arm64/gcs: Ensure that new threads have a GCS

When a new thread is created by a thread with GCS enabled the GCS needs
to be specified along with the regular stack.

Unfortunately plain clone() is not extensible and existing clone3()
users will not specify a stack so all existing code would be broken if
we mandated specifying the stack explicitly.  For compatibility with
these cases and also x86 (which did not initially implement clone3()
support for shadow stacks) if no GCS is specified we will allocate one
so when a thread is created which has GCS enabled allocate one for it.
We follow the extensively discussed x86 implementation and allocate
min(RLIMIT_STACK/2, 2G).  Since the GCS only stores the call stack and not
any variables this should be more than sufficient for most applications.

GCSs allocated via this mechanism will be freed when the thread exits.

Reviewed-by: Thiago Jung Bauermann <[email protected]>
Acked-by: Yury Khrustalev <[email protected]>
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>

Author: broonie

arch/arm64/include/asm/gcs.h

@@ -8,6 +8,8 @@
 #include <asm/types.h>
 #include <asm/uaccess.h>
 
+struct kernel_clone_args;
+
 static inline void gcsb_dsync(void)
 {
 	asm volatile(".inst 0xd503227f" : : : "memory");
@@ -58,6 +60,8 @@ static inline bool task_gcs_el0_enabled(struct task_struct *task)
 void gcs_set_el0_mode(struct task_struct *task);
 void gcs_free(struct task_struct *task);
 void gcs_preserve_current_state(void);
+unsigned long gcs_alloc_thread_stack(struct task_struct *tsk,
+				     const struct kernel_clone_args *args);
 
 #else
 
@@ -69,6 +73,11 @@ static inline bool task_gcs_el0_enabled(struct task_struct *task)
 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) { }
+static inline unsigned long gcs_alloc_thread_stack(struct task_struct *tsk,
+						   const struct kernel_clone_args *args)
+{
+	return -ENOTSUPP;
+}
 
 #endif
 

arch/arm64/include/asm/mmu_context.h

@@ -20,6 +20,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
 #include <asm/daifflags.h>
+#include <asm/gcs.h>
 #include <asm/proc-fns.h>
 #include <asm/cputype.h>
 #include <asm/sysreg.h>
@@ -311,6 +312,14 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 	return por_el0_allows_pkey(vma_pkey(vma), write, execute);
 }
 
+#define deactivate_mm deactivate_mm
+static inline void deactivate_mm(struct task_struct *tsk,
+			struct mm_struct *mm)
+{
+	gcs_free(tsk);
+}
+
+
 #include <asm-generic/mmu_context.h>
 
 #endif /* !__ASSEMBLY__ */

arch/arm64/kernel/process.c

@@ -294,9 +294,35 @@ static void flush_gcs(void)
 	write_sysreg_s(0, SYS_GCSPR_EL0);
 }
 
+static int copy_thread_gcs(struct task_struct *p,
+			   const struct kernel_clone_args *args)
+{
+	unsigned long gcs;
+
+	if (!system_supports_gcs())
+		return 0;
+
+	p->thread.gcs_base = 0;
+	p->thread.gcs_size = 0;
+
+	gcs = gcs_alloc_thread_stack(p, args);
+	if (IS_ERR_VALUE(gcs))
+		return PTR_ERR((void *)gcs);
+
+	p->thread.gcs_el0_mode = current->thread.gcs_el0_mode;
+	p->thread.gcs_el0_locked = current->thread.gcs_el0_locked;
+
+	return 0;
+}
+
 #else
 
 static void flush_gcs(void) { }
+static int copy_thread_gcs(struct task_struct *p,
+			   const struct kernel_clone_args *args)
+{
+	return 0;
+}
 
 #endif
 
@@ -313,6 +339,7 @@ void flush_thread(void)
 void arch_release_task_struct(struct task_struct *tsk)
 {
 	fpsimd_release_task(tsk);
+	gcs_free(tsk);
 }
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
@@ -376,6 +403,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	unsigned long stack_start = args->stack;
 	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
+	int ret;
 
 	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
 
@@ -420,6 +448,10 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 			p->thread.uw.tp_value = tls;
 			p->thread.tpidr2_el0 = 0;
 		}
+
+		ret = copy_thread_gcs(p, args);
+		if (ret != 0)
+			return ret;
 	} else {
 		/*
 		 * A kthread has no context to ERET to, so ensure any buggy

arch/arm64/mm/gcs.c

@@ -5,9 +5,69 @@
 #include <linux/syscalls.h>
 #include <linux/types.h>
 
+#include <asm/cmpxchg.h>
 #include <asm/cpufeature.h>
+#include <asm/gcs.h>
 #include <asm/page.h>
 
+static unsigned long alloc_gcs(unsigned long addr, unsigned long size)
+{
+	int flags = MAP_ANONYMOUS | MAP_PRIVATE;
+	struct mm_struct *mm = current->mm;
+	unsigned long mapped_addr, unused;
+
+	if (addr)
+		flags |= MAP_FIXED_NOREPLACE;
+
+	mmap_write_lock(mm);
+	mapped_addr = do_mmap(NULL, addr, size, PROT_READ, flags,
+			      VM_SHADOW_STACK | VM_WRITE, 0, &unused, NULL);
+	mmap_write_unlock(mm);
+
+	return mapped_addr;
+}
+
+static unsigned long gcs_size(unsigned long size)
+{
+	if (size)
+		return PAGE_ALIGN(size);
+
+	/* Allocate RLIMIT_STACK/2 with limits of PAGE_SIZE..2G */
+	size = PAGE_ALIGN(min_t(unsigned long long,
+				rlimit(RLIMIT_STACK) / 2, SZ_2G));
+	return max(PAGE_SIZE, size);
+}
+
+unsigned long gcs_alloc_thread_stack(struct task_struct *tsk,
+				     const struct kernel_clone_args *args)
+{
+	unsigned long addr, size;
+
+	if (!system_supports_gcs())
+		return 0;
+
+	if (!task_gcs_el0_enabled(tsk))
+		return 0;
+
+	if ((args->flags & (CLONE_VFORK | CLONE_VM)) != CLONE_VM) {
+		tsk->thread.gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0);
+		return 0;
+	}
+
+	size = args->stack_size / 2;
+
+	size = gcs_size(size);
+	addr = alloc_gcs(0, size);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
+	tsk->thread.gcs_base = addr;
+	tsk->thread.gcs_size = size;
+	tsk->thread.gcspr_el0 = addr + size - sizeof(u64);
+
+	return addr;
+}
+
 /*
  * Apply the GCS mode configured for the specified task to the
  * hardware.
@@ -33,6 +93,15 @@ void gcs_free(struct task_struct *task)
 	if (!system_supports_gcs())
 		return;
 
+	/*
+	 * When fork() with CLONE_VM fails, the child (tsk) already
+	 * has a GCS allocated, and exit_thread() calls this function
+	 * to free it.  In this case the parent (current) and the
+	 * child share the same mm struct.
+	 */
+	if (!task->mm || task->mm != current->mm)
+		return;
+
 	if (task->thread.gcs_base)
 		vm_munmap(task->thread.gcs_base, task->thread.gcs_size);