is not set then - * get_xsave_addr() will return NULL because the PKRU value - * in memory is not valid. This means pkru_val has to be - * set to 0 and not to init_pkru_value. - */ - pk = get_xsave_addr(&new_fpu->state.xsave, XFEATURE_PKRU); - pkru_val = pk ? pk->pkru : 0; - } - __write_pkru(pkru_val); + if (cpu_feature_enabled(X86_FEATURE_FPU)) + set_thread_flag(TIF_NEED_FPU_LOAD); } #endif /* _ASM_X86_FPU_INTERNAL_H */ From 0e8c54f6b2c8b1037cef9276e451522ee90ed969 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:22 +0200 Subject: [PATCH 63/74] x86/fpu: Don't store PKRU in xstate in fpu_reset_fpstate() PKRU for a task is stored in task->thread.pkru when the task is scheduled out. For 'current' the authoritative source of PKRU is the hardware. fpu_reset_fpstate() has two callers: 1) fpu__clear_user_states() for !FPU systems. For those PKRU is irrelevant 2) fpu_flush_thread() which is invoked from flush_thread(). flush_thread() resets the hardware to the kernel restrictive default value. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121456.802850233@linutronix.de --- arch/x86/kernel/fpu/core.c | 22 ++++------------------ 1 file changed, 4 insertions(+), 18 deletions(-) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 470576ced90799..5295cbafc92ede 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -337,23 +337,6 @@ static inline unsigned int init_fpstate_copy_size(void) return sizeof(init_fpstate.xsave); } -/* Temporary workaround. Will be removed once PKRU and XSTATE are untangled. */ -static inline void pkru_set_default_in_xstate(struct xregs_state *xsave) -{ - struct pkru_state *pk; - - if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) - return; - /* - * Force XFEATURE_PKRU to be set in the header otherwise - * get_xsave_addr() does not work and it also needs to be set to - * make XRSTOR(S) load it. - */ - xsave->header.xfeatures |= XFEATURE_MASK_PKRU; - pk = get_xsave_addr(xsave, XFEATURE_PKRU); - pk->pkru = pkru_get_init_value(); -} - /* * Reset current->fpu memory state to the init values. */ @@ -371,9 +354,12 @@ static void fpu_reset_fpstate(void) * * Do not use fpstate_init() here. Just copy init_fpstate which has * the correct content already except for PKRU. + * + * PKRU handling does not rely on the xstate when restoring for + * user space as PKRU is eagerly written in switch_to() and + * flush_thread(). */ memcpy(&fpu->state, &init_fpstate, init_fpstate_copy_size()); - pkru_set_default_in_xstate(&fpu->state.xsave); set_thread_flag(TIF_NEED_FPU_LOAD); fpregs_unlock(); } From 72a6c08c44e4460e39315ca828f60b8d5afd6b19 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:23 +0200 Subject: [PATCH 64/74] x86/pkru: Remove xstate fiddling from write_pkru() The PKRU value of a task is stored in task->thread.pkru when the task is scheduled out. PKRU is restored on schedule in from there. So keeping the XSAVE buffer up to date is a pointless exercise. Remove the xstate fiddling and cleanup all related functions. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121456.897372712@linutronix.de --- arch/x86/include/asm/pkru.h | 17 ++++------------- arch/x86/include/asm/special_insns.h | 14 +------------- arch/x86/kvm/x86.c | 4 ++-- 3 files changed, 7 insertions(+), 28 deletions(-) diff --git a/arch/x86/include/asm/pkru.h b/arch/x86/include/asm/pkru.h index 7e4550911c5134..ccc539faa5bbcc 100644 --- a/arch/x86/include/asm/pkru.h +++ b/arch/x86/include/asm/pkru.h @@ -41,23 +41,14 @@ static inline u32 read_pkru(void) static inline void write_pkru(u32 pkru) { - struct pkru_state *pk; - if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; - - pk = get_xsave_addr(¤t->thread.fpu.state.xsave, XFEATURE_PKRU); - /* - * The PKRU value in xstate needs to be in sync with the value that is - * written to the CPU. The FPU restore on return to userland would - * otherwise load the previous value again. + * WRPKRU is relatively expensive compared to RDPKRU. + * Avoid WRPKRU when it would not change the value. */ - fpregs_lock(); - if (pk) - pk->pkru = pkru; - __write_pkru(pkru); - fpregs_unlock(); + if (pkru != rdpkru()) + wrpkru(pkru); } static inline void pkru_write_default(void) diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 2acd6cb6232821..f3fbb84ff8a77f 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -104,25 +104,13 @@ static inline void wrpkru(u32 pkru) : : "a" (pkru), "c"(ecx), "d"(edx)); } -static inline void __write_pkru(u32 pkru) -{ - /* - * WRPKRU is relatively expensive compared to RDPKRU. - * Avoid WRPKRU when it would not change the value. - */ - if (pkru == rdpkru()) - return; - - wrpkru(pkru); -} - #else static inline u32 rdpkru(void) { return 0; } -static inline void __write_pkru(u32 pkru) +static inline void wrpkru(u32 pkru) { } #endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 07f788872ddf21..8ee7add0e7631a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -943,7 +943,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) && vcpu->arch.pkru != vcpu->arch.host_pkru) - __write_pkru(vcpu->arch.pkru); + write_pkru(vcpu->arch.pkru); } EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state); @@ -957,7 +957,7 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) { vcpu->arch.pkru = rdpkru(); if (vcpu->arch.pkru != vcpu->arch.host_pkru) - __write_pkru(vcpu->arch.host_pkru); + write_pkru(vcpu->arch.host_pkru); } if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { From bf68a7d98922e1665019b8bf0c4791500837c857 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:24 +0200 Subject: [PATCH 65/74] x86/fpu: Mark init_fpstate __ro_after_init Nothing has to write into that state after init. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121456.992342060@linutronix.de --- arch/x86/kernel/fpu/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 5295cbafc92ede..7ada7bd03a3272 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -23,7 +23,7 @@ * Represents the initial FPU state. It's mostly (but not completely) zeroes, * depending on the FPU hardware format: */ -union fpregs_state init_fpstate __read_mostly; +union fpregs_state init_fpstate __ro_after_init; /* * Track whether the kernel is using the FPU state From 99a5901951b70251965b0d1542d4a8c616842a99 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:25 +0200 Subject: [PATCH 66/74] x86/fpu/signal: Move initial checks into fpu__restore_sig() __fpu__restore_sig() is convoluted and some of the basic checks can trivially be done in the calling function as well as the final error handling of clearing user state. [ bp: Fixup typos. ] Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121457.086336154@linutronix.de --- arch/x86/kernel/fpu/signal.c | 76 +++++++++++++++++++----------------- 1 file changed, 41 insertions(+), 35 deletions(-) diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index a42bc9d0b1cc57..42e85c3fe9de04 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -277,11 +277,11 @@ static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only) return frstor_from_user_sigframe(buf); } -static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) +static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, + bool ia32_fxstate) { struct user_i387_ia32_struct *envp = NULL; int state_size = fpu_kernel_xstate_size; - int ia32_fxstate = (buf != buf_fx); struct task_struct *tsk = current; struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; @@ -289,26 +289,6 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) int fx_only = 0; int ret = 0; - ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) || - IS_ENABLED(CONFIG_IA32_EMULATION)); - - if (!buf) { - fpu__clear_user_states(fpu); - return 0; - } - - if (!access_ok(buf, size)) { - ret = -EACCES; - goto out; - } - - if (!static_cpu_has(X86_FEATURE_FPU)) { - ret = fpregs_soft_set(current, NULL, 0, - sizeof(struct user_i387_ia32_struct), - NULL, buf); - goto out; - } - if (use_xsave()) { struct _fpx_sw_bytes fx_sw_user; if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) { @@ -391,7 +371,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) */ ret = __copy_from_user(&env, buf, sizeof(env)); if (ret) - goto out; + return ret; envp = &env; } @@ -424,7 +404,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) ret = copy_sigframe_from_user_to_xstate(&fpu->state.xsave, buf_fx); if (ret) - goto out; + return ret; sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures, fx_only); @@ -442,10 +422,8 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) } else if (use_fxsr()) { ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size); - if (ret) { - ret = -EFAULT; - goto out; - } + if (ret) + return -EFAULT; sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures, fx_only); @@ -462,7 +440,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) } else { ret = __copy_from_user(&fpu->state.fsave, buf_fx, state_size); if (ret) - goto out; + return ret; fpregs_lock(); ret = frstor_safe(&fpu->state.fsave); @@ -472,10 +450,6 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) else fpregs_deactivate(fpu); fpregs_unlock(); - -out: - if (ret) - fpu__clear_user_states(fpu); return ret; } @@ -490,15 +464,47 @@ static inline int xstate_sigframe_size(void) */ int fpu__restore_sig(void __user *buf, int ia32_frame) { + unsigned int size = xstate_sigframe_size(); + struct fpu *fpu = ¤t->thread.fpu; void __user *buf_fx = buf; - int size = xstate_sigframe_size(); + bool ia32_fxstate = false; + int ret; + + if (unlikely(!buf)) { + fpu__clear_user_states(fpu); + return 0; + } + ia32_frame &= (IS_ENABLED(CONFIG_X86_32) || + IS_ENABLED(CONFIG_IA32_EMULATION)); + + /* + * Only FXSR enabled systems need the FX state quirk. + * FRSTOR does not need it and can use the fast path. + */ if (ia32_frame && use_fxsr()) { buf_fx = buf + sizeof(struct fregs_state); size += sizeof(struct fregs_state); + ia32_fxstate = true; } - return __fpu__restore_sig(buf, buf_fx, size); + if (!access_ok(buf, size)) { + ret = -EACCES; + 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); + } else { + ret = __fpu_restore_sig(buf, buf_fx, ia32_fxstate); + } + +out: + if (unlikely(ret)) + fpu__clear_user_states(fpu); + return ret; } unsigned long From 9ba589f9cdbd8906465b108bc7ec0fc1519a06d3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:26 +0200 Subject: [PATCH 67/74] x86/fpu/signal: Remove the legacy alignment check Checking for the XSTATE buffer being 64-byte aligned, and if not, deciding just to restore the FXSR state is daft. If user space provides an unaligned math frame and has the extended state magic set in the FX software reserved bytes, then it really can keep the pieces. If the frame is unaligned and the FX software magic is not set, then fx_only is already set and the restore will use fxrstor. Remove it. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121457.184149902@linutronix.de --- arch/x86/kernel/fpu/signal.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 42e85c3fe9de04..8a327c05bb8654 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -306,9 +306,6 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, } } - if ((unsigned long)buf_fx % 64) - fx_only = 1; - if (!ia32_fxstate) { /* * Attempt to restore the FPU registers directly from user From 1258a8c896044564514c1b53795ba3033b1e9fd6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:27 +0200 Subject: [PATCH 68/74] x86/fpu/signal: Sanitize the xstate check on sigframe Utilize the check for the extended state magic in the FX software reserved bytes and set the parameters for restoring fx_only in the relevant members of fw_sw_user. This allows further cleanups on top because the data is consistent. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121457.277738268@linutronix.de --- arch/x86/kernel/fpu/signal.c | 70 +++++++++++++++++------------------- 1 file changed, 33 insertions(+), 37 deletions(-) diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 8a327c05bb8654..d552410388711a 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -15,29 +15,30 @@ #include #include -static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32; +static struct _fpx_sw_bytes fx_sw_reserved __ro_after_init; +static struct _fpx_sw_bytes fx_sw_reserved_ia32 __ro_after_init; /* * Check for the presence of extended state information in the * user fpstate pointer in the sigcontext. */ -static inline int check_for_xstate(struct fxregs_state __user *buf, - void __user *fpstate, - struct _fpx_sw_bytes *fx_sw) +static inline int 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); + void __user *fpstate = fxbuf; unsigned int magic2; - if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw))) - return -1; + if (__copy_from_user(fx_sw, &fxbuf->sw_reserved[0], sizeof(*fx_sw))) + return -EFAULT; /* 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 > fx_sw->extended_size) - return -1; + goto setfx; /* * Check for the presence of second magic word at the end of memory @@ -45,10 +46,18 @@ static inline int check_for_xstate(struct fxregs_state __user *buf, * fpstate layout with out copying the extended state information * in the memory layout. */ - if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)) - || magic2 != FP_XSTATE_MAGIC2) - return -1; + if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))) + return -EFAULT; + if (likely(magic2 == FP_XSTATE_MAGIC2)) + return 0; +setfx: + trace_x86_fpu_xstate_check_failed(¤t->thread.fpu); + + /* Set the parameters for fx only state */ + fx_sw->magic1 = 0; + fx_sw->xstate_size = sizeof(struct fxregs_state); + fx_sw->xfeatures = XFEATURE_MASK_FPSSE; return 0; } @@ -213,21 +222,15 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) static inline void sanitize_restored_user_xstate(union fpregs_state *state, - struct user_i387_ia32_struct *ia32_env, - u64 user_xfeatures, int fx_only) + struct user_i387_ia32_struct *ia32_env, u64 mask) { struct xregs_state *xsave = &state->xsave; struct xstate_header *header = &xsave->header; if (use_xsave()) { /* - * Clear all feature bits which are not set in - * user_xfeatures and clear all extended features - * for fx_only mode. - */ - u64 mask = fx_only ? XFEATURE_MASK_FPSSE : user_xfeatures; - - /* + * Clear all feature bits which are not set in mask. + * * Supervisor state has to be preserved. The sigframe * restore can only modify user features, i.e. @mask * cannot contain them. @@ -286,24 +289,19 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; u64 user_xfeatures = 0; - int fx_only = 0; + bool fx_only = false; int ret = 0; if (use_xsave()) { struct _fpx_sw_bytes fx_sw_user; - if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) { - /* - * Couldn't find the extended state information in the - * memory layout. Restore just the FP/SSE and init all - * the other extended state. - */ - state_size = sizeof(struct fxregs_state); - fx_only = 1; - trace_x86_fpu_xstate_check_failed(fpu); - } else { - state_size = fx_sw_user.xstate_size; - user_xfeatures = fx_sw_user.xfeatures; - } + + ret = check_xstate_in_sigframe(buf_fx, &fx_sw_user); + if (unlikely(ret)) + return ret; + + fx_only = !fx_sw_user.magic1; + state_size = fx_sw_user.xstate_size; + user_xfeatures = fx_sw_user.xfeatures; } if (!ia32_fxstate) { @@ -403,8 +401,7 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, if (ret) return ret; - sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures, - fx_only); + sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures); fpregs_lock(); if (unlikely(init_bv)) @@ -422,8 +419,7 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, if (ret) return -EFAULT; - sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures, - fx_only); + sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures); fpregs_lock(); if (use_xsave()) { From cdcec1b77001e7f2cd10dccfc6d9b6d5d3f1f3ea Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:28 +0200 Subject: [PATCH 69/74] x86/fpu/signal: Sanitize copy_user_to_fpregs_zeroing() Now that user_xfeatures is correctly set when xsave is enabled, remove the duplicated initialization of components. Rename the function while at it. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121457.377341297@linutronix.de --- arch/x86/kernel/fpu/signal.c | 36 +++++++++++++++--------------------- 1 file changed, 15 insertions(+), 21 deletions(-) diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index d552410388711a..a1a70134e1fe5e 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -251,33 +251,27 @@ sanitize_restored_user_xstate(union fpregs_state *state, } /* - * Restore the extended state if present. Otherwise, restore the FP/SSE state. + * Restore the FPU state directly from the userspace signal frame. */ -static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only) +static int restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only) { - u64 init_bv; - int r; - if (use_xsave()) { - if (fx_only) { - init_bv = xfeatures_mask_uabi() & ~XFEATURE_MASK_FPSSE; + u64 init_bv = xfeatures_mask_uabi() & ~xrestore; + int ret; - r = fxrstor_from_user_sigframe(buf); - if (!r) - os_xrstor(&init_fpstate.xsave, init_bv); - return r; - } else { - init_bv = xfeatures_mask_uabi() & ~xbv; - - r = xrstor_from_user_sigframe(buf, xbv); - if (!r && unlikely(init_bv)) - os_xrstor(&init_fpstate.xsave, init_bv); - return r; - } + if (likely(!fx_only)) + ret = xrstor_from_user_sigframe(buf, xrestore); + else + ret = fxrstor_from_user_sigframe(buf); + + if (!ret && unlikely(init_bv)) + os_xrstor(&init_fpstate.xsave, init_bv); + return ret; } else if (use_fxsr()) { return fxrstor_from_user_sigframe(buf); - } else + } else { return frstor_from_user_sigframe(buf); + } } static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, @@ -314,7 +308,7 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, */ fpregs_lock(); pagefault_disable(); - ret = copy_user_to_fpregs_zeroing(buf_fx, user_xfeatures, fx_only); + ret = restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only); pagefault_enable(); if (!ret) { From 0a6c2e9ec91c96bde1e8ce063180ac6e05e680f7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:29 +0200 Subject: [PATCH 70/74] x86/fpu/signal: Split out the direct restore code Prepare for smarter failure handling of the direct restore. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121457.493455414@linutronix.de --- arch/x86/kernel/fpu/signal.c | 112 ++++++++++++++++++----------------- 1 file changed, 58 insertions(+), 54 deletions(-) diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index a1a70134e1fe5e..aa268d9cf22845 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -250,10 +250,8 @@ sanitize_restored_user_xstate(union fpregs_state *state, } } -/* - * Restore the FPU state directly from the userspace signal frame. - */ -static int restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only) +static int __restore_fpregs_from_user(void __user *buf, u64 xrestore, + bool fx_only) { if (use_xsave()) { u64 init_bv = xfeatures_mask_uabi() & ~xrestore; @@ -274,6 +272,57 @@ static int restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only } } +static int restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only) +{ + struct fpu *fpu = ¤t->thread.fpu; + int ret; + + fpregs_lock(); + pagefault_disable(); + ret = __restore_fpregs_from_user(buf, xrestore, fx_only); + pagefault_enable(); + + if (unlikely(ret)) { + /* + * The above did an FPU restore operation, restricted to + * the user portion of the registers, and failed, but the + * microcode might have modified the FPU registers + * nevertheless. + * + * If the FPU registers do not belong to current, then + * invalidate the FPU register state otherwise the task + * might preempt current and return to user space with + * corrupted FPU registers. + * + * In case current owns the FPU registers then no further + * action is required. The fixup in the slow path will + * handle it correctly. + */ + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + __cpu_invalidate_fpregs_state(); + fpregs_unlock(); + return ret; + } + + /* + * Restore supervisor states: previous context switch etc has done + * XSAVES and saved the supervisor states in the kernel buffer from + * which they can be restored now. + * + * It would be optimal to handle this with a single XRSTORS, but + * this does not work because the rest of the FPU registers have + * been restored from a user buffer directly. The single XRSTORS + * happens below, when the user buffer has been copied to the + * kernel one. + */ + if (test_thread_flag(TIF_NEED_FPU_LOAD) && xfeatures_mask_supervisor()) + os_xrstor(&fpu->state.xsave, xfeatures_mask_supervisor()); + + fpregs_mark_activate(); + fpregs_unlock(); + return 0; +} + static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, bool ia32_fxstate) { @@ -298,61 +347,16 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, user_xfeatures = fx_sw_user.xfeatures; } - if (!ia32_fxstate) { + 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. + * 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. */ - fpregs_lock(); - pagefault_disable(); ret = restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only); - pagefault_enable(); - if (!ret) { - - /* - * Restore supervisor states: previous context switch - * etc has done XSAVES and saved the supervisor states - * in the kernel buffer from which they can be restored - * now. - * - * We cannot do a single XRSTORS here - which would - * be nice - because the rest of the FPU registers are - * being restored from a user buffer directly. The - * single XRSTORS happens below, when the user buffer - * has been copied to the kernel one. - */ - if (test_thread_flag(TIF_NEED_FPU_LOAD) && - xfeatures_mask_supervisor()) { - os_xrstor(&fpu->state.xsave, - xfeatures_mask_supervisor()); - } - fpregs_mark_activate(); - fpregs_unlock(); + if (likely(!ret)) return 0; - } - - /* - * The above did an FPU restore operation, restricted to - * the user portion of the registers, and failed, but the - * microcode might have modified the FPU registers - * nevertheless. - * - * If the FPU registers do not belong to current, then - * invalidate the FPU register state otherwise the task might - * preempt current and return to user space with corrupted - * FPU registers. - * - * In case current owns the FPU registers then no further - * action is required. The fixup below will handle it - * correctly. - */ - if (test_thread_flag(TIF_NEED_FPU_LOAD)) - __cpu_invalidate_fpregs_state(); - - fpregs_unlock(); } else { /* * For 32-bit frames with fxstate, copy the fxstate so it can From aee8c67a4faa40a8df4e79316dbfc92d123989c1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:30 +0200 Subject: [PATCH 71/74] x86/fpu: Return proper error codes from user access functions When *RSTOR from user memory raises an exception, there is no way to differentiate them. That's bad because it forces the slow path even when the failure was not a fault. If the operation raised eg. #GP then going through the slow path is pointless. Use _ASM_EXTABLE_FAULT() which stores the trap number and let the exception fixup return the negated trap number as error. This allows to separate the fast path and let it handle faults directly and avoid the slow path for all other exceptions. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121457.601480369@linutronix.de --- arch/x86/include/asm/fpu/internal.h | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 528a86826f953c..5a18694a89b24d 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -88,6 +88,7 @@ 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; \ @@ -95,14 +96,14 @@ extern void save_fpregs_to_fpstate(struct fpu *fpu); might_fault(); \ \ asm volatile(ASM_STAC "\n" \ - "1:" #insn "\n\t" \ + "1: " #insn "\n" \ "2: " ASM_CLAC "\n" \ ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ + "3: negl %%eax\n" \ " jmp 2b\n" \ ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err), output \ + _ASM_EXTABLE_FAULT(1b, 3b) \ + : [err] "=a" (err), output \ : "0"(0), input); \ err; \ }) @@ -196,16 +197,20 @@ static inline void fxsave(struct fxregs_state *fx) #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: movl $-2,%[err]\n\t" \ + "3: negl %%eax\n\t" \ "jmp 2b\n\t" \ ".popsection\n\t" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err) \ + _ASM_EXTABLE_FAULT(1b, 3b) \ + : [err] "=a" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") From fcb3635f5018e53024c6be3c3213737f469f74ff Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:31 +0200 Subject: [PATCH 72/74] x86/fpu/signal: Handle #PF in the direct restore path If *RSTOR raises an exception, then the slow path is taken. That's wrong because if the reason was not #PF then going through the slow path is waste of time because that will end up with the same conclusion that the data is invalid. Now that the wrapper around *RSTOR return an negative error code, which is the negated trap number, it's possible to differentiate. If the *RSTOR raised #PF then handle it directly in the fast path and if it was some other exception, e.g. #GP, then give up and do not try the fast path. This removes the legacy frame FRSTOR code from the slow path because FRSTOR is not a ia32_fxstate frame and is therefore handled in the fast path. Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121457.696022863@linutronix.de --- arch/x86/kernel/fpu/signal.c | 67 ++++++++++++++++++------------------ 1 file changed, 33 insertions(+), 34 deletions(-) diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index aa268d9cf22845..4c252d0c8e6ae2 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -272,11 +272,17 @@ static int __restore_fpregs_from_user(void __user *buf, u64 xrestore, } } -static int restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only) +/* + * 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) { struct fpu *fpu = ¤t->thread.fpu; int ret; +retry: fpregs_lock(); pagefault_disable(); ret = __restore_fpregs_from_user(buf, xrestore, fx_only); @@ -293,14 +299,18 @@ static int restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only * invalidate the FPU register state otherwise the task * might preempt current and return to user space with * corrupted FPU registers. - * - * In case current owns the FPU registers then no further - * action is required. The fixup in the slow path will - * handle it correctly. */ if (test_thread_flag(TIF_NEED_FPU_LOAD)) __cpu_invalidate_fpregs_state(); fpregs_unlock(); + + /* Try to handle #PF, but anything else is fatal. */ + if (ret != -EFAULT) + return -EINVAL; + + ret = fault_in_pages_readable(buf, size); + if (!ret) + goto retry; return ret; } @@ -311,9 +321,7 @@ static int restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only * * It would be optimal to handle this with a single XRSTORS, but * this does not work because the rest of the FPU registers have - * been restored from a user buffer directly. The single XRSTORS - * happens below, when the user buffer has been copied to the - * kernel one. + * 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()); @@ -326,14 +334,13 @@ static int restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, bool ia32_fxstate) { - struct user_i387_ia32_struct *envp = NULL; int state_size = fpu_kernel_xstate_size; struct task_struct *tsk = current; struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; u64 user_xfeatures = 0; bool fx_only = false; - int ret = 0; + int ret; if (use_xsave()) { struct _fpx_sw_bytes fx_sw_user; @@ -354,20 +361,19 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, * faults. If it does, fall back to the slow path below, going * through the kernel buffer with the enabled pagefault handler. */ - ret = restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only); - if (likely(!ret)) - return 0; - } else { - /* - * For 32-bit frames with fxstate, copy the fxstate so it can - * be reconstructed later. - */ - ret = __copy_from_user(&env, buf, sizeof(env)); - if (ret) - return ret; - envp = &env; + return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only, + state_size); } + /* + * Copy the legacy state because the FP portion of the FX frame has + * 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; + /* * By setting TIF_NEED_FPU_LOAD it is ensured that our xstate is * not modified on context switch and that the xstate is considered @@ -382,8 +388,7 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, * supervisor state is preserved. Save the full state for * simplicity. There is no point in optimizing this by only * saving the supervisor states and then shuffle them to - * the right place in memory. This is the slow path and the - * above XRSTOR failed or ia32_fxstate is true. Shrug. + * the right place in memory. It's ia32 mode. Shrug. */ if (xfeatures_mask_supervisor()) os_xsave(&fpu->state.xsave); @@ -399,7 +404,7 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, if (ret) return ret; - sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures); + sanitize_restored_user_xstate(&fpu->state, &env, user_xfeatures); fpregs_lock(); if (unlikely(init_bv)) @@ -412,12 +417,12 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, ret = os_xrstor_safe(&fpu->state.xsave, user_xfeatures | xfeatures_mask_supervisor()); - } else if (use_fxsr()) { + } else { ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size); if (ret) return -EFAULT; - sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures); + sanitize_restored_user_xstate(&fpu->state, &env, user_xfeatures); fpregs_lock(); if (use_xsave()) { @@ -428,14 +433,8 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, } ret = fxrstor_safe(&fpu->state.fxsave); - } else { - ret = __copy_from_user(&fpu->state.fsave, buf_fx, state_size); - if (ret) - return ret; - - fpregs_lock(); - ret = frstor_safe(&fpu->state.fsave); } + if (!ret) fpregs_mark_activate(); else From 6f9866a166cd1ad3ebb2dcdb3874aa8fee8dea2f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:32 +0200 Subject: [PATCH 73/74] x86/fpu/signal: Let xrstor handle the features to init There is no reason to do an extra XRSTOR from init_fpstate for feature bits which have been cleared by user space in the FX magic xfeatures storage. Just clear them in the task's XSTATE header and do a full restore which will put these cleared features into init state. There is no real difference in performance because the current code already does a full restore when the xfeatures bits are preserved as the signal frame setup has stored them, which is the full UABI feature set. [ bp: Use the negated mxcsr_feature_mask in the MXCSR check. ] Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121457.804115017@linutronix.de --- arch/x86/kernel/fpu/signal.c | 89 +++++++++++++----------------------- 1 file changed, 31 insertions(+), 58 deletions(-) diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 4c252d0c8e6ae2..445c57c9c5397f 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -220,36 +220,6 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) return 0; } -static inline void -sanitize_restored_user_xstate(union fpregs_state *state, - struct user_i387_ia32_struct *ia32_env, u64 mask) -{ - struct xregs_state *xsave = &state->xsave; - struct xstate_header *header = &xsave->header; - - if (use_xsave()) { - /* - * Clear all feature bits which are not set in mask. - * - * Supervisor state has to be preserved. The sigframe - * restore can only modify user features, i.e. @mask - * cannot contain them. - */ - header->xfeatures &= mask | xfeatures_mask_supervisor(); - } - - if (use_fxsr()) { - /* - * mscsr reserved bits must be masked to zero for security - * reasons. - */ - xsave->i387.mxcsr &= mxcsr_feature_mask; - - if (ia32_env) - convert_to_fxsr(&state->fxsave, ia32_env); - } -} - static int __restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only) { @@ -352,6 +322,8 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, 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; } if (likely(!ia32_fxstate)) { @@ -395,54 +367,55 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, set_thread_flag(TIF_NEED_FPU_LOAD); } __fpu_invalidate_fpregs_state(fpu); + __cpu_invalidate_fpregs_state(); fpregs_unlock(); if (use_xsave() && !fx_only) { - u64 init_bv = xfeatures_mask_uabi() & ~user_xfeatures; - ret = copy_sigframe_from_user_to_xstate(&fpu->state.xsave, buf_fx); if (ret) return ret; + } else { + if (__copy_from_user(&fpu->state.fxsave, buf_fx, + sizeof(fpu->state.fxsave))) + return -EFAULT; - sanitize_restored_user_xstate(&fpu->state, &env, user_xfeatures); + /* Reject invalid MXCSR values. */ + if (fpu->state.fxsave.mxcsr & ~mxcsr_feature_mask) + return -EINVAL; - fpregs_lock(); - if (unlikely(init_bv)) - os_xrstor(&init_fpstate.xsave, init_bv); + /* Enforce XFEATURE_MASK_FPSSE when XSAVE is enabled */ + if (use_xsave()) + fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE; + } + + /* Fold the legacy FP storage */ + convert_to_fxsr(&fpu->state.fxsave, &env); + fpregs_lock(); + if (use_xsave()) { /* - * Restore previously saved supervisor xstates along with - * copied-in user xstates. + * Remove all UABI feature bits not set in user_xfeatures + * from the memory xstate header which makes the full + * restore below bring them into init state. This works for + * fx_only mode as well because that has only FP and SSE + * set in user_xfeatures. + * + * Preserve supervisor states! */ - ret = os_xrstor_safe(&fpu->state.xsave, - user_xfeatures | xfeatures_mask_supervisor()); + u64 mask = user_xfeatures | xfeatures_mask_supervisor(); + fpu->state.xsave.header.xfeatures &= mask; + ret = os_xrstor_safe(&fpu->state.xsave, xfeatures_mask_all); } else { - ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size); - if (ret) - return -EFAULT; - - sanitize_restored_user_xstate(&fpu->state, &env, user_xfeatures); - - fpregs_lock(); - if (use_xsave()) { - u64 init_bv; - - init_bv = xfeatures_mask_uabi() & ~XFEATURE_MASK_FPSSE; - os_xrstor(&init_fpstate.xsave, init_bv); - } - ret = fxrstor_safe(&fpu->state.fxsave); } - if (!ret) + if (likely(!ret)) fpregs_mark_activate(); - else - fpregs_deactivate(fpu); + fpregs_unlock(); return ret; } - static inline int xstate_sigframe_size(void) { return use_xsave() ? fpu_user_xstate_size + FP_XSTATE_MAGIC2_SIZE : From 93c2cdc975aab53c222472c5b96c2d41dbeb350c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 24 Jun 2021 17:09:18 +0200 Subject: [PATCH 74/74] x86/fpu/xstate: Clear xstate header in copy_xstate_to_uabi_buf() again The change which made copy_xstate_to_uabi_buf() usable for [x]fpregs_get() removed the zeroing of the header which means the header, which is copied to user space later, contains except for the xfeatures member, random stack content. Add the memset() back to zero it before usage. Fixes: eb6f51723f03 ("x86/fpu: Make copy_xstate_to_kernel() usable for [x]fpregs_get()") Reported-by: kernel test robot Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/875yy3wb8h.ffs@nanos.tec.linutronix.de --- arch/x86/kernel/fpu/xstate.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 21a10a66c4e450..c8def1b7f8fbad 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -982,6 +982,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, unsigned int zerofrom; int i; + memset(&header, 0, sizeof(header)); header.xfeatures = xsave->header.xfeatures; /* Mask out the feature bits depending on copy mode */