[RFC PATCH] arm64: compat: Implement misalignment fixups for multiword loads

Ard Biesheuvel ardb at kernel.org
Thu Jun 23 10:24:39 PDT 2022


The 32-bit ARM kernel implements fixups on behalf of user space when
using LDM/STM or LDRD/STRD instructions on addresses that are not 32-bit
aligned. This is not something that is supported by the architecture,
but was done anyway to increase compatibility with user space software,
which mostly targeted x86 at the time and did not care about aligned
accesses.

This feature is one of the remaining impediments to being able to switch
to 64-bit kernels on 64-bit capable hardware running 32-bit user space,
so let's implement it for the arm64 compat layer as well.

Note that the intent is to implement the exact same handling of
misaligned multi-word loads and stores as the 32-bit kernel does,
including what appears to be missing support for user space programs
that rely on SETEND to switch to a different byte order and back. Also,
like the 32-bit ARM version, we rely on the faulting address reported by
the CPU to infer the memory address, instead of decoding the instruction
fully to obtain this information.

This implementation is taken from the 32-bit ARM tree, with all pieces
removed that deal with instructions other than LDRD/STRD and LDM/STM, or
that deal with alignment exceptions taken in kernel mode.

Signed-off-by: Ard Biesheuvel <ardb at kernel.org>
---
 arch/arm64/Kconfig                   |   4 +
 arch/arm64/include/asm/exception.h   |   1 +
 arch/arm64/kernel/Makefile           |   1 +
 arch/arm64/kernel/compat_alignment.c | 388 ++++++++++++++++++++
 arch/arm64/mm/fault.c                |   3 +
 5 files changed, 397 insertions(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1652a9800ebe..401e4f8fa149 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1508,6 +1508,10 @@ config THUMB2_COMPAT_VDSO
 	  Compile the compat vDSO with '-mthumb -fomit-frame-pointer' if y,
 	  otherwise with '-marm'.
 
+config COMPAT_ALIGNMENT_FIXUPS
+	bool "Fix up misaligned multi-word loads and stores in user space"
+	default y
+
 menuconfig ARMV8_DEPRECATED
 	bool "Emulate deprecated/obsolete ARMv8 instructions"
 	depends on SYSCTL
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index d94aecff9690..e92ca08f754c 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -70,6 +70,7 @@ void do_sysinstr(unsigned long esr, struct pt_regs *regs);
 void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs);
 void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr);
 void do_cp15instr(unsigned long esr, struct pt_regs *regs);
+int do_compat_alignment_fixup(unsigned long addr, struct pt_regs *regs);
 void do_el0_svc(struct pt_regs *regs);
 void do_el0_svc_compat(struct pt_regs *regs);
 void do_ptrauth_fault(struct pt_regs *regs, unsigned long esr);
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index fa7981d0d917..58b472fa34fe 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -40,6 +40,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE
 obj-$(CONFIG_COMPAT)			+= sys32.o signal32.o			\
 					   sys_compat.o
 obj-$(CONFIG_COMPAT)			+= sigreturn32.o
+obj-$(CONFIG_COMPAT_ALIGNMENT_FIXUPS)	+= compat_alignment.o
 obj-$(CONFIG_KUSER_HELPERS)		+= kuser32.o
 obj-$(CONFIG_FUNCTION_TRACER)		+= ftrace.o entry-ftrace.o
 obj-$(CONFIG_MODULES)			+= module.o
diff --git a/arch/arm64/kernel/compat_alignment.c b/arch/arm64/kernel/compat_alignment.c
new file mode 100644
index 000000000000..1a904f1660cc
--- /dev/null
+++ b/arch/arm64/kernel/compat_alignment.c
@@ -0,0 +1,388 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// based on arch/arm/mm/alignment.c
+
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/uaccess.h>
+
+#include <asm/exception.h>
+#include <asm/ptrace.h>
+
+/*
+ * 32-bit misaligned trap handler (c) 1998 San Mehat (CCC) -July 1998
+ * /proc/sys/debug/alignment, modified and integrated into
+ * Linux 2.1 by Russell King
+ *
+ * Speed optimisations and better fault handling by Russell King.
+ *
+ * *** NOTE ***
+ * This code is not portable to processors with late data abort handling.
+ */
+#define CODING_BITS(i)	(i & 0x0e000000)
+
+#define LDST_P_BIT(i)	(i & (1 << 24))		/* Preindex		*/
+#define LDST_U_BIT(i)	(i & (1 << 23))		/* Add offset		*/
+#define LDST_W_BIT(i)	(i & (1 << 21))		/* Writeback		*/
+#define LDST_L_BIT(i)	(i & (1 << 20))		/* Load			*/
+
+#define LDST_P_EQ_U(i)	((((i) ^ ((i) >> 1)) & (1 << 23)) == 0)
+
+#define LDSTHD_I_BIT(i)	(i & (1 << 22))		/* double/half-word immed */
+
+#define RN_BITS(i)	((i >> 16) & 15)	/* Rn			*/
+#define RD_BITS(i)	((i >> 12) & 15)	/* Rd			*/
+#define RM_BITS(i)	(i & 15)		/* Rm			*/
+
+#define REGMASK_BITS(i)	(i & 0xffff)
+
+#define BAD_INSTR 	0xdeadc0de
+
+/* Thumb-2 32 bit format per ARMv7 DDI0406A A6.3, either f800h,e800h,f800h */
+#define IS_T32(hi16) \
+	(((hi16) & 0xe000) == 0xe000 && ((hi16) & 0x1800))
+
+union offset_union {
+	unsigned long un;
+	  signed long sn;
+};
+
+#define TYPE_ERROR	0
+#define TYPE_FAULT	1
+#define TYPE_LDST	2
+#define TYPE_DONE	3
+
+static void
+do_alignment_finish_ldst(unsigned long addr, u32 instr, struct pt_regs *regs,
+			 union offset_union offset)
+{
+	if (!LDST_U_BIT(instr))
+		offset.un = -offset.un;
+
+	if (!LDST_P_BIT(instr))
+		addr += offset.un;
+
+	if (!LDST_P_BIT(instr) || LDST_W_BIT(instr))
+		regs->regs[RN_BITS(instr)] = addr;
+}
+
+static int
+do_alignment_ldrdstrd(unsigned long addr, u32 instr, struct pt_regs *regs)
+{
+	unsigned int rd = RD_BITS(instr);
+	unsigned int rd2;
+	int load;
+
+	if ((instr & 0xfe000000) == 0xe8000000) {
+		/* ARMv7 Thumb-2 32-bit LDRD/STRD */
+		rd2 = (instr >> 8) & 0xf;
+		load = !!(LDST_L_BIT(instr));
+	} else if (((rd & 1) == 1) || (rd == 14)) {
+		return TYPE_ERROR;
+	} else {
+		load = ((instr & 0xf0) == 0xd0);
+		rd2 = rd + 1;
+	}
+
+	if (load) {
+		unsigned int val, val2;
+
+		if (get_user(val, (u32 __user *)addr) ||
+		    get_user(val2, (u32 __user *)(addr + 4)))
+			return TYPE_FAULT;
+		regs->regs[rd] = val;
+		regs->regs[rd2] = val2;
+	} else {
+		if (put_user(regs->regs[rd], (u32 __user *)addr) ||
+		    put_user(regs->regs[rd2], (u32 __user *)(addr + 4)))
+			return TYPE_FAULT;
+	}
+	return TYPE_LDST;
+}
+
+/*
+ * LDM/STM alignment handler.
+ *
+ * There are 4 variants of this instruction:
+ *
+ * B = rn pointer before instruction, A = rn pointer after instruction
+ *              ------ increasing address ----->
+ *	        |    | r0 | r1 | ... | rx |    |
+ * PU = 01             B                    A
+ * PU = 11        B                    A
+ * PU = 00        A                    B
+ * PU = 10             A                    B
+ */
+static int
+do_alignment_ldmstm(unsigned long addr, u32 instr, struct pt_regs *regs)
+{
+	unsigned int rd, rn, nr_regs, regbits;
+	unsigned long eaddr, newaddr;
+	unsigned int val;
+
+	/* count the number of registers in the mask to be transferred */
+	nr_regs = hweight16(REGMASK_BITS(instr)) * 4;
+
+	rn = RN_BITS(instr);
+	newaddr = eaddr = regs->regs[rn];
+
+	if (!LDST_U_BIT(instr))
+		nr_regs = -nr_regs;
+	newaddr += nr_regs;
+	if (!LDST_U_BIT(instr))
+		eaddr = newaddr;
+
+	if (LDST_P_EQ_U(instr))	/* U = P */
+		eaddr += 4;
+
+	for (regbits = REGMASK_BITS(instr), rd = 0; regbits;
+	     regbits >>= 1, rd += 1)
+		if (regbits & 1) {
+			if (LDST_L_BIT(instr)) {
+				if (get_user(val, (u32 __user *)eaddr))
+					return TYPE_FAULT;
+				if (rd < 15)
+					regs->regs[rd] = val;
+				else
+					regs->pc = val;
+			} else {
+				/*
+				 * The PC register has a bias of +8 in ARM mode
+				 * and +4 in Thumb mode. This means that a read
+				 * of the value of PC should account for this.
+				 * Since Thumb does not permit STM instructions
+				 * to refer to PC, just add 8 here.
+				 */
+				val = (rd < 15) ? regs->regs[rd] : regs->pc + 8;
+				if (put_user(val, (u32 __user *)eaddr))
+					return TYPE_FAULT;
+			}
+			eaddr += 4;
+		}
+
+	if (LDST_W_BIT(instr))
+		regs->regs[rn] = newaddr;
+	return TYPE_DONE;
+}
+
+/*
+ * Convert Thumb multi-word load/store instruction forms to equivalent ARM
+ * instructions so we can reuse ARM userland alignment fault fixups for Thumb.
+ *
+ * This implementation was initially based on the algorithm found in
+ * gdb/sim/arm/thumbemu.c. It is basically just a code reduction of same
+ * to convert only Thumb ld/st instruction forms to equivalent ARM forms.
+ *
+ * NOTES:
+ * 1. Comments below refer to ARM ARM DDI0100E Thumb Instruction sections.
+ * 2. If for some reason we're passed an non-ld/st Thumb instruction to
+ *    decode, we return 0xdeadc0de. This should never happen under normal
+ *    circumstances but if it does, we've got other problems to deal with
+ *    elsewhere and we obviously can't fix those problems here.
+ */
+
+static unsigned long thumb2arm(u16 tinstr)
+{
+	u32 L = (tinstr & (1<<11)) >> 11;
+
+	switch ((tinstr & 0xf800) >> 11) {
+	/* 6.6.1 Format 1: */
+	case 0xc000 >> 11:				/* 7.1.51 STMIA */
+	case 0xc800 >> 11:				/* 7.1.25 LDMIA */
+		{
+			u32 Rn = (tinstr & (7<<8)) >> 8;
+			u32 W = ((L<<Rn) & (tinstr&255)) ? 0 : 1<<21;
+
+			return 0xe8800000 | W | (L<<20) | (Rn<<16) |
+				(tinstr&255);
+		}
+
+	/* 6.6.1 Format 2: */
+	case 0xb000 >> 11:				/* 7.1.48 PUSH */
+	case 0xb800 >> 11:				/* 7.1.47 POP */
+		if ((tinstr & (3 << 9)) == 0x0400) {
+			static const u32 subset[4] = {
+				0xe92d0000,	/* STMDB sp!,{registers} */
+				0xe92d4000,	/* STMDB sp!,{registers,lr} */
+				0xe8bd0000,	/* LDMIA sp!,{registers} */
+				0xe8bd8000	/* LDMIA sp!,{registers,pc} */
+			};
+			return subset[(L<<1) | ((tinstr & (1<<8)) >> 8)] |
+			    (tinstr & 255);		/* register_list */
+		}
+		fallthrough;	/* for illegal instruction case */
+
+	default:
+		return BAD_INSTR;
+	}
+}
+
+/*
+ * Convert Thumb-2 32 bit LDM, STM, LDRD, STRD to equivalent instruction
+ * handlable by ARM alignment handler, also find the corresponding handler,
+ * so that we can reuse ARM userland alignment fault fixups for Thumb.
+ *
+ * @pinstr: original Thumb-2 instruction; returns new handlable instruction
+ * @regs: register context.
+ * @poffset: return offset from faulted addr for later writeback
+ *
+ * NOTES:
+ * 1. Comments below refer to ARMv7 DDI0406A Thumb Instruction sections.
+ * 2. Register name Rt from ARMv7 is same as Rd from ARMv6 (Rd is Rt)
+ */
+static void *
+do_alignment_t32_to_handler(u32 *pinstr, struct pt_regs *regs,
+			    union offset_union *poffset)
+{
+	u32 instr = *pinstr;
+	u16 tinst1 = (instr >> 16) & 0xffff;
+	u16 tinst2 = instr & 0xffff;
+
+	switch (tinst1 & 0xffe0) {
+	/* A6.3.5 Load/Store multiple */
+	case 0xe880:		/* STM/STMIA/STMEA,LDM/LDMIA, PUSH/POP T2 */
+	case 0xe8a0:		/* ...above writeback version */
+	case 0xe900:		/* STMDB/STMFD, LDMDB/LDMEA */
+	case 0xe920:		/* ...above writeback version */
+		/* no need offset decision since handler calculates it */
+		return do_alignment_ldmstm;
+
+	case 0xf840:		/* POP/PUSH T3 (single register) */
+		if (RN_BITS(instr) == 13 && (tinst2 & 0x09ff) == 0x0904) {
+			u32 L = !!(LDST_L_BIT(instr));
+			const u32 subset[2] = {
+				0xe92d0000,	/* STMDB sp!,{registers} */
+				0xe8bd0000,	/* LDMIA sp!,{registers} */
+			};
+			*pinstr = subset[L] | (1<<RD_BITS(instr));
+			return do_alignment_ldmstm;
+		}
+		/* Else fall through for illegal instruction case */
+		break;
+
+	/* A6.3.6 Load/store double, STRD/LDRD(immed, lit, reg) */
+	case 0xe860:
+	case 0xe960:
+	case 0xe8e0:
+	case 0xe9e0:
+		poffset->un = (tinst2 & 0xff) << 2;
+		fallthrough;
+
+	case 0xe940:
+	case 0xe9c0:
+		return do_alignment_ldrdstrd;
+
+	/*
+	 * No need to handle load/store instructions up to word size
+	 * since ARMv6 and later CPUs can perform unaligned accesses.
+	 */
+	default:
+		break;
+	}
+	return NULL;
+}
+
+static int alignment_get_arm(struct pt_regs *regs, u32 __user *ip, u32 *inst)
+{
+	u32 instr = 0;
+	int fault;
+
+	fault = get_user(instr, ip);
+	if (fault)
+		return fault;
+
+	*inst = __le32_to_cpu(instr);
+	return 0;
+}
+
+static int alignment_get_thumb(struct pt_regs *regs, u16 __user *ip, u16 *inst)
+{
+	u16 instr = 0;
+	int fault;
+
+	fault = get_user(instr, ip);
+	if (fault)
+		return fault;
+
+	*inst = __le16_to_cpu(instr);
+	return 0;
+}
+
+int do_compat_alignment_fixup(unsigned long addr, struct pt_regs *regs)
+{
+	union offset_union offset;
+	unsigned long instrptr;
+	int (*handler)(unsigned long addr, u32 instr, struct pt_regs *regs);
+	unsigned int type;
+	u32 instr = 0;
+	u16 tinstr = 0;
+	int isize = 4;
+	int thumb2_32b = 0;
+	int fault;
+
+	instrptr = instruction_pointer(regs);
+
+	if (compat_thumb_mode(regs)) {
+		u16 __user *ptr = (u16 __user *)(instrptr & ~1);
+
+		fault = alignment_get_thumb(regs, ptr, &tinstr);
+		if (!fault) {
+			if (IS_T32(tinstr)) {
+				/* Thumb-2 32-bit */
+				u16 tinst2;
+				fault = alignment_get_thumb(regs, ptr + 1, &tinst2);
+				instr = ((u32)tinstr << 16) | tinst2;
+				thumb2_32b = 1;
+			} else {
+				isize = 2;
+				instr = thumb2arm(tinstr);
+			}
+		}
+	} else {
+		fault = alignment_get_arm(regs, (u32 __user *)instrptr, &instr);
+	}
+
+	if (fault)
+		return 1;
+
+	switch (CODING_BITS(instr)) {
+	case 0x00000000:	/* 3.13.4 load/store instruction extensions */
+		if (LDSTHD_I_BIT(instr))
+			offset.un = (instr & 0xf00) >> 4 | (instr & 15);
+		else
+			offset.un = regs->regs[RM_BITS(instr)];
+
+		if ((instr & 0x001000f0) == 0x000000d0 || /* LDRD */
+		    (instr & 0x001000f0) == 0x000000f0)   /* STRD */
+			handler = do_alignment_ldrdstrd;
+		else
+			return 1;
+		break;
+
+	case 0x08000000:	/* ldm or stm, or thumb-2 32bit instruction */
+		if (thumb2_32b) {
+			offset.un = 0;
+			handler = do_alignment_t32_to_handler(&instr, regs, &offset);
+		} else {
+			offset.un = 0;
+			handler = do_alignment_ldmstm;
+		}
+		break;
+
+	default:
+		return 1;
+	}
+
+	type = handler(addr, instr, regs);
+
+	if (type == TYPE_ERROR || type == TYPE_FAULT)
+		return 1;
+
+	regs->pc += isize;	// advance PC over the emulated instruction
+
+	if (type == TYPE_LDST)
+		do_alignment_finish_ldst(addr, instr, regs, offset);
+
+	return 0;
+}
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index c5e11768e5c1..b25119b4beca 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -687,6 +687,9 @@ static int __kprobes do_translation_fault(unsigned long far,
 static int do_alignment_fault(unsigned long far, unsigned long esr,
 			      struct pt_regs *regs)
 {
+	if (IS_ENABLED(CONFIG_COMPAT_ALIGNMENT_FIXUPS) &&
+	    compat_user_mode(regs))
+		return do_compat_alignment_fixup(far, regs);
 	do_bad_area(far, esr, regs);
 	return 0;
 }
-- 
2.35.1




More information about the linux-arm-kernel mailing list