arm64: Work around Falkor erratum 1003

The Qualcomm Datacenter Technologies Falkor v1 CPU may allocate TLB entries
using an incorrect ASID when TTBRx_EL1 is being updated. When the erratum
is triggered, page table entries using the new translation table base
address (BADDR) will be allocated into the TLB using the old ASID. All
circumstances leading to the incorrect ASID being cached in the TLB arise
when software writes TTBRx_EL1[ASID] and TTBRx_EL1[BADDR], a memory
operation is in the process of performing a translation using the specific
TTBRx_EL1 being written, and the memory operation uses a translation table
descriptor designated as non-global. EL2 and EL3 code changing the EL1&0
ASID is not subject to this erratum because hardware is prohibited from
performing translations from an out-of-context translation regime.

Consider the following pseudo code.

  write new BADDR and ASID values to TTBRx_EL1

Replacing the above sequence with the one below will ensure that no TLB
entries with an incorrect ASID are used by software.

  write reserved value to TTBRx_EL1[ASID]
  ISB
  write new value to TTBRx_EL1[BADDR]
  ISB
  write new value to TTBRx_EL1[ASID]
  ISB

When the above sequence is used, page table entries using the new BADDR
value may still be incorrectly allocated into the TLB using the reserved
ASID. Yet this will not reduce functionality, since TLB entries incorrectly
tagged with the reserved ASID will never be hit by a later instruction.

Based on work by Shanker Donthineni <shankerd@codeaurora.org>

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Christopher Covington <cov@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>

Documentation/arm64/silicon-errata.txt

@@ -66,4 +66,5 @@ stable kernels.
 |                |                 |                 |                             |
 | Hisilicon      | Hip0{5,6,7}     | #161010101      | HISILICON_ERRATUM_161010101 |
 |                |                 |                 |                             |
+| Qualcomm Tech. | Falkor v1       | E1003           | QCOM_FALKOR_ERRATUM_1003    |
 | Qualcomm Tech. | Falkor v1       | E1009           | QCOM_FALKOR_ERRATUM_1009    |

arch/arm64/Kconfig

@@ -480,6 +480,24 @@ config CAVIUM_ERRATUM_27456
 
 	  If unsure, say Y.
 
+config QCOM_FALKOR_ERRATUM_1003
+	bool "Falkor E1003: Incorrect translation due to ASID change"
+	default y
+	select ARM64_PAN if ARM64_SW_TTBR0_PAN
+	help
+	  On Falkor v1, an incorrect ASID may be cached in the TLB when ASID
+	  and BADDR are changed together in TTBRx_EL1. The workaround for this
+	  issue is to use a reserved ASID in cpu_do_switch_mm() before
+	  switching to the new ASID. Saying Y here selects ARM64_PAN if
+	  ARM64_SW_TTBR0_PAN is selected. This is done because implementing and
+	  maintaining the E1003 workaround in the software PAN emulation code
+	  would be an unnecessary complication. The affected Falkor v1 CPU
+	  implements ARMv8.1 hardware PAN support and using hardware PAN
+	  support versus software PAN emulation is mutually exclusive at
+	  runtime.
+
+	  If unsure, say Y.
+
 config QCOM_FALKOR_ERRATUM_1009
 	bool "Falkor E1009: Prematurely complete a DSB after a TLBI"
 	default y

arch/arm64/include/asm/assembler.h

@@ -25,6 +25,7 @@
 
 #include <asm/asm-offsets.h>
 #include <asm/cpufeature.h>
+#include <asm/mmu_context.h>
 #include <asm/page.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/ptrace.h>
@@ -422,6 +423,28 @@ alternative_endif
 	mrs	\rd, sp_el0
 	.endm
 
+/*
+ * Errata workaround prior to TTBR0_EL1 update
+ *
+ * 	val:	TTBR value with new BADDR, preserved
+ * 	tmp0:	temporary register, clobbered
+ * 	tmp1:	other temporary register, clobbered
+ */
+	.macro	pre_ttbr0_update_workaround, val, tmp0, tmp1
+#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
+alternative_if ARM64_WORKAROUND_QCOM_FALKOR_E1003
+	mrs	\tmp0, ttbr0_el1
+	mov	\tmp1, #FALKOR_RESERVED_ASID
+	bfi	\tmp0, \tmp1, #48, #16		// reserved ASID + old BADDR
+	msr	ttbr0_el1, \tmp0
+	isb
+	bfi	\tmp0, \val, #0, #48		// reserved ASID + new BADDR
+	msr	ttbr0_el1, \tmp0
+	isb
+alternative_else_nop_endif
+#endif
+	.endm
+
 /*
  * Errata workaround post TTBR0_EL1 update.
  */

arch/arm64/include/asm/cpucaps.h

@@ -36,7 +36,8 @@
 #define ARM64_MISMATCHED_CACHE_LINE_SIZE	15
 #define ARM64_HAS_NO_FPSIMD			16
 #define ARM64_WORKAROUND_REPEAT_TLBI		17
+#define ARM64_WORKAROUND_QCOM_FALKOR_E1003	18
 
-#define ARM64_NCAPS				18
+#define ARM64_NCAPS				19
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/include/asm/mmu_context.h

@@ -19,6 +19,10 @@
 #ifndef __ASM_MMU_CONTEXT_H
 #define __ASM_MMU_CONTEXT_H
 
+#define FALKOR_RESERVED_ASID	1
+
+#ifndef __ASSEMBLY__
+
 #include <linux/compiler.h>
 #include <linux/sched.h>
 
@@ -220,4 +224,6 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 
 void verify_cpu_asid_bits(void);
 
-#endif
+#endif /* !__ASSEMBLY__ */
+
+#endif /* !__ASM_MMU_CONTEXT_H */

arch/arm64/kernel/cpu_errata.c

@@ -133,6 +133,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.def_scope = SCOPE_LOCAL_CPU,
 		.enable = cpu_enable_trap_ctr_access,
 	},
+#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
+	{
+		.desc = "Qualcomm Technologies Falkor erratum 1003",
+		.capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003,
+		MIDR_RANGE(MIDR_QCOM_FALKOR_V1,
+			   MIDR_CPU_VAR_REV(0, 0),
+			   MIDR_CPU_VAR_REV(0, 0)),
+	},
+#endif
 #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009
 	{
 		.desc = "Qualcomm Technologies Falkor erratum 1009",

arch/arm64/mm/context.c

@@ -79,6 +79,13 @@ void verify_cpu_asid_bits(void)
 	}
 }
 
+static void set_reserved_asid_bits(void)
+{
+	if (IS_ENABLED(CONFIG_QCOM_FALKOR_ERRATUM_1003) &&
+	    cpus_have_const_cap(ARM64_WORKAROUND_QCOM_FALKOR_E1003))
+		__set_bit(FALKOR_RESERVED_ASID, asid_map);
+}
+
 static void flush_context(unsigned int cpu)
 {
 	int i;
@@ -87,6 +94,8 @@ static void flush_context(unsigned int cpu)
 	/* Update the list of reserved ASIDs and the ASID bitmap. */
 	bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
 
+	set_reserved_asid_bits();
+
 	/*
 	 * Ensure the generation bump is observed before we xchg the
 	 * active_asids.
@@ -244,6 +253,8 @@ static int asids_init(void)
 		panic("Failed to allocate bitmap for %lu ASIDs\n",
 		      NUM_USER_ASIDS);
 
+	set_reserved_asid_bits();
+
 	pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS);
 	return 0;
 }

arch/arm64/mm/proc.S

@@ -138,6 +138,7 @@ ENDPROC(cpu_do_resume)
  *	- pgd_phys - physical address of new TTB
  */
 ENTRY(cpu_do_switch_mm)
+	pre_ttbr0_update_workaround x0, x1, x2
 	mmid	x1, x1				// get mm->context.id
 	bfi	x0, x1, #48, #16		// set the ASID
 	msr	ttbr0_el1, x0			// set TTBR0