[PATCH v10 11/28] x86/fpu/xstate: Update the XSTATE buffer address finder to support dynamic states

[Chang S. Bae]

__raw_xsave_addr() returns the requested component's pointer in an XSTATE
buffer, by simply looking up the offset table. The offset used to be fixed,
but, with dynamic user states, it becomes variable.

calculate_xstate_buf_size_from_mask() has a routine to find an offset at
runtime. Refactor to use it for the address finder.

Signed-off-by: Chang S. Bae <chang.seok.bae@xxxxxxxxx>
Reviewed-by: Len Brown <len.brown@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
---
Changes from v9:
* Update the function description. (Borislav Petkov)

Changes from v5:
* Updated for future proofed __raw_xsave_addr().

Changes from v3:
* Added the function description in the kernel-doc style. (Borislav Petkov)
* Removed 'no functional change' in the changelog. (Borislav Petkov)
---
 arch/x86/kernel/fpu/xstate.c | 68 ++++++++++++++++++++++++++----------
 1 file changed, 49 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index f56db3f77282..6929db20be0a 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -139,6 +139,33 @@ static bool xfeature_is_supervisor(int xfeature_nr)
 	return ecx & 1;
 }
 
+/**
+ * get_xstate_comp_offset - Find the feature offset in the compacted format.
+ * @mask:	This bitmap tells which components to be saved in the
+ *		format.
+ * @feature_nr:	The feature number
+ *
+ * Returns:	The offset value
+ */
+static unsigned int get_xstate_comp_offset(u64 mask, int feature_nr)
+{
+	unsigned int next_offset, offset = 0;
+	int i;
+
+	if (feature_nr < FIRST_EXTENDED_XFEATURE)
+		return xstate_comp_offsets[feature_nr];
+
+	for (next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE, i = FIRST_EXTENDED_XFEATURE;
+	     i <= feature_nr; i++) {
+		if (!(mask & BIT_ULL(i)))
+			continue;
+
+		offset = xstate_64byte_aligned[i] ? ALIGN(next_offset, 64) : next_offset;
+		next_offset += xstate_sizes[i];
+	}
+	return offset;
+}
+
 /**
  * calculate_xstate_buf_size_from_mask - Calculate an xstate buffer size
  * @mask:	A bitmap to tell which components to be saved in the buffer.
@@ -150,8 +177,8 @@ static bool xfeature_is_supervisor(int xfeature_nr)
  */
 unsigned int calculate_xstate_buf_size_from_mask(u64 mask)
 {
-	unsigned int size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-	int i, nr;
+	unsigned int offset;
+	int nr;
 
 	if (!mask)
 		return 0;
@@ -167,7 +194,7 @@ unsigned int calculate_xstate_buf_size_from_mask(u64 mask)
 
 	nr = fls64(mask) - 1;
 	if (nr < FIRST_EXTENDED_XFEATURE)
-		return size;
+		return FXSAVE_SIZE + XSAVE_HDR_SIZE;
 
 	/*
 	 * Each state offset in the non-compacted format is fixed. Take the
@@ -180,15 +207,8 @@ unsigned int calculate_xstate_buf_size_from_mask(u64 mask)
 	 * With the given mask, no relevant size is found so far. So,
 	 * calculate it by summing up each state size.
 	 */
-	for (i = FIRST_EXTENDED_XFEATURE; i <= nr; i++) {
-		if (!(mask & BIT_ULL(i)))
-			continue;
-
-		if (xstate_64byte_aligned[i])
-			size = ALIGN(size, 64);
-		size += xstate_sizes[i];
-	}
-	return size;
+	offset = get_xstate_comp_offset(mask, nr);
+	return offset + xstate_sizes[nr];
 }
 
 /*
@@ -941,19 +961,29 @@ void fpu__resume_cpu(void)
  */
 static void *__raw_xsave_addr(struct fpu *fpu, int xfeature_nr)
 {
+	unsigned int offset;
 	void *xsave;
 
 	if (!xfeature_enabled(xfeature_nr)) {
-		WARN_ON_FPU(1);
-		return NULL;
-	}
+		goto not_found;
+	} else if (!fpu) {
+		xsave = &init_fpstate.xsave;
 
-	if (fpu)
+		offset = get_xstate_comp_offset(xfeatures_mask_all, xfeature_nr);
+		if (offset > sizeof(init_fpstate))
+			goto not_found;
+	} else if (!(fpu->state_mask & BIT_ULL(xfeature_nr))) {
+		goto not_found;
+	} else {
 		xsave = &fpu->state->xsave;
-	else
-		xsave = &init_fpstate.xsave;
+		offset = get_xstate_comp_offset(fpu->state_mask, xfeature_nr);
+	}
+
+	return xsave + offset;
 
-	return xsave + xstate_comp_offsets[xfeature_nr];
+not_found:
+	WARN_ON_FPU(1);
+	return NULL;
 }
 /*
  * Given the xsave area and a state inside, this function returns the
-- 
2.17.1