[PATCH v7 19/29] arm64: mte: Allow user control of the generated random tags via prctl()

[Catalin Marinas <catalin.marinas@arm.com>]

The IRG, ADDG and SUBG instructions insert a random tag in the resulting
address. Certain tags can be excluded via the GCR_EL1.Exclude bitmap
when, for example, the user wants a certain colour for freed buffers.
Since the GCR_EL1 register is not accessible at EL0, extend the
prctl(PR_SET_TAGGED_ADDR_CTRL) interface to include a 16-bit field in
the first argument for controlling which tags can be generated by the
above instruction (an include rather than exclude mask). Note that by
default all non-zero tags are excluded. This setting is per-thread.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---

Notes:
    v5:
    - Rename gcr_incl to gcr_user_incl (there will be a subsequent
      gcr_kernel when support for in-kernel MTE is added).
    
    v2:
    - Switch from an exclude mask to an include one for the prctl()
      interface.
    - Reset the allowed tags mask during flush_thread().

 arch/arm64/include/asm/processor.h |  1 +
 arch/arm64/include/asm/sysreg.h    |  7 ++++++
 arch/arm64/kernel/mte.c            | 35 +++++++++++++++++++++++++++---
 arch/arm64/kernel/process.c        |  2 +-
 include/uapi/linux/prctl.h         |  3 +++
 5 files changed, 44 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 80e7f0573309..e1b1c2a6086e 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -153,6 +153,7 @@ struct thread_struct {
 #endif
 #ifdef CONFIG_ARM64_MTE
 	u64			sctlr_tcf0;
+	u64			gcr_user_incl;
 #endif
 };
 
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 2e12d8049d1c..d6357c4ea015 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1033,6 +1033,13 @@
 		write_sysreg(__scs_new, sysreg);			\
 } while (0)
 
+#define sysreg_clear_set_s(sysreg, clear, set) do {			\
+	u64 __scs_val = read_sysreg_s(sysreg);				\
+	u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set);		\
+	if (__scs_new != __scs_val)					\
+		write_sysreg_s(__scs_new, sysreg);			\
+} while (0)
+
 #endif
 
 #endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
index 375483a1f573..07798b8d5039 100644
--- a/arch/arm64/kernel/mte.c
+++ b/arch/arm64/kernel/mte.c
@@ -71,6 +71,25 @@ static void set_sctlr_el1_tcf0(u64 tcf0)
 	preempt_enable();
 }
 
+static void update_gcr_el1_excl(u64 incl)
+{
+	u64 excl = ~incl & SYS_GCR_EL1_EXCL_MASK;
+
+	/*
+	 * Note that 'incl' is an include mask (controlled by the user via
+	 * prctl()) while GCR_EL1 accepts an exclude mask.
+	 * No need for ISB since this only affects EL0 currently, implicit
+	 * with ERET.
+	 */
+	sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, excl);
+}
+
+static void set_gcr_el1_excl(u64 incl)
+{
+	current->thread.gcr_user_incl = incl;
+	update_gcr_el1_excl(incl);
+}
+
 void flush_mte_state(void)
 {
 	if (!system_supports_mte())
@@ -82,6 +101,8 @@ void flush_mte_state(void)
 	clear_thread_flag(TIF_MTE_ASYNC_FAULT);
 	/* disable tag checking */
 	set_sctlr_el1_tcf0(SCTLR_EL1_TCF0_NONE);
+	/* reset tag generation mask */
+	set_gcr_el1_excl(0);
 }
 
 void mte_thread_switch(struct task_struct *next)
@@ -92,6 +113,7 @@ void mte_thread_switch(struct task_struct *next)
 	/* avoid expensive SCTLR_EL1 accesses if no change */
 	if (current->thread.sctlr_tcf0 != next->thread.sctlr_tcf0)
 		update_sctlr_el1_tcf0(next->thread.sctlr_tcf0);
+	update_gcr_el1_excl(next->thread.gcr_user_incl);
 }
 
 long set_mte_ctrl(unsigned long arg)
@@ -116,23 +138,30 @@ long set_mte_ctrl(unsigned long arg)
 	}
 
 	set_sctlr_el1_tcf0(tcf0);
+	set_gcr_el1_excl((arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT);
 
 	return 0;
 }
 
 long get_mte_ctrl(void)
 {
+	unsigned long ret;
+
 	if (!system_supports_mte())
 		return 0;
 
+	ret = current->thread.gcr_user_incl << PR_MTE_TAG_SHIFT;
+
 	switch (current->thread.sctlr_tcf0) {
 	case SCTLR_EL1_TCF0_NONE:
 		return PR_MTE_TCF_NONE;
 	case SCTLR_EL1_TCF0_SYNC:
-		return PR_MTE_TCF_SYNC;
+		ret |= PR_MTE_TCF_SYNC;
+		break;
 	case SCTLR_EL1_TCF0_ASYNC:
-		return PR_MTE_TCF_ASYNC;
+		ret |= PR_MTE_TCF_ASYNC;
+		break;
 	}
 
-	return 0;
+	return ret;
 }
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index d19ce8053a03..b5c1c975d38e 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -616,7 +616,7 @@ long set_tagged_addr_ctrl(unsigned long arg)
 		return -EINVAL;
 
 	if (system_supports_mte())
-		valid_mask |= PR_MTE_TCF_MASK;
+		valid_mask |= PR_MTE_TCF_MASK | PR_MTE_TAG_MASK;
 
 	if (arg & ~valid_mask)
 		return -EINVAL;
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 2390ab324afa..7f0827705c9a 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -239,6 +239,9 @@ struct prctl_mm_map {
 # define PR_MTE_TCF_SYNC		(1UL << PR_MTE_TCF_SHIFT)
 # define PR_MTE_TCF_ASYNC		(2UL << PR_MTE_TCF_SHIFT)
 # define PR_MTE_TCF_MASK		(3UL << PR_MTE_TCF_SHIFT)
+/* MTE tag inclusion mask */
+# define PR_MTE_TAG_SHIFT		3
+# define PR_MTE_TAG_MASK		(0xffffUL << PR_MTE_TAG_SHIFT)
 
 /* Control reclaim behavior when allocating memory */
 #define PR_SET_IO_FLUSHER		57