8 files changed, 330 insertions, 24 deletions

diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h
index 122153b16ea4..390d7c9685fd 100644
--- a/tools/include/linux/filter.h
+++ b/tools/include/linux/filter.h
@@ -168,6 +168,16 @@
                 .off   = OFF,                                   \
                 .imm   = 0 })
 
+/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */
+
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF)                       \
+        ((struct bpf_insn) {                                    \
+                .code  = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD,   \
+                .dst_reg = DST,                                 \
+                .src_reg = SRC,                                 \
+                .off   = OFF,                                   \
+                .imm   = 0 })
+
 /* Memory store, *(uint *) (dst_reg + off16) = imm32 */
 
 #define BPF_ST_MEM(SIZE, DST, OFF, IMM)                         \
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 273f21fa32b5..7aa57225cbf7 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -130,6 +130,12 @@ static struct arch architectures[] = {
                 .name = "powerpc",
                 .init = powerpc__annotate_init,
         },
+        {
+                .name = "s390",
+                .objdump =  {
+                        .comment_char = '#',
+                },
+        },
 };
 
 static void ins__delete(struct ins_operands *ops)
diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c
index 93b0aa74ca03..39c2c7d067bb 100644
--- a/tools/power/cpupower/utils/helpers/cpuid.c
+++ b/tools/power/cpupower/utils/helpers/cpuid.c
@@ -156,6 +156,7 @@ out:
                                          */
                         case 0x2C:      /* Westmere EP - Gulftown */
                                 cpu_info->caps |= CPUPOWER_CAP_HAS_TURBO_RATIO;
+                                break;
                         case 0x2A:      /* SNB */
                         case 0x2D:      /* SNB Xeon */
                         case 0x3A:      /* IVB */
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index fedca3285326..ccf2a69365cc 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -100,6 +100,8 @@ The system configuration dump (if --quiet is not used) is followed by statistics
 \fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states.  These numbers are from hardware residency counters.
 \fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
 \fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
+\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms.
+\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz.
 \fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states.  These numbers are from hardware residency counters.
 \fBPkgWatt\fP Watts consumed by the whole package.
 \fBCorWatt\fP Watts consumed by the core part of the package.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 828dccd3f01e..b11294730771 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1142,7 +1142,7 @@ delta_thread(struct thread_data *new, struct thread_data *old,
                  * it is possible for mperf's non-halted cycles + idle states
                  * to exceed TSC's all cycles: show c1 = 0% in that case.
                  */
-                if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > old->tsc)
+                if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > (old->tsc * tsc_tweak))
                         old->c1 = 0;
                 else {
                         /* normal case, derive c1 */
@@ -2485,8 +2485,10 @@ int snapshot_gfx_mhz(void)
 
         if (fp == NULL)
                 fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r");
-        else
+        else {
                 rewind(fp);
+                fflush(fp);
+        }
 
         retval = fscanf(fp, "%d", &gfx_cur_mhz);
         if (retval != 1)
@@ -3111,7 +3113,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p)
                 return 0;
 
         fprintf(outf, "cpu%d: MSR_HWP_CAPABILITIES: 0x%08llx "
-                        "(high 0x%x guar 0x%x eff 0x%x low 0x%x)\n",
+                        "(high %d guar %d eff %d low %d)\n",
                         cpu, msr,
                         (unsigned int)HWP_HIGHEST_PERF(msr),
                         (unsigned int)HWP_GUARANTEED_PERF(msr),
@@ -3122,7 +3124,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p)
                 return 0;
 
         fprintf(outf, "cpu%d: MSR_HWP_REQUEST: 0x%08llx "
-                        "(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x pkg 0x%x)\n",
+                        "(min %d max %d des %d epp 0x%x window 0x%x pkg 0x%x)\n",
                         cpu, msr,
                         (unsigned int)(((msr) >> 0) & 0xff),
                         (unsigned int)(((msr) >> 8) & 0xff),
@@ -3136,7 +3138,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p)
                         return 0;
 
                 fprintf(outf, "cpu%d: MSR_HWP_REQUEST_PKG: 0x%08llx "
-                        "(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x)\n",
+                        "(min %d max %d des %d epp 0x%x window 0x%x)\n",
                         cpu, msr,
                         (unsigned int)(((msr) >> 0) & 0xff),
                         (unsigned int)(((msr) >> 8) & 0xff),
@@ -3353,17 +3355,19 @@ void rapl_probe(unsigned int family, unsigned int model)
         case INTEL_FAM6_SKYLAKE_DESKTOP:        /* SKL */
         case INTEL_FAM6_KABYLAKE_MOBILE:        /* KBL */
         case INTEL_FAM6_KABYLAKE_DESKTOP:       /* KBL */
-                do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+                do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO;
                 BIC_PRESENT(BIC_PKG__);
                 BIC_PRESENT(BIC_RAM__);
                 if (rapl_joules) {
                         BIC_PRESENT(BIC_Pkg_J);
                         BIC_PRESENT(BIC_Cor_J);
                         BIC_PRESENT(BIC_RAM_J);
+                        BIC_PRESENT(BIC_GFX_J);
                 } else {
                         BIC_PRESENT(BIC_PkgWatt);
                         BIC_PRESENT(BIC_CorWatt);
                         BIC_PRESENT(BIC_RAMWatt);
+                        BIC_PRESENT(BIC_GFXWatt);
                 }
                 break;
         case INTEL_FAM6_HASWELL_X:      /* HSX */
@@ -3478,7 +3482,7 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model)
 int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
         unsigned long long msr;
-        unsigned int dts;
+        unsigned int dts, dts2;
         int cpu;
 
         if (!(do_dts || do_ptm))
@@ -3503,7 +3507,6 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
                 fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n",
                         cpu, msr, tcc_activation_temp - dts);
 
-#ifdef  THERM_DEBUG
                 if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &msr))
                         return 0;
 
@@ -3511,11 +3514,10 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
                 dts2 = (msr >> 8) & 0x7F;
                 fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
                         cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2);
-#endif
         }
 
 
-        if (do_dts) {
+        if (do_dts && debug) {
                 unsigned int resolution;
 
                 if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr))
@@ -3526,7 +3528,6 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
                 fprintf(outf, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n",
                         cpu, msr, tcc_activation_temp - dts, resolution);
 
-#ifdef THERM_DEBUG
                 if (get_msr(cpu, MSR_IA32_THERM_INTERRUPT, &msr))
                         return 0;
 
@@ -3534,7 +3535,6 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
                 dts2 = (msr >> 8) & 0x7F;
                 fprintf(outf, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
                         cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2);
-#endif
         }
 
         return 0;
@@ -4578,7 +4578,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-        fprintf(outf, "turbostat version 17.02.24"
+        fprintf(outf, "turbostat version 17.04.12"
                 " - Len Brown <lenb@kernel.org>\n");
 }
 
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 6a1ad58cb66f..9af09e8099c0 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -1,7 +1,14 @@
 LIBDIR := ../../../lib
 BPFDIR := $(LIBDIR)/bpf
+APIDIR := ../../../include/uapi
+GENDIR := ../../../../include/generated
+GENHDR := $(GENDIR)/autoconf.h
 
-CFLAGS += -Wall -O2 -I../../../include/uapi -I$(LIBDIR)
+ifneq ($(wildcard $(GENHDR)),)
+  GENFLAGS := -DHAVE_GENHDR
+endif
+
+CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS)
 LDLIBS += -lcap
 
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index d1555e4240c0..c848e90b6421 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -30,6 +30,14 @@
 
 #include <bpf/bpf.h>
 
+#ifdef HAVE_GENHDR
+# include "autoconf.h"
+#else
+# if defined(__i386) || defined(__x86_64) || defined(__s390x__) || defined(__aarch64__)
+#  define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1
+# endif
+#endif
+
 #include "../../../include/linux/filter.h"
 
 #ifndef ARRAY_SIZE
@@ -39,6 +47,8 @@
 #define MAX_INSNS       512
 #define MAX_FIXUPS      8
 
+#define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS      (1 << 0)
+
 struct bpf_test {
         const char *descr;
         struct bpf_insn insns[MAX_INSNS];
@@ -53,6 +63,7 @@ struct bpf_test {
                 REJECT
         } result, result_unpriv;
         enum bpf_prog_type prog_type;
+        uint8_t flags;
 };
 
 /* Note we want this to be 64 bit aligned so that the end of our array is
@@ -2432,6 +2443,30 @@ static struct bpf_test tests[] = {
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
+                "direct packet access: test15 (spill with xadd)",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 8),
+                        BPF_MOV64_IMM(BPF_REG_5, 4096),
+                        BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+                        BPF_STX_XADD(BPF_DW, BPF_REG_4, BPF_REG_5, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0),
+                        BPF_STX_MEM(BPF_W, BPF_REG_2, BPF_REG_5, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R2 invalid mem access 'inv'",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
                 "helper access to packet: test1, valid packet_ptr range",
                 .insns = {
                         BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
@@ -2934,6 +2969,7 @@ static struct bpf_test tests[] = {
                 .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .result_unpriv = REJECT,
                 .result = ACCEPT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
         {
                 "valid map access into an array with a variable",
@@ -2957,6 +2993,7 @@ static struct bpf_test tests[] = {
                 .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .result_unpriv = REJECT,
                 .result = ACCEPT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
         {
                 "valid map access into an array with a signed variable",
@@ -2984,6 +3021,7 @@ static struct bpf_test tests[] = {
                 .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .result_unpriv = REJECT,
                 .result = ACCEPT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
         {
                 "invalid map access into an array with a constant",
@@ -3025,6 +3063,7 @@ static struct bpf_test tests[] = {
                 .errstr = "R0 min value is outside of the array range",
                 .result_unpriv = REJECT,
                 .result = REJECT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
         {
                 "invalid map access into an array with a variable",
@@ -3048,6 +3087,7 @@ static struct bpf_test tests[] = {
                 .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
                 .result_unpriv = REJECT,
                 .result = REJECT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
         {
                 "invalid map access into an array with no floor check",
@@ -3074,6 +3114,7 @@ static struct bpf_test tests[] = {
                 .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
                 .result_unpriv = REJECT,
                 .result = REJECT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
         {
                 "invalid map access into an array with a invalid max check",
@@ -3100,6 +3141,7 @@ static struct bpf_test tests[] = {
                 .errstr = "invalid access to map value, value_size=48 off=44 size=8",
                 .result_unpriv = REJECT,
                 .result = REJECT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
         {
                 "invalid map access into an array with a invalid max check",
@@ -3129,6 +3171,7 @@ static struct bpf_test tests[] = {
                 .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
                 .result_unpriv = REJECT,
                 .result = REJECT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
         {
                 "multiple registers share map_lookup_elem result",
@@ -3252,6 +3295,7 @@ static struct bpf_test tests[] = {
                 .result = REJECT,
                 .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .result_unpriv = REJECT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
         {
                 "constant register |= constant should keep constant type",
@@ -3418,6 +3462,26 @@ static struct bpf_test tests[] = {
                 .prog_type = BPF_PROG_TYPE_LWT_XMIT,
         },
         {
+                "overlapping checks for direct packet access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_2, 6),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_LWT_XMIT,
+        },
+        {
                 "invalid access of tc_classid for LWT_IN",
                 .insns = {
                         BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
@@ -3961,7 +4025,208 @@ static struct bpf_test tests[] = {
                 .result_unpriv = REJECT,
         },
         {
-                "map element value (adjusted) is preserved across register spilling",
+                "map element value or null is marked on register spilling",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -152),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1, 0),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr_unpriv = "R0 leaks addr",
+                .result = ACCEPT,
+                .result_unpriv = REJECT,
+        },
+        {
+                "map element value store of cleared call register",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr_unpriv = "R1 !read_ok",
+                .errstr = "R1 !read_ok",
+                .result = REJECT,
+                .result_unpriv = REJECT,
+        },
+        {
+                "map element value with unaligned store",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 17),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_0, 2, 43),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_0, -2, 44),
+                        BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 32),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_8, 2, 33),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_8, -2, 34),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_8, 5),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 22),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_8, 4, 23),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_8, -7, 24),
+                        BPF_MOV64_REG(BPF_REG_7, BPF_REG_8),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 3),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 22),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_7, 4, 23),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_7, -4, 24),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .result = ACCEPT,
+                .result_unpriv = REJECT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "map element value with unaligned load",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JGE, BPF_REG_1, MAX_ENTRIES, 9),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 2),
+                        BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 5),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 4),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .result = ACCEPT,
+                .result_unpriv = REJECT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "map element value illegal alu op, 1",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr = "invalid mem access 'inv'",
+                .result = REJECT,
+                .result_unpriv = REJECT,
+        },
+        {
+                "map element value illegal alu op, 2",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+                        BPF_ALU32_IMM(BPF_ADD, BPF_REG_0, 0),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr = "invalid mem access 'inv'",
+                .result = REJECT,
+                .result_unpriv = REJECT,
+        },
+        {
+                "map element value illegal alu op, 3",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+                        BPF_ALU64_IMM(BPF_DIV, BPF_REG_0, 42),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr = "invalid mem access 'inv'",
+                .result = REJECT,
+                .result_unpriv = REJECT,
+        },
+        {
+                "map element value illegal alu op, 4",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+                        BPF_ENDIAN(BPF_FROM_BE, BPF_REG_0, 64),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr = "invalid mem access 'inv'",
+                .result = REJECT,
+                .result_unpriv = REJECT,
+        },
+        {
+                "map element value illegal alu op, 5",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+                        BPF_MOV64_IMM(BPF_REG_3, 4096),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+                        BPF_STX_XADD(BPF_DW, BPF_REG_2, BPF_REG_3, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr_unpriv = "R0 invalid mem access 'inv'",
+                .errstr = "R0 invalid mem access 'inv'",
+                .result = REJECT,
+                .result_unpriv = REJECT,
+        },
+        {
+                "map element value is preserved across register spilling",
                 .insns = {
                         BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
                         BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
@@ -3983,6 +4248,7 @@ static struct bpf_test tests[] = {
                 .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .result = ACCEPT,
                 .result_unpriv = REJECT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
         {
                 "helper access to variable memory: stack, bitwise AND + JMP, correct bounds",
@@ -4421,6 +4687,7 @@ static struct bpf_test tests[] = {
                 .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
                 .result = REJECT,
                 .result_unpriv = REJECT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
         {
                 "invalid range check",
@@ -4452,6 +4719,7 @@ static struct bpf_test tests[] = {
                 .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
                 .result = REJECT,
                 .result_unpriv = REJECT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         }
 };
 
@@ -4530,11 +4798,11 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 static void do_test_single(struct bpf_test *test, bool unpriv,
                            int *passes, int *errors)
 {
+        int fd_prog, expected_ret, reject_from_alignment;
         struct bpf_insn *prog = test->insns;
         int prog_len = probe_filter_length(prog);
         int prog_type = test->prog_type;
         int fd_f1 = -1, fd_f2 = -1, fd_f3 = -1;
-        int fd_prog, expected_ret;
         const char *expected_err;
 
         do_test_fixup(test, prog, &fd_f1, &fd_f2, &fd_f3);
@@ -4547,8 +4815,19 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
                        test->result_unpriv : test->result;
         expected_err = unpriv && test->errstr_unpriv ?
                        test->errstr_unpriv : test->errstr;
+
+        reject_from_alignment = fd_prog < 0 &&
+                                (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) &&
+                                strstr(bpf_vlog, "Unknown alignment.");
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+        if (reject_from_alignment) {
+                printf("FAIL\nFailed due to alignment despite having efficient unaligned access: '%s'!\n",
+                       strerror(errno));
+                goto fail_log;
+        }
+#endif
         if (expected_ret == ACCEPT) {
-                if (fd_prog < 0) {
+                if (fd_prog < 0 && !reject_from_alignment) {
                         printf("FAIL\nFailed to load prog '%s'!\n",
                                strerror(errno));
                         goto fail_log;
@@ -4558,14 +4837,15 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
                         printf("FAIL\nUnexpected success to load!\n");
                         goto fail_log;
                 }
-                if (!strstr(bpf_vlog, expected_err)) {
+                if (!strstr(bpf_vlog, expected_err) && !reject_from_alignment) {
                         printf("FAIL\nUnexpected error message!\n");
                         goto fail_log;
                 }
         }
 
         (*passes)++;
-        printf("OK\n");
+        printf("OK%s\n", reject_from_alignment ?
+               " (NOTE: reject due to unknown alignment)" : "");
 close_fds:
         close(fd_prog);
         close(fd_f1);
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 1c5d0575802e..bf13fc2297aa 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -34,34 +34,34 @@ endif
 all: $(SUB_DIRS)
 
 $(SUB_DIRS):
-        BUILD_TARGET=$$OUTPUT/$@; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $@ all
+        BUILD_TARGET=$(OUTPUT)/$@; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $@ all
 
 include ../lib.mk
 
 override define RUN_TESTS
         @for TARGET in $(SUB_DIRS); do \
-                BUILD_TARGET=$$OUTPUT/$$TARGET; \
+                BUILD_TARGET=$(OUTPUT)/$$TARGET;        \
                 $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\
         done;
 endef
 
 override define INSTALL_RULE
         @for TARGET in $(SUB_DIRS); do \
-                BUILD_TARGET=$$OUTPUT/$$TARGET; \
+                BUILD_TARGET=$(OUTPUT)/$$TARGET;        \
                 $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install;\
         done;
 endef
 
 override define EMIT_TESTS
         @for TARGET in $(SUB_DIRS); do \
-                BUILD_TARGET=$$OUTPUT/$$TARGET; \
+                BUILD_TARGET=$(OUTPUT)/$$TARGET;        \
                 $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests;\
         done;
 endef
 
 clean:
         @for TARGET in $(SUB_DIRS); do \
-                BUILD_TARGET=$$OUTPUT/$$TARGET; \
+                BUILD_TARGET=$(OUTPUT)/$$TARGET;        \
                 $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean; \
         done;
         rm -f tags