[PATCH v4 1/2] arm64: errata: Workaround NVIDIA Olympus device store/load ordering

[Shanker Donthineni <sdonthineni@nvidia.com>]

On systems with NVIDIA Olympus cores, a Device-nGnR* load can be
observed by a peripheral before an older, non-overlapping Device-nGnR*
store to the same peripheral. This breaks the program-order guarantee
that software expects for Device-nGnR* accesses and can leave a
peripheral in an incorrect state, as a load is observed before an
earlier store takes effect.

The erratum can occur only when all of the following apply:

  - A PE executes a Device-nGnR* store followed by a younger
    Device-nGnR* load.
  - The store is not a store-release.
  - The accesses target the same peripheral and do not overlap in bytes.
  - There is at most one intervening Device-nGnR* store in program
    order, and there are no intervening Device-nGnR* loads.
  - There is no DSB, and no DMB that orders loads, between the store and
    the load.
  - Specific micro-architectural and timing conditions occur.

Promote the raw MMIO store helpers (__raw_writeb/w/l/q) from plain str*
to stlr* (Store-Release) on affected CPUs, which removes the "store is
not a store-release" condition for every device write the kernel issues.
Because writel() and writel_relaxed() are both built on __raw_writel()
in asm-generic/io.h, patching the raw variants covers both the
non-relaxed and relaxed APIs without touching the higher layers. Note
that writel()'s own barrier sits before the store, so it does not order
the store against a subsequent readl(); the store-release promotion is
what provides that ordering.

Like ARM64_ERRATUM_832075 on the load side, the change is gated on a new
ARM64_WORKAROUND_DEVICE_STORE_RELEASE capability and only activated on
parts that match MIDR_NVIDIA_OLYMPUS, so unaffected CPUs continue to use
plain str* instructions.

Note: stlr* only supports base-register addressing, so the raw MMIO
write helpers use a base-register str*/stlr* alternative sequence. This
gives up the offset-addressed str* code generation introduced by commit
d044d6ba6f02 ("arm64: io: permit offset addressing"). A static-branch
implementation would add extra control flow without preserving the
desired offset-addressed code generation in practice, so use a direct
base-register str*/stlr* alternative instead.

For the write-combining copy helpers (__iowrite{32,64}_copy()), the
contiguous str* groups are kept, because replacing those stores would
defeat the write-combining behaviour used to improve store performance.
Rather than rely on the relaxed, no-ordering contract of these helpers -
which would leave affected CPUs behaving differently from every other
arm64 system and exposed to any future driver that depends on ordering
across such copies - the DGH hint emitted once after each copy is
promoted to dmb osh on affected CPUs. That orders the grouped stores
against subsequent loads without placing a barrier in the copy loop,
while unaffected CPUs keep the existing DGH hint. The single-element
case of __const_memcpy_toio_aligned{32,64}() likewise uses a plain str*
(instead of __raw_write*()) so it shares that str* group + DGH path
rather than taking a per-store store-release.

Co-developed-by: Vikram Sethi <vsethi@nvidia.com>
Signed-off-by: Vikram Sethi <vsethi@nvidia.com>
Signed-off-by: Shanker Donthineni <sdonthineni@nvidia.com>
Link: https://lore.kernel.org/all/ajVZBJgKn-5sxHD6@willie-the-truck/
---
 Documentation/arch/arm64/silicon-errata.rst |  2 ++
 arch/arm64/Kconfig                          | 25 +++++++++++++++++
 arch/arm64/include/asm/barrier.h            |  4 ++-
 arch/arm64/include/asm/io.h                 | 31 +++++++++++++--------
 arch/arm64/kernel/cpu_errata.c              |  8 ++++++
 arch/arm64/tools/cpucaps                    |  1 +
 6 files changed, 59 insertions(+), 12 deletions(-)

diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
index ad04d1cdc0f0..c4137f89acef 100644
--- a/Documentation/arch/arm64/silicon-errata.rst
+++ b/Documentation/arch/arm64/silicon-errata.rst
@@ -298,6 +298,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | NVIDIA         | Carmel Core     | N/A             | NVIDIA_CARMEL_CNP_ERRATUM   |
 +----------------+-----------------+-----------------+-----------------------------+
+| NVIDIA         | Olympus core    | T410-OLY-1027   | NVIDIA_OLYMPUS_1027_ERRATUM |
++----------------+-----------------+-----------------+-----------------------------+
 | NVIDIA         | Olympus core    | T410-OLY-1029   | ARM64_ERRATUM_4118414       |
 +----------------+-----------------+-----------------+-----------------------------+
 | NVIDIA         | T241 GICv3/4.x  | T241-FABRIC-4   | N/A                         |
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 10c69474f276..da4e66b19209 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -564,6 +564,31 @@ config ARM64_ERRATUM_832075
 
 	  If unsure, say Y.
 
+config NVIDIA_OLYMPUS_1027_ERRATUM
+	bool "NVIDIA Olympus: device store/load ordering erratum"
+	default y
+	help
+	  This option adds an alternative code sequence to work around an
+	  NVIDIA Olympus core erratum where a Device-nGnR* store can be
+	  observed by a peripheral after a younger Device-nGnR* load to the
+	  same peripheral. This breaks the program order that drivers rely
+	  on for MMIO and can leave a device in an incorrect state.
+
+	  The workaround promotes the raw MMIO store helpers
+	  (__raw_writeb/w/l/q) to Store-Release (STLR), which restores the
+	  required ordering. Because writel() and writel_relaxed() are built
+	  on __raw_writel(), both are covered without changes to the higher
+	  layers. It also promotes the DGH hint used after write-combining
+	  memcpy-to-IO sequences to a DMB, so grouped stores are ordered
+	  against subsequent reads without placing a barrier in the copy loop.
+
+	  The fix is applied through the alternatives framework, so enabling
+	  this option does not by itself activate the workaround: it is
+	  patched in only when an affected CPU is detected, and is a no-op on
+	  unaffected CPUs.
+
+	  If unsure, say Y.
+
 config ARM64_ERRATUM_834220
 	bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault (rare)"
 	depends on KVM
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 9495c4441a46..22792d1305aa 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -38,7 +38,9 @@
  * Device-GRE attributes before the hint instruction with any memory accesses
  * appearing after the hint instruction.
  */
-#define dgh()		asm volatile("hint #6" : : : "memory")
+#define dgh()		asm volatile(ALTERNATIVE("hint #6", "dmb osh",	\
+					 ARM64_WORKAROUND_DEVICE_STORE_RELEASE)	\
+				     : : : "memory")
 
 #define spec_bar()	asm volatile(ALTERNATIVE("dsb nsh\nisb\n",		\
 						 SB_BARRIER_INSN"nop\n",	\
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 8cbd1e96fd50..69e0fa004d31 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -16,7 +16,6 @@
 #include <asm/memory.h>
 #include <asm/early_ioremap.h>
 #include <asm/alternative.h>
-#include <asm/cpufeature.h>
 #include <asm/rsi.h>
 
 /*
@@ -25,29 +24,37 @@
 #define __raw_writeb __raw_writeb
 static __always_inline void __raw_writeb(u8 val, volatile void __iomem *addr)
 {
-	volatile u8 __iomem *ptr = addr;
-	asm volatile("strb %w0, %1" : : "rZ" (val), "Qo" (*ptr));
+	asm volatile(ALTERNATIVE("strb %w0, [%1]",
+				 "stlrb %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_STORE_RELEASE)
+		     : : "rZ" (val), "r" (addr));
 }
 
 #define __raw_writew __raw_writew
 static __always_inline void __raw_writew(u16 val, volatile void __iomem *addr)
 {
-	volatile u16 __iomem *ptr = addr;
-	asm volatile("strh %w0, %1" : : "rZ" (val), "Qo" (*ptr));
+	asm volatile(ALTERNATIVE("strh %w0, [%1]",
+				 "stlrh %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_STORE_RELEASE)
+		     : : "rZ" (val), "r" (addr));
 }
 
 #define __raw_writel __raw_writel
 static __always_inline void __raw_writel(u32 val, volatile void __iomem *addr)
 {
-	volatile u32 __iomem *ptr = addr;
-	asm volatile("str %w0, %1" : : "rZ" (val), "Qo" (*ptr));
+	asm volatile(ALTERNATIVE("str %w0, [%1]",
+				 "stlr %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_STORE_RELEASE)
+		     : : "rZ" (val), "r" (addr));
 }
 
 #define __raw_writeq __raw_writeq
 static __always_inline void __raw_writeq(u64 val, volatile void __iomem *addr)
 {
-	volatile u64 __iomem *ptr = addr;
-	asm volatile("str %x0, %1" : : "rZ" (val), "Qo" (*ptr));
+	asm volatile(ALTERNATIVE("str %x0, [%1]",
+				 "stlr %x0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_STORE_RELEASE)
+		     : : "rZ" (val), "r" (addr));
 }
 
 #define __raw_readb __raw_readb
@@ -178,7 +185,8 @@ __const_memcpy_toio_aligned32(volatile u32 __iomem *to, const u32 *from,
 			     : "rZ"(from[0]), "rZ"(from[1]), "r"(to));
 		break;
 	case 1:
-		__raw_writel(*from, to);
+		asm volatile("str %w0, [%1]"
+			     : : "rZ"(from[0]), "r"(to) : "memory");
 		break;
 	default:
 		BUILD_BUG();
@@ -235,7 +243,8 @@ __const_memcpy_toio_aligned64(volatile u64 __iomem *to, const u64 *from,
 			     : "rZ"(from[0]), "rZ"(from[1]), "r"(to));
 		break;
 	case 1:
-		__raw_writeq(*from, to);
+		asm volatile("str %x0, [%1]"
+			     : : "rZ"(from[0]), "r"(to) : "memory");
 		break;
 	default:
 		BUILD_BUG();
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 4b0d5d932897..76c1f8cf1ee0 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -839,6 +839,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
 	},
 #endif
+#ifdef CONFIG_NVIDIA_OLYMPUS_1027_ERRATUM
+	{
+		/* NVIDIA Olympus core */
+		.desc = "NVIDIA Olympus device load/store ordering erratum",
+		.capability = ARM64_WORKAROUND_DEVICE_STORE_RELEASE,
+		ERRATA_MIDR_ALL_VERSIONS(MIDR_NVIDIA_OLYMPUS),
+	},
+#endif
 #ifdef CONFIG_ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE
 	{
 		/*
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 811c2479e82d..d367257bf770 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -120,6 +120,7 @@ WORKAROUND_CAVIUM_TX2_219_PRFM
 WORKAROUND_CAVIUM_TX2_219_TVM
 WORKAROUND_CLEAN_CACHE
 WORKAROUND_DEVICE_LOAD_ACQUIRE
+WORKAROUND_DEVICE_STORE_RELEASE
 WORKAROUND_NVIDIA_CARMEL_CNP
 WORKAROUND_PMUV3_IMPDEF_TRAPS
 WORKAROUND_QCOM_FALKOR_E1003
-- 
2.54.0.windows.1