Merge branch 'for-next/uprobes' into for-next/core

* for-next/uprobes:
  arm64: probes: Fix incorrect bl/blr address and register usage
  uprobes: uprobe_warn should use passed task
  arm64: Kconfig: Remove GCS restrictions on UPROBES
  arm64: uprobes: Add GCS support to uretprobes
  arm64: probes: Add GCS support to bl/blr/ret
  arm64: uaccess: Add additional userspace GCS accessors
  arm64: uaccess: Move existing GCS accessors definitions to gcs.h
  arm64: probes: Break ret out from bl/blr

arch/arm64/Kconfig

@@ -2213,7 +2213,6 @@ config ARM64_GCS
 	default y
 	select ARCH_HAS_USER_SHADOW_STACK
 	select ARCH_USES_HIGH_VMA_FLAGS
-	depends on !UPROBES
 	help
 	  Guarded Control Stack (GCS) provides support for a separate
 	  stack with restricted access which contains only return

arch/arm64/include/asm/gcs.h

@@ -21,7 +21,7 @@ static inline void gcsstr(u64 *addr, u64 val)
 	register u64 *_addr __asm__ ("x0") = addr;
 	register long _val __asm__ ("x1") = val;
 
-	/* GCSSTTR x1, x0 */
+	/* GCSSTTR x1, [x0] */
 	asm volatile(
 		".inst 0xd91f1c01\n"
 		:
@@ -81,6 +81,82 @@ static inline int gcs_check_locked(struct task_struct *task,
 	return 0;
 }
 
+static inline int gcssttr(unsigned long __user *addr, unsigned long val)
+{
+	register unsigned long __user *_addr __asm__ ("x0") = addr;
+	register unsigned long _val __asm__ ("x1") = val;
+	int err = 0;
+
+	/* GCSSTTR x1, [x0] */
+	asm volatile(
+		"1: .inst 0xd91f1c01\n"
+		"2: \n"
+		_ASM_EXTABLE_UACCESS_ERR(1b, 2b, %w0)
+		: "+r" (err)
+		: "rZ" (_val), "r" (_addr)
+		: "memory");
+
+	return err;
+}
+
+static inline void put_user_gcs(unsigned long val, unsigned long __user *addr,
+				int *err)
+{
+	int ret;
+
+	if (!access_ok((char __user *)addr, sizeof(u64))) {
+		*err = -EFAULT;
+		return;
+	}
+
+	uaccess_ttbr0_enable();
+	ret = gcssttr(addr, val);
+	if (ret != 0)
+		*err = ret;
+	uaccess_ttbr0_disable();
+}
+
+static inline void push_user_gcs(unsigned long val, int *err)
+{
+	u64 gcspr = read_sysreg_s(SYS_GCSPR_EL0);
+
+	gcspr -= sizeof(u64);
+	put_user_gcs(val, (unsigned long __user *)gcspr, err);
+	if (!*err)
+		write_sysreg_s(gcspr, SYS_GCSPR_EL0);
+}
+
+/*
+ * Unlike put/push_user_gcs() above, get/pop_user_gsc() doesn't
+ * validate the GCS permission is set on the page being read.  This
+ * differs from how the hardware works when it consumes data stored at
+ * GCSPR. Callers should ensure this is acceptable.
+ */
+static inline u64 get_user_gcs(unsigned long __user *addr, int *err)
+{
+	unsigned long ret;
+	u64 load = 0;
+
+	/* Ensure previous GCS operation are visible before we read the page */
+	gcsb_dsync();
+	ret = copy_from_user(&load, addr, sizeof(load));
+	if (ret != 0)
+		*err = ret;
+	return load;
+}
+
+static inline u64 pop_user_gcs(int *err)
+{
+	u64 gcspr = read_sysreg_s(SYS_GCSPR_EL0);
+	u64 read_val;
+
+	read_val = get_user_gcs((__force unsigned long __user *)gcspr, err);
+	if (!*err)
+		write_sysreg_s(gcspr + sizeof(u64), SYS_GCSPR_EL0);
+
+	return read_val;
+}
+
 #else
 
 static inline bool task_gcs_el0_enabled(struct task_struct *task)
@@ -91,6 +167,10 @@ 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 void put_user_gcs(unsigned long val, unsigned long __user *addr,
+				int *err) { }
+static inline void push_user_gcs(unsigned long val, int *err) { }
+
 static inline unsigned long gcs_alloc_thread_stack(struct task_struct *tsk,
 						   const struct kernel_clone_args *args)
 {
@@ -101,6 +181,15 @@ static inline int gcs_check_locked(struct task_struct *task,
 {
 	return 0;
 }
+static inline u64 get_user_gcs(unsigned long __user *addr, int *err)
+{
+	*err = -EFAULT;
+	return 0;
+}
+static inline u64 pop_user_gcs(int *err)
+{
+	return 0;
+}
 
 #endif
 

arch/arm64/include/asm/uaccess.h

@@ -502,44 +502,4 @@ static inline size_t probe_subpage_writeable(const char __user *uaddr,
 
 #endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */
 
-#ifdef CONFIG_ARM64_GCS
-
-static inline int gcssttr(unsigned long __user *addr, unsigned long val)
-{
-	register unsigned long __user *_addr __asm__ ("x0") = addr;
-	register unsigned long _val __asm__ ("x1") = val;
-	int err = 0;
-
-	/* GCSSTTR x1, x0 */
-	asm volatile(
-		"1: .inst 0xd91f1c01\n"
-		"2: \n"
-		_ASM_EXTABLE_UACCESS_ERR(1b, 2b, %w0)
-		: "+r" (err)
-		: "rZ" (_val), "r" (_addr)
-		: "memory");
-
-	return err;
-}
-
-static inline void put_user_gcs(unsigned long val, unsigned long __user *addr,
-				int *err)
-{
-	int ret;
-
-	if (!access_ok((char __user *)addr, sizeof(u64))) {
-		*err = -EFAULT;
-		return;
-	}
-
-	uaccess_ttbr0_enable();
-	ret = gcssttr(addr, val);
-	if (ret != 0)
-		*err = ret;
-	uaccess_ttbr0_disable();
-}
-
-
-#endif /* CONFIG_ARM64_GCS */
-
 #endif /* __ASM_UACCESS_H */

arch/arm64/kernel/probes/decode-insn.c

@@ -108,9 +108,10 @@ arm_probe_decode_insn(u32 insn, struct arch_probe_insn *api)
 	    aarch64_insn_is_bl(insn)) {
 		api->handler = simulate_b_bl;
 	} else if (aarch64_insn_is_br(insn) ||
-	    aarch64_insn_is_blr(insn) ||
-	    aarch64_insn_is_ret(insn)) {
-		api->handler = simulate_br_blr_ret;
+		aarch64_insn_is_blr(insn)) {
+		api->handler = simulate_br_blr;
+	} else if (aarch64_insn_is_ret(insn)) {
+		api->handler = simulate_ret;
 	} else {
 		/*
 		 * Instruction cannot be stepped out-of-line and we don't

arch/arm64/kernel/probes/simulate-insn.c

@@ -13,6 +13,7 @@
 #include <asm/traps.h>
 
 #include "simulate-insn.h"
+#include "asm/gcs.h"
 
 #define bbl_displacement(insn)		\
 	sign_extend32(((insn) & 0x3ffffff) << 2, 27)
@@ -49,6 +50,21 @@ static inline u32 get_w_reg(struct pt_regs *regs, int reg)
 	return lower_32_bits(pt_regs_read_reg(regs, reg));
 }
 
+static inline int update_lr(struct pt_regs *regs, long addr)
+{
+	int err = 0;
+
+	if (user_mode(regs) && task_gcs_el0_enabled(current)) {
+		push_user_gcs(addr, &err);
+		if (err) {
+			force_sig(SIGSEGV);
+			return err;
+		}
+	}
+	procedure_link_pointer_set(regs, addr);
+	return err;
+}
+
 static bool __kprobes check_cbz(u32 opcode, struct pt_regs *regs)
 {
 	int xn = opcode & 0x1f;
@@ -107,9 +123,9 @@ simulate_b_bl(u32 opcode, long addr, struct pt_regs *regs)
 {
 	int disp = bbl_displacement(opcode);
 
-	/* Link register is x30 */
 	if (opcode & (1 << 31))
-		set_x_reg(regs, 30, addr + 4);
+		if (update_lr(regs, addr + 4))
+			return;
 
 	instruction_pointer_set(regs, addr + disp);
 }
@@ -126,16 +142,34 @@ simulate_b_cond(u32 opcode, long addr, struct pt_regs *regs)
 }
 
 void __kprobes
-simulate_br_blr_ret(u32 opcode, long addr, struct pt_regs *regs)
+simulate_br_blr(u32 opcode, long addr, struct pt_regs *regs)
 {
 	int xn = (opcode >> 5) & 0x1f;
+	u64 b_target = get_x_reg(regs, xn);
 
-	/* update pc first in case we're doing a "blr lr" */
-	instruction_pointer_set(regs, get_x_reg(regs, xn));
-
-	/* Link register is x30 */
 	if (((opcode >> 21) & 0x3) == 1)
-		set_x_reg(regs, 30, addr + 4);
+		if (update_lr(regs, addr + 4))
+			return;
+
+	instruction_pointer_set(regs, b_target);
+}
+
+void __kprobes
+simulate_ret(u32 opcode, long addr, struct pt_regs *regs)
+{
+	u64 ret_addr;
+	int err = 0;
+	int xn = (opcode >> 5) & 0x1f;
+	u64 r_target = get_x_reg(regs, xn);
+
+	if (user_mode(regs) && task_gcs_el0_enabled(current)) {
+		ret_addr = pop_user_gcs(&err);
+		if (err || ret_addr != r_target) {
+			force_sig(SIGSEGV);
+			return;
+		}
+	}
+	instruction_pointer_set(regs, r_target);
 }
 
 void __kprobes

arch/arm64/kernel/probes/simulate-insn.h

@@ -11,7 +11,8 @@
 void simulate_adr_adrp(u32 opcode, long addr, struct pt_regs *regs);
 void simulate_b_bl(u32 opcode, long addr, struct pt_regs *regs);
 void simulate_b_cond(u32 opcode, long addr, struct pt_regs *regs);
-void simulate_br_blr_ret(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_br_blr(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_ret(u32 opcode, long addr, struct pt_regs *regs);
 void simulate_cbz_cbnz(u32 opcode, long addr, struct pt_regs *regs);
 void simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs);
 void simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs);

arch/arm64/kernel/probes/uprobes.c

@@ -6,6 +6,7 @@
 #include <linux/ptrace.h>
 #include <linux/uprobes.h>
 #include <asm/cacheflush.h>
+#include <asm/gcs.h>
 
 #include "decode-insn.h"
 
@@ -159,11 +160,43 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr,
 				  struct pt_regs *regs)
 {
 	unsigned long orig_ret_vaddr;
+	unsigned long gcs_ret_vaddr;
+	int err = 0;
+	u64 gcspr;
 
 	orig_ret_vaddr = procedure_link_pointer(regs);
+
+	if (task_gcs_el0_enabled(current)) {
+		gcspr = read_sysreg_s(SYS_GCSPR_EL0);
+		gcs_ret_vaddr = get_user_gcs((__force unsigned long __user *)gcspr, &err);
+		if (err) {
+			force_sig(SIGSEGV);
+			goto out;
+		}
+
+		/*
+		 * If the LR and GCS return addr don't match, then some kind of PAC
+		 * signing or control flow occurred since entering the probed function.
+		 * Likely because the user is attempting to retprobe on an instruction
+		 * that isn't a function boundary or inside a leaf function. Explicitly
+		 * abort this retprobe because it will generate a GCS exception.
+		 */
+		if (gcs_ret_vaddr != orig_ret_vaddr) {
+			orig_ret_vaddr = -1;
+			goto out;
+		}
+
+		put_user_gcs(trampoline_vaddr, (__force unsigned long __user *)gcspr, &err);
+		if (err) {
+			force_sig(SIGSEGV);
+			goto out;
+		}
+	}
+
 	/* Replace the return addr with trampoline addr */
 	procedure_link_pointer_set(regs, trampoline_vaddr);
 
+out:
 	return orig_ret_vaddr;
 }
 

kernel/events/uprobes.c

@@ -121,7 +121,7 @@ struct xol_area {
 
 static void uprobe_warn(struct task_struct *t, const char *msg)
 {
-	pr_warn("uprobe: %s:%d failed to %s\n", current->comm, current->pid, msg);
+	pr_warn("uprobe: %s:%d failed to %s\n", t->comm, t->pid, msg);
 }
 
 /*