Message-ID: <alpine.LFD.2.02.1208112220400.5231@xanadu.home>
Date:	Sat, 11 Aug 2012 22:22:12 -0400 (EDT)
From:	Nicolas Pitre <nicolas.pitre@...aro.org>
To:	Cyril Chemparathy <cyril@...com>
cc:	linux-kernel@...r.kernel.org, linux-arm-kernel@...ts.infradead.org,
	arnd@...db.de, catalin.marinas@....com, grant.likely@...retlab.ca,
	linux@....linux.org.uk, will.deacon@....com
Subject: Re: [PATCH v2 01/22] ARM: add mechanism for late code patching

On Fri, 10 Aug 2012, Cyril Chemparathy wrote:

> The original phys_to_virt/virt_to_phys patching implementation relied on early
> patching prior to MMU initialization.  On PAE systems running out of >4G
> address space, this would have entailed an additional round of patching after
> switching over to the high address space.
> 
> The approach implemented here conceptually extends the original PHYS_OFFSET
> patching implementation with the introduction of "early" patch stubs.  Early
> patch code is required to be functional out of the box, even before the patch
> is applied.  This is implemented by inserting functional (but inefficient)
> load code into the .runtime.patch.code init section.  Having functional code
> out of the box then allows us to defer the init time patch application until
> later in the init sequence.
> 
> In addition to fitting better with our need for physical address-space
> switch-over, this implementation should be somewhat more extensible by virtue
> of its more readable (and hackable) C implementation.  This should prove
> useful for other similar init time specialization needs, especially in light
> of our multi-platform kernel initiative.
> 
> This code has been boot tested in both ARM and Thumb-2 modes on an ARMv7
> (Cortex-A8) device.
> 
> Note: the obtuse use of stringified symbols in patch_stub() and
> early_patch_stub() is intentional.  Theoretically this should have been
> accomplished with formal operands passed into the asm block, but this requires
> the use of the 'c' modifier for instantiating the long (e.g. .long %c0).
> However, the 'c' modifier has been found to ICE certain versions of GCC, and
> therefore we resort to stringified symbols here.
> 
> Signed-off-by: Cyril Chemparathy <cyril@...com>

Reviewed-by: Nicolas Pitre <nico@...aro.org>


> ---
>  arch/arm/Kconfig                     |    3 +
>  arch/arm/include/asm/module.h        |    7 ++
>  arch/arm/include/asm/runtime-patch.h |  175 +++++++++++++++++++++++++++++++
>  arch/arm/kernel/Makefile             |    1 +
>  arch/arm/kernel/module.c             |    4 +
>  arch/arm/kernel/runtime-patch.c      |  189 ++++++++++++++++++++++++++++++++++
>  arch/arm/kernel/setup.c              |    3 +
>  arch/arm/kernel/vmlinux.lds.S        |   10 ++
>  8 files changed, 392 insertions(+)
>  create mode 100644 arch/arm/include/asm/runtime-patch.h
>  create mode 100644 arch/arm/kernel/runtime-patch.c
> 
> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
> index e91c7cd..d0a04ad 100644
> --- a/arch/arm/Kconfig
> +++ b/arch/arm/Kconfig
> @@ -61,6 +61,9 @@ config ARM
>  config ARM_HAS_SG_CHAIN
>  	bool
>  
> +config ARM_RUNTIME_PATCH
> +	bool
> +
>  config NEED_SG_DMA_LENGTH
>  	bool
>  
> diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h
> index 6c6809f..2090486 100644
> --- a/arch/arm/include/asm/module.h
> +++ b/arch/arm/include/asm/module.h
> @@ -43,9 +43,16 @@ struct mod_arch_specific {
>  #define MODULE_ARCH_VERMAGIC_ARMTHUMB ""
>  #endif
>  
> +#ifdef CONFIG_ARM_RUNTIME_PATCH
> +#define MODULE_ARCH_VERMAGIC_RT_PATCH "rt-patch "
> +#else
> +#define MODULE_ARCH_VERMAGIC_RT_PATCH ""
> +#endif
> +
>  #define MODULE_ARCH_VERMAGIC \
>  	MODULE_ARCH_VERMAGIC_ARMVSN \
>  	MODULE_ARCH_VERMAGIC_ARMTHUMB \
> +	MODULE_ARCH_VERMAGIC_RT_PATCH \
>  	MODULE_ARCH_VERMAGIC_P2V
>  
>  #endif /* _ASM_ARM_MODULE_H */
> diff --git a/arch/arm/include/asm/runtime-patch.h b/arch/arm/include/asm/runtime-patch.h
> new file mode 100644
> index 0000000..6c6e8a2
> --- /dev/null
> +++ b/arch/arm/include/asm/runtime-patch.h
> @@ -0,0 +1,175 @@
> +/*
> + * arch/arm/include/asm/runtime-patch.h
> + * Note: this file should not be included by non-asm/.h files
> + *
> + * Copyright 2012 Texas Instruments, Inc.
> + *
> + * This program is free software; you can redistribute it and/or modify it
> + * under the terms and conditions of the GNU General Public License,
> + * version 2, as published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope it will be useful, but WITHOUT
> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
> + * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
> + * more details.
> + *
> + * You should have received a copy of the GNU General Public License along with
> + * this program.  If not, see <http://www.gnu.org/licenses/>.
> + */
> +#ifndef __ASM_ARM_RUNTIME_PATCH_H
> +#define __ASM_ARM_RUNTIME_PATCH_H
> +
> +#include <linux/stringify.h>
> +
> +#ifndef __ASSEMBLY__
> +
> +#ifdef CONFIG_ARM_RUNTIME_PATCH
> +
> +struct patch_info {
> +	void	*insn;
> +	u16	 type;
> +	u8	 insn_size;
> +	u8	 data_size;
> +	u32	 data[0];
> +};
> +
> +#define patch_next(p)		((void *)(p) + sizeof(*(p)) + (p)->data_size)
> +
> +#define PATCH_TYPE_MASK		0x00ff
> +#define PATCH_IMM8		0x0001
> +
> +#define PATCH_EARLY		0x8000
> +
> +#define patch_stub(type, code, patch_data, ...)				\
> +	__asm__("@ patch stub\n"					\
> +		"1:\n"							\
> +		code							\
> +		"2:\n"							\
> +		"	.pushsection .runtime.patch.table, \"a\"\n"	\
> +		"3:\n"							\
> +		"	.word 1b\n"					\
> +		"	.hword (" __stringify(type) ")\n"		\
> +		"	.byte (2b-1b)\n"				\
> +		"	.byte (5f-4f)\n"				\
> +		"4:\n"							\
> +		patch_data						\
> +		"	.align\n"					\
> +		"5:\n"							\
> +		"	.popsection\n"					\
> +		__VA_ARGS__)
> +
> +#define early_patch_stub(type, code, patch_data, ...)			\
> +	__asm__("@ patch stub\n"					\
> +		"1:\n"							\
> +		"	b	6f\n"					\
> +		"2:\n"							\
> +		"	.pushsection .runtime.patch.table, \"a\"\n"	\
> +		"3:\n"							\
> +		"	.word 1b\n"					\
> +		"	.hword (" __stringify(type | PATCH_EARLY) ")\n"	\
> +		"	.byte (2b-1b)\n"				\
> +		"	.byte (5f-4f)\n"				\
> +		"4:\n"							\
> +		patch_data						\
> +		"	.align\n"					\
> +		"5:\n"							\
> +		"	.popsection\n"					\
> +		"	.pushsection .runtime.patch.code, \"ax\"\n"	\
> +		"6:\n"							\
> +		code							\
> +		"	b 2b\n"						\
> +		"	.popsection\n"					\
> +		__VA_ARGS__)
> +
> +/* constant used to force encoding */
> +#define __IMM8		(0x81 << 24)
> +
> +/*
> + * patch_imm8() - init-time specialized binary operation (imm8 operand)
> + *		  This effectively does: to = from "insn" sym,
> + *		  where the value of sym is fixed at init-time, and is patched
> + *		  in as an immediate operand.  This value must be
> + *		  representible as an 8-bit quantity with an optional
> + *		  rotation.
> + *
> + *		  The stub code produced by this variant is non-functional
> + *		  prior to patching.  Use early_patch_imm8() if you need the
> + *		  code to be functional early on in the init sequence.
> + */
> +#define patch_imm8(insn, to, from, sym, offset)				\
> +	patch_stub(PATCH_IMM8,						\
> +		   /* code */						\
> +		   insn " %0, %1, %2\n",				\
> +		   /* patch_data */					\
> +		   ".long " __stringify(sym + offset) "\n"		\
> +		   insn " %0, %1, %2\n",				\
> +		   : "=r" (to)						\
> +		   : "r" (from), "I" (__IMM8), "m" (sym)		\
> +		   : "cc")
> +
> +/*
> + * patch_imm8_mov() - same as patch_imm8(), but for mov/mvn instructions
> + */
> +#define patch_imm8_mov(insn, to, sym, offset)				\
> +	patch_stub(PATCH_IMM8,						\
> +		   /* code */						\
> +		   insn " %0, %1\n",					\
> +		   /* patch_data */					\
> +		   ".long " __stringify(sym + offset) "\n"		\
> +		   insn " %0, %1\n",					\
> +		   : "=r" (to)						\
> +		   : "I" (__IMM8), "m" (sym)				\
> +		   : "cc")
> +
> +/*
> + * early_patch_imm8() - early functional variant of patch_imm8() above.  The
> + *			same restrictions on the constant apply here.  This
> + *			version emits workable (albeit inefficient) code at
> + *			compile-time, and therefore functions even prior to
> + *			patch application.
> + */
> +#define early_patch_imm8(insn, to, from, sym, offset)			\
> +	early_patch_stub(PATCH_IMM8,					\
> +			 /* code */					\
> +			 "ldr	%0, =" __stringify(sym + offset) "\n"	\
> +			 "ldr	%0, [%0]\n"				\
> +			 insn " %0, %1, %0\n",				\
> +			 /* patch_data */				\
> +			 ".long " __stringify(sym + offset) "\n"	\
> +			 insn " %0, %1, %2\n",				\
> +			 : "=&r" (to)					\
> +			 : "r" (from), "I" (__IMM8), "m" (sym)		\
> +			 : "cc")
> +
> +#define early_patch_imm8_mov(insn, to, sym, offset)			\
> +	early_patch_stub(PATCH_IMM8,					\
> +			 /* code */					\
> +			 "ldr	%0, =" __stringify(sym + offset) "\n"	\
> +			 "ldr	%0, [%0]\n"				\
> +			 insn " %0, %0\n",				\
> +			 /* patch_data */				\
> +			 ".long " __stringify(sym + offset) "\n"	\
> +			 insn " %0, %1\n",				\
> +			 : "=&r" (to)					\
> +			 : "I" (__IMM8), "m" (sym)			\
> +			 : "cc")
> +
> +int runtime_patch(const void *table, unsigned size);
> +void runtime_patch_kernel(void);
> +
> +#else
> +
> +static inline int runtime_patch(const void *table, unsigned size)
> +{
> +	return 0;
> +}
> +
> +static inline void runtime_patch_kernel(void)
> +{
> +}
> +
> +#endif /* CONFIG_ARM_RUNTIME_PATCH */
> +
> +#endif /* __ASSEMBLY__ */
> +
> +#endif /* __ASM_ARM_RUNTIME_PATCH_H */
> diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
> index 7ad2d5c..12cc1e7 100644
> --- a/arch/arm/kernel/Makefile
> +++ b/arch/arm/kernel/Makefile
> @@ -81,5 +81,6 @@ endif
>  head-y			:= head$(MMUEXT).o
>  obj-$(CONFIG_DEBUG_LL)	+= debug.o
>  obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
> +obj-$(CONFIG_ARM_RUNTIME_PATCH)	+= runtime-patch.o
>  
>  extra-y := $(head-y) vmlinux.lds
> diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
> index 1e9be5d..dcebf80 100644
> --- a/arch/arm/kernel/module.c
> +++ b/arch/arm/kernel/module.c
> @@ -24,6 +24,7 @@
>  #include <asm/sections.h>
>  #include <asm/smp_plat.h>
>  #include <asm/unwind.h>
> +#include <asm/runtime-patch.h>
>  
>  #ifdef CONFIG_XIP_KERNEL
>  /*
> @@ -321,6 +322,9 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
>  	if (s)
>  		fixup_pv_table((void *)s->sh_addr, s->sh_size);
>  #endif
> +	s = find_mod_section(hdr, sechdrs, ".runtime.patch.table");
> +	if (s)
> +		runtime_patch((void *)s->sh_addr, s->sh_size);
>  	s = find_mod_section(hdr, sechdrs, ".alt.smp.init");
>  	if (s && !is_smp())
>  #ifdef CONFIG_SMP_ON_UP
> diff --git a/arch/arm/kernel/runtime-patch.c b/arch/arm/kernel/runtime-patch.c
> new file mode 100644
> index 0000000..fd37a2b
> --- /dev/null
> +++ b/arch/arm/kernel/runtime-patch.c
> @@ -0,0 +1,189 @@
> +/*
> + * arch/arm/kernel/runtime-patch.c
> + *
> + * Copyright 2012 Texas Instruments, Inc.
> + *
> + * This program is free software; you can redistribute it and/or modify it
> + * under the terms and conditions of the GNU General Public License,
> + * version 2, as published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope it will be useful, but WITHOUT
> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
> + * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
> + * more details.
> + *
> + * You should have received a copy of the GNU General Public License along with
> + * this program.  If not, see <http://www.gnu.org/licenses/>.
> + */
> +#include <linux/kernel.h>
> +#include <linux/sched.h>
> +
> +#include <asm/opcodes.h>
> +#include <asm/cacheflush.h>
> +#include <asm/runtime-patch.h>
> +
> +static inline void flush_icache_insn(void *insn_ptr, int bytes)
> +{
> +	unsigned long insn_addr = (unsigned long)insn_ptr;
> +	flush_icache_range(insn_addr, insn_addr + bytes - 1);
> +}
> +
> +#ifdef CONFIG_THUMB2_KERNEL
> +
> +static int do_patch_imm8(u32 insn, u32 imm, u32 *ninsn)
> +{
> +	u32 op, rot, val;
> +	const u32 supported_ops = (BIT(0)  | /* and */
> +				   BIT(1)  | /* bic */
> +				   BIT(2)  | /* orr/mov */
> +				   BIT(3)  | /* orn/mvn */
> +				   BIT(4)  | /* eor */
> +				   BIT(8)  | /* add */
> +				   BIT(10) | /* adc */
> +				   BIT(11) | /* sbc */
> +				   BIT(12) | /* sub */
> +				   BIT(13)); /* rsb */
> +
> +	insn = __mem_to_opcode_thumb32(insn);
> +
> +	if (!__opcode_is_thumb32(insn)) {
> +		pr_err("patch: invalid thumb2 insn %08x\n", insn);
> +		return -EINVAL;
> +	}
> +
> +	/* allow only data processing (immediate)
> +	 * 1111 0x0x xxx0 xxxx 0xxx xxxx xxxx xxxx */
> +	if ((insn & 0xfa008000) != 0xf0000000) {
> +		pr_err("patch: unknown insn %08x\n", insn);
> +		return -EINVAL;
> +	}
> +
> +	/* extract op code */
> +	op = (insn >> 21) & 0xf;
> +
> +	/* disallow unsupported opcodes */
> +	if ((supported_ops & BIT(op)) == 0) {
> +		pr_err("patch: unsupported opcode %x\n", op);
> +		return -EINVAL;
> +	}
> +
> +	if (imm <= 0xff) {
> +		rot = 0;
> +		val = imm;
> +	} else {
> +		rot = 32 - fls(imm); /* clz */
> +		if (imm & ~(0xff000000 >> rot)) {
> +			pr_err("patch: constant overflow %08x\n", imm);
> +			return -EINVAL;
> +		}
> +		val  = (imm >> (24 - rot)) & 0x7f;
> +		rot += 8; /* encoded i:imm3:a */
> +
> +		/* pack least-sig rot bit into most-sig val bit */
> +		val |= (rot & 1) << 7;
> +		rot >>= 1;
> +	}
> +
> +	*ninsn  = insn & ~(BIT(26) | 0x7 << 12 | 0xff);
> +	*ninsn |= (rot >> 3) << 26;	/* field "i" */
> +	*ninsn |= (rot & 0x7) << 12;	/* field "imm3" */
> +	*ninsn |= val;
> +	*ninsn  = __opcode_to_mem_thumb32(*ninsn);
> +
> +	return 0;
> +}
> +
> +#else
> +
> +static int do_patch_imm8(u32 insn, u32 imm, u32 *ninsn)
> +{
> +	u32 rot, val, op;
> +
> +	insn = __mem_to_opcode_arm(insn);
> +
> +	/* disallow special unconditional instructions
> +	 * 1111 xxxx xxxx xxxx xxxx xxxx xxxx xxxx */
> +	if ((insn >> 24) == 0xf) {
> +		pr_err("patch: unconditional insn %08x\n", insn);
> +		return -EINVAL;
> +	}
> +
> +	/* allow only data processing (immediate)
> +	 * xxxx 001x xxxx xxxx xxxx xxxx xxxx xxxx */
> +	if (((insn >> 25) & 0x3) != 1) {
> +		pr_err("patch: unknown insn %08x\n", insn);
> +		return -EINVAL;
> +	}
> +
> +	/* extract op code */
> +	op = (insn >> 20) & 0x1f;
> +
> +	/* disallow unsupported 10xxx op codes */
> +	if (((op >> 3) & 0x3) == 2) {
> +		pr_err("patch: unsupported opcode %08x\n", insn);
> +		return -EINVAL;
> +	}
> +
> +	rot = imm ? __ffs(imm) / 2 : 0;
> +	val = imm >> (rot * 2);
> +	rot = (-rot) & 0xf;
> +
> +	/* does this fit in 8-bit? */
> +	if (val > 0xff) {
> +		pr_err("patch: constant overflow %08x\n", imm);
> +		return -EINVAL;
> +	}
> +
> +	/* patch in new immediate and rotation */
> +	*ninsn = (insn & ~0xfff) | (rot << 8) | val;
> +	*ninsn = __opcode_to_mem_arm(*ninsn);
> +
> +	return 0;
> +}
> +
> +#endif	/* CONFIG_THUMB2_KERNEL */
> +
> +static int apply_patch_imm8(const struct patch_info *p)
> +{
> +	u32 *insn_ptr = p->insn;
> +	int ret;
> +
> +	if (p->insn_size != sizeof(u32) || p->data_size != 2 * sizeof(u32)) {
> +		pr_err("patch: bad patch, insn size %d, data size %d\n",
> +		       p->insn_size, p->data_size);
> +		return -EINVAL;
> +	}
> +
> +	ret = do_patch_imm8(p->data[1], *(u32 *)p->data[0], insn_ptr);
> +	if (ret < 0)
> +		return ret;
> +
> +	flush_icache_insn(insn_ptr, sizeof(u32));
> +
> +	return 0;
> +}
> +
> +int runtime_patch(const void *table, unsigned size)
> +{
> +	const struct patch_info *p = table, *end = (table + size);
> +
> +	for (p = table; p < end; p = patch_next(p)) {
> +		int type = p->type & PATCH_TYPE_MASK;
> +		int ret = -EINVAL;
> +
> +		if (type == PATCH_IMM8)
> +			ret = apply_patch_imm8(p);
> +		if (ret < 0)
> +			return ret;
> +	}
> +	return 0;
> +}
> +
> +void __init runtime_patch_kernel(void)
> +{
> +	extern unsigned __runtime_patch_table_begin, __runtime_patch_table_end;
> +	const void *start = &__runtime_patch_table_begin;
> +	const void *end   = &__runtime_patch_table_end;
> +
> +	BUG_ON(runtime_patch(start, end - start));
> +}
> diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
> index a81dcec..669bbf0 100644
> --- a/arch/arm/kernel/setup.c
> +++ b/arch/arm/kernel/setup.c
> @@ -55,6 +55,7 @@
>  #include <asm/traps.h>
>  #include <asm/unwind.h>
>  #include <asm/memblock.h>
> +#include <asm/runtime-patch.h>
>  
>  #if defined(CONFIG_DEPRECATED_PARAM_STRUCT)
>  #include "compat.h"
> @@ -998,6 +999,8 @@ void __init setup_arch(char **cmdline_p)
>  
>  	if (mdesc->init_early)
>  		mdesc->init_early();
> +
> +	runtime_patch_kernel();
>  }
>  
>  
> diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
> index 36ff15b..ea35ca0 100644
> --- a/arch/arm/kernel/vmlinux.lds.S
> +++ b/arch/arm/kernel/vmlinux.lds.S
> @@ -167,6 +167,16 @@ SECTIONS
>  		*(.pv_table)
>  		__pv_table_end = .;
>  	}
> +	.init.runtime_patch_table : {
> +		__runtime_patch_table_begin = .;
> +		*(.runtime.patch.table)
> +		__runtime_patch_table_end = .;
> +	}
> +	.init.runtime_patch_code : {
> +		__runtime_patch_code_begin = .;
> +		*(.runtime.patch.code)
> +		__runtime_patch_code_end = .;
> +	}
>  	.init.data : {
>  #ifndef CONFIG_XIP_KERNEL
>  		INIT_DATA
> -- 
> 1.7.9.5
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists