ARM: 7566/1: vfp: fix save and restore when running on pre-VFPv3 and CONFIG_VFPv3 set

After commit 846a1368 ("ARM: vfp: fix
saving d16-d31 vfp registers on v6+ kernels"), the OMAP 2430SDP board
started crashing during boot with omap2plus_defconfig:

[    3.875122] mmcblk0: mmc0:e624 SD04G 3.69 GiB
[    3.915954]  mmcblk0: p1
[    4.086639] Internal error: Oops - undefined instruction: 0 [#1] SMP ARM
[    4.093719] Modules linked in:
[    4.096954] CPU: 0    Not tainted  (3.6.0-02232-g759e00b8 #570)
[    4.103149] PC is at vfp_reload_hw+0x1c/0x44
[    4.107666] LR is at __und_usr_fault_32+0x0/0x8

It turns out that the context save/restore fix unmasked a latent bug
in commit 5aaf2544 ("ARM: 6203/1: Make
VFPv3 usable on ARMv6").  When CONFIG_VFPv3 is set, but the kernel is
booted on a pre-VFPv3 core, the code attempts to save and restore the
d16-d31 VFP registers.  These are only present on non-D16 VFPv3+, so
this results in an undefined instruction exception.  The code didn't
crash before commit 846a1368 because the save and restore code was
only touching d0-d15, present on all VFP.

Fix by implementing a request from Russell King to add a new HWCAP
flag that affirmatively indicates the presence of the d16-d31
registers:

   http://marc.info/?l=linux-arm-kernel&m=135013547905283&w=2

and some feedback from Måns to clarify the name of the HWCAP flag.
Signed-off-by: Paul Walmsley <paul@pwsan.com>
Cc: Tony Lindgren <tony@atomide.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Martin <dave.martin@linaro.org>
Cc: Måns Rullgård <mans.rullgard@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/include/asm/vfpmacros.h

@@ -27,9 +27,9 @@
 #if __LINUX_ARM_ARCH__ <= 6
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
-	tst	\tmp, #HWCAP_VFPv3D16
-	ldceql	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
-	addne	\base, \base, #32*4		    @ step over unused register space
+	tst	\tmp, #HWCAP_VFPD32
+	ldcnel	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
@@ -51,9 +51,9 @@
 #if __LINUX_ARM_ARCH__ <= 6
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
-	tst	\tmp, #HWCAP_VFPv3D16
-	stceql	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
-	addne	\base, \base, #32*4		    @ step over unused register space
+	tst	\tmp, #HWCAP_VFPD32
+	stcnel	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field

arch/arm/include/uapi/asm/hwcap.h

@@ -18,11 +18,12 @@
 #define HWCAP_THUMBEE	(1 << 11)
 #define HWCAP_NEON	(1 << 12)
 #define HWCAP_VFPv3	(1 << 13)
-#define HWCAP_VFPv3D16	(1 << 14)
+#define HWCAP_VFPv3D16	(1 << 14)	/* also set for VFPv4-D16 */
 #define HWCAP_TLS	(1 << 15)
 #define HWCAP_VFPv4	(1 << 16)
 #define HWCAP_IDIVA	(1 << 17)
 #define HWCAP_IDIVT	(1 << 18)
+#define HWCAP_VFPD32	(1 << 19)	/* set if VFP has 32 regs (not 16) */
 #define HWCAP_IDIV	(HWCAP_IDIVA | HWCAP_IDIVT)
 
 

arch/arm/vfp/vfpmodule.c

@@ -701,11 +701,14 @@ static int __init vfp_init(void)
 			elf_hwcap |= HWCAP_VFPv3;
 
 			/*
-			 * Check for VFPv3 D16. CPUs in this configuration
-			 * only have 16 x 64bit registers.
+			 * Check for VFPv3 D16 and VFPv4 D16.  CPUs in
+			 * this configuration only have 16 x 64bit
+			 * registers.
 			 */
 			if (((fmrx(MVFR0) & MVFR0_A_SIMD_MASK)) == 1)
-				elf_hwcap |= HWCAP_VFPv3D16;
+				elf_hwcap |= HWCAP_VFPv3D16; /* also v4-D16 */
+			else
+				elf_hwcap |= HWCAP_VFPD32;
 		}
 #endif
 		/*