powerpc/64s: Add support for a store forwarding barrier at kernel entry/exit

commit a048a07d7f4535baa4cbad6bc024f175317ab938 upstream.

On some CPUs we can prevent a vulnerability related to store-to-load
forwarding by preventing store forwarding between privilege domains,
by inserting a barrier in kernel entry and exit paths.

This is known to be the case on at least Power7, Power8 and Power9
powerpc CPUs.

Barriers must be inserted generally before the first load after moving
to a higher privilege, and after the last store before moving to a
lower privilege, HV and PR privilege transitions must be protected.

Barriers are added as patch sections, with all kernel/hypervisor entry
points patched, and the exit points to lower privilge levels patched
similarly to the RFI flush patching.

Firmware advertisement is not implemented yet, so CPU flush types
are hard coded.

Thanks to Michal Suchánek for bug fixes and review.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Mauricio Faria de Oliveira <mauricfo@linux.vnet.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michal Suchánek <msuchanek@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 115 insertions, 0 deletions

diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index d89d54fa6acc..cf1398e3c2e0 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -22,6 +22,7 @@
 #include <asm/page.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
+#include <asm/security_features.h>
 #include <asm/firmware.h>
 #include <asm/setup.h>
 
@@ -117,6 +118,120 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 }
 
 #ifdef CONFIG_PPC_BOOK3S_64
+void do_stf_entry_barrier_fixups(enum stf_barrier_type types)
+{
+	unsigned int instrs[3], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___stf_entry_barrier_fixup),
+	end = PTRRELOC(&__stop___stf_entry_barrier_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+
+	i = 0;
+	if (types & STF_BARRIER_FALLBACK) {
+		instrs[i++] = 0x7d4802a6; /* mflr r10		*/
+		instrs[i++] = 0x60000000; /* branch patched below */
+		instrs[i++] = 0x7d4803a6; /* mtlr r10		*/
+	} else if (types & STF_BARRIER_EIEIO) {
+		instrs[i++] = 0x7e0006ac; /* eieio + bit 6 hint */
+	} else if (types & STF_BARRIER_SYNC_ORI) {
+		instrs[i++] = 0x7c0004ac; /* hwsync		*/
+		instrs[i++] = 0xe94d0000; /* ld r10,0(r13)	*/
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+	}
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+
+		if (types & STF_BARRIER_FALLBACK)
+			patch_branch(dest + 1, (unsigned long)&stf_barrier_fallback,
+				     BRANCH_SET_LINK);
+		else
+			patch_instruction(dest + 1, instrs[1]);
+
+		patch_instruction(dest + 2, instrs[2]);
+	}
+
+	printk(KERN_DEBUG "stf-barrier: patched %d entry locations (%s barrier)\n", i,
+		(types == STF_BARRIER_NONE)                  ? "no" :
+		(types == STF_BARRIER_FALLBACK)              ? "fallback" :
+		(types == STF_BARRIER_EIEIO)                 ? "eieio" :
+		(types == (STF_BARRIER_SYNC_ORI))            ? "hwsync"
+		                                           : "unknown");
+}
+
+void do_stf_exit_barrier_fixups(enum stf_barrier_type types)
+{
+	unsigned int instrs[6], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___stf_exit_barrier_fixup),
+	end = PTRRELOC(&__stop___stf_exit_barrier_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+	instrs[3] = 0x60000000; /* nop */
+	instrs[4] = 0x60000000; /* nop */
+	instrs[5] = 0x60000000; /* nop */
+
+	i = 0;
+	if (types & STF_BARRIER_FALLBACK || types & STF_BARRIER_SYNC_ORI) {
+		if (cpu_has_feature(CPU_FTR_HVMODE)) {
+			instrs[i++] = 0x7db14ba6; /* mtspr 0x131, r13 (HSPRG1) */
+			instrs[i++] = 0x7db04aa6; /* mfspr r13, 0x130 (HSPRG0) */
+		} else {
+			instrs[i++] = 0x7db243a6; /* mtsprg 2,r13	*/
+			instrs[i++] = 0x7db142a6; /* mfsprg r13,1    */
+	        }
+		instrs[i++] = 0x7c0004ac; /* hwsync		*/
+		instrs[i++] = 0xe9ad0000; /* ld r13,0(r13)	*/
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+		if (cpu_has_feature(CPU_FTR_HVMODE)) {
+			instrs[i++] = 0x7db14aa6; /* mfspr r13, 0x131 (HSPRG1) */
+		} else {
+			instrs[i++] = 0x7db242a6; /* mfsprg r13,2 */
+		}
+	} else if (types & STF_BARRIER_EIEIO) {
+		instrs[i++] = 0x7e0006ac; /* eieio + bit 6 hint */
+	}
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+		patch_instruction(dest + 1, instrs[1]);
+		patch_instruction(dest + 2, instrs[2]);
+		patch_instruction(dest + 3, instrs[3]);
+		patch_instruction(dest + 4, instrs[4]);
+		patch_instruction(dest + 5, instrs[5]);
+	}
+	printk(KERN_DEBUG "stf-barrier: patched %d exit locations (%s barrier)\n", i,
+		(types == STF_BARRIER_NONE)                  ? "no" :
+		(types == STF_BARRIER_FALLBACK)              ? "fallback" :
+		(types == STF_BARRIER_EIEIO)                 ? "eieio" :
+		(types == (STF_BARRIER_SYNC_ORI))            ? "hwsync"
+		                                           : "unknown");
+}
+
+
+void do_stf_barrier_fixups(enum stf_barrier_type types)
+{
+	do_stf_entry_barrier_fixups(types);
+	do_stf_exit_barrier_fixups(types);
+}
+
 void do_rfi_flush_fixups(enum l1d_flush_type types)
 {
 	unsigned int instrs[3], *dest;