Merge tag 'powerpc-5.9-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:

 - Revert our removal of PROT_SAO, at least one user expressed an
   interest in using it on Power9. Instead don't allow it to be used in
   guests unless enabled explicitly at compile time.

 - A fix for a crash introduced by a recent change to FP handling.

 - Revert a change to our idle code that left Power10 with no idle
   support.

 - One minor fix for the new scv system call path to set PPR.

 - Fix a crash in our "generic" PMU if branch stack events were enabled.

 - A fix for the IMC PMU, to correctly identify host kernel samples.

 - The ADB_PMU powermac code was found to be incompatible with
   VMAP_STACK, so make them incompatible in Kconfig until the code can
   be fixed.

 - A build fix in drivers/video/fbdev/controlfb.c, and a documentation
   fix.

Thanks to Alexey Kardashevskiy, Athira Rajeev, Christophe Leroy,
Giuseppe Sacco, Madhavan Srinivasan, Milton Miller, Nicholas Piggin,
Pratik Rajesh Sampat, Randy Dunlap, Shawn Anastasio, Vaidyanathan
Srinivasan.

* tag 'powerpc-5.9-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/32s: Disable VMAP stack which CONFIG_ADB_PMU
  Revert "powerpc/powernv/idle: Replace CPU feature check with PVR check"
  powerpc/perf: Fix reading of MSR[HV/PR] bits in trace-imc
  powerpc/perf: Fix crashes with generic_compat_pmu & BHRB
  powerpc/64s: Fix crash in load_fp_state() due to fpexc_mode
  powerpc/64s: scv entry should set PPR
  Documentation/powerpc: fix malformed table in syscall64-abi
  video: fbdev: controlfb: Fix build for COMPILE_TEST=y && PPC_PMAC=n
  selftests/powerpc: Update PROT_SAO test to skip ISA 3.1
  powerpc/64s: Disallow PROT_SAO in LPARs by default
  Revert "powerpc/64s: Remove PROT_SAO support"

Documentation/powerpc/syscall64-abi.rst

@@ -49,16 +49,18 @@ Register preservation rules
 Register preservation rules match the ELF ABI calling sequence with the
 following differences:
 
-=========== ============= ========================================
 --- For the sc instruction, differences with the ELF ABI ---
+=========== ============= ========================================
 r0          Volatile      (System call number.)
 r3          Volatile      (Parameter 1, and return value.)
 r4-r8       Volatile      (Parameters 2-6.)
 cr0         Volatile      (cr0.SO is the return error condition.)
 cr1, cr5-7  Nonvolatile
 lr          Nonvolatile
+=========== ============= ========================================
 
 --- For the scv 0 instruction, differences with the ELF ABI ---
+=========== ============= ========================================
 r0          Volatile      (System call number.)
 r3          Volatile      (Parameter 1, and return value.)
 r4-r8       Volatile      (Parameters 2-6.)

arch/powerpc/Kconfig

@@ -860,6 +860,18 @@ config PPC_SUBPAGE_PROT
 
 	  If unsure, say N here.
 
+config PPC_PROT_SAO_LPAR
+	bool "Support PROT_SAO mappings in LPARs"
+	depends on PPC_BOOK3S_64
+	help
+	  This option adds support for PROT_SAO mappings from userspace
+	  inside LPARs on supported CPUs.
+
+	  This may cause issues when performing guest migration from
+	  a CPU that supports SAO to one that does not.
+
+	  If unsure, say N here.
+
 config PPC_COPRO_BASE
 	bool
 

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -20,13 +20,9 @@
 #define _PAGE_RW		(_PAGE_READ | _PAGE_WRITE)
 #define _PAGE_RWX		(_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
 #define _PAGE_PRIVILEGED	0x00008 /* kernel access only */
-
-#define _PAGE_CACHE_CTL		0x00030 /* Bits for the folowing cache modes */
-			/*	No bits set is normal cacheable memory */
-			/*	0x00010 unused, is SAO bit on radix POWER9 */
+#define _PAGE_SAO		0x00010 /* Strong access order */
 #define _PAGE_NON_IDEMPOTENT	0x00020 /* non idempotent memory */
 #define _PAGE_TOLERANT		0x00030 /* tolerant memory, cache inhibited */
-
 #define _PAGE_DIRTY		0x00080 /* C: page changed */
 #define _PAGE_ACCESSED		0x00100 /* R: page referenced */
 /*
@@ -828,6 +824,8 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	return hash__set_pte_at(mm, addr, ptep, pte, percpu);
 }
 
+#define _PAGE_CACHE_CTL	(_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT)
+
 #define pgprot_noncached pgprot_noncached
 static inline pgprot_t pgprot_noncached(pgprot_t prot)
 {

arch/powerpc/include/asm/cputable.h

@@ -196,7 +196,7 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTR_SPURR			LONG_ASM_CONST(0x0000000001000000)
 #define CPU_FTR_DSCR			LONG_ASM_CONST(0x0000000002000000)
 #define CPU_FTR_VSX			LONG_ASM_CONST(0x0000000004000000)
-// Free					LONG_ASM_CONST(0x0000000008000000)
+#define CPU_FTR_SAO			LONG_ASM_CONST(0x0000000008000000)
 #define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0000000010000000)
 #define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0000000020000000)
 #define CPU_FTR_ASYM_SMT		LONG_ASM_CONST(0x0000000040000000)
@@ -441,7 +441,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | CPU_FTR_ASYM_SMT | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | \
 	    CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX )
@@ -450,7 +450,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
@@ -461,7 +461,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
@@ -479,7 +479,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \

arch/powerpc/include/asm/mman.h

@@ -13,20 +13,43 @@
 #include <linux/pkeys.h>
 #include <asm/cpu_has_feature.h>
 
-#ifdef CONFIG_PPC_MEM_KEYS
 static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 		unsigned long pkey)
 {
-	return pkey_to_vmflag_bits(pkey);
+#ifdef CONFIG_PPC_MEM_KEYS
+	return (((prot & PROT_SAO) ? VM_SAO : 0) | pkey_to_vmflag_bits(pkey));
+#else
+	return ((prot & PROT_SAO) ? VM_SAO : 0);
+#endif
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
 
 static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
 {
-	return __pgprot(vmflag_to_pte_pkey_bits(vm_flags));
+#ifdef CONFIG_PPC_MEM_KEYS
+	return (vm_flags & VM_SAO) ?
+		__pgprot(_PAGE_SAO | vmflag_to_pte_pkey_bits(vm_flags)) :
+		__pgprot(0 | vmflag_to_pte_pkey_bits(vm_flags));
+#else
+	return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : __pgprot(0);
+#endif
 }
 #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
-#endif
+
+static inline bool arch_validate_prot(unsigned long prot, unsigned long addr)
+{
+	if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO))
+		return false;
+	if (prot & PROT_SAO) {
+		if (!cpu_has_feature(CPU_FTR_SAO))
+			return false;
+		if (firmware_has_feature(FW_FEATURE_LPAR) &&
+		    !IS_ENABLED(CONFIG_PPC_PROT_SAO_LPAR))
+			return false;
+	}
+	return true;
+}
+#define arch_validate_prot arch_validate_prot
 
 #endif /* CONFIG_PPC64 */
 #endif	/* _ASM_POWERPC_MMAN_H */

arch/powerpc/include/asm/nohash/64/pgtable.h

@@ -82,6 +82,8 @@
  */
 #include <asm/nohash/pte-book3e.h>
 
+#define _PAGE_SAO	0
+
 #define PTE_RPN_MASK	(~((1UL << PTE_RPN_SHIFT) - 1))
 
 /*

arch/powerpc/include/uapi/asm/mman.h

@@ -11,7 +11,7 @@
 #include <asm-generic/mman-common.h>
 
 
-#define PROT_SAO	0x10		/* Unsupported since v5.9 */
+#define PROT_SAO	0x10		/* Strong Access Ordering */
 
 #define MAP_RENAME      MAP_ANONYMOUS   /* In SunOS terminology */
 #define MAP_NORESERVE   0x40            /* don't reserve swap pages */

arch/powerpc/kernel/dt_cpu_ftrs.c

@@ -653,7 +653,7 @@ static struct dt_cpu_feature_match __initdata
 	{"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL},
 	{"processor-utilization-of-resources-register", feat_enable_purr, 0},
 	{"no-execute", feat_enable, 0},
-	/* strong-access-ordering is unused */
+	{"strong-access-ordering", feat_enable, CPU_FTR_SAO},
 	{"cache-inhibited-large-page", feat_enable_large_ci, 0},
 	{"coprocessor-icswx", feat_enable, 0},
 	{"hypervisor-virtualization-interrupt", feat_enable_hvi, 0},

arch/powerpc/kernel/entry_64.S

@@ -113,6 +113,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 	ld	r11,exception_marker@toc(r2)
 	std	r11,-16(r10)		/* "regshere" marker */
 
+BEGIN_FTR_SECTION
+	HMT_MEDIUM
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
 	/*
 	 * RECONCILE_IRQ_STATE without calling trace_hardirqs_off(), which
 	 * would clobber syscall parameters. Also we always enter with IRQs

arch/powerpc/kernel/process.c

@@ -548,7 +548,7 @@ void notrace restore_math(struct pt_regs *regs)
 	 * are live for the user thread).
 	 */
 	if ((!(msr & MSR_FP)) && should_restore_fp())
-		new_msr |= MSR_FP | current->thread.fpexc_mode;
+		new_msr |= MSR_FP;
 
 	if ((!(msr & MSR_VEC)) && should_restore_altivec())
 		new_msr |= MSR_VEC;
@@ -559,11 +559,17 @@ void notrace restore_math(struct pt_regs *regs)
 	}
 
 	if (new_msr) {
+		unsigned long fpexc_mode = 0;
+
 		msr_check_and_set(new_msr);
 
-		if (new_msr & MSR_FP)
+		if (new_msr & MSR_FP) {
 			do_restore_fp();
 
+			// This also covers VSX, because VSX implies FP
+			fpexc_mode = current->thread.fpexc_mode;
+		}
+
 		if (new_msr & MSR_VEC)
 			do_restore_altivec();
 
@@ -572,7 +578,7 @@ void notrace restore_math(struct pt_regs *regs)
 
 		msr_check_and_clear(new_msr);
 
-		regs->msr |= new_msr;
+		regs->msr |= new_msr | fpexc_mode;
 	}
 }
 #endif

arch/powerpc/mm/book3s64/hash_utils.c

@@ -232,6 +232,8 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
 		rflags |= HPTE_R_I;
 	else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT)
 		rflags |= (HPTE_R_I | HPTE_R_G);
+	else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
+		rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M);
 	else
 		/*
 		 * Add memory coherence if cache inhibited is not set

arch/powerpc/perf/core-book3s.c

@@ -1557,9 +1557,16 @@ static int power_pmu_add(struct perf_event *event, int ef_flags)
 	ret = 0;
  out:
 	if (has_branch_stack(event)) {
-		power_pmu_bhrb_enable(event);
-		cpuhw->bhrb_filter = ppmu->bhrb_filter_map(
-					event->attr.branch_sample_type);
+		u64 bhrb_filter = -1;
+
+		if (ppmu->bhrb_filter_map)
+			bhrb_filter = ppmu->bhrb_filter_map(
+				event->attr.branch_sample_type);
+
+		if (bhrb_filter != -1) {
+			cpuhw->bhrb_filter = bhrb_filter;
+			power_pmu_bhrb_enable(event);
+		}
 	}
 
 	perf_pmu_enable(event->pmu);
@@ -1881,7 +1888,6 @@ static int power_pmu_event_init(struct perf_event *event)
 	int n;
 	int err;
 	struct cpu_hw_events *cpuhw;
-	u64 bhrb_filter;
 
 	if (!ppmu)
 		return -ENOENT;
@@ -1987,7 +1993,10 @@ static int power_pmu_event_init(struct perf_event *event)
 	err = power_check_constraints(cpuhw, events, cflags, n + 1);
 
 	if (has_branch_stack(event)) {
-		bhrb_filter = ppmu->bhrb_filter_map(
+		u64 bhrb_filter = -1;
+
+		if (ppmu->bhrb_filter_map)
+			bhrb_filter = ppmu->bhrb_filter_map(
 					event->attr.branch_sample_type);
 
 		if (bhrb_filter == -1) {

arch/powerpc/perf/imc-pmu.c

@@ -1289,7 +1289,7 @@ static int trace_imc_prepare_sample(struct trace_imc_data *mem,
 	header->misc = 0;
 
 	if (cpu_has_feature(CPU_FTR_ARCH_31)) {
-		switch (IMC_TRACE_RECORD_VAL_HVPR(mem->val)) {
+		switch (IMC_TRACE_RECORD_VAL_HVPR(be64_to_cpu(READ_ONCE(mem->val)))) {
 		case 0:/* when MSR HV and PR not set in the trace-record */
 			header->misc |= PERF_RECORD_MISC_GUEST_KERNEL;
 			break;
@@ -1297,7 +1297,7 @@ static int trace_imc_prepare_sample(struct trace_imc_data *mem,
 			header->misc |= PERF_RECORD_MISC_GUEST_USER;
 			break;
 		case 2: /* MSR HV is 1 and PR is 0 */
-			header->misc |= PERF_RECORD_MISC_HYPERVISOR;
+			header->misc |= PERF_RECORD_MISC_KERNEL;
 			break;
 		case 3: /* MSR HV is 1 and PR is 1 */
 			header->misc |= PERF_RECORD_MISC_USER;

arch/powerpc/platforms/Kconfig.cputype

@@ -36,7 +36,7 @@ config PPC_BOOK3S_6xx
 	select PPC_HAVE_PMU_SUPPORT
 	select PPC_HAVE_KUEP
 	select PPC_HAVE_KUAP
-	select HAVE_ARCH_VMAP_STACK
+	select HAVE_ARCH_VMAP_STACK if !ADB_PMU
 
 config PPC_BOOK3S_601
 	bool "PowerPC 601"

arch/powerpc/platforms/powernv/idle.c

@@ -1223,7 +1223,7 @@ static void __init pnv_probe_idle_states(void)
 		return;
 	}
 
-	if (pvr_version_is(PVR_POWER9))
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
 		pnv_power9_idle_init();
 
 	for (i = 0; i < nr_pnv_idle_states; i++)

drivers/video/fbdev/controlfb.c

@@ -49,6 +49,8 @@
 #include <linux/cuda.h>
 #ifdef CONFIG_PPC_PMAC
 #include <asm/prom.h>
+#endif
+#ifdef CONFIG_BOOTX_TEXT
 #include <asm/btext.h>
 #endif
 

include/linux/mm.h

@@ -324,6 +324,8 @@ extern unsigned int kobjsize(const void *objp);
 
 #if defined(CONFIG_X86)
 # define VM_PAT		VM_ARCH_1	/* PAT reserves whole VMA at once (x86) */
+#elif defined(CONFIG_PPC)
+# define VM_SAO		VM_ARCH_1	/* Strong Access Ordering (powerpc) */
 #elif defined(CONFIG_PARISC)
 # define VM_GROWSUP	VM_ARCH_1
 #elif defined(CONFIG_IA64)

include/trace/events/mmflags.h

@@ -114,6 +114,8 @@ IF_HAVE_PG_IDLE(PG_idle,		"idle"		)
 
 #if defined(CONFIG_X86)
 #define __VM_ARCH_SPECIFIC_1 {VM_PAT,     "pat"           }
+#elif defined(CONFIG_PPC)
+#define __VM_ARCH_SPECIFIC_1 {VM_SAO,     "sao"           }
 #elif defined(CONFIG_PARISC) || defined(CONFIG_IA64)
 #define __VM_ARCH_SPECIFIC_1 {VM_GROWSUP,	"growsup"	}
 #elif !defined(CONFIG_MMU)

mm/ksm.c

@@ -2453,6 +2453,10 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		if (vma_is_dax(vma))
 			return 0;
 
+#ifdef VM_SAO
+		if (*vm_flags & VM_SAO)
+			return 0;
+#endif
 #ifdef VM_SPARC_ADI
 		if (*vm_flags & VM_SPARC_ADI)
 			return 0;

tools/testing/selftests/powerpc/mm/.gitignore

@@ -2,6 +2,7 @@
 hugetlb_vs_thp_test
 subpage_prot
 tempfile
+prot_sao
 segv_errors
 wild_bctr
 large_vm_fork_separation

tools/testing/selftests/powerpc/mm/Makefile

@@ -2,7 +2,7 @@
 noarg:
 	$(MAKE) -C ../
 
-TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot segv_errors wild_bctr \
+TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr \
 		  large_vm_fork_separation bad_accesses pkey_exec_prot \
 		  pkey_siginfo stack_expansion_signal stack_expansion_ldst
 
@@ -14,6 +14,8 @@ include ../../lib.mk
 
 $(TEST_GEN_PROGS): ../harness.c ../utils.c
 
+$(OUTPUT)/prot_sao: ../utils.c
+
 $(OUTPUT)/wild_bctr: CFLAGS += -m64
 $(OUTPUT)/large_vm_fork_separation: CFLAGS += -m64
 $(OUTPUT)/bad_accesses: CFLAGS += -m64

tools/testing/selftests/powerpc/mm/prot_sao.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2016, Michael Ellerman, IBM Corp.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+
+#include <asm/cputable.h>
+
+#include "utils.h"
+
+#define SIZE (64 * 1024)
+
+int test_prot_sao(void)
+{
+	char *p;
+
+	/* SAO was introduced in 2.06 and removed in 3.1 */
+	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06) ||
+		have_hwcap2(PPC_FEATURE2_ARCH_3_1));
+
+	/*
+	 * Ensure we can ask for PROT_SAO.
+	 * We can't really verify that it does the right thing, but at least we
+	 * confirm the kernel will accept it.
+	 */
+	p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE | PROT_SAO,
+		 MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	FAIL_IF(p == MAP_FAILED);
+
+	/* Write to the mapping, to at least cause a fault */
+	memset(p, 0xaa, SIZE);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test_prot_sao, "prot-sao");
+}