From e64f737ad70fee4a3c57d147fc511e5d5014b5dd Mon Sep 17 00:00:00 2001
From: Heiko Stuebner
Date: Wed, 11 May 2022 21:29:10 +0200
Subject: riscv: integrate alternatives better into the main architecture

Right now the alternatives need to be explicitly enabled and
erratas are limited to SiFive ones.

We want to use alternatives not only for patching soc erratas,
but in the future also for handling different behaviour depending
on the existence of future extensions.

So move the core alternatives over to the kernel subdirectory
and move the CONFIG_RISCV_ALTERNATIVE to be a hidden symbol
which we expect relevant erratas and extensions to just select
if needed.

Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Reviewed-by: Philipp Tomsich <philipp.tomsich@vrull.eu>
Link: https://lore.kernel.org/r/20220511192921.2223629-2-heiko@sntech.de
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'arch/riscv/Kconfig')

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 00fd9c548f26..26464dae8ab7 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -324,6 +324,15 @@ config NODES_SHIFT
 	  Specify the maximum number of NUMA Nodes available on the target
 	  system.  Increases memory reserved to accommodate various tables.
 
+config RISCV_ALTERNATIVE
+	bool
+	depends on !XIP_KERNEL
+	help
+	  This Kconfig allows the kernel to automatically patch the
+	  errata required by the execution platform at run time. The
+	  code patching is performed once in the boot stages. It means
+	  that the overhead from this mechanism is just taken once.
+
 config RISCV_ISA_C
 	bool "Emit compressed instructions when building Linux"
 	default y
-- 
cgit v1.2.3


From ff689fd21cb13098305bae3f8d0c0065df2e2fc1 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner
Date: Wed, 11 May 2022 21:29:18 +0200
Subject: riscv: add RISC-V Svpbmt extension support

Svpbmt (the S should be capitalized) is the
"Supervisor-mode: page-based memory types" extension
that specifies attributes for cacheability, idempotency
and ordering.

The relevant settings are done in special bits in PTEs:

Here is the svpbmt PTE format:
| 63 | 62-61 | 60-8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0
  N     MT     RSW    D   A   G   U   X   W   R   V
        ^

Of the Reserved bits [63:54] in a leaf PTE, the high bit is already
allocated (as the N bit), so bits [62:61] are used as the MT (aka
MemType) field. This field specifies one of three memory types that
are close equivalents (or equivalent in effect) to the three main x86
and ARMv8 memory types - as shown in the following table.

RISC-V
Encoding &
MemType     RISC-V Description
----------  ------------------------------------------------
00 - PMA    Normal Cacheable, No change to implied PMA memory type
01 - NC     Non-cacheable, idempotent, weakly-ordered Main Memory
10 - IO     Non-cacheable, non-idempotent, strongly-ordered I/O memory
11 - Rsvd   Reserved for future standard use

As the extension will not be present on all implementations,
implement a method to handle cpufeatures via alternatives
to not incur runtime penalties on cpu variants not supporting
specific extensions and patch relevant code parts at runtime.

Co-developed-by: Wei Fu <wefu@redhat.com>
Signed-off-by: Wei Fu <wefu@redhat.com>
Co-developed-by: Liu Shaohua <liush@allwinnertech.com>
Signed-off-by: Liu Shaohua <liush@allwinnertech.com>
Co-developed-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Guo Ren <guoren@kernel.org>
[moved to use the alternatives mechanism]
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Reviewed-by: Philipp Tomsich <philipp.tomsich@vrull.eu>
Link: https://lore.kernel.org/r/20220511192921.2223629-10-heiko@sntech.de
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig                    | 13 ++++++
 arch/riscv/include/asm/alternative.h  |  3 ++
 arch/riscv/include/asm/errata_list.h  | 15 +++++++
 arch/riscv/include/asm/hwcap.h        |  1 +
 arch/riscv/include/asm/pgtable-32.h   |  9 +++++
 arch/riscv/include/asm/pgtable-64.h   | 47 ++++++++++++++++++++++
 arch/riscv/include/asm/pgtable-bits.h |  4 --
 arch/riscv/include/asm/pgtable.h      | 29 +++++++++++---
 arch/riscv/kernel/alternative.c       |  2 +
 arch/riscv/kernel/cpu.c               |  1 +
 arch/riscv/kernel/cpufeature.c        | 75 ++++++++++++++++++++++++++++++++++-
 11 files changed, 189 insertions(+), 10 deletions(-)

(limited to 'arch/riscv/Kconfig')

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 26464dae8ab7..3935358c03f5 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -343,6 +343,19 @@ config RISCV_ISA_C
 
 	   If you don't know what to do here, say Y.
 
+config RISCV_ISA_SVPBMT
+	bool "SVPBMT extension support"
+	depends on 64BIT && MMU
+	select RISCV_ALTERNATIVE
+	default y
+	help
+	   Adds support to dynamically detect the presence of the SVPBMT extension
+	   (Supervisor-mode: page-based memory types) and enable its usage.
+
+	   The SVPBMT extension is only available on 64Bit cpus.
+
+	   If you don't know what to do here, say Y.
+
 config FPU
 	bool "FPU support"
 	default y
diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h
index 0859529ff08e..64936356c37c 100644
--- a/arch/riscv/include/asm/alternative.h
+++ b/arch/riscv/include/asm/alternative.h
@@ -42,6 +42,9 @@ void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
 			      unsigned long archid, unsigned long impid,
 			      unsigned int stage);
 
+void riscv_cpufeature_patch_func(struct alt_entry *begin, struct alt_entry *end,
+				 unsigned int stage);
+
 #else /* CONFIG_RISCV_ALTERNATIVE */
 
 static inline void apply_boot_alternatives(void) { }
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index 5f1046e82d9f..dbfcd9b72bd8 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -14,6 +14,9 @@
 #define	ERRATA_SIFIVE_NUMBER 2
 #endif
 
+#define	CPUFEATURE_SVPBMT 0
+#define	CPUFEATURE_NUMBER 1
+
 #ifdef __ASSEMBLY__
 
 #define ALT_INSN_FAULT(x)						\
@@ -34,6 +37,18 @@ asm(ALTERNATIVE("sfence.vma %0", "sfence.vma", SIFIVE_VENDOR_ID,	\
 		ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200)	\
 		: : "r" (addr) : "memory")
 
+/*
+ * _val is marked as "will be overwritten", so need to set it to 0
+ * in the default case.
+ */
+#define ALT_SVPBMT_SHIFT 61
+#define ALT_SVPBMT(_val, prot)						\
+asm(ALTERNATIVE("li %0, 0\t\nnop", "li %0, %1\t\nslli %0,%0,%2", 0,	\
+		CPUFEATURE_SVPBMT, CONFIG_RISCV_ISA_SVPBMT)		\
+		: "=r"(_val)						\
+		: "I"(prot##_SVPBMT >> ALT_SVPBMT_SHIFT),		\
+		  "I"(ALT_SVPBMT_SHIFT))
+
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 0734e42f74f2..4e2486881840 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -52,6 +52,7 @@ extern unsigned long elf_hwcap;
  */
 enum riscv_isa_ext_id {
 	RISCV_ISA_EXT_SSCOFPMF = RISCV_ISA_EXT_BASE,
+	RISCV_ISA_EXT_SVPBMT,
 	RISCV_ISA_EXT_ID_MAX = RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h
index e266a4fe7f43..59ba1fbaf784 100644
--- a/arch/riscv/include/asm/pgtable-32.h
+++ b/arch/riscv/include/asm/pgtable-32.h
@@ -24,4 +24,13 @@
  */
 #define _PAGE_PFN_MASK  GENMASK(31, 10)
 
+#define _PAGE_NOCACHE		0
+#define _PAGE_IO		0
+#define _PAGE_MTMASK		0
+
+/* Set of bits to preserve across pte_modify() */
+#define _PAGE_CHG_MASK  (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ |	\
+					  _PAGE_WRITE | _PAGE_EXEC |	\
+					  _PAGE_USER | _PAGE_GLOBAL))
+
 #endif /* _ASM_RISCV_PGTABLE_32_H */
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 15f3ad5aee4f..2354501f0203 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -8,6 +8,7 @@
 
 #include <linux/bits.h>
 #include <linux/const.h>
+#include <asm/errata_list.h>
 
 extern bool pgtable_l4_enabled;
 extern bool pgtable_l5_enabled;
@@ -73,6 +74,52 @@ typedef struct {
  */
 #define _PAGE_PFN_MASK  GENMASK(53, 10)
 
+/*
+ * [62:61] Svpbmt Memory Type definitions:
+ *
+ *  00 - PMA    Normal Cacheable, No change to implied PMA memory type
+ *  01 - NC     Non-cacheable, idempotent, weakly-ordered Main Memory
+ *  10 - IO     Non-cacheable, non-idempotent, strongly-ordered I/O memory
+ *  11 - Rsvd   Reserved for future standard use
+ */
+#define _PAGE_NOCACHE_SVPBMT	(1UL << 61)
+#define _PAGE_IO_SVPBMT		(1UL << 62)
+#define _PAGE_MTMASK_SVPBMT	(_PAGE_NOCACHE_SVPBMT | _PAGE_IO_SVPBMT)
+
+static inline u64 riscv_page_mtmask(void)
+{
+	u64 val;
+
+	ALT_SVPBMT(val, _PAGE_MTMASK);
+	return val;
+}
+
+static inline u64 riscv_page_nocache(void)
+{
+	u64 val;
+
+	ALT_SVPBMT(val, _PAGE_NOCACHE);
+	return val;
+}
+
+static inline u64 riscv_page_io(void)
+{
+	u64 val;
+
+	ALT_SVPBMT(val, _PAGE_IO);
+	return val;
+}
+
+#define _PAGE_NOCACHE		riscv_page_nocache()
+#define _PAGE_IO		riscv_page_io()
+#define _PAGE_MTMASK		riscv_page_mtmask()
+
+/* Set of bits to preserve across pte_modify() */
+#define _PAGE_CHG_MASK  (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ |	\
+					  _PAGE_WRITE | _PAGE_EXEC |	\
+					  _PAGE_USER | _PAGE_GLOBAL |	\
+					  _PAGE_MTMASK))
+
 static inline int pud_present(pud_t pud)
 {
 	return (pud_val(pud) & _PAGE_PRESENT);
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
index e571fa954afc..b9e13a8fe2b7 100644
--- a/arch/riscv/include/asm/pgtable-bits.h
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -29,10 +29,6 @@
 
 #define _PAGE_PFN_SHIFT 10
 
-/* Set of bits to preserve across pte_modify() */
-#define _PAGE_CHG_MASK  (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ |	\
-					  _PAGE_WRITE | _PAGE_EXEC |	\
-					  _PAGE_USER | _PAGE_GLOBAL))
 /*
  * when all of R/W/X are zero, the PTE is a pointer to the next level
  * of the page table; otherwise, it is a leaf PTE.
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index faba543e2b08..c55341b72de1 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -179,11 +179,8 @@ extern struct pt_alloc_ops pt_ops __initdata;
 
 #define PAGE_TABLE		__pgprot(_PAGE_TABLE)
 
-/*
- * The RISC-V ISA doesn't yet specify how to query or modify PMAs, so we can't
- * change the properties of memory regions.
- */
-#define _PAGE_IOREMAP _PAGE_KERNEL
+#define _PAGE_IOREMAP	((_PAGE_KERNEL & ~_PAGE_MTMASK) | _PAGE_IO)
+#define PAGE_KERNEL_IO		__pgprot(_PAGE_IOREMAP)
 
 extern pgd_t swapper_pg_dir[];
 
@@ -523,6 +520,28 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 	return ptep_test_and_clear_young(vma, address, ptep);
 }
 
+#define pgprot_noncached pgprot_noncached
+static inline pgprot_t pgprot_noncached(pgprot_t _prot)
+{
+	unsigned long prot = pgprot_val(_prot);
+
+	prot &= ~_PAGE_MTMASK;
+	prot |= _PAGE_IO;
+
+	return __pgprot(prot);
+}
+
+#define pgprot_writecombine pgprot_writecombine
+static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
+{
+	unsigned long prot = pgprot_val(_prot);
+
+	prot &= ~_PAGE_MTMASK;
+	prot |= _PAGE_NOCACHE;
+
+	return __pgprot(prot);
+}
+
 /*
  * THP functions
  */
diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c
index 223770b3945c..e6c9de9f9ba6 100644
--- a/arch/riscv/kernel/alternative.c
+++ b/arch/riscv/kernel/alternative.c
@@ -63,6 +63,8 @@ static void __init_or_module _apply_alternatives(struct alt_entry *begin,
 						 struct alt_entry *end,
 						 unsigned int stage)
 {
+	riscv_cpufeature_patch_func(begin, end, stage);
+
 	if (!vendor_patch_func)
 		return;
 
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index ccb617791e56..40c8776aec12 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -88,6 +88,7 @@ int riscv_of_parent_hartid(struct device_node *node)
  */
 static struct riscv_isa_ext_data isa_ext_arr[] = {
 	__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
+	__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
 	__RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX),
 };
 
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 1b2d42d7f589..f514b949c6a7 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -8,9 +8,15 @@
 
 #include <linux/bitmap.h>
 #include <linux/ctype.h>
+#include <linux/libfdt.h>
+#include <linux/module.h>
 #include <linux/of.h>
-#include <asm/processor.h>
+#include <asm/alternative.h>
+#include <asm/errata_list.h>
 #include <asm/hwcap.h>
+#include <asm/patch.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
 #include <asm/smp.h>
 #include <asm/switch_to.h>
 
@@ -192,6 +198,7 @@ void __init riscv_fill_hwcap(void)
 				set_bit(*ext - 'a', this_isa);
 			} else {
 				SET_ISA_EXT_MAP("sscofpmf", RISCV_ISA_EXT_SSCOFPMF);
+				SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT);
 			}
 #undef SET_ISA_EXT_MAP
 		}
@@ -237,3 +244,69 @@ void __init riscv_fill_hwcap(void)
 		static_branch_enable(&cpu_hwcap_fpu);
 #endif
 }
+
+#ifdef CONFIG_RISCV_ALTERNATIVE
+struct cpufeature_info {
+	char name[ERRATA_STRING_LENGTH_MAX];
+	bool (*check_func)(unsigned int stage);
+};
+
+static bool __init_or_module cpufeature_svpbmt_check_func(unsigned int stage)
+{
+#ifdef CONFIG_RISCV_ISA_SVPBMT
+	return riscv_isa_extension_available(NULL, SVPBMT);
+#endif
+
+	return false;
+}
+
+static const struct cpufeature_info __initdata_or_module
+cpufeature_list[CPUFEATURE_NUMBER] = {
+	{
+		.name = "svpbmt",
+		.check_func = cpufeature_svpbmt_check_func
+	},
+};
+
+static u32 __init_or_module cpufeature_probe(unsigned int stage)
+{
+	const struct cpufeature_info *info;
+	u32 cpu_req_feature = 0;
+	int idx;
+
+	for (idx = 0; idx < CPUFEATURE_NUMBER; idx++) {
+		info = &cpufeature_list[idx];
+
+		if (info->check_func(stage))
+			cpu_req_feature |= (1U << idx);
+	}
+
+	return cpu_req_feature;
+}
+
+void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin,
+						  struct alt_entry *end,
+						  unsigned int stage)
+{
+	u32 cpu_req_feature = cpufeature_probe(stage);
+	u32 cpu_apply_feature = 0;
+	struct alt_entry *alt;
+	u32 tmp;
+
+	for (alt = begin; alt < end; alt++) {
+		if (alt->vendor_id != 0)
+			continue;
+		if (alt->errata_id >= CPUFEATURE_NUMBER) {
+			WARN(1, "This feature id:%d is not in kernel cpufeature list",
+				alt->errata_id);
+			continue;
+		}
+
+		tmp = (1U << alt->errata_id);
+		if (cpu_req_feature & tmp) {
+			patch_text_nosync(alt->old_ptr, alt->alt_ptr, alt->alt_len);
+			cpu_apply_feature |= tmp;
+		}
+	}
+}
+#endif
-- 
cgit v1.2.3


From a35707c3d850dda0ceefb75b1b3bd191921d5765 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner
Date: Wed, 11 May 2022 21:29:21 +0200
Subject: riscv: add memory-type errata for T-Head

Some current cpus based on T-Head cores implement memory-types
way different than described in the svpbmt spec even going
so far as using PTE bits marked as reserved.

Add the T-Head vendor-id and necessary errata code to
replace the affected instructions.

Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Tested-by: Samuel Holland <samuel@sholland.org>
Link: https://lore.kernel.org/r/20220511192921.2223629-13-heiko@sntech.de
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig                     |  6 +++
 arch/riscv/Kconfig.erratas             | 21 +++++++++
 arch/riscv/errata/Makefile             |  1 +
 arch/riscv/errata/sifive/errata.c      |  7 ++-
 arch/riscv/errata/thead/Makefile       | 11 +++++
 arch/riscv/errata/thead/errata.c       | 82 ++++++++++++++++++++++++++++++++++
 arch/riscv/include/asm/alternative.h   |  6 +++
 arch/riscv/include/asm/errata_list.h   | 50 +++++++++++++++++++--
 arch/riscv/include/asm/pgtable-64.h    | 18 +++++++-
 arch/riscv/include/asm/pgtable.h       | 18 ++++++--
 arch/riscv/include/asm/vendorid_list.h |  1 +
 arch/riscv/kernel/Makefile             | 14 ++++++
 arch/riscv/kernel/alternative.c        | 26 +++++++++++
 arch/riscv/kernel/cpufeature.c         |  7 ++-
 arch/riscv/mm/init.c                   |  1 +
 15 files changed, 260 insertions(+), 9 deletions(-)
 create mode 100644 arch/riscv/errata/thead/Makefile
 create mode 100644 arch/riscv/errata/thead/errata.c

(limited to 'arch/riscv/Kconfig')

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 3935358c03f5..d08584681216 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -333,6 +333,12 @@ config RISCV_ALTERNATIVE
 	  code patching is performed once in the boot stages. It means
 	  that the overhead from this mechanism is just taken once.
 
+config RISCV_ALTERNATIVE_EARLY
+	bool
+	depends on RISCV_ALTERNATIVE
+	help
+	  Allows early patching of the kernel for special errata
+
 config RISCV_ISA_C
 	bool "Emit compressed instructions when building Linux"
 	default y
diff --git a/arch/riscv/Kconfig.erratas b/arch/riscv/Kconfig.erratas
index c521c2ae2de2..ebfcd5cc6eaf 100644
--- a/arch/riscv/Kconfig.erratas
+++ b/arch/riscv/Kconfig.erratas
@@ -33,4 +33,25 @@ config ERRATA_SIFIVE_CIP_1200
 
 	  If you don't know what to do here, say "Y".
 
+config ERRATA_THEAD
+	bool "T-HEAD errata"
+	select RISCV_ALTERNATIVE
+	help
+	  All T-HEAD errata Kconfig depend on this Kconfig. Disabling
+	  this Kconfig will disable all T-HEAD errata. Please say "Y"
+	  here if your platform uses T-HEAD CPU cores.
+
+	  Otherwise, please say "N" here to avoid unnecessary overhead.
+
+config ERRATA_THEAD_PBMT
+	bool "Apply T-Head memory type errata"
+	depends on ERRATA_THEAD && 64BIT
+	select RISCV_ALTERNATIVE_EARLY
+	default y
+	help
+	  This will apply the memory type errata to handle the non-standard
+	  memory type bits in page-table-entries on T-Head SoCs.
+
+	  If you don't know what to do here, say "Y".
+
 endmenu
diff --git a/arch/riscv/errata/Makefile b/arch/riscv/errata/Makefile
index 0ca1c5281a2d..a1055965fbee 100644
--- a/arch/riscv/errata/Makefile
+++ b/arch/riscv/errata/Makefile
@@ -1 +1,2 @@
 obj-$(CONFIG_ERRATA_SIFIVE) += sifive/
+obj-$(CONFIG_ERRATA_THEAD) += thead/
diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c
index 3e39587a49dc..672f02b21ce0 100644
--- a/arch/riscv/errata/sifive/errata.c
+++ b/arch/riscv/errata/sifive/errata.c
@@ -88,10 +88,15 @@ void __init_or_module sifive_errata_patch_func(struct alt_entry *begin,
 					       unsigned int stage)
 {
 	struct alt_entry *alt;
-	u32 cpu_req_errata = sifive_errata_probe(archid, impid);
+	u32 cpu_req_errata;
 	u32 cpu_apply_errata = 0;
 	u32 tmp;
 
+	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
+		return;
+
+	cpu_req_errata = sifive_errata_probe(archid, impid);
+
 	for (alt = begin; alt < end; alt++) {
 		if (alt->vendor_id != SIFIVE_VENDOR_ID)
 			continue;
diff --git a/arch/riscv/errata/thead/Makefile b/arch/riscv/errata/thead/Makefile
new file mode 100644
index 000000000000..137e700d9d3f
--- /dev/null
+++ b/arch/riscv/errata/thead/Makefile
@@ -0,0 +1,11 @@
+ifdef CONFIG_RISCV_ALTERNATIVE_EARLY
+CFLAGS_errata.o := -mcmodel=medany
+ifdef CONFIG_FTRACE
+CFLAGS_REMOVE_errata.o = $(CC_FLAGS_FTRACE)
+endif
+ifdef CONFIG_KASAN
+KASAN_SANITIZE_errata.o := n
+endif
+endif
+
+obj-y += errata.o
diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c
new file mode 100644
index 000000000000..e5d75270b99c
--- /dev/null
+++ b/arch/riscv/errata/thead/errata.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 Heiko Stuebner <heiko@sntech.de>
+ */
+
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <asm/alternative.h>
+#include <asm/cacheflush.h>
+#include <asm/errata_list.h>
+#include <asm/patch.h>
+#include <asm/vendorid_list.h>
+
+struct errata_info {
+	char name[ERRATA_STRING_LENGTH_MAX];
+	bool (*check_func)(unsigned long arch_id, unsigned long impid);
+	unsigned int stage;
+};
+
+static bool errata_mt_check_func(unsigned long  arch_id, unsigned long impid)
+{
+	if (arch_id != 0 || impid != 0)
+		return false;
+	return true;
+}
+
+static const struct errata_info errata_list[ERRATA_THEAD_NUMBER] = {
+	{
+		.name = "memory-types",
+		.stage = RISCV_ALTERNATIVES_EARLY_BOOT,
+		.check_func = errata_mt_check_func
+	},
+};
+
+static u32 thead_errata_probe(unsigned int stage, unsigned long archid, unsigned long impid)
+{
+	const struct errata_info *info;
+	u32 cpu_req_errata = 0;
+	int idx;
+
+	for (idx = 0; idx < ERRATA_THEAD_NUMBER; idx++) {
+		info = &errata_list[idx];
+
+		if ((stage == RISCV_ALTERNATIVES_MODULE ||
+		     info->stage == stage) && info->check_func(archid, impid))
+			cpu_req_errata |= (1U << idx);
+	}
+
+	return cpu_req_errata;
+}
+
+void __init_or_module thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
+					      unsigned long archid, unsigned long impid,
+					      unsigned int stage)
+{
+	struct alt_entry *alt;
+	u32 cpu_req_errata = thead_errata_probe(stage, archid, impid);
+	u32 tmp;
+
+	for (alt = begin; alt < end; alt++) {
+		if (alt->vendor_id != THEAD_VENDOR_ID)
+			continue;
+		if (alt->errata_id >= ERRATA_THEAD_NUMBER)
+			continue;
+
+		tmp = (1U << alt->errata_id);
+		if (cpu_req_errata & tmp) {
+			/* On vm-alternatives, the mmu isn't running yet */
+			if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
+				memcpy((void *)__pa_symbol(alt->old_ptr),
+				       (void *)__pa_symbol(alt->alt_ptr), alt->alt_len);
+			else
+				patch_text_nosync(alt->old_ptr, alt->alt_ptr, alt->alt_len);
+		}
+	}
+
+	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
+		local_flush_icache_all();
+}
diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h
index 64936356c37c..6511dd73e812 100644
--- a/arch/riscv/include/asm/alternative.h
+++ b/arch/riscv/include/asm/alternative.h
@@ -21,8 +21,10 @@
 
 #define RISCV_ALTERNATIVES_BOOT		0 /* alternatives applied during regular boot */
 #define RISCV_ALTERNATIVES_MODULE	1 /* alternatives applied during module-init */
+#define RISCV_ALTERNATIVES_EARLY_BOOT	2 /* alternatives applied before mmu start */
 
 void __init apply_boot_alternatives(void);
+void __init apply_early_boot_alternatives(void);
 void apply_module_alternatives(void *start, size_t length);
 
 struct alt_entry {
@@ -41,6 +43,9 @@ struct errata_checkfunc_id {
 void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
 			      unsigned long archid, unsigned long impid,
 			      unsigned int stage);
+void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
+			     unsigned long archid, unsigned long impid,
+			     unsigned int stage);
 
 void riscv_cpufeature_patch_func(struct alt_entry *begin, struct alt_entry *end,
 				 unsigned int stage);
@@ -48,6 +53,7 @@ void riscv_cpufeature_patch_func(struct alt_entry *begin, struct alt_entry *end,
 #else /* CONFIG_RISCV_ALTERNATIVE */
 
 static inline void apply_boot_alternatives(void) { }
+static inline void apply_early_boot_alternatives(void) { }
 static inline void apply_module_alternatives(void *start, size_t length) { }
 
 #endif /* CONFIG_RISCV_ALTERNATIVE */
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index dbfcd9b72bd8..9e2888dbb5b1 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -14,6 +14,11 @@
 #define	ERRATA_SIFIVE_NUMBER 2
 #endif
 
+#ifdef CONFIG_ERRATA_THEAD
+#define	ERRATA_THEAD_PBMT 0
+#define	ERRATA_THEAD_NUMBER 1
+#endif
+
 #define	CPUFEATURE_SVPBMT 0
 #define	CPUFEATURE_NUMBER 1
 
@@ -42,12 +47,51 @@ asm(ALTERNATIVE("sfence.vma %0", "sfence.vma", SIFIVE_VENDOR_ID,	\
  * in the default case.
  */
 #define ALT_SVPBMT_SHIFT 61
+#define ALT_THEAD_PBMT_SHIFT 59
 #define ALT_SVPBMT(_val, prot)						\
-asm(ALTERNATIVE("li %0, 0\t\nnop", "li %0, %1\t\nslli %0,%0,%2", 0,	\
-		CPUFEATURE_SVPBMT, CONFIG_RISCV_ISA_SVPBMT)		\
+asm(ALTERNATIVE_2("li %0, 0\t\nnop",					\
+		  "li %0, %1\t\nslli %0,%0,%3", 0,			\
+			CPUFEATURE_SVPBMT, CONFIG_RISCV_ISA_SVPBMT,	\
+		  "li %0, %2\t\nslli %0,%0,%4", THEAD_VENDOR_ID,	\
+			ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT)	\
 		: "=r"(_val)						\
 		: "I"(prot##_SVPBMT >> ALT_SVPBMT_SHIFT),		\
-		  "I"(ALT_SVPBMT_SHIFT))
+		  "I"(prot##_THEAD >> ALT_THEAD_PBMT_SHIFT),		\
+		  "I"(ALT_SVPBMT_SHIFT),				\
+		  "I"(ALT_THEAD_PBMT_SHIFT))
+
+#ifdef CONFIG_ERRATA_THEAD_PBMT
+/*
+ * IO/NOCACHE memory types are handled together with svpbmt,
+ * so on T-Head chips, check if no other memory type is set,
+ * and set the non-0 PMA type if applicable.
+ */
+#define ALT_THEAD_PMA(_val)						\
+asm volatile(ALTERNATIVE(						\
+	"nop\n\t"							\
+	"nop\n\t"							\
+	"nop\n\t"							\
+	"nop\n\t"							\
+	"nop\n\t"							\
+	"nop\n\t"							\
+	"nop",								\
+	"li      t3, %2\n\t"						\
+	"slli    t3, t3, %4\n\t"					\
+	"and     t3, %0, t3\n\t"					\
+	"bne     t3, zero, 2f\n\t"					\
+	"li      t3, %3\n\t"						\
+	"slli    t3, t3, %4\n\t"					\
+	"or      %0, %0, t3\n\t"					\
+	"2:",  THEAD_VENDOR_ID,						\
+		ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT)		\
+	: "+r"(_val)							\
+	: "0"(_val),							\
+	  "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_PBMT_SHIFT),		\
+	  "I"(_PAGE_PMA_THEAD >> ALT_THEAD_PBMT_SHIFT),			\
+	  "I"(ALT_THEAD_PBMT_SHIFT))
+#else
+#define ALT_THEAD_PMA(_val)
+#endif
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 2354501f0203..e4ff3e0ab887 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -86,6 +86,18 @@ typedef struct {
 #define _PAGE_IO_SVPBMT		(1UL << 62)
 #define _PAGE_MTMASK_SVPBMT	(_PAGE_NOCACHE_SVPBMT | _PAGE_IO_SVPBMT)
 
+/*
+ * [63:59] T-Head Memory Type definitions:
+ *
+ * 00000 - NC   Weakly-ordered, Non-cacheable, Non-bufferable, Non-shareable, Non-trustable
+ * 01110 - PMA  Weakly-ordered, Cacheable, Bufferable, Shareable, Non-trustable
+ * 10000 - IO   Strongly-ordered, Non-cacheable, Non-bufferable, Non-shareable, Non-trustable
+ */
+#define _PAGE_PMA_THEAD		((1UL << 62) | (1UL << 61) | (1UL << 60))
+#define _PAGE_NOCACHE_THEAD	0UL
+#define _PAGE_IO_THEAD		(1UL << 63)
+#define _PAGE_MTMASK_THEAD	(_PAGE_PMA_THEAD | _PAGE_IO_THEAD | (1UL << 59))
+
 static inline u64 riscv_page_mtmask(void)
 {
 	u64 val;
@@ -193,7 +205,11 @@ static inline bool mm_pud_folded(struct mm_struct *mm)
 
 static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot)
 {
-	return __pmd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+	unsigned long prot_val = pgprot_val(prot);
+
+	ALT_THEAD_PMA(prot_val);
+
+	return __pmd((pfn << _PAGE_PFN_SHIFT) | prot_val);
 }
 
 static inline unsigned long _pmd_pfn(pmd_t pmd)
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index c55341b72de1..6f0a260d3f2c 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -250,7 +250,11 @@ static inline void pmd_clear(pmd_t *pmdp)
 
 static inline pgd_t pfn_pgd(unsigned long pfn, pgprot_t prot)
 {
-	return __pgd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+	unsigned long prot_val = pgprot_val(prot);
+
+	ALT_THEAD_PMA(prot_val);
+
+	return __pgd((pfn << _PAGE_PFN_SHIFT) | prot_val);
 }
 
 static inline unsigned long _pgd_pfn(pgd_t pgd)
@@ -289,7 +293,11 @@ static inline unsigned long pte_pfn(pte_t pte)
 /* Constructs a page table entry */
 static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
 {
-	return __pte((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+	unsigned long prot_val = pgprot_val(prot);
+
+	ALT_THEAD_PMA(prot_val);
+
+	return __pte((pfn << _PAGE_PFN_SHIFT) | prot_val);
 }
 
 #define mk_pte(page, prot)       pfn_pte(page_to_pfn(page), prot)
@@ -398,7 +406,11 @@ static inline int pmd_protnone(pmd_t pmd)
 /* Modify page protection bits */
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+	unsigned long newprot_val = pgprot_val(newprot);
+
+	ALT_THEAD_PMA(newprot_val);
+
+	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | newprot_val);
 }
 
 #define pgd_ERROR(e) \
diff --git a/arch/riscv/include/asm/vendorid_list.h b/arch/riscv/include/asm/vendorid_list.h
index 9d934215b3c8..cb89af3f0704 100644
--- a/arch/riscv/include/asm/vendorid_list.h
+++ b/arch/riscv/include/asm/vendorid_list.h
@@ -6,5 +6,6 @@
 #define ASM_VENDOR_LIST_H
 
 #define SIFIVE_VENDOR_ID	0x489
+#define THEAD_VENDOR_ID		0x5b7
 
 #endif
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 0f8348ac30f1..bf3876a77ed7 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -14,6 +14,20 @@ ifdef CONFIG_KEXEC
 AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax)
 endif
 
+# cmodel=medany and notrace when patching early
+ifdef CONFIG_RISCV_ALTERNATIVE_EARLY
+CFLAGS_alternative.o := -mcmodel=medany
+CFLAGS_cpufeature.o := -mcmodel=medany
+ifdef CONFIG_FTRACE
+CFLAGS_REMOVE_alternative.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_cpufeature.o = $(CC_FLAGS_FTRACE)
+endif
+ifdef CONFIG_KASAN
+KASAN_SANITIZE_alternative.o := n
+KASAN_SANITIZE_cpufeature.o := n
+endif
+endif
+
 extra-y += head.o
 extra-y += vmlinux.lds
 
diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c
index 27f722ae452b..c9d0d3c53223 100644
--- a/arch/riscv/kernel/alternative.c
+++ b/arch/riscv/kernel/alternative.c
@@ -42,6 +42,11 @@ static void __init_or_module riscv_fill_cpu_mfr_info(struct cpu_manufacturer_inf
 	case SIFIVE_VENDOR_ID:
 		cpu_mfr_info->vendor_patch_func = sifive_errata_patch_func;
 		break;
+#endif
+#ifdef CONFIG_ERRATA_THEAD
+	case THEAD_VENDOR_ID:
+		cpu_mfr_info->vendor_patch_func = thead_errata_patch_func;
+		break;
 #endif
 	default:
 		cpu_mfr_info->vendor_patch_func = NULL;
@@ -82,6 +87,27 @@ void __init apply_boot_alternatives(void)
 			    RISCV_ALTERNATIVES_BOOT);
 }
 
+/*
+ * apply_early_boot_alternatives() is called from setup_vm() with MMU-off.
+ *
+ * Following requirements should be honoured for it to work correctly:
+ * 1) It should use PC-relative addressing for accessing kernel symbols.
+ *    To achieve this we always use GCC cmodel=medany.
+ * 2) The compiler instrumentation for FTRACE will not work for setup_vm()
+ *    so disable compiler instrumentation when FTRACE is enabled.
+ *
+ * Currently, the above requirements are honoured by using custom CFLAGS
+ * for alternative.o in kernel/Makefile.
+ */
+void __init apply_early_boot_alternatives(void)
+{
+#ifdef CONFIG_RISCV_ALTERNATIVE_EARLY
+	_apply_alternatives((struct alt_entry *)__alt_start,
+			    (struct alt_entry *)__alt_end,
+			    RISCV_ALTERNATIVES_EARLY_BOOT);
+#endif
+}
+
 #ifdef CONFIG_MODULES
 void apply_module_alternatives(void *start, size_t length)
 {
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index f514b949c6a7..dea3ea19deee 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -254,7 +254,12 @@ struct cpufeature_info {
 static bool __init_or_module cpufeature_svpbmt_check_func(unsigned int stage)
 {
 #ifdef CONFIG_RISCV_ISA_SVPBMT
-	return riscv_isa_extension_available(NULL, SVPBMT);
+	switch (stage) {
+	case RISCV_ALTERNATIVES_EARLY_BOOT:
+		return false;
+	default:
+		return riscv_isa_extension_available(NULL, SVPBMT);
+	}
 #endif
 
 	return false;
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 9535bea8688c..1d35a0667db3 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -935,6 +935,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K);
 #endif
 
+	apply_early_boot_alternatives();
 	pt_ops_set_early();
 
 	/* Setup early PGD for fixmap */
-- 
cgit v1.2.3


From 9be8459298eadb39b9fe9974b890239e9c123107 Mon Sep 17 00:00:00 2001
From: Guo Ren
Date: Tue, 5 Apr 2022 15:13:14 +0800
Subject: riscv: compat: Add COMPAT Kbuild skeletal support

Adds initial skeletal COMPAT Kbuild (Running 32bit U-mode on
64bit S-mode) support.
 - Setup kconfig & dummy functions for compiling.
 - Implement compat_start_thread by the way.

Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/r/20220405071314.3225832-21-guoren@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'arch/riscv/Kconfig')

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 00fd9c548f26..def9798e9675 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -76,6 +76,7 @@ config RISCV
 	select HAVE_ARCH_KGDB if !XIP_KERNEL
 	select HAVE_ARCH_KGDB_QXFER_PKT
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
+	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU
@@ -127,12 +128,18 @@ config ARCH_MMAP_RND_BITS_MIN
 	default 18 if 64BIT
 	default 8
 
+config ARCH_MMAP_RND_COMPAT_BITS_MIN
+	default 8
+
 # max bits determined by the following formula:
 #  VA_BITS - PAGE_SHIFT - 3
 config ARCH_MMAP_RND_BITS_MAX
 	default 24 if 64BIT # SV39 based
 	default 17
 
+config ARCH_MMAP_RND_COMPAT_BITS_MAX
+	default 17
+
 # set if we run in machine mode, cleared if we run in supervisor mode
 config RISCV_M_MODE
 	bool
@@ -394,6 +401,18 @@ config CRASH_DUMP
 
 	  For more details see Documentation/admin-guide/kdump/kdump.rst
 
+config COMPAT
+	bool "Kernel support for 32-bit U-mode"
+	default 64BIT
+	depends on 64BIT && MMU
+	help
+	  This option enables support for a 32-bit U-mode running under a 64-bit
+	  kernel at S-mode. riscv32-specific components such as system calls,
+	  the user helper functions (vdso), signal rt_frame functions and the
+	  ptrace interface are handled appropriately by the kernel.
+
+	  If you want to execute 32-bit userspace applications, say Y.
+
 endmenu
 
 menu "Boot options"
-- 
cgit v1.2.3


From 6261586e0c91db14c34f894f4bc48f2300cff1d4 Mon Sep 17 00:00:00 2001
From: Liao Chang
Date: Fri, 8 Apr 2022 18:09:11 +0800
Subject: RISC-V: Add kexec_file support

This patch adds support for kexec_file on RISC-V. I tested it on riscv64
QEMU with busybear-linux and single core along with the OpenSBI firmware
fw_jump.bin for generic platform.

On SMP system, it depends on CONFIG_{HOTPLUG_CPU, RISCV_SBI} to
resume/stop hart through OpenSBI firmware, it also needs a OpenSBI that
support the HSM extension.

Signed-off-by: Liao Chang <liaochang1@huawei.com>
Signed-off-by: Li Zhengyu <lizhengyu3@huawei.com>
Link: https://lore.kernel.org/r/20220408100914.150110-4-lizhengyu3@huawei.com
[Palmer: Make 64-bit only]
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig                     |  14 +++
 arch/riscv/include/asm/kexec.h         |   4 +
 arch/riscv/kernel/Makefile             |   1 +
 arch/riscv/kernel/elf_kexec.c          | 180 +++++++++++++++++++++++++++++++++
 arch/riscv/kernel/machine_kexec_file.c |  14 +++
 5 files changed, 213 insertions(+)
 create mode 100644 arch/riscv/kernel/elf_kexec.c
 create mode 100644 arch/riscv/kernel/machine_kexec_file.c

(limited to 'arch/riscv/Kconfig')

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 00fd9c548f26..860817a56af6 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -383,6 +383,20 @@ config KEXEC
 
 	  The name comes from the similarity to the exec system call.
 
+config KEXEC_FILE
+	bool "kexec file based systmem call"
+	select KEXEC_CORE
+	select KEXEC_ELF
+	select HAVE_IMA_KEXEC if IMA
+	depends on 64BIT
+	help
+	  This is new version of kexec system call. This system call is
+	  file based and takes file descriptors as system call argument
+	  for kernel and initramfs as opposed to list of segments as
+	  accepted by previous system call.
+
+	  If you don't know what to do here, say Y.
+
 config CRASH_DUMP
 	bool "Build kdump crash kernel"
 	help
diff --git a/arch/riscv/include/asm/kexec.h b/arch/riscv/include/asm/kexec.h
index e4e291d40759..206217b23301 100644
--- a/arch/riscv/include/asm/kexec.h
+++ b/arch/riscv/include/asm/kexec.h
@@ -53,4 +53,8 @@ typedef void (*riscv_kexec_method)(unsigned long first_ind_entry,
 
 extern riscv_kexec_method riscv_kexec_norelocate;
 
+#ifdef CONFIG_KEXEC_FILE
+extern const struct kexec_file_ops elf_kexec_ops;
+#endif
+
 #endif
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 87adbe47bc15..6673c50c58e2 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -64,6 +64,7 @@ endif
 obj-$(CONFIG_HOTPLUG_CPU)	+= cpu-hotplug.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_KEXEC)		+= kexec_relocate.o crash_save_regs.o machine_kexec.o
+obj-$(CONFIG_KEXEC_FILE)	+= elf_kexec.o machine_kexec_file.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 
 obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o
diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c
new file mode 100644
index 000000000000..2d442a849871
--- /dev/null
+++ b/arch/riscv/kernel/elf_kexec.c
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Load ELF vmlinux file for the kexec_file_load syscall.
+ *
+ * Copyright (C) 2021 Huawei Technologies Co, Ltd.
+ *
+ * Author: Liao Chang (liaochang1@huawei.com)
+ *
+ * Based on kexec-tools' kexec-elf-riscv.c, heavily modified
+ * for kernel.
+ */
+
+#define pr_fmt(fmt)	"kexec_image: " fmt
+
+#include <linux/elf.h>
+#include <linux/kexec.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/libfdt.h>
+#include <linux/types.h>
+
+static int riscv_kexec_elf_load(struct kimage *image, struct elfhdr *ehdr,
+				struct kexec_elf_info *elf_info, unsigned long old_pbase,
+				unsigned long new_pbase)
+{
+	int i;
+	int ret = 0;
+	size_t size;
+	struct kexec_buf kbuf;
+	const struct elf_phdr *phdr;
+
+	kbuf.image = image;
+
+	for (i = 0; i < ehdr->e_phnum; i++) {
+		phdr = &elf_info->proghdrs[i];
+		if (phdr->p_type != PT_LOAD)
+			continue;
+
+		size = phdr->p_filesz;
+		if (size > phdr->p_memsz)
+			size = phdr->p_memsz;
+
+		kbuf.buffer = (void *) elf_info->buffer + phdr->p_offset;
+		kbuf.bufsz = size;
+		kbuf.buf_align = phdr->p_align;
+		kbuf.mem = phdr->p_paddr - old_pbase + new_pbase;
+		kbuf.memsz = phdr->p_memsz;
+		kbuf.top_down = false;
+		ret = kexec_add_buffer(&kbuf);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+/*
+ * Go through the available phsyical memory regions and find one that hold
+ * an image of the specified size.
+ */
+static int elf_find_pbase(struct kimage *image, unsigned long kernel_len,
+			  struct elfhdr *ehdr, struct kexec_elf_info *elf_info,
+			  unsigned long *old_pbase, unsigned long *new_pbase)
+{
+	int i;
+	int ret;
+	struct kexec_buf kbuf;
+	const struct elf_phdr *phdr;
+	unsigned long lowest_paddr = ULONG_MAX;
+	unsigned long lowest_vaddr = ULONG_MAX;
+
+	for (i = 0; i < ehdr->e_phnum; i++) {
+		phdr = &elf_info->proghdrs[i];
+		if (phdr->p_type != PT_LOAD)
+			continue;
+
+		if (lowest_paddr > phdr->p_paddr)
+			lowest_paddr = phdr->p_paddr;
+
+		if (lowest_vaddr > phdr->p_vaddr)
+			lowest_vaddr = phdr->p_vaddr;
+	}
+
+	kbuf.image = image;
+	kbuf.buf_min = lowest_paddr;
+	kbuf.buf_max = ULONG_MAX;
+	kbuf.buf_align = PAGE_SIZE;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
+	kbuf.memsz = ALIGN(kernel_len, PAGE_SIZE);
+	kbuf.top_down = false;
+	ret = arch_kexec_locate_mem_hole(&kbuf);
+	if (!ret) {
+		*old_pbase = lowest_paddr;
+		*new_pbase = kbuf.mem;
+		image->start = ehdr->e_entry - lowest_vaddr + kbuf.mem;
+	}
+	return ret;
+}
+
+static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
+			    unsigned long kernel_len, char *initrd,
+			    unsigned long initrd_len, char *cmdline,
+			    unsigned long cmdline_len)
+{
+	int ret;
+	unsigned long old_kernel_pbase = ULONG_MAX;
+	unsigned long new_kernel_pbase = 0UL;
+	unsigned long initrd_pbase = 0UL;
+	void *fdt;
+	struct elfhdr ehdr;
+	struct kexec_buf kbuf;
+	struct kexec_elf_info elf_info;
+
+	ret = kexec_build_elf_info(kernel_buf, kernel_len, &ehdr, &elf_info);
+	if (ret)
+		return ERR_PTR(ret);
+
+	ret = elf_find_pbase(image, kernel_len, &ehdr, &elf_info,
+			     &old_kernel_pbase, &new_kernel_pbase);
+	if (ret)
+		goto out;
+	pr_notice("The entry point of kernel at 0x%lx\n", image->start);
+
+	/* Add the kernel binary to the image */
+	ret = riscv_kexec_elf_load(image, &ehdr, &elf_info,
+				   old_kernel_pbase, new_kernel_pbase);
+	if (ret)
+		goto out;
+
+	kbuf.image = image;
+	kbuf.buf_min = new_kernel_pbase + kernel_len;
+	kbuf.buf_max = ULONG_MAX;
+	/* Add the initrd to the image */
+	if (initrd != NULL) {
+		kbuf.buffer = initrd;
+		kbuf.bufsz = kbuf.memsz = initrd_len;
+		kbuf.buf_align = PAGE_SIZE;
+		kbuf.top_down = false;
+		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
+		ret = kexec_add_buffer(&kbuf);
+		if (ret)
+			goto out;
+		initrd_pbase = kbuf.mem;
+		pr_notice("Loaded initrd at 0x%lx\n", initrd_pbase);
+	}
+
+	/* Add the DTB to the image */
+	fdt = of_kexec_alloc_and_setup_fdt(image, initrd_pbase,
+					   initrd_len, cmdline, 0);
+	if (!fdt) {
+		pr_err("Error setting up the new device tree.\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	fdt_pack(fdt);
+	kbuf.buffer = fdt;
+	kbuf.bufsz = kbuf.memsz = fdt_totalsize(fdt);
+	kbuf.buf_align = PAGE_SIZE;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
+	kbuf.top_down = true;
+	ret = kexec_add_buffer(&kbuf);
+	if (ret) {
+		pr_err("Error add DTB kbuf ret=%d\n", ret);
+		goto out_free_fdt;
+	}
+	pr_notice("Loaded device tree at 0x%lx\n", kbuf.mem);
+	goto out;
+
+out_free_fdt:
+	kvfree(fdt);
+out:
+	kexec_free_elf_info(&elf_info);
+	return ret ? ERR_PTR(ret) : NULL;
+}
+
+const struct kexec_file_ops elf_kexec_ops = {
+	.probe = kexec_elf_probe,
+	.load  = elf_kexec_load,
+};
diff --git a/arch/riscv/kernel/machine_kexec_file.c b/arch/riscv/kernel/machine_kexec_file.c
new file mode 100644
index 000000000000..b0bf8c1722c0
--- /dev/null
+++ b/arch/riscv/kernel/machine_kexec_file.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * kexec_file for riscv, use vmlinux as the dump-capture kernel image.
+ *
+ * Copyright (C) 2021 Huawei Technologies Co, Ltd.
+ *
+ * Author: Liao Chang (liaochang1@huawei.com)
+ */
+#include <linux/kexec.h>
+
+const struct kexec_file_ops * const kexec_file_loaders[] = {
+	&elf_kexec_ops,
+	NULL
+};
-- 
cgit v1.2.3


From 736e30af583fb6e0e2b8211b894ff99dea0f1ee7 Mon Sep 17 00:00:00 2001
From: Li Zhengyu
Date: Fri, 8 Apr 2022 18:09:13 +0800
Subject: RISC-V: Add purgatory

This patch adds purgatory, the name and concept have been taken
from kexec-tools. Purgatory runs between two kernels, and do
verify sha256 hash to ensure the kernel to jump to is fine and
has not been corrupted after loading. Makefile is modified based
on x86 platform.

Signed-off-by: Li Zhengyu <lizhengyu3@huawei.com>
Link: https://lore.kernel.org/r/20220408100914.150110-6-lizhengyu3@huawei.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kbuild                |  2 +
 arch/riscv/Kconfig               |  6 +++
 arch/riscv/purgatory/.gitignore  |  4 ++
 arch/riscv/purgatory/Makefile    | 95 ++++++++++++++++++++++++++++++++++++++++
 arch/riscv/purgatory/entry.S     | 47 ++++++++++++++++++++
 arch/riscv/purgatory/purgatory.c | 45 +++++++++++++++++++
 6 files changed, 199 insertions(+)
 create mode 100644 arch/riscv/purgatory/.gitignore
 create mode 100644 arch/riscv/purgatory/Makefile
 create mode 100644 arch/riscv/purgatory/entry.S
 create mode 100644 arch/riscv/purgatory/purgatory.c

(limited to 'arch/riscv/Kconfig')

diff --git a/arch/riscv/Kbuild b/arch/riscv/Kbuild
index fb3397223d52..f562c7343fda 100644
--- a/arch/riscv/Kbuild
+++ b/arch/riscv/Kbuild
@@ -3,5 +3,7 @@
 obj-y += kernel/ mm/ net/
 obj-$(CONFIG_BUILTIN_DTB) += boot/dts/
 
+obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += purgatory/
+
 # for cleaning
 subdir- += boot
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 860817a56af6..898052ff743e 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -397,6 +397,12 @@ config KEXEC_FILE
 
 	  If you don't know what to do here, say Y.
 
+config ARCH_HAS_KEXEC_PURGATORY
+	def_bool KEXEC_FILE
+	select BUILD_BIN2C
+	depends on CRYPTO=y
+	depends on CRYPTO_SHA256=y
+
 config CRASH_DUMP
 	bool "Build kdump crash kernel"
 	help
diff --git a/arch/riscv/purgatory/.gitignore b/arch/riscv/purgatory/.gitignore
new file mode 100644
index 000000000000..38d7d1bda4d7
--- /dev/null
+++ b/arch/riscv/purgatory/.gitignore
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+purgatory.chk
+purgatory.ro
+kexec-purgatory.c
diff --git a/arch/riscv/purgatory/Makefile b/arch/riscv/purgatory/Makefile
new file mode 100644
index 000000000000..d4df200f7edf
--- /dev/null
+++ b/arch/riscv/purgatory/Makefile
@@ -0,0 +1,95 @@
+# SPDX-License-Identifier: GPL-2.0
+OBJECT_FILES_NON_STANDARD := y
+
+purgatory-y := purgatory.o sha256.o entry.o string.o ctype.o memcpy.o memset.o
+
+targets += $(purgatory-y)
+PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
+
+$(obj)/string.o: $(srctree)/lib/string.c FORCE
+	$(call if_changed_rule,cc_o_c)
+
+$(obj)/ctype.o: $(srctree)/lib/ctype.c FORCE
+	$(call if_changed_rule,cc_o_c)
+
+$(obj)/memcpy.o: $(srctree)/arch/riscv/lib/memcpy.S FORCE
+	$(call if_changed_rule,as_o_S)
+
+$(obj)/memset.o: $(srctree)/arch/riscv/lib/memset.S FORCE
+	$(call if_changed_rule,as_o_S)
+
+$(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE
+	$(call if_changed_rule,cc_o_c)
+
+CFLAGS_sha256.o := -D__DISABLE_EXPORTS
+CFLAGS_string.o := -D__DISABLE_EXPORTS
+CFLAGS_ctype.o := -D__DISABLE_EXPORTS
+
+# When linking purgatory.ro with -r unresolved symbols are not checked,
+# also link a purgatory.chk binary without -r to check for unresolved symbols.
+PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib
+LDFLAGS_purgatory.ro := -r $(PURGATORY_LDFLAGS)
+LDFLAGS_purgatory.chk := $(PURGATORY_LDFLAGS)
+targets += purgatory.ro purgatory.chk
+
+# Sanitizer, etc. runtimes are unavailable and cannot be linked here.
+GCOV_PROFILE	:= n
+KASAN_SANITIZE	:= n
+UBSAN_SANITIZE	:= n
+KCSAN_SANITIZE	:= n
+KCOV_INSTRUMENT := n
+
+# These are adjustments to the compiler flags used for objects that
+# make up the standalone purgatory.ro
+
+PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
+PURGATORY_CFLAGS := -mcmodel=medany -ffreestanding -fno-zero-initialized-in-bss
+PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING
+PURGATORY_CFLAGS += -fno-stack-protector -g0
+
+# Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
+# in turn leaves some undefined symbols like __fentry__ in purgatory and not
+# sure how to relocate those.
+ifdef CONFIG_FUNCTION_TRACER
+PURGATORY_CFLAGS_REMOVE		+= $(CC_FLAGS_FTRACE)
+endif
+
+ifdef CONFIG_STACKPROTECTOR
+PURGATORY_CFLAGS_REMOVE		+= -fstack-protector
+endif
+
+ifdef CONFIG_STACKPROTECTOR_STRONG
+PURGATORY_CFLAGS_REMOVE		+= -fstack-protector-strong
+endif
+
+CFLAGS_REMOVE_purgatory.o	+= $(PURGATORY_CFLAGS_REMOVE)
+CFLAGS_purgatory.o		+= $(PURGATORY_CFLAGS)
+
+CFLAGS_REMOVE_sha256.o		+= $(PURGATORY_CFLAGS_REMOVE)
+CFLAGS_sha256.o			+= $(PURGATORY_CFLAGS)
+
+CFLAGS_REMOVE_string.o		+= $(PURGATORY_CFLAGS_REMOVE)
+CFLAGS_string.o			+= $(PURGATORY_CFLAGS)
+
+CFLAGS_REMOVE_ctype.o		+= $(PURGATORY_CFLAGS_REMOVE)
+CFLAGS_ctype.o			+= $(PURGATORY_CFLAGS)
+
+AFLAGS_REMOVE_entry.o		+= -Wa,-gdwarf-2
+AFLAGS_REMOVE_memcpy.o		+= -Wa,-gdwarf-2
+AFLAGS_REMOVE_memset.o		+= -Wa,-gdwarf-2
+
+$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
+		$(call if_changed,ld)
+
+$(obj)/purgatory.chk: $(obj)/purgatory.ro FORCE
+		$(call if_changed,ld)
+
+targets += kexec-purgatory.c
+
+quiet_cmd_bin2c = BIN2C   $@
+      cmd_bin2c = $(objtree)/scripts/bin2c kexec_purgatory < $< > $@
+
+$(obj)/kexec-purgatory.c: $(obj)/purgatory.ro $(obj)/purgatory.chk FORCE
+	$(call if_changed,bin2c)
+
+obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY)	+= kexec-purgatory.o
diff --git a/arch/riscv/purgatory/entry.S b/arch/riscv/purgatory/entry.S
new file mode 100644
index 000000000000..0194f4554130
--- /dev/null
+++ b/arch/riscv/purgatory/entry.S
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * purgatory: Runs between two kernels
+ *
+ * Copyright (C) 2022 Huawei Technologies Co, Ltd.
+ *
+ * Author: Li Zhengyu (lizhengyu3@huawei.com)
+ *
+ */
+
+.macro	size, sym:req
+	.size \sym, . - \sym
+.endm
+
+.text
+
+.globl purgatory_start
+purgatory_start:
+
+	lla	sp, .Lstack
+	mv	s0, a0	/* The hartid of the current hart */
+	mv	s1, a1	/* Phys address of the FDT image */
+
+	jal	purgatory
+
+	/* Start new image. */
+	mv	a0, s0
+	mv	a1, s1
+	ld	a2, riscv_kernel_entry
+	jr	a2
+
+size purgatory_start
+
+.align 4
+	.rept	256
+	.quad	0
+	.endr
+.Lstack:
+
+.data
+
+.globl riscv_kernel_entry
+riscv_kernel_entry:
+	.quad	0
+size riscv_kernel_entry
+
+.end
diff --git a/arch/riscv/purgatory/purgatory.c b/arch/riscv/purgatory/purgatory.c
new file mode 100644
index 000000000000..80596ab5fb62
--- /dev/null
+++ b/arch/riscv/purgatory/purgatory.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * purgatory: Runs between two kernels
+ *
+ * Copyright (C) 2022 Huawei Technologies Co, Ltd.
+ *
+ * Author: Li Zhengyu (lizhengyu3@huawei.com)
+ *
+ */
+
+#include <linux/purgatory.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <asm/string.h>
+
+u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(".kexec-purgatory");
+
+struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(".kexec-purgatory");
+
+static int verify_sha256_digest(void)
+{
+	struct kexec_sha_region *ptr, *end;
+	struct sha256_state ss;
+	u8 digest[SHA256_DIGEST_SIZE];
+
+	sha256_init(&ss);
+	end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions);
+	for (ptr = purgatory_sha_regions; ptr < end; ptr++)
+		sha256_update(&ss, (uint8_t *)(ptr->start), ptr->len);
+	sha256_final(&ss, digest);
+	if (memcmp(digest, purgatory_sha256_digest, sizeof(digest)) != 0)
+		return 1;
+	return 0;
+}
+
+/* workaround for a warning with -Wmissing-prototypes */
+void purgatory(void);
+
+void purgatory(void)
+{
+	if (verify_sha256_digest())
+		for (;;)
+			/* loop forever */
+			;
+}
-- 
cgit v1.2.3