From 43aaa649d7c52a04768ff8abbbd461c2b4f2376a Mon Sep 17 00:00:00 2001
From: Julien Grall <jgrall@amazon.com>
Date: Tue, 24 Jan 2023 19:25:19 +0000
Subject: xen/arm64: flushtlb: Reduce scope of barrier for local TLB flush

Per D5-4929 in ARM DDI 0487H.a:
"A DSB NSH is sufficient to ensure completion of TLB maintenance
 instructions that apply to a single PE. A DSB ISH is sufficient to
 ensure completion of TLB maintenance instructions that apply to PEs
 in the same Inner Shareable domain.
"

This means barrier after local TLB flushes could be reduced to
non-shareable.

Note that the scope of the barrier in the workaround has not been
changed because Linux v6.1-rc8 is also using 'ish' and I couldn't
find anything in the Neoverse N1 suggesting that a 'nsh' would
be sufficient.

Signed-off-by: Julien Grall <jgrall@amazon.com>
Reviewed-by: Michal Orzel <michal.orzel@amd.com>
Tested-by: Henry Wang <Henry.Wang@arm.com>
(cherry picked from commit 7c438851475482bf73fcf451551d1cb718d4904c)

xen/arm: Remove stray semicolon at VREG_REG_HELPERS/TLB_HELPER* callers

This is inconsistent with the rest of the code where macros are used
to define functions, as it results in an empty declaration (i.e.
semicolon with nothing before it) after function definition. This is also
not allowed by C99.

Take the opportunity to undefine TLB_HELPER* macros after last use.

Signed-off-by: Michal Orzel <michal.orzel@amd.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
(cherry picked from commit 6044b485ba5b0e4073a773402cedc2f2fae540ad)

diff --git a/xen/arch/arm/include/asm/arm64/flushtlb.h b/xen/arch/arm/include/asm/arm64/flushtlb.h
index 7c5431518741..fcc0788c3049 100644
--- a/xen/arch/arm/include/asm/arm64/flushtlb.h
+++ b/xen/arch/arm/include/asm/arm64/flushtlb.h
@@ -12,8 +12,9 @@
  * ARM64_WORKAROUND_REPEAT_TLBI:
  * Modification of the translation table for a virtual address might lead to
  * read-after-read ordering violation.
- * The workaround repeats TLBI+DSB operation for all the TLB flush operations.
- * While this is stricly not necessary, we don't want to take any risk.
+ * The workaround repeats TLBI+DSB ISH operation for all the TLB flush
+ * operations. While this is strictly not necessary, we don't want to
+ * take any risk.
  *
  * For Xen page-tables the ISB will discard any instructions fetched
  * from the old mappings.
@@ -21,12 +22,17 @@
  * For the Stage-2 page-tables the ISB ensures the completion of the DSB
  * (and therefore the TLB invalidation) before continuing. So we know
  * the TLBs cannot contain an entry for a mapping we may have removed.
+ *
+ * Note that for local TLB flush, using non-shareable (nsh) is sufficient
+ * (see D5-4929 in ARM DDI 0487H.a). Although, the memory barrier in
+ * for the workaround is left as inner-shareable to match with Linux
+ * v6.1-rc8.
  */
-#define TLB_HELPER(name, tlbop)                  \
+#define TLB_HELPER(name, tlbop, sh)              \
 static inline void name(void)                    \
 {                                                \
     asm volatile(                                \
-        "dsb  ishst;"                            \
+        "dsb  "  # sh  "st;"                     \
         "tlbi "  # tlbop  ";"                    \
         ALTERNATIVE(                             \
             "nop; nop;",                         \
@@ -34,25 +40,25 @@ static inline void name(void)                    \
             "tlbi "  # tlbop  ";",               \
             ARM64_WORKAROUND_REPEAT_TLBI,        \
             CONFIG_ARM64_WORKAROUND_REPEAT_TLBI) \
-        "dsb  ish;"                              \
+        "dsb  "  # sh  ";"                       \
         "isb;"                                   \
         : : : "memory");                         \
 }
 
 /* Flush local TLBs, current VMID only. */
-TLB_HELPER(flush_guest_tlb_local, vmalls12e1);
+TLB_HELPER(flush_guest_tlb_local, vmalls12e1, nsh)
 
 /* Flush innershareable TLBs, current VMID only */
-TLB_HELPER(flush_guest_tlb, vmalls12e1is);
+TLB_HELPER(flush_guest_tlb, vmalls12e1is, ish)
 
 /* Flush local TLBs, all VMIDs, non-hypervisor mode */
-TLB_HELPER(flush_all_guests_tlb_local, alle1);
+TLB_HELPER(flush_all_guests_tlb_local, alle1, nsh)
 
 /* Flush innershareable TLBs, all VMIDs, non-hypervisor mode */
-TLB_HELPER(flush_all_guests_tlb, alle1is);
+TLB_HELPER(flush_all_guests_tlb, alle1is, ish)
 
 /* Flush all hypervisor mappings from the TLB of the local processor. */
-TLB_HELPER(flush_xen_tlb_local, alle2);
+TLB_HELPER(flush_xen_tlb_local, alle2, nsh)
 
 /* Flush TLB of local processor for address va. */
 static inline void  __flush_xen_tlb_one_local(vaddr_t va)
@@ -66,6 +72,8 @@ static inline void __flush_xen_tlb_one(vaddr_t va)
     asm volatile("tlbi vae2is, %0;" : : "r" (va>>PAGE_SHIFT) : "memory");
 }
 
+#undef TLB_HELPER
+
 #endif /* __ASM_ARM_ARM64_FLUSHTLB_H__ */
 /*
  * Local variables: