RISC-V Fixes for 6.9-rc6

* A fix for TASK_SIZE on rv64/NOMMU, to reflect the lack of user/kernel
   separation.
 * A fix to avoid loading rv64/NOMMU kernel past the start of RAM.
 * A fix for RISCV_HWPROBE_EXT_ZVFHMIN on ilp32 to avoid signed integer
   overflow in the bitmask.
 * The sud_test kselftest has been fixed to properly swizzle the syscall
   number into the return register, which are not the same on RISC-V.
 * A fix for a build warning in the perf tools on rv32.
 * A fix for the CBO selftests, to avoid non-constants leaking into the
   inline asm.
 * A pair of fixes for T-Head PBMT errata probing, which has been renamed
   MAE by the vendor.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCAAxFiEEKzw3R0RoQ7JKlDp6LhMZ81+7GIkFAmYr5BMTHHBhbG1lckBk
 YWJiZWx0LmNvbQAKCRAuExnzX7sYiVx+D/90GjeSGgPT25uJnGWIETJD/yn4V1IY
 RQ0/4J5ET+/VnzcZXRrBtrTSuy7YDbIhXMIABMl9hP1vkXcF9BvPxqKys1MdgATf
 mlqRt6Ue1N1HO7HRxWSq7oTHTR5omg0MGykbmL+1yl/EBu6d45wEU23TQSWRGM27
 O1IjjcjMGh3McoxSsczkSShuHi2NWox4vbRIOdNJyVC0wszzj5a/yLU7ZcPjGwsG
 hb33tEw2S8wd59aStUXHXRYFqxe8q42wx5F5ODpp5PILwmbXWY2f8VcHwJPjUHCz
 clS/7ogdrJHtlxc0td1QPSlw0IZEf7kqIHKgKdj9HwDG2LutrZNEX3iiJVrw1F6k
 fLbbwSKcVk17kkx+WqEk+c4ePLSfsKQqb5GyZKqMVMjgpToLraquQc7dIpzIhpxO
 gj+Xs6mGDz3Vo6luOKhcjaP+dyRF3W9a6Ufc0InwQHsJwHb8rI0iSo8Kw5mZMHa1
 iok8+z5lXpOkvXlBOGwpndObFqCDOyeP0v8Qf/+GC0c9MulRv+I1i2zjki5p7B9g
 9u8iEuMvkLvGEIYQxNUk5L/PJ98MGrwsHtjucNCuJNH4i5euH0RFXtKsKaM0O6bO
 NOq/kj/7ElQ+RyB5Q58G/fLmRtexqHbSsULY92uwzzTiVS2S/tZ32uBU+rACG2G7
 mzHuKBo4jRKS9Q==
 =LONm
 -----END PGP SIGNATURE-----

Merge tag 'riscv-for-linus-6.9-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V fixes from Palmer Dabbelt:

 - A fix for TASK_SIZE on rv64/NOMMU, to reflect the lack of user/kernel
   separation

 - A fix to avoid loading rv64/NOMMU kernel past the start of RAM

 - A fix for RISCV_HWPROBE_EXT_ZVFHMIN on ilp32 to avoid signed integer
   overflow in the bitmask

 - The sud_test kselftest has been fixed to properly swizzle the syscall
   number into the return register, which are not the same on RISC-V

 - A fix for a build warning in the perf tools on rv32

 - A fix for the CBO selftests, to avoid non-constants leaking into the
   inline asm

 - A pair of fixes for T-Head PBMT errata probing, which has been
   renamed MAE by the vendor

* tag 'riscv-for-linus-6.9-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  RISC-V: selftests: cbo: Ensure asm operands match constraints, take 2
  perf riscv: Fix the warning due to the incompatible type
  riscv: T-Head: Test availability bit before enabling MAE errata
  riscv: thead: Rename T-Head PBMT to MAE
  selftests: sud_test: return correct emulated syscall value on RISC-V
  riscv: hwprobe: fix invalid sign extension for RISCV_HWPROBE_EXT_ZVFHMIN
  riscv: Fix loading 64-bit NOMMU kernels past the start of RAM
  riscv: Fix TASK_SIZE on 64-bit NOMMU

arch/riscv/Kconfig.errata

@@ -82,14 +82,14 @@ config ERRATA_THEAD
 
 	  Otherwise, please say "N" here to avoid unnecessary overhead.
 
-config ERRATA_THEAD_PBMT
-	bool "Apply T-Head memory type errata"
+config ERRATA_THEAD_MAE
+	bool "Apply T-Head's memory attribute extension (XTheadMae) errata"
 	depends on ERRATA_THEAD && 64BIT && MMU
 	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.
+	  This will apply the memory attribute extension errata to handle the
+	  non-standard PTE utilization on T-Head SoCs (XTheadMae).
 
 	  If you don't know what to do here, say "Y".
 

arch/riscv/errata/thead/errata.c

@@ -19,20 +19,26 @@
 #include <asm/patch.h>
 #include <asm/vendorid_list.h>
 
-static bool errata_probe_pbmt(unsigned int stage,
-			      unsigned long arch_id, unsigned long impid)
+#define CSR_TH_SXSTATUS		0x5c0
+#define SXSTATUS_MAEE		_AC(0x200000, UL)
+
+static bool errata_probe_mae(unsigned int stage,
+			     unsigned long arch_id, unsigned long impid)
 {
-	if (!IS_ENABLED(CONFIG_ERRATA_THEAD_PBMT))
+	if (!IS_ENABLED(CONFIG_ERRATA_THEAD_MAE))
 		return false;
 
 	if (arch_id != 0 || impid != 0)
 		return false;
 
-	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT ||
-	    stage == RISCV_ALTERNATIVES_MODULE)
-		return true;
+	if (stage != RISCV_ALTERNATIVES_EARLY_BOOT &&
+	    stage != RISCV_ALTERNATIVES_MODULE)
+		return false;
 
-	return false;
+	if (!(csr_read(CSR_TH_SXSTATUS) & SXSTATUS_MAEE))
+		return false;
+
+	return true;
 }
 
 /*
@@ -140,8 +146,8 @@ static u32 thead_errata_probe(unsigned int stage,
 {
 	u32 cpu_req_errata = 0;
 
-	if (errata_probe_pbmt(stage, archid, impid))
-		cpu_req_errata |= BIT(ERRATA_THEAD_PBMT);
+	if (errata_probe_mae(stage, archid, impid))
+		cpu_req_errata |= BIT(ERRATA_THEAD_MAE);
 
 	errata_probe_cmo(stage, archid, impid);
 

arch/riscv/include/asm/errata_list.h

@@ -23,7 +23,7 @@
 #endif
 
 #ifdef CONFIG_ERRATA_THEAD
-#define	ERRATA_THEAD_PBMT 0
+#define	ERRATA_THEAD_MAE 0
 #define	ERRATA_THEAD_PMU 1
 #define	ERRATA_THEAD_NUMBER 2
 #endif
@@ -53,20 +53,20 @@ 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_THEAD_MAE_SHIFT 59
 #define ALT_SVPBMT(_val, prot)						\
 asm(ALTERNATIVE_2("li %0, 0\t\nnop",					\
 		  "li %0, %1\t\nslli %0,%0,%3", 0,			\
 			RISCV_ISA_EXT_SVPBMT, CONFIG_RISCV_ISA_SVPBMT,	\
 		  "li %0, %2\t\nslli %0,%0,%4", THEAD_VENDOR_ID,	\
-			ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT)	\
+			ERRATA_THEAD_MAE, CONFIG_ERRATA_THEAD_MAE)	\
 		: "=r"(_val)						\
 		: "I"(prot##_SVPBMT >> ALT_SVPBMT_SHIFT),		\
-		  "I"(prot##_THEAD >> ALT_THEAD_PBMT_SHIFT),		\
+		  "I"(prot##_THEAD >> ALT_THEAD_MAE_SHIFT),		\
 		  "I"(ALT_SVPBMT_SHIFT),				\
-		  "I"(ALT_THEAD_PBMT_SHIFT))
+		  "I"(ALT_THEAD_MAE_SHIFT))
 
-#ifdef CONFIG_ERRATA_THEAD_PBMT
+#ifdef CONFIG_ERRATA_THEAD_MAE
 /*
  * IO/NOCACHE memory types are handled together with svpbmt,
  * so on T-Head chips, check if no other memory type is set,
@@ -83,11 +83,11 @@ asm volatile(ALTERNATIVE(						\
 	"slli    t3, t3, %3\n\t"					\
 	"or      %0, %0, t3\n\t"					\
 	"2:",  THEAD_VENDOR_ID,						\
-		ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT)		\
+		ERRATA_THEAD_MAE, CONFIG_ERRATA_THEAD_MAE)		\
 	: "+r"(_val)							\
-	: "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_PBMT_SHIFT),		\
-	  "I"(_PAGE_PMA_THEAD >> ALT_THEAD_PBMT_SHIFT),			\
-	  "I"(ALT_THEAD_PBMT_SHIFT)					\
+	: "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_MAE_SHIFT),		\
+	  "I"(_PAGE_PMA_THEAD >> ALT_THEAD_MAE_SHIFT),			\
+	  "I"(ALT_THEAD_MAE_SHIFT)					\
 	: "t3")
 #else
 #define ALT_THEAD_PMA(_val)

arch/riscv/include/asm/page.h

@@ -89,7 +89,7 @@ typedef struct page *pgtable_t;
 #define PTE_FMT "%08lx"
 #endif
 
-#ifdef CONFIG_64BIT
+#if defined(CONFIG_64BIT) && defined(CONFIG_MMU)
 /*
  * We override this value as its generic definition uses __pa too early in
  * the boot process (before kernel_map.va_pa_offset is set).

arch/riscv/include/asm/pgtable.h

@@ -896,7 +896,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 #define PAGE_SHARED		__pgprot(0)
 #define PAGE_KERNEL		__pgprot(0)
 #define swapper_pg_dir		NULL
-#define TASK_SIZE		0xffffffffUL
+#define TASK_SIZE		_AC(-1, UL)
 #define VMALLOC_START		_AC(0, UL)
 #define VMALLOC_END		TASK_SIZE
 

arch/riscv/include/uapi/asm/hwprobe.h

@@ -54,7 +54,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZFHMIN	(1 << 28)
 #define		RISCV_HWPROBE_EXT_ZIHINTNTL	(1 << 29)
 #define		RISCV_HWPROBE_EXT_ZVFH		(1 << 30)
-#define		RISCV_HWPROBE_EXT_ZVFHMIN	(1 << 31)
+#define		RISCV_HWPROBE_EXT_ZVFHMIN	(1ULL << 31)
 #define		RISCV_HWPROBE_EXT_ZFA		(1ULL << 32)
 #define		RISCV_HWPROBE_EXT_ZTSO		(1ULL << 33)
 #define		RISCV_HWPROBE_EXT_ZACAS		(1ULL << 34)

arch/riscv/mm/init.c

@@ -231,7 +231,7 @@ static void __init setup_bootmem(void)
 	 * In 64-bit, any use of __va/__pa before this point is wrong as we
 	 * did not know the start of DRAM before.
 	 */
-	if (IS_ENABLED(CONFIG_64BIT))
+	if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU))
 		kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base;
 
 	/*

tools/perf/arch/riscv/util/header.c

@@ -41,7 +41,7 @@ static char *_get_cpuid(void)
 	char *mimpid = NULL;
 	char *cpuid = NULL;
 	int read;
-	unsigned long line_sz;
+	size_t line_sz;
 	FILE *cpuinfo;
 
 	cpuinfo = fopen(CPUINFO, "r");

tools/testing/selftests/riscv/hwprobe/cbo.c

@@ -19,7 +19,7 @@
 #include "hwprobe.h"
 #include "../../kselftest.h"
 
-#define MK_CBO(fn) cpu_to_le32((fn) << 20 | 10 << 15 | 2 << 12 | 0 << 7 | 15)
+#define MK_CBO(fn) le32_bswap((uint32_t)(fn) << 20 | 10 << 15 | 2 << 12 | 0 << 7 | 15)
 
 static char mem[4096] __aligned(4096) = { [0 ... 4095] = 0xa5 };
 

tools/testing/selftests/riscv/hwprobe/hwprobe.h

@@ -4,6 +4,16 @@
 #include <stddef.h>
 #include <asm/hwprobe.h>
 
+#if __BYTE_ORDER == __BIG_ENDIAN
+# define le32_bswap(_x)				\
+	((((_x) & 0x000000ffU) << 24) |		\
+	 (((_x) & 0x0000ff00U) <<  8) |		\
+	 (((_x) & 0x00ff0000U) >>  8) |		\
+	 (((_x) & 0xff000000U) >> 24))
+#else
+# define le32_bswap(_x) (_x)
+#endif
+
 /*
  * Rather than relying on having a new enough libc to define this, just do it
  * ourselves.  This way we don't need to be coupled to a new-enough libc to

tools/testing/selftests/syscall_user_dispatch/sud_test.c

@@ -158,6 +158,20 @@ static void handle_sigsys(int sig, siginfo_t *info, void *ucontext)
 
 	/* In preparation for sigreturn. */
 	SYSCALL_DISPATCH_OFF(glob_sel);
+
+	/*
+	 * The tests for argument handling assume that `syscall(x) == x`. This
+	 * is a NOP on x86 because the syscall number is passed in %rax, which
+	 * happens to also be the function ABI return register.  Other
+	 * architectures may need to swizzle the arguments around.
+	 */
+#if defined(__riscv)
+/* REG_A7 is not defined in libc headers */
+# define REG_A7 (REG_A0 + 7)
+
+	((ucontext_t *)ucontext)->uc_mcontext.__gregs[REG_A0] =
+			((ucontext_t *)ucontext)->uc_mcontext.__gregs[REG_A7];
+#endif
 }
 
 TEST(dispatch_and_return)