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>

Author: mmind

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

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) { }

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

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,
 };
 

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 */

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);

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.

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
  */

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;
 

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),
 };