[PATCH 3/5] x86/fpu/xstate: Fix PTRACE frames for XSAVES
From: Yu-cheng Yu
Date: Fri Jun 17 2016 - 16:13:40 EST
XSAVES uses compacted format and is a kernel instruction. The kernel
should use standard-format, non-supervisor state data for PTRACE.
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>
Reviewed-by: Dave Hansen <dave.hansen@xxxxxxxxx>
---
arch/x86/include/asm/fpu/xstate.h | 5 +-
arch/x86/kernel/fpu/regset.c | 55 +++++++++----
arch/x86/kernel/fpu/xstate.c | 167 +++++++++++++++++++++++++++++++++++++-
3 files changed, 210 insertions(+), 17 deletions(-)
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 92f376c..ae55a43 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -51,5 +51,8 @@ void fpu__xstate_clear_all_cpu_caps(void);
void *get_xsave_addr(struct xregs_state *xsave, int xstate);
const void *get_xsave_field_ptr(int xstate_field);
int using_compacted_format(void);
-
+int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
+ void __user *ubuf, struct xregs_state *xsave);
+int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
+ struct xregs_state *xsave);
#endif
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 81422df..5248491 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -4,6 +4,7 @@
#include <asm/fpu/internal.h>
#include <asm/fpu/signal.h>
#include <asm/fpu/regset.h>
+#include <asm/fpu/xstate.h>
/*
* The xstateregs_active() routine is the same as the regset_fpregs_active() routine,
@@ -85,21 +86,28 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
if (!boot_cpu_has(X86_FEATURE_XSAVE))
return -ENODEV;
- fpu__activate_fpstate_read(fpu);
-
xsave = &fpu->state.xsave;
- /*
- * Copy the 48bytes defined by the software first into the xstate
- * memory layout in the thread struct, so that we can copy the entire
- * xstateregs to the user using one user_regset_copyout().
- */
- memcpy(&xsave->i387.sw_reserved,
- xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
- /*
- * Copy the xstate memory layout.
- */
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+ fpu__activate_fpstate_read(fpu);
+
+ if (using_compacted_format()) {
+ ret = copyout_from_xsaves(pos, count, kbuf, ubuf, xsave);
+ } else {
+ fpstate_sanitize_xstate(fpu);
+ /*
+ * Copy the 48 bytes defined by the software into the xsave
+ * area in the thread struct, so that we can copy the whole
+ * area to user using one user_regset_copyout().
+ */
+ memcpy(&xsave->i387.sw_reserved,
+ xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
+
+ /*
+ * Copy the xstate memory layout.
+ */
+ ret = user_regset_copyout(&pos,
+ &count, &kbuf, &ubuf, xsave, 0, -1);
+ }
return ret;
}
@@ -114,11 +122,28 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
if (!boot_cpu_has(X86_FEATURE_XSAVE))
return -ENODEV;
- fpu__activate_fpstate_write(fpu);
+ /*
+ * A whole standard-format XSAVE buffer is needed.
+ */
+ if ((pos != 0) || (count < fpu_user_xstate_size))
+ return -EFAULT;
xsave = &fpu->state.xsave;
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+ fpu__activate_fpstate_write(fpu);
+
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
+ ret = copyin_to_xsaves(kbuf, ubuf, xsave);
+ else
+ ret = user_regset_copyin(&pos,
+ &count, &kbuf, &ubuf, xsave, 0, -1);
+
+ /*
+ * In case of failure, mark all states as init.
+ */
+ if (ret)
+ fpstate_init(&fpu->state);
+
/*
* mxcsr reserved bits must be masked to zero for security reasons.
*/
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index ec7e53b..8d5fb03 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -11,6 +11,7 @@
#include <asm/fpu/internal.h>
#include <asm/fpu/signal.h>
#include <asm/fpu/regset.h>
+#include <asm/fpu/xstate.h>
#include <asm/tlbflush.h>
@@ -697,7 +698,13 @@ void __init fpu__init_system_xstate(void)
return;
}
- update_regset_xstate_info(fpu_kernel_xstate_size, xfeatures_mask);
+ /*
+ * Update info used for ptrace frames; use standard-format size and no
+ * supervisor xstates.
+ */
+ update_regset_xstate_info(fpu_user_xstate_size,
+ xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR);
+
fpu__init_prepare_fx_sw_frame();
setup_init_fpu_buf();
setup_xstate_comp();
@@ -968,3 +975,161 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
return 0;
}
+
+/*
+ * This is similar to user_regset_copyout(), but will not add offset to
+ * the source data pointer or increment pos, count, kbuf, and ubuf.
+ */
+static inline int xstate_copyout(unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf,
+ const void *data, const int start_pos,
+ const int end_pos)
+{
+ if ((count == 0) || (pos < start_pos))
+ return 0;
+
+ if (end_pos < 0 || pos < end_pos) {
+ unsigned int copy =
+ (end_pos < 0 ? count : min(count, end_pos - pos));
+
+ if (kbuf)
+ memcpy(kbuf + pos, data, copy);
+ else if (__copy_to_user(ubuf + pos, data, copy))
+ return -EFAULT;
+ }
+ return 0;
+}
+
+/*
+ * Convert from kernel XSAVES compacted format to standard format and copy
+ * to a ptrace buffer. It supports partial copy but pos always starts from
+ * zero. This is called from xstateregs_get() and there we check the cpu
+ * has XSAVES.
+ */
+int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
+ void __user *ubuf, struct xregs_state *xsave)
+{
+ unsigned int offset, size;
+ int ret, i;
+ struct xstate_header header;
+
+ /*
+ * Currently copy_regset_to_user() starts from pos 0.
+ */
+ if (unlikely(pos != 0))
+ return -EFAULT;
+
+ /*
+ * The destination is a ptrace buffer; we put in only user xstates.
+ */
+ memset(&header, 0, sizeof(header));
+ header.xfeatures = xsave->header.xfeatures;
+ header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR;
+
+ /*
+ * Copy xregs_state->header.
+ */
+ offset = offsetof(struct xregs_state, header);
+ size = sizeof(header);
+
+ ret = xstate_copyout(offset, size, kbuf, ubuf, &header, 0, count);
+
+ if (ret)
+ return ret;
+
+ for (i = 0; i < XFEATURE_MAX; i++) {
+ /*
+ * Copy only in-use xstates.
+ */
+ if ((header.xfeatures >> i) & 1) {
+ void *src = __raw_xsave_addr(xsave, 1 << i);
+
+ offset = xstate_offsets[i];
+ size = xstate_sizes[i];
+
+ ret = xstate_copyout(offset, size, kbuf, ubuf, src, 0,
+ count);
+
+ if (ret)
+ return ret;
+
+ if (offset + size >= count)
+ break;
+ }
+
+ }
+
+ /*
+ * Fill xsave->i387.sw_reserved value for ptrace frame.
+ */
+ offset = offsetof(struct fxregs_state, sw_reserved);
+ size = sizeof(xstate_fx_sw_bytes);
+
+ ret = xstate_copyout(offset, size, kbuf, ubuf, xstate_fx_sw_bytes, 0,
+ count);
+
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+/*
+ * Convert from a ptrace standard-format buffer to kernel XSAVES format
+ * and copy to the target thread. This is called from xstateregs_set() and
+ * there we check the cpu has XSAVES and a whole standard-sized buffer
+ * exists.
+ */
+int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
+ struct xregs_state *xsave)
+{
+ unsigned int offset, size;
+ int i;
+ u64 xfeatures;
+ u64 allowed_features;
+
+ offset = offsetof(struct xregs_state, header);
+ size = sizeof(xfeatures);
+
+ if (kbuf)
+ memcpy(&xfeatures, kbuf + offset, size);
+ else if (__copy_from_user(&xfeatures, ubuf + offset, size))
+ return -EFAULT;
+
+ /*
+ * Reject if the user sets any disabled or supervisor features.
+ */
+ allowed_features = xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR;
+
+ if (xfeatures & ~allowed_features)
+ return -EINVAL;
+
+ for (i = 0; i < XFEATURE_MAX; i++) {
+ u64 mask = ((u64)1 << i);
+
+ if (xfeatures & mask) {
+ void *dst = __raw_xsave_addr(xsave, 1 << i);
+
+ offset = xstate_offsets[i];
+ size = xstate_sizes[i];
+
+ if (kbuf)
+ memcpy(dst, kbuf + offset, size);
+ else if (__copy_from_user(dst, ubuf + offset, size))
+ return -EFAULT;
+ }
+ }
+
+ /*
+ * The state that came in from userspace was user-state only.
+ * Mask all the user states out of 'xfeatures'.
+ */
+ xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR;
+
+ /*
+ * Add back in the features that came in from userspace.
+ */
+ xsave->header.xfeatures |= xfeatures;
+
+ return 0;
+}
--
1.9.1