summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/include/asm/word-at-a-time.h46
-rw-r--r--arch/x86/kernel/kdebugfs.c9
-rw-r--r--arch/x86/net/bpf_jit.S122
-rw-r--r--arch/x86/net/bpf_jit_comp.c41
-rw-r--r--arch/x86/xen/mmu.c4
-rw-r--r--arch/x86/xen/smp.c2
6 files changed, 166 insertions, 58 deletions
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
new file mode 100644
index 00000000000..6fe6767b712
--- /dev/null
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -0,0 +1,46 @@
+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+
+/*
+ * This is largely generic for little-endian machines, but the
+ * optimal byte mask counting is probably going to be something
+ * that is architecture-specific. If you have a reliably fast
+ * bit count instruction, that might be better than the multiply
+ * and shift, for example.
+ */
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Jan Achrenius on G+: microoptimized version of
+ * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
+ * that works for the bytemasks without having to
+ * mask them first.
+ */
+static inline long count_masked_bytes(unsigned long mask)
+{
+ return mask*0x0001020304050608ul >> 56;
+}
+
+#else /* 32-bit case */
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+ /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+ long a = (0x0ff0001+mask) >> 23;
+ /* Fix the 1 for 00 case */
+ return a & mask;
+}
+
+#endif
+
+#define REPEAT_BYTE(x) ((~0ul / 0xff) * (x))
+
+/* Return the high bit set in the first byte that is a zero */
+static inline unsigned long has_zero(unsigned long a)
+{
+ return ((a - REPEAT_BYTE(0x01)) & ~a) & REPEAT_BYTE(0x80);
+}
+
+#endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index 90fcf62854b..1d5d31ea686 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -68,16 +68,9 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf,
return count;
}
-static int setup_data_open(struct inode *inode, struct file *file)
-{
- file->private_data = inode->i_private;
-
- return 0;
-}
-
static const struct file_operations fops_setup_data = {
.read = setup_data_read,
- .open = setup_data_open,
+ .open = simple_open,
.llseek = default_llseek,
};
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 66870223f8c..877b9a1b215 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -18,17 +18,17 @@
* r9d : hlen = skb->len - skb->data_len
*/
#define SKBDATA %r8
-
-sk_load_word_ind:
- .globl sk_load_word_ind
-
- add %ebx,%esi /* offset += X */
-# test %esi,%esi /* if (offset < 0) goto bpf_error; */
- js bpf_error
+#define SKF_MAX_NEG_OFF $(-0x200000) /* SKF_LL_OFF from filter.h */
sk_load_word:
.globl sk_load_word
+ test %esi,%esi
+ js bpf_slow_path_word_neg
+
+sk_load_word_positive_offset:
+ .globl sk_load_word_positive_offset
+
mov %r9d,%eax # hlen
sub %esi,%eax # hlen - offset
cmp $3,%eax
@@ -37,16 +37,15 @@ sk_load_word:
bswap %eax /* ntohl() */
ret
-
-sk_load_half_ind:
- .globl sk_load_half_ind
-
- add %ebx,%esi /* offset += X */
- js bpf_error
-
sk_load_half:
.globl sk_load_half
+ test %esi,%esi
+ js bpf_slow_path_half_neg
+
+sk_load_half_positive_offset:
+ .globl sk_load_half_positive_offset
+
mov %r9d,%eax
sub %esi,%eax # hlen - offset
cmp $1,%eax
@@ -55,14 +54,15 @@ sk_load_half:
rol $8,%ax # ntohs()
ret
-sk_load_byte_ind:
- .globl sk_load_byte_ind
- add %ebx,%esi /* offset += X */
- js bpf_error
-
sk_load_byte:
.globl sk_load_byte
+ test %esi,%esi
+ js bpf_slow_path_byte_neg
+
+sk_load_byte_positive_offset:
+ .globl sk_load_byte_positive_offset
+
cmp %esi,%r9d /* if (offset >= hlen) goto bpf_slow_path_byte */
jle bpf_slow_path_byte
movzbl (SKBDATA,%rsi),%eax
@@ -73,25 +73,21 @@ sk_load_byte:
*
* Implements BPF_S_LDX_B_MSH : ldxb 4*([offset]&0xf)
* Must preserve A accumulator (%eax)
- * Inputs : %esi is the offset value, already known positive
+ * Inputs : %esi is the offset value
*/
-ENTRY(sk_load_byte_msh)
- CFI_STARTPROC
+sk_load_byte_msh:
+ .globl sk_load_byte_msh
+ test %esi,%esi
+ js bpf_slow_path_byte_msh_neg
+
+sk_load_byte_msh_positive_offset:
+ .globl sk_load_byte_msh_positive_offset
cmp %esi,%r9d /* if (offset >= hlen) goto bpf_slow_path_byte_msh */
jle bpf_slow_path_byte_msh
movzbl (SKBDATA,%rsi),%ebx
and $15,%bl
shl $2,%bl
ret
- CFI_ENDPROC
-ENDPROC(sk_load_byte_msh)
-
-bpf_error:
-# force a return 0 from jit handler
- xor %eax,%eax
- mov -8(%rbp),%rbx
- leaveq
- ret
/* rsi contains offset and can be scratched */
#define bpf_slow_path_common(LEN) \
@@ -138,3 +134,67 @@ bpf_slow_path_byte_msh:
shl $2,%al
xchg %eax,%ebx
ret
+
+#define sk_negative_common(SIZE) \
+ push %rdi; /* save skb */ \
+ push %r9; \
+ push SKBDATA; \
+/* rsi already has offset */ \
+ mov $SIZE,%ecx; /* size */ \
+ call bpf_internal_load_pointer_neg_helper; \
+ test %rax,%rax; \
+ pop SKBDATA; \
+ pop %r9; \
+ pop %rdi; \
+ jz bpf_error
+
+
+bpf_slow_path_word_neg:
+ cmp SKF_MAX_NEG_OFF, %esi /* test range */
+ jl bpf_error /* offset lower -> error */
+sk_load_word_negative_offset:
+ .globl sk_load_word_negative_offset
+ sk_negative_common(4)
+ mov (%rax), %eax
+ bswap %eax
+ ret
+
+bpf_slow_path_half_neg:
+ cmp SKF_MAX_NEG_OFF, %esi
+ jl bpf_error
+sk_load_half_negative_offset:
+ .globl sk_load_half_negative_offset
+ sk_negative_common(2)
+ mov (%rax),%ax
+ rol $8,%ax
+ movzwl %ax,%eax
+ ret
+
+bpf_slow_path_byte_neg:
+ cmp SKF_MAX_NEG_OFF, %esi
+ jl bpf_error
+sk_load_byte_negative_offset:
+ .globl sk_load_byte_negative_offset
+ sk_negative_common(1)
+ movzbl (%rax), %eax
+ ret
+
+bpf_slow_path_byte_msh_neg:
+ cmp SKF_MAX_NEG_OFF, %esi
+ jl bpf_error
+sk_load_byte_msh_negative_offset:
+ .globl sk_load_byte_msh_negative_offset
+ xchg %eax,%ebx /* dont lose A , X is about to be scratched */
+ sk_negative_common(1)
+ movzbl (%rax),%eax
+ and $15,%al
+ shl $2,%al
+ xchg %eax,%ebx
+ ret
+
+bpf_error:
+# force a return 0 from jit handler
+ xor %eax,%eax
+ mov -8(%rbp),%rbx
+ leaveq
+ ret
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5a5b6e4dd73..0597f95b6da 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -30,7 +30,10 @@ int bpf_jit_enable __read_mostly;
* assembly code in arch/x86/net/bpf_jit.S
*/
extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
-extern u8 sk_load_word_ind[], sk_load_half_ind[], sk_load_byte_ind[];
+extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
+extern u8 sk_load_byte_positive_offset[], sk_load_byte_msh_positive_offset[];
+extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[];
+extern u8 sk_load_byte_negative_offset[], sk_load_byte_msh_negative_offset[];
static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
{
@@ -117,6 +120,8 @@ static inline void bpf_flush_icache(void *start, void *end)
set_fs(old_fs);
}
+#define CHOOSE_LOAD_FUNC(K, func) \
+ ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
void bpf_jit_compile(struct sk_filter *fp)
{
@@ -473,44 +478,46 @@ void bpf_jit_compile(struct sk_filter *fp)
#endif
break;
case BPF_S_LD_W_ABS:
- func = sk_load_word;
+ func = CHOOSE_LOAD_FUNC(K, sk_load_word);
common_load: seen |= SEEN_DATAREF;
- if ((int)K < 0) {
- /* Abort the JIT because __load_pointer() is needed. */
- goto out;
- }
t_offset = func - (image + addrs[i]);
EMIT1_off32(0xbe, K); /* mov imm32,%esi */
EMIT1_off32(0xe8, t_offset); /* call */
break;
case BPF_S_LD_H_ABS:
- func = sk_load_half;
+ func = CHOOSE_LOAD_FUNC(K, sk_load_half);
goto common_load;
case BPF_S_LD_B_ABS:
- func = sk_load_byte;
+ func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
goto common_load;
case BPF_S_LDX_B_MSH:
- if ((int)K < 0) {
- /* Abort the JIT because __load_pointer() is needed. */
- goto out;
- }
+ func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
seen |= SEEN_DATAREF | SEEN_XREG;
- t_offset = sk_load_byte_msh - (image + addrs[i]);
+ t_offset = func - (image + addrs[i]);
EMIT1_off32(0xbe, K); /* mov imm32,%esi */
EMIT1_off32(0xe8, t_offset); /* call sk_load_byte_msh */
break;
case BPF_S_LD_W_IND:
- func = sk_load_word_ind;
+ func = sk_load_word;
common_load_ind: seen |= SEEN_DATAREF | SEEN_XREG;
t_offset = func - (image + addrs[i]);
- EMIT1_off32(0xbe, K); /* mov imm32,%esi */
+ if (K) {
+ if (is_imm8(K)) {
+ EMIT3(0x8d, 0x73, K); /* lea imm8(%rbx), %esi */
+ } else {
+ EMIT2(0x8d, 0xb3); /* lea imm32(%rbx),%esi */
+ EMIT(K, 4);
+ }
+ } else {
+ EMIT2(0x89,0xde); /* mov %ebx,%esi */
+ }
EMIT1_off32(0xe8, t_offset); /* call sk_load_xxx_ind */
break;
case BPF_S_LD_H_IND:
- func = sk_load_half_ind;
+ func = sk_load_half;
goto common_load_ind;
case BPF_S_LD_B_IND:
- func = sk_load_byte_ind;
+ func = sk_load_byte;
goto common_load_ind;
case BPF_S_JMP_JA:
t_offset = addrs[i + K] - addrs[i];
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 988828b479e..b8e279479a6 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1859,6 +1859,7 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
#endif /* CONFIG_X86_64 */
static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss;
+static unsigned char fake_ioapic_mapping[PAGE_SIZE] __page_aligned_bss;
static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
{
@@ -1899,7 +1900,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
* We just don't map the IO APIC - all access is via
* hypercalls. Keep the address in the pte for reference.
*/
- pte = pfn_pte(PFN_DOWN(__pa(dummy_mapping)), PAGE_KERNEL);
+ pte = pfn_pte(PFN_DOWN(__pa(fake_ioapic_mapping)), PAGE_KERNEL);
break;
#endif
@@ -2064,6 +2065,7 @@ void __init xen_init_mmu_ops(void)
pv_mmu_ops = xen_mmu_ops;
memset(dummy_mapping, 0xff, PAGE_SIZE);
+ memset(fake_ioapic_mapping, 0xfd, PAGE_SIZE);
}
/* Protected by xen_reservation_lock. */
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 02900e8ce26..5fac6919b95 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -59,7 +59,7 @@ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
static void __cpuinit cpu_bringup(void)
{
- int cpu = smp_processor_id();
+ int cpu;
cpu_init();
touch_softlockup_watchdog();
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-04-11 15:55:18 +0000