arm64/gcs: Context switch GCS state for EL0

There are two registers controlling the GCS state of EL0, GCSPR_EL0 which
is the current GCS pointer and GCSCRE0_EL1 which has enable bits for the
specific GCS functionality enabled for EL0. Manage these on context switch
and process lifetime events, GCS is reset on exec().  Also ensure that
any changes to the GCS memory are visible to other PEs and that changes
from other PEs are visible on this one by issuing a GCSB DSYNC when
moving to or from a thread with GCS.

Since the current GCS configuration of a thread will be visible to
userspace we store the configuration in the format used with userspace
and provide a helper which configures the system register as needed.

On systems that support GCS we always allow access to GCSPR_EL0, this
facilitates reporting of GCS faults if userspace implements disabling of
GCS on error - the GCS can still be discovered and examined even if GCS
has been disabled.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Thiago Jung Bauermann <thiago.bauermann@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20241001-arm64-gcs-v13-21-222b78d87eee@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/include/asm/gcs.h

@@ -48,4 +48,28 @@ static inline u64 gcsss2(void)
 	return Xt;
 }
 
+#ifdef CONFIG_ARM64_GCS
+
+static inline bool task_gcs_el0_enabled(struct task_struct *task)
+{
+	return current->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE;
+}
+
+void gcs_set_el0_mode(struct task_struct *task);
+void gcs_free(struct task_struct *task);
+void gcs_preserve_current_state(void);
+
+#else
+
+static inline bool task_gcs_el0_enabled(struct task_struct *task)
+{
+	return false;
+}
+
+static inline void gcs_set_el0_mode(struct task_struct *task) { }
+static inline void gcs_free(struct task_struct *task) { }
+static inline void gcs_preserve_current_state(void) { }
+
+#endif
+
 #endif

arch/arm64/include/asm/processor.h

@@ -185,6 +185,12 @@ struct thread_struct {
 	u64			svcr;
 	u64			tpidr2_el0;
 	u64			por_el0;
+#ifdef CONFIG_ARM64_GCS
+	unsigned int		gcs_el0_mode;
+	u64			gcspr_el0;
+	u64			gcs_base;
+	u64			gcs_size;
+#endif
 };
 
 static inline unsigned int thread_get_vl(struct thread_struct *thread,

arch/arm64/kernel/process.c

@@ -49,6 +49,7 @@
 #include <asm/cacheflush.h>
 #include <asm/exec.h>
 #include <asm/fpsimd.h>
+#include <asm/gcs.h>
 #include <asm/mmu_context.h>
 #include <asm/mte.h>
 #include <asm/processor.h>
@@ -280,6 +281,25 @@ static void flush_poe(void)
 	write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0);
 }
 
+#ifdef CONFIG_ARM64_GCS
+
+static void flush_gcs(void)
+{
+	if (!system_supports_gcs())
+		return;
+
+	gcs_free(current);
+	current->thread.gcs_el0_mode = 0;
+	write_sysreg_s(GCSCRE0_EL1_nTR, SYS_GCSCRE0_EL1);
+	write_sysreg_s(0, SYS_GCSPR_EL0);
+}
+
+#else
+
+static void flush_gcs(void) { }
+
+#endif
+
 void flush_thread(void)
 {
 	fpsimd_flush_thread();
@@ -287,6 +307,7 @@ void flush_thread(void)
 	flush_ptrace_hw_breakpoint(current);
 	flush_tagged_addr_state();
 	flush_poe();
+	flush_gcs();
 }
 
 void arch_release_task_struct(struct task_struct *tsk)
@@ -484,6 +505,46 @@ static void entry_task_switch(struct task_struct *next)
 	__this_cpu_write(__entry_task, next);
 }
 
+#ifdef CONFIG_ARM64_GCS
+
+void gcs_preserve_current_state(void)
+{
+	current->thread.gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0);
+}
+
+static void gcs_thread_switch(struct task_struct *next)
+{
+	if (!system_supports_gcs())
+		return;
+
+	/* GCSPR_EL0 is always readable */
+	gcs_preserve_current_state();
+	write_sysreg_s(next->thread.gcspr_el0, SYS_GCSPR_EL0);
+
+	if (current->thread.gcs_el0_mode != next->thread.gcs_el0_mode)
+		gcs_set_el0_mode(next);
+
+	/*
+	 * Ensure that GCS memory effects of the 'prev' thread are
+	 * ordered before other memory accesses with release semantics
+	 * (or preceded by a DMB) on the current PE. In addition, any
+	 * memory accesses with acquire semantics (or succeeded by a
+	 * DMB) are ordered before GCS memory effects of the 'next'
+	 * thread. This will ensure that the GCS memory effects are
+	 * visible to other PEs in case of migration.
+	 */
+	if (task_gcs_el0_enabled(current) || task_gcs_el0_enabled(next))
+		gcsb_dsync();
+}
+
+#else
+
+static void gcs_thread_switch(struct task_struct *next)
+{
+}
+
+#endif
+
 /*
  * Handle sysreg updates for ARM erratum 1418040 which affects the 32bit view of
  * CNTVCT, various other errata which require trapping all CNTVCT{,_EL0}
@@ -580,6 +641,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	cntkctl_thread_switch(prev, next);
 	ptrauth_thread_switch_user(next);
 	permission_overlay_switch(next);
+	gcs_thread_switch(next);
 
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case

arch/arm64/mm/Makefile

@@ -11,6 +11,7 @@ obj-$(CONFIG_TRANS_TABLE)	+= trans_pgd.o
 obj-$(CONFIG_TRANS_TABLE)	+= trans_pgd-asm.o
 obj-$(CONFIG_DEBUG_VIRTUAL)	+= physaddr.o
 obj-$(CONFIG_ARM64_MTE)		+= mteswap.o
+obj-$(CONFIG_ARM64_GCS)		+= gcs.o
 KASAN_SANITIZE_physaddr.o	+= n
 
 obj-$(CONFIG_KASAN)		+= kasan_init.o

arch/arm64/mm/gcs.c

@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/syscalls.h>
+#include <linux/types.h>
+
+#include <asm/cpufeature.h>
+#include <asm/page.h>
+
+/*
+ * Apply the GCS mode configured for the specified task to the
+ * hardware.
+ */
+void gcs_set_el0_mode(struct task_struct *task)
+{
+	u64 gcscre0_el1 = GCSCRE0_EL1_nTR;
+
+	if (task->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE)
+		gcscre0_el1 |= GCSCRE0_EL1_RVCHKEN | GCSCRE0_EL1_PCRSEL;
+
+	if (task->thread.gcs_el0_mode & PR_SHADOW_STACK_WRITE)
+		gcscre0_el1 |= GCSCRE0_EL1_STREn;
+
+	if (task->thread.gcs_el0_mode & PR_SHADOW_STACK_PUSH)
+		gcscre0_el1 |= GCSCRE0_EL1_PUSHMEn;
+
+	write_sysreg_s(gcscre0_el1, SYS_GCSCRE0_EL1);
+}
+
+void gcs_free(struct task_struct *task)
+{
+	if (!system_supports_gcs())
+		return;
+
+	if (task->thread.gcs_base)
+		vm_munmap(task->thread.gcs_base, task->thread.gcs_size);
+
+	task->thread.gcspr_el0 = 0;
+	task->thread.gcs_base = 0;
+	task->thread.gcs_size = 0;
+}