[PATCH v6 21/38] arm64/gcs: Allocate a new GCS for threads with GCS enabled

[Mark Brown <broonie@xxxxxxxxxx>]

We do not currently have a mechanism to specify a new GCS for a new
thread so when a thread is created which has GCS enabled allocate one
for it.  Since there is no current API for specifying the size of the
GCS we follow the extensively discussed x86 implementation and allocate
min(RLIMIT_STACK, 4G).  Since the GCS only stores the call stack and not
any variables this should be more than sufficient for most applications.

When allocating the stack we initialise GCSPR_EL0 to point to one entry
below the end of the region allocated, this keeps the top entry of the
stack 0 so software walking the GCS can easily detect the end of the
region.

Signed-off-by: Mark Brown <broonie@xxxxxxxxxx>
---
 arch/arm64/include/asm/gcs.h |  7 +++++++
 arch/arm64/kernel/process.c  | 36 +++++++++++++++++++++++++++++++++
 arch/arm64/mm/gcs.c          | 47 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 90 insertions(+)

diff --git a/arch/arm64/include/asm/gcs.h b/arch/arm64/include/asm/gcs.h
index 04594ef59dad..4371a2f99b4a 100644
--- a/arch/arm64/include/asm/gcs.h
+++ b/arch/arm64/include/asm/gcs.h
@@ -58,6 +58,8 @@ 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,
+			    unsigned long clone_flags, size_t size);
 
 #else
 
@@ -69,6 +71,11 @@ 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,
+				     unsigned long clone_flags, size_t size)
+{
+	return -ENOTSUPP;
+}
 
 #endif
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 84bac012f744..bc4f73fb0713 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -285,9 +285,40 @@ static void flush_gcs(void)
 	write_sysreg_s(0, SYS_GCSPR_EL0);
 }
 
+static int copy_thread_gcs(struct task_struct *p, unsigned long clone_flags,
+			   size_t stack_size)
+{
+	unsigned long gcs;
+
+	if (!system_supports_gcs())
+		return 0;
+
+	if (!task_gcs_el0_enabled(p))
+		return 0;
+
+	p->thread.gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0);
+
+	if ((clone_flags & (CLONE_VFORK | CLONE_VM)) != CLONE_VM)
+		return 0;
+
+	/* Ensure the current state of the GCS is seen by CoW */
+	gcsb_dsync();
+
+	gcs = gcs_alloc_thread_stack(p, clone_flags, stack_size);
+	if (IS_ERR_VALUE(gcs))
+		return PTR_ERR((void *)gcs);
+
+	return 0;
+}
+
 #else
 
 static void flush_gcs(void) { }
+static int copy_thread_gcs(struct task_struct *p, unsigned long clone_flags,
+			   size_t stack_size)
+{
+	return 0;
+}
 
 #endif
 
@@ -369,6 +400,7 @@ 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));
 
@@ -410,6 +442,10 @@ 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, clone_flags, args->stack_size);
+		if (ret != 0)
+			return ret;
 	} else {
 		/*
 		 * A kthread has no context to ERET to, so ensure any buggy
diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c
index b0a67efc522b..cb0a64bf90af 100644
--- a/arch/arm64/mm/gcs.c
+++ b/arch/arm64/mm/gcs.c
@@ -8,6 +8,53 @@
 #include <asm/cpufeature.h>
 #include <asm/page.h>
 
+static unsigned long alloc_gcs(unsigned long addr, unsigned long size,
+			       unsigned long token_offset, bool set_res_tok)
+{
+	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 | PROT_WRITE, flags,
+			      VM_SHADOW_STACK, 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,
+				     unsigned long clone_flags, size_t size)
+{
+	unsigned long addr;
+
+	size = gcs_size(size);
+
+	addr = alloc_gcs(0, size, 0, 0);
+	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.

-- 
2.30.2