[PATCH AUTOSEL 5.4 1/7] powerpc/selftests: Use timersub() for gettimeofday()

[PATCH AUTOSEL 5.4 1/7] powerpc/selftests: Use timersub() for gettimeofday()

[Sasha Levin]

From: ye xingchen <ye.xingchen@zte.com.cn>

[ Upstream commit c814bf958926ff45a9c1e899bd001006ab6cfbae ]

Use timersub() function to simplify the code.

Reported-by: Zeal Robot <zealci@zte.com.cn>
Signed-off-by: ye xingchen <ye.xingchen@zte.com.cn>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220816105106.82666-1-ye.xingchen@zte.com.cn
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/powerpc/benchmarks/gettimeofday.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c b/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c
index 6b415683357b..580fcac0a09f 100644
--- a/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c
+++ b/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c
@@ -12,7 +12,7 @@ static int test_gettimeofday(void)
 {
 	int i;
 
-	struct timeval tv_start, tv_end;
+	struct timeval tv_start, tv_end, tv_diff;
 
 	gettimeofday(&tv_start, NULL);
 
@@ -20,7 +20,9 @@ static int test_gettimeofday(void)
 		gettimeofday(&tv_end, NULL);
 	}
 
-	printf("time = %.6f\n", tv_end.tv_sec - tv_start.tv_sec + (tv_end.tv_usec - tv_start.tv_usec) * 1e-6);
+	timersub(&tv_start, &tv_end, &tv_diff);
+
+	printf("time = %.6f\n", tv_diff.tv_sec + (tv_diff.tv_usec) * 1e-6);
 
 	return 0;
 }
-- 
2.35.1

[PATCH AUTOSEL 5.4 2/7] powerpc/math-emu: Remove -w build flag and fix warnings

[Sasha Levin]

From: Christophe Leroy <christophe.leroy@csgroup.eu>

[ Upstream commit 7245fc5bb7a966852d5bd7779d1f5855530b461a ]

As reported by Nathan, the module_init() macro was not taken into
account because the header was missing. That means spe_mathemu_init()
was never called.

This should have been detected by gcc at build time, but due to
'-w' flag it went undetected.

Removing that flag leads to many warnings hence errors.

Fix those warnings then remove the -w flag.

Reported-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/2663961738a46073713786d4efeb53100ca156e7.1662134272.git.christophe.leroy@csgroup.eu
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/math-emu/Makefile   |  2 --
 arch/powerpc/math-emu/math.c     | 18 +++++-----
 arch/powerpc/math-emu/math_efp.c | 57 +++++++++++++++++---------------
 include/math-emu/op-common.h     |  3 ++
 4 files changed, 42 insertions(+), 38 deletions(-)

diff --git a/arch/powerpc/math-emu/Makefile b/arch/powerpc/math-emu/Makefile
index a8794032f15f..26fef2e5672e 100644
--- a/arch/powerpc/math-emu/Makefile
+++ b/arch/powerpc/math-emu/Makefile
@@ -16,5 +16,3 @@ obj-$(CONFIG_SPE)		+= math_efp.o
 
 CFLAGS_fabs.o = -fno-builtin-fabs
 CFLAGS_math.o = -fno-builtin-fabs
-
-ccflags-y = -w
diff --git a/arch/powerpc/math-emu/math.c b/arch/powerpc/math-emu/math.c
index 30b4b69c6941..d9ce80585ecd 100644
--- a/arch/powerpc/math-emu/math.c
+++ b/arch/powerpc/math-emu/math.c
@@ -24,9 +24,9 @@ FLOATFUNC(mtfsf);
 FLOATFUNC(mtfsfi);
 
 #ifdef CONFIG_MATH_EMULATION_HW_UNIMPLEMENTED
-#undef FLOATFUNC(x)
+#undef FLOATFUNC
 #define FLOATFUNC(x)	static inline int x(void *op1, void *op2, void *op3, \
-						 void *op4) { }
+						 void *op4) { return 0; }
 #endif
 
 FLOATFUNC(fadd);
@@ -396,28 +396,28 @@ do_mathemu(struct pt_regs *regs)
 
 	case XCR:
 		op0 = (void *)&regs->ccr;
-		op1 = (void *)((insn >> 23) & 0x7);
+		op1 = (void *)(long)((insn >> 23) & 0x7);
 		op2 = (void *)&current->thread.TS_FPR((insn >> 16) & 0x1f);
 		op3 = (void *)&current->thread.TS_FPR((insn >> 11) & 0x1f);
 		break;
 
 	case XCRL:
 		op0 = (void *)&regs->ccr;
-		op1 = (void *)((insn >> 23) & 0x7);
-		op2 = (void *)((insn >> 18) & 0x7);
+		op1 = (void *)(long)((insn >> 23) & 0x7);
+		op2 = (void *)(long)((insn >> 18) & 0x7);
 		break;
 
 	case XCRB:
-		op0 = (void *)((insn >> 21) & 0x1f);
+		op0 = (void *)(long)((insn >> 21) & 0x1f);
 		break;
 
 	case XCRI:
-		op0 = (void *)((insn >> 23) & 0x7);
-		op1 = (void *)((insn >> 12) & 0xf);
+		op0 = (void *)(long)((insn >> 23) & 0x7);
+		op1 = (void *)(long)((insn >> 12) & 0xf);
 		break;
 
 	case XFLB:
-		op0 = (void *)((insn >> 17) & 0xff);
+		op0 = (void *)(long)((insn >> 17) & 0xff);
 		op1 = (void *)&current->thread.TS_FPR((insn >> 11) & 0x1f);
 		break;
 
diff --git a/arch/powerpc/math-emu/math_efp.c b/arch/powerpc/math-emu/math_efp.c
index 0a05e51964c1..3b35340ffc90 100644
--- a/arch/powerpc/math-emu/math_efp.c
+++ b/arch/powerpc/math-emu/math_efp.c
@@ -218,6 +218,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 		case AB:
 		case XCR:
 			FP_UNPACK_SP(SA, va.wp + 1);
+			fallthrough;
 		case XB:
 			FP_UNPACK_SP(SB, vb.wp + 1);
 			break;
@@ -226,8 +227,8 @@ int do_spe_mathemu(struct pt_regs *regs)
 			break;
 		}
 
-		pr_debug("SA: %ld %08lx %ld (%ld)\n", SA_s, SA_f, SA_e, SA_c);
-		pr_debug("SB: %ld %08lx %ld (%ld)\n", SB_s, SB_f, SB_e, SB_c);
+		pr_debug("SA: %d %08x %d (%d)\n", SA_s, SA_f, SA_e, SA_c);
+		pr_debug("SB: %d %08x %d (%d)\n", SB_s, SB_f, SB_e, SB_c);
 
 		switch (func) {
 		case EFSABS:
@@ -278,7 +279,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 			} else {
 				SB_e += (func == EFSCTSF ? 31 : 32);
 				FP_TO_INT_ROUND_S(vc.wp[1], SB, 32,
-						(func == EFSCTSF));
+						(func == EFSCTSF) ? 1 : 0);
 			}
 			goto update_regs;
 
@@ -287,7 +288,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 			FP_CLEAR_EXCEPTIONS;
 			FP_UNPACK_DP(DB, vb.dp);
 
-			pr_debug("DB: %ld %08lx %08lx %ld (%ld)\n",
+			pr_debug("DB: %d %08x %08x %d (%d)\n",
 					DB_s, DB_f1, DB_f0, DB_e, DB_c);
 
 			FP_CONV(S, D, 1, 2, SR, DB);
@@ -301,7 +302,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 				FP_SET_EXCEPTION(FP_EX_INVALID);
 			} else {
 				FP_TO_INT_ROUND_S(vc.wp[1], SB, 32,
-						((func & 0x3) != 0));
+						((func & 0x3) != 0) ? 1 : 0);
 			}
 			goto update_regs;
 
@@ -312,7 +313,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 				FP_SET_EXCEPTION(FP_EX_INVALID);
 			} else {
 				FP_TO_INT_S(vc.wp[1], SB, 32,
-						((func & 0x3) != 0));
+						((func & 0x3) != 0) ? 1 : 0);
 			}
 			goto update_regs;
 
@@ -322,7 +323,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 		break;
 
 pack_s:
-		pr_debug("SR: %ld %08lx %ld (%ld)\n", SR_s, SR_f, SR_e, SR_c);
+		pr_debug("SR: %d %08x %d (%d)\n", SR_s, SR_f, SR_e, SR_c);
 
 		FP_PACK_SP(vc.wp + 1, SR);
 		goto update_regs;
@@ -346,6 +347,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 		case AB:
 		case XCR:
 			FP_UNPACK_DP(DA, va.dp);
+			fallthrough;
 		case XB:
 			FP_UNPACK_DP(DB, vb.dp);
 			break;
@@ -354,9 +356,9 @@ int do_spe_mathemu(struct pt_regs *regs)
 			break;
 		}
 
-		pr_debug("DA: %ld %08lx %08lx %ld (%ld)\n",
+		pr_debug("DA: %d %08x %08x %d (%d)\n",
 				DA_s, DA_f1, DA_f0, DA_e, DA_c);
-		pr_debug("DB: %ld %08lx %08lx %ld (%ld)\n",
+		pr_debug("DB: %d %08x %08x %d (%d)\n",
 				DB_s, DB_f1, DB_f0, DB_e, DB_c);
 
 		switch (func) {
@@ -408,7 +410,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 			} else {
 				DB_e += (func == EFDCTSF ? 31 : 32);
 				FP_TO_INT_ROUND_D(vc.wp[1], DB, 32,
-						(func == EFDCTSF));
+						(func == EFDCTSF) ? 1 : 0);
 			}
 			goto update_regs;
 
@@ -417,7 +419,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 			FP_CLEAR_EXCEPTIONS;
 			FP_UNPACK_SP(SB, vb.wp + 1);
 
-			pr_debug("SB: %ld %08lx %ld (%ld)\n",
+			pr_debug("SB: %d %08x %d (%d)\n",
 					SB_s, SB_f, SB_e, SB_c);
 
 			FP_CONV(D, S, 2, 1, DR, SB);
@@ -431,7 +433,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 				FP_SET_EXCEPTION(FP_EX_INVALID);
 			} else {
 				FP_TO_INT_D(vc.dp[0], DB, 64,
-						((func & 0x1) == 0));
+						((func & 0x1) == 0) ? 1 : 0);
 			}
 			goto update_regs;
 
@@ -442,7 +444,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 				FP_SET_EXCEPTION(FP_EX_INVALID);
 			} else {
 				FP_TO_INT_ROUND_D(vc.wp[1], DB, 32,
-						((func & 0x3) != 0));
+						((func & 0x3) != 0) ? 1 : 0);
 			}
 			goto update_regs;
 
@@ -453,7 +455,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 				FP_SET_EXCEPTION(FP_EX_INVALID);
 			} else {
 				FP_TO_INT_D(vc.wp[1], DB, 32,
-						((func & 0x3) != 0));
+						((func & 0x3) != 0) ? 1 : 0);
 			}
 			goto update_regs;
 
@@ -463,7 +465,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 		break;
 
 pack_d:
-		pr_debug("DR: %ld %08lx %08lx %ld (%ld)\n",
+		pr_debug("DR: %d %08x %08x %d (%d)\n",
 				DR_s, DR_f1, DR_f0, DR_e, DR_c);
 
 		FP_PACK_DP(vc.dp, DR);
@@ -492,6 +494,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 		case XCR:
 			FP_UNPACK_SP(SA0, va.wp);
 			FP_UNPACK_SP(SA1, va.wp + 1);
+			fallthrough;
 		case XB:
 			FP_UNPACK_SP(SB0, vb.wp);
 			FP_UNPACK_SP(SB1, vb.wp + 1);
@@ -502,13 +505,13 @@ int do_spe_mathemu(struct pt_regs *regs)
 			break;
 		}
 
-		pr_debug("SA0: %ld %08lx %ld (%ld)\n",
+		pr_debug("SA0: %d %08x %d (%d)\n",
 				SA0_s, SA0_f, SA0_e, SA0_c);
-		pr_debug("SA1: %ld %08lx %ld (%ld)\n",
+		pr_debug("SA1: %d %08x %d (%d)\n",
 				SA1_s, SA1_f, SA1_e, SA1_c);
-		pr_debug("SB0: %ld %08lx %ld (%ld)\n",
+		pr_debug("SB0: %d %08x %d (%d)\n",
 				SB0_s, SB0_f, SB0_e, SB0_c);
-		pr_debug("SB1: %ld %08lx %ld (%ld)\n",
+		pr_debug("SB1: %d %08x %d (%d)\n",
 				SB1_s, SB1_f, SB1_e, SB1_c);
 
 		switch (func) {
@@ -567,7 +570,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 			} else {
 				SB0_e += (func == EVFSCTSF ? 31 : 32);
 				FP_TO_INT_ROUND_S(vc.wp[0], SB0, 32,
-						(func == EVFSCTSF));
+						(func == EVFSCTSF) ? 1 : 0);
 			}
 			if (SB1_c == FP_CLS_NAN) {
 				vc.wp[1] = 0;
@@ -575,7 +578,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 			} else {
 				SB1_e += (func == EVFSCTSF ? 31 : 32);
 				FP_TO_INT_ROUND_S(vc.wp[1], SB1, 32,
-						(func == EVFSCTSF));
+						(func == EVFSCTSF) ? 1 : 0);
 			}
 			goto update_regs;
 
@@ -586,14 +589,14 @@ int do_spe_mathemu(struct pt_regs *regs)
 				FP_SET_EXCEPTION(FP_EX_INVALID);
 			} else {
 				FP_TO_INT_ROUND_S(vc.wp[0], SB0, 32,
-						((func & 0x3) != 0));
+						((func & 0x3) != 0) ? 1 : 0);
 			}
 			if (SB1_c == FP_CLS_NAN) {
 				vc.wp[1] = 0;
 				FP_SET_EXCEPTION(FP_EX_INVALID);
 			} else {
 				FP_TO_INT_ROUND_S(vc.wp[1], SB1, 32,
-						((func & 0x3) != 0));
+						((func & 0x3) != 0) ? 1 : 0);
 			}
 			goto update_regs;
 
@@ -604,14 +607,14 @@ int do_spe_mathemu(struct pt_regs *regs)
 				FP_SET_EXCEPTION(FP_EX_INVALID);
 			} else {
 				FP_TO_INT_S(vc.wp[0], SB0, 32,
-						((func & 0x3) != 0));
+						((func & 0x3) != 0) ? 1 : 0);
 			}
 			if (SB1_c == FP_CLS_NAN) {
 				vc.wp[1] = 0;
 				FP_SET_EXCEPTION(FP_EX_INVALID);
 			} else {
 				FP_TO_INT_S(vc.wp[1], SB1, 32,
-						((func & 0x3) != 0));
+						((func & 0x3) != 0) ? 1 : 0);
 			}
 			goto update_regs;
 
@@ -621,9 +624,9 @@ int do_spe_mathemu(struct pt_regs *regs)
 		break;
 
 pack_vs:
-		pr_debug("SR0: %ld %08lx %ld (%ld)\n",
+		pr_debug("SR0: %d %08x %d (%d)\n",
 				SR0_s, SR0_f, SR0_e, SR0_c);
-		pr_debug("SR1: %ld %08lx %ld (%ld)\n",
+		pr_debug("SR1: %d %08x %d (%d)\n",
 				SR1_s, SR1_f, SR1_e, SR1_c);
 
 		FP_PACK_SP(vc.wp, SR0);
diff --git a/include/math-emu/op-common.h b/include/math-emu/op-common.h
index adcc6a97db61..b4539358bb01 100644
--- a/include/math-emu/op-common.h
+++ b/include/math-emu/op-common.h
@@ -662,12 +662,14 @@ do {									\
 	if (X##_e < 0)								\
 	  {									\
 	    FP_SET_EXCEPTION(FP_EX_INEXACT);					\
+	    fallthrough;							\
 	  case FP_CLS_ZERO:							\
 	    r = 0;								\
 	  }									\
 	else if (X##_e >= rsize - (rsigned > 0 || X##_s)			\
 		 || (!rsigned && X##_s))					\
 	  {	/* overflow */							\
+	    fallthrough;							\
 	  case FP_CLS_NAN:                                                      \
 	  case FP_CLS_INF:							\
 	    if (rsigned == 2)							\
@@ -767,6 +769,7 @@ do {									\
 	if (X##_e >= rsize - (rsigned > 0 || X##_s)				\
 	    || (!rsigned && X##_s))						\
 	  {	/* overflow */							\
+	    fallthrough;							\
 	  case FP_CLS_NAN:                                                      \
 	  case FP_CLS_INF:							\
 	    if (!rsigned)							\
-- 
2.35.1

[PATCH AUTOSEL 5.4 3/7] powerpc/85xx: Fix fall-through warning for Clang

[Sasha Levin]

From: "Gustavo A. R. Silva" <gustavoars@kernel.org>

[ Upstream commit d4d944ff68cb1f896d3f3b1af0bc656949dc626a ]

Fix the following fallthrough warning:

arch/powerpc/platforms/85xx/mpc85xx_cds.c:161:3: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough]

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://github.com/KSPP/linux/issues/198
Link: https://lore.kernel.org/lkml/202209061224.KxORRGVg-lkp@intel.com/
Link: https://lore.kernel.org/r/Yxe8XTY5C9qJLd0Z@work
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/platforms/85xx/mpc85xx_cds.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
index 6b1436abe9b1..ee2e6906250c 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
@@ -158,6 +158,7 @@ static void __init mpc85xx_cds_pci_irq_fixup(struct pci_dev *dev)
 			else
 				dev->irq = 10;
 			pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq);
+			break;
 		default:
 			break;
 		}
-- 
2.35.1

[PATCH AUTOSEL 5.4 4/7] powerpc: Remove direct call to personality syscall handler

[Sasha Levin]

From: Rohan McLure <rmclure@linux.ibm.com>

[ Upstream commit 4df0221f9ded8c39aecfb1a80cef346026671cb7 ]

Syscall handlers should not be invoked internally by their symbol names,
as these symbols defined by the architecture-defined SYSCALL_DEFINE
macro. Fortunately, in the case of ppc64_personality, its call to
sys_personality can be replaced with an invocation to the
equivalent ksys_personality inline helper in <linux/syscalls.h>.

Signed-off-by: Rohan McLure <rmclure@linux.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220921065605.1051927-13-rmclure@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kernel/syscalls.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index 3bfb3888e897..8e5de71c4888 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -104,7 +104,7 @@ long ppc64_personality(unsigned long personality)
 	if (personality(current->personality) == PER_LINUX32
 	    && personality(personality) == PER_LINUX)
 		personality = (personality & ~PER_MASK) | PER_LINUX32;
-	ret = sys_personality(personality);
+	ret = ksys_personality(personality);
 	if (personality(ret) == PER_LINUX32)
 		ret = (ret & ~PER_MASK) | PER_LINUX;
 	return ret;
-- 
2.35.1

[PATCH AUTOSEL 5.4 5/7] powerpc/perf: Fix branch_filter support for multiple filters

[Sasha Levin]

From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>

[ Upstream commit b9c001276d4a756f98cc7dc4672eff5343949203 ]

For PERF_SAMPLE_BRANCH_STACK sample type, different branch_sample_type
ie branch filters are supported. The branch filters are requested via
event attribute "branch_sample_type". Multiple branch filters can be
passed in event attribute. eg:

  $ perf record -b -o- -B --branch-filter any,ind_call true

None of the Power PMUs support having multiple branch filters at
the same time. Branch filters for branch stack sampling is set via MMCRA
IFM bits [32:33]. But currently when requesting for multiple filter
types, the "perf record" command does not report any error.

eg:
  $ perf record -b -o- -B --branch-filter any,save_type true
  $ perf record -b -o- -B --branch-filter any,ind_call true

The "bhrb_filter_map" function in PMU driver code does the validity
check for supported branch filters. But this check is done for single
filter. Hence "perf record" will proceed here without reporting any
error.

Fix power_pmu_event_init() to return EOPNOTSUPP when multiple branch
filters are requested in the event attr.

After the fix:
  $ perf record --branch-filter any,ind_call -- ls
  Error:
  cycles: PMU Hardware doesn't support sampling/overflow-interrupts.
  Try 'perf stat'

Reported-by: Disha Goel <disgoel@linux.vnet.ibm.com>
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Tested-by: Disha Goel<disgoel@linux.vnet.ibm.com>
Reviewed-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Reviewed-by: Kajol Jain <kjain@linux.ibm.com>
[mpe: Tweak comment and change log wording]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220921145255.20972-1-atrajeev@linux.vnet.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/perf/core-book3s.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 6f013e418834..5433cb961fab 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1963,6 +1963,23 @@ static int power_pmu_event_init(struct perf_event *event)
 	if (has_branch_stack(event)) {
 		u64 bhrb_filter = -1;
 
+		/*
+		 * Currently no PMU supports having multiple branch filters
+		 * at the same time. Branch filters are set via MMCRA IFM[32:33]
+		 * bits for Power8 and above. Return EOPNOTSUPP when multiple
+		 * branch filters are requested in the event attr.
+		 *
+		 * When opening event via perf_event_open(), branch_sample_type
+		 * gets adjusted in perf_copy_attr(). Kernel will automatically
+		 * adjust the branch_sample_type based on the event modifier
+		 * settings to include PERF_SAMPLE_BRANCH_PLM_ALL. Hence drop
+		 * the check for PERF_SAMPLE_BRANCH_PLM_ALL.
+		 */
+		if (hweight64(event->attr.branch_sample_type & ~PERF_SAMPLE_BRANCH_PLM_ALL) > 1) {
+			local_irq_restore(irq_flags);
+			return -EOPNOTSUPP;
+		}
+
 		if (ppmu->bhrb_filter_map)
 			bhrb_filter = ppmu->bhrb_filter_map(
 					event->attr.branch_sample_type);
-- 
2.35.1

[PATCH AUTOSEL 5.4 6/7] powerpc/mm: Fix UBSAN warning reported on hugetlb

[Sasha Levin]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>

[ Upstream commit 7dd3a7b90bca2c12e2146a47d63cf69a2f5d7e89 ]

Powerpc architecture supports 16GB hugetlb pages with hash translation.
For 4K page size, this is implemented as a hugepage directory entry at
PGD level and for 64K it is implemented as a huge page pte at PUD level

With 16GB hugetlb size, offset within a page is greater than 32 bits.
Hence switch to use unsigned long type when using hugepd_shift.

In order to keep things simpler, we make sure we always use unsigned
long type when using hugepd_shift() even though all the hugetlb page
size won't require that.

The hugetlb_free_p*d_range changes are all related to nohash usage where
we can have multiple pgd entries pointing to the same hugepd entries.
Hence on book3s64 where we can have > 4GB hugetlb page size we will
always find more < next even if we compute the value of more correctly.

Hence there is no functional change in this patch except that it fixes
the below warning.

  UBSAN: shift-out-of-bounds in arch/powerpc/mm/hugetlbpage.c:499:21
  shift exponent 34 is too large for 32-bit type 'int'
  CPU: 39 PID: 1673 Comm: a.out Not tainted 6.0.0-rc2-00327-gee88a56e8517-dirty #1
  Call Trace:
    dump_stack_lvl+0x98/0xe0 (unreliable)
    ubsan_epilogue+0x18/0x70
    __ubsan_handle_shift_out_of_bounds+0x1bc/0x390
    hugetlb_free_pgd_range+0x5d8/0x600
    free_pgtables+0x114/0x290
    exit_mmap+0x150/0x550
    mmput+0xcc/0x210
    do_exit+0x420/0xdd0
    do_group_exit+0x4c/0xd0
    sys_exit_group+0x24/0x30
    system_call_exception+0x250/0x600
    system_call_common+0xec/0x250

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
[mpe: Drop generic change to be sent separately, change 1ULL to 1UL]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220908072440.258301-1-aneesh.kumar@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/mm/hugetlbpage.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 33b3461d91e8..19fc368e3f25 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -365,7 +365,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 		 * single hugepage, but all of them point to
 		 * the same kmem cache that holds the hugepte.
 		 */
-		more = addr + (1 << hugepd_shift(*(hugepd_t *)pmd));
+		more = addr + (1UL << hugepd_shift(*(hugepd_t *)pmd));
 		if (more > next)
 			next = more;
 
@@ -415,7 +415,7 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 			 * single hugepage, but all of them point to
 			 * the same kmem cache that holds the hugepte.
 			 */
-			more = addr + (1 << hugepd_shift(*(hugepd_t *)pud));
+			more = addr + (1UL << hugepd_shift(*(hugepd_t *)pud));
 			if (more > next)
 				next = more;
 
@@ -483,7 +483,7 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 			 * for a single hugepage, but all of them point to the
 			 * same kmem cache that holds the hugepte.
 			 */
-			more = addr + (1 << hugepd_shift(*(hugepd_t *)pgd));
+			more = addr + (1UL << hugepd_shift(*(hugepd_t *)pgd));
 			if (more > next)
 				next = more;
 
-- 
2.35.1

[PATCH AUTOSEL 5.4 7/7] powerpc/64: Fix msr_check_and_set/clear MSR[EE] race

[Sasha Levin]

From: Nicholas Piggin <npiggin@gmail.com>

[ Upstream commit 0fa6831811f62cfc10415d731bcf9fde2647ad81 ]

irq soft-masking means that when Linux irqs are disabled, the MSR[EE]
value can change from 1 to 0 asynchronously: if a masked interrupt of
the PACA_IRQ_MUST_HARD_MASK variety fires while irqs are disabled,
the masked handler will return with MSR[EE]=0.

This means a sequence like mtmsr(mfmsr() | MSR_FP) is racy if it can
be called with local irqs disabled, unless a hard_irq_disable has been
done.

Reported-by: Sachin Sant <sachinp@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221004051157.308999-2-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/include/asm/hw_irq.h | 24 ++++++++++++++++++++++++
 arch/powerpc/kernel/process.c     |  4 ++--
 2 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 32a18f2f49bc..3ef454f99d24 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -353,6 +353,30 @@ static inline void may_hard_irq_enable(void) { }
 
 #endif /* CONFIG_PPC64 */
 
+static inline unsigned long mtmsr_isync_irqsafe(unsigned long msr)
+{
+#ifdef CONFIG_PPC64
+	if (arch_irqs_disabled()) {
+		/*
+		 * With soft-masking, MSR[EE] can change from 1 to 0
+		 * asynchronously when irqs are disabled, and we don't want to
+		 * set MSR[EE] back to 1 here if that has happened. A race-free
+		 * way to do this is ensure EE is already 0. Another way it
+		 * could be done is with a RESTART_TABLE handler, but that's
+		 * probably overkill here.
+		 */
+		msr &= ~MSR_EE;
+		mtmsr_isync(msr);
+		irq_soft_mask_set(IRQS_ALL_DISABLED);
+		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+	} else
+#endif
+		mtmsr_isync(msr);
+
+	return msr;
+}
+
+
 #define ARCH_IRQ_INIT_FLAGS	IRQ_NOREQUEST
 
 /*
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index cf87573e6e78..e6516c6d62bb 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -131,7 +131,7 @@ unsigned long notrace msr_check_and_set(unsigned long bits)
 #endif
 
 	if (oldmsr != newmsr)
-		mtmsr_isync(newmsr);
+		newmsr = mtmsr_isync_irqsafe(newmsr);
 
 	return newmsr;
 }
@@ -151,7 +151,7 @@ void notrace __msr_check_and_clear(unsigned long bits)
 #endif
 
 	if (oldmsr != newmsr)
-		mtmsr_isync(newmsr);
+		mtmsr_isync_irqsafe(newmsr);
 }
 EXPORT_SYMBOL(__msr_check_and_clear);
 
-- 
2.35.1