Re: [PATCH 5.10] arm64/bpf: Remove 128MB limit for BPF JIT programs

[Puranjay Mohan <puranjay@kernel.org>]

[-- Attachment #1: Type: text/plain, Size: 6030 bytes --]


+CC Greg

> From: Russell King <russell.king@oracle.com>
>
> [ Upstream commit b89ddf4cca43f1269093942cf5c4e457fd45c335 ]
>
> 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
> [Replace usage of in_bpf_jit() with is_bpf_text_address()]
> Signed-off-by: Puranjay Mohan <pjy@amazon.com>
> ---
>  arch/arm64/include/asm/extable.h | 9 ---------
>  arch/arm64/include/asm/memory.h  | 5 +----
>  arch/arm64/kernel/traps.c        | 2 +-
>  arch/arm64/mm/extable.c          | 3 ++-
>  arch/arm64/mm/ptdump.c           | 2 --
>  arch/arm64/net/bpf_jit_comp.c    | 7 ++-----
>  6 files changed, 6 insertions(+), 22 deletions(-)
>
> diff --git a/arch/arm64/include/asm/extable.h b/arch/arm64/include/asm/extable.h
> index b15eb4a3e6b20..840a35ed92ec8 100644
> --- a/arch/arm64/include/asm/extable.h
> +++ b/arch/arm64/include/asm/extable.h
> @@ -22,15 +22,6 @@ struct exception_table_entry
>  
>  #define ARCH_HAS_RELATIVE_EXTABLE
>  
> -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
>  int arm64_bpf_fixup_exception(const struct exception_table_entry *ex,
>  			      struct pt_regs *regs);
> diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
> index 505bdd75b5411..eef03120c0daf 100644
> --- a/arch/arm64/include/asm/memory.h
> +++ b/arch/arm64/include/asm/memory.h
> @@ -44,11 +44,8 @@
>  #define _PAGE_OFFSET(va)	(-(UL(1) << (va)))
>  #define PAGE_OFFSET		(_PAGE_OFFSET(VA_BITS))
>  #define KIMAGE_VADDR		(MODULES_END)
> -#define BPF_JIT_REGION_START	(KASAN_SHADOW_END)
> -#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		(-VMEMMAP_SIZE - SZ_2M)
>  #define VMEMMAP_END		(VMEMMAP_START + VMEMMAP_SIZE)
> diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
> index 563d07d3904e4..e9cc15414133f 100644
> --- a/arch/arm64/kernel/traps.c
> +++ b/arch/arm64/kernel/traps.c
> @@ -913,7 +913,7 @@ static struct break_hook bug_break_hook = {
>  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 */
> diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c
> index aa0060178343a..9a8147b6878b9 100644
> --- a/arch/arm64/mm/extable.c
> +++ b/arch/arm64/mm/extable.c
> @@ -5,6 +5,7 @@
>  
>  #include <linux/extable.h>
>  #include <linux/uaccess.h>
> +#include <linux/filter.h>
>  
>  int fixup_exception(struct pt_regs *regs)
>  {
> @@ -14,7 +15,7 @@ int fixup_exception(struct pt_regs *regs)
>  	if (!fixup)
>  		return 0;
>  
> -	if (in_bpf_jit(regs))
> +	if (is_bpf_text_address(regs->pc))
>  		return arm64_bpf_fixup_exception(fixup, regs);
>  
>  	regs->pc = (unsigned long)&fixup->fixup + fixup->fixup;
> diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c
> index 807dc634bbd24..ba6d1d89f9b2a 100644
> --- a/arch/arm64/mm/ptdump.c
> +++ b/arch/arm64/mm/ptdump.c
> @@ -41,8 +41,6 @@ static struct addr_marker address_markers[] = {
>  	{ 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" },
> diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
> index 18627cbd6da4e..2a47165abbe5e 100644
> --- a/arch/arm64/net/bpf_jit_comp.c
> +++ b/arch/arm64/net/bpf_jit_comp.c
> @@ -1145,15 +1145,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
>  
>  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)
> -- 
> 2.40.1

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 255 bytes --]