summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/net/bpf_jit_32.c42
-rw-r--r--arch/arm64/crypto/crc32-arm64.c22
-rw-r--r--arch/arm64/crypto/sha1-ce-glue.c3
-rw-r--r--arch/arm64/crypto/sha2-ce-glue.c3
-rw-r--r--arch/arm64/kernel/alternative.c53
-rw-r--r--arch/arm64/kernel/perf_event.c8
-rw-r--r--arch/arm64/mm/dump.c2
-rw-r--r--arch/arm64/net/bpf_jit_comp.c2
-rw-r--r--arch/mips/include/asm/smp.h2
-rw-r--r--arch/mips/kernel/elf.c32
-rw-r--r--arch/mips/kernel/smp.c6
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c7
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_rapl.c1
-rw-r--r--arch/x86/net/bpf_jit_comp.c28
14 files changed, 126 insertions, 85 deletions
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index e1268f905026..e0e23582c8b4 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -54,6 +54,7 @@
#define SEEN_DATA (1 << (BPF_MEMWORDS + 3))
#define FLAG_NEED_X_RESET (1 << 0)
+#define FLAG_IMM_OVERFLOW (1 << 1)
struct jit_ctx {
const struct bpf_prog *skf;
@@ -293,6 +294,15 @@ static u16 imm_offset(u32 k, struct jit_ctx *ctx)
/* PC in ARM mode == address of the instruction + 8 */
imm = offset - (8 + ctx->idx * 4);
+ if (imm & ~0xfff) {
+ /*
+ * literal pool is too far, signal it into flags. we
+ * can only detect it on the second pass unfortunately.
+ */
+ ctx->flags |= FLAG_IMM_OVERFLOW;
+ return 0;
+ }
+
return imm;
}
@@ -449,10 +459,21 @@ static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx)
return;
}
#endif
- if (rm != ARM_R0)
- emit(ARM_MOV_R(ARM_R0, rm), ctx);
+
+ /*
+ * For BPF_ALU | BPF_DIV | BPF_K instructions, rm is ARM_R4
+ * (r_A) and rn is ARM_R0 (r_scratch) so load rn first into
+ * ARM_R1 to avoid accidentally overwriting ARM_R0 with rm
+ * before using it as a source for ARM_R1.
+ *
+ * For BPF_ALU | BPF_DIV | BPF_X rm is ARM_R4 (r_A) and rn is
+ * ARM_R5 (r_X) so there is no particular register overlap
+ * issues.
+ */
if (rn != ARM_R1)
emit(ARM_MOV_R(ARM_R1, rn), ctx);
+ if (rm != ARM_R0)
+ emit(ARM_MOV_R(ARM_R0, rm), ctx);
ctx->seen |= SEEN_CALL;
emit_mov_i(ARM_R3, (u32)jit_udiv, ctx);
@@ -855,6 +876,14 @@ b_epilogue:
default:
return -1;
}
+
+ if (ctx->flags & FLAG_IMM_OVERFLOW)
+ /*
+ * this instruction generated an overflow when
+ * trying to access the literal pool, so
+ * delegate this filter to the kernel interpreter.
+ */
+ return -1;
}
/* compute offsets only during the first pass */
@@ -917,7 +946,14 @@ void bpf_jit_compile(struct bpf_prog *fp)
ctx.idx = 0;
build_prologue(&ctx);
- build_body(&ctx);
+ if (build_body(&ctx) < 0) {
+#if __LINUX_ARM_ARCH__ < 7
+ if (ctx.imm_count)
+ kfree(ctx.imms);
+#endif
+ bpf_jit_binary_free(header);
+ goto out;
+ }
build_epilogue(&ctx);
flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx));
diff --git a/arch/arm64/crypto/crc32-arm64.c b/arch/arm64/crypto/crc32-arm64.c
index 9499199924ae..6a37c3c6b11d 100644
--- a/arch/arm64/crypto/crc32-arm64.c
+++ b/arch/arm64/crypto/crc32-arm64.c
@@ -147,13 +147,21 @@ static int chksum_final(struct shash_desc *desc, u8 *out)
{
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+ put_unaligned_le32(ctx->crc, out);
+ return 0;
+}
+
+static int chksumc_final(struct shash_desc *desc, u8 *out)
+{
+ struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
put_unaligned_le32(~ctx->crc, out);
return 0;
}
static int __chksum_finup(u32 crc, const u8 *data, unsigned int len, u8 *out)
{
- put_unaligned_le32(~crc32_arm64_le_hw(crc, data, len), out);
+ put_unaligned_le32(crc32_arm64_le_hw(crc, data, len), out);
return 0;
}
@@ -199,6 +207,14 @@ static int crc32_cra_init(struct crypto_tfm *tfm)
{
struct chksum_ctx *mctx = crypto_tfm_ctx(tfm);
+ mctx->key = 0;
+ return 0;
+}
+
+static int crc32c_cra_init(struct crypto_tfm *tfm)
+{
+ struct chksum_ctx *mctx = crypto_tfm_ctx(tfm);
+
mctx->key = ~0;
return 0;
}
@@ -229,7 +245,7 @@ static struct shash_alg crc32c_alg = {
.setkey = chksum_setkey,
.init = chksum_init,
.update = chksumc_update,
- .final = chksum_final,
+ .final = chksumc_final,
.finup = chksumc_finup,
.digest = chksumc_digest,
.descsize = sizeof(struct chksum_desc_ctx),
@@ -241,7 +257,7 @@ static struct shash_alg crc32c_alg = {
.cra_alignmask = 0,
.cra_ctxsize = sizeof(struct chksum_ctx),
.cra_module = THIS_MODULE,
- .cra_init = crc32_cra_init,
+ .cra_init = crc32c_cra_init,
}
};
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index 114e7cc5de8c..aefda9868627 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -74,6 +74,9 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
static int sha1_ce_final(struct shash_desc *desc, u8 *out)
{
+ struct sha1_ce_state *sctx = shash_desc_ctx(desc);
+
+ sctx->finalize = 0;
kernel_neon_begin_partial(16);
sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_ce_transform);
kernel_neon_end();
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 1340e44c048b..7cd587564a41 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -75,6 +75,9 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
static int sha256_ce_final(struct shash_desc *desc, u8 *out)
{
+ struct sha256_ce_state *sctx = shash_desc_ctx(desc);
+
+ sctx->finalize = 0;
kernel_neon_begin_partial(28);
sha256_base_do_finalize(desc, (sha256_block_fn *)sha2_ce_transform);
kernel_neon_end();
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 21033bba9390..28f8365edc4c 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -24,7 +24,6 @@
#include <asm/cacheflush.h>
#include <asm/alternative.h>
#include <asm/cpufeature.h>
-#include <asm/insn.h>
#include <linux/stop_machine.h>
extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
@@ -34,48 +33,6 @@ struct alt_region {
struct alt_instr *end;
};
-/*
- * Decode the imm field of a b/bl instruction, and return the byte
- * offset as a signed value (so it can be used when computing a new
- * branch target).
- */
-static s32 get_branch_offset(u32 insn)
-{
- s32 imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_26, insn);
-
- /* sign-extend the immediate before turning it into a byte offset */
- return (imm << 6) >> 4;
-}
-
-static u32 get_alt_insn(u8 *insnptr, u8 *altinsnptr)
-{
- u32 insn;
-
- aarch64_insn_read(altinsnptr, &insn);
-
- /* Stop the world on instructions we don't support... */
- BUG_ON(aarch64_insn_is_cbz(insn));
- BUG_ON(aarch64_insn_is_cbnz(insn));
- BUG_ON(aarch64_insn_is_bcond(insn));
- /* ... and there is probably more. */
-
- if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn)) {
- enum aarch64_insn_branch_type type;
- unsigned long target;
-
- if (aarch64_insn_is_b(insn))
- type = AARCH64_INSN_BRANCH_NOLINK;
- else
- type = AARCH64_INSN_BRANCH_LINK;
-
- target = (unsigned long)altinsnptr + get_branch_offset(insn);
- insn = aarch64_insn_gen_branch_imm((unsigned long)insnptr,
- target, type);
- }
-
- return insn;
-}
-
static int __apply_alternatives(void *alt_region)
{
struct alt_instr *alt;
@@ -83,9 +40,6 @@ static int __apply_alternatives(void *alt_region)
u8 *origptr, *replptr;
for (alt = region->begin; alt < region->end; alt++) {
- u32 insn;
- int i;
-
if (!cpus_have_cap(alt->cpufeature))
continue;
@@ -95,12 +49,7 @@ static int __apply_alternatives(void *alt_region)
origptr = (u8 *)&alt->orig_offset + alt->orig_offset;
replptr = (u8 *)&alt->alt_offset + alt->alt_offset;
-
- for (i = 0; i < alt->alt_len; i += sizeof(insn)) {
- insn = get_alt_insn(origptr + i, replptr + i);
- aarch64_insn_write(origptr + i, insn);
- }
-
+ memcpy(origptr, replptr, alt->alt_len);
flush_icache_range((uintptr_t)origptr,
(uintptr_t)(origptr + alt->alt_len));
}
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 23f25acf43a9..cce18c85d2e8 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1315,15 +1315,15 @@ static int armpmu_device_probe(struct platform_device *pdev)
if (!cpu_pmu)
return -ENODEV;
- irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
- if (!irqs)
- return -ENOMEM;
-
/* Don't bother with PPIs; they're already affine */
irq = platform_get_irq(pdev, 0);
if (irq >= 0 && irq_is_percpu(irq))
return 0;
+ irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
+ if (!irqs)
+ return -ENOMEM;
+
for (i = 0; i < pdev->num_resources; ++i) {
struct device_node *dn;
int cpu;
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 74c256744b25..f3d6221cd5bd 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -328,10 +328,12 @@ static int ptdump_init(void)
for (j = 0; j < pg_level[i].num; j++)
pg_level[i].mask |= pg_level[i].bits[j].mask;
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
address_markers[VMEMMAP_START_NR].start_address =
(unsigned long)virt_to_page(PAGE_OFFSET);
address_markers[VMEMMAP_END_NR].start_address =
(unsigned long)virt_to_page(high_memory);
+#endif
pe = debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
&ptdump_fops);
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index edba042b2325..dc6a4842683a 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -487,7 +487,7 @@ emit_cond_jmp:
return -EINVAL;
}
- imm64 = (u64)insn1.imm << 32 | imm;
+ imm64 = (u64)insn1.imm << 32 | (u32)imm;
emit_a64_mov_i64(dst, imm64, ctx);
return 1;
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index bb02fac9b4fa..2b25d1ba1ea0 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -45,7 +45,7 @@ extern int __cpu_logical_map[NR_CPUS];
#define SMP_DUMP 0x8
#define SMP_ASK_C0COUNT 0x10
-extern volatile cpumask_t cpu_callin_map;
+extern cpumask_t cpu_callin_map;
/* Mask of CPUs which are currently definitely operating coherently */
extern cpumask_t cpu_coherent_mask;
diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c
index be4899f3c393..4a4d9e067c89 100644
--- a/arch/mips/kernel/elf.c
+++ b/arch/mips/kernel/elf.c
@@ -76,14 +76,6 @@ int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf,
/* Lets see if this is an O32 ELF */
if (ehdr32->e_ident[EI_CLASS] == ELFCLASS32) {
- /* FR = 1 for N32 */
- if (ehdr32->e_flags & EF_MIPS_ABI2)
- state->overall_fp_mode = FP_FR1;
- else
- /* Set a good default FPU mode for O32 */
- state->overall_fp_mode = cpu_has_mips_r6 ?
- FP_FRE : FP_FR0;
-
if (ehdr32->e_flags & EF_MIPS_FP64) {
/*
* Set MIPS_ABI_FP_OLD_64 for EF_MIPS_FP64. We will override it
@@ -104,9 +96,6 @@ int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf,
(char *)&abiflags,
sizeof(abiflags));
} else {
- /* FR=1 is really the only option for 64-bit */
- state->overall_fp_mode = FP_FR1;
-
if (phdr64->p_type != PT_MIPS_ABIFLAGS)
return 0;
if (phdr64->p_filesz < sizeof(abiflags))
@@ -137,6 +126,7 @@ int arch_check_elf(void *_ehdr, bool has_interpreter,
struct elf32_hdr *ehdr = _ehdr;
struct mode_req prog_req, interp_req;
int fp_abi, interp_fp_abi, abi0, abi1, max_abi;
+ bool is_mips64;
if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT))
return 0;
@@ -152,10 +142,22 @@ int arch_check_elf(void *_ehdr, bool has_interpreter,
abi0 = abi1 = fp_abi;
}
- /* ABI limits. O32 = FP_64A, N32/N64 = FP_SOFT */
- max_abi = ((ehdr->e_ident[EI_CLASS] == ELFCLASS32) &&
- (!(ehdr->e_flags & EF_MIPS_ABI2))) ?
- MIPS_ABI_FP_64A : MIPS_ABI_FP_SOFT;
+ is_mips64 = (ehdr->e_ident[EI_CLASS] == ELFCLASS64) ||
+ (ehdr->e_flags & EF_MIPS_ABI2);
+
+ if (is_mips64) {
+ /* MIPS64 code always uses FR=1, thus the default is easy */
+ state->overall_fp_mode = FP_FR1;
+
+ /* Disallow access to the various FPXX & FP64 ABIs */
+ max_abi = MIPS_ABI_FP_SOFT;
+ } else {
+ /* Default to a mode capable of running code expecting FR=0 */
+ state->overall_fp_mode = cpu_has_mips_r6 ? FP_FRE : FP_FR0;
+
+ /* Allow all ABIs we know about */
+ max_abi = MIPS_ABI_FP_64A;
+ }
if ((abi0 > max_abi && abi0 != MIPS_ABI_FP_UNKNOWN) ||
(abi1 > max_abi && abi1 != MIPS_ABI_FP_UNKNOWN))
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 193ace7955fb..faa46ebd9dda 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -43,7 +43,7 @@
#include <asm/time.h>
#include <asm/setup.h>
-volatile cpumask_t cpu_callin_map; /* Bitmask of started secondaries */
+cpumask_t cpu_callin_map; /* Bitmask of started secondaries */
int __cpu_number_map[NR_CPUS]; /* Map physical to logical */
EXPORT_SYMBOL(__cpu_number_map);
@@ -218,8 +218,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
/*
* Trust is futile. We should really have timeouts ...
*/
- while (!cpumask_test_cpu(cpu, &cpu_callin_map))
+ while (!cpumask_test_cpu(cpu, &cpu_callin_map)) {
udelay(100);
+ schedule();
+ }
synchronise_count_master(cpu);
return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 960e85de13fb..3998131d1a68 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1134,7 +1134,7 @@ static __initconst const u64 slm_hw_cache_extra_regs
[ C(LL ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS,
- [ C(RESULT_MISS) ] = SLM_DMND_READ|SLM_LLC_MISS,
+ [ C(RESULT_MISS) ] = 0,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS,
@@ -1184,8 +1184,7 @@ static __initconst const u64 slm_hw_cache_event_ids
[ C(OP_READ) ] = {
/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01b7,
+ [ C(RESULT_MISS) ] = 0,
},
[ C(OP_WRITE) ] = {
/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
@@ -1217,7 +1216,7 @@ static __initconst const u64 slm_hw_cache_event_ids
[ C(ITLB) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */
- [ C(RESULT_MISS) ] = 0x0282, /* ITLB.MISSES */
+ [ C(RESULT_MISS) ] = 0x40205, /* PAGE_WALKS.I_SIDE_WALKS */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = -1,
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 999289b94025..358c54ad20d4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -722,6 +722,7 @@ static int __init rapl_pmu_init(void)
break;
case 60: /* Haswell */
case 69: /* Haswell-Celeron */
+ case 61: /* Broadwell */
rapl_cntr_mask = RAPL_IDX_HSW;
rapl_pmu_events_group.attrs = rapl_events_hsw_attr;
break;
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 987514396c1e..99f76103c6b7 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -559,6 +559,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
if (is_ereg(dst_reg))
EMIT1(0x41);
EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);
+
+ /* emit 'movzwl eax, ax' */
+ if (is_ereg(dst_reg))
+ EMIT3(0x45, 0x0F, 0xB7);
+ else
+ EMIT2(0x0F, 0xB7);
+ EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
break;
case 32:
/* emit 'bswap eax' to swap lower 4 bytes */
@@ -577,6 +584,27 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
break;
case BPF_ALU | BPF_END | BPF_FROM_LE:
+ switch (imm32) {
+ case 16:
+ /* emit 'movzwl eax, ax' to zero extend 16-bit
+ * into 64 bit
+ */
+ if (is_ereg(dst_reg))
+ EMIT3(0x45, 0x0F, 0xB7);
+ else
+ EMIT2(0x0F, 0xB7);
+ EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
+ break;
+ case 32:
+ /* emit 'mov eax, eax' to clear upper 32-bits */
+ if (is_ereg(dst_reg))
+ EMIT1(0x45);
+ EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg));
+ break;
+ case 64:
+ /* nop */
+ break;
+ }
break;
/* ST: *(u8*)(dst_reg + off) = imm */
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-27 05:04:03 +0100