Commit
91fc957c9b1d ("arm64/bpf: don't allocate BPF JIT programs in module
memory") restricts BPF JIT program allocation to a 128MB region to ensure
BPF programs are still in branching range of each other. However this
restriction should not apply to the aarch64 JIT, since BPF_JMP | BPF_CALL
are implemented as a 64-bit move into a register and then a BLR instruction -
which has the effect of being able to call anything without proximity
limitation.
The practical reason to relax this restriction on JIT memory is that 128MB of
JIT memory can be quickly exhausted, especially where PAGE_SIZE is 64KB - one
page is needed per program. In cases where seccomp filters are applied to
multiple VMs on VM launch - such filters are classic BPF but converted to
BPF - this can severely limit the number of VMs that can be launched. In a
world where we support BPF JIT always on, turning off the JIT isn't always an
option either.
Fixes:
91fc957c9b1d ("arm64/bpf: don't allocate BPF JIT programs in module memory")
Suggested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Russell King <russell.king@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Alan Maguire <alan.maguire@oracle.com>
Link: https://lore.kernel.org/bpf/1636131046-5982-2-git-send-email-alan.maguire@oracle.com
(b)->data = (tmp).data; \
} while (0)
-static inline bool in_bpf_jit(struct pt_regs *regs)
-{
- if (!IS_ENABLED(CONFIG_BPF_JIT))
- return false;
-
- return regs->pc >= BPF_JIT_REGION_START &&
- regs->pc < BPF_JIT_REGION_END;
-}
-
#ifdef CONFIG_BPF_JIT
bool ex_handler_bpf(const struct exception_table_entry *ex,
struct pt_regs *regs);
#define _PAGE_OFFSET(va) (-(UL(1) << (va)))
#define PAGE_OFFSET (_PAGE_OFFSET(VA_BITS))
#define KIMAGE_VADDR (MODULES_END)
-#define BPF_JIT_REGION_START (_PAGE_END(VA_BITS_MIN))
-#define BPF_JIT_REGION_SIZE (SZ_128M)
-#define BPF_JIT_REGION_END (BPF_JIT_REGION_START + BPF_JIT_REGION_SIZE)
#define MODULES_END (MODULES_VADDR + MODULES_VSIZE)
-#define MODULES_VADDR (BPF_JIT_REGION_END)
+#define MODULES_VADDR (_PAGE_END(VA_BITS_MIN))
#define MODULES_VSIZE (SZ_128M)
#define VMEMMAP_START (-(UL(1) << (VA_BITS - VMEMMAP_SHIFT)))
#define VMEMMAP_END (VMEMMAP_START + VMEMMAP_SIZE)
static int reserved_fault_handler(struct pt_regs *regs, unsigned int esr)
{
pr_err("%s generated an invalid instruction at %pS!\n",
- in_bpf_jit(regs) ? "BPF JIT" : "Kernel text patching",
+ "Kernel text patching",
(void *)instruction_pointer(regs));
/* We cannot handle this */
{ 0 /* KASAN_SHADOW_START */, "Kasan shadow start" },
{ KASAN_SHADOW_END, "Kasan shadow end" },
#endif
- { BPF_JIT_REGION_START, "BPF start" },
- { BPF_JIT_REGION_END, "BPF end" },
{ MODULES_VADDR, "Modules start" },
{ MODULES_END, "Modules end" },
{ VMALLOC_START, "vmalloc() area" },
u64 bpf_jit_alloc_exec_limit(void)
{
- return BPF_JIT_REGION_SIZE;
+ return VMALLOC_END - VMALLOC_START;
}
void *bpf_jit_alloc_exec(unsigned long size)
{
- return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
- BPF_JIT_REGION_END, GFP_KERNEL,
- PAGE_KERNEL, 0, NUMA_NO_NODE,
- __builtin_return_address(0));
+ return vmalloc(size);
}
void bpf_jit_free_exec(void *addr)