* [PATCH v5 10/27] mm/mmap: Prevent Shadow Stack VMA merges
From: Yu-cheng Yu @ 2018-10-11 15:15 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Cyrill Gorcunov, Dave Hansen,
Eugene Syromiatnikov, Florian Weimer, H.J. Lu, Jann Horn,
Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pa
Cc: Yu-cheng Yu
In-Reply-To: <20181011151523.27101-1-yu-cheng.yu@intel.com>
To prevent function call/return spills into the next shadow stack
area, we do not merge shadow stack areas.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
mm/mmap.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/mm/mmap.c b/mm/mmap.c
index 5f2b2b184c60..b85292014ec9 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1123,6 +1123,12 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
if (vm_flags & VM_SPECIAL)
return NULL;
+ /*
+ * Do not merge shadow stack areas.
+ */
+ if (vm_flags & VM_SHSTK)
+ return NULL;
+
if (prev)
next = prev->vm_next;
else
--
2.17.1
^ permalink raw reply related
* [PATCH v5 09/27] mm: Introduce VM_SHSTK for shadow stack memory
From: Yu-cheng Yu @ 2018-10-11 15:15 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Cyrill Gorcunov, Dave Hansen,
Eugene Syromiatnikov, Florian Weimer, H.J. Lu, Jann Horn,
Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pa
Cc: Yu-cheng Yu
In-Reply-To: <20181011151523.27101-1-yu-cheng.yu@intel.com>
VM_SHSTK indicates a shadow stack memory area.
The shadow stack is implemented only for the 64-bit kernel.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
fs/proc/task_mmu.c | 3 +++
include/linux/mm.h | 8 ++++++++
2 files changed, 11 insertions(+)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 5ea1d64cb0b4..b20450dde5b7 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -652,6 +652,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
[ilog2(VM_PKEY_BIT4)] = "",
#endif
#endif /* CONFIG_ARCH_HAS_PKEYS */
+#ifdef CONFIG_X86_INTEL_SHADOW_STACK_USER
+ [ilog2(VM_SHSTK)] = "ss"
+#endif
};
size_t i;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 53cfc104c0fb..f658923e76ad 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -224,11 +224,13 @@ extern unsigned int kobjsize(const void *objp);
#define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */
+#define VM_HIGH_ARCH_BIT_5 37 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0)
#define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1)
#define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2)
#define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3)
#define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4)
+#define VM_HIGH_ARCH_5 BIT(VM_HIGH_ARCH_BIT_5)
#endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */
#ifdef CONFIG_ARCH_HAS_PKEYS
@@ -266,6 +268,12 @@ extern unsigned int kobjsize(const void *objp);
# define VM_MPX VM_NONE
#endif
+#ifdef CONFIG_X86_INTEL_SHADOW_STACK_USER
+# define VM_SHSTK VM_HIGH_ARCH_5
+#else
+# define VM_SHSTK VM_NONE
+#endif
+
#ifndef VM_GROWSUP
# define VM_GROWSUP VM_NONE
#endif
--
2.17.1
^ permalink raw reply related
* [PATCH v5 08/27] x86/cet/shstk: Add Kconfig option for user-mode shadow stack
From: Yu-cheng Yu @ 2018-10-11 15:15 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Cyrill Gorcunov, Dave Hansen,
Eugene Syromiatnikov, Florian Weimer, H.J. Lu, Jann Horn,
Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pa
Cc: Yu-cheng Yu
In-Reply-To: <20181011151523.27101-1-yu-cheng.yu@intel.com>
Introduce Kconfig option X86_INTEL_SHADOW_STACK_USER.
An application has shadow stack protection when all the following are
true:
(1) The kernel has X86_INTEL_SHADOW_STACK_USER enabled,
(2) The running processor supports the shadow stack,
(3) The application is built with shadow stack enabled tools & libs
and, and at runtime, all dependent shared libs can support shadow
stack.
If this kernel config option is enabled, but (2) or (3) above is not
true, the application runs without the shadow stack protection.
Existing legacy applications will continue to work without the shadow
stack protection.
The user-mode shadow stack protection is only implemented for the
64-bit kernel. Thirty-two bit applications are supported under the
compatibility mode.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/Kconfig | 26 ++++++++++++++++++++++++++
arch/x86/Makefile | 7 +++++++
2 files changed, 33 insertions(+)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1a0be022f91d..5f73335b7a3a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1913,6 +1913,32 @@ config X86_INTEL_MEMORY_PROTECTION_KEYS
If unsure, say y.
+config X86_INTEL_CET
+ def_bool n
+
+config ARCH_HAS_SHSTK
+ def_bool n
+
+config X86_INTEL_SHADOW_STACK_USER
+ prompt "Intel Shadow Stack for user-mode"
+ def_bool n
+ depends on CPU_SUP_INTEL && X86_64
+ select ARCH_USES_HIGH_VMA_FLAGS
+ select X86_INTEL_CET
+ select ARCH_HAS_SHSTK
+ select VM_AREA_GUARD
+ ---help---
+ Shadow stack provides hardware protection against program stack
+ corruption. Only when all the following are true will an application
+ have the shadow stack protection: the kernel supports it (i.e. this
+ feature is enabled), the application is compiled and linked with
+ shadow stack enabled, and the processor supports this feature.
+ When the kernel has this configuration enabled, existing non shadow
+ stack applications will continue to work, but without shadow stack
+ protection.
+
+ If unsure, say y.
+
config EFI
bool "EFI runtime service support"
depends on ACPI
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 8f6e7eb8ae9f..b28842b80295 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -152,6 +152,13 @@ ifdef CONFIG_X86_X32
endif
export CONFIG_X86_X32_ABI
+# Check assembler shadow stack suppot
+ifdef CONFIG_X86_INTEL_SHADOW_STACK_USER
+ ifeq ($(call as-instr, saveprevssp, y),)
+ $(error CONFIG_X86_INTEL_SHADOW_STACK_USER not supported by the assembler)
+ endif
+endif
+
#
# If the function graph tracer is used with mcount instead of fentry,
# '-maccumulate-outgoing-args' is needed to prevent a GCC bug
--
2.17.1
^ permalink raw reply related
* [PATCH v5 07/27] mm/mmap: Create a guard area between VMAs
From: Yu-cheng Yu @ 2018-10-11 15:15 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Cyrill Gorcunov, Dave Hansen,
Eugene Syromiatnikov, Florian Weimer, H.J. Lu, Jann Horn,
Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pa
Cc: Yu-cheng Yu
In-Reply-To: <20181011151523.27101-1-yu-cheng.yu@intel.com>
Create a guard area between VMAs to detect memory corruption.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
include/linux/mm.h | 30 ++++++++++++++++++++----------
mm/Kconfig | 7 +++++++
2 files changed, 27 insertions(+), 10 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0416a7204be3..53cfc104c0fb 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2417,24 +2417,34 @@ static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * m
static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
{
unsigned long vm_start = vma->vm_start;
+ unsigned long gap = 0;
+
+ if (vma->vm_flags & VM_GROWSDOWN)
+ gap = stack_guard_gap;
+ else if (IS_ENABLED(CONFIG_VM_AREA_GUARD))
+ gap = PAGE_SIZE;
+
+ vm_start -= gap;
+ if (vm_start > vma->vm_start)
+ vm_start = 0;
- if (vma->vm_flags & VM_GROWSDOWN) {
- vm_start -= stack_guard_gap;
- if (vm_start > vma->vm_start)
- vm_start = 0;
- }
return vm_start;
}
static inline unsigned long vm_end_gap(struct vm_area_struct *vma)
{
unsigned long vm_end = vma->vm_end;
+ unsigned long gap = 0;
+
+ if (vma->vm_flags & VM_GROWSUP)
+ gap = stack_guard_gap;
+ else if (IS_ENABLED(CONFIG_VM_AREA_GUARD))
+ gap = PAGE_SIZE;
+
+ vm_end += gap;
+ if (vm_end < vma->vm_end)
+ vm_end = -PAGE_SIZE;
- if (vma->vm_flags & VM_GROWSUP) {
- vm_end += stack_guard_gap;
- if (vm_end < vma->vm_end)
- vm_end = -PAGE_SIZE;
- }
return vm_end;
}
diff --git a/mm/Kconfig b/mm/Kconfig
index de64ea658716..0cdcad65640d 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -764,4 +764,11 @@ config GUP_BENCHMARK
config ARCH_HAS_PTE_SPECIAL
bool
+config VM_AREA_GUARD
+ bool "VM area guard"
+ default n
+ help
+ Create a guard area between VM areas so that access beyond
+ limit can be detected.
+
endmenu
--
2.17.1
^ permalink raw reply related
* [PATCH v5 06/27] x86/cet: Control protection exception handler
From: Yu-cheng Yu @ 2018-10-11 15:15 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Cyrill Gorcunov, Dave Hansen,
Eugene Syromiatnikov, Florian Weimer, H.J. Lu, Jann Horn,
Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pa
Cc: Yu-cheng Yu
In-Reply-To: <20181011151523.27101-1-yu-cheng.yu@intel.com>
A control protection exception is triggered when a control flow transfer
attempt violated shadow stack or indirect branch tracking constraints.
For example, the return address for a RET instruction differs from the
safe copy on the shadow stack; or a JMP instruction arrives at a non-
ENDBR instruction.
The control protection exception handler works in a similar way as the
general protection fault handler.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/entry/entry_64.S | 2 +-
arch/x86/include/asm/traps.h | 3 ++
arch/x86/kernel/idt.c | 4 ++
arch/x86/kernel/signal_compat.c | 2 +-
arch/x86/kernel/traps.c | 64 ++++++++++++++++++++++++++++++
include/uapi/asm-generic/siginfo.h | 3 +-
6 files changed, 75 insertions(+), 3 deletions(-)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 957dfb693ecc..5f4914e988df 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1000,7 +1000,7 @@ idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0
idtentry coprocessor_error do_coprocessor_error has_error_code=0
idtentry alignment_check do_alignment_check has_error_code=1
idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0
-
+idtentry control_protection do_control_protection has_error_code=1
/*
* Reload gs selector with exception handling
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 3de69330e6c5..5196050ff3d5 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -26,6 +26,7 @@ asmlinkage void invalid_TSS(void);
asmlinkage void segment_not_present(void);
asmlinkage void stack_segment(void);
asmlinkage void general_protection(void);
+asmlinkage void control_protection(void);
asmlinkage void page_fault(void);
asmlinkage void async_page_fault(void);
asmlinkage void spurious_interrupt_bug(void);
@@ -77,6 +78,7 @@ dotraplinkage void do_stack_segment(struct pt_regs *, long);
dotraplinkage void do_double_fault(struct pt_regs *, long);
#endif
dotraplinkage void do_general_protection(struct pt_regs *, long);
+dotraplinkage void do_control_protection(struct pt_regs *, long);
dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long);
dotraplinkage void do_coprocessor_error(struct pt_regs *, long);
@@ -142,6 +144,7 @@ enum {
X86_TRAP_AC, /* 17, Alignment Check */
X86_TRAP_MC, /* 18, Machine Check */
X86_TRAP_XF, /* 19, SIMD Floating-Point Exception */
+ X86_TRAP_CP = 21, /* 21 Control Protection Fault */
X86_TRAP_IRET = 32, /* 32, IRET Exception */
};
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 01adea278a71..66ebc8cb16e2 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -104,6 +104,10 @@ static const __initconst struct idt_data def_idts[] = {
#elif defined(CONFIG_X86_32)
SYSG(IA32_SYSCALL_VECTOR, entry_INT80_32),
#endif
+
+#ifdef CONFIG_X86_64
+ INTG(X86_TRAP_CP, control_protection),
+#endif
};
/*
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index 9ccbf0576cd0..c572a3de1037 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -27,7 +27,7 @@ static inline void signal_compat_build_tests(void)
*/
BUILD_BUG_ON(NSIGILL != 11);
BUILD_BUG_ON(NSIGFPE != 15);
- BUILD_BUG_ON(NSIGSEGV != 7);
+ BUILD_BUG_ON(NSIGSEGV != 8);
BUILD_BUG_ON(NSIGBUS != 5);
BUILD_BUG_ON(NSIGTRAP != 5);
BUILD_BUG_ON(NSIGCHLD != 6);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index e6db475164ed..4188775681cf 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -578,6 +578,70 @@ do_general_protection(struct pt_regs *regs, long error_code)
}
NOKPROBE_SYMBOL(do_general_protection);
+static const char *control_protection_err[] =
+{
+ "unknown",
+ "near-ret",
+ "far-ret/iret",
+ "endbranch",
+ "rstorssp",
+ "setssbsy",
+};
+
+/*
+ * When a control protection exception occurs, send a signal
+ * to the responsible application. Currently, control
+ * protection is only enabled for the user mode. This
+ * exception should not come from the kernel mode.
+ */
+dotraplinkage void
+do_control_protection(struct pt_regs *regs, long error_code)
+{
+ struct task_struct *tsk;
+ siginfo_t info;
+
+ RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
+ if (notify_die(DIE_TRAP, "control protection fault", regs,
+ error_code, X86_TRAP_CP, SIGSEGV) == NOTIFY_STOP)
+ return;
+ cond_local_irq_enable(regs);
+
+ if (!user_mode(regs))
+ die("kernel control protection fault", regs, error_code);
+
+ if (!static_cpu_has(X86_FEATURE_SHSTK) &&
+ !static_cpu_has(X86_FEATURE_IBT))
+ WARN_ONCE(1, "CET is disabled but got control "
+ "protection fault\n");
+
+ tsk = current;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_nr = X86_TRAP_CP;
+
+ if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
+ printk_ratelimit()) {
+ unsigned int max_err;
+
+ max_err = ARRAY_SIZE(control_protection_err) - 1;
+ if ((error_code < 0) || (error_code > max_err))
+ error_code = 0;
+ pr_info("%s[%d] control protection ip:%lx sp:%lx error:%lx(%s)",
+ tsk->comm, task_pid_nr(tsk),
+ regs->ip, regs->sp, error_code,
+ control_protection_err[error_code]);
+ print_vma_addr(KERN_CONT " in ", regs->ip);
+ pr_cont("\n");
+ }
+
+ clear_siginfo(&info);
+ info.si_signo = SIGSEGV;
+ info.si_errno = error_code;
+ info.si_code = SEGV_CPERR;
+ info.si_addr = (void __user*)uprobe_get_trap_addr(regs);
+ force_sig_info(SIGSEGV, &info, tsk);
+}
+NOKPROBE_SYMBOL(do_control_protection);
+
dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
{
#ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index 80e2a7227205..264d8e03270f 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -228,7 +228,8 @@ typedef struct siginfo {
#define SEGV_ACCADI 5 /* ADI not enabled for mapped object */
#define SEGV_ADIDERR 6 /* Disrupting MCD error */
#define SEGV_ADIPERR 7 /* Precise MCD exception */
-#define NSIGSEGV 7
+#define SEGV_CPERR 8
+#define NSIGSEGV 8
/*
* SIGBUS si_codes
--
2.17.1
^ permalink raw reply related
* [PATCH v5 05/27] Documentation/x86: Add CET description
From: Yu-cheng Yu @ 2018-10-11 15:15 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Cyrill Gorcunov, Dave Hansen,
Eugene Syromiatnikov, Florian Weimer, H.J. Lu, Jann Horn,
Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pa
Cc: Yu-cheng Yu
In-Reply-To: <20181011151523.27101-1-yu-cheng.yu@intel.com>
Explain how CET works and the no_cet_shstk/no_cet_ibt kernel
parameters.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
.../admin-guide/kernel-parameters.txt | 6 +
Documentation/index.rst | 1 +
Documentation/x86/index.rst | 11 +
Documentation/x86/intel_cet.rst | 266 ++++++++++++++++++
4 files changed, 284 insertions(+)
create mode 100644 Documentation/x86/index.rst
create mode 100644 Documentation/x86/intel_cet.rst
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 92eb1f42240d..3854423f7c86 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2764,6 +2764,12 @@
noexec=on: enable non-executable mappings (default)
noexec=off: disable non-executable mappings
+ no_cet_ibt [X86-64] Disable indirect branch tracking for user-mode
+ applications
+
+ no_cet_shstk [X86-64] Disable shadow stack support for user-mode
+ applications
+
nosmap [X86]
Disable SMAP (Supervisor Mode Access Prevention)
even if it is supported by processor.
diff --git a/Documentation/index.rst b/Documentation/index.rst
index 5db7e87c7cb1..1cdc139adb40 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -104,6 +104,7 @@ implementation.
:maxdepth: 2
sh/index
+ x86/index
Filesystem Documentation
------------------------
diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst
new file mode 100644
index 000000000000..9c34d8cbc8f0
--- /dev/null
+++ b/Documentation/x86/index.rst
@@ -0,0 +1,11 @@
+=======================
+X86 Documentation
+=======================
+
+Control Flow Enforcement
+========================
+
+.. toctree::
+ :maxdepth: 1
+
+ intel_cet
diff --git a/Documentation/x86/intel_cet.rst b/Documentation/x86/intel_cet.rst
new file mode 100644
index 000000000000..946f4802a51f
--- /dev/null
+++ b/Documentation/x86/intel_cet.rst
@@ -0,0 +1,266 @@
+=========================================
+Control Flow Enforcement Technology (CET)
+=========================================
+
+[1] Overview
+============
+
+Control Flow Enforcement Technology (CET) provides protection against
+return/jump-oriented programming (ROP) attacks. It can be implemented
+to protect both the kernel and applications. In the first phase,
+only the user-mode protection is implemented on the 64-bit kernel.
+However, 32-bit applications are supported under the compatibility
+mode.
+
+CET includes shadow stack (SHSTK) and indirect branch tracking (IBT).
+The SHSTK is a secondary stack allocated from memory. The processor
+automatically pushes/pops a secure copy to the SHSTK every return
+address and, by comparing the secure copy to the program stack copy,
+verifies function returns are as intended. The IBT verifies all
+indirect CALL/JMP targets are intended and marked by the compiler with
+'ENDBR' op codes.
+
+There are two kernel configuration options:
+
+ INTEL_X86_SHADOW_STACK_USER, and
+ INTEL_X86_BRANCH_TRACKING_USER.
+
+To build a CET-enabled kernel, Binutils v2.31 and GCC v8.1 or later
+are required. To build a CET-enabled application, GLIBC v2.28 or
+later is also required.
+
+There are two command-line options for disabling CET features:
+
+ no_cet_shstk - disables SHSTK, and
+ no_cet_ibt - disables IBT.
+
+At run time, /proc/cpuinfo shows the availability of SHSTK and IBT.
+
+[2] CET assembly instructions
+=============================
+
+RDSSP %r
+ Read the SHSTK pointer into %r.
+
+INCSSP %r
+ Unwind (increment) the SHSTK pointer (0 ~ 255) steps as indicated
+ in the operand register. The GLIBC longjmp uses INCSSP to unwind
+ the SHSTK until that matches the program stack. When it is
+ necessary to unwind beyond 255 steps, longjmp divides and repeats
+ the process.
+
+RSTORSSP (%r)
+ Switch to the SHSTK indicated in the 'restore token' pointed by
+ the operand register and replace the 'restore token' with a new
+ token to be saved (with SAVEPREVSSP) for the outgoing SHSTK.
+
+::
+
+ Before RSTORSSP
+
+ Incoming SHSTK Current/Outgoing SHSTK
+
+ |----------------------| |----------------------|
+ addr=x | | ssp-> | |
+ |----------------------| |----------------------|
+ (%r)-> | rstor_token=(x|Lg) | addr=y-8 | |
+ |----------------------| |----------------------|
+
+ After RSTORSSP
+
+ |----------------------| |----------------------|
+ | | | |
+ |----------------------| |----------------------|
+ ssp-> | rstor_token=(y|Bz|Lg)| addr=y-8 | |
+ |----------------------| |----------------------|
+
+ note:
+ 1. Only valid addresses and restore tokens can be on the
+ user-mode SHSTK.
+ 2. A token is always of type u64 and must align to u64.
+ 3. The incoming SHSTK pointer in a rstor_token must point to
+ immediately above the token.
+ 4. 'Lg' is bit[0] of a rstor_token indicating a 64-bit SHSTK.
+ 5. 'Bz' is bit[1] of a rstor_token indicating the token is to
+ be used only for the next SAVEPREVSSP and invalid for the
+ RSTORSSP.
+
+SAVEPREVSSP
+ Store the SHSTK 'restore token' pointed by
+ (current_SHSTK_pointer + 8).
+
+::
+
+ After SAVEPREVSSP
+
+ |----------------------| |----------------------|
+ ssp-> | | | |
+ |----------------------| |----------------------|
+ | rstor_token=(y|Bz|Lg)| addr=y-8 | rstor_token(y|Lg) |
+ |----------------------| |----------------------|
+
+WRUSS %r0, (%r1)
+ Write the value in %r0 to the SHSTK address pointed by (%r1).
+ This is a kernel-mode only instruction.
+
+ENDBR
+ The compiler inserts an ENDBR at all valid branch targets. Any
+ CALL/JMP to a target without an ENDBR triggers a control
+ protection fault.
+
+[3] Application Enabling
+========================
+
+An application's CET capability is marked in its ELF header and can
+be verified from the following command output, in the
+NT_GNU_PROPERTY_TYPE_0 field:
+
+ readelf -n <application>
+
+If an application supports CET and is statically linked, it will run
+with CET protection. If the application needs any shared libraries,
+the loader checks all dependencies and enables CET only when all
+requirements are met.
+
+[4] Legacy Libraries
+====================
+
+GLIBC provides a few tunables for backward compatibility.
+
+GLIBC_TUNABLES=glibc.tune.hwcaps=-SHSTK,-IBT
+ Turn off SHSTK/IBT for the current shell.
+
+GLIBC_TUNABLES=glibc.tune.x86_shstk=<on, permissive>
+ This controls how dlopen() handles SHSTK legacy libraries:
+ on: continue with SHSTK enabled;
+ permissive: continue with SHSTK off.
+
+[5] CET system calls
+====================
+
+The following arch_prctl() system calls are added for CET:
+
+arch_prctl(ARCH_X86_CET_STATUS, unsigned long *addr)
+ Return CET feature status.
+
+ The parameter 'addr' is a pointer to a user buffer.
+ On returning to the caller, the kernel fills the following
+ information:
+
+ *addr = SHSTK/IBT status
+ *(addr + 1) = SHSTK base address
+ *(addr + 2) = SHSTK size
+
+arch_prctl(ARCH_X86_CET_DISABLE, unsigned long features)
+ Disable SHSTK and/or IBT specified in 'features'. Return -EPERM
+ if CET is locked.
+
+arch_prctl(ARCH_X86_CET_LOCK)
+ Lock in CET feature.
+
+arch_prctl(ARCH_X86_CET_ALLOC_SHSTK, unsigned long *addr)
+ Allocate a new SHSTK and put a restore token at top.
+
+ The parameter 'addr' is a pointer to a user buffer and indicates
+ the desired SHSTK size to allocate. On returning to the caller,
+ the kernel fills *addr with the base address of the new SHSTK.
+
+arch_prctl(ARCH_X86_CET_GET_LEGACY_BITMAP, unsigned long *addr)
+ Allocate an IBT legacy code bitmap if the current task does not
+ have one.
+
+ The parameter 'addr' is a pointer to a user buffer.
+ On returning to the caller, the kernel fills the following
+ information:
+
+ *addr = IBT bitmap base address
+ *(addr + 1) = IBT bitmap size
+
+Note:
+ There is no CET enabling arch_prctl function. By design, CET is
+ enabled automatically if the binary and the system can support it.
+
+ The parameters passed are always unsigned 64-bit. When an ia32
+ application passing pointers, it should only use the lower 32 bits.
+
+[6] The implementation of the SHSTK
+===================================
+
+SHSTK size
+----------
+
+A task's SHSTK is allocated from memory to a fixed size of
+RLIMIT_STACK.
+
+Signal
+------
+
+The main program and its signal handlers use the same SHSTK. Because
+the SHSTK stores only return addresses, we can use a large SHSTK to
+cover the condition that both the program stack and the sigaltstack
+run out.
+
+The kernel creates a restore token at the SHSTK restoring address and
+verifies that token when restoring from the signal handler.
+
+Fork
+----
+
+The SHSTK's vma has VM_SHSTK flag set; its PTEs are required to be
+read-only and dirty. When a SHSTK PTE is not present, RO, and dirty,
+a SHSTK access triggers a page fault with an additional SHSTK bit set
+in the page fault error code.
+
+When a task forks a child, its SHSTK PTEs are copied and both the
+parent's and the child's SHSTK PTEs are cleared of the dirty bit.
+Upon the next SHSTK access, the resulting SHSTK page fault is handled
+by page copy/re-use.
+
+When a pthread child is created, the kernel allocates a new SHSTK for
+the new thread.
+
+Setjmp/Longjmp
+--------------
+
+Longjmp unwinds SHSTK until it matches the program stack.
+
+Ucontext
+--------
+
+In GLIBC, getcontext/setcontext is implemented in similar way as
+setjmp/longjmp.
+
+When makecontext creates a new ucontext, a new SHSTK is allocated for
+that context with ARCH_X86_CET_ALLOC_SHSTK the syscall. The kernel
+creates a restore token at the top of the new SHSTK and the user-mode
+code switches to the new SHSTK with the RSTORSSP instruction.
+
+[7] The management of read-only & dirty PTEs for SHSTK
+======================================================
+
+A RO and dirty PTE exists in the following cases:
+
+(a) A page is modified and then shared with a fork()'ed child;
+(b) A R/O page that has been COW'ed;
+(c) A SHSTK page.
+
+The processor only checks the dirty bit for (c). To prevent the use
+of non-SHSTK memory as SHSTK, we use a spare bit of the 64-bit PTE as
+DIRTY_SW for (a) and (b) above. This results to the following PTE
+settings:
+
+Modified PTE: (R/W + DIRTY_HW)
+Modified and shared PTE: (R/O + DIRTY_SW)
+R/O PTE, COW'ed: (R/O + DIRTY_SW)
+SHSTK PTE: (R/O + DIRTY_HW)
+SHSTK PTE, COW'ed: (R/O + DIRTY_HW)
+SHSTK PTE, shared: (R/O + DIRTY_SW)
+
+Note that DIRTY_SW is only used in R/O PTEs but not R/W PTEs.
+
+[8] The implementation of IBT
+=============================
+
+The kernel provides IBT support in mmap() of the legacy code bit map.
+However, the management of the bitmap is done in the GLIBC or the
+application.
--
2.17.1
^ permalink raw reply related
* [PATCH v5 04/27] x86/fpu/xstate: Add XSAVES system states for shadow stack
From: Yu-cheng Yu @ 2018-10-11 15:15 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Cyrill Gorcunov, Dave Hansen,
Eugene Syromiatnikov, Florian Weimer, H.J. Lu, Jann Horn,
Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pa
Cc: Yu-cheng Yu
In-Reply-To: <20181011151523.27101-1-yu-cheng.yu@intel.com>
Intel Control-flow Enforcement Technology (CET) introduces the
following MSRs into the XSAVES system states.
IA32_U_CET (user-mode CET settings),
IA32_PL3_SSP (user-mode shadow stack),
IA32_PL0_SSP (kernel-mode shadow stack),
IA32_PL1_SSP (ring-1 shadow stack),
IA32_PL2_SSP (ring-2 shadow stack).
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/asm/fpu/types.h | 22 +++++++++++++++++++++
arch/x86/include/asm/fpu/xstate.h | 4 +++-
arch/x86/include/uapi/asm/processor-flags.h | 2 ++
arch/x86/kernel/fpu/xstate.c | 10 ++++++++++
4 files changed, 37 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 202c53918ecf..e55d51d172f1 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -114,6 +114,9 @@ enum xfeature {
XFEATURE_Hi16_ZMM,
XFEATURE_PT_UNIMPLEMENTED_SO_FAR,
XFEATURE_PKRU,
+ XFEATURE_RESERVED,
+ XFEATURE_SHSTK_USER,
+ XFEATURE_SHSTK_KERNEL,
XFEATURE_MAX,
};
@@ -128,6 +131,8 @@ enum xfeature {
#define XFEATURE_MASK_Hi16_ZMM (1 << XFEATURE_Hi16_ZMM)
#define XFEATURE_MASK_PT (1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR)
#define XFEATURE_MASK_PKRU (1 << XFEATURE_PKRU)
+#define XFEATURE_MASK_SHSTK_USER (1 << XFEATURE_SHSTK_USER)
+#define XFEATURE_MASK_SHSTK_KERNEL (1 << XFEATURE_SHSTK_KERNEL)
#define XFEATURE_MASK_FPSSE (XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
#define XFEATURE_MASK_AVX512 (XFEATURE_MASK_OPMASK \
@@ -229,6 +234,23 @@ struct pkru_state {
u32 pad;
} __packed;
+/*
+ * State component 11 is Control flow Enforcement user states
+ */
+struct cet_user_state {
+ u64 u_cet; /* user control flow settings */
+ u64 user_ssp; /* user shadow stack pointer */
+} __packed;
+
+/*
+ * State component 12 is Control flow Enforcement kernel states
+ */
+struct cet_kernel_state {
+ u64 kernel_ssp; /* kernel shadow stack */
+ u64 pl1_ssp; /* ring-1 shadow stack */
+ u64 pl2_ssp; /* ring-2 shadow stack */
+} __packed;
+
struct xstate_header {
u64 xfeatures;
u64 xcomp_bv;
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index d8e2ec99f635..18b60748a34d 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -28,7 +28,9 @@
XFEATURE_MASK_Hi16_ZMM | \
XFEATURE_MASK_PKRU | \
XFEATURE_MASK_BNDREGS | \
- XFEATURE_MASK_BNDCSR)
+ XFEATURE_MASK_BNDCSR | \
+ XFEATURE_MASK_SHSTK_USER | \
+ XFEATURE_MASK_SHSTK_KERNEL)
#ifdef CONFIG_X86_64
#define REX_PREFIX "0x48, "
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index bcba3c643e63..25311ec4b731 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -130,6 +130,8 @@
#define X86_CR4_SMAP _BITUL(X86_CR4_SMAP_BIT)
#define X86_CR4_PKE_BIT 22 /* enable Protection Keys support */
#define X86_CR4_PKE _BITUL(X86_CR4_PKE_BIT)
+#define X86_CR4_CET_BIT 23 /* enable Control flow Enforcement */
+#define X86_CR4_CET _BITUL(X86_CR4_CET_BIT)
/*
* x86-64 Task Priority Register, CR8
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 605ec6decf3e..ad36ea28bfd1 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -35,6 +35,9 @@ static const char *xfeature_names[] =
"Processor Trace (unused)" ,
"Protection Keys User registers",
"unknown xstate feature" ,
+ "Control flow User registers" ,
+ "Control flow Kernel registers" ,
+ "unknown xstate feature" ,
};
static short xsave_cpuid_features[] __initdata = {
@@ -48,6 +51,9 @@ static short xsave_cpuid_features[] __initdata = {
X86_FEATURE_AVX512F,
X86_FEATURE_INTEL_PT,
X86_FEATURE_PKU,
+ 0, /* Unused */
+ X86_FEATURE_SHSTK, /* XFEATURE_SHSTK_USER */
+ X86_FEATURE_SHSTK, /* XFEATURE_SHSTK_KERNEL */
};
/*
@@ -312,6 +318,8 @@ static void __init print_xstate_features(void)
print_xstate_feature(XFEATURE_MASK_ZMM_Hi256);
print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
print_xstate_feature(XFEATURE_MASK_PKRU);
+ print_xstate_feature(XFEATURE_MASK_SHSTK_USER);
+ print_xstate_feature(XFEATURE_MASK_SHSTK_KERNEL);
}
/*
@@ -558,6 +566,8 @@ static void check_xstate_against_struct(int nr)
XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state);
XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state);
XCHECK_SZ(sz, nr, XFEATURE_PKRU, struct pkru_state);
+ XCHECK_SZ(sz, nr, XFEATURE_SHSTK_USER, struct cet_user_state);
+ XCHECK_SZ(sz, nr, XFEATURE_SHSTK_KERNEL, struct cet_kernel_state);
/*
* Make *SURE* to add any feature numbers in below if
--
2.17.1
^ permalink raw reply related
* [PATCH v5 03/27] x86/fpu/xstate: Introduce XSAVES system states
From: Yu-cheng Yu @ 2018-10-11 15:14 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Cyrill Gorcunov, Dave Hansen,
Eugene Syromiatnikov, Florian Weimer, H.J. Lu, Jann Horn,
Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pa
Cc: Yu-cheng Yu
In-Reply-To: <20181011151523.27101-1-yu-cheng.yu@intel.com>
Control Flow Enforcement (CET) MSRs are XSAVES system states. To
support CET, we introduce XSAVES system states first.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/asm/fpu/internal.h | 3 +-
arch/x86/include/asm/fpu/xstate.h | 4 +-
arch/x86/kernel/fpu/core.c | 6 +-
arch/x86/kernel/fpu/init.c | 10 ----
arch/x86/kernel/fpu/xstate.c | 86 ++++++++++++++++++-----------
5 files changed, 62 insertions(+), 47 deletions(-)
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 02c4296478c8..9a5db5a63f60 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:
@@ -93,7 +92,7 @@ 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_user;
+ xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all;
}
static inline void fpstate_init_fxstate(struct fxregs_state *fx)
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 76f83d2ac10e..d8e2ec99f635 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -19,9 +19,6 @@
#define XSAVE_YMM_SIZE 256
#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
-/* Supervisor features */
-#define XFEATURE_MASK_SUPERVISOR (XFEATURE_MASK_PT)
-
/* All currently supported features */
#define SUPPORTED_XFEATURES_MASK (XFEATURE_MASK_FP | \
XFEATURE_MASK_SSE | \
@@ -40,6 +37,7 @@
#endif
extern u64 xfeatures_mask_user;
+extern u64 xfeatures_mask_all;
extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
extern void __init update_regset_xstate_info(unsigned int size,
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 4bd56079048f..5f076f593fa9 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -365,8 +365,12 @@ void fpu__drop(struct fpu *fpu)
*/
static inline void copy_init_user_fpstate_to_fpregs(void)
{
+ /*
+ * Only XSAVES user states are copied.
+ * System states are preserved.
+ */
if (use_xsave())
- copy_kernel_to_xregs(&init_fpstate.xsave, -1);
+ copy_kernel_to_xregs(&init_fpstate.xsave, xfeatures_mask_user);
else if (static_cpu_has(X86_FEATURE_FXSR))
copy_kernel_to_fxregs(&init_fpstate.fxsave);
else
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 761c3a5a9e07..eaf9d9d479a5 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -222,16 +222,6 @@ 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 SUPPORTED_XFEATURES_MASK;
-}
-
/* 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 e7cbaed12ef1..605ec6decf3e 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -56,9 +56,14 @@ static short xsave_cpuid_features[] __initdata = {
*/
u64 xfeatures_mask_user __read_mostly;
+/*
+ * Combined XSAVES system and user states.
+ */
+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[sizeof(xfeatures_mask_user)*8];
+static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask_all)*8];
/*
* The XSAVE area of kernel can be in standard or compacted format;
@@ -83,7 +88,7 @@ void fpu__xstate_clear_all_cpu_caps(void)
*/
int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
{
- u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask_user;
+ u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask_all;
if (unlikely(feature_name)) {
long xfeature_idx, max_idx;
@@ -162,7 +167,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
* 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_user) == xfeatures_mask_user)
+ if ((xfeatures & xfeatures_mask_all) == xfeatures_mask_all)
return;
/*
@@ -217,7 +222,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
*/
void fpu__init_cpu_xstate(void)
{
- if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask_user)
+ if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask_all)
return;
/*
* XCR_XFEATURE_ENABLED_MASK sets the features that are managed
@@ -225,20 +230,19 @@ void fpu__init_cpu_xstate(void)
* set here.
*/
- xfeatures_mask_user &= ~XFEATURE_MASK_SUPERVISOR;
-
cr4_set_bits(X86_CR4_OSXSAVE);
xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user);
+ /*
+ * MSR_IA32_XSS sets which XSAVES system states to be managed by
+ * XSAVES. Only XSAVES system states can be set here.
+ */
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
+ wrmsrl(MSR_IA32_XSS, xfeatures_mask_all & ~xfeatures_mask_user);
}
-/*
- * Note that in the future we will likely need a pair of
- * functions here: one for user xstates and the other for
- * system xstates. For now, they are the same.
- */
static int xfeature_enabled(enum xfeature xfeature)
{
- return !!(xfeatures_mask_user & BIT_ULL(xfeature));
+ return !!(xfeatures_mask_all & BIT_ULL(xfeature));
}
/*
@@ -344,7 +348,7 @@ static int xfeature_is_aligned(int xfeature_nr)
*/
static void __init setup_xstate_comp(void)
{
- unsigned int xstate_comp_sizes[sizeof(xfeatures_mask_user)*8];
+ unsigned int xstate_comp_sizes[sizeof(xfeatures_mask_all)*8];
int i;
/*
@@ -417,7 +421,7 @@ static void __init setup_init_fpu_buf(void)
print_xstate_features();
if (boot_cpu_has(X86_FEATURE_XSAVES))
- init_fpstate.xsave.header.xcomp_bv = BIT_ULL(63) | xfeatures_mask_user;
+ init_fpstate.xsave.header.xcomp_bv = BIT_ULL(63) | xfeatures_mask_all;
/*
* Init all the features state with header.xfeatures being 0x0
@@ -440,7 +444,7 @@ static int xfeature_uncompacted_offset(int xfeature_nr)
* format. Checking a system state's uncompacted offset is
* an error.
*/
- if (XFEATURE_MASK_SUPERVISOR & (1 << xfeature_nr)) {
+ if (~xfeatures_mask_user & BIT_ULL(xfeature_nr)) {
WARN_ONCE(1, "No fixed offset for xstate %d\n", xfeature_nr);
return -1;
}
@@ -612,15 +616,12 @@ static void do_extra_xstate_size_checks(void)
/*
- * Get total size of enabled xstates in XCR0/xfeatures_mask_user.
+ * Get total size of enabled xstates in XCR0 | IA32_XSS.
*
* Note the SDM's wording here. "sub-function 0" only enumerates
* the size of the *user* states. If we use it to size a buffer
* that we use 'XSAVES' on, we could potentially overflow the
* buffer because 'XSAVES' saves system states too.
- *
- * Note that we do not currently set any bits on IA32_XSS so
- * 'XCR0 | IA32_XSS == XCR0' for now.
*/
static unsigned int __init get_xsaves_size(void)
{
@@ -702,6 +703,7 @@ static int init_xstate_size(void)
*/
static void fpu__init_disable_system_xstate(void)
{
+ xfeatures_mask_all = 0;
xfeatures_mask_user = 0;
cr4_clear_bits(X86_CR4_OSXSAVE);
fpu__xstate_clear_all_cpu_caps();
@@ -717,6 +719,8 @@ void __init fpu__init_system_xstate(void)
static int on_boot_cpu __initdata = 1;
int err;
int i;
+ u64 cpu_user_xfeatures_mask;
+ u64 cpu_system_xfeatures_mask;
WARN_ON_FPU(!on_boot_cpu);
on_boot_cpu = 0;
@@ -737,10 +741,23 @@ void __init fpu__init_system_xstate(void)
return;
}
+ /*
+ * Find user states supported by the processor.
+ * Only these bits can be set in XCR0.
+ */
cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
- xfeatures_mask_user = eax + ((u64)edx << 32);
+ cpu_user_xfeatures_mask = eax + ((u64)edx << 32);
+
+ /*
+ * Find system states supported by the processor.
+ * Only these bits can be set in IA32_XSS MSR.
+ */
+ cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx);
+ cpu_system_xfeatures_mask = ecx + ((u64)edx << 32);
- if ((xfeatures_mask_user & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
+ xfeatures_mask_all = cpu_user_xfeatures_mask | cpu_system_xfeatures_mask;
+
+ if ((xfeatures_mask_all & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
/*
* This indicates that something really unexpected happened
* with the enumeration. Disable XSAVE and try to continue
@@ -755,10 +772,11 @@ void __init fpu__init_system_xstate(void)
*/
for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) {
if (!boot_cpu_has(xsave_cpuid_features[i]))
- xfeatures_mask_user &= ~BIT_ULL(i);
+ xfeatures_mask_all &= ~BIT_ULL(i);
}
- xfeatures_mask_user &= fpu__get_supported_xfeatures_mask();
+ xfeatures_mask_all &= SUPPORTED_XFEATURES_MASK;
+ xfeatures_mask_user = xfeatures_mask_all & cpu_user_xfeatures_mask;
/* Enable xstate instructions to be able to continue with initialization: */
fpu__init_cpu_xstate();
@@ -770,7 +788,7 @@ void __init fpu__init_system_xstate(void)
* Update info used for ptrace frames; use standard-format size and no
* system xstates:
*/
- update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask_user & ~XFEATURE_MASK_SUPERVISOR);
+ update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask_user);
fpu__init_prepare_fx_sw_frame();
setup_init_fpu_buf();
@@ -778,7 +796,7 @@ void __init fpu__init_system_xstate(void)
print_xstate_offset_size();
pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
- xfeatures_mask_user,
+ xfeatures_mask_all,
fpu_kernel_xstate_size,
boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard");
return;
@@ -798,6 +816,12 @@ void fpu__resume_cpu(void)
*/
if (boot_cpu_has(X86_FEATURE_XSAVE))
xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user);
+
+ /*
+ * Restore IA32_XSS
+ */
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
+ wrmsrl(MSR_IA32_XSS, xfeatures_mask_all & ~xfeatures_mask_user);
}
/*
@@ -847,9 +871,9 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
/*
* We should not ever be requesting features that we
* have not enabled. Remember that pcntxt_mask is
- * what we write to the XCR0 register.
+ * what we write to the XCR0 | IA32_XSS registers.
*/
- WARN_ONCE(!(xfeatures_mask_user & xstate_feature),
+ WARN_ONCE(!(xfeatures_mask_all & xstate_feature),
"get of unsupported state");
/*
* This assumes the last 'xsave*' instruction to
@@ -999,7 +1023,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of
*/
memset(&header, 0, sizeof(header));
header.xfeatures = xsave->header.xfeatures;
- header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR;
+ header.xfeatures &= xfeatures_mask_user;
/*
* Copy xregs_state->header:
@@ -1083,7 +1107,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i
*/
memset(&header, 0, sizeof(header));
header.xfeatures = xsave->header.xfeatures;
- header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR;
+ header.xfeatures &= xfeatures_mask_user;
/*
* Copy xregs_state->header:
@@ -1176,7 +1200,7 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf)
* 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;
+ xsave->header.xfeatures &= (xfeatures_mask_all & ~xfeatures_mask_user);
/*
* Add back in the features that came in from userspace:
@@ -1232,7 +1256,7 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf)
* 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;
+ xsave->header.xfeatures &= (xfeatures_mask_all & ~xfeatures_mask_user);
/*
* Add back in the features that came in from userspace:
--
2.17.1
^ permalink raw reply related
* [PATCH v5 02/27] x86/fpu/xstate: Change names to separate XSAVES system and user states
From: Yu-cheng Yu @ 2018-10-11 15:14 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Cyrill Gorcunov, Dave Hansen,
Eugene Syromiatnikov, Florian Weimer, H.J. Lu, Jann Horn,
Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pa
Cc: Yu-cheng Yu
In-Reply-To: <20181011151523.27101-1-yu-cheng.yu@intel.com>
Control Flow Enforcement (CET) MSRs are XSAVES system/supervisor
states. To support CET, we introduce XSAVES system states first.
XSAVES is a "supervisor" instruction and, comparing to XSAVE, saves
additional "supervisor" states that can be modified only from CPL 0.
However, these states are per-task and not kernel's own. Rename
"supervisor" states to "system" states to clearly separate them from
"user" states.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/asm/fpu/internal.h | 4 +-
arch/x86/include/asm/fpu/xstate.h | 20 +++----
arch/x86/kernel/fpu/core.c | 4 +-
arch/x86/kernel/fpu/init.c | 2 +-
arch/x86/kernel/fpu/signal.c | 6 +--
arch/x86/kernel/fpu/xstate.c | 82 ++++++++++++++---------------
6 files changed, 57 insertions(+), 61 deletions(-)
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index a38bf5a1e37a..02c4296478c8 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -93,7 +93,7 @@ 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;
+ xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_user;
}
static inline void fpstate_init_fxstate(struct fxregs_state *fx)
@@ -233,7 +233,7 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
/*
* If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact
- * format and supervisor states in addition to modified optimization in
+ * format and system states in addition to modified optimization in
* XSAVEOPT.
*
* Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 48581988d78c..76f83d2ac10e 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -23,15 +23,15 @@
#define XFEATURE_MASK_SUPERVISOR (XFEATURE_MASK_PT)
/* All currently supported features */
-#define XCNTXT_MASK (XFEATURE_MASK_FP | \
- XFEATURE_MASK_SSE | \
- XFEATURE_MASK_YMM | \
- XFEATURE_MASK_OPMASK | \
- XFEATURE_MASK_ZMM_Hi256 | \
- XFEATURE_MASK_Hi16_ZMM | \
- XFEATURE_MASK_PKRU | \
- XFEATURE_MASK_BNDREGS | \
- XFEATURE_MASK_BNDCSR)
+#define SUPPORTED_XFEATURES_MASK (XFEATURE_MASK_FP | \
+ XFEATURE_MASK_SSE | \
+ XFEATURE_MASK_YMM | \
+ XFEATURE_MASK_OPMASK | \
+ XFEATURE_MASK_ZMM_Hi256 | \
+ XFEATURE_MASK_Hi16_ZMM | \
+ XFEATURE_MASK_PKRU | \
+ XFEATURE_MASK_BNDREGS | \
+ XFEATURE_MASK_BNDCSR)
#ifdef CONFIG_X86_64
#define REX_PREFIX "0x48, "
@@ -39,7 +39,7 @@
#define REX_PREFIX
#endif
-extern u64 xfeatures_mask;
+extern u64 xfeatures_mask_user;
extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
extern void __init update_regset_xstate_info(unsigned int size,
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 2ea85b32421a..4bd56079048f 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -363,7 +363,7 @@ void fpu__drop(struct fpu *fpu)
* Clear FPU registers by setting them up from
* the init fpstate:
*/
-static inline void copy_init_fpstate_to_fpregs(void)
+static inline void copy_init_user_fpstate_to_fpregs(void)
{
if (use_xsave())
copy_kernel_to_xregs(&init_fpstate.xsave, -1);
@@ -395,7 +395,7 @@ void fpu__clear(struct fpu *fpu)
preempt_disable();
fpu__initialize(fpu);
user_fpu_begin();
- copy_init_fpstate_to_fpregs();
+ copy_init_user_fpstate_to_fpregs();
preempt_enable();
}
}
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 6abd83572b01..761c3a5a9e07 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -229,7 +229,7 @@ static void __init fpu__init_system_xstate_size_legacy(void)
*/
u64 __init fpu__get_supported_xfeatures_mask(void)
{
- return XCNTXT_MASK;
+ return SUPPORTED_XFEATURES_MASK;
}
/* Legacy code to initialize eager fpu mode. */
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 23f1691670b6..f77aa76ba675 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -249,11 +249,11 @@ static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_
{
if (use_xsave()) {
if ((unsigned long)buf % 64 || fx_only) {
- u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
+ u64 init_bv = xfeatures_mask_user & ~XFEATURE_MASK_FPSSE;
copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
return copy_user_to_fxregs(buf);
} else {
- u64 init_bv = xfeatures_mask & ~xbv;
+ u64 init_bv = xfeatures_mask_user & ~xbv;
if (unlikely(init_bv))
copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
return copy_user_to_xregs(buf, xbv);
@@ -417,7 +417,7 @@ 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;
+ fx_sw_reserved.xfeatures = xfeatures_mask_user;
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 87a57b7642d3..e7cbaed12ef1 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -51,13 +51,14 @@ static short xsave_cpuid_features[] __initdata = {
};
/*
- * Mask of xstate features supported by the CPU and the kernel:
+ * Mask of supported 'user' xstate features derived from boot_cpu_has() and
+ * SUPPORTED_XFEATURES_MASK.
*/
-u64 xfeatures_mask __read_mostly;
+u64 xfeatures_mask_user __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[sizeof(xfeatures_mask)*8];
+static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask_user)*8];
/*
* The XSAVE area of kernel can be in standard or compacted format;
@@ -82,7 +83,7 @@ void fpu__xstate_clear_all_cpu_caps(void)
*/
int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
{
- u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask;
+ u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask_user;
if (unlikely(feature_name)) {
long xfeature_idx, max_idx;
@@ -113,14 +114,11 @@ int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
}
EXPORT_SYMBOL_GPL(cpu_has_xfeatures);
-static int xfeature_is_supervisor(int xfeature_nr)
+static int xfeature_is_system(int xfeature_nr)
{
/*
- * We currently do not support supervisor states, but if
- * we did, we could find out like this.
- *
* SDM says: If state component 'i' is a user state component,
- * ECX[0] return 0; if state component i is a supervisor
+ * ECX[0] return 0; if state component i is a system
* state component, ECX[0] returns 1.
*/
u32 eax, ebx, ecx, edx;
@@ -131,7 +129,7 @@ static int xfeature_is_supervisor(int xfeature_nr)
static int xfeature_is_user(int xfeature_nr)
{
- return !xfeature_is_supervisor(xfeature_nr);
+ return !xfeature_is_system(xfeature_nr);
}
/*
@@ -164,7 +162,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
* 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) == xfeatures_mask)
+ if ((xfeatures & xfeatures_mask_user) == xfeatures_mask_user)
return;
/*
@@ -191,7 +189,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
* in a special way already:
*/
feature_bit = 0x2;
- xfeatures = (xfeatures_mask & ~xfeatures) >> 2;
+ xfeatures = (xfeatures_mask_user & ~xfeatures) >> 2;
/*
* Update all the remaining memory layouts according to their
@@ -219,20 +217,18 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
*/
void fpu__init_cpu_xstate(void)
{
- if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask)
+ if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask_user)
return;
/*
- * Make it clear that XSAVES supervisor states are not yet
- * implemented should anyone expect it to work by changing
- * bits in XFEATURE_MASK_* macros and XCR0.
+ * XCR_XFEATURE_ENABLED_MASK sets the features that are managed
+ * by XSAVE{C, OPT} and XRSTOR. Only XSAVE user states can be
+ * set here.
*/
- WARN_ONCE((xfeatures_mask & XFEATURE_MASK_SUPERVISOR),
- "x86/fpu: XSAVES supervisor states are not yet implemented.\n");
- xfeatures_mask &= ~XFEATURE_MASK_SUPERVISOR;
+ xfeatures_mask_user &= ~XFEATURE_MASK_SUPERVISOR;
cr4_set_bits(X86_CR4_OSXSAVE);
- xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user);
}
/*
@@ -242,7 +238,7 @@ void fpu__init_cpu_xstate(void)
*/
static int xfeature_enabled(enum xfeature xfeature)
{
- return !!(xfeatures_mask & (1UL << xfeature));
+ return !!(xfeatures_mask_user & BIT_ULL(xfeature));
}
/*
@@ -272,7 +268,7 @@ static void __init setup_xstate_features(void)
cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
/*
- * If an xfeature is supervisor state, the offset
+ * If an xfeature is system state, the offset
* in EBX is invalid. We leave it to -1.
*/
if (xfeature_is_user(i))
@@ -348,7 +344,7 @@ static int xfeature_is_aligned(int xfeature_nr)
*/
static void __init setup_xstate_comp(void)
{
- unsigned int xstate_comp_sizes[sizeof(xfeatures_mask)*8];
+ unsigned int xstate_comp_sizes[sizeof(xfeatures_mask_user)*8];
int i;
/*
@@ -421,7 +417,7 @@ static void __init setup_init_fpu_buf(void)
print_xstate_features();
if (boot_cpu_has(X86_FEATURE_XSAVES))
- init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask;
+ init_fpstate.xsave.header.xcomp_bv = BIT_ULL(63) | xfeatures_mask_user;
/*
* Init all the features state with header.xfeatures being 0x0
@@ -440,8 +436,8 @@ static int xfeature_uncompacted_offset(int xfeature_nr)
u32 eax, ebx, ecx, edx;
/*
- * Only XSAVES supports supervisor states and it uses compacted
- * format. Checking a supervisor state's uncompacted offset is
+ * Only XSAVES supports system states and it uses compacted
+ * format. Checking a system state's uncompacted offset is
* an error.
*/
if (XFEATURE_MASK_SUPERVISOR & (1 << xfeature_nr)) {
@@ -465,7 +461,7 @@ static int xfeature_size(int xfeature_nr)
/*
* 'XSAVES' implies two different things:
- * 1. saving of supervisor/system state
+ * 1. saving of system state
* 2. using the compacted format
*
* Use this function when dealing with the compacted format so
@@ -480,8 +476,8 @@ int using_compacted_format(void)
/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
int validate_xstate_header(const struct xstate_header *hdr)
{
- /* No unknown or supervisor features may be set */
- if (hdr->xfeatures & (~xfeatures_mask | XFEATURE_MASK_SUPERVISOR))
+ /* No unknown or system features may be set */
+ if (hdr->xfeatures & ~xfeatures_mask_user)
return -EINVAL;
/* Userspace must use the uncompacted format */
@@ -588,11 +584,11 @@ static void do_extra_xstate_size_checks(void)
check_xstate_against_struct(i);
/*
- * Supervisor state components can be managed only by
+ * System state components can be managed only by
* XSAVES, which is compacted-format only.
*/
if (!using_compacted_format())
- XSTATE_WARN_ON(xfeature_is_supervisor(i));
+ XSTATE_WARN_ON(xfeature_is_system(i));
/* Align from the end of the previous feature */
if (xfeature_is_aligned(i))
@@ -616,7 +612,7 @@ static void do_extra_xstate_size_checks(void)
/*
- * Get total size of enabled xstates in XCR0/xfeatures_mask.
+ * Get total size of enabled xstates in XCR0/xfeatures_mask_user.
*
* Note the SDM's wording here. "sub-function 0" only enumerates
* the size of the *user* states. If we use it to size a buffer
@@ -706,7 +702,7 @@ static int init_xstate_size(void)
*/
static void fpu__init_disable_system_xstate(void)
{
- xfeatures_mask = 0;
+ xfeatures_mask_user = 0;
cr4_clear_bits(X86_CR4_OSXSAVE);
fpu__xstate_clear_all_cpu_caps();
}
@@ -742,15 +738,15 @@ void __init fpu__init_system_xstate(void)
}
cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
- xfeatures_mask = eax + ((u64)edx << 32);
+ xfeatures_mask_user = eax + ((u64)edx << 32);
- if ((xfeatures_mask & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
+ if ((xfeatures_mask_user & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
/*
* This indicates that something really unexpected happened
* with the enumeration. Disable XSAVE and try to continue
* booting without it. This is too early to BUG().
*/
- pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask);
+ pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask_user);
goto out_disable;
}
@@ -759,10 +755,10 @@ void __init fpu__init_system_xstate(void)
*/
for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) {
if (!boot_cpu_has(xsave_cpuid_features[i]))
- xfeatures_mask &= ~BIT(i);
+ xfeatures_mask_user &= ~BIT_ULL(i);
}
- xfeatures_mask &= fpu__get_supported_xfeatures_mask();
+ xfeatures_mask_user &= fpu__get_supported_xfeatures_mask();
/* Enable xstate instructions to be able to continue with initialization: */
fpu__init_cpu_xstate();
@@ -772,9 +768,9 @@ void __init fpu__init_system_xstate(void)
/*
* Update info used for ptrace frames; use standard-format size and no
- * supervisor xstates:
+ * system xstates:
*/
- update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR);
+ update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask_user & ~XFEATURE_MASK_SUPERVISOR);
fpu__init_prepare_fx_sw_frame();
setup_init_fpu_buf();
@@ -782,7 +778,7 @@ void __init fpu__init_system_xstate(void)
print_xstate_offset_size();
pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
- xfeatures_mask,
+ xfeatures_mask_user,
fpu_kernel_xstate_size,
boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard");
return;
@@ -801,7 +797,7 @@ 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);
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user);
}
/*
@@ -853,7 +849,7 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
* have not enabled. Remember that pcntxt_mask is
* what we write to the XCR0 register.
*/
- WARN_ONCE(!(xfeatures_mask & xstate_feature),
+ WARN_ONCE(!(xfeatures_mask_user & xstate_feature),
"get of unsupported state");
/*
* This assumes the last 'xsave*' instruction to
--
2.17.1
^ permalink raw reply related
* [PATCH v5 01/27] x86/cpufeatures: Add CPUIDs for Control Flow Enforcement Technology (CET)
From: Yu-cheng Yu @ 2018-10-11 15:14 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Cyrill Gorcunov, Dave Hansen,
Eugene Syromiatnikov, Florian Weimer, H.J. Lu, Jann Horn,
Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pa
Cc: Yu-cheng Yu
In-Reply-To: <20181011151523.27101-1-yu-cheng.yu@intel.com>
Add CPUIDs for Control Flow Enforcement Technology (CET).
CPUID.(EAX=7,ECX=0):ECX[bit 7] Shadow stack
CPUID.(EAX=7,ECX=0):EDX[bit 20] Indirect branch tracking
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
arch/x86/include/asm/cpufeatures.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 89a048c2faec..142b15da06fd 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -321,6 +321,7 @@
#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */
#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
+#define X86_FEATURE_SHSTK (16*32+ 7) /* Shadow Stack */
#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */
#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */
#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* Carry-Less Multiplication Double Quadword */
@@ -341,6 +342,7 @@
#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
+#define X86_FEATURE_IBT (18*32+20) /* Indirect Branch Tracking */
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
#define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */
--
2.17.1
^ permalink raw reply related
* [PATCH v5 00/27] Control Flow Enforcement: Shadow Stack
From: Yu-cheng Yu @ 2018-10-11 15:14 UTC (permalink / raw)
To: x86, H. Peter Anvin, Thomas Gleixner, Ingo Molnar, linux-kernel,
linux-doc, linux-mm, linux-arch, linux-api, Arnd Bergmann,
Andy Lutomirski, Balbir Singh, Cyrill Gorcunov, Dave Hansen,
Eugene Syromiatnikov, Florian Weimer, H.J. Lu, Jann Horn,
Jonathan Corbet, Kees Cook, Mike Kravetz, Nadav Amit,
Oleg Nesterov, Pa
Cc: Yu-cheng Yu
The previous version of CET Shadow Stack patches is at the following
link:
https://lkml.org/lkml/2018/9/21/776
Summary of changes from v4:
Clean up XSAVES system states patches.
Update control protection fault handler to provide error code to user.
Add CONFIG_VM_AREA_GUARD.
Clean up arch_prctl.
Fix some typos and macros.
Yu-cheng Yu (27):
x86/cpufeatures: Add CPUIDs for Control Flow Enforcement Technology
(CET)
x86/fpu/xstate: Change names to separate XSAVES system and user states
x86/fpu/xstate: Introduce XSAVES system states
x86/fpu/xstate: Add XSAVES system states for shadow stack
Documentation/x86: Add CET description
x86/cet: Control protection exception handler
mm/mmap: Create a guard area between VMAs
x86/cet/shstk: Add Kconfig option for user-mode shadow stack
mm: Introduce VM_SHSTK for shadow stack memory
mm/mmap: Prevent Shadow Stack VMA merges
x86/mm: Change _PAGE_DIRTY to _PAGE_DIRTY_HW
x86/mm: Introduce _PAGE_DIRTY_SW
drm/i915/gvt: Update _PAGE_DIRTY to _PAGE_DIRTY_BITS
x86/mm: Modify ptep_set_wrprotect and pmdp_set_wrprotect for
_PAGE_DIRTY_SW
x86/mm: Shadow stack page fault error checking
mm: Handle shadow stack page fault
mm: Handle THP/HugeTLB shadow stack page fault
mm: Update can_follow_write_pte/pmd for shadow stack
mm: Introduce do_mmap_locked()
x86/cet/shstk: User-mode shadow stack support
x86/cet/shstk: Introduce WRUSS instruction
x86/cet/shstk: Signal handling for shadow stack
x86/cet/shstk: ELF header parsing of Shadow Stack
x86/cet/shstk: Handle thread shadow stack
mm/mmap: Add Shadow stack pages to memory accounting
x86/cet/shstk: Add arch_prctl functions for Shadow Stack
x86/cet/shstk: Add Shadow Stack instructions to opcode map
.../admin-guide/kernel-parameters.txt | 6 +
Documentation/index.rst | 1 +
Documentation/x86/index.rst | 11 +
Documentation/x86/intel_cet.rst | 266 ++++++++++++++
arch/x86/Kconfig | 30 ++
arch/x86/Makefile | 7 +
arch/x86/entry/entry_64.S | 2 +-
arch/x86/ia32/ia32_signal.c | 13 +
arch/x86/include/asm/cet.h | 46 +++
arch/x86/include/asm/cpufeatures.h | 2 +
arch/x86/include/asm/disabled-features.h | 8 +-
arch/x86/include/asm/elf.h | 5 +
arch/x86/include/asm/fpu/internal.h | 5 +-
arch/x86/include/asm/fpu/types.h | 22 ++
arch/x86/include/asm/fpu/xstate.h | 26 +-
arch/x86/include/asm/mmu_context.h | 3 +
arch/x86/include/asm/msr-index.h | 14 +
arch/x86/include/asm/pgtable.h | 191 ++++++++--
arch/x86/include/asm/pgtable_types.h | 38 +-
arch/x86/include/asm/processor.h | 5 +
arch/x86/include/asm/sighandling.h | 5 +
arch/x86/include/asm/special_insns.h | 32 ++
arch/x86/include/asm/traps.h | 5 +
arch/x86/include/uapi/asm/elf_property.h | 15 +
arch/x86/include/uapi/asm/prctl.h | 5 +
arch/x86/include/uapi/asm/processor-flags.h | 2 +
arch/x86/include/uapi/asm/sigcontext.h | 15 +
arch/x86/kernel/Makefile | 4 +
arch/x86/kernel/cet.c | 298 +++++++++++++++
arch/x86/kernel/cet_prctl.c | 86 +++++
arch/x86/kernel/cpu/common.c | 25 ++
arch/x86/kernel/elf.c | 341 ++++++++++++++++++
arch/x86/kernel/fpu/core.c | 10 +-
arch/x86/kernel/fpu/init.c | 10 -
arch/x86/kernel/fpu/signal.c | 6 +-
arch/x86/kernel/fpu/xstate.c | 146 +++++---
arch/x86/kernel/idt.c | 4 +
arch/x86/kernel/process.c | 7 +-
arch/x86/kernel/process_64.c | 7 +
arch/x86/kernel/relocate_kernel_64.S | 2 +-
arch/x86/kernel/signal.c | 97 +++++
arch/x86/kernel/signal_compat.c | 2 +-
arch/x86/kernel/traps.c | 64 ++++
arch/x86/kvm/vmx.c | 2 +-
arch/x86/lib/x86-opcode-map.txt | 26 +-
arch/x86/mm/fault.c | 27 ++
arch/x86/mm/pgtable.c | 41 +++
drivers/gpu/drm/i915/gvt/gtt.c | 2 +-
fs/binfmt_elf.c | 15 +
fs/proc/task_mmu.c | 3 +
include/asm-generic/pgtable.h | 14 +
include/linux/mm.h | 56 ++-
include/uapi/asm-generic/siginfo.h | 3 +-
include/uapi/linux/elf.h | 1 +
mm/Kconfig | 7 +
mm/gup.c | 8 +-
mm/huge_memory.c | 12 +-
mm/memory.c | 7 +-
mm/mmap.c | 11 +
tools/objtool/arch/x86/lib/x86-opcode-map.txt | 26 +-
60 files changed, 1986 insertions(+), 164 deletions(-)
create mode 100644 Documentation/x86/index.rst
create mode 100644 Documentation/x86/intel_cet.rst
create mode 100644 arch/x86/include/asm/cet.h
create mode 100644 arch/x86/include/uapi/asm/elf_property.h
create mode 100644 arch/x86/kernel/cet.c
create mode 100644 arch/x86/kernel/cet_prctl.c
create mode 100644 arch/x86/kernel/elf.c
--
2.17.1
^ permalink raw reply
* Re: [RFC PATCH for 4.21 01/16] rseq/selftests: Add reference counter to coexist with glibc
From: Mathieu Desnoyers @ 2018-10-11 15:13 UTC (permalink / raw)
To: Szabolcs Nagy
Cc: Peter Zijlstra, Paul E. McKenney, Boqun Feng, nd, linux-kernel,
linux-api, Thomas Gleixner, Andy Lutomirski, Dave Watson,
Paul Turner, Andrew Morton, Russell King, Ingo Molnar,
H. Peter Anvin, Andi Kleen, Chris Lameter, Ben Maurer, rostedt,
Josh Triplett, Linus Torvalds, Catalin Marinas
In-Reply-To: <38596780-30f7-0763-0c17-7517dbf0bf59@arm.com>
----- On Oct 11, 2018, at 6:37 AM, Szabolcs Nagy Szabolcs.Nagy@arm.com wrote:
> On 10/10/18 20:19, Mathieu Desnoyers wrote:
>> In order to integrate rseq into user-space applications, add a reference
>> counter field after the struct rseq TLS ABI so many rseq users can be
>> linked into the same application (e.g. librseq and glibc). The
>> reference count ensures that rseq syscall registration/unregistration
>> happens only for the most early/late user for each thread, thus ensuring
>> that rseq is registered across the lifetime of all rseq users for a
>> given thread.
> ...
>> +__attribute__((visibility("hidden"))) __thread
>> +volatile struct libc_rseq __lib_rseq_abi = {
> ...
>> +extern __attribute__((weak, alias("__lib_rseq_abi"))) __thread
>> +volatile struct rseq __rseq_abi;
> ...
>> @@ -70,7 +86,7 @@ int rseq_register_current_thread(void)
>> sigset_t oldset;
>>
>> signal_off_save(&oldset);
>> - if (refcount++)
>> + if (__lib_rseq_abi.refcount++)
>> goto end;
>> rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), 0, RSEQ_SIG);
>
> why do you use a local refcounter instead of the __rseq_abi one?
There is no refcount in struct rseq (the ABI between kernel and user-space).
The registration refcount was part of an earlier version of the rseq system call,
but we decided against keeping it in the kernel.
So I'm adding one _after_ struct rseq, purely to allow interaction between
various user-space components (program/libraries).
>
> what prevents calling rseq_register_current_thread more than 4G times?
Nothing. It would indeed be cleaner to error out if we detect that refcount is at
INT_MAX. Is that what you have in mind ?
>
> why cant the kernel see that the same address is registered again and succeed?
It can, and it does. However, refcounting at user-level is needed to ensure
the registration "lifetime" for rseq covers its entire use. If we have two libraries
using rseq, we end up with the following scenario:
Thread 1
libA registers rseq
libB registers rseq
libB unregisters rseq
libA uses rseq -> bug! it's been unregistered by libB.
libA unregisters rseq -> unexpected, it's already been unregistered.
same applies if libA unregisters rseq before libB (and libB try to use rseq
after libA has unregistered).
The refcount in user-space fixes this.
Thoughts ?
Thanks,
Mathieu
--
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com
^ permalink raw reply
* Re: [PATCH v7 3/6] seccomp: add a way to get a listener fd from ptrace
From: Jann Horn @ 2018-10-11 13:39 UTC (permalink / raw)
To: Paul Moore
Cc: christian, Tycho Andersen, Kees Cook, Linux API, containers,
suda.akihiro, Oleg Nesterov, kernel list, Eric W. Biederman,
linux-fsdevel, Christian Brauner, Andy Lutomirski,
linux-security-module, selinux, Stephen Smalley, Eric Paris
In-Reply-To: <16662034750.2781.85c95baa4474aabc7814e68940a78392@paul-moore.com>
On Thu, Oct 11, 2018 at 9:24 AM Paul Moore <paul@paul-moore.com> wrote:
> On October 10, 2018 11:34:11 AM Jann Horn <jannh@google.com> wrote:
> > On Wed, Oct 10, 2018 at 5:32 PM Paul Moore <paul@paul-moore.com> wrote:
> >> On Tue, Oct 9, 2018 at 9:36 AM Jann Horn <jannh@google.com> wrote:
> >>> +cc selinux people explicitly, since they probably have opinions on this
> >>
> >> I just spent about twenty minutes working my way through this thread,
> >> and digging through the containers archive trying to get a good
> >> understanding of what you guys are trying to do, and I'm not quite
> >> sure I understand it all. However, from what I have seen, this
> >> approach looks very ptrace-y to me (I imagine to others as well based
> >> on the comments) and because of this I think ensuring the usual ptrace
> >> access controls are evaluated, including the ptrace LSM hooks, is the
> >> right thing to do.
> >
> > Basically the problem is that this new ptrace() API does something
> > that doesn't just influence the target task, but also every other task
> > that has the same seccomp filter. So the classic ptrace check doesn't
> > work here.
>
> Due to some rather unfortunate events today I'm suddenly without easy access to the kernel code, but would it be possible to run the LSM ptrace access control checks against all of the affected tasks? If it is possible, how painful would it be?
There are currently no backlinks from seccomp filters to the tasks
that use them; the only thing you have is a refcount. If the refcount
is 1, and the target task uses the filter directly (it is the last
installed one), you'd be able to infer that the ptrace target is the
only task with a reference to the filter, and you could just do the
direct check; but if the refcount is >1, you might end up having to
take some spinlock and then iterate over all tasks' filters with that
spinlock held, or something like that.
^ permalink raw reply
* Re: [RFC PATCH for 4.21 01/16] rseq/selftests: Add reference counter to coexist with glibc
From: Szabolcs Nagy @ 2018-10-11 10:37 UTC (permalink / raw)
To: Mathieu Desnoyers, Peter Zijlstra, Paul E . McKenney, Boqun Feng
Cc: nd, linux-kernel@vger.kernel.org, linux-api@vger.kernel.org,
Thomas Gleixner, Andy Lutomirski, Dave Watson, Paul Turner,
Andrew Morton, Russell King, Ingo Molnar, H . Peter Anvin,
Andi Kleen, Chris Lameter, Ben Maurer, Steven Rostedt,
Josh Triplett, Linus Torvalds, Catalin Marinas, Will Deacon,
Michael Kerrisk
In-Reply-To: <20181010191936.7495-2-mathieu.desnoyers@efficios.com>
On 10/10/18 20:19, Mathieu Desnoyers wrote:
> In order to integrate rseq into user-space applications, add a reference
> counter field after the struct rseq TLS ABI so many rseq users can be
> linked into the same application (e.g. librseq and glibc). The
> reference count ensures that rseq syscall registration/unregistration
> happens only for the most early/late user for each thread, thus ensuring
> that rseq is registered across the lifetime of all rseq users for a
> given thread.
...
> +__attribute__((visibility("hidden"))) __thread
> +volatile struct libc_rseq __lib_rseq_abi = {
...
> +extern __attribute__((weak, alias("__lib_rseq_abi"))) __thread
> +volatile struct rseq __rseq_abi;
...
> @@ -70,7 +86,7 @@ int rseq_register_current_thread(void)
> sigset_t oldset;
>
> signal_off_save(&oldset);
> - if (refcount++)
> + if (__lib_rseq_abi.refcount++)
> goto end;
> rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), 0, RSEQ_SIG);
why do you use a local refcounter instead of the __rseq_abi one?
what prevents calling rseq_register_current_thread more than 4G times?
why cant the kernel see that the same address is registered again and succeed?
^ permalink raw reply
* Re: [PATCH v7 3/6] seccomp: add a way to get a listener fd from ptrace
From: Paul Moore @ 2018-10-11 7:24 UTC (permalink / raw)
To: Jann Horn
Cc: christian, Tycho Andersen, Kees Cook, Linux API, containers,
suda.akihiro, Oleg Nesterov, kernel list, Eric W. Biederman,
linux-fsdevel, Christian Brauner, Andy Lutomirski,
linux-security-module, selinux, Stephen Smalley, Eric Paris
In-Reply-To: <CAG48ez2hTBFwmA65FXv0zJjc0_wpc1S-uOBn1t+X=0vPH25YvQ@mail.gmail.com>
On October 10, 2018 11:34:11 AM Jann Horn <jannh@google.com> wrote:
> On Wed, Oct 10, 2018 at 5:32 PM Paul Moore <paul@paul-moore.com> wrote:
>> On Tue, Oct 9, 2018 at 9:36 AM Jann Horn <jannh@google.com> wrote:
>>> +cc selinux people explicitly, since they probably have opinions on this
>>
>> I just spent about twenty minutes working my way through this thread,
>> and digging through the containers archive trying to get a good
>> understanding of what you guys are trying to do, and I'm not quite
>> sure I understand it all. However, from what I have seen, this
>> approach looks very ptrace-y to me (I imagine to others as well based
>> on the comments) and because of this I think ensuring the usual ptrace
>> access controls are evaluated, including the ptrace LSM hooks, is the
>> right thing to do.
>
> Basically the problem is that this new ptrace() API does something
> that doesn't just influence the target task, but also every other task
> that has the same seccomp filter. So the classic ptrace check doesn't
> work here.
Due to some rather unfortunate events today I'm suddenly without easy access to the kernel code, but would it be possible to run the LSM ptrace access control checks against all of the affected tasks? If it is possible, how painful would it be?
>
>> If I've missed something, or I'm thinking about this wrong, please
>> educate me; just a heads-up that I'm largely offline for most of this
>> week so responses on my end are going to be delayed much more than
>> usual.
>>
>>> On Tue, Oct 9, 2018 at 3:29 PM Christian Brauner <christian@brauner.io> wrote:
>>>> On Tue, Oct 09, 2018 at 02:39:53PM +0200, Jann Horn wrote:
>>>>> On Mon, Oct 8, 2018 at 8:18 PM Christian Brauner <christian@brauner.io> wrote:
>>>>>> On Mon, Oct 08, 2018 at 06:42:00PM +0200, Jann Horn wrote:
>>>>>>> On Mon, Oct 8, 2018 at 6:21 PM Christian Brauner <christian@brauner.io> wrote:
>>>>>>> > On Mon, Oct 08, 2018 at 05:33:22PM +0200, Jann Horn wrote:
>>>>>>> > > On Mon, Oct 8, 2018 at 5:16 PM Christian Brauner <christian@brauner.io> wrote:
>>>>>>> > > > On Thu, Sep 27, 2018 at 09:11:16AM -0600, Tycho Andersen wrote:
>>>>>>> > > > > diff --git a/kernel/seccomp.c b/kernel/seccomp.c
>>>>>>> > > > > index 44a31ac8373a..17685803a2af 100644
>>>>>>> > > > > --- a/kernel/seccomp.c
>>>>>>> > > > > +++ b/kernel/seccomp.c
>>>>>>> > > > > @@ -1777,4 +1777,35 @@ static struct file *init_listener(struct task_struct *task,
>>>>>>> > > > >
>>>>>>> > > > > return ret;
>>>>>>> > > > > }
>>>>>>> > > > > +
>>>>>>> > > > > +long seccomp_new_listener(struct task_struct *task,
>>>>>>> > > > > + unsigned long filter_off)
>>>>>>> > > > > +{
>>>>>>> > > > > + struct seccomp_filter *filter;
>>>>>>> > > > > + struct file *listener;
>>>>>>> > > > > + int fd;
>>>>>>> > > > > +
>>>>>>> > > > > + if (!capable(CAP_SYS_ADMIN))
>>>>>>> > > > > + return -EACCES;
>>>>>>> > > >
>>>>>>> > > > I know this might have been discussed a while back but why exactly do we
>>>>>>> > > > require CAP_SYS_ADMIN in init_userns and not in the target userns? What
>>>>>>> > > > if I want to do a setns()fd, CLONE_NEWUSER) to the target process and
>>>>>>> > > > use ptrace from in there?
>>>>>>> > >
>>>>>>> > > See https://lore.kernel.org/lkml/CAG48ez3R+ZJ1vwGkDfGzKX2mz6f=jjJWsO5pCvnH68P+RKO8Ow@mail.gmail.com/
>>>>>>> > > . Basically, the problem is that this doesn't just give you capability
>>>>>>> > > over the target task, but also over every other task that has the same
>>>>>>> > > filter installed; you need some sort of "is the caller capable over
>>>>>>> > > the filter and anyone who uses it" check.
>>>>>>> >
>>>>>>> > Thanks.
>>>>>>> > But then this new ptrace feature as it stands is imho currently broken.
>>>>>>> > If you can install a seccomp filter with SECCOMP_RET_USER_NOTIF if you
>>>>>>> > are ns_cpabable(CAP_SYS_ADMIN) and also get an fd via seccomp() itself
>>>>>>> > if you are ns_cpabable(CAP_SYS_ADMIN)
>>>>>
>>>>> Actually, you don't need CAP_SYS_ADMIN for seccomp() at all as long as
>>>>> you enable the NNP flag, I think?
>>>>
>>>> Yes, if you turn on NNP you don't even need sys_admin.
>>>>
>>>>>
>>>>>>> > then either the new ptrace() api
>>>>>>> > extension should be fixed to allow for this too or the seccomp() way of
>>>>>>> > retrieving the pid - which I really think we want - needs to be fixed to
>>>>>>> > require capable(CAP_SYS_ADMIN) too.
>>>>>>> > The solution where both require ns_capable(CAP_SYS_ADMIN) is - imho -
>>>>>>> > the preferred way to solve this.
>>>>>>> > Everything else will just be confusing.
>>>>>>>
>>>>>>> First you say "broken", then you say "confusing". Which one do you mean?
>>>>>>
>>>>>> Both. It's broken in so far as it places a seemingly unnecessary
>>>>>> restriction that could be fixed. You outlined one possible fix yourself
>>>>>> in the link you provided.
>>>>>
>>>>> If by "possible fix" you mean "check whether the seccomp filter is
>>>>> only attached to a single task": That wouldn't fundamentally change
>>>>> the situation, it would only add an additional special case.
>>>>>
>>>>>> And it's confusing in so far as there is a way
>>>>>> via seccomp() to get the fd without said requirement.
>>>>>
>>>>> I don't find it confusing at all. seccomp() and ptrace() are very
>>>>
>>>> Fine, then that's a matter of opinion. I find it counterintuitive that
>>>> you can get an fd without privileges via one interface but not via
>>>> another.
>>>>
>>>>> different situations: When you use seccomp(), infrastructure is
>>>>
>>>> Sure. Note, that this is _one_ of the reasons why I want to make sure we
>>>> keep the native seccomp() only based way of getting an fd without
>>>> forcing userspace to switching to a differnet kernel api.
>>>>
>>>>> already in place for ensuring that your filter is only applied to
>>>>> processes over which you are capable, and propagation is limited by
>>>>> inheritance from your task down. When you use ptrace(), you need a
>>>>> pretty different sort of access check that checks whether you're
>>>>> privileged over ancestors, siblings and so on of the target task.
>>>>
>>>> So, don't get me wrong I'm not arguing against the ptrace() interface in
>>>> general. If this is something that people find useful, fine. But, I
>>>> would like to have a simple single-syscall pure-seccomp() based way of
>>>> getting an fd, i.e. what we have in patch 1 of this series.
>>>
>>> Yeah, I also prefer the seccomp() one.
>>>
>>>>> But thinking about it more, I think that CAP_SYS_ADMIN over the saved
>>>>> current->mm->user_ns of the task that installed the filter (stored as
>>>>> a "struct user_namespace *" in the filter) should be acceptable.
>>>>
>>>> Hm... Why not CAP_SYS_PTRACE?
>>>
>>> Because LSMs like SELinux add extra checks that apply even if you have
>>> CAP_SYS_PTRACE, and this would subvert those. The only capability I
>>> know of that lets you bypass LSM checks by design (if no LSM blocks
>>> the capability itself) is CAP_SYS_ADMIN.
>>>
>>>> One more thing. Citing from [1]
>>>>
>>>>> I think there's a security problem here. Imagine the following scenario:
>>>>>
>>>>> 1. task A (uid==0) sets up a seccomp filter that uses SECCOMP_RET_USER_NOTIF
>>>>> 2. task A forks off a child B
>>>>> 3. task B uses setuid(1) to drop its privileges
>>>>> 4. task B becomes dumpable again, either via prctl(PR_SET_DUMPABLE, 1)
>>>>> or via execve()
>>>>> 5. task C (the attacker, uid==1) attaches to task B via ptrace
>>>>> 6. task C uses PTRACE_SECCOMP_NEW_LISTENER on task B
>>>>
>>>> Sorry, to be late to the party but would this really pass
>>>> __ptrace_may_access() in ptrace_attach()? It doesn't seem obvious to me
>>>> that it would... Doesn't look like it would get past:
>>>>
>>>> tcred = __task_cred(task);
>>>> if (uid_eq(caller_uid, tcred->euid) &&
>>>> uid_eq(caller_uid, tcred->suid) &&
>>>> uid_eq(caller_uid, tcred->uid) &&
>>>> gid_eq(caller_gid, tcred->egid) &&
>>>> gid_eq(caller_gid, tcred->sgid) &&
>>>> gid_eq(caller_gid, tcred->gid))
>>>> goto ok;
>>>> if (ptrace_has_cap(tcred->user_ns, mode))
>>>> goto ok;
>>>> rcu_read_unlock();
>>>> return -EPERM;
>>>> ok:
>>>> rcu_read_unlock();
>>>> mm = task->mm;
>>>> if (mm &&
>>>> ((get_dumpable(mm) != SUID_DUMP_USER) &&
>>>> !ptrace_has_cap(mm->user_ns, mode)))
>>>> return -EPERM;
>>>
>>> Which specific check would prevent task C from attaching to task B? If
>>> the UIDs match, the first "goto ok" executes; and you're dumpable, so
>>> you don't trigger the second "return -EPERM".
>>>
>>>>> 7. because the seccomp filter is shared by task A and task B, task C
>>>>> is now able to influence syscall results for syscalls performed by
>>>>> task A
>>>>
>>>> [1]: https://lore.kernel.org/lkml/CAG48ez3R+ZJ1vwGkDfGzKX2mz6f=jjJWsO5pCvnH68P+RKO8Ow@mail.gmail.com/
>>
>>
>>
>> --
>> paul moore
>> www.paul-moore.com
^ permalink raw reply
* [RFC PATCH for 4.21 16/16] cpu-opv/selftests: Provide Makefile, scripts, gitignore
From: Mathieu Desnoyers @ 2018-10-10 19:19 UTC (permalink / raw)
To: Peter Zijlstra, Paul E . McKenney, Boqun Feng
Cc: linux-kernel, linux-api, Thomas Gleixner, Andy Lutomirski,
Dave Watson, Paul Turner, Andrew Morton, Russell King,
Ingo Molnar, H . Peter Anvin, Andi Kleen, Chris Lameter,
Ben Maurer, Steven Rostedt, Josh Triplett, Linus Torvalds,
Catalin Marinas, Will Deacon, Michael Kerrisk, Joel Fernandes,
Mathieu Desnoyers
In-Reply-To: <20181010191936.7495-1-mathieu.desnoyers@efficios.com>
A run_param_test.sh script runs many variants of the parametrizable
tests.
Wire up the cpu-opv Makefile, add directory entry into MAINTAINERS file.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
MAINTAINERS | 1 +
tools/testing/selftests/Makefile | 1 +
tools/testing/selftests/cpu-opv/.gitignore | 6 +
tools/testing/selftests/cpu-opv/Makefile | 39 +++++++
tools/testing/selftests/cpu-opv/run_param_test.sh | 134 ++++++++++++++++++++++
5 files changed, 181 insertions(+)
create mode 100644 tools/testing/selftests/cpu-opv/.gitignore
create mode 100644 tools/testing/selftests/cpu-opv/Makefile
create mode 100755 tools/testing/selftests/cpu-opv/run_param_test.sh
diff --git a/MAINTAINERS b/MAINTAINERS
index 3b50578fc5d9..206fe4597697 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3864,6 +3864,7 @@ L: linux-kernel@vger.kernel.org
S: Supported
F: kernel/cpu_opv.c
F: include/uapi/linux/cpu_opv.h
+F: tools/testing/selftests/cpu-opv/
CRAMFS FILESYSTEM
M: Nicolas Pitre <nico@linaro.org>
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index f1fe492c8e17..42bcc6e5fc5d 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -6,6 +6,7 @@ TARGETS += capabilities
TARGETS += cgroup
TARGETS += cpufreq
TARGETS += cpu-hotplug
+TARGETS += cpu-opv
TARGETS += efivarfs
TARGETS += exec
TARGETS += filesystems
diff --git a/tools/testing/selftests/cpu-opv/.gitignore b/tools/testing/selftests/cpu-opv/.gitignore
new file mode 100644
index 000000000000..8c7bb1f8be79
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/.gitignore
@@ -0,0 +1,6 @@
+basic_cpu_opv_test
+basic_percpu_ops_test
+param_test
+param_test_benchmark
+param_test_compare_twice
+param_test_skip_fastpath
diff --git a/tools/testing/selftests/cpu-opv/Makefile b/tools/testing/selftests/cpu-opv/Makefile
new file mode 100644
index 000000000000..46f49bf30bae
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/Makefile
@@ -0,0 +1,39 @@
+# SPDX-License-Identifier: GPL-2.0+ OR MIT
+CFLAGS += -O2 -Wall -g -I./ -I../rseq/ -I../../../../usr/include/ -L./ -Wl,-rpath=./
+LDLIBS += -lpthread
+
+# Own dependencies because we only want to build against 1st prerequisite, but
+# still track changes to header files and depend on shared object.
+OVERRIDE_TARGETS = 1
+
+TEST_GEN_PROGS = basic_cpu_opv_test basic_percpu_ops_test \
+ param_test param_test_skip_fastpath \
+ param_test_benchmark param_test_compare_twice
+
+TEST_GEN_PROGS_EXTENDED = librseq.so libcpu-op.so
+
+TEST_PROGS = run_param_test.sh
+
+include ../lib.mk
+
+$(OUTPUT)/libcpu-op.so: cpu-op.c cpu-op.h
+ $(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@
+
+$(OUTPUT)/librseq.so: ../rseq/rseq.c ../rseq/rseq.h ../rseq/rseq-*.h
+ $(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@
+
+$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) ../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h
+ $(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -lcpu-op -o $@
+
+$(OUTPUT)/param_test_skip_fastpath: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+ ../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h
+ $(CC) $(CFLAGS) -DRSEQ_SKIP_FASTPATH $< $(LDLIBS) -lrseq -lcpu-op -o $@
+
+$(OUTPUT)/param_test_benchmark: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+ ../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h
+ $(CC) $(CFLAGS) -DBENCHMARK $< $(LDLIBS) -lrseq -lcpu-op -o $@
+
+$(OUTPUT)/param_test_compare_twice: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+ ../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h
+ $(CC) $(CFLAGS) -DRSEQ_COMPARE_TWICE $< $(LDLIBS) -lrseq -lcpu-op -o $@
+
diff --git a/tools/testing/selftests/cpu-opv/run_param_test.sh b/tools/testing/selftests/cpu-opv/run_param_test.sh
new file mode 100755
index 000000000000..066d2479893c
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/run_param_test.sh
@@ -0,0 +1,134 @@
+#!/bin/bash
+
+NR_CPUS=`grep '^processor' /proc/cpuinfo | wc -l`
+
+EXTRA_ARGS=${@}
+
+OLDIFS="$IFS"
+IFS=$'\n'
+TEST_LIST=(
+ "-T s"
+ "-T l"
+ "-T b"
+ "-T b -M"
+ "-T m"
+ "-T m -M"
+ "-T i"
+)
+
+TEST_NAME=(
+ "spinlock"
+ "list"
+ "buffer"
+ "buffer with barrier"
+ "memcpy"
+ "memcpy with barrier"
+ "increment"
+)
+IFS="$OLDIFS"
+
+REPS=1000
+SLOW_REPS=100
+NR_THREADS=$((6*${NR_CPUS}))
+
+function do_tests()
+{
+ local i=0
+ while [ "$i" -lt "${#TEST_LIST[@]}" ]; do
+ echo "Running test ${TEST_NAME[$i]}"
+ ./param_test ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
+ echo "Running skip fast-path test ${TEST_NAME[$i]}"
+ ./param_test_skip_fastpath ${TEST_LIST[$i]} -r ${SLOW_REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
+ echo "Running compare-twice test ${TEST_NAME[$i]}"
+ ./param_test_compare_twice ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
+ let "i++"
+ done
+}
+
+echo "Default parameters"
+do_tests
+
+echo "Loop injection: 10000 loops"
+
+OLDIFS="$IFS"
+IFS=$'\n'
+INJECT_LIST=(
+ "1"
+ "2"
+ "3"
+ "4"
+ "5"
+ "6"
+ "7"
+ "8"
+ "9"
+)
+IFS="$OLDIFS"
+
+NR_LOOPS=10000
+
+i=0
+while [ "$i" -lt "${#INJECT_LIST[@]}" ]; do
+ echo "Injecting at <${INJECT_LIST[$i]}>"
+ do_tests -${INJECT_LIST[i]} ${NR_LOOPS}
+ let "i++"
+done
+NR_LOOPS=
+
+function inject_blocking()
+{
+ OLDIFS="$IFS"
+ IFS=$'\n'
+ INJECT_LIST=(
+ "7"
+ "8"
+ "9"
+ )
+ IFS="$OLDIFS"
+
+ NR_LOOPS=-1
+
+ i=0
+ while [ "$i" -lt "${#INJECT_LIST[@]}" ]; do
+ echo "Injecting at <${INJECT_LIST[$i]}>"
+ do_tests -${INJECT_LIST[i]} -1 ${@}
+ let "i++"
+ done
+ NR_LOOPS=
+}
+
+echo "Yield injection (25%)"
+inject_blocking -m 4 -y
+
+echo "Yield injection (50%)"
+inject_blocking -m 2 -y
+
+echo "Yield injection (100%)"
+inject_blocking -m 1 -y
+
+echo "Kill injection (25%)"
+inject_blocking -m 4 -k
+
+echo "Kill injection (50%)"
+inject_blocking -m 2 -k
+
+echo "Kill injection (100%)"
+inject_blocking -m 1 -k
+
+echo "Sleep injection (1ms, 25%)"
+inject_blocking -m 4 -s 1
+
+echo "Sleep injection (1ms, 50%)"
+inject_blocking -m 2 -s 1
+
+echo "Sleep injection (1ms, 100%)"
+inject_blocking -m 1 -s 1
+
+echo "Disable rseq for 25% threads"
+do_tests -D 4
+
+echo "Disable rseq for 50% threads"
+do_tests -D 2
+
+echo "Disable rseq"
+do_tests -d
--
2.11.0
^ permalink raw reply related
* [RFC PATCH for 4.21 15/16] cpu-opv/selftests: Provide parametrized tests
From: Mathieu Desnoyers @ 2018-10-10 19:19 UTC (permalink / raw)
To: Peter Zijlstra, Paul E . McKenney, Boqun Feng
Cc: linux-kernel, linux-api, Thomas Gleixner, Andy Lutomirski,
Dave Watson, Paul Turner, Andrew Morton, Russell King,
Ingo Molnar, H . Peter Anvin, Andi Kleen, Chris Lameter,
Ben Maurer, Steven Rostedt, Josh Triplett, Linus Torvalds,
Catalin Marinas, Will Deacon, Michael Kerrisk, Joel Fernandes,
Mathieu Desnoyers
In-Reply-To: <20181010191936.7495-1-mathieu.desnoyers@efficios.com>
"param_test" is a parametrizable percpu operations test using
both restartable sequences and cpu_opv. See the "--help" output for
usage.
"param_test_benchmark" is the same as "param_test", but it removes
testing book-keeping code to allow accurate benchmarks.
"param_test_compare_twice" is the same as "param_test", but it performs
each comparison within rseq critical section twice, thus validating
invariants. If any of the second comparisons fails, an error message
is printed and the test aborts.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
tools/testing/selftests/cpu-opv/param_test.c | 1187 ++++++++++++++++++++++++++
1 file changed, 1187 insertions(+)
create mode 100644 tools/testing/selftests/cpu-opv/param_test.c
diff --git a/tools/testing/selftests/cpu-opv/param_test.c b/tools/testing/selftests/cpu-opv/param_test.c
new file mode 100644
index 000000000000..c62e75f07385
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/param_test.c
@@ -0,0 +1,1187 @@
+// SPDX-License-Identifier: LGPL-2.1
+#define _GNU_SOURCE
+#include <assert.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <unistd.h>
+#include <poll.h>
+#include <sys/types.h>
+#include <signal.h>
+#include <errno.h>
+#include <stddef.h>
+
+static inline pid_t gettid(void)
+{
+ return syscall(__NR_gettid);
+}
+
+#define NR_INJECT 9
+static int loop_cnt[NR_INJECT + 1];
+
+static int loop_cnt_1 asm("asm_loop_cnt_1") __attribute__((used));
+static int loop_cnt_2 asm("asm_loop_cnt_2") __attribute__((used));
+static int loop_cnt_3 asm("asm_loop_cnt_3") __attribute__((used));
+static int loop_cnt_4 asm("asm_loop_cnt_4") __attribute__((used));
+static int loop_cnt_5 asm("asm_loop_cnt_5") __attribute__((used));
+static int loop_cnt_6 asm("asm_loop_cnt_6") __attribute__((used));
+
+static int opt_modulo, verbose;
+
+static int opt_yield, opt_signal, opt_sleep,
+ opt_disable_rseq, opt_threads = 200,
+ opt_disable_mod = 0, opt_test = 's', opt_mb = 0;
+
+#ifndef RSEQ_SKIP_FASTPATH
+static long long opt_reps = 5000;
+#else
+static long long opt_reps = 100;
+#endif
+
+static __thread __attribute__((tls_model("initial-exec")))
+unsigned int signals_delivered;
+
+#ifndef BENCHMARK
+
+static __thread __attribute__((tls_model("initial-exec"), unused))
+unsigned int yield_mod_cnt, nr_abort;
+
+#define printf_verbose(fmt, ...) \
+ do { \
+ if (verbose) \
+ printf(fmt, ## __VA_ARGS__); \
+ } while (0)
+
+#ifdef __i386__
+
+#define INJECT_ASM_REG "eax"
+
+#define RSEQ_INJECT_CLOBBER \
+ , INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+ "mov asm_loop_cnt_" #n ", %%" INJECT_ASM_REG "\n\t" \
+ "test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \
+ "jz 333f\n\t" \
+ "222:\n\t" \
+ "dec %%" INJECT_ASM_REG "\n\t" \
+ "jnz 222b\n\t" \
+ "333:\n\t"
+
+#elif defined(__x86_64__)
+
+#define INJECT_ASM_REG_P "rax"
+#define INJECT_ASM_REG "eax"
+
+#define RSEQ_INJECT_CLOBBER \
+ , INJECT_ASM_REG_P \
+ , INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+ "lea asm_loop_cnt_" #n "(%%rip), %%" INJECT_ASM_REG_P "\n\t" \
+ "mov (%%" INJECT_ASM_REG_P "), %%" INJECT_ASM_REG "\n\t" \
+ "test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \
+ "jz 333f\n\t" \
+ "222:\n\t" \
+ "dec %%" INJECT_ASM_REG "\n\t" \
+ "jnz 222b\n\t" \
+ "333:\n\t"
+
+#elif defined(__ARMEL__)
+
+#define RSEQ_INJECT_INPUT \
+ , [loop_cnt_1]"m"(loop_cnt[1]) \
+ , [loop_cnt_2]"m"(loop_cnt[2]) \
+ , [loop_cnt_3]"m"(loop_cnt[3]) \
+ , [loop_cnt_4]"m"(loop_cnt[4]) \
+ , [loop_cnt_5]"m"(loop_cnt[5]) \
+ , [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG "r4"
+
+#define RSEQ_INJECT_CLOBBER \
+ , INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+ "ldr " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+ "cmp " INJECT_ASM_REG ", #0\n\t" \
+ "beq 333f\n\t" \
+ "222:\n\t" \
+ "subs " INJECT_ASM_REG ", #1\n\t" \
+ "bne 222b\n\t" \
+ "333:\n\t"
+
+#elif __PPC__
+
+#define RSEQ_INJECT_INPUT \
+ , [loop_cnt_1]"m"(loop_cnt[1]) \
+ , [loop_cnt_2]"m"(loop_cnt[2]) \
+ , [loop_cnt_3]"m"(loop_cnt[3]) \
+ , [loop_cnt_4]"m"(loop_cnt[4]) \
+ , [loop_cnt_5]"m"(loop_cnt[5]) \
+ , [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG "r18"
+
+#define RSEQ_INJECT_CLOBBER \
+ , INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+ "lwz %%" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+ "cmpwi %%" INJECT_ASM_REG ", 0\n\t" \
+ "beq 333f\n\t" \
+ "222:\n\t" \
+ "subic. %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG ", 1\n\t" \
+ "bne 222b\n\t" \
+ "333:\n\t"
+#else
+#error unsupported target
+#endif
+
+#define RSEQ_INJECT_FAILED \
+ nr_abort++;
+
+#define RSEQ_INJECT_C(n) \
+{ \
+ int loc_i, loc_nr_loops = loop_cnt[n]; \
+ \
+ for (loc_i = 0; loc_i < loc_nr_loops; loc_i++) { \
+ rseq_barrier(); \
+ } \
+ if (loc_nr_loops == -1 && opt_modulo) { \
+ if (yield_mod_cnt == opt_modulo - 1) { \
+ if (opt_sleep > 0) \
+ poll(NULL, 0, opt_sleep); \
+ if (opt_yield) \
+ sched_yield(); \
+ if (opt_signal) \
+ raise(SIGUSR1); \
+ yield_mod_cnt = 0; \
+ } else { \
+ yield_mod_cnt++; \
+ } \
+ } \
+}
+
+#else
+
+#define printf_verbose(fmt, ...)
+
+#endif /* BENCHMARK */
+
+#include "percpu-op.h"
+
+struct percpu_lock_entry {
+ intptr_t v;
+} __attribute__((aligned(128)));
+
+struct percpu_lock {
+ struct percpu_lock_entry c[CPU_SETSIZE];
+};
+
+struct test_data_entry {
+ intptr_t count;
+} __attribute__((aligned(128)));
+
+struct spinlock_test_data {
+ struct percpu_lock lock;
+ struct test_data_entry c[CPU_SETSIZE];
+};
+
+struct spinlock_thread_test_data {
+ struct spinlock_test_data *data;
+ long long reps;
+ int reg;
+};
+
+struct inc_test_data {
+ struct test_data_entry c[CPU_SETSIZE];
+};
+
+struct inc_thread_test_data {
+ struct inc_test_data *data;
+ long long reps;
+ int reg;
+};
+
+struct percpu_list_node {
+ intptr_t data;
+ struct percpu_list_node *next;
+};
+
+struct percpu_list_entry {
+ struct percpu_list_node *head;
+} __attribute__((aligned(128)));
+
+struct percpu_list {
+ struct percpu_list_entry c[CPU_SETSIZE];
+};
+
+#define BUFFER_ITEM_PER_CPU 100
+
+struct percpu_buffer_node {
+ intptr_t data;
+};
+
+struct percpu_buffer_entry {
+ intptr_t offset;
+ intptr_t buflen;
+ struct percpu_buffer_node **array;
+} __attribute__((aligned(128)));
+
+struct percpu_buffer {
+ struct percpu_buffer_entry c[CPU_SETSIZE];
+};
+
+#define MEMCPY_BUFFER_ITEM_PER_CPU 100
+
+struct percpu_memcpy_buffer_node {
+ intptr_t data1;
+ uint64_t data2;
+};
+
+struct percpu_memcpy_buffer_entry {
+ intptr_t offset;
+ intptr_t buflen;
+ struct percpu_memcpy_buffer_node *array;
+} __attribute__((aligned(128)));
+
+struct percpu_memcpy_buffer {
+ struct percpu_memcpy_buffer_entry c[CPU_SETSIZE];
+};
+
+/* A simple percpu spinlock. */
+static void rseq_percpu_lock(struct percpu_lock *lock, int cpu)
+{
+ for (;;) {
+ int ret;
+
+ ret = percpu_cmpeqv_storev(&lock->c[cpu].v,
+ 0, 1, cpu);
+ if (rseq_likely(!ret))
+ break;
+ if (rseq_unlikely(ret < 0)) {
+ perror("cpu_opv");
+ abort();
+ }
+ /* Retry if comparison fails. */
+ }
+ /*
+ * Acquire semantic when taking lock after control dependency.
+ * Matches rseq_smp_store_release().
+ */
+ rseq_smp_acquire__after_ctrl_dep();
+}
+
+static void rseq_percpu_unlock(struct percpu_lock *lock, int cpu)
+{
+ assert(lock->c[cpu].v == 1);
+ /*
+ * Release lock, with release semantic. Matches
+ * rseq_smp_acquire__after_ctrl_dep().
+ */
+ rseq_smp_store_release(&lock->c[cpu].v, 0);
+}
+
+void *test_percpu_spinlock_thread(void *arg)
+{
+ struct spinlock_thread_test_data *thread_data = arg;
+ struct spinlock_test_data *data = thread_data->data;
+ long long i, reps;
+
+ if (!opt_disable_rseq && thread_data->reg &&
+ rseq_register_current_thread())
+ abort();
+ reps = thread_data->reps;
+ for (i = 0; i < reps; i++) {
+ int cpu = rseq_cpu_start();
+
+ rseq_percpu_lock(&data->lock, cpu);
+ data->c[cpu].count++;
+ rseq_percpu_unlock(&data->lock, cpu);
+#ifndef BENCHMARK
+ if (i != 0 && !(i % (reps / 10)))
+ printf_verbose("tid %d: count %lld\n", (int) gettid(), i);
+#endif
+ }
+ printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+ (int) gettid(), nr_abort, signals_delivered);
+ if (!opt_disable_rseq && thread_data->reg &&
+ rseq_unregister_current_thread())
+ abort();
+ return NULL;
+}
+
+/*
+ * A simple test which implements a sharded counter using a per-cpu
+ * lock. Obviously real applications might prefer to simply use a
+ * per-cpu increment; however, this is reasonable for a test and the
+ * lock can be extended to synchronize more complicated operations.
+ */
+void test_percpu_spinlock(void)
+{
+ const int num_threads = opt_threads;
+ int i, ret;
+ uint64_t sum;
+ pthread_t test_threads[num_threads];
+ struct spinlock_test_data data;
+ struct spinlock_thread_test_data thread_data[num_threads];
+
+ memset(&data, 0, sizeof(data));
+ for (i = 0; i < num_threads; i++) {
+ thread_data[i].reps = opt_reps;
+ if (opt_disable_mod <= 0 || (i % opt_disable_mod))
+ thread_data[i].reg = 1;
+ else
+ thread_data[i].reg = 0;
+ thread_data[i].data = &data;
+ ret = pthread_create(&test_threads[i], NULL,
+ test_percpu_spinlock_thread,
+ &thread_data[i]);
+ if (ret) {
+ errno = ret;
+ perror("pthread_create");
+ abort();
+ }
+ }
+
+ for (i = 0; i < num_threads; i++) {
+ ret = pthread_join(test_threads[i], NULL);
+ if (ret) {
+ errno = ret;
+ perror("pthread_join");
+ abort();
+ }
+ }
+
+ sum = 0;
+ for (i = 0; i < CPU_SETSIZE; i++)
+ sum += data.c[i].count;
+
+ assert(sum == (uint64_t)opt_reps * num_threads);
+}
+
+void *test_percpu_inc_thread(void *arg)
+{
+ struct inc_thread_test_data *thread_data = arg;
+ struct inc_test_data *data = thread_data->data;
+ long long i, reps;
+
+ if (!opt_disable_rseq && thread_data->reg &&
+ rseq_register_current_thread())
+ abort();
+ reps = thread_data->reps;
+ for (i = 0; i < reps; i++) {
+ int cpu, ret;
+
+ cpu = rseq_cpu_start();
+ ret = percpu_addv(&data->c[cpu].count, 1, cpu);
+ if (rseq_unlikely(ret)) {
+ perror("cpu_opv");
+ abort();
+ }
+#ifndef BENCHMARK
+ if (i != 0 && !(i % (reps / 10)))
+ printf_verbose("tid %d: count %lld\n", (int) gettid(), i);
+#endif
+ }
+ printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+ (int) gettid(), nr_abort, signals_delivered);
+ if (!opt_disable_rseq && thread_data->reg &&
+ rseq_unregister_current_thread())
+ abort();
+ return NULL;
+}
+
+void test_percpu_inc(void)
+{
+ const int num_threads = opt_threads;
+ int i, ret;
+ uint64_t sum;
+ pthread_t test_threads[num_threads];
+ struct inc_test_data data;
+ struct inc_thread_test_data thread_data[num_threads];
+
+ memset(&data, 0, sizeof(data));
+ for (i = 0; i < num_threads; i++) {
+ thread_data[i].reps = opt_reps;
+ if (opt_disable_mod <= 0 || (i % opt_disable_mod))
+ thread_data[i].reg = 1;
+ else
+ thread_data[i].reg = 0;
+ thread_data[i].data = &data;
+ ret = pthread_create(&test_threads[i], NULL,
+ test_percpu_inc_thread,
+ &thread_data[i]);
+ if (ret) {
+ errno = ret;
+ perror("pthread_create");
+ abort();
+ }
+ }
+
+ for (i = 0; i < num_threads; i++) {
+ ret = pthread_join(test_threads[i], NULL);
+ if (ret) {
+ errno = ret;
+ perror("pthread_join");
+ abort();
+ }
+ }
+
+ sum = 0;
+ for (i = 0; i < CPU_SETSIZE; i++)
+ sum += data.c[i].count;
+
+ assert(sum == (uint64_t)opt_reps * num_threads);
+}
+
+void percpu_list_push(struct percpu_list *list,
+ struct percpu_list_node *node,
+ int cpu)
+{
+ for (;;) {
+ intptr_t *targetptr, newval, expect;
+ int ret;
+
+ /* Load list->c[cpu].head with single-copy atomicity. */
+ expect = (intptr_t)RSEQ_READ_ONCE(list->c[cpu].head);
+ newval = (intptr_t)node;
+ targetptr = (intptr_t *)&list->c[cpu].head;
+ node->next = (struct percpu_list_node *)expect;
+ ret = percpu_cmpeqv_storev(targetptr, expect, newval, cpu);
+ if (rseq_likely(!ret))
+ break;
+ if (rseq_unlikely(ret < 0)) {
+ perror("cpu_opv");
+ abort();
+ }
+ /* Retry if comparison fails. */
+ }
+}
+
+/*
+ * Unlike a traditional lock-less linked list; the availability of a
+ * rseq primitive allows us to implement pop without concerns over
+ * ABA-type races.
+ */
+struct percpu_list_node *percpu_list_pop(struct percpu_list *list,
+ int cpu)
+{
+ struct percpu_list_node *head;
+ intptr_t *targetptr, expectnot, *load;
+ off_t offset;
+ int ret;
+
+ targetptr = (intptr_t *)&list->c[cpu].head;
+ expectnot = (intptr_t)NULL;
+ offset = offsetof(struct percpu_list_node, next);
+ load = (intptr_t *)&head;
+ ret = percpu_cmpnev_storeoffp_load(targetptr, expectnot,
+ offset, load, cpu);
+ if (rseq_unlikely(ret < 0)) {
+ perror("cpu_opv");
+ abort();
+ }
+ if (ret > 0)
+ return NULL;
+ return head;
+}
+
+void *test_percpu_list_thread(void *arg)
+{
+ long long i, reps;
+ struct percpu_list *list = (struct percpu_list *)arg;
+
+ if (!opt_disable_rseq && rseq_register_current_thread())
+ abort();
+
+ reps = opt_reps;
+ for (i = 0; i < reps; i++) {
+ struct percpu_list_node *node;
+
+ node = percpu_list_pop(list, rseq_cpu_start());
+ if (opt_yield)
+ sched_yield(); /* encourage shuffling */
+ if (node)
+ percpu_list_push(list, node, rseq_cpu_start());
+ }
+
+ printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+ (int) gettid(), nr_abort, signals_delivered);
+ if (!opt_disable_rseq && rseq_unregister_current_thread())
+ abort();
+
+ return NULL;
+}
+
+/* Simultaneous modification to a per-cpu linked list from many threads. */
+void test_percpu_list(void)
+{
+ const int num_threads = opt_threads;
+ int i, j, ret;
+ uint64_t sum = 0, expected_sum = 0;
+ struct percpu_list list;
+ pthread_t test_threads[num_threads];
+ cpu_set_t allowed_cpus;
+
+ memset(&list, 0, sizeof(list));
+
+ /* Generate list entries for every usable cpu. */
+ sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+ for (i = 0; i < CPU_SETSIZE; i++) {
+ if (!CPU_ISSET(i, &allowed_cpus))
+ continue;
+ for (j = 1; j <= 100; j++) {
+ struct percpu_list_node *node;
+
+ expected_sum += j;
+
+ node = malloc(sizeof(*node));
+ assert(node);
+ node->data = j;
+ node->next = list.c[i].head;
+ list.c[i].head = node;
+ }
+ }
+
+ for (i = 0; i < num_threads; i++) {
+ ret = pthread_create(&test_threads[i], NULL,
+ test_percpu_list_thread, &list);
+ if (ret) {
+ errno = ret;
+ perror("pthread_create");
+ abort();
+ }
+ }
+
+ for (i = 0; i < num_threads; i++) {
+ ret = pthread_join(test_threads[i], NULL);
+ if (ret) {
+ errno = ret;
+ perror("pthread_join");
+ abort();
+ }
+ }
+
+ for (i = 0; i < CPU_SETSIZE; i++) {
+ struct percpu_list_node *node;
+
+ if (!CPU_ISSET(i, &allowed_cpus))
+ continue;
+
+ while ((node = percpu_list_pop(&list, i))) {
+ sum += node->data;
+ free(node);
+ }
+ }
+
+ /*
+ * All entries should now be accounted for (unless some external
+ * actor is interfering with our allowed affinity while this
+ * test is running).
+ */
+ assert(sum == expected_sum);
+}
+
+bool percpu_buffer_push(struct percpu_buffer *buffer,
+ struct percpu_buffer_node *node,
+ int cpu)
+{
+ for (;;) {
+ intptr_t *targetptr_spec, newval_spec;
+ intptr_t *targetptr_final, newval_final;
+ intptr_t offset;
+ int ret;
+
+ offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+ if (offset == buffer->c[cpu].buflen)
+ return false;
+ newval_spec = (intptr_t)node;
+ targetptr_spec = (intptr_t *)&buffer->c[cpu].array[offset];
+ newval_final = offset + 1;
+ targetptr_final = &buffer->c[cpu].offset;
+ if (opt_mb)
+ ret = percpu_cmpeqv_storev_storev_release(
+ targetptr_final, offset, targetptr_spec,
+ newval_spec, newval_final, cpu);
+ else
+ ret = percpu_cmpeqv_storev_storev(targetptr_final,
+ offset, targetptr_spec, newval_spec,
+ newval_final, cpu);
+ if (rseq_likely(!ret))
+ break;
+ if (rseq_unlikely(ret < 0)) {
+ perror("cpu_opv");
+ abort();
+ }
+ /* Retry if comparison fails. */
+ }
+ return true;
+}
+
+struct percpu_buffer_node *percpu_buffer_pop(struct percpu_buffer *buffer,
+ int cpu)
+{
+ struct percpu_buffer_node *head;
+
+ for (;;) {
+ intptr_t *targetptr, newval;
+ intptr_t offset;
+ int ret;
+
+ /* Load offset with single-copy atomicity. */
+ offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+ if (offset == 0)
+ return NULL;
+ head = RSEQ_READ_ONCE(buffer->c[cpu].array[offset - 1]);
+ newval = offset - 1;
+ targetptr = (intptr_t *)&buffer->c[cpu].offset;
+ ret = percpu_cmpeqv_cmpeqv_storev(targetptr, offset,
+ (intptr_t *)&buffer->c[cpu].array[offset - 1],
+ (intptr_t)head, newval, cpu);
+ if (rseq_likely(!ret))
+ break;
+ if (rseq_unlikely(ret < 0)) {
+ perror("cpu_opv");
+ abort();
+ }
+ /* Retry if comparison fails. */
+ }
+ return head;
+}
+
+void *test_percpu_buffer_thread(void *arg)
+{
+ long long i, reps;
+ struct percpu_buffer *buffer = (struct percpu_buffer *)arg;
+
+ if (!opt_disable_rseq && rseq_register_current_thread())
+ abort();
+
+ reps = opt_reps;
+ for (i = 0; i < reps; i++) {
+ struct percpu_buffer_node *node;
+
+ node = percpu_buffer_pop(buffer, rseq_cpu_start());
+ if (opt_yield)
+ sched_yield(); /* encourage shuffling */
+ if (node) {
+ if (!percpu_buffer_push(buffer, node,
+ rseq_cpu_start())) {
+ /* Should increase buffer size. */
+ abort();
+ }
+ }
+ }
+
+ printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+ (int) gettid(), nr_abort, signals_delivered);
+ if (!opt_disable_rseq && rseq_unregister_current_thread())
+ abort();
+
+ return NULL;
+}
+
+/* Simultaneous modification to a per-cpu buffer from many threads. */
+void test_percpu_buffer(void)
+{
+ const int num_threads = opt_threads;
+ int i, j, ret;
+ uint64_t sum = 0, expected_sum = 0;
+ struct percpu_buffer buffer;
+ pthread_t test_threads[num_threads];
+ cpu_set_t allowed_cpus;
+
+ memset(&buffer, 0, sizeof(buffer));
+
+ /* Generate list entries for every usable cpu. */
+ sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+ for (i = 0; i < CPU_SETSIZE; i++) {
+ if (!CPU_ISSET(i, &allowed_cpus))
+ continue;
+ /* Worse-case is every item in same CPU. */
+ buffer.c[i].array =
+ malloc(sizeof(*buffer.c[i].array) * CPU_SETSIZE *
+ BUFFER_ITEM_PER_CPU);
+ assert(buffer.c[i].array);
+ buffer.c[i].buflen = CPU_SETSIZE * BUFFER_ITEM_PER_CPU;
+ for (j = 1; j <= BUFFER_ITEM_PER_CPU; j++) {
+ struct percpu_buffer_node *node;
+
+ expected_sum += j;
+
+ /*
+ * We could theoretically put the word-sized
+ * "data" directly in the buffer. However, we
+ * want to model objects that would not fit
+ * within a single word, so allocate an object
+ * for each node.
+ */
+ node = malloc(sizeof(*node));
+ assert(node);
+ node->data = j;
+ buffer.c[i].array[j - 1] = node;
+ buffer.c[i].offset++;
+ }
+ }
+
+ for (i = 0; i < num_threads; i++) {
+ ret = pthread_create(&test_threads[i], NULL,
+ test_percpu_buffer_thread, &buffer);
+ if (ret) {
+ errno = ret;
+ perror("pthread_create");
+ abort();
+ }
+ }
+
+ for (i = 0; i < num_threads; i++) {
+ ret = pthread_join(test_threads[i], NULL);
+ if (ret) {
+ errno = ret;
+ perror("pthread_join");
+ abort();
+ }
+ }
+
+ for (i = 0; i < CPU_SETSIZE; i++) {
+ struct percpu_buffer_node *node;
+
+ if (!CPU_ISSET(i, &allowed_cpus))
+ continue;
+
+ while ((node = percpu_buffer_pop(&buffer, i))) {
+ sum += node->data;
+ free(node);
+ }
+ free(buffer.c[i].array);
+ }
+
+ /*
+ * All entries should now be accounted for (unless some external
+ * actor is interfering with our allowed affinity while this
+ * test is running).
+ */
+ assert(sum == expected_sum);
+}
+
+bool percpu_memcpy_buffer_push(struct percpu_memcpy_buffer *buffer,
+ struct percpu_memcpy_buffer_node item, int cpu)
+{
+ for (;;) {
+ intptr_t *targetptr_final, newval_final, offset;
+ char *destptr, *srcptr;
+ size_t copylen;
+ int ret;
+
+ /* Load offset with single-copy atomicity. */
+ offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+ if (offset == buffer->c[cpu].buflen)
+ return false;
+ destptr = (char *)&buffer->c[cpu].array[offset];
+ srcptr = (char *)&item;
+ /* copylen must be <= 4kB. */
+ copylen = sizeof(item);
+ newval_final = offset + 1;
+ targetptr_final = &buffer->c[cpu].offset;
+ if (opt_mb)
+ ret = percpu_cmpeqv_memcpy_storev_release(
+ targetptr_final, offset,
+ destptr, srcptr, copylen,
+ newval_final, cpu);
+ else
+ ret = percpu_cmpeqv_memcpy_storev(targetptr_final,
+ offset, destptr, srcptr, copylen,
+ newval_final, cpu);
+ if (rseq_likely(!ret))
+ break;
+ if (rseq_unlikely(ret < 0)) {
+ perror("cpu_opv");
+ abort();
+ }
+ /* Retry if comparison fails. */
+ }
+ return true;
+}
+
+bool percpu_memcpy_buffer_pop(struct percpu_memcpy_buffer *buffer,
+ struct percpu_memcpy_buffer_node *item, int cpu)
+{
+ for (;;) {
+ intptr_t *targetptr_final, newval_final, offset;
+ char *destptr, *srcptr;
+ size_t copylen;
+ int ret;
+
+ /* Load offset with single-copy atomicity. */
+ offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+ if (offset == 0)
+ return false;
+ destptr = (char *)item;
+ srcptr = (char *)&buffer->c[cpu].array[offset - 1];
+ /* copylen must be <= 4kB. */
+ copylen = sizeof(*item);
+ newval_final = offset - 1;
+ targetptr_final = &buffer->c[cpu].offset;
+ ret = percpu_cmpeqv_memcpy_storev(targetptr_final,
+ offset, destptr, srcptr, copylen,
+ newval_final, cpu);
+ if (rseq_likely(!ret))
+ break;
+ if (rseq_unlikely(ret < 0)) {
+ perror("cpu_opv");
+ abort();
+ }
+ /* Retry if comparison fails. */
+ }
+ return true;
+}
+
+void *test_percpu_memcpy_buffer_thread(void *arg)
+{
+ long long i, reps;
+ struct percpu_memcpy_buffer *buffer = (struct percpu_memcpy_buffer *)arg;
+
+ if (!opt_disable_rseq && rseq_register_current_thread())
+ abort();
+
+ reps = opt_reps;
+ for (i = 0; i < reps; i++) {
+ struct percpu_memcpy_buffer_node item;
+ bool result;
+
+ result = percpu_memcpy_buffer_pop(buffer, &item,
+ rseq_cpu_start());
+ if (opt_yield)
+ sched_yield(); /* encourage shuffling */
+ if (result) {
+ if (!percpu_memcpy_buffer_push(buffer, item,
+ rseq_cpu_start())) {
+ /* Should increase buffer size. */
+ abort();
+ }
+ }
+ }
+
+ printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+ (int) gettid(), nr_abort, signals_delivered);
+ if (!opt_disable_rseq && rseq_unregister_current_thread())
+ abort();
+
+ return NULL;
+}
+
+/* Simultaneous modification to a per-cpu buffer from many threads. */
+void test_percpu_memcpy_buffer(void)
+{
+ const int num_threads = opt_threads;
+ int i, j, ret;
+ uint64_t sum = 0, expected_sum = 0;
+ struct percpu_memcpy_buffer buffer;
+ pthread_t test_threads[num_threads];
+ cpu_set_t allowed_cpus;
+
+ memset(&buffer, 0, sizeof(buffer));
+
+ /* Generate list entries for every usable cpu. */
+ sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+ for (i = 0; i < CPU_SETSIZE; i++) {
+ if (!CPU_ISSET(i, &allowed_cpus))
+ continue;
+ /* Worse-case is every item in same CPU. */
+ buffer.c[i].array =
+ malloc(sizeof(*buffer.c[i].array) * CPU_SETSIZE *
+ MEMCPY_BUFFER_ITEM_PER_CPU);
+ assert(buffer.c[i].array);
+ buffer.c[i].buflen = CPU_SETSIZE * MEMCPY_BUFFER_ITEM_PER_CPU;
+ for (j = 1; j <= MEMCPY_BUFFER_ITEM_PER_CPU; j++) {
+ expected_sum += 2 * j + 1;
+
+ /*
+ * We could theoretically put the word-sized
+ * "data" directly in the buffer. However, we
+ * want to model objects that would not fit
+ * within a single word, so allocate an object
+ * for each node.
+ */
+ buffer.c[i].array[j - 1].data1 = j;
+ buffer.c[i].array[j - 1].data2 = j + 1;
+ buffer.c[i].offset++;
+ }
+ }
+
+ for (i = 0; i < num_threads; i++) {
+ ret = pthread_create(&test_threads[i], NULL,
+ test_percpu_memcpy_buffer_thread,
+ &buffer);
+ if (ret) {
+ errno = ret;
+ perror("pthread_create");
+ abort();
+ }
+ }
+
+ for (i = 0; i < num_threads; i++) {
+ ret = pthread_join(test_threads[i], NULL);
+ if (ret) {
+ errno = ret;
+ perror("pthread_join");
+ abort();
+ }
+ }
+
+ for (i = 0; i < CPU_SETSIZE; i++) {
+ struct percpu_memcpy_buffer_node item;
+
+ if (!CPU_ISSET(i, &allowed_cpus))
+ continue;
+
+ while (percpu_memcpy_buffer_pop(&buffer, &item, i)) {
+ sum += item.data1;
+ sum += item.data2;
+ }
+ free(buffer.c[i].array);
+ }
+
+ /*
+ * All entries should now be accounted for (unless some external
+ * actor is interfering with our allowed affinity while this
+ * test is running).
+ */
+ assert(sum == expected_sum);
+}
+
+static void test_signal_interrupt_handler(int signo)
+{
+ signals_delivered++;
+}
+
+static int set_signal_handler(void)
+{
+ int ret = 0;
+ struct sigaction sa;
+ sigset_t sigset;
+
+ ret = sigemptyset(&sigset);
+ if (ret < 0) {
+ perror("sigemptyset");
+ return ret;
+ }
+
+ sa.sa_handler = test_signal_interrupt_handler;
+ sa.sa_mask = sigset;
+ sa.sa_flags = 0;
+ ret = sigaction(SIGUSR1, &sa, NULL);
+ if (ret < 0) {
+ perror("sigaction");
+ return ret;
+ }
+
+ printf_verbose("Signal handler set for SIGUSR1\n");
+
+ return ret;
+}
+
+static void show_usage(int argc, char **argv)
+{
+ printf("Usage : %s <OPTIONS>\n",
+ argv[0]);
+ printf("OPTIONS:\n");
+ printf(" [-1 loops] Number of loops for delay injection 1\n");
+ printf(" [-2 loops] Number of loops for delay injection 2\n");
+ printf(" [-3 loops] Number of loops for delay injection 3\n");
+ printf(" [-4 loops] Number of loops for delay injection 4\n");
+ printf(" [-5 loops] Number of loops for delay injection 5\n");
+ printf(" [-6 loops] Number of loops for delay injection 6\n");
+ printf(" [-7 loops] Number of loops for delay injection 7 (-1 to enable -m)\n");
+ printf(" [-8 loops] Number of loops for delay injection 8 (-1 to enable -m)\n");
+ printf(" [-9 loops] Number of loops for delay injection 9 (-1 to enable -m)\n");
+ printf(" [-m N] Yield/sleep/kill every modulo N (default 0: disabled) (>= 0)\n");
+ printf(" [-y] Yield\n");
+ printf(" [-k] Kill thread with signal\n");
+ printf(" [-s S] S: =0: disabled (default), >0: sleep time (ms)\n");
+ printf(" [-t N] Number of threads (default 200)\n");
+ printf(" [-r N] Number of repetitions per thread (default 5000)\n");
+ printf(" [-d] Disable rseq system call (no initialization)\n");
+ printf(" [-D M] Disable rseq for each M threads\n");
+ printf(" [-T test] Choose test: (s)pinlock, (l)ist, (b)uffer, (m)emcpy, (i)ncrement\n");
+ printf(" [-M] Push into buffer and memcpy buffer with memory barriers.\n");
+ printf(" [-v] Verbose output.\n");
+ printf(" [-h] Show this help.\n");
+ printf("\n");
+}
+
+int main(int argc, char **argv)
+{
+ int i;
+
+ for (i = 1; i < argc; i++) {
+ if (argv[i][0] != '-')
+ continue;
+ switch (argv[i][1]) {
+ case '1':
+ case '2':
+ case '3':
+ case '4':
+ case '5':
+ case '6':
+ case '7':
+ case '8':
+ case '9':
+ if (argc < i + 2) {
+ show_usage(argc, argv);
+ goto error;
+ }
+ loop_cnt[argv[i][1] - '0'] = atol(argv[i + 1]);
+ i++;
+ break;
+ case 'm':
+ if (argc < i + 2) {
+ show_usage(argc, argv);
+ goto error;
+ }
+ opt_modulo = atol(argv[i + 1]);
+ if (opt_modulo < 0) {
+ show_usage(argc, argv);
+ goto error;
+ }
+ i++;
+ break;
+ case 's':
+ if (argc < i + 2) {
+ show_usage(argc, argv);
+ goto error;
+ }
+ opt_sleep = atol(argv[i + 1]);
+ if (opt_sleep < 0) {
+ show_usage(argc, argv);
+ goto error;
+ }
+ i++;
+ break;
+ case 'y':
+ opt_yield = 1;
+ break;
+ case 'k':
+ opt_signal = 1;
+ break;
+ case 'd':
+ opt_disable_rseq = 1;
+ break;
+ case 'D':
+ if (argc < i + 2) {
+ show_usage(argc, argv);
+ goto error;
+ }
+ opt_disable_mod = atol(argv[i + 1]);
+ if (opt_disable_mod < 0) {
+ show_usage(argc, argv);
+ goto error;
+ }
+ i++;
+ break;
+ case 't':
+ if (argc < i + 2) {
+ show_usage(argc, argv);
+ goto error;
+ }
+ opt_threads = atol(argv[i + 1]);
+ if (opt_threads < 0) {
+ show_usage(argc, argv);
+ goto error;
+ }
+ i++;
+ break;
+ case 'r':
+ if (argc < i + 2) {
+ show_usage(argc, argv);
+ goto error;
+ }
+ opt_reps = atoll(argv[i + 1]);
+ if (opt_reps < 0) {
+ show_usage(argc, argv);
+ goto error;
+ }
+ i++;
+ break;
+ case 'h':
+ show_usage(argc, argv);
+ goto end;
+ case 'T':
+ if (argc < i + 2) {
+ show_usage(argc, argv);
+ goto error;
+ }
+ opt_test = *argv[i + 1];
+ switch (opt_test) {
+ case 's':
+ case 'l':
+ case 'i':
+ case 'b':
+ case 'm':
+ break;
+ default:
+ show_usage(argc, argv);
+ goto error;
+ }
+ i++;
+ break;
+ case 'v':
+ verbose = 1;
+ break;
+ case 'M':
+ opt_mb = 1;
+ break;
+ default:
+ show_usage(argc, argv);
+ goto error;
+ }
+ }
+
+ loop_cnt_1 = loop_cnt[1];
+ loop_cnt_2 = loop_cnt[2];
+ loop_cnt_3 = loop_cnt[3];
+ loop_cnt_4 = loop_cnt[4];
+ loop_cnt_5 = loop_cnt[5];
+ loop_cnt_6 = loop_cnt[6];
+
+ if (set_signal_handler())
+ goto error;
+
+ if (!opt_disable_rseq && rseq_register_current_thread())
+ goto error;
+ switch (opt_test) {
+ case 's':
+ printf_verbose("spinlock\n");
+ test_percpu_spinlock();
+ break;
+ case 'l':
+ printf_verbose("linked list\n");
+ test_percpu_list();
+ break;
+ case 'b':
+ printf_verbose("buffer\n");
+ test_percpu_buffer();
+ break;
+ case 'm':
+ printf_verbose("memcpy buffer\n");
+ test_percpu_memcpy_buffer();
+ break;
+ case 'i':
+ printf_verbose("counter increment\n");
+ test_percpu_inc();
+ break;
+ }
+ if (!opt_disable_rseq && rseq_unregister_current_thread())
+ abort();
+end:
+ return 0;
+
+error:
+ return -1;
+}
--
2.11.0
^ permalink raw reply related
* [RFC PATCH for 4.21 14/16] cpu-opv/selftests: Provide basic percpu ops test
From: Mathieu Desnoyers @ 2018-10-10 19:19 UTC (permalink / raw)
To: Peter Zijlstra, Paul E . McKenney, Boqun Feng
Cc: linux-kernel, linux-api, Thomas Gleixner, Andy Lutomirski,
Dave Watson, Paul Turner, Andrew Morton, Russell King,
Ingo Molnar, H . Peter Anvin, Andi Kleen, Chris Lameter,
Ben Maurer, Steven Rostedt, Josh Triplett, Linus Torvalds,
Catalin Marinas, Will Deacon, Michael Kerrisk, Joel Fernandes,
Mathieu Desnoyers
In-Reply-To: <20181010191936.7495-1-mathieu.desnoyers@efficios.com>
"basic_percpu_ops_test" implements a few simple per-cpu operations and
testing their correctness.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
.../selftests/cpu-opv/basic_percpu_ops_test.c | 295 +++++++++++++++++++++
1 file changed, 295 insertions(+)
create mode 100644 tools/testing/selftests/cpu-opv/basic_percpu_ops_test.c
diff --git a/tools/testing/selftests/cpu-opv/basic_percpu_ops_test.c b/tools/testing/selftests/cpu-opv/basic_percpu_ops_test.c
new file mode 100644
index 000000000000..2ce5202f25b2
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/basic_percpu_ops_test.c
@@ -0,0 +1,295 @@
+// SPDX-License-Identifier: LGPL-2.1
+#define _GNU_SOURCE
+#include <assert.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stddef.h>
+
+#include "percpu-op.h"
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+struct percpu_lock_entry {
+ intptr_t v;
+} __attribute__((aligned(128)));
+
+struct percpu_lock {
+ struct percpu_lock_entry c[CPU_SETSIZE];
+};
+
+struct test_data_entry {
+ intptr_t count;
+} __attribute__((aligned(128)));
+
+struct spinlock_test_data {
+ struct percpu_lock lock;
+ struct test_data_entry c[CPU_SETSIZE];
+ int reps;
+};
+
+struct percpu_list_node {
+ intptr_t data;
+ struct percpu_list_node *next;
+};
+
+struct percpu_list_entry {
+ struct percpu_list_node *head;
+} __attribute__((aligned(128)));
+
+struct percpu_list {
+ struct percpu_list_entry c[CPU_SETSIZE];
+};
+
+/* A simple percpu spinlock. */
+void rseq_percpu_lock(struct percpu_lock *lock, int cpu)
+{
+ for (;;) {
+ int ret;
+
+ ret = percpu_cmpeqv_storev(&lock->c[cpu].v,
+ 0, 1, cpu);
+ if (rseq_likely(!ret))
+ break;
+ if (rseq_unlikely(ret < 0)) {
+ perror("cpu_opv");
+ abort();
+ }
+ /* Retry if comparison fails. */
+ }
+ /*
+ * Acquire semantic when taking lock after control dependency.
+ * Matches rseq_smp_store_release().
+ */
+ rseq_smp_acquire__after_ctrl_dep();
+}
+
+void rseq_percpu_unlock(struct percpu_lock *lock, int cpu)
+{
+ assert(lock->c[cpu].v == 1);
+ /*
+ * Release lock, with release semantic. Matches
+ * rseq_smp_acquire__after_ctrl_dep().
+ */
+ rseq_smp_store_release(&lock->c[cpu].v, 0);
+}
+
+void *test_percpu_spinlock_thread(void *arg)
+{
+ struct spinlock_test_data *data = arg;
+ int i;
+
+ if (rseq_register_current_thread()) {
+ fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+ errno, strerror(errno));
+ abort();
+ }
+ for (i = 0; i < data->reps; i++) {
+ int cpu = percpu_current_cpu();
+
+ rseq_percpu_lock(&data->lock, cpu);
+ data->c[cpu].count++;
+ rseq_percpu_unlock(&data->lock, cpu);
+ }
+ if (rseq_unregister_current_thread()) {
+ fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+ errno, strerror(errno));
+ abort();
+ }
+
+ return NULL;
+}
+
+/*
+ * A simple test which implements a sharded counter using a per-cpu
+ * lock. Obviously real applications might prefer to simply use a
+ * per-cpu increment; however, this is reasonable for a test and the
+ * lock can be extended to synchronize more complicated operations.
+ */
+void test_percpu_spinlock(void)
+{
+ const int num_threads = 200;
+ int i;
+ uint64_t sum;
+ pthread_t test_threads[num_threads];
+ struct spinlock_test_data data;
+
+ memset(&data, 0, sizeof(data));
+ data.reps = 5000;
+
+ for (i = 0; i < num_threads; i++)
+ pthread_create(&test_threads[i], NULL,
+ test_percpu_spinlock_thread, &data);
+
+ for (i = 0; i < num_threads; i++)
+ pthread_join(test_threads[i], NULL);
+
+ sum = 0;
+ for (i = 0; i < CPU_SETSIZE; i++)
+ sum += data.c[i].count;
+
+ assert(sum == (uint64_t)data.reps * num_threads);
+}
+
+int percpu_list_push(struct percpu_list *list, struct percpu_list_node *node,
+ int cpu)
+{
+ for (;;) {
+ intptr_t *targetptr, newval, expect;
+ int ret;
+
+ /* Load list->c[cpu].head with single-copy atomicity. */
+ expect = (intptr_t)RSEQ_READ_ONCE(list->c[cpu].head);
+ newval = (intptr_t)node;
+ targetptr = (intptr_t *)&list->c[cpu].head;
+ node->next = (struct percpu_list_node *)expect;
+ ret = percpu_cmpeqv_storev(targetptr, expect, newval, cpu);
+ if (rseq_likely(!ret))
+ break;
+ if (rseq_unlikely(ret < 0)) {
+ perror("cpu_opv");
+ abort();
+ }
+ /* Retry if comparison fails. */
+ }
+ return cpu;
+}
+
+/*
+ * Unlike a traditional lock-less linked list; the availability of a
+ * rseq primitive allows us to implement pop without concerns over
+ * ABA-type races.
+ */
+struct percpu_list_node *percpu_list_pop(struct percpu_list *list,
+ int cpu)
+{
+ struct percpu_list_node *head;
+ intptr_t *targetptr, expectnot, *load;
+ off_t offset;
+ int ret;
+
+ targetptr = (intptr_t *)&list->c[cpu].head;
+ expectnot = (intptr_t)NULL;
+ offset = offsetof(struct percpu_list_node, next);
+ load = (intptr_t *)&head;
+ ret = percpu_cmpnev_storeoffp_load(targetptr, expectnot,
+ offset, load, cpu);
+ if (rseq_unlikely(ret < 0)) {
+ perror("cpu_opv");
+ abort();
+ }
+ if (ret > 0)
+ return NULL;
+ return head;
+}
+
+void *test_percpu_list_thread(void *arg)
+{
+ int i;
+ struct percpu_list *list = (struct percpu_list *)arg;
+
+ if (rseq_register_current_thread()) {
+ fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+ errno, strerror(errno));
+ abort();
+ }
+
+ for (i = 0; i < 100000; i++) {
+ struct percpu_list_node *node;
+
+ node = percpu_list_pop(list, percpu_current_cpu());
+ sched_yield(); /* encourage shuffling */
+ if (node)
+ percpu_list_push(list, node, percpu_current_cpu());
+ }
+
+ if (rseq_unregister_current_thread()) {
+ fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+ errno, strerror(errno));
+ abort();
+ }
+
+ return NULL;
+}
+
+/* Simultaneous modification to a per-cpu linked list from many threads. */
+void test_percpu_list(void)
+{
+ int i, j;
+ uint64_t sum = 0, expected_sum = 0;
+ struct percpu_list list;
+ pthread_t test_threads[200];
+ cpu_set_t allowed_cpus;
+
+ memset(&list, 0, sizeof(list));
+
+ /* Generate list entries for every usable cpu. */
+ sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+ for (i = 0; i < CPU_SETSIZE; i++) {
+ if (!CPU_ISSET(i, &allowed_cpus))
+ continue;
+ for (j = 1; j <= 100; j++) {
+ struct percpu_list_node *node;
+
+ expected_sum += j;
+
+ node = malloc(sizeof(*node));
+ assert(node);
+ node->data = j;
+ node->next = list.c[i].head;
+ list.c[i].head = node;
+ }
+ }
+
+ for (i = 0; i < 200; i++)
+ pthread_create(&test_threads[i], NULL,
+ test_percpu_list_thread, &list);
+
+ for (i = 0; i < 200; i++)
+ pthread_join(test_threads[i], NULL);
+
+ for (i = 0; i < CPU_SETSIZE; i++) {
+ struct percpu_list_node *node;
+
+ if (!CPU_ISSET(i, &allowed_cpus))
+ continue;
+
+ while ((node = percpu_list_pop(&list, i))) {
+ sum += node->data;
+ free(node);
+ }
+ }
+
+ /*
+ * All entries should now be accounted for (unless some external
+ * actor is interfering with our allowed affinity while this
+ * test is running).
+ */
+ assert(sum == expected_sum);
+}
+
+int main(int argc, char **argv)
+{
+ if (rseq_register_current_thread()) {
+ fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+ errno, strerror(errno));
+ goto error;
+ }
+ printf("spinlock\n");
+ test_percpu_spinlock();
+ printf("percpu_list\n");
+ test_percpu_list();
+ if (rseq_unregister_current_thread()) {
+ fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+ errno, strerror(errno));
+ goto error;
+ }
+ return 0;
+
+error:
+ return -1;
+}
+
--
2.11.0
^ permalink raw reply related
* [RFC PATCH for 4.21 13/16] cpu-opv/selftests: Provide percpu_op API
From: Mathieu Desnoyers @ 2018-10-10 19:19 UTC (permalink / raw)
To: Peter Zijlstra, Paul E . McKenney, Boqun Feng
Cc: linux-kernel, linux-api, Thomas Gleixner, Andy Lutomirski,
Dave Watson, Paul Turner, Andrew Morton, Russell King,
Ingo Molnar, H . Peter Anvin, Andi Kleen, Chris Lameter,
Ben Maurer, Steven Rostedt, Josh Triplett, Linus Torvalds,
Catalin Marinas, Will Deacon, Michael Kerrisk, Joel Fernandes,
Mathieu Desnoyers
In-Reply-To: <20181010191936.7495-1-mathieu.desnoyers@efficios.com>
Introduce percpu-op.h API. It uses rseq internally as fast-path if
invoked from the right CPU, else cpu_opv as slow-path if called
from the wrong CPU or if rseq fails.
This allows acting on per-cpu data from various CPUs transparently from
user-space: cpu_opv will take care of migrating the thread to the
requested CPU. Use-cases such as rebalancing memory across per-cpu
memory pools, or migrating tasks for a user-space scheduler, are thus
facilitated. This also handles debugger single-stepping.
The use from userspace is, e.g. for a counter increment:
int cpu, ret;
cpu = percpu_current_cpu();
ret = percpu_addv(&data->c[cpu].count, 1, cpu);
if (unlikely(ret)) {
perror("percpu_addv");
return -1;
}
return 0;
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Shuah Khan <shuah@kernel.org>
CC: Russell King <linux@arm.linux.org.uk>
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Paul Turner <pjt@google.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Andi Kleen <andi@firstfloor.org>
CC: Dave Watson <davejwatson@fb.com>
CC: Chris Lameter <cl@linux.com>
CC: Ingo Molnar <mingo@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Ben Maurer <bmaurer@fb.com>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: Josh Triplett <josh@joshtriplett.org>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: linux-kselftest@vger.kernel.org
CC: linux-api@vger.kernel.org
---
tools/testing/selftests/cpu-opv/percpu-op.h | 151 ++++++++++++++++++++++++++++
1 file changed, 151 insertions(+)
create mode 100644 tools/testing/selftests/cpu-opv/percpu-op.h
diff --git a/tools/testing/selftests/cpu-opv/percpu-op.h b/tools/testing/selftests/cpu-opv/percpu-op.h
new file mode 100644
index 000000000000..ffc64b268fd3
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/percpu-op.h
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * percpu-op.h
+ *
+ * (C) Copyright 2017-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef PERCPU_OP_H
+#define PERCPU_OP_H
+
+#include <stdint.h>
+#include <stdbool.h>
+#include <errno.h>
+#include <stdlib.h>
+#include "rseq.h"
+#include "cpu-op.h"
+
+static inline uint32_t percpu_current_cpu(void)
+{
+ return rseq_current_cpu();
+}
+
+static inline __attribute__((always_inline))
+int percpu_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv,
+ int cpu)
+{
+ int ret;
+
+ ret = rseq_cmpeqv_storev(v, expect, newv, cpu);
+ if (rseq_unlikely(ret)) {
+ if (ret > 0)
+ return ret;
+ return cpu_op_cmpeqv_storev(v, expect, newv, cpu);
+ }
+ return 0;
+}
+
+static inline __attribute__((always_inline))
+int percpu_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+ off_t voffp, intptr_t *load, int cpu)
+{
+ int ret;
+
+ ret = rseq_cmpnev_storeoffp_load(v, expectnot, voffp, load, cpu);
+ if (rseq_unlikely(ret)) {
+ if (ret > 0)
+ return ret;
+ return cpu_op_cmpnev_storeoffp_load(v, expectnot, voffp,
+ load, cpu);
+ }
+ return 0;
+}
+
+static inline __attribute__((always_inline))
+int percpu_addv(intptr_t *v, intptr_t count, int cpu)
+{
+ if (rseq_unlikely(rseq_addv(v, count, cpu)))
+ return cpu_op_addv(v, count, cpu);
+ return 0;
+}
+
+static inline __attribute__((always_inline))
+int percpu_cmpeqv_storev_storev(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t newv2,
+ intptr_t newv, int cpu)
+{
+ int ret;
+
+ ret = rseq_cmpeqv_trystorev_storev(v, expect, v2, newv2,
+ newv, cpu);
+ if (rseq_unlikely(ret)) {
+ if (ret > 0)
+ return ret;
+ return cpu_op_cmpeqv_storev_storev(v, expect, v2, newv2,
+ newv, cpu);
+ }
+ return 0;
+}
+
+static inline __attribute__((always_inline))
+int percpu_cmpeqv_storev_storev_release(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t newv2,
+ intptr_t newv, int cpu)
+{
+ int ret;
+
+ ret = rseq_cmpeqv_trystorev_storev_release(v, expect, v2, newv2,
+ newv, cpu);
+ if (rseq_unlikely(ret)) {
+ if (ret > 0)
+ return ret;
+ return cpu_op_cmpeqv_storev_mb_storev(v, expect, v2, newv2,
+ newv, cpu);
+ }
+ return 0;
+}
+
+static inline __attribute__((always_inline))
+int percpu_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t expect2,
+ intptr_t newv, int cpu)
+{
+ int ret;
+
+ ret = rseq_cmpeqv_cmpeqv_storev(v, expect, v2, expect2, newv, cpu);
+ if (rseq_unlikely(ret)) {
+ if (ret > 0)
+ return ret;
+ return cpu_op_cmpeqv_cmpeqv_storev(v, expect, v2, expect2,
+ newv, cpu);
+ }
+ return 0;
+}
+
+static inline __attribute__((always_inline))
+int percpu_cmpeqv_memcpy_storev(intptr_t *v, intptr_t expect,
+ void *dst, void *src, size_t len,
+ intptr_t newv, int cpu)
+{
+ int ret;
+
+ ret = rseq_cmpeqv_trymemcpy_storev(v, expect, dst, src, len,
+ newv, cpu);
+ if (rseq_unlikely(ret)) {
+ if (ret > 0)
+ return ret;
+ return cpu_op_cmpeqv_memcpy_storev(v, expect, dst, src, len,
+ newv, cpu);
+ }
+ return 0;
+}
+
+static inline __attribute__((always_inline))
+int percpu_cmpeqv_memcpy_storev_release(intptr_t *v, intptr_t expect,
+ void *dst, void *src, size_t len,
+ intptr_t newv, int cpu)
+{
+ int ret;
+
+ ret = rseq_cmpeqv_trymemcpy_storev_release(v, expect, dst, src, len,
+ newv, cpu);
+ if (rseq_unlikely(ret)) {
+ if (ret > 0)
+ return ret;
+ return cpu_op_cmpeqv_memcpy_mb_storev(v, expect, dst, src, len,
+ newv, cpu);
+ }
+ return 0;
+}
+
+#endif /* PERCPU_OP_H_ */
--
2.11.0
^ permalink raw reply related
* [RFC PATCH for 4.21 12/16] cpu-opv/selftests: Provide basic test
From: Mathieu Desnoyers @ 2018-10-10 19:19 UTC (permalink / raw)
To: Peter Zijlstra, Paul E . McKenney, Boqun Feng
Cc: linux-kernel, linux-api, Thomas Gleixner, Andy Lutomirski,
Dave Watson, Paul Turner, Andrew Morton, Russell King,
Ingo Molnar, H . Peter Anvin, Andi Kleen, Chris Lameter,
Ben Maurer, Steven Rostedt, Josh Triplett, Linus Torvalds,
Catalin Marinas, Will Deacon, Michael Kerrisk, Joel Fernandes,
Mathieu Desnoyers
In-Reply-To: <20181010191936.7495-1-mathieu.desnoyers@efficios.com>
"basic_cpu_opv_test" tests basic functionality of cpu_opv.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
.../testing/selftests/cpu-opv/basic_cpu_opv_test.c | 1362 ++++++++++++++++++++
1 file changed, 1362 insertions(+)
create mode 100644 tools/testing/selftests/cpu-opv/basic_cpu_opv_test.c
diff --git a/tools/testing/selftests/cpu-opv/basic_cpu_opv_test.c b/tools/testing/selftests/cpu-opv/basic_cpu_opv_test.c
new file mode 100644
index 000000000000..ec5adee20c7f
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/basic_cpu_opv_test.c
@@ -0,0 +1,1362 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Basic test coverage for cpu_opv system call.
+ */
+
+#define _GNU_SOURCE
+#include <assert.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <sys/mman.h>
+#include <sched.h>
+
+#include "../kselftest.h"
+
+#include "cpu-op.h"
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+#define TESTBUFLEN 4096
+#define TESTBUFLEN_CMP 16
+
+#define TESTBUFLEN_PAGE_MAX 65536
+
+#define NR_PF_ARRAY 16384
+#define PF_ARRAY_LEN 4096
+
+#define NR_HUGE_ARRAY 512
+#define HUGEMAPLEN (NR_HUGE_ARRAY * PF_ARRAY_LEN)
+
+/* 64 MB arrays for page fault testing. */
+char pf_array_dst[NR_PF_ARRAY][PF_ARRAY_LEN];
+char pf_array_src[NR_PF_ARRAY][PF_ARRAY_LEN];
+
+static int test_ops_supported(void)
+{
+ const char *test_name = "test_ops_supported";
+ int ret;
+
+ ret = cpu_opv(NULL, 0, -1, CPU_OP_NR_FLAG);
+ if (ret < 0) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (ret < NR_CPU_OPS) {
+ ksft_test_result_fail("%s test: only %d operations supported, expecting at least %d\n",
+ test_name, ret, NR_CPU_OPS);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_compare_eq_op(char *a, char *b, size_t len)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_COMPARE_EQ_OP,
+ .len = len,
+ .u.compare_op.a = (unsigned long)a,
+ .u.compare_op.b = (unsigned long)b,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ };
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_compare_eq_same(void)
+{
+ int i, ret;
+ char buf1[TESTBUFLEN];
+ char buf2[TESTBUFLEN];
+ const char *test_name = "test_compare_eq same";
+
+ /* Test compare_eq */
+ for (i = 0; i < TESTBUFLEN; i++)
+ buf1[i] = (char)i;
+ for (i = 0; i < TESTBUFLEN; i++)
+ buf2[i] = (char)i;
+ ret = test_compare_eq_op(buf2, buf1, TESTBUFLEN);
+ if (ret < 0) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (ret > 0) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, ret, 0);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_compare_eq_diff(void)
+{
+ int i, ret;
+ char buf1[TESTBUFLEN];
+ char buf2[TESTBUFLEN];
+ const char *test_name = "test_compare_eq different";
+
+ for (i = 0; i < TESTBUFLEN; i++)
+ buf1[i] = (char)i;
+ memset(buf2, 0, TESTBUFLEN);
+ ret = test_compare_eq_op(buf2, buf1, TESTBUFLEN);
+ if (ret < 0) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (ret == 0) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, ret, 1);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_compare_ne_op(char *a, char *b, size_t len)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_COMPARE_NE_OP,
+ .len = len,
+ .u.compare_op.a = (unsigned long)a,
+ .u.compare_op.b = (unsigned long)b,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ };
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_compare_ne_same(void)
+{
+ int i, ret;
+ char buf1[TESTBUFLEN];
+ char buf2[TESTBUFLEN];
+ const char *test_name = "test_compare_ne same";
+
+ /* Test compare_ne */
+ for (i = 0; i < TESTBUFLEN; i++)
+ buf1[i] = (char)i;
+ for (i = 0; i < TESTBUFLEN; i++)
+ buf2[i] = (char)i;
+ ret = test_compare_ne_op(buf2, buf1, TESTBUFLEN);
+ if (ret < 0) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (ret == 0) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, ret, 1);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_compare_ne_diff(void)
+{
+ int i, ret;
+ char buf1[TESTBUFLEN];
+ char buf2[TESTBUFLEN];
+ const char *test_name = "test_compare_ne different";
+
+ for (i = 0; i < TESTBUFLEN; i++)
+ buf1[i] = (char)i;
+ memset(buf2, 0, TESTBUFLEN);
+ ret = test_compare_ne_op(buf2, buf1, TESTBUFLEN);
+ if (ret < 0) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (ret != 0) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, ret, 0);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_2compare_eq_op(char *a, char *b, char *c, char *d,
+ size_t len)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_COMPARE_EQ_OP,
+ .len = len,
+ .u.compare_op.a = (unsigned long)a,
+ .u.compare_op.b = (unsigned long)b,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ [1] = {
+ .op = CPU_COMPARE_EQ_OP,
+ .len = len,
+ .u.compare_op.a = (unsigned long)c,
+ .u.compare_op.b = (unsigned long)d,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ };
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_2compare_eq_index(void)
+{
+ int i, ret;
+ char buf1[TESTBUFLEN_CMP];
+ char buf2[TESTBUFLEN_CMP];
+ char buf3[TESTBUFLEN_CMP];
+ char buf4[TESTBUFLEN_CMP];
+ const char *test_name = "test_2compare_eq index";
+
+ for (i = 0; i < TESTBUFLEN_CMP; i++)
+ buf1[i] = (char)i;
+ memset(buf2, 0, TESTBUFLEN_CMP);
+ memset(buf3, 0, TESTBUFLEN_CMP);
+ memset(buf4, 0, TESTBUFLEN_CMP);
+
+ /* First compare failure is op[0], expect 1. */
+ ret = test_2compare_eq_op(buf2, buf1, buf4, buf3, TESTBUFLEN_CMP);
+ if (ret < 0) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (ret != 1) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, ret, 1);
+ return -1;
+ }
+
+ /* All compares succeed. */
+ for (i = 0; i < TESTBUFLEN_CMP; i++)
+ buf2[i] = (char)i;
+ ret = test_2compare_eq_op(buf2, buf1, buf4, buf3, TESTBUFLEN_CMP);
+ if (ret < 0) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (ret != 0) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, ret, 0);
+ return -1;
+ }
+
+ /* First compare failure is op[1], expect 2. */
+ for (i = 0; i < TESTBUFLEN_CMP; i++)
+ buf3[i] = (char)i;
+ ret = test_2compare_eq_op(buf2, buf1, buf4, buf3, TESTBUFLEN_CMP);
+ if (ret < 0) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (ret != 2) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, ret, 2);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_2compare_ne_op(char *a, char *b, char *c, char *d,
+ size_t len)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_COMPARE_NE_OP,
+ .len = len,
+ .u.compare_op.a = (unsigned long)a,
+ .u.compare_op.b = (unsigned long)b,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ [1] = {
+ .op = CPU_COMPARE_NE_OP,
+ .len = len,
+ .u.compare_op.a = (unsigned long)c,
+ .u.compare_op.b = (unsigned long)d,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ };
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_2compare_ne_index(void)
+{
+ int i, ret;
+ char buf1[TESTBUFLEN_CMP];
+ char buf2[TESTBUFLEN_CMP];
+ char buf3[TESTBUFLEN_CMP];
+ char buf4[TESTBUFLEN_CMP];
+ const char *test_name = "test_2compare_ne index";
+
+ memset(buf1, 0, TESTBUFLEN_CMP);
+ memset(buf2, 0, TESTBUFLEN_CMP);
+ memset(buf3, 0, TESTBUFLEN_CMP);
+ memset(buf4, 0, TESTBUFLEN_CMP);
+
+ /* First compare ne failure is op[0], expect 1. */
+ ret = test_2compare_ne_op(buf2, buf1, buf4, buf3, TESTBUFLEN_CMP);
+ if (ret < 0) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (ret != 1) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, ret, 1);
+ return -1;
+ }
+
+ /* All compare ne succeed. */
+ for (i = 0; i < TESTBUFLEN_CMP; i++)
+ buf1[i] = (char)i;
+ for (i = 0; i < TESTBUFLEN_CMP; i++)
+ buf3[i] = (char)i;
+ ret = test_2compare_ne_op(buf2, buf1, buf4, buf3, TESTBUFLEN_CMP);
+ if (ret < 0) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (ret != 0) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, ret, 0);
+ return -1;
+ }
+
+ /* First compare failure is op[1], expect 2. */
+ for (i = 0; i < TESTBUFLEN_CMP; i++)
+ buf4[i] = (char)i;
+ ret = test_2compare_ne_op(buf2, buf1, buf4, buf3, TESTBUFLEN_CMP);
+ if (ret < 0) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (ret != 2) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, ret, 2);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_memcpy_op(void *dst, void *src, size_t len)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_MEMCPY_OP,
+ .len = len,
+ .u.memcpy_op.dst = (unsigned long)dst,
+ .u.memcpy_op.src = (unsigned long)src,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ };
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_memcpy(void)
+{
+ int i, ret;
+ char buf1[TESTBUFLEN];
+ char buf2[TESTBUFLEN];
+ const char *test_name = "test_memcpy";
+
+ /* Test memcpy */
+ for (i = 0; i < TESTBUFLEN; i++)
+ buf1[i] = (char)i;
+ memset(buf2, 0, TESTBUFLEN);
+ ret = test_memcpy_op(buf2, buf1, TESTBUFLEN);
+ if (ret) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ for (i = 0; i < TESTBUFLEN; i++) {
+ if (buf2[i] != (char)i) {
+ ksft_test_result_fail("%s test: unexpected value at offset %d. Found %d. Should be %d.\n",
+ test_name, i, buf2[i], (char)i);
+ return -1;
+ }
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_memcpy_u32(void)
+{
+ int ret;
+ uint32_t v1, v2;
+ const char *test_name = "test_memcpy_u32";
+
+ /* Test memcpy_u32 */
+ v1 = 42;
+ v2 = 0;
+ ret = test_memcpy_op(&v2, &v1, sizeof(v1));
+ if (ret) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (v1 != v2) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, v2, v1);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_memcpy_mb_memcpy_op(void *dst1, void *src1,
+ void *dst2, void *src2, size_t len)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_MEMCPY_OP,
+ .len = len,
+ .u.memcpy_op.dst = (unsigned long)dst1,
+ .u.memcpy_op.src = (unsigned long)src1,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ [1] = {
+ .op = CPU_MB_OP,
+ },
+ [2] = {
+ .op = CPU_MEMCPY_OP,
+ .len = len,
+ .u.memcpy_op.dst = (unsigned long)dst2,
+ .u.memcpy_op.src = (unsigned long)src2,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ };
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_memcpy_mb_memcpy(void)
+{
+ int ret;
+ int v1, v2, v3;
+ const char *test_name = "test_memcpy_mb_memcpy";
+
+ /* Test memcpy */
+ v1 = 42;
+ v2 = v3 = 0;
+ ret = test_memcpy_mb_memcpy_op(&v2, &v1, &v3, &v2, sizeof(int));
+ if (ret) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (v3 != v1) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, v3, v1);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_add_op(int *v, int64_t increment)
+{
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_op_add(v, increment, sizeof(*v), cpu);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_add(void)
+{
+ int orig_v = 42, v, ret;
+ int increment = 1;
+ const char *test_name = "test_add";
+
+ v = orig_v;
+ ret = test_add_op(&v, increment);
+ if (ret) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (v != orig_v + increment) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, v,
+ orig_v + increment);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_two_add_op(int *v, int64_t *increments)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_ADD_OP,
+ .len = sizeof(*v),
+ .u.arithmetic_op.p = (unsigned long)v,
+ .u.arithmetic_op.count = increments[0],
+ .u.arithmetic_op.expect_fault_p = 0,
+ },
+ [1] = {
+ .op = CPU_ADD_OP,
+ .len = sizeof(*v),
+ .u.arithmetic_op.p = (unsigned long)v,
+ .u.arithmetic_op.count = increments[1],
+ .u.arithmetic_op.expect_fault_p = 0,
+ },
+ };
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_two_add(void)
+{
+ int orig_v = 42, v, ret;
+ int64_t increments[2] = { 99, 123 };
+ const char *test_name = "test_two_add";
+
+ v = orig_v;
+ ret = test_two_add_op(&v, increments);
+ if (ret) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (v != orig_v + increments[0] + increments[1]) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, v,
+ orig_v + increments[0] + increments[1]);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_or_op(int *v, uint64_t mask)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_OR_OP,
+ .len = sizeof(*v),
+ .u.bitwise_op.p = (unsigned long)v,
+ .u.bitwise_op.mask = mask,
+ .u.bitwise_op.expect_fault_p = 0,
+ },
+ };
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_or(void)
+{
+ int orig_v = 0xFF00000, v, ret;
+ uint32_t mask = 0xFFF;
+ const char *test_name = "test_or";
+
+ v = orig_v;
+ ret = test_or_op(&v, mask);
+ if (ret) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (v != (orig_v | mask)) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, v, orig_v | mask);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_and_op(int *v, uint64_t mask)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_AND_OP,
+ .len = sizeof(*v),
+ .u.bitwise_op.p = (unsigned long)v,
+ .u.bitwise_op.mask = mask,
+ .u.bitwise_op.expect_fault_p = 0,
+ },
+ };
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_and(void)
+{
+ int orig_v = 0xF00, v, ret;
+ uint32_t mask = 0xFFF;
+ const char *test_name = "test_and";
+
+ v = orig_v;
+ ret = test_and_op(&v, mask);
+ if (ret) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (v != (orig_v & mask)) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, v, orig_v & mask);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_xor_op(int *v, uint64_t mask)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_XOR_OP,
+ .len = sizeof(*v),
+ .u.bitwise_op.p = (unsigned long)v,
+ .u.bitwise_op.mask = mask,
+ .u.bitwise_op.expect_fault_p = 0,
+ },
+ };
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_xor(void)
+{
+ int orig_v = 0xF00, v, ret;
+ uint32_t mask = 0xFFF;
+ const char *test_name = "test_xor";
+
+ v = orig_v;
+ ret = test_xor_op(&v, mask);
+ if (ret) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (v != (orig_v ^ mask)) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, v, orig_v ^ mask);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_lshift_op(int *v, uint32_t bits)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_LSHIFT_OP,
+ .len = sizeof(*v),
+ .u.shift_op.p = (unsigned long)v,
+ .u.shift_op.bits = bits,
+ .u.shift_op.expect_fault_p = 0,
+ },
+ };
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_lshift(void)
+{
+ int orig_v = 0xF00, v, ret;
+ uint32_t bits = 5;
+ const char *test_name = "test_lshift";
+
+ v = orig_v;
+ ret = test_lshift_op(&v, bits);
+ if (ret) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (v != (orig_v << bits)) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, v, orig_v << bits);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_rshift_op(int *v, uint32_t bits)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_RSHIFT_OP,
+ .len = sizeof(*v),
+ .u.shift_op.p = (unsigned long)v,
+ .u.shift_op.bits = bits,
+ .u.shift_op.expect_fault_p = 0,
+ },
+ };
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_rshift(void)
+{
+ int orig_v = 0xF00, v, ret;
+ uint32_t bits = 5;
+ const char *test_name = "test_rshift";
+
+ v = orig_v;
+ ret = test_rshift_op(&v, bits);
+ if (ret) {
+ ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (v != (orig_v >> bits)) {
+ ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+ test_name, v, orig_v >> bits);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_cmpxchg_op(void *v, void *expect, void *old, void *n,
+ size_t len)
+{
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_op_cmpxchg(v, expect, old, n, len, cpu);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_cmpxchg_success(void)
+{
+ int ret;
+ uint64_t orig_v = 1, v, expect = 1, old = 0, n = 3;
+ const char *test_name = "test_cmpxchg success";
+
+ v = orig_v;
+ ret = test_cmpxchg_op(&v, &expect, &old, &n, sizeof(uint64_t));
+ if (ret < 0) {
+ ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (ret) {
+ ksft_test_result_fail("%s returned %d, expecting %d\n",
+ test_name, ret, 0);
+ return -1;
+ }
+ if (v != n) {
+ ksft_test_result_fail("%s v is %lld, expecting %lld\n",
+ test_name, (long long)v, (long long)n);
+ return -1;
+ }
+ if (old != orig_v) {
+ ksft_test_result_fail("%s old is %lld, expecting %lld\n",
+ test_name, (long long)old,
+ (long long)orig_v);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_cmpxchg_fail(void)
+{
+ int ret;
+ uint64_t orig_v = 1, v, expect = 123, old = 0, n = 3;
+ const char *test_name = "test_cmpxchg fail";
+
+ v = orig_v;
+ ret = test_cmpxchg_op(&v, &expect, &old, &n, sizeof(uint64_t));
+ if (ret < 0) {
+ ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (ret == 0) {
+ ksft_test_result_fail("%s returned %d, expecting %d\n",
+ test_name, ret, 1);
+ return -1;
+ }
+ if (v == n) {
+ ksft_test_result_fail("%s returned %lld, expecting %lld\n",
+ test_name, (long long)v,
+ (long long)orig_v);
+ return -1;
+ }
+ if (old != orig_v) {
+ ksft_test_result_fail("%s old is %lld, expecting %lld\n",
+ test_name, (long long)old,
+ (long long)orig_v);
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_memcpy_expect_fault_op(void *dst, void *src, size_t len)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_MEMCPY_OP,
+ .len = len,
+ .u.memcpy_op.dst = (unsigned long)dst,
+ .u.memcpy_op.src = (unsigned long)src,
+ .u.memcpy_op.expect_fault_dst = 0,
+ /* Return EAGAIN on fault. */
+ .u.memcpy_op.expect_fault_src = 1,
+ },
+ };
+ int cpu;
+
+ cpu = cpu_op_get_current_cpu();
+ return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+static int test_memcpy_fault(void)
+{
+ int ret;
+ char buf1[TESTBUFLEN];
+ const char *test_name = "test_memcpy_fault";
+
+ /* Test memcpy */
+ ret = test_memcpy_op(buf1, NULL, TESTBUFLEN);
+ if (!ret || (ret < 0 && errno != EFAULT)) {
+ ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ /* Test memcpy expect fault */
+ ret = test_memcpy_expect_fault_op(buf1, NULL, TESTBUFLEN);
+ if (!ret || (ret < 0 && errno != EAGAIN)) {
+ ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int do_test_unknown_op(void)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = -1, /* Unknown */
+ .len = 0,
+ },
+ };
+ int cpu;
+
+ cpu = cpu_op_get_current_cpu();
+ return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+static int test_unknown_op(void)
+{
+ int ret;
+ const char *test_name = "test_unknown_op";
+
+ ret = do_test_unknown_op();
+ if (!ret || (ret < 0 && errno != EINVAL)) {
+ ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int do_test_max_ops(void)
+{
+ struct cpu_op opvec[] = {
+ [0] = { .op = CPU_MB_OP, },
+ [1] = { .op = CPU_MB_OP, },
+ [2] = { .op = CPU_MB_OP, },
+ [3] = { .op = CPU_MB_OP, },
+ [4] = { .op = CPU_MB_OP, },
+ [5] = { .op = CPU_MB_OP, },
+ [6] = { .op = CPU_MB_OP, },
+ [7] = { .op = CPU_MB_OP, },
+ [8] = { .op = CPU_MB_OP, },
+ [9] = { .op = CPU_MB_OP, },
+ [10] = { .op = CPU_MB_OP, },
+ [11] = { .op = CPU_MB_OP, },
+ [12] = { .op = CPU_MB_OP, },
+ [13] = { .op = CPU_MB_OP, },
+ [14] = { .op = CPU_MB_OP, },
+ [15] = { .op = CPU_MB_OP, },
+ };
+ int cpu;
+
+ cpu = cpu_op_get_current_cpu();
+ return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+static int test_max_ops(void)
+{
+ int ret;
+ const char *test_name = "test_max_ops";
+
+ ret = do_test_max_ops();
+ if (ret < 0) {
+ ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int do_test_too_many_ops(void)
+{
+ struct cpu_op opvec[] = {
+ [0] = { .op = CPU_MB_OP, },
+ [1] = { .op = CPU_MB_OP, },
+ [2] = { .op = CPU_MB_OP, },
+ [3] = { .op = CPU_MB_OP, },
+ [4] = { .op = CPU_MB_OP, },
+ [5] = { .op = CPU_MB_OP, },
+ [6] = { .op = CPU_MB_OP, },
+ [7] = { .op = CPU_MB_OP, },
+ [8] = { .op = CPU_MB_OP, },
+ [9] = { .op = CPU_MB_OP, },
+ [10] = { .op = CPU_MB_OP, },
+ [11] = { .op = CPU_MB_OP, },
+ [12] = { .op = CPU_MB_OP, },
+ [13] = { .op = CPU_MB_OP, },
+ [14] = { .op = CPU_MB_OP, },
+ [15] = { .op = CPU_MB_OP, },
+ [16] = { .op = CPU_MB_OP, },
+ };
+ int cpu;
+
+ cpu = cpu_op_get_current_cpu();
+ return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+static int test_too_many_ops(void)
+{
+ int ret;
+ const char *test_name = "test_too_many_ops";
+
+ ret = do_test_too_many_ops();
+ if (!ret || (ret < 0 && errno != EINVAL)) {
+ ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+/* Use 64kB len, largest page size known on Linux. */
+static int test_memcpy_single_too_large(void)
+{
+ int i, ret;
+ char buf1[TESTBUFLEN_PAGE_MAX + 1];
+ char buf2[TESTBUFLEN_PAGE_MAX + 1];
+ const char *test_name = "test_memcpy_single_too_large";
+
+ /* Test memcpy */
+ for (i = 0; i < TESTBUFLEN_PAGE_MAX + 1; i++)
+ buf1[i] = (char)i;
+ memset(buf2, 0, TESTBUFLEN_PAGE_MAX + 1);
+ ret = test_memcpy_op(buf2, buf1, TESTBUFLEN_PAGE_MAX + 1);
+ if (!ret || (ret < 0 && errno != EINVAL)) {
+ ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+static int test_memcpy_single_ok_sum_too_large_op(void *dst, void *src,
+ size_t len)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_MEMCPY_OP,
+ .len = len,
+ .u.memcpy_op.dst = (unsigned long)dst,
+ .u.memcpy_op.src = (unsigned long)src,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ [1] = {
+ .op = CPU_MEMCPY_OP,
+ .len = len,
+ .u.memcpy_op.dst = (unsigned long)dst,
+ .u.memcpy_op.src = (unsigned long)src,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ };
+ int ret, cpu;
+
+ do {
+ cpu = cpu_op_get_current_cpu();
+ ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_memcpy_single_ok_sum_too_large(void)
+{
+ int i, ret;
+ char buf1[TESTBUFLEN];
+ char buf2[TESTBUFLEN];
+ const char *test_name = "test_memcpy_single_ok_sum_too_large";
+
+ /* Test memcpy */
+ for (i = 0; i < TESTBUFLEN; i++)
+ buf1[i] = (char)i;
+ memset(buf2, 0, TESTBUFLEN);
+ ret = test_memcpy_single_ok_sum_too_large_op(buf2, buf1, TESTBUFLEN);
+ if (!ret || (ret < 0 && errno != EINVAL)) {
+ ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+/*
+ * Iterate over large uninitialized arrays to trigger page faults.
+ * This includes reading from zero pages.
+ */
+int test_page_fault(void)
+{
+ int ret = 0;
+ uint64_t i;
+ const char *test_name = "test_page_fault";
+
+ for (i = 0; i < NR_PF_ARRAY; i++) {
+ ret = test_memcpy_op(pf_array_dst[i],
+ pf_array_src[i],
+ PF_ARRAY_LEN);
+ if (ret) {
+ ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return ret;
+ }
+ }
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+}
+
+/*
+ * Try to use 2MB huge pages.
+ */
+int test_hugetlb(void)
+{
+ int ret = 0;
+ uint64_t i;
+ const char *test_name = "test_hugetlb";
+ int *dst, *src;
+
+ dst = mmap(NULL, HUGEMAPLEN, PROT_READ | PROT_WRITE,
+ MAP_HUGETLB | MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ if (dst == MAP_FAILED) {
+ switch (errno) {
+ case ENOMEM:
+ case ENOENT:
+ case EINVAL:
+ ksft_test_result_skip("%s test.\n", test_name);
+ goto end;
+ default:
+ break;
+ }
+ perror("mmap");
+ abort();
+ }
+ src = mmap(NULL, HUGEMAPLEN, PROT_READ | PROT_WRITE,
+ MAP_HUGETLB | MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ if (src == MAP_FAILED) {
+ if (errno == ENOMEM) {
+ ksft_test_result_skip("%s test.\n", test_name);
+ goto unmap_dst;
+ }
+ perror("mmap");
+ abort();
+ }
+
+ /* Read/write from/to huge zero pages. */
+ for (i = 0; i < NR_HUGE_ARRAY; i++) {
+ ret = test_memcpy_op(dst + (i * PF_ARRAY_LEN / sizeof(int)),
+ src + (i * PF_ARRAY_LEN / sizeof(int)),
+ PF_ARRAY_LEN);
+ if (ret) {
+ ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return ret;
+ }
+ }
+ for (i = 0; i < NR_HUGE_ARRAY * (PF_ARRAY_LEN / sizeof(int)); i++)
+ src[i] = i;
+
+ for (i = 0; i < NR_HUGE_ARRAY; i++) {
+ ret = test_memcpy_op(dst + (i * PF_ARRAY_LEN / sizeof(int)),
+ src + (i * PF_ARRAY_LEN / sizeof(int)),
+ PF_ARRAY_LEN);
+ if (ret) {
+ ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+ test_name, ret, strerror(errno));
+ return ret;
+ }
+ }
+
+ for (i = 0; i < NR_HUGE_ARRAY * (PF_ARRAY_LEN / sizeof(int)); i++) {
+ if (dst[i] != i) {
+ ksft_test_result_fail("%s mismatch, expect %d, got %d\n",
+ test_name, i, dst[i]);
+ return ret;
+ }
+ }
+
+ ksft_test_result_pass("%s test\n", test_name);
+
+ if (munmap(src, HUGEMAPLEN)) {
+ perror("munmap");
+ abort();
+ }
+unmap_dst:
+ if (munmap(dst, HUGEMAPLEN)) {
+ perror("munmap");
+ abort();
+ }
+end:
+ return 0;
+}
+
+static int test_cmpxchg_op_cpu(void *v, void *expect, void *old, void *n,
+ size_t len, int cpu)
+{
+ int ret;
+
+ do {
+ ret = cpu_op_cmpxchg(v, expect, old, n, len, cpu);
+ } while (ret == -1 && errno == EAGAIN);
+
+ return ret;
+}
+
+static int test_over_possible_cpu(void)
+{
+ int ret;
+ uint64_t orig_v = 1, v, expect = 1, old = 0, n = 3;
+ const char *test_name = "test_over_possible_cpu";
+
+ v = orig_v;
+ ret = test_cmpxchg_op_cpu(&v, &expect, &old, &n, sizeof(uint64_t),
+ 0xFFFFFFFF);
+ if (ret == 0) {
+ ksft_test_result_fail("%s test: ret = %d\n",
+ test_name, ret);
+ return -1;
+ }
+ if (ret < 0 && errno == EINVAL) {
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+ }
+ ksft_test_result_fail("%s returned %d, errno %s, expecting %d, errno %s\n",
+ test_name, ret, strerror(errno),
+ 0, strerror(EINVAL));
+ return -1;
+}
+
+static int test_allowed_affinity(void)
+{
+ int ret;
+ uint64_t orig_v = 1, v, expect = 1, old = 0, n = 3;
+ const char *test_name = "test_allowed_affinity";
+ cpu_set_t allowed_cpus, cpuset;
+
+ ret = sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+ if (ret) {
+ ksft_test_result_fail("%s returned %d, errno %s\n",
+ test_name, ret, strerror(errno));
+ return -1;
+ }
+ if (!(CPU_ISSET(0, &allowed_cpus) && CPU_ISSET(1, &allowed_cpus))) {
+ ksft_test_result_skip("%s test. Requiring allowed CPUs 0 and 1.\n",
+ test_name);
+ return 0;
+ }
+ CPU_ZERO(&cpuset);
+ CPU_SET(0, &cpuset);
+ if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) {
+ ksft_test_result_fail("%s test. Unable to set affinity. errno = %s\n",
+ test_name, strerror(errno));
+ return -1;
+ }
+ v = orig_v;
+ ret = test_cmpxchg_op_cpu(&v, &expect, &old, &n, sizeof(uint64_t),
+ 1);
+ if (sched_setaffinity(0, sizeof(allowed_cpus), &allowed_cpus) != 0) {
+ ksft_test_result_fail("%s test. Unable to set affinity. errno = %s\n",
+ test_name, strerror(errno));
+ return -1;
+ }
+ if (ret == 0) {
+ ksft_test_result_fail("%s test: ret = %d\n",
+ test_name, ret);
+ return -1;
+ }
+
+ if (ret < 0 && errno == EINVAL) {
+ ksft_test_result_pass("%s test\n", test_name);
+ return 0;
+ }
+ ksft_test_result_fail("%s returned %d, errno %s, expecting %d, errno %s\n",
+ test_name, ret, strerror(errno),
+ 0, strerror(EINVAL));
+ return -1;
+}
+
+int main(int argc, char **argv)
+{
+ ksft_print_header();
+
+ test_ops_supported();
+ test_compare_eq_same();
+ test_compare_eq_diff();
+ test_compare_ne_same();
+ test_compare_ne_diff();
+ test_2compare_eq_index();
+ test_2compare_ne_index();
+ test_memcpy();
+ test_memcpy_u32();
+ test_memcpy_mb_memcpy();
+ test_add();
+ test_two_add();
+ test_or();
+ test_and();
+ test_xor();
+ test_lshift();
+ test_rshift();
+ test_cmpxchg_success();
+ test_cmpxchg_fail();
+ test_memcpy_fault();
+ test_unknown_op();
+ test_max_ops();
+ test_too_many_ops();
+ test_memcpy_single_too_large();
+ test_memcpy_single_ok_sum_too_large();
+ test_page_fault();
+ test_hugetlb();
+ test_over_possible_cpu();
+ test_allowed_affinity();
+
+ return ksft_exit_pass();
+}
--
2.11.0
^ permalink raw reply related
* [RFC PATCH for 4.21 11/16] cpu-opv/selftests: Provide cpu-op library
From: Mathieu Desnoyers @ 2018-10-10 19:19 UTC (permalink / raw)
To: Peter Zijlstra, Paul E . McKenney, Boqun Feng
Cc: linux-kernel, linux-api, Thomas Gleixner, Andy Lutomirski,
Dave Watson, Paul Turner, Andrew Morton, Russell King,
Ingo Molnar, H . Peter Anvin, Andi Kleen, Chris Lameter,
Ben Maurer, Steven Rostedt, Josh Triplett, Linus Torvalds,
Catalin Marinas, Will Deacon, Michael Kerrisk, Joel Fernandes,
Mathieu Desnoyers
In-Reply-To: <20181010191936.7495-1-mathieu.desnoyers@efficios.com>
This cpu-op helper library provides a user-space API to the cpu_opv()
system call.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
tools/testing/selftests/cpu-opv/cpu-op.c | 353 +++++++++++++++++++++++++++++++
tools/testing/selftests/cpu-opv/cpu-op.h | 42 ++++
2 files changed, 395 insertions(+)
create mode 100644 tools/testing/selftests/cpu-opv/cpu-op.c
create mode 100644 tools/testing/selftests/cpu-opv/cpu-op.h
diff --git a/tools/testing/selftests/cpu-opv/cpu-op.c b/tools/testing/selftests/cpu-opv/cpu-op.c
new file mode 100644
index 000000000000..575cd51da421
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/cpu-op.c
@@ -0,0 +1,353 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * cpu-op.c
+ *
+ * Copyright (C) 2017 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; only
+ * version 2.1 of the License.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * Lesser General Public License for more details.
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <syscall.h>
+#include <assert.h>
+#include <signal.h>
+
+#include "cpu-op.h"
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+#define ACCESS_ONCE(x) (*(__volatile__ __typeof__(x) *)&(x))
+#define WRITE_ONCE(x, v) __extension__ ({ ACCESS_ONCE(x) = (v); })
+#define READ_ONCE(x) ACCESS_ONCE(x)
+
+int cpu_opv(struct cpu_op *cpu_opv, int cpuopcnt, int cpu, int flags)
+{
+ return syscall(__NR_cpu_opv, cpu_opv, cpuopcnt, cpu, flags);
+}
+
+int cpu_op_get_current_cpu(void)
+{
+ int cpu;
+
+ cpu = sched_getcpu();
+ if (cpu < 0) {
+ perror("sched_getcpu()");
+ abort();
+ }
+ return cpu;
+}
+
+int cpu_op_cmpxchg(void *v, void *expect, void *old, void *n, size_t len,
+ int cpu)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_MEMCPY_OP,
+ .len = len,
+ .u.memcpy_op.dst = (unsigned long)old,
+ .u.memcpy_op.src = (unsigned long)v,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ [1] = {
+ .op = CPU_COMPARE_EQ_OP,
+ .len = len,
+ .u.compare_op.a = (unsigned long)v,
+ .u.compare_op.b = (unsigned long)expect,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ [2] = {
+ .op = CPU_MEMCPY_OP,
+ .len = len,
+ .u.memcpy_op.dst = (unsigned long)v,
+ .u.memcpy_op.src = (unsigned long)n,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ };
+
+ return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_add(void *v, int64_t count, size_t len, int cpu)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_ADD_OP,
+ .len = len,
+ .u.arithmetic_op.p = (unsigned long)v,
+ .u.arithmetic_op.count = count,
+ .u.arithmetic_op.expect_fault_p = 0,
+ },
+ };
+
+ return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv,
+ int cpu)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_COMPARE_EQ_OP,
+ .len = sizeof(intptr_t),
+ .u.compare_op.a = (unsigned long)v,
+ .u.compare_op.b = (unsigned long)&expect,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ [1] = {
+ .op = CPU_MEMCPY_OP,
+ .len = sizeof(intptr_t),
+ .u.memcpy_op.dst = (unsigned long)v,
+ .u.memcpy_op.src = (unsigned long)&newv,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ };
+
+ return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+static int cpu_op_cmpeqv_storep_expect_fault(intptr_t *v, intptr_t expect,
+ intptr_t *newp, int cpu)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_COMPARE_EQ_OP,
+ .len = sizeof(intptr_t),
+ .u.compare_op.a = (unsigned long)v,
+ .u.compare_op.b = (unsigned long)&expect,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ [1] = {
+ .op = CPU_MEMCPY_OP,
+ .len = sizeof(intptr_t),
+ .u.memcpy_op.dst = (unsigned long)v,
+ .u.memcpy_op.src = (unsigned long)newp,
+ .u.memcpy_op.expect_fault_dst = 0,
+ /* Return EAGAIN on src fault. */
+ .u.memcpy_op.expect_fault_src = 1,
+ },
+ };
+
+ return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+ off_t voffp, intptr_t *load, int cpu)
+{
+ int ret;
+
+ do {
+ intptr_t oldv = READ_ONCE(*v);
+ intptr_t *newp = (intptr_t *)(oldv + voffp);
+
+ if (oldv == expectnot)
+ return 1;
+ ret = cpu_op_cmpeqv_storep_expect_fault(v, oldv, newp, cpu);
+ if (!ret) {
+ *load = oldv;
+ return 0;
+ }
+ } while (ret > 0);
+
+ return -1;
+}
+
+int cpu_op_cmpeqv_storev_storev(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t newv2,
+ intptr_t newv, int cpu)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_COMPARE_EQ_OP,
+ .len = sizeof(intptr_t),
+ .u.compare_op.a = (unsigned long)v,
+ .u.compare_op.b = (unsigned long)&expect,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ [1] = {
+ .op = CPU_MEMCPY_OP,
+ .len = sizeof(intptr_t),
+ .u.memcpy_op.dst = (unsigned long)v2,
+ .u.memcpy_op.src = (unsigned long)&newv2,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ [2] = {
+ .op = CPU_MEMCPY_OP,
+ .len = sizeof(intptr_t),
+ .u.memcpy_op.dst = (unsigned long)v,
+ .u.memcpy_op.src = (unsigned long)&newv,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ };
+
+ return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_cmpeqv_storev_mb_storev(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t newv2,
+ intptr_t newv, int cpu)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_COMPARE_EQ_OP,
+ .len = sizeof(intptr_t),
+ .u.compare_op.a = (unsigned long)v,
+ .u.compare_op.b = (unsigned long)&expect,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ [1] = {
+ .op = CPU_MEMCPY_OP,
+ .len = sizeof(intptr_t),
+ .u.memcpy_op.dst = (unsigned long)v2,
+ .u.memcpy_op.src = (unsigned long)&newv2,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ [2] = {
+ .op = CPU_MB_OP,
+ },
+ [3] = {
+ .op = CPU_MEMCPY_OP,
+ .len = sizeof(intptr_t),
+ .u.memcpy_op.dst = (unsigned long)v,
+ .u.memcpy_op.src = (unsigned long)&newv,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ };
+
+ return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t expect2,
+ intptr_t newv, int cpu)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_COMPARE_EQ_OP,
+ .len = sizeof(intptr_t),
+ .u.compare_op.a = (unsigned long)v,
+ .u.compare_op.b = (unsigned long)&expect,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ [1] = {
+ .op = CPU_COMPARE_EQ_OP,
+ .len = sizeof(intptr_t),
+ .u.compare_op.a = (unsigned long)v2,
+ .u.compare_op.b = (unsigned long)&expect2,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ [2] = {
+ .op = CPU_MEMCPY_OP,
+ .len = sizeof(intptr_t),
+ .u.memcpy_op.dst = (unsigned long)v,
+ .u.memcpy_op.src = (unsigned long)&newv,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ };
+
+ return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_cmpeqv_memcpy_storev(intptr_t *v, intptr_t expect,
+ void *dst, void *src, size_t len,
+ intptr_t newv, int cpu)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_COMPARE_EQ_OP,
+ .len = sizeof(intptr_t),
+ .u.compare_op.a = (unsigned long)v,
+ .u.compare_op.b = (unsigned long)&expect,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ [1] = {
+ .op = CPU_MEMCPY_OP,
+ .len = len,
+ .u.memcpy_op.dst = (unsigned long)dst,
+ .u.memcpy_op.src = (unsigned long)src,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ [2] = {
+ .op = CPU_MEMCPY_OP,
+ .len = sizeof(intptr_t),
+ .u.memcpy_op.dst = (unsigned long)v,
+ .u.memcpy_op.src = (unsigned long)&newv,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ };
+
+ return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_cmpeqv_memcpy_mb_storev(intptr_t *v, intptr_t expect,
+ void *dst, void *src, size_t len,
+ intptr_t newv, int cpu)
+{
+ struct cpu_op opvec[] = {
+ [0] = {
+ .op = CPU_COMPARE_EQ_OP,
+ .len = sizeof(intptr_t),
+ .u.compare_op.a = (unsigned long)v,
+ .u.compare_op.b = (unsigned long)&expect,
+ .u.compare_op.expect_fault_a = 0,
+ .u.compare_op.expect_fault_b = 0,
+ },
+ [1] = {
+ .op = CPU_MEMCPY_OP,
+ .len = len,
+ .u.memcpy_op.dst = (unsigned long)dst,
+ .u.memcpy_op.src = (unsigned long)src,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ [2] = {
+ .op = CPU_MB_OP,
+ },
+ [3] = {
+ .op = CPU_MEMCPY_OP,
+ .len = sizeof(intptr_t),
+ .u.memcpy_op.dst = (unsigned long)v,
+ .u.memcpy_op.src = (unsigned long)&newv,
+ .u.memcpy_op.expect_fault_dst = 0,
+ .u.memcpy_op.expect_fault_src = 0,
+ },
+ };
+
+ return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_addv(intptr_t *v, int64_t count, int cpu)
+{
+ return cpu_op_add(v, count, sizeof(intptr_t), cpu);
+}
diff --git a/tools/testing/selftests/cpu-opv/cpu-op.h b/tools/testing/selftests/cpu-opv/cpu-op.h
new file mode 100644
index 000000000000..075687a1365f
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/cpu-op.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * cpu-op.h
+ *
+ * (C) Copyright 2017-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef CPU_OPV_H
+#define CPU_OPV_H
+
+#include <stdlib.h>
+#include <stdint.h>
+#include <linux/cpu_opv.h>
+
+int cpu_opv(struct cpu_op *cpuopv, int cpuopcnt, int cpu, int flags);
+int cpu_op_get_current_cpu(void);
+
+int cpu_op_cmpxchg(void *v, void *expect, void *old, void *_new, size_t len,
+ int cpu);
+int cpu_op_add(void *v, int64_t count, size_t len, int cpu);
+
+int cpu_op_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu);
+int cpu_op_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+ off_t voffp, intptr_t *load, int cpu);
+int cpu_op_cmpeqv_storev_storev(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t newv2,
+ intptr_t newv, int cpu);
+int cpu_op_cmpeqv_storev_mb_storev(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t newv2,
+ intptr_t newv, int cpu);
+int cpu_op_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+ intptr_t *v2, intptr_t expect2,
+ intptr_t newv, int cpu);
+int cpu_op_cmpeqv_memcpy_storev(intptr_t *v, intptr_t expect,
+ void *dst, void *src, size_t len,
+ intptr_t newv, int cpu);
+int cpu_op_cmpeqv_memcpy_mb_storev(intptr_t *v, intptr_t expect,
+ void *dst, void *src, size_t len,
+ intptr_t newv, int cpu);
+int cpu_op_addv(intptr_t *v, int64_t count, int cpu);
+
+#endif /* CPU_OPV_H_ */
--
2.11.0
^ permalink raw reply related
* [RFC PATCH for 4.21 10/16] arm: Wire up cpu_opv system call
From: Mathieu Desnoyers @ 2018-10-10 19:19 UTC (permalink / raw)
To: Peter Zijlstra, Paul E . McKenney, Boqun Feng
Cc: linux-kernel, linux-api, Thomas Gleixner, Andy Lutomirski,
Dave Watson, Paul Turner, Andrew Morton, Russell King,
Ingo Molnar, H . Peter Anvin, Andi Kleen, Chris Lameter,
Ben Maurer, Steven Rostedt, Josh Triplett, Linus Torvalds,
Catalin Marinas, Will Deacon, Michael Kerrisk, Joel Fernandes,
Mathieu Desnoyers
In-Reply-To: <20181010191936.7495-1-mathieu.desnoyers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Russell King <linux@arm.linux.org.uk>
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Paul Turner <pjt@google.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Andi Kleen <andi@firstfloor.org>
CC: Dave Watson <davejwatson@fb.com>
CC: Chris Lameter <cl@linux.com>
CC: Ingo Molnar <mingo@redhat.com>
CC: Ben Maurer <bmaurer@fb.com>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: Josh Triplett <josh@joshtriplett.org>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: linux-api@vger.kernel.org
---
arch/arm/tools/syscall.tbl | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 8edf93b4490f..da2cb7a12644 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -414,3 +414,4 @@
397 common statx sys_statx
398 common rseq sys_rseq
399 common io_pgetevents sys_io_pgetevents
+400 common cpu_opv sys_cpu_opv
--
2.11.0
^ permalink raw reply related
* [RFC PATCH for 4.21 09/16] powerpc: Wire up cpu_opv system call
From: Mathieu Desnoyers @ 2018-10-10 19:19 UTC (permalink / raw)
To: Peter Zijlstra, Paul E . McKenney, Boqun Feng
Cc: linux-kernel, linux-api, Thomas Gleixner, Andy Lutomirski,
Dave Watson, Paul Turner, Andrew Morton, Russell King,
Ingo Molnar, H . Peter Anvin, Andi Kleen, Chris Lameter,
Ben Maurer, Steven Rostedt, Josh Triplett, Linus Torvalds,
Catalin Marinas, Will Deacon, Michael Kerrisk, Joel Fernandes,
Mathieu Desnoyers
In-Reply-To: <20181010191936.7495-1-mathieu.desnoyers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
CC: Michael Ellerman <mpe@ellerman.id.au>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: linuxppc-dev@lists.ozlabs.org
---
arch/powerpc/include/asm/systbl.h | 1 +
arch/powerpc/include/uapi/asm/unistd.h | 1 +
2 files changed, 2 insertions(+)
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 01b5171ea189..8f58710f5e8b 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -394,3 +394,4 @@ SYSCALL(pkey_free)
SYSCALL(pkey_mprotect)
SYSCALL(rseq)
COMPAT_SYS(io_pgetevents)
+SYSCALL(cpu_opv)
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index 985534d0b448..112e2c54750a 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -400,5 +400,6 @@
#define __NR_pkey_mprotect 386
#define __NR_rseq 387
#define __NR_io_pgetevents 388
+#define __NR_cpu_opv 389
#endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
--
2.11.0
^ permalink raw reply related
* [RFC PATCH for 4.21 08/16] x86: Wire up cpu_opv system call
From: Mathieu Desnoyers @ 2018-10-10 19:19 UTC (permalink / raw)
To: Peter Zijlstra, Paul E . McKenney, Boqun Feng
Cc: linux-kernel, linux-api, Thomas Gleixner, Andy Lutomirski,
Dave Watson, Paul Turner, Andrew Morton, Russell King,
Ingo Molnar, H . Peter Anvin, Andi Kleen, Chris Lameter,
Ben Maurer, Steven Rostedt, Josh Triplett, Linus Torvalds,
Catalin Marinas, Will Deacon, Michael Kerrisk, Joel Fernandes,
Mathieu Desnoyers
In-Reply-To: <20181010191936.7495-1-mathieu.desnoyers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul Turner <pjt@google.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Andi Kleen <andi@firstfloor.org>
CC: Dave Watson <davejwatson@fb.com>
CC: Chris Lameter <cl@linux.com>
CC: Ingo Molnar <mingo@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Ben Maurer <bmaurer@fb.com>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: Josh Triplett <josh@joshtriplett.org>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Russell King <linux@arm.linux.org.uk>
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Michael Kerrisk <mtk.manpages@gmail.com>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: linux-api@vger.kernel.org
---
arch/x86/entry/syscalls/syscall_32.tbl | 1 +
arch/x86/entry/syscalls/syscall_64.tbl | 1 +
2 files changed, 2 insertions(+)
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 3cf7b533b3d1..d3253547e15e 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -398,3 +398,4 @@
384 i386 arch_prctl sys_arch_prctl __ia32_compat_sys_arch_prctl
385 i386 io_pgetevents sys_io_pgetevents __ia32_compat_sys_io_pgetevents
386 i386 rseq sys_rseq __ia32_sys_rseq
+387 i386 cpu_opv sys_cpu_opv __ia32_sys_cpu_opv
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index f0b1709a5ffb..1391971b1517 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -343,6 +343,7 @@
332 common statx __x64_sys_statx
333 common io_pgetevents __x64_sys_io_pgetevents
334 common rseq __x64_sys_rseq
+335 common cpu_opv __x64_sys_cpu_opv
#
# x32-specific system call numbers start at 512 to avoid cache impact
--
2.11.0
^ permalink raw reply related
* [RFC PATCH for 4.21 07/16] cpu_opv: limit amount of virtual address space used by cpu_opv
From: Mathieu Desnoyers @ 2018-10-10 19:19 UTC (permalink / raw)
To: Peter Zijlstra, Paul E . McKenney, Boqun Feng
Cc: linux-kernel, linux-api, Thomas Gleixner, Andy Lutomirski,
Dave Watson, Paul Turner, Andrew Morton, Russell King,
Ingo Molnar, H . Peter Anvin, Andi Kleen, Chris Lameter,
Ben Maurer, Steven Rostedt, Josh Triplett, Linus Torvalds,
Catalin Marinas, Will Deacon, Michael Kerrisk, Joel Fernandes,
Mathieu Desnoyers
In-Reply-To: <20181010191936.7495-1-mathieu.desnoyers@efficios.com>
Introduce sysctl cpu_opv_va_max_bytes, which limits the amount of
virtual address space that can be used by cpu_opv.
Its default value is the maximum amount of virtual address space which
can be used by a single cpu_opv system call (256 kB on x86).
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul Turner <pjt@google.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Andi Kleen <andi@firstfloor.org>
CC: Dave Watson <davejwatson@fb.com>
CC: Chris Lameter <cl@linux.com>
CC: Ingo Molnar <mingo@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Ben Maurer <bmaurer@fb.com>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: Josh Triplett <josh@joshtriplett.org>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Russell King <linux@arm.linux.org.uk>
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Michael Kerrisk <mtk.manpages@gmail.com>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: linux-api@vger.kernel.org
---
kernel/cpu_opv.c | 75 +++++++++++++++++++++++++++++++++++++++++++++++++++++++-
kernel/sysctl.c | 15 ++++++++++++
2 files changed, 89 insertions(+), 1 deletion(-)
diff --git a/kernel/cpu_opv.c b/kernel/cpu_opv.c
index c4e4040bb5ff..db144b71d51a 100644
--- a/kernel/cpu_opv.c
+++ b/kernel/cpu_opv.c
@@ -30,6 +30,7 @@
#include <linux/pagemap.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
+#include <linux/atomic.h>
#include <asm/ptrace.h>
#include <asm/byteorder.h>
#include <asm/cacheflush.h>
@@ -49,6 +50,16 @@
/* Maximum number of virtual addresses per op. */
#define CPU_OP_VEC_MAX_ADDR (2 * CPU_OP_VEC_LEN_MAX)
+/* Maximum address range size (aligned on SHMLBA) per virtual address. */
+#define CPU_OP_RANGE_PER_ADDR_MAX (2 * SHMLBA)
+
+/*
+ * Minimum value for sysctl_cpu_opv_va_max_bytes is the maximum virtual memory
+ * space needed by one cpu_opv system call.
+ */
+#define CPU_OPV_VA_MAX_BYTES_MIN \
+ (CPU_OP_VEC_MAX_ADDR * CPU_OP_RANGE_PER_ADDR_MAX)
+
union op_fn_data {
uint8_t _u8;
uint16_t _u16;
@@ -81,6 +92,15 @@ typedef int (*op_fn_t)(union op_fn_data *data, uint64_t v, uint32_t len);
*/
static DEFINE_MUTEX(cpu_opv_offline_lock);
+/* Maximum virtual address space which can be used by cpu_opv. */
+int sysctl_cpu_opv_va_max_bytes __read_mostly;
+int sysctl_cpu_opv_va_max_bytes_min;
+
+static atomic_t cpu_opv_va_allocated_bytes;
+
+/* Waitqueue for cpu_opv blocked on virtual address space reservation. */
+static DECLARE_WAIT_QUEUE_HEAD(cpu_opv_va_wait);
+
/*
* The cpu_opv system call executes a vector of operations on behalf of
* user-space on a specific CPU with preemption disabled. It is inspired
@@ -546,6 +566,43 @@ static int cpu_opv_pin_pages_op(struct cpu_op *op,
return 0;
}
+/*
+ * Approximate the amount of virtual address space required per
+ * vaddr to a worse-case of CPU_OP_RANGE_PER_ADDR_MAX.
+ */
+static int cpu_opv_reserve_va(int nr_vaddr, int *reserved_va)
+{
+ int nr_bytes = nr_vaddr * CPU_OP_RANGE_PER_ADDR_MAX;
+ int old_bytes, new_bytes;
+
+ WARN_ON_ONCE(*reserved_va != 0);
+ if (nr_bytes > sysctl_cpu_opv_va_max_bytes) {
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+ }
+ do {
+ wait_event(cpu_opv_va_wait,
+ (old_bytes = atomic_read(&cpu_opv_va_allocated_bytes)) +
+ nr_bytes <= sysctl_cpu_opv_va_max_bytes);
+ new_bytes = old_bytes + nr_bytes;
+ } while (atomic_cmpxchg(&cpu_opv_va_allocated_bytes,
+ old_bytes, new_bytes) != old_bytes);
+
+ *reserved_va = nr_bytes;
+ return 0;
+}
+
+static void cpu_opv_unreserve_va(int *reserved_va)
+{
+ int nr_bytes = *reserved_va;
+
+ if (!nr_bytes)
+ return;
+ atomic_sub(nr_bytes, &cpu_opv_va_allocated_bytes);
+ wake_up(&cpu_opv_va_wait);
+ *reserved_va = 0;
+}
+
static int cpu_opv_pin_pages(struct cpu_op *cpuop, int cpuopcnt,
struct cpu_opv_vaddr *vaddr_ptrs)
{
@@ -1057,7 +1114,7 @@ SYSCALL_DEFINE4(cpu_opv, struct cpu_op __user *, ucpuopv, int, cpuopcnt,
.nr_vaddr = 0,
.is_kmalloc = false,
};
- int ret, i, nr_vaddr = 0;
+ int ret, i, nr_vaddr = 0, reserved_va = 0;
bool retry = false;
if (unlikely(flags & ~CPU_OP_NR_FLAG))
@@ -1082,6 +1139,9 @@ SYSCALL_DEFINE4(cpu_opv, struct cpu_op __user *, ucpuopv, int, cpuopcnt,
vaddr_ptrs.is_kmalloc = true;
}
again:
+ ret = cpu_opv_reserve_va(nr_vaddr, &reserved_va);
+ if (ret)
+ goto end;
ret = cpu_opv_pin_pages(cpuopv, cpuopcnt, &vaddr_ptrs);
if (ret)
goto end;
@@ -1106,6 +1166,7 @@ SYSCALL_DEFINE4(cpu_opv, struct cpu_op __user *, ucpuopv, int, cpuopcnt,
*/
if (vaddr_ptrs.nr_vaddr)
vm_unmap_aliases();
+ cpu_opv_unreserve_va(&reserved_va);
if (retry) {
retry = false;
vaddr_ptrs.nr_vaddr = 0;
@@ -1115,3 +1176,15 @@ SYSCALL_DEFINE4(cpu_opv, struct cpu_op __user *, ucpuopv, int, cpuopcnt,
kfree(vaddr_ptrs.addr);
return ret;
}
+
+/*
+ * Dynamic initialization is required on sparc because SHMLBA is not a
+ * constant.
+ */
+static int __init cpu_opv_init(void)
+{
+ sysctl_cpu_opv_va_max_bytes = CPU_OPV_VA_MAX_BYTES_MIN;
+ sysctl_cpu_opv_va_max_bytes_min = CPU_OPV_VA_MAX_BYTES_MIN;
+ return 0;
+}
+core_initcall(cpu_opv_init);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index cc02050fd0c4..eb34c6be2aa4 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -175,6 +175,11 @@ extern int unaligned_dump_stack;
extern int no_unaligned_warning;
#endif
+#ifdef CONFIG_CPU_OPV
+extern int sysctl_cpu_opv_va_max_bytes;
+extern int sysctl_cpu_opv_va_max_bytes_min;
+#endif
+
#ifdef CONFIG_PROC_SYSCTL
/**
@@ -1233,6 +1238,16 @@ static struct ctl_table kern_table[] = {
.extra2 = &one,
},
#endif
+#ifdef CONFIG_CPU_OPV
+ {
+ .procname = "cpu_opv_va_max_bytes",
+ .data = &sysctl_cpu_opv_va_max_bytes,
+ .maxlen = sizeof(sysctl_cpu_opv_va_max_bytes),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &sysctl_cpu_opv_va_max_bytes_min,
+ },
+#endif
{ }
};
--
2.11.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox