x86, fpu: Unify signal handling code paths for x86 and x86_64 kernels

Currently for x86 and x86_32 binaries, fpstate in the user sigframe is copied
to/from the fpstate in the task struct.

And in the case of signal delivery for x86_64 binaries, if the fpstate is live
in the CPU registers, then the live state is copied directly to the user
sigframe. Otherwise  fpstate in the task struct is copied to the user sigframe.
During restore, fpstate in the user sigframe is restored directly to the live
CPU registers.

Historically, different code paths led to different bugs. For example,
x86_64 code path was not preemption safe till recently. Also there is lot
of code duplication for support of new features like xsave etc.

Unify signal handling code paths for x86 and x86_64 kernels.

New strategy is as follows:

Signal delivery: Both for 32/64-bit frames, align the core math frame area to
64bytes as needed by xsave (this where the main fpu/extended state gets copied
to and excludes the legacy compatibility fsave header for the 32-bit [f]xsave
frames). If the state is live, copy the register state directly to the user
frame. If not live, copy the state in the thread struct to the user frame. And
for 32-bit [f]xsave frames, construct the fsave header separately before
the actual [f]xsave area.

Signal return: As the 32-bit frames with [f]xstate has an additional
'fsave' header, copy everything back from the user sigframe to the
fpstate in the task structure and reconstruct the fxstate from the 'fsave'
header (Also user passed pointers may not be correctly aligned for
any attempt to directly restore any partial state). At the next fpstate usage,
everything will be restored to the live CPU registers.
For all the 64-bit frames and the 32-bit fsave frame, restore the state from
the user sigframe directly to the live CPU registers. 64-bit signals always
restored the math frame directly, so we can expect the math frame pointer
to be correctly aligned. For 32-bit fsave frames, there are no alignment
requirements, so we can restore the state directly.

"lat_sig catch" microbenchmark numbers (for x86, x86_64, x86_32 binaries) are
with in the noise range with this change.

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Link: http://lkml.kernel.org/r/1343171129-2747-4-git-send-email-suresh.b.siddha@intel.com
[ Merged in compilation fix ]
Link: http://lkml.kernel.org/r/1344544736.8326.17.camel@sbsiddha-desk.sc.intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

1 files changed, 258 insertions, 174 deletions

diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 7a3d4df9eaf6..0923d27f23df 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -10,9 +10,7 @@
 #include <linux/compat.h>
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
-#ifdef CONFIG_IA32_EMULATION
-#include <asm/sigcontext32.h>
-#endif
+#include <asm/sigframe.h>
 #include <asm/xcr.h>
 
 /*
@@ -25,11 +23,7 @@ u64 pcntxt_mask;
  */
 static struct xsave_struct *init_xstate_buf;
 
-struct _fpx_sw_bytes fx_sw_reserved;
-#ifdef CONFIG_IA32_EMULATION
-struct _fpx_sw_bytes fx_sw_reserved_ia32;
-#endif
-
+static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
 static unsigned int *xstate_offsets, *xstate_sizes, xstate_features;
 
 /*
@@ -44,9 +38,9 @@ static unsigned int *xstate_offsets, *xstate_sizes, xstate_features;
  */
 void __sanitize_i387_state(struct task_struct *tsk)
 {
-	u64 xstate_bv;
-	int feature_bit = 0x2;
 	struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
+	int feature_bit = 0x2;
+	u64 xstate_bv;
 
 	if (!fx)
 		return;
@@ -104,215 +98,314 @@ void __sanitize_i387_state(struct task_struct *tsk)
  * Check for the presence of extended state information in the
  * user fpstate pointer in the sigcontext.
  */
-int check_for_xstate(struct i387_fxsave_struct __user *buf,
-		     void __user *fpstate,
-		     struct _fpx_sw_bytes *fx_sw_user)
+static inline int check_for_xstate(struct i387_fxsave_struct __user *buf,
+				   void __user *fpstate,
+				   struct _fpx_sw_bytes *fx_sw)
 {
 	int min_xstate_size = sizeof(struct i387_fxsave_struct) +
 			      sizeof(struct xsave_hdr_struct);
 	unsigned int magic2;
-	int err;
 
-	err = __copy_from_user(fx_sw_user, &buf->sw_reserved[0],
-			       sizeof(struct _fpx_sw_bytes));
-	if (err)
-		return -EFAULT;
+	if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
+		return -1;
 
-	/*
-	 * First Magic check failed.
-	 */
-	if (fx_sw_user->magic1 != FP_XSTATE_MAGIC1)
-		return -EINVAL;
+	/* Check for the first magic field and other error scenarios. */
+	if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
+	    fx_sw->xstate_size < min_xstate_size ||
+	    fx_sw->xstate_size > xstate_size ||
+	    fx_sw->xstate_size > fx_sw->extended_size)
+		return -1;
 
 	/*
-	 * Check for error scenarios.
-	 */
-	if (fx_sw_user->xstate_size < min_xstate_size ||
-	    fx_sw_user->xstate_size > xstate_size ||
-	    fx_sw_user->xstate_size > fx_sw_user->extended_size)
-		return -EINVAL;
-
-	err = __get_user(magic2, (__u32 __user *) (fpstate +
-						   fx_sw_user->extended_size -
-						   FP_XSTATE_MAGIC2_SIZE));
-	if (err)
-		return err;
-	/*
 	 * Check for the presence of second magic word at the end of memory
 	 * layout. This detects the case where the user just copied the legacy
 	 * fpstate layout with out copying the extended state information
 	 * in the memory layout.
 	 */
-	if (magic2 != FP_XSTATE_MAGIC2)
-		return -EFAULT;
+	if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
+	    || magic2 != FP_XSTATE_MAGIC2)
+		return -1;
 
 	return 0;
 }
 
-#ifdef CONFIG_X86_64
 /*
  * Signal frame handlers.
  */
+static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
+{
+	if (use_fxsr()) {
+		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+		struct user_i387_ia32_struct env;
+		struct _fpstate_ia32 __user *fp = buf;
 
-int save_i387_xstate(void __user *buf)
+		convert_from_fxsr(&env, tsk);
+
+		if (__copy_to_user(buf, &env, sizeof(env)) ||
+		    __put_user(xsave->i387.swd, &fp->status) ||
+		    __put_user(X86_FXSR_MAGIC, &fp->magic))
+			return -1;
+	} else {
+		struct i387_fsave_struct __user *fp = buf;
+		u32 swd;
+		if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
+			return -1;
+	}
+
+	return 0;
+}
+
+static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
 {
-	struct task_struct *tsk = current;
-	int err = 0;
+	struct xsave_struct __user *x = buf;
+	struct _fpx_sw_bytes *sw_bytes;
+	u32 xstate_bv;
+	int err;
 
-	if (!access_ok(VERIFY_WRITE, buf, sig_xstate_size))
-		return -EACCES;
+	/* Setup the bytes not touched by the [f]xsave and reserved for SW. */
+	sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
+	err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
 
-	BUG_ON(sig_xstate_size < xstate_size);
+	if (!use_xsave())
+		return err;
 
-	if ((unsigned long)buf % 64)
-		pr_err("%s: bad fpstate %p\n", __func__, buf);
+	err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
 
-	if (!used_math())
-		return 0;
+	/*
+	 * Read the xstate_bv which we copied (directly from the cpu or
+	 * from the state in task struct) to the user buffers.
+	 */
+	err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
 
-	if (user_has_fpu()) {
-		if (use_xsave())
-			err = xsave_user(buf);
-		else
-			err = fxsave_user(buf);
+	/*
+	 * For legacy compatible, we always set FP/SSE bits in the bit
+	 * vector while saving the state to the user context. This will
+	 * enable us capturing any changes(during sigreturn) to
+	 * the FP/SSE bits by the legacy applications which don't touch
+	 * xstate_bv in the xsave header.
+	 *
+	 * xsave aware apps can change the xstate_bv in the xsave
+	 * header as well as change any contents in the memory layout.
+	 * xrestore as part of sigreturn will capture all the changes.
+	 */
+	xstate_bv |= XSTATE_FPSSE;
 
-		if (unlikely(err)) {
-			__clear_user(buf, xstate_size);
-			return err;
-		}
+	err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
+
+	return err;
+}
+
+static inline int save_user_xstate(struct xsave_struct __user *buf)
+{
+	int err;
+
+	if (use_xsave())
+		err = xsave_user(buf);
+	else if (use_fxsr())
+		err = fxsave_user((struct i387_fxsave_struct __user *) buf);
+	else
+		err = fsave_user((struct i387_fsave_struct __user *) buf);
+
+	if (unlikely(err) && __clear_user(buf, xstate_size))
+		err = -EFAULT;
+	return err;
+}
+
+/*
+ * Save the fpu, extended register state to the user signal frame.
+ *
+ * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
+ *  state is copied.
+ *  'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
+ *
+ *	buf == buf_fx for 64-bit frames and 32-bit fsave frame.
+ *	buf != buf_fx for 32-bit frames with fxstate.
+ *
+ * If the fpu, extended register state is live, save the state directly
+ * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
+ * copy the thread's fpu state to the user frame starting at 'buf_fx'.
+ *
+ * If this is a 32-bit frame with fxstate, put a fsave header before
+ * the aligned state at 'buf_fx'.
+ *
+ * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
+ * indicating the absence/presence of the extended state to the user.
+ */
+int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
+{
+	struct xsave_struct *xsave = &current->thread.fpu.state->xsave;
+	struct task_struct *tsk = current;
+	int ia32_fxstate = (buf != buf_fx);
+
+	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+			 config_enabled(CONFIG_IA32_EMULATION));
+
+	if (!access_ok(VERIFY_WRITE, buf, size))
+		return -EACCES;
+
+	if (!HAVE_HWFP)
+		return fpregs_soft_get(current, NULL, 0,
+			sizeof(struct user_i387_ia32_struct), NULL,
+			(struct _fpstate_ia32 __user *) buf) ? -1 : 1;
+
+	if (user_has_fpu()) {
+		/* Save the live register state to the user directly. */
+		if (save_user_xstate(buf_fx))
+			return -1;
+		/* Update the thread's fxstate to save the fsave header. */
+		if (ia32_fxstate)
+			fpu_fxsave(&tsk->thread.fpu);
 		user_fpu_end();
 	} else {
 		sanitize_i387_state(tsk);
-		if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave,
-				   xstate_size))
+		if (__copy_to_user(buf_fx, xsave, xstate_size))
 			return -1;
 	}
 
-	clear_used_math(); /* trigger finit */
+	/* Save the fsave header for the 32-bit frames. */
+	if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
+		return -1;
 
-	if (use_xsave()) {
-		struct _fpstate __user *fx = buf;
-		struct _xstate __user *x = buf;
-		u64 xstate_bv;
+	if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
+		return -1;
+
+	drop_fpu(tsk);	/* trigger finit */
+
+	return 0;
+}
 
-		err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved,
-				     sizeof(struct _fpx_sw_bytes));
+static inline void
+sanitize_restored_xstate(struct task_struct *tsk,
+			 struct user_i387_ia32_struct *ia32_env,
+			 u64 xstate_bv, int fx_only)
+{
+	struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+	struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr;
 
-		err |= __put_user(FP_XSTATE_MAGIC2,
-				  (__u32 __user *) (buf + sig_xstate_size
-						    - FP_XSTATE_MAGIC2_SIZE));
+	if (use_xsave()) {
+		/* These bits must be zero. */
+		xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
 
 		/*
-		 * Read the xstate_bv which we copied (directly from the cpu or
-		 * from the state in task struct) to the user buffers and
-		 * set the FP/SSE bits.
+		 * Init the state that is not present in the memory
+		 * layout and not enabled by the OS.
 		 */
-		err |= __get_user(xstate_bv, &x->xstate_hdr.xstate_bv);
+		if (fx_only)
+			xsave_hdr->xstate_bv = XSTATE_FPSSE;
+		else
+			xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv);
+	}
 
+	if (use_fxsr()) {
 		/*
-		 * For legacy compatible, we always set FP/SSE bits in the bit
-		 * vector while saving the state to the user context. This will
-		 * enable us capturing any changes(during sigreturn) to
-		 * the FP/SSE bits by the legacy applications which don't touch
-		 * xstate_bv in the xsave header.
-		 *
-		 * xsave aware apps can change the xstate_bv in the xsave
-		 * header as well as change any contents in the memory layout.
-		 * xrestore as part of sigreturn will capture all the changes.
+		 * mscsr reserved bits must be masked to zero for security
+		 * reasons.
 		 */
-		xstate_bv |= XSTATE_FPSSE;
-
-		err |= __put_user(xstate_bv, &x->xstate_hdr.xstate_bv);
+		xsave->i387.mxcsr &= mxcsr_feature_mask;
 
-		if (err)
-			return err;
+		convert_to_fxsr(tsk, ia32_env);
 	}
-
-	return 1;
 }
 
 /*
- * Restore the extended state if present. Otherwise, restore the FP/SSE
- * state.
+ * Restore the extended state if present. Otherwise, restore the FP/SSE state.
  */
-static int restore_user_xstate(void __user *buf)
+static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only)
 {
-	struct _fpx_sw_bytes fx_sw_user;
-	u64 mask;
-	int err;
-
-	if (((unsigned long)buf % 64) ||
-	     check_for_xstate(buf, buf, &fx_sw_user))
-		goto fx_only;
-
-	mask = fx_sw_user.xstate_bv;
-
-	/*
-	 * restore the state passed by the user.
-	 */
-	err = xrestore_user(buf, mask);
-	if (err)
-		return err;
-
-	/*
-	 * init the state skipped by the user.
-	 */
-	mask = pcntxt_mask & ~mask;
-	if (unlikely(mask))
-		xrstor_state(init_xstate_buf, mask);
-
-	return 0;
-
-fx_only:
-	/*
-	 * couldn't find the extended state information in the
-	 * memory layout. Restore just the FP/SSE and init all
-	 * the other extended state.
-	 */
-	xrstor_state(init_xstate_buf, pcntxt_mask & ~XSTATE_FPSSE);
-	return fxrstor_checking((__force struct i387_fxsave_struct *)buf);
+	if (use_xsave()) {
+		if ((unsigned long)buf % 64 || fx_only) {
+			u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE;
+			xrstor_state(init_xstate_buf, init_bv);
+			return fxrstor_checking((__force void *) buf);
+		} else {
+			u64 init_bv = pcntxt_mask & ~xbv;
+			if (unlikely(init_bv))
+				xrstor_state(init_xstate_buf, init_bv);
+			return xrestore_user(buf, xbv);
+		}
+	} else if (use_fxsr()) {
+		return fxrstor_checking((__force void *) buf);
+	} else
+		return frstor_checking((__force void *) buf);
 }
 
-/*
- * This restores directly out of user space. Exceptions are handled.
- */
-int restore_i387_xstate(void __user *buf)
+int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 {
+	int ia32_fxstate = (buf != buf_fx);
 	struct task_struct *tsk = current;
-	int err = 0;
+	int state_size = xstate_size;
+	u64 xstate_bv = 0;
+	int fx_only = 0;
+
+	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+			 config_enabled(CONFIG_IA32_EMULATION));
 
 	if (!buf) {
-		if (used_math())
-			goto clear;
+		drop_fpu(tsk);
 		return 0;
-	} else
-		if (!access_ok(VERIFY_READ, buf, sig_xstate_size))
-			return -EACCES;
+	}
+
+	if (!access_ok(VERIFY_READ, buf, size))
+		return -EACCES;
+
+	if (!used_math() && init_fpu(tsk))
+		return -1;
 
-	if (!used_math()) {
-		err = init_fpu(tsk);
-		if (err)
-			return err;
+	if (!HAVE_HWFP) {
+		return fpregs_soft_set(current, NULL,
+				       0, sizeof(struct user_i387_ia32_struct),
+				       NULL, buf) != 0;
 	}
 
-	user_fpu_begin();
-	if (use_xsave())
-		err = restore_user_xstate(buf);
-	else
-		err = fxrstor_checking((__force struct i387_fxsave_struct *)
-				       buf);
-	if (unlikely(err)) {
+	if (use_xsave()) {
+		struct _fpx_sw_bytes fx_sw_user;
+		if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
+			/*
+			 * Couldn't find the extended state information in the
+			 * memory layout. Restore just the FP/SSE and init all
+			 * the other extended state.
+			 */
+			state_size = sizeof(struct i387_fxsave_struct);
+			fx_only = 1;
+		} else {
+			state_size = fx_sw_user.xstate_size;
+			xstate_bv = fx_sw_user.xstate_bv;
+		}
+	}
+
+	if (ia32_fxstate) {
+		/*
+		 * For 32-bit frames with fxstate, copy the user state to the
+		 * thread's fpu state, reconstruct fxstate from the fsave
+		 * header. Sanitize the copied state etc.
+		 */
+		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+		struct user_i387_ia32_struct env;
+
+		stop_fpu_preload(tsk);
+		unlazy_fpu(tsk);
+
+		if (__copy_from_user(xsave, buf_fx, state_size) ||
+		    __copy_from_user(&env, buf, sizeof(env))) {
+			drop_fpu(tsk);
+			return -1;
+		}
+
+		sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
+	} else {
 		/*
-		 * Encountered an error while doing the restore from the
-		 * user buffer, clear the fpu state.
+		 * For 64-bit frames and 32-bit fsave frames, restore the user
+		 * state to the registers directly (with exceptions handled).
 		 */
-clear:
-		clear_fpu(tsk);
-		clear_used_math();
+		user_fpu_begin();
+		if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) {
+			drop_fpu(tsk);
+			return -1;
+		}
 	}
-	return err;
+
+	return 0;
 }
-#endif
 
 /*
  * Prepare the SW reserved portion of the fxsave memory layout, indicating
@@ -323,31 +416,22 @@ clear:
  */
 static void prepare_fx_sw_frame(void)
 {
-	int size_extended = (xstate_size - sizeof(struct i387_fxsave_struct)) +
-			     FP_XSTATE_MAGIC2_SIZE;
-
-	sig_xstate_size = sizeof(struct _fpstate) + size_extended;
-
-#ifdef CONFIG_IA32_EMULATION
-	sig_xstate_ia32_size = sizeof(struct _fpstate_ia32) + size_extended;
-#endif
+	int fsave_header_size = sizeof(struct i387_fsave_struct);
+	int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
 
-	memset(&fx_sw_reserved, 0, sizeof(fx_sw_reserved));
+	if (config_enabled(CONFIG_X86_32))
+		size += fsave_header_size;
 
 	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
-	fx_sw_reserved.extended_size = sig_xstate_size;
+	fx_sw_reserved.extended_size = size;
 	fx_sw_reserved.xstate_bv = pcntxt_mask;
 	fx_sw_reserved.xstate_size = xstate_size;
-#ifdef CONFIG_IA32_EMULATION
-	memcpy(&fx_sw_reserved_ia32, &fx_sw_reserved,
-	       sizeof(struct _fpx_sw_bytes));
-	fx_sw_reserved_ia32.extended_size = sig_xstate_ia32_size;
-#endif
-}
 
-#ifdef CONFIG_X86_64
-unsigned int sig_xstate_size = sizeof(struct _fpstate);
-#endif
+	if (config_enabled(CONFIG_IA32_EMULATION)) {
+		fx_sw_reserved_ia32 = fx_sw_reserved;
+		fx_sw_reserved_ia32.extended_size += fsave_header_size;
+	}
+}
 
 /*
  * Enable the extended processor state save/restore feature